diff --git a/requirements-swh.txt b/requirements-swh.txt index 1c2878ea..fea0dfb2 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,4 +1,4 @@ swh.core[db,http] >= 0.14.0 swh.counters >= v0.8.0 -swh.model >= 2.1.0 +swh.model >= 4.0.0 swh.objstorage >= 0.2.2 diff --git a/sql/upgrades/179.sql b/sql/upgrades/179.sql new file mode 100644 index 00000000..e08dbe26 --- /dev/null +++ b/sql/upgrades/179.sql @@ -0,0 +1,159 @@ +-- SWH DB schema upgrade +-- from_version: 178 +-- to_version: 179 +-- description: add {,committer_}date_offset_bytes to rev/rel + raw_manifest to dir/rev/rel, part 1 + +insert into dbversion(version, release, description) + values(179, now(), 'Work In Progress'); + +-- step 1: add columns, update functions + +alter table release + add column date_offset_bytes bytea, + add column raw_manifest bytea; +comment on column release.date_offset_bytes is 'Raw git representation of the timezone, as an offset from UTC. It should follow this format: ``+HHMM`` or ``-HHMM``'; +comment on column release.raw_manifest is 'git manifest of the object, if it cannot be represented using only the other fields'; + + +alter table revision + add column date_offset_bytes bytea, + add column committer_date_offset_bytes bytea, + add column raw_manifest bytea; +comment on column revision.date_offset_bytes is 'Raw git representation of the timezone, as an offset from UTC. It should follow this format: ``+HHMM`` or ``-HHMM``'; +comment on column revision.committer_date_offset_bytes is 'Raw git representation of the timezone, as an offset from UTC. It should follow this format: ``+HHMM`` or ``-HHMM``'; +comment on column revision.raw_manifest is 'git manifest of the object, if it cannot be represented using only the other fields'; + +drop function swh_revision_log; +drop function swh_revision_list_by_object_id; +drop function swh_revision_add; +drop type revision_entry; +create type revision_entry as +( + id sha1_git, + date timestamptz, + date_offset smallint, + date_neg_utc_offset boolean, + date_offset_bytes bytea, + committer_date timestamptz, + committer_date_offset smallint, + committer_date_neg_utc_offset boolean, + committer_date_offset_bytes bytea, + type revision_type, + directory sha1_git, + message bytea, + author_id bigint, + author_fullname bytea, + author_name bytea, + author_email bytea, + committer_id bigint, + committer_fullname bytea, + committer_name bytea, + committer_email bytea, + metadata jsonb, + synthetic boolean, + parents bytea[], + object_id bigint, + extra_headers bytea[][], + raw_manifest bytea +); + +alter table directory + add column raw_manifest bytea; +comment on column directory.raw_manifest is 'git manifest of the object, if it cannot be represented using only the other fields'; + +create or replace function swh_directory_add() + returns void + language plpgsql +as $$ +begin + perform swh_directory_entry_add('file'); + perform swh_directory_entry_add('dir'); + perform swh_directory_entry_add('rev'); + + insert into directory (id, dir_entries, file_entries, rev_entries, raw_manifest) + select id, dir_entries, file_entries, rev_entries, raw_manifest from tmp_directory t + where not exists ( + select 1 from directory d + where d.id = t.id); + + return; +end +$$; + +create or replace function swh_revision_log(root_revisions bytea[], num_revs bigint default NULL) + returns setof revision_entry + language sql + stable +as $$ + select t.id, r.date, r.date_offset, r.date_neg_utc_offset, r.date_offset_bytes, + r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.committer_date_offset_bytes, + r.type, r.directory, r.message, + a.id, a.fullname, a.name, a.email, + c.id, c.fullname, c.name, c.email, + r.metadata, r.synthetic, t.parents, r.object_id, r.extra_headers, + r.raw_manifest + from swh_revision_list(root_revisions, num_revs) as t + left join revision r on t.id = r.id + left join person a on a.id = r.author + left join person c on c.id = r.committer; +$$; + +create or replace function swh_revision_list_by_object_id( + min_excl bigint, + max_incl bigint +) + returns setof revision_entry + language sql + stable +as $$ + with revs as ( + select * from revision + where object_id > min_excl and object_id <= max_incl + ) + select r.id, r.date, r.date_offset, r.date_neg_utc_offset, r.date_offset_bytes, + r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.committer_date_offset_bytes, + r.type, r.directory, r.message, + a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic, + array(select rh.parent_id::bytea from revision_history rh where rh.id = r.id order by rh.parent_rank) + as parents, r.object_id, r.extra_headers, r.raw_manifest + from revs r + left join person a on a.id = r.author + left join person c on c.id = r.committer + order by r.object_id; +$$; + +create or replace function swh_revision_add() + returns void + language plpgsql +as $$ +begin + perform swh_person_add_from_revision(); + + insert into revision (id, date, date_offset, date_neg_utc_offset, date_offset_bytes, committer_date, committer_date_offset, committer_date_neg_utc_offset, committer_date_offset_bytes, type, directory, message, author, committer, metadata, synthetic, extra_headers, raw_manifest) + select t.id, t.date, t.date_offset, t.date_neg_utc_offset, t.date_offset_bytes, t.committer_date, t.committer_date_offset, t.committer_date_neg_utc_offset, t.committer_date_offset_bytes, t.type, t.directory, t.message, a.id, c.id, t.metadata, t.synthetic, t.extra_headers, t.raw_manifest + from tmp_revision t + left join person a on a.fullname = t.author_fullname + left join person c on c.fullname = t.committer_fullname; + return; +end +$$; + +create or replace function swh_release_add() + returns void + language plpgsql +as $$ +begin + perform swh_person_add_from_release(); + + insert into release (id, target, target_type, date, date_offset, date_neg_utc_offset, date_offset_bytes, name, comment, author, synthetic, raw_manifest) + select distinct t.id, t.target, t.target_type, t.date, t.date_offset, t.date_neg_utc_offset, t.date_offset_bytes, t.name, t.comment, a.id, t.synthetic, t.raw_manifest + from tmp_release t + left join person a on a.fullname = t.author_fullname + where not exists (select 1 from release where t.id = release.id); + return; +end +$$; + +-- step 2: upgrade python code to start writing to them + +-- data migrations in 180.sql diff --git a/sql/upgrades/180.sql b/sql/upgrades/180.sql new file mode 100644 index 00000000..f1a310de --- /dev/null +++ b/sql/upgrades/180.sql @@ -0,0 +1,88 @@ +-- SWH DB schema upgrade +-- from_version: 177 +-- to_version: 180 +-- description: add {,committer_}date_offset_bytes to rev/rel + raw_manifest to dir/rev/rel, part 2 + +insert into dbversion(version, release, description) + values(180, now(), 'Work In Progress'); + +-- copied from 60-indexes.sql +select swh_get_dbflavor() != 'read_replica' as dbflavor_does_deduplication \gset + +-- step 3: fill the offsets + +create or replace function _format_offset(offset_ smallint, neg_utc_offset bool) + returns bytea + language plpgsql +as $$ + begin + return convert_to( + -- sign + case when offset_ < 0 or neg_utc_offset then '-' else '+' end + -- hours (unfortunately we can't use lpad because it truncates) + || case when abs(offset_) >= 600 then + cast(abs(offset_) / 60 as text) + else + '0' || cast(abs(offset_) / 60 as text) + end + -- minutes + || lpad(cast(mod(abs(offset_), 60) as text), 2, '0'), + 'utf8' + ); + end +$$; + +-- make sure it's correct +do $$ begin + assert (select _format_offset(NULL::smallint, NULL::bool)) is not distinct from NULL; + assert (select _format_offset(0::smallint, false)) = '+0000'::bytea; + assert (select _format_offset(0::smallint, true)) = '-0000'::bytea; + assert (select _format_offset(1::smallint, false)) = '+0001'::bytea; + assert (select _format_offset(-1::smallint, false)) = '-0001'::bytea; + assert (select _format_offset(120::smallint, false)) = '+0200'::bytea; + assert (select _format_offset(-120::smallint, false)) = '-0200'::bytea; + assert (select _format_offset(6000::smallint, false)) = '+10000'::bytea; + assert (select _format_offset(-6000::smallint, false)) = '-10000'::bytea; +end$$; + +update release + set date_offset_bytes=_format_offset(date_offset, date_neg_utc_offset) + where date is not null and date_offset_bytes is null; + +update revision + set date_offset_bytes=_format_offset(date_offset, date_neg_utc_offset), + committer_date_offset_bytes=_format_offset(committer_date_offset, committer_date_neg_utc_offset) + where (date is not null and date_offset_bytes is null) + or (committer_date is not null and committer_date_offset_bytes is null); + + +-- step 4: add integrity constraints + +\if :dbflavor_does_deduplication + + -- add new constraint on release dates + alter table release + add constraint release_date_offset_not_null + check (date is null or date_offset_bytes is not null) + not valid; + alter table release + validate constraint release_date_offset_not_null; + + alter table revision + add constraint revision_date_offset_not_null + check (date is null or date_offset_bytes is not null) + not valid; + + alter table revision + add constraint revision_committer_date_offset_not_null + check (committer_date is null or committer_date_offset_bytes is not null) + not valid; + + alter table revision + validate constraint revision_date_offset_not_null; + alter table revision + validate constraint revision_committer_date_offset_not_null; +\endif + +-- step 5: remove the old columns (date_offset and date_neg_utc_offset): in a future migration... + diff --git a/swh/storage/backfill.py b/swh/storage/backfill.py index a97a11fe..1ea0f4dd 100644 --- a/swh/storage/backfill.py +++ b/swh/storage/backfill.py @@ -1,658 +1,663 @@ # Copyright (C) 2017-2021 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 """Storage backfiller. The backfiller goal is to produce back part or all of the objects from a storage to the journal topics Current implementation consists in the JournalBackfiller class. It simply reads the objects from the storage and sends every object identifier back to the journal. """ import logging from typing import Any, Callable, Dict, Optional from swh.core.db import BaseDb from swh.model.model import ( BaseModel, Directory, DirectoryEntry, ExtID, RawExtrinsicMetadata, Release, Revision, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import ExtendedObjectType from swh.storage.postgresql.converters import ( db_to_extid, db_to_raw_extrinsic_metadata, db_to_release, db_to_revision, ) from swh.storage.replay import OBJECT_CONVERTERS from swh.storage.writer import JournalWriter logger = logging.getLogger(__name__) PARTITION_KEY = { "content": "sha1", "skipped_content": "sha1", "directory": "id", "extid": "target", "metadata_authority": "type, url", "metadata_fetcher": "name, version", "raw_extrinsic_metadata": "target", "revision": "revision.id", "release": "release.id", "snapshot": "id", "origin": "id", "origin_visit": "origin_visit.origin", "origin_visit_status": "origin_visit_status.origin", } COLUMNS = { "content": [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "status", "ctime", ], "skipped_content": [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "ctime", "status", "reason", ], - "directory": ["id", "dir_entries", "file_entries", "rev_entries"], + "directory": ["id", "dir_entries", "file_entries", "rev_entries", "raw_manifest"], "extid": ["extid_type", "extid", "extid_version", "target_type", "target"], "metadata_authority": ["type", "url"], "metadata_fetcher": ["name", "version"], "origin": ["url"], "origin_visit": ["visit", "type", ("origin.url", "origin"), "date",], "origin_visit_status": [ ("origin_visit_status.visit", "visit"), ("origin.url", "origin"), ("origin_visit_status.date", "date"), "type", "snapshot", "status", "metadata", ], "raw_extrinsic_metadata": [ "raw_extrinsic_metadata.type", "raw_extrinsic_metadata.target", "metadata_authority.type", "metadata_authority.url", "metadata_fetcher.name", "metadata_fetcher.version", "discovery_date", "format", "raw_extrinsic_metadata.metadata", "origin", "visit", "snapshot", "release", "revision", "path", "directory", ], "revision": [ ("revision.id", "id"), "date", "date_offset", "date_neg_utc_offset", + "date_offset_bytes", "committer_date", "committer_date_offset", "committer_date_neg_utc_offset", + "committer_date_offset_bytes", "type", "directory", "message", "synthetic", "metadata", "extra_headers", ( "array(select parent_id::bytea from revision_history rh " "where rh.id = revision.id order by rh.parent_rank asc)", "parents", ), + "raw_manifest", ("a.id", "author_id"), ("a.name", "author_name"), ("a.email", "author_email"), ("a.fullname", "author_fullname"), ("c.id", "committer_id"), ("c.name", "committer_name"), ("c.email", "committer_email"), ("c.fullname", "committer_fullname"), ], "release": [ ("release.id", "id"), "date", "date_offset", "date_neg_utc_offset", + "date_offset_bytes", "comment", ("release.name", "name"), "synthetic", "target", "target_type", ("a.id", "author_id"), ("a.name", "author_name"), ("a.email", "author_email"), ("a.fullname", "author_fullname"), + "raw_manifest", ], "snapshot": ["id", "object_id"], } JOINS = { "release": ["person a on release.author=a.id"], "revision": [ "person a on revision.author=a.id", "person c on revision.committer=c.id", ], "origin_visit": ["origin on origin_visit.origin=origin.id"], "origin_visit_status": ["origin on origin_visit_status.origin=origin.id",], "raw_extrinsic_metadata": [ "metadata_authority on " "raw_extrinsic_metadata.authority_id=metadata_authority.id", "metadata_fetcher on raw_extrinsic_metadata.fetcher_id=metadata_fetcher.id", ], } EXTRA_WHERE = { # hack to force the right index usage on table extid "extid": "target_type in ('revision', 'release', 'content', 'directory')" } def directory_converter(db: BaseDb, directory_d: Dict[str, Any]) -> Directory: """Convert directory from the flat representation to swh model compatible objects. """ columns = ["target", "name", "perms"] query_template = """ select %(columns)s from directory_entry_%(type)s where id in %%s """ types = ["file", "dir", "rev"] entries = [] with db.cursor() as cur: for type in types: ids = directory_d.pop("%s_entries" % type) if not ids: continue query = query_template % { "columns": ",".join(columns), "type": type, } cur.execute(query, (tuple(ids),)) for row in cur: entry_d = dict(zip(columns, row)) entry = DirectoryEntry( name=entry_d["name"], type=type, target=entry_d["target"], perms=entry_d["perms"], ) entries.append(entry) return Directory(id=directory_d["id"], entries=tuple(entries),) def raw_extrinsic_metadata_converter( db: BaseDb, metadata: Dict[str, Any] ) -> RawExtrinsicMetadata: """Convert a raw extrinsic metadata from the flat representation to swh model compatible objects. """ return db_to_raw_extrinsic_metadata(metadata) def extid_converter(db: BaseDb, extid: Dict[str, Any]) -> ExtID: """Convert an extid from the flat representation to swh model compatible objects. """ return db_to_extid(extid) def revision_converter(db: BaseDb, revision_d: Dict[str, Any]) -> Revision: """Convert revision from the flat representation to swh model compatible objects. """ revision = db_to_revision(revision_d) assert revision is not None, revision_d["id"] return revision def release_converter(db: BaseDb, release_d: Dict[str, Any]) -> Release: """Convert release from the flat representation to swh model compatible objects. """ release = db_to_release(release_d) assert release is not None, release_d["id"] return release def snapshot_converter(db: BaseDb, snapshot_d: Dict[str, Any]) -> Snapshot: """Convert snapshot from the flat representation to swh model compatible objects. """ columns = ["name", "target", "target_type"] query = """ select %s from snapshot_branches sbs inner join snapshot_branch sb on sb.object_id=sbs.branch_id where sbs.snapshot_id=%%s """ % ", ".join( columns ) with db.cursor() as cur: cur.execute(query, (snapshot_d["object_id"],)) branches = {} for name, *row in cur: branch_d = dict(zip(columns[1:], row)) if branch_d["target"] is not None and branch_d["target_type"] is not None: branch: Optional[SnapshotBranch] = SnapshotBranch( target=branch_d["target"], target_type=TargetType(branch_d["target_type"]), ) else: branch = None branches[name] = branch return Snapshot(id=snapshot_d["id"], branches=branches,) CONVERTERS: Dict[str, Callable[[BaseDb, Dict[str, Any]], BaseModel]] = { "directory": directory_converter, "extid": extid_converter, "raw_extrinsic_metadata": raw_extrinsic_metadata_converter, "revision": revision_converter, "release": release_converter, "snapshot": snapshot_converter, } def object_to_offset(object_id, numbits): """Compute the index of the range containing object id, when dividing space into 2^numbits. Args: object_id (str): The hex representation of object_id numbits (int): Number of bits in which we divide input space Returns: The index of the range containing object id """ q, r = divmod(numbits, 8) length = q + (r != 0) shift_bits = 8 - r if r else 0 truncated_id = object_id[: length * 2] if len(truncated_id) < length * 2: truncated_id += "0" * (length * 2 - len(truncated_id)) truncated_id_bytes = bytes.fromhex(truncated_id) return int.from_bytes(truncated_id_bytes, byteorder="big") >> shift_bits def byte_ranges(numbits, start_object=None, end_object=None): """Generate start/end pairs of bytes spanning numbits bits and constrained by optional start_object and end_object. Args: numbits (int): Number of bits in which we divide input space start_object (str): Hex object id contained in the first range returned end_object (str): Hex object id contained in the last range returned Yields: 2^numbits pairs of bytes """ q, r = divmod(numbits, 8) length = q + (r != 0) shift_bits = 8 - r if r else 0 def to_bytes(i): return int.to_bytes(i << shift_bits, length=length, byteorder="big") start_offset = 0 end_offset = 1 << numbits if start_object is not None: start_offset = object_to_offset(start_object, numbits) if end_object is not None: end_offset = object_to_offset(end_object, numbits) + 1 for start in range(start_offset, end_offset): end = start + 1 if start == 0: yield None, to_bytes(end) elif end == 1 << numbits: yield to_bytes(start), None else: yield to_bytes(start), to_bytes(end) def raw_extrinsic_metadata_target_ranges(start_object=None, end_object=None): """Generate ranges of values for the `target` attribute of `raw_extrinsic_metadata` objects. This generates one range for all values before the first SWHID (which would correspond to raw origin URLs), then a number of hex-based ranges for each known type of SWHID (2**12 ranges for directories, 2**8 ranges for all other types). Finally, it generates one extra range for values above all possible SWHIDs. """ if start_object is None: start_object = "" swhid_target_types = sorted(type.value for type in ExtendedObjectType) first_swhid = f"swh:1:{swhid_target_types[0]}:" # Generate a range for url targets, if the starting object is before SWHIDs if start_object < first_swhid: yield start_object, ( first_swhid if end_object is None or end_object >= first_swhid else end_object ) if end_object is not None and end_object <= first_swhid: return # Prime the following loop, which uses the upper bound of the previous range # as lower bound, to account for potential targets between two valid types # of SWHIDs (even though they would eventually be rejected by the # RawExtrinsicMetadata parser, they /might/ exist...) end_swhid = first_swhid # Generate ranges for swhid targets for target_type in swhid_target_types: finished = False base_swhid = f"swh:1:{target_type}:" last_swhid = base_swhid + ("f" * 40) if start_object > last_swhid: continue # Generate 2**8 or 2**12 ranges for _, end in byte_ranges(12 if target_type == "dir" else 8): # Reuse previous uppper bound start_swhid = end_swhid # Use last_swhid for this object type if on the last byte range end_swhid = (base_swhid + end.hex()) if end is not None else last_swhid # Ignore out of bounds ranges if start_object >= end_swhid: continue # Potentially clamp start of range to the first object requested start_swhid = max(start_swhid, start_object) # Handle ending the loop early if the last requested object id is in # the current range if end_object is not None and end_swhid >= end_object: end_swhid = end_object finished = True yield start_swhid, end_swhid if finished: return # Generate one final range for potential raw origin URLs after the last # valid SWHID start_swhid = max(start_object, end_swhid) yield start_swhid, end_object def integer_ranges(start, end, block_size=1000): for start in range(start, end, block_size): if start == 0: yield None, block_size elif start + block_size > end: yield start, end else: yield start, start + block_size RANGE_GENERATORS = { "content": lambda start, end: byte_ranges(24, start, end), "skipped_content": lambda start, end: [(None, None)], "directory": lambda start, end: byte_ranges(24, start, end), "extid": lambda start, end: byte_ranges(24, start, end), "revision": lambda start, end: byte_ranges(24, start, end), "release": lambda start, end: byte_ranges(16, start, end), "raw_extrinsic_metadata": raw_extrinsic_metadata_target_ranges, "snapshot": lambda start, end: byte_ranges(16, start, end), "origin": integer_ranges, "origin_visit": integer_ranges, "origin_visit_status": integer_ranges, } def compute_query(obj_type, start, end): columns = COLUMNS.get(obj_type) join_specs = JOINS.get(obj_type, []) join_clause = "\n".join("left join %s" % clause for clause in join_specs) additional_where = EXTRA_WHERE.get(obj_type) where = [] where_args = [] if start: where.append("%(keys)s >= %%s") where_args.append(start) if end: where.append("%(keys)s < %%s") where_args.append(end) if additional_where: where.append(additional_where) where_clause = "" if where: where_clause = ("where " + " and ".join(where)) % { "keys": "(%s)" % PARTITION_KEY[obj_type] } column_specs = [] column_aliases = [] for column in columns: if isinstance(column, str): column_specs.append(column) column_aliases.append(column) else: column_specs.append("%s as %s" % column) column_aliases.append(column[1]) query = """ select %(columns)s from %(table)s %(join)s %(where)s """ % { "columns": ",".join(column_specs), "table": obj_type, "join": join_clause, "where": where_clause, } return query, where_args, column_aliases def fetch(db, obj_type, start, end): """Fetch all obj_type's identifiers from db. This opens one connection, stream objects and when done, close the connection. Args: db (BaseDb): Db connection object obj_type (str): Object type start (Union[bytes|Tuple]): Range start identifier end (Union[bytes|Tuple]): Range end identifier Raises: ValueError if obj_type is not supported Yields: Objects in the given range """ query, where_args, column_aliases = compute_query(obj_type, start, end) converter = CONVERTERS.get(obj_type) with db.cursor() as cursor: logger.debug("Fetching data for table %s", obj_type) logger.debug("query: %s %s", query, where_args) cursor.execute(query, where_args) for row in cursor: record = dict(zip(column_aliases, row)) if converter: record = converter(db, record) else: record = OBJECT_CONVERTERS[obj_type](record) logger.debug("record: %s", record) yield record def _format_range_bound(bound): if isinstance(bound, bytes): return bound.hex() else: return str(bound) MANDATORY_KEYS = ["storage", "journal_writer"] class JournalBackfiller: """Class in charge of reading the storage's objects and sends those back to the journal's topics. This is designed to be run periodically. """ def __init__(self, config=None): self.config = config self.check_config(config) def check_config(self, config): missing_keys = [] for key in MANDATORY_KEYS: if not config.get(key): missing_keys.append(key) if missing_keys: raise ValueError( "Configuration error: The following keys must be" " provided: %s" % (",".join(missing_keys),) ) if "cls" not in config["storage"] or config["storage"]["cls"] not in ( "local", "postgresql", ): raise ValueError( "swh storage backfiller must be configured to use a local" " (PostgreSQL) storage" ) def parse_arguments(self, object_type, start_object, end_object): """Parse arguments Raises: ValueError for unsupported object type ValueError if object ids are not parseable Returns: Parsed start and end object ids """ if object_type not in COLUMNS: raise ValueError( "Object type %s is not supported. " "The only possible values are %s" % (object_type, ", ".join(sorted(COLUMNS.keys()))) ) if object_type in ["origin", "origin_visit", "origin_visit_status"]: if start_object: start_object = int(start_object) else: start_object = 0 if end_object: end_object = int(end_object) else: end_object = 100 * 1000 * 1000 # hard-coded limit return start_object, end_object def run(self, object_type, start_object, end_object, dry_run=False): """Reads storage's subscribed object types and send them to the journal's reading topic. """ start_object, end_object = self.parse_arguments( object_type, start_object, end_object ) db = BaseDb.connect(self.config["storage"]["db"]) writer = JournalWriter({"cls": "kafka", **self.config["journal_writer"]}) assert writer.journal is not None for range_start, range_end in RANGE_GENERATORS[object_type]( start_object, end_object ): logger.info( "Processing %s range %s to %s", object_type, _format_range_bound(range_start), _format_range_bound(range_end), ) objects = fetch(db, object_type, start=range_start, end=range_end) if not dry_run: writer.write_additions(object_type, objects) else: # only consume the objects iterator to check for any potential # decoding/encoding errors for obj in objects: pass if __name__ == "__main__": print('Please use the "swh-journal backfiller run" command') diff --git a/swh/storage/cassandra/model.py b/swh/storage/cassandra/model.py index 4fa4a2c0..54cbd303 100644 --- a/swh/storage/cassandra/model.py +++ b/swh/storage/cassandra/model.py @@ -1,334 +1,337 @@ # 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 """Classes representing tables in the Cassandra database. They are very close to classes found in swh.model.model, but most of them are subtly different: * Large objects are split into other classes (eg. RevisionRow has no 'parents' field, because parents are stored in a different table, represented by RevisionParentRow) * They have a "cols" field, which returns the list of column names of the table * They only use types that map directly to Cassandra's schema (ie. no enums) Therefore, this model doesn't reuse swh.model.model, except for types that can be mapped to UDTs (Person and TimestampWithTimezone). """ import dataclasses import datetime from typing import Any, ClassVar, Dict, List, Optional, Tuple, Type, TypeVar from swh.model.model import Person, TimestampWithTimezone MAGIC_NULL_PK = b"" """ NULLs (or all-empty blobs) are not allowed in primary keys; instead we use a special value that can't possibly be a valid hash. """ T = TypeVar("T", bound="BaseRow") def content_index_table_name(algo: str, skipped_content: bool) -> str: """Given an algorithm name, returns the name of one of the 'content_by_*' and 'skipped_content_by_*' tables that serve as index for the 'content' and 'skipped_content' tables based on this algorithm's hashes. For now it is a simple substitution, but future versions may append a version number to it, if needed for schema updates.""" if skipped_content: return f"skipped_content_by_{algo}" else: return f"content_by_{algo}" class BaseRow: TABLE: ClassVar[str] PARTITION_KEY: ClassVar[Tuple[str, ...]] CLUSTERING_KEY: ClassVar[Tuple[str, ...]] = () @classmethod def from_dict(cls: Type[T], d: Dict[str, Any]) -> T: return cls(**d) # type: ignore @classmethod def cols(cls) -> List[str]: return [field.name for field in dataclasses.fields(cls)] def to_dict(self) -> Dict[str, Any]: return dataclasses.asdict(self) @dataclasses.dataclass class ContentRow(BaseRow): TABLE = "content" PARTITION_KEY: ClassVar[Tuple[str, ...]] = ("sha256",) CLUSTERING_KEY = ( "sha1", "sha1_git", "blake2s256", ) sha1: bytes sha1_git: bytes sha256: bytes blake2s256: bytes length: int ctime: datetime.datetime status: str @dataclasses.dataclass class SkippedContentRow(BaseRow): TABLE = "skipped_content" PARTITION_KEY = ("sha1", "sha1_git", "sha256", "blake2s256") sha1: Optional[bytes] sha1_git: Optional[bytes] sha256: Optional[bytes] blake2s256: Optional[bytes] length: Optional[int] ctime: Optional[datetime.datetime] status: str reason: str origin: str @classmethod def from_dict(cls, d: Dict[str, Any]) -> "SkippedContentRow": d = d.copy() for k in ("sha1", "sha1_git", "sha256", "blake2s256"): if d[k] == MAGIC_NULL_PK: d[k] = None return super().from_dict(d) @dataclasses.dataclass class DirectoryRow(BaseRow): TABLE = "directory" PARTITION_KEY = ("id",) id: bytes + raw_manifest: Optional[bytes] @dataclasses.dataclass class DirectoryEntryRow(BaseRow): TABLE = "directory_entry" PARTITION_KEY = ("directory_id",) CLUSTERING_KEY = ("name",) directory_id: bytes name: bytes target: bytes perms: int type: str @dataclasses.dataclass class RevisionRow(BaseRow): TABLE = "revision" PARTITION_KEY = ("id",) id: bytes date: Optional[TimestampWithTimezone] committer_date: Optional[TimestampWithTimezone] type: str directory: bytes message: bytes author: Person committer: Person synthetic: bool metadata: str extra_headers: dict + raw_manifest: Optional[bytes] @dataclasses.dataclass class RevisionParentRow(BaseRow): TABLE = "revision_parent" PARTITION_KEY = ("id",) CLUSTERING_KEY = ("parent_rank",) id: bytes parent_rank: int parent_id: bytes @dataclasses.dataclass class ReleaseRow(BaseRow): TABLE = "release" PARTITION_KEY = ("id",) id: bytes target_type: str target: bytes date: TimestampWithTimezone name: bytes message: bytes author: Person synthetic: bool + raw_manifest: Optional[bytes] @dataclasses.dataclass class SnapshotRow(BaseRow): TABLE = "snapshot" PARTITION_KEY = ("id",) id: bytes @dataclasses.dataclass class SnapshotBranchRow(BaseRow): TABLE = "snapshot_branch" PARTITION_KEY = ("snapshot_id",) CLUSTERING_KEY = ("name",) snapshot_id: bytes name: bytes target_type: Optional[str] target: Optional[bytes] @dataclasses.dataclass class OriginVisitRow(BaseRow): TABLE = "origin_visit" PARTITION_KEY = ("origin",) CLUSTERING_KEY = ("visit",) origin: str visit: int date: datetime.datetime type: str @dataclasses.dataclass class OriginVisitStatusRow(BaseRow): TABLE = "origin_visit_status" PARTITION_KEY = ("origin",) CLUSTERING_KEY = ("visit", "date") origin: str visit: int date: datetime.datetime type: str status: str metadata: str snapshot: bytes @classmethod def from_dict(cls: Type[T], d: Dict[str, Any]) -> T: return cls(**d) # type: ignore @dataclasses.dataclass class OriginRow(BaseRow): TABLE = "origin" PARTITION_KEY = ("sha1",) sha1: bytes url: str next_visit_id: int @dataclasses.dataclass class MetadataAuthorityRow(BaseRow): TABLE = "metadata_authority" PARTITION_KEY = ("url",) CLUSTERING_KEY = ("type",) url: str type: str @dataclasses.dataclass class MetadataFetcherRow(BaseRow): TABLE = "metadata_fetcher" PARTITION_KEY = ("name",) CLUSTERING_KEY = ("version",) name: str version: str @dataclasses.dataclass class RawExtrinsicMetadataRow(BaseRow): TABLE = "raw_extrinsic_metadata" PARTITION_KEY = ("target",) CLUSTERING_KEY = ( "authority_type", "authority_url", "discovery_date", "id", ) id: bytes type: str target: str authority_type: str authority_url: str discovery_date: datetime.datetime fetcher_name: str fetcher_version: str format: str metadata: bytes origin: Optional[str] visit: Optional[int] snapshot: Optional[str] release: Optional[str] revision: Optional[str] path: Optional[bytes] directory: Optional[str] @dataclasses.dataclass class RawExtrinsicMetadataByIdRow(BaseRow): TABLE = "raw_extrinsic_metadata_by_id" PARTITION_KEY = ("id",) CLUSTERING_KEY = () id: bytes target: str authority_type: str authority_url: str @dataclasses.dataclass class ObjectCountRow(BaseRow): TABLE = "object_count" PARTITION_KEY = ("partition_key",) CLUSTERING_KEY = ("object_type",) partition_key: int object_type: str count: int @dataclasses.dataclass class ExtIDRow(BaseRow): TABLE = "extid" PARTITION_KEY = ("target", "target_type", "extid_version", "extid", "extid_type") extid_type: str extid: bytes extid_version: int target_type: str target: bytes @dataclasses.dataclass class ExtIDByTargetRow(BaseRow): TABLE = "extid_by_target" PARTITION_KEY = ("target_type", "target") CLUSTERING_KEY = ("target_token",) target_type: str target: bytes target_token: int diff --git a/swh/storage/cassandra/schema.py b/swh/storage/cassandra/schema.py index d4878fb7..d12b5e23 100644 --- a/swh/storage/cassandra/schema.py +++ b/swh/storage/cassandra/schema.py @@ -1,335 +1,342 @@ # Copyright (C) 2019-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import os _use_scylla = bool(os.environ.get("SWH_USE_SCYLLADB", "")) UDF_LANGUAGE = "lua" if _use_scylla else "java" if UDF_LANGUAGE == "java": # For Cassandra CREATE_TABLES_QUERIES = [ """ CREATE OR REPLACE FUNCTION ascii_bins_count_sfunc ( state tuple>, -- (nb_none, map) bin_name ascii ) CALLED ON NULL INPUT RETURNS tuple> LANGUAGE java AS $$ if (bin_name == null) { state.setInt(0, state.getInt(0) + 1); } else { Map counters = state.getMap( 1, String.class, Integer.class); Integer nb = counters.get(bin_name); if (nb == null) { nb = 0; } counters.put(bin_name, nb + 1); state.setMap(1, counters, String.class, Integer.class); } return state; $$;""", """ CREATE OR REPLACE AGGREGATE ascii_bins_count ( ascii ) SFUNC ascii_bins_count_sfunc STYPE tuple> INITCOND (0, {}) ;""", ] elif UDF_LANGUAGE == "lua": # For ScyllaDB # TODO: this is not implementable yet, because ScyllaDB does not support # user-defined aggregates. https://github.com/scylladb/scylla/issues/7201 CREATE_TABLES_QUERIES = [] else: assert False, f"{UDF_LANGUAGE} must be 'lua' or 'java'" CREATE_TABLES_QUERIES = [ *CREATE_TABLES_QUERIES, """ CREATE TYPE IF NOT EXISTS microtimestamp ( seconds bigint, - microseconds int + microseconds int, );""", """ CREATE TYPE IF NOT EXISTS microtimestamp_with_timezone ( timestamp frozen, offset smallint, - negative_utc boolean + negative_utc boolean, + offset_bytes blob, );""", """ CREATE TYPE IF NOT EXISTS person ( fullname blob, name blob, email blob );""", """ CREATE TABLE IF NOT EXISTS content ( sha1 blob, sha1_git blob, sha256 blob, blake2s256 blob, length bigint, ctime timestamp, -- creation time, i.e. time of (first) injection into the storage status ascii, PRIMARY KEY ((sha256), sha1, sha1_git, blake2s256) );""", """ CREATE TABLE IF NOT EXISTS skipped_content ( sha1 blob, sha1_git blob, sha256 blob, blake2s256 blob, length bigint, ctime timestamp, -- creation time, i.e. time of (first) injection into the storage status ascii, reason text, origin text, PRIMARY KEY ((sha1, sha1_git, sha256, blake2s256)) );""", """ CREATE TABLE IF NOT EXISTS revision ( id blob PRIMARY KEY, date microtimestamp_with_timezone, committer_date microtimestamp_with_timezone, type ascii, directory blob, -- source code "root" directory message blob, author person, committer person, synthetic boolean, -- true iff revision has been created by Software Heritage metadata text, -- extra metadata as JSON(tarball checksums, etc...) - extra_headers frozen> > + extra_headers frozen> >, -- extra commit information as (tuple(key, value), ...) + raw_manifest blob, + -- NULL if the object can be rebuild from other cells and revision_parent. );""", """ CREATE TABLE IF NOT EXISTS revision_parent ( id blob, parent_rank int, -- parent position in merge commits, 0-based parent_id blob, PRIMARY KEY ((id), parent_rank) );""", """ CREATE TABLE IF NOT EXISTS release ( id blob PRIMARY KEY, target_type ascii, target blob, date microtimestamp_with_timezone, name blob, message blob, author person, synthetic boolean, -- true iff release has been created by Software Heritage + raw_manifest blob, + -- NULL if the object can be rebuild from other cells );""", """ CREATE TABLE IF NOT EXISTS directory ( id blob PRIMARY KEY, + raw_manifest blob + -- NULL if the object can be rebuild from (sorted) entries );""", """ CREATE TABLE IF NOT EXISTS directory_entry ( directory_id blob, name blob, -- path name, relative to containing dir target blob, perms int, -- unix-like permissions type ascii, -- target type PRIMARY KEY ((directory_id), name) );""", """ CREATE TABLE IF NOT EXISTS snapshot ( id blob PRIMARY KEY, );""", """ -- For a given snapshot_id, branches are sorted by their name, -- allowing easy pagination. CREATE TABLE IF NOT EXISTS snapshot_branch ( snapshot_id blob, name blob, target_type ascii, target blob, PRIMARY KEY ((snapshot_id), name) );""", """ CREATE TABLE IF NOT EXISTS origin_visit ( origin text, visit bigint, date timestamp, type text, PRIMARY KEY ((origin), visit) );""", """ CREATE TABLE IF NOT EXISTS origin_visit_status ( origin text, visit bigint, date timestamp, type text, status ascii, metadata text, snapshot blob, PRIMARY KEY ((origin), visit, date) ) WITH CLUSTERING ORDER BY (visit DESC, date DESC) ;""", # 'WITH CLUSTERING ORDER BY' is optional with Cassandra 4, but ScyllaDB needs it """ CREATE TABLE IF NOT EXISTS origin ( sha1 blob PRIMARY KEY, url text, next_visit_id int, -- We need integer visit ids for compatibility with the pgsql -- storage, so we're using lightweight transactions with this trick: -- https://stackoverflow.com/a/29391877/539465 );""", """ CREATE TABLE IF NOT EXISTS metadata_authority ( url text, type ascii, PRIMARY KEY ((url), type) );""", """ CREATE TABLE IF NOT EXISTS metadata_fetcher ( name ascii, version ascii, PRIMARY KEY ((name), version) );""", """ CREATE TABLE IF NOT EXISTS raw_extrinsic_metadata ( id blob, type text, target text, -- metadata source authority_type text, authority_url text, discovery_date timestamp, fetcher_name ascii, fetcher_version ascii, -- metadata itself format ascii, metadata blob, -- context origin text, visit bigint, snapshot text, release text, revision text, path blob, directory text, PRIMARY KEY ((target), authority_type, authority_url, discovery_date, id) -- An explanation is in order for this primary key: -- -- Intuitively, the primary key should only be 'id', because two metadata -- entries are the same iff the id is the same; and 'id' is used for -- deduplication. -- -- However, we also want to query by -- (target, authority_type, authority_url, discovery_date) -- The naive solution to this would be an extra table, to use as index; -- but it means 1. extra code to keep them in sync 2. overhead when writing -- 3. overhead + random reads (instead of linear) when reading. -- -- Therefore, we use a single table for both, by adding the column -- we want to query with before the id. -- It solves both a) the query/order issues and b) the uniqueness issue because: -- -- a) adding the id at the end of the primary key does not change the rows' order: -- for two different rows, id1 != id2, so -- (target1, ..., date1) < (target2, ..., date2) -- <=> (target1, ..., date1, id1) < (target2, ..., date2, id2) -- -- b) the id is a hash of all the columns, so: -- rows are the same -- <=> id1 == id2 -- <=> (target1, ..., date1, id1) == (target2, ..., date2, id2) );""", """ CREATE TABLE IF NOT EXISTS raw_extrinsic_metadata_by_id ( id blob, target