diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 5a6b7c83..c4b180bc 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1867 +1,1870 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import defaultdict import copy from concurrent.futures import ThreadPoolExecutor import datetime import itertools import json import warnings import dateutil.parser import psycopg2 import psycopg2.pool from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageDBError from .algos import diff from .journal_writer import get_journal_writer from swh.model.hashutil import ALGORITHMS, hash_to_bytes from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 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: 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() @db_transaction() def check_config(self, *, check_write, db, cur): """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]) def _filter_new_content(self, content, db, cur): content_by_status = defaultdict(list) for d in content: if 'status' not in d: d['status'] = 'visible' if 'length' not in d: d['length'] = -1 content_by_status[d['status']].append(d) content_with_data = content_by_status['visible'] content_without_data = content_by_status['absent'] missing_content = set(self.content_missing(content_with_data, 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): 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: 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) @db_transaction() def content_add(self, content, db, cur): """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 if self.journal_writer: for item in content: if 'data' in item: item = item.copy() del item['data'] self.journal_writer.write_addition('content', item) (content_with_data, content_without_data, summary) = \ self._filter_new_content(content, db, cur) 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 @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.') 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) @db_transaction() def content_add_metadata(self, content, db, cur): """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 """ if self.journal_writer: for item in content: assert 'data' not in content self.journal_writer.write_addition('content', item) (content_with_data, content_without_data, summary) = \ self._filter_new_content(content, db, cur) self._content_add_metadata( db, cur, content_with_data, content_without_data) return summary 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} @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, } @db_transaction_generator(statement_timeout=500) def content_get_metadata(self, content, db=None, cur=None): """Retrieve content metadata in bulk Args: content: iterable of content identifiers (sha1) Returns: an iterable with content metadata corresponding to the given ids """ for metadata in db.content_get_metadata_from_sha1s(content, cur): yield dict(zip(db.content_get_metadata_keys, metadata)) @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] @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] @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)) @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] @db_transaction() def directory_add(self, directories, db, cur): """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 """ summary = {'directory:add': 0} if self.journal_writer: self.journal_writer.write_additions('directory', directories) dirs = set() dir_entries = { 'file': defaultdict(list), 'dir': defaultdict(list), 'rev': defaultdict(list), } for cur_dir in directories: dir_id = cur_dir['id'] dirs.add(dir_id) for src_entry in cur_dir['entries']: entry = src_entry.copy() entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs, db=db, cur=cur)) if not dirs_missing: return summary # 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 @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] @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)) @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)) @db_transaction() def revision_add(self, revisions, db, cur): """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 """ summary = {'revision:add': 0} if self.journal_writer: self.journal_writer.write_additions('revision', revisions) 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 = ( converters.revision_to_db(revision) for revision in revisions if revision['id'] in revisions_missing) parents_filtered = [] db.copy_to( revisions_filtered, 'tmp_revision', db.revision_add_cols, cur, lambda rev: parents_filtered.extend(rev['parents'])) db.revision_add_from_temp(cur) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) return {'revision:add': len(revisions_missing)} @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] @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 @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 @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) @db_transaction() def release_add(self, releases, db, cur): """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 """ summary = {'release:add': 0} if self.journal_writer: self.journal_writer.write_additions('release', releases) 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 = ( converters.release_to_db(release) for release in releases if release['id'] in releases_missing ) db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) return {'release:add': len(releases_missing)} @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] @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 @db_transaction() def snapshot_add(self, snapshots, origin=None, visit=None, 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) origin (int): legacy argument for backward compatibility visit (int): legacy argument for backward compatibility 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 """ if origin: if not visit: raise TypeError( 'snapshot_add expects one argument (or, as a legacy ' 'behavior, three arguments), not two') if isinstance(snapshots, int): # Called by legacy code that uses the new api/client.py (origin_id, visit_id, snapshots) = \ (snapshots, origin, [visit]) else: # Called by legacy code that uses the old api/client.py origin_id = origin visit_id = visit snapshots = [snapshots] else: # Called by new code that uses the new api/client.py origin_id = visit_id = None 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 if visit_id: # Legacy API, there can be only one snapshot self.origin_visit_update( origin_id, visit_id, snapshot=snapshots[0]['id'], db=db, cur=cur) return {'snapshot:add': count} @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) @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 @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 (Union[str,int]): the origin's URL or identifier allowed_statuses (list of str): list of visit statuses considered to find the latest snapshot for the visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. Returns: dict: a 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)['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 @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)]) @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 @db_transaction() def origin_visit_add(self, origin, date=None, type=None, db=None, cur=None, *, ts=None): """Add an origin_visit for the origin at ts with status 'ongoing'. For backward compatibility, `type` is optional and defaults to the origin's type. Args: origin (Union[int,str]): visited origin's identifier or URL date: 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 """ if ts is None: if date is None: raise TypeError('origin_visit_add expected 2 arguments.') else: assert date is None warnings.warn("argument 'ts' of origin_visit_add was renamed " "to 'date' in v0.0.109.", DeprecationWarning) date = ts if isinstance(origin, str): origin = self.origin_get({'url': origin}, db=db, cur=cur) origin_id = origin['id'] else: origin = self.origin_get({'id': origin}, db=db, cur=cur) origin_id = origin['id'] if isinstance(date, str): date = dateutil.parser.parse(date) if type is None: type = origin['type'] visit_id = db.origin_visit_add(origin_id, 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 del origin['id'] self.journal_writer.write_addition('origin_visit', { 'origin': origin, 'date': date, 'type': type, 'visit': visit_id, 'status': 'ongoing', 'metadata': None, 'snapshot': None}) return { 'origin': origin_id, 'visit': visit_id, } @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 (Union[int,str]): visited origin's identifier or 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 isinstance(origin, str): origin_id = self.origin_get({'url': origin}, db=db, cur=cur)['id'] else: origin_id = origin visit = db.origin_visit_get(origin_id, 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: origin = self.origin_get( [{'id': origin_id}], db=db, cur=cur)[0] del origin['id'] self.journal_writer.write_update('origin_visit', { **visit, **updates, 'origin': origin}) db.origin_visit_update(origin_id, visit_id, updates, cur) @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: Visited Origin id visit: origin visit id date: timestamp of such visit status: Visit's new status metadata: Data associated to the visit snapshot (sha1_git): 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 self.journal_writer: for visit in visits: visit = visit.copy() origin = self.origin_get( [{'id': visit['origin']}], db=db, cur=cur)[0] visit['origin'] = origin if visit.get('type') is None: visit['type'] = origin['type'] del visit['origin']['id'] 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) @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 (int): The occurrence's origin (identifier). 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 @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 """ if isinstance(origin, str): origin = self.origin_get({'url': origin}, db=db, cur=cur)['id'] 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)) @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 = self.origin_get({'url': origin}, db=db, cur=cur)['id'] 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)) @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 - id: the id of the object found - object_id: the numeric id of the 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 origin_keys = ['id', 'type', 'url'] @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 either the key url (and optionally type): - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to or the id: - id: the origin id Returns: dict: the origin dictionary with the keys: - id: origin's id - type: origin's type - url: origin's url Raises: ValueError: if the keys does not match (url and type) nor id. """ if isinstance(origins, dict): # Old API return_single = True origins = [origins] elif len(origins) == 0: return [] else: return_single = False origin_ids = [origin.get('id') for origin in origins] origin_types_and_urls = [(origin.get('type'), origin.get('url')) for origin in origins] if any(origin_ids): # Lookup per ID if all(origin_ids): results = db.origin_get(origin_ids, cur) else: raise ValueError( 'Either all origins or none at all should have an "id".') elif any(url for (type_, url) in origin_types_and_urls): # Lookup per type + URL if all(url for (type_, url) in origin_types_and_urls): results = db.origin_get_with(origin_types_and_urls, cur) else: raise ValueError( 'Either all origins or none at all should have ' 'an "url" key.') else: # unsupported lookup raise ValueError('Origin must have either id or url.') results = [dict(zip(self.origin_keys, result)) for result in results] if return_single: assert len(results) == 1 if results[0]['id'] is not None: return results[0] else: return None else: return [None if res['id'] is None else res for res in results] @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(self.origin_keys, origin)) @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(self.origin_keys, origin)) @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) @db_transaction_generator(statement_timeout=500) def