diff --git a/PKG-INFO b/PKG-INFO index 1dddabda..124b1668 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,213 +1,213 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.17.1 +Version: 0.17.2 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-storage Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-storage/ Description: swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects the path to `cassandra` to either be unspecified, it is then looked up at `/usr/sbin/cassandra`, either specified through the environment variable `SWH_CASSANDRA_BIN`. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` ## Development The storage server can be locally started. It requires a configuration file and a running Postgresql database. ### Sample configuration A typical configuration `storage.yml` file is: ``` storage: cls: local db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing root: /tmp/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to `softwareheritage-dev` local instance, - the objstorage uses a local objstorage instance whose: - `root` path is /tmp/swh-storage, - slicing scheme is `0:2/2:4/4:6`. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the `root` path should exist on disk before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

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

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local db: service=swh-dev objstorage: cls: pathslicing root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing Provides-Extra: schemata Provides-Extra: journal diff --git a/requirements-swh-journal.txt b/requirements-swh-journal.txt index 816f455a..ff0aef49 100644 --- a/requirements-swh-journal.txt +++ b/requirements-swh-journal.txt @@ -1 +1 @@ -swh.journal >= 0.4 +swh.journal >= 0.5.1 diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index 1dddabda..124b1668 100644 --- a/swh.storage.egg-info/PKG-INFO +++ b/swh.storage.egg-info/PKG-INFO @@ -1,213 +1,213 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.17.1 +Version: 0.17.2 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-storage Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-storage/ Description: swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects the path to `cassandra` to either be unspecified, it is then looked up at `/usr/sbin/cassandra`, either specified through the environment variable `SWH_CASSANDRA_BIN`. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` ## Development The storage server can be locally started. It requires a configuration file and a running Postgresql database. ### Sample configuration A typical configuration `storage.yml` file is: ``` storage: cls: local db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing root: /tmp/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to `softwareheritage-dev` local instance, - the objstorage uses a local objstorage instance whose: - `root` path is /tmp/swh-storage, - slicing scheme is `0:2/2:4/4:6`. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the `root` path should exist on disk before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

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

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local db: service=swh-dev objstorage: cls: pathslicing root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing Provides-Extra: schemata Provides-Extra: journal diff --git a/swh.storage.egg-info/requires.txt b/swh.storage.egg-info/requires.txt index 9413cb3f..0242c0d4 100644 --- a/swh.storage.egg-info/requires.txt +++ b/swh.storage.egg-info/requires.txt @@ -1,30 +1,30 @@ click flask psycopg2 aiohttp tenacity cassandra-driver!=3.21.0,>=3.19.0 deprecated typing-extensions mypy_extensions iso8601 swh.core[db,http]>=0.5 swh.model>=0.7.2 swh.objstorage>=0.2.2 [journal] -swh.journal>=0.4 +swh.journal>=0.5.1 [schemata] SQLAlchemy [testing] hypothesis>=3.11.0 pytest pytest-mock pytest-postgresql>=2.1.0 sqlalchemy-stubs swh.model[testing]>=0.0.50 pytz pytest-xdist -swh.journal>=0.4 +swh.journal>=0.5.1 diff --git a/swh/storage/backfill.py b/swh/storage/backfill.py index 4e910b20..ae7dd878 100644 --- a/swh/storage/backfill.py +++ b/swh/storage/backfill.py @@ -1,549 +1,554 @@ # Copyright (C) 2017-2020 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 """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 from swh.core.db import BaseDb -from swh.journal.writer import get_journal_writer from swh.model.model import ( BaseModel, Directory, DirectoryEntry, RawExtrinsicMetadata, Release, Revision, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.postgresql.converters import ( db_to_raw_extrinsic_metadata, db_to_release, db_to_revision, ) from swh.storage.replay import object_converter_fn +from swh.storage.writer import JournalWriter logger = logging.getLogger(__name__) PARTITION_KEY = { "content": "sha1", "skipped_content": "sha1", "directory": "id", "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"], "metadata_authority": ["type", "url", "metadata",], "metadata_fetcher": ["name", "version", "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", "committer_date", "committer_date_offset", "committer_date_neg_utc_offset", "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", ), ("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", "comment", ("release.name", "name"), "synthetic", "target", "target_type", ("a.id", "author_id"), ("a.name", "author_name"), ("a.email", "author_email"), ("a.fullname", "author_fullname"), ], "snapshot": ["id", "object_id"], "origin": ["url"], "origin_visit": ["visit", "type", ("origin.url", "origin"), "date",], "origin_visit_status": [ "visit", ("origin.url", "origin"), "date", "snapshot", "status", "metadata", ], } 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", ], } 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 revision from the flat representation to swh model compatible objects. """ return db_to_raw_extrinsic_metadata(metadata) 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"] or branch_d["target_type"]: branch = None else: branch = SnapshotBranch( target=branch_d["target"], target_type=TargetType(branch_d["target_type"]), ) branches[name] = branch return Snapshot(id=snapshot_d["id"], branches=branches,) CONVERTERS: Dict[str, Callable[[BaseDb, Dict[str, Any]], BaseModel]] = { "directory": directory_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 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), "revision": lambda start, end: byte_ranges(24, start, end), "release": lambda start, end: byte_ranges(16, start, end), "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) 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) 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_converter_fn[obj_type](record) - logger.debug("record: %s" % 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"] != "local": 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(COLUMNS.keys())) ) if object_type in ["origin", "origin_visit"]: 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 = get_journal_writer(cls="kafka", **self.config["journal_writer"]) + 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), ) - for obj in fetch(db, object_type, start=range_start, end=range_end,): - if dry_run: - continue - writer.write_addition(object_type=object_type, object_=obj) + objects = fetch(db, object_type, start=range_start, end=range_end) - writer.producer.flush() + 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/storage.py b/swh/storage/cassandra/storage.py index 65b062b3..c95ba912 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,1324 +1,1324 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import base64 import datetime import itertools import json import random import re from typing import ( Any, Callable, Dict, Iterable, List, Optional, Sequence, Set, Tuple, Union, ) import attr from swh.core.api.serializers import msgpack_dumps, msgpack_loads from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.model.identifiers import SWHID, parse_swhid from swh.model.model import ( Content, Directory, DirectoryEntry, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1Git, SkippedContent, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.interface import ( VISIT_STATUSES, ListOrder, PagedResult, PartialBranches, Sha1, ) 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 .common import TOKEN_BEGIN, TOKEN_END, hash_url, remove_keys from .cql import CqlRunner from .model import ( ContentRow, DirectoryEntryRow, DirectoryRow, MetadataAuthorityRow, MetadataFetcherRow, OriginRow, OriginVisitRow, OriginVisitStatusRow, RawExtrinsicMetadataRow, RevisionParentRow, SkippedContentRow, SnapshotBranchRow, SnapshotRow, ) from .schema import HASH_ALGORITHMS # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 class CassandraStorage: def __init__(self, hosts, keyspace, objstorage, port=9042, journal_writer=None): self._cql_runner: CqlRunner = CqlRunner(hosts, keyspace, port) self.journal_writer: JournalWriter = JournalWriter(journal_writer) self.objstorage: ObjStorage = ObjStorage(objstorage) def check_config(self, *, check_write: bool) -> bool: self._cql_runner.check_read() return True def _content_get_from_hash(self, algo, hash_) -> Iterable: """From the name of a hash algorithm and a value of that hash, looks up the "hash -> token" secondary table (content_by_{algo}) to get tokens. Then, looks up the main table (content) to get all contents with that token, and filters out contents whose hash doesn't match.""" found_tokens = self._cql_runner.content_get_tokens_from_single_hash(algo, hash_) for token in found_tokens: assert isinstance(token, int), found_tokens # Query the main table ('content'). res = self._cql_runner.content_get_from_token(token) for row in res: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) == hash_: yield row def _content_add(self, contents: List[Content], with_data: bool) -> Dict: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.content_get_from_pk(c.to_dict()) ] self.journal_writer.content_add(contents) if with_data: # First insert to the objstorage, if the endpoint is # `content_add` (as opposed to `content_add_metadata`). # TODO: this should probably be done in concurrently to inserting # in index tables (but still before the main table; so an entry is # only added to the main table after everything else was # successfully inserted. summary = self.objstorage.content_add( c for c in contents if c.status != "absent" ) content_add_bytes = summary["content:add:bytes"] content_add = 0 for content in contents: content_add += 1 # Check for sha1 or sha1_git collisions. This test is not atomic # with the insertion, so it won't detect a collision if both # contents are inserted at the same time, but it's good enough. # # The proper way to do it would probably be a BATCH, but this # would be inefficient because of the number of partitions we # need to affect (len(HASH_ALGORITHMS)+1, which is currently 5) for algo in {"sha1", "sha1_git"}: collisions = [] # Get tokens of 'content' rows with the same value for # sha1/sha1_git rows = self._content_get_from_hash(algo, content.get_hash(algo)) for row in rows: if getattr(row, algo) != content.get_hash(algo): # collision of token(partition key), ignore this # row continue for 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 def content_add(self, content: List[Content]) -> Dict: contents = [attr.evolve(c, ctime=now()) for c in content] return self._content_add(list(contents), with_data=True) def content_update( self, contents: List[Dict[str, Any]], keys: List[str] = [] ) -> None: raise NotImplementedError( "content_update is not supported by the Cassandra backend" ) def content_add_metadata(self, content: List[Content]) -> Dict: return self._content_add(content, with_data=False) def content_get_data(self, content: Sha1) -> Optional[bytes]: # FIXME: Make this method support slicing the `data` return self.objstorage.content_get(content) 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) def content_get(self, contents: List[Sha1]) -> List[Optional[Content]]: contents_by_sha1: Dict[Sha1, Optional[Content]] = {} for sha1 in contents: # Get all (sha1, sha1_git, sha256, blake2s256) whose sha1 # matches the argument, from the index table ('content_by_sha1') for row in self._content_get_from_hash("sha1", sha1): row_d = row.to_dict() row_d.pop("ctime") content = Content(**row_d) contents_by_sha1[content.sha1] = content return [contents_by_sha1.get(sha1) for sha1 in contents] def content_find(self, content: 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 = list(set(content).intersection(HASH_ALGORITHMS)) if not filter_algos: raise StorageArgumentException( "content keys must contain at least one " f"of: {', '.join(sorted(HASH_ALGORITHMS))}" ) common_algo = filter_algos[0] results = [] rows = self._content_get_from_hash(common_algo, content[common_algo]) for row in rows: # Re-check all the hashes, in case of collisions (either of the # hash of the partition key, or the hashes in it) for algo in HASH_ALGORITHMS: if content.get(algo) and getattr(row, algo) != content[algo]: # This hash didn't match; discard the row. break else: # All hashes match, keep this row. row_d = row.to_dict() row_d["ctime"] = row.ctime.replace(tzinfo=datetime.timezone.utc) results.append(Content(**row_d)) return results 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)}" ) for content in contents: res = self.content_find(content) if not res: yield content[key_hash] def content_missing_per_sha1(self, contents: List[bytes]) -> Iterable[bytes]: return self.content_missing([{"sha1": c} for c in contents]) 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" + [{"sha1_git": c} for c in contents], key_hash="sha1_git" ) 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: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.skipped_content_get_from_pk(c.to_dict()) ] self.journal_writer.skipped_content_add(contents) for content in contents: # Compute token of the row in the main table (token, insertion_finalizer) = self._cql_runner.skipped_content_add_prepare( 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)} def skipped_content_add(self, content: List[SkippedContent]) -> Dict: contents = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(contents) 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} def directory_add(self, directories: List[Directory]) -> Dict: # Filter out directories that are already inserted. missing = self.directory_missing([dir_.id for dir_ in directories]) directories = [dir_ for dir_ in directories if dir_.id in missing] self.journal_writer.directory_add(directories) for directory in directories: # Add directory entries to the 'directory_entry' table for entry in directory.entries: self._cql_runner.directory_entry_add_one( DirectoryEntryRow(directory_id=directory.id, **entry.to_dict()) ) # 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)) return {"directory:add": len(directories)} def directory_missing(self, directories: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.directory_missing(directories) def _join_dentry_to_content(self, dentry: DirectoryEntry) -> Dict[str, Any]: contents: Union[List[Content], List[SkippedContentRow]] keys = ( "status", "sha1", "sha1_git", "sha256", "length", ) ret = dict.fromkeys(keys) ret.update(dentry.to_dict()) if ret["type"] == "file": contents = self.content_find({"sha1_git": ret["target"]}) if not contents: tokens = list( self._cql_runner.skipped_content_get_tokens_from_single_hash( "sha1_git", ret["target"] ) ) if tokens: contents = list( self._cql_runner.skipped_content_get_from_token(tokens[0]) ) if contents: content = contents[0] 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])) 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) ret["name"] = prefix + ret["name"] ret["dir_id"] = directory_id yield ret if recursive and ret["type"] == "dir": yield from self._directory_ls( ret["target"], True, prefix + ret["name"] + b"/" ) def directory_entry_get_by_path( self, directory: 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"/" ) def directory_ls( self, directory: Sha1Git, recursive: bool = False ) -> Iterable[Dict[str, Any]]: yield from self._directory_ls(directory, recursive) def directory_get_random(self) -> Sha1Git: directory = self._cql_runner.directory_get_random() assert directory, "Could not find any directory" return directory.id def revision_add(self, revisions: List[Revision]) -> Dict: # Filter-out revisions already in the database missing = self.revision_missing([rev.id for rev in revisions]) revisions = [rev for rev in revisions if rev.id in missing] self.journal_writer.revision_add(revisions) for revision in revisions: revobject = 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)} def revision_missing(self, revisions: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.revision_missing(revisions) 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) 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) 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) def revision_get_random(self) -> Sha1Git: revision = self._cql_runner.revision_get_random() assert revision, "Could not find any revision" return revision.id def release_add(self, releases: List[Release]) -> Dict: to_add = [] for rel in releases: if rel not in to_add: to_add.append(rel) missing = set(self.release_missing([rel.id for rel in to_add])) to_add = [rel for rel in to_add if rel.id in missing] self.journal_writer.release_add(to_add) for release in to_add: if release: self._cql_runner.release_add_one(converters.release_to_db(release)) return {"release:add": len(to_add)} def release_missing(self, releases: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.release_missing(releases) 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] def release_get_random(self) -> Sha1Git: release = self._cql_runner.release_get_random() assert release, "Could not find any release" return release.id def snapshot_add(self, snapshots: List[Snapshot]) -> Dict: missing = self._cql_runner.snapshot_missing([snp.id for snp in snapshots]) snapshots = [snp for snp in snapshots if snp.id in missing] for snapshot in snapshots: self.journal_writer.snapshot_add([snapshot]) # Add branches for (branch_name, branch) in snapshot.branches.items(): if branch is None: target_type: 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)} def snapshot_missing(self, snapshots: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.snapshot_missing(snapshots) 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"], } def snapshot_count_branches( self, snapshot_id: Sha1Git ) -> 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) def snapshot_get_branches( self, snapshot_id: Sha1Git, branches_from: bytes = b"", branches_count: int = 1000, target_types: Optional[List[str]] = 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 ) ) if not new_branches: break branches_from = new_branches[-1].name new_branches_filtered = new_branches # Filter by target_type if target_types: new_branches_filtered = [ branch for branch in new_branches_filtered if branch.target is not None and branch.target_type in target_types ] branches.extend(new_branches_filtered) if len(new_branches) < branches_count + 1: break if len(branches) > branches_count: last_branch = branches.pop(-1).name else: last_branch = None 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, ) def snapshot_get_random(self) -> Sha1Git: snapshot = self._cql_runner.snapshot_get_random() assert snapshot, "Could not find any snapshot" return snapshot.id 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._cql_runner.content_missing_by_sha1_git), ("directory", self._cql_runner.directory_missing), ] for (object_type, query_fn) in queries: found_ids = missing_ids - set(query_fn(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 def origin_get(self, origins: List[str]) -> Iterable[Optional[Origin]]: return [self.origin_get_one(origin) for origin in origins] 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 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 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) def origin_search( self, url_pattern: str, page_token: Optional[str] = None, limit: int = 50, regexp: bool = False, with_visit: bool = False, ) -> 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] 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) 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" ) def origin_add(self, origins: List[Origin]) -> Dict[str, int]: to_add = [ori for ori in origins if self.origin_get_one(ori.url) is None] # keep only one occurrence of each given origin while keeping the list # sorted as originally given to_add = sorted(set(to_add), key=to_add.index) self.journal_writer.origin_add(to_add) for origin in to_add: self._cql_runner.origin_add_one( OriginRow(sha1=hash_url(origin.url), url=origin.url, next_visit_id=1) ) return {"origin:add": len(to_add)} 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 not visit.visit: visit_id = self._cql_runner.origin_generate_unique_visit_id( visit.origin ) visit = attr.evolve(visit, visit=visit_id) self.journal_writer.origin_visit_add([visit]) self._cql_runner.origin_visit_add_one(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, status="created", snapshot=None, ) ) return all_visits def _origin_visit_status_add(self, visit_status: OriginVisitStatus) -> None: """Add an origin visit status""" self.journal_writer.origin_visit_status_add([visit_status]) self._cql_runner.origin_visit_status_add_one( converters.visit_status_to_row(visit_status) ) def origin_visit_status_add(self, visit_statuses: List[OriginVisitStatus]) -> None: # 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) 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"], } 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), } 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) 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) 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 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 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 if updated_visit["visit"] < latest_visit["visit"]: continue 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"], ) 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]) def origin_visit_status_get_random( self, type: str ) -> Optional[Tuple[OriginVisit, 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, visit_status return None def stat_counters(self): rows = self._cql_runner.stat_counters() keys = ( "content", "directory", "origin", "origin_visit", "release", "revision", "skipped_content", "snapshot", ) stats = {key: 0 for key in keys} stats.update({row.object_type: row.count for row in rows}) return stats def refresh_stat_counters(self): pass def raw_extrinsic_metadata_add(self, metadata: List[RawExtrinsicMetadata]) -> None: self.journal_writer.raw_extrinsic_metadata_add(metadata) 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( type=metadata_entry.type.value, 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), ) self._cql_runner.raw_extrinsic_metadata_add(row) except TypeError as e: raise StorageArgumentException(*e.args) def raw_extrinsic_metadata_get( self, type: MetadataTargetType, target: Union[str, SWHID], authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, ) -> PagedResult[RawExtrinsicMetadata]: if type == MetadataTargetType.ORIGIN: if isinstance(target, SWHID): raise StorageArgumentException( f"raw_extrinsic_metadata_get called with type='origin', " f"but provided target is a SWHID: {target!r}" ) else: if not isinstance(target, SWHID): raise StorageArgumentException( f"raw_extrinsic_metadata_get called with type!