diff --git a/setup.py b/setup.py
index c5263a3d..7d2ca225 100755
--- a/setup.py
+++ b/setup.py
@@ -1,74 +1,76 @@
#!/usr/bin/env python3
# Copyright (C) 2015-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from io import open
from os import path
from setuptools import find_packages, setup
here = path.abspath(path.dirname(__file__))
# Get the long description from the README file
with open(path.join(here, "README.md"), encoding="utf-8") as f:
long_description = f.read()
def parse_requirements(name=None):
if name:
reqf = "requirements-%s.txt" % name
else:
reqf = "requirements.txt"
requirements = []
if not path.exists(reqf):
return requirements
with open(reqf) as f:
for line in f.readlines():
line = line.strip()
if not line or line.startswith("#"):
continue
requirements.append(line)
return requirements
setup(
name="swh.storage",
description="Software Heritage storage manager",
long_description=long_description,
long_description_content_type="text/markdown",
python_requires=">=3.7",
author="Software Heritage developers",
author_email="swh-devel@inria.fr",
url="https://forge.softwareheritage.org/diffusion/DSTO/",
setup_requires=["setuptools-scm"],
packages=find_packages(),
use_scm_version=True,
- scripts=["bin/swh-storage-add-dir",],
+ scripts=[
+ "bin/swh-storage-add-dir",
+ ],
entry_points="""
[swh.cli.subcommands]
storage=swh.storage.cli
""",
install_requires=parse_requirements() + parse_requirements("swh"),
extras_require={
"testing": (parse_requirements("test") + parse_requirements("swh-journal")),
"journal": parse_requirements("swh-journal"),
},
include_package_data=True,
classifiers=[
"Programming Language :: Python :: 3",
"Intended Audience :: Developers",
"License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
"Operating System :: OS Independent",
"Development Status :: 5 - Production/Stable",
],
project_urls={
"Bug Reports": "https://forge.softwareheritage.org/maniphest",
"Funding": "https://www.softwareheritage.org/donate",
"Source": "https://forge.softwareheritage.org/source/swh-storage",
"Documentation": "https://docs.softwareheritage.org/devel/swh-storage/",
},
)
diff --git a/swh/storage/algos/diff.py b/swh/storage/algos/diff.py
index 4a45dbce..4278fcf0 100644
--- a/swh/storage/algos/diff.py
+++ b/swh/storage/algos/diff.py
@@ -1,416 +1,416 @@
# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# Utility module to efficiently compute the list of changed files
# between two directory trees.
# The implementation is inspired from the work of Alberto Cortés
# for the go-git project. For more details, you can refer to:
# - this blog post: https://blog.sourced.tech/post/difftree/
# - the reference implementation in go:
# https://github.com/src-d/go-git/tree/master/utils/merkletrie
import collections
from typing import Any, Dict
from swh.model.model import Directory
from swh.storage.interface import StorageInterface
from .dir_iterators import DirectoryIterator, DoubleDirectoryIterator, Remaining
# get the hash identifier for an empty directory
_empty_dir_hash = Directory(entries=()).id
def _get_rev(storage: StorageInterface, rev_id: bytes) -> Dict[str, Any]:
"""
Return revision data from swh storage.
"""
revision = storage.revision_get([rev_id])[0]
assert revision is not None
return revision.to_dict()
class _RevisionChangesList(object):
"""
Helper class to track the changes between two
revision directories.
"""
def __init__(self, storage, track_renaming):
"""
Args:
storage: instance of swh storage
track_renaming (bool): whether to track or not files renaming
"""
self.storage = storage
self.track_renaming = track_renaming
self.result = []
# dicts used to track file renaming based on hash value
# we use a list instead of a single entry to handle the corner
# case when a repository contains multiple instance of
# the same file in different directories and a commit
# renames all of them
self.inserted_hash_idx = collections.defaultdict(list)
self.deleted_hash_idx = collections.defaultdict(list)
def add_insert(self, it_to):
"""
Add a file insertion in the to directory.
Args:
it_to (swh.storage.algos.dir_iterators.DirectoryIterator):
iterator on the to directory
"""
to_hash = it_to.current_hash()
# if the current file hash has been previously marked as deleted,
# the file has been renamed
if self.track_renaming and self.deleted_hash_idx[to_hash]:
# pop the delete change index in the same order it was inserted
change = self.result[self.deleted_hash_idx[to_hash].pop(0)]
# change the delete change as a rename one
change["type"] = "rename"
change["to"] = it_to.current()
change["to_path"] = it_to.current_path()
else:
# add the insert change in the list
self.result.append(
{
"type": "insert",
"from": None,
"from_path": None,
"to": it_to.current(),
"to_path": it_to.current_path(),
}
)
# if rename tracking is activated, add the change index in
# the inserted_hash_idx dict
if self.track_renaming:
self.inserted_hash_idx[to_hash].append(len(self.result) - 1)
def add_delete(self, it_from):
"""
Add a file deletion in the from directory.
Args:
it_from (swh.storage.algos.dir_iterators.DirectoryIterator):
iterator on the from directory
"""
from_hash = it_from.current_hash()
# if the current file has been previously marked as inserted,
# the file has been renamed
if self.track_renaming and self.inserted_hash_idx[from_hash]:
# pop the insert change index in the same order it was inserted
change = self.result[self.inserted_hash_idx[from_hash].pop(0)]
# change the insert change as a rename one
change["type"] = "rename"
change["from"] = it_from.current()
change["from_path"] = it_from.current_path()
else:
# add the delete change in the list
self.result.append(
{
"type": "delete",
"from": it_from.current(),
"from_path": it_from.current_path(),
"to": None,
"to_path": None,
}
)
# if rename tracking is activated, add the change index in
# the deleted_hash_idx dict
if self.track_renaming:
self.deleted_hash_idx[from_hash].append(len(self.result) - 1)
def add_modify(self, it_from, it_to):
"""
Add a file modification in the to directory.
Args:
it_from (swh.storage.algos.dir_iterators.DirectoryIterator):
iterator on the from directory
it_to (swh.storage.algos.dir_iterators.DirectoryIterator):
iterator on the to directory
"""
self.result.append(
{
"type": "modify",
"from": it_from.current(),
"from_path": it_from.current_path(),
"to": it_to.current(),
"to_path": it_to.current_path(),
}
)
def add_recursive(self, it, insert):
"""
Recursively add changes from a directory.
Args:
it (swh.storage.algos.dir_iterators.DirectoryIterator):
iterator on a directory
insert (bool): the type of changes to add (insertion
or deletion)
"""
# current iterated element is a regular file,
# simply add adequate change in the list
if not it.current_is_dir():
if insert:
self.add_insert(it)
else:
self.add_delete(it)
return
# current iterated element is a directory,
dir_id = it.current_hash()
# handle empty dir insertion/deletion as the swh model allow
# to have such object compared to git
if dir_id == _empty_dir_hash:
if insert:
self.add_insert(it)
else:
self.add_delete(it)
# iterate on files reachable from it and add
# adequate changes in the list
else:
sub_it = DirectoryIterator(self.storage, dir_id, it.current_path() + b"/")
sub_it_current = sub_it.step()
while sub_it_current:
if not sub_it.current_is_dir():
if insert:
self.add_insert(sub_it)
else:
self.add_delete(sub_it)
sub_it_current = sub_it.step()
def add_recursive_insert(self, it_to):
"""
Recursively add files insertion from a to directory.
Args:
it_to (swh.storage.algos.dir_iterators.DirectoryIterator):
iterator on a to directory
"""
self.add_recursive(it_to, True)
def add_recursive_delete(self, it_from):
"""
Recursively add files deletion from a from directory.
Args:
it_from (swh.storage.algos.dir_iterators.DirectoryIterator):
iterator on a from directory
"""
self.add_recursive(it_from, False)
def _diff_elts_same_name(changes, it):
- """"
+ """ "
Compare two directory entries with the same name and add adequate
changes if any.
Args:
changes (_RevisionChangesList): the list of changes between
two revisions
it (swh.storage.algos.dir_iterators.DoubleDirectoryIterator):
the iterator traversing two revision directories at the same time
"""
# compare the two current directory elements of the iterator
status = it.compare()
# elements have same hash and same permissions:
# no changes to add and call next on the two iterators
if status["same_hash"] and status["same_perms"]:
it.next_both()
# elements are regular files and have been modified:
# insert the modification change in the list and
# call next on the two iterators
elif status["both_are_files"]:
changes.add_modify(it.it_from, it.it_to)
it.next_both()
# one element is a regular file, the other a directory:
# recursively add delete/insert changes and call next
# on the two iterators
elif status["file_and_dir"]:
changes.add_recursive_delete(it.it_from)
changes.add_recursive_insert(it.it_to)
it.next_both()
# both elements are directories:
elif status["both_are_dirs"]:
# from directory is empty:
# recursively add insert changes in the to directory
# and call next on the two iterators
if status["from_is_empty_dir"]:
changes.add_recursive_insert(it.it_to)
it.next_both()
# to directory is empty:
# recursively add delete changes in the from directory
# and call next on the two iterators
elif status["to_is_empty_dir"]:
changes.add_recursive_delete(it.it_from)
it.next_both()
# both directories are not empty:
# call step on the two iterators to descend further in
# the directory trees.
elif not status["from_is_empty_dir"] and not status["to_is_empty_dir"]:
it.step_both()
def _compare_paths(path1, path2):
"""
Compare paths in lexicographic depth-first order.
For instance, it returns:
- "a" < "b"
- "b/c/d" < "b"
- "c/foo.txt" < "c.txt"
"""
path1_parts = path1.split(b"/")
path2_parts = path2.split(b"/")
i = 0
while True:
if len(path1_parts) == len(path2_parts) and i == len(path1_parts):
return 0
elif len(path2_parts) == i:
return 1
elif len(path1_parts) == i:
return -1
else:
if path2_parts[i] > path1_parts[i]:
return -1
elif path2_parts[i] < path1_parts[i]:
return 1
i = i + 1
def _diff_elts(changes, it):
"""
Compare two directory entries.
Args:
changes (_RevisionChangesList): the list of changes between
two revisions
it (swh.storage.algos.dir_iterators.DoubleDirectoryIterator):
the iterator traversing two revision directories at the same time
"""
# compare current to and from path in depth-first lexicographic order
c = _compare_paths(it.it_from.current_path(), it.it_to.current_path())
# current from path is lower than the current to path:
# the from path has been deleted
if c < 0:
changes.add_recursive_delete(it.it_from)
it.next_from()
# current from path is greater than the current to path:
# the to path has been inserted
elif c > 0:
changes.add_recursive_insert(it.it_to)
it.next_to()
# paths are the same and need more processing
else:
_diff_elts_same_name(changes, it)
def diff_directories(storage, from_dir, to_dir, track_renaming=False):
"""
Compute the differential between two directories, i.e. the list of
file changes (insertion / deletion / modification / renaming)
between them.
Args:
storage (swh.storage.interface.StorageInterface): instance of a swh
storage (either local or remote, for optimal performance
the use of a local storage is recommended)
from_dir (bytes): the swh identifier of the directory to compare from
to_dir (bytes): the swh identifier of the directory to compare to
track_renaming (bool): whether or not to track files renaming
Returns:
list: A list of dict representing the changes between the two
revisions. Each dict contains the following entries:
- *type*: a string describing the type of change
('insert' / 'delete' / 'modify' / 'rename')
- *from*: a dict containing the directory entry metadata in the
from revision (None in case of an insertion)
- *from_path*: bytes string corresponding to the absolute path
of the from revision entry (None in case of an insertion)
- *to*: a dict containing the directory entry metadata in the
to revision (None in case of a deletion)
- *to_path*: bytes string corresponding to the absolute path
of the to revision entry (None in case of a deletion)
The returned list is sorted in lexicographic depth-first order
according to the value of the *to_path* field.
"""
changes = _RevisionChangesList(storage, track_renaming)
it = DoubleDirectoryIterator(storage, from_dir, to_dir)
while True:
r = it.remaining()
if r == Remaining.NoMoreFiles:
break
elif r == Remaining.OnlyFromFilesRemain:
changes.add_recursive_delete(it.it_from)
it.next_from()
elif r == Remaining.OnlyToFilesRemain:
changes.add_recursive_insert(it.it_to)
it.next_to()
else:
_diff_elts(changes, it)
return changes.result
def diff_revisions(storage, from_rev, to_rev, track_renaming=False):
"""
Compute the differential between two revisions,
i.e. the list of file changes between the two associated directories.
Args:
storage (swh.storage.interface.StorageInterface): instance of a swh
storage (either local or remote, for optimal performance
the use of a local storage is recommended)
from_rev (bytes): the identifier of the revision to compare from
to_rev (bytes): the identifier of the revision to compare to
track_renaming (bool): whether or not to track files renaming
Returns:
list: A list of dict describing the introduced file changes
(see :func:`swh.storage.algos.diff.diff_directories`).
"""
from_dir = None
if from_rev:
from_dir = _get_rev(storage, from_rev)["directory"]
to_dir = _get_rev(storage, to_rev)["directory"]
return diff_directories(storage, from_dir, to_dir, track_renaming)
def diff_revision(storage, revision, track_renaming=False):
"""
Computes the differential between a revision and its first parent.
If the revision has no parents, the directory to compare from
is considered as empty.
In other words, it computes the file changes introduced in a
specific revision.
Args:
storage (swh.storage.interface.StorageInterface): instance of a swh
storage (either local or remote, for optimal performance
the use of a local storage is recommended)
revision (bytes): the identifier of the revision from which to
compute the introduced changes.
track_renaming (bool): whether or not to track files renaming
Returns:
list: A list of dict describing the introduced file changes
(see :func:`swh.storage.algos.diff.diff_directories`).
"""
rev_data = _get_rev(storage, revision)
parent = None
if rev_data["parents"]:
parent = rev_data["parents"][0]
return diff_revisions(storage, parent, revision, track_renaming)
diff --git a/swh/storage/algos/dir_iterators.py b/swh/storage/algos/dir_iterators.py
index e8a03dc0..6291f833 100644
--- a/swh/storage/algos/dir_iterators.py
+++ b/swh/storage/algos/dir_iterators.py
@@ -1,374 +1,374 @@
# Copyright (C) 2018 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# Utility module to iterate on directory trees.
# The implementation is inspired from the work of Alberto Cortés
# for the go-git project. For more details, you can refer to:
# - this blog post: https://blog.sourced.tech/post/difftree/
# - the reference implementation in go:
# https://github.com/src-d/go-git/tree/master/utils/merkletrie
from enum import Enum
from swh.model.model import Directory
# get the hash identifier for an empty directory
_empty_dir_hash = Directory(entries=()).id
def _get_dir(storage, dir_id):
"""
Return directory data from swh storage.
"""
return storage.directory_ls(dir_id) if dir_id else []
class DirectoryIterator(object):
"""
Helper class used to iterate on a directory tree in a depth-first search
way with some additional features:
- sibling nodes are iterated in lexicographic order by name
- it is possible to skip the visit of sub-directories nodes
for efficiency reasons when comparing two trees (no need to
go deeper if two directories have the same hash)
"""
def __init__(self, storage, dir_id, base_path=b""):
"""
- Args:
- storage (swh.storage.interface.StorageInterface): instance of
- swh storage (either local or remote)
- dir_id (bytes): identifier of a root directory
- base_path (bytes): optional base path used when traversing
- a sub-directory
+ Args:
+ storage (swh.storage.interface.StorageInterface): instance of
+ swh storage (either local or remote)
+ dir_id (bytes): identifier of a root directory
+ base_path (bytes): optional base path used when traversing
+ a sub-directory
"""
self.storage = storage
self.root_dir_id = dir_id
self.base_path = base_path
self.restart()
def restart(self):
"""
Restart the iteration at the beginning.
"""
# stack of frames representing currently visited directories:
# the root directory is at the bottom while the current one
# is at the top
self.frames = []
self._push_dir_frame(self.root_dir_id)
self.has_started = False
def _push_dir_frame(self, dir_id):
"""
Visit a sub-directory by pushing a new frame to the stack.
Each frame is itself a stack of directory entries.
Args:
dir_id (bytes): identifier of a root directory
"""
# get directory entries
dir_data = _get_dir(self.storage, dir_id)
# sort them in lexicographical order and reverse the ordering
# in order to unstack the "smallest" entry each time the
# iterator advances
dir_data = sorted(dir_data, key=lambda e: e["name"], reverse=True)
# push the directory frame to the main stack
self.frames.append(dir_data)
def top(self):
"""
Returns:
list: The top frame of the main directories stack
"""
if not self.frames:
return None
return self.frames[-1]
def current(self):
"""
Returns:
dict: The current visited directory entry, i.e. the
top element from the top frame
"""
top_frame = self.top()
if not top_frame:
return None
return top_frame[-1]
def current_hash(self):
"""
Returns:
bytes: The hash value of the currently visited directory
entry
"""
return self.current()["target"]
def current_perms(self):
"""
Returns:
int: The permissions value of the currently visited directory
entry
"""
return self.current()["perms"]
def current_path(self):
"""
Returns:
str: The absolute path from the root directory of
the currently visited directory entry
"""
top_frame = self.top()
if not top_frame:
return None
path = []
for frame in self.frames:
path.append(frame[-1]["name"])
return self.base_path + b"/".join(path)
def current_is_dir(self):
"""
Returns:
bool: If the currently visited directory entry is
a directory
"""
return self.current()["type"] == "dir"
def _advance(self, descend):
"""
Advance in the tree iteration.
Args:
descend (bool): whether or not to push a new frame
if the currently visited element is a sub-directory
Returns:
dict: The description of the newly visited directory entry
"""
current = self.current()
if not self.has_started or not current:
self.has_started = True
return current
if descend and self.current_is_dir() and current["target"] != _empty_dir_hash:
self._push_dir_frame(current["target"])
else:
self.drop()
return self.current()
def next(self):
"""
Advance the tree iteration by dropping the current visited
directory entry from the top frame. If the top frame ends up empty,
the operation is recursively applied to remove all empty frames
as the tree is climbed up towards its root.
Returns:
dict: The description of the newly visited directory entry
"""
return self._advance(False)
def step(self):
"""
Advance the tree iteration like the next operation with the
difference that if the current visited element is a sub-directory
a new frame representing its content is pushed to the main stack.
Returns:
dict: The description of the newly visited directory entry
"""
return self._advance(True)
def drop(self):
"""
Drop the current visited element from the top frame.
If the frame ends up empty, the operation is recursively
applied.
"""
frame = self.top()
if not frame:
return
frame.pop()
if not frame:
self.frames.pop()
self.drop()
def __next__(self):
entry = self.step()
if not entry:
raise StopIteration
entry["path"] = self.current_path()
return entry
def __iter__(self):
return DirectoryIterator(self.storage, self.root_dir_id, self.base_path)
def dir_iterator(storage, dir_id):
"""
Return an iterator for recursively visiting a directory and
its sub-directories. The associated paths are visited in
lexicographic depth-first search order.
Args:
storage (swh.storage.Storage): an instance of a swh storage
dir_id (bytes): a directory identifier
Returns:
swh.storage.algos.dir_iterators.DirectoryIterator: an iterator
returning a dict at each iteration step describing a directory
entry. A 'path' field is added in that dict to store the
absolute path of the entry.
"""
return DirectoryIterator(storage, dir_id)
class Remaining(Enum):
"""
Enum to represent the current state when iterating
on both directory trees at the same time.
"""
NoMoreFiles = 0
OnlyToFilesRemain = 1
OnlyFromFilesRemain = 2
BothHaveFiles = 3
class DoubleDirectoryIterator(object):
"""
Helper class to traverse two directory trees at the same
time and compare their contents to detect changes between them.
"""
def __init__(self, storage, dir_from, dir_to):
"""
Args:
storage: instance of swh storage
dir_from (bytes): hash identifier of the from directory
dir_to (bytes): hash identifier of the to directory
"""
self.storage = storage
self.dir_from = dir_from
self.dir_to = dir_to
self.restart()
def restart(self):
"""
Restart the double iteration at the beginning.
"""
# initialize custom dfs iterators for the two directories
self.it_from = DirectoryIterator(self.storage, self.dir_from)
self.it_to = DirectoryIterator(self.storage, self.dir_to)
# grab the first element of each iterator
self.it_from.next()
self.it_to.next()
def next_from(self):
"""
Apply the next operation on the from iterator.
"""
self.it_from.next()
def next_to(self):
"""
Apply the next operation on the to iterator.
"""
self.it_to.next()
def next_both(self):
"""
Apply the next operation on both iterators.
"""
self.next_from()
self.next_to()
def step_from(self):
"""
Apply the step operation on the from iterator.
"""
self.it_from.step()
def step_to(self):
"""
Apply the step operation on the from iterator.
"""
self.it_to.step()
def step_both(self):
"""
Apply the step operation on the both iterators.
"""
self.step_from()
self.step_to()
def remaining(self):
"""
Returns:
Remaining: the current state of the double iteration
"""
from_current = self.it_from.current()
to_current = self.it_to.current()
# no more files to iterate in both iterators
if not from_current and not to_current:
return Remaining.NoMoreFiles
# still some files to iterate in the to iterator
elif not from_current and to_current:
return Remaining.OnlyToFilesRemain
# still some files to iterate in the from iterator
elif from_current and not to_current:
return Remaining.OnlyFromFilesRemain
# still files to iterate in the both iterators
else:
return Remaining.BothHaveFiles
def compare(self):
"""
Compare the current iterated directory entries in both iterators
and return the comparison status.
Returns:
dict: The status of the comparison with the following bool values:
* *same_hash*: indicates if the two entries have the same hash
* *same_perms*: indicates if the two entries have the same
permissions
* *both_are_dirs*: indicates if the two entries are directories
* *both_are_files*: indicates if the two entries are regular
files
* *file_and_dir*: indicates if one of the entry is a directory
and the other a regular file
* *from_is_empty_dir*: indicates if the from entry is the
empty directory
* *from_is_empty_dir*: indicates if the to entry is the
empty directory
"""
from_current_hash = self.it_from.current_hash()
to_current_hash = self.it_to.current_hash()
from_current_perms = self.it_from.current_perms()
to_current_perms = self.it_to.current_perms()
from_is_dir = self.it_from.current_is_dir()
to_is_dir = self.it_to.current_is_dir()
status = {}
# compare hash
status["same_hash"] = from_current_hash == to_current_hash
# compare permissions
status["same_perms"] = from_current_perms == to_current_perms
# check if both elements are directories
status["both_are_dirs"] = from_is_dir and to_is_dir
# check if both elements are regular files
status["both_are_files"] = not from_is_dir and not to_is_dir
# check if one element is a directory, the other a regular file
status["file_and_dir"] = (
not status["both_are_dirs"] and not status["both_are_files"]
)
# check if the from element is the empty directory
status["from_is_empty_dir"] = (
from_is_dir and from_current_hash == _empty_dir_hash
)
# check if the to element is the empty directory
status["to_is_empty_dir"] = to_is_dir and to_current_hash == _empty_dir_hash
return status
diff --git a/swh/storage/algos/origin.py b/swh/storage/algos/origin.py
index 9a9d98b6..0ec69b2f 100644
--- a/swh/storage/algos/origin.py
+++ b/swh/storage/algos/origin.py
@@ -1,95 +1,94 @@
# Copyright (C) 2019-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from typing import Iterator, List, Optional
from swh.core.api.classes import stream_results
from swh.model.model import Origin, OriginVisit, OriginVisitStatus
from swh.storage.interface import ListOrder, StorageInterface
-def iter_origins(storage: StorageInterface, limit: int = 10000,) -> Iterator[Origin]:
+def iter_origins(
+ storage: StorageInterface,
+ limit: int = 10000,
+) -> Iterator[Origin]:
"""Iterates over origins in the storage.
Args:
storage: the storage object used for queries.
limit: maximum number of origins per page
Yields:
origin model objects from the storage in page of `limit` origins
"""
yield from stream_results(storage.origin_list, limit=limit)
def origin_get_latest_visit_status(
storage: StorageInterface,
origin_url: str,
type: Optional[str] = None,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
) -> Optional[OriginVisitStatus]:
"""Get the latest origin visit (and status) of an origin. Optionally, a combination of
criteria can be provided, origin type, allowed statuses or if a visit has a
snapshot.
If no visit matching the criteria is found, returns None. Otherwise, returns a tuple
of origin visit, origin visit status.
Args:
storage: A storage backend
origin: origin URL
type: Optional visit type to filter on (e.g git, tar, dsc, svn,
hg, npm, pypi, ...)
allowed_statuses: list of visit statuses considered
to find the latest visit. For instance,
``allowed_statuses=['full']`` will only consider visits that
have successfully run to completion.
require_snapshot: If True, only a visit with a snapshot
will be returned.
Returns:
a tuple of (visit, visit_status) model object if the visit *and* the visit
status exist (and match the search criteria), None otherwise.
"""
visit = storage.origin_visit_get_latest(
origin_url,
type=type,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
)
result: Optional[OriginVisitStatus] = None
if visit:
assert visit.visit is not None
visit_status = storage.origin_visit_status_get_latest(
origin_url,
visit.visit,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
)
if visit_status:
result = visit_status
return result
def iter_origin_visits(
storage: StorageInterface, origin: str, order: ListOrder = ListOrder.ASC
) -> Iterator[OriginVisit]:
- """Iter over origin visits from an origin
-
- """
+ """Iter over origin visits from an origin"""
yield from stream_results(storage.origin_visit_get, origin, order=order)
def iter_origin_visit_statuses(
storage: StorageInterface, origin: str, visit: int, order: ListOrder = ListOrder.ASC
) -> Iterator[OriginVisitStatus]:
- """Iter over origin visit status from an origin visit
-
- """
+ """Iter over origin visit status from an origin visit"""
yield from stream_results(
storage.origin_visit_status_get, origin, visit, order=order
)
diff --git a/swh/storage/algos/snapshot.py b/swh/storage/algos/snapshot.py
index 79803c27..cfa4ae5c 100644
--- a/swh/storage/algos/snapshot.py
+++ b/swh/storage/algos/snapshot.py
@@ -1,210 +1,213 @@
# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from typing import Iterator, List, Optional, Tuple
from swh.model.hashutil import hash_to_hex
from swh.model.model import (
OriginVisit,
OriginVisitStatus,
Sha1Git,
Snapshot,
SnapshotBranch,
TargetType,
)
from swh.storage.algos.origin import (
iter_origin_visit_statuses,
iter_origin_visits,
origin_get_latest_visit_status,
)
from swh.storage.interface import ListOrder, StorageInterface
def snapshot_get_all_branches(
storage: StorageInterface, snapshot_id: Sha1Git
) -> Optional[Snapshot]:
"""Get all the branches for a given snapshot
Args:
storage (swh.storage.interface.StorageInterface): the storage instance
snapshot_id (bytes): the snapshot's identifier
Returns:
dict: a dict with two keys:
* **id**: identifier of the snapshot
* **branches**: a dict of branches contained in the snapshot
whose keys are the branches' names.
"""
ret = storage.snapshot_get_branches(snapshot_id)
if not ret:
return None
next_branch = ret["next_branch"]
while next_branch:
data = storage.snapshot_get_branches(snapshot_id, branches_from=next_branch)
assert data, f"Snapshot {hash_to_hex(snapshot_id)} ceased to exist"
ret["branches"].update(data["branches"])
next_branch = data["next_branch"]
return Snapshot(id=ret["id"], branches=ret["branches"])
def snapshot_get_latest(
storage: StorageInterface,
origin: str,
allowed_statuses: Optional[List[str]] = None,
branches_count: Optional[int] = None,
) -> Optional[Snapshot]:
"""Get the latest snapshot for the given origin, optionally only from visits that have
one of the given allowed_statuses.
The branches of the snapshot are iterated in the lexicographical
order of their names.
Args:
storage: Storage instance
origin: the origin's URL
allowed_statuses: list of visit statuses considered
to find the latest snapshot for the visit. For instance,
``allowed_statuses=['full']`` will only consider visits that
have successfully run to completion.
branches_count: Optional parameter to retrieve snapshot with all branches
(default behavior when None) or not. If set to positive number, the snapshot
will be partial with only that number of branches.
Raises:
ValueError if branches_count is not a positive value
Returns:
The snapshot object if one is found matching the criteria or None.
"""
visit_status = origin_get_latest_visit_status(
- storage, origin, allowed_statuses=allowed_statuses, require_snapshot=True,
+ storage,
+ origin,
+ allowed_statuses=allowed_statuses,
+ require_snapshot=True,
)
if not visit_status:
return None
snapshot_id = visit_status.snapshot
if not snapshot_id:
return None
if branches_count: # partial snapshot
if not isinstance(branches_count, int) or branches_count <= 0:
raise ValueError(
"Parameter branches_count must be a positive integer. "
f"Current value is {branches_count}"
)
snapshot = storage.snapshot_get_branches(
snapshot_id, branches_count=branches_count
)
if snapshot is None:
return None
return Snapshot(id=snapshot["id"], branches=snapshot["branches"])
else:
return snapshot_get_all_branches(storage, snapshot_id)
def snapshot_id_get_from_revision(
storage: StorageInterface, origin: str, revision_id: bytes
) -> Optional[bytes]:
"""Retrieve the most recent snapshot id targeting the revision_id for the given origin.
*Warning* This is a potentially highly costly operation
Returns
The snapshot id if found. None otherwise.
"""
res = visits_and_snapshots_get_from_revision(storage, origin, revision_id)
# they are sorted by descending date, so we just need to return the first one,
# if any.
for (visit, status, snapshot) in res:
return snapshot.id
return None
def visits_and_snapshots_get_from_revision(
storage: StorageInterface, origin: str, revision_id: bytes
) -> Iterator[Tuple[OriginVisit, OriginVisitStatus, Snapshot]]:
"""Retrieve all visits, visit statuses, and matching snapshot of the given origin,
such that the snapshot targets the revision_id.
*Warning* This is a potentially highly costly operation
Yields:
Tuples of (visit, status, snapshot)
"""
revision = storage.revision_get([revision_id])
if not revision:
return
for visit in iter_origin_visits(storage, origin, order=ListOrder.DESC):
assert visit.visit is not None
for visit_status in iter_origin_visit_statuses(
storage, origin, visit.visit, order=ListOrder.DESC
):
snapshot_id = visit_status.snapshot
if snapshot_id is None:
continue
snapshot = snapshot_get_all_branches(storage, snapshot_id)
if not snapshot:
continue
for branch_name, branch in snapshot.branches.items():
if (
branch is not None
and branch.target_type == TargetType.REVISION
and branch.target == revision_id
): # snapshot found
yield (visit, visit_status, snapshot)
def snapshot_resolve_alias(
storage: StorageInterface, snapshot_id: Sha1Git, alias_name: bytes
) -> Optional[SnapshotBranch]:
"""
Transitively resolve snapshot branch alias to its real target, and return it;
ie. follows every branch that is an alias, until a branch that isn't an alias
is found.
Args:
storage: Storage instance
snapshot_id: snapshot identifier
alias_name: name of the branch alias to resolve
Returns:
The first branch that isn't an alias, in the alias chain; or None if
there is no such branch (ie. either because of a cycle alias, or a dangling
branch).
"""
snapshot = storage.snapshot_get_branches(
snapshot_id, branches_from=alias_name, branches_count=1
)
if snapshot is None:
return None
if alias_name not in snapshot["branches"]:
return None
last_branch = snapshot["branches"][alias_name]
seen_aliases = {alias_name}
while last_branch is not None and last_branch.target_type == TargetType.ALIAS:
if last_branch.target in seen_aliases:
return None
alias_target = last_branch.target
snapshot = storage.snapshot_get_branches(
snapshot_id, branches_from=alias_target, branches_count=1
)
assert snapshot is not None
last_branch = snapshot["branches"].get(alias_target)
seen_aliases.add(alias_target)
return last_branch
diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py
index 573e16a1..9929dea5 100644
--- a/swh/storage/api/server.py
+++ b/swh/storage/api/server.py
@@ -1,183 +1,183 @@
# Copyright (C) 2015-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import logging
import os
from typing import Any, Dict, Optional
from swh.core import config
from swh.core.api import RPCServerApp
from swh.core.api import encode_data_server as encode_data
from swh.core.api import error_handler
from swh.storage import get_storage as get_swhstorage
from ..exc import StorageArgumentException
from ..interface import StorageInterface
from ..metrics import send_metric, timed
from .serializers import DECODERS, ENCODERS
def get_storage():
global storage
if not storage:
storage = get_swhstorage(**app.config["storage"])
return storage
class StorageServerApp(RPCServerApp):
extra_type_decoders = DECODERS
extra_type_encoders = ENCODERS
method_decorators = [timed]
def _process_metrics(self, metrics, endpoint):
for metric, count in metrics.items():
send_metric(metric=metric, count=count, method_name=endpoint)
def post_content_add(self, ret, kw):
self._process_metrics(ret, "content_add")
def post_content_add_metadata(self, ret, kw):
self._process_metrics(ret, "content_add_metadata")
def post_skipped_content_add(self, ret, kw):
self._process_metrics(ret, "skipped_content_add")
def post_directory_add(self, ret, kw):
self._process_metrics(ret, "directory_add")
def post_revision_add(self, ret, kw):
self._process_metrics(ret, "revision_add")
def post_release_add(self, ret, kw):
self._process_metrics(ret, "release_add")
def post_snapshot_add(self, ret, kw):
self._process_metrics(ret, "snapshot_add")
def post_origin_visit_status_add(self, ret, kw):
self._process_metrics(ret, "origin_visit_status_add")
def post_origin_add(self, ret, kw):
self._process_metrics(ret, "origin_add")
def post_raw_extrinsic_metadata_add(self, ret, kw):
self._process_metrics(ret, "raw_extrinsic_metadata_add")
def post_metadata_fetcher_add(self, ret, kw):
self._process_metrics(ret, "metadata_fetcher_add")
def post_metadata_authority_add(self, ret, kw):
self._process_metrics(ret, "metadata_authority_add")
def post_extid_add(self, ret, kw):
self._process_metrics(ret, "extid_add")
def post_origin_visit_add(self, ret, kw):
nb_visits = len(ret)
send_metric(
"origin_visit:add",
count=nb_visits,
# method_name should be "origin_visit_add", but changing it now would break
# existing metrics
method_name="origin_visit",
)
app = StorageServerApp(
__name__, backend_class=StorageInterface, backend_factory=get_storage
)
storage = None
@app.errorhandler(StorageArgumentException)
def argument_error_handler(exception):
return error_handler(exception, encode_data, status_code=400)
@app.errorhandler(Exception)
def my_error_handler(exception):
return error_handler(exception, encode_data)
@app.route("/")
@timed
def index():
return """
Software Heritage storage server
You have reached the
Software Heritage
storage server.
See its
documentation
and API for more information
"""
@app.route("/stat/counters", methods=["GET"])
@timed
def stat_counters():
return encode_data(get_storage().stat_counters())
@app.route("/stat/refresh", methods=["GET"])
@timed
def refresh_stat_counters():
return encode_data(get_storage().refresh_stat_counters())
api_cfg = None
def load_and_check_config(config_path: Optional[str]) -> Dict[str, Any]:
"""Check the minimal configuration is set to run the api or raise an
error explanation.
Args:
config_path: Path to the configuration file to load
Raises:
Error if the setup is not as expected
Returns:
configuration as a dict
"""
if not config_path:
raise EnvironmentError("Configuration file must be defined")
if not os.path.exists(config_path):
raise FileNotFoundError(f"Configuration file {config_path} does not exist")
cfg = config.read(config_path)
if "storage" not in cfg:
raise KeyError("Missing 'storage' configuration")
return cfg
def make_app_from_configfile() -> StorageServerApp:
"""Run the WSGI app from the webserver, loading the configuration from
- a configuration file.
+ a configuration file.
- SWH_CONFIG_FILENAME environment variable defines the
- configuration path to load.
+ SWH_CONFIG_FILENAME environment variable defines the
+ configuration path to load.
"""
global api_cfg
if not api_cfg:
config_path = os.environ.get("SWH_CONFIG_FILENAME")
api_cfg = load_and_check_config(config_path)
app.config.update(api_cfg)
handler = logging.StreamHandler()
app.logger.addHandler(handler)
return app
if __name__ == "__main__":
print("Deprecated. Use swh-storage")
diff --git a/swh/storage/backfill.py b/swh/storage/backfill.py
index 556be498..49cfbca5 100644
--- a/swh/storage/backfill.py
+++ b/swh/storage/backfill.py
@@ -1,668 +1,678 @@
# Copyright (C) 2017-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
"""Storage backfiller.
The backfiller goal is to produce back part or all of the objects
from a storage to the journal topics
Current implementation consists in the JournalBackfiller class.
It simply reads the objects from the storage and sends every object identifier back to
the journal.
"""
import logging
from typing import Any, Callable, Dict, Iterable, Iterator, Optional, Tuple, Union
from swh.core.db import BaseDb
from swh.model.model import (
BaseModel,
Directory,
DirectoryEntry,
ExtID,
RawExtrinsicMetadata,
Release,
Revision,
Snapshot,
SnapshotBranch,
TargetType,
)
from swh.model.swhids import ExtendedObjectType
from swh.storage.postgresql.converters import (
db_to_extid,
db_to_raw_extrinsic_metadata,
db_to_release,
db_to_revision,
)
from swh.storage.replay import OBJECT_CONVERTERS
from swh.storage.writer import JournalWriter
logger = logging.getLogger(__name__)
PARTITION_KEY = {
"content": "sha1",
"skipped_content": "sha1",
"directory": "id",
"extid": "target",
"metadata_authority": "type, url",
"metadata_fetcher": "name, version",
"raw_extrinsic_metadata": "target",
"revision": "revision.id",
"release": "release.id",
"snapshot": "id",
"origin": "id",
"origin_visit": "origin_visit.origin",
"origin_visit_status": "origin_visit_status.origin",
}
COLUMNS = {
"content": [
"sha1",
"sha1_git",
"sha256",
"blake2s256",
"length",
"status",
"ctime",
],
"skipped_content": [
"sha1",
"sha1_git",
"sha256",
"blake2s256",
"length",
"ctime",
"status",
"reason",
],
"directory": ["id", "dir_entries", "file_entries", "rev_entries", "raw_manifest"],
"extid": ["extid_type", "extid", "extid_version", "target_type", "target"],
"metadata_authority": ["type", "url"],
"metadata_fetcher": ["name", "version"],
"origin": ["url"],
- "origin_visit": ["visit", "type", ("origin.url", "origin"), "date",],
+ "origin_visit": [
+ "visit",
+ "type",
+ ("origin.url", "origin"),
+ "date",
+ ],
"origin_visit_status": [
("origin_visit_status.visit", "visit"),
("origin.url", "origin"),
("origin_visit_status.date", "date"),
"type",
"snapshot",
"status",
"metadata",
],
"raw_extrinsic_metadata": [
"raw_extrinsic_metadata.type",
"raw_extrinsic_metadata.target",
"metadata_authority.type",
"metadata_authority.url",
"metadata_fetcher.name",
"metadata_fetcher.version",
"discovery_date",
"format",
"raw_extrinsic_metadata.metadata",
"origin",
"visit",
"snapshot",
"release",
"revision",
"path",
"directory",
],
"revision": [
("revision.id", "id"),
"date",
"date_offset_bytes",
"committer_date",
"committer_date_offset_bytes",
"type",
"directory",
"message",
"synthetic",
"metadata",
"extra_headers",
(
"array(select parent_id::bytea from revision_history rh "
"where rh.id = revision.id order by rh.parent_rank asc)",
"parents",
),
"raw_manifest",
("a.id", "author_id"),
("a.name", "author_name"),
("a.email", "author_email"),
("a.fullname", "author_fullname"),
("c.id", "committer_id"),
("c.name", "committer_name"),
("c.email", "committer_email"),
("c.fullname", "committer_fullname"),
],
"release": [
("release.id", "id"),
"date",
"date_offset_bytes",
"comment",
("release.name", "name"),
"synthetic",
"target",
"target_type",
("a.id", "author_id"),
("a.name", "author_name"),
("a.email", "author_email"),
("a.fullname", "author_fullname"),
"raw_manifest",
],
"snapshot": ["id", "object_id"],
}
JOINS = {
"release": ["person a on release.author=a.id"],
"revision": [
"person a on revision.author=a.id",
"person c on revision.committer=c.id",
],
"origin_visit": ["origin on origin_visit.origin=origin.id"],
- "origin_visit_status": ["origin on origin_visit_status.origin=origin.id",],
+ "origin_visit_status": [
+ "origin on origin_visit_status.origin=origin.id",
+ ],
"raw_extrinsic_metadata": [
"metadata_authority on "
"raw_extrinsic_metadata.authority_id=metadata_authority.id",
"metadata_fetcher on raw_extrinsic_metadata.fetcher_id=metadata_fetcher.id",
],
}
EXTRA_WHERE = {
# hack to force the right index usage on table extid
"extid": "target_type in ('revision', 'release', 'content', 'directory')"
}
def directory_converter(db: BaseDb, directory_d: Dict[str, Any]) -> Directory:
"""Convert directory from the flat representation to swh model
- compatible objects.
+ compatible objects.
"""
columns = ["target", "name", "perms"]
query_template = """
select %(columns)s
from directory_entry_%(type)s
where id in %%s
"""
types = ["file", "dir", "rev"]
entries = []
with db.cursor() as cur:
for type in types:
ids = directory_d.pop("%s_entries" % type)
if not ids:
continue
query = query_template % {
"columns": ",".join(columns),
"type": type,
}
cur.execute(query, (tuple(ids),))
for row in cur:
entry_d = dict(zip(columns, row))
entry = DirectoryEntry(
name=entry_d["name"],
type=type,
target=entry_d["target"],
perms=entry_d["perms"],
)
entries.append(entry)
return Directory(
id=directory_d["id"],
entries=tuple(entries),
raw_manifest=directory_d["raw_manifest"],
)
def raw_extrinsic_metadata_converter(
db: BaseDb, metadata: Dict[str, Any]
) -> RawExtrinsicMetadata:
"""Convert a raw extrinsic metadata from the flat representation to swh model
- compatible objects.
+ compatible objects.
"""
return db_to_raw_extrinsic_metadata(metadata)
def extid_converter(db: BaseDb, extid: Dict[str, Any]) -> ExtID:
"""Convert an extid from the flat representation to swh model
- compatible objects.
+ compatible objects.
"""
return db_to_extid(extid)
def revision_converter(db: BaseDb, revision_d: Dict[str, Any]) -> Revision:
"""Convert revision from the flat representation to swh model
- compatible objects.
+ compatible objects.
"""
revision = db_to_revision(revision_d)
assert revision is not None, revision_d["id"]
return revision
def release_converter(db: BaseDb, release_d: Dict[str, Any]) -> Release:
"""Convert release from the flat representation to swh model
- compatible objects.
+ compatible objects.
"""
release = db_to_release(release_d)
assert release is not None, release_d["id"]
return release
def snapshot_converter(db: BaseDb, snapshot_d: Dict[str, Any]) -> Snapshot:
"""Convert snapshot from the flat representation to swh model
- compatible objects.
+ compatible objects.
"""
columns = ["name", "target", "target_type"]
query = """
select %s
from snapshot_branches sbs
inner join snapshot_branch sb on sb.object_id=sbs.branch_id
where sbs.snapshot_id=%%s
""" % ", ".join(
columns
)
with db.cursor() as cur:
cur.execute(query, (snapshot_d["object_id"],))
branches = {}
for name, *row in cur:
branch_d = dict(zip(columns[1:], row))
if branch_d["target"] is not None and branch_d["target_type"] is not None:
branch: Optional[SnapshotBranch] = SnapshotBranch(
target=branch_d["target"],
target_type=TargetType(branch_d["target_type"]),
)
else:
branch = None
branches[name] = branch
- return Snapshot(id=snapshot_d["id"], branches=branches,)
+ return Snapshot(
+ id=snapshot_d["id"],
+ branches=branches,
+ )
CONVERTERS: Dict[str, Callable[[BaseDb, Dict[str, Any]], BaseModel]] = {
"directory": directory_converter,
"extid": extid_converter,
"raw_extrinsic_metadata": raw_extrinsic_metadata_converter,
"revision": revision_converter,
"release": release_converter,
"snapshot": snapshot_converter,
}
def object_to_offset(object_id, numbits):
"""Compute the index of the range containing object id, when dividing
space into 2^numbits.
Args:
object_id (str): The hex representation of object_id
numbits (int): Number of bits in which we divide input space
Returns:
The index of the range containing object id
"""
q, r = divmod(numbits, 8)
length = q + (r != 0)
shift_bits = 8 - r if r else 0
truncated_id = object_id[: length * 2]
if len(truncated_id) < length * 2:
truncated_id += "0" * (length * 2 - len(truncated_id))
truncated_id_bytes = bytes.fromhex(truncated_id)
return int.from_bytes(truncated_id_bytes, byteorder="big") >> shift_bits
def byte_ranges(
numbits: int, start_object: Optional[str] = None, end_object: Optional[str] = None
) -> Iterator[Tuple[Optional[bytes], Optional[bytes]]]:
"""Generate start/end pairs of bytes spanning numbits bits and
constrained by optional start_object and end_object.
Args:
numbits: Number of bits in which we divide input space
start_object: Hex object id contained in the first range
returned
end_object: Hex object id contained in the last range
returned
Yields:
2^numbits pairs of bytes
"""
q, r = divmod(numbits, 8)
length = q + (r != 0)
shift_bits = 8 - r if r else 0
def to_bytes(i):
return int.to_bytes(i << shift_bits, length=length, byteorder="big")
start_offset = 0
end_offset = 1 << numbits
if start_object is not None:
start_offset = object_to_offset(start_object, numbits)
if end_object is not None:
end_offset = object_to_offset(end_object, numbits) + 1
for start in range(start_offset, end_offset):
end = start + 1
if start == 0:
yield None, to_bytes(end)
elif end == 1 << numbits:
yield to_bytes(start), None
else:
yield to_bytes(start), to_bytes(end)
def raw_extrinsic_metadata_target_ranges(
start_object: Optional[str] = None, end_object: Optional[str] = None
) -> Iterator[Tuple[Optional[str], Optional[str]]]:
"""Generate ranges of values for the `target` attribute of `raw_extrinsic_metadata`
objects.
This generates one range for all values before the first SWHID (which would
correspond to raw origin URLs), then a number of hex-based ranges for each
known type of SWHID (2**12 ranges for directories, 2**8 ranges for all other
types). Finally, it generates one extra range for values above all possible
SWHIDs.
"""
if start_object is None:
start_object = ""
swhid_target_types = sorted(type.value for type in ExtendedObjectType)
first_swhid = f"swh:1:{swhid_target_types[0]}:"
# Generate a range for url targets, if the starting object is before SWHIDs
if start_object < first_swhid:
yield start_object, (
first_swhid
if end_object is None or end_object >= first_swhid
else end_object
)
if end_object is not None and end_object <= first_swhid:
return
# Prime the following loop, which uses the upper bound of the previous range
# as lower bound, to account for potential targets between two valid types
# of SWHIDs (even though they would eventually be rejected by the
# RawExtrinsicMetadata parser, they /might/ exist...)
end_swhid = first_swhid
# Generate ranges for swhid targets
for target_type in swhid_target_types:
finished = False
base_swhid = f"swh:1:{target_type}:"
last_swhid = base_swhid + ("f" * 40)
if start_object > last_swhid:
continue
# Generate 2**8 or 2**12 ranges
for _, end in byte_ranges(12 if target_type == "dir" else 8):
# Reuse previous uppper bound
start_swhid = end_swhid
# Use last_swhid for this object type if on the last byte range
end_swhid = (base_swhid + end.hex()) if end is not None else last_swhid
# Ignore out of bounds ranges
if start_object >= end_swhid:
continue
# Potentially clamp start of range to the first object requested
start_swhid = max(start_swhid, start_object)
# Handle ending the loop early if the last requested object id is in
# the current range
if end_object is not None and end_swhid >= end_object:
end_swhid = end_object
finished = True
yield start_swhid, end_swhid
if finished:
return
# Generate one final range for potential raw origin URLs after the last
# valid SWHID
start_swhid = max(start_object, end_swhid)
yield start_swhid, end_object
def integer_ranges(
start: str, end: str, block_size: int = 1000
) -> Iterator[Tuple[Optional[int], Optional[int]]]:
for range_start in range(int(start), int(end), block_size):
if range_start == 0:
yield None, block_size
elif range_start + block_size > int(end):
yield range_start, int(end)
else:
yield range_start, range_start + block_size
RANGE_GENERATORS: Dict[
str,
Union[
Callable[[str, str], Iterable[Tuple[Optional[str], Optional[str]]]],
Callable[[str, str], Iterable[Tuple[Optional[bytes], Optional[bytes]]]],
Callable[[str, str], Iterable[Tuple[Optional[int], Optional[int]]]],
],
] = {
"content": lambda start, end: byte_ranges(24, start, end),
"skipped_content": lambda start, end: [(None, None)],
"directory": lambda start, end: byte_ranges(24, start, end),
"extid": lambda start, end: byte_ranges(24, start, end),
"revision": lambda start, end: byte_ranges(24, start, end),
"release": lambda start, end: byte_ranges(16, start, end),
"raw_extrinsic_metadata": raw_extrinsic_metadata_target_ranges,
"snapshot": lambda start, end: byte_ranges(16, start, end),
"origin": integer_ranges,
"origin_visit": integer_ranges,
"origin_visit_status": integer_ranges,
}
def compute_query(obj_type, start, end):
columns = COLUMNS.get(obj_type)
join_specs = JOINS.get(obj_type, [])
join_clause = "\n".join("left join %s" % clause for clause in join_specs)
additional_where = EXTRA_WHERE.get(obj_type)
where = []
where_args = []
if start:
where.append("%(keys)s >= %%s")
where_args.append(start)
if end:
where.append("%(keys)s < %%s")
where_args.append(end)
if additional_where:
where.append(additional_where)
where_clause = ""
if where:
where_clause = ("where " + " and ".join(where)) % {
"keys": "(%s)" % PARTITION_KEY[obj_type]
}
column_specs = []
column_aliases = []
for column in columns:
if isinstance(column, str):
column_specs.append(column)
column_aliases.append(column)
else:
column_specs.append("%s as %s" % column)
column_aliases.append(column[1])
query = """
select %(columns)s
from %(table)s
%(join)s
%(where)s
""" % {
"columns": ",".join(column_specs),
"table": obj_type,
"join": join_clause,
"where": where_clause,
}
return query, where_args, column_aliases
def fetch(db, obj_type, start, end):
"""Fetch all obj_type's identifiers from db.
This opens one connection, stream objects and when done, close
the connection.
Args:
db (BaseDb): Db connection object
obj_type (str): Object type
start (Union[bytes|Tuple]): Range start identifier
end (Union[bytes|Tuple]): Range end identifier
Raises:
ValueError if obj_type is not supported
Yields:
Objects in the given range
"""
query, where_args, column_aliases = compute_query(obj_type, start, end)
converter = CONVERTERS.get(obj_type)
with db.cursor() as cursor:
logger.debug("Fetching data for table %s", obj_type)
logger.debug("query: %s %s", query, where_args)
cursor.execute(query, where_args)
for row in cursor:
record = dict(zip(column_aliases, row))
if converter:
record = converter(db, record)
else:
record = OBJECT_CONVERTERS[obj_type](record)
logger.debug("record: %s", record)
yield record
def _format_range_bound(bound):
if isinstance(bound, bytes):
return bound.hex()
else:
return str(bound)
MANDATORY_KEYS = ["storage", "journal_writer"]
class JournalBackfiller:
"""Class in charge of reading the storage's objects and sends those
- back to the journal's topics.
+ back to the journal's topics.
- This is designed to be run periodically.
+ This is designed to be run periodically.
"""
def __init__(self, config=None):
self.config = config
self.check_config(config)
def check_config(self, config):
missing_keys = []
for key in MANDATORY_KEYS:
if not config.get(key):
missing_keys.append(key)
if missing_keys:
raise ValueError(
"Configuration error: The following keys must be"
" provided: %s" % (",".join(missing_keys),)
)
if "cls" not in config["storage"] or config["storage"]["cls"] not in (
"local",
"postgresql",
):
raise ValueError(
"swh storage backfiller must be configured to use a local"
" (PostgreSQL) storage"
)
def parse_arguments(self, object_type, start_object, end_object):
"""Parse arguments
Raises:
ValueError for unsupported object type
ValueError if object ids are not parseable
Returns:
Parsed start and end object ids
"""
if object_type not in COLUMNS:
raise ValueError(
"Object type %s is not supported. "
"The only possible values are %s"
% (object_type, ", ".join(sorted(COLUMNS.keys())))
)
if object_type in ["origin", "origin_visit", "origin_visit_status"]:
start_object = start_object or "0"
end_object = end_object or str(100_000_000) # hard-coded limit
return start_object, end_object
def run(self, object_type, start_object, end_object, dry_run=False):
"""Reads storage's subscribed object types and send them to the
- journal's reading topic.
+ journal's reading topic.
"""
start_object, end_object = self.parse_arguments(
object_type, start_object, end_object
)
db = BaseDb.connect(self.config["storage"]["db"])
writer = JournalWriter({"cls": "kafka", **self.config["journal_writer"]})
assert writer.journal is not None
for range_start, range_end in RANGE_GENERATORS[object_type](
start_object, end_object
):
logger.info(
"Processing %s range %s to %s",
object_type,
_format_range_bound(range_start),
_format_range_bound(range_end),
)
objects = fetch(db, object_type, start=range_start, end=range_end)
if not dry_run:
writer.write_additions(object_type, objects)
else:
# only consume the objects iterator to check for any potential
# decoding/encoding errors
for obj in objects:
pass
if __name__ == "__main__":
print('Please use the "swh-journal backfiller run" command')
diff --git a/swh/storage/cassandra/common.py b/swh/storage/cassandra/common.py
index 486cdf67..6ae564ec 100644
--- a/swh/storage/cassandra/common.py
+++ b/swh/storage/cassandra/common.py
@@ -1,16 +1,16 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import hashlib
-TOKEN_BEGIN = -(2 ** 63)
+TOKEN_BEGIN = -(2**63)
"""Minimum value returned by the CQL function token()"""
-TOKEN_END = 2 ** 63 - 1
+TOKEN_END = 2**63 - 1
"""Maximum value returned by the CQL function token()"""
def hash_url(url: str) -> bytes:
return hashlib.sha1(url.encode("utf8")).digest()
diff --git a/swh/storage/cassandra/converters.py b/swh/storage/cassandra/converters.py
index a52b6a0e..2ebce726 100644
--- a/swh/storage/cassandra/converters.py
+++ b/swh/storage/cassandra/converters.py
@@ -1,147 +1,148 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from copy import deepcopy
import datetime
import json
from typing import Dict, Tuple
import attr
from swh.model.hashutil import DEFAULT_ALGORITHMS
from swh.model.model import (
CoreSWHID,
ExtendedSWHID,
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
ObjectType,
OriginVisit,
OriginVisitStatus,
RawExtrinsicMetadata,
Release,
Revision,
RevisionType,
Sha1Git,
)
from ..utils import map_optional, remove_keys
from .model import (
OriginVisitRow,
OriginVisitStatusRow,
RawExtrinsicMetadataRow,
ReleaseRow,
RevisionRow,
)
def revision_to_db(revision: Revision) -> RevisionRow:
# we use a deepcopy of the dict because we do not want to recurse the
# Model->dict conversion (to keep Timestamp & al. entities), BUT we do not
# want to modify original metadata (embedded in the Model entity), so we
# non-recursively convert it as a dict but make a deep copy.
db_revision = deepcopy(attr.asdict(revision, recurse=False))
metadata = revision.metadata
extra_headers = revision.extra_headers
if not extra_headers and metadata and "extra_headers" in metadata:
extra_headers = db_revision["metadata"].pop("extra_headers")
db_revision["metadata"] = json.dumps(
dict(db_revision["metadata"]) if db_revision["metadata"] is not None else None
)
db_revision["extra_headers"] = extra_headers
db_revision["type"] = db_revision["type"].value
return RevisionRow(**remove_keys(db_revision, ("parents",)))
def revision_from_db(
db_revision: RevisionRow, parents: Tuple[Sha1Git, ...]
) -> Revision:
revision = db_revision.to_dict()
metadata = json.loads(revision.pop("metadata", None))
extra_headers = revision.pop("extra_headers", ())
if not extra_headers and metadata and "extra_headers" in metadata:
extra_headers = metadata.pop("extra_headers")
if extra_headers is None:
extra_headers = ()
return Revision(
parents=parents,
type=RevisionType(revision.pop("type")),
metadata=metadata,
extra_headers=extra_headers,
**revision,
)
def release_to_db(release: Release) -> ReleaseRow:
db_release = attr.asdict(release, recurse=False)
db_release["target_type"] = db_release["target_type"].value
return ReleaseRow(**remove_keys(db_release, ("metadata",)))
def release_from_db(db_release: ReleaseRow) -> Release:
release = db_release.to_dict()
- return Release(target_type=ObjectType(release.pop("target_type")), **release,)
+ return Release(
+ target_type=ObjectType(release.pop("target_type")),
+ **release,
+ )
def row_to_content_hashes(row: ReleaseRow) -> Dict[str, bytes]:
- """Convert cassandra row to a content hashes
-
- """
+ """Convert cassandra row to a content hashes"""
hashes = {}
for algo in DEFAULT_ALGORITHMS:
hashes[algo] = getattr(row, algo)
return hashes
def row_to_visit(row: OriginVisitRow) -> OriginVisit:
- """Format a row representing an origin_visit to an actual OriginVisit.
-
- """
+ """Format a row representing an origin_visit to an actual OriginVisit."""
return OriginVisit(
origin=row.origin,
visit=row.visit,
date=row.date.replace(tzinfo=datetime.timezone.utc),
type=row.type,
)
def row_to_visit_status(row: OriginVisitStatusRow) -> OriginVisitStatus:
- """Format a row representing a visit_status to an actual OriginVisitStatus.
-
- """
+ """Format a row representing a visit_status to an actual OriginVisitStatus."""
return OriginVisitStatus.from_dict(
{
**row.to_dict(),
"date": row.date.replace(tzinfo=datetime.timezone.utc),
"metadata": (json.loads(row.metadata) if row.metadata else None),
}
)
def visit_status_to_row(status: OriginVisitStatus) -> OriginVisitStatusRow:
d = status.to_dict()
return OriginVisitStatusRow.from_dict({**d, "metadata": json.dumps(d["metadata"])})
def row_to_raw_extrinsic_metadata(row: RawExtrinsicMetadataRow) -> RawExtrinsicMetadata:
discovery_date = row.discovery_date.replace(tzinfo=datetime.timezone.utc)
return RawExtrinsicMetadata(
target=ExtendedSWHID.from_string(row.target),
authority=MetadataAuthority(
- type=MetadataAuthorityType(row.authority_type), url=row.authority_url,
+ type=MetadataAuthorityType(row.authority_type),
+ url=row.authority_url,
+ ),
+ fetcher=MetadataFetcher(
+ name=row.fetcher_name,
+ version=row.fetcher_version,
),
- fetcher=MetadataFetcher(name=row.fetcher_name, version=row.fetcher_version,),
discovery_date=discovery_date,
format=row.format,
metadata=row.metadata,
origin=row.origin,
visit=row.visit,
snapshot=map_optional(CoreSWHID.from_string, row.snapshot),
release=map_optional(CoreSWHID.from_string, row.release),
revision=map_optional(CoreSWHID.from_string, row.revision),
path=row.path,
directory=map_optional(CoreSWHID.from_string, row.directory),
)
diff --git a/swh/storage/cassandra/cql.py b/swh/storage/cassandra/cql.py
index 1b966ca9..f4487c70 100644
--- a/swh/storage/cassandra/cql.py
+++ b/swh/storage/cassandra/cql.py
@@ -1,1480 +1,1502 @@
# Copyright (C) 2019-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from collections import Counter
import dataclasses
import datetime
import functools
import itertools
import logging
import random
from typing import (
Any,
Callable,
Dict,
Iterable,
Iterator,
List,
Optional,
Sequence,
Tuple,
Type,
TypeVar,
Union,
)
from cassandra import ConsistencyLevel, CoordinationFailure
from cassandra.cluster import EXEC_PROFILE_DEFAULT, Cluster, ExecutionProfile, ResultSet
from cassandra.concurrent import execute_concurrent_with_args
from cassandra.policies import DCAwareRoundRobinPolicy, TokenAwarePolicy
from cassandra.query import BoundStatement, PreparedStatement, dict_factory
from mypy_extensions import NamedArg
from tenacity import (
retry,
retry_if_exception_type,
stop_after_attempt,
wait_random_exponential,
)
from swh.core.utils import grouper
from swh.model.model import (
Content,
Person,
Sha1Git,
SkippedContent,
Timestamp,
TimestampWithTimezone,
)
from swh.model.swhids import CoreSWHID
from swh.storage.interface import ListOrder
from ..utils import remove_keys
from .common import TOKEN_BEGIN, TOKEN_END, hash_url
from .model import (
MAGIC_NULL_PK,
BaseRow,
ContentRow,
DirectoryEntryRow,
DirectoryRow,
ExtIDByTargetRow,
ExtIDRow,
MetadataAuthorityRow,
MetadataFetcherRow,
ObjectCountRow,
OriginRow,
OriginVisitRow,
OriginVisitStatusRow,
RawExtrinsicMetadataByIdRow,
RawExtrinsicMetadataRow,
ReleaseRow,
RevisionParentRow,
RevisionRow,
SkippedContentRow,
SnapshotBranchRow,
SnapshotRow,
content_index_table_name,
)
from .schema import CREATE_TABLES_QUERIES, HASH_ALGORITHMS
PARTITION_KEY_RESTRICTION_MAX_SIZE = 100
"""Maximum number of restrictions in a single query.
Usually this is a very low number (eg. SELECT ... FROM ... WHERE x=?),
but some queries can request arbitrarily many (eg. SELECT ... FROM ... WHERE x IN ?).
This can cause performance issues, as the node getting the query need to
coordinate with other nodes to get the complete results.
See for details and rationale.
"""
BATCH_INSERT_MAX_SIZE = 1000
logger = logging.getLogger(__name__)
def get_execution_profiles(
consistency_level: str = "ONE",
) -> Dict[object, ExecutionProfile]:
if consistency_level not in ConsistencyLevel.name_to_value:
raise ValueError(
f"Configuration error: Unknown consistency level '{consistency_level}'"
)
return {
EXEC_PROFILE_DEFAULT: ExecutionProfile(
load_balancing_policy=TokenAwarePolicy(DCAwareRoundRobinPolicy()),
row_factory=dict_factory,
consistency_level=ConsistencyLevel.name_to_value[consistency_level],
)
}
# Configuration for cassandra-driver's access to servers:
# * hit the right server directly when sending a query (TokenAwarePolicy),
# * if there's more than one, then pick one at random that's in the same
# datacenter as the client (DCAwareRoundRobinPolicy)
def create_keyspace(
hosts: List[str], keyspace: str, port: int = 9042, *, durable_writes=True
):
cluster = Cluster(hosts, port=port, execution_profiles=get_execution_profiles())
session = cluster.connect()
extra_params = ""
if not durable_writes:
extra_params = "AND durable_writes = false"
session.execute(
"""CREATE KEYSPACE IF NOT EXISTS "%s"
WITH REPLICATION = {
'class' : 'SimpleStrategy',
'replication_factor' : 1
} %s;
"""
% (keyspace, extra_params)
)
session.execute('USE "%s"' % keyspace)
for query in CREATE_TABLES_QUERIES:
session.execute(query)
TRet = TypeVar("TRet")
def _prepared_statement(
query: str,
) -> Callable[[Callable[..., TRet]], Callable[..., TRet]]:
"""Returns a decorator usable on methods of CqlRunner, to
inject them with a 'statement' argument, that is a prepared
statement corresponding to the query.
This only works on methods of CqlRunner, as preparing a
statement requires a connection to a Cassandra server."""
def decorator(f):
@functools.wraps(f)
def newf(self, *args, **kwargs) -> TRet:
if f.__name__ not in self._prepared_statements:
statement: PreparedStatement = self._session.prepare(query)
self._prepared_statements[f.__name__] = statement
return f(
self, *args, **kwargs, statement=self._prepared_statements[f.__name__]
)
return newf
return decorator
TArg = TypeVar("TArg")
TSelf = TypeVar("TSelf")
def _insert_query(row_class):
columns = row_class.cols()
return (
f"INSERT INTO {row_class.TABLE} ({', '.join(columns)}) "
f"VALUES ({', '.join('?' for _ in columns)})"
)
def _prepared_insert_statement(
row_class: Type[BaseRow],
) -> Callable[
[Callable[[TSelf, TArg, NamedArg(Any, "statement")], TRet]], # noqa
Callable[[TSelf, TArg], TRet],
]:
"""Shorthand for using `_prepared_statement` for `INSERT INTO`
statements."""
return _prepared_statement(_insert_query(row_class))
def _prepared_exists_statement(
table_name: str,
) -> Callable[
[Callable[[TSelf, TArg, NamedArg(Any, "statement")], TRet]], # noqa
Callable[[TSelf, TArg], TRet],
]:
"""Shorthand for using `_prepared_statement` for queries that only
check which ids in a list exist in the table."""
return _prepared_statement(f"SELECT id FROM {table_name} WHERE id = ?")
def _prepared_select_statement(
- row_class: Type[BaseRow], clauses: str = "", cols: Optional[List[str]] = None,
+ row_class: Type[BaseRow],
+ clauses: str = "",
+ cols: Optional[List[str]] = None,
) -> Callable[[Callable[..., TRet]], Callable[..., TRet]]:
if cols is None:
cols = row_class.cols()
return _prepared_statement(
f"SELECT {', '.join(cols)} FROM {row_class.TABLE} {clauses}"
)
def _prepared_select_statements(
- row_class: Type[BaseRow], queries: Dict[Any, str],
+ row_class: Type[BaseRow],
+ queries: Dict[Any, str],
) -> Callable[[Callable[..., TRet]], Callable[..., TRet]]:
"""Like _prepared_statement, but supports multiple statements, passed a dict,
and passes a dict of prepared statements to the decorated method"""
cols = row_class.cols()
statement_start = f"SELECT {', '.join(cols)} FROM {row_class.TABLE} "
def decorator(f):
@functools.wraps(f)
def newf(self, *args, **kwargs) -> TRet:
if f.__name__ not in self._prepared_statements:
self._prepared_statements[f.__name__] = {
key: self._session.prepare(statement_start + query)
for (key, query) in queries.items()
}
return f(
self, *args, **kwargs, statements=self._prepared_statements[f.__name__]
)
return newf
return decorator
def _next_bytes_value(value: bytes) -> bytes:
"""Returns the next bytes value by incrementing the integer
representation of the provided value and converting it back
to bytes.
For instance when prefix is b"abcd", it returns b"abce".
"""
next_value_int = int.from_bytes(value, byteorder="big") + 1
return next_value_int.to_bytes(
(next_value_int.bit_length() + 7) // 8, byteorder="big"
)
class CqlRunner:
"""Class managing prepared statements and building queries to be sent
to Cassandra."""
def __init__(
self, hosts: List[str], keyspace: str, port: int, consistency_level: str
):
self._cluster = Cluster(
hosts,
port=port,
execution_profiles=get_execution_profiles(consistency_level),
)
self._session = self._cluster.connect(keyspace)
self._cluster.register_user_type(
keyspace, "microtimestamp_with_timezone", TimestampWithTimezone
)
self._cluster.register_user_type(keyspace, "microtimestamp", Timestamp)
self._cluster.register_user_type(keyspace, "person", Person)
# directly a PreparedStatement for methods decorated with
# @_prepared_statements (and its wrappers, _prepared_insert_statement,
# _prepared_exists_statement, and _prepared_select_statement);
# and a dict of PreparedStatements with @_prepared_select_statements
self._prepared_statements: Dict[
str, Union[PreparedStatement, Dict[Any, PreparedStatement]]
] = {}
##########################
# Common utility functions
##########################
MAX_RETRIES = 3
@retry(
wait=wait_random_exponential(multiplier=1, max=10),
stop=stop_after_attempt(MAX_RETRIES),
retry=retry_if_exception_type(CoordinationFailure),
)
def _execute_with_retries(self, statement, args: Optional[Sequence]) -> ResultSet:
return self._session.execute(statement, args, timeout=1000.0)
@retry(
wait=wait_random_exponential(multiplier=1, max=10),
stop=stop_after_attempt(MAX_RETRIES),
retry=retry_if_exception_type(CoordinationFailure),
)
def _execute_many_with_retries(
self, statement, args_list: Sequence[Tuple]
) -> Iterable[Dict[str, Any]]:
for res in execute_concurrent_with_args(self._session, statement, args_list):
yield from res.result_or_exc
def _add_one(self, statement, obj: BaseRow) -> None:
self._execute_with_retries(statement, dataclasses.astuple(obj))
def _add_many(self, statement, objs: Sequence[BaseRow]) -> None:
tables = {obj.TABLE for obj in objs}
assert len(tables) == 1, f"Cannot insert to multiple tables: {tables}"
rows = list(map(dataclasses.astuple, objs))
for _ in self._execute_many_with_retries(statement, rows):
# Need to consume the generator to actually run the INSERTs
pass
_T = TypeVar("_T", bound=BaseRow)
def _get_random_row(self, row_class: Type[_T], statement) -> Optional[_T]: # noqa
"""Takes a prepared statement of the form
"SELECT * FROM WHERE token() > ? LIMIT 1"
and uses it to return a random row"""
token = random.randint(TOKEN_BEGIN, TOKEN_END)
rows = self._execute_with_retries(statement, [token])
if not rows:
# There are no row with a greater token; wrap around to get
# the row with the smallest token
rows = self._execute_with_retries(statement, [TOKEN_BEGIN])
if rows:
return row_class.from_dict(rows.one()) # type: ignore
else:
return None
def _missing(self, statement: PreparedStatement, ids):
found_ids = set()
if not ids:
return []
for row in self._execute_many_with_retries(statement, [(id_,) for id_ in ids]):
found_ids.add(row["id"])
return [id_ for id_ in ids if id_ not in found_ids]
##########################
# 'content' table
##########################
def _content_add_finalize(self, statement: BoundStatement) -> None:
"""Returned currified by content_add_prepare, to be called when the
content row should be added to the primary table."""
self._execute_with_retries(statement, None)
@_prepared_insert_statement(ContentRow)
def content_add_prepare(
self, content: ContentRow, *, statement
) -> Tuple[int, Callable[[], None]]:
"""Prepares insertion of a Content to the main 'content' table.
Returns a token (to be used in secondary tables), and a function to be
called to perform the insertion in the main table."""
statement = statement.bind(dataclasses.astuple(content))
# Type used for hashing keys (usually, it will be
# cassandra.metadata.Murmur3Token)
token_class = self._cluster.metadata.token_map.token_class
# Token of the row when it will be inserted. This is equivalent to
# "SELECT token({', '.join(ContentRow.PARTITION_KEY)}) FROM content WHERE ..."
# after the row is inserted; but we need the token to insert in the
# index tables *before* inserting to the main 'content' table
token = token_class.from_key(statement.routing_key).value
assert TOKEN_BEGIN <= token <= TOKEN_END
# Function to be called after the indexes contain their respective
# row
finalizer = functools.partial(self._content_add_finalize, statement)
return (token, finalizer)
@_prepared_select_statement(
ContentRow, f"WHERE {' AND '.join(map('%s = ?'.__mod__, HASH_ALGORITHMS))}"
)
def content_get_from_pk(
self, content_hashes: Dict[str, bytes], *, statement
) -> Optional[ContentRow]:
rows = list(
self._execute_with_retries(
statement, [content_hashes[algo] for algo in HASH_ALGORITHMS]
)
)
assert len(rows) <= 1
if rows:
return ContentRow(**rows[0])
else:
return None
def content_missing_from_all_hashes(
self, contents_hashes: List[Dict[str, bytes]]
) -> Iterator[Dict[str, bytes]]:
for group in grouper(contents_hashes, PARTITION_KEY_RESTRICTION_MAX_SIZE):
group = list(group)
# Get all contents that share a sha256 with one of the contents in the group
present = set(
self._content_get_hashes_from_sha256(
[content["sha256"] for content in group]
)
)
for content in group:
for algo in HASH_ALGORITHMS:
assert content.get(algo) is not None, (
"content_missing_from_all_hashes must not be called with "
"partial hashes."
)
if tuple(content[algo] for algo in HASH_ALGORITHMS) not in present:
yield content
@_prepared_statement(
f"SELECT {', '.join(HASH_ALGORITHMS)} FROM content WHERE sha256 IN ?"
)
def _content_get_hashes_from_sha256(
self, ids: List[bytes], *, statement
) -> Iterator[Tuple[bytes, bytes, bytes, bytes]]:
for row in self._execute_with_retries(statement, [ids]):
yield tuple(row[algo] for algo in HASH_ALGORITHMS) # type: ignore
@_prepared_select_statement(
ContentRow, f"WHERE token({', '.join(ContentRow.PARTITION_KEY)}) = ?"
)
def content_get_from_tokens(self, tokens, *, statement) -> Iterable[ContentRow]:
return map(
ContentRow.from_dict,
self._execute_many_with_retries(statement, [(token,) for token in tokens]),
)
@_prepared_select_statement(
ContentRow, f"WHERE token({', '.join(ContentRow.PARTITION_KEY)}) > ? LIMIT 1"
)
def content_get_random(self, *, statement) -> Optional[ContentRow]:
return self._get_random_row(ContentRow, statement)
@_prepared_statement(
"""
SELECT token({pk}) AS tok, {cols} FROM {table}
WHERE token({pk}) >= ? AND token({pk}) <= ? LIMIT ?
""".format(
pk=", ".join(ContentRow.PARTITION_KEY),
cols=", ".join(ContentRow.cols()),
table=ContentRow.TABLE,
)
)
def content_get_token_range(
self, start: int, end: int, limit: int, *, statement
) -> Iterable[Tuple[int, ContentRow]]:
"""Returns an iterable of (token, row)"""
return (
(row["tok"], ContentRow.from_dict(remove_keys(row, ("tok",))))
for row in self._execute_with_retries(statement, [start, end, limit])
)
##########################
# 'content_by_*' tables
##########################
def content_index_add_one(self, algo: str, content: Content, token: int) -> None:
"""Adds a row mapping content[algo] to the token of the Content in
the main 'content' table."""
query = f"""
INSERT INTO {content_index_table_name(algo, skipped_content=False)}
({algo}, target_token)
VALUES (%s, %s)
"""
self._execute_with_retries(query, [content.get_hash(algo), token])
def content_get_tokens_from_single_algo(
self, algo: str, hashes: List[bytes]
) -> Iterable[int]:
assert algo in HASH_ALGORITHMS
query = f"""
SELECT target_token
FROM {content_index_table_name(algo, skipped_content=False)}
WHERE {algo} = %s
"""
return (
row["target_token"] # type: ignore
for row in self._execute_many_with_retries(
query, [(hash_,) for hash_ in hashes]
)
)
##########################
# 'skipped_content' table
##########################
def _skipped_content_add_finalize(self, statement: BoundStatement) -> None:
"""Returned currified by skipped_content_add_prepare, to be called
when the content row should be added to the primary table."""
self._execute_with_retries(statement, None)
@_prepared_insert_statement(SkippedContentRow)
def skipped_content_add_prepare(
self, content, *, statement
) -> Tuple[int, Callable[[], None]]:
"""Prepares insertion of a Content to the main 'skipped_content' table.
Returns a token (to be used in secondary tables), and a function to be
called to perform the insertion in the main table."""
# Replace NULLs (which are not allowed in the partition key) with
# an empty byte string
for key in SkippedContentRow.PARTITION_KEY:
if getattr(content, key) is None:
setattr(content, key, MAGIC_NULL_PK)
statement = statement.bind(dataclasses.astuple(content))
# Type used for hashing keys (usually, it will be
# cassandra.metadata.Murmur3Token)
token_class = self._cluster.metadata.token_map.token_class
# Token of the row when it will be inserted. This is equivalent to
# "SELECT token({', '.join(SkippedContentRow.PARTITION_KEY)})
# FROM skipped_content WHERE ..."
# after the row is inserted; but we need the token to insert in the
# index tables *before* inserting to the main 'skipped_content' table
token = token_class.from_key(statement.routing_key).value
assert TOKEN_BEGIN <= token <= TOKEN_END
# Function to be called after the indexes contain their respective
# row
finalizer = functools.partial(self._skipped_content_add_finalize, statement)
return (token, finalizer)
@_prepared_select_statement(
SkippedContentRow,
f"WHERE {' AND '.join(map('%s = ?'.__mod__, HASH_ALGORITHMS))}",
)
def skipped_content_get_from_pk(
self, content_hashes: Dict[str, bytes], *, statement
) -> Optional[SkippedContentRow]:
rows = list(
self._execute_with_retries(
statement,
[content_hashes[algo] or MAGIC_NULL_PK for algo in HASH_ALGORITHMS],
)
)
assert len(rows) <= 1
if rows:
return SkippedContentRow.from_dict(rows[0])
else:
return None
@_prepared_select_statement(
SkippedContentRow,
f"WHERE token({', '.join(SkippedContentRow.PARTITION_KEY)}) = ?",
)
def skipped_content_get_from_token(
self, token, *, statement
) -> Iterable[SkippedContentRow]:
return map(
SkippedContentRow.from_dict, self._execute_with_retries(statement, [token])
)
##########################
# 'skipped_content_by_*' tables
##########################
def skipped_content_index_add_one(
self, algo: str, content: SkippedContent, token: int
) -> None:
"""Adds a row mapping content[algo] to the token of the SkippedContent
in the main 'skipped_content' table."""
query = (
f"INSERT INTO skipped_content_by_{algo} ({algo}, target_token) "
f"VALUES (%s, %s)"
)
self._execute_with_retries(
query, [content.get_hash(algo) or MAGIC_NULL_PK, token]
)
def skipped_content_get_tokens_from_single_hash(
self, algo: str, hash_: bytes
) -> Iterable[int]:
assert algo in HASH_ALGORITHMS
query = f"""
SELECT target_token
FROM {content_index_table_name(algo, skipped_content=True)}
WHERE {algo} = %s
"""
return (
row["target_token"] for row in self._execute_with_retries(query, [hash_])
)
##########################
# 'revision' table
##########################
@_prepared_exists_statement("revision")
def revision_missing(self, ids: List[bytes], *, statement) -> List[bytes]:
return self._missing(statement, ids)
@_prepared_insert_statement(RevisionRow)
def revision_add_one(self, revision: RevisionRow, *, statement) -> None:
self._add_one(statement, revision)
@_prepared_statement(f"SELECT id FROM {RevisionRow.TABLE} WHERE id IN ?")
def revision_get_ids(self, revision_ids, *, statement) -> Iterable[int]:
return (
row["id"] for row in self._execute_with_retries(statement, [revision_ids])
)
@_prepared_select_statement(RevisionRow, "WHERE id IN ?")
def revision_get(
self, revision_ids: List[Sha1Git], *, statement
) -> Iterable[RevisionRow]:
return map(
RevisionRow.from_dict, self._execute_with_retries(statement, [revision_ids])
)
@_prepared_select_statement(RevisionRow, "WHERE token(id) > ? LIMIT 1")
def revision_get_random(self, *, statement) -> Optional[RevisionRow]:
return self._get_random_row(RevisionRow, statement)
##########################
# 'revision_parent' table
##########################
@_prepared_insert_statement(RevisionParentRow)
def revision_parent_add_one(
self, revision_parent: RevisionParentRow, *, statement
) -> None:
self._add_one(statement, revision_parent)
@_prepared_statement(
f"SELECT parent_id FROM {RevisionParentRow.TABLE} WHERE id = ?"
)
def revision_parent_get(
self, revision_id: Sha1Git, *, statement
) -> Iterable[bytes]:
return (
row["parent_id"]
for row in self._execute_with_retries(statement, [revision_id])
)
##########################
# 'release' table
##########################
@_prepared_exists_statement("release")
def release_missing(self, ids: List[bytes], *, statement) -> List[bytes]:
return self._missing(statement, ids)
@_prepared_insert_statement(ReleaseRow)
def release_add_one(self, release: ReleaseRow, *, statement) -> None:
self._add_one(statement, release)
@_prepared_select_statement(ReleaseRow, "WHERE id in ?")
def release_get(
self, release_ids: List[Sha1Git], *, statement
) -> Iterable[ReleaseRow]:
return map(
ReleaseRow.from_dict, self._execute_with_retries(statement, [release_ids])
)
@_prepared_select_statement(ReleaseRow, "WHERE token(id) > ? LIMIT 1")
def release_get_random(self, *, statement) -> Optional[ReleaseRow]:
return self._get_random_row(ReleaseRow, statement)
##########################
# 'directory' table
##########################
@_prepared_exists_statement("directory")
def directory_missing(self, ids: List[bytes], *, statement) -> List[bytes]:
return self._missing(statement, ids)
@_prepared_insert_statement(DirectoryRow)
def directory_add_one(self, directory: DirectoryRow, *, statement) -> None:
"""Called after all calls to directory_entry_add_one, to
commit/finalize the directory."""
self._add_one(statement, directory)
@_prepared_select_statement(DirectoryRow, "WHERE token(id) > ? LIMIT 1")
def directory_get_random(self, *, statement) -> Optional[DirectoryRow]:
return self._get_random_row(DirectoryRow, statement)
@_prepared_select_statement(DirectoryRow, "WHERE id in ?")
def directory_get(
self, directory_ids: List[Sha1Git], *, statement
) -> Iterable[DirectoryRow]:
"""Return fields from the main directory table (e.g. raw_manifest, but not
entries)"""
return map(
DirectoryRow.from_dict,
self._execute_with_retries(statement, [directory_ids]),
)
##########################
# 'directory_entry' table
##########################
@_prepared_insert_statement(DirectoryEntryRow)
def directory_entry_add_one(self, entry: DirectoryEntryRow, *, statement) -> None:
self._add_one(statement, entry)
@_prepared_insert_statement(DirectoryEntryRow)
def directory_entry_add_concurrent(
self, entries: List[DirectoryEntryRow], *, statement
) -> None:
if len(entries) == 0:
# nothing to do
return
assert (
len({entry.directory_id for entry in entries}) == 1
), "directory_entry_add_many must be called with entries for a single dir"
self._add_many(statement, entries)
@_prepared_statement(
"BEGIN UNLOGGED BATCH\n"
+ (_insert_query(DirectoryEntryRow) + ";\n") * BATCH_INSERT_MAX_SIZE
+ "APPLY BATCH"
)
def directory_entry_add_batch(
self, entries: List[DirectoryEntryRow], *, statement
) -> None:
if len(entries) == 0:
# nothing to do
return
assert (
len({entry.directory_id for entry in entries}) == 1
), "directory_entry_add_many must be called with entries for a single dir"
for entry_group in grouper(entries, BATCH_INSERT_MAX_SIZE):
entry_group = list(entry_group)
if len(entry_group) == BATCH_INSERT_MAX_SIZE:
entry_group = list(map(dataclasses.astuple, entry_group))
self._execute_with_retries(
statement, list(itertools.chain.from_iterable(entry_group))
)
else:
# Last group, with a smaller size than the BATCH we prepared.
# Creating a prepared BATCH just for this then discarding it would
# create too much churn on the server side; and using unprepared
# statements is annoying (we can't use _insert_query() as they have
# a different format)
# Fall back to inserting concurrently.
self.directory_entry_add_concurrent(entry_group)
@_prepared_select_statement(DirectoryEntryRow, "WHERE directory_id IN ?")
def directory_entry_get(
self, directory_ids, *, statement
) -> Iterable[DirectoryEntryRow]:
return map(
DirectoryEntryRow.from_dict,
self._execute_with_retries(statement, [directory_ids]),
)
@_prepared_select_statement(
DirectoryEntryRow, "WHERE directory_id = ? AND name >= ? LIMIT ?"
)
def directory_entry_get_from_name(
self, directory_id: Sha1Git, from_: bytes, limit: int, *, statement
) -> Iterable[DirectoryEntryRow]:
return map(
DirectoryEntryRow.from_dict,
self._execute_with_retries(statement, [directory_id, from_, limit]),
)
##########################
# 'snapshot' table
##########################
@_prepared_exists_statement("snapshot")
def snapshot_missing(self, ids: List[bytes], *, statement) -> List[bytes]:
return self._missing(statement, ids)
@_prepared_insert_statement(SnapshotRow)
def snapshot_add_one(self, snapshot: SnapshotRow, *, statement) -> None:
self._add_one(statement, snapshot)
@_prepared_select_statement(SnapshotRow, "WHERE token(id) > ? LIMIT 1")
def snapshot_get_random(self, *, statement) -> Optional[SnapshotRow]:
return self._get_random_row(SnapshotRow, statement)
##########################
# 'snapshot_branch' table
##########################
@_prepared_insert_statement(SnapshotBranchRow)
def snapshot_branch_add_one(self, branch: SnapshotBranchRow, *, statement) -> None:
self._add_one(statement, branch)
@_prepared_statement(
f"""
SELECT ascii_bins_count(target_type) AS counts
FROM {SnapshotBranchRow.TABLE}
WHERE snapshot_id = ? AND name >= ?
"""
)
def snapshot_count_branches_from_name(
self, snapshot_id: Sha1Git, from_: bytes, *, statement
) -> Dict[Optional[str], int]:
row = self._execute_with_retries(statement, [snapshot_id, from_]).one()
(nb_none, counts) = row["counts"]
return {None: nb_none, **counts}
@_prepared_statement(
f"""
SELECT ascii_bins_count(target_type) AS counts
FROM {SnapshotBranchRow.TABLE}
WHERE snapshot_id = ? AND name < ?
"""
)
def snapshot_count_branches_before_name(
- self, snapshot_id: Sha1Git, before: bytes, *, statement,
+ self,
+ snapshot_id: Sha1Git,
+ before: bytes,
+ *,
+ statement,
) -> Dict[Optional[str], int]:
row = self._execute_with_retries(statement, [snapshot_id, before]).one()
(nb_none, counts) = row["counts"]
return {None: nb_none, **counts}
def snapshot_count_branches(
- self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None,
+ self,
+ snapshot_id: Sha1Git,
+ branch_name_exclude_prefix: Optional[bytes] = None,
) -> Dict[Optional[str], int]:
"""Returns a dictionary from type names to the number of branches
of that type."""
prefix = branch_name_exclude_prefix
if prefix is None:
return self.snapshot_count_branches_from_name(snapshot_id, b"")
else:
# counts branches before exclude prefix
counts = Counter(
self.snapshot_count_branches_before_name(snapshot_id, prefix)
)
# no need to execute that part if each bit of the prefix equals 1
if prefix.replace(b"\xff", b"") != b"":
# counts branches after exclude prefix and update counters
counts.update(
self.snapshot_count_branches_from_name(
snapshot_id, _next_bytes_value(prefix)
)
)
return counts
@_prepared_select_statement(
SnapshotBranchRow, "WHERE snapshot_id = ? AND name >= ? LIMIT ?"
)
def snapshot_branch_get_from_name(
self, snapshot_id: Sha1Git, from_: bytes, limit: int, *, statement
) -> Iterable[SnapshotBranchRow]:
return map(
SnapshotBranchRow.from_dict,
self._execute_with_retries(statement, [snapshot_id, from_, limit]),
)
@_prepared_select_statement(
SnapshotBranchRow, "WHERE snapshot_id = ? AND name >= ? AND name < ? LIMIT ?"
)
def snapshot_branch_get_range(
self,
snapshot_id: Sha1Git,
from_: bytes,
before: bytes,
limit: int,
*,
statement,
) -> Iterable[SnapshotBranchRow]:
return map(
SnapshotBranchRow.from_dict,
self._execute_with_retries(statement, [snapshot_id, from_, before, limit]),
)
def snapshot_branch_get(
self,
snapshot_id: Sha1Git,
from_: bytes,
limit: int,
branch_name_exclude_prefix: Optional[bytes] = None,
) -> Iterable[SnapshotBranchRow]:
prefix = branch_name_exclude_prefix
if prefix is None:
return self.snapshot_branch_get_from_name(snapshot_id, from_, limit)
else:
# get branches before the exclude prefix
branches = list(
self.snapshot_branch_get_range(snapshot_id, from_, prefix, limit)
)
nb_branches = len(branches)
# no need to execute that part if limit is reached
# or if each bit of the prefix equals 1
if nb_branches < limit and prefix.replace(b"\xff", b"") != b"":
# get branches after the exclude prefix and update list to return
branches.extend(
self.snapshot_branch_get_from_name(
snapshot_id, _next_bytes_value(prefix), limit - nb_branches
)
)
return branches
##########################
# 'origin' table
##########################
@_prepared_insert_statement(OriginRow)
def origin_add_one(self, origin: OriginRow, *, statement) -> None:
self._add_one(statement, origin)
@_prepared_select_statement(OriginRow, "WHERE sha1 = ?")
def origin_get_by_sha1(self, sha1: bytes, *, statement) -> Iterable[OriginRow]:
return map(OriginRow.from_dict, self._execute_with_retries(statement, [sha1]))
def origin_get_by_url(self, url: str) -> Iterable[OriginRow]:
return self.origin_get_by_sha1(hash_url(url))
@_prepared_statement(
f"""
SELECT token(sha1) AS tok, {", ".join(OriginRow.cols())}
FROM {OriginRow.TABLE}
WHERE token(sha1) >= ? LIMIT ?
"""
)
def origin_list(
self, start_token: int, limit: int, *, statement
) -> Iterable[Tuple[int, OriginRow]]:
"""Returns an iterable of (token, origin)"""
return (
(row["tok"], OriginRow.from_dict(remove_keys(row, ("tok",))))
for row in self._execute_with_retries(statement, [start_token, limit])
)
@_prepared_select_statement(OriginRow)
def origin_iter_all(self, *, statement) -> Iterable[OriginRow]:
return map(OriginRow.from_dict, self._execute_with_retries(statement, []))
@_prepared_statement(
f"""
UPDATE {OriginRow.TABLE}
SET next_visit_id=?
WHERE sha1 = ? IF next_visit_id None:
origin_sha1 = hash_url(origin_url)
next_id = visit_id + 1
self._execute_with_retries(statement, [next_id, origin_sha1, next_id])
@_prepared_statement(f"SELECT next_visit_id FROM {OriginRow.TABLE} WHERE sha1 = ?")
def _origin_get_next_visit_id(self, origin_sha1: bytes, *, statement) -> int:
rows = list(self._execute_with_retries(statement, [origin_sha1]))
assert len(rows) == 1 # TODO: error handling
return rows[0]["next_visit_id"]
@_prepared_statement(
f"""
UPDATE {OriginRow.TABLE}
SET next_visit_id=?
WHERE sha1 = ? IF next_visit_id=?
"""
)
def origin_generate_unique_visit_id(self, origin_url: str, *, statement) -> int:
origin_sha1 = hash_url(origin_url)
next_id = self._origin_get_next_visit_id(origin_sha1)
while True:
res = list(
self._execute_with_retries(
statement, [next_id + 1, origin_sha1, next_id]
)
)
assert len(res) == 1
if res[0]["[applied]"]:
# No data race
return next_id
else:
# Someone else updated it before we did, let's try again
next_id = res[0]["next_visit_id"]
# TODO: abort after too many attempts
return next_id
##########################
# 'origin_visit' table
##########################
@_prepared_select_statements(
OriginVisitRow,
{
(True, ListOrder.ASC): (
"WHERE origin = ? AND visit > ? ORDER BY visit ASC LIMIT ?"
),
(True, ListOrder.DESC): (
"WHERE origin = ? AND visit < ? ORDER BY visit DESC LIMIT ?"
),
(False, ListOrder.ASC): "WHERE origin = ? ORDER BY visit ASC LIMIT ?",
(False, ListOrder.DESC): "WHERE origin = ? ORDER BY visit DESC LIMIT ?",
},
)
def origin_visit_get(
self,
origin_url: str,
last_visit: Optional[int],
limit: int,
order: ListOrder,
*,
statements,
) -> Iterable[OriginVisitRow]:
args: List[Any] = [origin_url]
if last_visit is not None:
args.append(last_visit)
args.append(limit)
statement = statements[(last_visit is not None, order)]
return map(
OriginVisitRow.from_dict, self._execute_with_retries(statement, args)
)
@_prepared_insert_statement(OriginVisitRow)
def origin_visit_add_one(self, visit: OriginVisitRow, *, statement) -> None:
self._add_one(statement, visit)
@_prepared_select_statement(OriginVisitRow, "WHERE origin = ? AND visit = ?")
def origin_visit_get_one(
self, origin_url: str, visit_id: int, *, statement
) -> Optional[OriginVisitRow]:
# TODO: error handling
rows = list(self._execute_with_retries(statement, [origin_url, visit_id]))
if rows:
return OriginVisitRow.from_dict(rows[0])
else:
return None
@_prepared_select_statement(OriginVisitRow, "WHERE origin = ? ORDER BY visit DESC")
def origin_visit_iter_all(
self, origin_url: str, *, statement
) -> Iterable[OriginVisitRow]:
"""Returns an iterator on visits for a given origin, ordered by descending
visit id."""
return map(
OriginVisitRow.from_dict,
self._execute_with_retries(statement, [origin_url]),
)
@_prepared_select_statement(OriginVisitRow, "WHERE token(origin) >= ?")
def _origin_visit_iter_from(
self, min_token: int, *, statement
) -> Iterable[OriginVisitRow]:
return map(
OriginVisitRow.from_dict, self._execute_with_retries(statement, [min_token])
)
@_prepared_select_statement(OriginVisitRow, "WHERE token(origin) < ?")
def _origin_visit_iter_to(
self, max_token: int, *, statement
) -> Iterable[OriginVisitRow]:
return map(
OriginVisitRow.from_dict, self._execute_with_retries(statement, [max_token])
)
def origin_visit_iter(self, start_token: int) -> Iterator[OriginVisitRow]:
"""Returns all origin visits in order from this token,
and wraps around the token space."""
yield from self._origin_visit_iter_from(start_token)
yield from self._origin_visit_iter_to(start_token)
##########################
# 'origin_visit_status' table
##########################
@_prepared_select_statements(
OriginVisitStatusRow,
{
(True, ListOrder.ASC): (
"WHERE origin = ? AND visit = ? AND date >= ? "
"ORDER BY visit ASC LIMIT ?"
),
(True, ListOrder.DESC): (
"WHERE origin = ? AND visit = ? AND date <= ? "
"ORDER BY visit DESC LIMIT ?"
),
(False, ListOrder.ASC): (
"WHERE origin = ? AND visit = ? ORDER BY visit ASC LIMIT ?"
),
(False, ListOrder.DESC): (
"WHERE origin = ? AND visit = ? ORDER BY visit DESC LIMIT ?"
),
},
)
def origin_visit_status_get_range(
self,
origin: str,
visit: int,
date_from: Optional[datetime.datetime],
limit: int,
order: ListOrder,
*,
statements,
) -> Iterable[OriginVisitStatusRow]:
args: List[Any] = [origin, visit]
if date_from is not None:
args.append(date_from)
args.append(limit)
statement = statements[(date_from is not None, order)]
return map(
OriginVisitStatusRow.from_dict, self._execute_with_retries(statement, args)
)
@_prepared_select_statement(
OriginVisitStatusRow,
"WHERE origin = ? AND visit >= ? AND visit <= ? ORDER BY visit ASC, date ASC",
)
def origin_visit_status_get_all_range(
- self, origin_url: str, visit_from: int, visit_to: int, *, statement,
+ self,
+ origin_url: str,
+ visit_from: int,
+ visit_to: int,
+ *,
+ statement,
) -> Iterable[OriginVisitStatusRow]:
args = (origin_url, visit_from, visit_to)
return map(
OriginVisitStatusRow.from_dict, self._execute_with_retries(statement, args)
)
@_prepared_insert_statement(OriginVisitStatusRow)
def origin_visit_status_add_one(
self, visit_update: OriginVisitStatusRow, *, statement
) -> None:
self._add_one(statement, visit_update)
def origin_visit_status_get_latest(
- self, origin: str, visit: int,
+ self,
+ origin: str,
+ visit: int,
) -> Optional[OriginVisitStatusRow]:
- """Given an origin visit id, return its latest origin_visit_status
-
- """
+ """Given an origin visit id, return its latest origin_visit_status"""
return next(self.origin_visit_status_get(origin, visit), None)
@_prepared_select_statement(
OriginVisitStatusRow,
# 'visit DESC,' is optional with Cassandra 4, but ScyllaDB needs it
"WHERE origin = ? AND visit = ? ORDER BY visit DESC, date DESC",
)
def origin_visit_status_get(
- self, origin: str, visit: int, *, statement,
+ self,
+ origin: str,
+ visit: int,
+ *,
+ statement,
) -> Iterator[OriginVisitStatusRow]:
- """Return all origin visit statuses for a given visit
-
- """
+ """Return all origin visit statuses for a given visit"""
return map(
OriginVisitStatusRow.from_dict,
self._execute_with_retries(statement, [origin, visit]),
)
@_prepared_statement("SELECT snapshot FROM origin_visit_status WHERE origin = ?")
def origin_snapshot_get_all(self, origin: str, *, statement) -> Iterable[Sha1Git]:
yield from {
d["snapshot"]
for d in self._execute_with_retries(statement, [origin])
if d["snapshot"] is not None
}
##########################
# 'metadata_authority' table
##########################
@_prepared_insert_statement(MetadataAuthorityRow)
def metadata_authority_add(self, authority: MetadataAuthorityRow, *, statement):
self._add_one(statement, authority)
@_prepared_select_statement(MetadataAuthorityRow, "WHERE type = ? AND url = ?")
def metadata_authority_get(
self, type, url, *, statement
) -> Optional[MetadataAuthorityRow]:
rows = list(self._execute_with_retries(statement, [type, url]))
if rows:
return MetadataAuthorityRow.from_dict(rows[0])
else:
return None
##########################
# 'metadata_fetcher' table
##########################
@_prepared_insert_statement(MetadataFetcherRow)
def metadata_fetcher_add(self, fetcher, *, statement):
self._add_one(statement, fetcher)
@_prepared_select_statement(MetadataFetcherRow, "WHERE name = ? AND version = ?")
def metadata_fetcher_get(
self, name, version, *, statement
) -> Optional[MetadataFetcherRow]:
rows = list(self._execute_with_retries(statement, [name, version]))
if rows:
return MetadataFetcherRow.from_dict(rows[0])
else:
return None
#########################
# 'raw_extrinsic_metadata_by_id' table
#########################
@_prepared_insert_statement(RawExtrinsicMetadataByIdRow)
def raw_extrinsic_metadata_by_id_add(self, row, *, statement):
self._add_one(statement, row)
@_prepared_select_statement(RawExtrinsicMetadataByIdRow, "WHERE id IN ?")
def raw_extrinsic_metadata_get_by_ids(
self, ids: List[Sha1Git], *, statement
) -> Iterable[RawExtrinsicMetadataByIdRow]:
return map(
RawExtrinsicMetadataByIdRow.from_dict,
self._execute_with_retries(statement, [ids]),
)
#########################
# 'raw_extrinsic_metadata' table
#########################
@_prepared_insert_statement(RawExtrinsicMetadataRow)
def raw_extrinsic_metadata_add(self, raw_extrinsic_metadata, *, statement):
self._add_one(statement, raw_extrinsic_metadata)
@_prepared_select_statement(
RawExtrinsicMetadataRow,
"WHERE target=? AND authority_url=? AND discovery_date>? AND authority_type=?",
)
def raw_extrinsic_metadata_get_after_date(
self,
target: str,
authority_type: str,
authority_url: str,
after: datetime.datetime,
*,
statement,
) -> Iterable[RawExtrinsicMetadataRow]:
return map(
RawExtrinsicMetadataRow.from_dict,
self._execute_with_retries(
statement, [target, authority_url, after, authority_type]
),
)
@_prepared_select_statement(
RawExtrinsicMetadataRow,
# This is equivalent to:
# WHERE target=? AND authority_type = ? AND authority_url = ? "
# AND (discovery_date, id) > (?, ?)"
# but it needs to be written this way to work with ScyllaDB.
"WHERE target=? AND (authority_type, authority_url) <= (?, ?) "
"AND (authority_type, authority_url, discovery_date, id) > (?, ?, ?, ?)",
)
def raw_extrinsic_metadata_get_after_date_and_id(
self,
target: str,
authority_type: str,
authority_url: str,
after_date: datetime.datetime,
after_id: bytes,
*,
statement,
) -> Iterable[RawExtrinsicMetadataRow]:
return map(
RawExtrinsicMetadataRow.from_dict,
self._execute_with_retries(
statement,
[
target,
authority_type,
authority_url,
authority_type,
authority_url,
after_date,
after_id,
],
),
)
@_prepared_select_statement(
RawExtrinsicMetadataRow,
"WHERE target=? AND authority_url=? AND authority_type=?",
)
def raw_extrinsic_metadata_get(
self, target: str, authority_type: str, authority_url: str, *, statement
) -> Iterable[RawExtrinsicMetadataRow]:
return map(
RawExtrinsicMetadataRow.from_dict,
self._execute_with_retries(
statement, [target, authority_url, authority_type]
),
)
@_prepared_statement(
"SELECT authority_type, authority_url FROM raw_extrinsic_metadata "
"WHERE target = ?"
