diff --git a/swh/storage/cassandra/converters.py b/swh/storage/cassandra/converters.py index abe96eac..595d78d7 100644 --- a/swh/storage/cassandra/converters.py +++ b/swh/storage/cassandra/converters.py @@ -1,63 +1,76 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy import json import attr +from typing import Dict + from swh.model.model import ( RevisionType, ObjectType, Revision, Release, ) - +from swh.model.hashutil import DEFAULT_ALGORITHMS from ..converters import git_headers_to_db, db_to_git_headers +from .common import Row def revision_to_db(revision: Revision) -> Revision: metadata = revision.metadata if metadata and 'extra_headers' in metadata: metadata = copy.deepcopy(metadata) metadata['extra_headers'] = git_headers_to_db( metadata['extra_headers']) revision = attr.evolve( revision, type=revision.type.value, metadata=json.dumps(metadata), ) return revision def revision_from_db(revision) -> Revision: metadata = json.loads(revision.metadata) if metadata and 'extra_headers' in metadata: extra_headers = db_to_git_headers( metadata['extra_headers']) metadata['extra_headers'] = extra_headers rev = attr.evolve( revision, type=RevisionType(revision.type), metadata=metadata, ) return rev def release_to_db(release: Release) -> Release: release = attr.evolve( release, target_type=release.target_type.value, ) return release def release_from_db(release: Release) -> Release: release = attr.evolve( release, target_type=ObjectType(release.target_type), ) return release + + +def row_to_content_hashes(row: Row) -> Dict[str, bytes]: + """Convert cassandra row to a content hashes + + """ + hashes = {} + for algo in DEFAULT_ALGORITHMS: + hashes[algo] = getattr(row, algo) + return hashes diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py index 27b945f2..b6451d36 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,953 +1,958 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import json import random import re from typing import Any, Dict, List, Iterable, Optional, Union import uuid import attr import dateutil from swh.model.model import ( Revision, Release, Directory, DirectoryEntry, Content, SkippedContent, OriginVisit, Snapshot, Origin ) from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.storage.objstorage import ObjStorage from swh.storage.writer import JournalWriter from .. import HashCollision from ..exc import StorageArgumentException from .common import TOKEN_BEGIN, TOKEN_END from .converters import ( revision_to_db, revision_from_db, release_to_db, release_from_db, + row_to_content_hashes, ) from .cql import CqlRunner from .schema import HASH_ALGORITHMS # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 def now(): return datetime.datetime.now(tz=datetime.timezone.utc) class CassandraStorage: def __init__(self, hosts, keyspace, objstorage, port=9042, journal_writer=None): self._cql_runner = CqlRunner(hosts, keyspace, port) self.journal_writer = JournalWriter(journal_writer) self.objstorage = ObjStorage(objstorage) def check_config(self, *, check_write): self._cql_runner.check_read() return True def _content_add(self, contents: List[Content], with_data: bool) -> Dict: # Filter-out content already in the database. contents = [c for c in contents if not self._cql_runner.content_get_from_pk(c.to_dict())] self.journal_writer.content_add(contents) if with_data: # First insert to the objstorage, if the endpoint is # `content_add` (as opposed to `content_add_metadata`). # TODO: this should probably be done in concurrently to inserting # in index tables (but still before the main table; so an entry is # only added to the main table after everything else was # successfully inserted. summary = self.objstorage.content_add( c for c in contents if c.status != 'absent') content_add_bytes = summary['content:add:bytes'] content_add = 0 for content in contents: content_add += 1 # Then add to index tables for algo in HASH_ALGORITHMS: self._cql_runner.content_index_add_one(algo, content) # Then to the main table self._cql_runner.content_add_one(content) # Note that we check for collisions *after* inserting. This # differs significantly from the pgsql storage, but checking # before insertion does not provide any guarantee in case # another thread inserts the colliding hash at the same time. # # The proper way to do it would probably be a BATCH, but this # would be inefficient because of the number of partitions we # need to affect (len(HASH_ALGORITHMS)+1, which is currently 5) for algo in {'sha1', 'sha1_git'}: pks = self._cql_runner.content_get_pks_from_single_hash( algo, content.get_hash(algo)) if len(pks) > 1: # There are more than the one we just inserted. - raise HashCollision(algo, content.get_hash(algo), pks) + colliding_content_hashes = [ + row_to_content_hashes(pk) for pk in pks + ] + raise HashCollision( + algo, content.get_hash(algo), colliding_content_hashes) summary = { 'content:add': content_add, } if with_data: summary['content:add:bytes'] = content_add_bytes return summary def content_add(self, content: Iterable[Content]) -> Dict: now = datetime.datetime.now(tz=datetime.timezone.utc) contents = [attr.evolve(c, ctime=now) for c in content] return self._content_add(list(contents), with_data=True) def content_update(self, content, keys=[]): raise NotImplementedError( 'content_update is not supported by the Cassandra backend') def content_add_metadata(self, content: Iterable[Content]) -> Dict: return self._content_add(list(content), with_data=False) def content_get(self, content): if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) yield from self.objstorage.content_get(content) def content_get_partition( self, partition_id: int, nb_partitions: int, limit: int = 1000, page_token: str = None): if limit is None: raise StorageArgumentException('limit should not be None') # Compute start and end of the range of tokens covered by the # requested partition partition_size = (TOKEN_END-TOKEN_BEGIN)//nb_partitions range_start = TOKEN_BEGIN + partition_id*partition_size range_end = TOKEN_BEGIN + (partition_id+1)*partition_size # offset the range start according to the `page_token`. if page_token is not None: if not (range_start <= int(page_token) <= range_end): raise StorageArgumentException('Invalid page_token.') range_start = int(page_token) # Get the first rows of the range rows = self._cql_runner.content_get_token_range( range_start, range_end, limit) rows = list(rows) if len(rows) == limit: next_page_token: Optional[str] = str(rows[-1].tok+1) else: next_page_token = None return { 'contents': [row._asdict() for row in rows if row.status != 'absent'], 'next_page_token': next_page_token, } def content_get_metadata( self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: result: Dict[bytes, List[Dict]] = {sha1: [] for sha1 in contents} for sha1 in contents: # Get all (sha1, sha1_git, sha256, blake2s256) whose sha1 # matches the argument, from the index table ('content_by_sha1') pks = self._cql_runner.content_get_pks_from_single_hash( 'sha1', sha1) if pks: # TODO: what to do if there are more than one? pk = pks[0] # Query the main table ('content') res = self._cql_runner.content_get_from_pk(pk._asdict()) # Rows in 'content' are inserted after corresponding # rows in 'content_by_*', so we might be missing it if res: content_metadata = res._asdict() content_metadata.pop('ctime') result[content_metadata['sha1']].append(content_metadata) return result def content_find(self, content): # Find an algorithm that is common to all the requested contents. # It will be used to do an initial filtering efficiently. filter_algos = list(set(content).intersection(HASH_ALGORITHMS)) if not filter_algos: raise StorageArgumentException( 'content keys must contain at least one of: ' '%s' % ', '.join(sorted(HASH_ALGORITHMS))) common_algo = filter_algos[0] # Find all contents whose common_algo matches at least one # of the requests. found_pks = self._cql_runner.content_get_pks_from_single_hash( common_algo, content[common_algo]) found_pks = [pk._asdict() for pk in found_pks] # Filter with the other hash algorithms. for algo in filter_algos[1:]: found_pks = [pk for pk in found_pks if pk[algo] == content[algo]] results = [] for pk in found_pks: # Query the main table ('content'). res = self._cql_runner.content_get_from_pk(pk) # Rows in 'content' are inserted after corresponding # rows in 'content_by_*', so we might be missing it if res: results.append({ **res._asdict(), 'ctime': res.ctime.replace(tzinfo=datetime.timezone.utc) }) return results def content_missing(self, content, key_hash='sha1'): for cont in content: res = self.content_find(cont) if not res: yield cont[key_hash] if any(c['status'] == 'missing' for c in res): yield cont[key_hash] def content_missing_per_sha1(self, contents): return self.content_missing([{'sha1': c for c in contents}]) def content_missing_per_sha1_git(self, contents): return self.content_missing([{'sha1_git': c for c in contents}], key_hash='sha1_git') def content_get_random(self): return self._cql_runner.content_get_random().sha1_git def _skipped_content_add(self, contents: Iterable[SkippedContent]) -> Dict: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.skipped_content_get_from_pk(c.to_dict())] self.journal_writer.skipped_content_add(contents) for content in contents: # Add to index tables for algo in HASH_ALGORITHMS: if content.get_hash(algo) is not None: self._cql_runner.skipped_content_index_add_one( algo, content) # Then to the main table self._cql_runner.skipped_content_add_one(content) return { 'skipped_content:add': len(contents) } def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: now = datetime.datetime.now(tz=datetime.timezone.utc) contents = [attr.evolve(c, ctime=now) for c in content] return self._skipped_content_add(contents) def skipped_content_missing(self, contents): for content in contents: if not self._cql_runner.skipped_content_get_from_pk(content): yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} def directory_add(self, directories: Iterable[Directory]) -> Dict: directories = list(directories) # Filter out directories that are already inserted. missing = self.directory_missing([dir_.id for dir_ in directories]) directories = [dir_ for dir_ in directories if dir_.id in missing] self.journal_writer.directory_add(directories) for directory in directories: # Add directory entries to the 'directory_entry' table for entry in directory.entries: self._cql_runner.directory_entry_add_one({ **entry.to_dict(), 'directory_id': directory.id }) # Add the directory *after* adding all the entries, so someone # calling snapshot_get_branch in the meantime won't end up # with half the entries. self._cql_runner.directory_add_one(directory.id) return {'directory:add': len(missing)} def directory_missing(self, directories): return self._cql_runner.directory_missing(directories) def _join_dentry_to_content(self, dentry): keys = ( 'status', 'sha1', 'sha1_git', 'sha256', 'length', ) ret = dict.fromkeys(keys) ret.update(dentry.to_dict()) if ret['type'] == 'file': content = self.content_find({'sha1_git': ret['target']}) if content: content = content[0] for key in keys: ret[key] = content[key] return ret def _directory_ls(self, directory_id, recursive, prefix=b''): if self.directory_missing([directory_id]): return rows = list(self._cql_runner.directory_entry_get([directory_id])) for row in rows: # Build and yield the directory entry dict entry = row._asdict() del entry['directory_id'] entry = DirectoryEntry.from_dict(entry) ret = self._join_dentry_to_content(entry) ret['name'] = prefix + ret['name'] ret['dir_id'] = directory_id yield ret if recursive and ret['type'] == 'dir': yield from self._directory_ls( ret['target'], True, prefix + ret['name'] + b'/') def directory_entry_get_by_path(self, directory, paths): return self._directory_entry_get_by_path(directory, paths, b'') def _directory_entry_get_by_path(self, directory, paths, prefix): if not paths: return contents = list(self.directory_ls(directory)) if not contents: return def _get_entry(entries, name): """Finds the entry with the requested name, prepends the prefix (to get its full path), and returns it. If no entry has that name, returns None.""" for entry in entries: if entry['name'] == name: entry = entry.copy() entry['name'] = prefix + entry['name'] return entry first_item = _get_entry(contents, paths[0]) if len(paths) == 1: return first_item if not first_item or first_item['type'] != 'dir': return return self._directory_entry_get_by_path( first_item['target'], paths[1:], prefix + paths[0] + b'/') def directory_ls(self, directory, recursive=False): yield from self._directory_ls(directory, recursive) def directory_get_random(self): return self._cql_runner.directory_get_random().id def revision_add(self, revisions: Iterable[Revision]) -> Dict: revisions = list(revisions) # Filter-out revisions already in the database missing = self.revision_missing([rev.id for rev in revisions]) revisions = [rev for rev in revisions if rev.id in missing] self.journal_writer.revision_add(revisions) for revision in revisions: revision = revision_to_db(revision) if revision: # Add parents first for (rank, parent) in enumerate(revision.parents): self._cql_runner.revision_parent_add_one( revision.id, rank, parent) # Then write the main revision row. # Writing this after all parents were written ensures that # read endpoints don't return a partial view while writing # the parents self._cql_runner.revision_add_one(revision) return {'revision:add': len(revisions)} def revision_missing(self, revisions): return self._cql_runner.revision_missing(revisions) def revision_get(self, revisions): rows = self._cql_runner.revision_get(revisions) revs = {} for row in rows: # TODO: use a single query to get all parents? # (it might have lower latency, but requires more code and more # bandwidth, because revision id would be part of each returned # row) parent_rows = self._cql_runner.revision_parent_get(row.id) # parent_rank is the clustering key, so results are already # sorted by rank. parents = [row.parent_id for row in parent_rows] rev = Revision(**row._asdict(), parents=parents) rev = revision_from_db(rev) revs[rev.id] = rev.to_dict() for rev_id in revisions: yield revs.get(rev_id) def _get_parent_revs(self, rev_ids, seen, limit, short): if limit and len(seen) >= limit: return rev_ids = [id_ for id_ in rev_ids if id_ not in seen] if not rev_ids: return seen |= set(rev_ids) # We need this query, even if short=True, to return consistent # results (ie. not return only a subset of a revision's parents # if it is being written) if short: rows = self._cql_runner.revision_get_ids(rev_ids) else: rows = self._cql_runner.revision_get(rev_ids) for row in rows: # TODO: use a single query to get all parents? # (it might have less latency, but requires less code and more # bandwidth (because revision id would be part of each returned # row) parent_rows = self._cql_runner.revision_parent_get(row.id) # parent_rank is the clustering key, so results are already # sorted by rank. parents = [row.parent_id for row in parent_rows] if short: yield (row.id, parents) else: rev = revision_from_db(Revision( **row._asdict(), parents=parents)) yield rev.to_dict() yield from self._get_parent_revs(parents, seen, limit, short) def revision_log(self, revisions, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, False) def revision_shortlog(self, revisions, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, True) def revision_get_random(self): return self._cql_runner.revision_get_random().id def release_add(self, releases: Iterable[Release]) -> Dict: missing = self.release_missing([rel.id for rel in releases]) releases = [rel for rel in releases if rel.id in missing] self.journal_writer.release_add(releases) for release in releases: if release: release = release_to_db(release) self._cql_runner.release_add_one(release) return {'release:add': len(missing)} def release_missing(self, releases): return self._cql_runner.release_missing(releases) def release_get(self, releases): rows = self._cql_runner.release_get(releases) rels = {} for row in rows: release = Release(**row._asdict()) release = release_from_db(release) rels[row.id] = release.to_dict() for rel_id in releases: yield rels.get(rel_id) def release_get_random(self): return self._cql_runner.release_get_random().id def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: missing = self._cql_runner.snapshot_missing( [snp.id for snp in snapshots]) snapshots = [snp for snp in snapshots if snp.id in missing] for snapshot in snapshots: self.journal_writer.snapshot_add(snapshot) # Add branches for (branch_name, branch) in snapshot.branches.items(): if branch is None: target_type = None target = None else: target_type = branch.target_type.value target = branch.target self._cql_runner.snapshot_branch_add_one({ 'snapshot_id': snapshot.id, 'name': branch_name, 'target_type': target_type, 'target': target, }) # Add the snapshot *after* adding all the branches, so someone # calling snapshot_get_branch in the meantime won't end up # with half the branches. self._cql_runner.snapshot_add_one(snapshot.id) return {'snapshot:add': len(snapshots)} def snapshot_missing(self, snapshots): return self._cql_runner.snapshot_missing(snapshots) def snapshot_get(self, snapshot_id): return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): try: visit = self._cql_runner.origin_visit_get_one(origin, visit) except IndexError: return None return self.snapshot_get(visit.snapshot) def snapshot_get_latest(self, origin, allowed_statuses=None): visit = self.