='origin', " f"but provided target is not a SWHID: {target!r}" ) if page_token is not None: (after_date, after_fetcher_name, after_fetcher_url) = 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_fetcher( # noqa str(target), authority.type.value, authority.url, after_date, after_fetcher_name, after_fetcher_url, ) 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: discovery_date = entry.discovery_date.replace(tzinfo=datetime.timezone.utc) assert str(target) == entry.target result = RawExtrinsicMetadata( type=MetadataTargetType(entry.type), target=target, authority=MetadataAuthority( type=MetadataAuthorityType(entry.authority_type), url=entry.authority_url, ), fetcher=MetadataFetcher( name=entry.fetcher_name, version=entry.fetcher_version, ), discovery_date=discovery_date, format=entry.format, metadata=entry.metadata, origin=entry.origin, visit=entry.visit, snapshot=map_optional(parse_swhid, entry.snapshot), release=map_optional(parse_swhid, entry.release), revision=map_optional(parse_swhid, entry.revision), path=entry.path, directory=map_optional(parse_swhid, entry.directory), ) results.append(result) if len(results) > limit: results.pop() assert len(results) == limit last_result = results[-1] next_page_token: Optional[str] = base64.b64encode( msgpack_dumps( ( last_result.discovery_date, last_result.fetcher.name, last_result.fetcher.version, ) ) ).decode() else: next_page_token = None return PagedResult(next_page_token=next_page_token, results=results,) def metadata_fetcher_add(self, fetchers: List[MetadataFetcher]) -> None: self.journal_writer.metadata_fetcher_add(fetchers) for fetcher in fetchers: self._cql_runner.metadata_fetcher_add( MetadataFetcherRow( name=fetcher.name, version=fetcher.version, metadata=json.dumps(map_optional(dict, fetcher.metadata)), ) ) def metadata_fetcher_get( self, name: str, version: str ) -> Optional[MetadataFetcher]: fetcher = self._cql_runner.metadata_fetcher_get(name, version) if fetcher: return MetadataFetcher( name=fetcher.name, version=fetcher.version, metadata=json.loads(fetcher.metadata), ) else: return None def metadata_authority_add(self, authorities: List[MetadataAuthority]) -> None: 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, metadata=json.dumps(map_optional(dict, authority.metadata)), ) ) def metadata_authority_get( self, type: MetadataAuthorityType, url: str ) -> Optional[MetadataAuthority]: authority = self._cql_runner.metadata_authority_get(type.value, url) if authority: return MetadataAuthority( type=MetadataAuthorityType(authority.type), url=authority.url, metadata=json.loads(authority.metadata), ) else: return None def clear_buffers(self, object_types: Sequence[str] = ()) -> None: """Do nothing """ return None def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]: return {} diff --git a/swh/storage/migrate_extrinsic_metadata.py b/swh/storage/migrate_extrinsic_metadata.py index 277b8103..22013355 100644 --- a/swh/storage/migrate_extrinsic_metadata.py +++ b/swh/storage/migrate_extrinsic_metadata.py @@ -1,1184 +1,1199 @@ #!/usr/bin/env python3 # 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 """This is an executable script to migrate extrinsic revision metadata from the revision table to the new extrinsic metadata storage. This is designed to be as conservative as possible, following this principle: for each revision the script reads (in "handle_row"), it will read some of the fields, write them directly to the metadata storage, and remove them. Then it checks all the remaining fields are in a hardcoded list of fields that are known not to require migration. This means that every field that isn't migrated was explicitly reviewed while writing this script. Additionally, this script contains many assertions to prevent false positives in its heuristics. """ import datetime import hashlib import json import os import re import sys import time from typing import Any, Dict, Optional from urllib.error import HTTPError from urllib.parse import unquote, urlparse from urllib.request import urlopen import iso8601 import psycopg2 from swh.core.db import BaseDb from swh.model.hashutil import hash_to_hex from swh.model.identifiers import SWHID, parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, RawExtrinsicMetadata, Sha1Git, ) from swh.storage import get_storage from swh.storage.algos.origin import iter_origin_visit_statuses, iter_origin_visits from swh.storage.algos.snapshot import snapshot_get_all_branches # XML namespaces and fields for metadata coming from the deposit: CODEMETA_NS = "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0" ATOM_NS = "http://www.w3.org/2005/Atom" ATOM_KEYS = ["id", "author", "external_identifier", "title"] # columns of the revision table (of the storage DB) REVISION_COLS = [ "id", "directory", "date", "committer_date", "type", "message", "metadata", ] # columns of the tables of the deposit DB DEPOSIT_COLS = [ "deposit.id", "deposit.external_id", "deposit.swhid_context", "deposit.status", "deposit_request.metadata", "deposit_request.date", "deposit_client.provider_url", "deposit_collection.name", "auth_user.username", ] # Formats we write to the extrinsic metadata storage OLD_DEPOSIT_FORMAT = ( "sword-v2-atom-codemeta-v2-in-json-with-expanded-namespaces" # before february 2018 ) NEW_DEPOSIT_FORMAT = "sword-v2-atom-codemeta-v2-in-json" # after february 2018 GNU_FORMAT = "gnu-tree-json" NIXGUIX_FORMAT = "nixguix-sources-json" NPM_FORMAT = "replicate-npm-package-json" ORIGINAL_ARTIFACT_FORMAT = "original-artifacts-json" PYPI_FORMAT = "pypi-project-json" # Information about this script, for traceability FETCHER = MetadataFetcher( name="migrate-extrinsic-metadata-from-revisions", version="0.0.1", ) # Authorities that we got the metadata from AUTHORITIES = { "npmjs": MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", metadata={} ), "pypi": MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://pypi.org/", metadata={} ), "gnu": MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://ftp.gnu.org/", metadata={} ), "swh": MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ), # for original_artifact (which are checksums computed by SWH) } # Regular expression for the format of revision messages written by the # deposit loader deposit_revision_message_re = re.compile( b"(?P[a-z-]*): " b"Deposit (?P[0-9]+) in collection (?P[a-z-]+).*" ) # not reliable, because PyPI allows arbitrary names def pypi_project_from_filename(filename): original_filename = filename if filename.endswith(".egg"): return None elif filename == "mongomotor-0.13.0.n.tar.gz": return "mongomotor" elif re.match(r"datahaven-rev[0-9]+\.tar\.gz", filename): return "datahaven" elif re.match(r"Dtls-[0-9]\.[0-9]\.[0-9]\.sdist_with_openssl\..*", filename): return "Dtls" elif re.match(r"(gae)?pytz-20[0-9][0-9][a-z]\.(tar\.gz|zip)", filename): return filename.split("-", 1)[0] elif filename.startswith(("powny-", "obedient.powny-",)): return filename.split("-")[0] elif filename.startswith("devpi-theme-16-"): return "devpi-theme-16" elif re.match("[^-]+-[0-9]+.tar.gz", filename): return filename.split("-")[0] elif filename == "ohai-1!0.tar.gz": return "ohai" elif filename == "collective.topicitemsevent-0.1dvl.tar.gz": return "collective.topicitemsevent" elif filename.startswith( ("SpiNNStorageHandlers-1!", "sPyNNakerExternalDevicesPlugin-1!") ): return filename.split("-")[0] elif filename.startswith("limnoria-201"): return "limnoria" elif filename.startswith("pytz-20"): return "pytz" elif filename.startswith("youtube_dl_server-alpha."): return "youtube_dl_server" elif filename == "json-extensions-b76bc7d.tar.gz": return "json-extensions" elif filename == "LitReview-0.6989ev.tar.gz": # typo of "dev" return "LitReview" elif filename.startswith("django_options-r"): return "django_options" elif filename == "Greater than, equal, or less Library-0.1.tar.gz": return "Greater-than-equal-or-less-Library" elif filename.startswith("upstart--main-"): return "upstart" elif filename == "duckduckpy0.1.tar.gz": return "duckduckpy" elif filename == "QUI for MPlayer snapshot_9-14-2011.zip": return "QUI-for-MPlayer" elif filename == "Eddy's Memory Game-1.0.zip": return "Eddy-s-Memory-Game" elif filename == "jekyll2nikola-0-0-1.tar.gz": return "jekyll2nikola" elif filename.startswith("ore.workflowed"): return "ore.workflowed" elif re.match("instancemanager-[0-9]*", filename): return "instancemanager" elif filename == "OrzMC_W&L-1.0.0.tar.gz": return "OrzMC-W-L" + elif filename == "use0mk.tar.gz": + return "use0mk" + elif filename == "play-0-develop-1-gd67cd85.tar.gz": + return "play" filename = filename.replace(" ", "-") match = re.match( r"^(?P[a-z_.-]+)" # project name r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, re.I, ) if match: return match.group("project_name") # First try with a rather strict format, but that allows accidentally # matching the version as part of the package name match = re.match( r"^(?P[a-z0-9_.]+?([-_][a-z][a-z0-9.]+?)*?)" # project name r"-v?" r"([0-9]+!)?" # epoch r"[0-9_.]+([a-z]+[0-9]+)?" # "main" version r"([.-]?(alpha|beta|dev|post|pre|rc)(\.?[0-9]+)?)*" # development status r"([.-]?20[012][0-9]{5,9})?" # date r"([.-]g?[0-9a-f]+)?" # git commit r"([-+]py(thon)?(3k|[23](\.?[0-9]{1,2})?))?" # python version r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, re.I, ) if match: return match.group("project_name") # If that doesn't work, give up on trying to parse version suffixes, # and just find the first version-like occurrence in the file name match = re.match( r"^(?P[a-z0-9_.-]+?)" # project name r"[-_.]v?" r"([0-9]+!)?" # epoch r"(" # "main" version r"[0-9_]+\.[0-9_.]+([a-z]+[0-9]+)?" # classic version number r"|20[012][0-9]{5,9}" # date as integer r"|20[012][0-9]-[01][0-9]-[0-3][0-9]" # date as ISO 8601 r")" # end of "main" version r"[a-z]?(dev|pre)?" # direct version suffix r"([._-].*)?" # extra suffixes r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, re.I, ) if match: return match.group("project_name") # If that still doesn't work, give one last chance if there's only one # dash or underscore in the name match = re.match( r"^(?P[^_-]+)" # project name r"[_-][^_-]+" # version r"\.(tar\.gz|tar\.bz2|tgz|zip)$", # extension filename, ) assert match, original_filename return match.group("project_name") def pypi_origin_from_project_name(project_name: str) -> str: return f"https://pypi.org/project/{project_name}/" def pypi_origin_from_filename(storage, rev_id: bytes, filename: str) -> Optional[str]: project_name = pypi_project_from_filename(filename) origin = pypi_origin_from_project_name(project_name) # But unfortunately, the filename is user-provided, and doesn't # necessarily match the package name on pypi. Therefore, we need # to check it. if _check_revision_in_origin(storage, origin, rev_id): return origin # if the origin we guessed does not exist, query the PyPI API with the # project name we guessed. If only the capitalisation and dash/underscores # are wrong (by far the most common case), PyPI kindly corrects them. try: resp = urlopen(f"https://pypi.org/pypi/{project_name}/json/") except HTTPError as e: assert e.code == 404 # nope; PyPI couldn't correct the wrong project name return None assert resp.code == 200, resp.code project_name = json.load(resp)["info"]["name"] origin = pypi_origin_from_project_name(project_name) if _check_revision_in_origin(storage, origin, rev_id): return origin else: # The origin exists, but the revision does not belong in it. # This happens sometimes, as the filename we guessed the origin # from is user-provided. return None def cran_package_from_url(filename): match = re.match( r"^https://cran\.r-project\.org/src/contrib/" r"(?P[a-zA-Z0-9.]+)_[0-9.-]+(\.tar\.gz)?$", filename, ) assert match, filename return match.group("package_name") def npm_package_from_source_url(package_source_url): match = re.match( "^https://registry.npmjs.org/(?P.