)
def raw_extrinsic_metadata_get_authorities(
self, target: str, *, statement
) -> Iterable[Tuple[str, str]]:
return (
(entry["authority_type"], entry["authority_url"])
for entry in self._execute_with_retries(statement, [target])
)
##########################
# 'extid' table
##########################
def _extid_add_finalize(self, statement: BoundStatement) -> None:
"""Returned currified by extid_add_prepare, to be called when the
extid row should be added to the primary table."""
self._execute_with_retries(statement, None)
@_prepared_insert_statement(ExtIDRow)
def extid_add_prepare(
self, extid: ExtIDRow, *, statement
) -> Tuple[int, Callable[[], None]]:
statement = statement.bind(dataclasses.astuple(extid))
token_class = self._cluster.metadata.token_map.token_class
token = token_class.from_key(statement.routing_key).value
assert TOKEN_BEGIN <= token <= TOKEN_END
# Function to be called after the indexes contain their respective
# row
finalizer = functools.partial(self._extid_add_finalize, statement)
return (token, finalizer)
@_prepared_select_statement(
ExtIDRow,
"WHERE extid_type=? AND extid=? AND extid_version=? "
"AND target_type=? AND target=?",
)
def extid_get_from_pk(
self,
extid_type: str,
extid: bytes,
extid_version: int,
target: CoreSWHID,
*,
statement,
) -> Optional[ExtIDRow]:
rows = list(
self._execute_with_retries(
statement,
[
extid_type,
extid,
extid_version,
target.object_type.value,
target.object_id,
],
),
)
assert len(rows) <= 1
if rows:
return ExtIDRow(**rows[0])
else:
return None
@_prepared_select_statement(
- ExtIDRow, "WHERE token(extid_type, extid) = ?",
+ ExtIDRow,
+ "WHERE token(extid_type, extid) = ?",
)
def extid_get_from_token(self, token: int, *, statement) -> Iterable[ExtIDRow]:
- return map(ExtIDRow.from_dict, self._execute_with_retries(statement, [token]),)
+ return map(
+ ExtIDRow.from_dict,
+ self._execute_with_retries(statement, [token]),
+ )
# Rows are partitioned by token(extid_type, extid), then ordered (aka. "clustered")
# by (extid_type, extid, extid_version, ...). This means that, without knowing the
# exact extid_type and extid, we need to scan the whole partition; which should be
# reasonably small. We can change the schema later if this becomes an issue
@_prepared_select_statement(
ExtIDRow,
"WHERE token(extid_type, extid) = ? AND extid_version = ? ALLOW FILTERING",
)
def extid_get_from_token_and_extid_version(
self, token: int, extid_version: int, *, statement
) -> Iterable[ExtIDRow]:
return map(
ExtIDRow.from_dict,
self._execute_with_retries(statement, [token, extid_version]),
)
@_prepared_select_statement(
- ExtIDRow, "WHERE extid_type=? AND extid=?",
+ ExtIDRow,
+ "WHERE extid_type=? AND extid=?",
)
def extid_get_from_extid(
self, extid_type: str, extid: bytes, *, statement
) -> Iterable[ExtIDRow]:
return map(
ExtIDRow.from_dict,
self._execute_with_retries(statement, [extid_type, extid]),
)
@_prepared_select_statement(
- ExtIDRow, "WHERE extid_type=? AND extid=? AND extid_version = ?",
+ ExtIDRow,
+ "WHERE extid_type=? AND extid=? AND extid_version = ?",
)
def extid_get_from_extid_and_version(
self, extid_type: str, extid: bytes, extid_version: int, *, statement
) -> Iterable[ExtIDRow]:
return map(
ExtIDRow.from_dict,
self._execute_with_retries(statement, [extid_type, extid, extid_version]),
)
def extid_get_from_target(
self,
target_type: str,
target: bytes,
extid_type: Optional[str] = None,
extid_version: Optional[int] = None,
) -> Iterable[ExtIDRow]:
for token in self._extid_get_tokens_from_target(target_type, target):
if token is not None:
if extid_type is not None and extid_version is not None:
extids = self.extid_get_from_token_and_extid_version(
token, extid_version
)
else:
extids = self.extid_get_from_token(token)
for extid in extids:
# re-check the extid against target (in case of murmur3 collision)
if (
extid is not None
and extid.target_type == target_type
and extid.target == target
and (
(extid_version is None and extid_type is None)
or (
(
extid_version is not None
and extid.extid_version == extid_version
and extid_type is not None
and extid.extid_type == extid_type
)
)
)
):
yield extid
##########################
# 'extid_by_target' table
##########################
@_prepared_insert_statement(ExtIDByTargetRow)
def extid_index_add_one(self, row: ExtIDByTargetRow, *, statement) -> None:
"""Adds a row mapping extid[target_type, target] to the token of the ExtID in
the main 'extid' table."""
self._add_one(statement, row)
@_prepared_statement(
f"""
SELECT target_token
FROM {ExtIDByTargetRow.TABLE}
WHERE target_type = ? AND target = ?
"""
)
def _extid_get_tokens_from_target(
self, target_type: str, target: bytes, *, statement
) -> Iterable[int]:
return (
row["target_token"]
for row in self._execute_with_retries(statement, [target_type, target])
)
##########################
# Miscellaneous
##########################
def stat_counters(self) -> Iterable[ObjectCountRow]:
raise NotImplementedError(
"stat_counters is not implemented by the Cassandra backend"
)
@_prepared_statement("SELECT uuid() FROM revision LIMIT 1;")
def check_read(self, *, statement):
self._execute_with_retries(statement, [])
diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py
index b163f72d..482fdc2a 100644
--- a/swh/storage/cassandra/storage.py
+++ b/swh/storage/cassandra/storage.py
@@ -1,1729 +1,1754 @@
# Copyright (C) 2019-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import base64
from collections import defaultdict
import datetime
import itertools
import operator
import random
import re
from typing import (
Any,
Callable,
Counter,
Dict,
Iterable,
List,
Optional,
Sequence,
Set,
Tuple,
Union,
)
import attr
from swh.core.api.classes import stream_results
from swh.core.api.serializers import msgpack_dumps, msgpack_loads
from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_hex
from swh.model.model import (
Content,
Directory,
DirectoryEntry,
ExtID,
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
OriginVisit,
OriginVisitStatus,
RawExtrinsicMetadata,
Release,
Revision,
Sha1Git,
SkippedContent,
Snapshot,
SnapshotBranch,
TargetType,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.model.swhids import ObjectType as SwhidObjectType
from swh.storage.interface import (
VISIT_STATUSES,
ListOrder,
OriginVisitWithStatuses,
PagedResult,
PartialBranches,
Sha1,
)
from swh.storage.objstorage import ObjStorage
from swh.storage.utils import map_optional, now
from swh.storage.writer import JournalWriter
from . import converters
from ..exc import HashCollision, StorageArgumentException
from ..utils import remove_keys
from .common import TOKEN_BEGIN, TOKEN_END, hash_url
from .cql import CqlRunner
from .model import (
ContentRow,
DirectoryEntryRow,
DirectoryRow,
ExtIDByTargetRow,
ExtIDRow,
MetadataAuthorityRow,
MetadataFetcherRow,
OriginRow,
OriginVisitRow,
OriginVisitStatusRow,
RawExtrinsicMetadataByIdRow,
RawExtrinsicMetadataRow,
RevisionParentRow,
SkippedContentRow,
SnapshotBranchRow,
SnapshotRow,
)
from .schema import HASH_ALGORITHMS
# Max block size of contents to return
BULK_BLOCK_CONTENT_LEN_MAX = 10000
DIRECTORY_ENTRIES_INSERT_ALGOS = ["one-by-one", "concurrent", "batch"]
class CassandraStorage:
def __init__(
self,
hosts,
keyspace,
objstorage,
port=9042,
journal_writer=None,
allow_overwrite=False,
consistency_level="ONE",
directory_entries_insert_algo="one-by-one",
):
"""
A backend of swh-storage backed by Cassandra
Args:
hosts: Seed Cassandra nodes, to start connecting to the cluster
keyspace: Name of the Cassandra database to use
objstorage: Passed as argument to :class:`ObjStorage`
port: Cassandra port
journal_writer: Passed as argument to :class:`JournalWriter`
allow_overwrite: Whether ``*_add`` functions will check if an object
already exists in the database before sending it in an INSERT.
``False`` is the default as it is more efficient when there is
a moderately high probability the object is already known,
but ``True`` can be useful to overwrite existing objects
(eg. when applying a schema update),
or when the database is known to be mostly empty.
Note that a ``False`` value does not guarantee there won't be
any overwrite.
consistency_level: The default read/write consistency to use
directory_entries_insert_algo: Must be one of:
* one-by-one: naive, one INSERT per directory entry, serialized
* concurrent: one INSERT per directory entry, concurrent
* batch: using UNLOGGED BATCH to insert many entries in a few statements
"""
self._hosts = hosts
self._keyspace = keyspace
self._port = port
self._consistency_level = consistency_level
self._set_cql_runner()
self.journal_writer: JournalWriter = JournalWriter(journal_writer)
self.objstorage: ObjStorage = ObjStorage(objstorage)
self._allow_overwrite = allow_overwrite
if directory_entries_insert_algo not in DIRECTORY_ENTRIES_INSERT_ALGOS:
raise ValueError(
f"directory_entries_insert_algo must be one of: "
f"{', '.join(DIRECTORY_ENTRIES_INSERT_ALGOS)}"
)
self._directory_entries_insert_algo = directory_entries_insert_algo
def _set_cql_runner(self):
"""Used by tests when they need to reset the CqlRunner"""
self._cql_runner: CqlRunner = CqlRunner(
self._hosts, self._keyspace, self._port, self._consistency_level
)
def check_config(self, *, check_write: bool) -> bool:
self._cql_runner.check_read()
return True
def _content_get_from_hashes(self, algo, hashes: List[bytes]) -> Iterable:
"""From the name of a hash algorithm and a value of that hash,
looks up the "hash -> token" secondary table (content_by_{algo})
to get tokens.
Then, looks up the main table (content) to get all contents with
that token, and filters out contents whose hash doesn't match."""
found_tokens = list(
self._cql_runner.content_get_tokens_from_single_algo(algo, hashes)
)
assert all(isinstance(token, int) for token in found_tokens)
# Query the main table ('content').
rows = self._cql_runner.content_get_from_tokens(found_tokens)
for row in rows:
# re-check the the hash (in case of murmur3 collision)
if getattr(row, algo) in hashes:
yield row
def _content_add(self, contents: List[Content], with_data: bool) -> Dict[str, int]:
# Filter-out content already in the database.
if not self._allow_overwrite:
contents = [
c
for c in contents
if not self._cql_runner.content_get_from_pk(c.to_dict())
]
if with_data:
# First insert to the objstorage, if the endpoint is
# `content_add` (as opposed to `content_add_metadata`).
# Must add to the objstorage before the DB and journal. Otherwise:
# 1. in case of a crash the DB may "believe" we have the content, but
# we didn't have time to write to the objstorage before the crash
# 2. the objstorage mirroring, which reads from the journal, may attempt to
# read from the objstorage before we finished writing it
summary = self.objstorage.content_add(
c for c in contents if c.status != "absent"
)
content_add_bytes = summary["content:add:bytes"]
self.journal_writer.content_add(contents)
content_add = 0
for content in contents:
content_add += 1
# Check for sha1 or sha1_git collisions. This test is not atomic
# with the insertion, so it won't detect a collision if both
# contents are inserted at the same time, but it's good enough.
#
# The proper way to do it would probably be a BATCH, but this
# would be inefficient because of the number of partitions we
# need to affect (len(HASH_ALGORITHMS)+1, which is currently 5)
if not self._allow_overwrite:
for algo in {"sha1", "sha1_git"}:
collisions = []
# Get tokens of 'content' rows with the same value for
# sha1/sha1_git
# TODO: batch these requests, instead of sending them one by one
rows = self._content_get_from_hashes(algo, [content.get_hash(algo)])
for row in rows:
if getattr(row, algo) != content.get_hash(algo):
# collision of token(partition key), ignore this
# row
continue
for other_algo in HASH_ALGORITHMS:
if getattr(row, other_algo) != content.get_hash(other_algo):
# This hash didn't match; discard the row.
collisions.append(
{k: getattr(row, k) for k in HASH_ALGORITHMS}
)
if collisions:
collisions.append(content.hashes())
raise HashCollision(algo, content.get_hash(algo), collisions)
(token, insertion_finalizer) = self._cql_runner.content_add_prepare(
ContentRow(**remove_keys(content.to_dict(), ("data",)))
)
# Then add to index tables
for algo in HASH_ALGORITHMS:
self._cql_runner.content_index_add_one(algo, content, token)
# Then to the main table
insertion_finalizer()
summary = {
"content:add": content_add,
}
if with_data:
summary["content:add:bytes"] = content_add_bytes
return summary
def content_add(self, content: List[Content]) -> Dict[str, int]:
to_add = {
(c.sha1, c.sha1_git, c.sha256, c.blake2s256): c for c in content
}.values()
contents = [attr.evolve(c, ctime=now()) for c in to_add]
return self._content_add(list(contents), with_data=True)
def content_update(
self, contents: List[Dict[str, Any]], keys: List[str] = []
) -> None:
raise NotImplementedError(
"content_update is not supported by the Cassandra backend"
)
def content_add_metadata(self, content: List[Content]) -> Dict[str, int]:
return self._content_add(content, with_data=False)
def content_get_data(self, content: Sha1) -> Optional[bytes]:
# FIXME: Make this method support slicing the `data`
return self.objstorage.content_get(content)
def content_get_partition(
self,
partition_id: int,
nb_partitions: int,
page_token: Optional[str] = None,
limit: int = 1000,
) -> PagedResult[Content]:
if limit is None:
raise StorageArgumentException("limit should not be None")
# Compute start and end of the range of tokens covered by the
# requested partition
partition_size = (TOKEN_END - TOKEN_BEGIN) // nb_partitions
range_start = TOKEN_BEGIN + partition_id * partition_size
range_end = TOKEN_BEGIN + (partition_id + 1) * partition_size
# offset the range start according to the `page_token`.
if page_token is not None:
if not (range_start <= int(page_token) <= range_end):
raise StorageArgumentException("Invalid page_token.")
range_start = int(page_token)
next_page_token: Optional[str] = None
rows = self._cql_runner.content_get_token_range(
range_start, range_end, limit + 1
)
contents = []
for counter, (tok, row) in enumerate(rows):
if row.status == "absent":
continue
row_d = row.to_dict()
if counter >= limit:
next_page_token = str(tok)
break
row_d.pop("ctime")
contents.append(Content(**row_d))
assert len(contents) <= limit
return PagedResult(results=contents, next_page_token=next_page_token)
def content_get(
self, contents: List[bytes], algo: str = "sha1"
) -> List[Optional[Content]]:
if algo not in DEFAULT_ALGORITHMS:
raise StorageArgumentException(
"algo should be one of {','.join(DEFAULT_ALGORITHMS)}"
)
key = operator.attrgetter(algo)
contents_by_hash: Dict[Sha1, Optional[Content]] = {}
for row in self._content_get_from_hashes(algo, contents):
# Get all (sha1, sha1_git, sha256, blake2s256) whose sha1/sha1_git
# matches the argument, from the index table ('content_by_*')
row_d = row.to_dict()
row_d.pop("ctime")
content = Content(**row_d)
contents_by_hash[key(content)] = content
return [contents_by_hash.get(hash_) for hash_ in contents]
def content_find(self, content: Dict[str, Any]) -> List[Content]:
return self._content_find_many([content])
def _content_find_many(self, contents: List[Dict[str, Any]]) -> List[Content]:
# Find an algorithm that is common to all the requested contents.
# It will be used to do an initial filtering efficiently.
# TODO: prioritize sha256, we can do more efficient lookups from this hash.
filter_algos = set(HASH_ALGORITHMS)
for content in contents:
filter_algos &= set(content)
if not filter_algos:
raise StorageArgumentException(
"content keys must contain at least one "
f"of: {', '.join(sorted(HASH_ALGORITHMS))}"
)
common_algo = list(filter_algos)[0]
results = []
rows = self._content_get_from_hashes(
common_algo, [content[common_algo] for content in contents]
)
for row in rows:
# Re-check all the hashes, in case of collisions (either of the
# hash of the partition key, or the hashes in it)
for content in contents:
for algo in HASH_ALGORITHMS:
if content.get(algo) and getattr(row, algo) != content[algo]:
# This hash didn't match; discard the row.
break
else:
# All hashes match, keep this row.
row_d = row.to_dict()
row_d["ctime"] = row.ctime.replace(tzinfo=datetime.timezone.utc)
results.append(Content(**row_d))
break
else:
# No content matched; skip it
pass
return results
def content_missing(
self, contents: List[Dict[str, Any]], key_hash: str = "sha1"
) -> Iterable[bytes]:
if key_hash not in DEFAULT_ALGORITHMS:
raise StorageArgumentException(
"key_hash should be one of {','.join(DEFAULT_ALGORITHMS)}"
)
contents_with_all_hashes = []
contents_with_missing_hashes = []
for content in contents:
if DEFAULT_ALGORITHMS <= set(content):
contents_with_all_hashes.append(content)
else:
contents_with_missing_hashes.append(content)
# These contents can be queried efficiently directly in the main table
for content in self._cql_runner.content_missing_from_all_hashes(
contents_with_all_hashes
):
yield content[key_hash]
if contents_with_missing_hashes:
# For these, we need the expensive index lookups + main table.
# Get all contents in the database that match (at least) one of the
# requested contents, concurrently.
found_contents = self._content_find_many(contents_with_missing_hashes)
# Bucket the known contents by hash
found_contents_by_hash: Dict[str, Dict[str, list]] = {
algo: defaultdict(list) for algo in DEFAULT_ALGORITHMS
}
for found_content in found_contents:
for algo in DEFAULT_ALGORITHMS:
found_contents_by_hash[algo][found_content.get_hash(algo)].append(
found_content
)
# For each of the requested contents, check if they are in the
# 'found_contents' set (via 'found_contents_by_hash' for efficient access,
# since we need to check using dict inclusion instead of hash+equality)
for missing_content in contents_with_missing_hashes:
# Pick any of the algorithms provided in missing_content
algo = next(algo for (algo, hash_) in missing_content.items() if hash_)
# Get the list of found_contents that match this hash in the
# missing_content. (its length is at most 1, unless there is a
# collision)
found_contents_with_same_hash = found_contents_by_hash[algo][
missing_content[algo]
]
# Check if there is a found_content that matches all hashes in the
# missing_content.
# This is functionally equivalent to 'for found_content in
# found_contents', but runs almost in constant time (it is linear
# in the number of hash collisions) instead of linear.
# This allows this function to run in linear time overall instead of
# quadratic.
for found_content in found_contents_with_same_hash:
# check if the found_content.hashes() dictionary contains a superset
# of the (key, value) pairs in missing_content
if missing_content.items() <= found_content.hashes().items():
# Found!
break
else:
# Not found
yield missing_content[key_hash]
def content_missing_per_sha1(self, contents: List[bytes]) -> Iterable[bytes]:
return self.content_missing([{"sha1": c} for c in contents])
def content_missing_per_sha1_git(
self, contents: List[Sha1Git]
) -> Iterable[Sha1Git]:
return self.content_missing(
[{"sha1_git": c} for c in contents], key_hash="sha1_git"
)
def content_get_random(self) -> Sha1Git:
content = self._cql_runner.content_get_random()
assert content, "Could not find any content"
return content.sha1_git
def _skipped_content_add(self, contents: List[SkippedContent]) -> Dict[str, int]:
# Filter-out content already in the database.
if not self._allow_overwrite:
contents = [
c
for c in contents
if not self._cql_runner.skipped_content_get_from_pk(c.to_dict())
]
self.journal_writer.skipped_content_add(contents)
for content in contents:
# Compute token of the row in the main table
(token, insertion_finalizer) = self._cql_runner.skipped_content_add_prepare(
SkippedContentRow.from_dict({"origin": None, **content.to_dict()})
)
# Then add to index tables
for algo in HASH_ALGORITHMS:
self._cql_runner.skipped_content_index_add_one(algo, content, token)
# Then to the main table
insertion_finalizer()
return {"skipped_content:add": len(contents)}
def skipped_content_add(self, content: List[SkippedContent]) -> Dict[str, int]:
contents = [attr.evolve(c, ctime=now()) for c in content]
return self._skipped_content_add(contents)
def skipped_content_missing(
self, contents: List[Dict[str, Any]]
) -> Iterable[Dict[str, Any]]:
for content in contents:
if not self._cql_runner.skipped_content_get_from_pk(content):
yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS}
def directory_add(self, directories: List[Directory]) -> Dict[str, int]:
to_add = {d.id: d for d in directories}.values()
if not self._allow_overwrite:
# Filter out directories that are already inserted.
missing = self.directory_missing([dir_.id for dir_ in to_add])
directories = [dir_ for dir_ in directories if dir_.id in missing]
self.journal_writer.directory_add(directories)
for directory in directories:
# Add directory entries to the 'directory_entry' table
rows = [
DirectoryEntryRow(directory_id=directory.id, **entry.to_dict())
for entry in directory.entries
]
if self._directory_entries_insert_algo == "one-by-one":
for row in rows:
self._cql_runner.directory_entry_add_one(row)
elif self._directory_entries_insert_algo == "concurrent":
self._cql_runner.directory_entry_add_concurrent(rows)
elif self._directory_entries_insert_algo == "batch":
self._cql_runner.directory_entry_add_batch(rows)
else:
raise ValueError(
f"Unexpected value for directory_entries_insert_algo: "
f"{self._directory_entries_insert_algo}"
)
# Add the directory *after* adding all the entries, so someone
# calling snapshot_get_branch in the meantime won't end up
# with half the entries.
self._cql_runner.directory_add_one(
DirectoryRow(id=directory.id, raw_manifest=directory.raw_manifest)
)
return {"directory:add": len(directories)}
def directory_missing(self, directories: List[Sha1Git]) -> Iterable[Sha1Git]:
return self._cql_runner.directory_missing(directories)
def _join_dentry_to_content(
self, dentry: DirectoryEntry, contents: List[Content]
) -> Dict[str, Any]:
content: Union[None, Content, SkippedContentRow]
keys = (
"status",
"sha1",
"sha1_git",
"sha256",
"length",
)
ret = dict.fromkeys(keys)
ret.update(dentry.to_dict())
if ret["type"] == "file":
for content in contents:
if dentry.target == content.sha1_git:
break
else:
target = ret["target"]
assert target is not None
tokens = list(
self._cql_runner.skipped_content_get_tokens_from_single_hash(
"sha1_git", target
)
)
if tokens:
content = list(
self._cql_runner.skipped_content_get_from_token(tokens[0])
)[0]
else:
content = None
if content:
for key in keys:
ret[key] = getattr(content, key)
return ret
def _directory_ls(
self, directory_id: Sha1Git, recursive: bool, prefix: bytes = b""
) -> Iterable[Dict[str, Any]]:
if self.directory_missing([directory_id]):
return
rows = list(self._cql_runner.directory_entry_get([directory_id]))
# TODO: dedup to be fast in case the directory contains the same subdir/file
# multiple times
contents = self._content_find_many([{"sha1_git": row.target} for row in rows])
for row in rows:
entry_d = row.to_dict()
# Build and yield the directory entry dict
del entry_d["directory_id"]
entry = DirectoryEntry.from_dict(entry_d)
ret = self._join_dentry_to_content(entry, contents)
ret["name"] = prefix + ret["name"]
ret["dir_id"] = directory_id
yield ret
if recursive and ret["type"] == "dir":
yield from self._directory_ls(
ret["target"], True, prefix + ret["name"] + b"/"
)
def directory_entry_get_by_path(
self, directory: Sha1Git, paths: List[bytes]
) -> Optional[Dict[str, Any]]:
return self._directory_entry_get_by_path(directory, paths, b"")
def _directory_entry_get_by_path(
self, directory: Sha1Git, paths: List[bytes], prefix: bytes
) -> Optional[Dict[str, Any]]:
if not paths:
return None
contents = list(self.directory_ls(directory))
if not contents:
return None
def _get_entry(entries, name):
"""Finds the entry with the requested name, prepends the
prefix (to get its full path), and returns it.
If no entry has that name, returns None."""
for entry in entries:
if entry["name"] == name:
entry = entry.copy()
entry["name"] = prefix + entry["name"]
return entry
first_item = _get_entry(contents, paths[0])
if len(paths) == 1:
return first_item
if not first_item or first_item["type"] != "dir":
return None
return self._directory_entry_get_by_path(
first_item["target"], paths[1:], prefix + paths[0] + b"/"
)
def directory_ls(
self, directory: Sha1Git, recursive: bool = False
) -> Iterable[Dict[str, Any]]:
yield from self._directory_ls(directory, recursive)
def directory_get_entries(
self,
directory_id: Sha1Git,
page_token: Optional[bytes] = None,
limit: int = 1000,
) -> Optional[PagedResult[DirectoryEntry]]:
if self.directory_missing([directory_id]):
return None
entries_from: bytes = page_token or b""
rows = self._cql_runner.directory_entry_get_from_name(
directory_id, entries_from, limit + 1
)
entries = [
DirectoryEntry.from_dict(remove_keys(row.to_dict(), ("directory_id",)))
for row in rows
]
if len(entries) > limit:
last_entry = entries.pop()
next_page_token = last_entry.name
else:
next_page_token = None
return PagedResult(results=entries, next_page_token=next_page_token)
def directory_get_raw_manifest(
self, directory_ids: List[Sha1Git]
) -> Dict[Sha1Git, Optional[bytes]]:
return {
dir_.id: dir_.raw_manifest
for dir_ in self._cql_runner.directory_get(directory_ids)
}
def directory_get_random(self) -> Sha1Git:
directory = self._cql_runner.directory_get_random()
assert directory, "Could not find any directory"
return directory.id
def revision_add(self, revisions: List[Revision]) -> Dict[str, int]:
# Filter-out revisions already in the database
if not self._allow_overwrite:
to_add = {r.id: r for r in revisions}.values()
missing = self.revision_missing([rev.id for rev in to_add])
revisions = [rev for rev in revisions if rev.id in missing]
self.journal_writer.revision_add(revisions)
for revision in revisions:
revobject = converters.revision_to_db(revision)
if revobject:
# Add parents first
for (rank, parent) in enumerate(revision.parents):
self._cql_runner.revision_parent_add_one(
RevisionParentRow(
id=revobject.id, parent_rank=rank, parent_id=parent
)
)
# Then write the main revision row.
# Writing this after all parents were written ensures that
# read endpoints don't return a partial view while writing
# the parents
self._cql_runner.revision_add_one(revobject)
return {"revision:add": len(revisions)}
def revision_missing(self, revisions: List[Sha1Git]) -> Iterable[Sha1Git]:
return self._cql_runner.revision_missing(revisions)
def revision_get(
self, revision_ids: List[Sha1Git], ignore_displayname: bool = False
) -> List[Optional[Revision]]:
rows = self._cql_runner.revision_get(revision_ids)
revisions: Dict[Sha1Git, Revision] = {}
for row in rows:
# TODO: use a single query to get all parents?
# (it might have lower latency, but requires more code and more
# bandwidth, because revision id would be part of each returned
# row)
parents = tuple(self._cql_runner.revision_parent_get(row.id))
# parent_rank is the clustering key, so results are already
# sorted by rank.
rev = converters.revision_from_db(row, parents=parents)
revisions[rev.id] = rev
return [revisions.get(rev_id) for rev_id in revision_ids]
def _get_parent_revs(
self,
rev_ids: Iterable[Sha1Git],
seen: Set[Sha1Git],
limit: Optional[int],
short: bool,
) -> Union[
- Iterable[Dict[str, Any]], Iterable[Tuple[Sha1Git, Tuple[Sha1Git, ...]]],
+ Iterable[Dict[str, Any]],
+ Iterable[Tuple[Sha1Git, Tuple[Sha1Git, ...]]],
]:
if limit and len(seen) >= limit:
return
rev_ids = [id_ for id_ in rev_ids if id_ not in seen]
if not rev_ids:
return
seen |= set(rev_ids)
# We need this query, even if short=True, to return consistent
# results (ie. not return only a subset of a revision's parents
# if it is being written)
if short:
ids = self._cql_runner.revision_get_ids(rev_ids)
for id_ in ids:
# TODO: use a single query to get all parents?
# (it might have less latency, but requires less code and more
# bandwidth (because revision id would be part of each returned
# row)
parents = tuple(self._cql_runner.revision_parent_get(id_))
# parent_rank is the clustering key, so results are already
# sorted by rank.
yield (id_, parents)
yield from self._get_parent_revs(parents, seen, limit, short)
else:
rows = self._cql_runner.revision_get(rev_ids)
for row in rows:
# TODO: use a single query to get all parents?
# (it might have less latency, but requires less code and more
# bandwidth (because revision id would be part of each returned
# row)
parents = tuple(self._cql_runner.revision_parent_get(row.id))
# parent_rank is the clustering key, so results are already
# sorted by rank.
rev = converters.revision_from_db(row, parents=parents)
yield rev.to_dict()
yield from self._get_parent_revs(parents, seen, limit, short)
def revision_log(
self,
revisions: List[Sha1Git],
ignore_displayname: bool = False,
limit: Optional[int] = None,
) -> Iterable[Optional[Dict[str, Any]]]:
seen: Set[Sha1Git] = set()
yield from self._get_parent_revs(revisions, seen, limit, False)
def revision_shortlog(
self, revisions: List[Sha1Git], limit: Optional[int] = None
) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]:
seen: Set[Sha1Git] = set()
yield from self._get_parent_revs(revisions, seen, limit, True)
def revision_get_random(self) -> Sha1Git:
revision = self._cql_runner.revision_get_random()
assert revision, "Could not find any revision"
return revision.id
def release_add(self, releases: List[Release]) -> Dict[str, int]:
if not self._allow_overwrite:
to_add = {r.id: r for r in releases}.values()
missing = set(self.release_missing([rel.id for rel in to_add]))
releases = [rel for rel in to_add if rel.id in missing]
self.journal_writer.release_add(releases)
for release in releases:
if release:
self._cql_runner.release_add_one(converters.release_to_db(release))
return {"release:add": len(releases)}
def release_missing(self, releases: List[Sha1Git]) -> Iterable[Sha1Git]:
return self._cql_runner.release_missing(releases)
def release_get(
self, releases: List[Sha1Git], ignore_displayname: bool = False
) -> List[Optional[Release]]:
rows = self._cql_runner.release_get(releases)
rels: Dict[Sha1Git, Release] = {}
for row in rows:
release = converters.release_from_db(row)
rels[row.id] = release
return [rels.get(rel_id) for rel_id in releases]
def release_get_random(self) -> Sha1Git:
release = self._cql_runner.release_get_random()
assert release, "Could not find any release"
return release.id
def snapshot_add(self, snapshots: List[Snapshot]) -> Dict[str, int]:
if not self._allow_overwrite:
to_add = {s.id: s for s in snapshots}.values()
missing = self._cql_runner.snapshot_missing([snp.id for snp in to_add])
snapshots = [snp for snp in snapshots if snp.id in missing]
for snapshot in snapshots:
self.journal_writer.snapshot_add([snapshot])
# Add branches
for (branch_name, branch) in snapshot.branches.items():
if branch is None:
target_type: Optional[str] = None
target: Optional[bytes] = None
else:
target_type = branch.target_type.value
target = branch.target
self._cql_runner.snapshot_branch_add_one(
SnapshotBranchRow(
snapshot_id=snapshot.id,
name=branch_name,
target_type=target_type,
target=target,
)
)
# Add the snapshot *after* adding all the branches, so someone
# calling snapshot_get_branch in the meantime won't end up
# with half the branches.
self._cql_runner.snapshot_add_one(SnapshotRow(id=snapshot.id))
return {"snapshot:add": len(snapshots)}
def snapshot_missing(self, snapshots: List[Sha1Git]) -> Iterable[Sha1Git]:
return self._cql_runner.snapshot_missing(snapshots)
def snapshot_get(self, snapshot_id: Sha1Git) -> Optional[Dict[str, Any]]:
d = self.snapshot_get_branches(snapshot_id)
if d is None:
return None
return {
"id": d["id"],
"branches": {
name: branch.to_dict() if branch else None
for (name, branch) in d["branches"].items()
},
"next_branch": d["next_branch"],
}
def snapshot_count_branches(
- self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None,
+ self,
+ snapshot_id: Sha1Git,
+ branch_name_exclude_prefix: Optional[bytes] = None,
) -> Optional[Dict[Optional[str], int]]:
if self._cql_runner.snapshot_missing([snapshot_id]):
# Makes sure we don't fetch branches for a snapshot that is
# being added.
return None
return self._cql_runner.snapshot_count_branches(
snapshot_id, branch_name_exclude_prefix
)
def snapshot_get_branches(
self,
snapshot_id: Sha1Git,
branches_from: bytes = b"",
branches_count: int = 1000,
target_types: Optional[List[str]] = None,
branch_name_include_substring: Optional[bytes] = None,
branch_name_exclude_prefix: Optional[bytes] = None,
) -> Optional[PartialBranches]:
if self._cql_runner.snapshot_missing([snapshot_id]):
# Makes sure we don't fetch branches for a snapshot that is
# being added.
return None
branches: List = []
while len(branches) < branches_count + 1:
new_branches = list(
self._cql_runner.snapshot_branch_get(
snapshot_id,
branches_from,
branches_count + 1,
branch_name_exclude_prefix,
)
)
if not new_branches:
break
branches_from = new_branches[-1].name
new_branches_filtered = new_branches
# Filter by target_type
if target_types:
new_branches_filtered = [
branch
for branch in new_branches_filtered
if branch.target is not None and branch.target_type in target_types
]
# Filter by branches_name_pattern
if branch_name_include_substring:
new_branches_filtered = [
branch
for branch in new_branches_filtered
if branch.name is not None
and (
branch_name_include_substring is None
or branch_name_include_substring in branch.name
)
]
branches.extend(new_branches_filtered)
if len(new_branches) < branches_count + 1:
break
if len(branches) > branches_count:
last_branch = branches.pop(-1).name
else:
last_branch = None
return PartialBranches(
id=snapshot_id,
branches={
branch.name: None
if branch.target is None
else SnapshotBranch(
target=branch.target, target_type=TargetType(branch.target_type)
)
for branch in branches
},
next_branch=last_branch,
)
def snapshot_get_random(self) -> Sha1Git:
snapshot = self._cql_runner.snapshot_get_random()
assert snapshot, "Could not find any snapshot"
return snapshot.id
def object_find_by_sha1_git(self, ids: List[Sha1Git]) -> Dict[Sha1Git, List[Dict]]:
results: Dict[Sha1Git, List[Dict]] = {id_: [] for id_ in ids}
missing_ids = set(ids)
# Mind the order, revision is the most likely one for a given ID,
# so we check revisions first.
queries: List[Tuple[str, Callable[[List[Sha1Git]], Iterable[Sha1Git]]]] = [
("revision", self._cql_runner.revision_missing),
("release", self._cql_runner.release_missing),
("content", self.content_missing_per_sha1_git),
("directory", self._cql_runner.directory_missing),
]
for (object_type, query_fn) in queries:
found_ids = missing_ids - set(query_fn(list(missing_ids)))
for sha1_git in found_ids:
results[sha1_git].append(
- {"sha1_git": sha1_git, "type": object_type,}
+ {
+ "sha1_git": sha1_git,
+ "type": object_type,
+ }
)
missing_ids.remove(sha1_git)
if not missing_ids:
# We found everything, skipping the next queries.
break
return results
def origin_get(self, origins: List[str]) -> Iterable[Optional[Origin]]:
return [self.origin_get_one(origin) for origin in origins]
def origin_get_one(self, origin_url: str) -> Optional[Origin]:
- """Given an origin url, return the origin if it exists, None otherwise
-
- """
+ """Given an origin url, return the origin if it exists, None otherwise"""
rows = list(self._cql_runner.origin_get_by_url(origin_url))
if rows:
assert len(rows) == 1
return Origin(url=rows[0].url)
else:
return None
def origin_get_by_sha1(self, sha1s: List[bytes]) -> List[Optional[Dict[str, Any]]]:
results = []
for sha1 in sha1s:
rows = list(self._cql_runner.origin_get_by_sha1(sha1))
origin = {"url": rows[0].url} if rows else None
results.append(origin)
return results
def origin_list(
self, page_token: Optional[str] = None, limit: int = 100
) -> PagedResult[Origin]:
# Compute what token to begin the listing from
start_token = TOKEN_BEGIN
if page_token:
start_token = int(page_token)
if not (TOKEN_BEGIN <= start_token <= TOKEN_END):
raise StorageArgumentException("Invalid page_token.")
next_page_token = None
origins = []
# Take one more origin so we can reuse it as the next page token if any
for (tok, row) in self._cql_runner.origin_list(start_token, limit + 1):
origins.append(Origin(url=row.url))
# keep reference of the last id for pagination purposes
last_id = tok
if len(origins) > limit:
# last origin id is the next page token
next_page_token = str(last_id)
# excluding that origin from the result to respect the limit size
origins = origins[:limit]
assert len(origins) <= limit
return PagedResult(results=origins, next_page_token=next_page_token)
def origin_search(
self,
url_pattern: str,
page_token: Optional[str] = None,
limit: int = 50,
regexp: bool = False,
with_visit: bool = False,
visit_types: Optional[List[str]] = None,
) -> PagedResult[Origin]:
# TODO: remove this endpoint, swh-search should be used instead.
next_page_token = None
offset = int(page_token) if page_token else 0
origin_rows = [row for row in self._cql_runner.origin_iter_all()]
if regexp:
pat = re.compile(url_pattern)
origin_rows = [row for row in origin_rows if pat.search(row.url)]
else:
origin_rows = [row for row in origin_rows if url_pattern in row.url]
if with_visit:
origin_rows = [row for row in origin_rows if row.next_visit_id > 1]
if visit_types:
def _has_visit_types(origin, visit_types):
for origin_visit in stream_results(self.origin_visit_get, origin):
if origin_visit.type in visit_types:
return True
return False
origin_rows = [
row for row in origin_rows if _has_visit_types(row.url, visit_types)
]
origins = [Origin(url=row.url) for row in origin_rows]
origins = origins[offset : offset + limit + 1]
if len(origins) > limit:
# next offset
next_page_token = str(offset + limit)
# excluding that origin from the result to respect the limit size
origins = origins[:limit]
assert len(origins) <= limit
return PagedResult(results=origins, next_page_token=next_page_token)
def origin_count(
self, url_pattern: str, regexp: bool = False, with_visit: bool = False
) -> int:
raise NotImplementedError(
"The Cassandra backend does not implement origin_count"
)
def origin_snapshot_get_all(self, origin_url: str) -> List[Sha1Git]:
return list(self._cql_runner.origin_snapshot_get_all(origin_url))
def origin_add(self, origins: List[Origin]) -> Dict[str, int]:
if not self._allow_overwrite:
to_add = {o.url: o for o in origins}.values()
origins = [ori for ori in to_add if self.origin_get_one(ori.url) is None]
self.journal_writer.origin_add(origins)
for origin in origins:
self._cql_runner.origin_add_one(
OriginRow(sha1=hash_url(origin.url), url=origin.url, next_visit_id=1)
)
return {"origin:add": len(origins)}
def origin_visit_add(self, visits: List[OriginVisit]) -> Iterable[OriginVisit]:
for visit in visits:
origin = self.origin_get_one(visit.origin)
if not origin: # Cannot add a visit without an origin
raise StorageArgumentException("Unknown origin %s", visit.origin)
all_visits = []
for visit in visits:
if visit.visit:
# Set origin.next_visit_id = max(origin.next_visit_id, visit.visit+1)
# so the next loader run does not reuse the id.
self._cql_runner.origin_bump_next_visit_id(visit.origin, visit.visit)
else:
visit_id = self._cql_runner.origin_generate_unique_visit_id(
visit.origin
)
visit = attr.evolve(visit, visit=visit_id)
self.journal_writer.origin_visit_add([visit])
self._cql_runner.origin_visit_add_one(OriginVisitRow(**visit.to_dict()))
assert visit.visit is not None
all_visits.append(visit)
self._origin_visit_status_add(
OriginVisitStatus(
origin=visit.origin,
visit=visit.visit,
date=visit.date,
type=visit.type,
status="created",
snapshot=None,
)
)
return all_visits
def _origin_visit_status_add(self, visit_status: OriginVisitStatus) -> None:
"""Add an origin visit status"""
if visit_status.type is None:
visit_row = self._cql_runner.origin_visit_get_one(
visit_status.origin, visit_status.visit
)
if visit_row is None:
raise StorageArgumentException(
f"Unknown origin visit {visit_status.visit} "
f"of origin {visit_status.origin}"
)
visit_status = attr.evolve(visit_status, type=visit_row.type)
self.journal_writer.origin_visit_status_add([visit_status])
self._cql_runner.origin_visit_status_add_one(
converters.visit_status_to_row(visit_status)
)
def origin_visit_status_add(
self, visit_statuses: List[OriginVisitStatus]
) -> Dict[str, int]:
# First round to check existence (fail early if any is ko)
for visit_status in visit_statuses:
origin_url = self.origin_get_one(visit_status.origin)
if not origin_url:
raise StorageArgumentException(f"Unknown origin {visit_status.origin}")
for visit_status in visit_statuses:
self._origin_visit_status_add(visit_status)
return {"origin_visit_status:add": len(visit_statuses)}
def _origin_visit_apply_status(
self, visit: Dict[str, Any], visit_status: OriginVisitStatusRow
) -> Dict[str, Any]:
"""Retrieve the latest visit status information for the origin visit.
Then merge it with the visit and return it.
"""
return {
# default to the values in visit
**visit,
# override with the last update
**visit_status.to_dict(),
# visit['origin'] is the URL (via a join), while
# visit_status['origin'] is only an id.
"origin": visit["origin"],
# but keep the date of the creation of the origin visit
"date": visit["date"],
# We use the visit type from origin visit
# if it's not present on the origin visit status
"type": visit_status.type or visit["type"],
}
def _origin_visit_get_latest_status(self, visit: OriginVisit) -> OriginVisitStatus:
- """Retrieve the latest visit status information for the origin visit object.
-
- """
+ """Retrieve the latest visit status information for the origin visit object."""
assert visit.visit
row = self._cql_runner.origin_visit_status_get_latest(visit.origin, visit.visit)
assert row is not None
visit_status = converters.row_to_visit_status(row)
return attr.evolve(visit_status, origin=visit.origin)
@staticmethod
def _format_origin_visit_row(visit):
return {
**visit.to_dict(),
"origin": visit.origin,
"date": visit.date.replace(tzinfo=datetime.timezone.utc),
}
def origin_visit_get(
self,
origin: str,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
) -> PagedResult[OriginVisit]:
if not isinstance(order, ListOrder):
raise StorageArgumentException("order must be a ListOrder value")
if page_token and not isinstance(page_token, str):
raise StorageArgumentException("page_token must be a string.")
next_page_token = None
visit_from = None if page_token is None else int(page_token)
visits: List[OriginVisit] = []
extra_limit = limit + 1
rows = self._cql_runner.origin_visit_get(origin, visit_from, extra_limit, order)
for row in rows:
visits.append(converters.row_to_visit(row))
assert len(visits) <= extra_limit
if len(visits) == extra_limit:
visits = visits[:limit]
next_page_token = str(visits[-1].visit)
return PagedResult(results=visits, next_page_token=next_page_token)
def origin_visit_get_with_statuses(
self,
origin: str,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
) -> PagedResult[OriginVisitWithStatuses]:
next_page_token = None
visit_from = None if page_token is None else int(page_token)
extra_limit = limit + 1
# First get visits (plus one so we can use it as the next page token if any)
rows = self._cql_runner.origin_visit_get(origin, visit_from, extra_limit, order)
visits: List[OriginVisit] = [converters.row_to_visit(row) for row in rows]
assert visits[0].visit is not None
assert visits[-1].visit is not None
visit_from = min(visits[0].visit, visits[-1].visit)
visit_to = max(visits[0].visit, visits[-1].visit)
# Then, fetch all statuses associated to these visits
statuses_rows = self._cql_runner.origin_visit_status_get_all_range(
origin, visit_from, visit_to
)
visit_statuses: Dict[int, List[OriginVisitStatus]] = defaultdict(list)
for status_row in statuses_rows:
if allowed_statuses and status_row.status not in allowed_statuses:
continue
if require_snapshot and status_row.snapshot is None:
continue
visit_status = converters.row_to_visit_status(status_row)
visit_statuses[visit_status.visit].append(visit_status)
# Add pagination if there are more visits
assert len(visits) <= extra_limit
if len(visits) == extra_limit:
# excluding that visit from the result to respect the limit size
visits = visits[:limit]
# last visit id is the next page token
next_page_token = str(visits[-1].visit)
results = [
OriginVisitWithStatuses(visit=visit, statuses=visit_statuses[visit.visit])
for visit in visits
if visit.visit is not None
]
return PagedResult(results=results, next_page_token=next_page_token)
def origin_visit_status_get(
self,
origin: str,
visit: int,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
) -> PagedResult[OriginVisitStatus]:
next_page_token = None
date_from = None
if page_token is not None:
date_from = datetime.datetime.fromisoformat(page_token)
# Take one more visit status so we can reuse it as the next page token if any
rows = self._cql_runner.origin_visit_status_get_range(
origin, visit, date_from, limit + 1, order
)
visit_statuses = [converters.row_to_visit_status(row) for row in rows]
if len(visit_statuses) > limit:
# last visit status date is the next page token
next_page_token = str(visit_statuses[-1].date)
# excluding that visit status from the result to respect the limit size
visit_statuses = visit_statuses[:limit]
return PagedResult(results=visit_statuses, next_page_token=next_page_token)
def origin_visit_find_by_date(
self, origin: str, visit_date: datetime.datetime
) -> Optional[OriginVisit]:
# Iterator over all the visits of the origin
# This should be ok for now, as there aren't too many visits
# per origin.
rows = list(self._cql_runner.origin_visit_iter_all(origin))
def key(visit):
dt = visit.date.replace(tzinfo=datetime.timezone.utc) - visit_date
return (abs(dt), -visit.visit)
if rows:
return converters.row_to_visit(min(rows, key=key))
return None
def origin_visit_get_by(self, origin: str, visit: int) -> Optional[OriginVisit]:
row = self._cql_runner.origin_visit_get_one(origin, visit)
if row:
return converters.row_to_visit(row)
return None
def origin_visit_get_latest(
self,
origin: str,
type: Optional[str] = None,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
) -> Optional[OriginVisit]:
if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES):
raise StorageArgumentException(
f"Unknown allowed statuses {','.join(allowed_statuses)}, only "
f"{','.join(VISIT_STATUSES)} authorized"
)
rows = self._cql_runner.origin_visit_iter_all(origin)
for row in rows:
visit = self._format_origin_visit_row(row)
for status_row in self._cql_runner.origin_visit_status_get(
origin, visit["visit"]
):
updated_visit = self._origin_visit_apply_status(visit, status_row)
if type is not None and updated_visit["type"] != type:
continue
if allowed_statuses and updated_visit["status"] not in allowed_statuses:
continue
if require_snapshot and updated_visit["snapshot"] is None:
continue
return OriginVisit(
origin=visit["origin"],
visit=visit["visit"],
date=visit["date"],
type=visit["type"],
)
return None
def origin_visit_status_get_latest(
self,
origin_url: str,
visit: int,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
) -> Optional[OriginVisitStatus]:
if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES):
raise StorageArgumentException(
f"Unknown allowed statuses {','.join(allowed_statuses)}, only "
f"{','.join(VISIT_STATUSES)} authorized"
)
rows = list(self._cql_runner.origin_visit_status_get(origin_url, visit))
# filtering is done python side as we cannot do it server side
if allowed_statuses:
rows = [row for row in rows if row.status in allowed_statuses]
if require_snapshot:
rows = [row for row in rows if row.snapshot is not None]
if not rows:
return None
return converters.row_to_visit_status(rows[0])
def origin_visit_status_get_random(self, type: str) -> Optional[OriginVisitStatus]:
back_in_the_day = now() - datetime.timedelta(weeks=12) # 3 months back
# Random position to start iteration at
start_token = random.randint(TOKEN_BEGIN, TOKEN_END)
# Iterator over all visits, ordered by token(origins) then visit_id
rows = self._cql_runner.origin_visit_iter(start_token)
for row in rows:
visit = converters.row_to_visit(row)
visit_status = self._origin_visit_get_latest_status(visit)
if visit.date > back_in_the_day and visit_status.status == "full":
return visit_status
return None
def stat_counters(self):
rows = self._cql_runner.stat_counters()
keys = (
"content",
"directory",
"origin",
"origin_visit",
"release",
"revision",
"skipped_content",
"snapshot",
)
stats = {key: 0 for key in keys}
stats.update({row.object_type: row.count for row in rows})
return stats
def refresh_stat_counters(self):
pass
def raw_extrinsic_metadata_add(
self, metadata: List[RawExtrinsicMetadata]
) -> Dict[str, int]:
self.journal_writer.raw_extrinsic_metadata_add(metadata)
counter = Counter[ExtendedObjectType]()
for metadata_entry in metadata:
if not self._cql_runner.metadata_authority_get(
metadata_entry.authority.type.value, metadata_entry.authority.url
):
raise StorageArgumentException(
f"Unknown authority {metadata_entry.authority}"
)
if not self._cql_runner.metadata_fetcher_get(
metadata_entry.fetcher.name, metadata_entry.fetcher.version
):
raise StorageArgumentException(
f"Unknown fetcher {metadata_entry.fetcher}"
)
try:
row = RawExtrinsicMetadataRow(
id=metadata_entry.id,
type=metadata_entry.target.object_type.name.lower(),
target=str(metadata_entry.target),
authority_type=metadata_entry.authority.type.value,
authority_url=metadata_entry.authority.url,
discovery_date=metadata_entry.discovery_date,
fetcher_name=metadata_entry.fetcher.name,
fetcher_version=metadata_entry.fetcher.version,
format=metadata_entry.format,
metadata=metadata_entry.metadata,
origin=metadata_entry.origin,
visit=metadata_entry.visit,
snapshot=map_optional(str, metadata_entry.snapshot),
release=map_optional(str, metadata_entry.release),
revision=map_optional(str, metadata_entry.revision),
path=metadata_entry.path,
directory=map_optional(str, metadata_entry.directory),
)
except TypeError as e:
raise StorageArgumentException(*e.args)
# Add to the index first
self._cql_runner.raw_extrinsic_metadata_by_id_add(
RawExtrinsicMetadataByIdRow(
id=row.id,
target=row.target,
authority_type=row.authority_type,
authority_url=row.authority_url,
)
)
# Then to the main table
self._cql_runner.raw_extrinsic_metadata_add(row)
counter[metadata_entry.target.object_type] += 1
return {
f"{type.value}_metadata:add": count for (type, count) in counter.items()
}
def raw_extrinsic_metadata_get(
self,
target: ExtendedSWHID,
authority: MetadataAuthority,
after: Optional[datetime.datetime] = None,
page_token: Optional[bytes] = None,
limit: int = 1000,
) -> PagedResult[RawExtrinsicMetadata]:
if page_token is not None:
(after_date, id_) = msgpack_loads(base64.b64decode(page_token))
if after and after_date < after:
raise StorageArgumentException(
"page_token is inconsistent with the value of 'after'."
)
entries = self._cql_runner.raw_extrinsic_metadata_get_after_date_and_id(
- str(target), authority.type.value, authority.url, after_date, id_,
+ str(target),
+ authority.type.value,
+ authority.url,
+ after_date,
+ id_,
)
elif after is not None:
entries = self._cql_runner.raw_extrinsic_metadata_get_after_date(
str(target), authority.type.value, authority.url, after
)
else:
entries = self._cql_runner.raw_extrinsic_metadata_get(
str(target), authority.type.value, authority.url
)
if limit:
entries = itertools.islice(entries, 0, limit + 1)
results = []
for entry in entries:
assert str(target) == entry.target
results.append(converters.row_to_raw_extrinsic_metadata(entry))
if len(results) > limit:
results.pop()
assert len(results) == limit
last_result = results[-1]
next_page_token: Optional[str] = base64.b64encode(
- msgpack_dumps((last_result.discovery_date, last_result.id,))
+ msgpack_dumps(
+ (
+ last_result.discovery_date,
+ last_result.id,
+ )
+ )
).decode()
else:
next_page_token = None
- return PagedResult(next_page_token=next_page_token, results=results,)
+ return PagedResult(
+ next_page_token=next_page_token,
+ results=results,
+ )
def raw_extrinsic_metadata_get_by_ids(
self, ids: List[Sha1Git]
) -> List[RawExtrinsicMetadata]:
keys = self._cql_runner.raw_extrinsic_metadata_get_by_ids(ids)
results: Set[RawExtrinsicMetadata] = set()
for key in keys:
candidates = self._cql_runner.raw_extrinsic_metadata_get(
key.target, key.authority_type, key.authority_url
)
candidates = [
candidate for candidate in candidates if candidate.id == key.id
]
if len(candidates) > 1:
raise Exception(
"Found multiple RawExtrinsicMetadata objects with the same id: "
+ hash_to_hex(key.id)
)
results.update(map(converters.row_to_raw_extrinsic_metadata, candidates))
return list(results)
def raw_extrinsic_metadata_get_authorities(
self, target: ExtendedSWHID
) -> List[MetadataAuthority]:
return [
MetadataAuthority(
type=MetadataAuthorityType(authority_type), url=authority_url
)
for (authority_type, authority_url) in set(
self._cql_runner.raw_extrinsic_metadata_get_authorities(str(target))
)
]
def metadata_fetcher_add(self, fetchers: List[MetadataFetcher]) -> Dict[str, int]:
self.journal_writer.metadata_fetcher_add(fetchers)
for fetcher in fetchers:
self._cql_runner.metadata_fetcher_add(
- MetadataFetcherRow(name=fetcher.name, version=fetcher.version,)
+ MetadataFetcherRow(
+ name=fetcher.name,
+ version=fetcher.version,
+ )
)
return {"metadata_fetcher:add": len(fetchers)}
def metadata_fetcher_get(
self, name: str, version: str
) -> Optional[MetadataFetcher]:
fetcher = self._cql_runner.metadata_fetcher_get(name, version)
if fetcher:
- return MetadataFetcher(name=fetcher.name, version=fetcher.version,)
+ return MetadataFetcher(
+ name=fetcher.name,
+ version=fetcher.version,
+ )
else:
return None
def metadata_authority_add(
self, authorities: List[MetadataAuthority]
) -> Dict[str, int]:
self.journal_writer.metadata_authority_add(authorities)
for authority in authorities:
self._cql_runner.metadata_authority_add(
- MetadataAuthorityRow(url=authority.url, type=authority.type.value,)
+ MetadataAuthorityRow(
+ url=authority.url,
+ type=authority.type.value,
+ )
)
return {"metadata_authority:add": len(authorities)}
def metadata_authority_get(
self, type: MetadataAuthorityType, url: str
) -> Optional[MetadataAuthority]:
authority = self._cql_runner.metadata_authority_get(type.value, url)
if authority:
return MetadataAuthority(
- type=MetadataAuthorityType(authority.type), url=authority.url,
+ type=MetadataAuthorityType(authority.type),
+ url=authority.url,
)
else:
return None
# ExtID tables
def extid_add(self, ids: List[ExtID]) -> Dict[str, int]:
if not self._allow_overwrite:
extids = [
extid
for extid in ids
if not self._cql_runner.extid_get_from_pk(
extid_type=extid.extid_type,
extid_version=extid.extid_version,
extid=extid.extid,
target=extid.target,
)
]
else:
extids = list(ids)
self.journal_writer.extid_add(extids)
inserted = 0
for extid in extids:
target_type = extid.target.object_type.value
target = extid.target.object_id
extid_version = extid.extid_version
extid_type = extid.extid_type
extidrow = ExtIDRow(
extid_type=extid_type,
extid_version=extid_version,
extid=extid.extid,
target_type=target_type,
target=target,
)
(token, insertion_finalizer) = self._cql_runner.extid_add_prepare(extidrow)
indexrow = ExtIDByTargetRow(
- target_type=target_type, target=target, target_token=token,
+ target_type=target_type,
+ target=target,
+ target_token=token,
)
self._cql_runner.extid_index_add_one(indexrow)
insertion_finalizer()
inserted += 1
return {"extid:add": inserted}
def extid_get_from_extid(
self, id_type: str, ids: List[bytes], version: Optional[int] = None
) -> List[ExtID]:
result: List[ExtID] = []
for extid in ids:
if version is not None:
extidrows = self._cql_runner.extid_get_from_extid_and_version(
id_type, extid, version
)
else:
extidrows = self._cql_runner.extid_get_from_extid(id_type, extid)
result.extend(
ExtID(
extid_type=extidrow.extid_type,
extid_version=extidrow.extid_version,
extid=extidrow.extid,
target=CoreSWHID(
- object_type=extidrow.target_type, object_id=extidrow.target,
+ object_type=extidrow.target_type,
+ object_id=extidrow.target,
),
)
for extidrow in extidrows
)
return result
def extid_get_from_target(
self,
target_type: SwhidObjectType,
ids: List[Sha1Git],
extid_type: Optional[str] = None,
extid_version: Optional[int] = None,
) -> List[ExtID]:
if (extid_version is not None and extid_type is None) or (
extid_version is None and extid_type is not None
):
raise ValueError("You must provide both extid_type and extid_version")
result: List[ExtID] = []
for target in ids:
extidrows = self._cql_runner.extid_get_from_target(
target_type.value,
target,
extid_type=extid_type,
extid_version=extid_version,
)
result.extend(
ExtID(
extid_type=extidrow.extid_type,
extid_version=extidrow.extid_version,
extid=extidrow.extid,
target=CoreSWHID(
object_type=SwhidObjectType(extidrow.target_type),
object_id=extidrow.target,
),
)
for extidrow in extidrows
)
return result
# Misc
def clear_buffers(self, object_types: Sequence[str] = ()) -> None:
- """Do nothing
-
- """
+ """Do nothing"""
return None
def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]:
return {}
diff --git a/swh/storage/cli.py b/swh/storage/cli.py
index f793c929..624c6b88 100644
--- a/swh/storage/cli.py
+++ b/swh/storage/cli.py
@@ -1,306 +1,309 @@
# Copyright (C) 2015-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# WARNING: do not import unnecessary things here to keep cli startup time under
# control
import logging
import os
from typing import Dict, Optional
import click
from swh.core.cli import CONTEXT_SETTINGS
from swh.core.cli import swh as swh_cli_group
from swh.storage.replay import ModelObjectDeserializer
try:
from systemd.daemon import notify
except ImportError:
notify = None
@swh_cli_group.group(name="storage", context_settings=CONTEXT_SETTINGS)
@click.option(
"--config-file",
"-C",
default=None,
- type=click.Path(exists=True, dir_okay=False,),
+ type=click.Path(
+ exists=True,
+ dir_okay=False,
+ ),
help="Configuration file.",
)
@click.option(
"--check-config",
default=None,
type=click.Choice(["no", "read", "write"]),
help=(
"Check the configuration of the storage at startup for read or write access; "
"if set, override the value present in the configuration file if any. "
"Defaults to 'read' for the 'backfill' command, and 'write' for 'rpc-server' "
"and 'replay' commands."
),
)
@click.pass_context
def storage(ctx, config_file, check_config):
"""Software Heritage Storage tools."""
from swh.core import config
if not config_file:
config_file = os.environ.get("SWH_CONFIG_FILENAME")
if config_file:
if not os.path.exists(config_file):
raise ValueError("%s does not exist" % config_file)
conf = config.read(config_file)
else:
conf = {}
if "storage" not in conf:
ctx.fail("You must have a storage configured in your config file.")
ctx.ensure_object(dict)
ctx.obj["config"] = conf
ctx.obj["check_config"] = check_config
@storage.command(name="rpc-serve")
@click.option(
"--host",
default="0.0.0.0",
metavar="IP",
show_default=True,
help="Host ip address to bind the server on",
)
@click.option(
"--port",
default=5002,
type=click.INT,
metavar="PORT",
show_default=True,
help="Binding port of the server",
)
@click.option(
"--debug/--no-debug",
default=True,
help="Indicates if the server should run in debug mode",
)
@click.pass_context
def serve(ctx, host, port, debug):
"""Software Heritage Storage RPC server.
Do NOT use this in a production environment.
"""
from swh.storage.api.server import app
if "log_level" in ctx.obj:
logging.getLogger("werkzeug").setLevel(ctx.obj["log_level"])
ensure_check_config(ctx.obj["config"], ctx.obj["check_config"], "write")
app.config.update(ctx.obj["config"])
app.run(host, port=int(port), debug=bool(debug))
@storage.command()
@click.argument("object_type")
@click.option("--start-object", default=None)
@click.option("--end-object", default=None)
@click.option("--dry-run", is_flag=True, default=False)
@click.pass_context
def backfill(ctx, object_type, start_object, end_object, dry_run):
"""Run the backfiller
The backfiller list objects from a Storage and produce journal entries from
there.
Typically used to rebuild a journal or compensate for missing objects in a
journal (eg. due to a downtime of this later).
The configuration file requires the following entries:
- brokers: a list of kafka endpoints (the journal) in which entries will be
added.
- storage_dbconn: URL to connect to the storage DB.
- prefix: the prefix of the topics (topics will be .).
- client_id: the kafka client ID.
"""
ensure_check_config(ctx.obj["config"], ctx.obj["check_config"], "read")
# for "lazy" loading
from swh.storage.backfill import JournalBackfiller
try:
from systemd.daemon import notify
except ImportError:
notify = None
conf = ctx.obj["config"]
backfiller = JournalBackfiller(conf)
if notify:
notify("READY=1")
try:
backfiller.run(
object_type=object_type,
start_object=start_object,
end_object=end_object,
dry_run=dry_run,
)
except KeyboardInterrupt:
if notify:
notify("STOPPING=1")
ctx.exit(0)
@storage.command()
@click.option(
"--stop-after-objects",
"-n",
default=None,
type=int,
help="Stop after processing this many objects. Default is to " "run forever.",
)
@click.option(
"--type",
"-t",
"object_types",
default=[],
type=click.Choice(
# use a hardcoded list to prevent having to load the
# replay module at cli loading time
[
"origin",
"origin_visit",
"origin_visit_status",
"snapshot",
"revision",
"release",
"directory",
"content",
"skipped_content",
"metadata_authority",
"metadata_fetcher",
"raw_extrinsic_metadata",
"extid",
]
),
help="Object types to replay",
multiple=True,
)
@click.pass_context
def replay(ctx, stop_after_objects, object_types):
"""Fill a Storage by reading a Journal.
This is typically used for a mirror configuration, reading the Software
Heritage kafka journal to retrieve objects of the Software Heritage main
storage to feed a replication storage. There can be several 'replayers'
filling a Storage as long as they use the same `group-id`.
The expected configuration file should have 2 sections:
- storage: the configuration of the storage in which to add objects
received from the kafka journal,
- journal_client: the configuration of access to the kafka journal. See the
documentation of `swh.journal` for more details on the possible
configuration entries in this section.
https://docs.softwareheritage.org/devel/apidoc/swh.journal.client.html
In addition to these 2 mandatory config sections, a third 'replayer' may be
specified with a 'error_reporter' config entry allowing to specify redis
connection parameters that will be used to report non-recoverable mirroring,
eg.::
storage:
[...]
journal_client:
[...]
replayer:
error_reporter:
host: redis.local
port: 6379
db: 1
"""
import functools
from swh.journal.client import get_journal_client
from swh.storage import get_storage
from swh.storage.replay import process_replay_objects
ensure_check_config(ctx.obj["config"], ctx.obj["check_config"], "write")
conf = ctx.obj["config"]
storage = get_storage(**conf.pop("storage"))
client_cfg = conf.pop("journal_client")
replayer_cfg = conf.pop("replayer", {})
if "error_reporter" in replayer_cfg:
from redis import Redis
reporter = Redis(**replayer_cfg.get("error_reporter")).set
else:
reporter = None
validate = client_cfg.get("privileged", False)
if not validate and reporter:
ctx.fail(
"Invalid configuration: you cannot have 'error_reporter' set if "
"'privileged' is False; we cannot validate anonymized objects."
)
deserializer = ModelObjectDeserializer(reporter=reporter, validate=validate)
client_cfg["value_deserializer"] = deserializer.convert
if object_types:
client_cfg["object_types"] = object_types
if stop_after_objects:
client_cfg["stop_after_objects"] = stop_after_objects
try:
client = get_journal_client(**client_cfg)
except ValueError as exc:
ctx.fail(exc)
worker_fn = functools.partial(process_replay_objects, storage=storage)
if notify:
notify("READY=1")
try:
client.process(worker_fn)
except KeyboardInterrupt:
ctx.exit(0)
else:
print("Done.")
finally:
if notify:
notify("STOPPING=1")
client.close()
def ensure_check_config(storage_cfg: Dict, check_config: Optional[str], default: str):
"""Helper function to inject the setting of check_config option in the storage config
dict according to the expected default value (default value depends on the command,
eg. backfill can be read-only).
"""
if check_config is not None:
if check_config == "no":
storage_cfg.pop("check_config", None)
else:
storage_cfg["check_config"] = {"check_write": check_config == "write"}
else:
if "check_config" not in storage_cfg:
storage_cfg["check_config"] = {"check_write": default == "write"}
def main():
logging.basicConfig()
return serve(auto_envvar_prefix="SWH_STORAGE")
if __name__ == "__main__":
main()
diff --git a/swh/storage/exc.py b/swh/storage/exc.py
index d15765f6..633195c3 100644
--- a/swh/storage/exc.py
+++ b/swh/storage/exc.py
@@ -1,49 +1,43 @@
# Copyright (C) 2015-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from typing import Dict, List
from swh.model.hashutil import hash_to_hex
from swh.storage.utils import content_bytes_hashes, content_hex_hashes
class StorageDBError(Exception):
- """Specific storage db error (connection, erroneous queries, etc...)
-
- """
+ """Specific storage db error (connection, erroneous queries, etc...)"""
def __str__(self):
return "An unexpected error occurred in the backend: %s" % self.args
class StorageAPIError(Exception):
- """Specific internal storage api (mainly connection)
-
- """
+ """Specific internal storage api (mainly connection)"""
def __str__(self):
args = self.args
return "An unexpected error occurred in the api backend: %s" % args
class StorageArgumentException(Exception):
"""Argument passed to a Storage endpoint is invalid."""
pass
class HashCollision(Exception):
- """Exception raised when a content collides in a storage backend
-
- """
+ """Exception raised when a content collides in a storage backend"""
def __init__(self, algo, hash_id, colliding_contents):
self.algo = algo
self.hash_id = hash_to_hex(hash_id)
self.colliding_contents = [content_hex_hashes(c) for c in colliding_contents]
super().__init__(self.algo, self.hash_id, self.colliding_contents)
def colliding_content_hashes(self) -> List[Dict[str, bytes]]:
return [content_bytes_hashes(c) for c in self.colliding_contents]
diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py
index 557c6dce..ddcd53b6 100644
--- a/swh/storage/in_memory.py
+++ b/swh/storage/in_memory.py
@@ -1,820 +1,842 @@
# Copyright (C) 2015-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from collections import defaultdict
import datetime
import functools
import itertools
import random
from typing import (
Any,
Dict,
Generic,
Iterable,
Iterator,
List,
Optional,
Tuple,
Type,
TypeVar,
Union,
)
from swh.model.model import Content, Sha1Git, SkippedContent
from swh.model.swhids import ExtendedSWHID
from swh.storage.cassandra import CassandraStorage
from swh.storage.cassandra.model import (
BaseRow,
ContentRow,
DirectoryEntryRow,
DirectoryRow,
ExtIDByTargetRow,
ExtIDRow,
MetadataAuthorityRow,
MetadataFetcherRow,
ObjectCountRow,
OriginRow,
OriginVisitRow,
OriginVisitStatusRow,
RawExtrinsicMetadataByIdRow,
RawExtrinsicMetadataRow,
ReleaseRow,
RevisionParentRow,
RevisionRow,
SkippedContentRow,
SnapshotBranchRow,
SnapshotRow,
)
from swh.storage.interface import ListOrder
from swh.storage.objstorage import ObjStorage
from .common import origin_url_to_sha1
from .writer import JournalWriter
TRow = TypeVar("TRow", bound=BaseRow)
class Table(Generic[TRow]):
def __init__(self, row_class: Type[TRow]):
self.row_class = row_class
self.primary_key_cols = row_class.PARTITION_KEY + row_class.CLUSTERING_KEY
# Map from tokens to clustering keys to rows
# These are not actually partitions (or rather, there is one partition
# for each token) and they aren't sorted.
# But it is good enough if we don't care about performance;
# and makes the code a lot simpler.
self.data: Dict[int, Dict[Tuple, TRow]] = defaultdict(dict)
def __repr__(self):
return f"<__module__.Table[{self.row_class.__name__}] object>"
def partition_key(self, row: Union[TRow, Dict[str, Any]]) -> Tuple:
"""Returns the partition key of a row (ie. the cells which get hashed
into the token."""
if isinstance(row, dict):
row_d = row
else:
row_d = row.to_dict()
return tuple(row_d[col] for col in self.row_class.PARTITION_KEY)
def clustering_key(self, row: Union[TRow, Dict[str, Any]]) -> Tuple:
"""Returns the clustering key of a row (ie. the cells which are used
for sorting rows within a partition."""
if isinstance(row, dict):
row_d = row
else:
row_d = row.to_dict()
return tuple(row_d[col] for col in self.row_class.CLUSTERING_KEY)
def primary_key(self, row):
return self.partition_key(row) + self.clustering_key(row)
def primary_key_from_dict(self, d: Dict[str, Any]) -> Tuple:
"""Returns the primary key (ie. concatenation of partition key and
clustering key) of the given dictionary interpreted as a row."""
return tuple(d[col] for col in self.primary_key_cols)
def token(self, key: Tuple):
"""Returns the token of a row (ie. the hash of its partition key)."""
return hash(key)
def get_partition(self, token: int) -> Dict[Tuple, TRow]:
"""Returns the partition that contains this token."""
return self.data[token]
def insert(self, row: TRow):
partition = self.data[self.token(self.partition_key(row))]
partition[self.clustering_key(row)] = row
def split_primary_key(self, key: Tuple) -> Tuple[Tuple, Tuple]:
"""Returns (partition_key, clustering_key) from a partition key"""
assert len(key) == len(self.primary_key_cols)
partition_key = key[0 : len(self.row_class.PARTITION_KEY)]
clustering_key = key[len(self.row_class.PARTITION_KEY) :]
return (partition_key, clustering_key)
def get_from_partition_key(self, partition_key: Tuple) -> Iterable[TRow]:
"""Returns at most one row, from its partition key."""
token = self.token(partition_key)
for row in self.get_from_token(token):
if self.partition_key(row) == partition_key:
yield row
def get_from_primary_key(self, primary_key: Tuple) -> Optional[TRow]:
"""Returns at most one row, from its primary key."""
(partition_key, clustering_key) = self.split_primary_key(primary_key)
token = self.token(partition_key)
partition = self.get_partition(token)
return partition.get(clustering_key)
def get_from_token(self, token: int) -> Iterable[TRow]:
"""Returns all rows whose token (ie. non-cryptographic hash of the
partition key) is the one passed as argument."""
return (v for (k, v) in sorted(self.get_partition(token).items()))
def iter_all(self) -> Iterator[Tuple[Tuple, TRow]]:
return (
(self.primary_key(row), row)
for (token, partition) in self.data.items()
for (clustering_key, row) in partition.items()
)
def get_random(self) -> Optional[TRow]:
return random.choice([row for (pk, row) in self.iter_all()])
class InMemoryCqlRunner:
def __init__(self):
self._contents = Table(ContentRow)
self._content_indexes = defaultdict(lambda: defaultdict(set))
self._skipped_contents = Table(ContentRow)
self._skipped_content_indexes = defaultdict(lambda: defaultdict(set))
self._directories = Table(DirectoryRow)
self._directory_entries = Table(DirectoryEntryRow)
self._revisions = Table(RevisionRow)
self._revision_parents = Table(RevisionParentRow)
self._releases = Table(ReleaseRow)
self._snapshots = Table(SnapshotRow)
self._snapshot_branches = Table(SnapshotBranchRow)
self._origins = Table(OriginRow)
self._origin_visits = Table(OriginVisitRow)
self._origin_visit_statuses = Table(OriginVisitStatusRow)
self._metadata_authorities = Table(MetadataAuthorityRow)
self._metadata_fetchers = Table(MetadataFetcherRow)
self._raw_extrinsic_metadata = Table(RawExtrinsicMetadataRow)
self._raw_extrinsic_metadata_by_id = Table(RawExtrinsicMetadataByIdRow)
self._extid = Table(ExtIDRow)
self._stat_counters = defaultdict(int)
def increment_counter(self, object_type: str, nb: int):
self._stat_counters[object_type] += nb
def stat_counters(self) -> Iterable[ObjectCountRow]:
for (object_type, count) in self._stat_counters.items():
yield ObjectCountRow(partition_key=0, object_type=object_type, count=count)
##########################
# 'content' table
##########################
def _content_add_finalize(self, content: ContentRow) -> None:
self._contents.insert(content)
self.increment_counter("content", 1)
def content_add_prepare(self, content: ContentRow):
finalizer = functools.partial(self._content_add_finalize, content)
return (self._contents.token(self._contents.partition_key(content)), finalizer)
def content_get_from_pk(
self, content_hashes: Dict[str, bytes]
) -> Optional[ContentRow]:
primary_key = self._contents.primary_key_from_dict(content_hashes)
return self._contents.get_from_primary_key(primary_key)
def content_get_from_tokens(self, tokens: List[int]) -> Iterable[ContentRow]:
return itertools.chain.from_iterable(map(self._contents.get_from_token, tokens))
def content_get_random(self) -> Optional[ContentRow]:
return self._contents.get_random()
def content_get_token_range(
- self, start: int, end: int, limit: int,
+ self,
+ start: int,
+ end: int,
+ limit: int,
) -> Iterable[Tuple[int, ContentRow]]:
matches = [
(token, row)
for (token, partition) in self._contents.data.items()
for (clustering_key, row) in partition.items()
if start <= token <= end
]
matches.sort()
return matches[0:limit]
def content_missing_from_all_hashes(
self, contents_hashes: List[Dict[str, bytes]]
) -> Iterator[Dict[str, bytes]]:
for content_hashes in contents_hashes:
if not self.content_get_from_pk(content_hashes):
yield content_hashes
##########################
# 'content_by_*' tables
##########################
def content_missing_by_sha1_git(self, ids: List[bytes]) -> List[bytes]:
missing = []
for id_ in ids:
if id_ not in self._content_indexes["sha1_git"]:
missing.append(id_)
return missing
def content_index_add_one(self, algo: str, content: Content, token: int) -> None:
self._content_indexes[algo][content.get_hash(algo)].add(token)
def content_get_tokens_from_single_algo(
self, algo: str, hashes: List[bytes]
) -> Iterable[int]:
for hash_ in hashes:
yield from self._content_indexes[algo][hash_]
##########################
# 'skipped_content' table
##########################
def _skipped_content_add_finalize(self, content: SkippedContentRow) -> None:
self._skipped_contents.insert(content)
self.increment_counter("skipped_content", 1)
def skipped_content_add_prepare(self, content: SkippedContentRow):
finalizer = functools.partial(self._skipped_content_add_finalize, content)
return (
self._skipped_contents.token(self._contents.partition_key(content)),
finalizer,
)
def skipped_content_get_from_pk(
self, content_hashes: Dict[str, bytes]
) -> Optional[SkippedContentRow]:
primary_key = self._skipped_contents.primary_key_from_dict(content_hashes)
return self._skipped_contents.get_from_primary_key(primary_key)
def skipped_content_get_from_token(self, token: int) -> Iterable[SkippedContentRow]:
return self._skipped_contents.get_from_token(token)
##########################
# 'skipped_content_by_*' tables
##########################
def skipped_content_index_add_one(
self, algo: str, content: SkippedContent, token: int
) -> None:
self._skipped_content_indexes[algo][content.get_hash(algo)].add(token)
def skipped_content_get_tokens_from_single_hash(
self, algo: str, hash_: bytes
) -> Iterable[int]:
return self._skipped_content_indexes[algo][hash_]
##########################
# 'directory' table
##########################
def directory_missing(self, ids: List[bytes]) -> List[bytes]:
missing = []
for id_ in ids:
if self._directories.get_from_primary_key((id_,)) is None:
missing.append(id_)
return missing
def directory_add_one(self, directory: DirectoryRow) -> None:
self._directories.insert(directory)
self.increment_counter("directory", 1)
def directory_get_random(self) -> Optional[DirectoryRow]:
return self._directories.get_random()
def directory_get(self, directory_ids: List[Sha1Git]) -> Iterable[DirectoryRow]:
for id_ in directory_ids:
row = self._directories.get_from_primary_key((id_,))
if row:
yield row
##########################
# 'directory_entry' table
##########################
def directory_entry_add_one(self, entry: DirectoryEntryRow) -> None:
self._directory_entries.insert(entry)
def directory_entry_get(
self, directory_ids: List[Sha1Git]
) -> Iterable[DirectoryEntryRow]:
for id_ in directory_ids:
yield from self._directory_entries.get_from_partition_key((id_,))
def directory_entry_get_from_name(
self, directory_id: Sha1Git, from_: bytes, limit: int
) -> Iterable[DirectoryEntryRow]:
# Get all entries
entries = self._directory_entries.get_from_partition_key((directory_id,))
# Filter out the ones before from_
entries = itertools.dropwhile(lambda entry: entry.name < from_, entries)
# Apply limit
return itertools.islice(entries, limit)
##########################
# 'revision' table
##########################
def revision_missing(self, ids: List[bytes]) -> Iterable[bytes]:
missing = []
for id_ in ids:
if self._revisions.get_from_primary_key((id_,)) is None:
missing.append(id_)
return missing
def revision_add_one(self, revision: RevisionRow) -> None:
self._revisions.insert(revision)
self.increment_counter("revision", 1)
def revision_get_ids(self, revision_ids) -> Iterable[int]:
for id_ in revision_ids:
if self._revisions.get_from_primary_key((id_,)) is not None:
yield id_
def revision_get(
self, revision_ids: List[Sha1Git], ignore_displayname: bool = False
) -> Iterable[RevisionRow]:
for id_ in revision_ids:
row = self._revisions.get_from_primary_key((id_,))
if row:
yield row
def revision_get_random(self) -> Optional[RevisionRow]:
return self._revisions.get_random()
##########################
# 'revision_parent' table
##########################
def revision_parent_add_one(self, revision_parent: RevisionParentRow) -> None:
self._revision_parents.insert(revision_parent)
def revision_parent_get(self, revision_id: Sha1Git) -> Iterable[bytes]:
for parent in self._revision_parents.get_from_partition_key((revision_id,)):
yield parent.parent_id
##########################
# 'release' table
##########################
def release_missing(self, ids: List[bytes]) -> List[bytes]:
missing = []
for id_ in ids:
if self._releases.get_from_primary_key((id_,)) is None:
missing.append(id_)
return missing
def release_add_one(self, release: ReleaseRow) -> None:
self._releases.insert(release)
self.increment_counter("release", 1)
def release_get(
self, release_ids: List[str], ignore_displayname: bool = False
) -> Iterable[ReleaseRow]:
for id_ in release_ids:
row = self._releases.get_from_primary_key((id_,))
if row:
yield row
def release_get_random(self) -> Optional[ReleaseRow]:
return self._releases.get_random()
##########################
# 'snapshot' table
##########################
def snapshot_missing(self, ids: List[bytes]) -> List[bytes]:
missing = []
for id_ in ids:
if self._snapshots.get_from_primary_key((id_,)) is None:
missing.append(id_)
return missing
def snapshot_add_one(self, snapshot: SnapshotRow) -> None:
self._snapshots.insert(snapshot)
self.increment_counter("snapshot", 1)
def snapshot_get_random(self) -> Optional[SnapshotRow]:
return self._snapshots.get_random()
##########################
# 'snapshot_branch' table
##########################
def snapshot_branch_add_one(self, branch: SnapshotBranchRow) -> None:
self._snapshot_branches.insert(branch)
def snapshot_count_branches(
- self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None,
+ self,
+ snapshot_id: Sha1Git,
+ branch_name_exclude_prefix: Optional[bytes] = None,
) -> Dict[Optional[str], int]:
"""Returns a dictionary from type names to the number of branches
of that type."""
counts: Dict[Optional[str], int] = defaultdict(int)
for branch in self._snapshot_branches.get_from_partition_key((snapshot_id,)):
if branch_name_exclude_prefix and branch.name.startswith(
branch_name_exclude_prefix
):
continue
if branch.target_type is None:
target_type = None
else:
target_type = branch.target_type
counts[target_type] += 1
return counts
def snapshot_branch_get(
self,
snapshot_id: Sha1Git,
from_: bytes,
limit: int,
branch_name_exclude_prefix: Optional[bytes] = None,
) -> Iterable[SnapshotBranchRow]:
count = 0
for branch in self._snapshot_branches.get_from_partition_key((snapshot_id,)):
prefix = branch_name_exclude_prefix
if branch.name >= from_ and (
prefix is None or not branch.name.startswith(prefix)
):
count += 1
yield branch
if count >= limit:
break
##########################
# 'origin' table
##########################
def origin_add_one(self, origin: OriginRow) -> None:
self._origins.insert(origin)
self.increment_counter("origin", 1)
def origin_get_by_sha1(self, sha1: bytes) -> Iterable[OriginRow]:
return self._origins.get_from_partition_key((sha1,))
def origin_get_by_url(self, url: str) -> Iterable[OriginRow]:
return self.origin_get_by_sha1(origin_url_to_sha1(url))
def origin_list(
self, start_token: int, limit: int
) -> Iterable[Tuple[int, OriginRow]]:
"""Returns an iterable of (token, origin)"""
matches = [
(token, row)
for (token, partition) in self._origins.data.items()
for (clustering_key, row) in partition.items()
if token >= start_token
]
matches.sort()
return matches[0:limit]
def origin_iter_all(self) -> Iterable[OriginRow]:
return (
row
for (token, partition) in self._origins.data.items()
for (clustering_key, row) in partition.items()
)
def origin_bump_next_visit_id(self, origin_url: str, visit_id: int) -> None:
origin = list(self.origin_get_by_url(origin_url))[0]
origin.next_visit_id = max(origin.next_visit_id, visit_id + 1)
def origin_generate_unique_visit_id(self, origin_url: str) -> int:
origin = list(self.origin_get_by_url(origin_url))[0]
visit_id = origin.next_visit_id
origin.next_visit_id += 1
return visit_id
##########################
# 'origin_visit' table
##########################
def origin_visit_get(
- self, origin_url: str, last_visit: Optional[int], limit: int, order: ListOrder,
+ self,
+ origin_url: str,
+ last_visit: Optional[int],
+ limit: int,
+ order: ListOrder,
) -> Iterable[OriginVisitRow]:
visits = list(self._origin_visits.get_from_partition_key((origin_url,)))
if last_visit is not None:
if order == ListOrder.ASC:
visits = [v for v in visits if v.visit > last_visit]
else:
visits = [v for v in visits if v.visit < last_visit]
visits.sort(key=lambda v: v.visit, reverse=order == ListOrder.DESC)
visits = visits[0:limit]
return visits
def origin_visit_add_one(self, visit: OriginVisitRow) -> None:
self._origin_visits.insert(visit)
self.increment_counter("origin_visit", 1)
def origin_visit_get_one(
self, origin_url: str, visit_id: int
) -> Optional[OriginVisitRow]:
return self._origin_visits.get_from_primary_key((origin_url, visit_id))
def origin_visit_iter_all(self, origin_url: str) -> Iterable[OriginVisitRow]:
return reversed(list(self._origin_visits.get_from_partition_key((origin_url,))))
def origin_visit_iter(self, start_token: int) -> Iterator[OriginVisitRow]:
"""Returns all origin visits in order from this token,
and wraps around the token space."""
return (
row
for (token, partition) in self._origin_visits.data.items()
for (clustering_key, row) in partition.items()
)
##########################
# 'origin_visit_status' table
##########################
def origin_visit_status_get_range(
self,
origin: str,
visit: int,
date_from: Optional[datetime.datetime],
limit: int,
order: ListOrder,
) -> Iterable[OriginVisitStatusRow]:
statuses = list(self.origin_visit_status_get(origin, visit))
if date_from is not None:
if order == ListOrder.ASC:
statuses = [s for s in statuses if s.date >= date_from]
else:
statuses = [s for s in statuses if s.date <= date_from]
statuses.sort(key=lambda s: s.date, reverse=order == ListOrder.DESC)
return statuses[0:limit]
def origin_visit_status_get_all_range(
self, origin: str, first_visit: int, last_visit: int
) -> Iterable[OriginVisitStatusRow]:
statuses = [
s
for s in self._origin_visit_statuses.get_from_partition_key((origin,))
if s.visit >= first_visit and s.visit <= last_visit
]
statuses.sort(key=lambda s: (s.visit, s.date))
return statuses
def origin_visit_status_add_one(self, visit_update: OriginVisitStatusRow) -> None:
self._origin_visit_statuses.insert(visit_update)
self.increment_counter("origin_visit_status", 1)
def origin_visit_status_get_latest(
- self, origin: str, visit: int,
+ self,
+ origin: str,
+ visit: int,
) -> Optional[OriginVisitStatusRow]:
- """Given an origin visit id, return its latest origin_visit_status
-
- """
+ """Given an origin visit id, return its latest origin_visit_status"""
return next(self.origin_visit_status_get(origin, visit), None)
def origin_visit_status_get(
- self, origin: str, visit: int,
+ self,
+ origin: str,
+ visit: int,
) -> Iterator[OriginVisitStatusRow]:
- """Return all origin visit statuses for a given visit
-
- """
+ """Return all origin visit statuses for a given visit"""
statuses = [
s
for s in self._origin_visit_statuses.get_from_partition_key((origin,))
if s.visit == visit
]
statuses.sort(key=lambda s: s.date, reverse=True)
return iter(statuses)
def origin_snapshot_get_all(self, origin: str) -> Iterator[Sha1Git]:
- """Return all snapshots for a given origin
-
- """
+ """Return all snapshots for a given origin"""
return iter(
{
s.snapshot
for s in self._origin_visit_statuses.get_from_partition_key((origin,))
if s.snapshot is not None
}
)
##########################
# 'metadata_authority' table
##########################
def metadata_authority_add(self, authority: MetadataAuthorityRow):
self._metadata_authorities.insert(authority)
self.increment_counter("metadata_authority", 1)
def metadata_authority_get(self, type, url) -> Optional[MetadataAuthorityRow]:
return self._metadata_authorities.get_from_primary_key((url, type))
##########################
# 'metadata_fetcher' table
##########################
def metadata_fetcher_add(self, fetcher: MetadataFetcherRow):
self._metadata_fetchers.insert(fetcher)
self.increment_counter("metadata_fetcher", 1)
def metadata_fetcher_get(self, name, version) -> Optional[MetadataAuthorityRow]:
return self._metadata_fetchers.get_from_primary_key((name, version))
#########################
# 'raw_extrinsic_metadata_by_id' table
#########################
def raw_extrinsic_metadata_by_id_add(
self, row: RawExtrinsicMetadataByIdRow
) -> None:
self._raw_extrinsic_metadata_by_id.insert(row)
def raw_extrinsic_metadata_get_by_ids(
self, ids
) -> List[RawExtrinsicMetadataByIdRow]:
results = []
for id_ in ids:
result = self._raw_extrinsic_metadata_by_id.get_from_primary_key((id_,))
if result:
results.append(result)
return results
#########################
# 'raw_extrinsic_metadata' table
#########################
def raw_extrinsic_metadata_add(self, raw_extrinsic_metadata):
self._raw_extrinsic_metadata.insert(raw_extrinsic_metadata)
self.increment_counter("raw_extrinsic_metadata", 1)
def raw_extrinsic_metadata_get_after_date(
self,
target: str,
authority_type: str,
authority_url: str,
after: datetime.datetime,
) -> Iterable[RawExtrinsicMetadataRow]:
metadata = self.raw_extrinsic_metadata_get(
target, authority_type, authority_url
)
return (m for m in metadata if m.discovery_date > after)
def raw_extrinsic_metadata_get_after_date_and_id(
self,
target: str,
authority_type: str,
authority_url: str,
after_date: datetime.datetime,
after_id: bytes,
) -> Iterable[RawExtrinsicMetadataRow]:
metadata = self._raw_extrinsic_metadata.get_from_partition_key((target,))
after_tuple = (after_date, after_id)
return (
m
for m in metadata
if m.authority_type == authority_type
and m.authority_url == authority_url
and (m.discovery_date, m.id) > after_tuple
)
def raw_extrinsic_metadata_get(
self, target: str, authority_type: str, authority_url: str
) -> Iterable[RawExtrinsicMetadataRow]:
metadata = self._raw_extrinsic_metadata.get_from_partition_key((target,))
return (
m
for m in metadata
if m.authority_type == authority_type and m.authority_url == authority_url
)
def raw_extrinsic_metadata_get_authorities(
self, target: str
) -> Iterable[Tuple[str, str]]:
metadata = self._raw_extrinsic_metadata.get_from_partition_key((target,))
return ((m.authority_type, m.authority_url) for m in metadata)
#########################
# 'extid' table
#########################
def _extid_add_finalize(self, extid: ExtIDRow) -> None:
self._extid.insert(extid)
self.increment_counter("extid", 1)
def extid_add_prepare(self, extid: ExtIDRow):
finalizer = functools.partial(self._extid_add_finalize, extid)
return (self._extid.token(self._extid.partition_key(extid)), finalizer)
def extid_index_add_one(self, row: ExtIDByTargetRow) -> None:
pass
def extid_get_from_pk(
- self, extid_type: str, extid: bytes, extid_version: int, target: ExtendedSWHID,
+ self,
+ extid_type: str,
+ extid: bytes,
+ extid_version: int,
+ target: ExtendedSWHID,
) -> Optional[ExtIDRow]:
primary_key = self._extid.primary_key_from_dict(
dict(
extid_type=extid_type,
extid=extid,
extid_version=extid_version,
target_type=target.object_type.value,
target=target.object_id,
)
)
return self._extid.get_from_primary_key(primary_key)
def extid_get_from_extid(
- self, extid_type: str, extid: bytes,
+ self,
+ extid_type: str,
+ extid: bytes,
) -> Iterable[ExtIDRow]:
return (
row
for pk, row in self._extid.iter_all()
if row.extid_type == extid_type and row.extid == extid
)
def extid_get_from_extid_and_version(
- self, extid_type: str, extid: bytes, extid_version: int,
+ self,
+ extid_type: str,
+ extid: bytes,
+ extid_version: int,
) -> Iterable[ExtIDRow]:
return (
row
for pk, row in self._extid.iter_all()
if row.extid_type == extid_type
and row.extid == extid
and (extid_version is None or row.extid_version == extid_version)
)
def _extid_get_from_target_with_type_and_version(
- self, target_type: str, target: bytes, extid_type: str, extid_version: int,
+ self,
+ target_type: str,
+ target: bytes,
+ extid_type: str,
+ extid_version: int,
) -> Iterable[ExtIDRow]:
return (
row
for pk, row in self._extid.iter_all()
if row.target_type == target_type
and row.target == target
and row.extid_version == extid_version
and row.extid_type == extid_type
)
def _extid_get_from_target(
- self, target_type: str, target: bytes,
+ self,
+ target_type: str,
+ target: bytes,
) -> Iterable[ExtIDRow]:
return (
row
for pk, row in self._extid.iter_all()
if row.target_type == target_type and row.target == target
)
def extid_get_from_target(
self,
target_type: str,
target: bytes,
extid_type: Optional[str] = None,
extid_version: Optional[int] = None,
) -> Iterable[ExtIDRow]:
if (extid_version is not None and extid_type is None) or (
extid_version is None and extid_type is not None
):
raise ValueError("You must provide both extid_type and extid_version")
if extid_type is not None and extid_version is not None:
extids = self._extid_get_from_target_with_type_and_version(
target_type, target, extid_type, extid_version
)
else:
extids = self._extid_get_from_target(target_type, target)
return extids
class InMemoryStorage(CassandraStorage):
_cql_runner: InMemoryCqlRunner # type: ignore
def __init__(self, journal_writer=None):
self.reset()
self.journal_writer = JournalWriter(journal_writer)
self._allow_overwrite = False
self._directory_entries_insert_algo = "one-by-one"
def reset(self):
self._cql_runner = InMemoryCqlRunner()
self.objstorage = ObjStorage({"cls": "memory"})
def check_config(self, *, check_write: bool) -> bool:
return True
diff --git a/swh/storage/interface.py b/swh/storage/interface.py
index 9b65020a..24ee6e31 100644
--- a/swh/storage/interface.py
+++ b/swh/storage/interface.py
@@ -1,1399 +1,1406 @@
# Copyright (C) 2015-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
from enum import Enum
from typing import Any, Dict, Iterable, List, Optional, Sequence, Tuple, TypeVar
import attr
from typing_extensions import Protocol, TypedDict, runtime_checkable
from swh.core.api import remote_api_endpoint
from swh.core.api.classes import PagedResult as CorePagedResult
from swh.model.model import (
Content,
Directory,
DirectoryEntry,
ExtID,
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
OriginVisit,
OriginVisitStatus,
RawExtrinsicMetadata,
Release,
Revision,
Sha1,
Sha1Git,
SkippedContent,
Snapshot,
SnapshotBranch,
)
from swh.model.swhids import ExtendedSWHID, ObjectType
class ListOrder(Enum):
"""Specifies the order for paginated endpoints returning sorted results."""
ASC = "asc"
DESC = "desc"
class PartialBranches(TypedDict):
"""Type of the dictionary returned by snapshot_get_branches"""
id: Sha1Git
"""Identifier of the snapshot"""
branches: Dict[bytes, Optional[SnapshotBranch]]
"""A dict of branches contained in the snapshot
whose keys are the branches' names"""
next_branch: Optional[bytes]
"""The name of the first branch not returned or :const:`None` if
the snapshot has less than the request number of branches."""
@attr.s
class OriginVisitWithStatuses:
visit = attr.ib(type=OriginVisit)
statuses = attr.ib(type=List[OriginVisitStatus])
TResult = TypeVar("TResult")
PagedResult = CorePagedResult[TResult, str]
# TODO: Make it an enum (too much impact)
VISIT_STATUSES = ["created", "ongoing", "full", "partial"]
def deprecated(f):
f.deprecated_endpoint = True
return f
@runtime_checkable
class StorageInterface(Protocol):
@remote_api_endpoint("check_config")
def check_config(self, *, check_write: bool) -> bool:
"""Check that the storage is configured and ready to go."""
...
@remote_api_endpoint("content/add")
def content_add(self, content: List[Content]) -> Dict[str, int]:
"""Add content blobs to the storage
Args:
contents (iterable): iterable of dictionaries representing
individual pieces of content to add. Each dictionary has the
following keys:
- data (bytes): the actual content
- length (int): content length
- one key for each checksum algorithm in
:data:`swh.model.hashutil.ALGORITHMS`, mapped to the
corresponding checksum
- status (str): one of visible, hidden
Raises:
The following exceptions can occur:
- HashCollision in case of collision
- Any other exceptions raise by the db
In case of errors, some of the content may have been stored in
the DB and in the objstorage.
Since additions to both idempotent, that should not be a problem.
Returns:
Summary dict with the following keys and associated values:
content:add: New contents added
content:add:bytes: Sum of the contents' length data
"""
...
@remote_api_endpoint("content/update")
def content_update(
self, contents: List[Dict[str, Any]], keys: List[str] = []
) -> None:
"""Update content blobs to the storage. Does nothing for unknown
contents or skipped ones.
Args:
content: iterable of dictionaries representing
individual pieces of content to update. Each dictionary has the
following keys:
- data (bytes): the actual content
- length (int): content length (default: -1)
- one key for each checksum algorithm in
:data:`swh.model.hashutil.ALGORITHMS`, mapped to the
corresponding checksum
- status (str): one of visible, hidden, absent
keys (list): List of keys (str) whose values needs an update, e.g.,
new hash column
"""
...
@remote_api_endpoint("content/add_metadata")
def content_add_metadata(self, content: List[Content]) -> Dict[str, int]:
"""Add content metadata to the storage (like `content_add`, but
without inserting to the objstorage).
Args:
content (iterable): iterable of dictionaries representing
individual pieces of content to add. Each dictionary has the
following keys:
- length (int): content length (default: -1)
- one key for each checksum algorithm in
:data:`swh.model.hashutil.ALGORITHMS`, mapped to the
corresponding checksum
- status (str): one of visible, hidden, absent
- reason (str): if status = absent, the reason why
- origin (int): if status = absent, the origin we saw the
content in
- ctime (datetime): time of insertion in the archive
Returns:
Summary dict with the following key and associated values:
content:add: New contents added
skipped_content:add: New skipped contents (no data) added
"""
...
@remote_api_endpoint("content/data")
def content_get_data(self, content: Sha1) -> Optional[bytes]:
"""Given a content identifier, returns its associated data if any.
Args:
content: sha1 identifier
Returns:
raw content data (bytes)
"""
...
@remote_api_endpoint("content/partition")
def content_get_partition(
self,
partition_id: int,
nb_partitions: int,
page_token: Optional[str] = None,
limit: int = 1000,
) -> PagedResult[Content]:
"""Splits contents into nb_partitions, and returns one of these based on
partition_id (which must be in [0, nb_partitions-1])
There is no guarantee on how the partitioning is done, or the
result order.
Args:
partition_id: index of the partition to fetch
nb_partitions: total number of partitions to split into
page_token: opaque token used for pagination.
limit: Limit result (default to 1000)
Returns:
PagedResult of Content model objects within the partition. If
next_page_token is None, there is no longer data to retrieve.
"""
...
@remote_api_endpoint("content/metadata")
def content_get(
self, contents: List[bytes], algo: str = "sha1"
) -> List[Optional[Content]]:
"""Retrieve content metadata in bulk
Args:
content: List of content identifiers
algo: one of the checksum algorithm in
:data:`swh.model.hashutil.DEFAULT_ALGORITHMS`
Returns:
List of contents model objects when they exist, None otherwise.
"""
...
@remote_api_endpoint("content/missing")
def content_missing(
self, contents: List[Dict[str, Any]], key_hash: str = "sha1"
) -> Iterable[bytes]:
"""List content missing from storage
Args:
content: iterable of dictionaries whose keys are either 'length' or an item
of :data:`swh.model.hashutil.ALGORITHMS`; mapped to the
corresponding checksum (or length).
key_hash: name of the column to use as hash id result (default: 'sha1')
Raises:
StorageArgumentException when key_hash is unknown.
TODO: an exception when we get a hash collision.
Returns:
iterable of missing content ids (as per the `key_hash` column)
"""
...
@remote_api_endpoint("content/missing/sha1")
def content_missing_per_sha1(self, contents: List[bytes]) -> Iterable[bytes]:
"""List content missing from storage based only on sha1.
Args:
contents: List of sha1 to check for absence.
Raises:
TODO: an exception when we get a hash collision.
Returns:
Iterable of missing content ids (sha1)
"""
...
@remote_api_endpoint("content/missing/sha1_git")
def content_missing_per_sha1_git(
self, contents: List[Sha1Git]
) -> Iterable[Sha1Git]:
"""List content missing from storage based only on sha1_git.
Args:
contents (List): An iterable of content id (sha1_git)
Yields:
missing contents sha1_git
"""
...
@remote_api_endpoint("content/present")
def content_find(self, content: Dict[str, Any]) -> List[Content]:
"""Find a content hash in db.
Args:
content: a dictionary representing one content hash, mapping
checksum algorithm names (see swh.model.hashutil.ALGORITHMS) to
checksum values
Raises:
ValueError: in case the key of the dictionary is not sha1, sha1_git
nor sha256.
Returns:
an iterable of Content objects matching the search criteria if the
content exist. Empty iterable otherwise.
"""
...
@remote_api_endpoint("content/get_random")
def content_get_random(self) -> Sha1Git:
"""Finds a random content id.
Returns:
a sha1_git
"""
...
@remote_api_endpoint("content/skipped/add")
def skipped_content_add(self, content: List[SkippedContent]) -> Dict[str, int]:
"""Add contents to the skipped_content list, which contains
(partial) information about content missing from the archive.
Args:
contents (iterable): iterable of dictionaries representing
individual pieces of content to add. Each dictionary has the
following keys:
- length (Optional[int]): content length (default: -1)
- one key for each checksum algorithm in
:data:`swh.model.hashutil.ALGORITHMS`, mapped to the
corresponding checksum; each is optional
- status (str): must be "absent"
- reason (str): the reason why the content is absent
- origin (int): if status = absent, the origin we saw the
content in
Raises:
The following exceptions can occur:
- HashCollision in case of collision
- Any other exceptions raise by the backend
In case of errors, some content may have been stored in
the DB and in the objstorage.
Since additions to both idempotent, that should not be a problem.
Returns:
Summary dict with the following key and associated values:
skipped_content:add: New skipped contents (no data) added
"""
...
@remote_api_endpoint("content/skipped/missing")
def skipped_content_missing(
self, contents: List[Dict[str, Any]]
) -> Iterable[Dict[str, Any]]:
"""List skipped contents missing from storage.
Args:
contents: iterable of dictionaries containing the data for each
checksum algorithm.
Returns:
Iterable of missing skipped contents as dict
"""
...
@remote_api_endpoint("directory/add")
def directory_add(self, directories: List[Directory]) -> Dict[str, int]:
"""Add directories to the storage
Args:
directories (iterable): iterable of dictionaries representing the
individual directories to add. Each dict has the following
keys:
- id (sha1_git): the id of the directory to add
- entries (list): list of dicts for each entry in the
directory. Each dict has the following keys:
- name (bytes)
- type (one of 'file', 'dir', 'rev'): type of the
directory entry (file, directory, revision)
- target (sha1_git): id of the object pointed at by the
directory entry
- perms (int): entry permissions
Returns:
Summary dict of keys with associated count as values:
directory:add: Number of directories actually added
"""
...
@remote_api_endpoint("directory/missing")
def directory_missing(self, directories: List[Sha1Git]) -> Iterable[Sha1Git]:
"""List directories missing from storage.
Args:
directories: list of directory ids
Yields:
missing directory ids
"""
...
@remote_api_endpoint("directory/ls")
def directory_ls(
self, directory: Sha1Git, recursive: bool = False
) -> Iterable[Dict[str, Any]]:
"""List entries for one directory.
If `recursive=True`, names in the path of a dir/file not at the
root are concatenated with a slash (`/`).
Args:
directory: the directory to list entries from.
recursive: if flag on, this list recursively from this directory.
Yields:
directory entries for such directory.
"""
...
@remote_api_endpoint("directory/path")
def directory_entry_get_by_path(
self, directory: Sha1Git, paths: List[bytes]
) -> Optional[Dict[str, Any]]:
"""Get the directory entry (either file or dir) from directory with path.
Args:
directory: directory id
paths: path to lookup from the top level directory. From left
(top) to right (bottom).
Returns:
The corresponding directory entry as dict if found, None otherwise.
"""
...
@remote_api_endpoint("directory/get_entries")
def directory_get_entries(
self,
directory_id: Sha1Git,
page_token: Optional[bytes] = None,
limit: int = 1000,
) -> Optional[PagedResult[DirectoryEntry]]:
"""Get the content, possibly partial, of a directory with the given id
The entries of the directory are not guaranteed to be returned in any
particular order.
The number of results is not guaranteed to be lower than the ``limit``.
Args:
directory_id: dentifier of the directory
page_token: opaque string used to get the next results of a search
limit: Number of entries to return
Returns:
None if the directory does not exist; a page of DirectoryEntry
objects otherwise.
"""
...
@remote_api_endpoint("directory/get_raw_manifest")
def directory_get_raw_manifest(
self, directory_ids: List[Sha1Git]
) -> Dict[Sha1Git, Optional[bytes]]:
"""Returns the raw manifest of directories that do not fit the SWH data model,
or None if they do.
Directories missing from the archive are not returned at all.
Args:
directory_ids: List of directory ids to query
"""
...
@remote_api_endpoint("directory/get_random")
def directory_get_random(self) -> Sha1Git:
"""Finds a random directory id.
Returns:
a sha1_git
"""
...