text, authority_type text, authority_url text, PRIMARY KEY ((id)) );""", """ CREATE TABLE IF NOT EXISTS extid ( extid_type ascii, extid blob, extid_version smallint, target_type ascii, target blob, PRIMARY KEY ((extid_type, extid), extid_version, target_type, target) );""", """ CREATE TABLE IF NOT EXISTS extid_by_target ( target_type ascii, target blob, target_token bigint, -- value of token(pk) on the "primary" table PRIMARY KEY ((target_type, target), target_token) );""", ] CONTENT_INDEX_TEMPLATE = """ -- Secondary table, used for looking up "content" from a single hash CREATE TABLE IF NOT EXISTS content_by_{main_algo} ( {main_algo} blob, target_token bigint, -- value of token(pk) on the "primary" table PRIMARY KEY (({main_algo}), target_token) ); CREATE TABLE IF NOT EXISTS skipped_content_by_{main_algo} ( {main_algo} blob, target_token bigint, -- value of token(pk) on the "primary" table PRIMARY KEY (({main_algo}), target_token) ); """ TABLES = [ "skipped_content", "content", "revision", "revision_parent", "release", "directory", "directory_entry", "snapshot", "snapshot_branch", "origin_visit", "origin", "raw_extrinsic_metadata", "origin_visit_status", "metadata_authority", "metadata_fetcher", "extid", "extid_by_target", ] HASH_ALGORITHMS = ["sha1", "sha1_git", "sha256", "blake2s256"] for main_algo in HASH_ALGORITHMS: CREATE_TABLES_QUERIES.extend( CONTENT_INDEX_TEMPLATE.format( main_algo=main_algo, other_algos=", ".join( [algo for algo in HASH_ALGORITHMS if algo != main_algo] ), ).split("\n\n") ) TABLES.append("content_by_%s" % main_algo) TABLES.append("skipped_content_by_%s" % main_algo) diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py index 260b5f2d..a138fdbc 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,1711 +1,1713 @@ # Copyright (C) 2019-2021 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 base64 import datetime import itertools import operator import random import re from typing import ( Any, Callable, Counter, Dict, Iterable, List, Optional, Sequence, Set, Tuple, Union, ) import attr from swh.core.api.classes import stream_results from swh.core.api.serializers import msgpack_dumps, msgpack_loads from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_hex from swh.model.model import ( Content, Directory, DirectoryEntry, ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1Git, SkippedContent, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID from swh.model.swhids import ObjectType as SwhidObjectType from swh.storage.interface import ( VISIT_STATUSES, ListOrder, PagedResult, PartialBranches, Sha1, ) from swh.storage.metrics import process_metrics, send_metric, timed from swh.storage.objstorage import ObjStorage from swh.storage.utils import map_optional, now from swh.storage.writer import JournalWriter from . import converters from ..exc import HashCollision, StorageArgumentException from ..utils import remove_keys from .common import TOKEN_BEGIN, TOKEN_END, hash_url from .cql import CqlRunner from .model import ( ContentRow, DirectoryEntryRow, DirectoryRow, ExtIDByTargetRow, ExtIDRow, MetadataAuthorityRow, MetadataFetcherRow, OriginRow, OriginVisitRow, OriginVisitStatusRow, RawExtrinsicMetadataByIdRow, RawExtrinsicMetadataRow, RevisionParentRow, SkippedContentRow, SnapshotBranchRow, SnapshotRow, ) from .schema import HASH_ALGORITHMS # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 DIRECTORY_ENTRIES_INSERT_ALGOS = ["one-by-one", "concurrent", "batch"] class CassandraStorage: def __init__( self, hosts, keyspace, objstorage, port=9042, journal_writer=None, allow_overwrite=False, consistency_level="ONE", directory_entries_insert_algo="one-by-one", ): """ A backend of swh-storage backed by Cassandra Args: hosts: Seed Cassandra nodes, to start connecting to the cluster keyspace: Name of the Cassandra database to use objstorage: Passed as argument to :class:`ObjStorage` port: Cassandra port journal_writer: Passed as argument to :class:`JournalWriter` allow_overwrite: Whether ``*_add`` functions will check if an object already exists in the database before sending it in an INSERT. ``False`` is the default as it is more efficient when there is a moderately high probability the object is already known, but ``True`` can be useful to overwrite existing objects (eg. when applying a schema update), or when the database is known to be mostly empty. Note that a ``False`` value does not guarantee there won't be any overwrite. consistency_level: The default read/write consistency to use directory_entries_insert_algo: Must be one of: * one-by-one: naive, one INSERT per directory entry, serialized * concurrent: one INSERT per directory entry, concurrent * batch: using UNLOGGED BATCH to insert many entries in a few statements """ self._hosts = hosts self._keyspace = keyspace self._port = port self._consistency_level = consistency_level self._set_cql_runner() self.journal_writer: JournalWriter = JournalWriter(journal_writer) self.objstorage: ObjStorage = ObjStorage(objstorage) self._allow_overwrite = allow_overwrite if directory_entries_insert_algo not in DIRECTORY_ENTRIES_INSERT_ALGOS: raise ValueError( f"directory_entries_insert_algo must be one of: " f"{', '.join(DIRECTORY_ENTRIES_INSERT_ALGOS)}" ) self._directory_entries_insert_algo = directory_entries_insert_algo def _set_cql_runner(self): """Used by tests when they need to reset the CqlRunner""" self._cql_runner: CqlRunner = CqlRunner( self._hosts, self._keyspace, self._port, self._consistency_level ) @timed def check_config(self, *, check_write: bool) -> bool: self._cql_runner.check_read() return True def _content_get_from_hashes(self, algo, hashes: List[bytes]) -> 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 = list( self._cql_runner.content_get_tokens_from_single_algo(algo, hashes) ) assert all(isinstance(token, int) for token in found_tokens) # Query the main table ('content'). rows = self._cql_runner.content_get_from_tokens(found_tokens) for row in rows: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) in hashes: yield row def _content_add(self, contents: List[Content], with_data: bool) -> Dict[str, int]: # Filter-out content already in the database. if not self._allow_overwrite: contents = [ c for c in contents if not self._cql_runner.content_get_from_pk(c.to_dict()) ] if with_data: # First insert to the objstorage, if the endpoint is # `content_add` (as opposed to `content_add_metadata`). # Must add to the objstorage before the DB and journal. Otherwise: # 1. in case of a crash the DB may "believe" we have the content, but # we didn't have time to write to the objstorage before the crash # 2. the objstorage mirroring, which reads from the journal, may attempt to # read from the objstorage before we finished writing it summary = self.objstorage.content_add( c for c in contents if c.status != "absent" ) content_add_bytes = summary["content:add:bytes"] self.journal_writer.content_add(contents) 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) if not self._allow_overwrite: for algo in {"sha1", "sha1_git"}: collisions = [] # Get tokens of 'content' rows with the same value for # sha1/sha1_git # TODO: batch these requests, instead of sending them one by one rows = self._content_get_from_hashes(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 other_algo in HASH_ALGORITHMS: if getattr(row, other_algo) != content.get_hash(other_algo): # This hash didn't match; discard the row. collisions.append( {k: getattr(row, k) for k 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( ContentRow(**remove_keys(content.to_dict(), ("data",))) ) # 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 @timed @process_metrics def content_add(self, content: List[Content]) -> Dict[str, int]: to_add = { (c.sha1, c.sha1_git, c.sha256, c.blake2s256): c for c in content }.values() contents = [attr.evolve(c, ctime=now()) for c in to_add] return self._content_add(list(contents), with_data=True) @timed def content_update( self, contents: List[Dict[str, Any]], keys: List[str] = [] ) -> None: raise NotImplementedError( "content_update is not supported by the Cassandra backend" ) @timed @process_metrics def content_add_metadata(self, content: List[Content]) -> Dict[str, int]: return self._content_add(content, with_data=False) @timed def content_get_data(self, content: Sha1) -> Optional[bytes]: # FIXME: Make this method support slicing the `data` return self.objstorage.content_get(content) @timed def content_get_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, ) -> PagedResult[Content]: 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) next_page_token: Optional[str] = None rows = self._cql_runner.content_get_token_range( range_start, range_end, limit + 1 ) contents = [] for counter, (tok, row) in enumerate(rows): if row.status == "absent": continue row_d = row.to_dict() if counter >= limit: next_page_token = str(tok) break row_d.pop("ctime") contents.append(Content(**row_d)) assert len(contents) <= limit return PagedResult(results=contents, next_page_token=next_page_token) @timed def content_get( self, contents: List[bytes], algo: str = "sha1" ) -> List[Optional[Content]]: if algo not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "algo should be one of {','.join(DEFAULT_ALGORITHMS)}" ) key = operator.attrgetter(algo) contents_by_hash: Dict[Sha1, Optional[Content]] = {} for row in self._content_get_from_hashes(algo, contents): # Get all (sha1, sha1_git, sha256, blake2s256) whose sha1/sha1_git # matches the argument, from the index table ('content_by_*') row_d = row.to_dict() row_d.pop("ctime") content = Content(**row_d) contents_by_hash[key(content)] = content return [contents_by_hash.get(hash_) for hash_ in contents] @timed def content_find(self, content: Dict[str, Any]) -> List[Content]: return self._content_find_many([content]) def _content_find_many(self, contents: List[Dict[str, Any]]) -> List[Content]: # Find an algorithm that is common to all the requested contents. # It will be used to do an initial filtering efficiently. filter_algos = set(HASH_ALGORITHMS) for content in contents: filter_algos &= set(content) if not filter_algos: raise StorageArgumentException( "content keys must contain at least one " f"of: {', '.join(sorted(HASH_ALGORITHMS))}" ) common_algo = list(filter_algos)[0] results = [] rows = self._content_get_from_hashes( common_algo, [content[common_algo] for content in contents] ) 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 content in contents: 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. row_d = row.to_dict() row_d["ctime"] = row.ctime.replace(tzinfo=datetime.timezone.utc) results.append(Content(**row_d)) break else: # No content matched; skip it pass return results @timed def content_missing( self, contents: List[Dict[str, Any]], key_hash: str = "sha1" ) -> Iterable[bytes]: if key_hash not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "key_hash should be one of {','.join(DEFAULT_ALGORITHMS)}" ) contents_with_all_hashes = [] contents_with_missing_hashes = [] for content in contents: if DEFAULT_ALGORITHMS <= set(content): contents_with_all_hashes.append(content) else: contents_with_missing_hashes.append(content) # These contents can be queried efficiently directly in the main table for content in self._cql_runner.content_missing_from_hashes( contents_with_all_hashes ): yield content[key_hash] # For these, we need the expensive index lookups + main table. for content in contents_with_missing_hashes: res = self.content_find(content) if not res: yield content[key_hash] @timed def content_missing_per_sha1(self, contents: List[bytes]) -> Iterable[bytes]: return self.content_missing([{"sha1": c} for c in contents]) @timed def content_missing_per_sha1_git( self, contents: List[Sha1Git] ) -> Iterable[Sha1Git]: return self.content_missing( [{"sha1_git": c} for c in contents], key_hash="sha1_git" ) @timed def content_get_random(self) -> Sha1Git: content = self._cql_runner.content_get_random() assert content, "Could not find any content" return content.sha1_git def _skipped_content_add(self, contents: List[SkippedContent]) -> Dict[str, int]: # Filter-out content already in the database. if not self._allow_overwrite: 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( SkippedContentRow.from_dict({"origin": None, **content.to_dict()}) ) # 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)} @timed @process_metrics def skipped_content_add(self, content: List[SkippedContent]) -> Dict[str, int]: contents = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(contents) @timed def skipped_content_missing( self, contents: List[Dict[str, Any]] ) -> Iterable[Dict[str, Any]]: for content in contents: if not self._cql_runner.skipped_content_get_from_pk(content): yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} @timed @process_metrics def directory_add(self, directories: List[Directory]) -> Dict[str, int]: to_add = {d.id: d for d in directories}.values() if not self._allow_overwrite: # Filter out directories that are already inserted. missing = self.directory_missing([dir_.id for dir_ in to_add]) 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 rows = [ DirectoryEntryRow(directory_id=directory.id, **entry.to_dict()) for entry in directory.entries ] if self._directory_entries_insert_algo == "one-by-one": for row in rows: self._cql_runner.directory_entry_add_one(row) elif self._directory_entries_insert_algo == "concurrent": self._cql_runner.directory_entry_add_concurrent(rows) elif self._directory_entries_insert_algo == "batch": self._cql_runner.directory_entry_add_batch(rows) else: raise ValueError( f"Unexpected value for directory_entries_insert_algo: " f"{self._directory_entries_insert_algo}" ) # 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(DirectoryRow(id=directory.id)) + self._cql_runner.directory_add_one( + DirectoryRow(id=directory.id, raw_manifest=directory.raw_manifest) + ) return {"directory:add": len(directories)} @timed def directory_missing(self, directories: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.directory_missing(directories) def _join_dentry_to_content( self, dentry: DirectoryEntry, contents: List[Content] ) -> Dict[str, Any]: content: Union[None, Content, SkippedContentRow] keys = ( "status", "sha1", "sha1_git", "sha256", "length", ) ret = dict.fromkeys(keys) ret.update(dentry.to_dict()) if ret["type"] == "file": for content in contents: if dentry.target == content.sha1_git: break else: target = ret["target"] assert target is not None tokens = list( self._cql_runner.skipped_content_get_tokens_from_single_hash( "sha1_git", target ) ) if tokens: content = list( self._cql_runner.skipped_content_get_from_token(tokens[0]) )[0] else: content = None if content: for key in keys: ret[key] = getattr(content, key) return ret def _directory_ls( self, directory_id: Sha1Git, recursive: bool, prefix: bytes = b"" ) -> Iterable[Dict[str, Any]]: if self.directory_missing([directory_id]): return rows = list(self._cql_runner.directory_entry_get([directory_id])) # TODO: dedup to be fast in case the directory contains the same subdir/file # multiple times contents = self._content_find_many([{"sha1_git": row.target} for row in rows]) for row in rows: entry_d = row.to_dict() # Build and yield the directory entry dict del entry_d["directory_id"] entry = DirectoryEntry.from_dict(entry_d) ret = self._join_dentry_to_content(entry, contents) 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"/" ) @timed def directory_entry_get_by_path( self, directory: Sha1Git, paths: List[bytes] ) -> Optional[Dict[str, Any]]: return self._directory_entry_get_by_path(directory, paths, b"") def _directory_entry_get_by_path( self, directory: Sha1Git, paths: List[bytes], prefix: bytes ) -> Optional[Dict[str, Any]]: if not paths: return None contents = list(self.directory_ls(directory)) if not contents: return None 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 None return self._directory_entry_get_by_path( first_item["target"], paths[1:], prefix + paths[0] + b"/" ) @timed def directory_ls( self, directory: Sha1Git, recursive: bool = False ) -> Iterable[Dict[str, Any]]: yield from self._directory_ls(directory, recursive) @timed def directory_get_entries( self, directory_id: Sha1Git, page_token: Optional[bytes] = None, limit: int = 1000, ) -> Optional[PagedResult[DirectoryEntry]]: if self.directory_missing([directory_id]): return None entries_from: bytes = page_token or b"" rows = self._cql_runner.directory_entry_get_from_name( directory_id, entries_from, limit + 1 ) entries = [ DirectoryEntry.from_dict(remove_keys(row.to_dict(), ("directory_id",))) for row in rows ] if len(entries) > limit: last_entry = entries.pop() next_page_token = last_entry.name else: next_page_token = None return PagedResult(results=entries, next_page_token=next_page_token) @timed def directory_get_random(self) -> Sha1Git: directory = self._cql_runner.directory_get_random() assert directory, "Could not find any directory" return directory.id @timed @process_metrics def revision_add(self, revisions: List[Revision]) -> Dict[str, int]: # Filter-out revisions already in the database if not self._allow_overwrite: to_add = {r.id: r for r in revisions}.values() missing = self.revision_missing([rev.id for rev in to_add]) revisions = [rev for rev in revisions if rev.id in missing] self.journal_writer.revision_add(revisions) for revision in revisions: revobject = converters.revision_to_db(revision) if revobject: # Add parents first for (rank, parent) in enumerate(revision.parents): self._cql_runner.revision_parent_add_one( RevisionParentRow( id=revobject.id, parent_rank=rank, parent_id=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)} @timed def revision_missing(self, revisions: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.revision_missing(revisions) @timed def revision_get(self, revision_ids: List[Sha1Git]) -> List[Optional[Revision]]: rows = self._cql_runner.revision_get(revision_ids) revisions: Dict[Sha1Git, Revision] = {} 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) parents = tuple(self._cql_runner.revision_parent_get(row.id)) # parent_rank is the clustering key, so results are already # sorted by rank. rev = converters.revision_from_db(row, parents=parents) revisions[rev.id] = rev return [revisions.get(rev_id) for rev_id in revision_ids] def _get_parent_revs( self, rev_ids: Iterable[Sha1Git], seen: Set[Sha1Git], limit: Optional[int], short: bool, ) -> Union[ Iterable[Dict[str, Any]], Iterable[Tuple[Sha1Git, Tuple[Sha1Git, ...]]], ]: 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: ids = self._cql_runner.revision_get_ids(rev_ids) for id_ in ids: # 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) parents = tuple(self._cql_runner.revision_parent_get(id_)) # parent_rank is the clustering key, so results are already # sorted by rank. yield (id_, parents) yield from self._get_parent_revs(parents, seen, limit, short) 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) parents = tuple(self._cql_runner.revision_parent_get(row.id)) # parent_rank is the clustering key, so results are already # sorted by rank. rev = converters.revision_from_db(row, parents=parents) yield rev.to_dict() yield from self._get_parent_revs(parents, seen, limit, short) @timed def revision_log( self, revisions: List[Sha1Git], limit: Optional[int] = None ) -> Iterable[Optional[Dict[str, Any]]]: seen: Set[Sha1Git] = set() yield from self._get_parent_revs(revisions, seen, limit, False) @timed def revision_shortlog( self, revisions: List[Sha1Git], limit: Optional[int] = None ) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]: seen: Set[Sha1Git] = set() yield from self._get_parent_revs(revisions, seen, limit, True) @timed def revision_get_random(self) -> Sha1Git: revision = self._cql_runner.revision_get_random() assert revision, "Could not find any revision" return revision.id @timed @process_metrics def release_add(self, releases: List[Release]) -> Dict[str, int]: if not self._allow_overwrite: to_add = {r.id: r for r in releases}.values() missing = set(self.release_missing([rel.id for rel in to_add])) releases = [rel for rel in to_add if rel.id in missing] self.journal_writer.release_add(releases) for release in releases: if release: self._cql_runner.release_add_one(converters.release_to_db(release)) return {"release:add": len(releases)} @timed def release_missing(self, releases: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.release_missing(releases) @timed def release_get(self, releases: List[Sha1Git]) -> List[Optional[Release]]: rows = self._cql_runner.release_get(releases) rels: Dict[Sha1Git, Release] = {} for row in rows: release = converters.release_from_db(row) rels[row.id] = release return [rels.get(rel_id) for rel_id in releases] @timed def release_get_random(self) -> Sha1Git: release = self._cql_runner.release_get_random() assert release, "Could not find any release" return release.id @timed @process_metrics def snapshot_add(self, snapshots: List[Snapshot]) -> Dict[str, int]: if not self._allow_overwrite: to_add = {s.id: s for s in snapshots}.values() missing = self._cql_runner.snapshot_missing([snp.id for snp in to_add]) 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: Optional[str] = None target: Optional[bytes] = None else: target_type = branch.target_type.value target = branch.target self._cql_runner.snapshot_branch_add_one( SnapshotBranchRow( 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(SnapshotRow(id=snapshot.id)) return {"snapshot:add": len(snapshots)} @timed def snapshot_missing(self, snapshots: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.snapshot_missing(snapshots) @timed def snapshot_get(self, snapshot_id: Sha1Git) -> Optional[Dict[str, Any]]: d = self.snapshot_get_branches(snapshot_id) if d is None: return None return { "id": d["id"], "branches": { name: branch.to_dict() if branch else None for (name, branch) in d["branches"].items() }, "next_branch": d["next_branch"], } @timed def snapshot_count_branches( self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None, ) -> Optional[Dict[Optional[str], int]]: if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None return self._cql_runner.snapshot_count_branches( snapshot_id, branch_name_exclude_prefix ) @timed def snapshot_get_branches( self, snapshot_id: Sha1Git, branches_from: bytes = b"", branches_count: int = 1000, target_types: Optional[List[str]] = None, branch_name_include_substring: Optional[bytes] = None, branch_name_exclude_prefix: Optional[bytes] = None, ) -> Optional[PartialBranches]: 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: List = [] while len(branches) < branches_count + 1: new_branches = list( self._cql_runner.snapshot_branch_get( snapshot_id, branches_from, branches_count + 1, branch_name_exclude_prefix, ) ) 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 ] # Filter by branches_name_pattern if branch_name_include_substring: new_branches_filtered = [ branch for branch in new_branches_filtered if branch.name is not None and ( branch_name_include_substring is None or branch_name_include_substring in branch.name ) ] 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 return PartialBranches( id=snapshot_id, branches={ branch.name: None if branch.target is None else SnapshotBranch( target=branch.target, target_type=TargetType(branch.target_type) ) for branch in branches }, next_branch=last_branch, ) @timed def snapshot_get_random(self) -> Sha1Git: snapshot = self._cql_runner.snapshot_get_random() assert snapshot, "Could not find any snapshot" return snapshot.id @timed def object_find_by_sha1_git(self, ids: List[Sha1Git]) -> Dict[Sha1Git, List[Dict]]: results: Dict[Sha1Git, List[Dict]] = {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: List[Tuple[str, Callable[[List[Sha1Git]], List[Sha1Git]]]] = [ ("revision", self._cql_runner.revision_missing), ("release", self._cql_runner.release_missing), ("content", self.content_missing_per_sha1_git), ("directory", self._cql_runner.directory_missing), ] for (object_type, query_fn) in queries: found_ids = missing_ids - set(query_fn(list(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 @timed def origin_get(self, origins: List[str]) -> Iterable[Optional[Origin]]: return [self.origin_get_one(origin) for origin in origins] @timed def origin_get_one(self, origin_url: str) -> Optional[Origin]: """Given an origin url, return the origin if it exists, None otherwise """ rows = list(self._cql_runner.origin_get_by_url(origin_url)) if rows: assert len(rows) == 1 return Origin(url=rows[0].url) else: return None @timed def origin_get_by_sha1(self, sha1s: List[bytes]) -> List[Optional[Dict[str, Any]]]: results = [] for sha1 in sha1s: rows = list(self._cql_runner.origin_get_by_sha1(sha1)) origin = {"url": rows[0].url} if rows else None results.append(origin) return results @timed def origin_list( self, page_token: Optional[str] = None, limit: int = 100 ) -> PagedResult[Origin]: # 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.") next_page_token = None origins = [] # Take one more origin so we can reuse it as the next page token if any for (tok, row) in self._cql_runner.origin_list(start_token, limit + 1): origins.append(Origin(url=row.url)) # keep reference of the last id for pagination purposes last_id = tok if len(origins) > limit: # last origin id is the next page token next_page_token = str(last_id) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @timed def origin_search( self, url_pattern: str, page_token: Optional[str] = None, limit: int = 50, regexp: bool = False, with_visit: bool = False, visit_types: Optional[List[str]] = None, ) -> PagedResult[Origin]: # TODO: remove this endpoint, swh-search should be used instead. next_page_token = None offset = int(page_token) if page_token else 0 origin_rows = [row for row in self._cql_runner.origin_iter_all()] if regexp: pat = re.compile(url_pattern) origin_rows = [row for row in origin_rows if pat.search(row.url)] else: origin_rows = [row for row in origin_rows if url_pattern in row.url] if with_visit: origin_rows = [row for row in origin_rows if row.next_visit_id > 1] if visit_types: def _has_visit_types(origin, visit_types): for origin_visit in stream_results(self.origin_visit_get, origin): if origin_visit.type in visit_types: return True return False origin_rows = [ row for row in origin_rows if _has_visit_types(row.url, visit_types) ] origins = [Origin(url=row.url) for row in origin_rows] origins = origins[offset : offset + limit + 1] if len(origins) > limit: # next offset next_page_token = str(offset + limit) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @timed def origin_count( self, url_pattern: str, regexp: bool = False, with_visit: bool = False ) -> int: raise NotImplementedError( "The Cassandra backend does not implement origin_count" ) @timed def origin_snapshot_get_all(self, origin_url: str) -> List[Sha1Git]: return list(self._cql_runner.origin_snapshot_get_all(origin_url)) @timed @process_metrics def origin_add(self, origins: List[Origin]) -> Dict[str, int]: if not self._allow_overwrite: to_add = {o.url: o for o in origins}.values() origins = [ori for ori in to_add if self.origin_get_one(ori.url) is None] self.journal_writer.origin_add(origins) for origin in origins: self._cql_runner.origin_add_one( OriginRow(sha1=hash_url(origin.url), url=origin.url, next_visit_id=1) ) return {"origin:add": len(origins)} @timed def origin_visit_add(self, visits: List[OriginVisit]) -> Iterable[OriginVisit]: for visit in visits: origin = self.origin_get_one(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 visit.visit: # Set origin.next_visit_id = max(origin.next_visit_id, visit.visit+1) # so the next loader run does not reuse the id. self._cql_runner.origin_bump_next_visit_id(visit.origin, visit.visit) else: 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(OriginVisitRow(**visit.to_dict())) 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, type=visit.type, status="created", snapshot=None, ) ) send_metric("origin_visit:add", count=nb_visits, method_name="origin_visit") return all_visits def _origin_visit_status_add(self, visit_status: OriginVisitStatus) -> None: """Add an origin visit status""" if visit_status.type is None: visit_row = self._cql_runner.origin_visit_get_one( visit_status.origin, visit_status.visit ) if visit_row is None: raise StorageArgumentException( f"Unknown origin visit {visit_status.visit} " f"of origin {visit_status.origin}" ) visit_status = attr.evolve(visit_status, type=visit_row.type) self.journal_writer.origin_visit_status_add([visit_status]) self._cql_runner.origin_visit_status_add_one( converters.visit_status_to_row(visit_status) ) @timed @process_metrics def origin_visit_status_add( self, visit_statuses: List[OriginVisitStatus] ) -> Dict[str, int]: # First round to check existence (fail early if any is ko) for visit_status in visit_statuses: origin_url = self.origin_get_one(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) return {"origin_visit_status:add": len(visit_statuses)} def _origin_visit_apply_status( self, visit: Dict[str, Any], visit_status: OriginVisitStatusRow ) -> Dict[str, Any]: """Retrieve the latest visit status information for the origin visit. Then merge it with the visit and return it. """ 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"], # We use the visit type from origin visit # if it's not present on the origin visit status "type": visit_status.type or visit["type"], } def _origin_visit_get_latest_status(self, visit: OriginVisit) -> OriginVisitStatus: """Retrieve the latest visit status information for the origin visit object. """ assert visit.visit row = self._cql_runner.origin_visit_status_get_latest(visit.origin, visit.visit) assert row is not None visit_status = converters.row_to_visit_status(row) return attr.evolve(visit_status, origin=visit.origin) @staticmethod def _format_origin_visit_row(visit): return { **visit.to_dict(), "origin": visit.origin, "date": visit.date.replace(tzinfo=datetime.timezone.utc), } @timed def origin_visit_get( self, origin: str, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, ) -> PagedResult[OriginVisit]: if not isinstance(order, ListOrder): raise StorageArgumentException("order must be a ListOrder value") if page_token and not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") next_page_token = None visit_from = None if page_token is None else int(page_token) visits: List[OriginVisit] = [] extra_limit = limit + 1 rows = self._cql_runner.origin_visit_get(origin, visit_from, extra_limit, order) for row in rows: visits.append(converters.row_to_visit(row)) assert len(visits) <= extra_limit if len(visits) == extra_limit: visits = visits[:limit] next_page_token = str(visits[-1].visit) return PagedResult(results=visits, next_page_token=next_page_token) @timed def origin_visit_status_get( self, origin: str, visit: int, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, ) -> PagedResult[OriginVisitStatus]: next_page_token = None date_from = None if page_token is not None: date_from = datetime.datetime.fromisoformat(page_token) # Take one more visit status so we can reuse it as the next page token if any rows = self._cql_runner.origin_visit_status_get_range( origin, visit, date_from, limit + 1, order ) visit_statuses = [converters.row_to_visit_status(row) for row in rows] if len(visit_statuses) > limit: # last visit status date is the next page token next_page_token = str(visit_statuses[-1].date) # excluding that visit status from the result to respect the limit size visit_statuses = visit_statuses[:limit] return PagedResult(results=visit_statuses, next_page_token=next_page_token) @timed def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime ) -> Optional[OriginVisit]: # 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: return converters.row_to_visit(min(rows, key=key)) return None @timed def origin_visit_get_by(self, origin: str, visit: int) -> Optional[OriginVisit]: row = self._cql_runner.origin_visit_get_one(origin, visit) if row: return converters.row_to_visit(row) return None @timed def origin_visit_get_latest( self, origin: str, type: Optional[str] = None, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[OriginVisit]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) # 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) for status_row in self._cql_runner.origin_visit_status_get( origin, visit["visit"] ): updated_visit = self._origin_visit_apply_status(visit, status_row) 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 assert ( updated_visit["visit"] >= latest_visit["visit"] ), "Cassandra returned visits not ordered by increasing visit id." latest_visit = updated_visit if latest_visit is None: return None return OriginVisit( origin=latest_visit["origin"], visit=latest_visit["visit"], date=latest_visit["date"], type=latest_visit["type"], ) @timed def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[OriginVisitStatus]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) rows = list(self._cql_runner.origin_visit_status_get(origin_url, visit)) # 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 converters.row_to_visit_status(rows[0]) @timed def origin_visit_status_get_random(self, type: str) -> Optional[OriginVisitStatus]: 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 = converters.row_to_visit(row) visit_status = self._origin_visit_get_latest_status(visit) if visit.date > back_in_the_day and visit_status.status == "full": return visit_status return None @timed 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 @timed def refresh_stat_counters(self): pass @timed @process_metrics def raw_extrinsic_metadata_add( self, metadata: List[RawExtrinsicMetadata] ) -> Dict[str, int]: self.journal_writer.raw_extrinsic_metadata_add(metadata) counter = Counter[ExtendedObjectType]() 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: row = RawExtrinsicMetadataRow( id=metadata_entry.id, type=metadata_entry.target.object_type.name.lower(), target=str(metadata_entry.target), 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) # Add to the index first self._cql_runner.raw_extrinsic_metadata_by_id_add( RawExtrinsicMetadataByIdRow( id=row.id, target=row.target, authority_type=row.authority_type, authority_url=row.authority_url, ) ) # Then to the main table self._cql_runner.raw_extrinsic_metadata_add(row) counter[metadata_entry.target.object_type] += 1 return { f"{type.value}_metadata:add": count for (type, count) in counter.items() } @timed def raw_extrinsic_metadata_get( self, target: ExtendedSWHID, authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, ) -> PagedResult[RawExtrinsicMetadata]: if page_token is not None: (after_date, id_) = msgpack_loads(base64.b64decode(page_token)) if after and after_date < after: raise StorageArgumentException( "page_token is inconsistent with the value of 'after'." ) entries = self._cql_runner.raw_extrinsic_metadata_get_after_date_and_id( str(target), authority.type.value, authority.url, after_date, id_, ) elif after is not None: entries = self._cql_runner.raw_extrinsic_metadata_get_after_date( str(target), authority.type.value, authority.url, after ) else: entries = self._cql_runner.raw_extrinsic_metadata_get( str(target), authority.type.value, authority.url ) if limit: entries = itertools.islice(entries, 0, limit + 1) results = [] for entry in entries: assert str(target) == entry.target results.append(converters.row_to_raw_extrinsic_metadata(entry)) if len(results) > limit: results.pop() assert len(results) == limit last_result = results[-1] next_page_token: Optional[str] = base64.b64encode( msgpack_dumps((last_result.discovery_date, last_result.id,)) ).decode() else: next_page_token = None return PagedResult(next_page_token=next_page_token, results=results,) @timed def raw_extrinsic_metadata_get_by_ids( self, ids: List[Sha1Git] ) -> List[RawExtrinsicMetadata]: keys = self._cql_runner.raw_extrinsic_metadata_get_by_ids(ids) results: Set[RawExtrinsicMetadata] = set() for key in keys: candidates = self._cql_runner.raw_extrinsic_metadata_get( key.target, key.authority_type, key.authority_url ) candidates = [ candidate for candidate in candidates if candidate.id == key.id ] if len(candidates) > 1: raise Exception( "Found multiple RawExtrinsicMetadata objects with the same id: " + hash_to_hex(key.id) ) results.update(map(converters.row_to_raw_extrinsic_metadata, candidates)) return list(results) @timed def raw_extrinsic_metadata_get_authorities( self, target: ExtendedSWHID ) -> List[MetadataAuthority]: return [ MetadataAuthority( type=MetadataAuthorityType(authority_type), url=authority_url ) for (authority_type, authority_url) in set( self._cql_runner.raw_extrinsic_metadata_get_authorities(str(target)) ) ] @timed @process_metrics def metadata_fetcher_add(self, fetchers: List[MetadataFetcher]) -> Dict[str, int]: self.journal_writer.metadata_fetcher_add(fetchers) for fetcher in fetchers: self._cql_runner.metadata_fetcher_add( MetadataFetcherRow(name=fetcher.name, version=fetcher.version,) ) return {"metadata_fetcher:add": len(fetchers)} @timed 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,) else: return None @timed @process_metrics def metadata_authority_add( self, authorities: List[MetadataAuthority] ) -> Dict[str, int]: self.journal_writer.metadata_authority_add(authorities) for authority in authorities: self._cql_runner.metadata_authority_add( MetadataAuthorityRow(url=authority.url, type=authority.type.value,) ) return {"metadata_authority:add": len(authorities)} @timed 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, ) else: return None # ExtID tables @timed @process_metrics def extid_add(self, ids: List[ExtID]) -> Dict[str, int]: if not self._allow_overwrite: extids = [ extid for extid in ids if not self._cql_runner.extid_get_from_pk( extid_type=extid.extid_type, extid_version=extid.extid_version, extid=extid.extid, target=extid.target, ) ] else: extids = list(ids) self.journal_writer.extid_add(extids) inserted = 0 for extid in extids: target_type = extid.target.object_type.value target = extid.target.object_id extid_version = extid.extid_version extid_type = extid.extid_type extidrow = ExtIDRow( extid_type=extid_type, extid_version=extid_version, extid=extid.extid, target_type=target_type, target=target, ) (token, insertion_finalizer) = self._cql_runner.extid_add_prepare(extidrow) indexrow = ExtIDByTargetRow( target_type=target_type, target=target, target_token=token, ) self._cql_runner.extid_index_add_one(indexrow) insertion_finalizer() inserted += 1 return {"extid:add": inserted} @timed def extid_get_from_extid( self, id_type: str, ids: List[bytes], version: Optional[int] = None ) -> List[ExtID]: result: List[ExtID] = [] for extid in ids: if version is not None: extidrows = self._cql_runner.extid_get_from_extid_and_version( id_type, extid, version ) else: extidrows = self._cql_runner.extid_get_from_extid(id_type, extid) result.extend( ExtID( extid_type=extidrow.extid_type, extid_version=extidrow.extid_version, extid=extidrow.extid, target=CoreSWHID( object_type=extidrow.target_type, object_id=extidrow.target, ), ) for extidrow in extidrows ) return result @timed def extid_get_from_target( self, target_type: SwhidObjectType, ids: List[Sha1Git], extid_type: Optional[str] = None, extid_version: