diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 0b60b610..677f5459 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,48 +1,41 @@ repos: - repo: https://github.com/pre-commit/pre-commit-hooks rev: v2.4.0 hooks: - id: trailing-whitespace - id: flake8 - id: check-json - id: check-yaml - repo: https://github.com/codespell-project/codespell rev: v1.16.0 hooks: - id: codespell exclude: TODO args: [-L iff] - repo: local hooks: - id: mypy name: mypy entry: mypy args: [swh] pass_filenames: false language: system types: [python] +- repo: https://github.com/python/black + rev: 19.10b0 + hooks: + - id: black + # unfortunately, we are far from being able to enable this... #- repo: https://github.com/PyCQA/pydocstyle.git # rev: 4.0.0 # hooks: # - id: pydocstyle # name: pydocstyle # description: pydocstyle is a static analysis tool for checking compliance with Python docstring conventions. # entry: pydocstyle --convention=google # language: python # types: [python] - -# black requires py3.6+ -#- repo: https://github.com/python/black -# rev: 19.3b0 -# hooks: -# - id: black -# language_version: python3 -#- repo: https://github.com/asottile/blacken-docs -# rev: v1.0.0-1 -# hooks: -# - id: blacken-docs -# additional_dependencies: [black==19.3b0] diff --git a/bin/swh-storage-add-dir b/bin/swh-storage-add-dir index 1c3d2f49..793183b1 100755 --- a/bin/swh-storage-add-dir +++ b/bin/swh-storage-add-dir @@ -1,39 +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 -if __name__ == '__main__': +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') + 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() + cont["data"] = open(path, "rb").read() yield cont storage.content_add(list_content()) diff --git a/setup.py b/setup.py index 74dc8a4a..309325da 100755 --- a/setup.py +++ b/setup.py @@ -1,78 +1,75 @@ #!/usr/bin/env python3 # 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 setuptools import setup, find_packages from os import path from io import open 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: +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 + reqf = "requirements-%s.txt" % name else: - reqf = 'requirements.txt' + 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('#'): + if not line or line.startswith("#"): continue requirements.append(line) return requirements setup( - name='swh.storage', - description='Software Heritage storage manager', + name="swh.storage", + description="Software Heritage storage manager", long_description=long_description, - long_description_content_type='text/markdown', - author='Software Heritage developers', - author_email='swh-devel@inria.fr', - url='https://forge.softwareheritage.org/diffusion/DSTO/', + long_description_content_type="text/markdown", + author="Software Heritage developers", + author_email="swh-devel@inria.fr", + url="https://forge.softwareheritage.org/diffusion/DSTO/", packages=find_packages(), - scripts=[ - 'bin/swh-storage-add-dir', - ], - entry_points=''' + scripts=["bin/swh-storage-add-dir",], + entry_points=""" [console_scripts] swh-storage=swh.storage.cli:main [swh.cli.subcommands] storage=swh.storage.cli:storage - ''', - setup_requires=['vcversioner'], - install_requires=parse_requirements() + parse_requirements('swh'), + """, + setup_requires=["vcversioner"], + install_requires=parse_requirements() + parse_requirements("swh"), extras_require={ - 'testing': (parse_requirements('test') + - parse_requirements('swh-journal')), - 'schemata': ['SQLAlchemy'], - 'journal': parse_requirements('swh-journal'), + "testing": (parse_requirements("test") + parse_requirements("swh-journal")), + "schemata": ["SQLAlchemy"], + "journal": parse_requirements("swh-journal"), }, vcversioner={}, 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', + "Bug Reports": "https://forge.softwareheritage.org/maniphest", + "Funding": "https://www.softwareheritage.org/donate", + "Source": "https://forge.softwareheritage.org/source/swh-storage", }, ) diff --git a/swh/storage/__init__.py b/swh/storage/__init__.py index d98cd3e2..757b615d 100644 --- a/swh/storage/__init__.py +++ b/swh/storage/__init__.py @@ -1,94 +1,104 @@ # 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 warnings STORAGE_IMPLEMENTATION = { - 'pipeline', 'local', 'remote', 'memory', 'filter', 'buffer', 'retry', - 'validate', 'cassandra', + "pipeline", + "local", + "remote", + "memory", + "filter", + "buffer", + "retry", + "validate", + "cassandra", } def get_storage(cls, **kwargs): """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 cls not in STORAGE_IMPLEMENTATION: - raise ValueError('Unknown storage class `%s`. Supported: %s' % ( - cls, ', '.join(STORAGE_IMPLEMENTATION))) + raise ValueError( + "Unknown storage class `%s`. Supported: %s" + % (cls, ", ".join(STORAGE_IMPLEMENTATION)) + ) - if 'args' in kwargs: + if "args" in kwargs: warnings.warn( 'Explicit "args" key is deprecated, use keys directly instead.', - DeprecationWarning) - kwargs = kwargs['args'] + DeprecationWarning, + ) + kwargs = kwargs["args"] - if cls == 'pipeline': + if cls == "pipeline": return get_storage_pipeline(**kwargs) - if cls == 'remote': + if cls == "remote": from .api.client import RemoteStorage as Storage - elif cls == 'local': + elif cls == "local": from .storage import Storage - elif cls == 'cassandra': + elif cls == "cassandra": from .cassandra import CassandraStorage as Storage - elif cls == 'memory': + elif cls == "memory": from .in_memory import InMemoryStorage as Storage - elif cls == 'filter': + elif cls == "filter": from .filter import FilteringProxyStorage as Storage - elif cls == 'buffer': + elif cls == "buffer": from .buffer import BufferingProxyStorage as Storage - elif cls == 'retry': + elif cls == "retry": from .retry import RetryingProxyStorage as Storage - elif cls == 'validate': + elif cls == "validate": from .validate import ValidatingProxyStorage as Storage return Storage(**kwargs) def get_storage_pipeline(steps): """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: + if "args" in step: warnings.warn( - 'Explicit "args" key is deprecated, use keys directly ' - 'instead.', - DeprecationWarning) + 'Explicit "args" key is deprecated, use keys directly ' "instead.", + DeprecationWarning, + ) step = { - 'cls': step['cls'], - **step['args'], + "cls": step["cls"], + **step["args"], } if storage_config: - step['storage'] = storage_config + step["storage"] = storage_config storage_config = step return get_storage(**storage_config) diff --git a/swh/storage/algos/diff.py b/swh/storage/algos/diff.py index 70e8d45e..3f67718a 100644 --- a/swh/storage/algos/diff.py +++ b/swh/storage/algos/diff.py @@ -1,404 +1,413 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information # Utility module to 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 swh.model.hashutil import hash_to_bytes from swh.model.identifiers import directory_identifier -from .dir_iterators import ( - DirectoryIterator, DoubleDirectoryIterator, Remaining -) +from .dir_iterators import DirectoryIterator, DoubleDirectoryIterator, Remaining # get the hash identifier for an empty directory -_empty_dir_hash = hash_to_bytes(directory_identifier({'entries': []})) +_empty_dir_hash = hash_to_bytes(directory_identifier({"entries": []})) def _get_rev(storage, rev_id): """ Return revision data from swh storage. """ return list(storage.revision_get([rev_id]))[0] 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() + 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()}) + 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() + 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}) + 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()}) + 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 = 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']: + 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']: + 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']: + 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']: + 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']: + 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']: + 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']: + 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'/') + 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.storage.Storage): 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.storage.Storage): 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'] + 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.storage.Storage): 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] + if rev_data["parents"]: + parent = rev_data["parents"][0] return diff_revisions(storage, parent, revision, track_renaming) diff --git a/swh/storage/algos/dir_iterators.py b/swh/storage/algos/dir_iterators.py index 9f997384..5616ab7a 100644 --- a/swh/storage/algos/dir_iterators.py +++ b/swh/storage/algos/dir_iterators.py @@ -1,375 +1,375 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information # Utility module to iterate on directory trees. # The implementation is inspired from the work of Alberto Cortés # for the go-git project. For more details, you can refer to: # - this blog post: https://blog.sourced.tech/post/difftree/ # - the reference implementation in go: # https://github.com/src-d/go-git/tree/master/utils/merkletrie from enum import Enum from swh.model.hashutil import hash_to_bytes from swh.model.identifiers import directory_identifier # get the hash identifier for an empty directory -_empty_dir_hash = hash_to_bytes(directory_identifier({'entries': []})) +_empty_dir_hash = hash_to_bytes(directory_identifier({"entries": []})) def _get_dir(storage, dir_id): """ Return directory data from swh storage. """ return storage.directory_ls(dir_id) if dir_id else [] class DirectoryIterator(object): """ Helper class used to iterate on a directory tree in a depth-first search way with some additional features: - sibling nodes are iterated in lexicographic order by name - it is possible to skip the visit of sub-directories nodes for efficiency reasons when comparing two trees (no need to go deeper if two directories have the same hash) """ - def __init__(self, storage, dir_id, base_path=b''): + def __init__(self, storage, dir_id, base_path=b""): """ Args: storage (swh.storage.storage.Storage): instance of swh storage (either local or remote) dir_id (bytes): identifier of a root directory base_path (bytes): optional base path used when traversing a sub-directory """ self.storage = storage self.root_dir_id = dir_id self.base_path = base_path self.restart() def restart(self): """ Restart the iteration at the beginning. """ # stack of frames representing currently visited directories: # the root directory is at the bottom while the current one # is at the top self.frames = [] self._push_dir_frame(self.root_dir_id) self.has_started = False def _push_dir_frame(self, dir_id): """ Visit a sub-directory by pushing a new frame to the stack. Each frame is itself a stack of directory entries. Args: dir_id (bytes): identifier of a root directory """ # get directory entries dir_data = _get_dir(self.storage, dir_id) # sort them in lexicographical order and reverse the ordering # in order to unstack the "smallest" entry each time the # iterator advances - dir_data = sorted(dir_data, key=lambda e: e['name'], reverse=True) + dir_data = sorted(dir_data, key=lambda e: e["name"], reverse=True) # push the directory frame to the main stack self.frames.append(dir_data) def top(self): """ Returns: list: The top frame of the main directories stack """ if not self.frames: return None return self.frames[-1] def current(self): """ Returns: dict: The current visited directory entry, i.e. the top element from the top frame """ top_frame = self.top() if not top_frame: return None return top_frame[-1] def current_hash(self): """ Returns: bytes: The hash value of the currently visited directory entry """ - return self.current()['target'] + return self.current()["target"] def current_perms(self): """ Returns: int: The permissions value of the currently visited directory entry """ - return self.current()['perms'] + return self.current()["perms"] def current_path(self): """ Returns: str: The absolute path from the root directory of the currently visited directory entry """ top_frame = self.top() if not top_frame: return None path = [] for frame in self.frames: - path.append(frame[-1]['name']) - return self.base_path + b'/'.join(path) + path.append(frame[-1]["name"]) + return self.base_path + b"/".join(path) def current_is_dir(self): """ Returns: bool: If the currently visited directory entry is a directory """ - return self.current()['type'] == 'dir' + return self.current()["type"] == "dir" def _advance(self, descend): """ Advance in the tree iteration. Args: descend (bool): whether or not to push a new frame if the currently visited element is a sub-directory Returns: dict: The description of the newly visited directory entry """ current = self.current() if not self.has_started or not current: self.has_started = True return current - if descend and self.current_is_dir() \ - and current['target'] != _empty_dir_hash: - self._push_dir_frame(current['target']) + if descend and self.current_is_dir() and current["target"] != _empty_dir_hash: + self._push_dir_frame(current["target"]) else: self.drop() return self.current() def next(self): """ Advance the tree iteration by dropping the current visited directory entry from the top frame. If the top frame ends up empty, the operation is recursively applied to remove all empty frames as the tree is climbed up towards its root. Returns: dict: The description of the newly visited directory entry """ return self._advance(False) def step(self): """ Advance the tree iteration like the next operation with the difference that if the current visited element is a sub-directory a new frame representing its content is pushed to the main stack. Returns: dict: The description of the newly visited directory entry """ return self._advance(True) def drop(self): """ Drop the current visited element from the top frame. If the frame ends up empty, the operation is recursively applied. """ frame = self.top() if not frame: return frame.pop() if not frame: self.frames.pop() self.drop() def __next__(self): entry = self.step() if not entry: raise StopIteration - entry['path'] = self.current_path() + entry["path"] = self.current_path() return entry def __iter__(self): - return DirectoryIterator(self.storage, self.root_dir_id, - self.base_path) + return DirectoryIterator(self.storage, self.root_dir_id, self.base_path) def dir_iterator(storage, dir_id): """ Return an iterator for recursively visiting a directory and its sub-directories. The associated paths are visited in lexicographic depth-first search order. Args: storage (swh.storage.Storage): an instance of a swh storage dir_id (bytes): a directory identifier Returns: swh.storage.algos.dir_iterators.DirectoryIterator: an iterator returning a dict at each iteration step describing a directory entry. A 'path' field is added in that dict to store the absolute path of the entry. """ return DirectoryIterator(storage, dir_id) class Remaining(Enum): """ Enum to represent the current state when iterating on both directory trees at the same time. """ + NoMoreFiles = 0 OnlyToFilesRemain = 1 OnlyFromFilesRemain = 2 BothHaveFiles = 3 class DoubleDirectoryIterator(object): """ Helper class to traverse two directory trees at the same time and compare their contents to detect changes between them. """ def __init__(self, storage, dir_from, dir_to): """ Args: storage: instance of swh storage dir_from (bytes): hash identifier of the from directory dir_to (bytes): hash identifier of the to directory """ self.storage = storage self.dir_from = dir_from self.dir_to = dir_to self.restart() def restart(self): """ Restart the double iteration at the beginning. """ # initialize custom dfs iterators for the two directories self.it_from = DirectoryIterator(self.storage, self.dir_from) self.it_to = DirectoryIterator(self.storage, self.dir_to) # grab the first element of each iterator self.it_from.next() self.it_to.next() def next_from(self): """ Apply the next operation on the from iterator. """ self.it_from.next() def next_to(self): """ Apply the next operation on the to iterator. """ self.it_to.next() def next_both(self): """ Apply the next operation on both iterators. """ self.next_from() self.next_to() def step_from(self): """ Apply the step operation on the from iterator. """ self.it_from.step() def step_to(self): """ Apply the step operation on the from iterator. """ self.it_to.step() def step_both(self): """ Apply the step operation on the both iterators. """ self.step_from() self.step_to() def remaining(self): """ Returns: Remaining: the current state of the double iteration """ from_current = self.it_from.current() to_current = self.it_to.current() # no more files to iterate in both iterators if not from_current and not to_current: return Remaining.NoMoreFiles # still some files to iterate in the to iterator elif not from_current and to_current: return Remaining.OnlyToFilesRemain # still some files to iterate in the from iterator elif from_current and not to_current: return Remaining.OnlyFromFilesRemain # still files to iterate in the both iterators else: return Remaining.BothHaveFiles def compare(self): """ Compare the current iterated directory entries in both iterators and return the comparison status. Returns: dict: The status of the comparison with the following bool values: * *same_hash*: indicates if the two entries have the same hash * *same_perms*: indicates if the two entries have the same permissions * *both_are_dirs*: indicates if the two entries are directories * *both_are_files*: indicates if the two entries are regular files * *file_and_dir*: indicates if one of the entry is a directory and the other a regular file * *from_is_empty_dir*: indicates if the from entry is the empty directory * *from_is_empty_dir*: indicates if the to entry is the empty directory """ from_current_hash = self.it_from.current_hash() to_current_hash = self.it_to.current_hash() from_current_perms = self.it_from.current_perms() to_current_perms = self.it_to.current_perms() from_is_dir = self.it_from.current_is_dir() to_is_dir = self.it_to.current_is_dir() status = {} # compare hash - status['same_hash'] = from_current_hash == to_current_hash + status["same_hash"] = from_current_hash == to_current_hash # compare permissions - status['same_perms'] = from_current_perms == to_current_perms + status["same_perms"] = from_current_perms == to_current_perms # check if both elements are directories - status['both_are_dirs'] = from_is_dir and to_is_dir + status["both_are_dirs"] = from_is_dir and to_is_dir # check if both elements are regular files - status['both_are_files'] = not from_is_dir and not to_is_dir + status["both_are_files"] = not from_is_dir and not to_is_dir # check if one element is a directory, the other a regular file - status['file_and_dir'] = (not status['both_are_dirs'] and - not status['both_are_files']) + status["file_and_dir"] = ( + not status["both_are_dirs"] and not status["both_are_files"] + ) # check if the from element is the empty directory - status['from_is_empty_dir'] = (from_is_dir and - from_current_hash == _empty_dir_hash) + status["from_is_empty_dir"] = ( + from_is_dir and from_current_hash == _empty_dir_hash + ) # check if the to element is the empty directory - status['to_is_empty_dir'] = (to_is_dir and - to_current_hash == _empty_dir_hash) + status["to_is_empty_dir"] = to_is_dir and to_current_hash == _empty_dir_hash return status diff --git a/swh/storage/algos/origin.py b/swh/storage/algos/origin.py index e3607423..e3f9aecc 100644 --- a/swh/storage/algos/origin.py +++ b/swh/storage/algos/origin.py @@ -1,34 +1,35 @@ # 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 def iter_origins(storage, origin_from=1, origin_to=None, batch_size=10000): """Iterates over all origins in the storage. Args: storage: the storage object used for queries. batch_size: number of origins per query Yields: dict: the origin dictionary with the keys: - type: origin's type - url: origin's url """ start = origin_from while True: if origin_to: origin_count = min(origin_to - start, batch_size) else: origin_count = batch_size - origins = list(storage.origin_get_range( - origin_from=start, origin_count=origin_count)) + origins = list( + storage.origin_get_range(origin_from=start, origin_count=origin_count) + ) if not origins: break - start = origins[-1]['id'] + 1 + start = origins[-1]["id"] + 1 for origin in origins: - del origin['id'] + del origin["id"] yield origin if origin_to and start > origin_to: break diff --git a/swh/storage/algos/revisions_walker.py b/swh/storage/algos/revisions_walker.py index fbd163a6..a49e9cac 100644 --- a/swh/storage/algos/revisions_walker.py +++ b/swh/storage/algos/revisions_walker.py @@ -1,548 +1,548 @@ # 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 _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 + 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.storage.Storage): 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._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.storage.Storage.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.storage.Storage.revision_get` """ - for parent_id in rev['parents']: + 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.storage.Storage.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 + 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 + "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' + 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'] + 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.storage.Storage.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' + 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.storage.Storage.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' + 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.storage.Storage.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' + 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.storage.Storage.revision_get` """ - for parent_id in reversed(rev['parents']): + 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.storage.Storage): 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' + 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)) + 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'] + 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'] + 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]) + 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.storage.Storage.revision_get` """ - rev_path_id = self._get_path_id(rev['id']) + rev_path_id = self._get_path_id(rev["id"]) if rev_path_id: - if len(rev['parents']) == 1: - self.process_rev(rev['parents'][0]) + 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: + 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.storage.Storage.revision_get` Returns: bool: Whether to return the revision in the iteration """ - rev_path_id = self._get_path_id(rev['id']) + rev_path_id = self._get_path_id(rev["id"]) - if not rev['parents']: + 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]) + 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) + 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 76eca618..2f497631 100644 --- a/swh/storage/algos/snapshot.py +++ b/swh/storage/algos/snapshot.py @@ -1,31 +1,30 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information def snapshot_get_all_branches(storage, snapshot_id): """Get all the branches for a given snapshot Args: storage (swh.storage.storage.Storage): 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(snapshot_id) if not ret: return - next_branch = ret.pop('next_branch', None) + next_branch = ret.pop("next_branch", None) while next_branch: - data = storage.snapshot_get_branches(snapshot_id, - branches_from=next_branch) - ret['branches'].update(data['branches']) - next_branch = data.get('next_branch') + data = storage.snapshot_get_branches(snapshot_id, branches_from=next_branch) + ret["branches"].update(data["branches"]) + next_branch = data.get("next_branch") return ret diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 17cb7b43..25cf33d6 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,52 +1,55 @@ # 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.model.model import Content from ..exc import StorageAPIError, StorageArgumentException, HashCollision from ..interface import StorageInterface from .serializers import ENCODERS, DECODERS 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': + 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']) + 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}) + 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', {}) + return self.post("reset", {}) def stat_counters(self): - return self.get('stat/counters') + return self.get("stat/counters") def refresh_stat_counters(self): - return self.get('stat/refresh') + return self.get("stat/refresh") diff --git a/swh/storage/api/serializers.py b/swh/storage/api/serializers.py index b5af0b81..d7f754e8 100644 --- a/swh/storage/api/serializers.py +++ b/swh/storage/api/serializers.py @@ -1,26 +1,26 @@ # 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 import swh.model.model as model def _encode_model_object(obj): d = obj.to_dict() - d['__type__'] = type(obj).__name__ + d["__type__"] = type(obj).__name__ return d ENCODERS: List[Tuple[type, str, Callable]] = [ - (model.BaseModel, 'model', _encode_model_object), + (model.BaseModel, "model", _encode_model_object), ] DECODERS: Dict[str, Callable] = { - 'model': lambda d: getattr(model, d.pop('__type__')).from_dict(d) + "model": lambda d: getattr(model, d.pop("__type__")).from_dict(d) } diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py index a16810d0..d64b16a2 100644 --- a/swh/storage/api/server.py +++ b/swh/storage/api/server.py @@ -1,131 +1,128 @@ # 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 from swh.core import config from swh.storage import get_storage as get_swhstorage -from swh.core.api import (RPCServerApp, - error_handler, - encode_data_server as encode_data) +from swh.core.api import RPCServerApp, error_handler, encode_data_server as encode_data from ..interface import StorageInterface from ..metrics import timed from ..exc import StorageArgumentException from .serializers import ENCODERS, DECODERS def get_storage(): global storage if not storage: - storage = get_swhstorage(**app.config['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) +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('/') +@app.route("/") @timed def index(): - return ''' + 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']) +@app.route("/stat/counters", methods=["GET"]) @timed def stat_counters(): return encode_data(get_storage().stat_counters()) -@app.route('/stat/refresh', methods=['GET']) +@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'): +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') + raise EnvironmentError("Configuration file must be defined") if not os.path.exists(config_file): - raise FileNotFoundError('Configuration file %s does not exist' % ( - config_file, )) + raise FileNotFoundError("Configuration file %s does not exist" % (config_file,)) cfg = config.read(config_file) - if 'storage' not in cfg: + 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') + 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') +if __name__ == "__main__": + print("Deprecated. Use swh-storage") diff --git a/swh/storage/buffer.py b/swh/storage/buffer.py index 04ac3b13..c6d0678a 100644 --- a/swh/storage/buffer.py +++ b/swh/storage/buffer.py @@ -1,129 +1,133 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from functools import partial from typing import Dict, Iterable, List, Optional from swh.core.utils import grouper from swh.model.model import Content, BaseModel from swh.storage import get_storage 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 = 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), + "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'] + "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 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': + 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: Iterable[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. """ content = list(content) s = self.object_add( - content, object_type='content', - keys=['sha1', 'sha1_git', 'sha256', 'blake2s256']) + content, + object_type="content", + keys=["sha1", "sha1_git", "sha256", "blake2s256"], + ) if not s: - buffer_ = self._objects['content'].values() + 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']) + if total_size >= self.min_batch_size["content_bytes"]: + return self.flush(["content"]) return s def skipped_content_add(self, content: Iterable[Content]) -> Dict: return self.object_add( - content, object_type='skipped_content', - keys=['sha1', 'sha1_git', 'sha256', 'blake2s256']) + content, + object_type="skipped_content", + keys=["sha1", "sha1_git", "sha256", "blake2s256"], + ) def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: if object_types is None: object_types = self.object_types summary = {} # type: Dict[str, Dict] for object_type in object_types: buffer_ = self._objects[object_type] - batches = grouper( - buffer_.values(), n=self.min_batch_size[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) + add_fn = getattr(self.storage, "%s_add" % object_type) s = add_fn(batch) - summary = {k: v + summary.get(k, 0) - for k, v in s.items()} + 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: + 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 {} diff --git a/swh/storage/cassandra/__init__.py b/swh/storage/cassandra/__init__.py index b3ab634c..2b6783dd 100644 --- a/swh/storage/cassandra/__init__.py +++ b/swh/storage/cassandra/__init__.py @@ -1,11 +1,11 @@ # 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'] +__all__ = ["create_keyspace", "CassandraStorage"] diff --git a/swh/storage/cassandra/common.py b/swh/storage/cassandra/common.py index 65bf67e0..3597b51b 100644 --- a/swh/storage/cassandra/common.py +++ b/swh/storage/cassandra/common.py @@ -1,20 +1,20 @@ # 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 Row = 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()''' +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() + return hashlib.sha1(url.encode("ascii")).digest() diff --git a/swh/storage/cassandra/converters.py b/swh/storage/cassandra/converters.py index 08f03ae6..fb931cf2 100644 --- a/swh/storage/cassandra/converters.py +++ b/swh/storage/cassandra/converters.py @@ -1,72 +1,73 @@ # 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 json from typing import Any, Dict, List import attr from swh.model.model import ( - RevisionType, ObjectType, Revision, Release, Sha1Git, + RevisionType, + ObjectType, + Revision, + Release, + Sha1Git, ) from swh.model.hashutil import DEFAULT_ALGORITHMS from ..converters import git_headers_to_db, db_to_git_headers from .common import Row def revision_to_db(revision: Revision) -> Dict[str, Any]: # 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 - if metadata and 'extra_headers' in metadata: - db_revision['metadata']['extra_headers'] = git_headers_to_db( - metadata['extra_headers']) - db_revision['metadata'] = json.dumps(db_revision['metadata']) - db_revision['type'] = db_revision['type'].value + if metadata and "extra_headers" in metadata: + db_revision["metadata"]["extra_headers"] = git_headers_to_db( + metadata["extra_headers"] + ) + db_revision["metadata"] = json.dumps(db_revision["metadata"]) + db_revision["type"] = db_revision["type"].value return db_revision def revision_from_db(db_revision: Row, parents: List[Sha1Git]) -> Revision: revision = db_revision._asdict() # type: ignore - metadata = json.loads(revision.pop('metadata', None)) - if metadata and 'extra_headers' in metadata: - extra_headers = db_to_git_headers( - metadata['extra_headers']) - metadata['extra_headers'] = extra_headers + metadata = json.loads(revision.pop("metadata", None)) + if metadata and "extra_headers" in metadata: + extra_headers = db_to_git_headers(metadata["extra_headers"]) + metadata["extra_headers"] = extra_headers return Revision( parents=parents, - type=RevisionType(revision.pop('type')), + type=RevisionType(revision.pop("type")), metadata=metadata, **revision, ) def release_to_db(release: Release) -> Dict[str, Any]: db_release = attr.asdict(release, recurse=False) - db_release['target_type'] = db_release['target_type'].value + db_release["target_type"] = db_release["target_type"].value return db_release def release_from_db(db_release: Row) -> Release: release = db_release._asdict() # type: ignore - return Release( - target_type=ObjectType(release.pop('target_type')), - **release, - ) + return Release(target_type=ObjectType(release.pop("target_type")), **release,) def row_to_content_hashes(row: Row) -> Dict[str, bytes]: """Convert cassandra row to a content hashes """ hashes = {} for algo in DEFAULT_ALGORITHMS: hashes[algo] = getattr(row, algo) return hashes diff --git a/swh/storage/cassandra/cql.py b/swh/storage/cassandra/cql.py index 8164fe66..140350a2 100644 --- a/swh/storage/cassandra/cql.py +++ b/swh/storage/cassandra/cql.py @@ -1,757 +1,829 @@ # 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 functools import json import logging import random from typing import ( - Any, Callable, Dict, Iterable, Iterator, List, Optional, - Tuple, TypeVar + Any, + Callable, + Dict, + Iterable, + Iterator, + List, + Optional, + Tuple, + TypeVar, ) from cassandra import CoordinationFailure -from cassandra.cluster import ( - Cluster, EXEC_PROFILE_DEFAULT, ExecutionProfile, ResultSet) +from cassandra.cluster import Cluster, EXEC_PROFILE_DEFAULT, ExecutionProfile, ResultSet from cassandra.policies import DCAwareRoundRobinPolicy, TokenAwarePolicy from cassandra.query import PreparedStatement, BoundStatement from tenacity import ( - retry, stop_after_attempt, wait_random_exponential, + retry, + stop_after_attempt, + wait_random_exponential, retry_if_exception_type, ) from swh.model.model import ( - Sha1Git, TimestampWithTimezone, Timestamp, Person, Content, - SkippedContent, OriginVisit, Origin + Sha1Git, + TimestampWithTimezone, + Timestamp, + Person, + Content, + SkippedContent, + OriginVisit, + Origin, ) from .common import Row, TOKEN_BEGIN, TOKEN_END, hash_url from .schema import CREATE_TABLES_QUERIES, HASH_ALGORITHMS logger = logging.getLogger(__name__) _execution_profiles = { EXEC_PROFILE_DEFAULT: ExecutionProfile( - load_balancing_policy=TokenAwarePolicy(DCAwareRoundRobinPolicy())), + load_balancing_policy=TokenAwarePolicy(DCAwareRoundRobinPolicy()) + ), } # 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) +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 = '' + extra_params = "" if not durable_writes: - extra_params = 'AND durable_writes = false' - session.execute('''CREATE KEYSPACE IF NOT EXISTS "%s" + 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)) + """ + % (keyspace, extra_params) + ) session.execute('USE "%s"' % keyspace) for query in CREATE_TABLES_QUERIES: session.execute(query) -T = TypeVar('T') +T = TypeVar("T") -def _prepared_statement( - query: str) -> Callable[[Callable[..., T]], Callable[..., T]]: +def _prepared_statement(query: str) -> Callable[[Callable[..., T]], Callable[..., T]]: """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) -> T: 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 f( + self, *args, **kwargs, statement=self._prepared_statements[f.__name__] + ) + return newf + return decorator def _prepared_insert_statement(table_name: str, columns: List[str]): """Shorthand for using `_prepared_statement` for `INSERT INTO` statements.""" return _prepared_statement( - 'INSERT INTO %s (%s) VALUES (%s)' % ( - table_name, - ', '.join(columns), ', '.join('?' for _ in columns), - ) + "INSERT INTO %s (%s) VALUES (%s)" + % (table_name, ", ".join(columns), ", ".join("?" for _ in columns),) ) def _prepared_exists_statement(table_name: str): """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 ?') + return _prepared_statement(f"SELECT id FROM {table_name} WHERE id IN ?") 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) + 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) + keyspace, "microtimestamp_with_timezone", TimestampWithTimezone + ) + self._cluster.register_user_type(keyspace, "microtimestamp", Timestamp) + self._cluster.register_user_type(keyspace, "person", Person) self._prepared_statements: Dict[str, 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)) + @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.) + return self._session.execute(statement, args, timeout=1000.0) - @_prepared_statement('UPDATE object_count SET count = count + ? ' - 'WHERE partition_key = 0 AND object_type = ?') + @_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, object_type: str, nb: int, *, statement: PreparedStatement + ) -> None: self._execute_with_retries(statement, [nb, object_type]) - def _add_one( - self, statement, object_type: str, obj, keys: List[str] - ) -> None: + def _add_one(self, statement, object_type: str, obj, keys: List[str]) -> None: self._increment_counter(object_type, 1) - self._execute_with_retries( - statement, [getattr(obj, key) for key in keys]) + self._execute_with_retries(statement, [getattr(obj, key) for key in keys]) def _get_random_row(self, statement) -> Optional[Row]: """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 rows.one() else: return None def _missing(self, statement, ids): res = self._execute_with_retries(statement, [ids]) found_ids = {id_ for (id_,) in res} return [id_ for id_ in ids if id_ not in found_ids] ########################## # 'content' table ########################## - _content_pk = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] + _content_pk = ["sha1", "sha1_git", "sha256", "blake2s256"] _content_keys = [ - 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', - 'ctime', 'status'] + "sha1", + "sha1_git", + "sha256", + "blake2s256", + "length", + "ctime", + "status", + ] 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) + self._increment_counter("content", 1) - @_prepared_insert_statement('content', _content_keys) + @_prepared_insert_statement("content", _content_keys) def content_add_prepare( - self, content, *, statement) -> Tuple[int, Callable[[], None]]: + self, content, *, 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([ - getattr(content, key) for key in self._content_keys]) + statement = statement.bind( + [getattr(content, key) for key in self._content_keys] + ) # 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(self._content_pk)}) 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_statement('SELECT * FROM content WHERE ' + - ' AND '.join(map('%s = ?'.__mod__, HASH_ALGORITHMS))) + @_prepared_statement( + "SELECT * FROM content WHERE " + + " AND ".join(map("%s = ?".__mod__, HASH_ALGORITHMS)) + ) def content_get_from_pk( - self, content_hashes: Dict[str, bytes], *, statement - ) -> Optional[Row]: - rows = list(self._execute_with_retries( - statement, [content_hashes[algo] for algo in HASH_ALGORITHMS])) + self, content_hashes: Dict[str, bytes], *, statement + ) -> Optional[Row]: + rows = list( + self._execute_with_retries( + statement, [content_hashes[algo] for algo in HASH_ALGORITHMS] + ) + ) assert len(rows) <= 1 if rows: return rows[0] else: return None - @_prepared_statement('SELECT * FROM content WHERE token(' - + ', '.join(_content_pk) - + ') = ?') + @_prepared_statement( + "SELECT * FROM content WHERE token(" + ", ".join(_content_pk) + ") = ?" + ) def content_get_from_token(self, token, *, statement) -> Iterable[Row]: return self._execute_with_retries(statement, [token]) - @_prepared_statement('SELECT * FROM content WHERE token(%s) > ? LIMIT 1' - % ', '.join(_content_pk)) + @_prepared_statement( + "SELECT * FROM content WHERE token(%s) > ? LIMIT 1" % ", ".join(_content_pk) + ) def content_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) - @_prepared_statement(('SELECT token({0}) AS tok, {1} FROM content ' - 'WHERE token({0}) >= ? AND token({0}) <= ? LIMIT ?') - .format(', '.join(_content_pk), - ', '.join(_content_keys))) + @_prepared_statement( + ( + "SELECT token({0}) AS tok, {1} FROM content " + "WHERE token({0}) >= ? AND token({0}) <= ? LIMIT ?" + ).format(", ".join(_content_pk), ", ".join(_content_keys)) + ) def content_get_token_range( - self, start: int, end: int, limit: int, *, statement) -> Row: + self, start: int, end: int, limit: int, *, statement + ) -> Row: return self._execute_with_retries(statement, [start, end, limit]) ########################## # 'content_by_*' tables ########################## - @_prepared_statement('SELECT sha1_git FROM content_by_sha1_git ' - 'WHERE sha1_git IN ?') + @_prepared_statement( + "SELECT sha1_git FROM content_by_sha1_git " "WHERE sha1_git IN ?" + ) def content_missing_by_sha1_git( - self, ids: List[bytes], *, statement) -> List[bytes]: + 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: + 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]) + 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]: + self, algo: str, hash_: bytes + ) -> Iterable[int]: assert algo in HASH_ALGORITHMS - query = f'SELECT target_token FROM content_by_{algo} WHERE {algo} = %s' + query = f"SELECT target_token FROM content_by_{algo} WHERE {algo} = %s" return (tok for (tok,) in self._execute_with_retries(query, [hash_])) ########################## # 'skipped_content' table ########################## - _skipped_content_pk = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] + _skipped_content_pk = ["sha1", "sha1_git", "sha256", "blake2s256"] _skipped_content_keys = [ - 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', - 'ctime', 'status', 'reason', 'origin'] - _magic_null_pk = b'' + "sha1", + "sha1_git", + "sha256", + "blake2s256", + "length", + "ctime", + "status", + "reason", + "origin", + ] + _magic_null_pk = b"" """ NULLs (or all-empty blobs) are not allowed in primary keys; instead use a special value that can't possibly be a valid hash. """ 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) + self._increment_counter("skipped_content", 1) - @_prepared_insert_statement('skipped_content', _skipped_content_keys) + @_prepared_insert_statement("skipped_content", _skipped_content_keys) def skipped_content_add_prepare( - self, content, *, statement) -> Tuple[int, Callable[[], None]]: + 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 content = content.to_dict() for key in self._skipped_content_pk: if content[key] is None: content[key] = self._magic_null_pk - statement = statement.bind([ - content.get(key) for key in self._skipped_content_keys]) + statement = statement.bind( + [content.get(key) for key in self._skipped_content_keys] + ) # 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(self._content_pk)}) # 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) + finalizer = functools.partial(self._skipped_content_add_finalize, statement) return (token, finalizer) - @_prepared_statement('SELECT * FROM skipped_content WHERE ' + - ' AND '.join(map('%s = ?'.__mod__, HASH_ALGORITHMS))) + @_prepared_statement( + "SELECT * FROM skipped_content WHERE " + + " AND ".join(map("%s = ?".__mod__, HASH_ALGORITHMS)) + ) def skipped_content_get_from_pk( - self, content_hashes: Dict[str, bytes], *, statement - ) -> Optional[Row]: - rows = list(self._execute_with_retries( - statement, [content_hashes[algo] or self._magic_null_pk - for algo in HASH_ALGORITHMS])) + self, content_hashes: Dict[str, bytes], *, statement + ) -> Optional[Row]: + rows = list( + self._execute_with_retries( + statement, + [ + content_hashes[algo] or self._magic_null_pk + for algo in HASH_ALGORITHMS + ], + ) + ) assert len(rows) <= 1 if rows: # TODO: convert _magic_null_pk back to None? return rows[0] else: return None ########################## # 'skipped_content_by_*' tables ########################## def skipped_content_index_add_one( - self, algo: str, content: SkippedContent, token: int) -> None: + 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)') + f"INSERT INTO skipped_content_by_{algo} ({algo}, target_token) " + f"VALUES (%s, %s)" + ) self._execute_with_retries( - query, [content.get_hash(algo) or self._magic_null_pk, token]) + query, [content.get_hash(algo) or self._magic_null_pk, token] + ) ########################## # 'revision' table ########################## _revision_keys = [ - 'id', 'date', 'committer_date', 'type', 'directory', 'message', - 'author', 'committer', - 'synthetic', 'metadata'] - - @_prepared_exists_statement('revision') + "id", + "date", + "committer_date", + "type", + "directory", + "message", + "author", + "committer", + "synthetic", + "metadata", + ] + + @_prepared_exists_statement("revision") def revision_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) - @_prepared_insert_statement('revision', _revision_keys) + @_prepared_insert_statement("revision", _revision_keys) def revision_add_one(self, revision: Dict[str, Any], *, statement) -> None: self._execute_with_retries( - statement, [revision[key] for key in self._revision_keys]) - self._increment_counter('revision', 1) + statement, [revision[key] for key in self._revision_keys] + ) + self._increment_counter("revision", 1) - @_prepared_statement('SELECT id FROM revision WHERE id IN ?') + @_prepared_statement("SELECT id FROM revision WHERE id IN ?") def revision_get_ids(self, revision_ids, *, statement) -> ResultSet: - return self._execute_with_retries( - statement, [revision_ids]) + return self._execute_with_retries(statement, [revision_ids]) - @_prepared_statement('SELECT * FROM revision WHERE id IN ?') + @_prepared_statement("SELECT * FROM revision WHERE id IN ?") def revision_get(self, revision_ids, *, statement) -> ResultSet: - return self._execute_with_retries( - statement, [revision_ids]) + return self._execute_with_retries(statement, [revision_ids]) - @_prepared_statement('SELECT * FROM revision WHERE token(id) > ? LIMIT 1') + @_prepared_statement("SELECT * FROM revision WHERE token(id) > ? LIMIT 1") def revision_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'revision_parent' table ########################## - _revision_parent_keys = ['id', 'parent_rank', 'parent_id'] + _revision_parent_keys = ["id", "parent_rank", "parent_id"] - @_prepared_insert_statement('revision_parent', _revision_parent_keys) + @_prepared_insert_statement("revision_parent", _revision_parent_keys) def revision_parent_add_one( - self, id_: Sha1Git, parent_rank: int, parent_id: Sha1Git, *, - statement) -> None: - self._execute_with_retries( - statement, [id_, parent_rank, parent_id]) + self, id_: Sha1Git, parent_rank: int, parent_id: Sha1Git, *, statement + ) -> None: + self._execute_with_retries(statement, [id_, parent_rank, parent_id]) - @_prepared_statement('SELECT parent_id FROM revision_parent WHERE id = ?') - def revision_parent_get( - self, revision_id: Sha1Git, *, statement) -> ResultSet: - return self._execute_with_retries( - statement, [revision_id]) + @_prepared_statement("SELECT parent_id FROM revision_parent WHERE id = ?") + def revision_parent_get(self, revision_id: Sha1Git, *, statement) -> ResultSet: + return self._execute_with_retries(statement, [revision_id]) ########################## # 'release' table ########################## _release_keys = [ - 'id', 'target', 'target_type', 'date', 'name', 'message', 'author', - 'synthetic'] - - @_prepared_exists_statement('release') + "id", + "target", + "target_type", + "date", + "name", + "message", + "author", + "synthetic", + ] + + @_prepared_exists_statement("release") def release_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) - @_prepared_insert_statement('release', _release_keys) + @_prepared_insert_statement("release", _release_keys) def release_add_one(self, release: Dict[str, Any], *, statement) -> None: self._execute_with_retries( - statement, [release[key] for key in self._release_keys]) - self._increment_counter('release', 1) + statement, [release[key] for key in self._release_keys] + ) + self._increment_counter("release", 1) - @_prepared_statement('SELECT * FROM release WHERE id in ?') + @_prepared_statement("SELECT * FROM release WHERE id in ?") def release_get(self, release_ids: List[str], *, statement) -> None: return self._execute_with_retries(statement, [release_ids]) - @_prepared_statement('SELECT * FROM release WHERE token(id) > ? LIMIT 1') + @_prepared_statement("SELECT * FROM release WHERE token(id) > ? LIMIT 1") def release_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'directory' table ########################## - _directory_keys = ['id'] + _directory_keys = ["id"] - @_prepared_exists_statement('directory') + @_prepared_exists_statement("directory") def directory_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) - @_prepared_insert_statement('directory', _directory_keys) + @_prepared_insert_statement("directory", _directory_keys) def directory_add_one(self, directory_id: Sha1Git, *, statement) -> None: """Called after all calls to directory_entry_add_one, to commit/finalize the directory.""" self._execute_with_retries(statement, [directory_id]) - self._increment_counter('directory', 1) + self._increment_counter("directory", 1) - @_prepared_statement('SELECT * FROM directory WHERE token(id) > ? LIMIT 1') + @_prepared_statement("SELECT * FROM directory WHERE token(id) > ? LIMIT 1") def directory_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'directory_entry' table ########################## - _directory_entry_keys = ['directory_id', 'name', 'type', 'target', 'perms'] + _directory_entry_keys = ["directory_id", "name", "type", "target", "perms"] - @_prepared_insert_statement('directory_entry', _directory_entry_keys) - def directory_entry_add_one( - self, entry: Dict[str, Any], *, statement) -> None: + @_prepared_insert_statement("directory_entry", _directory_entry_keys) + def directory_entry_add_one(self, entry: Dict[str, Any], *, statement) -> None: self._execute_with_retries( - statement, [entry[key] for key in self._directory_entry_keys]) + statement, [entry[key] for key in self._directory_entry_keys] + ) - @_prepared_statement('SELECT * FROM directory_entry ' - 'WHERE directory_id IN ?') + @_prepared_statement("SELECT * FROM directory_entry " "WHERE directory_id IN ?") def directory_entry_get(self, directory_ids, *, statement) -> ResultSet: - return self._execute_with_retries( - statement, [directory_ids]) + return self._execute_with_retries(statement, [directory_ids]) ########################## # 'snapshot' table ########################## - _snapshot_keys = ['id'] + _snapshot_keys = ["id"] - @_prepared_exists_statement('snapshot') + @_prepared_exists_statement("snapshot") def snapshot_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) - @_prepared_insert_statement('snapshot', _snapshot_keys) + @_prepared_insert_statement("snapshot", _snapshot_keys) def snapshot_add_one(self, snapshot_id: Sha1Git, *, statement) -> None: self._execute_with_retries(statement, [snapshot_id]) - self._increment_counter('snapshot', 1) + self._increment_counter("snapshot", 1) - @_prepared_statement('SELECT * FROM snapshot ' - 'WHERE id = ?') + @_prepared_statement("SELECT * FROM snapshot " "WHERE id = ?") def snapshot_get(self, snapshot_id: Sha1Git, *, statement) -> ResultSet: return self._execute_with_retries(statement, [snapshot_id]) - @_prepared_statement('SELECT * FROM snapshot WHERE token(id) > ? LIMIT 1') + @_prepared_statement("SELECT * FROM snapshot WHERE token(id) > ? LIMIT 1") def snapshot_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'snapshot_branch' table ########################## - _snapshot_branch_keys = ['snapshot_id', 'name', 'target_type', 'target'] + _snapshot_branch_keys = ["snapshot_id", "name", "target_type", "target"] - @_prepared_insert_statement('snapshot_branch', _snapshot_branch_keys) - def snapshot_branch_add_one( - self, branch: Dict[str, Any], *, statement) -> None: + @_prepared_insert_statement("snapshot_branch", _snapshot_branch_keys) + def snapshot_branch_add_one(self, branch: Dict[str, Any], *, statement) -> None: self._execute_with_retries( - statement, [branch[key] for key in self._snapshot_branch_keys]) + statement, [branch[key] for key in self._snapshot_branch_keys] + ) - @_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) -> ResultSet: + @_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) -> ResultSet: return self._execute_with_retries(statement, [snapshot_id]) - @_prepared_statement('SELECT * FROM snapshot_branch ' - 'WHERE snapshot_id = ? AND name >= ?' - 'LIMIT ?') + @_prepared_statement( + "SELECT * FROM snapshot_branch " "WHERE snapshot_id = ? AND name >= ?" "LIMIT ?" + ) def snapshot_branch_get( - self, snapshot_id: Sha1Git, from_: bytes, limit: int, *, - statement) -> None: - return self._execute_with_retries( - statement, [snapshot_id, from_, limit]) + self, snapshot_id: Sha1Git, from_: bytes, limit: int, *, statement + ) -> None: + return self._execute_with_retries(statement, [snapshot_id, from_, limit]) ########################## # 'origin' table ########################## - origin_keys = ['sha1', 'url', 'type', 'next_visit_id'] + origin_keys = ["sha1", "url", "type", "next_visit_id"] - @_prepared_statement('INSERT INTO origin (sha1, url, next_visit_id) ' - 'VALUES (?, ?, 1) IF NOT EXISTS') + @_prepared_statement( + "INSERT INTO origin (sha1, url, next_visit_id) " + "VALUES (?, ?, 1) IF NOT EXISTS" + ) def origin_add_one(self, origin: Origin, *, statement) -> None: - self._execute_with_retries( - statement, [hash_url(origin.url), origin.url]) - self._increment_counter('origin', 1) + self._execute_with_retries(statement, [hash_url(origin.url), origin.url]) + self._increment_counter("origin", 1) - @_prepared_statement('SELECT * FROM origin WHERE sha1 = ?') + @_prepared_statement("SELECT * FROM origin WHERE sha1 = ?") def origin_get_by_sha1(self, sha1: bytes, *, statement) -> ResultSet: return self._execute_with_retries(statement, [sha1]) def origin_get_by_url(self, url: str) -> ResultSet: return self.origin_get_by_sha1(hash_url(url)) @_prepared_statement( f'SELECT token(sha1) AS tok, {", ".join(origin_keys)} ' - f'FROM origin WHERE token(sha1) >= ? LIMIT ?') - def origin_list( - self, start_token: int, limit: int, *, statement) -> ResultSet: - return self._execute_with_retries( - statement, [start_token, limit]) + f"FROM origin WHERE token(sha1) >= ? LIMIT ?" + ) + def origin_list(self, start_token: int, limit: int, *, statement) -> ResultSet: + return self._execute_with_retries(statement, [start_token, limit]) - @_prepared_statement('SELECT * FROM origin') + @_prepared_statement("SELECT * FROM origin") def origin_iter_all(self, *, statement) -> ResultSet: return 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: + @_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: + @_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])) + 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 ########################## _origin_visit_keys = [ - 'origin', 'visit', 'type', 'date', 'status', 'metadata', 'snapshot'] - _origin_visit_update_keys = [ - 'type', 'date', 'status', 'metadata', 'snapshot'] - - @_prepared_statement('SELECT * FROM origin_visit ' - 'WHERE origin = ? AND visit > ?') + "origin", + "visit", + "type", + "date", + "status", + "metadata", + "snapshot", + ] + _origin_visit_update_keys = ["type", "date", "status", "metadata", "snapshot"] + + @_prepared_statement("SELECT * FROM origin_visit " "WHERE origin = ? AND visit > ?") def _origin_visit_get_no_limit( - self, origin_url: str, last_visit: int, *, statement) -> ResultSet: + self, origin_url: str, last_visit: int, *, statement + ) -> ResultSet: return self._execute_with_retries(statement, [origin_url, last_visit]) - @_prepared_statement('SELECT * FROM origin_visit ' - 'WHERE origin = ? AND visit > ? LIMIT ?') + @_prepared_statement( + "SELECT * FROM origin_visit " "WHERE origin = ? AND visit > ? LIMIT ?" + ) def _origin_visit_get_limit( - self, origin_url: str, last_visit: int, limit: int, *, statement - ) -> ResultSet: - return self._execute_with_retries( - statement, [origin_url, last_visit, limit]) + self, origin_url: str, last_visit: int, limit: int, *, statement + ) -> ResultSet: + return self._execute_with_retries(statement, [origin_url, last_visit, limit]) def origin_visit_get( - self, origin_url: str, last_visit: Optional[int], - limit: Optional[int]) -> ResultSet: + self, origin_url: str, last_visit: Optional[int], limit: Optional[int] + ) -> ResultSet: if last_visit is None: last_visit = -1 if limit is None: return self._origin_visit_get_no_limit(origin_url, last_visit) else: return self._origin_visit_get_limit(origin_url, last_visit, limit) def origin_visit_update( - self, origin_url: str, visit_id: int, updates: Dict[str, Any] - ) -> None: + self, origin_url: str, visit_id: int, updates: Dict[str, Any] + ) -> None: set_parts = [] args: List[Any] = [] for (column, value) in updates.items(): - set_parts.append(f'{column} = %s') - if column == 'metadata': + set_parts.append(f"{column} = %s") + if column == "metadata": args.append(json.dumps(value)) else: args.append(value) if not set_parts: return - query = ('UPDATE origin_visit SET ' + ', '.join(set_parts) + - ' WHERE origin = %s AND visit = %s') - self._execute_with_retries( - query, args + [origin_url, visit_id]) + query = ( + "UPDATE origin_visit SET " + + ", ".join(set_parts) + + " WHERE origin = %s AND visit = %s" + ) + self._execute_with_retries(query, args + [origin_url, visit_id]) - @_prepared_insert_statement('origin_visit', _origin_visit_keys) - def origin_visit_add_one( - self, visit: OriginVisit, *, statement) -> None: - self._add_one(statement, 'origin_visit', visit, - self._origin_visit_keys) + @_prepared_insert_statement("origin_visit", _origin_visit_keys) + def origin_visit_add_one(self, visit: OriginVisit, *, statement) -> None: + self._add_one(statement, "origin_visit", visit, self._origin_visit_keys) @_prepared_statement( - 'UPDATE origin_visit SET ' + - ', '.join('%s = ?' % key for key in _origin_visit_update_keys) + - ' WHERE origin = ? AND visit = ?') - def origin_visit_upsert( - self, visit: OriginVisit, *, statement) -> None: + "UPDATE origin_visit SET " + + ", ".join("%s = ?" % key for key in _origin_visit_update_keys) + + " WHERE origin = ? AND visit = ?" + ) + def origin_visit_upsert(self, visit: OriginVisit, *, statement) -> None: args: List[Any] = [] for column in self._origin_visit_update_keys: - if column == 'metadata': + if column == "metadata": args.append(json.dumps(visit.metadata)) else: args.append(getattr(visit, column)) - self._execute_with_retries( - statement, args + [visit.origin, visit.visit]) + self._execute_with_retries(statement, args + [visit.origin, visit.visit]) # TODO: check if there is already one - self._increment_counter('origin_visit', 1) + self._increment_counter("origin_visit", 1) - @_prepared_statement('SELECT * FROM origin_visit ' - 'WHERE origin = ? AND visit = ?') + @_prepared_statement("SELECT * FROM origin_visit " "WHERE origin = ? AND visit = ?") def origin_visit_get_one( - self, origin_url: str, visit_id: int, *, - statement) -> Optional[Row]: + self, origin_url: str, visit_id: int, *, statement + ) -> Optional[Row]: # TODO: error handling - rows = list(self._execute_with_retries( - statement, [origin_url, visit_id])) + rows = list(self._execute_with_retries(statement, [origin_url, visit_id])) if rows: return rows[0] else: return None - @_prepared_statement('SELECT * FROM origin_visit ' - 'WHERE origin = ?') + @_prepared_statement("SELECT * FROM origin_visit " "WHERE origin = ?") def origin_visit_get_all(self, origin_url: str, *, statement) -> ResultSet: return self._execute_with_retries(statement, [origin_url]) - @_prepared_statement('SELECT * FROM origin_visit WHERE origin = ?') + @_prepared_statement("SELECT * FROM origin_visit WHERE origin = ?") def origin_visit_get_latest( - self, origin: str, allowed_statuses: Optional[Iterable[str]], - require_snapshot: bool, *, statement) -> Optional[Row]: + self, + origin: str, + allowed_statuses: Optional[Iterable[str]], + require_snapshot: bool, + *, + statement, + ) -> Optional[Row]: # TODO: do the ordering and filtering in Cassandra rows = list(self._execute_with_retries(statement, [origin])) rows.sort(key=lambda row: (row.date, row.visit), reverse=True) for row in rows: if require_snapshot and row.snapshot is None: continue - if allowed_statuses is not None \ - and row.status not in allowed_statuses: + if allowed_statuses is not None and row.status not in allowed_statuses: continue - if row.snapshot is not None and \ - self.snapshot_missing([row.snapshot]): - raise ValueError('visit references unknown snapshot') + if row.snapshot is not None and self.snapshot_missing([row.snapshot]): + raise ValueError("visit references unknown snapshot") return row else: return None - @_prepared_statement('SELECT * FROM origin_visit WHERE token(origin) >= ?') - def _origin_visit_iter_from( - self, min_token: int, *, statement) -> Iterator[Row]: + @_prepared_statement("SELECT * FROM origin_visit WHERE token(origin) >= ?") + def _origin_visit_iter_from(self, min_token: int, *, statement) -> Iterator[Row]: yield from self._execute_with_retries(statement, [min_token]) - @_prepared_statement('SELECT * FROM origin_visit WHERE token(origin) < ?') - def _origin_visit_iter_to( - self, max_token: int, *, statement) -> Iterator[Row]: + @_prepared_statement("SELECT * FROM origin_visit WHERE token(origin) < ?") + def _origin_visit_iter_to(self, max_token: int, *, statement) -> Iterator[Row]: yield from self._execute_with_retries(statement, [max_token]) def origin_visit_iter(self, start_token: int) -> Iterator[Row]: """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) ########################## # 'tool' table ########################## - _tool_keys = ['id', 'name', 'version', 'configuration'] + _tool_keys = ["id", "name", "version", "configuration"] - @_prepared_insert_statement('tool_by_uuid', _tool_keys) + @_prepared_insert_statement("tool_by_uuid", _tool_keys) def tool_by_uuid_add_one(self, tool: Dict[str, Any], *, statement) -> None: - self._execute_with_retries( - statement, [tool[key] for