Software Heritage storage server

diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 3b067956..222076f7 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,24 +1,24 @@ # 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 swh.core.api import RPCClient from ..exc import StorageAPIError -from ..storage import Storage +from ..interface import StorageInterface class RemoteStorage(RPCClient): """Proxy to a remote storage API""" api_exception = StorageAPIError - backend_class = Storage + backend_class = StorageInterface def reset(self): return self.post('reset', {}) def stat_counters(self): return self.get('stat/counters') def refresh_stat_counters(self): return self.get('stat/refresh') diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py index cc6634ae..05cf12e0 100644 --- a/swh/storage/api/server.py +++ b/swh/storage/api/server.py @@ -1,118 +1,118 @@ # Copyright (C) 2015-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import os import logging from swh.core import config from swh.storage import get_storage as get_swhstorage from swh.core.api import (RPCServerApp, error_handler, encode_data_server as encode_data) -from ..storage import Storage +from ..interface import StorageInterface from ..metrics import timed def get_storage(): global storage if not storage: storage = get_swhstorage(**app.config['storage']) return storage app = RPCServerApp(__name__, - backend_class=Storage, + backend_class=StorageInterface, backend_factory=get_storage) storage = None @app.errorhandler(Exception) def my_error_handler(exception): return error_handler(exception, encode_data) @app.route('/') @timed def index(): return ''' Software Heritage storage server

You have reached the Software Heritage storage server.
See its documentation and API for more information

''' @app.route('/stat/counters', methods=['GET']) @timed def stat_counters(): return encode_data(get_storage().stat_counters()) @app.route('/stat/refresh', methods=['GET']) @timed def refresh_stat_counters(): return encode_data(get_storage().refresh_stat_counters()) api_cfg = None def load_and_check_config(config_file, type='local'): """Check the minimal configuration is set to run the api or raise an error explanation. Args: config_file (str): Path to the configuration file to load type (str): configuration type. For 'local' type, more checks are done. Raises: Error if the setup is not as expected Returns: configuration as a dict """ if not config_file: raise EnvironmentError('Configuration file must be defined') if not os.path.exists(config_file): raise FileNotFoundError('Configuration file %s does not exist' % ( config_file, )) cfg = config.read(config_file) if 'storage' not in cfg: raise KeyError("Missing '%storage' configuration") return cfg def make_app_from_configfile(): """Run the WSGI app from the webserver, loading the configuration from a configuration file. SWH_CONFIG_FILENAME environment variable defines the configuration path to load. """ global api_cfg if not api_cfg: config_file = os.environ.get('SWH_CONFIG_FILENAME') api_cfg = load_and_check_config(config_file) app.config.update(api_cfg) handler = logging.StreamHandler() app.logger.addHandler(handler) return app if __name__ == '__main__': print('Deprecated. Use swh-storage') diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py index 9cdfa5ad..656f040d 100644 --- a/swh/storage/in_memory.py +++ b/swh/storage/in_memory.py @@ -1,1915 +1,1053 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import re import bisect import dateutil import collections import copy import datetime import itertools import random from collections import defaultdict from datetime import timedelta from typing import Any, Dict, List, Optional import attr from swh.model.model import ( Content, Directory, Revision, Release, Snapshot, OriginVisit, Origin, SHA1_SIZE) from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError from .storage import get_journal_writer from .converters import origin_url_to_sha1 from .utils import get_partition_bounds_bytes # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 def now(): return datetime.datetime.now(tz=datetime.timezone.utc) class Storage: def __init__(self, journal_writer=None): self._contents = {} self._content_indexes = defaultdict(lambda: defaultdict(set)) self._skipped_contents = {} self._skipped_content_indexes = defaultdict(lambda: defaultdict(set)) self.reset() if journal_writer: self.journal_writer = get_journal_writer(**journal_writer) else: self.journal_writer = None def reset(self): self._directories = {} self._revisions = {} self._releases = {} self._snapshots = {} self._origins = {} self._origins_by_id = [] self._origins_by_sha1 = {} self._origin_visits = {} self._persons = [] self._origin_metadata = defaultdict(list) self._tools = {} self._metadata_providers = {} self._objects = defaultdict(list) # ideally we would want a skip list for both fast inserts and searches self._sorted_sha1s = [] self.objstorage = get_objstorage('memory', {}) def check_config(self, *, check_write): - """Check that the storage is configured and ready to go.""" return True def _content_add(self, contents, with_data): content_with_data = [] content_without_data = [] for content in contents: if content.status is None: content.status = 'visible' if content.length is None: content.length = -1 if content.status != 'absent': if self._content_key(content) not in self._contents: content_with_data.append(content) else: if self._content_key(content) not in self._skipped_contents: content_without_data.append(content) if self.journal_writer: for content in content_with_data: content = attr.evolve(content, data=None) self.journal_writer.write_addition('content', content) for content in content_without_data: self.journal_writer.write_addition('content', content) count_content_added, count_content_bytes_added = \ self._content_add_present(content_with_data, with_data) count_skipped_content_added = self._content_add_absent( content_without_data ) summary = { 'content:add': count_content_added, 'skipped_content:add': count_skipped_content_added, } if with_data: summary['content:add:bytes'] = count_content_bytes_added return summary def _content_add_present(self, contents, with_data): count_content_added = 0 count_content_bytes_added = 0 for content in contents: key = self._content_key(content) if key in self._contents: continue for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) if hash_ in self._content_indexes[algorithm]\ and (algorithm not in {'blake2s256', 'sha256'}): from . import HashCollision raise HashCollision(algorithm, hash_, key) for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(key) self._objects[content.sha1_git].append( ('content', content.sha1)) self._contents[key] = content bisect.insort(self._sorted_sha1s, content.sha1) count_content_added += 1 if with_data: content_data = self._contents[key].data self._contents[key] = attr.evolve( self._contents[key], data=None) count_content_bytes_added += len(content_data) self.objstorage.add(content_data, content.sha1) return (count_content_added, count_content_bytes_added) def _content_add_absent(self, contents): count = 0 skipped_content_missing = self.skipped_content_missing(contents) for content in skipped_content_missing: key = self._content_key(content) for algo in DEFAULT_ALGORITHMS: self._skipped_content_indexes[algo][content.get_hash(algo)] \ .add(key) self._skipped_contents[key] = content count += 1 return count def _content_to_model(self, contents): - """Takes a list of content dicts, optionally with an extra 'origin' - key, and yields tuples (model.Content, origin).""" for content in contents: content = content.copy() content.pop('origin', None) yield Content.from_dict(content) def content_add(self, content): - """Add content blobs to the storage - - 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.DEFAULT_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 - - Raises: - HashCollision in case of collision - - Returns: - Summary dict with the following key and associated values: - - content:add: New contents added - content_bytes:add: Sum of the contents' length data - skipped_content:add: New skipped contents (no data) added - - """ now = datetime.datetime.now(tz=datetime.timezone.utc) content = [attr.evolve(c, ctime=now) for c in self._content_to_model(content)] return self._content_add(content, with_data=True) def content_update(self, content, keys=[]): - """Update content blobs to the storage. Does nothing for unknown - contents or skipped ones. - - Args: - content (iterable): iterable of dictionaries representing - individual pieces of content to update. Each dictionary has the - following keys: - - - data (bytes): the actual content - - length (int): content length (default: -1) - - one key for each checksum algorithm in - :data:`swh.model.hashutil.ALGORITHMS`, mapped to the - corresponding checksum - - status (str): one of visible, hidden, absent - - keys (list): List of keys (str) whose values needs an update, e.g., - new hash column - """ if self.journal_writer: raise NotImplementedError( 'content_update is not yet supported with a journal_writer.') for cont_update in content: cont_update = cont_update.copy() sha1 = cont_update.pop('sha1') for old_key in self._content_indexes['sha1'][sha1]: old_cont = self._contents.pop(old_key) for algorithm in DEFAULT_ALGORITHMS: hash_ = old_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].remove(old_key) new_cont = attr.evolve(old_cont, **cont_update) new_key = self._content_key(new_cont) self._contents[new_key] = new_cont for algorithm in DEFAULT_ALGORITHMS: hash_ = new_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(new_key) def content_add_metadata(self, content): - """Add content metadata to the storage (like `content_add`, but - without inserting to the objstorage). - - Args: - content (iterable): iterable of dictionaries representing - individual pieces of content to add. Each dictionary has the - following keys: - - - length (int): content length (default: -1) - - one key for each checksum algorithm in - :data:`swh.model.hashutil.DEFAULT_ALGORITHMS`, mapped to the - corresponding checksum - - status (str): one of visible, hidden, absent - - reason (str): if status = absent, the reason why - - origin (int): if status = absent, the origin we saw the - content in - - ctime (datetime): time of insertion in the archive - - Raises: - HashCollision in case of collision - - Returns: - Summary dict with the following key and associated values: - - content:add: New contents added - skipped_content:add: New skipped contents (no data) added - - """ content = list(self._content_to_model(content)) return self._content_add(content, with_data=False) def content_get(self, content): - """Retrieve in bulk contents and their data. - - This function may yield more blobs than provided sha1 identifiers, - in case they collide. - - Args: - content: iterables of sha1 - - Yields: - Dict[str, bytes]: Generates streams of contents as dict with their - raw data: - - - sha1 (bytes): content id - - data (bytes): content's raw data - - Raises: - ValueError in case of too much contents are required. - cf. BULK_BLOCK_CONTENT_LEN_MAX - - """ # FIXME: Make this method support slicing the `data`. if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise ValueError( "Sending at most %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} def content_get_range(self, start, end, limit=1000): - """Retrieve contents within range [start, end] bound by limit. - - Note that this function may return more than one blob per hash. The - limit is enforced with multiplicity (ie. two blobs with the same hash - will count twice toward the limit). - - Args: - **start** (bytes): Starting identifier range (expected smaller - than end) - **end** (bytes): Ending identifier range (expected larger - than start) - **limit** (int): Limit result (default to 1000) - - Returns: - a dict with keys: - - contents [dict]: iterable of contents in between the range. - - next (bytes): There remains content in the range - starting from this next sha1 - - """ if limit is None: raise ValueError('Development error: limit should not be None') from_index = bisect.bisect_left(self._sorted_sha1s, start) sha1s = itertools.islice(self._sorted_sha1s, from_index, None) sha1s = ((sha1, content_key) for sha1 in sha1s for content_key in self._content_indexes['sha1'][sha1]) matched = [] next_content = None for sha1, key in sha1s: if sha1 > end: break if len(matched) >= limit: next_content = sha1 break matched.append(self._contents[key].to_dict()) return { 'contents': matched, 'next': next_content, } def content_get_partition( self, partition_id: int, nb_partitions: int, limit: int = 1000, page_token: str = None): - """Splits contents into nb_partitions, and returns one of these based on - partition_id (which must be in [0, nb_partitions-1]) - - There is no guarantee on how the partitioning is done, or the - result order. - - Args: - partition_id (int): index of the partition to fetch - nb_partitions (int): total number of partitions to split into - limit (int): Limit result (default to 1000) - page_token (Optional[str]): opaque token used for pagination. - - Returns: - a dict with keys: - - contents (List[dict]): iterable of contents in the partition. - - **next_page_token** (Optional[str]): opaque token to be used as - `page_token` for retrieving the next page. if absent, there is - no more pages to gather. - """ if limit is None: raise ValueError('Development error: limit should not be None') (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE) if page_token: start = hash_to_bytes(page_token) if end is None: end = b'\xff'*SHA1_SIZE result = self.content_get_range(start, end, limit) result2 = { 'contents': result['contents'], 'next_page_token': None, } if result['next']: result2['next_page_token'] = hash_to_hex(result['next']) return result2 def content_get_metadata( self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: - """Retrieve content metadata in bulk - - Args: - content: iterable of content identifiers (sha1) - - Returns: - a dict with keys the content's sha1 and the associated value - either the existing content's metadata or None if the content does - not exist. - - """ result: Dict = {sha1: [] for sha1 in contents} for sha1 in contents: if sha1 in self._content_indexes['sha1']: objs = self._content_indexes['sha1'][sha1] # only 1 element as content_add_metadata would have raised a # hash collision otherwise for key in objs: d = self._contents[key].to_dict() del d['ctime'] if 'data' in d: del d['data'] result[sha1].append(d) return result def content_find(self, content): if not set(content).intersection(DEFAULT_ALGORITHMS): raise ValueError('content keys must contain at least one of: ' '%s' % ', '.join(sorted(DEFAULT_ALGORITHMS))) found = [] for algo in DEFAULT_ALGORITHMS: hash = content.get(algo) if hash and hash in self._content_indexes[algo]: found.append(self._content_indexes[algo][hash]) if not found: return [] keys = list(set.intersection(*found)) return [self._contents[key].to_dict() for key in keys] def content_missing(self, content, key_hash='sha1'): - """List content missing from storage - - Args: - contents ([dict]): iterable of dictionaries whose keys are - either 'length' or an item of - :data:`swh.model.hashutil.ALGORITHMS`; - mapped to the corresponding checksum - (or length). - - key_hash (str): name of the column to use as hash id - result (default: 'sha1') - - Returns: - iterable ([bytes]): missing content ids (as per the - key_hash column) - """ for cont in content: for (algo, hash_) in cont.items(): if algo not in DEFAULT_ALGORITHMS: continue if hash_ not in self._content_indexes.get(algo, []): yield cont[key_hash] break else: for result in self.content_find(cont): if result['status'] == 'missing': yield cont[key_hash] def content_missing_per_sha1(self, contents): - """List content missing from storage based only on sha1. - - Args: - contents: Iterable of sha1 to check for absence. - - Returns: - iterable: missing ids - - Raises: - TODO: an exception when we get a hash collision. - - """ for content in contents: if content not in self._content_indexes['sha1']: yield content def content_missing_per_sha1_git(self, contents): - """List content missing from storage based only on sha1_git. - - Args: - contents: An iterable of content id (sha1_git) - - Yields: - missing contents sha1_git - """ for content in contents: if content not in self._content_indexes['sha1_git']: yield content def skipped_content_missing(self, contents): - """List all skipped_content missing from storage - - Args: - contents: Iterable of sha1 to check for skipped content entry - - Returns: - iterable: dict of skipped content entry - """ - for content in contents: for (key, algorithm) in self._content_key_algorithm(content): if algorithm == 'blake2s256': continue if key not in self._skipped_content_indexes[algorithm]: # index must contain hashes of algos except blake2s256 # else the content is considered skipped yield content break def content_get_random(self): - """Finds a random content id. - - Returns: - a sha1_git - """ return random.choice(list(self._content_indexes['sha1_git'])) 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 - Returns: - Summary dict of keys with associated count as values: - - directory:add: Number of directories actually added - - """ directories = list(directories) if self.journal_writer: self.journal_writer.write_additions( 'directory', (dir_ for dir_ in directories if dir_['id'] not in self._directories)) directories = [Directory.from_dict(d) for d in directories] count = 0 for directory in directories: if directory.id not in self._directories: count += 1 self._directories[directory.id] = directory self._objects[directory.id].append( ('directory', directory.id)) return {'directory:add': count} def directory_missing(self, directories): - """List directories missing from storage - - Args: - directories (iterable): an iterable of directory ids - - Yields: - missing directory ids - - """ for id in directories: if id not in self._directories: yield id def _join_dentry_to_content(self, dentry): keys = ( 'status', 'sha1', 'sha1_git', 'sha256', 'length', ) ret = dict.fromkeys(keys) ret.update(dentry) if ret['type'] == 'file': # TODO: Make it able to handle more than one content content = self.content_find({'sha1_git': ret['target']}) if content: content = content[0] for key in keys: ret[key] = content[key] return ret def _directory_ls(self, directory_id, recursive, prefix=b''): if directory_id in self._directories: for entry in self._directories[directory_id].entries: ret = self._join_dentry_to_content(entry.to_dict()) ret['name'] = prefix + ret['name'] ret['dir_id'] = directory_id yield ret if recursive and ret['type'] == 'dir': yield from self._directory_ls( ret['target'], True, prefix + ret['name'] + b'/') def directory_ls(self, directory, recursive=False): - """Get entries for one directory. - - Args: - - directory: the directory to list entries from. - - recursive: if flag on, this list recursively from this directory. - - Returns: - List of entries for such directory. - - If `recursive=True`, names in the path of a dir/file not at the - root are concatenated with a slash (`/`). - """ yield from self._directory_ls(directory, recursive) def directory_entry_get_by_path(self, directory, paths): - """Get the directory entry (either file or dir) from directory with path. - - Args: - - directory: sha1 of the top level directory - - paths: path to lookup from the top level directory. From left - (top) to right (bottom). - - Returns: - The corresponding directory entry if found, None otherwise. - - """ return self._directory_entry_get_by_path(directory, paths, b'') def directory_get_random(self): - """Finds a random directory id. - - Returns: - a sha1_git if any - - """ if not self._directories: return None return random.choice(list(self._directories)) def _directory_entry_get_by_path(self, directory, paths, prefix): if not paths: return contents = list(self.directory_ls(directory)) if not contents: return def _get_entry(entries, name): for entry in entries: if entry['name'] == name: entry = entry.copy() entry['name'] = prefix + entry['name'] return entry first_item = _get_entry(contents, paths[0]) if len(paths) == 1: return first_item if not first_item or first_item['type'] != 'dir': return return self._directory_entry_get_by_path( first_item['target'], paths[1:], prefix + paths[0] + b'/') def revision_add(self, revisions): - """Add revisions to the storage - - Args: - revisions (Iterable[dict]): iterable of dictionaries representing - the individual revisions to add. Each dict has the following - keys: - - - **id** (:class:`sha1_git`): id of the revision to add - - **date** (:class:`dict`): date the revision was written - - **committer_date** (:class:`dict`): date the revision got - added to the origin - - **type** (one of 'git', 'tar'): type of the - revision added - - **directory** (:class:`sha1_git`): the directory the - revision points at - - **message** (:class:`bytes`): the message associated with - the revision - - **author** (:class:`Dict[str, bytes]`): dictionary with - keys: name, fullname, email - - **committer** (:class:`Dict[str, bytes]`): dictionary with - keys: name, fullname, email - - **metadata** (:class:`jsonb`): extra information as - dictionary - - **synthetic** (:class:`bool`): revision's nature (tarball, - directory creates synthetic revision`) - - **parents** (:class:`list[sha1_git]`): the parents of - this revision - - date dictionaries have the form defined in :mod:`swh.model`. - - Returns: - Summary dict of keys with associated count as values - - revision_added: New objects actually stored in db - - """ revisions = list(revisions) if self.journal_writer: self.journal_writer.write_additions( 'revision', (rev for rev in revisions if rev['id'] not in self._revisions)) revisions = [Revision.from_dict(rev) for rev in revisions] count = 0 for revision in revisions: if revision.id not in self._revisions: revision = attr.evolve( revision, committer=self._person_add(revision.committer), author=self._person_add(revision.author)) self._revisions[revision.id] = revision self._objects[revision.id].append( ('revision', revision.id)) count += 1 return {'revision:add': count} def revision_missing(self, revisions): - """List revisions missing from storage - - Args: - revisions (iterable): revision ids - - Yields: - missing revision ids - - """ for id in revisions: if id not in self._revisions: yield id def revision_get(self, revisions): for id in revisions: if id in self._revisions: yield self._revisions.get(id).to_dict() else: yield None def _get_parent_revs(self, rev_id, seen, limit): if limit and len(seen) >= limit: return if rev_id in seen or rev_id not in self._revisions: return seen.add(rev_id) yield self._revisions[rev_id].to_dict() for parent in self._revisions[rev_id].parents: yield from self._get_parent_revs(parent, seen, limit) def revision_log(self, revisions, limit=None): - """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. - - """ seen = set() for rev_id in revisions: yield from self._get_parent_revs(rev_id, seen, limit) def revision_shortlog(self, revisions, limit=None): - """Fetch the shortlog for the given revisions - - Args: - revisions: list of root revisions to lookup - limit: depth limitation for the output - - Yields: - a list of (id, parents) tuples. - - """ yield from ((rev['id'], rev['parents']) for rev in self.revision_log(revisions, limit)) def revision_get_random(self): - """Finds a random revision id. - - Returns: - a sha1_git - """ return random.choice(list(self._revisions)) def release_add(self, releases): - """Add releases to the storage - - Args: - releases (Iterable[dict]): iterable of dictionaries representing - the individual releases to add. Each dict has the following - keys: - - - **id** (:class:`sha1_git`): id of the release to add - - **revision** (:class:`sha1_git`): id of the revision the - release points to - - **date** (:class:`dict`): the date the release was made - - **name** (:class:`bytes`): the name of the release - - **comment** (:class:`bytes`): the comment associated with - the release - - **author** (:class:`Dict[str, bytes]`): dictionary with - keys: name, fullname, email - - the date dictionary has the form defined in :mod:`swh.model`. - - Returns: - Summary dict of keys with associated count as values - - release:add: New objects contents actually stored in db - - """ releases = list(releases) if self.journal_writer: self.journal_writer.write_additions( 'release', (rel for rel in releases if rel['id'] not in self._releases)) releases = [Release.from_dict(rel) for rel in releases] count = 0 for rel in releases: if rel.id not in self._releases: if rel.author: self._person_add(rel.author) self._objects[rel.id].append( ('release', rel.id)) self._releases[rel.id] = rel count += 1 return {'release:add': count} def release_missing(self, releases): - """List releases missing from storage - - Args: - releases: an iterable of release ids - - Returns: - a list of missing release ids - - """ yield from (rel for rel in releases if rel not in self._releases) def release_get(self, releases): - """Given a list of sha1, return the releases's information - - Args: - releases: list of sha1s - - Yields: - dicts with the same keys as those given to `release_add` - (or ``None`` if a release does not exist) - - """ for rel_id in releases: if rel_id in self._releases: yield self._releases[rel_id].to_dict() else: yield None def release_get_random(self): - """Finds a random release id. - - Returns: - a sha1_git - """ return