@remote_api_endpoint("revision/add")
def revision_add(self, revisions: List[Revision]) -> Dict[str, int]:
"""Add revisions to the storage
Args:
revisions (List[dict]): iterable of dictionaries representing
the individual revisions to add. Each dict has the following
keys:
- **id** (:class:`sha1_git`): id of the revision to add
- **date** (:class:`dict`): date the revision was written
- **committer_date** (:class:`dict`): date the revision got
added to the origin
- **type** (one of 'git', 'tar'): type of the
revision added
- **directory** (:class:`sha1_git`): the directory the
revision points at
- **message** (:class:`bytes`): the message associated with
the revision
- **author** (:class:`Dict[str, bytes]`): dictionary with
keys: name, fullname, email
- **committer** (:class:`Dict[str, bytes]`): dictionary with
keys: name, fullname, email
- **metadata** (:class:`jsonb`): extra information as
dictionary
- **synthetic** (:class:`bool`): revision's nature (tarball,
directory creates synthetic revision`)
- **parents** (:class:`list[sha1_git]`): the parents of
this revision
date dictionaries have the form defined in :mod:`swh.model`.
Returns:
Summary dict of keys with associated count as values
revision:add: New objects actually stored in db
"""
...
@remote_api_endpoint("revision/missing")
def revision_missing(self, revisions: List[Sha1Git]) -> Iterable[Sha1Git]:
"""List revisions missing from storage
Args:
revisions: revision ids
Yields:
missing revision ids
"""
...
@remote_api_endpoint("revision")
def revision_get(
self, revision_ids: List[Sha1Git], ignore_displayname: bool = False
) -> List[Optional[Revision]]:
"""Get revisions from storage
Args:
revisions: revision ids
ignore_displayname: return the original author/committer's full name even if
it's masked by a displayname.
Returns:
list of revision object (if the revision exists or None otherwise)
"""
...
@remote_api_endpoint("extid/from_extid")
def extid_get_from_extid(
self, id_type: str, ids: List[bytes], version: Optional[int] = None
) -> List[ExtID]:
"""Get ExtID objects from external IDs
Args:
id_type: type of the given external identifiers (e.g. 'mercurial')
ids: list of external IDs
version: (Optional) version to use as filter
Returns:
list of ExtID objects
"""
...
@remote_api_endpoint("extid/from_target")
def extid_get_from_target(
self,
target_type: ObjectType,
ids: List[Sha1Git],
extid_type: Optional[str] = None,
extid_version: Optional[int] = None,
) -> List[ExtID]:
"""Get ExtID objects from target IDs and target_type
Args:
target_type: type the SWH object
ids: list of target IDs
extid_type: (Optional) extid_type to use as filter. This cannot be empty if
extid_version is provided.
extid_version: (Optional) version to use as filter. This cannot be empty if
extid_type is provided.
Raises:
ValueError if extid_version is provided without extid_type and vice versa.
Returns:
list of ExtID objects
"""
...
@remote_api_endpoint("extid/add")
def extid_add(self, ids: List[ExtID]) -> Dict[str, int]:
"""Add a series of ExtID objects
Args:
ids: list of ExtID objects
Returns:
Summary dict of keys with associated count as values
extid:add: New ExtID objects actually stored in db
"""
...
@remote_api_endpoint("revision/log")
def revision_log(
self,
revisions: List[Sha1Git],
ignore_displayname: bool = False,
limit: Optional[int] = None,
) -> Iterable[Optional[Dict[str, Any]]]:
"""Fetch revision entry from the given root revisions.
Args:
revisions: array of root revisions to lookup
ignore_displayname: return the original author/committer's full name even if
it's masked by a displayname.
limit: limitation on the output result. Default to None.
Yields:
revision entries log from the given root root revisions
"""
...
@remote_api_endpoint("revision/shortlog")
def revision_shortlog(
self, revisions: List[Sha1Git], limit: Optional[int] = None
) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]:
"""Fetch the shortlog for the given revisions
Args:
revisions: list of root revisions to lookup
limit: depth limitation for the output
Yields:
a list of (id, parents) tuples
"""
...
@remote_api_endpoint("revision/get_random")
def revision_get_random(self) -> Sha1Git:
"""Finds a random revision id.
Returns:
a sha1_git
"""
...
@remote_api_endpoint("release/add")
def release_add(self, releases: List[Release]) -> Dict[str, int]:
"""Add releases to the storage
Args:
releases (List[dict]): iterable of dictionaries representing
the individual releases to add. Each dict has the following
keys:
- **id** (:class:`sha1_git`): id of the release to add
- **revision** (:class:`sha1_git`): id of the revision the
release points to
- **date** (:class:`dict`): the date the release was made
- **name** (:class:`bytes`): the name of the release
- **comment** (:class:`bytes`): the comment associated with
the release
- **author** (:class:`Dict[str, bytes]`): dictionary with
keys: name, fullname, email
the date dictionary has the form defined in :mod:`swh.model`.
Returns:
Summary dict of keys with associated count as values
release:add: New objects contents actually stored in db
"""
...
@remote_api_endpoint("release/missing")
def release_missing(self, releases: List[Sha1Git]) -> Iterable[Sha1Git]:
"""List missing release ids from storage
Args:
releases: release ids
Yields:
a list of missing release ids
"""
...
@remote_api_endpoint("release")
def release_get(
self, releases: List[Sha1Git], ignore_displayname: bool = False
) -> List[Optional[Release]]:
"""Given a list of sha1, return the releases's information
Args:
releases: list of sha1s
ignore_displayname: return the original author's full name even if it's
masked by a displayname.
Returns:
List of releases matching the identifiers or None if the release does
not exist.
"""
...
@remote_api_endpoint("release/get_random")
def release_get_random(self) -> Sha1Git:
"""Finds a random release id.
Returns:
a sha1_git
"""
...
@remote_api_endpoint("snapshot/add")
def snapshot_add(self, snapshots: List[Snapshot]) -> Dict[str, int]:
"""Add snapshots to the storage.
Args:
snapshot ([dict]): the snapshots to add, containing the
following keys:
- **id** (:class:`bytes`): id of the snapshot
- **branches** (:class:`dict`): branches the snapshot contains,
mapping the branch name (:class:`bytes`) to the branch target,
itself a :class:`dict` (or ``None`` if the branch points to an
unknown object)
- **target_type** (:class:`str`): one of ``content``,
``directory``, ``revision``, ``release``,
``snapshot``, ``alias``
- **target** (:class:`bytes`): identifier of the target
(currently a ``sha1_git`` for all object kinds, or the name
of the target branch for aliases)
Raises:
ValueError: if the origin or visit id does not exist.
Returns:
Summary dict of keys with associated count as values
snapshot:add: Count of object actually stored in db
"""
...
@remote_api_endpoint("snapshot/missing")
def snapshot_missing(self, snapshots: List[Sha1Git]) -> Iterable[Sha1Git]:
"""List snapshots missing from storage
Args:
snapshots: snapshot ids
Yields:
missing snapshot ids
"""
...
@remote_api_endpoint("snapshot")
def snapshot_get(self, snapshot_id: Sha1Git) -> Optional[Dict[str, Any]]:
"""Get the content, possibly partial, of a snapshot with the given id
The branches of the snapshot are iterated in the lexicographical
order of their names.
.. warning:: At most 1000 branches contained in the snapshot will be
returned for performance reasons. In order to browse the whole
set of branches, the method :meth:`snapshot_get_branches`
should be used instead.
Args:
snapshot_id: snapshot identifier
Returns:
dict: a dict with three keys:
* **id**: identifier of the snapshot
* **branches**: a dict of branches contained in the snapshot
whose keys are the branches' names.
* **next_branch**: the name of the first branch not returned
or :const:`None` if the snapshot has less than 1000
branches.
"""
...
@remote_api_endpoint("snapshot/count_branches")
def snapshot_count_branches(
- self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None,
+ self,
+ snapshot_id: Sha1Git,
+ branch_name_exclude_prefix: Optional[bytes] = None,
) -> Optional[Dict[Optional[str], int]]:
"""Count the number of branches in the snapshot with the given id
Args:
snapshot_id: snapshot identifier
branch_name_exclude_prefix: if provided, do not count branches whose name
starts with given prefix
Returns:
A dict whose keys are the target types of branches and values their
corresponding amount
"""
...
@remote_api_endpoint("snapshot/get_branches")
def snapshot_get_branches(
self,
snapshot_id: Sha1Git,
branches_from: bytes = b"",
branches_count: int = 1000,
target_types: Optional[List[str]] = None,
branch_name_include_substring: Optional[bytes] = None,
branch_name_exclude_prefix: Optional[bytes] = None,
) -> Optional[PartialBranches]:
"""Get the content, possibly partial, of a snapshot with the given id
The branches of the snapshot are iterated in the lexicographical
order of their names.
Args:
snapshot_id: identifier of the snapshot
branches_from: optional parameter used to skip branches
whose name is lesser than it before returning them
branches_count: optional parameter used to restrain
the amount of returned branches
target_types: optional parameter used to filter the
target types of branch to return (possible values that can be
contained in that list are `'content', 'directory',
'revision', 'release', 'snapshot', 'alias'`)
branch_name_include_substring: if provided, only return branches whose name
contains given substring
branch_name_exclude_prefix: if provided, do not return branches whose name
contains given prefix
Returns:
dict: None if the snapshot does not exist;
a dict with three keys otherwise:
* **id**: identifier of the snapshot
* **branches**: a dict of branches contained in the snapshot
whose keys are the branches' names.
* **next_branch**: the name of the first branch not returned
or :const:`None` if the snapshot has less than
`branches_count` branches after `branches_from` included.
"""
...
@remote_api_endpoint("snapshot/get_random")
def snapshot_get_random(self) -> Sha1Git:
"""Finds a random snapshot id.
Returns:
a sha1_git
"""
...
@remote_api_endpoint("origin/visit/add")
def origin_visit_add(self, visits: List[OriginVisit]) -> Iterable[OriginVisit]:
"""Add visits to storage. If the visits have no id, they will be created and assigned
one. The resulted visits are visits with their visit id set.
Args:
visits: List of OriginVisit objects to add
Raises:
StorageArgumentException if some origin visit reference unknown origins
Returns:
List[OriginVisit] stored
"""
...
@remote_api_endpoint("origin/visit_status/add")
def origin_visit_status_add(
- self, visit_statuses: List[OriginVisitStatus],
+ self,
+ visit_statuses: List[OriginVisitStatus],
) -> Dict[str, int]:
"""Add origin visit statuses.
If there is already a status for the same origin and visit id at the same
date, the new one will be either dropped or will replace the existing one
(it is unspecified which one of these two behaviors happens).
Args:
visit_statuses: origin visit statuses to add
Raises: StorageArgumentException if the origin of the visit status is unknown
"""
...
@remote_api_endpoint("origin/visit/get")
def origin_visit_get(
self,
origin: str,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
) -> PagedResult[OriginVisit]:
"""Retrieve page of OriginVisit information.
Args:
origin: The visited origin
page_token: opaque string used to get the next results of a search
order: Order on visit id fields to list origin visits (default to asc)
limit: Number of visits to return
Raises:
StorageArgumentException if the order is wrong or the page_token type is
mistyped.
Returns: Page of OriginVisit data model objects. if next_page_token is None,
there is no longer data to retrieve.
"""
...
@remote_api_endpoint("origin/visit/find_by_date")
def origin_visit_find_by_date(
self, origin: str, visit_date: datetime.datetime
) -> Optional[OriginVisit]:
"""Retrieves the origin visit whose date is closest to the provided
timestamp.
In case of a tie, the visit with largest id is selected.
Args:
origin: origin (URL)
visit_date: expected visit date
Returns:
A visit if found, None otherwise
"""
...
@remote_api_endpoint("origin/visit/getby")
def origin_visit_get_by(self, origin: str, visit: int) -> Optional[OriginVisit]:
"""Retrieve origin visit's information.
Args:
origin: origin (URL)
visit: visit id
Returns:
The information on that particular OriginVisit or None if
it does not exist
"""
...
@remote_api_endpoint("origin/visit/get_latest")
def origin_visit_get_latest(
self,
origin: str,
type: Optional[str] = None,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
) -> Optional[OriginVisit]:
"""Get the latest origin visit for the given origin, optionally
looking only for those with one of the given allowed_statuses
or for those with a snapshot.
Args:
origin: origin URL
type: Optional visit type to filter on (e.g git, tar, dsc, svn,
hg, npm, pypi, ...)
allowed_statuses: list of visit statuses considered
to find the latest visit. For instance,
``allowed_statuses=['full']`` will only consider visits that
have successfully run to completion.
require_snapshot: If True, only a visit with a snapshot
will be returned.
Raises:
StorageArgumentException if values for the allowed_statuses parameters
are unknown
Returns:
OriginVisit matching the criteria if found, None otherwise. Note that as
OriginVisit no longer held reference on the visit status or snapshot, you
may want to use origin_visit_status_get_latest for those information.
"""
...
@remote_api_endpoint("origin/visit_status/get")
def origin_visit_status_get(
self,
origin: str,
visit: int,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
) -> PagedResult[OriginVisitStatus]:
"""Retrieve page of OriginVisitStatus information.
Args:
origin: The visited origin
visit: The visit identifier
page_token: opaque string used to get the next results of a search
order: Order on visit status objects to list (default to asc)
limit: Number of visit statuses to return
Returns: Page of OriginVisitStatus data model objects. if next_page_token is
None, there is no longer data to retrieve.
"""
...
@remote_api_endpoint("origin/visit_status/get_latest")
def origin_visit_status_get_latest(
self,
origin_url: str,
visit: int,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
) -> Optional[OriginVisitStatus]:
"""Get the latest origin visit status for the given origin visit, optionally
looking only for those with one of the given allowed_statuses or with a
snapshot.
Args:
origin: origin URL
allowed_statuses: list of visit statuses considered to find the latest
visit. Possible values are {created, ongoing, partial, full}. For
instance, ``allowed_statuses=['full']`` will only consider visits that
have successfully run to completion.
require_snapshot: If True, only a visit with a snapshot
will be returned.
Raises:
StorageArgumentException if values for the allowed_statuses parameters
are unknown
Returns:
The OriginVisitStatus matching the criteria
"""
...
@remote_api_endpoint("origin/visit_status/get_all_latest")
def origin_visit_get_with_statuses(
self,
origin: str,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
) -> PagedResult[OriginVisitWithStatuses]:
"""Retrieve page of origin visits and all their statuses.
Origin visit statuses are always sorted in ascending order of their dates.
Args:
origin: The visited origin URL
allowed_statuses: Only visit statuses matching that list will be returned.
If empty, all visit statuses will be returned. Possible status values
are ``created``, ``not_found``, ``ongoing``, ``failed``, ``partial``
and ``full``.
require_snapshot: If :const:`True`, only visit statuses with a snapshot
will be returned.
page_token: opaque string used to get the next results
order: Order on visit objects to list (default to asc)
limit: Number of visits with their statuses to return
Returns: Page of OriginVisitWithStatuses objects. if next_page_token is
None, there is no longer data to retrieve.
"""
...
@remote_api_endpoint("origin/visit_status/get_random")
def origin_visit_status_get_random(self, type: str) -> Optional[OriginVisitStatus]:
"""Randomly select one successful origin visit with
made in the last 3 months.
Returns:
One random OriginVisitStatus matching the selection criteria
"""
...
@remote_api_endpoint("object/find_by_sha1_git")
def object_find_by_sha1_git(self, ids: List[Sha1Git]) -> Dict[Sha1Git, List[Dict]]:
"""Return the objects found with the given ids.
Args:
ids: a generator of sha1_gits
Returns:
A dict from id to the list of objects found for that id. Each object
found is itself a dict with keys:
- sha1_git: the input id
- type: the type of object found
"""
...
@remote_api_endpoint("origin/get")
def origin_get(self, origins: List[str]) -> Iterable[Optional[Origin]]:
"""Return origins.
Args:
origin: a list of urls to find
Returns:
the list of associated existing origin model objects. The unknown origins
will be returned as None at the same index as the input.
"""
...
@remote_api_endpoint("origin/get_sha1")
def origin_get_by_sha1(self, sha1s: List[bytes]) -> List[Optional[Dict[str, Any]]]:
"""Return origins, identified by the sha1 of their URLs.
Args:
sha1s: a list of sha1s
Returns:
List of origins dict whose sha1 of their url match, None otherwise.
"""
...
@remote_api_endpoint("origin/list")
def origin_list(
self, page_token: Optional[str] = None, limit: int = 100
) -> PagedResult[Origin]:
"""Returns the list of origins
Args:
page_token: opaque token used for pagination.
limit: the maximum number of results to return
Returns:
Page of Origin data model objects. if next_page_token is None, there is
no longer data to retrieve.
"""
...
@remote_api_endpoint("origin/search")
def origin_search(
self,
url_pattern: str,
page_token: Optional[str] = None,
limit: int = 50,
regexp: bool = False,
with_visit: bool = False,
visit_types: Optional[List[str]] = None,
) -> PagedResult[Origin]:
"""Search for origins whose urls contain a provided string pattern
or match a provided regular expression.
The search is performed in a case insensitive way.
Args:
url_pattern: the string pattern to search for in origin urls
page_token: opaque token used for pagination
limit: the maximum number of found origins to return
regexp: if True, consider the provided pattern as a regular
expression and return origins whose urls match it
with_visit: if True, filter out origins with no visit
visit_types: Only origins having any of the provided visit types
(e.g. git, svn, pypi) will be returned
Yields:
PagedResult of Origin
"""
...
@deprecated
@remote_api_endpoint("origin/count")
def origin_count(
self, url_pattern: str, regexp: bool = False, with_visit: bool = False
) -> int:
"""Count origins whose urls contain a provided string pattern
or match a provided regular expression.
The pattern search in origin urls is performed in a case insensitive
way.
Args:
url_pattern (str): the string pattern to search for in origin urls
regexp (bool): if True, consider the provided pattern as a regular
expression and return origins whose urls match it
with_visit (bool): if True, filter out origins with no visit
Returns:
int: The number of origins matching the search criterion.
"""
...
@remote_api_endpoint("origin/snapshot/get")
def origin_snapshot_get_all(self, origin_url: str) -> List[Sha1Git]:
"""Return all unique snapshot identifiers resulting from origin visits.
Args:
origin_url: origin URL
Returns:
list of sha1s
"""
...
@remote_api_endpoint("origin/add_multi")
def origin_add(self, origins: List[Origin]) -> Dict[str, int]:
"""Add origins to the storage
Args:
origins: list of dictionaries representing the individual origins,
with the following keys:
- type: the origin type ('git', 'svn', 'deb', ...)
- url (bytes): the url the origin points to
Returns:
Summary dict of keys with associated count as values
origin:add: Count of object actually stored in db
"""
...
def stat_counters(self):
"""compute statistics about the number of tuples in various tables
Returns:
dict: a dictionary mapping textual labels (e.g., content) to
integer values (e.g., the number of tuples in table content)
"""
...
def refresh_stat_counters(self):
"""Recomputes the statistics for `stat_counters`."""
...
@remote_api_endpoint("raw_extrinsic_metadata/add")
def raw_extrinsic_metadata_add(
- self, metadata: List[RawExtrinsicMetadata],
+ self,
+ metadata: List[RawExtrinsicMetadata],
) -> Dict[str, int]:
"""Add extrinsic metadata on objects (contents, directories, ...).
The authority and fetcher must be known to the storage before
using this endpoint.
If there is already metadata for the same object, authority,
fetcher, and at the same date; the new one will be either dropped or
will replace the existing one
(it is unspecified which one of these two behaviors happens).
Args:
metadata: iterable of RawExtrinsicMetadata objects to be inserted.
"""
...
@remote_api_endpoint("raw_extrinsic_metadata/get")
def raw_extrinsic_metadata_get(
self,
target: ExtendedSWHID,
authority: MetadataAuthority,
after: Optional[datetime.datetime] = None,
page_token: Optional[bytes] = None,
limit: int = 1000,
) -> PagedResult[RawExtrinsicMetadata]:
"""Retrieve list of all raw_extrinsic_metadata entries targeting the id
Args:
target: the SWHID of the objects to find metadata on
authority: a dict containing keys `type` and `url`.
after: minimum discovery_date for a result to be returned
page_token: opaque token, used to get the next page of results
limit: maximum number of results to be returned
Returns:
PagedResult of RawExtrinsicMetadata
"""
...
@remote_api_endpoint("raw_extrinsic_metadata/get_by_ids")
def raw_extrinsic_metadata_get_by_ids(
self, ids: List[Sha1Git]
) -> List[RawExtrinsicMetadata]:
"""Retrieve list of raw_extrinsic_metadata entries of the given id
(unlike raw_extrinsic_metadata_get, which returns metadata entries
**targeting** the id)
Args:
ids: list of hashes of RawExtrinsicMetadata objects
"""
...
@remote_api_endpoint("raw_extrinsic_metadata/get_authorities")
def raw_extrinsic_metadata_get_authorities(
self, target: ExtendedSWHID
) -> List[MetadataAuthority]:
"""Returns all authorities that provided metadata on the given object."""
...
@remote_api_endpoint("metadata_fetcher/add")
- def metadata_fetcher_add(self, fetchers: List[MetadataFetcher],) -> Dict[str, int]:
+ def metadata_fetcher_add(
+ self,
+ fetchers: List[MetadataFetcher],
+ ) -> Dict[str, int]:
"""Add new metadata fetchers to the storage.
Their `name` and `version` together are unique identifiers of this
fetcher; and `metadata` is an arbitrary dict of JSONable data
with information about this fetcher, which must not be `None`
(but may be empty).
Args:
fetchers: iterable of MetadataFetcher to be inserted
"""
...
@remote_api_endpoint("metadata_fetcher/get")
def metadata_fetcher_get(
self, name: str, version: str
) -> Optional[MetadataFetcher]:
"""Retrieve information about a fetcher
Args:
name: the name of the fetcher
version: version of the fetcher
Returns:
a MetadataFetcher object (with a non-None metadata field) if it is known,
else None.
"""
...
@remote_api_endpoint("metadata_authority/add")
def metadata_authority_add(
self, authorities: List[MetadataAuthority]
) -> Dict[str, int]:
"""Add new metadata authorities to the storage.
Their `type` and `url` together are unique identifiers of this
authority; and `metadata` is an arbitrary dict of JSONable data
with information about this authority, which must not be `None`
(but may be empty).
Args:
authorities: iterable of MetadataAuthority to be inserted
"""
...
@remote_api_endpoint("metadata_authority/get")
def metadata_authority_get(
self, type: MetadataAuthorityType, url: str
) -> Optional[MetadataAuthority]:
"""Retrieve information about an authority
Args:
type: one of "deposit_client", "forge", or "registry"
url: unique URI identifying the authority
Returns:
a MetadataAuthority object (with a non-None metadata field) if it is known,
else None.
"""
...
@remote_api_endpoint("clear/buffer")
def clear_buffers(self, object_types: Sequence[str] = ()) -> None:
"""For backend storages (pg, storage, in-memory), this is a noop operation. For proxy
storages (especially filter, buffer), this is an operation which cleans internal
state.
"""
@remote_api_endpoint("flush")
def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]:
"""For backend storages (pg, storage, in-memory), this is expected to be a noop
operation. For proxy storages (especially buffer), this is expected to trigger
actual writes to the backend.
"""
...
diff --git a/swh/storage/metrics.py b/swh/storage/metrics.py
index 70054bee..37acd4fc 100644
--- a/swh/storage/metrics.py
+++ b/swh/storage/metrics.py
@@ -1,83 +1,79 @@
# Copyright (C) 2019 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from functools import wraps
import logging
from swh.core.statsd import statsd
OPERATIONS_METRIC = "swh_storage_operations_total"
OPERATIONS_UNIT_METRIC = "swh_storage_operations_{unit}_total"
DURATION_METRIC = "swh_storage_request_duration_seconds"
def timed(f):
- """Time that function!
-
- """
+ """Time that function!"""
@wraps(f)
def d(*a, **kw):
with statsd.timed(DURATION_METRIC, tags={"endpoint": f.__name__}):
return f(*a, **kw)
return d
def send_metric(metric, count, method_name):
"""Send statsd metric with count for method `method_name`
If count is 0, the metric is discarded. If the metric is not
parseable, the metric is discarded with a log message.
Args:
metric (str): Metric's name (e.g content:add, content:add:bytes)
count (int): Associated value for the metric
method_name (str): Method's name
Returns:
Bool to explicit if metric has been set or not
"""
if count == 0:
return False
metric_type = metric.split(":")
_length = len(metric_type)
if _length == 2:
object_type, operation = metric_type
metric_name = OPERATIONS_METRIC
elif _length == 3:
object_type, operation, unit = metric_type
metric_name = OPERATIONS_UNIT_METRIC.format(unit=unit)
else:
logging.warning("Skipping unknown metric {%s: %s}" % (metric, count))
return False
statsd.increment(
metric_name,
count,
tags={
"endpoint": method_name,
"object_type": object_type,
"operation": operation,
},
)
return True
def process_metrics(f):
- """Increment object counters for the decorated function.
-
- """
+ """Increment object counters for the decorated function."""
@wraps(f)
def d(*a, **kw):
r = f(*a, **kw)
for metric, count in r.items():
send_metric(metric=metric, count=count, method_name=f.__name__)
return r
return d
diff --git a/swh/storage/migrate_extrinsic_metadata.py b/swh/storage/migrate_extrinsic_metadata.py
index aae67737..d4304c2b 100644
--- a/swh/storage/migrate_extrinsic_metadata.py
+++ b/swh/storage/migrate_extrinsic_metadata.py
@@ -1,1260 +1,1270 @@
#!/usr/bin/env python3
# Copyright (C) 2020-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
"""This is an executable script to migrate extrinsic revision metadata from
the revision table to the new extrinsic metadata storage.
This is designed to be as conservative as possible, following this principle:
for each revision the script reads (in "handle_row"), it will read some of the
fields, write them directly to the metadata storage, and remove them.
Then it checks all the remaining fields are in a hardcoded list of fields that
are known not to require migration.
This means that every field that isn't migrated was explicitly reviewed while
writing this script.
Additionally, this script contains many assertions to prevent false positives
in its heuristics.
"""
import datetime
import hashlib
import itertools
import json
import os
import re
import sys
import time
from typing import Any, Dict, Optional
from urllib.error import HTTPError
from urllib.parse import unquote, urlparse
from urllib.request import urlopen
import iso8601
import psycopg2
from swh.core.db import BaseDb
from swh.model.hashutil import hash_to_hex
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
RawExtrinsicMetadata,
Sha1Git,
)
from swh.model.swhids import (
CoreSWHID,
ExtendedObjectType,
ExtendedSWHID,
ObjectType,
QualifiedSWHID,
)
from swh.storage import get_storage
from swh.storage.algos.origin import iter_origin_visit_statuses, iter_origin_visits
from swh.storage.algos.snapshot import snapshot_get_all_branches
# XML namespaces and fields for metadata coming from the deposit:
CODEMETA_NS = "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0"
ATOM_NS = "http://www.w3.org/2005/Atom"
ATOM_KEYS = ["id", "author", "external_identifier", "title"]
# columns of the revision table (of the storage DB)
REVISION_COLS = [
"id",
"directory",
"date",
"committer_date",
"type",
"message",
"metadata",
]
# columns of the tables of the deposit DB
DEPOSIT_COLS = [
"deposit.id",
"deposit.external_id",
"deposit.swhid_context",
"deposit.status",
"deposit_request.metadata",
"deposit_request.date",
"deposit_client.provider_url",
"deposit_collection.name",
"auth_user.username",
]
# Formats we write to the extrinsic metadata storage
OLD_DEPOSIT_FORMAT = (
"sword-v2-atom-codemeta-v2-in-json-with-expanded-namespaces" # before february 2018
)
NEW_DEPOSIT_FORMAT = "sword-v2-atom-codemeta-v2-in-json" # after february 2018
GNU_FORMAT = "gnu-tree-json"
NIXGUIX_FORMAT = "nixguix-sources-json"
NPM_FORMAT = "replicate-npm-package-json"
ORIGINAL_ARTIFACT_FORMAT = "original-artifacts-json"
PYPI_FORMAT = "pypi-project-json"
# Information about this script, for traceability
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
# Authorities that we got the metadata from
AUTHORITIES = {
"npmjs": MetadataAuthority(
type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", metadata={}
),
"pypi": MetadataAuthority(
type=MetadataAuthorityType.FORGE, url="https://pypi.org/", metadata={}
),
"gnu": MetadataAuthority(
type=MetadataAuthorityType.FORGE, url="https://ftp.gnu.org/", metadata={}
),
"swh": MetadataAuthority(
type=MetadataAuthorityType.REGISTRY,
url="https://softwareheritage.org/",
metadata={},
), # for original_artifact (which are checksums computed by SWH)
}
# Regular expression for the format of revision messages written by the
# deposit loader
deposit_revision_message_re = re.compile(
b"(?P[a-z-]*): "
b"Deposit (?P[0-9]+) in collection (?P[a-z-]+).*"
)
# not reliable, because PyPI allows arbitrary names
def pypi_project_from_filename(filename):
original_filename = filename
if filename.endswith(".egg"):
return None
elif filename == "mongomotor-0.13.0.n.tar.gz":
return "mongomotor"
elif re.match(r"datahaven-rev[0-9]+\.tar\.gz", filename):
return "datahaven"
elif re.match(r"Dtls-[0-9]\.[0-9]\.[0-9]\.sdist_with_openssl\..*", filename):
return "Dtls"
elif re.match(r"(gae)?pytz-20[0-9][0-9][a-z]\.(tar\.gz|zip)", filename):
return filename.split("-", 1)[0]
- elif filename.startswith(("powny-", "obedient.powny-",)):
+ elif filename.startswith(
+ (
+ "powny-",
+ "obedient.powny-",
+ )
+ ):
return filename.split("-")[0]
elif filename.startswith("devpi-theme-16-"):
return "devpi-theme-16"
elif re.match("[^-]+-[0-9]+.tar.gz", filename):
return filename.split("-")[0]
elif filename == "ohai-1!0.tar.gz":
return "ohai"
elif filename == "collective.topicitemsevent-0.1dvl.tar.gz":
return "collective.topicitemsevent"
elif filename.startswith(
("SpiNNStorageHandlers-1!", "sPyNNakerExternalDevicesPlugin-1!")
):
return filename.split("-")[0]
elif filename.startswith("limnoria-201"):
return "limnoria"
elif filename.startswith("pytz-20"):
return "pytz"
elif filename.startswith("youtube_dl_server-alpha."):
return "youtube_dl_server"
elif filename == "json-extensions-b76bc7d.tar.gz":
return "json-extensions"
elif filename == "LitReview-0.6989ev.tar.gz":
# typo of "dev"
return "LitReview"
elif filename.startswith("django_options-r"):
return "django_options"
elif filename == "Greater than, equal, or less Library-0.1.tar.gz":
return "Greater-than-equal-or-less-Library"
elif filename.startswith("upstart--main-"):
return "upstart"
elif filename == "duckduckpy0.1.tar.gz":
return "duckduckpy"
elif filename == "QUI for MPlayer snapshot_9-14-2011.zip":
return "QUI-for-MPlayer"
elif filename == "Eddy's Memory Game-1.0.zip":
return "Eddy-s-Memory-Game"
elif filename == "jekyll2nikola-0-0-1.tar.gz":
return "jekyll2nikola"
elif filename.startswith("ore.workflowed"):
return "ore.workflowed"
elif re.match("instancemanager-[0-9]*", filename):
return "instancemanager"
elif filename == "OrzMC_W&L-1.0.0.tar.gz":
return "OrzMC-W-L"
elif filename == "use0mk.tar.gz":
return "use0mk"
elif filename == "play-0-develop-1-gd67cd85.tar.gz":
return "play"
elif filename.startswith("mosaic-nist-"):
return "mosaic-nist"
elif filename.startswith("pypops-"):
return "pypops"
elif filename.startswith("pdfcomparator-"):
return "pdfcomparator"
elif filename.startswith("LabJackPython-"):
return "LabJackPython"
elif filename == "MD2K: Cerebral Cortex-3.0.0.tar.gz":
return "cerebralcortex-kernel"
elif filename.startswith("LyMaker-0 (copy)"):
return "LyMaker"
elif filename.startswith("python-tplink-smarthome-"):
return "python-tplink-smarthome"
elif filename.startswith("jtt=tm-utils-"):
return "jtt-tm-utils"
elif filename == "atproject0.1.tar.gz":
return "atproject"
elif filename == "labm8.tar.gz":
return "labm8"
elif filename == "Bugs Everywhere (BEurtle fork)-1.5.0.1.-2012-07-16-.zip":
return "Bugs-Everywhere-BEurtle-fork"
filename = filename.replace(" ", "-")
match = re.match(
r"^(?P[a-z_.-]+)" # project name
r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension
filename,
re.I,
)
if match:
return match.group("project_name")
# First try with a rather strict format, but that allows accidentally
# matching the version as part of the package name
match = re.match(
r"^(?P[a-z0-9_.]+?([-_][a-z][a-z0-9.]+?)*?)" # project name
r"-v?"
r"([0-9]+!)?" # epoch
r"[0-9_.]+([a-z]+[0-9]+)?" # "main" version
r"([.-]?(alpha|beta|dev|post|pre|rc)(\.?[0-9]+)?)*" # development status
r"([.-]?20[012][0-9]{5,9})?" # date
r"([.-]g?[0-9a-f]+)?" # git commit
r"([-+]py(thon)?(3k|[23](\.?[0-9]{1,2})?))?" # python version
r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension
filename,
re.I,
)
if match:
return match.group("project_name")
# If that doesn't work, give up on trying to parse version suffixes,
# and just find the first version-like occurrence in the file name
match = re.match(
r"^(?P[a-z0-9_.-]+?)" # project name
r"[-_.]v?"
r"([0-9]+!)?" # epoch
r"(" # "main" version
r"[0-9_]+\.[0-9_.]+([a-z]+[0-9]+)?" # classic version number
r"|20[012][0-9]{5,9}" # date as integer
r"|20[012][0-9]-[01][0-9]-[0-3][0-9]" # date as ISO 8601
r")" # end of "main" version
r"[a-z]?(dev|pre)?" # direct version suffix
r"([._-].*)?" # extra suffixes
r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension
filename,
re.I,
)
if match:
return match.group("project_name")
# If that still doesn't work, give one last chance if there's only one
# dash or underscore in the name
match = re.match(
r"^(?P[^_-]+)" # project name
r"[_-][^_-]+" # version
r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension
filename,
)
assert match, original_filename
return match.group("project_name")
def pypi_origin_from_project_name(project_name: str) -> str:
return f"https://pypi.org/project/{project_name}/"
def pypi_origin_from_filename(storage, rev_id: bytes, filename: str) -> Optional[str]:
project_name = pypi_project_from_filename(filename)
origin = pypi_origin_from_project_name(project_name)
# But unfortunately, the filename is user-provided, and doesn't
# necessarily match the package name on pypi. Therefore, we need
# to check it.
if _check_revision_in_origin(storage, origin, rev_id):
return origin
# if the origin we guessed does not exist, query the PyPI API with the
# project name we guessed. If only the capitalisation and dash/underscores
# are wrong (by far the most common case), PyPI kindly corrects them.
try:
resp = urlopen(f"https://pypi.org/pypi/{project_name}/json/")
except HTTPError as e:
assert e.code == 404
# nope; PyPI couldn't correct the wrong project name
return None
assert resp.code == 200, resp.code
project_name = json.load(resp)["info"]["name"]
origin = pypi_origin_from_project_name(project_name)
if _check_revision_in_origin(storage, origin, rev_id):
return origin
else:
# The origin exists, but the revision does not belong in it.
# This happens sometimes, as the filename we guessed the origin
# from is user-provided.
return None
def cran_package_from_url(filename):
match = re.match(
r"^https://cran\.r-project\.org/src/contrib/"
r"(?P[a-zA-Z0-9.]+)_[0-9.-]+(\.tar\.gz)?$",
filename,
)
assert match, filename
return match.group("package_name")
def npm_package_from_source_url(package_source_url):
match = re.match(
"^https://registry.npmjs.org/(?P.*)/-/[^/]+.tgz$",
package_source_url,
)
assert match, package_source_url
return unquote(match.group("package_name"))
def remove_atom_codemeta_metadata_with_xmlns(metadata):
"""Removes all known Atom and Codemeta metadata fields from the dict,
assuming this is a dict generated by xmltodict without expanding namespaces.
"""
keys_to_remove = ATOM_KEYS + ["@xmlns", "@xmlns:codemeta"]
for key in list(metadata):
if key.startswith("codemeta:") or key in keys_to_remove:
del metadata[key]
def remove_atom_codemeta_metadata_without_xmlns(metadata):
"""Removes all known Atom and Codemeta metadata fields from the dict,
assuming this is a dict generated by xmltodict with expanded namespaces.
"""
for key in list(metadata):
if key.startswith(("{%s}" % ATOM_NS, "{%s}" % CODEMETA_NS)):
del metadata[key]
def _check_revision_in_origin(storage, origin, revision_id):
seen_snapshots = set() # no need to visit them again
seen_revisions = set()
for visit in iter_origin_visits(storage, origin):
for status in iter_origin_visit_statuses(storage, origin, visit.visit):
if status.snapshot is None:
continue
if status.snapshot in seen_snapshots:
continue
seen_snapshots.add(status.snapshot)
snapshot = snapshot_get_all_branches(storage, status.snapshot)
for (branch_name, branch) in snapshot.branches.items():
if branch is None:
continue
# If it's the revision passed as argument, then it is indeed in the
# origin
if branch.target == revision_id:
return True
# Else, let's make sure the branch doesn't have any other revision
# Get the revision at the top of the branch.
if branch.target in seen_revisions:
continue
seen_revisions.add(branch.target)
revision = storage.revision_get([branch.target])[0]
if revision is None:
# https://forge.softwareheritage.org/T997
continue
# Check it doesn't have parents (else we would have to
# recurse)
assert revision.parents == (), "revision with parents"
return False
def debian_origins_from_row(row, storage):
"""Guesses a Debian origin from a row. May return an empty list if it
cannot reliably guess it, but all results are guaranteed to be correct."""
filenames = [entry["filename"] for entry in row["metadata"]["original_artifact"]]
package_names = {filename.split("_")[0] for filename in filenames}
assert len(package_names) == 1, package_names
(package_name,) = package_names
candidate_origins = [
f"deb://Debian/packages/{package_name}",
f"deb://Debian-Security/packages/{package_name}",
f"http://snapshot.debian.org/package/{package_name}/",
]
return [
origin
for origin in candidate_origins
if _check_revision_in_origin(storage, origin, row["id"])
]
# Cache of origins that are known to exist
_origins = set()
def assert_origin_exists(storage, origin):
assert check_origin_exists(storage, origin), origin
def check_origin_exists(storage, origin):
return (
(
hashlib.sha1(origin.encode()).digest() in _origins # very fast
or storage.origin_get([origin])[0] is not None # slow, but up to date
),
origin,
)
def load_metadata(
storage,
revision_id,
directory_id,
discovery_date: datetime.datetime,
metadata: Dict[str, Any],
format: str,
authority: MetadataAuthority,
origin: Optional[str],
dry_run: bool,
):
"""Does the actual loading to swh-storage."""
directory_swhid = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=directory_id
)
revision_swhid = CoreSWHID(object_type=ObjectType.REVISION, object_id=revision_id)
obj = RawExtrinsicMetadata(
target=directory_swhid,
discovery_date=discovery_date,
authority=authority,
fetcher=FETCHER,
format=format,
metadata=json.dumps(metadata).encode(),
origin=origin,
revision=revision_swhid,
)
if not dry_run:
storage.raw_extrinsic_metadata_add([obj])
def handle_deposit_row(
row,
discovery_date: Optional[datetime.datetime],
origin,
storage,
deposit_cur,
dry_run: bool,
):
"""Loads metadata from the deposit database (which is more reliable as the
metadata on the revision object, as some versions of the deposit loader were
a bit lossy; and they used very different format for the field in the
revision table).
"""
parsed_message = deposit_revision_message_re.match(row["message"])
assert parsed_message is not None, row["message"]
deposit_id = int(parsed_message.group("deposit_id"))
collection = parsed_message.group("collection").decode()
client_name = parsed_message.group("client").decode()
deposit_cur.execute(
f"SELECT {', '.join(DEPOSIT_COLS)} FROM deposit "
f"INNER JOIN deposit_collection "
f" ON (deposit.collection_id=deposit_collection.id) "
f"INNER JOIN deposit_client ON (deposit.client_id=deposit_client.user_ptr_id) "
f"INNER JOIN auth_user ON (deposit.client_id=auth_user.id) "
f"INNER JOIN deposit_request ON (deposit.id=deposit_request.deposit_id) "
f"WHERE deposit.id = %s",
(deposit_id,),
)
provider_urls = set()
swhids = set()
metadata_entries = []
dates = set()
external_identifiers = set()
for deposit_request_row in deposit_cur:
deposit_request = dict(zip(DEPOSIT_COLS, deposit_request_row))
# Sanity checks to make sure we selected the right deposit
assert deposit_request["deposit.id"] == deposit_id
assert deposit_request["deposit_collection.name"] == collection, deposit_request
if client_name != "":
# Sometimes it's missing from the commit message
assert deposit_request["auth_user.username"] == client_name
# Date of the deposit request (either the initial request, of subsequent ones)
date = deposit_request["deposit_request.date"]
dates.add(date)
if deposit_request["deposit.external_id"] == "hal-02355563":
# Failed deposit
swhids.add(
"swh:1:rev:9293f230baca9814490d4fff7ac53d487a20edb6"
";origin=https://hal.archives-ouvertes.fr/hal-02355563"
)
else:
assert deposit_request["deposit.swhid_context"], deposit_request
swhids.add(deposit_request["deposit.swhid_context"])
external_identifiers.add(deposit_request["deposit.external_id"])
# Client of the deposit
provider_urls.add(deposit_request["deposit_client.provider_url"])
metadata = deposit_request["deposit_request.metadata"]
if metadata is not None:
json.dumps(metadata).encode() # check it's valid
if "@xmlns" in metadata:
assert metadata["@xmlns"] == ATOM_NS
assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS])
format = NEW_DEPOSIT_FORMAT
elif "{http://www.w3.org/2005/Atom}id" in metadata:
assert (
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in metadata
or "{http://www.w3.org/2005/Atom}author" in metadata
)
format = OLD_DEPOSIT_FORMAT
else:
# new format introduced in
# https://forge.softwareheritage.org/D4065
# it's the same as the first case, but with the @xmlns
# declarations stripped
# Most of them should have the "id", but some revisions,
# like 4d3890004fade1f4ec3bf7004a4af0c490605128, are missing
# this field
assert "id" in metadata or "title" in metadata
assert "codemeta:author" in metadata
format = NEW_DEPOSIT_FORMAT
metadata_entries.append((date, format, metadata))
if discovery_date is None:
discovery_date = max(dates)
# Sanity checks to make sure deposit requests are consistent with each other
assert len(metadata_entries) >= 1, deposit_id
assert len(provider_urls) == 1, f"expected 1 provider url, got {provider_urls}"
(provider_url,) = provider_urls
assert len(swhids) == 1
(swhid,) = swhids
assert (
len(external_identifiers) == 1
), f"expected 1 external identifier, got {external_identifiers}"
(external_identifier,) = external_identifiers
# computed the origin from the external_identifier if we don't have one
if origin is None:
origin = f"{provider_url.strip('/')}/{external_identifier}"
# explicit list of mistakes that happened in the past, but shouldn't
# happen again:
if origin == "https://hal.archives-ouvertes.fr/hal-01588781":
# deposit id 75
origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588781"
elif origin == "https://hal.archives-ouvertes.fr/hal-01588782":
# deposit id 76
origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588782"
elif origin == "https://hal.archives-ouvertes.fr/hal-01592430":
# deposit id 143
origin = "https://hal-preprod.archives-ouvertes.fr/hal-01592430"
elif origin == "https://hal.archives-ouvertes.fr/hal-01588927":
origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588927"
elif origin == "https://hal.archives-ouvertes.fr/hal-01593875":
# deposit id 175
origin = "https://hal-preprod.archives-ouvertes.fr/hal-01593875"
elif deposit_id == 160:
assert origin == "https://www.softwareheritage.org/je-suis-gpl", origin
origin = "https://forge.softwareheritage.org/source/jesuisgpl/"
elif origin == "https://hal.archives-ouvertes.fr/hal-01588942":
# deposit id 90
origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588942"
elif origin == "https://hal.archives-ouvertes.fr/hal-01592499":
# deposit id 162
origin = "https://hal-preprod.archives-ouvertes.fr/hal-01592499"
elif origin == "https://hal.archives-ouvertes.fr/hal-01588935":
# deposit id 89
origin = "https://hal-preprod.archives-ouvertes.fr/hal-01588935"
assert_origin_exists(storage, origin)
# check the origin we computed matches the one in the deposit db
swhid_origin = QualifiedSWHID.from_string(swhid).origin
if origin is not None:
# explicit list of mistakes that happened in the past, but shouldn't
# happen again:
exceptions = [
(
# deposit id 229
"https://hal.archives-ouvertes.fr/hal-01243573",
"https://hal-test.archives-ouvertes.fr/hal-01243573",
),
(
# deposit id 199
"https://hal.archives-ouvertes.fr/hal-01243065",
"https://hal-test.archives-ouvertes.fr/hal-01243065",
),
(
# deposit id 164
"https://hal.archives-ouvertes.fr/hal-01593855",
"https://hal-preprod.archives-ouvertes.fr/hal-01593855",
),
]
if (origin, swhid_origin) not in exceptions:
assert origin == swhid_origin, (
f"the origin we guessed from the deposit db or revision ({origin}) "
f"doesn't match the one in the deposit db's SWHID ({swhid})"
)
authority = MetadataAuthority(
- type=MetadataAuthorityType.DEPOSIT_CLIENT, url=provider_url, metadata={},
+ type=MetadataAuthorityType.DEPOSIT_CLIENT,
+ url=provider_url,
+ metadata={},
)
for (date, format, metadata) in metadata_entries:
load_metadata(
storage,
row["id"],
row["directory"],
date,
metadata,
format,
authority=authority,
origin=origin,
dry_run=dry_run,
)
return (origin, discovery_date)
def handle_row(row: Dict[str, Any], storage, deposit_cur, dry_run: bool):
type_ = row["type"]
# default date in case we can't find a better one
discovery_date = row["date"] or row["committer_date"]
metadata = row["metadata"]
if metadata is None:
return
if type_ == "dsc":
origin = None # it will be defined later, using debian_origins_from_row
# TODO: the debian loader writes the changelog date as the revision's
# author date and committer date. Instead, we should use the visit's date
if "extrinsic" in metadata:
extrinsic_files = metadata["extrinsic"]["raw"]["files"]
for artifact_entry in metadata["original_artifact"]:
extrinsic_file = extrinsic_files[artifact_entry["filename"]]
for key in ("sha256",):
assert artifact_entry["checksums"][key] == extrinsic_file[key]
artifact_entry["url"] = extrinsic_file["uri"]
del metadata["extrinsic"]
elif type_ == "tar":
provider = metadata.get("extrinsic", {}).get("provider")
if provider is not None:
# This is the format all the package loaders currently write, and
# it is the easiest, thanks to the 'provider' and 'when' fields,
# which have all the information we need to tell them easily
# and generate accurate metadata
discovery_date = iso8601.parse_date(metadata["extrinsic"]["when"])
# New versions of the loaders write the provider; use it.
if provider.startswith("https://replicate.npmjs.com/"):
# npm loader format 1
parsed_url = urlparse(provider)
assert re.match("^/[^/]+/?$", parsed_url.path), parsed_url
package_name = unquote(parsed_url.path.strip("/"))
origin = "https://www.npmjs.com/package/" + package_name
assert_origin_exists(storage, origin)
load_metadata(
storage,
row["id"],
row["directory"],
discovery_date,
metadata["extrinsic"]["raw"],
NPM_FORMAT,
authority=AUTHORITIES["npmjs"],
origin=origin,
dry_run=dry_run,
)
del metadata["extrinsic"]
elif provider.startswith("https://pypi.org/"):
# pypi loader format 1
match = re.match(
"https://pypi.org/pypi/(?P.*)/json", provider
)
assert match, f"unexpected provider URL format: {provider}"
project_name = match.group("project_name")
origin = f"https://pypi.org/project/{project_name}/"
assert_origin_exists(storage, origin)
load_metadata(
storage,
row["id"],
row["directory"],
discovery_date,
metadata["extrinsic"]["raw"],
PYPI_FORMAT,
authority=AUTHORITIES["pypi"],
origin=origin,
dry_run=dry_run,
)
del metadata["extrinsic"]
elif provider.startswith("https://cran.r-project.org/"):
# cran loader
provider = metadata["extrinsic"]["provider"]
if provider.startswith("https://cran.r-project.org/package="):
origin = metadata["extrinsic"]["provider"]
else:
package_name = cran_package_from_url(provider)
origin = f"https://cran.r-project.org/package={package_name}"
assert origin is not None
# Ideally we should assert the origin exists, but we can't:
# https://forge.softwareheritage.org/T2536
if (
hashlib.sha1(origin.encode()).digest() not in _origins
and storage.origin_get([origin])[0] is None
):
return
raw_extrinsic_metadata = metadata["extrinsic"]["raw"]
# this is actually intrinsic, ignore it
if "version" in raw_extrinsic_metadata:
del raw_extrinsic_metadata["version"]
# Copy the URL to the original_artifacts metadata
assert len(metadata["original_artifact"]) == 1
if "url" in metadata["original_artifact"][0]:
assert (
metadata["original_artifact"][0]["url"]
== raw_extrinsic_metadata["url"]
), row
else:
metadata["original_artifact"][0]["url"] = raw_extrinsic_metadata[
"url"
]
del raw_extrinsic_metadata["url"]
assert (
raw_extrinsic_metadata == {}
), f"Unexpected metadata keys: {list(raw_extrinsic_metadata)}"
del metadata["extrinsic"]
elif (
provider.startswith("https://nix-community.github.io/nixpkgs-swh/")
or provider == "https://guix.gnu.org/sources.json"
):
# nixguix loader
origin = provider
assert_origin_exists(storage, origin)
authority = MetadataAuthority(
- type=MetadataAuthorityType.FORGE, url=provider, metadata={},
+ type=MetadataAuthorityType.FORGE,
+ url=provider,
+ metadata={},
)
assert row["date"] is None # the nixguix loader does not write dates
load_metadata(
storage,
row["id"],
row["directory"],
discovery_date,
metadata["extrinsic"]["raw"],
NIXGUIX_FORMAT,
authority=authority,
origin=origin,
dry_run=dry_run,
)
del metadata["extrinsic"]
elif provider.startswith("https://ftp.gnu.org/"):
# archive loader format 1
origin = provider
assert_origin_exists(storage, origin)
assert len(metadata["original_artifact"]) == 1
metadata["original_artifact"][0]["url"] = metadata["extrinsic"]["raw"][
"url"
]
# Remove duplicate keys of original_artifacts
for key in ("url", "time", "length", "version", "filename"):
del metadata["extrinsic"]["raw"][key]
assert metadata["extrinsic"]["raw"] == {}
del metadata["extrinsic"]
elif provider.startswith("https://deposit.softwareheritage.org/"):
origin = metadata["extrinsic"]["raw"]["origin"]["url"]
assert_origin_exists(storage, origin)
if "@xmlns" in metadata:
assert metadata["@xmlns"] == ATOM_NS
assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS])
assert "intrinsic" not in metadata
assert "extra_headers" not in metadata
# deposit loader format 1
# in this case, the metadata seems to be both directly in metadata
# and in metadata["extrinsic"]["raw"]["metadata"]
(origin, discovery_date) = handle_deposit_row(
row, discovery_date, origin, storage, deposit_cur, dry_run
)
remove_atom_codemeta_metadata_with_xmlns(metadata)
if "client" in metadata:
del metadata["client"]
del metadata["extrinsic"]
else:
# deposit loader format 2
actual_metadata = metadata["extrinsic"]["raw"]["origin_metadata"][
"metadata"
]
if isinstance(actual_metadata, str):
# new format introduced in
# https://forge.softwareheritage.org/D4105
actual_metadata = json.loads(actual_metadata)
if "@xmlns" in actual_metadata:
assert actual_metadata["@xmlns"] == ATOM_NS
assert actual_metadata["@xmlns:codemeta"] in (
CODEMETA_NS,
[CODEMETA_NS],
)
elif "{http://www.w3.org/2005/Atom}id" in actual_metadata:
assert (
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author"
in actual_metadata
)
else:
# new format introduced in
# https://forge.softwareheritage.org/D4065
# it's the same as the first case, but with the @xmlns
# declarations stripped
# Most of them should have the "id", but some revisions,
# like 4d3890004fade1f4ec3bf7004a4af0c490605128, are missing
# this field
assert (
"id" in actual_metadata
or "title" in actual_metadata
or "atom:title" in actual_metadata
)
assert "codemeta:author" in actual_metadata
(origin, discovery_date) = handle_deposit_row(
row, discovery_date, origin, storage, deposit_cur, dry_run
)
del metadata["extrinsic"]
else:
assert False, f"unknown provider {provider}"
# Older versions don't write the provider; use heuristics instead.
elif (
metadata.get("package_source", {})
.get("url", "")
.startswith("https://registry.npmjs.org/")
):
# npm loader format 2
package_source_url = metadata["package_source"]["url"]
package_name = npm_package_from_source_url(package_source_url)
origin = "https://www.npmjs.com/package/" + package_name
assert_origin_exists(storage, origin)
load_metadata(
storage,
row["id"],
row["directory"],
discovery_date,
metadata["package"],
NPM_FORMAT,
authority=AUTHORITIES["npmjs"],
origin=origin,
dry_run=dry_run,
)
del metadata["package"]
assert "original_artifact" not in metadata
# rebuild an "original_artifact"-like metadata dict from what we
# can salvage of "package_source"
package_source_metadata = metadata["package_source"]
keep_keys = {"blake2s256", "filename", "sha1", "sha256", "url"}
discard_keys = {
"date", # is equal to the revision date
"name", # was loaded above
"version", # same
}
assert (
set(package_source_metadata) == keep_keys | discard_keys
), package_source_metadata
# will be loaded below
metadata["original_artifact"] = [
{
"filename": package_source_metadata["filename"],
"checksums": {
"sha1": package_source_metadata["sha1"],
"sha256": package_source_metadata["sha256"],
"blake2s256": package_source_metadata["blake2s256"],
},
"url": package_source_metadata["url"],
}
]
del metadata["package_source"]
elif "@xmlns" in metadata:
assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS])
assert "intrinsic" not in metadata
assert "extra_headers" not in metadata
# deposit loader format 3
if row["message"] == b"swh: Deposit 159 in collection swh":
# There is no deposit 159 in the deposit DB, for some reason
assert (
hash_to_hex(row["id"]) == "8e9cee14a6ad39bca4347077b87fb5bbd8953bb1"
)
return
elif row["message"] == b"hal: Deposit 342 in collection hal":
# They have status 'failed' and no swhid
return
origin = None # TODO
discovery_date = None # TODO
(origin, discovery_date) = handle_deposit_row(
row, discovery_date, origin, storage, deposit_cur, dry_run
)
remove_atom_codemeta_metadata_with_xmlns(metadata)
if "client" in metadata:
del metadata["client"] # found in the deposit db
if "committer" in metadata:
del metadata["committer"] # found on the revision object
elif "{http://www.w3.org/2005/Atom}id" in metadata:
assert (
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in metadata
or "{http://www.w3.org/2005/Atom}author" in metadata
)
assert "intrinsic" not in metadata
assert "extra_headers" not in metadata
# deposit loader format 4
origin = None
discovery_date = None # TODO
(origin, discovery_date) = handle_deposit_row(
row, discovery_date, origin, storage, deposit_cur, dry_run
)
remove_atom_codemeta_metadata_without_xmlns(metadata)
elif hash_to_hex(row["id"]) == "a86747d201ab8f8657d145df4376676d5e47cf9f":
# deposit 91, is missing "{http://www.w3.org/2005/Atom}id" for some
# reason, and has an invalid oririn
return
elif (
isinstance(metadata.get("original_artifact"), dict)
and metadata["original_artifact"]["url"].startswith(
"https://files.pythonhosted.org/"
)
) or (
isinstance(metadata.get("original_artifact"), list)
and len(metadata.get("original_artifact")) == 1
and metadata["original_artifact"][0]
.get("url", "")
.startswith("https://files.pythonhosted.org/")
):
if isinstance(metadata.get("original_artifact"), dict):
metadata["original_artifact"] = [metadata["original_artifact"]]
assert len(metadata["original_artifact"]) == 1
version = metadata.get("project", {}).get("version")
filename = metadata["original_artifact"][0]["filename"]
if version:
origin = pypi_origin_from_project_name(filename.split("-" + version)[0])
if not _check_revision_in_origin(storage, origin, row["id"]):
origin = None
else:
origin = None
if origin is None:
origin = pypi_origin_from_filename(storage, row["id"], filename)
if "project" in metadata:
# pypi loader format 2
load_metadata(
storage,
row["id"],
row["directory"],
discovery_date,
metadata["project"],
PYPI_FORMAT,
authority=AUTHORITIES["pypi"],
origin=origin,
dry_run=dry_run,
)
del metadata["project"]
else:
assert set(metadata) == {"original_artifact"}, set(metadata)
# pypi loader format 3
pass # nothing to do, there's no metadata
elif row["message"] == b"synthetic revision message":
assert isinstance(metadata["original_artifact"], list), metadata
assert not any("url" in d for d in metadata["original_artifact"])
# archive loader format 2
origin = None
elif deposit_revision_message_re.match(row["message"]):
# deposit without metadata in the revision
assert set(metadata) == {"original_artifact"}, metadata
origin = None # TODO
discovery_date = None
(origin, discovery_date) = handle_deposit_row(
row, discovery_date, origin, storage, deposit_cur, dry_run
)
else:
assert False, f"Unable to detect type of metadata for row: {row}"
# Ignore common intrinsic metadata keys
for key in ("intrinsic", "extra_headers"):
if key in metadata:
del metadata[key]
# Ignore loader-specific intrinsic metadata keys
if type_ == "hg":
del metadata["node"]
elif type_ == "dsc":
if "package_info" in metadata:
del metadata["package_info"]
if "original_artifact" in metadata:
for original_artifact in metadata["original_artifact"]:
# Rename keys to the expected format of original-artifacts-json.
rename_keys = [
("name", "filename"), # eg. from old Debian loader
("size", "length"), # eg. from old PyPI loader
]
for (old_name, new_name) in rename_keys:
if old_name in original_artifact:
assert new_name not in original_artifact
original_artifact[new_name] = original_artifact.pop(old_name)
# Move the checksums to their own subdict, which is the expected format
# of original-artifacts-json.
if "sha1" in original_artifact:
assert "checksums" not in original_artifact
original_artifact["checksums"] = {}
for key in ("sha1", "sha256", "sha1_git", "blake2s256"):
if key in original_artifact:
original_artifact["checksums"][key] = original_artifact.pop(key)
if "date" in original_artifact:
# The information comes from the package repository rather than SWH,
# so it shouldn't be in the 'original-artifacts' metadata
# (which has SWH as authority).
# Moreover, it's not a very useful information, so let's just drop it.
del original_artifact["date"]
allowed_keys = {
"checksums",
"filename",
"length",
"url",
"archive_type",
}
assert set(original_artifact) <= allowed_keys, set(original_artifact)
if type_ == "dsc":
assert origin is None
origins = debian_origins_from_row(row, storage)
if not origins:
print(f"Missing Debian origin for revision: {hash_to_hex(row['id'])}")
else:
origins = [origin]
for origin in origins:
load_metadata(
storage,
row["id"],
row["directory"],
discovery_date,
metadata["original_artifact"],
ORIGINAL_ARTIFACT_FORMAT,
authority=AUTHORITIES["swh"],
origin=origin,
dry_run=dry_run,
)
del metadata["original_artifact"]
assert metadata == {}, (
f"remaining metadata keys for {row['id'].hex()} (type: {row['type']}): "
f"{metadata}"
)
def create_fetchers(db):
with db.cursor() as cur:
cur.execute(
"""
INSERT INTO metadata_fetcher (name, version, metadata)
VALUES (%s, %s, %s)
ON CONFLICT DO NOTHING
""",
(FETCHER.name, FETCHER.version, FETCHER.metadata),
)
def iter_revision_rows(storage_dbconn: str, first_id: Sha1Git):
after_id = first_id
failures = 0
while True:
try:
storage_db = BaseDb.connect(storage_dbconn)
with storage_db.cursor() as cur:
while True:
cur.execute(
f"SELECT {', '.join(REVISION_COLS)} FROM revision "
f"WHERE id >= %s AND metadata IS NOT NULL AND type != 'git'"
f"ORDER BY id LIMIT 1000",
(after_id,),
)
new_rows = 0
for row in cur:
new_rows += 1
row_d = dict(zip(REVISION_COLS, row))
yield row_d
after_id = row_d["id"]
if new_rows == 0:
return
except psycopg2.OperationalError as e:
print(e)
# most likely a temporary error, try again
if failures >= 60:
raise
else:
time.sleep(60)
failures += 1
def main(storage_dbconn, storage_url, deposit_dbconn, first_id, limit, dry_run):
storage_db = BaseDb.connect(storage_dbconn)
deposit_db = BaseDb.connect(deposit_dbconn)
storage = get_storage(
"pipeline",
steps=[
{"cls": "retry"},
{
"cls": "postgresql",
"db": storage_dbconn,
"objstorage": {"cls": "memory", "args": {}},
},
],
)
if not dry_run:
create_fetchers(storage_db)
# Not creating authorities, as the loaders are presumably already running
# and created them already.
# This also helps make sure this script doesn't accidentally create
# authorities that differ from what the loaders use.
total_rows = 0
with deposit_db.cursor() as deposit_cur:
rows = iter_revision_rows(storage_dbconn, first_id)
if limit is not None:
rows = itertools.islice(rows, limit)
for row in rows:
handle_row(row, storage, deposit_cur, dry_run)
total_rows += 1
if total_rows % 1000 == 0:
percents = (
int.from_bytes(row["id"][0:4], byteorder="big") * 100 / (1 << 32)
)
print(
f"Processed {total_rows/1000000.:.2f}M rows "
f"(~{percents:.1f}%, last revision: {row['id'].hex()})"
)
if __name__ == "__main__":
if len(sys.argv) == 4:
(_, storage_dbconn, storage_url, deposit_dbconn) = sys.argv
first_id = "00" * 20
elif len(sys.argv) == 5:
(_, storage_dbconn, storage_url, deposit_dbconn, first_id) = sys.argv
limit = None
elif len(sys.argv) == 6:
(_, storage_dbconn, storage_url, deposit_dbconn, first_id, limit_str) = sys.argv
limit = int(limit_str)
else:
print(
f"Syntax: {sys.argv[0]} "
f" [ [limit]]"
)
exit(1)
if os.path.isfile("./origins.txt"):
# You can generate this file with:
# psql service=swh-replica \
# -c "\copy (select digest(url, 'sha1') from origin) to stdout" \
# | pv -l > origins.txt
print("Loading origins...")
with open("./origins.txt") as fd:
for line in fd:
digest = line.strip()[3:]
_origins.add(bytes.fromhex(digest))
print("Done loading origins.")
main(
storage_dbconn,
storage_url,
deposit_dbconn,
bytes.fromhex(first_id),
limit,
True,
)
diff --git a/swh/storage/postgresql/converters.py b/swh/storage/postgresql/converters.py
index 15fa7949..14763122 100644
--- a/swh/storage/postgresql/converters.py
+++ b/swh/storage/postgresql/converters.py
@@ -1,347 +1,362 @@
# Copyright (C) 2015-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
import math
from typing import Any, Dict, Optional
import warnings
from swh.core.utils import encode_with_unescape
from swh.model.model import (
ExtID,
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
ObjectType,
Origin,
Person,
RawExtrinsicMetadata,
Release,
Revision,
RevisionType,
Timestamp,
TimestampWithTimezone,
)
from swh.model.swhids import CoreSWHID, ExtendedSWHID
from swh.model.swhids import ObjectType as SwhidObjectType
from ..utils import map_optional
DEFAULT_AUTHOR = {
"fullname": None,
"name": None,
"email": None,
}
DEFAULT_DATE = {
"timestamp": None,
"offset": 0,
"neg_utc_offset": None,
"offset_bytes": None,
}
def author_to_db(author: Optional[Person]) -> Dict[str, Any]:
"""Convert a swh-model author to its DB representation.
Args:
author: a :mod:`swh.model` compatible author
Returns:
dict: a dictionary with three keys: author, fullname and email
"""
if author is None:
return DEFAULT_AUTHOR
return author.to_dict()
def db_to_author(
fullname: Optional[bytes], name: Optional[bytes], email: Optional[bytes]
) -> Optional[Person]:
"""Convert the DB representation of an author to a swh-model author.
Args:
fullname (bytes): the author's fullname
name (bytes): the author's name
email (bytes): the author's email
Returns:
a Person object, or None if 'fullname' is None.
"""
if fullname is None:
return None
if name is None and email is None:
# The fullname hasn't been parsed, try that again
return Person.from_fullname(fullname)
- return Person(fullname=fullname, name=name, email=email,)
+ return Person(
+ fullname=fullname,
+ name=name,
+ email=email,
+ )
def db_to_git_headers(db_git_headers):
ret = []
for key, value in db_git_headers:
ret.append([key.encode("utf-8"), encode_with_unescape(value)])
return ret
def db_to_date(
- date: Optional[datetime.datetime], offset_bytes: bytes,
+ date: Optional[datetime.datetime],
+ offset_bytes: bytes,
) -> Optional[TimestampWithTimezone]:
"""Convert the DB representation of a date to a swh-model compatible date.
Args:
date: a date pulled out of the database
offset_bytes: a byte representation of the latter two, usually as "+HHMM"
or "-HHMM"
Returns:
a TimestampWithTimezone, or None if the date is None.
"""
if date is None:
return None
return TimestampWithTimezone(
timestamp=Timestamp(
# we use floor() instead of int() to round down, because of negative dates
seconds=math.floor(date.timestamp()),
microseconds=date.microsecond,
),
offset_bytes=offset_bytes,
)
def date_to_db(ts_with_tz: Optional[TimestampWithTimezone]) -> Dict[str, Any]:
"""Convert a swh-model date_offset to its DB representation.
Args:
ts_with_tz: a TimestampWithTimezone object
Returns:
dict: a dictionary with these keys:
- timestamp: a date in ISO format
- offset_bytes: a byte representation of the latter two, usually as "+HHMM"
or "-HHMM"
"""
if ts_with_tz is None:
return DEFAULT_DATE
ts = ts_with_tz.timestamp
timestamp = datetime.datetime.fromtimestamp(ts.seconds, datetime.timezone.utc)
timestamp = timestamp.replace(microsecond=ts.microseconds)
return {
# PostgreSQL supports isoformatted timestamps
"timestamp": timestamp.isoformat(),
"offset": ts_with_tz.offset_minutes(),
"neg_utc_offset": ts_with_tz.offset_minutes() == 0
and ts_with_tz.offset_bytes.startswith(b"-"),
"offset_bytes": ts_with_tz.offset_bytes,
}
def revision_to_db(revision: Revision) -> Dict[str, Any]:
- """Convert a swh-model revision to its database representation.
- """
+ """Convert a swh-model revision to its database representation."""
author = author_to_db(revision.author)
date = date_to_db(revision.date)
committer = author_to_db(revision.committer)
committer_date = date_to_db(revision.committer_date)
return {
"id": revision.id,
"author_fullname": author["fullname"],
"author_name": author["name"],
"author_email": author["email"],
"date": date["timestamp"],
"date_offset": date["offset"],
"date_neg_utc_offset": date["neg_utc_offset"],
"date_offset_bytes": date["offset_bytes"],
"committer_fullname": committer["fullname"],
"committer_name": committer["name"],
"committer_email": committer["email"],
"committer_date": committer_date["timestamp"],
"committer_date_offset": committer_date["offset"],
"committer_date_neg_utc_offset": committer_date["neg_utc_offset"],
"committer_date_offset_bytes": committer_date["offset_bytes"],
"type": revision.type.value,
"directory": revision.directory,
"message": revision.message,
"metadata": None if revision.metadata is None else dict(revision.metadata),
"synthetic": revision.synthetic,
"extra_headers": revision.extra_headers,
"raw_manifest": revision.raw_manifest,
"parents": [
- {"id": revision.id, "parent_id": parent, "parent_rank": i,}
+ {
+ "id": revision.id,
+ "parent_id": parent,
+ "parent_rank": i,
+ }
for i, parent in enumerate(revision.parents)
],
}
def db_to_revision(db_revision: Dict[str, Any]) -> Optional[Revision]:
"""Convert a database representation of a revision to its swh-model
representation."""
if db_revision["type"] is None:
assert all(
v is None for (k, v) in db_revision.items() if k not in ("id", "parents")
)
return None
author = db_to_author(
db_revision["author_fullname"],
db_revision["author_name"],
db_revision["author_email"],
)
- date = db_to_date(db_revision["date"], db_revision["date_offset_bytes"],)
+ date = db_to_date(
+ db_revision["date"],
+ db_revision["date_offset_bytes"],
+ )
committer = db_to_author(
db_revision["committer_fullname"],
db_revision["committer_name"],
db_revision["committer_email"],
)
committer_date = db_to_date(
- db_revision["committer_date"], db_revision["committer_date_offset_bytes"],
+ db_revision["committer_date"],
+ db_revision["committer_date_offset_bytes"],
)
assert (author is None) == (
db_revision["author_fullname"] is None
), "author is unexpectedly None"
assert (committer is None) == (
db_revision["committer_fullname"] is None
), "committer is unexpectedly None"
parents = []
if "parents" in db_revision:
for parent in db_revision["parents"]:
if parent:
parents.append(parent)
metadata = db_revision["metadata"]
extra_headers = db_revision["extra_headers"]
if not extra_headers:
if metadata and "extra_headers" in metadata:
extra_headers = db_to_git_headers(metadata.pop("extra_headers"))
else:
# For older versions of the database that were not migrated to schema v161
extra_headers = ()
return Revision(
id=db_revision["id"],
author=author,
date=date,
committer=committer,
committer_date=committer_date,
type=RevisionType(db_revision["type"]),
directory=db_revision["directory"],
message=db_revision["message"],
metadata=metadata,
synthetic=db_revision["synthetic"],
extra_headers=extra_headers,
parents=tuple(parents),
raw_manifest=db_revision["raw_manifest"],
)
def release_to_db(release: Release) -> Dict[str, Any]:
- """Convert a swh-model release to its database representation.
- """
+ """Convert a swh-model release to its database representation."""
author = author_to_db(release.author)
date = date_to_db(release.date)
return {
"id": release.id,
"author_fullname": author["fullname"],
"author_name": author["name"],
"author_email": author["email"],
"date": date["timestamp"],
"date_offset": date["offset"],
"date_neg_utc_offset": date["neg_utc_offset"],
"date_offset_bytes": date["offset_bytes"],
"name": release.name,
"target": release.target,
"target_type": release.target_type.value,
"comment": release.message,
"synthetic": release.synthetic,
"raw_manifest": release.raw_manifest,
}
def db_to_release(db_release: Dict[str, Any]) -> Optional[Release]:
"""Convert a database representation of a release to its swh-model
representation.
"""
if db_release["target_type"] is None:
assert all(v is None for (k, v) in db_release.items() if k != "id")
return None
author = db_to_author(
db_release["author_fullname"],
db_release["author_name"],
db_release["author_email"],
)
- date = db_to_date(db_release["date"], db_release["date_offset_bytes"],)
+ date = db_to_date(
+ db_release["date"],
+ db_release["date_offset_bytes"],
+ )
return Release(
author=author,
date=date,
id=db_release["id"],
name=db_release["name"],
message=db_release["comment"],
synthetic=db_release["synthetic"],
target=db_release["target"],
target_type=ObjectType(db_release["target_type"]),
raw_manifest=db_release["raw_manifest"],
)
def db_to_raw_extrinsic_metadata(row) -> RawExtrinsicMetadata:
target = row["raw_extrinsic_metadata.target"]
if not target.startswith("swh:1:"):
warnings.warn(
"Fetching raw_extrinsic_metadata row with URL target", DeprecationWarning
)
target = str(Origin(url=target).swhid())
return RawExtrinsicMetadata(
target=ExtendedSWHID.from_string(target),
authority=MetadataAuthority(
type=MetadataAuthorityType(row["metadata_authority.type"]),
url=row["metadata_authority.url"],
),
fetcher=MetadataFetcher(
- name=row["metadata_fetcher.name"], version=row["metadata_fetcher.version"],
+ name=row["metadata_fetcher.name"],
+ version=row["metadata_fetcher.version"],
),
discovery_date=row["discovery_date"],
format=row["format"],
metadata=row["raw_extrinsic_metadata.metadata"],
origin=row["origin"],
visit=row["visit"],
snapshot=map_optional(CoreSWHID.from_string, row["snapshot"]),
release=map_optional(CoreSWHID.from_string, row["release"]),
revision=map_optional(CoreSWHID.from_string, row["revision"]),
path=row["path"],
directory=map_optional(CoreSWHID.from_string, row["directory"]),
)
def db_to_extid(row) -> ExtID:
return ExtID(
extid=row["extid"],
extid_type=row["extid_type"],
extid_version=row.get("extid_version", 0),
target=CoreSWHID(
object_id=row["target"],
object_type=SwhidObjectType[row["target_type"].upper()],
),
)
diff --git a/swh/storage/postgresql/db.py b/swh/storage/postgresql/db.py
index 51045f4a..8e908105 100644
--- a/swh/storage/postgresql/db.py
+++ b/swh/storage/postgresql/db.py
@@ -1,1572 +1,1570 @@
# Copyright (C) 2015-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
import logging
import random
from typing import Any, Dict, Iterable, List, Optional, Tuple
from swh.core.db import BaseDb
from swh.core.db.db_utils import execute_values_generator
from swh.core.db.db_utils import jsonize as _jsonize
from swh.core.db.db_utils import stored_procedure
from swh.model.hashutil import DEFAULT_ALGORITHMS
from swh.model.model import SHA1_SIZE, OriginVisit, OriginVisitStatus, Sha1Git
from swh.model.swhids import ObjectType
from swh.storage.interface import ListOrder
logger = logging.getLogger(__name__)
def jsonize(d):
return _jsonize(dict(d) if d is not None else None)
class Db(BaseDb):
- """Proxy to the SWH DB, with wrappers around stored procedures
-
- """
+ """Proxy to the SWH DB, with wrappers around stored procedures"""
current_version = 182
def mktemp_dir_entry(self, entry_type, cur=None):
self._cursor(cur).execute(
"SELECT swh_mktemp_dir_entry(%s)", (("directory_entry_%s" % entry_type),)
)
@stored_procedure("swh_mktemp_revision")
def mktemp_revision(self, cur=None):
pass
@stored_procedure("swh_mktemp_release")
def mktemp_release(self, cur=None):
pass
@stored_procedure("swh_mktemp_snapshot_branch")
def mktemp_snapshot_branch(self, cur=None):
pass
@stored_procedure("swh_content_add")
def content_add_from_temp(self, cur=None):
pass
@stored_procedure("swh_directory_add")
def directory_add_from_temp(self, cur=None):
pass
@stored_procedure("swh_skipped_content_add")
def skipped_content_add_from_temp(self, cur=None):
pass
@stored_procedure("swh_revision_add")
def revision_add_from_temp(self, cur=None):
pass
@stored_procedure("swh_extid_add")
def extid_add_from_temp(self, cur=None):
pass
@stored_procedure("swh_release_add")
def release_add_from_temp(self, cur=None):
pass
def content_update_from_temp(self, keys_to_update, cur=None):
cur = self._cursor(cur)
cur.execute(
"""select swh_content_update(ARRAY[%s] :: text[])""" % keys_to_update
)
content_get_metadata_keys = [
"sha1",
"sha1_git",
"sha256",
"blake2s256",
"length",
"status",
]
content_add_keys = content_get_metadata_keys + ["ctime"]
skipped_content_keys = [
"sha1",
"sha1_git",
"sha256",
"blake2s256",
"length",
"reason",
"status",
"origin",
]
def content_get_metadata_from_hashes(
self, hashes: List[bytes], algo: str, cur=None
):
cur = self._cursor(cur)
assert algo in DEFAULT_ALGORITHMS
query = f"""
select {", ".join(self.content_get_metadata_keys)}
from (values %s) as t (hash)
inner join content on (content.{algo}=hash)
"""
yield from execute_values_generator(
- cur, query, ((hash_,) for hash_ in hashes),
+ cur,
+ query,
+ ((hash_,) for hash_ in hashes),
)
def content_get_range(self, start, end, limit=None, cur=None):
- """Retrieve contents within range [start, end].
-
- """
+ """Retrieve contents within range [start, end]."""
cur = self._cursor(cur)
query = """select %s from content
where %%s <= sha1 and sha1 <= %%s
order by sha1
limit %%s""" % ", ".join(
self.content_get_metadata_keys
)
cur.execute(query, (start, end, limit))
yield from cur
content_hash_keys = ["sha1", "sha1_git", "sha256", "blake2s256"]
def content_missing_from_list(self, contents, cur=None):
cur = self._cursor(cur)
keys = ", ".join(self.content_hash_keys)
equality = " AND ".join(
("t.%s = c.%s" % (key, key)) for key in self.content_hash_keys
)
yield from execute_values_generator(
cur,
"""
SELECT %s
FROM (VALUES %%s) as t(%s)
WHERE NOT EXISTS (
SELECT 1 FROM content c
WHERE %s
)
"""
% (keys, keys, equality),
(tuple(c[key] for key in self.content_hash_keys) for c in contents),
)
def content_missing_per_sha1(self, sha1s, cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
SELECT t.sha1 FROM (VALUES %s) AS t(sha1)
WHERE NOT EXISTS (
SELECT 1 FROM content c WHERE c.sha1 = t.sha1
)""",
((sha1,) for sha1 in sha1s),
)
def content_missing_per_sha1_git(self, contents, cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
SELECT t.sha1_git FROM (VALUES %s) AS t(sha1_git)
WHERE NOT EXISTS (
SELECT 1 FROM content c WHERE c.sha1_git = t.sha1_git
)""",
((sha1,) for sha1 in contents),
)
def skipped_content_missing(self, contents, cur=None):
if not contents:
return []
cur = self._cursor(cur)
query = """SELECT * FROM (VALUES %s) AS t (%s)
WHERE not exists
(SELECT 1 FROM skipped_content s WHERE
s.sha1 is not distinct from t.sha1::sha1 and
s.sha1_git is not distinct from t.sha1_git::sha1 and
s.sha256 is not distinct from t.sha256::bytea);""" % (
(", ".join("%s" for _ in contents)),
", ".join(self.content_hash_keys),
)
cur.execute(
query,
[tuple(cont[key] for key in self.content_hash_keys) for cont in contents],
)
yield from cur
def snapshot_exists(self, snapshot_id, cur=None):
"""Check whether a snapshot with the given id exists"""
cur = self._cursor(cur)
cur.execute("""SELECT 1 FROM snapshot where id=%s""", (snapshot_id,))
return bool(cur.fetchone())
def snapshot_missing_from_list(self, snapshots, cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
SELECT id FROM (VALUES %s) as t(id)
WHERE NOT EXISTS (
SELECT 1 FROM snapshot d WHERE d.id = t.id
)
""",
((id,) for id in snapshots),
)
def snapshot_add(self, snapshot_id, cur=None):
"""Add a snapshot from the temporary table"""
cur = self._cursor(cur)
cur.execute("""SELECT swh_snapshot_add(%s)""", (snapshot_id,))
snapshot_count_cols = ["target_type", "count"]
def snapshot_count_branches(
- self, snapshot_id, branch_name_exclude_prefix=None, cur=None,
+ self,
+ snapshot_id,
+ branch_name_exclude_prefix=None,
+ cur=None,
):
cur = self._cursor(cur)
query = """\
SELECT %s FROM swh_snapshot_count_branches(%%s, %%s)
""" % ", ".join(
self.snapshot_count_cols
)
cur.execute(query, (snapshot_id, branch_name_exclude_prefix))
yield from cur
snapshot_get_cols = ["snapshot_id", "name", "target", "target_type"]
def snapshot_get_by_id(
self,
snapshot_id,
branches_from=b"",
branches_count=None,
target_types=None,
branch_name_include_substring=None,
branch_name_exclude_prefix=None,
cur=None,
):
cur = self._cursor(cur)
query = """\
SELECT %s
FROM swh_snapshot_get_by_id(%%s, %%s, %%s, %%s :: snapshot_target[], %%s, %%s)
""" % ", ".join(
self.snapshot_get_cols
)
cur.execute(
query,
(
snapshot_id,
branches_from,
branches_count,
target_types,
branch_name_include_substring,
branch_name_exclude_prefix,
),
)
yield from cur
def snapshot_get_random(self, cur=None):
return self._get_random_row_from_table("snapshot", ["id"], "id", cur)
content_find_cols = [
"sha1",
"sha1_git",
"sha256",
"blake2s256",
"length",
"ctime",
"status",
]
def content_find(
self,
sha1: Optional[bytes] = None,
sha1_git: Optional[bytes] = None,
sha256: Optional[bytes] = None,
blake2s256: Optional[bytes] = None,
cur=None,
):
"""Find the content optionally on a combination of the following
checksums sha1, sha1_git, sha256 or blake2s256.
Args:
sha1: sha1 content
git_sha1: the sha1 computed `a la git` sha1 of the content
sha256: sha256 content
blake2s256: blake2s256 content
Returns:
The tuple (sha1, sha1_git, sha256, blake2s256) if found or None.
"""
cur = self._cursor(cur)
checksum_dict = {
"sha1": sha1,
"sha1_git": sha1_git,
"sha256": sha256,
"blake2s256": blake2s256,
}
query_parts = [f"SELECT {','.join(self.content_find_cols)} FROM content WHERE "]
query_params = []
where_parts = []
# Adds only those keys which have values exist
for algorithm in checksum_dict:
if checksum_dict[algorithm] is not None:
where_parts.append(f"{algorithm} = %s")
query_params.append(checksum_dict[algorithm])
query_parts.append(" AND ".join(where_parts))
query = "\n".join(query_parts)
cur.execute(query, query_params)
content = cur.fetchall()
return content
def content_get_random(self, cur=None):
return self._get_random_row_from_table("content", ["sha1_git"], "sha1_git", cur)
def directory_missing_from_list(self, directories, cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
SELECT id FROM (VALUES %s) as t(id)
WHERE NOT EXISTS (
SELECT 1 FROM directory d WHERE d.id = t.id
)
""",
((id,) for id in directories),
)
directory_ls_cols = [
"dir_id",
"type",
"target",
"name",
"perms",
"status",
"sha1",
"sha1_git",
"sha256",
"length",
]
def directory_walk_one(self, directory, cur=None):
cur = self._cursor(cur)
cols = ", ".join(self.directory_ls_cols)
query = "SELECT %s FROM swh_directory_walk_one(%%s)" % cols
cur.execute(query, (directory,))
yield from cur
def directory_walk(self, directory, cur=None):
cur = self._cursor(cur)
cols = ", ".join(self.directory_ls_cols)
query = "SELECT %s FROM swh_directory_walk(%%s)" % cols
cur.execute(query, (directory,))
yield from cur
def directory_entry_get_by_path(self, directory, paths, cur=None):
- """Retrieve a directory entry by path.
-
- """
+ """Retrieve a directory entry by path."""
cur = self._cursor(cur)
cols = ", ".join(self.directory_ls_cols)
query = "SELECT %s FROM swh_find_directory_entry_by_path(%%s, %%s)" % cols
cur.execute(query, (directory, paths))
data = cur.fetchone()
if set(data) == {None}:
return None
return data
directory_get_entries_cols = ["type", "target", "name", "perms"]
def directory_get_entries(self, directory: Sha1Git, cur=None) -> List[Tuple]:
cur = self._cursor(cur)
cur.execute(
"SELECT * FROM swh_directory_get_entries(%s::sha1_git)", (directory,)
)
return list(cur)
def directory_get_raw_manifest(
self, directory_ids: List[Sha1Git], cur=None
) -> Iterable[Tuple[Sha1Git, bytes]]:
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
SELECT t.id, raw_manifest FROM (VALUES %s) as t(id)
INNER JOIN directory ON (t.id=directory.id)
""",
((id_,) for id_ in directory_ids),
)
def directory_get_random(self, cur=None):
return self._get_random_row_from_table("directory", ["id"], "id", cur)
def revision_missing_from_list(self, revisions, cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
SELECT id FROM (VALUES %s) as t(id)
WHERE NOT EXISTS (
SELECT 1 FROM revision r WHERE r.id = t.id
)
""",
((id,) for id in revisions),
)
revision_add_cols = [
"id",
"date",
"date_offset",
"date_neg_utc_offset",
"date_offset_bytes",
"committer_date",
"committer_date_offset",
"committer_date_neg_utc_offset",
"committer_date_offset_bytes",
"type",
"directory",
"message",
"author_fullname",
"author_name",
"author_email",
"committer_fullname",
"committer_name",
"committer_email",
"metadata",
"synthetic",
"extra_headers",
"raw_manifest",
]
revision_get_cols = revision_add_cols + ["parents"]
def origin_visit_add(self, origin, ts, type, cur=None):
"""Add a new origin_visit for origin origin at timestamp ts.
Args:
origin: origin concerned by the visit
ts: the date of the visit
type: type of loader for the visit
Returns:
The new visit index step for that origin
"""
cur = self._cursor(cur)
self._cursor(cur).execute(
"SELECT swh_origin_visit_add(%s, %s, %s)", (origin, ts, type)
)
return cur.fetchone()[0]
origin_visit_status_cols = [
"origin",
"visit",
"date",
"type",
"status",
"snapshot",
"metadata",
]
def origin_visit_status_add(
self, visit_status: OriginVisitStatus, cur=None
) -> None:
- """Add new origin visit status
-
- """
+ """Add new origin visit status"""
assert self.origin_visit_status_cols[0] == "origin"
assert self.origin_visit_status_cols[-1] == "metadata"
cols = self.origin_visit_status_cols[1:-1]
cur = self._cursor(cur)
cur.execute(
f"WITH origin_id as (select id from origin where url=%s) "
f"INSERT INTO origin_visit_status "
f"(origin, {', '.join(cols)}, metadata) "
f"VALUES ((select id from origin_id), "
f"{', '.join(['%s']*len(cols))}, %s) "
f"ON CONFLICT (origin, visit, date) do nothing",
[visit_status.origin]
+ [getattr(visit_status, key) for key in cols]
+ [jsonize(visit_status.metadata)],
)
origin_visit_cols = ["origin", "visit", "date", "type"]
def origin_visit_add_with_id(self, origin_visit: OriginVisit, cur=None) -> None:
- """Insert origin visit when id are already set
-
- """
+ """Insert origin visit when id are already set"""
ov = origin_visit
assert ov.visit is not None
cur = self._cursor(cur)
query = """INSERT INTO origin_visit ({cols})
VALUES ((select id from origin where url=%s), {values})
ON CONFLICT (origin, visit) DO NOTHING""".format(
cols=", ".join(self.origin_visit_cols),
values=", ".join("%s" for col in self.origin_visit_cols[1:]),
)
cur.execute(query, (ov.origin, ov.visit, ov.date, ov.type))
origin_visit_get_cols = [
"origin",
"visit",
"date",
"type",
"status",
"metadata",
"snapshot",
]
origin_visit_select_cols = [
"o.url AS origin",
"ov.visit",
"ov.date",
"ov.type AS type",
"ovs.status",
"ovs.snapshot",
"ovs.metadata",
]
origin_visit_status_select_cols = [
"o.url AS origin",
"ovs.visit",
"ovs.date",
"ovs.type AS type",
"ovs.status",
"ovs.snapshot",
"ovs.metadata",
]
def _make_origin_visit_status(
self, row: Optional[Tuple[Any]]
) -> Optional[Dict[str, Any]]:
- """Make an origin_visit_status dict out of a row
-
- """
+ """Make an origin_visit_status dict out of a row"""
if not row:
return None
return dict(zip(self.origin_visit_status_cols, row))
def origin_visit_status_get_latest(
self,
origin_url: str,
visit: int,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
cur=None,
) -> Optional[Dict[str, Any]]:
- """Given an origin visit id, return its latest origin_visit_status
-
- """
+ """Given an origin visit id, return its latest origin_visit_status"""
cur = self._cursor(cur)
query_parts = [
"SELECT %s" % ", ".join(self.origin_visit_status_select_cols),
"FROM origin_visit_status ovs ",
"INNER JOIN origin o ON o.id = ovs.origin",
]
query_parts.append("WHERE o.url = %s")
query_params: List[Any] = [origin_url]
query_parts.append("AND ovs.visit = %s")
query_params.append(visit)
if require_snapshot:
query_parts.append("AND ovs.snapshot is not null")
if allowed_statuses:
query_parts.append("AND ovs.status IN %s")
query_params.append(tuple(allowed_statuses))
query_parts.append("ORDER BY ovs.date DESC LIMIT 1")
query = "\n".join(query_parts)
cur.execute(query, tuple(query_params))
row = cur.fetchone()
return self._make_origin_visit_status(row)
def origin_visit_status_get_range(
self,
origin: str,
visit: int,
date_from: Optional[datetime.datetime],
order: ListOrder,
limit: int,
cur=None,
):
- """Retrieve visit_status rows for visit (origin, visit) in a paginated way.
-
- """
+ """Retrieve visit_status rows for visit (origin, visit) in a paginated way."""
cur = self._cursor(cur)
query_parts = [
f"SELECT {', '.join(self.origin_visit_status_select_cols)} "
"FROM origin_visit_status ovs ",
"INNER JOIN origin o ON o.id = ovs.origin ",
]
query_parts.append("WHERE o.url = %s AND ovs.visit = %s ")
query_params: List[Any] = [origin, visit]
if date_from is not None:
op_comparison = ">=" if order == ListOrder.ASC else "<="
query_parts.append(f"and ovs.date {op_comparison} %s ")
query_params.append(date_from)
if order == ListOrder.ASC:
query_parts.append("ORDER BY ovs.date ASC ")
elif order == ListOrder.DESC:
query_parts.append("ORDER BY ovs.date DESC ")
else:
assert False
query_parts.append("LIMIT %s")
query_params.append(limit)
query = "\n".join(query_parts)
cur.execute(query, tuple(query_params))
yield from cur
def origin_visit_get_range(
- self, origin: str, visit_from: int, order: ListOrder, limit: int, cur=None,
+ self,
+ origin: str,
+ visit_from: int,
+ order: ListOrder,
+ limit: int,
+ cur=None,
):
cur = self._cursor(cur)
origin_visit_cols = ["o.url as origin", "ov.visit", "ov.date", "ov.type"]
query_parts = [
f"SELECT {', '.join(origin_visit_cols)} FROM origin_visit ov ",
"INNER JOIN origin o ON o.id = ov.origin ",
]
query_parts.append("WHERE o.url = %s")
query_params: List[Any] = [origin]
if visit_from > 0:
op_comparison = ">" if order == ListOrder.ASC else "<"
query_parts.append(f"and ov.visit {op_comparison} %s")
query_params.append(visit_from)
if order == ListOrder.ASC:
query_parts.append("ORDER BY ov.visit ASC")
elif order == ListOrder.DESC:
query_parts.append("ORDER BY ov.visit DESC")
query_parts.append("LIMIT %s")
query_params.append(limit)
query = "\n".join(query_parts)
cur.execute(query, tuple(query_params))
yield from cur
def origin_visit_status_get_all_in_range(
self,
origin: str,
allowed_statuses: Optional[List[str]],
require_snapshot: bool,
visit_from: int,
visit_to: int,
cur=None,
):
cur = self._cursor(cur)
query_parts = [
f"SELECT {', '.join(self.origin_visit_status_select_cols)}",
" FROM origin_visit_status ovs",
" INNER JOIN origin o ON o.id = ovs.origin",
]
query_parts.append("WHERE o.url = %s")
query_params: List[Any] = [origin]
assert visit_from <= visit_to
query_parts.append("AND ovs.visit >= %s")
query_params.append(visit_from)
query_parts.append("AND ovs.visit <= %s")
query_params.append(visit_to)
if require_snapshot:
query_parts.append("AND ovs.snapshot is not null")
if allowed_statuses:
query_parts.append("AND ovs.status IN %s")
query_params.append(tuple(allowed_statuses))
query_parts.append("ORDER BY ovs.visit ASC, ovs.date ASC")
query = "\n".join(query_parts)
cur.execute(query, tuple(query_params))
yield from cur
def origin_visit_get(self, origin_id, visit_id, cur=None):
"""Retrieve information on visit visit_id of origin origin_id.
Args:
origin_id: the origin concerned
visit_id: The visit step for that origin
Returns:
The origin_visit information
"""
cur = self._cursor(cur)
query = """\
SELECT %s
FROM origin_visit ov
INNER JOIN origin o ON o.id = ov.origin
INNER JOIN origin_visit_status ovs USING (origin, visit)
WHERE o.url = %%s AND ov.visit = %%s
ORDER BY ovs.date DESC
LIMIT 1
""" % (
", ".join(self.origin_visit_select_cols)
)
cur.execute(query, (origin_id, visit_id))
r = cur.fetchall()
if not r:
return None
return r[0]
def origin_visit_find_by_date(self, origin, visit_date, cur=None):
cur = self._cursor(cur)
cur.execute(
"SELECT * FROM swh_visit_find_by_date(%s, %s)", (origin, visit_date)
)
rows = cur.fetchall()
if rows:
visit = dict(zip(self.origin_visit_get_cols, rows[0]))
visit["origin"] = origin
return visit
def origin_visit_exists(self, origin_id, visit_id, cur=None):
"""Check whether an origin visit with the given ids exists"""
cur = self._cursor(cur)
query = "SELECT 1 FROM origin_visit where origin = %s AND visit = %s"
cur.execute(query, (origin_id, visit_id))
return bool(cur.fetchone())
def origin_visit_get_latest(
self,
origin_id: str,
type: Optional[str],
allowed_statuses: Optional[Iterable[str]],
require_snapshot: bool,
cur=None,
):
"""Retrieve the most recent origin_visit of the given origin,
with optional filters.
Args:
origin_id: the origin concerned
type: Optional visit type to filter on
allowed_statuses: the visit statuses allowed for the returned visit
require_snapshot (bool): If True, only a visit with a known
snapshot will be returned.
Returns:
The origin_visit information, or None if no visit matches.
"""
cur = self._cursor(cur)
query_parts = [
"SELECT %s" % ", ".join(self.origin_visit_select_cols),
"FROM origin_visit ov ",
"INNER JOIN origin o ON o.id = ov.origin",
"INNER JOIN origin_visit_status ovs USING (origin, visit)",
]
query_parts.append(
"WHERE ov.origin = (SELECT id FROM origin o WHERE o.url = %s)"
)
query_params: List[Any] = [origin_id]
if type is not None:
query_parts.append("AND ov.type = %s")
query_params.append(type)
if require_snapshot:
query_parts.append("AND ovs.snapshot is not null")
if allowed_statuses:
query_parts.append("AND ovs.status IN %s")
query_params.append(tuple(allowed_statuses))
query_parts.append("ORDER BY ov.visit DESC, ovs.date DESC LIMIT 1")
query = "\n".join(query_parts)
cur.execute(query, tuple(query_params))
r = cur.fetchone()
if not r:
return None
return r
def origin_visit_get_random(self, type, cur=None):
"""Randomly select one origin visit that was full and in the last 3
- months
+ months
"""
cur = self._cursor(cur)
columns = ",".join(self.origin_visit_select_cols)
query = f"""select {columns}
from origin_visit ov
inner join origin o on ov.origin=o.id
inner join origin_visit_status ovs using (origin, visit)
where ovs.status='full'
and ov.type=%s
and ov.date > now() - '3 months'::interval
and random() < 0.1
limit 1
"""
cur.execute(query, (type,))
return cur.fetchone()
@staticmethod
def mangle_query_key(key, main_table, ignore_displayname=False):
if key == "id":
return "t.id"
if key == "parents":
return """
ARRAY(
SELECT rh.parent_id::bytea
FROM revision_history rh
WHERE rh.id = t.id
ORDER BY rh.parent_rank
)"""
if "_" not in key:
return f"{main_table}.{key}"
head, tail = key.split("_", 1)
if head not in ("author", "committer") or tail not in (
"name",
"email",
"id",
"fullname",
):
return f"{main_table}.{key}"
if ignore_displayname:
return f"{head}.{tail}"
else:
if tail == "id":
return f"{head}.{tail}"
elif tail in ("name", "email"):
# These fields get populated again from fullname by
# converters.db_to_author if they're None, so we can just NULLify them
# when displayname is set.
return (
f"CASE"
f" WHEN {head}.displayname IS NULL THEN {head}.{tail} "
f" ELSE NULL "
f"END AS {key}"
)
elif tail == "fullname":
return f"COALESCE({head}.displayname, {head}.fullname) AS {key}"
assert False, "All cases should have been handled here"
def revision_get_from_list(self, revisions, ignore_displayname=False, cur=None):
cur = self._cursor(cur)
query_keys = ", ".join(
self.mangle_query_key(k, "revision", ignore_displayname)
for k in self.revision_get_cols
)
yield from execute_values_generator(
cur,
"""
SELECT %s FROM (VALUES %%s) as t(sortkey, id)
LEFT JOIN revision ON t.id = revision.id
LEFT JOIN person author ON revision.author = author.id
LEFT JOIN person committer ON revision.committer = committer.id
ORDER BY sortkey
"""
% query_keys,
((sortkey, id) for sortkey, id in enumerate(revisions)),
)
extid_cols = ["extid", "extid_version", "extid_type", "target", "target_type"]
def extid_get_from_extid_list(
self, extid_type: str, ids: List[bytes], version: Optional[int] = None, cur=None
):
cur = self._cursor(cur)
query_keys = ", ".join(
self.mangle_query_key(k, "extid") for k in self.extid_cols
)
filter_query = ""
if version is not None:
filter_query = cur.mogrify(
f"WHERE extid_version={version}", (version,)
).decode()
sql = f"""
SELECT {query_keys}
FROM (VALUES %s) as t(sortkey, extid, extid_type)
LEFT JOIN extid USING (extid, extid_type)
{filter_query}
ORDER BY sortkey
"""
yield from execute_values_generator(
cur,
sql,
(((sortkey, extid, extid_type) for sortkey, extid in enumerate(ids))),
)
def extid_get_from_swhid_list(
self,
target_type: str,
ids: List[bytes],
extid_version: Optional[int] = None,
extid_type: Optional[str] = None,
cur=None,
):
cur = self._cursor(cur)
target_type = ObjectType(
target_type
).name.lower() # aka "rev" -> "revision", ...
query_keys = ", ".join(
self.mangle_query_key(k, "extid") for k in self.extid_cols
)
filter_query = ""
if extid_version is not None and extid_type is not None:
filter_query = cur.mogrify(
- "WHERE extid_version=%s AND extid_type=%s", (extid_version, extid_type,)
+ "WHERE extid_version=%s AND extid_type=%s",
+ (
+ extid_version,
+ extid_type,
+ ),
).decode()
sql = f"""
SELECT {query_keys}
FROM (VALUES %s) as t(sortkey, target, target_type)
LEFT JOIN extid USING (target, target_type)
{filter_query}
ORDER BY sortkey
"""
yield from execute_values_generator(
cur,
sql,
(((sortkey, target, target_type) for sortkey, target in enumerate(ids))),
template=b"(%s,%s,%s::object_type)",
)
def revision_log(
self, root_revisions, ignore_displayname=False, limit=None, cur=None
):
cur = self._cursor(cur)
query = """\
SELECT %s
FROM swh_revision_log(
"root_revisions" := %%s, num_revs := %%s, "ignore_displayname" := %%s
)""" % ", ".join(
self.revision_get_cols
)
cur.execute(query, (root_revisions, limit, ignore_displayname))
yield from cur
revision_shortlog_cols = ["id", "parents"]
def revision_shortlog(self, root_revisions, limit=None, cur=None):
cur = self._cursor(cur)
query = """SELECT %s
FROM swh_revision_list(%%s, %%s)
""" % ", ".join(
self.revision_shortlog_cols
)
cur.execute(query, (root_revisions, limit))
yield from cur
def revision_get_random(self, cur=None):
return self._get_random_row_from_table("revision", ["id"], "id", cur)
def release_missing_from_list(self, releases, cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
SELECT id FROM (VALUES %s) as t(id)
WHERE NOT EXISTS (
SELECT 1 FROM release r WHERE r.id = t.id
)
""",
((id,) for id in releases),
)
object_find_by_sha1_git_cols = ["sha1_git", "type"]
def object_find_by_sha1_git(self, ids, cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
"""
WITH t (sha1_git) AS (VALUES %s),
known_objects as ((
select
id as sha1_git,
'release'::object_type as type,
object_id
from release r
where exists (select 1 from t where t.sha1_git = r.id)
) union all (
select
id as sha1_git,
'revision'::object_type as type,
object_id
from revision r
where exists (select 1 from t where t.sha1_git = r.id)
) union all (
select
id as sha1_git,
'directory'::object_type as type,
object_id
from directory d
where exists (select 1 from t where t.sha1_git = d.id)
) union all (
select
sha1_git as sha1_git,
'content'::object_type as type,
object_id
from content c
where exists (select 1 from t where t.sha1_git = c.sha1_git)
))
select t.sha1_git as sha1_git, k.type
from t
left join known_objects k on t.sha1_git = k.sha1_git
""",
((id,) for id in ids),
)
def stat_counters(self, cur=None):
cur = self._cursor(cur)
cur.execute("SELECT * FROM swh_stat_counters()")
yield from cur
def origin_add(self, url, cur=None):
"""Insert a new origin and return the new identifier."""
insert = """INSERT INTO origin (url) values (%s)
ON CONFLICT DO NOTHING
"""
cur.execute(insert, (url,))
return cur.rowcount
origin_cols = ["url"]
def origin_get_by_url(self, origins, cur=None):
"""Retrieve origin `(type, url)` from urls if found."""
cur = self._cursor(cur)
query = """SELECT %s FROM (VALUES %%s) as t(url)
LEFT JOIN origin ON t.url = origin.url
""" % ",".join(
"origin." + col for col in self.origin_cols
)
yield from execute_values_generator(cur, query, ((url,) for url in origins))
def origin_get_by_sha1(self, sha1s, cur=None):
"""Retrieve origin urls from sha1s if found."""
cur = self._cursor(cur)
query = """SELECT %s FROM (VALUES %%s) as t(sha1)
LEFT JOIN origin ON t.sha1 = digest(origin.url, 'sha1')
""" % ",".join(
"origin." + col for col in self.origin_cols
)
yield from execute_values_generator(cur, query, ((sha1,) for sha1 in sha1s))
def origin_id_get_by_url(self, origins, cur=None):
"""Retrieve origin `(type, url)` from urls if found."""
cur = self._cursor(cur)
query = """SELECT id FROM (VALUES %s) as t(url)
LEFT JOIN origin ON t.url = origin.url
"""
for row in execute_values_generator(cur, query, ((url,) for url in origins)):
yield row[0]
origin_get_range_cols = ["id", "url"]
def origin_get_range(self, origin_from: int = 1, origin_count: int = 100, cur=None):
"""Retrieve ``origin_count`` origins whose ids are greater
or equal than ``origin_from``.
