diff --git a/swh/storage/__init__.py b/swh/storage/__init__.py index 757b615d..7d82a4ab 100644 --- a/swh/storage/__init__.py +++ b/swh/storage/__init__.py @@ -1,104 +1,101 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import warnings STORAGE_IMPLEMENTATION = { "pipeline", "local", "remote", "memory", "filter", "buffer", "retry", - "validate", "cassandra", } def get_storage(cls, **kwargs): """Get a storage object of class `storage_class` with arguments `storage_args`. Args: storage (dict): dictionary with keys: - cls (str): storage's class, either local, remote, memory, filter, buffer - args (dict): dictionary with keys Returns: an instance of swh.storage.Storage or compatible class Raises: ValueError if passed an unknown storage class. """ if cls not in STORAGE_IMPLEMENTATION: raise ValueError( "Unknown storage class `%s`. Supported: %s" % (cls, ", ".join(STORAGE_IMPLEMENTATION)) ) if "args" in kwargs: warnings.warn( 'Explicit "args" key is deprecated, use keys directly instead.', DeprecationWarning, ) kwargs = kwargs["args"] if cls == "pipeline": return get_storage_pipeline(**kwargs) if cls == "remote": from .api.client import RemoteStorage as Storage elif cls == "local": from .storage import Storage elif cls == "cassandra": from .cassandra import CassandraStorage as Storage elif cls == "memory": from .in_memory import InMemoryStorage as Storage elif cls == "filter": from .filter import FilteringProxyStorage as Storage elif cls == "buffer": from .buffer import BufferingProxyStorage as Storage elif cls == "retry": from .retry import RetryingProxyStorage as Storage - elif cls == "validate": - from .validate import ValidatingProxyStorage as Storage return Storage(**kwargs) def get_storage_pipeline(steps): """Recursively get a storage object that may use other storage objects as backends. Args: steps (List[dict]): List of dicts that may be used as kwargs for `get_storage`. Returns: an instance of swh.storage.Storage or compatible class Raises: ValueError if passed an unknown storage class. """ storage_config = None for step in reversed(steps): if "args" in step: warnings.warn( 'Explicit "args" key is deprecated, use keys directly ' "instead.", DeprecationWarning, ) step = { "cls": step["cls"], **step["args"], } if storage_config: step["storage"] = storage_config storage_config = step return get_storage(**storage_config) diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py index feb5996f..41008892 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,1187 +1,1189 @@ # 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 itertools import json import random import re from typing import Any, Dict, List, Iterable, Optional, Union import attr from swh.core.api.serializers import msgpack_loads, msgpack_dumps from swh.model.identifiers import parse_swhid, SWHID from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.model.model import ( Revision, Release, Directory, DirectoryEntry, Content, SkippedContent, OriginVisit, OriginVisitStatus, Snapshot, Origin, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, RawExtrinsicMetadata, ) from swh.storage.objstorage import ObjStorage from swh.storage.writer import JournalWriter from swh.storage.utils import map_optional, now from ..exc import StorageArgumentException, HashCollision from .common import TOKEN_BEGIN, TOKEN_END from .converters import ( revision_to_db, revision_from_db, release_to_db, release_from_db, row_to_visit_status, ) from .cql import CqlRunner from .schema import HASH_ALGORITHMS # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 class CassandraStorage: def __init__(self, hosts, keyspace, objstorage, port=9042, journal_writer=None): self._cql_runner = CqlRunner(hosts, keyspace, port) self.journal_writer = JournalWriter(journal_writer) self.objstorage = ObjStorage(objstorage) def check_config(self, *, check_write): self._cql_runner.check_read() return True def _content_get_from_hash(self, algo, hash_) -> Iterable: """From the name of a hash algorithm and a value of that hash, looks up the "hash -> token" secondary table (content_by_{algo}) to get tokens. Then, looks up the main table (content) to get all contents with that token, and filters out contents whose hash doesn't match.""" found_tokens = self._cql_runner.content_get_tokens_from_single_hash(algo, hash_) for token in found_tokens: # Query the main table ('content'). res = self._cql_runner.content_get_from_token(token) for row in res: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) == hash_: yield row def _content_add(self, contents: List[Content], with_data: bool) -> Dict: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.content_get_from_pk(c.to_dict()) ] 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 # Check for sha1 or sha1_git collisions. This test is not atomic # with the insertion, so it won't detect a collision if both # contents are inserted at the same time, but it's good enough. # # The proper way to do it would probably be a BATCH, but this # would be inefficient because of the number of partitions we # need to affect (len(HASH_ALGORITHMS)+1, which is currently 5) for algo in {"sha1", "sha1_git"}: collisions = [] # Get tokens of 'content' rows with the same value for # sha1/sha1_git rows = self._content_get_from_hash(algo, content.get_hash(algo)) for row in rows: if getattr(row, algo) != content.get_hash(algo): # collision of token(partition key), ignore this # row continue for algo in HASH_ALGORITHMS: if getattr(row, algo) != content.get_hash(algo): # This hash didn't match; discard the row. collisions.append( {algo: getattr(row, algo) for algo in HASH_ALGORITHMS} ) if collisions: collisions.append(content.hashes()) raise HashCollision(algo, content.get_hash(algo), collisions) (token, insertion_finalizer) = self._cql_runner.content_add_prepare(content) # Then add to index tables for algo in HASH_ALGORITHMS: self._cql_runner.content_index_add_one(algo, content, token) # Then to the main table insertion_finalizer() summary = { "content:add": content_add, } if with_data: summary["content:add:bytes"] = content_add_bytes return summary def content_add(self, content: Iterable[Content]) -> Dict: contents = [attr.evolve(c, ctime=now()) for c in content] return self._content_add(list(contents), with_data=True) def content_update(self, content, keys=[]): raise NotImplementedError( "content_update is not supported by the Cassandra backend" ) 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') for row in self._content_get_from_hash("sha1", sha1): content_metadata = row._asdict() content_metadata.pop("ctime") result[content_metadata["sha1"]].append(content_metadata) 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] results = [] rows = self._content_get_from_hash(common_algo, content[common_algo]) for row in rows: # Re-check all the hashes, in case of collisions (either of the # hash of the partition key, or the hashes in it) for algo in HASH_ALGORITHMS: if content.get(algo) and getattr(row, algo) != content[algo]: # This hash didn't match; discard the row. break else: # All hashes match, keep this row. results.append( { **row._asdict(), "ctime": row.ctime.replace(tzinfo=datetime.timezone.utc), } ) 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_get_from_hash(self, algo, hash_) -> Iterable: """From the name of a hash algorithm and a value of that hash, looks up the "hash -> token" secondary table (skipped_content_by_{algo}) to get tokens. Then, looks up the main table (content) to get all contents with that token, and filters out contents whose hash doesn't match.""" found_tokens = self._cql_runner.skipped_content_get_tokens_from_single_hash( algo, hash_ ) for token in found_tokens: # Query the main table ('content'). res = self._cql_runner.skipped_content_get_from_token(token) for row in res: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) == hash_: yield row def _skipped_content_add(self, contents: Iterable[SkippedContent]) -> Dict: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.skipped_content_get_from_pk(c.to_dict()) ] self.journal_writer.skipped_content_add(contents) for content in contents: # Compute token of the row in the main table (token, insertion_finalizer) = self._cql_runner.skipped_content_add_prepare( content ) # Then add to index tables for algo in HASH_ALGORITHMS: self._cql_runner.skipped_content_index_add_one(algo, content, token) # Then to the main table insertion_finalizer() return {"skipped_content:add": len(contents)} def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: contents = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(contents) def skipped_content_missing(self, contents): for content in contents: if not self._cql_runner.skipped_content_get_from_pk(content): yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} def directory_add(self, directories: Iterable[Directory]) -> Dict: directories = list(directories) # Filter out directories that are already inserted. missing = self.directory_missing([dir_.id for dir_ in directories]) directories = [dir_ for dir_ in directories if dir_.id in missing] self.journal_writer.directory_add(directories) for directory in directories: # Add directory entries to the 'directory_entry' table for entry in directory.entries: self._cql_runner.directory_entry_add_one( {**entry.to_dict(), "directory_id": directory.id} ) # 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: revobject = revision_to_db(revision) if revobject: # Add parents first for (rank, parent) in enumerate(revobject["parents"]): self._cql_runner.revision_parent_add_one( revobject["id"], rank, parent ) # Then write the main revision row. # Writing this after all parents were written ensures that # read endpoints don't return a partial view while writing # the parents self._cql_runner.revision_add_one(revobject) return {"revision:add": len(revisions)} 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 = tuple(row.parent_id for row in parent_rows) rev = revision_from_db(row, parents=parents) revs[rev.id] = rev.to_dict() for rev_id in revisions: yield revs.get(rev_id) def _get_parent_revs(self, rev_ids, seen, limit, short): if limit and len(seen) >= limit: return rev_ids = [id_ for id_ in rev_ids if id_ not in seen] if not rev_ids: return seen |= set(rev_ids) # We need this query, even if short=True, to return consistent # results (ie. not return only a subset of a revision's parents # if it is being written) if short: rows = self._cql_runner.revision_get_ids(rev_ids) else: rows = self._cql_runner.revision_get(rev_ids) for row in rows: # TODO: use a single query to get all parents? # (it might have less latency, but requires less code and more # bandwidth (because revision id would be part of each returned # row) parent_rows = self._cql_runner.revision_parent_get(row.id) # parent_rank is the clustering key, so results are already # sorted by rank. parents = tuple(row.parent_id for row in parent_rows) if short: yield (row.id, parents) else: rev = revision_from_db(row, parents=parents) yield rev.to_dict() yield from self._get_parent_revs(parents, seen, limit, short) def revision_log(self, revisions, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, False) def revision_shortlog(self, revisions, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, True) def revision_get_random(self): return self._cql_runner.revision_get_random().id def release_add(self, releases: Iterable[Release]) -> Dict: to_add = [] for rel in releases: if rel not in to_add: to_add.append(rel) missing = set(self.release_missing([rel.id for rel in to_add])) to_add = [rel for rel in to_add if rel.id in missing] self.journal_writer.release_add(to_add) for release in to_add: if release: self._cql_runner.release_add_one(release_to_db(release)) return {"release:add": len(to_add)} def release_missing(self, releases): return self._cql_runner.release_missing(releases) def release_get(self, releases): rows = self._cql_runner.release_get(releases) rels = {} for row in rows: release = release_from_db(row) rels[row.id] = release.to_dict() for rel_id in releases: yield rels.get(rel_id) def release_get_random(self): return self._cql_runner.release_get_random().id def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: + snapshots = list(snapshots) missing = self._cql_runner.snapshot_missing([snp.id for snp in snapshots]) snapshots = [snp for snp in snapshots if snp.id in missing] for snapshot in snapshots: self.journal_writer.snapshot_add([snapshot]) # Add branches for (branch_name, branch) in snapshot.branches.items(): if branch is None: target_type = None target = None else: target_type = branch.target_type.value target = branch.target self._cql_runner.snapshot_branch_add_one( { "snapshot_id": snapshot.id, "name": branch_name, "target_type": target_type, "target": target, } ) # 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.origin_visit_get_by(origin, visit) except IndexError: return None return self.snapshot_get(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: Dict[str, Any]) -> Optional[Dict[str, Any]]: if "id" in origin: raise StorageArgumentException("Origin ids are not supported.") if "url" not in origin: raise StorageArgumentException("Missing origin url") rows = self._cql_runner.origin_get_by_url(origin["url"]) rows = list(rows) if rows: assert len(rows) == 1 result = rows[0]._asdict() return { "url": result["url"], } 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]) -> Dict[str, int]: + origins = list(origins) known_origins = [ Origin.from_dict(d) for d in self.origin_get([origin.to_dict() for origin in origins]) if d is not None ] to_add = [origin for origin in origins if origin not in known_origins] self.journal_writer.origin_add(to_add) for origin in to_add: self._cql_runner.origin_add_one(origin) return {"origin:add": len(to_add)} def origin_visit_add(self, visits: Iterable[OriginVisit]) -> Iterable[OriginVisit]: for visit in visits: origin = self.origin_get({"url": visit.origin}) if not origin: # Cannot add a visit without an origin raise StorageArgumentException("Unknown origin %s", visit.origin) all_visits = [] nb_visits = 0 for visit in visits: nb_visits += 1 if not visit.visit: visit_id = self._cql_runner.origin_generate_unique_visit_id( visit.origin ) visit = attr.evolve(visit, visit=visit_id) self.journal_writer.origin_visit_add([visit]) self._cql_runner.origin_visit_add_one(visit) assert visit.visit is not None all_visits.append(visit) self._origin_visit_status_add( OriginVisitStatus( origin=visit.origin, visit=visit.visit, date=visit.date, status="created", snapshot=None, ) ) return all_visits def _origin_visit_status_add(self, visit_status: OriginVisitStatus) -> None: """Add an origin visit status""" self.journal_writer.origin_visit_status_add([visit_status]) self._cql_runner.origin_visit_status_add_one(visit_status) def origin_visit_status_add( self, visit_statuses: Iterable[OriginVisitStatus] ) -> None: # First round to check existence (fail early if any is ko) for visit_status in visit_statuses: origin_url = self.origin_get({"url": visit_status.origin}) if not origin_url: raise StorageArgumentException(f"Unknown origin {visit_status.origin}") for visit_status in visit_statuses: self._origin_visit_status_add(visit_status) def _origin_visit_apply_last_status(self, visit: Dict[str, Any]) -> Dict[str, Any]: """Retrieve the latest visit status information for the origin visit. Then merge it with the visit and return it. """ row = self._cql_runner.origin_visit_status_get_latest( visit["origin"], visit["visit"] ) assert row is not None visit_status = row_to_visit_status(row) return { # default to the values in visit **visit, # override with the last update **visit_status.to_dict(), # visit['origin'] is the URL (via a join), while # visit_status['origin'] is only an id. "origin": visit["origin"], # but keep the date of the creation of the origin visit "date": visit["date"], } def _origin_visit_get_updated(self, origin: str, visit_id: int) -> Dict[str, Any]: """Retrieve origin visit and latest origin visit status and merge them into an origin visit. """ row_visit = self._cql_runner.origin_visit_get_one(origin, visit_id) assert row_visit is not None visit = self._format_origin_visit_row(row_visit) return self._origin_visit_apply_last_status(visit) @staticmethod def _format_origin_visit_row(visit): return { **visit._asdict(), "origin": visit.origin, "date": visit.date.replace(tzinfo=datetime.timezone.utc), } def origin_visit_get( self, origin: str, last_visit: Optional[int] = None, limit: Optional[int] = None, order: str = "asc", ) -> Iterable[Dict[str, Any]]: rows = self._cql_runner.origin_visit_get(origin, last_visit, limit, order) for row in rows: visit = self._format_origin_visit_row(row) yield self._origin_visit_apply_last_status(visit) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime ) -> Optional[Dict[str, Any]]: # Iterator over all the visits of the origin # This should be ok for now, as there aren't too many visits # per origin. rows = 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 rows: row = min(rows, key=key) visit = self._format_origin_visit_row(row) return self._origin_visit_apply_last_status(visit) return None def origin_visit_get_by(self, origin: str, visit: int) -> Optional[Dict[str, Any]]: row = self._cql_runner.origin_visit_get_one(origin, visit) if row: visit_ = self._format_origin_visit_row(row) return self._origin_visit_apply_last_status(visit_) return None def origin_visit_get_latest( self, origin: str, type: Optional[str] = None, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[Dict[str, Any]]: # TODO: Do not fetch all visits rows = self._cql_runner.origin_visit_get_all(origin) latest_visit = None for row in rows: visit = self._format_origin_visit_row(row) updated_visit = self._origin_visit_apply_last_status(visit) if type is not None and updated_visit["type"] != type: continue if allowed_statuses and updated_visit["status"] not in allowed_statuses: continue if require_snapshot and updated_visit["snapshot"] is None: continue # updated_visit is a candidate if latest_visit is not None: if updated_visit["date"] < latest_visit["date"]: continue if updated_visit["visit"] < latest_visit["visit"]: continue latest_visit = updated_visit return latest_visit def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[OriginVisitStatus]: rows = self._cql_runner.origin_visit_status_get( origin_url, visit, allowed_statuses, require_snapshot ) # filtering is done python side as we cannot do it server side if allowed_statuses: rows = [row for row in rows if row.status in allowed_statuses] if require_snapshot: rows = [row for row in rows if row.snapshot is not None] if not rows: return None return row_to_visit_status(rows[0]) 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) visit_status = self._origin_visit_apply_last_status(visit) if ( visit_status["date"] > back_in_the_day and visit_status["status"] == "full" ): return visit_status 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 object_metadata_add(self, metadata: Iterable[RawExtrinsicMetadata]) -> None: for metadata_entry in metadata: if not self._cql_runner.metadata_authority_get( metadata_entry.authority.type.value, metadata_entry.authority.url ): raise StorageArgumentException( f"Unknown authority {metadata_entry.authority}" ) if not self._cql_runner.metadata_fetcher_get( metadata_entry.fetcher.name, metadata_entry.fetcher.version ): raise StorageArgumentException( f"Unknown fetcher {metadata_entry.fetcher}" ) try: self._cql_runner.object_metadata_add( type=metadata_entry.type.value, id=str(metadata_entry.id), authority_type=metadata_entry.authority.type.value, authority_url=metadata_entry.authority.url, discovery_date=metadata_entry.discovery_date, fetcher_name=metadata_entry.fetcher.name, fetcher_version=metadata_entry.fetcher.version, format=metadata_entry.format, metadata=metadata_entry.metadata, origin=metadata_entry.origin, visit=metadata_entry.visit, snapshot=map_optional(str, metadata_entry.snapshot), release=map_optional(str, metadata_entry.release), revision=map_optional(str, metadata_entry.revision), path=metadata_entry.path, directory=map_optional(str, metadata_entry.directory), ) except TypeError as e: raise StorageArgumentException(*e.args) def object_metadata_get( self, object_type: MetadataTargetType, id: Union[str, SWHID], authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, ) -> Dict[str, Union[Optional[bytes], List[RawExtrinsicMetadata]]]: if object_type == MetadataTargetType.ORIGIN: if isinstance(id, SWHID): raise StorageArgumentException( f"object_metadata_get called with object_type='origin', but " f"provided id is an SWHID: {id!r}" ) else: if not isinstance(id, SWHID): raise StorageArgumentException( f"object_metadata_get called with object_type!