diff --git a/.gitignore b/.gitignore index c5baade4c..63df7cfb6 100644 --- a/.gitignore +++ b/.gitignore @@ -1,9 +1,10 @@ *.pyc *.sw? *~ .coverage .eggs/ __pycache__ dist *.egg-info version.txt +.vscode/ diff --git a/.vscode/settings.json b/.vscode/settings.json deleted file mode 100644 index f5d2a49cd..000000000 --- a/.vscode/settings.json +++ /dev/null @@ -1,3 +0,0 @@ -{ - "restructuredtext.workspaceRoot": "/home/antoine/swh/swh-environment/swh-storage" -} \ No newline at end of file diff --git a/PKG-INFO b/PKG-INFO index 3333a7719..bd6051b6d 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,12 +1,12 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.0.99 +Version: 0.0.100 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Description: UNKNOWN Platform: UNKNOWN Provides-Extra: listener Provides-Extra: schemata diff --git a/debian/control b/debian/control index 868fad918..d30fc5864 100644 --- a/debian/control +++ b/debian/control @@ -1,50 +1,53 @@ Source: swh-storage Maintainer: Software Heritage developers Section: python Priority: optional Build-Depends: debhelper (>= 9), dh-python (>= 2), python3-aiohttp, python3-all, python3-click, python3-dateutil, python3-flask, python3-kafka, python3-nose, python3-psycopg2, python3-requests, python3-setuptools, python3-sqlalchemy (>= 1.0), - python3-swh.core (>= 0.0.28~), + python3-swh.core (>= 0.0.37~), python3-swh.model (>= 0.0.18~), python3-swh.objstorage (>= 0.0.17~), python3-swh.scheduler (>= 0.0.14~), python3-vcversioner Standards-Version: 3.9.6 Homepage: https://forge.softwareheritage.org/diffusion/DSTO/ Package: python3-swh.storage Architecture: all Depends: python3-swh.core (>= 0.0.28~), python3-swh.model (>= 0.0.18~), python3-swh.objstorage (>= 0.0.17~), ${misc:Depends}, ${python3:Depends} +Breaks: python3-swh.archiver (<< 0.0.3~), + python3-swh.indexer (<< 0.0.48~), + python3-swh.vault (<< 0.0.19~) Description: Software Heritage storage utilities Package: python3-swh.storage.listener Architecture: all Depends: python3-kafka (>= 1.3.1~), python3-swh.journal (>= 0.0.2~), python3-swh.storage (= ${binary:Version}), ${misc:Depends}, ${python3:Depends} Description: Software Heritage storage listener Package: python3-swh.storage.schemata Architecture: all Depends: python3-sqlalchemy (>= 1.0), python3-swh.storage (= ${binary:Version}), ${misc:Depends}, ${python3:Depends} Description: Ancillary schemata for Software Heritage diff --git a/requirements-swh.txt b/requirements-swh.txt index f6eca736b..85ad7ed4c 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,4 +1,4 @@ -swh.core >= 0.0.28 +swh.core >= 0.0.37 swh.model >= 0.0.18 swh.objstorage >= 0.0.17 swh.scheduler >= 0.0.14 diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index 3333a7719..bd6051b6d 100644 --- a/swh.storage.egg-info/PKG-INFO +++ b/swh.storage.egg-info/PKG-INFO @@ -1,12 +1,12 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.0.99 +Version: 0.0.100 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Description: UNKNOWN Platform: UNKNOWN Provides-Extra: listener Provides-Extra: schemata diff --git a/swh.storage.egg-info/SOURCES.txt b/swh.storage.egg-info/SOURCES.txt index ef6901974..ef5814da4 100644 --- a/swh.storage.egg-info/SOURCES.txt +++ b/swh.storage.egg-info/SOURCES.txt @@ -1,201 +1,199 @@ .gitignore AUTHORS LICENSE MANIFEST.in Makefile Makefile.local README.db_testing README.dev requirements-swh.txt requirements.txt setup.py version.txt -.vscode/settings.json bin/swh-storage-add-dir debian/changelog debian/compat debian/control debian/copyright debian/rules debian/source/format docs/.gitignore docs/Makefile docs/Makefile.local docs/archiver-blueprint.rst docs/conf.py docs/index.rst docs/sql-storage.rst docs/_static/.placeholder docs/_templates/.placeholder sql/.gitignore sql/Makefile sql/TODO sql/clusters.dot sql/swh-data.sql sql/swh-enums.sql sql/swh-func.sql sql/swh-indexes.sql sql/swh-init.sql sql/swh-schema.sql sql/swh-triggers.sql sql/bin/db-init sql/bin/db-upgrade sql/bin/dot_add_content sql/doc/json sql/doc/json/.gitignore sql/doc/json/Makefile sql/doc/json/entity.lister_metadata.schema.json sql/doc/json/entity.metadata.schema.json sql/doc/json/entity_history.lister_metadata.schema.json sql/doc/json/entity_history.metadata.schema.json sql/doc/json/fetch_history.result.schema.json sql/doc/json/list_history.result.schema.json sql/doc/json/listable_entity.list_params.schema.json sql/doc/json/origin_visit.metadata.json sql/doc/json/tool.tool_configuration.schema.json sql/json/.gitignore sql/json/Makefile sql/json/entity.lister_metadata.schema.json sql/json/entity.metadata.schema.json sql/json/entity_history.lister_metadata.schema.json sql/json/entity_history.metadata.schema.json sql/json/fetch_history.result.schema.json sql/json/list_history.result.schema.json sql/json/listable_entity.list_params.schema.json sql/json/origin_visit.metadata.json sql/json/tool.tool_configuration.schema.json sql/upgrades/015.sql sql/upgrades/016.sql sql/upgrades/017.sql sql/upgrades/018.sql sql/upgrades/019.sql sql/upgrades/020.sql sql/upgrades/021.sql sql/upgrades/022.sql sql/upgrades/023.sql sql/upgrades/024.sql sql/upgrades/025.sql sql/upgrades/026.sql sql/upgrades/027.sql sql/upgrades/028.sql sql/upgrades/029.sql sql/upgrades/030.sql sql/upgrades/032.sql sql/upgrades/033.sql sql/upgrades/034.sql sql/upgrades/035.sql sql/upgrades/036.sql sql/upgrades/037.sql sql/upgrades/038.sql sql/upgrades/039.sql sql/upgrades/040.sql sql/upgrades/041.sql sql/upgrades/042.sql sql/upgrades/043.sql sql/upgrades/044.sql sql/upgrades/045.sql sql/upgrades/046.sql sql/upgrades/047.sql sql/upgrades/048.sql sql/upgrades/049.sql sql/upgrades/050.sql sql/upgrades/051.sql sql/upgrades/052.sql sql/upgrades/053.sql sql/upgrades/054.sql sql/upgrades/055.sql sql/upgrades/056.sql sql/upgrades/057.sql sql/upgrades/058.sql sql/upgrades/059.sql sql/upgrades/060.sql sql/upgrades/061.sql sql/upgrades/062.sql sql/upgrades/063.sql sql/upgrades/064.sql sql/upgrades/065.sql sql/upgrades/066.sql sql/upgrades/067.sql sql/upgrades/068.sql sql/upgrades/069.sql sql/upgrades/070.sql sql/upgrades/071.sql sql/upgrades/072.sql sql/upgrades/073.sql sql/upgrades/074.sql sql/upgrades/075.sql sql/upgrades/076.sql sql/upgrades/077.sql sql/upgrades/078.sql sql/upgrades/079.sql sql/upgrades/080.sql sql/upgrades/081.sql sql/upgrades/082.sql sql/upgrades/083.sql sql/upgrades/084.sql sql/upgrades/085.sql sql/upgrades/086.sql sql/upgrades/087.sql sql/upgrades/088.sql sql/upgrades/089.sql sql/upgrades/090.sql sql/upgrades/091.sql sql/upgrades/092.sql sql/upgrades/093.sql sql/upgrades/094.sql sql/upgrades/095.sql sql/upgrades/096.sql sql/upgrades/097.sql sql/upgrades/098.sql sql/upgrades/099.sql sql/upgrades/100.sql sql/upgrades/101.sql sql/upgrades/102.sql sql/upgrades/103.sql sql/upgrades/104.sql sql/upgrades/105.sql sql/upgrades/106.sql sql/upgrades/107.sql sql/upgrades/108.sql sql/upgrades/109.sql sql/upgrades/110.sql sql/upgrades/111.sql sql/upgrades/112.sql sql/upgrades/113.sql sql/upgrades/114.sql sql/upgrades/115.sql sql/upgrades/116.sql sql/upgrades/117.sql sql/upgrades/118.sql swh/__init__.py swh.storage.egg-info/PKG-INFO swh.storage.egg-info/SOURCES.txt swh.storage.egg-info/dependency_links.txt swh.storage.egg-info/requires.txt swh.storage.egg-info/top_level.txt swh/storage/__init__.py swh/storage/common.py swh/storage/converters.py swh/storage/db.py swh/storage/exc.py swh/storage/listener.py swh/storage/storage.py swh/storage/algos/__init__.py swh/storage/algos/diff.py swh/storage/algos/dir_iterators.py swh/storage/api/__init__.py swh/storage/api/client.py swh/storage/api/server.py swh/storage/schemata/__init__.py swh/storage/schemata/distribution.py swh/storage/tests/__init__.py -swh/storage/tests/server_testing.py swh/storage/tests/storage_testing.py swh/storage/tests/test_api_client.py swh/storage/tests/test_converters.py swh/storage/tests/test_db.py swh/storage/tests/test_storage.py swh/storage/tests/algos/__init__.py swh/storage/tests/algos/test_diff.py utils/dump_revisions.py utils/fix_revisions_from_dump.py \ No newline at end of file diff --git a/swh.storage.egg-info/requires.txt b/swh.storage.egg-info/requires.txt index 4b29f4150..263f2477e 100644 --- a/swh.storage.egg-info/requires.txt +++ b/swh.storage.egg-info/requires.txt @@ -1,16 +1,16 @@ aiohttp click flask psycopg2 python-dateutil -swh.core>=0.0.28 +swh.core>=0.0.37 swh.model>=0.0.18 swh.objstorage>=0.0.17 swh.scheduler>=0.0.14 vcversioner [listener] kafka_python [schemata] SQLAlchemy diff --git a/swh/storage/algos/dir_iterators.py b/swh/storage/algos/dir_iterators.py index 798644d5f..691906c7b 100644 --- a/swh/storage/algos/dir_iterators.py +++ b/swh/storage/algos/dir_iterators.py @@ -1,347 +1,347 @@ # 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.identifiers import directory_identifier # get the hash identifier for an empty directory _empty_dir_hash = 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 additionnal features: - sibling nodes are iterated in lexicographic order by name - it is possible to skip the visit of sub-directories nodes - for efficency reasons when comparing two trees (no need to + for efficiency reasons when comparing two trees (no need to go deeper if two directories have the same hash) """ def __init__(self, storage, dir_id, base_path=b''): """ Args: storage (swh.storage.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 """ if dir_id: if dir_id == _empty_dir_hash: self.frames.append([]) else: # get directory entries dir_data = _get_dir(self.storage, dir_id) # sort them in lexicographical order dir_data = sorted(dir_data, key=lambda e: e['name']) # reverse the ordering in order to unstack the "smallest" # entry each time the iterator advances dir_data.reverse() # push the directory frame to the main stack self.frames.append(dir_data) def top(self): """ Returns: list: The top frame of the main directories stack """ if not self.frames: return None return self.frames[-1] def current(self): """ Returns: dict: The current visited directory entry, i.e. the top element from the top frame """ top_frame = self.top() if not top_frame: return None return top_frame[-1] def current_hash(self): """ Returns: bytes: The hash value of the currently visited directory entry """ return self.current()['target'] def current_perms(self): """ Returns: int: The permissions value of the currently visited directory entry """ return self.current()['perms'] def current_path(self): """ Returns: str: The absolute path from the root directory of the currently visited directory entry """ top_frame = self.top() if not top_frame: return None path = [] for frame in self.frames: path.append(frame[-1]['name']) return self.base_path + b'/'.join(path) def current_is_dir(self): """ Returns: bool: If the currently visited directory entry is a directory """ return self.current()['type'] == 'dir' def _advance(self, descend): """ Advance in the tree iteration. Args: descend (bool): whether or not to push a new frame if the currently visited element is a sub-directory Returns: dict: The description of the newly visited directory entry """ current = self.current() if not self.has_started or not current: self.has_started = True return current if descend and self.current_is_dir(): 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() class Remaining(Enum): """ Enum to represent the current state when iterating on both directory trees at the same time. """ NoMoreFiles = 0 OnlyToFilesRemain = 1 OnlyFromFilesRemain = 2 BothHaveFiles = 3 class DoubleDirectoryIterator(object): """ Helper class to traverse two directory trees at the same time and compare their contents to detect changes between them. """ def __init__(self, storage, dir_from, dir_to): """ Args: storage: instance of swh storage dir_from (bytes): hash identifier of the from directory dir_to (bytes): hash identifier of the to directory """ self.storage = storage self.dir_from = dir_from self.dir_to = dir_to self.restart() def restart(self): """ Restart the double iteration at the beginning. """ # initialize custom dfs iterators for the two directories self.it_from = DirectoryIterator(self.storage, self.dir_from) self.it_to = DirectoryIterator(self.storage, self.dir_to) # grab the first element of each iterator self.it_from.next() self.it_to.next() def next_from(self): """ Apply the next operation on the from iterator. """ self.it_from.next() def next_to(self): """ Apply the next operation on the to iterator. """ self.it_to.next() def next_both(self): """ Apply the next operation on both iterators. """ self.next_from() self.next_to() def step_from(self): """ Apply the step operation on the from iterator. """ self.it_from.step() def step_to(self): """ Apply the step operation on the from iterator. """ self.it_to.step() def step_both(self): """ Apply the step operation on the both iterators. """ self.step_from() self.step_to() def remaining(self): """ Returns: Remaining: the current state of the double iteration """ from_current = self.it_from.current() to_current = self.it_to.current() # no more files to iterate in both iterators if not from_current and not to_current: return Remaining.NoMoreFiles # still some files to iterate in the to iterator elif not from_current and to_current: return Remaining.OnlyToFilesRemain # still some files to iterate in the from iterator elif from_current and not to_current: return Remaining.OnlyFromFilesRemain # still files to iterate in the both iterators else: return Remaining.BothHaveFiles def compare(self): """ Compare the current iterated directory entries in both iterators and return the comparison status. Returns: dict: The status of the comparison with the following bool values: * *same_hash*: indicates if the two entries have the same hash * *same_perms*: indicates if the two entries have the same permissions * *both_are_dirs*: indicates if the two entries are directories * *both_are_files*: indicates if the two entries are regular files * *file_and_dir*: indicates if one of the entry is a directory and the other a regular file * *from_is_empty_dir*: indicates if the from entry is the empty directory * *from_is_empty_dir*: indicates if the to entry is the empty directory """ from_current_hash = self.it_from.current_hash() to_current_hash = self.it_to.current_hash() from_current_perms = self.it_from.current_perms() to_current_perms = self.it_to.current_perms() from_is_dir = self.it_from.current_is_dir() to_is_dir = self.it_to.current_is_dir() status = {} # compare hash status['same_hash'] = from_current_hash == to_current_hash # compare permissions status['same_perms'] = from_current_perms == to_current_perms # check if both elements are directories status['both_are_dirs'] = from_is_dir and to_is_dir # check if both elements are regular files status['both_are_files'] = not from_is_dir and not to_is_dir # check if one element is a directory, the other a regular file status['file_and_dir'] = (not status['both_are_dirs'] and not status['both_are_files']) # check if the from element is the empty directory status['from_is_empty_dir'] = (from_is_dir and from_current_hash == _empty_dir_hash) # check if the to element is the empty directory status['to_is_empty_dir'] = (to_is_dir and to_current_hash == _empty_dir_hash) return status diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py index 23c48cc43..6be0d06e1 100644 --- a/swh/storage/api/server.py +++ b/swh/storage/api/server.py @@ -1,389 +1,403 @@ # Copyright (C) 2015-2017 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 json import logging import click -from flask import g, request +from flask import request from swh.core import config -from swh.storage import get_storage +from swh.storage import get_storage as get_swhstorage from swh.core.api import (SWHServerAPIApp, decode_request, error_handler, encode_data_server as encode_data) DEFAULT_CONFIG_PATH = 'storage/storage' DEFAULT_CONFIG = { 'storage': ('dict', { 'cls': 'local', 'args': { 'db': 'dbname=softwareheritage-dev', 'objstorage': { 'cls': 'pathslicing', 'args': { 'root': '/srv/softwareheritage/objects', 'slicing': '0:2/2:4/4:6', }, }, }, }) } app = SWHServerAPIApp(__name__) +storage = None @app.errorhandler(Exception) def my_error_handler(exception): return error_handler(exception, encode_data) -@app.before_request -def before_request(): - g.storage = get_storage(**app.config['storage']) +def get_storage(): + global storage + if not storage: + storage = get_swhstorage(**app.config['storage']) + + return storage @app.route('/') def index(): return 'SWH Storage API server' @app.route('/check_config', methods=['POST']) def check_config(): - return encode_data(g.storage.check_config(**decode_request(request))) + return encode_data(get_storage().check_config(**decode_request(request))) @app.route('/content/missing', methods=['POST']) def content_missing(): - return encode_data(g.storage.content_missing(**decode_request(request))) + return encode_data(get_storage().content_missing( + **decode_request(request))) @app.route('/content/missing/sha1', methods=['POST']) def content_missing_per_sha1(): - return encode_data(g.storage.content_missing_per_sha1( + return encode_data(get_storage().content_missing_per_sha1( **decode_request(request))) @app.route('/content/present', methods=['POST']) def content_find(): - return encode_data(g.storage.content_find(**decode_request(request))) + return encode_data(get_storage().content_find(**decode_request(request))) @app.route('/content/add', methods=['POST']) def content_add(): - return encode_data(g.storage.content_add(**decode_request(request))) + return encode_data(get_storage().content_add(**decode_request(request))) @app.route('/content/update', methods=['POST']) def content_update(): - return encode_data(g.storage.content_update(**decode_request(request))) + return encode_data(get_storage().content_update(**decode_request(request))) @app.route('/content/data', methods=['POST']) def content_get(): - return encode_data(g.storage.content_get(**decode_request(request))) + return encode_data(get_storage().content_get(**decode_request(request))) @app.route('/content/metadata', methods=['POST']) def content_get_metadata(): - return encode_data(g.storage.content_get_metadata( + return encode_data(get_storage().content_get_metadata( **decode_request(request))) @app.route('/directory', methods=['POST']) def directory_get(): - return encode_data(g.storage.directory_get(**decode_request(request))) + return encode_data(get_storage().directory_get(**decode_request(request))) @app.route('/directory/missing', methods=['POST']) def directory_missing(): - return encode_data(g.storage.directory_missing(**decode_request(request))) + return encode_data(get_storage().directory_missing( + **decode_request(request))) @app.route('/directory/add', methods=['POST']) def directory_add(): - return encode_data(g.storage.directory_add(**decode_request(request))) + return encode_data(get_storage().directory_add(**decode_request(request))) @app.route('/directory/path', methods=['POST']) def directory_entry_get_by_path(): - return