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=True) if visit: assert visit['snapshot'] if self._cql_runner.snapshot_missing([visit['snapshot']]): raise StorageArgumentException( 'Visit references unknown snapshot') return self.snapshot_get_branches(visit['snapshot']) def snapshot_count_branches(self, snapshot_id): if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None rows = list(self._cql_runner.snapshot_count_branches(snapshot_id)) assert len(rows) == 1 (nb_none, counts) = rows[0].counts counts = dict(counts) if nb_none: counts[None] = nb_none return counts def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None): if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None branches = [] while len(branches) < branches_count+1: new_branches = list(self._cql_runner.snapshot_branch_get( snapshot_id, branches_from, branches_count+1)) if not new_branches: break branches_from = new_branches[-1].name new_branches_filtered = new_branches # Filter by target_type if target_types: new_branches_filtered = [ branch for branch in new_branches_filtered if branch.target is not None and branch.target_type in target_types] branches.extend(new_branches_filtered) if len(new_branches) < branches_count+1: break if len(branches) > branches_count: last_branch = branches.pop(-1).name else: last_branch = None branches = { branch.name: { 'target': branch.target, 'target_type': branch.target_type, } if branch.target else None for branch in branches } return { 'id': snapshot_id, 'branches': branches, 'next_branch': last_branch, } def snapshot_get_random(self): return self._cql_runner.snapshot_get_random().id def object_find_by_sha1_git(self, ids): results = {id_: [] for id_ in ids} missing_ids = set(ids) # Mind the order, revision is the most likely one for a given ID, # so we check revisions first. queries = [ ('revision', self._cql_runner.revision_missing), ('release', self._cql_runner.release_missing), ('content', self._cql_runner.content_missing_by_sha1_git), ('directory', self._cql_runner.directory_missing), ] for (object_type, query_fn) in queries: found_ids = missing_ids - set(query_fn(missing_ids)) for sha1_git in found_ids: results[sha1_git].append({ 'sha1_git': sha1_git, 'type': object_type, }) missing_ids.remove(sha1_git) if not missing_ids: # We found everything, skipping the next queries. break return results def origin_get(self, origins): if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False if any('id' in origin for origin in origins): raise StorageArgumentException('Origin ids are not supported.') results = [self.origin_get_one(origin) for origin in origins] if return_single: assert len(results) == 1 return results[0] else: return results def origin_get_one(self, origin): if 'id' in origin: raise StorageArgumentException('Origin ids are not supported.') if 'url' not in origin: raise StorageArgumentException('Missing origin url') rows = self._cql_runner.origin_get_by_url(origin['url']) rows = list(rows) if rows: assert len(rows) == 1 result = rows[0]._asdict() return { 'url': result['url'], } else: return None def origin_get_by_sha1(self, sha1s): results = [] for sha1 in sha1s: rows = self._cql_runner.origin_get_by_sha1(sha1) if rows: results.append({'url': rows.one().url}) else: results.append(None) return results def origin_list(self, page_token: Optional[str] = None, limit: int = 100 ) -> dict: # Compute what token to begin the listing from start_token = TOKEN_BEGIN if page_token: start_token = int(page_token) if not (TOKEN_BEGIN <= start_token <= TOKEN_END): raise StorageArgumentException('Invalid page_token.') rows = self._cql_runner.origin_list(start_token, limit) rows = list(rows) if len(rows) == limit: next_page_token: Optional[str] = str(rows[-1].tok+1) else: next_page_token = None return { 'origins': [{'url': row.url} for row in rows], 'next_page_token': next_page_token, } def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False): # TODO: remove this endpoint, swh-search should be used instead. origins = self._cql_runner.origin_iter_all() if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.search(orig.url)] else: origins = [orig for orig in origins if url_pattern in orig.url] if with_visit: origins = [orig for orig in origins if orig.next_visit_id > 1] return [ { 'url': orig.url, } for orig in origins[offset:offset+limit]] def origin_add(self, origins: Iterable[Origin]) -> List[Dict]: results = [] for origin in origins: self.origin_add_one(origin) results.append(origin.to_dict()) return results def origin_add_one(self, origin: Origin) -> str: known_origin = self.origin_get_one(origin.to_dict()) if known_origin: origin_url = known_origin['url'] else: self.journal_writer.origin_add_one(origin) self._cql_runner.origin_add_one(origin) origin_url = origin.url return origin_url def origin_visit_add( self, origin, date, type) -> Optional[Dict[str, Union[str, int]]]: origin_url = origin # TODO: rename the argument if isinstance(date, str): date = dateutil.parser.parse(date) origin = self.origin_get_one({'url': origin_url}) if not origin: return None visit_id = self._cql_runner.origin_generate_unique_visit_id(origin_url) try: visit = OriginVisit.from_dict({ 'origin': origin_url, 'date': date, 'type': type, 'status': 'ongoing', 'snapshot': None, 'metadata': None, 'visit': visit_id }) except (KeyError, TypeError, ValueError) as e: raise StorageArgumentException(*e.args) self.journal_writer.origin_visit_add(visit) self._cql_runner.origin_visit_add_one(visit) return { 'origin': origin_url, 'visit': visit_id, } def origin_visit_update( self, origin: str, visit_id: int, status: Optional[str] = None, metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None): origin_url = origin # TODO: rename the argument # Get the existing data of the visit row = self._cql_runner.origin_visit_get_one(origin_url, visit_id) if not row: raise StorageArgumentException('This origin visit does not exist.') try: visit = OriginVisit.from_dict(self._format_origin_visit_row(row)) except (KeyError, TypeError, ValueError) as e: raise StorageArgumentException(*e.args) updates: Dict[str, Any] = {} if status: updates['status'] = status if metadata: updates['metadata'] = metadata if snapshot: updates['snapshot'] = snapshot try: visit = attr.evolve(visit, **updates) except (KeyError, TypeError, ValueError) as e: raise StorageArgumentException(*e.args) self.journal_writer.origin_visit_update(visit) self._cql_runner.origin_visit_update(origin_url, visit_id, updates) def origin_visit_upsert(self, visits): visits = [visit.copy() for visit in visits] for visit in visits: if isinstance(visit['date'], str): visit['date'] = dateutil.parser.parse(visit['date']) self.journal_writer.origin_visit_upsert(visits) for visit in visits: visit = visit.copy() if visit.get('metadata'): visit['metadata'] = json.dumps(visit['metadata']) self._cql_runner.origin_visit_upsert(visit) @staticmethod def _format_origin_visit_row(visit): return { **visit._asdict(), 'origin': visit.origin, 'date': visit.date.replace(tzinfo=datetime.timezone.utc), 'metadata': (json.loads(visit.metadata) if visit.metadata else None), } def origin_visit_get(self, origin, last_visit=None, limit=None): rows = self._cql_runner.origin_visit_get(origin, last_visit, limit) yield from map(self._format_origin_visit_row, rows) def origin_visit_find_by_date(self, origin, visit_date): # Iterator over all the visits of the origin # This should be ok for now, as there aren't too many visits # per origin. visits = list(self._cql_runner.origin_visit_get_all(origin)) def key(visit): dt = visit.date.replace(tzinfo=datetime.timezone.utc) - visit_date return (abs(dt), -visit.visit) if visits: visit = min(visits, key=key) return visit._asdict() def origin_visit_get_by(self, origin, visit): visit = self._cql_runner.origin_visit_get_one(origin, visit) if visit: return self._format_origin_visit_row(visit) def origin_visit_get_latest( self, origin, allowed_statuses=None, require_snapshot=False): visit = self._cql_runner.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot) if visit: return self._format_origin_visit_row(visit) def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: back_in_the_day = now() - datetime.timedelta(weeks=12) # 3 months back # Random position to start iteration at start_token = random.randint(TOKEN_BEGIN, TOKEN_END) # Iterator over all visits, ordered by token(origins) then visit_id rows = self._cql_runner.origin_visit_iter(start_token) for row in rows: visit = self._format_origin_visit_row(row) if visit['date'] > back_in_the_day \ and visit['status'] == 'full': return visit else: return None def tool_add(self, tools): inserted = [] for tool in tools: tool = tool.copy() tool_json = tool.copy() tool_json['configuration'] = json.dumps( tool['configuration'], sort_keys=True).encode() id_ = self._cql_runner.tool_get_one_uuid(**tool_json) if not id_: id_ = uuid.uuid1() tool_json['id'] = id_ self._cql_runner.tool_by_uuid_add_one(tool_json) self._cql_runner.tool_add_one(tool_json) tool['id'] = id_ inserted.append(tool) return inserted def tool_get(self, tool): id_ = self._cql_runner.tool_get_one_uuid( tool['name'], tool['version'], json.dumps(tool['configuration'], sort_keys=True).encode()) if id_: tool = tool.copy() tool['id'] = id_ return tool else: return None def stat_counters(self): rows = self._cql_runner.stat_counters() keys = ( 'content', 'directory', 'origin', 'origin_visit', 'release', 'revision', 'skipped_content', 'snapshot') stats = {key: 0 for key in keys} stats.update({row.object_type: row.count for row in rows}) return stats def refresh_stat_counters(self): pass def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): # TODO raise NotImplementedError('not yet supported for Cassandra') def origin_metadata_get_by(self, origin_url, provider_type=None): # TODO raise NotImplementedError('not yet supported for Cassandra') def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata): # TODO raise NotImplementedError('not yet supported for Cassandra') def metadata_provider_get(self, provider_id): # TODO raise NotImplementedError('not yet supported for Cassandra') def metadata_provider_get_by(self, provider): # TODO raise NotImplementedError('not yet supported for Cassandra') diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py index 5c2aacd3..eb4b92ac 100644 --- a/swh/storage/in_memory.py +++ b/swh/storage/in_memory.py @@ -1,1001 +1,1010 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import re import bisect import dateutil import collections import copy import datetime import itertools import random from collections import defaultdict from datetime import timedelta from typing import Any, Dict, Iterable, List, Optional, Union import attr from swh.model.model import ( BaseContent, Content, SkippedContent, Directory, Revision, Release, Snapshot, OriginVisit, Origin, SHA1_SIZE) from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.storage.objstorage import ObjStorage from . import HashCollision from .exc import StorageArgumentException from .converters import origin_url_to_sha1 from .utils import get_partition_bounds_bytes from .writer import JournalWriter # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 def now(): return datetime.datetime.now(tz=datetime.timezone.utc) class InMemoryStorage: def __init__(self, journal_writer=None): self.reset() self.journal_writer = JournalWriter(journal_writer) def reset(self): self._contents = {} self._content_indexes = defaultdict(lambda: defaultdict(set)) self._skipped_contents = {} self._skipped_content_indexes = defaultdict(lambda: defaultdict(set)) self._directories = {} self._revisions = {} self._releases = {} self._snapshots = {} self._origins = {} self._origins_by_id = [] self._origins_by_sha1 = {} self._origin_visits = {} self._persons = [] self._origin_metadata = defaultdict(list) self._tools = {} self._metadata_providers = {} self._objects = defaultdict(list) # ideally we would want a skip list for both fast inserts and searches self._sorted_sha1s = [] self.objstorage = ObjStorage({'cls': 'memory', 'args': {}}) def check_config(self, *, check_write): return True def _content_add( self, contents: Iterable[Content], with_data: bool) -> Dict: self.journal_writer.content_add(contents) content_add = 0 content_add_bytes = 0 if with_data: summary = self.objstorage.content_add( c for c in contents if c.status != 'absent') content_add_bytes = summary['content:add:bytes'] for content in contents: key = self._content_key(content) if key in self._contents: continue for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) if hash_ in self._content_indexes[algorithm]\ and (algorithm not in {'blake2s256', 'sha256'}): - raise HashCollision(algorithm, hash_, key) + colliding_content_hashes = [] + # Add the already stored contents + for content_hashes_set in self._content_indexes[ + algorithm][hash_]: + hashes = dict(content_hashes_set) + colliding_content_hashes.append(hashes) + # Add the new colliding content + colliding_content_hashes.append(content.hashes()) + raise HashCollision( + algorithm, hash_, colliding_content_hashes) for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(key) self._objects[content.sha1_git].append( ('content', content.sha1)) self._contents[key] = content bisect.insort(self._sorted_sha1s, content.sha1) self._contents[key] = attr.evolve( self._contents[key], data=None) content_add += 1 summary = { 'content:add': content_add, } if with_data: summary['content:add:bytes'] = content_add_bytes return summary def content_add(self, content: Iterable[Content]) -> Dict: now = datetime.datetime.now(tz=datetime.timezone.utc) content = [attr.evolve(c, ctime=now) for c in content] return self._content_add(content, with_data=True) def content_update(self, content, keys=[]): self.journal_writer.content_update(content) for cont_update in content: cont_update = cont_update.copy() sha1 = cont_update.pop('sha1') for old_key in self._content_indexes['sha1'][sha1]: old_cont = self._contents.pop(old_key) for algorithm in DEFAULT_ALGORITHMS: hash_ = old_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].remove(old_key) new_cont = attr.evolve(old_cont, **cont_update) new_key = self._content_key(new_cont) self._contents[new_key] = new_cont for algorithm in DEFAULT_ALGORITHMS: hash_ = new_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(new_key) def content_add_metadata(self, content: Iterable[Content]) -> Dict: return self._content_add(content, with_data=False) def content_get(self, content): # FIXME: Make this method support slicing the `data`. if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) yield from self.objstorage.content_get(content) def content_get_range(self, start, end, limit=1000): if limit is None: raise StorageArgumentException('limit should not be None') from_index = bisect.bisect_left(self._sorted_sha1s, start) sha1s = itertools.islice(self._sorted_sha1s, from_index, None) sha1s = ((sha1, content_key) for sha1 in sha1s for content_key in self._content_indexes['sha1'][sha1]) matched = [] next_content = None for sha1, key in sha1s: if sha1 > end: break if len(matched) >= limit: next_content = sha1 break matched.append(self._contents[key].to_dict()) return { 'contents': matched, 'next': next_content, } def content_get_partition( self, partition_id: int, nb_partitions: int, limit: int = 1000, page_token: str = None): if limit is None: raise StorageArgumentException('limit should not be None') (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE) if page_token: start = hash_to_bytes(page_token) if end is None: end = b'\xff'*SHA1_SIZE result = self.content_get_range(start, end, limit) result2 = { 'contents': result['contents'], 'next_page_token': None, } if result['next']: result2['next_page_token'] = hash_to_hex(result['next']) return result2 def content_get_metadata( self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: result: Dict = {sha1: [] for sha1 in contents} for sha1 in contents: if sha1 in self._content_indexes['sha1']: objs = self._content_indexes['sha1'][sha1] # only 1 element as content_add_metadata would have raised a # hash collision otherwise for key in objs: d = self._contents[key].to_dict() del d['ctime'] if 'data' in d: del d['data'] result[sha1].append(d) return result def content_find(self, content): if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( 'content keys must contain at least one of: %s' % ', '.join(sorted(DEFAULT_ALGORITHMS))) found = [] for algo in DEFAULT_ALGORITHMS: hash = content.get(algo) if hash and hash in self._content_indexes[algo]: found.append(self._content_indexes[algo][hash]) if not found: return [] keys = list(set.intersection(*found)) return [self._contents[key].to_dict() for key in keys] def content_missing(self, content, key_hash='sha1'): for cont in content: for (algo, hash_) in cont.items(): if algo not in DEFAULT_ALGORITHMS: continue if hash_ not in self._content_indexes.get(algo, []): yield cont[key_hash] break else: for result in self.content_find(cont): if result['status'] == 'missing': yield cont[key_hash] def content_missing_per_sha1(self, contents): for content in contents: if content not in self._content_indexes['sha1']: yield content def content_missing_per_sha1_git(self, contents): for content in contents: if content not in self._content_indexes['sha1_git']: yield content def content_get_random(self): return random.choice(list(self._content_indexes['sha1_git'])) def _skipped_content_add(self, contents: List[SkippedContent]) -> Dict: self.journal_writer.skipped_content_add(contents) summary = { 'skipped_content:add': 0 } missing_contents = self.skipped_content_missing( [c.hashes() for c in contents]) missing = {self._content_key(c) for c in missing_contents} contents = [c for c in contents if self._content_key(c) in missing] for content in contents: key = self._content_key(content) for algo in DEFAULT_ALGORITHMS: if content.get_hash(algo): self._skipped_content_indexes[algo][ content.get_hash(algo)].add(key) self._skipped_contents[key] = content summary['skipped_content:add'] += 1 return summary def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: now = datetime.datetime.now(tz=datetime.timezone.utc) content = [attr.evolve(c, ctime=now) for c in content] return self._skipped_content_add(content) def skipped_content_missing(self, contents): for content in contents: matches = list(self._skipped_contents.values()) for (algorithm, key) in self._content_key(content): if algorithm == 'blake2s256': continue # Filter out skipped contents with the same hash matches = [ match for match in matches if match.get_hash(algorithm) == key] # if none of the contents match if not matches: yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} def directory_add(self, directories: Iterable[Directory]) -> Dict: directories = [dir_ for dir_ in directories if dir_.id not in self._directories] self.journal_writer.directory_add(directories) count = 0 for directory in directories: count += 1 self._directories[directory.id] = directory self._objects[directory.id].append( ('directory', directory.id)) return {'directory:add': count} def directory_missing(self, directories): for id in directories: if id not in self._directories: yield id def _join_dentry_to_content(self, dentry): keys = ( 'status', 'sha1', 'sha1_git', 'sha256', 'length', ) ret = dict.fromkeys(keys) ret.update(dentry) if ret['type'] == 'file': # TODO: Make it able to handle more than one content content = self.content_find({'sha1_git': ret['target']}) if content: content = content[0] for key in keys: ret[key] = content[key] return ret def _directory_ls(self, directory_id, recursive, prefix=b''): if directory_id in self._directories: for entry in self._directories[directory_id].entries: ret = self._join_dentry_to_content(entry.to_dict()) ret['name'] = prefix + ret['name'] ret['dir_id'] = directory_id yield ret if recursive and ret['type'] == 'dir': yield from self._directory_ls( ret['target'], True, prefix + ret['name'] + b'/') def directory_ls(self, directory, recursive=False): yield from self._directory_ls(directory, recursive) def directory_entry_get_by_path(self, directory, paths): return self._directory_entry_get_by_path(directory, paths, b'') def directory_get_random(self): if not self._directories: return None return random.choice(list(self._directories)) def _directory_entry_get_by_path(self, directory, paths, prefix): if not paths: return contents = list(self.directory_ls(directory)) if not contents: return def _get_entry(entries, name): for entry in entries: if entry['name'] == name: entry = entry.copy() entry['name'] = prefix + entry['name'] return entry first_item = _get_entry(contents, paths[0]) if len(paths) == 1: return first_item if not first_item or first_item['type'] != 'dir': return return self._directory_entry_get_by_path( first_item['target'], paths[1:], prefix + paths[0] + b'/') def revision_add(self, revisions: Iterable[Revision]) -> Dict: revisions = [rev for rev in revisions if rev.id not in self._revisions] self.journal_writer.revision_add(revisions) count = 0 for revision in revisions: revision = attr.evolve( revision, committer=self._person_add(revision.committer), author=self._person_add(revision.author)) self._revisions[revision.id] = revision self._objects[revision.id].append( ('revision', revision.id)) count += 1 return {'revision:add': count} def revision_missing(self, revisions): for id in revisions: if id not in self._revisions: yield id def revision_get(self, revisions): for id in revisions: if id in self._revisions: yield self._revisions.get(id).to_dict() else: yield None def _get_parent_revs(self, rev_id, seen, limit): if limit and len(seen) >= limit: return if rev_id in seen or rev_id not in self._revisions: return seen.add(rev_id) yield self._revisions[rev_id].to_dict() for parent in self._revisions[rev_id].parents: yield from self._get_parent_revs(parent, seen, limit) def revision_log(self, revisions, limit=None): seen = set() for rev_id in revisions: yield from self._get_parent_revs(rev_id, seen, limit) def revision_shortlog(self, revisions, limit=None): yield from ((rev['id'], rev['parents']) for rev in self.revision_log(revisions, limit)) def revision_get_random(self): return random.choice(list(self._revisions)) def release_add(self, releases: Iterable[Release]) -> Dict: releases = [rel for rel in releases if rel.id not in self._releases] self.journal_writer.release_add(releases) count = 0 for rel in releases: if rel.author: self._person_add(rel.author) self._objects[rel.id].append( ('release', rel.id)) self._releases[rel.id] = rel count += 1 return {'release:add': count} def release_missing(self, releases): yield from (rel for rel in releases if rel not in self._releases) def release_get(self, releases): for rel_id in releases: if rel_id in self._releases: yield self._releases[rel_id].to_dict() else: yield None def release_get_random(self): return random.choice(list(self._releases)) def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: count = 0 snapshots = (snap for snap in snapshots if snap.id not in self._snapshots) for snapshot in snapshots: self.journal_writer.snapshot_add(snapshot) sorted_branch_names = sorted(snapshot.branches) self._snapshots[snapshot.id] = (snapshot, sorted_branch_names) self._objects[snapshot.id].append(('snapshot', snapshot.id)) count += 1 return {'snapshot:add': count} def snapshot_missing(self, snapshots): for id in snapshots: if id not in self._snapshots: yield id def snapshot_get(self, snapshot_id): return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): origin_url = self._get_origin_url(origin) if not origin_url: return if origin_url not in self._origins or \ visit > len(self._origin_visits[origin_url]): return None snapshot_id = self._origin_visits[origin_url][visit-1].snapshot if snapshot_id: return self.snapshot_get(snapshot_id) else: return None def snapshot_get_latest(self, origin, allowed_statuses=None): origin_url = self._get_origin_url(origin) if not origin_url: return visit = self.origin_visit_get_latest( origin_url, allowed_statuses=allowed_statuses, require_snapshot=True) if visit and visit['snapshot']: snapshot = self.snapshot_get(visit['snapshot']) if not snapshot: raise StorageArgumentException( 'last origin visit references an unknown snapshot') return snapshot def snapshot_count_branches(self, snapshot_id): (snapshot, _) = self._snapshots[snapshot_id] return collections.Counter(branch.target_type.value if branch else None for branch in snapshot.branches.values()) def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None): res = self._snapshots.get(snapshot_id) if res is None: return None (snapshot, sorted_branch_names) = res from_index = bisect.bisect_left( sorted_branch_names, branches_from) if target_types: next_branch = None branches = {} for branch_name in sorted_branch_names[from_index:]: branch = snapshot.branches[branch_name] if branch and branch.target_type.value in target_types: if len(branches) < branches_count: branches[branch_name] = branch else: next_branch = branch_name break else: # As there is no 'target_types', we can do that much faster to_index = from_index + branches_count returned_branch_names = sorted_branch_names[from_index:to_index] branches = {branch_name: snapshot.branches[branch_name] for branch_name in returned_branch_names} if to_index >= len(sorted_branch_names): next_branch = None else: next_branch = sorted_branch_names[to_index] branches = {name: branch.to_dict() if branch else None for (name, branch) in branches.items()} return { 'id': snapshot_id, 'branches': branches, 'next_branch': next_branch, } def snapshot_get_random(self): return random.choice(list(self._snapshots)) def object_find_by_sha1_git(self, ids): ret = {} for id_ in ids: objs = self._objects.get(id_, []) ret[id_] = [{ 'sha1_git': id_, 'type': obj[0], } for obj in objs] return ret def _convert_origin(self, t): if t is None: return None return t.to_dict() def origin_get(self, origins): if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False # Sanity check to be error-compatible with the pgsql backend if any('id' in origin for origin in origins) \ and not all('id' in origin for origin in origins): raise StorageArgumentException( 'Either all origins or none at all should have an "id".') if any('url' in origin for origin in origins) \ and not all('url' in origin for origin in origins): raise StorageArgumentException( 'Either all origins or none at all should have ' 'an "url" key.') results = [] for origin in origins: result = None if 'url' in origin: if origin['url'] in self._origins: result = self._origins[origin['url']] else: raise StorageArgumentException( 'Origin must have an url.') results.append(self._convert_origin(result)) if return_single: assert len(results) == 1 return results[0] else: return results def origin_get_by_sha1(self, sha1s): return [ self._convert_origin(self._origins_by_sha1.get(sha1)) for sha1 in sha1s ] def origin_get_range(self, origin_from=1, origin_count=100): origin_from = max(origin_from, 1) if origin_from <= len(self._origins_by_id): max_idx = origin_from + origin_count - 1 if max_idx > len(self._origins_by_id): max_idx = len(self._origins_by_id) for idx in range(origin_from-1, max_idx): origin = self._convert_origin( self._origins[self._origins_by_id[idx]]) yield {'id': idx+1, **origin} def origin_list(self, page_token: Optional[str] = None, limit: int = 100 ) -> dict: origin_urls = sorted(self._origins) if page_token: from_ = bisect.bisect_left(origin_urls, page_token) else: from_ = 0 result = { 'origins': [{'url': origin_url} for origin_url in origin_urls[from_:from_+limit]] } if from_+limit < len(origin_urls): result['next_page_token'] = origin_urls[from_+limit] return result def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False): origins = map(self._convert_origin, self._origins.values()) if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.search(orig['url'])] else: origins = [orig for orig in origins if url_pattern in orig['url']] if with_visit: origins = [ orig for orig in origins if len(self._origin_visits[orig['url']]) > 0 and set(ov.snapshot for ov in self._origin_visits[orig['url']] if ov.snapshot) & set(self._snapshots)] return origins[offset:offset+limit] def origin_count(self, url_pattern, regexp=False, with_visit=False): return len(self.origin_search(url_pattern, regexp=regexp, with_visit=with_visit, limit=len(self._origins))) def origin_add(self, origins: Iterable[Origin]) -> List[Dict]: origins = copy.deepcopy(list(origins)) for origin in origins: self.origin_add_one(origin) return [origin.to_dict() for origin in origins] def origin_add_one(self, origin: Origin) -> str: if origin.url not in self._origins: self.journal_writer.origin_add_one(origin) # generate an origin_id because it is needed by origin_get_range. # TODO: remove this when we remove origin_get_range origin_id = len(self._origins) + 1 self._origins_by_id.append(origin.url) assert len(self._origins_by_id) == origin_id self._origins[origin.url] = origin self._origins_by_sha1[origin_url_to_sha1(origin.url)] = origin self._origin_visits[origin.url] = [] self._objects[origin.url].append(('origin', origin.url)) return origin.url def origin_visit_add( self, origin, date, type) -> Optional[Dict[str, Union[str, int]]]: origin_url = origin if origin_url is None: raise StorageArgumentException('Unknown origin.') if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): raise StorageArgumentException( 'date must be a datetime or a string.') visit_ret = None if origin_url in self._origins: origin = self._origins[origin_url] # visit ids are in the range [1, +inf[ visit_id = len(self._origin_visits[origin_url]) + 1 status = 'ongoing' visit = OriginVisit( origin=origin.url, date=date, type=type, status=status, snapshot=None, metadata=None, visit=visit_id, ) self._origin_visits[origin_url].append(visit) visit_ret = { 'origin': origin.url, 'visit': visit_id, } self._objects[(origin_url, visit_id)].append( ('origin_visit', None)) self.journal_writer.origin_visit_add(visit) return visit_ret def origin_visit_update( self, origin: str, visit_id: int, status: Optional[str] = None, metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None): origin_url = self._get_origin_url(origin) if origin_url is None: raise StorageArgumentException('Unknown origin.') try: visit = self._origin_visits[origin_url][visit_id-1] except IndexError: raise StorageArgumentException( 'Unknown visit_id for this origin') from None updates: Dict[str, Any] = {} if status: updates['status'] = status if metadata: updates['metadata'] = metadata if snapshot: updates['snapshot'] = snapshot try: visit = attr.evolve(visit, **updates) except (KeyError, TypeError, ValueError) as e: raise StorageArgumentException(*e.args) self.journal_writer.origin_visit_update(visit) self._origin_visits[origin_url][visit_id-1] = visit def origin_visit_upsert(self, visits): for visit in visits: if not isinstance(visit['origin'], str): raise TypeError("visit['origin'] must be a string, not %r" % (visit['origin'],)) try: visits = [OriginVisit.from_dict(d) for d in visits] except (KeyError, TypeError, ValueError) as e: raise StorageArgumentException(*e.args) self.journal_writer.origin_visit_upsert(visits) for visit in visits: visit_id = visit.visit origin_url = visit.origin try: visit = attr.evolve(visit, origin=origin_url) except (KeyError, TypeError, ValueError) as e: raise StorageArgumentException(*e.args) self._objects[(origin_url, visit_id)].append( ('origin_visit', None)) while len(self._origin_visits[origin_url]) <= visit_id: self._origin_visits[origin_url].append(None) self._origin_visits[origin_url][visit_id-1] = visit def _convert_visit(self, visit): if visit is None: return visit = visit.to_dict() return visit def origin_visit_get(self, origin, last_visit=None, limit=None): origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] if last_visit is not None: visits = visits[last_visit:] if limit is not None: visits = visits[:limit] for visit in visits: if not visit: continue visit_id = visit.visit yield self._convert_visit( self._origin_visits[origin_url][visit_id-1]) def origin_visit_find_by_date(self, origin, visit_date): origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] visit = min( visits, key=lambda v: (abs(v.date - visit_date), -v.visit)) return self._convert_visit(visit) def origin_visit_get_by(self, origin, visit): origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits and \ visit <= len(self._origin_visits[origin_url]): return self._convert_visit( self._origin_visits[origin_url][visit-1]) def origin_visit_get_latest( self, origin, allowed_statuses=None, require_snapshot=False): origin = self._origins.get(origin) if not origin: return visits = self._origin_visits[origin.url] if allowed_statuses is not None: visits = [visit for visit in visits if visit.status in allowed_statuses] if require_snapshot: visits = [visit for visit in visits if visit.snapshot] visit = max( visits, key=lambda v: (v.date, v.visit), default=None) return self._convert_visit(visit) def _select_random_origin_visit_by_type(self, type: str) -> str: while True: url = random.choice(list(self._origin_visits.keys())) random_origin_visits = self._origin_visits[url] if random_origin_visits[0].type == type: return url def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: url = self._select_random_origin_visit_by_type(type) random_origin_visits = copy.deepcopy(self._origin_visits[url]) random_origin_visits.reverse() back_in_the_day = now() - timedelta(weeks=12) # 3 months back # This should be enough for tests for visit in random_origin_visits: if visit.date > back_in_the_day and visit.status == 'full': return visit.to_dict() else: return None def stat_counters(self): keys = ( 'content', 'directory', 'origin', 'origin_visit', 'person', 'release', 'revision', 'skipped_content', 'snapshot' ) stats = {key: 0 for key in keys} stats.update(collections.Counter( obj_type for (obj_type, obj_id) in itertools.chain(*self._objects.values()))) return stats def refresh_stat_counters(self): pass def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): if not isinstance(origin_url, str): raise TypeError('origin_id must be str, not %r' % (origin_url,)) if isinstance(ts, str): ts = dateutil.parser.parse(ts) origin_metadata = { 'origin_url': origin_url, 'discovery_date': ts, 'tool_id': tool, 'metadata': metadata, 'provider_id': provider, } self._origin_metadata[origin_url].append(origin_metadata) return None def origin_metadata_get_by(self, origin_url, provider_type=None): if not isinstance(origin_url, str): raise TypeError('origin_url must be str, not %r' % (origin_url,)) metadata = [] for item in self._origin_metadata[origin_url]: item = copy.deepcopy(item) provider = self.metadata_provider_get(item['provider_id']) for attr_name in ('name', 'type', 'url'): item['provider_' + attr_name] = \ provider['provider_' + attr_name] metadata.append(item) return metadata def tool_add(self, tools): inserted = [] for tool in tools: key = self._tool_key(tool) assert 'id' not in tool record = copy.deepcopy(tool) record['id'] = key # TODO: remove this if key not in self._tools: self._tools[key] = record inserted.append(copy.deepcopy(self._tools[key])) return inserted def tool_get(self, tool): return self._tools.get(self._tool_key(tool)) def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata): provider = { 'provider_name': provider_name, 'provider_type': provider_type, 'provider_url': provider_url, 'metadata': metadata, } key = self._metadata_provider_key(provider) provider['id'] = key self._metadata_providers[key] = provider return key def metadata_provider_get(self, provider_id): return self._metadata_providers.get(provider_id) def metadata_provider_get_by(self, provider): key = self._metadata_provider_key(provider) return self._metadata_providers.get(key) def _get_origin_url(self, origin): if isinstance(origin, str): return origin else: raise TypeError('origin must be a string.') def _person_add(self, person): key = ('person', person.fullname) if key not in self._objects: person_id = len(self._persons) + 1 self._persons.append(person) self._objects[key].append(('person', person_id)) else: person_id = self._objects[key][0][1] person = self._persons[person_id-1] return person @staticmethod def _content_key(content): """ A stable key and the algorithm for a content""" if isinstance(content, BaseContent): content = content.to_dict() return tuple((key, content.get(key)) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _tool_key(tool): return '%r %r %r' % (tool['name'], tool['version'], tuple(sorted(tool['configuration'].items()))) @staticmethod def _metadata_provider_key(provider): return '%r %r' % (provider['provider_name'], provider['provider_url']) def diff_directories(self, from_dir, to_dir, track_renaming=False): raise NotImplementedError('InMemoryStorage.diff_directories') def diff_revisions(self, from_rev, to_rev, track_renaming=False): raise NotImplementedError('InMemoryStorage.diff_revisions') def diff_revision(self, revision, track_renaming=False): raise NotImplementedError('InMemoryStorage.diff_revision') diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 464b70d4..be931040 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1145 +1,1160 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import contextlib import copy import datetime import itertools import json from collections import defaultdict from concurrent.futures import ThreadPoolExecutor from contextlib import contextmanager from typing import Any, Dict, Iterable, List, Optional, Union import attr import dateutil.parser import psycopg2 import psycopg2.pool import psycopg2.errors from swh.model.model import ( SkippedContent, Content, Directory, Revision, Release, Snapshot, Origin, SHA1_SIZE ) from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.storage.objstorage import ObjStorage from . import converters, HashCollision from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageArgumentException, StorageDBError from .algos import diff from .metrics import timed, send_metric, process_metrics -from .utils import get_partition_bounds_bytes +from .utils import ( + get_partition_bounds_bytes, extract_collision_hash +) from .writer import JournalWriter # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 EMPTY_SNAPSHOT_ID = hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e') """Identifier for the empty snapshot""" VALIDATION_EXCEPTIONS = ( psycopg2.errors.CheckViolation, psycopg2.errors.IntegrityError, psycopg2.errors.InvalidTextRepresentation, psycopg2.errors.NotNullViolation, psycopg2.errors.NumericValueOutOfRange, psycopg2.errors.UndefinedFunction, # (raised on wrong argument typs) ) """Exceptions raised by postgresql when validation of the arguments failed.""" @contextlib.contextmanager def convert_validation_exceptions(): """Catches postgresql errors related to invalid arguments, and re-raises a StorageArgumentException.""" try: yield except VALIDATION_EXCEPTIONS as e: raise StorageArgumentException(*e.args) class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db, objstorage, min_pool_conns=1, max_pool_conns=10, journal_writer=None): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ try: if isinstance(db, psycopg2.extensions.connection): self._pool = None self._db = Db(db) else: self._pool = psycopg2.pool.ThreadedConnectionPool( min_pool_conns, max_pool_conns, db ) self._db = None except psycopg2.OperationalError as e: raise StorageDBError(e) self.journal_writer = JournalWriter(journal_writer) self.objstorage = ObjStorage(objstorage) def get_db(self): if self._db: return self._db else: return Db.from_pool(self._pool) def put_db(self, db): if db is not self._db: db.put_conn() @contextmanager def db(self): db = None try: db = self.get_db() yield db finally: if db: self.put_db(db) @timed @db_transaction() def check_config(self, *, check_write, db=None, cur=None): if not self.objstorage.check_config(check_write=check_write): return False # Check permissions on one of the tables if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content', %s)", (check,) ) return cur.fetchone()[0] def _content_unique_key(self, hash, db): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ keys = db.content_hash_keys if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) def _content_add_metadata(self, db, cur, content): """Add content to the postgresql database but not the object storage. """ # create temporary table for metadata injection db.mktemp('content', cur) db.copy_to((c.to_dict() for c in content), 'tmp_content', db.content_add_keys, cur) # move metadata in place try: db.content_add_from_temp(cur) except psycopg2.IntegrityError as e: if e.diag.sqlstate == '23505' and \ e.diag.table_name == 'content': - constraint_to_hash_name = { - 'content_pkey': 'sha1', - 'content_sha1_git_idx': 'sha1_git', - 'content_sha256_idx': 'sha256', + message_detail = e.diag.message_detail + if message_detail: + hash_name, hash_id = extract_collision_hash(message_detail) + collision_contents_hashes = [ + c.hashes() for c in content + if c.get_hash(hash_name) == hash_id + ] + else: + constraint_to_hash_name = { + 'content_pkey': 'sha1', + 'content_sha1_git_idx': 'sha1_git', + 'content_sha256_idx': 'sha256', } - colliding_hash_name = constraint_to_hash_name \ - .get(e.diag.constraint_name) - raise HashCollision(colliding_hash_name) from None + hash_name = constraint_to_hash_name \ + .get(e.diag.constraint_name) + hash_id = None + collision_contents_hashes = None + + raise HashCollision( + hash_name, hash_id, collision_contents_hashes + ) from None else: raise @timed @process_metrics @db_transaction() def content_add( self, content: Iterable[Content], db=None, cur=None) -> Dict: now = datetime.datetime.now(tz=datetime.timezone.utc) contents = [attr.evolve(c, ctime=now) for c in content] missing = list(self.content_missing( map(Content.to_dict, contents), key_hash='sha1_git')) contents = [c for c in contents if c.sha1_git in missing] self.journal_writer.content_add(contents) 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. """ summary = self.objstorage.content_add(contents) return summary['content:add:bytes'] with ThreadPoolExecutor(max_workers=1) as executor: added_to_objstorage = executor.submit(add_to_objstorage) self._content_add_metadata(db, cur, contents) # Wait for objstorage addition before returning from the # transaction, bubbling up any exception content_bytes_added = added_to_objstorage.result() return { 'content:add': len(contents), 'content:add:bytes': content_bytes_added, } @timed @db_transaction() def content_update(self, content, keys=[], db=None, cur=None): # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. self.journal_writer.content_update(content) db.mktemp('content', cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) with convert_validation_exceptions(): db.copy_to(content, 'tmp_content', select_keys, cur) db.content_update_from_temp(keys_to_update=keys, cur=cur) @timed @process_metrics @db_transaction() def content_add_metadata(self, content: Iterable[Content], db=None, cur=None) -> Dict: contents = list(content) missing = self.content_missing( (c.to_dict() for c in contents), key_hash='sha1_git') contents = [c for c in contents if c.sha1_git in missing] self.journal_writer.content_add_metadata(contents) self._content_add_metadata(db, cur, contents) return { 'content:add': len(contents), } @timed def content_get(self, content): # FIXME: Make this method support slicing the `data`. if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( "Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) yield from self.objstorage.content_get(content) @timed @db_transaction() def content_get_range(self, start, end, limit=1000, db=None, cur=None): if limit is None: raise StorageArgumentException('limit should not be None') 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, } @timed @db_transaction() def content_get_partition( self, partition_id: int, nb_partitions: int, limit: int = 1000, page_token: str = None, db=None, cur=None): if limit is None: raise StorageArgumentException('limit should not be None') (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE) if page_token: start = hash_to_bytes(page_token) if end is None: end = b'\xff'*SHA1_SIZE result = self.content_get_range(start, end, limit) result2 = { 'contents': result['contents'], 'next_page_token': None, } if result['next']: result2['next_page_token'] = hash_to_hex(result['next']) return result2 @timed @db_transaction(statement_timeout=500) def content_get_metadata( self, contents: List[bytes], db=None, cur=None) -> Dict[bytes, List[Dict]]: result: Dict[bytes, List[Dict]] = {sha1: [] for sha1 in contents} for row in db.content_get_metadata_from_sha1s(contents, cur): content_meta = dict(zip(db.content_get_metadata_keys, row)) result[content_meta['sha1']].append(content_meta) return result @timed @db_transaction_generator() def content_missing(self, content, key_hash='sha1', db=None, cur=None): keys = db.content_hash_keys if key_hash not in keys: raise StorageArgumentException( "key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) if not content: return for obj in db.content_missing_from_list(content, cur): yield obj[key_hash_idx] @timed @db_transaction_generator() def content_missing_per_sha1(self, contents, db=None, cur=None): for obj in db.content_missing_per_sha1(contents, cur): yield obj[0] @timed @db_transaction_generator() def content_missing_per_sha1_git(self, contents, db=None, cur=None): for obj in db.content_missing_per_sha1_git(contents, cur): yield obj[0] @timed @db_transaction() def content_find(self, content, db=None, cur=None): if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( 'content keys must contain at least one of: ' 'sha1, sha1_git, sha256, blake2s256') contents = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), blake2s256=content.get('blake2s256'), cur=cur) return [dict(zip(db.content_find_cols, content)) for content in contents] @timed @db_transaction() def content_get_random(self, db=None, cur=None): return db.content_get_random(cur) @staticmethod def _skipped_content_normalize(d): d = d.copy() if d.get('status') is None: d['status'] = 'absent' if d.get('length') is None: d['length'] = -1 return d @staticmethod def _skipped_content_validate(d): """Sanity checks on status / reason / length, that postgresql doesn't enforce.""" if d['status'] != 'absent': raise StorageArgumentException( 'Invalid content status: {}'.format(d['status'])) if d.get('reason') is None: raise StorageArgumentException( 'Must provide a reason if content is absent.') if d['length'] < -1: raise StorageArgumentException( 'Content length must be positive or -1.') def _skipped_content_add_metadata( self, db, cur, content: Iterable[SkippedContent]): origin_ids = db.origin_id_get_by_url( [cont.origin for cont in content], cur=cur) content = [attr.evolve(c, origin=origin_id) for (c, origin_id) in zip(content, origin_ids)] db.mktemp('skipped_content', cur) db.copy_to([c.to_dict() for c in content], 'tmp_skipped_content', db.skipped_content_keys, cur) # move metadata in place db.skipped_content_add_from_temp(cur) @timed @process_metrics @db_transaction() def skipped_content_add(self, content: Iterable[SkippedContent], db=None, cur=None) -> Dict: now = datetime.datetime.now(tz=datetime.timezone.utc) content = [attr.evolve(c, ctime=now) for c in content] missing_contents = self.skipped_content_missing( c.to_dict() for c in content) content = [c for c in content if any(all(c.get_hash(algo) == missing_content.get(algo) for algo in DEFAULT_ALGORITHMS) for missing_content in missing_contents)] self.journal_writer.skipped_content_add(content) self._skipped_content_add_metadata(db, cur, content) return { 'skipped_content:add': len(content), } @timed @db_transaction_generator() def skipped_content_missing(self, contents, db=None, cur=None): contents = list(contents) for content in db.skipped_content_missing(contents, cur): yield dict(zip(db.content_hash_keys, content)) @timed @process_metrics @db_transaction() def directory_add(self, directories: Iterable[Directory], db=None, cur=None) -> Dict: directories = list(directories) summary = {'directory:add': 0} dirs = set() dir_entries: Dict[str, defaultdict] = { 'file': defaultdict(list), 'dir': defaultdict(list), 'rev': defaultdict(list), } for cur_dir in directories: dir_id = cur_dir.id dirs.add(dir_id) for src_entry in cur_dir.entries: entry = src_entry.to_dict() entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs, db=db, cur=cur)) if not dirs_missing: return summary self.journal_writer.directory_add( dir_ for dir_ in directories if dir_.id in dirs_missing ) # Copy directory ids dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.mktemp('directory', cur) db.copy_to(dirs_missing_dict, 'tmp_directory', ['id'], cur) # Copy entries for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'dir_id'], cur, ) # Do the final copy db.directory_add_from_temp(cur) summary['directory:add'] = len(dirs_missing) return summary @timed @db_transaction_generator() def directory_missing(self, directories, db=None, cur=None): for obj in db.directory_missing_from_list(directories, cur): yield obj[0] @timed @db_transaction_generator(statement_timeout=20000) def directory_ls(self, directory, recursive=False, db=None, cur=None): if recursive: res_gen = db.directory_walk(directory, cur=cur) else: res_gen = db.directory_walk_one(directory, cur=cur) for line in res_gen: yield dict(zip(db.directory_ls_cols, line)) @timed @db_transaction(statement_timeout=2000) def directory_entry_get_by_path(self, directory, paths, db=None, cur=None): res = db.directory_entry_get_by_path(directory, paths, cur) if res: return dict(zip(db.directory_ls_cols, res)) @timed @db_transaction() def directory_get_random(self, db=None, cur=None): return db.directory_get_random(cur) @timed @process_metrics @db_transaction() def revision_add(self, revisions: Iterable[Revision], db=None, cur=None) -> Dict: revisions = list(revisions) summary = {'revision:add': 0} revisions_missing = set(self.revision_missing( set(revision.id for revision in revisions), db=db, cur=cur)) if not revisions_missing: return summary db.mktemp_revision(cur) revisions_filtered = [ revision for revision in revisions if revision.id in revisions_missing] self.journal_writer.revision_add(revisions_filtered) revisions_filtered = \ list(map(converters.revision_to_db, revisions_filtered)) parents_filtered: List[bytes] = [] with convert_validation_exceptions(): db.copy_to( revisions_filtered, 'tmp_revision', db.revision_add_cols, cur, lambda rev: parents_filtered.extend(rev['parents'])) db.revision_add_from_temp(cur) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) return {'revision:add': len(revisions_missing)} @timed @db_transaction_generator() def revision_missing(self, revisions, db=None, cur=None): if not revisions: return for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @timed @db_transaction_generator(statement_timeout=1000) def revision_get(self, revisions, db=None, cur=None): for line in db.revision_get_from_list(revisions, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @timed @db_transaction_generator(statement_timeout=2000) def revision_log(self, revisions, limit=None, db=None, cur=None): for line in db.revision_log(revisions, limit, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @timed @db_transaction_generator(statement_timeout=2000) def revision_shortlog(self, revisions, limit=None, db=None, cur=None): yield from db.revision_shortlog(revisions, limit, cur) @timed @db_transaction() def revision_get_random(self, db=None, cur=None): return db.revision_get_random(cur) @timed @process_metrics @db_transaction() def release_add( self, releases: Iterable[Release], db=None, cur=None) -> Dict: releases = list(releases) summary = {'release:add': 0} release_ids = set(release.id for release in releases) releases_missing = set(self.release_missing(release_ids, db=db, cur=cur)) if not releases_missing: return summary db.mktemp_release(cur) releases_filtered = [ release for release in releases if release.id in releases_missing ] self.journal_writer.release_add(releases_filtered) releases_filtered = \ list(map(converters.release_to_db, releases_filtered)) with convert_validation_exceptions(): db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) return {'release:add': len(releases_missing)} @timed @db_transaction_generator() def release_missing(self, releases, db=None, cur=None): if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @timed @db_transaction_generator(statement_timeout=500) def release_get(self, releases, db=None, cur=None): for release in db.release_get_from_list(releases, cur): data = converters.db_to_release( dict(zip(db.release_get_cols, release)) ) yield data if data['target_type'] else None @timed @db_transaction() def release_get_random(self, db=None, cur=None): return db.release_get_random(cur) @timed @process_metrics @db_transaction() def snapshot_add( self, snapshots: Iterable[Snapshot], db=None, cur=None) -> Dict: 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 try: db.copy_to( ( { 'name': name, 'target': info.target if info else None, 'target_type': (info.target_type.value if info else None), } for name, info in snapshot.branches.items() ), 'tmp_snapshot_branch', ['name', 'target', 'target_type'], cur, ) except VALIDATION_EXCEPTIONS + (KeyError,) as e: raise StorageArgumentException(*e.args) self.journal_writer.snapshot_add(snapshot) db.snapshot_add(snapshot.id, cur) count += 1 return {'snapshot:add': count} @timed @db_transaction_generator() def snapshot_missing(self, snapshots, db=None, cur=None): for obj in db.snapshot_missing_from_list(snapshots, cur): yield obj[0] @timed @db_transaction(statement_timeout=2000) def snapshot_get(self, snapshot_id, db=None, cur=None): return self.snapshot_get_branches(snapshot_id, db=db, cur=cur) @timed @db_transaction(statement_timeout=2000) def snapshot_get_by_origin_visit(self, origin, visit, db=None, cur=None): snapshot_id = db.snapshot_get_by_origin_visit(origin, visit, cur) if snapshot_id: return self.snapshot_get(snapshot_id, db=db, cur=cur) return None @timed @db_transaction(statement_timeout=4000) def snapshot_get_latest(self, origin, allowed_statuses=None, db=None, cur=None): if isinstance(origin, int): origin = self.origin_get({'id': origin}, db=db, cur=cur) if not origin: return origin = origin['url'] origin_visit = self.