='origin', but " f"provided id is not an SWHID: {id!r}" ) if page_token is not None: (after_date, after_fetcher_name, after_fetcher_url) = msgpack_loads( page_token ) if after and after_date < after: raise StorageArgumentException( "page_token is inconsistent with the value of 'after'." ) entries = self._cql_runner.object_metadata_get_after_date_and_fetcher( str(id), authority.type.value, authority.url, after_date, after_fetcher_name, after_fetcher_url, ) elif after is not None: entries = self._cql_runner.object_metadata_get_after_date( str(id), authority.type.value, authority.url, after ) else: entries = self._cql_runner.object_metadata_get( str(id), authority.type.value, authority.url ) if limit: entries = itertools.islice(entries, 0, limit + 1) results = [] for entry in entries: discovery_date = entry.discovery_date.replace(tzinfo=datetime.timezone.utc) assert str(id) == entry.id result = RawExtrinsicMetadata( type=MetadataTargetType(entry.type), id=id, authority=MetadataAuthority( type=MetadataAuthorityType(entry.authority_type), url=entry.authority_url, ), fetcher=MetadataFetcher( name=entry.fetcher_name, version=entry.fetcher_version, ), discovery_date=discovery_date, format=entry.format, metadata=entry.metadata, origin=entry.origin, visit=entry.visit, snapshot=map_optional(parse_swhid, entry.snapshot), release=map_optional(parse_swhid, entry.release), revision=map_optional(parse_swhid, entry.revision), path=entry.path, directory=map_optional(parse_swhid, entry.directory), ) results.append(result) if len(results) > limit: results.pop() assert len(results) == limit last_result = results[-1] next_page_token: Optional[bytes] = msgpack_dumps( ( last_result.discovery_date, last_result.fetcher.name, last_result.fetcher.version, ) ) else: next_page_token = None return { "next_page_token": next_page_token, "results": results, } def metadata_fetcher_add(self, fetchers: Iterable[MetadataFetcher]) -> None: for fetcher in fetchers: self._cql_runner.metadata_fetcher_add( fetcher.name, fetcher.version, json.dumps(map_optional(dict, fetcher.metadata)), ) def metadata_fetcher_get( self, name: str, version: str ) -> Optional[MetadataFetcher]: fetcher = self._cql_runner.metadata_fetcher_get(name, version) if fetcher: return MetadataFetcher( name=fetcher.name, version=fetcher.version, metadata=json.loads(fetcher.metadata), ) else: return None def metadata_authority_add(self, authorities: Iterable[MetadataAuthority]) -> None: for authority in authorities: self._cql_runner.metadata_authority_add( authority.url, authority.type.value, json.dumps(map_optional(dict, authority.metadata)), ) def metadata_authority_get( self, type: MetadataAuthorityType, url: str ) -> Optional[MetadataAuthority]: authority = self._cql_runner.metadata_authority_get(type.value, url) if authority: return MetadataAuthority( type=MetadataAuthorityType(authority.type), url=authority.url, metadata=json.loads(authority.metadata), ) else: return None def clear_buffers(self, object_types: Optional[Iterable[str]] = None) -> None: """Do nothing """ return None def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: return {} diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 21e30b4d..2103fe3f 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1357 +1,1342 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import contextlib import datetime import itertools from collections import defaultdict from contextlib import contextmanager from typing import ( Any, Counter, Dict, Iterable, List, Optional, Union, ) import attr import psycopg2 import psycopg2.pool import psycopg2.errors from swh.core.api.serializers import msgpack_loads, msgpack_dumps from swh.model.identifiers import parse_swhid, SWHID from swh.model.model import ( Content, Directory, Origin, OriginVisit, OriginVisitStatus, Revision, Release, SkippedContent, Snapshot, SHA1_SIZE, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, RawExtrinsicMetadata, ) from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.storage.objstorage import ObjStorage -from swh.storage.validate import VALIDATION_EXCEPTIONS from swh.storage.utils import now from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageArgumentException, StorageDBError, HashCollision from .algos import diff from .metrics import timed, send_metric, process_metrics from .utils import get_partition_bounds_bytes, extract_collision_hash, map_optional 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 = VALIDATION_EXCEPTIONS + [ +VALIDATION_EXCEPTIONS = ( + KeyError, + TypeError, + ValueError, psycopg2.errors.CheckViolation, psycopg2.errors.IntegrityError, psycopg2.errors.InvalidTextRepresentation, psycopg2.errors.NotNullViolation, psycopg2.errors.NumericValueOutOfRange, psycopg2.errors.UndefinedFunction, # (raised on wrong argument typs) -] +) """Exceptions raised by postgresql when validation of the arguments failed.""" @contextlib.contextmanager def convert_validation_exceptions(): """Catches postgresql errors related to invalid arguments, and re-raises a StorageArgumentException.""" try: yield except tuple(VALIDATION_EXCEPTIONS) as e: raise StorageArgumentException(str(e)) class Storage: """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": 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", } hash_name = constraint_to_hash_name.get(e.diag.constraint_name) hash_id = None collision_contents_hashes = None raise HashCollision( hash_name, hash_id, collision_contents_hashes ) from None else: raise @timed @process_metrics def content_add(self, content: Iterable[Content]) -> Dict: ctime = now() contents = [attr.evolve(c, ctime=ctime) for c in content] objstorage_summary = self.objstorage.content_add(contents) with self.db() as db: with db.transaction() as cur: missing = list( self.content_missing( map(Content.to_dict, contents), key_hash="sha1_git", db=db, cur=cur, ) ) contents = [c for c in contents if c.sha1_git in missing] self.journal_writer.content_add(contents) self._content_add_metadata(db, cur, contents) return { "content:add": len(contents), "content:add:bytes": objstorage_summary["content:add:bytes"], } @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", db=db, cur=cur, ) contents = [c for c in contents if c.sha1_git in missing] self.journal_writer.content_add_metadata(contents) self._content_add_metadata(db, cur, contents) return { "content:add": len(contents), } @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 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 @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: ctime = now() content = [attr.evolve(c, ctime=ctime) for c in content] missing_contents = self.skipped_content_missing( (c.to_dict() for c in content), db=db, cur=cur, ) 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 with convert_validation_exceptions(): db.copy_to( ( { "name": name, "target": info.target if info else None, "target_type": ( info.target_type.value if info else None ), } for name, info in snapshot.branches.items() ), "tmp_snapshot_branch", ["name", "target", "target_type"], cur, ) self.journal_writer.snapshot_add([snapshot]) db.snapshot_add(snapshot.id, cur) count += 1 return {"snapshot:add": count} @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=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, visits: Iterable[OriginVisit], db=None, cur=None ) -> Iterable[OriginVisit]: for visit in visits: origin = self.origin_get({"url": visit.origin}, db=db, cur=cur) if not origin: # Cannot add a visit without an origin raise StorageArgumentException("Unknown origin %s", visit.origin) all_visits = [] nb_visits = 0 for visit in visits: nb_visits += 1 if not visit.visit: with convert_validation_exceptions(): visit_id = db.origin_visit_add( visit.origin, visit.date, visit.type, cur=cur ) visit = attr.evolve(visit, visit=visit_id) else: db.origin_visit_add_with_id(visit, cur=cur) assert visit.visit is not None all_visits.append(visit) # Forced to write after for the case when the visit has no id self.journal_writer.origin_visit_add([visit]) visit_status = OriginVisitStatus( origin=visit.origin, visit=visit.visit, date=visit.date, status="created", snapshot=None, ) self._origin_visit_status_add(visit_status, db=db, cur=cur) send_metric("origin_visit:add", count=nb_visits, method_name="origin_visit") return all_visits def _origin_visit_status_add( self, visit_status: OriginVisitStatus, db, cur ) -> None: """Add an origin visit status""" self.journal_writer.origin_visit_status_add([visit_status]) db.origin_visit_status_add(visit_status, cur=cur) send_metric( "origin_visit_status:add", count=1, method_name="origin_visit_status" ) @timed @db_transaction() def origin_visit_status_add( self, visit_statuses: Iterable[OriginVisitStatus], db=None, cur=None, ) -> None: # First round to check existence (fail early if any is ko) for visit_status in visit_statuses: origin_url = self.origin_get({"url": visit_status.origin}, db=db, cur=cur) if not origin_url: raise StorageArgumentException(f"Unknown origin {visit_status.origin}") for visit_status in visit_statuses: self._origin_visit_status_add(visit_status, db, cur) @timed @db_transaction() def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, db=None, cur=None, ) -> Optional[OriginVisitStatus]: row = db.origin_visit_status_get_latest( origin_url, visit, allowed_statuses, require_snapshot, cur=cur ) if not row: return None return OriginVisitStatus.from_dict(row) def _origin_visit_apply_update( self, visit: Dict[str, Any], db, cur=None ) -> Dict[str, Any]: """Retrieve the latest visit status information for the origin visit. Then merge it with the visit and return it. """ visit_status = db.origin_visit_status_get_latest( visit["origin"], visit["visit"], cur=cur ) return { # default to the values in visit **visit, # override with the last update **visit_status, # visit['origin'] is the URL (via a join), while # visit_status['origin'] is only an id. "origin": visit["origin"], # but keep the date of the creation of the origin visit "date": visit["date"], } @timed @db_transaction_generator(statement_timeout=500) def origin_visit_get( self, origin: str, last_visit: Optional[int] = None, limit: Optional[int] = None, order: str = "asc", db=None, cur=None, ) -> Iterable[Dict[str, Any]]: assert order in ["asc", "desc"] lines = db.origin_visit_get_all( origin, last_visit=last_visit, limit=limit, order=order, cur=cur ) for line in lines: visit = dict(zip(db.origin_visit_get_cols, line)) yield self._origin_visit_apply_update(visit, db) @timed @db_transaction(statement_timeout=500) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime, db=None, cur=None ) -> Optional[Dict[str, Any]]: visit = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if visit: return self._origin_visit_apply_update(visit, db) return None @timed @db_transaction(statement_timeout=500) def origin_visit_get_by( self, origin: str, visit: int, db=None, cur=None ) -> Optional[Dict[str, Any]]: row = db.origin_visit_get(origin, visit, cur) if row: visit_dict = dict(zip(db.origin_visit_get_cols, row)) return self._origin_visit_apply_update(visit_dict, db) return None @timed @db_transaction(statement_timeout=4000) def origin_visit_get_latest( self, origin: str, type: Optional[str] = None, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, db=None, cur=None, ) -> Optional[Dict[str, Any]]: row = db.origin_visit_get_latest( origin, type=type, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, cur=cur, ) if row: visit = dict(zip(db.origin_visit_get_cols, row)) return self._origin_visit_apply_update(visit, db) return None @timed @db_transaction() def origin_visit_get_random( self, type: str, db=None, cur=None ) -> Optional[Dict[str, Any]]: row = db.origin_visit_get_random(type, cur) if row: visit = dict(zip(db.origin_visit_get_cols, row)) return self._origin_visit_apply_update(visit, db) 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 @process_metrics @db_transaction() def origin_add( self, origins: Iterable[Origin], db=None, cur=None ) -> Dict[str, int]: urls = [o.url for o in origins] known_origins = set(url for (url,) in db.origin_get_by_url(urls, cur)) # use lists here to keep origins sorted; some tests depend on this to_add = [url for url in urls if url not in known_origins] self.journal_writer.origin_add([Origin(url=url) for url in to_add]) added = 0 for url in to_add: if db.origin_add(url, cur): added += 1 return {"origin:add": added} @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,)) @db_transaction() def object_metadata_add( self, metadata: Iterable[RawExtrinsicMetadata], db, cur, ) -> None: counter = Counter[MetadataTargetType]() for metadata_entry in metadata: authority_id = self._get_authority_id(metadata_entry.authority, db, cur) fetcher_id = self._get_fetcher_id(metadata_entry.fetcher, db, cur) db.object_metadata_add( object_type=metadata_entry.type.value, id=str(metadata_entry.id), discovery_date=metadata_entry.discovery_date, authority_id=authority_id, fetcher_id=fetcher_id, format=metadata_entry.format, metadata=metadata_entry.metadata, origin=metadata_entry.origin, visit=metadata_entry.visit, snapshot=map_optional(str, metadata_entry.snapshot), release=map_optional(str, metadata_entry.release), revision=map_optional(str, metadata_entry.revision), path=metadata_entry.path, directory=map_optional(str, metadata_entry.directory), cur=cur, ) counter[metadata_entry.type] += 1 for (object_type, count) in counter.items(): send_metric( f"{object_type.value}_metadata:add", count=count, method_name=f"{object_type.value}_metadata_add", ) @db_transaction() def object_metadata_get( self, object_type: MetadataTargetType, id: Union[str, SWHID], authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, db=None, cur=None, ) -> Dict[str, Union[Optional[bytes], List[RawExtrinsicMetadata]]]: if object_type == MetadataTargetType.ORIGIN: if isinstance(id, SWHID): raise StorageArgumentException( f"object_metadata_get called with object_type='origin', but " f"provided id is an SWHID: {id!r}" ) else: if not isinstance(id, SWHID): raise StorageArgumentException( f"object_metadata_get called with object_type!='origin', but " f"provided id is not an SWHID: {id!r}" ) if page_token: (after_time, after_fetcher) = msgpack_loads(page_token) if after and after_time < after: raise StorageArgumentException( "page_token is inconsistent with the value of 'after'." ) else: after_time = after after_fetcher = None authority_id = self._get_authority_id(authority, db, cur) if not authority_id: return { "next_page_token": None, "results": [], } rows = db.object_metadata_get( object_type, str(id), authority_id, after_time, after_fetcher, limit + 1, cur, ) rows = [dict(zip(db.object_metadata_get_cols, row)) for row in rows] results = [] for row in rows: row = row.copy() row.pop("metadata_fetcher.id") assert str(id) == row["object_metadata.id"] result = RawExtrinsicMetadata( type=MetadataTargetType(row["object_metadata.type"]), id=id, authority=MetadataAuthority( type=MetadataAuthorityType(row["metadata_authority.type"]), url=row["metadata_authority.url"], ), fetcher=MetadataFetcher( name=row["metadata_fetcher.name"], version=row["metadata_fetcher.version"], ), discovery_date=row["discovery_date"], format=row["format"], metadata=row["object_metadata.metadata"], origin=row["origin"], visit=row["visit"], snapshot=map_optional(parse_swhid, row["snapshot"]), release=map_optional(parse_swhid, row["release"]), revision=map_optional(parse_swhid, row["revision"]), path=row["path"], directory=map_optional(parse_swhid, row["directory"]), ) results.append(result) if len(results) > limit: results.pop() assert len(results) == limit last_returned_row = rows[-2] # rows[-1] corresponds to the popped result next_page_token: Optional[bytes] = msgpack_dumps( ( last_returned_row["discovery_date"], last_returned_row["metadata_fetcher.id"], ) ) else: next_page_token = None return { "next_page_token": next_page_token, "results": results, } @timed @db_transaction() def metadata_fetcher_add( self, fetchers: Iterable[MetadataFetcher], db=None, cur=None ) -> None: for (i, fetcher) in enumerate(fetchers): if fetcher.metadata is None: raise StorageArgumentException( "MetadataFetcher.metadata may not be None in metadata_fetcher_add." ) db.metadata_fetcher_add( fetcher.name, fetcher.version, dict(fetcher.metadata), cur=cur ) send_metric("metadata_fetcher:add", count=i + 1, method_name="metadata_fetcher") @timed @db_transaction(statement_timeout=500) def metadata_fetcher_get( self, name: str, version: str, db=None, cur=None ) -> Optional[MetadataFetcher]: row = db.metadata_fetcher_get(name, version, cur=cur) if not row: return None return MetadataFetcher.from_dict(dict(zip(db.metadata_fetcher_cols, row))) @timed @db_transaction() def metadata_authority_add( self, authorities: Iterable[MetadataAuthority], db=None, cur=None ) -> None: for (i, authority) in enumerate(authorities): if authority.metadata is None: raise StorageArgumentException( "MetadataAuthority.metadata may not be None in " "metadata_authority_add." ) db.metadata_authority_add( authority.type.value, authority.url, dict(authority.metadata), cur=cur ) send_metric( "metadata_authority:add", count=i + 1, method_name="metadata_authority" ) @timed @db_transaction() def metadata_authority_get( self, type: MetadataAuthorityType, url: str, db=None, cur=None ) -> Optional[MetadataAuthority]: row = db.metadata_authority_get(type.value, url, cur=cur) if not row: return None return MetadataAuthority.from_dict(dict(zip(db.metadata_authority_cols, row))) @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) def clear_buffers(self, object_types: Optional[Iterable[str]] = None) -> None: """Do nothing """ return None def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: return {} def _get_authority_id(self, authority: MetadataAuthority, db, cur): authority_id = db.metadata_authority_get_id( authority.type.value, authority.url, cur ) if not authority_id: raise StorageArgumentException(f"Unknown authority {authority}") return authority_id def _get_fetcher_id(self, fetcher: MetadataFetcher, db, cur): fetcher_id = db.metadata_fetcher_get_id(fetcher.name, fetcher.version, cur) if not fetcher_id: raise StorageArgumentException(f"Unknown fetcher {fetcher}") return fetcher_id diff --git a/swh/storage/tests/conftest.py b/swh/storage/tests/conftest.py index c1fd1113..cd91a78c 100644 --- a/swh/storage/tests/conftest.py +++ b/swh/storage/tests/conftest.py @@ -1,69 +1,63 @@ # 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 pytest import multiprocessing.util from hypothesis import settings try: import pytest_cov.embed except ImportError: pytest_cov = None from typing import Iterable from swh.model.model import BaseContent, Origin from swh.model.tests.generate_testdata import gen_contents, gen_origins -from swh.storage import get_storage from swh.storage.interface import StorageInterface # define tests profile. Full documentation is at: # https://hypothesis.readthedocs.io/en/latest/settings.html#settings-profiles settings.register_profile("fast", max_examples=5, deadline=5000) settings.register_profile("slow", max_examples=20, deadline=5000) if pytest_cov is not None: # pytest_cov + multiprocessing can cause a segmentation fault when starting # the child process ; so we're # removing pytest-coverage's hook that runs when a child process starts. # This means code run in child processes won't be counted in the coverage # report, but this is not an issue because the only code that runs only in # child processes is the RPC server. for (key, value) in multiprocessing.util._afterfork_registry.items(): if value is pytest_cov.embed.multiprocessing_start: del multiprocessing.util._afterfork_registry[key] break else: assert False, "missing pytest_cov.embed.multiprocessing_start?" @pytest.fixture def swh_storage_backend_config(swh_storage_backend_config): """storage should test with its journal writer collaborator on """ yield {**swh_storage_backend_config, "journal_writer": {"cls": "memory",}} -@pytest.fixture -def swh_storage(swh_storage_backend_config): - return get_storage(cls="validate", storage=swh_storage_backend_config) - - @pytest.fixture def swh_contents(swh_storage: StorageInterface) -> Iterable[BaseContent]: contents = [BaseContent.from_dict(c) for c in gen_contents(n=20)] swh_storage.content_add([c for c in contents if c.status != "absent"]) swh_storage.skipped_content_add([c for c in contents if c.status == "absent"]) return contents @pytest.fixture def swh_origins(swh_storage: StorageInterface) -> Iterable[Origin]: origins = [Origin.from_dict(o) for o in gen_origins(n=100)] swh_storage.origin_add(origins) return origins diff --git a/swh/storage/tests/test_api_client.py b/swh/storage/tests/test_api_client.py index a3d5b49a..5ba0e023 100644 --- a/swh/storage/tests/test_api_client.py +++ b/swh/storage/tests/test_api_client.py @@ -1,67 +1,70 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from unittest.mock import patch import pytest import swh.storage.api.server as server import swh.storage.storage from swh.storage import get_storage from swh.storage.tests.test_storage import TestStorageGeneratedData # noqa from swh.storage.tests.test_storage import TestStorage as _TestStorage # tests are executed using imported classes (TestStorage and # TestStorageGeneratedData) using overloaded swh_storage fixture # below @pytest.fixture def app_server(): server.storage = swh.storage.get_storage( cls="memory", journal_writer={"cls": "memory"} ) yield server @pytest.fixture def app(app_server): return app_server.app @pytest.fixture def swh_rpc_client_class(): def storage_factory(**kwargs): - storage_config = {"cls": "validate", "storage": {"cls": "remote", **kwargs,}} + storage_config = { + "cls": "remote", + **kwargs, + } return get_storage(**storage_config) return storage_factory @pytest.fixture def swh_storage(swh_rpc_client, app_server): # This