*)/-/[^/]+.tgz$", package_source_url, ) assert match, package_source_url return unquote(match.group("package_name")) def remove_atom_codemeta_metadata_with_xmlns(metadata): """Removes all known Atom and Codemeta metadata fields from the dict, assuming this is a dict generated by xmltodict without expanding namespaces. """ keys_to_remove = ATOM_KEYS + ["@xmlns", "@xmlns:codemeta"] for key in list(metadata): if key.startswith("codemeta:") or key in keys_to_remove: del metadata[key] def remove_atom_codemeta_metadata_without_xmlns(metadata): """Removes all known Atom and Codemeta metadata fields from the dict, assuming this is a dict generated by xmltodict with expanded namespaces. """ for key in list(metadata): if key.startswith(("{%s}" % ATOM_NS, "{%s}" % CODEMETA_NS)): del metadata[key] def _check_revision_in_origin(storage, origin, revision_id): seen_snapshots = set() # no need to visit them again seen_revisions = set() for visit in iter_origin_visits(storage, origin): for status in iter_origin_visit_statuses(storage, origin, visit.visit): if status.snapshot is None: continue if status.snapshot in seen_snapshots: continue seen_snapshots.add(status.snapshot) snapshot = snapshot_get_all_branches(storage, status.snapshot) for (branch_name, branch) in snapshot.branches.items(): if branch is None: continue # If it's the revision passed as argument, then it is indeed in the # origin if branch.target == revision_id: return True # Else, let's make sure the branch doesn't have any other revision # Get the revision at the top of the branch. if branch.target in seen_revisions: continue seen_revisions.add(branch.target) revision = storage.revision_get([branch.target])[0] if revision is None: # https://forge.softwareheritage.org/T997 continue # Check it doesn't have parents (else we would have to # recurse) assert revision.parents == (), "revision with parents" return False def debian_origins_from_row(row, storage): """Guesses a Debian origin from a row. May return an empty list if it cannot reliably guess it, but all results are guaranteed to be correct.""" filenames = [entry["filename"] for entry in row["metadata"]["original_artifact"]] package_names = {filename.split("_")[0] for filename in filenames} assert len(package_names) == 1, package_names (package_name,) = package_names candidate_origins = [ f"deb://Debian/packages/{package_name}", f"deb://Debian-Security/packages/{package_name}", f"http://snapshot.debian.org/package/{package_name}/", ] return [ origin for origin in candidate_origins if _check_revision_in_origin(storage, origin, row["id"]) ] # Cache of origins that are known to exist _origins = set() def assert_origin_exists(storage, origin): assert check_origin_exists(storage, origin), origin def check_origin_exists(storage, origin): return ( ( hashlib.sha1(origin.encode()).digest() in _origins # very fast or storage.origin_get([origin])[0] is not None # slow, but up to date ), origin, ) def load_metadata( storage, revision_id, directory_id, discovery_date: datetime.datetime, metadata: Dict[str, Any], format: str, authority: MetadataAuthority, origin: Optional[str], dry_run: bool, ): """Does the actual loading to swh-storage.""" directory_swhid = SWHID( object_type="directory", object_id=hash_to_hex(directory_id) ) revision_swhid = SWHID(object_type="revision", object_id=hash_to_hex(revision_id)) obj = RawExtrinsicMetadata( type=MetadataTargetType.DIRECTORY, target=directory_swhid, discovery_date=discovery_date, authority=authority, fetcher=FETCHER, format=format, metadata=json.dumps(metadata).encode(), origin=origin, revision=revision_swhid, ) if not dry_run: storage.raw_extrinsic_metadata_add([obj]) def handle_deposit_row( row, discovery_date: Optional[datetime.datetime], origin, storage, deposit_cur, dry_run: bool, ): """Loads metadata from the deposit database (which is more reliable as the metadata on the revision object, as some versions of the deposit loader were a bit lossy; and they used very different format for the field in the revision table). """ parsed_message = deposit_revision_message_re.match(row["message"]) assert parsed_message is not None, row["message"] deposit_id = int(parsed_message.group("deposit_id")) collection = parsed_message.group("collection").decode() client_name = parsed_message.group("client").decode() deposit_cur.execute( f"SELECT {', '.join(DEPOSIT_COLS)} FROM deposit " f"INNER JOIN deposit_collection " f" ON (deposit.collection_id=deposit_collection.id) " f"INNER JOIN deposit_client ON (deposit.client_id=deposit_client.user_ptr_id) " f"INNER JOIN auth_user ON (deposit.client_id=auth_user.id) " f"INNER JOIN deposit_request ON (deposit.id=deposit_request.deposit_id) " f"WHERE deposit.id = %s", (deposit_id,), ) provider_urls = set() swhids = set() metadata_entries = [] dates = set() external_identifiers = set() for deposit_request_row in deposit_cur: deposit_request = dict(zip(DEPOSIT_COLS, deposit_request_row)) # Sanity checks to make sure we selected the right deposit assert deposit_request["deposit.id"] == deposit_id assert deposit_request["deposit_collection.name"] == collection, deposit_request if client_name != "": # Sometimes it's missing from the commit message assert deposit_request["auth_user.username"] == client_name # Date of the deposit request (either the initial request, of subsequent ones) date = deposit_request["deposit_request.date"] dates.add(date) assert deposit_request["deposit.swhid_context"], deposit_request external_identifiers.add(deposit_request["deposit.external_id"]) swhids.add(deposit_request["deposit.swhid_context"]) # Client of the deposit provider_urls.add(deposit_request["deposit_client.provider_url"]) metadata = deposit_request["deposit_request.metadata"] if metadata is not None: json.dumps(metadata).encode() # check it's valid if "@xmlns" in metadata: assert metadata["@xmlns"] == ATOM_NS assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS]) format = NEW_DEPOSIT_FORMAT elif "{http://www.w3.org/2005/Atom}id" in metadata: assert ( "{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in metadata or "{http://www.w3.org/2005/Atom}author" in metadata ) format = OLD_DEPOSIT_FORMAT else: # new format introduced in # https://forge.softwareheritage.org/D4065 # it's the same as the first case, but with the @xmlns # declarations stripped # Most of them should have the "id", but some revisions, # like 4d3890004fade1f4ec3bf7004a4af0c490605128, are missing # this field assert "id" in metadata or "title" in metadata assert "codemeta:author" in metadata format = NEW_DEPOSIT_FORMAT metadata_entries.append((date, format, metadata)) if discovery_date is None: discovery_date = max(dates) # Sanity checks to make sure deposit requests are consistent with each other assert len(metadata_entries) >= 1, deposit_id assert len(provider_urls) == 1, f"expected 1 provider url, got {provider_urls}" (provider_url,) = provider_urls assert len(swhids) == 1 (swhid,) = swhids assert ( len(external_identifiers) == 1 ), f"expected 1 external identifier, got {external_identifiers}" (external_identifier,) = external_identifiers # computed the origin from the external_identifier if we don't have one if origin is None: origin = f"{provider_url.strip('/')}/{external_identifier}" # explicit list of mistakes that happened in the past, but shouldn't # happen again: if origin == "https://hal.archives-ouvertes.fr/hal-01588781": # deposit id 75 origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588781" elif origin == "https://hal.archives-ouvertes.fr/hal-01588782": # deposit id 76 origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588782" elif origin == "https://hal.archives-ouvertes.fr/hal-01592430": # deposit id 143 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01592430" elif origin == "https://hal.archives-ouvertes.fr/hal-01588927": origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588927" elif origin == "https://hal.archives-ouvertes.fr/hal-01593875": # deposit id 175 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01593875" elif deposit_id == 160: assert origin == "https://www.softwareheritage.org/je-suis-gpl", origin origin = "https://forge.softwareheritage.org/source/jesuisgpl/" elif origin == "https://hal.archives-ouvertes.fr/hal-01588942": # deposit id 90 origin = "https://inria.halpreprod.archives-ouvertes.fr/hal-01588942" elif origin == "https://hal.archives-ouvertes.fr/hal-01592499": # deposit id 162 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01592499" elif origin == "https://hal.archives-ouvertes.fr/hal-01588935": # deposit id 89 origin = "https://hal-preprod.archives-ouvertes.fr/hal-01588935" assert_origin_exists(storage, origin) # check the origin we computed matches the one in the deposit db swhid_origin = parse_swhid(swhid).metadata["origin"] if origin is not None: # explicit list of mistakes that happened in the past, but shouldn't # happen again: exceptions = [ ( # deposit id 229 "https://hal.archives-ouvertes.fr/hal-01243573", "https://hal-test.archives-ouvertes.fr/hal-01243573", ), ( # deposit id 199 "https://hal.archives-ouvertes.fr/hal-01243065", "https://hal-test.archives-ouvertes.fr/hal-01243065", ), ( # deposit id 164 "https://hal.archives-ouvertes.fr/hal-01593855", "https://hal-preprod.archives-ouvertes.fr/hal-01593855", ), ] if (origin, swhid_origin) not in exceptions: assert origin == swhid_origin, ( f"the origin we guessed from the deposit db or revision ({origin}) " f"doesn't match the one in the deposit db's SWHID ({swhid})" ) authority = MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url=provider_url, metadata={}, ) for (date, format, metadata) in metadata_entries: load_metadata( storage, row["id"], row["directory"], date, metadata, format, authority=authority, origin=origin, dry_run=dry_run, ) return (origin, discovery_date) def handle_row(row: Dict[str, Any], storage, deposit_cur, dry_run: bool): type_ = row["type"] # default date in case we can't find a better one discovery_date = row["date"] or row["committer_date"] metadata = row["metadata"] if metadata is None: return if type_ == "dsc": origin = None # it will be defined later, using debian_origins_from_row # TODO: the debian loader writes the changelog date as the revision's # author date and committer date. Instead, we should use the visit's date if "extrinsic" in metadata: extrinsic_files = metadata["extrinsic"]["raw"]["files"] for artifact_entry in metadata["original_artifact"]: extrinsic_file = extrinsic_files[artifact_entry["filename"]] for key in ("sha256",): assert artifact_entry["checksums"][key] == extrinsic_file[key] artifact_entry["url"] = extrinsic_file["uri"] del metadata["extrinsic"] elif type_ == "tar": provider = metadata.get("extrinsic", {}).get("provider") if provider is not None: # This is the format all the package loaders currently write, and # it is the easiest, thanks to the 'provider' and 'when' fields, # which have all the information we need to tell them easily # and generate accurate metadata discovery_date = iso8601.parse_date(metadata["extrinsic"]["when"]) # New versions of the loaders write the provider; use it. if provider.startswith("https://replicate.npmjs.com/"): # npm loader format 1 parsed_url = urlparse(provider) assert re.match("^/[^/]+/?$", parsed_url.path), parsed_url package_name = unquote(parsed_url.path.strip("/")) origin = "https://www.npmjs.com/package/" + package_name assert_origin_exists(storage, origin) load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["extrinsic"]["raw"], NPM_FORMAT, authority=AUTHORITIES["npmjs"], origin=origin, dry_run=dry_run, ) del metadata["extrinsic"] elif provider.startswith("https://pypi.org/"): # pypi loader format 1 match = re.match( "https://pypi.org/pypi/(?P.*)/json", provider ) assert match, f"unexpected provider URL format: {provider}" project_name = match.group("project_name") origin = f"https://pypi.org/project/{project_name}/" assert_origin_exists(storage, origin) load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["extrinsic"]["raw"], PYPI_FORMAT, authority=AUTHORITIES["pypi"], origin=origin, dry_run=dry_run, ) del metadata["extrinsic"] elif provider.startswith("https://cran.r-project.org/"): # cran loader provider = metadata["extrinsic"]["provider"] if provider.startswith("https://cran.r-project.org/package="): origin = metadata["extrinsic"]["provider"] else: package_name = cran_package_from_url(provider) origin = f"https://cran.r-project.org/package={package_name}" - # TODO https://forge.softwareheritage.org/T2536 assert origin is not None + + # Ideally we should assert the origin exists, but we can't: + # https://forge.softwareheritage.org/T2536 if ( hashlib.sha1(origin.encode()).digest() not in _origins and storage.origin_get([origin])[0] is None ): - print("MISSING CRAN ORIGIN", hash_to_hex(row["id"]), origin) return raw_extrinsic_metadata = metadata["extrinsic"]["raw"] # this is actually intrinsic, ignore it if "version" in raw_extrinsic_metadata: del raw_extrinsic_metadata["version"] # Copy the URL to the original_artifacts metadata assert len(metadata["original_artifact"]) == 1 if "url" in metadata["original_artifact"][0]: assert ( metadata["original_artifact"][0]["url"] == raw_extrinsic_metadata["url"] ), row else: metadata["original_artifact"][0]["url"] = raw_extrinsic_metadata[ "url" ] del raw_extrinsic_metadata["url"] assert ( raw_extrinsic_metadata == {} ), f"Unexpected metadata keys: {list(raw_extrinsic_metadata)}" del metadata["extrinsic"] elif ( provider.startswith("https://nix-community.github.io/nixpkgs-swh/") or provider == "https://guix.gnu.org/sources.json" ): # nixguix loader origin = provider assert_origin_exists(storage, origin) authority = MetadataAuthority( type=MetadataAuthorityType.FORGE, url=provider, metadata={}, ) assert row["date"] is None # the nixguix