key in self._tool_keys]) + self._execute_with_retries(statement, [tool[key] for key in self._tool_keys]) - @_prepared_insert_statement('tool', _tool_keys) + @_prepared_insert_statement("tool", _tool_keys) def tool_add_one(self, tool: Dict[str, Any], *, statement) -> None: - self._execute_with_retries( - statement, [tool[key] for key in self._tool_keys]) - self._increment_counter('tool', 1) + self._execute_with_retries(statement, [tool[key] for key in self._tool_keys]) + self._increment_counter("tool", 1) - @_prepared_statement('SELECT id FROM tool ' - 'WHERE name = ? AND version = ? ' - 'AND configuration = ?') + @_prepared_statement( + "SELECT id FROM tool " "WHERE name = ? AND version = ? " "AND configuration = ?" + ) def tool_get_one_uuid( - self, name: str, version: str, configuration: Dict[str, Any], *, - statement) -> Optional[str]: - rows = list(self._execute_with_retries( - statement, [name, version, configuration])) + self, name: str, version: str, configuration: Dict[str, Any], *, statement + ) -> Optional[str]: + rows = list( + self._execute_with_retries(statement, [name, version, configuration]) + ) if rows: assert len(rows) == 1 return rows[0].id else: return None ########################## # Miscellaneous ########################## - @_prepared_statement('SELECT uuid() FROM revision LIMIT 1;') + @_prepared_statement("SELECT uuid() FROM revision LIMIT 1;") def check_read(self, *, statement): self._execute_with_retries(statement, []) - @_prepared_statement('SELECT object_type, count FROM object_count ' - 'WHERE partition_key=0') + @_prepared_statement( + "SELECT object_type, count FROM object_count " "WHERE partition_key=0" + ) def stat_counters(self, *, statement) -> ResultSet: - return self._execute_with_retries( - statement, []) + return self._execute_with_retries(statement, []) diff --git a/swh/storage/cassandra/schema.py b/swh/storage/cassandra/schema.py index 85c55ddd..597ad7f1 100644 --- a/swh/storage/cassandra/schema.py +++ b/swh/storage/cassandra/schema.py @@ -1,223 +1,230 @@ # 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 -CREATE_TABLES_QUERIES = ''' +CREATE_TABLES_QUERIES = """ CREATE OR REPLACE FUNCTION ascii_bins_count_sfunc ( state tuple>, -- (nb_none, map) bin_name ascii ) CALLED ON NULL INPUT RETURNS tuple> LANGUAGE java AS $$ if (bin_name == null) { state.setInt(0, state.getInt(0) + 1); } else { Map counters = state.getMap( 1, String.class, Integer.class); Integer nb = counters.get(bin_name); if (nb == null) { nb = 0; } counters.put(bin_name, nb + 1); state.setMap(1, counters, String.class, Integer.class); } return state; $$ ; CREATE OR REPLACE AGGREGATE ascii_bins_count ( ascii ) SFUNC ascii_bins_count_sfunc STYPE tuple> INITCOND (0, {}) ; CREATE TYPE IF NOT EXISTS microtimestamp ( seconds bigint, microseconds int ); CREATE TYPE IF NOT EXISTS microtimestamp_with_timezone ( timestamp frozen, offset smallint, negative_utc boolean ); CREATE TYPE IF NOT EXISTS person ( fullname blob, name blob, email blob ); CREATE TABLE IF NOT EXISTS content ( sha1 blob, sha1_git blob, sha256 blob, blake2s256 blob, length bigint, ctime timestamp, -- creation time, i.e. time of (first) injection into the storage status ascii, PRIMARY KEY ((sha1, sha1_git, sha256, blake2s256)) ); CREATE TABLE IF NOT EXISTS skipped_content ( sha1 blob, sha1_git blob, sha256 blob, blake2s256 blob, length bigint, ctime timestamp, -- creation time, i.e. time of (first) injection into the storage status ascii, reason text, origin text, PRIMARY KEY ((sha1, sha1_git, sha256, blake2s256)) ); CREATE TABLE IF NOT EXISTS revision ( id blob PRIMARY KEY, date microtimestamp_with_timezone, committer_date microtimestamp_with_timezone, type ascii, directory blob, -- source code "root" directory message blob, author person, committer person, synthetic boolean, -- true iff revision has been created by Software Heritage metadata text -- extra metadata as JSON(tarball checksums, -- extra commit information, etc...) ); CREATE TABLE IF NOT EXISTS revision_parent ( id blob, parent_rank int, -- parent position in merge commits, 0-based parent_id blob, PRIMARY KEY ((id), parent_rank) ); CREATE TABLE IF NOT EXISTS release ( id blob PRIMARY KEY, target_type ascii, target blob, date microtimestamp_with_timezone, name blob, message blob, author person, synthetic boolean, -- true iff release has been created by Software Heritage ); CREATE TABLE IF NOT EXISTS directory ( id blob PRIMARY KEY, ); CREATE TABLE IF NOT EXISTS directory_entry ( directory_id blob, name blob, -- path name, relative to containing dir target blob, perms int, -- unix-like permissions type ascii, -- target type PRIMARY KEY ((directory_id), name) ); CREATE TABLE IF NOT EXISTS snapshot ( id blob PRIMARY KEY, ); -- For a given snapshot_id, branches are sorted by their name, -- allowing easy pagination. CREATE TABLE IF NOT EXISTS snapshot_branch ( snapshot_id blob, name blob, target_type ascii, target blob, PRIMARY KEY ((snapshot_id), name) ); CREATE TABLE IF NOT EXISTS origin_visit ( origin text, visit bigint, date timestamp, type text, status ascii, metadata text, snapshot blob, PRIMARY KEY ((origin), visit) ); CREATE TABLE IF NOT EXISTS origin ( sha1 blob PRIMARY KEY, url text, type text, next_visit_id int, -- We need integer visit ids for compatibility with the pgsql -- storage, so we're using lightweight transactions with this trick: -- https://stackoverflow.com/a/29391877/539465 ); CREATE TABLE IF NOT EXISTS tool_by_uuid ( id timeuuid PRIMARY KEY, name ascii, version ascii, configuration blob, ); CREATE TABLE IF NOT EXISTS tool ( id timeuuid, name ascii, version ascii, configuration blob, PRIMARY KEY ((name, version, configuration)) ) CREATE TABLE IF NOT EXISTS object_count ( partition_key smallint, -- Constant, must always be 0 object_type ascii, count counter, PRIMARY KEY ((partition_key), object_type) ); -'''.split('\n\n') +""".split( + "\n\n" +) -CONTENT_INDEX_TEMPLATE = ''' +CONTENT_INDEX_TEMPLATE = """ -- Secondary table, used for looking up "content" from a single hash CREATE TABLE IF NOT EXISTS content_by_{main_algo} ( {main_algo} blob, target_token bigint, -- value of token(pk) on the "primary" table PRIMARY KEY (({main_algo}), target_token) ); CREATE TABLE IF NOT EXISTS skipped_content_by_{main_algo} ( {main_algo} blob, target_token bigint, -- value of token(pk) on the "primary" table PRIMARY KEY (({main_algo}), target_token) ); -''' +""" -TABLES = ('skipped_content content revision revision_parent release ' - 'directory directory_entry snapshot snapshot_branch ' - 'origin_visit origin tool_by_uuid tool object_count').split() +TABLES = ( + "skipped_content content revision revision_parent release " + "directory directory_entry snapshot snapshot_branch " + "origin_visit origin tool_by_uuid tool object_count" +).split() -HASH_ALGORITHMS = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] +HASH_ALGORITHMS = ["sha1", "sha1_git", "sha256", "blake2s256"] for main_algo in HASH_ALGORITHMS: - CREATE_TABLES_QUERIES.extend(CONTENT_INDEX_TEMPLATE.format( - main_algo=main_algo, - other_algos=', '.join( - [algo for algo in HASH_ALGORITHMS if algo != main_algo]) - ).split('\n\n')) - - TABLES.append('content_by_%s' % main_algo) - TABLES.append('skipped_content_by_%s' % main_algo) + CREATE_TABLES_QUERIES.extend( + CONTENT_INDEX_TEMPLATE.format( + main_algo=main_algo, + other_algos=", ".join( + [algo for algo in HASH_ALGORITHMS if algo != main_algo] + ), + ).split("\n\n") + ) + + TABLES.append("content_by_%s" % main_algo) + TABLES.append("skipped_content_by_%s" % main_algo) diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py index d8db82b4..f4edd0a9 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,981 +1,1004 @@ # 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 import json import random import re from typing import Any, Dict, List, Iterable, Optional, Union import uuid import attr import dateutil from swh.model.model import ( - Revision, Release, Directory, DirectoryEntry, Content, - SkippedContent, OriginVisit, Snapshot, Origin + Revision, + Release, + Directory, + DirectoryEntry, + Content, + SkippedContent, + OriginVisit, + Snapshot, + Origin, ) from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.storage.objstorage import ObjStorage from swh.storage.writer import JournalWriter from swh.storage.validate import convert_validation_exceptions from swh.storage.utils import now from ..exc import StorageArgumentException, HashCollision from .common import TOKEN_BEGIN, TOKEN_END from .converters import ( - revision_to_db, revision_from_db, release_to_db, release_from_db, + revision_to_db, + revision_from_db, + release_to_db, + release_from_db, ) from .cql import CqlRunner 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): + def __init__(self, hosts, keyspace, objstorage, port=9042, journal_writer=None): self._cql_runner = CqlRunner(hosts, keyspace, port) self.journal_writer = JournalWriter(journal_writer) self.objstorage = ObjStorage(objstorage) def check_config(self, *, check_write): 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_) + found_tokens = self._cql_runner.content_get_tokens_from_single_hash(algo, hash_) for token in 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())] + 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'] + 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'}: + 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)) + 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 algo in HASH_ALGORITHMS: if getattr(row, algo) != content.get_hash(algo): # This hash didn't match; discard the row. - collisions.append({ - algo: getattr(row, algo) - for algo in HASH_ALGORITHMS}) + collisions.append( + {algo: getattr(row, algo) for algo in HASH_ALGORITHMS} + ) if collisions: collisions.append(content.hashes()) - raise HashCollision( - algo, content.get_hash(algo), collisions) + raise HashCollision(algo, content.get_hash(algo), collisions) - (token, insertion_finalizer) = \ - self._cql_runner.content_add_prepare(content) + (token, insertion_finalizer) = self._cql_runner.content_add_prepare(content) # 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, + "content:add": content_add, } if with_data: - summary['content:add:bytes'] = content_add_bytes + summary["content:add:bytes"] = content_add_bytes return summary def content_add(self, content: Iterable[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, content, keys=[]): raise NotImplementedError( - 'content_update is not supported by the Cassandra backend') + "content_update is not supported by the Cassandra backend" + ) def content_add_metadata(self, content: Iterable[Content]) -> Dict: return self._content_add(list(content), with_data=False) def content_get(self, content): if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( - "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) + "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX + ) yield from self.objstorage.content_get(content) def content_get_partition( - self, partition_id: int, nb_partitions: int, limit: int = 1000, - page_token: str = None): + self, + partition_id: int, + nb_partitions: int, + limit: int = 1000, + page_token: str = None, + ): if limit is None: - raise StorageArgumentException('limit should not be 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 + 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.') + raise StorageArgumentException("Invalid page_token.") range_start = int(page_token) # Get the first rows of the range - rows = self._cql_runner.content_get_token_range( - range_start, range_end, limit) + rows = self._cql_runner.content_get_token_range(range_start, range_end, limit) rows = list(rows) if len(rows) == limit: - next_page_token: Optional[str] = str(rows[-1].tok+1) + next_page_token: Optional[str] = str(rows[-1].tok + 1) else: next_page_token = None return { - 'contents': [row._asdict() for row in rows - if row.status != 'absent'], - 'next_page_token': next_page_token, + "contents": [row._asdict() for row in rows if row.status != "absent"], + "next_page_token": next_page_token, } - def content_get_metadata( - self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: + def content_get_metadata(self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: result: Dict[bytes, List[Dict]] = {sha1: [] for sha1 in contents} 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): + for row in self._content_get_from_hash("sha1", sha1): content_metadata = row._asdict() - content_metadata.pop('ctime') - result[content_metadata['sha1']].append(content_metadata) + content_metadata.pop("ctime") + result[content_metadata["sha1"]].append(content_metadata) return result def content_find(self, 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 of: ' - '%s' % ', '.join(sorted(HASH_ALGORITHMS))) + "content keys must contain at least one of: " + "%s" % ", ".join(sorted(HASH_ALGORITHMS)) + ) common_algo = filter_algos[0] results = [] - rows = self._content_get_from_hash( - common_algo, content[common_algo]) + 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. - results.append({ - **row._asdict(), - 'ctime': row.ctime.replace(tzinfo=datetime.timezone.utc) - }) + results.append( + { + **row._asdict(), + "ctime": row.ctime.replace(tzinfo=datetime.timezone.utc), + } + ) return results - def content_missing(self, content, key_hash='sha1'): + def content_missing(self, content, key_hash="sha1"): for cont in content: res = self.content_find(cont) if not res: yield cont[key_hash] - if any(c['status'] == 'missing' for c in res): + if any(c["status"] == "missing" for c in res): yield cont[key_hash] def content_missing_per_sha1(self, contents): - return self.content_missing([{'sha1': c for c in contents}]) + return self.content_missing([{"sha1": c for c in contents}]) def content_missing_per_sha1_git(self, contents): - return self.content_missing([{'sha1_git': c for c in contents}], - key_hash='sha1_git') + return self.content_missing( + [{"sha1_git": c for c in contents}], key_hash="sha1_git" + ) def content_get_random(self): return self._cql_runner.content_get_random().sha1_git def _skipped_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 (skipped_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.skipped_content_get_tokens_from_single_hash( - algo, hash_) + found_tokens = self._cql_runner.skipped_content_get_tokens_from_single_hash( + algo, hash_ + ) for token in found_tokens: # Query the main table ('content'). res = self._cql_runner.skipped_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 _skipped_content_add(self, contents: Iterable[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())] + 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(content) + (token, insertion_finalizer) = self._cql_runner.skipped_content_add_prepare( + content + ) # Then add to index tables for algo in HASH_ALGORITHMS: - self._cql_runner.skipped_content_index_add_one( - algo, content, token) + self._cql_runner.skipped_content_index_add_one(algo, content, token) # Then to the main table insertion_finalizer() - return { - 'skipped_content:add': len(contents) - } + return {"skipped_content:add": len(contents)} def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: contents = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(contents) def skipped_content_missing(self, contents): 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: Iterable[Directory]) -> Dict: directories = list(directories) # 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({ - **entry.to_dict(), - 'directory_id': directory.id - }) + self._cql_runner.directory_entry_add_one( + {**entry.to_dict(), "directory_id": directory.id} + ) # 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(directory.id) - return {'directory:add': len(missing)} + return {"directory:add": len(missing)} def directory_missing(self, directories): return self._cql_runner.directory_missing(directories) def _join_dentry_to_content(self, dentry): keys = ( - 'status', - 'sha1', - 'sha1_git', - 'sha256', - 'length', + "status", + "sha1", + "sha1_git", + "sha256", + "length", ) ret = dict.fromkeys(keys) ret.update(dentry.to_dict()) - if ret['type'] == 'file': - content = self.content_find({'sha1_git': ret['target']}) + if ret["type"] == "file": + content = self.content_find({"sha1_git": ret["target"]}) if content: content = content[0] for key in keys: ret[key] = content[key] return ret - def _directory_ls(self, directory_id, recursive, prefix=b''): + def _directory_ls(self, directory_id, recursive, prefix=b""): if self.directory_missing([directory_id]): return rows = list(self._cql_runner.directory_entry_get([directory_id])) for row in rows: # Build and yield the directory entry dict entry = row._asdict() - del entry['directory_id'] + del entry["directory_id"] entry = DirectoryEntry.from_dict(entry) ret = self._join_dentry_to_content(entry) - ret['name'] = prefix + ret['name'] - ret['dir_id'] = directory_id + ret["name"] = prefix + ret["name"] + ret["dir_id"] = directory_id yield ret - if recursive and ret['type'] == 'dir': + if recursive and ret["type"] == "dir": yield from self._directory_ls( - ret['target'], True, prefix + ret['name'] + b'/') + ret["target"], True, prefix + ret["name"] + b"/" + ) def directory_entry_get_by_path(self, directory, paths): - return self._directory_entry_get_by_path(directory, paths, b'') + return self._directory_entry_get_by_path(directory, paths, b"") def _directory_entry_get_by_path(self, directory, paths, prefix): if not paths: return contents = list(self.directory_ls(directory)) if not contents: return 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: + if entry["name"] == name: entry = entry.copy() - entry['name'] = prefix + entry['name'] + 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': + if not first_item or first_item["type"] != "dir": return return self._directory_entry_get_by_path( - first_item['target'], paths[1:], prefix + paths[0] + b'/') + first_item["target"], paths[1:], prefix + paths[0] + b"/" + ) def directory_ls(self, directory, recursive=False): yield from self._directory_ls(directory, recursive) def directory_get_random(self): return self._cql_runner.directory_get_random().id def revision_add(self, revisions: Iterable[Revision]) -> Dict: revisions = list(revisions) # 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 = revision_to_db(revision) if revobject: # Add parents first - for (rank, parent) in enumerate(revobject['parents']): + for (rank, parent) in enumerate(revobject["parents"]): self._cql_runner.revision_parent_add_one( - revobject['id'], rank, parent) + revobject["id"], rank, 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)} + return {"revision:add": len(revisions)} def revision_missing(self, revisions): return self._cql_runner.revision_missing(revisions) def revision_get(self, revisions): rows = self._cql_runner.revision_get(revisions) revs = {} 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) parent_rows = self._cql_runner.revision_parent_get(row.id) # parent_rank is the clustering key, so results are already # sorted by rank. parents = [row.parent_id for row in parent_rows] rev = revision_from_db(row, parents=parents) revs[rev.id] = rev.to_dict() for rev_id in revisions: yield revs.get(rev_id) def _get_parent_revs(self, rev_ids, seen, limit, short): 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: rows = self._cql_runner.revision_get_ids(rev_ids) 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) parent_rows = self._cql_runner.revision_parent_get(row.id) # parent_rank is the clustering key, so results are already # sorted by rank. parents = [row.parent_id for row in parent_rows] if short: yield (row.id, parents) else: rev = 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, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, False) def revision_shortlog(self, revisions, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, True) def revision_get_random(self): return self._cql_runner.revision_get_random().id def release_add(self, releases: Iterable[Release]) -> Dict: missing = self.release_missing([rel.id for rel in releases]) releases = [rel for rel in releases if rel.id in missing] self.journal_writer.release_add(releases) for release in releases: if release: self._cql_runner.release_add_one(release_to_db(release)) - return {'release:add': len(missing)} + return {"release:add": len(missing)} def release_missing(self, releases): return self._cql_runner.release_missing(releases) def release_get(self, releases): rows = self._cql_runner.release_get(releases) rels = {} for row in rows: release = release_from_db(row) rels[row.id] = release.to_dict() for rel_id in releases: yield rels.get(rel_id) def release_get_random(self): return self._cql_runner.release_get_random().id def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: - missing = self._cql_runner.snapshot_missing( - [snp.id for snp in snapshots]) + 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 = None target = None else: target_type = branch.target_type.value target = branch.target - self._cql_runner.snapshot_branch_add_one({ - 'snapshot_id': snapshot.id, - 'name': branch_name, - 'target_type': target_type, - 'target': target, - }) + self._cql_runner.snapshot_branch_add_one( + { + "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(snapshot.id) - return {'snapshot:add': len(snapshots)} + return {"snapshot:add": len(snapshots)} def snapshot_missing(self, snapshots): return self._cql_runner.snapshot_missing(snapshots) def snapshot_get(self, snapshot_id): return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): try: visit = self._cql_runner.origin_visit_get_one(origin, visit) except IndexError: return None return self.snapshot_get(visit.snapshot) def snapshot_get_latest(self, origin, allowed_statuses=None): visit = self.origin_visit_get_latest( - origin, - allowed_statuses=allowed_statuses, - require_snapshot=True) + origin, allowed_statuses=allowed_statuses, require_snapshot=True + ) if visit: - assert visit['snapshot'] - if self._cql_runner.snapshot_missing([visit['snapshot']]): - raise StorageArgumentException( - 'Visit references unknown snapshot') - return self.snapshot_get_branches(visit['snapshot']) + assert visit["snapshot"] + if self._cql_runner.snapshot_missing([visit["snapshot"]]): + raise StorageArgumentException("Visit references unknown snapshot") + return self.snapshot_get_branches(visit["snapshot"]) def snapshot_count_branches(self, snapshot_id): if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None rows = list(self._cql_runner.snapshot_count_branches(snapshot_id)) assert len(rows) == 1 (nb_none, counts) = rows[0].counts counts = dict(counts) if nb_none: counts[None] = nb_none return counts - def snapshot_get_branches(self, snapshot_id, branches_from=b'', - branches_count=1000, target_types=None): + def snapshot_get_branches( + self, snapshot_id, branches_from=b"", branches_count=1000, target_types=None + ): 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 = [] - while len(branches) < branches_count+1: - new_branches = list(self._cql_runner.snapshot_branch_get( - snapshot_id, branches_from, branches_count+1)) + 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] + 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: + if len(new_branches) < branches_count + 1: break if len(branches) > branches_count: last_branch = branches.pop(-1).name else: last_branch = None branches = { - branch.name: { - 'target': branch.target, - 'target_type': branch.target_type, - } if branch.target else None + branch.name: {"target": branch.target, "target_type": branch.target_type,} + if branch.target + else None for branch in branches } return { - 'id': snapshot_id, - 'branches': branches, - 'next_branch': last_branch, + "id": snapshot_id, + "branches": branches, + "next_branch": last_branch, } def snapshot_get_random(self): return self._cql_runner.snapshot_get_random().id def object_find_by_sha1_git(self, ids): results = {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 = [ - ('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), + ("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(missing_ids)) for sha1_git in found_ids: - results[sha1_git].append({ - 'sha1_git': sha1_git, - 'type': object_type, - }) + 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): if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False - if any('id' in origin for origin in origins): - raise StorageArgumentException('Origin ids are not supported.') + if any("id" in origin for origin in origins): + raise StorageArgumentException("Origin ids are not supported.") results = [self.origin_get_one(origin) for origin in origins] if return_single: assert len(results) == 1 return results[0] else: return results - def origin_get_one(self, origin: Dict[str, Any]) -> Optional[ - Dict[str, Any]]: - if 'id' in origin: - raise StorageArgumentException('Origin ids are not supported.') - if 'url' not in origin: - raise StorageArgumentException('Missing origin url') - rows = self._cql_runner.origin_get_by_url(origin['url']) + def origin_get_one(self, origin: Dict[str, Any]) -> Optional[Dict[str, Any]]: + if "id" in origin: + raise StorageArgumentException("Origin ids are not supported.") + if "url" not in origin: + raise StorageArgumentException("Missing origin url") + rows = self._cql_runner.origin_get_by_url(origin["url"]) rows = list(rows) if rows: assert len(rows) == 1 result = rows[0]._asdict() return { - 'url': result['url'], + "url": result["url"], } else: return None def origin_get_by_sha1(self, sha1s): results = [] for sha1 in sha1s: rows = self._cql_runner.origin_get_by_sha1(sha1) if rows: - results.append({'url': rows.one().url}) + results.append({"url": rows.one().url}) else: results.append(None) return results - def origin_list(self, page_token: Optional[str] = None, limit: int = 100 - ) -> dict: + def origin_list(self, page_token: Optional[str] = None, limit: int = 100) -> dict: # 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.') + raise StorageArgumentException("Invalid page_token.") rows = self._cql_runner.origin_list(start_token, limit) rows = list(rows) if len(rows) == limit: - next_page_token: Optional[str] = str(rows[-1].tok+1) + next_page_token: Optional[str] = str(rows[-1].tok + 1) else: next_page_token = None return { - 'origins': [{'url': row.url} for row in rows], - 'next_page_token': next_page_token, + "origins": [{"url": row.url} for row in rows], + "next_page_token": next_page_token, } - def origin_search(self, url_pattern, offset=0, limit=50, - regexp=False, with_visit=False): + def origin_search( + self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False + ): # TODO: remove this endpoint, swh-search should be used instead. origins = self._cql_runner.origin_iter_all() if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.search(orig.url)] else: origins = [orig for orig in origins if url_pattern in orig.url] if with_visit: - origins = [orig for orig in origins - if orig.next_visit_id > 1] + origins = [orig for orig in origins if orig.next_visit_id > 1] - return [ - { - 'url': orig.url, - } - for orig in origins[offset:offset+limit]] + return [{"url": orig.url,} for orig in origins[offset : offset + limit]] def origin_add(self, origins: Iterable[Origin]) -> List[Dict]: results = [] for origin in origins: self.origin_add_one(origin) results.append(origin.to_dict()) return results def origin_add_one(self, origin: Origin) -> str: known_origin = self.origin_get_one(origin.to_dict()) if known_origin: - origin_url = known_origin['url'] + origin_url = known_origin["url"] else: self.journal_writer.origin_add_one(origin) self._cql_runner.origin_add_one(origin) origin_url = origin.url return origin_url - def origin_visit_add(self, origin_url: str, - date: Union[str, datetime.datetime], - type: str) -> OriginVisit: + def origin_visit_add( + self, origin_url: str, date: Union[str, datetime.datetime], type: str + ) -> OriginVisit: if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): - raise StorageArgumentException( - 'Date must be a datetime or a string') + raise StorageArgumentException("Date must be a datetime or a string") - if not self.origin_get_one({'url': origin_url}): - raise StorageArgumentException( - 'Unknown origin %s', origin_url) + if not self.origin_get_one({"url": origin_url}): + raise StorageArgumentException("Unknown origin %s", origin_url) visit_id = self._cql_runner.origin_generate_unique_visit_id(origin_url) with convert_validation_exceptions(): - visit = OriginVisit.from_dict({ - 'origin': origin_url, - 'date': date, - 'type': type, - 'status': 'ongoing', - 'snapshot': None, - 'metadata': None, - 'visit': visit_id - }) + visit = OriginVisit.from_dict( + { + "origin": origin_url, + "date": date, + "type": type, + "status": "ongoing", + "snapshot": None, + "metadata": None, + "visit": visit_id, + } + ) self.journal_writer.origin_visit_add(visit) self._cql_runner.origin_visit_add_one(visit) return visit def origin_visit_update( - self, origin: str, visit_id: int, status: str, - metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None, - date: Optional[datetime.datetime] = None): + self, + origin: str, + visit_id: int, + status: str, + metadata: Optional[Dict] = None, + snapshot: Optional[bytes] = None, + date: Optional[datetime.datetime] = None, + ): origin_url = origin # TODO: rename the argument # Get the existing data of the visit row = self._cql_runner.origin_visit_get_one(origin_url, visit_id) if not row: - raise StorageArgumentException('This origin visit does not exist.') + raise StorageArgumentException("This origin visit does not exist.") with convert_validation_exceptions(): visit = OriginVisit.from_dict(self._format_origin_visit_row(row)) - updates: Dict[str, Any] = { - 'status': status - } + updates: Dict[str, Any] = {"status": status} if metadata: - updates['metadata'] = metadata + updates["metadata"] = metadata if snapshot: - updates['snapshot'] = snapshot + updates["snapshot"] = snapshot with convert_validation_exceptions(): visit = attr.evolve(visit, **updates) self.journal_writer.origin_visit_update(visit) self._cql_runner.origin_visit_update(origin_url, visit_id, updates) def origin_visit_upsert(self, visits: Iterable[OriginVisit]) -> None: for visit in visits: if visit.visit is None: - raise StorageArgumentException( - f'Missing visit id for visit {visit}') + raise StorageArgumentException(f"Missing visit id for visit {visit}") self.journal_writer.origin_visit_upsert(visits) for visit in visits: self._cql_runner.origin_visit_upsert(visit) @staticmethod def _format_origin_visit_row(visit): return { **visit._asdict(), - 'origin': visit.origin, - 'date': visit.date.replace(tzinfo=datetime.timezone.utc), - 'metadata': (json.loads(visit.metadata) - if visit.metadata else None), + "origin": visit.origin, + "date": visit.date.replace(tzinfo=datetime.timezone.utc), + "metadata": (json.loads(visit.metadata) if visit.metadata else None), } def origin_visit_get( - self, origin: str, last_visit: Optional[int] = None, - limit: Optional[int] = None) -> Iterable[Dict[str, Any]]: + self, origin: str, last_visit: Optional[int] = None, limit: Optional[int] = None + ) -> Iterable[Dict[str, Any]]: rows = self._cql_runner.origin_visit_get(origin, last_visit, limit) yield from map(self._format_origin_visit_row, rows) def origin_visit_find_by_date( - self, origin: str, - visit_date: datetime.datetime) -> Optional[Dict[str, Any]]: + self, origin: str, visit_date: datetime.datetime + ) -> Optional[Dict[str, Any]]: # Iterator over all the visits of the origin # This should be ok for now, as there aren't too many visits # per origin. visits = 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 visits: visit = min(visits, key=key) return visit._asdict() return None - def origin_visit_get_by( - self, origin: str, visit: int) -> Optional[Dict[str, Any]]: + def origin_visit_get_by(self, origin: str, visit: int) -> Optional[Dict[str, Any]]: visit = self._cql_runner.origin_visit_get_one(origin, visit) if visit: return self._format_origin_visit_row(visit) return None def origin_visit_get_latest( - self, origin: str, allowed_statuses: Optional[List[str]] = None, - require_snapshot: bool = False) -> Optional[Dict[str, Any]]: + self, + origin: str, + allowed_statuses: Optional[List[str]] = None, + require_snapshot: bool = False, + ) -> Optional[Dict[str, Any]]: visit = self._cql_runner.origin_visit_get_latest( - origin, - allowed_statuses=allowed_statuses, - require_snapshot=require_snapshot) + origin, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot + ) if visit: return self._format_origin_visit_row(visit) return None def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: 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 = self._format_origin_visit_row(row) - if visit['date'] > back_in_the_day \ - and visit['status'] == 'full': + if visit["date"] > back_in_the_day and visit["status"] == "full": return visit else: return None def tool_add(self, tools): inserted = [] for tool in tools: tool = tool.copy() tool_json = tool.copy() - tool_json['configuration'] = json.dumps( - tool['configuration'], sort_keys=True).encode() + tool_json["configuration"] = json.dumps( + tool["configuration"], sort_keys=True + ).encode() id_ = self._cql_runner.tool_get_one_uuid(**tool_json) if not id_: id_ = uuid.uuid1() - tool_json['id'] = id_ + tool_json["id"] = id_ self._cql_runner.tool_by_uuid_add_one(tool_json) self._cql_runner.tool_add_one(tool_json) - tool['id'] = id_ + tool["id"] = id_ inserted.append(tool) return inserted def tool_get(self, tool): id_ = self._cql_runner.tool_get_one_uuid( - tool['name'], tool['version'], - json.dumps(tool['configuration'], sort_keys=True).encode()) + tool["name"], + tool["version"], + json.dumps(tool["configuration"], sort_keys=True).encode(), + ) if id_: tool = tool.copy() - tool['id'] = id_ + tool["id"] = id_ return tool else: return None def stat_counters(self): rows = self._cql_runner.stat_counters() keys = ( - 'content', 'directory', 'origin', 'origin_visit', - 'release', 'revision', 'skipped_content', 'snapshot') + "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 origin_metadata_add(self, origin_url, ts, provider, tool, metadata): # TODO - raise NotImplementedError('not yet supported for Cassandra') + raise NotImplementedError("not yet supported for Cassandra") def origin_metadata_get_by(self, origin_url, provider_type=None): # TODO - raise NotImplementedError('not yet supported for Cassandra') + raise NotImplementedError("not yet supported for Cassandra") - def metadata_provider_add(self, provider_name, provider_type, provider_url, - metadata): + def metadata_provider_add( + self, provider_name, provider_type, provider_url, metadata + ): # TODO - raise NotImplementedError('not yet supported for Cassandra') + raise NotImplementedError("not yet supported for Cassandra") def metadata_provider_get(self, provider_id): # TODO - raise NotImplementedError('not yet supported for Cassandra') + raise NotImplementedError("not yet supported for Cassandra") def metadata_provider_get_by(self, provider): # TODO - raise NotImplementedError('not yet supported for Cassandra') + raise NotImplementedError("not yet supported for Cassandra") diff --git a/swh/storage/cli.py b/swh/storage/cli.py index 88af1093..13b26128 100644 --- a/swh/storage/cli.py +++ b/swh/storage/cli.py @@ -1,50 +1,62 @@ # 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 logging import click from swh.core.cli import CONTEXT_SETTINGS from swh.storage.api.server import load_and_check_config, app -@click.group(name='storage', context_settings=CONTEXT_SETTINGS) +@click.group(name="storage", context_settings=CONTEXT_SETTINGS) @click.pass_context def storage(ctx): - '''Software Heritage Storage tools.''' + """Software Heritage Storage tools.""" pass -@storage.command(name='rpc-serve') -@click.argument('config-path', required=True) -@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") +@storage.command(name="rpc-serve") +@click.argument("config-path", required=True) +@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, config_path, host, port, debug): - '''Software Heritage Storage RPC server. + """Software Heritage Storage RPC server. Do NOT use this in a production environment. - ''' - if 'log_level' in ctx.obj: - logging.getLogger('werkzeug').setLevel(ctx.obj['log_level']) - api_cfg = load_and_check_config(config_path, type='any') + """ + if "log_level" in ctx.obj: + logging.getLogger("werkzeug").setLevel(ctx.obj["log_level"]) + api_cfg = load_and_check_config(config_path, type="any") app.config.update(api_cfg) app.run(host, port=int(port), debug=bool(debug)) def main(): logging.basicConfig() - return serve(auto_envvar_prefix='SWH_STORAGE') + return serve(auto_envvar_prefix="SWH_STORAGE") -if __name__ == '__main__': +if __name__ == "__main__": main() diff --git a/swh/storage/converters.py b/swh/storage/converters.py index 38e9d27a..7bdc4421 100644 --- a/swh/storage/converters.py +++ b/swh/storage/converters.py @@ -1,323 +1,315 @@ # 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 datetime from swh.core.utils import decode_with_escape, encode_with_unescape from swh.model import identifiers from swh.model.hashutil import MultiHash DEFAULT_AUTHOR = { - 'fullname': None, - 'name': None, - 'email': None, + "fullname": None, + "name": None, + "email": None, } DEFAULT_DATE = { - 'timestamp': None, - 'offset': 0, - 'neg_utc_offset': None, + "timestamp": None, + "offset": 0, + "neg_utc_offset": None, } def author_to_db(author): """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 def db_to_author(fullname, name, email): """Convert the DB representation of an author to a swh-model author. Args: id (long): the author's identifier fullname (bytes): the author's fullname name (bytes): the author's name email (bytes): the author's email Returns: dict: a dictionary with four keys: id, fullname, name and email, or None if the id is None """ return { - 'fullname': fullname, - 'name': name, - 'email': email, + "fullname": fullname, + "name": name, + "email": email, } def git_headers_to_db(git_headers): """Convert git headers to their database representation. We convert the bytes to unicode by decoding them into utf-8 and replacing invalid utf-8 sequences with backslash escapes. """ ret = [] for key, values in git_headers: if isinstance(values, list): ret.append([key, [decode_with_escape(value) for value in values]]) else: ret.append([key, decode_with_escape(values)]) return ret def db_to_git_headers(db_git_headers): ret = [] for key, values in db_git_headers: if isinstance(values, list): - ret.append([key, [encode_with_unescape(value) - for value in values]]) + ret.append([key, [encode_with_unescape(value) for value in values]]) else: ret.append([key, encode_with_unescape(values)]) return ret def db_to_date(date, offset, neg_utc_offset): """Convert the DB representation of a date to a swh-model compatible date. Args: date (datetime.datetime): a date pulled out of the database offset (int): an integer number of minutes representing an UTC offset neg_utc_offset (boolean): whether an utc offset is negative Returns: dict: a dict with three keys: - timestamp: a timestamp from UTC - offset: the number of minutes since UTC - negative_utc: whether a null UTC offset is negative """ if date is None: return None return { - 'timestamp': { - 'seconds': int(date.timestamp()), - 'microseconds': date.microsecond, + "timestamp": { + "seconds": int(date.timestamp()), + "microseconds": date.microsecond, }, - 'offset': offset, - 'negative_utc': neg_utc_offset, + "offset": offset, + "negative_utc": neg_utc_offset, } def date_to_db(date_offset): """Convert a swh-model date_offset to its DB representation. Args: date_offset: a :mod:`swh.model` compatible date_offset 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 date_offset is None: return DEFAULT_DATE normalized = identifiers.normalize_timestamp(date_offset) - ts = normalized['timestamp'] - seconds = ts.get('seconds', 0) - microseconds = ts.get('microseconds', 0) + ts = normalized["timestamp"] + seconds = ts.get("seconds", 0) + microseconds = ts.get("microseconds", 0) timestamp = datetime.datetime.fromtimestamp(seconds, datetime.timezone.utc) timestamp = timestamp.replace(microsecond=microseconds) return { # PostgreSQL supports isoformatted timestamps - 'timestamp': timestamp.isoformat(), - 'offset': normalized['offset'], - 'neg_utc_offset': normalized['negative_utc'], + "timestamp": timestamp.isoformat(), + "offset": normalized["offset"], + "neg_utc_offset": normalized["negative_utc"], } def revision_to_db(rev): """Convert a swh-model revision to its database representation. """ revision = rev.to_dict() - 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']) + 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"]) - metadata = revision['metadata'] + metadata = revision["metadata"] - if metadata and 'extra_headers' in metadata: + if metadata and "extra_headers" in metadata: metadata = metadata.copy() - extra_headers = git_headers_to_db(metadata['extra_headers']) - metadata['extra_headers'] = extra_headers + extra_headers = git_headers_to_db(metadata["extra_headers"]) + metadata["extra_headers"] = extra_headers 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'], - 'directory': revision['directory'], - 'message': revision['message'], - 'metadata': metadata, - 'synthetic': revision['synthetic'], - 'parents': [ - { - 'id': revision['id'], - 'parent_id': parent, - 'parent_rank': i, - } for i, parent in enumerate(revision['parents']) + "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"], + "directory": revision["directory"], + "message": revision["message"], + "metadata": metadata, + "synthetic": revision["synthetic"], + "parents": [ + {"id": revision["id"], "parent_id": parent, "parent_rank": i,} + for i, parent in enumerate(revision["parents"]) ], } def db_to_revision(db_revision): """Convert a database representation of a revision to its swh-model representation.""" author = db_to_author( - db_revision['author_fullname'], - db_revision['author_name'], - db_revision['author_email'], + 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'], + 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'], + 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'] + db_revision["committer_date"], + db_revision["committer_date_offset"], + db_revision["committer_date_neg_utc_offset"], ) - metadata = db_revision['metadata'] + metadata = db_revision["metadata"] - if metadata and 'extra_headers' in metadata: - extra_headers = db_to_git_headers(metadata['extra_headers']) - metadata['extra_headers'] = extra_headers + if metadata and "extra_headers" in metadata: + extra_headers = db_to_git_headers(metadata["extra_headers"]) + metadata["extra_headers"] = extra_headers parents = [] - if 'parents' in db_revision: - for parent in db_revision['parents']: + if "parents" in db_revision: + for parent in db_revision["parents"]: if parent: parents.append(parent) ret = { - 'id': db_revision['id'], - 'author': author, - 'date': date, - 'committer': committer, - 'committer_date': committer_date, - 'type': db_revision['type'], - 'directory': db_revision['directory'], - 'message': db_revision['message'], - 'metadata': metadata, - 'synthetic': db_revision['synthetic'], - 'parents': parents, + "id": db_revision["id"], + "author": author, + "date": date, + "committer": committer, + "committer_date": committer_date, + "type": db_revision["type"], + "directory": db_revision["directory"], + "message": db_revision["message"], + "metadata": metadata, + "synthetic": db_revision["synthetic"], + "parents": parents, } - if 'object_id' in db_revision: - ret['object_id'] = db_revision['object_id'] + if "object_id" in db_revision: + ret["object_id"] = db_revision["object_id"] return ret def release_to_db(rel): """Convert a swh-model release to its database representation. """ release = rel.to_dict() - author = author_to_db(release['author']) - date = date_to_db(release['date']) + 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'], - 'comment': release['message'], - 'synthetic': release['synthetic'], + "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"], + "comment": release["message"], + "synthetic": release["synthetic"], } def db_to_release(db_release): """Convert a database representation of a release to its swh-model representation. """ author = db_to_author( - db_release['author_fullname'], - db_release['author_name'], - db_release['author_email'], + 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'] + db_release["date"], db_release["date_offset"], db_release["date_neg_utc_offset"] ) ret = { - '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': db_release['target_type'], + "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": db_release["target_type"], } - if 'object_id' in db_release: - ret['object_id'] = db_release['object_id'] + if "object_id" in db_release: + ret["object_id"] = db_release["object_id"] return ret def origin_url_to_sha1(origin_url): """Convert an origin URL to a sha1. Encodes URL to utf-8.""" - return MultiHash.from_data( - origin_url.encode('utf-8'), {'sha1'} - ).digest()['sha1'] + return MultiHash.from_data(origin_url.encode("utf-8"), {"sha1"}).digest()["sha1"] diff --git a/swh/storage/db.py b/swh/storage/db.py index 3fc2f1ee..c5fff7c9 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,972 +1,1145 @@ # 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 random import select from swh.core.db import BaseDb from swh.core.db.db_utils import stored_procedure, jsonize from swh.core.db.db_utils import execute_values_generator from swh.model.model import OriginVisit, SHA1_SIZE class Db(BaseDb): """Proxy to the SWH DB, with wrappers around stored procedures """ def mktemp_dir_entry(self, entry_type, cur=None): - self._cursor(cur).execute('SELECT swh_mktemp_dir_entry(%s)', - (('directory_entry_%s' % entry_type),)) + 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_revision") + def mktemp_revision(self, cur=None): + pass - @stored_procedure('swh_mktemp_release') - def mktemp_release(self, cur=None): pass + @stored_procedure("swh_mktemp_release") + def mktemp_release(self, cur=None): + pass - @stored_procedure('swh_mktemp_snapshot_branch') - def mktemp_snapshot_branch(self, cur=None): pass + @stored_procedure("swh_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_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_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_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_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 + @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) + cur.execute( + """select swh_content_update(ARRAY[%s] :: text[])""" % keys_to_update + ) content_get_metadata_keys = [ - 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', 'status'] + "sha1", + "sha1_git", + "sha256", + "blake2s256", + "length", + "status", + ] - content_add_keys = content_get_metadata_keys + ['ctime'] + content_add_keys = content_get_metadata_keys + ["ctime"] skipped_content_keys = [ - 'sha1', 'sha1_git', 'sha256', 'blake2s256', - 'length', 'reason', 'status', 'origin'] + "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, """ + cur, + """ select t.sha1, %s from (values %%s) as t (sha1) inner join content using (sha1) - """ % ', '.join(self.content_get_metadata_keys[1:]), + """ + % ", ".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) + 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'] + 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 + 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, """ + 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) + """ + % (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, """ + 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)) + )""", + ((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, """ + 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)) + )""", + ((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]) + 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, """ + 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)) + """, + ((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'] + 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) + """ % ", ".join( + self.snapshot_count_cols + ) cur.execute(query, (snapshot_id,)) yield from cur - snapshot_get_cols = ['snapshot_id', 'name', 'target', 'target_type'] + 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): + 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) + """ % ", ".join( + self.snapshot_get_cols + ) - cur.execute(query, (snapshot_id, branches_from, branches_count, - target_types)) + cur.execute(query, (snapshot_id, branches_from, branches_count, target_types)) yield from cur def snapshot_get_by_origin_visit(self, origin_url, visit_id, cur=None): cur = self._cursor(cur) query = """\ SELECT snapshot FROM origin_visit INNER JOIN origin ON origin.id = origin_visit.origin WHERE origin.url=%s AND origin_visit.visit=%s; """ cur.execute(query, (origin_url, visit_id)) ret = cur.fetchone() if ret: return ret[0] 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'] + 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=None, sha1_git=None, sha256=None, - blake2s256=None, cur=None): + def content_find( + self, sha1=None, sha1_git=None, sha256=None, blake2s256=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} + checksum_dict = { + "sha1": sha1, + "sha1_git": sha1_git, + "sha256": sha256, + "blake2s256": blake2s256, + } where_parts = [] args = [] # Adds only those keys which have value other than None for algorithm in checksum_dict: if checksum_dict[algorithm] is not None: args.append(checksum_dict[algorithm]) - where_parts.append(algorithm + '= %s') - query = ' AND '.join(where_parts) - cur.execute("""SELECT %s + where_parts.append(algorithm + "= %s") + query = " AND ".join(where_parts) + cur.execute( + """SELECT %s FROM content WHERE %s """ - % (','.join(self.content_find_cols), query), - args) + % (",".join(self.content_find_cols), query), + args, + ) 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) + 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, """ + 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)) + """, + ((id,) for id in directories), + ) - directory_ls_cols = ['dir_id', 'type', 'target', 'name', 'perms', - 'status', 'sha1', 'sha1_git', 'sha256', 'length'] + 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 + 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 + 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) + 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) + 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, """ + 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)) + """, + ((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', + "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", ] - revision_get_cols = revision_add_cols + ['parents'] + 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 with status 'ongoing'. 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)) + self._cursor(cur).execute( + "SELECT swh_origin_visit_add(%s, %s, %s)", (origin, ts, type) + ) return cur.fetchone()[0] def origin_visit_update(self, origin_id, visit_id, updates, cur=None): """Update origin_visit's status.""" cur = self._cursor(cur) update_cols = [] values = [] - where = ['origin.id = origin_visit.origin', - 'origin.url=%s', - 'visit=%s'] + where = ["origin.id = origin_visit.origin", "origin.url=%s", "visit=%s"] where_values = [origin_id, visit_id] - if 'status' in updates: - update_cols.append('status=%s') - values.append(updates.pop('status')) - if 'metadata' in updates: - update_cols.append('metadata=%s') - values.append(jsonize(updates.pop('metadata'))) - if 'snapshot' in updates: - update_cols.append('snapshot=%s') - values.append(updates.pop('snapshot')) - assert not updates, 'Unknown fields: %r' % updates + if "status" in updates: + update_cols.append("status=%s") + values.append(updates.pop("status")) + if "metadata" in updates: + update_cols.append("metadata=%s") + values.append(jsonize(updates.pop("metadata"))) + if "snapshot" in updates: + update_cols.append("snapshot=%s") + values.append(updates.pop("snapshot")) + assert not updates, "Unknown fields: %r" % updates query = """UPDATE origin_visit SET {update_cols} FROM origin - WHERE {where}""".format(**{ - 'update_cols': ', '.join(update_cols), - 'where': ' AND '.join(where) - }) + WHERE {where}""".format( + **{"update_cols": ", ".join(update_cols), "where": " AND ".join(where)} + ) cur.execute(query, (*values, *where_values)) def origin_visit_upsert(self, origin_visit: OriginVisit, cur=None) -> None: # doing an extra query like this is way simpler than trying to join # the origin id in the query below ov = origin_visit origin_id = next(self.origin_id_get_by_url([ov.origin])) cur = self._cursor(cur) query = """INSERT INTO origin_visit ({cols}) VALUES ({values}) ON CONFLICT ON CONSTRAINT origin_visit_pkey DO UPDATE SET {updates}""".format( - cols=', '.join(self.origin_visit_get_cols), - values=', '.join('%s' for col in self.origin_visit_get_cols), - updates=', '.join('{0}=excluded.{0}'.format(col) - for col in self.origin_visit_get_cols)) + cols=", ".join(self.origin_visit_get_cols), + values=", ".join("%s" for col in self.origin_visit_get_cols), + updates=", ".join( + "{0}=excluded.{0}".format(col) for col in self.origin_visit_get_cols + ), + ) cur.execute( - query, (origin_id, ov.visit, ov.date, ov.type, ov.status, - ov.metadata, ov.snapshot)) + query, + ( + origin_id, + ov.visit, + ov.date, + ov.type, + ov.status, + ov.metadata, + ov.snapshot, + ), + ) origin_visit_get_cols = [ - 'origin', 'visit', 'date', 'type', - 'status', 'metadata', 'snapshot'] + "origin", + "visit", + "date", + "type", + "status", + "metadata", + "snapshot", + ] origin_visit_select_cols = [ - 'origin.url AS origin', 'visit', 'date', 'origin_visit.type AS type', - 'status', 'metadata', 'snapshot'] + "origin.url AS origin", + "visit", + "date", + "origin_visit.type AS type", + "status", + "metadata", + "snapshot", + ] - def origin_visit_get_all(self, origin_id, - last_visit=None, limit=None, cur=None): + def origin_visit_get_all(self, origin_id, last_visit=None, limit=None, cur=None): """Retrieve all visits for origin with id origin_id. Args: origin_id: The occurrence's origin Yields: The occurrence's history visits """ cur = self._cursor(cur) if last_visit: - extra_condition = 'and visit > %s' + extra_condition = "and visit > %s" args = (origin_id, last_visit, limit) else: - extra_condition = '' + extra_condition = "" args = (origin_id, limit) query = """\ SELECT %s FROM origin_visit INNER JOIN origin ON origin.id = origin_visit.origin WHERE origin.url=%%s %s order by visit asc limit %%s""" % ( - ', '.join(self.origin_visit_select_cols), extra_condition + ", ".join(self.origin_visit_select_cols), + extra_condition, ) cur.execute(query, args) 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 INNER JOIN origin ON origin.id = origin_visit.origin WHERE origin.url = %%s AND visit = %%s - """ % (', '.join(self.origin_visit_select_cols)) + """ % ( + ", ".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)) + "SELECT * FROM swh_visit_find_by_date(%s, %s)", (origin, visit_date) + ) r = cur.fetchall() if r: return r[0] 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, allowed_statuses=None, require_snapshot=False, - cur=None): + self, origin_id, allowed_statuses=None, require_snapshot=False, cur=None + ): """Retrieve the most recent origin_visit of the given origin, with optional filters. Args: origin_id: the origin concerned 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', - 'INNER JOIN origin ON origin.id = origin_visit.origin'] + "SELECT %s" % ", ".join(self.origin_visit_select_cols), + "FROM origin_visit", + "INNER JOIN origin ON origin.id = origin_visit.origin", + ] - query_parts.append('WHERE origin.url = %s') + query_parts.append("WHERE origin.url = %s") if require_snapshot: - query_parts.append('AND snapshot is not null') + query_parts.append("AND snapshot is not null") if allowed_statuses: query_parts.append( - cur.mogrify('AND status IN %s', - (tuple(allowed_statuses),)).decode()) + cur.mogrify("AND status IN %s", (tuple(allowed_statuses),)).decode() + ) - query_parts.append('ORDER BY date DESC, visit DESC LIMIT 1') + query_parts.append("ORDER BY date DESC, visit DESC LIMIT 1") - query = '\n'.join(query_parts) + query = "\n".join(query_parts) cur.execute(query, (origin_id,)) 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) + columns = ",".join(self.origin_visit_select_cols) query = f"""with visits as ( select * from origin_visit where origin_visit.status='full' and origin_visit.type=%s and origin_visit.date > now() - '3 months'::interval ) select {columns} from visits as origin_visit inner join origin on origin_visit.origin=origin.id where random() < 0.1 limit 1 """ - cur.execute(query, (type, )) + 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 ''' + 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) + )""" + 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) + 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) + 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 + query_keys = ", ".join( + self.mangle_query_key(k, "revision") for k in self.revision_get_cols ) yield from execute_values_generator( - cur, """ + 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))) + """ + % 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) + """ % ", ".join( + self.revision_get_cols + ) cur.execute(query, (root_revisions, limit)) yield from cur - revision_shortlog_cols = ['id', 'parents'] + 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) + """ % ", ".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) + 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, """ + 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)) + """, + ((id,) for id in releases), + ) - object_find_by_sha1_git_cols = ['sha1_git', 'type'] + 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, """ + 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) + ((id,) for id in ids), ) def stat_counters(self, cur=None): cur = self._cursor(cur) - cur.execute('SELECT * FROM swh_stat_counters()') + 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'] + 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) + """ % ",".join( + "origin." + col for col in self.origin_cols + ) - yield from execute_values_generator( - cur, query, ((url,) for url in origins)) + 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) + """ % ",".join( + "origin." + col for col in self.origin_cols + ) - yield from execute_values_generator( - cur, query, ((sha1,) for sha1 in sha1s)) + 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)): + for row in execute_values_generator(cur, query, ((url,) for url in origins)): yield row[0] - origin_get_range_cols = ['id', 'url'] + origin_get_range_cols = ["id", "url"] def origin_get_range(self, origin_from=1, origin_count=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 (int): the minimum id of origins to retrieve origin_count (int): 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) + """ % ",".