diff --git a/bin/swh-storage-add-dir b/bin/swh-storage-add-dir index 793183b1..ae3cd8ff 100755 --- a/bin/swh-storage-add-dir +++ b/bin/swh-storage-add-dir @@ -1,40 +1,40 @@ #!/usr/bin/env python3 # Copyright (C) 2015 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 import sys -from swh.storage.storage import Storage from swh.model.hashutil import MultiHash +from swh.storage.storage import Storage if __name__ == "__main__": try: db_connstring = sys.argv[1] obj_root = sys.argv[2] dirname = sys.argv[3] except IndexError: print("Usage: swh-storage-add-dir" + " DB_CONNSTRING OBJ_STORAGE_DIR DATA_DIR") print( 'Example: swh-storage-add-dir "dbname=swh user=foo"' + " /srv/softwareheritage/objects /usr/src/linux-4.2" ) sys.exit(1) logging.basicConfig(level=logging.INFO) storage = Storage(db_connstring, obj_root) def list_content(): for root, _dirs, files in os.walk(dirname): for name in files: path = os.path.join(root, name) cont = MultiHash.from_path(path).digest() cont["data"] = open(path, "rb").read() yield cont storage.content_add(list_content()) diff --git a/setup.py b/setup.py index 442e90f1..bf699682 100755 --- a/setup.py +++ b/setup.py @@ -1,77 +1,77 @@ #!/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 setuptools import setup, find_packages - -from os import path 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",], entry_points=""" [console_scripts] swh-storage=swh.storage.cli:main [swh.cli.subcommands] storage=swh.storage.cli:storage """, install_requires=parse_requirements() + parse_requirements("swh"), extras_require={ "testing": (parse_requirements("test") + parse_requirements("swh-journal")), "schemata": ["SQLAlchemy"], "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/__init__.py b/swh/storage/__init__.py index 0d78c906..d13eb462 100644 --- a/swh/storage/__init__.py +++ b/swh/storage/__init__.py @@ -1,106 +1,106 @@ # 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 importlib -from typing import Any, Dict, List, TYPE_CHECKING +from typing import TYPE_CHECKING, Any, Dict, List import warnings if TYPE_CHECKING: from .interface import StorageInterface STORAGE_IMPLEMENTATIONS = { "local": ".postgresql.storage.Storage", "remote": ".api.client.RemoteStorage", "memory": ".in_memory.InMemoryStorage", "filter": ".filter.FilteringProxyStorage", "buffer": ".buffer.BufferingProxyStorage", "retry": ".retry.RetryingProxyStorage", "cassandra": ".cassandra.CassandraStorage", "validate": ".validate.ValidatingProxyStorage", } def get_storage(cls: str, **kwargs) -> "StorageInterface": """Get a storage object of class `storage_class` with arguments `storage_args`. Args: storage (dict): dictionary with keys: - cls (str): storage's class, either local, remote, memory, filter, buffer - args (dict): dictionary with keys Returns: an instance of swh.storage.Storage or compatible class Raises: ValueError if passed an unknown storage class. """ if "args" in kwargs: warnings.warn( 'Explicit "args" key is deprecated, use keys directly instead.', DeprecationWarning, ) kwargs = kwargs["args"] if cls == "pipeline": return get_storage_pipeline(**kwargs) class_path = STORAGE_IMPLEMENTATIONS.get(cls) if class_path is None: raise ValueError( "Unknown storage class `%s`. Supported: %s" % (cls, ", ".join(STORAGE_IMPLEMENTATIONS)) ) (module_path, class_name) = class_path.rsplit(".", 1) module = importlib.import_module(module_path, package=__package__) Storage = getattr(module, class_name) check_config = kwargs.pop("check_config", {}) storage = Storage(**kwargs) if check_config: if not storage.check_config(**check_config): raise EnvironmentError("storage check config failed") return storage def get_storage_pipeline( steps: List[Dict[str, Any]], check_config=None ) -> "StorageInterface": """Recursively get a storage object that may use other storage objects as backends. Args: steps (List[dict]): List of dicts that may be used as kwargs for `get_storage`. Returns: an instance of swh.storage.Storage or compatible class Raises: ValueError if passed an unknown storage class. """ storage_config = None for step in reversed(steps): if "args" in step: warnings.warn( 'Explicit "args" key is deprecated, use keys directly ' "instead.", DeprecationWarning, ) step = { "cls": step["cls"], **step["args"], } if storage_config: step["storage"] = storage_config step["check_config"] = check_config storage_config = step if storage_config is None: raise ValueError("'pipeline' has no steps.") return get_storage(**storage_config) diff --git a/swh/storage/algos/diff.py b/swh/storage/algos/diff.py index ba098470..328469b6 100644 --- a/swh/storage/algos/diff.py +++ b/swh/storage/algos/diff.py @@ -1,420 +1,417 @@ # 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.hashutil import hash_to_bytes from swh.model.identifiers import directory_identifier - from swh.storage.interface import StorageInterface from .dir_iterators import DirectoryIterator, DoubleDirectoryIterator, Remaining - # get the hash identifier for an empty directory _empty_dir_hash = hash_to_bytes(directory_identifier({"entries": []})) 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/revisions_walker.py b/swh/storage/algos/revisions_walker.py index 20a52a28..bde3a871 100644 --- a/swh/storage/algos/revisions_walker.py +++ b/swh/storage/algos/revisions_walker.py @@ -1,548 +1,547 @@ # Copyright (C) 2018-2019 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 -import heapq - from abc import ABCMeta, abstractmethod from collections import deque +import heapq _revs_walker_classes = {} class _RevisionsWalkerMetaClass(ABCMeta): def __new__(cls, clsname, bases, attrs): newclass = super().__new__(cls, clsname, bases, attrs) if "rw_type" in attrs: _revs_walker_classes[attrs["rw_type"]] = newclass return newclass class RevisionsWalker(metaclass=_RevisionsWalkerMetaClass): """ Abstract base class encapsulating the logic to walk across a revisions history starting from a given one. It defines an iterator returning the revisions according to a specific ordering implemented in derived classes. The iteration step performs the following operations: 1) Check if the iteration is finished by calling method :meth:`is_finished` and raises :exc:`StopIteration` if it it is the case 2) Get the next unseen revision by calling method :meth:`get_next_rev_id` 3) Process parents of that revision by calling method :meth:`process_parent_revs` for the next iteration steps 4) Check if the revision should be returned by calling method :meth:`should_return` and returns it if it is the case In order to easily instantiate a specific type of revisions walker, it is recommended to use the factory function :func:`get_revisions_walker`. Args: storage (swh.storage.interface.StorageInterface): instance of swh storage (either local or remote) rev_start (bytes): a revision identifier max_revs (Optional[int]): maximum number of revisions to return state (Optional[dict]): previous state of that revisions walker """ def __init__(self, storage, rev_start, max_revs=None, state=None): self._revs_to_visit = [] self._done = set() self._revs = {} self._last_rev = None self._num_revs = 0 self._max_revs = max_revs self._missing_revs = set() if state: self._revs_to_visit = state["revs_to_visit"] self._done = state["done"] self._last_rev = state["last_rev"] self._num_revs = state["num_revs"] self._missing_revs = state["missing_revs"] self.storage = storage self.process_rev(rev_start) @abstractmethod def process_rev(self, rev_id): """ Abstract method whose purpose is to process a newly visited revision during the walk. Derived classes must implement it according to the desired method to walk across the revisions history (for instance through a dfs on the revisions DAG). Args: rev_id (bytes): the newly visited revision identifier """ pass @abstractmethod def get_next_rev_id(self): """ Abstract method whose purpose is to return the next revision during the iteration. Derived classes must implement it according to the desired method to walk across the revisions history. Returns: dict: A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` """ pass def process_parent_revs(self, rev): """ Process the parents of a revision when it is iterated. The default implementation simply calls :meth:`process_rev` for each parent revision in the order they are declared. Args: rev (dict): A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` """ for parent_id in rev["parents"]: self.process_rev(parent_id) def should_return(self, rev): """ Filter out a revision to return if needed. Default implementation returns all iterated revisions. Args: rev (dict): A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` Returns: bool: Whether to return the revision in the iteration """ return True def is_finished(self): """ Determine if the iteration is finished. This method is called at the beginning of each iteration loop. Returns: bool: Whether the iteration is finished """ if self._max_revs is not None and self._num_revs >= self._max_revs: return True if not self._revs_to_visit: return True return False def _get_rev(self, rev_id): rev = self._revs.get(rev_id) if rev is None: # cache some revisions in advance to avoid sending too much # requests to storage and thus speedup the revisions walk for rev in self.storage.revision_log([rev_id], limit=100): # revision data is missing, returned history will be truncated if rev is None: continue self._revs[rev["id"]] = rev return self._revs.get(rev_id) def missing_revisions(self): """ Return a set of revision identifiers whose associated data were found missing into the archive content while walking on the revisions graph. Returns: Set[bytes]: a set of revision identifiers """ return self._missing_revs def is_history_truncated(self): """ Return if the revision history generated so far has been truncated of not. A revision history might end up truncated if some revision data were found missing into the archive content. Returns: bool: Whether the history got truncated or not """ return len(self.missing_revisions()) > 0 def export_state(self): """ Export the internal state of that revision walker to a dict. Its purpose is to continue the iteration in a pagination context. Returns: dict: A dict containing the internal state of that revisions walker """ return { "revs_to_visit": self._revs_to_visit, "done": self._done, "last_rev": self._last_rev, "num_revs": self._num_revs, "missing_revs": self._missing_revs, } def __next__(self): if self.is_finished(): raise StopIteration while self._revs_to_visit: rev_id = self.get_next_rev_id() if rev_id in self._done: continue self._done.add(rev_id) rev = self._get_rev(rev_id) # revision data is missing, returned history will be truncated if rev is None: self._missing_revs.add(rev_id) continue self.process_parent_revs(rev) if self.should_return(rev): self._num_revs += 1 self._last_rev = rev return rev raise StopIteration def __iter__(self): return self class CommitterDateRevisionsWalker(RevisionsWalker): """ Revisions walker that returns revisions in reverse chronological order according to committer date (same behaviour as ``git log``) """ rw_type = "committer_date" def process_rev(self, rev_id): """ Add the revision to a priority queue according to the committer date. Args: rev_id (bytes): the newly visited revision identifier """ if rev_id not in self._done: rev = self._get_rev(rev_id) if rev is not None: commit_time = rev["committer_date"]["timestamp"]["seconds"] heapq.heappush(self._revs_to_visit, (-commit_time, rev_id)) else: self._missing_revs.add(rev_id) def get_next_rev_id(self): """ Return the smallest revision from the priority queue, i.e. the one with highest committer date. Returns: dict: A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` """ _, rev_id = heapq.heappop(self._revs_to_visit) return rev_id class BFSRevisionsWalker(RevisionsWalker): """ Revisions walker that returns revisions in the same order as when performing a breadth-first search on the revisions DAG. """ rw_type = "bfs" def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self._revs_to_visit = deque(self._revs_to_visit) def process_rev(self, rev_id): """ Append the revision to a queue. Args: rev_id (bytes): the newly visited revision identifier """ if rev_id not in self._done: self._revs_to_visit.append(rev_id) def get_next_rev_id(self): """ Return the next revision from the queue. Returns: dict: A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` """ return self._revs_to_visit.popleft() class DFSPostRevisionsWalker(RevisionsWalker): """ Revisions walker that returns revisions in the same order as when performing a depth-first search in post-order on the revisions DAG (i.e. after visiting a merge commit, the merged commit will be visited before the base it was merged on). """ rw_type = "dfs_post" def process_rev(self, rev_id): """ Append the revision to a stack. Args: rev_id (bytes): the newly visited revision identifier """ if rev_id not in self._done: self._revs_to_visit.append(rev_id) def get_next_rev_id(self): """ Return the next revision from the stack. Returns: dict: A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` """ return self._revs_to_visit.pop() class DFSRevisionsWalker(DFSPostRevisionsWalker): """ Revisions walker that returns revisions in the same order as when performing a depth-first search in pre-order on the revisions DAG (i.e. after visiting a merge commit, the base commit it was merged on will be visited before the merged commit). """ rw_type = "dfs" def process_parent_revs(self, rev): """ Process the parents of a revision when it is iterated in the reversed order they are declared. Args: rev (dict): A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` """ for parent_id in reversed(rev["parents"]): self.process_rev(parent_id) class PathRevisionsWalker(CommitterDateRevisionsWalker): """ Revisions walker that returns revisions where a specific path in the source tree has been modified, in other terms it allows to get the history for a specific file or directory. It has a behaviour similar to what ``git log`` offers by default, meaning the returned history is simplified in order to only show relevant revisions (see the `History Simplification `_ section of the associated manual for more details). Please note that to avoid walking the entire history, the iteration will stop once a revision where the path has been added is found. .. warning:: Due to client-side implementation, performances are not optimal when the total numbers of revisions to walk is large. This should only be used when the total number of revisions does not exceed a couple of thousands. Args: storage (swh.storage.interface.StorageInterface): instance of swh storage (either local or remote) rev_start (bytes): a revision identifier path (str): the path in the source tree to retrieve the history max_revs (Optional[int]): maximum number of revisions to return state (Optional[dict]): previous state of that revisions walker """ rw_type = "path" def __init__(self, storage, rev_start, path, **kwargs): super().__init__(storage, rev_start, **kwargs) paths = path.strip("/").split("/") self._path = list(map(lambda p: p.encode("utf-8"), paths)) self._rev_dir_path = {} def _get_path_id(self, rev_id): """ Return the path checksum identifier in the source tree of the provided revision. If the path corresponds to a directory, the value computed by :func:`swh.model.identifiers.directory_identifier` will be returned. If the path corresponds to a file, its sha1 checksum will be returned. Args: rev_id (bytes): a revision identifier Returns: bytes: the path identifier """ rev = self._get_rev(rev_id) rev_dir_id = rev["directory"] if rev_dir_id not in self._rev_dir_path: try: dir_info = self.storage.directory_entry_get_by_path( rev_dir_id, self._path ) self._rev_dir_path[rev_dir_id] = dir_info["target"] except Exception: self._rev_dir_path[rev_dir_id] = None return self._rev_dir_path[rev_dir_id] def is_finished(self): """ Check if the revisions iteration is finished. This checks for the specified path's existence in the last returned revision's parents' source trees. If not, the iteration is considered finished. Returns: bool: Whether to return the revision in the iteration """ if self._path and self._last_rev: last_rev_parents = self._last_rev["parents"] last_rev_parents_path_ids = [ self._get_path_id(p_rev) for p_rev in last_rev_parents ] no_path = all([path_id is None for path_id in last_rev_parents_path_ids]) if no_path: return True return super().is_finished() def process_parent_revs(self, rev): """ Process parents when a new revision is iterated. It enables to get a simplified revisions history in the same manner as ``git log``. When a revision has multiple parents, the following process is applied. If the revision was a merge, and has the same path identifier to one parent, follow only that parent (even if there are several parents with the same path identifier, follow only one of them.) Otherwise, follow all parents. Args: rev (dict): A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` """ rev_path_id = self._get_path_id(rev["id"]) if rev_path_id: if len(rev["parents"]) == 1: self.process_rev(rev["parents"][0]) else: parent_rev_path_ids = [ self._get_path_id(p_rev) for p_rev in rev["parents"] ] different_trees = all( [path_id != rev_path_id for path_id in parent_rev_path_ids] ) for i, p_rev in enumerate(rev["parents"]): if different_trees or parent_rev_path_ids[i] == rev_path_id: self.process_rev(p_rev) if not different_trees: break else: super().process_parent_revs(rev) def should_return(self, rev): """ Check if a revision should be returned when iterating. It verifies that the specified path has been modified by the revision but also that all parents have a path identifier different from the revision one in order to get a simplified history. Args: rev (dict): A dict describing a revision as returned by :meth:`swh.storage.interface.StorageInterface.revision_get` Returns: bool: Whether to return the revision in the iteration """ rev_path_id = self._get_path_id(rev["id"]) if not rev["parents"]: return rev_path_id is not None parent_rev_path_ids = [self._get_path_id(p_rev) for p_rev in rev["parents"]] different_trees = all( [path_id != rev_path_id for path_id in parent_rev_path_ids] ) if rev_path_id != parent_rev_path_ids[0] and different_trees: return True return False def get_revisions_walker(rev_walker_type, *args, **kwargs): """ Instantiate a revisions walker of a given type. The following code snippet demonstrates how to use a revisions walker for processing a whole revisions history:: from swh.storage import get_storage storage = get_storage(...) revs_walker = get_revisions_walker('committer_date', storage, rev_id) for rev in revs_walker: # process revision rev It is also possible to walk a revisions history in a paginated way as illustrated below:: def get_revs_history_page(rw_type, storage, rev_id, page_num, page_size, rw_state): max_revs = (page_num + 1) * page_size revs_walker = get_revisions_walker(rw_type, storage, rev_id, max_revs=max_revs, state=rw_state) revs = list(revs_walker) rw_state = revs_walker.export_state() return revs rev_start = ... per_page = 50 rw_state = {} for page in range(0, 10): revs_page = get_revs_history_page('dfs', storage, rev_start, page, per_page, rw_state) # process revisions page Args: rev_walker_type (str): the type of revisions walker to return, possible values are: *committer_date*, *dfs*, *dfs_post*, *bfs* and *path* args (list): position arguments to pass to the revisions walker constructor kwargs (dict): keyword arguments to pass to the revisions walker constructor """ if rev_walker_type not in _revs_walker_classes: raise Exception('No revisions walker found for type "%s"' % rev_walker_type) revs_walker_class = _revs_walker_classes[rev_walker_type] return revs_walker_class(*args, **kwargs) diff --git a/swh/storage/algos/snapshot.py b/swh/storage/algos/snapshot.py index 7c78111b..21d5607b 100644 --- a/swh/storage/algos/snapshot.py +++ b/swh/storage/algos/snapshot.py @@ -1,167 +1,166 @@ # 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, TargetType, ) - from swh.storage.algos.origin import ( - origin_get_latest_visit_status, - iter_origin_visits, 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_and_status = origin_get_latest_visit_status( storage, origin, allowed_statuses=allowed_statuses, require_snapshot=True, ) if not visit_and_status: return None _, visit_status = visit_and_status 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) diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 25cf33d6..1c8d1648 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,55 +1,54 @@ # 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 Any, Dict, Iterable, Union -from swh.core.api import RPCClient, RemoteException +from swh.core.api import RemoteException, RPCClient from swh.model.model import Content -from ..exc import StorageAPIError, StorageArgumentException, HashCollision +from ..exc import HashCollision, StorageAPIError, StorageArgumentException from ..interface import StorageInterface - -from .serializers import ENCODERS, DECODERS +from .serializers import DECODERS, ENCODERS class RemoteStorage(RPCClient): """Proxy to a remote storage API""" api_exception = StorageAPIError backend_class = StorageInterface reraise_exceptions = [ StorageArgumentException, ] extra_type_decoders = DECODERS extra_type_encoders = ENCODERS def raise_for_status(self, response) -> None: try: super().raise_for_status(response) except RemoteException as e: if ( e.response is not None and e.response.status_code == 500 and e.args and e.args[0].get("type") == "HashCollision" ): # XXX: workaround until we fix these HashCollisions happening # when they shouldn't raise HashCollision(*e.args[0]["args"]) else: raise def content_add(self, content: Iterable[Union[Content, Dict[str, Any]]]): content = [c.with_data() if isinstance(c, Content) else c for c in content] return self.post("content/add", {"content": content}) def reset(self): return self.post("reset", {}) def stat_counters(self): return self.get("stat/counters") def refresh_stat_counters(self): return self.get("stat/refresh") diff --git a/swh/storage/api/serializers.py b/swh/storage/api/serializers.py index abc458b3..ec10d1fb 100644 --- a/swh/storage/api/serializers.py +++ b/swh/storage/api/serializers.py @@ -1,52 +1,51 @@ # 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 """Decoder and encoders for swh-model objects.""" from typing import Callable, Dict, List, Tuple from swh.model.identifiers import SWHID, parse_swhid import swh.model.model as model - from swh.storage import interface def _encode_model_object(obj): d = obj.to_dict() d["__type__"] = type(obj).__name__ return d def _encode_enum(obj): return { "value": obj.value, "__type__": type(obj).