Origins are sorted by id before retrieving them.
Args:
origin_from: the minimum id of origins to retrieve
origin_count: the maximum number of origins to retrieve
"""
cur = self._cursor(cur)
query = """SELECT %s
FROM origin WHERE id >= %%s
ORDER BY id LIMIT %%s
""" % ",".join(
self.origin_get_range_cols
)
cur.execute(query, (origin_from, origin_count))
yield from cur
def _origin_query(
self,
url_pattern,
count=False,
offset=0,
limit=50,
regexp=False,
with_visit=False,
visit_types=None,
cur=None,
):
"""
Method factorizing query creation for searching and counting origins.
"""
cur = self._cursor(cur)
if count:
origin_cols = "COUNT(*)"
order_clause = ""
else:
origin_cols = ",".join(self.origin_cols)
order_clause = "ORDER BY id"
if not regexp:
operator = "ILIKE"
query_params = [f"%{url_pattern}%"]
else:
operator = "~*"
query_params = [url_pattern]
query = f"""
WITH filtered_origins AS (
SELECT *
FROM origin
WHERE url {operator} %s
{order_clause}
)
SELECT {origin_cols}
FROM filtered_origins AS o
"""
if with_visit or visit_types:
visit_predicat = (
"""
INNER JOIN origin_visit_status ovs USING (origin, visit)
INNER JOIN snapshot ON ovs.snapshot=snapshot.id
"""
if with_visit
else ""
)
type_predicat = (
f"AND ov.type=any(ARRAY{visit_types})" if visit_types else ""
)
query += f"""
WHERE EXISTS (
SELECT 1
FROM origin_visit ov
{visit_predicat}
WHERE ov.origin=o.id {type_predicat}
)
"""
if not count:
query += "OFFSET %s LIMIT %s"
query_params.extend([offset, limit])
cur.execute(query, query_params)
def origin_search(
self,
url_pattern: str,
offset: int = 0,
limit: int = 50,
regexp: bool = False,
with_visit: bool = False,
visit_types: Optional[List[str]] = None,
cur=None,
):
"""Search for origins whose urls contain a provided string pattern
or match a provided regular expression.
The search is performed in a case insensitive way.
Args:
url_pattern: the string pattern to search for in origin urls
offset: number of found origins to skip before returning
results
limit: the maximum number of found origins to return
regexp: if True, consider the provided pattern as a regular
expression and returns origins whose urls match it
with_visit: if True, filter out origins with no visit
"""
self._origin_query(
url_pattern,
offset=offset,
limit=limit,
regexp=regexp,
with_visit=with_visit,
visit_types=visit_types,
cur=cur,
)
yield from cur
def origin_count(self, url_pattern, regexp=False, with_visit=False, cur=None):
"""Count origins whose urls contain a provided string pattern
or match a provided regular expression.
The pattern search in origin urls is performed in a case insensitive
way.
Args:
url_pattern (str): the string pattern to search for in origin urls
regexp (bool): if True, consider the provided pattern as a regular
expression and returns origins whose urls match it
with_visit (bool): if True, filter out origins with no visit
"""
self._origin_query(
url_pattern, count=True, regexp=regexp, with_visit=with_visit, cur=cur
)
return cur.fetchone()[0]
release_add_cols = [
"id",
"target",
"target_type",
"date",
"date_offset",
"date_neg_utc_offset",
"date_offset_bytes",
"name",
"comment",
"synthetic",
"raw_manifest",
"author_fullname",
"author_name",
"author_email",
]
release_get_cols = release_add_cols
def origin_snapshot_get_all(self, origin_url: str, cur=None) -> Iterable[Sha1Git]:
cur = self._cursor(cur)
query = f"""\
SELECT DISTINCT snapshot FROM origin_visit_status ovs
INNER JOIN origin o ON o.id = ovs.origin
WHERE o.url = '{origin_url}' and snapshot IS NOT NULL;
"""
cur.execute(query)
yield from map(lambda row: row[0], cur)
def release_get_from_list(self, releases, ignore_displayname=False, cur=None):
cur = self._cursor(cur)
query_keys = ", ".join(
self.mangle_query_key(k, "release", ignore_displayname)
for k in self.release_get_cols
)
yield from execute_values_generator(
cur,
"""
SELECT %s FROM (VALUES %%s) as t(sortkey, id)
LEFT JOIN release ON t.id = release.id
LEFT JOIN person author ON release.author = author.id
ORDER BY sortkey
"""
% query_keys,
((sortkey, id) for sortkey, id in enumerate(releases)),
)
def release_get_random(self, cur=None):
return self._get_random_row_from_table("release", ["id"], "id", cur)
_raw_extrinsic_metadata_context_cols = [
"origin",
"visit",
"snapshot",
"release",
"revision",
"path",
"directory",
]
"""The list of context columns for all artifact types."""
_raw_extrinsic_metadata_insert_cols = [
"id",
"type",
"target",
"authority_id",
"fetcher_id",
"discovery_date",
"format",
"metadata",
*_raw_extrinsic_metadata_context_cols,
]
"""List of columns of the raw_extrinsic_metadata table, used when writing
metadata."""
_raw_extrinsic_metadata_insert_query = f"""
INSERT INTO raw_extrinsic_metadata
({', '.join(_raw_extrinsic_metadata_insert_cols)})
VALUES ({', '.join('%s' for _ in _raw_extrinsic_metadata_insert_cols)})
ON CONFLICT (id)
DO NOTHING
"""
raw_extrinsic_metadata_get_cols = [
"raw_extrinsic_metadata.target",
"raw_extrinsic_metadata.type",
"discovery_date",
"metadata_authority.type",
"metadata_authority.url",
"metadata_fetcher.id",
"metadata_fetcher.name",
"metadata_fetcher.version",
*_raw_extrinsic_metadata_context_cols,
"format",
"raw_extrinsic_metadata.metadata",
]
"""List of columns of the raw_extrinsic_metadata, metadata_authority,
and metadata_fetcher tables, used when reading object metadata."""
_raw_extrinsic_metadata_select_query = f"""
SELECT
{', '.join(raw_extrinsic_metadata_get_cols)}
FROM raw_extrinsic_metadata
INNER JOIN metadata_authority
ON (metadata_authority.id=authority_id)
INNER JOIN metadata_fetcher ON (metadata_fetcher.id=fetcher_id)
"""
def raw_extrinsic_metadata_add(
self,
id: bytes,
type: str,
target: str,
discovery_date: datetime.datetime,
authority_id: int,
fetcher_id: int,
format: str,
metadata: bytes,
origin: Optional[str],
visit: Optional[int],
snapshot: Optional[str],
release: Optional[str],
revision: Optional[str],
path: Optional[bytes],
directory: Optional[str],
cur,
):
query = self._raw_extrinsic_metadata_insert_query
args: Dict[str, Any] = dict(
id=id,
type=type,
target=target,
authority_id=authority_id,
fetcher_id=fetcher_id,
discovery_date=discovery_date,
format=format,
metadata=metadata,
origin=origin,
visit=visit,
snapshot=snapshot,
release=release,
revision=revision,
path=path,
directory=directory,
)
params = [args[col] for col in self._raw_extrinsic_metadata_insert_cols]
cur.execute(query, params)
def raw_extrinsic_metadata_get(
self,
target: str,
authority_id: int,
after_time: Optional[datetime.datetime],
after_fetcher: Optional[int],
limit: int,
cur,
):
query_parts = [self._raw_extrinsic_metadata_select_query]
query_parts.append("WHERE raw_extrinsic_metadata.target=%s AND authority_id=%s")
args = [target, authority_id]
if after_fetcher is not None:
assert after_time
query_parts.append("AND (discovery_date, fetcher_id) > (%s, %s)")
args.extend([after_time, after_fetcher])
elif after_time is not None:
query_parts.append("AND discovery_date > %s")
args.append(after_time)
query_parts.append("ORDER BY discovery_date, fetcher_id")
if limit:
query_parts.append("LIMIT %s")
args.append(limit)
cur.execute(" ".join(query_parts), args)
yield from cur
def raw_extrinsic_metadata_get_by_ids(self, ids: List[Sha1Git], cur=None):
cur = self._cursor(cur)
yield from execute_values_generator(
cur,
self._raw_extrinsic_metadata_select_query
+ "INNER JOIN (VALUES %s) AS t(id) ON t.id = raw_extrinsic_metadata.id",
[(id_,) for id_ in ids],
)
def raw_extrinsic_metadata_get_authorities(self, id: str, cur=None):
cur = self._cursor(cur)
cur.execute(
"""
SELECT
DISTINCT metadata_authority.type, metadata_authority.url
FROM raw_extrinsic_metadata
INNER JOIN metadata_authority
ON (metadata_authority.id=authority_id)
WHERE raw_extrinsic_metadata.target = %s
""",
(id,),
)
yield from cur
metadata_fetcher_cols = ["name", "version"]
def metadata_fetcher_add(self, name: str, version: str, cur=None) -> None:
cur = self._cursor(cur)
cur.execute(
"INSERT INTO metadata_fetcher (name, version) "
"VALUES (%s, %s) ON CONFLICT DO NOTHING",
(name, version),
)
def metadata_fetcher_get(self, name: str, version: str, cur=None):
cur = self._cursor(cur)
cur.execute(
f"SELECT {', '.join(self.metadata_fetcher_cols)} "
f"FROM metadata_fetcher "
f"WHERE name=%s AND version=%s",
(name, version),
)
return cur.fetchone()
def metadata_fetcher_get_id(
self, name: str, version: str, cur=None
) -> Optional[int]:
cur = self._cursor(cur)
cur.execute(
"SELECT id FROM metadata_fetcher WHERE name=%s AND version=%s",
(name, version),
)
row = cur.fetchone()
if row:
return row[0]
else:
return None
metadata_authority_cols = ["type", "url"]
def metadata_authority_add(self, type: str, url: str, cur=None) -> None:
cur = self._cursor(cur)
cur.execute(
"INSERT INTO metadata_authority (type, url) "
"VALUES (%s, %s) ON CONFLICT DO NOTHING",
(type, url),
)
def metadata_authority_get(self, type: str, url: str, cur=None):
cur = self._cursor(cur)
cur.execute(
f"SELECT {', '.join(self.metadata_authority_cols)} "
f"FROM metadata_authority "
f"WHERE type=%s AND url=%s",
(type, url),
)
return cur.fetchone()
def metadata_authority_get_id(self, type: str, url: str, cur=None) -> Optional[int]:
cur = self._cursor(cur)
cur.execute(
"SELECT id FROM metadata_authority WHERE type=%s AND url=%s", (type, url)
)
row = cur.fetchone()
if row:
return row[0]
else:
return None
def _get_random_row_from_table(self, table_name, cols, id_col, cur=None):
random_sha1 = bytes(random.randint(0, 255) for _ in range(SHA1_SIZE))
cur = self._cursor(cur)
query = """
(SELECT {cols} FROM {table} WHERE {id_col} >= %s
ORDER BY {id_col} LIMIT 1)
UNION
(SELECT {cols} FROM {table} WHERE {id_col} < %s
ORDER BY {id_col} DESC LIMIT 1)
LIMIT 1
""".format(
cols=", ".join(cols), table=table_name, id_col=id_col
)
cur.execute(query, (random_sha1, random_sha1))
row = cur.fetchone()
if row:
return row[0]
dbversion_cols = ["version", "release", "description"]
def dbversion(self):
with self.transaction() as cur:
cur.execute(
f"""
SELECT {', '.join(self.dbversion_cols)}
FROM dbversion
ORDER BY version DESC
LIMIT 1
"""
)
return dict(zip(self.dbversion_cols, cur.fetchone()))
def check_dbversion(self):
dbversion = self.dbversion()["version"]
if dbversion != self.current_version:
logger.warning(
"database dbversion (%s) != %s current_version (%s)",
dbversion,
__name__,
self.current_version,
)
return dbversion == self.current_version
diff --git a/swh/storage/postgresql/storage.py b/swh/storage/postgresql/storage.py
index cdc3106a..8141324a 100644
--- a/swh/storage/postgresql/storage.py
+++ b/swh/storage/postgresql/storage.py
@@ -1,1642 +1,1681 @@
# Copyright (C) 2015-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import base64
from collections import defaultdict
import contextlib
from contextlib import contextmanager
import datetime
import itertools
import operator
from typing import Any, Counter, Dict, Iterable, List, Optional, Sequence, Tuple
import attr
import psycopg2
import psycopg2.errors
import psycopg2.pool
from swh.core.api.serializers import msgpack_dumps, msgpack_loads
from swh.core.db.common import db_transaction, db_transaction_generator
from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex
from swh.model.model import (
SHA1_SIZE,
Content,
Directory,
DirectoryEntry,
ExtID,
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
OriginVisit,
OriginVisitStatus,
RawExtrinsicMetadata,
Release,
Revision,
Sha1,
Sha1Git,
SkippedContent,
Snapshot,
SnapshotBranch,
TargetType,
)
from swh.model.swhids import ExtendedObjectType, ExtendedSWHID, ObjectType
from swh.storage.exc import HashCollision, StorageArgumentException, StorageDBError
from swh.storage.interface import (
VISIT_STATUSES,
ListOrder,
OriginVisitWithStatuses,
PagedResult,
PartialBranches,
)
from swh.storage.objstorage import ObjStorage
from swh.storage.utils import (
extract_collision_hash,
get_partition_bounds_bytes,
map_optional,
now,
)
from swh.storage.writer import JournalWriter
from . import converters
from .db import Db
# Max block size of contents to return
BULK_BLOCK_CONTENT_LEN_MAX = 10000
EMPTY_SNAPSHOT_ID = hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e")
"""Identifier for the empty snapshot"""
VALIDATION_EXCEPTIONS = (
KeyError,
TypeError,
ValueError,
psycopg2.errors.CheckViolation,
psycopg2.errors.IntegrityError,
psycopg2.errors.InvalidTextRepresentation,
psycopg2.errors.NotNullViolation,
psycopg2.errors.NumericValueOutOfRange,
psycopg2.errors.UndefinedFunction, # (raised on wrong argument typs)
)
"""Exceptions raised by postgresql when validation of the arguments
failed."""
@contextlib.contextmanager
def convert_validation_exceptions():
"""Catches postgresql errors related to invalid arguments, and
re-raises a StorageArgumentException."""
try:
yield
except psycopg2.errors.UniqueViolation:
# This only happens because of concurrent insertions, but it is
# a subclass of IntegrityError; so we need to catch and reraise it
# before the next clause converts it to StorageArgumentException.
raise
except VALIDATION_EXCEPTIONS as e:
raise StorageArgumentException(str(e))
class Storage:
- """SWH storage proxy, encompassing DB and object storage
-
- """
+ """SWH storage proxy, encompassing DB and object storage"""
def __init__(
self,
db,
objstorage,
min_pool_conns=1,
max_pool_conns=10,
journal_writer=None,
query_options=None,
):
"""Instantiate a storage instance backed by a PostgreSQL database and an
objstorage.
When ``db`` is passed as a connection string, then this module automatically
manages a connection pool between ``min_pool_conns`` and ``max_pool_conns``.
When ``db`` is an explicit psycopg2 connection, then ``min_pool_conns`` and
``max_pool_conns`` are ignored and the connection is used directly.
Args:
db: either a libpq connection string, or a psycopg2 connection
objstorage: configuration for the backend :class:`ObjStorage`
min_pool_conns: min number of connections in the psycopg2 pool
max_pool_conns: max number of connections in the psycopg2 pool
journal_writer: configuration for the :class:`JournalWriter`
query_options: configuration for the sql connections; keys of the dict are
the method names decorated with :func:`db_transaction` or
:func:`db_transaction_generator` (eg. :func:`content_find`), and values
are dicts (config_name, config_value) used to configure the sql
connection for the method_name. For example, using::
{"content_get": {"statement_timeout": 5000}}
will override the default statement timeout for the :func:`content_get`
endpoint from 500ms to 5000ms.
See :mod:`swh.core.db.common` for more details.
"""
try:
if isinstance(db, psycopg2.extensions.connection):
self._pool = None
self._db = Db(db)
# See comment below
self._db.cursor().execute("SET TIME ZONE 'UTC'")
else:
self._pool = psycopg2.pool.ThreadedConnectionPool(
min_pool_conns, max_pool_conns, db
)
self._db = None
except psycopg2.OperationalError as e:
raise StorageDBError(e)
self.journal_writer = JournalWriter(journal_writer)
self.objstorage = ObjStorage(objstorage)
self.query_options = query_options
def get_db(self):
if self._db:
return self._db
else:
db = Db.from_pool(self._pool)
# Workaround for psycopg2 < 2.9.0 not handling fractional timezones,
# which may happen on old revision/release dates on systems configured
# with non-UTC timezones.
# https://www.psycopg.org/docs/usage.html#time-zones-handling
db.cursor().execute("SET TIME ZONE 'UTC'")
return db
def put_db(self, db):
if db is not self._db:
db.put_conn()
@contextmanager
def db(self):
db = None
try:
db = self.get_db()
yield db
finally:
if db:
self.put_db(db)
@db_transaction()
def check_config(self, *, check_write: bool, db: Db, cur=None) -> bool:
if not self.objstorage.check_config(check_write=check_write):
return False
if not db.check_dbversion():
return False
# Check permissions on one of the tables
if check_write:
check = "INSERT"
else:
check = "SELECT"
cur.execute("select has_table_privilege(current_user, 'content', %s)", (check,))
return cur.fetchone()[0]
@db_transaction()
def get_current_version(self, *, db: Db, cur=None):
"""Returns the current code (expected) version"""
return db.current_version
def _content_unique_key(self, hash, db):
"""Given a hash (tuple or dict), return a unique key from the
- aggregation of keys.
+ aggregation of keys.
"""
keys = db.content_hash_keys
if isinstance(hash, tuple):
return hash
return tuple([hash[k] for k in keys])
def _content_add_metadata(self, db, cur, content):
- """Add content to the postgresql database but not the object storage.
- """
+ """Add content to the postgresql database but not the object storage."""
# create temporary table for metadata injection
db.mktemp("content", cur)
db.copy_to(
(c.to_dict() for c in content), "tmp_content", db.content_add_keys, cur
)
# move metadata in place
try:
db.content_add_from_temp(cur)
except psycopg2.IntegrityError as e:
if e.diag.sqlstate == "23505" and e.diag.table_name == "content":
message_detail = e.diag.message_detail
if message_detail:
hash_name, hash_id = extract_collision_hash(message_detail)
collision_contents_hashes = [
c.hashes() for c in content if c.get_hash(hash_name) == hash_id
]
else:
constraint_to_hash_name = {
"content_pkey": "sha1",
"content_sha1_git_idx": "sha1_git",
"content_sha256_idx": "sha256",
}
hash_name = constraint_to_hash_name.get(e.diag.constraint_name)
hash_id = None
collision_contents_hashes = None
raise HashCollision(
hash_name, hash_id, collision_contents_hashes
) from None
else:
raise
def content_add(self, content: List[Content]) -> Dict[str, int]:
ctime = now()
contents = [attr.evolve(c, ctime=ctime) for c in content]
# Must add to the objstorage before the DB and journal. Otherwise:
# 1. in case of a crash the DB may "believe" we have the content, but
# we didn't have time to write to the objstorage before the crash
# 2. the objstorage mirroring, which reads from the journal, may attempt to
# read from the objstorage before we finished writing it
objstorage_summary = self.objstorage.content_add(contents)
with self.db() as db:
with db.transaction() as cur:
missing = list(
self.content_missing(
map(Content.to_dict, contents),
key_hash="sha1_git",
db=db,
cur=cur,
)
)
contents = [c for c in contents if c.sha1_git in missing]
self.journal_writer.content_add(contents)
self._content_add_metadata(db, cur, contents)
return {
"content:add": len(contents),
"content:add:bytes": objstorage_summary["content:add:bytes"],
}
@db_transaction()
def content_update(
self, contents: List[Dict[str, Any]], keys: List[str] = [], *, db: Db, cur=None
) -> None:
# TODO: Add a check on input keys. How to properly implement
# this? We don't know yet the new columns.
self.journal_writer.content_update(contents)
db.mktemp("content", cur)
select_keys = list(set(db.content_get_metadata_keys).union(set(keys)))
with convert_validation_exceptions():
db.copy_to(contents, "tmp_content", select_keys, cur)
db.content_update_from_temp(keys_to_update=keys, cur=cur)
@db_transaction()
def content_add_metadata(
self, content: List[Content], *, db: Db, cur=None
) -> Dict[str, int]:
missing = self.content_missing(
- (c.to_dict() for c in content), key_hash="sha1_git", db=db, cur=cur,
+ (c.to_dict() for c in content),
+ key_hash="sha1_git",
+ db=db,
+ cur=cur,
)
contents = [c for c in content if c.sha1_git in missing]
self.journal_writer.content_add_metadata(contents)
self._content_add_metadata(db, cur, contents)
return {
"content:add": len(contents),
}
def content_get_data(self, content: Sha1) -> Optional[bytes]:
# FIXME: Make this method support slicing the `data`
return self.objstorage.content_get(content)
@db_transaction()
def content_get_partition(
self,
partition_id: int,
nb_partitions: int,
page_token: Optional[str] = None,
limit: int = 1000,
*,
db: Db,
cur=None,
) -> PagedResult[Content]:
if limit is None:
raise StorageArgumentException("limit should not be None")
(start, end) = get_partition_bounds_bytes(
partition_id, nb_partitions, SHA1_SIZE
)
if page_token:
start = hash_to_bytes(page_token)
if end is None:
end = b"\xff" * SHA1_SIZE
next_page_token: Optional[str] = None
contents = []
for counter, row in enumerate(db.content_get_range(start, end, limit + 1, cur)):
row_d = dict(zip(db.content_get_metadata_keys, row))
content = Content(**row_d)
if counter >= limit:
# take the last content for the next page starting from this
next_page_token = hash_to_hex(content.sha1)
break
contents.append(content)
assert len(contents) <= limit
return PagedResult(results=contents, next_page_token=next_page_token)
@db_transaction(statement_timeout=500)
def content_get(
self, contents: List[bytes], algo: str = "sha1", *, db: Db, cur=None
) -> List[Optional[Content]]:
contents_by_hash: Dict[bytes, Optional[Content]] = {}
if algo not in DEFAULT_ALGORITHMS:
raise StorageArgumentException(
"algo should be one of {','.join(DEFAULT_ALGORITHMS)}"
)
rows = db.content_get_metadata_from_hashes(contents, algo, cur)
key = operator.attrgetter(algo)
for row in rows:
row_d = dict(zip(db.content_get_metadata_keys, row))
content = Content(**row_d)
contents_by_hash[key(content)] = content
return [contents_by_hash.get(sha1) for sha1 in contents]
@db_transaction_generator()
def content_missing(
self,
contents: List[Dict[str, Any]],
key_hash: str = "sha1",
*,
db: Db,
cur=None,
) -> Iterable[bytes]:
if key_hash not in DEFAULT_ALGORITHMS:
raise StorageArgumentException(
"key_hash should be one of {','.join(DEFAULT_ALGORITHMS)}"
)
keys = db.content_hash_keys
key_hash_idx = keys.index(key_hash)
for obj in db.content_missing_from_list(contents, cur):
yield obj[key_hash_idx]
@db_transaction_generator()
def content_missing_per_sha1(
self, contents: List[bytes], *, db: Db, cur=None
) -> Iterable[bytes]:
for obj in db.content_missing_per_sha1(contents, cur):
yield obj[0]
@db_transaction_generator()
def content_missing_per_sha1_git(
self, contents: List[bytes], *, db: Db, cur=None
) -> Iterable[Sha1Git]:
for obj in db.content_missing_per_sha1_git(contents, cur):
yield obj[0]
@db_transaction()
def content_find(
self, content: Dict[str, Any], *, db: Db, cur=None
) -> List[Content]:
if not set(content).intersection(DEFAULT_ALGORITHMS):
raise StorageArgumentException(
"content keys must contain at least one "
f"of: {', '.join(sorted(DEFAULT_ALGORITHMS))}"
)
rows = db.content_find(
sha1=content.get("sha1"),
sha1_git=content.get("sha1_git"),
sha256=content.get("sha256"),
blake2s256=content.get("blake2s256"),
cur=cur,
)
contents = []
for row in rows:
row_d = dict(zip(db.content_find_cols, row))
contents.append(Content(**row_d))
return contents
@db_transaction()
def content_get_random(self, *, db: Db, cur=None) -> Sha1Git:
return db.content_get_random(cur)
@staticmethod
def _skipped_content_normalize(d):
d = d.copy()
if d.get("status") is None:
d["status"] = "absent"
if d.get("length") is None:
d["length"] = -1
return d
def _skipped_content_add_metadata(self, db, cur, content: List[SkippedContent]):
origin_ids = db.origin_id_get_by_url([cont.origin for cont in content], cur=cur)
content = [
attr.evolve(c, origin=origin_id)
for (c, origin_id) in zip(content, origin_ids)
]
db.mktemp("skipped_content", cur)
db.copy_to(
[c.to_dict() for c in content],
"tmp_skipped_content",
db.skipped_content_keys,
cur,
)
# move metadata in place
db.skipped_content_add_from_temp(cur)
@db_transaction()
def skipped_content_add(
self, content: List[SkippedContent], *, db: Db, cur=None
) -> Dict[str, int]:
ctime = now()
content = [attr.evolve(c, ctime=ctime) for c in content]
missing_contents = self.skipped_content_missing(
- (c.to_dict() for c in content), db=db, cur=cur,
+ (c.to_dict() for c in content),
+ db=db,
+ cur=cur,
)
content = [
c
for c in content
if any(
all(
c.get_hash(algo) == missing_content.get(algo)
for algo in DEFAULT_ALGORITHMS
)
for missing_content in missing_contents
)
]
self.journal_writer.skipped_content_add(content)
self._skipped_content_add_metadata(db, cur, content)
return {
"skipped_content:add": len(content),
}
@db_transaction_generator()
def skipped_content_missing(
self, contents: List[Dict[str, Any]], *, db: Db, cur=None
) -> Iterable[Dict[str, Any]]:
contents = list(contents)
for content in db.skipped_content_missing(contents, cur):
yield dict(zip(db.content_hash_keys, content))
@db_transaction()
def directory_add(
self, directories: List[Directory], *, db: Db, cur=None
) -> Dict[str, int]:
summary = {"directory:add": 0}
dirs = set()
dir_entries: Dict[str, defaultdict] = {
"file": defaultdict(list),
"dir": defaultdict(list),
"rev": defaultdict(list),
}
for cur_dir in directories:
dir_id = cur_dir.id
dirs.add(dir_id)
for src_entry in cur_dir.entries:
entry = src_entry.to_dict()
entry["dir_id"] = dir_id
dir_entries[entry["type"]][dir_id].append(entry)
dirs_missing = set(self.directory_missing(dirs, db=db, cur=cur))
if not dirs_missing:
return summary
self.journal_writer.directory_add(
dir_ for dir_ in directories if dir_.id in dirs_missing
)
# Copy directory metadata
dirs_missing_dict = (
{"id": dir_.id, "raw_manifest": dir_.raw_manifest}
for dir_ in directories
if dir_.id in dirs_missing
)
db.mktemp("directory", cur)
db.copy_to(dirs_missing_dict, "tmp_directory", ["id", "raw_manifest"], cur)
# Copy entries
for entry_type, entry_list in dir_entries.items():
entries = itertools.chain.from_iterable(
entries_for_dir
for dir_id, entries_for_dir in entry_list.items()
if dir_id in dirs_missing
)
db.mktemp_dir_entry(entry_type)
db.copy_to(
entries,
"tmp_directory_entry_%s" % entry_type,
["target", "name", "perms", "dir_id"],
cur,
)
# Do the final copy
db.directory_add_from_temp(cur)
summary["directory:add"] = len(dirs_missing)
return summary
@db_transaction_generator()
def directory_missing(
self, directories: List[Sha1Git], *, db: Db, cur=None
) -> Iterable[Sha1Git]:
for obj in db.directory_missing_from_list(directories, cur):
yield obj[0]
@db_transaction_generator(statement_timeout=20000)
def directory_ls(
self, directory: Sha1Git, recursive: bool = False, *, db: Db, cur=None
) -> Iterable[Dict[str, Any]]:
if recursive:
res_gen = db.directory_walk(directory, cur=cur)
else:
res_gen = db.directory_walk_one(directory, cur=cur)
for line in res_gen:
yield dict(zip(db.directory_ls_cols, line))
@db_transaction(statement_timeout=4000)
def directory_entry_get_by_path(
self, directory: Sha1Git, paths: List[bytes], *, db: Db, cur=None
) -> Optional[Dict[str, Any]]:
res = db.directory_entry_get_by_path(directory, paths, cur)
return dict(zip(db.directory_ls_cols, res)) if res else None
@db_transaction()
def directory_get_random(self, *, db: Db, cur=None) -> Sha1Git:
return db.directory_get_random(cur)
@db_transaction()
def directory_get_entries(
self,
directory_id: Sha1Git,
page_token: Optional[bytes] = None,
limit: int = 1000,
*,
db: Db,
cur=None,
) -> Optional[PagedResult[DirectoryEntry]]:
if list(self.directory_missing([directory_id], db=db, cur=cur)):
return None
if page_token is not None:
raise StorageArgumentException("Unsupported page token")
# TODO: actually paginate
rows = db.directory_get_entries(directory_id, cur=cur)
return PagedResult(
results=[
DirectoryEntry(**dict(zip(db.directory_get_entries_cols, row)))
for row in rows
],
next_page_token=None,
)
@db_transaction()
def directory_get_raw_manifest(
self, directory_ids: List[Sha1Git], *, db: Db, cur=None
) -> Dict[Sha1Git, Optional[bytes]]:
return dict(db.directory_get_raw_manifest(directory_ids, cur=cur))
@db_transaction()
def revision_add(
self, revisions: List[Revision], *, db: Db, cur=None
) -> Dict[str, int]:
summary = {"revision:add": 0}
revisions_missing = set(
self.revision_missing(
set(revision.id for revision in revisions), db=db, cur=cur
)
)
if not revisions_missing:
return summary
db.mktemp_revision(cur)
revisions_filtered = [
revision for revision in revisions if revision.id in revisions_missing
]
self.journal_writer.revision_add(revisions_filtered)
db_revisions_filtered = list(map(converters.revision_to_db, revisions_filtered))
parents_filtered: List[Dict[str, Any]] = []
with convert_validation_exceptions():
db.copy_to(
db_revisions_filtered,
"tmp_revision",
db.revision_add_cols,
cur,
lambda rev: parents_filtered.extend(rev["parents"]),
)
db.revision_add_from_temp(cur)
db.copy_to(
parents_filtered,
"revision_history",
["id", "parent_id", "parent_rank"],
cur,
)
return {"revision:add": len(revisions_missing)}
@db_transaction_generator()
def revision_missing(
self, revisions: List[Sha1Git], *, db: Db, cur=None
) -> Iterable[Sha1Git]:
if not revisions:
return None
for obj in db.revision_missing_from_list(revisions, cur):
yield obj[0]
@db_transaction(statement_timeout=2000)
def revision_get(
self,
revision_ids: List[Sha1Git],
ignore_displayname: bool = False,
*,
db: Db,
cur=None,
) -> List[Optional[Revision]]:
revisions = []
for line in db.revision_get_from_list(revision_ids, ignore_displayname, cur):
revision = converters.db_to_revision(dict(zip(db.revision_get_cols, line)))
revisions.append(revision)
return revisions
@db_transaction_generator(statement_timeout=2000)
def revision_log(
self,
revisions: List[Sha1Git],
ignore_displayname: bool = False,
limit: Optional[int] = None,
*,
db: Db,
cur=None,
) -> Iterable[Optional[Dict[str, Any]]]:
for line in db.revision_log(
revisions, ignore_displayname=ignore_displayname, limit=limit, cur=cur
):
data = converters.db_to_revision(dict(zip(db.revision_get_cols, line)))
if not data:
yield None
continue
yield data.to_dict()
@db_transaction_generator(statement_timeout=2000)
def revision_shortlog(
self, revisions: List[Sha1Git], limit: Optional[int] = None, *, db: Db, cur=None
) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]:
yield from db.revision_shortlog(revisions, limit, cur)
@db_transaction()
def revision_get_random(self, *, db: Db, cur=None) -> Sha1Git:
return db.revision_get_random(cur)
@db_transaction()
def extid_get_from_extid(
self,
id_type: str,
ids: List[bytes],
version: Optional[int] = None,
*,
db: Db,
cur=None,
) -> List[ExtID]:
extids = []
for row in db.extid_get_from_extid_list(id_type, ids, version=version, cur=cur):
if row[0] is not None:
extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row))))
return extids
@db_transaction()
def extid_get_from_target(
self,
target_type: ObjectType,
ids: List[Sha1Git],
extid_type: Optional[str] = None,
extid_version: Optional[int] = None,
*,
db: Db,
cur=None,
) -> List[ExtID]:
extids = []
if (extid_version is not None and extid_type is None) or (
extid_version is None and extid_type is not None
):
raise ValueError("You must provide both extid_type and extid_version")
for row in db.extid_get_from_swhid_list(
target_type.value,
ids,
extid_version=extid_version,
extid_type=extid_type,
cur=cur,
):
if row[0] is not None:
extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row))))
return extids
@db_transaction()
def extid_add(self, ids: List[ExtID], *, db: Db, cur=None) -> Dict[str, int]:
extid = [
{
"extid": extid.extid,
"extid_type": extid.extid_type,
"extid_version": getattr(extid, "extid_version", 0),
"target": extid.target.object_id,
"target_type": extid.target.object_type.name.lower(), # arghh
}
for extid in ids
]
db.mktemp("extid", cur)
self.journal_writer.extid_add(ids)
db.copy_to(extid, "tmp_extid", db.extid_cols, cur)
# move metadata in place
db.extid_add_from_temp(cur)
return {"extid:add": len(extid)}
@db_transaction()
def release_add(
self, releases: List[Release], *, db: Db, cur=None
) -> Dict[str, int]:
summary = {"release:add": 0}
release_ids = set(release.id for release in releases)
releases_missing = set(self.release_missing(release_ids, db=db, cur=cur))
if not releases_missing:
return summary
db.mktemp_release(cur)
releases_filtered = [
release for release in releases if release.id in releases_missing
]
self.journal_writer.release_add(releases_filtered)
db_releases_filtered = list(map(converters.release_to_db, releases_filtered))
with convert_validation_exceptions():
db.copy_to(db_releases_filtered, "tmp_release", db.release_add_cols, cur)
db.release_add_from_temp(cur)
return {"release:add": len(releases_missing)}
@db_transaction_generator()
def release_missing(
self, releases: List[Sha1Git], *, db: Db, cur=None
) -> Iterable[Sha1Git]:
if not releases:
return
for obj in db.release_missing_from_list(releases, cur):
yield obj[0]
@db_transaction(statement_timeout=1000)
def release_get(
self,
releases: List[Sha1Git],
ignore_displayname: bool = False,
*,
db: Db,
cur=None,
) -> List[Optional[Release]]:
rels = []
for release in db.release_get_from_list(releases, ignore_displayname, cur):
data = converters.db_to_release(dict(zip(db.release_get_cols, release)))
rels.append(data if data else None)
return rels
@db_transaction()
def release_get_random(self, *, db: Db, cur=None) -> Sha1Git:
return db.release_get_random(cur)
@db_transaction()
def snapshot_add(
self, snapshots: List[Snapshot], *, db: Db, cur=None
) -> Dict[str, int]:
created_temp_table = False
count = 0
for snapshot in snapshots:
if not db.snapshot_exists(snapshot.id, cur):
if not created_temp_table:
db.mktemp_snapshot_branch(cur)
created_temp_table = True
with convert_validation_exceptions():
db.copy_to(
(
{
"name": name,
"target": info.target if info else None,
"target_type": (
info.target_type.value if info else None
),
}
for name, info in snapshot.branches.items()
),
"tmp_snapshot_branch",
["name", "target", "target_type"],
cur,
)
self.journal_writer.snapshot_add([snapshot])
db.snapshot_add(snapshot.id, cur)
count += 1
return {"snapshot:add": count}
@db_transaction_generator()
def snapshot_missing(
self, snapshots: List[Sha1Git], *, db: Db, cur=None
) -> Iterable[Sha1Git]:
for obj in db.snapshot_missing_from_list(snapshots, cur):
yield obj[0]
@db_transaction(statement_timeout=2000)
def snapshot_get(
self, snapshot_id: Sha1Git, *, db: Db, cur=None
) -> Optional[Dict[str, Any]]:
d = self.snapshot_get_branches(snapshot_id)
if d is None:
return d
return {
"id": d["id"],
"branches": {
name: branch.to_dict() if branch else None
for (name, branch) in d["branches"].items()
},
"next_branch": d["next_branch"],
}
@db_transaction(statement_timeout=2000)
def snapshot_count_branches(
self,
snapshot_id: Sha1Git,
branch_name_exclude_prefix: Optional[bytes] = None,
*,
db: Db,
cur=None,
) -> Optional[Dict[Optional[str], int]]:
return dict(
[
bc
for bc in db.snapshot_count_branches(
- snapshot_id, branch_name_exclude_prefix, cur,
+ snapshot_id,
+ branch_name_exclude_prefix,
+ cur,
)
]
)
@db_transaction(statement_timeout=2000)
def snapshot_get_branches(
self,
snapshot_id: Sha1Git,
branches_from: bytes = b"",
branches_count: int = 1000,
target_types: Optional[List[str]] = None,
branch_name_include_substring: Optional[bytes] = None,
branch_name_exclude_prefix: Optional[bytes] = None,
*,
db: Db,
cur=None,
) -> Optional[PartialBranches]:
if snapshot_id == EMPTY_SNAPSHOT_ID:
- return PartialBranches(id=snapshot_id, branches={}, next_branch=None,)
+ return PartialBranches(
+ id=snapshot_id,
+ branches={},
+ next_branch=None,
+ )
if list(self.snapshot_missing([snapshot_id])):
return None
branches = {}
next_branch = None
fetched_branches = list(
db.snapshot_get_by_id(
snapshot_id,
branches_from=branches_from,
# the underlying SQL query can be quite expensive to execute for small
# branches_count value, so we ensure a minimum branches limit of 10 for
# optimal performances
branches_count=max(branches_count + 1, 10),
target_types=target_types,
branch_name_include_substring=branch_name_include_substring,
branch_name_exclude_prefix=branch_name_exclude_prefix,
cur=cur,
)
)
for row in fetched_branches[:branches_count]:
branch_d = dict(zip(db.snapshot_get_cols, row))
del branch_d["snapshot_id"]
name = branch_d.pop("name")
if branch_d["target"] is None and branch_d["target_type"] is None:
branch = None
else:
assert branch_d["target_type"] is not None
branch = SnapshotBranch(
target=branch_d["target"],
target_type=TargetType(branch_d["target_type"]),
)
branches[name] = branch
if len(fetched_branches) > branches_count:
next_branch = dict(
zip(db.snapshot_get_cols, fetched_branches[branches_count])
)["name"]
return PartialBranches(
- id=snapshot_id, branches=branches, next_branch=next_branch,
+ id=snapshot_id,
+ branches=branches,
+ next_branch=next_branch,
)
@db_transaction()
def snapshot_get_random(self, *, db: Db, cur=None) -> Sha1Git:
return db.snapshot_get_random(cur)
@db_transaction()
def origin_visit_add(
self, visits: List[OriginVisit], *, db: Db, cur=None
) -> Iterable[OriginVisit]:
for visit in visits:
origin = self.origin_get([visit.origin], db=db, cur=cur)[0]
if not origin: # Cannot add a visit without an origin
raise StorageArgumentException("Unknown origin %s", visit.origin)
all_visits = []
for visit in visits:
if not visit.visit:
with convert_validation_exceptions():
visit_id = db.origin_visit_add(
visit.origin, visit.date, visit.type, cur=cur
)
visit = attr.evolve(visit, visit=visit_id)
else:
db.origin_visit_add_with_id(visit, cur=cur)
assert visit.visit is not None
all_visits.append(visit)
# Forced to write after for the case when the visit has no id
self.journal_writer.origin_visit_add([visit])
visit_status = OriginVisitStatus(
origin=visit.origin,
visit=visit.visit,
date=visit.date,
type=visit.type,
status="created",
snapshot=None,
)
self._origin_visit_status_add(visit_status, db=db, cur=cur)
return all_visits
def _origin_visit_status_add(
self, visit_status: OriginVisitStatus, db, cur
) -> None:
"""Add an origin visit status"""
self.journal_writer.origin_visit_status_add([visit_status])
db.origin_visit_status_add(visit_status, cur=cur)
@db_transaction()
def origin_visit_status_add(
- self, visit_statuses: List[OriginVisitStatus], *, db: Db, cur=None,
+ self,
+ visit_statuses: List[OriginVisitStatus],
+ *,
+ db: Db,
+ cur=None,
) -> Dict[str, int]:
visit_statuses_ = []
# First round to check existence (fail early if any is ko)
for visit_status in visit_statuses:
origin_url = self.origin_get([visit_status.origin], db=db, cur=cur)[0]
if not origin_url:
raise StorageArgumentException(f"Unknown origin {visit_status.origin}")
if visit_status.type is None:
origin_visit = self.origin_visit_get_by(
visit_status.origin, visit_status.visit, db=db, cur=cur
)
if origin_visit is None:
raise StorageArgumentException(
f"Unknown origin visit {visit_status.visit} "
f"of origin {visit_status.origin}"
)
origin_visit_status = attr.evolve(visit_status, type=origin_visit.type)
else:
origin_visit_status = visit_status
visit_statuses_.append(origin_visit_status)
for visit_status in visit_statuses_:
self._origin_visit_status_add(visit_status, db, cur)
return {"origin_visit_status:add": len(visit_statuses_)}
@db_transaction()
def origin_visit_status_get_latest(
self,
origin_url: str,
visit: int,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
*,
db: Db,
cur=None,
) -> Optional[OriginVisitStatus]:
if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES):
raise StorageArgumentException(
f"Unknown allowed statuses {','.join(allowed_statuses)}, only "
f"{','.join(VISIT_STATUSES)} authorized"
)
row_d = db.origin_visit_status_get_latest(
origin_url, visit, allowed_statuses, require_snapshot, cur=cur
)
if not row_d:
return None
return OriginVisitStatus(**row_d)
@db_transaction(statement_timeout=500)
def origin_visit_get(
self,
origin: str,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
*,
db: Db,
cur=None,
) -> PagedResult[OriginVisit]:
page_token = page_token or "0"
if not isinstance(order, ListOrder):
raise StorageArgumentException("order must be a ListOrder value")
if not isinstance(page_token, str):
raise StorageArgumentException("page_token must be a string.")
next_page_token = None
visit_from = int(page_token)
visits: List[OriginVisit] = []
extra_limit = limit + 1
for row in db.origin_visit_get_range(
origin, visit_from=visit_from, order=order, limit=extra_limit, cur=cur
):
row_d = dict(zip(db.origin_visit_cols, row))
visits.append(
OriginVisit(
origin=row_d["origin"],
visit=row_d["visit"],
date=row_d["date"],
type=row_d["type"],
)
)
assert len(visits) <= extra_limit
if len(visits) == extra_limit:
visits = visits[:limit]
next_page_token = str(visits[-1].visit)
return PagedResult(results=visits, next_page_token=next_page_token)
@db_transaction(statement_timeout=500)
def origin_visit_get_with_statuses(
self,
origin: str,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
*,
db: Db,
cur=None,
) -> PagedResult[OriginVisitWithStatuses]:
page_token = page_token or "0"
if not isinstance(order, ListOrder):
raise StorageArgumentException("order must be a ListOrder value")
if not isinstance(page_token, str):
raise StorageArgumentException("page_token must be a string.")
# First get visits (plus one so we can use it as the next page token if any)
visits_page = self.origin_visit_get(
origin=origin,
page_token=page_token,
order=order,
limit=limit,
db=db,
cur=cur,
)
visits = visits_page.results
next_page_token = visits_page.next_page_token
if visits:
visit_from = min(visits[0].visit, visits[-1].visit)
visit_to = max(visits[0].visit, visits[-1].visit)
# Then, fetch all statuses associated to these visits
visit_statuses: Dict[int, List[OriginVisitStatus]] = defaultdict(list)
for row in db.origin_visit_status_get_all_in_range(
origin,
allowed_statuses,
require_snapshot,
visit_from=visit_from,
visit_to=visit_to,
cur=cur,
):
row_d = dict(zip(db.origin_visit_status_cols, row))
visit_statuses[row_d["visit"]].append(OriginVisitStatus(**row_d))
results = [
OriginVisitWithStatuses(
visit=visit, statuses=visit_statuses[visit.visit]
)
for visit in visits
]
return PagedResult(results=results, next_page_token=next_page_token)
@db_transaction(statement_timeout=1000)
def origin_visit_find_by_date(
self, origin: str, visit_date: datetime.datetime, *, db: Db, cur=None
) -> Optional[OriginVisit]:
row_d = db.origin_visit_find_by_date(origin, visit_date, cur=cur)
if not row_d:
return None
return OriginVisit(
origin=row_d["origin"],
visit=row_d["visit"],
date=row_d["date"],
type=row_d["type"],
)
@db_transaction(statement_timeout=500)
def origin_visit_get_by(
self, origin: str, visit: int, *, db: Db, cur=None
) -> Optional[OriginVisit]:
row = db.origin_visit_get(origin, visit, cur)
if row:
row_d = dict(zip(db.origin_visit_get_cols, row))
return OriginVisit(
origin=row_d["origin"],
visit=row_d["visit"],
date=row_d["date"],
type=row_d["type"],
)
return None
@db_transaction(statement_timeout=4000)
def origin_visit_get_latest(
self,
origin: str,
type: Optional[str] = None,
allowed_statuses: Optional[List[str]] = None,
require_snapshot: bool = False,
*,
db: Db,
cur=None,
) -> Optional[OriginVisit]:
if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES):
raise StorageArgumentException(
f"Unknown allowed statuses {','.join(allowed_statuses)}, only "
f"{','.join(VISIT_STATUSES)} authorized"
)
row = db.origin_visit_get_latest(
origin,
type=type,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
cur=cur,
)
if row:
row_d = dict(zip(db.origin_visit_get_cols, row))
visit = OriginVisit(
origin=row_d["origin"],
visit=row_d["visit"],
date=row_d["date"],
type=row_d["type"],
)
return visit
return None
@db_transaction(statement_timeout=500)
def origin_visit_status_get(
self,
origin: str,
visit: int,
page_token: Optional[str] = None,
order: ListOrder = ListOrder.ASC,
limit: int = 10,
*,
db: Db,
cur=None,
) -> PagedResult[OriginVisitStatus]:
next_page_token = None
date_from = None
if page_token is not None:
date_from = datetime.datetime.fromisoformat(page_token)
visit_statuses: List[OriginVisitStatus] = []
# Take one more visit status so we can reuse it as the next page token if any
for row in db.origin_visit_status_get_range(
- origin, visit, date_from=date_from, order=order, limit=limit + 1, cur=cur,
+ origin,
+ visit,
+ date_from=date_from,
+ order=order,
+ limit=limit + 1,
+ cur=cur,
):
row_d = dict(zip(db.origin_visit_status_cols, row))
visit_statuses.append(OriginVisitStatus(**row_d))
if len(visit_statuses) > limit:
# last visit status date is the next page token
next_page_token = str(visit_statuses[-1].date)
# excluding that visit status from the result to respect the limit size
visit_statuses = visit_statuses[:limit]
return PagedResult(results=visit_statuses, next_page_token=next_page_token)
@db_transaction()
def origin_visit_status_get_random(
self, type: str, *, db: Db, cur=None
) -> Optional[OriginVisitStatus]:
row = db.origin_visit_get_random(type, cur)
if row is not None:
row_d = dict(zip(db.origin_visit_status_cols, row))
return OriginVisitStatus(**row_d)
return None
@db_transaction(statement_timeout=2000)
def object_find_by_sha1_git(
self, ids: List[Sha1Git], *, db: Db, cur=None
) -> Dict[Sha1Git, List[Dict]]:
ret: Dict[Sha1Git, List[Dict]] = {id: [] for id in ids}
for retval in db.object_find_by_sha1_git(ids, cur=cur):
if retval[1]:
ret[retval[0]].append(
dict(zip(db.object_find_by_sha1_git_cols, retval))
)
return ret
@db_transaction(statement_timeout=1000)
def origin_get(
self, origins: List[str], *, db: Db, cur=None
) -> Iterable[Optional[Origin]]:
rows = db.origin_get_by_url(origins, cur)
result: List[Optional[Origin]] = []
for row in rows:
origin_d = dict(zip(db.origin_cols, row))
url = origin_d["url"]
result.append(None if url is None else Origin(url=url))
return result
@db_transaction(statement_timeout=1000)
def origin_get_by_sha1(
self, sha1s: List[bytes], *, db: Db, cur=None
) -> List[Optional[Dict[str, Any]]]:
return [
dict(zip(db.origin_cols, row)) if row[0] else None
for row in db.origin_get_by_sha1(sha1s, cur)
]
@db_transaction_generator()
def origin_get_range(self, origin_from=1, origin_count=100, *, db: Db, cur=None):
for origin in db.origin_get_range(origin_from, origin_count, cur):
yield dict(zip(db.origin_get_range_cols, origin))
@db_transaction()
def origin_list(
self, page_token: Optional[str] = None, limit: int = 100, *, db: Db, cur=None
) -> PagedResult[Origin]:
page_token = page_token or "0"
if not isinstance(page_token, str):
raise StorageArgumentException("page_token must be a string.")
origin_from = int(page_token)
next_page_token = None
origins: List[Origin] = []
# Take one more origin so we can reuse it as the next page token if any
for row_d in self.origin_get_range(origin_from, limit + 1, db=db, cur=cur):
origins.append(Origin(url=row_d["url"]))
# keep the last_id for the pagination if needed
last_id = row_d["id"]
if len(origins) > limit: # data left for subsequent call
# last origin id is the next page token
next_page_token = str(last_id)
# excluding that origin from the result to respect the limit size
origins = origins[:limit]
assert len(origins) <= limit
return PagedResult(results=origins, next_page_token=next_page_token)
@db_transaction()
def origin_search(
self,
url_pattern: str,
page_token: Optional[str] = None,
limit: int = 50,
regexp: bool = False,
with_visit: bool = False,
visit_types: Optional[List[str]] = None,
*,
db: Db,
cur=None,
) -> PagedResult[Origin]:
next_page_token = None
offset = int(page_token) if page_token else 0
origins = []
# Take one more origin so we can reuse it as the next page token if any
for origin in db.origin_search(
url_pattern, offset, limit + 1, regexp, with_visit, visit_types, cur
):
row_d = dict(zip(db.origin_cols, origin))
origins.append(Origin(url=row_d["url"]))
if len(origins) > limit:
# next offset
next_page_token = str(offset + limit)
# excluding that origin from the result to respect the limit size
origins = origins[:limit]
assert len(origins) <= limit
return PagedResult(results=origins, next_page_token=next_page_token)
@db_transaction()
def origin_count(
self,
url_pattern: str,
regexp: bool = False,
with_visit: bool = False,
*,
db: Db,
cur=None,
) -> int:
return db.origin_count(url_pattern, regexp, with_visit, cur)
@db_transaction()
def origin_snapshot_get_all(
self, origin_url: str, *, db: Db, cur=None
) -> List[Sha1Git]:
return list(db.origin_snapshot_get_all(origin_url, cur))
@db_transaction()
def origin_add(self, origins: List[Origin], *, db: Db, cur=None) -> Dict[str, int]:
urls = [o.url for o in origins]
known_origins = set(url for (url,) in db.origin_get_by_url(urls, cur))
# keep only one occurrence of each given origin while keeping the list
# sorted as originally given
to_add = sorted(set(urls) - known_origins, key=urls.index)
self.journal_writer.origin_add([Origin(url=url) for url in to_add])
added = 0
for url in to_add:
if db.origin_add(url, cur):
added += 1
return {"origin:add": added}
@db_transaction(statement_timeout=500)
def stat_counters(self, *, db: Db, cur=None):
return {k: v for (k, v) in db.stat_counters()}
@db_transaction()
def refresh_stat_counters(self, *, db: Db, cur=None):
keys = [
"content",
"directory",
"directory_entry_dir",
"directory_entry_file",
"directory_entry_rev",
"origin",
"origin_visit",
"person",
"release",
"revision",
"revision_history",
"skipped_content",
"snapshot",
]
for key in keys:
cur.execute("select * from swh_update_counter(%s)", (key,))
@db_transaction()
def raw_extrinsic_metadata_add(
- self, metadata: List[RawExtrinsicMetadata], db, cur,
+ self,
+ metadata: List[RawExtrinsicMetadata],
+ db,
+ cur,
) -> Dict[str, int]:
metadata = list(metadata)
self.journal_writer.raw_extrinsic_metadata_add(metadata)
counter = Counter[ExtendedObjectType]()
for metadata_entry in metadata:
authority_id = self._get_authority_id(metadata_entry.authority, db, cur)
fetcher_id = self._get_fetcher_id(metadata_entry.fetcher, db, cur)
db.raw_extrinsic_metadata_add(
id=metadata_entry.id,
type=metadata_entry.target.object_type.name.lower(),
target=str(metadata_entry.target),
discovery_date=metadata_entry.discovery_date,
authority_id=authority_id,
fetcher_id=fetcher_id,
format=metadata_entry.format,
metadata=metadata_entry.metadata,
origin=metadata_entry.origin,
visit=metadata_entry.visit,
snapshot=map_optional(str, metadata_entry.snapshot),
release=map_optional(str, metadata_entry.release),
revision=map_optional(str, metadata_entry.revision),
path=metadata_entry.path,
directory=map_optional(str, metadata_entry.directory),
cur=cur,
)
counter[metadata_entry.target.object_type] += 1
return {
f"{type.value}_metadata:add": count for (type, count) in counter.items()
}
@db_transaction()
def raw_extrinsic_metadata_get(
self,
target: ExtendedSWHID,
authority: MetadataAuthority,
after: Optional[datetime.datetime] = None,
page_token: Optional[bytes] = None,
limit: int = 1000,
*,
db: Db,
cur=None,
) -> PagedResult[RawExtrinsicMetadata]:
if page_token:
(after_time, after_fetcher) = msgpack_loads(base64.b64decode(page_token))
if after and after_time < after:
raise StorageArgumentException(
"page_token is inconsistent with the value of 'after'."
)
else:
after_time = after
after_fetcher = None
authority_id = self._get_authority_id(authority, db, cur)
if not authority_id:
- return PagedResult(next_page_token=None, results=[],)
+ return PagedResult(
+ next_page_token=None,
+ results=[],
+ )
rows = db.raw_extrinsic_metadata_get(
- str(target), authority_id, after_time, after_fetcher, limit + 1, cur,
+ str(target),
+ authority_id,
+ after_time,
+ after_fetcher,
+ limit + 1,
+ cur,
)
rows = [dict(zip(db.raw_extrinsic_metadata_get_cols, row)) for row in rows]
results = []
for row in rows:
assert str(target) == row["raw_extrinsic_metadata.target"]
results.append(converters.db_to_raw_extrinsic_metadata(row))
if len(results) > limit:
results.pop()
assert len(results) == limit
last_returned_row = rows[-2] # rows[-1] corresponds to the popped result
next_page_token: Optional[str] = base64.b64encode(
msgpack_dumps(
(
last_returned_row["discovery_date"],
last_returned_row["metadata_fetcher.id"],
)
)
).decode()
else:
next_page_token = None
- return PagedResult(next_page_token=next_page_token, results=results,)
+ return PagedResult(
+ next_page_token=next_page_token,
+ results=results,
+ )
@db_transaction()
def raw_extrinsic_metadata_get_by_ids(
- self, ids: List[Sha1Git], *, db: Db, cur=None,
+ self,
+ ids: List[Sha1Git],
+ *,
+ db: Db,
+ cur=None,
) -> List[RawExtrinsicMetadata]:
return [
converters.db_to_raw_extrinsic_metadata(
dict(zip(db.raw_extrinsic_metadata_get_cols, row))
)
for row in db.raw_extrinsic_metadata_get_by_ids(ids)
]
@db_transaction()
def raw_extrinsic_metadata_get_authorities(
- self, target: ExtendedSWHID, *, db: Db, cur=None,
+ self,
+ target: ExtendedSWHID,
+ *,
+ db: Db,
+ cur=None,
) -> List[MetadataAuthority]:
return [
MetadataAuthority(
type=MetadataAuthorityType(authority_type), url=authority_url
)
for (
authority_type,
authority_url,
) in db.raw_extrinsic_metadata_get_authorities(str(target), cur)
]
@db_transaction()
def metadata_fetcher_add(
self, fetchers: List[MetadataFetcher], *, db: Db, cur=None
) -> Dict[str, int]:
fetchers = list(fetchers)
self.journal_writer.metadata_fetcher_add(fetchers)
count = 0
for fetcher in fetchers:
db.metadata_fetcher_add(fetcher.name, fetcher.version, cur=cur)
count += 1
return {"metadata_fetcher:add": count}
@db_transaction(statement_timeout=500)
def metadata_fetcher_get(
self, name: str, version: str, *, db: Db, cur=None
) -> Optional[MetadataFetcher]:
row = db.metadata_fetcher_get(name, version, cur=cur)
if not row:
return None
return MetadataFetcher.from_dict(dict(zip(db.metadata_fetcher_cols, row)))
@db_transaction()
def metadata_authority_add(
self, authorities: List[MetadataAuthority], *, db: Db, cur=None
) -> Dict[str, int]:
authorities = list(authorities)
self.journal_writer.metadata_authority_add(authorities)
count = 0
for authority in authorities:
db.metadata_authority_add(authority.type.value, authority.url, cur=cur)
count += 1
return {"metadata_authority:add": count}
@db_transaction()
def metadata_authority_get(
self, type: MetadataAuthorityType, url: str, *, db: Db, cur=None
) -> Optional[MetadataAuthority]:
row = db.metadata_authority_get(type.value, url, cur=cur)
if not row:
return None
return MetadataAuthority.from_dict(dict(zip(db.metadata_authority_cols, row)))
def clear_buffers(self, object_types: Sequence[str] = ()) -> None:
- """Do nothing
-
- """
+ """Do nothing"""
return None
def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]:
return {}
def _get_authority_id(self, authority: MetadataAuthority, db, cur):
authority_id = db.metadata_authority_get_id(
authority.type.value, authority.url, cur
)
if not authority_id:
raise StorageArgumentException(f"Unknown authority {authority}")
return authority_id
def _get_fetcher_id(self, fetcher: MetadataFetcher, db, cur):
fetcher_id = db.metadata_fetcher_get_id(fetcher.name, fetcher.version, cur)
if not fetcher_id:
raise StorageArgumentException(f"Unknown fetcher {fetcher}")
return fetcher_id
diff --git a/swh/storage/proxies/buffer.py b/swh/storage/proxies/buffer.py
index 61b0037d..fc86c713 100644
--- a/swh/storage/proxies/buffer.py
+++ b/swh/storage/proxies/buffer.py
@@ -1,322 +1,326 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from functools import partial
import logging
from typing import Dict, Iterable, Mapping, Sequence, Tuple, cast
from typing_extensions import Literal
from swh.core.utils import grouper
from swh.model.model import (
BaseModel,
Content,
Directory,
Release,
Revision,
SkippedContent,
)
from swh.storage import get_storage
from swh.storage.interface import StorageInterface
logger = logging.getLogger(__name__)
LObjectType = Literal[
"content",
"skipped_content",
"directory",
"revision",
"release",
"snapshot",
"extid",
]
OBJECT_TYPES: Tuple[LObjectType, ...] = (
"content",
"skipped_content",
"directory",
"revision",
"release",
"snapshot",
"extid",
)
DEFAULT_BUFFER_THRESHOLDS: Dict[str, int] = {
"content": 10000,
"content_bytes": 100 * 1024 * 1024,
"skipped_content": 10000,
"directory": 25000,
"directory_entries": 200000,
"revision": 100000,
"revision_parents": 200000,
"revision_bytes": 100 * 1024 * 1024,
"release": 100000,
"release_bytes": 100 * 1024 * 1024,
"snapshot": 25000,
"extid": 10000,
}
def estimate_revision_size(revision: Revision) -> int:
"""Estimate the size of a revision, by summing the size of variable length fields"""
s = 20 * len(revision.parents)
if revision.message:
s += len(revision.message)
if revision.author is not None:
s += len(revision.author.fullname)
if revision.committer is not None:
s += len(revision.committer.fullname)
s += sum(len(h) + len(v) for h, v in revision.extra_headers)
return s
def estimate_release_size(release: Release) -> int:
"""Estimate the size of a release, by summing the size of variable length fields"""
s = 0
if release.message:
s += len(release.message)
if release.author:
s += len(release.author.fullname)
return s
class BufferingProxyStorage:
"""Storage implementation in charge of accumulating objects prior to
discussing with the "main" storage.
Deduplicates values based on a tuple of keys depending on the object type.
Sample configuration use case for buffering storage:
.. code-block:: yaml
storage:
cls: buffer
args:
storage:
cls: remote
args: http://storage.internal.staging.swh.network:5002/
min_batch_size:
content: 10000
content_bytes: 100000000
skipped_content: 10000
directory: 5000
directory_entries: 100000
revision: 1000
revision_parents: 2000
revision_bytes: 100000000
release: 10000
release_bytes: 100000000
snapshot: 5000
"""
def __init__(self, storage: Mapping, min_batch_size: Mapping = {}):
self.storage: StorageInterface = get_storage(**storage)
self._buffer_thresholds = {**DEFAULT_BUFFER_THRESHOLDS, **min_batch_size}
self._objects: Dict[LObjectType, Dict[Tuple[str, ...], BaseModel]] = {
k: {} for k in OBJECT_TYPES
}
self._contents_size: int = 0
self._directory_entries: int = 0
self._revision_parents: int = 0
self._revision_size: int = 0
self._release_size: int = 0
def __getattr__(self, key: str):
if key.endswith("_add"):
object_type = key.rsplit("_", 1)[0]
if object_type in OBJECT_TYPES:
- return partial(self.object_add, object_type=object_type, keys=["id"],)
+ return partial(
+ self.object_add,
+ object_type=object_type,
+ keys=["id"],
+ )
if key == "storage":
raise AttributeError(key)
return getattr(self.storage, key)
def content_add(self, contents: Sequence[Content]) -> Dict[str, int]:
"""Push contents to write to the storage in the buffer.
Following policies apply:
- if the buffer's threshold is hit, flush content to the storage.
- otherwise, if the total size of buffered contents's threshold is hit,
flush content to the storage.
"""
stats = self.object_add(
contents,
object_type="content",
keys=["sha1", "sha1_git", "sha256", "blake2s256"],
)
if not stats:
# We did not flush based on number of objects; check total size
self._contents_size += sum(c.length for c in contents)
if self._contents_size >= self._buffer_thresholds["content_bytes"]:
return self.flush(["content"])
return stats
def skipped_content_add(self, contents: Sequence[SkippedContent]) -> Dict[str, int]:
return self.object_add(
contents,
object_type="skipped_content",
keys=["sha1", "sha1_git", "sha256", "blake2s256"],
)
def directory_add(self, directories: Sequence[Directory]) -> Dict[str, int]:
stats = self.object_add(directories, object_type="directory", keys=["id"])
if not stats:
# We did not flush based on number of objects; check the number of entries
self._directory_entries += sum(len(d.entries) for d in directories)
if self._directory_entries >= self._buffer_thresholds["directory_entries"]:
return self.flush(["content", "directory"])
return stats
def revision_add(self, revisions: Sequence[Revision]) -> Dict[str, int]:
stats = self.object_add(revisions, object_type="revision", keys=["id"])
if not stats:
# We did not flush based on number of objects; check the number of
# parents and estimated size
self._revision_parents += sum(len(r.parents) for r in revisions)
self._revision_size += sum(estimate_revision_size(r) for r in revisions)
if (
self._revision_parents >= self._buffer_thresholds["revision_parents"]
or self._revision_size >= self._buffer_thresholds["revision_bytes"]
):
return self.flush(["content", "directory", "revision"])
return stats
def release_add(self, releases: Sequence[Release]) -> Dict[str, int]:
stats = self.object_add(releases, object_type="release", keys=["id"])
if not stats:
# We did not flush based on number of objects; check the estimated size
self._release_size += sum(estimate_release_size(r) for r in releases)
if self._release_size >= self._buffer_thresholds["release_bytes"]:
return self.flush(["content", "directory", "revision", "release"])
return stats
def object_add(
self,
objects: Sequence[BaseModel],
*,
object_type: LObjectType,
keys: Iterable[str],
) -> Dict[str, int]:
"""Push objects to write to the storage in the buffer. Flushes the
buffer to the storage if the threshold is hit.
"""
buffer_ = self._objects[object_type]
for obj in objects:
obj_key = tuple(getattr(obj, key) for key in keys)
buffer_[obj_key] = obj
if len(buffer_) >= self._buffer_thresholds[object_type]:
return self.flush()
return {}
def flush(
self, object_types: Sequence[LObjectType] = OBJECT_TYPES
) -> Dict[str, int]:
summary: Dict[str, int] = {}
def update_summary(stats):
for k, v in stats.items():
summary[k] = v + summary.get(k, 0)
for object_type in object_types:
buffer_ = self._objects[object_type]
if not buffer_:
continue
if logger.isEnabledFor(logging.DEBUG):
log = "Flushing %s objects of type %s"
log_args = [len(buffer_), object_type]
if object_type == "content":
log += " (%s bytes)"
log_args.append(
sum(cast(Content, c).length for c in buffer_.values())
)
elif object_type == "directory":
log += " (%s entries)"
log_args.append(
sum(len(cast(Directory, d).entries) for d in buffer_.values())
)
elif object_type == "revision":
log += " (%s parents, %s estimated bytes)"
log_args.extend(
(
sum(
len(cast(Revision, r).parents) for r in buffer_.values()
),
sum(
estimate_revision_size(cast(Revision, r))
for r in buffer_.values()
),
)
)
elif object_type == "release":
log += " (%s estimated bytes)"
log_args.append(
sum(
estimate_release_size(cast(Release, r))
for r in buffer_.values()
)
)
logger.debug(log, *log_args)
batches = grouper(buffer_.values(), n=self._buffer_thresholds[object_type])
for batch in batches:
add_fn = getattr(self.storage, "%s_add" % object_type)
stats = add_fn(list(batch))
update_summary(stats)
# Flush underlying storage
stats = self.storage.flush(object_types)
update_summary(stats)
self.clear_buffers(object_types)
return summary
def clear_buffers(self, object_types: Sequence[LObjectType] = OBJECT_TYPES) -> None:
"""Clear objects from current buffer.
WARNING:
data that has not been flushed to storage will be lost when this
method is called. This should only be called when `flush` fails and
you want to continue your processing.
"""
for object_type in object_types:
buffer_ = self._objects[object_type]
buffer_.clear()
if object_type == "content":
self._contents_size = 0
elif object_type == "directory":
self._directory_entries = 0
elif object_type == "revision":
self._revision_parents = 0
self._revision_size = 0
elif object_type == "release":
self._release_size = 0
self.storage.clear_buffers(object_types)
diff --git a/swh/storage/proxies/filter.py b/swh/storage/proxies/filter.py
index 14bff3cc..53757be4 100644
--- a/swh/storage/proxies/filter.py
+++ b/swh/storage/proxies/filter.py
@@ -1,145 +1,150 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from typing import Dict, Iterable, List, Set
from swh.model.model import (
Content,
Directory,
Release,
Revision,
Sha1Git,
SkippedContent,
)
from swh.storage import get_storage
from swh.storage.interface import StorageInterface
class FilteringProxyStorage:
"""Filtering Storage implementation. This is in charge of transparently
filtering out known objects prior to adding them to storage.
Sample configuration use case for filtering storage:
.. code-block: yaml
storage:
cls: filter
storage:
cls: remote
url: http://storage.internal.staging.swh.network:5002/
"""
object_types = ["content", "skipped_content", "directory", "revision", "release"]
def __init__(self, storage):
self.storage: StorageInterface = get_storage(**storage)
def __getattr__(self, key):
if key == "storage":
raise AttributeError(key)
return getattr(self.storage, key)
def content_add(self, content: List[Content]) -> Dict[str, int]:
empty_stat = {
"content:add": 0,
"content:add:bytes": 0,
}
if not content:
return empty_stat
contents_to_add = self._filter_missing_contents(content)
if not contents_to_add:
return empty_stat
return self.storage.content_add(
[x for x in content if x.sha256 in contents_to_add]
)
def skipped_content_add(self, content: List[SkippedContent]) -> Dict[str, int]:
empty_stat = {"skipped_content:add": 0}
if not content:
return empty_stat
contents_to_add = self._filter_missing_skipped_contents(content)
if not contents_to_add and not any(c.sha1_git is None for c in content):
return empty_stat
return self.storage.skipped_content_add(
[x for x in content if x.sha1_git is None or x.sha1_git in contents_to_add]
)
def directory_add(self, directories: List[Directory]) -> Dict[str, int]:
empty_stat = {"directory:add": 0}
if not directories:
return empty_stat
missing_ids = self._filter_missing_ids("directory", (d.id for d in directories))
if not missing_ids:
return empty_stat
return self.storage.directory_add(
[d for d in directories if d.id in missing_ids]
)
def revision_add(self, revisions: List[Revision]) -> Dict[str, int]:
empty_stat = {"revision:add": 0}
if not revisions:
return empty_stat
missing_ids = self._filter_missing_ids("revision", (r.id for r in revisions))
if not missing_ids:
return empty_stat
return self.storage.revision_add([r for r in revisions if r.id in missing_ids])
def release_add(self, releases: List[Release]) -> Dict[str, int]:
empty_stat = {"release:add": 0}
if not releases:
return empty_stat
missing_ids = self._filter_missing_ids("release", (r.id for r in releases))
if not missing_ids:
return empty_stat
return self.storage.release_add([r for r in releases if r.id in missing_ids])
def _filter_missing_contents(self, contents: List[Content]) -> Set[bytes]:
"""Return only the content keys missing from swh
Args:
content_hashes: List of sha256 to check for existence in swh
storage
"""
missing_contents = []
for content in contents:
missing_contents.append(content.hashes())
- return set(self.storage.content_missing(missing_contents, key_hash="sha256",))
+ return set(
+ self.storage.content_missing(
+ missing_contents,
+ key_hash="sha256",
+ )
+ )
def _filter_missing_skipped_contents(
self, contents: List[SkippedContent]
) -> Set[Sha1Git]:
"""Return only the content keys missing from swh
Args:
content_hashes: List of sha1_git to check for existence in swh
storage
"""
missing_contents = [c.hashes() for c in contents if c.sha1_git is not None]
ids = set()
for c in self.storage.skipped_content_missing(missing_contents):
if c is None or c.get("sha1_git") is None:
continue
ids.add(c["sha1_git"])
return ids
def _filter_missing_ids(self, object_type: str, ids: Iterable[bytes]) -> Set[bytes]:
"""Filter missing ids from the storage for a given object type.
Args:
object_type: object type to use {revision, directory}
ids: List of object_type ids
Returns:
Missing ids from the storage for object_type
"""
return set(getattr(self.storage, f"{object_type}_missing")(list(ids)))
diff --git a/swh/storage/proxies/retry.py b/swh/storage/proxies/retry.py
index 6beaafa1..402b1ef7 100644
--- a/swh/storage/proxies/retry.py
+++ b/swh/storage/proxies/retry.py
@@ -1,83 +1,81 @@
# Copyright (C) 2019-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import logging
import traceback
from tenacity import retry, stop_after_attempt, wait_random_exponential
from swh.storage import get_storage
from swh.storage.exc import StorageArgumentException
from swh.storage.interface import StorageInterface
logger = logging.getLogger(__name__)
def should_retry_adding(retry_state) -> bool:
- """Retry if the error/exception is (probably) not about a caller error
-
- """
+ """Retry if the error/exception is (probably) not about a caller error"""
attempt = retry_state.outcome
if attempt.failed:
error = attempt.exception()
if isinstance(error, StorageArgumentException):
# Exception is due to an invalid argument
return False
elif isinstance(error, KeyboardInterrupt):
return False
else:
# Other exception
module = getattr(error, "__module__", None)
if module:
error_name = error.__module__ + "." + error.__class__.__name__
else:
error_name = error.__class__.__name__
logger.warning(
"Retrying RPC call",
exc_info=False,
extra={
"swh_type": "storage_retry",
"swh_exception_type": error_name,
"swh_exception": traceback.format_exc(),
},
)
return True
else:
# No exception
return False
swh_retry = retry(
retry=should_retry_adding,
wait=wait_random_exponential(multiplier=1, max=10),
stop=stop_after_attempt(3),
)
def retry_function(storage, attribute_name):
@swh_retry
def newf(*args, **kwargs):
return getattr(storage, attribute_name)(*args, **kwargs)
return newf
class RetryingProxyStorage:
"""Storage implementation which retries adding objects when it specifically
- fails (hash collision, integrity error).
+ fails (hash collision, integrity error).
"""
def __init__(self, storage):
self.storage: StorageInterface = get_storage(**storage)
for attribute_name in dir(StorageInterface):
if attribute_name.startswith("_"):
continue
attribute = getattr(self.storage, attribute_name)
if hasattr(attribute, "__call__"):
setattr(
self, attribute_name, retry_function(self.storage, attribute_name)
)
diff --git a/swh/storage/proxies/tenacious.py b/swh/storage/proxies/tenacious.py
index 1c47c032..ac14c200 100644
--- a/swh/storage/proxies/tenacious.py
+++ b/swh/storage/proxies/tenacious.py
@@ -1,175 +1,176 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from collections import Counter, deque
from functools import partial
import logging
from typing import Counter as CounterT
from typing import Deque, Dict, Iterable, List, Optional
from swh.model.model import BaseModel
from swh.storage import get_storage
logger = logging.getLogger(__name__)
class RateQueue:
def __init__(self, size: int, max_errors: int):
assert size > max_errors
self._size = size
self._max_errors = max_errors
self._errors: Deque[bool] = deque(maxlen=size)
def add_ok(self, n_ok: int = 1) -> None:
self._errors.extend([False] * n_ok)
def add_error(self, n_error: int = 1) -> None:
self._errors.extend([True] * n_error)
def limit_reached(self) -> bool:
return sum(self._errors) > self._max_errors
def reset(self):
# mainly for testing purpose
self._errors.clear()
class TenaciousProxyStorage:
"""Storage proxy that have a tenacious insertion behavior.
When an xxx_add method is called, it's first attempted as is against the backend
storage. If a failure occurs, split the list of inserted objects in pieces until
erroneous objects have been identified, so all the valid objects are guaranteed to
be inserted.
Also provides a error-rate limit feature: if more than n errors occurred during the
insertion of the last p (window_size) objects, stop accepting any insertion.
The number of insertion retries for a single object can be specified via
the 'retries' parameter.
This proxy is mainly intended to be used in a replayer configuration (aka a
mirror stack), where insertion errors are mostly unexpected (which explains
the low default ratio errors/window_size).
Conversely, it should not be used in a loader configuration, as it may
drop objects without stopping the loader, which leads to holes in the graph.
Deployments using this proxy should carefully monitor their logs to check any
failure is expected (because the failed object is corrupted),
not because of transient errors or issues with the storage backend.
Sample configuration use case for tenacious storage:
.. code-block:: yaml
storage:
cls: tenacious
storage:
cls: remote
args: http://storage.internal.staging.swh.network:5002/
error-rate-limit:
errors: 10
window_size: 1000
"""
tenacious_methods: Dict[str, str] = {
"content_add": "content",
"content_add_metadata": "content",
"skipped_content_add": "skipped_content",
"directory_add": "directory",
"revision_add": "revision",
"extid_add": "extid",
"release_add": "release",
"snapshot_add": "snapshot",
"origin_add": "origin",
}
def __init__(
self,
storage,
error_rate_limit: Optional[Dict[str, int]] = None,
retries: int = 3,
):
self.storage = get_storage(**storage)
if error_rate_limit is None:
error_rate_limit = {"errors": 10, "window_size": 1000}
assert "errors" in error_rate_limit
assert "window_size" in error_rate_limit
self.rate_queue = RateQueue(
- size=error_rate_limit["window_size"], max_errors=error_rate_limit["errors"],
+ size=error_rate_limit["window_size"],
+ max_errors=error_rate_limit["errors"],
)
self._single_object_retries: int = retries
def __getattr__(self, key):
if key in self.tenacious_methods:
return partial(self._tenacious_add, key)
return getattr(self.storage, key)
def _tenacious_add(self, func_name, objects: Iterable[BaseModel]) -> Dict[str, int]:
"""Enqueue objects to write to the storage. This checks if the queue's
- threshold is hit. If it is actually write those to the storage.
+ threshold is hit. If it is actually write those to the storage.
"""
add_function = getattr(self.storage, func_name)
object_type = self.tenacious_methods[func_name]
# list of lists of objects; note this to_add list is consumed from the tail
to_add: List[List[BaseModel]] = [list(objects)]
n_objs: int = len(to_add[0])
results: CounterT[str] = Counter()
retries: int = self._single_object_retries
while to_add:
if self.rate_queue.limit_reached():
logging.error(
"Too many insertion errors have been detected; "
"disabling insertions"
)
raise RuntimeError(
"Too many insertion errors have been detected; "
"disabling insertions"
)
objs = to_add.pop()
try:
results.update(add_function(objs))
self.rate_queue.add_ok(len(objs))
except Exception as exc:
if len(objs) > 1:
logger.info(
f"{func_name}: failed to insert a batch of "
f"{len(objs)} {object_type} objects, splitting"
)
# reinsert objs split in 2 parts at the end of to_add
to_add.append(objs[(len(objs) // 2) :])
to_add.append(objs[: (len(objs) // 2)])
# each time we append a batch in the to_add bag, reset the
# one-object-batch retries counter
retries = self._single_object_retries
else:
retries -= 1
if retries:
logger.info(
f"{func_name}: failed to insert an {object_type}, retrying"
)
# give it another chance
to_add.append(objs)
else:
logger.error(
f"{func_name}: failed to insert an object, "
f"excluding {objs} (from a batch of {n_objs})"
)
logger.exception(f"Exception was: {exc}")
results.update({f"{object_type}:add:errors": 1})
self.rate_queue.add_error()
# reset the retries counter (needed in case the next
# batch is also 1 element only)
retries = self._single_object_retries
return dict(results)
def reset(self):
self.rate_queue.reset()
diff --git a/swh/storage/replay.py b/swh/storage/replay.py
index eb86a16b..5bdbefcf 100644
--- a/swh/storage/replay.py
+++ b/swh/storage/replay.py
@@ -1,231 +1,229 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from collections import Counter
from functools import partial
import logging
from typing import Any, Callable
from typing import Counter as CounterT
from typing import Dict, List, Optional, TypeVar, Union, cast
try:
from systemd.daemon import notify
except ImportError:
notify = None
from swh.core.statsd import statsd
from swh.journal.serializers import kafka_to_value
from swh.model.hashutil import hash_to_hex
from swh.model.model import (
BaseContent,
BaseModel,
Content,
Directory,
ExtID,
HashableObject,
MetadataAuthority,
MetadataFetcher,
Origin,
OriginVisit,
OriginVisitStatus,
RawExtrinsicMetadata,
Release,
Revision,
SkippedContent,
Snapshot,
)
from swh.storage.exc import HashCollision, StorageArgumentException
from swh.storage.interface import StorageInterface
from swh.storage.utils import remove_keys
logger = logging.getLogger(__name__)
GRAPH_OPERATIONS_METRIC = "swh_graph_replayer_operations_total"
GRAPH_DURATION_METRIC = "swh_graph_replayer_duration_seconds"
OBJECT_CONVERTERS: Dict[str, Callable[[Dict], BaseModel]] = {
"origin": Origin.from_dict,
"origin_visit": OriginVisit.from_dict,
"origin_visit_status": OriginVisitStatus.from_dict,
"snapshot": Snapshot.from_dict,
"revision": Revision.from_dict,
"release": Release.from_dict,
"directory": Directory.from_dict,
"content": Content.from_dict,
"skipped_content": SkippedContent.from_dict,
"metadata_authority": MetadataAuthority.from_dict,
"metadata_fetcher": MetadataFetcher.from_dict,
"raw_extrinsic_metadata": RawExtrinsicMetadata.from_dict,
"extid": ExtID.from_dict,
}
# Deprecated, for BW compat only.
object_converter_fn = OBJECT_CONVERTERS
OBJECT_FIXERS = {
"revision": partial(remove_keys, keys=("metadata",)),
}
class ModelObjectDeserializer:
"""A swh.journal object deserializer that checks object validity and reports
invalid objects
The deserializer will directly produce BaseModel objects from journal
objects representations.
If validation is activated and the object is hashable, it will check if the
computed hash matches the identifier of the object.
If the object is invalid and a 'reporter' function is given, it will be
called with 2 arguments::
reporter(object_id, journal_msg)
Where 'object_id' is a string representation of the object identifier (from
the journal message), and 'journal_msg' is the row message (bytes)
retrieved from the journal.
If 'raise_on_error' is True, a 'StorageArgumentException' exception is
raised.
Typical usage::
deserializer = ModelObjectDeserializer(validate=True, reporter=reporter_cb)
client = get_journal_client(
cls="kafka", value_deserializer=deserializer, **cfg)
"""
def __init__(
self,
validate: bool = True,
raise_on_error: bool = False,
reporter: Optional[Callable[[str, bytes], None]] = None,
):
self.validate = validate
self.reporter = reporter
self.raise_on_error = raise_on_error
def convert(self, object_type: str, msg: bytes) -> Optional[BaseModel]:
dict_repr = kafka_to_value(msg)
if object_type in OBJECT_FIXERS:
dict_repr = OBJECT_FIXERS[object_type](dict_repr)
obj = OBJECT_CONVERTERS[object_type](dict_repr)
if self.validate:
if isinstance(obj, HashableObject):
cid = obj.compute_hash()
if obj.id != cid:
error_msg = (
f"Object has id {hash_to_hex(obj.id)}, "
f"but it should be {hash_to_hex(cid)}: {obj}"
)
logger.error(error_msg)
self.report_failure(msg, obj)
if self.raise_on_error:
raise StorageArgumentException(error_msg)
return None
return obj
def report_failure(self, msg: bytes, obj: BaseModel):
if self.reporter:
oid: str = ""
if hasattr(obj, "swhid"):
swhid = obj.swhid() # type: ignore[attr-defined]
oid = str(swhid)
elif isinstance(obj, HashableObject):
uid = obj.compute_hash()
oid = f"{obj.object_type}:{uid.hex()}" # type: ignore[attr-defined]
if oid:
self.reporter(oid, msg)
def process_replay_objects(
all_objects: Dict[str, List[BaseModel]], *, storage: StorageInterface
) -> None:
for (object_type, objects) in all_objects.items():
logger.debug("Inserting %s %s objects", len(objects), object_type)
with statsd.timed(GRAPH_DURATION_METRIC, tags={"object_type": object_type}):
_insert_objects(object_type, objects, storage)
statsd.increment(
GRAPH_OPERATIONS_METRIC, len(objects), tags={"object_type": object_type}
)
if notify:
notify("WATCHDOG=1")
ContentType = TypeVar("ContentType", bound=BaseContent)
def collision_aware_content_add(
contents: List[ContentType],
content_add_fn: Callable[[List[ContentType]], Dict[str, int]],
) -> Dict[str, int]:
"""Add contents to storage. If a hash collision is detected, an error is
logged. Then this adds the other non colliding contents to the storage.
Args:
content_add_fn: Storage content callable
contents: List of contents or skipped contents to add to storage
"""
if not contents:
return {}
colliding_content_hashes: List[Dict[str, Any]] = []
results: CounterT[str] = Counter()
while True:
try:
results.update(content_add_fn(contents))
except HashCollision as e:
colliding_content_hashes.append(
{
"algo": e.algo,
"hash": e.hash_id, # hex hash id
"objects": e.colliding_contents, # hex hashes
}
)
colliding_hashes = e.colliding_content_hashes()
# Drop the colliding contents from the transaction
contents = [c for c in contents if c.hashes() not in colliding_hashes]
else:
# Successfully added contents, we are done
break
if colliding_content_hashes:
for collision in colliding_content_hashes:
logger.error("Collision detected: %(collision)s", {"collision": collision})
return dict(results)
def _insert_objects(
object_type: str, objects: List[BaseModel], storage: StorageInterface
) -> None:
- """Insert objects of type object_type in the storage.
-
- """
+ """Insert objects of type object_type in the storage."""
if object_type not in OBJECT_CONVERTERS:
logger.warning("Received a series of %s, this should not happen", object_type)
return
method = getattr(storage, f"{object_type}_add")
if object_type == "skipped_content":
method = partial(collision_aware_content_add, content_add_fn=method)
elif object_type == "content":
method = partial(
collision_aware_content_add, content_add_fn=storage.content_add_metadata
)
elif object_type in ("origin_visit", "origin_visit_status"):
origins: List[Origin] = []
for obj in cast(List[Union[OriginVisit, OriginVisitStatus]], objects):
origins.append(Origin(url=obj.origin))
storage.origin_add(origins)
elif object_type == "raw_extrinsic_metadata":
emds = cast(List[RawExtrinsicMetadata], objects)
authorities = {emd.authority for emd in emds}
fetchers = {emd.fetcher for emd in emds}
storage.metadata_authority_add(list(authorities))
storage.metadata_fetcher_add(list(fetchers))
method(objects)
diff --git a/swh/storage/tests/algos/test_origin.py b/swh/storage/tests/algos/test_origin.py
index 80bced32..03ad695b 100644
--- a/swh/storage/tests/algos/test_origin.py
+++ b/swh/storage/tests/algos/test_origin.py
@@ -1,356 +1,356 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
from swh.model.model import Origin, OriginVisit, OriginVisitStatus
from swh.storage.algos.origin import (
iter_origin_visit_statuses,
iter_origin_visits,
iter_origins,
origin_get_latest_visit_status,
)
from swh.storage.interface import ListOrder
from swh.storage.tests.storage_tests import round_to_milliseconds
from swh.storage.utils import now
def test_iter_origins(swh_storage):
origins = [
Origin(url="bar"),
Origin(url="qux"),
Origin(url="quuz"),
]
assert swh_storage.origin_add(origins) == {"origin:add": 3}
# this returns all the origins, only the number of paged called is different
assert list(iter_origins(swh_storage)) == origins
assert list(iter_origins(swh_storage, limit=1)) == origins
assert list(iter_origins(swh_storage, limit=2)) == origins
def test_origin_get_latest_visit_status_none(swh_storage, sample_data):
- """Looking up unknown objects should return nothing
-
- """
+ """Looking up unknown objects should return nothing"""
# unknown origin so no result
assert origin_get_latest_visit_status(swh_storage, "unknown-origin") is None
# unknown type so no result
origin = sample_data.origin
origin_visit = sample_data.origin_visit
assert origin_visit.origin == origin.url
swh_storage.origin_add([origin])
swh_storage.origin_visit_add([origin_visit])[0]
assert origin_visit.type != "unknown"
actual_origin_visit = origin_get_latest_visit_status(
swh_storage, origin.url, type="unknown"
)
assert actual_origin_visit is None
actual_origin_visit = origin_get_latest_visit_status(
swh_storage, origin.url, require_snapshot=True
)
assert actual_origin_visit is None
def init_storage_with_origin_visits(swh_storage, sample_data):
- """Initialize storage with origin/origin-visit/origin-visit-status
-
- """
+ """Initialize storage with origin/origin-visit/origin-visit-status"""
snapshot = sample_data.snapshots[2]
origin1, origin2 = sample_data.origins[:2]
swh_storage.origin_add([origin1, origin2])
ov1, ov2 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin1.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
),
OriginVisit(
origin=origin2.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
),
]
)
swh_storage.snapshot_add([snapshot])
date_now = now()
date_now = round_to_milliseconds(date_now)
assert sample_data.date_visit1 < sample_data.date_visit2
assert sample_data.date_visit2 < date_now
# origin visit status 1 for origin visit 1
ovs11 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=ov1.date + datetime.timedelta(seconds=10), # so it's not ignored
type=ov1.type,
status="partial",
snapshot=None,
)
# origin visit status 2 for origin visit 1
ovs12 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=sample_data.date_visit2,
type=ov1.type,
status="ongoing",
snapshot=None,
)
# origin visit status 1 for origin visit 2
ovs21 = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=ov2.date + datetime.timedelta(seconds=10), # so it's not ignored
type=ov2.type,
status="ongoing",
snapshot=None,
)
# origin visit status 2 for origin visit 2
ovs22 = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=date_now,
type=ov2.type,
status="full",
snapshot=snapshot.id,
metadata={"something": "wicked"},
)
swh_storage.origin_visit_status_add([ovs11, ovs12, ovs21, ovs22])
return {
"origin": [origin1, origin2],
"origin_visit": [ov1, ov2],
"origin_visit_status": [ovs11, ovs12, ovs21, ovs22],
}
def test_origin_get_latest_visit_status_filter_type(swh_storage, sample_data):
- """Filtering origin visit per types should yield consistent results
-
- """
+ """Filtering origin visit per types should yield consistent results"""
objects = init_storage_with_origin_visits(swh_storage, sample_data)
origin1, origin2 = objects["origin"]
ov1, ov2 = objects["origin_visit"]
ovs11, ovs12, _, ovs22 = objects["origin_visit_status"]
# no visit for origin1 url with type_visit2
assert (
origin_get_latest_visit_status(
swh_storage, origin1.url, type=sample_data.type_visit2
)
is None
)
# no visit for origin2 url with type_visit1
assert (
origin_get_latest_visit_status(
swh_storage, origin2.url, type=sample_data.type_visit1
)
is None
)
# Two visits, both with no snapshot, take the most recent
actual_ovs12 = origin_get_latest_visit_status(
swh_storage, origin1.url, type=sample_data.type_visit1
)
assert isinstance(actual_ovs12, OriginVisitStatus)
assert actual_ovs12 == ovs12
assert actual_ovs12.origin == ov1.origin
assert actual_ovs12.visit == ov1.visit
assert actual_ovs12.type == sample_data.type_visit1
# take the most recent visit with type_visit2
actual_ovs22 = origin_get_latest_visit_status(
swh_storage, origin2.url, type=sample_data.type_visit2
)
assert isinstance(actual_ovs22, OriginVisitStatus)
assert actual_ovs22 == ovs22
assert actual_ovs22.origin == ov2.origin
assert actual_ovs22.visit == ov2.visit
assert actual_ovs22.type == sample_data.type_visit2
def test_origin_get_latest_visit_status_filter_status(swh_storage, sample_data):
objects = init_storage_with_origin_visits(swh_storage, sample_data)
origin1, origin2 = objects["origin"]
ov1, ov2 = objects["origin_visit"]
ovs11, ovs12, _, ovs22 = objects["origin_visit_status"]
# no partial status for that origin visit
assert (
origin_get_latest_visit_status(
swh_storage, origin2.url, allowed_statuses=["partial"]
)
is None
)
# only 1 partial for that visit
actual_ovs11 = origin_get_latest_visit_status(
swh_storage, origin1.url, allowed_statuses=["partial"]
)
assert actual_ovs11 == ovs11
assert actual_ovs11.origin == ov1.origin
assert actual_ovs11.visit == ov1.visit
assert actual_ovs11.type == sample_data.type_visit1
# both status exist, take the latest one
actual_ovs12 = origin_get_latest_visit_status(
swh_storage, origin1.url, allowed_statuses=["partial", "ongoing"]
)
assert actual_ovs12 == ovs12
assert actual_ovs12.origin == ov1.origin
assert actual_ovs12.visit == ov1.visit
assert actual_ovs12.type == sample_data.type_visit1
assert isinstance(actual_ovs12, OriginVisitStatus)
assert actual_ovs12 == ovs12
assert actual_ovs12.origin == ov1.origin
assert actual_ovs12.visit == ov1.visit
assert actual_ovs12.type == sample_data.type_visit1
# take the most recent visit with type_visit2
actual_ovs22 = origin_get_latest_visit_status(
swh_storage, origin2.url, allowed_statuses=["full"]
)
assert actual_ovs22 == ovs22
assert actual_ovs22.origin == ov2.origin
assert actual_ovs22.visit == ov2.visit
assert actual_ovs22.type == sample_data.type_visit2
def test_origin_get_latest_visit_status_filter_snapshot(swh_storage, sample_data):
objects = init_storage_with_origin_visits(swh_storage, sample_data)
origin1, origin2 = objects["origin"]
_, ov2 = objects["origin_visit"]
_, _, _, ovs22 = objects["origin_visit_status"]
# there is no visit with snapshot yet for that visit
assert (
origin_get_latest_visit_status(swh_storage, origin1.url, require_snapshot=True)
is None
)
# visit status with partial status visit elected
actual_ovs22 = origin_get_latest_visit_status(
swh_storage, origin2.url, require_snapshot=True
)
assert actual_ovs22 == ovs22
assert actual_ovs22.origin == ov2.origin
assert actual_ovs22.visit == ov2.visit
assert actual_ovs22.type == ov2.type
date_now = now()
# Add another visit
swh_storage.origin_visit_add(
- [OriginVisit(origin=origin2.url, date=date_now, type=sample_data.type_visit2,),]
+ [
+ OriginVisit(
+ origin=origin2.url,
+ date=date_now,
+ type=sample_data.type_visit2,
+ ),
+ ]
)
# Requiring the latest visit with a snapshot, we still find the previous visit
ovs22 = origin_get_latest_visit_status(
swh_storage, origin2.url, require_snapshot=True
)
assert actual_ovs22 == ovs22
assert actual_ovs22.origin == ov2.origin
assert actual_ovs22.visit == ov2.visit
assert actual_ovs22.type == ov2.type
def test_iter_origin_visits(swh_storage, sample_data):
"""Iter over origin visits for an origin returns all visits"""
origin1, origin2 = sample_data.origins[:2]
swh_storage.origin_add([origin1, origin2])
date_past = now() - datetime.timedelta(weeks=20)
new_visits = []
for visit_id in range(20):
new_visits.append(
OriginVisit(
origin=origin1.url,
date=date_past + datetime.timedelta(days=visit_id),
type="git",
)
)
visits = swh_storage.origin_visit_add(new_visits)
reversed_visits = list(reversed(visits))
# no limit, order asc
actual_visits = list(iter_origin_visits(swh_storage, origin1.url))
assert actual_visits == visits
# no limit, order desc
actual_visits = list(
iter_origin_visits(swh_storage, origin1.url, order=ListOrder.DESC)
)
assert actual_visits == reversed_visits
# no result
actual_visits = list(iter_origin_visits(swh_storage, origin2.url))
assert actual_visits == []
def test_iter_origin_visit_status(swh_storage, sample_data):
origin1, origin2 = sample_data.origins[:2]
swh_storage.origin_add([origin1])
ov1 = swh_storage.origin_visit_add([sample_data.origin_visit])[0]
assert ov1.origin == origin1.url
date_past = now() - datetime.timedelta(weeks=20)
ovs1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=ov1.date,
type=ov1.type,
status="created",
snapshot=None,
)
new_visit_statuses = [ovs1]
for i in range(20):
status_date = date_past + datetime.timedelta(days=i)
new_visit_statuses.append(
OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=status_date,
type=ov1.type,
status="created",
snapshot=None,
)
)
swh_storage.origin_visit_status_add(new_visit_statuses)
reversed_visit_statuses = list(reversed(new_visit_statuses))
# order asc
actual_visit_statuses = list(
iter_origin_visit_statuses(swh_storage, ov1.origin, ov1.visit)
)
assert actual_visit_statuses == new_visit_statuses
# order desc
actual_visit_statuses = list(
iter_origin_visit_statuses(
swh_storage, ov1.origin, ov1.visit, order=ListOrder.DESC
)
)
assert actual_visit_statuses == reversed_visit_statuses
# no result
actual_visit_statuses = list(
iter_origin_visit_statuses(swh_storage, origin2.url, ov1.visit)
)
assert actual_visit_statuses == []
diff --git a/swh/storage/tests/algos/test_snapshot.py b/swh/storage/tests/algos/test_snapshot.py
index 4ea67356..5e6e9af6 100644
--- a/swh/storage/tests/algos/test_snapshot.py
+++ b/swh/storage/tests/algos/test_snapshot.py
@@ -1,403 +1,425 @@
# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from hypothesis import given, settings
import pytest
from swh.model.hypothesis_strategies import branch_names, branch_targets, snapshots
from swh.model.model import (
OriginVisit,
OriginVisitStatus,
Snapshot,
SnapshotBranch,
TargetType,
)
from swh.storage.algos.snapshot import (
snapshot_get_all_branches,
snapshot_get_latest,
snapshot_id_get_from_revision,
snapshot_resolve_alias,
visits_and_snapshots_get_from_revision,
)
from swh.storage.tests.conftest import function_scoped_fixture_check
from swh.storage.utils import now
@pytest.fixture
def swh_storage_backend_config():
yield {
"cls": "memory",
"journal_writer": None,
}
@settings(suppress_health_check=function_scoped_fixture_check)
@given(snapshot=snapshots(min_size=0, max_size=10, only_objects=False))
def test_snapshot_small(swh_storage, snapshot): # noqa
swh_storage.snapshot_add([snapshot])
returned_snapshot = snapshot_get_all_branches(swh_storage, snapshot.id)
assert snapshot == returned_snapshot
@settings(suppress_health_check=function_scoped_fixture_check)
@given(branch_name=branch_names(), branch_target=branch_targets(only_objects=True))
def test_snapshot_large(swh_storage, branch_name, branch_target): # noqa
snapshot = Snapshot(
branches={b"%s%05d" % (branch_name, i): branch_target for i in range(10000)},
)
swh_storage.snapshot_add([snapshot])
returned_snapshot = snapshot_get_all_branches(swh_storage, snapshot.id)
assert snapshot == returned_snapshot
def test_snapshot_get_latest_none(swh_storage, sample_data):
"""Retrieve latest snapshot on unknown origin or origin without snapshot should
yield no result
"""
# unknown origin so None
assert snapshot_get_latest(swh_storage, "unknown-origin") is None
# no snapshot on origin visit so None
origin = sample_data.origin
swh_storage.origin_add([origin])
origin_visit, origin_visit2 = sample_data.origin_visits[:2]
assert origin_visit.origin == origin.url
swh_storage.origin_visit_add([origin_visit])
assert snapshot_get_latest(swh_storage, origin.url) is None
ov1 = swh_storage.origin_visit_get_latest(origin.url)
assert ov1 is not None
# visit references a snapshot but the snapshot does not exist in backend for some
# reason
complete_snapshot = sample_data.snapshots[2]
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=origin_visit2.date,
status="partial",
snapshot=complete_snapshot.id,
)
]
)
# so we do not find it
assert snapshot_get_latest(swh_storage, origin.url) is None
assert snapshot_get_latest(swh_storage, origin.url, branches_count=1) is None
def test_snapshot_get_latest(swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
visit1, visit2 = sample_data.origin_visits[:2]
assert visit1.origin == origin.url
swh_storage.origin_visit_add([visit1])
ov1 = swh_storage.origin_visit_get_latest(origin.url)
# Add snapshot to visit1, latest snapshot = visit 1 snapshot
complete_snapshot = sample_data.snapshots[2]
swh_storage.snapshot_add([complete_snapshot])
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=visit2.date,
status="partial",
snapshot=None,
)
]
)
assert visit1.date < visit2.date
# no snapshot associated to the visit, so None
actual_snapshot = snapshot_get_latest(
swh_storage, origin.url, allowed_statuses=["partial"]
)
assert actual_snapshot is None
date_now = now()
assert visit2.date < date_now
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_now,
type=ov1.type,
status="full",
snapshot=complete_snapshot.id,
)
]
)
swh_storage.origin_visit_add(
- [OriginVisit(origin=origin.url, date=now(), type=visit1.type,)]
+ [
+ OriginVisit(
+ origin=origin.url,
+ date=now(),
+ type=visit1.type,
+ )
+ ]
)
actual_snapshot = snapshot_get_latest(swh_storage, origin.url)
assert actual_snapshot is not None
assert actual_snapshot == complete_snapshot
actual_snapshot = snapshot_get_latest(swh_storage, origin.url, branches_count=1)
assert actual_snapshot is not None
assert actual_snapshot.id == complete_snapshot.id
assert len(actual_snapshot.branches.values()) == 1
with pytest.raises(ValueError, match="branches_count must be a positive integer"):
snapshot_get_latest(swh_storage, origin.url, branches_count="something-wrong")
def test_snapshot_id_get_from_revision(swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
date_visit2 = now()
visit1, visit2 = sample_data.origin_visits[:2]
assert visit1.origin == origin.url
ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2])
revision1, revision2, revision3 = sample_data.revisions[:3]
swh_storage.revision_add([revision1, revision2])
empty_snapshot, complete_snapshot = sample_data.snapshots[1:3]
swh_storage.snapshot_add([complete_snapshot])
# Add complete_snapshot to visit1 which targets revision1
ovs1, ovs2 = [
OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit2,
type=ov1.type,
status="partial",
snapshot=complete_snapshot.id,
),
OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=now(),
type=ov2.type,
status="full",
snapshot=empty_snapshot.id,
),
]
swh_storage.origin_visit_status_add([ovs1, ovs2])
assert ov1.date < ov2.date
assert ov2.date < ovs1.date
assert ovs1.date < ovs2.date
# revision3 does not exist so result is None
actual_snapshot_id = snapshot_id_get_from_revision(
swh_storage, origin.url, revision3.id
)
assert actual_snapshot_id is None
# no snapshot targets revision2 for origin.url so result is None
actual_snapshot_id = snapshot_id_get_from_revision(
swh_storage, origin.url, revision2.id
)
assert actual_snapshot_id is None
# complete_snapshot targets at least revision1
actual_snapshot_id = snapshot_id_get_from_revision(
swh_storage, origin.url, revision1.id
)
assert actual_snapshot_id == complete_snapshot.id
def test_visit_and_snapshot_get_from_revision(swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
date_visit2 = now()
visit1, visit2 = sample_data.origin_visits[:2]
assert visit1.origin == origin.url
ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2])
revision1, revision2, revision3 = sample_data.revisions[:3]
swh_storage.revision_add([revision1, revision2])
empty_snapshot, complete_snapshot = sample_data.snapshots[1:3]
swh_storage.snapshot_add([complete_snapshot])
# Add complete_snapshot to visit1 which targets revision1
ovs1, ovs2 = [
OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit2,
type=ov1.type,
status="partial",
snapshot=complete_snapshot.id,
),
OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=now(),
type=ov2.type,
status="full",
snapshot=empty_snapshot.id,
),
]
swh_storage.origin_visit_status_add([ovs1, ovs2])
assert ov1.date < ov2.date
assert ov2.date < ovs1.date
assert ovs1.date < ovs2.date
# revision3 does not exist so result is None
actual_snapshot_id = snapshot_id_get_from_revision(
swh_storage, origin.url, revision3.id
)
assert actual_snapshot_id is None
# no snapshot targets revision2 for origin.url so result is None
res = list(
visits_and_snapshots_get_from_revision(swh_storage, origin.url, revision2.id)
)
assert res == []
# complete_snapshot targets at least revision1
res = list(
visits_and_snapshots_get_from_revision(swh_storage, origin.url, revision1.id)
)
assert res == [(ov1, ovs1, complete_snapshot)]
def test_snapshot_resolve_aliases_unknown_snapshot(swh_storage):
assert snapshot_resolve_alias(swh_storage, b"foo", b"HEAD") is None
def test_snapshot_resolve_aliases_no_aliases(swh_storage):
snapshot = Snapshot(branches={})
swh_storage.snapshot_add([snapshot])
assert snapshot_resolve_alias(swh_storage, snapshot.id, b"HEAD") is None
def test_snapshot_resolve_alias(swh_storage, sample_data):
rev_branch_name = b"revision_branch"
rel_branch_name = b"release_branch"
rev_alias1_name = b"rev_alias1"
rev_alias2_name = b"rev_alias2"
rev_alias3_name = b"rev_alias3"
rel_alias_name = b"rel_alias"
rev_branch_info = SnapshotBranch(
- target=sample_data.revisions[0].id, target_type=TargetType.REVISION,
+ target=sample_data.revisions[0].id,
+ target_type=TargetType.REVISION,
)
rel_branch_info = SnapshotBranch(
- target=sample_data.releases[0].id, target_type=TargetType.RELEASE,
+ target=sample_data.releases[0].id,
+ target_type=TargetType.RELEASE,
)
rev_alias1_branch_info = SnapshotBranch(
target=rev_branch_name, target_type=TargetType.ALIAS
)
rev_alias2_branch_info = SnapshotBranch(
target=rev_alias1_name, target_type=TargetType.ALIAS
)
rev_alias3_branch_info = SnapshotBranch(
target=rev_alias2_name, target_type=TargetType.ALIAS
)
rel_alias_branch_info = SnapshotBranch(
target=rel_branch_name, target_type=TargetType.ALIAS
)
snapshot = Snapshot(
branches={
rev_branch_name: rev_branch_info,
rel_branch_name: rel_branch_info,
rev_alias1_name: rev_alias1_branch_info,
rev_alias2_name: rev_alias2_branch_info,
rev_alias3_name: rev_alias3_branch_info,
rel_alias_name: rel_alias_branch_info,
}
)
swh_storage.snapshot_add([snapshot])
for alias_name, expected_branch in (
(rev_alias1_name, rev_branch_info),
- (rev_alias2_name, rev_branch_info,),
- (rev_alias3_name, rev_branch_info,),
+ (
+ rev_alias2_name,
+ rev_branch_info,
+ ),
+ (
+ rev_alias3_name,
+ rev_branch_info,
+ ),
(rel_alias_name, rel_branch_info),
):
assert (
snapshot_resolve_alias(swh_storage, snapshot.id, alias_name)
== expected_branch
)
def test_snapshot_resolve_alias_dangling_branch(swh_storage):
dangling_branch_name = b"dangling_branch"
alias_name = b"rev_alias"
alias_branch = SnapshotBranch(
target=dangling_branch_name, target_type=TargetType.ALIAS
)
snapshot = Snapshot(
- branches={dangling_branch_name: None, alias_name: alias_branch,}
+ branches={
+ dangling_branch_name: None,
+ alias_name: alias_branch,
+ }
)
swh_storage.snapshot_add([snapshot])
assert snapshot_resolve_alias(swh_storage, snapshot.id, alias_name) is None
def test_snapshot_resolve_alias_missing_branch(swh_storage):
missing_branch_name = b"missing_branch"
alias_name = b"rev_alias"
alias_branch = SnapshotBranch(
target=missing_branch_name, target_type=TargetType.ALIAS
)
- snapshot = Snapshot(id=b"42" * 10, branches={alias_name: alias_branch,})
+ snapshot = Snapshot(
+ id=b"42" * 10,
+ branches={
+ alias_name: alias_branch,
+ },
+ )
swh_storage.snapshot_add([snapshot])
assert snapshot_resolve_alias(swh_storage, snapshot.id, alias_name) is None
def test_snapshot_resolve_alias_cycle_found(swh_storage):
alias1_name = b"alias_1"
alias2_name = b"alias_2"
alias3_name = b"alias_3"
alias4_name = b"alias_4"
alias1_branch_info = SnapshotBranch(
target=alias2_name, target_type=TargetType.ALIAS
)
alias2_branch_info = SnapshotBranch(
target=alias3_name, target_type=TargetType.ALIAS
)
alias3_branch_info = SnapshotBranch(
target=alias4_name, target_type=TargetType.ALIAS
)
alias4_branch_info = SnapshotBranch(
target=alias2_name, target_type=TargetType.ALIAS
)
snapshot = Snapshot(
branches={
alias1_name: alias1_branch_info,
alias2_name: alias2_branch_info,
alias3_name: alias3_branch_info,
alias4_name: alias4_branch_info,
}
)
swh_storage.snapshot_add([snapshot])
assert snapshot_resolve_alias(swh_storage, snapshot.id, alias1_name) is None
diff --git a/swh/storage/tests/conftest.py b/swh/storage/tests/conftest.py
index 1add5093..d8817936 100644
--- a/swh/storage/tests/conftest.py
+++ b/swh/storage/tests/conftest.py
@@ -1,73 +1,76 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import multiprocessing.util
from hypothesis import HealthCheck, settings
import pytest
try:
import pytest_cov.embed
except ImportError:
pytest_cov = None
from typing import Iterable
from swh.model.model import BaseContent, Origin
from swh.model.tests.generate_testdata import gen_contents, gen_origins
from swh.storage.interface import StorageInterface
# we use getattr here to keep mypy happy regardless hypothesis version
function_scoped_fixture_check = (
[getattr(HealthCheck, "function_scoped_fixture")]
if hasattr(HealthCheck, "function_scoped_fixture")
else []
)
# define tests profile. Full documentation is at:
# https://hypothesis.readthedocs.io/en/latest/settings.html#settings-profiles
settings.register_profile("fast", max_examples=5, deadline=5000)
settings.register_profile("slow", max_examples=20, deadline=5000)
# Load the fast profile by default to overcome default hypothesis values
# (max_examples=100, deadline=200) that are unsuitable for our tests.
# This can still be overloaded via the --hypothesis-profile option.
settings.load_profile("fast")
if pytest_cov is not None:
# pytest_cov + multiprocessing can cause a segmentation fault when starting
# the child process ; so we're
# removing pytest-coverage's hook that runs when a child process starts.
# This means code run in child processes won't be counted in the coverage
# report, but this is not an issue because the only code that runs only in
# child processes is the RPC server.
for (key, value) in multiprocessing.util._afterfork_registry.items():
if value is pytest_cov.embed.multiprocessing_start:
del multiprocessing.util._afterfork_registry[key]
break
else:
assert False, "missing pytest_cov.embed.multiprocessing_start?"