random.choice(list(self._releases)) def snapshot_add(self, snapshots): - """Add a snapshot to the storage - - Args: - snapshot ([dict]): the snapshots to add, containing the - following keys: - - - **id** (:class:`bytes`): id of the snapshot - - **branches** (:class:`dict`): branches the snapshot contains, - mapping the branch name (:class:`bytes`) to the branch target, - itself a :class:`dict` (or ``None`` if the branch points to an - unknown object) - - - **target_type** (:class:`str`): one of ``content``, - ``directory``, ``revision``, ``release``, - ``snapshot``, ``alias`` - - **target** (:class:`bytes`): identifier of the target - (currently a ``sha1_git`` for all object kinds, or the name - of the target branch for aliases) - - Raises: - ValueError: if the origin's or visit's identifier does not exist. - - Returns: - Summary dict of keys with associated count as values - - snapshot_added: Count of object actually stored in db - - """ count = 0 snapshots = (Snapshot.from_dict(d) for d in snapshots) snapshots = (snap for snap in snapshots if snap.id not in self._snapshots) for snapshot in snapshots: if self.journal_writer: self.journal_writer.write_addition('snapshot', snapshot) sorted_branch_names = sorted(snapshot.branches) self._snapshots[snapshot.id] = (snapshot, sorted_branch_names) self._objects[snapshot.id].append(('snapshot', snapshot.id)) count += 1 return {'snapshot:add': count} def snapshot_missing(self, snapshots): - """List snapshot missing from storage - - Args: - snapshots (iterable): an iterable of snapshot ids - - Yields: - missing snapshot ids - """ for id in snapshots: if id not in self._snapshots: yield id def snapshot_get(self, snapshot_id): - """Get the content, possibly partial, of a snapshot with the given id - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - .. warning:: At most 1000 branches contained in the snapshot will be - returned for performance reasons. In order to browse the whole - set of branches, the method :meth:`snapshot_get_branches` - should be used instead. - - Args: - snapshot_id (bytes): identifier of the snapshot - Returns: - dict: a dict with three keys: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than 1000 - branches. - """ return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): - """Get the content, possibly partial, of a snapshot for the given origin visit - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - .. warning:: At most 1000 branches contained in the snapshot will be - returned for performance reasons. In order to browse the whole - set of branches, the method :meth:`snapshot_get_branches` - should be used instead. - - Args: - origin (int): the origin's identifier - visit (int): the visit's identifier - Returns: - dict: None if the snapshot does not exist; - a dict with three keys otherwise: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than 1000 - branches. - - """ origin_url = self._get_origin_url(origin) if not origin_url: return if origin_url not in self._origins or \ visit > len(self._origin_visits[origin_url]): return None snapshot_id = self._origin_visits[origin_url][visit-1].snapshot if snapshot_id: return self.snapshot_get(snapshot_id) else: return None def snapshot_get_latest(self, origin, allowed_statuses=None): - """Get the content, possibly partial, of the latest snapshot for the - given origin, optionally only from visits that have one of the given - allowed_statuses - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - .. warning:: At most 1000 branches contained in the snapshot will be - returned for performance reasons. In order to browse the whole - set of branches, the methods :meth:`origin_visit_get_latest` - and :meth:`snapshot_get_branches` should be used instead. - - Args: - origin (str): the origin's URL - allowed_statuses (list of str): list of visit statuses considered - to find the latest snapshot for the origin. For instance, - ``allowed_statuses=['full']`` will only consider visits that - have successfully run to completion. - Returns: - dict: a dict with three keys: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than 1000 - branches. - """ origin_url = self._get_origin_url(origin) if not origin_url: return visit = self.origin_visit_get_latest( origin_url, allowed_statuses=allowed_statuses, require_snapshot=True) if visit and visit['snapshot']: snapshot = self.snapshot_get(visit['snapshot']) if not snapshot: raise ValueError( 'last origin visit references an unknown snapshot') return snapshot def snapshot_count_branches(self, snapshot_id): - """Count the number of branches in the snapshot with the given id - - Args: - snapshot_id (bytes): identifier of the snapshot - - Returns: - dict: A dict whose keys are the target types of branches and - values their corresponding amount - """ (snapshot, _) = self._snapshots[snapshot_id] return collections.Counter(branch.target_type.value if branch else None for branch in snapshot.branches.values()) def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None): - """Get the content, possibly partial, of a snapshot with the given id - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - Args: - snapshot_id (bytes): identifier of the snapshot - branches_from (bytes): optional parameter used to skip branches - whose name is lesser than it before returning them - branches_count (int): optional parameter used to restrain - the amount of returned branches - target_types (list): optional parameter used to filter the - target types of branch to return (possible values that can be - contained in that list are `'content', 'directory', - 'revision', 'release', 'snapshot', 'alias'`) - Returns: - dict: None if the snapshot does not exist; - a dict with three keys otherwise: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than - `branches_count` branches after `branches_from` included. - """ res = self._snapshots.get(snapshot_id) if res is None: return None (snapshot, sorted_branch_names) = res from_index = bisect.bisect_left( sorted_branch_names, branches_from) if target_types: next_branch = None branches = {} for branch_name in sorted_branch_names[from_index:]: branch = snapshot.branches[branch_name] if branch and branch.target_type.value in target_types: if len(branches) < branches_count: branches[branch_name] = branch else: next_branch = branch_name break else: # As there is no 'target_types', we can do that much faster to_index = from_index + branches_count returned_branch_names = sorted_branch_names[from_index:to_index] branches = {branch_name: snapshot.branches[branch_name] for branch_name in returned_branch_names} if to_index >= len(sorted_branch_names): next_branch = None else: next_branch = sorted_branch_names[to_index] branches = {name: branch.to_dict() if branch else None for (name, branch) in branches.items()} return { 'id': snapshot_id, 'branches': branches, 'next_branch': next_branch, } def snapshot_get_random(self): - """Finds a random snapshot id. - - Returns: - a sha1_git - """ return random.choice(list(self._snapshots)) def object_find_by_sha1_git(self, ids): - """Return the objects found with the given ids. - - Args: - ids: a generator of sha1_gits - - Returns: - dict: a mapping from id to the list of objects found. Each object - found is itself a dict with keys: - - - sha1_git: the input id - - type: the type of object found - - """ ret = {} for id_ in ids: objs = self._objects.get(id_, []) ret[id_] = [{ 'sha1_git': id_, 'type': obj[0], } for obj in objs] return ret def _convert_origin(self, t): if t is None: return None return t.to_dict() def origin_get(self, origins): - """Return origins, either all identified by their ids or all - identified by urls. - - Args: - origin: a list of dictionaries representing the individual - origins to find. - These dicts have either the key url (and optionally type): - - - url (bytes): the url the origin points to - - or the id: - - - id (int): the origin's identifier - - Returns: - dict: the origin dictionary with the keys: - - - id: origin's id - - url: origin's url - - Raises: - ValueError: if the keys does not match (url and type) nor id. - - """ if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False # Sanity check to be error-compatible with the pgsql backend if any('id' in origin for origin in origins) \ and not all('id' in origin for origin in origins): raise ValueError( 'Either all origins or none at all should have an "id".') if any('url' in origin for origin in origins) \ and not all('url' in origin for origin in origins): raise ValueError( 'Either all origins or none at all should have ' 'an "url" key.') results = [] for origin in origins: result = None if 'url' in origin: if origin['url'] in self._origins: result = self._origins[origin['url']] else: raise ValueError( 'Origin must have an url.') results.append(self._convert_origin(result)) if return_single: assert len(results) == 1 return results[0] else: return results def origin_get_by_sha1(self, sha1s): - """Return origins, identified by the sha1 of their URLs. - - Args: - sha1s (list[bytes]): a list of sha1s - - Yields: - dicts containing origin information as returned - by :meth:`swh.storage.in_memory.Storage.origin_get`, or None if an - origin matching the sha1 is not found. - """ return [ self._convert_origin(self._origins_by_sha1.get(sha1)) for sha1 in sha1s ] def origin_get_range(self, origin_from=1, origin_count=100): - """Retrieve ``origin_count`` origins whose ids are greater - or equal than ``origin_from``. - - Origins are sorted by id before retrieving them. - - Args: - origin_from (int): the minimum id of origins to retrieve - origin_count (int): the maximum number of origins to retrieve - - Yields: - dicts containing origin information as returned - by :meth:`swh.storage.in_memory.Storage.origin_get`, plus - an 'id' key. - """ origin_from = max(origin_from, 1) if origin_from <= len(self._origins_by_id): max_idx = origin_from + origin_count - 1 if max_idx > len(self._origins_by_id): max_idx = len(self._origins_by_id) for idx in range(origin_from-1, max_idx): origin = self._convert_origin( self._origins[self._origins_by_id[idx]]) yield {'id': idx+1, **origin} def origin_list(self, page_token: Optional[str] = None, limit: int = 100 ) -> dict: - """Returns the list of origins - - Args: - page_token: opaque token used for pagination. - limit: the maximum number of results to return - - Returns: - dict: dict with the following keys: - - **next_page_token** (str, optional): opaque token to be used as - `page_token` for retrieving the next page. if absent, there is - no more pages to gather. - - **origins** (List[dict]): list of origins, as returned by - `origin_get`. - """ origin_urls = sorted(self._origins) if page_token: from_ = bisect.bisect_left(origin_urls, page_token) else: from_ = 0 result = { 'origins': [{'url': origin_url} for origin_url in origin_urls[from_:from_+limit]] } if from_+limit < len(origin_urls): result['next_page_token'] = origin_urls[from_+limit] return result def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False): - """Search for origins whose urls contain a provided string pattern - or match a provided regular expression. - The search is performed in a case insensitive way. - - Args: - url_pattern (str): the string pattern to search for in origin urls - offset (int): number of found origins to skip before returning - results - limit (int): the maximum number of found origins to return - regexp (bool): if True, consider the provided pattern as a regular - expression and return origins whose urls match it - with_visit (bool): if True, filter out origins with no visit - - Returns: - An iterable of dict containing origin information as returned - by :meth:`swh.storage.storage.Storage.origin_get`. - """ origins = map(self._convert_origin, self._origins.values()) if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.search(orig['url'])] else: origins = [orig for orig in origins if url_pattern in orig['url']] if with_visit: origins = [ orig for orig in origins if len(self._origin_visits[orig['url']]) > 0 and set(ov.snapshot for ov in self._origin_visits[orig['url']] if ov.snapshot) & set(self._snapshots)] return origins[offset:offset+limit] def origin_count(self, url_pattern, regexp=False, with_visit=False): - """Count origins whose urls contain a provided string pattern - or match a provided regular expression. - The pattern search in origin urls is performed in a case insensitive - way. - - Args: - url_pattern (str): the string pattern to search for in origin urls - regexp (bool): if True, consider the provided pattern as a regular - expression and return origins whose urls match it - with_visit (bool): if True, filter out origins with no visit - - Returns: - int: The number of origins matching the search criterion. - """ return len(self.origin_search(url_pattern, regexp=regexp, with_visit=with_visit, limit=len(self._origins))) def origin_add(self, origins): - """Add origins to the storage - - Args: - origins: list of dictionaries representing the individual origins, - with the following keys: - - - url (bytes): the url the origin points to - - Returns: - list: given origins as dict updated with their id - - """ origins = copy.deepcopy(list(origins)) for origin in origins: self.origin_add_one(origin) return origins def origin_add_one(self, origin): - """Add origin to the storage - - Args: - origin: dictionary representing the individual origin to add. This - dict has the following keys: - - - url (bytes): the url the origin points to - - Returns: - the id of the added origin, or of the identical one that already - exists. - - """ origin = Origin.from_dict(origin) if origin.url not in self._origins: if self.journal_writer: self.journal_writer.write_addition('origin', origin) # generate an origin_id because it is needed by origin_get_range. # TODO: remove this when we remove origin_get_range origin_id = len(self._origins) + 1 self._origins_by_id.append(origin.url) assert len(self._origins_by_id) == origin_id self._origins[origin.url] = origin self._origins_by_sha1[origin_url_to_sha1(origin.url)] = origin self._origin_visits[origin.url] = [] self._objects[origin.url].append(('origin', origin.url)) return origin.url def origin_visit_add(self, origin, date, type): - """Add an origin_visit for the origin at date with status 'ongoing'. - - Args: - origin (str): visited origin's identifier or URL - date (Union[str,datetime]): timestamp of such visit - type (str): the type of loader used for the visit (hg, git, ...) - - Returns: - dict: dictionary with keys origin and visit where: - - - origin: origin's identifier - - visit: the visit's identifier for the new visit occurrence - - """ origin_url = origin if origin_url is None: raise ValueError('Unknown origin.') if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): raise TypeError('date must be a datetime or a string.') visit_ret = None if origin_url in self._origins: origin = self._origins[origin_url] # visit ids are in the range [1, +inf[ visit_id = len(self._origin_visits[origin_url]) + 1 status = 'ongoing' visit = OriginVisit( origin=origin.url, date=date, type=type, status=status, snapshot=None, metadata=None, visit=visit_id, ) self._origin_visits[origin_url].append(visit) visit_ret = { 'origin': origin.url, 'visit': visit_id, } self._objects[(origin_url, visit_id)].append( ('origin_visit', None)) if self.journal_writer: self.journal_writer.write_addition('origin_visit', visit) return visit_ret def origin_visit_update(self, origin, visit_id, status=None, metadata=None, snapshot=None): - """Update an origin_visit's status. - - Args: - origin (str): visited origin's URL - visit_id (int): visit's identifier - status: visit's new status - metadata: data associated to the visit - snapshot (sha1_git): identifier of the snapshot to add to - the visit - - Returns: - None - - """ if not isinstance(origin, str): raise TypeError('origin must be a string, not %r' % (origin,)) origin_url = self._get_origin_url(origin) if origin_url is None: raise ValueError('Unknown origin.') try: visit = self._origin_visits[origin_url][visit_id-1] except IndexError: raise ValueError('Unknown visit_id for this origin') \ from None updates = {} if status: updates['status'] = status if metadata: updates['metadata'] = metadata if snapshot: updates['snapshot'] = snapshot visit = attr.evolve(visit, **updates) if self.journal_writer: self.journal_writer.write_update('origin_visit', visit) self._origin_visits[origin_url][visit_id-1] = visit def origin_visit_upsert(self, visits): - """Add a origin_visits with a specific id and with all its data. - If there is already an origin_visit with the same - `(origin_url, visit_id)`, updates it instead of inserting a new one. - - Args: - visits: iterable of dicts with keys: - - - **origin**: origin url - - **visit**: origin visit id - - **type**: type of loader used for the visit - - **date**: timestamp of such visit - - **status**: Visit's new status - - **metadata**: Data associated to the visit - - **snapshot**: identifier of the snapshot to add to - the visit - """ for visit in visits: if not isinstance(visit['origin'], str): raise TypeError("visit['origin'] must be a string, not %r" % (visit['origin'],)) visits = [OriginVisit.from_dict(d) for d in visits] if self.journal_writer: for visit in visits: self.journal_writer.write_addition('origin_visit', visit) for visit in visits: visit_id = visit.visit origin_url = visit.origin visit = attr.evolve(visit, origin=origin_url) self._objects[(origin_url, visit_id)].append( ('origin_visit', None)) while len(self._origin_visits[origin_url]) <= visit_id: self._origin_visits[origin_url].append(None) self._origin_visits[origin_url][visit_id-1] = visit def _convert_visit(self, visit): if visit is None: return visit = visit.to_dict() return visit def origin_visit_get(self, origin, last_visit=None, limit=None): - """Retrieve all the origin's visit's information. - - Args: - origin (int): the origin's identifier - last_visit (int): visit's id from which listing the next ones, - default to None - limit (int): maximum number of results to return, - default to None - - Yields: - List of visits. - - """ origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] if last_visit is not None: visits = visits[last_visit:] if limit is not None: visits = visits[:limit] for visit in visits: if not visit: continue visit_id = visit.visit yield self._convert_visit( self._origin_visits[origin_url][visit_id-1]) def origin_visit_find_by_date(self, origin, visit_date): - """Retrieves the origin visit whose date is closest to the provided - timestamp. - In case of a tie, the visit with largest id is selected. - - Args: - origin (str): The occurrence's origin (URL). - target (datetime): target timestamp - - Returns: - A visit. - - """ origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] visit = min( visits, key=lambda v: (abs(v.date - visit_date), -v.visit)) return self._convert_visit(visit) def origin_visit_get_by(self, origin, visit): - """Retrieve origin visit's information. - - Args: - origin (int): the origin's identifier - - Returns: - The information on that particular (origin, visit) or None if - it does not exist - - """ origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits and \ visit <= len(self._origin_visits[origin_url]): return self._convert_visit( self._origin_visits[origin_url][visit-1]) def origin_visit_get_latest( self, origin, allowed_statuses=None, require_snapshot=False): - """Get the latest origin visit for the given origin, optionally - looking only for those with one of the given allowed_statuses - or for those with a known snapshot. - - Args: - origin (str): the origin's URL - allowed_statuses (list of str): list of visit statuses considered - to find the latest visit. For instance, - ``allowed_statuses=['full']`` will only consider visits that - have successfully run to completion. - require_snapshot (bool): If True, only a visit with a snapshot - will be returned. - - Returns: - dict: a dict with the following keys: - - - **origin**: the URL of the origin - - **visit**: origin visit id - - **type**: type of loader used for the visit - - **date**: timestamp of such visit - - **status**: Visit's new status - - **metadata**: Data associated to the visit - - **snapshot** (Optional[sha1_git]): identifier of the snapshot - associated to the visit - """ origin = self._origins.get(origin) if not origin: return visits = self._origin_visits[origin.url] if allowed_statuses is not None: visits = [visit for visit in visits if visit.status in allowed_statuses] if require_snapshot: visits = [visit for visit in visits if visit.snapshot] visit = max( visits, key=lambda v: (v.date, v.visit), default=None) return self._convert_visit(visit) def _select_random_origin_visit_by_type(self, type: str) -> str: - """Select randomly an origin visit """ while True: url = random.choice(list(self._origin_visits.keys())) random_origin_visits = self._origin_visits[url] if random_origin_visits[0].type == type: return url def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: - """Randomly select one successful origin visit with - made in the last 3 months. - - Returns: - dict representing an origin visit, in the same format as - `origin_visit_get`. - - """ url = self._select_random_origin_visit_by_type(type) random_origin_visits = copy.deepcopy(self._origin_visits[url]) random_origin_visits.reverse() back_in_the_day = now() - timedelta(weeks=12) # 3 months back # This should be enough for tests for visit in random_origin_visits: if visit.date > back_in_the_day and visit.status == 'full': return visit.to_dict() else: return None def stat_counters(self): - """compute statistics about the number of tuples in various tables - - Returns: - dict: a dictionary mapping textual labels (e.g., content) to - integer values (e.g., the number of tuples in table content) - - """ keys = ( 'content', 'directory', 'origin', 'origin_visit', 'person', 'release', 'revision', 'skipped_content', 'snapshot' ) stats = {key: 0 for key in keys} stats.update(collections.Counter( obj_type for (obj_type, obj_id) in itertools.chain(*self._objects.values()))) return stats def refresh_stat_counters(self): - """Recomputes the statistics for `stat_counters`.""" pass def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): - """ Add an origin_metadata for the origin at ts with provenance and - metadata. - - Args: - origin_url (str): the origin url for which the metadata is added - ts (datetime): timestamp of the found metadata - provider: id of the provider of metadata (ex:'hal') - tool: id of the tool used to extract metadata - metadata (jsonb): the metadata retrieved at the time and location - """ if not isinstance(origin_url, str): raise TypeError('origin_id must be str, not %r' % (origin_url,)) if isinstance(ts, str): ts = dateutil.parser.parse(ts) origin_metadata = { 'origin_url': origin_url, 'discovery_date': ts, 'tool_id': tool, 'metadata': metadata, 'provider_id': provider, } self._origin_metadata[origin_url].append(origin_metadata) return None def origin_metadata_get_by(self, origin_url, provider_type=None): - """Retrieve list of all origin_metadata entries for the origin_url - - Args: - origin_url (str): the origin's url - provider_type (str): (optional) type of provider - - Returns: - list of dicts: the origin_metadata dictionary with the keys: - - - origin_url (int): origin's URL - - 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) - - """ if not isinstance(origin_url, str): raise TypeError('origin_url must be str, not %r' % (origin_url,)) metadata = [] for item in self._origin_metadata[origin_url]: item = copy.deepcopy(item) provider = self.metadata_provider_get(item['provider_id']) for attr_name in ('name', 'type', 'url'): item['provider_' + attr_name] = \ provider['provider_' + attr_name] metadata.append(item) return metadata def tool_add(self, tools): - """Add new tools to the storage. - - Args: - tools (iterable of :class:`dict`): Tool information to add to - storage. Each tool is a :class:`dict` with the following keys: - - - name (:class:`str`): name of the tool - - version (:class:`str`): version of the tool - - configuration (:class:`dict`): configuration of the tool, - must be json-encodable - - Returns: - :class:`dict`: All the tools inserted in storage - (including the internal ``id``). The order of the list is not - guaranteed to match the order of the initial list. - - """ inserted = [] for tool in tools: key = self._tool_key(tool) assert 'id' not in tool record = copy.deepcopy(tool) record['id'] = key # TODO: remove this if key not in self._tools: self._tools[key] = record inserted.append(copy.deepcopy(self._tools[key])) return inserted def tool_get(self, tool): - """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. - - """ return self._tools.get(self._tool_key(tool)) def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata): - """Add a metadata provider. - - Args: - provider_name (str): Its name - provider_type (str): Its type - provider_url (str): Its URL - metadata: JSON-encodable object - - Returns: - an identifier of the provider - """ provider = { 'provider_name': provider_name, 'provider_type': provider_type, 'provider_url': provider_url, 'metadata': metadata, } key = self._metadata_provider_key(provider) provider['id'] = key self._metadata_providers[key] = provider return key def metadata_provider_get(self, provider_id): - """Get a metadata provider - - Args: - provider_id: Its identifier, as given by `metadata_provider_add`. - - Returns: - dict: same as `metadata_provider_add`; - or None if it does not exist. - """ return self._metadata_providers.get(provider_id) def metadata_provider_get_by(self, provider): - """Get