__name__, } def _decode_model_enum(d): return getattr(model, d.pop("__type__"))(d["value"]) def _decode_storage_enum(d): return getattr(interface, d.pop("__type__"))(d["value"]) ENCODERS: List[Tuple[type, str, Callable]] = [ (model.BaseModel, "model", _encode_model_object), (SWHID, "swhid", str), (model.MetadataTargetType, "model_enum", _encode_enum), (model.MetadataAuthorityType, "model_enum", _encode_enum), (interface.ListOrder, "storage_enum", _encode_enum), ] DECODERS: Dict[str, Callable] = { "swhid": parse_swhid, "model": lambda d: getattr(model, d.pop("__type__")).from_dict(d), "model_enum": _decode_model_enum, "model_enum": _decode_model_enum, "storage_enum": _decode_storage_enum, } diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py index d64b16a2..d72723fb 100644 --- a/swh/storage/api/server.py +++ b/swh/storage/api/server.py @@ -1,128 +1,129 @@ # Copyright (C) 2015-2019 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 -import os import logging +import os 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 swh.core.api import RPCServerApp, error_handler, encode_data_server as encode_data +from ..exc import StorageArgumentException from ..interface import StorageInterface from ..metrics import timed -from ..exc import StorageArgumentException - -from .serializers import ENCODERS, DECODERS +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 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_file, type="local"): """Check the minimal configuration is set to run the api or raise an error explanation. Args: config_file (str): Path to the configuration file to load type (str): configuration type. For 'local' type, more checks are done. Raises: Error if the setup is not as expected Returns: configuration as a dict """ if not config_file: raise EnvironmentError("Configuration file must be defined") if not os.path.exists(config_file): raise FileNotFoundError("Configuration file %s does not exist" % (config_file,)) cfg = config.read(config_file) if "storage" not in cfg: raise KeyError("Missing '%storage' configuration") return cfg def make_app_from_configfile(): """Run the WSGI app from the webserver, loading the configuration from a configuration file. SWH_CONFIG_FILENAME environment variable defines the configuration path to load. """ global api_cfg if not api_cfg: config_file = os.environ.get("SWH_CONFIG_FILENAME") api_cfg = load_and_check_config(config_file) 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 90b1ba1e..76494861 100644 --- a/swh/storage/backfill.py +++ b/swh/storage/backfill.py @@ -1,548 +1,547 @@ # Copyright (C) 2017-2020 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 """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 from swh.core.db import BaseDb from swh.journal.writer.kafka import KafkaJournalWriter from swh.model.model import ( BaseModel, Directory, DirectoryEntry, RawExtrinsicMetadata, Release, Revision, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.postgresql.converters import ( db_to_raw_extrinsic_metadata, db_to_release, db_to_revision, ) from swh.storage.replay import object_converter_fn - logger = logging.getLogger(__name__) PARTITION_KEY = { "content": "sha1", "skipped_content": "sha1", "directory": "id", "metadata_authority": "type, url", "metadata_fetcher": "name, version", "raw_extrinsic_metadata": "id", "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"], "metadata_authority": ["type", "url", "metadata",], "metadata_fetcher": ["name", "version", "metadata",], "raw_extrinsic_metadata": [ "raw_extrinsic_metadata.type", "raw_extrinsic_metadata.id", "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", "date_neg_utc_offset", "committer_date", "committer_date_offset", "committer_date_neg_utc_offset", "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", ), ("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", "date_neg_utc_offset", "comment", ("release.name", "name"), "synthetic", "target", "target_type", ("a.id", "author_id"), ("a.name", "author_name"), ("a.email", "author_email"), ("a.fullname", "author_fullname"), ], "snapshot": ["id", "object_id"], "origin": ["url"], "origin_visit": ["visit", "type", ("origin.url", "origin"), "date",], "origin_visit_status": [ "visit", ("origin.url", "origin"), "date", "snapshot", "status", "metadata", ], } 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"], "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", ], } def directory_converter(db: BaseDb, directory_d: Dict[str, Any]) -> Directory: """Convert directory from the flat representation to swh model 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),) def raw_extrinsic_metadata_converter( db: BaseDb, metadata: Dict[str, Any] ) -> RawExtrinsicMetadata: """Convert revision from the flat representation to swh model compatible objects. """ return db_to_raw_extrinsic_metadata(metadata) def revision_converter(db: BaseDb, revision_d: Dict[str, Any]) -> Revision: """Convert revision from the flat representation to swh model 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. """ 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. """ 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"] or branch_d["target_type"]: branch = None else: branch = SnapshotBranch( target=branch_d["target"], target_type=TargetType(branch_d["target_type"]), ) branches[name] = branch return Snapshot(id=snapshot_d["id"], branches=branches,) CONVERTERS: Dict[str, Callable[[BaseDb, Dict[str, Any]], BaseModel]] = { "directory": directory_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, start_object=None, end_object=None): """Generate start/end pairs of bytes spanning numbits bits and constrained by optional start_object and end_object. Args: numbits (int): Number of bits in which we divide input space start_object (str): Hex object id contained in the first range returned end_object (str): 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 integer_ranges(start, end, block_size=1000): for start in range(start, end, block_size): if start == 0: yield None, block_size elif start + block_size > end: yield start, end else: yield start, start + block_size RANGE_GENERATORS = { "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), "revision": lambda start, end: byte_ranges(24, start, end), "release": lambda start, end: byte_ranges(16, start, end), "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) 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) 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_converter_fn[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 = ["brokers", "storage_dbconn", "prefix", "client_id"] class JournalBackfiller: """Class in charge of reading the storage's objects and sends those back to the journal's topics. 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),) ) 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(COLUMNS.keys())) ) if object_type in ["origin", "origin_visit"]: if start_object: start_object = int(start_object) else: start_object = 0 if end_object: end_object = int(end_object) else: end_object = 100 * 1000 * 1000 # 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. """ start_object, end_object = self.parse_arguments( object_type, start_object, end_object ) db = BaseDb.connect(self.config["storage_dbconn"]) writer = KafkaJournalWriter( brokers=self.config["brokers"], prefix=self.config["prefix"], client_id=self.config["client_id"], ) 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), ) for obj in fetch(db, object_type, start=range_start, end=range_end,): if dry_run: continue writer.write_addition(object_type=object_type, object_=obj) writer.producer.flush() if __name__ == "__main__": print('Please use the "swh-journal backfiller run" command') diff --git a/swh/storage/buffer.py b/swh/storage/buffer.py index f1de11d5..95702570 100644 --- a/swh/storage/buffer.py +++ b/swh/storage/buffer.py @@ -1,152 +1,152 @@ # 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 from typing import Dict, Iterable, List, Optional from swh.core.utils import grouper -from swh.model.model import Content, BaseModel +from swh.model.model import BaseModel, Content from swh.storage import get_storage from swh.storage.interface import StorageInterface class BufferingProxyStorage: """Storage implementation in charge of accumulating objects prior to discussing with the "main" storage. 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 revision: 1000 release: 10000 """ def __init__(self, storage, min_batch_size=None): self.storage: StorageInterface = get_storage(**storage) if min_batch_size is None: min_batch_size = {} self.min_batch_size = { "content": min_batch_size.get("content", 10000), "content_bytes": min_batch_size.get("content_bytes", 100 * 1024 * 1024), "skipped_content": min_batch_size.get("skipped_content", 10000), "directory": min_batch_size.get("directory", 25000), "revision": min_batch_size.get("revision", 100000), "release": min_batch_size.get("release", 100000), } self.object_types = [ "content", "skipped_content", "directory", "revision", "release", ] self._objects = {k: {} for k in self.object_types} def __getattr__(self, key): if key.endswith("_add"): object_type = key.rsplit("_", 1)[0] if object_type in self.object_types: 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, content: List[Content]) -> Dict: """Enqueue contents to write to the storage. Following policies apply: - First, check if the queue's threshold is hit. If it is flush content to the storage. - If not, check if the total size of enqueued contents's threshold is hit. If it is flush content to the storage. """ s = self.object_add( content, object_type="content", keys=["sha1", "sha1_git", "sha256", "blake2s256"], ) if not s: buffer_ = self._objects["content"].values() total_size = sum(c.length for c in buffer_) if total_size >= self.min_batch_size["content_bytes"]: return self.flush(["content"]) return s def skipped_content_add(self, content: List[Content]) -> Dict: return self.object_add( content, object_type="skipped_content", keys=["sha1", "sha1_git", "sha256", "blake2s256"], ) def flush(self, object_types: Optional[List[str]] = None) -> Dict: summary: Dict[str, int] = self.storage.flush(object_types) if object_types is None: object_types = self.object_types for object_type in object_types: buffer_ = self._objects[object_type] batches = grouper(buffer_.values(), n=self.min_batch_size[object_type]) for batch in batches: add_fn = getattr(self.storage, "%s_add" % object_type) s = add_fn(list(batch)) summary = {k: v + summary.get(k, 0) for k, v in s.items()} buffer_.clear() return summary def object_add( self, objects: Iterable[BaseModel], *, object_type: str, keys: List[str] ) -> Dict: """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. """ buffer_ = self._objects[object_type] threshold = self.min_batch_size[object_type] for obj in objects: obj_key = tuple(getattr(obj, key) for key in keys) buffer_[obj_key] = obj if len(buffer_) >= threshold: return self.flush() return {} def clear_buffers(self, object_types: Optional[List[str]] = None) -> 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. """ if object_types is None: object_types = self.object_types for object_type in object_types: q = self._objects[object_type] q.clear() return self.storage.clear_buffers(object_types) diff --git a/swh/storage/cassandra/__init__.py b/swh/storage/cassandra/__init__.py index 2b6783dd..7de25cb7 100644 --- a/swh/storage/cassandra/__init__.py +++ b/swh/storage/cassandra/__init__.py @@ -1,11 +1,10 @@ # 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 .cql import create_keyspace from .storage import CassandraStorage - __all__ = ["create_keyspace", "CassandraStorage"] diff --git a/swh/storage/cassandra/common.py b/swh/storage/cassandra/common.py index 58e5e60d..dfcec0ff 100644 --- a/swh/storage/cassandra/common.py +++ b/swh/storage/cassandra/common.py @@ -1,22 +1,21 @@ # 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 from typing import Any, Dict, Tuple - TOKEN_BEGIN = -(2 ** 63) """Minimum value returned by the CQL function token()""" TOKEN_END = 2 ** 63 - 1 """Maximum value returned by the CQL function token()""" def hash_url(url: str) -> bytes: return hashlib.sha1(url.encode("ascii")).digest() def remove_keys(d: Dict[str, Any], keys: Tuple[str, ...]) -> Dict[str, Any]: return {k: v for (k, v) in d.items() if k not in keys} diff --git a/swh/storage/cassandra/converters.py b/swh/storage/cassandra/converters.py index 75324ca0..5972c393 100644 --- a/swh/storage/cassandra/converters.py +++ b/swh/storage/cassandra/converters.py @@ -1,113 +1,113 @@ # 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 -import attr - -from copy import deepcopy from typing import Dict, Tuple +import attr + +from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.model.model import ( ObjectType, OriginVisit, OriginVisitStatus, + Release, Revision, RevisionType, - Release, Sha1Git, ) -from swh.model.hashutil import DEFAULT_ALGORITHMS from .common import remove_keys -from .model import OriginVisitRow, OriginVisitStatusRow, RevisionRow, ReleaseRow +from .model import OriginVisitRow, OriginVisitStatusRow, 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,) def row_to_content_hashes(row: ReleaseRow) -> Dict[str, bytes]: """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. """ 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. """ 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"])}) diff --git a/swh/storage/cassandra/cql.py b/swh/storage/cassandra/cql.py index 9ea99fe6..560de43a 100644 --- a/swh/storage/cassandra/cql.py +++ b/swh/storage/cassandra/cql.py @@ -1,975 +1,973 @@ # 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 random from typing import ( Any, Callable, Dict, Iterable, Iterator, List, Optional, Tuple, Type, TypeVar, Union, ) from cassandra import CoordinationFailure -from cassandra.cluster import Cluster, EXEC_PROFILE_DEFAULT, ExecutionProfile, ResultSet +from cassandra.cluster import EXEC_PROFILE_DEFAULT, Cluster, ExecutionProfile, ResultSet from cassandra.policies import DCAwareRoundRobinPolicy, TokenAwarePolicy -from cassandra.query import PreparedStatement, BoundStatement, dict_factory +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, - retry_if_exception_type, ) -from mypy_extensions import NamedArg from swh.model.model import ( Content, - SkippedContent, + Person, Sha1Git, - TimestampWithTimezone, + SkippedContent, Timestamp, - Person, + TimestampWithTimezone, ) - from swh.storage.interface import ListOrder from .common import TOKEN_BEGIN, TOKEN_END, hash_url, remove_keys from .model import ( + MAGIC_NULL_PK, BaseRow, ContentRow, DirectoryEntryRow, DirectoryRow, - MAGIC_NULL_PK, MetadataAuthorityRow, MetadataFetcherRow, ObjectCountRow, OriginRow, OriginVisitRow, OriginVisitStatusRow, RawExtrinsicMetadataRow, ReleaseRow, RevisionParentRow, RevisionRow, SkippedContentRow, SnapshotBranchRow, SnapshotRow, ) from .schema import CREATE_TABLES_QUERIES, HASH_ALGORITHMS - logger = logging.getLogger(__name__) _execution_profiles = { EXEC_PROFILE_DEFAULT: ExecutionProfile( load_balancing_policy=TokenAwarePolicy(DCAwareRoundRobinPolicy()), row_factory=dict_factory, ), } # 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=_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 _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.""" columns = row_class.cols() return _prepared_statement( "INSERT INTO %s (%s) VALUES (%s)" % (row_class.TABLE, ", ".join(columns), ", ".join("?" for _ in columns),) ) 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 IN ?") def _prepared_select_statement( 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], ) -> 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 class CqlRunner: """Class managing prepared statements and building queries to be sent to Cassandra.""" def __init__(self, hosts: List[str], keyspace: str, port: int): self._cluster = Cluster( hosts, port=port, execution_profiles=_execution_profiles ) 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) -> ResultSet: return self._session.execute(statement, args, timeout=1000.0) @_prepared_statement( "UPDATE object_count SET count = count + ? " "WHERE partition_key = 0 AND object_type = ?" ) def _increment_counter( self, object_type: str, nb: int, *, statement: PreparedStatement ) -> None: self._execute_with_retries(statement, [nb, object_type]) def _add_one(self, statement, obj: BaseRow) -> None: self._increment_counter(obj.TABLE, 1) self._execute_with_retries(statement, dataclasses.astuple(obj)) _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, ids): rows = self._execute_with_retries(statement, [ids]) found_ids = {row["id"] for row in rows} 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) self._increment_counter("content", 1) @_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 @_prepared_select_statement( ContentRow, f"WHERE token({', '.join(ContentRow.PARTITION_KEY)}) = ?" ) def content_get_from_token(self, token, *, statement) -> Iterable[ContentRow]: return map(ContentRow.from_dict, self._execute_with_retries(statement, [token])) @_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({0}) AS tok, {1} FROM content " "WHERE token({0}) >= ? AND token({0}) <= ? LIMIT ?" ).format(", ".join(ContentRow.PARTITION_KEY), ", ".join(ContentRow.cols())) ) 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 ########################## @_prepared_statement( "SELECT sha1_git AS id FROM content_by_sha1_git WHERE sha1_git IN ?" ) def content_missing_by_sha1_git( self, ids: List[bytes], *, statement ) -> List[bytes]: return self._missing(statement, ids) 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_by_{algo} ({algo}, target_token) " f"VALUES (%s, %s)" ) self._execute_with_retries(query, [content.get_hash(algo), token]) def 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_by_{algo} WHERE {algo} = %s" return ( row["target_token"] for row in self._execute_with_retries(query, [hash_]) ) ########################## # '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) self._increment_counter("skipped_content", 1) @_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 skipped_content_by_{algo} 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("SELECT id FROM revision 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("SELECT parent_id FROM revision_parent 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[str], *, 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) ########################## # 'directory_entry' table ########################## @_prepared_insert_statement(DirectoryEntryRow) def directory_entry_add_one(self, entry: DirectoryEntryRow, *, statement) -> None: self._add_one(statement, entry) @_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]), ) ########################## # '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( "SELECT ascii_bins_count(target_type) AS counts " "FROM snapshot_branch " "WHERE snapshot_id = ? " ) def snapshot_count_branches( self, snapshot_id: Sha1Git, *, statement ) -> Dict[Optional[str], int]: """Returns a dictionary from type names to the number of branches of that type.""" row = self._execute_with_retries(statement, [snapshot_id]).one() (nb_none, counts) = row["counts"] return {None: nb_none, **counts} @_prepared_select_statement( SnapshotBranchRow, "WHERE snapshot_id = ? AND name >= ? LIMIT ?" ) def snapshot_branch_get( 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]), ) ########################## # '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())} ' f"FROM origin 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("SELECT next_visit_id FROM origin 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( "UPDATE origin 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 = ?") def origin_visit_get_all( self, origin_url: str, *, statement ) -> Iterable[OriginVisitRow]: 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_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, ) -> Optional[OriginVisitStatusRow]: """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, "WHERE origin = ? AND visit = ? ORDER BY date DESC" ) def origin_visit_status_get( self, origin: str, visit: int, *, statement, ) -> Iterator[OriginVisitStatusRow]: """Return all origin visit statuses for a given visit """ return map( OriginVisitStatusRow.from_dict, self._execute_with_retries(statement, [origin, visit]), ) ########################## # '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' 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 id=? AND authority_url=? AND discovery_date>? AND authority_type=?", ) def raw_extrinsic_metadata_get_after_date( self, id: str, authority_type: str, authority_url: str, after: datetime.datetime, *, statement, ) -> Iterable[RawExtrinsicMetadataRow]: return map( RawExtrinsicMetadataRow.from_dict, self._execute_with_retries( statement, [id, authority_url, after, authority_type] ), ) @_prepared_select_statement( RawExtrinsicMetadataRow, "WHERE id=? AND authority_type=? AND authority_url=? " "AND (discovery_date, fetcher_name, fetcher_version) > (?, ?, ?)", ) def raw_extrinsic_metadata_get_after_date_and_fetcher( self, id: str, authority_type: str, authority_url: str, after_date: datetime.datetime, after_fetcher_name: str, after_fetcher_version: str, *, statement, ) -> Iterable[RawExtrinsicMetadataRow]: return map( RawExtrinsicMetadataRow.from_dict, self._execute_with_retries( statement, [ id, authority_type, authority_url, after_date, after_fetcher_name, after_fetcher_version, ], ), ) @_prepared_select_statement( RawExtrinsicMetadataRow, "WHERE id=? AND authority_url=? AND authority_type=?" ) def raw_extrinsic_metadata_get( self, id: str, authority_type: str, authority_url: str, *, statement ) -> Iterable[RawExtrinsicMetadataRow]: return map( RawExtrinsicMetadataRow.from_dict, self._execute_with_retries(statement, [id, authority_url, authority_type]), ) ########################## # Miscellaneous ########################## @_prepared_statement("SELECT uuid() FROM revision LIMIT 1;") def check_read(self, *, statement): self._execute_with_retries(statement, []) @_prepared_select_statement(ObjectCountRow, "WHERE partition_key=0") def stat_counters(self, *, statement) -> Iterable[ObjectCountRow]: return map(ObjectCountRow.from_dict, self._execute_with_retries(statement, [])) diff --git a/swh/storage/cassandra/model.py b/swh/storage/cassandra/model.py index fddd1c2a..500b147c 100644 --- a/swh/storage/cassandra/model.py +++ b/swh/storage/cassandra/model.py @@ -1,278 +1,277 @@ # 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 """Classes representing tables in the Cassandra database. They are very close to classes found in swh.model.model, but most of them are subtly different: * Large objects are split into other classes (eg. RevisionRow has no 'parents' field, because parents are stored in a different table, represented by RevisionParentRow) * They have a "cols" field, which returns the list of column names of the table * They only use types that map directly to Cassandra's schema (ie. no enums) Therefore, this model doesn't reuse swh.model.model, except for types that can be mapped to UDTs (Person and TimestampWithTimezone). """ import dataclasses import datetime from typing import Any, ClassVar, Dict, List, Optional, Tuple, Type, TypeVar from swh.model.model import Person, TimestampWithTimezone - MAGIC_NULL_PK = b"" """ NULLs (or all-empty blobs) are not allowed in primary keys; instead we use a special value that can't possibly be a valid hash. """ T = TypeVar("T", bound="BaseRow") class BaseRow: TABLE: ClassVar[str] PARTITION_KEY: ClassVar[Tuple[str, ...]] CLUSTERING_KEY: ClassVar[Tuple[str, ...]] = () @classmethod def from_dict(cls: Type[T], d: Dict[str, Any]) -> T: return cls(**d) # type: ignore @classmethod def cols(cls) -> List[str]: return [field.name for field in dataclasses.fields(cls)] def to_dict(self) -> Dict[str, Any]: return dataclasses.asdict(self) @dataclasses.dataclass class ContentRow(BaseRow): TABLE = "content" PARTITION_KEY = ("sha1", "sha1_git", "sha256", "blake2s256") sha1: bytes sha1_git: bytes sha256: bytes blake2s256: bytes length: int ctime: datetime.datetime status: str @dataclasses.dataclass class SkippedContentRow(BaseRow): TABLE = "skipped_content" PARTITION_KEY = ("sha1", "sha1_git", "sha256", "blake2s256") sha1: Optional[bytes] sha1_git: Optional[bytes] sha256: Optional[bytes] blake2s256: Optional[bytes] length: Optional[int] ctime: Optional[datetime.datetime] status: str reason: str origin: str @classmethod def from_dict(cls, d: Dict[str, Any]) -> "SkippedContentRow": d = d.copy() for k in ("sha1", "sha1_git", "sha256", "blake2s256"): if d[k] == MAGIC_NULL_PK: d[k] = None return super().from_dict(d) @dataclasses.dataclass class DirectoryRow(BaseRow): TABLE = "directory" PARTITION_KEY = ("id",) id: bytes @dataclasses.dataclass class DirectoryEntryRow(BaseRow): TABLE = "directory_entry" PARTITION_KEY = ("directory_id",) CLUSTERING_KEY = ("name",) directory_id: bytes name: bytes target: bytes perms: int type: str @dataclasses.dataclass class RevisionRow(BaseRow): TABLE = "revision" PARTITION_KEY = ("id",) id: bytes date: Optional[TimestampWithTimezone] committer_date: Optional[TimestampWithTimezone] type: str directory: bytes message: bytes author: Person committer: Person synthetic: bool metadata: str extra_headers: dict @dataclasses.dataclass class RevisionParentRow(BaseRow): TABLE = "revision_parent" PARTITION_KEY = ("id",) CLUSTERING_KEY = ("parent_rank",) id: bytes parent_rank: int parent_id: bytes @dataclasses.dataclass class ReleaseRow(BaseRow): TABLE = "release" PARTITION_KEY = ("id",) id: bytes target_type: str target: bytes date: TimestampWithTimezone name: bytes message: bytes author: Person synthetic: bool @dataclasses.dataclass class SnapshotRow(BaseRow): TABLE = "snapshot" PARTITION_KEY = ("id",) id: bytes @dataclasses.dataclass class SnapshotBranchRow(BaseRow): TABLE = "snapshot_branch" PARTITION_KEY = ("snapshot_id",) CLUSTERING_KEY = ("name",) snapshot_id: bytes name: bytes target_type: Optional[str] target: Optional[bytes] @dataclasses.dataclass class OriginVisitRow(BaseRow): TABLE = "origin_visit" PARTITION_KEY = ("origin",) CLUSTERING_KEY = ("visit",) origin: str visit: int date: datetime.datetime type: str @dataclasses.dataclass class OriginVisitStatusRow(BaseRow): TABLE = "origin_visit_status" PARTITION_KEY = ("origin",) CLUSTERING_KEY = ("visit", "date") origin: str visit: int date: datetime.datetime status: str metadata: str snapshot: bytes @dataclasses.dataclass class OriginRow(BaseRow): TABLE = "origin" PARTITION_KEY = ("sha1",) sha1: bytes url: str next_visit_id: int @dataclasses.dataclass class MetadataAuthorityRow(BaseRow): TABLE = "metadata_authority" PARTITION_KEY = ("url",) CLUSTERING_KEY = ("type",) url: str type: str metadata: str @dataclasses.dataclass class MetadataFetcherRow(BaseRow): TABLE = "metadata_fetcher" PARTITION_KEY = ("name",) CLUSTERING_KEY = ("version",) name: str version: str metadata: str @dataclasses.dataclass class RawExtrinsicMetadataRow(BaseRow): TABLE = "raw_extrinsic_metadata" PARTITION_KEY = ("id",) CLUSTERING_KEY = ( "authority_type", "authority_url", "discovery_date", "fetcher_name", "fetcher_version", ) type: str id: str authority_type: str authority_url: str discovery_date: datetime.datetime fetcher_name: str fetcher_version: str 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] @dataclasses.dataclass class ObjectCountRow(BaseRow): TABLE = "object_count" PARTITION_KEY = ("partition_key",) CLUSTERING_KEY = ("object_type",) partition_key: int object_type: str count: int diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py index 69f02860..2319ff0b 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,1314 +1,1313 @@ # 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 base64 import datetime import itertools import json import random import re -from typing import Any, Callable, Dict, List, Iterable, Optional, Set, Tuple, Union +from typing import Any, Callable, Dict, Iterable, List, Optional, Set, Tuple, Union import attr -from swh.core.api.serializers import msgpack_loads, msgpack_dumps -from swh.model.identifiers import parse_swhid, SWHID +from swh.core.api.serializers import msgpack_dumps, msgpack_loads from swh.model.hashutil import DEFAULT_ALGORITHMS +from swh.model.identifiers import SWHID, parse_swhid from swh.model.model import ( - Revision, - Release, + Content, Directory, DirectoryEntry, - Content, - SkippedContent, - OriginVisit, - OriginVisitStatus, - Snapshot, - SnapshotBranch, - TargetType, - Origin, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, + Origin, + OriginVisit, + OriginVisitStatus, RawExtrinsicMetadata, + Release, + Revision, Sha1Git, + SkippedContent, + Snapshot, + SnapshotBranch, + TargetType, ) from