version of the swh_storage fixture uses the swh_rpc_client fixture # to instantiate a RemoteStorage (see swh_rpc_client_class above) that # proxies, via the swh.core RPC mechanism, the local (in memory) storage # configured in the app_server fixture above. # # Also note that, for the sake of # making it easier to write tests, the in-memory journal writer of the # in-memory backend storage is attached to the RemoteStorage as its # journal_writer attribute. storage = swh_rpc_client journal_writer = getattr(storage, "journal_writer", None) storage.journal_writer = app_server.storage.journal_writer yield storage storage.journal_writer = journal_writer class TestStorage(_TestStorage): def test_content_update(self, swh_storage, app_server, sample_data_model): # TODO, journal_writer not supported swh_storage.journal_writer.journal = None with patch.object(server.storage.journal_writer, "journal", None): super().test_content_update(swh_storage, sample_data_model) diff --git a/swh/storage/tests/test_cassandra.py b/swh/storage/tests/test_cassandra.py index 4938190b..4a6ca92d 100644 --- a/swh/storage/tests/test_cassandra.py +++ b/swh/storage/tests/test_cassandra.py @@ -1,410 +1,404 @@ # Copyright (C) 2018-2020 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 attr import os import signal import socket import subprocess import time from collections import namedtuple import pytest from swh.storage import get_storage from swh.storage.cassandra import create_keyspace from swh.storage.cassandra.schema import TABLES, HASH_ALGORITHMS from swh.storage.utils import now from swh.storage.tests.test_storage import TestStorage as _TestStorage from swh.storage.tests.test_storage import ( TestStorageGeneratedData as _TestStorageGeneratedData, ) CONFIG_TEMPLATE = """ data_file_directories: - {data_dir}/data commitlog_directory: {data_dir}/commitlog hints_directory: {data_dir}/hints saved_caches_directory: {data_dir}/saved_caches commitlog_sync: periodic commitlog_sync_period_in_ms: 1000000 partitioner: org.apache.cassandra.dht.Murmur3Partitioner endpoint_snitch: SimpleSnitch seed_provider: - class_name: org.apache.cassandra.locator.SimpleSeedProvider parameters: - seeds: "127.0.0.1" storage_port: {storage_port} native_transport_port: {native_transport_port} start_native_transport: true listen_address: 127.0.0.1 enable_user_defined_functions: true # speed-up by disabling period saving to disk key_cache_save_period: 0 row_cache_save_period: 0 trickle_fsync: false commitlog_sync_period_in_ms: 100000 """ def free_port(): sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) sock.bind(("127.0.0.1", 0)) port = sock.getsockname()[1] sock.close() return port def wait_for_peer(addr, port): wait_until = time.time() + 20 while time.time() < wait_until: try: sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) sock.connect((addr, port)) except ConnectionRefusedError: time.sleep(0.1) else: sock.close() return True return False @pytest.fixture(scope="session") def cassandra_cluster(tmpdir_factory): cassandra_conf = tmpdir_factory.mktemp("cassandra_conf") cassandra_data = tmpdir_factory.mktemp("cassandra_data") cassandra_log = tmpdir_factory.mktemp("cassandra_log") native_transport_port = free_port() storage_port = free_port() jmx_port = free_port() with open(str(cassandra_conf.join("cassandra.yaml")), "w") as fd: fd.write( CONFIG_TEMPLATE.format( data_dir=str(cassandra_data), storage_port=storage_port, native_transport_port=native_transport_port, ) ) if os.environ.get("SWH_CASSANDRA_LOG"): stdout = stderr = None else: stdout = stderr = subprocess.DEVNULL cassandra_bin = os.environ.get("SWH_CASSANDRA_BIN", "/usr/sbin/cassandra") proc = subprocess.Popen( [ cassandra_bin, "-Dcassandra.config=file://%s/cassandra.yaml" % cassandra_conf, "-Dcassandra.logdir=%s" % cassandra_log, "-Dcassandra.jmx.local.port=%d" % jmx_port, "-Dcassandra-foreground=yes", ], start_new_session=True, env={ "MAX_HEAP_SIZE": "300M", "HEAP_NEWSIZE": "50M", "JVM_OPTS": "-Xlog:gc=error:file=%s/gc.log" % cassandra_log, }, stdout=stdout, stderr=stderr, ) running = wait_for_peer("127.0.0.1", native_transport_port) if running: yield (["127.0.0.1"], native_transport_port) if not running or os.environ.get("SWH_CASSANDRA_LOG"): debug_log_path = str(cassandra_log.join("debug.log")) if os.path.exists(debug_log_path): with open(debug_log_path) as fd: print(fd.read()) if not running: raise Exception("cassandra process stopped unexpectedly.") pgrp = os.getpgid(proc.pid) os.killpg(pgrp, signal.SIGKILL) class RequestHandler: def on_request(self, rf): if hasattr(rf.message, "query"): print() print(rf.message.query) @pytest.fixture(scope="session") def keyspace(cassandra_cluster): (hosts, port) = cassandra_cluster keyspace = os.urandom(10).hex() create_keyspace(hosts, keyspace, port) return keyspace # tests are executed using imported classes (TestStorage and # TestStorageGeneratedData) using overloaded swh_storage fixture # below @pytest.fixture def swh_storage_backend_config(cassandra_cluster, keyspace): (hosts, port) = cassandra_cluster storage_config = dict( cls="cassandra", hosts=hosts, port=port, keyspace=keyspace, journal_writer={"cls": "memory",}, objstorage={"cls": "memory", "args": {},}, ) yield storage_config storage = get_storage(**storage_config) for table in TABLES: storage._cql_runner._session.execute('TRUNCATE TABLE "%s"' % table) storage._cql_runner._cluster.shutdown() @pytest.mark.cassandra class TestCassandraStorage(_TestStorage): def test_content_add_murmur3_collision( self, swh_storage, mocker, sample_data_model ): """The Murmur3 token is used as link from index tables to the main table; and non-matching contents with colliding murmur3-hash are filtered-out when reading the main table. This test checks the content methods do filter out these collision. """ called = 0 cont, cont2 = sample_data_model["content"][:2] # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( - swh_storage.storage._cql_runner, - "content_get_tokens_from_single_hash", - mock_cgtfsh, + swh_storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return cont Row = namedtuple("Row", HASH_ALGORITHMS) def mock_cgft(token): nonlocal called called += 1 return [Row(**{algo: getattr(cont, algo) for algo in HASH_ALGORITHMS})] mocker.patch.object( - swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft + swh_storage._cql_runner, "content_get_from_token", mock_cgft ) actual_result = swh_storage.content_add([cont2]) assert called == 4 assert actual_result == { "content:add": 1, "content:add:bytes": cont2.length, } def test_content_get_metadata_murmur3_collision( self, swh_storage, mocker, sample_data_model ): """The Murmur3 token is used as link from index tables to the main table; and non-matching contents with colliding murmur3-hash are filtered-out when reading the main table. This test checks the content methods do filter out these collisions. """ called = 0 cont, cont2 = [ attr.evolve(c, ctime=now()) for c in sample_data_model["content"][:2] ] # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( - swh_storage.storage._cql_runner, - "content_get_tokens_from_single_hash", - mock_cgtfsh, + swh_storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return cont and cont2 cols = list(set(cont.to_dict()) - {"data"}) Row = namedtuple("Row", cols) def mock_cgft(token): nonlocal called called += 1 return [ Row(**{col: getattr(cont, col) for col in cols}) for cont in [cont, cont2] ] mocker.patch.object( - swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft + swh_storage._cql_runner, "content_get_from_token", mock_cgft ) actual_result = swh_storage.content_get_metadata([cont.sha1]) assert called == 2 # dropping extra column not returned expected_cont = attr.evolve(cont, data=None, ctime=None).to_dict() del expected_cont["ctime"] # forced to pop it as to_dict does not # but cont2 should be filtered out assert actual_result == {cont.sha1: [expected_cont]} def test_content_find_murmur3_collision( self, swh_storage, mocker, sample_data_model ): """The Murmur3 token is used as link from index tables to the main table; and non-matching contents with colliding murmur3-hash are filtered-out when reading the main table. This test checks the content methods do filter out these collisions. """ called = 0 cont, cont2 = [ attr.evolve(c, ctime=now()) for c in sample_data_model["content"][:2] ] # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( - swh_storage.storage._cql_runner, - "content_get_tokens_from_single_hash", - mock_cgtfsh, + swh_storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return cont and cont2 cols = list(set(cont.to_dict()) - {"data"}) Row = namedtuple("Row", cols) def mock_cgft(token): nonlocal called called += 1 return [ Row(**{col: getattr(cont, col) for col in cols}) for cont in [cont, cont2] ] mocker.patch.object( - swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft + swh_storage._cql_runner, "content_get_from_token", mock_cgft ) expected_cont = attr.evolve(cont, data=None).to_dict() actual_result = swh_storage.content_find({"sha1": cont.sha1}) assert called == 2 # but cont2 should be filtered out assert actual_result == [expected_cont] @pytest.mark.skip("content_update is not yet implemented for Cassandra") def test_content_update(self): pass @pytest.mark.skip( 'The "person" table of the pgsql is a legacy thing, and not ' "supported by the cassandra backend." ) def test_person_fullname_unicity(self): pass @pytest.mark.skip( 'The "person" table of the pgsql is a legacy thing, and not ' "supported by the cassandra backend." ) def test_person_get(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count(self): pass @pytest.mark.cassandra class TestCassandraStorageGeneratedData(_TestStorageGeneratedData): @pytest.mark.skip("Not supported by Cassandra") def test_origin_count(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_get_range(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_get_range_from_zero(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_limit(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_no_limit(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_empty(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_limit_none(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_full(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count_with_visit_no_visits(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count_with_visit_with_visits_and_snapshot(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count_with_visit_with_visits_no_snapshot(self): pass diff --git a/swh/storage/tests/test_pytest_plugin.py b/swh/storage/tests/test_pytest_plugin.py index 1f699cd7..c58b178d 100644 --- a/swh/storage/tests/test_pytest_plugin.py +++ b/swh/storage/tests/test_pytest_plugin.py @@ -1,77 +1,76 @@ # 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.storage.pytest_plugin import OBJECT_FACTORY from swh.model.model import BaseModel +from swh.storage.interface import StorageInterface def test_sample_data(sample_data, sample_data_model): assert set(sample_data.keys()) == set( [ "content", "content_no_data", "skipped_content", "person", "directory", "revision", "release", "snapshot", "origin", "origin_visit", "fetcher", "authority", "origin_metadata", "content_metadata", ] ) for object_type, objs in sample_data.items(): for obj in objs: assert isinstance(obj, dict) if sample_data_model.get(object_type): # metadata keys are missing because conversion is not possible yet assert len(objs) == len(sample_data_model[object_type]) def test_sample_data_model(sample_data, sample_data_model): assert set(sample_data_model.keys()) == set( [ "content", "content_no_data", "skipped_content", "person", "directory", "revision", "release", "snapshot", "origin", "origin_visit", "fetcher", "authority", "origin_metadata", "content_metadata", ] ) for object_type, objs in sample_data_model.items(): assert object_type in OBJECT_FACTORY for obj in objs: assert isinstance(obj, BaseModel) assert len(objs) == len(sample_data[object_type]) -def test_swh_storage(swh_storage): - # Cannot check yet that it's an instance of StorageInterface (due to validate proxy - # again). That ensures though that it's instantiable - assert swh_storage is not None +def test_swh_storage(swh_storage: StorageInterface): + assert isinstance(swh_storage, StorageInterface) is not None def test_swh_storage_backend_config(swh_storage_backend_config): assert isinstance(swh_storage_backend_config, dict) diff --git a/swh/storage/tests/test_retry.py b/swh/storage/tests/test_retry.py index 56795c50..973a3d9b 100644 --- a/swh/storage/tests/test_retry.py +++ b/swh/storage/tests/test_retry.py @@ -1,874 +1,831 @@ # 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 unittest.mock import call import psycopg2 import pytest from swh.model.model import ( OriginVisit, MetadataTargetType, ) -from swh.storage import get_storage from swh.storage.exc import HashCollision, StorageArgumentException from .storage_data import date_visit1 @pytest.fixture def monkeypatch_sleep(monkeypatch, swh_storage): """In test context, we don't want to wait, make test faster """ from swh.storage.retry import RetryingProxyStorage for method_name, method in RetryingProxyStorage.__dict__.items(): if "_add" in method_name or "_update" in method_name: monkeypatch.setattr(method.retry, "sleep", lambda x: None) return monkeypatch @pytest.fixture def fake_hash_collision(sample_data): return HashCollision("sha1", "38762cf7f55934b34d179ae6a4c80cadccbb7f0a", []) @pytest.fixture def swh_storage_backend_config(): yield { "cls": "pipeline", "steps": [{"cls": "retry"}, {"cls": "memory"},], } -@pytest.fixture -def swh_storage(swh_storage_backend_config): - return get_storage(**swh_storage_backend_config) - - -@pytest.fixture -def swh_storage_validate(swh_storage_backend_config): - return get_storage(cls="validate", storage=swh_storage_backend_config) - - def test_retrying_proxy_storage_content_add(swh_storage, sample_data_model): """Standard content_add works as before """ sample_content = sample_data_model["content"][0] content = next(swh_storage.content_get([sample_content.sha1])) assert not content s = swh_storage.content_add([sample_content]) assert s == { "content:add": 1, "content:add:bytes": sample_content.length, } content = next(swh_storage.content_get([sample_content.sha1])) assert content["sha1"] == sample_content.sha1 def test_retrying_proxy_storage_content_add_with_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision, ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("content already inserted"), # ok then! {"content:add": 1}, ] sample_content = sample_data_model["content"][0] content = next(swh_storage.content_get([sample_content.sha1])) assert not content s = swh_storage.content_add([sample_content]) assert s == {"content:add": 1} mock_memory.assert_has_calls( [call([sample_content]), call([sample_content]), call([sample_content]),] ) def test_retrying_proxy_swh_storage_content_add_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = StorageArgumentException("Refuse to add content always!") sample_content = sample_data_model["content"][0] content = next(swh_storage.content_get([sample_content.sha1])) assert not content with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.content_add([sample_content]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_content_add_metadata(swh_storage, sample_data_model): """Standard content_add_metadata works as before """ sample_content = sample_data_model["content_no_data"][0] pk = sample_content.sha1 content_metadata = swh_storage.content_get_metadata([pk]) assert not content_metadata[pk] s = swh_storage.content_add_metadata([sample_content]) assert s == { "content:add": 1, } content_metadata = swh_storage.content_get_metadata([pk]) assert len(content_metadata[pk]) == 1 assert content_metadata[pk][0]["sha1"] == pk def test_retrying_proxy_storage_content_add_metadata_with_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.content_add_metadata" ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("content_metadata already inserted"), # ok then! {"content:add": 1}, ] sample_content = sample_data_model["content_no_data"][0] s = swh_storage.content_add_metadata([sample_content]) assert s == {"content:add": 1} mock_memory.assert_has_calls( [call([sample_content]), call([sample_content]), call([sample_content]),] ) def test_retrying_proxy_swh_storage_content_add_metadata_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.content_add_metadata" ) mock_memory.side_effect = StorageArgumentException( "Refuse to add content_metadata!" ) sample_content = sample_data_model["content_no_data"][0] pk = sample_content.sha1 content_metadata = swh_storage.content_get_metadata([pk]) assert not content_metadata[pk] with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.content_add_metadata([sample_content]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_skipped_content_add(swh_storage, sample_data_model): """Standard skipped_content_add works as before """ sample_content = sample_data_model["skipped_content"][0] sample_content_dict = sample_content.to_dict() skipped_contents = list(swh_storage.skipped_content_missing([sample_content_dict])) assert len(skipped_contents) == 1 s = swh_storage.skipped_content_add([sample_content]) assert s == { "skipped_content:add": 1, } skipped_content = list(swh_storage.skipped_content_missing([sample_content_dict])) assert len(skipped_content) == 0 def test_retrying_proxy_storage_skipped_content_add_with_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.skipped_content_add" ) mock_memory.side_effect = [ # 1st & 2nd try goes ko fake_hash_collision, psycopg2.IntegrityError("skipped_content already inserted"), # ok then! {"skipped_content:add": 1}, ] sample_content = sample_data_model["skipped_content"][0] s = swh_storage.skipped_content_add([sample_content]) assert s == {"skipped_content:add": 1} mock_memory.assert_has_calls( [call([sample_content]), call([sample_content]), call([sample_content]),] ) def test_retrying_proxy_swh_storage_skipped_content_add_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.skipped_content_add" ) mock_memory.side_effect = StorageArgumentException( "Refuse to add content_metadata!" ) sample_content = sample_data_model["skipped_content"][0] sample_content_dict = sample_content.to_dict() skipped_contents = list(swh_storage.skipped_content_missing([sample_content_dict])) assert len(skipped_contents) == 1 with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.skipped_content_add([sample_content]) skipped_contents = list(swh_storage.skipped_content_missing([sample_content_dict])) assert len(skipped_contents) == 1 assert mock_memory.call_count == 1 def test_retrying_proxy_swh_storage_origin_visit_add(swh_storage, sample_data_model): """Standard origin_visit_add works as before """ origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) origins = list(swh_storage.origin_visit_get(origin.url)) assert not origins visit = OriginVisit(origin=origin.url, date=date_visit1, type="hg") origin_visit = swh_storage.origin_visit_add([visit])[0] assert origin_visit.origin == origin.url assert isinstance(origin_visit.visit, int) origin_visit = next(swh_storage.origin_visit_get(origin.url)) assert origin_visit["origin"] == origin.url assert isinstance(origin_visit["visit"], int) def test_retrying_proxy_swh_storage_origin_visit_add_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ origin = sample_data_model["origin"][1] swh_storage.origin_add([origin]) mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.origin_visit_add") visit = OriginVisit(origin=origin.url, date=date_visit1, type="git") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("origin already inserted"), # ok then! [visit], ] origins = list(swh_storage.origin_visit_get(origin.url)) assert not origins r = swh_storage.origin_visit_add([visit]) assert r == [visit] mock_memory.assert_has_calls( [call([visit]), call([visit]), call([visit]),] ) def test_retrying_proxy_swh_storage_origin_visit_add_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.origin_visit_add") mock_memory.side_effect = StorageArgumentException("Refuse to add origin always!") origin = sample_data_model["origin"][0] origins = list(swh_storage.origin_visit_get(origin.url)) assert not origins with pytest.raises(StorageArgumentException, match="Refuse to add"): visit = OriginVisit(origin=origin.url, date=date_visit1, type="svn",) swh_storage.origin_visit_add([visit]) mock_memory.assert_has_calls( [call([visit]),] ) -def test_retrying_proxy_storage_metadata_fetcher_add( - swh_storage_validate, sample_data_model -): +def test_retrying_proxy_storage_metadata_fetcher_add(swh_storage, sample_data_model): """Standard metadata_fetcher_add works as before """ fetcher = sample_data_model["fetcher"][0] - metadata_fetcher = swh_storage_validate.metadata_fetcher_get( - fetcher.name, fetcher.version - ) + metadata_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert not metadata_fetcher - swh_storage_validate.metadata_fetcher_add([fetcher]) + swh_storage.metadata_fetcher_add([fetcher]) - actual_fetcher = swh_storage_validate.metadata_fetcher_get( - fetcher.name, fetcher.version - ) + actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert actual_fetcher == fetcher def