encode_data(g.storage.directory_entry_get_by_path( + return encode_data(get_storage().directory_entry_get_by_path( **decode_request(request))) @app.route('/directory/ls', methods=['GET']) def directory_ls(): dir = request.args['directory'].encode('utf-8', 'surrogateescape') rec = json.loads(request.args.get('recursive', 'False').lower()) - return encode_data(g.storage.directory_ls(dir, recursive=rec)) + return encode_data(get_storage().directory_ls(dir, recursive=rec)) @app.route('/revision/add', methods=['POST']) def revision_add(): - return encode_data(g.storage.revision_add(**decode_request(request))) + return encode_data(get_storage().revision_add(**decode_request(request))) @app.route('/revision', methods=['POST']) def revision_get(): - return encode_data(g.storage.revision_get(**decode_request(request))) + return encode_data(get_storage().revision_get(**decode_request(request))) @app.route('/revision/by', methods=['POST']) def revision_get_by(): - return encode_data(g.storage.revision_get_by(**decode_request(request))) + return encode_data(get_storage().revision_get_by( + **decode_request(request))) @app.route('/revision/log', methods=['POST']) def revision_log(): - return encode_data(g.storage.revision_log(**decode_request(request))) + return encode_data(get_storage().revision_log(**decode_request(request))) @app.route('/revision/logby', methods=['POST']) def revision_log_by(): - return encode_data(g.storage.revision_log_by(**decode_request(request))) + return encode_data(get_storage().revision_log_by( + **decode_request(request))) @app.route('/revision/shortlog', methods=['POST']) def revision_shortlog(): - return encode_data(g.storage.revision_shortlog(**decode_request(request))) + return encode_data(get_storage().revision_shortlog( + **decode_request(request))) @app.route('/revision/missing', methods=['POST']) def revision_missing(): - return encode_data(g.storage.revision_missing(**decode_request(request))) + return encode_data(get_storage().revision_missing( + **decode_request(request))) @app.route('/release/add', methods=['POST']) def release_add(): - return encode_data(g.storage.release_add(**decode_request(request))) + return encode_data(get_storage().release_add(**decode_request(request))) @app.route('/release', methods=['POST']) def release_get(): - return encode_data(g.storage.release_get(**decode_request(request))) + return encode_data(get_storage().release_get(**decode_request(request))) @app.route('/release/by', methods=['POST']) def release_get_by(): - return encode_data(g.storage.release_get_by(**decode_request(request))) + return encode_data(get_storage().release_get_by(**decode_request(request))) @app.route('/release/missing', methods=['POST']) def release_missing(): - return encode_data(g.storage.release_missing(**decode_request(request))) + return encode_data(get_storage().release_missing( + **decode_request(request))) @app.route('/object/find_by_sha1_git', methods=['POST']) def object_find_by_sha1_git(): - return encode_data(g.storage.object_find_by_sha1_git( + return encode_data(get_storage().object_find_by_sha1_git( **decode_request(request))) @app.route('/occurrence', methods=['POST']) def occurrence_get(): - return encode_data(g.storage.occurrence_get(**decode_request(request))) + return encode_data(get_storage().occurrence_get(**decode_request(request))) @app.route('/occurrence/add', methods=['POST']) def occurrence_add(): - return encode_data(g.storage.occurrence_add(**decode_request(request))) + return encode_data(get_storage().occurrence_add(**decode_request(request))) @app.route('/snapshot/add', methods=['POST']) def snapshot_add(): - return encode_data(g.storage.snapshot_add(**decode_request(request))) + return encode_data(get_storage().snapshot_add(**decode_request(request))) @app.route('/snapshot', methods=['POST']) def snapshot_get(): - return encode_data(g.storage.snapshot_get(**decode_request(request))) + return encode_data(get_storage().snapshot_get(**decode_request(request))) @app.route('/snapshot/by_origin_visit', methods=['POST']) def snapshot_get_by_origin_visit(): - return encode_data(g.storage.snapshot_get_by_origin_visit( + return encode_data(get_storage().snapshot_get_by_origin_visit( **decode_request(request))) @app.route('/snapshot/latest', methods=['POST']) def snapshot_get_latest(): - return encode_data(g.storage.snapshot_get_latest( + return encode_data(get_storage().snapshot_get_latest( **decode_request(request))) @app.route('/origin/get', methods=['POST']) def origin_get(): - return encode_data(g.storage.origin_get(**decode_request(request))) + return encode_data(get_storage().origin_get(**decode_request(request))) @app.route('/origin/search', methods=['POST']) def origin_search(): - return encode_data(g.storage.origin_search(**decode_request(request))) + return encode_data(get_storage().origin_search(**decode_request(request))) @app.route('/origin/add_multi', methods=['POST']) def origin_add(): - return encode_data(g.storage.origin_add(**decode_request(request))) + return encode_data(get_storage().origin_add(**decode_request(request))) @app.route('/origin/add', methods=['POST']) def origin_add_one(): - return encode_data(g.storage.origin_add_one(**decode_request(request))) + return encode_data(get_storage().origin_add_one(**decode_request(request))) @app.route('/origin/visit/get', methods=['POST']) def origin_visit_get(): - return encode_data(g.storage.origin_visit_get(**decode_request(request))) + return encode_data(get_storage().origin_visit_get( + **decode_request(request))) @app.route('/origin/visit/getby', methods=['POST']) def origin_visit_get_by(): return encode_data( - g.storage.origin_visit_get_by(**decode_request(request))) + get_storage().origin_visit_get_by(**decode_request(request))) @app.route('/origin/visit/add', methods=['POST']) def origin_visit_add(): - return encode_data(g.storage.origin_visit_add(**decode_request(request))) + return encode_data(get_storage().origin_visit_add( + **decode_request(request))) @app.route('/origin/visit/update', methods=['POST']) def origin_visit_update(): - return encode_data(g.storage.origin_visit_update( + return encode_data(get_storage().origin_visit_update( **decode_request(request))) @app.route('/person', methods=['POST']) def person_get(): - return encode_data(g.storage.person_get(**decode_request(request))) + return encode_data(get_storage().person_get(**decode_request(request))) @app.route('/fetch_history', methods=['GET']) def fetch_history_get(): - return encode_data(g.storage.fetch_history_get(request.args['id'])) + return encode_data(get_storage().fetch_history_get(request.args['id'])) @app.route('/fetch_history/start', methods=['POST']) def fetch_history_start(): return encode_data( - g.storage.fetch_history_start(**decode_request(request))) + get_storage().fetch_history_start(**decode_request(request))) @app.route('/fetch_history/end', methods=['POST']) def fetch_history_end(): return encode_data( - g.storage.fetch_history_end(**decode_request(request))) + get_storage().fetch_history_end(**decode_request(request))) @app.route('/entity/add', methods=['POST']) def entity_add(): return encode_data( - g.storage.entity_add(**decode_request(request))) + get_storage().entity_add(**decode_request(request))) @app.route('/entity/get', methods=['POST']) def entity_get(): return encode_data( - g.storage.entity_get(**decode_request(request))) + get_storage().entity_get(**decode_request(request))) @app.route('/entity', methods=['GET']) def entity_get_one(): - return encode_data(g.storage.entity_get_one(request.args['uuid'])) + return encode_data(get_storage().entity_get_one(request.args['uuid'])) @app.route('/entity/from_lister_metadata', methods=['POST']) def entity_from_lister_metadata(): - return encode_data( - g.storage.entity_get_from_lister_metadata(**decode_request(request))) + return encode_data(get_storage().entity_get_from_lister_metadata( + **decode_request(request))) @app.route('/tool/data', methods=['POST']) def tool_get(): - return encode_data(g.storage.tool_get( + return encode_data(get_storage().tool_get( **decode_request(request))) @app.route('/tool/add', methods=['POST']) def tool_add(): - return encode_data(g.storage.tool_add( + return encode_data(get_storage().tool_add( **decode_request(request))) @app.route('/origin/metadata/add', methods=['POST']) def origin_metadata_add(): - return encode_data(g.storage.origin_metadata_add(**decode_request( + return encode_data(get_storage().origin_metadata_add(**decode_request( request))) @app.route('/origin/metadata/get', methods=['POST']) def origin_metadata_get_by(): - return encode_data(g.storage.origin_metadata_get_by(**decode_request( + return encode_data(get_storage().origin_metadata_get_by(**decode_request( request))) @app.route('/provider/add', methods=['POST']) def metadata_provider_add(): - return encode_data(g.storage.metadata_provider_add(**decode_request( + return encode_data(get_storage().metadata_provider_add(**decode_request( request))) @app.route('/provider/get', methods=['POST']) def metadata_provider_get(): - return encode_data(g.storage.metadata_provider_get(**decode_request( + return encode_data(get_storage().metadata_provider_get(**decode_request( request))) @app.route('/provider/getby', methods=['POST']) def metadata_provider_get_by(): - return encode_data(g.storage.metadata_provider_get_by(**decode_request( + return encode_data(get_storage().metadata_provider_get_by(**decode_request( request))) @app.route('/stat/counters', methods=['GET']) def stat_counters(): - return encode_data(g.storage.stat_counters()) + return encode_data(get_storage().stat_counters()) @app.route('/algos/diff_directories', methods=['POST']) def diff_directories(): - return encode_data(g.storage.diff_directories(**decode_request(request))) + return encode_data(get_storage().diff_directories( + **decode_request(request))) @app.route('/algos/diff_revisions', methods=['POST']) def diff_revisions(): - return encode_data(g.storage.diff_revisions(**decode_request(request))) + return encode_data(get_storage().diff_revisions(**decode_request(request))) @app.route('/algos/diff_revision', methods=['POST']) def diff_revision(): - return encode_data(g.storage.diff_revision(**decode_request(request))) + return encode_data(get_storage().diff_revision(**decode_request(request))) def run_from_webserver(environ, start_response, config_path=DEFAULT_CONFIG_PATH): """Run the WSGI app from the webserver, loading the configuration.""" cfg = config.load_named_config(config_path, DEFAULT_CONFIG) app.config.update(cfg) handler = logging.StreamHandler() app.logger.addHandler(handler) return app(environ, start_response) @click.command() @click.argument('config-path', required=1) @click.option('--host', default='0.0.0.0', help="Host to run the server") @click.option('--port', default=5002, type=click.INT, help="Binding port of the server") @click.option('--debug/--nodebug', default=True, help="Indicates if the server should run in debug mode") def launch(config_path, host, port, debug): app.config.update(config.read(config_path, DEFAULT_CONFIG)) app.run(host, port=int(port), debug=bool(debug)) if __name__ == '__main__': launch() diff --git a/swh/storage/common.py b/swh/storage/common.py index 01285ca70..4c0fbed60 100644 --- a/swh/storage/common.py +++ b/swh/storage/common.py @@ -1,38 +1,40 @@ # Copyright (C) 2015-2016 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 def db_transaction(meth): """decorator to execute Storage methods within DB transactions The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): if 'cur' in kwargs and kwargs['cur']: return meth(self, *args, **kwargs) else: - with self.db.transaction() as cur: - return meth(self, *args, cur=cur, **kwargs) + db = self.get_db() + with db.transaction() as cur: + return meth(self, *args, db=db, cur=cur, **kwargs) return _meth def db_transaction_generator(meth): """decorator to execute Storage methods within DB transactions, while returning a generator The decorated method must accept a `cur` keyword argument """ @functools.wraps(meth) def _meth(self, *args, **kwargs): if 'cur' in kwargs and kwargs['cur']: yield from meth(self, *args, **kwargs) else: - with self.db.transaction() as cur: - yield from meth(self, *args, cur=cur, **kwargs) + db = self.get_db() + with db.transaction() as cur: + yield from meth(self, *args, db=db, cur=cur, **kwargs) return _meth diff --git a/swh/storage/db.py b/swh/storage/db.py index 25166b606..f84f0a7da 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,1038 +1,1052 @@ # Copyright (C) 2015-2017 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 binascii import datetime import enum import functools import json import os import select import threading from contextlib import contextmanager import psycopg2 import psycopg2.extras TMP_CONTENT_TABLE = 'tmp_content' psycopg2.extras.register_uuid() def stored_procedure(stored_proc): """decorator to execute remote stored procedure, specified as argument Generally, the body of the decorated function should be empty. If it is not, the stored procedure will be executed first; the function body then. """ def wrap(meth): @functools.wraps(meth) def _meth(self, *args, **kwargs): cur = kwargs.get('cur', None) self._cursor(cur).execute('SELECT %s()' % stored_proc) meth(self, *args, **kwargs) return _meth return wrap def jsonize(value): """Convert a value to a psycopg2 JSON object if necessary""" if isinstance(value, dict): return psycopg2.extras.Json(value) return value def entry_to_bytes(entry): """Convert an entry coming from the database to bytes""" if isinstance(entry, memoryview): return entry.tobytes() if isinstance(entry, list): return [entry_to_bytes(value) for value in entry] return entry def line_to_bytes(line): """Convert a line coming from the database to bytes""" if not line: return line if isinstance(line, dict): return {k: entry_to_bytes(v) for k, v in line.items()} return line.__class__(entry_to_bytes(entry) for entry in line) def cursor_to_bytes(cursor): """Yield all the data from a cursor as bytes""" yield from (line_to_bytes(line) for line in cursor) class BaseDb: """Base class for swh.storage.*Db. cf. swh.storage.db.Db, swh.archiver.db.ArchiverDb """ @classmethod def connect(cls, *args, **kwargs): """factory method to create a DB proxy Accepts all arguments of psycopg2.connect; only some specific possibilities are reported below. Args: connstring: libpq2 connection string """ conn = psycopg2.connect(*args, **kwargs) return cls(conn) + @classmethod + def from_pool(cls, pool): + return cls(pool.getconn(), pool=pool) + def _cursor(self, cur_arg): """get a cursor: from cur_arg if given, or a fresh one otherwise meant to avoid boilerplate if/then/else in methods that proxy stored procedures """ if cur_arg is not None: return cur_arg # elif self.cur is not None: # return self.cur else: return self.conn.cursor() - def __init__(self, conn): + def __init__(self, conn, pool=None): """create a DB proxy Args: conn: psycopg2 connection to the SWH DB + pool: psycopg2 pool of connections """ self.conn = conn + self.pool = pool + + def __del__(self): + if self.pool: + self.pool.putconn(self.conn) @contextmanager def transaction(self): """context manager to execute within a DB transaction Yields: a psycopg2 cursor """ with self.conn.cursor() as cur: try: yield cur self.conn.commit() except Exception: if not self.conn.closed: self.conn.rollback() raise def copy_to(self, items, tblname, columns, cur=None, item_cb=None): """Copy items' entries to table tblname with columns information. Args: items (dict): dictionary of data to copy over tblname tblname (str): Destination table's name columns ([str]): keys to access data in items and also the column names in the destination table. item_cb (fn): optional function to apply to items's entry """ def escape(data): if data is None: return '' if isinstance(data, bytes): return '\\x%s' % binascii.hexlify(data).decode('ascii') elif isinstance(data, str): return '"%s"' % data.replace('"', '""') elif isinstance(data, datetime.datetime): # We escape twice to make sure the string generated by # isoformat gets escaped return escape(data.isoformat()) elif isinstance(data, dict): return escape(json.dumps(data)) elif isinstance(data, list): return escape("{%s}" % ','.join(escape(d) for d in data)) elif isinstance(data, psycopg2.extras.Range): # We escape twice here too, so that we make sure # everything gets passed to copy properly return escape( '%s%s,%s%s' % ( '[' if data.lower_inc else '(', '-infinity' if data.lower_inf else escape(data.lower), 'infinity' if data.upper_inf else escape(data.upper), ']' if data.upper_inc else ')', ) ) elif isinstance(data, enum.IntEnum): return escape(int(data)) else: # We don't escape here to make sure we pass literals properly return str(data) read_file, write_file = os.pipe() def writer(): cursor = self._cursor(cur) with open(read_file, 'r') as f: cursor.copy_expert('COPY %s (%s) FROM STDIN CSV' % ( tblname, ', '.join(columns)), f) write_thread = threading.Thread(target=writer) write_thread.start() - with open(write_file, 'w') as f: - for d in items: - if item_cb is not None: - item_cb(d) - line = [escape(d.get(k)) for k in columns] - f.write(','.join(line)) - f.write('\n') - - write_thread.join() + try: + with open(write_file, 'w') as f: + for d in items: + if item_cb is not None: + item_cb(d) + line = [escape(d.get(k)) for k in columns] + f.write(','.join(line)) + f.write('\n') + finally: + # No problem bubbling up exceptions, but we still need to make sure + # we finish copying, even though we're probably going to cancel the + # transaction. + write_thread.join() def mktemp(self, tblname, cur=None): self._cursor(cur).execute('SELECT swh_mktemp(%s)', (tblname,)) 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),)) @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_occurrence_history') def mktemp_occurrence_history(self, cur=None): pass @stored_procedure('swh_mktemp_snapshot_branch') def mktemp_snapshot_branch(self, cur=None): pass @stored_procedure('swh_mktemp_entity_lister') def mktemp_entity_lister(self, cur=None): pass @stored_procedure('swh_mktemp_entity_history') def mktemp_entity_history(self, cur=None): pass @stored_procedure('swh_mktemp_bytea') def mktemp_bytea(self, cur=None): pass def register_listener(self, notify_queue, cur=None): """Register a listener for NOTIFY queue `notify_queue`""" self._cursor(cur).execute("LISTEN %s" % notify_queue) def listen_notifies(self, timeout): """Listen to notifications for `timeout` seconds""" if select.select([self.conn], [], [], timeout) == ([], [], []): return else: self.conn.poll() while self.conn.notifies: yield self.conn.notifies.pop(0) @stored_procedure('swh_content_add') def content_add_from_temp(self, cur=None): pass @stored_procedure('swh_directory_add') def directory_add_from_temp(self, cur=None): pass @stored_procedure('swh_skipped_content_add') def skipped_content_add_from_temp(self, cur=None): pass @stored_procedure('swh_revision_add') def revision_add_from_temp(self, cur=None): pass @stored_procedure('swh_release_add') def