a metadata provider - - Args: - provider_name: Its name - provider_url: Its URL - - Returns: - dict: same as `metadata_provider_add`; - or None if it does not exist. - """ key = self._metadata_provider_key(provider) return self._metadata_providers.get(key) def _get_origin_url(self, origin): if isinstance(origin, str): return origin else: raise TypeError('origin must be a string.') def _person_add(self, person): - """Add a person in storage. - - Note: Private method, do not use outside of this class. - - Args: - person: dictionary with keys fullname, name and email. - - """ key = ('person', person.fullname) if key not in self._objects: person_id = len(self._persons) + 1 self._persons.append(person) self._objects[key].append(('person', person_id)) else: person_id = self._objects[key][0][1] person = self._persons[person_id-1] return person @staticmethod def _content_key(content): """A stable key for a content""" return tuple(getattr(content, key) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _content_key_algorithm(content): """ A stable key and the algorithm for a content""" if isinstance(content, Content): content = content.to_dict() return tuple((content.get(key), key) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _tool_key(tool): return '%r %r %r' % (tool['name'], tool['version'], tuple(sorted(tool['configuration'].items()))) @staticmethod def _metadata_provider_key(provider): return '%r %r' % (provider['provider_name'], provider['provider_url']) + + def diff_directories(self, from_dir, to_dir, track_renaming=False): + raise NotImplementedError('InMemoryStorage.diff_directories') + + def diff_revisions(self, from_rev, to_rev, track_renaming=False): + raise NotImplementedError('InMemoryStorage.diff_revisions') + + def diff_revision(self, revision, track_renaming=False): + raise NotImplementedError('InMemoryStorage.diff_revision') diff --git a/swh/storage/interface.py b/swh/storage/interface.py new file mode 100644 index 00000000..7824d024 --- /dev/null +++ b/swh/storage/interface.py @@ -0,0 +1,1224 @@ +# Copyright (C) 2015-2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from typing import Any, Dict, List, Optional + +from swh.core.api import remote_api_endpoint + + +class StorageInterface: + @remote_api_endpoint('check_config') + def check_config(self, *, check_write): + """Check that the storage is configured and ready to go.""" + ... + + @remote_api_endpoint('content/add') + def content_add(self, content): + """Add content blobs to the storage + + Args: + contents (iterable): iterable of dictionaries representing + individual pieces of content to add. Each dictionary has the + following keys: + + - data (bytes): the actual content + - length (int): content length (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 + + Raises: + + The following exceptions can occur: + + - HashCollision in case of collision + - Any other exceptions raise by the db + + In case of errors, some of the content may have been stored in + the DB and in the objstorage. + Since additions to both idempotent, that should not be a problem. + + Returns: + Summary dict with the following key and associated values: + + content:add: New contents added + content:add:bytes: Sum of the contents' length data + skipped_content:add: New skipped contents (no data) added + """ + ... + + @remote_api_endpoint('content/update') + def content_update(self, content, keys=[]): + """Update content blobs to the storage. Does nothing for unknown + contents or skipped ones. + + Args: + content (iterable): iterable of dictionaries representing + individual pieces of content to update. Each dictionary has the + following keys: + + - data (bytes): the actual content + - length (int): content length (default: -1) + - one key for each checksum algorithm in + :data:`swh.model.hashutil.ALGORITHMS`, mapped to the + corresponding checksum + - status (str): one of visible, hidden, absent + + keys (list): List of keys (str) whose values needs an update, e.g., + new hash column + + """ + ... + + @remote_api_endpoint('content/add_metadata') + def content_add_metadata(self, content): + """Add content metadata to the storage (like `content_add`, but + without inserting to the objstorage). + + Args: + content (iterable): iterable of dictionaries representing + individual pieces of content to add. Each dictionary has the + following keys: + + - length (int): content length (default: -1) + - one key for each checksum algorithm in + :data:`swh.model.hashutil.ALGORITHMS`, mapped to the + corresponding checksum + - status (str): one of visible, hidden, absent + - reason (str): if status = absent, the reason why + - origin (int): if status = absent, the origin we saw the + content in + - ctime (datetime): time of insertion in the archive + + Returns: + Summary dict with the following key and associated values: + + content:add: New contents added + skipped_content:add: New skipped contents (no data) added + """ + ... + + @remote_api_endpoint('content/data') + def content_get(self, content): + """Retrieve in bulk contents and their data. + + This generator yields exactly as many items than provided sha1 + identifiers, but callers should not assume this will always be true. + + It may also yield `None` values in case an object was not found. + + Args: + content: iterables of sha1 + + Yields: + Dict[str, bytes]: Generates streams of contents as dict with their + raw data: + + - sha1 (bytes): content id + - data (bytes): content's raw data + + Raises: + ValueError in case of too much contents are required. + cf. BULK_BLOCK_CONTENT_LEN_MAX + + """ + ... + + @remote_api_endpoint('content/range') + def content_get_range(self, start, end, limit=1000): + """Retrieve contents within range [start, end] bound by limit. + + Note that this function may return more than one blob per hash. The + limit is enforced with multiplicity (ie. two blobs with the same hash + will count twice toward the limit). + + Args: + **start** (bytes): Starting identifier range (expected smaller + than end) + **end** (bytes): Ending identifier range (expected larger + than start) + **limit** (int): Limit result (default to 1000) + + Returns: + a dict with keys: + - contents [dict]: iterable of contents in between the range. + - next (bytes): There remains content in the range + starting from this next sha1 + + """ + ... + + @remote_api_endpoint('content/partition') + def content_get_partition( + self, partition_id: int, nb_partitions: int, limit: int = 1000, + page_token: str = None): + """Splits contents into nb_partitions, and returns one of these based on + partition_id (which must be in [0, nb_partitions-1]) + + There is no guarantee on how the partitioning is done, or the + result order. + + Args: + partition_id (int): index of the partition to fetch + nb_partitions (int): total number of partitions to split into + limit (int): Limit result (default to 1000) + page_token (Optional[str]): opaque token used for pagination. + + Returns: + a dict with keys: + - contents (List[dict]): iterable of contents in the partition. + - **next_page_token** (Optional[str]): opaque token to be used as + `page_token` for retrieving the next page. if absent, there is + no more pages to gather. + """ + ... + + @remote_api_endpoint('content/metadata') + def content_get_metadata( + self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: + """Retrieve content metadata in bulk + + Args: + content: iterable of content identifiers (sha1) + + Returns: + a dict with keys the content's sha1 and the associated value + either the existing content's metadata or None if the content does + not exist. + + """ + ... + + @remote_api_endpoint('content/missing') + def content_missing(self, content, key_hash='sha1'): + """List content missing from storage + + Args: + content ([dict]): iterable of dictionaries whose keys are + either 'length' or an item of + :data:`swh.model.hashutil.ALGORITHMS`; + mapped to the corresponding checksum + (or length). + + key_hash (str): name of the column to use as hash id + result (default: 'sha1') + + Returns: + iterable ([bytes]): missing content ids (as per the + key_hash column) + + Raises: + TODO: an exception when we get a hash collision. + + """ + ... + + @remote_api_endpoint('content/missing/sha1') + def content_missing_per_sha1(self, contents): + """List content missing from storage based only on sha1. + + Args: + contents: Iterable of sha1 to check for absence. + + Returns: + iterable: missing ids + + Raises: + TODO: an exception when we get a hash collision. + + """ + ... + + @remote_api_endpoint('content/missing/sha1_git') + def content_missing_per_sha1_git(self, contents): + """List content missing from storage based only on sha1_git. + + Args: + contents (Iterable): An iterable of content id (sha1_git) + + Yields: + missing contents sha1_git + """ + ... + + @remote_api_endpoint('content/skipped/missing') + def skipped_content_missing(self, contents): + """List skipped_content missing from storage + + Args: + content: iterable of dictionaries containing the data for each + checksum algorithm. + + Returns: + iterable: missing signatures + + """ + ... + + @remote_api_endpoint('content/present') + def content_find(self, content): + """Find a content hash in db. + + Args: + content: a dictionary representing one content hash, mapping + checksum algorithm names (see swh.model.hashutil.ALGORITHMS) to + checksum values + + Returns: + a triplet (sha1, sha1_git, sha256) if the content exist + or None otherwise. + + Raises: + ValueError: in case the key of the dictionary is not sha1, sha1_git + nor sha256. + + """ + ... + + @remote_api_endpoint('content/get_random') + def content_get_random(self): + """Finds a random content id. + + Returns: + a sha1_git + """ + ... + + @remote_api_endpoint('directory/add') + 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 + + Returns: + Summary dict of keys with associated count as values: + + directory:add: Number of directories actually added + + """ + ... + + @remote_api_endpoint('directory/missing') + def directory_missing(self, directories): + """List directories missing from storage + + Args: + directories (iterable): an iterable of directory ids + + Yields: + missing directory ids + + """ + ... + + @remote_api_endpoint('directory/ls') + def directory_ls(self, directory, recursive=False): + """Get entries for one directory. + + Args: + - directory: the directory to list entries from. + - recursive: if flag on, this list recursively from this directory. + + Returns: + List of entries for such directory. + + If `recursive=True`, names in the path of a dir/file not at the + root are concatenated with a slash (`/`). + + """ + ... + + @remote_api_endpoint('directory/path') + def directory_entry_get_by_path(self, directory, paths): + """Get the directory entry (either file or dir) from directory with path. + + Args: + - directory: sha1 of the top level directory + - paths: path to lookup from the top level directory. From left + (top) to right (bottom). + + Returns: + The corresponding directory entry if found, None otherwise. + + """ + ... + + @remote_api_endpoint('directory/get_random') + def directory_get_random(self): + """Finds a random directory id. + + Returns: + a sha1_git + """ + ... + + @remote_api_endpoint('revision/add') + def revision_add(self, revisions): + """Add revisions to the storage + + Args: + revisions (Iterable[dict]): iterable of dictionaries representing + the individual revisions to add. Each dict has the following + keys: + + - **id** (:class:`sha1_git`): id of the revision to add + - **date** (:class:`dict`): date the revision was written + - **committer_date** (:class:`dict`): date the revision got + added to the origin + - **type** (one of 'git', 'tar'): type of the + revision added + - **directory** (:class:`sha1_git`): the directory the + revision points at + - **message** (:class:`bytes`): the message associated with + the revision + - **author** (:class:`Dict[str, bytes]`): dictionary with + keys: name, fullname, email + - **committer** (:class:`Dict[str, bytes]`): dictionary with + keys: name, fullname, email + - **metadata** (:class:`jsonb`): extra information as + dictionary + - **synthetic** (:class:`bool`): revision's nature (tarball, + directory creates synthetic revision`) + - **parents** (:class:`list[sha1_git]`): the parents of + this revision + + date dictionaries have the form defined in :mod:`swh.model`. + + Returns: + Summary dict of keys with associated count as values + + revision:add: New objects actually stored in db + + """ + ... + + @remote_api_endpoint('revision/missing') + def revision_missing(self, revisions): + """List revisions missing from storage + + Args: + revisions (iterable): revision ids + + Yields: + missing revision ids + + """ + ... + + @remote_api_endpoint('revision') + def revision_get(self, revisions): + """Get all revisions from storage + + Args: + revisions: an iterable of revision ids + + Returns: + iterable: an iterable of revisions as dictionaries (or None if the + revision doesn't exist) + + """ + ... + + @remote_api_endpoint('revision/log') + def revision_log(self, revisions, limit=None): + """Fetch revision entry from the given root revisions. + + Args: + revisions: array of root revision to lookup + limit: limitation on the output result. Default to None. + + Yields: + List of revision log from such revisions root. + + """ + ... + + @remote_api_endpoint('revision/shortlog') + def revision_shortlog(self, revisions, limit=None): + """Fetch the shortlog for the given revisions + + Args: + revisions: list of root revisions to lookup + limit: depth limitation for the output + + Yields: + a list of (id, parents) tuples. + + """ + ... + + @remote_api_endpoint('revision/get_random') + def revision_get_random(self): + """Finds a random revision id. + + Returns: + a sha1_git + """ + ... + + @remote_api_endpoint('release/add') + def release_add(self, releases): + """Add releases to the storage + + Args: + releases (Iterable[dict]): iterable of dictionaries representing + the individual releases to add. Each dict has the following + keys: + + - **id** (:class:`sha1_git`): id of the release to add + - **revision** (:class:`sha1_git`): id of the revision the + release points to + - **date** (:class:`dict`): the date the release was made + - **name** (:class:`bytes`): the name of the release + - **comment** (:class:`bytes`): the comment associated with + the release + - **author** (:class:`Dict[str, bytes]`): dictionary with + keys: name, fullname, email + + the date dictionary has the form defined in :mod:`swh.model`. + + Returns: + Summary dict of keys with associated count as values + + release:add: New objects contents actually stored in db + + """ + ... + + @remote_api_endpoint('release/missing') + def release_missing(self, releases): + """List releases missing from storage + + Args: + releases: an iterable of release ids + + Returns: + a list of missing release ids + + """ + ... + + @remote_api_endpoint('release') + def release_get(self, releases): + """Given a list of sha1, return the releases's information + + Args: + releases: list of sha1s + + Yields: + dicts with the same keys as those given to `release_add` + (or ``None`` if a release does not exist) + + """ + ... + + @remote_api_endpoint('release/get_random') + def release_get_random(self): + """Finds a random release id. + + Returns: + a sha1_git + """ + ... + + @remote_api_endpoint('snapshot/add') + def snapshot_add(self, snapshots): + """Add snapshots to the storage. + + Args: + snapshot ([dict]): the snapshots to add, containing the + following keys: + + - **id** (:class:`bytes`): id of the snapshot + - **branches** (:class:`dict`): branches the snapshot contains, + mapping the branch name (:class:`bytes`) to the branch target, + itself a :class:`dict` (or ``None`` if the branch points to an + unknown object) + + - **target_type** (:class:`str`): one of ``content``, + ``directory``, ``revision``, ``release``, + ``snapshot``, ``alias`` + - **target** (:class:`bytes`): identifier of the target + (currently a ``sha1_git`` for all object kinds, or the name + of the target branch for aliases) + + Raises: + ValueError: if the origin or visit id does not exist. + + Returns: + + Summary dict of keys with associated count as values + + snapshot:add: Count of object actually stored in db + + """ + ... + + @remote_api_endpoint('snapshot/missing') + def snapshot_missing(self, snapshots): + """List snapshots missing from storage + + Args: + snapshots (iterable): an iterable of snapshot ids + + Yields: + missing snapshot ids + + """ + ... + + @remote_api_endpoint('snapshot') + def snapshot_get(self, snapshot_id): + """Get the content, possibly partial, of a snapshot with the given id + + The branches of the snapshot are iterated in the lexicographical + order of their names. + + .. warning:: At most 1000 branches contained in the snapshot will be + returned for performance reasons. In order to browse the whole + set of branches, the method :meth:`snapshot_get_branches` + should be used instead. + + Args: + snapshot_id (bytes): identifier of the snapshot + Returns: + dict: a dict with three keys: + * **id**: identifier of the snapshot + * **branches**: a dict of branches contained in the snapshot + whose keys are the branches' names. + * **next_branch**: the name of the first branch not returned + or :const:`None` if the snapshot has less than 1000 + branches. + """ + ... + + @remote_api_endpoint('snapshot/by_origin_visit') + def snapshot_get_by_origin_visit(self, origin, visit): + """Get the content, possibly partial, of a snapshot for the given origin visit + + The branches of the snapshot are iterated in the lexicographical + order of their names. + + .. warning:: At most 1000 branches contained in the snapshot will be + returned for performance reasons. In order to browse the whole + set of branches, the method :meth:`snapshot_get_branches` + should be used instead. + + Args: + origin (int): the origin identifier + visit (int): the visit identifier + Returns: + dict: None if the snapshot does not exist; + a dict with three keys otherwise: + * **id**: identifier of the snapshot + * **branches**: a dict of branches contained in the snapshot + whose keys are the branches' names. + * **next_branch**: the name of the first branch not returned + or :const:`None` if the snapshot has less than 1000 + branches. + + """ + ... + + @remote_api_endpoint('snapshot/latest') + def snapshot_get_latest(self, origin, allowed_statuses=None): + """Get the content, possibly partial, of the latest snapshot for the + given origin, optionally only from visits that have one of the given + allowed_statuses + + The branches of the snapshot are iterated in the lexicographical + order of their names. + + .. warning:: At most 1000 branches contained in the snapshot will be + returned for performance reasons. In order to browse the whole + set of branches, the method :meth:`snapshot_get_branches` + should be used instead. + + Args: + origin (str): the origin's URL + allowed_statuses (list of str): list of visit statuses considered + to find the latest snapshot for the visit. For instance, + ``allowed_statuses=['full']`` will only consider visits that + have successfully run to completion. + Returns: + dict: a dict with three keys: + * **id**: identifier of the snapshot + * **branches**: a dict of branches contained in the snapshot + whose keys are the branches' names. + * **next_branch**: the name of the first branch not returned + or :const:`None` if the snapshot has less than 1000 + branches. + """ + ... + + @remote_api_endpoint('snapshot/count_branches') + def snapshot_count_branches(self, snapshot_id): + """Count the number of branches in the snapshot with the given id + + Args: + snapshot_id (bytes): identifier of the snapshot + + Returns: + dict: A dict whose keys are the target types of branches and + values their corresponding amount + """ + ... + + @remote_api_endpoint('snapshot/get_branches') + def snapshot_get_branches(self, snapshot_id, branches_from=b'', + branches_count=1000, target_types=None): + """Get the content, possibly partial, of a snapshot with the given id + + The branches of the snapshot are iterated in the lexicographical + order of their names. + + Args: + snapshot_id (bytes): identifier of the snapshot + branches_from (bytes): optional parameter used to skip branches + whose name is lesser than it before returning them + branches_count (int): optional parameter used to restrain + the amount of returned branches + target_types (list): optional parameter used to filter the + target types of branch to return (possible values that can be + contained in that list are `'content', 'directory', + 'revision', 'release', 'snapshot', 'alias'`) + Returns: + dict: None if the snapshot does not exist; + a dict with three keys otherwise: + * **id**: identifier of the snapshot + * **branches**: a dict of branches contained in the snapshot + whose keys are the branches' names. + * **next_branch**: the name of the first branch not returned + or :const:`None` if the snapshot has less than + `branches_count` branches after `branches_from` included. + """ + ... + + @remote_api_endpoint('snapshot/get_random') + def snapshot_get_random(self): + """Finds a random snapshot id. + + Returns: + a sha1_git + """ + ... + + @remote_api_endpoint('origin/visit/add') + def origin_visit_add(self, origin, date, type): + """Add an origin_visit for the origin at ts with status 'ongoing'. + + Args: + origin (str): visited origin's identifier or URL + date (Union[str,datetime]): timestamp of such visit + type (str): the type of loader used for the visit (hg, git, ...) + + Returns: + dict: dictionary with keys origin and visit where: + + - origin: origin identifier + - visit: the visit identifier for the new visit occurrence + + """ + ... + + @remote_api_endpoint('origin/visit/update') + def origin_visit_update(self, origin, visit_id, status=None, + metadata=None, snapshot=None): + """Update an origin_visit's status. + + Args: + origin (str): visited origin's URL + visit_id: Visit's id + status: Visit's new status + metadata: Data associated to the visit + snapshot (sha1_git): identifier of the snapshot to add to + the visit + + Returns: + None + + """ + ... + + @remote_api_endpoint('origin/visit/upsert') + def origin_visit_upsert(self, visits): + """Add a origin_visits with a specific id and with all its data. + If there is already an origin_visit with the same + `(origin_id, visit_id)`, overwrites it. + + Args: + visits: iterable of dicts with keys: + + - **origin**: dict with keys either `id` or `url` + - **visit**: origin visit id + - **date**: timestamp of such visit + - **status**: Visit's new status + - **metadata**: Data associated to the visit + - **snapshot**: identifier of the snapshot to add to + the visit + """ + ... + + @remote_api_endpoint('origin/visit/get') + def origin_visit_get(self, origin, last_visit=None, limit=None): + """Retrieve all the origin's visit's information. + + Args: + origin (str): The visited origin + last_visit: 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. + + """ + ... + + @remote_api_endpoint('origin/visit/find_by_date') + def origin_visit_find_by_date(self, origin, visit_date): + """Retrieves the origin visit whose date is closest to the provided + timestamp. + In case of a tie, the visit with largest id is selected. + + Args: + origin (str): The occurrence's origin (URL). + target (datetime): target timestamp + + Returns: + A visit. + + """ + ... + + @remote_api_endpoint('origin/visit/getby') + def origin_visit_get_by(self, origin, visit): + """Retrieve origin visit's information. + + Args: + origin: The occurrence's origin (identifier). + + Returns: + The information on that particular (origin, visit) or None if + it does not exist + + """ + ... + + @remote_api_endpoint('origin/visit/get_latest') + def origin_visit_get_latest( + self, origin, allowed_statuses=None, require_snapshot=False): + """Get the latest origin visit for the given origin, optionally + looking only for those with one of the given allowed_statuses + or for those with a known snapshot. + + Args: + origin (str): the origin's URL + allowed_statuses (list of str): list of visit statuses considered + to find the latest visit. For instance, + ``allowed_statuses=['full']`` will only consider visits that + have successfully run to completion. + require_snapshot (bool): If True, only a visit with a snapshot + will be returned. + + Returns: + dict: a dict with the following keys: + + - **origin**: the URL of the origin + - **visit**: origin visit id + - **type**: type of loader used for the visit + - **date**: timestamp of such visit + - **status**: Visit's new status + - **metadata**: Data associated to the visit + - **snapshot** (Optional[sha1_git]): identifier of the snapshot + associated to the visit + """ + ... + + @remote_api_endpoint('origin/visit/get_random') + def origin_visit_get_random( + self, type: str) -> Optional[Dict[str, Any]]: + """Randomly select one successful origin visit with + made in the last 3 months. + + Returns: + dict representing an origin visit, in the same format as + :py:meth:`origin_visit_get`. + + """ + ... + + @remote_api_endpoint('object/find_by_sha1_git') + def object_find_by_sha1_git(self, ids): + """Return the objects found with the given ids. + + Args: + ids: a generator of sha1_gits + + Returns: + dict: a mapping from id to the list of objects found. Each object + found is itself a dict with keys: + + - sha1_git: the input id + - type: the type of object found + + """ + ... + + @remote_api_endpoint('origin/get') + def