test_retrying_proxy_storage_metadata_fetcher_add_with_retry( - monkeypatch_sleep, - swh_storage_validate, - sample_data_model, - mocker, - fake_hash_collision, + monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision, ): """Multiple retries for hash collision and psycopg2 error but finally ok """ fetcher = sample_data_model["fetcher"][0] mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.metadata_fetcher_add" ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("metadata_fetcher already inserted"), # ok then! [fetcher], ] - actual_fetcher = swh_storage_validate.metadata_fetcher_get( - fetcher.name, fetcher.version - ) + actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert not actual_fetcher - swh_storage_validate.metadata_fetcher_add([fetcher]) + swh_storage.metadata_fetcher_add([fetcher]) mock_memory.assert_has_calls( [call([fetcher]), call([fetcher]), call([fetcher]),] ) def test_retrying_proxy_swh_storage_metadata_fetcher_add_failure( - swh_storage_validate, sample_data_model, mocker + swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.metadata_fetcher_add" ) mock_memory.side_effect = StorageArgumentException( "Refuse to add metadata_fetcher always!" ) fetcher = sample_data_model["fetcher"][0] - actual_fetcher = swh_storage_validate.metadata_fetcher_get( - fetcher.name, fetcher.version - ) + actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert not actual_fetcher with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage_validate.metadata_fetcher_add([fetcher]) + swh_storage.metadata_fetcher_add([fetcher]) assert mock_memory.call_count == 1 -def test_retrying_proxy_storage_metadata_authority_add( - swh_storage_validate, sample_data_model -): +def test_retrying_proxy_storage_metadata_authority_add(swh_storage, sample_data_model): """Standard metadata_authority_add works as before """ authority = sample_data_model["authority"][0] - assert not swh_storage_validate.metadata_authority_get( - authority.type, authority.url - ) + assert not swh_storage.metadata_authority_get(authority.type, authority.url) - swh_storage_validate.metadata_authority_add([authority]) + swh_storage.metadata_authority_add([authority]) - actual_authority = swh_storage_validate.metadata_authority_get( - authority.type, authority.url - ) + actual_authority = swh_storage.metadata_authority_get(authority.type, authority.url) assert actual_authority == authority def test_retrying_proxy_storage_metadata_authority_add_with_retry( - monkeypatch_sleep, - swh_storage_validate, - sample_data_model, - mocker, - fake_hash_collision, + monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision, ): """Multiple retries for hash collision and psycopg2 error but finally ok """ authority = sample_data_model["authority"][0] mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.metadata_authority_add" ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("foo bar"), # ok then! None, ] - assert not swh_storage_validate.metadata_authority_get( - authority.type, authority.url - ) + assert not swh_storage.metadata_authority_get(authority.type, authority.url) - swh_storage_validate.metadata_authority_add([authority]) + swh_storage.metadata_authority_add([authority]) mock_memory.assert_has_calls( [call([authority]), call([authority]), call([authority])] ) def test_retrying_proxy_swh_storage_metadata_authority_add_failure( - swh_storage_validate, sample_data_model, mocker + swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.metadata_authority_add" ) mock_memory.side_effect = StorageArgumentException( "Refuse to add authority_id always!" ) authority = sample_data_model["authority"][0] - swh_storage_validate.metadata_authority_get(authority.type, authority.url) + swh_storage.metadata_authority_get(authority.type, authority.url) with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage_validate.metadata_authority_add([authority]) + swh_storage.metadata_authority_add([authority]) assert mock_memory.call_count == 1 -def test_retrying_proxy_storage_object_metadata_add( - swh_storage_validate, sample_data_model -): +def test_retrying_proxy_storage_object_metadata_add(swh_storage, sample_data_model): """Standard object_metadata_add works as before """ origin = sample_data_model["origin"][0] ori_meta = sample_data_model["origin_metadata"][0] assert origin.url == ori_meta.id - swh_storage_validate.origin_add([origin]) - swh_storage_validate.metadata_authority_add([sample_data_model["authority"][0]]) - swh_storage_validate.metadata_fetcher_add([sample_data_model["fetcher"][0]]) + swh_storage.origin_add([origin]) + swh_storage.metadata_authority_add([sample_data_model["authority"][0]]) + swh_storage.metadata_fetcher_add([sample_data_model["fetcher"][0]]) - origin_metadata = swh_storage_validate.object_metadata_get( + origin_metadata = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, ori_meta.id, ori_meta.authority ) assert origin_metadata["next_page_token"] is None assert not origin_metadata["results"] - swh_storage_validate.object_metadata_add([ori_meta]) + swh_storage.object_metadata_add([ori_meta]) - origin_metadata = swh_storage_validate.object_metadata_get( + origin_metadata = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, ori_meta.id, ori_meta.authority ) assert origin_metadata def test_retrying_proxy_storage_object_metadata_add_with_retry( - monkeypatch_sleep, - swh_storage_validate, - sample_data_model, - mocker, - fake_hash_collision, + monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision, ): """Multiple retries for hash collision and psycopg2 error but finally ok """ origin = sample_data_model["origin"][0] ori_meta = sample_data_model["origin_metadata"][0] assert origin.url == ori_meta.id - swh_storage_validate.origin_add([origin]) - swh_storage_validate.metadata_authority_add([sample_data_model["authority"][0]]) - swh_storage_validate.metadata_fetcher_add([sample_data_model["fetcher"][0]]) + swh_storage.origin_add([origin]) + swh_storage.metadata_authority_add([sample_data_model["authority"][0]]) + swh_storage.metadata_fetcher_add([sample_data_model["fetcher"][0]]) mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.object_metadata_add" ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("foo bar"), # ok then! None, ] # No exception raised as insertion finally came through - swh_storage_validate.object_metadata_add([ori_meta]) + swh_storage.object_metadata_add([ori_meta]) mock_memory.assert_has_calls( [ # 3 calls, as long as error raised call([ori_meta]), call([ori_meta]), call([ori_meta]), ] ) def test_retrying_proxy_swh_storage_object_metadata_add_failure( - swh_storage_validate, sample_data_model, mocker + swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.object_metadata_add" ) mock_memory.side_effect = StorageArgumentException("Refuse to add always!") origin = sample_data_model["origin"][0] ori_meta = sample_data_model["origin_metadata"][0] assert origin.url == ori_meta.id - swh_storage_validate.origin_add([origin]) + swh_storage.origin_add([origin]) with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage_validate.object_metadata_add([ori_meta]) + swh_storage.object_metadata_add([ori_meta]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_directory_add(swh_storage, sample_data_model): """Standard directory_add works as before """ sample_dir = sample_data_model["directory"][0] directory = swh_storage.directory_get_random() # no directory assert not directory s = swh_storage.directory_add([sample_dir]) assert s == { "directory:add": 1, } directory_id = swh_storage.directory_get_random() # only 1 assert directory_id == sample_dir.id def test_retrying_proxy_storage_directory_add_with_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.directory_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("directory already inserted"), # ok then! {"directory:add": 1}, ] sample_dir = sample_data_model["directory"][1] directory_id = swh_storage.directory_get_random() # no directory assert not directory_id s = swh_storage.directory_add([sample_dir]) assert s == { "directory:add": 1, } mock_memory.assert_has_calls( [call([sample_dir]), call([sample_dir]), call([sample_dir]),] ) def test_retrying_proxy_swh_storage_directory_add_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.directory_add") mock_memory.side_effect = StorageArgumentException( "Refuse to add directory always!" ) sample_dir = sample_data_model["directory"][0] directory_id = swh_storage.directory_get_random() # no directory assert not directory_id with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.directory_add([sample_dir]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_revision_add(swh_storage, sample_data_model): """Standard revision_add works as before """ sample_rev = sample_data_model["revision"][0] revision = next(swh_storage.revision_get([sample_rev.id])) assert not revision s = swh_storage.revision_add([sample_rev]) assert s == { "revision:add": 1, } revision = next(swh_storage.revision_get([sample_rev.id])) assert revision["id"] == sample_rev.id def test_retrying_proxy_storage_revision_add_with_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.revision_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("revision already inserted"), # ok then! {"revision:add": 1}, ] sample_rev = sample_data_model["revision"][0] revision = next(swh_storage.revision_get([sample_rev.id])) assert not revision s = swh_storage.revision_add([sample_rev]) assert s == { "revision:add": 1, } mock_memory.assert_has_calls( [call([sample_rev]), call([sample_rev]), call([sample_rev]),] ) def test_retrying_proxy_swh_storage_revision_add_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.revision_add") mock_memory.side_effect = StorageArgumentException("Refuse to add revision always!") sample_rev = sample_data_model["revision"][0] revision = next(swh_storage.revision_get([sample_rev.id])) assert not revision with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.revision_add([sample_rev]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_release_add(swh_storage, sample_data_model): """Standard release_add works as before """ sample_rel = sample_data_model["release"][0] release = next(swh_storage.release_get([sample_rel.id])) assert not release s = swh_storage.release_add([sample_rel]) assert s == { "release:add": 1, } release = next(swh_storage.release_get([sample_rel.id])) assert release["id"] == sample_rel.id def test_retrying_proxy_storage_release_add_with_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.release_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("release already inserted"), # ok then! {"release:add": 1}, ] sample_rel = sample_data_model["release"][0] release = next(swh_storage.release_get([sample_rel.id])) assert not release s = swh_storage.release_add([sample_rel]) assert s == { "release:add": 1, } mock_memory.assert_has_calls( [call([sample_rel]), call([sample_rel]), call([sample_rel]),] ) def test_retrying_proxy_swh_storage_release_add_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.release_add") mock_memory.side_effect = StorageArgumentException("Refuse to add release always!") sample_rel = sample_data_model["release"][0] release = next(swh_storage.release_get([sample_rel.id])) assert not release with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.release_add([sample_rel]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_snapshot_add(swh_storage, sample_data_model): """Standard snapshot_add works as before """ sample_snap = sample_data_model["snapshot"][0] snapshot = swh_storage.snapshot_get(sample_snap.id) assert not snapshot s = swh_storage.snapshot_add([sample_snap]) assert s == { "snapshot:add": 1, } snapshot = swh_storage.snapshot_get(sample_snap.id) assert snapshot["id"] == sample_snap.id def test_retrying_proxy_storage_snapshot_add_with_retry( monkeypatch_sleep, swh_storage, sample_data_model, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.snapshot_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("snapshot already inserted"), # ok then! {"snapshot:add": 1}, ] sample_snap = sample_data_model["snapshot"][0] snapshot = swh_storage.snapshot_get(sample_snap.id) assert not snapshot s = swh_storage.snapshot_add([sample_snap]) assert s == { "snapshot:add": 1, } mock_memory.assert_has_calls( [call([sample_snap]), call([sample_snap]), call([sample_snap]),] ) def test_retrying_proxy_swh_storage_snapshot_add_failure( swh_storage, sample_data_model, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.snapshot_add") mock_memory.side_effect = StorageArgumentException("Refuse to add snapshot always!") sample_snap = sample_data_model["snapshot"][0] snapshot = swh_storage.snapshot_get(sample_snap.id) assert not snapshot with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.snapshot_add([sample_snap]) assert mock_memory.call_count == 1 diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index af0fac43..7a4bbdfd 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,4282 +1,4147 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import inspect import itertools import math import queue import random import threading from collections import defaultdict from contextlib import contextmanager from datetime import timedelta from unittest.mock import Mock import attr -import psycopg2 import pytest from hypothesis import given, strategies, settings, HealthCheck -from typing import ClassVar, Dict, Optional, Union +from typing import ClassVar, Optional -from swh.model import from_disk, identifiers +from swh.model import from_disk from swh.model.hashutil import hash_to_bytes from swh.model.identifiers import SWHID from swh.model.model import ( Content, Directory, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, Person, Release, Revision, SkippedContent, Snapshot, ) from swh.model.hypothesis_strategies import objects from swh.storage import get_storage from swh.storage.converters import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.interface import StorageInterface from swh.storage.utils import content_hex_hashes, now from .storage_data import data @contextmanager def db_transaction(storage): with storage.db() as db: with db.transaction() as cur: yield db, cur -def normalize_entity(obj: Union[Revision, Release]) -> Dict: - """Normalize entity model object (revision, release)""" - entity = obj.to_dict() - for key in ("date", "committer_date"): - if key in entity: - entity[key] = identifiers.normalize_timestamp(entity[key]) - return entity - - def transform_entries(dir_, *, prefix=b""): for ent in dir_.entries: yield { "dir_id": dir_.id, "type": ent.type, "target": ent.target, "name": prefix + ent.name, "perms": ent.perms, "status": None, "sha1": None, "sha1_git": None, "sha256": None, "length": None, } def cmpdir(directory): return (directory["type"], directory["dir_id"]) def assert_contents_ok( expected_contents, actual_contents, keys_to_check={"sha1", "data"} ): """Assert that a given list of contents matches on a given set of keys. """ for k in keys_to_check: expected_list = set([c.get(k) for c in expected_contents]) actual_list = set([c.get(k) for c in actual_contents]) assert actual_list == expected_list, k def round_to_milliseconds(date): """Round datetime to milliseconds before insertion, so equality doesn't fail after a round-trip through a DB (eg. Cassandra) """ return date.replace(microsecond=(date.microsecond // 1000) * 1000) def test_round_to_milliseconds(): date = now() for (ms, expected_ms) in [(0, 0), (1000, 1000), (555555, 555000), (999500, 999000)]: date = date.replace(microsecond=ms) actual_date = round_to_milliseconds(date) assert actual_date.microsecond == expected_ms class LazyContent(Content): def with_data(self): return Content.from_dict({**self.to_dict(), "data": data.cont["data"]}) class TestStorage: """Main class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ maxDiff = None # type: ClassVar[Optional[int]] def test_types(self, swh_storage_backend_config): """Checks all methods of StorageInterface are implemented by this backend, and that they have the same signature.""" # Create an instance of the protocol (which cannot be instantiated # directly, so this creates a subclass, then instantiates it) interface = type("_", (StorageInterface,), {})() storage = get_storage(**swh_storage_backend_config) assert "content_add" in dir(interface) missing_methods = [] for meth_name in dir(interface): if meth_name.startswith("_"): continue interface_meth = getattr(interface, meth_name) try: concrete_meth = getattr(storage, meth_name) except AttributeError: if not getattr(interface_meth, "deprecated_endpoint", False): # The backend is missing a (non-deprecated) endpoint missing_methods.append(meth_name) continue expected_signature = inspect.signature(interface_meth) actual_signature = inspect.signature(concrete_meth) assert expected_signature == actual_signature, meth_name assert missing_methods == [] def test_check_config(self, swh_storage): assert swh_storage.check_config(check_write=True) assert swh_storage.check_config(check_write=False) def test_content_add(self, swh_storage, sample_data_model): cont = sample_data_model["content"][0] insertion_start_time = now() actual_result = swh_storage.content_add([cont]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } assert list(swh_storage.content_get([cont.sha1])) == [ {"sha1": cont.sha1, "data": cont.data} ] expected_cont = attr.evolve(cont, data=None) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time assert obj == expected_cont swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_generator(self, swh_storage, sample_data_model): cont = sample_data_model["content"][0] def _cnt_gen(): yield cont actual_result = swh_storage.content_add(_cnt_gen()) assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_lazy_content(self, swh_storage, sample_data_model): cont = sample_data_model["content"][0] lazy_content = LazyContent.from_dict(cont.to_dict()) insertion_start_time = now() - # bypass the validation proxy for now, to directly put a dict - actual_result = swh_storage.storage.content_add([lazy_content]) + actual_result = swh_storage.content_add([lazy_content]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } # the fact that we retrieve the content object from the storage with # the correct 'data' field ensures it has been 'called' assert list(swh_storage.content_get([cont.sha1])) == [ {"sha1": cont.sha1, "data": cont.data} ] expected_cont = attr.evolve(lazy_content, data=None, ctime=None) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time assert attr.evolve(obj, ctime=None).to_dict() == expected_cont.to_dict() swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 - def test_content_add_validation(self, swh_storage, sample_data_model): - cont = sample_data_model["content"][0].to_dict() - - with pytest.raises(StorageArgumentException, match="status"): - swh_storage.content_add([{**cont, "status": "absent"}]) - - with pytest.raises(StorageArgumentException, match="status"): - swh_storage.content_add([{**cont, "status": "foobar"}]) - - with pytest.raises(StorageArgumentException, match="(?i)length"): - swh_storage.content_add([{**cont, "length": -2}]) - - with pytest.raises(StorageArgumentException, match="reason"): - swh_storage.content_add([{**cont, "reason": "foobar"}]) - - def test_skipped_content_add_validation(self, swh_storage, sample_data_model): - cont = attr.evolve(sample_data_model["content"][0], data=None).to_dict() - - with pytest.raises(StorageArgumentException, match="status"): - swh_storage.skipped_content_add([{**cont, "status": "visible"}]) - - with pytest.raises(StorageArgumentException, match="reason") as cm: - swh_storage.skipped_content_add([{**cont, "status": "absent"}]) - - if type(cm.value) == psycopg2.IntegrityError: - assert cm.exception.