@pytest.fixture
def swh_storage_backend_config(swh_storage_backend_config):
- """storage should test with its journal writer collaborator on
-
- """
- yield {**swh_storage_backend_config, "journal_writer": {"cls": "memory",}}
+ """storage should test with its journal writer collaborator on"""
+ yield {
+ **swh_storage_backend_config,
+ "journal_writer": {
+ "cls": "memory",
+ },
+ }
@pytest.fixture
def swh_contents(swh_storage: StorageInterface) -> Iterable[BaseContent]:
contents = [BaseContent.from_dict(c) for c in gen_contents(n=20)]
swh_storage.content_add([c for c in contents if c.status != "absent"])
swh_storage.skipped_content_add([c for c in contents if c.status == "absent"])
return contents
@pytest.fixture
def swh_origins(swh_storage: StorageInterface) -> Iterable[Origin]:
origins = [Origin.from_dict(o) for o in gen_origins(n=100)]
swh_storage.origin_add(origins)
return origins
diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_cran.py b/swh/storage/tests/migrate_extrinsic_metadata/test_cran.py
index be4eaf02..7ff8adfe 100644
--- a/swh/storage/tests/migrate_extrinsic_metadata/test_cran.py
+++ b/swh/storage/tests/migrate_extrinsic_metadata/test_cran.py
@@ -1,302 +1,336 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# flake8: noqa
# because of long lines
import copy
import datetime
import json
from unittest.mock import Mock, call
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
RawExtrinsicMetadata,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.storage.migrate_extrinsic_metadata import cran_package_from_url, handle_row
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
SWH_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.REGISTRY,
url="https://softwareheritage.org/",
metadata={},
)
DIRECTORY_ID = b"a" * 20
DIRECTORY_SWHID = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=DIRECTORY_ID
)
def test_cran_package_from_url():
files = [
("https://cran.r-project.org/src/contrib/shapeR_0.1-5.tar.gz", "shapeR"),
("https://cran.r-project.org/src/contrib/hot.deck_1.1.tar.gz", "hot.deck"),
]
for (filename, project) in files:
assert cran_package_from_url(filename) == project
def test_cran():
source_original_artifacts = [
{
"length": 170623,
"filename": "ExtremeRisks_0.0.3.tar.gz",
"checksums": {
"sha1": "f2f19fc0f24b66b5ea9413366c632f3c229f7f3f",
"sha256": "6f232556313019809dde3554149a1399bb1901a366b4965af49dc007d01945c9",
},
}
]
dest_original_artifacts = [
{
"length": 170623,
"filename": "ExtremeRisks_0.0.3.tar.gz",
"checksums": {
"sha1": "f2f19fc0f24b66b5ea9413366c632f3c229f7f3f",
"sha256": "6f232556313019809dde3554149a1399bb1901a366b4965af49dc007d01945c9",
},
"url": "https://cran.r-project.org/src/contrib/ExtremeRisks_0.0.3.tar.gz",
}
]
row = {
"id": b"\x00\x03a\xaa3\x84,\xbd\xea_\xa6\xe7}\xb6\x96\xb97\xeb\xd2i",
"directory": DIRECTORY_ID,
- "date": datetime.datetime(2020, 5, 5, 0, 0, tzinfo=datetime.timezone.utc,),
+ "date": datetime.datetime(
+ 2020,
+ 5,
+ 5,
+ 0,
+ 0,
+ tzinfo=datetime.timezone.utc,
+ ),
"committer_date": datetime.datetime(
- 2020, 5, 5, 0, 0, tzinfo=datetime.timezone.utc,
+ 2020,
+ 5,
+ 5,
+ 0,
+ 0,
+ tzinfo=datetime.timezone.utc,
),
"type": "tar",
"message": b"0.0.3",
"metadata": {
"extrinsic": {
"raw": {
"url": "https://cran.r-project.org/src/contrib/ExtremeRisks_0.0.3.tar.gz",
"version": "0.0.3",
},
"when": "2020-05-07T15:27:38.652281+00:00",
"provider": "https://cran.r-project.org/package=ExtremeRisks",
},
"intrinsic": {
"raw": {
"URL": "mypage.unibocconi.it/simonepadoan/",
"Date": "2020-05-05",
"Title": "Extreme Risk Measures",
"Author": "Simone Padoan [cre, aut],\n Gilles Stupfler [aut]",
# ...
"Date/Publication": "2020-05-07 10:20:02 UTC",
},
"tool": "DESCRIPTION",
},
"original_artifact": source_original_artifacts,
},
}
origin_url = "https://cran.r-project.org/package=ExtremeRisks"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(row, storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 5, 7, 15, 27, 38, 652281, tzinfo=datetime.timezone.utc,
+ 2020,
+ 5,
+ 7,
+ 15,
+ 27,
+ 38,
+ 652281,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:000361aa33842cbdea5fa6e77db696b937ebd269"
),
),
]
),
]
def test_cran_without_revision_date():
"""Tests a CRAN revision with a date in the metadata but not as revision date"""
source_original_artifacts = [
{
"length": 8018,
"filename": "gofgamma_1.0.tar.gz",
"checksums": {
"sha1": "58f2993140f9e9e1a136554f0af0174a252f2c7b",
"sha256": "55408f004642b5043bb01de831a7e7a0b9f24a30cb0151e70c2d37abdc508d03",
},
}
]
dest_original_artifacts = [
{
"length": 8018,
"filename": "gofgamma_1.0.tar.gz",
"checksums": {
"sha1": "58f2993140f9e9e1a136554f0af0174a252f2c7b",
"sha256": "55408f004642b5043bb01de831a7e7a0b9f24a30cb0151e70c2d37abdc508d03",
},
"url": "https://cran.r-project.org/src/contrib/gofgamma_1.0.tar.gz",
}
]
row = {
"id": b'\x00\x00\xd4\xef^\x16a"\xae\xe6\x86*\xd3\x8a\x18\xceS\x86\xcc>',
"directory": DIRECTORY_ID,
"date": None,
"committer_date": None,
"type": "tar",
"message": b"1.0",
"metadata": {
"extrinsic": {
"raw": {
"url": "https://cran.r-project.org/src/contrib/gofgamma_1.0.tar.gz",
"version": "1.0",
},
"when": "2020-04-30T11:01:57.832481+00:00",
"provider": "https://cran.r-project.org/package=gofgamma",
},
"intrinsic": {
"raw": {
"Type": "Package",
"Title": "Goodness-of-Fit Tests for the Gamma Distribution",
"Author": "Lucas Butsch [aut],\n Bruno Ebner [aut, cre],\n Steffen Betsch [aut]",
# ...
},
"tool": "DESCRIPTION",
},
"original_artifact": source_original_artifacts,
},
}
origin_url = "https://cran.r-project.org/package=gofgamma"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 4, 30, 11, 1, 57, 832481, tzinfo=datetime.timezone.utc,
+ 2020,
+ 4,
+ 30,
+ 11,
+ 1,
+ 57,
+ 832481,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0000d4ef5e166122aee6862ad38a18ce5386cc3e"
),
),
]
),
]
def test_cran_with_new_original_artifacts_format():
original_artifacts = [
{
"url": "https://cran.r-project.org/src/contrib/r2mlm_0.1.0.tar.gz",
"length": 346563,
"filename": "r2mlm_0.1.0.tar.gz",
"checksums": {
"sha1": "25c06b4af523c35a7813b58dd0db414e79848501",
"sha256": "c887fe6c4f78c94b2279759052e12d639cf80225b444c1f67931c6aa6f0faf23",
},
}
]
row = {
"id": b'."7\x82\xeeK\xa1R\xe4\xc8\x86\xf7\x97\x97bA\xc3\x9a\x9a\xab',
"directory": DIRECTORY_ID,
"date": None,
"committer_date": None,
"type": "tar",
"message": b"0.1.0",
"metadata": {
"extrinsic": {
"raw": {
"url": "https://cran.r-project.org/src/contrib/r2mlm_0.1.0.tar.gz"
},
"when": "2020-09-25T14:04:20.926667+00:00",
"provider": "https://cran.r-project.org/package=r2mlm",
},
"intrinsic": {
"raw": {
"URL": "https://github.com/mkshaw/r2mlm",
"Type": "Package",
"Title": "R-Squared Measures for Multilevel Models",
"Author": "Mairead Shaw [aut, cre],\n Jason Rights [aut],\n Sonya Sterba [aut],\n Jessica Flake [aut]",
# ...
},
"tool": "DESCRIPTION",
},
"original_artifact": original_artifacts,
},
}
origin_url = "https://cran.r-project.org/package=r2mlm"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(row, storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 9, 25, 14, 4, 20, 926667, tzinfo=datetime.timezone.utc,
+ 2020,
+ 9,
+ 25,
+ 14,
+ 4,
+ 20,
+ 926667,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:2e223782ee4ba152e4c886f797976241c39a9aab"
),
),
]
),
]
diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py b/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py
index 33a11d54..418fd111 100644
--- a/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py
+++ b/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py
@@ -1,568 +1,615 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# flake8: noqa
# because of long lines
import copy
import datetime
import json
from unittest.mock import Mock, call
from unittest.mock import patch as _patch
import attr
import pytest
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
OriginVisit,
OriginVisitStatus,
Person,
RawExtrinsicMetadata,
Revision,
RevisionType,
Snapshot,
SnapshotBranch,
TargetType,
Timestamp,
TimestampWithTimezone,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.storage import get_storage
from swh.storage.interface import ListOrder, PagedResult
from swh.storage.migrate_extrinsic_metadata import debian_origins_from_row, handle_row
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
SWH_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.REGISTRY,
url="https://softwareheritage.org/",
metadata={},
)
DIRECTORY_ID = b"a" * 20
DIRECTORY_SWHID = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=DIRECTORY_ID
)
def now():
return datetime.datetime.now(tz=datetime.timezone.utc)
def patch(function_name, *args, **kwargs):
# It's a long name, this function spares some line breaks in 'with' statements
return _patch(
"swh.storage.migrate_extrinsic_metadata." + function_name, *args, **kwargs
)
def test_debian_origins_from_row():
"""Tests debian_origins_from_row on a real example (with some parts
omitted, for conciseness)."""
origin_url = "deb://Debian/packages/kalgebra"
visit = OriginVisit(
origin=origin_url,
date=datetime.datetime(
- 2020, 1, 27, 19, 32, 3, 925498, tzinfo=datetime.timezone.utc,
+ 2020,
+ 1,
+ 27,
+ 19,
+ 32,
+ 3,
+ 925498,
+ tzinfo=datetime.timezone.utc,
),
type="deb",
visit=280,
)
storage = get_storage("memory")
storage.origin_add(
[
Origin(url=origin_url),
Origin(url="http://snapshot.debian.org/package/kalgebra/"),
]
)
storage.origin_visit_add([visit])
storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin_url,
visit=280,
date=datetime.datetime(
2020, 1, 27, 19, 32, 3, 925498, tzinfo=datetime.timezone.utc
),
status="full",
snapshot=b"\xafD\x15\x98){\xd4$\xdeI\x1f\xbe\x95lh`x\x14\xce\xc4",
metadata=None,
)
],
)
snapshot = Snapshot(
id=b"\xafD\x15\x98){\xd4$\xdeI\x1f\xbe\x95lh`x\x14\xce\xc4",
branches={
# ...
b"releases/unstable/main/4:19.12.1-1": SnapshotBranch(
target=b"\x00\x00\x03l1\x1e\xf3:(\x1b\x05h\x8fn\xad\xcf\xc0\x94:\xee",
target_type=TargetType.REVISION,
),
},
)
revision_row = {
"id": b"\x00\x00\x03l1\x1e\xf3:(\x1b\x05h\x8fn\xad\xcf\xc0\x94:\xee",
"directory": DIRECTORY_ID,
"metadata": {
# ...
"original_artifact": [
{
"filename": "kalgebra_19.12.1-1.dsc",
# ...
},
]
},
}
storage.snapshot_add([snapshot])
assert debian_origins_from_row(revision_row, storage) == [origin_url]
def test_debian_origins_from_row__no_result():
"""Tests debian_origins_from_row when there's no origin, visit, status,
snapshot, branch, or matching branch.
"""
storage = get_storage("memory")
origin_url = "deb://Debian/packages/kalgebra"
snapshot_id = b"42424242424242424242"
revision_id = b"21212121212121212121"
storage.origin_add([Origin(url=origin_url)])
revision_row = {
"id": b"\x00\x00\x03l1\x1e\xf3:(\x1b\x05h\x8fn\xad\xcf\xc0\x94:\xee",
"directory": DIRECTORY_ID,
- "metadata": {"original_artifact": [{"filename": "kalgebra_19.12.1-1.dsc",},]},
+ "metadata": {
+ "original_artifact": [
+ {
+ "filename": "kalgebra_19.12.1-1.dsc",
+ },
+ ]
+ },
}
# no visit
assert debian_origins_from_row(revision_row, storage) == []
storage.origin_visit_add(
- [OriginVisit(origin=origin_url, date=now(), type="deb", visit=280,)]
+ [
+ OriginVisit(
+ origin=origin_url,
+ date=now(),
+ type="deb",
+ visit=280,
+ )
+ ]
)
# no status
assert debian_origins_from_row(revision_row, storage) == []
status = OriginVisitStatus(
origin=origin_url,
visit=280,
date=now(),
status="full",
snapshot=None,
metadata=None,
)
storage.origin_visit_status_add([status])
# no snapshot
assert debian_origins_from_row(revision_row, storage) == []
status = attr.evolve(status, snapshot=snapshot_id, date=now())
storage.origin_visit_status_add([status])
storage_before_snapshot = copy.deepcopy(storage)
snapshot = Snapshot(id=snapshot_id, branches={})
storage.snapshot_add([snapshot])
# no branch
assert debian_origins_from_row(revision_row, storage) == []
# "remove" the snapshot, so we can add a new one with the same id
storage = copy.deepcopy(storage_before_snapshot)
- snapshot = attr.evolve(snapshot, branches={b"foo": None,},)
+ snapshot = attr.evolve(
+ snapshot,
+ branches={
+ b"foo": None,
+ },
+ )
storage.snapshot_add([snapshot])
# dangling branch
assert debian_origins_from_row(revision_row, storage) == []
# "remove" the snapshot again
storage = copy.deepcopy(storage_before_snapshot)
snapshot = attr.evolve(
snapshot,
branches={
- b"foo": SnapshotBranch(target_type=TargetType.REVISION, target=revision_id,)
+ b"foo": SnapshotBranch(
+ target_type=TargetType.REVISION,
+ target=revision_id,
+ )
},
)
storage.snapshot_add([snapshot])
# branch points to unknown revision
assert debian_origins_from_row(revision_row, storage) == []
revision = Revision(
id=revision_id,
message=b"foo",
author=Person.from_fullname(b"foo"),
committer=Person.from_fullname(b"foo"),
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1580076204, microseconds=0),
offset_bytes=b"+0100",
),
committer_date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1580076204, microseconds=0),
offset_bytes=b"+0100",
),
type=RevisionType.DSC,
directory=b"\xd5\x9a\x1f\x9c\x80\x9d\x8c}19P\xf6\xc8\xa2\x0f^%H\xcd\xdb",
synthetic=True,
metadata=None,
parents=(),
extra_headers=(),
)
storage.revision_add([revision])
# no matching branch
assert debian_origins_from_row(revision_row, storage) == []
def test_debian_origins_from_row__check_revisions():
"""Tests debian_origins_from_row errors when the revision at the head
of a branch is a DSC and has no parents
"""
storage = get_storage("memory")
origin_url = "deb://Debian/packages/kalgebra"
revision_id = b"21" * 10
storage.origin_add([Origin(url=origin_url)])
revision_row = {
"id": b"\x00\x00\x03l1\x1e\xf3:(\x1b\x05h\x8fn\xad\xcf\xc0\x94:\xee",
"directory": DIRECTORY_ID,
- "metadata": {"original_artifact": [{"filename": "kalgebra_19.12.1-1.dsc",},]},
+ "metadata": {
+ "original_artifact": [
+ {
+ "filename": "kalgebra_19.12.1-1.dsc",
+ },
+ ]
+ },
}
storage.origin_visit_add(
[
OriginVisit(
origin=origin_url,
date=datetime.datetime.now(tz=datetime.timezone.utc),
type="deb",
visit=280,
)
]
)
storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin_url,
visit=280,
date=datetime.datetime.now(tz=datetime.timezone.utc),
status="full",
snapshot=b"42" * 10,
metadata=None,
)
]
)
storage.snapshot_add(
[
Snapshot(
id=b"42" * 10,
branches={
b"foo": SnapshotBranch(
target_type=TargetType.REVISION, target=revision_id
)
},
)
]
)
storage_before_revision = copy.deepcopy(storage)
revision = Revision(
id=revision_id,
message=b"foo",
author=Person.from_fullname(b"foo"),
committer=Person.from_fullname(b"foo"),
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1580076204, microseconds=0),
offset_bytes=b"+0100",
),
committer_date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1580076204, microseconds=0),
offset_bytes=b"+0100",
),
type=RevisionType.DSC,
directory=b"\xd5\x9a\x1f\x9c\x80\x9d\x8c}19P\xf6\xc8\xa2\x0f^%H\xcd\xdb",
synthetic=True,
metadata=None,
parents=(b"parent " * 2,),
extra_headers=(),
)
storage.revision_add([revision])
with pytest.raises(AssertionError, match="revision with parents"):
debian_origins_from_row(revision_row, storage)
def test_debian_with_extrinsic():
dest_original_artifacts = [
{
"length": 2936,
"filename": "kalgebra_19.12.1-1.dsc",
"checksums": {
"sha1": "f869e9f1155b1ee6d28ae3b40060570152a358cd",
"sha256": "75f77150aefdaa4bcf8bc5b1e9b8b90b5cb1651b76a068c5e58e5b83658d5d11",
},
"url": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1-1.dsc",
},
{
"length": 1156408,
"filename": "kalgebra_19.12.1.orig.tar.xz",
"checksums": {
"sha1": "e496032962212983a5359aebadfe13c4026fd45c",
"sha256": "49d623186800eb8f6fbb91eb43fb14dff78e112624c9cda6b331d494d610b16a",
},
"url": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1.orig.tar.xz",
},
{
"length": 10044,
"filename": "kalgebra_19.12.1-1.debian.tar.xz",
"checksums": {
"sha1": "b518bfc2ac708b40577c595bd539faa8b84572db",
"sha256": "1a30acd2699c3769da302f7a0c63a7d7b060f80925b38c8c43ce3bec92744d67",
},
"url": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1-1.debian.tar.xz",
},
{
"length": 488,
"filename": "kalgebra_19.12.1.orig.tar.xz.asc",
"checksums": {
"sha1": "ff53a5c21c1aef2b9caa38a02fa3488f43df4c20",
"sha256": "a37e0b95bb1f16b19b0587bc5d3b99ba63a195d7f6335c4a359122ad96d682dd",
},
"url": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1.orig.tar.xz.asc",
},
]
source_original_artifacts = [
{k: v for (k, v) in d.items() if k != "url"} for d in dest_original_artifacts
]
row = {
"id": b"\x00\x00\x03l1\x1e\xf3:(\x1b\x05h\x8fn\xad\xcf\xc0\x94:\xee",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
- 2020, 1, 26, 22, 3, 24, tzinfo=datetime.timezone.utc,
+ 2020,
+ 1,
+ 26,
+ 22,
+ 3,
+ 24,
+ tzinfo=datetime.timezone.utc,
),
"date_offset": 60,
"type": "dsc",
"message": b"Synthetic revision for Debian source package kalgebra version 4:19.12.1-1",
"metadata": {
"extrinsic": {
"raw": {
"id": 2718802,
"name": "kalgebra",
"files": {
"kalgebra_19.12.1-1.dsc": {
"uri": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1-1.dsc",
"name": "kalgebra_19.12.1-1.dsc",
"size": 2936,
"md5sum": "fd28f604d4cc31a0a305543230f1622a",
"sha256": "75f77150aefdaa4bcf8bc5b1e9b8b90b5cb1651b76a068c5e58e5b83658d5d11",
},
"kalgebra_19.12.1.orig.tar.xz": {
"uri": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1.orig.tar.xz",
"name": "kalgebra_19.12.1.orig.tar.xz",
"size": 1156408,
"md5sum": "34e09ed152da762d53101ea33634712b",
"sha256": "49d623186800eb8f6fbb91eb43fb14dff78e112624c9cda6b331d494d610b16a",
},
"kalgebra_19.12.1-1.debian.tar.xz": {
"uri": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1-1.debian.tar.xz",
"name": "kalgebra_19.12.1-1.debian.tar.xz",
"size": 10044,
"md5sum": "4f639f36143898d97d044f273f038e58",
"sha256": "1a30acd2699c3769da302f7a0c63a7d7b060f80925b38c8c43ce3bec92744d67",
},
"kalgebra_19.12.1.orig.tar.xz.asc": {
"uri": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1.orig.tar.xz.asc",
"name": "kalgebra_19.12.1.orig.tar.xz.asc",
"size": 488,
"md5sum": "3c29291e4e6f0c294de80feb8e9fce4c",
"sha256": "a37e0b95bb1f16b19b0587bc5d3b99ba63a195d7f6335c4a359122ad96d682dd",
},
},
"version": "4:19.12.1-1",
"revision_id": None,
},
"when": "2020-01-27T19:32:03.925498+00:00",
"provider": "http://deb.debian.org/debian//pool/main/k/kalgebra/kalgebra_19.12.1-1.dsc",
},
"intrinsic": {
"raw": {
"name": "kalgebra",
"version": "4:19.12.1-1",
# ...
},
"tool": "dsc",
},
"original_artifact": source_original_artifacts,
},
}
origin_url = "deb://Debian/packages/kalgebra"
storage = Mock()
deposit_cur = None
with patch("debian_origins_from_row", return_value=[origin_url]):
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 1, 26, 22, 3, 24, tzinfo=datetime.timezone.utc,
+ 2020,
+ 1,
+ 26,
+ 22,
+ 3,
+ 24,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0000036c311ef33a281b05688f6eadcfc0943aee"
),
),
]
),
]
def test_debian_without_extrinsic():
source_original_artifacts = [
{
"name": "pymongo_1.10-1.dsc",
"sha1": "81877c1ae4406c2519b9cc9c4557cf6b0775a241",
"length": 99,
"sha256": "40269a73f38ee4c2f9cc021f1d5d091cc59ca6e778c339684b7be030e29e282f",
"sha1_git": "0ac7bdb8e4d10926c5d3e51baa2be7bb29a3966b",
},
{
"name": "pymongo_1.10.orig.tar.gz",
"sha1": "4f4c97641b86ac8f21396281bd1a7369236693c3",
"length": 99,
"sha256": "0b6bffb310782ffaeb3916c75790742ec5830c63a758fc711cd1f557eb5a4b5f",
"sha1_git": "19ef0adda8868520d1ef9d4164b3ace4df1d62ad",
},
{
"name": "pymongo_1.10-1.debian.tar.gz",
"sha1": "fbf378296613c8d55e043aec98896b3e50a94971",
"length": 99,
"sha256": "3970cc70fe3ba6499a9c56ba4b4c6c3782f56433d0d17d72b7a0e2ceae31b513",
"sha1_git": "2eea9904806050a8fda95edd5d4fa60d29c1fdec",
},
]
dest_original_artifacts = [
{
"length": 99,
"filename": "pymongo_1.10-1.dsc",
"checksums": {
"sha1": "81877c1ae4406c2519b9cc9c4557cf6b0775a241",
"sha256": "40269a73f38ee4c2f9cc021f1d5d091cc59ca6e778c339684b7be030e29e282f",
"sha1_git": "0ac7bdb8e4d10926c5d3e51baa2be7bb29a3966b",
},
},
{
"length": 99,
"filename": "pymongo_1.10.orig.tar.gz",
"checksums": {
"sha1": "4f4c97641b86ac8f21396281bd1a7369236693c3",
"sha256": "0b6bffb310782ffaeb3916c75790742ec5830c63a758fc711cd1f557eb5a4b5f",
"sha1_git": "19ef0adda8868520d1ef9d4164b3ace4df1d62ad",
},
},
{
"length": 99,
"filename": "pymongo_1.10-1.debian.tar.gz",
"checksums": {
"sha1": "fbf378296613c8d55e043aec98896b3e50a94971",
"sha256": "3970cc70fe3ba6499a9c56ba4b4c6c3782f56433d0d17d72b7a0e2ceae31b513",
"sha1_git": "2eea9904806050a8fda95edd5d4fa60d29c1fdec",
},
},
]
row = {
"id": b"\x00\x00\x01\xc2\x8c\x8f\xca\x01\xb9\x04\xde\x92\xa2d\n\x86l\xe0<\xb7",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2011, 3, 31, 20, 17, 41, tzinfo=datetime.timezone.utc
),
"date_offset": 0,
"type": "dsc",
"message": b"Synthetic revision for Debian source package pymongo version 1.10-1",
"metadata": {
"package_info": {
"name": "pymongo",
"version": "1.10-1",
"changelog": {
# ...
},
"maintainers": [
{"name": "Federico Ceratto", "email": "federico.ceratto@gmail.com"},
{"name": "Janos Guljas", "email": "janos@resenje.org"},
],
"pgp_signature": {
"date": "2011-03-31T21:02:44+00:00",
"keyid": "2BABC6254E66E7B8450AC3E1E6AA90171392B174",
"person": {"name": "David Paleino", "email": "d.paleino@gmail.com"},
},
"lister_metadata": {"id": 244296, "lister": "snapshot.debian.org"},
},
"original_artifact": source_original_artifacts,
},
}
storage = Mock()
origin_url = "http://snapshot.debian.org/package/pymongo"
deposit_cur = None
with patch("debian_origins_from_row", return_value=[origin_url]):
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2011, 3, 31, 20, 17, 41, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:000001c28c8fca01b904de92a2640a866ce03cb7"
),
),
]
)
]
diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py b/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py
index 2e150d0d..d88baf76 100644
--- a/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py
+++ b/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py
@@ -1,1340 +1,1361 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# flake8: noqa
# because of long lines
import copy
import datetime
import json
from unittest.mock import MagicMock, Mock, call
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
RawExtrinsicMetadata,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.storage.migrate_extrinsic_metadata import (
DEPOSIT_COLS,
cran_package_from_url,
handle_row,
)
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
SWH_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.REGISTRY,
url="https://softwareheritage.org/",
metadata={},
)
SWH_DEPOSIT_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.DEPOSIT_CLIENT,
url="https://www.softwareheritage.org",
metadata={},
)
HAL_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.DEPOSIT_CLIENT,
url="https://hal.archives-ouvertes.fr/",
metadata={},
)
INTEL_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.DEPOSIT_CLIENT,
url="https://software.intel.com",
metadata={},
)
DIRECTORY_ID = b"a" * 20
DIRECTORY_SWHID = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=DIRECTORY_ID
)
def get_mock_deposit_cur(row_dicts):
rows = [tuple(d[key] for key in DEPOSIT_COLS) for d in row_dicts]
deposit_cur = MagicMock()
deposit_cur.__iter__.side_effect = [iter(rows)]
return deposit_cur
def test_deposit_1():
"""Has a provider and xmlns, and the metadata is in the revision twice
(at the root of the metadata dict, and in
metadata->extrinsic->raw->origin_metadata)"""
extrinsic_metadata = {
"title": "Je suis GPL",
"@xmlns": "http://www.w3.org/2005/Atom",
"client": "swh",
"codemeta:url": "https://forge.softwareheritage.org/source/jesuisgpl/",
"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",
"codemeta:author": {
"codemeta:name": "Stefano Zacchiroli",
"codemeta:jobTitle": "Maintainer",
},
"codemeta:license": {
"codemeta:url": "https://spdx.org/licenses/GPL-3.0-or-later.html",
"codemeta:name": "GNU General Public License v3.0 or later",
},
# ...
}
original_artifacts = [
{
"length": 80880,
"filename": "archive.zip",
"checksums": {
"sha1": "bad32a47a359e0e16ebdca2ad2dc6a771dac8f71",
"sha256": "182b7ee3b7b5b550e83d3bcfed029bb2f625ee760ebfe9557d5fd072bd4e22e4",
},
}
]
row = {
"id": b"\x02#\x10\xdf\x16\xfd\x9eMO\x81\xfe6\xa1B\xe8-\xb9w\xc0\x1d",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2018, 1, 5, 0, 0, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2018, 1, 5, 0, 0, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"swh: Deposit 467 in collection swh",
"metadata": {
"client": "swh",
"extrinsic": {
"raw": {
"origin": {
"url": "https://www.softwareheritage.org/check-deposit-2020-03-11T11:07:18.424476",
"type": "deposit",
},
"branch_name": "master",
"origin_metadata": {
"tool": {
"name": "swh-deposit",
"version": "0.0.1",
"configuration": {"sword_version": 2},
},
"metadata": extrinsic_metadata,
},
},
"when": "2020-03-11T11:11:36.336283+00:00",
"provider": "https://deposit.softwareheritage.org/1/private/467/meta/",
},
"original_artifact": original_artifacts,
**extrinsic_metadata,
},
}
origin_url = (
"https://www.softwareheritage.org/check-deposit-2020-03-11T11:07:18.424476"
)
swhid = (
f"swh:1:dir:ef04a768181417fbc5eef4243e2507915f24deea"
f";origin={origin_url}"
f";visit=swh:1:snp:14433c19dbb03ad57c86b58b53a800d6a0e32dd3"
f";anchor=swh:1:rev:022310df16fd9e4d4f81fe36a142e82db977c01d"
f";path=/"
)
deposit_rows = [
{
"deposit.id": 467,
"deposit.external_id": "check-deposit-2020-03-11T11:07:18.424476",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2020, 3, 11, 11, 7, 18, 688410, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://www.softwareheritage.org",
"deposit_collection.name": "swh",
"auth_user.username": "swh",
},
{
"deposit.id": 467,
"deposit.external_id": "check-deposit-2020-03-11T11:07:18.424476",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2020, 3, 11, 11, 7, 18, 669428, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://www.softwareheritage.org",
"deposit_collection.name": "swh",
"auth_user.username": "swh",
},
]
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 3, 11, 11, 7, 18, 688410, tzinfo=datetime.timezone.utc
),
authority=SWH_DEPOSIT_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:022310df16fd9e4d4f81fe36a142e82db977c01d"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 3, 11, 11, 11, 36, 336283, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:022310df16fd9e4d4f81fe36a142e82db977c01d"
),
),
]
),
]
def test_deposit_2_without_xmlns():
"""Has a provider, no xmlns, and the metadata is only in
metadata->extrinsic->raw->origin_metadata)"""
extrinsic_metadata = {
"{http://www.w3.org/2005/Atom}id": "hal-01243573",
"{http://www.w3.org/2005/Atom}author": {
"{http://www.w3.org/2005/Atom}name": "HAL",
"{http://www.w3.org/2005/Atom}email": "hal@ccsd.cnrs.fr",
},
"{http://www.w3.org/2005/Atom}client": "hal",
"{http://www.w3.org/2005/Atom}external_identifier": "hal-01243573",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}url": "https://hal-test.archives-ouvertes.fr/hal-01243573",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}name": "The assignment problem",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author": {
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}name": "Morane Gruenpeter"
},
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}version": 1,
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}identifier": "10.5281/zenodo.438684",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}dateCreated": "2017-11-16T14:54:23+01:00",
}
original_artifacts = [
{
"length": 208357,
"filename": "archive.zip",
"checksums": {
"sha1": "fa0aec08e8a44ea144dba7ce366c8b5d66c14453",
"sha256": "f53c05fe947e88ce83751a93bd522b1f88478ea2e7b984c07fc7a7c68128bf87",
},
}
]
row = {
"id": b"\x01\x16\xca\xb7\x19d\xd5\x9c\x85p\xb4\xc5r\x9b(\xbd\xd6<\x9bF",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2018, 1, 17, 12, 54, 0, 723882, tzinfo=datetime.timezone.utc
),
"committer_date": datetime.datetime(
2018, 1, 17, 12, 54, 0, 723882, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"hal: Deposit 82 in collection hal",
"metadata": {
"extrinsic": {
"raw": {
"origin": {
"url": "https://hal.archives-ouvertes.fr/hal-01243573",
"type": "deposit",
},
"origin_metadata": {
"tool": {
"name": "swh-deposit",
"version": "0.0.1",
"configuration": {"sword_version": 2},
},
"metadata": extrinsic_metadata,
"provider": {
"metadata": {},
"provider_url": "https://hal.archives-ouvertes.fr/",
"provider_name": "hal",
"provider_type": "deposit_client",
},
},
},
"when": "2020-05-15T14:27:21.462270+00:00",
"provider": "https://deposit.softwareheritage.org/1/private/82/meta/",
},
"original_artifact": original_artifacts,
},
}
swhid = (
"swh:1:dir:e04b2a7b8a8838da0693e9fd992a10d6fd211b50"
";origin=https://hal.archives-ouvertes.fr/hal-01243573"
";visit=swh:1:snp:abc9ae594245a740235b6c039f044352a5f723ec"
";anchor=swh:1:rev:0116cab71964d59c8570b4c5729b28bdd63c9b46"
";path=/"
)
deposit_rows = [
{
"deposit.id": 82,
"deposit.external_id": "hal-01243573",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2018, 1, 17, 12, 54, 1, 533972, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
{
"deposit.id": 82,
"deposit.external_id": "hal-01243573",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2018, 1, 17, 12, 54, 0, 413748, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
]
origin_url = "https://hal.archives-ouvertes.fr/hal-01243573"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2018, 1, 17, 12, 54, 0, 413748, tzinfo=datetime.timezone.utc
),
authority=HAL_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json-with-expanded-namespaces",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0116cab71964d59c8570b4c5729b28bdd63c9b46"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 5, 15, 14, 27, 21, 462270, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0116cab71964d59c8570b4c5729b28bdd63c9b46"
),
),
]
),
]
def test_deposit_2_with_xmlns():
"""Has a provider, xmlns, and the metadata is only in
metadata->extrinsic->raw->origin_metadata)"""
extrinsic_metadata = {
"title": "Je suis GPL",
"@xmlns": "http://www.w3.org/2005/Atom",
"client": "swh",
"codemeta:url": "https://forge.softwareheritage.org/source/jesuisgpl/",
"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",
"codemeta:author": {
"codemeta:name": "Stefano Zacchiroli",
"codemeta:jobTitle": "Maintainer",
},
"codemeta:license": {
"codemeta:url": "https://spdx.org/licenses/GPL-3.0-or-later.html",
"codemeta:name": "GNU General Public License v3.0 or later",
},
"external_identifier": "je-suis-gpl",
"codemeta:dateCreated": "2018-01-05",
}
original_artifacts = [
{
"length": 80880,
"filename": "archive.zip",
"checksums": {
"sha1": "bad32a47a359e0e16ebdca2ad2dc6a771dac8f71",
"sha256": "182b7ee3b7b5b550e83d3bcfed029bb2f625ee760ebfe9557d5fd072bd4e22e4",
},
}
]
row = {
"id": b'\x01"\x96nP\x93\x17\xae\xcejA\xd0\xf0\x88\xdas<\xc0\x9d\x0f',
"directory": DIRECTORY_ID,
"date": datetime.datetime(2018, 1, 5, 0, 0, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2018, 1, 5, 0, 0, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"swh: Deposit 687 in collection swh",
"metadata": {
"extrinsic": {
"raw": {
"origin": {
"url": "https://www.softwareheritage.org/check-deposit-2020-06-26T13:50:07.564420",
"type": "deposit",
},
"origin_metadata": {
"tool": {
"name": "swh-deposit",
"version": "0.0.1",
"configuration": {"sword_version": 2},
},
"metadata": extrinsic_metadata,
"provider": {
"metadata": {},
"provider_url": "https://www.softwareheritage.org",
"provider_name": "swh",
"provider_type": "deposit_client",
},
},
},
"when": "2020-06-26T13:50:22.640625+00:00",
"provider": "https://deposit.softwareheritage.org/1/private/687/meta/",
},
"original_artifact": original_artifacts,
},
}
swhid = (
"swh:1:dir:ef04a768181417fbc5eef4243e2507915f24deea"
";origin=https://www.softwareheritage.org/check-deposit-2020-06-26T13:50:07.564420"
";visit=swh:1:snp:8fd469e280fb0724175c64906627f619143d5bdb"
";anchor=swh:1:rev:0122966e509317aece6a41d0f088da733cc09d0f"
";path=/"
)
deposit_rows = [
{
"deposit.id": 687,
"deposit.external_id": "check-deposit-2020-06-26T13:50:07.564420",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2020, 6, 26, 13, 50, 8, 216113, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://www.softwareheritage.org",
"deposit_collection.name": "swh",
"auth_user.username": "swh",
},
{
"deposit.id": 687,
"deposit.external_id": "check-deposit-2020-06-26T13:50:07.564420",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2020, 6, 26, 13, 50, 8, 150498, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://www.softwareheritage.org",
"deposit_collection.name": "swh",
"auth_user.username": "swh",
},
]
origin_url = (
"https://www.softwareheritage.org/check-deposit-2020-06-26T13:50:07.564420"
)
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 6, 26, 13, 50, 8, 216113, tzinfo=datetime.timezone.utc
),
authority=SWH_DEPOSIT_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0122966e509317aece6a41d0f088da733cc09d0f"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 6, 26, 13, 50, 22, 640625, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0122966e509317aece6a41d0f088da733cc09d0f"
),
),
]
),
]
def test_deposit_2_with_json_in_json_and_no_xmlns():
"""New formats introduced in https://forge.softwareheritage.org/D4105 ,
where the raw metadata is itself JSONed inside the metadata JSON tree
and https://forge.softwareheritage.org/D4065 where the @xmlns declarations
are stripped before being sent to the deposit DB"""
extrinsic_metadata = {
"id": "hal-02960679",
"author": {"name": "HAL", "email": "hal@ccsd.cnrs.fr"},
"client": "hal",
"codemeta:url": "https://hal.archives-ouvertes.fr/hal-02960679",
"codemeta:name": "Compressive Spectral Clustering Toolbox",
"codemeta:author": [
{"codemeta:name": "Nicolas Tremblay", "codemeta:affiliation": "PANAMA"},
{"codemeta:name": "Gilles Puy", "codemeta:affiliation": "PANAMA"},
{"codemeta:name": "R{\\'e}mi Gribonval", "codemeta:affiliation": "PANAMA"},
{"codemeta:name": "Pierre Vandergheynst"},
],
# ...
}
original_artifacts = [
{
"url": "https://deposit.softwareheritage.org/1/private/1037/raw/",
"length": 4546913,
"filename": "archive.zip",
"checksums": {
"sha1": "01a0069c626a383de9a17ace40ecfd588e5c4f26",
"sha256": "c780a6de91286c70ceecc69fe0c6d201d3fe944aa89e193f3a89ae85dc25c3b1",
},
}
]
row = {
"id": b"J\x9dc{\xa5\x07\xa2\xb93e%\x04(\xe6\xe3\xf0!\xf1\x94\xd0",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2016, 1, 29, 0, 0, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2020, 10, 8, 0, 0, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"hal: Deposit 1037 in collection hal",
"metadata": {
"extrinsic": {
"raw": {
"origin": {
"url": "https://hal.archives-ouvertes.fr/hal-02960679",
"type": "deposit",
},
"origin_metadata": {
"tool": {
"name": "swh-deposit",
"version": "0.2.0",
"configuration": {"sword_version": "2"},
},
"metadata": json.dumps(extrinsic_metadata),
"provider": {
"metadata": {},
"provider_url": "https://hal.archives-ouvertes.fr/",
"provider_name": "hal",
"provider_type": "deposit_client",
},
},
},
"when": "2020-10-09T13:38:25.888646+00:00",
"provider": "https://deposit.softwareheritage.org/1/private/1037/meta/",
},
"original_artifact": original_artifacts,
},
}
swhid = (
"swh:1:dir:8bfdf74037ae1c51335995891c6226e0f85e46e2"
";origin=https://hal.archives-ouvertes.fr/hal-02960679"
";visit=swh:1:snp:bc4a2ddf84dd0cc13d74e1970a1471c2574ed6aa"
";anchor=swh:1:rev:4a9d637ba507a2b93365250428e6e3f021f194d0"
";path=/"
)
deposit_rows = [
{
"deposit.id": 1037,
"deposit.external_id": "hal-02960679",
"deposit.swhid_context": swhid,
"deposit.status": "done",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
- 2020, 10, 9, 13, 38, 8, 269611, tzinfo=datetime.timezone.utc,
+ 2020,
+ 10,
+ 9,
+ 13,
+ 38,
+ 8,
+ 269611,
+ tzinfo=datetime.timezone.utc,
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
{
"deposit.id": 1037,
"deposit.external_id": "hal-02960679",
"deposit.swhid_context": swhid,
"deposit.status": "done",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
- 2020, 10, 9, 13, 38, 7, 394544, tzinfo=datetime.timezone.utc,
+ 2020,
+ 10,
+ 9,
+ 13,
+ 38,
+ 7,
+ 394544,
+ tzinfo=datetime.timezone.utc,
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
]
origin_url = "https://hal.archives-ouvertes.fr/hal-02960679"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 10, 9, 13, 38, 7, 394544, tzinfo=datetime.timezone.utc
),
authority=HAL_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:4a9d637ba507a2b93365250428e6e3f021f194d0"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 10, 9, 13, 38, 25, 888646, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:4a9d637ba507a2b93365250428e6e3f021f194d0"
),
),
]
),
]
def test_deposit_3_and_wrong_external_id_in_metadata():
extrinsic_metadata = {
"title": "VTune Perf tool",
"@xmlns": "http://www.w3.org/2005/Atom",
"client": "swh",
"codemeta:url": "https://software.intel.com/en-us/vtune",
"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",
"codemeta:author": {
"codemeta:name": "VTune developer",
"codemeta:jobTitle": "Software Engineer",
},
"external_identifier": "vtune-perf-tool",
"codemeta:dateCreated": "2019-05-14",
"codemeta:description": "Modified version of Linux Perf tool which is used by Intel VTune Amplifier",
}
source_original_artifacts = [
{
"name": "archive.zip",
"sha1": "07251dbb1d904d143fd7da9935701f17670d4d9b",
"length": 4350528,
"sha256": "1f7d111ac79e468002f3edf4b7b2487538d41f6bea362d49b2eb08a537efafb6",
"sha1_git": "e2d894efcaad4ff36f09eda3b3c0096416b03429",
"blake2s256": "e2c08b82efbc361fbb2d28aa8352668cd71217f165f63de16b61ed61ace7509d",
"archive_type": "zip",
}
]
dest_original_artifacts = [
{
"length": 4350528,
"archive_type": "zip",
"filename": "archive.zip",
"checksums": {
"sha1": "07251dbb1d904d143fd7da9935701f17670d4d9b",
"sha256": "1f7d111ac79e468002f3edf4b7b2487538d41f6bea362d49b2eb08a537efafb6",
"sha1_git": "e2d894efcaad4ff36f09eda3b3c0096416b03429",
"blake2s256": "e2c08b82efbc361fbb2d28aa8352668cd71217f165f63de16b61ed61ace7509d",
},
}
]
row = {
"id": b"\t5`S\xc4\x9a\xd0\xf9\xe6.Q\xc2\x9d>a|y\x11@\xdf",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2019, 5, 14, 0, 0, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2019, 5, 14, 0, 0, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"intel: Deposit 268 in collection intel",
"metadata": {
**extrinsic_metadata,
"original_artifact": source_original_artifacts,
},
}
swhid = (
"swh:1:dir:527c8e4a67d391f2bf1bbc86dd94af5d5cfc8ef7"
";origin=https://software.intel.com/f80482de-90a8-4c32-bce4-6f6918d492ff"
";visit=swh:1:snp:49d60943d9c061da1aba6266a811412f9db8de2e"
";anchor=swh:1:rev:09356053c49ad0f9e62e51c29d3e617c791140df"
";path=/"
)
deposit_rows = [
{
"deposit.id": 268,
"deposit.external_id": "f80482de-90a8-4c32-bce4-6f6918d492ff",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2019, 5, 14, 7, 49, 36, 775072, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://software.intel.com",
"deposit_collection.name": "intel",
"auth_user.username": "intel",
},
{
"deposit.id": 268,
"deposit.external_id": "f80482de-90a8-4c32-bce4-6f6918d492ff",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2019, 5, 14, 7, 49, 36, 477061, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://software.intel.com",
"deposit_collection.name": "intel",
"auth_user.username": "intel",
},
{
"deposit.id": 268,
"deposit.external_id": "f80482de-90a8-4c32-bce4-6f6918d492ff",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2019, 5, 14, 7, 28, 33, 210100, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://software.intel.com",
"deposit_collection.name": "intel",
"auth_user.username": "intel",
},
{
"deposit.id": 268,
"deposit.external_id": "f80482de-90a8-4c32-bce4-6f6918d492ff",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2019, 5, 14, 7, 28, 33, 41454, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://software.intel.com",
"deposit_collection.name": "intel",
"auth_user.username": "intel",
},
]
origin_url = "https://software.intel.com/f80482de-90a8-4c32-bce4-6f6918d492ff"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2019, 5, 14, 7, 49, 36, 775072, tzinfo=datetime.timezone.utc
),
authority=INTEL_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:09356053c49ad0f9e62e51c29d3e617c791140df"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2019, 5, 14, 7, 28, 33, 210100, tzinfo=datetime.timezone.utc
),
authority=INTEL_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:09356053c49ad0f9e62e51c29d3e617c791140df"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2019, 5, 14, 7, 49, 36, 775072, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:09356053c49ad0f9e62e51c29d3e617c791140df"
),
),
]
),
]
def test_deposit_3_and_no_swhid():
extrinsic_metadata = {
"id": "hal-02337300",
"@xmlns": "http://www.w3.org/2005/Atom",
"author": {"name": "HAL", "email": "hal@ccsd.cnrs.fr"},
"client": "hal",
"codemeta:url": "https://hal.archives-ouvertes.fr/hal-02337300",
"codemeta:name": "R package SMM, Simulation and Estimation of Multi-State Discrete-Time Semi-Markov and Markov Models",
"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",
"codemeta:author": [
# ...
],
# ...
}
original_artifacts = [
# ...
]
row = {
"id": b"\x91\xe5\xca\x8b'K\xf1\xa8cFd2\xd7Q\xf7A\xbc\x94\xba&",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2017, 1, 1, 0, 0, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2019, 11, 6, 14, 47, 30, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"hal: Deposit 342 in collection hal",
- "metadata": {**extrinsic_metadata, "original_artifact": original_artifacts,},
+ "metadata": {
+ **extrinsic_metadata,
+ "original_artifact": original_artifacts,
+ },
}
storage = Mock()
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == []
def test_deposit_3_and_unknown_deposit():
extrinsic_metadata = {
"title": "Je suis GPL",
"@xmlns": "http://www.w3.org/2005/Atom",
"client": "swh",
"codemeta:url": "https://forge.softwareheritage.org/source/jesuisgpl/",
"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",
"codemeta:author": {
"codemeta:name": "Stefano Zacchiroli",
"codemeta:jobTitle": "Maintainer",
},
# ...
}
row = {
"id": b"\x8e\x9c\xee\x14\xa6\xad9\xbc\xa44pw\xb8\x7f\xb5\xbb\xd8\x95;\xb1",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2018, 7, 23, 12, 25, 45, 907132, tzinfo=datetime.timezone.utc
),
"committer_date": datetime.datetime(
2018, 7, 23, 12, 25, 45, 907132, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"swh: Deposit 159 in collection swh",
"metadata": extrinsic_metadata,
}
origin_url = "https://software.intel.com/f80482de-90a8-4c32-bce4-6f6918d492ff"
storage = Mock()
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == []
def test_deposit_4_without_xmlns():
extrinsic_metadata = {
"{http://www.w3.org/2005/Atom}id": "hal-01243573",
"{http://www.w3.org/2005/Atom}author": {
"{http://www.w3.org/2005/Atom}name": "HAL",
"{http://www.w3.org/2005/Atom}email": "hal@ccsd.cnrs.fr",
},
"{http://www.w3.org/2005/Atom}client": "hal",
"{http://www.w3.org/2005/Atom}external_identifier": "hal-01243573",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}url": "https://hal-test.archives-ouvertes.fr/hal-01243573",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}name": "The assignment problem",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author": {
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}name": "Morane Gruenpeter"
},
# ...
}
row = {
"id": b"\x03\x98\x7f\x05n\xafE\x96\xcd \xd7\xb2\xee\x01\xc9\xb8L\xed\xdf\xa8",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2018, 1, 17, 12, 49, 30, 902891, tzinfo=datetime.timezone.utc
),
"committer_date": datetime.datetime(
2018, 1, 17, 12, 49, 30, 902891, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b": Deposit 79 in collection hal",
"metadata": extrinsic_metadata,
}
swhid = (
"swh:1:dir:e04b2a7b8a8838da0693e9fd992a10d6fd211b50"
";origin=https://hal.archives-ouvertes.fr/hal-01243573"
";visit=swh:1:snp:c31851534c86676a040fb10f438728c90f1c9d55"
";anchor=swh:1:rev:43549ebbe70c9cdf0be1647e6319392eaa06f3a3"
";path=/"
)
deposit_rows = [
{
"deposit.id": 79,
"deposit.external_id": "hal-01243573",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2018, 1, 17, 12, 49, 31, 208347, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
{
"deposit.id": 79,
"deposit.external_id": "hal-01243573",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2018, 1, 17, 12, 49, 30, 645576, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
]
origin_url = "https://hal.archives-ouvertes.fr/hal-01243573"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2018, 1, 17, 12, 49, 30, 645576, tzinfo=datetime.timezone.utc
),
authority=HAL_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json-with-expanded-namespaces",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:03987f056eaf4596cd20d7b2ee01c9b84ceddfa8"
),
),
]
),
# note: no original artifacts
]
def test_deposit_4_wrong_origin():
extrinsic_metadata = {
"{http://www.w3.org/2005/Atom}id": "hal-01588781",
"{http://www.w3.org/2005/Atom}author": {
"{http://www.w3.org/2005/Atom}name": "HAL",
"{http://www.w3.org/2005/Atom}email": "hal@ccsd.cnrs.fr",
},
"{http://www.w3.org/2005/Atom}client": "hal",
"{http://www.w3.org/2005/Atom}external_identifier": "hal-01588781",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}url": "https://inria.halpreprod.archives-ouvertes.fr/hal-01588781",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}name": "The assignment problem ",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author": {
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}name": "Morane Gruenpeter",
"{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}affiliation": "Initiative pour la Recherche et l'Innovation sur le Logiciel Libre",
},
# ...
}
row = {
"id": b"-{\xcec\x1f\xc7\x91\x08\x03\x11\xeb\x83\\GB\x8eXjn\xa4",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2018, 1, 10, 13, 14, 51, 77033, tzinfo=datetime.timezone.utc
),
"committer_date": datetime.datetime(
2018, 1, 10, 13, 14, 51, 77033, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b": Deposit 75 in collection hal",
"metadata": extrinsic_metadata,
}
swhid = (
"swh:1:dir:d8971c651fe256942aa4499a3ccdbaa305d3bade"
";origin=https://inria.halpreprod.archives-ouvertes.fr/hal-01588781"
";visit=swh:1:snp:7c70cc8ea5b79e376605fd6e9b3b04d98861ffc0"
";anchor=swh:1:rev:2d7bce631fc791080311eb835c47428e586a6ea4"
";path=/"
)
deposit_rows = [
{
"deposit.id": 75,
"deposit.external_id": "hal-01588781",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2018, 1, 10, 13, 14, 51, 523963, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
{
"deposit.id": 75,
"deposit.external_id": "hal-01588781",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2018, 1, 10, 13, 14, 50, 555143, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
]
origin_url = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588781"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2018, 1, 10, 13, 14, 50, 555143, tzinfo=datetime.timezone.utc
),
authority=HAL_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json-with-expanded-namespaces",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:2d7bce631fc791080311eb835c47428e586a6ea4"
),
),
]
),
# note: no original artifacts
]
def test_deposit_missing_metadata_in_revision():
extrinsic_metadata = {
"id": "hal-01243573",
"@xmlns": "http://www.w3.org/2005/Atom",
"author": {"name": "HAL", "email": "hal@ccsd.cnrs.fr"},
"client": "hal",
"committer": "Administrateur Du Ccsd",
"codemeta:url": "https://hal-test.archives-ouvertes.fr/hal-01243573",
"codemeta:name": "The assignment problem",
"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",
"codemeta:author": {"codemeta:name": "Morane Gruenpeter"},
"codemeta:version": "1",
- "codemeta:identifier": {"#text": "10.5281/zenodo.438684", "@name": "doi",},
+ "codemeta:identifier": {
+ "#text": "10.5281/zenodo.438684",
+ "@name": "doi",
+ },
"external_identifier": "hal-01243573",
"codemeta:dateCreated": "2017-11-16T14:54:23+01:00",
}
source_original_artifacts = [
{
"name": "archive.zip",
"sha1": "e8e46324970cd5af7f98c5a86f33f47fa4a41b4a",
"length": 118650,
"sha256": "fec81b63d666c43524f966bbd3263da5bee55051d2b48c1659cca5f56fd953e5",
"sha1_git": "9da2bbd08bec590b36ede2ed43d74cd510b10a79",
"blake2s256": "5d0973ba3644cc2bcfdb41ff1891744337d6aa9547a7e59fe466f684b027f295",
"archive_type": "zip",
}
]
dest_original_artifacts = [
{
"length": 118650,
"archive_type": "zip",
"filename": "archive.zip",
"checksums": {
"sha1": "e8e46324970cd5af7f98c5a86f33f47fa4a41b4a",
"sha256": "fec81b63d666c43524f966bbd3263da5bee55051d2b48c1659cca5f56fd953e5",
"sha1_git": "9da2bbd08bec590b36ede2ed43d74cd510b10a79",
"blake2s256": "5d0973ba3644cc2bcfdb41ff1891744337d6aa9547a7e59fe466f684b027f295",
},
}
]
row = {
"id": b"\x03@v\xf3\xf4\x1e\xe1 N\xb9\xf6@\x82\xcb\xe6\xe9P\xd7\xbb\x8a",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2019, 2, 25, 15, 49, 16, 594536, tzinfo=datetime.timezone.utc
),
"committer_date": datetime.datetime(
2019, 2, 25, 15, 49, 16, 594536, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"hal: Deposit 229 in collection hal",
"metadata": {"original_artifact": source_original_artifacts},
}
swhid = (
"swh:1:dir:3d65b6f065118cb856272829b459f0dfa55549aa"
";origin=https://hal-test.archives-ouvertes.fr/hal-01243573"
";visit=swh:1:snp:322c54ff4023d3216a994bc9ff9ee524ed80ee1f"
";anchor=swh:1:rev:034076f3f41ee1204eb9f64082cbe6e950d7bb8a"
";path=/"
)
deposit_rows = [
{
"deposit.id": 229,
"deposit.external_id": "hal-01243573",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": None,
"deposit_request.date": datetime.datetime(
2019, 2, 25, 15, 54, 30, 102072, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
{
"deposit.id": 229,
"deposit.external_id": "hal-01243573",
"deposit.swhid_context": swhid,
"deposit.status": "success",
"deposit_request.metadata": extrinsic_metadata,
"deposit_request.date": datetime.datetime(
2019, 2, 25, 15, 49, 12, 302745, tzinfo=datetime.timezone.utc
),
"deposit_client.provider_url": "https://hal.archives-ouvertes.fr/",
"deposit_collection.name": "hal",
"auth_user.username": "hal",
},
]
origin_url = "https://hal.archives-ouvertes.fr/hal-01243573"
# /!\ not https://hal-test.archives-ouvertes.fr/hal-01243573
# do not trust the metadata!
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = get_mock_deposit_cur(deposit_rows)
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
deposit_cur.execute.assert_called_once()
deposit_cur.__iter__.assert_called_once()
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2019, 2, 25, 15, 49, 12, 302745, tzinfo=datetime.timezone.utc
),
authority=HAL_AUTHORITY,
fetcher=FETCHER,
format="sword-v2-atom-codemeta-v2-in-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:034076f3f41ee1204eb9f64082cbe6e950d7bb8a"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2019, 2, 25, 15, 54, 30, 102072, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:034076f3f41ee1204eb9f64082cbe6e950d7bb8a"
),
),
]
),
]
diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py b/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py
index 1d0bfdda..24553a86 100644
--- a/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py
+++ b/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py
@@ -1,111 +1,112 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# flake8: noqa
# because of long lines
import copy
import datetime
import json
from unittest.mock import Mock, call
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
RawExtrinsicMetadata,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.storage.migrate_extrinsic_metadata import cran_package_from_url, handle_row
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
SWH_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.REGISTRY,
url="https://softwareheritage.org/",
metadata={},
)
DIRECTORY_ID = b"a" * 20
DIRECTORY_SWHID = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=DIRECTORY_ID
)
def test_gnu():
original_artifacts = [
{
"length": 842501,
"filename": "gperf-3.0.1.tar.gz",
"checksums": {
"sha1": "c4453ee492032b369006ee464f4dd4e2c0c0e650",
"sha256": "5be283ef62e1bd26abdaaf88b416dbea4b14c360b09befcda2f055656dc43f87",
"sha1_git": "bf1d5bb57d571101dd7b6acab2b78ae11bb861de",
"blake2s256": "661f84afeb1e0b914defe2b249d424af1dfe380a96016b3282ae758c70e19a70",
},
}
]
row = {
"id": b"\x00\x1cqE\x8e@[%\xba\xcc\xc8\x0b\x99\xf6cM\xff\x9d+\x18",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2003, 6, 13, 0, 11, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2003, 6, 13, 0, 11, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"swh-loader-package: synthetic revision message",
"metadata": {
"extrinsic": {
"raw": {
"url": "https://ftp.gnu.org/gnu/gperf/gperf-3.0.1.tar.gz",
"time": "2003-06-13T00:11:00+00:00",
"length": 842501,
"version": "3.0.1",
"filename": "gperf-3.0.1.tar.gz",
},
"when": "2019-11-27T11:17:38.318997+00:00",
"provider": "https://ftp.gnu.org/gnu/gperf/",
},
"intrinsic": {},
"original_artifact": original_artifacts,
},
}
origin_url = "https://ftp.gnu.org/gnu/gperf/"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(row, storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2019, 11, 27, 11, 17, 38, 318997, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:001c71458e405b25baccc80b99f6634dff9d2b18"
),
),
]
),
]
diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py b/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py
index cf722eb5..41e530bf 100644
--- a/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py
+++ b/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py
@@ -1,127 +1,128 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# flake8: noqa
# because of long lines
import copy
import datetime
import json
from unittest.mock import Mock, call
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
RawExtrinsicMetadata,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.storage.migrate_extrinsic_metadata import cran_package_from_url, handle_row
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
SWH_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.REGISTRY,
url="https://softwareheritage.org/",
metadata={},
)
NIX_UNSTABLE_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.FORGE,
url="https://nix-community.github.io/nixpkgs-swh/sources-unstable.json",
metadata={},
)
DIRECTORY_ID = b"a" * 20
DIRECTORY_SWHID = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=DIRECTORY_ID
)
def test_nixguix():
extrinsic_metadata = {
"url": "https://files.pythonhosted.org/packages/source/a/alerta/alerta-7.4.5.tar.gz",
"integrity": "sha256-km8RAaG1ep+tYR8eHVr3UWk+/MNEqdsBr1Di/g02LYQ=",
}
original_artifacts = [
{
"length": 34903,
"filename": "alerta-7.4.5.tar.gz",
"checksums": {
"sha1": "66db4398b664de272fd5aa6610caa776b5e64651",
"sha256": "926f1101a1b57a9fad611f1e1d5af751693efcc344a9db01af50e2fe0d362d84",
},
}
]
row = {
"id": b"\x00\x01\xbaM\xd0S\x94\x85\x02\x11\xd7\xb3\x85M\x99\x13\xd2:\xe3y",
"directory": DIRECTORY_ID,
"date": None,
"committer_date": None,
"type": "tar",
"message": b"",
"metadata": {
"extrinsic": {
"raw": extrinsic_metadata,
"when": "2020-06-03T11:25:05.259341+00:00",
"provider": "https://nix-community.github.io/nixpkgs-swh/sources-unstable.json",
},
"original_artifact": original_artifacts,
},
}
origin_url = "https://nix-community.github.io/nixpkgs-swh/sources-unstable.json"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(row, storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 6, 3, 11, 25, 5, 259341, tzinfo=datetime.timezone.utc
),
authority=NIX_UNSTABLE_AUTHORITY,
fetcher=FETCHER,
format="nixguix-sources-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0001ba4dd05394850211d7b3854d9913d23ae379"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
2020, 6, 3, 11, 25, 5, 259341, tzinfo=datetime.timezone.utc
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:0001ba4dd05394850211d7b3854d9913d23ae379"
),
),
]
),
]
diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py b/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py
index c6fa97fa..373c38b9 100644
--- a/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py
+++ b/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py
@@ -1,381 +1,428 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# flake8: noqa
# because of long lines
import copy
import datetime
import json
from unittest.mock import Mock, call
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
RawExtrinsicMetadata,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.storage.migrate_extrinsic_metadata import (
handle_row,
npm_package_from_source_url,
)
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
NPM_AUTHORITY = MetadataAuthority(
- type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", metadata={},
+ type=MetadataAuthorityType.FORGE,
+ url="https://npmjs.com/",
+ metadata={},
)
SWH_AUTHORITY = MetadataAuthority(
type=MetadataAuthorityType.REGISTRY,
url="https://softwareheritage.org/",
metadata={},
)
DIRECTORY_ID = b"a" * 20
DIRECTORY_SWHID = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=DIRECTORY_ID
)
def test_npm_package_from_source_url():
package_urls = [
(
"@l3ilkojr/jdinsults",
"https://registry.npmjs.org/@l3ilkojr/jdinsults/-/jdinsults-3.0.0.tgz",
),
("simplemaps", "https://registry.npmjs.org/simplemaps/-/simplemaps-0.0.6.tgz"),
(
"@piximi/components",
"https://registry.npmjs.org/@piximi/components/-/components-0.1.11.tgz",
),
(
"@chappa'ai/get-next-rc",
"https://registry.npmjs.org/@chappa%27ai/get-next-rc/-/get-next-rc-1.0.0.tgz",
),
]
for (package_name, source_url) in package_urls:
assert npm_package_from_source_url(source_url) == package_name
def test_npm_1():
"""Tests loading a revision generated by a new NPM loader that
has a provider."""
extrinsic_metadata = {
"_id": "@l3ilkojr/jdinsults@3.0.0",
"dist": {
"shasum": "b7f0d66090e0285f4e95d082d39bcb0c1b8f4ec8",
"tarball": "https://registry.npmjs.org/@l3ilkojr/jdinsults/-/jdinsults-3.0.0.tgz",
"fileCount": 4,
"integrity": "sha512-qpv8Zg51g0l51VjODEooMUGSGanGUuQpzX5msfR7ZzbgTsgPbpDNyTIsQ0wQzI9RzCCUjS84Ii2VhMISEQcEUA==",
"unpackedSize": 1583,
"npm-signature": "-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\n2Gw4\r\n=8uqZ\r\n-----END PGP SIGNATURE-----\r\n",
},
"name": "@l3ilkojr/jdinsults",
"version": "3.0.0",
"_npmUser": {"name": "l3ilkojr", "email": "l3ilkojr@example.com"},
"_npmVersion": "6.13.6",
"description": "Generates insults",
"directories": {},
"maintainers": [{"name": "l3ilkojr", "email": "l3ilkojr@example.com"}],
"_nodeVersion": "10.14.0",
"_hasShrinkwrap": False,
"_npmOperationalInternal": {
"tmp": "tmp/jdinsults_3.0.0_1582351545285_0.2614827716102821",
"host": "s3://npm-registry-packages",
},
}
original_artifacts = [
{
"length": 1033,
"filename": "jdinsults-3.0.0.tgz",
"checksums": {
"sha1": "b7f0d66090e0285f4e95d082d39bcb0c1b8f4ec8",
"sha256": "42f22795ac883b02fded0b2bf3d8a77f6507d40bc67f28eea6b1b73eb59c515f",
},
}
]
row = {
"id": b"\x00\x00\x02\xa4\x9b\xba\x17\xca\x8c\xf3\x7f_=\x16\xaa\xac\xf9S`\xfc",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2020, 2, 22, 6, 5, 45, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2020, 2, 22, 6, 5, 45, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"3.0.0",
"metadata": {
"extrinsic": {
"raw": extrinsic_metadata,
"when": "2020-02-27T01:35:47.965375+00:00",
"provider": "https://replicate.npmjs.com/%40l3ilkojr%2Fjdinsults/",
},
"intrinsic": {
"raw": {"name": "@l3ilkojr/jdinsults", "version": "3.0.0"},
"tool": "package.json",
},
"original_artifact": original_artifacts,
},
}
origin_url = "https://www.npmjs.com/package/@l3ilkojr/jdinsults"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 2, 27, 1, 35, 47, 965375, tzinfo=datetime.timezone.utc,
+ 2020,
+ 2,
+ 27,
+ 1,
+ 35,
+ 47,
+ 965375,
+ tzinfo=datetime.timezone.utc,
),
authority=NPM_AUTHORITY,
fetcher=FETCHER,
format="replicate-npm-package-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:000002a49bba17ca8cf37f5f3d16aaacf95360fc"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 2, 27, 1, 35, 47, 965375, tzinfo=datetime.timezone.utc,
+ 2020,
+ 2,
+ 27,
+ 1,
+ 35,
+ 47,
+ 965375,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:000002a49bba17ca8cf37f5f3d16aaacf95360fc"
),
),
]
),
]
def test_npm_2_unscoped():
"""Tests loading a revision generated by an old NPM loader that doesn't
have a provider; and the package name is unscoped (ie. doesn't contain a
slash)."""
extrinsic_metadata = {
"bugs": {"url": "https://github.com/niwasawa/simplemaps/issues"},
"name": "simplemaps",
"author": "Naoki Iwasawa",
"license": "MIT",
# ...
}
package_source = {
"url": "https://registry.npmjs.org/simplemaps/-/simplemaps-0.0.6.tgz",
"date": "2016-12-23T07:21:29.733Z",
"name": "simplemaps",
"sha1": "e2b8222930196def764527f5c61048c5b28fe3c4",
"sha256": "3ce94927bab5feafea5695d1fa4c2b8131413e53e249b32f9ac2ccff4d865a0b",
"version": "0.0.6",
"filename": "simplemaps-0.0.6.tgz",
"blake2s256": "6769b4009f8162be2e745604b153443d4907a85781d31a724217a3e2d42a7462",
}
original_artifacts = [
{
"filename": "simplemaps-0.0.6.tgz",
"checksums": {
"sha1": "e2b8222930196def764527f5c61048c5b28fe3c4",
"sha256": "3ce94927bab5feafea5695d1fa4c2b8131413e53e249b32f9ac2ccff4d865a0b",
"blake2s256": "6769b4009f8162be2e745604b153443d4907a85781d31a724217a3e2d42a7462",
},
"url": "https://registry.npmjs.org/simplemaps/-/simplemaps-0.0.6.tgz",
}
]
row = {
"id": b"\x00\x00\x04\xae\xed\t\xee\x08\x9cx\x12d\xc0M%d\xfdX\xfe\xb5",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2016, 12, 23, 7, 21, 29, tzinfo=datetime.timezone.utc
),
"committer_date": datetime.datetime(
2016, 12, 23, 7, 21, 29, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"0.0.6",
- "metadata": {"package": extrinsic_metadata, "package_source": package_source,},
+ "metadata": {
+ "package": extrinsic_metadata,
+ "package_source": package_source,
+ },
}
origin_url = "https://www.npmjs.com/package/simplemaps"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2016, 12, 23, 7, 21, 29, tzinfo=datetime.timezone.utc,
+ 2016,
+ 12,
+ 23,
+ 7,
+ 21,
+ 29,
+ tzinfo=datetime.timezone.utc,
),
authority=NPM_AUTHORITY,
fetcher=FETCHER,
format="replicate-npm-package-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:000004aeed09ee089c781264c04d2564fd58feb5"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2016, 12, 23, 7, 21, 29, tzinfo=datetime.timezone.utc,
+ 2016,
+ 12,
+ 23,
+ 7,
+ 21,
+ 29,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:000004aeed09ee089c781264c04d2564fd58feb5"
),
),
]
),
]
def test_npm_2_scoped():
"""Tests loading a revision generated by an old NPM loader that doesn't
have a provider; and the package name is scoped (ie. in the format
@org/name)."""
extrinsic_metadata = {
"bugs": {"url": "https://github.com/piximi/components/issues"},
"name": "@piximi/components",
# ...
}
package_source = {
"url": "https://registry.npmjs.org/@piximi/components/-/components-0.1.11.tgz",
"date": "2019-06-07T19:56:04.753Z",
"name": "@piximi/components",
"sha1": "4ab74e563cb61bb5b2022601a5133a2dd19d19ec",
"sha256": "69bb980bd6de3277b6bca86fd79c91f1c28db6910c8d03ecd05b32b78a35188f",
"version": "0.1.11",
"filename": "components-0.1.11.tgz",
"blake2s256": "ce33181d5eff25b70ffdd6f1a18acd472a1707ede23cd2adc6af272dfc40dbfd",
}
original_artifacts = [
{
"filename": "components-0.1.11.tgz",
"checksums": {
"sha1": "4ab74e563cb61bb5b2022601a5133a2dd19d19ec",
"sha256": "69bb980bd6de3277b6bca86fd79c91f1c28db6910c8d03ecd05b32b78a35188f",
"blake2s256": "ce33181d5eff25b70ffdd6f1a18acd472a1707ede23cd2adc6af272dfc40dbfd",
},
"url": "https://registry.npmjs.org/@piximi/components/-/components-0.1.11.tgz",
}
]
row = {
"id": b"\x00\x00 \x19\xc5wXt\xbc\xed\x00zR\x9b\xd3\xb7\x8b\xf6\x04W",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2019, 6, 7, 19, 56, 4, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2019, 6, 7, 19, 56, 4, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"0.1.11",
- "metadata": {"package": extrinsic_metadata, "package_source": package_source,},
+ "metadata": {
+ "package": extrinsic_metadata,
+ "package_source": package_source,
+ },
}
origin_url = "https://www.npmjs.com/package/@piximi/components"
storage = Mock()
def origin_get(urls):
assert urls == [origin_url]
return [Origin(url=origin_url)]
storage.origin_get.side_effect = origin_get
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
assert storage.method_calls == [
call.origin_get([origin_url]),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2019, 6, 7, 19, 56, 4, tzinfo=datetime.timezone.utc,
+ 2019,
+ 6,
+ 7,
+ 19,
+ 56,
+ 4,
+ tzinfo=datetime.timezone.utc,
),
authority=NPM_AUTHORITY,
fetcher=FETCHER,
format="replicate-npm-package-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:00002019c5775874bced007a529bd3b78bf60457"
),
),
]
),
call.raw_extrinsic_metadata_add(
[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2019, 6, 7, 19, 56, 4, tzinfo=datetime.timezone.utc,
+ 2019,
+ 6,
+ 7,
+ 19,
+ 56,
+ 4,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=CoreSWHID.from_string(
"swh:1:rev:00002019c5775874bced007a529bd3b78bf60457"
),
),
]
),
]
diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py b/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py
index 58b36a17..111dcee1 100644
--- a/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py
+++ b/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py
@@ -1,653 +1,721 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
# flake8: noqa
# because of long lines
import copy
import datetime
import json
import urllib.error
import attr
from swh.model.model import (
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
Origin,
OriginVisit,
OriginVisitStatus,
RawExtrinsicMetadata,
Snapshot,
SnapshotBranch,
TargetType,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.storage import get_storage
from swh.storage.interface import PagedResult
from swh.storage.migrate_extrinsic_metadata import (
handle_row,
pypi_origin_from_filename,
pypi_project_from_filename,
)
FETCHER = MetadataFetcher(
- name="migrate-extrinsic-metadata-from-revisions", version="0.0.1",
+ name="migrate-extrinsic-metadata-from-revisions",
+ version="0.0.1",
)
PYPI_AUTHORITY = MetadataAuthority(
- type=MetadataAuthorityType.FORGE, url="https://pypi.org/",
+ type=MetadataAuthorityType.FORGE,
+ url="https://pypi.org/",
)
SWH_AUTHORITY = MetadataAuthority(
- type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/",
+ type=MetadataAuthorityType.REGISTRY,
+ url="https://softwareheritage.org/",
)
DIRECTORY_ID = b"a" * 20
DIRECTORY_SWHID = ExtendedSWHID(
object_type=ExtendedObjectType.DIRECTORY, object_id=DIRECTORY_ID
)
def now():
return datetime.datetime.now(tz=datetime.timezone.utc)
def test_pypi_project_from_filename():
files = [
("django-agent-trust-0.1.8.tar.gz", "django-agent-trust"),
("python_test-1.0.1.zip", "python_test"),
("py-evm-0.2.0a9.tar.gz", "py-evm"),
("collective.texttospeech-1.0rc1.tar.gz", "collective.texttospeech"),
("flatland-fork-0.4.post1.dev40550160.zip", "flatland-fork"),
("fake-factory-0.5.6-proper.tar.gz", "fake-factory"),
("ariane_procos-0.1.2-b05.tar.gz", "ariane_procos"),
("Yelpy-0.2.2dev.tar.gz", "Yelpy"),
("geventhttpclient_c-1.0a-t1.tar.gz", "geventhttpclient_c"),
("codeforlife-portal-1.0.0.post.dev618.tar.gz", "codeforlife-portal"),
("ChecklistDSL-0.0.1.alpha.1.tar.gz", "ChecklistDSL"),
("transifex-1.1.0beta.tar.gz", "transifex"),
("thespian-2.5.10.tar.bz2", "thespian"),
("janis pipelines-0.5.3.tar.gz", "janis-pipelines"),
("pants-1.0.0-beta.2.tar.gz", "pants"),
("uforge_python_sdk-3.8.4-RC15.tar.gz", "uforge_python_sdk"),
("virtuoso-0.11.0.48.b5865c2b46fb.tar.gz", "virtuoso"),
("cloud_ftp-v1.0.0.tar.gz", "cloud_ftp"),
("frozenordereddict-1.0.0.tgz", "frozenordereddict"),
("pywebsite-0.1.2pre.tar.gz", "pywebsite"),
("Flask Unchained-0.2.0.tar.gz", "Flask-Unchained"),
("mongomotor-0.13.0.n.tar.gz", "mongomotor"),
("datahaven-rev8784.tar.gz", "datahaven"),
("geopandas-0.1.0.dev-120d5ee.tar.gz", "geopandas"),
("aimmo-v0.1.1-alpha.post.dev61.tar.gz", "aimmo"),
("django-migrations-plus-0.1.0.dev5.gdd1abd3.tar.gz", "django-migrations-plus"),
("function_shield.tar.gz", "function_shield"),
("Dtls-0.1.0.sdist_with_openssl.mingw-win32.tar.gz", "Dtls"),
("pytz-2005m.tar.gz", "pytz"),
("python-librsync-0.1-3.tar.gz", "python-librsync"),
("powny-1.4.0-alpha-20141205-1452-f5a2b03.tar.gz", "powny"),
("stp-3pc-batch-0.1.11.tar.gz", "stp-3pc-batch"),
("obedient.powny-3.0.0-alpha-20141027-2102-9e53ebd.tar.gz", "obedient.powny"),
("mojimoji-0.0.9_2.tar.gz", "mojimoji"),
("devpi-theme-16-2.0.0.tar.gz", "devpi-theme-16"),
("Orange3-WONDER-1-1.0.7.tar.gz", "Orange3-WONDER-1"),
("obj-34.tar.gz", "obj"),
("pytorch-ignite-nightly-20190825.tar.gz", "pytorch-ignite-nightly"),
("tlds-2019081900.tar.gz", "tlds"),
("dominator-12.1.2-alpha-20141027-1446-ad46e0f.tar.gz", "dominator"),
("waferslim-1.0.0-py3.1.zip", "waferslim"),
("Beaver-21.tar.gz", "Beaver"),
("aimmo-0.post.dev460.tar.gz", "aimmo"),
("ohai-1!0.tar.gz", "ohai"),
("nevolution-risk-139.tar.gz", "nevolution-risk"),
("collective.topicitemsevent-0.1dvl.tar.gz", "collective.topicitemsevent"),
("lesscpy-0.9g.tar.gz", "lesscpy"),
("SpiNNStorageHandlers-1!4.0.0a1.tar.gz", "SpiNNStorageHandlers"),
("limnoria-2013-03-27T16:32:26+0100.tar.gz", "limnoria"),
(
"sPyNNakerExternalDevicesPlugin-1!4.0.0a2.tar.gz",
"sPyNNakerExternalDevicesPlugin",
),
("django-bootstrap-italia_0.1.tar.gz", "django-bootstrap-italia"),
("sPyNNaker8-1!4.0.0a1.tar.gz", "sPyNNaker8"),
("betahaus.openmember-0.1adev-r1651.tar.gz", "betahaus.openmember"),
("mailer.0.8.0.zip", "mailer"),
("pytz-2005k.tar.bz2", "pytz"),
("aha.plugin.microne-0.62bdev.tar.gz", "aha.plugin.microne"),
("youtube_dl_server-alpha.3.tar.gz", "youtube_dl_server"),
("json-extensions-b76bc7d.tar.gz", "json-extensions"),
("LitReview-0.6989ev.tar.gz", "LitReview"),
("django_options-r5.tar.gz", "django_options"),
("ddlib-2013-11-07.tar.gz", "ddlib"),
("python-morfeusz-0.3000+py3k.tar.gz", "python-morfeusz"),
("gaepytz-2011h.zip", "gaepytz"),
("ftldat-r3.tar.gz", "ftldat"),
("tigretoolbox-0.0.0-py2.7-linux-x86_64.egg", None),
(
"Greater than, equal, or less Library-0.1.tar.gz",
"Greater-than-equal-or-less-Library",
),
("upstart--main-.-VLazy.object.at.0x104ba8b50-.tar.gz", "upstart"),
("duckduckpy0.1.tar.gz", "duckduckpy"),
("QUI for MPlayer snapshot_9-14-2011.zip", "QUI-for-MPlayer"),
("Eddy's Memory Game-1.0.zip", "Eddy-s-Memory-Game"),
("jekyll2nikola-0-0-1.tar.gz", "jekyll2nikola"),
("ore.workflowed-0-6-2.tar.gz", "ore.workflowed"),
("instancemanager-1.0rc-r34317.tar.gz", "instancemanager"),
("OrzMC_W&L-1.0.0.tar.gz", "OrzMC-W-L"),
("use0mk.tar.gz", "use0mk"),
("play-0-develop-1-gd67cd85.tar.gz", "play"),
("mosaic-nist-2.0b1+f98ae80.tar.gz", "mosaic-nist"),
("pypops-201408-r3.tar.gz", "pypops"),
]
for (filename, project) in files:
assert pypi_project_from_filename(filename) == project
def test_pypi_origin_from_project_name(mocker):
origin_url = "https://pypi.org/project/ProjectName/"
storage = get_storage("memory")
revision_id = b"41" * 10
snapshot_id = b"42" * 10
storage.origin_add([Origin(url=origin_url)])
storage.origin_visit_add(
[OriginVisit(origin=origin_url, visit=1, date=now(), type="pypi")]
)
storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin_url,
visit=1,
date=now(),
status="partial",
snapshot=snapshot_id,
)
]
)
storage.snapshot_add(
[
Snapshot(
id=snapshot_id,
branches={
b"foo": SnapshotBranch(
- target_type=TargetType.REVISION, target=revision_id,
+ target_type=TargetType.REVISION,
+ target=revision_id,
)
},
)
]
)
class response:
code = 200
def read(self):
return b'{"info": {"name": "ProjectName"}}'
mock_urlopen = mocker.patch(
- "swh.storage.migrate_extrinsic_metadata.urlopen", return_value=response(),
+ "swh.storage.migrate_extrinsic_metadata.urlopen",
+ return_value=response(),
)
assert (
pypi_origin_from_filename(storage, revision_id, "ProjectName-1.0.0.tar.gz")
== origin_url
)
mock_urlopen.assert_not_called()
assert (
pypi_origin_from_filename(storage, revision_id, "projectname-1.0.0.tar.gz")
== origin_url
)
mock_urlopen.assert_called_once_with("https://pypi.org/pypi/projectname/json/")
def test_pypi_1():
"""Tests loading a revision generated by a new PyPI loader that
has a provider."""
extrinsic_metadata = {
"url": "https://files.pythonhosted.org/packages/70/89/a498245baf1bf3dde73d3da00b4b067a8aa7c7378ad83472078803ea3e43/m3-ui-2.2.73.tar.gz",
"size": 3933168,
"digests": {
"md5": "a374ac3f655e97df5db5335e2142d344",
"sha256": "1bc2756f7d0d2e15cf5880ca697682ff35e8b58116bf73eb9c78b3db358c5b7d",
},
"has_sig": False,
"filename": "m3-ui-2.2.73.tar.gz",
"downloads": -1,
"md5_digest": "a374ac3f655e97df5db5335e2142d344",
"packagetype": "sdist",
"upload_time": "2019-11-11T06:21:20",
"comment_text": "",
"python_version": "source",
"requires_python": None,
"upload_time_iso_8601": "2019-11-11T06:21:20.073082Z",
}
original_artifacts = [
{
"length": 3933168,
"filename": "m3-ui-2.2.73.tar.gz",
"checksums": {
"sha1": "9f4ec7ce64b7fea4b122e85d47ea31146c367b03",
"sha256": "1bc2756f7d0d2e15cf5880ca697682ff35e8b58116bf73eb9c78b3db358c5b7d",
},
}
]
row = {
"id": b"\x00\x00\x07a{S\xe7\xb1E\x8fi]\xd0}\xe4\xceU\xaf\x15\x17",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
- 2019, 11, 11, 6, 21, 20, tzinfo=datetime.timezone.utc,
+ 2019,
+ 11,
+ 11,
+ 6,
+ 21,
+ 20,
+ tzinfo=datetime.timezone.utc,
),
"committer_date": datetime.datetime(
- 2019, 11, 11, 6, 21, 20, tzinfo=datetime.timezone.utc,
+ 2019,
+ 11,
+ 11,
+ 6,
+ 21,
+ 20,
+ tzinfo=datetime.timezone.utc,
),
"type": "tar",
"message": b"2.2.73",
"metadata": {
"extrinsic": {
"raw": extrinsic_metadata,
"when": "2020-01-23T18:43:09.109407+00:00",
"provider": "https://pypi.org/pypi/m3-ui/json",
},
"intrinsic": {
"raw": {
"name": "m3-ui",
"summary": "======",
"version": "2.2.73",
# ...
"metadata_version": "1.1",
},
"tool": "PKG-INFO",
},
"original_artifact": original_artifacts,
},
}
origin_url = "https://pypi.org/project/m3-ui/"
storage = get_storage("memory")
storage.origin_add([Origin(url=origin_url)])
storage.metadata_authority_add(
[
attr.evolve(PYPI_AUTHORITY, metadata={}),
attr.evolve(SWH_AUTHORITY, metadata={}),
]
)
storage.metadata_fetcher_add([FETCHER])
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
revision_swhid = CoreSWHID.from_string(
"swh:1:rev:000007617b53e7b1458f695dd07de4ce55af1517"
)
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=PYPI_AUTHORITY,
+ DIRECTORY_SWHID,
+ authority=PYPI_AUTHORITY,
) == PagedResult(
results=[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 1, 23, 18, 43, 9, 109407, tzinfo=datetime.timezone.utc,
+ 2020,
+ 1,
+ 23,
+ 18,
+ 43,
+ 9,
+ 109407,
+ tzinfo=datetime.timezone.utc,
),
authority=PYPI_AUTHORITY,
fetcher=FETCHER,
format="pypi-project-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=origin_url,
revision=revision_swhid,
),
],
next_page_token=None,
)
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=SWH_AUTHORITY,
+ DIRECTORY_SWHID,
+ authority=SWH_AUTHORITY,
) == PagedResult(
results=[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2020, 1, 23, 18, 43, 9, 109407, tzinfo=datetime.timezone.utc,
+ 2020,
+ 1,
+ 23,
+ 18,
+ 43,
+ 9,
+ 109407,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(original_artifacts).encode(),
origin=origin_url,
revision=revision_swhid,
),
],
next_page_token=None,
)
def test_pypi_2(mocker):
"""Tests loading a revision generated by an old PyPI loader that
does not have a provider, but has 'project' metadata."""
mocker.patch(
"swh.storage.migrate_extrinsic_metadata.urlopen",
side_effect=urllib.error.HTTPError(None, 404, "Not Found", None, None),
)
extrinsic_metadata = {
"name": "jupyterhub-simx",
"author": "Jupyter Development Team",
"license": "BSD",
"summary": "JupyterHub: A multi-user server for Jupyter notebooks",
"version": "1.0.5",
# ...
}
source_original_artifacts = [
{
"url": "https://files.pythonhosted.org/packages/72/28/a8098763d78e2c4607cb67602c0d726a97ac38d4c1f531aac28f49de2e1a/jupyterhub-simx-1.0.5.tar.gz",
"date": "2019-01-23T22:10:55",
"sha1": "ede3eadd5a06e70912e3ba7cfccef789c4ad3168",
"size": 2346538,
"sha256": "0399d7f5f0d90c525d369f0507ad0e8ef8729c1c7fa63aadfc46a27514d14a46",
"filename": "jupyterhub-simx-1.0.5.tar.gz",
"sha1_git": "734301124712182eb30fc90e97cc18cef5432f02",
"blake2s256": "bb4aa82ffb5891a05dcf6d4dce3ad56fd2c18e9abdba9d20972910649d869322",
"archive_type": "tar",
}
]
dest_original_artifacts = [
{
"url": "https://files.pythonhosted.org/packages/72/28/a8098763d78e2c4607cb67602c0d726a97ac38d4c1f531aac28f49de2e1a/jupyterhub-simx-1.0.5.tar.gz",
"filename": "jupyterhub-simx-1.0.5.tar.gz",
"archive_type": "tar",
"length": 2346538,
"checksums": {
"sha1": "ede3eadd5a06e70912e3ba7cfccef789c4ad3168",
"sha256": "0399d7f5f0d90c525d369f0507ad0e8ef8729c1c7fa63aadfc46a27514d14a46",
"sha1_git": "734301124712182eb30fc90e97cc18cef5432f02",
"blake2s256": "bb4aa82ffb5891a05dcf6d4dce3ad56fd2c18e9abdba9d20972910649d869322",
},
}
]
row = {
"id": b"\x00\x00\x04\xd68,J\xd4\xc0Q\x92fbl6U\x1f\x0eQ\xca",
"directory": DIRECTORY_ID,
"date": datetime.datetime(
2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc
),
"committer_date": datetime.datetime(
2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"1.0.5",
"metadata": {
"project": extrinsic_metadata,
"original_artifact": source_original_artifacts,
},
}
origin_url = "https://pypi.org/project/jupyterhub-simx/"
storage = get_storage("memory")
storage.origin_add([Origin(url=origin_url)])
storage.metadata_authority_add(
[
attr.evolve(PYPI_AUTHORITY, metadata={}),
attr.evolve(SWH_AUTHORITY, metadata={}),
]
)
storage.metadata_fetcher_add([FETCHER])
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
revision_swhid = CoreSWHID.from_string(
"swh:1:rev:000004d6382c4ad4c0519266626c36551f0e51ca"
)
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=PYPI_AUTHORITY,
+ DIRECTORY_SWHID,
+ authority=PYPI_AUTHORITY,
) == PagedResult(
results=[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc,
+ 2019,
+ 1,
+ 23,
+ 22,
+ 10,
+ 55,
+ tzinfo=datetime.timezone.utc,
),
authority=PYPI_AUTHORITY,
fetcher=FETCHER,
format="pypi-project-json",
metadata=json.dumps(extrinsic_metadata).encode(),
origin=None,
revision=revision_swhid,
),
],
next_page_token=None,
)
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=SWH_AUTHORITY,
+ DIRECTORY_SWHID,
+ authority=SWH_AUTHORITY,
) == PagedResult(
results=[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc,
+ 2019,
+ 1,
+ 23,
+ 22,
+ 10,
+ 55,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=None,
revision=revision_swhid,
),
],
next_page_token=None,
)
def test_pypi_3(mocker):
"""Tests loading a revision generated by a very old PyPI loader that
does not have a provider or has 'project' metadata."""
mocker.patch(
"swh.storage.migrate_extrinsic_metadata.urlopen",
side_effect=urllib.error.HTTPError(None, 404, "Not Found", None, None),
)
source_original_artifact = {
"url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz",
"date": "2014-05-07T22:03:00",
"sha1": "3289269f75b4111dd00eaea53e00330db9a1db12",
"size": 46644,
"sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824",
"filename": "PyPDFLite-0.1.32.tar.gz",
"sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5",
"blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385",
"archive_type": "tar",
}
dest_original_artifacts = [
{
"url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz",
"filename": "PyPDFLite-0.1.32.tar.gz",
"archive_type": "tar",
"length": 46644,
"checksums": {
"sha1": "3289269f75b4111dd00eaea53e00330db9a1db12",
"sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824",
"sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5",
"blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385",
},
}
]
row = {
"id": b"N\xa9\x91|\xdfS\xcd\x13SJ\x04.N\xb3x{\x86\xc84\xd2",
"directory": DIRECTORY_ID,
"date": datetime.datetime(2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"0.1.32",
"metadata": {"original_artifact": source_original_artifact},
}
origin_url = "https://pypi.org/project/PyPDFLite/"
storage = get_storage("memory")
storage.origin_add([Origin(url=origin_url)])
storage.metadata_authority_add(
[
attr.evolve(PYPI_AUTHORITY, metadata={}),
attr.evolve(SWH_AUTHORITY, metadata={}),
]
)
storage.metadata_fetcher_add([FETCHER])
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
revision_swhid = CoreSWHID.from_string(
"swh:1:rev:4ea9917cdf53cd13534a042e4eb3787b86c834d2"
)
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=PYPI_AUTHORITY,
- ) == PagedResult(results=[], next_page_token=None,)
+ DIRECTORY_SWHID,
+ authority=PYPI_AUTHORITY,
+ ) == PagedResult(
+ results=[],
+ next_page_token=None,
+ )
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=SWH_AUTHORITY,
+ DIRECTORY_SWHID,
+ authority=SWH_AUTHORITY,
) == PagedResult(
results=[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc,
+ 2014,
+ 5,
+ 7,
+ 22,
+ 3,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=None,
revision=revision_swhid,
),
],
next_page_token=None,
)
def test_pypi_good_origin():
"""Tests loading a revision whose origin we can find"""
source_original_artifact = {
"url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz",
"date": "2014-05-07T22:03:00",
"sha1": "3289269f75b4111dd00eaea53e00330db9a1db12",
"size": 46644,
"sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824",
"filename": "PyPDFLite-0.1.32.tar.gz",
"sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5",
"blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385",
"archive_type": "tar",
}
dest_original_artifacts = [
{
"url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz",
"filename": "PyPDFLite-0.1.32.tar.gz",
"archive_type": "tar",
"length": 46644,
"checksums": {
"sha1": "3289269f75b4111dd00eaea53e00330db9a1db12",
"sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824",
"sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5",
"blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385",
},
}
]
revision_id = b"N\xa9\x91|\xdfS\xcd\x13SJ\x04.N\xb3x{\x86\xc84\xd2"
row = {
"id": revision_id,
"directory": DIRECTORY_ID,
"date": datetime.datetime(2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc),
"committer_date": datetime.datetime(
2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc
),
"type": "tar",
"message": b"0.1.32",
"metadata": {"original_artifact": source_original_artifact},
}
origin_url = "https://pypi.org/project/PyPDFLite/"
storage = get_storage("memory")
snapshot_id = b"42" * 10
storage.origin_add([Origin(url=origin_url)])
storage.origin_visit_add(
[OriginVisit(origin=origin_url, visit=1, date=now(), type="pypi")]
)
storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin_url,
visit=1,
date=now(),
status="partial",
snapshot=snapshot_id,
)
]
)
storage.snapshot_add(
[
Snapshot(
id=snapshot_id,
branches={
b"foo": SnapshotBranch(
- target_type=TargetType.REVISION, target=revision_id,
+ target_type=TargetType.REVISION,
+ target=revision_id,
)
},
)
]
)
storage.metadata_authority_add(
[
attr.evolve(PYPI_AUTHORITY, metadata={}),
attr.evolve(SWH_AUTHORITY, metadata={}),
]
)
storage.metadata_fetcher_add([FETCHER])
deposit_cur = None
handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False)
revision_swhid = CoreSWHID.from_string(
"swh:1:rev:4ea9917cdf53cd13534a042e4eb3787b86c834d2"
)
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=PYPI_AUTHORITY,
- ) == PagedResult(results=[], next_page_token=None,)
+ DIRECTORY_SWHID,
+ authority=PYPI_AUTHORITY,
+ ) == PagedResult(
+ results=[],
+ next_page_token=None,
+ )
assert storage.raw_extrinsic_metadata_get(
- DIRECTORY_SWHID, authority=SWH_AUTHORITY,
+ DIRECTORY_SWHID,
+ authority=SWH_AUTHORITY,
) == PagedResult(
results=[
RawExtrinsicMetadata(
target=DIRECTORY_SWHID,
discovery_date=datetime.datetime(
- 2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc,
+ 2014,
+ 5,
+ 7,
+ 22,
+ 3,
+ tzinfo=datetime.timezone.utc,
),
authority=SWH_AUTHORITY,
fetcher=FETCHER,
format="original-artifacts-json",
metadata=json.dumps(dest_original_artifacts).encode(),
origin=origin_url,
revision=revision_swhid,
),
],
next_page_token=None,
)
diff --git a/swh/storage/tests/storage_data.py b/swh/storage/tests/storage_data.py
index a1e96802..f790293d 100644
--- a/swh/storage/tests/storage_data.py
+++ b/swh/storage/tests/storage_data.py
@@ -1,696 +1,781 @@
# Copyright (C) 2015-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
from typing import Tuple
import attr
from swh.model import from_disk
from swh.model.hashutil import hash_to_bytes
from swh.model.model import (
Content,
Directory,
DirectoryEntry,
ExtID,
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
ObjectType,
Origin,
OriginVisit,
Person,
RawExtrinsicMetadata,
Release,
Revision,
RevisionType,
SkippedContent,
Snapshot,
SnapshotBranch,
TargetType,
Timestamp,
TimestampWithTimezone,
)
from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID
from swh.model.swhids import ObjectType as SwhidObjectType
class StorageData:
- """Data model objects to use within tests.