loader does not write dates load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["extrinsic"]["raw"], NIXGUIX_FORMAT, authority=authority, origin=origin, dry_run=dry_run, ) del metadata["extrinsic"] elif provider.startswith("https://ftp.gnu.org/"): # archive loader format 1 origin = provider assert_origin_exists(storage, origin) assert len(metadata["original_artifact"]) == 1 metadata["original_artifact"][0]["url"] = metadata["extrinsic"]["raw"][ "url" ] # Remove duplicate keys of original_artifacts for key in ("url", "time", "length", "version", "filename"): del metadata["extrinsic"]["raw"][key] assert metadata["extrinsic"]["raw"] == {} del metadata["extrinsic"] elif provider.startswith("https://deposit.softwareheritage.org/"): origin = metadata["extrinsic"]["raw"]["origin"]["url"] assert_origin_exists(storage, origin) if "@xmlns" in metadata: assert metadata["@xmlns"] == ATOM_NS assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS]) assert "intrinsic" not in metadata assert "extra_headers" not in metadata # deposit loader format 1 # in this case, the metadata seems to be both directly in metadata # and in metadata["extrinsic"]["raw"]["metadata"] (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) remove_atom_codemeta_metadata_with_xmlns(metadata) if "client" in metadata: del metadata["client"] del metadata["extrinsic"] else: # deposit loader format 2 actual_metadata = metadata["extrinsic"]["raw"]["origin_metadata"][ "metadata" ] if isinstance(actual_metadata, str): # new format introduced in # https://forge.softwareheritage.org/D4105 actual_metadata = json.loads(actual_metadata) if "@xmlns" in actual_metadata: assert actual_metadata["@xmlns"] == ATOM_NS assert actual_metadata["@xmlns:codemeta"] in ( CODEMETA_NS, [CODEMETA_NS], ) elif "{http://www.w3.org/2005/Atom}id" in actual_metadata: assert ( "{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in actual_metadata ) else: # new format introduced in # https://forge.softwareheritage.org/D4065 # it's the same as the first case, but with the @xmlns # declarations stripped # Most of them should have the "id", but some revisions, # like 4d3890004fade1f4ec3bf7004a4af0c490605128, are missing # this field assert "id" in actual_metadata or "title" in actual_metadata assert "codemeta:author" in actual_metadata (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) del metadata["extrinsic"] else: assert False, f"unknown provider {provider}" # Older versions don't write the provider; use heuristics instead. elif ( metadata.get("package_source", {}) .get("url", "") .startswith("https://registry.npmjs.org/") ): # npm loader format 2 package_source_url = metadata["package_source"]["url"] package_name = npm_package_from_source_url(package_source_url) origin = "https://www.npmjs.com/package/" + package_name assert_origin_exists(storage, origin) load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["package"], NPM_FORMAT, authority=AUTHORITIES["npmjs"], origin=origin, dry_run=dry_run, ) del metadata["package"] assert "original_artifact" not in metadata # rebuild an "original_artifact"-like metadata dict from what we # can salvage of "package_source" package_source_metadata = metadata["package_source"] keep_keys = {"blake2s256", "filename", "sha1", "sha256", "url"} discard_keys = { "date", # is equal to the revision date "name", # was loaded above "version", # same } assert ( set(package_source_metadata) == keep_keys | discard_keys ), package_source_metadata # will be loaded below metadata["original_artifact"] = [ { "filename": package_source_metadata["filename"], "checksums": { "sha1": package_source_metadata["sha1"], "sha256": package_source_metadata["sha256"], "blake2s256": package_source_metadata["blake2s256"], }, "url": package_source_metadata["url"], } ] del metadata["package_source"] elif "@xmlns" in metadata: assert metadata["@xmlns:codemeta"] in (CODEMETA_NS, [CODEMETA_NS]) assert "intrinsic" not in metadata assert "extra_headers" not in metadata # deposit loader format 3 if row["message"] == b"swh: Deposit 159 in collection swh": # There is no deposit 159 in the deposit DB, for some reason assert ( hash_to_hex(row["id"]) == "8e9cee14a6ad39bca4347077b87fb5bbd8953bb1" ) return elif row["message"] == b"hal: Deposit 342 in collection hal": # They have status 'failed' and no swhid return origin = None # TODO discovery_date = None # TODO (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) remove_atom_codemeta_metadata_with_xmlns(metadata) if "client" in metadata: del metadata["client"] # found in the deposit db if "committer" in metadata: del metadata["committer"] # found on the revision object elif "{http://www.w3.org/2005/Atom}id" in metadata: assert ( "{https://doi.org/10.5063/SCHEMA/CODEMETA-2.0}author" in metadata or "{http://www.w3.org/2005/Atom}author" in metadata ) assert "intrinsic" not in metadata assert "extra_headers" not in metadata # deposit loader format 4 origin = None discovery_date = None # TODO (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) remove_atom_codemeta_metadata_without_xmlns(metadata) elif hash_to_hex(row["id"]) == "a86747d201ab8f8657d145df4376676d5e47cf9f": # deposit 91, is missing "{http://www.w3.org/2005/Atom}id" for some # reason, and has an invalid oririn return elif ( isinstance(metadata.get("original_artifact"), dict) and metadata["original_artifact"]["url"].startswith( "https://files.pythonhosted.org/" ) ) or ( isinstance(metadata.get("original_artifact"), list) and len(metadata.get("original_artifact")) == 1 and metadata["original_artifact"][0] .get("url", "") .startswith("https://files.pythonhosted.org/") ): if isinstance(metadata.get("original_artifact"), dict): metadata["original_artifact"] = [metadata["original_artifact"]] assert len(metadata["original_artifact"]) == 1 origin = pypi_origin_from_filename( storage, row["id"], metadata["original_artifact"][0]["filename"] ) if "project" in metadata: # pypi loader format 2 load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["project"], PYPI_FORMAT, authority=AUTHORITIES["pypi"], origin=origin, dry_run=dry_run, ) del metadata["project"] else: assert set(metadata) == {"original_artifact"}, set(metadata) # pypi loader format 3 pass # nothing to do, there's no metadata elif row["message"] == b"synthetic revision message": assert isinstance(metadata["original_artifact"], list), metadata assert not any("url" in d for d in metadata["original_artifact"]) # archive loader format 2 origin = None elif deposit_revision_message_re.match(row["message"]): # deposit without metadata in the revision assert set(metadata) == {"original_artifact"}, metadata origin = None # TODO discovery_date = None (origin, discovery_date) = handle_deposit_row( row, discovery_date, origin, storage, deposit_cur, dry_run ) else: assert False, f"Unable to detect type of metadata for row: {row}" # Ignore common intrinsic metadata keys for key in ("intrinsic", "extra_headers"): if key in metadata: del metadata[key] # Ignore loader-specific intrinsic metadata keys if type_ == "hg": del metadata["node"] elif type_ == "dsc": if "package_info" in metadata: del metadata["package_info"] if "original_artifact" in metadata: for original_artifact in metadata["original_artifact"]: # Rename keys to the expected format of original-artifacts-json. rename_keys = [ ("name", "filename"), # eg. from old Debian loader ("size", "length"), # eg. from old PyPI loader ] for (old_name, new_name) in rename_keys: if old_name in original_artifact: assert new_name not in original_artifact original_artifact[new_name] = original_artifact.pop(old_name) # Move the checksums to their own subdict, which is the expected format # of original-artifacts-json. if "sha1" in original_artifact: assert "checksums" not in original_artifact original_artifact["checksums"] = {} for key in ("sha1", "sha256", "sha1_git", "blake2s256"): if key in original_artifact: original_artifact["checksums"][key] = original_artifact.pop(key) if "date" in original_artifact: # The information comes from the package repository rather than SWH, # so it shouldn't be in the 'original-artifacts' metadata # (which has SWH as authority). # Moreover, it's not a very useful information, so let's just drop it. del original_artifact["date"] allowed_keys = { "checksums", "filename", "length", "url", "archive_type", } assert set(original_artifact) <= allowed_keys, set(original_artifact) if type_ == "dsc": assert origin is None origins = debian_origins_from_row(row, storage) assert origins, row else: origins = [origin] for origin in origins: load_metadata( storage, row["id"], row["directory"], discovery_date, metadata["original_artifact"], ORIGINAL_ARTIFACT_FORMAT, authority=AUTHORITIES["swh"], origin=origin, dry_run=dry_run, ) del metadata["original_artifact"] assert metadata == {}, ( f"remaining metadata keys for {row['id'].hex()} (type: {row['type']}): " f"{metadata}" ) def create_fetchers(db): with db.cursor() as cur: cur.execute( """ INSERT INTO metadata_fetcher (name, version, metadata) VALUES (%s, %s, %s) ON CONFLICT DO NOTHING """, (FETCHER.name, FETCHER.version, FETCHER.metadata), ) def iter_revision_rows(storage_dbconn: str, first_id: Sha1Git): after_id = first_id failures = 0 while True: try: storage_db = BaseDb.connect(storage_dbconn) with storage_db.cursor() as cur: while True: cur.execute( f"SELECT {', '.join(REVISION_COLS)} FROM revision " f"WHERE id > %s AND metadata IS NOT NULL " f"ORDER BY id LIMIT 1000", (after_id,), ) new_rows = 0 for row in cur: new_rows += 1 row_d = dict(zip(REVISION_COLS, row)) yield row_d after_id = row_d["id"] if new_rows == 0: return except psycopg2.OperationalError as e: print(e) # most likely a temporary error, try again if failures >= 60: raise else: time.sleep(60) failures += 1 def main(storage_dbconn, storage_url, deposit_dbconn, first_id, dry_run): storage_db = BaseDb.connect(storage_dbconn) deposit_db = BaseDb.connect(deposit_dbconn) - storage = get_storage("remote", url=storage_url) + storage = get_storage( + "pipeline", + steps=[ + {"cls": "retry"}, + { + "cls": "local", + "db": storage_dbconn, + "objstorage": {"cls": "memory", "args": {}}, + }, + ], + ) if not dry_run: create_fetchers(storage_db) # Not creating authorities, as the loaders are presumably already running # and created them already. # This also helps make sure this script doesn't accidentally create # authorities that differ from what the loaders use. total_rows = 0 with deposit_db.cursor() as deposit_cur: for row in iter_revision_rows(storage_dbconn, first_id): handle_row(row, storage, deposit_cur, dry_run) total_rows += 1 if total_rows % 1000 == 0: percents = ( int.from_bytes(row["id"][0:4], byteorder="big") * 100 / (1 << 32) ) print( f"Processed {total_rows/1000000.:.2f}M rows " f"(~{percents:.1f}%, last revision: {row['id'].hex()})" ) if __name__ == "__main__": if len(sys.argv) == 4: (_, storage_dbconn, storage_url, deposit_dbconn) = sys.argv first_id = "00" * 20 elif len(sys.argv) == 5: (_, storage_dbconn, storage_url, deposit_dbconn, first_id) = sys.argv else: print( f"Syntax: {sys.argv[0]} " f" []" ) exit(1) if os.path.isfile("./origins.txt"): # You can generate this file with: # psql service=swh-replica \ # -c "\copy (select digest(url, 'sha1') from origin) to stdout" \ # | pv -l > origins.txt print("Loading origins...") with open("./origins.txt") as fd: for line in fd: digest = line.strip()[3:] _origins.add(bytes.fromhex(digest)) print("Done loading origins.") main(storage_dbconn, storage_url, deposit_dbconn, bytes.fromhex(first_id), True) diff --git a/swh/storage/retry.py b/swh/storage/retry.py index 19e0d2b3..d74f196e 100644 --- a/swh/storage/retry.py +++ b/swh/storage/retry.py @@ -1,133 +1,87 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import logging import traceback -from typing import Dict, Iterable, List from tenacity import retry, stop_after_attempt, wait_random_exponential -from swh.model.model import ( - Content, - Directory, - MetadataAuthority, - MetadataFetcher, - OriginVisit, - RawExtrinsicMetadata, - Release, - Revision, - SkippedContent, - Snapshot, -) from swh.storage import get_storage from swh.storage.exc import StorageArgumentException from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) def should_retry_adding(retry_state) -> bool: """Retry if the error/exception is (probably) not about a caller error """ try: attempt = retry_state.outcome except AttributeError: # tenacity < 5.0 attempt = retry_state if attempt.failed: error = attempt.exception() if isinstance(error, StorageArgumentException): # Exception is due to an invalid argument return False elif isinstance(error, KeyboardInterrupt): return False else: # Other exception module = getattr(error, "__module__", None) if module: error_name = error.