swh.storage.interface import ( + VISIT_STATUSES, ListOrder, PagedResult, PartialBranches, Sha1, - VISIT_STATUSES, ) from swh.storage.objstorage import ObjStorage -from swh.storage.writer import JournalWriter from swh.storage.utils import map_optional, now +from swh.storage.writer import JournalWriter -from ..exc import StorageArgumentException, HashCollision -from .common import TOKEN_BEGIN, TOKEN_END, hash_url, remove_keys from . import converters +from ..exc import HashCollision, StorageArgumentException +from .common import TOKEN_BEGIN, TOKEN_END, hash_url, remove_keys from .cql import CqlRunner -from .schema import HASH_ALGORITHMS from .model import ( ContentRow, DirectoryEntryRow, DirectoryRow, MetadataAuthorityRow, MetadataFetcherRow, OriginRow, OriginVisitRow, OriginVisitStatusRow, RawExtrinsicMetadataRow, RevisionParentRow, SkippedContentRow, SnapshotBranchRow, SnapshotRow, ) - +from .schema import HASH_ALGORITHMS # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 class CassandraStorage: def __init__(self, hosts, keyspace, objstorage, port=9042, journal_writer=None): self._cql_runner: CqlRunner = CqlRunner(hosts, keyspace, port) self.journal_writer: JournalWriter = JournalWriter(journal_writer) self.objstorage: ObjStorage = ObjStorage(objstorage) def check_config(self, *, check_write: bool) -> bool: self._cql_runner.check_read() return True def _content_get_from_hash(self, algo, hash_) -> 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 = self._cql_runner.content_get_tokens_from_single_hash(algo, hash_) for token in found_tokens: assert isinstance(token, int), found_tokens # Query the main table ('content'). res = self._cql_runner.content_get_from_token(token) for row in res: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) == hash_: yield row def _content_add(self, contents: List[Content], with_data: bool) -> Dict: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.content_get_from_pk(c.to_dict()) ] self.journal_writer.content_add(contents) if with_data: # First insert to the objstorage, if the endpoint is # `content_add` (as opposed to `content_add_metadata`). # TODO: this should probably be done in concurrently to inserting # in index tables (but still before the main table; so an entry is # only added to the main table after everything else was # successfully inserted. summary = self.objstorage.content_add( c for c in contents if c.status != "absent" ) content_add_bytes = summary["content:add:bytes"] 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) for algo in {"sha1", "sha1_git"}: collisions = [] # Get tokens of 'content' rows with the same value for # sha1/sha1_git rows = self._content_get_from_hash(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: contents = [attr.evolve(c, ctime=now()) for c in content] 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: 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[Sha1]) -> List[Optional[Content]]: contents_by_sha1: Dict[Sha1, Optional[Content]] = {} for sha1 in contents: # Get all (sha1, sha1_git, sha256, blake2s256) whose sha1 # matches the argument, from the index table ('content_by_sha1') for row in self._content_get_from_hash("sha1", sha1): row_d = row.to_dict() row_d.pop("ctime") content = Content(**row_d) contents_by_sha1[content.sha1] = content return [contents_by_sha1.get(sha1) for sha1 in contents] def content_find(self, content: 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. filter_algos = list(set(content).intersection(HASH_ALGORITHMS)) if not filter_algos: raise StorageArgumentException( "content keys must contain at least one " f"of: {', '.join(sorted(HASH_ALGORITHMS))}" ) common_algo = filter_algos[0] results = [] rows = self._content_get_from_hash(common_algo, content[common_algo]) 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 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)) 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)}" ) for content in contents: res = self.content_find(content) if not res: yield 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: # Filter-out content already in the database. 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: 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: # Filter out directories that are already inserted. missing = self.directory_missing([dir_.id for dir_ in directories]) 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 for entry in directory.entries: self._cql_runner.directory_entry_add_one( DirectoryEntryRow(directory_id=directory.id, **entry.to_dict()) ) # 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)) 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) -> Dict[str, Any]: contents: Union[List[Content], List[SkippedContentRow]] keys = ( "status", "sha1", "sha1_git", "sha256", "length", ) ret = dict.fromkeys(keys) ret.update(dentry.to_dict()) if ret["type"] == "file": contents = self.content_find({"sha1_git": ret["target"]}) if not contents: tokens = list( self._cql_runner.skipped_content_get_tokens_from_single_hash( "sha1_git", ret["target"] ) ) if tokens: contents = list( self._cql_runner.skipped_content_get_from_token(tokens[0]) ) if contents: content = contents[0] 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])) 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) 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_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: # Filter-out revisions already in the database missing = self.revision_missing([rev.id for rev in revisions]) 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]) -> 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, ...]]], ]: 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], 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: to_add = [] for rel in releases: if rel not in to_add: to_add.append(rel) missing = set(self.release_missing([rel.id for rel in to_add])) to_add = [rel for rel in to_add if rel.id in missing] self.journal_writer.release_add(to_add) for release in to_add: if release: self._cql_runner.release_add_one(converters.release_to_db(release)) return {"release:add": len(to_add)} def release_missing(self, releases: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.release_missing(releases) def release_get(self, releases: List[Sha1Git]) -> 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: missing = self._cql_runner.snapshot_missing([snp.id for snp in snapshots]) 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 ) -> 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) def snapshot_get_branches( self, snapshot_id: Sha1Git, branches_from: bytes = b"", branches_count: int = 1000, target_types: Optional[List[str]] = 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 ) ) 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 ] 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]], List[Sha1Git]]]] = [ ("revision", self._cql_runner.revision_missing), ("release", self._cql_runner.release_missing), ("content", self._cql_runner.content_missing_by_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,} ) 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 """ 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, ) -> 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] 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_add(self, origins: List[Origin]) -> Dict[str, int]: to_add = [ori for ori in origins if self.origin_get_one(ori.url) is None] # keep only one occurrence of each given origin while keeping the list # sorted as originally given to_add = sorted(set(to_add), key=to_add.index) self.journal_writer.origin_add(to_add) for origin in to_add: self._cql_runner.origin_add_one( OriginRow(sha1=hash_url(origin.url), url=origin.url, next_visit_id=1) ) return {"origin:add": len(to_add)} 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 = [] nb_visits = 0 for visit in visits: nb_visits += 1 if not visit.visit: 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, status="created", snapshot=None, ) ) return all_visits def _origin_visit_status_add(self, visit_status: OriginVisitStatus) -> None: """Add an origin visit status""" 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]) -> None: # 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) 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"], } def _origin_visit_get_latest_status(self, visit: OriginVisit) -> OriginVisitStatus: """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_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_get_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" ) # TODO: Do not fetch all visits rows = self._cql_runner.origin_visit_get_all(origin) latest_visit = None 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 # updated_visit is a candidate if latest_visit is not None: if updated_visit["date"] < latest_visit["date"]: continue if updated_visit["visit"] < latest_visit["visit"]: continue latest_visit = updated_visit if latest_visit is None: return None return OriginVisit( origin=latest_visit["origin"], visit=latest_visit["visit"], date=latest_visit["date"], type=latest_visit["type"], ) 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[Tuple[OriginVisit, 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, 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]) -> None: self.journal_writer.raw_extrinsic_metadata_add(metadata) 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( type=metadata_entry.type.value, id=str(metadata_entry.id), 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), ) self._cql_runner.raw_extrinsic_metadata_add(row) except TypeError as e: raise StorageArgumentException(*e.args) def raw_extrinsic_metadata_get( self, type: MetadataTargetType, id: Union[str, SWHID], authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, ) -> PagedResult[RawExtrinsicMetadata]: if type == MetadataTargetType.ORIGIN: if isinstance(id, SWHID): raise StorageArgumentException( f"raw_extrinsic_metadata_get called with type='origin', " f"but provided id is an SWHID: {id!r}" ) else: if not isinstance(id, SWHID): raise StorageArgumentException( f"raw_extrinsic_metadata_get called with type!='origin', " f"but provided id is not an SWHID: {id!r}" ) if page_token is not None: (after_date, after_fetcher_name, after_fetcher_url) = 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_fetcher( # noqa str(id), authority.type.value, authority.url, after_date, after_fetcher_name, after_fetcher_url, ) elif after is not None: entries = self._cql_runner.raw_extrinsic_metadata_get_after_date( str(id), authority.type.value, authority.url, after ) else: entries = self._cql_runner.raw_extrinsic_metadata_get( str(id), authority.type.value, authority.url ) if limit: entries = itertools.islice(entries, 0, limit + 1) results = [] for entry in entries: discovery_date = entry.discovery_date.replace(tzinfo=datetime.timezone.utc) assert str(id) == entry.id result = RawExtrinsicMetadata( type=MetadataTargetType(entry.type), id=id, authority=MetadataAuthority( type=MetadataAuthorityType(entry.authority_type), url=entry.authority_url, ), fetcher=MetadataFetcher( name=entry.fetcher_name, version=entry.fetcher_version, ), discovery_date=discovery_date, format=entry.format, metadata=entry.metadata, origin=entry.origin, visit=entry.visit, snapshot=map_optional(parse_swhid, entry.snapshot), release=map_optional(parse_swhid, entry.release), revision=map_optional(parse_swhid, entry.revision), path=entry.path, directory=map_optional(parse_swhid, entry.directory), ) results.append(result) 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.fetcher.name, last_result.fetcher.version, ) ) ).decode() else: next_page_token = None return PagedResult(next_page_token=next_page_token, results=results,) def metadata_fetcher_add(self, fetchers: List[MetadataFetcher]) -> None: self.journal_writer.metadata_fetcher_add(fetchers) for fetcher in fetchers: self._cql_runner.metadata_fetcher_add( MetadataFetcherRow( name=fetcher.name, version=fetcher.version, metadata=json.dumps(map_optional(dict, fetcher.metadata)), ) ) 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, metadata=json.loads(fetcher.metadata), ) else: return None def metadata_authority_add(self, authorities: List[MetadataAuthority]) -> None: 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, metadata=json.dumps(map_optional(dict, authority.metadata)), ) ) 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, metadata=json.loads(authority.metadata), ) else: return None def clear_buffers(self, object_types: Optional[List[str]] = None) -> None: """Do nothing """ return None def flush(self, object_types: Optional[List[str]] = None) -> Dict: return {} diff --git a/swh/storage/cli.py b/swh/storage/cli.py index f191e8d3..44f03a4d 100644 --- a/swh/storage/cli.py +++ b/swh/storage/cli.py @@ -1,226 +1,225 @@ # 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 try: from systemd.daemon import notify except ImportError: notify = None @click.group(name="storage", context_settings=CONTEXT_SETTINGS) @click.option( "--config-file", "-C", default=None, 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.pass_context def replay(ctx, stop_after_objects): """Fill a Storage by reading a Journal. There can be several 'replayers' filling a Storage as long as they use the same `group-id`. """ 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") 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 7edf3cbc..d15765f6 100644 --- a/swh/storage/exc.py +++ b/swh/storage/exc.py @@ -1,50 +1,49 @@ # 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_hex_hashes, content_bytes_hashes +from swh.storage.utils import content_bytes_hashes, content_hex_hashes class StorageDBError(Exception): """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) """ 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 """ 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/filter.py b/swh/storage/filter.py index 2a35723b..6964f367 100644 --- a/swh/storage/filter.py +++ b/swh/storage/filter.py @@ -1,123 +1,116 @@ # 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, - SkippedContent, - Directory, - Revision, - Sha1Git, -) - +from swh.model.model import Content, Directory, 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"] 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: contents_to_add = self._filter_missing_contents(content) 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: contents_to_add = self._filter_missing_skipped_contents(content) 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: missing_ids = self._filter_missing_ids("directory", (d.id for d in directories)) return self.storage.directory_add( [d for d in directories if d.id in missing_ids] ) def revision_add(self, revisions: List[Revision]) -> Dict: missing_ids = self._filter_missing_ids("revision", (r.id for r in revisions)) return self.storage.revision_add([r for r in revisions 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",)) 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 """ missing_ids = [] for id in ids: missing_ids.append(id) fn_by_object_type = { "revision": self.storage.revision_missing, "directory": self.storage.directory_missing, } fn = fn_by_object_type[object_type] return set(fn(missing_ids)) diff --git a/swh/storage/fixer.py b/swh/storage/fixer.py index 45826859..a719954a 100644 --- a/swh/storage/fixer.py +++ b/swh/storage/fixer.py @@ -1,308 +1,308 @@ # 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 datetime import logging - from typing import Any, Dict, List, Optional + from swh.model.identifiers import normalize_timestamp logger = logging.getLogger(__name__) def _fix_content(content: Dict[str, Any]) -> Dict[str, Any]: """Filters-out invalid 'perms' key that leaked from swh.model.from_disk to the journal. >>> _fix_content({'perms': 0o100644, 'sha1_git': b'foo'}) {'sha1_git': b'foo'} >>> _fix_content({'sha1_git': b'bar'}) {'sha1_git': b'bar'} """ content = content.copy() content.pop("perms", None) return content def _fix_revision_pypi_empty_string(rev): """PyPI loader failed to encode empty strings as bytes, see: swh:1:rev:8f0095ee0664867055d03de9bcc8f95b91d8a2b9 or https://forge.softwareheritage.org/D1772 """ rev = { **rev, "author": rev["author"].copy(), "committer": rev["committer"].copy(), } if rev["author"].get("email") == "": rev["author"]["email"] = b"" if rev["author"].get("name") == "": rev["author"]["name"] = b"" if rev["committer"].get("email") == "": rev["committer"]["email"] = b"" if rev["committer"].get("name") == "": rev["committer"]["name"] = b"" return rev def _fix_revision_transplant_source(rev): if rev.get("metadata") and rev["metadata"].get("extra_headers"): rev = copy.deepcopy(rev) rev["metadata"]["extra_headers"] = [ [key, value.encode("ascii")] if key == "transplant_source" and isinstance(value, str) else [key, value] for (key, value) in rev["metadata"]["extra_headers"] ] return rev def _check_date(date): """Returns whether the date can be represented in backends with sane limits on timestamps and timezones (resp. signed 64-bits and signed 16 bits), and that microseconds is valid (ie. between 0 and 10^6). """ if date is None: return True date = normalize_timestamp(date) return ( (-(2 ** 63) <= date["timestamp"]["seconds"] < 2 ** 63) and (0 <= date["timestamp"]["microseconds"] < 10 ** 6) and (-(2 ** 15) <= date["offset"] < 2 ** 15) ) def _check_revision_date(rev): """Exclude revisions with invalid dates. See https://forge.softwareheritage.org/T1339""" return _check_date(rev["date"]) and _check_date(rev["committer_date"]) def _fix_revision(revision: Dict[str, Any]) -> Optional[Dict]: """Fix various legacy revision issues. Fix author/committer person: >>> from pprint import pprint >>> date = { ... 'timestamp': { ... 'seconds': 1565096932, ... 'microseconds': 0, ... }, ... 'offset': 0, ... } >>> rev0 = _fix_revision({ ... 'id': b'rev-id', ... 'author': {'fullname': b'', 'name': '', 'email': ''}, ... 'committer': {'fullname': b'', 'name': '', 'email': ''}, ... 'date': date, ... 'committer_date': date, ... 'type': 'git', ... 'message': '', ... 'directory': b'dir-id', ... 'synthetic': False, ... }) >>> rev0['author'] {'fullname': b'', 'name': b'', 'email': b''} >>> rev0['committer'] {'fullname': b'', 'name': b'', 'email': b''} Fix type of 'transplant_source' extra headers: >>> rev1 = _fix_revision({ ... 'id': b'rev-id', ... 'author': {'fullname': b'', 'name': '', 'email': ''}, ... 'committer': {'fullname': b'', 'name': '', 'email': ''}, ... 'date': date, ... 'committer_date': date, ... 'metadata': { ... 'extra_headers': [ ... ['time_offset_seconds', b'-3600'], ... ['transplant_source', '29c154a012a70f49df983625090434587622b39e'] ... ]}, ... 'type': 'git', ... 'message': '', ... 'directory': b'dir-id', ... 'synthetic': False, ... }) >>> pprint(rev1['metadata']['extra_headers']) [['time_offset_seconds', b'-3600'], ['transplant_source', b'29c154a012a70f49df983625090434587622b39e']] Revision with invalid date are filtered: >>> from copy import deepcopy >>> invalid_date1 = deepcopy(date) >>> invalid_date1['timestamp']['microseconds'] = 1000000000 # > 10^6 >>> rev = _fix_revision({ ... 'author': {'fullname': b'', 'name': '', 'email': ''}, ... 'committer': {'fullname': b'', 'name': '', 'email': ''}, ... 'date': invalid_date1, ... 'committer_date': date, ... }) >>> rev is None True >>> invalid_date2 = deepcopy(date) >>> invalid_date2['timestamp']['seconds'] = 2**70 # > 10^63 >>> rev = _fix_revision({ ... 'author': {'fullname': b'', 'name': '', 'email': ''}, ... 'committer': {'fullname': b'', 'name': '', 'email': ''}, ... 'date': invalid_date2, ... 'committer_date': date, ... }) >>> rev is None True >>> invalid_date3 = deepcopy(date) >>> invalid_date3['offset'] = 2**20 # > 10^15 >>> rev = _fix_revision({ ... 'author': {'fullname': b'', 'name': '', 'email': ''}, ... 'committer': {'fullname': b'', 'name': '', 'email': ''}, ... 'date': date, ... 'committer_date': invalid_date3, ... }) >>> rev is None True """ # noqa rev = _fix_revision_pypi_empty_string(revision) rev = _fix_revision_transplant_source(rev) if not _check_revision_date(rev): logger.warning( "Invalid revision date detected: %(revision)s", {"revision": rev} ) return None return rev def _fix_origin(origin: Dict) -> Dict: """Fix legacy origin with type which is no longer part of the model. >>> from pprint import pprint >>> pprint(_fix_origin({ ... 'url': 'http://foo', ... })) {'url': 'http://foo'} >>> pprint(_fix_origin({ ... 'url': 'http://bar', ... 'type': 'foo', ... })) {'url': 'http://bar'} """ o = origin.copy() o.pop("type", None) return o def _fix_origin_visit(visit: Dict) -> Dict: """Fix various legacy origin visit issues. `visit['origin']` is a dict instead of an URL: >>> from datetime import datetime, timezone >>> from pprint import pprint >>> date = datetime(2020, 2, 27, 14, 39, 19, tzinfo=timezone.utc) >>> pprint(_fix_origin_visit({ ... 'origin': {'url': 'http://foo'}, ... 'date': date, ... 'type': 'git', ... 'status': 'ongoing', ... 'snapshot': None, ... })) {'date': datetime.datetime(2020, 2, 27, 14, 39, 19, tzinfo=datetime.timezone.utc), 'origin': 'http://foo', 'type': 'git'} `visit['type']` is missing , but `origin['visit']['type']` exists: >>> pprint(_fix_origin_visit( ... {'origin': {'type': 'hg', 'url': 'http://foo'}, ... 'date': date, ... 'status': 'ongoing', ... 'snapshot': None, ... })) {'date': datetime.datetime(2020, 2, 27, 14, 39, 19, tzinfo=datetime.timezone.utc), 'origin': 'http://foo', 'type': 'hg'} >>> pprint(_fix_origin_visit( ... {'origin': {'type': 'hg', 'url': 'http://foo'}, ... 'date': '2020-02-27 14:39:19+00:00', ... 'status': 'ongoing', ... 'snapshot': None, ... })) {'date': datetime.datetime(2020, 2, 27, 14, 39, 19, tzinfo=datetime.timezone.utc), 'origin': 'http://foo', 'type': 'hg'} Old visit format (origin_visit with no type) raises: >>> _fix_origin_visit({ ... 'origin': {'url': 'http://foo'}, ... 'date': date, ... 'status': 'ongoing', ... 'snapshot': None ... }) Traceback (most recent call last): ... ValueError: Old origin visit format detected... >>> _fix_origin_visit({ ... 'origin': 'http://foo', ... 'date': date, ... 'status': 'ongoing', ... 'snapshot': None ... }) Traceback (most recent call last): ... ValueError: Old origin visit format detected... """ # noqa visit = visit.copy() if "type" not in visit: if isinstance(visit["origin"], dict) and "type" in visit["origin"]: # Very old version of the schema: visits did not have a type, # but their 'origin' field was a dict with a 'type' key. visit["type"] = visit["origin"]["type"] else: # Very old schema version: 'type' is missing, stop early # We expect the journal's origin_visit topic to no longer reference # such visits. If it does, the replayer must crash so we can fix # the journal's topic. raise ValueError(f"Old origin visit format detected: {visit}") if isinstance(visit["origin"], dict): # Old version of the schema: visit['origin'] was a dict. visit["origin"] = visit["origin"]["url"] date = visit["date"] if isinstance(date, str): visit["date"] = datetime.datetime.fromisoformat(date) # Those are no longer part of the model for key in ["status", "snapshot", "metadata"]: visit.pop(key, None) return visit def fix_objects(object_type: str, objects: List[Dict]) -> List[Dict]: """ Fix legacy objects from the journal to bring them up to date with the latest storage schema. """ if object_type == "content": return [_fix_content(v) for v in objects] elif object_type == "revision": revisions = [_fix_revision(v) for v in objects] return [rev for rev in revisions if rev is not None] elif object_type == "origin": return [_fix_origin(v) for v in objects] elif object_type == "origin_visit": return [_fix_origin_visit(v) for v in objects] else: return objects diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py index f94b11bd..d78473fd 100644 --- a/swh/storage/in_memory.py +++ b/swh/storage/in_memory.py @@ -1,633 +1,626 @@ # 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 collections import defaultdict import datetime import functools import random - -from collections import defaultdict from typing import ( Any, Dict, Generic, Iterable, Iterator, List, Optional, Tuple, Type, TypeVar, Union, ) -from swh.model.model import ( - Content, - SkippedContent, - Sha1Git, -) - +from swh.model.model import Content, Sha1Git, SkippedContent from swh.storage.cassandra import CassandraStorage from swh.storage.cassandra.model import ( BaseRow, ContentRow, - DirectoryRow, DirectoryEntryRow, + DirectoryRow, MetadataAuthorityRow, MetadataFetcherRow, ObjectCountRow, OriginRow, OriginVisitRow, OriginVisitStatusRow, RawExtrinsicMetadataRow, ReleaseRow, - RevisionRow, RevisionParentRow, + RevisionRow, SkippedContentRow, - SnapshotRow, 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._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_token(self, token: int) -> Iterable[ContentRow]: return self._contents.get_from_token(token) def content_get_random(self) -> Optional[ContentRow]: return self._contents.get_random() def content_get_token_range( 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] ########################## # '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_hash( self, algo: str, hash_: bytes ) -> Iterable[int]: return 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() ########################## # '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_,)) ########################## # '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]) -> 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]) -> 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) -> 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.