-
- """
+ """Data model objects to use within tests."""
content = Content(
data=b"42\n",
length=3,
sha1=hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4689"),
sha1_git=hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"),
sha256=hash_to_bytes(
"084c799cd551dd1d8d5c5f9a5d593b2e931f5e36122ee5c793c1d08a19839cc0"
),
blake2s256=hash_to_bytes(
"d5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d"
),
status="visible",
)
content2 = Content(
data=b"4242\n",
length=5,
sha1=hash_to_bytes("61c2b3a30496d329e21af70dd2d7e097046d07b7"),
sha1_git=hash_to_bytes("36fade77193cb6d2bd826161a0979d64c28ab4fa"),
sha256=hash_to_bytes(
"859f0b154fdb2d630f45e1ecae4a862915435e663248bb8461d914696fc047cd"
),
blake2s256=hash_to_bytes(
"849c20fad132b7c2d62c15de310adfe87be94a379941bed295e8141c6219810d"
),
status="visible",
)
content3 = Content(
data=b"424242\n",
length=7,
sha1=hash_to_bytes("3e21cc4942a4234c9e5edd8a9cacd1670fe59f13"),
sha1_git=hash_to_bytes("c932c7649c6dfa4b82327d121215116909eb3bea"),
sha256=hash_to_bytes(
"92fb72daf8c6818288a35137b72155f507e5de8d892712ab96277aaed8cf8a36"
),
blake2s256=hash_to_bytes(
"76d0346f44e5a27f6bafdd9c2befd304aff83780f93121d801ab6a1d4769db11"
),
status="visible",
ctime=datetime.datetime(2019, 12, 1, tzinfo=datetime.timezone.utc),
)
contents: Tuple[Content, ...] = (content, content2, content3)
skipped_content = SkippedContent(
length=1024 * 1024 * 200,
sha1_git=hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8920"),
sha1=hash_to_bytes("43e45d56f88993aae6a0198013efa80716fd8920"),
sha256=hash_to_bytes(
"7bbd052ab054ef222c1c87be60cd191addedd24cc882d1f5f7f7be61dc61bb3a"
),
blake2s256=hash_to_bytes(
"ade18b1adecb33f891ca36664da676e12c772cc193778aac9a137b8dc5834b9b"
),
reason="Content too long",
status="absent",
origin="file:///dev/zero",
)
skipped_content2 = SkippedContent(
length=1024 * 1024 * 300,
sha1_git=hash_to_bytes("44e45d56f88993aae6a0198013efa80716fd8921"),
sha1=hash_to_bytes("54e45d56f88993aae6a0198013efa80716fd8920"),
sha256=hash_to_bytes(
"8cbd052ab054ef222c1c87be60cd191addedd24cc882d1f5f7f7be61dc61bb3a"
),
blake2s256=hash_to_bytes(
"9ce18b1adecb33f891ca36664da676e12c772cc193778aac9a137b8dc5834b9b"
),
reason="Content too long",
status="absent",
)
skipped_contents: Tuple[SkippedContent, ...] = (skipped_content, skipped_content2)
directory5 = Directory(
- id=hash_to_bytes("4b825dc642cb6eb9a060e54bf8d69288fbee4904"), entries=(),
+ id=hash_to_bytes("4b825dc642cb6eb9a060e54bf8d69288fbee4904"),
+ entries=(),
)
directory = Directory(
id=hash_to_bytes("5256e856a0a0898966d6ba14feb4388b8b82d302"),
entries=tuple(
[
DirectoryEntry(
name=b"foo",
type="file",
target=content.sha1_git,
perms=from_disk.DentryPerms.content,
),
DirectoryEntry(
name=b"bar\xc3",
type="dir",
target=directory5.id,
perms=from_disk.DentryPerms.directory,
),
],
),
)
directory2 = Directory(
id=hash_to_bytes("8505808532953da7d2581741f01b29c04b1cb9ab"),
entries=tuple(
[
DirectoryEntry(
name=b"oof",
type="file",
target=content2.sha1_git,
perms=from_disk.DentryPerms.content,
)
],
),
)
directory3 = Directory(
id=hash_to_bytes("13089e6e544f78df7c9a40a3059050d10dee686a"),
entries=tuple(
[
DirectoryEntry(
name=b"foo",
type="file",
target=content.sha1_git,
perms=from_disk.DentryPerms.content,
),
DirectoryEntry(
name=b"subdir",
type="dir",
target=directory.id,
perms=from_disk.DentryPerms.directory,
),
DirectoryEntry(
name=b"hello",
type="file",
target=content2.sha1_git,
perms=from_disk.DentryPerms.content,
),
],
),
)
directory4 = Directory(
id=hash_to_bytes("cd5dfd9c09d9e99ed123bc7937a0d5fddc3cd531"),
entries=tuple(
[
DirectoryEntry(
name=b"subdir1",
type="dir",
target=directory3.id,
perms=from_disk.DentryPerms.directory,
)
],
),
)
directories: Tuple[Directory, ...] = (
directory2,
directory,
directory3,
directory4,
directory5,
)
revision = Revision(
id=hash_to_bytes("01a7114f36fddd5ef2511b2cadda237a68adbb12"),
message=b"hello",
author=Person(
name=b"Nicolas Dandrimont",
email=b"nicolas@example.com",
fullname=b"Nicolas Dandrimont ",
),
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1234567890, microseconds=0),
offset_bytes=b"+0200",
),
committer=Person(
name=b"St\xc3fano Zacchiroli",
email=b"stefano@example.com",
fullname=b"St\xc3fano Zacchiroli ",
),
committer_date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1123456789, microseconds=0),
offset_bytes=b"+0200",
),
parents=(),
type=RevisionType.GIT,
directory=directory.id,
metadata={
- "checksums": {"sha1": "tarball-sha1", "sha256": "tarball-sha256",},
+ "checksums": {
+ "sha1": "tarball-sha1",
+ "sha256": "tarball-sha256",
+ },
"signed-off-by": "some-dude",
},
extra_headers=(
(b"gpgsig", b"test123"),
(b"mergetag", b"foo\\bar"),
(b"mergetag", b"\x22\xaf\x89\x80\x01\x00"),
),
synthetic=True,
)
revision2 = Revision(
id=hash_to_bytes("a646dd94c912829659b22a1e7e143d2fa5ebde1b"),
message=b"hello again",
author=Person(
name=b"Roberto Dicosmo",
email=b"roberto@example.com",
fullname=b"Roberto Dicosmo ",
),
date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1234567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
committer=Person(
- name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ",
+ name=b"tony",
+ email=b"ar@dumont.fr",
+ fullname=b"tony ",
),
committer_date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1123456789, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1123456789,
+ microseconds=220000,
+ ),
offset_bytes=b"+0000",
),
parents=tuple([revision.id]),
type=RevisionType.GIT,
directory=directory2.id,
metadata=None,
extra_headers=(),
synthetic=False,
)
revision3 = Revision(
id=hash_to_bytes("beb2844dff30658e27573cb46eb55980e974b391"),
message=b"a simple revision with no parents this time",
author=Person(
name=b"Roberto Dicosmo",
email=b"roberto@example.com",
fullname=b"Roberto Dicosmo ",
),
date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1234567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
committer=Person(
- name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ",
+ name=b"tony",
+ email=b"ar@dumont.fr",
+ fullname=b"tony ",
),
committer_date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1127351742, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1127351742,
+ microseconds=220000,
+ ),
offset_bytes=b"+0000",
),
parents=tuple([revision.id, revision2.id]),
type=RevisionType.GIT,
directory=directory2.id,
metadata=None,
extra_headers=(),
synthetic=True,
)
revision4 = Revision(
id=hash_to_bytes("ae860aec43700c7f5a295e2ef47e2ae41b535dfe"),
message=b"parent of self.revision2",
author=Person(
- name=b"me", email=b"me@soft.heri", fullname=b"me ",
+ name=b"me",
+ email=b"me@soft.heri",
+ fullname=b"me ",
),
date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1234567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
committer=Person(
name=b"committer-dude",
email=b"committer@dude.com",
fullname=b"committer-dude ",
),
committer_date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1244567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1244567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
parents=tuple([revision3.id]),
type=RevisionType.GIT,
directory=directory.id,
metadata=None,
extra_headers=(),
synthetic=False,
)
git_revisions: Tuple[Revision, ...] = (revision, revision2, revision3, revision4)
hg_revision = Revision(
id=hash_to_bytes("951c9503541e7beaf002d7aebf2abd1629084c68"),
message=b"hello",
author=Person(
name=b"Nicolas Dandrimont",
email=b"nicolas@example.com",
fullname=b"Nicolas Dandrimont ",
),
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1234567890, microseconds=0),
offset_bytes=b"+0200",
),
committer=Person(
name=b"St\xc3fano Zacchiroli",
email=b"stefano@example.com",
fullname=b"St\xc3fano Zacchiroli ",
),
committer_date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1123456789, microseconds=0),
offset_bytes=b"+0200",
),
parents=(),
type=RevisionType.MERCURIAL,
directory=directory.id,
metadata={
- "checksums": {"sha1": "tarball-sha1", "sha256": "tarball-sha256",},
+ "checksums": {
+ "sha1": "tarball-sha1",
+ "sha256": "tarball-sha256",
+ },
"signed-off-by": "some-dude",
"node": "a316dfb434af2b451c1f393496b7eaeda343f543",
},
extra_headers=(),
synthetic=True,
)
hg_revision2 = Revision(
id=hash_to_bytes("df4afb063236300eb13b96a0d7fff03f7b7cbbaf"),
message=b"hello again",
author=Person(
name=b"Roberto Dicosmo",
email=b"roberto@example.com",
fullname=b"Roberto Dicosmo ",
),
date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1234567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
committer=Person(
- name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ",
+ name=b"tony",
+ email=b"ar@dumont.fr",
+ fullname=b"tony ",
),
committer_date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1123456789, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1123456789,
+ microseconds=220000,
+ ),
offset_bytes=b"+0000",
),
parents=tuple([hg_revision.id]),
type=RevisionType.MERCURIAL,
directory=directory2.id,
metadata=None,
extra_headers=(
(b"node", hash_to_bytes("fa1b7c84a9b40605b67653700f268349a6d6aca1")),
),
synthetic=False,
)
hg_revision3 = Revision(
id=hash_to_bytes("84d8e7081b47ebb88cad9fa1f25de5f330872a37"),
message=b"a simple revision with no parents this time",
author=Person(
name=b"Roberto Dicosmo",
email=b"roberto@example.com",
fullname=b"Roberto Dicosmo ",
),
date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1234567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
committer=Person(
- name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ",
+ name=b"tony",
+ email=b"ar@dumont.fr",
+ fullname=b"tony ",
),
committer_date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1127351742, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1127351742,
+ microseconds=220000,
+ ),
offset_bytes=b"+0000",
),
parents=tuple([hg_revision.id, hg_revision2.id]),
type=RevisionType.MERCURIAL,
directory=directory2.id,
metadata=None,
extra_headers=(
(b"node", hash_to_bytes("7f294a01c49065a90b3fe8b4ad49f08ce9656ef6")),
),
synthetic=True,
)
hg_revision4 = Revision(
id=hash_to_bytes("4683324ba26dfe941a72cc7552e86eaaf7c27fe3"),
message=b"parent of self.revision2",
author=Person(
- name=b"me", email=b"me@soft.heri", fullname=b"me ",
+ name=b"me",
+ email=b"me@soft.heri",
+ fullname=b"me ",
),
date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1234567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
committer=Person(
name=b"committer-dude",
email=b"committer@dude.com",
fullname=b"committer-dude ",
),
committer_date=TimestampWithTimezone(
- timestamp=Timestamp(seconds=1244567843, microseconds=220000,),
+ timestamp=Timestamp(
+ seconds=1244567843,
+ microseconds=220000,
+ ),
offset_bytes=b"-1200",
),
parents=tuple([hg_revision3.id]),
type=RevisionType.MERCURIAL,
directory=directory.id,
metadata=None,
extra_headers=(
(b"node", hash_to_bytes("f4160af0485c85823d9e829bae2c00b00a2e6297")),
),
synthetic=False,
)
hg_revisions: Tuple[Revision, ...] = (
hg_revision,
hg_revision2,
hg_revision3,
hg_revision4,
)
revisions: Tuple[Revision, ...] = git_revisions + hg_revisions
origins: Tuple[Origin, ...] = (
Origin(url="https://github.com/user1/repo1"),
Origin(url="https://github.com/user2/repo1"),
Origin(url="https://github.com/user3/repo1"),
Origin(url="https://gitlab.com/user1/repo1"),
Origin(url="https://gitlab.com/user2/repo1"),
Origin(url="https://forge.softwareheritage.org/source/repo1"),
Origin(url="https://example.рф/🏛️.txt"),
)
origin, origin2 = origins[:2]
metadata_authority = MetadataAuthority(
- type=MetadataAuthorityType.DEPOSIT_CLIENT, url="http://hal.inria.example.com/",
+ type=MetadataAuthorityType.DEPOSIT_CLIENT,
+ url="http://hal.inria.example.com/",
)
metadata_authority2 = MetadataAuthority(
- type=MetadataAuthorityType.REGISTRY, url="http://wikidata.example.com/",
+ type=MetadataAuthorityType.REGISTRY,
+ url="http://wikidata.example.com/",
)
authorities: Tuple[MetadataAuthority, ...] = (
metadata_authority,
metadata_authority2,
)
- metadata_fetcher = MetadataFetcher(name="swh-deposit", version="0.0.1",)
- metadata_fetcher2 = MetadataFetcher(name="swh-example", version="0.0.1",)
+ metadata_fetcher = MetadataFetcher(
+ name="swh-deposit",
+ version="0.0.1",
+ )
+ metadata_fetcher2 = MetadataFetcher(
+ name="swh-example",
+ version="0.0.1",
+ )
fetchers: Tuple[MetadataFetcher, ...] = (metadata_fetcher, metadata_fetcher2)
date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc)
date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc)
date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc)
type_visit1 = "git"
type_visit2 = "hg"
type_visit3 = "deb"
origin_visit = OriginVisit(
- origin=origin.url, visit=1, date=date_visit1, type=type_visit1,
+ origin=origin.url,
+ visit=1,
+ date=date_visit1,
+ type=type_visit1,
)
origin_visit2 = OriginVisit(
- origin=origin.url, visit=2, date=date_visit2, type=type_visit1,
+ origin=origin.url,
+ visit=2,
+ date=date_visit2,
+ type=type_visit1,
)
origin_visit3 = OriginVisit(
- origin=origin2.url, visit=1, date=date_visit1, type=type_visit2,
+ origin=origin2.url,
+ visit=1,
+ date=date_visit1,
+ type=type_visit2,
)
origin_visits: Tuple[OriginVisit, ...] = (
origin_visit,
origin_visit2,
origin_visit3,
)
release = Release(
id=hash_to_bytes("f7f222093a18ec60d781070abec4a630c850b837"),
name=b"v0.0.1",
author=Person(
- name=b"olasd", email=b"nic@olasd.fr", fullname=b"olasd ",
+ name=b"olasd",
+ email=b"nic@olasd.fr",
+ fullname=b"olasd ",
),
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1234567890, microseconds=0),
offset_bytes=b"+0042",
),
target=revision.id,
target_type=ObjectType.REVISION,
message=b"synthetic release",
synthetic=True,
)
release2 = Release(
id=hash_to_bytes("db81a26783a3f4a9db07b4759ffc37621f159bb2"),
name=b"v0.0.2",
author=Person(
- name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ",
+ name=b"tony",
+ email=b"ar@dumont.fr",
+ fullname=b"tony ",
),
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1634366813, microseconds=0),
offset_bytes=b"-0200",
),
target=revision2.id,
target_type=ObjectType.REVISION,
message=b"v0.0.2\nMisc performance improvements + bug fixes",
synthetic=False,
)
release3 = Release(
id=hash_to_bytes("1c5d42e603ce2eea44917fadca76c78bad76aeb9"),
name=b"v0.0.2",
author=Person(
name=b"tony",
email=b"tony@ardumont.fr",
fullname=b"tony ",
),
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=1634366813, microseconds=0),
offset_bytes=b"-0200",
),
target=revision3.id,
target_type=ObjectType.REVISION,
message=b"yet another synthetic release",
synthetic=True,
)
releases: Tuple[Release, ...] = (release, release2, release3)
snapshot = Snapshot(
id=hash_to_bytes("9b922e6d8d5b803c1582aabe5525b7b91150788e"),
branches={
b"master": SnapshotBranch(
- target=revision.id, target_type=TargetType.REVISION,
+ target=revision.id,
+ target_type=TargetType.REVISION,
),
},
)
empty_snapshot = Snapshot(
- id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), branches={},
+ id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"),
+ branches={},
)
complete_snapshot = Snapshot(
id=hash_to_bytes("db99fda25b43dc5cd90625ee4b0744751799c917"),
branches={
b"directory": SnapshotBranch(
- target=directory.id, target_type=TargetType.DIRECTORY,
+ target=directory.id,
+ target_type=TargetType.DIRECTORY,
),
b"directory2": SnapshotBranch(
- target=directory2.id, target_type=TargetType.DIRECTORY,
+ target=directory2.id,
+ target_type=TargetType.DIRECTORY,
),
b"content": SnapshotBranch(
- target=content.sha1_git, target_type=TargetType.CONTENT,
+ target=content.sha1_git,
+ target_type=TargetType.CONTENT,
+ ),
+ b"alias": SnapshotBranch(
+ target=b"revision",
+ target_type=TargetType.ALIAS,
),
- b"alias": SnapshotBranch(target=b"revision", target_type=TargetType.ALIAS,),
b"revision": SnapshotBranch(
- target=revision.id, target_type=TargetType.REVISION,
+ target=revision.id,
+ target_type=TargetType.REVISION,
),
b"release": SnapshotBranch(
- target=release.id, target_type=TargetType.RELEASE,
+ target=release.id,
+ target_type=TargetType.RELEASE,
),
b"snapshot": SnapshotBranch(
- target=empty_snapshot.id, target_type=TargetType.SNAPSHOT,
+ target=empty_snapshot.id,
+ target_type=TargetType.SNAPSHOT,
),
b"dangling": None,
},
)
snapshots: Tuple[Snapshot, ...] = (snapshot, empty_snapshot, complete_snapshot)
content_metadata1 = RawExtrinsicMetadata(
target=ExtendedSWHID(
object_type=ExtendedObjectType.CONTENT, object_id=content.sha1_git
),
origin=origin.url,
discovery_date=datetime.datetime(
2015, 1, 1, 21, 0, 0, tzinfo=datetime.timezone.utc
),
authority=metadata_authority,
fetcher=metadata_fetcher,
format="json",
metadata=b'{"foo": "bar"}',
)
content_metadata2 = RawExtrinsicMetadata(
target=ExtendedSWHID(
object_type=ExtendedObjectType.CONTENT, object_id=content.sha1_git
),
origin=origin2.url,
discovery_date=datetime.datetime(
2017, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc
),
authority=metadata_authority,
fetcher=metadata_fetcher,
format="yaml",
metadata=b"foo: bar",
)
content_metadata3 = RawExtrinsicMetadata(
target=ExtendedSWHID(
object_type=ExtendedObjectType.CONTENT, object_id=content.sha1_git
),
discovery_date=datetime.datetime(
2017, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc
),
authority=attr.evolve(metadata_authority2, metadata=None),
fetcher=attr.evolve(metadata_fetcher2, metadata=None),
format="yaml",
metadata=b"foo: bar",
origin=origin.url,
visit=42,
snapshot=snapshot.swhid(),
release=release.swhid(),
revision=revision.swhid(),
directory=directory.swhid(),
path=b"/foo/bar",
)
content_metadata: Tuple[RawExtrinsicMetadata, ...] = (
content_metadata1,
content_metadata2,
content_metadata3,
)
origin_metadata1 = RawExtrinsicMetadata(
target=Origin(origin.url).swhid(),
discovery_date=datetime.datetime(
2015, 1, 1, 21, 0, 0, tzinfo=datetime.timezone.utc
),
authority=attr.evolve(metadata_authority, metadata=None),
fetcher=attr.evolve(metadata_fetcher, metadata=None),
format="json",
metadata=b'{"foo": "bar"}',
)
origin_metadata2 = RawExtrinsicMetadata(
target=Origin(origin.url).swhid(),
discovery_date=datetime.datetime(
2017, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc
),
authority=attr.evolve(metadata_authority, metadata=None),
fetcher=attr.evolve(metadata_fetcher, metadata=None),
format="yaml",
metadata=b"foo: bar",
)
origin_metadata3 = RawExtrinsicMetadata(
target=Origin(origin.url).swhid(),
discovery_date=datetime.datetime(
2017, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc
),
authority=attr.evolve(metadata_authority2, metadata=None),
fetcher=attr.evolve(metadata_fetcher2, metadata=None),
format="yaml",
metadata=b"foo: bar",
)
origin_metadata: Tuple[RawExtrinsicMetadata, ...] = (
origin_metadata1,
origin_metadata2,
origin_metadata3,
)
extid1 = ExtID(
target=CoreSWHID(object_type=SwhidObjectType.REVISION, object_id=revision.id),
extid_type="git",
extid=revision.id,
)
extid2 = ExtID(
target=CoreSWHID(
object_type=SwhidObjectType.REVISION, object_id=hg_revision.id
),
extid_type="mercurial",
extid=hash_to_bytes("a316dfb434af2b451c1f393496b7eaeda343f543"),
)
extid3 = ExtID(
target=CoreSWHID(object_type=SwhidObjectType.DIRECTORY, object_id=directory.id),
extid_type="directory",
extid=b"something",
)
extid4 = ExtID(
target=CoreSWHID(
object_type=SwhidObjectType.DIRECTORY, object_id=directory2.id
),
extid_type="directory",
extid=b"something",
extid_version=2,
)
extids: Tuple[ExtID, ...] = (
extid1,
extid2,
extid3,
extid4,
)
diff --git a/swh/storage/tests/storage_tests.py b/swh/storage/tests/storage_tests.py
index 9d830828..05292579 100644
--- a/swh/storage/tests/storage_tests.py
+++ b/swh/storage/tests/storage_tests.py
@@ -1,5323 +1,5547 @@
# Copyright (C) 2015-2022 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from collections import defaultdict
import datetime
from datetime import timedelta
import inspect
import itertools
import math
import random
from typing import Any, ClassVar, Dict, Iterator, Optional
from unittest.mock import MagicMock
import attr
from hypothesis import HealthCheck, given, settings, strategies
import pytest
from swh.core.api import RemoteException
from swh.core.api.classes import stream_results
from swh.model import from_disk, hypothesis_strategies
from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes
from swh.model.model import (
Content,
Directory,
ExtID,
Origin,
OriginVisit,
OriginVisitStatus,
Person,
RawExtrinsicMetadata,
Revision,
RevisionType,
SkippedContent,
Snapshot,
SnapshotBranch,
TargetType,
Timestamp,
TimestampWithTimezone,
)
from swh.model.swhids import CoreSWHID, ObjectType
from swh.storage import get_storage
from swh.storage.cassandra.storage import CassandraStorage
from swh.storage.common import origin_url_to_sha1 as sha1
from swh.storage.exc import HashCollision, StorageArgumentException
from swh.storage.in_memory import InMemoryStorage
from swh.storage.interface import (
ListOrder,
OriginVisitWithStatuses,
PagedResult,
StorageInterface,
)
from swh.storage.tests.conftest import function_scoped_fixture_check
from swh.storage.utils import (
content_hex_hashes,
now,
remove_keys,
round_to_milliseconds,
)
def transform_entries(
storage: StorageInterface, dir_: Directory, *, prefix: bytes = b""
) -> Iterator[Dict[str, Any]]:
"""Iterate through a directory's entries, and yields the items 'directory_ls' is
- expected to return; including content metadata for file entries."""
+ expected to return; including content metadata for file entries."""
for ent in dir_.entries:
if ent.type == "dir":
yield {
"dir_id": dir_.id,
"type": ent.type,
"target": ent.target,
"name": prefix + ent.name,
"perms": ent.perms,
"status": None,
"sha1": None,
"sha1_git": None,
"sha256": None,
"length": None,
}
elif ent.type == "file":
contents = storage.content_find({"sha1_git": ent.target})
assert contents
ent_dict = contents[0].to_dict()
for key in ["ctime", "blake2s256"]:
ent_dict.pop(key, None)
ent_dict.update(
{
"dir_id": dir_.id,
"type": ent.type,
"target": ent.target,
"name": prefix + ent.name,
"perms": ent.perms,
}
)
yield ent_dict
def assert_contents_ok(
expected_contents, actual_contents, keys_to_check={"sha1", "data"}
):
- """Assert that a given list of contents matches on a given set of keys.
-
- """
+ """Assert that a given list of contents matches on a given set of keys."""
for k in keys_to_check:
expected_list = set([c.get(k) for c in expected_contents])
actual_list = set([c.get(k) for c in actual_contents])
assert actual_list == expected_list, k
class LazyContent(Content):
def with_data(self):
return Content.from_dict({**self.to_dict(), "data": b"42\n"})
class TestStorage:
"""Main class for Storage testing.
This class is used as-is to test local storage (see TestLocalStorage
below) and remote storage (see TestRemoteStorage in
test_remote_storage.py.
We need to have the two classes inherit from this base class
separately to avoid nosetests running the tests from the base
class twice.
"""
maxDiff = None # type: ClassVar[Optional[int]]
def test_types(self, swh_storage_backend_config):
"""Checks all methods of StorageInterface are implemented by this
backend, and that they have the same signature."""
# Create an instance of the protocol (which cannot be instantiated
# directly, so this creates a subclass, then instantiates it)
interface = type("_", (StorageInterface,), {})()
storage = get_storage(**swh_storage_backend_config)
assert "content_add" in dir(interface)
missing_methods = []
for meth_name in dir(interface):
if meth_name.startswith("_"):
continue
interface_meth = getattr(interface, meth_name)
try:
concrete_meth = getattr(storage, meth_name)
except AttributeError:
if not getattr(interface_meth, "deprecated_endpoint", False):
# The backend is missing a (non-deprecated) endpoint
missing_methods.append(meth_name)
continue
expected_signature = inspect.signature(interface_meth)
actual_signature = inspect.signature(concrete_meth)
assert expected_signature == actual_signature, meth_name
assert missing_methods == []
# If all the assertions above succeed, then this one should too.
# But there's no harm in double-checking.
# And we could replace the assertions above by this one, but unlike
# the assertions above, it doesn't explain what is missing.
assert isinstance(storage, StorageInterface)
def test_check_config(self, swh_storage):
assert swh_storage.check_config(check_write=True)
assert swh_storage.check_config(check_write=False)
def test_content_add(self, swh_storage, sample_data):
cont = sample_data.content
insertion_start_time = now()
actual_result = swh_storage.content_add([cont])
insertion_end_time = now()
assert actual_result == {
"content:add": 1,
"content:add:bytes": cont.length,
}
assert swh_storage.content_get_data(cont.sha1) == cont.data
expected_cont = attr.evolve(cont, data=None)
contents = [
obj
for (obj_type, obj) in swh_storage.journal_writer.journal.objects
if obj_type == "content"
]
assert len(contents) == 1
for obj in contents:
assert insertion_start_time <= obj.ctime
assert obj.ctime <= insertion_end_time
assert obj == expected_cont
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
assert swh_storage.stat_counters()["content"] == 1
def test_content_add_from_lazy_content(self, swh_storage, sample_data):
cont = sample_data.content
lazy_content = LazyContent.from_dict(cont.to_dict())
insertion_start_time = now()
actual_result = swh_storage.content_add([lazy_content])
insertion_end_time = now()
assert actual_result == {
"content:add": 1,
"content:add:bytes": cont.length,
}
# the fact that we retrieve the content object from the storage with
# the correct 'data' field ensures it has been 'called'
assert swh_storage.content_get_data(cont.sha1) == cont.data
expected_cont = attr.evolve(lazy_content, data=None, ctime=None)
contents = [
obj
for (obj_type, obj) in swh_storage.journal_writer.journal.objects
if obj_type == "content"
]
assert len(contents) == 1
for obj in contents:
assert insertion_start_time <= obj.ctime
assert obj.ctime <= insertion_end_time
assert attr.evolve(obj, ctime=None).to_dict() == expected_cont.to_dict()
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
assert swh_storage.stat_counters()["content"] == 1
def test_content_get_data_missing(self, swh_storage, sample_data):
cont, cont2 = sample_data.contents[:2]
swh_storage.content_add([cont])
# Query a single missing content
actual_content_data = swh_storage.content_get_data(cont2.sha1)
assert actual_content_data is None
# Check content_get does not abort after finding a missing content
actual_content_data = swh_storage.content_get_data(cont.sha1)
assert actual_content_data == cont.data
actual_content_data = swh_storage.content_get_data(cont2.sha1)
assert actual_content_data is None
def test_content_add_different_input(self, swh_storage, sample_data):
cont, cont2 = sample_data.contents[:2]
actual_result = swh_storage.content_add([cont, cont2])
assert actual_result == {
"content:add": 2,
"content:add:bytes": cont.length + cont2.length,
}
def test_content_add_twice(self, swh_storage, sample_data):
cont, cont2 = sample_data.contents[:2]
actual_result = swh_storage.content_add([cont])
assert actual_result == {
"content:add": 1,
"content:add:bytes": cont.length,
}
assert len(swh_storage.journal_writer.journal.objects) == 1
actual_result = swh_storage.content_add([cont, cont2])
assert actual_result == {
"content:add": 1,
"content:add:bytes": cont2.length,
}
assert 2 <= len(swh_storage.journal_writer.journal.objects) <= 3
assert len(swh_storage.content_find(cont.to_dict())) == 1
assert len(swh_storage.content_find(cont2.to_dict())) == 1
def test_content_add_collision(self, swh_storage, sample_data):
cont1 = sample_data.content
# create (corrupted) content with same sha1{,_git} but != sha256
sha256_array = bytearray(cont1.sha256)
sha256_array[0] += 1
cont1b = attr.evolve(cont1, sha256=bytes(sha256_array))
with pytest.raises(HashCollision) as cm:
swh_storage.content_add([cont1, cont1b])
exc = cm.value
actual_algo = exc.algo
assert actual_algo in ["sha1", "sha1_git"]
actual_id = exc.hash_id
assert actual_id == getattr(cont1, actual_algo).hex()
collisions = exc.args[2]
assert len(collisions) == 2
assert collisions == [
content_hex_hashes(cont1.hashes()),
content_hex_hashes(cont1b.hashes()),
]
assert exc.colliding_content_hashes() == [
cont1.hashes(),
cont1b.hashes(),
]
def test_content_add_duplicate(self, swh_storage, sample_data):
cont = sample_data.content
swh_storage.content_add([cont, cont])
assert swh_storage.content_get_data(cont.sha1) == cont.data
def test_content_update(self, swh_storage, sample_data):
cont1 = sample_data.content
if hasattr(swh_storage, "journal_writer"):
swh_storage.journal_writer.journal = None # TODO, not supported
swh_storage.content_add([cont1])
# alter the sha1_git for example
cont1b = attr.evolve(
cont1, sha1_git=hash_to_bytes("3a60a5275d0333bf13468e8b3dcab90f4046e654")
)
swh_storage.content_update([cont1b.to_dict()], keys=["sha1_git"])
actual_contents = swh_storage.content_get([cont1.sha1])
expected_content = attr.evolve(cont1b, data=None)
assert actual_contents == [expected_content]
def test_content_add_metadata(self, swh_storage, sample_data):
cont = attr.evolve(sample_data.content, data=None, ctime=now())
actual_result = swh_storage.content_add_metadata([cont])
assert actual_result == {
"content:add": 1,
}
expected_cont = cont
assert swh_storage.content_get([cont.sha1]) == [expected_cont]
contents = [
obj
for (obj_type, obj) in swh_storage.journal_writer.journal.objects
if obj_type == "content"
]
assert len(contents) == 1
for obj in contents:
obj = attr.evolve(obj, ctime=None)
assert obj == cont
def test_content_add_metadata_different_input(self, swh_storage, sample_data):
contents = sample_data.contents[:2]
cont = attr.evolve(contents[0], data=None, ctime=now())
cont2 = attr.evolve(contents[1], data=None, ctime=now())
actual_result = swh_storage.content_add_metadata([cont, cont2])
assert actual_result == {
"content:add": 2,
}
def test_content_add_metadata_collision(self, swh_storage, sample_data):
cont1 = attr.evolve(sample_data.content, data=None, ctime=now())
# create (corrupted) content with same sha1{,_git} but != sha256
sha1_git_array = bytearray(cont1.sha256)
sha1_git_array[0] += 1
cont1b = attr.evolve(cont1, sha256=bytes(sha1_git_array))
with pytest.raises(HashCollision) as cm:
swh_storage.content_add_metadata([cont1, cont1b])
exc = cm.value
actual_algo = exc.algo
assert actual_algo in ["sha1", "sha1_git", "blake2s256"]
actual_id = exc.hash_id
assert actual_id == getattr(cont1, actual_algo).hex()
collisions = exc.args[2]
assert len(collisions) == 2
assert collisions == [
content_hex_hashes(cont1.hashes()),
content_hex_hashes(cont1b.hashes()),
]
assert exc.colliding_content_hashes() == [
cont1.hashes(),
cont1b.hashes(),
]
def test_content_add_objstorage_first(self, swh_storage, sample_data):
"""Tests the objstorage is written to before the DB and journal"""
cont = sample_data.content
swh_storage.objstorage.content_add = MagicMock(side_effect=Exception("Oops"))
# Try to add, but the objstorage crashes
try:
swh_storage.content_add([cont])
except Exception:
pass
# The DB must be written to after the objstorage, so the DB should be
# unchanged if the objstorage crashed
assert swh_storage.content_get_data(cont.sha1) is None
# The journal too
assert list(swh_storage.journal_writer.journal.objects) == []
def test_skipped_content_add(self, swh_storage, sample_data):
contents = sample_data.skipped_contents[:2]
cont = contents[0]
cont2 = attr.evolve(contents[1], blake2s256=None)
contents_dict = [c.to_dict() for c in [cont, cont2]]
missing = list(swh_storage.skipped_content_missing(contents_dict))
assert missing == [cont.hashes(), cont2.hashes()]
actual_result = swh_storage.skipped_content_add([cont, cont, cont2])
assert 2 <= actual_result.pop("skipped_content:add") <= 3
assert actual_result == {}
missing = list(swh_storage.skipped_content_missing(contents_dict))
assert missing == []
def test_skipped_content_add_missing_hashes(self, swh_storage, sample_data):
cont, cont2 = [
attr.evolve(c, sha1_git=None) for c in sample_data.skipped_contents[:2]
]
contents_dict = [c.to_dict() for c in [cont, cont2]]
missing = list(swh_storage.skipped_content_missing(contents_dict))
assert len(missing) == 2
actual_result = swh_storage.skipped_content_add([cont, cont, cont2])
assert 2 <= actual_result.pop("skipped_content:add") <= 3
assert actual_result == {}
missing = list(swh_storage.skipped_content_missing(contents_dict))
assert missing == []
def test_skipped_content_missing_partial_hash(self, swh_storage, sample_data):
cont = sample_data.skipped_content
cont2 = attr.evolve(cont, sha1_git=None)
contents_dict = [c.to_dict() for c in [cont, cont2]]
missing = list(swh_storage.skipped_content_missing(contents_dict))
assert len(missing) == 2
actual_result = swh_storage.skipped_content_add([cont])
assert actual_result.pop("skipped_content:add") == 1
assert actual_result == {}
missing = list(swh_storage.skipped_content_missing(contents_dict))
assert missing == [cont2.hashes()]
@pytest.mark.property_based
@settings(
deadline=None, # this test is very slow
suppress_health_check=function_scoped_fixture_check,
)
@given(
strategies.sets(
elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]),
min_size=0,
)
)
def test_content_missing(self, swh_storage, sample_data, algos):
algos |= {"sha1"}
content, missing_content = [sample_data.content2, sample_data.skipped_content]
swh_storage.content_add([content])
test_contents = [content.to_dict()]
missing_per_hash = defaultdict(list)
for i in range(256):
test_content = missing_content.to_dict()
for hash in algos:
test_content[hash] = bytes([i]) + test_content[hash][1:]
missing_per_hash[hash].append(test_content[hash])
test_contents.append(test_content)
assert set(swh_storage.content_missing(test_contents)) == set(
missing_per_hash["sha1"]
)
for hash in algos:
assert set(
swh_storage.content_missing(test_contents, key_hash=hash)
) == set(missing_per_hash[hash])
@pytest.mark.property_based
- @settings(suppress_health_check=function_scoped_fixture_check,)
+ @settings(
+ suppress_health_check=function_scoped_fixture_check,
+ )
@given(
strategies.sets(
elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]),
min_size=0,
)
)
def test_content_missing_unknown_algo(self, swh_storage, sample_data, algos):
algos |= {"sha1"}
content, missing_content = [sample_data.content2, sample_data.skipped_content]
swh_storage.content_add([content])
test_contents = [content.to_dict()]
missing_per_hash = defaultdict(list)
for i in range(16):
test_content = missing_content.to_dict()
for hash in algos:
test_content[hash] = bytes([i]) + test_content[hash][1:]
missing_per_hash[hash].append(test_content[hash])
test_content["nonexisting_algo"] = b"\x00"
test_contents.append(test_content)
assert set(swh_storage.content_missing(test_contents)) == set(
missing_per_hash["sha1"]
)
for hash in algos:
assert set(
swh_storage.content_missing(test_contents, key_hash=hash)
) == set(missing_per_hash[hash])
def test_content_missing_per_sha1(self, swh_storage, sample_data):
# given
cont = sample_data.content
cont2 = sample_data.content2
missing_cont = sample_data.skipped_content
missing_cont2 = sample_data.skipped_content2
swh_storage.content_add([cont, cont2])
# when
gen = swh_storage.content_missing_per_sha1(
[cont.sha1, missing_cont.sha1, cont2.sha1, missing_cont2.sha1]
)
# then
assert list(gen) == [missing_cont.sha1, missing_cont2.sha1]
def test_content_missing_per_sha1_git(self, swh_storage, sample_data):
cont, cont2 = sample_data.contents[:2]
missing_cont = sample_data.skipped_content
missing_cont2 = sample_data.skipped_content2
swh_storage.content_add([cont, cont2])
contents = [
cont.sha1_git,
cont2.sha1_git,
missing_cont.sha1_git,
missing_cont2.sha1_git,
]
missing_contents = swh_storage.content_missing_per_sha1_git(contents)
assert list(missing_contents) == [missing_cont.sha1_git, missing_cont2.sha1_git]
missing_contents = swh_storage.content_missing_per_sha1_git([])
assert list(missing_contents) == []
def test_content_get_partition(self, swh_storage, swh_contents):
"""content_get_partition paginates results if limit exceeded"""
expected_contents = [
attr.evolve(c, data=None) for c in swh_contents if c.status != "absent"
]
actual_contents = []
for i in range(16):
actual_result = swh_storage.content_get_partition(i, 16)
assert actual_result.next_page_token is None
actual_contents.extend(actual_result.results)
assert len(actual_contents) == len(expected_contents)
for content in actual_contents:
assert content in expected_contents
assert content.ctime is None
def test_content_get_partition_full(self, swh_storage, swh_contents):
- """content_get_partition for a single partition returns all available contents
-
- """
+ """content_get_partition for a single partition returns all available contents"""
expected_contents = [
attr.evolve(c, data=None) for c in swh_contents if c.status != "absent"
]
actual_result = swh_storage.content_get_partition(0, 1)
assert actual_result.next_page_token is None
actual_contents = actual_result.results
assert len(actual_contents) == len(expected_contents)
for content in actual_contents:
assert content in expected_contents
def test_content_get_partition_empty(self, swh_storage, swh_contents):
"""content_get_partition when at least one of the partitions is empty"""
expected_contents = {
cont.sha1 for cont in swh_contents if cont.status != "absent"
}
# nb_partitions = smallest power of 2 such that at least one of
# the partitions is empty
nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1)
seen_sha1s = []
for i in range(nb_partitions):
actual_result = swh_storage.content_get_partition(
i, nb_partitions, limit=len(swh_contents) + 1
)
for content in actual_result.results:
seen_sha1s.append(content.sha1)
# Limit is higher than the max number of results
assert actual_result.next_page_token is None
assert set(seen_sha1s) == expected_contents
def test_content_get_partition_limit_none(self, swh_storage):
"""content_get_partition call with wrong limit input should fail"""
with pytest.raises(StorageArgumentException, match="limit should not be None"):
swh_storage.content_get_partition(1, 16, limit=None)
def test_content_get_partition_pagination_generate(self, swh_storage, swh_contents):
"""content_get_partition returns contents within range provided"""
expected_contents = [
attr.evolve(c, data=None) for c in swh_contents if c.status != "absent"
]
# retrieve contents
actual_contents = []
for i in range(4):
page_token = None
while True:
actual_result = swh_storage.content_get_partition(
i, 4, limit=3, page_token=page_token
)
actual_contents.extend(actual_result.results)
page_token = actual_result.next_page_token
if page_token is None:
break
assert len(actual_contents) == len(expected_contents)
for content in actual_contents:
assert content in expected_contents
@pytest.mark.parametrize("algo", sorted(DEFAULT_ALGORITHMS))
def test_content_get(self, swh_storage, sample_data, algo):
cont1, cont2 = sample_data.contents[:2]
swh_storage.content_add([cont1, cont2])
actual_contents = swh_storage.content_get(
[getattr(cont1, algo), getattr(cont2, algo)], algo
)
# we only retrieve the metadata so no data nor ctime within
expected_contents = [attr.evolve(c, data=None) for c in [cont1, cont2]]
assert actual_contents == expected_contents
for content in actual_contents:
assert content.ctime is None
@pytest.mark.parametrize("algo", sorted(DEFAULT_ALGORITHMS))
def test_content_get_missing(self, swh_storage, sample_data, algo):
cont1, cont2 = sample_data.contents[:2]
assert cont1.sha1 != cont2.sha1
missing_cont = sample_data.skipped_content
swh_storage.content_add([cont1, cont2])
actual_contents = swh_storage.content_get(
[getattr(cont1, algo), getattr(cont2, algo), getattr(missing_cont, algo)],
algo,
)
expected_contents = [
attr.evolve(c, data=None) if c else None for c in [cont1, cont2, None]
]
assert actual_contents == expected_contents
def test_content_get_random(self, swh_storage, sample_data):
cont, cont2, cont3 = sample_data.contents[:3]
swh_storage.content_add([cont, cont2, cont3])
assert swh_storage.content_get_random() in {
cont.sha1_git,
cont2.sha1_git,
cont3.sha1_git,
}
def test_directory_add(self, swh_storage, sample_data):
content = sample_data.content
directory = sample_data.directory
assert directory.entries[0].target == content.sha1_git
swh_storage.content_add([content])
init_missing = list(swh_storage.directory_missing([directory.id]))
assert [directory.id] == init_missing
actual_result = swh_storage.directory_add([directory])
assert actual_result == {"directory:add": 1}
assert ("directory", directory) in list(
swh_storage.journal_writer.journal.objects
)
actual_data = list(swh_storage.directory_ls(directory.id))
expected_data = list(transform_entries(swh_storage, directory))
for data in actual_data:
assert data in expected_data
after_missing = list(swh_storage.directory_missing([directory.id]))
assert after_missing == []
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
assert swh_storage.stat_counters()["directory"] == 1
def test_directory_add_with_raw_manifest(self, swh_storage, sample_data):
content = sample_data.content
directory = sample_data.directory
directory = attr.evolve(directory, raw_manifest=b"foo")
directory = attr.evolve(directory, id=directory.compute_hash())
assert directory.entries[0].target == content.sha1_git
swh_storage.content_add([content])
init_missing = list(swh_storage.directory_missing([directory.id]))
assert [directory.id] == init_missing
assert swh_storage.directory_get_raw_manifest([directory.id]) == {}
actual_result = swh_storage.directory_add([directory])
assert actual_result == {"directory:add": 1}
assert ("directory", directory) in list(
swh_storage.journal_writer.journal.objects
)
actual_data = list(swh_storage.directory_ls(directory.id))
expected_data = list(transform_entries(swh_storage, directory))
for data in actual_data:
assert data in expected_data
after_missing = list(swh_storage.directory_missing([directory.id]))
assert after_missing == []
assert swh_storage.directory_get_raw_manifest([directory.id]) == {
directory.id: b"foo"
}
directory2 = attr.evolve(directory, raw_manifest=b"bar")
directory2 = attr.evolve(directory2, id=directory2.compute_hash())
swh_storage.directory_add([directory2])
assert swh_storage.directory_get_raw_manifest(
[directory.id, directory2.id]
) == {directory.id: b"foo", directory2.id: b"bar"}
@settings(
suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large]
+ function_scoped_fixture_check,
)
@given(
strategies.lists(hypothesis_strategies.directories(), min_size=1, max_size=10)
)
def test_directory_add_get_arbitrary(self, swh_storage, directories):
swh_storage.directory_add(directories)
for directory in directories:
assert directory == Directory(
id=directory.id,
entries=tuple(
stream_results(swh_storage.directory_get_entries, directory.id)
),
raw_manifest=swh_storage.directory_get_raw_manifest([directory.id])[
directory.id
],
)
def test_directory_add_twice(self, swh_storage, sample_data):
directory = sample_data.directories[1]
actual_result = swh_storage.directory_add([directory])
assert actual_result == {"directory:add": 1}
assert list(swh_storage.journal_writer.journal.objects) == [
("directory", directory)
]
actual_result = swh_storage.directory_add([directory])
assert actual_result == {"directory:add": 0}
assert list(swh_storage.journal_writer.journal.objects) == [
("directory", directory)
]
def test_directory_ls_recursive(self, swh_storage, sample_data):
# create consistent dataset regarding the directories we want to list
content, content2 = sample_data.contents[:2]
swh_storage.content_add([content, content2])
dir1, dir2, dir3 = sample_data.directories[:3]
dir_ids = [d.id for d in [dir1, dir2, dir3]]
init_missing = list(swh_storage.directory_missing(dir_ids))
assert init_missing == dir_ids
actual_result = swh_storage.directory_add([dir1, dir2, dir3])
assert actual_result == {"directory:add": 3}
# List directory containing one file
actual_data = list(swh_storage.directory_ls(dir1.id, recursive=True))
expected_data = list(transform_entries(swh_storage, dir1))
for data in actual_data:
assert data in expected_data
# List directory containing a file and an unknown subdirectory
actual_data = list(swh_storage.directory_ls(dir2.id, recursive=True))
expected_data = list(transform_entries(swh_storage, dir2))
for data in actual_data:
assert data in expected_data
# List directory containing both a known and unknown subdirectory, entries
# should be both those of the directory and of the known subdir (up to contents)
actual_data = list(swh_storage.directory_ls(dir3.id, recursive=True))
expected_data = list(
itertools.chain(
transform_entries(swh_storage, dir3),
transform_entries(swh_storage, dir2, prefix=b"subdir/"),
)
)
for data in actual_data:
assert data in expected_data
def test_directory_ls_non_recursive(self, swh_storage, sample_data):
# create consistent dataset regarding the directories we want to list
content, content2 = sample_data.contents[:2]
swh_storage.content_add([content, content2])
dir1, dir2, dir3, _, dir5 = sample_data.directories[:5]
dir_ids = [d.id for d in [dir1, dir2, dir3, dir5]]
init_missing = list(swh_storage.directory_missing(dir_ids))
assert init_missing == dir_ids
actual_result = swh_storage.directory_add([dir1, dir2, dir3, dir5])
assert actual_result == {"directory:add": 4}
# List directory containing a file and an unknown subdirectory
actual_data = list(swh_storage.directory_ls(dir1.id))
expected_data = list(transform_entries(swh_storage, dir1))
for data in actual_data:
assert data in expected_data
# List directory containing a single file
actual_data = list(swh_storage.directory_ls(dir2.id))
expected_data = list(transform_entries(swh_storage, dir2))
for data in actual_data:
assert data in expected_data
# List directory containing a known subdirectory, entries should
# only be those of the parent directory, not of the subdir
actual_data = list(swh_storage.directory_ls(dir3.id))
expected_data = list(transform_entries(swh_storage, dir3))
for data in actual_data:
assert data in expected_data
def test_directory_ls_missing_content(self, swh_storage, sample_data):
swh_storage.directory_add([sample_data.directory2])
assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [
{
"dir_id": sample_data.directory2.id,
"length": None,
"name": b"oof",
"perms": 33188,
"sha1": None,
"sha1_git": None,
"sha256": None,
"status": None,
"target": sample_data.directory2.entries[0].target,
"type": "file",
},
]
def test_directory_ls_skipped_content(self, swh_storage, sample_data):
swh_storage.directory_add([sample_data.directory2])
cont = SkippedContent(
sha1_git=sample_data.directory2.entries[0].target,
sha1=b"c" * 20,
sha256=None,
blake2s256=None,
length=42,
status="absent",
reason="You need a premium subscription to access this content",
)
swh_storage.skipped_content_add([cont])
assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [
{
"dir_id": sample_data.directory2.id,
"length": 42,
"name": b"oof",
"perms": 33188,
"sha1": b"c" * 20,
"sha1_git": sample_data.directory2.entries[0].target,
"sha256": None,
"status": "absent",
"target": sample_data.directory2.entries[0].target,
"type": "file",
},
]
def test_directory_entry_get_by_path(self, swh_storage, sample_data):
cont, content2 = sample_data.contents[:2]
dir1, dir2, dir3, dir4, dir5 = sample_data.directories[:5]
# given
dir_ids = [d.id for d in [dir1, dir2, dir3, dir4, dir5]]
init_missing = list(swh_storage.directory_missing(dir_ids))
assert init_missing == dir_ids
actual_result = swh_storage.directory_add([dir3, dir4])
assert actual_result == {"directory:add": 2}
expected_entries = [
{
"dir_id": dir3.id,
"name": b"foo",
"type": "file",
"target": cont.sha1_git,
"sha1": None,
"sha1_git": None,
"sha256": None,
"status": None,
"perms": from_disk.DentryPerms.content,
"length": None,
},
{
"dir_id": dir3.id,
"name": b"subdir",
"type": "dir",
"target": dir2.id,
"sha1": None,
"sha1_git": None,
"sha256": None,
"status": None,
"perms": from_disk.DentryPerms.directory,
"length": None,
},
{
"dir_id": dir3.id,
"name": b"hello",
"type": "file",
"target": content2.sha1_git,
"sha1": None,
"sha1_git": None,
"sha256": None,
"status": None,
"perms": from_disk.DentryPerms.content,
"length": None,
},
]
# when (all must be found here)
for entry, expected_entry in zip(dir3.entries, expected_entries):
actual_entry = swh_storage.directory_entry_get_by_path(
dir3.id, [entry.name]
)
assert actual_entry == expected_entry
# same, but deeper
for entry, expected_entry in zip(dir3.entries, expected_entries):
actual_entry = swh_storage.directory_entry_get_by_path(
dir4.id, [b"subdir1", entry.name]
)
expected_entry = expected_entry.copy()
expected_entry["name"] = b"subdir1/" + expected_entry["name"]
assert actual_entry == expected_entry
# when (nothing should be found here since `dir` is not persisted.)
for entry in dir2.entries:
actual_entry = swh_storage.directory_entry_get_by_path(
dir2.id, [entry.name]
)
assert actual_entry is None
def test_directory_get_entries_pagination(self, swh_storage, sample_data):
dir_ = sample_data.directory3
entries = sorted(dir_.entries, key=lambda entry: entry.name)
swh_storage.directory_add(sample_data.directories)
# No pagination needed
actual_data = swh_storage.directory_get_entries(dir_.id)
assert sorted(actual_data.results) == sorted(entries)
assert actual_data.next_page_token is None, actual_data
# A little pagination
actual_data = swh_storage.directory_get_entries(dir_.id, limit=2)
assert len(actual_data.results) == 2, actual_data
assert actual_data.next_page_token is not None, actual_data
all_results = list(actual_data.results)
actual_data = swh_storage.directory_get_entries(
dir_.id, page_token=actual_data.next_page_token
)
assert len(actual_data.results) == len(entries) - 2, actual_data
assert actual_data.next_page_token is None, actual_data
all_results.extend(actual_data.results)
assert sorted(all_results) == sorted(entries)
@pytest.mark.parametrize("limit", [1, 2, 3, 4, 5])
def test_directory_get_entries(self, swh_storage, sample_data, limit):
dir_ = sample_data.directory3
swh_storage.directory_add(sample_data.directories)
actual_data = list(
- stream_results(swh_storage.directory_get_entries, dir_.id, limit=limit,)
+ stream_results(
+ swh_storage.directory_get_entries,
+ dir_.id,
+ limit=limit,
+ )
)
assert sorted(actual_data) == sorted(dir_.entries)
def test_directory_get_random(self, swh_storage, sample_data):
dir1, dir2, dir3 = sample_data.directories[:3]
swh_storage.directory_add([dir1, dir2, dir3])
assert swh_storage.directory_get_random() in {
dir1.id,
dir2.id,
dir3.id,
}
def test_revision_add(self, swh_storage, sample_data):
revision = sample_data.revision
init_missing = swh_storage.revision_missing([revision.id])
assert list(init_missing) == [revision.id]
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 1}
end_missing = swh_storage.revision_missing([revision.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("revision", revision)
]
# already there so nothing added
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 0}
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
assert swh_storage.stat_counters()["revision"] == 1
def test_revision_add_twice(self, swh_storage, sample_data):
revision, revision2 = sample_data.revisions[:2]
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 1}
assert list(swh_storage.journal_writer.journal.objects) == [
("revision", revision)
]
actual_result = swh_storage.revision_add([revision, revision2])
assert actual_result == {"revision:add": 1}
assert list(swh_storage.journal_writer.journal.objects) == [
("revision", revision),
("revision", revision2),
]
def test_revision_add_fractional_timezone(self, swh_storage, sample_data):
# When reading a date from this time period on systems configured with
# timezone Europe/Paris, postgresql returns them with UTC+00:09:21 as timezone,
# but psycopg2 < 2.9.0 had to truncate them.
# https://www.psycopg.org/docs/usage.html#time-zones-handling
#
# There is a workaround in swh.storage.postgresql.storage.Storage.get_db,
# to set the timezone to UTC so it works on all psycopg2 versions.
#
# Therefore, this test always succeeds in tox (because psycopg2 >= 2.9.0)
# and on the CI (both because psycopg2 >= 2.9.0 and TZ=UTC); but which means
# this test is only useful on machines with older psycopg2 versions and
# TZ=Europe/Paris. But the workaround is also only needed on this kind of
# configuration, so this is good enough.
revision = attr.evolve(
sample_data.revision,
date=TimestampWithTimezone(
timestamp=Timestamp(seconds=-1855958962, microseconds=0),
offset_bytes=b"+0000",
),
)
init_missing = swh_storage.revision_missing([revision.id])
assert list(init_missing) == [revision.id]
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 1}
end_missing = swh_storage.revision_missing([revision.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("revision", revision)
]
assert swh_storage.revision_get([revision.id])[0] == revision
def test_revision_add_with_raw_manifest(self, swh_storage, sample_data):
revision = sample_data.revision
revision = attr.evolve(revision, raw_manifest=b"foo")
revision = attr.evolve(revision, id=revision.compute_hash())
init_missing = swh_storage.revision_missing([revision.id])
assert list(init_missing) == [revision.id]
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 1}
end_missing = swh_storage.revision_missing([revision.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("revision", revision)
]
assert swh_storage.revision_get([revision.id]) == [revision]
@settings(
suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large]
+ function_scoped_fixture_check,
)
@given(
- strategies.lists(hypothesis_strategies.revisions(), min_size=1, max_size=10,)
+ strategies.lists(
+ hypothesis_strategies.revisions(),
+ min_size=1,
+ max_size=10,
+ )
)
def test_revision_add_get_arbitrary(self, swh_storage, revisions):
# remove non-intrinsic data, so releases inserted with different hypothesis
# data can't clash with each other
revisions = [
attr.evolve(
revision,
synthetic=False,
metadata=None,
author=None
if revision.author is None
else Person.from_fullname(revision.author.fullname),
committer=None
if revision.committer is None
else Person.from_fullname(revision.committer.fullname),
type=RevisionType.GIT,
)
for revision in revisions
]
swh_storage.revision_add(revisions)
for revision in revisions:
(rev,) = swh_storage.revision_get([revision.id])
if rev.raw_manifest is None:
assert rev == revision
else:
assert rev.raw_manifest == revision.raw_manifest
# we can't compare the other fields, because they become non-intrinsic,
# so they may clash between hypothesis runs
def test_revision_add_name_clash(self, swh_storage, sample_data):
revision, revision2 = sample_data.revisions[:2]
revision1 = attr.evolve(
revision,
author=Person(
fullname=b"John Doe ",
name=b"John Doe",
email=b"john.doe@example.com",
),
)
revision2 = attr.evolve(
revision2,
author=Person(
fullname=b"John Doe ",
name=b"John Doe ",
email=b"john.doe@example.com ",
),
)
actual_result = swh_storage.revision_add([revision1, revision2])
assert actual_result == {"revision:add": 2}
def test_revision_get_order(self, swh_storage, sample_data):
revision, revision2 = sample_data.revisions[:2]
add_result = swh_storage.revision_add([revision, revision2])
assert add_result == {"revision:add": 2}
# order 1
actual_revisions = swh_storage.revision_get([revision.id, revision2.id])
assert actual_revisions == [revision, revision2]
# order 2
actual_revisions2 = swh_storage.revision_get([revision2.id, revision.id])
assert actual_revisions2 == [revision2, revision]
def test_revision_log(self, swh_storage, sample_data):
revision1, revision2, revision3, revision4 = sample_data.revisions[:4]
# rev4 -is-child-of-> rev3 -> rev1, (rev2 -> rev1)
swh_storage.revision_add([revision1, revision2, revision3, revision4])
# when
results = list(swh_storage.revision_log([revision4.id]))
# for comparison purposes
actual_results = [Revision.from_dict(r) for r in results]
assert len(actual_results) == 4 # rev4 -child-> rev3 -> rev1, (rev2 -> rev1)
assert actual_results == [revision4, revision3, revision1, revision2]
def test_revision_log_with_limit(self, swh_storage, sample_data):
revision1, revision2, revision3, revision4 = sample_data.revisions[:4]
# revision4 -is-child-of-> revision3
swh_storage.revision_add([revision3, revision4])
results = list(swh_storage.revision_log([revision4.id], limit=1))
actual_results = [Revision.from_dict(r) for r in results]
assert len(actual_results) == 1
assert actual_results[0] == revision4
def test_revision_log_unknown_revision(self, swh_storage, sample_data):
revision = sample_data.revision
rev_log = list(swh_storage.revision_log([revision.id]))
assert rev_log == []
def test_revision_shortlog(self, swh_storage, sample_data):
revision1, revision2, revision3, revision4 = sample_data.revisions[:4]
# rev4 -is-child-of-> rev3 -> (rev1, rev2); rev2 -> rev1
swh_storage.revision_add([revision1, revision2, revision3, revision4])
results = list(swh_storage.revision_shortlog([revision4.id]))
actual_results = [[id, tuple(parents)] for (id, parents) in results]
assert len(actual_results) == 4
assert actual_results == [
[revision4.id, revision4.parents],
[revision3.id, revision3.parents],
[revision1.id, revision1.parents],
[revision2.id, revision2.parents],
]
def test_revision_shortlog_with_limit(self, swh_storage, sample_data):
revision1, revision2, revision3, revision4 = sample_data.revisions[:4]
# revision4 -is-child-of-> revision3
swh_storage.revision_add([revision1, revision2, revision3, revision4])
results = list(swh_storage.revision_shortlog([revision4.id], 1))
actual_results = [[id, tuple(parents)] for (id, parents) in results]
assert len(actual_results) == 1
assert list(actual_results[0]) == [revision4.id, revision4.parents]
def test_revision_get(self, swh_storage, sample_data):
revision, revision2 = sample_data.revisions[:2]
swh_storage.revision_add([revision])
actual_revisions = swh_storage.revision_get([revision.id, revision2.id])
assert len(actual_revisions) == 2
assert actual_revisions == [revision, None]
def test_revision_get_no_parents(self, swh_storage, sample_data):
revision = sample_data.revision
swh_storage.revision_add([revision])
actual_revision = swh_storage.revision_get([revision.id])[0]
assert revision.parents == ()
assert actual_revision.parents == () # no parents on this one
def test_revision_get_random(self, swh_storage, sample_data):
revision1, revision2, revision3 = sample_data.revisions[:3]
swh_storage.revision_add([revision1, revision2, revision3])
assert swh_storage.revision_get_random() in {
revision1.id,
revision2.id,
revision3.id,
}
def test_revision_missing_many(self, swh_storage, sample_data):
"""Large number of revision ids to check can cause ScyllaDB to reject
queries."""
revision = sample_data.revision
ids = [bytes([b1, b2]) * 10 for b1 in range(256) for b2 in range(10)]
ids.append(revision.id)
ids.sort()
init_missing = swh_storage.revision_missing(ids)
assert set(init_missing) == set(ids)
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 1}
end_missing = swh_storage.revision_missing(ids)
assert set(end_missing) == set(ids) - {revision.id}
def test_revision_add_no_author_or_date(self, swh_storage, sample_data):
full_revision = sample_data.revision
revision = attr.evolve(full_revision, author=None, date=None)
revision = attr.evolve(revision, id=revision.compute_hash())
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 1}
end_missing = swh_storage.revision_missing([revision.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("revision", revision)
]
assert swh_storage.revision_get([revision.id]) == [revision]
def test_revision_add_no_committer_or_date(self, swh_storage, sample_data):
full_revision = sample_data.revision
revision = attr.evolve(full_revision, committer=None, committer_date=None)
revision = attr.evolve(revision, id=revision.compute_hash())
actual_result = swh_storage.revision_add([revision])
assert actual_result == {"revision:add": 1}
end_missing = swh_storage.revision_missing([revision.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("revision", revision)
]
assert swh_storage.revision_get([revision.id]) == [revision]
def test_extid_add_git(self, swh_storage, sample_data):
gitids = [
revision.id
for revision in sample_data.revisions
if revision.type.value == "git"
]
extids = [
ExtID(
extid=gitid,
extid_type="git",
- target=CoreSWHID(object_id=gitid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=gitid,
+ object_type=ObjectType.REVISION,
+ ),
)
for gitid in gitids
]
assert swh_storage.extid_get_from_extid("git", gitids) == []
assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == []
summary = swh_storage.extid_add(extids)
assert summary == {"extid:add": len(gitids)}
assert swh_storage.extid_get_from_extid("git", gitids) == extids
assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids
assert swh_storage.extid_get_from_extid("hg", gitids) == []
assert swh_storage.extid_get_from_target(ObjectType.RELEASE, gitids) == []
# check ExtIDs have been added to the journal
extids_in_journal = [
obj
for (obj_type, obj) in swh_storage.journal_writer.journal.objects
if obj_type == "extid"
]
assert extids == extids_in_journal
def test_extid_add_hg(self, swh_storage, sample_data):
def get_node(revision):
node = None
if revision.extra_headers:
node = dict(revision.extra_headers).get(b"node")
if node is None and revision.metadata:
node = hash_to_bytes(revision.metadata.get("node"))
return node
swhids = [
revision.id
for revision in sample_data.revisions
if revision.type.value == "hg"
]
extids = [
get_node(revision)
for revision in sample_data.revisions
if revision.type.value == "hg"
]
assert swh_storage.extid_get_from_extid("hg", extids) == []
assert swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == []
extid_objs = [
ExtID(
extid=hgid,
extid_type="hg",
extid_version=1,
- target=CoreSWHID(object_id=swhid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=swhid,
+ object_type=ObjectType.REVISION,
+ ),
)
for hgid, swhid in zip(extids, swhids)
]
summary = swh_storage.extid_add(extid_objs)
assert summary == {"extid:add": len(swhids)}
assert swh_storage.extid_get_from_extid("hg", extids) == extid_objs
assert (
swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == extid_objs
)
assert swh_storage.extid_get_from_extid("git", extids) == []
assert swh_storage.extid_get_from_target(ObjectType.RELEASE, swhids) == []
# check ExtIDs have been added to the journal
extids_in_journal = [
obj
for (obj_type, obj) in swh_storage.journal_writer.journal.objects
if obj_type == "extid"
]
assert extid_objs == extids_in_journal
def test_extid_add_twice(self, swh_storage, sample_data):
gitids = [
revision.id
for revision in sample_data.revisions
if revision.type.value == "git"
]
extids = [
ExtID(
extid=gitid,
extid_type="git",
- target=CoreSWHID(object_id=gitid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=gitid,
+ object_type=ObjectType.REVISION,
+ ),
)
for gitid in gitids
]
summary = swh_storage.extid_add(extids)
assert summary == {"extid:add": len(gitids)}
# add them again, should be noop
summary = swh_storage.extid_add(extids)
# assert summary == {"extid:add": 0}
assert swh_storage.extid_get_from_extid("git", gitids) == extids
assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids
def test_extid_add_extid_multicity(self, swh_storage, sample_data):
ids = [
revision.id
for revision in sample_data.revisions
if revision.type.value == "git"
]
extids = [
ExtID(
extid=extid,
extid_type="git",
extid_version=2,
- target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=extid,
+ object_type=ObjectType.REVISION,
+ ),
)
for extid in ids
]
swh_storage.extid_add(extids)
# try to add "modified-extid" versions, should be added
extids2 = [
ExtID(
extid=extid,
extid_type="hg",
extid_version=2,
- target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=extid,
+ object_type=ObjectType.REVISION,
+ ),
)
for extid in ids
]
swh_storage.extid_add(extids2)
assert swh_storage.extid_get_from_extid("git", ids) == extids
assert swh_storage.extid_get_from_extid("hg", ids) == extids2
assert set(swh_storage.extid_get_from_target(ObjectType.REVISION, ids)) == {
*extids,
*extids2,
}
def test_extid_add_target_multicity(self, swh_storage, sample_data):
ids = [
revision.id
for revision in sample_data.revisions
if revision.type.value == "git"
]
extids = [
ExtID(
extid=extid,
extid_type="git",
- target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=extid,
+ object_type=ObjectType.REVISION,
+ ),
)
for extid in ids
]
swh_storage.extid_add(extids)
# try to add "modified" versions, should be added
extids2 = [
ExtID(
extid=extid,
extid_type="git",
- target=CoreSWHID(object_id=extid, object_type=ObjectType.RELEASE,),
+ target=CoreSWHID(
+ object_id=extid,
+ object_type=ObjectType.RELEASE,
+ ),
)
for extid in ids
]
swh_storage.extid_add(extids2)
assert set(swh_storage.extid_get_from_extid("git", ids)) == {*extids, *extids2}
assert swh_storage.extid_get_from_target(ObjectType.REVISION, ids) == extids
assert swh_storage.extid_get_from_target(ObjectType.RELEASE, ids) == extids2
def test_extid_version_behavior(self, swh_storage, sample_data):
ids = [
revision.id
for revision in sample_data.revisions
if revision.type.value == "git"
]
# Insert extids with several different versions
extids = [
ExtID(
extid=extid,
extid_type="git",
extid_version=0,
- target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=extid,
+ object_type=ObjectType.REVISION,
+ ),
)
for extid in ids
] + [
ExtID(
extid=extid,
extid_type="git",
extid_version=1,
- target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,),
+ target=CoreSWHID(
+ object_id=extid,
+ object_type=ObjectType.REVISION,
+ ),
)
for extid in ids
]
swh_storage.extid_add(extids)
# Check that both versions get returned
for git_id in ids:
objs = swh_storage.extid_get_from_extid("git", [git_id])
assert len(objs) == 2
assert set(obj.extid_version for obj in objs) == {0, 1}
for swhid in ids:
objs = swh_storage.extid_get_from_target(ObjectType.REVISION, [swhid])
assert len(objs) == 2
assert set(obj.extid_version for obj in objs) == {0, 1}
for version in [0, 1]:
for git_id in ids:
objs = swh_storage.extid_get_from_extid(
"git", [git_id], version=version
)
assert len(objs) == 1
assert objs[0].extid_version == version
for swhid in ids:
objs = swh_storage.extid_get_from_target(
ObjectType.REVISION,
[swhid],
extid_version=version,
extid_type="git",
)
assert len(objs) == 1
assert objs[0].extid_version == version
assert objs[0].extid_type == "git"
def test_extid_version_behavior_failure(self, swh_storage, sample_data):
"""Calls with wrong input should raise"""
ids = [
revision.id
for revision in sample_data.revisions
if revision.type.value == "git"
]
# Other edge cases
with pytest.raises(
(ValueError, RemoteException), match="both extid_type and extid_version"
):
swh_storage.extid_get_from_target(
ObjectType.REVISION, [ids[0]], extid_version=0
)
with pytest.raises(
(ValueError, RemoteException), match="both extid_type and extid_version"
):
swh_storage.extid_get_from_target(
ObjectType.REVISION, [ids[0]], extid_type="git"
)
def test_release_add(self, swh_storage, sample_data):
release, release2 = sample_data.releases[:2]
init_missing = swh_storage.release_missing([release.id, release2.id])
assert list(init_missing) == [release.id, release2.id]
actual_result = swh_storage.release_add([release, release2])
assert actual_result == {"release:add": 2}
end_missing = swh_storage.release_missing([release.id, release2.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("release", release),
("release", release2),
]
# already present so nothing added
actual_result = swh_storage.release_add([release, release2])
assert actual_result == {"release:add": 0}
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
assert swh_storage.stat_counters()["release"] == 2
def test_release_add_with_raw_manifest(self, swh_storage, sample_data):
release = sample_data.releases[0]
release = attr.evolve(release, raw_manifest=b"foo")
release = attr.evolve(release, id=release.compute_hash())
init_missing = swh_storage.release_missing([release.id])
assert list(init_missing) == [release.id]
actual_result = swh_storage.release_add([release])
assert actual_result == {"release:add": 1}
end_missing = swh_storage.release_missing([release.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("release", release),
]
assert swh_storage.release_get([release.id]) == [release]
@settings(
suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large]
+ function_scoped_fixture_check,
)
- @given(strategies.lists(hypothesis_strategies.releases(), min_size=1, max_size=10,))
+ @given(
+ strategies.lists(
+ hypothesis_strategies.releases(),
+ min_size=1,
+ max_size=10,
+ )
+ )
def test_release_add_get_arbitrary(self, swh_storage, releases):
# remove non-intrinsic data, so releases inserted with different hypothesis
# data can't clash with each other
releases = [
attr.evolve(
release,
synthetic=False,
metadata=None,
author=Person.from_fullname(release.author.fullname)
if release.author
else None,
)
for release in releases
]
swh_storage.release_add(releases)
for release in releases:
(rev,) = swh_storage.release_get([release.id])
if rev.raw_manifest is None:
assert rev == release
else:
assert rev.raw_manifest == release.raw_manifest
# we can't compare the other fields, because they become non-intrinsic,
# so they may clash between hypothesis runs
def test_release_add_no_author_date(self, swh_storage, sample_data):
full_release = sample_data.release
release = attr.evolve(full_release, author=None, date=None)
actual_result = swh_storage.release_add([release])
assert actual_result == {"release:add": 1}
end_missing = swh_storage.release_missing([release.id])
assert list(end_missing) == []
assert list(swh_storage.journal_writer.journal.objects) == [
("release", release)
]
def test_release_add_twice(self, swh_storage, sample_data):
release, release2 = sample_data.releases[:2]
actual_result = swh_storage.release_add([release])
assert actual_result == {"release:add": 1}
assert list(swh_storage.journal_writer.journal.objects) == [
("release", release)
]
actual_result = swh_storage.release_add([release, release2, release, release2])
assert actual_result == {"release:add": 1}
assert set(swh_storage.journal_writer.journal.objects) == set(
- [("release", release), ("release", release2),]
+ [
+ ("release", release),
+ ("release", release2),
+ ]
)
def test_release_add_name_clash(self, swh_storage, sample_data):
release, release2 = [
attr.evolve(
c,
author=Person(
fullname=b"John Doe ",
name=b"John Doe",
email=b"john.doe@example.com",
),
)
for c in sample_data.releases[:2]
]
actual_result = swh_storage.release_add([release, release2])
assert actual_result == {"release:add": 2}
def test_release_get(self, swh_storage, sample_data):
release, release2, release3 = sample_data.releases[:3]
# given
swh_storage.release_add([release, release2])
# when
actual_releases = swh_storage.release_get([release.id, release2.id])
# then
assert actual_releases == [release, release2]
unknown_releases = swh_storage.release_get([release3.id])
assert unknown_releases[0] is None
def test_release_get_order(self, swh_storage, sample_data):
release, release2 = sample_data.releases[:2]
add_result = swh_storage.release_add([release, release2])
assert add_result == {"release:add": 2}
# order 1
actual_releases = swh_storage.release_get([release.id, release2.id])
assert actual_releases == [release, release2]
# order 2
actual_releases2 = swh_storage.release_get([release2.id, release.id])
assert actual_releases2 == [release2, release]
def test_release_get_random(self, swh_storage, sample_data):
release, release2, release3 = sample_data.releases[:3]
swh_storage.release_add([release, release2, release3])
assert swh_storage.release_get_random() in {
release.id,
release2.id,
release3.id,
}
def test_origin_add(self, swh_storage, sample_data):
origins = list(sample_data.origins)
origin_urls = [o.url for o in origins]
assert swh_storage.origin_get(origin_urls) == [None] * len(origins)
stats = swh_storage.origin_add(origins)
assert stats == {"origin:add": len(origin_urls)}
actual_origins = swh_storage.origin_get(origin_urls)
assert actual_origins == origins
assert set(swh_storage.journal_writer.journal.objects) == set(
[("origin", origin) for origin in origins]
)
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
assert swh_storage.stat_counters()["origin"] == len(origins)
def test_origin_add_twice(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
add1 = swh_storage.origin_add([origin, origin2])
assert set(swh_storage.journal_writer.journal.objects) == set(
- [("origin", origin), ("origin", origin2),]
+ [
+ ("origin", origin),
+ ("origin", origin2),
+ ]
)
assert add1 == {"origin:add": 2}
add2 = swh_storage.origin_add([origin, origin2])
assert set(swh_storage.journal_writer.journal.objects) == set(
- [("origin", origin), ("origin", origin2),]
+ [
+ ("origin", origin),
+ ("origin", origin2),
+ ]
)
assert add2 == {"origin:add": 0}
def test_origin_add_twice_at_once(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
add1 = swh_storage.origin_add([origin, origin2, origin, origin2])
assert set(swh_storage.journal_writer.journal.objects) == set(
- [("origin", origin), ("origin", origin2),]
+ [
+ ("origin", origin),
+ ("origin", origin2),
+ ]
)
assert add1 == {"origin:add": 2}
add2 = swh_storage.origin_add([origin, origin2, origin, origin2])
assert set(swh_storage.journal_writer.journal.objects) == set(
- [("origin", origin), ("origin", origin2),]
+ [
+ ("origin", origin),
+ ("origin", origin2),
+ ]
)
assert add2 == {"origin:add": 0}
def test_origin_get(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
assert swh_storage.origin_get([origin.url]) == [None]
swh_storage.origin_add([origin])
actual_origins = swh_storage.origin_get([origin.url])
assert actual_origins == [origin]
actual_origins = swh_storage.origin_get([origin.url, "not://exists"])
assert actual_origins == [origin, None]
def _generate_random_visits(self, nb_visits=100, start=0, end=7):
"""Generate random visits within the last 2 months (to avoid
computations)
"""
visits = []
today = now()
for weeks in range(nb_visits, 0, -1):
hours = random.randint(0, 24)
minutes = random.randint(0, 60)
seconds = random.randint(0, 60)
days = random.randint(0, 28)
weeks = random.randint(start, end)
date_visit = today - timedelta(
weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days
)
visits.append(date_visit)
return visits
def test_origin_visit_get__unknown_origin(self, swh_storage):
actual_page = swh_storage.origin_visit_get("foo")
assert actual_page.next_page_token is None
assert actual_page.results == []
assert actual_page == PagedResult()
def test_origin_visit_get__validation_failure(self, swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
with pytest.raises(
StorageArgumentException, match="page_token must be a string"
):
swh_storage.origin_visit_get(origin.url, page_token=10) # not bytes
with pytest.raises(
StorageArgumentException, match="order must be a ListOrder value"
):
swh_storage.origin_visit_get(origin.url, order="foobar") # wrong order
def test_origin_visit_get_all(self, swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
ov1, ov2, ov3 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
),
OriginVisit(
origin=origin.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
),
OriginVisit(
origin=origin.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
),
]
)
# order asc, no token, no limit
actual_page = swh_storage.origin_visit_get(origin.url)
assert actual_page.next_page_token is None
assert actual_page.results == [ov1, ov2, ov3]
# order asc, no token, limit
actual_page = swh_storage.origin_visit_get(origin.url, limit=2)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ov1, ov2]
# order asc, token, no limit
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token
)
assert actual_page.next_page_token is None
assert actual_page.results == [ov3]
# order asc, no token, limit
actual_page = swh_storage.origin_visit_get(origin.url, limit=1)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ov1]
# order asc, token, no limit
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token
)
assert actual_page.next_page_token is None
assert actual_page.results == [ov2, ov3]
# order asc, token, limit
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token, limit=2
)
assert actual_page.next_page_token is None
assert actual_page.results == [ov2, ov3]
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token, limit=1
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ov2]
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token, limit=1
)
assert actual_page.next_page_token is None
assert actual_page.results == [ov3]
# order desc, no token, no limit
actual_page = swh_storage.origin_visit_get(origin.url, order=ListOrder.DESC)
assert actual_page.next_page_token is None
assert actual_page.results == [ov3, ov2, ov1]
# order desc, no token, limit
actual_page = swh_storage.origin_visit_get(
origin.url, limit=2, order=ListOrder.DESC
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ov3, ov2]
# order desc, token, no limit
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token, order=ListOrder.DESC
)
assert actual_page.next_page_token is None
assert actual_page.results == [ov1]
# order desc, no token, limit
actual_page = swh_storage.origin_visit_get(
origin.url, limit=1, order=ListOrder.DESC
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ov3]
# order desc, token, no limit
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token, order=ListOrder.DESC
)
assert actual_page.next_page_token is None
assert actual_page.results == [ov2, ov1]
# order desc, token, limit
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token, order=ListOrder.DESC, limit=1
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ov2]
actual_page = swh_storage.origin_visit_get(
origin.url, page_token=next_page_token, order=ListOrder.DESC
)
assert actual_page.next_page_token is None
assert actual_page.results == [ov1]
@pytest.mark.parametrize(
"allowed_statuses,require_snapshot",
[
([], False),
(["failed"], False),
(["failed", "full"], False),
([], True),
(["failed"], True),
(["failed", "full"], True),
],
)
def test_origin_visit_get_with_statuses(
self, swh_storage, sample_data, allowed_statuses, require_snapshot
):
origin = sample_data.origin
swh_storage.origin_add([origin])
ov1, ov2, ov3 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
),
OriginVisit(
origin=origin.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
),
OriginVisit(
origin=origin.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
),
]
)
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=sample_data.date_visit1 + datetime.timedelta(hours=1),
type=sample_data.type_visit1,
status="failed",
snapshot=None,
),
OriginVisitStatus(
origin=origin.url,
visit=ov2.visit,
date=sample_data.date_visit2 + datetime.timedelta(hours=1),
type=sample_data.type_visit2,
status="failed",
snapshot=None,
),
OriginVisitStatus(
origin=origin.url,
visit=ov3.visit,
date=sample_data.date_visit2 + datetime.timedelta(hours=1),
type=sample_data.type_visit2,
status="failed",
snapshot=None,
),
]
)
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=sample_data.date_visit1 + datetime.timedelta(hours=2),
type=sample_data.type_visit1,
status="full",
snapshot=sample_data.snapshots[0].id,
),
OriginVisitStatus(
origin=origin.url,
visit=ov2.visit,
date=sample_data.date_visit2 + datetime.timedelta(hours=2),
type=sample_data.type_visit2,
status="full",
snapshot=sample_data.snapshots[1].id,
),
OriginVisitStatus(
origin=origin.url,
visit=ov3.visit,
date=sample_data.date_visit2 + datetime.timedelta(hours=2),
type=sample_data.type_visit2,
status="full",
snapshot=sample_data.snapshots[2].id,
),
]
)
ov1_statuses = swh_storage.origin_visit_status_get(
origin.url, visit=ov1.visit
).results
ov2_statuses = swh_storage.origin_visit_status_get(
origin.url, visit=ov2.visit
).results
ov3_statuses = swh_storage.origin_visit_status_get(
origin.url, visit=ov3.visit
).results
def _filter_statuses(ov_statuses):
if allowed_statuses:
ov_statuses = [
ovs for ovs in ov_statuses if ovs.status in allowed_statuses
]
assert [ovs.status for ovs in ov_statuses] == allowed_statuses
else:
assert [ovs.status for ovs in ov_statuses] == [
"created",
"failed",
"full",
]
if require_snapshot:
ov_statuses = [ovs for ovs in ov_statuses if ovs.snapshot is not None]
return ov_statuses
ov1_statuses = _filter_statuses(ov1_statuses)
ov2_statuses = _filter_statuses(ov2_statuses)
ov3_statuses = _filter_statuses(ov3_statuses)
ovws1 = OriginVisitWithStatuses(visit=ov1, statuses=ov1_statuses)
ovws2 = OriginVisitWithStatuses(visit=ov2, statuses=ov2_statuses)
ovws3 = OriginVisitWithStatuses(visit=ov3, statuses=ov3_statuses)
# order asc, no token, no limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws1, ovws2, ovws3]
# order asc, no token, limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
limit=2,
)
next_page_token = actual_page.next_page_token
assert len(actual_page.results) == 2
assert next_page_token is not None
assert actual_page.results == [ovws1, ovws2]
# order asc, token, no limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws3]
# order asc, no token, limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
limit=1,
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovws1]
# order asc, token, no limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws2, ovws3]
# order asc, token, limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
limit=2,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws2, ovws3]
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
limit=1,
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovws2]
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
limit=1,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws3]
# order desc, no token, no limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
order=ListOrder.DESC,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws3, ovws2, ovws1]
# order desc, no token, limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
limit=2,
order=ListOrder.DESC,
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovws3, ovws2]
# order desc, token, no limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
order=ListOrder.DESC,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws1]
# order desc, no token, limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
limit=1,
order=ListOrder.DESC,
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovws3]
# order desc, token, no limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
order=ListOrder.DESC,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws2, ovws1]
# order desc, token, limit
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
order=ListOrder.DESC,
limit=1,
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovws2]
actual_page = swh_storage.origin_visit_get_with_statuses(
origin.url,
allowed_statuses=allowed_statuses,
require_snapshot=require_snapshot,
page_token=next_page_token,
order=ListOrder.DESC,
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovws1]
def test_origin_visit_status_get__unknown_cases(self, swh_storage, sample_data):
origin = sample_data.origin
actual_page = swh_storage.origin_visit_status_get("foobar", 1)
assert actual_page.next_page_token is None
assert actual_page.results == []
actual_page = swh_storage.origin_visit_status_get(origin.url, 1)
assert actual_page.next_page_token is None
assert actual_page.results == []
origin = sample_data.origin
swh_storage.origin_add([origin])
ov1 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
),
]
)[0]
actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit + 10)
assert actual_page.next_page_token is None
assert actual_page.results == []
def test_origin_visit_status_add_unknown_type(self, swh_storage, sample_data):
ov = OriginVisit(
origin=sample_data.origin.url,
date=now(),
type=sample_data.type_visit1,
visit=42,
)
ovs = OriginVisitStatus(
origin=ov.origin,
visit=ov.visit,
date=now(),
status="created",
snapshot=None,
)
with pytest.raises(StorageArgumentException):
swh_storage.origin_visit_status_add([ovs])
swh_storage.origin_add([sample_data.origin])
with pytest.raises(StorageArgumentException):
swh_storage.origin_visit_status_add([ovs])
swh_storage.origin_visit_add([ov])
swh_storage.origin_visit_status_add([ovs])
def test_origin_visit_status_get_all(self, swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
date_visit3 = round_to_milliseconds(now())
date_visit1 = date_visit3 - datetime.timedelta(hours=2)
date_visit2 = date_visit3 - datetime.timedelta(hours=1)
assert date_visit1 < date_visit2 < date_visit3
ov1 = swh_storage.origin_visit_add(
[
OriginVisit(
- origin=origin.url, date=date_visit1, type=sample_data.type_visit1,
+ origin=origin.url,
+ date=date_visit1,
+ type=sample_data.type_visit1,
),
]
)[0]
ovs1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit1,
type=ov1.type,
status="created",
snapshot=None,
)
ovs2 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit2,
type=ov1.type,
status="partial",
snapshot=None,
)
ovs3 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit3,
type=ov1.type,
status="full",
snapshot=sample_data.snapshot.id,
metadata={},
)
swh_storage.origin_visit_status_add([ovs2, ovs3])
# order asc, no token, no limit
actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs1, ovs2, ovs3]
# order asc, no token, limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, limit=2
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovs1, ovs2]
# order asc, token, no limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, page_token=next_page_token
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs3]
# order asc, no token, limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, limit=1
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovs1]
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, page_token=next_page_token
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs2, ovs3]
# order asc, token, limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, page_token=next_page_token, limit=2
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs2, ovs3]
# order asc, no token, limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, limit=2
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovs1, ovs2]
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, page_token=next_page_token, limit=1
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs3]
# order desc, no token, no limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, order=ListOrder.DESC
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs3, ovs2, ovs1]
# order desc, no token, limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, limit=2, order=ListOrder.DESC
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovs3, ovs2]
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs1]
# order desc, no token, limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, order=ListOrder.DESC, limit=1
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovs3]
# order desc, token, no limit
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs2, ovs1]
# order desc, token, limit
actual_page = swh_storage.origin_visit_status_get(
origin.url,
ov1.visit,
page_token=next_page_token,
order=ListOrder.DESC,
limit=1,
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [ovs2]
actual_page = swh_storage.origin_visit_status_get(
origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC
)
assert actual_page.next_page_token is None
assert actual_page.results == [ovs1]
def test_origin_visit_status_get_random(self, swh_storage, sample_data):
origins = sample_data.origins[:2]
swh_storage.origin_add(origins)
# Add some random visits within the selection range
visits = self._generate_random_visits()
visit_type = "git"
# Add visits to those origins
for origin in origins:
for date_visit in visits:
visit = swh_storage.origin_visit_add(
- [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)]
+ [
+ OriginVisit(
+ origin=origin.url,
+ date=date_visit,
+ type=visit_type,
+ )
+ ]
)[0]
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=visit.visit,
date=now(),
status="full",
snapshot=hash_to_bytes(
"9b922e6d8d5b803c1582aabe5525b7b91150788e"
),
)
]
)
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
stats = swh_storage.stat_counters()
assert stats["origin"] == len(origins)
assert stats["origin_visit"] == len(origins) * len(visits)
random_ovs = swh_storage.origin_visit_status_get_random(visit_type)
assert random_ovs
assert random_ovs.origin is not None
assert random_ovs.origin in [o.url for o in origins]
assert random_ovs.type is not None
def test_origin_visit_status_get_random_nothing_found(
self, swh_storage, sample_data
):
origins = sample_data.origins
swh_storage.origin_add(origins)
visit_type = "hg"
# Add some visits outside of the random generation selection so nothing
# will be found by the random selection
visits = self._generate_random_visits(nb_visits=3, start=13, end=24)
for origin in origins:
for date_visit in visits:
visit = swh_storage.origin_visit_add(
- [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)]
+ [
+ OriginVisit(
+ origin=origin.url,
+ date=date_visit,
+ type=visit_type,
+ )
+ ]
)[0]
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=visit.visit,
date=now(),
status="full",
snapshot=None,
)
]
)
random_origin_visit = swh_storage.origin_visit_status_get_random(visit_type)
assert random_origin_visit is None
def test_origin_snapshot_get_all(self, swh_storage, sample_data):
origin = sample_data.origins[0]
swh_storage.origin_add([origin])
# add some random visits within the selection range
visits = self._generate_random_visits()
visit_type = "git"
# set first visit to a null snapshot
visit = swh_storage.origin_visit_add(
- [OriginVisit(origin=origin.url, date=visits[0], type=visit_type,)]
+ [
+ OriginVisit(
+ origin=origin.url,
+ date=visits[0],
+ type=visit_type,
+ )
+ ]
)[0]
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=visit.visit,
date=now(),
status="created",
snapshot=None,
)
]
)
# add visits to origin
snapshots = set()
for date_visit in visits[1:]:
visit = swh_storage.origin_visit_add(
- [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)]
+ [
+ OriginVisit(
+ origin=origin.url,
+ date=date_visit,
+ type=visit_type,
+ )
+ ]
)[0]
# pick a random snapshot and keep track of it
snapshot = random.choice(sample_data.snapshots).id
snapshots.add(snapshot)
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=visit.visit,
date=now(),
status="full",
snapshot=snapshot,
)
]
)
# check expected snapshots are returned
assert set(swh_storage.origin_snapshot_get_all(origin.url)) == snapshots
def test_origin_get_by_sha1(self, swh_storage, sample_data):
origin = sample_data.origin
assert swh_storage.origin_get([origin.url])[0] is None
swh_storage.origin_add([origin])
origins = list(swh_storage.origin_get_by_sha1([sha1(origin.url)]))
assert len(origins) == 1
assert origins[0]["url"] == origin.url
def test_origin_get_by_sha1_not_found(self, swh_storage, sample_data):
unknown_origin = sample_data.origin
assert swh_storage.origin_get([unknown_origin.url])[0] is None
origins = list(swh_storage.origin_get_by_sha1([sha1(unknown_origin.url)]))
assert len(origins) == 1
assert origins[0] is None
def test_origin_search_single_result(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
actual_page = swh_storage.origin_search(origin.url)
assert actual_page.next_page_token is None
assert actual_page.results == []
actual_page = swh_storage.origin_search(origin.url, regexp=True)
assert actual_page.next_page_token is None
assert actual_page.results == []
swh_storage.origin_add([origin])
actual_page = swh_storage.origin_search(origin.url)
assert actual_page.next_page_token is None
assert actual_page.results == [origin]
actual_page = swh_storage.origin_search(f".{origin.url[1:-1]}.", regexp=True)
assert actual_page.next_page_token is None
assert actual_page.results == [origin]
swh_storage.origin_add([origin2])
actual_page = swh_storage.origin_search(origin2.url)
assert actual_page.next_page_token is None
assert actual_page.results == [origin2]
actual_page = swh_storage.origin_search(f".{origin2.url[1:-1]}.", regexp=True)
assert actual_page.next_page_token is None
assert actual_page.results == [origin2]
def test_origin_search_no_regexp(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
swh_storage.origin_add([origin, origin2])
# no pagination
actual_page = swh_storage.origin_search("/")
assert actual_page.next_page_token is None
assert actual_page.results == [origin, origin2]
# offset=0
actual_page = swh_storage.origin_search("/", page_token=None, limit=1)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [origin]
# offset=1
actual_page = swh_storage.origin_search(
"/", page_token=next_page_token, limit=1
)
assert actual_page.next_page_token is None
assert actual_page.results == [origin2]
def test_origin_search_regexp_substring(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
swh_storage.origin_add([origin, origin2])
# no pagination
actual_page = swh_storage.origin_search("/", regexp=True)
assert actual_page.next_page_token is None
assert actual_page.results == [origin, origin2]
# offset=0
actual_page = swh_storage.origin_search(
"/", page_token=None, limit=1, regexp=True
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [origin]
# offset=1
actual_page = swh_storage.origin_search(
"/", page_token=next_page_token, limit=1, regexp=True
)
assert actual_page.next_page_token is None
assert actual_page.results == [origin2]
def test_origin_search_regexp_fullstring(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
swh_storage.origin_add([origin, origin2])
# no pagination
actual_page = swh_storage.origin_search(".*/.*", regexp=True)
assert actual_page.next_page_token is None
assert actual_page.results == [origin, origin2]
# offset=0
actual_page = swh_storage.origin_search(
".*/.*", page_token=None, limit=1, regexp=True
)
next_page_token = actual_page.next_page_token
assert next_page_token is not None
assert actual_page.results == [origin]
# offset=1
actual_page = swh_storage.origin_search(
".*/.*", page_token=next_page_token, limit=1, regexp=True
)
assert actual_page.next_page_token is None
assert actual_page.results == [origin2]
def test_origin_search_no_visit_types(self, swh_storage, sample_data):
origin = sample_data.origins[0]
swh_storage.origin_add([origin])
actual_page = swh_storage.origin_search(origin.url, visit_types=["git"])
assert actual_page.next_page_token is None
assert actual_page.results == []
def test_origin_search_with_visit_types(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
swh_storage.origin_add([origin, origin2])
swh_storage.origin_visit_add(
[
OriginVisit(origin=origin.url, date=now(), type="git"),
OriginVisit(origin=origin2.url, date=now(), type="svn"),
]
)
actual_page = swh_storage.origin_search(origin.url, visit_types=["git"])
assert actual_page.next_page_token is None
assert actual_page.results == [origin]
actual_page = swh_storage.origin_search(origin2.url, visit_types=["svn"])
assert actual_page.next_page_token is None
assert actual_page.results == [origin2]
def test_origin_search_multiple_visit_types(self, swh_storage, sample_data):
origin = sample_data.origins[0]
swh_storage.origin_add([origin])
def _add_visit_type(visit_type):
swh_storage.origin_visit_add(
[OriginVisit(origin=origin.url, date=now(), type=visit_type)]
)
def _check_visit_types(visit_types):
actual_page = swh_storage.origin_search(origin.url, visit_types=visit_types)
assert actual_page.next_page_token is None
assert actual_page.results == [origin]
_add_visit_type("git")
_check_visit_types(["git"])
_check_visit_types(["git", "hg"])
_add_visit_type("hg")
_check_visit_types(["hg"])
_check_visit_types(["git", "hg"])
def test_origin_visit_add(self, swh_storage, sample_data):
origin1 = sample_data.origins[1]
swh_storage.origin_add([origin1])
date_visit = now()
date_visit2 = date_visit + datetime.timedelta(minutes=1)
date_visit = round_to_milliseconds(date_visit)
date_visit2 = round_to_milliseconds(date_visit2)
visit1 = OriginVisit(
- origin=origin1.url, date=date_visit, type=sample_data.type_visit1,
+ origin=origin1.url,
+ date=date_visit,
+ type=sample_data.type_visit1,
)
visit2 = OriginVisit(
- origin=origin1.url, date=date_visit2, type=sample_data.type_visit2,
+ origin=origin1.url,
+ date=date_visit2,
+ type=sample_data.type_visit2,
)
# add once
ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2])
# then again (will be ignored as they already exist)
origin_visit1, origin_visit2 = swh_storage.origin_visit_add([ov1, ov2])
assert ov1 == origin_visit1
assert ov2 == origin_visit2
assert ov1.visit == 1
assert ov2.visit == 2
ovs1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit,
type=ov1.type,
status="created",
snapshot=None,
)
ovs2 = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=date_visit2,
type=ov2.type,
status="created",
snapshot=None,
)
actual_visits = swh_storage.origin_visit_get(origin1.url).results
expected_visits = [ov1, ov2]
assert len(expected_visits) == len(actual_visits)
for visit in expected_visits:
assert visit in actual_visits
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_objects = list(
[("origin", origin1)]
+ [("origin_visit", visit) for visit in expected_visits] * 2
+ [("origin_visit_status", ovs) for ovs in [ovs1, ovs2]]
)
for obj in expected_objects:
assert obj in actual_objects
def test_origin_visit_add_replayed(self, swh_storage, sample_data):
"""Tests adding a visit with an id makes sure the next id is higher"""
origin1 = sample_data.origins[1]
swh_storage.origin_add([origin1])
date_visit = now()
date_visit2 = date_visit + datetime.timedelta(minutes=1)
date_visit = round_to_milliseconds(date_visit)
date_visit2 = round_to_milliseconds(date_visit2)
visit1 = OriginVisit(
origin=origin1.url, date=date_visit, type=sample_data.type_visit1, visit=42
)
visit2 = OriginVisit(
- origin=origin1.url, date=date_visit2, type=sample_data.type_visit2,
+ origin=origin1.url,
+ date=date_visit2,
+ type=sample_data.type_visit2,
)
# add once
ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2])
# then again (will be ignored as they already exist)
origin_visit1, origin_visit2 = swh_storage.origin_visit_add([ov1, ov2])
assert ov1 == origin_visit1
assert ov2 == origin_visit2
assert ov1.visit == 42
assert ov2.visit == 43
visit3 = OriginVisit(
origin=origin1.url, date=date_visit, type=sample_data.type_visit1, visit=12
)
visit4 = OriginVisit(
- origin=origin1.url, date=date_visit2, type=sample_data.type_visit2,
+ origin=origin1.url,
+ date=date_visit2,
+ type=sample_data.type_visit2,
)
# add once
ov3, ov4 = swh_storage.origin_visit_add([visit3, visit4])
# then again (will be ignored as they already exist)
origin_visit3, origin_visit4 = swh_storage.origin_visit_add([ov3, ov4])
assert ov3 == origin_visit3
assert ov4 == origin_visit4
assert ov3.visit == 12
assert ov4.visit == 44
def test_origin_visit_add_validation(self, swh_storage, sample_data):
"""Unknown origin when adding visits should raise"""
visit = attr.evolve(sample_data.origin_visit, origin="something-unknonw")
with pytest.raises(StorageArgumentException, match="Unknown origin"):
swh_storage.origin_visit_add([visit])
objects = list(swh_storage.journal_writer.journal.objects)
assert not objects
def test_origin_visit_status_add_validation(self, swh_storage):
"""Wrong origin_visit_status input should raise storage argument error"""
date_visit = now()
visit_status1 = OriginVisitStatus(
origin="unknown-origin-url",
visit=10,
date=date_visit,
status="full",
snapshot=None,
)
with pytest.raises(StorageArgumentException, match="Unknown origin"):
swh_storage.origin_visit_status_add([visit_status1])
objects = list(swh_storage.journal_writer.journal.objects)
assert not objects
def test_origin_visit_status_add(self, swh_storage, sample_data):
- """Correct origin visit statuses should add a new visit status
-
- """
+ """Correct origin visit statuses should add a new visit status"""
snapshot = sample_data.snapshot
origin1 = sample_data.origins[1]
origin2 = Origin(url="new-origin")
swh_storage.origin_add([origin1, origin2])
ov1, ov2 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin1.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
),
OriginVisit(
origin=origin2.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
),
]
)
ovs1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=sample_data.date_visit1,
type=ov1.type,
status="created",
snapshot=None,
)
ovs2 = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=sample_data.date_visit2,
type=ov2.type,
status="created",
snapshot=None,
)
date_visit_now = round_to_milliseconds(now())
visit_status1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit_now,
type=ov1.type,
status="full",
snapshot=snapshot.id,
)
date_visit_now = round_to_milliseconds(now())
visit_status2 = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=date_visit_now,
type=ov2.type,
status="ongoing",
snapshot=None,
metadata={"intrinsic": "something"},
)
stats = swh_storage.origin_visit_status_add([visit_status1, visit_status2])
assert stats == {"origin_visit_status:add": 2}
visit = swh_storage.origin_visit_get_latest(origin1.url, require_snapshot=True)
visit_status = swh_storage.origin_visit_status_get_latest(
origin1.url, visit.visit, require_snapshot=True
)
assert visit_status == visit_status1
visit = swh_storage.origin_visit_get_latest(origin2.url, require_snapshot=False)
visit_status = swh_storage.origin_visit_status_get_latest(
origin2.url, visit.visit, require_snapshot=False
)
assert origin2.url != origin1.url
assert visit_status == visit_status2
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_origins = [origin1, origin2]
expected_visits = [ov1, ov2]
expected_visit_statuses = [ovs1, ovs2, visit_status1, visit_status2]
expected_objects = (
[("origin", o) for o in expected_origins]
+ [("origin_visit", v) for v in expected_visits]
+ [("origin_visit_status", ovs) for ovs in expected_visit_statuses]
)
for obj in expected_objects:
assert obj in actual_objects
def test_origin_visit_status_add_twice(self, swh_storage, sample_data):
- """Correct origin visit statuses should add a new visit status
-
- """
+ """Correct origin visit statuses should add a new visit status"""
snapshot = sample_data.snapshot
origin1 = sample_data.origins[1]
swh_storage.origin_add([origin1])
ov1 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin1.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
),
]
)[0]
ovs1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=sample_data.date_visit1,
type=ov1.type,
status="created",
snapshot=None,
)
date_visit_now = round_to_milliseconds(now())
visit_status1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_visit_now,
type=ov1.type,
status="full",
snapshot=snapshot.id,
)
stats = swh_storage.origin_visit_status_add([visit_status1])
assert stats == {"origin_visit_status:add": 1}
# second call will ignore existing entries (will send to storage though)
stats = swh_storage.origin_visit_status_add([visit_status1])
# ...so the storage still returns it as an addition
assert stats == {"origin_visit_status:add": 1}
visit_status = swh_storage.origin_visit_status_get_latest(ov1.origin, ov1.visit)
assert visit_status == visit_status1
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_origins = [origin1]
expected_visits = [ov1]
expected_visit_statuses = [ovs1, visit_status1, visit_status1]
# write twice in the journal
expected_objects = (
[("origin", o) for o in expected_origins]
+ [("origin_visit", v) for v in expected_visits]
+ [("origin_visit_status", ovs) for ovs in expected_visit_statuses]
)
for obj in expected_objects:
assert obj in actual_objects
def test_origin_visit_find_by_date(self, swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
visit1 = OriginVisit(
origin=origin.url,
date=sample_data.date_visit2,
type=sample_data.type_visit1,
)
visit2 = OriginVisit(
origin=origin.url,
date=sample_data.date_visit3,
type=sample_data.type_visit2,
)
visit3 = OriginVisit(
origin=origin.url,
date=sample_data.date_visit2,
type=sample_data.type_visit3,
)
ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3])
ovs1 = OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=sample_data.date_visit2,
status="ongoing",
snapshot=None,
)
ovs2 = OriginVisitStatus(
origin=origin.url,
visit=ov2.visit,
date=sample_data.date_visit3,
status="ongoing",
snapshot=None,
)
ovs3 = OriginVisitStatus(
origin=origin.url,
visit=ov3.visit,
date=sample_data.date_visit2,
status="ongoing",
snapshot=None,
)
swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3])
# Simple case
actual_visit = swh_storage.origin_visit_find_by_date(
origin.url, sample_data.date_visit3
)
assert actual_visit == ov2
# There are two visits at the same date, the latest must be returned
actual_visit = swh_storage.origin_visit_find_by_date(
origin.url, sample_data.date_visit2
)
assert actual_visit == ov3
def test_origin_visit_find_by_date__unknown_origin(self, swh_storage, sample_data):
actual_visit = swh_storage.origin_visit_find_by_date(
"foo", sample_data.date_visit2
)
assert actual_visit is None
def test_origin_visit_get_by(self, swh_storage, sample_data):