release_add_from_temp(self, cur=None): pass @stored_procedure('swh_occurrence_history_add') def occurrence_history_add_from_temp(self, cur=None): pass @stored_procedure('swh_entity_history_add') def entity_history_add_from_temp(self, cur=None): pass def store_tmp_bytea(self, ids, cur=None): """Store the given identifiers in a new tmp_bytea table""" cur = self._cursor(cur) self.mktemp_bytea(cur) self.copy_to(({'id': elem} for elem in ids), 'tmp_bytea', ['id'], cur) def content_update_from_temp(self, keys_to_update, cur=None): cur = self._cursor(cur) cur.execute("""select swh_content_update(ARRAY[%s] :: text[])""" % keys_to_update) content_get_metadata_keys = [ 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', 'status'] skipped_content_keys = [ 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', 'reason', 'status', 'origin'] def content_get_metadata_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""select t.id as sha1, %s from tmp_bytea t left join content on t.id = content.sha1 """ % ', '.join(self.content_get_metadata_keys[1:])) yield from cursor_to_bytes(cur) def content_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""SELECT sha1, sha1_git, sha256, blake2s256 FROM swh_content_missing()""") yield from cursor_to_bytes(cur) def content_missing_per_sha1_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""SELECT * FROM swh_content_missing_per_sha1()""") yield from cursor_to_bytes(cur) def skipped_content_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""SELECT sha1, sha1_git, sha256, blake2s256 FROM swh_skipped_content_missing()""") yield from cursor_to_bytes(cur) def occurrence_get(self, origin_id, cur=None): """Retrieve latest occurrence's information by origin_id. """ cur = self._cursor(cur) cur.execute("""SELECT origin, branch, target, target_type, (select max(date) from origin_visit where origin=%s) as date FROM occurrence WHERE origin=%s """, (origin_id, origin_id)) yield from cursor_to_bytes(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_add(self, origin, visit, snapshot_id, cur=None): """Add a snapshot for origin/visit from the temporary table""" cur = self._cursor(cur) cur.execute("""SELECT swh_snapshot_add(%s, %s, %s)""", (origin, visit, snapshot_id)) snapshot_get_cols = ['snapshot_id', 'name', 'target', 'target_type'] def snapshot_get_by_id(self, snapshot_id, cur=None): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_get_by_id(%%s) """ % ', '.join(self.snapshot_get_cols) cur.execute(query, (snapshot_id,)) yield from cursor_to_bytes(cur) def snapshot_get_by_origin_visit(self, origin_id, visit_id, cur=None): cur = self._cursor(cur) query = """\ SELECT swh_snapshot_get_by_origin_visit(%s, %s) """ cur.execute(query, (origin_id, visit_id)) ret = cur.fetchone() if ret: return line_to_bytes(ret)[0] 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): """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) cur.execute("""SELECT %s FROM swh_content_find(%%s, %%s, %%s, %%s) LIMIT 1""" % ','.join(self.content_find_cols), (sha1, sha1_git, sha256, blake2s256)) content = line_to_bytes(cur.fetchone()) if set(content) == {None}: return None else: return content def directory_get_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('''SELECT id, file_entries, dir_entries, rev_entries FROM swh_directory_get()''') yield from cursor_to_bytes(cur) def directory_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_directory_missing()') yield from cursor_to_bytes(cur) directory_ls_cols = ['dir_id', 'type', 'target', 'name', 'perms', 'status', 'sha1', 'sha1_git', 'sha256', 'length'] def directory_walk_one(self, directory, cur=None): cur = self._cursor(cur) cols = ', '.join(self.directory_ls_cols) query = 'SELECT %s FROM swh_directory_walk_one(%%s)' % cols cur.execute(query, (directory,)) yield from cursor_to_bytes(cur) def directory_walk(self, directory, cur=None): cur = self._cursor(cur) cols = ', '.join(self.directory_ls_cols) query = 'SELECT %s FROM swh_directory_walk(%%s)' % cols cur.execute(query, (directory,)) yield from cursor_to_bytes(cur) def directory_entry_get_by_path(self, directory, paths, cur=None): """Retrieve a directory entry by path. """ cur = self._cursor(cur) cols = ', '.join(self.directory_ls_cols) query = ( 'SELECT %s FROM swh_find_directory_entry_by_path(%%s, %%s)' % cols) cur.execute(query, (directory, paths)) data = cur.fetchone() if set(data) == {None}: return None return line_to_bytes(data) def revision_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT id FROM swh_revision_missing() as r(id)') yield from cursor_to_bytes(cur) 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', ] revision_get_cols = revision_add_cols + [ 'author_id', 'committer_id', 'parents'] def origin_visit_add(self, origin, ts, 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 Returns: The new visit index step for that origin """ cur = self._cursor(cur) self._cursor(cur).execute('SELECT swh_origin_visit_add(%s, %s)', (origin, ts)) return cur.fetchone()[0] def origin_visit_update(self, origin, visit_id, status, metadata, cur=None): """Update origin_visit's status.""" cur = self._cursor(cur) update = """UPDATE origin_visit SET status=%s, metadata=%s WHERE origin=%s AND visit=%s""" cur.execute(update, (status, jsonize(metadata), origin, visit_id)) origin_visit_get_cols = ['origin', 'visit', 'date', 'status', 'metadata', 'snapshot'] 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' args = (origin_id, last_visit, limit) else: extra_condition = '' args = (origin_id, limit) query = """\ SELECT %s, (select id from snapshot where object_id = snapshot_id) as snapshot FROM origin_visit WHERE origin=%%s %s order by date, visit asc limit %%s""" % ( ', '.join(self.origin_visit_get_cols[:-1]), extra_condition ) cur.execute(query, args) yield from cursor_to_bytes(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, (select id from snapshot where object_id = snapshot_id) as snapshot FROM origin_visit WHERE origin = %%s AND visit = %%s """ % (', '.join(self.origin_visit_get_cols[:-1])) cur.execute(query, (origin_id, visit_id)) r = cur.fetchall() if not r: return None return line_to_bytes(r[0]) def origin_visit_get_latest_snapshot(self, origin_id, allowed_statuses=None, cur=None): """Retrieve the most recent origin_visit which references a snapshot Args: origin_id: the origin concerned allowed_statuses: the visit statuses allowed for the returned visit Returns: The origin_visit information, or None if no visit matches. """ cur = self._cursor(cur) extra_clause = "" if allowed_statuses: extra_clause = cur.mogrify("AND status IN %s", (tuple(allowed_statuses),)).decode() query = """\ SELECT %s, (select id from snapshot where object_id = snapshot_id) as snapshot FROM origin_visit WHERE origin = %%s AND snapshot_id is not null %s ORDER BY date, visit DESC LIMIT 1 """ % (', '.join(self.origin_visit_get_cols[:-1]), extra_clause) cur.execute(query, (origin_id,)) r = cur.fetchone() if not r: return None return line_to_bytes(r) occurrence_cols = ['origin', 'branch', 'target', 'target_type'] def occurrence_by_origin_visit(self, origin_id, visit_id, cur=None): """Retrieve all occurrences for a particular origin_visit. Args: origin_id: the origin concerned visit_id: The visit step for that origin Yields: The occurrence's history visits """ cur = self._cursor(cur) query = """\ SELECT %s FROM swh_occurrence_by_origin_visit(%%s, %%s) """ % (', '.join(self.occurrence_cols)) cur.execute(query, (origin_id, visit_id)) yield from cursor_to_bytes(cur) def revision_get_from_temp(self, cur=None): cur = self._cursor(cur) query = 'SELECT %s FROM swh_revision_get()' % ( ', '.join(self.revision_get_cols)) cur.execute(query) yield from cursor_to_bytes(cur) def revision_log(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_log(%%s, %%s) """ % ', '.join(self.revision_get_cols) cur.execute(query, (root_revisions, limit)) yield from cursor_to_bytes(cur) revision_shortlog_cols = ['id', 'parents'] def revision_shortlog(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_list(%%s, %%s) """ % ', '.join(self.revision_shortlog_cols) cur.execute(query, (root_revisions, limit)) yield from cursor_to_bytes(cur) def release_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT id FROM swh_release_missing() as r(id)') yield from cursor_to_bytes(cur) object_find_by_sha1_git_cols = ['sha1_git', 'type', 'id', 'object_id'] def object_find_by_sha1_git(self, ids, cur=None): cur = self._cursor(cur) self.store_tmp_bytea(ids, cur) query = 'select %s from swh_object_find_by_sha1_git()' % ( ', '.join(self.object_find_by_sha1_git_cols) ) cur.execute(query) yield from cursor_to_bytes(cur) def stat_counters(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_stat_counters()') yield from cur fetch_history_cols = ['origin', 'date', 'status', 'result', 'stdout', 'stderr', 'duration'] def create_fetch_history(self, fetch_history, cur=None): """Create a fetch_history entry with the data in fetch_history""" cur = self._cursor(cur) query = '''INSERT INTO fetch_history (%s) VALUES (%s) RETURNING id''' % ( ','.join(self.fetch_history_cols), ','.join(['%s'] * len(self.fetch_history_cols)) ) cur.execute(query, [fetch_history.get(col) for col in self.fetch_history_cols]) return cur.fetchone()[0] def get_fetch_history(self, fetch_history_id, cur=None): """Get a fetch_history entry with the given id""" cur = self._cursor(cur) query = '''SELECT %s FROM fetch_history WHERE id=%%s''' % ( ', '.join(self.fetch_history_cols), ) cur.execute(query, (fetch_history_id,)) data = cur.fetchone() if not data: return None ret = {'id': fetch_history_id} for i, col in enumerate(self.fetch_history_cols): ret[col] = data[i] return ret def update_fetch_history(self, fetch_history, cur=None): """Update the fetch_history entry from the data in fetch_history""" cur = self._cursor(cur) query = '''UPDATE fetch_history SET %s WHERE id=%%s''' % ( ','.join('%s=%%s' % col for col in self.fetch_history_cols) ) cur.execute(query, [jsonize(fetch_history.get(col)) for col in self.fetch_history_cols + ['id']]) base_entity_cols = ['uuid', 'parent', 'name', 'type', 'description', 'homepage', 'active', 'generated', 'lister_metadata', 'metadata'] entity_cols = base_entity_cols + ['last_seen', 'last_id'] entity_history_cols = base_entity_cols + ['id', 'validity'] def origin_add(self, type, url, cur=None): """Insert a new origin and return the new identifier.""" insert = """INSERT INTO origin (type, url) values (%s, %s) RETURNING id""" cur.execute(insert, (type, url)) return cur.fetchone()[0] origin_cols = ['id', 'type', 'url', 'lister', 'project'] def origin_get_with(self, type, url, cur=None): """Retrieve the origin id from its type and url if found.""" cur = self._cursor(cur) query = """SELECT %s FROM origin WHERE type=%%s AND url=%%s """ % ','.join(self.origin_cols) cur.execute(query, (type, url)) data = cur.fetchone() if data: return line_to_bytes(data) return None def origin_get(self, id, cur=None): """Retrieve the origin per its identifier. """ cur = self._cursor(cur) query = """SELECT %s FROM origin WHERE id=%%s """ % ','.join(self.origin_cols) cur.execute(query, (id,)) data = cur.fetchone() if data: return line_to_bytes(data) return None def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, cur=None): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. Args: url_pattern: the string pattern to search for in origin urls offset: number of found origins to skip before returning results limit: the maximum number of found origins to return regexp: if True, consider the provided pattern as a regular expression and returns origins whose urls match it """ cur = self._cursor(cur) origin_cols = ','.join(self.origin_cols) query = """SELECT %s FROM origin WHERE url %s %%s ORDER BY id OFFSET %%s LIMIT %%s""" if not regexp: query = query % (origin_cols, 'ILIKE') query_params = ('%'+url_pattern+'%', offset, limit) else: query = query % (origin_cols, '~*') query_params = (url_pattern, offset, limit) cur.execute(query, query_params) yield from cursor_to_bytes(cur) person_cols = ['fullname', 'name', 'email'] person_get_cols = person_cols + ['id'] def person_add(self, person, cur=None): """Add a person identified by its name and email. Returns: The new person's id """ cur = self._cursor(cur) query_new_person = '''\ INSERT INTO person(%s) VALUES (%s) RETURNING id''' % ( ', '.join(self.person_cols), ', '.join('%s' for i in range(len(self.person_cols))) ) cur.execute(query_new_person, [person[col] for col in self.person_cols]) return cur.fetchone()[0] def person_get(self, ids, cur=None): """Retrieve the persons identified by the list of ids. """ cur = self._cursor(cur) query = """SELECT %s FROM person WHERE id IN %%s""" % ', '.join(self.person_get_cols) cur.execute(query, (tuple(ids),)) yield from cursor_to_bytes(cur) release_add_cols = [ 'id', 'target', 'target_type', 'date', 'date_offset', 'date_neg_utc_offset', 'name', 'comment', 'synthetic', 'author_fullname', 'author_name', 'author_email', ] release_get_cols = release_add_cols + ['author_id'] def release_get_from_temp(self, cur=None): cur = self._cursor(cur) query = ''' SELECT %s FROM swh_release_get() ''' % ', '.join(self.release_get_cols) cur.execute(query) yield from cursor_to_bytes(cur) def release_get_by(self, origin_id, limit=None, cur=None): """Retrieve a release by occurrence criterion (only origin right now) Args: - origin_id: The origin to look for. """ cur = self._cursor(cur) query = """ SELECT %s FROM swh_release_get_by(%%s) LIMIT %%s """ % ', '.join(self.release_get_cols) cur.execute(query, (origin_id, limit)) yield from cursor_to_bytes(cur) def revision_get_by(self, origin_id, branch_name, datetime, limit=None, cur=None): """Retrieve a revision by occurrence criterion. Args: - origin_id: The origin to look for - branch_name: the branch name to look for - datetime: the lower bound of timerange to look for. - limit: limit number of results to return The upper bound being now. """ cur = self._cursor(cur) if branch_name and isinstance(branch_name, str): branch_name = branch_name.encode('utf-8') query = ''' SELECT %s FROM swh_revision_get_by(%%s, %%s, %%s) LIMIT %%s ''' % ', '.join(self.revision_get_cols) cur.execute(query, (origin_id, branch_name, datetime, limit)) yield from cursor_to_bytes(cur) def entity_get(self, uuid, cur=None): """Retrieve the entity and its parent hierarchy chain per uuid. """ cur = self._cursor(cur) cur.execute("""SELECT %s FROM swh_entity_get(%%s)""" % ( ', '.join(self.entity_cols)), (uuid, )) yield from cursor_to_bytes(cur) def entity_get_one(self, uuid, cur=None): """Retrieve a single entity given its uuid. """ cur = self._cursor(cur) cur.execute("""SELECT %s FROM entity WHERE uuid = %%s""" % ( ', '.join(self.entity_cols)), (uuid, )) data = cur.fetchone() if not data: return None return line_to_bytes(data) 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) values (%s, %s, %s, %s, %s) RETURNING id""" cur.execute(insert, (origin, ts, provider, tool, jsonize(metadata))) return cur.fetchone()[0] origin_metadata_get_cols = ['id', 'origin_id', 'discovery_date', 'tool_id', 'metadata', 'provider_id', 'provider_name', 'provider_type', 'provider_url'] def origin_metadata_get_by(self, origin_id, provider_type=None, cur=None): """Retrieve all origin_metadata entries for one origin_id """ cur = self._cursor(cur) if not provider_type: query = '''SELECT %s FROM swh_origin_metadata_get_by_origin( %%s)''' % (','.join( self.origin_metadata_get_cols)) cur.execute(query, (origin_id, )) else: query = '''SELECT %s FROM swh_origin_metadata_get_by_provider_type( %%s, %%s)''' % (','.join( self.origin_metadata_get_cols)) cur.execute(query, (origin_id, provider_type)) yield from cursor_to_bytes(cur) tool_cols = ['id', 'name', 'version', 'configuration'] @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), )) yield from cursor_to_bytes(cur) def tool_get(self, name, version, configuration, cur=None): cur = self._cursor(cur) cur.execute('''select %s from tool where name=%%s and version=%%s and configuration=%%s''' % ( ','.join(self.tool_cols)), (name, version, configuration)) data = cur.fetchone() if not data: return None return line_to_bytes(data) 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): """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))) return cur.fetchone()[0] def metadata_provider_get(self, provider_id, cur=None): cur = self._cursor(cur) cur.execute('''select %s from metadata_provider where provider_id=%%s ''' % ( ','.join(self.metadata_provider_cols)), (provider_id, )) data = cur.fetchone() if not data: return None return line_to_bytes(data) def metadata_provider_get_by(self, provider_name, provider_url, cur=None): cur = self._cursor(cur) cur.execute('''select %s from metadata_provider where provider_name=%%s and provider_url=%%s''' % ( ','.join(self.metadata_provider_cols)), (provider_name, provider_url)) data = cur.fetchone() if not data: return None return line_to_bytes(data) diff --git a/swh/storage/storage.py b/swh/storage/storage.py index d58d1efb1..e54e45b7e 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1638 +1,1588 @@ # Copyright (C) 2015-2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import defaultdict +import concurrent.futures import datetime import itertools import json + import dateutil.parser import psycopg2 +import psycopg2.pool from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageDBError from .algos import diff from swh.model.hashutil import ALGORITHMS from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 CONTENT_HASH_KEYS = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] class Storage(): """SWH storage proxy, encompassing DB and object storage """ - def __init__(self, db, objstorage): + def __init__(self, db, objstorage, min_pool_conns=1, max_pool_conns=10): """ 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.db = Db(db) + self._pool = None + self._db = Db(db) else: - self.db = Db.connect(db) + self._pool = psycopg2.pool.ThreadedConnectionPool( + min_pool_conns, max_pool_conns, db + ) + self._db = None except psycopg2.OperationalError as e: raise StorageDBError(e) self.objstorage = get_objstorage(**objstorage) + def get_db(self): + if self._db: + return self._db + else: + return Db.from_pool(self._pool) + def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" if not self.objstorage.check_config(check_write=check_write): return False # Check permissions on one of the tables - with self.db.transaction() as cur: + with self.get_db().transaction() as cur: if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content', %s)", (check,) ) return cur.fetchone()[0] return True def content_add(self, content): """Add content blobs to the storage Note: in case of DB errors, objects might have already been added to the object storage and will not be removed. Since addition to the object storage is idempotent, that should not be a problem. Args: content (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 (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 """ - db = self.db + db = self.get_db() def _unique_key(hash, keys=CONTENT_HASH_KEYS): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) content_by_status = defaultdict(list) for d in content: if 'status' not in d: d['status'] = 'visible' if 'length' not in d: d['length'] = -1 content_by_status[d['status']].append(d) content_with_data = content_by_status['visible'] content_without_data = content_by_status['absent'] missing_content = set(self.content_missing(content_with_data)) missing_skipped = set(_unique_key(hashes) for hashes in self.skipped_content_missing( content_without_data)) + def add_to_objstorage(): + data = { + cont['sha1']: cont['data'] + for cont in content_with_data + if cont['sha1'] in missing_content + } + self.objstorage.add_batch(data) + with db.transaction() as cur: - if missing_content: - # create temporary table for metadata injection - db.mktemp('content', cur) + with concurrent.futures.ThreadPoolExecutor(max_workers=1) as executor: + added_to_objstorage = executor.submit(add_to_objstorage) + if missing_content: + # create temporary table for metadata injection + db.mktemp('content', cur) - def add_to_objstorage(cont): - self.objstorage.add(cont['data'], - obj_id=cont['sha1']) + content_filtered = (cont for cont in content_with_data + if cont['sha1'] in missing_content) - content_filtered = (cont for cont in content_with_data - if cont['sha1'] in missing_content) + db.copy_to(content_filtered, 'tmp_content', + db.content_get_metadata_keys, cur) - db.copy_to(content_filtered, 'tmp_content', - db.content_get_metadata_keys, - cur, item_cb=add_to_objstorage) + # move metadata in place + db.content_add_from_temp(cur) - # move metadata in place - db.content_add_from_temp(cur) + if missing_skipped: + missing_filtered = ( + cont for cont in content_without_data + if _unique_key(cont) in missing_skipped + ) - if missing_skipped: - missing_filtered = (cont for cont in content_without_data - if _unique_key(cont) in missing_skipped) + db.mktemp('skipped_content', cur) + db.copy_to(missing_filtered, 'tmp_skipped_content', + db.skipped_content_keys, cur) - db.mktemp('skipped_content', cur) - db.copy_to(missing_filtered, 'tmp_skipped_content', - db.skipped_content_keys, cur) + # move metadata in place + db.skipped_content_add_from_temp(cur) - # move metadata in place - db.skipped_content_add_from_temp(cur) + # Wait for objstorage addition before returning from the + # transaction, bubbling up any exception + _ = added_to_objstorage.result() @db_transaction - def content_update(self, content, keys=[], cur=None): + def content_update(self, content, keys=[], db=None, cur=None): """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 """ - db = self.db - # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. - db.mktemp('content') + db.mktemp('content', cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) db.copy_to(content, 'tmp_content', select_keys, cur) db.content_update_from_temp(keys_to_update=keys, cur=cur) def content_get(self, content): """Retrieve in bulk contents and their data. Args: content: iterables of sha1 Yields: dict: Generates streams of contents as dict with their raw data: - sha1: sha1's content - data: bytes data of the content Raises: ValueError in case of too much contents are required. cf. BULK_BLOCK_CONTENT_LEN_MAX """ # FIXME: Improve on server module to slice the result if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise ValueError( "Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) for obj_id in content: try: data = self.objstorage.get(obj_id) except ObjNotFoundError: yield None continue yield {'sha1': obj_id, 'data': data} @db_transaction_generator - def content_get_metadata(self, content, cur=None): + def content_get_metadata(self, content, db=None, cur=None): """Retrieve content metadata in bulk Args: content: iterable of content identifiers (sha1) Returns: an iterable with content metadata corresponding to the given ids """ - db = self.db - db.store_tmp_bytea(content, cur) for content_metadata in db.content_get_metadata_from_temp(cur): yield dict(zip(db.content_get_metadata_keys, content_metadata)) @db_transaction_generator - def content_missing(self, content, key_hash='sha1', cur=None): + def content_missing(self, content, key_hash='sha1', db=None, cur=None): """List content missing from storage Args: content ([dict]): iterable of dictionaries containing one key for each checksum algorithm in :data:`swh.model.hashutil.ALGORITHMS`, mapped to the corresponding checksum, and a length key mapped to the content 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. """ - db = self.db - keys = CONTENT_HASH_KEYS if key_hash not in CONTENT_HASH_KEYS: raise ValueError("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) # Create temporary table for metadata injection db.mktemp('content', cur) db.copy_to(content, 'tmp_content', keys + ['length'], cur) for obj in db.content_missing_from_temp(cur): yield obj[key_hash_idx] @db_transaction_generator - def content_missing_per_sha1(self, contents, cur=None): + def content_missing_per_sha1(self, contents, db=None, cur=None): """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. """ - db = self.db - db.store_tmp_bytea(contents, cur) for obj in db.content_missing_per_sha1_from_temp(cur): yield obj[0] @db_transaction_generator - def skipped_content_missing(self, content, cur=None): + def skipped_content_missing(self, content, db=None, cur=None): """List skipped_content missing from storage Args: content: iterable of dictionaries containing the data for each checksum algorithm. Returns: iterable: missing signatures """ keys = CONTENT_HASH_KEYS - db = self.db - db.mktemp('skipped_content', cur) db.copy_to(content, 'tmp_skipped_content', keys + ['length', 'reason'], cur) yield from db.skipped_content_missing_from_temp(cur) @db_transaction - def content_find(self, content, cur=None): + def content_find(self, content, db=None, cur=None): """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. """ - db = self.db - if not set(content).intersection(ALGORITHMS): raise ValueError('content keys must contain at least one of: ' 'sha1, sha1_git, sha256, blake2s256') c = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), blake2s256=content.get('blake2s256'), cur=cur) if c: return dict(zip(db.content_find_cols, c)) return None def directory_add(self, directories): """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 """ dirs = set() dir_entries = { '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.copy() entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs)) if not dirs_missing: return - db = self.db + db = self.get_db() with db.transaction() as cur: # Copy directory ids dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.mktemp('directory', cur) db.copy_to(dirs_missing_dict, 'tmp_directory', ['id'], cur) # Copy entries for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'dir_id'], cur, ) # Do the final copy db.directory_add_from_temp(cur) @db_transaction_generator - def directory_missing(self, directories, cur): + def directory_missing(self, directories, db=None, cur=None): """List directories missing from storage Args: directories (iterable): an iterable of directory ids Yields: missing directory ids """ - db = self.db - # Create temporary table for metadata injection db.mktemp('directory', cur) directories_dicts = ({'id': dir} for dir in directories) db.copy_to(directories_dicts, 'tmp_directory', ['id'], cur) for obj in db.directory_missing_from_temp(cur): yield obj[0] @db_transaction_generator - def directory_get(self, - directories, - cur=None): + def directory_get(self, directories, db=None, cur=None): """Get information on directories. Args: - directories: an iterable of directory ids Returns: List of directories as dict with keys and associated values. """ - db = self.db keys = ('id', 'dir_entries', 'file_entries', 'rev_entries') db.mktemp('directory', cur) db.copy_to(({'id': dir_id} for dir_id in directories), 'tmp_directory', ['id'], cur) dirs = db.directory_get_from_temp(cur) for line in dirs: yield dict(zip(keys, line)) @db_transaction_generator - def directory_ls(self, directory, recursive=False, cur=None): + def directory_ls(self, directory, recursive=False, db=None, cur=None): """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. """ - db = self.db - if recursive: res_gen = db.directory_walk(directory, cur=cur) else: res_gen = db.directory_walk_one(directory, cur=cur) for line in res_gen: yield dict(zip(db.directory_ls_cols, line)) @db_transaction - def directory_entry_get_by_path(self, directory, paths, cur=None): + def directory_entry_get_by_path(self, directory, paths, db=None, cur=None): """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. """ - db = self.db - res = db.directory_entry_get_by_path(directory, paths, cur) if res: return dict(zip(db.directory_ls_cols, res)) def revision_add(self, revisions): """Add revisions to the storage Args: revisions (iterable): iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - id (sha1_git): id of the revision to add - date (datetime.DateTime): date the revision was written - date_offset (int): offset from UTC in minutes the revision was written - date_neg_utc_offset (boolean): whether a null date_offset represents a negative UTC offset - committer_date (datetime.DateTime): date the revision got added to the origin - committer_date_offset (int): offset from UTC in minutes the revision was added to the origin - committer_date_neg_utc_offset (boolean): whether a null committer_date_offset represents a negative UTC offset - type (one of 'git', 'tar'): type of the revision added - directory (sha1_git): the directory the revision points at - message (bytes): the message associated with the revision - author_name (bytes): the name of the revision author - author_email (bytes): the email of the revision author - committer_name (bytes): the name of the revision committer - committer_email (bytes): the email of the revision committer - metadata (jsonb): extra information as dictionary - synthetic (bool): revision's nature (tarball, directory creates synthetic revision) - parents (list of sha1_git): the parents of this revision """ - db = self.db + db = self.get_db() revisions_missing = set(self.revision_missing( set(revision['id'] for revision in revisions))) if not revisions_missing: return with db.transaction() as cur: db.mktemp_revision(cur) revisions_filtered = ( converters.revision_to_db(revision) for revision in revisions if revision['id'] in revisions_missing) parents_filtered = [] db.copy_to( revisions_filtered, 'tmp_revision', db.revision_add_cols, cur, lambda rev: parents_filtered.extend(rev['parents'])) db.revision_add_from_temp(cur) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) @db_transaction_generator - def revision_missing(self, revisions, cur=None): + def revision_missing(self, revisions, db=None, cur=None): """List revisions missing from storage Args: revisions (iterable): revision ids Yields: missing revision ids """ - db = self.db - db.store_tmp_bytea(revisions, cur) for obj in db.revision_missing_from_temp(cur): yield obj[0] @db_transaction_generator - def revision_get(self, revisions, cur): + def revision_get(self, revisions, db=None, cur=None): """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) """ - - db = self.db - db.store_tmp_bytea(revisions, cur) - for line in self.db.revision_get_from_temp(cur): + for line in db.revision_get_from_temp(cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @db_transaction_generator - def revision_log(self, revisions, limit=None, cur=None): + def revision_log(self, revisions, limit=None, db=None, cur=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. """ - db = self.db - 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']: yield None continue yield data @db_transaction_generator - def revision_shortlog(self, revisions, limit=None, cur=None): + def revision_shortlog(self, revisions, limit=None, db=None, cur=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. """ - db = self.db - yield from db.revision_shortlog(revisions, limit, cur) @db_transaction_generator def revision_log_by(self, origin_id, branch_name=None, timestamp=None, - limit=None, cur=None): + limit=None, db=None, cur=None): """Fetch revision entry from the actual origin_id's latest revision. Args: origin_id: the origin id from which deriving the revision branch_name: (optional) occurrence's branch name timestamp: (optional) occurrence's time limit: (optional) depth limitation for the output. Default to None. Yields: The revision log starting from the revision derived from the (origin, branch_name, timestamp) combination if any. Returns: None if no revision matching this combination is found. """ - db = self.db - # Retrieve the revision by criterion revisions = list(db.revision_get_by( - origin_id, branch_name, timestamp, limit=1)) + origin_id, branch_name, timestamp, limit=1, cur=cur)) if not revisions: return None revision_id = revisions[0][0] # otherwise, retrieve the revision log from that revision - yield from self.revision_log([revision_id], limit) + yield from self.revision_log([revision_id], limit, db=db, cur=cur) def release_add(self, releases): """Add releases to the storage Args: releases (iterable): iterable of dictionaries representing the individual releases to add. Each dict has the following keys: - id (sha1_git): id of the release to add - revision (sha1_git): id of the revision the release points to - date (datetime.DateTime): the date the release was made - date_offset (int): offset from UTC in minutes the release was made - date_neg_utc_offset (boolean): whether a null date_offset represents a negative UTC offset - name (bytes): the name of the release - comment (bytes): the comment associated with the release - author_name (bytes): the name of the release author - author_email (bytes): the email of the release author """ - db = self.db + db = self.get_db() release_ids = set(release['id'] for release in releases) releases_missing = set(self.release_missing(release_ids)) if not releases_missing: return with db.transaction() as cur: db.mktemp_release(cur) releases_filtered = ( converters.release_to_db(release) for release in releases if release['id'] in releases_missing ) db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) @db_transaction_generator - def release_missing(self, releases, cur=None): + def release_missing(self, releases, db=None, cur=None): """List releases missing from storage Args: releases: an iterable of release ids Returns: a list of missing release ids """ - db = self.db - # Create temporary table for metadata injection db.store_tmp_bytea(releases, cur) for obj in db.release_missing_from_temp(cur): yield obj[0] @db_transaction_generator - def release_get(self, releases, cur=None): + def release_get(self, releases, db=None, cur=None): """Given a list of sha1, return the releases's information Args: releases: list of sha1s Yields: releases: list of releases as dicts with the following keys: - id: origin's id - revision: origin's type - url: origin's url - lister: lister's uuid - project: project's uuid (FIXME, retrieve this information) Raises: ValueError: if the keys does not match (url and type) nor id. """ - db = self.db - # Create temporary table for metadata injection db.store_tmp_bytea(releases, cur) for release in db.release_get_from_temp(cur): yield converters.db_to_release( dict(zip(db.release_get_cols, release)) ) @db_transaction def snapshot_add(self, origin, visit, snapshot, back_compat=False, - cur=None): + db=None, cur=None): """Add a snapshot for the given origin/visit couple Args: origin (int): id of the origin visit (int): id of the visit snapshot (dict): the snapshot to add to the visit, 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) back_compat (bool): whether to add the occurrences for backwards-compatibility """ - db = self.db - if not db.snapshot_exists(snapshot['id'], cur): db.mktemp_snapshot_branch(cur) db.copy_to( ( { 'name': name, 'target': info['target'] if info else None, 'target_type': info['target_type'] if info else None, } for name, info in snapshot['branches'].items() ), 'tmp_snapshot_branch', ['name', 'target', 'target_type'], cur, ) db.snapshot_add(origin, visit, snapshot['id'], cur) if not back_compat: return # TODO: drop this compat feature occurrences = [] for name, info in snapshot['branches'].items(): if not info: target = b'\x00' * 20 target_type = 'revision' elif info['target_type'] == 'alias': continue else: target = info['target'] target_type = info['target_type'] occurrences.append({ 'origin': origin, 'visit': visit, 'branch': name, 'target': target, 'target_type': target_type, }) - self.occurrence_add(occurrences) + self.occurrence_add(occurrences, db=db, cur=cur) @db_transaction - def snapshot_get(self, snapshot_id, cur=None): + def snapshot_get(self, snapshot_id, db=None, cur=None): """Get the snapshot with the given id Args: snapshot_id (bytes): id of the snapshot Returns: dict: a snapshot with two keys: id:: identifier for the snapshot branches:: a list of branches contained by the snapshot """ - db = self.db - branches = {} for branch in db.snapshot_get_by_id(snapshot_id, cur): branch = dict(zip(db.snapshot_get_cols, branch)) del branch['snapshot_id'] name = branch.pop('name') if branch == {'target': None, 'target_type': None}: branch = None branches[name] = branch if branches: return {'id': snapshot_id, 'branches': branches} if db.snapshot_exists(snapshot_id, cur): # empty snapshot return {'id': snapshot_id, 'branches': {}} return None @db_transaction - def snapshot_get_by_origin_visit(self, origin, visit, cur=None): + def snapshot_get_by_origin_visit(self, origin, visit, db=None, cur=None): """Get the snapshot for the given origin visit Args: origin (int): the origin identifier visit (int): the visit identifier Returns: dict: a snapshot with two keys: id:: identifier for the snapshot branches:: a dictionary containing the snapshot branch information """ - db = self.db - snapshot_id = db.snapshot_get_by_origin_visit(origin, visit, cur) if snapshot_id: - return self.snapshot_get(snapshot_id, cur=cur) + return self.snapshot_get(snapshot_id, db=db, cur=cur) else: # compatibility code during the snapshot migration origin_visit_info = self.origin_visit_get_by(origin, visit, - cur=cur) + db=db, cur=cur) if origin_visit_info is None: return None ret = {'id': None} ret['branches'] = origin_visit_info['occurrences'] return ret return None @db_transaction - def snapshot_get_latest(self, origin, allowed_statuses=None, cur=None): + def snapshot_get_latest(self, origin, allowed_statuses=None, db=None, + cur=None): """Get the latest snapshot for the given origin, optionally only from visits that have one of the given allowed_statuses. Args: origin (int): the origin identifier 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 snapshot with two keys: id:: identifier for the snapshot branches:: a dictionary containing the snapshot branch information """ - db = self.db - origin_visit = db.origin_visit_get_latest_snapshot( origin, allowed_statuses=allowed_statuses, cur=cur) if