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 ) -> Iterable[SnapshotBranchRow]: count = 0 for branch in self._snapshot_branches.get_from_partition_key((snapshot_id,)): if branch.name >= from_: 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_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, ) -> 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_get_all(self, origin_url: str) -> Iterable[OriginVisitRow]: return 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_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, ) -> Optional[OriginVisitStatusRow]: """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, ) -> Iterator[OriginVisitStatusRow]: """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) ########################## # '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' 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, id: str, authority_type: str, authority_url: str, after: datetime.datetime, ) -> Iterable[RawExtrinsicMetadataRow]: metadata = self.raw_extrinsic_metadata_get(id, authority_type, authority_url) return (m for m in metadata if m.discovery_date > after) def raw_extrinsic_metadata_get_after_date_and_fetcher( self, id: str, authority_type: str, authority_url: str, after_date: datetime.datetime, after_fetcher_name: str, after_fetcher_version: str, ) -> Iterable[RawExtrinsicMetadataRow]: metadata = self._raw_extrinsic_metadata.get_from_partition_key((id,)) after_tuple = (after_date, after_fetcher_name, after_fetcher_version) return ( m for m in metadata if m.authority_type == authority_type and m.authority_url == authority_url and (m.discovery_date, m.fetcher_name, m.fetcher_version) > after_tuple ) def raw_extrinsic_metadata_get( self, id: str, authority_type: str, authority_url: str ) -> Iterable[RawExtrinsicMetadataRow]: metadata = self._raw_extrinsic_metadata.get_from_partition_key((id,)) return ( m for m in metadata if m.authority_type == authority_type and m.authority_url == authority_url ) class InMemoryStorage(CassandraStorage): _cql_runner: InMemoryCqlRunner # type: ignore def __init__(self, journal_writer=None): self.reset() self.journal_writer = JournalWriter(journal_writer) def reset(self): self._cql_runner = InMemoryCqlRunner() self.objstorage = ObjStorage({"cls": "memory", "args": {}}) def check_config(self, *, check_write: bool) -> bool: return True diff --git a/swh/storage/interface.py b/swh/storage/interface.py index 3b77a040..e7ff3d64 100644 --- a/swh/storage/interface.py +++ b/swh/storage/interface.py @@ -1,1202 +1,1201 @@ # 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 datetime - from enum import Enum from typing import Any, Dict, Iterable, List, Optional, Tuple, TypeVar, Union 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.identifiers import SWHID from swh.model.model import ( Content, Directory, - Origin, - OriginVisit, - OriginVisitStatus, - Revision, - Release, - Snapshot, - SkippedContent, - SnapshotBranch, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, + Origin, + OriginVisit, + OriginVisitStatus, RawExtrinsicMetadata, + Release, + Revision, Sha1, Sha1Git, + SkippedContent, + Snapshot, + SnapshotBranch, ) 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.""" 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: """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: """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[Sha1]) -> List[Optional[Content]]: """Retrieve content metadata in bulk Args: content: List of content identifiers 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: """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: """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_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: """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]) -> List[Optional[Revision]]: """Get revisions from storage Args: revisions: revision ids Returns: list of revision object (if the revision exists or None otherwise) """ ... @remote_api_endpoint("revision/log") def revision_log( self, revisions: List[Sha1Git], 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 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: """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]) -> List[Optional[Release]]: """Given a list of sha1, return the releases's information Args: releases: list of sha1s 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: """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 ) -> Optional[Dict[Optional[str], int]]: """Count the number of branches in the snapshot with the given id Args: snapshot_id: snapshot identifier 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, ) -> 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'`) 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],) -> None: """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_random") def origin_visit_status_get_random( self, type: str ) -> Optional[Tuple[OriginVisit, OriginVisitStatus]]: """Randomly select one successful origin visit with made in the last 3 months. Returns: One random tuple of (OriginVisit, 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, ) -> 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 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/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],) -> None: """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, type: MetadataTargetType, id: Union[str, SWHID], 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 for the id Args: type: one of the values of swh.model.model.MetadataTargetType id: an URL if type is 'origin', else a core SWHID 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("metadata_fetcher/add") def metadata_fetcher_add(self, fetchers: List[MetadataFetcher],) -> None: """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]) -> None: """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: Optional[List[str]] = None) -> 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: Optional[List[str]] = None) -> Dict: """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/migrate_extrinsic_metadata.py b/swh/storage/migrate_extrinsic_metadata.py index 806832dc..e81fc1c4 100644 --- a/swh/storage/migrate_extrinsic_metadata.py +++ b/swh/storage/migrate_extrinsic_metadata.py @@ -1,987 +1,987 @@ #!/usr/bin/env python3 # 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 """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 json import os import re import sys import time from typing import Any, Dict, Optional from urllib.parse import unquote, urlparse import iso8601 import psycopg2 from swh.core.db import BaseDb from swh.model.hashutil import hash_to_hex from swh.model.identifiers import SWHID, parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, RawExtrinsicMetadata, Sha1Git, ) from swh.storage import get_storage -from swh.storage.algos.origin import iter_origin_visits, iter_origin_visit_statuses +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", "date", "committer_date", "type", "message", "metadata"] # columns of the tables of the deposit DB DEPOSIT_COLS = [ "deposit.id", "deposit.external_id", "deposit.swh_id_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", ) # 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): match = re.match( r"^(?P[a-zA-Z0-9_.-]+)" r"-[0-9.]+([a-z]+[0-9]+)?(dev|\.dev[0-9]+)?(-[a-z][a-z0-9]*)?\.(tar\.gz|zip)$", filename, ) assert match, filename return match.group("project_name") def cran_package_from_url(filename): match = re.match( r"^https://cran\.r-project\.org/src/contrib/" r"(?P[a-zA-Z0-9.]+)_[0-9.-]+(\.tar\.gz)?$", 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 ( 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, 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.""" revision_swhid = SWHID(object_type="revision", object_id=hash_to_hex(revision_id)) obj = RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=revision_swhid, discovery_date=discovery_date, authority=authority, fetcher=FETCHER, format=format, metadata=json.dumps(metadata).encode(), origin=origin, ) 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) assert deposit_request["deposit.swh_id_context"], deposit_request external_identifiers.add(deposit_request["deposit.external_id"]) swhids.add(deposit_request["deposit.swh_id_context"]) # 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 else: assert "{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 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 = parse_swhid(swhid).metadata["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={}, ) for (date, format, metadata) in metadata_entries: load_metadata( storage, row["id"], 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"], 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"], 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}" # TODO https://forge.softwareheritage.org/T2536 assert origin is not None if ( hashlib.sha1(origin.encode()).digest() not in _origins and storage.origin_get([origin])[0] is None ): print("MISSING CRAN ORIGIN", hash_to_hex(row["id"]), origin) return raw_extrinsic_metadata = metadata["extrinsic"]["raw"] # this is actually intrinsic, ignore it del raw_extrinsic_metadata["version"] # Copy the URL to the original_artifacts metadata assert len(metadata["original_artifact"]) == 1 assert "url" not in metadata["original_artifact"][0] 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/"): # nixguix loader origin = provider assert_origin_exists(storage, origin) authority = MetadataAuthority( type=MetadataAuthorityType.FORGE, url=provider, metadata={}, ) assert row["date"] is None # the nixguix loader does not write dates load_metadata( storage, row["id"], 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 "@xmlns" in actual_metadata: assert actual_metadata["@xmlns"] == ATOM_NS assert actual_metadata["@xmlns:codemeta"] in ( CODEMETA_NS, [CODEMETA_NS], ) else: assert "{http://www.w3.org/2005/Atom}id" in actual_metadata assert ( "{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}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"], 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 project_name = pypi_project_from_filename( metadata["original_artifact"][0]["filename"] ) origin = f"https://pypi.org/project/{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 not _check_revision_in_origin(storage, origin, row["id"]): origin = None if "project" in metadata: # pypi loader format 2 # same reason as above, we can't do this: # if metadata["project"]: # assert metadata["project"]["name"] == project_name load_metadata( storage, row["id"], 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) assert origins, row else: origins = [origin] for origin in origins: load_metadata( storage, row["id"], 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 " 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, dry_run): storage_db = BaseDb.connect(storage_dbconn) deposit_db = BaseDb.connect(deposit_dbconn) storage = get_storage("remote", url=storage_url) 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: for row in iter_revision_rows(storage_dbconn, first_id): 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 else: print( f"Syntax: {sys.argv[0]} " f" []" ) 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), True) diff --git a/swh/storage/objstorage.py b/swh/storage/objstorage.py index fa3fced0..6c79ac4f 100644 --- a/swh/storage/objstorage.py +++ b/swh/storage/objstorage.py @@ -1,66 +1,66 @@ # 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 Dict, Iterable, Optional -from swh.storage.interface import Sha1 from swh.model.model import Content, MissingData -from swh.objstorage.factory import get_objstorage from swh.objstorage.exc import ObjNotFoundError +from swh.objstorage.factory import get_objstorage +from swh.storage.interface import Sha1 from .exc import StorageArgumentException class ObjStorage: """Objstorage collaborator in charge of adding objects to the objstorage. """ def __init__(self, objstorage_config: Dict): self.objstorage = get_objstorage(**objstorage_config) def __getattr__(self, key): if key == "objstorage": raise AttributeError(key) return getattr(self.objstorage, key) def content_get(self, obj_id: Sha1) -> Optional[bytes]: """Retrieve data associated to the content from the objstorage Args: content: content identitier Returns: associated content's data if any, None otherwise. """ try: data = self.objstorage.get(obj_id) except ObjNotFoundError: data = None return data def content_add(self, contents: Iterable[Content]) -> Dict: """Add contents to the objstorage. Args: contents: List of contents to add1 Returns: The summary dict of content and content bytes added to the objstorage. """ try: contents = [c.with_data() for c in contents] except MissingData: raise StorageArgumentException("Missing data") from None summary = self.objstorage.add_batch({cont.sha1: cont.data for cont in contents}) return { "content:add": summary["object:add"], "content:add:bytes": summary["object:add:bytes"], } diff --git a/swh/storage/postgresql/converters.py b/swh/storage/postgresql/converters.py index a6509456..7282f080 100644 --- a/swh/storage/postgresql/converters.py +++ b/swh/storage/postgresql/converters.py @@ -1,324 +1,322 @@ # 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 datetime - -from typing import Any, Optional, Dict +from typing import Any, Dict, Optional from swh.core.utils import encode_with_unescape from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, ObjectType, Person, RawExtrinsicMetadata, Release, Revision, RevisionType, Timestamp, TimestampWithTimezone, ) from ..utils import map_optional - DEFAULT_AUTHOR = { "fullname": None, "name": None, "email": None, } DEFAULT_DATE = { "timestamp": None, "offset": 0, "neg_utc_offset": 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 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: int, neg_utc_offset: Optional[bool] ) -> 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: an integer number of minutes representing an UTC offset neg_utc_offset: whether an utc offset is negative Returns: a TimestampWithTimezone, or None if the date is None. """ if date is None: return None if neg_utc_offset is None: # For older versions of the database that were not migrated to schema v160 neg_utc_offset = False return TimestampWithTimezone( timestamp=Timestamp( seconds=int(date.timestamp()), microseconds=date.microsecond, ), offset=offset, negative_utc=neg_utc_offset, ) 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 three keys: - timestamp: a date in ISO format - offset: the UTC offset in minutes - neg_utc_offset: a boolean indicating whether a null offset is negative or positive. """ 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, "neg_utc_offset": ts_with_tz.negative_utc, } def revision_to_db(revision: Revision) -> Dict[str, Any]: """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"], "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"], "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, "parents": [ {"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"], db_revision["date_neg_utc_offset"], ) 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"], db_revision["committer_date_neg_utc_offset"], ) assert author, "author is None" assert committer, "committer is 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), ) def release_to_db(release: Release) -> Dict[str, Any]: """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"], "name": release.name, "target": release.target, "target_type": release.target_type.value, "comment": release.message, "synthetic": release.synthetic, } 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"], db_release["date_neg_utc_offset"] ) 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"]), ) def db_to_raw_extrinsic_metadata(row) -> RawExtrinsicMetadata: type_ = MetadataTargetType(row["raw_extrinsic_metadata.type"]) id_ = row["raw_extrinsic_metadata.id"] if type_ != MetadataTargetType.ORIGIN: id_ = parse_swhid(id_) return RawExtrinsicMetadata( type=type_, id=id_, 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"], ), discovery_date=row["discovery_date"], format=row["format"], metadata=row["raw_extrinsic_metadata.metadata"], origin=row["origin"], visit=row["visit"], snapshot=map_optional(parse_swhid, row["snapshot"]), release=map_optional(parse_swhid, row["release"]), revision=map_optional(parse_swhid, row["revision"]), path=row["path"], directory=map_optional(parse_swhid, row["directory"]), ) diff --git a/swh/storage/postgresql/db.py b/swh/storage/postgresql/db.py index 998a51be..01a78ffe 100644 --- a/swh/storage/postgresql/db.py +++ b/swh/storage/postgresql/db.py @@ -1,1342 +1,1343 @@ # 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 datetime import random import select from typing import Any, Dict, Iterable, List, Optional, Tuple from swh.core.db import BaseDb -from swh.core.db.db_utils import stored_procedure, jsonize as _jsonize from swh.core.db.db_utils import execute_values_generator -from swh.model.model import OriginVisit, OriginVisitStatus, SHA1_SIZE +from swh.core.db.db_utils import jsonize as _jsonize +from swh.core.db.db_utils import stored_procedure +from swh.model.model import SHA1_SIZE, OriginVisit, OriginVisitStatus from swh.storage.interface import ListOrder 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 """ current_version = 162 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 def register_listener(self, notify_queue, cur=None): """Register a listener for NOTIFY queue `notify_queue`""" self._cursor(cur).execute("LISTEN %s" % notify_queue) def listen_notifies(self, timeout): """Listen to notifications for `timeout` seconds""" if select.select([self.conn], [], [], timeout) == ([], [], []): return else: self.conn.poll() while self.conn.notifies: yield self.conn.notifies.pop(0) @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_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_sha1s(self, sha1s, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ select t.sha1, %s from (values %%s) as t (sha1) inner join content using (sha1) """ % ", ".join(self.content_get_metadata_keys[1:]), ((sha1,) for sha1 in sha1s), ) def content_get_range(self, start, end, limit=None, cur=None): """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, cur=None): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_count_branches(%%s) """ % ", ".join( self.snapshot_count_cols ) cur.execute(query, (snapshot_id,)) 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, cur=None, ): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_get_by_id(%%s, %%s, %%s, %%s :: snapshot_target[]) """ % ", ".join( self.snapshot_get_cols ) cur.execute(query, (snapshot_id, branches_from, branches_count, target_types)) 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. """ 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 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", "committer_date", "committer_date_offset", "committer_date_neg_utc_offset", "type", "directory", "message", "author_fullname", "author_name", "author_email", "committer_fullname", "committer_name", "committer_email", "metadata", "synthetic", "extra_headers", ] 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", "status", "snapshot", "metadata", ] def origin_visit_status_add( self, visit_status: OriginVisitStatus, cur=None ) -> None: """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 """ 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.metadata", "ovs.snapshot", ] origin_visit_status_select_cols = [ "o.url AS origin", "ovs.visit", "ovs.date", "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 """ 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 """ 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. """ 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, ): 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_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 ON ov.origin = ovs.origin AND ov.visit = ovs.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 ", "ON o.id = ovs.origin AND ov.visit = ovs.visit ", ] query_parts.append("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.date DESC, 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 """ 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 on ov.origin = ovs.origin and ov.visit = ovs.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): 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 "%s.%s" % (main_table, key) head, tail = key.split("_", 1) if head in ("author", "committer") and tail in ( "name", "email", "id", "fullname", ): return "%s.%s" % (head, tail) return "%s.%s" % (main_table, key) def revision_get_from_list(self, revisions, cur=None): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "revision") 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)), ) def revision_log(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_log(%%s, %%s) """ % ", ".join( self.revision_get_cols ) cur.execute(query, (root_revisions, limit)) 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) RETURNING url""" cur.execute(insert, (url,)) return cur.fetchone()[0] 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, 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: query += """ WHERE EXISTS ( SELECT 1 FROM origin_visit ov INNER JOIN origin_visit_status ovs ON ov.origin = ovs.origin AND ov.visit = ovs.visit INNER JOIN snapshot ON ovs.snapshot=snapshot.id WHERE ov.origin=o.id ) """ 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, 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, 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", "name", "comment", "synthetic", "author_fullname", "author_name", "author_email", ] release_get_cols = release_add_cols def release_get_from_list(self, releases, cur=None): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "release") 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 = [ "type", "id", "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, authority_id, discovery_date, fetcher_id) DO NOTHING """ raw_extrinsic_metadata_get_cols = [ "raw_extrinsic_metadata.id", "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) WHERE raw_extrinsic_metadata.id=%s AND authority_id=%s """ def raw_extrinsic_metadata_add( self, type: str, id: 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( type=type, id=id, 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, type: str, id: str, authority_id: int, after_time: Optional[datetime.datetime], after_fetcher: Optional[int], limit: int, cur, ): query_parts = [self._raw_extrinsic_metadata_select_query] args = [id, 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 metadata_fetcher_cols = ["name", "version", "metadata"] def metadata_fetcher_add( self, name: str, version: str, metadata: bytes, cur=None ) -> None: cur = self._cursor(cur) cur.execute( "INSERT INTO metadata_fetcher (name, version, metadata) " "VALUES (%s, %s, %s) ON CONFLICT DO NOTHING", (name, version, jsonize(metadata)), ) 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", "metadata"] def metadata_authority_add( self, type: str, url: str, metadata: bytes, cur=None ) -> None: cur = self._cursor(cur) cur.execute( "INSERT INTO metadata_authority (type, url, metadata) " "VALUES (%s, %s, %s) ON CONFLICT DO NOTHING", (type, url, jsonize(metadata)), ) 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") return dict(zip(self.dbversion_cols, cur.fetchone())) def check_dbversion(self): return self.dbversion()["version"] == self.current_version diff --git a/swh/storage/postgresql/storage.py b/swh/storage/postgresql/storage.py index a7a1496f..75050c06 100644 --- a/swh/storage/postgresql/storage.py +++ b/swh/storage/postgresql/storage.py @@ -1,1431 +1,1420 @@ # 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 base64 +from collections import defaultdict import contextlib +from contextlib import contextmanager import datetime import itertools - -from collections import defaultdict -from contextlib import contextmanager -from typing import ( - Any, - Counter, - Dict, - Iterable, - List, - Optional, - Tuple, - Union, -) +from typing import Any, Counter, Dict, Iterable, List, Optional, Tuple, Union import attr import psycopg2 -import psycopg2.pool import psycopg2.errors +import psycopg2.pool -from swh.core.api.serializers import msgpack_loads, msgpack_dumps -from swh.core.db.common import db_transaction_generator, db_transaction +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.identifiers import SWHID from swh.model.model import ( + SHA1_SIZE, Content, Directory, + MetadataAuthority, + MetadataAuthorityType, + MetadataFetcher, + MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, - Revision, + RawExtrinsicMetadata, Release, - SkippedContent, + Revision, Sha1, Sha1Git, + SkippedContent, Snapshot, SnapshotBranch, TargetType, - SHA1_SIZE, - MetadataAuthority, - MetadataAuthorityType, - MetadataFetcher, - MetadataTargetType, - RawExtrinsicMetadata, ) -from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex -from swh.storage.exc import StorageArgumentException, StorageDBError, HashCollision +from swh.storage.exc import HashCollision, StorageArgumentException, StorageDBError from swh.storage.interface import ( + VISIT_STATUSES, ListOrder, PagedResult, PartialBranches, - VISIT_STATUSES, ) -from swh.storage.metrics import timed, send_metric, process_metrics +from swh.storage.metrics import process_metrics, send_metric, timed from swh.storage.objstorage import ObjStorage from swh.storage.utils import ( - get_partition_bounds_bytes, 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 tuple(VALIDATION_EXCEPTIONS) as e: raise StorageArgumentException(str(e)) class 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 ): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ try: if isinstance(db, psycopg2.extensions.connection): self._pool = None self._db = Db(db) 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) def get_db(self): if self._db: return self._db else: return Db.from_pool(self._pool) 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) @timed @db_transaction() def check_config(self, *, check_write: bool, db=None, 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] def _content_unique_key(self, hash, db): """Given a hash (tuple or dict), return a unique key from the 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. """ # 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 @timed @process_metrics def content_add(self, content: List[Content]) -> Dict: ctime = now() contents = [attr.evolve(c, ctime=ctime) for c in content] 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"], } @timed @db_transaction() def content_update( self, contents: List[Dict[str, Any]], keys: List[str] = [], db=None, 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) @timed @process_metrics @db_transaction() def content_add_metadata(self, content: List[Content], db=None, cur=None) -> Dict: missing = self.content_missing( (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), } @timed def content_get_data(self, content: Sha1) -> Optional[bytes]: # FIXME: Make this method support slicing the `data` return self.objstorage.content_get(content) @timed @db_transaction() def content_get_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, db=None, 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) @timed @db_transaction(statement_timeout=500) def content_get( self, contents: List[Sha1], db=None, cur=None ) -> List[Optional[Content]]: contents_by_sha1: Dict[Sha1, Optional[Content]] = {} for row in db.content_get_metadata_from_sha1s(contents, cur): row_d = dict(zip(db.content_get_metadata_keys, row)) content = Content(**row_d) contents_by_sha1[content.sha1] = content return [contents_by_sha1.get(sha1) for sha1 in contents] @timed @db_transaction_generator() def content_missing( self, contents: List[Dict[str, Any]], key_hash: str = "sha1", db=None, 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] @timed @db_transaction_generator() def content_missing_per_sha1( self, contents: List[bytes], db=None, cur=None ) -> Iterable[bytes]: for obj in db.content_missing_per_sha1(contents, cur): yield obj[0] @timed @db_transaction_generator() def content_missing_per_sha1_git( self, contents: List[bytes], db=None, cur=None ) -> Iterable[Sha1Git]: for obj in db.content_missing_per_sha1_git(contents, cur): yield obj[0] @timed @db_transaction() def content_find(self, content: Dict[str, Any], db=None, 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 @timed @db_transaction() def content_get_random(self, db=None, 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) @timed @process_metrics @db_transaction() def skipped_content_add( self, content: List[SkippedContent], db=None, cur=None ) -> Dict: 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, ) 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), } @timed @db_transaction_generator() def skipped_content_missing( self, contents: List[Dict[str, Any]], db=None, 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)) @timed @process_metrics @db_transaction() def directory_add(self, directories: List[Directory], db=None, cur=None) -> Dict: 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 ids dirs_missing_dict = ({"id": dir} for dir in dirs_missing) db.mktemp("directory", cur) db.copy_to(dirs_missing_dict, "tmp_directory", ["id"], 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 @timed @db_transaction_generator() def directory_missing( self, directories: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: for obj in db.directory_missing_from_list(directories, cur): yield obj[0] @timed @db_transaction_generator(statement_timeout=20000) def directory_ls( self, directory: Sha1Git, recursive: bool = False, db=None, 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)) @timed @db_transaction(statement_timeout=2000) def directory_entry_get_by_path( self, directory: Sha1Git, paths: List[bytes], db=None, 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 @timed @db_transaction() def directory_get_random(self, db=None, cur=None) -> Sha1Git: return db.directory_get_random(cur) @timed @process_metrics @db_transaction() def revision_add(self, revisions: List[Revision], db=None, cur=None) -> Dict: 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[bytes] = [] 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)} @timed @db_transaction_generator() def revision_missing( self, revisions: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: if not revisions: return None for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @timed @db_transaction(statement_timeout=1000) def revision_get( self, revision_ids: List[Sha1Git], db=None, cur=None ) -> List[Optional[Revision]]: revisions = [] for line in db.revision_get_from_list(revision_ids, cur): revision = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) revisions.append(revision) return revisions @timed @db_transaction_generator(statement_timeout=2000) def revision_log( self, revisions: List[Sha1Git], limit: Optional[int] = None, db=None, cur=None ) -> Iterable[Optional[Dict[str, Any]]]: for line in db.revision_log(revisions, limit, cur): data = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) if not data: yield None continue yield data.to_dict() @timed @db_transaction_generator(statement_timeout=2000) def revision_shortlog( self, revisions: List[Sha1Git], limit: Optional[int] = None, db=None, cur=None ) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]: yield from db.revision_shortlog(revisions, limit, cur) @timed @db_transaction() def revision_get_random(self, db=None, cur=None) -> Sha1Git: return db.revision_get_random(cur) @timed @process_metrics @db_transaction() def release_add(self, releases: List[Release], db=None, cur=None) -> Dict: 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)} @timed @db_transaction_generator() def release_missing( self, releases: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @timed @db_transaction(statement_timeout=500) def release_get( self, releases: List[Sha1Git], db=None, cur=None ) -> List[Optional[Release]]: rels = [] for release in db.release_get_from_list(releases, cur): data = converters.db_to_release(dict(zip(db.release_get_cols, release))) rels.append(data if data else None) return rels @timed @db_transaction() def release_get_random(self, db=None, cur=None) -> Sha1Git: return db.release_get_random(cur) @timed @process_metrics @db_transaction() def snapshot_add(self, snapshots: List[Snapshot], db=None, cur=None) -> Dict: 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} @timed @db_transaction_generator() def snapshot_missing( self, snapshots: List[Sha1Git], db=None, cur=None ) -> Iterable[Sha1Git]: for obj in db.snapshot_missing_from_list(snapshots, cur): yield obj[0] @timed @db_transaction(statement_timeout=2000) def snapshot_get( self, snapshot_id: Sha1Git, db=None, 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"], } @timed @db_transaction(statement_timeout=2000) def snapshot_count_branches( self, snapshot_id: Sha1Git, db=None, cur=None ) -> Optional[Dict[Optional[str], int]]: return dict([bc for bc in db.snapshot_count_branches(snapshot_id, cur)]) @timed @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, db=None, cur=None, ) -> Optional[PartialBranches]: if snapshot_id == EMPTY_SNAPSHOT_ID: return PartialBranches(id=snapshot_id, branches={}, next_branch=None,) branches = {} next_branch = None fetched_branches = list( db.snapshot_get_by_id( snapshot_id, branches_from=branches_from, branches_count=branches_count + 1, target_types=target_types, 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[-1]))["name"] if branches: return PartialBranches( id=snapshot_id, branches=branches, next_branch=next_branch, ) return None @timed @db_transaction() def snapshot_get_random(self, db=None, cur=None) -> Sha1Git: return db.snapshot_get_random(cur) @timed @db_transaction() def origin_visit_add( self, visits: List[OriginVisit], db=None, 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 = [] nb_visits = 0 for visit in visits: nb_visits += 1 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, status="created", snapshot=None, ) self._origin_visit_status_add(visit_status, db=db, cur=cur) send_metric("origin_visit:add", count=nb_visits, method_name="origin_visit") 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) send_metric( "origin_visit_status:add", count=1, method_name="origin_visit_status" ) @timed @db_transaction() def origin_visit_status_add( self, visit_statuses: List[OriginVisitStatus], db=None, cur=None, ) -> None: # 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}") for visit_status in visit_statuses: self._origin_visit_status_add(visit_status, db, cur) @timed @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=None, 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 = db.origin_visit_status_get_latest( origin_url, visit, allowed_statuses, require_snapshot, cur=cur ) if not row: return None return OriginVisitStatus.from_dict(row) @timed @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=None, 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) @timed @db_transaction(statement_timeout=500) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime, db=None, 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"], ) @timed @db_transaction(statement_timeout=500) def origin_visit_get_by( self, origin: str, visit: int, db=None, 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 @timed @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=None, 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 @timed @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=None, 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, ): row_d = dict(zip(db.origin_visit_status_cols, row)) visit_statuses.append( OriginVisitStatus( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], status=row_d["status"], snapshot=row_d["snapshot"], metadata=row_d["metadata"], ) ) 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) @timed @db_transaction() def origin_visit_status_get_random( self, type: str, db=None, cur=None ) -> Optional[Tuple[OriginVisit, OriginVisitStatus]]: row = db.origin_visit_get_random(type, cur) if row is not None: 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"], ) visit_status = OriginVisitStatus( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], status=row_d["status"], metadata=row_d["metadata"], snapshot=row_d["snapshot"], ) return visit, visit_status return None @timed @db_transaction(statement_timeout=2000) def object_find_by_sha1_git( self, ids: List[Sha1Git], db=None, 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 @timed @db_transaction(statement_timeout=500) def origin_get( self, origins: List[str], db=None, 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 @timed @db_transaction(statement_timeout=500) def origin_get_by_sha1( self, sha1s: List[bytes], db=None, 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) ] @timed @db_transaction_generator() def origin_get_range(self, origin_from=1, origin_count=100, db=None, cur=None): for origin in db.origin_get_range(origin_from, origin_count, cur): yield dict(zip(db.origin_get_range_cols, origin)) @timed @db_transaction() def origin_list( self, page_token: Optional[str] = None, limit: int = 100, *, db=None, 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) @timed @db_transaction() def origin_search( self, url_pattern: str, page_token: Optional[str] = None, limit: int = 50, regexp: bool = False, with_visit: bool = False, db=None, 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, 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) @timed @db_transaction() def origin_count( self, url_pattern: str, regexp: bool = False, with_visit: bool = False, db=None, cur=None, ) -> int: return db.origin_count(url_pattern, regexp, with_visit, cur) @timed @process_metrics @db_transaction() def origin_add(self, origins: List[Origin], db=None, 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=None, cur=None): return {k: v for (k, v) in db.stat_counters()} @db_transaction() def refresh_stat_counters(self, db=None, 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, ) -> None: metadata = list(metadata) self.journal_writer.raw_extrinsic_metadata_add(metadata) counter = Counter[MetadataTargetType]() 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( type=metadata_entry.type.value, id=str(metadata_entry.id), 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.type] += 1 for (type, count) in counter.items(): send_metric( f"{type.value}_metadata:add", count=count, method_name=f"{type.value}_metadata_add", ) @db_transaction() def raw_extrinsic_metadata_get( self, type: MetadataTargetType, id: Union[str, SWHID], authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, db=None, cur=None, ) -> PagedResult[RawExtrinsicMetadata]: if type == MetadataTargetType.ORIGIN: if isinstance(id, SWHID): raise StorageArgumentException( f"raw_extrinsic_metadata_get called with type='origin', " f"but provided id is an SWHID: {id!r}" ) else: if not isinstance(id, SWHID): raise StorageArgumentException( f"raw_extrinsic_metadata_get called with type!='origin', " f"but provided id is not an SWHID: {id!r}" ) 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=[],) rows = db.raw_extrinsic_metadata_get( type, str(id), 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(id) == row["raw_extrinsic_metadata.id"] 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,) @timed @db_transaction() def metadata_fetcher_add( self, fetchers: List[MetadataFetcher], db=None, cur=None ) -> None: fetchers = list(fetchers) self.journal_writer.metadata_fetcher_add(fetchers) count = 0 for fetcher in fetchers: if fetcher.metadata is None: raise StorageArgumentException( "MetadataFetcher.metadata may not be None in metadata_fetcher_add." ) db.metadata_fetcher_add( fetcher.name, fetcher.version, dict(fetcher.metadata), cur=cur ) count += 1 send_metric("metadata_fetcher:add", count=count, method_name="metadata_fetcher") @timed @db_transaction(statement_timeout=500) def metadata_fetcher_get( self, name: str, version: str, db=None, 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))) @timed @db_transaction() def metadata_authority_add( self, authorities: List[MetadataAuthority], db=None, cur=None ) -> None: authorities = list(authorities) self.journal_writer.metadata_authority_add(authorities) count = 0 for authority in authorities: if authority.metadata is None: raise StorageArgumentException( "MetadataAuthority.metadata may not be None in " "metadata_authority_add." ) db.metadata_authority_add( authority.type.value, authority.url, dict(authority.metadata), cur=cur ) count += 1 send_metric( "metadata_authority:add", count=count, method_name="metadata_authority" ) @timed @db_transaction() def metadata_authority_get( self, type: MetadataAuthorityType, url: str, db=None, 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: Optional[List[str]] = None) -> None: """Do nothing """ return None def flush(self, object_types: Optional[List[str]] = None) -> Dict: 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/pytest_plugin.py b/swh/storage/pytest_plugin.py index 7e7fbfdb..c1771557 100644 --- a/swh/storage/pytest_plugin.py +++ b/swh/storage/pytest_plugin.py @@ -1,201 +1,196 @@ # 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 glob - -from os import path, environ +from os import environ, path from typing import Union import pytest - -import swh.storage - from pytest_postgresql import factories -from pytest_postgresql.janitor import DatabaseJanitor, psycopg2, Version +from pytest_postgresql.janitor import DatabaseJanitor, Version, psycopg2 from swh.core.utils import numfile_sortkey as sortkey +import swh.storage from swh.storage import get_storage - from swh.storage.tests.storage_data import StorageData - SQL_DIR = path.join(path.dirname(swh.storage.__file__), "sql") environ["LC_ALL"] = "C.UTF-8" DUMP_FILES = path.join(SQL_DIR, "*.sql") @pytest.fixture def swh_storage_backend_config(postgresql_proc, swh_storage_postgresql): """Basic pg storage configuration with no journal collaborator (to avoid pulling optional dependency on clients of this fixture) """ yield { "cls": "local", "db": "postgresql://{user}@{host}:{port}/{dbname}".format( host=postgresql_proc.host, port=postgresql_proc.port, user="postgres", dbname="tests", ), "objstorage": {"cls": "memory", "args": {}}, "check_config": {"check_write": True}, } @pytest.fixture def swh_storage(swh_storage_backend_config): return get_storage(**swh_storage_backend_config) # the postgres_fact factory fixture below is mostly a copy of the code # from pytest-postgresql. We need a custom version here to be able to # specify our version of the DBJanitor we use. def postgresql_fact(process_fixture_name, db_name=None, dump_files=DUMP_FILES): @pytest.fixture def postgresql_factory(request): """ Fixture factory for PostgreSQL. :param FixtureRequest request: fixture request object :rtype: psycopg2.connection :returns: postgresql client """ config = factories.get_config(request) if not psycopg2: raise ImportError("No module named psycopg2. Please install it.") proc_fixture = request.getfixturevalue(process_fixture_name) # _, config = try_import('psycopg2', request) pg_host = proc_fixture.host pg_port = proc_fixture.port pg_user = proc_fixture.user pg_options = proc_fixture.options pg_db = db_name or config["dbname"] with SwhDatabaseJanitor( pg_user, pg_host, pg_port, pg_db, proc_fixture.version, dump_files=dump_files, ): connection = psycopg2.connect( dbname=pg_db, user=pg_user, host=pg_host, port=pg_port, options=pg_options, ) yield connection connection.close() return postgresql_factory swh_storage_postgresql = postgresql_fact("postgresql_proc") # This version of the DatabaseJanitor implement a different setup/teardown # behavior than than the stock one: instead of dropping, creating and # initializing the database for each test, it create and initialize the db only # once, then it truncate the tables. This is needed to have acceptable test # performances. class SwhDatabaseJanitor(DatabaseJanitor): def __init__( self, user: str, host: str, port: str, db_name: str, version: Union[str, float, Version], dump_files: str = DUMP_FILES, ) -> None: super().__init__(user, host, port, db_name, version) self.dump_files = sorted(glob.glob(dump_files), key=sortkey) def db_setup(self): with psycopg2.connect( dbname=self.db_name, user=self.user, host=self.host, port=self.port, ) as cnx: with cnx.cursor() as cur: for fname in self.dump_files: with open(fname) as fobj: sql = fobj.read().replace("concurrently", "").strip() if sql: cur.execute(sql) cnx.commit() def db_reset(self): with psycopg2.connect( dbname=self.db_name, user=self.user, host=self.host, port=self.port, ) as cnx: with cnx.cursor() as cur: cur.execute( "SELECT table_name FROM information_schema.tables " "WHERE table_schema = %s", ("public",), ) tables = set(table for (table,) in cur.fetchall()) - {"dbversion"} for table in tables: cur.execute("truncate table %s cascade" % table) cur.execute( "SELECT sequence_name FROM information_schema.sequences " "WHERE sequence_schema = %s", ("public",), ) seqs = set(seq for (seq,) in cur.fetchall()) for seq in seqs: cur.execute("ALTER SEQUENCE %s RESTART;" % seq) cnx.commit() def init(self): with self.cursor() as cur: cur.execute( "SELECT COUNT(1) FROM pg_database WHERE datname=%s;", (self.db_name,) ) db_exists = cur.fetchone()[0] == 1 if db_exists: cur.execute( "UPDATE pg_database SET datallowconn=true " "WHERE datname = %s;", (self.db_name,), ) if db_exists: self.db_reset() else: with self.cursor() as cur: cur.execute('CREATE DATABASE "{}";'.format(self.db_name)) self.db_setup() def drop(self): pid_column = "pid" with self.cursor() as cur: cur.execute( "UPDATE pg_database SET datallowconn=false " "WHERE datname = %s;", (self.db_name,), ) cur.execute( "SELECT pg_terminate_backend(pg_stat_activity.{})" "FROM pg_stat_activity " "WHERE pg_stat_activity.datname = %s;".format(pid_column), (self.db_name,), ) @pytest.fixture def sample_data() -> StorageData: """Pre-defined sample storage object data to manipulate Returns: StorageData whose attribute keys are data model objects. Either multiple objects: contents, directories, revisions, releases, ... or simple ones: content, directory, revision, release, ... """ return StorageData() diff --git a/swh/storage/replay.py b/swh/storage/replay.py index fdd62864..049f5712 100644 --- a/swh/storage/replay.py +++ b/swh/storage/replay.py @@ -1,141 +1,140 @@ # 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 logging from typing import Any, Callable, Dict, Iterable, List try: from systemd.daemon import notify except ImportError: notify = None from swh.core.statsd import statsd -from swh.storage.fixer import fix_objects - from swh.model.model import ( BaseContent, BaseModel, Content, Directory, MetadataAuthority, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, SkippedContent, Snapshot, ) from swh.storage.exc import HashCollision +from swh.storage.fixer import fix_objects logger = logging.getLogger(__name__) GRAPH_OPERATIONS_METRIC = "swh_graph_replayer_operations_total" GRAPH_DURATION_METRIC = "swh_graph_replayer_duration_seconds" object_converter_fn: 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, } def process_replay_objects(all_objects, *, storage): 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") def collision_aware_content_add( content_add_fn: Callable[[Iterable[Any]], None], contents: List[BaseContent] ) -> None: """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]] = [] while True: try: 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}) def _insert_objects(object_type: str, objects: List[Dict], storage) -> None: """Insert objects of type object_type in the storage. """ objects = fix_objects(object_type, objects) if object_type == "content": # for bw compat, skipped content should now be delivered in the skipped_content # topic contents: List[BaseContent] = [] skipped_contents: List[BaseContent] = [] for content in objects: c = BaseContent.from_dict(content) if isinstance(c, SkippedContent): skipped_contents.append(c) else: contents.append(c) collision_aware_content_add(storage.skipped_content_add, skipped_contents) collision_aware_content_add(storage.content_add_metadata, contents) if object_type == "skipped_content": skipped_contents = [SkippedContent.from_dict(obj) for obj in objects] collision_aware_content_add(storage.skipped_content_add, skipped_contents) elif object_type in ("origin_visit", "origin_visit_status"): origins: List[Origin] = [] converter_fn = object_converter_fn[object_type] model_objs = [] for obj in objects: origins.append(Origin(url=obj["origin"])) model_objs.append(converter_fn(obj)) storage.origin_add(origins) method = getattr(storage, f"{object_type}_add") method(model_objs) elif object_type in ("directory", "revision", "release", "snapshot", "origin",): method = getattr(storage, object_type + "_add") method([object_converter_fn[object_type](o) for o in objects]) else: logger.warning("Received a series of %s, this should not happen", object_type) diff --git a/swh/storage/retry.py b/swh/storage/retry.py index 1616273f..f400e9b9 100644 --- a/swh/storage/retry.py +++ b/swh/storage/retry.py @@ -1,147 +1,140 @@ # 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 logging import traceback - from typing import Dict, Iterable, List, Optional -from tenacity import ( - retry, - stop_after_attempt, - wait_random_exponential, -) +from tenacity import retry, stop_after_attempt, wait_random_exponential from swh.model.model import ( Content, - SkippedContent, Directory, - Revision, - Release, - Snapshot, - OriginVisit, MetadataAuthority, MetadataFetcher, + OriginVisit, RawExtrinsicMetadata, + Release, + Revision, + SkippedContent, + Snapshot, ) - 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 """ try: attempt = retry_state.outcome except AttributeError: # tenacity < 5.0 attempt = retry_state if attempt.failed: error = attempt.exception() if isinstance(error, StorageArgumentException): # Exception is due to an invalid argument 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( "Retry adding a batch", 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), ) class RetryingProxyStorage: """Storage implementation which retries adding objects when it specifically fails (hash collision, integrity error). """ 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) @swh_retry def content_add(self, content: List[Content]) -> Dict: return self.storage.content_add(content) @swh_retry def content_add_metadata(self, content: List[Content]) -> Dict: return self.storage.content_add_metadata(content) @swh_retry def skipped_content_add(self, content: List[SkippedContent]) -> Dict: return self.storage.skipped_content_add(content) @swh_retry def origin_visit_add(self, visits: List[OriginVisit]) -> Iterable[OriginVisit]: return self.storage.origin_visit_add(visits) @swh_retry def metadata_fetcher_add(self, fetchers: List[MetadataFetcher],) -> None: return self.storage.metadata_fetcher_add(fetchers) @swh_retry def metadata_authority_add(self, authorities: List[MetadataAuthority]) -> None: return self.storage.metadata_authority_add(authorities) @swh_retry def raw_extrinsic_metadata_add(self, metadata: List[RawExtrinsicMetadata],) -> None: return self.storage.raw_extrinsic_metadata_add(metadata) @swh_retry def directory_add(self, directories: List[Directory]) -> Dict: return self.storage.directory_add(directories) @swh_retry def revision_add(self, revisions: List[Revision]) -> Dict: return self.storage.revision_add(revisions) @swh_retry def release_add(self, releases: List[Release]) -> Dict: return self.storage.release_add(releases) @swh_retry def snapshot_add(self, snapshots: List[Snapshot]) -> Dict: return self.storage.snapshot_add(snapshots) def clear_buffers(self, object_types: Optional[List[str]] = None) -> None: return self.storage.clear_buffers(object_types) def flush(self, object_types: Optional[List[str]] = None) -> Dict: """Specific case for buffer proxy storage failing to flush data """ return self.storage.flush(object_types) diff --git a/swh/storage/tests/__init__.py b/swh/storage/tests/__init__.py index b5710627..7eef6ebd 100644 --- a/swh/storage/tests/__init__.py +++ b/swh/storage/tests/__init__.py @@ -1,10 +1,10 @@ # Copyright (C) 2015-2018 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 from os import path -import swh.storage +import swh.storage SQL_DIR = path.join(path.dirname(swh.storage.