snapshot = sample_data.snapshot
origins = sample_data.origins[:2]
swh_storage.origin_add(origins)
origin_url, origin_url2 = [o.url for o in origins]
visit = OriginVisit(
origin=origin_url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
)
origin_visit1 = swh_storage.origin_visit_add([visit])[0]
swh_storage.snapshot_add([snapshot])
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin_url,
visit=origin_visit1.visit,
date=now(),
status="ongoing",
snapshot=snapshot.id,
)
]
)
# Add some other {origin, visit} entries
visit2 = OriginVisit(
origin=origin_url,
date=sample_data.date_visit3,
type=sample_data.type_visit3,
)
visit3 = OriginVisit(
origin=origin_url2,
date=sample_data.date_visit3,
type=sample_data.type_visit3,
)
swh_storage.origin_visit_add([visit2, visit3])
# when
visit1_metadata = {
"contents": 42,
"directories": 22,
}
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin_url,
visit=origin_visit1.visit,
date=now(),
status="full",
snapshot=snapshot.id,
metadata=visit1_metadata,
)
]
)
actual_visit = swh_storage.origin_visit_get_by(origin_url, origin_visit1.visit)
assert actual_visit == origin_visit1
def test_origin_visit_get_by__no_result(self, swh_storage, sample_data):
actual_visit = swh_storage.origin_visit_get_by("unknown", 10) # unknown origin
assert actual_visit is None
origin = sample_data.origin
swh_storage.origin_add([origin])
actual_visit = swh_storage.origin_visit_get_by(origin.url, 999) # unknown visit
assert actual_visit is None
def test_origin_visit_get_latest_edge_cases(self, swh_storage, sample_data):
# unknown origin so no result
assert swh_storage.origin_visit_get_latest("unknown-origin") is None
# unknown type so no result
origin = sample_data.origin
swh_storage.origin_add([origin])
assert swh_storage.origin_visit_get_latest(origin.url, type="unknown") is None
# unknown allowed statuses should raise
with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"):
swh_storage.origin_visit_get_latest(
origin.url, allowed_statuses=["unknown"]
)
def test_origin_visit_get_latest_filter_type(self, swh_storage, sample_data):
- """Filtering origin visit get latest with filter type should be ok
-
- """
+ """Filtering origin visit get latest with filter type should be ok"""
origin = sample_data.origin
swh_storage.origin_add([origin])
visit1 = OriginVisit(
- origin=origin.url, date=sample_data.date_visit1, type="git",
+ origin=origin.url,
+ date=sample_data.date_visit1,
+ type="git",
)
visit2 = OriginVisit(
- origin=origin.url, date=sample_data.date_visit2, type="hg",
+ origin=origin.url,
+ date=sample_data.date_visit2,
+ type="hg",
)
date_now = round_to_milliseconds(now())
- visit3 = OriginVisit(origin=origin.url, date=date_now, type="hg",)
+ visit3 = OriginVisit(
+ origin=origin.url,
+ date=date_now,
+ type="hg",
+ )
assert sample_data.date_visit1 < sample_data.date_visit2
assert sample_data.date_visit2 < date_now
ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3])
# Check type filter is ok
actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="git")
assert actual_visit == ov1
actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="hg")
assert actual_visit == ov3
actual_visit_unknown_type = swh_storage.origin_visit_get_latest(
- origin.url, type="npm", # no visit matching that type
+ origin.url,
+ type="npm", # no visit matching that type
)
assert actual_visit_unknown_type is None
def test_origin_visit_get_latest(self, swh_storage, sample_data):
empty_snapshot, complete_snapshot = sample_data.snapshots[1:3]
origin = sample_data.origin
swh_storage.origin_add([origin])
visit1 = OriginVisit(
- origin=origin.url, date=sample_data.date_visit1, type="git",
+ origin=origin.url,
+ date=sample_data.date_visit1,
+ type="git",
)
visit2 = OriginVisit(
- origin=origin.url, date=sample_data.date_visit2, type="hg",
+ origin=origin.url,
+ date=sample_data.date_visit2,
+ type="hg",
)
date_now = round_to_milliseconds(now())
- visit3 = OriginVisit(origin=origin.url, date=date_now, type="hg",)
+ visit3 = OriginVisit(
+ origin=origin.url,
+ date=date_now,
+ type="hg",
+ )
assert visit1.date < visit2.date
assert visit2.date < visit3.date
ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3])
# no filters, latest visit is the last one (whose date is most recent)
actual_visit = swh_storage.origin_visit_get_latest(origin.url)
assert actual_visit == ov3
# 3 visits, none has snapshot so nothing is returned
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, require_snapshot=True
)
assert actual_visit is None
# visit are created with "created" status, so nothing will get returned
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, allowed_statuses=["partial"]
)
assert actual_visit is None
# visit are created with "created" status, so most recent again
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, allowed_statuses=["created"]
)
assert actual_visit == ov3
# Add snapshot to visit1; require_snapshot=True makes it return first visit
swh_storage.snapshot_add([complete_snapshot])
visit_status_with_snapshot = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=round_to_milliseconds(now()),
type=ov1.type,
status="ongoing",
snapshot=complete_snapshot.id,
)
swh_storage.origin_visit_status_add([visit_status_with_snapshot])
# only the first visit has a snapshot now
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, require_snapshot=True
)
assert actual_visit == ov1
# only the first visit has a status ongoing now
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, allowed_statuses=["ongoing"]
)
assert actual_visit == ov1
actual_visit_status = swh_storage.origin_visit_status_get_latest(
origin.url, ov1.visit, require_snapshot=True
)
assert actual_visit_status == visit_status_with_snapshot
# ... and require_snapshot=False (defaults) still returns latest visit (3rd)
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, require_snapshot=False
)
assert actual_visit == ov3
# no specific filter, this returns as before the latest visit
actual_visit = swh_storage.origin_visit_get_latest(origin.url)
assert actual_visit == ov3
# Status filter: all three visits are status=ongoing, so no visit
# returned
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, allowed_statuses=["full"]
)
assert actual_visit is None
visit_status1_full = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=round_to_milliseconds(now()),
type=ov1.type,
status="full",
snapshot=complete_snapshot.id,
)
# Mark the first visit as completed and check status filter again
swh_storage.origin_visit_status_add([visit_status1_full])
# only the first visit has the full status
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, allowed_statuses=["full"]
)
assert actual_visit == ov1
actual_visit_status = swh_storage.origin_visit_status_get_latest(
origin.url, ov1.visit, allowed_statuses=["full"]
)
assert actual_visit_status == visit_status1_full
# no specific filter, this returns as before the latest visit
actual_visit = swh_storage.origin_visit_get_latest(origin.url)
assert actual_visit == ov3
# Add snapshot to visit2 and check that the new snapshot is returned
swh_storage.snapshot_add([empty_snapshot])
visit_status2_full = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=round_to_milliseconds(now()),
type=ov2.type,
status="ongoing",
snapshot=empty_snapshot.id,
)
swh_storage.origin_visit_status_add([visit_status2_full])
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, require_snapshot=True
)
# 2nd visit is most recent with a snapshot
assert actual_visit == ov2
actual_visit_status = swh_storage.origin_visit_status_get_latest(
origin.url, ov2.visit, require_snapshot=True
)
assert actual_visit_status == visit_status2_full
# no specific filter, this returns as before the latest visit, 3rd one
actual_origin = swh_storage.origin_visit_get_latest(origin.url)
assert actual_origin == ov3
# full status is still the first visit
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, allowed_statuses=["full"]
)
assert actual_visit == ov1
# Add snapshot to visit3 (same date as visit2)
visit_status3_with_snapshot = OriginVisitStatus(
origin=ov3.origin,
visit=ov3.visit,
date=round_to_milliseconds(now()),
type=ov3.type,
status="ongoing",
snapshot=complete_snapshot.id,
)
swh_storage.origin_visit_status_add([visit_status3_with_snapshot])
# full status is still the first visit
actual_visit = swh_storage.origin_visit_get_latest(
- origin.url, allowed_statuses=["full"], require_snapshot=True,
+ origin.url,
+ allowed_statuses=["full"],
+ require_snapshot=True,
)
assert actual_visit == ov1
actual_visit_status = swh_storage.origin_visit_status_get_latest(
origin.url,
visit=actual_visit.visit,
allowed_statuses=["full"],
require_snapshot=True,
)
assert actual_visit_status == visit_status1_full
# most recent is still the 3rd visit
actual_visit = swh_storage.origin_visit_get_latest(origin.url)
assert actual_visit == ov3
# 3rd visit has a snapshot now, so it's elected
actual_visit = swh_storage.origin_visit_get_latest(
origin.url, require_snapshot=True
)
assert actual_visit == ov3
actual_visit_status = swh_storage.origin_visit_status_get_latest(
origin.url, ov3.visit, require_snapshot=True
)
assert actual_visit_status == visit_status3_with_snapshot
def test_origin_visit_get_latest__same_date(self, swh_storage, sample_data):
empty_snapshot, complete_snapshot = sample_data.snapshots[1:3]
origin = sample_data.origin
swh_storage.origin_add([origin])
visit1 = OriginVisit(
- origin=origin.url, date=sample_data.date_visit1, type="git",
+ origin=origin.url,
+ date=sample_data.date_visit1,
+ type="git",
)
visit2 = OriginVisit(
- origin=origin.url, date=sample_data.date_visit1, type="hg",
+ origin=origin.url,
+ date=sample_data.date_visit1,
+ type="hg",
)
ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2])
# ties should be broken by using the visit id
actual_visit = swh_storage.origin_visit_get_latest(origin.url)
assert actual_visit == ov2
def test_origin_visit_get_latest_order(self, swh_storage, sample_data):
empty_snapshot, complete_snapshot = sample_data.snapshots[1:3]
origin = sample_data.origin
id1 = 2
id2 = 1
id3 = 3
date1 = datetime.datetime(2021, 8, 2, tzinfo=datetime.timezone.utc)
date2 = datetime.datetime(2021, 8, 3, tzinfo=datetime.timezone.utc)
date3 = datetime.datetime(2021, 8, 1, tzinfo=datetime.timezone.utc)
swh_storage.origin_add([origin])
- visit1 = OriginVisit(origin=origin.url, visit=id1, date=date1, type="git",)
- visit2 = OriginVisit(origin=origin.url, visit=id2, date=date2, type="hg",)
- visit3 = OriginVisit(origin=origin.url, visit=id3, date=date3, type="tar",)
+ visit1 = OriginVisit(
+ origin=origin.url,
+ visit=id1,
+ date=date1,
+ type="git",
+ )
+ visit2 = OriginVisit(
+ origin=origin.url,
+ visit=id2,
+ date=date2,
+ type="hg",
+ )
+ visit3 = OriginVisit(
+ origin=origin.url,
+ visit=id3,
+ date=date3,
+ type="tar",
+ )
ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3])
# no filters
actual_visit = swh_storage.origin_visit_get_latest(origin.url)
assert actual_visit == ov3
def test_origin_visit_get_latest__not_last(self, swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
visit1, visit2 = sample_data.origin_visits[:2]
assert visit1.origin == origin.url
swh_storage.origin_visit_add([visit1])
ov1 = swh_storage.origin_visit_get_latest(origin.url)
# Add snapshot to visit1, latest snapshot = visit 1 snapshot
complete_snapshot = sample_data.snapshots[2]
swh_storage.snapshot_add([complete_snapshot])
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=visit2.date,
status="partial",
snapshot=None,
)
]
)
assert visit1.date < visit2.date
# no snapshot associated to the visit, so None
visit = swh_storage.origin_visit_get_latest(
- origin.url, allowed_statuses=["partial"], require_snapshot=True,
+ origin.url,
+ allowed_statuses=["partial"],
+ require_snapshot=True,
)
assert visit is None
date_now = now()
assert visit2.date < date_now
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=date_now,
status="full",
snapshot=complete_snapshot.id,
)
]
)
swh_storage.origin_visit_add(
- [OriginVisit(origin=origin.url, date=now(), type=visit1.type,)]
+ [
+ OriginVisit(
+ origin=origin.url,
+ date=now(),
+ type=visit1.type,
+ )
+ ]
)
visit = swh_storage.origin_visit_get_latest(origin.url, require_snapshot=True)
assert visit is not None
def test_origin_visit_status_get_latest__validation(self, swh_storage, sample_data):
origin = sample_data.origin
swh_storage.origin_add([origin])
visit1 = OriginVisit(
- origin=origin.url, date=sample_data.date_visit1, type="git",
+ origin=origin.url,
+ date=sample_data.date_visit1,
+ type="git",
)
# unknown allowed statuses should raise
with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"):
swh_storage.origin_visit_status_get_latest(
origin.url, visit1.visit, allowed_statuses=["unknown"]
)
def test_origin_visit_status_get_latest(self, swh_storage, sample_data):
snapshot = sample_data.snapshots[2]
origin1 = sample_data.origin
swh_storage.origin_add([origin1])
# to have some reference visits
ov1, ov2 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin1.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
),
OriginVisit(
origin=origin1.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
),
]
)
swh_storage.snapshot_add([snapshot])
date_now = round_to_milliseconds(now())
assert sample_data.date_visit1 < sample_data.date_visit2
assert sample_data.date_visit2 < date_now
ovs1 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=sample_data.date_visit1,
type=ov1.type,
status="partial",
snapshot=None,
)
ovs2 = OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=sample_data.date_visit2,
type=ov1.type,
status="ongoing",
snapshot=None,
)
ovs3 = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=sample_data.date_visit2
+ datetime.timedelta(minutes=1), # to not be ignored
type=ov2.type,
status="ongoing",
snapshot=None,
)
ovs4 = OriginVisitStatus(
origin=ov2.origin,
visit=ov2.visit,
date=date_now,
type=ov2.type,
status="full",
snapshot=snapshot.id,
metadata={"something": "wicked"},
)
swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3, ovs4])
# unknown origin so no result
actual_origin_visit = swh_storage.origin_visit_status_get_latest(
"unknown-origin", ov1.visit
)
assert actual_origin_visit is None
# unknown visit so no result
actual_origin_visit = swh_storage.origin_visit_status_get_latest(
ov1.origin, ov1.visit + 10
)
assert actual_origin_visit is None
# Two visits, both with no snapshot, take the most recent
actual_origin_visit2 = swh_storage.origin_visit_status_get_latest(
origin1.url, ov1.visit
)
assert isinstance(actual_origin_visit2, OriginVisitStatus)
assert actual_origin_visit2 == ovs2
assert ovs2.origin == origin1.url
assert ovs2.visit == ov1.visit
actual_origin_visit = swh_storage.origin_visit_status_get_latest(
origin1.url, ov1.visit, require_snapshot=True
)
# there is no visit with snapshot yet for that visit
assert actual_origin_visit is None
actual_origin_visit2 = swh_storage.origin_visit_status_get_latest(
origin1.url, ov1.visit, allowed_statuses=["partial", "ongoing"]
)
# visit status with partial status visit elected
assert actual_origin_visit2 == ovs2
assert actual_origin_visit2.status == "ongoing"
actual_origin_visit4 = swh_storage.origin_visit_status_get_latest(
origin1.url, ov2.visit, require_snapshot=True
)
assert actual_origin_visit4 == ovs4
assert actual_origin_visit4.snapshot == snapshot.id
actual_origin_visit = swh_storage.origin_visit_status_get_latest(
origin1.url, ov2.visit, require_snapshot=True, allowed_statuses=["ongoing"]
)
# nothing matches so nothing
assert actual_origin_visit is None # there is no visit with status full
actual_origin_visit3 = swh_storage.origin_visit_status_get_latest(
origin1.url, ov2.visit, allowed_statuses=["ongoing"]
)
assert actual_origin_visit3 == ovs3
def test_person_fullname_unicity(self, swh_storage, sample_data):
revision, rev2 = sample_data.revisions[0:2]
# create a revision with same committer fullname but wo name and email
revision2 = attr.evolve(
rev2,
committer=Person(
fullname=revision.committer.fullname, name=None, email=None
),
)
swh_storage.revision_add([revision, revision2])
# when getting added revisions
revisions = swh_storage.revision_get([revision.id, revision2.id])
# then check committers are the same
assert revisions[0].committer == revisions[1].committer
def test_snapshot_add_get_empty(self, swh_storage, sample_data):
empty_snapshot = sample_data.snapshots[1]
empty_snapshot_dict = empty_snapshot.to_dict()
origin = sample_data.origin
swh_storage.origin_add([origin])
ov1 = swh_storage.origin_visit_add(
[
OriginVisit(
origin=origin.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
)
]
)[0]
actual_result = swh_storage.snapshot_add([empty_snapshot])
assert actual_result == {"snapshot:add": 1}
date_now = now()
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=ov1.origin,
visit=ov1.visit,
date=date_now,
type=ov1.type,
status="full",
snapshot=empty_snapshot.id,
)
]
)
by_id = swh_storage.snapshot_get(empty_snapshot.id)
assert by_id == {**empty_snapshot_dict, "next_branch": None}
ovs1 = OriginVisitStatus.from_dict(
{
"origin": ov1.origin,
"date": sample_data.date_visit1,
"type": ov1.type,
"visit": ov1.visit,
"status": "created",
"snapshot": None,
"metadata": None,
}
)
ovs2 = OriginVisitStatus.from_dict(
{
"origin": ov1.origin,
"date": date_now,
"type": ov1.type,
"visit": ov1.visit,
"status": "full",
"metadata": None,
"snapshot": empty_snapshot.id,
}
)
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_objects = [
("origin", origin),
("origin_visit", ov1),
- ("origin_visit_status", ovs1,),
+ (
+ "origin_visit_status",
+ ovs1,
+ ),
("snapshot", empty_snapshot),
- ("origin_visit_status", ovs2,),
+ (
+ "origin_visit_status",
+ ovs2,
+ ),
]
for obj in expected_objects:
assert obj in actual_objects
def test_snapshot_add_get_complete(self, swh_storage, sample_data):
complete_snapshot = sample_data.snapshots[2]
complete_snapshot_dict = complete_snapshot.to_dict()
origin = sample_data.origin
swh_storage.origin_add([origin])
visit = OriginVisit(
origin=origin.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
)
origin_visit1 = swh_storage.origin_visit_add([visit])[0]
actual_result = swh_storage.snapshot_add([complete_snapshot])
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=origin_visit1.visit,
date=now(),
status="ongoing",
snapshot=complete_snapshot.id,
)
]
)
assert actual_result == {"snapshot:add": 1}
by_id = swh_storage.snapshot_get(complete_snapshot.id)
assert by_id == {**complete_snapshot_dict, "next_branch": None}
@settings(
suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large]
+ function_scoped_fixture_check,
)
@given(strategies.lists(hypothesis_strategies.snapshots(), min_size=1, max_size=10))
def test_snapshot_add_get_arbitrary(self, swh_storage, snapshots):
swh_storage.snapshot_add(snapshots)
for snapshot in snapshots:
assert swh_storage.snapshot_get(snapshot.id) == {
**snapshot.to_dict(),
"next_branch": None,
}
def test_snapshot_add_many(self, swh_storage, sample_data):
snapshot, _, complete_snapshot = sample_data.snapshots[:3]
actual_result = swh_storage.snapshot_add([snapshot, complete_snapshot])
assert actual_result == {"snapshot:add": 2}
assert swh_storage.snapshot_get(complete_snapshot.id) == {
**complete_snapshot.to_dict(),
"next_branch": None,
}
assert swh_storage.snapshot_get(snapshot.id) == {
**snapshot.to_dict(),
"next_branch": None,
}
if isinstance(swh_storage, InMemoryStorage) or not isinstance(
swh_storage, CassandraStorage
):
swh_storage.refresh_stat_counters()
assert swh_storage.stat_counters()["snapshot"] == 2
def test_snapshot_add_many_incremental(self, swh_storage, sample_data):
snapshot, _, complete_snapshot = sample_data.snapshots[:3]
actual_result = swh_storage.snapshot_add([complete_snapshot])
assert actual_result == {"snapshot:add": 1}
actual_result2 = swh_storage.snapshot_add([snapshot, complete_snapshot])
assert actual_result2 == {"snapshot:add": 1}
assert swh_storage.snapshot_get(complete_snapshot.id) == {
**complete_snapshot.to_dict(),
"next_branch": None,
}
assert swh_storage.snapshot_get(snapshot.id) == {
**snapshot.to_dict(),
"next_branch": None,
}
def test_snapshot_add_twice(self, swh_storage, sample_data):
snapshot, empty_snapshot = sample_data.snapshots[:2]
actual_result = swh_storage.snapshot_add([empty_snapshot])
assert actual_result == {"snapshot:add": 1}
assert list(swh_storage.journal_writer.journal.objects) == [
("snapshot", empty_snapshot)
]
actual_result = swh_storage.snapshot_add([snapshot])
assert actual_result == {"snapshot:add": 1}
assert list(swh_storage.journal_writer.journal.objects) == [
("snapshot", empty_snapshot),
("snapshot", snapshot),
]
def test_snapshot_add_count_branches(self, swh_storage, sample_data):
complete_snapshot = sample_data.snapshots[2]
actual_result = swh_storage.snapshot_add([complete_snapshot])
assert actual_result == {"snapshot:add": 1}
snp_size = swh_storage.snapshot_count_branches(complete_snapshot.id)
expected_snp_size = {
"alias": 1,
"content": 1,
"directory": 2,
"release": 1,
"revision": 1,
"snapshot": 1,
None: 1,
}
assert snp_size == expected_snp_size
def test_snapshot_add_count_branches_with_filtering(self, swh_storage, sample_data):
complete_snapshot = sample_data.snapshots[2]
actual_result = swh_storage.snapshot_add([complete_snapshot])
assert actual_result == {"snapshot:add": 1}
snp_size = swh_storage.snapshot_count_branches(
complete_snapshot.id, branch_name_exclude_prefix=b"release"
)
expected_snp_size = {
"alias": 1,
"content": 1,
"directory": 2,
"revision": 1,
"snapshot": 1,
None: 1,
}
assert snp_size == expected_snp_size
def test_snapshot_add_count_branches_with_filtering_edge_cases(
self, swh_storage, sample_data
):
snapshot = Snapshot(
branches={
b"\xaa\xff": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"\xaa\xff\x00": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"\xff\xff": SnapshotBranch(
- target=sample_data.release.id, target_type=TargetType.RELEASE,
+ target=sample_data.release.id,
+ target_type=TargetType.RELEASE,
),
b"\xff\xff\x00": SnapshotBranch(
- target=sample_data.release.id, target_type=TargetType.RELEASE,
+ target=sample_data.release.id,
+ target_type=TargetType.RELEASE,
),
b"dangling": None,
},
)
swh_storage.snapshot_add([snapshot])
assert swh_storage.snapshot_count_branches(
snapshot.id, branch_name_exclude_prefix=b"\xaa\xff"
) == {None: 1, "release": 2}
assert swh_storage.snapshot_count_branches(
snapshot.id, branch_name_exclude_prefix=b"\xff\xff"
) == {None: 1, "revision": 2}
def test_snapshot_add_get_paginated(self, swh_storage, sample_data):
complete_snapshot = sample_data.snapshots[2]
swh_storage.snapshot_add([complete_snapshot])
snp_id = complete_snapshot.id
branches = complete_snapshot.branches
branch_names = list(sorted(branches))
# Test branch_from
snapshot = swh_storage.snapshot_get_branches(snp_id, branches_from=b"release")
rel_idx = branch_names.index(b"release")
expected_snapshot = {
"id": snp_id,
"branches": {name: branches[name] for name in branch_names[rel_idx:]},
"next_branch": None,
}
assert snapshot == expected_snapshot
# Test branches_count
snapshot = swh_storage.snapshot_get_branches(snp_id, branches_count=1)
expected_snapshot = {
"id": snp_id,
- "branches": {branch_names[0]: branches[branch_names[0]],},
+ "branches": {
+ branch_names[0]: branches[branch_names[0]],
+ },
"next_branch": b"content",
}
assert snapshot == expected_snapshot
# test branch_from + branches_count
snapshot = swh_storage.snapshot_get_branches(
snp_id, branches_from=b"directory", branches_count=3
)
dir_idx = branch_names.index(b"directory")
expected_snapshot = {
"id": snp_id,
"branches": {
name: branches[name] for name in branch_names[dir_idx : dir_idx + 3]
},
"next_branch": branch_names[dir_idx + 3],
}
assert snapshot == expected_snapshot
def test_snapshot_add_get_filtered(self, swh_storage, sample_data):
origin = sample_data.origin
complete_snapshot = sample_data.snapshots[2]
swh_storage.origin_add([origin])
visit = OriginVisit(
origin=origin.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
)
origin_visit1 = swh_storage.origin_visit_add([visit])[0]
swh_storage.snapshot_add([complete_snapshot])
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=origin_visit1.visit,
date=now(),
status="ongoing",
snapshot=complete_snapshot.id,
)
]
)
snp_id = complete_snapshot.id
branches = complete_snapshot.branches
snapshot = swh_storage.snapshot_get_branches(
snp_id, target_types=["release", "revision"]
)
expected_snapshot = {
"id": snp_id,
"branches": {
name: tgt
for name, tgt in branches.items()
if tgt and tgt.target_type in [TargetType.RELEASE, TargetType.REVISION]
},
"next_branch": None,
}
assert snapshot == expected_snapshot
snapshot = swh_storage.snapshot_get_branches(snp_id, target_types=["alias"])
expected_snapshot = {
"id": snp_id,
"branches": {
name: tgt
for name, tgt in branches.items()
if tgt and tgt.target_type == TargetType.ALIAS
},
"next_branch": None,
}
assert snapshot == expected_snapshot
def test_snapshot_add_get_filtered_and_paginated(self, swh_storage, sample_data):
complete_snapshot = sample_data.snapshots[2]
swh_storage.snapshot_add([complete_snapshot])
snp_id = complete_snapshot.id
branches = complete_snapshot.branches
branch_names = list(sorted(branches))
# Test branch_from
snapshot = swh_storage.snapshot_get_branches(
snp_id, target_types=["directory", "release"], branches_from=b"directory2"
)
expected_snapshot = {
"id": snp_id,
"branches": {name: branches[name] for name in (b"directory2", b"release")},
"next_branch": None,
}
assert snapshot == expected_snapshot
# Test branches_count
snapshot = swh_storage.snapshot_get_branches(
snp_id, target_types=["directory", "release"], branches_count=1
)
expected_snapshot = {
"id": snp_id,
"branches": {b"directory": branches[b"directory"]},
"next_branch": b"directory2",
}
assert snapshot == expected_snapshot
# Test branches_count
snapshot = swh_storage.snapshot_get_branches(
snp_id, target_types=["directory", "release"], branches_count=2
)
expected_snapshot = {
"id": snp_id,
"branches": {
name: branches[name] for name in (b"directory", b"directory2")
},
"next_branch": b"release",
}
assert snapshot == expected_snapshot
# test branch_from + branches_count
snapshot = swh_storage.snapshot_get_branches(
snp_id,
target_types=["directory", "release"],
branches_from=b"directory2",
branches_count=1,
)
dir_idx = branch_names.index(b"directory2")
expected_snapshot = {
"id": snp_id,
- "branches": {branch_names[dir_idx]: branches[branch_names[dir_idx]],},
+ "branches": {
+ branch_names[dir_idx]: branches[branch_names[dir_idx]],
+ },
"next_branch": b"release",
}
assert snapshot == expected_snapshot
def test_snapshot_add_get_branch_by_type(self, swh_storage, sample_data):
complete_snapshot = sample_data.snapshots[2]
snapshot = complete_snapshot.to_dict()
alias1 = b"alias1"
alias2 = b"alias2"
target1 = random.choice(list(snapshot["branches"].keys()))
target2 = random.choice(list(snapshot["branches"].keys()))
snapshot["branches"][alias2] = {
"target": target2,
"target_type": "alias",
}
snapshot["branches"][alias1] = {
"target": target1,
"target_type": "alias",
}
new_snapshot = Snapshot.from_dict(snapshot)
swh_storage.snapshot_add([new_snapshot])
branches = swh_storage.snapshot_get_branches(
new_snapshot.id,
target_types=["alias"],
branches_from=alias1,
branches_count=1,
)["branches"]
assert len(branches) == 1
assert alias1 in branches
def test_snapshot_add_get_by_branches_name_pattern(self, swh_storage, sample_data):
snapshot = Snapshot(
branches={
b"refs/heads/master": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"refs/heads/incoming": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"refs/pull/1": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"refs/pull/2": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"dangling": None,
b"\xaa\xff": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"\xaa\xff\x00": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"\xff\xff": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
b"\xff\xff\x00": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
},
)
swh_storage.snapshot_add([snapshot])
for include_pattern, exclude_prefix, nb_results in (
(b"pull", None, 2),
(b"incoming", None, 1),
(b"dangling", None, 1),
(None, b"refs/heads/", 7),
(b"refs", b"refs/heads/master", 3),
(b"refs", b"refs/heads/master", 3),
(None, b"\xaa\xff", 7),
(None, b"\xff\xff", 7),
):
branches = swh_storage.snapshot_get_branches(
snapshot.id,
branch_name_include_substring=include_pattern,
branch_name_exclude_prefix=exclude_prefix,
)["branches"]
expected_branches = [
branch_name
for branch_name in snapshot.branches
if (include_pattern is None or include_pattern in branch_name)
and (
exclude_prefix is None or not branch_name.startswith(exclude_prefix)
)
]
assert sorted(branches) == sorted(expected_branches)
assert len(branches) == nb_results
def test_snapshot_add_get_by_branches_name_pattern_filtered_paginated(
self, swh_storage, sample_data
):
pattern = b"foo"
nb_branches_by_target_type = 10
branches = {}
for i in range(nb_branches_by_target_type):
branches[f"branch/directory/bar{i}".encode()] = SnapshotBranch(
- target=sample_data.directory.id, target_type=TargetType.DIRECTORY,
+ target=sample_data.directory.id,
+ target_type=TargetType.DIRECTORY,
)
branches[f"branch/revision/bar{i}".encode()] = SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
)
branches[f"branch/directory/{pattern}{i}".encode()] = SnapshotBranch(
- target=sample_data.directory.id, target_type=TargetType.DIRECTORY,
+ target=sample_data.directory.id,
+ target_type=TargetType.DIRECTORY,
)
branches[f"branch/revision/{pattern}{i}".encode()] = SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
)
snapshot = Snapshot(branches=branches)
swh_storage.snapshot_add([snapshot])
branches_count = nb_branches_by_target_type // 2
for target_type in (
TargetType.DIRECTORY,
TargetType.REVISION,
):
target_type_str = target_type.value
partial_branches = swh_storage.snapshot_get_branches(
snapshot.id,
branch_name_include_substring=pattern,
target_types=[target_type_str],
branches_count=branches_count,
)
branches = partial_branches["branches"]
expected_branches = [
branch_name
for branch_name, branch_data in snapshot.branches.items()
if pattern in branch_name and branch_data.target_type == target_type
][:branches_count]
assert sorted(branches) == sorted(expected_branches)
assert (
partial_branches["next_branch"]
== f"branch/{target_type_str}/{pattern}{branches_count}".encode()
)
partial_branches = swh_storage.snapshot_get_branches(
snapshot.id,
branch_name_include_substring=pattern,
target_types=[target_type_str],
branches_from=partial_branches["next_branch"],
)
branches = partial_branches["branches"]
expected_branches = [
branch_name
for branch_name, branch_data in snapshot.branches.items()
if pattern in branch_name and branch_data.target_type == target_type
][branches_count:]
assert sorted(branches) == sorted(expected_branches)
assert partial_branches["next_branch"] is None
def test_snapshot_get_branches_from_no_result(self, swh_storage, sample_data):
snapshot = Snapshot(
branches={
b"refs/heads/master": SnapshotBranch(
- target=sample_data.revision.id, target_type=TargetType.REVISION,
+ target=sample_data.revision.id,
+ target_type=TargetType.REVISION,
),
},
)
swh_storage.snapshot_add([snapshot])
partial_branches = swh_storage.snapshot_get_branches(
- snapshot.id, branches_from=b"s",
+ snapshot.id,
+ branches_from=b"s",
)
assert partial_branches is not None
assert partial_branches["branches"] == {}
- @settings(suppress_health_check=function_scoped_fixture_check,)
+ @settings(
+ suppress_health_check=function_scoped_fixture_check,
+ )
@given(hypothesis_strategies.snapshots(min_size=1))
def test_snapshot_get_unknown_snapshot(self, swh_storage, unknown_snapshot):
assert swh_storage.snapshot_get(unknown_snapshot.id) is None
assert swh_storage.snapshot_get_branches(unknown_snapshot.id) is None
def test_snapshot_add_get(self, swh_storage, sample_data):
snapshot = sample_data.snapshot
origin = sample_data.origin
swh_storage.origin_add([origin])
visit = OriginVisit(
origin=origin.url,
date=sample_data.date_visit1,
type=sample_data.type_visit1,
)
ov1 = swh_storage.origin_visit_add([visit])[0]
swh_storage.snapshot_add([snapshot])
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=ov1.visit,
date=now(),
status="ongoing",
snapshot=snapshot.id,
)
]
)
expected_snapshot = {**snapshot.to_dict(), "next_branch": None}
by_id = swh_storage.snapshot_get(snapshot.id)
assert by_id == expected_snapshot
actual_visit = swh_storage.origin_visit_get_by(origin.url, ov1.visit)
assert actual_visit == ov1
visit_status = swh_storage.origin_visit_status_get_latest(
origin.url, ov1.visit, require_snapshot=True
)
assert visit_status.snapshot == snapshot.id
def test_snapshot_get_random(self, swh_storage, sample_data):
snapshot, empty_snapshot, complete_snapshot = sample_data.snapshots[:3]
swh_storage.snapshot_add([snapshot, empty_snapshot, complete_snapshot])
assert swh_storage.snapshot_get_random() in {
snapshot.id,
empty_snapshot.id,
complete_snapshot.id,
}
def test_snapshot_missing(self, swh_storage, sample_data):
snapshot, missing_snapshot = sample_data.snapshots[:2]
snapshots = [snapshot.id, missing_snapshot.id]
swh_storage.snapshot_add([snapshot])
missing_snapshots = swh_storage.snapshot_missing(snapshots)
assert list(missing_snapshots) == [missing_snapshot.id]
def test_stat_counters(self, swh_storage, sample_data):
if isinstance(swh_storage, CassandraStorage) and not isinstance(
swh_storage, InMemoryStorage
):
pytest.skip("Cassandra backend does not support stat counters")
origin = sample_data.origin
snapshot = sample_data.snapshot
revision = sample_data.revision
release = sample_data.release
directory = sample_data.directory
content = sample_data.content
expected_keys = ["content", "directory", "origin", "revision"]
# Initially, all counters are 0
swh_storage.refresh_stat_counters()
counters = swh_storage.stat_counters()
assert set(expected_keys) <= set(counters)
for key in expected_keys:
assert counters[key] == 0
# Add a content. Only the content counter should increase.
swh_storage.content_add([content])
swh_storage.refresh_stat_counters()
counters = swh_storage.stat_counters()
assert set(expected_keys) <= set(counters)
for key in expected_keys:
if key != "content":
assert counters[key] == 0
assert counters["content"] == 1
# Add other objects. Check their counter increased as well.
swh_storage.origin_add([origin])
visit = OriginVisit(
origin=origin.url,
date=sample_data.date_visit2,
type=sample_data.type_visit2,
)
origin_visit1 = swh_storage.origin_visit_add([visit])[0]
swh_storage.snapshot_add([snapshot])
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin.url,
visit=origin_visit1.visit,
date=now(),
status="ongoing",
snapshot=snapshot.id,
)
]
)
swh_storage.directory_add([directory])
swh_storage.revision_add([revision])
swh_storage.release_add([release])
swh_storage.refresh_stat_counters()
counters = swh_storage.stat_counters()
assert counters["content"] == 1
assert counters["directory"] == 1
assert counters["snapshot"] == 1
assert counters["origin"] == 1
assert counters["origin_visit"] == 1
assert counters["revision"] == 1
assert counters["release"] == 1
assert counters["snapshot"] == 1
if "person" in counters:
assert counters["person"] == 3
def test_content_find_ctime(self, swh_storage, sample_data):
origin_content = sample_data.content
ctime = round_to_milliseconds(now())
content = attr.evolve(origin_content, data=None, ctime=ctime)
swh_storage.content_add_metadata([content])
actually_present = swh_storage.content_find({"sha1": content.sha1})
assert actually_present[0] == content
assert actually_present[0].ctime is not None
assert actually_present[0].ctime.tzinfo is not None
def test_content_find_with_present_content(self, swh_storage, sample_data):
content = sample_data.content
expected_content = attr.evolve(content, data=None)
# 1. with something to find
swh_storage.content_add([content])
actually_present = swh_storage.content_find({"sha1": content.sha1})
assert 1 == len(actually_present)
assert actually_present[0] == expected_content
# 2. with something to find
actually_present = swh_storage.content_find({"sha1_git": content.sha1_git})
assert 1 == len(actually_present)
assert actually_present[0] == expected_content
# 3. with something to find
actually_present = swh_storage.content_find({"sha256": content.sha256})
assert 1 == len(actually_present)
assert actually_present[0] == expected_content
# 4. with something to find
actually_present = swh_storage.content_find(content.hashes())
assert 1 == len(actually_present)
assert actually_present[0] == expected_content
def test_content_find_with_non_present_content(self, swh_storage, sample_data):
missing_content = sample_data.skipped_content
# 1. with something that does not exist
actually_present = swh_storage.content_find({"sha1": missing_content.sha1})
assert actually_present == []
# 2. with something that does not exist
actually_present = swh_storage.content_find(
{"sha1_git": missing_content.sha1_git}
)
assert actually_present == []
# 3. with something that does not exist
actually_present = swh_storage.content_find({"sha256": missing_content.sha256})
assert actually_present == []
def test_content_find_with_duplicate_input(self, swh_storage, sample_data):
content = sample_data.content
# Create fake data with colliding sha256 and blake2s256
sha1_array = bytearray(content.sha1)
sha1_array[0] += 1
sha1git_array = bytearray(content.sha1_git)
sha1git_array[0] += 1
duplicated_content = attr.evolve(
content, sha1=bytes(sha1_array), sha1_git=bytes(sha1git_array)
)
# Inject the data
swh_storage.content_add([content, duplicated_content])
actual_result = swh_storage.content_find(
{
"blake2s256": duplicated_content.blake2s256,
"sha256": duplicated_content.sha256,
}
)
expected_content = attr.evolve(content, data=None)
expected_duplicated_content = attr.evolve(duplicated_content, data=None)
for result in actual_result:
assert result in [expected_content, expected_duplicated_content]
def test_content_find_with_duplicate_sha256(self, swh_storage, sample_data):
content = sample_data.content
hashes = {}
# Create fake data with colliding sha256
for hashalgo in ("sha1", "sha1_git", "blake2s256"):
value = bytearray(getattr(content, hashalgo))
value[0] += 1
hashes[hashalgo] = bytes(value)
duplicated_content = attr.evolve(
content,
sha1=hashes["sha1"],
sha1_git=hashes["sha1_git"],
blake2s256=hashes["blake2s256"],
)
swh_storage.content_add([content, duplicated_content])
actual_result = swh_storage.content_find({"sha256": duplicated_content.sha256})
assert len(actual_result) == 2
expected_content = attr.evolve(content, data=None)
expected_duplicated_content = attr.evolve(duplicated_content, data=None)
for result in actual_result:
assert result in [expected_content, expected_duplicated_content]
# Find with both sha256 and blake2s256
actual_result = swh_storage.content_find(
{
"sha256": duplicated_content.sha256,
"blake2s256": duplicated_content.blake2s256,
}
)
assert len(actual_result) == 1
assert actual_result == [expected_duplicated_content]
def test_content_find_with_duplicate_blake2s256(self, swh_storage, sample_data):
content = sample_data.content
# Create fake data with colliding sha256 and blake2s256
sha1_array = bytearray(content.sha1)
sha1_array[0] += 1
sha1git_array = bytearray(content.sha1_git)
sha1git_array[0] += 1
sha256_array = bytearray(content.sha256)
sha256_array[0] += 1
duplicated_content = attr.evolve(
content,
sha1=bytes(sha1_array),
sha1_git=bytes(sha1git_array),
sha256=bytes(sha256_array),
)
swh_storage.content_add([content, duplicated_content])
actual_result = swh_storage.content_find(
{"blake2s256": duplicated_content.blake2s256}
)
expected_content = attr.evolve(content, data=None)
expected_duplicated_content = attr.evolve(duplicated_content, data=None)
for result in actual_result:
assert result in [expected_content, expected_duplicated_content]
# Find with both sha256 and blake2s256
actual_result = swh_storage.content_find(
{
"sha256": duplicated_content.sha256,
"blake2s256": duplicated_content.blake2s256,
}
)
assert actual_result == [expected_duplicated_content]
def test_content_find_bad_input(self, swh_storage):
# 1. with no hash to lookup
with pytest.raises(StorageArgumentException):
swh_storage.content_find({}) # need at least one hash
# 2. with bad hash
with pytest.raises(StorageArgumentException):
swh_storage.content_find({"unknown-sha1": "something"}) # not the right key
def test_object_find_by_sha1_git(self, swh_storage, sample_data):
content = sample_data.content
directory = sample_data.directory
revision = sample_data.revision
release = sample_data.release
sha1_gits = [b"00000000000000000000"]
expected = {
b"00000000000000000000": [],
}
swh_storage.content_add([content])
sha1_gits.append(content.sha1_git)
expected[content.sha1_git] = [
- {"sha1_git": content.sha1_git, "type": "content",}
+ {
+ "sha1_git": content.sha1_git,
+ "type": "content",
+ }
]
swh_storage.directory_add([directory])
sha1_gits.append(directory.id)
- expected[directory.id] = [{"sha1_git": directory.id, "type": "directory",}]
+ expected[directory.id] = [
+ {
+ "sha1_git": directory.id,
+ "type": "directory",
+ }
+ ]
swh_storage.revision_add([revision])
sha1_gits.append(revision.id)
- expected[revision.id] = [{"sha1_git": revision.id, "type": "revision",}]
+ expected[revision.id] = [
+ {
+ "sha1_git": revision.id,
+ "type": "revision",
+ }
+ ]
swh_storage.release_add([release])
sha1_gits.append(release.id)
- expected[release.id] = [{"sha1_git": release.id, "type": "release",}]
+ expected[release.id] = [
+ {
+ "sha1_git": release.id,
+ "type": "release",
+ }
+ ]
ret = swh_storage.object_find_by_sha1_git(sha1_gits)
assert expected == ret
def test_metadata_fetcher_add_get(self, swh_storage, sample_data):
fetcher = sample_data.metadata_fetcher
actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version)
assert actual_fetcher is None # does not exist
swh_storage.metadata_fetcher_add([fetcher])
res = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version)
assert res == fetcher
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_objects = [
("metadata_fetcher", fetcher),
]
for obj in expected_objects:
assert obj in actual_objects
def test_metadata_fetcher_add_zero(self, swh_storage, sample_data):
fetcher = sample_data.metadata_fetcher
actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version)
assert actual_fetcher is None # does not exist
swh_storage.metadata_fetcher_add([])
def test_metadata_authority_add_get(self, swh_storage, sample_data):
authority = sample_data.metadata_authority
actual_authority = swh_storage.metadata_authority_get(
authority.type, authority.url
)
assert actual_authority is None # does not exist
swh_storage.metadata_authority_add([authority])
res = swh_storage.metadata_authority_get(authority.type, authority.url)
assert res == authority
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_objects = [
("metadata_authority", authority),
]
for obj in expected_objects:
assert obj in actual_objects
def test_metadata_authority_add_zero(self, swh_storage, sample_data):
authority = sample_data.metadata_authority
actual_authority = swh_storage.metadata_authority_get(
authority.type, authority.url
)
assert actual_authority is None # does not exist
swh_storage.metadata_authority_add([])
def test_content_metadata_add(self, swh_storage, sample_data):
content = sample_data.content
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
content_metadata = sample_data.content_metadata[:2]
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add(content_metadata)
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(), authority
)
assert result.next_page_token is None
- assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == list(
- content_metadata
- )
+ assert list(
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
+ ) == list(content_metadata)
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_objects = [
("metadata_authority", authority),
("metadata_fetcher", fetcher),
] + [("raw_extrinsic_metadata", item) for item in content_metadata]
for obj in expected_objects:
assert obj in actual_objects
def test_content_metadata_add_duplicate(self, swh_storage, sample_data):
"""Duplicates should be silently ignored."""
content = sample_data.content
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
content_metadata, content_metadata2 = sample_data.content_metadata[:2]
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2])
swh_storage.raw_extrinsic_metadata_add([content_metadata2, content_metadata])
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(), authority
)
assert result.next_page_token is None
expected_results = (content_metadata, content_metadata2)
assert (
- tuple(sorted(result.results, key=lambda x: x.discovery_date,))
+ tuple(
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
+ )
== expected_results
)
def test_content_metadata_get(self, swh_storage, sample_data):
content, content2 = sample_data.contents[:2]
fetcher, fetcher2 = sample_data.fetchers[:2]
authority, authority2 = sample_data.authorities[:2]
(
content1_metadata1,
content1_metadata2,
content1_metadata3,
) = sample_data.content_metadata[:3]
content2_metadata = RawExtrinsicMetadata.from_dict(
{
**remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id
"target": str(content2.swhid()),
}
)
swh_storage.metadata_authority_add([authority, authority2])
swh_storage.metadata_fetcher_add([fetcher, fetcher2])
swh_storage.raw_extrinsic_metadata_add(
[
content1_metadata1,
content1_metadata2,
content1_metadata3,
content2_metadata,
]
)
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(), authority
)
assert result.next_page_token is None
assert [content1_metadata1, content1_metadata2] == list(
- sorted(result.results, key=lambda x: x.discovery_date,)
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
)
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(), authority2
)
assert result.next_page_token is None
assert [content1_metadata3] == list(
- sorted(result.results, key=lambda x: x.discovery_date,)
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
)
result = swh_storage.raw_extrinsic_metadata_get(
content2.swhid().to_extended(), authority
)
assert result.next_page_token is None
- assert [content2_metadata] == list(result.results,)
+ assert [content2_metadata] == list(
+ result.results,
+ )
def test_content_metadata_get_after(self, swh_storage, sample_data):
content = sample_data.content
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
content_metadata, content_metadata2 = sample_data.content_metadata[:2]
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2])
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(),
authority,
after=content_metadata.discovery_date - timedelta(seconds=1),
)
assert result.next_page_token is None
assert [content_metadata, content_metadata2] == list(
- sorted(result.results, key=lambda x: x.discovery_date,)
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
)
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(),
authority,
after=content_metadata.discovery_date,
)
assert result.next_page_token is None
assert result.results == [content_metadata2]
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(),
authority,
after=content_metadata2.discovery_date,
)
assert result.next_page_token is None
assert result.results == []
def test_content_metadata_get_paginate(self, swh_storage, sample_data):
content = sample_data.content
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
content_metadata, content_metadata2 = sample_data.content_metadata[:2]
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2])
swh_storage.raw_extrinsic_metadata_get(content.swhid().to_extended(), authority)
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(), authority, limit=1
)
assert result.next_page_token is not None
assert result.results == [content_metadata]
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(),
authority,
limit=1,
page_token=result.next_page_token,
)
assert result.next_page_token is None
assert result.results == [content_metadata2]
def test_content_metadata_get_paginate_same_date(self, swh_storage, sample_data):
content = sample_data.content
fetcher1, fetcher2 = sample_data.fetchers[:2]
authority = sample_data.metadata_authority
content_metadata, content_metadata2 = sample_data.content_metadata[:2]
swh_storage.metadata_fetcher_add([fetcher1, fetcher2])
swh_storage.metadata_authority_add([authority])
new_content_metadata2 = RawExtrinsicMetadata.from_dict(
{
**remove_keys(content_metadata2.to_dict(), ("id",)), # recompute id
"discovery_date": content_metadata2.discovery_date,
"fetcher": attr.evolve(fetcher2, metadata=None).to_dict(),
}
)
swh_storage.raw_extrinsic_metadata_add(
[content_metadata, new_content_metadata2]
)
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(), authority, limit=1
)
assert result.next_page_token is not None
assert result.results == [content_metadata]
result = swh_storage.raw_extrinsic_metadata_get(
content.swhid().to_extended(),
authority,
limit=1,
page_token=result.next_page_token,
)
assert result.next_page_token is None
assert result.results[0].to_dict() == new_content_metadata2.to_dict()
assert result.results == [new_content_metadata2]
def test_content_metadata_get_by_ids(self, swh_storage, sample_data):
content, content2 = sample_data.contents[:2]
fetcher, fetcher2 = sample_data.fetchers[:2]
authority, authority2 = sample_data.authorities[:2]
(
content1_metadata1,
content1_metadata2,
content1_metadata3,
) = sample_data.content_metadata[:3]
content2_metadata = RawExtrinsicMetadata.from_dict(
{
**remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id
"target": str(content2.swhid()),
}
)
swh_storage.metadata_authority_add([authority, authority2])
swh_storage.metadata_fetcher_add([fetcher, fetcher2])
swh_storage.raw_extrinsic_metadata_add(
[
content1_metadata1,
content1_metadata2,
content1_metadata3,
content2_metadata,
]
)
assert set(
swh_storage.raw_extrinsic_metadata_get_by_ids(
[content1_metadata1.id, b"\x00" * 20, content2_metadata.id]
)
) == {content1_metadata1, content2_metadata}
def test_content_metadata_get_authorities(self, swh_storage, sample_data):
content1, content2, content3 = sample_data.contents[:3]
fetcher, fetcher2 = sample_data.fetchers[:2]
authority, authority2 = sample_data.authorities[:2]
(
content1_metadata1,
content1_metadata2,
content1_metadata3,
) = sample_data.content_metadata[:3]
content2_metadata = RawExtrinsicMetadata.from_dict(
{
**remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id
"target": str(content2.swhid()),
}
)
content1_metadata2 = RawExtrinsicMetadata.from_dict(
{
**remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id
"authority": authority2.to_dict(),
}
)
swh_storage.metadata_authority_add([authority, authority2])
swh_storage.metadata_fetcher_add([fetcher, fetcher2])
swh_storage.raw_extrinsic_metadata_add(
[
content1_metadata1,
content1_metadata2,
content1_metadata3,
content2_metadata,
]
)
assert swh_storage.raw_extrinsic_metadata_get_authorities(content1.swhid()) in (
[authority, authority2],
[authority2, authority],
)
assert swh_storage.raw_extrinsic_metadata_get_authorities(content2.swhid()) == [
authority
]
assert (
swh_storage.raw_extrinsic_metadata_get_authorities(content3.swhid()) == []
)
def test_origin_metadata_add(self, swh_storage, sample_data):
origin = sample_data.origin
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2]
assert swh_storage.origin_add([origin]) == {"origin:add": 1}
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2])
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(), authority
)
assert result.next_page_token is None
assert list(sorted(result.results, key=lambda x: x.discovery_date)) == [
origin_metadata,
origin_metadata2,
]
actual_objects = list(swh_storage.journal_writer.journal.objects)
expected_objects = [
("metadata_authority", authority),
("metadata_fetcher", fetcher),
("raw_extrinsic_metadata", origin_metadata),
("raw_extrinsic_metadata", origin_metadata2),
]
for obj in expected_objects:
assert obj in actual_objects
def test_origin_metadata_add_duplicate(self, swh_storage, sample_data):
"""Duplicates should be silently updated."""
origin = sample_data.origin
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2]
assert swh_storage.origin_add([origin]) == {"origin:add": 1}
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2])
swh_storage.raw_extrinsic_metadata_add([origin_metadata2, origin_metadata])
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(), authority
)
assert result.next_page_token is None
# which of the two behavior happens is backend-specific.
expected_results = (origin_metadata, origin_metadata2)
assert (
- tuple(sorted(result.results, key=lambda x: x.discovery_date,))
+ tuple(
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
+ )
== expected_results
)
def test_origin_metadata_get(self, swh_storage, sample_data):
origin, origin2 = sample_data.origins[:2]
fetcher, fetcher2 = sample_data.fetchers[:2]
authority, authority2 = sample_data.authorities[:2]
(
origin1_metadata1,
origin1_metadata2,
origin1_metadata3,
) = sample_data.origin_metadata[:3]
assert swh_storage.origin_add([origin, origin2]) == {"origin:add": 2}
origin2_metadata = RawExtrinsicMetadata.from_dict(
{
**remove_keys(origin1_metadata2.to_dict(), ("id",)), # recompute id
"target": str(Origin(origin2.url).swhid()),
}
)
swh_storage.metadata_authority_add([authority, authority2])
swh_storage.metadata_fetcher_add([fetcher, fetcher2])
swh_storage.raw_extrinsic_metadata_add(
[origin1_metadata1, origin1_metadata2, origin1_metadata3, origin2_metadata]
)
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(), authority
)
assert result.next_page_token is None
assert [origin1_metadata1, origin1_metadata2] == list(
- sorted(result.results, key=lambda x: x.discovery_date,)
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
)
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(), authority2
)
assert result.next_page_token is None
assert [origin1_metadata3] == list(
- sorted(result.results, key=lambda x: x.discovery_date,)
+ sorted(
+ result.results,
+ key=lambda x: x.discovery_date,
+ )
)
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin2.url).swhid(), authority
)
assert result.next_page_token is None
- assert [origin2_metadata] == list(result.results,)
+ assert [origin2_metadata] == list(
+ result.results,
+ )
def test_origin_metadata_get_after(self, swh_storage, sample_data):
origin = sample_data.origin
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2]
assert swh_storage.origin_add([origin]) == {"origin:add": 1}
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2])
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(),
authority,
after=origin_metadata.discovery_date - timedelta(seconds=1),
)
assert result.next_page_token is None
assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == [
origin_metadata,
origin_metadata2,
]
result = swh_storage.raw_extrinsic_metadata_get(
- Origin(origin.url).swhid(), authority, after=origin_metadata.discovery_date,
+ Origin(origin.url).swhid(),
+ authority,
+ after=origin_metadata.discovery_date,
)
assert result.next_page_token is None
assert result.results == [origin_metadata2]
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(),
authority,
after=origin_metadata2.discovery_date,
)
assert result.next_page_token is None
assert result.results == []
def test_origin_metadata_get_paginate(self, swh_storage, sample_data):
origin = sample_data.origin
fetcher = sample_data.metadata_fetcher
authority = sample_data.metadata_authority
origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2]
assert swh_storage.origin_add([origin]) == {"origin:add": 1}
swh_storage.metadata_fetcher_add([fetcher])
swh_storage.metadata_authority_add([authority])
swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2])
swh_storage.raw_extrinsic_metadata_get(Origin(origin.url).swhid(), authority)
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(), authority, limit=1
)
assert result.next_page_token is not None
assert result.results == [origin_metadata]
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(),
authority,
limit=1,
page_token=result.next_page_token,
)
assert result.next_page_token is None
assert result.results == [origin_metadata2]
def test_origin_metadata_get_paginate_same_date(self, swh_storage, sample_data):
origin = sample_data.origin
fetcher1, fetcher2 = sample_data.fetchers[:2]
authority = sample_data.metadata_authority
origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2]
assert swh_storage.origin_add([origin]) == {"origin:add": 1}
swh_storage.metadata_fetcher_add([fetcher1, fetcher2])
swh_storage.metadata_authority_add([authority])
new_origin_metadata2 = RawExtrinsicMetadata.from_dict(
{
**remove_keys(origin_metadata2.to_dict(), ("id",)), # recompute id
"discovery_date": origin_metadata2.discovery_date,
"fetcher": attr.evolve(fetcher2, metadata=None).to_dict(),
}
)
swh_storage.raw_extrinsic_metadata_add([origin_metadata, new_origin_metadata2])
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(), authority, limit=1
)
assert result.next_page_token is not None
assert result.results == [origin_metadata]
result = swh_storage.raw_extrinsic_metadata_get(
Origin(origin.url).swhid(),
authority,
limit=1,
page_token=result.next_page_token,
)
assert result.next_page_token is None
assert result.results == [new_origin_metadata2]
def test_origin_metadata_add_missing_authority(self, swh_storage, sample_data):
origin = sample_data.origin
fetcher = sample_data.metadata_fetcher
origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2]
assert swh_storage.origin_add([origin]) == {"origin:add": 1}
swh_storage.metadata_fetcher_add([fetcher])
with pytest.raises(StorageArgumentException, match="authority"):
swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2])
def test_origin_metadata_add_missing_fetcher(self, swh_storage, sample_data):
origin = sample_data.origin
authority = sample_data.metadata_authority
origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2]
assert swh_storage.origin_add([origin]) == {"origin:add": 1}
swh_storage.metadata_authority_add([authority])
with pytest.raises(StorageArgumentException, match="fetcher"):
swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2])
class TestStorageGeneratedData:
def test_generate_content_get_data(self, swh_storage, swh_contents):
contents_with_data = [c for c in swh_contents if c.status != "absent"]
# retrieve contents
for content in contents_with_data:
actual_content_data = swh_storage.content_get_data(content.sha1)
assert actual_content_data is not None
assert actual_content_data == content.data
def test_generate_content_get(self, swh_storage, swh_contents):
expected_contents = [
attr.evolve(c, data=None) for c in swh_contents if c.status != "absent"
]
actual_contents = swh_storage.content_get([c.sha1 for c in expected_contents])
assert len(actual_contents) == len(expected_contents)
assert actual_contents == expected_contents
@pytest.mark.parametrize("limit", [1, 7, 10, 100, 1000])
def test_origin_list(self, swh_storage, swh_origins, limit):
returned_origins = []
page_token = None
i = 0
while True:
actual_page = swh_storage.origin_list(page_token=page_token, limit=limit)
assert len(actual_page.results) <= limit
returned_origins.extend(actual_page.results)
i += 1
page_token = actual_page.next_page_token
if page_token is None:
assert i * limit >= len(swh_origins)
break
else:
assert len(actual_page.results) == limit
assert sorted(returned_origins) == sorted(swh_origins)
def test_origin_count(self, swh_storage, sample_data):
swh_storage.origin_add(sample_data.origins)
assert swh_storage.origin_count("github") == 3
assert swh_storage.origin_count("gitlab") == 2
assert swh_storage.origin_count(".*user.*", regexp=True) == 5
assert swh_storage.origin_count(".*user.*", regexp=False) == 0
assert swh_storage.origin_count(".*user1.*", regexp=True) == 2
assert swh_storage.origin_count(".*user1.*", regexp=False) == 0
def test_origin_count_with_visit_no_visits(self, swh_storage, sample_data):
swh_storage.origin_add(sample_data.origins)
# none of them have visits, so with_visit=True => 0
assert swh_storage.origin_count("github", with_visit=True) == 0
assert swh_storage.origin_count("gitlab", with_visit=True) == 0
assert swh_storage.origin_count(".*user.*", regexp=True, with_visit=True) == 0
assert swh_storage.origin_count(".*user.*", regexp=False, with_visit=True) == 0
assert swh_storage.origin_count(".*user1.*", regexp=True, with_visit=True) == 0
assert swh_storage.origin_count(".*user1.*", regexp=False, with_visit=True) == 0
def test_origin_count_with_visit_with_visits_no_snapshot(
self, swh_storage, sample_data
):
swh_storage.origin_add(sample_data.origins)
origin_url = "https://github.com/user1/repo1"
- visit = OriginVisit(origin=origin_url, date=now(), type="git",)
+ visit = OriginVisit(
+ origin=origin_url,
+ date=now(),
+ type="git",
+ )
swh_storage.origin_visit_add([visit])
assert swh_storage.origin_count("github", with_visit=False) == 3
# it has a visit, but no snapshot, so with_visit=True => 0
assert swh_storage.origin_count("github", with_visit=True) == 0
assert swh_storage.origin_count("gitlab", with_visit=False) == 2
# these gitlab origins have no visit
assert swh_storage.origin_count("gitlab", with_visit=True) == 0
assert (
swh_storage.origin_count("github.*user1", regexp=True, with_visit=False)
== 1
)
assert (
swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 0
)
assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 0
def test_origin_count_with_visit_with_visits_and_snapshot(
self, swh_storage, sample_data
):
snapshot = sample_data.snapshot
swh_storage.origin_add(sample_data.origins)
swh_storage.snapshot_add([snapshot])
origin_url = "https://github.com/user1/repo1"
- visit = OriginVisit(origin=origin_url, date=now(), type="git",)
+ visit = OriginVisit(
+ origin=origin_url,
+ date=now(),
+ type="git",
+ )
visit = swh_storage.origin_visit_add([visit])[0]
swh_storage.origin_visit_status_add(
[
OriginVisitStatus(
origin=origin_url,
visit=visit.visit,
date=now(),
status="ongoing",
snapshot=snapshot.id,
)
]
)
assert swh_storage.origin_count("github", with_visit=False) == 3
# github/user1 has a visit and a snapshot, so with_visit=True => 1
assert swh_storage.origin_count("github", with_visit=True) == 1
assert (
swh_storage.origin_count("github.*user1", regexp=True, with_visit=False)
== 1
)
assert (
swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 1
)
assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 1
@settings(
suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large]
+ function_scoped_fixture_check,
)
@given(
strategies.lists(hypothesis_strategies.objects(split_content=True), max_size=2)
)
def test_add_arbitrary(self, swh_storage, objects):
for (obj_type, obj) in objects:
if obj.object_type == "origin_visit":
swh_storage.origin_add([Origin(url=obj.origin)])
- visit = OriginVisit(origin=obj.origin, date=obj.date, type=obj.type,)
+ visit = OriginVisit(
+ origin=obj.origin,
+ date=obj.date,
+ type=obj.type,
+ )
swh_storage.origin_visit_add([visit])
elif obj.object_type == "raw_extrinsic_metadata":
swh_storage.metadata_authority_add([obj.authority])
swh_storage.metadata_fetcher_add([obj.fetcher])
swh_storage.raw_extrinsic_metadata_add([obj])
else:
method = getattr(swh_storage, obj_type + "_add")
try:
method([obj])
except HashCollision:
pass
diff --git a/swh/storage/tests/test_backfill.py b/swh/storage/tests/test_backfill.py
index fc0c0f51..f1eaf178 100644
--- a/swh/storage/tests/test_backfill.py
+++ b/swh/storage/tests/test_backfill.py
@@ -1,301 +1,297 @@
# Copyright (C) 2019-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import functools
import logging
from unittest.mock import patch
import pytest
from swh.journal.client import JournalClient
from swh.model.tests.swh_model_data import TEST_OBJECTS
from swh.storage import get_storage
from swh.storage.backfill import (
PARTITION_KEY,
JournalBackfiller,
byte_ranges,
compute_query,
raw_extrinsic_metadata_target_ranges,
)
from swh.storage.in_memory import InMemoryStorage
from swh.storage.replay import ModelObjectDeserializer, process_replay_objects
from swh.storage.tests.test_replay import check_replayed
TEST_CONFIG = {
"journal_writer": {
"brokers": ["localhost"],
"prefix": "swh.tmp_journal.new",
"client_id": "swh.journal.client.test",
},
"storage": {"cls": "postgresql", "db": "service=swh-dev"},
}
def test_config_ko_missing_mandatory_key():
- """Missing configuration key will make the initialization fail
-
- """
+ """Missing configuration key will make the initialization fail"""
for key in TEST_CONFIG.keys():
config = TEST_CONFIG.copy()
config.pop(key)
with pytest.raises(ValueError) as e:
JournalBackfiller(config)
error = "Configuration error: The following keys must be provided: %s" % (
",".join([key]),
)
assert e.value.args[0] == error
def test_config_ko_unknown_object_type():
- """Parse arguments will fail if the object type is unknown
-
- """
+ """Parse arguments will fail if the object type is unknown"""
backfiller = JournalBackfiller(TEST_CONFIG)
with pytest.raises(ValueError) as e:
backfiller.parse_arguments("unknown-object-type", 1, 2)
error = (
"Object type unknown-object-type is not supported. "
"The only possible values are %s" % (", ".join(sorted(PARTITION_KEY)))
)
assert e.value.args[0] == error
def test_compute_query_content():
query, where_args, column_aliases = compute_query("content", "\x000000", "\x000001")
assert where_args == ["\x000000", "\x000001"]
assert column_aliases == [
"sha1",
"sha1_git",
"sha256",
"blake2s256",
"length",
"status",
"ctime",
]
assert (
query
== """
select sha1,sha1_git,sha256,blake2s256,length,status,ctime
from content
where (sha1) >= %s and (sha1) < %s
"""
)
def test_compute_query_skipped_content():
query, where_args, column_aliases = compute_query("skipped_content", None, None)
assert where_args == []
assert column_aliases == [
"sha1",
"sha1_git",
"sha256",
"blake2s256",
"length",
"ctime",
"status",
"reason",
]
assert (
query
== """
select sha1,sha1_git,sha256,blake2s256,length,ctime,status,reason
from skipped_content
"""
)
def test_compute_query_origin_visit():
query, where_args, column_aliases = compute_query("origin_visit", 1, 10)
assert where_args == [1, 10]
assert column_aliases == [
"visit",
"type",
"origin",
"date",
]
assert (
query
== """
select visit,type,origin.url as origin,date
from origin_visit
left join origin on origin_visit.origin=origin.id
where (origin_visit.origin) >= %s and (origin_visit.origin) < %s
"""
)
def test_compute_query_release():
query, where_args, column_aliases = compute_query("release", "\x000002", "\x000003")
assert where_args == ["\x000002", "\x000003"]
assert column_aliases == [
"id",
"date",
"date_offset_bytes",
"comment",
"name",
"synthetic",
"target",
"target_type",
"author_id",
"author_name",
"author_email",
"author_fullname",
"raw_manifest",
]
assert (
query
== """
select release.id as id,date,date_offset_bytes,comment,release.name as name,synthetic,target,target_type,a.id as author_id,a.name as author_name,a.email as author_email,a.fullname as author_fullname,raw_manifest
from release
left join person a on release.author=a.id
where (release.id) >= %s and (release.id) < %s
""" # noqa
)
@pytest.mark.parametrize("numbits", [2, 3, 8, 16])
def test_byte_ranges(numbits):
ranges = list(byte_ranges(numbits))
- assert len(ranges) == 2 ** numbits
+ assert len(ranges) == 2**numbits
assert ranges[0][0] is None
assert ranges[-1][1] is None
bounds = []
for i, (left, right) in enumerate(zip(ranges[:-1], ranges[1:])):
assert left[1] == right[0], f"Mismatched bounds in {i}th range"
bounds.append(left[1])
assert bounds == sorted(bounds)
def test_raw_extrinsic_metadata_target_ranges():
ranges = list(raw_extrinsic_metadata_target_ranges())
assert ranges[0][0] == ""
assert ranges[-1][1] is None
bounds = []
for i, (left, right) in enumerate(zip(ranges[:-1], ranges[1:])):
assert left[1] == right[0], f"Mismatched bounds in {i}th range"
bounds.append(left[1])
assert bounds == sorted(bounds)
RANGE_GENERATORS = {
"content": lambda start, end: [(None, None)],
"skipped_content": lambda start, end: [(None, None)],
"directory": lambda start, end: [(None, None)],
"extid": lambda start, end: [(None, None)],
"metadata_authority": lambda start, end: [(None, None)],
"metadata_fetcher": lambda start, end: [(None, None)],
"revision": lambda start, end: [(None, None)],
"release": lambda start, end: [(None, None)],
"snapshot": lambda start, end: [(None, None)],
"origin": lambda start, end: [(None, 10000)],
"origin_visit": lambda start, end: [(None, 10000)],
"origin_visit_status": lambda start, end: [(None, 10000)],
"raw_extrinsic_metadata": lambda start, end: [(None, None)],
}
@patch("swh.storage.backfill.RANGE_GENERATORS", RANGE_GENERATORS)
def test_backfiller(
swh_storage_backend_config,
kafka_prefix: str,
kafka_consumer_group: str,
kafka_server: str,
caplog,
):
prefix1 = f"{kafka_prefix}-1"
prefix2 = f"{kafka_prefix}-2"
journal1 = {
"cls": "kafka",
"brokers": [kafka_server],
"client_id": "kafka_writer-1",
"prefix": prefix1,
}
swh_storage_backend_config["journal_writer"] = journal1
storage = get_storage(**swh_storage_backend_config)
# fill the storage and the journal (under prefix1)
for object_type, objects in TEST_OBJECTS.items():
method = getattr(storage, object_type + "_add")
method(objects)
# now apply the backfiller on the storage to fill the journal under prefix2
backfiller_config = {
"journal_writer": {
"brokers": [kafka_server],
"client_id": "kafka_writer-2",
"prefix": prefix2,
},
"storage": swh_storage_backend_config,
}
# Backfilling
backfiller = JournalBackfiller(backfiller_config)
for object_type in TEST_OBJECTS:
backfiller.run(object_type, None, None)
# Trace log messages for unhandled object types in the replayer
caplog.set_level(logging.DEBUG, "swh.storage.replay")
# now check journal content are the same under both topics
# use the replayer scaffolding to fill storages to make is a bit easier
# Replaying #1
deserializer = ModelObjectDeserializer()
sto1 = get_storage(cls="memory")
replayer1 = JournalClient(
brokers=kafka_server,
group_id=f"{kafka_consumer_group}-1",
prefix=prefix1,
stop_on_eof=True,
value_deserializer=deserializer.convert,
)
worker_fn1 = functools.partial(process_replay_objects, storage=sto1)
replayer1.process(worker_fn1)
# Replaying #2
sto2 = get_storage(cls="memory")
replayer2 = JournalClient(
brokers=kafka_server,
group_id=f"{kafka_consumer_group}-2",
prefix=prefix2,
stop_on_eof=True,
value_deserializer=deserializer.convert,
)
worker_fn2 = functools.partial(process_replay_objects, storage=sto2)
replayer2.process(worker_fn2)
# Compare storages
assert isinstance(sto1, InMemoryStorage) # needed to help mypy
assert isinstance(sto2, InMemoryStorage)
check_replayed(sto1, sto2)
for record in caplog.records:
assert (
"this should not happen" not in record.message
), "Replayer ignored some message types, see captured logging"
diff --git a/swh/storage/tests/test_buffer.py b/swh/storage/tests/test_buffer.py
index 8f0f30ef..0cf3b3a1 100644
--- a/swh/storage/tests/test_buffer.py
+++ b/swh/storage/tests/test_buffer.py
@@ -1,729 +1,806 @@
# Copyright (C) 2019-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from collections import Counter
from typing import Optional
from unittest.mock import Mock
from swh.storage import get_storage
from swh.storage.proxies.buffer import (
BufferingProxyStorage,
estimate_release_size,
estimate_revision_size,
)
def get_storage_with_buffer_config(**buffer_config) -> BufferingProxyStorage:
steps = [
{"cls": "buffer", **buffer_config},
{"cls": "memory"},
]
ret = get_storage("pipeline", steps=steps)
assert isinstance(ret, BufferingProxyStorage)
return ret
def test_buffering_proxy_storage_content_threshold_not_hit(sample_data) -> None:
contents = sample_data.contents[:2]
contents_dict = [c.to_dict() for c in contents]
- storage = get_storage_with_buffer_config(min_batch_size={"content": 10,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "content": 10,
+ }
+ )
s = storage.content_add(contents)
assert s == {}
# contents have not been written to storage
missing_contents = storage.content_missing(contents_dict)
assert set(missing_contents) == set([contents[0].sha1, contents[1].sha1])
s = storage.flush()
assert s == {
"content:add": 1 + 1,
"content:add:bytes": contents[0].length + contents[1].length,
}
missing_contents = storage.content_missing(contents_dict)
assert list(missing_contents) == []
def test_buffering_proxy_storage_content_threshold_nb_hit(sample_data) -> None:
content = sample_data.content
content_dict = content.to_dict()
- storage = get_storage_with_buffer_config(min_batch_size={"content": 1,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "content": 1,
+ }
+ )
s = storage.content_add([content])
assert s == {
"content:add": 1,
"content:add:bytes": content.length,
}
missing_contents = storage.content_missing([content_dict])
assert list(missing_contents) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_content_deduplicate(sample_data) -> None:
contents = sample_data.contents[:2]
- storage = get_storage_with_buffer_config(min_batch_size={"content": 2,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "content": 2,
+ }
+ )
s = storage.content_add([contents[0], contents[0]])
assert s == {}
s = storage.content_add([contents[0]])
assert s == {}
s = storage.content_add([contents[1]])
assert s == {
"content:add": 1 + 1,
"content:add:bytes": contents[0].length + contents[1].length,
}
missing_contents = storage.content_missing([c.to_dict() for c in contents])
assert list(missing_contents) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_content_threshold_bytes_hit(sample_data) -> None:
contents = sample_data.contents[:2]
content_bytes_min_batch_size = 2
storage = get_storage_with_buffer_config(
- min_batch_size={"content": 10, "content_bytes": content_bytes_min_batch_size,}
+ min_batch_size={
+ "content": 10,
+ "content_bytes": content_bytes_min_batch_size,
+ }
)
assert contents[0].length > content_bytes_min_batch_size
s = storage.content_add([contents[0]])
assert s == {
"content:add": 1,
"content:add:bytes": contents[0].length,
}
missing_contents = storage.content_missing([contents[0].to_dict()])
assert list(missing_contents) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_skipped_content_threshold_not_hit(sample_data) -> None:
contents = sample_data.skipped_contents
contents_dict = [c.to_dict() for c in contents]
- storage = get_storage_with_buffer_config(min_batch_size={"skipped_content": 10,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "skipped_content": 10,
+ }
+ )
s = storage.skipped_content_add([contents[0], contents[1]])
assert s == {}
# contents have not been written to storage
missing_contents = storage.skipped_content_missing(contents_dict)
assert {c["sha1"] for c in missing_contents} == {c.sha1 for c in contents}
s = storage.flush()
assert s == {"skipped_content:add": 1 + 1}
missing_contents = storage.skipped_content_missing(contents_dict)
assert list(missing_contents) == []
def test_buffering_proxy_storage_skipped_content_threshold_nb_hit(sample_data) -> None:
contents = sample_data.skipped_contents
- storage = get_storage_with_buffer_config(min_batch_size={"skipped_content": 1,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "skipped_content": 1,
+ }
+ )
s = storage.skipped_content_add([contents[0]])
assert s == {"skipped_content:add": 1}
missing_contents = storage.skipped_content_missing([contents[0].to_dict()])
assert list(missing_contents) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_skipped_content_deduplicate(sample_data):
contents = sample_data.skipped_contents[:2]
- storage = get_storage_with_buffer_config(min_batch_size={"skipped_content": 2,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "skipped_content": 2,
+ }
+ )
s = storage.skipped_content_add([contents[0], contents[0]])
assert s == {}
s = storage.skipped_content_add([contents[0]])
assert s == {}
s = storage.skipped_content_add([contents[1]])
assert s == {
"skipped_content:add": 1 + 1,
}
missing_contents = storage.skipped_content_missing([c.to_dict() for c in contents])
assert list(missing_contents) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_extid_threshold_not_hit(sample_data) -> None:
extid = sample_data.extid1
- storage = get_storage_with_buffer_config(min_batch_size={"extid": 10,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "extid": 10,
+ }
+ )
s = storage.extid_add([extid])
assert s == {}
present_extids = storage.extid_get_from_target(
extid.target.object_type, [extid.target.object_id]
)
assert list(present_extids) == []
s = storage.flush()
assert s == {
"extid:add": 1,
}
present_extids = storage.extid_get_from_target(
extid.target.object_type, [extid.target.object_id]
)
assert list(present_extids) == [extid]
def test_buffering_proxy_storage_extid_threshold_hit(sample_data) -> None:
extid = sample_data.extid1
- storage = get_storage_with_buffer_config(min_batch_size={"extid": 1,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "extid": 1,
+ }
+ )
s = storage.extid_add([extid])
assert s == {
"extid:add": 1,
}
present_extids = storage.extid_get_from_target(
extid.target.object_type, [extid.target.object_id]
)
assert list(present_extids) == [extid]
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_extid_deduplicate(sample_data) -> None:
extids = sample_data.extids[:2]
- storage = get_storage_with_buffer_config(min_batch_size={"extid": 2,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "extid": 2,
+ }
+ )
s = storage.extid_add([extids[0], extids[0]])
assert s == {}
s = storage.extid_add([extids[0]])
assert s == {}
s = storage.extid_add([extids[1]])
assert s == {
"extid:add": 1 + 1,
}
for extid in extids:
present_extids = storage.extid_get_from_target(
extid.target.object_type, [extid.target.object_id]
)
assert list(present_extids) == [extid]
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_directory_threshold_not_hit(sample_data) -> None:
directory = sample_data.directory
- storage = get_storage_with_buffer_config(min_batch_size={"directory": 10,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "directory": 10,
+ }
+ )
s = storage.directory_add([directory])
assert s == {}
missing_directories = storage.directory_missing([directory.id])
assert list(missing_directories) == [directory.id]
s = storage.flush()
assert s == {
"directory:add": 1,
}
missing_directories = storage.directory_missing([directory.id])
assert list(missing_directories) == []
def test_buffering_proxy_storage_directory_threshold_hit(sample_data) -> None:
directory = sample_data.directory
- storage = get_storage_with_buffer_config(min_batch_size={"directory": 1,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "directory": 1,
+ }
+ )
s = storage.directory_add([directory])
assert s == {
"directory:add": 1,
}
missing_directories = storage.directory_missing([directory.id])
assert list(missing_directories) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_directory_deduplicate(sample_data) -> None:
directories = sample_data.directories[:2]
- storage = get_storage_with_buffer_config(min_batch_size={"directory": 2,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "directory": 2,
+ }
+ )
s = storage.directory_add([directories[0], directories[0]])
assert s == {}
s = storage.directory_add([directories[0]])
assert s == {}
s = storage.directory_add([directories[1]])
assert s == {
"directory:add": 1 + 1,
}
missing_directories = storage.directory_missing([d.id for d in directories])
assert list(missing_directories) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_directory_entries_threshold(sample_data) -> None:
directories = sample_data.directories
n_entries = sum(len(d.entries) for d in directories)
threshold = sum(len(d.entries) for d in directories[:-2])
# ensure the threshold is in the middle
assert 0 < threshold < n_entries
storage = get_storage_with_buffer_config(
min_batch_size={"directory_entries": threshold}
)
storage.storage = Mock(wraps=storage.storage)
for directory in directories:
storage.directory_add([directory])
storage.flush()
# We should have called the underlying directory_add at least twice, as
# we have hit the threshold for number of entries on directory n-2
method_calls = Counter(c[0] for c in storage.storage.method_calls)
assert method_calls["directory_add"] >= 2
def test_buffering_proxy_storage_revision_threshold_not_hit(sample_data) -> None:
revision = sample_data.revision
- storage = get_storage_with_buffer_config(min_batch_size={"revision": 10,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "revision": 10,
+ }
+ )
s = storage.revision_add([revision])
assert s == {}
missing_revisions = storage.revision_missing([revision.id])
assert list(missing_revisions) == [revision.id]
s = storage.flush()
assert s == {
"revision:add": 1,
}
missing_revisions = storage.revision_missing([revision.id])
assert list(missing_revisions) == []
def test_buffering_proxy_storage_revision_threshold_hit(sample_data) -> None:
revision = sample_data.revision
- storage = get_storage_with_buffer_config(min_batch_size={"revision": 1,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "revision": 1,
+ }
+ )
s = storage.revision_add([revision])
assert s == {
"revision:add": 1,
}
missing_revisions = storage.revision_missing([revision.id])
assert list(missing_revisions) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_revision_deduplicate(sample_data) -> None:
revisions = sample_data.revisions[:2]
- storage = get_storage_with_buffer_config(min_batch_size={"revision": 2,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "revision": 2,
+ }
+ )
s = storage.revision_add([revisions[0], revisions[0]])
assert s == {}
s = storage.revision_add([revisions[0]])
assert s == {}
s = storage.revision_add([revisions[1]])
assert s == {
"revision:add": 1 + 1,
}
missing_revisions = storage.revision_missing([r.id for r in revisions])
assert list(missing_revisions) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_revision_parents_threshold(sample_data) -> None:
revisions = sample_data.revisions
n_parents = sum(len(r.parents) for r in revisions)
threshold = sum(len(r.parents) for r in revisions[:-2])
# ensure the threshold is in the middle
assert 0 < threshold < n_parents
storage = get_storage_with_buffer_config(
min_batch_size={"revision_parents": threshold}
)
storage.storage = Mock(wraps=storage.storage)
for revision in revisions:
storage.revision_add([revision])
storage.flush()
# We should have called the underlying revision_add at least twice, as
# we have hit the threshold for number of parents on revision n-2
method_calls = Counter(c[0] for c in storage.storage.method_calls)
assert method_calls["revision_add"] >= 2
def test_buffering_proxy_storage_revision_size_threshold(sample_data) -> None:
revisions = sample_data.revisions
total_size = sum(estimate_revision_size(r) for r in revisions)
threshold = sum(estimate_revision_size(r) for r in revisions[:-2])
# ensure the threshold is in the middle
assert 0 < threshold < total_size
storage = get_storage_with_buffer_config(
min_batch_size={"revision_bytes": threshold}
)
storage.storage = Mock(wraps=storage.storage)
for revision in revisions:
storage.revision_add([revision])
storage.flush()
# We should have called the underlying revision_add at least twice, as
# we have hit the threshold for number of parents on revision n-2
method_calls = Counter(c[0] for c in storage.storage.method_calls)
assert method_calls["revision_add"] >= 2
def test_buffering_proxy_storage_release_threshold_not_hit(sample_data) -> None:
releases = sample_data.releases
threshold = 10
assert len(releases) < threshold
storage = get_storage_with_buffer_config(
- min_batch_size={"release": threshold,} # configuration set
+ min_batch_size={
+ "release": threshold,
+ } # configuration set
)
s = storage.release_add(releases)
assert s == {}
release_ids = [r.id for r in releases]
missing_releases = storage.release_missing(release_ids)
assert list(missing_releases) == release_ids
s = storage.flush()
assert s == {
"release:add": len(releases),
}
missing_releases = storage.release_missing(release_ids)
assert list(missing_releases) == []
def test_buffering_proxy_storage_release_threshold_hit(sample_data) -> None:
releases = sample_data.releases
threshold = 2
assert len(releases) > threshold
storage = get_storage_with_buffer_config(
- min_batch_size={"release": threshold,} # configuration set
+ min_batch_size={
+ "release": threshold,
+ } # configuration set
)
s = storage.release_add(releases)
assert s == {
"release:add": len(releases),
}
release_ids = [r.id for r in releases]
missing_releases = storage.release_missing(release_ids)
assert list(missing_releases) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_release_deduplicate(sample_data) -> None:
releases = sample_data.releases[:2]
- storage = get_storage_with_buffer_config(min_batch_size={"release": 2,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "release": 2,
+ }
+ )
s = storage.release_add([releases[0], releases[0]])
assert s == {}
s = storage.release_add([releases[0]])
assert s == {}
s = storage.release_add([releases[1]])
assert s == {
"release:add": 1 + 1,
}
missing_releases = storage.release_missing([r.id for r in releases])
assert list(missing_releases) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_release_size_threshold(sample_data) -> None:
releases = sample_data.releases
total_size = sum(estimate_release_size(r) for r in releases)
threshold = sum(estimate_release_size(r) for r in releases[:-2])
# ensure the threshold is in the middle
assert 0 < threshold < total_size
storage = get_storage_with_buffer_config(
min_batch_size={"release_bytes": threshold}
)
storage.storage = Mock(wraps=storage.storage)
for release in releases:
storage.release_add([release])
storage.flush()
# We should have called the underlying release_add at least twice, as
# we have hit the threshold for number of parents on release n-2
method_calls = Counter(c[0] for c in storage.storage.method_calls)
assert method_calls["release_add"] >= 2
def test_buffering_proxy_storage_snapshot_threshold_not_hit(sample_data) -> None:
snapshots = sample_data.snapshots
threshold = 10
assert len(snapshots) < threshold
storage = get_storage_with_buffer_config(
- min_batch_size={"snapshot": threshold,} # configuration set
+ min_batch_size={
+ "snapshot": threshold,
+ } # configuration set
)
s = storage.snapshot_add(snapshots)
assert s == {}
snapshot_ids = [r.id for r in snapshots]
missing_snapshots = storage.snapshot_missing(snapshot_ids)
assert list(missing_snapshots) == snapshot_ids
s = storage.flush()
assert s == {
"snapshot:add": len(snapshots),
}
missing_snapshots = storage.snapshot_missing(snapshot_ids)
assert list(missing_snapshots) == []
def test_buffering_proxy_storage_snapshot_threshold_hit(sample_data) -> None:
snapshots = sample_data.snapshots
threshold = 2
assert len(snapshots) > threshold
storage = get_storage_with_buffer_config(
- min_batch_size={"snapshot": threshold,} # configuration set
+ min_batch_size={
+ "snapshot": threshold,
+ } # configuration set
)
s = storage.snapshot_add(snapshots)
assert s == {
"snapshot:add": len(snapshots),
}
snapshot_ids = [r.id for r in snapshots]
missing_snapshots = storage.snapshot_missing(snapshot_ids)
assert list(missing_snapshots) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_snapshot_deduplicate(sample_data) -> None:
snapshots = sample_data.snapshots[:2]
- storage = get_storage_with_buffer_config(min_batch_size={"snapshot": 2,})
+ storage = get_storage_with_buffer_config(
+ min_batch_size={
+ "snapshot": 2,
+ }
+ )
s = storage.snapshot_add([snapshots[0], snapshots[0]])
assert s == {}
s = storage.snapshot_add([snapshots[0]])
assert s == {}
s = storage.snapshot_add([snapshots[1]])
assert s == {
"snapshot:add": 1 + 1,
}
missing_snapshots = storage.snapshot_missing([r.id for r in snapshots])
assert list(missing_snapshots) == []
s = storage.flush()
assert s == {}
def test_buffering_proxy_storage_clear(sample_data) -> None:
- """Clear operation on buffer
-
- """
+ """Clear operation on buffer"""
threshold = 10
contents = sample_data.contents
assert 0 < len(contents) < threshold
skipped_contents = sample_data.skipped_contents
assert 0 < len(skipped_contents) < threshold
directories = sample_data.directories
assert 0 < len(directories) < threshold
revisions = sample_data.revisions
assert 0 < len(revisions) < threshold
releases = sample_data.releases
assert 0 < len(releases) < threshold
snapshots = sample_data.snapshots
assert 0 < len(snapshots) < threshold
storage = get_storage_with_buffer_config(
min_batch_size={
"content": threshold,
"skipped_content": threshold,
"directory": threshold,
"revision": threshold,
"release": threshold,
}
)
s = storage.content_add(contents)
assert s == {}
s = storage.skipped_content_add(skipped_contents)
assert s == {}
s = storage.directory_add(directories)
assert s == {}
s = storage.revision_add(revisions)
assert s == {}
s = storage.release_add(releases)
assert s == {}
s = storage.snapshot_add(snapshots)
assert s == {}
assert len(storage._objects["content"]) == len(contents)
assert len(storage._objects["skipped_content"]) == len(skipped_contents)
assert len(storage._objects["directory"]) == len(directories)
assert len(storage._objects["revision"]) == len(revisions)
assert len(storage._objects["release"]) == len(releases)
assert len(storage._objects["snapshot"]) == len(snapshots)
# clear only content from the buffer
s = storage.clear_buffers(["content"]) # type: ignore
assert s is None
# specific clear operation on specific object type content only touched
# them
assert len(storage._objects["content"]) == 0
assert len(storage._objects["skipped_content"]) == len(skipped_contents)
assert len(storage._objects["directory"]) == len(directories)
assert len(storage._objects["revision"]) == len(revisions)
assert len(storage._objects["release"]) == len(releases)
assert len(storage._objects["snapshot"]) == len(snapshots)
# clear current buffer from all object types
s = storage.clear_buffers() # type: ignore
assert s is None
assert len(storage._objects["content"]) == 0
assert len(storage._objects["skipped_content"]) == 0
assert len(storage._objects["directory"]) == 0
assert len(storage._objects["revision"]) == 0
assert len(storage._objects["release"]) == 0
assert len(storage._objects["snapshot"]) == 0
def test_buffer_proxy_with_default_args() -> None:
storage = get_storage_with_buffer_config()
assert storage is not None
def test_buffer_flush_stats(sample_data) -> None:
storage = get_storage_with_buffer_config()
s = storage.content_add(sample_data.contents)
assert s == {}
s = storage.skipped_content_add(sample_data.skipped_contents)
assert s == {}
s = storage.directory_add(sample_data.directories)
assert s == {}
s = storage.revision_add(sample_data.revisions)
assert s == {}
s = storage.release_add(sample_data.releases)
assert s == {}
s = storage.snapshot_add(sample_data.snapshots)
assert s == {}
# Flush all the things
s = storage.flush()
assert s["content:add"] > 0
assert s["content:add:bytes"] > 0
assert s["skipped_content:add"] > 0
assert s["directory:add"] > 0
assert s["revision:add"] > 0
assert s["release:add"] > 0
assert s["snapshot:add"] > 0
def test_buffer_operation_order(sample_data) -> None:
storage = get_storage_with_buffer_config()
# Wrap the inner storage in a mock to track all method calls.
storage.storage = mocked_storage = Mock(wraps=storage.storage)
# Simulate a loader: add contents, directories, revisions, releases, then
# snapshots.
storage.content_add(sample_data.contents)
storage.skipped_content_add(sample_data.skipped_contents)
storage.directory_add(sample_data.directories)
storage.revision_add(sample_data.revisions)
storage.release_add(sample_data.releases)
storage.snapshot_add(sample_data.snapshots)
# Check that nothing has been flushed yet
assert mocked_storage.method_calls == []
# Flush all the things
storage.flush()
methods_called = [c[0] for c in mocked_storage.method_calls]
prev = -1
for method in [
"content_add",
"skipped_content_add",
"directory_add",
"revision_add",
"release_add",
"snapshot_add",
"flush",
]:
try:
cur: Optional[int] = methods_called.index(method)
except ValueError:
cur = None
assert cur is not None, "Method %s not called" % method
assert cur > prev, "Method %s called out of order; all calls were: %s" % (
method,
methods_called,
)
prev = cur
def test_buffer_empty_batches() -> None:
"Flushing an empty buffer storage doesn't call any underlying _add method"
storage = get_storage_with_buffer_config()
storage.storage = mocked_storage = Mock(wraps=storage.storage)
storage.flush()
methods_called = {c[0] for c in mocked_storage.method_calls}
assert methods_called == {"flush", "clear_buffers"}
diff --git a/swh/storage/tests/test_cassandra.py b/swh/storage/tests/test_cassandra.py
index 89b843cc..5234a84e 100644
--- a/swh/storage/tests/test_cassandra.py
+++ b/swh/storage/tests/test_cassandra.py
@@ -1,745 +1,767 @@
# Copyright (C) 2018-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
import itertools
import os
import resource
import signal
import socket
import subprocess
import time
from typing import Any, Dict
import attr
from cassandra.cluster import NoHostAvailable
import pytest
from swh.core.api.classes import stream_results
from swh.model import from_disk
from swh.model.model import Directory, DirectoryEntry, Snapshot, SnapshotBranch
from swh.storage import get_storage
from swh.storage.cassandra import create_keyspace
from swh.storage.cassandra.cql import BATCH_INSERT_MAX_SIZE
from swh.storage.cassandra.model import ContentRow, ExtIDRow
from swh.storage.cassandra.schema import HASH_ALGORITHMS, TABLES
from swh.storage.cassandra.storage import DIRECTORY_ENTRIES_INSERT_ALGOS
from swh.storage.tests.storage_data import StorageData
from swh.storage.tests.storage_tests import (
TestStorageGeneratedData as _TestStorageGeneratedData,
)
from swh.storage.tests.storage_tests import TestStorage as _TestStorage
from swh.storage.utils import now, remove_keys
CONFIG_TEMPLATE = """
data_file_directories:
- {data_dir}/data
commitlog_directory: {data_dir}/commitlog
hints_directory: {data_dir}/hints
saved_caches_directory: {data_dir}/saved_caches
commitlog_sync: periodic
commitlog_sync_period_in_ms: 1000000
partitioner: org.apache.cassandra.dht.Murmur3Partitioner
endpoint_snitch: SimpleSnitch
seed_provider:
- class_name: org.apache.cassandra.locator.SimpleSeedProvider
parameters:
- seeds: "127.0.0.1"
storage_port: {storage_port}
native_transport_port: {native_transport_port}
start_native_transport: true
listen_address: 127.0.0.1
enable_user_defined_functions: true
# speed-up by disabling period saving to disk
key_cache_save_period: 0
row_cache_save_period: 0
trickle_fsync: false
commitlog_sync_period_in_ms: 100000
"""
SCYLLA_EXTRA_CONFIG_TEMPLATE = """
experimental_features:
- udf
view_hints_directory: {data_dir}/view_hints
prometheus_port: 0 # disable prometheus server
start_rpc: false # disable thrift server
api_port: {api_port}
"""
def free_port():
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.bind(("127.0.0.1", 0))
port = sock.getsockname()[1]
sock.close()
return port
def wait_for_peer(addr, port):
wait_until = time.time() + 60
while time.time() < wait_until:
try:
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.connect((addr, port))
except ConnectionRefusedError:
time.sleep(0.1)
else:
sock.close()
return True
return False
@pytest.fixture(scope="session")
def cassandra_cluster(tmpdir_factory):
cassandra_conf = tmpdir_factory.mktemp("cassandra_conf")
cassandra_data = tmpdir_factory.mktemp("cassandra_data")
cassandra_log = tmpdir_factory.mktemp("cassandra_log")
native_transport_port = free_port()
storage_port = free_port()
jmx_port = free_port()
api_port = free_port()
use_scylla = bool(os.environ.get("SWH_USE_SCYLLADB", ""))
cassandra_bin = os.environ.get(
"SWH_CASSANDRA_BIN", "/usr/bin/scylla" if use_scylla else "/usr/sbin/cassandra"
)
if use_scylla:
os.makedirs(cassandra_conf.join("conf"))
config_path = cassandra_conf.join("conf/scylla.yaml")
config_template = CONFIG_TEMPLATE + SCYLLA_EXTRA_CONFIG_TEMPLATE
else:
config_path = cassandra_conf.join("cassandra.yaml")
config_template = CONFIG_TEMPLATE
with open(str(config_path), "w") as fd:
fd.write(
config_template.format(
data_dir=str(cassandra_data),
storage_port=storage_port,
native_transport_port=native_transport_port,
api_port=api_port,
)
)
if os.environ.get("SWH_CASSANDRA_LOG"):
stdout = stderr = None
else:
stdout = stderr = subprocess.DEVNULL
env = {
"MAX_HEAP_SIZE": "300M",
"HEAP_NEWSIZE": "50M",
"JVM_OPTS": "-Xlog:gc=error:file=%s/gc.log" % cassandra_log,
}
if "JAVA_HOME" in os.environ:
env["JAVA_HOME"] = os.environ["JAVA_HOME"]
if use_scylla:
env = {
**env,
"SCYLLA_HOME": cassandra_conf,
}
# prevent "NOFILE rlimit too low (recommended setting 200000,
# minimum setting 10000; refusing to start."
resource.setrlimit(resource.RLIMIT_NOFILE, (200000, 200000))
proc = subprocess.Popen(
- [cassandra_bin, "--developer-mode=1",],
+ [
+ cassandra_bin,
+ "--developer-mode=1",
+ ],
start_new_session=True,
env=env,
stdout=stdout,
stderr=stderr,
)
else:
proc = subprocess.Popen(
[
cassandra_bin,
"-Dcassandra.config=file://%s/cassandra.yaml" % cassandra_conf,
"-Dcassandra.logdir=%s" % cassandra_log,
"-Dcassandra.jmx.local.port=%d" % jmx_port,
"-Dcassandra-foreground=yes",
],
start_new_session=True,
env=env,
stdout=stdout,
stderr=stderr,
)
listening = wait_for_peer("127.0.0.1", native_transport_port)
if listening:
yield (["127.0.0.1"], native_transport_port)
if not listening or os.environ.get("SWH_CASSANDRA_LOG"):
debug_log_path = str(cassandra_log.join("debug.log"))
if os.path.exists(debug_log_path):
with open(debug_log_path) as fd:
print(fd.read())
if not listening:
if proc.poll() is None:
raise Exception("cassandra process unexpectedly not listening.")
else:
raise Exception("cassandra process unexpectedly stopped.")
pgrp = os.getpgid(proc.pid)
os.killpg(pgrp, signal.SIGKILL)
class RequestHandler:
def on_request(self, rf):
if hasattr(rf.message, "query"):
print()
print(rf.message.query)
@pytest.fixture(scope="session")
def keyspace(cassandra_cluster):
(hosts, port) = cassandra_cluster
keyspace = os.urandom(10).hex()
create_keyspace(hosts, keyspace, port)
return keyspace
# tests are executed using imported classes (TestStorage and
# TestStorageGeneratedData) using overloaded swh_storage fixture
# below
@pytest.fixture
def swh_storage_backend_config(cassandra_cluster, keyspace):
(hosts, port) = cassandra_cluster
storage_config = dict(
cls="cassandra",
hosts=hosts,
port=port,
keyspace=keyspace,
journal_writer={"cls": "memory"},
objstorage={"cls": "memory"},
)
yield storage_config
storage = get_storage(**storage_config)
for table in TABLES:
storage._cql_runner._session.execute('TRUNCATE TABLE "%s"' % table)
storage._cql_runner._cluster.shutdown()
@pytest.mark.cassandra
class TestCassandraStorage(_TestStorage):
def test_config_wrong_consistency_should_raise(self):
storage_config = dict(
cls="cassandra",
hosts=["first"],
port=9999,
keyspace="any",
consistency_level="fake",
journal_writer={"cls": "memory"},
objstorage={"cls": "memory"},
)
with pytest.raises(ValueError, match="Unknown consistency"):
get_storage(**storage_config)
def test_config_consistency_used(self, swh_storage_backend_config):
config_with_consistency = dict(
swh_storage_backend_config, **{"consistency_level": "THREE"}
)
storage = get_storage(**config_with_consistency)
with pytest.raises(NoHostAvailable):
storage.content_get_random()
def test_content_add_murmur3_collision(self, swh_storage, mocker, sample_data):
"""The Murmur3 token is used as link from index tables to the main
table; and non-matching contents with colliding murmur3-hash
are filtered-out when reading the main table.
This test checks the content methods do filter out these collision.
"""
called = 0
cont, cont2 = sample_data.contents[:2]
# always return a token
def mock_cgtfsa(algo, hashes):
nonlocal called
called += 1
assert algo in ("sha1", "sha1_git")
return [123456]
mocker.patch.object(
- swh_storage._cql_runner, "content_get_tokens_from_single_algo", mock_cgtfsa,
+ swh_storage._cql_runner,
+ "content_get_tokens_from_single_algo",
+ mock_cgtfsa,
)
# For all tokens, always return cont
def mock_cgft(tokens):
nonlocal called
called += 1
return [
ContentRow(
length=10,
ctime=datetime.datetime.now(),
status="present",
**{algo: getattr(cont, algo) for algo in HASH_ALGORITHMS},
)
]
mocker.patch.object(
swh_storage._cql_runner, "content_get_from_tokens", mock_cgft
)
actual_result = swh_storage.content_add([cont2])
assert called == 4
assert actual_result == {
"content:add": 1,
"content:add:bytes": cont2.length,
}
def test_content_get_metadata_murmur3_collision(
self, swh_storage, mocker, sample_data
):
"""The Murmur3 token is used as link from index tables to the main
table; and non-matching contents with colliding murmur3-hash
are filtered-out when reading the main table.
This test checks the content methods do filter out these collisions.
"""
called = 0
cont, cont2 = [attr.evolve(c, ctime=now()) for c in sample_data.contents[:2]]
# always return a token
def mock_cgtfsa(algo, hashes):
nonlocal called
called += 1
assert algo in ("sha1", "sha1_git")
return [123456]
mocker.patch.object(
- swh_storage._cql_runner, "content_get_tokens_from_single_algo", mock_cgtfsa,
+ swh_storage._cql_runner,
+ "content_get_tokens_from_single_algo",
+ mock_cgtfsa,
)
# For all tokens, always return cont and cont2
cols = list(set(cont.to_dict()) - {"data"})
def mock_cgft(tokens):
nonlocal called
called += 1
return [
- ContentRow(**{col: getattr(cont, col) for col in cols},)
+ ContentRow(
+ **{col: getattr(cont, col) for col in cols},
+ )
for cont in [cont, cont2]
]
mocker.patch.object(
swh_storage._cql_runner, "content_get_from_tokens", mock_cgft
)
actual_result = swh_storage.content_get([cont.sha1])
assert called == 2
# dropping extra column not returned
expected_cont = attr.evolve(cont, data=None)
# but cont2 should be filtered out
assert actual_result == [expected_cont]
def test_content_find_murmur3_collision(self, swh_storage, mocker, sample_data):
"""The Murmur3 token is used as link from index tables to the main
table; and non-matching contents with colliding murmur3-hash
are filtered-out when reading the main table.
This test checks the content methods do filter out these collisions.
"""
called = 0
cont, cont2 = [attr.evolve(c, ctime=now()) for c in sample_data.contents[:2]]
# always return a token
def mock_cgtfsa(algo, hashes):
nonlocal called
called += 1
assert algo in ("sha1", "sha1_git")
return [123456]
mocker.patch.object(
- swh_storage._cql_runner, "content_get_tokens_from_single_algo", mock_cgtfsa,
+ swh_storage._cql_runner,
+ "content_get_tokens_from_single_algo",
+ mock_cgtfsa,
)
# For all tokens, always return cont and cont2
cols = list(set(cont.to_dict()) - {"data"})
def mock_cgft(tokens):
nonlocal called
called += 1
return [
ContentRow(**{col: getattr(cont, col) for col in cols})
for cont in [cont, cont2]
]
mocker.patch.object(
swh_storage._cql_runner, "content_get_from_tokens", mock_cgft
)
expected_content = attr.evolve(cont, data=None)
actual_result = swh_storage.content_find({"sha1": cont.sha1})
assert called == 2
# but cont2 should be filtered out
assert actual_result == [expected_content]
def test_content_get_partition_murmur3_collision(
self, swh_storage, mocker, sample_data
):
"""The Murmur3 token is used as link from index tables to the main table; and
non-matching contents with colliding murmur3-hash are filtered-out when reading
the main table.
This test checks the content_get_partition endpoints return all contents, even
the collisions.
"""
called = 0
rows: Dict[int, Dict] = {}
for tok, content in enumerate(sample_data.contents):
cont = attr.evolve(content, data=None, ctime=now())
row_d = {**cont.to_dict(), "tok": tok}
rows[tok] = row_d
# For all tokens, always return cont
def mock_content_get_token_range(range_start, range_end, limit):
nonlocal called
called += 1
for tok in list(rows.keys()) * 3: # yield multiple times the same tok
row_d = dict(rows[tok].items())
row_d.pop("tok")
yield (tok, ContentRow(**row_d))
mocker.patch.object(
swh_storage._cql_runner,
"content_get_token_range",
mock_content_get_token_range,
)
actual_results = list(
stream_results(
swh_storage.content_get_partition, partition_id=0, nb_partitions=1
)
)
assert called > 0
# everything is listed, even collisions
assert len(actual_results) == 3 * len(sample_data.contents)
# as we duplicated the returned results, dropping duplicate should yield
# the original length
assert len(set(actual_results)) == len(sample_data.contents)
@pytest.mark.skip("content_update is not yet implemented for Cassandra")
def test_content_update(self):
pass
def test_extid_murmur3_collision(self, swh_storage, mocker, sample_data):
"""The Murmur3 token is used as link from index table to the main
table; and non-matching extid with colliding murmur3-hash
are filtered-out when reading the main table.
This test checks the extid methods do filter out these collision.