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION - def test_content_get_missing(self, swh_storage, sample_data_model): cont, cont2 = sample_data_model["content"][:2] swh_storage.content_add([cont]) # Query a single missing content results = list(swh_storage.content_get([cont2.sha1])) assert results == [None] # Check content_get does not abort after finding a missing content results = list(swh_storage.content_get([cont.sha1, cont2.sha1])) assert results == [{"sha1": cont.sha1, "data": cont.data}, None] # Check content_get does not discard found countent when it finds # a missing content. results = list(swh_storage.content_get([cont2.sha1, cont.sha1])) assert results == [None, {"sha1": cont.sha1, "data": cont.data}] def test_content_add_different_input(self, swh_storage, sample_data_model): cont, cont2 = sample_data_model["content"][:2] actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { "content:add": 2, "content:add:bytes": cont.length + cont2.length, } def test_content_add_twice(self, swh_storage, sample_data_model): cont, cont2 = sample_data_model["content"][:2] actual_result = swh_storage.content_add([cont]) assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } assert len(swh_storage.journal_writer.journal.objects) == 1 actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { "content:add": 1, "content:add:bytes": cont2.length, } assert 2 <= len(swh_storage.journal_writer.journal.objects) <= 3 assert len(swh_storage.content_find(cont.to_dict())) == 1 assert len(swh_storage.content_find(cont2.to_dict())) == 1 def test_content_add_collision(self, swh_storage, sample_data_model): cont1 = sample_data_model["content"][0] # create (corrupted) content with same sha1{,_git} but != sha256 sha256_array = bytearray(cont1.sha256) sha256_array[0] += 1 cont1b = attr.evolve(cont1, sha256=bytes(sha256_array)) with pytest.raises(HashCollision) as cm: swh_storage.content_add([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == getattr(cont1, actual_algo).hex() collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(cont1.hashes()), content_hex_hashes(cont1b.hashes()), ] assert exc.colliding_content_hashes() == [ cont1.hashes(), cont1b.hashes(), ] def test_content_add_duplicate(self, swh_storage, sample_data_model): cont = sample_data_model["content"][0] swh_storage.content_add([cont, cont]) assert list(swh_storage.content_get([cont.sha1])) == [ {"sha1": cont.sha1, "data": cont.data} ] def test_content_update(self, swh_storage, sample_data_model): cont1 = sample_data_model["content"][0] - if hasattr(swh_storage, "storage"): + if hasattr(swh_storage, "journal_writer"): swh_storage.journal_writer.journal = None # TODO, not supported swh_storage.content_add([cont1]) # alter the sha1_git for example cont1b = attr.evolve( cont1, sha1_git=hash_to_bytes("3a60a5275d0333bf13468e8b3dcab90f4046e654") ) swh_storage.content_update([cont1b.to_dict()], keys=["sha1_git"]) results = swh_storage.content_get_metadata([cont1.sha1]) expected_content = attr.evolve(cont1b, data=None).to_dict() del expected_content["ctime"] assert tuple(results[cont1.sha1]) == (expected_content,) def test_content_add_metadata(self, swh_storage, sample_data_model): cont = attr.evolve(sample_data_model["content"][0], data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } expected_cont = cont.to_dict() del expected_cont["ctime"] assert tuple(swh_storage.content_get_metadata([cont.sha1])[cont.sha1]) == ( expected_cont, ) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: obj = attr.evolve(obj, ctime=None) assert obj == cont def test_content_add_metadata_different_input(self, swh_storage, sample_data_model): contents = sample_data_model["content"][:2] cont = attr.evolve(contents[0], data=None, ctime=now()) cont2 = attr.evolve(contents[1], data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { "content:add": 2, } def test_content_add_metadata_collision(self, swh_storage, sample_data_model): cont1 = attr.evolve(sample_data_model["content"][0], data=None, ctime=now()) # create (corrupted) content with same sha1{,_git} but != sha256 sha1_git_array = bytearray(cont1.sha256) sha1_git_array[0] += 1 cont1b = attr.evolve(cont1, sha256=bytes(sha1_git_array)) with pytest.raises(HashCollision) as cm: swh_storage.content_add_metadata([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == getattr(cont1, actual_algo).hex() collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(cont1.hashes()), content_hex_hashes(cont1b.hashes()), ] assert exc.colliding_content_hashes() == [ cont1.hashes(), cont1b.hashes(), ] def test_skipped_content_add(self, swh_storage, sample_data_model): contents = sample_data_model["skipped_content"][:2] cont = contents[0] cont2 = attr.evolve(contents[1], blake2s256=None) contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [cont.hashes(), cont2.hashes()] actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [] def test_skipped_content_add_missing_hashes(self, swh_storage, sample_data_model): cont, cont2 = [ attr.evolve(c, sha1_git=None) for c in sample_data_model["skipped_content"][:2] ] contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [] def test_skipped_content_missing_partial_hash(self, swh_storage, sample_data_model): cont = sample_data_model["skipped_content"][0] cont2 = attr.evolve(cont, sha1_git=None) contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont]) assert actual_result.pop("skipped_content:add") == 1 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [cont2.hashes()] @pytest.mark.property_based @settings(deadline=None) # this test is very slow @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing(self, swh_storage, algos): algos |= {"sha1"} cont = Content.from_dict(data.cont2) missing_cont = SkippedContent.from_dict(data.missing_cont) swh_storage.content_add([cont]) test_contents = [cont.to_dict()] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_cont.to_dict() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == set( missing_per_hash["sha1"] ) for hash in algos: assert set( swh_storage.content_missing(test_contents, key_hash=hash) ) == set(missing_per_hash[hash]) @pytest.mark.property_based @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing_unknown_algo(self, swh_storage, algos): algos |= {"sha1"} cont = Content.from_dict(data.cont2) missing_cont = SkippedContent.from_dict(data.missing_cont) swh_storage.content_add([cont]) test_contents = [cont.to_dict()] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_cont.to_dict() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_content["nonexisting_algo"] = b"\x00" test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == set( missing_per_hash["sha1"] ) for hash in algos: assert set( swh_storage.content_missing(test_contents, key_hash=hash) ) == set(missing_per_hash[hash]) def test_content_missing_per_sha1(self, swh_storage, sample_data_model): # given cont = sample_data_model["content"][0] missing_cont = sample_data_model["skipped_content"][0] swh_storage.content_add([cont]) # when gen = swh_storage.content_missing_per_sha1([cont.sha1, missing_cont.sha1]) # then assert list(gen) == [missing_cont.sha1] def test_content_missing_per_sha1_git(self, swh_storage, sample_data_model): cont, cont2 = sample_data_model["content"][:2] missing_cont = sample_data_model["skipped_content"][0] swh_storage.content_add([cont, cont2]) contents = [cont.sha1_git, cont2.sha1_git, missing_cont.sha1_git] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont.sha1_git] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [c.to_dict() for c in swh_contents if c.status != "absent"] actual_contents = [] for i in range(16): actual_result = swh_storage.content_get_partition(i, 16) assert actual_result["next_page_token"] is None actual_contents.extend(actual_result["contents"]) assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents""" expected_contents = [c.to_dict() for c in swh_contents if c.status != "absent"] actual_result = swh_storage.content_get_partition(0, 1) assert actual_result["next_page_token"] is None actual_contents = actual_result["contents"] assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_partition_empty(self, swh_storage, swh_contents): """content_get_partition when at least one of the partitions is empty""" expected_contents = { cont.sha1 for cont in swh_contents if cont.status != "absent" } # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1) seen_sha1s = [] for i in range(nb_partitions): actual_result = swh_storage.content_get_partition( i, nb_partitions, limit=len(swh_contents) + 1 ) for cont in actual_result["contents"]: seen_sha1s.append(cont["sha1"]) # Limit is higher than the max number of results assert actual_result["next_page_token"] is None assert set(seen_sha1s) == expected_contents def test_content_get_partition_limit_none(self, swh_storage): """content_get_partition call with wrong limit input should fail""" with pytest.raises(StorageArgumentException) as e: swh_storage.content_get_partition(1, 16, limit=None) assert e.value.args == ("limit should not be None",) def test_generate_content_get_partition_pagination(self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [c.to_dict() for c in swh_contents if c.status != "absent"] # retrieve contents actual_contents = [] for i in range(4): page_token = None while True: actual_result = swh_storage.content_get_partition( i, 4, limit=3, page_token=page_token ) actual_contents.extend(actual_result["contents"]) page_token = actual_result["next_page_token"] if page_token is None: break assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_metadata(self, swh_storage, sample_data_model): cont1, cont2 = sample_data_model["content"][:2] swh_storage.content_add([cont1, cont2]) actual_md = swh_storage.content_get_metadata([cont1.sha1, cont2.sha1]) # we only retrieve the metadata so no data nor ctime within expected_cont1, expected_cont2 = [ attr.evolve(c, data=None).to_dict() for c in [cont1, cont2] ] expected_cont1.pop("ctime") expected_cont2.pop("ctime") assert tuple(actual_md[cont1.sha1]) == (expected_cont1,) assert tuple(actual_md[cont2.sha1]) == (expected_cont2,) assert len(actual_md.keys()) == 2 def test_content_get_metadata_missing_sha1(self, swh_storage, sample_data_model): cont1, cont2 = sample_data_model["content"][:2] missing_cont = sample_data_model["skipped_content"][0] swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get_metadata([missing_cont.sha1]) assert len(actual_contents) == 1 assert tuple(actual_contents[missing_cont.sha1]) == () def test_content_get_random(self, swh_storage, sample_data_model): cont, cont2 = sample_data_model["content"][:2] cont3 = sample_data_model["content_no_data"][0] swh_storage.content_add([cont, cont2, cont3]) assert swh_storage.content_get_random() in { cont.sha1_git, cont2.sha1_git, cont3.sha1_git, } def test_directory_add(self, swh_storage, sample_data_model): directory = sample_data_model["directory"][1] init_missing = list(swh_storage.directory_missing([directory.id])) assert [directory.id] == init_missing actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)) ] actual_data = list(swh_storage.directory_ls(directory.id)) expected_data = list(transform_entries(directory)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) after_missing = list(swh_storage.directory_missing([directory.id])) assert after_missing == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_from_generator(self, swh_storage, sample_data_model): directory = sample_data_model["directory"][1] def _dir_gen(): yield directory actual_result = swh_storage.directory_add(directories=_dir_gen()) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", directory) ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 - def test_directory_add_validation(self, swh_storage, sample_data_model): - directory = sample_data_model["directory"][1] - dir_ = directory.to_dict() - dir_["entries"][0]["type"] = "foobar" - - with pytest.raises(StorageArgumentException, match="type.*foobar"): - swh_storage.directory_add([dir_]) - - dir_ = directory.to_dict() - del dir_["entries"][0]["target"] - - with pytest.raises(StorageArgumentException, match="target") as cm: - swh_storage.directory_add([dir_]) - - if type(cm.value) == psycopg2.IntegrityError: - assert cm.value.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION - def test_directory_add_twice(self, swh_storage, sample_data_model): directory = sample_data_model["directory"][1] actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", directory) ] actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 0} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", directory) ] def test_directory_get_recursive(self, swh_storage, sample_data_model): dir1, dir2, dir3 = sample_data_model["directory"][:3] init_missing = list(swh_storage.directory_missing([dir1.id])) assert init_missing == [dir1.id] actual_result = swh_storage.directory_add([dir1, dir2, dir3]) assert actual_result == {"directory:add": 3} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", dir1), ("directory", dir2), ("directory", dir3), ] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir1.id, recursive=True)) expected_data = list(transform_entries(dir1)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir2.id, recursive=True)) expected_data = list(transform_entries(dir2)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # be both those of the directory and of the subdir actual_data = list(swh_storage.directory_ls(dir3.id, recursive=True)) expected_data = list( itertools.chain( transform_entries(dir3), transform_entries(dir2, prefix=b"subdir/"), ) ) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) def test_directory_get_non_recursive(self, swh_storage, sample_data_model): dir1, dir2, dir3 = sample_data_model["directory"][:3] init_missing = list(swh_storage.directory_missing([dir1.id])) assert init_missing == [dir1.id] actual_result = swh_storage.directory_add([dir1, dir2, dir3]) assert actual_result == {"directory:add": 3} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", dir1), ("directory", dir2), ("directory", dir3), ] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir1.id)) expected_data = list(transform_entries(dir1)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory contaiining a single file actual_data = list(swh_storage.directory_ls(dir2.id)) expected_data = list(transform_entries(dir2)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(swh_storage.directory_ls(dir3.id)) expected_data = list(transform_entries(dir3)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) def test_directory_entry_get_by_path(self, swh_storage, sample_data_model): cont = sample_data_model["content"][0] dir1, dir2, dir3, dir4 = sample_data_model["directory"][:4] # given init_missing = list(swh_storage.directory_missing([dir3.id])) assert init_missing == [dir3.id] actual_result = swh_storage.directory_add([dir3, dir4]) assert actual_result == {"directory:add": 2} expected_entries = [ { "dir_id": dir3.id, "name": b"foo", "type": "file", "target": cont.sha1_git, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.content, "length": None, }, { "dir_id": dir3.id, "name": b"subdir", "type": "dir", "target": dir2.id, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.directory, "length": None, }, { "dir_id": dir3.id, "name": b"hello", "type": "file", "target": b"12345678901234567890", "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.content, "length": None, }, ] # when (all must be found here) for entry, expected_entry in zip(dir3.entries, expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( dir3.id, [entry.name] ) assert actual_entry == expected_entry # same, but deeper for entry, expected_entry in zip(dir3.entries, expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( dir4.id, [b"subdir1", entry.name] ) expected_entry = expected_entry.copy() expected_entry["name"] = b"subdir1/" + expected_entry["name"] assert actual_entry == expected_entry # when (nothing should be found here since data.dir is not persisted.) for entry in dir2.entries: actual_entry = swh_storage.directory_entry_get_by_path( dir2.id, [entry.name] ) assert actual_entry is None def test_directory_get_random(self, swh_storage, sample_data_model): dir1, dir2, dir3 = sample_data_model["directory"][:3] swh_storage.directory_add([dir1, dir2, dir3]) assert swh_storage.directory_get_random() in { dir1.id, dir2.id, dir3.id, } def test_revision_add(self, swh_storage, sample_data_model): revision = sample_data_model["revision"][0] init_missing = swh_storage.revision_missing([revision.id]) assert list(init_missing) == [revision.id] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([revision.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] # already there so nothing added actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_from_generator(self, swh_storage, sample_data_model): revision = sample_data_model["revision"][0] def _rev_gen(): yield revision actual_result = swh_storage.revision_add(_rev_gen()) assert actual_result == {"revision:add": 1} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 - def test_revision_add_validation(self, swh_storage, sample_data_model): - revision = sample_data_model["revision"][0] - - rev = revision.to_dict() - rev["date"]["offset"] = 2 ** 16 - - with pytest.raises(StorageArgumentException, match="offset") as cm: - swh_storage.revision_add([rev]) - - if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE - - rev = revision.to_dict() - rev["committer_date"]["offset"] = 2 ** 16 - - with pytest.raises(StorageArgumentException, match="offset") as cm: - swh_storage.revision_add([rev]) - - if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE - - rev = revision.to_dict() - rev["type"] = "foobar" - - with pytest.raises(StorageArgumentException, match="(?i)type") as cm: - swh_storage.revision_add([rev]) - - if type(cm.value) == psycopg2.DataError: - assert cm.value.pgcode == psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION - def test_revision_add_twice(self, swh_storage, sample_data_model): revision, revision2 = sample_data_model["revision"][:2] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] actual_result = swh_storage.revision_add([revision, revision2]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision), ("revision", revision2), ] def test_revision_add_name_clash(self, swh_storage, sample_data_model): revision, revision2 = sample_data_model["revision"][:2] revision1 = attr.evolve( revision, author=Person( fullname=b"John Doe ", name=b"John Doe", email=b"john.doe@example.com", ), ) revision2 = attr.evolve( revision2, author=Person( 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, sample_data_model): revision, revision2 = sample_data_model["revision"][:2] add_result = swh_storage.revision_add([revision, revision2]) assert add_result == {"revision:add": 2} # order 1 res1 = swh_storage.revision_get([revision.id, revision2.id]) - assert list(res1) == [revision.to_dict(), revision2.to_dict()] + + assert [Revision.from_dict(r) for r in res1] == [revision, revision2] # order 2 res2 = swh_storage.revision_get([revision2.id, revision.id]) - assert list(res2) == [revision2.to_dict(), revision.to_dict()] + assert [Revision.from_dict(r) for r in res2] == [revision2, revision] def test_revision_log(self, swh_storage, sample_data_model): revision3, revision4 = sample_data_model["revision"][2:4] # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([revision3, revision4]) # when - actual_results = list(swh_storage.revision_log([revision4.id])) + results = list(swh_storage.revision_log([revision4.id])) + # for comparison purposes + actual_results = [Revision.from_dict(r) for r in results] assert len(actual_results) == 2 # rev4 -child-> rev3 - assert actual_results[0] == normalize_entity(revision4) - assert actual_results[1] == normalize_entity(revision3) + assert actual_results == [revision4, revision3] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision3), ("revision", revision4), ] def test_revision_log_with_limit(self, swh_storage, sample_data_model): revision3, revision4 = sample_data_model["revision"][2:4] # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([revision3, revision4]) - actual_results = list(swh_storage.revision_log([revision4.id], 1)) + results = list(swh_storage.revision_log([revision4.id], 1)) + actual_results = [Revision.from_dict(r) for r in results] assert len(actual_results) == 1 - assert actual_results[0] == normalize_entity(revision4) + assert actual_results[0] == revision4 def test_revision_log_unknown_revision(self, swh_storage, sample_data_model): revision = sample_data_model["revision"][0] rev_log = list(swh_storage.revision_log([revision.id])) assert rev_log == [] def test_revision_shortlog(self, swh_storage, sample_data_model): revision3, revision4 = sample_data_model["revision"][2:4] # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([revision3, revision4]) # when - actual_results = list(swh_storage.revision_shortlog([revision4.id])) + results = list(swh_storage.revision_shortlog([revision4.id])) + + actual_results = [[id, tuple(parents)] for (id, parents) in results] assert len(actual_results) == 2 # rev4 -child-> rev3 assert list(actual_results[0]) == [revision4.id, revision4.parents] assert list(actual_results[1]) == [revision3.id, revision3.parents] def test_revision_shortlog_with_limit(self, swh_storage, sample_data_model): revision3, revision4 = sample_data_model["revision"][2:4] # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([revision3, revision4]) - actual_results = list(swh_storage.revision_shortlog([revision4.id], 1)) + results = list(swh_storage.revision_shortlog([revision4.id], 1)) + actual_results = [[id, tuple(parents)] for (id, parents) in results] assert len(actual_results) == 1 assert list(actual_results[0]) == [revision4.id, revision4.parents] def test_revision_get(self, swh_storage, sample_data_model): revision, revision2 = sample_data_model["revision"][:2] swh_storage.revision_add([revision]) actual_revisions = list(swh_storage.revision_get([revision.id, revision2.id])) assert len(actual_revisions) == 2 - assert actual_revisions[0] == normalize_entity(revision) + assert Revision.from_dict(actual_revisions[0]) == revision assert actual_revisions[1] is None def test_revision_get_no_parents(self, swh_storage, sample_data_model): revision = sample_data_model["revision"][2] swh_storage.revision_add([revision]) get = list(swh_storage.revision_get([revision.id])) assert len(get) == 1 - assert get[0]["parents"] == () # no parents on this one + assert tuple(get[0]["parents"]) == () # no parents on this one def test_revision_get_random(self, swh_storage, sample_data_model): revision1, revision2, revision3 = sample_data_model["revision"][:3] swh_storage.revision_add([revision1, revision2, revision3]) assert swh_storage.revision_get_random() in { revision1.id, revision2.id, revision3.id, } def test_release_add(self, swh_storage, sample_data_model): release, release2 = sample_data_model["release"][:2] init_missing = swh_storage.release_missing([release.id, release2.id]) assert list(init_missing) == [release.id, release2.id] actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 2} end_missing = swh_storage.release_missing([release.id, release2.