__file__), "sql") diff --git a/swh/storage/tests/algos/test_diff.py b/swh/storage/tests/algos/test_diff.py index 8998037d..e19e26d8 100644 --- a/swh/storage/tests/algos/test_diff.py +++ b/swh/storage/tests/algos/test_diff.py @@ -1,389 +1,389 @@ # 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 # flake8: noqa -import pytest import unittest - from unittest.mock import patch +import pytest + from swh.model.hashutil import hash_to_bytes from swh.model.identifiers import directory_identifier from swh.storage.algos import diff from .test_dir_iterator import DirectoryModel def test__get_rev(swh_storage, sample_data): revision = sample_data.revision # does not exist then raises with pytest.raises(AssertionError): diff._get_rev(swh_storage, revision.id) # otherwise, we retrieve its dict representation swh_storage.revision_add([revision]) actual_revision = diff._get_rev(swh_storage, revision.id) assert actual_revision == revision.to_dict() @patch("swh.storage.algos.diff._get_rev") @patch("swh.storage.algos.dir_iterators._get_dir") class TestDiffRevisions(unittest.TestCase): def diff_revisions( self, rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ): rev_from_bytes = hash_to_bytes(rev_from) rev_to_bytes = hash_to_bytes(rev_to) def _get_rev(*args, **kwargs): if args[1] == rev_from_bytes: return {"directory": from_dir_model["target"]} else: return {"directory": to_dir_model["target"]} def _get_dir(*args, **kwargs): from_dir = from_dir_model.get_hash_data(args[1]) to_dir = to_dir_model.get_hash_data(args[1]) return from_dir if from_dir != None else to_dir mock_get_rev.side_effect = _get_rev mock_get_dir.side_effect = _get_dir changes = diff.diff_revisions( None, rev_from_bytes, rev_to_bytes, track_renaming=True ) self.assertEqual(changes, expected_changes) def test_insert_delete(self, mock_get_dir, mock_get_rev): rev_from = "898ff03e1e7925ecde3da66327d3cdc7e07625ba" rev_to = "647c3d381e67490e82cdbbe6c96e46d5e1628ce2" from_dir_model = DirectoryModel() to_dir_model = DirectoryModel() to_dir_model.add_file(b"file1", "ea15f54ca215e7920c60f564315ebb7f911a5204") to_dir_model.add_file(b"file2", "3e5faecb3836ffcadf82cc160787e35d4e2bec6a") to_dir_model.add_file(b"file3", "2ae33b2984974d35eababe4890d37fbf4bce6b2c") expected_changes = [ { "type": "insert", "from": None, "from_path": None, "to": to_dir_model.get_path_data(b"file1"), "to_path": b"file1", }, { "type": "insert", "from": None, "from_path": None, "to": to_dir_model.get_path_data(b"file2"), "to_path": b"file2", }, { "type": "insert", "from": None, "from_path": None, "to": to_dir_model.get_path_data(b"file3"), "to_path": b"file3", }, ] self.diff_revisions( rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ) from_dir_model = DirectoryModel() from_dir_model.add_file(b"file1", "ea15f54ca215e7920c60f564315ebb7f911a5204") from_dir_model.add_file(b"file2", "3e5faecb3836ffcadf82cc160787e35d4e2bec6a") from_dir_model.add_file(b"file3", "2ae33b2984974d35eababe4890d37fbf4bce6b2c") to_dir_model = DirectoryModel() expected_changes = [ { "type": "delete", "from": from_dir_model.get_path_data(b"file1"), "from_path": b"file1", "to": None, "to_path": None, }, { "type": "delete", "from": from_dir_model.get_path_data(b"file2"), "from_path": b"file2", "to": None, "to_path": None, }, { "type": "delete", "from": from_dir_model.get_path_data(b"file3"), "from_path": b"file3", "to": None, "to_path": None, }, ] self.diff_revisions( rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ) def test_onelevel_diff(self, mock_get_dir, mock_get_rev): rev_from = "898ff03e1e7925ecde3da66327d3cdc7e07625ba" rev_to = "647c3d381e67490e82cdbbe6c96e46d5e1628ce2" from_dir_model = DirectoryModel() from_dir_model.add_file(b"file1", "ea15f54ca215e7920c60f564315ebb7f911a5204") from_dir_model.add_file(b"file2", "f4a96b2000be83b61254d107046fa9777b17eb34") from_dir_model.add_file(b"file3", "d3c00f9396c6d0277727cec522ff6ad1ea0bc2da") to_dir_model = DirectoryModel() to_dir_model.add_file(b"file2", "3ee0f38ee0ea23cc2c8c0b9d66b27be4596b002b") to_dir_model.add_file(b"file3", "d3c00f9396c6d0277727cec522ff6ad1ea0bc2da") to_dir_model.add_file(b"file4", "40460b9653b1dc507e1b6eb333bd4500634bdffc") expected_changes = [ { "type": "delete", "from": from_dir_model.get_path_data(b"file1"), "from_path": b"file1", "to": None, "to_path": None, }, { "type": "modify", "from": from_dir_model.get_path_data(b"file2"), "from_path": b"file2", "to": to_dir_model.get_path_data(b"file2"), "to_path": b"file2", }, { "type": "insert", "from": None, "from_path": None, "to": to_dir_model.get_path_data(b"file4"), "to_path": b"file4", }, ] self.diff_revisions( rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ) def test_twolevels_diff(self, mock_get_dir, mock_get_rev): rev_from = "898ff03e1e7925ecde3da66327d3cdc7e07625ba" rev_to = "647c3d381e67490e82cdbbe6c96e46d5e1628ce2" from_dir_model = DirectoryModel() from_dir_model.add_file(b"file1", "ea15f54ca215e7920c60f564315ebb7f911a5204") from_dir_model.add_file( b"dir1/file1", "8335fca266811bac7ae5c8e1621476b4cf4156b6" ) from_dir_model.add_file( b"dir1/file2", "a6127d909e79f1fcb28bbf220faf86e7be7831e5" ) from_dir_model.add_file( b"dir1/file3", "18049b8d067ce1194a7e1cce26cfa3ae4242a43d" ) from_dir_model.add_file(b"file2", "d3c00f9396c6d0277727cec522ff6ad1ea0bc2da") to_dir_model = DirectoryModel() to_dir_model.add_file(b"file1", "3ee0f38ee0ea23cc2c8c0b9d66b27be4596b002b") to_dir_model.add_file(b"dir1/file2", "de3548b32a8669801daa02143a66dae21fe852fd") to_dir_model.add_file(b"dir1/file3", "18049b8d067ce1194a7e1cce26cfa3ae4242a43d") to_dir_model.add_file(b"dir1/file4", "f5c3f42aec5fe7b92276196c350cbadaf4c51f87") to_dir_model.add_file(b"file2", "d3c00f9396c6d0277727cec522ff6ad1ea0bc2da") expected_changes = [ { "type": "delete", "from": from_dir_model.get_path_data(b"dir1/file1"), "from_path": b"dir1/file1", "to": None, "to_path": None, }, { "type": "modify", "from": from_dir_model.get_path_data(b"dir1/file2"), "from_path": b"dir1/file2", "to": to_dir_model.get_path_data(b"dir1/file2"), "to_path": b"dir1/file2", }, { "type": "insert", "from": None, "from_path": None, "to": to_dir_model.get_path_data(b"dir1/file4"), "to_path": b"dir1/file4", }, { "type": "modify", "from": from_dir_model.get_path_data(b"file1"), "from_path": b"file1", "to": to_dir_model.get_path_data(b"file1"), "to_path": b"file1", }, ] self.diff_revisions( rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ) def test_insert_delete_empty_dirs(self, mock_get_dir, mock_get_rev): rev_from = "898ff03e1e7925ecde3da66327d3cdc7e07625ba" rev_to = "647c3d381e67490e82cdbbe6c96e46d5e1628ce2" from_dir_model = DirectoryModel() from_dir_model.add_file( b"dir3/file1", "ea15f54ca215e7920c60f564315ebb7f911a5204" ) to_dir_model = DirectoryModel() to_dir_model.add_file(b"dir3/file1", "ea15f54ca215e7920c60f564315ebb7f911a5204") to_dir_model.add_file(b"dir3/dir1/") expected_changes = [ { "type": "insert", "from": None, "from_path": None, "to": to_dir_model.get_path_data(b"dir3/dir1"), "to_path": b"dir3/dir1", } ] self.diff_revisions( rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ) from_dir_model = DirectoryModel() from_dir_model.add_file(b"dir1/dir2/") from_dir_model.add_file( b"dir1/file1", "ea15f54ca215e7920c60f564315ebb7f911a5204" ) to_dir_model = DirectoryModel() to_dir_model.add_file(b"dir1/file1", "ea15f54ca215e7920c60f564315ebb7f911a5204") expected_changes = [ { "type": "delete", "from": from_dir_model.get_path_data(b"dir1/dir2"), "from_path": b"dir1/dir2", "to": None, "to_path": None, } ] self.diff_revisions( rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ) def test_track_renaming(self, mock_get_dir, mock_get_rev): rev_from = "898ff03e1e7925ecde3da66327d3cdc7e07625ba" rev_to = "647c3d381e67490e82cdbbe6c96e46d5e1628ce2" from_dir_model = DirectoryModel() from_dir_model.add_file( b"file1_oldname", "ea15f54ca215e7920c60f564315ebb7f911a5204" ) from_dir_model.add_file( b"dir1/file1_oldname", "ea15f54ca215e7920c60f564315ebb7f911a5204" ) from_dir_model.add_file( b"file2_oldname", "d3c00f9396c6d0277727cec522ff6ad1ea0bc2da" ) to_dir_model = DirectoryModel() to_dir_model.add_file( b"dir1/file1_newname", "ea15f54ca215e7920c60f564315ebb7f911a5204" ) to_dir_model.add_file( b"dir2/file1_newname", "ea15f54ca215e7920c60f564315ebb7f911a5204" ) to_dir_model.add_file( b"file2_newname", "d3c00f9396c6d0277727cec522ff6ad1ea0bc2da" ) expected_changes = [ { "type": "rename", "from": from_dir_model.get_path_data(b"dir1/file1_oldname"), "from_path": b"dir1/file1_oldname", "to": to_dir_model.get_path_data(b"dir1/file1_newname"), "to_path": b"dir1/file1_newname", }, { "type": "rename", "from": from_dir_model.get_path_data(b"file1_oldname"), "from_path": b"file1_oldname", "to": to_dir_model.get_path_data(b"dir2/file1_newname"), "to_path": b"dir2/file1_newname", }, { "type": "rename", "from": from_dir_model.get_path_data(b"file2_oldname"), "from_path": b"file2_oldname", "to": to_dir_model.get_path_data(b"file2_newname"), "to_path": b"file2_newname", }, ] self.diff_revisions( rev_from, rev_to, from_dir_model, to_dir_model, expected_changes, mock_get_dir, mock_get_rev, ) diff --git a/swh/storage/tests/algos/test_origin.py b/swh/storage/tests/algos/test_origin.py index 367b0d99..6d1d40e4 100644 --- a/swh/storage/tests/algos/test_origin.py +++ b/swh/storage/tests/algos/test_origin.py @@ -1,355 +1,353 @@ # 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, - iter_origin_visits, - iter_origin_visit_statuses, ) from swh.storage.interface import ListOrder -from swh.storage.utils import now - 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 """ # 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 """ 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=origin1.url, visit=ov1.visit, date=ov1.date + datetime.timedelta(seconds=10), # so it's not ignored status="partial", snapshot=None, ) # origin visit status 2 for origin visit 1 ovs12 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) # origin visit status 1 for origin visit 2 ovs21 = OriginVisitStatus( origin=origin2.url, visit=ov2.visit, date=ov2.date + datetime.timedelta(seconds=10), # so it's not ignored status="ongoing", snapshot=None, ) # origin visit status 2 for origin visit 2 ovs22 = OriginVisitStatus( origin=origin2.url, visit=ov2.visit, date=date_now, 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 """ 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_ov1, actual_ovs12 = origin_get_latest_visit_status( swh_storage, origin1.url, type=sample_data.type_visit1 ) assert isinstance(actual_ov1, OriginVisit) assert isinstance(actual_ovs12, OriginVisitStatus) assert actual_ov1.origin == ov1.origin assert actual_ov1.visit == ov1.visit assert actual_ov1.type == sample_data.type_visit1 assert actual_ovs12 == ovs12 # take the most recent visit with type_visit2 actual_ov2, actual_ovs22 = origin_get_latest_visit_status( swh_storage, origin2.url, type=sample_data.type_visit2 ) assert isinstance(actual_ov2, OriginVisit) assert isinstance(actual_ovs22, OriginVisitStatus) assert actual_ov2.origin == ov2.origin assert actual_ov2.visit == ov2.visit assert actual_ov2.type == sample_data.type_visit2 assert actual_ovs22 == ovs22 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_ov1, actual_ovs11 = origin_get_latest_visit_status( swh_storage, origin1.url, allowed_statuses=["partial"] ) assert actual_ov1.origin == ov1.origin assert actual_ov1.visit == ov1.visit assert actual_ov1.type == sample_data.type_visit1 assert actual_ovs11 == ovs11 # both status exist, take the latest one actual_ov1, actual_ovs12 = origin_get_latest_visit_status( swh_storage, origin1.url, allowed_statuses=["partial", "ongoing"] ) assert actual_ov1.origin == ov1.origin assert actual_ov1.visit == ov1.visit assert actual_ov1.type == sample_data.type_visit1 assert actual_ovs12 == ovs12 assert isinstance(actual_ov1, OriginVisit) assert isinstance(actual_ovs12, OriginVisitStatus) assert actual_ov1.origin == ov1.origin assert actual_ov1.visit == ov1.visit assert actual_ov1.type == sample_data.type_visit1 assert actual_ovs12 == ovs12 # take the most recent visit with type_visit2 actual_ov2, actual_ovs22 = origin_get_latest_visit_status( swh_storage, origin2.url, allowed_statuses=["full"] ) assert actual_ov2.origin == ov2.origin assert actual_ov2.visit == ov2.visit assert actual_ov2.type == sample_data.type_visit2 assert actual_ovs22 == ovs22 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_ov2, actual_ovs22 = origin_get_latest_visit_status( swh_storage, origin2.url, require_snapshot=True ) assert actual_ov2.origin == ov2.origin assert actual_ov2.visit == ov2.visit assert actual_ov2.type == ov2.type assert actual_ovs22 == ovs22 date_now = now() # Add another visit swh_storage.origin_visit_add( [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 ov2, ovs22 = origin_get_latest_visit_status( swh_storage, origin2.url, require_snapshot=True ) assert actual_ov2.origin == ov2.origin assert actual_ov2.visit == ov2.visit assert actual_ov2.type == ov2.type assert actual_ovs22 == ovs22 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=origin1.url, visit=ov1.visit, date=ov1.date, 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=origin1.url, visit=ov1.visit, date=status_date, 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_revisions_walker.py b/swh/storage/tests/algos/test_revisions_walker.py index c8ba0477..7eeecc1f 100644 --- a/swh/storage/tests/algos/test_revisions_walker.py +++ b/swh/storage/tests/algos/test_revisions_walker.py @@ -1,511 +1,510 @@ # Copyright (C) 2018-2019 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 import unittest - from unittest.mock import patch from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.storage.algos.revisions_walker import get_revisions_walker # For those tests, we will walk the following revisions history # with different orderings: # # * commit b364f53155044e5308a0f73abb3b5f01995a5b7d # |\ Merge: 836d498 b94886c # | | Author: Adam # | | AuthorDate: Fri Oct 4 12:50:49 2013 +0200 # | | Commit: Adam # | | CommitDate: Fri Oct 4 12:50:49 2013 +0200 # | | # | | Merge branch 'release/1.0' # | | # | * commit b94886c500c46e32dc3d7ebae8a5409accd592e5 # | | Author: Adam # | | AuthorDate: Fri Oct 4 12:50:38 2013 +0200 # | | Commit: Adam # | | CommitDate: Fri Oct 4 12:50:38 2013 +0200 # | | # | | updating poms for 1.0 release # | | # | * commit 0cb6b4611d65bee0f57821dac7f611e2f8a02433 # | | Author: Adam # | | AuthorDate: Fri Oct 4 12:50:38 2013 +0200 # | | Commit: Adam # | | CommitDate: Fri Oct 4 12:50:38 2013 +0200 # | | # | | updating poms for 1.0 release # | | # | * commit 2b0240c6d682bad51532eec15b8a7ed6b75c8d31 # | | Author: Adam Janicki # | | AuthorDate: Fri Oct 4 12:50:22 2013 +0200 # | | Commit: Adam Janicki # | | CommitDate: Fri Oct 4 12:50:22 2013 +0200 # | | # | | For 1.0 release. Allow untracked. # | | # | * commit b401c50863475db4440c85c10ac0b6423b61554d # | | Author: Adam # | | AuthorDate: Fri Oct 4 12:48:12 2013 +0200 # | | Commit: Adam # | | CommitDate: Fri Oct 4 12:48:12 2013 +0200 # | | # | | updating poms for 1.0 release # | | # | * commit 9c5051397e5c2e0c258bb639c3dd34406584ca10 # |/ Author: Adam Janicki # | AuthorDate: Fri Oct 4 12:47:48 2013 +0200 # | Commit: Adam Janicki # | CommitDate: Fri Oct 4 12:47:48 2013 +0200 # | # | For 1.0 release. # | # * commit 836d498396fb9b5d45c896885f84d8d60a5651dc # | Author: Adam Janicki # | AuthorDate: Fri Oct 4 12:08:16 2013 +0200 # | Commit: Adam Janicki # | CommitDate: Fri Oct 4 12:08:16 2013 +0200 # | # | Add ignores # | # * commit ee96c2a2d397b79070d2b6fe3051290963748358 # | Author: Adam # | AuthorDate: Fri Oct 4 10:48:16 2013 +0100 # | Commit: Adam # | CommitDate: Fri Oct 4 10:48:16 2013 +0100 # | # | Reset author # | # * commit 8f89dda8e072383cf50d42532ae8f52ad89f8fdf # Author: Adam # AuthorDate: Fri Oct 4 02:20:19 2013 -0700 # Commit: Adam # CommitDate: Fri Oct 4 02:20:19 2013 -0700 # # Initial commit # raw dump of the above history in swh format _revisions_list = [ { "author": { "email": b"adam.janicki@roche.com", # noqa "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer_date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883849}, }, "date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883849}, }, "directory": b"\xefX\xe7\xa6\\\xda\xdf\xfdH\xdbH\xfbq\x96@{\x98?9\xfe", "id": b"\xb3d\xf51U\x04NS\x08\xa0\xf7:\xbb;_\x01\x99Z[}", "message": b"Merge branch 'release/1.0'", "metadata": None, "parents": [ b"\x83mI\x83\x96\xfb\x9b]E\xc8\x96\x88_\x84\xd8\xd6\nVQ\xdc", b"\xb9H\x86\xc5\x00\xc4n2\xdc=~\xba\xe8\xa5@\x9a\xcc\xd5\x92\xe5", ], # noqa "synthetic": False, "type": "git", }, { "author": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer_date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883838}, }, "date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883838}, }, "directory": b"\xefX\xe7\xa6\\\xda\xdf\xfdH\xdbH\xfbq\x96@{\x98?9\xfe", "id": b"\xb9H\x86\xc5\x00\xc4n2\xdc=~\xba\xe8\xa5@\x9a\xcc\xd5\x92\xe5", "message": b"updating poms for 1.0 release", "metadata": None, "parents": [ b"\x0c\xb6\xb4a\x1de\xbe\xe0\xf5x!\xda\xc7\xf6\x11\xe2\xf8\xa0$3" ], # noqa "synthetic": False, "type": "git", }, { "author": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer_date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883838}, }, "date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883838}, }, "directory": b"\xefX\xe7\xa6\\\xda\xdf\xfdH\xdbH\xfbq\x96@{\x98?9\xfe", "id": b"\x0c\xb6\xb4a\x1de\xbe\xe0\xf5x!\xda\xc7\xf6\x11\xe2\xf8\xa0$3", "message": b"updating poms for 1.0 release", "metadata": None, "parents": [b"+\x02@\xc6\xd6\x82\xba\xd5\x152\xee\xc1[\x8a~\xd6\xb7\\\x8d1"], "synthetic": False, "type": "git", }, { "author": { "email": b"janickia", "fullname": b"Adam Janicki ", "id": 8040906, "name": b"Adam Janicki", }, "committer": { "email": b"janickia", "fullname": b"Adam Janicki ", "id": 8040906, "name": b"Adam Janicki", }, "committer_date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883822}, }, "date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883822}, }, "directory": b"\xefX\xe7\xa6\\\xda\xdf\xfdH\xdbH\xfbq\x96@{\x98?9\xfe", "id": b"+\x02@\xc6\xd6\x82\xba\xd5\x152\xee\xc1[\x8a~\xd6\xb7\\\x8d1", "message": b"For 1.0 release. Allow untracked.\n", "metadata": None, "parents": [b"\xb4\x01\xc5\x08cG]\xb4D\x0c\x85\xc1\n\xc0\xb6B;aUM"], "synthetic": False, "type": "git", }, { "author": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer_date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883692}, }, "date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883692}, }, "directory": b"d@\xe7\x143w\xcb\xf7\xad\xae\x91\xd5\xec\xd8\x95\x82" b"\x02\xa6=\x1b", "id": b"\xb4\x01\xc5\x08cG]\xb4D\x0c\x85\xc1\n\xc0\xb6B;aUM", "message": b"updating poms for 1.0 release", "metadata": None, "parents": [b"\x9cPQ9~\\.\x0c%\x8b\xb69\xc3\xdd4@e\x84\xca\x10"], "synthetic": False, "type": "git", }, { "author": { "email": b"janickia", "fullname": b"Adam Janicki ", "id": 8040906, "name": b"Adam Janicki", }, "committer": { "email": b"janickia", "fullname": b"Adam Janicki ", "id": 8040906, "name": b"Adam Janicki", }, "committer_date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883668}, }, "date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380883668}, }, "directory": b"\n\x857\x94r\xbe\xcc\x04=\xe9}\xe5\xfd\xdf?nR\xe6\xa7\x9e", "id": b"\x9cPQ9~\\.\x0c%\x8b\xb69\xc3\xdd4@e\x84\xca\x10", "message": b"For 1.0 release.\n", "metadata": None, "parents": [b"\x83mI\x83\x96\xfb\x9b]E\xc8\x96\x88_\x84\xd8\xd6\nVQ\xdc"], "synthetic": False, "type": "git", }, { "author": { "email": b"janickia", "fullname": b"Adam Janicki ", "id": 8040906, "name": b"Adam Janicki", }, "committer": { "email": b"janickia", "fullname": b"Adam Janicki ", "id": 8040906, "name": b"Adam Janicki", }, "committer_date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380881296}, }, "date": { "negative_utc": None, "offset": 120, "timestamp": {"microseconds": 0, "seconds": 1380881296}, }, "directory": b".\xf9\xa5\xcb\xb0\xd3\xdc\x9b{\xb8\x81\x03l\xe2P\x16c\x0b|\xe6", # noqa "id": b"\x83mI\x83\x96\xfb\x9b]E\xc8\x96\x88_\x84\xd8\xd6\nVQ\xdc", "message": b"Add ignores\n", "metadata": None, "parents": [b"\xee\x96\xc2\xa2\xd3\x97\xb7\x90p\xd2\xb6\xfe0Q)\tct\x83X"], "synthetic": False, "type": "git", }, { "author": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer_date": { "negative_utc": None, "offset": 60, "timestamp": {"microseconds": 0, "seconds": 1380880096}, }, "date": { "negative_utc": None, "offset": 60, "timestamp": {"microseconds": 0, "seconds": 1380880096}, }, "directory": b"\xc7r\xc4\x9f\xc0$\xd4\xab\xff\xcb]\xf6<\xcb\x8b~\xec\xc4\xd1)", # noqa "id": b"\xee\x96\xc2\xa2\xd3\x97\xb7\x90p\xd2\xb6\xfe0Q)\tct\x83X", "message": b"Reset author\n", "metadata": None, "parents": [b"\x8f\x89\xdd\xa8\xe0r8<\xf5\rBS*\xe8\xf5*\xd8\x9f\x8f\xdf"], "synthetic": False, "type": "git", }, { "author": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer": { "email": b"adam.janicki@roche.com", "fullname": b"Adam ", "id": 8040905, "name": b"Adam", }, "committer_date": { "negative_utc": None, "offset": -420, "timestamp": {"microseconds": 0, "seconds": 1380878419}, }, "date": { "negative_utc": None, "offset": -420, "timestamp": {"microseconds": 0, "seconds": 1380878419}, }, "directory": b"WS\xbaX\xd6x{q\x8f\x020i\xc5\x95\xa01\xf7y\xb2\x80", "id": b"\x8f\x89\xdd\xa8\xe0r8<\xf5\rBS*\xe8\xf5*\xd8\x9f\x8f\xdf", "message": b"Initial commit\n", "metadata": None, "parents": [], "synthetic": False, "type": "git", }, ] _rev_start = "b364f53155044e5308a0f73abb3b5f01995a5b7d" _rev_missing = "836d498396fb9b5d45c896885f84d8d60a5651dc" class RevisionsWalkerTest(unittest.TestCase): def check_revisions_ordering( self, rev_walker_type, expected_result, truncated_history ): with patch("swh.storage.postgresql.storage.Storage") as MockStorage: storage = MockStorage() if not truncated_history: storage.revision_log.return_value = _revisions_list else: revs_lists_truncated = [ None if hash_to_hex(rev["id"]) == _rev_missing else rev for rev in _revisions_list ] storage.revision_log.return_value = revs_lists_truncated revs_walker = get_revisions_walker( rev_walker_type, storage, hash_to_bytes(_rev_start) ) self.assertEqual( list(map(hash_to_bytes, expected_result)), [rev["id"] for rev in revs_walker], ) self.assertEqual(revs_walker.is_history_truncated(), truncated_history) if truncated_history: missing_revs = revs_walker.missing_revisions() self.assertEqual(missing_revs, {hash_to_bytes(_rev_missing)}) else: self.assertEqual(revs_walker.missing_revisions(), set()) def test_revisions_walker_committer_date(self): # revisions should be returned in reverse chronological order # of their committer date expected_result = [ "b364f53155044e5308a0f73abb3b5f01995a5b7d", "b94886c500c46e32dc3d7ebae8a5409accd592e5", "0cb6b4611d65bee0f57821dac7f611e2f8a02433", "2b0240c6d682bad51532eec15b8a7ed6b75c8d31", "b401c50863475db4440c85c10ac0b6423b61554d", "9c5051397e5c2e0c258bb639c3dd34406584ca10", "836d498396fb9b5d45c896885f84d8d60a5651dc", "ee96c2a2d397b79070d2b6fe3051290963748358", "8f89dda8e072383cf50d42532ae8f52ad89f8fdf", ] self.check_revisions_ordering( "committer_date", expected_result, truncated_history=False ) def test_revisions_walker_dfs(self): # revisions should be returned in the same order they are # visited when performing a depth-first search in pre order # on the revisions DAG expected_result = [ "b364f53155044e5308a0f73abb3b5f01995a5b7d", "836d498396fb9b5d45c896885f84d8d60a5651dc", "ee96c2a2d397b79070d2b6fe3051290963748358", "8f89dda8e072383cf50d42532ae8f52ad89f8fdf", "b94886c500c46e32dc3d7ebae8a5409accd592e5", "0cb6b4611d65bee0f57821dac7f611e2f8a02433", "2b0240c6d682bad51532eec15b8a7ed6b75c8d31", "b401c50863475db4440c85c10ac0b6423b61554d", "9c5051397e5c2e0c258bb639c3dd34406584ca10", ] self.check_revisions_ordering("dfs", expected_result, truncated_history=False) def test_revisions_walker_dfs_post(self): # revisions should be returned in the same order they are # visited when performing a depth-first search in post order # on the revisions DAG expected_result = [ "b364f53155044e5308a0f73abb3b5f01995a5b7d", "b94886c500c46e32dc3d7ebae8a5409accd592e5", "0cb6b4611d65bee0f57821dac7f611e2f8a02433", "2b0240c6d682bad51532eec15b8a7ed6b75c8d31", "b401c50863475db4440c85c10ac0b6423b61554d", "9c5051397e5c2e0c258bb639c3dd34406584ca10", "836d498396fb9b5d45c896885f84d8d60a5651dc", "ee96c2a2d397b79070d2b6fe3051290963748358", "8f89dda8e072383cf50d42532ae8f52ad89f8fdf", ] self.check_revisions_ordering( "dfs_post", expected_result, truncated_history=False ) def test_revisions_walker_bfs(self): # revisions should be returned in the same order they are # visited when performing a breadth-first search on the # revisions DAG expected_result = [ "b364f53155044e5308a0f73abb3b5f01995a5b7d", "836d498396fb9b5d45c896885f84d8d60a5651dc", "b94886c500c46e32dc3d7ebae8a5409accd592e5", "ee96c2a2d397b79070d2b6fe3051290963748358", "0cb6b4611d65bee0f57821dac7f611e2f8a02433", "8f89dda8e072383cf50d42532ae8f52ad89f8fdf", "2b0240c6d682bad51532eec15b8a7ed6b75c8d31", "b401c50863475db4440c85c10ac0b6423b61554d", "9c5051397e5c2e0c258bb639c3dd34406584ca10", ] self.check_revisions_ordering("bfs", expected_result, truncated_history=False) def test_revisions_walker_truncated_history(self): expected_result = [ "b364f53155044e5308a0f73abb3b5f01995a5b7d", "b94886c500c46e32dc3d7ebae8a5409accd592e5", "0cb6b4611d65bee0f57821dac7f611e2f8a02433", "2b0240c6d682bad51532eec15b8a7ed6b75c8d31", "b401c50863475db4440c85c10ac0b6423b61554d", "9c5051397e5c2e0c258bb639c3dd34406584ca10", ] for revs_walker_type in ("committer_date", "bfs", "dfs", "dfs_post"): self.check_revisions_ordering( revs_walker_type, expected_result, truncated_history=True ) diff --git a/swh/storage/tests/algos/test_snapshot.py b/swh/storage/tests/algos/test_snapshot.py index 0c12a942..2759e7f4 100644 --- a/swh/storage/tests/algos/test_snapshot.py +++ b/swh/storage/tests/algos/test_snapshot.py @@ -1,268 +1,267 @@ # 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 import pytest from swh.model.collections import ImmutableDict -from swh.model.hypothesis_strategies import snapshots, branch_names, branch_targets +from swh.model.hypothesis_strategies import branch_names, branch_targets, snapshots from swh.model.model import OriginVisit, OriginVisitStatus, Snapshot - from swh.storage.algos.snapshot import ( snapshot_get_all_branches, snapshot_get_latest, snapshot_id_get_from_revision, visits_and_snapshots_get_from_revision, ) from swh.storage.utils import now @pytest.fixture def swh_storage_backend_config(): yield { "cls": "memory", "journal_writer": None, } @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 @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=ImmutableDict( (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=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,)] ) 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=origin.url, visit=ov1.visit, date=date_visit2, status="partial", snapshot=complete_snapshot.id, ), OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=now(), 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=origin.url, visit=ov1.visit, date=date_visit2, status="partial", snapshot=complete_snapshot.id, ), OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=now(), 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)] diff --git a/swh/storage/tests/conftest.py b/swh/storage/tests/conftest.py index ff19af87..51f95939 100644 --- a/swh/storage/tests/conftest.py +++ b/swh/storage/tests/conftest.py @@ -1,66 +1,66 @@ # 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 pytest import multiprocessing.util from hypothesis import 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 # 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",}} @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 8edce012..2a32824e 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_cran.