"""
swh_storage.extid_add(sample_data.extids)
# For any token, always return all extids, i.e. make as if all tokens
# for all extid entries collide
def mock_egft(token):
return [
ExtIDRow(
extid_type=extid.extid_type,
extid=extid.extid,
extid_version=extid.extid_version,
target_type=extid.target.object_type.value,
target=extid.target.object_id,
)
for extid in sample_data.extids
]
mocker.patch.object(
- swh_storage._cql_runner, "extid_get_from_token", mock_egft,
+ swh_storage._cql_runner,
+ "extid_get_from_token",
+ mock_egft,
)
for extid in sample_data.extids:
extids = swh_storage.extid_get_from_target(
target_type=extid.target.object_type, ids=[extid.target.object_id]
)
assert extids == [extid]
def _directory_with_entries(self, sample_data, nb_entries):
"""Returns a dir with ``nb_entries``, all pointing to
the same content"""
return Directory(
entries=tuple(
DirectoryEntry(
name=f"file{i:10}".encode(),
type="file",
target=sample_data.content.sha1_git,
perms=from_disk.DentryPerms.directory,
)
for i in range(nb_entries)
)
)
@pytest.mark.parametrize(
"insert_algo,nb_entries",
[
("one-by-one", 10),
("concurrent", 10),
("batch", 1),
("batch", 2),
("batch", BATCH_INSERT_MAX_SIZE - 1),
("batch", BATCH_INSERT_MAX_SIZE),
("batch", BATCH_INSERT_MAX_SIZE + 1),
("batch", BATCH_INSERT_MAX_SIZE * 2),
],
)
def test_directory_add_algos(
- self, swh_storage, sample_data, mocker, insert_algo, nb_entries,
+ self,
+ swh_storage,
+ sample_data,
+ mocker,
+ insert_algo,
+ nb_entries,
):
mocker.patch.object(swh_storage, "_directory_entries_insert_algo", insert_algo)
class new_sample_data:
content = sample_data.content
directory = self._directory_with_entries(sample_data, nb_entries)
self.test_directory_add(swh_storage, new_sample_data)
@pytest.mark.parametrize("insert_algo", DIRECTORY_ENTRIES_INSERT_ALGOS)
def test_directory_add_atomic(self, swh_storage, sample_data, mocker, insert_algo):
"""Checks that a crash occurring after some directory entries were written
does not cause the directory to be (partially) visible.
ie. checks directories are added somewhat atomically."""
# Disable the journal writer, it would detect the CrashyEntry exception too
# early for this test to be relevant
swh_storage.journal_writer.journal = None
mocker.patch.object(swh_storage, "_directory_entries_insert_algo", insert_algo)
class CrashyEntry(DirectoryEntry):
def __init__(self):
super().__init__(**{**directory.entries[0].to_dict(), "name": b"crash"})
def to_dict(self):
return {**super().to_dict(), "perms": "abcde"}
directory = self._directory_with_entries(sample_data, BATCH_INSERT_MAX_SIZE)
entries = directory.entries
directory = attr.evolve(directory, entries=entries + (CrashyEntry(),))
with pytest.raises(TypeError):
swh_storage.directory_add([directory])
# This should have written some of the entries to the database:
entry_rows = swh_storage._cql_runner.directory_entry_get([directory.id])
assert {row.name for row in entry_rows} == {entry.name for entry in entries}
# BUT, because not all the entries were written, the directory should
# be considered not written.
assert swh_storage.directory_missing([directory.id]) == [directory.id]
assert list(swh_storage.directory_ls(directory.id)) == []
assert swh_storage.directory_get_entries(directory.id) is None
def test_snapshot_add_atomic(self, swh_storage, sample_data, mocker):
"""Checks that a crash occurring after some snapshot branches were written
does not cause the snapshot to be (partially) visible.
ie. checks snapshots are added somewhat atomically."""
# Disable the journal writer, it would detect the CrashyBranch exception too
# early for this test to be relevant
swh_storage.journal_writer.journal = None
class MyException(Exception):
pass
class CrashyBranch(SnapshotBranch):
def __getattribute__(self, name):
if name == "target" and should_raise:
raise MyException()
else:
return super().__getattribute__(name)
snapshot = sample_data.complete_snapshot
branches = snapshot.branches
should_raise = False # just so that we can construct the object
crashy_branch = CrashyBranch.from_dict(branches[b"directory"].to_dict())
should_raise = True
snapshot = attr.evolve(
- snapshot, branches={**branches, b"crashy": crashy_branch,},
+ snapshot,
+ branches={
+ **branches,
+ b"crashy": crashy_branch,
+ },
)
with pytest.raises(MyException):
swh_storage.snapshot_add([snapshot])
# This should have written some of the branches to the database:
branch_rows = swh_storage._cql_runner.snapshot_branch_get(snapshot.id, b"", 10)
assert {row.name for row in branch_rows} == set(branches)
# BUT, because not all the branches were written, the snapshot should
# be considered not written.
assert swh_storage.snapshot_missing([snapshot.id]) == [snapshot.id]
assert swh_storage.snapshot_get(snapshot.id) is None
assert swh_storage.snapshot_count_branches(snapshot.id) is None
assert swh_storage.snapshot_get_branches(snapshot.id) is None
@pytest.mark.skip(
'The "person" table of the pgsql is a legacy thing, and not '
"supported by the cassandra backend."
)
def test_person_fullname_unicity(self):
pass
@pytest.mark.skip(
'The "person" table of the pgsql is a legacy thing, and not '
"supported by the cassandra backend."
)
def test_person_get(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count(self):
pass
@pytest.mark.cassandra
class TestCassandraStorageGeneratedData(_TestStorageGeneratedData):
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count_with_visit_no_visits(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count_with_visit_with_visits_and_snapshot(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count_with_visit_with_visits_no_snapshot(self):
pass
@pytest.mark.parametrize(
"allow_overwrite,object_type",
itertools.product(
[False, True],
# Note the absence of "content", it's tested above.
["directory", "revision", "release", "snapshot", "origin", "extid"],
),
)
def test_allow_overwrite(
allow_overwrite: bool, object_type: str, swh_storage_backend_config
):
if object_type in ("origin", "extid"):
pytest.skip(
f"test_disallow_overwrite not implemented for {object_type} objects, "
f"because all their columns are in the primary key."
)
swh_storage = get_storage(
allow_overwrite=allow_overwrite, **swh_storage_backend_config
)
# directory_ls joins with content and directory table, and needs those to return
# non-None entries:
if object_type == "directory":
swh_storage.directory_add([StorageData.directory5])
swh_storage.content_add([StorageData.content, StorageData.content2])
obj1: Any
obj2: Any
# Get two test objects
if object_type == "directory":
(obj1, obj2, *_) = StorageData.directories
elif object_type == "snapshot":
# StorageData.snapshots[1] is the empty snapshot, which is the corner case
# that makes this test succeed for the wrong reasons
obj1 = StorageData.snapshot
obj2 = StorageData.complete_snapshot
else:
(obj1, obj2, *_) = getattr(StorageData, (object_type + "s"))
# Let's make both objects have the same hash, but different content
obj1 = attr.evolve(obj1, id=obj2.id)
# Get the methods used to add and get these objects
add = getattr(swh_storage, object_type + "_add")
if object_type == "directory":
def get(ids):
return [
Directory(
id=ids[0],
entries=tuple(
map(
lambda entry: DirectoryEntry(
name=entry["name"],
type=entry["type"],
target=entry["sha1_git"],
perms=entry["perms"],
),
swh_storage.directory_ls(ids[0]),
)
),
)
]
elif object_type == "snapshot":
def get(ids):
return [
Snapshot.from_dict(
remove_keys(swh_storage.snapshot_get(ids[0]), ("next_branch",))
)
]
else:
get = getattr(swh_storage, object_type + "_get")
# Add the first object
add([obj1])
# It should be returned as-is
assert get([obj1.id]) == [obj1]
# Add the second object
add([obj2])
if allow_overwrite:
# obj1 was overwritten by obj2
expected = obj2
else:
# obj2 was not written, because obj1 already exists and has the same hash
expected = obj1
if allow_overwrite and object_type in ("directory", "snapshot"):
# TODO
pytest.xfail(
"directory entries and snapshot branches are concatenated "
"instead of being replaced"
)
assert get([obj1.id]) == [expected]
diff --git a/swh/storage/tests/test_cli.py b/swh/storage/tests/test_cli.py
index f472dbf1..5276e878 100644
--- a/swh/storage/tests/test_cli.py
+++ b/swh/storage/tests/test_cli.py
@@ -1,125 +1,139 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import copy
import logging
import re
import tempfile
from unittest.mock import patch
from click.testing import CliRunner
from confluent_kafka import Producer
import pytest
import yaml
from swh.journal.serializers import key_to_kafka, value_to_kafka
from swh.model.model import Snapshot, SnapshotBranch, TargetType
from swh.storage import get_storage
from swh.storage.cli import storage as cli
from swh.storage.replay import OBJECT_CONVERTERS
logger = logging.getLogger(__name__)
CLI_CONFIG = {
- "storage": {"cls": "memory",},
+ "storage": {
+ "cls": "memory",
+ },
}
@pytest.fixture
def swh_storage():
"""An swh-storage object that gets injected into the CLI functions."""
storage = get_storage(**CLI_CONFIG["storage"])
with patch("swh.storage.get_storage") as get_storage_mock:
get_storage_mock.return_value = storage
yield storage
@pytest.fixture
def monkeypatch_retry_sleep(monkeypatch):
from swh.journal.replay import copy_object, obj_in_objstorage
monkeypatch.setattr(copy_object.retry, "sleep", lambda x: None)
monkeypatch.setattr(obj_in_objstorage.retry, "sleep", lambda x: None)
def invoke(*args, env=None, journal_config=None):
config = copy.deepcopy(CLI_CONFIG)
if journal_config:
config["journal_client"] = journal_config.copy()
config["journal_client"]["cls"] = "kafka"
runner = CliRunner()
with tempfile.NamedTemporaryFile("a", suffix=".yml") as config_fd:
yaml.dump(config, config_fd)
config_fd.seek(0)
args = ["-C" + config_fd.name] + list(args)
- ret = runner.invoke(cli, args, obj={"log_level": logging.DEBUG}, env=env,)
+ ret = runner.invoke(
+ cli,
+ args,
+ obj={"log_level": logging.DEBUG},
+ env=env,
+ )
return ret
def test_replay(
- swh_storage, kafka_prefix: str, kafka_consumer_group: str, kafka_server: str,
+ swh_storage,
+ kafka_prefix: str,
+ kafka_consumer_group: str,
+ kafka_server: str,
):
kafka_prefix += ".swh.journal.objects"
producer = Producer(
{
"bootstrap.servers": kafka_server,
"client.id": "test-producer",
"acks": "all",
}
)
snapshot = Snapshot(
branches={
b"HEAD": SnapshotBranch(
- target_type=TargetType.REVISION, target=b"\x01" * 20,
+ target_type=TargetType.REVISION,
+ target=b"\x01" * 20,
)
},
)
snapshot_dict = snapshot.to_dict()
producer.produce(
topic=kafka_prefix + ".snapshot",
key=key_to_kafka(snapshot.id),
value=value_to_kafka(snapshot_dict),
)
producer.flush()
logger.debug("Flushed producer")
result = invoke(
"replay",
"--stop-after-objects",
"1",
journal_config={
"brokers": [kafka_server],
"group_id": kafka_consumer_group,
"prefix": kafka_prefix,
},
)
expected = r"Done.\n"
assert result.exit_code == 0, result.output
assert re.fullmatch(expected, result.output, re.MULTILINE), result.output
assert swh_storage.snapshot_get(snapshot.id) == {
**snapshot_dict,
"next_branch": None,
}
def test_replay_type_list():
- result = invoke("replay", "--help",)
+ result = invoke(
+ "replay",
+ "--help",
+ )
assert result.exit_code == 0, result.output
types_in_help = re.findall("--type [[]([a-z_|]+)[]]", result.output)
assert len(types_in_help) == 1
types = types_in_help[0].split("|")
assert sorted(types) == sorted(list(OBJECT_CONVERTERS.keys())), (
"Make sure the list of accepted types in cli.py "
"matches implementation in replay.py"
)
diff --git a/swh/storage/tests/test_filter.py b/swh/storage/tests/test_filter.py
index 0ffe9cea..92e7fea3 100644
--- a/swh/storage/tests/test_filter.py
+++ b/swh/storage/tests/test_filter.py
@@ -1,181 +1,184 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from unittest.mock import Mock
import attr
import pytest
from swh.storage import get_storage
@pytest.fixture
def swh_storage():
storage_config = {
"cls": "pipeline",
- "steps": [{"cls": "filter"}, {"cls": "memory"},],
+ "steps": [
+ {"cls": "filter"},
+ {"cls": "memory"},
+ ],
}
return get_storage(**storage_config)
def test_filtering_proxy_storage_content(swh_storage, sample_data):
sample_content = sample_data.content
content = swh_storage.content_get_data(sample_content.sha1)
assert content is None
s = swh_storage.content_add([sample_content])
assert s == {
"content:add": 1,
"content:add:bytes": sample_content.length,
}
content = swh_storage.content_get_data(sample_content.sha1)
assert content is not None
s = swh_storage.content_add([sample_content])
assert s == {
"content:add": 0,
"content:add:bytes": 0,
}
def test_filtering_proxy_storage_skipped_content(swh_storage, sample_data):
sample_content = sample_data.skipped_content
sample_content_dict = sample_content.to_dict()
content = next(swh_storage.skipped_content_missing([sample_content_dict]))
assert content["sha1"] == sample_content.sha1
s = swh_storage.skipped_content_add([sample_content])
assert s == {
"skipped_content:add": 1,
}
content = list(swh_storage.skipped_content_missing([sample_content_dict]))
assert content == []
s = swh_storage.skipped_content_add([sample_content])
assert s == {
"skipped_content:add": 0,
}
def test_filtering_proxy_storage_skipped_content_missing_sha1_git(
swh_storage, sample_data
):
sample_contents = [
attr.evolve(c, sha1_git=None) for c in sample_data.skipped_contents
]
sample_content, sample_content2 = [c.to_dict() for c in sample_contents[:2]]
content = next(swh_storage.skipped_content_missing([sample_content]))
assert content["sha1"] == sample_content["sha1"]
s = swh_storage.skipped_content_add([sample_contents[0]])
assert s == {
"skipped_content:add": 1,
}
content = list(swh_storage.skipped_content_missing([sample_content]))
assert content == []
s = swh_storage.skipped_content_add([sample_contents[1]])
assert s == {
"skipped_content:add": 1,
}
content = list(swh_storage.skipped_content_missing([sample_content2]))
assert content == []
def test_filtering_proxy_storage_revision(swh_storage, sample_data):
sample_revision = sample_data.revision
revision = swh_storage.revision_get([sample_revision.id])[0]
assert revision is None
s = swh_storage.revision_add([sample_revision])
assert s == {
"revision:add": 1,
}
revision = swh_storage.revision_get([sample_revision.id])[0]
assert revision is not None
s = swh_storage.revision_add([sample_revision])
assert s == {
"revision:add": 0,
}
def test_filtering_proxy_storage_release(swh_storage, sample_data):
sample_release = sample_data.release
release = swh_storage.release_get([sample_release.id])[0]
assert release is None
s = swh_storage.release_add([sample_release])
assert s == {
"release:add": 1,
}
release = swh_storage.release_get([sample_release.id])[0]
assert release is not None
s = swh_storage.release_add([sample_release])
assert s == {
"release:add": 0,
}
def test_filtering_proxy_storage_directory(swh_storage, sample_data):
sample_directory = sample_data.directory
directory = list(swh_storage.directory_missing([sample_directory.id]))[0]
assert directory
s = swh_storage.directory_add([sample_directory])
assert s == {
"directory:add": 1,
}
directory = list(swh_storage.directory_missing([sample_directory.id]))
assert not directory
s = swh_storage.directory_add([sample_directory])
assert s == {
"directory:add": 0,
}
def test_filtering_proxy_storage_empty_list(swh_storage, sample_data):
swh_storage.storage = mock_storage = Mock(wraps=swh_storage.storage)
calls = 0
for object_type in swh_storage.object_types:
calls += 1
method_name = f"{object_type}_add"
method = getattr(swh_storage, method_name)
one_object = getattr(sample_data, object_type)
# Call with empty list: ensure underlying storage not called
method([])
assert method_name not in {c[0] for c in mock_storage.method_calls}
mock_storage.reset_mock()
# Call with an object: ensure underlying storage is called
method([one_object])
assert method_name in {c[0] for c in mock_storage.method_calls}
mock_storage.reset_mock()
# Call with the same object: ensure underlying storage is not called again
method([one_object])
assert method_name not in {c[0] for c in mock_storage.method_calls}
mock_storage.reset_mock()
assert calls > 0, "Empty list never tested"
diff --git a/swh/storage/tests/test_in_memory.py b/swh/storage/tests/test_in_memory.py
index 7f6b753b..47090d47 100644
--- a/swh/storage/tests/test_in_memory.py
+++ b/swh/storage/tests/test_in_memory.py
@@ -1,129 +1,131 @@
# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import dataclasses
import pytest
from swh.storage.cassandra.model import BaseRow
from swh.storage.in_memory import Table
from swh.storage.tests.storage_tests import (
TestStorageGeneratedData as _TestStorageGeneratedData,
)
from swh.storage.tests.storage_tests import TestStorage as _TestStorage
# tests are executed using imported classes (TestStorage and
# TestStorageGeneratedData) using overloaded swh_storage fixture
# below
@pytest.fixture
def swh_storage_backend_config():
yield {
"cls": "memory",
- "journal_writer": {"cls": "memory",},
+ "journal_writer": {
+ "cls": "memory",
+ },
}
@dataclasses.dataclass
class Row(BaseRow):
PARTITION_KEY = ("col1", "col2")
CLUSTERING_KEY = ("col3", "col4")
col1: str
col2: str
col3: str
col4: str
col5: str
col6: int
def test_table_keys():
table = Table(Row)
primary_key = ("foo", "bar", "baz", "qux")
partition_key = ("foo", "bar")
clustering_key = ("baz", "qux")
row = Row(col1="foo", col2="bar", col3="baz", col4="qux", col5="quux", col6=4)
assert table.partition_key(row) == partition_key
assert table.clustering_key(row) == clustering_key
assert table.primary_key(row) == primary_key
assert table.primary_key_from_dict(row.to_dict()) == primary_key
assert table.split_primary_key(primary_key) == (partition_key, clustering_key)
def test_table():
table = Table(Row)
row1 = Row(col1="foo", col2="bar", col3="baz", col4="qux", col5="quux", col6=4)
row2 = Row(col1="foo", col2="bar", col3="baz", col4="qux2", col5="quux", col6=4)
row3 = Row(col1="foo", col2="bar", col3="baz", col4="qux1", col5="quux", col6=4)
row4 = Row(col1="foo", col2="bar2", col3="baz", col4="qux1", col5="quux", col6=4)
partition_key = ("foo", "bar")
partition_key4 = ("foo", "bar2")
primary_key1 = ("foo", "bar", "baz", "qux")
primary_key2 = ("foo", "bar", "baz", "qux2")
primary_key3 = ("foo", "bar", "baz", "qux1")
primary_key4 = ("foo", "bar2", "baz", "qux1")
table.insert(row1)
table.insert(row2)
table.insert(row3)
table.insert(row4)
assert table.get_from_primary_key(primary_key1) == row1
assert table.get_from_primary_key(primary_key2) == row2
assert table.get_from_primary_key(primary_key3) == row3
assert table.get_from_primary_key(primary_key4) == row4
# order matters
assert list(table.get_from_token(table.token(partition_key))) == [row1, row3, row2]
# order matters
assert list(table.get_from_partition_key(partition_key)) == [row1, row3, row2]
assert list(table.get_from_partition_key(partition_key4)) == [row4]
all_rows = list(table.iter_all())
assert len(all_rows) == 4
for row in (row1, row2, row3, row4):
assert (table.primary_key(row), row) in all_rows
class TestInMemoryStorage(_TestStorage):
@pytest.mark.skip(
'The "person" table of the pgsql is a legacy thing, and not '
"supported by the cassandra backend."
)
def test_person_fullname_unicity(self):
pass
@pytest.mark.skip("content_update is not yet implemented for Cassandra")
def test_content_update(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count(self):
pass
class TestInMemoryStorageGeneratedData(_TestStorageGeneratedData):
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count_with_visit_no_visits(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count_with_visit_with_visits_and_snapshot(self):
pass
@pytest.mark.skip("Not supported by Cassandra")
def test_origin_count_with_visit_with_visits_no_snapshot(self):
pass
diff --git a/swh/storage/tests/test_init.py b/swh/storage/tests/test_init.py
index 4ff3fe9c..069d5c3c 100644
--- a/swh/storage/tests/test_init.py
+++ b/swh/storage/tests/test_init.py
@@ -1,234 +1,257 @@
# Copyright (C) 2019-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from unittest.mock import patch
import pytest
from swh.core.pytest_plugin import RPCTestAdapter
from swh.storage import get_storage
from swh.storage.api import client, server
from swh.storage.in_memory import InMemoryStorage
from swh.storage.postgresql.storage import Storage as DbStorage
from swh.storage.proxies.buffer import BufferingProxyStorage
from swh.storage.proxies.filter import FilteringProxyStorage
from swh.storage.proxies.retry import RetryingProxyStorage
STORAGES = [
pytest.param(cls, real_class, kwargs, id=cls)
for (cls, real_class, kwargs) in [
("remote", client.RemoteStorage, {"url": "url"}),
("memory", InMemoryStorage, {}),
(
"postgresql",
DbStorage,
{"db": "postgresql://db", "objstorage": {"cls": "memory"}},
),
("filter", FilteringProxyStorage, {"storage": {"cls": "memory"}}),
("buffer", BufferingProxyStorage, {"storage": {"cls": "memory"}}),
("retry", RetryingProxyStorage, {"storage": {"cls": "memory"}}),
]
]
@pytest.mark.parametrize("cls,real_class,args", STORAGES)
@patch("swh.storage.postgresql.storage.psycopg2.pool")
def test_get_storage(mock_pool, cls, real_class, args):
- """Instantiating an existing storage should be ok
-
- """
+ """Instantiating an existing storage should be ok"""
mock_pool.ThreadedConnectionPool.return_value = None
actual_storage = get_storage(cls, **args)
assert actual_storage is not None
assert isinstance(actual_storage, real_class)
@pytest.mark.parametrize("cls,real_class,args", STORAGES)
@patch("swh.storage.postgresql.storage.psycopg2.pool")
def test_get_storage_legacy_args(mock_pool, cls, real_class, args):
"""Instantiating an existing storage should be ok even with the legacy
explicit 'args' keys
"""
mock_pool.ThreadedConnectionPool.return_value = None
with pytest.warns(DeprecationWarning):
actual_storage = get_storage(cls, args=args)
assert actual_storage is not None
assert isinstance(actual_storage, real_class)
def test_get_storage_failure():
- """Instantiating an unknown storage should raise
-
- """
+ """Instantiating an unknown storage should raise"""
with pytest.raises(ValueError, match="Unknown storage class `unknown`"):
get_storage("unknown")
def test_get_storage_pipeline():
config = {
"cls": "pipeline",
"steps": [
- {"cls": "filter",},
- {"cls": "buffer", "min_batch_size": {"content": 10,},},
- {"cls": "memory",},
+ {
+ "cls": "filter",
+ },
+ {
+ "cls": "buffer",
+ "min_batch_size": {
+ "content": 10,
+ },
+ },
+ {
+ "cls": "memory",
+ },
],
}
storage = get_storage(**config)
assert isinstance(storage, FilteringProxyStorage)
assert isinstance(storage.storage, BufferingProxyStorage)
assert isinstance(storage.storage.storage, InMemoryStorage)
def test_get_storage_pipeline_legacy_args():
config = {
"cls": "pipeline",
"steps": [
- {"cls": "filter",},
- {"cls": "buffer", "args": {"min_batch_size": {"content": 10,},}},
- {"cls": "memory",},
+ {
+ "cls": "filter",
+ },
+ {
+ "cls": "buffer",
+ "args": {
+ "min_batch_size": {
+ "content": 10,
+ },
+ },
+ },
+ {
+ "cls": "memory",
+ },
],
}
with pytest.warns(DeprecationWarning):
storage = get_storage(**config)
assert isinstance(storage, FilteringProxyStorage)
assert isinstance(storage.storage, BufferingProxyStorage)
assert isinstance(storage.storage.storage, InMemoryStorage)
# get_storage's check_config argument tests
# the "remote" and "pipeline" cases are tested in dedicated test functions below
@pytest.mark.parametrize(
"cls,real_class,kwargs",
[x for x in STORAGES if x.id not in ("remote", "local", "postgresql")],
)
def test_get_storage_check_config(cls, real_class, kwargs, monkeypatch):
- """Instantiating an existing storage with check_config should be ok
-
- """
+ """Instantiating an existing storage with check_config should be ok"""
check_backend_check_config(monkeypatch, dict(cls=cls, **kwargs))
@patch("swh.storage.postgresql.storage.psycopg2.pool")
@pytest.mark.parametrize("clazz", ["local", "postgresql"])
def test_get_storage_local_check_config(mock_pool, monkeypatch, clazz):
- """Instantiating a local storage with check_config should be ok
-
- """
+ """Instantiating a local storage with check_config should be ok"""
mock_pool.ThreadedConnectionPool.return_value = None
check_backend_check_config(
monkeypatch,
{"cls": clazz, "db": "postgresql://db", "objstorage": {"cls": "memory"}},
backend_storage_cls=DbStorage,
)
def test_get_storage_pipeline_check_config(monkeypatch):
"""Test that the check_config option works as intended for a pipelined storage"""
config = {
"cls": "pipeline",
"steps": [
- {"cls": "filter",},
- {"cls": "buffer", "min_batch_size": {"content": 10,},},
- {"cls": "memory",},
+ {
+ "cls": "filter",
+ },
+ {
+ "cls": "buffer",
+ "min_batch_size": {
+ "content": 10,
+ },
+ },
+ {
+ "cls": "memory",
+ },
],
}
check_backend_check_config(
- monkeypatch, config,
+ monkeypatch,
+ config,
)
def test_get_storage_remote_check_config(monkeypatch):
"""Test that the check_config option works as intended for a remote storage"""
monkeypatch.setattr(
server, "storage", get_storage(cls="memory", journal_writer={"cls": "memory"})
)
test_client = server.app.test_client()
class MockedRemoteStorage(client.RemoteStorage):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.session.adapters.clear()
self.session.mount("mock://", RPCTestAdapter(test_client))
monkeypatch.setattr(client, "RemoteStorage", MockedRemoteStorage)
config = {
"cls": "remote",
"url": "mock://example.com",
}
check_backend_check_config(
- monkeypatch, config,
+ monkeypatch,
+ config,
)
def check_backend_check_config(
monkeypatch, config, backend_storage_cls=InMemoryStorage
):
"""Check the staged/indirect storage (pipeline or remote) works
as desired with regard to the check_config option of the get_storage()
factory function.
If set, the check_config argument is used to call the Storage.check_config() at
instantiation time in the get_storage() factory function. This is supposed to be
passed through each step of the Storage pipeline until it reached the actual
backend's (typically in memory or local) check_config() method which will perform
the verification for read/write access to the backend storage.
monkeypatch is supposed to be the monkeypatch pytest fixture to be used from the
calling test_ function.
config is the config dict passed to get_storage()
backend_storage_cls is the class of the backend storage to be mocked to
simulate the check_config behavior; it should then be the class of the
actual backend storage defined in the `config`.
"""
access = None
def mockcheck(self, check_write=False):
if access == "none":
return False
if access == "read":
return check_write is False
if access == "write":
return True
monkeypatch.setattr(backend_storage_cls, "check_config", mockcheck)
# simulate no read nor write access to the underlying (memory) storage
access = "none"
# by default, no check, so no complain
assert get_storage(**config)
# if asked to check, complain
with pytest.raises(EnvironmentError):
get_storage(check_config={"check_write": False}, **config)
with pytest.raises(EnvironmentError):
get_storage(check_config={"check_write": True}, **config)
# simulate no write access to the underlying (memory) storage
access = "read"
# by default, no check so no complain
assert get_storage(**config)
# if asked to check for read access, no complain
get_storage(check_config={"check_write": False}, **config)
# if asked to check for write access, complain
with pytest.raises(EnvironmentError):
get_storage(check_config={"check_write": True}, **config)
# simulate read & write access to the underlying (memory) storage
access = "write"
# by default, no check so no complain
assert get_storage(**config)
# if asked to check for read access, no complain
get_storage(check_config={"check_write": False}, **config)
# if asked to check for write access, no complain
get_storage(check_config={"check_write": True}, **config)
diff --git a/swh/storage/tests/test_kafka_writer.py b/swh/storage/tests/test_kafka_writer.py
index 71766eb3..4de94837 100644
--- a/swh/storage/tests/test_kafka_writer.py
+++ b/swh/storage/tests/test_kafka_writer.py
@@ -1,163 +1,171 @@
# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from typing import Any, Dict
from attr import asdict, has
from confluent_kafka import Consumer
from hypothesis import given
from hypothesis.strategies import lists
from swh.journal.pytest_plugin import assert_all_objects_consumed, consume_messages
from swh.model.hypothesis_strategies import objects
from swh.model.model import Origin, OriginVisit, Person
from swh.model.tests.swh_model_data import TEST_OBJECTS
from swh.storage import get_storage
def test_storage_direct_writer(kafka_prefix: str, kafka_server, consumer: Consumer):
writer_config = {
"cls": "kafka",
"brokers": [kafka_server],
"client_id": "kafka_writer",
"prefix": kafka_prefix,
"anonymize": False,
}
storage_config: Dict[str, Any] = {
"cls": "pipeline",
- "steps": [{"cls": "memory", "journal_writer": writer_config},],
+ "steps": [
+ {"cls": "memory", "journal_writer": writer_config},
+ ],
}
storage = get_storage(**storage_config)
expected_messages = 0
for obj_type, objs in TEST_OBJECTS.items():
method = getattr(storage, obj_type + "_add")
if obj_type in (
"content",
"skipped_content",
"directory",
"extid",
"metadata_authority",
"metadata_fetcher",
"revision",
"release",
"snapshot",
"origin",
"origin_visit_status",
"raw_extrinsic_metadata",
):
method(objs)
expected_messages += len(objs)
elif obj_type in ("origin_visit",):
for obj in objs:
assert isinstance(obj, OriginVisit)
storage.origin_add([Origin(url=obj.origin)])
method([obj])
expected_messages += 1 + 1 # 1 visit + 1 visit status
else:
assert False, obj_type
existing_topics = set(
topic
for topic in consumer.list_topics(timeout=10).topics.keys()
if topic.startswith(f"{kafka_prefix}.") # final . to exclude privileged topics
)
assert existing_topics == {
f"{kafka_prefix}.{obj_type}"
for obj_type in (
"content",
"directory",
"extid",
"metadata_authority",
"metadata_fetcher",
"origin",
"origin_visit",
"origin_visit_status",
"raw_extrinsic_metadata",
"release",
"revision",
"snapshot",
"skipped_content",
)
}
consumed_messages = consume_messages(consumer, kafka_prefix, expected_messages)
assert_all_objects_consumed(consumed_messages)
def test_storage_direct_writer_anonymized(
kafka_prefix: str, kafka_server, consumer: Consumer
):
writer_config = {
"cls": "kafka",
"brokers": [kafka_server],
"client_id": "kafka_writer",
"prefix": kafka_prefix,
"anonymize": True,
}
storage_config: Dict[str, Any] = {
"cls": "pipeline",
- "steps": [{"cls": "memory", "journal_writer": writer_config},],
+ "steps": [
+ {"cls": "memory", "journal_writer": writer_config},
+ ],
}
storage = get_storage(**storage_config)
expected_messages = 0
for obj_type, objs in TEST_OBJECTS.items():
if obj_type == "origin_visit":
# these have non-consistent API and are unrelated with what we
# want to test here
continue
method = getattr(storage, obj_type + "_add")
method(objs)
expected_messages += len(objs)
existing_topics = set(
topic
for topic in consumer.list_topics(timeout=10).topics.keys()
if topic.startswith(kafka_prefix)
)
assert existing_topics == {
f"{kafka_prefix}.{obj_type}"
for obj_type in (
"content",
"directory",
"extid",
"metadata_authority",
"metadata_fetcher",
"origin",
"origin_visit",
"origin_visit_status",
"raw_extrinsic_metadata",
"release",
"revision",
"snapshot",
"skipped_content",
)
} | {
- f"{kafka_prefix}_privileged.{obj_type}" for obj_type in ("release", "revision",)
+ f"{kafka_prefix}_privileged.{obj_type}"
+ for obj_type in (
+ "release",
+ "revision",
+ )
}
def check_anonymized_obj(obj):
if has(obj):
if isinstance(obj, Person):
assert obj.name is None
assert obj.email is None
assert len(obj.fullname) == 32
else:
for key, value in asdict(obj, recurse=False).items():
check_anonymized_obj(value)
@given(lists(objects(split_content=True)))
def test_anonymizer(obj_type_and_objs):
for obj_type, obj in obj_type_and_objs:
check_anonymized_obj(obj.anonymize())
diff --git a/swh/storage/tests/test_metrics.py b/swh/storage/tests/test_metrics.py
index bf3358ae..08609a63 100644
--- a/swh/storage/tests/test_metrics.py
+++ b/swh/storage/tests/test_metrics.py
@@ -1,48 +1,56 @@
# Copyright (C) 2019 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from unittest.mock import patch
from swh.storage.metrics import OPERATIONS_METRIC, OPERATIONS_UNIT_METRIC, send_metric
def test_send_metric_unknown_unit():
r = send_metric("content", count=10, method_name="content_add")
assert r is False
r = send_metric("sthg:add:bytes:extra", count=10, method_name="sthg_add")
assert r is False
def test_send_metric_no_value():
r = send_metric("content:add", count=0, method_name="content_add")
assert r is False
@patch("swh.storage.metrics.statsd.increment")
def test_send_metric_no_unit(mock_statsd):
r = send_metric("content:add", count=10, method_name="content_add")
mock_statsd.assert_called_with(
OPERATIONS_METRIC,
10,
- tags={"endpoint": "content_add", "object_type": "content", "operation": "add",},
+ tags={
+ "endpoint": "content_add",
+ "object_type": "content",
+ "operation": "add",
+ },
)
assert r
@patch("swh.storage.metrics.statsd.increment")
def test_send_metric_unit(mock_statsd):
unit_ = "bytes"
r = send_metric("c:add:%s" % unit_, count=100, method_name="c_add")
expected_metric = OPERATIONS_UNIT_METRIC.format(unit=unit_)
mock_statsd.assert_called_with(
expected_metric,
100,
- tags={"endpoint": "c_add", "object_type": "c", "operation": "add",},
+ tags={
+ "endpoint": "c_add",
+ "object_type": "c",
+ "operation": "add",
+ },
)
assert r
diff --git a/swh/storage/tests/test_postgresql.py b/swh/storage/tests/test_postgresql.py
index 4509ff9e..28ec5fb5 100644
--- a/swh/storage/tests/test_postgresql.py
+++ b/swh/storage/tests/test_postgresql.py
@@ -1,412 +1,410 @@
# Copyright (C) 2015-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from contextlib import contextmanager
import queue
import threading
from unittest.mock import Mock
import attr
import pytest
from swh.model.model import Person
from swh.storage.postgresql.db import Db
from swh.storage.tests.storage_tests import TestStorage as _TestStorage
from swh.storage.tests.storage_tests import TestStorageGeneratedData # noqa
from swh.storage.utils import now
@contextmanager
def db_transaction(storage):
with storage.db() as db:
with db.transaction() as cur:
yield db, cur
class TestStorage(_TestStorage):
@pytest.mark.skip(
"Directory pagination is not implemented in the postgresql backend yet."
)
def test_directory_get_entries_pagination(self):
pass
@pytest.mark.db
class TestLocalStorage:
"""Test the local storage"""
# This test is only relevant on the local storage, with an actual
# objstorage raising an exception
def test_content_add_objstorage_exception(self, swh_storage, sample_data):
content = sample_data.content
swh_storage.objstorage.content_add = Mock(
side_effect=Exception("mocked broken objstorage")
)
with pytest.raises(Exception, match="mocked broken"):
swh_storage.content_add([content])
missing = list(swh_storage.content_missing([content.hashes()]))
assert missing == [content.sha1]
@pytest.mark.db
class TestStorageRaceConditions:
@pytest.mark.xfail
def test_content_add_race(self, swh_storage, sample_data):
content = attr.evolve(sample_data.content, ctime=now())
results = queue.Queue()
def thread():
try:
with db_transaction(swh_storage) as (db, cur):
ret = swh_storage._content_add_metadata(db, cur, [content])
results.put((threading.get_ident(), "data", ret))
except Exception as e:
results.put((threading.get_ident(), "exc", e))
t1 = threading.Thread(target=thread)
t2 = threading.Thread(target=thread)
t1.start()
# this avoids the race condition
# import time
# time.sleep(1)
t2.start()
t1.join()
t2.join()
r1 = results.get(block=False)
r2 = results.get(block=False)
with pytest.raises(queue.Empty):
results.get(block=False)
assert r1[0] != r2[0]
assert r1[1] == "data", "Got exception %r in Thread%s" % (r1[2], r1[0])
assert r2[1] == "data", "Got exception %r in Thread%s" % (r2[2], r2[0])
@pytest.mark.db
class TestPgStorage:
"""This class is dedicated for the rare case where the schema needs to
- be altered dynamically.
+ be altered dynamically.
- Otherwise, the tests could be blocking when ran altogether.
+ Otherwise, the tests could be blocking when ran altogether.
"""
def test_content_update_with_new_cols(self, swh_storage, sample_data):
content, content2 = sample_data.contents[:2]
swh_storage.journal_writer.journal = None # TODO, not supported
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"""alter table content
add column test text default null,
add column test2 text default null"""
)
swh_storage.content_add([content])
cont = content.to_dict()
cont["test"] = "value-1"
cont["test2"] = "value-2"
swh_storage.content_update([cont], keys=["test", "test2"])
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"""SELECT sha1, sha1_git, sha256, length, status,
test, test2
FROM content WHERE sha1 = %s""",
(cont["sha1"],),
)
datum = cur.fetchone()
assert datum == (
cont["sha1"],
cont["sha1_git"],
cont["sha256"],
cont["length"],
"visible",
cont["test"],
cont["test2"],
)
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"""alter table content drop column test,
drop column test2"""
)
def test_content_add_db(self, swh_storage, sample_data):
content = sample_data.content
actual_result = swh_storage.content_add([content])
assert actual_result == {
"content:add": 1,
"content:add:bytes": content.length,
}
if hasattr(swh_storage, "objstorage"):
assert content.sha1 in swh_storage.objstorage.objstorage
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"SELECT sha1, sha1_git, sha256, length, status"
" FROM content WHERE sha1 = %s",
(content.sha1,),
)
datum = cur.fetchone()
assert datum == (
content.sha1,
content.sha1_git,
content.sha256,
content.length,
"visible",
)
contents = [
obj
for (obj_type, obj) in swh_storage.journal_writer.journal.objects
if obj_type == "content"
]
assert len(contents) == 1
assert contents[0] == attr.evolve(content, data=None)
def test_content_add_metadata_db(self, swh_storage, sample_data):
content = attr.evolve(sample_data.content, data=None, ctime=now())
actual_result = swh_storage.content_add_metadata([content])
assert actual_result == {
"content:add": 1,
}
if hasattr(swh_storage, "objstorage"):
assert content.sha1 not in swh_storage.objstorage.objstorage
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"SELECT sha1, sha1_git, sha256, length, status"
" FROM content WHERE sha1 = %s",
(content.sha1,),
)
datum = cur.fetchone()
assert datum == (
content.sha1,
content.sha1_git,
content.sha256,
content.length,
"visible",
)
contents = [
obj
for (obj_type, obj) in swh_storage.journal_writer.journal.objects
if obj_type == "content"
]
assert len(contents) == 1
assert contents[0] == content
def test_skipped_content_add_db(self, swh_storage, sample_data):
content, cont2 = sample_data.skipped_contents[:2]
content2 = attr.evolve(cont2, blake2s256=None)
actual_result = swh_storage.skipped_content_add([content, content, content2])
assert 2 <= actual_result.pop("skipped_content:add") <= 3
assert actual_result == {}
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"SELECT sha1, sha1_git, sha256, blake2s256, "
"length, status, reason "
"FROM skipped_content ORDER BY sha1_git"
)
dbdata = cur.fetchall()
assert len(dbdata) == 2
assert dbdata[0] == (
content.sha1,
content.sha1_git,
content.sha256,
content.blake2s256,
content.length,
"absent",
"Content too long",
)
assert dbdata[1] == (
content2.sha1,
content2.sha1_git,
content2.sha256,
content2.blake2s256,
content2.length,
"absent",
"Content too long",
)
def test_revision_get_displayname_behavior(self, swh_storage, sample_data):
"""Check revision_get behavior when displayname is set"""
revision, revision2 = sample_data.revisions[:2]
# Make authors and committers known
revision = attr.evolve(
revision,
author=Person.from_fullname(b"author1 "),
committer=Person.from_fullname(b"committer1 "),
)
revision = attr.evolve(revision, id=revision.compute_hash())
revision2 = attr.evolve(
revision2,
author=Person.from_fullname(b"author2 "),
committer=Person.from_fullname(b"committer2 "),
)
revision2 = attr.evolve(revision2, id=revision2.compute_hash())
add_result = swh_storage.revision_add([revision, revision2])
assert add_result == {"revision:add": 2}
# Before displayname change
revisions = swh_storage.revision_get([revision.id, revision2.id])
assert revisions == [revision, revision2]
displayname = b"Display Name "
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"UPDATE person set displayname = %s where fullname = %s",
(displayname, revision.author.fullname),
)
revisions = swh_storage.revision_get([revision.id, revision2.id])
assert revisions == [
attr.evolve(revision, author=Person.from_fullname(displayname)),
revision2,
]
revisions = swh_storage.revision_get(
[revision.id, revision2.id], ignore_displayname=True
)
assert revisions == [revision, revision2]
def test_revision_log_displayname_behavior(self, swh_storage, sample_data):
"""Check revision_log behavior when displayname is set"""
revision, revision2 = sample_data.revisions[:2]
# Make authors, committers and parenthood relationship known
# (revision2 -[parent]-> revision1)
revision = attr.evolve(
revision,
author=Person.from_fullname(b"author1 "),
committer=Person.from_fullname(b"committer1 "),
)
revision = attr.evolve(revision, id=revision.compute_hash())
revision2 = attr.evolve(
revision2,
parents=(revision.id,),
author=Person.from_fullname(b"author2 "),
committer=Person.from_fullname(b"committer2 "),
)
revision2 = attr.evolve(revision2, id=revision2.compute_hash())
add_result = swh_storage.revision_add([revision, revision2])
assert add_result == {"revision:add": 2}
# Before displayname change
revisions = swh_storage.revision_log([revision2.id])
assert list(revisions) == [revision2.to_dict(), revision.to_dict()]
displayname = b"Display Name "
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"UPDATE person set displayname = %s where fullname = %s",
(displayname, revision.author.fullname),
)
revisions = swh_storage.revision_log([revision2.id])
assert list(revisions) == [
revision2.to_dict(),
attr.evolve(revision, author=Person.from_fullname(displayname)).to_dict(),
]
revisions = swh_storage.revision_log([revision2.id], ignore_displayname=True)
assert list(revisions) == [revision2.to_dict(), revision.to_dict()]
def test_release_get_displayname_behavior(self, swh_storage, sample_data):
"""Check release_get behavior when displayname is set"""
release, release2 = sample_data.releases[:2]
# Make authors known
release = attr.evolve(
- release, author=Person.from_fullname(b"author1 "),
+ release,
+ author=Person.from_fullname(b"author1 "),
)
release = attr.evolve(release, id=release.compute_hash())
release2 = attr.evolve(
- release2, author=Person.from_fullname(b"author2 "),
+ release2,
+ author=Person.from_fullname(b"author2 "),
)
release2 = attr.evolve(release2, id=release2.compute_hash())
add_result = swh_storage.release_add([release, release2])
assert add_result == {"release:add": 2}
# Before displayname change
releases = swh_storage.release_get([release.id, release2.id])
assert releases == [release, release2]
displayname = b"Display Name "
with db_transaction(swh_storage) as (_, cur):
cur.execute(
"UPDATE person set displayname = %s where fullname = %s",
(displayname, release.author.fullname),
)
releases = swh_storage.release_get([release.id, release2.id])
assert releases == [
attr.evolve(release, author=Person.from_fullname(displayname)),
release2,
]
releases = swh_storage.release_get(
[release.id, release2.id], ignore_displayname=True
)
assert releases == [release, release2]
def test_clear_buffers(self, swh_storage):
- """Calling clear buffers on real storage does nothing
-
- """
+ """Calling clear buffers on real storage does nothing"""
assert swh_storage.clear_buffers() is None
def test_flush(self, swh_storage):
- """Calling clear buffers on real storage does nothing
-
- """
+ """Calling clear buffers on real storage does nothing"""
assert swh_storage.flush() == {}
def test_dbversion(self, swh_storage):
with swh_storage.db() as db:
assert db.check_dbversion()
def test_dbversion_mismatch(self, swh_storage, monkeypatch):
monkeypatch.setattr(Db, "current_version", -1)
with swh_storage.db() as db:
assert db.check_dbversion() is False
def test_check_config(self, swh_storage):
assert swh_storage.check_config(check_write=True)
assert swh_storage.check_config(check_write=False)
def test_check_config_dbversion(self, swh_storage, monkeypatch):
monkeypatch.setattr(Db, "current_version", -1)
assert swh_storage.check_config(check_write=True) is False
assert swh_storage.check_config(check_write=False) is False
diff --git a/swh/storage/tests/test_postgresql_converters.py b/swh/storage/tests/test_postgresql_converters.py
index 94902a60..c075a67b 100644
--- a/swh/storage/tests/test_postgresql_converters.py
+++ b/swh/storage/tests/test_postgresql_converters.py
@@ -1,312 +1,355 @@
# Copyright (C) 2015-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import datetime
import pytest
from swh.model.model import (
ObjectType,
Person,
Release,
Revision,
RevisionType,
Timestamp,
TimestampWithTimezone,
)
from swh.model.swhids import ExtendedSWHID
from swh.storage.postgresql import converters
@pytest.mark.parametrize(
"model_date,db_date",
[
(
None,
{
"timestamp": None,
"offset": 0,
"neg_utc_offset": None,
"offset_bytes": None,
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567890, microseconds=0,),
+ timestamp=Timestamp(
+ seconds=1234567890,
+ microseconds=0,
+ ),
offset_bytes=b"+0200",
),
{
"timestamp": "2009-02-13T23:31:30+00:00",
"offset": 120,
"neg_utc_offset": False,
"offset_bytes": b"+0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=1123456789, microseconds=0,),
+ timestamp=Timestamp(
+ seconds=1123456789,
+ microseconds=0,
+ ),
offset_bytes=b"-0000",
),
{
"timestamp": "2005-08-07T23:19:49+00:00",
"offset": 0,
"neg_utc_offset": True,
"offset_bytes": b"-0000",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567890, microseconds=0,),
+ timestamp=Timestamp(
+ seconds=1234567890,
+ microseconds=0,
+ ),
offset_bytes=b"+0042",
),
{
"timestamp": "2009-02-13T23:31:30+00:00",
"offset": 42,
"neg_utc_offset": False,
"offset_bytes": b"+0042",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=1634366813, microseconds=0,),
+ timestamp=Timestamp(
+ seconds=1634366813,
+ microseconds=0,
+ ),
offset_bytes=b"-0200",
),
{
"timestamp": "2021-10-16T06:46:53+00:00",
"offset": -120,
"neg_utc_offset": False,
"offset_bytes": b"-0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=0, microseconds=0,), offset_bytes=b"-0200",
+ timestamp=Timestamp(
+ seconds=0,
+ microseconds=0,
+ ),
+ offset_bytes=b"-0200",
),
{
"timestamp": "1970-01-01T00:00:00+00:00",
"offset": -120,
"neg_utc_offset": False,
"offset_bytes": b"-0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=0, microseconds=1,), offset_bytes=b"-0200",
+ timestamp=Timestamp(
+ seconds=0,
+ microseconds=1,
+ ),
+ offset_bytes=b"-0200",
),
{
"timestamp": "1970-01-01T00:00:00.000001+00:00",
"offset": -120,
"neg_utc_offset": False,
"offset_bytes": b"-0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=-1, microseconds=0,), offset_bytes=b"-0200",
+ timestamp=Timestamp(
+ seconds=-1,
+ microseconds=0,
+ ),
+ offset_bytes=b"-0200",
),
{
"timestamp": "1969-12-31T23:59:59+00:00",
"offset": -120,
"neg_utc_offset": False,
"offset_bytes": b"-0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=-1, microseconds=1,), offset_bytes=b"-0200",
+ timestamp=Timestamp(
+ seconds=-1,
+ microseconds=1,
+ ),
+ offset_bytes=b"-0200",
),
{
"timestamp": "1969-12-31T23:59:59.000001+00:00",
"offset": -120,
"neg_utc_offset": False,
"offset_bytes": b"-0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=-3600, microseconds=0,),
+ timestamp=Timestamp(
+ seconds=-3600,
+ microseconds=0,
+ ),
offset_bytes=b"-0200",
),
{
"timestamp": "1969-12-31T23:00:00+00:00",
"offset": -120,
"neg_utc_offset": False,
"offset_bytes": b"-0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=-3600, microseconds=1,),
+ timestamp=Timestamp(
+ seconds=-3600,
+ microseconds=1,
+ ),
offset_bytes=b"-0200",
),
{
"timestamp": "1969-12-31T23:00:00.000001+00:00",
"offset": -120,
"neg_utc_offset": False,
"offset_bytes": b"-0200",
},
),
(
TimestampWithTimezone(
- timestamp=Timestamp(seconds=1234567890, microseconds=0,),
+ timestamp=Timestamp(
+ seconds=1234567890,
+ microseconds=0,
+ ),
offset_bytes=b"+200",
),
{
"timestamp": "2009-02-13T23:31:30+00:00",
"offset": 120,
"neg_utc_offset": False,
"offset_bytes": b"+200",
},
),
],
)
def test_date(model_date, db_date):
assert converters.date_to_db(model_date) == db_date
assert (
converters.db_to_date(
date=None
if db_date["timestamp"] is None
else datetime.datetime.fromisoformat(db_date["timestamp"]),
offset_bytes=db_date["offset_bytes"],
)
== model_date
)
def test_db_to_author():
# when
actual_author = converters.db_to_author(b"name ", b"name", b"email")
# then
assert actual_author == Person.from_fullname(b"name ")
def test_db_to_author_none():
# when
actual_author = converters.db_to_author(None, None, None)
# then
assert actual_author is None
def test_db_to_author_unparsed():
author = converters.db_to_author(b"Fullname ", None, None)
assert author == Person.from_fullname(b"Fullname ")
def test_db_to_revision():
# when
actual_revision = converters.db_to_revision(
{
"id": b"revision-id",
"date": None,
"date_offset": None,
"date_neg_utc_offset": None,
"date_offset_bytes": None,
"committer_date": None,
"committer_date_offset": None,
"committer_date_neg_utc_offset": None,
"committer_date_offset_bytes": None,
"type": "git",
"directory": b"dir-sha1",
"message": b"commit message",
"author_fullname": b"auth-name ",
"author_name": b"auth-name",
"author_email": b"auth-email",
"committer_fullname": b"comm-name ",
"committer_name": b"comm-name",
"committer_email": b"comm-email",
"metadata": {},
"synthetic": False,
"extra_headers": (),
"raw_manifest": None,
"parents": [b"123", b"456"],
}
)
# then
assert actual_revision == Revision(
id=b"revision-id",
author=Person(
- fullname=b"auth-name ", name=b"auth-name", email=b"auth-email",
+ fullname=b"auth-name ",
+ name=b"auth-name",
+ email=b"auth-email",
),
date=None,
committer=Person(
- fullname=b"comm-name ", name=b"comm-name", email=b"comm-email",
+ fullname=b"comm-name ",
+ name=b"comm-name",
+ email=b"comm-email",
),
committer_date=None,
type=RevisionType.GIT,
directory=b"dir-sha1",
message=b"commit message",
metadata={},
synthetic=False,
extra_headers=(),
parents=(b"123", b"456"),
)
def test_db_to_release():
# when
actual_release = converters.db_to_release(
{
"id": b"release-id",
"target": b"revision-id",
"target_type": "revision",
"date": None,
"date_offset": None,
"date_neg_utc_offset": None,
"date_offset_bytes": None,
"name": b"release-name",
"comment": b"release comment",
"synthetic": True,
"author_fullname": b"auth-name ",
"author_name": b"auth-name",
"author_email": b"auth-email",
"raw_manifest": None,
}
)
# then
assert actual_release == Release(
author=Person(
- fullname=b"auth-name ", name=b"auth-name", email=b"auth-email",
+ fullname=b"auth-name ",
+ name=b"auth-name",
+ email=b"auth-email",
),
date=None,
id=b"release-id",
name=b"release-name",
message=b"release comment",
synthetic=True,
target=b"revision-id",
target_type=ObjectType.REVISION,
)
def test_db_to_raw_extrinsic_metadata_raw_target():
row = {
"raw_extrinsic_metadata.target": "https://example.com/origin",
"metadata_authority.type": "forge",
"metadata_authority.url": "https://example.com",
"metadata_fetcher.name": "swh.lister",
"metadata_fetcher.version": "1.0.0",
"discovery_date": datetime.datetime(
2021, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc
),
"format": "text/plain",
"raw_extrinsic_metadata.metadata": b"metadata",
"origin": None,
"visit": None,
"snapshot": None,
"release": None,
"revision": None,
"path": None,
"directory": None,
}
with pytest.deprecated_call():
computed_rem = converters.db_to_raw_extrinsic_metadata(row)
assert computed_rem.target == ExtendedSWHID.from_string(
"swh:1:ori:5a7439b0b93a5d230b6a67b8e7e0f7dc3c9f6c70"
)
diff --git a/swh/storage/tests/test_replay.py b/swh/storage/tests/test_replay.py
index 8c13fa95..d90ea9e9 100644
--- a/swh/storage/tests/test_replay.py
+++ b/swh/storage/tests/test_replay.py
@@ -1,544 +1,549 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import dataclasses
import datetime
import functools
import logging
import re
from typing import Any, Container, Dict, Optional, cast
import attr
import pytest
from swh.journal.client import JournalClient
from swh.journal.serializers import kafka_to_value, key_to_kafka, value_to_kafka
from swh.model.hashutil import DEFAULT_ALGORITHMS, MultiHash, hash_to_bytes, hash_to_hex
from swh.model.model import Revision, RevisionType
from swh.model.tests.swh_model_data import (
COMMITTERS,
DATES,
DUPLICATE_CONTENTS,
REVISIONS,
)
from swh.model.tests.swh_model_data import TEST_OBJECTS as _TEST_OBJECTS
from swh.storage import get_storage
from swh.storage.cassandra.model import ContentRow, SkippedContentRow
from swh.storage.exc import StorageArgumentException
from swh.storage.in_memory import InMemoryStorage
from swh.storage.replay import ModelObjectDeserializer, process_replay_objects
UTC = datetime.timezone.utc
TEST_OBJECTS = _TEST_OBJECTS.copy()
# add a revision with metadata to check this later is dropped while being replayed
TEST_OBJECTS["revision"] = list(_TEST_OBJECTS["revision"]) + [
Revision(
id=hash_to_bytes("51d9d94ab08d3f75512e3a9fd15132e0a7ca7928"),
message=b"hello again",
date=DATES[1],
committer=COMMITTERS[1],
author=COMMITTERS[0],
committer_date=DATES[0],
type=RevisionType.GIT,
directory=b"\x03" * 20,
synthetic=False,
metadata={"something": "interesting"},
parents=(REVISIONS[0].id,),
),
]
WRONG_ID_REG = re.compile(
"Object has id [0-9a-f]{40}, but it should be [0-9a-f]{40}: .*"
)
def nullify_ctime(obj):
if isinstance(obj, (ContentRow, SkippedContentRow)):
return dataclasses.replace(obj, ctime=None)
else:
return obj
@pytest.fixture()
def replayer_storage_and_client(
kafka_prefix: str, kafka_consumer_group: str, kafka_server: str
):
journal_writer_config = {
"cls": "kafka",
"brokers": [kafka_server],
"client_id": "kafka_writer",
"prefix": kafka_prefix,
}
storage_config: Dict[str, Any] = {
"cls": "memory",
"journal_writer": journal_writer_config,
}
storage = get_storage(**storage_config)
deserializer = ModelObjectDeserializer()
replayer = JournalClient(
brokers=kafka_server,
group_id=kafka_consumer_group,
prefix=kafka_prefix,
stop_on_eof=True,
value_deserializer=deserializer.convert,
)
yield storage, replayer
def test_storage_replayer(replayer_storage_and_client, caplog):
"""Optimal replayer scenario.
This:
- writes objects to a source storage
- replayer consumes objects from the topic and replays them
- a destination storage is filled from this
In the end, both storages should have the same content.
"""
src, replayer = replayer_storage_and_client
# Fill Kafka using a source storage
nb_sent = 0
for object_type, objects in TEST_OBJECTS.items():
method = getattr(src, object_type + "_add")
method(objects)
if object_type == "origin_visit":
nb_sent += len(objects) # origin-visit-add adds origin-visit-status as well
nb_sent += len(objects)
caplog.set_level(logging.ERROR, "swh.journal.replay")
# Fill the destination storage from Kafka
dst = get_storage(cls="memory")
worker_fn = functools.partial(process_replay_objects, storage=dst)
nb_inserted = replayer.process(worker_fn)
assert nb_sent == nb_inserted
assert isinstance(src, InMemoryStorage) # needed to help mypy
assert isinstance(dst, InMemoryStorage)
check_replayed(src, dst)
collision = 0
for record in caplog.records:
logtext = record.getMessage()
if "Colliding contents:" in logtext:
collision += 1
assert collision == 0, "No collision should be detected"
def test_storage_replay_with_collision(replayer_storage_and_client, caplog):
"""Another replayer scenario with collisions.
This:
- writes objects to the topic, including colliding contents
- replayer consumes objects from the topic and replay them
- This drops the colliding contents from the replay when detected
"""
src, replayer = replayer_storage_and_client
# Fill Kafka using a source storage
nb_sent = 0
for object_type, objects in TEST_OBJECTS.items():
method = getattr(src, object_type + "_add")
method(objects)
if object_type == "origin_visit":
nb_sent += len(objects) # origin-visit-add adds origin-visit-status as well
nb_sent += len(objects)
# Create collision in input data
# These should not be written in the destination
producer = src.journal_writer.journal.producer
prefix = src.journal_writer.journal._prefix
for content in DUPLICATE_CONTENTS:
topic = f"{prefix}.content"
key = content.sha1
now = datetime.datetime.now(tz=UTC)
content = attr.evolve(content, ctime=now)
producer.produce(
- topic=topic, key=key_to_kafka(key), value=value_to_kafka(content.to_dict()),
+ topic=topic,
+ key=key_to_kafka(key),
+ value=value_to_kafka(content.to_dict()),
)
nb_sent += 1
producer.flush()
caplog.set_level(logging.ERROR, "swh.journal.replay")
# Fill the destination storage from Kafka
dst = get_storage(cls="memory")
worker_fn = functools.partial(process_replay_objects, storage=dst)
nb_inserted = replayer.process(worker_fn)
assert nb_sent == nb_inserted
# check the logs for the collision being properly detected
nb_collisions = 0
actual_collision: Dict
for record in caplog.records:
logtext = record.getMessage()
if "Collision detected:" in logtext:
nb_collisions += 1
actual_collision = record.args["collision"]
assert nb_collisions == 1, "1 collision should be detected"
algo = "sha1"
assert actual_collision["algo"] == algo
expected_colliding_hash = hash_to_hex(DUPLICATE_CONTENTS[0].get_hash(algo))
assert actual_collision["hash"] == expected_colliding_hash
actual_colliding_hashes = actual_collision["objects"]
assert len(actual_colliding_hashes) == len(DUPLICATE_CONTENTS)
for content in DUPLICATE_CONTENTS:
expected_content_hashes = {
k: hash_to_hex(v) for k, v in content.hashes().items()
}
assert expected_content_hashes in actual_colliding_hashes
# all objects from the src should exists in the dst storage
assert isinstance(src, InMemoryStorage) # needed to help mypy
assert isinstance(dst, InMemoryStorage) # needed to help mypy
check_replayed(src, dst, exclude=["contents"])
# but the dst has one content more (one of the 2 colliding ones)
assert (
len(list(src._cql_runner._contents.iter_all()))
== len(list(dst._cql_runner._contents.iter_all())) - 1
)
def test_replay_skipped_content(replayer_storage_and_client):
"""Test the 'skipped_content' topic is properly replayed."""
src, replayer = replayer_storage_and_client
_check_replay_skipped_content(src, replayer, "skipped_content")
# utility functions
def check_replayed(
src: InMemoryStorage,
dst: InMemoryStorage,
exclude: Optional[Container] = None,
expected_anonymized=False,
):
"""Simple utility function to compare the content of 2 in_memory storages"""
def fix_expected(attr, row):
if expected_anonymized:
if attr == "releases":
row = dataclasses.replace(
row, author=row.author and row.author.anonymize()
)
elif attr == "revisions":
row = dataclasses.replace(
row,
author=row.author.anonymize(),
committer=row.committer.anonymize(),
)
if attr == "revisions":
# the replayer should now drop the metadata attribute; see
# swh/storgae/replay.py:_insert_objects()
row.metadata = "null"
return row
for attr_ in (
"contents",
"skipped_contents",
"directories",
"extid",
"revisions",
"releases",
"snapshots",
"origins",
"origin_visits",
"origin_visit_statuses",
"raw_extrinsic_metadata",
):
if exclude and attr_ in exclude:
continue
expected_objects = [
(id, nullify_ctime(fix_expected(attr_, obj)))
for id, obj in sorted(getattr(src._cql_runner, f"_{attr_}").iter_all())
]
got_objects = [
(id, nullify_ctime(obj))
for id, obj in sorted(getattr(dst._cql_runner, f"_{attr_}").iter_all())
]
assert got_objects == expected_objects, f"Mismatch object list for {attr_}"
def _check_replay_skipped_content(storage, replayer, topic):
skipped_contents = _gen_skipped_contents(100)
nb_sent = len(skipped_contents)
producer = storage.journal_writer.journal.producer
prefix = storage.journal_writer.journal._prefix
for i, obj in enumerate(skipped_contents):
producer.produce(
topic=f"{prefix}.{topic}",
key=key_to_kafka({"sha1": obj["sha1"]}),
value=value_to_kafka(obj),
)
producer.flush()
dst_storage = get_storage(cls="memory")
worker_fn = functools.partial(process_replay_objects, storage=dst_storage)
nb_inserted = replayer.process(worker_fn)
assert nb_sent == nb_inserted
for content in skipped_contents:
assert not storage.content_find({"sha1": content["sha1"]})
# no skipped_content_find API endpoint, so use this instead
assert not list(dst_storage.skipped_content_missing(skipped_contents))
def _updated(d1, d2):
d1.update(d2)
d1.pop("data", None)
return d1
def _gen_skipped_contents(n=10):
# we do not use the hypothesis strategy here because this does not play well with
# pytest fixtures, and it makes test execution very slow
algos = DEFAULT_ALGORITHMS | {"length"}
now = datetime.datetime.now(tz=UTC)
return [
_updated(
MultiHash.from_data(data=f"foo{i}".encode(), hash_names=algos).digest(),
{
"status": "absent",
"reason": "why not",
"origin": f"https://somewhere/{i}",
"ctime": now,
},
)
for i in range(n)
]
@pytest.mark.parametrize("privileged", [True, False])
def test_storage_replay_anonymized(
- kafka_prefix: str, kafka_consumer_group: str, kafka_server: str, privileged: bool,
+ kafka_prefix: str,
+ kafka_consumer_group: str,
+ kafka_server: str,
+ privileged: bool,
):
"""Optimal replayer scenario.
This:
- writes objects to the topic
- replayer consumes objects from the topic and replay them
This tests the behavior with both a privileged and non-privileged replayer
"""
writer_config = {
"cls": "kafka",
"brokers": [kafka_server],
"client_id": "kafka_writer",
"prefix": kafka_prefix,
"anonymize": True,
}
src_config: Dict[str, Any] = {"cls": "memory", "journal_writer": writer_config}
storage = get_storage(**src_config)
# Fill the src storage
nb_sent = 0
for obj_type, objs in TEST_OBJECTS.items():
if obj_type in ("origin_visit", "origin_visit_status"):
# these are unrelated with what we want to test here
continue
method = getattr(storage, obj_type + "_add")
method(objs)
nb_sent += len(objs)
# Fill a destination storage from Kafka, potentially using privileged topics
dst_storage = get_storage(cls="memory")
deserializer = ModelObjectDeserializer(
validate=False
) # we cannot validate an anonymized replay
replayer = JournalClient(
brokers=kafka_server,
group_id=kafka_consumer_group,
prefix=kafka_prefix,
stop_after_objects=nb_sent,
privileged=privileged,
value_deserializer=deserializer.convert,
)
worker_fn = functools.partial(process_replay_objects, storage=dst_storage)
nb_inserted = replayer.process(worker_fn)
replayer.consumer.commit()
assert nb_sent == nb_inserted
# Check the contents of the destination storage, and whether the anonymization was
# properly used
assert isinstance(storage, InMemoryStorage) # needed to help mypy
assert isinstance(dst_storage, InMemoryStorage)
check_replayed(storage, dst_storage, expected_anonymized=not privileged)
def test_storage_replayer_with_validation_ok(
replayer_storage_and_client, caplog, redisdb
):
"""Optimal replayer scenario
with validation activated and reporter set to a redis db.
- writes objects to a source storage
- replayer consumes objects from the topic and replays them
- a destination storage is filled from this
- nothing has been reported in the redis db
- both storages should have the same content
"""
src, replayer = replayer_storage_and_client
replayer.deserializer = ModelObjectDeserializer(validate=True, reporter=redisdb.set)
# Fill Kafka using a source storage
nb_sent = 0
for object_type, objects in TEST_OBJECTS.items():
method = getattr(src, object_type + "_add")
method(objects)
if object_type == "origin_visit":
nb_sent += len(objects) # origin-visit-add adds origin-visit-status as well
nb_sent += len(objects)
# Fill the destination storage from Kafka
dst = get_storage(cls="memory")
worker_fn = functools.partial(process_replay_objects, storage=dst)
nb_inserted = replayer.process(worker_fn)
assert nb_sent == nb_inserted
# check we do not have invalid objects reported
invalid = 0
for record in caplog.records:
logtext = record.getMessage()
if WRONG_ID_REG.match(logtext):
invalid += 1
assert invalid == 0, "Invalid objects should not be detected"
assert not redisdb.keys()
# so the dst should be the same as src storage
check_replayed(cast(InMemoryStorage, src), cast(InMemoryStorage, dst))
def test_storage_replayer_with_validation_nok(
replayer_storage_and_client, caplog, redisdb
):
"""Replayer scenario with invalid objects
with validation and reporter set to a redis db.
- writes objects to a source storage
- replayer consumes objects from the topic and replays them
- the destination storage is filled with only valid objects
- the redis db contains the invalid (raw kafka mesg) objects
"""
src, replayer = replayer_storage_and_client
replayer.value_deserializer = ModelObjectDeserializer(
validate=True, reporter=redisdb.set
).convert
caplog.set_level(logging.ERROR, "swh.journal.replay")
# Fill Kafka using a source storage
nb_sent = 0
for object_type, objects in TEST_OBJECTS.items():
method = getattr(src, object_type + "_add")
method(objects)
if object_type == "origin_visit":
nb_sent += len(objects) # origin-visit-add adds origin-visit-status as well
nb_sent += len(objects)
# insert invalid objects
for object_type in ("revision", "directory", "release", "snapshot"):
method = getattr(src, object_type + "_add")
method([attr.evolve(TEST_OBJECTS[object_type][0], id=b"\x00" * 20)])
nb_sent += 1
# Fill the destination storage from Kafka
dst = get_storage(cls="memory")
worker_fn = functools.partial(process_replay_objects, storage=dst)
nb_inserted = replayer.process(worker_fn)
assert nb_sent == nb_inserted
# check we do have invalid objects reported
invalid = 0
for record in caplog.records:
logtext = record.getMessage()
if WRONG_ID_REG.match(logtext):
invalid += 1
assert invalid == 4, "Invalid objects should be detected"
assert set(redisdb.keys()) == {
f"swh:1:{typ}:{'0'*40}".encode() for typ in ("rel", "rev", "snp", "dir")
}
for key in redisdb.keys():
# check the stored value looks right
rawvalue = redisdb.get(key)
value = kafka_to_value(rawvalue)
assert isinstance(value, dict)
assert "id" in value
assert value["id"] == b"\x00" * 20
# check that invalid objects did not reach the dst storage
for attr_ in (
"directories",
"revisions",
"releases",
"snapshots",
):
for id, obj in sorted(getattr(dst._cql_runner, f"_{attr_}").iter_all()):
assert id != b"\x00" * 20
def test_storage_replayer_with_validation_nok_raises(
replayer_storage_and_client, caplog, redisdb
):
"""Replayer scenario with invalid objects
with raise_on_error set to True
This:
- writes both valid & invalid objects to a source storage
- a StorageArgumentException should be raised while replayer consumes
objects from the topic and replays them
"""
src, replayer = replayer_storage_and_client
replayer.value_deserializer = ModelObjectDeserializer(
validate=True, reporter=redisdb.set, raise_on_error=True
).convert
caplog.set_level(logging.ERROR, "swh.journal.replay")
# Fill Kafka using a source storage
nb_sent = 0
for object_type, objects in TEST_OBJECTS.items():
method = getattr(src, object_type + "_add")
method(objects)
if object_type == "origin_visit":
nb_sent += len(objects) # origin-visit-add adds origin-visit-status as well
nb_sent += len(objects)
# insert invalid objects
for object_type in ("revision", "directory", "release", "snapshot"):
method = getattr(src, object_type + "_add")
method([attr.evolve(TEST_OBJECTS[object_type][0], id=b"\x00" * 20)])
nb_sent += 1
# Fill the destination storage from Kafka
dst = get_storage(cls="memory")
worker_fn = functools.partial(process_replay_objects, storage=dst)
with pytest.raises(StorageArgumentException):
replayer.process(worker_fn)
# check we do have invalid objects reported
invalid = 0
for record in caplog.records:
logtext = record.getMessage()
if WRONG_ID_REG.match(logtext):
invalid += 1
assert invalid == 1, "One invalid objects should be detected"
assert len(redisdb.keys()) == 1
diff --git a/swh/storage/tests/test_retry.py b/swh/storage/tests/test_retry.py
index 4b0b75fc..a4dc9d8a 100644
--- a/swh/storage/tests/test_retry.py
+++ b/swh/storage/tests/test_retry.py
@@ -1,197 +1,196 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from unittest.mock import call
import attr
import psycopg2
import pytest
from swh.storage.exc import HashCollision, StorageArgumentException
from swh.storage.utils import now
@pytest.fixture
def monkeypatch_sleep(monkeypatch, swh_storage):
- """In test context, we don't want to wait, make test faster
-
- """
+ """In test context, we don't want to wait, make test faster"""
from swh.storage.proxies.retry import RetryingProxyStorage
for method_name, method in RetryingProxyStorage.__dict__.items():
if "_add" in method_name or "_update" in method_name:
monkeypatch.setattr(method.retry, "sleep", lambda x: None)
return monkeypatch
@pytest.fixture
def fake_hash_collision(sample_data):
return HashCollision("sha1", "38762cf7f55934b34d179ae6a4c80cadccbb7f0a", [])
@pytest.fixture
def swh_storage_backend_config():
yield {
"cls": "pipeline",
- "steps": [{"cls": "retry"}, {"cls": "memory"},],
+ "steps": [
+ {"cls": "retry"},
+ {"cls": "memory"},
+ ],
}
def test_retrying_proxy_storage_content_add(swh_storage, sample_data):
- """Standard content_add works as before
-
- """
+ """Standard content_add works as before"""
sample_content = sample_data.content
content = swh_storage.content_get_data(sample_content.sha1)
assert content is None
s = swh_storage.content_add([sample_content])
assert s == {
"content:add": 1,
"content:add:bytes": sample_content.length,
}
content = swh_storage.content_get_data(sample_content.sha1)
assert content == sample_content.data
def test_retrying_proxy_storage_content_add_with_retry(
- monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision,
+ monkeypatch_sleep,
+ swh_storage,
+ sample_data,
+ mocker,
+ fake_hash_collision,
):
- """Multiple retries for hash collision and psycopg2 error but finally ok
-
- """
+ """Multiple retries for hash collision and psycopg2 error but finally ok"""
mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add")
mock_memory.side_effect = [
# first try goes ko
fake_hash_collision,
# second try goes ko
psycopg2.IntegrityError("content already inserted"),
# ok then!
{"content:add": 1},
]
sample_content = sample_data.content
content = swh_storage.content_get_data(sample_content.sha1)
assert content is None
s = swh_storage.content_add([sample_content])
assert s == {"content:add": 1}
mock_memory.assert_has_calls(
- [call([sample_content]), call([sample_content]), call([sample_content]),]
+ [
+ call([sample_content]),
+ call([sample_content]),
+ call([sample_content]),
+ ]
)
def test_retrying_proxy_swh_storage_content_add_failure(
swh_storage, sample_data, mocker
):
- """Unfiltered errors are raising without retry
-
- """
+ """Unfiltered errors are raising without retry"""
mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add")
mock_memory.side_effect = StorageArgumentException("Refuse to add content always!")
sample_content = sample_data.content
content = swh_storage.content_get_data(sample_content.sha1)
assert content is None
with pytest.raises(StorageArgumentException, match="Refuse to add"):
swh_storage.content_add([sample_content])
assert mock_memory.call_count == 1
def test_retrying_proxy_storage_content_add_metadata(swh_storage, sample_data):
- """Standard content_add_metadata works as before
-
- """
+ """Standard content_add_metadata works as before"""
sample_content = sample_data.content
content = attr.evolve(sample_content, data=None)
pk = content.sha1
content_metadata = swh_storage.content_get([pk])
assert content_metadata == [None]
s = swh_storage.content_add_metadata([attr.evolve(content, ctime=now())])
assert s == {
"content:add": 1,
}
content_metadata = swh_storage.content_get([pk])
assert len(content_metadata) == 1
assert content_metadata[0].sha1 == pk
def test_retrying_proxy_storage_content_add_metadata_with_retry(
monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision
):
- """Multiple retries for hash collision and psycopg2 error but finally ok
-
- """
+ """Multiple retries for hash collision and psycopg2 error but finally ok"""
mock_memory = mocker.patch(
"swh.storage.in_memory.InMemoryStorage.content_add_metadata"
)
mock_memory.side_effect = [
# first try goes ko
fake_hash_collision,
# second try goes ko
psycopg2.IntegrityError("content_metadata already inserted"),
# ok then!
{"content:add": 1},
]
sample_content = sample_data.content
content = attr.evolve(sample_content, data=None)
s = swh_storage.content_add_metadata([content])
assert s == {"content:add": 1}
mock_memory.assert_has_calls(
- [call([content]), call([content]), call([content]),]
+ [
+ call([content]),
+ call([content]),
+ call([content]),
+ ]
)
def test_retrying_proxy_swh_storage_content_add_metadata_failure(
swh_storage, sample_data, mocker
):
- """Unfiltered errors are raising without retry
-
- """
+ """Unfiltered errors are raising without retry"""
mock_memory = mocker.patch(
"swh.storage.in_memory.InMemoryStorage.content_add_metadata"
)
mock_memory.side_effect = StorageArgumentException(
"Refuse to add content_metadata!"
)
sample_content = sample_data.content
content = attr.evolve(sample_content, data=None)
with pytest.raises(StorageArgumentException, match="Refuse to add"):
swh_storage.content_add_metadata([content])
assert mock_memory.call_count == 1
def test_retrying_proxy_swh_storage_keyboardinterrupt(swh_storage, sample_data, mocker):
- """Unfiltered errors are raising without retry
-
- """
+ """Unfiltered errors are raising without retry"""
mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add")
mock_memory.side_effect = KeyboardInterrupt()
sample_content = sample_data.content
content = swh_storage.content_get_data(sample_content.sha1)
assert content is None
with pytest.raises(KeyboardInterrupt):
swh_storage.content_add([sample_content])
assert mock_memory.call_count == 1
diff --git a/swh/storage/tests/test_server.py b/swh/storage/tests/test_server.py
index 2c75ac85..9bcb3ed2 100644
--- a/swh/storage/tests/test_server.py
+++ b/swh/storage/tests/test_server.py
@@ -1,96 +1,102 @@
# Copyright (C) 2019-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import os
from typing import Any, Dict
import pytest
import yaml
from swh.core.config import load_from_envvar
from swh.storage.api.server import (
StorageServerApp,
load_and_check_config,
make_app_from_configfile,
)
def prepare_config_file(tmpdir, content, name="config.yml"):
"""Prepare configuration file in `$tmpdir/name` with content `content`.
Args:
tmpdir (LocalPath): root directory
content (str/dict): Content of the file either as string or as a dict.
If a dict, converts the dict into a yaml string.
name (str): configuration filename
Returns
path (str) of the configuration file prepared.
"""
config_path = tmpdir / name
if isinstance(content, dict): # convert if needed
content = yaml.dump(content)
config_path.write_text(content, encoding="utf-8")
# pytest on python3.5 does not support LocalPath manipulation, so
# convert path to string
return str(config_path)
@pytest.mark.parametrize("storage_class", [None, ""])
def test_load_and_check_config_no_configuration(storage_class):
"""Inexistent configuration files raises"""
with pytest.raises(EnvironmentError, match="Configuration file must be defined"):
load_and_check_config(storage_class)
def test_load_and_check_config_inexistent_file():
config_path = "/some/inexistent/config.yml"
expected_error = f"Configuration file {config_path} does not exist"
with pytest.raises(FileNotFoundError, match=expected_error):
load_and_check_config(config_path)
def test_load_and_check_config_wrong_configuration(tmpdir):
"""Wrong configuration raises"""
config_path = prepare_config_file(tmpdir, "something: useless")
with pytest.raises(KeyError, match="Missing 'storage' configuration"):
load_and_check_config(config_path)
def test_load_and_check_config_local_config_fine(tmpdir):
"""'local' complete configuration is fine"""
- config = {"storage": {"cls": "postgresql", "db": "db", "objstorage": "something",}}
+ config = {
+ "storage": {
+ "cls": "postgresql",
+ "db": "db",
+ "objstorage": "something",
+ }
+ }
config_path = prepare_config_file(tmpdir, config)
cfg = load_and_check_config(config_path)
assert cfg == config
@pytest.fixture
def swh_storage_server_config(
swh_storage_backend_config: Dict[str, Any]
) -> Dict[str, Any]:
return {"storage": swh_storage_backend_config}
@pytest.fixture
def swh_storage_config(monkeypatch, swh_storage_server_config, tmp_path):
conf_path = os.path.join(str(tmp_path), "storage.yml")
with open(conf_path, "w") as f:
f.write(yaml.dump(swh_storage_server_config))
monkeypatch.setenv("SWH_CONFIG_FILENAME", conf_path)
return conf_path
def test_server_make_app_from_config_file(swh_storage_config):
app = make_app_from_configfile()
expected_cfg = load_from_envvar()
assert app is not None
assert isinstance(app, StorageServerApp)
assert app.config["storage"] == expected_cfg["storage"]
app2 = make_app_from_configfile()
assert app is app2
diff --git a/swh/storage/tests/test_tenacious.py b/swh/storage/tests/test_tenacious.py
index 40508f7b..0af1853e 100644
--- a/swh/storage/tests/test_tenacious.py
+++ b/swh/storage/tests/test_tenacious.py
@@ -1,423 +1,430 @@
# Copyright (C) 2020-2021 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from collections import Counter
from contextlib import contextmanager
from unittest.mock import patch
import attr
import pytest
from swh.model import model
from swh.model.tests.swh_model_data import TEST_OBJECTS
from swh.storage import get_storage
from swh.storage.in_memory import InMemoryStorage
from swh.storage.proxies.tenacious import TenaciousProxyStorage
from swh.storage.tests.storage_data import StorageData
from swh.storage.tests.storage_tests import (
TestStorageGeneratedData as _TestStorageGeneratedData,
)
from swh.storage.tests.storage_tests import TestStorage as _TestStorage # noqa
from swh.storage.utils import now
data = StorageData()
collections = {
"origin": data.origins,
"content": data.contents,
"skipped_content": data.skipped_contents,
"revision": data.revisions,
"directory": data.directories,
"release": data.releases,
"snapshot": data.snapshots,
}
# generic storage tests (using imported TestStorage* classes)
@pytest.fixture
def swh_storage_backend_config2():
yield {
"cls": "memory",
- "journal_writer": {"cls": "memory",},
+ "journal_writer": {
+ "cls": "memory",
+ },
}
@pytest.fixture
def swh_storage():
storage_config = {
"cls": "pipeline",
"steps": [
{"cls": "tenacious"},
- {"cls": "memory", "journal_writer": {"cls": "memory",}},
+ {
+ "cls": "memory",
+ "journal_writer": {
+ "cls": "memory",
+ },
+ },
],
}
storage = get_storage(**storage_config)
storage.journal_writer = storage.storage.journal_writer
return storage
class TestTenaciousStorage(_TestStorage):
@pytest.mark.skip(
'The "person" table of the pgsql is a legacy thing, and not '
"supported by the cassandra/in-memory backend."
)
def test_person_fullname_unicity(self):
pass
@pytest.mark.skip(reason="No collision with the tenacious storage")
def test_content_add_collision(self, swh_storage, sample_data):
pass
@pytest.mark.skip(reason="No collision with the tenacious storage")
def test_content_add_metadata_collision(self, swh_storage, sample_data):
pass
@pytest.mark.skip("content_update is not implemented")
def test_content_update(self):
pass
@pytest.mark.skip("Not supported by Cassandra/InMemory storage")
def test_origin_count(self):
pass
class TestTenaciousStorageGeneratedData(_TestStorageGeneratedData):
@pytest.mark.skip("Not supported by Cassandra/InMemory")
def test_origin_count(self):
pass
@pytest.mark.skip("Not supported by Cassandra/InMemory")
def test_origin_count_with_visit_no_visits(self):
pass
@pytest.mark.skip("Not supported by Cassandra/InMemory")
def test_origin_count_with_visit_with_visits_and_snapshot(self):
pass
@pytest.mark.skip("Not supported by Cassandra/InMemory")
def test_origin_count_with_visit_with_visits_no_snapshot(self):
pass
# specific tests for the tenacious behavior
def get_tenacious_storage(**config):
storage_config = {
"cls": "pipeline",
"steps": [
{"cls": "validate"},
{"cls": "tenacious", **config},
{"cls": "memory"},
],
}
return get_storage(**storage_config)
@contextmanager
def disabled_validators():
attr.set_run_validators(False)
yield
attr.set_run_validators(True)
def popid(d):
d.pop("id")
return d
testdata = [
pytest.param(
"content",
"content_add",
list(TEST_OBJECTS["content"]),
attr.evolve(model.Content.from_data(data=b"too big"), length=1000),
attr.evolve(model.Content.from_data(data=b"to fail"), length=1000),
id="content",
),
pytest.param(
"content",
"content_add_metadata",
[attr.evolve(cnt, ctime=now()) for cnt in TEST_OBJECTS["content"]],
attr.evolve(model.Content.from_data(data=b"too big"), length=1000, ctime=now()),
attr.evolve(model.Content.from_data(data=b"to fail"), length=1000, ctime=now()),
id="content_metadata",
),
pytest.param(
"skipped_content",
"skipped_content_add",
list(TEST_OBJECTS["skipped_content"]),
attr.evolve(
model.SkippedContent.from_data(data=b"too big", reason="too big"),
length=1000,
),
attr.evolve(
model.SkippedContent.from_data(data=b"to fail", reason="to fail"),
length=1000,
),
id="skipped_content",
),
pytest.param(
"directory",
"directory_add",
list(TEST_OBJECTS["directory"]),
data.directory,
data.directory2,
id="directory",
),
pytest.param(
"revision",
"revision_add",
list(TEST_OBJECTS["revision"]),
data.revision,
data.revision2,
id="revision",
),
pytest.param(
"release",
"release_add",
list(TEST_OBJECTS["release"]),
data.release,
data.release2,
id="release",
),
pytest.param(
"snapshot",
"snapshot_add",
list(TEST_OBJECTS["snapshot"]),
data.snapshot,
data.complete_snapshot,
id="snapshot",
),
pytest.param(
"origin",
"origin_add",
list(TEST_OBJECTS["origin"]),
data.origin,
data.origin2,
id="origin",
),
]
class LimitedInMemoryStorage(InMemoryStorage):
# forbidden are 'bad1' and 'bad2' arguments of `testdata`
forbidden = [x[0][3] for x in testdata] + [x[0][4] for x in testdata]
def __init__(self, *args, **kw):
self.add_calls = Counter()
super().__init__(*args, **kw)
def reset(self):
super().reset()
self.add_calls.clear()
def content_add(self, contents):
return self._maybe_add(super().content_add, "content", contents)
def content_add_metadata(self, contents):
return self._maybe_add(super().content_add_metadata, "content", contents)
def skipped_content_add(self, skipped_contents):
return self._maybe_add(
super().skipped_content_add, "skipped_content", skipped_contents
)
def origin_add(self, origins):
return self._maybe_add(super().origin_add, "origin", origins)
def directory_add(self, directories):
return self._maybe_add(super().directory_add, "directory", directories)
def revision_add(self, revisions):
return self._maybe_add(super().revision_add, "revision", revisions)
def release_add(self, releases):
return self._maybe_add(super().release_add, "release", releases)
def snapshot_add(self, snapshots):
return self._maybe_add(super().snapshot_add, "snapshot", snapshots)
def _maybe_add(self, add_func, object_type, objects):
self.add_calls[object_type] += 1
if any(c in self.forbidden for c in objects):
raise ValueError(
f"{object_type} is forbidden",
[c.unique_key() for c in objects if c in self.forbidden],
)
return add_func(objects)
@patch("swh.storage.in_memory.InMemoryStorage", LimitedInMemoryStorage)
@pytest.mark.parametrize("object_type, add_func_name, objects, bad1, bad2", testdata)
def test_tenacious_proxy_storage(object_type, add_func_name, objects, bad1, bad2):
storage = get_tenacious_storage()
tenacious = storage.storage
in_memory = tenacious.storage
assert isinstance(tenacious, TenaciousProxyStorage)
assert isinstance(in_memory, LimitedInMemoryStorage)
size = len(objects)
add_func = getattr(storage, add_func_name)
# Note: when checking the LimitedInMemoryStorage.add_calls counter, it's
# hard to guess the exact number of calls in the end (depends on the size
# of batch and the position of bad objects in this batch). So we will only
# check a lower limit of the form (n + m), where n is the minimum expected
# number of additions (due to the batch begin split), and m is the fact
# that bad objects are tried (individually) several (3) times before giving
# up. So for one bad object, m is 3; for 2 bad objects, m is 6, etc.
s = add_func(objects)
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 0
assert storage.add_calls[object_type] == (1 + 0)
in_memory.reset()
tenacious.reset()
# bad1 is the last element
s = add_func(objects + [bad1])
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 1
assert storage.add_calls[object_type] >= (2 + 3)
in_memory.reset()
tenacious.reset()
# bad1 and bad2 are the last elements
s = add_func(objects + [bad1, bad2])
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 2
assert storage.add_calls[object_type] >= (3 + 6)
in_memory.reset()
tenacious.reset()
# bad1 is the first element
s = add_func([bad1] + objects)
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 1
assert storage.add_calls[object_type] >= (2 + 3)
in_memory.reset()
tenacious.reset()
# bad1 and bad2 are the first elements
s = add_func([bad1, bad2] + objects)
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 2
assert storage.add_calls[object_type] >= (3 + 6)
in_memory.reset()
tenacious.reset()
# bad1 is in the middle of the list of inserted elements
s = add_func(objects[: size // 2] + [bad1] + objects[size // 2 :])
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 1
assert storage.add_calls[object_type] >= (3 + 3)
in_memory.reset()
tenacious.reset()
# bad1 and bad2 are together in the middle of the list of inserted elements
s = add_func(objects[: size // 2] + [bad1, bad2] + objects[size // 2 :])
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 2
assert storage.add_calls[object_type] >= (3 + 6)
in_memory.reset()
tenacious.reset()
# bad1 and bad2 are spread in the middle of the list of inserted elements
s = add_func(
objects[: size // 3]
+ [bad1]
+ objects[size // 3 : 2 * (size // 3)]
+ [bad2]
+ objects[2 * (size // 3) :]
)
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 2
assert storage.add_calls[object_type] >= (3 + 6)
in_memory.reset()
tenacious.reset()
# bad1 is the only element
s = add_func([bad1])
assert s.get(f"{object_type}:add", 0) == 0
assert s.get(f"{object_type}:add:errors", 0) == 1
assert storage.add_calls[object_type] == (0 + 3)
in_memory.reset()
tenacious.reset()
# bad1 and bad2 are the only elements
s = add_func([bad1, bad2])
assert s.get(f"{object_type}:add", 0) == 0
assert s.get(f"{object_type}:add:errors", 0) == 2
assert storage.add_calls[object_type] == (1 + 6)
in_memory.reset()
tenacious.reset()
@patch("swh.storage.in_memory.InMemoryStorage", LimitedInMemoryStorage)
@pytest.mark.parametrize("object_type, add_func_name, objects, bad1, bad2", testdata)
def test_tenacious_proxy_storage_rate_limit(
object_type, add_func_name, objects, bad1, bad2
):
storage = get_tenacious_storage(error_rate_limit={"errors": 1, "window_size": 2})
tenacious = storage.storage
in_memory = tenacious.storage
assert isinstance(tenacious, TenaciousProxyStorage)
assert isinstance(in_memory, LimitedInMemoryStorage)
size = len(objects)
add_func = getattr(storage, add_func_name)
# with no insertion failure, no impact
s = add_func(objects)
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 0
in_memory.reset()
tenacious.reset()
# with one insertion failure, no impact
s = add_func([bad1] + objects)
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 1
in_memory.reset()
tenacious.reset()
s = add_func(objects[: size // 2] + [bad1] + objects[size // 2 :])
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 1
in_memory.reset()
tenacious.reset()
# with two consecutive insertion failures, exception is raised
with pytest.raises(RuntimeError, match="Too many insertion errors"):
add_func([bad1, bad2] + objects)
in_memory.reset()
tenacious.reset()
if size > 2:
# with two consecutive insertion failures, exception is raised
# (errors not at the beginning)
with pytest.raises(RuntimeError, match="Too many insertion errors"):
add_func(objects[: size // 2] + [bad1, bad2] + objects[size // 2 :])
in_memory.reset()
tenacious.reset()
# with two non-consecutive insertion failures, no impact
# (errors are far enough to not reach the rate limit)
s = add_func(
objects[: size // 3]
+ [bad1]
+ objects[size // 3 : 2 * (size // 3)]
+ [bad2]
+ objects[2 * (size // 3) :]
)
assert s.get(f"{object_type}:add", 0) == size
assert s.get(f"{object_type}:add:errors", 0) == 2
in_memory.reset()
tenacious.reset()
diff --git a/swh/storage/tests/test_validate.py b/swh/storage/tests/test_validate.py
index 5efb538e..e5697bab 100644
--- a/swh/storage/tests/test_validate.py
+++ b/swh/storage/tests/test_validate.py
@@ -1,135 +1,138 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
import attr
import pytest
from swh.model.hashutil import hash_to_hex
from swh.storage import get_storage
from swh.storage.exc import StorageArgumentException
@pytest.fixture
def swh_storage():
storage_config = {
"cls": "pipeline",
- "steps": [{"cls": "validate"}, {"cls": "memory"},],
+ "steps": [
+ {"cls": "validate"},
+ {"cls": "memory"},
+ ],
}
return get_storage(**storage_config)
def test_validating_proxy_storage_content(swh_storage, sample_data):
sample_content = sample_data.content
content = swh_storage.content_get_data(sample_content.sha1)
assert content is None
with pytest.raises(StorageArgumentException, match="hashes"):
s = swh_storage.content_add([attr.evolve(sample_content, sha1=b"a" * 20)])
content = swh_storage.content_get_data(sample_content.sha1)
assert content is None
s = swh_storage.content_add([sample_content])
assert s == {
"content:add": 1,
"content:add:bytes": sample_content.length,
}
content = swh_storage.content_get_data(sample_content.sha1)
assert content is not None
def test_validating_proxy_storage_skipped_content(swh_storage, sample_data):
sample_content = sample_data.skipped_content
sample_content = attr.evolve(sample_content, sha1=b"a" * 20)
sample_content_dict = sample_content.to_dict()
s = swh_storage.skipped_content_add([sample_content])
content = list(swh_storage.skipped_content_missing([sample_content_dict]))
assert content == []
s = swh_storage.skipped_content_add([sample_content])
assert s == {
"skipped_content:add": 0,
}
def test_validating_proxy_storage_directory(swh_storage, sample_data):
sample_directory = sample_data.directory
id_ = hash_to_hex(sample_directory.id)
assert swh_storage.directory_missing([sample_directory.id]) == [sample_directory.id]
with pytest.raises(StorageArgumentException, match=f"should be {id_}"):
s = swh_storage.directory_add([attr.evolve(sample_directory, id=b"a" * 20)])
assert swh_storage.directory_missing([sample_directory.id]) == [sample_directory.id]
s = swh_storage.directory_add([sample_directory])
assert s == {
"directory:add": 1,
}
assert swh_storage.directory_missing([sample_directory.id]) == []
def test_validating_proxy_storage_revision(swh_storage, sample_data):
sample_revision = sample_data.revision
id_ = hash_to_hex(sample_revision.id)
assert swh_storage.revision_missing([sample_revision.id]) == [sample_revision.id]
with pytest.raises(StorageArgumentException, match=f"should be {id_}"):
s = swh_storage.revision_add([attr.evolve(sample_revision, id=b"a" * 20)])
assert swh_storage.revision_missing([sample_revision.id]) == [sample_revision.id]
s = swh_storage.revision_add([sample_revision])
assert s == {
"revision:add": 1,
}
assert swh_storage.revision_missing([sample_revision.id]) == []
def test_validating_proxy_storage_release(swh_storage, sample_data):
sample_release = sample_data.release
id_ = hash_to_hex(sample_release.id)
assert swh_storage.release_missing([sample_release.id]) == [sample_release.id]
with pytest.raises(StorageArgumentException, match=f"should be {id_}"):
s = swh_storage.release_add([attr.evolve(sample_release, id=b"a" * 20)])
assert swh_storage.release_missing([sample_release.id]) == [sample_release.id]
s = swh_storage.release_add([sample_release])
assert s == {
"release:add": 1,
}
assert swh_storage.release_missing([sample_release.id]) == []
def test_validating_proxy_storage_snapshot(swh_storage, sample_data):
sample_snapshot = sample_data.snapshot
id_ = hash_to_hex(sample_snapshot.id)
assert swh_storage.snapshot_missing([sample_snapshot.id]) == [sample_snapshot.id]
with pytest.raises(StorageArgumentException, match=f"should be {id_}"):
s = swh_storage.snapshot_add([attr.evolve(sample_snapshot, id=b"a" * 20)])
assert swh_storage.snapshot_missing([sample_snapshot.id]) == [sample_snapshot.id]
s = swh_storage.snapshot_add([sample_snapshot])
assert s == {
"snapshot:add": 1,
}
assert swh_storage.snapshot_missing([sample_snapshot.id]) == []
diff --git a/swh/storage/utils.py b/swh/storage/utils.py
index dfaab304..774b5464 100644
--- a/swh/storage/utils.py
+++ b/swh/storage/utils.py
@@ -1,111 +1,107 @@
# Copyright (C) 2019-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from datetime import datetime, timezone
import re
from typing import Callable, Dict, Optional, Tuple, TypeVar
from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex
def now() -> datetime:
return datetime.now(tz=timezone.utc)
T1 = TypeVar("T1")
T2 = TypeVar("T2")
def map_optional(f: Callable[[T1], T2], x: Optional[T1]) -> Optional[T2]:
if x is None:
return None
else:
return f(x)
def _is_power_of_two(n: int) -> bool:
return n > 0 and n & (n - 1) == 0
def get_partition_bounds_bytes(
i: int, n: int, nb_bytes: int
) -> Tuple[bytes, Optional[bytes]]:
r"""Splits the range [0; 2^(nb_bytes*8)) into n same-length intervals,
and returns the boundaries of this interval (both inclusive); or None
as upper bound, if this is the last partition
n must be a power of 2.
>>> get_partition_bounds_bytes(0, 16, 2) == (b'\x00\x00', b'\x10\x00')
True
>>> get_partition_bounds_bytes(1, 16, 2) == (b'\x10\x00', b'\x20\x00')
True
>>> get_partition_bounds_bytes(14, 16, 2) == (b'\xe0\x00', b'\xf0\x00')
True
>>> get_partition_bounds_bytes(15, 16, 2) == (b'\xf0\x00', None)
True
"""
if not _is_power_of_two(n):
raise ValueError("number of partitions must be a power of two")
if not 0 <= i < n:
raise ValueError(
"partition index must be between 0 and the number of partitions."
)
space_size = 1 << (nb_bytes * 8)
partition_size = space_size // n
start = (partition_size * i).to_bytes(nb_bytes, "big")
end = None if i == n - 1 else (partition_size * (i + 1)).to_bytes(nb_bytes, "big")
return (start, end)
def extract_collision_hash(error_message: str) -> Optional[Tuple[str, bytes]]:
"""Utilities to extract the hash information from a hash collision error.
Hash collision error message are of the form:
'Key ()=([^)]+)\)=\(\\x(?P[a-f0-9]+)\) \w*"
result = re.match(pattern, error_message)
if result:
hash_type = result.group("type")
hash_id = result.group("id")
return hash_type, hash_to_bytes(hash_id)
return None
def content_hex_hashes(content: Dict[str, bytes]) -> Dict[str, str]:
- """Convert bytes hashes into hex hashes.
-
- """
+ """Convert bytes hashes into hex hashes."""
return {algo: hash_to_hex(content[algo]) for algo in DEFAULT_ALGORITHMS}
def content_bytes_hashes(content: Dict[str, str]) -> Dict[str, bytes]:
- """Convert bytes hashes into hex hashes.
-
- """
+ """Convert bytes hashes into hex hashes."""
return {algo: hash_to_bytes(content[algo]) for algo in DEFAULT_ALGORITHMS}
def remove_keys(d: Dict[T1, T2], keys: Tuple[T1, ...]) -> Dict[T1, T2]:
"""Returns a copy of ``d`` minus the given keys."""
return {k: v for (k, v) in d.items() if k not in keys}
def round_to_milliseconds(date):
"""Round datetime to milliseconds before insertion, so equality doesn't fail after a
round-trip through a DB (eg. Cassandra)
"""
return date.replace(microsecond=(date.microsecond // 1000) * 1000)
diff --git a/swh/storage/writer.py b/swh/storage/writer.py
index f8339b6b..58161cf9 100644
--- a/swh/storage/writer.py
+++ b/swh/storage/writer.py
@@ -1,121 +1,119 @@
# Copyright (C) 2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
from typing import Any, Dict, Iterable
from attr import evolve
from swh.model.model import (
Content,
Directory,
ExtID,
MetadataAuthority,
MetadataFetcher,
Origin,
OriginVisit,
OriginVisitStatus,
RawExtrinsicMetadata,
Release,
Revision,
SkippedContent,
Snapshot,
)
try:
from swh.journal.writer import get_journal_writer
except ImportError:
get_journal_writer = None # type: ignore
# mypy limitation, see https://github.com/python/mypy/issues/1153
def model_object_dict_sanitizer(
object_type: str, object_dict: Dict[str, Any]
) -> Dict[str, str]:
object_dict = object_dict.copy()
if object_type == "content":
object_dict.pop("data", None)
return object_dict
class JournalWriter:
"""Journal writer storage collaborator. It's in charge of adding objects to
the journal.
"""
def __init__(self, journal_writer):
if journal_writer:
if get_journal_writer is None:
raise EnvironmentError(
"You need the swh.journal package to use the "
"journal_writer feature"
)
self.journal = get_journal_writer(
value_sanitizer=model_object_dict_sanitizer, **journal_writer
)
else:
self.journal = None
def write_addition(self, object_type, value) -> None:
if self.journal:
self.journal.write_addition(object_type, value)
def write_additions(self, object_type, values) -> None:
if self.journal:
self.journal.write_additions(object_type, values)
def content_add(self, contents: Iterable[Content]) -> None:
- """Add contents to the journal. Drop the data field if provided.
-
- """
+ """Add contents to the journal. Drop the data field if provided."""
contents = [evolve(item, data=None) for item in contents]
self.write_additions("content", contents)
def content_update(self, contents: Iterable[Dict[str, Any]]) -> None:
if self.journal:
raise NotImplementedError("content_update is not supported by the journal.")
def content_add_metadata(self, contents: Iterable[Content]) -> None:
self.content_add(contents)
def skipped_content_add(self, contents: Iterable[SkippedContent]) -> None:
self.write_additions("skipped_content", contents)
def directory_add(self, directories: Iterable[Directory]) -> None:
self.write_additions("directory", directories)
def revision_add(self, revisions: Iterable[Revision]) -> None:
self.write_additions("revision", revisions)
def release_add(self, releases: Iterable[Release]) -> None:
self.write_additions("release", releases)
def snapshot_add(self, snapshots: Iterable[Snapshot]) -> None:
self.write_additions("snapshot", snapshots)
def origin_visit_add(self, visits: Iterable[OriginVisit]) -> None:
self.write_additions("origin_visit", visits)
def origin_visit_status_add(
self, visit_statuses: Iterable[OriginVisitStatus]
) -> None:
self.write_additions("origin_visit_status", visit_statuses)
def origin_add(self, origins: Iterable[Origin]) -> None:
self.write_additions("origin", origins)
def raw_extrinsic_metadata_add(
self, metadata: Iterable[RawExtrinsicMetadata]
) -> None:
self.write_additions("raw_extrinsic_metadata", metadata)
def metadata_fetcher_add(self, fetchers: Iterable[MetadataFetcher]) -> None:
self.write_additions("metadata_fetcher", fetchers)
def metadata_authority_add(self, authorities: Iterable[MetadataAuthority]) -> None:
self.write_additions("metadata_authority", authorities)
def extid_add(self, extids: Iterable[ExtID]) -> None:
self.write_additions("extid", extids)