__module__ + "." + error.__class__.__name__ else: error_name = error.__class__.__name__ logger.warning( - "Retry adding a batch", + "Retrying RPC call", exc_info=False, extra={ "swh_type": "storage_retry", "swh_exception_type": error_name, "swh_exception": traceback.format_exc(), }, ) return True else: # No exception return False swh_retry = retry( retry=should_retry_adding, wait=wait_random_exponential(multiplier=1, max=10), stop=stop_after_attempt(3), ) +def retry_function(storage, attribute_name): + @swh_retry + def newf(*args, **kwargs): + return getattr(storage, attribute_name)(*args, **kwargs) + + return newf + + class RetryingProxyStorage: """Storage implementation which retries adding objects when it specifically fails (hash collision, integrity error). """ def __init__(self, storage): self.storage: StorageInterface = get_storage(**storage) - - def __getattr__(self, key): - if key == "storage": - raise AttributeError(key) - return getattr(self.storage, key) - - @swh_retry - def content_add(self, content: List[Content]) -> Dict: - return self.storage.content_add(content) - - @swh_retry - def content_add_metadata(self, content: List[Content]) -> Dict: - return self.storage.content_add_metadata(content) - - @swh_retry - def skipped_content_add(self, content: List[SkippedContent]) -> Dict: - return self.storage.skipped_content_add(content) - - @swh_retry - def origin_visit_add(self, visits: List[OriginVisit]) -> Iterable[OriginVisit]: - return self.storage.origin_visit_add(visits) - - @swh_retry - def metadata_fetcher_add(self, fetchers: List[MetadataFetcher],) -> None: - return self.storage.metadata_fetcher_add(fetchers) - - @swh_retry - def metadata_authority_add(self, authorities: List[MetadataAuthority]) -> None: - return self.storage.metadata_authority_add(authorities) - - @swh_retry - def raw_extrinsic_metadata_add(self, metadata: List[RawExtrinsicMetadata],) -> None: - return self.storage.raw_extrinsic_metadata_add(metadata) - - @swh_retry - def directory_add(self, directories: List[Directory]) -> Dict: - return self.storage.directory_add(directories) - - @swh_retry - def revision_add(self, revisions: List[Revision]) -> Dict: - return self.storage.revision_add(revisions) - - @swh_retry - def release_add(self, releases: List[Release]) -> Dict: - return self.storage.release_add(releases) - - @swh_retry - def snapshot_add(self, snapshots: List[Snapshot]) -> Dict: - return self.storage.snapshot_add(snapshots) + for attribute_name in dir(StorageInterface): + if attribute_name.startswith("_"): + continue + attribute = getattr(self.storage, attribute_name) + if hasattr(attribute, "__call__"): + setattr( + self, attribute_name, retry_function(self.storage, attribute_name) + ) diff --git a/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py b/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py index 2a39eb48..152ed701 100644 --- a/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py +++ b/swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py @@ -1,646 +1,648 @@ # 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 # flake8: noqa # because of long lines import copy import datetime import json import urllib.error import attr from swh.model.identifiers import parse_swhid from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Snapshot, SnapshotBranch, TargetType, ) from swh.storage import get_storage from swh.storage.interface import PagedResult from swh.storage.migrate_extrinsic_metadata import ( handle_row, pypi_origin_from_filename, pypi_project_from_filename, ) FETCHER = MetadataFetcher( name="migrate-extrinsic-metadata-from-revisions", version="0.0.1", ) PYPI_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://pypi.org/", ) SWH_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", ) DIRECTORY_ID = b"a" * 20 DIRECTORY_SWHID = parse_swhid("swh:1:dir:" + DIRECTORY_ID.hex()) def now(): return datetime.datetime.now(tz=datetime.timezone.utc) def test_pypi_project_from_filename(): files = [ ("django-agent-trust-0.1.8.tar.gz", "django-agent-trust"), ("python_test-1.0.1.zip", "python_test"), ("py-evm-0.2.0a9.tar.gz", "py-evm"), ("collective.texttospeech-1.0rc1.tar.gz", "collective.texttospeech"), ("flatland-fork-0.4.post1.dev40550160.zip", "flatland-fork"), ("fake-factory-0.5.6-proper.tar.gz", "fake-factory"), ("ariane_procos-0.1.2-b05.tar.gz", "ariane_procos"), ("Yelpy-0.2.2dev.tar.gz", "Yelpy"), ("geventhttpclient_c-1.0a-t1.tar.gz", "geventhttpclient_c"), ("codeforlife-portal-1.0.0.post.dev618.tar.gz", "codeforlife-portal"), ("ChecklistDSL-0.0.1.alpha.1.tar.gz", "ChecklistDSL"), ("transifex-1.1.0beta.tar.gz", "transifex"), ("thespian-2.5.10.tar.bz2", "thespian"), ("janis pipelines-0.5.3.tar.gz", "janis-pipelines"), ("pants-1.0.0-beta.2.tar.gz", "pants"), ("uforge_python_sdk-3.8.4-RC15.tar.gz", "uforge_python_sdk"), ("virtuoso-0.11.0.48.b5865c2b46fb.tar.gz", "virtuoso"), ("cloud_ftp-v1.0.0.tar.gz", "cloud_ftp"), ("frozenordereddict-1.0.0.tgz", "frozenordereddict"), ("pywebsite-0.1.2pre.tar.gz", "pywebsite"), ("Flask Unchained-0.2.0.tar.gz", "Flask-Unchained"), ("mongomotor-0.13.0.n.tar.gz", "mongomotor"), ("datahaven-rev8784.tar.gz", "datahaven"), ("geopandas-0.1.0.dev-120d5ee.tar.gz", "geopandas"), ("aimmo-v0.1.1-alpha.post.dev61.tar.gz", "aimmo"), ("django-migrations-plus-0.1.0.dev5.gdd1abd3.tar.gz", "django-migrations-plus"), ("function_shield.tar.gz", "function_shield"), ("Dtls-0.1.0.sdist_with_openssl.mingw-win32.tar.gz", "Dtls"), ("pytz-2005m.tar.gz", "pytz"), ("python-librsync-0.1-3.tar.gz", "python-librsync"), ("powny-1.4.0-alpha-20141205-1452-f5a2b03.tar.gz", "powny"), ("stp-3pc-batch-0.1.11.tar.gz", "stp-3pc-batch"), ("obedient.powny-3.0.0-alpha-20141027-2102-9e53ebd.tar.gz", "obedient.powny"), ("mojimoji-0.0.9_2.tar.gz", "mojimoji"), ("devpi-theme-16-2.0.0.tar.gz", "devpi-theme-16"), ("Orange3-WONDER-1-1.0.7.tar.gz", "Orange3-WONDER-1"), ("obj-34.tar.gz", "obj"), ("pytorch-ignite-nightly-20190825.tar.gz", "pytorch-ignite-nightly"), ("tlds-2019081900.tar.gz", "tlds"), ("dominator-12.1.2-alpha-20141027-1446-ad46e0f.tar.gz", "dominator"), ("waferslim-1.0.0-py3.1.zip", "waferslim"), ("Beaver-21.tar.gz", "Beaver"), ("aimmo-0.post.dev460.tar.gz", "aimmo"), ("ohai-1!0.tar.gz", "ohai"), ("nevolution-risk-139.tar.gz", "nevolution-risk"), ("collective.topicitemsevent-0.1dvl.tar.gz", "collective.topicitemsevent"), ("lesscpy-0.9g.tar.gz", "lesscpy"), ("SpiNNStorageHandlers-1!4.0.0a1.tar.gz", "SpiNNStorageHandlers"), ("limnoria-2013-03-27T16:32:26+0100.tar.gz", "limnoria"), ( "sPyNNakerExternalDevicesPlugin-1!4.0.0a2.tar.gz", "sPyNNakerExternalDevicesPlugin", ), ("django-bootstrap-italia_0.1.tar.gz", "django-bootstrap-italia"), ("sPyNNaker8-1!4.0.0a1.tar.gz", "sPyNNaker8"), ("betahaus.openmember-0.1adev-r1651.tar.gz", "betahaus.openmember"), ("mailer.0.8.0.zip", "mailer"), ("pytz-2005k.tar.bz2", "pytz"), ("aha.plugin.microne-0.62bdev.tar.gz", "aha.plugin.microne"), ("youtube_dl_server-alpha.3.tar.gz", "youtube_dl_server"), ("json-extensions-b76bc7d.tar.gz", "json-extensions"), ("LitReview-0.6989ev.tar.gz", "LitReview"), ("django_options-r5.tar.gz", "django_options"), ("ddlib-2013-11-07.tar.gz", "ddlib"), ("python-morfeusz-0.3000+py3k.tar.gz", "python-morfeusz"), ("gaepytz-2011h.zip", "gaepytz"), ("ftldat-r3.tar.gz", "ftldat"), ("tigretoolbox-0.0.0-py2.7-linux-x86_64.egg", None), ( "Greater than, equal, or less Library-0.1.tar.gz", "Greater-than-equal-or-less-Library", ), ("upstart--main-.-VLazy.object.at.0x104ba8b50-.tar.gz", "upstart"), ("duckduckpy0.1.tar.gz", "duckduckpy"), ("QUI for MPlayer snapshot_9-14-2011.zip", "QUI-for-MPlayer"), ("Eddy's Memory Game-1.0.zip", "Eddy-s-Memory-Game"), ("jekyll2nikola-0-0-1.tar.gz", "jekyll2nikola"), ("ore.workflowed-0-6-2.tar.gz", "ore.workflowed"), ("instancemanager-1.0rc-r34317.tar.gz", "instancemanager"), ("OrzMC_W&L-1.0.0.tar.gz", "OrzMC-W-L"), + ("use0mk.tar.gz", "use0mk"), + ("play-0-develop-1-gd67cd85.tar.gz", "play"), ] for (filename, project) in files: assert pypi_project_from_filename(filename) == project def test_pypi_origin_from_project_name(mocker): origin_url = "https://pypi.org/project/ProjectName/" storage = get_storage("memory") revision_id = b"41" * 10 snapshot_id = b"42" * 10 storage.origin_add([Origin(url=origin_url)]) storage.origin_visit_add( [OriginVisit(origin=origin_url, visit=1, date=now(), type="pypi")] ) storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=1, date=now(), status="partial", snapshot=snapshot_id, ) ] ) storage.snapshot_add( [ Snapshot( id=snapshot_id, branches={ b"foo": SnapshotBranch( target_type=TargetType.REVISION, target=revision_id, ) }, ) ] ) class response: code = 200 def read(self): return b'{"info": {"name": "ProjectName"}}' mock_urlopen = mocker.patch( "swh.storage.migrate_extrinsic_metadata.urlopen", return_value=response(), ) assert ( pypi_origin_from_filename(storage, revision_id, "ProjectName-1.0.0.tar.gz") == origin_url ) mock_urlopen.assert_not_called() assert ( pypi_origin_from_filename(storage, revision_id, "projectname-1.0.0.tar.gz") == origin_url ) mock_urlopen.assert_called_once_with("https://pypi.org/pypi/projectname/json/") def test_pypi_1(): """Tests loading a revision generated by a new PyPI loader that has a provider.""" extrinsic_metadata = { "url": "https://files.pythonhosted.org/packages/70/89/a498245baf1bf3dde73d3da00b4b067a8aa7c7378ad83472078803ea3e43/m3-ui-2.2.73.tar.gz", "size": 3933168, "digests": { "md5": "a374ac3f655e97df5db5335e2142d344", "sha256": "1bc2756f7d0d2e15cf5880ca697682ff35e8b58116bf73eb9c78b3db358c5b7d", }, "has_sig": False, "filename": "m3-ui-2.2.73.tar.gz", "downloads": -1, "md5_digest": "a374ac3f655e97df5db5335e2142d344", "packagetype": "sdist", "upload_time": "2019-11-11T06:21:20", "comment_text": "", "python_version": "source", "requires_python": None, "upload_time_iso_8601": "2019-11-11T06:21:20.073082Z", } original_artifacts = [ { "length": 3933168, "filename": "m3-ui-2.2.73.tar.gz", "checksums": { "sha1": "9f4ec7ce64b7fea4b122e85d47ea31146c367b03", "sha256": "1bc2756f7d0d2e15cf5880ca697682ff35e8b58116bf73eb9c78b3db358c5b7d", }, } ] row = { "id": b"\x00\x00\x07a{S\xe7\xb1E\x8fi]\xd0}\xe4\xceU\xaf\x15\x17", "directory": DIRECTORY_ID, "date": datetime.datetime( 2019, 11, 11, 6, 21, 20, tzinfo=datetime.timezone.utc, ), "committer_date": datetime.datetime( 2019, 11, 11, 6, 21, 20, tzinfo=datetime.timezone.utc, ), "type": "tar", "message": b"2.2.73", "metadata": { "extrinsic": { "raw": extrinsic_metadata, "when": "2020-01-23T18:43:09.109407+00:00", "provider": "https://pypi.org/pypi/m3-ui/json", }, "intrinsic": { "raw": { "name": "m3-ui", "summary": "======", "version": "2.2.73", # ... "metadata_version": "1.1", }, "tool": "PKG-INFO", }, "original_artifact": original_artifacts, }, } origin_url = "https://pypi.org/project/m3-ui/" storage = get_storage("memory") storage.origin_add([Origin(url=origin_url)]) storage.metadata_authority_add( [ attr.evolve(PYPI_AUTHORITY, metadata={}), attr.evolve(SWH_AUTHORITY, metadata={}), ] ) storage.metadata_fetcher_add([FETCHER]) deposit_cur = None handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False) revision_swhid = parse_swhid("swh:1:rev:000007617b53e7b1458f695dd07de4ce55af1517") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=PYPI_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.DIRECTORY, target=DIRECTORY_SWHID, discovery_date=datetime.datetime( 2020, 1, 23, 18, 43, 9, 109407, tzinfo=datetime.timezone.utc, ), authority=PYPI_AUTHORITY, fetcher=FETCHER, format="pypi-project-json", metadata=json.dumps(extrinsic_metadata).encode(), origin=origin_url, revision=revision_swhid, ), ], next_page_token=None, ) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.DIRECTORY, target=DIRECTORY_SWHID, discovery_date=datetime.datetime( 2020, 1, 23, 18, 43, 9, 109407, tzinfo=datetime.timezone.utc, ), authority=SWH_AUTHORITY, fetcher=FETCHER, format="original-artifacts-json", metadata=json.dumps(original_artifacts).encode(), origin=origin_url, revision=revision_swhid, ), ], next_page_token=None, ) def