person_get(self, person, db=None, cur=None): """Return the persons identified by their ids. Args: person: array of ids. Returns: The array of persons corresponding of the ids. """ for person in db.person_get(person): yield dict(zip(db.person_get_cols, person)) @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(origins) for origin in origins: origin['id'] = self.origin_add_one(origin, db=db, cur=cur) return origins @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_id = list(db.origin_get_with( [(origin['type'], origin['url'])], cur))[0][0] if origin_id: return origin_id if self.journal_writer: self.journal_writer.write_addition('origin', origin) return db.origin_add(origin['type'], origin['url'], cur) @db_transaction() def fetch_history_start(self, origin_id, db=None, cur=None): """Add an entry for origin origin_id in fetch_history. Returns the id of the added fetch_history entry """ + if isinstance(origin_id, str): + origin_id = \ + self.origin_get([{'url': origin_id}], db=db, cur=cur)[0]['id'] fetch_history = { 'origin': origin_id, 'date': datetime.datetime.now(tz=datetime.timezone.utc), } return db.create_fetch_history(fetch_history, cur) @db_transaction() def fetch_history_end(self, fetch_history_id, data, db=None, cur=None): """Close the fetch_history entry with id `fetch_history_id`, replacing its data with `data`. """ now = datetime.datetime.now(tz=datetime.timezone.utc) fetch_history = db.get_fetch_history(fetch_history_id, cur) if not fetch_history: raise ValueError('No fetch_history with id %d' % fetch_history_id) fetch_history['duration'] = now - fetch_history['date'] fetch_history.update(data) db.update_fetch_history(fetch_history, cur) @db_transaction() def fetch_history_get(self, fetch_history_id, db=None, cur=None): """Get the fetch_history entry with id `fetch_history_id`. """ return db.get_fetch_history(fetch_history_id, cur) @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,)) @db_transaction() def origin_metadata_add(self, origin_id, ts, provider, tool, metadata, db=None, cur=None): """ Add an origin_metadata for the origin at ts with provenance and metadata. Args: origin_id (int): the origin's id for which the metadata is added ts (datetime): timestamp of the found metadata provider (int): the provider of metadata (ex:'hal') tool (int): tool used to extract metadata metadata (jsonb): the metadata retrieved at the time and location Returns: id (int): the origin_metadata unique id """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) return db.origin_metadata_add(origin_id, ts, provider, tool, metadata, cur) @db_transaction_generator(statement_timeout=500) def origin_metadata_get_by(self, origin_id, provider_type=None, db=None, cur=None): """Retrieve list of all origin_metadata entries for the origin_id Args: origin_id (int): the unique origin identifier provider_type (str): (optional) type of provider Returns: list of dicts: the origin_metadata dictionary with the keys: - 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_id, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) @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) return [dict(zip(db.tool_cols, line)) for line in tools] @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)) @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 """ return db.metadata_provider_add(provider_name, provider_type, provider_url, metadata, cur) @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)) @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)) def diff_directories(self, from_dir, to_dir, track_renaming=False): """Compute the list of file changes introduced between two arbitrary directories (insertion / deletion / modification / renaming of files). Args: from_dir (bytes): identifier of the directory to compare from to_dir (bytes): identifier of the directory to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_directories(self, from_dir, to_dir, track_renaming) def diff_revisions(self, from_rev, to_rev, track_renaming=False): """Compute the list of file changes introduced between two arbitrary revisions (insertion / deletion / modification / renaming of files). Args: from_rev (bytes): identifier of the revision to compare from to_rev (bytes): identifier of the revision to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_revisions(self, from_rev, to_rev, track_renaming) def diff_revision(self, revision, track_renaming=False): """Compute the list of file changes introduced by a specific revision (insertion / deletion / modification / renaming of files) by comparing it against its first parent. Args: revision (bytes): identifier of the revision from which to compute the list of files changes track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_revision(self, revision, track_renaming) diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index 0bbb2a83..fd12487b 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,4005 +1,4010 @@ # 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 copy import datetime import itertools import random import unittest from collections import defaultdict from unittest.mock import Mock, patch import pytest from hypothesis import given, strategies, settings, HealthCheck from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.model.hypothesis_strategies import origins, objects from swh.storage.tests.storage_testing import StorageTestFixture from swh.storage import HashCollision from .generate_data_test import gen_contents @pytest.mark.db class StorageTestDbFixture(StorageTestFixture): def setUp(self): super().setUp() db = self.test_db[self.TEST_DB_NAME] self.conn = db.conn self.cursor = db.cursor self.maxDiff = None def tearDown(self): self.reset_storage_tables() super().tearDown() class TestStorageData: def setUp(self): super().setUp() self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hash_to_bytes( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hash_to_bytes( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hash_to_bytes( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), 'blake2s256': hash_to_bytes('d5fe1939576527e42cfd76a9455a2' '432fe7f56669564577dd93c4280e76d661d'), 'status': 'visible', } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hash_to_bytes( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hash_to_bytes( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hash_to_bytes( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), 'blake2s256': hash_to_bytes('849c20fad132b7c2d62c15de310adfe87be' '94a379941bed295e8141c6219810d'), 'status': 'visible', } self.cont3 = { 'data': b'424242\n', 'length': 7, 'sha1': hash_to_bytes( '3e21cc4942a4234c9e5edd8a9cacd1670fe59f13'), 'sha1_git': hash_to_bytes( 'c932c7649c6dfa4b82327d121215116909eb3bea'), 'sha256': hash_to_bytes( '92fb72daf8c6818288a35137b72155f5' '07e5de8d892712ab96277aaed8cf8a36'), 'blake2s256': hash_to_bytes('76d0346f44e5a27f6bafdd9c2befd304af' 'f83780f93121d801ab6a1d4769db11'), 'status': 'visible', } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hash_to_bytes( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hash_to_bytes( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes('306856b8fd879edb7b6f1aeaaf8db9bbecc9' '93cd7f776c333ac3a782fa5c6eba'), 'status': 'absent', } self.skipped_cont = { 'length': 1024 * 1024 * 200, 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8920'), 'sha1': hash_to_bytes( '43e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '7bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( 'ade18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.skipped_cont2 = { 'length': 1024 * 1024 * 300, 'sha1_git': hash_to_bytes( '44e45d56f88993aae6a0198013efa80716fd8921'), 'sha1': hash_to_bytes( '54e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '8cbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( '9ce18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.dir = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90', 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': from_disk.DentryPerms.content, }, { 'name': b'bar\xc3', 'type': 'dir', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.directory, }, ], } self.dir2 = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa95', 'entries': [ { 'name': b'oof', 'type': 'file', 'target': self.cont2['sha1_git'], 'perms': from_disk.DentryPerms.content, } ], } self.dir3 = { 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'), 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': from_disk.DentryPerms.content, }, { 'name': b'subdir', 'type': 'dir', 'target': self.dir['id'], 'perms': from_disk.DentryPerms.directory, }, { 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.content, }, ], } self.dir4 = { 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8922'), 'entries': [ { 'name': b'subdir1', 'type': 'dir', 'target': self.dir3['id'], 'perms': from_disk.DentryPerms.directory, }, ] } self.minus_offset = datetime.timezone(datetime.timedelta(minutes=-120)) self.plus_offset = datetime.timezone(datetime.timedelta(minutes=120)) self.revision = { 'id': b'56789012345678901234', 'message': b'hello', 'author': { 'name': b'Nicolas Dandrimont', 'email': b'nicolas@example.com', 'fullname': b'Nicolas Dandrimont ', }, 'date': { 'timestamp': 1234567890, 'offset': 120, 'negative_utc': None, }, 'committer': { 'name': b'St\xc3fano Zacchiroli', 'email': b'stefano@example.com', 'fullname': b'St\xc3fano Zacchiroli ' }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': True, }, 'parents': [b'01234567890123456789', b'23434512345123456789'], 'type': 'git', 'directory': self.dir['id'], 'metadata': { 'checksums': { 'sha1': 'tarball-sha1', 'sha256': 'tarball-sha256', }, 'signed-off-by': 'some-dude', 'extra_headers': [ ['gpgsig', b'test123'], ['mergetags', [b'foo\\bar', b'\x22\xaf\x89\x80\x01\x00']], ], }, 'synthetic': True } self.revision2 = { 'id': b'87659012345678904321', 'message': b'hello again', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': False, }, 'parents': [b'01234567890123456789'], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': False } self.revision3 = { 'id': hash_to_bytes('7026b7c1a2af56521e951c01ed20f255fa054238'), 'message': b'a simple revision with no parents this time', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1127351742, 'offset': 0, 'negative_utc': False, }, 'parents': [], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': True } self.revision4 = { 'id': hash_to_bytes('368a48fe15b7db2383775f97c6b247011b3f14f4'), 'message': b'parent of self.revision2', 'author': { 'name': b'me', 'email': b'me@soft.heri', 'fullname': b'me ', }, 'date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'committer-dude', 'email': b'committer@dude.com', 'fullname': b'committer-dude ', }, 'committer_date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'parents': [self.revision3['id']], 'type': 'git', 'directory': self.dir['id'], 'metadata': None, 'synthetic': False } self.origin = { 'url': 'file:///dev/null', 'type': 'git', } self.origin2 = { 'url': 'file:///dev/zero', 'type': 'hg', } self.provider = { 'name': 'hal', 'type': 'deposit-client', 'url': 'http:///hal/inria', 'metadata': { 'location': 'France' } } self.metadata_tool = { 'name': 'swh-deposit', 'version': '0.0.1', 'configuration': { 'sword_version': '2' } } self.origin_metadata = { 'origin': self.origin, 'discovery_date': datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.origin_metadata2 = { 'origin': self.origin, 'discovery_date': datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.release = { 'id': b'87659012345678901234', 'name': b'v0.0.1', 'author': { 'name': b'olasd', 'email': b'nic@olasd.fr', 'fullname': b'olasd ', }, 'date': { 'timestamp': 1234567890, 'offset': 42, 'negative_utc': None, }, 'target': b'43210987654321098765', 'target_type': 'revision', 'message': b'synthetic release', 'synthetic': True, } self.release2 = { 'id': b'56789012348765901234', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634366813, 'offset': -120, 'negative_utc': None, }, 