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): + 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(*)' + origin_cols = "COUNT(*)" else: - origin_cols = ','.join(self.origin_cols) + origin_cols = ",".join(self.origin_cols) query = """SELECT %s FROM origin WHERE """ if with_visit: query += """ EXISTS ( SELECT 1 FROM origin_visit INNER JOIN snapshot ON snapshot=snapshot.id WHERE origin=origin.id ) AND """ - query += 'url %s %%s ' + query += "url %s %%s " if not count: - query += 'ORDER BY id OFFSET %%s LIMIT %%s' + query += "ORDER BY id OFFSET %%s LIMIT %%s" if not regexp: - query = query % (origin_cols, 'ILIKE') - query_params = ('%'+url_pattern+'%', offset, limit) + query = query % (origin_cols, "ILIKE") + query_params = ("%" + url_pattern + "%", offset, limit) else: - query = query % (origin_cols, '~*') + query = query % (origin_cols, "~*") query_params = (url_pattern, offset, limit) if count: query_params = (query_params[0],) cur.execute(query, query_params) - def origin_search(self, url_pattern, offset=0, limit=50, - regexp=False, with_visit=False, cur=None): + def origin_search( + self, url_pattern, offset=0, limit=50, regexp=False, with_visit=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 (str): the string pattern to search for in origin urls offset (int): number of found origins to skip before returning results limit (int): the maximum number of found origins to return 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, offset=offset, limit=limit, - regexp=regexp, with_visit=with_visit, cur=cur) + 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): + 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) + 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', + "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 + query_keys = ", ".join( + self.mangle_query_key(k, "release") for k in self.release_get_cols ) yield from execute_values_generator( - cur, """ + 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))) + """ + % 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) + return self._get_random_row_from_table("release", ["id"], "id", cur) - def origin_metadata_add(self, origin, ts, provider, tool, - metadata, cur=None): + def origin_metadata_add(self, origin, ts, provider, tool, metadata, cur=None): """ Add an origin_metadata for the origin at ts with provider, tool and metadata. Args: origin (int): the origin's id for which the metadata is added ts (datetime): time when the metadata was found provider (int): the metadata provider identifier tool (int): the tool's identifier used to extract metadata metadata (jsonb): the metadata retrieved at the time and location Returns: id (int): the origin_metadata unique id """ cur = self._cursor(cur) insert = """INSERT INTO origin_metadata (origin_id, discovery_date, provider_id, tool_id, metadata) SELECT id, %s, %s, %s, %s FROM origin WHERE url = %s""" cur.execute(insert, (ts, provider, tool, jsonize(metadata), origin)) - origin_metadata_get_cols = ['origin_url', 'discovery_date', - 'tool_id', 'metadata', 'provider_id', - 'provider_name', 'provider_type', - 'provider_url'] + origin_metadata_get_cols = [ + "origin_url", + "discovery_date", + "tool_id", + "metadata", + "provider_id", + "provider_name", + "provider_type", + "provider_url", + ] def origin_metadata_get_by(self, origin_url, provider_type=None, cur=None): """Retrieve all origin_metadata entries for one origin_url """ cur = self._cursor(cur) if not provider_type: - query = '''SELECT %s + query = """SELECT %s FROM swh_origin_metadata_get_by_origin( - %%s)''' % (','.join( - self.origin_metadata_get_cols)) + %%s)""" % ( + ",".join(self.origin_metadata_get_cols) + ) - cur.execute(query, (origin_url, )) + cur.execute(query, (origin_url,)) else: - query = '''SELECT %s + query = """SELECT %s FROM swh_origin_metadata_get_by_provider_type( - %%s, %%s)''' % (','.join( - self.origin_metadata_get_cols)) + %%s, %%s)""" % ( + ",".join(self.origin_metadata_get_cols) + ) cur.execute(query, (origin_url, provider_type)) yield from cur - tool_cols = ['id', 'name', 'version', 'configuration'] + tool_cols = ["id", "name", "version", "configuration"] - @stored_procedure('swh_mktemp_tool') + @stored_procedure("swh_mktemp_tool") def mktemp_tool(self, cur=None): pass def tool_add_from_temp(self, cur=None): cur = self._cursor(cur) - cur.execute("SELECT %s from swh_tool_add()" % ( - ','.join(self.tool_cols), )) + cur.execute("SELECT %s from swh_tool_add()" % (",".join(self.tool_cols),)) yield from cur def tool_get(self, name, version, configuration, cur=None): cur = self._cursor(cur) - cur.execute('''select %s + cur.execute( + """select %s from tool where name=%%s and version=%%s and - configuration=%%s''' % ( - ','.join(self.tool_cols)), - (name, version, configuration)) + configuration=%%s""" + % (",".join(self.tool_cols)), + (name, version, configuration), + ) return cur.fetchone() - metadata_provider_cols = ['id', 'provider_name', 'provider_type', - 'provider_url', 'metadata'] + metadata_provider_cols = [ + "id", + "provider_name", + "provider_type", + "provider_url", + "metadata", + ] - def metadata_provider_add(self, provider_name, provider_type, - provider_url, metadata, cur=None): + def metadata_provider_add( + self, provider_name, provider_type, provider_url, metadata, cur=None + ): """Insert a new provider and return the new identifier.""" cur = self._cursor(cur) insert = """INSERT INTO metadata_provider (provider_name, provider_type, provider_url, metadata) values (%s, %s, %s, %s) RETURNING id""" - cur.execute(insert, (provider_name, provider_type, provider_url, - jsonize(metadata))) + cur.execute( + insert, (provider_name, provider_type, provider_url, jsonize(metadata)) + ) return cur.fetchone()[0] def metadata_provider_get(self, provider_id, cur=None): cur = self._cursor(cur) - cur.execute('''select %s + cur.execute( + """select %s from metadata_provider - where id=%%s ''' % ( - ','.join(self.metadata_provider_cols)), - (provider_id, )) + where id=%%s """ + % (",".join(self.metadata_provider_cols)), + (provider_id,), + ) return cur.fetchone() - def metadata_provider_get_by(self, provider_name, provider_url, - cur=None): + def metadata_provider_get_by(self, provider_name, provider_url, cur=None): cur = self._cursor(cur) - cur.execute('''select %s + cur.execute( + """select %s from metadata_provider where provider_name=%%s and - provider_url=%%s''' % ( - ','.join(self.metadata_provider_cols)), - (provider_name, provider_url)) + provider_url=%%s""" + % (",".join(self.metadata_provider_cols)), + (provider_name, provider_url), + ) return cur.fetchone() 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 = ''' + 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) + """.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] diff --git a/swh/storage/exc.py b/swh/storage/exc.py index f04f09eb..7edf3cbc 100644 --- a/swh/storage/exc.py +++ b/swh/storage/exc.py @@ -1,49 +1,50 @@ # 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 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 + 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 + 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] + 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 f14dc400..392ef27f 100644 --- a/swh/storage/filter.py +++ b/swh/storage/filter.py @@ -1,151 +1,139 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from typing import Dict, Iterable, Set from swh.model.model import ( - Content, SkippedContent, Directory, Revision, + Content, + SkippedContent, + Directory, + Revision, ) from swh.storage import get_storage 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/ """ + def __init__(self, storage): self.storage = get_storage(**storage) self.objects_seen = { - 'content': set(), # sha256 - 'skipped_content': set(), # sha1_git - 'directory': set(), # sha1_git - 'revision': set(), # sha1_git + "content": set(), # sha256 + "skipped_content": set(), # sha1_git + "directory": set(), # sha1_git + "revision": set(), # sha1_git } def __getattr__(self, key): - if key == 'storage': + if key == "storage": raise AttributeError(key) return getattr(self.storage, key) def content_add(self, content: Iterable[Content]) -> Dict: contents = list(content) contents_to_add = self._filter_missing_contents(contents) return self.storage.content_add( x for x in contents if x.sha256 in contents_to_add ) def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: contents = list(content) contents_to_add = self._filter_missing_skipped_contents(contents) return self.storage.skipped_content_add( - x for x in contents - if x.sha1_git is None or x.sha1_git in contents_to_add + x for x in contents if x.sha1_git is None or x.sha1_git in contents_to_add ) def directory_add(self, directories: Iterable[Directory]) -> Dict: directories = list(directories) - 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 - ) + 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: Iterable[Revision]) -> Dict: revisions = list(revisions) - 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 - ) + 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: Iterable[Content]) -> Set[bytes]: + def _filter_missing_contents(self, contents: Iterable[Content]) -> Set[bytes]: """Return only the content keys missing from swh Args: content_hashes: List of sha256 to check for existence in swh storage """ - objects_seen = self.objects_seen['content'] + objects_seen = self.objects_seen["content"] missing_contents = [] for content in contents: if content.sha256 in objects_seen: continue objects_seen.add(content.sha256) missing_contents.append(content.hashes()) - return set(self.storage.content_missing( - missing_contents, - key_hash='sha256', - )) + return set(self.storage.content_missing(missing_contents, key_hash="sha256",)) def _filter_missing_skipped_contents( - self, contents: Iterable[SkippedContent]) -> Set[bytes]: + self, contents: Iterable[SkippedContent] + ) -> Set[bytes]: """Return only the content keys missing from swh Args: content_hashes: List of sha1_git to check for existence in swh storage """ - objects_seen = self.objects_seen['skipped_content'] + objects_seen = self.objects_seen["skipped_content"] missing_contents = [] for content in contents: if content.sha1_git is None or content.sha1_git in objects_seen: continue objects_seen.add(content.sha1_git) missing_contents.append(content.hashes()) return { - c.get('sha1_git') - for c in self.storage.skipped_content_missing(missing_contents)} + c.get("sha1_git") + for c in self.storage.skipped_content_missing(missing_contents) + } - def _filter_missing_ids( - self, - object_type: str, - ids: Iterable[bytes]) -> Set[bytes]: + 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: Iterable of object_type ids Returns: Missing ids from the storage for object_type """ objects_seen = self.objects_seen[object_type] missing_ids = [] for id in ids: if id in objects_seen: continue objects_seen.add(id) missing_ids.append(id) fn_by_object_type = { - 'revision': self.storage.revision_missing, - 'directory': self.storage.directory_missing, + "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/in_memory.py b/swh/storage/in_memory.py index edf858a3..1e97a33c 100644 --- a/swh/storage/in_memory.py +++ b/swh/storage/in_memory.py @@ -1,1007 +1,1018 @@ # 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 re import bisect import dateutil import collections import copy import datetime import itertools import random from collections import defaultdict from datetime import timedelta from typing import Any, Dict, Iterable, List, Optional, Union import attr from swh.model.model import ( - BaseContent, Content, SkippedContent, Directory, Revision, - Release, Snapshot, OriginVisit, Origin, SHA1_SIZE + BaseContent, + Content, + SkippedContent, + Directory, + Revision, + Release, + Snapshot, + OriginVisit, + Origin, + SHA1_SIZE, ) from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.storage.objstorage import ObjStorage from swh.storage.validate import convert_validation_exceptions from swh.storage.utils import now from .exc import StorageArgumentException, HashCollision from .converters import origin_url_to_sha1 from .utils import get_partition_bounds_bytes from .writer import JournalWriter # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 class InMemoryStorage: def __init__(self, journal_writer=None): self.reset() self.journal_writer = JournalWriter(journal_writer) def reset(self): self._contents = {} self._content_indexes = defaultdict(lambda: defaultdict(set)) self._skipped_contents = {} self._skipped_content_indexes = defaultdict(lambda: defaultdict(set)) self._directories = {} self._revisions = {} self._releases = {} self._snapshots = {} self._origins = {} self._origins_by_id = [] self._origins_by_sha1 = {} self._origin_visits = {} self._persons = [] self._origin_metadata = defaultdict(list) self._tools = {} self._metadata_providers = {} self._objects = defaultdict(list) # ideally we would want a skip list for both fast inserts and searches self._sorted_sha1s = [] - self.objstorage = ObjStorage({'cls': 'memory', 'args': {}}) + self.objstorage = ObjStorage({"cls": "memory", "args": {}}) def check_config(self, *, check_write): return True - def _content_add( - self, contents: Iterable[Content], with_data: bool) -> Dict: + def _content_add(self, contents: Iterable[Content], with_data: bool) -> Dict: self.journal_writer.content_add(contents) content_add = 0 content_add_bytes = 0 if with_data: summary = self.objstorage.content_add( - c for c in contents - if c.status != 'absent') - content_add_bytes = summary['content:add:bytes'] + c for c in contents if c.status != "absent" + ) + content_add_bytes = summary["content:add:bytes"] for content in contents: key = self._content_key(content) if key in self._contents: continue for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) - if hash_ in self._content_indexes[algorithm]\ - and (algorithm not in {'blake2s256', 'sha256'}): + if hash_ in self._content_indexes[algorithm] and ( + algorithm not in {"blake2s256", "sha256"} + ): colliding_content_hashes = [] # Add the already stored contents - for content_hashes_set in self._content_indexes[ - algorithm][hash_]: + for content_hashes_set in self._content_indexes[algorithm][hash_]: hashes = dict(content_hashes_set) colliding_content_hashes.append(hashes) # Add the new colliding content colliding_content_hashes.append(content.hashes()) - raise HashCollision( - algorithm, hash_, colliding_content_hashes) + raise HashCollision(algorithm, hash_, colliding_content_hashes) for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(key) - self._objects[content.sha1_git].append( - ('content', content.sha1)) + self._objects[content.sha1_git].append(("content", content.sha1)) self._contents[key] = content bisect.insort(self._sorted_sha1s, content.sha1) - self._contents[key] = attr.evolve( - self._contents[key], - data=None) + self._contents[key] = attr.evolve(self._contents[key], data=None) content_add += 1 summary = { - 'content:add': content_add, + "content:add": content_add, } if with_data: - summary['content:add:bytes'] = content_add_bytes + summary["content:add:bytes"] = content_add_bytes return summary def content_add(self, content: Iterable[Content]) -> Dict: content = [attr.evolve(c, ctime=now()) for c in content] return self._content_add(content, with_data=True) def content_update(self, content, keys=[]): self.journal_writer.content_update(content) for cont_update in content: cont_update = cont_update.copy() - sha1 = cont_update.pop('sha1') - for old_key in self._content_indexes['sha1'][sha1]: + sha1 = cont_update.pop("sha1") + for old_key in self._content_indexes["sha1"][sha1]: old_cont = self._contents.pop(old_key) for algorithm in DEFAULT_ALGORITHMS: hash_ = old_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].remove(old_key) new_cont = attr.evolve(old_cont, **cont_update) new_key = self._content_key(new_cont) self._contents[new_key] = new_cont for algorithm in DEFAULT_ALGORITHMS: hash_ = new_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(new_key) def content_add_metadata(self, content: Iterable[Content]) -> Dict: return self._content_add(content, with_data=False) def content_get(self, content): # FIXME: Make this method support slicing the `data`. if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( - "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) + "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX + ) yield from self.objstorage.content_get(content) def content_get_range(self, start, end, limit=1000): if limit is None: - raise StorageArgumentException('limit should not be None') + raise StorageArgumentException("limit should not be None") from_index = bisect.bisect_left(self._sorted_sha1s, start) sha1s = itertools.islice(self._sorted_sha1s, from_index, None) - sha1s = ((sha1, content_key) - for sha1 in sha1s - for content_key in self._content_indexes['sha1'][sha1]) + sha1s = ( + (sha1, content_key) + for sha1 in sha1s + for content_key in self._content_indexes["sha1"][sha1] + ) matched = [] next_content = None for sha1, key in sha1s: if sha1 > end: break if len(matched) >= limit: next_content = sha1 break matched.append(self._contents[key].to_dict()) return { - 'contents': matched, - 'next': next_content, + "contents": matched, + "next": next_content, } def content_get_partition( - self, partition_id: int, nb_partitions: int, limit: int = 1000, - page_token: str = None): + self, + partition_id: int, + nb_partitions: int, + limit: int = 1000, + page_token: str = None, + ): if limit is None: - raise StorageArgumentException('limit should not be None') + raise StorageArgumentException("limit should not be None") (start, end) = get_partition_bounds_bytes( - partition_id, nb_partitions, SHA1_SIZE) + partition_id, nb_partitions, SHA1_SIZE + ) if page_token: start = hash_to_bytes(page_token) if end is None: - end = b'\xff'*SHA1_SIZE + end = b"\xff" * SHA1_SIZE result = self.content_get_range(start, end, limit) result2 = { - 'contents': result['contents'], - 'next_page_token': None, + "contents": result["contents"], + "next_page_token": None, } - if result['next']: - result2['next_page_token'] = hash_to_hex(result['next']) + if result["next"]: + result2["next_page_token"] = hash_to_hex(result["next"]) return result2 - def content_get_metadata( - self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: + def content_get_metadata(self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: result: Dict = {sha1: [] for sha1 in contents} for sha1 in contents: - if sha1 in self._content_indexes['sha1']: - objs = self._content_indexes['sha1'][sha1] + if sha1 in self._content_indexes["sha1"]: + objs = self._content_indexes["sha1"][sha1] # only 1 element as content_add_metadata would have raised a # hash collision otherwise for key in objs: d = self._contents[key].to_dict() - del d['ctime'] - if 'data' in d: - del d['data'] + del d["ctime"] + if "data" in d: + del d["data"] result[sha1].append(d) return result def content_find(self, content): if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( - 'content keys must contain at least one of: %s' - % ', '.join(sorted(DEFAULT_ALGORITHMS))) + "content keys must contain at least one of: %s" + % ", ".join(sorted(DEFAULT_ALGORITHMS)) + ) found = [] for algo in DEFAULT_ALGORITHMS: hash = content.get(algo) if hash and hash in self._content_indexes[algo]: found.append(self._content_indexes[algo][hash]) if not found: return [] keys = list(set.intersection(*found)) return [self._contents[key].to_dict() for key in keys] - def content_missing(self, content, key_hash='sha1'): + def content_missing(self, content, key_hash="sha1"): for cont in content: for (algo, hash_) in cont.items(): if algo not in DEFAULT_ALGORITHMS: continue if hash_ not in self._content_indexes.get(algo, []): yield cont[key_hash] break else: for result in self.content_find(cont): - if result['status'] == 'missing': + if result["status"] == "missing": yield cont[key_hash] def content_missing_per_sha1(self, contents): for content in contents: - if content not in self._content_indexes['sha1']: + if content not in self._content_indexes["sha1"]: yield content def content_missing_per_sha1_git(self, contents): for content in contents: - if content not in self._content_indexes['sha1_git']: + if content not in self._content_indexes["sha1_git"]: yield content def content_get_random(self): - return random.choice(list(self._content_indexes['sha1_git'])) + return random.choice(list(self._content_indexes["sha1_git"])) def _skipped_content_add(self, contents: List[SkippedContent]) -> Dict: self.journal_writer.skipped_content_add(contents) - summary = { - 'skipped_content:add': 0 - } + summary = {"skipped_content:add": 0} - missing_contents = self.skipped_content_missing( - [c.hashes() for c in contents]) + missing_contents = self.skipped_content_missing([c.hashes() for c in contents]) missing = {self._content_key(c) for c in missing_contents} - contents = [c for c in contents - if self._content_key(c) in missing] + contents = [c for c in contents if self._content_key(c) in missing] for content in contents: key = self._content_key(content) for algo in DEFAULT_ALGORITHMS: if content.get_hash(algo): - self._skipped_content_indexes[algo][ - content.get_hash(algo)].add(key) + self._skipped_content_indexes[algo][content.get_hash(algo)].add(key) self._skipped_contents[key] = content - summary['skipped_content:add'] += 1 + summary["skipped_content:add"] += 1 return summary def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: content = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(content) def skipped_content_missing(self, contents): for content in contents: matches = list(self._skipped_contents.values()) for (algorithm, key) in self._content_key(content): - if algorithm == 'blake2s256': + if algorithm == "blake2s256": continue # Filter out skipped contents with the same hash matches = [ - match for match in matches - if match.get_hash(algorithm) == key] + match for match in matches if match.get_hash(algorithm) == key + ] # if none of the contents match if not matches: - yield {algo: content[algo] - for algo in DEFAULT_ALGORITHMS} + yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} def directory_add(self, directories: Iterable[Directory]) -> Dict: - directories = [dir_ for dir_ in directories - if dir_.id not in self._directories] + directories = [dir_ for dir_ in directories if dir_.id not in self._directories] self.journal_writer.directory_add(directories) count = 0 for directory in directories: count += 1 self._directories[directory.id] = directory - self._objects[directory.id].append( - ('directory', directory.id)) + self._objects[directory.id].append(("directory", directory.id)) - return {'directory:add': count} + return {"directory:add": count} def directory_missing(self, directories): for id in directories: if id not in self._directories: yield id def _join_dentry_to_content(self, dentry): keys = ( - 'status', - 'sha1', - 'sha1_git', - 'sha256', - 'length', + "status", + "sha1", + "sha1_git", + "sha256", + "length", ) ret = dict.fromkeys(keys) ret.update(dentry) - if ret['type'] == 'file': + if ret["type"] == "file": # TODO: Make it able to handle more than one content - content = self.content_find({'sha1_git': ret['target']}) + content = self.content_find({"sha1_git": ret["target"]}) if content: content = content[0] for key in keys: ret[key] = content[key] return ret - def _directory_ls(self, directory_id, recursive, prefix=b''): + def _directory_ls(self, directory_id, recursive, prefix=b""): if directory_id in self._directories: for entry in self._directories[directory_id].entries: ret = self._join_dentry_to_content(entry.to_dict()) - ret['name'] = prefix + ret['name'] - ret['dir_id'] = directory_id + ret["name"] = prefix + ret["name"] + ret["dir_id"] = directory_id yield ret - if recursive and ret['type'] == 'dir': + if recursive and ret["type"] == "dir": yield from self._directory_ls( - ret['target'], True, prefix + ret['name'] + b'/') + ret["target"], True, prefix + ret["name"] + b"/" + ) def directory_ls(self, directory, recursive=False): yield from self._directory_ls(directory, recursive) def directory_entry_get_by_path(self, directory, paths): - return self._directory_entry_get_by_path(directory, paths, b'') + return self._directory_entry_get_by_path(directory, paths, b"") def directory_get_random(self): if not self._directories: return None return random.choice(list(self._directories)) def _directory_entry_get_by_path(self, directory, paths, prefix): if not paths: return contents = list(self.directory_ls(directory)) if not contents: return def _get_entry(entries, name): for entry in entries: - if entry['name'] == name: + if entry["name"] == name: entry = entry.copy() - entry['name'] = prefix + entry['name'] + 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': + if not first_item or first_item["type"] != "dir": return return self._directory_entry_get_by_path( - first_item['target'], paths[1:], prefix + paths[0] + b'/') + first_item["target"], paths[1:], prefix + paths[0] + b"/" + ) def revision_add(self, revisions: Iterable[Revision]) -> Dict: - revisions = [rev for rev in revisions - if rev.id not in self._revisions] + revisions = [rev for rev in revisions if rev.id not in self._revisions] self.journal_writer.revision_add(revisions) count = 0 for revision in revisions: revision = attr.evolve( revision, committer=self._person_add(revision.committer), - author=self._person_add(revision.author)) + author=self._person_add(revision.author), + ) self._revisions[revision.id] = revision - self._objects[revision.id].append( - ('revision', revision.id)) + self._objects[revision.id].append(("revision", revision.id)) count += 1 - return {'revision:add': count} + return {"revision:add": count} def revision_missing(self, revisions): for id in revisions: if id not in self._revisions: yield id def revision_get(self, revisions): for id in revisions: if id in self._revisions: yield self._revisions.get(id).to_dict() else: yield None def _get_parent_revs(self, rev_id, seen, limit): if limit and len(seen) >= limit: return if rev_id in seen or rev_id not in self._revisions: return seen.add(rev_id) yield self._revisions[rev_id].to_dict() for parent in self._revisions[rev_id].parents: yield from self._get_parent_revs(parent, seen, limit) def revision_log(self, revisions, limit=None): seen = set() for rev_id in revisions: yield from self._get_parent_revs(rev_id, seen, limit) def revision_shortlog(self, revisions, limit=None): - yield from ((rev['id'], rev['parents']) - for rev in self.revision_log(revisions, limit)) + yield from ( + (rev["id"], rev["parents"]) for rev in self.revision_log(revisions, limit) + ) def revision_get_random(self): return random.choice(list(self._revisions)) def release_add(self, releases: Iterable[Release]) -> Dict: - releases = [rel for rel in releases - if rel.id not in self._releases] + releases = [rel for rel in releases if rel.id not in self._releases] self.journal_writer.release_add(releases) count = 0 for rel in releases: if rel.author: self._person_add(rel.author) - self._objects[rel.id].append( - ('release', rel.id)) + self._objects[rel.id].append(("release", rel.id)) self._releases[rel.id] = rel count += 1 - return {'release:add': count} + return {"release:add": count} def release_missing(self, releases): yield from (rel for rel in releases if rel not in self._releases) def release_get(self, releases): for rel_id in releases: if rel_id in self._releases: yield self._releases[rel_id].to_dict() else: yield None def release_get_random(self): return random.choice(list(self._releases)) def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: count = 0 - snapshots = (snap for snap in snapshots - if snap.id not in self._snapshots) + snapshots = (snap for snap in snapshots if snap.id not in self._snapshots) for snapshot in snapshots: self.journal_writer.snapshot_add(snapshot) sorted_branch_names = sorted(snapshot.branches) self._snapshots[snapshot.id] = (snapshot, sorted_branch_names) - self._objects[snapshot.id].append(('snapshot', snapshot.id)) + self._objects[snapshot.id].append(("snapshot", snapshot.id)) count += 1 - return {'snapshot:add': count} + return {"snapshot:add": count} def snapshot_missing(self, snapshots): for id in snapshots: if id not in self._snapshots: yield id def snapshot_get(self, snapshot_id): return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): origin_url = self._get_origin_url(origin) if not origin_url: return - if origin_url not in self._origins or \ - visit > len(self._origin_visits[origin_url]): + if origin_url not in self._origins or visit > len( + self._origin_visits[origin_url] + ): return None - snapshot_id = self._origin_visits[origin_url][visit-1].snapshot + snapshot_id = self._origin_visits[origin_url][visit - 1].snapshot if snapshot_id: return self.snapshot_get(snapshot_id) else: return None def snapshot_get_latest(self, origin, allowed_statuses=None): origin_url = self._get_origin_url(origin) if not origin_url: return visit = self.origin_visit_get_latest( - origin_url, - allowed_statuses=allowed_statuses, - require_snapshot=True) - if visit and visit['snapshot']: - snapshot = self.snapshot_get(visit['snapshot']) + origin_url, allowed_statuses=allowed_statuses, require_snapshot=True + ) + if visit and visit["snapshot"]: + snapshot = self.snapshot_get(visit["snapshot"]) if not snapshot: raise StorageArgumentException( - 'last origin visit references an unknown snapshot') + "last origin visit references an unknown snapshot" + ) return snapshot def snapshot_count_branches(self, snapshot_id): (snapshot, _) = self._snapshots[snapshot_id] - return collections.Counter(branch.target_type.value if branch else None - for branch in snapshot.branches.values()) + return collections.Counter( + branch.target_type.value if branch else None + for branch in snapshot.branches.values() + ) - def snapshot_get_branches(self, snapshot_id, branches_from=b'', - branches_count=1000, target_types=None): + def snapshot_get_branches( + self, snapshot_id, branches_from=b"", branches_count=1000, target_types=None + ): res = self._snapshots.get(snapshot_id) if res is None: return None (snapshot, sorted_branch_names) = res - from_index = bisect.bisect_left( - sorted_branch_names, branches_from) + from_index = bisect.bisect_left(sorted_branch_names, branches_from) if target_types: next_branch = None branches = {} for branch_name in sorted_branch_names[from_index:]: branch = snapshot.branches[branch_name] if branch and branch.target_type.value in target_types: if len(branches) < branches_count: branches[branch_name] = branch else: next_branch = branch_name break else: # As there is no 'target_types', we can do that much faster to_index = from_index + branches_count returned_branch_names = sorted_branch_names[from_index:to_index] - branches = {branch_name: snapshot.branches[branch_name] - for branch_name in returned_branch_names} + branches = { + branch_name: snapshot.branches[branch_name] + for branch_name in returned_branch_names + } if to_index >= len(sorted_branch_names): next_branch = None else: next_branch = sorted_branch_names[to_index] - branches = {name: branch.to_dict() if branch else None - for (name, branch) in branches.items()} + branches = { + name: branch.to_dict() if branch else None + for (name, branch) in branches.items() + } return { - 'id': snapshot_id, - 'branches': branches, - 'next_branch': next_branch, - } + "id": snapshot_id, + "branches": branches, + "next_branch": next_branch, + } def snapshot_get_random(self): return random.choice(list(self._snapshots)) def object_find_by_sha1_git(self, ids): ret = {} for id_ in ids: objs = self._objects.get(id_, []) - ret[id_] = [{ - 'sha1_git': id_, - 'type': obj[0], - } for obj in objs] + ret[id_] = [{"sha1_git": id_, "type": obj[0],} for obj in objs] return ret def _convert_origin(self, t): if t is None: return None return t.to_dict() def origin_get(self, origins): if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False # Sanity check to be error-compatible with the pgsql backend - if any('id' in origin for origin in origins) \ - and not all('id' in origin for origin in origins): + if any("id" in origin for origin in origins) and not all( + "id" in origin for origin in origins + ): raise StorageArgumentException( - 'Either all origins or none at all should have an "id".') - if any('url' in origin for origin in origins) \ - and not all('url' in origin for origin in origins): + 'Either all origins or none at all should have an "id".' + ) + if any("url" in origin for origin in origins) and not all( + "url" in origin for origin in origins + ): raise StorageArgumentException( - 'Either all origins or none at all should have ' - 'an "url" key.') + "Either all origins or none at all should have " 'an "url" key.' + ) results = [] for origin in origins: result = None - if 'url' in origin: - if origin['url'] in self._origins: - result = self._origins[origin['url']] + if "url" in origin: + if origin["url"] in self._origins: + result = self._origins[origin["url"]] else: - raise StorageArgumentException( - 'Origin must have an url.') + raise StorageArgumentException("Origin must have an url.") results.append(self._convert_origin(result)) if return_single: assert len(results) == 1 return results[0] else: return results def origin_get_by_sha1(self, sha1s): - return [ - self._convert_origin(self._origins_by_sha1.get(sha1)) - for sha1 in sha1s - ] + return [self._convert_origin(self._origins_by_sha1.get(sha1)) for sha1 in sha1s] def origin_get_range(self, origin_from=1, origin_count=100): origin_from = max(origin_from, 1) if origin_from <= len(self._origins_by_id): max_idx = origin_from + origin_count - 1 if max_idx > len(self._origins_by_id): max_idx = len(self._origins_by_id) - for idx in range(origin_from-1, max_idx): - origin = self._convert_origin( - self._origins[self._origins_by_id[idx]]) - yield {'id': idx+1, **origin} + for idx in range(origin_from - 1, max_idx): + origin = self._convert_origin(self._origins[self._origins_by_id[idx]]) + yield {"id": idx + 1, **origin} - def origin_list(self, page_token: Optional[str] = None, limit: int = 100 - ) -> dict: + def origin_list(self, page_token: Optional[str] = None, limit: int = 100) -> dict: origin_urls = sorted(self._origins) if page_token: from_ = bisect.bisect_left(origin_urls, page_token) else: from_ = 0 result = { - 'origins': [{'url': origin_url} - for origin_url in origin_urls[from_:from_+limit]] + "origins": [ + {"url": origin_url} for origin_url in origin_urls[from_ : from_ + limit] + ] } - if from_+limit < len(origin_urls): - result['next_page_token'] = origin_urls[from_+limit] + if from_ + limit < len(origin_urls): + result["next_page_token"] = origin_urls[from_ + limit] return result - def origin_search(self, url_pattern, offset=0, limit=50, - regexp=False, with_visit=False): + def origin_search( + self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False + ): origins = map(self._convert_origin, self._origins.values()) if regexp: pat = re.compile(url_pattern) - origins = [orig for orig in origins if pat.search(orig['url'])] + origins = [orig for orig in origins if pat.search(orig["url"])] else: - origins = [orig for orig in origins if url_pattern in orig['url']] + origins = [orig for orig in origins if url_pattern in orig["url"]] if with_visit: origins = [ - orig for orig in origins - if len(self._origin_visits[orig['url']]) > 0 and - set(ov.snapshot - for ov in self._origin_visits[orig['url']] - if ov.snapshot) & - set(self._snapshots)] - - return origins[offset:offset+limit] + orig + for orig in origins + if len(self._origin_visits[orig["url"]]) > 0 + and set( + ov.snapshot + for ov in self._origin_visits[orig["url"]] + if ov.snapshot + ) + & set(self._snapshots) + ] + + return origins[offset : offset + limit] def origin_count(self, url_pattern, regexp=False, with_visit=False): - return len(self.origin_search(url_pattern, regexp=regexp, - with_visit=with_visit, - limit=len(self._origins))) + return len( + self.origin_search( + url_pattern, + regexp=regexp, + with_visit=with_visit, + limit=len(self._origins), + ) + ) def origin_add(self, origins: Iterable[Origin]) -> List[Dict]: origins = copy.deepcopy(list(origins)) for origin in origins: self.origin_add_one(origin) return [origin.to_dict() for origin in origins] def origin_add_one(self, origin: Origin) -> str: if origin.url not in self._origins: self.journal_writer.origin_add_one(origin) # generate an origin_id because it is needed by origin_get_range. # TODO: remove this when we remove origin_get_range origin_id = len(self._origins) + 1 self._origins_by_id.append(origin.url) assert len(self._origins_by_id) == origin_id self._origins[origin.url] = origin self._origins_by_sha1[origin_url_to_sha1(origin.url)] = origin self._origin_visits[origin.url] = [] - self._objects[origin.url].append(('origin', origin.url)) + self._objects[origin.url].append(("origin", origin.url)) return origin.url - def origin_visit_add(self, origin_url: str, - date: Union[str, datetime.datetime], - type: str) -> OriginVisit: + def origin_visit_add( + self, origin_url: str, date: Union[str, datetime.datetime], type: str + ) -> OriginVisit: if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): - raise StorageArgumentException( - 'Date must be a datetime or a string') + raise StorageArgumentException("Date must be a datetime or a string") - origin = self.origin_get({'url': origin_url}) + origin = self.origin_get({"url": origin_url}) if not origin: # Cannot add a visit without an origin - raise StorageArgumentException( - 'Unknown origin %s', origin_url) + raise StorageArgumentException("Unknown origin %s", origin_url) if origin_url in self._origins: origin = self._origins[origin_url] # visit ids are in the range [1, +inf[ visit_id = len(self._origin_visits[origin_url]) + 1 - status = 'ongoing' + status = "ongoing" visit = OriginVisit( origin=origin_url, date=date, type=type, status=status, snapshot=None, metadata=None, visit=visit_id, ) self._origin_visits[origin_url].append(visit) visit = visit - self._objects[(origin_url, visit.visit)].append( - ('origin_visit', None)) + self._objects[(origin_url, visit.visit)].append(("origin_visit", None)) self.journal_writer.origin_visit_add(visit) # return last visit return visit def origin_visit_update( - self, origin: str, visit_id: int, status: str, - metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None, - date: Optional[datetime.datetime] = None): + self, + origin: str, + visit_id: int, + status: str, + metadata: Optional[Dict] = None, + snapshot: Optional[bytes] = None, + date: Optional[datetime.datetime] = None, + ): origin_url = self._get_origin_url(origin) if origin_url is None: - raise StorageArgumentException('Unknown origin.') + raise StorageArgumentException("Unknown origin.") try: - visit = self._origin_visits[origin_url][visit_id-1] + visit = self._origin_visits[origin_url][visit_id - 1] except IndexError: - raise StorageArgumentException( - 'Unknown visit_id for this origin') from None + raise StorageArgumentException("Unknown visit_id for this origin") from None - updates: Dict[str, Any] = { - 'status': status - } + updates: Dict[str, Any] = {"status": status} if metadata: - updates['metadata'] = metadata + updates["metadata"] = metadata if snapshot: - updates['snapshot'] = snapshot + updates["snapshot"] = snapshot with convert_validation_exceptions(): visit = attr.evolve(visit, **updates) self.journal_writer.origin_visit_update(visit) - self._origin_visits[origin_url][visit_id-1] = visit + self._origin_visits[origin_url][visit_id - 1] = visit def origin_visit_upsert(self, visits: Iterable[OriginVisit]) -> None: for visit in visits: if visit.visit is None: - raise StorageArgumentException( - f'Missing visit id for visit {visit}') + raise StorageArgumentException(f"Missing visit id for visit {visit}") self.journal_writer.origin_visit_upsert(visits) for visit in visits: visit_id = visit.visit origin_url = visit.origin with convert_validation_exceptions(): visit = attr.evolve(visit, origin=origin_url) - self._objects[(origin_url, visit_id)].append( - ('origin_visit', None)) + self._objects[(origin_url, visit_id)].append(("origin_visit", None)) if visit_id: while len(self._origin_visits[origin_url]) <= visit_id: self._origin_visits[origin_url].append(None) - self._origin_visits[origin_url][visit_id-1] = visit + self._origin_visits[origin_url][visit_id - 1] = visit def _convert_visit(self, visit): if visit is None: return visit = visit.to_dict() return visit def origin_visit_get( - self, origin: str, last_visit: Optional[int] = None, - limit: Optional[int] = None) -> Iterable[Dict[str, Any]]: + self, origin: str, last_visit: Optional[int] = None, limit: Optional[int] = None + ) -> Iterable[Dict[str, Any]]: origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] if last_visit is not None: visits = visits[last_visit:] if limit is not None: visits = visits[:limit] for visit in visits: if not visit: continue visit_id = visit.visit - yield self._convert_visit( - self._origin_visits[origin_url][visit_id-1]) + yield self._convert_visit(self._origin_visits[origin_url][visit_id - 1]) def origin_visit_find_by_date( - self, origin: str, - visit_date: datetime.datetime) -> Optional[Dict[str, Any]]: + self, origin: str, visit_date: datetime.datetime + ) -> Optional[Dict[str, Any]]: origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] - visit = min( - visits, - key=lambda v: (abs(v.date - visit_date), -v.visit)) + visit = min(visits, key=lambda v: (abs(v.date - visit_date), -v.visit)) return self._convert_visit(visit) return None - def origin_visit_get_by( - self, origin: str, visit: int) -> Optional[Dict[str, Any]]: + def origin_visit_get_by(self, origin: str, visit: int) -> Optional[Dict[str, Any]]: origin_url = self._get_origin_url(origin) - if origin_url in self._origin_visits and \ - visit <= len(self._origin_visits[origin_url]): - return self._convert_visit( - self._origin_visits[origin_url][visit-1]) + if origin_url in self._origin_visits and visit <= len( + self._origin_visits[origin_url] + ): + return self._convert_visit(self._origin_visits[origin_url][visit - 1]) return None def origin_visit_get_latest( - self, origin: str, allowed_statuses: Optional[List[str]] = None, - require_snapshot: bool = False) -> Optional[Dict[str, Any]]: + self, + origin: str, + allowed_statuses: Optional[List[str]] = None, + require_snapshot: bool = False, + ) -> Optional[Dict[str, Any]]: ori = self._origins.get(origin) if not ori: return None visits = self._origin_visits[ori.url] if allowed_statuses is not None: - visits = [visit for visit in visits - if visit.status in allowed_statuses] + visits = [visit for visit in visits if visit.status in allowed_statuses] if require_snapshot: - visits = [visit for visit in visits - if visit.snapshot] + visits = [visit for visit in visits if visit.snapshot] - visit = max( - visits, key=lambda v: (v.date, v.visit), default=None) + visit = max(visits, key=lambda v: (v.date, v.visit), default=None) return self._convert_visit(visit) def _select_random_origin_visit_by_type(self, type: str) -> str: while True: url = random.choice(list(self._origin_visits.keys())) random_origin_visits = self._origin_visits[url] if random_origin_visits[0].type == type: return url def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: url = self._select_random_origin_visit_by_type(type) random_origin_visits = copy.deepcopy(self._origin_visits[url]) random_origin_visits.reverse() back_in_the_day = now() - timedelta(weeks=12) # 3 months back # This should be enough for tests for visit in random_origin_visits: - if visit.date > back_in_the_day and visit.status == 'full': + if visit.date > back_in_the_day and visit.status == "full": return visit.to_dict() else: return None def stat_counters(self): keys = ( - 'content', - 'directory', - 'origin', - 'origin_visit', - 'person', - 'release', - 'revision', - 'skipped_content', - 'snapshot' - ) + "content", + "directory", + "origin", + "origin_visit", + "person", + "release", + "revision", + "skipped_content", + "snapshot", + ) stats = {key: 0 for key in keys} - stats.update(collections.Counter( - obj_type - for (obj_type, obj_id) - in itertools.chain(*self._objects.values()))) + stats.update( + collections.Counter( + obj_type + for (obj_type, obj_id) in itertools.chain(*self._objects.values()) + ) + ) return stats def refresh_stat_counters(self): pass def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): if not isinstance(origin_url, str): - raise TypeError('origin_id must be str, not %r' % (origin_url,)) + raise TypeError("origin_id must be str, not %r" % (origin_url,)) if isinstance(ts, str): ts = dateutil.parser.parse(ts) origin_metadata = { - 'origin_url': origin_url, - 'discovery_date': ts, - 'tool_id': tool, - 'metadata': metadata, - 'provider_id': provider, - } + "origin_url": origin_url, + "discovery_date": ts, + "tool_id": tool, + "metadata": metadata, + "provider_id": provider, + } self._origin_metadata[origin_url].append(origin_metadata) return None def origin_metadata_get_by(self, origin_url, provider_type=None): if not isinstance(origin_url, str): - raise TypeError('origin_url must be str, not %r' % (origin_url,)) + raise TypeError("origin_url must be str, not %r" % (origin_url,)) metadata = [] for item in self._origin_metadata[origin_url]: item = copy.deepcopy(item) - provider = self.metadata_provider_get(item['provider_id']) - for attr_name in ('name', 'type', 'url'): - item['provider_' + attr_name] = \ - provider['provider_' + attr_name] + provider = self.metadata_provider_get(item["provider_id"]) + for attr_name in ("name", "type", "url"): + item["provider_" + attr_name] = provider["provider_" + attr_name] metadata.append(item) return metadata def tool_add(self, tools): inserted = [] for tool in tools: key = self._tool_key(tool) - assert 'id' not in tool + assert "id" not in tool record = copy.deepcopy(tool) - record['id'] = key # TODO: remove this + record["id"] = key # TODO: remove this if key not in self._tools: self._tools[key] = record inserted.append(copy.deepcopy(self._tools[key])) return inserted def tool_get(self, tool): return self._tools.get(self._tool_key(tool)) - def metadata_provider_add(self, provider_name, provider_type, provider_url, - metadata): + def metadata_provider_add( + self, provider_name, provider_type, provider_url, metadata + ): provider = { - 'provider_name': provider_name, - 'provider_type': provider_type, - 'provider_url': provider_url, - 'metadata': metadata, - } + "provider_name": provider_name, + "provider_type": provider_type, + "provider_url": provider_url, + "metadata": metadata, + } key = self._metadata_provider_key(provider) - provider['id'] = key + provider["id"] = key self._metadata_providers[key] = provider return key def metadata_provider_get(self, provider_id): return self._metadata_providers.get(provider_id) def metadata_provider_get_by(self, provider): key = self._metadata_provider_key(provider) return self._metadata_providers.get(key) def _get_origin_url(self, origin): if isinstance(origin, str): return origin else: - raise TypeError('origin must be a string.') + raise TypeError("origin must be a string.") def _person_add(self, person): - key = ('person', person.fullname) + key = ("person", person.fullname) if key not in self._objects: person_id = len(self._persons) + 1 self._persons.append(person) - self._objects[key].append(('person', person_id)) + self._objects[key].append(("person", person_id)) else: person_id = self._objects[key][0][1] - person = self._persons[person_id-1] + person = self._persons[person_id - 1] return person @staticmethod def _content_key(content): """ A stable key and the algorithm for a content""" if isinstance(content, BaseContent): content = content.to_dict() - return tuple((key, content.get(key)) - for key in sorted(DEFAULT_ALGORITHMS)) + return tuple((key, content.get(key)) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _tool_key(tool): - return '%r %r %r' % (tool['name'], tool['version'], - tuple(sorted(tool['configuration'].items()))) + return "%r %r %r" % ( + tool["name"], + tool["version"], + tuple(sorted(tool["configuration"].items())), + ) @staticmethod def _metadata_provider_key(provider): - return '%r %r' % (provider['provider_name'], provider['provider_url']) + return "%r %r" % (provider["provider_name"], provider["provider_url"]) def diff_directories(self, from_dir, to_dir, track_renaming=False): - raise NotImplementedError('InMemoryStorage.diff_directories') + raise NotImplementedError("InMemoryStorage.diff_directories") def diff_revisions(self, from_rev, to_rev, track_renaming=False): - raise NotImplementedError('InMemoryStorage.diff_revisions') + raise NotImplementedError("InMemoryStorage.diff_revisions") def diff_revision(self, revision, track_renaming=False): - raise NotImplementedError('InMemoryStorage.diff_revision') + raise NotImplementedError("InMemoryStorage.diff_revision") diff --git a/swh/storage/interface.py b/swh/storage/interface.py index a17673ad..3d73e840 100644 --- a/swh/storage/interface.py +++ b/swh/storage/interface.py @@ -1,1290 +1,1305 @@ # 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, Dict, Iterable, List, Optional, Union from swh.core.api import remote_api_endpoint from swh.model.model import ( - Content, Directory, Origin, OriginVisit, Revision, Release, - Snapshot, SkippedContent + Content, + Directory, + Origin, + OriginVisit, + Revision, + Release, + Snapshot, + SkippedContent, ) def deprecated(f): f.deprecated_endpoint = True return f class StorageInterface: - @remote_api_endpoint('check_config') + @remote_api_endpoint("check_config") def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" ... - @remote_api_endpoint('content/add') + @remote_api_endpoint("content/add") def content_add(self, content: Iterable[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') + @remote_api_endpoint("content/update") def content_update(self, content, keys=[]): """Update content blobs to the storage. Does nothing for unknown contents or skipped ones. Args: content (iterable): 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') + @remote_api_endpoint("content/add_metadata") def content_add_metadata(self, content: Iterable[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') + @remote_api_endpoint("content/data") def content_get(self, content): """Retrieve in bulk contents and their data. This generator yields exactly as many items than provided sha1 identifiers, but callers should not assume this will always be true. It may also yield `None` values in case an object was not found. Args: content: iterables of sha1 Yields: Dict[str, bytes]: Generates streams of contents as dict with their raw data: - sha1 (bytes): content id - data (bytes): content's raw data Raises: ValueError in case of too much contents are required. cf. BULK_BLOCK_CONTENT_LEN_MAX """ ... @deprecated - @remote_api_endpoint('content/range') + @remote_api_endpoint("content/range") def content_get_range(self, start, end, limit=1000): """Retrieve contents within range [start, end] bound by limit. Note that this function may return more than one blob per hash. The limit is enforced with multiplicity (ie. two blobs with the same hash will count twice toward the limit). Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **limit** (int): Limit result (default to 1000) Returns: a dict with keys: - contents [dict]: iterable of contents in between the range. - next (bytes): There remains content in the range starting from this next sha1 """ ... - @remote_api_endpoint('content/partition') + @remote_api_endpoint("content/partition") def content_get_partition( - self, partition_id: int, nb_partitions: int, limit: int = 1000, - page_token: str = None): + self, + partition_id: int, + nb_partitions: int, + limit: int = 1000, + page_token: str = None, + ): """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 (int): index of the partition to fetch nb_partitions (int): total number of partitions to split into limit (int): Limit result (default to 1000) page_token (Optional[str]): opaque token used for pagination. Returns: a dict with keys: - contents (List[dict]): iterable of contents in the partition. - **next_page_token** (Optional[str]): opaque token to be used as `page_token` for retrieving the next page. if absent, there is no more pages to gather. """ ... - @remote_api_endpoint('content/metadata') - def content_get_metadata( - self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: + @remote_api_endpoint("content/metadata") + def content_get_metadata(self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: """Retrieve content metadata in bulk Args: content: iterable of content identifiers (sha1) Returns: a dict with keys the content's sha1 and the associated value either the existing content's metadata or None if the content does not exist. """ ... - @remote_api_endpoint('content/missing') - def content_missing(self, content, key_hash='sha1'): + @remote_api_endpoint("content/missing") + def content_missing(self, content, key_hash="sha1"): """List content missing from storage Args: content ([dict]): 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 (str): name of the column to use as hash id result (default: 'sha1') Returns: iterable ([bytes]): missing content ids (as per the key_hash column) Raises: TODO: an exception when we get a hash collision. """ ... - @remote_api_endpoint('content/missing/sha1') + @remote_api_endpoint("content/missing/sha1") def content_missing_per_sha1(self, contents): """List content missing from storage based only on sha1. Args: contents: Iterable of sha1 to check for absence. Returns: iterable: missing ids Raises: TODO: an exception when we get a hash collision. """ ... - @remote_api_endpoint('content/missing/sha1_git') + @remote_api_endpoint("content/missing/sha1_git") def content_missing_per_sha1_git(self, contents): """List content missing from storage based only on sha1_git. Args: contents (Iterable): An iterable of content id (sha1_git) Yields: missing contents sha1_git """ ... - @remote_api_endpoint('content/present') + @remote_api_endpoint("content/present") def content_find(self, 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 Returns: a triplet (sha1, sha1_git, sha256) if the content exist or None otherwise. Raises: ValueError: in case the key of the dictionary is not sha1, sha1_git nor sha256. """ ... - @remote_api_endpoint('content/get_random') + @remote_api_endpoint("content/get_random") def content_get_random(self): """Finds a random content id. Returns: a sha1_git """ ... - @remote_api_endpoint('content/skipped/add') + @remote_api_endpoint("content/skipped/add") def skipped_content_add(self, content: Iterable[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') + @remote_api_endpoint("content/skipped/missing") def skipped_content_missing(self, contents): """List skipped_content missing from storage Args: content: iterable of dictionaries containing the data for each checksum algorithm. Returns: iterable: missing signatures """ ... - @remote_api_endpoint('directory/add') + @remote_api_endpoint("directory/add") def directory_add(self, directories: Iterable[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') + @remote_api_endpoint("directory/missing") def directory_missing(self, directories): """List directories missing from storage Args: directories (iterable): an iterable of directory ids Yields: missing directory ids """ ... - @remote_api_endpoint('directory/ls') + @remote_api_endpoint("directory/ls") def directory_ls(self, directory, recursive=False): """Get entries for one directory. Args: - directory: the directory to list entries from. - recursive: if flag on, this list recursively from this directory. Returns: List of entries for such directory. If `recursive=True`, names in the path of a dir/file not at the root are concatenated with a slash (`/`). """ ... - @remote_api_endpoint('directory/path') + @remote_api_endpoint("directory/path") def directory_entry_get_by_path(self, directory, paths): """Get the directory entry (either file or dir) from directory with path. Args: - directory: sha1 of the top level directory - paths: path to lookup from the top level directory. From left (top) to right (bottom). Returns: The corresponding directory entry if found, None otherwise. """ ... - @remote_api_endpoint('directory/get_random') + @remote_api_endpoint("directory/get_random") def directory_get_random(self): """Finds a random directory id. Returns: a sha1_git """ ... - @remote_api_endpoint('revision/add') + @remote_api_endpoint("revision/add") def revision_add(self, revisions: Iterable[Revision]) -> Dict: """Add revisions to the storage Args: revisions (Iterable[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') + @remote_api_endpoint("revision/missing") def revision_missing(self, revisions): """List revisions missing from storage Args: revisions (iterable): revision ids Yields: missing revision ids """ ... - @remote_api_endpoint('revision') + @remote_api_endpoint("revision") def revision_get(self, revisions): """Get all revisions from storage Args: revisions: an iterable of revision ids Returns: iterable: an iterable of revisions as dictionaries (or None if the revision doesn't exist) """ ... - @remote_api_endpoint('revision/log') + @remote_api_endpoint("revision/log") def revision_log(self, revisions, limit=None): """Fetch revision entry from the given root revisions. Args: revisions: array of root revision to lookup limit: limitation on the output result. Default to None. Yields: List of revision log from such revisions root. """ ... - @remote_api_endpoint('revision/shortlog') + @remote_api_endpoint("revision/shortlog") def revision_shortlog(self, revisions, limit=None): """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') + @remote_api_endpoint("revision/get_random") def revision_get_random(self): """Finds a random revision id. Returns: a sha1_git """ ... - @remote_api_endpoint('release/add') + @remote_api_endpoint("release/add") def release_add(self, releases: Iterable[Release]) -> Dict: """Add releases to the storage Args: releases (Iterable[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') + @remote_api_endpoint("release/missing") def release_missing(self, releases): """List releases missing from storage Args: releases: an iterable of release ids Returns: a list of missing release ids """ ... - @remote_api_endpoint('release') + @remote_api_endpoint("release") def release_get(self, releases): """Given a list of sha1, return the releases's information Args: releases: list of sha1s Yields: dicts with the same keys as those given to `release_add` (or ``None`` if a release does not exist) """ ... - @remote_api_endpoint('release/get_random') + @remote_api_endpoint("release/get_random") def release_get_random(self): """Finds a random release id. Returns: a sha1_git """ ... - @remote_api_endpoint('snapshot/add') + @remote_api_endpoint("snapshot/add") def snapshot_add(self, snapshots: Iterable[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') + @remote_api_endpoint("snapshot/missing") def snapshot_missing(self, snapshots): """List snapshots missing from storage Args: snapshots (iterable): an iterable of snapshot ids Yields: missing snapshot ids """ ... - @remote_api_endpoint('snapshot') + @remote_api_endpoint("snapshot") def snapshot_get(self, snapshot_id): """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 (bytes): identifier of the snapshot 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/by_origin_visit') + @remote_api_endpoint("snapshot/by_origin_visit") def snapshot_get_by_origin_visit(self, origin, visit): """Get the content, possibly partial, of a snapshot for the given origin visit 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: origin (int): the origin identifier visit (int): the visit identifier 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 1000 branches. """ ... - @remote_api_endpoint('snapshot/latest') + @remote_api_endpoint("snapshot/latest") def snapshot_get_latest(self, origin, allowed_statuses=None): """Get the content, possibly partial, of 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. .. 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: origin (str): the origin's URL allowed_statuses (list of str): 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. 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') + @remote_api_endpoint("snapshot/count_branches") def snapshot_count_branches(self, snapshot_id): """Count the number of branches in the snapshot with the given id Args: snapshot_id (bytes): identifier of the snapshot Returns: dict: 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, branches_from=b'', - branches_count=1000, target_types=None): + @remote_api_endpoint("snapshot/get_branches") + def snapshot_get_branches( + self, snapshot_id, branches_from=b"", branches_count=1000, target_types=None + ): """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 (bytes): identifier of the snapshot branches_from (bytes): optional parameter used to skip branches whose name is lesser than it before returning them branches_count (int): optional parameter used to restrain the amount of returned branches target_types (list): 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') + @remote_api_endpoint("snapshot/get_random") def snapshot_get_random(self): """Finds a random snapshot id. Returns: a sha1_git """ ... - @remote_api_endpoint('origin/visit/add') + @remote_api_endpoint("origin/visit/add") def origin_visit_add( - self, origin_url: str, - date: Union[str, datetime.datetime], - type: str) -> OriginVisit: + self, origin_url: str, date: Union[str, datetime.datetime], type: str + ) -> OriginVisit: """Add an origin_visit for the origin at ts with status 'ongoing'. Args: origin_url: visited origin identifier (its URL) date: timestamp of such visit type: the type of loader used for the visit (hg, git, ...) Raises: StorageArgumentException if the date is mistyped, or the origin is unknown. Returns: dict: dictionary with keys origin and visit where: - origin: origin object - visit: the visit object for the new visit occurrence """ ... - @remote_api_endpoint('origin/visit/update') + @remote_api_endpoint("origin/visit/update") def origin_visit_update( - self, origin: str, visit_id: int, status: str, - metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None, - date: Optional[datetime.datetime] = None): + self, + origin: str, + visit_id: int, + status: str, + metadata: Optional[Dict] = None, + snapshot: Optional[bytes] = None, + date: Optional[datetime.datetime] = None, + ): """Update an origin_visit's status. Args: origin (str): visited origin's URL visit_id: Visit's id status: Visit's new status metadata: Data associated to the visit snapshot (sha1_git): identifier of the snapshot to add to the visit date: Update date Returns: None """ ... - @remote_api_endpoint('origin/visit/upsert') + @remote_api_endpoint("origin/visit/upsert") def origin_visit_upsert(self, visits: Iterable[OriginVisit]) -> None: """Add a origin_visits with a specific id and with all its data. If there is already an origin_visit with the same `(origin_id, visit_id)`, overwrites it. Args: visits: iterable of dicts with keys: - **origin**: dict with keys either `id` or `url` - **visit**: origin visit id - **date**: timestamp of such visit - **status**: Visit's new status - **metadata**: Data associated to the visit - **snapshot**: identifier of the snapshot to add to the visit """ ... - @remote_api_endpoint('origin/visit/get') + @remote_api_endpoint("origin/visit/get") def origin_visit_get( - self, origin: str, last_visit: Optional[int] = None, - limit: Optional[int] = None) -> Iterable[Dict[str, Any]]: + self, origin: str, last_visit: Optional[int] = None, limit: Optional[int] = None + ) -> Iterable[Dict[str, Any]]: """Retrieve all the origin's visit's information. Args: origin: The visited origin last_visit: Starting point from which listing the next visits Default to None limit: Number of results to return from the last visit. Default to None Yields: List of visits. """ ... - @remote_api_endpoint('origin/visit/find_by_date') + @remote_api_endpoint("origin/visit/find_by_date") def origin_visit_find_by_date( - self, origin: str, - visit_date: datetime.datetime) -> Optional[Dict[str, Any]]: + self, origin: str, visit_date: datetime.datetime + ) -> Optional[Dict[str, Any]]: """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 """ ... - @remote_api_endpoint('origin/visit/getby') - def origin_visit_get_by( - self, origin: str, visit: int) -> Optional[Dict[str, Any]]: + @remote_api_endpoint("origin/visit/getby") + def origin_visit_get_by(self, origin: str, visit: int) -> Optional[Dict[str, Any]]: """Retrieve origin visit's information. Args: origin: origin (URL) visit: visit id Returns: The information on that particular (origin, visit) or None if it does not exist """ ... - @remote_api_endpoint('origin/visit/get_latest') + @remote_api_endpoint("origin/visit/get_latest") def origin_visit_get_latest( - self, origin: str, allowed_statuses: Optional[List[str]] = None, - require_snapshot: bool = False) -> Optional[Dict[str, Any]]: + self, + origin: str, + allowed_statuses: Optional[List[str]] = None, + require_snapshot: bool = False, + ) -> Optional[Dict[str, Any]]: """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 known snapshot. Args: origin: origin URL allowed_statuses: list of visit statuses considered to find the latest visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. require_snapshot: If True, only a visit with a snapshot will be returned. Returns: dict: a dict with the following keys: - **origin**: the URL of the origin - **visit**: origin visit id - **type**: type of loader used for the visit - **date**: timestamp of such visit - **status**: Visit's new status - **metadata**: Data associated to the visit - **snapshot** (Optional[sha1_git]): identifier of the snapshot associated to the visit """ ... - @remote_api_endpoint('origin/visit/get_random') - def origin_visit_get_random( - self, type: str) -> Optional[Dict[str, Any]]: + @remote_api_endpoint("origin/visit/get_random") + def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: """Randomly select one successful origin visit with made in the last 3 months. Returns: dict representing an origin visit, in the same format as :py:meth:`origin_visit_get`. """ ... - @remote_api_endpoint('object/find_by_sha1_git') + @remote_api_endpoint("object/find_by_sha1_git") def object_find_by_sha1_git(self, ids): """Return the objects found with the given ids. Args: ids: a generator of sha1_gits Returns: dict: a mapping from id to the list of objects found. 