Optional[int] = None, ) -> List[ExtID]: if (extid_version is not None and extid_type is None) or ( extid_version is None and extid_type is not None ): raise ValueError("You must provide both extid_type and extid_version") result: List[ExtID] = [] for target in ids: extidrows = self._cql_runner.extid_get_from_target( target_type.value, target, extid_type=extid_type, extid_version=extid_version, ) result.extend( ExtID( extid_type=extidrow.extid_type, extid_version=extidrow.extid_version, extid=extidrow.extid, target=CoreSWHID( object_type=SwhidObjectType(extidrow.target_type), object_id=extidrow.target, ), ) for extidrow in extidrows ) return result # Misc def clear_buffers(self, object_types: Sequence[str] = ()) -> None: """Do nothing """ return None def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]: return {} diff --git a/swh/storage/postgresql/converters.py b/swh/storage/postgresql/converters.py index e5c8e45e..36c75c31 100644 --- a/swh/storage/postgresql/converters.py +++ b/swh/storage/postgresql/converters.py @@ -1,342 +1,367 @@ # Copyright (C) 2015-2021 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 math from typing import Any, Dict, Optional import warnings from swh.core.utils import encode_with_unescape from swh.model.model import ( ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ObjectType, Origin, Person, RawExtrinsicMetadata, Release, Revision, RevisionType, Timestamp, TimestampWithTimezone, ) from swh.model.swhids import CoreSWHID, ExtendedSWHID from swh.model.swhids import ObjectType as SwhidObjectType from ..utils import map_optional DEFAULT_AUTHOR = { "fullname": None, "name": None, "email": None, } DEFAULT_DATE = { "timestamp": None, "offset": 0, "neg_utc_offset": None, + "offset_bytes": None, } def author_to_db(author: Optional[Person]) -> Dict[str, Any]: """Convert a swh-model author to its DB representation. Args: author: a :mod:`swh.model` compatible author Returns: dict: a dictionary with three keys: author, fullname and email """ if author is None: return DEFAULT_AUTHOR return author.to_dict() def db_to_author( fullname: Optional[bytes], name: Optional[bytes], email: Optional[bytes] ) -> Optional[Person]: """Convert the DB representation of an author to a swh-model author. Args: fullname (bytes): the author's fullname name (bytes): the author's name email (bytes): the author's email Returns: a Person object, or None if 'fullname' is None. """ if fullname is None: return None return Person(fullname=fullname, name=name, email=email,) def db_to_git_headers(db_git_headers): ret = [] for key, value in db_git_headers: ret.append([key.encode("utf-8"), encode_with_unescape(value)]) return ret def db_to_date( - date: Optional[datetime.datetime], offset: int, neg_utc_offset: Optional[bool] + date: Optional[datetime.datetime], + offset: int, + neg_utc_offset: Optional[bool], + offset_bytes: Optional[bytes], ) -> Optional[TimestampWithTimezone]: """Convert the DB representation of a date to a swh-model compatible date. Args: date: a date pulled out of the database offset: an integer number of minutes representing an UTC offset neg_utc_offset: whether an utc offset is negative Returns: a TimestampWithTimezone, or None if the date is None. """ if date is None: return None if neg_utc_offset is None: # For older versions of the database that were not migrated to schema v160 neg_utc_offset = False + kwargs = {} + if offset_bytes: + # TODO: remove the conditional after migration is complete. + kwargs["offset_bytes"] = offset_bytes + return TimestampWithTimezone( timestamp=Timestamp( # we use floor() instead of int() to round down, because of negative dates seconds=math.floor(date.timestamp()), microseconds=date.microsecond, ), offset=offset, negative_utc=neg_utc_offset, + **kwargs, ) def date_to_db(ts_with_tz: Optional[TimestampWithTimezone]) -> Dict[str, Any]: """Convert a swh-model date_offset to its DB representation. Args: ts_with_tz: a TimestampWithTimezone object Returns: - dict: a dictionary with three keys: + dict: a dictionary with these keys: - timestamp: a date in ISO format - offset: the UTC offset in minutes - neg_utc_offset: a boolean indicating whether a null offset is negative or positive. + - offset_bytes: a byte representation of the latter two, usually as "+HHMM" + or "-HHMM" """ if ts_with_tz is None: return DEFAULT_DATE ts = ts_with_tz.timestamp timestamp = datetime.datetime.fromtimestamp(ts.seconds, datetime.timezone.utc) timestamp = timestamp.replace(microsecond=ts.microseconds) return { # PostgreSQL supports isoformatted timestamps "timestamp": timestamp.isoformat(), "offset": ts_with_tz.offset, "neg_utc_offset": ts_with_tz.negative_utc, + "offset_bytes": ts_with_tz.offset_bytes, } def revision_to_db(revision: Revision) -> Dict[str, Any]: """Convert a swh-model revision to its database representation. """ author = author_to_db(revision.author) date = date_to_db(revision.date) committer = author_to_db(revision.committer) committer_date = date_to_db(revision.committer_date) return { "id": revision.id, "author_fullname": author["fullname"], "author_name": author["name"], "author_email": author["email"], "date": date["timestamp"], "date_offset": date["offset"], "date_neg_utc_offset": date["neg_utc_offset"], + "date_offset_bytes": date["offset_bytes"], "committer_fullname": committer["fullname"], "committer_name": committer["name"], "committer_email": committer["email"], "committer_date": committer_date["timestamp"], "committer_date_offset": committer_date["offset"], "committer_date_neg_utc_offset": committer_date["neg_utc_offset"], + "committer_date_offset_bytes": committer_date["offset_bytes"], "type": revision.type.value, "directory": revision.directory, "message": revision.message, "metadata": None if revision.metadata is None else dict(revision.metadata), "synthetic": revision.synthetic, "extra_headers": revision.extra_headers, + "raw_manifest": revision.raw_manifest, "parents": [ {"id": revision.id, "parent_id": parent, "parent_rank": i,} for i, parent in enumerate(revision.parents) ], } def db_to_revision(db_revision: Dict[str, Any]) -> Optional[Revision]: """Convert a database representation of a revision to its swh-model representation.""" if db_revision["type"] is None: assert all( v is None for (k, v) in db_revision.items() if k not in ("id", "parents") ) return None author = db_to_author( db_revision["author_fullname"], db_revision["author_name"], db_revision["author_email"], ) date = db_to_date( db_revision["date"], db_revision["date_offset"], db_revision["date_neg_utc_offset"], + db_revision["date_offset_bytes"], ) committer = db_to_author( db_revision["committer_fullname"], db_revision["committer_name"], db_revision["committer_email"], ) committer_date = db_to_date( db_revision["committer_date"], db_revision["committer_date_offset"], db_revision["committer_date_neg_utc_offset"], + db_revision["committer_date_offset_bytes"], ) assert author, "author is None" assert committer, "committer is None" parents = [] if "parents" in db_revision: for parent in db_revision["parents"]: if parent: parents.append(parent) metadata = db_revision["metadata"] extra_headers = db_revision["extra_headers"] if not extra_headers: if metadata and "extra_headers" in metadata: extra_headers = db_to_git_headers(metadata.pop("extra_headers")) else: # For older versions of the database that were not migrated to schema v161 extra_headers = () return Revision( id=db_revision["id"], author=author, date=date, committer=committer, committer_date=committer_date, type=RevisionType(db_revision["type"]), directory=db_revision["directory"], message=db_revision["message"], metadata=metadata, synthetic=db_revision["synthetic"], extra_headers=extra_headers, parents=tuple(parents), + raw_manifest=db_revision["raw_manifest"], ) def release_to_db(release: Release) -> Dict[str, Any]: """Convert a swh-model release to its database representation. """ author = author_to_db(release.author) date = date_to_db(release.date) return { "id": release.id, "author_fullname": author["fullname"], "author_name": author["name"], "author_email": author["email"], "date": date["timestamp"], "date_offset": date["offset"], "date_neg_utc_offset": date["neg_utc_offset"], + "date_offset_bytes": date["offset_bytes"], "name": release.name, "target": release.target, "target_type": release.target_type.value, "comment": release.message, "synthetic": release.synthetic, + "raw_manifest": release.raw_manifest, } def db_to_release(db_release: Dict[str, Any]) -> Optional[Release]: """Convert a database representation of a release to its swh-model representation. """ if db_release["target_type"] is None: assert all(v is None for (k, v) in db_release.items() if k != "id") return None author = db_to_author( db_release["author_fullname"], db_release["author_name"], db_release["author_email"], ) date = db_to_date( - db_release["date"], db_release["date_offset"], db_release["date_neg_utc_offset"] + db_release["date"], + db_release["date_offset"], + db_release["date_neg_utc_offset"], + db_release["date_offset_bytes"], ) return Release( author=author, date=date, id=db_release["id"], name=db_release["name"], message=db_release["comment"], synthetic=db_release["synthetic"], target=db_release["target"], target_type=ObjectType(db_release["target_type"]), + raw_manifest=db_release["raw_manifest"], ) def db_to_raw_extrinsic_metadata(row) -> RawExtrinsicMetadata: target = row["raw_extrinsic_metadata.target"] if not target.startswith("swh:1:"): warnings.warn( "Fetching raw_extrinsic_metadata row with URL target", DeprecationWarning ) target = str(Origin(url=target).swhid()) return RawExtrinsicMetadata( target=ExtendedSWHID.from_string(target), 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["raw_extrinsic_metadata.metadata"], origin=row["origin"], visit=row["visit"], snapshot=map_optional(CoreSWHID.from_string, row["snapshot"]), release=map_optional(CoreSWHID.from_string, row["release"]), revision=map_optional(CoreSWHID.from_string, row["revision"]), path=row["path"], directory=map_optional(CoreSWHID.from_string, row["directory"]), ) def db_to_extid(row) -> ExtID: return ExtID( extid=row["extid"], extid_type=row["extid_type"], extid_version=row.get("extid_version", 0), target=CoreSWHID( object_id=row["target"], object_type=SwhidObjectType[row["target_type"].upper()], ), ) diff --git a/swh/storage/postgresql/db.py b/swh/storage/postgresql/db.py index 3d66868c..51f0b4de 100644 --- a/swh/storage/postgresql/db.py +++ b/swh/storage/postgresql/db.py @@ -1,1503 +1,1508 @@ # Copyright (C) 2015-2021 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 logging import random import select from typing import Any, Dict, Iterable, List, Optional, Tuple from swh.core.db import BaseDb from swh.core.db.db_utils import execute_values_generator from swh.core.db.db_utils import jsonize as _jsonize from swh.core.db.db_utils import stored_procedure from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.model.model import SHA1_SIZE, OriginVisit, OriginVisitStatus, Sha1Git from swh.model.swhids import ObjectType from swh.storage.interface import ListOrder logger = logging.getLogger(__name__) def jsonize(d): return _jsonize(dict(d) if d is not None else None) class Db(BaseDb): """Proxy to the SWH DB, with wrappers around stored procedures """ - current_version = 178 + current_version = 180 def mktemp_dir_entry(self, entry_type, cur=None): self._cursor(cur).execute( "SELECT swh_mktemp_dir_entry(%s)", (("directory_entry_%s" % entry_type),) ) @stored_procedure("swh_mktemp_revision") def mktemp_revision(self, cur=None): pass @stored_procedure("swh_mktemp_release") def mktemp_release(self, cur=None): pass @stored_procedure("swh_mktemp_snapshot_branch") def mktemp_snapshot_branch(self, cur=None): pass def register_listener(self, notify_queue, cur=None): """Register a listener for NOTIFY queue `notify_queue`""" self._cursor(cur).execute("LISTEN %s" % notify_queue) def listen_notifies(self, timeout): """Listen to notifications for `timeout` seconds""" if select.select([self.conn], [], [], timeout) == ([], [], []): return else: self.conn.poll() while self.conn.notifies: yield self.conn.notifies.pop(0) @stored_procedure("swh_content_add") def content_add_from_temp(self, cur=None): pass @stored_procedure("swh_directory_add") def directory_add_from_temp(self, cur=None): pass @stored_procedure("swh_skipped_content_add") def skipped_content_add_from_temp(self, cur=None): pass @stored_procedure("swh_revision_add") def revision_add_from_temp(self, cur=None): pass @stored_procedure("swh_extid_add") def extid_add_from_temp(self, cur=None): pass @stored_procedure("swh_release_add") def release_add_from_temp(self, cur=None): pass def content_update_from_temp(self, keys_to_update, cur=None): cur = self._cursor(cur) cur.execute( """select swh_content_update(ARRAY[%s] :: text[])""" % keys_to_update ) content_get_metadata_keys = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "status", ] content_add_keys = content_get_metadata_keys + ["ctime"] skipped_content_keys = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "reason", "status", "origin", ] def content_get_metadata_from_hashes( self, hashes: List[bytes], algo: str, cur=None ): cur = self._cursor(cur) assert algo in DEFAULT_ALGORITHMS query = f""" select {", ".join(self.content_get_metadata_keys)} from (values %s) as t (hash) inner join content on (content.{algo}=hash) """ yield from execute_values_generator( cur, query, ((hash_,) for hash_ in hashes), ) def content_get_range(self, start, end, limit=None, cur=None): """Retrieve contents within range [start, end]. """ cur = self._cursor(cur) query = """select %s from content where %%s <= sha1 and sha1 <= %%s order by sha1 limit %%s""" % ", ".join( self.content_get_metadata_keys ) cur.execute(query, (start, end, limit)) yield from cur content_hash_keys = ["sha1", "sha1_git", "sha256", "blake2s256"] def content_missing_from_list(self, contents, cur=None): cur = self._cursor(cur) keys = ", ".join(self.content_hash_keys) equality = " AND ".join( ("t.%s = c.%s" % (key, key)) for key in self.content_hash_keys ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(%s) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE %s ) """ % (keys, keys, equality), (tuple(c[key] for key in self.content_hash_keys) for c in contents), ) def content_missing_per_sha1(self, sha1s, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT t.sha1 FROM (VALUES %s) AS t(sha1) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE c.sha1 = t.sha1 )""", ((sha1,) for sha1 in sha1s), ) def content_missing_per_sha1_git(self, contents, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT t.sha1_git FROM (VALUES %s) AS t(sha1_git) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE c.sha1_git = t.sha1_git )""", ((sha1,) for sha1 in contents), ) def skipped_content_missing(self, contents, cur=None): if not contents: return [] cur = self._cursor(cur) query = """SELECT * FROM (VALUES %s) AS t (%s) WHERE not exists (SELECT 1 FROM skipped_content s WHERE s.sha1 is not distinct from t.sha1::sha1 and s.sha1_git is not distinct from t.sha1_git::sha1 and s.sha256 is not distinct from t.sha256::bytea);""" % ( (", ".join("%s" for _ in contents)), ", ".join(self.content_hash_keys), ) cur.execute( query, [tuple(cont[key] for key in self.content_hash_keys) for cont in contents], ) yield from cur def snapshot_exists(self, snapshot_id, cur=None): """Check whether a snapshot with the given id exists""" cur = self._cursor(cur) cur.execute("""SELECT 1 FROM snapshot where id=%s""", (snapshot_id,)) return bool(cur.fetchone()) def snapshot_missing_from_list(self, snapshots, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM snapshot d WHERE d.id = t.id ) """, ((id,) for id in snapshots), ) def snapshot_add(self, snapshot_id, cur=None): """Add a snapshot from the temporary table""" cur = self._cursor(cur) cur.execute("""SELECT swh_snapshot_add(%s)""", (snapshot_id,)) snapshot_count_cols = ["target_type", "count"] def snapshot_count_branches( self, snapshot_id, branch_name_exclude_prefix=None, cur=None, ): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_count_branches(%%s, %%s) """ % ", ".join( self.snapshot_count_cols ) cur.execute(query, (snapshot_id, branch_name_exclude_prefix)) yield from cur snapshot_get_cols = ["snapshot_id", "name", "target", "target_type"] def snapshot_get_by_id( self, snapshot_id, branches_from=b"", branches_count=None, target_types=None, branch_name_include_substring=None, branch_name_exclude_prefix=None, cur=None, ): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_get_by_id(%%s, %%s, %%s, %%s :: snapshot_target[], %%s, %%s) """ % ", ".join( self.snapshot_get_cols ) cur.execute( query, ( snapshot_id, branches_from, branches_count, target_types, branch_name_include_substring, branch_name_exclude_prefix, ), ) yield from cur def snapshot_get_random(self, cur=None): return self._get_random_row_from_table("snapshot", ["id"], "id", cur) content_find_cols = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "ctime", "status", ] def content_find( self, sha1: Optional[bytes] = None, sha1_git: Optional[bytes] = None, sha256: Optional[bytes] = None, blake2s256: Optional[bytes] = None, cur=None, ): """Find the content optionally on a combination of the following checksums sha1, sha1_git, sha256 or blake2s256. Args: sha1: sha1 content git_sha1: the sha1 computed `a la git` sha1 of the content sha256: sha256 content blake2s256: blake2s256 content Returns: The tuple (sha1, sha1_git, sha256, blake2s256) if found or None. """ cur = self._cursor(cur) checksum_dict = { "sha1": sha1, "sha1_git": sha1_git, "sha256": sha256, "blake2s256": blake2s256, } query_parts = [f"SELECT {','.join(self.content_find_cols)} FROM content WHERE "] query_params = [] where_parts = [] # Adds only those keys which have values exist for algorithm in checksum_dict: if checksum_dict[algorithm] is not None: where_parts.append(f"{algorithm} = %s") query_params.append(checksum_dict[algorithm]) query_parts.append(" AND ".join(where_parts)) query = "\n".join(query_parts) cur.execute(query, query_params) content = cur.fetchall() return content def content_get_random(self, cur=None): return self._get_random_row_from_table("content", ["sha1_git"], "sha1_git", cur) def directory_missing_from_list(self, directories, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM directory d WHERE d.id = t.id ) """, ((id,) for id in directories), ) directory_ls_cols = [ "dir_id", "type", "target", "name", "perms", "status", "sha1", "sha1_git", "sha256", "length", ] def directory_walk_one(self, directory, cur=None): cur = self._cursor(cur) cols = ", ".join(self.directory_ls_cols) query = "SELECT %s FROM swh_directory_walk_one(%%s)" % cols cur.execute(query, (directory,)) yield from cur def directory_walk(self, directory, cur=None): cur = self._cursor(cur) cols = ", ".join(self.directory_ls_cols) query = "SELECT %s FROM swh_directory_walk(%%s)" % cols cur.execute(query, (directory,)) yield from cur def directory_entry_get_by_path(self, directory, paths, cur=None): """Retrieve a directory entry by path. """ cur = self._cursor(cur) cols = ", ".join(self.directory_ls_cols) query = "SELECT %s FROM swh_find_directory_entry_by_path(%%s, %%s)" % cols cur.execute(query, (directory, paths)) data = cur.fetchone() if set(data) == {None}: return None return data directory_get_entries_cols = ["type", "target", "name", "perms"] def directory_get_entries(self, directory: Sha1Git, cur=None) -> List[Tuple]: cur = self._cursor(cur) cur.execute( "SELECT * FROM swh_directory_get_entries(%s::sha1_git)", (directory,) ) return list(cur) def directory_get_random(self, cur=None): return self._get_random_row_from_table("directory", ["id"], "id", cur) def revision_missing_from_list(self, revisions, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM revision r WHERE r.id = t.id ) """, ((id,) for id in revisions), ) revision_add_cols = [ "id", "date", "date_offset", "date_neg_utc_offset", + "date_offset_bytes", "committer_date", "committer_date_offset", "committer_date_neg_utc_offset", + "committer_date_offset_bytes", "type", "directory", "message", "author_fullname", "author_name", "author_email", "committer_fullname", "committer_name", "committer_email", "metadata", "synthetic", "extra_headers", + "raw_manifest", ] revision_get_cols = revision_add_cols + ["parents"] def origin_visit_add(self, origin, ts, type, cur=None): """Add a new origin_visit for origin origin at timestamp ts. Args: origin: origin concerned by the visit ts: the date of the visit type: type of loader for the visit Returns: The new visit index step for that origin """ cur = self._cursor(cur) self._cursor(cur).execute( "SELECT swh_origin_visit_add(%s, %s, %s)", (origin, ts, type) ) return cur.fetchone()[0] origin_visit_status_cols = [ "origin", "visit", "date", "type", "status", "snapshot", "metadata", ] def origin_visit_status_add( self, visit_status: OriginVisitStatus, cur=None ) -> None: """Add new origin visit status """ assert self.origin_visit_status_cols[0] == "origin" assert self.origin_visit_status_cols[-1] == "metadata" cols = self.origin_visit_status_cols[1:-1] cur = self._cursor(cur) cur.execute( f"WITH origin_id as (select id from origin where url=%s) " f"INSERT INTO origin_visit_status " f"(origin, {', '.join(cols)}, metadata) " f"VALUES ((select id from origin_id), " f"{', '.join(['%s']*len(cols))}, %s) " f"ON CONFLICT (origin, visit, date) do nothing", [visit_status.origin] + [getattr(visit_status, key) for key in cols] + [jsonize(visit_status.metadata)], ) origin_visit_cols = ["origin", "visit", "date", "type"] def origin_visit_add_with_id(self, origin_visit: OriginVisit, cur=None) -> None: """Insert origin visit when id are already set """ ov = origin_visit assert ov.visit is not None cur = self._cursor(cur) query = """INSERT INTO origin_visit ({cols}) VALUES ((select id from origin where url=%s), {values}) ON CONFLICT (origin, visit) DO NOTHING""".format( cols=", ".join(self.origin_visit_cols), values=", ".join("%s" for col in self.origin_visit_cols[1:]), ) cur.execute(query, (ov.origin, ov.visit, ov.date, ov.type)) origin_visit_get_cols = [ "origin", "visit", "date", "type", "status", "metadata", "snapshot", ] origin_visit_select_cols = [ "o.url AS origin", "ov.visit", "ov.date", "ov.type AS type", "ovs.status", "ovs.snapshot", "ovs.metadata", ] origin_visit_status_select_cols = [ "o.url AS origin", "ovs.visit", "ovs.date", "ovs.type AS type", "ovs.status", "ovs.snapshot", "ovs.metadata", ] def _make_origin_visit_status( self, row: Optional[Tuple[Any]] ) -> Optional[Dict[str, Any]]: """Make an origin_visit_status dict out of a row """ if not row: return None return dict(zip(self.origin_visit_status_cols, row)) def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, cur=None, ) -> Optional[Dict[str, Any]]: """Given an origin visit id, return its latest origin_visit_status """ cur = self._cursor(cur) query_parts = [ "SELECT %s" % ", ".join(self.origin_visit_status_select_cols), "FROM origin_visit_status ovs ", "INNER JOIN origin o ON o.id = ovs.origin", ] query_parts.append("WHERE o.url = %s") query_params: List[Any] = [origin_url] query_parts.append("AND ovs.visit = %s") query_params.append(visit) if require_snapshot: query_parts.append("AND ovs.snapshot is not null") if allowed_statuses: query_parts.append("AND ovs.status IN %s") query_params.append(tuple(allowed_statuses)) query_parts.append("ORDER BY ovs.date DESC LIMIT 1") query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) row = cur.fetchone() return self._make_origin_visit_status(row) def origin_visit_status_get_range( self, origin: str, visit: int, date_from: Optional[datetime.datetime], order: ListOrder, limit: int, cur=None, ): """Retrieve visit_status rows for visit (origin, visit) in a paginated way. """ cur = self._cursor(cur) query_parts = [ f"SELECT {', '.join(self.origin_visit_status_select_cols)} " "FROM origin_visit_status ovs ", "INNER JOIN origin o ON o.id = ovs.origin ", ] query_parts.append("WHERE o.url = %s AND ovs.visit = %s ") query_params: List[Any] = [origin, visit] if date_from is not None: op_comparison = ">=" if order == ListOrder.ASC else "<=" query_parts.append(f"and ovs.date {op_comparison} %s ") query_params.append(date_from) if order == ListOrder.ASC: query_parts.append("ORDER BY ovs.date ASC ") elif order == ListOrder.DESC: query_parts.append("ORDER BY ovs.date DESC ") else: assert False query_parts.append("LIMIT %s") query_params.append(limit) query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) yield from cur def origin_visit_get_range( self, origin: str, visit_from: int, order: ListOrder, limit: int, cur=None, ): cur = self._cursor(cur) origin_visit_cols = ["o.url as origin", "ov.visit", "ov.date", "ov.type"] query_parts = [ f"SELECT {', '.join(origin_visit_cols)} FROM origin_visit ov ", "INNER JOIN origin o ON o.id = ov.origin ", ] query_parts.append("WHERE o.url = %s") query_params: List[Any] = [origin] if visit_from > 0: op_comparison = ">" if order == ListOrder.ASC else "<" query_parts.append(f"and ov.visit {op_comparison} %s") query_params.append(visit_from) if order == ListOrder.ASC: query_parts.append("ORDER BY ov.visit ASC") elif order == ListOrder.DESC: query_parts.append("ORDER BY ov.visit DESC") query_parts.append("LIMIT %s") query_params.append(limit) query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) yield from cur def origin_visit_get(self, origin_id, visit_id, cur=None): """Retrieve information on visit visit_id of origin origin_id. Args: origin_id: the origin concerned visit_id: The visit step for that origin Returns: The origin_visit information """ cur = self._cursor(cur) query = """\ SELECT %s FROM origin_visit ov INNER JOIN origin o ON o.id = ov.origin INNER JOIN origin_visit_status ovs USING (origin, visit) WHERE o.url = %%s AND ov.visit = %%s ORDER BY ovs.date DESC LIMIT 1 """ % ( ", ".join(self.origin_visit_select_cols) ) cur.execute(query, (origin_id, visit_id)) r = cur.fetchall() if not r: return None return r[0] def origin_visit_find_by_date(self, origin, visit_date, cur=None): cur = self._cursor(cur) cur.execute( "SELECT * FROM swh_visit_find_by_date(%s, %s)", (origin, visit_date) ) rows = cur.fetchall() if rows: visit = dict(zip(self.origin_visit_get_cols, rows[0])) visit["origin"] = origin return visit def origin_visit_exists(self, origin_id, visit_id, cur=None): """Check whether an origin visit with the given ids exists""" cur = self._cursor(cur) query = "SELECT 1 FROM origin_visit where origin = %s AND visit = %s" cur.execute(query, (origin_id, visit_id)) return bool(cur.fetchone()) def origin_visit_get_latest( self, origin_id: str, type: Optional[str], allowed_statuses: Optional[Iterable[str]], require_snapshot: bool, cur=None, ): """Retrieve the most recent origin_visit of the given origin, with optional filters. Args: origin_id: the origin concerned type: Optional visit type to filter on allowed_statuses: the visit statuses allowed for the returned visit require_snapshot (bool): If True, only a visit with a known snapshot will be returned. Returns: The origin_visit information, or None if no visit matches. """ cur = self._cursor(cur) query_parts = [ "SELECT %s" % ", ".join(self.origin_visit_select_cols), "FROM origin_visit ov ", "INNER JOIN origin o ON o.id = ov.origin", "INNER JOIN origin_visit_status ovs USING (origin, visit)", ] query_parts.append("WHERE o.url = %s") query_params: List[Any] = [origin_id] if type is not None: query_parts.append("AND ov.type = %s") query_params.append(type) if require_snapshot: query_parts.append("AND ovs.snapshot is not null") if allowed_statuses: query_parts.append("AND ovs.status IN %s") query_params.append(tuple(allowed_statuses)) query_parts.append( "ORDER BY ov.date DESC, ov.visit DESC, ovs.date DESC LIMIT 1" ) query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) r = cur.fetchone() if not r: return None return r def origin_visit_get_random(self, type, cur=None): """Randomly select one origin visit that was full and in the last 3 months """ cur = self._cursor(cur) columns = ",".join(self.origin_visit_select_cols) query = f"""select {columns} from origin_visit ov inner join origin o on ov.origin=o.id inner join origin_visit_status ovs using (origin, visit) where ovs.status='full' and ov.type=%s and ov.date > now() - '3 months'::interval and random() < 0.1 limit 1 """ cur.execute(query, (type,)) return cur.fetchone() @staticmethod def mangle_query_key(key, main_table): if key == "id": return "t.id" if key == "parents": return """ ARRAY( SELECT rh.parent_id::bytea FROM revision_history rh WHERE rh.id = t.id ORDER BY rh.parent_rank )""" if "_" not in key: return "%s.%s" % (main_table, key) head, tail = key.split("_", 1) if head in ("author", "committer") and tail in ( "name", "email", "id", "fullname", ): return "%s.%s" % (head, tail) return "%s.%s" % (main_table, key) def revision_get_from_list(self, revisions, cur=None): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "revision") for k in self.revision_get_cols ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(sortkey, id) LEFT JOIN revision ON t.id = revision.id LEFT JOIN person author ON revision.author = author.id LEFT JOIN person committer ON revision.committer = committer.id ORDER BY sortkey """ % query_keys, ((sortkey, id) for sortkey, id in enumerate(revisions)), ) extid_cols = ["extid", "extid_version", "extid_type", "target", "target_type"] def extid_get_from_extid_list( self, extid_type: str, ids: List[bytes], version: Optional[int] = None, cur=None ): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "extid") for k in self.extid_cols ) filter_query = "" if version is not None: filter_query = cur.mogrify( f"WHERE extid_version={version}", (version,) ).decode() sql = f""" SELECT {query_keys} FROM (VALUES %s) as t(sortkey, extid, extid_type) LEFT JOIN extid USING (extid, extid_type) {filter_query} ORDER BY sortkey """ yield from execute_values_generator( cur, sql, (((sortkey, extid, extid_type) for sortkey, extid in enumerate(ids))), ) def extid_get_from_swhid_list( self, target_type: str, ids: List[bytes], extid_version: Optional[int] = None, extid_type: Optional[str] = None, cur=None, ): cur = self._cursor(cur) target_type = ObjectType( target_type ).name.lower() # aka "rev" -> "revision", ... query_keys = ", ".join( self.mangle_query_key(k, "extid") for k in self.extid_cols ) filter_query = "" if extid_version is not None and extid_type is not None: filter_query = cur.mogrify( "WHERE extid_version=%s AND extid_type=%s", (extid_version, extid_type,) ).decode() sql = f""" SELECT {query_keys} FROM (VALUES %s) as t(sortkey, target, target_type) LEFT JOIN extid USING (target, target_type) {filter_query} ORDER BY sortkey """ yield from execute_values_generator( cur, sql, (((sortkey, target, target_type) for sortkey, target in enumerate(ids))), template=b"(%s,%s,%s::object_type)", ) def revision_log(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_log(%%s, %%s) """ % ", ".join( self.revision_get_cols ) cur.execute(query, (root_revisions, limit)) yield from cur revision_shortlog_cols = ["id", "parents"] def revision_shortlog(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_list(%%s, %%s) """ % ", ".join( self.revision_shortlog_cols ) cur.execute(query, (root_revisions, limit)) yield from cur def revision_get_random(self, cur=None): return self._get_random_row_from_table("revision", ["id"], "id", cur) def release_missing_from_list(self, releases, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM release r WHERE r.id = t.id ) """, ((id,) for id in releases), ) object_find_by_sha1_git_cols = ["sha1_git", "type"] def object_find_by_sha1_git(self, ids, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ WITH t (sha1_git) AS (VALUES %s), known_objects as (( select id as sha1_git, 'release'::object_type as type, object_id from release r where exists (select 1 from t where t.sha1_git = r.id) ) union all ( select id as sha1_git, 'revision'::object_type as type, object_id from revision r where exists (select 1 from t where t.sha1_git = r.id) ) union all ( select id as sha1_git, 'directory'::object_type as type, object_id from directory d where exists (select 1 from t where t.sha1_git = d.id) ) union all ( select sha1_git as sha1_git, 'content'::object_type as type, object_id from content c where exists (select 1 from t where t.sha1_git = c.sha1_git) )) select t.sha1_git as sha1_git, k.type from t left join known_objects k on t.sha1_git = k.sha1_git """, ((id,) for id in ids), ) def stat_counters(self, cur=None): cur = self._cursor(cur) cur.execute("SELECT * FROM swh_stat_counters()") yield from cur def origin_add(self, url, cur=None): """Insert a new origin and return the new identifier.""" insert = """INSERT INTO origin (url) values (%s) ON CONFLICT DO NOTHING """ cur.execute(insert, (url,)) return cur.rowcount origin_cols = ["url"] def origin_get_by_url(self, origins, cur=None): """Retrieve origin `(type, url)` from urls if found.""" cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(url) LEFT JOIN origin ON t.url = origin.url """ % ",".join( "origin." + col for col in self.origin_cols ) yield from execute_values_generator(cur, query, ((url,) for url in origins)) def origin_get_by_sha1(self, sha1s, cur=None): """Retrieve origin urls from sha1s if found.""" cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(sha1) LEFT JOIN origin ON t.sha1 = digest(origin.url, 'sha1') """ % ",".join( "origin." + col for col in self.origin_cols ) yield from execute_values_generator(cur, query, ((sha1,) for sha1 in sha1s)) def origin_id_get_by_url(self, origins, cur=None): """Retrieve origin `(type, url)` from urls if found.""" cur = self._cursor(cur) query = """SELECT id FROM (VALUES %s) as t(url) LEFT JOIN origin ON t.url = origin.url """ for row in execute_values_generator(cur, query, ((url,) for url in origins)): yield row[0] origin_get_range_cols = ["id", "url"] def origin_get_range(self, origin_from: int = 1, origin_count: int = 100, cur=None): """Retrieve ``origin_count`` origins whose ids are greater or equal than ``origin_from``. Origins are sorted by id before retrieving them. Args: origin_from: the minimum id of origins to retrieve origin_count: the maximum number of origins to retrieve """ cur = self._cursor(cur) query = """SELECT %s FROM origin WHERE id >= %%s ORDER BY id LIMIT %%s """ % ",".join( self.origin_get_range_cols ) cur.execute(query, (origin_from, origin_count)) yield from cur def _origin_query( self, url_pattern, count=False, offset=0, limit=50, regexp=False, with_visit=False, visit_types=None, cur=None, ): """ Method factorizing query creation for searching and counting origins. """ cur = self._cursor(cur) if count: origin_cols = "COUNT(*)" order_clause = "" else: origin_cols = ",".join(self.origin_cols) order_clause = "ORDER BY id" if not regexp: operator = "ILIKE" query_params = [f"%{url_pattern}%"] else: operator = "~*" query_params = [url_pattern] query = f""" WITH filtered_origins AS ( SELECT * FROM origin WHERE url {operator} %s {order_clause} ) SELECT {origin_cols} FROM filtered_origins AS o """ if with_visit or visit_types: visit_predicat = ( """ INNER JOIN origin_visit_status ovs USING (origin, visit) INNER JOIN snapshot ON ovs.snapshot=snapshot.id """ if with_visit else "" ) type_predicat = ( f"AND ov.type=any(ARRAY{visit_types})" if visit_types else "" ) query += f""" WHERE EXISTS ( SELECT 1 FROM origin_visit ov {visit_predicat} WHERE ov.origin=o.id {type_predicat} ) """ if not count: query += "OFFSET %s LIMIT %s" query_params.extend([offset, limit]) cur.execute(query, query_params) def origin_search( self, url_pattern: str, offset: int = 0, limit: int = 50, regexp: bool = False, with_visit: bool = False, visit_types: Optional[List[str]] = None, cur=None, ): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. Args: url_pattern: the string pattern to search for in origin urls offset: number of found origins to skip before returning results limit: the maximum number of found origins to return regexp: if True, consider the provided pattern as a regular expression and returns origins whose urls match it with_visit: if True, filter out origins with no visit """ self._origin_query( url_pattern, offset=offset, limit=limit, regexp=regexp, with_visit=with_visit, visit_types=visit_types, cur=cur, ) yield from cur def origin_count(self, url_pattern, regexp=False, with_visit=False, cur=None): """Count origins whose urls contain a provided string pattern or match a provided regular expression. The pattern search in origin urls is performed in a case insensitive way. Args: url_pattern (str): the string pattern to search for in origin urls regexp (bool): if True, consider the provided pattern as a regular expression and returns origins whose urls match it with_visit (bool): if True, filter out origins with no visit """ self._origin_query( url_pattern, count=True, regexp=regexp, with_visit=with_visit, cur=cur ) return cur.fetchone()[0] release_add_cols = [ "id", "target", "target_type", "date", "date_offset", "date_neg_utc_offset", + "date_offset_bytes", "name", "comment", "synthetic", + "raw_manifest", "author_fullname", "author_name", "author_email", ] release_get_cols = release_add_cols def origin_snapshot_get_all(self, origin_url: str, cur=None) -> Iterable[Sha1Git]: cur = self._cursor(cur) query = f"""\ SELECT DISTINCT snapshot FROM origin_visit_status ovs INNER JOIN origin o ON o.id = ovs.origin WHERE o.url = '{origin_url}' and snapshot IS NOT NULL; """ cur.execute(query) yield from map(lambda row: row[0], cur) def release_get_from_list(self, releases, cur=None): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "release") for k in self.release_get_cols ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(sortkey, id) LEFT JOIN release ON t.id = release.id LEFT JOIN person author ON release.author = author.id ORDER BY sortkey """ % query_keys, ((sortkey, id) for sortkey, id in enumerate(releases)), ) def release_get_random(self, cur=None): return self._get_random_row_from_table("release", ["id"], "id", cur) _raw_extrinsic_metadata_context_cols = [ "origin", "visit", "snapshot", "release", "revision", "path", "directory", ] """The list of context columns for all artifact types.""" _raw_extrinsic_metadata_insert_cols = [ "id", "type", "target", "authority_id", "fetcher_id", "discovery_date", "format", "metadata", *_raw_extrinsic_metadata_context_cols, ] """List of columns of the raw_extrinsic_metadata table, used when writing metadata.""" _raw_extrinsic_metadata_insert_query = f""" INSERT INTO raw_extrinsic_metadata ({', '.join(_raw_extrinsic_metadata_insert_cols)}) VALUES ({', '.join('%s' for _ in _raw_extrinsic_metadata_insert_cols)}) ON CONFLICT (id) DO NOTHING """ raw_extrinsic_metadata_get_cols = [ "raw_extrinsic_metadata.target", "raw_extrinsic_metadata.type", "discovery_date", "metadata_authority.type", "metadata_authority.url", "metadata_fetcher.id", "metadata_fetcher.name", "metadata_fetcher.version", *_raw_extrinsic_metadata_context_cols, "format", "raw_extrinsic_metadata.metadata", ] """List of columns of the raw_extrinsic_metadata, metadata_authority, and metadata_fetcher tables, used when reading object metadata.""" _raw_extrinsic_metadata_select_query = f""" SELECT {', '.join(raw_extrinsic_metadata_get_cols)} FROM raw_extrinsic_metadata INNER JOIN metadata_authority ON (metadata_authority.id=authority_id) INNER JOIN metadata_fetcher ON (metadata_fetcher.id=fetcher_id) """ def raw_extrinsic_metadata_add( self, id: bytes, type: str, target: str, discovery_date: datetime.datetime, authority_id: int, fetcher_id: int, format: str, metadata: bytes, origin: Optional[str], visit: Optional[int], snapshot: Optional[str], release: Optional[str], revision: Optional[str], path: Optional[bytes], directory: Optional[str], cur, ): query = self._raw_extrinsic_metadata_insert_query args: Dict[str, Any] = dict( id=id, type=type, target=target, authority_id=authority_id, fetcher_id=fetcher_id, discovery_date=discovery_date, format=format, metadata=metadata, origin=origin, visit=visit, snapshot=snapshot, release=release, revision=revision, path=path, directory=directory, ) params = [args[col] for col in self._raw_extrinsic_metadata_insert_cols] cur.execute(query, params) def raw_extrinsic_metadata_get( self, target: str, authority_id: int, after_time: Optional[datetime.datetime], after_fetcher: Optional[int], limit: int, cur, ): query_parts = [self._raw_extrinsic_metadata_select_query] query_parts.append("WHERE raw_extrinsic_metadata.target=%s AND authority_id=%s") args = [target, authority_id] if after_fetcher is not None: assert after_time query_parts.append("AND (discovery_date, fetcher_id) > (%s, %s)") args.extend([after_time, after_fetcher]) elif after_time is not None: query_parts.append("AND discovery_date > %s") args.append(after_time) query_parts.append("ORDER BY discovery_date, fetcher_id") if limit: query_parts.append("LIMIT %s") args.append(limit) cur.execute(" ".join(query_parts), args) yield from cur def raw_extrinsic_metadata_get_by_ids(self, ids: List[Sha1Git], cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, self._raw_extrinsic_metadata_select_query + "INNER JOIN (VALUES %s) AS t(id) ON t.id = raw_extrinsic_metadata.id", [(id_,) for id_ in ids], ) def raw_extrinsic_metadata_get_authorities(self, id: str, cur=None): cur = self._cursor(cur) cur.execute( """ SELECT DISTINCT metadata_authority.type, metadata_authority.url FROM raw_extrinsic_metadata INNER JOIN metadata_authority ON (metadata_authority.id=authority_id) WHERE raw_extrinsic_metadata.target = %s """, (id,), ) yield from cur metadata_fetcher_cols = ["name", "version"] def metadata_fetcher_add(self, name: str, version: str, cur=None) -> None: cur = self._cursor(cur) cur.execute( "INSERT INTO metadata_fetcher (name, version) " "VALUES (%s, %s) ON CONFLICT DO NOTHING", (name, version), ) def metadata_fetcher_get(self, name: str, version: str, cur=None): cur = self._cursor(cur) cur.execute( f"SELECT {', '.join(self.metadata_fetcher_cols)} " f"FROM metadata_fetcher " f"WHERE name=%s AND version=%s", (name, version), ) return cur.fetchone() def metadata_fetcher_get_id( self, name: str, version: str, cur=None ) -> Optional[int]: cur = self._cursor(cur) cur.execute( "SELECT id FROM metadata_fetcher WHERE name=%s AND version=%s", (name, version), ) row = cur.fetchone() if row: return row[0] else: return None metadata_authority_cols = ["type", "url"] def metadata_authority_add(self, type: str, url: str, cur=None) -> None: cur = self._cursor(cur) cur.execute( "INSERT INTO metadata_authority (type, url) " "VALUES (%s, %s) ON CONFLICT DO NOTHING", (type, url), ) def metadata_authority_get(self, type: str, url: str, cur=None): cur = self._cursor(cur) cur.execute( f"SELECT {', '.join(self.metadata_authority_cols)} " f"FROM metadata_authority " f"WHERE type=%s AND url=%s", (type, url), ) return cur.fetchone() def metadata_authority_get_id(self, type: str, url: str, cur=None) -> Optional[int]: cur = self._cursor(cur) cur.execute( "SELECT id FROM metadata_authority WHERE type=%s AND url=%s", (type, url) ) row = cur.fetchone() if row: return row[0] else: return None def _get_random_row_from_table(self, table_name, cols, id_col, cur=None): random_sha1 = bytes(random.randint(0, 255) for _ in range(SHA1_SIZE)) cur = self._cursor(cur) query = """ (SELECT {cols} FROM {table} WHERE {id_col} >= %s ORDER BY {id_col} LIMIT 1) UNION (SELECT {cols} FROM {table} WHERE {id_col} < %s ORDER BY {id_col} DESC LIMIT 1) LIMIT 1 """.format( cols=", ".join(cols), table=table_name, id_col=id_col ) cur.execute(query, (random_sha1, random_sha1)) row = cur.fetchone() if row: return row[0] dbversion_cols = ["version", "release", "description"] def dbversion(self): with self.transaction() as cur: cur.execute( f""" SELECT {', '.join(self.dbversion_cols)} FROM dbversion ORDER BY version DESC LIMIT 1 """ ) return dict(zip(self.dbversion_cols, cur.fetchone())) def check_dbversion(self): dbversion = self.dbversion()["version"] if dbversion != self.current_version: logger.warning( "database dbversion (%s) != %s current_version (%s)", dbversion, __name__, self.current_version, ) return dbversion == self.current_version diff --git a/swh/storage/postgresql/storage.py b/swh/storage/postgresql/storage.py index b9fe715a..98c9f243 100644 --- a/swh/storage/postgresql/storage.py +++ b/swh/storage/postgresql/storage.py @@ -1,1596 +1,1596 @@ # Copyright (C) 2015-2021 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 base64 from collections import defaultdict import contextlib from contextlib import contextmanager import datetime import itertools import operator from typing import Any, Counter, Dict, Iterable, List, Optional, Sequence, Tuple import attr import psycopg2 import psycopg2.errors import psycopg2.pool from swh.core.api.serializers import msgpack_dumps, msgpack_loads from swh.core.db.common import db_transaction, db_transaction_generator from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.model.model import ( SHA1_SIZE, Content, Directory, DirectoryEntry, ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1, Sha1Git, SkippedContent, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.exc import HashCollision, StorageArgumentException, StorageDBError from swh.storage.interface import ( VISIT_STATUSES, ListOrder, PagedResult, PartialBranches, ) from swh.storage.metrics import process_metrics, send_metric, timed from swh.storage.objstorage import ObjStorage from swh.storage.utils import ( extract_collision_hash, get_partition_bounds_bytes, map_optional, now, ) from swh.storage.writer import JournalWriter from . import converters from .db import Db # 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 = ( 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 psycopg2.errors.UniqueViolation: # This only happens because of concurrent insertions, but it is # a subclass of IntegrityError; so we need to catch and reraise it # before the next clause converts it to StorageArgumentException. raise except 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) # See comment below self._db.cursor().execute("SET TIME ZONE 'UTC'") 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: db = Db.from_pool(self._pool) # Workaround for psycopg2 < 2.9.0 not handling fractional timezones, # which may happen on old revision/release dates on systems configured # with non-UTC timezones. # https://www.psycopg.org/docs/usage.html#time-zones-handling db.cursor().execute("SET TIME ZONE 'UTC'") return db 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: bool, db: Db, cur=None) -> bool: if not self.objstorage.check_config(check_write=check_write): return False if not db.check_dbversion(): 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: List[Content]) -> Dict[str, int]: ctime = now() contents = [attr.evolve(c, ctime=ctime) for c in content] # Must add to the objstorage before the DB and journal. Otherwise: # 1. in case of a crash the DB may "believe" we have the content, but # we didn't have time to write to the objstorage before the crash # 2. the objstorage mirroring, which reads from the journal, may attempt to # read from the objstorage before we finished writing it 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, contents: List[Dict[str, Any]], keys: List[str] = [], *, db: Db, cur=None ) -> 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(contents) db.mktemp("content", cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) with convert_validation_exceptions(): db.copy_to(contents, "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: List[Content], *, db: Db, cur=None ) -> Dict[str, int]: missing = self.content_missing( (c.to_dict() for c in content), key_hash="sha1_git", db=db, cur=cur, ) contents = [c for c in content 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_data(self, content: Sha1) -> Optional[bytes]: # FIXME: Make this method support slicing the `data` return self.objstorage.content_get(content) @timed @db_transaction() def content_get_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, *, db: Db, cur=None, ) -> PagedResult[Content]: 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 next_page_token: Optional[str] = None contents = [] for counter, row in enumerate(db.content_get_range(start, end, limit + 1, cur)): row_d = dict(zip(db.content_get_metadata_keys, row)) content = Content(**row_d) if counter >= limit: # take the last content for the next page starting from this next_page_token = hash_to_hex(content.sha1) break contents.append(content) assert len(contents) <= limit return PagedResult(results=contents, next_page_token=next_page_token) @timed @db_transaction(statement_timeout=500) def content_get( self, contents: List[bytes], algo: str = "sha1", *, db: Db, cur=None ) -> List[Optional[Content]]: contents_by_hash: Dict[bytes, Optional[Content]] = {} if algo not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "algo should be one of {','.join(DEFAULT_ALGORITHMS)}" ) rows = db.content_get_metadata_from_hashes(contents, algo, cur) key = operator.attrgetter(algo) for row in rows: row_d = dict(zip(db.content_get_metadata_keys, row)) content = Content(**row_d) contents_by_hash[key(content)] = content return [contents_by_hash.get(sha1) for sha1 in contents] @timed @db_transaction_generator() def content_missing( self, contents: List[Dict[str, Any]], key_hash: str = "sha1", *, db: Db, cur=None, ) -> Iterable[bytes]: if key_hash not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "key_hash should be one of {','.join(DEFAULT_ALGORITHMS)}" ) keys = db.content_hash_keys key_hash_idx = keys.index(key_hash) for obj in db.content_missing_from_list(contents, cur): yield obj[key_hash_idx] @timed @db_transaction_generator() def content_missing_per_sha1( self, contents: List[bytes], *, db: Db, cur=None ) -> Iterable[bytes]: 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: List[bytes], *, db: Db, cur=None ) -> Iterable[Sha1Git]: for obj in db.content_missing_per_sha1_git(contents, cur): yield obj[0] @timed @db_transaction() def content_find( self, content: Dict[str, Any], *, db: Db, cur=None ) -> List[Content]: if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( "content keys must contain at least one " f"of: {', '.join(sorted(DEFAULT_ALGORITHMS))}" ) rows = db.content_find( sha1=content.get("sha1"), sha1_git=content.get("sha1_git"), sha256=content.get("sha256"), blake2s256=content.get("blake2s256"), cur=cur, ) contents = [] for row in rows: row_d = dict(zip(db.content_find_cols, row)) contents.append(Content(**row_d)) return contents @timed @db_transaction() def content_get_random(self, *, db: Db, cur=None) -> Sha1Git: 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 def _skipped_content_add_metadata(self, db, cur, content: List[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: List[SkippedContent], *, db: Db, cur=None ) -> Dict[str, int]: 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: List[Dict[str, Any]], *, db: Db, cur=None ) -> Iterable[Dict[str, Any]]: 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: List[Directory], *, db: Db, cur=None ) -> Dict[str, int]: 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) + db.copy_to(dirs_missing_dict, "tmp_directory", ["id", "raw_manifest"], 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: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: 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: Sha1Git, recursive: bool = False, *, db: Db, cur=None ) -> Iterable[Dict[str, Any]]: 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: Sha1Git, paths: List[bytes], *, db: Db, cur=None ) -> Optional[Dict[str, Any]]: res = db.directory_entry_get_by_path(directory, paths, cur) return dict(zip(db.directory_ls_cols, res)) if res else None @timed @db_transaction() def directory_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.directory_get_random(cur) @db_transaction() def directory_get_entries( self, directory_id: Sha1Git, page_token: Optional[bytes] = None, limit: int = 1000, *, db: Db, cur=None, ) -> Optional[PagedResult[DirectoryEntry]]: if list(self.directory_missing([directory_id], db=db, cur=cur)): return None if page_token is not None: raise StorageArgumentException("Unsupported page token") # TODO: actually paginate rows = db.directory_get_entries(directory_id, cur=cur) return PagedResult( results=[ DirectoryEntry(**dict(zip(db.directory_get_entries_cols, row))) for row in rows ], next_page_token=None, ) @timed @process_metrics @db_transaction() def revision_add( self, revisions: List[Revision], *, db: Db, cur=None ) -> Dict[str, int]: 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) db_revisions_filtered = list(map(converters.revision_to_db, revisions_filtered)) parents_filtered: List[Dict[str, Any]] = [] with convert_validation_exceptions(): db.copy_to( db_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: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: if not revisions: return None for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @timed @db_transaction(statement_timeout=1000) def revision_get( self, revision_ids: List[Sha1Git], *, db: Db, cur=None ) -> List[Optional[Revision]]: revisions = [] for line in db.revision_get_from_list(revision_ids, cur): revision = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) revisions.append(revision) return revisions @timed @db_transaction_generator(statement_timeout=2000) def revision_log( self, revisions: List[Sha1Git], limit: Optional[int] = None, *, db: Db, cur=None ) -> Iterable[Optional[Dict[str, Any]]]: for line in db.revision_log(revisions, limit, cur): data = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) if not data: yield None continue yield data.to_dict() @timed @db_transaction_generator(statement_timeout=2000) def revision_shortlog( self, revisions: List[Sha1Git], limit: Optional[int] = None, *, db: Db, cur=None ) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]: yield from db.revision_shortlog(revisions, limit, cur) @timed @db_transaction() def revision_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.revision_get_random(cur) @timed @db_transaction() def extid_get_from_extid( self, id_type: str, ids: List[bytes], version: Optional[int] = None, *, db: Db, cur=None, ) -> List[ExtID]: extids = [] for row in db.extid_get_from_extid_list(id_type, ids, version=version, cur=cur): if row[0] is not None: extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row)))) return extids @timed @db_transaction() def extid_get_from_target( self, target_type: ObjectType, ids: List[Sha1Git], extid_type: Optional[str] = None, extid_version: Optional[int] = None, *, db: Db, cur=None, ) -> List[ExtID]: extids = [] if (extid_version is not None and extid_type is None) or ( extid_version is None and extid_type is not None ): raise ValueError("You must provide both extid_type and extid_version") for row in db.extid_get_from_swhid_list( target_type.value, ids, extid_version=extid_version, extid_type=extid_type, cur=cur, ): if row[0] is not None: extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row)))) return extids @timed @db_transaction() def extid_add(self, ids: List[ExtID], *, db: Db, cur=None) -> Dict[str, int]: extid = [ { "extid": extid.extid, "extid_type": extid.extid_type, "extid_version": getattr(extid, "extid_version", 0), "target": extid.target.object_id, "target_type": extid.target.object_type.name.lower(), # arghh } for extid in ids ] db.mktemp("extid", cur) self.journal_writer.extid_add(ids) db.copy_to(extid, "tmp_extid", db.extid_cols, cur) # move metadata in place db.extid_add_from_temp(cur) return {"extid:add": len(extid)} @timed @process_metrics @db_transaction() def release_add( self, releases: List[Release], *, db: Db, cur=None ) -> Dict[str, int]: 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) db_releases_filtered = list(map(converters.release_to_db, releases_filtered)) with convert_validation_exceptions(): db.copy_to(db_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: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @timed @db_transaction(statement_timeout=500) def release_get( self, releases: List[Sha1Git], *, db: Db, cur=None ) -> List[Optional[Release]]: rels = [] for release in db.release_get_from_list(releases, cur): data = converters.db_to_release(dict(zip(db.release_get_cols, release))) rels.append(data if data else None) return rels @timed @db_transaction() def release_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.release_get_random(cur) @timed @process_metrics @db_transaction() def snapshot_add( self, snapshots: List[Snapshot], *, db: Db, cur=None ) -> Dict[str, int]: 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: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: 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: Sha1Git, *, db: Db, cur=None ) -> Optional[Dict[str, Any]]: d = self.snapshot_get_branches(snapshot_id) if d is None: return d return { "id": d["id"], "branches": { name: branch.to_dict() if branch else None for (name, branch) in d["branches"].items() }, "next_branch": d["next_branch"], } @timed @db_transaction(statement_timeout=2000) def snapshot_count_branches( self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None, *, db: Db, cur=None, ) -> Optional[Dict[Optional[str], int]]: return dict( [ bc for bc in db.snapshot_count_branches( snapshot_id, branch_name_exclude_prefix, cur, ) ] ) @timed @db_transaction(statement_timeout=2000) def snapshot_get_branches( self, snapshot_id: Sha1Git, branches_from: bytes = b"", branches_count: int = 1000, target_types: Optional[List[str]] = None, branch_name_include_substring: Optional[bytes] = None, branch_name_exclude_prefix: Optional[bytes] = None, *, db: Db, cur=None, ) -> Optional[PartialBranches]: if snapshot_id == EMPTY_SNAPSHOT_ID: return PartialBranches(id=snapshot_id, branches={}, next_branch=None,) if list(self.snapshot_missing([snapshot_id])): return None branches = {} next_branch = None fetched_branches = list( db.snapshot_get_by_id( snapshot_id, branches_from=branches_from, # the underlying SQL query can be quite expensive to execute for small # branches_count value, so we ensure a minimum branches limit of 10 for # optimal performances branches_count=max(branches_count + 1, 10), target_types=target_types, branch_name_include_substring=branch_name_include_substring, branch_name_exclude_prefix=branch_name_exclude_prefix, cur=cur, ) ) for row in fetched_branches[:branches_count]: branch_d = dict(zip(db.snapshot_get_cols, row)) del branch_d["snapshot_id"] name = branch_d.pop("name") if branch_d["target"] is None and branch_d["target_type"] is None: branch = None else: assert branch_d["target_type"] is not None branch = SnapshotBranch( target=branch_d["target"], target_type=TargetType(branch_d["target_type"]), ) branches[name] = branch if len(fetched_branches) > branches_count: next_branch = dict( zip(db.snapshot_get_cols, fetched_branches[branches_count]) )["name"] return PartialBranches( id=snapshot_id, branches=branches, next_branch=next_branch, ) @timed @db_transaction() def snapshot_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.snapshot_get_random(cur) @timed @db_transaction() def origin_visit_add( self, visits: List[OriginVisit], *, db: Db, cur=None ) -> Iterable[OriginVisit]: for visit in visits: origin = self.origin_get([visit.origin], db=db, cur=cur)[0] 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, type=visit.type, 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) @timed @process_metrics @db_transaction() def origin_visit_status_add( self, visit_statuses: List[OriginVisitStatus], *, db: Db, cur=None, ) -> Dict[str, int]: visit_statuses_ = [] # First round to check existence (fail early if any is ko) for visit_status in visit_statuses: origin_url = self.origin_get([visit_status.origin], db=db, cur=cur)[0] if not origin_url: raise StorageArgumentException(f"Unknown origin {visit_status.origin}") if visit_status.type is None: origin_visit = self.origin_visit_get_by( visit_status.origin, visit_status.visit, db=db, cur=cur ) if origin_visit is None: raise StorageArgumentException( f"Unknown origin visit {visit_status.visit} " f"of origin {visit_status.origin}" ) origin_visit_status = attr.evolve(visit_status, type=origin_visit.type) else: origin_visit_status = visit_status visit_statuses_.append(origin_visit_status) for visit_status in visit_statuses_: self._origin_visit_status_add(visit_status, db, cur) return {"origin_visit_status:add": len(visit_statuses_)} @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: Db, cur=None, ) -> Optional[OriginVisitStatus]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) row_d = db.origin_visit_status_get_latest( origin_url, visit, allowed_statuses, require_snapshot, cur=cur ) if not row_d: return None return OriginVisitStatus(**row_d) @timed @db_transaction(statement_timeout=500) def origin_visit_get( self, origin: str, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, *, db: Db, cur=None, ) -> PagedResult[OriginVisit]: page_token = page_token or "0" if not isinstance(order, ListOrder): raise StorageArgumentException("order must be a ListOrder value") if not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") next_page_token = None visit_from = int(page_token) visits: List[OriginVisit] = [] extra_limit = limit + 1 for row in db.origin_visit_get_range( origin, visit_from=visit_from, order=order, limit=extra_limit, cur=cur ): row_d = dict(zip(db.origin_visit_cols, row)) visits.append( OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) ) assert len(visits) <= extra_limit if len(visits) == extra_limit: visits = visits[:limit] next_page_token = str(visits[-1].visit) return PagedResult(results=visits, next_page_token=next_page_token) @timed @db_transaction(statement_timeout=500) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime, *, db: Db, cur=None ) -> Optional[OriginVisit]: row_d = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if not row_d: return None return OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) @timed @db_transaction(statement_timeout=500) def origin_visit_get_by( self, origin: str, visit: int, *, db: Db, cur=None ) -> Optional[OriginVisit]: row = db.origin_visit_get(origin, visit, cur) if row: row_d = dict(zip(db.origin_visit_get_cols, row)) return OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) 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: Db, cur=None, ) -> Optional[OriginVisit]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) row = db.origin_visit_get_latest( origin, type=type, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, cur=cur, ) if row: row_d = dict(zip(db.origin_visit_get_cols, row)) visit = OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) return visit return None @timed @db_transaction(statement_timeout=500) def origin_visit_status_get( self, origin: str, visit: int, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, *, db: Db, cur=None, ) -> PagedResult[OriginVisitStatus]: next_page_token = None date_from = None if page_token is not None: date_from = datetime.datetime.fromisoformat(page_token) visit_statuses: List[OriginVisitStatus] = [] # Take one more visit status so we can reuse it as the next page token if any for row in db.origin_visit_status_get_range( origin, visit, date_from=date_from, order=order, limit=limit + 1, cur=cur, ): row_d = dict(zip(db.origin_visit_status_cols, row)) visit_statuses.append(OriginVisitStatus(**row_d)) if len(visit_statuses) > limit: # last visit status date is the next page token next_page_token = str(visit_statuses[-1].date) # excluding that visit status from the result to respect the limit size visit_statuses = visit_statuses[:limit] return PagedResult(results=visit_statuses, next_page_token=next_page_token) @timed @db_transaction() def origin_visit_status_get_random( self, type: str, *, db: Db, cur=None ) -> Optional[OriginVisitStatus]: row = db.origin_visit_get_random(type, cur) if row is not None: row_d = dict(zip(db.origin_visit_status_cols, row)) return OriginVisitStatus(**row_d) return None @timed @db_transaction(statement_timeout=2000) def object_find_by_sha1_git( self, ids: List[Sha1Git], *, db: Db, cur=None ) -> Dict[Sha1Git, List[Dict]]: ret: Dict[Sha1Git, List[Dict]] = {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: List[str], *, db: Db, cur=None ) -> Iterable[Optional[Origin]]: rows = db.origin_get_by_url(origins, cur) result: List[Optional[Origin]] = [] for row in rows: origin_d = dict(zip(db.origin_cols, row)) url = origin_d["url"] result.append(None if url is None else Origin(url=url)) return result @timed @db_transaction(statement_timeout=500) def origin_get_by_sha1( self, sha1s: List[bytes], *, db: Db, cur=None ) -> List[Optional[Dict[str, Any]]]: return [ dict(zip(db.origin_cols, row)) if row[0] else None for row in db.origin_get_by_sha1(sha1s, cur) ] @timed @db_transaction_generator() def origin_get_range(self, origin_from=1, origin_count=100, *, db: Db, 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: Db, cur=None ) -> PagedResult[Origin]: 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) next_page_token = None origins: List[Origin] = [] # Take one more origin so we can reuse it as the next page token if any for row_d in self.origin_get_range(origin_from, limit + 1, db=db, cur=cur): origins.append(Origin(url=row_d["url"])) # keep the last_id for the pagination if needed last_id = row_d["id"] if len(origins) > limit: # data left for subsequent call # last origin id is the next page token next_page_token = str(last_id) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @timed @db_transaction() def origin_search( self, url_pattern: str, page_token: Optional[str] = None, limit: int = 50, regexp: bool = False, with_visit: bool = False, visit_types: Optional[List[str]] = None, *, db: Db, cur=None, ) -> PagedResult[Origin]: next_page_token = None offset = int(page_token) if page_token else 0 origins = [] # Take one more origin so we can reuse it as the next page token if any for origin in db.origin_search( url_pattern, offset, limit + 1, regexp, with_visit, visit_types, cur ): row_d = dict(zip(db.origin_cols, origin)) origins.append(Origin(url=row_d["url"])) if len(origins) > limit: # next offset next_page_token = str(offset + limit) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @timed @db_transaction() def origin_count( self, url_pattern: str, regexp: bool = False, with_visit: bool = False, *, db: Db, cur=None, ) -> int: return db.origin_count(url_pattern, regexp, with_visit, cur) @timed @db_transaction() def origin_snapshot_get_all( self, origin_url: str, *, db: Db, cur=None ) -> List[Sha1Git]: return list(db.origin_snapshot_get_all(origin_url, cur)) @timed @process_metrics @db_transaction() def origin_add(self, origins: List[Origin], *, db: Db, 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)) # keep only one occurrence of each given origin while keeping the list # sorted as originally given to_add = sorted(set(urls) - known_origins, key=urls.index) 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: Db, cur=None): return {k: v for (k, v) in db.stat_counters()} @db_transaction() def refresh_stat_counters(self, *, db: Db, cur=None): keys = [ "content", "directory", "directory_entry_dir", "directory_entry_file", "directory_entry_rev", "origin", "origin_visit", "person", "release", "revision", "revision_history", "skipped_content", "snapshot", ] for key in keys: cur.execute("select * from swh_update_counter(%s)", (key,)) @timed @process_metrics @db_transaction() def raw_extrinsic_metadata_add( self, metadata: List[RawExtrinsicMetadata], db, cur, ) -> Dict[str, int]: metadata = list(metadata) self.journal_writer.raw_extrinsic_metadata_add(metadata) counter = Counter[ExtendedObjectType]() 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.raw_extrinsic_metadata_add( id=metadata_entry.id, type=metadata_entry.target.object_type.name.lower(), target=str(metadata_entry.target), 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.target.object_type] += 1 return { f"{type.value}_metadata:add": count for (type, count) in counter.items() } @db_transaction() def raw_extrinsic_metadata_get( self, target: ExtendedSWHID, authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, *, db: Db, cur=None, ) -> PagedResult[RawExtrinsicMetadata]: if page_token: (after_time, after_fetcher) = msgpack_loads(base64.b64decode(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 PagedResult(next_page_token=None, results=[],) rows = db.raw_extrinsic_metadata_get( str(target), authority_id, after_time, after_fetcher, limit + 1, cur, ) rows = [dict(zip(db.raw_extrinsic_metadata_get_cols, row)) for row in rows] results = [] for row in rows: assert str(target) == row["raw_extrinsic_metadata.target"] results.append(converters.db_to_raw_extrinsic_metadata(row)) 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[str] = base64.b64encode( msgpack_dumps( ( last_returned_row["discovery_date"], last_returned_row["metadata_fetcher.id"], ) ) ).decode() else: next_page_token = None return PagedResult(next_page_token=next_page_token, results=results,) @db_transaction() def raw_extrinsic_metadata_get_by_ids( self, ids: List[Sha1Git], *, db: Db, cur=None, ) -> List[RawExtrinsicMetadata]: return [ converters.db_to_raw_extrinsic_metadata( dict(zip(db.raw_extrinsic_metadata_get_cols, row)) ) for row in db.raw_extrinsic_metadata_get_by_ids(ids) ] @db_transaction() def raw_extrinsic_metadata_get_authorities( self, target: ExtendedSWHID, *, db: Db, cur=None, ) -> List[MetadataAuthority]: return [ MetadataAuthority( type=MetadataAuthorityType(authority_type), url=authority_url ) for ( authority_type, authority_url, ) in db.raw_extrinsic_metadata_get_authorities(str(target), cur) ] @timed @process_metrics @db_transaction() def metadata_fetcher_add( self, fetchers: List[MetadataFetcher], *, db: Db, cur=None ) -> Dict[str, int]: fetchers = list(fetchers) self.journal_writer.metadata_fetcher_add(fetchers) count = 0 for fetcher in fetchers: db.metadata_fetcher_add(fetcher.name, fetcher.version, cur=cur) count += 1 return {"metadata_fetcher:add": count} @timed @db_transaction(statement_timeout=500) def metadata_fetcher_get( self, name: str, version: str, *, db: Db, 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 @process_metrics @db_transaction() def metadata_authority_add( self, authorities: List[MetadataAuthority], *, db: Db, cur=None ) -> Dict[str, int]: authorities = list(authorities) self.journal_writer.metadata_authority_add(authorities) count = 0 for authority in authorities: db.metadata_authority_add(authority.type.value, authority.url, cur=cur) count += 1 return {"metadata_authority:add": count} @timed @db_transaction() def metadata_authority_get( self, type: MetadataAuthorityType, url: str, *, db: Db, 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))) def clear_buffers(self, object_types: Sequence[str] = ()) -> None: """Do nothing """ return None def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]: 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/sql/30-schema.sql b/swh/storage/sql/30-schema.sql index e2f851ce..b067ebdc 100644 --- a/swh/storage/sql/30-schema.sql +++ b/swh/storage/sql/30-schema.sql @@ -1,517 +1,529 @@ --- --- SQL implementation of the Software Heritage data model --- -- schema versions create table dbversion ( version int primary key, release timestamptz, description text ); comment on table dbversion is 'Details of current db version'; comment on column dbversion.version is 'SQL schema version'; comment on column dbversion.release is 'Version deployment timestamp'; comment on column dbversion.description is 'Release description'; -- latest schema version insert into dbversion(version, release, description) - values(178, now(), 'Work In Progress'); + values(180, now(), 'Work In Progress'); -- a SHA1 checksum create domain sha1 as bytea check (length(value) = 20); -- a Git object ID, i.e., a Git-style salted SHA1 checksum create domain sha1_git as bytea check (length(value) = 20); -- a SHA256 checksum create domain sha256 as bytea check (length(value) = 32); -- a blake2 checksum create domain blake2s256 as bytea check (length(value) = 32); -- UNIX path (absolute, relative, individual path component, etc.) create domain unix_path as bytea; -- a set of UNIX-like access permissions, as manipulated by, e.g., chmod create domain file_perms as int; -- an SWHID create domain swhid as text check (value ~ '^swh:[0-9]+:.*'); -- Checksums about actual file content. Note that the content itself is not -- stored in the DB, but on external (key-value) storage. A single checksum is -- used as key there, but the other can be used to verify that we do not inject -- content collisions not knowingly. create table content ( sha1 sha1 not null, sha1_git sha1_git not null, sha256 sha256 not null, blake2s256 blake2s256 not null, length bigint not null, ctime timestamptz not null default now(), -- creation time, i.e. time of (first) injection into the storage status content_status not null default 'visible', object_id bigserial ); comment on table content is 'Checksums of file content which is actually stored externally'; comment on column content.sha1 is 'Content sha1 hash'; comment on column content.sha1_git is 'Git object sha1 hash'; comment on column content.sha256 is 'Content Sha256 hash'; comment on column content.blake2s256 is 'Content blake2s hash'; comment on column content.length is 'Content length'; comment on column content.ctime is 'First seen time'; comment on column content.status is 'Content status (absent, visible, hidden)'; comment on column content.object_id is 'Content identifier'; -- An origin is a place, identified by an URL, where software source code -- artifacts can be found. We support different kinds of origins, e.g., git and -- other VCS repositories, web pages that list tarballs URLs (e.g., -- http://www.kernel.org), indirect tarball URLs (e.g., -- http://www.example.org/latest.tar.gz), etc. The key feature of an origin is -- that it can be *fetched* from (wget, git clone, svn checkout, etc.) to -- retrieve all the contained software. create table origin ( id bigserial not null, url text not null ); comment on column origin.id is 'Artifact origin id'; comment on column origin.url is 'URL of origin'; -- Content blobs observed somewhere, but not ingested into the archive for -- whatever reason. This table is separate from the content table as we might -- not have the sha1 checksum of skipped contents (for instance when we inject -- git repositories, objects that are too big will be skipped here, and we will -- only know their sha1_git). 