origin_visit: origin_visit = dict(zip(db.origin_visit_get_cols, origin_visit)) - return self.snapshot_get(origin_visit['snapshot'], cur=cur) + return self.snapshot_get(origin_visit['snapshot'], db=db, cur=cur) @db_transaction - def occurrence_add(self, occurrences, cur=None): + def occurrence_add(self, occurrences, db=None, cur=None): """Add occurrences to the storage Args: occurrences: iterable of dictionaries representing the individual occurrences to add. Each dict has the following keys: - origin (int): id of the origin corresponding to the occurrence - visit (int): id of the visit corresponding to the occurrence - branch (str): the reference name of the occurrence - target (sha1_git): the id of the object pointed to by the occurrence - target_type (str): the type of object pointed to by the occurrence """ - db = self.db - db.mktemp_occurrence_history(cur) db.copy_to(occurrences, 'tmp_occurrence_history', ['origin', 'branch', 'target', 'target_type', 'visit'], cur) db.occurrence_history_add_from_temp(cur) @db_transaction_generator - def occurrence_get(self, origin_id, cur=None): + def occurrence_get(self, origin_id, db=None, cur=None): """Retrieve occurrence information per origin_id. Args: origin_id: The occurrence's origin. Yields: List of occurrences matching criterion. """ - db = self.db for line in db.occurrence_get(origin_id, cur): yield { 'origin': line[0], 'branch': line[1], 'target': line[2], 'target_type': line[3], } @db_transaction - def origin_visit_add(self, origin, ts, cur=None): + def origin_visit_add(self, origin, ts, db=None, cur=None): """Add an origin_visit for the origin at ts with status 'ongoing'. Args: origin: Visited Origin id ts: timestamp of such visit Returns: dict: dictionary with keys origin and visit where: - origin: origin identifier - visit: the visit identifier for the new visit occurrence - ts (datetime.DateTime): the visit date """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) return { 'origin': origin, - 'visit': self.db.origin_visit_add(origin, ts, cur) + 'visit': db.origin_visit_add(origin, ts, cur) } @db_transaction def origin_visit_update(self, origin, visit_id, status, metadata=None, - cur=None): + db=None, cur=None): """Update an origin_visit's status. Args: origin: Visited Origin id visit_id: Visit's id status: Visit's new status metadata: Data associated to the visit Returns: None """ - return self.db.origin_visit_update(origin, visit_id, status, metadata, - cur) + return db.origin_visit_update(origin, visit_id, status, metadata, cur) @db_transaction_generator - def origin_visit_get(self, origin, last_visit=None, limit=None, cur=None): + def origin_visit_get(self, origin, last_visit=None, limit=None, db=None, + cur=None): """Retrieve all the origin's visit's information. Args: origin (int): The occurrence's origin (identifier). last_visit (int): Starting point from which listing the next visits Default to None limit (int): Number of results to return from the last visit. Default to None Yields: List of visits. """ - db = self.db for line in db.origin_visit_get_all( origin, last_visit=last_visit, limit=limit, cur=cur): - data = dict(zip(self.db.origin_visit_get_cols, line)) + data = dict(zip(db.origin_visit_get_cols, line)) yield data @db_transaction - def origin_visit_get_by(self, origin, visit, cur=None): + def origin_visit_get_by(self, origin, visit, db=None, cur=None): """Retrieve origin visit's information. Args: origin: The occurrence's origin (identifier). Returns: The information on that particular (origin, visit) """ - db = self.db - ori_visit = db.origin_visit_get(origin, visit, cur) if not ori_visit: return None - ori_visit = dict(zip(self.db.origin_visit_get_cols, ori_visit)) + ori_visit = dict(zip(db.origin_visit_get_cols, ori_visit)) if ori_visit['snapshot']: - ori_visit['occurrences'] = self.snapshot_get(ori_visit['snapshot'], - cur=cur)['branches'] + ori_visit['occurrences'] = self.snapshot_get( + ori_visit['snapshot'], db=db, cur=cur)['branches'] return ori_visit # TODO: remove Backwards compatibility after snapshot migration occs = {} for occ in db.occurrence_by_origin_visit(origin, visit): _, branch_name, target, target_type = occ occs[branch_name] = { 'target': target, 'target_type': target_type } ori_visit['occurrences'] = occs return ori_visit @db_transaction_generator def revision_get_by(self, origin_id, branch_name=None, timestamp=None, limit=None, + db=None, cur=None): """Given an origin_id, retrieve occurrences' list per given criterions. Args: origin_id: The origin to filter on. branch_name: (optional) branch name. timestamp: (optional) time. limit: (optional) limit Yields: List of occurrences matching the criterions or None if nothing is found. """ - for line in self.db.revision_get_by(origin_id, - branch_name, - timestamp, - limit=limit, - cur=cur): + for line in db.revision_get_by(origin_id, branch_name, timestamp, + limit=limit, cur=cur): data = converters.db_to_revision( - dict(zip(self.db.revision_get_cols, line)) + dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data - def release_get_by(self, origin_id, limit=None): + @db_transaction_generator + def release_get_by(self, origin_id, limit=None, db=None, cur=None): """Given an origin id, return all the tag objects pointing to heads of origin_id. Args: origin_id: the origin to filter on. limit: None by default Yields: List of releases matching the criterions or None if nothing is found. """ - - for line in self.db.release_get_by(origin_id, limit=limit): + for line in db.release_get_by(origin_id, limit=limit, cur=cur): data = converters.db_to_release( - dict(zip(self.db.release_get_cols, line)) + dict(zip(db.release_get_cols, line)) ) yield data @db_transaction - def object_find_by_sha1_git(self, ids, cur=None): + def object_find_by_sha1_git(self, ids, db=None, cur=None): """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 - id: the id of the object found - object_id: the numeric id of the object found. """ - db = self.db - ret = {id: [] for id in ids} - for retval in db.object_find_by_sha1_git(ids): + for retval in db.object_find_by_sha1_git(ids, cur=cur): if retval[1]: ret[retval[0]].append(dict(zip(db.object_find_by_sha1_git_cols, retval))) return ret origin_keys = ['id', 'type', 'url', 'lister', 'project'] @db_transaction - def origin_get(self, origin, cur=None): + def origin_get(self, origin, db=None, cur=None): """Return the origin either identified by its id or its tuple (type, url). Args: origin: dictionary representing the individual origin to find. This dict has either the keys type and url: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to or the id: - id: the origin id Returns: dict: the origin dictionary with the keys: - id: origin's id - type: origin's type - url: origin's url - lister: lister's uuid - project: project's uuid (FIXME, retrieve this information) Raises: ValueError: if the keys does not match (url and type) nor id. """ - db = self.db - origin_id = origin.get('id') if origin_id: # check lookup per id first ori = db.origin_get(origin_id, cur) elif 'type' in origin and 'url' in origin: # or lookup per type, url ori = db.origin_get_with(origin['type'], origin['url'], cur) else: # unsupported lookup raise ValueError('Origin must have either id or (type and url).') if ori: return dict(zip(self.origin_keys, ori)) return None @db_transaction_generator def origin_search(self, url_pattern, offset=0, limit=50, - regexp=False, cur=None): + regexp=False, db=None, cur=None): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. Args: url_pattern: the string pattern to search for in origin urls offset: number of found origins to skip before returning results limit: the maximum number of found origins to return regexp: if True, consider the provided pattern as a regular expression and return origins whose urls match it Returns: An iterable of dict containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`. """ - db = self.db - for origin in db.origin_search(url_pattern, offset, limit, regexp, cur): yield dict(zip(self.origin_keys, origin)) @db_transaction - def _person_add(self, person, cur=None): + def _person_add(self, person, db=None, cur=None): """Add a person in storage. Note: Internal function for now, do not use outside of this module. Do not do anything fancy in case a person already exists. Please adapt code if more checks are needed. Args: person: dictionary with keys name and email. Returns: Id of the new person. """ - db = self.db - return db.person_add(person) @db_transaction_generator - def person_get(self, person, cur=None): + def person_get(self, person, db=None, cur=None): """Return the persons identified by their ids. Args: person: array of ids. Returns: The array of persons corresponding of the ids. """ - db = self.db - for person in db.person_get(person): yield dict(zip(db.person_get_cols, person)) @db_transaction - def origin_add(self, origins, cur=None): + def origin_add(self, origins, db=None, cur=None): """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: ids corresponding to the given origins """ ret = [] for origin in origins: - ret.append(self.origin_add_one(origin, cur=cur)) + ret.append(self.origin_add_one(origin, db=db, cur=cur)) return ret @db_transaction - def origin_add_one(self, origin, cur=None): + def origin_add_one(self, origin, db=None, cur=None): """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. """ - db = self.db - data = db.origin_get_with(origin['type'], origin['url'], cur) if data: return data[0] return db.origin_add(origin['type'], origin['url'], cur) @db_transaction - def fetch_history_start(self, origin_id, cur=None): + def fetch_history_start(self, origin_id, db=None, cur=None): """Add an entry for origin origin_id in fetch_history. Returns the id of the added fetch_history entry """ fetch_history = { 'origin': origin_id, 'date': datetime.datetime.now(tz=datetime.timezone.utc), } - return self.db.create_fetch_history(fetch_history, cur) + return db.create_fetch_history(fetch_history, cur) @db_transaction - def fetch_history_end(self, fetch_history_id, data, cur=None): + def fetch_history_end(self, fetch_history_id, data, db=None, cur=None): """Close the fetch_history entry with id `fetch_history_id`, replacing its data with `data`. """ now = datetime.datetime.now(tz=datetime.timezone.utc) - fetch_history = self.db.get_fetch_history(fetch_history_id, cur) + fetch_history = db.get_fetch_history(fetch_history_id, cur) if not fetch_history: raise ValueError('No fetch_history with id %d' % fetch_history_id) fetch_history['duration'] = now - fetch_history['date'] fetch_history.update(data) - self.db.update_fetch_history(fetch_history, cur) + db.update_fetch_history(fetch_history, cur) @db_transaction - def fetch_history_get(self, fetch_history_id, cur=None): + def fetch_history_get(self, fetch_history_id, db=None, cur=None): """Get the fetch_history entry with id `fetch_history_id`. """ - return self.db.get_fetch_history(fetch_history_id, cur) + return db.get_fetch_history(fetch_history_id, cur) @db_transaction - def entity_add(self, entities, cur=None): + def entity_add(self, entities, db=None, cur=None): """Add the given entitites to the database (in entity_history). Args: entities (iterable): iterable of dictionaries with the following keys: - uuid (uuid): id of the entity - parent (uuid): id of the parent entity - name (str): name of the entity - type (str): type of entity (one of 'organization', 'group_of_entities', 'hosting', 'group_of_persons', 'person', 'project') - description (str, optional): description of the entity - homepage (str): url of the entity's homepage - active (bool): whether the entity is active - generated (bool): whether the entity was generated - lister_metadata (dict): lister-specific entity metadata - metadata (dict): other metadata for the entity - validity (datetime.DateTime array): timestamps at which we listed the entity. """ - db = self.db - cols = list(db.entity_history_cols) cols.remove('id') db.mktemp_entity_history() db.copy_to(entities, 'tmp_entity_history', cols, cur) db.entity_history_add_from_temp() @db_transaction_generator - def entity_get_from_lister_metadata(self, entities, cur=None): + def entity_get_from_lister_metadata(self, entities, db=None, cur=None): """Fetch entities from the database, matching with the lister and associated metadata. Args: entities (iterable): dictionaries containing the lister metadata to look for. Useful keys are 'lister', 'type', 'id', ... Yields: fetched entities with all their attributes. If no match was found, the returned entity is None. """ - db = self.db - db.mktemp_entity_lister(cur) mapped_entities = [] for i, entity in enumerate(entities): mapped_entity = { 'id': i, 'lister_metadata': entity, } mapped_entities.append(mapped_entity) db.copy_to(mapped_entities, 'tmp_entity_lister', ['id', 'lister_metadata'], cur) cur.execute('''select id, %s from swh_entity_from_tmp_entity_lister() order by id''' % ','.join(db.entity_cols)) for id, *entity_vals in cur: fetched_entity = dict(zip(db.entity_cols, entity_vals)) if fetched_entity['uuid']: yield fetched_entity else: yield { 'uuid': None, 'lister_metadata': entities[i], } @db_transaction_generator - def entity_get(self, uuid, cur=None): + def entity_get(self, uuid, db=None, cur=None): """Returns the list of entity per its uuid identifier and also its parent hierarchy. Args: uuid: entity's identifier Returns: List of entities starting with entity with uuid and the parent hierarchy from such entity. """ - db = self.db for entity in db.entity_get(uuid, cur): yield dict(zip(db.entity_cols, entity)) @db_transaction - def entity_get_one(self, uuid, cur=None): + def entity_get_one(self, uuid, db=None, cur=None): """Returns one entity using its uuid identifier. Args: uuid: entity's identifier Returns: the object corresponding to the given entity """ - db = self.db entity = db.entity_get_one(uuid, cur) if entity: return dict(zip(db.entity_cols, entity)) else: return None @db_transaction - def stat_counters(self, cur=None): + def stat_counters(self, db=None, cur=None): """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) """ - return {k: v for (k, v) in self.db.stat_counters()} + return {k: v for (k, v) in db.stat_counters()} @db_transaction def origin_metadata_add(self, origin_id, ts, provider, tool, metadata, - cur=None): + db=None, cur=None): """ Add an origin_metadata for the origin at ts with provenance and metadata. Args: origin_id (int): the origin's id 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 Returns: id (int): the origin_metadata unique id """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) - return self.db.origin_metadata_add(origin_id, ts, provider, tool, - metadata, cur) + return db.origin_metadata_add(origin_id, ts, provider, tool, + metadata, cur) @db_transaction_generator - def origin_metadata_get_by(self, origin_id, provider_type=None, cur=None): + def origin_metadata_get_by(self, origin_id, provider_type=None, db=None, + cur=None): """Retrieve list of all origin_metadata entries for the origin_id Args: origin_id (int): the unique origin identifier provider_type (str): (optional) type of provider Returns: list of dicts: the origin_metadata dictionary with the keys: - id (int): origin_metadata's id - 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) """ - db = self.db for line in db.origin_metadata_get_by(origin_id, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) @db_transaction_generator - def tool_add(self, tools, cur=None): + def tool_add(self, tools, db=None, cur=None): """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: `iterable` of :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. """ - db = self.db db.mktemp_tool(cur) db.copy_to(tools, 'tmp_tool', ['name', 'version', 'configuration'], cur) tools = db.tool_add_from_temp(cur) for line in tools: yield dict(zip(db.tool_cols, line)) @db_transaction - def tool_get(self, tool, cur=None): + def tool_get(self, tool, db=None, cur=None): """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. """ - db = self.db 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) if not idx: return None - return dict(zip(self.db.tool_cols, idx)) + return dict(zip(db.tool_cols, idx)) @db_transaction def metadata_provider_add(self, provider_name, provider_type, provider_url, - metadata, cur=None): - db = self.db + metadata, db=None, cur=None): return db.metadata_provider_add(provider_name, provider_type, provider_url, metadata, cur) @db_transaction - def metadata_provider_get(self, provider_id, cur=None): - db = self.db + 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(self.db.metadata_provider_cols, result)) + return dict(zip(db.metadata_provider_cols, result)) @db_transaction - def metadata_provider_get_by(self, provider, cur=None): - db = self.db + def metadata_provider_get_by(self, provider, db=None, cur=None): result = db.metadata_provider_get_by(provider['provider_name'], provider['provider_url']) if not result: return None - return dict(zip(self.db.metadata_provider_cols, result)) + return dict(zip(db.metadata_provider_cols, result)) 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). """ return diff.diff_directories(self, from_dir, to_dir, track_renaming) 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). """ return diff.diff_revisions(self, from_rev, to_rev, track_renaming) 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). """ return diff.diff_revision(self, revision, track_renaming) diff --git a/swh/storage/tests/server_testing.py b/swh/storage/tests/server_testing.py deleted file mode 100644 index f3c57588a..000000000 --- a/swh/storage/tests/server_testing.py +++ /dev/null @@ -1,146 +0,0 @@ -# Copyright (C) 2015-2017 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 abc -import aiohttp -import multiprocessing -import socket -import time - -from urllib.request import urlopen - - -class ServerTestFixtureBaseClass(metaclass=abc.ABCMeta): - """Base class for http client/server testing implementations. - - Override this class to implement the following methods: - - process_config: to do something needed for the server - configuration (e.g propagate the configuration to other part) - - define_worker_function: define the function that will actually - run the server. - - To ensure test isolation, each test will run in a different server - and a different folder. - - In order to correctly work, the subclass must call the parents - class's setUp() and tearDown() methods. - - """ - def setUp(self): - super().setUp() - self.start_server() - - def tearDown(self): - self.stop_server() - super().tearDown() - - def url(self): - return 'http://127.0.0.1:%d/' % self.port - - def process_config(self): - """Process the server's configuration. Do something useful for - example, pass along the self.config dictionary inside the - self.app. - - By default, do nothing. - - """ - pass - - @abc.abstractmethod - def define_worker_function(self, app, port): - """Define how the actual implementation server will run. - - """ - pass - - def start_server(self): - """ Spawn the API server using multiprocessing. - """ - self.process = None - - self.process_config() - - # Get an available port number - sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) - sock.bind(('127.0.0.1', 0)) - self.port = sock.getsockname()[1] - sock.close() - - worker_fn = self.define_worker_function() - - self.process = multiprocessing.Process( - target=worker_fn, args=(self.app, self.port) - ) - self.process.start() - - # Wait max 5 seconds for server to spawn - i = 0 - while i < 500: - try: - urlopen(self.url()) - except Exception: - i += 1 - time.sleep(0.01) - else: - return - - def stop_server(self): - """ Terminate the API server's process. - """ - if self.process: - self.process.terminate() - - -class ServerTestFixture(ServerTestFixtureBaseClass): - """Base class for http client/server testing (e.g flask). - - Mix this in a test class in order to have access to an http server - running in background. - - Note that the subclass should define a dictionary in self.config - that contains the server config. And an application in self.app - that corresponds to the type of server the tested client needs. - - To ensure test isolation, each test will run in a different server - and a different folder. - - In order to correctly work, the subclass must call the parents - class's setUp() and tearDown() methods. - """ - def process_config(self): - # WSGI app configuration - for key, value in self.config.items(): - self.app.config[key] = value - - def define_worker_function(self): - def worker(app, port): - return app.run(port=port, use_reloader=False) - - return worker - - -class ServerTestFixtureAsync(ServerTestFixtureBaseClass): - """Base class for http client/server async testing (e.g aiohttp). - - Mix this in a test class in order to have access to an http server - running in background. - - Note that the subclass should define an application in self.app - that corresponds to the type of server the tested client needs. - - To ensure test isolation, each test will run in a different server - and a different folder. - - In order to correctly work, the subclass must call the parents - class's setUp() and tearDown() methods. - - """ - def define_worker_function(self): - def worker(app, port): - return aiohttp.web.run_app(app, port=int(port), - print=lambda *_: None) - - return worker diff --git a/swh/storage/tests/storage_testing.py b/swh/storage/tests/storage_testing.py index 8d0a098a6..13ecb9b75 100644 --- a/swh/storage/tests/storage_testing.py +++ b/swh/storage/tests/storage_testing.py @@ -1,72 +1,73 @@ # Copyright (C) 2015-2017 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 tempfile import pathlib from swh.storage import get_storage class StorageTestFixture: """Mix this in a test subject class to get Storage testing support. This fixture requires to come before DbTestFixture in the inheritance list as it uses its methods to setup its own internal database. Usage example: class TestStorage(StorageTestFixture, DbTestFixture): ... """ TEST_STORAGE_DB_NAME = 'softwareheritage-test-storage' @classmethod def setUpClass(cls): if not hasattr(cls, 'DB_TEST_FIXTURE_IMPORTED'): raise RuntimeError("StorageTestFixture needs to be followed by " "DbTestFixture in the inheritance list.") test_dir = pathlib.Path(__file__).absolute().parent test_data_dir = test_dir / '../../../../swh-storage-testdata' test_db_dump = (test_data_dir / 'dumps/swh.dump').absolute() cls.add_db(cls.TEST_STORAGE_DB_NAME, str(test_db_dump), 'pg_dump') super().setUpClass() def setUp(self): super().setUp() self.objtmp = tempfile.TemporaryDirectory() self.storage_config = { 'cls': 'local', 'args': { - 'db': self.test_db[self.TEST_STORAGE_DB_NAME].conn, + 'db': 'dbname=%s' % self.TEST_STORAGE_DB_NAME, 'objstorage': { 'cls': 'pathslicing', 'args': { 'root': self.objtmp.name, 'slicing': '0:1/1:5', }, }, }, } self.storage = get_storage(**self.storage_config) def tearDown(self): self.objtmp.cleanup() + self.storage = None super().tearDown() def reset_storage_tables(self): excluded = {'dbversion', 'entity', 'entity_history', 'listable_entity', 'tool'} self.reset_db_tables(self.TEST_STORAGE_DB_NAME, excluded=excluded) db = self.test_db[self.TEST_STORAGE_DB_NAME] conn = db.conn cursor = db.cursor cursor.execute('delete from entity where generated=true') cursor.execute('delete from entity_history where generated=true') conn.commit() diff --git a/swh/storage/tests/test_api_client.py b/swh/storage/tests/test_api_client.py index cd73e512a..d6f1e5268 100644 --- a/swh/storage/tests/test_api_client.py +++ b/swh/storage/tests/test_api_client.py @@ -1,49 +1,54 @@ -# Copyright (C) 2015-2016 The Software Heritage developers +# 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 -import unittest +import shutil import tempfile +import unittest +from swh.core.tests.server_testing import ServerTestFixture from swh.storage.tests.test_storage import CommonTestStorage -from swh.storage.tests.server_testing import ServerTestFixture from swh.storage.api.client import RemoteStorage from swh.storage.api.server import app class TestRemoteStorage(CommonTestStorage, ServerTestFixture, unittest.TestCase): """Test the remote storage API. This class doesn't define any tests as we want identical functionality between local and remote storage. All the tests are therefore defined in CommonTestStorage. """ def setUp(self): # ServerTestFixture needs to have self.objroot for # setUp() method, but this field is defined in # AbstractTestStorage's setUp() # To avoid confusion, override the self.objroot to a - # one choosen in this class. - storage_base = tempfile.mkdtemp() + # one chosen in this class. + self.storage_base = tempfile.mkdtemp() self.config = { 'storage': { 'cls': 'local', 'args': { 'db': 'dbname=%s' % self.TEST_STORAGE_DB_NAME, 'objstorage': { 'cls': 'pathslicing', 'args': { - 'root': storage_base, - 'slicing': '0:2/2:4/4:6', + 'root': self.storage_base, + 'slicing': '0:2', }, }, } } } self.app = app super().setUp() self.storage = RemoteStorage(self.url()) - self.objroot = storage_base + self.objroot = self.storage_base + + def tearDown(self): + super().tearDown() + shutil.rmtree(self.storage_base) diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index cb99e7fd2..68b41938b 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,2522 +1,2542 @@ # Copyright (C) 2015-2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy import datetime from operator import itemgetter import psycopg2 import unittest from uuid import UUID -from unittest.mock import patch +from unittest.mock import Mock, patch from nose.tools import istest from nose.plugins.attrib import attr from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.core.tests.db_testing import DbTestFixture from swh.storage.tests.storage_testing import StorageTestFixture @attr('db') class BaseTestStorage(StorageTestFixture, DbTestFixture): def setUp(self): super().setUp() db = self.test_db[self.TEST_STORAGE_DB_NAME] self.conn = db.conn self.cursor = db.cursor self.maxDiff = None self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hash_to_bytes( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hash_to_bytes( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hash_to_bytes( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), 'blake2s256': hash_to_bytes('d5fe1939576527e42cfd76a9455a2' '432fe7f56669564577dd93c4280e76d661d'), 'status': 'visible', } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hash_to_bytes( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hash_to_bytes( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hash_to_bytes( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), 'blake2s256': hash_to_bytes('849c20fad132b7c2d62c15de310adfe87be' '94a379941bed295e8141c6219810d'), 'status': 'visible', } self.cont3 = { 'data': b'424242\n', 'length': 7, 'sha1': hash_to_bytes( '3e21cc4942a4234c9e5edd8a9cacd1670fe59f13'), 'sha1_git': hash_to_bytes( 'c932c7649c6dfa4b82327d121215116909eb3bea'), 'sha256': hash_to_bytes( '92fb72daf8c6818288a35137b72155f5' '07e5de8d892712ab96277aaed8cf8a36'), 'blake2s256': hash_to_bytes('76d0346f44e5a27f6bafdd9c2befd304af' 'f83780f93121d801ab6a1d4769db11'), 'status': 'visible', } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hash_to_bytes( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hash_to_bytes( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes('306856b8fd879edb7b6f1aeaaf8db9bbecc9' '93cd7f776c333ac3a782fa5c6eba'), 'status': 'absent', } self.skipped_cont = { 'length': 1024 * 1024 * 200, 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8920'), 'sha1': hash_to_bytes( '43e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '7bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( 'ade18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.skipped_cont2 = { 'length': 1024 * 1024 * 300, 'sha1_git': hash_to_bytes( '44e45d56f88993aae6a0198013efa80716fd8921'), 'sha1': hash_to_bytes( '54e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '8cbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( '9ce18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.dir = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90', 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': from_disk.DentryPerms.content, }, { 'name': b'bar\xc3', 'type': 'dir', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.directory, }, ], } self.dir2 = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa95', 'entries': [ { 'name': b'oof', 'type': 'file', 'target': self.cont2['sha1_git'], 'perms': from_disk.DentryPerms.content, } ], } self.dir3 = { 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'), 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': from_disk.DentryPerms.content, }, { 'name': b'bar', 'type': 'dir', 'target': b'12345678901234560000', 'perms': from_disk.DentryPerms.directory, }, { 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.content, }, ], } self.minus_offset = datetime.timezone(datetime.timedelta(minutes=-120)) self.plus_offset = datetime.timezone(datetime.timedelta(minutes=120)) self.revision = { 'id': b'56789012345678901234', 'message': b'hello', 'author': { 'name': b'Nicolas Dandrimont', 'email': b'nicolas@example.com', 'fullname': b'Nicolas Dandrimont ', }, 'date': { 'timestamp': 1234567890, 'offset': 120, 'negative_utc': None, }, 'committer': { 'name': b'St\xc3fano Zacchiroli', 'email': b'stefano@example.com', 'fullname': b'St\xc3fano Zacchiroli ' }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': True, }, 'parents': [b'01234567890123456789', b'23434512345123456789'], 'type': 'git', 'directory': self.dir['id'], '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 } self.revision2 = { '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': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': False, }, 'parents': [b'01234567890123456789'], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': False } self.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 ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1127351742, 'offset': 0, 'negative_utc': False, }, 'parents': [], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': True } self.revision4 = { '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': None, }, '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': None, }, 'parents': [self.revision3['id']], 'type': 'git', 'directory': self.dir['id'], 'metadata': None, 'synthetic': False } self.origin = { 'url': 'file:///dev/null', 'type': 'git', } self.origin2 = { 'url': 'file:///dev/zero', 'type': 'git', } self.provider = { 'name': 'hal', 'type': 'deposit-client', 'url': 'http:///hal/inria', 'metadata': { 'location': 'France' } } self.metadata_tool = { 'name': 'swh-deposit', 'version': '0.0.1', 'configuration': { 'sword_version': '2' } } self.origin_metadata = { 'origin': self.origin, 'discovery_date': datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.origin_metadata2 = { 'origin': self.origin, 'discovery_date': datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.occurrence = { 'branch': b'master', 'target': self.revision['id'], 'target_type': 'revision', } self.date_visit2 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.occurrence2 = { 'branch': b'master', 'target': self.revision2['id'], 'target_type': 'revision', } self.date_visit3 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) # template occurrence to be filled in test (cf. revision_log_by) self.occurrence3 = { 'branch': b'master', 'target_type': 'revision', } self.release = { 'id': b'87659012345678901234', 'name': b'v0.0.1', 'author': { 'name': b'olasd', 'email': b'nic@olasd.fr', 'fullname': b'olasd ', }, 'date': { 'timestamp': 1234567890, 'offset': 42, 'negative_utc': None, }, 'target': b'43210987654321098765', 'target_type': 'revision', 'message': b'synthetic release', 'synthetic': True, } self.release2 = { 'id': b'56789012348765901234', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634366813, 'offset': -120, 'negative_utc': None, }, 'target': b'432109\xa9765432\xc309\x00765', 'target_type': 'revision', - 'message': b'v0.0.2\nMisc performance improvments + bug fixes', + 'message': b'v0.0.2\nMisc performance improvements + bug fixes', 'synthetic': False } self.release3 = { 'id': b'87659012345678904321', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'tony@ardumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634336813, 'offset': 0, 'negative_utc': False, }, 'target': self.revision2['id'], 'target_type': 'revision', 'message': b'yet another synthetic release', 'synthetic': True, } self.fetch_history_date = datetime.datetime( 2015, 1, 2, 21, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_end = datetime.datetime( 2015, 1, 2, 23, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_duration = (self.fetch_history_end - self.fetch_history_date) self.fetch_history_data = { 'status': True, 'result': {'foo': 'bar'}, 'stdout': 'blabla', 'stderr': 'blablabla', } self.entity1 = { 'uuid': UUID('f96a7ec1-0058-4920-90cc-7327e4b5a4bf'), # GitHub users 'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'), 'name': 'github:user:olasd', 'type': 'person', 'description': 'Nicolas Dandrimont', 'homepage': 'http://example.com', 'active': True, 'generated': True, 'lister_metadata': { # swh.lister.github 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 12877, 'type': 'user', 'last_activity': '2015-11-03', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity1_query = { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 12877, 'type': 'user', } self.entity2 = { 'uuid': UUID('3903d075-32d6-46d4-9e29-0aef3612c4eb'), # GitHub users 'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'), 'name': 'github:user:zacchiro', 'type': 'person', 'description': 'Stefano Zacchiroli', 'homepage': 'http://example.com', 'active': True, 'generated': True, 'lister_metadata': { # swh.lister.github 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 216766, 'type': 'user', 'last_activity': '2015-11-03', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity3 = { 'uuid': UUID('111df473-c1d2-4f40-bc58-2b091d4a7111'), # GitHub users 'parent': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'), 'name': 'github:user:ardumont', 'type': 'person', 'description': 'Antoine R. Dumont a.k.a tony', 'homepage': 'https://ardumont.github.io', 'active': True, 'generated': True, 'lister_metadata': { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 666, 'type': 'user', 'last_activity': '2016-01-15', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity4 = { 'uuid': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'), # GitHub users 'parent': None, 'name': 'github:user:ToNyX', 'type': 'person', 'description': 'ToNyX', 'homepage': 'https://ToNyX.github.io', 'active': True, 'generated': True, 'lister_metadata': { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 999, 'type': 'user', 'last_activity': '2015-12-24', }, 'metadata': None, 'validity': [ datetime.datetime(2015, 11, 3, 11, 0, 0, tzinfo=datetime.timezone.utc), ] } self.entity2_query = { 'lister_metadata': { 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4', 'id': 216766, 'type': 'user', }, } self.snapshot = { 'id': hash_to_bytes('2498dbf535f882bc7f9a18fb16c9ad27fda7bab7'), 'branches': { self.occurrence['branch']: { 'target': self.occurrence['target'], 'target_type': self.occurrence['target_type'], }, }, } self.empty_snapshot = { 'id': hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'branches': {}, } self.complete_snapshot = { 'id': hash_to_bytes('6e65b86363953b780d92b0a928f3e8fcdd10db36'), 'branches': { b'directory': { 'target': hash_to_bytes( '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'), 'target_type': 'directory', }, b'content': { 'target': hash_to_bytes( 'fe95a46679d128ff167b7c55df5d02356c5a1ae1'), 'target_type': 'content', }, b'alias': { 'target': b'revision', 'target_type': 'alias', }, b'revision': { 'target': hash_to_bytes( 'aafb16d69fd30ff58afdd69036a26047f3aebdc6'), 'target_type': 'revision', }, b'release': { 'target': hash_to_bytes( '7045404f3d1c54e6473c71bbb716529fbad4be24'), 'target_type': 'release', }, b'snapshot': { 'target': hash_to_bytes( '1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'target_type': 'snapshot', }, b'dangling': None, } } def tearDown(self): self.reset_storage_tables() super().tearDown() class CommonTestStorage(BaseTestStorage): """Base 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. """ @staticmethod def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ('date', 'committer_date'): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity @istest def check_config(self): self.assertTrue(self.storage.check_config(check_write=True)) self.assertTrue(self.storage.check_config(check_write=False)) @istest def content_add(self): cont = self.cont self.storage.content_add([cont]) if hasattr(self.storage, 'objstorage'): self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) @istest def content_add_collision(self): cont1 = self.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b['sha256']) sha256_array[0] += 1 cont1b['sha256'] = bytes(sha256_array) with self.assertRaises(psycopg2.IntegrityError): self.storage.content_add([cont1, cont1b]) @istest def skipped_content_add(self): cont = self.skipped_cont.copy() cont2 = self.skipped_cont2.copy() cont2['blake2s256'] = None self.storage.content_add([cont, cont, cont2]) self.cursor.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') datums = self.cursor.fetchall() self.assertEquals(2, len(datums)) datum = datums[0] self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3].tobytes(), datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') ) datum2 = datums[1] self.assertEqual( (datum2[0].tobytes(), datum2[1].tobytes(), datum2[2].tobytes(), datum2[3], datum2[4], datum2[5], datum2[6]), (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') ) @istest def content_missing(self): cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) gen = self.storage.content_missing([cont2, missing_cont]) self.assertEqual(list(gen), [missing_cont['sha1']]) @istest def content_missing_per_sha1(self): # given cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) # when gen = self.storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then self.assertEqual(list(gen), [missing_cont['sha1']]) @istest def content_get_metadata(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([cont1['sha1'], cont2['sha1']]) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') self.assertEqual(list(gen), [cont1, cont2]) @istest def content_get_metadata_missing_sha1(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() missing_cont = self.missing_cont.