'target': b'432109\xa9765432\xc309\x00765', 'target_type': 'revision', 'message': b'v0.0.2\nMisc performance improvements + bug fixes', 'synthetic': False } self.release3 = { 'id': b'87659012345678904321', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'tony@ardumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634336813, 'offset': 0, 'negative_utc': False, }, 'target': self.revision2['id'], 'target_type': 'revision', 'message': b'yet another synthetic release', 'synthetic': True, } self.fetch_history_date = datetime.datetime( 2015, 1, 2, 21, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_end = datetime.datetime( 2015, 1, 2, 23, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_duration = (self.fetch_history_end - self.fetch_history_date) self.fetch_history_data = { 'status': True, 'result': {'foo': 'bar'}, 'stdout': 'blabla', 'stderr': 'blablabla', } self.snapshot = { 'id': hash_to_bytes('2498dbf535f882bc7f9a18fb16c9ad27fda7bab7'), 'branches': { b'master': { 'target': self.revision['id'], 'target_type': 'revision', }, }, 'next_branch': None } self.empty_snapshot = { 'id': hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'branches': {}, 'next_branch': None } self.complete_snapshot = { 'id': hash_to_bytes('6e65b86363953b780d92b0a928f3e8fcdd10db36'), 'branches': { b'directory': { 'target': hash_to_bytes( '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'), 'target_type': 'directory', }, b'directory2': { 'target': hash_to_bytes( '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'), 'target_type': 'directory', }, b'content': { 'target': hash_to_bytes( 'fe95a46679d128ff167b7c55df5d02356c5a1ae1'), 'target_type': 'content', }, b'alias': { 'target': b'revision', 'target_type': 'alias', }, b'revision': { 'target': hash_to_bytes( 'aafb16d69fd30ff58afdd69036a26047f3aebdc6'), 'target_type': 'revision', }, b'release': { 'target': hash_to_bytes( '7045404f3d1c54e6473c71bbb716529fbad4be24'), 'target_type': 'release', }, b'snapshot': { 'target': hash_to_bytes( '1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'target_type': 'snapshot', }, b'dangling': None, }, 'next_branch': None } class CommonTestStorage(TestStorageData): """Base class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ maxDiff = None @staticmethod def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ('date', 'committer_date'): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity def test_check_config(self): self.assertTrue(self.storage.check_config(check_write=True)) self.assertTrue(self.storage.check_config(check_write=False)) def test_content_add(self): cont = self.cont insertion_start_time = datetime.datetime.now(tz=datetime.timezone.utc) actual_result = self.storage.content_add([cont]) insertion_end_time = datetime.datetime.now(tz=datetime.timezone.utc) self.assertEqual(actual_result, { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 }) self.assertEqual(list(self.storage.content_get([cont['sha1']])), [{'sha1': cont['sha1'], 'data': cont['data']}]) expected_cont = cont.copy() del expected_cont['data'] journal_objects = list(self.journal_writer.objects) for (obj_type, obj) in journal_objects: self.assertLessEqual(insertion_start_time, obj['ctime']) self.assertLessEqual(obj['ctime'], insertion_end_time) del obj['ctime'] self.assertEqual(journal_objects, [('content', expected_cont)]) def test_content_get_missing(self): cont = self.cont self.storage.content_add([cont]) # Query a single missing content results = list(self.storage.content_get( [self.cont2['sha1']])) self.assertEqual(results, [None]) # Check content_get does not abort after finding a missing content results = list(self.storage.content_get( [self.cont['sha1'], self.cont2['sha1']])) self.assertEqual(results, [{'sha1': cont['sha1'], 'data': cont['data']}, None]) # Check content_get does not discard found countent when it finds # a missing content. results = list(self.storage.content_get( [self.cont2['sha1'], self.cont['sha1']])) self.assertEqual(results, [None, {'sha1': cont['sha1'], 'data': cont['data']}]) def test_content_add_same_input(self): cont = self.cont actual_result = self.storage.content_add([cont, cont]) self.assertEqual(actual_result, { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 }) def test_content_add_different_input(self): cont = self.cont cont2 = self.cont2 actual_result = self.storage.content_add([cont, cont2]) self.assertEqual(actual_result, { 'content:add': 2, 'content:add:bytes': cont['length'] + cont2['length'], 'skipped_content:add': 0 }) def test_content_add_again(self): actual_result = self.storage.content_add([self.cont]) self.assertEqual(actual_result, { 'content:add': 1, 'content:add:bytes': self.cont['length'], 'skipped_content:add': 0 }) actual_result = self.storage.content_add([self.cont, self.cont2]) self.assertEqual(actual_result, { 'content:add': 1, 'content:add:bytes': self.cont2['length'], 'skipped_content:add': 0 }) self.assertEqual(len(self.storage.content_find(self.cont)), 1) self.assertEqual(len(self.storage.content_find(self.cont2)), 1) def test_content_add_db(self): cont = self.cont actual_result = self.storage.content_add([cont]) self.assertEqual(actual_result, { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 }) if hasattr(self.storage, 'objstorage'): self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) expected_cont = cont.copy() del expected_cont['data'] journal_objects = list(self.journal_writer.objects) for (obj_type, obj) in journal_objects: del obj['ctime'] self.assertEqual(journal_objects, [('content', expected_cont)]) def test_content_add_collision(self): cont1 = self.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b['sha256']) sha256_array[0] += 1 cont1b['sha256'] = bytes(sha256_array) with self.assertRaises(HashCollision) as cm: self.storage.content_add([cont1, cont1b]) self.assertIn(cm.exception.args[0], ['sha1', 'sha1_git', 'blake2s256']) def test_content_add_metadata(self): cont = self.cont.copy() del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = self.storage.content_add_metadata([cont]) self.assertEqual(actual_result, { 'content:add': 1, 'skipped_content:add': 0 }) expected_cont = cont.copy() del expected_cont['ctime'] self.assertEqual( list(self.storage.content_get_metadata([cont['sha1']])), [expected_cont]) self.assertEqual(list(self.journal_writer.objects), [('content', cont)]) def test_content_add_metadata_same_input(self): cont = self.cont.copy() del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = self.storage.content_add_metadata([cont, cont]) self.assertEqual(actual_result, { 'content:add': 1, 'skipped_content:add': 0 }) def test_content_add_metadata_different_input(self): cont = self.cont.copy() del cont['data'] cont['ctime'] = datetime.datetime.now() cont2 = self.cont2.copy() del cont2['data'] cont2['ctime'] = datetime.datetime.now() actual_result = self.storage.content_add_metadata([cont, cont2]) self.assertEqual(actual_result, { 'content:add': 2, 'skipped_content:add': 0 }) def test_content_add_metadata_db(self): cont = self.cont.copy() del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = self.storage.content_add_metadata([cont]) self.assertEqual(actual_result, { 'content:add': 1, 'skipped_content:add': 0 }) if hasattr(self.storage, 'objstorage'): self.assertNotIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) self.assertEqual(list(self.journal_writer.objects), [('content', cont)]) def test_content_add_metadata_collision(self): cont1 = self.cont.copy() 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 self.assertRaises(HashCollision) as cm: self.storage.content_add_metadata([cont1, cont1b]) self.assertIn(cm.exception.args[0], ['sha1', 'sha1_git', 'blake2s256']) def test_skipped_content_add_db(self): cont = self.skipped_cont.copy() cont2 = self.skipped_cont2.copy() cont2['blake2s256'] = None actual_result = self.storage.content_add([cont, cont, cont2]) self.assertEqual(actual_result, { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, }) self.cursor.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') datums = self.cursor.fetchall() self.assertEqual(2, len(datums)) datum = datums[0] self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3].tobytes(), datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') ) datum2 = datums[1] self.assertEqual( (datum2[0].tobytes(), datum2[1].tobytes(), datum2[2].tobytes(), datum2[3], datum2[4], datum2[5], datum2[6]), (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') ) def test_skipped_content_add(self): cont = self.skipped_cont.copy() cont2 = self.skipped_cont2.copy() cont2['blake2s256'] = None missing = list(self.storage.skipped_content_missing([cont, cont2])) self.assertEqual(len(missing), 2, missing) actual_result = self.storage.content_add([cont, cont, cont2]) self.assertEqual(actual_result, { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, }) missing = list(self.storage.skipped_content_missing([cont, cont2])) self.assertEqual(missing, []) @pytest.mark.property_based @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing(self, algos): algos |= {'sha1'} cont2 = self.cont2 missing_cont = self.missing_cont self.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) self.assertCountEqual( self.storage.content_missing(test_contents), missing_per_hash['sha1'] ) for hash in algos: self.assertCountEqual( self.storage.content_missing(test_contents, key_hash=hash), missing_per_hash[hash] ) def test_content_missing__marked_missing(self): cont2 = self.cont2.copy() cont2['status'] = 'missing' del cont2['data'] self.storage.content_add([cont2]) test_content = { algo: cont2[algo] for algo in ('sha1', 'sha1_git', 'sha256', 'blake2s256')} self.assertCountEqual( self.storage.content_missing([test_content]), [cont2['sha1']] ) @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, algos): algos |= {'sha1'} cont2 = self.cont2 missing_cont = self.missing_cont self.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) self.assertCountEqual( self.storage.content_missing(test_contents), missing_per_hash['sha1'] ) for hash in algos: self.assertCountEqual( self.storage.content_missing(test_contents, key_hash=hash), missing_per_hash[hash] ) def test_content_missing_per_sha1(self): # given cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) # when gen = self.storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then self.assertEqual(list(gen), [missing_cont['sha1']]) def test_content_get_metadata(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([cont1['sha1'], cont2['sha1']]) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') self.assertCountEqual(list(gen), [cont1, cont2]) def test_content_get_metadata_missing_sha1(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() missing_cont = self.missing_cont.