origin_get(self, origins): + """Return origins, either all identified by their ids or all + identified by tuples (type, url). + + If the url is given and the type is omitted, one of the origins with + that url is returned. + + Args: + origin: a list of dictionaries representing the individual + origins to find. + These dicts have the key url: + + - url (bytes): the url the origin points to + + Returns: + dict: the origin dictionary with the keys: + + - id: origin's id + - url: origin's url + + Raises: + ValueError: if the url or the id don't exist. + + """ + ... + + @remote_api_endpoint('origin/get_sha1') + def origin_get_by_sha1(self, sha1s): + """Return origins, identified by the sha1 of their URLs. + + Args: + sha1s (list[bytes]): a list of sha1s + + Yields: + dicts containing origin information as returned + by :meth:`swh.storage.storage.Storage.origin_get`, or None if an + origin matching the sha1 is not found. + + """ + ... + + @remote_api_endpoint('origin/get_range') + def origin_get_range(self, origin_from=1, origin_count=100): + """Retrieve ``origin_count`` origins whose ids are greater + or equal than ``origin_from``. + + Origins are sorted by id before retrieving them. + + Args: + origin_from (int): the minimum id of origins to retrieve + origin_count (int): the maximum number of origins to retrieve + + Yields: + dicts containing origin information as returned + by :meth:`swh.storage.storage.Storage.origin_get`. + """ + ... + + @remote_api_endpoint('origin/list') + def origin_list( + self, page_token: Optional[str] = None, limit: int = 100) -> dict: + """Returns the list of origins + + Args: + page_token: opaque token used for pagination. + limit: the maximum number of results to return + + Returns: + dict: dict with the following keys: + - **next_page_token** (str, optional): opaque token to be used as + `page_token` for retrieving the next page. if absent, there is + no more pages to gather. + - **origins** (List[dict]): list of origins, as returned by + `origin_get`. + """ + ... + + @remote_api_endpoint('origin/search') + def origin_search(self, url_pattern, offset=0, limit=50, + regexp=False, with_visit=False): + """Search for origins whose urls contain a provided string pattern + or match a provided regular expression. + The search is performed in a case insensitive way. + + Args: + url_pattern (str): the string pattern to search for in origin urls + offset (int): number of found origins to skip before returning + results + limit (int): the maximum number of found origins to return + regexp (bool): if True, consider the provided pattern as a regular + expression and return origins whose urls match it + with_visit (bool): if True, filter out origins with no visit + + Yields: + dicts containing origin information as returned + by :meth:`swh.storage.storage.Storage.origin_get`. + """ + ... + + @remote_api_endpoint('origin/count') + def origin_count(self, url_pattern, regexp=False, + with_visit=False): + """Count origins whose urls contain a provided string pattern + or match a provided regular expression. + The pattern search in origin urls is performed in a case insensitive + way. + + Args: + url_pattern (str): the string pattern to search for in origin urls + regexp (bool): if True, consider the provided pattern as a regular + expression and return origins whose urls match it + with_visit (bool): if True, filter out origins with no visit + + Returns: + int: The number of origins matching the search criterion. + """ + ... + + @remote_api_endpoint('origin/add_multi') + def origin_add(self, origins): + """Add origins to the storage + + Args: + origins: list of dictionaries representing the individual origins, + with the following keys: + + - type: the origin type ('git', 'svn', 'deb', ...) + - url (bytes): the url the origin points to + + Returns: + list: given origins as dict updated with their id + + """ + ... + + @remote_api_endpoint('origin/add') + def origin_add_one(self, origin): + """Add origin to the storage + + Args: + origin: dictionary representing the individual origin to add. This + dict has the following keys: + + - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) + - url (bytes): the url the origin points to + + Returns: + the id of the added origin, or of the identical one that already + exists. + + """ + ... + + def stat_counters(self): + """compute statistics about the number of tuples in various tables + + Returns: + dict: a dictionary mapping textual labels (e.g., content) to + integer values (e.g., the number of tuples in table content) + + """ + ... + + def refresh_stat_counters(self): + """Recomputes the statistics for `stat_counters`.""" + ... + + @remote_api_endpoint('origin/metadata/add') + def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): + """ Add an origin_metadata for the origin at ts with provenance and + metadata. + + Args: + origin_url (str): the origin url for which the metadata is added + ts (datetime): timestamp of the found metadata + provider (int): the provider of metadata (ex:'hal') + tool (int): tool used to extract metadata + metadata (jsonb): the metadata retrieved at the time and location + """ + ... + + @remote_api_endpoint('origin/metadata/get') + def origin_metadata_get_by(self, origin_url, provider_type=None): + """Retrieve list of all origin_metadata entries for the origin_id + + Args: + origin_url (str): the origin's URL + provider_type (str): (optional) type of provider + + Returns: + list of dicts: the origin_metadata dictionary with the keys: + + - origin_id (int): origin's id + - discovery_date (datetime): timestamp of discovery + - tool_id (int): metadata's extracting tool + - metadata (jsonb) + - provider_id (int): metadata's provider + - provider_name (str) + - provider_type (str) + - provider_url (str) + + """ + ... + + @remote_api_endpoint('tool/add') + def tool_add(self, tools): + """Add new tools to the storage. + + Args: + tools (iterable of :class:`dict`): Tool information to add to + storage. Each tool is a :class:`dict` with the following keys: + + - name (:class:`str`): name of the tool + - version (:class:`str`): version of the tool + - configuration (:class:`dict`): configuration of the tool, + must be json-encodable + + Returns: + :class:`dict`: All the tools inserted in storage + (including the internal ``id``). The order of the list is not + guaranteed to match the order of the initial list. + + """ + ... + + @remote_api_endpoint('tool/data') + def tool_get(self, tool): + """Retrieve tool information. + + Args: + tool (dict): Tool information we want to retrieve from storage. + The dicts have the same keys as those used in :func:`tool_add`. + + Returns: + dict: The full tool information if it exists (``id`` included), + None otherwise. + + """ + ... + + @remote_api_endpoint('provider/add') + def metadata_provider_add(self, provider_name, provider_type, provider_url, + metadata): + """Add a metadata provider. + + Args: + provider_name (str): Its name + provider_type (str): Its type (eg. `'deposit-client'`) + provider_url (str): Its URL + metadata: JSON-encodable object + + Returns: + int: an identifier of the provider + """ + ... + + @remote_api_endpoint('provider/get') + def metadata_provider_get(self, provider_id): + """Get a metadata provider + + Args: + provider_id: Its identifier, as given by `metadata_provider_add`. + + Returns: + dict: same as `metadata_provider_add`; + or None if it does not exist. + """ + ... + + @remote_api_endpoint('provider/getby') + def metadata_provider_get_by(self, provider): + """Get a metadata provider + + Args: + provider (dict): A dictionary with keys: + * provider_name: Its name + * provider_url: Its URL + + Returns: + dict: same as `metadata_provider_add`; + or None if it does not exist. + """ + ... + + @remote_api_endpoint('algos/diff_directories') + def diff_directories(self, from_dir, to_dir, track_renaming=False): + """Compute the list of file changes introduced between two arbitrary + directories (insertion / deletion / modification / renaming of files). + + Args: + from_dir (bytes): identifier of the directory to compare from + to_dir (bytes): identifier of the directory to compare to + track_renaming (bool): whether or not to track files renaming + + Returns: + A list of dict describing the introduced file changes + (see :func:`swh.storage.algos.diff.diff_directories` + for more details). + """ + ... + + @remote_api_endpoint('algos/diff_revisions') + def diff_revisions(self, from_rev, to_rev, track_renaming=False): + """Compute the list of file changes introduced between two arbitrary + revisions (insertion / deletion / modification / renaming of files). + + Args: + from_rev (bytes): identifier of the revision to compare from + to_rev (bytes): identifier of the revision to compare to + track_renaming (bool): whether or not to track files renaming + + Returns: + A list of dict describing the introduced file changes + (see :func:`swh.storage.algos.diff.diff_directories` + for more details). + """ + ... + + @remote_api_endpoint('algos/diff_revision') + def diff_revision(self, revision, track_renaming=False): + """Compute the list of file changes introduced by a specific revision + (insertion / deletion / modification / renaming of files) by comparing + it against its first parent. + + Args: + revision (bytes): identifier of the revision from which to + compute the list of files changes + track_renaming (bool): whether or not to track files renaming + + Returns: + A list of dict describing the introduced file changes + (see :func:`swh.storage.algos.diff.diff_directories` + for more details). + """ + ... diff --git a/swh/storage/storage.py b/swh/storage/storage.py index b74d31b8..5a919934 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,2171 +1,1162 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy import datetime import itertools import json from collections import defaultdict from concurrent.futures import ThreadPoolExecutor from contextlib import contextmanager from typing import Any, Dict, List, Optional import dateutil.parser import psycopg2 import psycopg2.pool -from swh.core.api import remote_api_endpoint from swh.model.model import SHA1_SIZE from swh.model.hashutil import ALGORITHMS, hash_to_bytes, hash_to_hex from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError try: from swh.journal.writer import get_journal_writer except ImportError: get_journal_writer = None # type: ignore # mypy limitation, see https://github.com/python/mypy/issues/1153 from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageDBError from .algos import diff from .metrics import timed, send_metric, process_metrics from .utils import get_partition_bounds_bytes # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 EMPTY_SNAPSHOT_ID = hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e') """Identifier for the empty snapshot""" class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db, objstorage, min_pool_conns=1, max_pool_conns=10, journal_writer=None): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ try: if isinstance(db, psycopg2.extensions.connection): self._pool = None self._db = Db(db) else: self._pool = psycopg2.pool.ThreadedConnectionPool( min_pool_conns, max_pool_conns, db ) self._db = None except psycopg2.OperationalError as e: raise StorageDBError(e) self.objstorage = get_objstorage(**objstorage) if journal_writer: if get_journal_writer is None: raise EnvironmentError( 'You need the swh.journal package to use the ' 'journal_writer feature') self.journal_writer = get_journal_writer(**journal_writer) else: self.journal_writer = None def get_db(self): if self._db: return self._db else: return Db.from_pool(self._pool) def put_db(self, db): if db is not self._db: db.put_conn() @contextmanager def db(self): db = None try: db = self.get_db() yield db finally: if db: self.put_db(db) - @remote_api_endpoint('check_config') @timed @db_transaction() def check_config(self, *, check_write, db=None, cur=None): - """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 if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content', %s)", (check,) ) return cur.fetchone()[0] def _content_unique_key(self, hash, db): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ keys = db.content_hash_keys if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) @staticmethod def _normalize_content(d): d = d.copy() if 'status' not in d: d['status'] = 'visible' if 'length' not in d: d['length'] = -1 return d @staticmethod def _validate_content(d): """Sanity checks on status / reason / length, that postgresql doesn't enforce.""" if d['status'] not in ('visible', 'absent', 'hidden'): raise ValueError('Invalid content status: {}'.format(d['status'])) if d['status'] != 'absent' and d.get('reason') is not None: raise ValueError( 'Must not provide a reason if content is not absent.') if d['length'] < -1: raise ValueError('Content length must be positive or -1.') def _filter_new_content(self, content, db=None, cur=None): """Sort contents into buckets 'with data' and 'without data', and filter out those already in the database.""" content_by_status = defaultdict(list) for d in content: content_by_status[d['status']].append(d) content_with_data = content_by_status['visible'] \ + content_by_status['hidden'] content_without_data = content_by_status['absent'] missing_content = set(self.content_missing(content_with_data, db=db, cur=cur)) missing_skipped = set(self._content_unique_key(hashes, db) for hashes in self.skipped_content_missing( content_without_data, db=db, cur=cur)) content_with_data = [ cont for cont in content_with_data if cont['sha1'] in missing_content] content_without_data = [ cont for cont in content_without_data if self._content_unique_key(cont, db) in missing_skipped] summary = { 'content:add': len(missing_content), 'skipped_content:add': len(missing_skipped), } return (content_with_data, content_without_data, summary) def _content_add_metadata(self, db, cur, content_with_data, content_without_data): """Add content to the postgresql database but not the object storage. """ if content_with_data: # create temporary table for metadata injection db.mktemp('content', cur) db.copy_to(content_with_data, 'tmp_content', db.content_add_keys, cur) # move metadata in place try: db.content_add_from_temp(cur) except psycopg2.IntegrityError as e: from . import HashCollision if e.diag.sqlstate == '23505' and \ e.diag.table_name == 'content': constraint_to_hash_name = { 'content_pkey': 'sha1', 'content_sha1_git_idx': 'sha1_git', 'content_sha256_idx': 'sha256', } colliding_hash_name = constraint_to_hash_name \ .get(e.diag.constraint_name) raise HashCollision(colliding_hash_name) from None else: raise if content_without_data: content_without_data = \ [cont.copy() for cont in content_without_data] origin_ids = db.origin_id_get_by_url( [cont.get('origin') for cont in content_without_data], cur=cur) for (cont, origin_id) in zip(content_without_data, origin_ids): if 'origin' in cont: cont['origin'] = origin_id db.mktemp('skipped_content', cur) db.copy_to(content_without_data, 'tmp_skipped_content', db.skipped_content_keys, cur) # move metadata in place db.skipped_content_add_from_temp(cur) - @remote_api_endpoint('content/add') @timed @process_metrics @db_transaction() def content_add(self, content, db=None, cur=None): - """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: - contents (iterable): iterable of dictionaries representing - individual pieces of content to add. Each dictionary has the - following keys: - - - data (bytes): the actual content - - length (int): content length (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 - - Raises: - - In case of errors, nothing is stored in the db (in the - objstorage, it could though). The following exceptions can - occur: - - - HashCollision in case of collision - - Any other exceptions raise by the db - - Returns: - Summary dict with the following key and associated values: - - content:add: New contents added - content:add:bytes: Sum of the contents' length data - skipped_content:add: New skipped contents (no data) added - """ content = [dict(c.items()) for c in content] # semi-shallow copy now = datetime.datetime.now(tz=datetime.timezone.utc) for item in content: item['ctime'] = now content = [self._normalize_content(c) for c in content] for c in content: self._validate_content(c) (content_with_data, content_without_data, summary) = \ self._filter_new_content(content, db, cur) if self.journal_writer: for item in content_with_data: if 'data' in item: item = item.copy() del item['data'] self.journal_writer.write_addition('content', item) for item in content_without_data: self.journal_writer.write_addition('content', item) def add_to_objstorage(): """Add to objstorage the new missing_content Returns: Sum of all the content's data length pushed to the objstorage. Content present twice is only sent once. """ content_bytes_added = 0 data = {} for cont in content_with_data: if cont['sha1'] not in data: data[cont['sha1']] = cont['data'] content_bytes_added += max(0, cont['length']) # FIXME: Since we do the filtering anyway now, we might as # well make the objstorage's add_batch call return what we # want here (real bytes added)... that'd simplify this... self.objstorage.add_batch(data) return content_bytes_added with ThreadPoolExecutor(max_workers=1) as executor: added_to_objstorage = executor.submit(add_to_objstorage) self._content_add_metadata( db, cur, content_with_data, content_without_data) # Wait for objstorage addition before returning from the # transaction, bubbling up any exception content_bytes_added = added_to_objstorage.result() summary['content:add:bytes'] = content_bytes_added return summary - @remote_api_endpoint('content/update') @timed @db_transaction() 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 - - """ # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. if self.journal_writer: raise NotImplementedError( - 'content_update is not yet support with a journal_writer.') + 'content_update is not yet supported with a journal_writer.') 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) - @remote_api_endpoint('content/add_metadata') @timed @process_metrics @db_transaction() def content_add_metadata(self, content, db=None, cur=None): - """Add content metadata to the storage (like `content_add`, but - without inserting to the objstorage). - - Args: - content (iterable): iterable of dictionaries representing - individual pieces of content to add. Each dictionary has the - following keys: - - - length (int): content length (default: -1) - - one key for each checksum algorithm in - :data:`swh.model.hashutil.ALGORITHMS`, mapped to the - corresponding checksum - - status (str): one of visible, hidden, absent - - reason (str): if status = absent, the reason why - - origin (int): if status = absent, the origin we saw the - content in - - ctime (datetime): time of insertion in the archive - - Returns: - Summary dict with the following key and associated values: - - content:add: New contents added - skipped_content:add: New skipped contents (no data) added - """ - content = [self._normalize_content(c) for c in content] for c in content: self._validate_content(c) (content_with_data, content_without_data, summary) = \ self._filter_new_content(content, db, cur) if self.journal_writer: for item in itertools.chain(content_with_data, content_without_data): assert 'data' not in content self.journal_writer.write_addition('content', item) self._content_add_metadata( db, cur, content_with_data, content_without_data) return summary - @remote_api_endpoint('content/data') @timed def content_get(self, content): - """Retrieve in bulk contents and their data. - - This generator yields exactly as many items than provided sha1 - identifiers, but callers should not assume this will always be true. - - It may also yield `None` values in case an object was not found. - - Args: - content: iterables of sha1 - - Yields: - Dict[str, bytes]: Generates streams of contents as dict with their - raw data: - - - sha1 (bytes): content id - - data (bytes): content's raw data - - Raises: - ValueError in case of too much contents are required. - cf. BULK_BLOCK_CONTENT_LEN_MAX - - """ # FIXME: Make this method support slicing the `data`. 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} - @remote_api_endpoint('content/range') @timed @db_transaction() def content_get_range(self, start, end, limit=1000, db=None, cur=None): - """Retrieve contents within range [start, end] bound by limit. - - Note that this function may return more than one blob per hash. The - limit is enforced with multiplicity (ie. two blobs with the same hash - will count twice toward the limit). - - Args: - **start** (bytes): Starting identifier range (expected smaller - than end) - **end** (bytes): Ending identifier range (expected larger - than start) - **limit** (int): Limit result (default to 1000) - - Returns: - a dict with keys: - - contents [dict]: iterable of contents in between the range. - - next (bytes): There remains content in the range - starting from this next sha1 - - """ if limit is None: raise ValueError('Development error: limit should not be None') contents = [] next_content = None for counter, content_row in enumerate( db.content_get_range(start, end, limit+1, cur)): content = dict(zip(db.content_get_metadata_keys, content_row)) if counter >= limit: # take the last commit for the next page starting from this next_content = content['sha1'] break contents.append(content) return { 'contents': contents, 'next': next_content, } - @remote_api_endpoint('content/partition') @timed @db_transaction() def content_get_partition( self, partition_id: int, nb_partitions: int, limit: int = 1000, page_token: str = None, db=None, cur=None): - """Splits contents into nb_partitions, and returns one of these based on - partition_id (which must be in [0, nb_partitions-1]) - - There is no guarantee on how the partitioning is done, or the - result order. - - Args: - partition_id (int): index of the partition to fetch - nb_partitions (int): total number of partitions to split into - limit (int): Limit result (default to 1000) - page_token (Optional[str]): opaque token used for pagination. - - Returns: - a dict with keys: - - contents (List[dict]): iterable of contents in the partition. - - **next_page_token** (Optional[str]): opaque token to be used as - `page_token` for retrieving the next page. if absent, there is - no more pages to gather. - """ if limit is None: raise ValueError('Development error: limit should not be None') (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE) if page_token: start = hash_to_bytes(page_token) if end is None: end = b'\xff'*SHA1_SIZE result = self.content_get_range(start, end, limit) result2 = { 'contents': result['contents'], 'next_page_token': None, } if result['next']: result2['next_page_token'] = hash_to_hex(result['next']) return result2 - @remote_api_endpoint('content/metadata') @timed @db_transaction(statement_timeout=500) def content_get_metadata( self, contents: List[bytes], db=None, cur=None) -> Dict[bytes, List[Dict]]: - """Retrieve content metadata in bulk - - Args: - content: iterable of content identifiers (sha1) - - Returns: - a dict with keys the content's sha1 and the associated value - either the existing content's metadata or None if the content does - not exist. - - """ result: Dict[bytes, List[Dict]] = {sha1: [] for sha1 in contents} for row in db.content_get_metadata_from_sha1s(contents, cur): content_meta = dict(zip(db.content_get_metadata_keys, row)) result[content_meta['sha1']].append(content_meta) return result - @remote_api_endpoint('content/missing') @timed @db_transaction_generator() def content_missing(self, content, key_hash='sha1', db=None, cur=None): - """List content missing from storage - - Args: - content ([dict]): iterable of dictionaries whose keys are - either 'length' or an item of - :data:`swh.model.hashutil.ALGORITHMS`; - mapped to the corresponding checksum - (or length). - - key_hash (str): name of the column to use as hash id - result (default: 'sha1') - - Returns: - iterable ([bytes]): missing content ids (as per the - key_hash column) - - Raises: - TODO: an exception when we get a hash collision. - - """ keys = db.content_hash_keys if key_hash not in keys: raise ValueError("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) if not content: return for obj in db.content_missing_from_list(content, cur): yield obj[key_hash_idx] - @remote_api_endpoint('content/missing/sha1') @timed @db_transaction_generator() 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. - - """ for obj in db.content_missing_per_sha1(contents, cur): yield obj[0] - @remote_api_endpoint('content/missing/sha1_git') @timed @db_transaction_generator() def content_missing_per_sha1_git(self, contents, db=None, cur=None): - """List content missing from storage based only on sha1_git. - - Args: - contents (Iterable): An iterable of content id (sha1_git) - - Yields: - missing contents sha1_git - """ for obj in db.content_missing_per_sha1_git(contents, cur): yield obj[0] - @remote_api_endpoint('content/skipped/missing') @timed @db_transaction_generator() def skipped_content_missing(self, contents, 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 - - """ for content in db.skipped_content_missing(contents, cur): yield dict(zip(db.content_hash_keys, content)) - @remote_api_endpoint('content/present') @timed @db_transaction() 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. - - """ if not set(content).intersection(ALGORITHMS): raise ValueError('content keys must contain at least one of: ' 'sha1, sha1_git, sha256, blake2s256') contents = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), blake2s256=content.get('blake2s256'), cur=cur) return [dict(zip(db.content_find_cols, content)) for content in contents] - @remote_api_endpoint('content/get_random') @timed @db_transaction() def content_get_random(self, db=None, cur=None): - """Finds a random content id. - - Returns: - a sha1_git - """ return db.content_get_random(cur) - @remote_api_endpoint('directory/add') @timed @process_metrics @db_transaction() def directory_add(self, directories, db=None, cur=None): - """Add directories to the storage - - Args: - directories (iterable): iterable of dictionaries representing the - individual directories to add. Each dict has the following - keys: - - - id (sha1_git): the id of the directory to add - - entries (list): list of dicts for each entry in the - directory. Each dict has the following keys: - - - name (bytes) - - type (one of 'file', 'dir', 'rev'): type of the - directory entry (file, directory, revision) - - target (sha1_git): id of the object pointed at by the - directory entry - - perms (int): entry permissions - - Returns: - Summary dict of keys with associated count as values: - - directory:add: Number of directories actually added - - """ directories = list(directories) summary = {'directory:add': 0} 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 if entry['type'] not in ('file', 'dir', 'rev'): raise ValueError( 'Entry type must be file, dir, or rev; not %s' % entry['type']) dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs, db=db, cur=cur)) if not dirs_missing: return summary if self.journal_writer: self.journal_writer.write_additions( 'directory', (dir_ for dir_ in directories if dir_['id'] in dirs_missing)) # Copy directory ids dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.mktemp('directory', cur) db.copy_to(dirs_missing_dict, 'tmp_directory', ['id'], cur) # Copy entries for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'dir_id'], cur, ) # Do the final copy db.directory_add_from_temp(cur) summary['directory:add'] = len(dirs_missing) return summary - @remote_api_endpoint('directory/missing') @timed @db_transaction_generator() 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 - - """ for obj in db.directory_missing_from_list(directories, cur): yield obj[0] - @remote_api_endpoint('directory/ls') @timed @db_transaction_generator(statement_timeout=20000) 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. - - If `recursive=True`, names in the path of a dir/file not at the - root are concatenated with a slash (`/`). - - """ 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)) - @remote_api_endpoint('directory/path') @timed @db_transaction(statement_timeout=2000) 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. - - """ res = db.directory_entry_get_by_path(directory, paths, cur) if res: return dict(zip(db.directory_ls_cols, res)) - @remote_api_endpoint('directory/get_random') @timed @db_transaction() def directory_get_random(self, db=None, cur=None): - """Finds a random directory id. - - Returns: - a sha1_git - """ return db.directory_get_random(cur) - @remote_api_endpoint('revision/add') @timed @process_metrics @db_transaction() def revision_add(self, revisions, db=None, cur=None): - """Add revisions to the storage - - Args: - revisions (Iterable[dict]): iterable of dictionaries representing - the individual revisions to add. Each dict has the following - keys: - - - **id** (:class:`sha1_git`): id of the revision to add - - **date** (:class:`dict`): date the revision was written - - **committer_date** (:class:`dict`): date the revision got - added to the origin - - **type** (one of 'git', 'tar'): type of the - revision added - - **directory** (:class:`sha1_git`): the directory the - revision points at - - **message** (:class:`bytes`): the message associated with - the revision - - **author** (:class:`Dict[str, bytes]`): dictionary with - keys: name, fullname, email - - **committer** (:class:`Dict[str, bytes]`): dictionary with - keys: name, fullname, email - - **metadata** (:class:`jsonb`): extra information as - dictionary - - **synthetic** (:class:`bool`): revision's nature (tarball, - directory creates synthetic revision`) - - **parents** (:class:`list[sha1_git]`): the parents of - this revision - - date dictionaries have the form defined in :mod:`swh.model`. - - Returns: - Summary dict of keys with associated count as values - - revision:add: New objects actually stored in db - - """ revisions = list(revisions) summary = {'revision:add': 0} revisions_missing = set(self.revision_missing( set(revision['id'] for revision in revisions), db=db, cur=cur)) if not revisions_missing: return summary db.mktemp_revision(cur) revisions_filtered = [ revision for revision in revisions if revision['id'] in revisions_missing] if self.journal_writer: self.journal_writer.write_additions('revision', revisions_filtered) revisions_filtered = map(converters.revision_to_db, revisions_filtered) 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) return {'revision:add': len(revisions_missing)} - @remote_api_endpoint('revision/missing') @timed @db_transaction_generator() def revision_missing(self, revisions, db=None, cur=None): - """List revisions missing from storage - - Args: - revisions (iterable): revision ids - - Yields: - missing revision ids - - """ if not revisions: return for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] - @remote_api_endpoint('revision') @timed @db_transaction_generator(statement_timeout=1000) 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) - - """ for line in db.revision_get_from_list(revisions, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data - @remote_api_endpoint('revision/log') @timed @db_transaction_generator(statement_timeout=2000) 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. - - """ 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 - @remote_api_endpoint('revision/shortlog') @timed @db_transaction_generator(statement_timeout=2000) 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. - - """ yield from db.revision_shortlog(revisions, limit, cur) - @remote_api_endpoint('revision/get_random') @timed @db_transaction() def revision_get_random(self, db=None, cur=None): - """Finds a random revision id. - - Returns: - a sha1_git - """ return db.revision_get_random(cur) - @remote_api_endpoint('release/add') @timed @process_metrics @db_transaction() def release_add(self, releases, db=None, cur=None): - """Add releases to the storage - - Args: - releases (Iterable[dict]): iterable of dictionaries representing - the individual releases to add. Each dict has the following - keys: - - - **id** (:class:`sha1_git`): id of the release to add - - **revision** (:class:`sha1_git`): id of the revision the - release points to - - **date** (:class:`dict`): the date the release was made - - **name** (:class:`bytes`): the name of the release - - **comment** (:class:`bytes`): the comment associated with - the release - - **author** (:class:`Dict[str, bytes]`): dictionary with - keys: name, fullname, email - - the date dictionary has the form defined in :mod:`swh.model`. - - Returns: - Summary dict of keys with associated count as values - - release:add: New objects contents actually stored in db - - """ releases = list(releases) summary = {'release:add': 0} release_ids = set(release['id'] for release in releases) releases_missing = set(self.release_missing(release_ids, db=db, cur=cur)) if not releases_missing: return summary db.mktemp_release(cur) releases_missing = list(releases_missing) releases_filtered = [ release for release in releases if release['id'] in releases_missing ] if self.journal_writer: self.journal_writer.write_additions('release', releases_filtered) releases_filtered = map(converters.release_to_db, releases_filtered) db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) return {'release:add': len(releases_missing)} - @remote_api_endpoint('release/missing') @timed @db_transaction_generator() 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 - - """ if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] - @remote_api_endpoint('release') @timed @db_transaction_generator(statement_timeout=500) 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: - dicts with the same keys as those given to `release_add` - (or ``None`` if a release does not exist) - - """ for release in db.release_get_from_list(releases, cur): data = converters.db_to_release( dict(zip(db.release_get_cols, release)) ) yield data if data['target_type'] else None - @remote_api_endpoint('release/get_random') @timed @db_transaction() def release_get_random(self, db=None, cur=None): - """Finds a random release id. - - Returns: - a sha1_git - """ return db.release_get_random(cur) - @remote_api_endpoint('snapshot/add') @timed @process_metrics @db_transaction() def snapshot_add(self, snapshots, db=None, cur=None): - """Add snapshots to the storage. - - Args: - snapshot ([dict]): the snapshots to add, containing the - following keys: - - - **id** (:class:`bytes`): id of the snapshot - - **branches** (:class:`dict`): branches the snapshot contains, - mapping the branch name (:class:`bytes`) to the branch target, - itself a :class:`dict` (or ``None`` if the branch points to an - unknown object) - - - **target_type** (:class:`str`): one of ``content``, - ``directory``, ``revision``, ``release``, - ``snapshot``, ``alias`` - - **target** (:class:`bytes`): identifier of the target - (currently a ``sha1_git`` for all object kinds, or the name - of the target branch for aliases) - - Raises: - ValueError: if the origin or visit id does not exist. - - Returns: - - Summary dict of keys with associated count as values - - snapshot:add: Count of object actually stored in db - - """ created_temp_table = False count = 0 for snapshot in snapshots: if not db.snapshot_exists(snapshot['id'], cur): if not created_temp_table: db.mktemp_snapshot_branch(cur) created_temp_table = True 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, ) if self.journal_writer: self.journal_writer.write_addition('snapshot', snapshot) db.snapshot_add(snapshot['id'], cur) count += 1 return {'snapshot:add': count} - @remote_api_endpoint('snapshot/missing') @timed @db_transaction_generator() def snapshot_missing(self, snapshots, db=None, cur=None): - """List snapshots missing from storage - - Args: - snapshots (iterable): an iterable of snapshot ids - - Yields: - missing snapshot ids - - """ for obj in db.snapshot_missing_from_list(snapshots, cur): yield obj[0] - @remote_api_endpoint('snapshot') @timed @db_transaction(statement_timeout=2000) def snapshot_get(self, snapshot_id, db=None, cur=None): - """Get the content, possibly partial, of a snapshot with the given id - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - .. warning:: At most 1000 branches contained in the snapshot will be - returned for performance reasons. In order to browse the whole - set of branches, the method :meth:`snapshot_get_branches` - should be used instead. - - Args: - snapshot_id (bytes): identifier of the snapshot - Returns: - dict: a dict with three keys: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than 1000 - branches. - """ return self.snapshot_get_branches(snapshot_id, db=db, cur=cur) - @remote_api_endpoint('snapshot/by_origin_visit') @timed @db_transaction(statement_timeout=2000) def snapshot_get_by_origin_visit(self, origin, visit, db=None, cur=None): - """Get the content, possibly partial, of a snapshot for the given origin visit - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - .. warning:: At most 1000 branches contained in the snapshot will be - returned for performance reasons. In order to browse the whole - set of branches, the method :meth:`snapshot_get_branches` - should be used instead. - - Args: - origin (int): the origin identifier - visit (int): the visit identifier - Returns: - dict: None if the snapshot does not exist; - a dict with three keys otherwise: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than 1000 - branches. - - """ snapshot_id = db.snapshot_get_by_origin_visit(origin, visit, cur) if snapshot_id: return self.snapshot_get(snapshot_id, db=db, cur=cur) return None - @remote_api_endpoint('snapshot/latest') @timed @db_transaction(statement_timeout=4000) def snapshot_get_latest(self, origin, allowed_statuses=None, db=None, cur=None): - """Get the content, possibly partial, of the latest snapshot for the - given origin, optionally only from visits that have one of the given - allowed_statuses - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - .. warning:: At most 1000 branches contained in the snapshot will be - returned for performance reasons. In order to browse the whole - set of branches, the method :meth:`snapshot_get_branches` - should be used instead. - - Args: - origin (str): the origin's URL - allowed_statuses (list of str): list of visit statuses considered - to find the latest snapshot for the visit. For instance, - ``allowed_statuses=['full']`` will only consider visits that - have successfully run to completion. - Returns: - dict: a dict with three keys: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than 1000 - branches. - """ if isinstance(origin, int): origin = self.origin_get({'id': origin}, db=db, cur=cur) if not origin: return origin = origin['url'] origin_visit = self.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=True, db=db, cur=cur) if origin_visit and origin_visit['snapshot']: snapshot = self.snapshot_get( origin_visit['snapshot'], db=db, cur=cur) if not snapshot: raise ValueError( 'last origin visit references an unknown snapshot') return snapshot - @remote_api_endpoint('snapshot/count_branches') @timed @db_transaction(statement_timeout=2000) def snapshot_count_branches(self, snapshot_id, db=None, cur=None): - """Count the number of branches in the snapshot with the given id - - Args: - snapshot_id (bytes): identifier of the snapshot - - Returns: - dict: A dict whose keys are the target types of branches and - values their corresponding amount - """ return dict([bc for bc in db.snapshot_count_branches(snapshot_id, cur)]) - @remote_api_endpoint('snapshot/get_branches') @timed @db_transaction(statement_timeout=2000) def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None, db=None, cur=None): - """Get the content, possibly partial, of a snapshot with the given id - - The branches of the snapshot are iterated in the lexicographical - order of their names. - - Args: - snapshot_id (bytes): identifier of the snapshot - branches_from (bytes): optional parameter used to skip branches - whose name is lesser than it before returning them - branches_count (int): optional parameter used to restrain - the amount of returned branches - target_types (list): optional parameter used to filter the - target types of branch to return (possible values that can be - contained in that list are `'content', 'directory', - 'revision', 'release', 'snapshot', 'alias'`) - Returns: - dict: None if the snapshot does not exist; - a dict with three keys otherwise: - * **id**: identifier of the snapshot - * **branches**: a dict of branches contained in the snapshot - whose keys are the branches' names. - * **next_branch**: the name of the first branch not returned - or :const:`None` if the snapshot has less than - `branches_count` branches after `branches_from` included. - """ if snapshot_id == EMPTY_SNAPSHOT_ID: return { 'id': snapshot_id, 'branches': {}, 'next_branch': None, } branches = {} next_branch = None fetched_branches = list(db.snapshot_get_by_id( snapshot_id, branches_from=branches_from, branches_count=branches_count+1, target_types=target_types, cur=cur, )) for branch in fetched_branches[:branches_count]: branch = dict(zip(db.snapshot_get_cols, branch)) del branch['snapshot_id'] name = branch.pop('name') if branch == {'target': None, 'target_type': None}: branch = None branches[name] = branch if len(fetched_branches) > branches_count: branch = dict(zip(db.snapshot_get_cols, fetched_branches[-1])) next_branch = branch['name'] if branches: return { 'id': snapshot_id, 'branches': branches, 'next_branch': next_branch, } return None - @remote_api_endpoint('snapshot/get_random') @timed @db_transaction() def snapshot_get_random(self, db=None, cur=None): - """Finds a random snapshot id. - - Returns: - a sha1_git - """ return db.snapshot_get_random(cur) - @remote_api_endpoint('origin/visit/add') @timed @db_transaction() def origin_visit_add(self, origin, date, type, db=None, cur=None): - """Add an origin_visit for the origin at ts with status 'ongoing'. - - Args: - origin (str): visited origin's identifier or URL - date (Union[str,datetime]): timestamp of such visit - type (str): the type of loader used for the visit (hg, git, ...) - - Returns: - dict: dictionary with keys origin and visit where: - - - origin: origin identifier - - visit: the visit identifier for the new visit occurrence - - """ origin_url = origin if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) visit_id = db.origin_visit_add(origin_url, date, type, cur) if self.journal_writer: # We can write to the journal only after inserting to the # DB, because we want the id of the visit self.journal_writer.write_addition('origin_visit', { 'origin': origin_url, 'date': date, 'type': type, 'visit': visit_id, 'status': 'ongoing', 'metadata': None, 'snapshot': None}) send_metric('origin_visit:add', count=1, method_name='origin_visit') return { 'origin': origin_url, 'visit': visit_id, } - @remote_api_endpoint('origin/visit/update') @timed @db_transaction() def origin_visit_update(self, origin, visit_id, status=None, metadata=None, snapshot=None, db=None, cur=None): - """Update an origin_visit's status. - - Args: - origin (str): visited origin's URL - visit_id: Visit's id - status: Visit's new status - metadata: Data associated to the visit - snapshot (sha1_git): identifier of the snapshot to add to - the visit - - Returns: - None - - """ if not isinstance(origin, str): raise TypeError('origin must be a string, not %r' % (origin,)) origin_url = origin visit = db.origin_visit_get(origin_url, visit_id, cur=cur) if not visit: raise ValueError('Invalid visit_id for this origin.') visit = dict(zip(db.origin_visit_get_cols, visit)) updates = {} if status and status != visit['status']: updates['status'] = status if metadata and metadata != visit['metadata']: updates['metadata'] = metadata if snapshot and snapshot != visit['snapshot']: updates['snapshot'] = snapshot if updates: if self.journal_writer: self.journal_writer.write_update('origin_visit', { **visit, **updates}) db.origin_visit_update(origin_url, visit_id, updates, cur) - @remote_api_endpoint('origin/visit/upsert') @timed @db_transaction() def origin_visit_upsert(self, visits, db=None, cur=None): - """Add a origin_visits with a specific id and with all its data. - If there is already an origin_visit with the same - `(origin_id, visit_id)`, overwrites it. - - Args: - visits: iterable of dicts with keys: - - - **origin**: dict with keys either `id` or `url` - - **visit**: origin visit id - - **date**: timestamp of such visit - - **status**: Visit's new status - - **metadata**: Data associated to the visit - - **snapshot**: identifier of the snapshot to add to - the visit - """ visits = copy.deepcopy(visits) for visit in visits: if isinstance(visit['date'], str): visit['date'] = dateutil.parser.parse(visit['date']) if not isinstance(visit['origin'], str): raise TypeError("visit['origin'] must be a string, not %r" % (visit['origin'],)) if self.journal_writer: for visit in visits: self.journal_writer.write_addition('origin_visit', visit) for visit in visits: # TODO: upsert them all in a single query db.origin_visit_upsert(**visit, cur=cur) - @remote_api_endpoint('origin/visit/get') @timed @db_transaction_generator(statement_timeout=500) 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 (str): The visited origin - last_visit: 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. - - """ for line in db.origin_visit_get_all( origin, last_visit=last_visit, limit=limit, cur=cur): data = dict(zip(db.origin_visit_get_cols, line)) yield data - @remote_api_endpoint('origin/visit/find_by_date') @timed @db_transaction(statement_timeout=500) def origin_visit_find_by_date(self, origin, visit_date, db=None, cur=None): - """Retrieves the origin visit whose date is closest to the provided - timestamp. - In case of a tie, the visit with largest id is selected. - - Args: - origin (str): The occurrence's origin (URL). - target (datetime): target timestamp - - Returns: - A visit. - - """ line = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if line: return dict(zip(db.origin_visit_get_cols, line)) - @remote_api_endpoint('origin/visit/getby') @timed @db_transaction(statement_timeout=500) 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) or None if - it does not exist - - """ ori_visit = db.origin_visit_get(origin, visit, cur) if not ori_visit: return None return dict(zip(db.origin_visit_get_cols, ori_visit)) - @remote_api_endpoint('origin/visit/get_latest') @timed @db_transaction(statement_timeout=4000) def origin_visit_get_latest( self, origin, allowed_statuses=None, require_snapshot=False, db=None, cur=None): - """Get the latest origin visit for the given origin, optionally - looking only for those with one of the given allowed_statuses - or for those with a known snapshot. - - Args: - origin (str): the origin's URL - allowed_statuses (list of str): list of visit statuses considered - to find the latest visit. For instance, - ``allowed_statuses=['full']`` will only consider visits that - have successfully run to completion. - require_snapshot (bool): If True, only a visit with a snapshot - will be returned. - - Returns: - dict: a dict with the following keys: - - - **origin**: the URL of the origin - - **visit**: origin visit id - - **type**: type of loader used for the visit - - **date**: timestamp of such visit - - **status**: Visit's new status - - **metadata**: Data associated to the visit - - **snapshot** (Optional[sha1_git]): identifier of the snapshot - associated to the visit - """ origin_visit = db.