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([missing_cont['sha1']]) # All the metadata keys are None missing_cont.pop('data') for key in list(missing_cont): if key != 'sha1': missing_cont[key] = None self.assertEqual(list(gen), [missing_cont]) @istest def directory_get(self): # given init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) # when actual_dirs = list(self.storage.directory_get([self.dir['id']])) self.assertEqual(len(actual_dirs), 1) dir0 = actual_dirs[0] self.assertEqual(dir0['id'], self.dir['id']) # ids are generated so non deterministic value self.assertEqual(len(dir0['file_entries']), 1) self.assertEqual(len(dir0['dir_entries']), 1) self.assertIsNone(dir0['rev_entries']) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) @istest def directory_add(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) stored_data = list(self.storage.directory_ls(self.dir['id'])) data_to_store = [] for ent in sorted(self.dir['entries'], key=itemgetter('name')): data_to_store.append({ 'dir_id': self.dir['id'], 'type': ent['type'], 'target': ent['target'], 'name': ent['name'], 'perms': ent['perms'], 'status': None, 'sha1': None, 'sha1_git': None, 'sha256': None, 'length': None, }) self.assertEqual(data_to_store, stored_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) @istest def directory_entry_get_by_path(self): # given init_missing = list(self.storage.directory_missing([self.dir3['id']])) self.assertEqual([self.dir3['id']], init_missing) self.storage.directory_add([self.dir3]) expected_entries = [ { 'dir_id': self.dir3['id'], 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'bar', 'type': 'dir', 'target': b'12345678901234560000', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.directory, 'length': None, }, { 'dir_id': self.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(self.dir3['entries'], expected_entries): actual_entry = self.storage.directory_entry_get_by_path( self.dir3['id'], [entry['name']]) self.assertEqual(actual_entry, expected_entry) # when (nothing should be found here since self.dir is not persisted.) for entry in self.dir['entries']: actual_entry = self.storage.directory_entry_get_by_path( self.dir['id'], [entry['name']]) self.assertIsNone(actual_entry) @istest def revision_add(self): init_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([self.revision['id']], list(init_missing)) self.storage.revision_add([self.revision]) end_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([], list(end_missing)) @istest def revision_log(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_log( [self.revision4['id']])) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEquals(actual_results[0], self.normalize_entity(self.revision4)) self.assertEquals(actual_results[1], self.normalize_entity(self.revision3)) @istest def revision_log_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_log( [self.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 1) self.assertEquals(actual_results[0], self.revision4) @istest def revision_log_by(self): # given origin_id = self.storage.origin_add_one(self.origin2) self.storage.revision_add([self.revision3, self.revision4]) # occurrence3 targets 'revision4' # with branch 'master' and origin origin_id occurrence3 = self.occurrence3.copy() date_visit1 = self.date_visit3 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) occurrence3.update({ 'origin': origin_id, 'target': self.revision4['id'], 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occurrence3]) # self.revision4 -is-child-of-> self.revision3 # when actual_results = list(self.storage.revision_log_by( origin_id, branch_name=occurrence3['branch'], timestamp=date_visit1)) # hack: ids generated for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 2) self.assertEquals(actual_results[0], self.normalize_entity(self.revision4)) self.assertEquals(actual_results[1], self.normalize_entity(self.revision3)) # when - 2 actual_results = list(self.storage.revision_log_by( origin_id, branch_name=None, timestamp=None, limit=1)) # then for actual_result in actual_results: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEqual(len(actual_results), 1) self.assertEquals(actual_results[0], self.revision4) # when - 3 (revision not found) actual_res = list(self.storage.revision_log_by( origin_id, branch_name='inexistant-branch', timestamp=None)) self.assertEquals(actual_res, []) @staticmethod def _short_revision(revision): return [revision['id'], revision['parents']] @istest def revision_shortlog(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_shortlog( [self.revision4['id']])) self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEquals(list(actual_results[0]), self._short_revision(self.revision4)) self.assertEquals(list(actual_results[1]), self._short_revision(self.revision3)) @istest def revision_shortlog_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_shortlog( [self.revision4['id']], 1)) self.assertEqual(len(actual_results), 1) self.assertEquals(list(actual_results[0]), self._short_revision(self.revision4)) @istest def revision_get(self): self.storage.revision_add([self.revision]) actual_revisions = list(self.storage.revision_get( [self.revision['id'], self.revision2['id']])) # when del actual_revisions[0]['author']['id'] # hack: ids are generated del actual_revisions[0]['committer']['id'] self.assertEqual(len(actual_revisions), 2) self.assertEqual(actual_revisions[0], self.normalize_entity(self.revision)) self.assertIsNone(actual_revisions[1]) @istest def revision_get_no_parents(self): self.storage.revision_add([self.revision3]) get = list(self.storage.revision_get([self.revision3['id']])) self.assertEqual(len(get), 1) self.assertEqual(get[0]['parents'], []) # no parents on this one @istest def revision_get_by(self): # given self.storage.content_add([self.cont2]) self.storage.directory_add([self.dir2]) # point to self.cont self.storage.revision_add([self.revision2]) # points to self.dir origin_id = self.storage.origin_add_one(self.origin2) # occurrence2 points to 'revision2' with branch 'master', we # need to point to the right origin occurrence2 = self.occurrence2.copy() date_visit1 = self.date_visit2 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) occurrence2.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occurrence2]) # we want only revision 2 expected_revisions = list(self.storage.revision_get( [self.revision2['id']])) # when actual_results = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], None)) self.assertEqual(actual_results[0], expected_revisions[0]) # when (with no branch filtering, it's still ok) actual_results = list(self.storage.revision_get_by( origin_id, None, None)) self.assertEqual(actual_results[0], expected_revisions[0]) @istest def revision_get_by_multiple_occurrence(self): # 2 occurrences pointing to 2 different revisions - # each occurence have 1 day delta + # each occurrence have 1 day delta # the api must return the revision whose occurrence is the nearest. # given self.storage.content_add([self.cont2]) self.storage.directory_add([self.dir2]) self.storage.revision_add([self.revision2, self.revision3]) origin_id = self.storage.origin_add_one(self.origin2) # occurrence2 points to 'revision2' with branch 'master', we # need to point to the right origin date_visit1 = self.date_visit2 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) occurrence2 = self.occurrence2.copy() occurrence2.update({ 'origin': origin_id, 'visit': origin_visit1['visit'] }) dt = datetime.timedelta(days=1) date_visit2 = date_visit1 + dt origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2) occurrence3 = self.occurrence2.copy() occurrence3.update({ 'origin': origin_id, 'visit': origin_visit2['visit'], 'target': self.revision3['id'], }) # 2 occurrences on same revision with lower validity date with 1 day # delta self.storage.occurrence_add([occurrence2]) self.storage.occurrence_add([occurrence3]) # when actual_results0 = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], date_visit1)) # hack: ids are generated del actual_results0[0]['author']['id'] del actual_results0[0]['committer']['id'] self.assertEquals(len(actual_results0), 1) self.assertEqual(actual_results0, [self.normalize_entity(self.revision2)]) # when actual_results1 = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], date_visit1 + dt/3)) # closer to first visit # hack: ids are generated del actual_results1[0]['author']['id'] del actual_results1[0]['committer']['id'] self.assertEquals(len(actual_results1), 1) self.assertEqual(actual_results1, [self.normalize_entity(self.revision2)]) # when actual_results2 = list(self.storage.revision_get_by( origin_id, occurrence2['branch'], date_visit1 + 2*dt/3)) # closer to second visit del actual_results2[0]['author']['id'] del actual_results2[0]['committer']['id'] self.assertEquals(len(actual_results2), 1) self.assertEqual(actual_results2, [self.normalize_entity(self.revision3)]) # when actual_results3 = list(self.storage.revision_get_by( origin_id, occurrence3['branch'], date_visit2)) # hack: ids are generated del actual_results3[0]['author']['id'] del actual_results3[0]['committer']['id'] self.assertEquals(len(actual_results3), 1) self.assertEqual(actual_results3, [self.normalize_entity(self.revision3)]) # when actual_results4 = list(self.storage.revision_get_by( origin_id, None, None)) for actual_result in actual_results4: del actual_result['author']['id'] del actual_result['committer']['id'] self.assertEquals(len(actual_results4), 1) self.assertCountEqual(actual_results4, [self.normalize_entity(self.revision3)]) @istest def release_add(self): init_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([self.release['id'], self.release2['id']], list(init_missing)) self.storage.release_add([self.release, self.release2]) end_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([], list(end_missing)) @istest def release_get(self): # given self.storage.release_add([self.release, self.release2]) # when actual_releases = list(self.storage.release_get([self.release['id'], self.release2['id']])) # then for actual_release in actual_releases: del actual_release['author']['id'] # hack: ids are generated self.assertEquals([self.normalize_entity(self.release), self.normalize_entity(self.release2)], [actual_releases[0], actual_releases[1]]) @istest def release_get_by(self): # given self.storage.revision_add([self.revision2]) # points to self.dir self.storage.release_add([self.release3]) origin_id = self.storage.origin_add_one(self.origin2) # occurrence2 points to 'revision2' with branch 'master', we # need to point to the right origin origin_visit = self.storage.origin_visit_add(origin_id, self.date_visit2) occurrence2 = self.occurrence2.copy() occurrence2.update({ 'origin': origin_id, 'visit': origin_visit['visit'], }) self.storage.occurrence_add([occurrence2]) # we want only revision 2 expected_releases = list(self.storage.release_get( [self.release3['id']])) # when actual_results = list(self.storage.release_get_by( occurrence2['origin'])) # then self.assertEqual(actual_results[0], expected_releases[0]) @istest def origin_add_one(self): origin0 = self.storage.origin_get(self.origin) self.assertIsNone(origin0) id = self.storage.origin_add_one(self.origin) actual_origin = self.storage.origin_get({'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin['id'], id) id2 = self.storage.origin_add_one(self.origin) self.assertEqual(id, id2) @istest def origin_add(self): origin0 = self.storage.origin_get(self.origin) self.assertIsNone(origin0) id1, id2 = self.storage.origin_add([self.origin, self.origin2]) actual_origin = self.storage.origin_get({ 'url': self.origin['url'], 'type': self.origin['type'], }) self.assertEqual(actual_origin['id'], id1) actual_origin2 = self.storage.origin_get({ 'url': self.origin2['url'], 'type': self.origin2['type'], }) self.assertEqual(actual_origin2['id'], id2) @istest def origin_add_twice(self): add1 = self.storage.origin_add([self.origin, self.origin2]) add2 = self.storage.origin_add([self.origin, self.origin2]) self.assertEqual(add1, add2) @istest def origin_get(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) # lookup per type and url (returns id) actual_origin0 = self.storage.origin_get({'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin0['id'], id) # lookup per id (returns dict) actual_origin1 = self.storage.origin_get({'id': id}) self.assertEqual(actual_origin1, {'id': id, 'type': self.origin['type'], 'url': self.origin['url'], 'lister': None, 'project': None}) @istest def origin_search(self): found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 0) found_origins = list(self.storage.origin_search(self.origin['url'], regexp=True)) self.assertEqual(len(found_origins), 0) id = self.storage.origin_add_one(self.origin) origin_data = {'id': id, 'type': self.origin['type'], 'url': self.origin['url'], 'lister': None, 'project': None} found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search( '.' + self.origin['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) id2 = self.storage.origin_add_one(self.origin2) origin2_data = {'id': id2, 'type': self.origin2['type'], 'url': self.origin2['url'], 'lister': None, 'project': None} found_origins = list(self.storage.origin_search(self.origin2['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search( '.' + self.origin2['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search('/')) self.assertEqual(len(found_origins), 2) found_origins = list(self.storage.origin_search('.*/.*', regexp=True)) self.assertEqual(len(found_origins), 2) found_origins = list(self.storage.origin_search('/', offset=0, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('/', offset=1, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) @istest def origin_visit_add(self): # given self.assertIsNone(self.storage.origin_get(self.origin2)) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) # then self.assertEquals(origin_visit1['origin'], origin_id) self.assertIsNotNone(origin_visit1['visit']) self.assertTrue(origin_visit1['visit'] > 0) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEquals(actual_origin_visits, [{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) @istest def origin_visit_update(self): # given origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) origin_visit2 = self.storage.origin_visit_add( origin_id, ts=self.date_visit3) origin_visit3 = self.storage.origin_visit_add( origin_id2, ts=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) self.storage.origin_visit_update(origin_id2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEquals(actual_origin_visits, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits_bis = list(self.storage.origin_visit_get( origin_id, limit=1)) self.assertEquals(actual_origin_visits_bis, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }]) actual_origin_visits_ter = list(self.storage.origin_visit_get( origin_id, last_visit=origin_visit1['visit'])) self.assertEquals(actual_origin_visits_ter, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2)) self.assertEquals(actual_origin_visits2, [{ 'origin': origin_visit3['origin'], 'date': self.date_visit3, 'visit': origin_visit3['visit'], 'status': 'partial', 'metadata': None, 'snapshot': None, }]) @istest def origin_visit_get_by(self): origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, ts=self.date_visit2) occurrence2 = self.occurrence2.copy() occurrence2.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occurrence2]) # Add some other {origin, visit} entries self.storage.origin_visit_add(origin_id, ts=self.date_visit3) self.storage.origin_visit_add(origin_id2, ts=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], 'date': self.date_visit2, 'metadata': visit1_metadata, 'status': 'full', 'occurrences': { occurrence2['branch']: { 'target': occurrence2['target'], 'target_type': occurrence2['target_type'], } }, 'snapshot': None, }) # when actual_origin_visit1 = self.storage.origin_visit_get_by( origin_visit1['origin'], origin_visit1['visit']) # then self.assertEquals(actual_origin_visit1, expected_origin_visit) @istest def origin_visit_get_by_no_result(self): # No result actual_origin_visit = self.storage.origin_visit_get_by( 10, 999) self.assertIsNone(actual_origin_visit) @istest def occurrence_add(self): occur = self.occurrence.copy() origin_id = self.storage.origin_add_one(self.origin2) date_visit1 = self.date_visit1 origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1) revision = self.revision.copy() revision['id'] = occur['target'] self.storage.revision_add([revision]) occur.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occur]) test_query = ''' with indiv_occurrences as ( select origin, branch, target, target_type, unnest(visits) as visit from occurrence_history ) select origin, branch, target, target_type, date from indiv_occurrences left join origin_visit using(origin, visit) order by origin, date''' self.cursor.execute(test_query) ret = self.cursor.fetchall() self.assertEqual(len(ret), 1) self.assertEqual( (ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(), ret[0][3], ret[0][4]), (occur['origin'], occur['branch'], occur['target'], occur['target_type'], self.date_visit1)) date_visit2 = date_visit1 + datetime.timedelta(hours=10) origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2) occur2 = occur.copy() occur2.update({ 'visit': origin_visit2['visit'], }) self.storage.occurrence_add([occur2]) self.cursor.execute(test_query) ret = self.cursor.fetchall() self.assertEqual(len(ret), 2) self.assertEqual( (ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(), ret[0][3], ret[0][4]), (occur['origin'], occur['branch'], occur['target'], occur['target_type'], date_visit1)) self.assertEqual( (ret[1][0], ret[1][1].tobytes(), ret[1][2].tobytes(), ret[1][3], ret[1][4]), (occur2['origin'], occur2['branch'], occur2['target'], occur2['target_type'], date_visit2)) @istest def occurrence_get(self): # given occur = self.occurrence.copy() origin_id = self.storage.origin_add_one(self.origin2) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) revision = self.revision.copy() revision['id'] = occur['target'] self.storage.revision_add([revision]) occur.