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([missing_cont['sha1']]) # All the metadata keys are None missing_cont.pop('data') for key in list(missing_cont): if key != 'sha1': missing_cont[key] = None self.assertEqual(list(gen), [missing_cont]) @staticmethod 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 test_directory_add(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) actual_result = self.storage.directory_add([self.dir]) self.assertEqual(actual_result, {'directory:add': 1}) self.assertEqual(list(self.journal_writer.objects), [('directory', self.dir)]) actual_data = list(self.storage.directory_ls(self.dir['id'])) expected_data = list(self._transform_entries(self.dir)) self.assertCountEqual(expected_data, actual_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) def test_directory_get_recursive(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) actual_result = self.storage.directory_add( [self.dir, self.dir2, self.dir3]) self.assertEqual(actual_result, {'directory:add': 3}) self.assertEqual(list(self.journal_writer.objects), [('directory', self.dir), ('directory', self.dir2), ('directory', self.dir3)]) # List directory containing a file and an unknown subdirectory actual_data = list(self.storage.directory_ls( self.dir['id'], recursive=True)) expected_data = list(self._transform_entries(self.dir)) self.assertCountEqual(expected_data, actual_data) # List directory containing a file and an unknown subdirectory actual_data = list(self.storage.directory_ls( self.dir2['id'], recursive=True)) expected_data = list(self._transform_entries(self.dir2)) self.assertCountEqual(expected_data, actual_data) # List directory containing a known subdirectory, entries should # be both those of the directory and of the subdir actual_data = list(self.storage.directory_ls( self.dir3['id'], recursive=True)) expected_data = list(itertools.chain( self._transform_entries(self.dir3), self._transform_entries(self.dir, prefix=b'subdir/'))) self.assertCountEqual(expected_data, actual_data) def test_directory_get_non_recursive(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) actual_result = self.storage.directory_add( [self.dir, self.dir2, self.dir3]) self.assertEqual(actual_result, {'directory:add': 3}) self.assertEqual(list(self.journal_writer.objects), [('directory', self.dir), ('directory', self.dir2), ('directory', self.dir3)]) # List directory containing a file and an unknown subdirectory actual_data = list(self.storage.directory_ls(self.dir['id'])) expected_data = list(self._transform_entries(self.dir)) self.assertCountEqual(expected_data, actual_data) # List directory contaiining a single file actual_data = list(self.storage.directory_ls(self.dir2['id'])) expected_data = list(self._transform_entries(self.dir2)) self.assertCountEqual(expected_data, actual_data) # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(self.storage.directory_ls(self.dir3['id'])) expected_data = list(self._transform_entries(self.dir3)) self.assertCountEqual(expected_data, actual_data) def test_directory_entry_get_by_path(self): # given init_missing = list(self.storage.directory_missing([self.dir3['id']])) self.assertEqual([self.dir3['id']], init_missing) actual_result = self.storage.directory_add([self.dir3, self.dir4]) self.assertEqual(actual_result, {'directory:add': 2}) expected_entries = [ { 'dir_id': self.dir3['id'], 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'subdir', 'type': 'dir', 'target': self.dir['id'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.directory, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, ] # when (all must be found here) for entry, expected_entry in zip(self.dir3['entries'], expected_entries): actual_entry = self.storage.directory_entry_get_by_path( self.dir3['id'], [entry['name']]) self.assertEqual(actual_entry, expected_entry) # same, but deeper for entry, expected_entry in zip(self.dir3['entries'], expected_entries): actual_entry = self.storage.directory_entry_get_by_path( self.dir4['id'], [b'subdir1', entry['name']]) expected_entry = expected_entry.copy() expected_entry['name'] = b'subdir1/' + expected_entry['name'] self.assertEqual(actual_entry, expected_entry) # when (nothing should be found here since self.dir is not persisted.) for entry in self.dir['entries']: actual_entry = self.storage.directory_entry_get_by_path( self.dir['id'], [entry['name']]) self.assertIsNone(actual_entry) def test_revision_add(self): init_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([self.revision['id']], list(init_missing)) actual_result = self.storage.revision_add([self.revision]) self.assertEqual(actual_result, {'revision:add': 1}) end_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([], list(end_missing)) self.assertEqual(list(self.journal_writer.objects), [('revision', self.revision)]) # already there so nothing added actual_result = self.storage.revision_add([self.revision]) self.assertEqual(actual_result, {'revision:add': 0}) def test_revision_add_name_clash(self): revision1 = self.revision.copy() revision2 = self.revision2.copy() 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 = self.storage.revision_add([revision1, revision2]) self.assertEqual(actual_result, {'revision:add': 2}) def test_revision_log(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_log( [self.revision4['id']])) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEqual(actual_results[0], self.normalize_entity(self.revision4)) self.assertEqual(actual_results[1], self.normalize_entity(self.revision3)) self.assertEqual(list(self.journal_writer.objects), [('revision', self.revision3), ('revision', self.revision4)]) def test_revision_log_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_log( [self.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] self.assertEqual(len(actual_results), 1) self.assertEqual(actual_results[0], self.revision4) def test_revision_log_unknown_revision(self): rev_log = list(self.storage.revision_log([self.revision['id']])) self.assertEqual(rev_log, []) @staticmethod def _short_revision(revision): return [revision['id'], revision['parents']] def test_revision_shortlog(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_shortlog( [self.revision4['id']])) self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEqual(list(actual_results[0]), self._short_revision(self.revision4)) self.assertEqual(list(actual_results[1]), self._short_revision(self.revision3)) def test_revision_shortlog_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_shortlog( [self.revision4['id']], 1)) self.assertEqual(len(actual_results), 1) self.assertEqual(list(actual_results[0]), self._short_revision(self.revision4)) def test_revision_get(self): self.storage.revision_add([self.revision]) actual_revisions = list(self.storage.revision_get( [self.revision['id'], self.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'] self.assertEqual(len(actual_revisions), 2) self.assertEqual(actual_revisions[0], self.normalize_entity(self.revision)) self.assertIsNone(actual_revisions[1]) def test_revision_get_no_parents(self): self.storage.revision_add([self.revision3]) get = list(self.storage.revision_get([self.revision3['id']])) self.assertEqual(len(get), 1) self.assertEqual(get[0]['parents'], []) # no parents on this one def test_release_add(self): init_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([self.release['id'], self.release2['id']], list(init_missing)) actual_result = self.storage.release_add([self.release, self.release2]) self.assertEqual(actual_result, {'release:add': 2}) end_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([], list(end_missing)) self.assertEqual(list(self.journal_writer.objects), [('release', self.release), ('release', self.release2)]) # already present so nothing added actual_result = self.storage.release_add([self.release, self.release2]) self.assertEqual(actual_result, {'release:add': 0}) def test_release_add_no_author_date(self): release = self.release.copy() release['author'] = None release['date'] = None actual_result = self.storage.release_add([release]) self.assertEqual(actual_result, {'release:add': 1}) end_missing = self.storage.release_missing([self.release['id']]) self.assertEqual([], list(end_missing)) self.assertEqual(list(self.journal_writer.objects), [('release', release)]) def test_release_add_name_clash(self): release1 = self.release.copy() release2 = self.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 = self.storage.release_add([release1, release2]) self.assertEqual(actual_result, {'release:add': 2}) def test_release_get(self): # given self.storage.release_add([self.release, self.release2]) # when actual_releases = list(self.storage.release_get([self.release['id'], self.release2['id']])) # then for actual_release in actual_releases: if 'id' in actual_release['author']: del actual_release['author']['id'] # hack: ids are generated self.assertEqual([self.normalize_entity(self.release), self.normalize_entity(self.release2)], [actual_releases[0], actual_releases[1]]) unknown_releases = \ list(self.storage.release_get([self.release3['id']])) self.assertIsNone(unknown_releases[0]) def test_origin_add_one(self): origin0 = self.storage.origin_get(self.origin) self.assertIsNone(origin0) id = self.storage.origin_add_one(self.origin) actual_origin = self.storage.origin_get({'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin['id'], id) id2 = self.storage.origin_add_one(self.origin) self.assertEqual(id, id2) def test_origin_add(self): origin0 = self.storage.origin_get([self.origin])[0] self.assertIsNone(origin0) origin1, origin2 = self.storage.origin_add([self.origin, self.origin2]) actual_origin = self.storage.origin_get([{ 'url': self.origin['url'], 'type': self.origin['type'], }])[0] self.assertEqual(actual_origin['id'], origin1['id']) actual_origin2 = self.storage.origin_get([{ 'url': self.origin2['url'], 'type': self.origin2['type'], }])[0] self.assertEqual(actual_origin2['id'], origin2['id']) del actual_origin['id'] del actual_origin2['id'] self.assertEqual(list(self.journal_writer.objects), [('origin', actual_origin), ('origin', actual_origin2)]) def test_origin_add_twice(self): add1 = self.storage.origin_add([self.origin, self.origin2]) add2 = self.storage.origin_add([self.origin, self.origin2]) self.assertEqual(add1, add2) def test_origin_get_without_type(self): origin0 = self.storage.origin_get([self.origin])[0] self.assertIsNone(origin0) origin3 = self.origin2.copy() origin3['type'] += 'foo' origin1, origin2, origin3 = self.storage.origin_add( [self.origin, self.origin2, origin3]) actual_origin = self.storage.origin_get([{ 'url': self.origin['url'], }])[0] self.assertEqual(actual_origin['id'], origin1['id']) actual_origin_2_or_3 = self.storage.origin_get([{ 'url': self.origin2['url'], }])[0] self.assertIn( actual_origin_2_or_3['id'], [origin2['id'], origin3['id']]) del actual_origin['id'] del actual_origin_2_or_3['id'] del origin3['id'] self.assertEqual(list(self.journal_writer.objects), [('origin', self.origin), ('origin', self.origin2), ('origin', origin3)]) def test_origin_get_legacy(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) # lookup per type and url (returns id) actual_origin0 = self.storage.origin_get( {'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin0['id'], id) # lookup per id (returns dict) actual_origin1 = self.storage.origin_get({'id': id}) self.assertEqual(actual_origin1, {'id': id, 'type': self.origin['type'], 'url': self.origin['url']}) def test_origin_get(self): self.assertIsNone(self.storage.origin_get(self.origin)) origin_id = self.storage.origin_add_one(self.origin) # lookup per type and url (returns id) actual_origin0 = self.storage.origin_get( [{'url': self.origin['url'], 'type': self.origin['type']}]) self.assertEqual(len(actual_origin0), 1, actual_origin0) self.assertEqual(actual_origin0[0]['id'], origin_id) # lookup per id (returns dict) actual_origin1 = self.storage.origin_get([{'id': origin_id}]) self.assertEqual(len(actual_origin1), 1, actual_origin1) self.assertEqual(actual_origin1[0], {'id': origin_id, 'type': self.origin['type'], 'url': self.origin['url']}) def test_origin_get_consistency(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) with self.assertRaises(ValueError): self.storage.origin_get([ {'url': self.origin['url'], 'type': self.origin['type']}, {'id': id}]) def test_origin_search(self): found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 0) found_origins = list(self.storage.origin_search(self.origin['url'], regexp=True)) self.assertEqual(len(found_origins), 0) id = self.storage.origin_add_one(self.origin) origin_data = {'id': id, 'type': self.origin['type'], 'url': self.origin['url']} found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search( '.' + self.origin['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) id2 = self.storage.origin_add_one(self.origin2) origin2_data = {'id': id2, 'type': self.origin2['type'], 'url': self.origin2['url']} found_origins = list(self.storage.origin_search(self.origin2['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search( '.' + self.origin2['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) # Search / (regexp=False) found_origins = list(self.storage.origin_search('/')) self.assertEqual(len(found_origins), 2) found_origins0 = list(self.storage.origin_search('/', offset=0, limit=1)) # noqa self.assertEqual(len(found_origins0), 1) self.assertIn(found_origins0[0], [origin_data, origin2_data]) found_origins1 = list(self.storage.origin_search('/', offset=1, limit=1)) # noqa self.assertEqual(len(found_origins1), 1) self.assertIn(found_origins1[0], [origin_data, origin2_data]) self.assertCountEqual(found_origins0 + found_origins1, [origin_data, origin2_data]) # Search / (regexp=True) found_origins = list(self.storage.origin_search('/', regexp=True)) self.assertEqual(len(found_origins), 2) found_origins0 = list(self.storage.origin_search('/', offset=0, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins0), 1) self.assertIn(found_origins0[0], [origin_data, origin2_data]) found_origins1 = list(self.storage.origin_search('/', offset=1, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins1), 1) self.assertIn(found_origins1[0], [origin_data, origin2_data]) self.assertCountEqual(found_origins0 + found_origins1, [origin_data, origin2_data]) # Search .