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, cur=cur) if origin_visit: return dict(zip(db.origin_visit_get_cols, origin_visit)) - @remote_api_endpoint('origin/visit/get_random') @timed @db_transaction() def origin_visit_get_random( self, type: str, db=None, cur=None) -> Optional[Dict[str, Any]]: - """Randomly select one successful origin visit with - made in the last 3 months. - - Returns: - dict representing an origin visit, in the same format as - :py:meth:`origin_visit_get`. - - """ result = db.origin_visit_get_random(type, cur) if result: return dict(zip(db.origin_visit_get_cols, result)) else: return None - @remote_api_endpoint('object/find_by_sha1_git') @timed @db_transaction(statement_timeout=2000) 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 - - """ ret = {id: [] for id in ids} for retval in db.object_find_by_sha1_git(ids, cur=cur): if retval[1]: ret[retval[0]].append(dict(zip(db.object_find_by_sha1_git_cols, retval))) return ret - @remote_api_endpoint('origin/get') @timed @db_transaction(statement_timeout=500) def origin_get(self, origins, db=None, cur=None): - """Return origins, either all identified by their ids or all - identified by tuples (type, url). - - If the url is given and the type is omitted, one of the origins with - that url is returned. - - Args: - origin: a list of dictionaries representing the individual - origins to find. - These dicts have the key url: - - - url (bytes): the url the origin points to - - Returns: - dict: the origin dictionary with the keys: - - - id: origin's id - - url: origin's url - - Raises: - ValueError: if the url or the id don't exist. - - """ if isinstance(origins, dict): # Old API return_single = True origins = [origins] elif len(origins) == 0: return [] else: return_single = False origin_urls = [origin['url'] for origin in origins] results = db.origin_get_by_url(origin_urls, cur) results = [dict(zip(db.origin_cols, result)) for result in results] if return_single: assert len(results) == 1 if results[0]['url'] is not None: return results[0] else: return None else: return [None if res['url'] is None else res for res in results] - @remote_api_endpoint('origin/get_sha1') @timed @db_transaction_generator(statement_timeout=500) def origin_get_by_sha1(self, sha1s, db=None, cur=None): - """Return origins, identified by the sha1 of their URLs. - - Args: - sha1s (list[bytes]): a list of sha1s - - Yields: - dicts containing origin information as returned - by :meth:`swh.storage.storage.Storage.origin_get`, or None if an - origin matching the sha1 is not found. - - """ for line in db.origin_get_by_sha1(sha1s, cur): if line[0] is not None: yield dict(zip(db.origin_cols, line)) else: yield None - @remote_api_endpoint('origin/get_range') @timed @db_transaction_generator() def origin_get_range(self, origin_from=1, origin_count=100, db=None, cur=None): - """Retrieve ``origin_count`` origins whose ids are greater - or equal than ``origin_from``. - - Origins are sorted by id before retrieving them. - - Args: - origin_from (int): the minimum id of origins to retrieve - origin_count (int): the maximum number of origins to retrieve - - Yields: - dicts containing origin information as returned - by :meth:`swh.storage.storage.Storage.origin_get`. - """ for origin in db.origin_get_range(origin_from, origin_count, cur): yield dict(zip(db.origin_get_range_cols, origin)) - @remote_api_endpoint('origin/list') @timed @db_transaction() def origin_list(self, page_token: Optional[str] = None, limit: int = 100, *, db=None, cur=None) -> dict: - """Returns the list of origins - - Args: - page_token: opaque token used for pagination. - limit: the maximum number of results to return - - Returns: - dict: dict with the following keys: - - **next_page_token** (str, optional): opaque token to be used as - `page_token` for retrieving the next page. if absent, there is - no more pages to gather. - - **origins** (List[dict]): list of origins, as returned by - `origin_get`. - """ page_token = page_token or '0' if not isinstance(page_token, str): raise TypeError('page_token must be a string.') origin_from = int(page_token) result: Dict[str, Any] = { 'origins': [ dict(zip(db.origin_get_range_cols, origin)) for origin in db.origin_get_range(origin_from, limit, cur) ], } assert len(result['origins']) <= limit if len(result['origins']) == limit: result['next_page_token'] = str(result['origins'][limit-1]['id']+1) for origin in result['origins']: del origin['id'] return result - @remote_api_endpoint('origin/search') @timed @db_transaction_generator() def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=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 (str): the string pattern to search for in origin urls - offset (int): number of found origins to skip before returning - results - limit (int): the maximum number of found origins to return - regexp (bool): if True, consider the provided pattern as a regular - expression and return origins whose urls match it - with_visit (bool): if True, filter out origins with no visit - - Yields: - dicts containing origin information as returned - by :meth:`swh.storage.storage.Storage.origin_get`. - """ for origin in db.origin_search(url_pattern, offset, limit, regexp, with_visit, cur): yield dict(zip(db.origin_cols, origin)) - @remote_api_endpoint('origin/count') @timed @db_transaction() def origin_count(self, url_pattern, regexp=False, with_visit=False, db=None, cur=None): - """Count origins whose urls contain a provided string pattern - or match a provided regular expression. - The pattern search in origin urls is performed in a case insensitive - way. - - Args: - url_pattern (str): the string pattern to search for in origin urls - regexp (bool): if True, consider the provided pattern as a regular - expression and return origins whose urls match it - with_visit (bool): if True, filter out origins with no visit - - Returns: - int: The number of origins matching the search criterion. - """ return db.origin_count(url_pattern, regexp, with_visit, cur) - @remote_api_endpoint('origin/add_multi') @timed @db_transaction() 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: given origins as dict updated with their id - - """ origins = copy.deepcopy(list(origins)) for origin in origins: self.origin_add_one(origin, db=db, cur=cur) send_metric('origin:add', count=len(origins), method_name='origin_add') return origins - @remote_api_endpoint('origin/add') @timed @db_transaction() 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. - - """ origin_row = list(db.origin_get_by_url([origin['url']], cur))[0] origin_url = dict(zip(db.origin_cols, origin_row))['url'] if origin_url: return origin_url if self.journal_writer: self.journal_writer.write_addition('origin', origin) origins = db.origin_add(origin['url'], cur) send_metric('origin:add', count=len(origins), method_name='origin_add') return origins @db_transaction(statement_timeout=500) 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 db.stat_counters()} @db_transaction() def refresh_stat_counters(self, db=None, cur=None): - """Recomputes the statistics for `stat_counters`.""" keys = [ 'content', 'directory', 'directory_entry_dir', 'directory_entry_file', 'directory_entry_rev', 'origin', 'origin_visit', 'person', 'release', 'revision', 'revision_history', 'skipped_content', 'snapshot'] for key in keys: cur.execute('select * from swh_update_counter(%s)', (key,)) - @remote_api_endpoint('origin/metadata/add') @timed @db_transaction() def origin_metadata_add(self, origin_url, ts, provider, tool, metadata, db=None, cur=None): - """ Add an origin_metadata for the origin at ts with provenance and - metadata. - - Args: - origin_url (str): the origin url for which the metadata is added - ts (datetime): timestamp of the found metadata - provider (int): the provider of metadata (ex:'hal') - tool (int): tool used to extract metadata - metadata (jsonb): the metadata retrieved at the time and location - """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) db.origin_metadata_add(origin_url, ts, provider, tool, metadata, cur) send_metric( 'origin_metadata:add', count=1, method_name='origin_metadata_add') - @remote_api_endpoint('origin/metadata/get') @timed @db_transaction_generator(statement_timeout=500) def origin_metadata_get_by(self, origin_url, provider_type=None, db=None, cur=None): - """Retrieve list of all origin_metadata entries for the origin_id - - Args: - origin_url (str): the origin's URL - provider_type (str): (optional) type of provider - - Returns: - list of dicts: the origin_metadata dictionary with the keys: - - - origin_id (int): origin's id - - discovery_date (datetime): timestamp of discovery - - tool_id (int): metadata's extracting tool - - metadata (jsonb) - - provider_id (int): metadata's provider - - provider_name (str) - - provider_type (str) - - provider_url (str) - - """ for line in db.origin_metadata_get_by(origin_url, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) - @remote_api_endpoint('tool/add') @timed @db_transaction() 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: - :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.mktemp_tool(cur) db.copy_to(tools, 'tmp_tool', ['name', 'version', 'configuration'], cur) tools = db.tool_add_from_temp(cur) results = [dict(zip(db.tool_cols, line)) for line in tools] send_metric('tool:add', count=len(results), method_name='tool_add') return results - @remote_api_endpoint('tool/data') @timed @db_transaction(statement_timeout=500) 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. - - """ 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(db.tool_cols, idx)) - @remote_api_endpoint('provider/add') @timed @db_transaction() def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata, db=None, cur=None): - """Add a metadata provider. - - Args: - provider_name (str): Its name - provider_type (str): Its type (eg. `'deposit-client'`) - provider_url (str): Its URL - metadata: JSON-encodable object - - Returns: - int: an identifier of the provider - """ result = db.metadata_provider_add(provider_name, provider_type, provider_url, metadata, cur) send_metric( 'metadata_provider:add', count=1, method_name='metadata_provider') return result - @remote_api_endpoint('provider/get') @timed @db_transaction() def metadata_provider_get(self, provider_id, db=None, cur=None): - """Get a metadata provider - - Args: - provider_id: Its identifier, as given by `metadata_provider_add`. - - Returns: - dict: same as `metadata_provider_add`; - or None if it does not exist. - """ result = db.metadata_provider_get(provider_id) if not result: return None return dict(zip(db.metadata_provider_cols, result)) - @remote_api_endpoint('provider/getby') @timed @db_transaction() def metadata_provider_get_by(self, provider, db=None, cur=None): - """Get a metadata provider - - Args: - provider (dict): A dictionary with keys: - * provider_name: Its name - * provider_url: Its URL - - Returns: - dict: same as `metadata_provider_add`; - or None if it does not exist. - """ result = db.metadata_provider_get_by(provider['provider_name'], provider['provider_url']) if not result: return None return dict(zip(db.metadata_provider_cols, result)) - @remote_api_endpoint('algos/diff_directories') @timed 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) - @remote_api_endpoint('algos/diff_revisions') @timed 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) - @remote_api_endpoint('algos/diff_revision') @timed 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/test_storage.py b/swh/storage/tests/test_storage.py index e7f854ee..6dd7ced9 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,3750 +1,3780 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy from contextlib import contextmanager import datetime +import inspect import itertools import math import queue import random import threading from collections import defaultdict from datetime import timedelta from unittest.mock import Mock import psycopg2 import pytest from hypothesis import given, strategies, settings, HealthCheck from typing import ClassVar, Optional from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.model.hypothesis_strategies import objects from swh.storage import HashCollision from swh.storage.converters import origin_url_to_sha1 as sha1 +from swh.storage.interface import StorageInterface from .storage_data import data @contextmanager def db_transaction(storage): with storage.db() as db: with db.transaction() as cur: yield db, cur def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ('date', 'committer_date'): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity def transform_entries(dir_, *, prefix=b''): for ent in dir_['entries']: yield { 'dir_id': dir_['id'], 'type': ent['type'], 'target': ent['target'], 'name': prefix + ent['name'], 'perms': ent['perms'], 'status': None, 'sha1': None, 'sha1_git': None, 'sha256': None, 'length': None, } def cmpdir(directory): return (directory['type'], directory['dir_id']) def short_revision(revision): return [revision['id'], revision['parents']] def assert_contents_ok(expected_contents, actual_contents, keys_to_check={'sha1', 'data'}): """Assert that a given list of contents matches on a given set of keys. """ for k in keys_to_check: expected_list = set([c.get(k) for c in expected_contents]) actual_list = set([c.get(k) for c in actual_contents]) assert actual_list == expected_list, k class TestStorage: """Main class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ maxDiff = None # type: ClassVar[Optional[int]] + def test_types(self, swh_storage): + """Checks all methods of StorageInterface are implemented by this + backend, and that they have the same signature.""" + # Create an instance of the protocol (which cannot be instantiated + # directly, so this creates a subclass, then instantiates it) + interface = type('_', (StorageInterface,), {})() + + assert 'content_add' in dir(interface) + + missing_methods = [] + + for meth_name in dir(interface): + if meth_name.startswith('_'): + continue + interface_meth = getattr(interface, meth_name) + try: + concrete_meth = getattr(swh_storage, meth_name) + except AttributeError: + missing_methods.append(meth_name) + continue + + expected_signature = inspect.signature(interface_meth) + actual_signature = inspect.signature(concrete_meth) + + assert expected_signature == actual_signature, meth_name + + assert missing_methods == [] + def test_check_config(self, swh_storage): assert swh_storage.check_config(check_write=True) assert swh_storage.check_config(check_write=False) def test_content_add(self, swh_storage): cont = data.cont insertion_start_time = datetime.datetime.now(tz=datetime.timezone.utc) actual_result = swh_storage.content_add([cont]) insertion_end_time = datetime.datetime.now(tz=datetime.timezone.utc) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 } assert list(swh_storage.content_get([cont['sha1']])) == \ [{'sha1': cont['sha1'], 'data': cont['data']}] expected_cont = data.cont del expected_cont['data'] journal_objects = list(swh_storage.journal_writer.objects) for (obj_type, obj) in journal_objects: assert insertion_start_time <= obj['ctime'] assert obj['ctime'] <= insertion_end_time del obj['ctime'] assert journal_objects == [('content', expected_cont)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['content'] == 1 def test_content_add_from_generator(self, swh_storage): def _cnt_gen(): yield data.cont actual_result = swh_storage.content_add(_cnt_gen()) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont['length'], 'skipped_content:add': 0 } swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['content'] == 1 def test_content_add_validation(self, swh_storage): cont = data.cont with pytest.raises(ValueError, match='status'): swh_storage.content_add([{**cont, 'status': 'foobar'}]) with pytest.raises(ValueError, match="(?i)length"): swh_storage.content_add([{**cont, 'length': -2}]) with pytest.raises((ValueError, psycopg2.IntegrityError), match='reason') as cm: swh_storage.content_add([{**cont, 'status': 'absent'}]) if type(cm.value) == psycopg2.IntegrityError: assert cm.exception.pgcode == \ psycopg2.errorcodes.NOT_NULL_VIOLATION with pytest.raises( ValueError, match="^Must not provide a reason if content is not absent.$"): swh_storage.content_add([{**cont, 'reason': 'foobar'}]) def test_content_get_missing(self, swh_storage): cont = data.cont swh_storage.content_add([cont]) # Query a single missing content results = list(swh_storage.content_get( [data.cont2['sha1']])) assert results == [None] # Check content_get does not abort after finding a missing content results = list(swh_storage.content_get( [data.cont['sha1'], data.cont2['sha1']])) assert results == [{'sha1': cont['sha1'], 'data': cont['data']}, None] # Check content_get does not discard found countent when it finds # a missing content. results = list(swh_storage.content_get( [data.cont2['sha1'], data.cont['sha1']])) assert results == [None, {'sha1': cont['sha1'], 'data': cont['data']}] def test_content_add_different_input(self, swh_storage): cont = data.cont cont2 = data.cont2 actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { 'content:add': 2, 'content:add:bytes': cont['length'] + cont2['length'], 'skipped_content:add': 0 } def test_content_add_twice(self, swh_storage): actual_result = swh_storage.content_add([data.cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont['length'], 'skipped_content:add': 0 } assert len(swh_storage.journal_writer.objects) == 1 actual_result = swh_storage.content_add([data.cont, data.cont2]) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont2['length'], 'skipped_content:add': 0 } assert len(swh_storage.journal_writer.objects) == 2 assert len(swh_storage.content_find(data.cont)) == 1 assert len(swh_storage.content_find(data.cont2)) == 1 def test_content_add_collision(self, swh_storage): cont1 = data.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b['sha256']) sha256_array[0] += 1 cont1b['sha256'] = bytes(sha256_array) with pytest.raises(HashCollision) as cm: swh_storage.content_add([cont1, cont1b]) assert cm.value.args[0] in ['sha1', 'sha1_git', 'blake2s256'] def test_content_update(self, swh_storage): swh_storage.journal_writer = None # TODO, not supported cont = copy.deepcopy(data.cont) swh_storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') swh_storage.content_update([cont], keys=['sha1_git']) results = swh_storage.content_get_metadata([cont['sha1']]) del cont['data'] assert results == {cont['sha1']: [cont]} def test_content_add_metadata(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { 'content:add': 1, 'skipped_content:add': 0 } expected_cont = cont.copy() del expected_cont['ctime'] assert swh_storage.content_get_metadata([cont['sha1']]) == { cont['sha1']: [expected_cont] } assert list(swh_storage.journal_writer.objects) == [('content', cont)] def test_content_add_metadata_different_input(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() cont2 = data.cont2 del cont2['data'] cont2['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { 'content:add': 2, 'skipped_content:add': 0 } def test_content_add_metadata_collision(self, swh_storage): cont1 = data.cont del cont1['data'] cont1['ctime'] = datetime.datetime.now() # 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 pytest.raises(HashCollision) as cm: swh_storage.content_add_metadata([cont1, cont1b]) assert cm.value.args[0] in ['sha1', 'sha1_git', 'blake2s256'] def test_skipped_content_add(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2['blake2s256'] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert len(missing) == 2 actual_result = swh_storage.content_add([cont, cont, cont2]) assert actual_result == { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, } missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [] @pytest.mark.property_based @settings(deadline=None) # this test is very slow @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing(self, swh_storage, algos): algos |= {'sha1'} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_cont.copy() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == \ set(missing_per_hash['sha1']) for hash in algos: assert set(swh_storage.content_missing( test_contents, key_hash=hash)) == set(missing_per_hash[hash]) @pytest.mark.property_based @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing_unknown_algo(self, swh_storage, algos): algos |= {'sha1'} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_cont.copy() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_content['nonexisting_algo'] = b'\x00' test_contents.append(test_content) assert set( swh_storage.content_missing(test_contents)) == set( missing_per_hash['sha1']) for hash in algos: assert set(swh_storage.content_missing( test_contents, key_hash=hash)) == set( missing_per_hash[hash]) def test_content_missing_per_sha1(self, swh_storage): # given cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) # when gen = swh_storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then assert list(gen) == [missing_cont['sha1']] def test_content_missing_per_sha1_git(self, swh_storage): cont = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont, cont2]) contents = [cont['sha1_git'], cont2['sha1_git'], missing_cont['sha1_git']] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont['sha1_git']] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [c for c in swh_contents if c['status'] != 'absent'] actual_contents = [] for i in range(16): actual_result = swh_storage.content_get_partition(i, 16) assert actual_result['next_page_token'] is None actual_contents.extend(actual_result['contents']) assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents""" expected_contents = [c for c in swh_contents if c['status'] != 'absent'] actual_result = swh_storage.content_get_partition(0, 1) assert actual_result['next_page_token'] is None actual_contents = actual_result['contents'] assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_content_get_partition_empty(self, swh_storage, swh_contents): """content_get_partition when at least one of the partitions is empty""" expected_contents = {cont['sha1'] for cont in swh_contents if cont['status'] != 'absent'} # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1) seen_sha1s = [] for i in range(nb_partitions): actual_result = swh_storage.content_get_partition( i, nb_partitions, limit=len(swh_contents)+1) for cont in actual_result['contents']: seen_sha1s.append(cont['sha1']) # Limit is higher than the max number of results assert actual_result['next_page_token'] is None assert set(seen_sha1s) == expected_contents def test_content_get_partition_limit_none(self, swh_storage): """content_get_partition call with wrong limit input should fail""" with pytest.raises(ValueError) as e: swh_storage.content_get_partition(1, 16, limit=None) assert e.value.args == ('Development error: limit should not be None',) def test_generate_content_get_partition_pagination( self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [c for c in swh_contents if c['status'] != 'absent'] # retrieve contents actual_contents = [] for i in range(4): page_token = None while True: actual_result = swh_storage.content_get_partition( i, 4, limit=3, page_token=page_token) actual_contents.extend(actual_result['contents']) page_token = actual_result['next_page_token'] if page_token is None: break assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_content_get_metadata(self, swh_storage): cont1 = data.cont cont2 = data.cont2 swh_storage.content_add([cont1, cont2]) actual_md = swh_storage.content_get_metadata( [cont1['sha1'], cont2['sha1']]) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') assert actual_md[cont1['sha1']] == [cont1] assert actual_md[cont2['sha1']] == [cont2] assert len(actual_md.keys()) == 2 def test_content_get_metadata_missing_sha1(self, swh_storage): cont1 = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get_metadata( [missing_cont['sha1']]) assert actual_contents == {missing_cont['sha1']: []} def test_content_get_random(self, swh_storage): swh_storage.content_add([data.cont, data.cont2, data.cont3]) assert swh_storage.content_get_random() in { data.cont['sha1_git'], data.cont2['sha1_git'], data.cont3['sha1_git']} def test_directory_add(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert [data.dir['id']] == init_missing actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) == \ [('directory', data.dir)] actual_data = list(swh_storage.directory_ls(data.dir['id'])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) after_missing = list(swh_storage.directory_missing([data.dir['id']])) assert after_missing == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['directory'] == 1 def test_directory_add_from_generator(self, swh_storage): def _dir_gen(): yield data.dir actual_result = swh_storage.directory_add(directories=_dir_gen()) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) == \ [('directory', data.dir)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['directory'] == 1 def test_directory_add_validation(self, swh_storage): dir_ = copy.deepcopy(data.dir) dir_['entries'][0]['type'] = 'foobar' with pytest.raises(ValueError, match='type.*foobar'): swh_storage.directory_add([dir_]) dir_ = copy.deepcopy(data.dir) del dir_['entries'][0]['target'] with pytest.raises((TypeError, psycopg2.IntegrityError), match='target') as cm: swh_storage.directory_add([dir_]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION def test_directory_add_twice(self, swh_storage): actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('directory', data.dir)] actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 0} assert list(swh_storage.journal_writer.objects) \ == [('directory', data.dir)] def test_directory_get_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert init_missing == [data.dir['id']] actual_result = swh_storage.directory_add( [data.dir, data.dir2, data.dir3]) assert actual_result == {'directory:add': 3} assert list(swh_storage.journal_writer.objects) == [ ('directory', data.dir), ('directory', data.dir2), ('directory', data.dir3)] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls( data.dir['id'], recursive=True)) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls( data.dir2['id'], recursive=True)) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # be both those of the directory and of the subdir actual_data = list(swh_storage.directory_ls( data.dir3['id'], recursive=True)) expected_data = list(itertools.chain( transform_entries(data.dir3), transform_entries(data.dir, prefix=b'subdir/'))) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) def test_directory_get_non_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert init_missing == [data.dir['id']] actual_result = swh_storage.directory_add( [data.dir, data.dir2, data.dir3]) assert actual_result == {'directory:add': 3} assert list(swh_storage.journal_writer.objects) == [ ('directory', data.dir), ('directory', data.dir2), ('directory', data.dir3)] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(data.dir['id'])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory contaiining a single file actual_data = list(swh_storage.directory_ls(data.dir2['id'])) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(swh_storage.directory_ls(data.dir3['id'])) expected_data = list(transform_entries(data.dir3)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) def test_directory_entry_get_by_path(self, swh_storage): # given init_missing = list(swh_storage.directory_missing([data.dir3['id']])) assert [data.dir3['id']] == init_missing actual_result = swh_storage.directory_add([data.dir3, data.dir4]) assert actual_result == {'directory:add': 2} expected_entries = [ { 'dir_id': data.dir3['id'], 'name': b'foo', 'type': 'file', 'target': data.