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release), ("release", release2), ] # already present so nothing added actual_result = swh_storage.release_add([release, 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, sample_data_model): release, release2 = sample_data_model["release"][:2] def _rel_gen(): yield release yield release2 actual_result = swh_storage.release_add(_rel_gen()) assert actual_result == {"release:add": 2} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release), ("release", release2), ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 def test_release_add_no_author_date(self, swh_storage, sample_data_model): full_release = sample_data_model["release"][0] release = attr.evolve(full_release, author=None, date=None) actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} end_missing = swh_storage.release_missing([release.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release) ] - def test_release_add_validation(self, swh_storage, sample_data_model): - release = sample_data_model["release"][0] - - rel = release.to_dict() - 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 = release.to_dict() - 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_validation_type(self, swh_storage, sample_data_model): - release = sample_data_model["release"][0] - rel = release.to_dict() - rel["date"]["offset"] = "toto" - with pytest.raises(StorageArgumentException): - swh_storage.release_add([rel]) - def test_release_add_twice(self, swh_storage, sample_data_model): release, release2 = sample_data_model["release"][:2] actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release) ] actual_result = swh_storage.release_add([release, release2, release, release2]) assert actual_result == {"release:add": 1} assert set(swh_storage.journal_writer.journal.objects) == set( [("release", release), ("release", release2),] ) def test_release_add_name_clash(self, swh_storage, sample_data_model): release, release2 = [ attr.evolve( c, author=Person( fullname=b"John Doe ", name=b"John Doe", email=b"john.doe@example.com", ), ) for c in sample_data_model["release"][:2] ] actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 2} def test_release_get(self, swh_storage, sample_data_model): release, release2, release3 = sample_data_model["release"][:3] # given swh_storage.release_add([release, release2]) # when - actual_releases = list(swh_storage.release_get([release.id, release2.id])) + releases = list(swh_storage.release_get([release.id, release2.id])) + actual_releases = [Release.from_dict(r) for r in releases] # then - assert [actual_releases[0], actual_releases[1],] == [ - normalize_entity(release), - normalize_entity(release2), - ] + assert actual_releases == [release, release2] unknown_releases = list(swh_storage.release_get([release3.id])) assert unknown_releases[0] is None def test_release_get_order(self, swh_storage, sample_data_model): release, release2 = sample_data_model["release"][:2] add_result = swh_storage.release_add([release, release2]) assert add_result == {"release:add": 2} # order 1 res1 = swh_storage.release_get([release.id, release2.id]) assert list(res1) == [release.to_dict(), release2.to_dict()] # order 2 res2 = swh_storage.release_get([release2.id, release.id]) assert list(res2) == [release2.to_dict(), release.to_dict()] def test_release_get_random(self, swh_storage, sample_data_model): release, release2, release3 = sample_data_model["release"][:3] swh_storage.release_add([release, release2, release3]) assert swh_storage.release_get_random() in { release.id, release2.id, release3.id, } def test_origin_add(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dict, origin2_dict = [o.to_dict() for o in [origin, origin2]] assert swh_storage.origin_get([origin_dict])[0] is None stats = swh_storage.origin_add([origin, origin2]) assert stats == {"origin:add": 2} actual_origin = swh_storage.origin_get([origin_dict])[0] assert actual_origin["url"] == origin.url actual_origin2 = swh_storage.origin_get([origin2_dict])[0] assert actual_origin2["url"] == origin2.url assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_from_generator(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dict, origin2_dict = [o.to_dict() for o in [origin, origin2]] def _ori_gen(): yield origin yield origin2 stats = swh_storage.origin_add(_ori_gen()) assert stats == {"origin:add": 2} actual_origin = swh_storage.origin_get([origin_dict])[0] assert actual_origin["url"] == origin.url actual_origin2 = swh_storage.origin_get([origin2_dict])[0] assert actual_origin2["url"] == origin2.url assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_twice(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dict, origin2_dict = [o.to_dict() for o in [origin, origin2]] add1 = swh_storage.origin_add([origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) assert add1 == {"origin:add": 2} add2 = swh_storage.origin_add([origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) assert add2 == {"origin:add": 0} - def test_origin_add_validation(self, swh_storage): - """Incorrect formatted origin should fail the validation - - """ - with pytest.raises(StorageArgumentException, match="url"): - swh_storage.origin_add([{}]) - with pytest.raises( - StorageArgumentException, match="unexpected keyword argument" - ): - swh_storage.origin_add([{"ul": "mistyped url key"}]) - def test_origin_get_legacy(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dict, origin2_dict = [o.to_dict() for o in [origin, origin2]] assert swh_storage.origin_get(origin_dict) is None swh_storage.origin_add([origin]) actual_origin0 = swh_storage.origin_get(origin_dict) assert actual_origin0["url"] == origin.url def test_origin_get(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dict, origin2_dict = [o.to_dict() for o in [origin, origin2]] assert swh_storage.origin_get(origin_dict) is None assert swh_storage.origin_get([origin_dict]) == [None] swh_storage.origin_add([origin]) actual_origins = swh_storage.origin_get([origin_dict]) assert len(actual_origins) == 1 actual_origin0 = swh_storage.origin_get(origin_dict) assert actual_origin0 == actual_origins[0] assert actual_origin0["url"] == origin.url actual_origins = swh_storage.origin_get([origin_dict, {"url": "not://exists"}]) assert actual_origins == [origin_dict, None] 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 = now() 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_all(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) visits = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ), OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ), OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ), ] ) ov1, ov2, ov3 = [ {**v.to_dict(), "status": "created", "snapshot": None, "metadata": None,} for v in visits ] # order asc, no pagination, no limit all_visits = list(swh_storage.origin_visit_get(origin.url)) assert all_visits == [ov1, ov2, ov3] # order asc, no pagination, limit all_visits2 = list(swh_storage.origin_visit_get(origin.url, limit=2)) assert all_visits2 == [ov1, ov2] # order asc, pagination, no limit all_visits3 = list( swh_storage.origin_visit_get(origin.url, last_visit=ov1["visit"]) ) assert all_visits3 == [ov2, ov3] # order asc, pagination, limit all_visits4 = list( swh_storage.origin_visit_get(origin.url, last_visit=ov2["visit"], limit=1) ) assert all_visits4 == [ov3] # order desc, no pagination, no limit all_visits5 = list(swh_storage.origin_visit_get(origin.url, order="desc")) assert all_visits5 == [ov3, ov2, ov1] # order desc, no pagination, limit all_visits6 = list( swh_storage.origin_visit_get(origin.url, limit=2, order="desc") ) assert all_visits6 == [ov3, ov2] # order desc, pagination, no limit all_visits7 = list( swh_storage.origin_visit_get( origin.url, last_visit=ov3["visit"], order="desc" ) ) assert all_visits7 == [ov2, ov1] # order desc, pagination, limit all_visits8 = list( swh_storage.origin_visit_get( origin.url, last_visit=ov3["visit"], order="desc", limit=1 ) ) assert all_visits8 == [ov2] def test_origin_visit_get__unknown_origin(self, swh_storage): assert [] == list(swh_storage.origin_visit_get("foo")) def test_origin_visit_get_random(self, swh_storage, sample_data_model): origins = sample_data_model["origin"][:2] swh_storage.origin_add(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 origins: for date_visit in visits: visit = swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=None, ) ] ) swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(origins) assert stats["origin_visit"] == len(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 assert random_origin_visit["origin"] in [o.url for o in origins] def test_origin_visit_get_random_nothing_found( self, swh_storage, sample_data_model ): origins = sample_data_model["origin"] swh_storage.origin_add(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 origins: for date_visit in visits: visit = swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=None, ) ] ) 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, sample_data_model): origin = sample_data_model["origin"][0] assert swh_storage.origin_get(origin.to_dict()) is None swh_storage.origin_add([origin]) origins = list(swh_storage.origin_get_by_sha1([sha1(origin.url)])) assert len(origins) == 1 assert origins[0]["url"] == origin.url def test_origin_get_by_sha1_not_found(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] assert swh_storage.origin_get(origin.to_dict()) is None origins = list(swh_storage.origin_get_by_sha1([sha1(origin.url)])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] found_origins = list(swh_storage.origin_search(origin.url)) assert len(found_origins) == 0 found_origins = list(swh_storage.origin_search(origin.url, regexp=True)) assert len(found_origins) == 0 swh_storage.origin_add([origin]) origin_data = origin.to_dict() found_origins = list(swh_storage.origin_search(origin.url)) assert len(found_origins) == 1 assert found_origins[0] == origin_data found_origins = list( swh_storage.origin_search(f".{origin.url[1:-1]}.", regexp=True) ) assert len(found_origins) == 1 assert found_origins[0] == origin_data swh_storage.origin_add([origin2]) origin2_data = origin2.to_dict() found_origins = list(swh_storage.origin_search(origin2.url)) assert len(found_origins) == 1 assert found_origins[0] == origin2_data found_origins = list( swh_storage.origin_search(f".{origin2.url[1:-1]}.", regexp=True) ) assert len(found_origins) == 1 assert found_origins[0] == origin2_data def test_origin_search_no_regexp(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dicts = [o.to_dict() for o in [origin, origin2]] swh_storage.origin_add([origin, origin2]) # 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)) assert len(found_origins0) == 1 assert found_origins0[0] in origin_dicts # offset=1 found_origins1 = list(swh_storage.origin_search("/", offset=1, limit=1)) assert len(found_origins1) == 1 assert found_origins1[0] in origin_dicts # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_substring(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dicts = [o.to_dict() for o in [origin, origin2]] swh_storage.origin_add([origin, origin2]) # 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) ) assert len(found_origins0) == 1 assert found_origins0[0] in origin_dicts # offset=1 found_origins1 = list( swh_storage.origin_search("/", offset=1, limit=1, regexp=True) ) assert len(found_origins1) == 1 assert found_origins1[0] in origin_dicts # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_fullstring(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] origin_dicts = [o.to_dict() for o in [origin, origin2]] swh_storage.origin_add([origin, origin2]) # 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) ) assert len(found_origins0) == 1 assert found_origins0[0] in origin_dicts # offset=1 found_origins1 = list( swh_storage.origin_search(".*/.*", offset=1, limit=1, regexp=True) ) assert len(found_origins1) == 1 assert found_origins1[0] in origin_dicts # check both origins were returned assert found_origins0 != found_origins1 def test_origin_visit_add(self, swh_storage, sample_data_model): origin1 = sample_data_model["origin"][1] swh_storage.origin_add([origin1]) date_visit = now() date_visit2 = date_visit + datetime.timedelta(minutes=1) date_visit = round_to_milliseconds(date_visit) date_visit2 = round_to_milliseconds(date_visit2) visit1 = OriginVisit( origin=origin1.url, date=date_visit, type=data.type_visit1, ) visit2 = OriginVisit( origin=origin1.url, date=date_visit2, type=data.type_visit2, ) # add once ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2]) # then again (will be ignored as they already exist) origin_visit1, origin_visit2 = swh_storage.origin_visit_add([ov1, ov2]) assert ov1 == origin_visit1 assert ov2 == origin_visit2 ovs1 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=date_visit, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=date_visit2, status="created", snapshot=None, ) actual_origin_visits = list(swh_storage.origin_visit_get(origin1.url)) expected_visits = [ {**ovs1.to_dict(), "type": ov1.type}, {**ovs2.to_dict(), "type": ov2.type}, ] assert len(expected_visits) == len(actual_origin_visits) for visit in expected_visits: assert visit in actual_origin_visits actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = list( [("origin", origin1)] + [("origin_visit", visit) for visit in [ov1, ov2]] * 2 + [("origin_visit_status", ovs) for ovs in [ovs1, ovs2]] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_add_validation(self, swh_storage): """Unknown origin when adding visits should raise""" visit = OriginVisit( origin="something-unknown", date=now(), type=data.type_visit1, ) with pytest.raises(StorageArgumentException, match="Unknown origin"): swh_storage.origin_visit_add([visit]) objects = list(swh_storage.journal_writer.journal.objects) assert not objects def test_origin_visit_status_add_validation(self, swh_storage): """Wrong origin_visit_status input should raise storage argument error""" date_visit = now() visit_status1 = OriginVisitStatus( origin="unknown-origin-url", visit=10, date=date_visit, status="full", snapshot=None, ) with pytest.raises(StorageArgumentException, match="Unknown origin"): swh_storage.origin_visit_status_add([visit_status1]) objects = list(swh_storage.journal_writer.journal.objects) assert not objects def test_origin_visit_status_add(self, swh_storage, sample_data_model): """Correct origin visit statuses should add a new visit status """ snapshot = sample_data_model["snapshot"][0] origin1 = sample_data_model["origin"][1] origin2 = Origin(url="new-origin") swh_storage.origin_add([origin1, origin2]) ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=data.date_visit1, type=data.type_visit1, ), OriginVisit( origin=origin2.url, date=data.date_visit2, type=data.type_visit2, ), ] ) ovs1 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=data.date_visit1, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin2.url, visit=ov2.visit, date=data.date_visit2, status="created", snapshot=None, ) date_visit_now = now() visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, status="full", snapshot=snapshot.id, ) date_visit_now = now() visit_status2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_visit_now, status="ongoing", snapshot=None, metadata={"intrinsic": "something"}, ) swh_storage.origin_visit_status_add([visit_status1, visit_status2]) origin_visit1 = swh_storage.origin_visit_get_latest( origin1.url, require_snapshot=True ) assert origin_visit1 assert origin_visit1["status"] == "full" assert origin_visit1["snapshot"] == snapshot.id origin_visit2 = swh_storage.origin_visit_get_latest( origin2.url, require_snapshot=False ) assert origin2.url != origin1.url assert origin_visit2 assert origin_visit2["status"] == "ongoing" assert origin_visit2["snapshot"] is None assert origin_visit2["metadata"] == {"intrinsic": "something"} actual_objects = list(swh_storage.journal_writer.journal.objects) expected_origins = [origin1, origin2] expected_visits = [ov1, ov2] expected_visit_statuses = [ovs1, ovs2, visit_status1, visit_status2] expected_objects = ( [("origin", o) for o in expected_origins] + [("origin_visit", v) for v in expected_visits] + [("origin_visit_status", ovs) for ovs in expected_visit_statuses] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_status_add_twice(self, swh_storage, sample_data_model): """Correct origin visit statuses should add a new visit status """ snapshot = sample_data_model["snapshot"][0] origin1 = sample_data_model["origin"][1] swh_storage.origin_add([origin1]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=data.date_visit1, type=data.type_visit1, ), ] )[0] ovs1 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=data.date_visit1, status="created", snapshot=None, ) date_visit_now = now() visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, status="full", snapshot=snapshot.id, ) swh_storage.origin_visit_status_add([visit_status1]) # second call will ignore existing entries (will send to storage though) swh_storage.origin_visit_status_add([visit_status1]) origin_visits = list(swh_storage.origin_visit_get(ov1.origin)) assert len(origin_visits) == 1 origin_visit1 = origin_visits[0] assert origin_visit1 assert origin_visit1["status"] == "full" assert origin_visit1["snapshot"] == snapshot.id actual_objects = list(swh_storage.journal_writer.journal.objects) expected_origins = [origin1] expected_visits = [ov1] expected_visit_statuses = [ovs1, visit_status1, visit_status1] # write twice in the journal expected_objects = ( [("origin", o) for o in expected_origins] + [("origin_visit", v) for v in expected_visits] + [("origin_visit_status", ovs) for ovs in expected_visit_statuses] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_find_by_date(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit1, ) visit2 = OriginVisit( origin=origin.url, date=data.date_visit3, type=data.type_visit2, ) visit3 = OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit3, ) ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) ovs1 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=data.date_visit2, status="ongoing", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=data.date_visit3, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin.url, visit=ov3.visit, date=data.date_visit2, status="ongoing", snapshot=None, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3]) # Simple case visit = swh_storage.origin_visit_find_by_date(origin.url, data.date_visit3) assert visit["visit"] == ov2.visit # There are two visits at the same date, the latest must be returned visit = swh_storage.origin_visit_find_by_date(origin.url, data.date_visit2) assert visit["visit"] == ov3.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_get_by(self, swh_storage, sample_data_model): snapshot = sample_data_model["snapshot"][0] origins = sample_data_model["origin"][:2] swh_storage.origin_add(origins) origin_url, origin_url2 = [o.url for o in origins] visit = OriginVisit( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) # Add some other {origin, visit} entries visit2 = OriginVisit( origin=origin_url, date=data.date_visit3, type=data.type_visit3, ) visit3 = OriginVisit( origin=origin_url2, date=data.date_visit3, type=data.type_visit3, ) swh_storage.origin_visit_add([visit2, visit3]) # when visit1_metadata = { "contents": 42, "directories": 22, } swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=origin_visit1.visit, date=now(), status="full", snapshot=snapshot.id, metadata=visit1_metadata, ) ] ) expected_origin_visit = origin_visit1.to_dict() expected_origin_visit.update( { "origin": origin_url, "visit": origin_visit1.visit, "date": data.date_visit2, "type": data.type_visit2, "metadata": visit1_metadata, "status": "full", "snapshot": 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_get_by_no_result(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) actual_origin_visit = swh_storage.origin_visit_get_by(origin.url, 999) assert actual_origin_visit is None def test_origin_visit_get_latest_none(self, swh_storage, sample_data_model): """Origin visit get latest on unknown objects should return nothing """ # unknown origin so no result assert swh_storage.origin_visit_get_latest("unknown-origin") is None # unknown type origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) assert swh_storage.origin_visit_get_latest(origin.url, type="unknown") is None def test_origin_visit_get_latest_filter_type(self, swh_storage, sample_data_model): """Filtering origin visit get latest with filter type should be ok """ origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ) visit2 = OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ) # Add a visit with the same date as the previous one visit3 = OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ) assert data.type_visit1 != data.type_visit2 assert data.date_visit1 < data.date_visit2 ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) origin_visit1 = swh_storage.origin_visit_get_by(origin.url, ov1.visit) origin_visit3 = swh_storage.origin_visit_get_by(origin.url, ov3.visit) assert data.type_visit1 != data.type_visit2 # Check type filter is ok actual_ov1 = swh_storage.origin_visit_get_latest( origin.url, type=data.type_visit1, ) assert actual_ov1 == origin_visit1 actual_ov3 = swh_storage.origin_visit_get_latest( origin.url, type=data.type_visit2, ) assert actual_ov3 == origin_visit3 new_type = "npm" assert new_type not in [data.type_visit1, data.type_visit2] assert ( swh_storage.origin_visit_get_latest( origin.url, type=new_type, # no visit matching that type ) is None ) def test_origin_visit_get_latest(self, swh_storage, sample_data_model): empty_snapshot, complete_snapshot = sample_data_model["snapshot"][1:3] origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ) visit2 = OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ) # Add a visit with the same date as the previous one visit3 = OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ) ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) origin_visit1 = swh_storage.origin_visit_get_by(origin.url, ov1.visit) origin_visit2 = swh_storage.origin_visit_get_by(origin.url, ov2.visit) origin_visit3 = swh_storage.origin_visit_get_by(origin.url, ov3.visit) # Two visits, both with no snapshot assert origin_visit3 == swh_storage.origin_visit_get_latest(origin.url) assert ( swh_storage.origin_visit_get_latest(origin.url, require_snapshot=True) is None ) # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit == { **origin_visit1, "snapshot": complete_snapshot.id, "status": "ongoing", # visit1 has status created now } 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_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=now(), status="full", snapshot=complete_snapshot.id, ) ] ) assert { **origin_visit1, "snapshot": 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([empty_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=now(), status="ongoing", snapshot=empty_snapshot.id, ) ] ) assert { **origin_visit2, "snapshot": empty_snapshot.id, "status": "ongoing", } == 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": 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.