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], }) self.storage.occurrence_add([occur]) self.storage.occurrence_add([occur]) # when actual_occurrence = list(self.storage.occurrence_get(origin_id)) # then expected_occurrence = self.occurrence.copy() expected_occurrence.update({ 'origin': origin_id }) self.assertEquals(len(actual_occurrence), 1) self.assertEquals(actual_occurrence[0], expected_occurrence) @istest def snapshot_add_get_empty(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.empty_snapshot) by_id = self.storage.snapshot_get(self.empty_snapshot['id']) self.assertEqual(by_id, self.empty_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.empty_snapshot) @istest def snapshot_add_get_complete(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) by_id = self.storage.snapshot_get(self.complete_snapshot['id']) self.assertEqual(by_id, self.complete_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.complete_snapshot) @istest def snapshot_add_get(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.snapshot) by_id = self.storage.snapshot_get(self.snapshot['id']) self.assertEqual(by_id, self.snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.snapshot) # retrocompat test origin_visit_info = self.storage.origin_visit_get_by(origin_id, visit_id) self.assertEqual(origin_visit_info['occurrences'], self.snapshot['branches']) @istest def snapshot_add_twice(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit1_id, self.snapshot) by_ov1 = self.storage.snapshot_get_by_origin_visit(origin_id, visit1_id) self.assertEqual(by_ov1, self.snapshot) origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] self.storage.snapshot_add(origin_id, visit2_id, self.snapshot) by_ov2 = self.storage.snapshot_get_by_origin_visit(origin_id, visit2_id) self.assertEqual(by_ov2, self.snapshot) @istest def snapshot_get_nonexistent(self): bogus_snapshot_id = b'bogus snapshot id 00' bogus_origin_id = 1 bogus_visit_id = 1 by_id = self.storage.snapshot_get(bogus_snapshot_id) self.assertIsNone(by_id) by_ov = self.storage.snapshot_get_by_origin_visit(bogus_origin_id, bogus_visit_id) self.assertIsNone(by_ov) @istest def snapshot_get_retrocompat(self): empty_retro_snapshot = { 'id': None, 'branches': {}, } origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, empty_retro_snapshot) self.storage.revision_add([self.revision]) self.storage.occurrence_add([{ 'origin': origin_id, 'visit': visit_id, 'branch': self.occurrence['branch'], 'target': self.occurrence['target'], 'target_type': self.occurrence['target_type'], }]) one_branch_retro_snapshot = { 'id': None, 'branches': { self.occurrence['branch']: { 'target': self.occurrence['target'], 'target_type': self.occurrence['target_type'], }, }, } by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, one_branch_retro_snapshot) @istest def snapshot_add_back_compat(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot, back_compat=True) ov = self.storage.origin_visit_get_by(origin_id, visit_id) self.assertEquals(ov['occurrences'], self.complete_snapshot['branches']) self.assertEquals(ov['snapshot'], self.complete_snapshot['id']) origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit_id = origin_visit2['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot, back_compat=False) ov = self.storage.origin_visit_get_by(origin_id, visit_id) self.assertEquals(ov['occurrences'], self.complete_snapshot['branches']) self.assertEquals(ov['snapshot'], self.complete_snapshot['id']) @istest def snapshot_get_latest(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] # Two visits, both with no snapshot: latest snapshot is None self.assertIsNone(self.storage.snapshot_get_latest(origin_id)) # Add snapshot to visit1, latest snapshot = visit 1 snapshot self.storage.snapshot_add(origin_id, visit1_id, self.complete_snapshot) self.assertEquals(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) # Status filter: both visits are status=ongoing, so no snapshot # returned self.assertIsNone( self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_id, visit1_id, status='full') self.assertEquals( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit2 and check that the new snapshot is returned self.storage.snapshot_add(origin_id, visit2_id, self.empty_snapshot) self.assertEquals(self.empty_snapshot, self.storage.snapshot_get_latest(origin_id)) # Check that the status filter is still working self.assertEquals( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) @istest def entity_get_from_lister_metadata(self): self.storage.entity_add([self.entity1]) fetched_entities = list( self.storage.entity_get_from_lister_metadata( [self.entity1_query, self.entity2_query])) # Entity 1 should have full metadata, with last_seen/last_id instead # of validity entity1 = self.entity1.copy() entity1['last_seen'] = entity1['validity'][0] del fetched_entities[0]['last_id'] del entity1['validity'] # Entity 2 should have no metadata entity2 = { 'uuid': None, 'lister_metadata': self.entity2_query.copy(), } self.assertEquals(fetched_entities, [entity1, entity2]) @istest def entity_get_from_lister_metadata_twice(self): self.storage.entity_add([self.entity1]) fetched_entities1 = list( self.storage.entity_get_from_lister_metadata( [self.entity1_query])) fetched_entities2 = list( self.storage.entity_get_from_lister_metadata( [self.entity1_query])) self.assertEquals(fetched_entities1, fetched_entities2) @istest def entity_get(self): # given self.storage.entity_add([self.entity4]) self.storage.entity_add([self.entity3]) # when: entity3 -child-of-> entity4 actual_entity3 = list(self.storage.entity_get(self.entity3['uuid'])) self.assertEquals(len(actual_entity3), 2) # remove dynamic data (modified by db) entity3 = self.entity3.copy() entity4 = self.entity4.copy() del entity3['validity'] del entity4['validity'] del actual_entity3[0]['last_seen'] del actual_entity3[0]['last_id'] del actual_entity3[1]['last_seen'] del actual_entity3[1]['last_id'] self.assertEquals(actual_entity3, [entity3, entity4]) # when: entity4 only child actual_entity4 = list(self.storage.entity_get(self.entity4['uuid'])) self.assertEquals(len(actual_entity4), 1) # remove dynamic data (modified by db) entity4 = self.entity4.copy() del entity4['validity'] del actual_entity4[0]['last_id'] del actual_entity4[0]['last_seen'] self.assertEquals(actual_entity4, [entity4]) @istest def entity_get_one(self): # given self.storage.entity_add([self.entity3, self.entity4]) # when: entity3 -child-of-> entity4 actual_entity3 = self.storage.entity_get_one(self.entity3['uuid']) # remove dynamic data (modified by db) entity3 = self.entity3.copy() del entity3['validity'] del actual_entity3['last_seen'] del actual_entity3['last_id'] self.assertEquals(actual_entity3, entity3) @istest def stat_counters(self): expected_keys = ['content', 'directory', 'directory_entry_dir', 'occurrence', 'origin', 'person', 'revision'] for key in expected_keys: self.cursor.execute('select * from swh_update_counter(%s)', (key,)) self.conn.commit() counters = self.storage.stat_counters() self.assertTrue(set(expected_keys) <= set(counters)) self.assertIsInstance(counters[expected_keys[0]], int) @istest def content_find_with_present_content(self): # 1. with something to find cont = self.cont self.storage.content_add([cont]) actually_present = self.storage.content_find({'sha1': cont['sha1']}) actually_present.pop('ctime') self.assertEqual(actually_present, { '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 = self.storage.content_find( {'sha1_git': cont['sha1_git']}) actually_present.pop('ctime') self.assertEqual(actually_present, { '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 = self.storage.content_find( {'sha256': cont['sha256']}) actually_present.pop('ctime') self.assertEqual(actually_present, { '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 = self.storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) @istest def content_find_with_non_present_content(self): # 1. with something that does not exist missing_cont = self.missing_cont actually_present = self.storage.content_find( {'sha1': missing_cont['sha1']}) self.assertIsNone(actually_present) # 2. with something that does not exist actually_present = self.storage.content_find( {'sha1_git': missing_cont['sha1_git']}) self.assertIsNone(actually_present) # 3. with something that does not exist actually_present = self.storage.content_find( {'sha256': missing_cont['sha256']}) self.assertIsNone(actually_present) @istest def content_find_bad_input(self): # 1. with bad input with self.assertRaises(ValueError): self.storage.content_find({}) # empty is bad # 2. with bad input with self.assertRaises(ValueError): self.storage.content_find( {'unknown-sha1': 'something'}) # not the right key @istest def object_find_by_sha1_git(self): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } self.storage.content_add([self.cont]) sha1_gits.append(self.cont['sha1_git']) expected[self.cont['sha1_git']] = [{ 'sha1_git': self.cont['sha1_git'], 'type': 'content', 'id': self.cont['sha1'], }] self.storage.directory_add([self.dir]) sha1_gits.append(self.dir['id']) expected[self.dir['id']] = [{ 'sha1_git': self.dir['id'], 'type': 'directory', 'id': self.dir['id'], }] self.storage.revision_add([self.revision]) sha1_gits.append(self.revision['id']) expected[self.revision['id']] = [{ 'sha1_git': self.revision['id'], 'type': 'revision', 'id': self.revision['id'], }] self.storage.release_add([self.release]) sha1_gits.append(self.release['id']) expected[self.release['id']] = [{ 'sha1_git': self.release['id'], 'type': 'release', 'id': self.release['id'], }] ret = self.storage.object_find_by_sha1_git(sha1_gits) for val in ret.values(): for obj in val: del obj['object_id'] self.assertEqual(expected, ret) @istest def tool_add(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) # does not exist # add it actual_tools = list(self.storage.tool_add([tool])) self.assertEquals(len(actual_tools), 1) actual_tool = actual_tools[0] self.assertIsNotNone(actual_tool) # now it exists new_id = actual_tool.pop('id') self.assertEquals(actual_tool, tool) actual_tools2 = list(self.storage.tool_add([tool])) actual_tool2 = actual_tools2[0] self.assertIsNotNone(actual_tool2) # now it exists new_id2 = actual_tool2.pop('id') self.assertEqual(new_id, new_id2) self.assertEqual(actual_tool, actual_tool2) @istest def tool_add_multiple(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(self.storage.tool_add([tool])) self.assertEqual(len(actual_tools), 1) new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = list(self.storage.tool_add(new_tools)) self.assertEqual(len(actual_tools), 2) # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') self.assertIsNotNone(_id) self.assertIn(tool, new_tools) @istest def tool_get_missing(self): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) @istest def tool_metadata_get_missing_context(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) @istest def tool_metadata_get(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } tools = list(self.storage.tool_add([tool])) expected_tool = tools[0] # when actual_tool = self.storage.tool_get(tool) # then self.assertEqual(expected_tool, actual_tool) @istest def metadata_provider_get_by(self): # given no_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.assertIsNone(no_provider) # when provider_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) actual_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) # then self.assertTrue(provider_id, actual_provider['id']) @istest def origin_metadata_add(self): # given origin_id = self.storage.origin_add([self.origin])[0] origin_metadata0 = list(self.storage.origin_metadata_get_by(origin_id)) self.assertTrue(len(origin_metadata0) == 0) tools = list(self.storage.tool_add([self.metadata_tool])) tool = tools[0] self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) tool = self.storage.tool_get(self.metadata_tool) # when adding for the same origin 2 metadatas o_m1 = self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) actual_om1 = list(self.storage.origin_metadata_get_by(origin_id)) # then self.assertEqual(actual_om1[0]['id'], o_m1) self.assertEqual(len(actual_om1), 1) self.assertEqual(actual_om1[0]['origin_id'], origin_id) @istest def origin_metadata_get(self): # given origin_id = self.storage.origin_add([self.origin])[0] origin_id2 = self.storage.origin_add([self.origin2])[0] self.storage.metadata_provider_add(self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) tool = self.storage.tool_get(self.metadata_tool) # when adding for the same origin 2 metadatas o_m1 = self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) o_m2 = self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) o_m3 = self.storage.origin_metadata_add( origin_id, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) all_metadatas = list(self.storage.origin_metadata_get_by(origin_id)) metadatas_for_origin2 = list(self.storage.origin_metadata_get_by( origin_id2)) expected_results = [{ 'origin_id': origin_id, 'discovery_date': datetime.datetime( 2017, 1, 2, 0, 0, tzinfo=psycopg2.tz.FixedOffsetTimezone( offset=60, name=None)), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'id': o_m3, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }, { 'origin_id': origin_id, 'discovery_date': datetime.datetime( 2015, 1, 2, 0, 0, tzinfo=psycopg2.tz.FixedOffsetTimezone( offset=60, name=None)), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'id': o_m1, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }] # then self.assertEqual(len(all_metadatas), 2) self.assertEqual(len(metadatas_for_origin2), 1) self.assertEqual(metadatas_for_origin2[0]['id'], o_m2) self.assertEqual(all_metadatas, expected_results) @istest def origin_metadata_get_by_provider_type(self): # given origin_id = self.storage.origin_add([self.origin])[0] origin_id2 = self.storage.origin_add([self.origin2])[0] self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider1 = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = self.storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) # using the only tool now inserted in the data.sql, but for this # provider should be a crawler tool (not yet implemented) tool = self.storage.tool_get(self.metadata_tool) # when adding for the same origin 2 metadatas o_m1 = self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider1['id'], tool['id'], self.origin_metadata['metadata']) o_m2 = self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider2['id'], tool['id'], self.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(self.storage. origin_metadata_get_by( origin_id2, provider_type)) expected_results = [{ 'origin_id': origin_id2, 'discovery_date': datetime.datetime( 2017, 1, 2, 0, 0, tzinfo=psycopg2.tz.FixedOffsetTimezone( offset=60, name=None)), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'id': o_m2, 'provider_id': provider2['id'], 'provider_name': 'swMATH', 'provider_type': provider_type, 'provider_url': 'http://www.swmath.org/', 'tool_id': tool['id'] }] # then self.assertEqual(len(m_by_provider), 1) self.assertEqual(m_by_provider, expected_results) self.assertEqual(m_by_provider[0]['id'], o_m2) self.assertIsNotNone(o_m1) class TestLocalStorage(CommonTestStorage, unittest.TestCase): """Test the local storage""" # Can only be tested with local storage as you can't mock # datetimes for the remote server @istest def fetch_history(self): origin = self.storage.origin_add_one(self.origin) with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_date fetch_history_id = self.storage.fetch_history_start(origin) datetime.datetime.now.assert_called_with(tz=datetime.timezone.utc) with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_end self.storage.fetch_history_end(fetch_history_id, self.fetch_history_data) fetch_history = self.storage.fetch_history_get(fetch_history_id) expected_fetch_history = self.fetch_history_data.copy() expected_fetch_history['id'] = fetch_history_id expected_fetch_history['origin'] = origin expected_fetch_history['date'] = self.fetch_history_date expected_fetch_history['duration'] = self.fetch_history_duration self.assertEqual(expected_fetch_history, fetch_history) # The remote API doesn't expose _person_add @istest def person_get(self): # given person0 = { 'fullname': b'bob ', 'name': b'bob', 'email': b'alice@bob', } id0 = self.storage._person_add(person0) person1 = { 'fullname': b'tony ', 'name': b'tony', 'email': b'tony@bob', } id1 = self.storage._person_add(person1) # when actual_persons = self.storage.person_get([id0, id1]) # given (person injection through release for example) self.assertEqual( list(actual_persons), [ { 'id': id0, 'fullname': person0['fullname'], 'name': person0['name'], 'email': person0['email'], }, { 'id': id1, 'fullname': person1['fullname'], 'name': person1['name'], 'email': person1['email'], }, ]) + # This test is only relevant on the local storage, with an actual + # objstorage raising an exception + @istest + def content_add_objstorage_exception(self): + self.storage.objstorage.add = Mock( + side_effect=Exception('mocked broken objstorage') + ) + + with self.assertRaises(Exception) as e: + self.storage.content_add([self.cont]) + + self.assertEqual(e.exception.args, ('mocked broken objstorage',)) + missing = list(self.storage.content_missing([self.cont])) + self.assertEqual(missing, [self.cont['sha1']]) + class AlteringSchemaTest(BaseTestStorage, unittest.TestCase): """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. """ @istest def content_update(self): cont = copy.deepcopy(self.cont) self.storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') self.storage.content_update([cont], keys=['sha1_git']) - self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' - ' FROM content WHERE sha1 = %s', - (cont['sha1'],)) - datum = self.cursor.fetchone() + with self.storage.get_db().transaction() as cur: + cur.execute('SELECT sha1, sha1_git, sha256, length, status' + ' FROM content WHERE sha1 = %s', + (cont['sha1'],)) + datum = cur.fetchone() + self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) @istest def content_update_with_new_cols(self): - self.cursor.execute("""alter table content - add column test text default null, - add column test2 text default null""") + with self.storage.get_db().transaction() as cur: + cur.execute("""alter table content + add column test text default null, + add column test2 text default null""") cont = copy.deepcopy(self.cont2) self.storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' self.storage.content_update([cont], keys=['test', 'test2']) + with self.storage.get_db().transaction() as cur: + cur.execute( + 'SELECT sha1, sha1_git, sha256, length, status, test, test2' + ' FROM content WHERE sha1 = %s', + (cont['sha1'],)) - self.cursor.execute( - 'SELECT sha1, sha1_git, sha256, length, status, test, test2' - ' FROM content WHERE sha1 = %s', - (cont['sha1'],)) + datum = cur.fetchone() - datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2'])) - self.cursor.execute("""alter table content drop column test, - drop column test2""") + with self.storage.get_db().transaction() as cur: + cur.execute("""alter table content drop column test, + drop column test2""") diff --git a/version.txt b/version.txt index c97df7a17..8285fee10 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.99-0-gd8ad992 \ No newline at end of file +v0.0.100-0-g77e69ec \ No newline at end of file