*/.* (regexp=True) found_origins = list(self.storage.origin_search('.*/.*', regexp=True)) self.assertEqual(len(found_origins), 2) found_origins = list(self.storage.origin_search('/', offset=0, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('/', offset=1, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) def test_origin_visit_add(self): # given self.assertIsNone(self.storage.origin_get([self.origin2])[0]) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_id, type='git', date=self.date_visit2) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': 'git', 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) expected_origin = self.origin2.copy() data = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': 'git', 'status': 'ongoing', 'metadata': None, 'snapshot': None, } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data)]) def test_origin_visit_add_from_url(self): # given self.assertIsNone(self.storage.origin_get([self.origin2])[0]) origin_id = self.storage.origin_add_one(self.origin2) origin_url = self.origin2['url'] self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_url, type='git', date=self.date_visit2) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': 'git', 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) expected_origin = self.origin2.copy() data = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': 'git', 'status': 'ongoing', 'metadata': None, 'snapshot': None, } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data)]) def test_origin_visit_add_default_type(self): # given self.assertIsNone(self.storage.origin_get([self.origin2])[0]) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) origin_visit2 = self.storage.origin_visit_add( origin_id, date='2018-01-01 23:00:00+00') # then self.assertEqual(origin_visit1['origin'], origin_id) self.assertIsNotNone(origin_visit1['visit']) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [ { 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': 'hg', 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, { 'origin': origin_id, 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'type': 'hg', 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, ]) expected_origin = self.origin2.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': 'hg', 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'type': 'hg', 'status': 'ongoing', 'metadata': None, 'snapshot': None, } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data1), ('origin_visit', data2)]) def test_origin_visit_update(self): # given origin_id = self.storage.origin_add_one(self.origin) origin_id2 = self.storage.origin_add_one(self.origin2) origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) origin_visit2 = self.storage.origin_visit_add( origin_id, date=self.date_visit3) origin_visit3 = self.storage.origin_visit_add( origin_id2, date=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) self.storage.origin_visit_update(origin_id2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits_bis = list(self.storage.origin_visit_get( origin_id, limit=1)) self.assertEqual(actual_origin_visits_bis, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }]) actual_origin_visits_ter = list(self.storage.origin_visit_get( origin_id, last_visit=origin_visit1['visit'])) self.assertEqual(actual_origin_visits_ter, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2)) self.assertEqual(actual_origin_visits2, [{ 'origin': origin_visit3['origin'], 'date': self.date_visit3, 'visit': origin_visit3['visit'], 'type': self.origin2['type'], 'status': 'partial', 'metadata': None, 'snapshot': None, }]) expected_origin = self.origin.copy() expected_origin2 = self.origin2.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data3 = { 'origin': expected_origin2, 'date': self.date_visit3, 'visit': origin_visit3['visit'], 'type': self.origin2['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'metadata': visit1_metadata, 'status': 'full', 'snapshot': None, } data5 = { 'origin': expected_origin2, 'date': self.date_visit3, 'visit': origin_visit3['visit'], 'type': self.origin2['type'], 'status': 'partial', 'metadata': None, 'snapshot': None, } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin', expected_origin2), ('origin_visit', data1), ('origin_visit', data2), ('origin_visit', data3), ('origin_visit', data4), ('origin_visit', data5)]) def test_origin_visit_update_missing_snapshot(self): # given origin_id = self.storage.origin_add_one(self.origin) origin_visit = self.storage.origin_visit_add( origin_id, date=self.date_visit1) # when self.storage.origin_visit_update( origin_id, origin_visit['visit'], snapshot=self.snapshot['id']) # then actual_origin_visit = self.storage.origin_visit_get_by( origin_visit['origin'], origin_visit['visit']) self.assertEqual(actual_origin_visit['snapshot'], self.snapshot['id']) # when self.storage.snapshot_add([self.snapshot]) self.assertEqual(actual_origin_visit['snapshot'], self.snapshot['id']) def test_origin_visit_get_by(self): origin_id = self.storage.origin_add_one(self.origin) origin_id2 = self.storage.origin_add_one(self.origin2) origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) self.storage.snapshot_add(origin_id, origin_visit1['visit'], self.snapshot) # Add some other {origin, visit} entries self.storage.origin_visit_add(origin_id, date=self.date_visit3) self.storage.origin_visit_add(origin_id2, date=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], 'date': self.date_visit2, 'type': self.origin['type'], 'metadata': visit1_metadata, 'status': 'full', 'snapshot': self.snapshot['id'], }) # when actual_origin_visit1 = self.storage.origin_visit_get_by( origin_visit1['origin'], origin_visit1['visit']) # then self.assertEqual(actual_origin_visit1, expected_origin_visit) def test_origin_visit_upsert_new(self): # given self.assertIsNone(self.storage.origin_get([self.origin2])[0]) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when self.storage.origin_visit_upsert([ { 'origin': origin_id, 'date': self.date_visit2, 'visit': 123, 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_id, 'date': '2018-01-01 23:00:00+00', 'visit': 1234, 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, }, ]) # then actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [ { 'origin': origin_id, 'date': self.date_visit2, 'visit': 123, 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_id, 'date': self.date_visit3, 'visit': 1234, 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, }, ]) expected_origin = self.origin2.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': 123, 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit3, 'visit': 1234, 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data1), ('origin_visit', data2)]) def test_origin_visit_upsert_existing(self): # given self.assertIsNone(self.storage.origin_get([self.origin2])[0]) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) self.storage.origin_visit_upsert([{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, }]) # then self.assertEqual(origin_visit1['origin'], origin_id) self.assertIsNotNone(origin_visit1['visit']) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, }]) expected_origin = self.origin2.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin2['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'type': self.origin2['type'], 'status': 'full', 'metadata': None, 'snapshot': None, } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data1), ('origin_visit', data2)]) def test_origin_visit_get_by_no_result(self): # No result actual_origin_visit = self.storage.origin_visit_get_by( 10, 999) self.assertIsNone(actual_origin_visit) def test_person_get(self): # given (person injection through revision for example) self.storage.revision_add([self.revision]) rev = list(self.storage.revision_get([self.revision['id']]))[0] id0 = rev['committer']['id'] person0 = self.revision['committer'] id1 = rev['author']['id'] person1 = self.revision['author'] # when actual_persons = self.storage.person_get([id0, id1]) # then expected_persons = [ { 'id': id0, 'fullname': person0['fullname'], 'name': person0['name'], 'email': person0['email'], }, { 'id': id1, 'fullname': person1['fullname'], 'name': person1['name'], 'email': person1['email'], } ] self.assertEqual(list(actual_persons), expected_persons) # when actual_persons = self.storage.person_get([id1, id0]) # then expected_persons.reverse() self.assertEqual(list(actual_persons), expected_persons) def test_origin_visit_get_latest(self): origin_id = self.storage.origin_add_one(self.origin) origin_url = self.origin['url'] origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit3_id = origin_visit3['visit'] origin_visit1 = self.storage.origin_visit_get_by(origin_url, visit1_id) origin_visit2 = self.storage.origin_visit_get_by(origin_url, visit2_id) origin_visit3 = self.storage.origin_visit_get_by(origin_url, visit3_id) # Two visits, both with no snapshot self.assertEqual( origin_visit3, self.storage.origin_visit_get_latest(origin_url)) self.assertIsNone( self.storage.origin_visit_get_latest(origin_url, require_snapshot=True)) # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 self.storage.snapshot_add([self.complete_snapshot]) self.storage.origin_visit_update( origin_id, visit1_id, snapshot=self.complete_snapshot['id']) self.assertEqual( {**origin_visit1, 'snapshot': self.complete_snapshot['id']}, self.storage.origin_visit_get_latest( origin_url, require_snapshot=True) ) self.assertEqual( origin_visit3, self.storage.origin_visit_get_latest(origin_url) ) # Status filter: all three visits are status=ongoing, so no visit # returned self.assertIsNone( self.storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_id, visit1_id, status='full') self.assertEqual( { **origin_visit1, 'snapshot': self.complete_snapshot['id'], 'status': 'full'}, self.storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']), ) self.assertEqual( origin_visit3, self.storage.origin_visit_get_latest(origin_url), ) # Add snapshot to visit2 and check that the new snapshot is returned self.storage.snapshot_add([self.empty_snapshot]) self.storage.origin_visit_update( origin_id, visit2_id, snapshot=self.empty_snapshot['id']) self.assertEqual( {**origin_visit2, 'snapshot': self.empty_snapshot['id']}, self.storage.origin_visit_get_latest( origin_url, require_snapshot=True), ) self.assertEqual( origin_visit3, self.storage.origin_visit_get_latest(origin_url), ) # Check that the status filter is still working self.assertEqual( { **origin_visit1, 'snapshot': self.complete_snapshot['id'], 'status': 'full'}, self.storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']), ) # Add snapshot to visit3 (same date as visit2) self.storage.snapshot_add([self.complete_snapshot]) self.storage.origin_visit_update( origin_id, visit3_id, snapshot=self.complete_snapshot['id']) self.assertEqual( { **origin_visit1, 'snapshot': self.complete_snapshot['id'], 'status': 'full'}, self.storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']), ) self.assertEqual( { **origin_visit1, 'snapshot': self.complete_snapshot['id'], 'status': 'full'}, self.storage.origin_visit_get_latest( origin_url, allowed_statuses=['full'], require_snapshot=True), ) self.assertEqual( {**origin_visit3, 'snapshot': self.complete_snapshot['id']}, self.storage.origin_visit_get_latest( origin_url), ) self.assertEqual( {**origin_visit3, 'snapshot': self.complete_snapshot['id']}, self.storage.origin_visit_get_latest( origin_url, require_snapshot=True), ) def test_person_get_fullname_unicity(self): # given (person injection through revisions for example) revision = self.