'reason' contains the reason the content was -- skipped. origin is a nullable column allowing to find out which origin -- contains that skipped content. create table skipped_content ( sha1 sha1, sha1_git sha1_git, sha256 sha256, blake2s256 blake2s256, length bigint not null, ctime timestamptz not null default now(), status content_status not null default 'absent', reason text not null, origin bigint, object_id bigserial ); comment on table skipped_content is 'Content blobs observed, but not ingested in the archive'; comment on column skipped_content.sha1 is 'Skipped content sha1 hash'; comment on column skipped_content.sha1_git is 'Git object sha1 hash'; comment on column skipped_content.sha256 is 'Skipped content sha256 hash'; comment on column skipped_content.blake2s256 is 'Skipped content blake2s hash'; comment on column skipped_content.length is 'Skipped content length'; comment on column skipped_content.ctime is 'First seen time'; comment on column skipped_content.status is 'Skipped content status (absent, visible, hidden)'; comment on column skipped_content.reason is 'Reason for skipping'; comment on column skipped_content.origin is 'Origin table identifier'; comment on column skipped_content.object_id is 'Skipped content identifier'; -- A file-system directory. A directory is a list of directory entries (see -- tables: directory_entry_{dir,file}). -- -- To list the contents of a directory: -- 1. list the contained directory_entry_dir using array dir_entries -- 2. list the contained directory_entry_file using array file_entries -- 3. list the contained directory_entry_rev using array rev_entries -- 4. UNION -- -- Synonyms/mappings: -- * git: tree create table directory ( id sha1_git not null, dir_entries bigint[], -- sub-directories, reference directory_entry_dir file_entries bigint[], -- contained files, reference directory_entry_file rev_entries bigint[], -- mounted revisions, reference directory_entry_rev - object_id bigserial -- short object identifier + object_id bigserial, -- short object identifier + raw_manifest bytea -- git manifest of the object, if it cannot be represented using only the other fields ); comment on table directory is 'Contents of a directory, synonymous to tree (git)'; comment on column directory.id is 'Git object sha1 hash'; comment on column directory.dir_entries is 'Sub-directories, reference directory_entry_dir'; comment on column directory.file_entries is 'Contained files, reference directory_entry_file'; comment on column directory.rev_entries is 'Mounted revisions, reference directory_entry_rev'; comment on column directory.object_id is 'Short object identifier'; +comment on column directory.raw_manifest is 'git manifest of the object, if it cannot be represented using only the other fields'; -- A directory entry pointing to a (sub-)directory. create table directory_entry_dir ( id bigserial, target sha1_git not null, -- id of target directory name unix_path not null, -- path name, relative to containing dir perms file_perms not null -- unix-like permissions ); comment on table directory_entry_dir is 'Directory entry for directory'; comment on column directory_entry_dir.id is 'Directory identifier'; comment on column directory_entry_dir.target is 'Target directory identifier'; comment on column directory_entry_dir.name is 'Path name, relative to containing directory'; comment on column directory_entry_dir.perms is 'Unix-like permissions'; -- A directory entry pointing to a file content. create table directory_entry_file ( id bigserial, target sha1_git not null, -- id of target file name unix_path not null, -- path name, relative to containing dir perms file_perms not null -- unix-like permissions ); comment on table directory_entry_file is 'Directory entry for file'; comment on column directory_entry_file.id is 'File identifier'; comment on column directory_entry_file.target is 'Target file identifier'; comment on column directory_entry_file.name is 'Path name, relative to containing directory'; comment on column directory_entry_file.perms is 'Unix-like permissions'; -- A directory entry pointing to a revision. create table directory_entry_rev ( id bigserial, target sha1_git not null, -- id of target revision name unix_path not null, -- path name, relative to containing dir perms file_perms not null -- unix-like permissions ); comment on table directory_entry_rev is 'Directory entry for revision'; comment on column directory_entry_dir.id is 'Revision identifier'; comment on column directory_entry_dir.target is 'Target revision in identifier'; comment on column directory_entry_dir.name is 'Path name, relative to containing directory'; comment on column directory_entry_dir.perms is 'Unix-like permissions'; -- A person referenced by some source code artifacts, e.g., a VCS revision or -- release metadata. create table person ( id bigserial, name bytea, -- advisory: not null if we managed to parse a name email bytea, -- advisory: not null if we managed to parse an email fullname bytea not null -- freeform specification; what is actually used in the checksums -- will usually be of the form 'name ' ); comment on table person is 'Person referenced in code artifact release metadata'; comment on column person.id is 'Person identifier'; comment on column person.name is 'Name'; comment on column person.email is 'Email'; comment on column person.fullname is 'Full name (raw name)'; -- The state of a source code tree at a specific point in time. -- -- Synonyms/mappings: -- * git / subversion / etc: commit -- * tarball: a specific tarball -- -- Revisions are organized as DAGs. Each revision points to 0, 1, or more (in -- case of merges) parent revisions. Each revision points to a directory, i.e., -- a file-system tree containing files and directories. create table revision ( id sha1_git not null, date timestamptz, date_offset smallint, committer_date timestamptz, committer_date_offset smallint, type revision_type not null, directory sha1_git, -- source code 'root' directory message bytea, author bigint, committer bigint, synthetic boolean not null default false, -- true iff revision has been created by Software Heritage metadata jsonb, -- extra metadata (tarball checksums, extra commit information, etc...) object_id bigserial, date_neg_utc_offset boolean, committer_date_neg_utc_offset boolean, - extra_headers bytea[][] not null -- extra headers (used in hash computation) + extra_headers bytea[][] not null, -- extra headers (used in hash computation) + date_offset_bytes bytea, + committer_date_offset_bytes bytea, + raw_manifest bytea -- git manifest of the object, if it cannot be represented using only the other fields ); comment on table revision is 'A revision represents the state of a source code tree at a specific point in time'; comment on column revision.id is 'Git-style SHA1 commit identifier'; comment on column revision.date is 'Author timestamp as UNIX epoch'; comment on column revision.date_offset is 'Author timestamp timezone, as minute offsets from UTC'; comment on column revision.date_neg_utc_offset is 'True indicates a -0 UTC offset on author timestamp'; comment on column revision.committer_date is 'Committer timestamp as UNIX epoch'; comment on column revision.committer_date_offset is 'Committer timestamp timezone, as minute offsets from UTC'; comment on column revision.committer_date_neg_utc_offset is 'True indicates a -0 UTC offset on committer timestamp'; comment on column revision.type is 'Type of revision'; comment on column revision.directory is 'Directory identifier'; comment on column revision.message is 'Commit message'; comment on column revision.author is 'Author identity'; comment on column revision.committer is 'Committer identity'; comment on column revision.synthetic is 'True iff revision has been synthesized by Software Heritage'; comment on column revision.metadata is 'Extra revision metadata'; comment on column revision.object_id is 'Non-intrinsic, sequential object identifier'; comment on column revision.extra_headers is 'Extra revision headers; used in revision hash computation'; +comment on column revision.date_offset_bytes is 'Raw git representation of the timezone, as an offset from UTC. It should follow this format: ``+HHMM`` or ``-HHMM``'; +comment on column revision.committer_date_offset_bytes is 'Raw git representation of the timezone, as an offset from UTC. It should follow this format: ``+HHMM`` or ``-HHMM``'; +comment on column revision.raw_manifest is 'git manifest of the object, if it cannot be represented using only the other fields'; -- either this table or the sha1_git[] column on the revision table create table revision_history ( id sha1_git not null, parent_id sha1_git not null, parent_rank int not null default 0 -- parent position in merge commits, 0-based ); comment on table revision_history is 'Sequence of revision history with parent and position in history'; comment on column revision_history.id is 'Revision history git object sha1 checksum'; comment on column revision_history.parent_id is 'Parent revision git object identifier'; comment on column revision_history.parent_rank is 'Parent position in merge commits, 0-based'; -- Crawling history of software origins visited by Software Heritage. Each -- visit is a 3-way mapping between a software origin, a timestamp, and a -- snapshot object capturing the full-state of the origin at visit time. create table origin_visit ( origin bigint not null, visit bigint not null, date timestamptz not null, type text not null ); comment on column origin_visit.origin is 'Visited origin'; comment on column origin_visit.visit is 'Sequential visit number for the origin'; comment on column origin_visit.date is 'Visit timestamp'; comment on column origin_visit.type is 'Type of loader that did the visit (hg, git, ...)'; -- Crawling history of software origin visits by Software Heritage. Each -- visit see its history change through new origin visit status updates create table origin_visit_status ( origin bigint not null, visit bigint not null, date timestamptz not null, type text not null, status origin_visit_state not null, metadata jsonb, snapshot sha1_git ); comment on column origin_visit_status.origin is 'Origin concerned by the visit update'; comment on column origin_visit_status.visit is 'Visit concerned by the visit update'; comment on column origin_visit_status.date is 'Visit update timestamp'; comment on column origin_visit_status.type is 'Type of loader that did the visit (hg, git, ...)'; comment on column origin_visit_status.status is 'Visit status (ongoing, failed, full)'; comment on column origin_visit_status.metadata is 'Optional origin visit metadata'; comment on column origin_visit_status.snapshot is 'Optional, possibly partial, snapshot of the origin visit. It can be partial.'; -- A snapshot represents the entire state of a software origin as crawled by -- Software Heritage. This table is a simple mapping between (public) intrinsic -- snapshot identifiers and (private) numeric sequential identifiers. create table snapshot ( object_id bigserial not null, -- PK internal object identifier id sha1_git not null -- snapshot intrinsic identifier ); comment on table snapshot is 'State of a software origin as crawled by Software Heritage'; comment on column snapshot.object_id is 'Internal object identifier'; comment on column snapshot.id is 'Intrinsic snapshot identifier'; -- Each snapshot associate "branch" names to other objects in the Software -- Heritage Merkle DAG. This table describes branches as mappings between names -- and target typed objects. create table snapshot_branch ( object_id bigserial not null, -- PK internal object identifier name bytea not null, -- branch name, e.g., "master" or "feature/drag-n-drop" target bytea, -- target object identifier, e.g., a revision identifier target_type snapshot_target -- target object type, e.g., "revision" ); comment on table snapshot_branch is 'Associates branches with objects in Heritage Merkle DAG'; comment on column snapshot_branch.object_id is 'Internal object identifier'; comment on column snapshot_branch.name is 'Branch name'; comment on column snapshot_branch.target is 'Target object identifier'; comment on column snapshot_branch.target_type is 'Target object type'; -- Mapping between snapshots and their branches. create table snapshot_branches ( snapshot_id bigint not null, -- snapshot identifier, ref. snapshot.object_id branch_id bigint not null -- branch identifier, ref. snapshot_branch.object_id ); comment on table snapshot_branches is 'Mapping between snapshot and their branches'; comment on column snapshot_branches.snapshot_id is 'Snapshot identifier'; comment on column snapshot_branches.branch_id is 'Branch identifier'; -- A "memorable" point in time in the development history of a software -- project. -- -- Synonyms/mappings: -- * git: tag (of the annotated kind, otherwise they are just references) -- * tarball: the release version number create table release ( id sha1_git not null, target sha1_git, date timestamptz, date_offset smallint, name bytea, comment bytea, author bigint, synthetic boolean not null default false, -- true iff release has been created by Software Heritage object_id bigserial, target_type object_type not null, - date_neg_utc_offset boolean + date_neg_utc_offset boolean, + date_offset_bytes bytea, + raw_manifest bytea ); comment on table release is 'Details of a software release, synonymous with a tag (git) or version number (tarball)'; comment on column release.id is 'Release git identifier'; comment on column release.target is 'Target git identifier'; comment on column release.date is 'Release timestamp'; comment on column release.date_offset is 'Timestamp offset from UTC'; comment on column release.name is 'Name'; comment on column release.comment is 'Comment'; comment on column release.author is 'Author'; comment on column release.synthetic is 'Indicates if created by Software Heritage'; comment on column release.object_id is 'Object identifier'; comment on column release.target_type is 'Object type (''content'', ''directory'', ''revision'', ''release'', ''snapshot'')'; comment on column release.date_neg_utc_offset is 'True indicates -0 UTC offset for release timestamp'; +comment on column release.date_offset_bytes is 'Raw git representation of the timezone, as an offset from UTC. It should follow this format: ``+HHMM`` or ``-HHMM``'; +comment on column release.raw_manifest is 'git manifest of the object, if it cannot be represented using only the other fields'; -- Tools create table metadata_fetcher ( id serial not null, name text not null, version text not null ); comment on table metadata_fetcher is 'Tools used to retrieve metadata'; comment on column metadata_fetcher.id is 'Internal identifier of the fetcher'; comment on column metadata_fetcher.name is 'Fetcher name'; comment on column metadata_fetcher.version is 'Fetcher version'; create table metadata_authority ( id serial not null, type text not null, url text not null ); comment on table metadata_authority is 'Metadata authority information'; comment on column metadata_authority.id is 'Internal identifier of the authority'; comment on column metadata_authority.type is 'Type of authority (deposit_client/forge/registry)'; comment on column metadata_authority.url is 'Authority''s uri'; -- Extrinsic metadata on a DAG objects and origins. create table raw_extrinsic_metadata ( id sha1_git not null, type text not null, target text not null, -- metadata source authority_id bigint not null, fetcher_id bigint not null, discovery_date timestamptz not null, -- metadata itself format text not null, metadata bytea not null, -- context origin text, visit bigint, snapshot swhid, release swhid, revision swhid, path bytea, directory swhid ); comment on table raw_extrinsic_metadata is 'keeps all metadata found concerning an object'; comment on column raw_extrinsic_metadata.type is 'the type of object (content/directory/revision/release/snapshot/origin) the metadata is on'; comment on column raw_extrinsic_metadata.target is 'the SWHID or origin URL for which the metadata was found'; comment on column raw_extrinsic_metadata.discovery_date is 'the date of retrieval'; comment on column raw_extrinsic_metadata.authority_id is 'the metadata provider: github, openhub, deposit, etc.'; comment on column raw_extrinsic_metadata.fetcher_id is 'the tool used for extracting metadata: loaders, crawlers, etc.'; comment on column raw_extrinsic_metadata.format is 'name of the format of metadata, used by readers to interpret it.'; comment on column raw_extrinsic_metadata.metadata is 'original metadata in opaque format'; -- Keep a cache of object counts create table object_counts ( object_type text, -- table for which we're counting objects (PK) value bigint, -- count of objects in the table last_update timestamptz, -- last update for the object count in this table single_update boolean -- whether we update this table standalone (true) or through bucketed counts (false) ); comment on table object_counts is 'Cache of object counts'; comment on column object_counts.object_type is 'Object type (''content'', ''directory'', ''revision'', ''release'', ''snapshot'')'; comment on column object_counts.value is 'Count of objects in the table'; comment on column object_counts.last_update is 'Last update for object count'; comment on column object_counts.single_update is 'standalone (true) or bucketed counts (false)'; create table object_counts_bucketed ( line serial not null, -- PK object_type text not null, -- table for which we're counting objects identifier text not null, -- identifier across which we're bucketing objects bucket_start bytea, -- lower bound (inclusive) for the bucket bucket_end bytea, -- upper bound (exclusive) for the bucket value bigint, -- count of objects in the bucket last_update timestamptz -- last update for the object count in this bucket ); comment on table object_counts_bucketed is 'Bucketed count for objects ordered by type'; comment on column object_counts_bucketed.line is 'Auto incremented idenitfier value'; comment on column object_counts_bucketed.object_type is 'Object type (''content'', ''directory'', ''revision'', ''release'', ''snapshot'')'; comment on column object_counts_bucketed.identifier is 'Common identifier for bucketed objects'; comment on column object_counts_bucketed.bucket_start is 'Lower bound (inclusive) for the bucket'; comment on column object_counts_bucketed.bucket_end is 'Upper bound (exclusive) for the bucket'; comment on column object_counts_bucketed.value is 'Count of objects in the bucket'; comment on column object_counts_bucketed.last_update is 'Last update for the object count in this bucket'; -- The ExtID (typ. original VCS) <-> swhid relation table create table extid ( extid_type text not null, extid bytea not null, target_type object_type not null, target sha1_git not null, extid_version bigint not null default 0 ); comment on table extid is 'Correspondance SWH object (SWHID) <-> original revision id (vcs id)'; comment on column extid.extid_type is 'ExtID type'; comment on column extid.extid is 'Intrinsic identifier of the object (e.g. hg revision)'; comment on column extid.target_type is 'Type of SWHID of the referenced SWH object'; comment on column extid.target is 'Value (hash) of SWHID of the refenced SWH object'; comment on column extid.extid_version is 'Version of the extid type for the given original object'; diff --git a/swh/storage/sql/40-funcs.sql b/swh/storage/sql/40-funcs.sql index 184cf78c..980c85fa 100644 --- a/swh/storage/sql/40-funcs.sql +++ b/swh/storage/sql/40-funcs.sql @@ -1,1011 +1,1015 @@ create or replace function hash_sha1(text) returns text as $$ select encode(digest($1, 'sha1'), 'hex') $$ language sql strict immutable; comment on function hash_sha1(text) is 'Compute SHA1 hash as text'; -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: -- tblname: name of the table to mimic create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table if not exists tmp_%1$I (like %1$I including defaults) on commit delete rows; alter table tmp_%1$I drop column if exists object_id; ', tblname); return; end $$; -- create a temporary table for directory entries called tmp_TBLNAME, -- mimicking existing table TBLNAME with an extra dir_id (sha1_git) -- column, and dropping the id column. -- -- This is used to create the tmp_directory_entry_ tables. -- -- Args: -- tblname: name of the table to mimic create or replace function swh_mktemp_dir_entry(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table if not exists tmp_%1$I (like %1$I including defaults, dir_id sha1_git) on commit delete rows; alter table tmp_%1$I drop column if exists id; ', tblname); return; end $$; -- create a temporary table for revisions called tmp_revisions, -- mimicking existing table revision, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_revision() returns void language sql as $$ create temporary table if not exists tmp_revision ( like revision including defaults, author_fullname bytea, author_name bytea, author_email bytea, committer_fullname bytea, committer_name bytea, committer_email bytea ) on commit delete rows; alter table tmp_revision drop column if exists author; alter table tmp_revision drop column if exists committer; alter table tmp_revision drop column if exists object_id; $$; -- create a temporary table for releases called tmp_release, -- mimicking existing table release, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_release() returns void language sql as $$ create temporary table if not exists tmp_release ( like release including defaults, author_fullname bytea, author_name bytea, author_email bytea ) on commit delete rows; alter table tmp_release drop column if exists author; alter table tmp_release drop column if exists object_id; $$; -- create a temporary table for the branches of a snapshot create or replace function swh_mktemp_snapshot_branch() returns void language sql as $$ create temporary table if not exists tmp_snapshot_branch ( name bytea not null, target bytea, target_type snapshot_target ) on commit delete rows; $$; -- a content signature is a set of cryptographic checksums that we use to -- uniquely identify content, for the purpose of verifying if we already have -- some content or not during content injection create type content_signature as ( sha1 sha1, sha1_git sha1_git, sha256 sha256, blake2s256 blake2s256 ); -- check which entries of tmp_skipped_content are missing from skipped_content -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_missing() returns setof content_signature language plpgsql as $$ begin return query select sha1, sha1_git, sha256, blake2s256 from tmp_skipped_content t where not exists (select 1 from skipped_content s where s.sha1 is not distinct from t.sha1 and s.sha1_git is not distinct from t.sha1_git and s.sha256 is not distinct from t.sha256); return; end $$; -- add tmp_content entries to content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content, -- 2. call this function create or replace function swh_content_add() returns void language plpgsql as $$ begin insert into content (sha1, sha1_git, sha256, blake2s256, length, status, ctime) select distinct sha1, sha1_git, sha256, blake2s256, length, status, ctime from tmp_content; return; end $$; -- add tmp_skipped_content entries to skipped_content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_add() returns void language plpgsql as $$ begin insert into skipped_content (sha1, sha1_git, sha256, blake2s256, length, status, reason, origin) select distinct sha1, sha1_git, sha256, blake2s256, length, status, reason, origin from tmp_skipped_content where (coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '')) in ( select coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '') from swh_skipped_content_missing() ); -- TODO XXX use postgres 9.5 "UPSERT" support here, when available. -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid -- the extra swh_skipped_content_missing() query here. return; end $$; -- Update content entries from temporary table. -- (columns are potential new columns added to the schema, this cannot be empty) -- create or replace function swh_content_update(columns_update text[]) returns void language plpgsql as $$ declare query text; tmp_array text[]; begin if array_length(columns_update, 1) = 0 then raise exception 'Please, provide the list of column names to update.'; end if; tmp_array := array(select format('%1$s=t.%1$s', unnest) from unnest(columns_update)); query = format('update content set %s from tmp_content t where t.sha1 = content.sha1', array_to_string(tmp_array, ', ')); execute query; return; end $$; comment on function swh_content_update(text[]) IS 'Update existing content''s columns'; create type directory_entry_type as enum('file', 'dir', 'rev'); -- Add tmp_directory_entry_* entries to directory_entry_* and directory, -- skipping duplicates in directory_entry_*. This is a generic function that -- works on all kind of directory entries. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_*'), 1 COPY to -- tmp_directory_entry_*, 2. call this function -- -- Assumption: this function is used in the same transaction that inserts the -- context directory in table "directory". create or replace function swh_directory_entry_add(typ directory_entry_type) returns void language plpgsql as $$ begin execute format(' insert into directory_entry_%1$s (target, name, perms) select distinct t.target, t.name, t.perms from tmp_directory_entry_%1$s t where not exists ( select 1 from directory_entry_%1$s i where t.target = i.target and t.name = i.name and t.perms = i.perms) ', typ); execute format(' with new_entries as ( select t.dir_id, array_agg(i.id) as entries from tmp_directory_entry_%1$s t inner join directory_entry_%1$s i using (target, name, perms) group by t.dir_id ) update tmp_directory as d set %1$s_entries = new_entries.entries from new_entries where d.id = new_entries.dir_id ', typ); return; end $$; -- Insert the data from tmp_directory, tmp_directory_entry_file, -- tmp_directory_entry_dir, tmp_directory_entry_rev into their final -- tables. -- -- Prerequisites: -- directory ids in tmp_directory -- entries in tmp_directory_entry_{file,dir,rev} -- create or replace function swh_directory_add() returns void language plpgsql as $$ begin perform swh_directory_entry_add('file'); perform swh_directory_entry_add('dir'); perform swh_directory_entry_add('rev'); - insert into directory - select * from tmp_directory t + insert into directory (id, dir_entries, file_entries, rev_entries, raw_manifest) + select id, dir_entries, file_entries, rev_entries, raw_manifest from tmp_directory t where not exists ( select 1 from directory d where d.id = t.id); return; end $$; -- a directory listing entry with all the metadata -- -- can be used to list a directory, and retrieve all the data in one go. create type directory_entry as ( dir_id sha1_git, -- id of the parent directory type directory_entry_type, -- type of entry target sha1_git, -- id of target name unix_path, -- path name, relative to containing dir perms file_perms, -- unix-like permissions status content_status, -- visible or absent sha1 sha1, -- content if sha1 if type is not dir sha1_git sha1_git, -- content's sha1 git if type is not dir sha256 sha256, -- content's sha256 if type is not dir length bigint -- content length if type is not dir ); -- List a single level of directory walked_dir_id -- FIXME: order by name is not correct. For git, we need to order by -- lexicographic order but as if a trailing / is present in directory -- name create or replace function swh_directory_walk_one(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with dir as ( select id as dir_id, dir_entries, file_entries, rev_entries from directory where id = walked_dir_id), ls_d as (select dir_id, unnest(dir_entries) as entry_id from dir), ls_f as (select dir_id, unnest(file_entries) as entry_id from dir), ls_r as (select dir_id, unnest(rev_entries) as entry_id from dir) (select dir_id, 'dir'::directory_entry_type as type, e.target, e.name, e.perms, NULL::content_status, NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint from ls_d left join directory_entry_dir e on ls_d.entry_id = e.id) union (with known_contents as (select dir_id, 'file'::directory_entry_type as type, e.target, e.name, e.perms, c.status, c.sha1, c.sha1_git, c.sha256, c.length from ls_f left join directory_entry_file e on ls_f.entry_id = e.id inner join content c on e.target = c.sha1_git) select * from known_contents union (select dir_id, 'file'::directory_entry_type as type, e.target, e.name, e.perms, c.status, c.sha1, c.sha1_git, c.sha256, c.length from ls_f left join directory_entry_file e on ls_f.entry_id = e.id left join skipped_content c on e.target = c.sha1_git where not exists (select 1 from known_contents where known_contents.sha1_git=e.target))) union (select dir_id, 'rev'::directory_entry_type as type, e.target, e.name, e.perms, NULL::content_status, NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint from ls_r left join directory_entry_rev e on ls_r.entry_id = e.id) order by name; $$; -- List recursively the revision directory arborescence create or replace function swh_directory_walk(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with recursive entries as ( select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length from swh_directory_walk_one(walked_dir_id) union all select dir_id, type, target, (dirname || '/' || name)::unix_path as name, perms, status, sha1, sha1_git, sha256, length from (select (swh_directory_walk_one(dirs.target)).*, dirs.name as dirname from (select target, name from entries where type = 'dir') as dirs) as with_parent ) select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length from entries $$; -- Find a directory entry by its path create or replace function swh_find_directory_entry_by_path( walked_dir_id sha1_git, dir_or_content_path bytea[]) returns directory_entry language plpgsql as $$ declare end_index integer; paths bytea default ''; path bytea; res bytea[]; r record; begin end_index := array_upper(dir_or_content_path, 1); res[1] := walked_dir_id; for i in 1..end_index loop path := dir_or_content_path[i]; -- concatenate path for patching the name in the result record (if we found it) if i = 1 then paths = path; else paths := paths || '/' || path; -- concatenate paths end if; if i <> end_index then select * from swh_directory_walk_one(res[i] :: sha1_git) where name=path and type = 'dir' limit 1 into r; else select * from swh_directory_walk_one(res[i] :: sha1_git) where name=path limit 1 into r; end if; -- find the path if r is null then return null; else -- store the next dir to lookup the next local path from res[i+1] := r.target; end if; end loop; -- at this moment, r is the result. Patch its 'name' with the full path before returning it. r.name := paths; return r; end $$; -- Returns the entries in a directory, without joining with their target tables create or replace function swh_directory_get_entries(dir_id sha1_git) returns table ( dir_id directory_entry_type, target sha1_git, name unix_path, perms file_perms ) language sql stable as $$ with dir as ( select id as dir_id, dir_entries, file_entries, rev_entries from directory where id = dir_id), ls_d as (select dir_id, unnest(dir_entries) as entry_id from dir), ls_f as (select dir_id, unnest(file_entries) as entry_id from dir), ls_r as (select dir_id, unnest(rev_entries) as entry_id from dir) (select 'dir'::directory_entry_type, e.target, e.name, e.perms from ls_d left join directory_entry_dir e on ls_d.entry_id = e.id) union (select 'file'::directory_entry_type, e.target, e.name, e.perms from ls_f left join directory_entry_file e on ls_f.entry_id = e.id) union (select 'rev'::directory_entry_type, e.target, e.name, e.perms from ls_r left join directory_entry_rev e on ls_r.entry_id = e.id) $$; -- List all revision IDs starting from a given revision, going back in time -- -- TODO ordering: should be breadth-first right now (what do we want?) -- TODO ordering: ORDER BY parent_rank somewhere? create or replace function swh_revision_list(root_revisions bytea[], num_revs bigint default NULL) returns table (id sha1_git, parents bytea[]) language sql stable as $$ with recursive full_rev_list(id) as ( (select id from revision where id = ANY(root_revisions)) union (select h.parent_id from revision_history as h join full_rev_list on h.id = full_rev_list.id) ), rev_list as (select id from full_rev_list limit num_revs) select rev_list.id as id, array(select rh.parent_id::bytea from revision_history rh where rh.id = rev_list.id order by rh.parent_rank ) as parent from rev_list; $$; -- Detailed entry for a revision create type revision_entry as ( id sha1_git, date timestamptz, date_offset smallint, date_neg_utc_offset boolean, + date_offset_bytes bytea, committer_date timestamptz, committer_date_offset smallint, committer_date_neg_utc_offset boolean, + committer_date_offset_bytes bytea, type revision_type, directory sha1_git, message bytea, author_id bigint, author_fullname bytea, author_name bytea, author_email bytea, committer_id bigint, committer_fullname bytea, committer_name bytea, committer_email bytea, metadata jsonb, synthetic boolean, parents bytea[], object_id bigint, - extra_headers bytea[][] + extra_headers bytea[][], + raw_manifest bytea ); -- "git style" revision log. Similar to swh_revision_list(), but returning all -- information associated to each revision, and expanding authors/committers create or replace function swh_revision_log(root_revisions bytea[], num_revs bigint default NULL) returns setof revision_entry language sql stable as $$ - select t.id, r.date, r.date_offset, r.date_neg_utc_offset, - r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, + select t.id, r.date, r.date_offset, r.date_neg_utc_offset, r.date_offset_bytes, + r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.committer_date_offset_bytes, r.type, r.directory, r.message, a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, - r.metadata, r.synthetic, t.parents, r.object_id, r.extra_headers + r.metadata, r.synthetic, t.parents, r.object_id, r.extra_headers, + r.raw_manifest from swh_revision_list(root_revisions, num_revs) as t left join revision r on t.id = r.id left join person a on a.id = r.author left join person c on c.id = r.committer; $$; -- Detailed entry for a release create type release_entry as ( id sha1_git, target sha1_git, target_type object_type, date timestamptz, date_offset smallint, date_neg_utc_offset boolean, name bytea, comment bytea, synthetic boolean, author_id bigint, author_fullname bytea, author_name bytea, author_email bytea, object_id bigint ); -- Create entries in person from tmp_revision create or replace function swh_person_add_from_revision() returns void language plpgsql as $$ begin with t as ( select author_fullname as fullname, author_name as name, author_email as email from tmp_revision union select committer_fullname as fullname, committer_name as name, committer_email as email from tmp_revision ) insert into person (fullname, name, email) select distinct on (fullname) fullname, name, email from t where not exists ( select 1 from person p where t.fullname = p.fullname ); return; end $$; -- Create entries in revision from tmp_revision create or replace function swh_revision_add() returns void language plpgsql as $$ begin perform swh_person_add_from_revision(); - insert into revision (id, date, date_offset, date_neg_utc_offset, committer_date, committer_date_offset, committer_date_neg_utc_offset, type, directory, message, author, committer, metadata, synthetic, extra_headers) - select t.id, t.date, t.date_offset, t.date_neg_utc_offset, t.committer_date, t.committer_date_offset, t.committer_date_neg_utc_offset, t.type, t.directory, t.message, a.id, c.id, t.metadata, t.synthetic, t.extra_headers + insert into revision (id, date, date_offset, date_neg_utc_offset, date_offset_bytes, committer_date, committer_date_offset, committer_date_neg_utc_offset, committer_date_offset_bytes, type, directory, message, author, committer, metadata, synthetic, extra_headers, raw_manifest) + select t.id, t.date, t.date_offset, t.date_neg_utc_offset, t.date_offset_bytes, t.committer_date, t.committer_date_offset, t.committer_date_neg_utc_offset, t.committer_date_offset_bytes, t.type, t.directory, t.message, a.id, c.id, t.metadata, t.synthetic, t.extra_headers, t.raw_manifest from tmp_revision t left join person a on a.fullname = t.author_fullname left join person c on c.fullname = t.committer_fullname; return; end $$; -- Create entries in extid from tmp_extid -- operates in bulk: 0. swh_mktemp(extid), 1. COPY to tmp_extid, -- 2. call this function create or replace function swh_extid_add() returns void language plpgsql as $$ begin insert into extid (extid_type, extid, extid_version, target_type, target) select distinct t.extid_type, t.extid, t.extid_version, t.target_type, t.target from tmp_extid t on conflict do nothing; return; end $$; -- Create entries in person from tmp_release create or replace function swh_person_add_from_release() returns void language plpgsql as $$ begin with t as ( select distinct author_fullname as fullname, author_name as name, author_email as email from tmp_release where author_fullname is not null ) insert into person (fullname, name, email) select distinct on (fullname) fullname, name, email from t where not exists ( select 1 from person p where t.fullname = p.fullname ); return; end $$; -- Create entries in release from tmp_release create or replace function swh_release_add() returns void language plpgsql as $$ begin perform swh_person_add_from_release(); - insert into release (id, target, target_type, date, date_offset, date_neg_utc_offset, name, comment, author, synthetic) - select distinct t.id, t.target, t.target_type, t.date, t.date_offset, t.date_neg_utc_offset, t.name, t.comment, a.id, t.synthetic + insert into release (id, target, target_type, date, date_offset, date_neg_utc_offset, date_offset_bytes, name, comment, author, synthetic, raw_manifest) + select distinct t.id, t.target, t.target_type, t.date, t.date_offset, t.date_neg_utc_offset, t.date_offset_bytes, t.name, t.comment, a.id, t.synthetic, t.raw_manifest from tmp_release t left join person a on a.fullname = t.author_fullname where not exists (select 1 from release where t.id = release.id); return; end $$; -- add a new origin_visit for origin origin_id at date. -- -- Returns the new visit id. create or replace function swh_origin_visit_add(origin_url text, date timestamptz, type text) returns bigint language sql as $$ with origin_id as ( select id from origin where url = origin_url ), last_known_visit as ( select coalesce(max(visit), 0) as visit from origin_visit where origin = (select id from origin_id) ) insert into origin_visit (origin, date, type, visit) values ((select id from origin_id), date, type, (select visit from last_known_visit) + 1) returning visit; $$; create or replace function swh_snapshot_add(snapshot_id sha1_git) returns void language plpgsql as $$ declare snapshot_object_id snapshot.object_id%type; begin select object_id from snapshot where id = snapshot_id into snapshot_object_id; if snapshot_object_id is null then insert into snapshot (id) values (snapshot_id) returning object_id into snapshot_object_id; insert into snapshot_branch (name, target_type, target) select name, target_type, target from tmp_snapshot_branch tmp where not exists ( select 1 from snapshot_branch sb where sb.name = tmp.name and sb.target = tmp.target and sb.target_type = tmp.target_type ) on conflict do nothing; insert into snapshot_branches (snapshot_id, branch_id) select snapshot_object_id, sb.object_id as branch_id from tmp_snapshot_branch tmp join snapshot_branch sb using (name, target, target_type) where tmp.target is not null and tmp.target_type is not null union select snapshot_object_id, sb.object_id as branch_id from tmp_snapshot_branch tmp join snapshot_branch sb using (name) where tmp.target is null and tmp.target_type is null and sb.target is null and sb.target_type is null; end if; truncate table tmp_snapshot_branch; end; $$; create type snapshot_result as ( snapshot_id sha1_git, name bytea, target bytea, target_type snapshot_target ); create or replace function swh_snapshot_get_by_id(id sha1_git, branches_from bytea default '', branches_count bigint default null, target_types snapshot_target[] default NULL, branch_name_include_substring bytea default NULL, branch_name_exclude_prefix bytea default NULL) returns setof snapshot_result language sql stable as $$ -- with small limits, the "naive" version of this query can degenerate into -- using the deduplication index on snapshot_branch (name, target, -- target_type); The planner happily scans several hundred million rows. -- Do the query in two steps: first pull the relevant branches for the given -- snapshot (filtering them by type), then do the limiting. This two-step -- process guides the planner into using the proper index. with filtered_snapshot_branches as ( select swh_snapshot_get_by_id.id as snapshot_id, name, target, target_type from snapshot_branches inner join snapshot_branch on snapshot_branches.branch_id = snapshot_branch.object_id where snapshot_id = (select object_id from snapshot where snapshot.id = swh_snapshot_get_by_id.id) and (target_types is null or target_type = any(target_types)) order by name ) select snapshot_id, name, target, target_type from filtered_snapshot_branches where name >= branches_from and (branch_name_include_substring is null or name like '%'||branch_name_include_substring||'%') and (branch_name_exclude_prefix is null or name not like branch_name_exclude_prefix||'%') order by name limit branches_count; $$; create type snapshot_size as ( target_type snapshot_target, count bigint ); create or replace function swh_snapshot_count_branches(id sha1_git, branch_name_exclude_prefix bytea default NULL) returns setof snapshot_size language sql stable as $$ SELECT target_type, count(name) from swh_snapshot_get_by_id(swh_snapshot_count_branches.id, branch_name_exclude_prefix => swh_snapshot_count_branches.branch_name_exclude_prefix) group by target_type; $$; -- Absolute path: directory reference + complete path relative to it create type content_dir as ( directory sha1_git, path unix_path ); -- Find the containing directory of a given content, specified by sha1 -- (note: *not* sha1_git). -- -- Return a pair (dir_it, path) where path is a UNIX path that, from the -- directory root, reach down to a file with the desired content. Return NULL -- if no match is found. -- -- In case of multiple paths (i.e., pretty much always), an arbitrary one is -- chosen. create or replace function swh_content_find_directory(content_id sha1) returns content_dir language sql stable as $$ with recursive path as ( -- Recursively build a path from the requested content to a root -- directory. Each iteration returns a pair (dir_id, filename) where -- filename is relative to dir_id. Stops when no parent directory can -- be found. (select dir.id as dir_id, dir_entry_f.name as name, 0 as depth from directory_entry_file as dir_entry_f join content on content.sha1_git = dir_entry_f.target join directory as dir on dir.file_entries @> array[dir_entry_f.id] where content.sha1 = content_id limit 1) union all (select dir.id as dir_id, (dir_entry_d.name || '/' || path.name)::unix_path as name, path.depth + 1 from path join directory_entry_dir as dir_entry_d on dir_entry_d.target = path.dir_id join directory as dir on dir.dir_entries @> array[dir_entry_d.id] limit 1) ) select dir_id, name from path order by depth desc limit 1; $$; -- Find the visit of origin closest to date visit_date -- Breaks ties by selecting the largest visit id create or replace function swh_visit_find_by_date(origin_url text, visit_date timestamptz default NOW()) returns setof origin_visit language plpgsql stable as $$ declare origin_id bigint; begin select id into origin_id from origin where url=origin_url; return query with closest_two_visits as (( select ov, (date - visit_date), visit as interval from origin_visit ov where ov.origin = origin_id and ov.date >= visit_date order by ov.date asc, ov.visit desc limit 1 ) union ( select ov, (visit_date - date), visit as interval from origin_visit ov where ov.origin = origin_id and ov.date < visit_date order by ov.date desc, ov.visit desc limit 1 )) select (ov).