test_pypi_2(mocker): """Tests loading a revision generated by an old PyPI loader that does not have a provider, but has 'project' metadata.""" mocker.patch( "swh.storage.migrate_extrinsic_metadata.urlopen", side_effect=urllib.error.HTTPError(None, 404, "Not Found", None, None), ) extrinsic_metadata = { "name": "jupyterhub-simx", "author": "Jupyter Development Team", "license": "BSD", "summary": "JupyterHub: A multi-user server for Jupyter notebooks", "version": "1.0.5", # ... } source_original_artifacts = [ { "url": "https://files.pythonhosted.org/packages/72/28/a8098763d78e2c4607cb67602c0d726a97ac38d4c1f531aac28f49de2e1a/jupyterhub-simx-1.0.5.tar.gz", "date": "2019-01-23T22:10:55", "sha1": "ede3eadd5a06e70912e3ba7cfccef789c4ad3168", "size": 2346538, "sha256": "0399d7f5f0d90c525d369f0507ad0e8ef8729c1c7fa63aadfc46a27514d14a46", "filename": "jupyterhub-simx-1.0.5.tar.gz", "sha1_git": "734301124712182eb30fc90e97cc18cef5432f02", "blake2s256": "bb4aa82ffb5891a05dcf6d4dce3ad56fd2c18e9abdba9d20972910649d869322", "archive_type": "tar", } ] dest_original_artifacts = [ { "url": "https://files.pythonhosted.org/packages/72/28/a8098763d78e2c4607cb67602c0d726a97ac38d4c1f531aac28f49de2e1a/jupyterhub-simx-1.0.5.tar.gz", "filename": "jupyterhub-simx-1.0.5.tar.gz", "archive_type": "tar", "length": 2346538, "checksums": { "sha1": "ede3eadd5a06e70912e3ba7cfccef789c4ad3168", "sha256": "0399d7f5f0d90c525d369f0507ad0e8ef8729c1c7fa63aadfc46a27514d14a46", "sha1_git": "734301124712182eb30fc90e97cc18cef5432f02", "blake2s256": "bb4aa82ffb5891a05dcf6d4dce3ad56fd2c18e9abdba9d20972910649d869322", }, } ] row = { "id": b"\x00\x00\x04\xd68,J\xd4\xc0Q\x92fbl6U\x1f\x0eQ\xca", "directory": DIRECTORY_ID, "date": datetime.datetime( 2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc ), "committer_date": datetime.datetime( 2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc ), "type": "tar", "message": b"1.0.5", "metadata": { "project": extrinsic_metadata, "original_artifact": source_original_artifacts, }, } origin_url = "https://pypi.org/project/jupyterhub-simx/" storage = get_storage("memory") storage.origin_add([Origin(url=origin_url)]) storage.metadata_authority_add( [ attr.evolve(PYPI_AUTHORITY, metadata={}), attr.evolve(SWH_AUTHORITY, metadata={}), ] ) storage.metadata_fetcher_add([FETCHER]) deposit_cur = None handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False) revision_swhid = parse_swhid("swh:1:rev:000004d6382c4ad4c0519266626c36551f0e51ca") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=PYPI_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.DIRECTORY, target=DIRECTORY_SWHID, discovery_date=datetime.datetime( 2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc, ), authority=PYPI_AUTHORITY, fetcher=FETCHER, format="pypi-project-json", metadata=json.dumps(extrinsic_metadata).encode(), origin=None, revision=revision_swhid, ), ], next_page_token=None, ) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.DIRECTORY, target=DIRECTORY_SWHID, discovery_date=datetime.datetime( 2019, 1, 23, 22, 10, 55, tzinfo=datetime.timezone.utc, ), authority=SWH_AUTHORITY, fetcher=FETCHER, format="original-artifacts-json", metadata=json.dumps(dest_original_artifacts).encode(), origin=None, revision=revision_swhid, ), ], next_page_token=None, ) def test_pypi_3(mocker): """Tests loading a revision generated by a very old PyPI loader that does not have a provider or has 'project' metadata.""" mocker.patch( "swh.storage.migrate_extrinsic_metadata.urlopen", side_effect=urllib.error.HTTPError(None, 404, "Not Found", None, None), ) source_original_artifact = { "url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz", "date": "2014-05-07T22:03:00", "sha1": "3289269f75b4111dd00eaea53e00330db9a1db12", "size": 46644, "sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824", "filename": "PyPDFLite-0.1.32.tar.gz", "sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5", "blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385", "archive_type": "tar", } dest_original_artifacts = [ { "url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz", "filename": "PyPDFLite-0.1.32.tar.gz", "archive_type": "tar", "length": 46644, "checksums": { "sha1": "3289269f75b4111dd00eaea53e00330db9a1db12", "sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824", "sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5", "blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385", }, } ] row = { "id": b"N\xa9\x91|\xdfS\xcd\x13SJ\x04.N\xb3x{\x86\xc84\xd2", "directory": DIRECTORY_ID, "date": datetime.datetime(2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc), "committer_date": datetime.datetime( 2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc ), "type": "tar", "message": b"0.1.32", "metadata": {"original_artifact": source_original_artifact}, } origin_url = "https://pypi.org/project/PyPDFLite/" storage = get_storage("memory") storage.origin_add([Origin(url=origin_url)]) storage.metadata_authority_add( [ attr.evolve(PYPI_AUTHORITY, metadata={}), attr.evolve(SWH_AUTHORITY, metadata={}), ] ) storage.metadata_fetcher_add([FETCHER]) deposit_cur = None handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False) revision_swhid = parse_swhid("swh:1:rev:4ea9917cdf53cd13534a042e4eb3787b86c834d2") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=PYPI_AUTHORITY, ) == PagedResult(results=[], next_page_token=None,) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.DIRECTORY, target=DIRECTORY_SWHID, discovery_date=datetime.datetime( 2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc, ), authority=SWH_AUTHORITY, fetcher=FETCHER, format="original-artifacts-json", metadata=json.dumps(dest_original_artifacts).encode(), origin=None, revision=revision_swhid, ), ], next_page_token=None, ) def test_pypi_good_origin(): """Tests loading a revision whose origin we can find""" source_original_artifact = { "url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz", "date": "2014-05-07T22:03:00", "sha1": "3289269f75b4111dd00eaea53e00330db9a1db12", "size": 46644, "sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824", "filename": "PyPDFLite-0.1.32.tar.gz", "sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5", "blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385", "archive_type": "tar", } dest_original_artifacts = [ { "url": "https://files.pythonhosted.org/packages/34/4f/30087f22eaae8ad7077a28ce157342745a2977e264b8a8e4e7f804a8aa5e/PyPDFLite-0.1.32.tar.gz", "filename": "PyPDFLite-0.1.32.tar.gz", "archive_type": "tar", "length": 46644, "checksums": { "sha1": "3289269f75b4111dd00eaea53e00330db9a1db12", "sha256": "911497d655cf7ef6530c5b57773dad7da97e21cf4d608ad9ad1e38bd7bec7824", "sha1_git": "1e5c38014731242cfa8594839bcba8a0c4e158c5", "blake2s256": "45792e57873f56d385c694e36c98a580cbba60d5ea91eb6fd0a2d1c71c1fb385", }, } ] revision_id = b"N\xa9\x91|\xdfS\xcd\x13SJ\x04.N\xb3x{\x86\xc84\xd2" row = { "id": revision_id, "directory": DIRECTORY_ID, "date": datetime.datetime(2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc), "committer_date": datetime.datetime( 2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc ), "type": "tar", "message": b"0.1.32", "metadata": {"original_artifact": source_original_artifact}, } origin_url = "https://pypi.org/project/PyPDFLite/" storage = get_storage("memory") snapshot_id = b"42" * 10 storage.origin_add([Origin(url=origin_url)]) storage.origin_visit_add( [OriginVisit(origin=origin_url, visit=1, date=now(), type="pypi")] ) storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=1, date=now(), status="partial", snapshot=snapshot_id, ) ] ) storage.snapshot_add( [ Snapshot( id=snapshot_id, branches={ b"foo": SnapshotBranch( target_type=TargetType.REVISION, target=revision_id, ) }, ) ] ) storage.metadata_authority_add( [ attr.evolve(PYPI_AUTHORITY, metadata={}), attr.evolve(SWH_AUTHORITY, metadata={}), ] ) storage.metadata_fetcher_add([FETCHER]) deposit_cur = None handle_row(copy.deepcopy(row), storage, deposit_cur, dry_run=False) revision_swhid = parse_swhid("swh:1:rev:4ea9917cdf53cd13534a042e4eb3787b86c834d2") assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=PYPI_AUTHORITY, ) == PagedResult(results=[], next_page_token=None,) assert storage.raw_extrinsic_metadata_get( MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, authority=SWH_AUTHORITY, ) == PagedResult( results=[ RawExtrinsicMetadata( type=MetadataTargetType.DIRECTORY, target=DIRECTORY_SWHID, discovery_date=datetime.datetime( 2014, 5, 7, 22, 3, tzinfo=datetime.timezone.utc, ), authority=SWH_AUTHORITY, fetcher=FETCHER, format="original-artifacts-json", metadata=json.dumps(dest_original_artifacts).encode(), origin=origin_url, revision=revision_swhid, ), ], next_page_token=None, ) diff --git a/swh/storage/tests/storage_tests.py b/swh/storage/tests/storage_tests.py index 702a5ac2..33bcd4f4 100644 --- a/swh/storage/tests/storage_tests.py +++ b/swh/storage/tests/storage_tests.py @@ -1,3927 +1,3936 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from 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 import attr from hypothesis import HealthCheck, given, settings, strategies import pytest from swh.model import from_disk from swh.model.hashutil import hash_to_bytes from swh.model.hypothesis_strategies import objects from swh.model.identifiers import SWHID from swh.model.model import ( Content, Directory, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, Person, Revision, SkippedContent, Snapshot, TargetType, ) from swh.storage import get_storage from swh.storage.common import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.interface import ListOrder, PagedResult, StorageInterface from swh.storage.utils import content_hex_hashes, now, 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 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() 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_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 @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 @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] + 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] + 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 def test_content_get(self, swh_storage, sample_data): cont1, cont2 = sample_data.contents[:2] swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get([cont1.sha1, cont2.sha1]) # 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 def test_content_get_missing_sha1(self, swh_storage, sample_data): 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( [cont1.sha1, cont2.sha1, missing_cont.sha1] ) 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.directories[1] 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 == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 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_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} 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_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_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} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 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[:2]) origin_urls = [o.url for o in origins] assert swh_storage.origin_get(origin_urls) == [None, None] stats = swh_storage.origin_add(origins) assert stats == {"origin:add": 2} actual_origins = swh_storage.origin_get(origin_urls) assert actual_origins == origins assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origins[0]), ("origin", origins[1]),] ) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 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_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=origin.url, visit=ov1.visit, date=date_visit1, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_visit2, status="partial", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date_visit3, 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=None, ) ] ) swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(origins) assert stats["origin_visit"] == len(origins) * len(visits) random_ov, random_ovs = swh_storage.origin_visit_status_get_random(visit_type) assert random_ov and random_ovs assert random_ov.origin is not None assert random_ov.origin == random_ovs.origin assert random_ov.origin in [o.url for o in origins] 