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(self.revision2) revision2['committer'] = dict(revision['committer']) revision2['committer']['email'] = None revision2['committer']['name'] = None self.storage.revision_add([revision]) self.storage.revision_add([revision2]) # when getting added revisions revisions = list( self.storage.revision_get([revision['id'], revision2['id']])) # then # check committers are the same self.assertEqual(revisions[0]['committer'], revisions[1]['committer']) # check person_get return same result person0 = list( self.storage.person_get([revisions[0]['committer']['id']]))[0] person1 = list( self.storage.person_get([revisions[1]['committer']['id']]))[0] self.assertEqual(person0, person1) def test_snapshot_add_get_empty(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] actual_result = self.storage.snapshot_add([self.empty_snapshot]) self.assertEqual(actual_result, {'snapshot:add': 1}) self.storage.origin_visit_update( origin_id, visit_id, snapshot=self.empty_snapshot['id']) by_id = self.storage.snapshot_get(self.empty_snapshot['id']) self.assertEqual(by_id, self.empty_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.empty_snapshot) expected_origin = self.origin.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': self.empty_snapshot['id'], } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data1), ('snapshot', self.empty_snapshot), ('origin_visit', data2)]) def test_snapshot_add_get_empty__legacy_add(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.empty_snapshot) by_id = self.storage.snapshot_get(self.empty_snapshot['id']) self.assertEqual(by_id, self.empty_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.empty_snapshot) expected_origin = self.origin.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': self.empty_snapshot['id'], } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data1), ('snapshot', self.empty_snapshot), ('origin_visit', data2)]) def test_snapshot_add_get_complete(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] actual_result = self.storage.snapshot_add( origin_id, visit_id, self.complete_snapshot) self.assertEqual(actual_result, {'snapshot:add': 1}) by_id = self.storage.snapshot_get(self.complete_snapshot['id']) self.assertEqual(by_id, self.complete_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.complete_snapshot) def test_snapshot_add_many(self): actual_result = self.storage.snapshot_add( [self.snapshot, self.complete_snapshot]) self.assertEqual(actual_result, {'snapshot:add': 2}) self.assertEqual( self.complete_snapshot, self.storage.snapshot_get(self.complete_snapshot['id'])) self.assertEqual( self.snapshot, self.storage.snapshot_get(self.snapshot['id'])) def test_snapshot_add_many_incremental(self): actual_result = self.storage.snapshot_add([self.complete_snapshot]) self.assertEqual(actual_result, {'snapshot:add': 1}) actual_result2 = self.storage.snapshot_add( [self.snapshot, self.complete_snapshot]) self.assertEqual(actual_result2, {'snapshot:add': 1}) self.assertEqual( self.complete_snapshot, self.storage.snapshot_get(self.complete_snapshot['id'])) self.assertEqual( self.snapshot, self.storage.snapshot_get(self.snapshot['id'])) def test_snapshot_add_count_branches(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] actual_result = self.storage.snapshot_add( origin_id, visit_id, self.complete_snapshot) self.assertEqual(actual_result, {'snapshot:add': 1}) snp_id = self.complete_snapshot['id'] snp_size = self.storage.snapshot_count_branches(snp_id) expected_snp_size = { 'alias': 1, 'content': 1, 'directory': 2, 'release': 1, 'revision': 1, 'snapshot': 1, None: 1 } self.assertEqual(snp_size, expected_snp_size) def test_snapshot_add_get_paginated(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] branches = self.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = self.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, } self.assertEqual(snapshot, expected_snapshot) # Test branches_count snapshot = self.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', } self.assertEqual(snapshot, expected_snapshot) # test branch_from + branches_count snapshot = self.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], } self.assertEqual(snapshot, expected_snapshot) def test_snapshot_add_get_filtered(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] branches = self.complete_snapshot['branches'] snapshot = self.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, } self.assertEqual(snapshot, expected_snapshot) snapshot = self.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, } self.assertEqual(snapshot, expected_snapshot) def test_snapshot_add_get_filtered_and_paginated(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] branches = self.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = self.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, } self.assertEqual(snapshot, expected_snapshot) # Test branches_count snapshot = self.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', } self.assertEqual(snapshot, expected_snapshot) # Test branches_count snapshot = self.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', } self.assertEqual(snapshot, expected_snapshot) # test branch_from + branches_count snapshot = self.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', } self.assertEqual(snapshot, expected_snapshot) def test_snapshot_add_get(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.snapshot) by_id = self.storage.snapshot_get(self.snapshot['id']) self.assertEqual(by_id, self.snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.snapshot) origin_visit_info = self.storage.origin_visit_get_by(origin_id, visit_id) self.assertEqual(origin_visit_info['snapshot'], self.snapshot['id']) def test_snapshot_add_nonexistent_visit(self): origin_id = self.storage.origin_add_one(self.origin) visit_id = 54164461156 self.journal_writer.objects[:] = [] self.storage.snapshot_add([self.snapshot]) with self.assertRaises(ValueError): self.storage.origin_visit_update( origin_id, visit_id, snapshot=self.snapshot['id']) self.assertEqual(list(self.journal_writer.objects), [ ('snapshot', self.snapshot)]) def test_snapshot_add_nonexistent_visit__legacy_add(self): origin_id = self.storage.origin_add_one(self.origin) visit_id = 54164461156 self.journal_writer.objects[:] = [] with self.assertRaises(ValueError): self.storage.snapshot_add(origin_id, visit_id, self.snapshot) # Note: the actual legacy behavior was to abort before adding # the snapshot; but delaying non-existence checks makes the # compatibility code simpler self.assertEqual(list(self.journal_writer.objects), [ ('snapshot', self.snapshot)]) def test_snapshot_add_twice(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] self.storage.snapshot_add([self.snapshot]) self.storage.origin_visit_update( origin_id, visit1_id, snapshot=self.snapshot['id']) by_ov1 = self.storage.snapshot_get_by_origin_visit(origin_id, visit1_id) self.assertEqual(by_ov1, self.snapshot) origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] self.storage.snapshot_add([self.snapshot]) self.storage.origin_visit_update( origin_id, visit2_id, snapshot=self.snapshot['id']) by_ov2 = self.storage.snapshot_get_by_origin_visit(origin_id, visit2_id) self.assertEqual(by_ov2, self.snapshot) expected_origin = self.origin.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': self.snapshot['id'], } data3 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit2['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit2['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': self.snapshot['id'], } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data1), ('snapshot', self.snapshot), ('origin_visit', data2), ('origin_visit', data3), ('origin_visit', data4)]) def test_snapshot_add_twice__legacy_add(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit1_id, self.snapshot) by_ov1 = self.storage.snapshot_get_by_origin_visit(origin_id, visit1_id) self.assertEqual(by_ov1, self.snapshot) origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] self.storage.snapshot_add(origin_id, visit2_id, self.snapshot) by_ov2 = self.storage.snapshot_get_by_origin_visit(origin_id, visit2_id) self.assertEqual(by_ov2, self.snapshot) expected_origin = self.origin.copy() data1 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': self.date_visit1, 'visit': origin_visit1['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': self.snapshot['id'], } data3 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit2['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': expected_origin, 'date': self.date_visit2, 'visit': origin_visit2['visit'], 'type': self.origin['type'], 'status': 'ongoing', 'metadata': None, 'snapshot': self.snapshot['id'], } self.assertEqual(list(self.journal_writer.objects), [('origin', expected_origin), ('origin_visit', data1), ('snapshot', self.snapshot), ('origin_visit', data2), ('origin_visit', data3), ('origin_visit', data4)]) def test_snapshot_get_nonexistent(self): bogus_snapshot_id = b'bogus snapshot id 00' bogus_origin_id = 1 bogus_visit_id = 1 by_id = self.storage.snapshot_get(bogus_snapshot_id) self.assertIsNone(by_id) by_ov = self.storage.snapshot_get_by_origin_visit(bogus_origin_id, bogus_visit_id) self.assertIsNone(by_ov) def test_snapshot_get_latest(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None self.assertIsNone(self.storage.snapshot_get_latest(origin_id)) # Add snapshot to visit1, latest snapshot = visit 1 snapshot self.storage.snapshot_add([self.complete_snapshot]) self.storage.origin_visit_update( origin_id, visit1_id, snapshot=self.complete_snapshot['id']) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) # Status filter: all three visits are status=ongoing, so no snapshot # returned self.assertIsNone( self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_id, visit1_id, status='full') self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit2 and check that the new snapshot is returned self.storage.snapshot_add([self.empty_snapshot]) self.storage.origin_visit_update( origin_id, visit2_id, snapshot=self.empty_snapshot['id']) self.assertEqual(self.empty_snapshot, self.storage.snapshot_get_latest(origin_id)) # Check that the status filter is still working self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned self.storage.snapshot_add([self.complete_snapshot]) self.storage.origin_visit_update( origin_id, visit3_id, snapshot=self.complete_snapshot['id']) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) def test_snapshot_get_latest_from_url(self): self.storage.origin_add_one(self.origin) origin_url = self.origin['url'] origin_visit1 = self.storage.origin_visit_add(origin_url, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_url, self.date_visit2) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = self.storage.origin_visit_add(origin_url, self.date_visit2) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None self.assertIsNone(self.storage.snapshot_get_latest(origin_url)) # Add snapshot to visit1, latest snapshot = visit 1 snapshot self.storage.snapshot_add([self.complete_snapshot]) self.storage.origin_visit_update( origin_url, visit1_id, snapshot=self.complete_snapshot['id']) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_url)) # Status filter: both visits are status=ongoing, so no snapshot # returned self.assertIsNone( self.storage.snapshot_get_latest(origin_url, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_url, visit1_id, status='full') self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_url, allowed_statuses=['full']), ) # Add snapshot to visit2 and check that the new snapshot is returned self.storage.snapshot_add([self.empty_snapshot]) self.storage.origin_visit_update( origin_url, visit2_id, snapshot=self.empty_snapshot['id']) self.assertEqual(self.empty_snapshot, self.storage.snapshot_get_latest(origin_url)) # Check that the status filter is still working self.assertEqual( self.complete_snapshot, self.