* from closest_two_visits order by interval, visit limit 1; end $$; -- Object listing by object_id create or replace function swh_content_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof content language sql stable as $$ select * from content where object_id > min_excl and object_id <= max_incl order by object_id; $$; create or replace function swh_revision_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof revision_entry language sql stable as $$ with revs as ( select * from revision where object_id > min_excl and object_id <= max_incl ) - select r.id, r.date, r.date_offset, r.date_neg_utc_offset, - r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, + select r.id, r.date, r.date_offset, r.date_neg_utc_offset, r.date_offset_bytes, + r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.committer_date_offset_bytes, r.type, r.directory, r.message, a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic, array(select rh.parent_id::bytea from revision_history rh where rh.id = r.id order by rh.parent_rank) - as parents, r.object_id, r.extra_headers + as parents, r.object_id, r.extra_headers, r.raw_manifest from revs r left join person a on a.id = r.author left join person c on c.id = r.committer order by r.object_id; $$; create or replace function swh_release_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof release_entry language sql stable as $$ with rels as ( select * from release where object_id > min_excl and object_id <= max_incl ) select r.id, r.target, r.target_type, r.date, r.date_offset, r.date_neg_utc_offset, r.name, r.comment, r.synthetic, p.id as author_id, p.fullname as author_fullname, p.name as author_name, p.email as author_email, r.object_id from rels r left join person p on p.id = r.author order by r.object_id; $$; -- simple counter mapping a textual label to an integer value create type counter as ( label text, value bigint ); -- return statistics about the number of tuples in various SWH tables -- -- Note: the returned values are based on postgres internal statistics -- (pg_class table), which are only updated daily (by autovacuum) or so create or replace function swh_stat_counters() returns setof counter language sql stable as $$ select object_type as label, value as value from object_counts where object_type in ( 'content', 'directory', 'directory_entry_dir', 'directory_entry_file', 'directory_entry_rev', 'origin', 'origin_visit', 'person', 'release', 'revision', 'revision_history', 'skipped_content', 'snapshot' ); $$; create or replace function swh_update_counter(object_type text) returns void language plpgsql as $$ begin execute format(' insert into object_counts (value, last_update, object_type) values ((select count(*) from %1$I), NOW(), %1$L) on conflict (object_type) do update set value = excluded.value, last_update = excluded.last_update', object_type); return; end; $$; create or replace function swh_update_counter_bucketed() returns void language plpgsql as $$ declare query text; line_to_update int; new_value bigint; begin select object_counts_bucketed.line, format( 'select count(%I) from %I where %s', coalesce(identifier, '*'), object_type, coalesce( concat_ws( ' and ', case when bucket_start is not null then format('%I >= %L', identifier, bucket_start) -- lower bound condition, inclusive end, case when bucket_end is not null then format('%I < %L', identifier, bucket_end) -- upper bound condition, exclusive end ), 'true' ) ) from object_counts_bucketed order by coalesce(last_update, now() - '1 month'::interval) asc limit 1 into line_to_update, query; execute query into new_value; update object_counts_bucketed set value = new_value, last_update = now() where object_counts_bucketed.line = line_to_update; END $$; create or replace function swh_update_counters_from_buckets() returns trigger language plpgsql as $$ begin with to_update as ( select object_type, sum(value) as value, max(last_update) as last_update from object_counts_bucketed ob1 where not exists ( select 1 from object_counts_bucketed ob2 where ob1.object_type = ob2.object_type and value is null ) group by object_type ) update object_counts set value = to_update.value, last_update = to_update.last_update from to_update where object_counts.object_type = to_update.object_type and object_counts.value != to_update.value; return null; end $$; create trigger update_counts_from_bucketed after insert or update on object_counts_bucketed for each row when (NEW.line % 256 = 0) execute procedure swh_update_counters_from_buckets(); diff --git a/swh/storage/sql/60-indexes.sql b/swh/storage/sql/60-indexes.sql index 3f2f1354..dea3ee36 100644 --- a/swh/storage/sql/60-indexes.sql +++ b/swh/storage/sql/60-indexes.sql @@ -1,293 +1,315 @@ -- psql variables to get the current database flavor select swh_get_dbflavor() = 'read_replica' as dbflavor_read_replica \gset select swh_get_dbflavor() != 'read_replica' as dbflavor_does_deduplication \gset select swh_get_dbflavor() = 'mirror' as dbflavor_mirror \gset select swh_get_dbflavor() = 'default' as dbflavor_default \gset -- content create unique index concurrently content_pkey on content(sha1); alter table content add primary key using index content_pkey; \if :dbflavor_does_deduplication create unique index concurrently on content(sha1_git); \else create index concurrently on content(sha1_git); \endif create index concurrently on content(sha256); create index concurrently on content(blake2s256); \if :dbflavor_default create unique index concurrently on content(object_id); -- to be reviewed create index concurrently on content(ctime); -- to be reviewed \endif -- origin create unique index concurrently origin_pkey on origin(id); alter table origin add primary key using index origin_pkey; \if :dbflavor_does_deduplication create unique index concurrently on origin using btree(url); \else create index concurrently on origin using btree(url); \endif create index concurrently on origin using gin (url gin_trgm_ops); create index concurrently on origin using btree(digest(url, 'sha1')); -- skipped_content \if :dbflavor_does_deduplication alter table skipped_content add constraint skipped_content_sha1_sha1_git_sha256_key unique (sha1, sha1_git, sha256); \endif create index concurrently on skipped_content(sha1); create index concurrently on skipped_content(sha1_git); create index concurrently on skipped_content(sha256); create index concurrently on skipped_content(blake2s256); create unique index concurrently on skipped_content(object_id); \if :dbflavor_default alter table skipped_content add constraint skipped_content_origin_fkey foreign key (origin) references origin(id) not valid; alter table skipped_content validate constraint skipped_content_origin_fkey; \endif -- directory create unique index concurrently directory_pkey on directory(id); alter table directory add primary key using index directory_pkey; \if :dbflavor_default create index concurrently on directory using gin (dir_entries); -- to be reviewed create index concurrently on directory using gin (file_entries); -- to be reviewed create index concurrently on directory using gin (rev_entries); -- to be reviewed create unique index concurrently on directory(object_id); -- to be reviewed \endif -- directory_entry_dir create unique index concurrently directory_entry_dir_pkey on directory_entry_dir(id); alter table directory_entry_dir add primary key using index directory_entry_dir_pkey; \if :dbflavor_does_deduplication create unique index concurrently on directory_entry_dir(target, name, perms); \endif -- directory_entry_file create unique index concurrently directory_entry_file_pkey on directory_entry_file(id); alter table directory_entry_file add primary key using index directory_entry_file_pkey; \if :dbflavor_does_deduplication create unique index concurrently on directory_entry_file(target, name, perms); \endif -- directory_entry_rev create unique index concurrently directory_entry_rev_pkey on directory_entry_rev(id); alter table directory_entry_rev add primary key using index directory_entry_rev_pkey; \if :dbflavor_does_deduplication create unique index concurrently on directory_entry_rev(target, name, perms); \endif -- person create unique index concurrently person_pkey on person(id); alter table person add primary key using index person_pkey; \if :dbflavor_does_deduplication create unique index concurrently on person(fullname); \else create index concurrently on person(fullname); -- to be reviewed \endif \if :dbflavor_default create index concurrently on person(name); -- to be reviewed create index concurrently on person(email); -- to be reviewed \endif -- revision create unique index concurrently revision_pkey on revision(id); alter table revision add primary key using index revision_pkey; \if :dbflavor_does_deduplication alter table revision add constraint revision_author_fkey foreign key (author) references person(id) not valid; alter table revision validate constraint revision_author_fkey; alter table revision add constraint revision_committer_fkey foreign key (committer) references person(id) not valid; alter table revision validate constraint revision_committer_fkey; alter table revision add constraint revision_date_neg_utc_offset_not_null check (date is null or date_neg_utc_offset is not null) not valid; + alter table revision add constraint revision_committer_date_neg_utc_offset_not_null check (committer_date is null or committer_date_neg_utc_offset is not null) not valid; + alter table revision + add constraint revision_date_offset_not_null + check (date is null or date_offset_bytes is not null) + not valid; + + alter table revision + add constraint revision_committer_date_offset_not_null + check (committer_date is null or committer_date_offset_bytes is not null) + not valid; + alter table revision validate constraint revision_date_neg_utc_offset_not_null; alter table revision validate constraint revision_committer_date_neg_utc_offset_not_null; + alter table revision + validate constraint revision_date_offset_not_null; + alter table revision + validate constraint revision_committer_date_offset_not_null; \endif \if :dbflavor_default create index concurrently on revision(directory); -- to be reviewed create unique index concurrently on revision(object_id); -- to be reviewed \endif -- revision_history create unique index concurrently revision_history_pkey on revision_history(id, parent_rank); alter table revision_history add primary key using index revision_history_pkey; \if :dbflavor_default create index concurrently on revision_history(parent_id); -- to be reviewed \endif \if :dbflavor_does_deduplication alter table revision_history add constraint revision_history_id_fkey foreign key (id) references revision(id) not valid; alter table revision_history validate constraint revision_history_id_fkey; \endif -- snapshot create unique index concurrently snapshot_pkey on snapshot(object_id); alter table snapshot add primary key using index snapshot_pkey; \if :dbflavor_does_deduplication create unique index concurrently on snapshot(id); \else create index concurrently on snapshot(id); \endif -- snapshot_branch create unique index concurrently snapshot_branch_pkey on snapshot_branch(object_id); alter table snapshot_branch add primary key using index snapshot_branch_pkey; \if :dbflavor_does_deduplication create unique index concurrently on snapshot_branch (target_type, target, name); alter table snapshot_branch add constraint snapshot_branch_target_check check ((target_type is null) = (target is null)) not valid; alter table snapshot_branch validate constraint snapshot_branch_target_check; alter table snapshot_branch add constraint snapshot_target_check check (target_type not in ('content', 'directory', 'revision', 'release', 'snapshot') or length(target) = 20) not valid; alter table snapshot_branch validate constraint snapshot_target_check; create unique index concurrently on snapshot_branch (name) where target_type is null and target is null; \endif -- snapshot_branches create unique index concurrently snapshot_branches_pkey on snapshot_branches(snapshot_id, branch_id); alter table snapshot_branches add primary key using index snapshot_branches_pkey; \if :dbflavor_does_deduplication alter table snapshot_branches add constraint snapshot_branches_snapshot_id_fkey foreign key (snapshot_id) references snapshot(object_id) not valid; alter table snapshot_branches validate constraint snapshot_branches_snapshot_id_fkey; alter table snapshot_branches add constraint snapshot_branches_branch_id_fkey foreign key (branch_id) references snapshot_branch(object_id) not valid; alter table snapshot_branches validate constraint snapshot_branches_branch_id_fkey; \endif -- origin_visit create unique index concurrently origin_visit_pkey on origin_visit(origin, visit); alter table origin_visit add primary key using index origin_visit_pkey; \if :dbflavor_default create index concurrently on origin_visit(date); -- to be reviewed create index concurrently origin_visit_type_date on origin_visit(type, date); -- to be reviewed \endif \if :dbflavor_does_deduplication alter table origin_visit add constraint origin_visit_origin_fkey foreign key (origin) references origin(id) not valid; alter table origin_visit validate constraint origin_visit_origin_fkey; \endif -- origin_visit_status create unique index concurrently origin_visit_status_pkey on origin_visit_status(origin, visit, date); alter table origin_visit_status add primary key using index origin_visit_status_pkey; \if :dbflavor_default alter table origin_visit_status add constraint origin_visit_status_origin_visit_fkey foreign key (origin, visit) references origin_visit(origin, visit) not valid; alter table origin_visit_status validate constraint origin_visit_status_origin_visit_fkey; \endif -- release create unique index concurrently release_pkey on release(id); alter table release add primary key using index release_pkey; \if :dbflavor_default create index concurrently on release(target, target_type); -- to be reviewed create unique index concurrently on release(object_id); -- to be reviewed \endif \if :dbflavor_does_deduplication alter table release add constraint release_author_fkey foreign key (author) references person(id) not valid; alter table release validate constraint release_author_fkey; alter table release add constraint release_date_neg_utc_offset_not_null check (date is null or date_neg_utc_offset is not null) not valid; + alter table release + add constraint release_date_offset_not_null + check (date is null or date_offset_bytes is not null) + not valid; + alter table release validate constraint release_date_neg_utc_offset_not_null; + alter table release + validate constraint release_date_offset_not_null; -- if the author is null, then the date must be null alter table release add constraint release_author_date_check check ((date is null) or (author is not null)) not valid; alter table release validate constraint release_author_date_check; \endif -- metadata_fetcher create unique index metadata_fetcher_pkey on metadata_fetcher(id); alter table metadata_fetcher add primary key using index metadata_fetcher_pkey; \if :dbflavor_does_deduplication create unique index metadata_fetcher_name_version on metadata_fetcher(name, version); \else create index metadata_fetcher_name_version on metadata_fetcher(name, version); \endif -- metadata_authority create unique index concurrently metadata_authority_pkey on metadata_authority(id); alter table metadata_authority add primary key using index metadata_authority_pkey; \if :dbflavor_does_deduplication create unique index concurrently metadata_authority_type_url on metadata_authority(type, url); \else create index concurrently metadata_authority_type_url on metadata_authority(type, url); \endif -- raw_extrinsic_metadata create unique index concurrently raw_extrinsic_metadata_pkey on raw_extrinsic_metadata(id); alter table raw_extrinsic_metadata add primary key using index raw_extrinsic_metadata_pkey; create index concurrently raw_extrinsic_metadata_content_authority_date on raw_extrinsic_metadata(target, authority_id, discovery_date); \if :dbflavor_default alter table raw_extrinsic_metadata add constraint raw_extrinsic_metadata_authority_fkey foreign key (authority_id) references metadata_authority(id) not valid; alter table raw_extrinsic_metadata validate constraint raw_extrinsic_metadata_authority_fkey; alter table raw_extrinsic_metadata add constraint raw_extrinsic_metadata_fetcher_fkey foreign key (fetcher_id) references metadata_fetcher(id) not valid; alter table raw_extrinsic_metadata validate constraint raw_extrinsic_metadata_fetcher_fkey; \endif -- object_counts create unique index concurrently object_counts_pkey on object_counts(object_type); alter table object_counts add primary key using index object_counts_pkey; -- object_counts_bucketed create unique index concurrently object_counts_bucketed_pkey on object_counts_bucketed(line); alter table object_counts_bucketed add primary key using index object_counts_bucketed_pkey; -- extid -- used to query by (extid_type, extid) + to deduplicate the whole row create unique index concurrently on extid(extid_type, extid, extid_version, target_type, target); create index concurrently on extid(target_type, target); diff --git a/swh/storage/tests/storage_tests.py b/swh/storage/tests/storage_tests.py index 765d213e..25be8307 100644 --- a/swh/storage/tests/storage_tests.py +++ b/swh/storage/tests/storage_tests.py @@ -1,4887 +1,4976 @@ # Copyright (C) 2015-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import defaultdict import datetime from datetime import timedelta import inspect import itertools import math import random from typing import Any, ClassVar, Dict, Iterator, Optional from unittest.mock import MagicMock import attr from hypothesis import HealthCheck, given, settings, strategies import pytest from swh.core.api import RemoteException from swh.core.api.classes import stream_results from swh.model import from_disk, hypothesis_strategies from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes from swh.model.model import ( Content, Directory, ExtID, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Revision, + RevisionType, SkippedContent, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) from swh.model.swhids import CoreSWHID, ObjectType from swh.storage import get_storage from swh.storage.cassandra.storage import CassandraStorage from swh.storage.common import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.in_memory import InMemoryStorage from swh.storage.interface import ListOrder, PagedResult, StorageInterface from swh.storage.tests.conftest import function_scoped_fixture_check from swh.storage.utils import ( content_hex_hashes, now, remove_keys, round_to_milliseconds, ) def transform_entries( storage: StorageInterface, dir_: Directory, *, prefix: bytes = b"" ) -> Iterator[Dict[str, Any]]: """Iterate through a directory's entries, and yields the items 'directory_ls' is expected to return; including content metadata for file entries.""" for ent in dir_.entries: if ent.type == "dir": 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, } elif ent.type == "file": contents = storage.content_find({"sha1_git": ent.target}) assert contents ent_dict = contents[0].to_dict() for key in ["ctime", "blake2s256"]: ent_dict.pop(key, None) ent_dict.update( { "dir_id": dir_.id, "type": ent.type, "target": ent.target, "name": prefix + ent.name, "perms": ent.perms, } ) yield ent_dict def assert_contents_ok( expected_contents, actual_contents, keys_to_check={"sha1", "data"} ): """Assert that a given list of contents matches on a given set of keys. """ for k in keys_to_check: expected_list = set([c.get(k) for c in expected_contents]) actual_list = set([c.get(k) for c in actual_contents]) assert actual_list == expected_list, k class LazyContent(Content): def with_data(self): return Content.from_dict({**self.to_dict(), "data": b"42\n"}) 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 == [] # If all the assertions above succeed, then this one should too. # But there's no harm in double-checking. # And we could replace the assertions above by this one, but unlike # the assertions above, it doesn't explain what is missing. assert isinstance(storage, StorageInterface) 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): cont = sample_data.content 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 swh_storage.content_get_data(cont.sha1) == 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 if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_lazy_content(self, swh_storage, sample_data): cont = sample_data.content lazy_content = LazyContent.from_dict(cont.to_dict()) insertion_start_time = now() 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 swh_storage.content_get_data(cont.sha1) == 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() if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_get_data_missing(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] swh_storage.content_add([cont]) # Query a single missing content actual_content_data = swh_storage.content_get_data(cont2.sha1) assert actual_content_data is None # Check content_get does not abort after finding a missing content actual_content_data = swh_storage.content_get_data(cont.sha1) assert actual_content_data == cont.data actual_content_data = swh_storage.content_get_data(cont2.sha1) assert actual_content_data is None def test_content_add_different_input(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[: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): cont, cont2 = sample_data.contents[: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): cont1 = sample_data.content # 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"] 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): cont = sample_data.content swh_storage.content_add([cont, cont]) assert swh_storage.content_get_data(cont.sha1) == cont.data def test_content_update(self, swh_storage, sample_data): cont1 = sample_data.content 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"]) actual_contents = swh_storage.content_get([cont1.sha1]) expected_content = attr.evolve(cont1b, data=None) assert actual_contents == [expected_content] def test_content_add_metadata(self, swh_storage, sample_data): cont = attr.evolve(sample_data.content, data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } expected_cont = cont assert swh_storage.content_get([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): contents = sample_data.contents[: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): cont1 = attr.evolve(sample_data.content, 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_content_add_objstorage_first(self, swh_storage, sample_data): """Tests the objstorage is written to before the DB and journal""" cont = sample_data.content swh_storage.objstorage.content_add = MagicMock(side_effect=Exception("Oops")) # Try to add, but the objstorage crashes try: swh_storage.content_add([cont]) except Exception: pass # The DB must be written to after the objstorage, so the DB should be # unchanged if the objstorage crashed assert swh_storage.content_get_data(cont.sha1) is None # The journal too assert list(swh_storage.journal_writer.journal.objects) == [] def test_skipped_content_add(self, swh_storage, sample_data): contents = sample_data.skipped_contents[: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): cont, cont2 = [ attr.evolve(c, sha1_git=None) for c in sample_data.skipped_contents[: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): cont = sample_data.skipped_content 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 suppress_health_check=function_scoped_fixture_check, ) @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing(self, swh_storage, sample_data, algos): algos |= {"sha1"} content, missing_content = [sample_data.content2, sample_data.skipped_content] swh_storage.content_add([content]) test_contents = [content.to_dict()] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_content.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 @settings(suppress_health_check=function_scoped_fixture_check,) @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing_unknown_algo(self, swh_storage, sample_data, algos): algos |= {"sha1"} content, missing_content = [sample_data.content2, sample_data.skipped_content] swh_storage.content_add([content]) test_contents = [content.to_dict()] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_content.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): # given cont = sample_data.content cont2 = sample_data.content2 missing_cont = sample_data.skipped_content missing_cont2 = sample_data.skipped_content2 swh_storage.content_add([cont, cont2]) # when gen = swh_storage.content_missing_per_sha1( [cont.sha1, missing_cont.sha1, cont2.sha1, missing_cont2.sha1] ) # then assert list(gen) == [missing_cont.sha1, missing_cont2.sha1] def test_content_missing_per_sha1_git(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] missing_cont = sample_data.skipped_content missing_cont2 = sample_data.skipped_content2 swh_storage.content_add([cont, cont2]) contents = [ cont.sha1_git, cont2.sha1_git, missing_cont.sha1_git, missing_cont2.sha1_git, ] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont.sha1_git, missing_cont2.sha1_git] missing_contents = swh_storage.content_missing_per_sha1_git([]) assert list(missing_contents) == [] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [ attr.evolve(c, data=None) 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.results) assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents assert content.ctime is None def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents """ expected_contents = [ attr.evolve(c, data=None) 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.results assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents 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 content in actual_result.results: seen_sha1s.append(content.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, match="limit should not be None"): swh_storage.content_get_partition(1, 16, limit=None) def test_content_get_partition_pagination_generate(self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [ attr.evolve(c, data=None) 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.results) page_token = actual_result.next_page_token if page_token is None: break assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents @pytest.mark.parametrize("algo", sorted(DEFAULT_ALGORITHMS)) def test_content_get(self, swh_storage, sample_data, algo): cont1, cont2 = sample_data.contents[:2] swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get( [getattr(cont1, algo), getattr(cont2, algo)], algo ) # we only retrieve the metadata so no data nor ctime within expected_contents = [attr.evolve(c, data=None) for c in [cont1, cont2]] assert actual_contents == expected_contents for content in actual_contents: assert content.ctime is None @pytest.mark.parametrize("algo", sorted(DEFAULT_ALGORITHMS)) def test_content_get_missing(self, swh_storage, sample_data, algo): cont1, cont2 = sample_data.contents[:2] assert cont1.sha1 != cont2.sha1 missing_cont = sample_data.skipped_content swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get( [getattr(cont1, algo), getattr(cont2, algo), getattr(missing_cont, algo)], algo, ) expected_contents = [ attr.evolve(c, data=None) if c else None for c in [cont1, cont2, None] ] assert actual_contents == expected_contents def test_content_get_random(self, swh_storage, sample_data): cont, cont2, cont3 = sample_data.contents[:3] 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): content = sample_data.content directory = sample_data.directory assert directory.entries[0].target == content.sha1_git swh_storage.content_add([content]) 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 ("directory", directory) in list( swh_storage.journal_writer.journal.objects ) actual_data = list(swh_storage.directory_ls(directory.id)) expected_data = list(transform_entries(swh_storage, directory)) for data in actual_data: assert data in expected_data after_missing = list(swh_storage.directory_missing([directory.id])) assert after_missing == [] if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 + def test_directory_add_with_raw_manifest(self, swh_storage, sample_data): + content = sample_data.content + directory = sample_data.directory + directory = attr.evolve(directory, raw_manifest=b"foo") + directory = attr.evolve(directory, id=directory.compute_hash()) + + assert directory.entries[0].target == content.sha1_git + swh_storage.content_add([content]) + + 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 ("directory", directory) in list( + swh_storage.journal_writer.journal.objects + ) + + actual_data = list(swh_storage.directory_ls(directory.id)) + expected_data = list(transform_entries(swh_storage, directory)) + + for data in actual_data: + assert data in expected_data + + after_missing = list(swh_storage.directory_missing([directory.id])) + assert after_missing == [] + + # TODO: check the recorded manifest + @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists(hypothesis_strategies.directories(), min_size=1, max_size=10) ) def test_directory_add_get_arbitrary(self, swh_storage, directories): swh_storage.directory_add(directories) for directory in directories: - assert swh_storage.directory_get_entries(directory.id) == PagedResult( - results=list(directory.entries), next_page_token=None, - ) + if directory.raw_manifest is None: + assert swh_storage.directory_get_entries(directory.id) == PagedResult( + results=list(directory.entries), next_page_token=None, + ) + else: + # TODO: compare the manifests are the same (currently, we can't + # because there is no way to get the raw_manifest of a directory) + # we can't compare the other fields, because they become non-intrinsic, + # so they may clash between hypothesis runs + pass def test_directory_add_twice(self, swh_storage, sample_data): directory = sample_data.directories[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_ls_recursive(self, swh_storage, sample_data): # create consistent dataset regarding the directories we want to list content, content2 = sample_data.contents[:2] swh_storage.content_add([content, content2]) dir1, dir2, dir3 = sample_data.directories[:3] dir_ids = [d.id for d in [dir1, dir2, dir3]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir1, dir2, dir3]) assert actual_result == {"directory:add": 3} # List directory containing one file actual_data = list(swh_storage.directory_ls(dir1.id, recursive=True)) expected_data = list(transform_entries(swh_storage, dir1)) for data in actual_data: assert data in expected_data # 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(swh_storage, dir2)) for data in actual_data: assert data in expected_data # List directory containing both a known and unknown subdirectory, entries # should be both those of the directory and of the known subdir (up to contents) actual_data = list(swh_storage.directory_ls(dir3.id, recursive=True)) expected_data = list( itertools.chain( transform_entries(swh_storage, dir3), transform_entries(swh_storage, dir2, prefix=b"subdir/"), ) ) for data in actual_data: assert data in expected_data def test_directory_ls_non_recursive(self, swh_storage, sample_data): # create consistent dataset regarding the directories we want to list content, content2 = sample_data.contents[:2] swh_storage.content_add([content, content2]) dir1, dir2, dir3, _, dir5 = sample_data.directories[:5] dir_ids = [d.id for d in [dir1, dir2, dir3, dir5]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir1, dir2, dir3, dir5]) assert actual_result == {"directory:add": 4} # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir1.id)) expected_data = list(transform_entries(swh_storage, dir1)) for data in actual_data: assert data in expected_data # List directory containing a single file actual_data = list(swh_storage.directory_ls(dir2.id)) expected_data = list(transform_entries(swh_storage, dir2)) for data in actual_data: assert data in expected_data # 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(swh_storage, dir3)) for data in actual_data: assert data in expected_data def test_directory_ls_missing_content(self, swh_storage, sample_data): swh_storage.directory_add([sample_data.directory2]) assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [ { "dir_id": sample_data.directory2.id, "length": None, "name": b"oof", "perms": 33188, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "target": sample_data.directory2.entries[0].target, "type": "file", }, ] def test_directory_ls_skipped_content(self, swh_storage, sample_data): swh_storage.directory_add([sample_data.directory2]) cont = SkippedContent( sha1_git=sample_data.directory2.entries[0].target, sha1=b"c" * 20, sha256=None, blake2s256=None, length=42, status="absent", reason="You need a premium subscription to access this content", ) swh_storage.skipped_content_add([cont]) assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [ { "dir_id": sample_data.directory2.id, "length": 42, "name": b"oof", "perms": 33188, "sha1": b"c" * 20, "sha1_git": sample_data.directory2.entries[0].target, "sha256": None, "status": "absent", "target": sample_data.directory2.entries[0].target, "type": "file", }, ] def test_directory_entry_get_by_path(self, swh_storage, sample_data): cont, content2 = sample_data.contents[:2] dir1, dir2, dir3, dir4, dir5 = sample_data.directories[:5] # given dir_ids = [d.id for d in [dir1, dir2, dir3, dir4, dir5]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids 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": content2.sha1_git, "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 `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_entries_pagination(self, swh_storage, sample_data): dir_ = sample_data.directory3 entries = sorted(dir_.entries, key=lambda entry: entry.name) swh_storage.directory_add(sample_data.directories) # No pagination needed actual_data = swh_storage.directory_get_entries(dir_.id) assert sorted(actual_data.results) == sorted(entries) assert actual_data.next_page_token is None, actual_data # A little pagination actual_data = swh_storage.directory_get_entries(dir_.id, limit=2) assert len(actual_data.results) == 2, actual_data assert actual_data.next_page_token is not None, actual_data all_results = list(actual_data.results) actual_data = swh_storage.directory_get_entries( dir_.id, page_token=actual_data.next_page_token ) assert len(actual_data.results) == len(entries) - 2, actual_data assert actual_data.next_page_token is None, actual_data all_results.extend(actual_data.results) assert sorted(all_results) == sorted(entries) @pytest.mark.parametrize("limit", [1, 2, 3, 4, 5]) def test_directory_get_entries(self, swh_storage, sample_data, limit): dir_ = sample_data.directory3 swh_storage.directory_add(sample_data.directories) actual_data = list( stream_results(swh_storage.directory_get_entries, dir_.id, limit=limit,) ) assert sorted(actual_data) == sorted(dir_.entries) def test_directory_get_random(self, swh_storage, sample_data): dir1, dir2, dir3 = sample_data.directories[: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): revision = sample_data.revision 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} if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_twice(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[: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_fractional_timezone(self, swh_storage, sample_data): # When reading a date from this time period on systems configured with # timezone Europe/Paris, postgresql returns them with UTC+00:09:21 as timezone, # but psycopg2 < 2.9.0 had to truncate them. # https://www.psycopg.org/docs/usage.html#time-zones-handling # # There is a workaround in swh.storage.postgresql.storage.Storage.get_db, # to set the timezone to UTC so it works on all psycopg2 versions. # # Therefore, this test always succeeds in tox (because psycopg2 >= 2.9.0) # and on the CI (both because psycopg2 >= 2.9.0 and TZ=UTC); but which means # this test is only useful on machines with older psycopg2 versions and # TZ=Europe/Paris. But the workaround is also only needed on this kind of # configuration, so this is good enough. revision = attr.evolve( sample_data.revision, date=TimestampWithTimezone( timestamp=Timestamp(seconds=-1855958962, microseconds=0), offset=0, negative_utc=False, ), ) 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) ] assert swh_storage.revision_get([revision.id])[0] == revision + def test_revision_add_with_raw_manifest(self, swh_storage, sample_data): + revision = sample_data.revision + revision = attr.evolve(revision, raw_manifest=b"foo") + revision = attr.evolve(revision, id=revision.compute_hash()) + 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) + ] + + assert swh_storage.revision_get([revision.id]) == [revision] + @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists(hypothesis_strategies.revisions(), min_size=1, max_size=10,) ) def test_revision_add_get_arbitrary(self, swh_storage, revisions): # remove non-intrinsic data, so releases inserted with different hypothesis # data can't clash with each other revisions = [ attr.evolve( revision, synthetic=False, metadata=None, committer=attr.evolve(revision.committer, name=None, email=None), author=attr.evolve(revision.author, name=None, email=None), + type=RevisionType.GIT, ) for revision in revisions ] swh_storage.revision_add(revisions) - revs = swh_storage.revision_get([revision.id for revision in revisions]) - assert set(revs) == set(revisions) + for revision in revisions: + (rev,) = swh_storage.revision_get([revision.id]) + if rev.raw_manifest is None: + assert rev == revision + else: + assert rev.raw_manifest == revision.raw_manifest + # we can't compare the other fields, because they become non-intrinsic, + # so they may clash between hypothesis runs def test_revision_add_name_clash(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[: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): revision, revision2 = sample_data.revisions[:2] add_result = swh_storage.revision_add([revision, revision2]) assert add_result == {"revision:add": 2} # order 1 actual_revisions = swh_storage.revision_get([revision.id, revision2.id]) assert actual_revisions == [revision, revision2] # order 2 actual_revisions2 = swh_storage.revision_get([revision2.id, revision.id]) assert actual_revisions2 == [revision2, revision] def test_revision_log(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # rev4 -is-child-of-> rev3 -> rev1, (rev2 -> rev1) swh_storage.revision_add([revision1, revision2, revision3, revision4]) # when 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) == 4 # rev4 -child-> rev3 -> rev1, (rev2 -> rev1) assert actual_results == [revision4, revision3, revision1, revision2] def test_revision_log_with_limit(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # revision4 -is-child-of-> revision3 swh_storage.revision_add([revision3, revision4]) 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] == revision4 def test_revision_log_unknown_revision(self, swh_storage, sample_data): revision = sample_data.revision rev_log = list(swh_storage.revision_log([revision.id])) assert rev_log == [] def test_revision_shortlog(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # rev4 -is-child-of-> rev3 -> (rev1, rev2); rev2 -> rev1 swh_storage.revision_add([revision1, revision2, revision3, revision4]) results = list(swh_storage.revision_shortlog([revision4.id])) actual_results = [[id, tuple(parents)] for (id, parents) in results] assert len(actual_results) == 4 assert actual_results == [ [revision4.id, revision4.parents], [revision3.id, revision3.parents], [revision1.id, revision1.parents], [revision2.id, revision2.parents], ] def test_revision_shortlog_with_limit(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # revision4 -is-child-of-> revision3 swh_storage.revision_add([revision1, revision2, revision3, revision4]) 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): revision, revision2 = sample_data.revisions[:2] swh_storage.revision_add([revision]) actual_revisions = swh_storage.revision_get([revision.id, revision2.id]) assert len(actual_revisions) == 2 assert actual_revisions == [revision, None] def test_revision_get_no_parents(self, swh_storage, sample_data): revision = sample_data.revision swh_storage.revision_add([revision]) actual_revision = swh_storage.revision_get([revision.id])[0] assert revision.parents == () assert actual_revision.parents == () # no parents on this one def test_revision_get_random(self, swh_storage, sample_data): revision1, revision2, revision3 = sample_data.revisions[:3] swh_storage.revision_add([revision1, revision2, revision3]) assert swh_storage.revision_get_random() in { revision1.id, revision2.id, revision3.id, } def test_revision_missing_many(self, swh_storage, sample_data): """Large number of revision ids to check can cause ScyllaDB to reject queries.""" revision = sample_data.revision ids = [bytes([b1, b2]) * 10 for b1 in range(256) for b2 in range(10)] ids.append(revision.id) ids.sort() init_missing = swh_storage.revision_missing(ids) assert set(init_missing) == set(ids) actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing(ids) assert set(end_missing) == set(ids) - {revision.id} def test_extid_add_git(self, swh_storage, sample_data): gitids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=gitid, extid_type="git", target=CoreSWHID(object_id=gitid, object_type=ObjectType.REVISION,), ) for gitid in gitids ] assert swh_storage.extid_get_from_extid("git", gitids) == [] assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == [] summary = swh_storage.extid_add(extids) assert summary == {"extid:add": len(gitids)} assert swh_storage.extid_get_from_extid("git", gitids) == extids assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids assert swh_storage.extid_get_from_extid("hg", gitids) == [] assert swh_storage.extid_get_from_target(ObjectType.RELEASE, gitids) == [] # check ExtIDs have been added to the journal extids_in_journal = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "extid" ] assert extids == extids_in_journal def test_extid_add_hg(self, swh_storage, sample_data): def get_node(revision): node = None if revision.extra_headers: node = dict(revision.extra_headers).get(b"node") if node is None and revision.metadata: node = hash_to_bytes(revision.metadata.get("node")) return node swhids = [ revision.id for revision in sample_data.revisions if revision.type.value == "hg" ] extids = [ get_node(revision) for revision in sample_data.revisions if revision.type.value == "hg" ] assert swh_storage.extid_get_from_extid("hg", extids) == [] assert swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == [] extid_objs = [ ExtID( extid=hgid, extid_type="hg", extid_version=1, target=CoreSWHID(object_id=swhid, object_type=ObjectType.REVISION,), ) for hgid, swhid in zip(extids, swhids) ] summary = swh_storage.extid_add(extid_objs) assert summary == {"extid:add": len(swhids)} assert swh_storage.extid_get_from_extid("hg", extids) == extid_objs assert ( swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == extid_objs ) assert swh_storage.extid_get_from_extid("git", extids) == [] assert swh_storage.extid_get_from_target(ObjectType.RELEASE, swhids) == [] # check ExtIDs have been added to the journal extids_in_journal = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "extid" ] assert extid_objs == extids_in_journal def test_extid_add_twice(self, swh_storage, sample_data): gitids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=gitid, extid_type="git", target=CoreSWHID(object_id=gitid, object_type=ObjectType.REVISION,), ) for gitid in gitids ] summary = swh_storage.extid_add(extids) assert summary == {"extid:add": len(gitids)} # add them again, should be noop summary = swh_storage.extid_add(extids) # assert summary == {"extid:add": 0} assert swh_storage.extid_get_from_extid("git", gitids) == extids assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids def test_extid_add_extid_multicity(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=extid, extid_type="git", extid_version=2, target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] swh_storage.extid_add(extids) # try to add "modified-extid" versions, should be added extids2 = [ ExtID( extid=extid, extid_type="hg", extid_version=2, target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] swh_storage.extid_add(extids2) assert swh_storage.extid_get_from_extid("git", ids) == extids assert swh_storage.extid_get_from_extid("hg", ids) == extids2 assert set(swh_storage.extid_get_from_target(ObjectType.REVISION, ids)) == { *extids, *extids2, } def test_extid_add_target_multicity(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=extid, extid_type="git", target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] swh_storage.extid_add(extids) # try to add "modified" versions, should be added extids2 = [ ExtID( extid=extid, extid_type="git", target=CoreSWHID(object_id=extid, object_type=ObjectType.RELEASE,), ) for extid in ids ] swh_storage.extid_add(extids2) assert set(swh_storage.extid_get_from_extid("git", ids)) == {*extids, *extids2} assert swh_storage.extid_get_from_target(ObjectType.REVISION, ids) == extids assert swh_storage.extid_get_from_target(ObjectType.RELEASE, ids) == extids2 def test_extid_version_behavior(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] # Insert extids with several different versions extids = [ ExtID( extid=extid, extid_type="git", extid_version=0, target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] + [ ExtID( extid=extid, extid_type="git", extid_version=1, target=CoreSWHID(object_id=extid, object_type=ObjectType.REVISION,), ) for extid in ids ] swh_storage.extid_add(extids) # Check that both versions get returned for git_id in ids: objs = swh_storage.extid_get_from_extid("git", [git_id]) assert len(objs) == 2 assert set(obj.extid_version for obj in objs) == {0, 1} for swhid in ids: objs = swh_storage.extid_get_from_target(ObjectType.REVISION, [swhid]) assert len(objs) == 2 assert set(obj.extid_version for obj in objs) == {0, 1} for version in [0, 1]: for git_id in ids: objs = swh_storage.extid_get_from_extid( "git", [git_id], version=version ) assert len(objs) == 1 assert objs[0].extid_version == version for swhid in ids: objs = swh_storage.extid_get_from_target( ObjectType.REVISION, [swhid], extid_version=version, extid_type="git", ) assert len(objs) == 1 assert objs[0].extid_version == version assert objs[0].extid_type == "git" def test_extid_version_behavior_failure(self, swh_storage, sample_data): """Calls with wrong input should raise""" ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] # Other edge cases with pytest.raises( (ValueError, RemoteException), match="both extid_type and extid_version" ): swh_storage.extid_get_from_target( ObjectType.REVISION, [ids[0]], extid_version=0 ) with pytest.raises( (ValueError, RemoteException), match="both extid_type and extid_version" ): swh_storage.extid_get_from_target( ObjectType.REVISION, [ids[0]], extid_type="git" ) def test_release_add(self, swh_storage, sample_data): release, release2 = sample_data.releases[: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} if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 + def test_release_add_with_raw_manifest(self, swh_storage, sample_data): + release = sample_data.releases[0] + release = attr.evolve(release, raw_manifest=b"foo") + release = attr.evolve(release, id=release.compute_hash()) + + init_missing = swh_storage.release_missing([release.id]) + assert list(init_missing) == [release.id] + + 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), + ] + + assert swh_storage.release_get([release.id]) == [release] + @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given(strategies.lists(hypothesis_strategies.releases(), min_size=1, max_size=10,)) def test_release_add_get_arbitrary(self, swh_storage, releases): # remove non-intrinsic data, so releases inserted with different hypothesis # data can't clash with each other releases = [ attr.evolve( release, synthetic=False, metadata=None, author=attr.evolve(release.author, name=None, email=None) if release.author else None, ) for release in releases ] swh_storage.release_add(releases) - assert set( - swh_storage.release_get([release.id for release in releases]) - ) == set(releases) + for release in releases: + (rev,) = swh_storage.release_get([release.id]) + if rev.raw_manifest is None: + assert rev == release + else: + assert rev.raw_manifest == release.raw_manifest + # we can't compare the other fields, because they become non-intrinsic, + # so they may clash between hypothesis runs def test_release_add_no_author_date(self, swh_storage, sample_data): full_release = sample_data.release 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_twice(self, swh_storage, sample_data): release, release2 = sample_data.releases[: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): 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.releases[:2] ] actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 2} def test_release_get(self, swh_storage, sample_data): release, release2, release3 = sample_data.releases[:3] # given swh_storage.release_add([release, release2]) # when actual_releases = swh_storage.release_get([release.id, release2.id]) # then assert actual_releases == [release, release2] unknown_releases = swh_storage.release_get([release3.id]) assert unknown_releases[0] is None def test_release_get_order(self, swh_storage, sample_data): release, release2 = sample_data.releases[:2] add_result = swh_storage.release_add([release, release2]) assert add_result == {"release:add": 2} # order 1 actual_releases = swh_storage.release_get([release.id, release2.id]) assert actual_releases == [release, release2] # order 2 actual_releases2 = swh_storage.release_get([release2.id, release.id]) assert actual_releases2 == [release2, release] def test_release_get_random(self, swh_storage, sample_data): release, release2, release3 = sample_data.releases[: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): origins = list(sample_data.origins) origin_urls = [o.url for o in origins] assert swh_storage.origin_get(origin_urls) == [None] * len(origins) stats = swh_storage.origin_add(origins) assert stats == {"origin:add": len(origin_urls)} actual_origins = swh_storage.origin_get(origin_urls) assert actual_origins == origins assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin) for origin in origins] ) if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == len(origins) def test_origin_add_twice(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] 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_twice_at_once(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] add1 = swh_storage.origin_add([origin, origin2, 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, origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin), ("origin", origin2),] ) assert add2 == {"origin:add": 0} def test_origin_get(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] assert swh_storage.origin_get([origin.url]) == [None] swh_storage.origin_add([origin]) actual_origins = swh_storage.origin_get([origin.url]) assert actual_origins == [origin] actual_origins = swh_storage.origin_get([origin.url, "not://exists"]) assert actual_origins == [origin, 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__unknown_origin(self, swh_storage): actual_page = swh_storage.origin_visit_get("foo") assert actual_page.next_page_token is None assert actual_page.results == [] assert actual_page == PagedResult() def test_origin_visit_get__validation_failure(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) with pytest.raises( StorageArgumentException, match="page_token must be a string" ): swh_storage.origin_visit_get(origin.url, page_token=10) # not bytes with pytest.raises( StorageArgumentException, match="order must be a ListOrder value" ): swh_storage.origin_visit_get(origin.url, order="foobar") # wrong order def test_origin_visit_get_all(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) ov1, ov2, ov3 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) # order asc, no token, no limit actual_page = swh_storage.origin_visit_get(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [ov1, ov2, ov3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get(origin.url, limit=2) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov1, ov2] # order asc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ov3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get(origin.url, limit=1) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov1] # order asc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov3] # order asc, token, limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=2 ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov3] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov2] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [ov3] # order desc, no token, no limit actual_page = swh_storage.origin_visit_get(origin.url, order=ListOrder.DESC) assert actual_page.next_page_token is None assert actual_page.results == [ov3, ov2, ov1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get( origin.url, limit=2, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov3, ov2] # order desc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get( origin.url, limit=1, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov3] # order desc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov1] # order desc, token, limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov2] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov1] def test_origin_visit_status_get__unknown_cases(self, swh_storage, sample_data): origin = sample_data.origin actual_page = swh_storage.origin_visit_status_get("foobar", 1) assert actual_page.next_page_token is None assert actual_page.results == [] actual_page = swh_storage.origin_visit_status_get(origin.url, 1) assert actual_page.next_page_token is None assert actual_page.results == [] origin = sample_data.origin swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), ] )[0] actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit + 10) assert actual_page.next_page_token is None assert actual_page.results == [] def test_origin_visit_status_add_unknown_type(self, swh_storage, sample_data): ov = OriginVisit( origin=sample_data.origin.url, date=now(), type=sample_data.type_visit1, visit=42, ) ovs = OriginVisitStatus( origin=ov.origin, visit=ov.visit, date=now(), status="created", snapshot=None, ) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_status_add([ovs]) swh_storage.origin_add([sample_data.origin]) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_status_add([ovs]) swh_storage.origin_visit_add([ov]) swh_storage.origin_visit_status_add([ovs]) def test_origin_visit_status_get_all(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) date_visit3 = round_to_milliseconds(now()) date_visit1 = date_visit3 - datetime.timedelta(hours=2) date_visit2 = date_visit3 - datetime.timedelta(hours=1) assert date_visit1 < date_visit2 < date_visit3 ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=date_visit1, type=sample_data.type_visit1, ), ] )[0] ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit1, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit2, type=ov1.type, status="partial", snapshot=None, ) ovs3 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit3, type=ov1.type, status="full", snapshot=sample_data.snapshot.id, metadata={}, ) swh_storage.origin_visit_status_add([ovs2, ovs3]) # order asc, no token, no limit actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit) assert actual_page.next_page_token is None assert actual_page.results == [ovs1, ovs2, ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1, ovs2] # order asc, token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs3] # order asc, token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, limit=2 ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1, ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3] # order desc, no token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3, ovs2, ovs1] # order desc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs3, ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs1] # order desc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, order=ListOrder.DESC, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs3] # order desc, token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs1] # order desc, token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC, limit=1, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs1] def test_origin_visit_status_get_random(self, swh_storage, sample_data): origins = sample_data.origins[: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=hash_to_bytes( "9b922e6d8d5b803c1582aabe5525b7b91150788e" ), ) ] ) if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(origins) assert stats["origin_visit"] == len(origins) * len(visits) random_ovs = swh_storage.origin_visit_status_get_random(visit_type) assert random_ovs assert random_ovs.origin is not None assert random_ovs.origin in [o.url for o in origins] assert random_ovs.type is not None def test_origin_visit_status_get_random_nothing_found( self, swh_storage, sample_data ): origins = sample_data.origins 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_status_get_random(visit_type) assert random_origin_visit is None def test_origin_snapshot_get_all(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) # add some random visits within the selection range visits = self._generate_random_visits() visit_type = "git" # set first visit to a null snapshot visit = swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=visits[0], type=visit_type,)] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="created", snapshot=None, ) ] ) # add visits to origin snapshots = set() for date_visit in visits[1:]: visit = swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=date_visit, type=visit_type,)] )[0] # pick a random snapshot and keep track of it snapshot = random.choice(sample_data.snapshots).id snapshots.add(snapshot) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=snapshot, ) ] ) # check expected snapshots are returned assert set(swh_storage.origin_snapshot_get_all(origin.url)) == snapshots def test_origin_get_by_sha1(self, swh_storage, sample_data): origin = sample_data.origin assert swh_storage.origin_get([origin.url])[0] 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): unknown_origin = sample_data.origin assert swh_storage.origin_get([unknown_origin.url])[0] is None origins = list(swh_storage.origin_get_by_sha1([sha1(unknown_origin.url)])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] actual_page = swh_storage.origin_search(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [] actual_page = swh_storage.origin_search(origin.url, regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [] swh_storage.origin_add([origin]) actual_page = swh_storage.origin_search(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [origin] actual_page = swh_storage.origin_search(f".{origin.url[1:-1]}.", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin] swh_storage.origin_add([origin2]) actual_page = swh_storage.origin_search(origin2.url) assert actual_page.next_page_token is None assert actual_page.results == [origin2] actual_page = swh_storage.origin_search(f".{origin2.url[1:-1]}.", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_no_regexp(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search("/") assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search("/", page_token=None, limit=1) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( "/", page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_regexp_substring(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search("/", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search( "/", page_token=None, limit=1, regexp=True ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( "/", page_token=next_page_token, limit=1, regexp=True ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_regexp_fullstring(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search(".*/.*", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search( ".*/.*", page_token=None, limit=1, regexp=True ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( ".*/.*", page_token=next_page_token, limit=1, regexp=True ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_no_visit_types(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) actual_page = swh_storage.origin_search(origin.url, visit_types=["git"]) assert actual_page.next_page_token is None assert actual_page.results == [] def test_origin_search_with_visit_types(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) swh_storage.origin_visit_add( [ OriginVisit(origin=origin.url, date=now(), type="git"), OriginVisit(origin=origin2.url, date=now(), type="svn"), ] ) actual_page = swh_storage.origin_search(origin.url, visit_types=["git"]) assert actual_page.next_page_token is None assert actual_page.results == [origin] actual_page = swh_storage.origin_search(origin2.url, visit_types=["svn"]) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_multiple_visit_types(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) def _add_visit_type(visit_type): swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=now(), type=visit_type)] ) def _check_visit_types(visit_types): actual_page = swh_storage.origin_search(origin.url, visit_types=visit_types) assert actual_page.next_page_token is None assert actual_page.results == [origin] _add_visit_type("git") _check_visit_types(["git"]) _check_visit_types(["git", "hg"]) _add_visit_type("hg") _check_visit_types(["hg"]) _check_visit_types(["git", "hg"]) def test_origin_visit_add(self, swh_storage, sample_data): origin1 = sample_data.origins[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=sample_data.type_visit1, ) visit2 = OriginVisit( origin=origin1.url, date=date_visit2, type=sample_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 assert ov1.visit == 1 assert ov2.visit == 2 ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_visit2, type=ov2.type, status="created", snapshot=None, ) actual_visits = swh_storage.origin_visit_get(origin1.url).results expected_visits = [ov1, ov2] assert len(expected_visits) == len(actual_visits) for visit in expected_visits: assert visit in actual_visits actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = list( [("origin", origin1)] + [("origin_visit", visit) for visit in expected_visits] * 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_replayed(self, swh_storage, sample_data): """Tests adding a visit with an id makes sure the next id is higher""" origin1 = sample_data.origins[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=sample_data.type_visit1, visit=42 ) visit2 = OriginVisit( origin=origin1.url, date=date_visit2, type=sample_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 assert ov1.visit == 42 assert ov2.visit == 43 visit3 = OriginVisit( origin=origin1.url, date=date_visit, type=sample_data.type_visit1, visit=12 ) visit4 = OriginVisit( origin=origin1.url, date=date_visit2, type=sample_data.type_visit2, ) # add once ov3, ov4 = swh_storage.origin_visit_add([visit3, visit4]) # then again (will be ignored as they already exist) origin_visit3, origin_visit4 = swh_storage.origin_visit_add([ov3, ov4]) assert ov3 == origin_visit3 assert ov4 == origin_visit4 assert ov3.visit == 12 assert ov4.visit == 44 def test_origin_visit_add_validation(self, swh_storage, sample_data): """Unknown origin when adding visits should raise""" visit = attr.evolve(sample_data.origin_visit, origin="something-unknonw") 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): """Correct origin visit statuses should add a new visit status """ snapshot = sample_data.snapshot origin1 = sample_data.origins[1] origin2 = Origin(url="new-origin") swh_storage.origin_add([origin1, origin2]) ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin2.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=sample_data.date_visit2, type=ov2.type, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, type=ov1.type, status="full", snapshot=snapshot.id, ) date_visit_now = round_to_milliseconds(now()) visit_status2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_visit_now, type=ov2.type, status="ongoing", snapshot=None, metadata={"intrinsic": "something"}, ) stats = swh_storage.origin_visit_status_add([visit_status1, visit_status2]) assert stats == {"origin_visit_status:add": 2} visit = swh_storage.origin_visit_get_latest(origin1.url, require_snapshot=True) visit_status = swh_storage.origin_visit_status_get_latest( origin1.url, visit.visit, require_snapshot=True ) assert visit_status == visit_status1 visit = swh_storage.origin_visit_get_latest(origin2.url, require_snapshot=False) visit_status = swh_storage.origin_visit_status_get_latest( origin2.url, visit.visit, require_snapshot=False ) assert origin2.url != origin1.url assert visit_status == visit_status2 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): """Correct origin visit statuses should add a new visit status """ snapshot = sample_data.snapshot origin1 = sample_data.origins[1] swh_storage.origin_add([origin1]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), ] )[0] ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, type=ov1.type, status="full", snapshot=snapshot.id, ) stats = swh_storage.origin_visit_status_add([visit_status1]) assert stats == {"origin_visit_status:add": 1} # second call will ignore existing entries (will send to storage though) stats = swh_storage.origin_visit_status_add([visit_status1]) # ...so the storage still returns it as an addition assert stats == {"origin_visit_status:add": 1} visit_status = swh_storage.origin_visit_status_get_latest(ov1.origin, ov1.visit) assert visit_status == visit_status1 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): origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit1, ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit3, type=sample_data.type_visit2, ) visit3 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit3, ) ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) ovs1 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=sample_data.date_visit3, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin.url, visit=ov3.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3]) # Simple case actual_visit = swh_storage.origin_visit_find_by_date( origin.url, sample_data.date_visit3 ) assert actual_visit == ov2 # There are two visits at the same date, the latest must be returned actual_visit = swh_storage.origin_visit_find_by_date( origin.url, sample_data.date_visit2 ) assert actual_visit == ov3 def test_origin_visit_find_by_date__unknown_origin(self, swh_storage, sample_data): actual_visit = swh_storage.origin_visit_find_by_date( "foo", sample_data.date_visit2 ) assert actual_visit is None def test_origin_visit_get_by(self, swh_storage, sample_data): snapshot = sample_data.snapshot origins = sample_data.origins[:2] swh_storage.origin_add(origins) origin_url, origin_url2 = [o.url for o in origins] visit = OriginVisit( origin=origin_url, date=sample_data.date_visit2, type=sample_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=sample_data.date_visit3, type=sample_data.type_visit3, ) visit3 = OriginVisit( origin=origin_url2, date=sample_data.date_visit3, type=sample_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, ) ] ) actual_visit = swh_storage.origin_visit_get_by(origin_url, origin_visit1.visit) assert actual_visit == origin_visit1 def test_origin_visit_get_by__no_result(self, swh_storage, sample_data): actual_visit = swh_storage.origin_visit_get_by("unknown", 10) # unknown origin assert actual_visit is None origin = sample_data.origin swh_storage.origin_add([origin]) actual_visit = swh_storage.origin_visit_get_by(origin.url, 999) # unknown visit assert actual_visit is None def test_origin_visit_get_latest_edge_cases(self, swh_storage, sample_data): # unknown origin so no result assert swh_storage.origin_visit_get_latest("unknown-origin") is None # unknown type so no result origin = sample_data.origin swh_storage.origin_add([origin]) assert swh_storage.origin_visit_get_latest(origin.url, type="unknown") is None # unknown allowed statuses should raise with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"): swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["unknown"] ) def test_origin_visit_get_latest_filter_type(self, swh_storage, sample_data): """Filtering origin visit get latest with filter type should be ok """ origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type="hg", ) date_now = round_to_milliseconds(now()) visit3 = OriginVisit(origin=origin.url, date=date_now, type="hg",) assert sample_data.date_visit1 < sample_data.date_visit2 assert sample_data.date_visit2 < date_now ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) # Check type filter is ok actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="git") assert actual_visit == ov1 actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="hg") assert actual_visit == ov3 actual_visit_unknown_type = swh_storage.origin_visit_get_latest( origin.url, type="npm", # no visit matching that type ) assert actual_visit_unknown_type is None def test_origin_visit_get_latest(self, swh_storage, sample_data): empty_snapshot, complete_snapshot = sample_data.snapshots[1:3] origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type="hg", ) date_now = round_to_milliseconds(now()) visit3 = OriginVisit(origin=origin.url, date=date_now, type="hg",) assert visit1.date < visit2.date assert visit2.date < visit3.date ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) # no filters, latest visit is the last one (whose date is most recent) actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # 3 visits, none has snapshot so nothing is returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit is None # visit are created with "created" status, so nothing will get returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["partial"] ) assert actual_visit is None # visit are created with "created" status, so most recent again actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["created"] ) assert actual_visit == ov3 # Add snapshot to visit1; require_snapshot=True makes it return first visit swh_storage.snapshot_add([complete_snapshot]) visit_status_with_snapshot = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=round_to_milliseconds(now()), type=ov1.type, status="ongoing", snapshot=complete_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status_with_snapshot]) # only the first visit has a snapshot now actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit == ov1 # only the first visit has a status ongoing now actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["ongoing"] ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, require_snapshot=True ) assert actual_visit_status == visit_status_with_snapshot # ... and require_snapshot=False (defaults) still returns latest visit (3rd) actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=False ) assert actual_visit == ov3 # no specific filter, this returns as before the latest visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # Status filter: all three visits are status=ongoing, so no visit # returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit is None visit_status1_full = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=round_to_milliseconds(now()), type=ov1.type, status="full", snapshot=complete_snapshot.id, ) # Mark the first visit as completed and check status filter again swh_storage.origin_visit_status_add([visit_status1_full]) # only the first visit has the full status actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, allowed_statuses=["full"] ) assert actual_visit_status == visit_status1_full # no specific filter, this returns as before the latest visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([empty_snapshot]) visit_status2_full = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=round_to_milliseconds(now()), type=ov2.type, status="ongoing", snapshot=empty_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status2_full]) actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) # 2nd visit is most recent with a snapshot assert actual_visit == ov2 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov2.visit, require_snapshot=True ) assert actual_visit_status == visit_status2_full # no specific filter, this returns as before the latest visit, 3rd one actual_origin = swh_storage.origin_visit_get_latest(origin.url) assert actual_origin == ov3 # full status is still the first visit actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit == ov1 # Add snapshot to visit3 (same date as visit2) visit_status3_with_snapshot = OriginVisitStatus( origin=ov3.origin, visit=ov3.visit, date=round_to_milliseconds(now()), type=ov3.type, status="ongoing", snapshot=complete_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status3_with_snapshot]) # full status is still the first visit actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"], require_snapshot=True, ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, visit=actual_visit.visit, allowed_statuses=["full"], require_snapshot=True, ) assert actual_visit_status == visit_status1_full # most recent is still the 3rd visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # 3rd visit has a snapshot now, so it's elected actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit == ov3 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov3.visit, require_snapshot=True ) assert actual_visit_status == visit_status3_with_snapshot def test_origin_visit_get_latest__same_date(self, swh_storage, sample_data): empty_snapshot, complete_snapshot = sample_data.snapshots[1:3] origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="hg", ) ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2]) # ties should be broken by using the visit id actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov2 def test_origin_visit_get_latest_order(self, swh_storage, sample_data): empty_snapshot, complete_snapshot = sample_data.snapshots[1:3] origin = sample_data.origin id1 = 2 id2 = 1 id3 = 3 date1 = datetime.datetime(2021, 8, 2, tzinfo=datetime.timezone.utc) date2 = datetime.datetime(2021, 8, 3, tzinfo=datetime.timezone.utc) date3 = datetime.datetime(2021, 8, 1, tzinfo=datetime.timezone.utc) swh_storage.origin_add([origin]) visit1 = OriginVisit(origin=origin.url, visit=id1, date=date1, type="git",) visit2 = OriginVisit(origin=origin.url, visit=id2, date=date2, type="hg",) visit3 = OriginVisit(origin=origin.url, visit=id3, date=date3, type="tar",) ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) # no filters, latest visit is the last one (whose date is most recent) actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov2 def test_origin_visit_get_latest__not_last(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) visit1, visit2 = sample_data.origin_visits[:2] assert visit1.origin == origin.url swh_storage.origin_visit_add([visit1]) ov1 = swh_storage.origin_visit_get_latest(origin.url) # Add snapshot to visit1, latest snapshot = visit 1 snapshot complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=visit2.date, status="partial", snapshot=None, ) ] ) assert visit1.date < visit2.date # no snapshot associated to the visit, so None visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["partial"], require_snapshot=True, ) assert visit is None date_now = now() assert visit2.date < date_now swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_now, status="full", snapshot=complete_snapshot.id, ) ] ) swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=now(), type=visit1.type,)] ) visit = swh_storage.origin_visit_get_latest(origin.url, require_snapshot=True) assert visit is not None def test_origin_visit_status_get_latest__validation(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) # unknown allowed statuses should raise with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"): swh_storage.origin_visit_status_get_latest( origin.url, visit1.visit, allowed_statuses=["unknown"] ) def test_origin_visit_status_get_latest(self, swh_storage, sample_data): snapshot = sample_data.snapshots[2] origin1 = sample_data.origin swh_storage.origin_add([origin1]) # to have some reference visits ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin1.