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, { 'dir_id': data.dir3['id'], 'name': b'subdir', 'type': 'dir', 'target': data.dir['id'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.directory, 'length': None, }, { 'dir_id': data.dir3['id'], 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, ] # when (all must be found here) for entry, expected_entry in zip( data.dir3['entries'], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir3['id'], [entry['name']]) assert actual_entry == expected_entry # same, but deeper for entry, expected_entry in zip( data.dir3['entries'], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir4['id'], [b'subdir1', entry['name']]) expected_entry = expected_entry.copy() expected_entry['name'] = b'subdir1/' + expected_entry['name'] assert actual_entry == expected_entry # when (nothing should be found here since data.dir is not persisted.) for entry in data.dir['entries']: actual_entry = swh_storage.directory_entry_get_by_path( data.dir['id'], [entry['name']]) assert actual_entry is None def test_directory_get_random(self, swh_storage): swh_storage.directory_add([data.dir, data.dir2, data.dir3]) assert swh_storage.directory_get_random() in \ {data.dir['id'], data.dir2['id'], data.dir3['id']} def test_revision_add(self, swh_storage): init_missing = swh_storage.revision_missing([data.revision['id']]) assert list(init_missing) == [data.revision['id']] actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 1} end_missing = swh_storage.revision_missing([data.revision['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision)] # already there so nothing added actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['revision'] == 1 def test_revision_add_from_generator(self, swh_storage): def _rev_gen(): yield data.revision actual_result = swh_storage.revision_add(_rev_gen()) assert actual_result == {'revision:add': 1} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['revision'] == 1 def test_revision_add_validation(self, swh_storage): rev = copy.deepcopy(data.revision) rev['date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev['committer_date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev['type'] = 'foobar' with pytest.raises((ValueError, psycopg2.DataError), match='(?i)type') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == \ psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_revision_add_twice(self, swh_storage): actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision)] actual_result = swh_storage.revision_add( [data.revision, data.revision2]) assert actual_result == {'revision:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision), ('revision', data.revision2)] def test_revision_add_name_clash(self, swh_storage): revision1 = data.revision revision2 = data.revision2 revision1['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe', 'email': b'john.doe@example.com' } revision2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.revision_add([revision1, revision2]) assert actual_result == {'revision:add': 2} def test_revision_log(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_log( [data.revision4['id']])) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] assert len(actual_results) == 2 # rev4 -child-> rev3 assert actual_results[0] == normalize_entity(data.revision4) assert actual_results[1] == normalize_entity(data.revision3) assert list(swh_storage.journal_writer.objects) == [ ('revision', data.revision3), ('revision', data.revision4)] def test_revision_log_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_log( [data.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] assert len(actual_results) == 1 assert actual_results[0] == data.revision4 def test_revision_log_unknown_revision(self, swh_storage): rev_log = list(swh_storage.revision_log([data.revision['id']])) assert rev_log == [] def test_revision_shortlog(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']])) assert len(actual_results) == 2 # rev4 -child-> rev3 assert list(actual_results[0]) == short_revision(data.revision4) assert list(actual_results[1]) == short_revision(data.revision3) def test_revision_shortlog_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']], 1)) assert len(actual_results) == 1 assert list(actual_results[0]) == short_revision(data.revision4) def test_revision_get(self, swh_storage): swh_storage.revision_add([data.revision]) actual_revisions = list(swh_storage.revision_get( [data.revision['id'], data.revision2['id']])) # when if 'id' in actual_revisions[0]['author']: del actual_revisions[0]['author']['id'] # hack: ids are generated if 'id' in actual_revisions[0]['committer']: del actual_revisions[0]['committer']['id'] assert len(actual_revisions) == 2 assert actual_revisions[0] == normalize_entity(data.revision) assert actual_revisions[1] is None def test_revision_get_no_parents(self, swh_storage): swh_storage.revision_add([data.revision3]) get = list(swh_storage.revision_get([data.revision3['id']])) assert len(get) == 1 assert get[0]['parents'] == [] # no parents on this one def test_revision_get_random(self, swh_storage): swh_storage.revision_add( [data.revision, data.revision2, data.revision3]) assert swh_storage.revision_get_random() in \ {data.revision['id'], data.revision2['id'], data.revision3['id']} def test_release_add(self, swh_storage): init_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert [data.release['id'], data.release2['id']] == list(init_missing) actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 2} end_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) == [ ('release', data.release), ('release', data.release2)] # already present so nothing added actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['release'] == 2 def test_release_add_from_generator(self, swh_storage): def _rel_gen(): yield data.release yield data.release2 actual_result = swh_storage.release_add(_rel_gen()) assert actual_result == {'release:add': 2} assert list(swh_storage.journal_writer.objects) == [ ('release', data.release), ('release', data.release2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['release'] == 2 def test_release_add_no_author_date(self, swh_storage): release = data.release release['author'] = None release['date'] = None actual_result = swh_storage.release_add([release]) assert actual_result == {'release:add': 1} end_missing = swh_storage.release_missing([data.release['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) \ == [('release', release)] def test_release_add_validation(self, swh_storage): rel = copy.deepcopy(data.release) rel['date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rel = copy.deepcopy(data.release) rel['author'] = None with pytest.raises((ValueError, psycopg2.IntegrityError), match='date') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.CHECK_VIOLATION def test_release_add_twice(self, swh_storage): actual_result = swh_storage.release_add([data.release]) assert actual_result == {'release:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('release', data.release)] actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('release', data.release), ('release', data.release2)] def test_release_add_name_clash(self, swh_storage): release1 = data.release.copy() release2 = data.release2.copy() release1['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe', 'email': b'john.doe@example.com' } release2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.release_add([release1, release2]) assert actual_result == {'release:add': 2} def test_release_get(self, swh_storage): # given swh_storage.release_add([data.release, data.release2]) # when actual_releases = list(swh_storage.release_get([data.release['id'], data.release2['id']])) # then for actual_release in actual_releases: if 'id' in actual_release['author']: del actual_release['author']['id'] # hack: ids are generated assert [ normalize_entity(data.release), normalize_entity(data.release2)] \ == [actual_releases[0], actual_releases[1]] unknown_releases = \ list(swh_storage.release_get([data.release3['id']])) assert unknown_releases[0] is None def test_release_get_random(self, swh_storage): swh_storage.release_add([data.release, data.release2, data.release3]) assert swh_storage.release_get_random() in \ {data.release['id'], data.release2['id'], data.release3['id']} def test_origin_add_one(self, swh_storage): origin0 = swh_storage.origin_get(data.origin) assert origin0 is None id = swh_storage.origin_add_one(data.origin) actual_origin = swh_storage.origin_get({'url': data.origin['url']}) assert actual_origin['url'] == data.origin['url'] id2 = swh_storage.origin_add_one(data.origin) assert id == id2 def test_origin_add(self, swh_storage): origin0 = swh_storage.origin_get([data.origin])[0] assert origin0 is None origin1, origin2 = swh_storage.origin_add([data.origin, data.origin2]) actual_origin = swh_storage.origin_get([{ 'url': data.origin['url'], }])[0] assert actual_origin['url'] == origin1['url'] actual_origin2 = swh_storage.origin_get([{ 'url': data.origin2['url'], }])[0] assert actual_origin2['url'] == origin2['url'] if 'id' in actual_origin: del actual_origin['id'] del actual_origin2['id'] assert list(swh_storage.journal_writer.objects) \ == [('origin', actual_origin), ('origin', actual_origin2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['origin'] == 2 def test_origin_add_from_generator(self, swh_storage): def _ori_gen(): yield data.origin yield data.origin2 origin1, origin2 = swh_storage.origin_add(_ori_gen()) actual_origin = swh_storage.origin_get([{ 'url': data.origin['url'], }])[0] assert actual_origin['url'] == origin1['url'] actual_origin2 = swh_storage.origin_get([{ 'url': data.origin2['url'], }])[0] assert actual_origin2['url'] == origin2['url'] if 'id' in actual_origin: del actual_origin['id'] del actual_origin2['id'] assert list(swh_storage.journal_writer.objects) \ == [('origin', actual_origin), ('origin', actual_origin2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['origin'] == 2 def test_origin_add_twice(self, swh_storage): add1 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin', data.origin2)] add2 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin', data.origin2)] assert add1 == add2 def test_origin_add_validation(self, swh_storage): with pytest.raises((TypeError, KeyError), match='url'): swh_storage.origin_add([{'type': 'git'}]) def test_origin_get_legacy(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get( {'url': data.origin['url']}) assert actual_origin0['url'] == data.origin['url'] def test_origin_get(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get( [{'url': data.origin['url']}]) assert len(actual_origin0) == 1 assert actual_origin0[0]['url'] == data.origin['url'] def _generate_random_visits(self, nb_visits=100, start=0, end=7): """Generate random visits within the last 2 months (to avoid computations) """ visits = [] today = datetime.datetime.now(tz=datetime.timezone.utc) for weeks in range(nb_visits, 0, -1): hours = random.randint(0, 24) minutes = random.randint(0, 60) seconds = random.randint(0, 60) days = random.randint(0, 28) weeks = random.randint(start, end) date_visit = today - timedelta( weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days) visits.append(date_visit) return visits def test_origin_visit_get_random(self, swh_storage): swh_storage.origin_add(data.origins) # Add some random visits within the selection range visits = self._generate_random_visits() visit_type = 'git' # Add visits to those origins for origin in data.origins: for date_visit in visits: visit = swh_storage.origin_visit_add( origin['url'], date=date_visit, type=visit_type) swh_storage.origin_visit_update( origin['url'], visit_id=visit['visit'], status='full') swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats['origin'] == len(data.origins) assert stats['origin_visit'] == len(data.origins) * len(visits) random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit assert random_origin_visit['origin'] is not None original_urls = [o['url'] for o in data.origins] assert random_origin_visit['origin'] in original_urls def test_origin_visit_get_random_nothing_found(self, swh_storage): swh_storage.origin_add(data.origins) visit_type = 'hg' # Add some visits outside of the random generation selection so nothing # will be found by the random selection visits = self._generate_random_visits(nb_visits=3, start=13, end=24) for origin in data.origins: for date_visit in visits: visit = swh_storage.origin_visit_add( origin['url'], date=date_visit, type=visit_type) swh_storage.origin_visit_update( origin['url'], visit_id=visit['visit'], status='full') random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit is None def test_origin_get_by_sha1(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) origins = list(swh_storage.origin_get_by_sha1([ sha1(data.origin['url']) ])) assert len(origins) == 1 assert origins[0]['url'] == data.origin['url'] def test_origin_get_by_sha1_not_found(self, swh_storage): assert swh_storage.origin_get(data.origin) is None origins = list(swh_storage.origin_get_by_sha1([ sha1(data.origin['url']) ])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage): found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 0 found_origins = list(swh_storage.origin_search(data.origin['url'], regexp=True)) assert len(found_origins) == 0 swh_storage.origin_add_one(data.origin) origin_data = { 'url': data.origin['url']} found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data found_origins = list(swh_storage.origin_search( '.' + data.origin['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data swh_storage.origin_add_one(data.origin2) origin2_data = {'url': data.origin2['url']} found_origins = list(swh_storage.origin_search(data.origin2['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data found_origins = list(swh_storage.origin_search( '.' + data.origin2['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data def test_origin_search_no_regexp(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/')) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_substring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_fullstring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('.*/.*', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_visit_add(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when date_visit = datetime.datetime.now(datetime.timezone.utc) origin_visit1 = swh_storage.origin_visit_add( origin_url, type=data.type_visit1, date=date_visit) actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } in actual_origin_visits origin_visit = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.objects) assert ('origin', data.origin2) in objects assert ('origin_visit', origin_visit) in objects def test_origin_visit_get__unknown_origin(self, swh_storage): assert [] == list(swh_storage.origin_visit_get('foo')) def test_origin_visit_add_default_type(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when date_visit = datetime.datetime.now(datetime.timezone.utc) date_visit2 = date_visit + datetime.timedelta(minutes=1) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2, ) # then assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) expected_visits = [ { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, ] for visit in expected_visits: assert visit in actual_origin_visits objects = list(swh_storage.journal_writer.objects) assert ('origin', data.origin2) in objects for visit in expected_visits: assert ('origin_visit', visit) in objects def test_origin_visit_add_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin2) with pytest.raises((TypeError, psycopg2.ProgrammingError)) as cm: swh_storage.origin_visit_add(origin_url, date=[b'foo']) if type(cm.value) == psycopg2.ProgrammingError: assert cm.value.pgcode \ == psycopg2.errorcodes.UNDEFINED_FUNCTION def test_origin_visit_update(self, swh_storage): # given swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] date_visit = datetime.datetime.now(datetime.timezone.utc) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1, ) date_visit2 = date_visit + datetime.timedelta(minutes=1) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) swh_storage.origin_add_one(data.origin2) origin_url2 = data.origin2['url'] origin_visit3 = swh_storage.origin_visit_add( origin_url2, date=date_visit2, type=data.type_visit3 ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) swh_storage.origin_visit_update( origin_url2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) expected_visits = [{ 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] for visit in expected_visits: assert visit in actual_origin_visits actual_origin_visits_bis = list(swh_storage.origin_visit_get( origin_url, limit=1)) assert actual_origin_visits_bis == [ { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }] actual_origin_visits_ter = list(swh_storage.origin_visit_get( origin_url, last_visit=origin_visit1['visit'])) assert actual_origin_visits_ter == [ { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] actual_origin_visits2 = list(swh_storage.origin_visit_get( origin_url2)) assert actual_origin_visits2 == [ { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, }] data1 = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data3 = { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': None, } data5 = { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.objects) assert ('origin', data.origin) in objects assert ('origin', data.origin2) in objects assert ('origin_visit', data1) in objects assert ('origin_visit', data2) in objects assert ('origin_visit', data3) in objects assert ('origin_visit', data4) in objects assert ('origin_visit', data5) in objects def test_origin_visit_update_validation(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2, ) with pytest.raises((ValueError, psycopg2.DataError), match='status') as cm: swh_storage.origin_visit_update( origin_url, visit['visit'], status='foobar') if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == \ psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_origin_visit_find_by_date(self, swh_storage): # given swh_storage.origin_add_one(data.origin) swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit3, type=data.type_visit2, ) origin_visit3 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit3, ) # Simple case visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit3) assert visit['visit'] == origin_visit2['visit'] # There are two visits at the same date, the latest must be returned visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit2) assert visit['visit'] == origin_visit3['visit'] def test_origin_visit_find_by_date__unknown_origin(self, swh_storage): swh_storage.origin_visit_find_by_date('foo', data.date_visit2) def test_origin_visit_update_missing_snapshot(self, swh_storage): # given swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1, ) # when swh_storage.origin_visit_update( origin_url, origin_visit['visit'], snapshot=data.snapshot['id']) # then actual_origin_visit = swh_storage.origin_visit_get_by( origin_url, origin_visit['visit']) assert actual_origin_visit['snapshot'] == data.snapshot['id'] # when swh_storage.snapshot_add([data.snapshot]) assert actual_origin_visit['snapshot'] == data.snapshot['id'] def test_origin_visit_get_by(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin_url = data.origin['url'] origin2_url = data.origin2['url'] origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], snapshot=data.snapshot['id']) # Add some other {origin, visit} entries swh_storage.origin_visit_add( origin_url, date=data.date_visit3, type=data.type_visit3, ) swh_storage.origin_visit_add( origin2_url, date=data.date_visit3, type=data.type_visit3, ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_url, 'visit': origin_visit1['visit'], 'date': data.date_visit2, 'type': data.type_visit2, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': data.snapshot['id'], }) # when actual_origin_visit1 = swh_storage.origin_visit_get_by( origin_url, origin_visit1['visit']) # then assert actual_origin_visit1 == expected_origin_visit def test_origin_visit_get_by__unknown_origin(self, swh_storage): assert swh_storage.origin_visit_get_by('foo', 10) is None def test_origin_visit_upsert_new(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when swh_storage.origin_visit_upsert([ { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': '2018-01-01 23:00:00+00', 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ]) # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ] data1 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.objects) == [ ('origin', data.origin2), ('origin_visit', data1), ('origin_visit', data2)] def test_origin_visit_upsert_existing(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1, ) swh_storage.origin_visit_upsert([{ 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }]) # then assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }] data1 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.objects) == [ ('origin', data.origin2), ('origin_visit', data1), ('origin_visit', data2)] def test_origin_visit_get_by_no_result(self, swh_storage): swh_storage.origin_add([data.origin]) actual_origin_visit = swh_storage.origin_visit_get_by( data.origin['url'], 999) assert actual_origin_visit is None def test_origin_visit_get_latest(self, swh_storage): swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit3_id = origin_visit3['visit'] origin_visit1 = swh_storage.origin_visit_get_by(origin_url, visit1_id) origin_visit2 = swh_storage.origin_visit_get_by(origin_url, visit2_id) origin_visit3 = swh_storage.origin_visit_get_by(origin_url, visit3_id) # Two visits, both with no snapshot assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) assert swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) is None # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**origin_visit1, 'snapshot': data.complete_snapshot['id']} \ == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no visit # returned assert swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**origin_visit2, 'snapshot': data.empty_snapshot['id']} == \ swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Check that the status filter is still working assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full'], require_snapshot=True) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest(origin_url) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) def test_person_fullname_unicity(self, swh_storage): # given (person injection through revisions for example) revision = data.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(data.revision2) revision2['committer'] = dict(revision['committer']) revision2['committer']['email'] = None revision2['committer']['name'] = None swh_storage.revision_add([revision]) swh_storage.revision_add([revision2]) # when getting added revisions revisions = list( swh_storage.revision_get([revision['id'], revision2['id']])) # then # check committers are the same assert revisions[0]['committer'] == revisions[1]['committer'] def test_snapshot_add_get_empty(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.empty_snapshot['id']) by_id = swh_storage.snapshot_get(data.empty_snapshot['id']) assert by_id == {**data.empty_snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.empty_snapshot, 'next_branch': None} data1 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.empty_snapshot['id'], } assert list(swh_storage.journal_writer.objects) == \ [('origin', data.origin), ('origin_visit', data1), ('snapshot', data.empty_snapshot), ('origin_visit', data2)] def test_snapshot_add_get_complete(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.complete_snapshot['id']) assert actual_result == {'snapshot:add': 1} by_id = swh_storage.snapshot_get(data.complete_snapshot['id']) assert by_id == {**data.complete_snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.complete_snapshot, 'next_branch': None} def test_snapshot_add_many(self, swh_storage): actual_result = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result == {'snapshot:add': 2} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['snapshot'] == 2 def test_snapshot_add_many_from_generator(self, swh_storage): def _snp_gen(): yield data.snapshot yield data.complete_snapshot actual_result = swh_storage.snapshot_add(_snp_gen()) assert actual_result == {'snapshot:add': 2} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['snapshot'] == 2 def test_snapshot_add_many_incremental(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} actual_result2 = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result2 == {'snapshot:add': 1} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) def test_snapshot_add_twice(self, swh_storage): actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('snapshot', data.empty_snapshot)] actual_result = swh_storage.snapshot_add([data.snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('snapshot', data.empty_snapshot), ('snapshot', data.snapshot)] def test_snapshot_add_validation(self, swh_storage): snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target_type': 'revision'} with pytest.raises(KeyError, match='target'): swh_storage.snapshot_add([snap]) snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target': b'\x42'*20} with pytest.raises(KeyError, match='target_type'): swh_storage.snapshot_add([snap]) def test_snapshot_add_count_branches(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} snp_id = data.complete_snapshot['id'] snp_size = swh_storage.snapshot_count_branches(snp_id) expected_snp_size = { 'alias': 1, 'content': 1, 'directory': 2, 'release': 1, 'revision': 1, 'snapshot': 1, None: 1 } assert snp_size == expected_snp_size def test_snapshot_add_get_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b'release') rel_idx = branch_names.index(b'release') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[rel_idx:] }, 'next_branch': None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { branch_names[0]: branches[branch_names[0]], }, 'next_branch': b'content', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b'directory', branches_count=3) dir_idx = branch_names.index(b'directory') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[dir_idx:dir_idx + 3] }, 'next_branch': branch_names[dir_idx + 3], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.complete_snapshot['id']) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['release', 'revision']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] in ['release', 'revision'] }, 'next_branch': None, } assert snapshot == expected_snapshot snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['alias']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] == 'alias' }, 'next_branch': None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory2', b'release') }, 'next_branch': None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { b'directory': branches[b'directory'] }, 'next_branch': b'directory2', } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=2) expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory', b'directory2') }, 