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=True, db=db, cur=cur) if origin_visit and origin_visit['snapshot']: snapshot = self.snapshot_get( origin_visit['snapshot'], db=db, cur=cur) if not snapshot: raise StorageArgumentException( 'last origin visit references an unknown snapshot') return snapshot @timed @db_transaction(statement_timeout=2000) def snapshot_count_branches(self, snapshot_id, db=None, cur=None): return dict([bc for bc in db.snapshot_count_branches(snapshot_id, cur)]) @timed @db_transaction(statement_timeout=2000) def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None, db=None, cur=None): 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 @timed @db_transaction() def snapshot_get_random(self, db=None, cur=None): return db.snapshot_get_random(cur) @timed @db_transaction() def origin_visit_add( self, origin, date, type, db=None, cur=None ) -> Optional[Dict[str, Union[str, int]]]: origin_url = origin if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) with convert_validation_exceptions(): visit_id = db.origin_visit_add(origin_url, date, type, cur) # We can write to the journal only after inserting to the # DB, because we want the id of the visit visit = { 'origin': origin_url, 'date': date, 'type': type, 'visit': visit_id, 'status': 'ongoing', 'metadata': None, 'snapshot': None } self.journal_writer.origin_visit_add(visit) send_metric('origin_visit:add', count=1, method_name='origin_visit') return { 'origin': origin_url, 'visit': visit_id, } @timed @db_transaction() def origin_visit_update(self, origin: str, visit_id: int, status: Optional[str] = None, metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None, db=None, cur=None): if not isinstance(origin, str): raise StorageArgumentException( 'origin must be a string, not %r' % (origin,)) origin_url = origin visit = db.origin_visit_get(origin_url, visit_id, cur=cur) if not visit: raise StorageArgumentException('Invalid visit_id for this origin.') visit = dict(zip(db.origin_visit_get_cols, visit)) updates: Dict[str, Any] = {} 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: updated_visit = {**visit, **updates} self.journal_writer.origin_visit_update(updated_visit) with convert_validation_exceptions(): db.origin_visit_update(origin_url, visit_id, updates, cur) @timed @db_transaction() def origin_visit_upsert(self, visits, db=None, cur=None): visits = copy.deepcopy(visits) for visit in visits: if isinstance(visit['date'], str): visit['date'] = dateutil.parser.parse(visit['date']) if not isinstance(visit['origin'], str): raise StorageArgumentException( "visit['origin'] must be a string, not %r" % (visit['origin'],)) self.journal_writer.origin_visit_upsert(visits) for visit in visits: # TODO: upsert them all in a single query db.origin_visit_upsert(**visit, cur=cur) @timed @db_transaction_generator(statement_timeout=500) def origin_visit_get(self, origin, last_visit=None, limit=None, db=None, cur=None): 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 @timed @db_transaction(statement_timeout=500) def origin_visit_find_by_date(self, origin, visit_date, db=None, cur=None): line = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if line: return dict(zip(db.origin_visit_get_cols, line)) @timed @db_transaction(statement_timeout=500) def origin_visit_get_by(self, origin, visit, db=None, cur=None): ori_visit = db.origin_visit_get(origin, visit, cur) if not ori_visit: return None return dict(zip(db.origin_visit_get_cols, ori_visit)) @timed @db_transaction(statement_timeout=4000) def origin_visit_get_latest( self, origin, allowed_statuses=None, require_snapshot=False, db=None, cur=None): 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)) @timed @db_transaction() def origin_visit_get_random( self, type: str, db=None, cur=None) -> Optional[Dict[str, Any]]: result = db.origin_visit_get_random(type, cur) if result: return dict(zip(db.origin_visit_get_cols, result)) else: return None @timed @db_transaction(statement_timeout=2000) def object_find_by_sha1_git(self, ids, db=None, cur=None): ret = {id: [] for id in ids} for retval in db.object_find_by_sha1_git(ids, cur=cur): if retval[1]: ret[retval[0]].append(dict(zip(db.object_find_by_sha1_git_cols, retval))) return ret @timed @db_transaction(statement_timeout=500) def origin_get(self, origins, db=None, cur=None): if isinstance(origins, dict): # Old API return_single = True origins = [origins] elif len(origins) == 0: return [] else: return_single = False origin_urls = [origin['url'] for origin in origins] results = db.origin_get_by_url(origin_urls, cur) results = [dict(zip(db.origin_cols, result)) for result in results] if return_single: assert len(results) == 1 if results[0]['url'] is not None: return results[0] else: return None else: return [None if res['url'] is None else res for res in results] @timed @db_transaction_generator(statement_timeout=500) def origin_get_by_sha1(self, sha1s, db=None, cur=None): for line in db.origin_get_by_sha1(sha1s, cur): if line[0] is not None: yield dict(zip(db.origin_cols, line)) else: yield None @timed @db_transaction_generator() def origin_get_range(self, origin_from=1, origin_count=100, db=None, cur=None): for origin in db.origin_get_range(origin_from, origin_count, cur): yield dict(zip(db.origin_get_range_cols, origin)) @timed @db_transaction() def origin_list(self, page_token: Optional[str] = None, limit: int = 100, *, db=None, cur=None) -> dict: page_token = page_token or '0' if not isinstance(page_token, str): raise StorageArgumentException('page_token must be a string.') origin_from = int(page_token) result: Dict[str, Any] = { 'origins': [ dict(zip(db.origin_get_range_cols, origin)) for origin in db.origin_get_range(origin_from, limit, cur) ], } assert len(result['origins']) <= limit if len(result['origins']) == limit: result['next_page_token'] = str(result['origins'][limit-1]['id']+1) for origin in result['origins']: del origin['id'] return result @timed @db_transaction_generator() def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False, db=None, cur=None): for origin in db.origin_search(url_pattern, offset, limit, regexp, with_visit, cur): yield dict(zip(db.origin_cols, origin)) @timed @db_transaction() def origin_count(self, url_pattern, regexp=False, with_visit=False, db=None, cur=None): return db.origin_count(url_pattern, regexp, with_visit, cur) @timed @db_transaction() def origin_add( self, origins: Iterable[Origin], db=None, cur=None) -> List[Dict]: origins = list(origins) for origin in origins: self.origin_add_one(origin, db=db, cur=cur) send_metric('origin:add', count=len(origins), method_name='origin_add') return [o.to_dict() for o in origins] @timed @db_transaction() def origin_add_one(self, origin: Origin, db=None, cur=None) -> str: origin_row = list(db.origin_get_by_url([origin.url], cur))[0] origin_url = dict(zip(db.origin_cols, origin_row))['url'] if origin_url: return origin_url self.journal_writer.origin_add_one(origin) origins = db.origin_add(origin.url, cur) send_metric('origin:add', count=len(origins), method_name='origin_add') return origins @db_transaction(statement_timeout=500) def stat_counters(self, db=None, cur=None): return {k: v for (k, v) in db.stat_counters()} @db_transaction() def refresh_stat_counters(self, db=None, cur=None): keys = [ 'content', 'directory', 'directory_entry_dir', 'directory_entry_file', 'directory_entry_rev', 'origin', 'origin_visit', 'person', 'release', 'revision', 'revision_history', 'skipped_content', 'snapshot'] for key in keys: cur.execute('select * from swh_update_counter(%s)', (key,)) @timed @db_transaction() def origin_metadata_add(self, origin_url, ts, provider, tool, metadata, db=None, cur=None): if isinstance(ts, str): ts = dateutil.parser.parse(ts) db.origin_metadata_add(origin_url, ts, provider, tool, metadata, cur) send_metric( 'origin_metadata:add', count=1, method_name='origin_metadata_add') @timed @db_transaction_generator(statement_timeout=500) def origin_metadata_get_by(self, origin_url, provider_type=None, db=None, cur=None): for line in db.origin_metadata_get_by(origin_url, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) @timed @db_transaction() def tool_add(self, tools, db=None, cur=None): db.mktemp_tool(cur) with convert_validation_exceptions(): db.copy_to(tools, 'tmp_tool', ['name', 'version', 'configuration'], cur) tools = db.tool_add_from_temp(cur) results = [dict(zip(db.tool_cols, line)) for line in tools] send_metric('tool:add', count=len(results), method_name='tool_add') return results @timed @db_transaction(statement_timeout=500) def tool_get(self, tool, db=None, cur=None): 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)) @timed @db_transaction() def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata, db=None, cur=None): result = db.metadata_provider_add(provider_name, provider_type, provider_url, metadata, cur) send_metric( 'metadata_provider:add', count=1, method_name='metadata_provider') return result @timed @db_transaction() def metadata_provider_get(self, provider_id, db=None, cur=None): result = db.metadata_provider_get(provider_id) if not result: return None return dict(zip(db.metadata_provider_cols, result)) @timed @db_transaction() def metadata_provider_get_by(self, provider, db=None, cur=None): result = db.metadata_provider_get_by(provider['provider_name'], provider['provider_url']) if not result: return None return dict(zip(db.metadata_provider_cols, result)) @timed def diff_directories(self, from_dir, to_dir, track_renaming=False): return diff.diff_directories(self, from_dir, to_dir, track_renaming) @timed def diff_revisions(self, from_rev, to_rev, track_renaming=False): return diff.diff_revisions(self, from_rev, to_rev, track_renaming) @timed def diff_revision(self, revision, track_renaming=False): return diff.diff_revision(self, revision, track_renaming) diff --git a/swh/storage/tests/test_cassandra_converters.py b/swh/storage/tests/test_cassandra_converters.py new file mode 100644 index 00000000..25594d63 --- /dev/null +++ b/swh/storage/tests/test_cassandra_converters.py @@ -0,0 +1,37 @@ +# Copyright (C) 2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from collections import namedtuple +from typing import List + +from swh.storage.cassandra import converters + +from swh.model.hashutil import DEFAULT_ALGORITHMS + + +# Test purposes +field_names: List[str] = list(DEFAULT_ALGORITHMS) +Row = namedtuple('Row', field_names) # type: ignore + + +def test_row_to_content_hashes(): + for row in [Row( + sha1=b'4\x972t\xcc\xefj\xb4\xdf\xaa\xf8e\x99y/\xa9\xc3\xfeF\x89', + sha1_git=b'\xd8\x1c\xc0q\x0e\xb6\xcf\x9e\xfd[\x92\n\x84S\xe1\xe0qW\xb6\xcd', # noqa + sha256=b'g6P\xf96\xcb;\n/\x93\xce\t\xd8\x1b\xe1\x07H\xb1\xb2\x03\xc1\x9e\x81v\xb4\xee\xfc\x19d\xa0\xcf:', # noqa + blake2s256=b"\xd5\xfe\x199We'\xe4,\xfdv\xa9EZ$2\xfe\x7fVf\x95dW}\xd9', 'name': b'John Doe', 'email': b'john.doe@example.com' } revision2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.revision_add([revision1, revision2]) assert actual_result == {'revision:add': 2} def test_revision_get_order(self, swh_storage): normalized_rev1 = Revision.from_dict(data.revision).to_dict() normalized_rev2 = Revision.from_dict(data.revision2).to_dict() add_result = swh_storage.revision_add( [normalized_rev1, normalized_rev2] ) assert add_result == {'revision:add': 2} # order 1 res1 = swh_storage.revision_get( [normalized_rev1['id'], normalized_rev2['id']] ) assert list(res1) == [normalized_rev1, normalized_rev2] # order 2 res2 = swh_storage.revision_get( [normalized_rev2['id'], normalized_rev1['id']] ) assert list(res2) == [normalized_rev2, normalized_rev1] def test_revision_log(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_log( [data.revision4['id']])) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] assert len(actual_results) == 2 # rev4 -child-> rev3 assert actual_results[0] == normalize_entity(data.revision4) assert actual_results[1] == normalize_entity(data.revision3) normalized_revision3 = Revision.from_dict(data.revision3).to_dict() normalized_revision4 = Revision.from_dict(data.revision4).to_dict() assert list(swh_storage.journal_writer.journal.objects) == [ ('revision', normalized_revision3), ('revision', normalized_revision4)] def test_revision_log_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_log( [data.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] assert len(actual_results) == 1 assert actual_results[0] == data.revision4 def test_revision_log_unknown_revision(self, swh_storage): rev_log = list(swh_storage.revision_log([data.revision['id']])) assert rev_log == [] def test_revision_shortlog(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']])) assert len(actual_results) == 2 # rev4 -child-> rev3 assert list(actual_results[0]) == short_revision(data.revision4) assert list(actual_results[1]) == short_revision(data.revision3) def test_revision_shortlog_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']], 1)) assert len(actual_results) == 1 assert list(actual_results[0]) == short_revision(data.revision4) def test_revision_get(self, swh_storage): swh_storage.revision_add([data.revision]) actual_revisions = list(swh_storage.revision_get( [data.revision['id'], data.revision2['id']])) # when if 'id' in actual_revisions[0]['author']: del actual_revisions[0]['author']['id'] # hack: ids are generated if 'id' in actual_revisions[0]['committer']: del actual_revisions[0]['committer']['id'] assert len(actual_revisions) == 2 assert actual_revisions[0] == normalize_entity(data.revision) assert actual_revisions[1] is None def test_revision_get_no_parents(self, swh_storage): swh_storage.revision_add([data.revision3]) get = list(swh_storage.revision_get([data.revision3['id']])) assert len(get) == 1 assert get[0]['parents'] == [] # no parents on this one def test_revision_get_random(self, swh_storage): swh_storage.revision_add( [data.revision, data.revision2, data.revision3]) assert swh_storage.revision_get_random() in \ {data.revision['id'], data.revision2['id'], data.revision3['id']} def test_release_add(self, swh_storage): normalized_release = Release.from_dict(data.release).to_dict() normalized_release2 = Release.from_dict(data.release2).to_dict() init_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert [data.release['id'], data.release2['id']] == list(init_missing) actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 2} end_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ('release', normalized_release), ('release', normalized_release2)] # already present so nothing added actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['release'] == 2 def test_release_add_from_generator(self, swh_storage): def _rel_gen(): yield data.release yield data.release2 normalized_release = Release.from_dict(data.release).to_dict() normalized_release2 = Release.from_dict(data.release2).to_dict() actual_result = swh_storage.release_add(_rel_gen()) assert actual_result == {'release:add': 2} assert list(swh_storage.journal_writer.journal.objects) == [ ('release', normalized_release), ('release', normalized_release2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['release'] == 2 def test_release_add_no_author_date(self, swh_storage): release = data.release release['author'] = None release['date'] = None actual_result = swh_storage.release_add([release]) assert actual_result == {'release:add': 1} end_missing = swh_storage.release_missing([data.release['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) \ == [('release', release)] def test_release_add_validation(self, swh_storage): rel = copy.deepcopy(data.release) rel['date']['offset'] = 2**16 with pytest.raises(StorageArgumentException, match='offset') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rel = copy.deepcopy(data.release) rel['author'] = None with pytest.raises(StorageArgumentException, match='date') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.CHECK_VIOLATION def test_release_add_twice(self, swh_storage): actual_result = swh_storage.release_add([data.release]) assert actual_result == {'release:add': 1} normalized_release = Release.from_dict(data.release).to_dict() normalized_release2 = Release.from_dict(data.release2).to_dict() assert list(swh_storage.journal_writer.journal.objects) \ == [('release', normalized_release)] actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 1} assert list(swh_storage.journal_writer.journal.objects) \ == [('release', normalized_release), ('release', normalized_release2)] def test_release_add_name_clash(self, swh_storage): release1 = data.release.copy() release2 = data.release2.copy() release1['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe', 'email': b'john.doe@example.com' } release2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.release_add([release1, release2]) assert actual_result == {'release:add': 2} def test_release_get(self, swh_storage): # given swh_storage.release_add([data.release, data.release2]) # when actual_releases = list(swh_storage.release_get([data.release['id'], data.release2['id']])) # then for actual_release in actual_releases: if 'id' in actual_release['author']: del actual_release['author']['id'] # hack: ids are generated assert [ normalize_entity(data.release), normalize_entity(data.release2)] \ == [actual_releases[0], actual_releases[1]] unknown_releases = \ list(swh_storage.release_get([data.release3['id']])) assert unknown_releases[0] is None def test_release_get_order(self, swh_storage): normalized_rel1 = Release.from_dict(data.release).to_dict() normalized_rel2 = Release.from_dict(data.release2).to_dict() add_result = swh_storage.release_add( [normalized_rel1, normalized_rel2] ) assert add_result == {'release:add': 2} # order 1 res1 = swh_storage.release_get( [normalized_rel1['id'], normalized_rel2['id']] ) assert list(res1) == [normalized_rel1, normalized_rel2] # order 2 res2 = swh_storage.release_get( [normalized_rel2['id'], normalized_rel1['id']] ) assert list(res2) == [normalized_rel2, normalized_rel1] def test_release_get_random(self, swh_storage): swh_storage.release_add([data.release, data.release2, data.release3]) assert swh_storage.release_get_random() in \ {data.release['id'], data.release2['id'], data.release3['id']} def test_origin_add_one(self, swh_storage): origin0 = swh_storage.origin_get(data.origin) assert origin0 is None id = swh_storage.origin_add_one(data.origin) actual_origin = swh_storage.origin_get({'url': data.origin['url']}) assert actual_origin['url'] == data.origin['url'] id2 = swh_storage.origin_add_one(data.origin) assert id == id2 def test_origin_add(self, swh_storage): origin0 = swh_storage.origin_get([data.origin])[0] assert origin0 is None origin1, origin2 = swh_storage.origin_add([data.origin, data.origin2]) actual_origin = swh_storage.origin_get([{ 'url': data.origin['url'], }])[0] assert actual_origin['url'] == origin1['url'] actual_origin2 = swh_storage.origin_get([{ 'url': data.origin2['url'], }])[0] assert actual_origin2['url'] == origin2['url'] if 'id' in actual_origin: del actual_origin['id'] del actual_origin2['id'] assert list(swh_storage.journal_writer.journal.objects) \ == [('origin', actual_origin), ('origin', actual_origin2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['origin'] == 2 def test_origin_add_from_generator(self, swh_storage): def _ori_gen(): yield data.origin yield data.origin2 origin1, origin2 = swh_storage.origin_add(_ori_gen()) actual_origin = swh_storage.origin_get([{ 'url': data.origin['url'], }])[0] assert actual_origin['url'] == origin1['url'] actual_origin2 = swh_storage.origin_get([{ 'url': data.origin2['url'], }])[0] assert actual_origin2['url'] == origin2['url'] if 'id' in actual_origin: del actual_origin['id'] del actual_origin2['id'] assert list(swh_storage.journal_writer.journal.objects) \ == [('origin', actual_origin), ('origin', actual_origin2)] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['origin'] == 2 def test_origin_add_twice(self, swh_storage): add1 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.journal.objects) \ == [('origin', data.origin), ('origin', data.origin2)] add2 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.journal.objects) \ == [('origin', data.origin), ('origin', data.origin2)] assert add1 == add2 def test_origin_add_validation(self, swh_storage): with pytest.raises(StorageArgumentException, match='url'): swh_storage.origin_add([{'type': 'git'}]) def test_origin_get_legacy(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get( {'url': data.origin['url']}) assert actual_origin0['url'] == data.origin['url'] def test_origin_get(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get( [{'url': data.origin['url']}]) assert len(actual_origin0) == 1 assert actual_origin0[0]['url'] == data.origin['url'] def _generate_random_visits(self, nb_visits=100, start=0, end=7): """Generate random visits within the last 2 months (to avoid computations) """ visits = [] today = datetime.datetime.now(tz=datetime.timezone.utc) for weeks in range(nb_visits, 0, -1): hours = random.randint(0, 24) minutes = random.randint(0, 60) seconds = random.randint(0, 60) days = random.randint(0, 28) weeks = random.randint(start, end) date_visit = today - timedelta( weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days) visits.append(date_visit) return visits def test_origin_visit_get_random(self, swh_storage): swh_storage.origin_add(data.origins) # Add some random visits within the selection range visits = self._generate_random_visits() visit_type = 'git' # Add visits to those origins for origin in data.origins: for date_visit in visits: visit = swh_storage.origin_visit_add( origin['url'], date=date_visit, type=visit_type) swh_storage.origin_visit_update( origin['url'], visit_id=visit['visit'], status='full') swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats['origin'] == len(data.origins) assert stats['origin_visit'] == len(data.origins) * len(visits) random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit assert random_origin_visit['origin'] is not None original_urls = [o['url'] for o in data.origins] assert random_origin_visit['origin'] in original_urls def test_origin_visit_get_random_nothing_found(self, swh_storage): swh_storage.origin_add(data.origins) visit_type = 'hg' # Add some visits outside of the random generation selection so nothing # will be found by the random selection visits = self._generate_random_visits(nb_visits=3, start=13, end=24) for origin in data.origins: for date_visit in visits: visit = swh_storage.origin_visit_add( origin['url'], date=date_visit, type=visit_type) swh_storage.origin_visit_update( origin['url'], visit_id=visit['visit'], status='full') random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit is None def test_origin_get_by_sha1(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) origins = list(swh_storage.origin_get_by_sha1([ sha1(data.origin['url']) ])) assert len(origins) == 1 assert origins[0]['url'] == data.origin['url'] def test_origin_get_by_sha1_not_found(self, swh_storage): assert swh_storage.origin_get(data.origin) is None origins = list(swh_storage.origin_get_by_sha1([ sha1(data.origin['url']) ])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage): found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 0 found_origins = list(swh_storage.origin_search(data.origin['url'], regexp=True)) assert len(found_origins) == 0 swh_storage.origin_add_one(data.origin) origin_data = { 'url': data.origin['url']} found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data found_origins = list(swh_storage.origin_search( '.' + data.origin['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data swh_storage.origin_add_one(data.origin2) origin2_data = {'url': data.origin2['url']} found_origins = list(swh_storage.origin_search(data.origin2['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data found_origins = list(swh_storage.origin_search( '.' + data.origin2['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data def test_origin_search_no_regexp(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/')) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_substring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_fullstring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('.*/.*', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_visit_add(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] date_visit = datetime.datetime.now(datetime.timezone.utc) # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace( microsecond=round(date_visit.microsecond, -3)) # when origin_visit1 = swh_storage.origin_visit_add( origin_url, type=data.type_visit1, date=date_visit) actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } in actual_origin_visits origin_visit = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.journal.objects) assert ('origin', data.origin2) in objects assert ('origin_visit', origin_visit) in objects def test_origin_visit_get__unknown_origin(self, swh_storage): assert [] == list(swh_storage.origin_visit_get('foo')) def test_origin_visit_add_default_type(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when date_visit = datetime.datetime.now(datetime.timezone.utc) date_visit2 = date_visit + datetime.timedelta(minutes=1) # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace( microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( microsecond=round(date_visit2.microsecond, -3)) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2, ) # then assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) expected_visits = [ { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, ] for visit in expected_visits: assert visit in actual_origin_visits objects = list(swh_storage.journal_writer.journal.objects) assert ('origin', data.origin2) in objects for visit in expected_visits: assert ('origin_visit', visit) in objects def test_origin_visit_add_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin2) with pytest.raises(StorageArgumentException) as cm: swh_storage.origin_visit_add(origin_url, date=[b'foo'], type='git') if type(cm.value) == psycopg2.ProgrammingError: assert cm.value.pgcode \ == psycopg2.errorcodes.UNDEFINED_FUNCTION def test_origin_visit_update(self, swh_storage): # given swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] date_visit = datetime.datetime.now(datetime.timezone.utc) date_visit2 = date_visit + datetime.timedelta(minutes=1) # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace( microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( microsecond=round(date_visit2.microsecond, -3)) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) swh_storage.origin_add_one(data.origin2) origin_url2 = data.origin2['url'] origin_visit3 = swh_storage.origin_visit_add( origin_url2, date=date_visit2, type=data.type_visit3 ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) swh_storage.origin_visit_update( origin_url2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) expected_visits = [{ 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] for visit in expected_visits: assert visit in actual_origin_visits actual_origin_visits_bis = list(swh_storage.origin_visit_get( origin_url, limit=1)) assert actual_origin_visits_bis == [ { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }] actual_origin_visits_ter = list(swh_storage.origin_visit_get( origin_url, last_visit=origin_visit1['visit'])) assert actual_origin_visits_ter == [ { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] actual_origin_visits2 = list(swh_storage.origin_visit_get( origin_url2)) assert actual_origin_visits2 == [ { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, }] data1 = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data3 = { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': None, } data5 = { 'origin': origin_url2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.journal.objects) assert ('origin', data.origin) in objects assert ('origin', data.origin2) in objects assert ('origin_visit', data1) in objects assert ('origin_visit', data2) in objects assert ('origin_visit', data3) in objects assert ('origin_visit', data4) in objects assert ('origin_visit', data5) in objects def test_origin_visit_update_validation(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2, ) with pytest.raises(StorageArgumentException, match='status') as cm: swh_storage.origin_visit_update( origin_url, visit['visit'], status='foobar') if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == \ psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_origin_visit_find_by_date(self, swh_storage): # given swh_storage.origin_add_one(data.origin) swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit3, type=data.type_visit2, ) origin_visit3 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit3, ) # Simple case visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit3) assert visit['visit'] == origin_visit2['visit'] # There are two visits at the same date, the latest must be returned visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit2) assert visit['visit'] == origin_visit3['visit'] def test_origin_visit_find_by_date__unknown_origin(self, swh_storage): swh_storage.origin_visit_find_by_date('foo', data.date_visit2) def test_origin_visit_update_missing_snapshot(self, swh_storage): # given swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1, ) # when swh_storage.origin_visit_update( origin_url, origin_visit['visit'], snapshot=data.snapshot['id']) # then actual_origin_visit = swh_storage.origin_visit_get_by( origin_url, origin_visit['visit']) assert actual_origin_visit['snapshot'] == data.snapshot['id'] # when swh_storage.snapshot_add([data.snapshot]) assert actual_origin_visit['snapshot'] == data.snapshot['id'] def test_origin_visit_get_by(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin_url = data.origin['url'] origin2_url = data.origin2['url'] origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], snapshot=data.snapshot['id']) # Add some other {origin, visit} entries swh_storage.origin_visit_add( origin_url, date=data.date_visit3, type=data.type_visit3, ) swh_storage.origin_visit_add( origin2_url, date=data.date_visit3, type=data.type_visit3, ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_url, 'visit': origin_visit1['visit'], 'date': data.date_visit2, 'type': data.type_visit2, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': data.snapshot['id'], }) # when actual_origin_visit1 = swh_storage.origin_visit_get_by( origin_url, origin_visit1['visit']) # then assert actual_origin_visit1 == expected_origin_visit def test_origin_visit_get_by__unknown_origin(self, swh_storage): assert swh_storage.origin_visit_get_by('foo', 10) is None def test_origin_visit_upsert_new(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when swh_storage.origin_visit_upsert([ { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': '2018-01-01 23:00:00+00', 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ]) # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': origin_url, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ] data1 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.journal.objects) == [ ('origin', data.origin2), ('origin_visit', data1), ('origin_visit', data2)] def test_origin_visit_upsert_existing(self, swh_storage): # given swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] # when origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1, ) swh_storage.origin_visit_upsert([{ 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }]) # then assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }] data1 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.journal.objects) == [ ('origin', data.origin2), ('origin_visit', data1), ('origin_visit', data2)] def test_origin_visit_get_by_no_result(self, swh_storage): swh_storage.origin_add([data.origin]) actual_origin_visit = swh_storage.origin_visit_get_by( data.origin['url'], 999) assert actual_origin_visit is None def test_origin_visit_get_latest(self, swh_storage): swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit3_id = origin_visit3['visit'] origin_visit1 = swh_storage.origin_visit_get_by(origin_url, visit1_id) origin_visit2 = swh_storage.origin_visit_get_by(origin_url, visit2_id) origin_visit3 = swh_storage.origin_visit_get_by(origin_url, visit3_id) # Two visits, both with no snapshot assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) assert swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) is None # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**origin_visit1, 'snapshot': data.complete_snapshot['id']} \ == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no visit # returned assert swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**origin_visit2, 'snapshot': data.empty_snapshot['id']} == \ swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Check that the status filter is still working assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full'], require_snapshot=True) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest(origin_url) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) def test_person_fullname_unicity(self, swh_storage): # given (person injection through revisions for example) revision = data.