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_cran.py @@ -1,221 +1,219 @@ # 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 call, Mock +from unittest.mock import Mock, call from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, RawExtrinsicMetadata, ) - -from swh.storage.migrate_extrinsic_metadata import handle_row, cran_package_from_url - +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", ) SWH_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ) 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", "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, ), "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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:000361aa33842cbdea5fa6e77db696b937ebd269" ), discovery_date=datetime.datetime( 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, ), ] ), ] 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>', "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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0000d4ef5e166122aee6862ad38a18ce5386cc3e" ), discovery_date=datetime.datetime( 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, ), ] ), ] diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py b/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py index 76215ef9..a923f985 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_debian.py @@ -1,564 +1,563 @@ # 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 call, Mock, patch as _patch +from unittest.mock import Mock, call +from unittest.mock import patch as _patch import attr import pytest from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Revision, RevisionType, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) - from swh.storage import get_storage from swh.storage.interface import ListOrder, PagedResult -from swh.storage.migrate_extrinsic_metadata import handle_row, debian_origins_from_row - +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", ) SWH_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ) 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, ), 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", "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", "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,)] ) # 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,},) 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,) }, ) 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=60, negative_utc=False, ), committer_date=TimestampWithTimezone( timestamp=Timestamp(seconds=1580076204, microseconds=0), offset=60, negative_utc=False, ), 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", "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=60, negative_utc=False, ), committer_date=TimestampWithTimezone( timestamp=Timestamp(seconds=1580076204, microseconds=0), offset=60, negative_utc=False, ), 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", "date": datetime.datetime( 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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0000036c311ef33a281b05688f6eadcfc0943aee" ), discovery_date=datetime.datetime( 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, ), ] ), ] 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", "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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:000001c28c8fca01b904de92a2640a866ce03cb7" ), 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, ), ] ) ] diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py b/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py index 1c018ac8..2edca7ce 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py @@ -1,1167 +1,1165 @@ # 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 call, Mock, MagicMock +from unittest.mock import MagicMock, Mock, call from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, RawExtrinsicMetadata, ) - from swh.storage.migrate_extrinsic_metadata import ( DEPOSIT_COLS, - handle_row, cran_package_from_url, + handle_row, ) - FETCHER = MetadataFetcher( 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={}, ) 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", "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.swh_id_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.swh_id_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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:022310df16fd9e4d4f81fe36a142e82db977c01d" ), 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:022310df16fd9e4d4f81fe36a142e82db977c01d" ), 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, ), ] ), ] 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", "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.swh_id_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.swh_id_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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0116cab71964d59c8570b4c5729b28bdd63c9b46" ), 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0116cab71964d59c8570b4c5729b28bdd63c9b46" ), 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, ), ] ), ] 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', "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.swh_id_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.swh_id_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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0122966e509317aece6a41d0f088da733cc09d0f" ), 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0122966e509317aece6a41d0f088da733cc09d0f" ), 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, ), ] ), ] 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", "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.swh_id_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.swh_id_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.swh_id_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.swh_id_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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:09356053c49ad0f9e62e51c29d3e617c791140df" ), 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:09356053c49ad0f9e62e51c29d3e617c791140df" ), 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:09356053c49ad0f9e62e51c29d3e617c791140df" ), 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, ), ] ), ] 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&", "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,}, } 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", "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", "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.swh_id_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.swh_id_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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:03987f056eaf4596cd20d7b2ee01c9b84ceddfa8" ), 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, ), ] ), # 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", "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.swh_id_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.swh_id_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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:2d7bce631fc791080311eb835c47428e586a6ea4" ), 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, ), ] ), # 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",}, "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", "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.swh_id_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.swh_id_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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:034076f3f41ee1204eb9f64082cbe6e950d7bb8a" ), 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:034076f3f41ee1204eb9f64082cbe6e950d7bb8a" ), 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, ), ] ), ] diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py b/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py index a0479357..2e0f5d52 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py @@ -1,108 +1,106 @@ # 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 call, Mock +from unittest.mock import Mock, call from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, RawExtrinsicMetadata, ) - -from swh.storage.migrate_extrinsic_metadata import handle_row, cran_package_from_url - +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", ) SWH_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ) 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", "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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:001c71458e405b25baccc80b99f6634dff9d2b18" ), 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, ), ] ), ] diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py b/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py index 58541e67..b1bcdcac 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py @@ -1,124 +1,122 @@ # 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 call, Mock +from unittest.mock import Mock, call from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, RawExtrinsicMetadata, ) - -from swh.storage.migrate_extrinsic_metadata import handle_row, cran_package_from_url - +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", ) 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={}, ) 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", "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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0001ba4dd05394850211d7b3854d9913d23ae379" ), 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:0001ba4dd05394850211d7b3854d9913d23ae379" ), 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, ), ] ), ] diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py b/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py index ae82d559..4f8890ba 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_npm.py @@ -1,376 +1,374 @@ # 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 call, Mock +from unittest.mock import Mock, call from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, RawExtrinsicMetadata, ) - 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", ) NPM_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", metadata={}, ) SWH_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ) 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", "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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:000002a49bba17ca8cf37f5f3d16aaacf95360fc" ), discovery_date=datetime.datetime( 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:000002a49bba17ca8cf37f5f3d16aaacf95360fc" ), discovery_date=datetime.datetime( 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, ), ] ), ] 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", "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,}, } 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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:000004aeed09ee089c781264c04d2564fd58feb5" ), discovery_date=datetime.datetime( 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:000004aeed09ee089c781264c04d2564fd58feb5" ), discovery_date=datetime.datetime( 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, ), ] ), ] 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", "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,}, } 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( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:00002019c5775874bced007a529bd3b78bf60457" ), discovery_date=datetime.datetime( 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, ), ] ), call.raw_extrinsic_metadata_add( [ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=parse_swhid( "swh:1:rev:00002019c5775874bced007a529bd3b78bf60457" ), discovery_date=datetime.datetime( 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, ), ] ), ] diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py b/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py index 52df7bcc..21c0e346 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py @@ -1,494 +1,492 @@ # 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 attr from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Snapshot, SnapshotBranch, TargetType, ) - from swh.storage import get_storage from swh.storage.interface import PagedResult from swh.storage.migrate_extrinsic_metadata import ( handle_row, pypi_project_from_filename, ) - FETCHER = MetadataFetcher( name="migrate-extrinsic-metadata-from-revisions", version="0.0.1", ) PYPI_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://pypi.org/", ) SWH_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", ) 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"), ] for (filename, project) in files: assert pypi_project_from_filename(filename) == project 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", "date": datetime.datetime( 2019, 11, 11, 6, 21, 20, tzinfo=datetime.timezone.utc, ), "committer_date": datetime.datetime( 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 = parse_swhid("swh:1:rev:000007617b53e7b1458f695dd07de4ce55af1517") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=PYPI_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=revision_swhid, discovery_date=datetime.datetime( 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, ), ], next_page_token=None, ) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=revision_swhid, discovery_date=datetime.datetime( 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, ), ], next_page_token=None, ) def test_pypi_2(): """Tests loading a revision generated by an old PyPI loader that does not have a provider, but has 'project' metadata.""" 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", "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 = parse_swhid("swh:1:rev:000004d6382c4ad4c0519266626c36551f0e51ca") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=PYPI_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=revision_swhid, discovery_date=datetime.datetime( 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, ), ], next_page_token=None, ) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=revision_swhid, discovery_date=datetime.datetime( 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, ), ], next_page_token=None, ) def test_pypi_3(): """Tests loading a revision generated by a very old PyPI loader that does not have a provider or has 'project' metadata.""" 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", "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 = parse_swhid("swh:1:rev:4ea9917cdf53cd13534a042e4eb3787b86c834d2") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=PYPI_AUTHORITY, ) == PagedResult(results=[], next_page_token=None,) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=revision_swhid, discovery_date=datetime.datetime( 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, ), ], 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, "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, ) }, ) ] ) 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 = parse_swhid("swh:1:rev:4ea9917cdf53cd13534a042e4eb3787b86c834d2") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=PYPI_AUTHORITY, ) == PagedResult(results=[], next_page_token=None,) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, revision_swhid, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=revision_swhid, discovery_date=datetime.datetime( 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, ), ], next_page_token=None, ) diff --git a/swh/storage/tests/storage_data.py b/swh/storage/tests/storage_data.py index fe904176..12429721 100644 --- a/swh/storage/tests/storage_data.py +++ b/swh/storage/tests/storage_data.py @@ -1,553 +1,552 @@ # 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 datetime +from typing import Tuple import attr -from typing import Tuple - -from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model import from_disk +from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.identifiers import parse_swhid from swh.model.model import ( Content, Directory, DirectoryEntry, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, ObjectType, Origin, OriginVisit, Person, RawExtrinsicMetadata, Release, Revision, RevisionType, SkippedContent, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) class StorageData: """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(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("4ea8c6b2f54445e5dd1a9d5bb2afd875d66f3150"), 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("377aa5fcd944fbabf502dbfda55cd14d33c8c3c6"), 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=120, negative_utc=False, ), 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=120, negative_utc=False, ), parents=(), type=RevisionType.GIT, directory=directory.id, metadata={ "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("df7a6f6a99671fb7f7343641aff983a314ef6161"), 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,), offset=-720, negative_utc=False, ), committer=Person( name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ", ), committer_date=TimestampWithTimezone( timestamp=Timestamp(seconds=1123456789, microseconds=220000,), offset=0, negative_utc=False, ), parents=tuple([revision.id]), type=RevisionType.GIT, directory=directory2.id, metadata=None, extra_headers=(), synthetic=False, ) revision3 = Revision( id=hash_to_bytes("2cbd7bb22c653bbb23a29657852a50a01b591d46"), 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,), offset=-720, negative_utc=False, ), committer=Person( name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ", ), committer_date=TimestampWithTimezone( timestamp=Timestamp(seconds=1127351742, microseconds=220000,), offset=0, negative_utc=False, ), parents=tuple([revision.id, revision2.id]), type=RevisionType.GIT, directory=directory2.id, metadata=None, extra_headers=(), synthetic=True, ) revision4 = Revision( id=hash_to_bytes("88cd5126fc958ed70089d5340441a1c2477bcc20"), message=b"parent of self.revision2", author=Person( name=b"me", email=b"me@soft.heri", fullname=b"me ", ), date=TimestampWithTimezone( timestamp=Timestamp(seconds=1234567843, microseconds=220000,), offset=-720, negative_utc=False, ), committer=Person( name=b"committer-dude", email=b"committer@dude.com", fullname=b"committer-dude ", ), committer_date=TimestampWithTimezone( timestamp=Timestamp(seconds=1244567843, microseconds=220000,), offset=-720, negative_utc=False, ), parents=tuple([revision3.id]), type=RevisionType.GIT, directory=directory.id, metadata=None, extra_headers=(), synthetic=False, ) revisions: Tuple[Revision, ...] = (revision, revision2, revision3, revision4) 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, origin2 = origins[:2] metadata_authority = MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url="http://hal.inria.example.com/", metadata={"location": "France"}, ) metadata_authority2 = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="http://wikidata.example.com/", metadata={}, ) authorities: Tuple[MetadataAuthority, ...] = ( metadata_authority, metadata_authority2, ) metadata_fetcher = MetadataFetcher( name="swh-deposit", version="0.0.1", metadata={"sword_version": "2"}, ) metadata_fetcher2 = MetadataFetcher( name="swh-example", version="0.0.1", metadata={}, ) 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_visit2 = OriginVisit( 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_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 ", ), date=TimestampWithTimezone( timestamp=Timestamp(seconds=1234567890, microseconds=0), offset=42, negative_utc=False, ), target=revision.id, target_type=ObjectType.REVISION, message=b"synthetic release", synthetic=True, ) release2 = Release( id=hash_to_bytes("6902bd4c82b7d19a421d224aedab2b74197e420d"), name=b"v0.0.2", author=Person( name=b"tony", email=b"ar@dumont.fr", fullname=b"tony ", ), date=TimestampWithTimezone( timestamp=Timestamp(seconds=1634366813, microseconds=0), offset=-120, negative_utc=False, ), 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("3e9050196aa288264f2a9d279d6abab8b158448b"), 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=-120, negative_utc=False, ), 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, ), }, ) empty_snapshot = Snapshot( id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), branches={}, ) complete_snapshot = Snapshot( id=hash_to_bytes("a56ce2d81c190023bb99a3a36279307522cb85f6"), branches={ b"directory": SnapshotBranch( target=directory.id, target_type=TargetType.DIRECTORY, ), b"directory2": SnapshotBranch( target=directory2.id, target_type=TargetType.DIRECTORY, ), b"content": SnapshotBranch( target=content.sha1_git, target_type=TargetType.CONTENT, ), b"alias": SnapshotBranch(target=b"revision", target_type=TargetType.ALIAS,), b"revision": SnapshotBranch( target=revision.id, target_type=TargetType.REVISION, ), b"release": SnapshotBranch( target=release.id, target_type=TargetType.RELEASE, ), b"snapshot": SnapshotBranch( target=empty_snapshot.id, target_type=TargetType.SNAPSHOT, ), b"dangling": None, }, ) snapshots: Tuple[Snapshot, ...] = (snapshot, empty_snapshot, complete_snapshot) content_metadata1 = RawExtrinsicMetadata( type=MetadataTargetType.CONTENT, id=parse_swhid(f"swh:1:cnt:{hash_to_hex(content.sha1_git)}"), origin=origin.url, 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"}', ) content_metadata2 = RawExtrinsicMetadata( type=MetadataTargetType.CONTENT, id=parse_swhid(f"swh:1:cnt:{hash_to_hex(content.sha1_git)}"), origin=origin2.url, 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", ) content_metadata3 = RawExtrinsicMetadata( type=MetadataTargetType.CONTENT, id=parse_swhid(f"swh:1:cnt:{hash_to_hex(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=parse_swhid(f"swh:1:snp:{hash_to_hex(snapshot.id)}"), release=parse_swhid(f"swh:1:rel:{hash_to_hex(release.id)}"), revision=parse_swhid(f"swh:1:rev:{hash_to_hex(revision.id)}"), directory=parse_swhid(f"swh:1:dir:{hash_to_hex(directory.id)}"), path=b"/foo/bar", ) content_metadata: Tuple[RawExtrinsicMetadata, ...] = ( content_metadata1, content_metadata2, content_metadata3, ) origin_metadata1 = RawExtrinsicMetadata( type=MetadataTargetType.ORIGIN, id=origin.url, 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( type=MetadataTargetType.ORIGIN, id=origin.url, 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( type=MetadataTargetType.ORIGIN, id=origin.url, 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, ) diff --git a/swh/storage/tests/storage_tests.py b/swh/storage/tests/storage_tests.py index 8409dc97..911d6d98 100644 --- a/swh/storage/tests/storage_tests.py +++ b/swh/storage/tests/storage_tests.py @@ -1,3929 +1,3927 @@ # 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 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 import attr +from hypothesis import HealthCheck, given, settings, strategies import pytest -from hypothesis import given, strategies, settings, HealthCheck - -from typing import Any, ClassVar, Dict, Iterator, Optional - from swh.model import from_disk from swh.model.hashutil import hash_to_bytes +from swh.model.hypothesis_strategies import objects from swh.model.identifiers import SWHID from swh.model.model import ( Content, Directory, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, Person, Revision, SkippedContent, Snapshot, TargetType, ) -from swh.model.hypothesis_strategies import objects from swh.storage import get_storage from swh.storage.common import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.interface import ListOrder, PagedResult, StorageInterface from swh.storage.utils import content_hex_hashes, now, 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.""" 