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 self.storage.snapshot_add([self.complete_snapshot]) self.storage.origin_visit_update( origin_url, visit3_id, snapshot=self.complete_snapshot['id']) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_url)) def test_snapshot_get_latest__missing_snapshot(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] # Two visits, both with no snapshot: latest snapshot is None self.assertIsNone(self.storage.snapshot_get_latest(origin_id)) # Add unknown snapshot to visit1, check that the inconsistency is # detected self.storage.origin_visit_update( origin_id, visit1_id, snapshot=self.complete_snapshot['id']) with self.assertRaises(ValueError): self.storage.snapshot_get_latest(origin_id) # Status filter: both visits are status=ongoing, so no snapshot # returned self.assertIsNone( self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_id, visit1_id, status='full') with self.assertRaises(ValueError): self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), # Actually add the snapshot and check status filter again self.storage.snapshot_add([self.complete_snapshot]) self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id) ) # Add unknown snapshot to visit2 and check that the inconsistency # is detected self.storage.origin_visit_update( origin_id, visit2_id, snapshot=self.snapshot['id']) with self.assertRaises(ValueError): self.storage.snapshot_get_latest(origin_id) # Actually add that snapshot and check that the new one is returned self.storage.snapshot_add([self.snapshot]) self.assertEqual( self.snapshot, self.storage.snapshot_get_latest(origin_id) ) def test_snapshot_get_latest__legacy_add(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None self.assertIsNone(self.storage.snapshot_get_latest(origin_id)) # Add snapshot to visit1, latest snapshot = visit 1 snapshot self.storage.snapshot_add(origin_id, visit1_id, self.complete_snapshot) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) # Status filter: both visits are status=ongoing, so no snapshot # returned self.assertIsNone( self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_id, visit1_id, status='full') self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit2 and check that the new snapshot is returned self.storage.snapshot_add(origin_id, visit2_id, self.empty_snapshot) self.assertEqual(self.empty_snapshot, self.storage.snapshot_get_latest(origin_id)) # Check that the status filter is still working self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned self.storage.snapshot_add(origin_id, visit3_id, self.complete_snapshot) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) def test_stat_counters(self): expected_keys = ['content', 'directory', 'origin', 'person', 'revision'] # Initially, all counters are 0 self.storage.refresh_stat_counters() counters = self.storage.stat_counters() self.assertTrue(set(expected_keys) <= set(counters)) for key in expected_keys: self.assertEqual(counters[key], 0) # Add a content. Only the content counter should increase. self.storage.content_add([self.cont]) self.storage.refresh_stat_counters() counters = self.storage.stat_counters() self.assertTrue(set(expected_keys) <= set(counters)) for key in expected_keys: if key != 'content': self.assertEqual(counters[key], 0) self.assertEqual(counters['content'], 1) # Add other objects. Check their counter increased as well. origin_id = self.storage.origin_add_one(self.origin2) origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) self.storage.snapshot_add(origin_id, origin_visit1['visit'], self.snapshot) self.storage.directory_add([self.dir]) self.storage.revision_add([self.revision]) self.storage.release_add([self.release]) self.storage.refresh_stat_counters() counters = self.storage.stat_counters() self.assertEqual(counters['content'], 1) self.assertEqual(counters['directory'], 1) self.assertEqual(counters['snapshot'], 1) self.assertEqual(counters['origin'], 1) self.assertEqual(counters['origin_visit'], 1) self.assertEqual(counters['revision'], 1) self.assertEqual(counters['release'], 1) self.assertEqual(counters['snapshot'], 1) self.assertEqual(counters['person'], 3) def test_content_find_ctime(self): cont = self.cont.copy() del cont['data'] now = datetime.datetime.now(tz=datetime.timezone.utc) cont['ctime'] = now self.storage.content_add_metadata([cont]) actually_present = self.storage.content_find({'sha1': cont['sha1']}) self.assertEqual(actually_present[0], { 'ctime': now, '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): # 1. with something to find cont = self.cont self.storage.content_add([cont, self.cont2]) actually_present = self.storage.content_find( {'sha1': cont['sha1']} ) self.assertEqual(1, len(actually_present)) actually_present[0].pop('ctime') self.assertEqual(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 = self.storage.content_find( {'sha1_git': cont['sha1_git']}) self.assertEqual(1, len(actually_present)) actually_present[0].pop('ctime') self.assertEqual(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 = self.storage.content_find( {'sha256': cont['sha256']}) self.assertEqual(1, len(actually_present)) actually_present[0].pop('ctime') self.assertEqual(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 = self.storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) self.assertEqual(1, len(actually_present)) actually_present[0].pop('ctime') self.assertEqual(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): # 1. with something that does not exist missing_cont = self.missing_cont actually_present = self.storage.content_find( {'sha1': missing_cont['sha1']}) self.assertEqual(actually_present, []) # 2. with something that does not exist actually_present = self.storage.content_find( {'sha1_git': missing_cont['sha1_git']}) self.assertEqual(actually_present, []) # 3. with something that does not exist actually_present = self.storage.content_find( {'sha256': missing_cont['sha256']}) self.assertEqual(actually_present, []) def test_content_find_with_duplicate_input(self): cont1 = self.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 self.storage.content_add([cont1, duplicate_cont]) finder = {'blake2s256': duplicate_cont['blake2s256'], 'sha256': duplicate_cont['sha256']} actual_result = list(self.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 ] self.assertCountEqual(expected_result, actual_result) def test_content_find_with_duplicate_sha256(self): cont1 = self.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) blake2s256_array = bytearray(duplicate_cont['blake2s256']) blake2s256_array[0] += 1 duplicate_cont['blake2s256'] = bytes(blake2s256_array) self.storage.content_add([cont1, duplicate_cont]) finder = { 'sha256': duplicate_cont['sha256'] } actual_result = list(self.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 ] self.assertCountEqual(expected_result, actual_result) # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(self.storage.content_find(finder)) actual_result[0].pop('ctime') expected_result = [ duplicate_cont ] self.assertCountEqual(expected_result, actual_result) def test_content_find_with_duplicate_blake2s256(self): cont1 = self.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) self.storage.content_add([cont1, duplicate_cont]) finder = { 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(self.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 ] self.assertCountEqual(expected_result, actual_result) # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(self.storage.content_find(finder)) actual_result[0].pop('ctime') expected_result = [ duplicate_cont ] self.assertCountEqual(expected_result, actual_result) def test_content_find_bad_input(self): # 1. with bad input with self.assertRaises(ValueError): self.storage.content_find({}) # empty is bad # 2. with bad input with self.assertRaises(ValueError): self.storage.content_find( {'unknown-sha1': 'something'}) # not the right key def test_object_find_by_sha1_git(self): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } self.storage.content_add([self.cont]) sha1_gits.append(self.cont['sha1_git']) expected[self.cont['sha1_git']] = [{ 'sha1_git': self.cont['sha1_git'], 'type': 'content', 'id': self.cont['sha1'], }] self.storage.directory_add([self.dir]) sha1_gits.append(self.dir['id']) expected[self.dir['id']] = [{ 'sha1_git': self.dir['id'], 'type': 'directory', 'id': self.dir['id'], }] self.storage.revision_add([self.revision]) sha1_gits.append(self.revision['id']) expected[self.revision['id']] = [{ 'sha1_git': self.revision['id'], 'type': 'revision', 'id': self.revision['id'], }] self.storage.release_add([self.release]) sha1_gits.append(self.release['id']) expected[self.release['id']] = [{ 'sha1_git': self.release['id'], 'type': 'release', 'id': self.release['id'], }] ret = self.storage.object_find_by_sha1_git(sha1_gits) for val in ret.values(): for obj in val: del obj['object_id'] self.assertEqual(expected, ret) def test_tool_add(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) # does not exist # add it actual_tools = self.storage.tool_add([tool]) self.assertEqual(len(actual_tools), 1) actual_tool = actual_tools[0] self.assertIsNotNone(actual_tool) # now it exists new_id = actual_tool.pop('id') self.assertEqual(actual_tool, tool) actual_tools2 = self.storage.tool_add([tool]) actual_tool2 = actual_tools2[0] self.assertIsNotNone(actual_tool2) # now it exists new_id2 = actual_tool2.pop('id') self.assertEqual(new_id, new_id2) self.assertEqual(actual_tool, actual_tool2) def test_tool_add_multiple(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(self.storage.tool_add([tool])) self.assertEqual(len(actual_tools), 1) new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = self.storage.tool_add(new_tools) self.assertEqual(len(actual_tools), 2) # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') self.assertIsNotNone(_id) self.assertIn(tool, new_tools) def test_tool_get_missing(self): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) def test_tool_metadata_get_missing_context(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) def test_tool_metadata_get(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } tools = self.storage.tool_add([tool]) expected_tool = tools[0] # when actual_tool = self.storage.tool_get(tool) # then self.assertEqual(expected_tool, actual_tool) def test_metadata_provider_get(self): # given no_provider = self.storage.metadata_provider_get(6459456445615) self.assertIsNone(no_provider) # when provider_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) actual_provider = self.storage.metadata_provider_get(provider_id) expected_provider = { 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] } # then del actual_provider['id'] self.assertTrue(actual_provider, expected_provider) def test_metadata_provider_get_by(self): # given no_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.assertIsNone(no_provider) # when provider_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) actual_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) # then self.assertTrue(provider_id, actual_provider['id']) def test_origin_metadata_add(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_metadata0 = list(self.storage.origin_metadata_get_by(origin_id)) self.assertTrue(len(origin_metadata0) == 0) tools = self.storage.tool_add([self.metadata_tool]) tool = tools[0] self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) # when adding for the same origin 2 metadatas