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(data.revision2) revision2['committer'] = dict(revision['committer']) revision2['committer']['email'] = None revision2['committer']['name'] = None swh_storage.revision_add([revision]) swh_storage.revision_add([revision2]) # when getting added revisions revisions = list( swh_storage.revision_get([revision['id'], revision2['id']])) # then # check committers are the same assert revisions[0]['committer'] == revisions[1]['committer'] def test_snapshot_add_get_empty(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.empty_snapshot['id']) by_id = swh_storage.snapshot_get(data.empty_snapshot['id']) assert by_id == {**data.empty_snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.empty_snapshot, 'next_branch': None} data1 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.empty_snapshot['id'], } assert list(swh_storage.journal_writer.journal.objects) == \ [('origin', data.origin), ('origin_visit', data1), ('snapshot', data.empty_snapshot), ('origin_visit', data2)] def test_snapshot_add_get_complete(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.complete_snapshot['id']) assert actual_result == {'snapshot:add': 1} by_id = swh_storage.snapshot_get(data.complete_snapshot['id']) assert by_id == {**data.complete_snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.complete_snapshot, 'next_branch': None} def test_snapshot_add_many(self, swh_storage): actual_result = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result == {'snapshot:add': 2} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['snapshot'] == 2 def test_snapshot_add_many_from_generator(self, swh_storage): def _snp_gen(): yield data.snapshot yield data.complete_snapshot actual_result = swh_storage.snapshot_add(_snp_gen()) assert actual_result == {'snapshot:add': 2} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()['snapshot'] == 2 def test_snapshot_add_many_incremental(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} actual_result2 = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result2 == {'snapshot:add': 1} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) def test_snapshot_add_twice(self, swh_storage): actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.journal.objects) \ == [('snapshot', data.empty_snapshot)] actual_result = swh_storage.snapshot_add([data.snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.journal.objects) \ == [('snapshot', data.empty_snapshot), ('snapshot', data.snapshot)] def test_snapshot_add_validation(self, swh_storage): snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target_type': 'revision'} with pytest.raises(StorageArgumentException, match='target'): swh_storage.snapshot_add([snap]) snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target': b'\x42'*20} with pytest.raises(StorageArgumentException, match='target_type'): swh_storage.snapshot_add([snap]) def test_snapshot_add_count_branches(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} snp_id = data.complete_snapshot['id'] snp_size = swh_storage.snapshot_count_branches(snp_id) expected_snp_size = { 'alias': 1, 'content': 1, 'directory': 2, 'release': 1, 'revision': 1, 'snapshot': 1, None: 1 } assert snp_size == expected_snp_size def test_snapshot_add_get_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b'release') rel_idx = branch_names.index(b'release') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[rel_idx:] }, 'next_branch': None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { branch_names[0]: branches[branch_names[0]], }, 'next_branch': b'content', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b'directory', branches_count=3) dir_idx = branch_names.index(b'directory') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[dir_idx:dir_idx + 3] }, 'next_branch': branch_names[dir_idx + 3], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.complete_snapshot['id']) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['release', 'revision']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] in ['release', 'revision'] }, 'next_branch': None, } assert snapshot == expected_snapshot snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['alias']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] == 'alias' }, 'next_branch': None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory2', b'release') }, 'next_branch': None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { b'directory': branches[b'directory'] }, 'next_branch': b'directory2', } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=2) expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory', b'directory2') }, 'next_branch': b'release', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2', branches_count=1) dir_idx = branch_names.index(b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { branch_names[dir_idx]: branches[branch_names[dir_idx]], }, 'next_branch': b'release', } assert snapshot == expected_snapshot def test_snapshot_add_get(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.snapshot['id']) by_id = swh_storage.snapshot_get(data.snapshot['id']) assert by_id == {**data.snapshot, 'next_branch': None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.snapshot, 'next_branch': None} origin_visit_info = swh_storage.origin_visit_get_by( origin_url, visit_id) assert origin_visit_info['snapshot'] == data.snapshot['id'] def test_snapshot_add_nonexistent_visit(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) visit_id = 54164461156 swh_storage.journal_writer.journal.objects[:] = [] swh_storage.snapshot_add([data.snapshot]) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_update( origin_url, visit_id, snapshot=data.snapshot['id']) assert list(swh_storage.journal_writer.journal.objects) == [ ('snapshot', data.snapshot)] def test_snapshot_add_twice__by_origin_visit(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.snapshot['id']) by_ov1 = swh_storage.snapshot_get_by_origin_visit( origin_url, visit1_id) assert by_ov1 == {**data.snapshot, 'next_branch': None} origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.snapshot['id']) by_ov2 = swh_storage.snapshot_get_by_origin_visit( origin_url, visit2_id) assert by_ov2 == {**data.snapshot, 'next_branch': None} data1 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': origin_url, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } data3 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } assert list(swh_storage.journal_writer.journal.objects) \ == [('origin', data.origin), ('origin_visit', data1), ('snapshot', data.snapshot), ('origin_visit', data2), ('origin_visit', data3), ('origin_visit', data4)] def test_snapshot_get_latest(self, swh_storage): origin_url = data.origin['url'] swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit3, ) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add snapshot to visit1, latest snapshot = visit 1 snapshot swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update(origin_url, visit1_id, status='full') assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**data.empty_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Check that the status filter is still working assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_latest__missing_snapshot(self, swh_storage): # Origin does not exist origin_url = data.origin['url'] assert swh_storage.snapshot_get_latest(origin_url) is None swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add unknown snapshot to visit1, check that the inconsistency is # detected swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) with pytest.raises(Exception): # XXX: should the exception be more specific than this? swh_storage.snapshot_get_latest(origin_url) # Status filter: both visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') with pytest.raises(Exception): # XXX: should the exception be more specific than this? swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']), # Actually add the snapshot and check status filter again swh_storage.snapshot_add([data.complete_snapshot]) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Add unknown snapshot to visit2 and check that the inconsistency # is detected swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.snapshot['id']) with pytest.raises(Exception): # XXX: should the exception be more specific than this? swh_storage.snapshot_get_latest( origin_url) # Actually add that snapshot and check that the new one is returned swh_storage.snapshot_add([data.snapshot]) assert{**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_random(self, swh_storage): swh_storage.snapshot_add( [data.snapshot, data.empty_snapshot, data.complete_snapshot]) assert swh_storage.snapshot_get_random() in { data.snapshot['id'], data.empty_snapshot['id'], data.complete_snapshot['id']} def test_snapshot_missing(self, swh_storage): snap = data.snapshot missing_snap = data.empty_snapshot snapshots = [snap['id'], missing_snap['id']] swh_storage.snapshot_add([snap]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snap['id']] def test_stat_counters(self, swh_storage): expected_keys = ['content', 'directory', 'origin', 'revision'] # Initially, all counters are 0 swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: assert counters[key] == 0 # Add a content. Only the content counter should increase. swh_storage.content_add([data.cont]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: if key != 'content': assert counters[key] == 0 assert counters['content'] == 1 # Add other objects. Check their counter increased as well. swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin=data.origin2['url'], date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( data.origin2['url'], origin_visit1['visit'], snapshot=data.snapshot['id']) swh_storage.directory_add([data.dir]) swh_storage.revision_add([data.revision]) swh_storage.release_add([data.release]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert counters['content'] == 1 assert counters['directory'] == 1 assert counters['snapshot'] == 1 assert counters['origin'] == 1 assert counters['origin_visit'] == 1 assert counters['revision'] == 1 assert counters['release'] == 1 assert counters['snapshot'] == 1 if 'person' in counters: assert counters['person'] == 3 def test_content_find_ctime(self, swh_storage): cont = data.cont.copy() del cont['data'] now = datetime.datetime.now(tz=datetime.timezone.utc) cont['ctime'] = now swh_storage.content_add_metadata([cont]) actually_present = swh_storage.content_find({'sha1': cont['sha1']}) # check ctime up to one second dt = actually_present[0]['ctime'] - now assert abs(dt.total_seconds()) <= 1 del actually_present[0]['ctime'] assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } def test_content_find_with_present_content(self, swh_storage): # 1. with something to find cont = data.cont swh_storage.content_add([cont, data.cont2]) actually_present = swh_storage.content_find( {'sha1': cont['sha1']} ) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 2. with something to find actually_present = swh_storage.content_find( {'sha1_git': cont['sha1_git']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 3. with something to find actually_present = swh_storage.content_find( {'sha256': cont['sha256']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } # 4. with something to find actually_present = swh_storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } def test_content_find_with_non_present_content(self, swh_storage): # 1. with something that does not exist missing_cont = data.missing_cont actually_present = swh_storage.content_find( {'sha1': missing_cont['sha1']}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {'sha1_git': missing_cont['sha1_git']}) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find( {'sha256': missing_cont['sha256']}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) # Inject the data swh_storage.content_add([cont1, duplicate_cont]) finder = {'blake2s256': duplicate_cont['blake2s256'], 'sha256': duplicate_cont['sha256']} actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result def test_content_find_with_duplicate_sha256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 for hashalgo in ('sha1', 'sha1_git', 'blake2s256'): value = bytearray(duplicate_cont[hashalgo]) value[0] += 1 duplicate_cont[hashalgo] = bytes(value) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'sha256': duplicate_cont['sha256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 2 cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] assert expected_result == sorted(actual_result, key=lambda x: x['sha1']) # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 1 actual_result[0].pop('ctime') expected_result = [duplicate_cont] assert actual_result[0] == duplicate_cont def test_content_find_with_duplicate_blake2s256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) sha256_array = bytearray(duplicate_cont['sha256']) sha256_array[0] += 1 duplicate_cont['sha256'] = bytes(sha256_array) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) actual_result[0].pop('ctime') expected_result = [ duplicate_cont ] assert expected_result == actual_result def test_content_find_bad_input(self, swh_storage): # 1. with bad input with pytest.raises(StorageArgumentException): swh_storage.content_find({}) # empty is bad # 2. with bad input with pytest.raises(StorageArgumentException): swh_storage.content_find( {'unknown-sha1': 'something'}) # not the right key def test_object_find_by_sha1_git(self, swh_storage): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } swh_storage.content_add([data.cont]) sha1_gits.append(data.cont['sha1_git']) expected[data.cont['sha1_git']] = [{ 'sha1_git': data.cont['sha1_git'], 'type': 'content', }] swh_storage.directory_add([data.dir]) sha1_gits.append(data.dir['id']) expected[data.dir['id']] = [{ 'sha1_git': data.dir['id'], 'type': 'directory', }] swh_storage.revision_add([data.revision]) sha1_gits.append(data.revision['id']) expected[data.revision['id']] = [{ 'sha1_git': data.revision['id'], 'type': 'revision', }] swh_storage.release_add([data.release]) sha1_gits.append(data.release['id']) expected[data.release['id']] = [{ 'sha1_git': data.release['id'], 'type': 'release', }] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_tool_add(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None # does not exist # add it actual_tools = swh_storage.tool_add([tool]) assert len(actual_tools) == 1 actual_tool = actual_tools[0] assert actual_tool is not None # now it exists new_id = actual_tool.pop('id') assert actual_tool == tool actual_tools2 = swh_storage.tool_add([tool]) actual_tool2 = actual_tools2[0] assert actual_tool2 is not None # now it exists new_id2 = actual_tool2.pop('id') assert new_id == new_id2 assert actual_tool == actual_tool2 def test_tool_add_multiple(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(swh_storage.tool_add([tool])) assert len(actual_tools) == 1 new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = swh_storage.tool_add(new_tools) assert len(actual_tools) == 2 # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') assert _id is not None assert tool in new_tools def test_tool_get_missing(self, swh_storage): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get_missing_context(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } expected_tool = swh_storage.tool_add([tool])[0] # when actual_tool = swh_storage.tool_get(tool) # then assert expected_tool == actual_tool def test_metadata_provider_get(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get(6459456445615) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get(provider_id) expected_provider = { 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] } # then del actual_provider['id'] assert actual_provider, expected_provider def test_metadata_provider_get_by(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # then assert provider_id, actual_provider['id'] def test_origin_metadata_add(self, swh_storage): # given origin = data.origin swh_storage.origin_add([origin])[0] tools = swh_storage.tool_add([data.metadata_tool]) tool = tools[0] swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # when adding for the same origin 2 metadatas n_om = len(list(swh_storage.origin_metadata_get_by(origin['url']))) swh_storage.origin_metadata_add( origin['url'], data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin['url'], '2015-01-01 23:00:00+00', provider['id'], tool['id'], data.origin_metadata2['metadata']) n_actual_om = len(list( swh_storage.origin_metadata_get_by(origin['url']))) # then assert n_actual_om == n_om + 2 def test_origin_metadata_get(self, swh_storage): # given origin_url = data.origin['url'] origin_url2 = data.origin2['url'] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) swh_storage.metadata_provider_add(data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( origin_url, data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin_url2, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) swh_storage.origin_metadata_add( origin_url, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) all_metadatas = list(sorted(swh_storage.origin_metadata_get_by( origin_url), key=lambda x: x['discovery_date'])) metadatas_for_origin2 = list(swh_storage.origin_metadata_get_by( origin_url2)) expected_results = [{ 'origin_url': origin_url, 'discovery_date': datetime.datetime( 2015, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }, { 'origin_url': origin_url, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }] # then assert len(all_metadatas) == 2 assert len(metadatas_for_origin2) == 1 assert all_metadatas == expected_results def test_metadata_provider_add(self, swh_storage): provider = { 'provider_name': 'swMATH', 'provider_type': 'registry', 'provider_url': 'http://www.swmath.org/', 'metadata': { 'email': 'contact@swmath.org', 'license': 'All rights reserved' } } provider['id'] = provider_id = swh_storage.metadata_provider_add( **provider) assert provider == swh_storage.metadata_provider_get_by( {'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/'}) assert provider == swh_storage.metadata_provider_get(provider_id) def test_origin_metadata_get_by_provider_type(self, swh_storage): # given origin_url = data.origin['url'] origin_url2 = data.origin2['url'] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) provider1_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider1 = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert provider1 == swh_storage.metadata_provider_get(provider1_id) provider2_id = swh_storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = swh_storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) assert provider2 == swh_storage.metadata_provider_get(provider2_id) # using the only tool now inserted in the data.sql, but for this # provider should be a crawler tool (not yet implemented) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( origin_url, data.origin_metadata['discovery_date'], provider1['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( origin_url2, data.origin_metadata2['discovery_date'], provider2['id'], tool['id'], data.