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov3.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) assert { **origin_visit1, "snapshot": complete_snapshot.id, "status": "full", } == swh_storage.origin_visit_get_latest(origin.url, allowed_statuses=["full"]) assert { **origin_visit1, "snapshot": complete_snapshot.id, "status": "full", } == swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"], require_snapshot=True ) assert { **origin_visit3, "snapshot": complete_snapshot.id, "status": "ongoing", } == swh_storage.origin_visit_get_latest(origin.url) assert { **origin_visit3, "snapshot": complete_snapshot.id, "status": "ongoing", } == swh_storage.origin_visit_get_latest(origin.url, require_snapshot=True) def test_origin_visit_status_get_latest(self, swh_storage, sample_data_model): snapshot = sample_data_model["snapshot"][2] origin1 = sample_data_model["origin"][0] swh_storage.origin_add([origin1]) # to have some reference visits ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=data.date_visit1, type=data.type_visit1, ), OriginVisit( origin=origin1.url, date=data.date_visit2, type=data.type_visit2, ), ] ) swh_storage.snapshot_add([snapshot]) date_now = now() date_now = round_to_milliseconds(date_now) assert data.date_visit1 < data.date_visit2 assert data.date_visit2 < date_now ovs1 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=data.date_visit1, status="partial", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=data.date_visit2, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=data.date_visit2 + datetime.timedelta(minutes=1), # to not be ignored status="ongoing", snapshot=None, ) ovs4 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=date_now, status="full", snapshot=snapshot.id, metadata={"something": "wicked"}, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3, ovs4]) # unknown origin so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( "unknown-origin", ov1.visit ) assert actual_origin_visit is None # unknown visit so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( ov1.origin, ov1.visit + 10 ) assert actual_origin_visit is None # Two visits, both with no snapshot, take the most recent actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit ) assert isinstance(actual_origin_visit2, OriginVisitStatus) assert actual_origin_visit2 == ovs2 assert ovs2.origin == origin1.url assert ovs2.visit == ov1.visit actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, require_snapshot=True ) # there is no visit with snapshot yet for that visit assert actual_origin_visit is None actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, allowed_statuses=["partial", "ongoing"] ) # visit status with partial status visit elected assert actual_origin_visit2 == ovs2 assert actual_origin_visit2.status == "ongoing" actual_origin_visit4 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True ) assert actual_origin_visit4 == ovs4 assert actual_origin_visit4.snapshot == snapshot.id actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True, allowed_statuses=["ongoing"] ) # nothing matches so nothing assert actual_origin_visit is None # there is no visit with status full actual_origin_visit3 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, allowed_statuses=["ongoing"] ) assert actual_origin_visit3 == ovs3 def test_person_fullname_unicity(self, swh_storage, sample_data_model): revision, rev2 = sample_data_model["revision"][0:2] # create a revision with same committer fullname but wo name and email revision2 = attr.evolve( rev2, committer=Person( fullname=revision.committer.fullname, name=None, email=None ), ) swh_storage.revision_add([revision, 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, sample_data_model): empty_snapshot = sample_data_model["snapshot"][1] empty_snapshot_dict = empty_snapshot.to_dict() origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ) ] )[0] actual_result = swh_storage.snapshot_add([empty_snapshot]) assert actual_result == {"snapshot:add": 1} date_now = now() swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_now, status="full", snapshot=empty_snapshot.id, ) ] ) by_id = swh_storage.snapshot_get(empty_snapshot.id) assert by_id == {**empty_snapshot_dict, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin.url, ov1.visit) assert by_ov == {**empty_snapshot_dict, "next_branch": None} ovs1 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": data.date_visit1, "visit": ov1.visit, "status": "created", "snapshot": None, "metadata": None, } ) ovs2 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": date_now, "visit": ov1.visit, "status": "full", "metadata": None, "snapshot": empty_snapshot.id, } ) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("origin", origin), ("origin_visit", ov1), ("origin_visit_status", ovs1,), ("snapshot", empty_snapshot), ("origin_visit_status", ovs2,), ] for obj in expected_objects: assert obj in actual_objects def test_snapshot_add_get_complete(self, swh_storage, sample_data_model): complete_snapshot = sample_data_model["snapshot"][2] complete_snapshot_dict = complete_snapshot.to_dict() origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] visit_id = origin_visit1.visit actual_result = swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) assert actual_result == {"snapshot:add": 1} by_id = swh_storage.snapshot_get(complete_snapshot.id) assert by_id == {**complete_snapshot_dict, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin.url, visit_id) assert by_ov == {**complete_snapshot_dict, "next_branch": None} def test_snapshot_add_many(self, swh_storage, sample_data_model): snapshot, _, complete_snapshot = sample_data_model["snapshot"][:3] actual_result = swh_storage.snapshot_add([snapshot, complete_snapshot]) assert actual_result == {"snapshot:add": 2} assert swh_storage.snapshot_get(complete_snapshot.id) == { **complete_snapshot.to_dict(), "next_branch": None, } assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_from_generator(self, swh_storage, sample_data_model): snapshot, _, complete_snapshot = sample_data_model["snapshot"][:3] def _snp_gen(): yield from [snapshot, 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, sample_data_model): snapshot, _, complete_snapshot = sample_data_model["snapshot"][:3] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} actual_result2 = swh_storage.snapshot_add([snapshot, complete_snapshot]) assert actual_result2 == {"snapshot:add": 1} assert swh_storage.snapshot_get(complete_snapshot.id) == { **complete_snapshot.to_dict(), "next_branch": None, } assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } def test_snapshot_add_twice(self, swh_storage, sample_data_model): snapshot, empty_snapshot = sample_data_model["snapshot"][:2] actual_result = swh_storage.snapshot_add([empty_snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", empty_snapshot) ] actual_result = swh_storage.snapshot_add([snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", empty_snapshot), ("snapshot", snapshot), ] - def test_snapshot_add_validation(self, swh_storage, sample_data_model): - snapshot = sample_data_model["snapshot"][0] - - snap = snapshot.to_dict() - snap["branches"][b"foo"] = {"target_type": "revision"} - - with pytest.raises(StorageArgumentException, match="target"): - swh_storage.snapshot_add([snap]) - - snap = snapshot.to_dict() - 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, sample_data_model): complete_snapshot = sample_data_model["snapshot"][2] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} snp_size = swh_storage.snapshot_count_branches(complete_snapshot.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, sample_data_model): complete_snapshot = sample_data_model["snapshot"][2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.to_dict()["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, sample_data_model): origin = sample_data_model["origin"][0] complete_snapshot = sample_data_model["snapshot"][2] swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) snp_id = complete_snapshot.id branches = complete_snapshot.to_dict()["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, sample_data_model ): complete_snapshot = sample_data_model["snapshot"][2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.to_dict()["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_branch_by_type(self, swh_storage, sample_data_model): complete_snapshot = sample_data_model["snapshot"][2] snapshot = complete_snapshot.to_dict() alias1 = b"alias1" alias2 = b"alias2" target1 = random.choice(list(snapshot["branches"].keys())) target2 = random.choice(list(snapshot["branches"].keys())) snapshot["branches"][alias2] = { "target": target2, "target_type": "alias", } snapshot["branches"][alias1] = { "target": target1, "target_type": "alias", } new_snapshot = Snapshot.from_dict(snapshot) swh_storage.snapshot_add([new_snapshot]) branches = swh_storage.snapshot_get_branches( new_snapshot.id, target_types=["alias"], branches_from=alias1, branches_count=1, )["branches"] assert len(branches) == 1 assert alias1 in branches def test_snapshot_add_get(self, swh_storage, sample_data_model): snapshot = sample_data_model["snapshot"][0] origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] visit_id = origin_visit1.visit swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) expected_snapshot = {**snapshot.to_dict(), "next_branch": None} by_id = swh_storage.snapshot_get(snapshot.id) assert by_id == expected_snapshot by_ov = swh_storage.snapshot_get_by_origin_visit(origin.url, visit_id) assert by_ov == expected_snapshot origin_visit_info = swh_storage.origin_visit_get_by(origin.url, visit_id) assert origin_visit_info["snapshot"] == snapshot.id def test_snapshot_add_twice__by_origin_visit(self, swh_storage, sample_data_model): snapshot = sample_data_model["snapshot"][0] origin = sample_data_model["origin"][0] swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=data.date_visit1, type=data.type_visit1, ) ] )[0] swh_storage.snapshot_add([snapshot]) date_now2 = now() swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_now2, status="ongoing", snapshot=snapshot.id, ) ] ) expected_snapshot = {**snapshot.to_dict(), "next_branch": None} by_ov1 = swh_storage.snapshot_get_by_origin_visit(origin.url, ov1.visit) assert by_ov1 == expected_snapshot ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ) ] )[0] date_now4 = now() swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=date_now4, status="ongoing", snapshot=snapshot.id, ) ] ) by_ov2 = swh_storage.snapshot_get_by_origin_visit(origin.url, ov2.visit) assert by_ov2 == expected_snapshot ovs1 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": data.date_visit1, "visit": ov1.visit, "status": "created", "metadata": None, "snapshot": None, } ) ovs2 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": date_now2, "visit": ov1.visit, "status": "ongoing", "metadata": None, "snapshot": snapshot.id, } ) ovs3 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": data.date_visit2, "visit": ov2.visit, "status": "created", "metadata": None, "snapshot": None, } ) ovs4 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": date_now4, "visit": ov2.visit, "status": "ongoing", "metadata": None, "snapshot": snapshot.id, } ) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("origin", origin), ("origin_visit", ov1), ("origin_visit_status", ovs1), ("snapshot", snapshot), ("origin_visit_status", ovs2), ("origin_visit", ov2), ("origin_visit_status", ovs3), ("origin_visit_status", ovs4), ] for obj in expected_objects: assert obj in actual_objects def test_snapshot_get_random(self, swh_storage, sample_data_model): snapshot, empty_snapshot, complete_snapshot = sample_data_model["snapshot"][:3] swh_storage.snapshot_add([snapshot, empty_snapshot, complete_snapshot]) assert swh_storage.snapshot_get_random() in { snapshot.id, empty_snapshot.id, complete_snapshot.id, } def test_snapshot_missing(self, swh_storage, sample_data_model): snapshot, missing_snapshot = sample_data_model["snapshot"][:2] snapshots = [snapshot.id, missing_snapshot.id] swh_storage.snapshot_add([snapshot]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snapshot.id] def test_stat_counters(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] snapshot = sample_data_model["snapshot"][0] revision = sample_data_model["revision"][0] release = sample_data_model["release"][0] directory = sample_data_model["directory"][0] content = sample_data_model["content"][0] 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([content]) 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([origin]) visit = OriginVisit( origin=origin.url, date=data.date_visit2, type=data.type_visit2, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) swh_storage.directory_add([directory]) swh_storage.revision_add([revision]) swh_storage.release_add([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, sample_data_model): origin_content = sample_data_model["content"][0] ctime = round_to_milliseconds(now()) content = attr.evolve(origin_content, data=None, ctime=ctime) swh_storage.content_add_metadata([content]) actually_present = swh_storage.content_find({"sha1": content.sha1}) assert actually_present[0] == content.to_dict() def test_content_find_with_present_content(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] expected_content = content.to_dict() del expected_content["data"] del expected_content["ctime"] # 1. with something to find swh_storage.content_add([content]) actually_present = swh_storage.content_find({"sha1": content.sha1}) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == expected_content # 2. with something to find actually_present = swh_storage.content_find({"sha1_git": content.sha1_git}) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == expected_content # 3. with something to find actually_present = swh_storage.content_find({"sha256": content.sha256}) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == expected_content # 4. with something to find actually_present = swh_storage.content_find(content.hashes()) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == expected_content def test_content_find_with_non_present_content( self, swh_storage, sample_data_model ): missing_content = sample_data_model["content_no_data"][0] # 1. with something that does not exist actually_present = swh_storage.content_find({"sha1": missing_content.sha1}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {"sha1_git": missing_content.sha1_git} ) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find({"sha256": missing_content.sha256}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(content.sha1) sha1_array[0] += 1 sha1git_array = bytearray(content.sha1_git) sha1git_array[0] += 1 duplicated_content = attr.evolve( content, sha1=bytes(sha1_array), sha1_git=bytes(sha1git_array) ) # Inject the data swh_storage.content_add([content, duplicated_content]) actual_result = list( swh_storage.content_find( { "blake2s256": duplicated_content.blake2s256, "sha256": duplicated_content.sha256, } ) ) expected_content = content.to_dict() expected_duplicated_content = duplicated_content.to_dict() for key in ["data", "ctime"]: # so we can compare for dict_ in [ expected_content, expected_duplicated_content, actual_result[0], actual_result[1], ]: dict_.pop(key, None) expected_result = [expected_content, expected_duplicated_content] for result in expected_result: assert result in actual_result def test_content_find_with_duplicate_sha256(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] hashes = {} # Create fake data with colliding sha256 for hashalgo in ("sha1", "sha1_git", "blake2s256"): value = bytearray(getattr(content, hashalgo)) value[0] += 1 hashes[hashalgo] = bytes(value) duplicated_content = attr.evolve( content, sha1=hashes["sha1"], sha1_git=hashes["sha1_git"], blake2s256=hashes["blake2s256"], ) swh_storage.content_add([content, duplicated_content]) actual_result = list( swh_storage.content_find({"sha256": duplicated_content.sha256}) ) assert len(actual_result) == 2 expected_content = content.to_dict() expected_duplicated_content = duplicated_content.to_dict() for key in ["data", "ctime"]: # so we can compare for dict_ in [ expected_content, expected_duplicated_content, actual_result[0], actual_result[1], ]: dict_.pop(key, None) assert sorted(actual_result, key=lambda x: x["sha1"]) == [ expected_content, expected_duplicated_content, ] # Find with both sha256 and blake2s256 actual_result = list( swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) ) assert len(actual_result) == 1 actual_result[0].pop("ctime") assert actual_result == [expected_duplicated_content] def test_content_find_with_duplicate_blake2s256( self, swh_storage, sample_data_model ): content = sample_data_model["content"][0] # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(content.sha1) sha1_array[0] += 1 sha1git_array = bytearray(content.sha1_git) sha1git_array[0] += 1 sha256_array = bytearray(content.sha256) sha256_array[0] += 1 duplicated_content = attr.evolve( content, sha1=bytes(sha1_array), sha1_git=bytes(sha1git_array), sha256=bytes(sha256_array), ) swh_storage.content_add([content, duplicated_content]) actual_result = list( swh_storage.content_find({"blake2s256": duplicated_content.blake2s256}) ) expected_content = content.to_dict() expected_duplicated_content = duplicated_content.to_dict() for key in ["data", "ctime"]: # so we can compare for dict_ in [ expected_content, expected_duplicated_content, actual_result[0], actual_result[1], ]: dict_.pop(key, None) expected_result = [expected_content, expected_duplicated_content] for result in expected_result: assert result in actual_result # Find with both sha256 and blake2s256 actual_result = list( swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) ) actual_result[0].pop("ctime") assert actual_result == [expected_duplicated_content] 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, sample_data_model): content = sample_data_model["content"][0] directory = sample_data_model["directory"][0] revision = sample_data_model["revision"][0] release = sample_data_model["release"][0] sha1_gits = [b"00000000000000000000"] expected = { b"00000000000000000000": [], } swh_storage.content_add([content]) sha1_gits.append(content.sha1_git) expected[content.sha1_git] = [ {"sha1_git": content.sha1_git, "type": "content",} ] swh_storage.directory_add([directory]) sha1_gits.append(directory.id) expected[directory.id] = [{"sha1_git": directory.id, "type": "directory",}] swh_storage.revision_add([revision]) sha1_gits.append(revision.id) expected[revision.id] = [{"sha1_git": revision.id, "type": "revision",}] swh_storage.release_add([release]) sha1_gits.append(release.id) expected[release.id] = [{"sha1_git": release.id, "type": "release",}] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_metadata_fetcher_add_get(self, swh_storage, sample_data_model): fetcher = sample_data_model["fetcher"][0] actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert actual_fetcher is None # does not exist swh_storage.metadata_fetcher_add([fetcher]) res = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert res == fetcher def test_metadata_authority_add_get(self, swh_storage, sample_data_model): authority = sample_data_model["authority"][0] actual_authority = swh_storage.metadata_authority_get( authority.type, authority.url ) assert actual_authority is None # does not exist swh_storage.metadata_authority_add([authority]) res = swh_storage.metadata_authority_get(authority.type, authority.url) assert res == authority def test_content_metadata_add(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] content_metadata = sample_data_model["content_metadata"][:2] content_swhid = SWHID( object_type="content", object_id=hash_to_bytes(content.sha1_git) ) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add(content_metadata) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority ) assert result["next_page_token"] is None assert ( list(sorted(result["results"], key=lambda x: x.discovery_date,)) == content_metadata ) def test_content_metadata_add_duplicate(self, swh_storage, sample_data_model): """Duplicates should be silently updated.""" content = sample_data_model["content"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] content_metadata, content_metadata2 = sample_data_model["content_metadata"][:2] content_swhid = SWHID( object_type="content", object_id=hash_to_bytes(content.sha1_git) ) new_content_metadata2 = attr.evolve( content_metadata2, format="new-format", metadata=b"new-metadata", ) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([content_metadata, content_metadata2]) swh_storage.object_metadata_add([new_content_metadata2]) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority ) assert result["next_page_token"] is None expected_results1 = (content_metadata, new_content_metadata2) expected_results2 = (content_metadata, content_metadata2) assert tuple(sorted(result["results"], key=lambda x: x.discovery_date,)) in ( expected_results1, # cassandra expected_results2, # postgresql ) def test_content_metadata_get(self, swh_storage, sample_data_model): content, content2 = sample_data_model["content"][:2] fetcher, fetcher2 = sample_data_model["fetcher"][:2] authority, authority2 = sample_data_model["authority"][:2] content1_metadata1, content1_metadata2, content1_metadata3 = sample_data_model[ "content_metadata" ][:3] content1_swhid = SWHID(object_type="content", object_id=content.sha1_git) content2_swhid = SWHID(object_type="content", object_id=content2.sha1_git) content2_metadata = attr.evolve(content1_metadata2, id=content2_swhid) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.object_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content1_swhid, authority ) assert result["next_page_token"] is None assert [content1_metadata1, content1_metadata2] == list( sorted(result["results"], key=lambda x: x.discovery_date,) ) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content1_swhid, authority2 ) assert result["next_page_token"] is None assert [content1_metadata3] == list( sorted(result["results"], key=lambda x: x.discovery_date,) ) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content2_swhid, authority ) assert result["next_page_token"] is None assert [content2_metadata] == list(result["results"],) def test_content_metadata_get_after(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] content_metadata, content_metadata2 = sample_data_model["content_metadata"][:2] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([content_metadata, content_metadata2]) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, after=content_metadata.discovery_date - timedelta(seconds=1), ) assert result["next_page_token"] is None assert [content_metadata, content_metadata2] == list( sorted(result["results"], key=lambda x: x.discovery_date,) ) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, after=content_metadata.discovery_date, ) assert result["next_page_token"] is None assert result["results"] == [content_metadata2] result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, after=content_metadata2.discovery_date, ) assert result["next_page_token"] is None assert result["results"] == [] def test_content_metadata_get_paginate(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] content_metadata, content_metadata2 = sample_data_model["content_metadata"][:2] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([content_metadata, content_metadata2]) swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority ) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1 ) assert result["next_page_token"] is not None assert result["results"] == [content_metadata] result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1, page_token=result["next_page_token"], ) assert result["next_page_token"] is None assert result["results"] == [content_metadata2] def test_content_metadata_get_paginate_same_date( self, swh_storage, sample_data_model ): content = sample_data_model["content"][0] fetcher1, fetcher2 = sample_data_model["fetcher"][:2] authority = sample_data_model["authority"][0] content_metadata, content_metadata2 = sample_data_model["content_metadata"][:2] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_content_metadata2 = attr.evolve( content_metadata2, discovery_date=content_metadata2.discovery_date, fetcher=attr.evolve(fetcher2, metadata=None), ) swh_storage.object_metadata_add([content_metadata, new_content_metadata2]) result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1 ) assert result["next_page_token"] is not None assert result["results"] == [content_metadata] result = swh_storage.object_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1, page_token=result["next_page_token"], ) assert result["next_page_token"] is None assert result["results"] == [new_content_metadata2] def test_content_metadata_get__invalid_id(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] content_metadata, content_metadata2 = sample_data_model["content_metadata"][:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([content_metadata, content_metadata2]) with pytest.raises(StorageArgumentException, match="SWHID"): swh_storage.object_metadata_get( MetadataTargetType.CONTENT, origin.url, authority ) def test_origin_metadata_add(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority ) assert result["next_page_token"] is None assert list(sorted(result["results"], key=lambda x: x.discovery_date)) == [ origin_metadata, origin_metadata2, ] def test_origin_metadata_add_duplicate(self, swh_storage, sample_data_model): """Duplicates should be silently updated.""" origin = sample_data_model["origin"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} new_origin_metadata2 = attr.evolve( origin_metadata2, format="new-format", metadata=b"new-metadata", ) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([origin_metadata, origin_metadata2]) swh_storage.object_metadata_add([new_origin_metadata2]) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority ) assert result["next_page_token"] is None # which of the two behavior happens is backend-specific. expected_results1 = (origin_metadata, new_origin_metadata2) expected_results2 = (origin_metadata, origin_metadata2) assert tuple(sorted(result["results"], key=lambda x: x.discovery_date,)) in ( expected_results1, # cassandra expected_results2, # postgresql ) def test_origin_metadata_get(self, swh_storage, sample_data_model): origin, origin2 = sample_data_model["origin"][:2] fetcher, fetcher2 = sample_data_model["fetcher"][:2] authority, authority2 = sample_data_model["authority"][:2] origin1_metadata1, origin1_metadata2, origin1_metadata3 = sample_data_model[ "origin_metadata" ][:3] assert swh_storage.origin_add([origin, origin2]) == {"origin:add": 2} origin2_metadata = attr.evolve(origin1_metadata2, id=origin2.url) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.object_metadata_add( [origin1_metadata1, origin1_metadata2, origin1_metadata3, origin2_metadata] ) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority ) assert result["next_page_token"] is None assert [origin1_metadata1, origin1_metadata2] == list( sorted(result["results"], key=lambda x: x.discovery_date,) ) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority2 ) assert result["next_page_token"] is None assert [origin1_metadata3] == list( sorted(result["results"], key=lambda x: x.discovery_date,) ) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin2.url, authority ) assert result["next_page_token"] is None assert [origin2_metadata] == list(result["results"],) def test_origin_metadata_get_after(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, after=origin_metadata.discovery_date - timedelta(seconds=1), ) assert result["next_page_token"] is None assert list(sorted(result["results"], key=lambda x: x.discovery_date,)) == [ origin_metadata, origin_metadata2, ] result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, after=origin_metadata.discovery_date, ) assert result["next_page_token"] is None assert result["results"] == [origin_metadata2] result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, after=origin_metadata2.discovery_date, ) assert result["next_page_token"] is None assert result["results"] == [] def test_origin_metadata_get_paginate(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] fetcher = sample_data_model["fetcher"][0] authority = sample_data_model["authority"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([origin_metadata, origin_metadata2]) swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority ) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1 ) assert result["next_page_token"] is not None assert result["results"] == [origin_metadata] result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1, page_token=result["next_page_token"], ) assert result["next_page_token"] is None assert result["results"] == [origin_metadata2] def test_origin_metadata_get_paginate_same_date( self, swh_storage, sample_data_model ): origin = sample_data_model["origin"][0] fetcher1, fetcher2 = sample_data_model["fetcher"][:2] authority = sample_data_model["authority"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_origin_metadata2 = attr.evolve( origin_metadata2, discovery_date=origin_metadata2.discovery_date, fetcher=attr.evolve(fetcher2, metadata=None), ) swh_storage.object_metadata_add([origin_metadata, new_origin_metadata2]) result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1 ) assert result["next_page_token"] is not None assert result["results"] == [origin_metadata] result = swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1, page_token=result["next_page_token"], ) assert result["next_page_token"] is None assert result["results"] == [new_origin_metadata2] def test_origin_metadata_add_missing_authority( self, swh_storage, sample_data_model ): origin = sample_data_model["origin"][0] fetcher = sample_data_model["fetcher"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) with pytest.raises(StorageArgumentException, match="authority"): swh_storage.object_metadata_add([origin_metadata, origin_metadata2]) def test_origin_metadata_add_missing_fetcher(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] authority = sample_data_model["authority"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_authority_add([authority]) with pytest.raises(StorageArgumentException, match="fetcher"): swh_storage.object_metadata_add([origin_metadata, origin_metadata2]) def test_origin_metadata_get__invalid_id_type(self, swh_storage, sample_data_model): origin = sample_data_model["origin"][0] authority = sample_data_model["authority"][0] fetcher = sample_data_model["fetcher"][0] origin_metadata, origin_metadata2 = sample_data_model["origin_metadata"][:2] content_metadata = sample_data_model["content_metadata"][0] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.object_metadata_add([origin_metadata, origin_metadata2]) with pytest.raises(StorageArgumentException, match="SWHID"): swh_storage.object_metadata_get( MetadataTargetType.ORIGIN, content_metadata.id, authority, ) class TestStorageGeneratedData: def test_generate_content_get(self, swh_storage, swh_contents): contents_with_data = [c.to_dict() 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.to_dict() 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.to_dict() 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.to_dict() 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.to_dict() 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.to_dict() 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 = [ Origin(url="https://github.com/user1/repo1"), Origin(url="https://github.com/user2/repo1"), Origin(url="https://github.com/user3/repo1"), Origin(url="https://gitlab.com/user1/repo1"), Origin(url="https://gitlab.com/user2/repo1"), Origin(url="https://forge.softwareheritage.org/source/repo1"), ] def test_origin_count(self, swh_storage): swh_storage.origin_add(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(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(self.ORIGINS) origin_url = "https://github.com/user1/repo1" visit = OriginVisit(origin=origin_url, date=now(), type="git",) swh_storage.origin_visit_add([visit]) 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, sample_data_model ): snapshot = sample_data_model["snapshot"][0] swh_storage.origin_add(self.ORIGINS) swh_storage.snapshot_add([snapshot]) origin_url = "https://github.com/user1/repo1" visit = OriginVisit(origin=origin_url, date=now(), type="git",) visit = swh_storage.origin_visit_add([visit])[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=visit.visit, date=now(), status="ongoing", snapshot=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(split_content=True), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: if obj.object_type == "origin_visit": swh_storage.origin_add([Origin(url=obj.origin)]) visit = OriginVisit(origin=obj.origin, date=obj.date, type=obj.type,) swh_storage.origin_visit_add([visit]) else: method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] swh_storage.objstorage.content_add = Mock( side_effect=Exception("mocked broken objstorage") ) with pytest.raises(Exception, match="mocked broken"): swh_storage.content_add([content]) missing = list(swh_storage.content_missing([content.hashes()])) assert missing == [content.sha1] @pytest.mark.db class TestStorageRaceConditions: @pytest.mark.xfail def test_content_add_race(self, swh_storage, sample_data_model): content = sample_data_model["content"][0] results = queue.Queue() def thread(): try: with db_transaction(swh_storage) as (db, cur): ret = swh_storage.content_add([content], 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, sample_data_model): content, content2 = sample_data_model["content"][:2] 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""" ) swh_storage.content_add([content]) cont = content.to_dict() 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, sample_data_model): content = sample_data_model["content"][0] actual_result = swh_storage.content_add([content]) assert actual_result == { "content:add": 1, "content:add:bytes": content.length, } if hasattr(swh_storage, "objstorage"): assert content.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", (content.sha1,), ) datum = cur.fetchone() assert datum == ( content.sha1, content.sha1_git, content.sha256, content.length, "visible", ) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 assert contents[0] == attr.evolve(content, data=None) def test_content_add_metadata_db(self, swh_storage, sample_data_model): content = attr.evolve(sample_data_model["content"][0], data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([content]) assert actual_result == { "content:add": 1, } if hasattr(swh_storage, "objstorage"): assert content.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", (content.sha1,), ) datum = cur.fetchone() assert datum == ( content.sha1, content.sha1_git, content.sha256, content.length, "visible", ) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 assert contents[0] == content def test_skipped_content_add_db(self, swh_storage, sample_data_model): content, cont2 = sample_data_model["skipped_content"][:2] content2 = attr.evolve(cont2, blake2s256=None) actual_result = swh_storage.skipped_content_add([content, content, content2]) 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] == ( content.sha1, content.sha1_git, content.sha256, content.blake2s256, content.length, "absent", "Content too long", ) assert dbdata[1] == ( content2.sha1, content2.sha1_git, content2.sha256, content2.blake2s256, content2.length, "absent", "Content too long", ) def test_clear_buffers(self, swh_storage): """Calling clear buffers on real storage does nothing """ assert swh_storage.clear_buffers() is None def test_flush(self, swh_storage): """Calling clear buffers on real storage does nothing """ assert swh_storage.flush() == {} diff --git a/swh/storage/validate.py b/swh/storage/validate.py deleted file mode 100644 index 65512eb9..00000000 --- a/swh/storage/validate.py +++ /dev/null @@ -1,148 +0,0 @@ -# Copyright (C) 2020 The Software Heritage developers -# See the AUTHORS file at the top-level directory of this distribution -# License: GNU General Public License version 3, or any later version -# See top-level LICENSE file for more information - -import contextlib -from typing import Dict, Iterable, Iterator, Optional, Tuple, Type, TypeVar, Union - -from swh.model.model import ( - SkippedContent, - Content, - Directory, - Revision, - Release, - Snapshot, - OriginVisit, - Origin, -) - -from . import get_storage -from .exc import StorageArgumentException - - -VALIDATION_EXCEPTIONS = [ - KeyError, - TypeError, - ValueError, -] - - -@contextlib.contextmanager -def convert_validation_exceptions(): - """Catches validation errors arguments, and re-raises a - StorageArgumentException.""" - try: - yield - except tuple(VALIDATION_EXCEPTIONS) as e: - raise StorageArgumentException(str(e)) - - -ModelObject = TypeVar( - "ModelObject", - Content, - SkippedContent, - Directory, - Revision, - Release, - Snapshot, - OriginVisit, - Origin, -) - - -def dict_converter( - model: Type[ModelObject], obj: Union[Dict, ModelObject] -) -> ModelObject: - """Convert dicts to model objects; Passes through model objects as well.""" - if isinstance(obj, dict): - with convert_validation_exceptions(): - return model.from_dict(obj) - else: - return obj - - -class ValidatingProxyStorage: - """Storage implementation converts dictionaries to swh-model objects - before calling its backend, and back to dicts before returning results - - For test purposes. - """ - - def __init__(self, storage): - self.storage = get_storage(**storage) - - def __getattr__(self, key): - if key == "storage": - raise AttributeError(key) - return getattr(self.storage, key) - - def content_add(self, content: Iterable[Union[Content, Dict]]) -> Dict: - return self.storage.content_add([dict_converter(Content, c) for c in content]) - - def content_add_metadata(self, content: Iterable[Union[Content, Dict]]) -> Dict: - return self.storage.content_add_metadata( - [dict_converter(Content, c) for c in content] - ) - - def skipped_content_add( - self, content: Iterable[Union[SkippedContent, Dict]] - ) -> Dict: - return self.storage.skipped_content_add( - [dict_converter(SkippedContent, c) for c in content] - ) - - def directory_add(self, directories: Iterable[Union[Directory, Dict]]) -> Dict: - return self.storage.directory_add( - [dict_converter(Directory, d) for d in directories] - ) - - def revision_add(self, revisions: Iterable[Union[Revision, Dict]]) -> Dict: - return self.storage.revision_add( - [dict_converter(Revision, r) for r in revisions] - ) - - def revision_get(self, revisions: Iterable[bytes]) -> Iterator[Optional[Dict]]: - rev_dicts = self.storage.revision_get(revisions) - with convert_validation_exceptions(): - for rev_dict in rev_dicts: - if rev_dict is None: - yield None - else: - yield Revision.from_dict(rev_dict).to_dict() - - def revision_log( - self, revisions: Iterable[bytes], limit: Optional[int] = None - ) -> Iterator[Dict]: - for rev_dict in self.storage.revision_log(revisions, limit): - with convert_validation_exceptions(): - rev_obj = Revision.from_dict(rev_dict) - yield rev_obj.to_dict() - - def revision_shortlog( - self, revisions: Iterable[bytes], limit: Optional[int] = None - ) -> Iterator[Tuple[bytes, Tuple]]: - for rev, parents in self.storage.revision_shortlog(revisions, limit): - yield (rev, tuple(parents)) - - def release_add(self, releases: Iterable[Union[Dict, Release]]) -> Dict: - return self.storage.release_add( - [dict_converter(Release, release) for release in releases] - ) - - def snapshot_add(self, snapshots: Iterable[Union[Dict, Snapshot]]) -> Dict: - return self.storage.snapshot_add( - [dict_converter(Snapshot, snapshot) for snapshot in snapshots] - ) - - def origin_visit_add(self, visits: Iterable[OriginVisit]) -> Iterable[OriginVisit]: - return self.storage.origin_visit_add(visits) - - def origin_add(self, origins: Iterable[Union[Dict, Origin]]) -> Dict[str, int]: - return self.storage.origin_add([dict_converter(Origin, o) for o in origins]) - - def clear_buffers(self, object_types: Optional[Iterable[str]] = None) -> None: - return self.storage.clear_buffers(object_types) - - def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: - return self.storage.flush(object_types)