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') + @remote_api_endpoint("origin/get") def origin_get(self, origins): """Return origins, either all identified by their ids or all identified by tuples (type, url). If the url is given and the type is omitted, one of the origins with that url is returned. Args: origin: a list of dictionaries representing the individual origins to find. These dicts have the key url: - url (bytes): the url the origin points to Returns: dict: the origin dictionary with the keys: - id: origin's id - url: origin's url Raises: ValueError: if the url or the id don't exist. """ ... - @remote_api_endpoint('origin/get_sha1') + @remote_api_endpoint("origin/get_sha1") def origin_get_by_sha1(self, sha1s): """Return origins, identified by the sha1 of their URLs. Args: sha1s (list[bytes]): a list of sha1s Yields: dicts containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`, or None if an origin matching the sha1 is not found. """ ... @deprecated - @remote_api_endpoint('origin/get_range') + @remote_api_endpoint("origin/get_range") def origin_get_range(self, origin_from=1, origin_count=100): """Retrieve ``origin_count`` origins whose ids are greater or equal than ``origin_from``. Origins are sorted by id before retrieving them. Args: origin_from (int): the minimum id of origins to retrieve origin_count (int): the maximum number of origins to retrieve Yields: dicts containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`. """ ... - @remote_api_endpoint('origin/list') - def origin_list( - self, page_token: Optional[str] = None, limit: int = 100) -> dict: + @remote_api_endpoint("origin/list") + def origin_list(self, page_token: Optional[str] = None, limit: int = 100) -> dict: """Returns the list of origins Args: page_token: opaque token used for pagination. limit: the maximum number of results to return Returns: dict: dict with the following keys: - **next_page_token** (str, optional): opaque token to be used as `page_token` for retrieving the next page. if absent, there is no more pages to gather. - **origins** (List[dict]): list of origins, as returned by `origin_get`. """ ... - @remote_api_endpoint('origin/search') - def origin_search(self, url_pattern, offset=0, limit=50, - regexp=False, with_visit=False): + @remote_api_endpoint("origin/search") + def origin_search( + self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False + ): """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 (str): the string pattern to search for in origin urls offset (int): number of found origins to skip before returning results limit (int): the maximum number of found origins to return 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 Yields: dicts containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`. """ ... @deprecated - @remote_api_endpoint('origin/count') - def origin_count(self, url_pattern, regexp=False, - with_visit=False): + @remote_api_endpoint("origin/count") + def origin_count(self, url_pattern, regexp=False, with_visit=False): """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') + @remote_api_endpoint("origin/add_multi") def origin_add(self, origins: Iterable[Origin]) -> List[Dict]: """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: list: given origins as dict updated with their id """ ... - @remote_api_endpoint('origin/add') + @remote_api_endpoint("origin/add") def origin_add_one(self, origin: Origin) -> str: """Add origin to the storage Args: origin: dictionary representing the individual origin to add. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the added origin, or of the identical one that already exists. """ ... 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('origin/metadata/add') + @remote_api_endpoint("origin/metadata/add") def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): """ Add an origin_metadata for the origin at ts with provenance and metadata. Args: origin_url (str): the origin url for which the metadata is added ts (datetime): timestamp of the found metadata provider (int): the provider of metadata (ex:'hal') tool (int): tool used to extract metadata metadata (jsonb): the metadata retrieved at the time and location """ ... - @remote_api_endpoint('origin/metadata/get') + @remote_api_endpoint("origin/metadata/get") def origin_metadata_get_by(self, origin_url, provider_type=None): """Retrieve list of all origin_metadata entries for the origin_id Args: origin_url (str): the origin's URL provider_type (str): (optional) type of provider Returns: list of dicts: the origin_metadata dictionary with the keys: - origin_id (int): origin's id - discovery_date (datetime): timestamp of discovery - tool_id (int): metadata's extracting tool - metadata (jsonb) - provider_id (int): metadata's provider - provider_name (str) - provider_type (str) - provider_url (str) """ ... - @remote_api_endpoint('tool/add') + @remote_api_endpoint("tool/add") def tool_add(self, tools): """Add new tools to the storage. Args: tools (iterable of :class:`dict`): Tool information to add to storage. Each tool is a :class:`dict` with the following keys: - name (:class:`str`): name of the tool - version (:class:`str`): version of the tool - configuration (:class:`dict`): configuration of the tool, must be json-encodable Returns: :class:`dict`: All the tools inserted in storage (including the internal ``id``). The order of the list is not guaranteed to match the order of the initial list. """ ... - @remote_api_endpoint('tool/data') + @remote_api_endpoint("tool/data") def tool_get(self, tool): """Retrieve tool information. Args: tool (dict): Tool information we want to retrieve from storage. The dicts have the same keys as those used in :func:`tool_add`. Returns: dict: The full tool information if it exists (``id`` included), None otherwise. """ ... - @remote_api_endpoint('provider/add') - def metadata_provider_add(self, provider_name, provider_type, provider_url, - metadata): + @remote_api_endpoint("provider/add") + def metadata_provider_add( + self, provider_name, provider_type, provider_url, metadata + ): """Add a metadata provider. Args: provider_name (str): Its name provider_type (str): Its type (eg. `'deposit-client'`) provider_url (str): Its URL metadata: JSON-encodable object Returns: int: an identifier of the provider """ ... - @remote_api_endpoint('provider/get') + @remote_api_endpoint("provider/get") def metadata_provider_get(self, provider_id): """Get a metadata provider Args: provider_id: Its identifier, as given by `metadata_provider_add`. Returns: dict: same as `metadata_provider_add`; or None if it does not exist. """ ... - @remote_api_endpoint('provider/getby') + @remote_api_endpoint("provider/getby") def metadata_provider_get_by(self, provider): """Get a metadata provider Args: provider (dict): A dictionary with keys: * provider_name: Its name * provider_url: Its URL Returns: dict: same as `metadata_provider_add`; or None if it does not exist. """ ... @deprecated - @remote_api_endpoint('algos/diff_directories') + @remote_api_endpoint("algos/diff_directories") def diff_directories(self, from_dir, to_dir, track_renaming=False): """Compute the list of file changes introduced between two arbitrary directories (insertion / deletion / modification / renaming of files). Args: from_dir (bytes): identifier of the directory to compare from to_dir (bytes): identifier of the directory to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ ... @deprecated - @remote_api_endpoint('algos/diff_revisions') + @remote_api_endpoint("algos/diff_revisions") def diff_revisions(self, from_rev, to_rev, track_renaming=False): """Compute the list of file changes introduced between two arbitrary revisions (insertion / deletion / modification / renaming of files). Args: from_rev (bytes): identifier of the revision to compare from to_rev (bytes): identifier of the revision to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ ... @deprecated - @remote_api_endpoint('algos/diff_revision') + @remote_api_endpoint("algos/diff_revision") def diff_revision(self, revision, track_renaming=False): """Compute the list of file changes introduced by a specific revision (insertion / deletion / modification / renaming of files) by comparing it against its first parent. Args: revision (bytes): identifier of the revision from which to compute the list of files changes track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ ... diff --git a/swh/storage/metrics.py b/swh/storage/metrics.py index 6eaded8f..70054bee 100644 --- a/swh/storage/metrics.py +++ b/swh/storage/metrics.py @@ -1,79 +1,83 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from functools import wraps import logging from swh.core.statsd import statsd -OPERATIONS_METRIC = 'swh_storage_operations_total' +OPERATIONS_METRIC = "swh_storage_operations_total" OPERATIONS_UNIT_METRIC = "swh_storage_operations_{unit}_total" DURATION_METRIC = "swh_storage_request_duration_seconds" def timed(f): """Time that function! """ + @wraps(f) def d(*a, **kw): - with statsd.timed(DURATION_METRIC, tags={'endpoint': f.__name__}): + with statsd.timed(DURATION_METRIC, tags={"endpoint": f.__name__}): return f(*a, **kw) return d def send_metric(metric, count, method_name): """Send statsd metric with count for method `method_name` If count is 0, the metric is discarded. If the metric is not parseable, the metric is discarded with a log message. Args: metric (str): Metric's name (e.g content:add, content:add:bytes) count (int): Associated value for the metric method_name (str): Method's name Returns: Bool to explicit if metric has been set or not """ if count == 0: return False - metric_type = metric.split(':') + metric_type = metric.split(":") _length = len(metric_type) if _length == 2: object_type, operation = metric_type metric_name = OPERATIONS_METRIC elif _length == 3: object_type, operation, unit = metric_type metric_name = OPERATIONS_UNIT_METRIC.format(unit=unit) else: - logging.warning('Skipping unknown metric {%s: %s}' % ( - metric, count)) + logging.warning("Skipping unknown metric {%s: %s}" % (metric, count)) return False statsd.increment( - metric_name, count, tags={ - 'endpoint': method_name, - 'object_type': object_type, - 'operation': operation, - }) + metric_name, + count, + tags={ + "endpoint": method_name, + "object_type": object_type, + "operation": operation, + }, + ) return True def process_metrics(f): """Increment object counters for the decorated function. """ + @wraps(f) def d(*a, **kw): r = f(*a, **kw) for metric, count in r.items(): send_metric(metric=metric, count=count, method_name=f.__name__) return r return d diff --git a/swh/storage/objstorage.py b/swh/storage/objstorage.py index 273984d3..4d5c8d52 100644 --- a/swh/storage/objstorage.py +++ b/swh/storage/objstorage.py @@ -1,66 +1,64 @@ # 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, Generator, Iterable from swh.model.model import Content, MissingData from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError 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': + if key == "objstorage": raise AttributeError(key) return getattr(self.objstorage, key) def content_get(self, contents: Iterable[bytes]) -> Generator: """Retrieve content data from the objstorage Args: contents: List of contents to retrieve data from """ for obj_id in contents: try: data = self.objstorage.get(obj_id) except ObjNotFoundError: yield None continue - yield {'sha1': obj_id, 'data': data} + yield {"sha1": obj_id, "data": 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 - }) + 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'] + "content:add": summary["object:add"], + "content:add:bytes": summary["object:add:bytes"], } diff --git a/swh/storage/retry.py b/swh/storage/retry.py index d8a3d438..cf1df075 100644 --- a/swh/storage/retry.py +++ b/swh/storage/retry.py @@ -1,151 +1,178 @@ # 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 datetime import datetime from typing import Dict, Iterable, List, Optional, Union from tenacity import ( - retry, stop_after_attempt, wait_random_exponential, + retry, + stop_after_attempt, + wait_random_exponential, ) from swh.model.model import ( - Content, SkippedContent, Directory, Revision, Release, Snapshot, - Origin, OriginVisit + Content, + SkippedContent, + Directory, + Revision, + Release, + Snapshot, + Origin, + OriginVisit, ) from swh.storage import get_storage from swh.storage.exc import StorageArgumentException 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) + module = getattr(error, "__module__", None) if module: - error_name = error.__module__ + '.' + error.__class__.__name__ + 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(), - }) + 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)) +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 = get_storage(**storage) def __getattr__(self, key): - if key == 'storage': + if key == "storage": raise AttributeError(key) return getattr(self.storage, key) @swh_retry def content_add(self, content: Iterable[Content]) -> Dict: return self.storage.content_add(content) @swh_retry def content_add_metadata(self, content: Iterable[Content]) -> Dict: return self.storage.content_add_metadata(content) @swh_retry def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: return self.storage.skipped_content_add(content) @swh_retry def origin_add_one(self, origin: Origin) -> str: return self.storage.origin_add_one(origin) @swh_retry - def origin_visit_add(self, origin_url: str, - date: Union[datetime, str], type: str) -> OriginVisit: + def origin_visit_add( + self, origin_url: str, date: Union[datetime, str], type: str + ) -> OriginVisit: return self.storage.origin_visit_add(origin_url, date, type) @swh_retry def origin_visit_update( - self, origin: str, visit_id: int, status: Optional[str] = None, - metadata: Optional[Dict] = None, - snapshot: Optional[Dict] = None) -> Dict: + self, + origin: str, + visit_id: int, + status: Optional[str] = None, + metadata: Optional[Dict] = None, + snapshot: Optional[Dict] = None, + ) -> Dict: return self.storage.origin_visit_update( - origin, visit_id, status=status, - metadata=metadata, snapshot=snapshot) + origin, visit_id, status=status, metadata=metadata, snapshot=snapshot + ) @swh_retry def tool_add(self, tools: Iterable[Dict]) -> List[Dict]: tools = list(tools) return self.storage.tool_add(tools) @swh_retry def metadata_provider_add( - self, provider_name: str, provider_type: str, provider_url: str, - metadata: Dict) -> Union[str, int]: + self, provider_name: str, provider_type: str, provider_url: str, metadata: Dict + ) -> Union[str, int]: return self.storage.metadata_provider_add( - provider_name, provider_type, provider_url, metadata) + provider_name, provider_type, provider_url, metadata + ) @swh_retry def origin_metadata_add( - self, origin_url: str, ts: Union[str, datetime], - provider_id: int, tool_id: int, metadata: Dict) -> None: + self, + origin_url: str, + ts: Union[str, datetime], + provider_id: int, + tool_id: int, + metadata: Dict, + ) -> None: return self.storage.origin_metadata_add( - origin_url, ts, provider_id, tool_id, metadata) + origin_url, ts, provider_id, tool_id, metadata + ) @swh_retry def directory_add(self, directories: Iterable[Directory]) -> Dict: return self.storage.directory_add(directories) @swh_retry def revision_add(self, revisions: Iterable[Revision]) -> Dict: return self.storage.revision_add(revisions) @swh_retry def release_add(self, releases: Iterable[Release]) -> Dict: return self.storage.release_add(releases) @swh_retry def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: return self.storage.snapshot_add(snapshots) @swh_retry def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: """Specific case for buffer proxy storage failing to flush data """ - if hasattr(self.storage, 'flush'): + if hasattr(self.storage, "flush"): return self.storage.flush(object_types) return {} diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 19a77c2c..e34ff153 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1157 +1,1217 @@ # 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 contextlib import datetime import itertools import json from collections import defaultdict from contextlib import contextmanager from typing import Any, Dict, Iterable, List, Optional, Union import attr import dateutil.parser import psycopg2 import psycopg2.pool import psycopg2.errors from swh.model.model import ( - Content, Directory, Origin, OriginVisit, - Revision, Release, SkippedContent, Snapshot, SHA1_SIZE + Content, + Directory, + Origin, + OriginVisit, + Revision, + Release, + SkippedContent, + Snapshot, + SHA1_SIZE, ) from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.storage.objstorage import ObjStorage from swh.storage.validate import VALIDATION_EXCEPTIONS from swh.storage.utils import now from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageArgumentException, StorageDBError, HashCollision from .algos import diff from .metrics import timed, send_metric, process_metrics -from .utils import ( - get_partition_bounds_bytes, extract_collision_hash -) +from .utils import get_partition_bounds_bytes, extract_collision_hash from .writer import JournalWriter # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 -EMPTY_SNAPSHOT_ID = hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e') +EMPTY_SNAPSHOT_ID = hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e") """Identifier for the empty snapshot""" VALIDATION_EXCEPTIONS = VALIDATION_EXCEPTIONS + [ 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(): +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): + 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, db=None, cur=None): if not self.objstorage.check_config(check_write=check_write): return False # Check permissions on one of the tables if check_write: - check = 'INSERT' + check = "INSERT" else: - check = 'SELECT' + check = "SELECT" - cur.execute( - "select has_table_privilege(current_user, 'content', %s)", - (check,) - ) + 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.mktemp("content", cur) - db.copy_to((c.to_dict() for c in content), 'tmp_content', - db.content_add_keys, 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': + 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 + 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', + "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_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: Iterable[Content]) -> Dict: + def content_add(self, content: Iterable[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, - )) + 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'], + "content:add": len(contents), + "content:add:bytes": objstorage_summary["content:add:bytes"], } @timed @db_transaction() def content_update(self, content, keys=[], db=None, cur=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(content) - db.mktemp('content', cur) + db.mktemp("content", cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) with convert_validation_exceptions(): - db.copy_to(content, 'tmp_content', select_keys, cur) - db.content_update_from_temp(keys_to_update=keys, - cur=cur) + db.copy_to(content, "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: Iterable[Content], - db=None, cur=None) -> Dict: + def content_add_metadata( + self, content: Iterable[Content], db=None, cur=None + ) -> Dict: contents = list(content) missing = self.content_missing( - (c.to_dict() for c in contents), key_hash='sha1_git', - db=db, cur=cur, + (c.to_dict() for c in 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_metadata(contents) self._content_add_metadata(db, cur, contents) return { - 'content:add': len(contents), + "content:add": len(contents), } @timed def content_get(self, content): # FIXME: Make this method support slicing the `data`. if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( - "Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) + "Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX + ) yield from self.objstorage.content_get(content) @timed @db_transaction() def content_get_range(self, start, end, limit=1000, db=None, cur=None): if limit is None: - raise StorageArgumentException('limit should not be None') + raise StorageArgumentException("limit should not be None") contents = [] next_content = None for counter, content_row in enumerate( - db.content_get_range(start, end, limit + 1, cur)): + db.content_get_range(start, end, limit + 1, cur) + ): content = dict(zip(db.content_get_metadata_keys, content_row)) if counter >= limit: # take the last commit for the next page starting from this - next_content = content['sha1'] + next_content = content["sha1"] break contents.append(content) return { - 'contents': contents, - 'next': next_content, + "contents": contents, + "next": next_content, } @timed def content_get_partition( - self, partition_id: int, nb_partitions: int, limit: int = 1000, - page_token: str = None): + self, + partition_id: int, + nb_partitions: int, + limit: int = 1000, + page_token: str = None, + ): if limit is None: - raise StorageArgumentException('limit should not be None') + raise StorageArgumentException("limit should not be None") (start, end) = get_partition_bounds_bytes( - partition_id, nb_partitions, SHA1_SIZE) + partition_id, nb_partitions, SHA1_SIZE + ) if page_token: start = hash_to_bytes(page_token) if end is None: - end = b'\xff' * SHA1_SIZE + end = b"\xff" * SHA1_SIZE result = self.content_get_range(start, end, limit) result2 = { - 'contents': result['contents'], - 'next_page_token': None, + "contents": result["contents"], + "next_page_token": None, } - if result['next']: - result2['next_page_token'] = hash_to_hex(result['next']) + if result["next"]: + result2["next_page_token"] = hash_to_hex(result["next"]) return result2 @timed @db_transaction(statement_timeout=500) def content_get_metadata( - self, contents: List[bytes], - db=None, cur=None) -> Dict[bytes, List[Dict]]: + self, contents: List[bytes], db=None, cur=None + ) -> Dict[bytes, List[Dict]]: result: Dict[bytes, List[Dict]] = {sha1: [] for sha1 in contents} for row in db.content_get_metadata_from_sha1s(contents, cur): content_meta = dict(zip(db.content_get_metadata_keys, row)) - result[content_meta['sha1']].append(content_meta) + result[content_meta["sha1"]].append(content_meta) return result @timed @db_transaction_generator() - def content_missing(self, content, key_hash='sha1', db=None, cur=None): + def content_missing(self, content, key_hash="sha1", db=None, cur=None): keys = db.content_hash_keys if key_hash not in keys: - raise StorageArgumentException( - "key_hash should be one of %s" % keys) + raise StorageArgumentException("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) if not content: return for obj in db.content_missing_from_list(content, cur): yield obj[key_hash_idx] @timed @db_transaction_generator() def content_missing_per_sha1(self, contents, db=None, cur=None): 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, db=None, cur=None): for obj in db.content_missing_per_sha1_git(contents, cur): yield obj[0] @timed @db_transaction() def content_find(self, content, db=None, cur=None): if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( - 'content keys must contain at least one of: ' - 'sha1, sha1_git, sha256, blake2s256') + "content keys must contain at least one of: " + "sha1, sha1_git, sha256, blake2s256" + ) - contents = db.content_find(sha1=content.get('sha1'), - sha1_git=content.get('sha1_git'), - sha256=content.get('sha256'), - blake2s256=content.get('blake2s256'), - cur=cur) - return [dict(zip(db.content_find_cols, content)) - for content in contents] + contents = db.content_find( + sha1=content.get("sha1"), + sha1_git=content.get("sha1_git"), + sha256=content.get("sha256"), + blake2s256=content.get("blake2s256"), + cur=cur, + ) + return [dict(zip(db.content_find_cols, content)) for content in contents] @timed @db_transaction() def content_get_random(self, db=None, cur=None): 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("status") is None: + d["status"] = "absent" - if d.get('length') is None: - d['length'] = -1 + if d.get("length") is None: + d["length"] = -1 return d @staticmethod def _skipped_content_validate(d): """Sanity checks on status / reason / length, that postgresql doesn't enforce.""" - if d['status'] != 'absent': + if d["status"] != "absent": raise StorageArgumentException( - 'Invalid content status: {}'.format(d['status'])) + "Invalid content status: {}".format(d["status"]) + ) - if d.get('reason') is None: + if d.get("reason") is None: raise StorageArgumentException( - 'Must provide a reason if content is absent.') + "Must provide a reason if content is absent." + ) - if d['length'] < -1: - raise StorageArgumentException( - 'Content length must be positive or -1.') - - def _skipped_content_add_metadata( - self, db, cur, content: Iterable[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) + if d["length"] < -1: + raise StorageArgumentException("Content length must be positive or -1.") + + def _skipped_content_add_metadata(self, db, cur, content: Iterable[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: Iterable[SkippedContent], - db=None, cur=None) -> Dict: + def skipped_content_add( + self, content: Iterable[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, + (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)] + 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), + "skipped_content:add": len(content), } @timed @db_transaction_generator() def skipped_content_missing(self, contents, db=None, cur=None): 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: Iterable[Directory], - db=None, cur=None) -> Dict: + def directory_add( + self, directories: Iterable[Directory], db=None, cur=None + ) -> Dict: directories = list(directories) - summary = {'directory:add': 0} + summary = {"directory:add": 0} dirs = set() dir_entries: Dict[str, defaultdict] = { - 'file': defaultdict(list), - 'dir': defaultdict(list), - 'rev': defaultdict(list), + "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) + 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 + 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) + 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) + 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'], + "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) + summary["directory:add"] = len(dirs_missing) return summary @timed @db_transaction_generator() def directory_missing(self, directories, db=None, cur=None): 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, recursive=False, db=None, cur=None): 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, paths, db=None, cur=None): res = db.directory_entry_get_by_path(directory, paths, cur) if res: return dict(zip(db.directory_ls_cols, res)) @timed @db_transaction() def directory_get_random(self, db=None, cur=None): return db.directory_get_random(cur) @timed @process_metrics @db_transaction() - def revision_add(self, revisions: Iterable[Revision], - db=None, cur=None) -> Dict: + def revision_add(self, revisions: Iterable[Revision], db=None, cur=None) -> Dict: revisions = list(revisions) - summary = {'revision:add': 0} + summary = {"revision:add": 0} - revisions_missing = set(self.revision_missing( - set(revision.id for revision in revisions), - db=db, cur=cur)) + 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] + revision for revision in revisions if revision.id in revisions_missing + ] self.journal_writer.revision_add(revisions_filtered) - revisions_filtered = \ - list(map(converters.revision_to_db, revisions_filtered)) + revisions_filtered = list(map(converters.revision_to_db, revisions_filtered)) parents_filtered: List[bytes] = [] with convert_validation_exceptions(): db.copy_to( - revisions_filtered, 'tmp_revision', db.revision_add_cols, + revisions_filtered, + "tmp_revision", + db.revision_add_cols, cur, - lambda rev: parents_filtered.extend(rev['parents'])) + 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) + db.copy_to( + parents_filtered, + "revision_history", + ["id", "parent_id", "parent_rank"], + cur, + ) - return {'revision:add': len(revisions_missing)} + return {"revision:add": len(revisions_missing)} @timed @db_transaction_generator() def revision_missing(self, revisions, db=None, cur=None): if not revisions: return for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @timed @db_transaction_generator(statement_timeout=1000) def revision_get(self, revisions, db=None, cur=None): for line in db.revision_get_from_list(revisions, cur): - data = converters.db_to_revision( - dict(zip(db.revision_get_cols, line)) - ) - if not data['type']: + data = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) + if not data["type"]: yield None continue yield data @timed @db_transaction_generator(statement_timeout=2000) def revision_log(self, revisions, limit=None, db=None, cur=None): for line in db.revision_log(revisions, limit, cur): - data = converters.db_to_revision( - dict(zip(db.revision_get_cols, line)) - ) - if not data['type']: + data = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) + if not data["type"]: yield None continue yield data @timed @db_transaction_generator(statement_timeout=2000) def revision_shortlog(self, revisions, limit=None, db=None, cur=None): yield from db.revision_shortlog(revisions, limit, cur) @timed @db_transaction() def revision_get_random(self, db=None, cur=None): return db.revision_get_random(cur) @timed @process_metrics @db_transaction() - def release_add( - self, releases: Iterable[Release], db=None, cur=None) -> Dict: + def release_add(self, releases: Iterable[Release], db=None, cur=None) -> Dict: releases = list(releases) - summary = {'release:add': 0} + 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)) + 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 + release for release in releases if release.id in releases_missing ] self.journal_writer.release_add(releases_filtered) - releases_filtered = \ - list(map(converters.release_to_db, releases_filtered)) + releases_filtered = list(map(converters.release_to_db, releases_filtered)) with convert_validation_exceptions(): - db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, - cur) + db.copy_to(releases_filtered, "tmp_release", db.release_add_cols, cur) db.release_add_from_temp(cur) - return {'release:add': len(releases_missing)} + return {"release:add": len(releases_missing)} @timed @db_transaction_generator() def release_missing(self, releases, db=None, cur=None): if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @timed @db_transaction_generator(statement_timeout=500) def release_get(self, releases, db=None, cur=None): for release in db.release_get_from_list(releases, cur): - data = converters.db_to_release( - dict(zip(db.release_get_cols, release)) - ) - yield data if data['target_type'] else None + data = converters.db_to_release(dict(zip(db.release_get_cols, release))) + yield data if data["target_type"] else None @timed @db_transaction() def release_get_random(self, db=None, cur=None): return db.release_get_random(cur) @timed @process_metrics @db_transaction() - def snapshot_add( - self, snapshots: Iterable[Snapshot], db=None, cur=None) -> Dict: + def snapshot_add(self, snapshots: Iterable[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), + "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'], + "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} + return {"snapshot:add": count} @timed @db_transaction_generator() def snapshot_missing(self, snapshots, db=None, cur=None): 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, db=None, cur=None): return self.snapshot_get_branches(snapshot_id, db=db, cur=cur) @timed @db_transaction(statement_timeout=2000) def snapshot_get_by_origin_visit(self, origin, visit, db=None, cur=None): snapshot_id = db.snapshot_get_by_origin_visit(origin, visit, cur) if snapshot_id: return self.snapshot_get(snapshot_id, db=db, cur=cur) return None @timed @db_transaction(statement_timeout=4000) - def snapshot_get_latest(self, origin, allowed_statuses=None, db=None, - cur=None): + def snapshot_get_latest(self, origin, allowed_statuses=None, db=None, cur=None): if isinstance(origin, int): - origin = self.origin_get({'id': origin}, db=db, cur=cur) + origin = self.origin_get({"id": origin}, db=db, cur=cur) if not origin: return - origin = origin['url'] + origin = origin["url"] origin_visit = self.origin_visit_get_latest( - origin, allowed_statuses=allowed_statuses, require_snapshot=True, - db=db, cur=cur) - if origin_visit and origin_visit['snapshot']: - snapshot = self.snapshot_get( - origin_visit['snapshot'], db=db, cur=cur) + origin, + allowed_statuses=allowed_statuses, + require_snapshot=True, + db=db, + cur=cur, + ) + if origin_visit and origin_visit["snapshot"]: + snapshot = self.snapshot_get(origin_visit["snapshot"], db=db, cur=cur) if not snapshot: raise StorageArgumentException( - 'last origin visit references an unknown snapshot') + "last origin visit references an unknown snapshot" + ) return snapshot @timed @db_transaction(statement_timeout=2000) def snapshot_count_branches(self, snapshot_id, db=None, cur=None): - return dict([bc for bc in - db.snapshot_count_branches(snapshot_id, cur)]) + 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, branches_from=b'', - branches_count=1000, target_types=None, - db=None, cur=None): + def snapshot_get_branches( + self, + snapshot_id, + branches_from=b"", + branches_count=1000, + target_types=None, + db=None, + cur=None, + ): if snapshot_id == EMPTY_SNAPSHOT_ID: return { - 'id': snapshot_id, - 'branches': {}, - 'next_branch': None, + "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, - )) + 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 branch in fetched_branches[:branches_count]: branch = dict(zip(db.snapshot_get_cols, branch)) - del branch['snapshot_id'] - name = branch.pop('name') - if branch == {'target': None, 'target_type': None}: + del branch["snapshot_id"] + name = branch.pop("name") + if branch == {"target": None, "target_type": None}: branch = None branches[name] = branch if len(fetched_branches) > branches_count: branch = dict(zip(db.snapshot_get_cols, fetched_branches[-1])) - next_branch = branch['name'] + next_branch = branch["name"] if branches: return { - 'id': snapshot_id, - 'branches': branches, - 'next_branch': next_branch, + "id": snapshot_id, + "branches": branches, + "next_branch": next_branch, } return None @timed @db_transaction() def snapshot_get_random(self, db=None, cur=None): return db.snapshot_get_random(cur) @timed @db_transaction() def origin_visit_add( - self, origin_url: str, date: Union[str, datetime.datetime], - type: str, db=None, cur=None) -> OriginVisit: + self, + origin_url: str, + date: Union[str, datetime.datetime], + type: str, + db=None, + cur=None, + ) -> OriginVisit: if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): - raise StorageArgumentException( - 'Date must be a datetime or a string') + raise StorageArgumentException("Date must be a datetime or a string") - origin = self.origin_get({'url': origin_url}, db=db, cur=cur) + origin = self.origin_get({"url": origin_url}, db=db, cur=cur) if not origin: # Cannot add a visit without an origin - raise StorageArgumentException( - 'Unknown origin %s', origin_url) + raise StorageArgumentException("Unknown origin %s", origin_url) with convert_validation_exceptions(): visit_id = db.origin_visit_add(origin_url, date, type, cur=cur) # We can write to the journal only after inserting to the # DB, because we want the id of the visit - visit = OriginVisit.from_dict({ - 'origin': origin_url, - 'date': date, - 'type': type, - 'visit': visit_id, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None - }) + visit = OriginVisit.from_dict( + { + "origin": origin_url, + "date": date, + "type": type, + "visit": visit_id, + "status": "ongoing", + "metadata": None, + "snapshot": None, + } + ) self.journal_writer.origin_visit_add(visit) - send_metric('origin_visit:add', count=1, method_name='origin_visit') + send_metric("origin_visit:add", count=1, method_name="origin_visit") return visit @timed @db_transaction() - def origin_visit_update(self, origin: str, visit_id: int, - status: str, - metadata: Optional[Dict] = None, - snapshot: Optional[bytes] = None, - date: Optional[datetime.datetime] = None, - db=None, cur=None): + def origin_visit_update( + self, + origin: str, + visit_id: int, + status: str, + metadata: Optional[Dict] = None, + snapshot: Optional[bytes] = None, + date: Optional[datetime.datetime] = None, + db=None, + cur=None, + ): if not isinstance(origin, str): raise StorageArgumentException( - 'origin must be a string, not %r' % (origin,)) + "origin must be a string, not %r" % (origin,) + ) origin_url = origin visit = db.origin_visit_get(origin_url, visit_id, cur=cur) if not visit: - raise StorageArgumentException('Invalid visit_id for this origin.') + raise StorageArgumentException("Invalid visit_id for this origin.") visit = dict(zip(db.origin_visit_get_cols, visit)) updates: Dict[str, Any] = { - 'status': status, + "status": status, } - if metadata and metadata != visit['metadata']: - updates['metadata'] = metadata - if snapshot and snapshot != visit['snapshot']: - updates['snapshot'] = snapshot + if metadata and metadata != visit["metadata"]: + updates["metadata"] = metadata + if snapshot and snapshot != visit["snapshot"]: + updates["snapshot"] = snapshot if updates: with convert_validation_exceptions(): updated_visit = OriginVisit.from_dict({**visit, **updates}) self.journal_writer.origin_visit_update(updated_visit) with convert_validation_exceptions(): db.origin_visit_update(origin_url, visit_id, updates, cur) @timed @db_transaction() - def origin_visit_upsert(self, visits: Iterable[OriginVisit], - db=None, cur=None) -> None: + def origin_visit_upsert( + self, visits: Iterable[OriginVisit], db=None, cur=None + ) -> None: for visit in visits: if visit.visit is None: - raise StorageArgumentException( - f'Missing visit id for visit {visit}') + raise StorageArgumentException(f"Missing visit id for visit {visit}") self.journal_writer.origin_visit_upsert(visits) for visit in visits: # TODO: upsert them all in a single query db.origin_visit_upsert(visit, cur=cur) @timed @db_transaction_generator(statement_timeout=500) def origin_visit_get( - self, origin: str, last_visit: Optional[int] = None, - limit: Optional[int] = None, - db=None, cur=None) -> Iterable[Dict[str, Any]]: + self, + origin: str, + last_visit: Optional[int] = None, + limit: Optional[int] = None, + db=None, + cur=None, + ) -> Iterable[Dict[str, Any]]: for line in db.origin_visit_get_all( - origin, last_visit=last_visit, limit=limit, cur=cur): + origin, last_visit=last_visit, limit=limit, cur=cur + ): data = dict(zip(db.origin_visit_get_cols, line)) yield data @timed @db_transaction(statement_timeout=500) def origin_visit_find_by_date( - self, origin: str, visit_date: datetime.datetime, - db=None, cur=None) -> Optional[Dict[str, Any]]: + self, origin: str, visit_date: datetime.datetime, db=None, cur=None + ) -> Optional[Dict[str, Any]]: line = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if line: return dict(zip(db.origin_visit_get_cols, line)) return None @timed @db_transaction(statement_timeout=500) def origin_visit_get_by( - self, origin: str, - visit: int, db=None, cur=None) -> Optional[Dict[str, Any]]: + self, origin: str, visit: int, db=None, cur=None + ) -> Optional[Dict[str, Any]]: ori_visit = db.origin_visit_get(origin, visit, cur) if not ori_visit: return None return dict(zip(db.origin_visit_get_cols, ori_visit)) @timed @db_transaction(statement_timeout=4000) def origin_visit_get_latest( - self, origin: str, allowed_statuses: Optional[List[str]] = None, - require_snapshot: bool = False, - db=None, cur=None) -> Optional[Dict[str, Any]]: + self, + origin: str, + allowed_statuses: Optional[List[str]] = None, + require_snapshot: bool = False, + db=None, + cur=None, + ) -> Optional[Dict[str, Any]]: origin_visit = db.origin_visit_get_latest( - origin, allowed_statuses=allowed_statuses, - require_snapshot=require_snapshot, cur=cur) + origin, + allowed_statuses=allowed_statuses, + require_snapshot=require_snapshot, + cur=cur, + ) if origin_visit: return dict(zip(db.origin_visit_get_cols, origin_visit)) return None @timed @db_transaction() def origin_visit_get_random( - self, type: str, db=None, cur=None) -> Optional[Dict[str, Any]]: + self, type: str, db=None, cur=None + ) -> Optional[Dict[str, Any]]: result = db.origin_visit_get_random(type, cur) if result: return dict(zip(db.origin_visit_get_cols, result)) else: return None @timed @db_transaction(statement_timeout=2000) def object_find_by_sha1_git(self, ids, db=None, cur=None): ret = {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))) + 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, db=None, cur=None): if isinstance(origins, dict): # Old API return_single = True origins = [origins] elif len(origins) == 0: return [] else: return_single = False - origin_urls = [origin['url'] for origin in origins] + origin_urls = [origin["url"] for origin in origins] results = db.origin_get_by_url(origin_urls, cur) - results = [dict(zip(db.origin_cols, result)) - for result in results] + results = [dict(zip(db.origin_cols, result)) for result in results] if return_single: assert len(results) == 1 - if results[0]['url'] is not None: + if results[0]["url"] is not None: return results[0] else: return None else: - return [None if res['url'] is None else res for res in results] + return [None if res["url"] is None else res for res in results] @timed @db_transaction_generator(statement_timeout=500) def origin_get_by_sha1(self, sha1s, db=None, cur=None): for line in db.origin_get_by_sha1(sha1s, cur): if line[0] is not None: yield dict(zip(db.origin_cols, line)) else: yield None @timed @db_transaction_generator() - def origin_get_range(self, origin_from=1, origin_count=100, - db=None, cur=None): + 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) -> dict: - page_token = page_token or '0' + def origin_list( + self, page_token: Optional[str] = None, limit: int = 100, *, db=None, cur=None + ) -> dict: + page_token = page_token or "0" if not isinstance(page_token, str): - raise StorageArgumentException('page_token must be a string.') + raise StorageArgumentException("page_token must be a string.") origin_from = int(page_token) result: Dict[str, Any] = { - 'origins': [ + "origins": [ dict(zip(db.origin_get_range_cols, origin)) for origin in db.origin_get_range(origin_from, limit, cur) ], } - assert len(result['origins']) <= limit - if len(result['origins']) == limit: - result['next_page_token'] = str(result['origins'][limit - 1]['id'] + 1) + assert len(result["origins"]) <= limit + if len(result["origins"]) == limit: + result["next_page_token"] = str(result["origins"][limit - 1]["id"] + 1) - for origin in result['origins']: - del origin['id'] + for origin in result["origins"]: + del origin["id"] return result @timed @db_transaction_generator() - def origin_search(self, url_pattern, offset=0, limit=50, - regexp=False, with_visit=False, db=None, cur=None): - for origin in db.origin_search(url_pattern, offset, limit, - regexp, with_visit, cur): + def origin_search( + self, + url_pattern, + offset=0, + limit=50, + regexp=False, + with_visit=False, + db=None, + cur=None, + ): + for origin in db.origin_search( + url_pattern, offset, limit, regexp, with_visit, cur + ): yield dict(zip(db.origin_cols, origin)) @timed @db_transaction() - def origin_count(self, url_pattern, regexp=False, - with_visit=False, db=None, cur=None): + def origin_count( + self, url_pattern, regexp=False, with_visit=False, db=None, cur=None + ): return db.origin_count(url_pattern, regexp, with_visit, cur) @timed @db_transaction() - def origin_add( - self, origins: Iterable[Origin], db=None, cur=None) -> List[Dict]: + def origin_add(self, origins: Iterable[Origin], db=None, cur=None) -> List[Dict]: origins = list(origins) for origin in origins: self.origin_add_one(origin, db=db, cur=cur) return [o.to_dict() for o in origins] @timed @db_transaction() def origin_add_one(self, origin: Origin, db=None, cur=None) -> str: origin_row = list(db.origin_get_by_url([origin.url], cur))[0] - origin_url = dict(zip(db.origin_cols, origin_row))['url'] + origin_url = dict(zip(db.origin_cols, origin_row))["url"] if origin_url: return origin_url self.journal_writer.origin_add_one(origin) url = db.origin_add(origin.url, cur) - send_metric('origin:add', count=1, method_name='origin_add_one') + send_metric("origin:add", count=1, method_name="origin_add_one") return url @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'] + "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,)) + cur.execute("select * from swh_update_counter(%s)", (key,)) @timed @db_transaction() - def origin_metadata_add(self, origin_url, ts, provider, tool, metadata, - db=None, cur=None): + def origin_metadata_add( + self, origin_url, ts, provider, tool, metadata, db=None, cur=None + ): if isinstance(ts, str): ts = dateutil.parser.parse(ts) - db.origin_metadata_add(origin_url, ts, provider, tool, - metadata, cur) - send_metric( - 'origin_metadata:add', count=1, method_name='origin_metadata_add') + db.origin_metadata_add(origin_url, ts, provider, tool, metadata, cur) + send_metric("origin_metadata:add", count=1, method_name="origin_metadata_add") @timed @db_transaction_generator(statement_timeout=500) - def origin_metadata_get_by(self, origin_url, provider_type=None, db=None, - cur=None): + def origin_metadata_get_by(self, origin_url, provider_type=None, db=None, cur=None): for line in db.origin_metadata_get_by(origin_url, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) @timed @db_transaction() def tool_add(self, tools, db=None, cur=None): db.mktemp_tool(cur) with convert_validation_exceptions(): - db.copy_to(tools, 'tmp_tool', - ['name', 'version', 'configuration'], - cur) + db.copy_to(tools, "tmp_tool", ["name", "version", "configuration"], cur) tools = db.tool_add_from_temp(cur) results = [dict(zip(db.tool_cols, line)) for line in tools] - send_metric('tool:add', count=len(results), method_name='tool_add') + send_metric("tool:add", count=len(results), method_name="tool_add") return results @timed @db_transaction(statement_timeout=500) def tool_get(self, tool, db=None, cur=None): - tool_conf = tool['configuration'] + tool_conf = tool["configuration"] if isinstance(tool_conf, dict): tool_conf = json.dumps(tool_conf) - idx = db.tool_get(tool['name'], - tool['version'], - tool_conf) + idx = db.tool_get(tool["name"], tool["version"], tool_conf) if not idx: return None return dict(zip(db.tool_cols, idx)) @timed @db_transaction() - def metadata_provider_add(self, provider_name, provider_type, provider_url, - metadata, db=None, cur=None): - result = db.metadata_provider_add(provider_name, provider_type, - provider_url, metadata, cur) - send_metric( - 'metadata_provider:add', count=1, method_name='metadata_provider') + def metadata_provider_add( + self, provider_name, provider_type, provider_url, metadata, db=None, cur=None + ): + result = db.metadata_provider_add( + provider_name, provider_type, provider_url, metadata, cur + ) + send_metric("metadata_provider:add", count=1, method_name="metadata_provider") return result @timed @db_transaction() def metadata_provider_get(self, provider_id, db=None, cur=None): result = db.metadata_provider_get(provider_id) if not result: return None return dict(zip(db.metadata_provider_cols, result)) @timed @db_transaction() def metadata_provider_get_by(self, provider, db=None, cur=None): - result = db.metadata_provider_get_by(provider['provider_name'], - provider['provider_url']) + result = db.metadata_provider_get_by( + provider["provider_name"], provider["provider_url"] + ) if not result: return None return dict(zip(db.metadata_provider_cols, result)) @timed def diff_directories(self, from_dir, to_dir, track_renaming=False): return diff.diff_directories(self, from_dir, to_dir, track_renaming) @timed def diff_revisions(self, from_rev, to_rev, track_renaming=False): return diff.diff_revisions(self, from_rev, to_rev, track_renaming) @timed def diff_revision(self, revision, track_renaming=False): return diff.diff_revision(self, revision, track_renaming) diff --git a/swh/storage/tests/__init__.py b/swh/storage/tests/__init__.py index 08a55a03..b5710627 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 -SQL_DIR = path.join(path.dirname(swh.storage.__file__), 'sql') +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 ecc9f107..8bbeae75 100644 --- a/swh/storage/tests/algos/test_diff.py +++ b/swh/storage/tests/algos/test_diff.py @@ -1,294 +1,374 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information # flake8: noqa import unittest from unittest.mock import patch 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 -@patch('swh.storage.algos.diff._get_rev') -@patch('swh.storage.algos.dir_iterators._get_dir') +@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): + 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']} + return {"directory": from_dir_model["target"]} else: - return {'directory': to_dir_model['target']} + 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) + 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' + 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' + 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"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) + "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') + 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 + 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"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) + "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' + 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') + 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}, + 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': '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": "delete", + "from": from_dir_model.get_path_data(b"file1"), + "from_path": b"file1", + "to": None, + "to_path": None, + }, { - '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) + "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' + 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') + 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 + 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": "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": "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) + "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' + rev_from = "898ff03e1e7925ecde3da66327d3cdc7e07625ba" + rev_to = "647c3d381e67490e82cdbbe6c96e46d5e1628ce2" from_dir_model = DirectoryModel() - from_dir_model.add_file(b'dir3/file1', 'ea15f54ca215e7920c60f564315ebb7f911a5204') + 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) + 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') + 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 - }] + to_dir_model.add_file(b"dir1/file1", "ea15f54ca215e7920c60f564315ebb7f911a5204") - self.diff_revisions(rev_from, rev_to, from_dir_model, - to_dir_model, expected_changes, - mock_get_dir, mock_get_rev) + 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' + 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') + 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' + 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"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) + "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_dir_iterator.py b/swh/storage/tests/algos/test_dir_iterator.py index 1590afdb..4b3c4488 100644 --- a/swh/storage/tests/algos/test_dir_iterator.py +++ b/swh/storage/tests/algos/test_dir_iterator.py @@ -1,146 +1,153 @@ - # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import unittest from unittest.mock import patch from swh.model.from_disk import DentryPerms from swh.model.hashutil import MultiHash, hash_to_bytes from swh.model.identifiers import directory_identifier from swh.storage.algos.dir_iterators import dir_iterator # flake8: noqa + class DirectoryModel(object): """ Quick and dirty directory model to ease the writing of directory iterators and revision trees differential tests. """ - def __init__(self, name=''): + + def __init__(self, name=""): self.data = {} - self.data['name'] = name - self.data['perms'] = DentryPerms.directory - self.data['type'] = 'dir' - self.data['entries'] = [] - self.data['entry_idx'] = {} + self.data["name"] = name + self.data["perms"] = DentryPerms.directory + self.data["type"] = "dir" + self.data["entries"] = [] + self.data["entry_idx"] = {} def __getitem__(self, item): - if item == 'target': + if item == "target": return hash_to_bytes(directory_identifier(self)) else: return self.data[item] def add_file(self, path, sha1=None): - path_parts = path.split(b'/') - sha1 = hash_to_bytes(sha1) if sha1 \ - else MultiHash.from_data(path).digest()['sha1'] + path_parts = path.split(b"/") + sha1 = ( + hash_to_bytes(sha1) if sha1 else MultiHash.from_data(path).digest()["sha1"] + ) if len(path_parts) == 1: - self['entry_idx'][path] = len(self['entries']) - self['entries'].append({ - 'target': sha1, - 'name': path, - 'perms': DentryPerms.content, - 'type': 'file' - }) + self["entry_idx"][path] = len(self["entries"]) + self["entries"].append( + { + "target": sha1, + "name": path, + "perms": DentryPerms.content, + "type": "file", + } + ) else: - if not path_parts[0] in self['entry_idx']: - self['entry_idx'][path_parts[0]] = len(self['entries']) - self['entries'].append(DirectoryModel(path_parts[0])) + if not path_parts[0] in self["entry_idx"]: + self["entry_idx"][path_parts[0]] = len(self["entries"]) + self["entries"].append(DirectoryModel(path_parts[0])) if path_parts[1]: - dir_idx = self['entry_idx'][path_parts[0]] - self['entries'][dir_idx].add_file(b'/'.join(path_parts[1:]), sha1) + dir_idx = self["entry_idx"][path_parts[0]] + self["entries"][dir_idx].add_file(b"/".join(path_parts[1:]), sha1) def get_hash_data(self, entry_hash): - if self['target'] == entry_hash: + if self["target"] == entry_hash: ret = [] - for e in self['entries']: - ret.append({ - 'target': e['target'], - 'name': e['name'], - 'perms': e['perms'], - 'type': e['type'] - }) + for e in self["entries"]: + ret.append( + { + "target": e["target"], + "name": e["name"], + "perms": e["perms"], + "type": e["type"], + } + ) return ret else: - for e in self['entries']: - if e['type'] == 'file' and e['target'] == entry_hash: + for e in self["entries"]: + if e["type"] == "file" and e["target"] == entry_hash: return e - elif e['type'] == 'dir': + elif e["type"] == "dir": data = e.get_hash_data(entry_hash) if data: return data return None def get_path_data(self, path): - path_parts = path.split(b'/') - entry_idx = self['entry_idx'][path_parts[0]] - entry = self['entries'][entry_idx] + path_parts = path.split(b"/") + entry_idx = self["entry_idx"][path_parts[0]] + entry = self["entries"][entry_idx] if len(path_parts) == 1: return { - 'target': entry['target'], - 'name': entry['name'], - 'perms': entry['perms'], - 'type': entry['type'] + "target": entry["target"], + "name": entry["name"], + "perms": entry["perms"], + "type": entry["type"], } else: - return entry.get_path_data(b'/'.join(path_parts[1:])) + return entry.get_path_data(b"/".join(path_parts[1:])) -@patch('swh.storage.algos.dir_iterators._get_dir') +@patch("swh.storage.algos.dir_iterators._get_dir") class TestDirectoryIterator(unittest.TestCase): - - def check_iterated_paths(self, dir_model, expected_paths_order, - mock_get_dir): - + def check_iterated_paths(self, dir_model, expected_paths_order, mock_get_dir): def _get_dir(*args, **kwargs): return dir_model.get_hash_data(args[1]) - mock_get_dir.side_effect = _get_dir # noqa - paths_order = [e['path'] for e in dir_iterator(None, dir_model['target'])] + mock_get_dir.side_effect = _get_dir # noqa + paths_order = [e["path"] for e in dir_iterator(None, dir_model["target"])] self.assertEqual(paths_order, expected_paths_order) def test_dir_iterator_empty_dir(self, mock_get_dir): dir_model = DirectoryModel() expected_paths_order = [] self.check_iterated_paths(dir_model, expected_paths_order, mock_get_dir) def test_dir_iterator_no_empty_dirs(self, mock_get_dir): dir_model = DirectoryModel() - dir_model.add_file(b'xyz/gtr/uhb') - dir_model.add_file(b'bca/ef') - dir_model.add_file(b'abc/ab') - dir_model.add_file(b'abc/bc') - dir_model.add_file(b'xyz/ouy/poi') - - expected_paths_order = [b'abc', - b'abc/ab', - b'abc/bc', - b'bca', - b'bca/ef', - b'xyz', - b'xyz/gtr', - b'xyz/gtr/uhb', - b'xyz/ouy', - b'xyz/ouy/poi'] + dir_model.add_file(b"xyz/gtr/uhb") + dir_model.add_file(b"bca/ef") + dir_model.add_file(b"abc/ab") + dir_model.add_file(b"abc/bc") + dir_model.add_file(b"xyz/ouy/poi") + + expected_paths_order = [ + b"abc", + b"abc/ab", + b"abc/bc", + b"bca", + b"bca/ef", + b"xyz", + b"xyz/gtr", + b"xyz/gtr/uhb", + b"xyz/ouy", + b"xyz/ouy/poi", + ] self.check_iterated_paths(dir_model, expected_paths_order, mock_get_dir) def test_dir_iterator_with_empty_dirs(self, mock_get_dir): dir_model = DirectoryModel() - dir_model.add_file(b'xyz/gtr/') - dir_model.add_file(b'bca/ef') - dir_model.add_file(b'abc/') - dir_model.add_file(b'xyz/ouy/poi') - - expected_paths_order = [b'abc', - b'bca', - b'bca/ef', - b'xyz', - b'xyz/gtr', - b'xyz/ouy', - b'xyz/ouy/poi'] + dir_model.add_file(b"xyz/gtr/") + dir_model.add_file(b"bca/ef") + dir_model.add_file(b"abc/") + dir_model.add_file(b"xyz/ouy/poi") + + expected_paths_order = [ + b"abc", + b"bca", + b"bca/ef", + b"xyz", + b"xyz/gtr", + b"xyz/ouy", + b"xyz/ouy/poi", + ] self.check_iterated_paths(dir_model, expected_paths_order, mock_get_dir) diff --git a/swh/storage/tests/algos/test_origin.py b/swh/storage/tests/algos/test_origin.py index e0e5fdde..5445477d 100644 --- a/swh/storage/tests/algos/test_origin.py +++ b/swh/storage/tests/algos/test_origin.py @@ -1,82 +1,66 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from unittest.mock import patch from swh.storage import get_storage from swh.storage.algos.origin import iter_origins def assert_list_eq(left, right, msg=None): assert list(left) == list(right), msg -storage_config = { - 'cls': 'validate', - 'storage': { - 'cls': 'memory', - } -} +storage_config = {"cls": "validate", "storage": {"cls": "memory",}} def test_iter_origins(): storage = get_storage(**storage_config) - origins = storage.origin_add([ - {'url': 'bar'}, - {'url': 'qux'}, - {'url': 'quuz'}, - ]) + origins = storage.origin_add([{"url": "bar"}, {"url": "qux"}, {"url": "quuz"},]) assert_list_eq(iter_origins(storage), origins) assert_list_eq(iter_origins(storage, batch_size=1), origins) assert_list_eq(iter_origins(storage, batch_size=2), origins) for i in range(1, 5): - assert_list_eq( - iter_origins(storage, origin_from=i+1), - origins[i:], - i) + assert_list_eq(iter_origins(storage, origin_from=i + 1), origins[i:], i) assert_list_eq( - iter_origins(storage, origin_from=i+1, batch_size=1), - origins[i:], - i) + iter_origins(storage, origin_from=i + 1, batch_size=1), origins[i:], i + ) assert_list_eq( - iter_origins(storage, origin_from=i+1, batch_size=2), - origins[i:], - i) + iter_origins(storage, origin_from=i + 1, batch_size=2), origins[i:], i + ) for j in range(i, 5): assert_list_eq( - iter_origins( - storage, origin_from=i+1, origin_to=j+1), + iter_origins(storage, origin_from=i + 1, origin_to=j + 1), origins[i:j], - (i, j)) + (i, j), + ) assert_list_eq( - iter_origins( - storage, origin_from=i+1, origin_to=j+1, batch_size=1), + iter_origins(storage, origin_from=i + 1, origin_to=j + 1, batch_size=1), origins[i:j], - (i, j)) + (i, j), + ) assert_list_eq( - iter_origins( - storage, origin_from=i+1, origin_to=j+1, batch_size=2), + iter_origins(storage, origin_from=i + 1, origin_to=j + 1, batch_size=2), origins[i:j], - (i, j)) + (i, j), + ) -@patch('swh.storage.in_memory.InMemoryStorage.origin_get_range') +@patch("swh.storage.in_memory.InMemoryStorage.origin_get_range") def test_iter_origins_batch_size(mock_origin_get_range): storage = get_storage(**storage_config) mock_origin_get_range.return_value = [] list(iter_origins(storage)) - mock_origin_get_range.assert_called_with( - origin_from=1, origin_count=10000) + mock_origin_get_range.assert_called_with(origin_from=1, origin_count=10000) list(iter_origins(storage, batch_size=42)) - mock_origin_get_range.assert_called_with( - origin_from=1, origin_count=42) + mock_origin_get_range.assert_called_with(origin_from=1, origin_count=42) diff --git a/swh/storage/tests/algos/test_revisions_walker.py b/swh/storage/tests/algos/test_revisions_walker.py index 3468131d..edd20780 100644 --- a/swh/storage/tests/algos/test_revisions_walker.py +++ b/swh/storage/tests/algos/test_revisions_walker.py @@ -1,403 +1,511 @@ # 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' +_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.storage.Storage') as MockStorage: + def check_revisions_ordering( + self, rev_walker_type, expected_result, truncated_history + ): + with patch("swh.storage.