self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) self.storage.origin_metadata_add( origin_id, '2015-01-01 23:00:00+00', provider['id'], tool['id'], self.origin_metadata2['metadata']) actual_om = list(self.storage.origin_metadata_get_by(origin_id)) # then self.assertCountEqual( [item['origin_id'] for item in actual_om], [origin_id, origin_id]) def test_origin_metadata_get(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_id2 = self.storage.origin_add([self.origin2])[0]['id'] self.storage.metadata_provider_add(self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) tool = self.storage.tool_add([self.metadata_tool])[0] # when adding for the same origin 2 metadatas self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) self.storage.origin_metadata_add( origin_id, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) all_metadatas = list(self.storage.origin_metadata_get_by(origin_id)) metadatas_for_origin2 = list(self.storage.origin_metadata_get_by( origin_id2)) expected_results = [{ 'origin_id': origin_id, 'discovery_date': datetime.datetime( 2017, 1, 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_id': origin_id, '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'] }] # then self.assertEqual(len(all_metadatas), 2) self.assertEqual(len(metadatas_for_origin2), 1) self.assertCountEqual(all_metadatas, expected_results) def test_metadata_provider_add(self): 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 = self.storage.metadata_provider_add( **provider) self.assertEqual( provider, self.storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' })) self.assertEqual( provider, self.storage.metadata_provider_get(provider_id)) def test_origin_metadata_get_by_provider_type(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_id2 = self.storage.origin_add([self.origin2])[0]['id'] provider1_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider1 = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.assertEqual(provider1, self.storage.metadata_provider_get(provider1_id)) provider2_id = self.storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = self.storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) self.assertEqual(provider2, self.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 = self.storage.tool_add([self.metadata_tool])[0] # when adding for the same origin 2 metadatas self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider1['id'], tool['id'], self.origin_metadata['metadata']) self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider2['id'], tool['id'], self.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(self.storage. origin_metadata_get_by( origin_id2, provider_type)) for item in m_by_provider: if 'id' in item: del item['id'] expected_results = [{ 'origin_id': origin_id2, '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 self.assertEqual(len(m_by_provider), 1) self.assertEqual(m_by_provider, expected_results) class CommonPropTestStorage: def assert_contents_ok(self, 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 = sorted([c[k] for c in expected_contents]) actual_list = sorted([c[k] for c in actual_contents]) self.assertEqual(actual_list, expected_list) @given(gen_contents(min_size=1, max_size=4)) def test_generate_content_get(self, contents): self.reset_storage_tables() # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents] # retrieve contents actual_contents = list(self.storage.content_get(get_sha1s)) self.assert_contents_ok(contents, actual_contents) @given(gen_contents(min_size=1, max_size=4)) def test_generate_content_get_metadata(self, contents): self.reset_storage_tables() # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents] # retrieve contents actual_contents = list(self.storage.content_get_metadata(get_sha1s)) self.assertEqual(len(actual_contents), len(contents)) # will check that all contents are retrieved correctly one_content = contents[0] # content_get_metadata does not return data keys_to_check = set(one_content.keys()) - {'data'} self.assert_contents_ok(contents, actual_contents, keys_to_check=keys_to_check) def test_generate_content_get_range_limit_none(self): """content_get_range call with wrong limit input should fail""" with self.assertRaises(ValueError) as e: self.storage.content_get_range(start=None, end=None, limit=None) self.assertEqual(e.exception.args, ( 'Development error: limit should not be None',)) @given(gen_contents(min_size=1, max_size=4)) def test_generate_content_get_range_no_limit(self, contents): """content_get_range returns contents within range provided""" self.reset_storage_tables() # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in contents]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = self.storage.content_get_range(start, end) actual_contents = actual_result['contents'] actual_next = actual_result['next'] self.assertEqual(len(contents), len(actual_contents)) self.assertIsNone(actual_next) one_content = contents[0] keys_to_check = set(one_content.keys()) - {'data'} self.assert_contents_ok(contents, actual_contents, keys_to_check) @given(gen_contents(min_size=4, max_size=4)) def test_generate_content_get_range_limit(self, contents): """content_get_range paginates results if limit exceeded""" self.reset_storage_tables() contents_map = {c['sha1']: c for c in contents} # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in contents]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to 3 results limited_results = len(contents) - 1 actual_result = self.storage.content_get_range(start, end, limit=limited_results) actual_contents = actual_result['contents'] actual_next = actual_result['next'] self.assertEqual(limited_results, len(actual_contents)) self.assertIsNotNone(actual_next) self.assertEqual(actual_next, get_sha1s[-1]) expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] keys_to_check = set(contents[0].keys()) - {'data'} self.assert_contents_ok(expected_contents, actual_contents, keys_to_check) # retrieve next part actual_results2 = self.storage.content_get_range(start=end, end=end) actual_contents2 = actual_results2['contents'] actual_next2 = actual_results2['next'] self.assertEqual(1, len(actual_contents2)) self.assertIsNone(actual_next2) self.assert_contents_ok([contents_map[actual_next]], actual_contents2, keys_to_check) def test_origin_get_invalid_id_legacy(self): invalid_origin_id = 1 origin_info = self.storage.origin_get({'id': invalid_origin_id}) self.assertIsNone(origin_info) origin_visits = list(self.storage.origin_visit_get( invalid_origin_id)) self.assertEqual(origin_visits, []) def test_origin_get_invalid_id(self): origin_info = self.storage.origin_get([{'id': 1}, {'id': 2}]) self.assertEqual(origin_info, [None, None]) origin_visits = list(self.storage.origin_visit_get(1)) self.assertEqual(origin_visits, []) @given(strategies.sets(origins().map(lambda x: tuple(x.to_dict().items())), min_size=6, max_size=15)) def test_origin_get_range(self, new_origins): self.reset_storage_tables() new_origins = list(map(dict, new_origins)) nb_origins = len(new_origins) self.storage.origin_add(new_origins) origin_from = random.randint(1, nb_origins-1) origin_count = random.randint(1, nb_origins - origin_from) actual_origins = list( self.storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) for origin in actual_origins: del origin['id'] for origin in actual_origins: self.assertIn(origin, new_origins) origin_from = -1 origin_count = 5 origins = list( self.storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) self.assertEqual(len(origins), origin_count) origin_from = 10000 origins = list( self.storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) self.assertEqual(len(origins), 0) def test_origin_count(self): new_origins = [ { 'type': 'git', 'url': 'https://github.com/user1/repo1' }, { 'type': 'git', 'url': 'https://github.com/user2/repo1' }, { 'type': 'git', 'url': 'https://github.com/user3/repo1' }, { 'type': 'git', 'url': 'https://gitlab.com/user1/repo1' }, { 'type': 'git', 'url': 'https://gitlab.com/user2/repo1' } ] self.storage.origin_add(new_origins) self.assertEqual(self.storage.origin_count('github'), 3) self.assertEqual(self.storage.origin_count('gitlab'), 2) self.assertEqual( self.storage.origin_count('.*user.*', regexp=True), 5) self.assertEqual( self.storage.origin_count('.*user.*', regexp=False), 0) self.assertEqual( self.storage.origin_count('.*user1.*', regexp=True), 2) self.assertEqual( self.storage.origin_count('.*user1.*', regexp=False), 0) @settings(suppress_health_check=[HealthCheck.too_slow]) @given(strategies.lists(objects(), max_size=2)) def test_add_arbitrary(self, objects): self.reset_storage_tables() for (obj_type, obj) in objects: obj = obj.to_dict() if obj_type == 'origin_visit': origin_id = self.storage.origin_add_one(obj.pop('origin')) if 'visit' in obj: del obj['visit'] self.storage.origin_visit_add(origin_id, **obj) else: method = getattr(self.storage, obj_type + '_add') try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage(CommonTestStorage, StorageTestDbFixture, unittest.TestCase): """Test the local storage""" # Can only be tested with local storage as you can't mock # datetimes for the remote server - def test_fetch_history(self): + @given(strategies.booleans()) + def test_fetch_history(self, use_url): origin = self.storage.origin_add_one(self.origin) + if use_url: + origin_id = self.origin['url'] + else: + origin_id = origin with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_date - fetch_history_id = self.storage.fetch_history_start(origin) + fetch_history_id = self.storage.fetch_history_start(origin_id) datetime.datetime.now.assert_called_with(tz=datetime.timezone.utc) with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_end self.storage.fetch_history_end(fetch_history_id, self.fetch_history_data) fetch_history = self.storage.fetch_history_get(fetch_history_id) expected_fetch_history = self.fetch_history_data.copy() expected_fetch_history['id'] = fetch_history_id expected_fetch_history['origin'] = origin expected_fetch_history['date'] = self.fetch_history_date expected_fetch_history['duration'] = self.fetch_history_duration self.assertEqual(expected_fetch_history, fetch_history) # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self): self.storage.objstorage.add = Mock( side_effect=Exception('mocked broken objstorage') ) with self.assertRaises(Exception) as e: self.storage.content_add([self.cont]) self.assertEqual(e.exception.args, ('mocked broken objstorage',)) missing = list(self.storage.content_missing([self.cont])) self.assertEqual(missing, [self.cont['sha1']]) @pytest.mark.db @pytest.mark.property_based class PropTestLocalStorage(CommonPropTestStorage, StorageTestDbFixture, unittest.TestCase): pass class AlteringSchemaTest(TestStorageData, StorageTestDbFixture, unittest.TestCase): """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update(self): self.storage.journal_writer = None # TODO, not supported cont = copy.deepcopy(self.cont) self.storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') self.storage.content_update([cont], keys=['sha1_git']) with self.storage.get_db().transaction() as cur: cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() self.assertEqual( (datum[0], datum[1], datum[2], datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) def test_content_update_with_new_cols(self): self.storage.journal_writer = None # TODO, not supported with self.storage.get_db().transaction() as cur: cur.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(self.cont2) self.storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' self.storage.content_update([cont], keys=['test', 'test2']) with self.storage.get_db().transaction() as cur: cur.execute( 'SELECT sha1, sha1_git, sha256, length, status, test, test2' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() self.assertEqual( (datum[0], datum[1], datum[2], datum[3], datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2'])) with self.storage.get_db().transaction() as cur: cur.execute("""alter table content drop column test, drop column test2""")