'next_branch': b'release', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2', branches_count=1) dir_idx = branch_names.index(b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { branch_names[dir_idx]: branches[branch_names[dir_idx]], }, 'next_branch': b'release', } assert snapshot == expected_snapshot def test_snapshot_add_get(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.snapshot['id']) by_id = swh_storage.snapshot_get(data.snapshot['id']) assert by_id == {**data.snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.snapshot, 'next_branch': None} origin_visit_info = swh_storage.origin_visit_get_by( origin_url, visit_id) assert origin_visit_info['snapshot'] == data.snapshot['id'] def test_snapshot_add_nonexistent_visit(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) visit_id = 54164461156 swh_storage.journal_writer.objects[:] = [] swh_storage.snapshot_add([data.snapshot]) with pytest.raises(ValueError): swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.snapshot['id']) assert list(swh_storage.journal_writer.objects) == [ ('snapshot', data.snapshot)] def test_snapshot_add_twice__by_origin_visit(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.snapshot['id']) by_ov1 = swh_storage.snapshot_get_by_origin_visit( origin_url, visit1_id) assert by_ov1 == {**data.snapshot, 'next_branch': None} origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.snapshot['id']) by_ov2 = swh_storage.snapshot_get_by_origin_visit( origin_url, visit2_id) assert by_ov2 == {**data.snapshot, 'next_branch': None} data1 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } data3 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin_visit', data1), ('snapshot', data.snapshot), ('origin_visit', data2), ('origin_visit', data3), ('origin_visit', data4)] def test_snapshot_get_latest(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit3, ) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add snapshot to visit1, latest snapshot = visit 1 snapshot swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update(origin_url, visit1_id, status='full') assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**data.empty_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Check that the status filter is still working assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_latest__missing_snapshot(self, swh_storage): # Origin does not exist origin_url = data.origin['url'] assert swh_storage.snapshot_get_latest(origin_url) is None swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add unknown snapshot to visit1, check that the inconsistency is # detected swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url) # Status filter: both visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']), # Actually add the snapshot and check status filter again swh_storage.snapshot_add([data.complete_snapshot]) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Add unknown snapshot to visit2 and check that the inconsistency # is detected swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.snapshot['id']) with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url) # Actually add that snapshot and check that the new one is returned swh_storage.snapshot_add([data.snapshot]) assert{**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_random(self, swh_storage): swh_storage.snapshot_add( [data.snapshot, data.empty_snapshot, data.complete_snapshot]) assert swh_storage.snapshot_get_random() in { data.snapshot['id'], data.empty_snapshot['id'], data.complete_snapshot['id']} def test_snapshot_missing(self, swh_storage): snap = data.snapshot missing_snap = data.empty_snapshot snapshots = [snap['id'], missing_snap['id']] swh_storage.snapshot_add([snap]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snap['id']] def test_stat_counters(self, swh_storage): expected_keys = ['content', 'directory', 'origin', 'revision'] # Initially, all counters are 0 swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: assert counters[key] == 0 # Add a content. Only the content counter should increase. swh_storage.content_add([data.cont]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: if key != 'content': assert counters[key] == 0 assert counters['content'] == 1 # Add other objects. Check their counter increased as well. swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin=data.origin2['url'], date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( data.origin2['url'], origin_visit1['visit'], snapshot=data.snapshot['id']) swh_storage.directory_add([data.dir]) swh_storage.revision_add([data.revision]) swh_storage.release_add([data.release]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert counters['content'] == 1 assert counters['directory'] == 1 assert counters['snapshot'] == 1 assert counters['origin'] == 1 assert counters['origin_visit'] == 1 assert counters['revision'] == 1 assert counters['release'] == 1 assert counters['snapshot'] == 1 if 'person' in counters: assert counters['person'] == 3 def test_content_find_ctime(self, swh_storage): cont = data.cont.copy() del cont['data'] now = datetime.datetime.now(tz=datetime.timezone.utc) cont['ctime'] = now swh_storage.content_add_metadata([cont]) actually_present = swh_storage.content_find({'sha1': cont['sha1']}) # check ctime up to one second dt = actually_present[0]['ctime'] - now assert abs(dt.total_seconds()) <= 1 del actually_present[0]['ctime'] assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } def test_content_find_with_present_content(self, swh_storage): # 1. with something to find cont = data.cont swh_storage.content_add([cont, data.cont2]) actually_present = swh_storage.content_find( {'sha1': cont['sha1']} ) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 2. with something to find actually_present = swh_storage.content_find( {'sha1_git': cont['sha1_git']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 3. with something to find actually_present = swh_storage.content_find( {'sha256': cont['sha256']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 4. with something to find actually_present = swh_storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } def test_content_find_with_non_present_content(self, swh_storage): # 1. with something that does not exist missing_cont = data.missing_cont actually_present = swh_storage.content_find( {'sha1': missing_cont['sha1']}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {'sha1_git': missing_cont['sha1_git']}) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find( {'sha256': missing_cont['sha256']}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) # Inject the data swh_storage.content_add([cont1, duplicate_cont]) finder = {'blake2s256': duplicate_cont['blake2s256'], 'sha256': duplicate_cont['sha256']} actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result def test_content_find_with_duplicate_sha256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 for hashalgo in ('sha1', 'sha1_git', 'blake2s256'): value = bytearray(duplicate_cont[hashalgo]) value[0] += 1 duplicate_cont[hashalgo] = bytes(value) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'sha256': duplicate_cont['sha256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 2 cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] assert expected_result == sorted(actual_result, key=lambda x: x['sha1']) # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 1 actual_result[0].pop('ctime') expected_result = [duplicate_cont] assert actual_result[0] == duplicate_cont def test_content_find_with_duplicate_blake2s256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) sha256_array = bytearray(duplicate_cont['sha256']) sha256_array[0] += 1 duplicate_cont['sha256'] = bytes(sha256_array) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) actual_result[0].pop('ctime') expected_result = [ duplicate_cont ] assert expected_result == actual_result def test_content_find_bad_input(self, swh_storage): # 1. with bad input with pytest.raises(ValueError): swh_storage.content_find({}) # empty is bad # 2. with bad input with pytest.raises(ValueError): swh_storage.content_find( {'unknown-sha1': 'something'}) # not the right key def test_object_find_by_sha1_git(self, swh_storage): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } swh_storage.content_add([data.cont]) sha1_gits.append(data.cont['sha1_git']) expected[data.cont['sha1_git']] = [{ 'sha1_git': data.cont['sha1_git'], 'type': 'content', }] swh_storage.directory_add([data.dir]) sha1_gits.append(data.dir['id']) expected[data.dir['id']] = [{ 'sha1_git': data.dir['id'], 'type': 'directory', }] swh_storage.revision_add([data.revision]) sha1_gits.append(data.revision['id']) expected[data.revision['id']] = [{ 'sha1_git': data.revision['id'], 'type': 'revision', }] swh_storage.release_add([data.release]) sha1_gits.append(data.release['id']) expected[data.release['id']] = [{ 'sha1_git': data.release['id'], 'type': 'release', }] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_tool_add(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None # does not exist # add it actual_tools = swh_storage.tool_add([tool]) assert len(actual_tools) == 1 actual_tool = actual_tools[0] assert actual_tool is not None # now it exists new_id = actual_tool.pop('id') assert actual_tool == tool actual_tools2 = swh_storage.tool_add([tool]) actual_tool2 = actual_tools2[0] assert actual_tool2 is not None # now it exists new_id2 = actual_tool2.pop('id') assert new_id == new_id2 assert actual_tool == actual_tool2 def test_tool_add_multiple(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(swh_storage.tool_add([tool])) assert len(actual_tools) == 1 new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = swh_storage.tool_add(new_tools) assert len(actual_tools) == 2 # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') assert _id is not None assert tool in new_tools def test_tool_get_missing(self, swh_storage): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get_missing_context(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } expected_tool = swh_storage.tool_add([tool])[0] # when actual_tool = swh_storage.tool_get(tool) # then assert expected_tool == actual_tool def test_metadata_provider_get(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get(6459456445615) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get(provider_id) expected_provider = { 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] } # then del actual_provider['id'] assert actual_provider, expected_provider def test_metadata_provider_get_by(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # then assert provider_id, actual_provider['id'] def test_origin_metadata_add(self, swh_storage): # given origin = data.origin swh_storage.origin_add([origin])[0] tools = swh_storage.tool_add([data.metadata_tool]) tool = tools[0] swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # when adding for the same origin 2 metadatas n_om = len(list(swh_storage.origin_metadata_get_by(origin['url']))) swh_storage.origin_metadata_add( origin['url'], data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin['url'], '2015-01-01 23:00:00+00', provider['id'], tool['id'], data.origin_metadata2['metadata']) n_actual_om = len(list( swh_storage.origin_metadata_get_by(origin['url']))) # then assert n_actual_om == n_om + 2 def test_origin_metadata_get(self, swh_storage): # given origin_url = data.origin['url'] origin_url2 = data.origin2['url'] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) swh_storage.metadata_provider_add(data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( origin_url, data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin_url2, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) swh_storage.origin_metadata_add( origin_url, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) all_metadatas = list(sorted(swh_storage.origin_metadata_get_by( origin_url), key=lambda x: x['discovery_date'])) metadatas_for_origin2 = list(swh_storage.origin_metadata_get_by( origin_url2)) expected_results = [{ 'origin_url': origin_url, 'discovery_date': datetime.datetime( 2015, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }, { 'origin_url': origin_url, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }] # then assert len(all_metadatas) == 2 assert len(metadatas_for_origin2) == 1 assert all_metadatas == expected_results def test_metadata_provider_add(self, swh_storage): provider = { 'provider_name': 'swMATH', 'provider_type': 'registry', 'provider_url': 'http://www.swmath.org/', 'metadata': { 'email': 'contact@swmath.org', 'license': 'All rights reserved' } } provider['id'] = provider_id = swh_storage.metadata_provider_add( **provider) assert provider == swh_storage.metadata_provider_get_by( {'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/'}) assert provider == swh_storage.metadata_provider_get(provider_id) def test_origin_metadata_get_by_provider_type(self, swh_storage): # given origin_url = data.origin['url'] origin_url2 = data.origin2['url'] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) provider1_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider1 = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert provider1 == swh_storage.metadata_provider_get(provider1_id) provider2_id = swh_storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = swh_storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) assert provider2 == swh_storage.metadata_provider_get(provider2_id) # using the only tool now inserted in the data.sql, but for this # provider should be a crawler tool (not yet implemented) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( origin_url, data.origin_metadata['discovery_date'], provider1['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin_url2, data.origin_metadata2['discovery_date'], provider2['id'], tool['id'], data.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(swh_storage.origin_metadata_get_by( origin_url2, provider_type)) for item in m_by_provider: if 'id' in item: del item['id'] expected_results = [{ 'origin_url': origin_url2, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider2['id'], 'provider_name': 'swMATH', 'provider_type': provider_type, 'provider_url': 'http://www.swmath.org/', 'tool_id': tool['id'] }] # then assert len(m_by_provider) == 1 assert m_by_provider == expected_results class TestStorageGeneratedData: def test_generate_content_get(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c['status'] != 'absent'] # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents_with_data] # retrieve contents actual_contents = list(swh_storage.content_get(get_sha1s)) assert None not in actual_contents assert_contents_ok(contents_with_data, actual_contents) def test_generate_content_get_metadata(self, swh_storage, swh_contents): # input the list of sha1s we want from storage expected_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = [c['sha1'] for c in expected_contents] # retrieve contents meta_contents = swh_storage.content_get_metadata(get_sha1s) assert len(list(meta_contents)) == len(get_sha1s) actual_contents = [] for contents in meta_contents.values(): actual_contents.extend(contents) keys_to_check = {'length', 'status', 'sha1', 'sha1_git', 'sha256', 'blake2s256'} assert_contents_ok(expected_contents, actual_contents, keys_to_check=keys_to_check) def test_generate_content_get_range(self, swh_storage, swh_contents): """content_get_range returns complete range""" present_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[2] end = get_sha1s[-2] actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_full(self, swh_storage, swh_contents): """content_get_range for a full range returns all available contents""" present_contents = [c for c in swh_contents if c['status'] != 'absent'] start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_empty(self, swh_storage, swh_contents): """content_get_range for an empty range returns nothing""" start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(end, start) assert actual_result['next'] is None assert len(actual_result['contents']) == 0 def test_generate_content_get_range_limit_none(self, swh_storage): """content_get_range call with wrong limit input should fail""" with pytest.raises(ValueError) as e: swh_storage.content_get_range(start=None, end=None, limit=None) assert e.value.args == ('Development error: limit should not be None',) def test_generate_content_get_range_no_limit( self, swh_storage, swh_contents): """content_get_range returns contents within range provided""" # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = swh_storage.content_get_range(start, end) actual_contents = actual_result['contents'] assert actual_result['next'] is None assert len(actual_contents) == len(get_sha1s) expected_contents = [c for c in swh_contents if c['status'] != 'absent'] assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_generate_content_get_range_limit(self, swh_storage, swh_contents): """content_get_range paginates results if limit exceeded""" contents_map = {c['sha1']: c for c in swh_contents} # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to n-1 results limited_results = len(get_sha1s) - 1 actual_result = swh_storage.content_get_range( start, end, limit=limited_results) actual_contents = actual_result['contents'] assert actual_result['next'] == get_sha1s[-1] assert len(actual_contents) == limited_results expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] assert_contents_ok( expected_contents, actual_contents, ['sha1']) # retrieve next part actual_results2 = swh_storage.content_get_range(start=end, end=end) assert actual_results2['next'] is None actual_contents2 = actual_results2['contents'] assert len(actual_contents2) == 1 assert_contents_ok( [contents_map[get_sha1s[-1]]], actual_contents2, ['sha1']) def test_origin_get_range_from_zero(self, swh_storage, swh_origins): actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=0)) assert len(actual_origins) == 0 actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=1)) assert len(actual_origins) == 1 assert actual_origins[0]['id'] == 1 assert actual_origins[0]['url'] == swh_origins[0]['url'] @pytest.mark.parametrize('origin_from,origin_count', [ (1, 1), (1, 10), (1, 20), (1, 101), (11, 0), (11, 10), (91, 11)]) def test_origin_get_range( self, swh_storage, swh_origins, origin_from, origin_count): actual_origins = list( swh_storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) origins_with_id = list(enumerate(swh_origins, start=1)) expected_origins = [ { 'url': origin['url'], 'id': origin_id, } for (origin_id, origin) in origins_with_id[origin_from-1:origin_from+origin_count-1] ] assert actual_origins == expected_origins @pytest.mark.parametrize('limit', [1, 7, 10, 100, 1000]) def test_origin_list(self, swh_storage, swh_origins, limit): returned_origins = [] page_token = None i = 0 while True: result = swh_storage.origin_list( page_token=page_token, limit=limit) assert len(result['origins']) <= limit returned_origins.extend( origin['url'] for origin in result['origins']) i += 1 page_token = result.get('next_page_token') if page_token is None: assert i*limit >= len(swh_origins) break else: assert len(result['origins']) == limit expected_origins = [origin['url'] for origin in swh_origins] assert sorted(returned_origins) == sorted(expected_origins) ORIGINS = [ 'https://github.com/user1/repo1', 'https://github.com/user2/repo1', 'https://github.com/user3/repo1', 'https://gitlab.com/user1/repo1', 'https://gitlab.com/user2/repo1', 'https://forge.softwareheritage.org/source/repo1', ] def test_origin_count(self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) assert swh_storage.origin_count('github') == 3 assert swh_storage.origin_count('gitlab') == 2 assert swh_storage.origin_count('.*user.*', regexp=True) == 5 assert swh_storage.origin_count('.*user.*', regexp=False) == 0 assert swh_storage.origin_count('.*user1.*', regexp=True) == 2 assert swh_storage.origin_count('.*user1.*', regexp=False) == 0 def test_origin_count_with_visit_no_visits(self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) # none of them have visits, so with_visit=True => 0 assert swh_storage.origin_count('github', with_visit=True) == 0 assert swh_storage.origin_count('gitlab', with_visit=True) == 0 assert swh_storage.origin_count('.*user.*', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('.*user.*', regexp=False, with_visit=True) == 0 assert swh_storage.origin_count('.*user1.*', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('.*user1.*', regexp=False, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_no_snapshot( self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) swh_storage.origin_visit_add( origin='https://github.com/user1/repo1', date=now, type='git') assert swh_storage.origin_count('github', with_visit=False) == 3 # it has a visit, but no snapshot, so with_visit=True => 0 assert swh_storage.origin_count('github', with_visit=True) == 0 assert swh_storage.origin_count('gitlab', with_visit=False) == 2 # these gitlab origins have no visit assert swh_storage.origin_count('gitlab', with_visit=True) == 0 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=False) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('github', regexp=True, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_and_snapshot( self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) swh_storage.snapshot_add([data.snapshot]) visit = swh_storage.origin_visit_add( origin='https://github.com/user1/repo1', date=now, type='git') swh_storage.origin_visit_update( origin='https://github.com/user1/repo1', visit_id=visit['visit'], snapshot=data.snapshot['id']) assert swh_storage.origin_count('github', with_visit=False) == 3 # github/user1 has a visit and a snapshot, so with_visit=True => 1 assert swh_storage.origin_count('github', with_visit=True) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=False) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=True) == 1 assert swh_storage.origin_count('github', regexp=True, with_visit=True) == 1 @settings(suppress_health_check=[HealthCheck.too_slow]) @given(strategies.lists(objects(), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: obj = obj.to_dict() if obj_type == 'origin_visit': origin = obj.pop('origin') swh_storage.origin_add_one({'url': origin}) if 'visit' in obj: del obj['visit'] swh_storage.origin_visit_add( origin, obj['date'], obj['type']) else: method = getattr(swh_storage, obj_type + '_add') try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self, swh_storage): swh_storage.objstorage.add = Mock( side_effect=Exception('mocked broken objstorage') ) with pytest.raises(Exception) as e: swh_storage.content_add([data.cont]) assert e.value.args == ('mocked broken objstorage',) missing = list(swh_storage.content_missing([data.cont])) assert missing == [data.cont['sha1']] @pytest.mark.db class TestStorageRaceConditions: @pytest.mark.xfail def test_content_add_race(self, swh_storage): results = queue.Queue() def thread(): try: with db_transaction(swh_storage) as (db, cur): ret = swh_storage.content_add([data.cont], db=db, cur=cur) results.put((threading.get_ident(), 'data', ret)) except Exception as e: results.put((threading.get_ident(), 'exc', e)) t1 = threading.Thread(target=thread) t2 = threading.Thread(target=thread) t1.start() # this avoids the race condition # import time # time.sleep(1) t2.start() t1.join() t2.join() r1 = results.get(block=False) r2 = results.get(block=False) with pytest.raises(queue.Empty): results.get(block=False) assert r1[0] != r2[0] assert r1[1] == 'data', 'Got exception %r in Thread%s' % (r1[2], r1[0]) assert r2[1] == 'data', 'Got exception %r in Thread%s' % (r2[2], r2[0]) @pytest.mark.db class TestPgStorage: """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update_with_new_cols(self, swh_storage): swh_storage.journal_writer = None # TODO, not supported with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(data.cont2) swh_storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' swh_storage.content_update([cont], keys=['test', 'test2']) with db_transaction(swh_storage) as (_, cur): cur.execute( '''SELECT sha1, sha1_git, sha256, length, status, test, test2 FROM content WHERE sha1 = %s''', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2']) with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content drop column test, drop column test2""") def test_content_add_db(self, swh_storage): cont = data.cont actual_result = swh_storage.content_add([cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] in swh_storage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') expected_cont = cont.copy() del expected_cont['data'] journal_objects = list(swh_storage.journal_writer.objects) for (obj_type, obj) in journal_objects: del obj['ctime'] assert journal_objects == [('content', expected_cont)] def test_content_add_metadata_db(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { 'content:add': 1, 'skipped_content:add': 0 } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] not in swh_storage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') assert list(swh_storage.journal_writer.objects) == [('content', cont)] def test_skipped_content_add_db(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2['blake2s256'] = None actual_result = swh_storage.content_add([cont, cont, cont2]) assert actual_result == { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, } with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') dbdata = cur.fetchall() assert len(dbdata) == 2 assert dbdata[0] == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') assert dbdata[1] == (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long')