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. """ 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 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() 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_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 @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 @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 swh_storage.content_add([cont, cont2]) contents = [cont.sha1_git, cont2.sha1_git, missing_cont.sha1_git] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont.sha1_git] 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 """ 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 def test_content_get(self, swh_storage, sample_data): cont1, cont2 = sample_data.contents[:2] swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get([cont1.sha1, cont2.sha1]) # 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 def test_content_get_missing_sha1(self, swh_storage, sample_data): 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( [cont1.sha1, cont2.sha1, missing_cont.sha1] ) 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.directories[1] 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 == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 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_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} 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_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], 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_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} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 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),] ) 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[:2]) origin_urls = [o.url for o in origins] assert swh_storage.origin_get(origin_urls) == [None, None] stats = swh_storage.origin_add(origins) assert stats == {"origin:add": 2} actual_origins = swh_storage.origin_get(origin_urls) assert actual_origins == origins assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origins[0]), ("origin", origins[1]),] ) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 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),] ) 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),] ) 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),] ) 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),] ) 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] 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_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, ), ] )[0] ovs1 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_visit1, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_visit2, status="partial", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_visit3, 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,)] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=None, ) ] ) swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(origins) assert stats["origin_visit"] == len(origins) * len(visits) random_ov, random_ovs = swh_storage.origin_visit_status_get_random(visit_type) assert random_ov and random_ovs assert random_ov.origin is not None assert random_ov.origin == random_ovs.origin assert random_ov.origin in [o.url for o in origins] 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,)] )[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_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_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, ) visit2 = OriginVisit( 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 ovs1 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=date_visit, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=date_visit2, 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_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 """ 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=origin1.url, visit=ov1.visit, date=sample_data.date_visit1, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin2.url, visit=ov2.visit, date=sample_data.date_visit2, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, 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, status="ongoing", snapshot=None, metadata={"intrinsic": "something"}, ) swh_storage.origin_visit_status_add([visit_status1, visit_status2]) 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 """ 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=origin1.url, visit=ov1.visit, date=sample_data.date_visit1, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, status="full", snapshot=snapshot.id, ) swh_storage.origin_visit_status_add([visit_status1]) # second call will ignore existing entries (will send to storage though) swh_storage.origin_visit_status_add([visit_status1]) 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 """ origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( 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",) 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 ) 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", ) visit2 = OriginVisit( 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",) 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=origin.url, visit=ov1.visit, date=round_to_milliseconds(now()), 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=origin.url, visit=ov1.visit, date=round_to_milliseconds(now()), 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=origin.url, visit=ov2.visit, date=round_to_milliseconds(now()), 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=origin.url, visit=ov3.visit, date=round_to_milliseconds(now()), 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, ) 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", ) visit2 = OriginVisit( 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__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, ) 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,)] ) 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", ) # 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=origin1.url, visit=ov1.visit, date=sample_data.date_visit1, status="partial", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=sample_data.date_visit2 + datetime.timedelta(minutes=1), # to not be ignored status="ongoing", snapshot=None, ) ovs4 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=date_now, 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=origin.url, visit=ov1.visit, date=date_now, 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": origin.url, "date": sample_data.date_visit1, "visit": ov1.visit, "status": "created", "snapshot": None, "metadata": None, } ) ovs2 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": date_now, "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,), ("snapshot", empty_snapshot), ("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} 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, } 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_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]],}, "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]],}, "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(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): 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",} ] swh_storage.directory_add([directory]) sha1_gits.append(directory.id) 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",}] swh_storage.release_add([release]) sha1_gits.append(release.id) 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] content_swhid = SWHID( object_type="content", object_id=hash_to_bytes(content.sha1_git) ) 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( MetadataTargetType.CONTENT, content_swhid, authority ) assert result.next_page_token is None 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 updated.""" content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] content_swhid = SWHID( object_type="content", object_id=hash_to_bytes(content.sha1_git) ) new_content_metadata2 = attr.evolve( content_metadata2, format="new-format", metadata=b"new-metadata", ) 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([new_content_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority ) assert result.next_page_token is None expected_results1 = (content_metadata, new_content_metadata2) expected_results2 = (content_metadata, content_metadata2) assert tuple(sorted(result.results, key=lambda x: x.discovery_date,)) in ( expected_results1, # cassandra expected_results2, # postgresql ) 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] content1_swhid = SWHID(object_type="content", object_id=content.sha1_git) content2_swhid = SWHID(object_type="content", object_id=content2.sha1_git) content2_metadata = attr.evolve(content1_metadata2, id=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( MetadataTargetType.CONTENT, content1_swhid, authority ) assert result.next_page_token is None assert [content1_metadata1, content1_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content1_swhid, authority2 ) assert result.next_page_token is None assert [content1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content2_swhid, authority ) assert result.next_page_token is None 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] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) 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( MetadataTargetType.CONTENT, content_swhid, 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,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, 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( MetadataTargetType.CONTENT, content_swhid, 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] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) 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( MetadataTargetType.CONTENT, content_swhid, authority ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, 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] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_content_metadata2 = attr.evolve( content_metadata2, discovery_date=content_metadata2.discovery_date, fetcher=attr.evolve(fetcher2, metadata=None), ) swh_storage.raw_extrinsic_metadata_add( [content_metadata, new_content_metadata2] ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [new_content_metadata2] def test_content_metadata_get__invalid_id(self, swh_storage, sample_data): origin = sample_data.origin 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]) with pytest.raises(StorageArgumentException, match="SWHID"): swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, origin.url, authority ) 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( MetadataTargetType.ORIGIN, origin.url, 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} new_origin_metadata2 = attr.evolve( origin_metadata2, format="new-format", metadata=b"new-metadata", ) 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([new_origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority ) assert result.next_page_token is None # which of the two behavior happens is backend-specific. expected_results1 = (origin_metadata, new_origin_metadata2) expected_results2 = (origin_metadata, origin_metadata2) assert tuple(sorted(result.results, key=lambda x: x.discovery_date,)) in ( expected_results1, # cassandra expected_results2, # postgresql ) 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 = attr.evolve(origin1_metadata2, id=origin2.url) 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( MetadataTargetType.ORIGIN, origin.url, authority ) assert result.next_page_token is None assert [origin1_metadata1, origin1_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority2 ) assert result.next_page_token is None assert [origin1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin2.url, authority ) assert result.next_page_token is None 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( MetadataTargetType.ORIGIN, origin.url, 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( MetadataTargetType.ORIGIN, origin.url, 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( MetadataTargetType.ORIGIN, origin.url, 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( MetadataTargetType.ORIGIN, origin.url, authority ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, 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 = attr.evolve( origin_metadata2, discovery_date=origin_metadata2.discovery_date, fetcher=attr.evolve(fetcher2, metadata=None), ) swh_storage.raw_extrinsic_metadata_add([origin_metadata, new_origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, 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]) def test_origin_metadata_get__invalid_id_type(self, swh_storage, sample_data): origin = sample_data.origin authority = sample_data.metadata_authority fetcher = sample_data.metadata_fetcher origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] content_metadata = sample_data.content_metadata[0] 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]) with pytest.raises(StorageArgumentException, match="SWHID"): swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, content_metadata.id, authority, ) 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",) 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 = 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]) @given(strategies.lists(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,) swh_storage.origin_visit_add([visit]) else: method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass diff --git a/swh/storage/tests/test_api_client.py b/swh/storage/tests/test_api_client.py index d46881dd..f68aaa69 100644 --- a/swh/storage/tests/test_api_client.py +++ b/swh/storage/tests/test_api_client.py @@ -1,97 +1,97 @@ # 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 pytest -import swh.storage.api.server as server import swh.storage from swh.storage import get_storage +import swh.storage.api.server as server 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 app_server(): server.storage = swh.storage.get_storage( cls="memory", journal_writer={"cls": "memory"} ) yield server @pytest.fixture def app(app_server): return app_server.app @pytest.fixture def swh_rpc_client_class(): def storage_factory(**kwargs): storage_config = { "cls": "remote", **kwargs, } return get_storage(**storage_config) return storage_factory @pytest.fixture def swh_storage(swh_rpc_client, app_server): # This version of the swh_storage fixture uses the swh_rpc_client fixture # to instantiate a RemoteStorage (see swh_rpc_client_class above) that # proxies, via the swh.core RPC mechanism, the local (in memory) storage # configured in the app_server fixture above. # # Also note that, for the sake of # making it easier to write tests, the in-memory journal writer of the # in-memory backend storage is attached to the RemoteStorage as its # journal_writer attribute. storage = swh_rpc_client journal_writer = getattr(storage, "journal_writer", None) storage.journal_writer = app_server.storage.journal_writer yield storage storage.journal_writer = journal_writer class TestStorageApi(_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 TestStorageApiGeneratedData(_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_backfill.py b/swh/storage/tests/test_backfill.py index 172e0b81..d801132e 100644 --- a/swh/storage/tests/test_backfill.py +++ b/swh/storage/tests/test_backfill.py @@ -1,244 +1,244 @@ # 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 -import pytest import functools from unittest.mock import patch -from swh.storage import get_storage -from swh.storage.backfill import JournalBackfiller, compute_query, PARTITION_KEY -from swh.storage.replay import process_replay_objects -from swh.storage.tests.test_replay import check_replayed +import pytest from swh.journal.client import JournalClient from swh.journal.tests.journal_data import TEST_OBJECTS +from swh.storage import get_storage +from swh.storage.backfill import PARTITION_KEY, JournalBackfiller, compute_query +from swh.storage.replay import process_replay_objects +from swh.storage.tests.test_replay import check_replayed TEST_CONFIG = { "brokers": ["localhost"], "prefix": "swh.tmp_journal.new", "client_id": "swh.journal.client.test", "storage_dbconn": "service=swh-dev", } def test_config_ko_missing_mandatory_key(): """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 """ 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(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", "date_neg_utc_offset", "comment", "name", "synthetic", "target", "target_type", "author_id", "author_name", "author_email", "author_fullname", ] assert ( query == """ select release.id as id,date,date_offset,date_neg_utc_offset,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 from release left join person a on release.author=a.id where (release.id) >= %s and (release.id) < %s """ # noqa ) RANGE_GENERATORS = { "content": lambda start, end: [(None, None)], "skipped_content": lambda start, end: [(None, None)], "directory": 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, ): 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 = { "brokers": [kafka_server], "client_id": "kafka_writer-2", "prefix": prefix2, "storage_dbconn": swh_storage_backend_config["db"], } # Backfilling backfiller = JournalBackfiller(backfiller_config) for object_type in TEST_OBJECTS: backfiller.run(object_type, None, None) # 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 sto1 = get_storage(cls="memory") replayer1 = JournalClient( brokers=kafka_server, group_id=f"{kafka_consumer_group}-1", prefix=prefix1, stop_on_eof=True, ) 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, ) worker_fn2 = functools.partial(process_replay_objects, storage=sto2) replayer2.process(worker_fn2) # Compare storages check_replayed(sto1, sto2) diff --git a/swh/storage/tests/test_cassandra.py b/swh/storage/tests/test_cassandra.py index 04af928c..00bebb3b 100644 --- a/swh/storage/tests/test_cassandra.py +++ b/swh/storage/tests/test_cassandra.py @@ -1,417 +1,415 @@ # 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 datetime import os import signal import socket import subprocess import time from typing import Dict import attr import pytest from swh.core.api.classes import stream_results from swh.storage import get_storage from swh.storage.cassandra import create_keyspace -from swh.storage.cassandra.schema import TABLES, HASH_ALGORITHMS from swh.storage.cassandra.model import ContentRow - -from swh.storage.utils import now -from swh.storage.tests.storage_tests import TestStorage as _TestStorage +from swh.storage.cassandra.schema import HASH_ALGORITHMS, TABLES 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 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 """ 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() + 20 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() with open(str(cassandra_conf.join("cassandra.yaml")), "w") as fd: fd.write( CONFIG_TEMPLATE.format( data_dir=str(cassandra_data), storage_port=storage_port, native_transport_port=native_transport_port, ) ) if os.environ.get("SWH_CASSANDRA_LOG"): stdout = stderr = None else: stdout = stderr = subprocess.DEVNULL cassandra_bin = os.environ.get("SWH_CASSANDRA_BIN", "/usr/sbin/cassandra") 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={ "MAX_HEAP_SIZE": "300M", "HEAP_NEWSIZE": "50M", "JVM_OPTS": "-Xlog:gc=error:file=%s/gc.log" % cassandra_log, }, stdout=stdout, stderr=stderr, ) running = wait_for_peer("127.0.0.1", native_transport_port) if running: yield (["127.0.0.1"], native_transport_port) if not running 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 running: raise Exception("cassandra process stopped unexpectedly.") 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", "args": {},}, ) 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_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_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( swh_storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return cont def mock_cgft(token): 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_token", 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_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( swh_storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return cont and cont2 cols = list(set(cont.to_dict()) - {"data"}) def mock_cgft(token): 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_token", 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_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( swh_storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return cont and cont2 cols = list(set(cont.to_dict()) - {"data"}) def mock_cgft(token): 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_token", 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 @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 diff --git a/swh/storage/tests/test_cassandra_converters.py b/swh/storage/tests/test_cassandra_converters.py index d3319064..6df85a56 100644 --- a/swh/storage/tests/test_cassandra_converters.py +++ b/swh/storage/tests/test_cassandra_converters.py @@ -1,38 +1,36 @@ # 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 namedtuple from typing import List -from swh.storage.cassandra import converters - from swh.model.hashutil import DEFAULT_ALGORITHMS - +from swh.storage.cassandra import converters # Test purposes field_names: List[str] = list(DEFAULT_ALGORITHMS) Row = namedtuple("Row", field_names) # type: ignore def test_row_to_content_hashes(): for row in [ Row( sha1=b"4\x972t\xcc\xefj\xb4\xdf\xaa\xf8e\x99y/\xa9\xc3\xfeF\x89", sha1_git=b"\xd8\x1c\xc0q\x0e\xb6\xcf\x9e\xfd[\x92\n\x84S\xe1\xe0qW\xb6\xcd", # noqa sha256=b"g6P\xf96\xcb;\n/\x93\xce\t\xd8\x1b\xe1\x07H\xb1\xb2\x03\xc1\x9e\x81v\xb4\xee\xfc\x19d\xa0\xcf:", # noqa blake2s256=b"\xd5\xfe\x199We'\xe4,\xfdv\xa9EZ$2\xfe\x7fVf\x95dW}\xd9 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. """ 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. """ return {algo: hash_to_bytes(content[algo]) for algo in DEFAULT_ALGORITHMS} 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/validate.py b/swh/storage/validate.py index eab18255..2e7faddc 100644 --- a/swh/storage/validate.py +++ b/swh/storage/validate.py @@ -1,78 +1,71 @@ # 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 Dict, Iterable, List from swh.model.hashutil import MultiHash, hash_to_bytes, hash_to_hex -from swh.model.model import ( - Content, - Directory, - Release, - Revision, - Snapshot, -) - +from swh.model.model import Content, Directory, Release, Revision, Snapshot from swh.storage import get_storage from swh.storage.exc import StorageArgumentException from swh.storage.interface import StorageInterface class ValidatingProxyStorage: """Proxy for storage classes, which checks inserted objects have a correct hash. Sample configuration use case for filtering storage: .. code-block: yaml storage: cls: validate storage: cls: remote url: http://storage.internal.staging.swh.network:5002/ """ 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 _check_hashes(self, objects: Iterable): for obj in objects: id_ = hash_to_bytes(obj.__class__.compute_hash(obj.to_dict())) if id_ != obj.id: raise StorageArgumentException( f"Object has id {hash_to_hex(obj.id)}, " f"but it should be {hash_to_hex(id_)}: {obj}" ) def content_add(self, content: List[Content]) -> Dict: for cont in content: hashes = MultiHash.from_data(cont.data).digest() if hashes != cont.hashes(): raise StorageArgumentException( f"Object has hashes {cont.hashes()}, but they should be {hashes}" ) return self.storage.content_add(content) def directory_add(self, directories: List[Directory]) -> Dict: self._check_hashes(directories) return self.storage.directory_add(directories) def revision_add(self, revisions: List[Revision]) -> Dict: self._check_hashes(revisions) return self.storage.revision_add(revisions) def release_add(self, releases: List[Release]) -> Dict: self._check_hashes(releases) return self.storage.release_add(releases) def snapshot_add(self, snapshots: List[Snapshot]) -> Dict: self._check_hashes(snapshots) return self.storage.snapshot_add(snapshots) diff --git a/swh/storage/writer.py b/swh/storage/writer.py index 4879f68b..fe2a49db 100644 --- a/swh/storage/writer.py +++ b/swh/storage/writer.py @@ -1,102 +1,102 @@ # 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, + MetadataAuthority, + MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, - Snapshot, - Directory, - Revision, + RawExtrinsicMetadata, Release, - Content, + Revision, SkippedContent, - RawExtrinsicMetadata, - MetadataFetcher, - MetadataAuthority, + 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 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(**journal_writer) else: self.journal = None def write_additions(self, obj_type, values) -> None: if self.journal: self.journal.write_additions(obj_type, values) def content_add(self, contents: Iterable[Content]) -> None: """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)