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(swh_storage.origin_metadata_get_by( origin_url2, provider_type)) for item in m_by_provider: if 'id' in item: del item['id'] expected_results = [{ 'origin_url': origin_url2, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider2['id'], 'provider_name': 'swMATH', 'provider_type': provider_type, 'provider_url': 'http://www.swmath.org/', 'tool_id': tool['id'] }] # then assert len(m_by_provider) == 1 assert m_by_provider == expected_results class TestStorageGeneratedData: def test_generate_content_get(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c['status'] != 'absent'] # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents_with_data] # retrieve contents actual_contents = list(swh_storage.content_get(get_sha1s)) assert None not in actual_contents assert_contents_ok(contents_with_data, actual_contents) def test_generate_content_get_metadata(self, swh_storage, swh_contents): # input the list of sha1s we want from storage expected_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = [c['sha1'] for c in expected_contents] # retrieve contents meta_contents = swh_storage.content_get_metadata(get_sha1s) assert len(list(meta_contents)) == len(get_sha1s) actual_contents = [] for contents in meta_contents.values(): actual_contents.extend(contents) keys_to_check = {'length', 'status', 'sha1', 'sha1_git', 'sha256', 'blake2s256'} assert_contents_ok(expected_contents, actual_contents, keys_to_check=keys_to_check) def test_generate_content_get_range(self, swh_storage, swh_contents): """content_get_range returns complete range""" present_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[2] end = get_sha1s[-2] actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_full(self, swh_storage, swh_contents): """content_get_range for a full range returns all available contents""" present_contents = [c for c in swh_contents if c['status'] != 'absent'] start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_empty(self, swh_storage, swh_contents): """content_get_range for an empty range returns nothing""" start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(end, start) assert actual_result['next'] is None assert len(actual_result['contents']) == 0 def test_generate_content_get_range_limit_none(self, swh_storage): """content_get_range call with wrong limit input should fail""" with pytest.raises(StorageArgumentException) as e: swh_storage.content_get_range(start=None, end=None, limit=None) assert e.value.args == ('limit should not be None',) def test_generate_content_get_range_no_limit( self, swh_storage, swh_contents): """content_get_range returns contents within range provided""" # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = swh_storage.content_get_range(start, end) actual_contents = actual_result['contents'] assert actual_result['next'] is None assert len(actual_contents) == len(get_sha1s) expected_contents = [c for c in swh_contents if c['status'] != 'absent'] assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_generate_content_get_range_limit(self, swh_storage, swh_contents): """content_get_range paginates results if limit exceeded""" contents_map = {c['sha1']: c for c in swh_contents} # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to n-1 results limited_results = len(get_sha1s) - 1 actual_result = swh_storage.content_get_range( start, end, limit=limited_results) actual_contents = actual_result['contents'] assert actual_result['next'] == get_sha1s[-1] assert len(actual_contents) == limited_results expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] assert_contents_ok( expected_contents, actual_contents, ['sha1']) # retrieve next part actual_results2 = swh_storage.content_get_range(start=end, end=end) assert actual_results2['next'] is None actual_contents2 = actual_results2['contents'] assert len(actual_contents2) == 1 assert_contents_ok( [contents_map[get_sha1s[-1]]], actual_contents2, ['sha1']) def test_origin_get_range_from_zero(self, swh_storage, swh_origins): actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=0)) assert len(actual_origins) == 0 actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=1)) assert len(actual_origins) == 1 assert actual_origins[0]['id'] == 1 assert actual_origins[0]['url'] == swh_origins[0]['url'] @pytest.mark.parametrize('origin_from,origin_count', [ (1, 1), (1, 10), (1, 20), (1, 101), (11, 0), (11, 10), (91, 11)]) def test_origin_get_range( self, swh_storage, swh_origins, origin_from, origin_count): actual_origins = list( swh_storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) origins_with_id = list(enumerate(swh_origins, start=1)) expected_origins = [ { 'url': origin['url'], 'id': origin_id, } for (origin_id, origin) in origins_with_id[origin_from-1:origin_from+origin_count-1] ] assert actual_origins == expected_origins @pytest.mark.parametrize('limit', [1, 7, 10, 100, 1000]) def test_origin_list(self, swh_storage, swh_origins, limit): returned_origins = [] page_token = None i = 0 while True: result = swh_storage.origin_list( page_token=page_token, limit=limit) assert len(result['origins']) <= limit returned_origins.extend( origin['url'] for origin in result['origins']) i += 1 page_token = result.get('next_page_token') if page_token is None: assert i*limit >= len(swh_origins) break else: assert len(result['origins']) == limit expected_origins = [origin['url'] for origin in swh_origins] assert sorted(returned_origins) == sorted(expected_origins) ORIGINS = [ 'https://github.com/user1/repo1', 'https://github.com/user2/repo1', 'https://github.com/user3/repo1', 'https://gitlab.com/user1/repo1', 'https://gitlab.com/user2/repo1', 'https://forge.softwareheritage.org/source/repo1', ] def test_origin_count(self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) assert swh_storage.origin_count('github') == 3 assert swh_storage.origin_count('gitlab') == 2 assert swh_storage.origin_count('.*user.*', regexp=True) == 5 assert swh_storage.origin_count('.*user.*', regexp=False) == 0 assert swh_storage.origin_count('.*user1.*', regexp=True) == 2 assert swh_storage.origin_count('.*user1.*', regexp=False) == 0 def test_origin_count_with_visit_no_visits(self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) # none of them have visits, so with_visit=True => 0 assert swh_storage.origin_count('github', with_visit=True) == 0 assert swh_storage.origin_count('gitlab', with_visit=True) == 0 assert swh_storage.origin_count('.*user.*', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('.*user.*', regexp=False, with_visit=True) == 0 assert swh_storage.origin_count('.*user1.*', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('.*user1.*', regexp=False, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_no_snapshot( self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) swh_storage.origin_visit_add( origin='https://github.com/user1/repo1', date=now, type='git') assert swh_storage.origin_count('github', with_visit=False) == 3 # it has a visit, but no snapshot, so with_visit=True => 0 assert swh_storage.origin_count('github', with_visit=True) == 0 assert swh_storage.origin_count('gitlab', with_visit=False) == 2 # these gitlab origins have no visit assert swh_storage.origin_count('gitlab', with_visit=True) == 0 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=False) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=True) == 0 assert swh_storage.origin_count('github', regexp=True, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_and_snapshot( self, swh_storage): swh_storage.origin_add([{'url': url} for url in self.ORIGINS]) now = datetime.datetime.now(tz=datetime.timezone.utc) swh_storage.snapshot_add([data.snapshot]) visit = swh_storage.origin_visit_add( origin='https://github.com/user1/repo1', date=now, type='git') swh_storage.origin_visit_update( origin='https://github.com/user1/repo1', visit_id=visit['visit'], snapshot=data.snapshot['id']) assert swh_storage.origin_count('github', with_visit=False) == 3 # github/user1 has a visit and a snapshot, so with_visit=True => 1 assert swh_storage.origin_count('github', with_visit=True) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=False) == 1 assert swh_storage.origin_count('github.*user1', regexp=True, with_visit=True) == 1 assert swh_storage.origin_count('github', regexp=True, with_visit=True) == 1 @settings(suppress_health_check=[HealthCheck.too_slow]) @given(strategies.lists(objects(), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: obj = obj.to_dict() if obj_type == 'origin_visit': origin = obj.pop('origin') swh_storage.origin_add_one({'url': origin}) if 'visit' in obj: del obj['visit'] swh_storage.origin_visit_add( origin, obj['date'], obj['type']) else: if obj_type == 'content' and obj['status'] == 'absent': obj_type = 'skipped_content' method = getattr(swh_storage, obj_type + '_add') try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self, swh_storage): swh_storage.objstorage.content_add = Mock( side_effect=Exception('mocked broken objstorage') ) with pytest.raises(Exception) as e: swh_storage.content_add([data.cont]) assert e.value.args == ('mocked broken objstorage',) missing = list(swh_storage.content_missing([data.cont])) assert missing == [data.cont['sha1']] @pytest.mark.db class TestStorageRaceConditions: @pytest.mark.xfail def test_content_add_race(self, swh_storage): results = queue.Queue() def thread(): try: with db_transaction(swh_storage) as (db, cur): ret = swh_storage.content_add([data.cont], db=db, cur=cur) results.put((threading.get_ident(), 'data', ret)) except Exception as e: results.put((threading.get_ident(), 'exc', e)) t1 = threading.Thread(target=thread) t2 = threading.Thread(target=thread) t1.start() # this avoids the race condition # import time # time.sleep(1) t2.start() t1.join() t2.join() r1 = results.get(block=False) r2 = results.get(block=False) with pytest.raises(queue.Empty): results.get(block=False) assert r1[0] != r2[0] assert r1[1] == 'data', 'Got exception %r in Thread%s' % (r1[2], r1[0]) assert r2[1] == 'data', 'Got exception %r in Thread%s' % (r2[2], r2[0]) @pytest.mark.db class TestPgStorage: """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update_with_new_cols(self, swh_storage): swh_storage.journal_writer.journal = None # TODO, not supported with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(data.cont2) swh_storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' swh_storage.content_update([cont], keys=['test', 'test2']) with db_transaction(swh_storage) as (_, cur): cur.execute( '''SELECT sha1, sha1_git, sha256, length, status, test, test2 FROM content WHERE sha1 = %s''', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2']) with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content drop column test, drop column test2""") def test_content_add_db(self, swh_storage): cont = data.cont actual_result = swh_storage.content_add([cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] in swh_storage.objstorage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') expected_cont = cont.copy() del expected_cont['data'] journal_objects = list(swh_storage.journal_writer.journal.objects) for (obj_type, obj) in journal_objects: del obj['ctime'] assert journal_objects == [('content', expected_cont)] def test_content_add_metadata_db(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { 'content:add': 1, } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] not in swh_storage.objstorage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') assert list(swh_storage.journal_writer.journal.objects) == [ ('content', cont)] def test_skipped_content_add_db(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2['blake2s256'] = None actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop('skipped_content:add') <= 3 assert actual_result == {} with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') dbdata = cur.fetchall() assert len(dbdata) == 2 assert dbdata[0] == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') assert dbdata[1] == (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') diff --git a/swh/storage/tests/test_utils.py b/swh/storage/tests/test_utils.py new file mode 100644 index 00000000..b3422e65 --- /dev/null +++ b/swh/storage/tests/test_utils.py @@ -0,0 +1,35 @@ +# Copyright (C) 2020 The Software Heritage developers +# See the AUTHORS file at the top-level directory of this distribution +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from swh.model.hashutil import hash_to_bytes +from swh.storage.utils import extract_collision_hash + + +def test_extract_collision_hash(): + for msg, expected_result in [ + ( + 'Key (sha1)=(\\x34973274ccef6ab4dfaaf86599792fa9c3fe4689) ...', + ('sha1', hash_to_bytes( + '34973274ccef6ab4dfaaf86599792fa9c3fe4689')), + ), + ( + 'Key (sha1_git)=(\\x34973274ccef6ab4dfaaf86599792fa9c3fe4699) already exists', # noqa + ('sha1_git', hash_to_bytes( + '34973274ccef6ab4dfaaf86599792fa9c3fe4699')), + ), + ( + 'Key (sha256)=(\\x673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a) ...', # noqa + ('sha256', hash_to_bytes( + '673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a')) # noqa + ), + ( + 'Key (blake2s)=(\\xd5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d) ...', # noqa + ('blake2s', hash_to_bytes( + 'd5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d')) # noqa + ), + ]: + assert extract_collision_hash(msg) == expected_result + + assert extract_collision_hash('Nothing matching') is None diff --git a/swh/storage/utils.py b/swh/storage/utils.py index 95f3ecab..3697da87 100644 --- a/swh/storage/utils.py +++ b/swh/storage/utils.py @@ -1,42 +1,68 @@ -# Copyright (C) 2019 The Software Heritage developers +# Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information +import re + from typing import Optional, Tuple +from swh.model.hashutil import hash_to_bytes + def _is_power_of_two(n: int) -> bool: return n > 0 and n & (n-1) == 0 def get_partition_bounds_bytes( i: int, n: int, nb_bytes: int) -> Tuple[bytes, Optional[bytes]]: r"""Splits the range [0; 2^(nb_bytes*8)) into n same-length intervals, and returns the boundaries of this interval (both inclusive); or None as upper bound, if this is the last partition n must be a power of 2. >>> get_partition_bounds_bytes(0, 16, 2) == (b'\x00\x00', b'\x10\x00') True >>> get_partition_bounds_bytes(1, 16, 2) == (b'\x10\x00', b'\x20\x00') True >>> get_partition_bounds_bytes(14, 16, 2) == (b'\xe0\x00', b'\xf0\x00') True >>> get_partition_bounds_bytes(15, 16, 2) == (b'\xf0\x00', None) True """ if not _is_power_of_two(n): raise ValueError('number of partitions must be a power of two') if not 0 <= i < n: raise ValueError( 'partition index must be between 0 and the number of partitions.') space_size = 1 << (nb_bytes*8) partition_size = space_size//n start = (partition_size*i).to_bytes(nb_bytes, 'big') end = None if i == n-1 \ else (partition_size*(i+1)).to_bytes(nb_bytes, 'big') return (start, end) + + +def extract_collision_hash(error_message: str) -> Optional[Tuple[str, bytes]]: + """Utilities to extract the hash information from a hash collision error. + + Hash collision error message are of the form: + 'Key ()=([^)]+)\)=\(\\x(?P[a-f0-9]+)\) \w*' + result = re.match(pattern, error_message) + if result: + hash_type = result.group('type') + hash_id = result.group('id') + return hash_type, hash_to_bytes(hash_id) + return None