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) swh_storage.snapshot_add([snapshot]) date_now = round_to_milliseconds(now()) assert sample_data.date_visit1 < sample_data.date_visit2 assert sample_data.date_visit2 < date_now ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="partial", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit2, type=ov1.type, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=sample_data.date_visit2 + datetime.timedelta(minutes=1), # to not be ignored type=ov2.type, status="ongoing", snapshot=None, ) ovs4 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_now, type=ov2.type, 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): revision, rev2 = sample_data.revisions[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 = 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): empty_snapshot = sample_data.snapshots[1] empty_snapshot_dict = empty_snapshot.to_dict() origin = sample_data.origin swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_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=ov1.origin, visit=ov1.visit, date=date_now, type=ov1.type, status="full", snapshot=empty_snapshot.id, ) ] ) by_id = swh_storage.snapshot_get(empty_snapshot.id) assert by_id == {**empty_snapshot_dict, "next_branch": None} ovs1 = OriginVisitStatus.from_dict( { "origin": ov1.origin, "date": sample_data.date_visit1, "type": ov1.type, "visit": ov1.visit, "status": "created", "snapshot": None, "metadata": None, } ) ovs2 = OriginVisitStatus.from_dict( { "origin": ov1.origin, "date": date_now, "type": ov1.type, "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): complete_snapshot = sample_data.snapshots[2] complete_snapshot_dict = complete_snapshot.to_dict() origin = sample_data.origin swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] 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} @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given(strategies.lists(hypothesis_strategies.snapshots(), min_size=1, max_size=10)) def test_snapshot_add_get_arbitrary(self, swh_storage, snapshots): swh_storage.snapshot_add(snapshots) for snapshot in snapshots: assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } def test_snapshot_add_many(self, swh_storage, sample_data): snapshot, _, complete_snapshot = sample_data.snapshots[: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, } if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_incremental(self, swh_storage, sample_data): snapshot, _, complete_snapshot = sample_data.snapshots[: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): snapshot, empty_snapshot = sample_data.snapshots[: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_count_branches(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[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_count_branches_with_filtering(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[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, branch_name_exclude_prefix=b"release" ) expected_snp_size = { "alias": 1, "content": 1, "directory": 2, "revision": 1, "snapshot": 1, None: 1, } assert snp_size == expected_snp_size def test_snapshot_add_count_branches_with_filtering_edge_cases( self, swh_storage, sample_data ): snapshot = Snapshot( branches={ b"\xaa\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xaa\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff": SnapshotBranch( target=sample_data.release.id, target_type=TargetType.RELEASE, ), b"\xff\xff\x00": SnapshotBranch( target=sample_data.release.id, target_type=TargetType.RELEASE, ), b"dangling": None, }, ) swh_storage.snapshot_add([snapshot]) assert swh_storage.snapshot_count_branches( snapshot.id, branch_name_exclude_prefix=b"\xaa\xff" ) == {None: 1, "release": 2} assert swh_storage.snapshot_count_branches( snapshot.id, branch_name_exclude_prefix=b"\xff\xff" ) == {None: 1, "revision": 2} def test_snapshot_add_get_paginated(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.branches branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches(snp_id, branches_from=b"release") rel_idx = branch_names.index(b"release") expected_snapshot = { "id": snp_id, "branches": {name: branches[name] for name in branch_names[rel_idx:]}, "next_branch": None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches(snp_id, branches_count=1) expected_snapshot = { "id": snp_id, "branches": {branch_names[0]: branches[branch_names[0]],}, "next_branch": b"content", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b"directory", branches_count=3 ) dir_idx = branch_names.index(b"directory") expected_snapshot = { "id": snp_id, "branches": { name: branches[name] for name in branch_names[dir_idx : dir_idx + 3] }, "next_branch": branch_names[dir_idx + 3], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage, sample_data): origin = sample_data.origin complete_snapshot = sample_data.snapshots[2] swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_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.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 [TargetType.RELEASE, TargetType.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 == TargetType.ALIAS }, "next_branch": None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.branches branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2" ) expected_snapshot = { "id": snp_id, "branches": {name: branches[name] for name in (b"directory2", b"release")}, "next_branch": None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=1 ) expected_snapshot = { "id": snp_id, "branches": {b"directory": branches[b"directory"]}, "next_branch": b"directory2", } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=2 ) expected_snapshot = { "id": snp_id, "branches": { name: branches[name] for name in (b"directory", b"directory2") }, "next_branch": b"release", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2", branches_count=1, ) dir_idx = branch_names.index(b"directory2") expected_snapshot = { "id": snp_id, "branches": {branch_names[dir_idx]: branches[branch_names[dir_idx]],}, "next_branch": b"release", } assert snapshot == expected_snapshot def test_snapshot_add_get_branch_by_type(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[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_by_branches_name_pattern(self, swh_storage, sample_data): snapshot = Snapshot( branches={ b"refs/heads/master": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/heads/incoming": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/pull/1": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/pull/2": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"dangling": None, b"\xaa\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xaa\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot]) for include_pattern, exclude_prefix, nb_results in ( (b"pull", None, 2), (b"incoming", None, 1), (b"dangling", None, 1), (None, b"refs/heads/", 7), (b"refs", b"refs/heads/master", 3), (b"refs", b"refs/heads/master", 3), (None, b"\xaa\xff", 7), (None, b"\xff\xff", 7), ): branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=include_pattern, branch_name_exclude_prefix=exclude_prefix, )["branches"] expected_branches = [ branch_name for branch_name in snapshot.branches if (include_pattern is None or include_pattern in branch_name) and ( exclude_prefix is None or not branch_name.startswith(exclude_prefix) ) ] assert sorted(branches) == sorted(expected_branches) assert len(branches) == nb_results def test_snapshot_add_get_by_branches_name_pattern_filtered_paginated( self, swh_storage, sample_data ): pattern = b"foo" nb_branches_by_target_type = 10 branches = {} for i in range(nb_branches_by_target_type): branches[f"branch/directory/bar{i}".encode()] = SnapshotBranch( target=sample_data.directory.id, target_type=TargetType.DIRECTORY, ) branches[f"branch/revision/bar{i}".encode()] = SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ) branches[f"branch/directory/{pattern}{i}".encode()] = SnapshotBranch( target=sample_data.directory.id, target_type=TargetType.DIRECTORY, ) branches[f"branch/revision/{pattern}{i}".encode()] = SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ) snapshot = Snapshot(branches=branches) swh_storage.snapshot_add([snapshot]) branches_count = nb_branches_by_target_type // 2 for target_type in ( TargetType.DIRECTORY, TargetType.REVISION, ): target_type_str = target_type.value partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=pattern, target_types=[target_type_str], branches_count=branches_count, ) branches = partial_branches["branches"] expected_branches = [ branch_name for branch_name, branch_data in snapshot.branches.items() if pattern in branch_name and branch_data.target_type == target_type ][:branches_count] assert sorted(branches) == sorted(expected_branches) assert ( partial_branches["next_branch"] == f"branch/{target_type_str}/{pattern}{branches_count}".encode() ) partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=pattern, target_types=[target_type_str], branches_from=partial_branches["next_branch"], ) branches = partial_branches["branches"] expected_branches = [ branch_name for branch_name, branch_data in snapshot.branches.items() if pattern in branch_name and branch_data.target_type == target_type ][branches_count:] assert sorted(branches) == sorted(expected_branches) assert partial_branches["next_branch"] is None def test_snapshot_get_branches_from_no_result(self, swh_storage, sample_data): snapshot = Snapshot( branches={ b"refs/heads/master": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot]) partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branches_from=b"s", ) assert partial_branches is not None assert partial_branches["branches"] == {} @settings(suppress_health_check=function_scoped_fixture_check,) @given(hypothesis_strategies.snapshots(min_size=1)) def test_snapshot_get_unknown_snapshot(self, swh_storage, unknown_snapshot): assert swh_storage.snapshot_get(unknown_snapshot.id) is None assert swh_storage.snapshot_get_branches(unknown_snapshot.id) is None def test_snapshot_add_get(self, swh_storage, sample_data): snapshot = sample_data.snapshot origin = sample_data.origin swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) ov1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.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 actual_visit = swh_storage.origin_visit_get_by(origin.url, ov1.visit) assert actual_visit == ov1 visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, require_snapshot=True ) assert visit_status.snapshot == snapshot.id def test_snapshot_get_random(self, swh_storage, sample_data): snapshot, empty_snapshot, complete_snapshot = sample_data.snapshots[: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): snapshot, missing_snapshot = sample_data.snapshots[: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): if isinstance(swh_storage, CassandraStorage) and not isinstance( swh_storage, InMemoryStorage ): pytest.skip("Cassandra backend does not support stat counters") origin = sample_data.origin snapshot = sample_data.snapshot revision = sample_data.revision release = sample_data.release directory = sample_data.directory content = sample_data.content 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=sample_data.date_visit2, type=sample_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): origin_content = sample_data.content 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 assert actually_present[0].ctime is not None assert actually_present[0].ctime.tzinfo is not None def test_content_find_with_present_content(self, swh_storage, sample_data): content = sample_data.content expected_content = attr.evolve(content, data=None) # 1. with something to find swh_storage.content_add([content]) actually_present = swh_storage.content_find({"sha1": content.sha1}) assert 1 == len(actually_present) 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) 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) assert actually_present[0] == expected_content # 4. with something to find actually_present = swh_storage.content_find(content.hashes()) assert 1 == len(actually_present) assert actually_present[0] == expected_content def test_content_find_with_non_present_content(self, swh_storage, sample_data): missing_content = sample_data.skipped_content # 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): content = sample_data.content # 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 = swh_storage.content_find( { "blake2s256": duplicated_content.blake2s256, "sha256": duplicated_content.sha256, } ) expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] def test_content_find_with_duplicate_sha256(self, swh_storage, sample_data): content = sample_data.content 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 = swh_storage.content_find({"sha256": duplicated_content.sha256}) assert len(actual_result) == 2 expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] # Find with both sha256 and blake2s256 actual_result = swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) assert len(actual_result) == 1 assert actual_result == [expected_duplicated_content] def test_content_find_with_duplicate_blake2s256(self, swh_storage, sample_data): content = sample_data.content # 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 = swh_storage.content_find( {"blake2s256": duplicated_content.blake2s256} ) expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] # Find with both sha256 and blake2s256 actual_result = swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) assert actual_result == [expected_duplicated_content] def test_content_find_bad_input(self, swh_storage): # 1. with no hash to lookup with pytest.raises(StorageArgumentException): swh_storage.content_find({}) # need at least one hash # 2. with bad hash 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): content = sample_data.content directory = sample_data.directory revision = sample_data.revision release = sample_data.release 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): fetcher = sample_data.metadata_fetcher 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 actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_fetcher", fetcher), ] for obj in expected_objects: assert obj in actual_objects def test_metadata_fetcher_add_zero(self, swh_storage, sample_data): fetcher = sample_data.metadata_fetcher actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert actual_fetcher is None # does not exist swh_storage.metadata_fetcher_add([]) def test_metadata_authority_add_get(self, swh_storage, sample_data): authority = sample_data.metadata_authority 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 actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ] for obj in expected_objects: assert obj in actual_objects def test_metadata_authority_add_zero(self, swh_storage, sample_data): authority = sample_data.metadata_authority actual_authority = swh_storage.metadata_authority_get( authority.type, authority.url ) assert actual_authority is None # does not exist swh_storage.metadata_authority_add([]) def test_content_metadata_add(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add(content_metadata) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == list( content_metadata ) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ("metadata_fetcher", fetcher), ] + [("raw_extrinsic_metadata", item) for item in content_metadata] for obj in expected_objects: assert obj in actual_objects def test_content_metadata_add_duplicate(self, swh_storage, sample_data): """Duplicates should be silently ignored.""" content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_add([content_metadata2, content_metadata]) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None expected_results = (content_metadata, content_metadata2) assert ( tuple(sorted(result.results, key=lambda x: x.discovery_date,)) == expected_results ) def test_content_metadata_get(self, swh_storage, sample_data): content, content2 = sample_data.contents[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( content1_metadata1, content1_metadata2, content1_metadata3, ) = sample_data.content_metadata[:3] content2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "target": str(content2.swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), 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.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority2 ) assert result.next_page_token is None assert [content1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( content2.swhid().to_extended(), 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): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), 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.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, after=content_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [content_metadata2] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), 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): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_get(content.swhid().to_extended(), authority) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), 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): content = sample_data.content fetcher1, fetcher2 = sample_data.fetchers[:2] authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_content_metadata2 = RawExtrinsicMetadata.from_dict( { **remove_keys(content_metadata2.to_dict(), ("id",)), # recompute id "discovery_date": content_metadata2.discovery_date, "fetcher": attr.evolve(fetcher2, metadata=None).to_dict(), } ) swh_storage.raw_extrinsic_metadata_add( [content_metadata, new_content_metadata2] ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results[0].to_dict() == new_content_metadata2.to_dict() assert result.results == [new_content_metadata2] def test_content_metadata_get_by_ids(self, swh_storage, sample_data): content, content2 = sample_data.contents[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( content1_metadata1, content1_metadata2, content1_metadata3, ) = sample_data.content_metadata[:3] content2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "target": str(content2.swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) assert set( swh_storage.raw_extrinsic_metadata_get_by_ids( [content1_metadata1.id, b"\x00" * 20, content2_metadata.id] ) ) == {content1_metadata1, content2_metadata} def test_content_metadata_get_authorities(self, swh_storage, sample_data): content1, content2, content3 = sample_data.contents[:3] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( content1_metadata1, content1_metadata2, content1_metadata3, ) = sample_data.content_metadata[:3] content2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "target": str(content2.swhid()), } ) content1_metadata2 = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "authority": authority2.to_dict(), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) assert swh_storage.raw_extrinsic_metadata_get_authorities(content1.swhid()) in ( [authority, authority2], [authority2, authority], ) assert swh_storage.raw_extrinsic_metadata_get_authorities(content2.swhid()) == [ authority ] assert ( swh_storage.raw_extrinsic_metadata_get_authorities(content3.swhid()) == [] ) def test_origin_metadata_add(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.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.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date)) == [ origin_metadata, origin_metadata2, ] actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ("metadata_fetcher", fetcher), ("raw_extrinsic_metadata", origin_metadata), ("raw_extrinsic_metadata", origin_metadata2), ] for obj in expected_objects: assert obj in actual_objects def test_origin_metadata_add_duplicate(self, swh_storage, sample_data): """Duplicates should be silently updated.""" origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.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.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) swh_storage.raw_extrinsic_metadata_add([origin_metadata2, origin_metadata]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None # which of the two behavior happens is backend-specific. expected_results = (origin_metadata, origin_metadata2) assert ( tuple(sorted(result.results, key=lambda x: x.discovery_date,)) == expected_results ) def test_origin_metadata_get(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( origin1_metadata1, origin1_metadata2, origin1_metadata3, ) = sample_data.origin_metadata[:3] assert swh_storage.origin_add([origin, origin2]) == {"origin:add": 2} origin2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(origin1_metadata2.to_dict(), ("id",)), # recompute id "target": str(Origin(origin2.url).swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [origin1_metadata1, origin1_metadata2, origin1_metadata3, origin2_metadata] ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), 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.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority2 ) assert result.next_page_token is None assert [origin1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin2.url).swhid(), 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): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.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.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), 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.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, after=origin_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [origin_metadata2] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), 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): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.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.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) swh_storage.raw_extrinsic_metadata_get(Origin(origin.url).swhid(), authority) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), 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): origin = sample_data.origin fetcher1, fetcher2 = sample_data.fetchers[:2] authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.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 = RawExtrinsicMetadata.from_dict( { **remove_keys(origin_metadata2.to_dict(), ("id",)), # recompute id "discovery_date": origin_metadata2.discovery_date, "fetcher": attr.evolve(fetcher2, metadata=None).to_dict(), } ) swh_storage.raw_extrinsic_metadata_add([origin_metadata, new_origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), 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): origin = sample_data.origin fetcher = sample_data.metadata_fetcher origin_metadata, origin_metadata2 = sample_data.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.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) def test_origin_metadata_add_missing_fetcher(self, swh_storage, sample_data): origin = sample_data.origin authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.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.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) class TestStorageGeneratedData: def test_generate_content_get_data(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c.status != "absent"] # retrieve contents for content in contents_with_data: actual_content_data = swh_storage.content_get_data(content.sha1) assert actual_content_data is not None assert actual_content_data == content.data def test_generate_content_get(self, swh_storage, swh_contents): expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] actual_contents = swh_storage.content_get([c.sha1 for c in expected_contents]) assert len(actual_contents) == len(expected_contents) assert actual_contents == expected_contents @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: actual_page = swh_storage.origin_list(page_token=page_token, limit=limit) assert len(actual_page.results) <= limit returned_origins.extend(actual_page.results) i += 1 page_token = actual_page.next_page_token if page_token is None: assert i * limit >= len(swh_origins) break else: assert len(actual_page.results) == limit assert sorted(returned_origins) == sorted(swh_origins) def test_origin_count(self, swh_storage, sample_data): swh_storage.origin_add(sample_data.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, sample_data): swh_storage.origin_add(sample_data.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, sample_data ): swh_storage.origin_add(sample_data.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 ): snapshot = sample_data.snapshot swh_storage.origin_add(sample_data.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, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists(hypothesis_strategies.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]) elif obj.object_type == "raw_extrinsic_metadata": swh_storage.metadata_authority_add([obj.authority]) swh_storage.metadata_fetcher_add([obj.fetcher]) swh_storage.raw_extrinsic_metadata_add([obj]) else: method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass diff --git a/swh/storage/tests/test_backfill.py b/swh/storage/tests/test_backfill.py index 787cad12..a9037838 100644 --- a/swh/storage/tests/test_backfill.py +++ b/swh/storage/tests/test_backfill.py @@ -1,301 +1,303 @@ # Copyright (C) 2019-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import functools import logging from unittest.mock import patch import pytest from swh.journal.client import JournalClient from swh.model.tests.swh_model_data import TEST_OBJECTS from swh.storage import get_storage from swh.storage.backfill import ( PARTITION_KEY, JournalBackfiller, byte_ranges, compute_query, raw_extrinsic_metadata_target_ranges, ) from swh.storage.in_memory import InMemoryStorage from swh.storage.replay import ModelObjectDeserializer, process_replay_objects from swh.storage.tests.test_replay import check_replayed TEST_CONFIG = { "journal_writer": { "brokers": ["localhost"], "prefix": "swh.tmp_journal.new", "client_id": "swh.journal.client.test", }, "storage": {"cls": "postgresql", "db": "service=swh-dev"}, } def test_config_ko_missing_mandatory_key(): """Missing configuration key will make the initialization fail """ for key in TEST_CONFIG.keys(): config = TEST_CONFIG.copy() config.pop(key) with pytest.raises(ValueError) as e: JournalBackfiller(config) error = "Configuration error: The following keys must be provided: %s" % ( ",".join([key]), ) assert e.value.args[0] == error def test_config_ko_unknown_object_type(): """Parse arguments will fail if the object type is unknown """ backfiller = JournalBackfiller(TEST_CONFIG) with pytest.raises(ValueError) as e: backfiller.parse_arguments("unknown-object-type", 1, 2) error = ( "Object type unknown-object-type is not supported. " "The only possible values are %s" % (", ".join(sorted(PARTITION_KEY))) ) assert e.value.args[0] == error def test_compute_query_content(): query, where_args, column_aliases = compute_query("content", "\x000000", "\x000001") assert where_args == ["\x000000", "\x000001"] assert column_aliases == [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "status", "ctime", ] assert ( query == """ select sha1,sha1_git,sha256,blake2s256,length,status,ctime from content where (sha1) >= %s and (sha1) < %s """ ) def test_compute_query_skipped_content(): query, where_args, column_aliases = compute_query("skipped_content", None, None) assert where_args == [] assert column_aliases == [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "ctime", "status", "reason", ] assert ( query == """ select sha1,sha1_git,sha256,blake2s256,length,ctime,status,reason from skipped_content """ ) def test_compute_query_origin_visit(): query, where_args, column_aliases = compute_query("origin_visit", 1, 10) assert where_args == [1, 10] assert column_aliases == [ "visit", "type", "origin", "date", ] assert ( query == """ select visit,type,origin.url as origin,date from origin_visit left join origin on origin_visit.origin=origin.id where (origin_visit.origin) >= %s and (origin_visit.origin) < %s """ ) def test_compute_query_release(): query, where_args, column_aliases = compute_query("release", "\x000002", "\x000003") assert where_args == ["\x000002", "\x000003"] assert column_aliases == [ "id", "date", "date_offset", "date_neg_utc_offset", + "date_offset_bytes", "comment", "name", "synthetic", "target", "target_type", "author_id", "author_name", "author_email", "author_fullname", + "raw_manifest", ] assert ( query == """ -select release.id as id,date,date_offset,date_neg_utc_offset,comment,release.name as name,synthetic,target,target_type,a.id as author_id,a.name as author_name,a.email as author_email,a.fullname as author_fullname +select release.id as id,date,date_offset,date_neg_utc_offset,date_offset_bytes,comment,release.name as name,synthetic,target,target_type,a.id as author_id,a.name as author_name,a.email as author_email,a.fullname as author_fullname,raw_manifest from release left join person a on release.author=a.id where (release.id) >= %s and (release.id) < %s """ # noqa ) @pytest.mark.parametrize("numbits", [2, 3, 8, 16]) def test_byte_ranges(numbits): ranges = list(byte_ranges(numbits)) assert len(ranges) == 2 ** numbits assert ranges[0][0] is None assert ranges[-1][1] is None bounds = [] for i, (left, right) in enumerate(zip(ranges[:-1], ranges[1:])): assert left[1] == right[0], f"Mismatched bounds in {i}th range" bounds.append(left[1]) assert bounds == sorted(bounds) def test_raw_extrinsic_metadata_target_ranges(): ranges = list(raw_extrinsic_metadata_target_ranges()) assert ranges[0][0] == "" assert ranges[-1][1] is None bounds = [] for i, (left, right) in enumerate(zip(ranges[:-1], ranges[1:])): assert left[1] == right[0], f"Mismatched bounds in {i}th range" bounds.append(left[1]) assert bounds == sorted(bounds) RANGE_GENERATORS = { "content": lambda start, end: [(None, None)], "skipped_content": lambda start, end: [(None, None)], "directory": lambda start, end: [(None, None)], "extid": lambda start, end: [(None, None)], "metadata_authority": lambda start, end: [(None, None)], "metadata_fetcher": lambda start, end: [(None, None)], "revision": lambda start, end: [(None, None)], "release": lambda start, end: [(None, None)], "snapshot": lambda start, end: [(None, None)], "origin": lambda start, end: [(None, 10000)], "origin_visit": lambda start, end: [(None, 10000)], "origin_visit_status": lambda start, end: [(None, 10000)], "raw_extrinsic_metadata": lambda start, end: [(None, None)], } @patch("swh.storage.backfill.RANGE_GENERATORS", RANGE_GENERATORS) def test_backfiller( swh_storage_backend_config, kafka_prefix: str, kafka_consumer_group: str, kafka_server: str, caplog, ): prefix1 = f"{kafka_prefix}-1" prefix2 = f"{kafka_prefix}-2" journal1 = { "cls": "kafka", "brokers": [kafka_server], "client_id": "kafka_writer-1", "prefix": prefix1, } swh_storage_backend_config["journal_writer"] = journal1 storage = get_storage(**swh_storage_backend_config) # fill the storage and the journal (under prefix1) for object_type, objects in TEST_OBJECTS.items(): method = getattr(storage, object_type + "_add") method(objects) # now apply the backfiller on the storage to fill the journal under prefix2 backfiller_config = { "journal_writer": { "brokers": [kafka_server], "client_id": "kafka_writer-2", "prefix": prefix2, }, "storage": swh_storage_backend_config, } # Backfilling backfiller = JournalBackfiller(backfiller_config) for object_type in TEST_OBJECTS: backfiller.run(object_type, None, None) # Trace log messages for unhandled object types in the replayer caplog.set_level(logging.DEBUG, "swh.storage.replay") # now check journal content are the same under both topics # use the replayer scaffolding to fill storages to make is a bit easier # Replaying #1 deserializer = ModelObjectDeserializer() sto1 = get_storage(cls="memory") replayer1 = JournalClient( brokers=kafka_server, group_id=f"{kafka_consumer_group}-1", prefix=prefix1, stop_on_eof=True, value_deserializer=deserializer.convert, ) worker_fn1 = functools.partial(process_replay_objects, storage=sto1) replayer1.process(worker_fn1) # Replaying #2 sto2 = get_storage(cls="memory") replayer2 = JournalClient( brokers=kafka_server, group_id=f"{kafka_consumer_group}-2", prefix=prefix2, stop_on_eof=True, value_deserializer=deserializer.convert, ) worker_fn2 = functools.partial(process_replay_objects, storage=sto2) replayer2.process(worker_fn2) # Compare storages assert isinstance(sto1, InMemoryStorage) # needed to help mypy assert isinstance(sto2, InMemoryStorage) check_replayed(sto1, sto2) for record in caplog.records: assert ( "this should not happen" not in record.message ), "Replayer ignored some message types, see captured logging" diff --git a/swh/storage/tests/test_postgresql_converters.py b/swh/storage/tests/test_postgresql_converters.py index 124a2ae3..5f6d4937 100644 --- a/swh/storage/tests/test_postgresql_converters.py +++ b/swh/storage/tests/test_postgresql_converters.py @@ -1,287 +1,335 @@ # Copyright (C) 2015-2021 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 pytest from swh.model.model import ( ObjectType, Person, Release, Revision, RevisionType, Timestamp, TimestampWithTimezone, ) from swh.model.swhids import ExtendedSWHID from swh.storage.postgresql import converters @pytest.mark.parametrize( "model_date,db_date", [ - (None, {"timestamp": None, "offset": 0, "neg_utc_offset": None}), + ( + None, + { + "timestamp": None, + "offset": 0, + "neg_utc_offset": None, + "offset_bytes": None, + }, + ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=1234567890, microseconds=0,), offset=120, negative_utc=False, + offset_bytes=b"+0200", ), { "timestamp": "2009-02-13T23:31:30+00:00", "offset": 120, "neg_utc_offset": False, + "offset_bytes": b"+0200", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=1123456789, microseconds=0,), offset=0, negative_utc=True, + offset_bytes=b"-0000", ), { "timestamp": "2005-08-07T23:19:49+00:00", "offset": 0, "neg_utc_offset": True, + "offset_bytes": b"-0000", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=1234567890, microseconds=0,), offset=42, negative_utc=False, + offset_bytes=b"+0042", ), { "timestamp": "2009-02-13T23:31:30+00:00", "offset": 42, "neg_utc_offset": False, + "offset_bytes": b"+0042", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=1634366813, microseconds=0,), offset=-120, negative_utc=False, + offset_bytes=b"-0200", ), { "timestamp": "2021-10-16T06:46:53+00:00", "offset": -120, "neg_utc_offset": False, + "offset_bytes": b"-0200", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=0, microseconds=0,), offset=-120, negative_utc=False, + offset_bytes=b"-0200", ), { "timestamp": "1970-01-01T00:00:00+00:00", "offset": -120, "neg_utc_offset": False, + "offset_bytes": b"-0200", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=0, microseconds=1,), offset=-120, negative_utc=False, + offset_bytes=b"-0200", ), { "timestamp": "1970-01-01T00:00:00.000001+00:00", "offset": -120, "neg_utc_offset": False, + "offset_bytes": b"-0200", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=-1, microseconds=0,), offset=-120, negative_utc=False, + offset_bytes=b"-0200", ), { "timestamp": "1969-12-31T23:59:59+00:00", "offset": -120, "neg_utc_offset": False, + "offset_bytes": b"-0200", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=-1, microseconds=1,), offset=-120, negative_utc=False, + offset_bytes=b"-0200", ), { "timestamp": "1969-12-31T23:59:59.000001+00:00", "offset": -120, "neg_utc_offset": False, + "offset_bytes": b"-0200", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=-3600, microseconds=0,), offset=-120, negative_utc=False, + offset_bytes=b"-0200", ), { "timestamp": "1969-12-31T23:00:00+00:00", "offset": -120, "neg_utc_offset": False, + "offset_bytes": b"-0200", }, ), ( TimestampWithTimezone( timestamp=Timestamp(seconds=-3600, microseconds=1,), offset=-120, negative_utc=False, + offset_bytes=b"-0200", ), { "timestamp": "1969-12-31T23:00:00.000001+00:00", "offset": -120, "neg_utc_offset": False, + "offset_bytes": b"-0200", + }, + ), + ( + TimestampWithTimezone( + timestamp=Timestamp(seconds=1234567890, microseconds=0,), + offset=120, + negative_utc=False, + offset_bytes=b"+200", + ), + { + "timestamp": "2009-02-13T23:31:30+00:00", + "offset": 120, + "neg_utc_offset": False, + "offset_bytes": b"+200", }, ), ], ) def test_date(model_date, db_date): assert converters.date_to_db(model_date) == db_date assert ( converters.db_to_date( date=None if db_date["timestamp"] is None else datetime.datetime.fromisoformat(db_date["timestamp"]), offset=db_date["offset"], neg_utc_offset=db_date["neg_utc_offset"], + offset_bytes=db_date["offset_bytes"], ) == model_date ) def test_db_to_author(): # when actual_author = converters.db_to_author(b"fullname", b"name", b"email") # then assert actual_author == Person(fullname=b"fullname", name=b"name", email=b"email",) def test_db_to_author_none(): # when actual_author = converters.db_to_author(None, None, None) # then assert actual_author is None def test_db_to_revision(): # when actual_revision = converters.db_to_revision( { "id": b"revision-id", "date": None, "date_offset": None, "date_neg_utc_offset": None, + "date_offset_bytes": None, "committer_date": None, "committer_date_offset": None, "committer_date_neg_utc_offset": None, + "committer_date_offset_bytes": None, "type": "git", "directory": b"dir-sha1", "message": b"commit message", "author_fullname": b"auth-fullname", "author_name": b"auth-name", "author_email": b"auth-email", "committer_fullname": b"comm-fullname", "committer_name": b"comm-name", "committer_email": b"comm-email", "metadata": {}, "synthetic": False, "extra_headers": (), + "raw_manifest": None, "parents": [b"123", b"456"], } ) # then assert actual_revision == Revision( id=b"revision-id", author=Person( fullname=b"auth-fullname", name=b"auth-name", email=b"auth-email", ), date=None, committer=Person( fullname=b"comm-fullname", name=b"comm-name", email=b"comm-email", ), committer_date=None, type=RevisionType.GIT, directory=b"dir-sha1", message=b"commit message", metadata={}, synthetic=False, extra_headers=(), parents=(b"123", b"456"), ) def test_db_to_release(): # when actual_release = converters.db_to_release( { "id": b"release-id", "target": b"revision-id", "target_type": "revision", "date": None, "date_offset": None, "date_neg_utc_offset": None, + "date_offset_bytes": None, "name": b"release-name", "comment": b"release comment", "synthetic": True, "author_fullname": b"auth-fullname", "author_name": b"auth-name", "author_email": b"auth-email", + "raw_manifest": None, } ) # then assert actual_release == Release( author=Person( fullname=b"auth-fullname", name=b"auth-name", email=b"auth-email", ), date=None, id=b"release-id", name=b"release-name", message=b"release comment", synthetic=True, target=b"revision-id", target_type=ObjectType.REVISION, ) def test_db_to_raw_extrinsic_metadata_raw_target(): row = { "raw_extrinsic_metadata.target": "https://example.com/origin", "metadata_authority.type": "forge", "metadata_authority.url": "https://example.com", "metadata_fetcher.name": "swh.lister", "metadata_fetcher.version": "1.0.0", "discovery_date": datetime.datetime( 2021, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc ), "format": "text/plain", "raw_extrinsic_metadata.metadata": b"metadata", "origin": None, "visit": None, "snapshot": None, "release": None, "revision": None, "path": None, "directory": None, } with pytest.deprecated_call(): computed_rem = converters.db_to_raw_extrinsic_metadata(row) assert computed_rem.target == ExtendedSWHID.from_string( "swh:1:ori:5a7439b0b93a5d230b6a67b8e7e0f7dc3c9f6c70" )