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 + 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)) + 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( + list(map(hash_to_bytes, expected_result)), + [rev["id"] for rev in revs_walker], + ) - self.assertEqual(revs_walker.is_history_truncated(), - truncated_history) + 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) + 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) + 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) + 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) + 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'] + expected_result = [ + "b364f53155044e5308a0f73abb3b5f01995a5b7d", + "b94886c500c46e32dc3d7ebae8a5409accd592e5", + "0cb6b4611d65bee0f57821dac7f611e2f8a02433", + "2b0240c6d682bad51532eec15b8a7ed6b75c8d31", + "b401c50863475db4440c85c10ac0b6423b61554d", + "9c5051397e5c2e0c258bb639c3dd34406584ca10", + ] - for revs_walker_type in ('committer_date', 'bfs', 'dfs', 'dfs_post'): + for revs_walker_type in ("committer_date", "bfs", "dfs", "dfs_post"): - self.check_revisions_ordering(revs_walker_type, expected_result, - truncated_history=True) + 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 15107c73..912fb4c2 100644 --- a/swh/storage/tests/algos/test_snapshot.py +++ b/swh/storage/tests/algos/test_snapshot.py @@ -1,43 +1,36 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from hypothesis import given from swh.model.identifiers import snapshot_identifier, identifier_to_bytes -from swh.model.hypothesis_strategies import \ - snapshots, branch_names, branch_targets +from swh.model.hypothesis_strategies import snapshots, branch_names, branch_targets from swh.storage.algos.snapshot import snapshot_get_all_branches from swh.storage.tests.test_in_memory import swh_storage_backend_config # noqa @given(snapshot=snapshots(min_size=0, max_size=10, only_objects=False)) def test_snapshot_small(swh_storage, snapshot): # noqa snapshot = snapshot.to_dict() swh_storage.snapshot_add([snapshot]) - returned_snapshot = snapshot_get_all_branches( - swh_storage, snapshot['id']) + 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)) +@given(branch_name=branch_names(), branch_target=branch_targets(only_objects=True)) def test_snapshot_large(swh_storage, branch_name, branch_target): # noqa branch_target = branch_target.to_dict() snapshot = { - 'branches': { - b'%s%05d' % (branch_name, i): branch_target - for i in range(10000) - } + "branches": {b"%s%05d" % (branch_name, i): branch_target for i in range(10000)} } - snapshot['id'] = identifier_to_bytes(snapshot_identifier(snapshot)) + snapshot["id"] = identifier_to_bytes(snapshot_identifier(snapshot)) swh_storage.snapshot_add([snapshot]) - returned_snapshot = snapshot_get_all_branches( - swh_storage, snapshot['id']) + returned_snapshot = snapshot_get_all_branches(swh_storage, snapshot["id"]) assert snapshot == returned_snapshot diff --git a/swh/storage/tests/conftest.py b/swh/storage/tests/conftest.py index 5449d01d..7334b457 100644 --- a/swh/storage/tests/conftest.py +++ b/swh/storage/tests/conftest.py @@ -1,243 +1,235 @@ # 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 glob import pytest from typing import Union from pytest_postgresql import factories from pytest_postgresql.janitor import DatabaseJanitor, psycopg2, Version from os import path, environ from hypothesis import settings from typing import Dict import swh.storage from swh.core.utils import numfile_sortkey as sortkey from swh.model.tests.generate_testdata import gen_contents, gen_origins -SQL_DIR = path.join(path.dirname(swh.storage.__file__), 'sql') +SQL_DIR = path.join(path.dirname(swh.storage.__file__), "sql") -environ['LC_ALL'] = 'C.UTF-8' +environ["LC_ALL"] = "C.UTF-8" -DUMP_FILES = path.join(SQL_DIR, '*.sql') +DUMP_FILES = path.join(SQL_DIR, "*.sql") # 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) @pytest.fixture def swh_storage_backend_config(postgresql_proc, swh_storage_postgresql): yield { - 'cls': 'local', - 'db': 'postgresql://{user}@{host}:{port}/{dbname}'.format( + "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': {} - }, - 'journal_writer': { - 'cls': 'memory', - }, + user="postgres", + dbname="tests", + ), + "objstorage": {"cls": "memory", "args": {}}, + "journal_writer": {"cls": "memory",}, } @pytest.fixture def swh_storage(swh_storage_backend_config): - storage_config = { - 'cls': 'validate', - 'storage': swh_storage_backend_config - } + storage_config = {"cls": "validate", "storage": swh_storage_backend_config} storage = swh.storage.get_storage(**storage_config) return storage @pytest.fixture def swh_contents(swh_storage): contents = 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']) + 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): origins = gen_origins(n=100) swh_storage.origin_add(origins) return origins # 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.' - ) + 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'] + pg_db = db_name or config["dbname"] with SwhDatabaseJanitor( - pg_user, pg_host, pg_port, pg_db, proc_fixture.version, - dump_files=dump_files + 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 + options=pg_options, ) yield connection connection.close() return postgresql_factory -swh_storage_postgresql = postgresql_fact('postgresql_proc') +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 + 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) + 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, + 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() + 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, + 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',)) + "WHERE table_schema = %s", + ("public",), + ) tables = set(table for (table,) in cur.fetchall()) for table in tables: - cur.execute('truncate table %s cascade' % table) + cur.execute("truncate table %s cascade" % table) cur.execute( "SELECT sequence_name FROM information_schema.sequences " - "WHERE sequence_schema = %s", ('public',)) + "WHERE sequence_schema = %s", + ("public",), + ) seqs = set(seq for (seq,) in cur.fetchall()) for seq in seqs: - cur.execute('ALTER SEQUENCE %s RESTART;' % seq) + 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,)) + "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,)) + "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' + pid_column = "pid" with self.cursor() as cur: cur.execute( - 'UPDATE pg_database SET datallowconn=false ' - 'WHERE datname = %s;', (self.db_name,)) + "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,)) + "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() -> Dict: """Pre-defined sample storage object data to manipulate Returns: Dict of data (keys: content, directory, revision, release, person, origin) """ from .storage_data import data return { - 'content': [data.cont, data.cont2], - 'content_metadata': [data.cont3], - 'skipped_content': [data.skipped_cont, data.skipped_cont2], - 'person': [data.person], - 'directory': [data.dir2, data.dir], - 'revision': [data.revision, data.revision2, data.revision3], - 'release': [data.release, data.release2, data.release3], - 'snapshot': [data.snapshot], - 'origin': [data.origin, data.origin2], - 'tool': [data.metadata_tool], - 'provider': [data.provider], - 'origin_metadata': [data.origin_metadata, data.origin_metadata2], + "content": [data.cont, data.cont2], + "content_metadata": [data.cont3], + "skipped_content": [data.skipped_cont, data.skipped_cont2], + "person": [data.person], + "directory": [data.dir2, data.dir], + "revision": [data.revision, data.revision2, data.revision3], + "release": [data.release, data.release2, data.release3], + "snapshot": [data.snapshot], + "origin": [data.origin, data.origin2], + "tool": [data.metadata_tool], + "provider": [data.provider], + "origin_metadata": [data.origin_metadata, data.origin_metadata2], } diff --git a/swh/storage/tests/generate_data_test.py b/swh/storage/tests/generate_data_test.py index 8cea4ecf..32cb642e 100644 --- a/swh/storage/tests/generate_data_test.py +++ b/swh/storage/tests/generate_data_test.py @@ -1,49 +1,49 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information -from hypothesis.strategies import (binary, composite, sets) +from hypothesis.strategies import binary, composite, sets from swh.model.hashutil import MultiHash def gen_raw_content(): """Generate raw content binary. """ return binary(min_size=20, max_size=100) @composite def gen_contents(draw, *, min_size=0, max_size=100): """Generate valid and consistent content. Context: Test purposes Args: **draw**: Used by hypothesis to generate data **min_size** (int): Minimal number of elements to generate (default: 0) **max_size** (int): Maximal number of elements to generate (default: 100) Returns: [dict] representing contents. The list's size is between [min_size:max_size]. """ - raw_contents = draw(sets( - gen_raw_content(), - min_size=min_size, max_size=max_size)) + raw_contents = draw(sets(gen_raw_content(), min_size=min_size, max_size=max_size)) contents = [] for raw_content in raw_contents: - contents.append({ - 'data': raw_content, - 'length': len(raw_content), - 'status': 'visible', - **MultiHash.from_data(raw_content).digest() - }) + contents.append( + { + "data": raw_content, + "length": len(raw_content), + "status": "visible", + **MultiHash.from_data(raw_content).digest(), + } + ) return contents diff --git a/swh/storage/tests/storage_data.py b/swh/storage/tests/storage_data.py index 5785cad6..253db454 100644 --- a/swh/storage/tests/storage_data.py +++ b/swh/storage/tests/storage_data.py @@ -1,540 +1,481 @@ # 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 datetime from swh.model.hashutil import hash_to_bytes from swh.model import from_disk class StorageData: def __getattr__(self, key): try: v = globals()[key] except KeyError as e: raise AttributeError(e.args[0]) - if hasattr(v, 'copy'): + if hasattr(v, "copy"): return v.copy() return v data = StorageData() cont = { - 'data': b'42\n', - 'length': 3, - 'sha1': hash_to_bytes( - '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), - 'sha1_git': hash_to_bytes( - 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), - 'sha256': hash_to_bytes( - '673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a'), - 'blake2s256': hash_to_bytes( - 'd5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d'), - 'status': 'visible', + "data": b"42\n", + "length": 3, + "sha1": hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4689"), + "sha1_git": hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), + "sha256": hash_to_bytes( + "673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a" + ), + "blake2s256": hash_to_bytes( + "d5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d" + ), + "status": "visible", } cont2 = { - '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', + "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", } cont3 = { - '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': '2019-12-01', + "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": "2019-12-01", } contents = (cont, cont2, cont3) missing_cont = { - 'data': b'missing\n', - 'length': 8, - 'sha1': hash_to_bytes( - 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), - 'sha1_git': hash_to_bytes( - '33e45d56f88993aae6a0198013efa80716fd8919'), - 'sha256': hash_to_bytes( - '6bbd052ab054ef222c1c87be60cd191addedd24cc882d1f5f7f7be61dc61bb3a'), - 'blake2s256': hash_to_bytes( - '306856b8fd879edb7b6f1aeaaf8db9bbecc993cd7f776c333ac3a782fa5c6eba'), - 'status': 'absent', + "data": b"missing\n", + "length": 8, + "sha1": hash_to_bytes("f9c24e2abb82063a3ba2c44efd2d3c797f28ac90"), + "sha1_git": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8919"), + "sha256": hash_to_bytes( + "6bbd052ab054ef222c1c87be60cd191addedd24cc882d1f5f7f7be61dc61bb3a" + ), + "blake2s256": hash_to_bytes( + "306856b8fd879edb7b6f1aeaaf8db9bbecc993cd7f776c333ac3a782fa5c6eba" + ), + "status": "absent", } skipped_cont = { - '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', + "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_cont2 = { - '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', + "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", } dir = { - 'id': hash_to_bytes( - '340133423253310030f531e632a733ff37c3a930'), - 'entries': [ + "id": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), + "entries": [ { - 'name': b'foo', - 'type': 'file', - 'target': hash_to_bytes( # cont - 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), - 'perms': from_disk.DentryPerms.content, + "name": b"foo", + "type": "file", + "target": hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), # cont + "perms": from_disk.DentryPerms.content, }, { - 'name': b'bar\xc3', - 'type': 'dir', - 'target': b'12345678901234567890', - 'perms': from_disk.DentryPerms.directory, + "name": b"bar\xc3", + "type": "dir", + "target": b"12345678901234567890", + "perms": from_disk.DentryPerms.directory, }, ], } dir2 = { - 'id': hash_to_bytes( - '340133423253310030f531e632a733ff37c3a935'), - 'entries': [ + "id": hash_to_bytes("340133423253310030f531e632a733ff37c3a935"), + "entries": [ { - 'name': b'oof', - 'type': 'file', - 'target': hash_to_bytes( # cont2 - '36fade77193cb6d2bd826161a0979d64c28ab4fa'), - 'perms': from_disk.DentryPerms.content, + "name": b"oof", + "type": "file", + "target": hash_to_bytes( # cont2 + "36fade77193cb6d2bd826161a0979d64c28ab4fa" + ), + "perms": from_disk.DentryPerms.content, } ], } dir3 = { - 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'), - 'entries': [ + "id": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8921"), + "entries": [ { - 'name': b'foo', - 'type': 'file', - 'target': hash_to_bytes( # cont - 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), - 'perms': from_disk.DentryPerms.content, + "name": b"foo", + "type": "file", + "target": hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), # cont + "perms": from_disk.DentryPerms.content, }, { - 'name': b'subdir', - 'type': 'dir', - 'target': hash_to_bytes( # dir - '340133423253310030f531e632a733ff37c3a930'), - 'perms': from_disk.DentryPerms.directory, + "name": b"subdir", + "type": "dir", + "target": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), # dir + "perms": from_disk.DentryPerms.directory, }, { - 'name': b'hello', - 'type': 'file', - 'target': b'12345678901234567890', - 'perms': from_disk.DentryPerms.content, + "name": b"hello", + "type": "file", + "target": b"12345678901234567890", + "perms": from_disk.DentryPerms.content, }, ], } dir4 = { - 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8922'), - 'entries': [ + "id": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8922"), + "entries": [ { - 'name': b'subdir1', - 'type': 'dir', - 'target': hash_to_bytes( - '33e45d56f88993aae6a0198013efa80716fd8921'), # dir3 - 'perms': from_disk.DentryPerms.directory, + "name": b"subdir1", + "type": "dir", + "target": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8921"), # dir3 + "perms": from_disk.DentryPerms.directory, }, - ] + ], } dierctories = (dir, dir2, dir3, dir4) minus_offset = datetime.timezone(datetime.timedelta(minutes=-120)) plus_offset = datetime.timezone(datetime.timedelta(minutes=120)) revision = { - 'id': b'56789012345678901234', - 'message': b'hello', - 'author': { - 'name': b'Nicolas Dandrimont', - 'email': b'nicolas@example.com', - 'fullname': b'Nicolas Dandrimont ', + "id": b"56789012345678901234", + "message": b"hello", + "author": { + "name": b"Nicolas Dandrimont", + "email": b"nicolas@example.com", + "fullname": b"Nicolas Dandrimont ", }, - 'date': { - 'timestamp': { - 'seconds': 1234567890, - 'microseconds': 0}, - 'offset': 120, - 'negative_utc': False, + "date": { + "timestamp": {"seconds": 1234567890, "microseconds": 0}, + "offset": 120, + "negative_utc": False, }, - 'committer': { - 'name': b'St\xc3fano Zacchiroli', - 'email': b'stefano@example.com', - 'fullname': b'St\xc3fano Zacchiroli ' + "committer": { + "name": b"St\xc3fano Zacchiroli", + "email": b"stefano@example.com", + "fullname": b"St\xc3fano Zacchiroli ", }, - 'committer_date': { - 'timestamp': { - 'seconds': 1123456789, - 'microseconds': 0}, - 'offset': 0, - 'negative_utc': True, + "committer_date": { + "timestamp": {"seconds": 1123456789, "microseconds": 0}, + "offset": 0, + "negative_utc": True, }, - 'parents': [b'01234567890123456789', b'23434512345123456789'], - 'type': 'git', - 'directory': hash_to_bytes( # dir - '340133423253310030f531e632a733ff37c3a930'), - 'metadata': { - 'checksums': { - 'sha1': 'tarball-sha1', - 'sha256': 'tarball-sha256', - }, - 'signed-off-by': 'some-dude', - 'extra_headers': [ - ['gpgsig', b'test123'], - ['mergetags', [b'foo\\bar', b'\x22\xaf\x89\x80\x01\x00']], + "parents": [b"01234567890123456789", b"23434512345123456789"], + "type": "git", + "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), # dir + "metadata": { + "checksums": {"sha1": "tarball-sha1", "sha256": "tarball-sha256",}, + "signed-off-by": "some-dude", + "extra_headers": [ + ["gpgsig", b"test123"], + ["mergetags", [b"foo\\bar", b"\x22\xaf\x89\x80\x01\x00"]], ], }, - 'synthetic': True + "synthetic": True, } revision2 = { - 'id': b'87659012345678904321', - 'message': b'hello again', - 'author': { - 'name': b'Roberto Dicosmo', - 'email': b'roberto@example.com', - 'fullname': b'Roberto Dicosmo ', + "id": b"87659012345678904321", + "message": b"hello again", + "author": { + "name": b"Roberto Dicosmo", + "email": b"roberto@example.com", + "fullname": b"Roberto Dicosmo ", }, - 'date': { - 'timestamp': { - 'seconds': 1234567843, - 'microseconds': 220000, - }, - 'offset': -720, - 'negative_utc': False, + "date": { + "timestamp": {"seconds": 1234567843, "microseconds": 220000,}, + "offset": -720, + "negative_utc": False, }, - 'committer': { - 'name': b'tony', - 'email': b'ar@dumont.fr', - 'fullname': b'tony ', + "committer": { + "name": b"tony", + "email": b"ar@dumont.fr", + "fullname": b"tony ", }, - 'committer_date': { - 'timestamp': { - 'seconds': 1123456789, - 'microseconds': 0}, - 'offset': 0, - 'negative_utc': False, + "committer_date": { + "timestamp": {"seconds": 1123456789, "microseconds": 0}, + "offset": 0, + "negative_utc": False, }, - 'parents': [b'01234567890123456789'], - 'type': 'git', - 'directory': hash_to_bytes( # dir2 - '340133423253310030f531e632a733ff37c3a935'), - 'metadata': None, - 'synthetic': False + "parents": [b"01234567890123456789"], + "type": "git", + "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a935"), # dir2 + "metadata": None, + "synthetic": False, } revision3 = { - 'id': hash_to_bytes('7026b7c1a2af56521e951c01ed20f255fa054238'), - 'message': b'a simple revision with no parents this time', - 'author': { - 'name': b'Roberto Dicosmo', - 'email': b'roberto@example.com', - 'fullname': b'Roberto Dicosmo ', + "id": hash_to_bytes("7026b7c1a2af56521e951c01ed20f255fa054238"), + "message": b"a simple revision with no parents this time", + "author": { + "name": b"Roberto Dicosmo", + "email": b"roberto@example.com", + "fullname": b"Roberto Dicosmo ", }, - 'date': { - 'timestamp': { - 'seconds': 1234567843, - 'microseconds': 220000, - }, - 'offset': -720, - 'negative_utc': False, + "date": { + "timestamp": {"seconds": 1234567843, "microseconds": 220000,}, + "offset": -720, + "negative_utc": False, }, - 'committer': { - 'name': b'tony', - 'email': b'ar@dumont.fr', - 'fullname': b'tony ', + "committer": { + "name": b"tony", + "email": b"ar@dumont.fr", + "fullname": b"tony ", }, - 'committer_date': { - 'timestamp': { - 'seconds': 1127351742, - 'microseconds': 0}, - 'offset': 0, - 'negative_utc': False, + "committer_date": { + "timestamp": {"seconds": 1127351742, "microseconds": 0}, + "offset": 0, + "negative_utc": False, }, - 'parents': [], - 'type': 'git', - 'directory': hash_to_bytes( # dir2 - '340133423253310030f531e632a733ff37c3a935'), - 'metadata': None, - 'synthetic': True + "parents": [], + "type": "git", + "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a935"), # dir2 + "metadata": None, + "synthetic": True, } revision4 = { - 'id': hash_to_bytes('368a48fe15b7db2383775f97c6b247011b3f14f4'), - 'message': b'parent of self.revision2', - 'author': { - 'name': b'me', - 'email': b'me@soft.heri', - 'fullname': b'me ', + "id": hash_to_bytes("368a48fe15b7db2383775f97c6b247011b3f14f4"), + "message": b"parent of self.revision2", + "author": { + "name": b"me", + "email": b"me@soft.heri", + "fullname": b"me ", }, - 'date': { - 'timestamp': { - 'seconds': 1244567843, - 'microseconds': 220000, - }, - 'offset': -720, - 'negative_utc': False, + "date": { + "timestamp": {"seconds": 1244567843, "microseconds": 220000,}, + "offset": -720, + "negative_utc": False, }, - 'committer': { - 'name': b'committer-dude', - 'email': b'committer@dude.com', - 'fullname': b'committer-dude ', + "committer": { + "name": b"committer-dude", + "email": b"committer@dude.com", + "fullname": b"committer-dude ", }, - 'committer_date': { - 'timestamp': { - 'seconds': 1244567843, - 'microseconds': 220000, - }, - 'offset': -720, - 'negative_utc': False, + "committer_date": { + "timestamp": {"seconds": 1244567843, "microseconds": 220000,}, + "offset": -720, + "negative_utc": False, }, - 'parents': [hash_to_bytes( # revision3 - '7026b7c1a2af56521e951c01ed20f255fa054238')], - 'type': 'git', - 'directory': hash_to_bytes( # dir - '340133423253310030f531e632a733ff37c3a930'), - 'metadata': None, - 'synthetic': False + "parents": [hash_to_bytes("7026b7c1a2af56521e951c01ed20f255fa054238")], # revision3 + "type": "git", + "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), # dir + "metadata": None, + "synthetic": False, } revisions = (revision, revision2, revision3, revision4) origin = { - 'url': 'file:///dev/null', + "url": "file:///dev/null", } origin2 = { - 'url': 'file:///dev/zero', + "url": "file:///dev/zero", } origins = (origin, origin2) provider = { - 'name': 'hal', - 'type': 'deposit-client', - 'url': 'http:///hal/inria', - 'metadata': { - 'location': 'France' - } + "name": "hal", + "type": "deposit-client", + "url": "http:///hal/inria", + "metadata": {"location": "France"}, } metadata_tool = { - 'name': 'swh-deposit', - 'version': '0.0.1', - 'configuration': { - 'sword_version': '2' - } + "name": "swh-deposit", + "version": "0.0.1", + "configuration": {"sword_version": "2"}, } -date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, - tzinfo=datetime.timezone.utc) -type_visit1 = 'git' +date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) +type_visit1 = "git" -date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0, - tzinfo=datetime.timezone.utc) -type_visit2 = 'hg' +date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) +type_visit2 = "hg" -date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0, - tzinfo=datetime.timezone.utc) -type_visit3 = 'deb' +date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) +type_visit3 = "deb" release = { - 'id': b'87659012345678901234', - 'name': b'v0.0.1', - 'author': { - 'name': b'olasd', - 'email': b'nic@olasd.fr', - 'fullname': b'olasd ', + "id": b"87659012345678901234", + "name": b"v0.0.1", + "author": { + "name": b"olasd", + "email": b"nic@olasd.fr", + "fullname": b"olasd ", }, - 'date': { - 'timestamp': { - 'seconds': 1234567890, - 'microseconds': 0}, - 'offset': 42, - 'negative_utc': False, + "date": { + "timestamp": {"seconds": 1234567890, "microseconds": 0}, + "offset": 42, + "negative_utc": False, }, - 'target': b'43210987654321098765', - 'target_type': 'revision', - 'message': b'synthetic release', - 'synthetic': True, + "target": b"43210987654321098765", + "target_type": "revision", + "message": b"synthetic release", + "synthetic": True, } release2 = { - 'id': b'56789012348765901234', - 'name': b'v0.0.2', - 'author': { - 'name': b'tony', - 'email': b'ar@dumont.fr', - 'fullname': b'tony ', + "id": b"56789012348765901234", + "name": b"v0.0.2", + "author": { + "name": b"tony", + "email": b"ar@dumont.fr", + "fullname": b"tony ", }, - 'date': { - 'timestamp': { - 'seconds': 1634366813, - 'microseconds': 0}, - 'offset': -120, - 'negative_utc': False, + "date": { + "timestamp": {"seconds": 1634366813, "microseconds": 0}, + "offset": -120, + "negative_utc": False, }, - 'target': b'432109\xa9765432\xc309\x00765', - 'target_type': 'revision', - 'message': b'v0.0.2\nMisc performance improvements + bug fixes', - 'synthetic': False + "target": b"432109\xa9765432\xc309\x00765", + "target_type": "revision", + "message": b"v0.0.2\nMisc performance improvements + bug fixes", + "synthetic": False, } release3 = { - 'id': b'87659012345678904321', - 'name': b'v0.0.2', - 'author': { - 'name': b'tony', - 'email': b'tony@ardumont.fr', - 'fullname': b'tony ', + "id": b"87659012345678904321", + "name": b"v0.0.2", + "author": { + "name": b"tony", + "email": b"tony@ardumont.fr", + "fullname": b"tony ", }, - 'date': { - 'timestamp': { - 'seconds': 1634336813, - 'microseconds': 0}, - 'offset': 0, - 'negative_utc': False, + "date": { + "timestamp": {"seconds": 1634336813, "microseconds": 0}, + "offset": 0, + "negative_utc": False, }, - 'target': b'87659012345678904321', # revision2 - 'target_type': 'revision', - 'message': b'yet another synthetic release', - 'synthetic': True, + "target": b"87659012345678904321", # revision2 + "target_type": "revision", + "message": b"yet another synthetic release", + "synthetic": True, } releases = (release, release2, release3) snapshot = { - 'id': hash_to_bytes('2498dbf535f882bc7f9a18fb16c9ad27fda7bab7'), - 'branches': { - b'master': { - 'target': b'56789012345678901234', # revision - 'target_type': 'revision', + "id": hash_to_bytes("2498dbf535f882bc7f9a18fb16c9ad27fda7bab7"), + "branches": { + b"master": { + "target": b"56789012345678901234", # revision + "target_type": "revision", }, }, } empty_snapshot = { - 'id': hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), - 'branches': {}, + "id": hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), + "branches": {}, } complete_snapshot = { - 'id': hash_to_bytes('6e65b86363953b780d92b0a928f3e8fcdd10db36'), - 'branches': { - b'directory': { - 'target': hash_to_bytes( - '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'), - 'target_type': 'directory', + "id": hash_to_bytes("6e65b86363953b780d92b0a928f3e8fcdd10db36"), + "branches": { + b"directory": { + "target": hash_to_bytes("1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8"), + "target_type": "directory", }, - b'directory2': { - 'target': hash_to_bytes( - '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'), - 'target_type': 'directory', + b"directory2": { + "target": hash_to_bytes("1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8"), + "target_type": "directory", }, - b'content': { - 'target': hash_to_bytes( - 'fe95a46679d128ff167b7c55df5d02356c5a1ae1'), - 'target_type': 'content', + b"content": { + "target": hash_to_bytes("fe95a46679d128ff167b7c55df5d02356c5a1ae1"), + "target_type": "content", }, - b'alias': { - 'target': b'revision', - 'target_type': 'alias', + b"alias": {"target": b"revision", "target_type": "alias",}, + b"revision": { + "target": hash_to_bytes("aafb16d69fd30ff58afdd69036a26047f3aebdc6"), + "target_type": "revision", }, - b'revision': { - 'target': hash_to_bytes( - 'aafb16d69fd30ff58afdd69036a26047f3aebdc6'), - 'target_type': 'revision', + b"release": { + "target": hash_to_bytes("7045404f3d1c54e6473c71bbb716529fbad4be24"), + "target_type": "release", }, - b'release': { - 'target': hash_to_bytes( - '7045404f3d1c54e6473c71bbb716529fbad4be24'), - 'target_type': 'release', + b"snapshot": { + "target": hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), + "target_type": "snapshot", }, - b'snapshot': { - 'target': hash_to_bytes( - '1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), - 'target_type': 'snapshot', - }, - b'dangling': None, - } + b"dangling": None, + }, } origin_metadata = { - 'origin': origin, - 'discovery_date': datetime.datetime(2015, 1, 1, 23, 0, 0, - tzinfo=datetime.timezone.utc), - 'provider': provider, - 'tool': 'swh-deposit', - 'metadata': { - 'name': 'test_origin_metadata', - 'version': '0.0.1' - } - } + "origin": origin, + "discovery_date": datetime.datetime( + 2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc + ), + "provider": provider, + "tool": "swh-deposit", + "metadata": {"name": "test_origin_metadata", "version": "0.0.1"}, +} origin_metadata2 = { - 'origin': origin, - 'discovery_date': datetime.datetime(2017, 1, 1, 23, 0, 0, - tzinfo=datetime.timezone.utc), - 'provider': provider, - 'tool': 'swh-deposit', - 'metadata': { - 'name': 'test_origin_metadata', - 'version': '0.0.1' - } - } + "origin": origin, + "discovery_date": datetime.datetime( + 2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc + ), + "provider": provider, + "tool": "swh-deposit", + "metadata": {"name": "test_origin_metadata", "version": "0.0.1"}, +} person = { - 'name': b'John Doe', - 'email': b'john.doe@institute.org', - 'fullname': b'John Doe ' + "name": b"John Doe", + "email": b"john.doe@institute.org", + "fullname": b"John Doe ", } diff --git a/swh/storage/tests/test_api_client.py b/swh/storage/tests/test_api_client.py index eb42a538..0ed20588 100644 --- a/swh/storage/tests/test_api_client.py +++ b/swh/storage/tests/test_api_client.py @@ -1,77 +1,69 @@ # 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 unittest.mock import patch import pytest import swh.storage.api.server as server import swh.storage.storage from swh.storage import get_storage -from swh.storage.tests.test_storage import TestStorageGeneratedData # noqa +from swh.storage.tests.test_storage import TestStorageGeneratedData # noqa from swh.storage.tests.test_storage import TestStorage as _TestStorage # tests are executed using imported classes (TestStorage and # TestStorageGeneratedData) using overloaded swh_storage fixture # below @pytest.fixture def app_server(): storage_config = { - 'cls': 'memory', - 'journal_writer': { - 'cls': 'memory', - }, + "cls": "memory", + "journal_writer": {"cls": "memory",}, } server.storage = swh.storage.get_storage(**storage_config) 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': 'validate', - 'storage': { - 'cls': 'remote', - **kwargs, - } - } + storage_config = {"cls": "validate", "storage": {"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) + journal_writer = getattr(storage, "journal_writer", None) storage.journal_writer = app_server.storage.journal_writer yield storage storage.journal_writer = journal_writer class TestStorage(_TestStorage): def test_content_update(self, swh_storage, app_server): # TODO, journal_writer not supported swh_storage.journal_writer.journal = None - with patch.object(server.storage.journal_writer, 'journal', None): + with patch.object(server.storage.journal_writer, "journal", None): super().test_content_update(swh_storage) diff --git a/swh/storage/tests/test_api_client_dicts.py b/swh/storage/tests/test_api_client_dicts.py index e1fa80d1..d6c65fb1 100644 --- a/swh/storage/tests/test_api_client_dicts.py +++ b/swh/storage/tests/test_api_client_dicts.py @@ -1,73 +1,68 @@ # 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 unittest.mock import patch import pytest from swh.storage.api.client import RemoteStorage import swh.storage.api.server as server import swh.storage.storage -from swh.storage.tests.test_storage import TestStorageGeneratedData # noqa +from swh.storage.tests.test_storage import TestStorageGeneratedData # noqa from swh.storage.tests.test_storage import TestStorage as _TestStorage # tests are executed using imported classes (TestStorage and # TestStorageGeneratedData) using overloaded swh_storage fixture # below @pytest.fixture def app_server(): storage_config = { - 'cls': 'validate', - 'storage': { - 'cls': 'memory', - 'journal_writer': { - 'cls': 'memory', - }, - } + "cls": "validate", + "storage": {"cls": "memory", "journal_writer": {"cls": "memory",},}, } server.storage = swh.storage.get_storage(**storage_config) yield server @pytest.fixture def app(app_server): return app_server.app @pytest.fixture def swh_rpc_client_class(): return RemoteStorage @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) + journal_writer = getattr(storage, "journal_writer", None) storage.journal_writer = app_server.storage.journal_writer yield storage storage.journal_writer = journal_writer class TestStorage(_TestStorage): def test_content_update(self, swh_storage, app_server): # TODO, journal_writer not supported swh_storage.journal_writer.journal = None - with patch.object(server.storage.journal_writer, 'journal', None): + with patch.object(server.storage.journal_writer, "journal", None): super().test_content_update(swh_storage) - @pytest.mark.skip('non-applicable test') + @pytest.mark.skip("non-applicable test") def test_content_add_from_lazy_content(self): pass diff --git a/swh/storage/tests/test_buffer.py b/swh/storage/tests/test_buffer.py index aceab756..e8509951 100644 --- a/swh/storage/tests/test_buffer.py +++ b/swh/storage/tests/test_buffer.py @@ -1,415 +1,338 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from swh.storage import get_storage def get_storage_with_buffer_config(**buffer_config): storage_config = { - 'cls': 'pipeline', - 'steps': [ - {'cls': 'validate'}, - {'cls': 'buffer', **buffer_config}, - {'cls': 'memory'}, - ] + "cls": "pipeline", + "steps": [ + {"cls": "validate"}, + {"cls": "buffer", **buffer_config}, + {"cls": "memory"}, + ], } return get_storage(**storage_config) def test_buffering_proxy_storage_content_threshold_not_hit(sample_data): - contents = sample_data['content'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'content': 10, - } - ) + contents = sample_data["content"] + storage = get_storage_with_buffer_config(min_batch_size={"content": 10,}) s = storage.content_add([contents[0], contents[1]]) assert s == {} # contents have not been written to storage - missing_contents = storage.content_missing( - [contents[0], contents[1]]) - assert set(missing_contents) == set( - [contents[0]['sha1'], contents[1]['sha1']]) + missing_contents = storage.content_missing([contents[0], contents[1]]) + assert set(missing_contents) == set([contents[0]["sha1"], contents[1]["sha1"]]) s = storage.flush() assert s == { - 'content:add': 1 + 1, - 'content:add:bytes': contents[0]['length'] + contents[1]['length'], + "content:add": 1 + 1, + "content:add:bytes": contents[0]["length"] + contents[1]["length"], } - missing_contents = storage.content_missing( - [contents[0], contents[1]]) + missing_contents = storage.content_missing([contents[0], contents[1]]) assert list(missing_contents) == [] def test_buffering_proxy_storage_content_threshold_nb_hit(sample_data): - contents = sample_data['content'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'content': 1, - } - ) + contents = sample_data["content"] + storage = get_storage_with_buffer_config(min_batch_size={"content": 1,}) s = storage.content_add([contents[0]]) assert s == { - 'content:add': 1, - 'content:add:bytes': contents[0]['length'], + "content:add": 1, + "content:add:bytes": contents[0]["length"], } missing_contents = storage.content_missing([contents[0]]) assert list(missing_contents) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_content_deduplicate(sample_data): - contents = sample_data['content'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'content': 2, - } - ) + contents = sample_data["content"] + storage = get_storage_with_buffer_config(min_batch_size={"content": 2,}) s = storage.content_add([contents[0], contents[0]]) assert s == {} s = storage.content_add([contents[0]]) assert s == {} s = storage.content_add([contents[1]]) assert s == { - 'content:add': 1 + 1, - 'content:add:bytes': contents[0]['length'] + contents[1]['length'], + "content:add": 1 + 1, + "content:add:bytes": contents[0]["length"] + contents[1]["length"], } - missing_contents = storage.content_missing( - [contents[0], contents[1]]) + missing_contents = storage.content_missing([contents[0], contents[1]]) assert list(missing_contents) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_content_threshold_bytes_hit(sample_data): - contents = sample_data['content'] + contents = sample_data["content"] content_bytes_min_batch_size = 2 storage = get_storage_with_buffer_config( - min_batch_size={ - 'content': 10, - 'content_bytes': content_bytes_min_batch_size, - } + min_batch_size={"content": 10, "content_bytes": content_bytes_min_batch_size,} ) - assert contents[0]['length'] > content_bytes_min_batch_size + assert contents[0]["length"] > content_bytes_min_batch_size s = storage.content_add([contents[0]]) assert s == { - 'content:add': 1, - 'content:add:bytes': contents[0]['length'], + "content:add": 1, + "content:add:bytes": contents[0]["length"], } missing_contents = storage.content_missing([contents[0]]) assert list(missing_contents) == [] s = storage.flush() assert s == {} -def test_buffering_proxy_storage_skipped_content_threshold_not_hit( - sample_data): - contents = sample_data['skipped_content'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'skipped_content': 10, - } - ) +def test_buffering_proxy_storage_skipped_content_threshold_not_hit(sample_data): + contents = sample_data["skipped_content"] + storage = get_storage_with_buffer_config(min_batch_size={"skipped_content": 10,}) s = storage.skipped_content_add([contents[0], contents[1]]) assert s == {} # contents have not been written to storage - missing_contents = storage.skipped_content_missing( - [contents[0], contents[1]]) - assert {c['sha1'] for c in missing_contents} \ - == {c['sha1'] for c in contents} + missing_contents = storage.skipped_content_missing([contents[0], contents[1]]) + assert {c["sha1"] for c in missing_contents} == {c["sha1"] for c in contents} s = storage.flush() - assert s == { - 'skipped_content:add': 1 + 1 - } + assert s == {"skipped_content:add": 1 + 1} - missing_contents = storage.skipped_content_missing( - [contents[0], contents[1]]) + missing_contents = storage.skipped_content_missing([contents[0], contents[1]]) assert list(missing_contents) == [] def test_buffering_proxy_storage_skipped_content_threshold_nb_hit(sample_data): - contents = sample_data['skipped_content'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'skipped_content': 1, - } - ) + contents = sample_data["skipped_content"] + storage = get_storage_with_buffer_config(min_batch_size={"skipped_content": 1,}) s = storage.skipped_content_add([contents[0]]) - assert s == { - 'skipped_content:add': 1 - } + assert s == {"skipped_content:add": 1} missing_contents = storage.skipped_content_missing([contents[0]]) assert list(missing_contents) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_skipped_content_deduplicate(sample_data): - contents = sample_data['skipped_content'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'skipped_content': 2, - } - ) + contents = sample_data["skipped_content"] + storage = get_storage_with_buffer_config(min_batch_size={"skipped_content": 2,}) s = storage.skipped_content_add([contents[0], contents[0]]) assert s == {} s = storage.skipped_content_add([contents[0]]) assert s == {} s = storage.skipped_content_add([contents[1]]) assert s == { - 'skipped_content:add': 1 + 1, + "skipped_content:add": 1 + 1, } - missing_contents = storage.skipped_content_missing( - [contents[0], contents[1]]) + missing_contents = storage.skipped_content_missing([contents[0], contents[1]]) assert list(missing_contents) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_directory_threshold_not_hit(sample_data): - directories = sample_data['directory'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'directory': 10, - } - ) + directories = sample_data["directory"] + storage = get_storage_with_buffer_config(min_batch_size={"directory": 10,}) s = storage.directory_add([directories[0]]) assert s == {} - directory_id = directories[0]['id'] - missing_directories = storage.directory_missing( - [directory_id]) + directory_id = directories[0]["id"] + missing_directories = storage.directory_missing([directory_id]) assert list(missing_directories) == [directory_id] s = storage.flush() assert s == { - 'directory:add': 1, + "directory:add": 1, } - missing_directories = storage.directory_missing( - [directory_id]) + missing_directories = storage.directory_missing([directory_id]) assert list(missing_directories) == [] def test_buffering_proxy_storage_directory_threshold_hit(sample_data): - directories = sample_data['directory'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'directory': 1, - } - ) + directories = sample_data["directory"] + storage = get_storage_with_buffer_config(min_batch_size={"directory": 1,}) s = storage.directory_add([directories[0]]) assert s == { - 'directory:add': 1, + "directory:add": 1, } - missing_directories = storage.directory_missing( - [directories[0]['id']]) + missing_directories = storage.directory_missing([directories[0]["id"]]) assert list(missing_directories) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_directory_deduplicate(sample_data): - directories = sample_data['directory'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'directory': 2, - } - ) + directories = sample_data["directory"] + storage = get_storage_with_buffer_config(min_batch_size={"directory": 2,}) s = storage.directory_add([directories[0], directories[0]]) assert s == {} s = storage.directory_add([directories[0]]) assert s == {} s = storage.directory_add([directories[1]]) assert s == { - 'directory:add': 1 + 1, + "directory:add": 1 + 1, } missing_directories = storage.directory_missing( - [directories[0]['id'], directories[1]['id']]) + [directories[0]["id"], directories[1]["id"]] + ) assert list(missing_directories) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_revision_threshold_not_hit(sample_data): - revisions = sample_data['revision'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'revision': 10, - } - ) + revisions = sample_data["revision"] + storage = get_storage_with_buffer_config(min_batch_size={"revision": 10,}) s = storage.revision_add([revisions[0]]) assert s == {} - revision_id = revisions[0]['id'] - missing_revisions = storage.revision_missing( - [revision_id]) + revision_id = revisions[0]["id"] + missing_revisions = storage.revision_missing([revision_id]) assert list(missing_revisions) == [revision_id] s = storage.flush() assert s == { - 'revision:add': 1, + "revision:add": 1, } - missing_revisions = storage.revision_missing( - [revision_id]) + missing_revisions = storage.revision_missing([revision_id]) assert list(missing_revisions) == [] def test_buffering_proxy_storage_revision_threshold_hit(sample_data): - revisions = sample_data['revision'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'revision': 1, - } - ) + revisions = sample_data["revision"] + storage = get_storage_with_buffer_config(min_batch_size={"revision": 1,}) s = storage.revision_add([revisions[0]]) assert s == { - 'revision:add': 1, + "revision:add": 1, } - missing_revisions = storage.revision_missing( - [revisions[0]['id']]) + missing_revisions = storage.revision_missing([revisions[0]["id"]]) assert list(missing_revisions) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_revision_deduplicate(sample_data): - revisions = sample_data['revision'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'revision': 2, - } - ) + revisions = sample_data["revision"] + storage = get_storage_with_buffer_config(min_batch_size={"revision": 2,}) s = storage.revision_add([revisions[0], revisions[0]]) assert s == {} s = storage.revision_add([revisions[0]]) assert s == {} s = storage.revision_add([revisions[1]]) assert s == { - 'revision:add': 1 + 1, + "revision:add": 1 + 1, } missing_revisions = storage.revision_missing( - [revisions[0]['id'], revisions[1]['id']]) + [revisions[0]["id"], revisions[1]["id"]] + ) assert list(missing_revisions) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_release_threshold_not_hit(sample_data): - releases = sample_data['release'] + releases = sample_data["release"] threshold = 10 assert len(releases) < threshold storage = get_storage_with_buffer_config( - min_batch_size={ - 'release': threshold, # configuration set - } + min_batch_size={"release": threshold,} # configuration set ) s = storage.release_add(releases) assert s == {} - release_ids = [r['id'] for r in releases] + release_ids = [r["id"] for r in releases] missing_releases = storage.release_missing(release_ids) assert list(missing_releases) == release_ids s = storage.flush() assert s == { - 'release:add': len(releases), + "release:add": len(releases), } missing_releases = storage.release_missing(release_ids) assert list(missing_releases) == [] def test_buffering_proxy_storage_release_threshold_hit(sample_data): - releases = sample_data['release'] + releases = sample_data["release"] threshold = 2 assert len(releases) > threshold storage = get_storage_with_buffer_config( - min_batch_size={ - 'release': threshold, # configuration set - } + min_batch_size={"release": threshold,} # configuration set ) s = storage.release_add(releases) assert s == { - 'release:add': len(releases), + "release:add": len(releases), } - release_ids = [r['id'] for r in releases] + release_ids = [r["id"] for r in releases] missing_releases = storage.release_missing(release_ids) assert list(missing_releases) == [] s = storage.flush() assert s == {} def test_buffering_proxy_storage_release_deduplicate(sample_data): - releases = sample_data['release'] - storage = get_storage_with_buffer_config( - min_batch_size={ - 'release': 2, - } - ) + releases = sample_data["release"] + storage = get_storage_with_buffer_config(min_batch_size={"release": 2,}) s = storage.release_add([releases[0], releases[0]]) assert s == {} s = storage.release_add([releases[0]]) assert s == {} s = storage.release_add([releases[1]]) assert s == { - 'release:add': 1 + 1, + "release:add": 1 + 1, } - missing_releases = storage.release_missing( - [releases[0]['id'], releases[1]['id']]) + missing_releases = storage.release_missing([releases[0]["id"], releases[1]["id"]]) assert list(missing_releases) == [] s = storage.flush() assert s == {} diff --git a/swh/storage/tests/test_cassandra.py b/swh/storage/tests/test_cassandra.py index 963db083..cacdabaa 100644 --- a/swh/storage/tests/test_cassandra.py +++ b/swh/storage/tests/test_cassandra.py @@ -1,407 +1,415 @@ # 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 from collections import namedtuple import datetime import os import signal import socket import subprocess import time import pytest 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.tests.test_storage import TestStorage as _TestStorage -from swh.storage.tests.test_storage import TestStorageGeneratedData \ - as _TestStorageGeneratedData +from swh.storage.tests.test_storage import ( + TestStorageGeneratedData as _TestStorageGeneratedData, +) from .storage_data import data -CONFIG_TEMPLATE = ''' +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)) + 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') +@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') + 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, - )) + 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('LOG_CASSANDRA'): + if os.environ.get("LOG_CASSANDRA"): stdout = stderr = None else: stdout = stderr = subprocess.DEVNULL proc = subprocess.Popen( [ - '/usr/sbin/cassandra', - '-Dcassandra.config=file://%s/cassandra.yaml' % cassandra_conf, - '-Dcassandra.logdir=%s' % cassandra_log, - '-Dcassandra.jmx.local.port=%d' % jmx_port, - '-Dcassandra-foreground=yes', + "/usr/sbin/cassandra", + "-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, + "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) + running = wait_for_peer("127.0.0.1", native_transport_port) if running: - yield (['127.0.0.1'], native_transport_port) + yield (["127.0.0.1"], native_transport_port) - if not running or os.environ.get('LOG_CASSANDRA'): - with open(str(cassandra_log.join('debug.log'))) as fd: + if not running or os.environ.get("LOG_CASSANDRA"): + with open(str(cassandra_log.join("debug.log"))) as fd: print(fd.read()) if not running: - raise Exception('cassandra process stopped unexpectedly.') + 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'): + if hasattr(rf.message, "query"): print() print(rf.message.query) -@pytest.fixture(scope='session') +@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', + cls="cassandra", hosts=hosts, port=port, keyspace=keyspace, - journal_writer={ - 'cls': 'memory', - }, - objstorage={ - 'cls': 'memory', - 'args': {}, - }, + 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): """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 # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 - assert algo in ('sha1', 'sha1_git') + assert algo in ("sha1", "sha1_git") return [123456] + mocker.patch.object( swh_storage.storage._cql_runner, - 'content_get_tokens_from_single_hash', - mock_cgtfsh) + "content_get_tokens_from_single_hash", + mock_cgtfsh, + ) # For all tokens, always return data.cont - Row = namedtuple('Row', HASH_ALGORITHMS) + Row = namedtuple("Row", HASH_ALGORITHMS) def mock_cgft(token): nonlocal called called += 1 return [Row(**{algo: data.cont[algo] for algo in HASH_ALGORITHMS})] + mocker.patch.object( - swh_storage.storage._cql_runner, - 'content_get_from_token', - mock_cgft) + swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft + ) actual_result = swh_storage.content_add([data.cont2]) assert called == 4 assert actual_result == { - 'content:add': 1, - 'content:add:bytes': data.cont2['length'], - } + "content:add": 1, + "content:add:bytes": data.cont2["length"], + } def test_content_get_metadata_murmur3_collision(self, swh_storage, mocker): """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 # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 - assert algo in ('sha1', 'sha1_git') + assert algo in ("sha1", "sha1_git") return [123456] + mocker.patch.object( swh_storage.storage._cql_runner, - 'content_get_tokens_from_single_hash', - mock_cgtfsh) + "content_get_tokens_from_single_hash", + mock_cgtfsh, + ) # For all tokens, always return data.cont and data.cont2 - cols = list(set(data.cont) - {'data'}) - Row = namedtuple('Row', cols + ['ctime']) + cols = list(set(data.cont) - {"data"}) + Row = namedtuple("Row", cols + ["ctime"]) def mock_cgft(token): nonlocal called called += 1 - return [Row(ctime=42, **{col: cont[col] for col in cols}) - for cont in [data.cont, data.cont2]] + return [ + Row(ctime=42, **{col: cont[col] for col in cols}) + for cont in [data.cont, data.cont2] + ] + mocker.patch.object( - swh_storage.storage._cql_runner, - 'content_get_from_token', - mock_cgft) + swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft + ) expected_cont = data.cont.copy() - del expected_cont['data'] + del expected_cont["data"] - actual_result = swh_storage.content_get_metadata([data.cont['sha1']]) + actual_result = swh_storage.content_get_metadata([data.cont["sha1"]]) assert called == 2 # but data.cont2 should be filtered out - assert actual_result == { - data.cont['sha1']: [expected_cont] - } + assert actual_result == {data.cont["sha1"]: [expected_cont]} def test_content_find_murmur3_collision(self, swh_storage, mocker): """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 # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 - assert algo in ('sha1', 'sha1_git') + assert algo in ("sha1", "sha1_git") return [123456] + mocker.patch.object( swh_storage.storage._cql_runner, - 'content_get_tokens_from_single_hash', - mock_cgtfsh) + "content_get_tokens_from_single_hash", + mock_cgtfsh, + ) # For all tokens, always return data.cont and data.cont2 - cols = list(set(data.cont) - {'data'}) - Row = namedtuple('Row', cols + ['ctime']) + cols = list(set(data.cont) - {"data"}) + Row = namedtuple("Row", cols + ["ctime"]) def mock_cgft(token): nonlocal called called += 1 - return [Row(ctime=datetime.datetime.now(), - **{col: cont[col] for col in cols}) - for cont in [data.cont, data.cont2]] + return [ + Row(ctime=datetime.datetime.now(), **{col: cont[col] for col in cols}) + for cont in [data.cont, data.cont2] + ] + mocker.patch.object( - swh_storage.storage._cql_runner, - 'content_get_from_token', - mock_cgft) + swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft + ) expected_cont = data.cont.copy() - del expected_cont['data'] + del expected_cont["data"] - actual_result = swh_storage.content_find({'sha1': data.cont['sha1']}) + actual_result = swh_storage.content_find({"sha1": data.cont["sha1"]}) assert called == 2 # but data.cont2 should be filtered out - del actual_result[0]['ctime'] + del actual_result[0]["ctime"] assert actual_result == [expected_cont] - @pytest.mark.skip('content_update is not yet implemented for Cassandra') + @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.') + "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.') + "supported by the cassandra backend." + ) def test_person_get(self): pass - @pytest.mark.skip('Not yet implemented') + @pytest.mark.skip("Not yet implemented") def test_metadata_provider_add(self): pass - @pytest.mark.skip('Not yet implemented') + @pytest.mark.skip("Not yet implemented") def test_metadata_provider_get(self): pass - @pytest.mark.skip('Not yet implemented') + @pytest.mark.skip("Not yet implemented") def test_metadata_provider_get_by(self): pass - @pytest.mark.skip('Not yet implemented') + @pytest.mark.skip("Not yet implemented") def test_origin_metadata_add(self): pass - @pytest.mark.skip('Not yet implemented') + @pytest.mark.skip("Not yet implemented") def test_origin_metadata_get(self): pass - @pytest.mark.skip('Not yet implemented') + @pytest.mark.skip("Not yet implemented") def test_origin_metadata_get_by_provider_type(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @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') + @pytest.mark.skip("Not supported by Cassandra") def test_origin_count(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_origin_get_range(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_origin_get_range_from_zero(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_limit(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_no_limit(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_empty(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_limit_none(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_full(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @pytest.mark.skip("Not supported by Cassandra") def test_origin_count_with_visit_no_visits(self): pass - @pytest.mark.skip('Not supported by Cassandra') + @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') + @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 25594d63..d3319064 100644 --- a/swh/storage/tests/test_cassandra_converters.py +++ b/swh/storage/tests/test_cassandra_converters.py @@ -1,37 +1,38 @@ # 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 # Test purposes field_names: List[str] = list(DEFAULT_ALGORITHMS) -Row = namedtuple('Row', field_names) # type: ignore +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 + 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 Dict: return { - 'provider_name': provider['name'], - 'provider_url': provider['url'], - 'provider_type': provider['type'], - 'metadata': provider['metadata'], + "provider_name": provider["name"], + "provider_url": provider["url"], + "provider_type": provider["type"], + "metadata": provider["metadata"], } -def test_retrying_proxy_storage_metadata_provider_add( - swh_storage, sample_data): +def test_retrying_proxy_storage_metadata_provider_add(swh_storage, sample_data): """Standard metadata_provider_add works as before """ - provider = sample_data['provider'][0] + provider = sample_data["provider"][0] provider_get = to_provider(provider) provider = swh_storage.metadata_provider_get_by(provider_get) assert not provider provider_id = swh_storage.metadata_provider_add(**provider_get) assert provider_id actual_provider = swh_storage.metadata_provider_get(provider_id) assert actual_provider - actual_provider_id = actual_provider.pop('id') + actual_provider_id = actual_provider.pop("id") assert actual_provider_id == provider_id assert actual_provider == provider_get def test_retrying_proxy_storage_metadata_provider_add_with_retry( - swh_storage, sample_data, mocker, fake_hash_collision): + swh_storage, sample_data, mocker, fake_hash_collision +): """Multiple retries for hash collision and psycopg2 error but finally ok """ - provider = sample_data['provider'][0] + provider = sample_data["provider"][0] provider_get = to_provider(provider) mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.metadata_provider_add') + "swh.storage.in_memory.InMemoryStorage.metadata_provider_add" + ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko - psycopg2.IntegrityError('provider_id already inserted'), + psycopg2.IntegrityError("provider_id already inserted"), # ok then! - 'provider_id', + "provider_id", ] mock_sleep = mocker.patch( - 'swh.storage.retry.RetryingProxyStorage' - '.metadata_provider_add.retry.sleep') + "swh.storage.retry.RetryingProxyStorage" ".metadata_provider_add.retry.sleep" + ) provider = swh_storage.metadata_provider_get_by(provider_get) assert not provider provider_id = swh_storage.metadata_provider_add(**provider_get) - assert provider_id == 'provider_id' + assert provider_id == "provider_id" - provider_arg_names = ( - 'provider_name', 'provider_type', 'provider_url', 'metadata') + provider_arg_names = ("provider_name", "provider_type", "provider_url", "metadata") provider_args = [provider_get[key] for key in provider_arg_names] - mock_memory.assert_has_calls([ - call(*provider_args), - call(*provider_args), - call(*provider_args), - ]) + mock_memory.assert_has_calls( + [call(*provider_args), call(*provider_args), call(*provider_args),] + ) assert mock_sleep.call_count == 2 def test_retrying_proxy_swh_storage_metadata_provider_add_failure( - swh_storage, sample_data, mocker): + swh_storage, sample_data, mocker +): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.metadata_provider_add') + "swh.storage.in_memory.InMemoryStorage.metadata_provider_add" + ) mock_memory.side_effect = StorageArgumentException( - 'Refuse to add provider_id always!') + "Refuse to add provider_id always!" + ) - provider = sample_data['provider'][0] + provider = sample_data["provider"][0] provider_get = to_provider(provider) provider_id = swh_storage.metadata_provider_get_by(provider_get) assert not provider_id - with pytest.raises(StorageArgumentException, match='Refuse to add'): + with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.metadata_provider_add(**provider_get) assert mock_memory.call_count == 1 -def test_retrying_proxy_storage_origin_metadata_add( - swh_storage, sample_data): +def test_retrying_proxy_storage_origin_metadata_add(swh_storage, sample_data): """Standard origin_metadata_add works as before """ - ori_meta = sample_data['origin_metadata'][0] - origin = ori_meta['origin'] + ori_meta = sample_data["origin_metadata"][0] + origin = ori_meta["origin"] swh_storage.origin_add_one(origin) - provider_get = to_provider(ori_meta['provider']) + provider_get = to_provider(ori_meta["provider"]) provider_id = swh_storage.metadata_provider_add(**provider_get) - origin_metadata = swh_storage.origin_metadata_get_by(origin['url']) + origin_metadata = swh_storage.origin_metadata_get_by(origin["url"]) assert not origin_metadata swh_storage.origin_metadata_add( - origin['url'], ori_meta['discovery_date'], - provider_id, ori_meta['tool'], ori_meta['metadata']) - - origin_metadata = swh_storage.origin_metadata_get_by( - origin['url']) + origin["url"], + ori_meta["discovery_date"], + provider_id, + ori_meta["tool"], + ori_meta["metadata"], + ) + + origin_metadata = swh_storage.origin_metadata_get_by(origin["url"]) assert origin_metadata def test_retrying_proxy_storage_origin_metadata_add_with_retry( - swh_storage, sample_data, mocker, fake_hash_collision): + swh_storage, sample_data, mocker, fake_hash_collision +): """Multiple retries for hash collision and psycopg2 error but finally ok """ - ori_meta = sample_data['origin_metadata'][0] - origin = ori_meta['origin'] + ori_meta = sample_data["origin_metadata"][0] + origin = ori_meta["origin"] swh_storage.origin_add_one(origin) - provider_get = to_provider(ori_meta['provider']) + provider_get = to_provider(ori_meta["provider"]) provider_id = swh_storage.metadata_provider_add(**provider_get) mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.origin_metadata_add') + "swh.storage.in_memory.InMemoryStorage.origin_metadata_add" + ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko - psycopg2.IntegrityError('provider_id already inserted'), + psycopg2.IntegrityError("provider_id already inserted"), # ok then! - None + None, ] mock_sleep = mocker.patch( - 'swh.storage.retry.RetryingProxyStorage' - '.origin_metadata_add.retry.sleep') + "swh.storage.retry.RetryingProxyStorage" ".origin_metadata_add.retry.sleep" + ) - url = origin['url'] - ts = ori_meta['discovery_date'] - tool_id = ori_meta['tool'] - metadata = ori_meta['metadata'] + url = origin["url"] + ts = ori_meta["discovery_date"] + tool_id = ori_meta["tool"] + metadata = ori_meta["metadata"] # No exception raised as insertion finally came through swh_storage.origin_metadata_add(url, ts, provider_id, tool_id, metadata) - mock_memory.assert_has_calls([ # 3 calls, as long as error raised - call(url, ts, provider_id, tool_id, metadata), - call(url, ts, provider_id, tool_id, metadata), - call(url, ts, provider_id, tool_id, metadata) - ]) + mock_memory.assert_has_calls( + [ # 3 calls, as long as error raised + call(url, ts, provider_id, tool_id, metadata), + call(url, ts, provider_id, tool_id, metadata), + call(url, ts, provider_id, tool_id, metadata), + ] + ) assert mock_sleep.call_count == 2 def test_retrying_proxy_swh_storage_origin_metadata_add_failure( - swh_storage, sample_data, mocker): + swh_storage, sample_data, mocker +): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.origin_metadata_add') - mock_memory.side_effect = StorageArgumentException( - 'Refuse to add always!') + "swh.storage.in_memory.InMemoryStorage.origin_metadata_add" + ) + mock_memory.side_effect = StorageArgumentException("Refuse to add always!") - ori_meta = sample_data['origin_metadata'][0] - origin = ori_meta['origin'] + ori_meta = sample_data["origin_metadata"][0] + origin = ori_meta["origin"] swh_storage.origin_add_one(origin) - url = origin['url'] - ts = ori_meta['discovery_date'] - provider_id = 'provider_id' - tool_id = ori_meta['tool'] - metadata = ori_meta['metadata'] + url = origin["url"] + ts = ori_meta["discovery_date"] + provider_id = "provider_id" + tool_id = ori_meta["tool"] + metadata = ori_meta["metadata"] - with pytest.raises(StorageArgumentException, match='Refuse to add'): - swh_storage.origin_metadata_add(url, ts, provider_id, tool_id, - metadata) + with pytest.raises(StorageArgumentException, match="Refuse to add"): + swh_storage.origin_metadata_add(url, ts, provider_id, tool_id, metadata) assert mock_memory.call_count == 1 -def test_retrying_proxy_swh_storage_origin_visit_update( - swh_storage, sample_data): +def test_retrying_proxy_swh_storage_origin_visit_update(swh_storage, sample_data): """Standard origin_visit_update works as before """ - sample_origin = sample_data['origin'][0] + sample_origin = sample_data["origin"][0] origin_url = swh_storage.origin_add_one(sample_origin) - origin_visit = swh_storage.origin_visit_add(origin_url, date_visit1, 'hg') + origin_visit = swh_storage.origin_visit_add(origin_url, date_visit1, "hg") ov = next(swh_storage.origin_visit_get(origin_url)) - assert ov['origin'] == origin_url - assert ov['visit'] == origin_visit.visit - assert ov['status'] == 'ongoing' - assert ov['snapshot'] is None - assert ov['metadata'] is None + assert ov["origin"] == origin_url + assert ov["visit"] == origin_visit.visit + assert ov["status"] == "ongoing" + assert ov["snapshot"] is None + assert ov["metadata"] is None - swh_storage.origin_visit_update( - origin_url, origin_visit.visit, status='full') + swh_storage.origin_visit_update(origin_url, origin_visit.visit, status="full") ov = next(swh_storage.origin_visit_get(origin_url)) - assert ov['origin'] == origin_url - assert ov['visit'] == origin_visit.visit - assert ov['status'] == 'full' - assert ov['snapshot'] is None - assert ov['metadata'] is None + assert ov["origin"] == origin_url + assert ov["visit"] == origin_visit.visit + assert ov["status"] == "full" + assert ov["snapshot"] is None + assert ov["metadata"] is None def test_retrying_proxy_swh_storage_origin_visit_update_retry( - swh_storage, sample_data, mocker, fake_hash_collision): + swh_storage, sample_data, mocker, fake_hash_collision +): """Multiple retries for hash collision and psycopg2 error but finally ok """ - sample_origin = sample_data['origin'][1] - origin_url = sample_origin['url'] + sample_origin = sample_data["origin"][1] + origin_url = sample_origin["url"] mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.origin_visit_update') + "swh.storage.in_memory.InMemoryStorage.origin_visit_update" + ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko - psycopg2.IntegrityError('origin already inserted'), + psycopg2.IntegrityError("origin already inserted"), # ok then! - {'origin': origin_url, 'visit': 1} + {"origin": origin_url, "visit": 1}, ] mock_sleep = mocker.patch( - 'swh.storage.retry.RetryingProxyStorage' - '.origin_visit_update.retry.sleep') + "swh.storage.retry.RetryingProxyStorage" ".origin_visit_update.retry.sleep" + ) visit_id = 1 - swh_storage.origin_visit_update(origin_url, visit_id, status='full') - - mock_memory.assert_has_calls([ - call(origin_url, visit_id, metadata=None, - snapshot=None, status='full'), - call(origin_url, visit_id, metadata=None, - snapshot=None, status='full'), - call(origin_url, visit_id, metadata=None, - snapshot=None, status='full'), - ]) + swh_storage.origin_visit_update(origin_url, visit_id, status="full") + + mock_memory.assert_has_calls( + [ + call(origin_url, visit_id, metadata=None, snapshot=None, status="full"), + call(origin_url, visit_id, metadata=None, snapshot=None, status="full"), + call(origin_url, visit_id, metadata=None, snapshot=None, status="full"), + ] + ) assert mock_sleep.call_count == 2 def test_retrying_proxy_swh_storage_origin_visit_update_failure( - swh_storage, sample_data, mocker): + swh_storage, sample_data, mocker +): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.origin_visit_update') - mock_memory.side_effect = StorageArgumentException( - 'Refuse to add origin always!') - origin_url = sample_data['origin'][0]['url'] + "swh.storage.in_memory.InMemoryStorage.origin_visit_update" + ) + mock_memory.side_effect = StorageArgumentException("Refuse to add origin always!") + origin_url = sample_data["origin"][0]["url"] visit_id = 9 - with pytest.raises(StorageArgumentException, match='Refuse to add'): - swh_storage.origin_visit_update(origin_url, visit_id, 'partial') + with pytest.raises(StorageArgumentException, match="Refuse to add"): + swh_storage.origin_visit_update(origin_url, visit_id, "partial") assert mock_memory.call_count == 1 def test_retrying_proxy_storage_directory_add(swh_storage, sample_data): """Standard directory_add works as before """ - sample_dir = sample_data['directory'][0] + sample_dir = sample_data["directory"][0] directory = swh_storage.directory_get_random() # no directory assert not directory s = swh_storage.directory_add([sample_dir]) assert s == { - 'directory:add': 1, + "directory:add": 1, } directory_id = swh_storage.directory_get_random() # only 1 - assert directory_id == sample_dir['id'] + assert directory_id == sample_dir["id"] def test_retrying_proxy_storage_directory_add_with_retry( - swh_storage, sample_data, mocker, fake_hash_collision): + swh_storage, sample_data, mocker, fake_hash_collision +): """Multiple retries for hash collision and psycopg2 error but finally ok """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.directory_add') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.directory_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko - psycopg2.IntegrityError('directory already inserted'), + psycopg2.IntegrityError("directory already inserted"), # ok then! - {'directory:add': 1} + {"directory:add": 1}, ] mock_sleep = mocker.patch( - 'swh.storage.retry.RetryingProxyStorage' - '.directory_add.retry.sleep') + "swh.storage.retry.RetryingProxyStorage" ".directory_add.retry.sleep" + ) - sample_dir = sample_data['directory'][1] + sample_dir = sample_data["directory"][1] directory_id = swh_storage.directory_get_random() # no directory assert not directory_id s = swh_storage.directory_add([sample_dir]) assert s == { - 'directory:add': 1, + "directory:add": 1, } - mock_memory.assert_has_calls([ - call([Directory.from_dict(sample_dir)]), - call([Directory.from_dict(sample_dir)]), - call([Directory.from_dict(sample_dir)]), - ]) + mock_memory.assert_has_calls( + [ + call([Directory.from_dict(sample_dir)]), + call([Directory.from_dict(sample_dir)]), + call([Directory.from_dict(sample_dir)]), + ] + ) assert mock_sleep.call_count == 2 def test_retrying_proxy_swh_storage_directory_add_failure( - swh_storage, sample_data, mocker): + swh_storage, sample_data, mocker +): """Unfiltered errors are raising without retry """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.directory_add') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.directory_add") mock_memory.side_effect = StorageArgumentException( - 'Refuse to add directory always!') + "Refuse to add directory always!" + ) - sample_dir = sample_data['directory'][0] + sample_dir = sample_data["directory"][0] directory_id = swh_storage.directory_get_random() # no directory assert not directory_id - with pytest.raises(StorageArgumentException, match='Refuse to add'): + with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.directory_add([sample_dir]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_revision_add(swh_storage, sample_data): """Standard revision_add works as before """ - sample_rev = sample_data['revision'][0] + sample_rev = sample_data["revision"][0] - revision = next(swh_storage.revision_get([sample_rev['id']])) + revision = next(swh_storage.revision_get([sample_rev["id"]])) assert not revision s = swh_storage.revision_add([sample_rev]) assert s == { - 'revision:add': 1, + "revision:add": 1, } - revision = next(swh_storage.revision_get([sample_rev['id']])) - assert revision['id'] == sample_rev['id'] + revision = next(swh_storage.revision_get([sample_rev["id"]])) + assert revision["id"] == sample_rev["id"] def test_retrying_proxy_storage_revision_add_with_retry( - swh_storage, sample_data, mocker, fake_hash_collision): + swh_storage, sample_data, mocker, fake_hash_collision +): """Multiple retries for hash collision and psycopg2 error but finally ok """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.revision_add') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.revision_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko - psycopg2.IntegrityError('revision already inserted'), + psycopg2.IntegrityError("revision already inserted"), # ok then! - {'revision:add': 1} + {"revision:add": 1}, ] mock_sleep = mocker.patch( - 'swh.storage.retry.RetryingProxyStorage' - '.revision_add.retry.sleep') + "swh.storage.retry.RetryingProxyStorage" ".revision_add.retry.sleep" + ) - sample_rev = sample_data['revision'][0] + sample_rev = sample_data["revision"][0] - revision = next(swh_storage.revision_get([sample_rev['id']])) + revision = next(swh_storage.revision_get([sample_rev["id"]])) assert not revision s = swh_storage.revision_add([sample_rev]) assert s == { - 'revision:add': 1, + "revision:add": 1, } - mock_memory.assert_has_calls([ - call([Revision.from_dict(sample_rev)]), - call([Revision.from_dict(sample_rev)]), - call([Revision.from_dict(sample_rev)]), - ]) + mock_memory.assert_has_calls( + [ + call([Revision.from_dict(sample_rev)]), + call([Revision.from_dict(sample_rev)]), + call([Revision.from_dict(sample_rev)]), + ] + ) assert mock_sleep.call_count == 2 def test_retrying_proxy_swh_storage_revision_add_failure( - swh_storage, sample_data, mocker): + swh_storage, sample_data, mocker +): """Unfiltered errors are raising without retry """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.revision_add') - mock_memory.side_effect = StorageArgumentException( - 'Refuse to add revision always!') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.revision_add") + mock_memory.side_effect = StorageArgumentException("Refuse to add revision always!") - sample_rev = sample_data['revision'][0] + sample_rev = sample_data["revision"][0] - revision = next(swh_storage.revision_get([sample_rev['id']])) + revision = next(swh_storage.revision_get([sample_rev["id"]])) assert not revision - with pytest.raises(StorageArgumentException, match='Refuse to add'): + with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.revision_add([sample_rev]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_release_add(swh_storage, sample_data): """Standard release_add works as before """ - sample_rel = sample_data['release'][0] + sample_rel = sample_data["release"][0] - release = next(swh_storage.release_get([sample_rel['id']])) + release = next(swh_storage.release_get([sample_rel["id"]])) assert not release s = swh_storage.release_add([sample_rel]) assert s == { - 'release:add': 1, + "release:add": 1, } - release = next(swh_storage.release_get([sample_rel['id']])) - assert release['id'] == sample_rel['id'] + release = next(swh_storage.release_get([sample_rel["id"]])) + assert release["id"] == sample_rel["id"] def test_retrying_proxy_storage_release_add_with_retry( - swh_storage, sample_data, mocker, fake_hash_collision): + swh_storage, sample_data, mocker, fake_hash_collision +): """Multiple retries for hash collision and psycopg2 error but finally ok """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.release_add') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.release_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko - psycopg2.IntegrityError('release already inserted'), + psycopg2.IntegrityError("release already inserted"), # ok then! - {'release:add': 1} + {"release:add": 1}, ] mock_sleep = mocker.patch( - 'swh.storage.retry.RetryingProxyStorage' - '.release_add.retry.sleep') + "swh.storage.retry.RetryingProxyStorage" ".release_add.retry.sleep" + ) - sample_rel = sample_data['release'][0] + sample_rel = sample_data["release"][0] - release = next(swh_storage.release_get([sample_rel['id']])) + release = next(swh_storage.release_get([sample_rel["id"]])) assert not release s = swh_storage.release_add([sample_rel]) assert s == { - 'release:add': 1, + "release:add": 1, } - mock_memory.assert_has_calls([ - call([Release.from_dict(sample_rel)]), - call([Release.from_dict(sample_rel)]), - call([Release.from_dict(sample_rel)]), - ]) + mock_memory.assert_has_calls( + [ + call([Release.from_dict(sample_rel)]), + call([Release.from_dict(sample_rel)]), + call([Release.from_dict(sample_rel)]), + ] + ) assert mock_sleep.call_count == 2 def test_retrying_proxy_swh_storage_release_add_failure( - swh_storage, sample_data, mocker): + swh_storage, sample_data, mocker +): """Unfiltered errors are raising without retry """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.release_add') - mock_memory.side_effect = StorageArgumentException( - 'Refuse to add release always!') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.release_add") + mock_memory.side_effect = StorageArgumentException("Refuse to add release always!") - sample_rel = sample_data['release'][0] + sample_rel = sample_data["release"][0] - release = next(swh_storage.release_get([sample_rel['id']])) + release = next(swh_storage.release_get([sample_rel["id"]])) assert not release - with pytest.raises(StorageArgumentException, match='Refuse to add'): + with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.release_add([sample_rel]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_snapshot_add(swh_storage, sample_data): """Standard snapshot_add works as before """ - sample_snap = sample_data['snapshot'][0] + sample_snap = sample_data["snapshot"][0] - snapshot = swh_storage.snapshot_get(sample_snap['id']) + snapshot = swh_storage.snapshot_get(sample_snap["id"]) assert not snapshot s = swh_storage.snapshot_add([sample_snap]) assert s == { - 'snapshot:add': 1, + "snapshot:add": 1, } - snapshot = swh_storage.snapshot_get(sample_snap['id']) - assert snapshot['id'] == sample_snap['id'] + snapshot = swh_storage.snapshot_get(sample_snap["id"]) + assert snapshot["id"] == sample_snap["id"] def test_retrying_proxy_storage_snapshot_add_with_retry( - swh_storage, sample_data, mocker, fake_hash_collision): + swh_storage, sample_data, mocker, fake_hash_collision +): """Multiple retries for hash collision and psycopg2 error but finally ok """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.snapshot_add') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.snapshot_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko - psycopg2.IntegrityError('snapshot already inserted'), + psycopg2.IntegrityError("snapshot already inserted"), # ok then! - {'snapshot:add': 1} + {"snapshot:add": 1}, ] mock_sleep = mocker.patch( - 'swh.storage.retry.RetryingProxyStorage' - '.snapshot_add.retry.sleep') + "swh.storage.retry.RetryingProxyStorage" ".snapshot_add.retry.sleep" + ) - sample_snap = sample_data['snapshot'][0] + sample_snap = sample_data["snapshot"][0] - snapshot = swh_storage.snapshot_get(sample_snap['id']) + snapshot = swh_storage.snapshot_get(sample_snap["id"]) assert not snapshot s = swh_storage.snapshot_add([sample_snap]) assert s == { - 'snapshot:add': 1, + "snapshot:add": 1, } - mock_memory.assert_has_calls([ - call([Snapshot.from_dict(sample_snap)]), - call([Snapshot.from_dict(sample_snap)]), - call([Snapshot.from_dict(sample_snap)]), - ]) + mock_memory.assert_has_calls( + [ + call([Snapshot.from_dict(sample_snap)]), + call([Snapshot.from_dict(sample_snap)]), + call([Snapshot.from_dict(sample_snap)]), + ] + ) assert mock_sleep.call_count == 2 def test_retrying_proxy_swh_storage_snapshot_add_failure( - swh_storage, sample_data, mocker): + swh_storage, sample_data, mocker +): """Unfiltered errors are raising without retry """ - mock_memory = mocker.patch( - 'swh.storage.in_memory.InMemoryStorage.snapshot_add') - mock_memory.side_effect = StorageArgumentException( - 'Refuse to add snapshot always!') + mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.snapshot_add") + mock_memory.side_effect = StorageArgumentException("Refuse to add snapshot always!") - sample_snap = sample_data['snapshot'][0] + sample_snap = sample_data["snapshot"][0] - snapshot = swh_storage.snapshot_get(sample_snap['id']) + snapshot = swh_storage.snapshot_get(sample_snap["id"]) assert not snapshot - with pytest.raises(StorageArgumentException, match='Refuse to add'): + with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.snapshot_add([sample_snap]) assert mock_memory.call_count == 1 diff --git a/swh/storage/tests/test_server.py b/swh/storage/tests/test_server.py index a412c5a1..3aea1f2a 100644 --- a/swh/storage/tests/test_server.py +++ b/swh/storage/tests/test_server.py @@ -1,85 +1,73 @@ # 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 yaml from swh.storage.api.server import load_and_check_config -def prepare_config_file(tmpdir, content, name='config.yml'): +def prepare_config_file(tmpdir, content, name="config.yml"): """Prepare configuration file in `$tmpdir/name` with content `content`. Args: tmpdir (LocalPath): root directory content (str/dict): Content of the file either as string or as a dict. If a dict, converts the dict into a yaml string. name (str): configuration filename Returns path (str) of the configuration file prepared. """ config_path = tmpdir / name if isinstance(content, dict): # convert if needed content = yaml.dump(content) - config_path.write_text(content, encoding='utf-8') + config_path.write_text(content, encoding="utf-8") # pytest on python3.5 does not support LocalPath manipulation, so # convert path to string return str(config_path) def test_load_and_check_config_no_configuration(): """Inexistent configuration files raises""" with pytest.raises(EnvironmentError) as e: load_and_check_config(None) - assert e.value.args[0] == 'Configuration file must be defined' + assert e.value.args[0] == "Configuration file must be defined" - config_path = '/some/inexistent/config.yml' + config_path = "/some/inexistent/config.yml" with pytest.raises(FileNotFoundError) as e: load_and_check_config(config_path) - assert e.value.args[0] == 'Configuration file %s does not exist' % ( - config_path, ) + assert e.value.args[0] == "Configuration file %s does not exist" % (config_path,) def test_load_and_check_config_wrong_configuration(tmpdir): """Wrong configuration raises""" - config_path = prepare_config_file(tmpdir, 'something: useless') + config_path = prepare_config_file(tmpdir, "something: useless") with pytest.raises(KeyError) as e: load_and_check_config(config_path) - assert e.value.args[0] == 'Missing \'%storage\' configuration' + assert e.value.args[0] == "Missing '%storage' configuration" def test_load_and_check_config_local_config_fine(tmpdir): """'Remote configuration is fine""" config = { - 'storage': { - 'cls': 'local', - 'args': { - 'db': 'db', - 'objstorage': 'something', - } - } + "storage": {"cls": "local", "args": {"db": "db", "objstorage": "something",}} } config_path = prepare_config_file(tmpdir, config) - cfg = load_and_check_config(config_path, type='local') + cfg = load_and_check_config(config_path, type="local") assert cfg == config def test_load_and_check_config_remote_config_fine(tmpdir): """'Remote configuration is fine""" - config = { - 'storage': { - 'cls': 'remote', - 'args': {} - } - } + config = {"storage": {"cls": "remote", "args": {}}} config_path = prepare_config_file(tmpdir, config) - cfg = load_and_check_config(config_path, type='any') + cfg = load_and_check_config(config_path, type="any") assert cfg == config diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index 24682589..8e266f60 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,3902 +1,3992 @@ # 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 copy from contextlib import contextmanager import datetime import inspect import itertools import math import queue import random import threading from collections import defaultdict from datetime import timedelta from unittest.mock import Mock import psycopg2 import pytest from hypothesis import given, strategies, settings, HealthCheck from typing import ClassVar, Optional from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.model.model import Content, OriginVisit from swh.model.hypothesis_strategies import objects from swh.model.hashutil import hash_to_hex from swh.storage import get_storage from swh.storage.converters import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.interface import StorageInterface from swh.storage.utils import content_hex_hashes from .storage_data import data @contextmanager def db_transaction(storage): with storage.db() as db: with db.transaction() as cur: yield db, cur def normalize_entity(entity): entity = copy.deepcopy(entity) - for key in ('date', 'committer_date'): + for key in ("date", "committer_date"): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity -def transform_entries(dir_, *, prefix=b''): - for ent in dir_['entries']: +def transform_entries(dir_, *, prefix=b""): + for ent in dir_["entries"]: 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, + "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, } def cmpdir(directory): - return (directory['type'], directory['dir_id']) + return (directory["type"], directory["dir_id"]) def short_revision(revision): - return [revision['id'], revision['parents']] + return [revision["id"], revision["parents"]] -def assert_contents_ok(expected_contents, actual_contents, - keys_to_check={'sha1', 'data'}): +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 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,), {})() + interface = type("_", (StorageInterface,), {})() storage = get_storage(**swh_storage_backend_config) - assert 'content_add' in dir(interface) + assert "content_add" in dir(interface) missing_methods = [] for meth_name in dir(interface): - if meth_name.startswith('_'): + 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): + 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 == [] 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): cont = data.cont insertion_start_time = datetime.datetime.now(tz=datetime.timezone.utc) actual_result = swh_storage.content_add([cont]) insertion_end_time = datetime.datetime.now(tz=datetime.timezone.utc) assert actual_result == { - 'content:add': 1, - 'content:add:bytes': cont['length'], + "content:add": 1, + "content:add:bytes": cont["length"], } - assert list(swh_storage.content_get([cont['sha1']])) == \ - [{'sha1': cont['sha1'], 'data': cont['data']}] + assert list(swh_storage.content_get([cont["sha1"]])) == [ + {"sha1": cont["sha1"], "data": cont["data"]} + ] expected_cont = data.cont - del expected_cont['data'] + del expected_cont["data"] journal_objects = list(swh_storage.journal_writer.journal.objects) for (obj_type, obj) in journal_objects: - assert insertion_start_time <= obj['ctime'] - assert obj['ctime'] <= insertion_end_time - del obj['ctime'] - assert journal_objects == [('content', expected_cont)] + assert insertion_start_time <= obj["ctime"] + assert obj["ctime"] <= insertion_end_time + del obj["ctime"] + assert journal_objects == [("content", expected_cont)] swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['content'] == 1 + assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_generator(self, swh_storage): def _cnt_gen(): yield data.cont actual_result = swh_storage.content_add(_cnt_gen()) assert actual_result == { - 'content:add': 1, - 'content:add:bytes': data.cont['length'], + "content:add": 1, + "content:add:bytes": data.cont["length"], } swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['content'] == 1 + assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_lazy_content(self, swh_storage): called = False cont = data.cont class LazyContent(Content): def with_data(self): nonlocal called called = True - return Content.from_dict({ - **self.to_dict(), - 'data': cont['data'] - }) + return Content.from_dict({**self.to_dict(), "data": cont["data"]}) - lazy_content = LazyContent.from_dict({ - **cont, - 'data': b'nope', - }) + lazy_content = LazyContent.from_dict({**cont, "data": b"nope",}) insertion_start_time = datetime.datetime.now(tz=datetime.timezone.utc) # bypass the validation proxy for now, to directly put a dict actual_result = swh_storage.storage.content_add([lazy_content]) insertion_end_time = datetime.datetime.now(tz=datetime.timezone.utc) assert actual_result == { - 'content:add': 1, - 'content:add:bytes': cont['length'], + "content:add": 1, + "content:add:bytes": cont["length"], } assert called - assert list(swh_storage.content_get([cont['sha1']])) == \ - [{'sha1': cont['sha1'], 'data': cont['data']}] + assert list(swh_storage.content_get([cont["sha1"]])) == [ + {"sha1": cont["sha1"], "data": cont["data"]} + ] expected_cont = data.cont - del expected_cont['data'] + del expected_cont["data"] journal_objects = list(swh_storage.journal_writer.journal.objects) for (obj_type, obj) in journal_objects: - assert insertion_start_time <= obj['ctime'] - assert obj['ctime'] <= insertion_end_time - del obj['ctime'] - assert journal_objects == [('content', expected_cont)] + assert insertion_start_time <= obj["ctime"] + assert obj["ctime"] <= insertion_end_time + del obj["ctime"] + assert journal_objects == [("content", expected_cont)] swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['content'] == 1 + assert swh_storage.stat_counters()["content"] == 1 def test_content_add_validation(self, swh_storage): cont = data.cont - with pytest.raises(StorageArgumentException, match='status'): - swh_storage.content_add([{**cont, 'status': 'absent'}]) + with pytest.raises(StorageArgumentException, match="status"): + swh_storage.content_add([{**cont, "status": "absent"}]) - with pytest.raises(StorageArgumentException, match='status'): - swh_storage.content_add([{**cont, 'status': 'foobar'}]) + with pytest.raises(StorageArgumentException, match="status"): + swh_storage.content_add([{**cont, "status": "foobar"}]) with pytest.raises(StorageArgumentException, match="(?i)length"): - swh_storage.content_add([{**cont, 'length': -2}]) + swh_storage.content_add([{**cont, "length": -2}]) with pytest.raises(StorageArgumentException, match="reason"): - swh_storage.content_add([{**cont, 'reason': 'foobar'}]) + swh_storage.content_add([{**cont, "reason": "foobar"}]) def test_skipped_content_add_validation(self, swh_storage): cont = data.cont.copy() - del cont['data'] + del cont["data"] - with pytest.raises(StorageArgumentException, match='status'): - swh_storage.skipped_content_add([{**cont, 'status': 'visible'}]) + with pytest.raises(StorageArgumentException, match="status"): + swh_storage.skipped_content_add([{**cont, "status": "visible"}]) - with pytest.raises(StorageArgumentException, match='reason') as cm: - swh_storage.skipped_content_add([{**cont, 'status': 'absent'}]) + with pytest.raises(StorageArgumentException, match="reason") as cm: + swh_storage.skipped_content_add([{**cont, "status": "absent"}]) if type(cm.value) == psycopg2.IntegrityError: - assert cm.exception.pgcode == \ - psycopg2.errorcodes.NOT_NULL_VIOLATION + assert cm.exception.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION def test_content_get_missing(self, swh_storage): cont = data.cont swh_storage.content_add([cont]) # Query a single missing content - results = list(swh_storage.content_get( - [data.cont2['sha1']])) + results = list(swh_storage.content_get([data.cont2["sha1"]])) assert results == [None] # Check content_get does not abort after finding a missing content - results = list(swh_storage.content_get( - [data.cont['sha1'], data.cont2['sha1']])) - assert results == [{'sha1': cont['sha1'], 'data': cont['data']}, None] + results = list(swh_storage.content_get([data.cont["sha1"], data.cont2["sha1"]])) + assert results == [{"sha1": cont["sha1"], "data": cont["data"]}, None] # Check content_get does not discard found countent when it finds # a missing content. - results = list(swh_storage.content_get( - [data.cont2['sha1'], data.cont['sha1']])) - assert results == [None, {'sha1': cont['sha1'], 'data': cont['data']}] + results = list(swh_storage.content_get([data.cont2["sha1"], data.cont["sha1"]])) + assert results == [None, {"sha1": cont["sha1"], "data": cont["data"]}] def test_content_add_different_input(self, swh_storage): cont = data.cont cont2 = data.cont2 actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { - 'content:add': 2, - 'content:add:bytes': cont['length'] + cont2['length'], - } + "content:add": 2, + "content:add:bytes": cont["length"] + cont2["length"], + } def test_content_add_twice(self, swh_storage): actual_result = swh_storage.content_add([data.cont]) assert actual_result == { - 'content:add': 1, - 'content:add:bytes': data.cont['length'], - } + "content:add": 1, + "content:add:bytes": data.cont["length"], + } assert len(swh_storage.journal_writer.journal.objects) == 1 actual_result = swh_storage.content_add([data.cont, data.cont2]) assert actual_result == { - 'content:add': 1, - 'content:add:bytes': data.cont2['length'], - } + "content:add": 1, + "content:add:bytes": data.cont2["length"], + } assert 2 <= len(swh_storage.journal_writer.journal.objects) <= 3 assert len(swh_storage.content_find(data.cont)) == 1 assert len(swh_storage.content_find(data.cont2)) == 1 def test_content_add_collision(self, swh_storage): cont1 = data.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() - sha256_array = bytearray(cont1b['sha256']) + sha256_array = bytearray(cont1b["sha256"]) sha256_array[0] += 1 - cont1b['sha256'] = bytes(sha256_array) + cont1b["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', 'blake2s256'] + assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == hash_to_hex(cont1[actual_algo]) collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(Content.from_dict(cont1).hashes()), - content_hex_hashes(Content.from_dict(cont1b).hashes()) + content_hex_hashes(Content.from_dict(cont1b).hashes()), ] assert exc.colliding_content_hashes() == [ Content.from_dict(cont1).hashes(), - Content.from_dict(cont1b).hashes() + Content.from_dict(cont1b).hashes(), ] def test_content_add_duplicate(self, swh_storage): swh_storage.content_add([data.cont, data.cont]) - assert list(swh_storage.content_get([data.cont['sha1']])) == \ - [{'sha1': data.cont['sha1'], 'data': data.cont['data']}] + assert list(swh_storage.content_get([data.cont["sha1"]])) == [ + {"sha1": data.cont["sha1"], "data": data.cont["data"]} + ] def test_content_update(self, swh_storage): - if hasattr(swh_storage, 'storage'): + if hasattr(swh_storage, "storage"): swh_storage.journal_writer.journal = None # TODO, not supported cont = copy.deepcopy(data.cont) swh_storage.content_add([cont]) # alter the sha1_git for example - cont['sha1_git'] = hash_to_bytes( - '3a60a5275d0333bf13468e8b3dcab90f4046e654') + cont["sha1_git"] = hash_to_bytes("3a60a5275d0333bf13468e8b3dcab90f4046e654") - swh_storage.content_update([cont], keys=['sha1_git']) + swh_storage.content_update([cont], keys=["sha1_git"]) - results = swh_storage.content_get_metadata([cont['sha1']]) - del cont['data'] - assert results == {cont['sha1']: [cont]} + results = swh_storage.content_get_metadata([cont["sha1"]]) + del cont["data"] + assert results == {cont["sha1"]: [cont]} def test_content_add_metadata(self, swh_storage): cont = data.cont - del cont['data'] - cont['ctime'] = datetime.datetime.now() + del cont["data"] + cont["ctime"] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { - 'content:add': 1, - } + "content:add": 1, + } expected_cont = cont.copy() - del expected_cont['ctime'] - assert swh_storage.content_get_metadata([cont['sha1']]) == { - cont['sha1']: [expected_cont] + del expected_cont["ctime"] + assert swh_storage.content_get_metadata([cont["sha1"]]) == { + cont["sha1"]: [expected_cont] } - assert list(swh_storage.journal_writer.journal.objects) == [ - ('content', cont)] + assert list(swh_storage.journal_writer.journal.objects) == [("content", cont)] def test_content_add_metadata_different_input(self, swh_storage): cont = data.cont - del cont['data'] - cont['ctime'] = datetime.datetime.now() + del cont["data"] + cont["ctime"] = datetime.datetime.now() cont2 = data.cont2 - del cont2['data'] - cont2['ctime'] = datetime.datetime.now() + del cont2["data"] + cont2["ctime"] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { - 'content:add': 2, - } + "content:add": 2, + } def test_content_add_metadata_collision(self, swh_storage): cont1 = data.cont - del cont1['data'] - cont1['ctime'] = datetime.datetime.now() + del cont1["data"] + cont1["ctime"] = datetime.datetime.now() # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() - sha1_git_array = bytearray(cont1b['sha256']) + sha1_git_array = bytearray(cont1b["sha256"]) sha1_git_array[0] += 1 - cont1b['sha256'] = bytes(sha1_git_array) + cont1b["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'] + assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == hash_to_hex(cont1[actual_algo]) collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(Content.from_dict(cont1).hashes()), - content_hex_hashes(Content.from_dict(cont1b).hashes()) + content_hex_hashes(Content.from_dict(cont1b).hashes()), ] assert exc.colliding_content_hashes() == [ Content.from_dict(cont1).hashes(), - Content.from_dict(cont1b).hashes() + Content.from_dict(cont1b).hashes(), ] def test_skipped_content_add(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 - cont2['blake2s256'] = None + cont2["blake2s256"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [ { - 'sha1': cont['sha1'], - 'sha1_git': cont['sha1_git'], - 'blake2s256': cont['blake2s256'], - 'sha256': cont['sha256'] + "sha1": cont["sha1"], + "sha1_git": cont["sha1_git"], + "blake2s256": cont["blake2s256"], + "sha256": cont["sha256"], }, { - 'sha1': cont2['sha1'], - 'sha1_git': cont2['sha1_git'], - 'blake2s256': cont2['blake2s256'], - 'sha256': cont2['sha256'] + "sha1": cont2["sha1"], + "sha1_git": cont2["sha1_git"], + "blake2s256": cont2["blake2s256"], + "sha256": cont2["sha256"], }, ] actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) - assert 2 <= actual_result.pop('skipped_content:add') <= 3 + assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [] def test_skipped_content_add_missing_hashes(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 - cont['sha1_git'] = cont2['sha1_git'] = None + cont["sha1_git"] = cont2["sha1_git"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) - assert 2 <= actual_result.pop('skipped_content:add') <= 3 + assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [] def test_skipped_content_missing_partial_hash(self, swh_storage): cont = data.skipped_cont cont2 = cont.copy() - cont2['sha1_git'] = None + cont2["sha1_git"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont]) - assert actual_result.pop('skipped_content:add') == 1 + assert actual_result.pop("skipped_content:add") == 1 assert actual_result == {} missing = list(swh_storage.skipped_content_missing([cont, cont2])) - assert missing == [{ - 'sha1': cont2['sha1'], - 'sha1_git': cont2['sha1_git'], - 'blake2s256': cont2['blake2s256'], - 'sha256': cont2['sha256'] - }] + assert missing == [ + { + "sha1": cont2["sha1"], + "sha1_git": cont2["sha1_git"], + "blake2s256": cont2["blake2s256"], + "sha256": cont2["sha256"], + } + ] @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)) + @given( + strategies.sets( + elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), + min_size=0, + ) + ) def test_content_missing(self, swh_storage, algos): - algos |= {'sha1'} + algos |= {"sha1"} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_cont.copy() 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']) + 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]) + 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)) + @given( + strategies.sets( + elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), + min_size=0, + ) + ) def test_content_missing_unknown_algo(self, swh_storage, algos): - algos |= {'sha1'} + algos |= {"sha1"} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_cont.copy() 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_content["nonexisting_algo"] = b"\x00" test_contents.append(test_content) - assert set( - swh_storage.content_missing(test_contents)) == set( - missing_per_hash['sha1']) + 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]) + 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): # given cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) # when - gen = swh_storage.content_missing_per_sha1([cont2['sha1'], - missing_cont['sha1']]) + gen = swh_storage.content_missing_per_sha1( + [cont2["sha1"], missing_cont["sha1"]] + ) # then - assert list(gen) == [missing_cont['sha1']] + assert list(gen) == [missing_cont["sha1"]] def test_content_missing_per_sha1_git(self, swh_storage): cont = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont, cont2]) - contents = [cont['sha1_git'], cont2['sha1_git'], - missing_cont['sha1_git']] + 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']] + 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 = [c for c in swh_contents - if c['status'] != 'absent'] + expected_contents = [c 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['contents']) + assert actual_result["next_page_token"] is None + actual_contents.extend(actual_result["contents"]) - assert_contents_ok( - expected_contents, actual_contents, ['sha1']) + assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents""" - expected_contents = [c for c in swh_contents - if c['status'] != 'absent'] + expected_contents = [c 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 + assert actual_result["next_page_token"] is None - actual_contents = actual_result['contents'] - assert_contents_ok( - expected_contents, actual_contents, ['sha1']) + actual_contents = actual_result["contents"] + assert_contents_ok(expected_contents, actual_contents, ["sha1"]) 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'} + 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) + i, nb_partitions, limit=len(swh_contents) + 1 + ) - for cont in actual_result['contents']: - seen_sha1s.append(cont['sha1']) + for cont in actual_result["contents"]: + seen_sha1s.append(cont["sha1"]) # Limit is higher than the max number of results - assert actual_result['next_page_token'] is None + 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) as e: swh_storage.content_get_partition(1, 16, limit=None) - assert e.value.args == ('limit should not be None',) + assert e.value.args == ("limit should not be None",) - def test_generate_content_get_partition_pagination( - self, swh_storage, swh_contents): + def test_generate_content_get_partition_pagination(self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" - expected_contents = [c for c in swh_contents - if c['status'] != 'absent'] + expected_contents = [c 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['contents']) - page_token = actual_result['next_page_token'] + i, 4, limit=3, page_token=page_token + ) + actual_contents.extend(actual_result["contents"]) + page_token = actual_result["next_page_token"] if page_token is None: break - assert_contents_ok( - expected_contents, actual_contents, ['sha1']) + assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_metadata(self, swh_storage): cont1 = data.cont cont2 = data.cont2 swh_storage.content_add([cont1, cont2]) - actual_md = swh_storage.content_get_metadata( - [cont1['sha1'], cont2['sha1']]) + actual_md = swh_storage.content_get_metadata([cont1["sha1"], cont2["sha1"]]) # we only retrieve the metadata - cont1.pop('data') - cont2.pop('data') + cont1.pop("data") + cont2.pop("data") - assert actual_md[cont1['sha1']] == [cont1] - assert actual_md[cont2['sha1']] == [cont2] + assert actual_md[cont1["sha1"]] == [cont1] + assert actual_md[cont2["sha1"]] == [cont2] assert len(actual_md.keys()) == 2 def test_content_get_metadata_missing_sha1(self, swh_storage): cont1 = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont1, cont2]) - actual_contents = swh_storage.content_get_metadata( - [missing_cont['sha1']]) + actual_contents = swh_storage.content_get_metadata([missing_cont["sha1"]]) - assert actual_contents == {missing_cont['sha1']: []} + assert actual_contents == {missing_cont["sha1"]: []} def test_content_get_random(self, swh_storage): swh_storage.content_add([data.cont, data.cont2, data.cont3]) assert swh_storage.content_get_random() in { - data.cont['sha1_git'], data.cont2['sha1_git'], - data.cont3['sha1_git']} + data.cont["sha1_git"], + data.cont2["sha1_git"], + data.cont3["sha1_git"], + } def test_directory_add(self, swh_storage): - init_missing = list(swh_storage.directory_missing([data.dir['id']])) - assert [data.dir['id']] == init_missing + init_missing = list(swh_storage.directory_missing([data.dir["id"]])) + assert [data.dir["id"]] == init_missing actual_result = swh_storage.directory_add([data.dir]) - assert actual_result == {'directory:add': 1} + assert actual_result == {"directory:add": 1} - assert list(swh_storage.journal_writer.journal.objects) == \ - [('directory', data.dir)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("directory", data.dir) + ] - actual_data = list(swh_storage.directory_ls(data.dir['id'])) + actual_data = list(swh_storage.directory_ls(data.dir["id"])) expected_data = list(transform_entries(data.dir)) - assert sorted(expected_data, key=cmpdir) \ - == sorted(actual_data, key=cmpdir) + assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) - after_missing = list(swh_storage.directory_missing([data.dir['id']])) + after_missing = list(swh_storage.directory_missing([data.dir["id"]])) assert after_missing == [] swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['directory'] == 1 + assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_from_generator(self, swh_storage): def _dir_gen(): yield data.dir actual_result = swh_storage.directory_add(directories=_dir_gen()) - assert actual_result == {'directory:add': 1} + assert actual_result == {"directory:add": 1} - assert list(swh_storage.journal_writer.journal.objects) == \ - [('directory', data.dir)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("directory", data.dir) + ] swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['directory'] == 1 + assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_validation(self, swh_storage): dir_ = copy.deepcopy(data.dir) - dir_['entries'][0]['type'] = 'foobar' + dir_["entries"][0]["type"] = "foobar" - with pytest.raises(StorageArgumentException, match='type.*foobar'): + with pytest.raises(StorageArgumentException, match="type.*foobar"): swh_storage.directory_add([dir_]) dir_ = copy.deepcopy(data.dir) - del dir_['entries'][0]['target'] + del dir_["entries"][0]["target"] - with pytest.raises(StorageArgumentException, match='target') as cm: + with pytest.raises(StorageArgumentException, match="target") as cm: swh_storage.directory_add([dir_]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION def test_directory_add_twice(self, swh_storage): actual_result = swh_storage.directory_add([data.dir]) - assert actual_result == {'directory:add': 1} + assert actual_result == {"directory:add": 1} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('directory', data.dir)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("directory", data.dir) + ] actual_result = swh_storage.directory_add([data.dir]) - assert actual_result == {'directory:add': 0} + assert actual_result == {"directory:add": 0} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('directory', data.dir)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("directory", data.dir) + ] def test_directory_get_recursive(self, swh_storage): - init_missing = list(swh_storage.directory_missing([data.dir['id']])) - assert init_missing == [data.dir['id']] + init_missing = list(swh_storage.directory_missing([data.dir["id"]])) + assert init_missing == [data.dir["id"]] - actual_result = swh_storage.directory_add( - [data.dir, data.dir2, data.dir3]) - assert actual_result == {'directory:add': 3} + actual_result = swh_storage.directory_add([data.dir, data.dir2, data.dir3]) + assert actual_result == {"directory:add": 3} assert list(swh_storage.journal_writer.journal.objects) == [ - ('directory', data.dir), - ('directory', data.dir2), - ('directory', data.dir3)] + ("directory", data.dir), + ("directory", data.dir2), + ("directory", data.dir3), + ] # List directory containing a file and an unknown subdirectory - actual_data = list(swh_storage.directory_ls( - data.dir['id'], recursive=True)) + actual_data = list(swh_storage.directory_ls(data.dir["id"], recursive=True)) expected_data = list(transform_entries(data.dir)) - assert sorted(expected_data, key=cmpdir) \ - == sorted(actual_data, key=cmpdir) + assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a file and an unknown subdirectory - actual_data = list(swh_storage.directory_ls( - data.dir2['id'], recursive=True)) + actual_data = list(swh_storage.directory_ls(data.dir2["id"], recursive=True)) expected_data = list(transform_entries(data.dir2)) - assert sorted(expected_data, key=cmpdir) \ - == sorted(actual_data, key=cmpdir) + assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # be both those of the directory and of the subdir - actual_data = list(swh_storage.directory_ls( - data.dir3['id'], recursive=True)) - expected_data = list(itertools.chain( - transform_entries(data.dir3), - transform_entries(data.dir, prefix=b'subdir/'))) - assert sorted(expected_data, key=cmpdir) \ - == sorted(actual_data, key=cmpdir) + actual_data = list(swh_storage.directory_ls(data.dir3["id"], recursive=True)) + expected_data = list( + itertools.chain( + transform_entries(data.dir3), + transform_entries(data.dir, prefix=b"subdir/"), + ) + ) + assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) def test_directory_get_non_recursive(self, swh_storage): - init_missing = list(swh_storage.directory_missing([data.dir['id']])) - assert init_missing == [data.dir['id']] + init_missing = list(swh_storage.directory_missing([data.dir["id"]])) + assert init_missing == [data.dir["id"]] - actual_result = swh_storage.directory_add( - [data.dir, data.dir2, data.dir3]) - assert actual_result == {'directory:add': 3} + actual_result = swh_storage.directory_add([data.dir, data.dir2, data.dir3]) + assert actual_result == {"directory:add": 3} assert list(swh_storage.journal_writer.journal.objects) == [ - ('directory', data.dir), - ('directory', data.dir2), - ('directory', data.dir3)] + ("directory", data.dir), + ("directory", data.dir2), + ("directory", data.dir3), + ] # List directory containing a file and an unknown subdirectory - actual_data = list(swh_storage.directory_ls(data.dir['id'])) + actual_data = list(swh_storage.directory_ls(data.dir["id"])) expected_data = list(transform_entries(data.dir)) - assert sorted(expected_data, key=cmpdir) \ - == sorted(actual_data, key=cmpdir) + assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory contaiining a single file - actual_data = list(swh_storage.directory_ls(data.dir2['id'])) + actual_data = list(swh_storage.directory_ls(data.dir2["id"])) expected_data = list(transform_entries(data.dir2)) - assert sorted(expected_data, key=cmpdir) \ - == sorted(actual_data, key=cmpdir) + assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # 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(data.dir3['id'])) + actual_data = list(swh_storage.directory_ls(data.dir3["id"])) expected_data = list(transform_entries(data.dir3)) - assert sorted(expected_data, key=cmpdir) \ - == sorted(actual_data, key=cmpdir) + assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) def test_directory_entry_get_by_path(self, swh_storage): # given - init_missing = list(swh_storage.directory_missing([data.dir3['id']])) - assert [data.dir3['id']] == init_missing + init_missing = list(swh_storage.directory_missing([data.dir3["id"]])) + assert [data.dir3["id"]] == init_missing actual_result = swh_storage.directory_add([data.dir3, data.dir4]) - assert actual_result == {'directory:add': 2} + assert actual_result == {"directory:add": 2} expected_entries = [ { - 'dir_id': data.dir3['id'], - 'name': b'foo', - 'type': 'file', - 'target': data.cont['sha1_git'], - 'sha1': None, - 'sha1_git': None, - 'sha256': None, - 'status': None, - 'perms': from_disk.DentryPerms.content, - 'length': None, + "dir_id": data.dir3["id"], + "name": b"foo", + "type": "file", + "target": data.cont["sha1_git"], + "sha1": None, + "sha1_git": None, + "sha256": None, + "status": None, + "perms": from_disk.DentryPerms.content, + "length": None, }, { - 'dir_id': data.dir3['id'], - 'name': b'subdir', - 'type': 'dir', - 'target': data.dir['id'], - 'sha1': None, - 'sha1_git': None, - 'sha256': None, - 'status': None, - 'perms': from_disk.DentryPerms.directory, - 'length': None, + "dir_id": data.dir3["id"], + "name": b"subdir", + "type": "dir", + "target": data.dir["id"], + "sha1": None, + "sha1_git": None, + "sha256": None, + "status": None, + "perms": from_disk.DentryPerms.directory, + "length": None, }, { - 'dir_id': data.dir3['id'], - 'name': b'hello', - 'type': 'file', - 'target': b'12345678901234567890', - 'sha1': None, - 'sha1_git': None, - 'sha256': None, - 'status': None, - 'perms': from_disk.DentryPerms.content, - 'length': None, + "dir_id": data.dir3["id"], + "name": b"hello", + "type": "file", + "target": b"12345678901234567890", + "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( - data.dir3['entries'], expected_entries): + for entry, expected_entry in zip(data.dir3["entries"], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( - data.dir3['id'], - [entry['name']]) + data.dir3["id"], [entry["name"]] + ) assert actual_entry == expected_entry # same, but deeper - for entry, expected_entry in zip( - data.dir3['entries'], expected_entries): + for entry, expected_entry in zip(data.dir3["entries"], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( - data.dir4['id'], - [b'subdir1', entry['name']]) + data.dir4["id"], [b"subdir1", entry["name"]] + ) expected_entry = expected_entry.copy() - expected_entry['name'] = b'subdir1/' + expected_entry['name'] + expected_entry["name"] = b"subdir1/" + expected_entry["name"] assert actual_entry == expected_entry # when (nothing should be found here since data.dir is not persisted.) - for entry in data.dir['entries']: + for entry in data.dir["entries"]: actual_entry = swh_storage.directory_entry_get_by_path( - data.dir['id'], - [entry['name']]) + data.dir["id"], [entry["name"]] + ) assert actual_entry is None def test_directory_get_random(self, swh_storage): swh_storage.directory_add([data.dir, data.dir2, data.dir3]) - assert swh_storage.directory_get_random() in \ - {data.dir['id'], data.dir2['id'], data.dir3['id']} + assert swh_storage.directory_get_random() in { + data.dir["id"], + data.dir2["id"], + data.dir3["id"], + } def test_revision_add(self, swh_storage): - init_missing = swh_storage.revision_missing([data.revision['id']]) - assert list(init_missing) == [data.revision['id']] + init_missing = swh_storage.revision_missing([data.revision["id"]]) + assert list(init_missing) == [data.revision["id"]] actual_result = swh_storage.revision_add([data.revision]) - assert actual_result == {'revision:add': 1} + assert actual_result == {"revision:add": 1} - end_missing = swh_storage.revision_missing([data.revision['id']]) + end_missing = swh_storage.revision_missing([data.revision["id"]]) assert list(end_missing) == [] - assert list(swh_storage.journal_writer.journal.objects) \ - == [('revision', data.revision)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("revision", data.revision) + ] # already there so nothing added actual_result = swh_storage.revision_add([data.revision]) - assert actual_result == {'revision:add': 0} + assert actual_result == {"revision:add": 0} swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['revision'] == 1 + assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_from_generator(self, swh_storage): def _rev_gen(): yield data.revision actual_result = swh_storage.revision_add(_rev_gen()) - assert actual_result == {'revision:add': 1} + assert actual_result == {"revision:add": 1} swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['revision'] == 1 + assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_validation(self, swh_storage): rev = copy.deepcopy(data.revision) - rev['date']['offset'] = 2**16 + rev["date"]["offset"] = 2 ** 16 - with pytest.raises(StorageArgumentException, match='offset') as cm: + with pytest.raises(StorageArgumentException, match="offset") as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode \ - == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE + assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) - rev['committer_date']['offset'] = 2**16 + rev["committer_date"]["offset"] = 2 ** 16 - with pytest.raises(StorageArgumentException, match='offset') as cm: + with pytest.raises(StorageArgumentException, match="offset") as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode \ - == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE + assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) - rev['type'] = 'foobar' + rev["type"] = "foobar" - with pytest.raises(StorageArgumentException, match='(?i)type') as cm: + with pytest.raises(StorageArgumentException, match="(?i)type") as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode == \ - psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION + assert cm.value.pgcode == psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_revision_add_twice(self, swh_storage): actual_result = swh_storage.revision_add([data.revision]) - assert actual_result == {'revision:add': 1} + assert actual_result == {"revision:add": 1} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('revision', data.revision)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("revision", data.revision) + ] - actual_result = swh_storage.revision_add( - [data.revision, data.revision2]) - assert actual_result == {'revision:add': 1} + actual_result = swh_storage.revision_add([data.revision, data.revision2]) + assert actual_result == {"revision:add": 1} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('revision', data.revision), - ('revision', data.revision2)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("revision", data.revision), + ("revision", data.revision2), + ] def test_revision_add_name_clash(self, swh_storage): revision1 = data.revision revision2 = data.revision2 - revision1['author'] = { - 'fullname': b'John Doe ', - 'name': b'John Doe', - 'email': b'john.doe@example.com' + revision1["author"] = { + "fullname": b"John Doe ", + "name": b"John Doe", + "email": b"john.doe@example.com", } - revision2['author'] = { - 'fullname': b'John Doe ', - 'name': b'John Doe ', - 'email': b'john.doe@example.com ' + revision2["author"] = { + "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} + assert actual_result == {"revision:add": 2} def test_revision_get_order(self, swh_storage): - add_result = swh_storage.revision_add( - [data.revision, data.revision2] - ) - assert add_result == {'revision:add': 2} + add_result = swh_storage.revision_add([data.revision, data.revision2]) + assert add_result == {"revision:add": 2} # order 1 - res1 = swh_storage.revision_get( - [data.revision['id'], data.revision2['id']] - ) + res1 = swh_storage.revision_get([data.revision["id"], data.revision2["id"]]) assert list(res1) == [data.revision, data.revision2] # order 2 - res2 = swh_storage.revision_get( - [data.revision2['id'], data.revision['id']] - ) + res2 = swh_storage.revision_get([data.revision2["id"], data.revision["id"]]) assert list(res2) == [data.revision2, data.revision] def test_revision_log(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 - swh_storage.revision_add([data.revision3, - data.revision4]) + swh_storage.revision_add([data.revision3, data.revision4]) # when - actual_results = list(swh_storage.revision_log( - [data.revision4['id']])) + actual_results = list(swh_storage.revision_log([data.revision4["id"]])) # hack: ids generated for actual_result in actual_results: - if 'id' in actual_result['author']: - del actual_result['author']['id'] - if 'id' in actual_result['committer']: - del actual_result['committer']['id'] + if "id" in actual_result["author"]: + del actual_result["author"]["id"] + if "id" in actual_result["committer"]: + del actual_result["committer"]["id"] assert len(actual_results) == 2 # rev4 -child-> rev3 assert actual_results[0] == normalize_entity(data.revision4) assert actual_results[1] == normalize_entity(data.revision3) assert list(swh_storage.journal_writer.journal.objects) == [ - ('revision', data.revision3), - ('revision', data.revision4)] + ("revision", data.revision3), + ("revision", data.revision4), + ] def test_revision_log_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 - swh_storage.revision_add([data.revision3, - data.revision4]) - actual_results = list(swh_storage.revision_log( - [data.revision4['id']], 1)) + swh_storage.revision_add([data.revision3, data.revision4]) + actual_results = list(swh_storage.revision_log([data.revision4["id"]], 1)) # hack: ids generated for actual_result in actual_results: - if 'id' in actual_result['author']: - del actual_result['author']['id'] - if 'id' in actual_result['committer']: - del actual_result['committer']['id'] + if "id" in actual_result["author"]: + del actual_result["author"]["id"] + if "id" in actual_result["committer"]: + del actual_result["committer"]["id"] assert len(actual_results) == 1 assert actual_results[0] == data.revision4 def test_revision_log_unknown_revision(self, swh_storage): - rev_log = list(swh_storage.revision_log([data.revision['id']])) + rev_log = list(swh_storage.revision_log([data.revision["id"]])) assert rev_log == [] def test_revision_shortlog(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 - swh_storage.revision_add([data.revision3, - data.revision4]) + swh_storage.revision_add([data.revision3, data.revision4]) # when - actual_results = list(swh_storage.revision_shortlog( - [data.revision4['id']])) + actual_results = list(swh_storage.revision_shortlog([data.revision4["id"]])) assert len(actual_results) == 2 # rev4 -child-> rev3 assert list(actual_results[0]) == short_revision(data.revision4) assert list(actual_results[1]) == short_revision(data.revision3) def test_revision_shortlog_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 - swh_storage.revision_add([data.revision3, - data.revision4]) - actual_results = list(swh_storage.revision_shortlog( - [data.revision4['id']], 1)) + swh_storage.revision_add([data.revision3, data.revision4]) + actual_results = list(swh_storage.revision_shortlog([data.revision4["id"]], 1)) assert len(actual_results) == 1 assert list(actual_results[0]) == short_revision(data.revision4) def test_revision_get(self, swh_storage): swh_storage.revision_add([data.revision]) - actual_revisions = list(swh_storage.revision_get( - [data.revision['id'], data.revision2['id']])) + actual_revisions = list( + swh_storage.revision_get([data.revision["id"], data.revision2["id"]]) + ) # when - if 'id' in actual_revisions[0]['author']: - del actual_revisions[0]['author']['id'] # hack: ids are generated - if 'id' in actual_revisions[0]['committer']: - del actual_revisions[0]['committer']['id'] + if "id" in actual_revisions[0]["author"]: + del actual_revisions[0]["author"]["id"] # hack: ids are generated + if "id" in actual_revisions[0]["committer"]: + del actual_revisions[0]["committer"]["id"] assert len(actual_revisions) == 2 assert actual_revisions[0] == normalize_entity(data.revision) assert actual_revisions[1] is None def test_revision_get_no_parents(self, swh_storage): swh_storage.revision_add([data.revision3]) - get = list(swh_storage.revision_get([data.revision3['id']])) + get = list(swh_storage.revision_get([data.revision3["id"]])) assert len(get) == 1 - assert get[0]['parents'] == [] # no parents on this one + assert get[0]["parents"] == [] # no parents on this one def test_revision_get_random(self, swh_storage): - swh_storage.revision_add( - [data.revision, data.revision2, data.revision3]) + swh_storage.revision_add([data.revision, data.revision2, data.revision3]) - assert swh_storage.revision_get_random() in \ - {data.revision['id'], data.revision2['id'], data.revision3['id']} + assert swh_storage.revision_get_random() in { + data.revision["id"], + data.revision2["id"], + data.revision3["id"], + } def test_release_add(self, swh_storage): - init_missing = swh_storage.release_missing([data.release['id'], - data.release2['id']]) - assert [data.release['id'], data.release2['id']] == list(init_missing) + init_missing = swh_storage.release_missing( + [data.release["id"], data.release2["id"]] + ) + assert [data.release["id"], data.release2["id"]] == list(init_missing) actual_result = swh_storage.release_add([data.release, data.release2]) - assert actual_result == {'release:add': 2} + assert actual_result == {"release:add": 2} - end_missing = swh_storage.release_missing([data.release['id'], - data.release2['id']]) + end_missing = swh_storage.release_missing( + [data.release["id"], data.release2["id"]] + ) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ - ('release', data.release), - ('release', data.release2)] + ("release", data.release), + ("release", data.release2), + ] # already present so nothing added actual_result = swh_storage.release_add([data.release, data.release2]) - assert actual_result == {'release:add': 0} + assert actual_result == {"release:add": 0} swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['release'] == 2 + assert swh_storage.stat_counters()["release"] == 2 def test_release_add_from_generator(self, swh_storage): def _rel_gen(): yield data.release yield data.release2 actual_result = swh_storage.release_add(_rel_gen()) - assert actual_result == {'release:add': 2} + assert actual_result == {"release:add": 2} assert list(swh_storage.journal_writer.journal.objects) == [ - ('release', data.release), - ('release', data.release2)] + ("release", data.release), + ("release", data.release2), + ] swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['release'] == 2 + assert swh_storage.stat_counters()["release"] == 2 def test_release_add_no_author_date(self, swh_storage): release = data.release - release['author'] = None - release['date'] = None + release["author"] = None + release["date"] = None actual_result = swh_storage.release_add([release]) - assert actual_result == {'release:add': 1} + assert actual_result == {"release:add": 1} - end_missing = swh_storage.release_missing([data.release['id']]) + end_missing = swh_storage.release_missing([data.release["id"]]) assert list(end_missing) == [] - assert list(swh_storage.journal_writer.journal.objects) \ - == [('release', release)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("release", release) + ] def test_release_add_validation(self, swh_storage): rel = copy.deepcopy(data.release) - rel['date']['offset'] = 2**16 + rel["date"]["offset"] = 2 ** 16 - with pytest.raises(StorageArgumentException, match='offset') as cm: + with pytest.raises(StorageArgumentException, match="offset") as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode \ - == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE + assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rel = copy.deepcopy(data.release) - rel['author'] = None + rel["author"] = None - with pytest.raises(StorageArgumentException, match='date') as cm: + with pytest.raises(StorageArgumentException, match="date") as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.CHECK_VIOLATION def test_release_add_validation_type(self, swh_storage): rel = copy.deepcopy(data.release) - rel['date']['offset'] = 'toto' + rel["date"]["offset"] = "toto" with pytest.raises(StorageArgumentException): swh_storage.release_add([rel]) def test_release_add_twice(self, swh_storage): actual_result = swh_storage.release_add([data.release]) - assert actual_result == {'release:add': 1} + assert actual_result == {"release:add": 1} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('release', data.release)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("release", data.release) + ] actual_result = swh_storage.release_add([data.release, data.release2]) - assert actual_result == {'release:add': 1} + assert actual_result == {"release:add": 1} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('release', data.release), - ('release', data.release2)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("release", data.release), + ("release", data.release2), + ] def test_release_add_name_clash(self, swh_storage): release1 = data.release.copy() release2 = data.release2.copy() - release1['author'] = { - 'fullname': b'John Doe ', - 'name': b'John Doe', - 'email': b'john.doe@example.com' + release1["author"] = { + "fullname": b"John Doe ", + "name": b"John Doe", + "email": b"john.doe@example.com", } - release2['author'] = { - 'fullname': b'John Doe ', - 'name': b'John Doe ', - 'email': b'john.doe@example.com ' + release2["author"] = { + "fullname": b"John Doe ", + "name": b"John Doe ", + "email": b"john.doe@example.com ", } actual_result = swh_storage.release_add([release1, release2]) - assert actual_result == {'release:add': 2} + assert actual_result == {"release:add": 2} def test_release_get(self, swh_storage): # given swh_storage.release_add([data.release, data.release2]) # when - actual_releases = list(swh_storage.release_get([data.release['id'], - data.release2['id']])) + actual_releases = list( + swh_storage.release_get([data.release["id"], data.release2["id"]]) + ) # then for actual_release in actual_releases: - if 'id' in actual_release['author']: - del actual_release['author']['id'] # hack: ids are generated + if "id" in actual_release["author"]: + del actual_release["author"]["id"] # hack: ids are generated - assert [ - normalize_entity(data.release), normalize_entity(data.release2)] \ - == [actual_releases[0], actual_releases[1]] + assert [normalize_entity(data.release), normalize_entity(data.release2)] == [ + actual_releases[0], + actual_releases[1], + ] - unknown_releases = \ - list(swh_storage.release_get([data.release3['id']])) + unknown_releases = list(swh_storage.release_get([data.release3["id"]])) assert unknown_releases[0] is None def test_release_get_order(self, swh_storage): - add_result = swh_storage.release_add( - [data.release, data.release2] - ) - assert add_result == {'release:add': 2} + add_result = swh_storage.release_add([data.release, data.release2]) + assert add_result == {"release:add": 2} # order 1 - res1 = swh_storage.release_get( - [data.release['id'], data.release2['id']] - ) + res1 = swh_storage.release_get([data.release["id"], data.release2["id"]]) assert list(res1) == [data.release, data.release2] # order 2 - res2 = swh_storage.release_get( - [data.release2['id'], data.release['id']] - ) + res2 = swh_storage.release_get([data.release2["id"], data.release["id"]]) assert list(res2) == [data.release2, data.release] def test_release_get_random(self, swh_storage): swh_storage.release_add([data.release, data.release2, data.release3]) - assert swh_storage.release_get_random() in \ - {data.release['id'], data.release2['id'], data.release3['id']} + assert swh_storage.release_get_random() in { + data.release["id"], + data.release2["id"], + data.release3["id"], + } def test_origin_add_one(self, swh_storage): origin0 = swh_storage.origin_get(data.origin) assert origin0 is None id = swh_storage.origin_add_one(data.origin) - actual_origin = swh_storage.origin_get({'url': data.origin['url']}) - assert actual_origin['url'] == data.origin['url'] + actual_origin = swh_storage.origin_get({"url": data.origin["url"]}) + assert actual_origin["url"] == data.origin["url"] id2 = swh_storage.origin_add_one(data.origin) assert id == id2 def test_origin_add(self, swh_storage): origin0 = swh_storage.origin_get([data.origin])[0] assert origin0 is None origin1, origin2 = swh_storage.origin_add([data.origin, data.origin2]) - actual_origin = swh_storage.origin_get([{ - 'url': data.origin['url'], - }])[0] - assert actual_origin['url'] == origin1['url'] + actual_origin = swh_storage.origin_get([{"url": data.origin["url"],}])[0] + assert actual_origin["url"] == origin1["url"] - actual_origin2 = swh_storage.origin_get([{ - 'url': data.origin2['url'], - }])[0] - assert actual_origin2['url'] == origin2['url'] + actual_origin2 = swh_storage.origin_get([{"url": data.origin2["url"],}])[0] + assert actual_origin2["url"] == origin2["url"] - if 'id' in actual_origin: - del actual_origin['id'] - del actual_origin2['id'] + if "id" in actual_origin: + del actual_origin["id"] + del actual_origin2["id"] - assert list(swh_storage.journal_writer.journal.objects) \ - == [('origin', actual_origin), - ('origin', actual_origin2)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("origin", actual_origin), + ("origin", actual_origin2), + ] swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['origin'] == 2 + assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_from_generator(self, swh_storage): def _ori_gen(): yield data.origin yield data.origin2 origin1, origin2 = swh_storage.origin_add(_ori_gen()) - actual_origin = swh_storage.origin_get([{ - 'url': data.origin['url'], - }])[0] - assert actual_origin['url'] == origin1['url'] + actual_origin = swh_storage.origin_get([{"url": data.origin["url"],}])[0] + assert actual_origin["url"] == origin1["url"] - actual_origin2 = swh_storage.origin_get([{ - 'url': data.origin2['url'], - }])[0] - assert actual_origin2['url'] == origin2['url'] + actual_origin2 = swh_storage.origin_get([{"url": data.origin2["url"],}])[0] + assert actual_origin2["url"] == origin2["url"] - if 'id' in actual_origin: - del actual_origin['id'] - del actual_origin2['id'] + if "id" in actual_origin: + del actual_origin["id"] + del actual_origin2["id"] - assert list(swh_storage.journal_writer.journal.objects) \ - == [('origin', actual_origin), - ('origin', actual_origin2)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("origin", actual_origin), + ("origin", actual_origin2), + ] swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['origin'] == 2 + assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_twice(self, swh_storage): add1 = swh_storage.origin_add([data.origin, data.origin2]) - assert list(swh_storage.journal_writer.journal.objects) \ - == [('origin', data.origin), - ('origin', data.origin2)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("origin", data.origin), + ("origin", data.origin2), + ] add2 = swh_storage.origin_add([data.origin, data.origin2]) - assert list(swh_storage.journal_writer.journal.objects) \ - == [('origin', data.origin), - ('origin', data.origin2)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("origin", data.origin), + ("origin", data.origin2), + ] assert add1 == add2 def test_origin_add_validation(self, swh_storage): """Incorrect formatted origin should fail the validation """ - with pytest.raises(StorageArgumentException, match='url'): + with pytest.raises(StorageArgumentException, match="url"): swh_storage.origin_add([{}]) - with pytest.raises(StorageArgumentException, - match='unexpected keyword argument'): - swh_storage.origin_add([{'ul': 'mistyped url key'}]) + with pytest.raises( + StorageArgumentException, match="unexpected keyword argument" + ): + swh_storage.origin_add([{"ul": "mistyped url key"}]) def test_origin_get_legacy(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) - actual_origin0 = swh_storage.origin_get( - {'url': data.origin['url']}) - assert actual_origin0['url'] == data.origin['url'] + actual_origin0 = swh_storage.origin_get({"url": data.origin["url"]}) + assert actual_origin0["url"] == data.origin["url"] def test_origin_get(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) - actual_origin0 = swh_storage.origin_get( - [{'url': data.origin['url']}]) + actual_origin0 = swh_storage.origin_get([{"url": data.origin["url"]}]) assert len(actual_origin0) == 1 - assert actual_origin0[0]['url'] == data.origin['url'] + assert actual_origin0[0]["url"] == data.origin["url"] 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 = datetime.datetime.now(tz=datetime.timezone.utc) 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) + weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days + ) visits.append(date_visit) return visits def test_origin_visit_get_random(self, swh_storage): swh_storage.origin_add(data.origins) # Add some random visits within the selection range visits = self._generate_random_visits() - visit_type = 'git' + visit_type = "git" # Add visits to those origins for origin in data.origins: - origin_url = origin['url'] + origin_url = origin["url"] for date_visit in visits: visit = swh_storage.origin_visit_add( - origin_url, date=date_visit, type=visit_type) + origin_url, date=date_visit, type=visit_type + ) swh_storage.origin_visit_update( - origin_url, visit_id=visit.visit, status='full') + origin_url, visit_id=visit.visit, status="full" + ) swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() - assert stats['origin'] == len(data.origins) - assert stats['origin_visit'] == len(data.origins) * len(visits) + assert stats["origin"] == len(data.origins) + assert stats["origin_visit"] == len(data.origins) * len(visits) random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit - assert random_origin_visit['origin'] is not None - original_urls = [o['url'] for o in data.origins] - assert random_origin_visit['origin'] in original_urls + assert random_origin_visit["origin"] is not None + original_urls = [o["url"] for o in data.origins] + assert random_origin_visit["origin"] in original_urls def test_origin_visit_get_random_nothing_found(self, swh_storage): swh_storage.origin_add(data.origins) - visit_type = 'hg' + 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 data.origins: - origin_url = origin['url'] + origin_url = origin["url"] for date_visit in visits: visit = swh_storage.origin_visit_add( - origin_url, date=date_visit, type=visit_type) - swh_storage.origin_visit_update( - origin_url, visit.visit, status='full') + origin_url, date=date_visit, type=visit_type + ) + swh_storage.origin_visit_update(origin_url, visit.visit, status="full") random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit is None def test_origin_get_by_sha1(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) - origins = list(swh_storage.origin_get_by_sha1([ - sha1(data.origin['url']) - ])) + origins = list(swh_storage.origin_get_by_sha1([sha1(data.origin["url"])])) assert len(origins) == 1 - assert origins[0]['url'] == data.origin['url'] + assert origins[0]["url"] == data.origin["url"] def test_origin_get_by_sha1_not_found(self, swh_storage): assert swh_storage.origin_get(data.origin) is None - origins = list(swh_storage.origin_get_by_sha1([ - sha1(data.origin['url']) - ])) + origins = list(swh_storage.origin_get_by_sha1([sha1(data.origin["url"])])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage): - found_origins = list(swh_storage.origin_search(data.origin['url'])) + found_origins = list(swh_storage.origin_search(data.origin["url"])) assert len(found_origins) == 0 - found_origins = list(swh_storage.origin_search(data.origin['url'], - regexp=True)) + found_origins = list(swh_storage.origin_search(data.origin["url"], regexp=True)) assert len(found_origins) == 0 swh_storage.origin_add_one(data.origin) - origin_data = { - 'url': data.origin['url']} - found_origins = list(swh_storage.origin_search(data.origin['url'])) + origin_data = {"url": data.origin["url"]} + found_origins = list(swh_storage.origin_search(data.origin["url"])) assert len(found_origins) == 1 - if 'id' in found_origins[0]: - del found_origins[0]['id'] + if "id" in found_origins[0]: + del found_origins[0]["id"] assert found_origins[0] == origin_data - found_origins = list(swh_storage.origin_search( - '.' + data.origin['url'][1:-1] + '.', regexp=True)) + found_origins = list( + swh_storage.origin_search("." + data.origin["url"][1:-1] + ".", regexp=True) + ) assert len(found_origins) == 1 - if 'id' in found_origins[0]: - del found_origins[0]['id'] + if "id" in found_origins[0]: + del found_origins[0]["id"] assert found_origins[0] == origin_data swh_storage.origin_add_one(data.origin2) - origin2_data = {'url': data.origin2['url']} - found_origins = list(swh_storage.origin_search(data.origin2['url'])) + origin2_data = {"url": data.origin2["url"]} + found_origins = list(swh_storage.origin_search(data.origin2["url"])) assert len(found_origins) == 1 - if 'id' in found_origins[0]: - del found_origins[0]['id'] + if "id" in found_origins[0]: + del found_origins[0]["id"] assert found_origins[0] == origin2_data - found_origins = list(swh_storage.origin_search( - '.' + data.origin2['url'][1:-1] + '.', regexp=True)) + found_origins = list( + swh_storage.origin_search( + "." + data.origin2["url"][1:-1] + ".", regexp=True + ) + ) assert len(found_origins) == 1 - if 'id' in found_origins[0]: - del found_origins[0]['id'] + if "id" in found_origins[0]: + del found_origins[0]["id"] assert found_origins[0] == origin2_data def test_origin_search_no_regexp(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) - origin = swh_storage.origin_get({'url': data.origin['url']}) - origin2 = swh_storage.origin_get({'url': data.origin2['url']}) + origin = swh_storage.origin_get({"url": data.origin["url"]}) + origin2 = swh_storage.origin_get({"url": data.origin2["url"]}) # no pagination - found_origins = list(swh_storage.origin_search('/')) + found_origins = list(swh_storage.origin_search("/")) assert len(found_origins) == 2 # offset=0 - found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1)) # noqa + found_origins0 = list(swh_storage.origin_search("/", offset=0, limit=1)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 - found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1)) # noqa + found_origins1 = list(swh_storage.origin_search("/", offset=1, limit=1)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_substring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) - origin = swh_storage.origin_get({'url': data.origin['url']}) - origin2 = swh_storage.origin_get({'url': data.origin2['url']}) + origin = swh_storage.origin_get({"url": data.origin["url"]}) + origin2 = swh_storage.origin_get({"url": data.origin2["url"]}) # no pagination - found_origins = list(swh_storage.origin_search('/', regexp=True)) + found_origins = list(swh_storage.origin_search("/", regexp=True)) assert len(found_origins) == 2 # offset=0 - found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1, regexp=True)) # noqa + found_origins0 = list( + swh_storage.origin_search("/", offset=0, limit=1, regexp=True) + ) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 - found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1, regexp=True)) # noqa + found_origins1 = list( + swh_storage.origin_search("/", offset=1, limit=1, regexp=True) + ) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_fullstring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) - origin = swh_storage.origin_get({'url': data.origin['url']}) - origin2 = swh_storage.origin_get({'url': data.origin2['url']}) + origin = swh_storage.origin_get({"url": data.origin["url"]}) + origin2 = swh_storage.origin_get({"url": data.origin2["url"]}) # no pagination - found_origins = list(swh_storage.origin_search('.*/.*', regexp=True)) + found_origins = list(swh_storage.origin_search(".*/.*", regexp=True)) assert len(found_origins) == 2 # offset=0 - found_origins0 = list(swh_storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa + found_origins0 = list( + swh_storage.origin_search(".*/.*", offset=0, limit=1, regexp=True) + ) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 - found_origins1 = list(swh_storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa + found_origins1 = list( + swh_storage.origin_search(".*/.*", offset=1, limit=1, regexp=True) + ) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_visit_add(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) date_visit = datetime.datetime.now(datetime.timezone.utc) # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) - date_visit = date_visit.replace( - microsecond=round(date_visit.microsecond, -3)) + date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) # when origin_visit = swh_storage.origin_visit_add( - origin_url, type=data.type_visit1, date=date_visit) + origin_url, type=data.type_visit1, date=date_visit + ) expected_origin_visit = { - 'origin': origin_url, - 'date': date_visit, - 'visit': origin_visit.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": date_visit, + "visit": origin_visit.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": None, } assert origin_visit == OriginVisit.from_dict(expected_origin_visit) - actual_origin_visits = list(swh_storage.origin_visit_get( - origin_url)) + actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) assert expected_origin_visit in actual_origin_visits objects = list(swh_storage.journal_writer.journal.objects) - assert ('origin', data.origin2) in objects - assert ('origin_visit', expected_origin_visit) in objects + assert ("origin", data.origin2) in objects + assert ("origin_visit", expected_origin_visit) in objects def test_origin_visit_get__unknown_origin(self, swh_storage): - assert [] == list(swh_storage.origin_visit_get('foo')) + assert [] == list(swh_storage.origin_visit_get("foo")) def test_origin_visit_add_default_type(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when date_visit = datetime.datetime.now(datetime.timezone.utc) date_visit2 = date_visit + datetime.timedelta(minutes=1) # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) - date_visit = date_visit.replace( - microsecond=round(date_visit.microsecond, -3)) + date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( - microsecond=round(date_visit2.microsecond, -3)) + microsecond=round(date_visit2.microsecond, -3) + ) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=date_visit, type=data.type_visit1) + origin_url, date=date_visit, type=data.type_visit1 + ) origin_visit2 = swh_storage.origin_visit_add( - origin_url, date=date_visit2, type=data.type_visit2) + origin_url, date=date_visit2, type=data.type_visit2 + ) # then assert origin_visit1.origin == origin_url assert origin_visit1.visit is not None - actual_origin_visits = list(swh_storage.origin_visit_get( - origin_url)) + actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) expected_visits = [ { - 'origin': origin_url, - 'date': date_visit, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": date_visit, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": None, }, { - 'origin': origin_url, - 'date': date_visit2, - 'visit': origin_visit2.visit, - 'type': data.type_visit2, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": date_visit2, + "visit": origin_visit2.visit, + "type": data.type_visit2, + "status": "ongoing", + "metadata": None, + "snapshot": None, }, ] assert len(expected_visits) == len(actual_origin_visits) for visit in expected_visits: assert visit in actual_origin_visits objects = list(swh_storage.journal_writer.journal.objects) - assert ('origin', data.origin2) in objects + assert ("origin", data.origin2) in objects for visit in expected_visits: - assert ('origin_visit', visit) in objects + assert ("origin_visit", visit) in objects def test_origin_visit_add_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin2) with pytest.raises(StorageArgumentException) as cm: - swh_storage.origin_visit_add(origin_url, date=[b'foo'], type='git') + swh_storage.origin_visit_add(origin_url, date=[b"foo"], type="git") if type(cm.value) == psycopg2.ProgrammingError: - assert cm.value.pgcode \ - == psycopg2.errorcodes.UNDEFINED_FUNCTION + assert cm.value.pgcode == psycopg2.errorcodes.UNDEFINED_FUNCTION def test_origin_visit_update(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) origin_url2 = swh_storage.origin_add_one(data.origin2) # date_visit < date_visit2 date_visit = data.date_visit1 date_visit2 = data.date_visit2 # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) - date_visit = date_visit.replace( - microsecond=round(date_visit.microsecond, -3)) + date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( - microsecond=round(date_visit2.microsecond, -3)) + microsecond=round(date_visit2.microsecond, -3) + ) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=date_visit, type=data.type_visit1) + origin_url, date=date_visit, type=data.type_visit1 + ) origin_visit2 = swh_storage.origin_visit_add( - origin_url, date=date_visit2, type=data.type_visit2) + origin_url, date=date_visit2, type=data.type_visit2 + ) origin_visit3 = swh_storage.origin_visit_add( - origin_url2, date=date_visit2, type=data.type_visit3) + origin_url2, date=date_visit2, type=data.type_visit3 + ) # when visit1_metadata = { - 'contents': 42, - 'directories': 22, + "contents": 42, + "directories": 22, } swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, status='full', - metadata=visit1_metadata) + origin_url, origin_visit1.visit, status="full", metadata=visit1_metadata + ) swh_storage.origin_visit_update( - origin_url2, origin_visit3.visit, status='partial') + origin_url2, origin_visit3.visit, status="partial" + ) # then - actual_origin_visits = list(swh_storage.origin_visit_get( - origin_url)) - expected_visits = [{ - 'origin': origin_url, - 'date': date_visit, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'full', - 'metadata': visit1_metadata, - 'snapshot': None, - }, { - 'origin': origin_url, - 'date': date_visit2, - 'visit': origin_visit2.visit, - 'type': data.type_visit2, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, - }] + actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) + expected_visits = [ + { + "origin": origin_url, + "date": date_visit, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "full", + "metadata": visit1_metadata, + "snapshot": None, + }, + { + "origin": origin_url, + "date": date_visit2, + "visit": origin_visit2.visit, + "type": data.type_visit2, + "status": "ongoing", + "metadata": None, + "snapshot": None, + }, + ] for visit in expected_visits: assert visit in actual_origin_visits - actual_origin_visits_bis = list(swh_storage.origin_visit_get( - origin_url, limit=1)) + actual_origin_visits_bis = list( + swh_storage.origin_visit_get(origin_url, limit=1) + ) assert actual_origin_visits_bis == [ { - 'origin': origin_url, - 'date': date_visit, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'full', - 'metadata': visit1_metadata, - 'snapshot': None, - }] - - actual_origin_visits_ter = list(swh_storage.origin_visit_get( - origin_url, last_visit=origin_visit1.visit)) + "origin": origin_url, + "date": date_visit, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "full", + "metadata": visit1_metadata, + "snapshot": None, + } + ] + + actual_origin_visits_ter = list( + swh_storage.origin_visit_get(origin_url, last_visit=origin_visit1.visit) + ) assert actual_origin_visits_ter == [ { - 'origin': origin_url, - 'date': date_visit2, - 'visit': origin_visit2.visit, - 'type': data.type_visit2, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, - }] - - actual_origin_visits2 = list(swh_storage.origin_visit_get( - origin_url2)) + "origin": origin_url, + "date": date_visit2, + "visit": origin_visit2.visit, + "type": data.type_visit2, + "status": "ongoing", + "metadata": None, + "snapshot": None, + } + ] + + actual_origin_visits2 = list(swh_storage.origin_visit_get(origin_url2)) assert actual_origin_visits2 == [ { - 'origin': origin_url2, - 'date': date_visit2, - 'visit': origin_visit3.visit, - 'type': data.type_visit3, - 'status': 'partial', - 'metadata': None, - 'snapshot': None, - }] + "origin": origin_url2, + "date": date_visit2, + "visit": origin_visit3.visit, + "type": data.type_visit3, + "status": "partial", + "metadata": None, + "snapshot": None, + } + ] data1 = { - 'origin': origin_url, - 'date': date_visit, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": date_visit, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": None, } data2 = { - 'origin': origin_url, - 'date': date_visit2, - 'visit': origin_visit2.visit, - 'type': data.type_visit2, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": date_visit2, + "visit": origin_visit2.visit, + "type": data.type_visit2, + "status": "ongoing", + "metadata": None, + "snapshot": None, } data3 = { - 'origin': origin_url2, - 'date': date_visit2, - 'visit': origin_visit3.visit, - 'type': data.type_visit3, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url2, + "date": date_visit2, + "visit": origin_visit3.visit, + "type": data.type_visit3, + "status": "ongoing", + "metadata": None, + "snapshot": None, } data4 = { - 'origin': origin_url, - 'date': date_visit, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'metadata': visit1_metadata, - 'status': 'full', - 'snapshot': None, + "origin": origin_url, + "date": date_visit, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "metadata": visit1_metadata, + "status": "full", + "snapshot": None, } data5 = { - 'origin': origin_url2, - 'date': date_visit2, - 'visit': origin_visit3.visit, - 'type': data.type_visit3, - 'status': 'partial', - 'metadata': None, - 'snapshot': None, + "origin": origin_url2, + "date": date_visit2, + "visit": origin_visit3.visit, + "type": data.type_visit3, + "status": "partial", + "metadata": None, + "snapshot": None, } objects = list(swh_storage.journal_writer.journal.objects) - assert ('origin', data.origin) in objects - assert ('origin', data.origin2) in objects - assert ('origin_visit', data1) in objects - assert ('origin_visit', data2) in objects - assert ('origin_visit', data3) in objects - assert ('origin_visit', data4) in objects - assert ('origin_visit', data5) in objects + assert ("origin", data.origin) in objects + assert ("origin", data.origin2) in objects + assert ("origin_visit", data1) in objects + assert ("origin_visit", data2) in objects + assert ("origin_visit", data3) in objects + assert ("origin_visit", data4) in objects + assert ("origin_visit", data5) in objects def test_origin_visit_update_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) visit = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) - with pytest.raises(StorageArgumentException, match='status') as cm: - swh_storage.origin_visit_update( - origin_url, visit.visit, status='foobar') + origin_url, date=data.date_visit2, type=data.type_visit2 + ) + with pytest.raises(StorageArgumentException, match="status") as cm: + swh_storage.origin_visit_update(origin_url, visit.visit, status="foobar") if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode == \ - psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION + assert cm.value.pgcode == psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_origin_visit_find_by_date(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit1) + origin_url, date=data.date_visit2, type=data.type_visit1 + ) origin_visit2 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit3, type=data.type_visit2) + origin_url, date=data.date_visit3, type=data.type_visit2 + ) origin_visit3 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit3) + origin_url, date=data.date_visit2, type=data.type_visit3 + ) # Simple case - visit = swh_storage.origin_visit_find_by_date( - origin_url, data.date_visit3) - assert visit['visit'] == origin_visit2.visit + visit = swh_storage.origin_visit_find_by_date(origin_url, data.date_visit3) + assert visit["visit"] == origin_visit2.visit # There are two visits at the same date, the latest must be returned - visit = swh_storage.origin_visit_find_by_date( - origin_url, data.date_visit2) - assert visit['visit'] == origin_visit3.visit + visit = swh_storage.origin_visit_find_by_date(origin_url, data.date_visit2) + assert visit["visit"] == origin_visit3.visit def test_origin_visit_find_by_date__unknown_origin(self, swh_storage): - swh_storage.origin_visit_find_by_date('foo', data.date_visit2) + swh_storage.origin_visit_find_by_date("foo", data.date_visit2) def test_origin_visit_update_missing_snapshot(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) origin_visit = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) # when swh_storage.origin_visit_update( origin_url, origin_visit.visit, - status='ongoing', - snapshot=data.snapshot['id']) # snapshot does not exist yet + status="ongoing", + snapshot=data.snapshot["id"], + ) # snapshot does not exist yet # then actual_origin_visit = swh_storage.origin_visit_get_by( - origin_url, origin_visit.visit) - assert actual_origin_visit['snapshot'] == data.snapshot['id'] + origin_url, origin_visit.visit + ) + assert actual_origin_visit["snapshot"] == data.snapshot["id"] # when swh_storage.snapshot_add([data.snapshot]) - assert actual_origin_visit['snapshot'] == data.snapshot['id'] + assert actual_origin_visit["snapshot"] == data.snapshot["id"] def test_origin_visit_get_by(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_url2 = swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) + origin_url, date=data.date_visit2, type=data.type_visit2 + ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.snapshot['id']) + status="ongoing", + snapshot=data.snapshot["id"], + ) # Add some other {origin, visit} entries swh_storage.origin_visit_add( - origin_url, date=data.date_visit3, type=data.type_visit3) + origin_url, date=data.date_visit3, type=data.type_visit3 + ) swh_storage.origin_visit_add( - origin_url2, date=data.date_visit3, type=data.type_visit3) + origin_url2, date=data.date_visit3, type=data.type_visit3 + ) # when visit1_metadata = { - 'contents': 42, - 'directories': 22, + "contents": 42, + "directories": 22, } swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='full', metadata=visit1_metadata) + origin_url, origin_visit1.visit, status="full", metadata=visit1_metadata + ) expected_origin_visit = origin_visit1.to_dict() - expected_origin_visit.update({ - 'origin': origin_url, - 'visit': origin_visit1.visit, - 'date': data.date_visit2, - 'type': data.type_visit2, - 'metadata': visit1_metadata, - 'status': 'full', - 'snapshot': data.snapshot['id'], - }) + expected_origin_visit.update( + { + "origin": origin_url, + "visit": origin_visit1.visit, + "date": data.date_visit2, + "type": data.type_visit2, + "metadata": visit1_metadata, + "status": "full", + "snapshot": data.snapshot["id"], + } + ) # when actual_origin_visit1 = swh_storage.origin_visit_get_by( - origin_url, - origin_visit1.visit) + origin_url, origin_visit1.visit + ) # then assert actual_origin_visit1 == expected_origin_visit def test_origin_visit_get_by__unknown_origin(self, swh_storage): - assert swh_storage.origin_visit_get_by('foo', 10) is None + assert swh_storage.origin_visit_get_by("foo", 10) is None def test_origin_visit_upsert_new(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when - swh_storage.origin_visit_upsert([ - OriginVisit.from_dict({ - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': 123, - 'type': data.type_visit2, - 'status': 'full', - 'metadata': None, - 'snapshot': None, - }), - OriginVisit.from_dict({ - 'origin': origin_url, - 'date': '2018-01-01 23:00:00+00', - 'visit': 1234, - 'type': data.type_visit2, - 'status': 'full', - 'metadata': None, - 'snapshot': None, - }), - ]) + swh_storage.origin_visit_upsert( + [ + OriginVisit.from_dict( + { + "origin": origin_url, + "date": data.date_visit2, + "visit": 123, + "type": data.type_visit2, + "status": "full", + "metadata": None, + "snapshot": None, + } + ), + OriginVisit.from_dict( + { + "origin": origin_url, + "date": "2018-01-01 23:00:00+00", + "visit": 1234, + "type": data.type_visit2, + "status": "full", + "metadata": None, + "snapshot": None, + } + ), + ] + ) # then - actual_origin_visits = list(swh_storage.origin_visit_get( - origin_url)) + actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) assert actual_origin_visits == [ { - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': 123, - 'type': data.type_visit2, - 'status': 'full', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit2, + "visit": 123, + "type": data.type_visit2, + "status": "full", + "metadata": None, + "snapshot": None, }, { - 'origin': origin_url, - 'date': data.date_visit3, - 'visit': 1234, - 'type': data.type_visit2, - 'status': 'full', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit3, + "visit": 1234, + "type": data.type_visit2, + "status": "full", + "metadata": None, + "snapshot": None, }, ] data1 = { - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': 123, - 'type': data.type_visit2, - 'status': 'full', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit2, + "visit": 123, + "type": data.type_visit2, + "status": "full", + "metadata": None, + "snapshot": None, } data2 = { - 'origin': origin_url, - 'date': data.date_visit3, - 'visit': 1234, - 'type': data.type_visit2, - 'status': 'full', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit3, + "visit": 1234, + "type": data.type_visit2, + "status": "full", + "metadata": None, + "snapshot": None, } assert list(swh_storage.journal_writer.journal.objects) == [ - ('origin', data.origin2), - ('origin_visit', data1), - ('origin_visit', data2)] + ("origin", data.origin2), + ("origin_visit", data1), + ("origin_visit", data2), + ] def test_origin_visit_upsert_existing(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit1) - - swh_storage.origin_visit_upsert([OriginVisit.from_dict({ - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'full', - 'metadata': None, - 'snapshot': None, - })]) + origin_url, date=data.date_visit2, type=data.type_visit1 + ) + + swh_storage.origin_visit_upsert( + [ + OriginVisit.from_dict( + { + "origin": origin_url, + "date": data.date_visit2, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "full", + "metadata": None, + "snapshot": None, + } + ) + ] + ) # then assert origin_visit1.origin == origin_url assert origin_visit1.visit is not None - actual_origin_visits = list(swh_storage.origin_visit_get( - origin_url)) + actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) assert actual_origin_visits == [ { - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'full', - 'metadata': None, - 'snapshot': None, - }] + "origin": origin_url, + "date": data.date_visit2, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "full", + "metadata": None, + "snapshot": None, + } + ] data1 = { - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit2, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": None, } data2 = { - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'full', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit2, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "full", + "metadata": None, + "snapshot": None, } assert list(swh_storage.journal_writer.journal.objects) == [ - ('origin', data.origin2), - ('origin_visit', data1), - ('origin_visit', data2)] + ("origin", data.origin2), + ("origin_visit", data1), + ("origin_visit", data2), + ] def test_origin_visit_upsert_missing_visit_id(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # then - with pytest.raises(StorageArgumentException, match='Missing visit id'): - swh_storage.origin_visit_upsert([OriginVisit.from_dict({ - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': None, # <- make the test raise - 'type': data.type_visit1, - 'status': 'full', - 'metadata': None, - 'snapshot': None, - })]) + with pytest.raises(StorageArgumentException, match="Missing visit id"): + swh_storage.origin_visit_upsert( + [ + OriginVisit.from_dict( + { + "origin": origin_url, + "date": data.date_visit2, + "visit": None, # <- make the test raise + "type": data.type_visit1, + "status": "full", + "metadata": None, + "snapshot": None, + } + ) + ] + ) assert list(swh_storage.journal_writer.journal.objects) == [ - ('origin', data.origin2) + ("origin", data.origin2) ] def test_origin_visit_get_by_no_result(self, swh_storage): swh_storage.origin_add([data.origin]) - actual_origin_visit = swh_storage.origin_visit_get_by( - data.origin['url'], 999) + actual_origin_visit = swh_storage.origin_visit_get_by(data.origin["url"], 999) assert actual_origin_visit is None def test_origin_visit_get_latest(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) ov1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) ov2 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) + origin_url, date=data.date_visit2, type=data.type_visit2 + ) # Add a visit with the same date as the previous one ov3 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) - - origin_visit1 = swh_storage.origin_visit_get_by( - origin_url, ov1.visit) - origin_visit2 = swh_storage.origin_visit_get_by( - origin_url, ov2.visit) - origin_visit3 = swh_storage.origin_visit_get_by( - origin_url, ov3.visit) + origin_url, date=data.date_visit2, type=data.type_visit2 + ) + + origin_visit1 = swh_storage.origin_visit_get_by(origin_url, ov1.visit) + origin_visit2 = swh_storage.origin_visit_get_by(origin_url, ov2.visit) + origin_visit3 = swh_storage.origin_visit_get_by(origin_url, ov3.visit) # Two visits, both with no snapshot assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) - assert swh_storage.origin_visit_get_latest( - origin_url, require_snapshot=True) is None + assert ( + swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) + is None + ) # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_url, ov1.visit, - status='ongoing', - snapshot=data.complete_snapshot['id']) - assert {**origin_visit1, - 'snapshot': data.complete_snapshot['id']} \ - == swh_storage.origin_visit_get_latest( - origin_url, require_snapshot=True) + origin_url, + ov1.visit, + status="ongoing", + snapshot=data.complete_snapshot["id"], + ) + assert { + **origin_visit1, + "snapshot": data.complete_snapshot["id"], + } == swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no visit # returned - assert swh_storage.origin_visit_get_latest( - origin_url, allowed_statuses=['full']) is None + assert ( + swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) + is None + ) # Mark the first visit as completed and check status filter again - swh_storage.origin_visit_update( - origin_url, ov1.visit, status='full') + swh_storage.origin_visit_update(origin_url, ov1.visit, status="full") assert { **origin_visit1, - 'snapshot': data.complete_snapshot['id'], - 'status': 'full'} == swh_storage.origin_visit_get_latest( - origin_url, allowed_statuses=['full']) + "snapshot": data.complete_snapshot["id"], + "status": "full", + } == swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( - origin_url, ov2.visit, - status='ongoing', - snapshot=data.empty_snapshot['id']) - assert {**origin_visit2, 'snapshot': data.empty_snapshot['id']} == \ - swh_storage.origin_visit_get_latest( - origin_url, require_snapshot=True) + origin_url, ov2.visit, status="ongoing", snapshot=data.empty_snapshot["id"] + ) + assert { + **origin_visit2, + "snapshot": data.empty_snapshot["id"], + } == swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Check that the status filter is still working assert { **origin_visit1, - 'snapshot': data.complete_snapshot['id'], - 'status': 'full'} == swh_storage.origin_visit_get_latest( - origin_url, allowed_statuses=['full']) + "snapshot": data.complete_snapshot["id"], + "status": "full", + } == swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) # Add snapshot to visit3 (same date as visit2) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_url, ov3.visit, - status='ongoing', - snapshot=data.complete_snapshot['id']) + origin_url, + ov3.visit, + status="ongoing", + snapshot=data.complete_snapshot["id"], + ) assert { **origin_visit1, - 'snapshot': data.complete_snapshot['id'], - 'status': 'full'} == swh_storage.origin_visit_get_latest( - origin_url, allowed_statuses=['full']) + "snapshot": data.complete_snapshot["id"], + "status": "full", + } == swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) assert { **origin_visit1, - 'snapshot': data.complete_snapshot['id'], - 'status': 'full'} == swh_storage.origin_visit_get_latest( - origin_url, allowed_statuses=['full'], require_snapshot=True) + "snapshot": data.complete_snapshot["id"], + "status": "full", + } == swh_storage.origin_visit_get_latest( + origin_url, allowed_statuses=["full"], require_snapshot=True + ) assert { **origin_visit3, - 'snapshot': data.complete_snapshot['id'] - } == swh_storage.origin_visit_get_latest(origin_url) + "snapshot": data.complete_snapshot["id"], + } == swh_storage.origin_visit_get_latest(origin_url) assert { **origin_visit3, - 'snapshot': data.complete_snapshot['id'] - } == swh_storage.origin_visit_get_latest( - origin_url, require_snapshot=True) + "snapshot": data.complete_snapshot["id"], + } == swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) def test_person_fullname_unicity(self, swh_storage): # given (person injection through revisions for example) revision = data.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(data.revision2) - revision2['committer'] = dict(revision['committer']) - revision2['committer']['email'] = None - revision2['committer']['name'] = None + revision2["committer"] = dict(revision["committer"]) + revision2["committer"]["email"] = None + revision2["committer"]["name"] = None swh_storage.revision_add([revision]) swh_storage.revision_add([revision2]) # when getting added revisions - revisions = list( - swh_storage.revision_get([revision['id'], revision2['id']])) + revisions = list(swh_storage.revision_get([revision["id"], revision2["id"]])) # then # check committers are the same - assert revisions[0]['committer'] == revisions[1]['committer'] + assert revisions[0]["committer"] == revisions[1]["committer"] def test_snapshot_add_get_empty(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) visit_id = origin_visit1.visit actual_result = swh_storage.snapshot_add([data.empty_snapshot]) - assert actual_result == {'snapshot:add': 1} + assert actual_result == {"snapshot:add": 1} swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.empty_snapshot['id']) + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.empty_snapshot["id"], + ) - by_id = swh_storage.snapshot_get(data.empty_snapshot['id']) - assert by_id == {**data.empty_snapshot, 'next_branch': None} + by_id = swh_storage.snapshot_get(data.empty_snapshot["id"]) + assert by_id == {**data.empty_snapshot, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) - assert by_ov == {**data.empty_snapshot, 'next_branch': None} + assert by_ov == {**data.empty_snapshot, "next_branch": None} data1 = { - 'origin': origin_url, - 'date': data.date_visit1, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit1, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": None, } data2 = { - 'origin': origin_url, - 'date': data.date_visit1, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': data.empty_snapshot['id'], - } - assert list(swh_storage.journal_writer.journal.objects) == \ - [('origin', data.origin), - ('origin_visit', data1), - ('snapshot', data.empty_snapshot), - ('origin_visit', data2)] + "origin": origin_url, + "date": data.date_visit1, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": data.empty_snapshot["id"], + } + assert list(swh_storage.journal_writer.journal.objects) == [ + ("origin", data.origin), + ("origin_visit", data1), + ("snapshot", data.empty_snapshot), + ("origin_visit", data2), + ] def test_snapshot_add_get_complete(self, swh_storage): - origin_url = data.origin['url'] + origin_url = data.origin["url"] origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) visit_id = origin_visit1.visit actual_result = swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.complete_snapshot['id']) - assert actual_result == {'snapshot:add': 1} + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.complete_snapshot["id"], + ) + assert actual_result == {"snapshot:add": 1} - by_id = swh_storage.snapshot_get(data.complete_snapshot['id']) - assert by_id == {**data.complete_snapshot, 'next_branch': None} + by_id = swh_storage.snapshot_get(data.complete_snapshot["id"]) + assert by_id == {**data.complete_snapshot, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) - assert by_ov == {**data.complete_snapshot, 'next_branch': None} + assert by_ov == {**data.complete_snapshot, "next_branch": None} def test_snapshot_add_many(self, swh_storage): actual_result = swh_storage.snapshot_add( - [data.snapshot, data.complete_snapshot]) - assert actual_result == {'snapshot:add': 2} + [data.snapshot, data.complete_snapshot] + ) + assert actual_result == {"snapshot:add": 2} - assert {**data.complete_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get(data.complete_snapshot['id']) + assert { + **data.complete_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get(data.complete_snapshot["id"]) - assert {**data.snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get(data.snapshot['id']) + assert {**data.snapshot, "next_branch": None} == swh_storage.snapshot_get( + data.snapshot["id"] + ) swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['snapshot'] == 2 + assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_from_generator(self, swh_storage): def _snp_gen(): yield data.snapshot yield data.complete_snapshot actual_result = swh_storage.snapshot_add(_snp_gen()) - assert actual_result == {'snapshot:add': 2} + assert actual_result == {"snapshot:add": 2} swh_storage.refresh_stat_counters() - assert swh_storage.stat_counters()['snapshot'] == 2 + assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_incremental(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) - assert actual_result == {'snapshot:add': 1} + assert actual_result == {"snapshot:add": 1} actual_result2 = swh_storage.snapshot_add( - [data.snapshot, data.complete_snapshot]) - assert actual_result2 == {'snapshot:add': 1} + [data.snapshot, data.complete_snapshot] + ) + assert actual_result2 == {"snapshot:add": 1} - assert {**data.complete_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get(data.complete_snapshot['id']) + assert { + **data.complete_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get(data.complete_snapshot["id"]) - assert {**data.snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get(data.snapshot['id']) + assert {**data.snapshot, "next_branch": None} == swh_storage.snapshot_get( + data.snapshot["id"] + ) def test_snapshot_add_twice(self, swh_storage): actual_result = swh_storage.snapshot_add([data.empty_snapshot]) - assert actual_result == {'snapshot:add': 1} + assert actual_result == {"snapshot:add": 1} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('snapshot', data.empty_snapshot)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("snapshot", data.empty_snapshot) + ] actual_result = swh_storage.snapshot_add([data.snapshot]) - assert actual_result == {'snapshot:add': 1} + assert actual_result == {"snapshot:add": 1} - assert list(swh_storage.journal_writer.journal.objects) \ - == [('snapshot', data.empty_snapshot), - ('snapshot', data.snapshot)] + assert list(swh_storage.journal_writer.journal.objects) == [ + ("snapshot", data.empty_snapshot), + ("snapshot", data.snapshot), + ] def test_snapshot_add_validation(self, swh_storage): snap = copy.deepcopy(data.snapshot) - snap['branches'][b'foo'] = {'target_type': 'revision'} + snap["branches"][b"foo"] = {"target_type": "revision"} - with pytest.raises(StorageArgumentException, match='target'): + with pytest.raises(StorageArgumentException, match="target"): swh_storage.snapshot_add([snap]) snap = copy.deepcopy(data.snapshot) - snap['branches'][b'foo'] = {'target': b'\x42'*20} + snap["branches"][b"foo"] = {"target": b"\x42" * 20} - with pytest.raises(StorageArgumentException, match='target_type'): + with pytest.raises(StorageArgumentException, match="target_type"): swh_storage.snapshot_add([snap]) def test_snapshot_add_count_branches(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) - assert actual_result == {'snapshot:add': 1} + assert actual_result == {"snapshot:add": 1} - snp_id = data.complete_snapshot['id'] + snp_id = data.complete_snapshot["id"] snp_size = swh_storage.snapshot_count_branches(snp_id) expected_snp_size = { - 'alias': 1, - 'content': 1, - 'directory': 2, - 'release': 1, - 'revision': 1, - 'snapshot': 1, - None: 1 + "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): swh_storage.snapshot_add([data.complete_snapshot]) - snp_id = data.complete_snapshot['id'] - branches = data.complete_snapshot['branches'] + snp_id = data.complete_snapshot["id"] + branches = data.complete_snapshot["branches"] branch_names = list(sorted(branches)) # Test branch_from - snapshot = swh_storage.snapshot_get_branches( - snp_id, branches_from=b'release') + snapshot = swh_storage.snapshot_get_branches(snp_id, branches_from=b"release") - rel_idx = branch_names.index(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, + "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) + 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', + "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) + snp_id, branches_from=b"directory", branches_count=3 + ) - dir_idx = branch_names.index(b'directory') + 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] + "id": snp_id, + "branches": { + name: branches[name] for name in branch_names[dir_idx : dir_idx + 3] }, - 'next_branch': branch_names[dir_idx + 3], + "next_branch": branch_names[dir_idx + 3], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.complete_snapshot['id']) + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.complete_snapshot["id"], + ) - snp_id = data.complete_snapshot['id'] - branches = data.complete_snapshot['branches'] + snp_id = data.complete_snapshot["id"] + branches = data.complete_snapshot["branches"] snapshot = swh_storage.snapshot_get_branches( - snp_id, target_types=['release', 'revision']) + snp_id, target_types=["release", "revision"] + ) expected_snapshot = { - 'id': snp_id, - 'branches': { + "id": snp_id, + "branches": { name: tgt for name, tgt in branches.items() - if tgt and tgt['target_type'] in ['release', 'revision'] + if tgt and tgt["target_type"] in ["release", "revision"] }, - 'next_branch': None, + "next_branch": None, } assert snapshot == expected_snapshot - snapshot = swh_storage.snapshot_get_branches( - snp_id, target_types=['alias']) + snapshot = swh_storage.snapshot_get_branches(snp_id, target_types=["alias"]) expected_snapshot = { - 'id': snp_id, - 'branches': { + "id": snp_id, + "branches": { name: tgt for name, tgt in branches.items() - if tgt and tgt['target_type'] == 'alias' + if tgt and tgt["target_type"] == "alias" }, - 'next_branch': None, + "next_branch": None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) - snp_id = data.complete_snapshot['id'] - branches = data.complete_snapshot['branches'] + snp_id = data.complete_snapshot["id"] + branches = data.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') + 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, + "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) + snp_id, target_types=["directory", "release"], branches_count=1 + ) expected_snapshot = { - 'id': snp_id, - 'branches': { - b'directory': branches[b'directory'] - }, - 'next_branch': b'directory2', + "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) + 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') + "id": snp_id, + "branches": { + name: branches[name] for name in (b"directory", b"directory2") }, - 'next_branch': b'release', + "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) + snp_id, + target_types=["directory", "release"], + branches_from=b"directory2", + branches_count=1, + ) - dir_idx = branch_names.index(b'directory2') + 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', + "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(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) visit_id = origin_visit1.visit swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.snapshot['id']) + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.snapshot["id"], + ) - by_id = swh_storage.snapshot_get(data.snapshot['id']) - assert by_id == {**data.snapshot, 'next_branch': None} + by_id = swh_storage.snapshot_get(data.snapshot["id"]) + assert by_id == {**data.snapshot, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) - assert by_ov == {**data.snapshot, 'next_branch': None} + assert by_ov == {**data.snapshot, "next_branch": None} - origin_visit_info = swh_storage.origin_visit_get_by( - origin_url, visit_id) - assert origin_visit_info['snapshot'] == data.snapshot['id'] + origin_visit_info = swh_storage.origin_visit_get_by(origin_url, visit_id) + assert origin_visit_info["snapshot"] == data.snapshot["id"] def test_snapshot_add_nonexistent_visit(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) # unknown visit visit_id = 54164461156 swh_storage.journal_writer.journal.objects[:] = [] swh_storage.snapshot_add([data.snapshot]) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_update( - origin_url, visit_id, - status='ongoing', - snapshot=data.snapshot['id']) + origin_url, visit_id, status="ongoing", snapshot=data.snapshot["id"] + ) assert list(swh_storage.journal_writer.journal.objects) == [ - ('snapshot', data.snapshot)] + ("snapshot", data.snapshot) + ] def test_snapshot_add_twice__by_origin_visit(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) visit1_id = origin_visit1.visit swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.snapshot['id']) + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.snapshot["id"], + ) - by_ov1 = swh_storage.snapshot_get_by_origin_visit( - origin_url, visit1_id) - assert by_ov1 == {**data.snapshot, 'next_branch': None} + by_ov1 = swh_storage.snapshot_get_by_origin_visit(origin_url, visit1_id) + assert by_ov1 == {**data.snapshot, "next_branch": None} origin_visit2 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) + origin_url, date=data.date_visit2, type=data.type_visit2 + ) visit2_id = origin_visit2.visit swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit2.visit, - status='ongoing', - snapshot=data.snapshot['id']) + origin_url, + origin_visit2.visit, + status="ongoing", + snapshot=data.snapshot["id"], + ) - by_ov2 = swh_storage.snapshot_get_by_origin_visit( - origin_url, visit2_id) - assert by_ov2 == {**data.snapshot, 'next_branch': None} + by_ov2 = swh_storage.snapshot_get_by_origin_visit(origin_url, visit2_id) + assert by_ov2 == {**data.snapshot, "next_branch": None} data1 = { - 'origin': origin_url, - 'date': data.date_visit1, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit1, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": None, } data2 = { - 'origin': origin_url, - 'date': data.date_visit1, - 'visit': origin_visit1.visit, - 'type': data.type_visit1, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': data.snapshot['id'], + "origin": origin_url, + "date": data.date_visit1, + "visit": origin_visit1.visit, + "type": data.type_visit1, + "status": "ongoing", + "metadata": None, + "snapshot": data.snapshot["id"], } data3 = { - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': origin_visit2.visit, - 'type': data.type_visit2, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': None, + "origin": origin_url, + "date": data.date_visit2, + "visit": origin_visit2.visit, + "type": data.type_visit2, + "status": "ongoing", + "metadata": None, + "snapshot": None, } data4 = { - 'origin': origin_url, - 'date': data.date_visit2, - 'visit': origin_visit2.visit, - 'type': data.type_visit2, - 'status': 'ongoing', - 'metadata': None, - 'snapshot': data.snapshot['id'], - } - assert list(swh_storage.journal_writer.journal.objects) \ - == [('origin', data.origin), - ('origin_visit', data1), - ('snapshot', data.snapshot), - ('origin_visit', data2), - ('origin_visit', data3), - ('origin_visit', data4)] + "origin": origin_url, + "date": data.date_visit2, + "visit": origin_visit2.visit, + "type": data.type_visit2, + "status": "ongoing", + "metadata": None, + "snapshot": data.snapshot["id"], + } + assert list(swh_storage.journal_writer.journal.objects) == [ + ("origin", data.origin), + ("origin_visit", data1), + ("snapshot", data.snapshot), + ("origin_visit", data2), + ("origin_visit", data3), + ("origin_visit", data4), + ] def test_snapshot_get_latest(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) origin_visit2 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) + origin_url, date=data.date_visit2, type=data.type_visit2 + ) # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit3) + origin_url, date=data.date_visit2, type=data.type_visit3 + ) # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add snapshot to visit1, latest snapshot = visit 1 snapshot swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.complete_snapshot['id']) - assert {**data.complete_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest(origin_url) + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.complete_snapshot["id"], + ) + assert { + **data.complete_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no snapshot # returned - assert swh_storage.snapshot_get_latest( - origin_url, - allowed_statuses=['full']) is None + assert ( + swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) + is None + ) # Mark the first visit as completed and check status filter again - swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, status='full') - assert {**data.complete_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest( - origin_url, - allowed_statuses=['full']) + swh_storage.origin_visit_update(origin_url, origin_visit1.visit, status="full") + assert { + **data.complete_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit2.visit, - status='ongoing', - snapshot=data.empty_snapshot['id']) - assert {**data.empty_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest(origin_url) + origin_url, + origin_visit2.visit, + status="ongoing", + snapshot=data.empty_snapshot["id"], + ) + assert { + **data.empty_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get_latest(origin_url) # Check that the status filter is still working - assert {**data.complete_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest( - origin_url, - allowed_statuses=['full']) + assert { + **data.complete_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit3.visit, - status='ongoing', - snapshot=data.complete_snapshot['id']) - assert {**data.complete_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest(origin_url) + origin_url, + origin_visit3.visit, + status="ongoing", + snapshot=data.complete_snapshot["id"], + ) + assert { + **data.complete_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_latest__missing_snapshot(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) assert swh_storage.snapshot_get_latest(origin_url) is None origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit1, type=data.type_visit1) + origin_url, date=data.date_visit1, type=data.type_visit1 + ) origin_visit2 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) + origin_url, date=data.date_visit2, type=data.type_visit2 + ) # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add unknown snapshot to visit1, check that the inconsistency is # detected swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.complete_snapshot['id']) + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.complete_snapshot["id"], + ) with pytest.raises(Exception): # XXX: should the exception be more specific than this? swh_storage.snapshot_get_latest(origin_url) # Status filter: both visits are status=ongoing, so no snapshot # returned - assert swh_storage.snapshot_get_latest( - origin_url, allowed_statuses=['full']) is None + assert ( + swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) + is None + ) # Mark the first visit as completed and check status filter again - swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, status='full') + swh_storage.origin_visit_update(origin_url, origin_visit1.visit, status="full") with pytest.raises(Exception): # XXX: should the exception be more specific than this? - swh_storage.snapshot_get_latest( - origin_url, - allowed_statuses=['full']), + swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]), # Actually add the snapshot and check status filter again swh_storage.snapshot_add([data.complete_snapshot]) - assert {**data.complete_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest(origin_url) + assert { + **data.complete_snapshot, + "next_branch": None, + } == swh_storage.snapshot_get_latest(origin_url) # Add unknown snapshot to visit2 and check that the inconsistency # is detected swh_storage.origin_visit_update( - origin_url, origin_visit2.visit, - status='ongoing', - snapshot=data.snapshot['id']) + origin_url, + origin_visit2.visit, + status="ongoing", + snapshot=data.snapshot["id"], + ) with pytest.raises(Exception): # XXX: should the exception be more specific than this? - swh_storage.snapshot_get_latest( - origin_url) + swh_storage.snapshot_get_latest(origin_url) # Actually add that snapshot and check that the new one is returned swh_storage.snapshot_add([data.snapshot]) - assert{**data.snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest(origin_url) + assert { + **data.snapshot, + "next_branch": None, + } == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_random(self, swh_storage): swh_storage.snapshot_add( - [data.snapshot, data.empty_snapshot, data.complete_snapshot]) + [data.snapshot, data.empty_snapshot, data.complete_snapshot] + ) assert swh_storage.snapshot_get_random() in { - data.snapshot['id'], data.empty_snapshot['id'], - data.complete_snapshot['id']} + data.snapshot["id"], + data.empty_snapshot["id"], + data.complete_snapshot["id"], + } def test_snapshot_missing(self, swh_storage): snap = data.snapshot missing_snap = data.empty_snapshot - snapshots = [snap['id'], missing_snap['id']] + snapshots = [snap["id"], missing_snap["id"]] swh_storage.snapshot_add([snap]) missing_snapshots = swh_storage.snapshot_missing(snapshots) - assert list(missing_snapshots) == [missing_snap['id']] + assert list(missing_snapshots) == [missing_snap["id"]] def test_stat_counters(self, swh_storage): - expected_keys = ['content', 'directory', - 'origin', 'revision'] + 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([data.cont]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: - if key != 'content': + if key != "content": assert counters[key] == 0 - assert counters['content'] == 1 + assert counters["content"] == 1 # Add other objects. Check their counter increased as well. origin_url = swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( - origin_url, date=data.date_visit2, type=data.type_visit2) + origin_url, date=data.date_visit2, type=data.type_visit2 + ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_url, origin_visit1.visit, - status='ongoing', - snapshot=data.snapshot['id']) + origin_url, + origin_visit1.visit, + status="ongoing", + snapshot=data.snapshot["id"], + ) swh_storage.directory_add([data.dir]) swh_storage.revision_add([data.revision]) swh_storage.release_add([data.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 + 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): cont = data.cont.copy() - del cont['data'] + del cont["data"] now = datetime.datetime.now(tz=datetime.timezone.utc) - cont['ctime'] = now + cont["ctime"] = now swh_storage.content_add_metadata([cont]) - actually_present = swh_storage.content_find({'sha1': cont['sha1']}) + actually_present = swh_storage.content_find({"sha1": cont["sha1"]}) # check ctime up to one second - dt = actually_present[0]['ctime'] - now + dt = actually_present[0]["ctime"] - now assert abs(dt.total_seconds()) <= 1 - del actually_present[0]['ctime'] + del actually_present[0]["ctime"] assert actually_present[0] == { - 'sha1': cont['sha1'], - 'sha256': cont['sha256'], - 'sha1_git': cont['sha1_git'], - 'blake2s256': cont['blake2s256'], - 'length': cont['length'], - 'status': 'visible' + "sha1": cont["sha1"], + "sha256": cont["sha256"], + "sha1_git": cont["sha1_git"], + "blake2s256": cont["blake2s256"], + "length": cont["length"], + "status": "visible", } def test_content_find_with_present_content(self, swh_storage): # 1. with something to find cont = data.cont swh_storage.content_add([cont, data.cont2]) - actually_present = swh_storage.content_find( - {'sha1': cont['sha1']} - ) + actually_present = swh_storage.content_find({"sha1": cont["sha1"]}) assert 1 == len(actually_present) - actually_present[0].pop('ctime') + actually_present[0].pop("ctime") assert actually_present[0] == { - 'sha1': cont['sha1'], - 'sha256': cont['sha256'], - 'sha1_git': cont['sha1_git'], - 'blake2s256': cont['blake2s256'], - 'length': cont['length'], - 'status': 'visible' - } + "sha1": cont["sha1"], + "sha256": cont["sha256"], + "sha1_git": cont["sha1_git"], + "blake2s256": cont["blake2s256"], + "length": cont["length"], + "status": "visible", + } # 2. with something to find - actually_present = swh_storage.content_find( - {'sha1_git': cont['sha1_git']}) + actually_present = swh_storage.content_find({"sha1_git": cont["sha1_git"]}) assert 1 == len(actually_present) - actually_present[0].pop('ctime') + actually_present[0].pop("ctime") assert actually_present[0] == { - 'sha1': cont['sha1'], - 'sha256': cont['sha256'], - 'sha1_git': cont['sha1_git'], - 'blake2s256': cont['blake2s256'], - 'length': cont['length'], - 'status': 'visible' - } + "sha1": cont["sha1"], + "sha256": cont["sha256"], + "sha1_git": cont["sha1_git"], + "blake2s256": cont["blake2s256"], + "length": cont["length"], + "status": "visible", + } # 3. with something to find - actually_present = swh_storage.content_find( - {'sha256': cont['sha256']}) + actually_present = swh_storage.content_find({"sha256": cont["sha256"]}) assert 1 == len(actually_present) - actually_present[0].pop('ctime') + actually_present[0].pop("ctime") assert actually_present[0] == { - 'sha1': cont['sha1'], - 'sha256': cont['sha256'], - 'sha1_git': cont['sha1_git'], - 'blake2s256': cont['blake2s256'], - 'length': cont['length'], - 'status': 'visible' - } + "sha1": cont["sha1"], + "sha256": cont["sha256"], + "sha1_git": cont["sha1_git"], + "blake2s256": cont["blake2s256"], + "length": cont["length"], + "status": "visible", + } # 4. with something to find - actually_present = swh_storage.content_find({ - 'sha1': cont['sha1'], - 'sha1_git': cont['sha1_git'], - 'sha256': cont['sha256'], - 'blake2s256': cont['blake2s256'], - }) + actually_present = swh_storage.content_find( + { + "sha1": cont["sha1"], + "sha1_git": cont["sha1_git"], + "sha256": cont["sha256"], + "blake2s256": cont["blake2s256"], + } + ) assert 1 == len(actually_present) - actually_present[0].pop('ctime') + actually_present[0].pop("ctime") assert actually_present[0] == { - 'sha1': cont['sha1'], - 'sha256': cont['sha256'], - 'sha1_git': cont['sha1_git'], - 'blake2s256': cont['blake2s256'], - 'length': cont['length'], - 'status': 'visible' - } + "sha1": cont["sha1"], + "sha256": cont["sha256"], + "sha1_git": cont["sha1_git"], + "blake2s256": cont["blake2s256"], + "length": cont["length"], + "status": "visible", + } def test_content_find_with_non_present_content(self, swh_storage): # 1. with something that does not exist missing_cont = data.missing_cont - actually_present = swh_storage.content_find( - {'sha1': missing_cont['sha1']}) + actually_present = swh_storage.content_find({"sha1": missing_cont["sha1"]}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( - {'sha1_git': missing_cont['sha1_git']}) + {"sha1_git": missing_cont["sha1_git"]} + ) assert actually_present == [] # 3. with something that does not exist - actually_present = swh_storage.content_find( - {'sha256': missing_cont['sha256']}) + actually_present = swh_storage.content_find({"sha256": missing_cont["sha256"]}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 - sha1_array = bytearray(duplicate_cont['sha1']) + sha1_array = bytearray(duplicate_cont["sha1"]) sha1_array[0] += 1 - duplicate_cont['sha1'] = bytes(sha1_array) - sha1git_array = bytearray(duplicate_cont['sha1_git']) + duplicate_cont["sha1"] = bytes(sha1_array) + sha1git_array = bytearray(duplicate_cont["sha1_git"]) sha1git_array[0] += 1 - duplicate_cont['sha1_git'] = bytes(sha1git_array) + duplicate_cont["sha1_git"] = bytes(sha1git_array) # Inject the data swh_storage.content_add([cont1, duplicate_cont]) - finder = {'blake2s256': duplicate_cont['blake2s256'], - 'sha256': duplicate_cont['sha256']} + finder = { + "blake2s256": duplicate_cont["blake2s256"], + "sha256": duplicate_cont["sha256"], + } actual_result = list(swh_storage.content_find(finder)) - cont1.pop('data') - duplicate_cont.pop('data') - actual_result[0].pop('ctime') - actual_result[1].pop('ctime') + cont1.pop("data") + duplicate_cont.pop("data") + actual_result[0].pop("ctime") + actual_result[1].pop("ctime") - expected_result = [ - cont1, duplicate_cont - ] + expected_result = [cont1, duplicate_cont] for result in expected_result: assert result in actual_result def test_content_find_with_duplicate_sha256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 - for hashalgo in ('sha1', 'sha1_git', 'blake2s256'): + for hashalgo in ("sha1", "sha1_git", "blake2s256"): value = bytearray(duplicate_cont[hashalgo]) value[0] += 1 duplicate_cont[hashalgo] = bytes(value) swh_storage.content_add([cont1, duplicate_cont]) - finder = { - 'sha256': duplicate_cont['sha256'] - } + finder = {"sha256": duplicate_cont["sha256"]} actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 2 - cont1.pop('data') - duplicate_cont.pop('data') - actual_result[0].pop('ctime') - actual_result[1].pop('ctime') - expected_result = [ - cont1, duplicate_cont - ] - assert expected_result == sorted(actual_result, - key=lambda x: x['sha1']) + cont1.pop("data") + duplicate_cont.pop("data") + actual_result[0].pop("ctime") + actual_result[1].pop("ctime") + expected_result = [cont1, duplicate_cont] + assert expected_result == sorted(actual_result, key=lambda x: x["sha1"]) # Find with both sha256 and blake2s256 finder = { - 'sha256': duplicate_cont['sha256'], - 'blake2s256': duplicate_cont['blake2s256'] + "sha256": duplicate_cont["sha256"], + "blake2s256": duplicate_cont["blake2s256"], } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 1 - actual_result[0].pop('ctime') + actual_result[0].pop("ctime") expected_result = [duplicate_cont] assert actual_result[0] == duplicate_cont def test_content_find_with_duplicate_blake2s256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 - sha1_array = bytearray(duplicate_cont['sha1']) + sha1_array = bytearray(duplicate_cont["sha1"]) sha1_array[0] += 1 - duplicate_cont['sha1'] = bytes(sha1_array) - sha1git_array = bytearray(duplicate_cont['sha1_git']) + duplicate_cont["sha1"] = bytes(sha1_array) + sha1git_array = bytearray(duplicate_cont["sha1_git"]) sha1git_array[0] += 1 - duplicate_cont['sha1_git'] = bytes(sha1git_array) - sha256_array = bytearray(duplicate_cont['sha256']) + duplicate_cont["sha1_git"] = bytes(sha1git_array) + sha256_array = bytearray(duplicate_cont["sha256"]) sha256_array[0] += 1 - duplicate_cont['sha256'] = bytes(sha256_array) + duplicate_cont["sha256"] = bytes(sha256_array) swh_storage.content_add([cont1, duplicate_cont]) - finder = { - 'blake2s256': duplicate_cont['blake2s256'] - } + finder = {"blake2s256": duplicate_cont["blake2s256"]} actual_result = list(swh_storage.content_find(finder)) - cont1.pop('data') - duplicate_cont.pop('data') - actual_result[0].pop('ctime') - actual_result[1].pop('ctime') - expected_result = [ - cont1, duplicate_cont - ] + cont1.pop("data") + duplicate_cont.pop("data") + actual_result[0].pop("ctime") + actual_result[1].pop("ctime") + expected_result = [cont1, duplicate_cont] for result in expected_result: assert result in actual_result # Find with both sha256 and blake2s256 finder = { - 'sha256': duplicate_cont['sha256'], - 'blake2s256': duplicate_cont['blake2s256'] + "sha256": duplicate_cont["sha256"], + "blake2s256": duplicate_cont["blake2s256"], } actual_result = list(swh_storage.content_find(finder)) - actual_result[0].pop('ctime') + actual_result[0].pop("ctime") - expected_result = [ - duplicate_cont - ] + expected_result = [duplicate_cont] assert expected_result == actual_result def test_content_find_bad_input(self, swh_storage): # 1. with bad input with pytest.raises(StorageArgumentException): swh_storage.content_find({}) # empty is bad # 2. with bad input with pytest.raises(StorageArgumentException): - swh_storage.content_find( - {'unknown-sha1': 'something'}) # not the right key + swh_storage.content_find({"unknown-sha1": "something"}) # not the right key def test_object_find_by_sha1_git(self, swh_storage): - sha1_gits = [b'00000000000000000000'] + sha1_gits = [b"00000000000000000000"] expected = { - b'00000000000000000000': [], + b"00000000000000000000": [], } swh_storage.content_add([data.cont]) - sha1_gits.append(data.cont['sha1_git']) - expected[data.cont['sha1_git']] = [{ - 'sha1_git': data.cont['sha1_git'], - 'type': 'content', - }] + sha1_gits.append(data.cont["sha1_git"]) + expected[data.cont["sha1_git"]] = [ + {"sha1_git": data.cont["sha1_git"], "type": "content",} + ] swh_storage.directory_add([data.dir]) - sha1_gits.append(data.dir['id']) - expected[data.dir['id']] = [{ - 'sha1_git': data.dir['id'], - 'type': 'directory', - }] + sha1_gits.append(data.dir["id"]) + expected[data.dir["id"]] = [{"sha1_git": data.dir["id"], "type": "directory",}] swh_storage.revision_add([data.revision]) - sha1_gits.append(data.revision['id']) - expected[data.revision['id']] = [{ - 'sha1_git': data.revision['id'], - 'type': 'revision', - }] + sha1_gits.append(data.revision["id"]) + expected[data.revision["id"]] = [ + {"sha1_git": data.revision["id"], "type": "revision",} + ] swh_storage.release_add([data.release]) - sha1_gits.append(data.release['id']) - expected[data.release['id']] = [{ - 'sha1_git': data.release['id'], - 'type': 'release', - }] + sha1_gits.append(data.release["id"]) + expected[data.release["id"]] = [ + {"sha1_git": data.release["id"], "type": "release",} + ] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_tool_add(self, swh_storage): tool = { - 'name': 'some-unknown-tool', - 'version': 'some-version', - 'configuration': {"debian-package": "some-package"}, + "name": "some-unknown-tool", + "version": "some-version", + "configuration": {"debian-package": "some-package"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None # does not exist # add it actual_tools = swh_storage.tool_add([tool]) assert len(actual_tools) == 1 actual_tool = actual_tools[0] assert actual_tool is not None # now it exists - new_id = actual_tool.pop('id') + new_id = actual_tool.pop("id") assert actual_tool == tool actual_tools2 = swh_storage.tool_add([tool]) actual_tool2 = actual_tools2[0] assert actual_tool2 is not None # now it exists - new_id2 = actual_tool2.pop('id') + new_id2 = actual_tool2.pop("id") assert new_id == new_id2 assert actual_tool == actual_tool2 def test_tool_add_multiple(self, swh_storage): tool = { - 'name': 'some-unknown-tool', - 'version': 'some-version', - 'configuration': {"debian-package": "some-package"}, + "name": "some-unknown-tool", + "version": "some-version", + "configuration": {"debian-package": "some-package"}, } actual_tools = list(swh_storage.tool_add([tool])) assert len(actual_tools) == 1 - new_tools = [tool, { - 'name': 'yet-another-tool', - 'version': 'version', - 'configuration': {}, - }] + new_tools = [ + tool, + {"name": "yet-another-tool", "version": "version", "configuration": {},}, + ] actual_tools = swh_storage.tool_add(new_tools) assert len(actual_tools) == 2 # order not guaranteed, so we iterate over results to check for tool in actual_tools: - _id = tool.pop('id') + _id = tool.pop("id") assert _id is not None assert tool in new_tools def test_tool_get_missing(self, swh_storage): tool = { - 'name': 'unknown-tool', - 'version': '3.1.0rc2-31-ga2cbb8c', - 'configuration': {"command_line": "nomossa "}, + "name": "unknown-tool", + "version": "3.1.0rc2-31-ga2cbb8c", + "configuration": {"command_line": "nomossa "}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get_missing_context(self, swh_storage): tool = { - 'name': 'swh-metadata-translator', - 'version': '0.0.1', - 'configuration': {"context": "unknown-context"}, + "name": "swh-metadata-translator", + "version": "0.0.1", + "configuration": {"context": "unknown-context"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get(self, swh_storage): tool = { - 'name': 'swh-metadata-translator', - 'version': '0.0.1', - 'configuration': {"type": "local", "context": "npm"}, + "name": "swh-metadata-translator", + "version": "0.0.1", + "configuration": {"type": "local", "context": "npm"}, } expected_tool = swh_storage.tool_add([tool])[0] # when actual_tool = swh_storage.tool_get(tool) # then assert expected_tool == actual_tool def test_metadata_provider_get(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get(6459456445615) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( - data.provider['name'], - data.provider['type'], - data.provider['url'], - data.provider['metadata']) + data.provider["name"], + data.provider["type"], + data.provider["url"], + data.provider["metadata"], + ) actual_provider = swh_storage.metadata_provider_get(provider_id) expected_provider = { - 'provider_name': data.provider['name'], - 'provider_url': data.provider['url'] + "provider_name": data.provider["name"], + "provider_url": data.provider["url"], } # then - del actual_provider['id'] + del actual_provider["id"] assert actual_provider, expected_provider def test_metadata_provider_get_by(self, swh_storage): # given - no_provider = swh_storage.metadata_provider_get_by({ - 'provider_name': data.provider['name'], - 'provider_url': data.provider['url'] - }) + no_provider = swh_storage.metadata_provider_get_by( + { + "provider_name": data.provider["name"], + "provider_url": data.provider["url"], + } + ) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( - data.provider['name'], - data.provider['type'], - data.provider['url'], - data.provider['metadata']) - - actual_provider = swh_storage.metadata_provider_get_by({ - 'provider_name': data.provider['name'], - 'provider_url': data.provider['url'] - }) + data.provider["name"], + data.provider["type"], + data.provider["url"], + data.provider["metadata"], + ) + + actual_provider = swh_storage.metadata_provider_get_by( + { + "provider_name": data.provider["name"], + "provider_url": data.provider["url"], + } + ) # then - assert provider_id, actual_provider['id'] + assert provider_id, actual_provider["id"] def test_origin_metadata_add(self, swh_storage): # given origin = data.origin swh_storage.origin_add([origin])[0] tools = swh_storage.tool_add([data.metadata_tool]) tool = tools[0] swh_storage.metadata_provider_add( - data.provider['name'], - data.provider['type'], - data.provider['url'], - data.provider['metadata']) - provider = swh_storage.metadata_provider_get_by({ - 'provider_name': data.provider['name'], - 'provider_url': data.provider['url'] - }) + data.provider["name"], + data.provider["type"], + data.provider["url"], + data.provider["metadata"], + ) + provider = swh_storage.metadata_provider_get_by( + { + "provider_name": data.provider["name"], + "provider_url": data.provider["url"], + } + ) # when adding for the same origin 2 metadatas - n_om = len(list(swh_storage.origin_metadata_get_by(origin['url']))) + n_om = len(list(swh_storage.origin_metadata_get_by(origin["url"]))) swh_storage.origin_metadata_add( - origin['url'], - data.origin_metadata['discovery_date'], - provider['id'], - tool['id'], - data.origin_metadata['metadata']) + origin["url"], + data.origin_metadata["discovery_date"], + provider["id"], + tool["id"], + data.origin_metadata["metadata"], + ) swh_storage.origin_metadata_add( - origin['url'], - '2015-01-01 23:00:00+00', - provider['id'], - tool['id'], - data.origin_metadata2['metadata']) - n_actual_om = len(list( - swh_storage.origin_metadata_get_by(origin['url']))) + origin["url"], + "2015-01-01 23:00:00+00", + provider["id"], + tool["id"], + data.origin_metadata2["metadata"], + ) + n_actual_om = len(list(swh_storage.origin_metadata_get_by(origin["url"]))) # then assert n_actual_om == n_om + 2 def test_origin_metadata_get(self, swh_storage): # given - origin_url = data.origin['url'] - origin_url2 = data.origin2['url'] + origin_url = data.origin["url"] + origin_url2 = data.origin2["url"] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) - swh_storage.metadata_provider_add(data.provider['name'], - data.provider['type'], - data.provider['url'], - data.provider['metadata']) - provider = swh_storage.metadata_provider_get_by({ - 'provider_name': data.provider['name'], - 'provider_url': data.provider['url'] - }) + swh_storage.metadata_provider_add( + data.provider["name"], + data.provider["type"], + data.provider["url"], + data.provider["metadata"], + ) + provider = swh_storage.metadata_provider_get_by( + { + "provider_name": data.provider["name"], + "provider_url": data.provider["url"], + } + ) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( - origin_url, - data.origin_metadata['discovery_date'], - provider['id'], - tool['id'], - data.origin_metadata['metadata']) + origin_url, + data.origin_metadata["discovery_date"], + provider["id"], + tool["id"], + data.origin_metadata["metadata"], + ) swh_storage.origin_metadata_add( - origin_url2, - data.origin_metadata2['discovery_date'], - provider['id'], - tool['id'], - data.origin_metadata2['metadata']) + origin_url2, + data.origin_metadata2["discovery_date"], + provider["id"], + tool["id"], + data.origin_metadata2["metadata"], + ) swh_storage.origin_metadata_add( - origin_url, - data.origin_metadata2['discovery_date'], - provider['id'], - tool['id'], - data.origin_metadata2['metadata']) - all_metadatas = list(sorted(swh_storage.origin_metadata_get_by( - origin_url), key=lambda x: x['discovery_date'])) - metadatas_for_origin2 = list(swh_storage.origin_metadata_get_by( - origin_url2)) - expected_results = [{ - 'origin_url': origin_url, - 'discovery_date': datetime.datetime( - 2015, 1, 1, 23, 0, - tzinfo=datetime.timezone.utc), - 'metadata': { - 'name': 'test_origin_metadata', - 'version': '0.0.1' + origin_url, + data.origin_metadata2["discovery_date"], + provider["id"], + tool["id"], + data.origin_metadata2["metadata"], + ) + all_metadatas = list( + sorted( + swh_storage.origin_metadata_get_by(origin_url), + key=lambda x: x["discovery_date"], + ) + ) + metadatas_for_origin2 = list(swh_storage.origin_metadata_get_by(origin_url2)) + expected_results = [ + { + "origin_url": origin_url, + "discovery_date": datetime.datetime( + 2015, 1, 1, 23, 0, tzinfo=datetime.timezone.utc + ), + "metadata": {"name": "test_origin_metadata", "version": "0.0.1"}, + "provider_id": provider["id"], + "provider_name": "hal", + "provider_type": "deposit-client", + "provider_url": "http:///hal/inria", + "tool_id": tool["id"], }, - 'provider_id': provider['id'], - 'provider_name': 'hal', - 'provider_type': 'deposit-client', - 'provider_url': 'http:///hal/inria', - 'tool_id': tool['id'] - }, { - 'origin_url': origin_url, - 'discovery_date': datetime.datetime( - 2017, 1, 1, 23, 0, - tzinfo=datetime.timezone.utc), - 'metadata': { - 'name': 'test_origin_metadata', - 'version': '0.0.1' + { + "origin_url": origin_url, + "discovery_date": datetime.datetime( + 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc + ), + "metadata": {"name": "test_origin_metadata", "version": "0.0.1"}, + "provider_id": provider["id"], + "provider_name": "hal", + "provider_type": "deposit-client", + "provider_url": "http:///hal/inria", + "tool_id": tool["id"], }, - 'provider_id': provider['id'], - 'provider_name': 'hal', - 'provider_type': 'deposit-client', - 'provider_url': 'http:///hal/inria', - 'tool_id': tool['id'] - }] + ] # then assert len(all_metadatas) == 2 assert len(metadatas_for_origin2) == 1 assert all_metadatas == expected_results def test_metadata_provider_add(self, swh_storage): provider = { - 'provider_name': 'swMATH', - 'provider_type': 'registry', - 'provider_url': 'http://www.swmath.org/', - 'metadata': { - 'email': 'contact@swmath.org', - 'license': 'All rights reserved' - } + "provider_name": "swMATH", + "provider_type": "registry", + "provider_url": "http://www.swmath.org/", + "metadata": { + "email": "contact@swmath.org", + "license": "All rights reserved", + }, } - provider['id'] = provider_id = swh_storage.metadata_provider_add( - **provider) + provider["id"] = provider_id = swh_storage.metadata_provider_add(**provider) assert provider == swh_storage.metadata_provider_get_by( - {'provider_name': 'swMATH', - 'provider_url': 'http://www.swmath.org/'}) + {"provider_name": "swMATH", "provider_url": "http://www.swmath.org/"} + ) assert provider == swh_storage.metadata_provider_get(provider_id) def test_origin_metadata_get_by_provider_type(self, swh_storage): # given - origin_url = data.origin['url'] - origin_url2 = data.origin2['url'] + origin_url = data.origin["url"] + origin_url2 = data.origin2["url"] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) provider1_id = swh_storage.metadata_provider_add( - data.provider['name'], - data.provider['type'], - data.provider['url'], - data.provider['metadata']) - provider1 = swh_storage.metadata_provider_get_by({ - 'provider_name': data.provider['name'], - 'provider_url': data.provider['url'] - }) + data.provider["name"], + data.provider["type"], + data.provider["url"], + data.provider["metadata"], + ) + provider1 = swh_storage.metadata_provider_get_by( + { + "provider_name": data.provider["name"], + "provider_url": data.provider["url"], + } + ) assert provider1 == swh_storage.metadata_provider_get(provider1_id) provider2_id = swh_storage.metadata_provider_add( - 'swMATH', - 'registry', - 'http://www.swmath.org/', - {'email': 'contact@swmath.org', - 'license': 'All rights reserved'}) - provider2 = swh_storage.metadata_provider_get_by({ - 'provider_name': 'swMATH', - 'provider_url': 'http://www.swmath.org/' - }) + "swMATH", + "registry", + "http://www.swmath.org/", + {"email": "contact@swmath.org", "license": "All rights reserved"}, + ) + provider2 = swh_storage.metadata_provider_get_by( + {"provider_name": "swMATH", "provider_url": "http://www.swmath.org/"} + ) assert provider2 == swh_storage.metadata_provider_get(provider2_id) # using the only tool now inserted in the data.sql, but for this # provider should be a crawler tool (not yet implemented) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( origin_url, - data.origin_metadata['discovery_date'], - provider1['id'], - tool['id'], - data.origin_metadata['metadata']) + data.origin_metadata["discovery_date"], + provider1["id"], + tool["id"], + data.origin_metadata["metadata"], + ) swh_storage.origin_metadata_add( origin_url2, - data.origin_metadata2['discovery_date'], - provider2['id'], - tool['id'], - data.origin_metadata2['metadata']) - provider_type = 'registry' - m_by_provider = list(swh_storage.origin_metadata_get_by( - origin_url2, - provider_type)) + data.origin_metadata2["discovery_date"], + provider2["id"], + tool["id"], + data.origin_metadata2["metadata"], + ) + provider_type = "registry" + m_by_provider = list( + swh_storage.origin_metadata_get_by(origin_url2, provider_type) + ) for item in m_by_provider: - if 'id' in item: - del item['id'] - expected_results = [{ - 'origin_url': origin_url2, - 'discovery_date': datetime.datetime( - 2017, 1, 1, 23, 0, - tzinfo=datetime.timezone.utc), - 'metadata': { - 'name': 'test_origin_metadata', - 'version': '0.0.1' - }, - 'provider_id': provider2['id'], - 'provider_name': 'swMATH', - 'provider_type': provider_type, - 'provider_url': 'http://www.swmath.org/', - 'tool_id': tool['id'] - }] + if "id" in item: + del item["id"] + expected_results = [ + { + "origin_url": origin_url2, + "discovery_date": datetime.datetime( + 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc + ), + "metadata": {"name": "test_origin_metadata", "version": "0.0.1"}, + "provider_id": provider2["id"], + "provider_name": "swMATH", + "provider_type": provider_type, + "provider_url": "http://www.swmath.org/", + "tool_id": tool["id"], + } + ] # then assert len(m_by_provider) == 1 assert m_by_provider == expected_results class TestStorageGeneratedData: def test_generate_content_get(self, swh_storage, swh_contents): - contents_with_data = [c for c in swh_contents - if c['status'] != 'absent'] + contents_with_data = [c for c in swh_contents if c["status"] != "absent"] # input the list of sha1s we want from storage - get_sha1s = [c['sha1'] for c in contents_with_data] + get_sha1s = [c["sha1"] for c in contents_with_data] # retrieve contents actual_contents = list(swh_storage.content_get(get_sha1s)) assert None not in actual_contents assert_contents_ok(contents_with_data, actual_contents) def test_generate_content_get_metadata(self, swh_storage, swh_contents): # input the list of sha1s we want from storage - expected_contents = [c for c in swh_contents - if c['status'] != 'absent'] - get_sha1s = [c['sha1'] for c in expected_contents] + expected_contents = [c for c in swh_contents if c["status"] != "absent"] + get_sha1s = [c["sha1"] for c in expected_contents] # retrieve contents meta_contents = swh_storage.content_get_metadata(get_sha1s) assert len(list(meta_contents)) == len(get_sha1s) actual_contents = [] for contents in meta_contents.values(): actual_contents.extend(contents) - keys_to_check = {'length', 'status', - 'sha1', 'sha1_git', 'sha256', 'blake2s256'} + keys_to_check = {"length", "status", "sha1", "sha1_git", "sha256", "blake2s256"} - assert_contents_ok(expected_contents, actual_contents, - keys_to_check=keys_to_check) + assert_contents_ok( + expected_contents, actual_contents, keys_to_check=keys_to_check + ) def test_generate_content_get_range(self, swh_storage, swh_contents): """content_get_range returns complete range""" - present_contents = [c for c in swh_contents - if c['status'] != 'absent'] + present_contents = [c for c in swh_contents if c["status"] != "absent"] - get_sha1s = sorted([c['sha1'] for c in swh_contents - if c['status'] != 'absent']) + get_sha1s = sorted([c["sha1"] for c in swh_contents if c["status"] != "absent"]) start = get_sha1s[2] end = get_sha1s[-2] actual_result = swh_storage.content_get_range(start, end) - assert actual_result['next'] is None + assert actual_result["next"] is None - actual_contents = actual_result['contents'] - expected_contents = [c for c in present_contents - if start <= c['sha1'] <= end] + actual_contents = actual_result["contents"] + expected_contents = [c for c in present_contents if start <= c["sha1"] <= end] if expected_contents: - assert_contents_ok( - expected_contents, actual_contents, ['sha1']) + assert_contents_ok(expected_contents, actual_contents, ["sha1"]) else: assert actual_contents == [] def test_generate_content_get_range_full(self, swh_storage, swh_contents): """content_get_range for a full range returns all available contents""" - present_contents = [c for c in swh_contents - if c['status'] != 'absent'] + present_contents = [c for c in swh_contents if c["status"] != "absent"] - start = b'0' * 40 - end = b'f' * 40 + start = b"0" * 40 + end = b"f" * 40 actual_result = swh_storage.content_get_range(start, end) - assert actual_result['next'] is None + assert actual_result["next"] is None - actual_contents = actual_result['contents'] - expected_contents = [c for c in present_contents - if start <= c['sha1'] <= end] + actual_contents = actual_result["contents"] + expected_contents = [c for c in present_contents if start <= c["sha1"] <= end] if expected_contents: - assert_contents_ok( - expected_contents, actual_contents, ['sha1']) + assert_contents_ok(expected_contents, actual_contents, ["sha1"]) else: assert actual_contents == [] def test_generate_content_get_range_empty(self, swh_storage, swh_contents): """content_get_range for an empty range returns nothing""" - start = b'0' * 40 - end = b'f' * 40 + start = b"0" * 40 + end = b"f" * 40 actual_result = swh_storage.content_get_range(end, start) - assert actual_result['next'] is None - assert len(actual_result['contents']) == 0 + assert actual_result["next"] is None + assert len(actual_result["contents"]) == 0 def test_generate_content_get_range_limit_none(self, swh_storage): """content_get_range call with wrong limit input should fail""" with pytest.raises(StorageArgumentException) as e: swh_storage.content_get_range(start=None, end=None, limit=None) - assert e.value.args == ('limit should not be None',) + assert e.value.args == ("limit should not be None",) - def test_generate_content_get_range_no_limit( - self, swh_storage, swh_contents): + def test_generate_content_get_range_no_limit(self, swh_storage, swh_contents): """content_get_range returns contents within range provided""" # input the list of sha1s we want from storage - get_sha1s = sorted([c['sha1'] for c in swh_contents - if c['status'] != 'absent']) + get_sha1s = sorted([c["sha1"] for c in swh_contents if c["status"] != "absent"]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = swh_storage.content_get_range(start, end) - actual_contents = actual_result['contents'] - assert actual_result['next'] is None + actual_contents = actual_result["contents"] + assert actual_result["next"] is None assert len(actual_contents) == len(get_sha1s) - expected_contents = [c for c in swh_contents - if c['status'] != 'absent'] - assert_contents_ok( - expected_contents, actual_contents, ['sha1']) + expected_contents = [c for c in swh_contents if c["status"] != "absent"] + assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_generate_content_get_range_limit(self, swh_storage, swh_contents): """content_get_range paginates results if limit exceeded""" - contents_map = {c['sha1']: c for c in swh_contents} + contents_map = {c["sha1"]: c for c in swh_contents} # input the list of sha1s we want from storage - get_sha1s = sorted([c['sha1'] for c in swh_contents - if c['status'] != 'absent']) + get_sha1s = sorted([c["sha1"] for c in swh_contents if c["status"] != "absent"]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to n-1 results limited_results = len(get_sha1s) - 1 - actual_result = swh_storage.content_get_range( - start, end, limit=limited_results) + actual_result = swh_storage.content_get_range(start, end, limit=limited_results) - actual_contents = actual_result['contents'] - assert actual_result['next'] == get_sha1s[-1] + actual_contents = actual_result["contents"] + assert actual_result["next"] == get_sha1s[-1] assert len(actual_contents) == limited_results expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] - assert_contents_ok( - expected_contents, actual_contents, ['sha1']) + assert_contents_ok(expected_contents, actual_contents, ["sha1"]) # retrieve next part actual_results2 = swh_storage.content_get_range(start=end, end=end) - assert actual_results2['next'] is None - actual_contents2 = actual_results2['contents'] + assert actual_results2["next"] is None + actual_contents2 = actual_results2["contents"] assert len(actual_contents2) == 1 - assert_contents_ok( - [contents_map[get_sha1s[-1]]], actual_contents2, ['sha1']) + assert_contents_ok([contents_map[get_sha1s[-1]]], actual_contents2, ["sha1"]) def test_origin_get_range_from_zero(self, swh_storage, swh_origins): actual_origins = list( - swh_storage.origin_get_range(origin_from=0, - origin_count=0)) + swh_storage.origin_get_range(origin_from=0, origin_count=0) + ) assert len(actual_origins) == 0 actual_origins = list( - swh_storage.origin_get_range(origin_from=0, - origin_count=1)) + swh_storage.origin_get_range(origin_from=0, origin_count=1) + ) assert len(actual_origins) == 1 - assert actual_origins[0]['id'] == 1 - assert actual_origins[0]['url'] == swh_origins[0]['url'] + assert actual_origins[0]["id"] == 1 + assert actual_origins[0]["url"] == swh_origins[0]["url"] - @pytest.mark.parametrize('origin_from,origin_count', [ - (1, 1), (1, 10), (1, 20), (1, 101), (11, 0), - (11, 10), (91, 11)]) + @pytest.mark.parametrize( + "origin_from,origin_count", + [(1, 1), (1, 10), (1, 20), (1, 101), (11, 0), (11, 10), (91, 11)], + ) def test_origin_get_range( - self, swh_storage, swh_origins, origin_from, origin_count): + self, swh_storage, swh_origins, origin_from, origin_count + ): actual_origins = list( - swh_storage.origin_get_range(origin_from=origin_from, - origin_count=origin_count)) + swh_storage.origin_get_range( + origin_from=origin_from, origin_count=origin_count + ) + ) origins_with_id = list(enumerate(swh_origins, start=1)) expected_origins = [ - { - 'url': origin['url'], - 'id': origin_id, - } - for (origin_id, origin) - in origins_with_id[origin_from-1:origin_from+origin_count-1] + {"url": origin["url"], "id": origin_id,} + for (origin_id, origin) in origins_with_id[ + origin_from - 1 : origin_from + origin_count - 1 + ] ] assert actual_origins == expected_origins - @pytest.mark.parametrize('limit', [1, 7, 10, 100, 1000]) + @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: - result = swh_storage.origin_list( - page_token=page_token, limit=limit) - assert len(result['origins']) <= limit + result = swh_storage.origin_list(page_token=page_token, limit=limit) + assert len(result["origins"]) <= limit - returned_origins.extend( - origin['url'] for origin in result['origins']) + returned_origins.extend(origin["url"] for origin in result["origins"]) i += 1 - page_token = result.get('next_page_token') + page_token = result.get("next_page_token") if page_token is None: - assert i*limit >= len(swh_origins) + assert i * limit >= len(swh_origins) break else: - assert len(result['origins']) == limit + assert len(result["origins"]) == limit - expected_origins = [origin['url'] for origin in swh_origins] + expected_origins = [origin["url"] for origin in swh_origins] assert sorted(returned_origins) == sorted(expected_origins) ORIGINS = [ - 'https://github.com/user1/repo1', - 'https://github.com/user2/repo1', - 'https://github.com/user3/repo1', - 'https://gitlab.com/user1/repo1', - 'https://gitlab.com/user2/repo1', - 'https://forge.softwareheritage.org/source/repo1', + "https://github.com/user1/repo1", + "https://github.com/user2/repo1", + "https://github.com/user3/repo1", + "https://gitlab.com/user1/repo1", + "https://gitlab.com/user2/repo1", + "https://forge.softwareheritage.org/source/repo1", ] def test_origin_count(self, swh_storage): - swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) + swh_storage.origin_add([{"url": url} for url in self.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 + 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): - swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) + swh_storage.origin_add([{"url": url} for url in self.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): - swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) + 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): + swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) - origin_url = 'https://github.com/user1/repo1' - swh_storage.origin_visit_add( - origin_url, date=now, type='git') + origin_url = "https://github.com/user1/repo1" + swh_storage.origin_visit_add(origin_url, date=now, type="git") - assert swh_storage.origin_count('github', with_visit=False) == 3 + 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("github", with_visit=True) == 0 - assert swh_storage.origin_count('gitlab', with_visit=False) == 2 + 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): - swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) + 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): + swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) swh_storage.snapshot_add([data.snapshot]) - origin_url = 'https://github.com/user1/repo1' - visit = swh_storage.origin_visit_add( - origin_url, date=now, type='git') + origin_url = "https://github.com/user1/repo1" + visit = swh_storage.origin_visit_add(origin_url, date=now, type="git") swh_storage.origin_visit_update( - origin_url, visit.visit, - status='ongoing', - snapshot=data.snapshot['id']) + origin_url, visit.visit, status="ongoing", snapshot=data.snapshot["id"] + ) - assert swh_storage.origin_count('github', with_visit=False) == 3 + 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", 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 + 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(), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: obj = obj.to_dict() - if obj_type == 'origin_visit': - origin_url = obj.pop('origin') - swh_storage.origin_add_one({'url': origin_url}) - if 'visit' in obj: - del obj['visit'] - swh_storage.origin_visit_add( - origin_url, obj['date'], obj['type']) - elif obj_type == 'origin_visit_update': + if obj_type == "origin_visit": + origin_url = obj.pop("origin") + swh_storage.origin_add_one({"url": origin_url}) + if "visit" in obj: + del obj["visit"] + swh_storage.origin_visit_add(origin_url, obj["date"], obj["type"]) + elif obj_type == "origin_visit_update": # internal object for now, they don't have a storage # endpoint yet continue else: - if obj_type == 'content' and obj['status'] == 'absent': - obj_type = 'skipped_content' - method = getattr(swh_storage, obj_type + '_add') + if obj_type == "content" and obj["status"] == "absent": + obj_type = "skipped_content" + method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" + # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self, swh_storage): swh_storage.objstorage.content_add = Mock( - side_effect=Exception('mocked broken objstorage') + side_effect=Exception("mocked broken objstorage") ) with pytest.raises(Exception) as e: swh_storage.content_add([data.cont]) - assert e.value.args == ('mocked broken objstorage',) + assert e.value.args == ("mocked broken objstorage",) missing = list(swh_storage.content_missing([data.cont])) - assert missing == [data.cont['sha1']] + assert missing == [data.cont["sha1"]] @pytest.mark.db class TestStorageRaceConditions: @pytest.mark.xfail def test_content_add_race(self, swh_storage): results = queue.Queue() def thread(): try: with db_transaction(swh_storage) as (db, cur): - ret = swh_storage.content_add([data.cont], db=db, - cur=cur) - results.put((threading.get_ident(), 'data', ret)) + ret = swh_storage.content_add([data.cont], db=db, cur=cur) + results.put((threading.get_ident(), "data", ret)) except Exception as e: - results.put((threading.get_ident(), 'exc', e)) + results.put((threading.get_ident(), "exc", e)) t1 = threading.Thread(target=thread) t2 = threading.Thread(target=thread) t1.start() # this avoids the race condition # import time # time.sleep(1) t2.start() t1.join() t2.join() r1 = results.get(block=False) r2 = results.get(block=False) with pytest.raises(queue.Empty): results.get(block=False) assert r1[0] != r2[0] - assert r1[1] == 'data', 'Got exception %r in Thread%s' % (r1[2], r1[0]) - assert r2[1] == 'data', 'Got exception %r in Thread%s' % (r2[2], r2[0]) + assert r1[1] == "data", "Got exception %r in Thread%s" % (r1[2], r1[0]) + assert r2[1] == "data", "Got exception %r in Thread%s" % (r2[2], r2[0]) @pytest.mark.db class TestPgStorage: """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update_with_new_cols(self, swh_storage): swh_storage.journal_writer.journal = None # TODO, not supported with db_transaction(swh_storage) as (_, cur): - cur.execute("""alter table content + cur.execute( + """alter table content add column test text default null, - add column test2 text default null""") + add column test2 text default null""" + ) cont = copy.deepcopy(data.cont2) swh_storage.content_add([cont]) - cont['test'] = 'value-1' - cont['test2'] = 'value-2' + cont["test"] = "value-1" + cont["test2"] = "value-2" - swh_storage.content_update([cont], keys=['test', 'test2']) + swh_storage.content_update([cont], keys=["test", "test2"]) with db_transaction(swh_storage) as (_, cur): cur.execute( - '''SELECT sha1, sha1_git, sha256, length, status, + """SELECT sha1, sha1_git, sha256, length, status, test, test2 - FROM content WHERE sha1 = %s''', - (cont['sha1'],)) + FROM content WHERE sha1 = %s""", + (cont["sha1"],), + ) datum = cur.fetchone() - assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], - cont['length'], 'visible', - cont['test'], cont['test2']) + assert datum == ( + cont["sha1"], + cont["sha1_git"], + cont["sha256"], + cont["length"], + "visible", + cont["test"], + cont["test2"], + ) with db_transaction(swh_storage) as (_, cur): - cur.execute("""alter table content drop column test, - drop column test2""") + cur.execute( + """alter table content drop column test, + drop column test2""" + ) def test_content_add_db(self, swh_storage): cont = data.cont actual_result = swh_storage.content_add([cont]) assert actual_result == { - 'content:add': 1, - 'content:add:bytes': cont['length'], - } + "content:add": 1, + "content:add:bytes": cont["length"], + } - if hasattr(swh_storage, 'objstorage'): - assert cont['sha1'] in swh_storage.objstorage.objstorage + if hasattr(swh_storage, "objstorage"): + assert cont["sha1"] in swh_storage.objstorage.objstorage with db_transaction(swh_storage) as (_, cur): - cur.execute('SELECT sha1, sha1_git, sha256, length, status' - ' FROM content WHERE sha1 = %s', - (cont['sha1'],)) + cur.execute( + "SELECT sha1, sha1_git, sha256, length, status" + " FROM content WHERE sha1 = %s", + (cont["sha1"],), + ) datum = cur.fetchone() - assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], - cont['length'], 'visible') + assert datum == ( + cont["sha1"], + cont["sha1_git"], + cont["sha256"], + cont["length"], + "visible", + ) expected_cont = cont.copy() - del expected_cont['data'] + del expected_cont["data"] journal_objects = list(swh_storage.journal_writer.journal.objects) for (obj_type, obj) in journal_objects: - del obj['ctime'] - assert journal_objects == [('content', expected_cont)] + del obj["ctime"] + assert journal_objects == [("content", expected_cont)] def test_content_add_metadata_db(self, swh_storage): cont = data.cont - del cont['data'] - cont['ctime'] = datetime.datetime.now() + del cont["data"] + cont["ctime"] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { - 'content:add': 1, - } + "content:add": 1, + } - if hasattr(swh_storage, 'objstorage'): - assert cont['sha1'] not in swh_storage.objstorage.objstorage + if hasattr(swh_storage, "objstorage"): + assert cont["sha1"] not in swh_storage.objstorage.objstorage with db_transaction(swh_storage) as (_, cur): - cur.execute('SELECT sha1, sha1_git, sha256, length, status' - ' FROM content WHERE sha1 = %s', - (cont['sha1'],)) + cur.execute( + "SELECT sha1, sha1_git, sha256, length, status" + " FROM content WHERE sha1 = %s", + (cont["sha1"],), + ) datum = cur.fetchone() - assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], - cont['length'], 'visible') + assert datum == ( + cont["sha1"], + cont["sha1_git"], + cont["sha256"], + cont["length"], + "visible", + ) - assert list(swh_storage.journal_writer.journal.objects) == [ - ('content', cont)] + assert list(swh_storage.journal_writer.journal.objects) == [("content", cont)] def test_skipped_content_add_db(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 - cont2['blake2s256'] = None + cont2["blake2s256"] = None actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) - assert 2 <= actual_result.pop('skipped_content:add') <= 3 + assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} with db_transaction(swh_storage) as (_, cur): - cur.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' - 'length, status, reason ' - 'FROM skipped_content ORDER BY sha1_git') + cur.execute( + "SELECT sha1, sha1_git, sha256, blake2s256, " + "length, status, reason " + "FROM skipped_content ORDER BY sha1_git" + ) dbdata = cur.fetchall() assert len(dbdata) == 2 - assert dbdata[0] == (cont['sha1'], cont['sha1_git'], cont['sha256'], - cont['blake2s256'], cont['length'], 'absent', - 'Content too long') + assert dbdata[0] == ( + cont["sha1"], + cont["sha1_git"], + cont["sha256"], + cont["blake2s256"], + cont["length"], + "absent", + "Content too long", + ) - assert dbdata[1] == (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], - cont2['blake2s256'], cont2['length'], 'absent', - 'Content too long') + assert dbdata[1] == ( + cont2["sha1"], + cont2["sha1_git"], + cont2["sha256"], + cont2["blake2s256"], + cont2["length"], + "absent", + "Content too long", + ) diff --git a/swh/storage/tests/test_utils.py b/swh/storage/tests/test_utils.py index 9e2fd435..a8c680fd 100644 --- a/swh/storage/tests/test_utils.py +++ b/swh/storage/tests/test_utils.py @@ -1,97 +1,107 @@ # 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 swh.model import hashutil from swh.storage.utils import ( - extract_collision_hash, content_hex_hashes, content_bytes_hashes + extract_collision_hash, + content_hex_hashes, + content_bytes_hashes, ) def test_extract_collision_hash(): for msg, expected_result in [ + ( + "Key (sha1)=(\\x34973274ccef6ab4dfaaf86599792fa9c3fe4689) ...", ( - 'Key (sha1)=(\\x34973274ccef6ab4dfaaf86599792fa9c3fe4689) ...', - ('sha1', hashutil.hash_to_bytes( - '34973274ccef6ab4dfaaf86599792fa9c3fe4689')), + "sha1", + hashutil.hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4689"), ), + ), + ( + "Key (sha1_git)=(\\x34973274ccef6ab4dfaaf86599792fa9c3fe4699) already exists", # noqa ( - 'Key (sha1_git)=(\\x34973274ccef6ab4dfaaf86599792fa9c3fe4699) already exists', # noqa - ('sha1_git', hashutil.hash_to_bytes( - '34973274ccef6ab4dfaaf86599792fa9c3fe4699')), + "sha1_git", + hashutil.hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4699"), ), + ), + ( + "Key (sha256)=(\\x673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a) ...", # noqa ( - 'Key (sha256)=(\\x673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a) ...', # noqa - ('sha256', hashutil.hash_to_bytes( - '673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a')) # noqa - ), + "sha256", + hashutil.hash_to_bytes( + "673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a" + ), + ), # noqa + ), + ( + "Key (blake2s)=(\\xd5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d) ...", # noqa ( - 'Key (blake2s)=(\\xd5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d) ...', # noqa - ('blake2s', hashutil.hash_to_bytes( - 'd5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d')) # noqa - ), + "blake2s", + hashutil.hash_to_bytes( + "d5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d" + ), + ), # noqa + ), ]: assert extract_collision_hash(msg) == expected_result - assert extract_collision_hash('Nothing matching') is None + assert extract_collision_hash("Nothing matching") is None def test_content_hex_hashes(): input_content = { "blake2s256": hashutil.hash_to_bytes( "8f677e3214ca8b2acad91884a1571ef3f12b786501f9a6bedfd6239d82095dd2" ), - "sha1_git": hashutil.hash_to_bytes( - "ba9aaa145ccd24ef760cf31c74d8f7ca1a2e47b0"), + "sha1_git": hashutil.hash_to_bytes("ba9aaa145ccd24ef760cf31c74d8f7ca1a2e47b0"), "sha256": hashutil.hash_to_bytes( "2bb787a73e37352f92383abe7e2902936d1059ad9f1ba6daaa9c1e58ee6970d0" ), - "sha1": hashutil.hash_to_bytes( - "38762cf7f55934b34d179ae6a4c80cadccbb7f0a"), + "sha1": hashutil.hash_to_bytes("38762cf7f55934b34d179ae6a4c80cadccbb7f0a"), } expected_content = { - "blake2s256": - "8f677e3214ca8b2acad91884a1571ef3f12b786501f9a6bedfd6239d82095dd2", + "blake2s256": ( + "8f677e3214ca8b2acad91884a1571ef3" "f12b786501f9a6bedfd6239d82095dd2" + ), "sha1_git": "ba9aaa145ccd24ef760cf31c74d8f7ca1a2e47b0", - "sha256": - "2bb787a73e37352f92383abe7e2902936d1059ad9f1ba6daaa9c1e58ee6970d0", - "sha1": "38762cf7f55934b34d179ae6a4c80cadccbb7f0a" + "sha256": "2bb787a73e37352f92383abe7e2902936d1059ad9f1ba6daaa9c1e58ee6970d0", + "sha1": "38762cf7f55934b34d179ae6a4c80cadccbb7f0a", } actual_content = content_hex_hashes(input_content) assert len(actual_content) == len(expected_content) for algo in hashutil.DEFAULT_ALGORITHMS: assert actual_content[algo] == expected_content[algo] def test_content_bytes_hashes(): input_content = { - "blake2s256": - "8f677e3214ca8b2acad91884a1571ef3f12b786501f9a6bedfd6239d82095dd2", + "blake2s256": ( + "8f677e3214ca8b2acad91884a1571ef3" "f12b786501f9a6bedfd6239d82095dd2" + ), "sha1_git": "ba9aaa145ccd24ef760cf31c74d8f7ca1a2e47b0", - "sha256": - "2bb787a73e37352f92383abe7e2902936d1059ad9f1ba6daaa9c1e58ee6970d0", - "sha1": "38762cf7f55934b34d179ae6a4c80cadccbb7f0a" + "sha256": "2bb787a73e37352f92383abe7e2902936d1059ad9f1ba6daaa9c1e58ee6970d0", + "sha1": "38762cf7f55934b34d179ae6a4c80cadccbb7f0a", } expected_content = { "blake2s256": hashutil.hash_to_bytes( "8f677e3214ca8b2acad91884a1571ef3f12b786501f9a6bedfd6239d82095dd2" ), - "sha1_git": hashutil.hash_to_bytes( - "ba9aaa145ccd24ef760cf31c74d8f7ca1a2e47b0"), + "sha1_git": hashutil.hash_to_bytes("ba9aaa145ccd24ef760cf31c74d8f7ca1a2e47b0"), "sha256": hashutil.hash_to_bytes( "2bb787a73e37352f92383abe7e2902936d1059ad9f1ba6daaa9c1e58ee6970d0" ), - "sha1": hashutil.hash_to_bytes( - "38762cf7f55934b34d179ae6a4c80cadccbb7f0a"), + "sha1": hashutil.hash_to_bytes("38762cf7f55934b34d179ae6a4c80cadccbb7f0a"), } actual_content = content_bytes_hashes(input_content) assert len(actual_content) == len(expected_content) for algo in hashutil.DEFAULT_ALGORITHMS: assert actual_content[algo] == expected_content[algo] diff --git a/swh/storage/utils.py b/swh/storage/utils.py index 83e7e9ba..72ba2823 100644 --- a/swh/storage/utils.py +++ b/swh/storage/utils.py @@ -1,93 +1,88 @@ # 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 re from datetime import datetime, timezone from typing import Dict, Optional, Tuple -from swh.model.hashutil import ( - hash_to_bytes, hash_to_hex, DEFAULT_ALGORITHMS -) +from swh.model.hashutil import hash_to_bytes, hash_to_hex, DEFAULT_ALGORITHMS def now() -> datetime: return datetime.now(tz=timezone.utc) def _is_power_of_two(n: int) -> bool: - return n > 0 and n & (n-1) == 0 + return n > 0 and n & (n - 1) == 0 def get_partition_bounds_bytes( - i: int, n: int, nb_bytes: int) -> Tuple[bytes, Optional[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') + 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.') + "partition index must be between 0 and the number of partitions." + ) - space_size = 1 << (nb_bytes*8) - partition_size = space_size//n + 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') + 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*' + pattern = r"\w* \((?P[^)]+)\)=\(\\x(?P[a-f0-9]+)\) \w*" result = re.match(pattern, error_message) if result: - hash_type = result.group('type') - hash_id = result.group('id') + 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 - } + 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 - } + return {algo: hash_to_bytes(content[algo]) for algo in DEFAULT_ALGORITHMS} diff --git a/swh/storage/validate.py b/swh/storage/validate.py index 8f2ed1cd..61077d57 100644 --- a/swh/storage/validate.py +++ b/swh/storage/validate.py @@ -1,102 +1,109 @@ # 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 datetime import contextlib from typing import Dict, Iterable, List from swh.model.model import ( - BaseModel, SkippedContent, Content, Directory, Revision, Release, Snapshot, - OriginVisit, Origin + BaseModel, + SkippedContent, + Content, + Directory, + Revision, + Release, + Snapshot, + OriginVisit, + Origin, ) from . import get_storage from .exc import StorageArgumentException VALIDATION_EXCEPTIONS = [ KeyError, TypeError, ValueError, ] @contextlib.contextmanager def convert_validation_exceptions(): """Catches validation errors arguments, and re-raises a StorageArgumentException.""" try: yield except tuple(VALIDATION_EXCEPTIONS) as e: raise StorageArgumentException(str(e)) class ValidatingProxyStorage: """Storage implementation converts dictionaries to swh-model objects before calling its backend, and back to dicts before returning results """ + def __init__(self, storage): self.storage = get_storage(**storage) def __getattr__(self, key): - if key == 'storage': + if key == "storage": raise AttributeError(key) return getattr(self.storage, key) def content_add(self, content: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): contents = [Content.from_dict(c) for c in content] return self.storage.content_add(contents) def content_add_metadata(self, content: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): contents = [Content.from_dict(c) for c in content] return self.storage.content_add_metadata(contents) def skipped_content_add(self, content: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): contents = [SkippedContent.from_dict(c) for c in content] return self.storage.skipped_content_add(contents) def directory_add(self, directories: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): directories = [Directory.from_dict(d) for d in directories] return self.storage.directory_add(directories) def revision_add(self, revisions: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): revisions = [Revision.from_dict(r) for r in revisions] return self.storage.revision_add(revisions) def release_add(self, releases: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): releases = [Release.from_dict(r) for r in releases] return self.storage.release_add(releases) def snapshot_add(self, snapshots: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): snapshots = [Snapshot.from_dict(s) for s in snapshots] return self.storage.snapshot_add(snapshots) def origin_visit_add( - self, origin_url: str, - date: datetime.datetime, - type: str) -> Dict[str, BaseModel]: + self, origin_url: str, date: datetime.datetime, type: str + ) -> Dict[str, BaseModel]: with convert_validation_exceptions(): - visit = OriginVisit(origin=origin_url, date=date, type=type, - status='ongoing', snapshot=None) - return self.storage.origin_visit_add( - visit.origin, visit.date, visit.type) + visit = OriginVisit( + origin=origin_url, date=date, type=type, status="ongoing", snapshot=None + ) + return self.storage.origin_visit_add(visit.origin, visit.date, visit.type) def origin_add(self, origins: Iterable[Dict]) -> List[Dict]: with convert_validation_exceptions(): origins = [Origin.from_dict(o) for o in origins] return self.storage.origin_add(origins) def origin_add_one(self, origin: Dict) -> int: with convert_validation_exceptions(): origin = Origin.from_dict(origin) return self.storage.origin_add_one(origin) diff --git a/swh/storage/writer.py b/swh/storage/writer.py index 85b908a2..2a78993f 100644 --- a/swh/storage/writer.py +++ b/swh/storage/writer.py @@ -1,102 +1,108 @@ # 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 Iterable, Union from attr import evolve from swh.model.model import ( - Origin, OriginVisit, Snapshot, Directory, Revision, Release, - Content, SkippedContent, + Origin, + OriginVisit, + Snapshot, + Directory, + Revision, + Release, + Content, + SkippedContent, ) 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') + "You need the swh.journal package to use the " + "journal_writer feature" + ) self.journal = get_journal_writer(**journal_writer) else: self.journal = None def content_add(self, contents: Iterable[Content]) -> None: """Add contents to the journal. Drop the data field if provided. """ if not self.journal: return contents = [evolve(item, data=None) for item in contents] - self.journal.write_additions('content', contents) + self.journal.write_additions("content", contents) def content_update(self, contents: Iterable[Content]) -> None: if not self.journal: return raise NotImplementedError( - 'content_update is not yet supported with a journal writer.') + "content_update is not yet supported with a journal writer." + ) - def content_add_metadata( - self, contents: Iterable[Content]) -> None: + def content_add_metadata(self, contents: Iterable[Content]) -> None: return self.content_add(contents) - def skipped_content_add( - self, contents: Iterable[SkippedContent]) -> None: + def skipped_content_add(self, contents: Iterable[SkippedContent]) -> None: if not self.journal: return - self.journal.write_additions('content', contents) + self.journal.write_additions("content", contents) def directory_add(self, directories: Iterable[Directory]) -> None: if not self.journal: return - self.journal.write_additions('directory', directories) + self.journal.write_additions("directory", directories) def revision_add(self, revisions: Iterable[Revision]) -> None: if not self.journal: return - self.journal.write_additions('revision', revisions) + self.journal.write_additions("revision", revisions) def release_add(self, releases: Iterable[Release]) -> None: if not self.journal: return - self.journal.write_additions('release', releases) + self.journal.write_additions("release", releases) - def snapshot_add( - self, snapshots: Union[Iterable[Snapshot], Snapshot]) -> None: + def snapshot_add(self, snapshots: Union[Iterable[Snapshot], Snapshot]) -> None: if not self.journal: return snaps = snapshots if isinstance(snapshots, list) else [snapshots] - self.journal.write_additions('snapshot', snaps) + self.journal.write_additions("snapshot", snaps) def origin_visit_add(self, visit: OriginVisit): if not self.journal: return - self.journal.write_addition('origin_visit', visit) + self.journal.write_addition("origin_visit", visit) def origin_visit_update(self, visit: OriginVisit): if not self.journal: return - self.journal.write_update('origin_visit', visit) + self.journal.write_update("origin_visit", visit) def origin_visit_upsert(self, visits: Iterable[OriginVisit]): if not self.journal: return - self.journal.write_additions('origin_visit', visits) + self.journal.write_additions("origin_visit", visits) def origin_add_one(self, origin: Origin): if not self.journal: return - self.journal.write_addition('origin', origin) + self.journal.write_addition("origin", origin) diff --git a/tox.ini b/tox.ini index fe5c8492..e82bc0ab 100644 --- a/tox.ini +++ b/tox.ini @@ -1,34 +1,41 @@ [tox] -envlist=flake8,mypy,py3 +envlist=black,flake8,mypy,py3 [testenv] extras = testing deps = pytest-cov dev: ipdb passenv = LOG_CASSANDRA commands = pytest \ !slow: --hypothesis-profile=fast \ slow: --hypothesis-profile=slow \ --cov={envsitepackagesdir}/swh/storage \ {envsitepackagesdir}/swh/storage \ --doctest-modules \ --cov-branch {posargs} +[testenv:black] +skip_install = true +deps = + black +commands = + {envpython} -m black --check swh + [testenv:flake8] skip_install = true deps = flake8 commands = {envpython} -m flake8 [testenv:mypy] extras = testing deps = mypy commands = mypy swh