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_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_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 ovs1 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=date_visit, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=date_visit2, status="created", snapshot=None, ) actual_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_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=origin1.url, visit=ov1.visit, date=sample_data.date_visit1, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin2.url, visit=ov2.visit, date=sample_data.date_visit2, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, 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, status="ongoing", snapshot=None, metadata={"intrinsic": "something"}, ) swh_storage.origin_visit_status_add([visit_status1, visit_status2]) 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=origin1.url, visit=ov1.visit, date=sample_data.date_visit1, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, status="full", snapshot=snapshot.id, ) swh_storage.origin_visit_status_add([visit_status1]) # second call will ignore existing entries (will send to storage though) swh_storage.origin_visit_status_add([visit_status1]) 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=origin.url, visit=ov1.visit, date=round_to_milliseconds(now()), 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=origin.url, visit=ov1.visit, date=round_to_milliseconds(now()), 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=origin.url, visit=ov2.visit, date=round_to_milliseconds(now()), 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=origin.url, visit=ov3.visit, date=round_to_milliseconds(now()), 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__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=origin1.url, visit=ov1.visit, date=sample_data.date_visit1, status="partial", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin1.url, visit=ov1.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=sample_data.date_visit2 + datetime.timedelta(minutes=1), # to not be ignored status="ongoing", snapshot=None, ) ovs4 = OriginVisitStatus( origin=origin1.url, visit=ov2.visit, date=date_now, status="full", snapshot=snapshot.id, metadata={"something": "wicked"}, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3, ovs4]) # unknown origin so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( "unknown-origin", ov1.visit ) assert actual_origin_visit is None # unknown visit so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( ov1.origin, ov1.visit + 10 ) assert actual_origin_visit is None # Two visits, both with no snapshot, take the most recent actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit ) assert isinstance(actual_origin_visit2, OriginVisitStatus) assert actual_origin_visit2 == ovs2 assert ovs2.origin == origin1.url assert ovs2.visit == ov1.visit actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, require_snapshot=True ) # there is no visit with snapshot yet for that visit assert actual_origin_visit is None actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, allowed_statuses=["partial", "ongoing"] ) # visit status with partial status visit elected assert actual_origin_visit2 == ovs2 assert actual_origin_visit2.status == "ongoing" actual_origin_visit4 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True ) assert actual_origin_visit4 == ovs4 assert actual_origin_visit4.snapshot == snapshot.id actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True, allowed_statuses=["ongoing"] ) # nothing matches so nothing assert actual_origin_visit is None # there is no visit with status full actual_origin_visit3 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, allowed_statuses=["ongoing"] ) assert actual_origin_visit3 == ovs3 def test_person_fullname_unicity(self, swh_storage, sample_data): 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=origin.url, visit=ov1.visit, date=date_now, status="full", snapshot=empty_snapshot.id, ) ] ) by_id = swh_storage.snapshot_get(empty_snapshot.id) assert by_id == {**empty_snapshot_dict, "next_branch": None} ovs1 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": sample_data.date_visit1, "visit": ov1.visit, "status": "created", "snapshot": None, "metadata": None, } ) ovs2 = OriginVisitStatus.from_dict( { "origin": origin.url, "date": date_now, "visit": ov1.visit, "status": "full", "metadata": None, "snapshot": empty_snapshot.id, } ) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("origin", origin), ("origin_visit", ov1), ("origin_visit_status", ovs1,), ("snapshot", empty_snapshot), ("origin_visit_status", ovs2,), ] for obj in expected_objects: assert obj in actual_objects def test_snapshot_add_get_complete(self, swh_storage, sample_data): 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} 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, } 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_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(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): 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] content_swhid = SWHID( object_type="content", object_id=hash_to_bytes(content.sha1_git) ) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add(content_metadata) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == 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 updated.""" content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] content_swhid = SWHID( object_type="content", object_id=hash_to_bytes(content.sha1_git) ) new_content_metadata2 = attr.evolve( content_metadata2, format="new-format", metadata=b"new-metadata", ) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_add([new_content_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority ) assert result.next_page_token is None expected_results1 = (content_metadata, new_content_metadata2) expected_results2 = (content_metadata, content_metadata2) assert tuple(sorted(result.results, key=lambda x: x.discovery_date,)) in ( expected_results1, # cassandra expected_results2, # postgresql ) def test_content_metadata_get(self, swh_storage, sample_data): 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] content1_swhid = SWHID(object_type="content", object_id=content.sha1_git) content2_swhid = SWHID(object_type="content", object_id=content2.sha1_git) content2_metadata = attr.evolve(content1_metadata2, target=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( MetadataTargetType.CONTENT, content1_swhid, authority ) assert result.next_page_token is None assert [content1_metadata1, content1_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content1_swhid, authority2 ) assert result.next_page_token is None assert [content1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content2_swhid, authority ) assert result.next_page_token is None assert [content2_metadata] == list(result.results,) def test_content_metadata_get_after(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, after=content_metadata.discovery_date - timedelta(seconds=1), ) assert result.next_page_token is None assert [content_metadata, content_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, after=content_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [content_metadata2] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, after=content_metadata2.discovery_date, ) assert result.next_page_token is None assert result.results == [] def test_content_metadata_get_paginate(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [content_metadata2] def test_content_metadata_get_paginate_same_date(self, swh_storage, sample_data): content = sample_data.content fetcher1, fetcher2 = sample_data.fetchers[:2] authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] content_swhid = SWHID(object_type="content", object_id=content.sha1_git) swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_content_metadata2 = attr.evolve( content_metadata2, discovery_date=content_metadata2.discovery_date, fetcher=attr.evolve(fetcher2, metadata=None), ) swh_storage.raw_extrinsic_metadata_add( [content_metadata, new_content_metadata2] ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, content_swhid, authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [new_content_metadata2] def test_content_metadata_get__invalid_id(self, swh_storage, sample_data): origin = sample_data.origin 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]) with pytest.raises(StorageArgumentException, match="SWHID"): swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.CONTENT, origin.url, authority ) 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( MetadataTargetType.ORIGIN, origin.url, authority ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date)) == [ origin_metadata, origin_metadata2, ] 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} new_origin_metadata2 = attr.evolve( origin_metadata2, format="new-format", metadata=b"new-metadata", ) swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) swh_storage.raw_extrinsic_metadata_add([new_origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority ) assert result.next_page_token is None # which of the two behavior happens is backend-specific. expected_results1 = (origin_metadata, new_origin_metadata2) expected_results2 = (origin_metadata, origin_metadata2) assert tuple(sorted(result.results, key=lambda x: x.discovery_date,)) in ( expected_results1, # cassandra expected_results2, # postgresql ) def test_origin_metadata_get(self, swh_storage, sample_data): 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 = attr.evolve(origin1_metadata2, target=origin2.url) 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( MetadataTargetType.ORIGIN, origin.url, authority ) assert result.next_page_token is None assert [origin1_metadata1, origin1_metadata2] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority2 ) assert result.next_page_token is None assert [origin1_metadata3] == list( sorted(result.results, key=lambda x: x.discovery_date,) ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin2.url, authority ) assert result.next_page_token is None assert [origin2_metadata] == list(result.results,) def test_origin_metadata_get_after(self, swh_storage, sample_data): 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( MetadataTargetType.ORIGIN, origin.url, authority, after=origin_metadata.discovery_date - timedelta(seconds=1), ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == [ origin_metadata, origin_metadata2, ] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, after=origin_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [origin_metadata2] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, after=origin_metadata2.discovery_date, ) assert result.next_page_token is None assert result.results == [] def test_origin_metadata_get_paginate(self, swh_storage, sample_data): 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( MetadataTargetType.ORIGIN, origin.url, authority ) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [origin_metadata2] def test_origin_metadata_get_paginate_same_date(self, swh_storage, sample_data): 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 = attr.evolve( origin_metadata2, discovery_date=origin_metadata2.discovery_date, fetcher=attr.evolve(fetcher2, metadata=None), ) swh_storage.raw_extrinsic_metadata_add([origin_metadata, new_origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, origin.url, authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [new_origin_metadata2] def test_origin_metadata_add_missing_authority(self, swh_storage, sample_data): 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]) def test_origin_metadata_get__invalid_id_type(self, swh_storage, sample_data): origin = sample_data.origin authority = sample_data.metadata_authority fetcher = sample_data.metadata_fetcher origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] content_metadata = sample_data.content_metadata[0] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) with pytest.raises(StorageArgumentException, match="SWHID"): swh_storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, content_metadata.target, authority, ) 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]) @given(strategies.lists(objects(split_content=True), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: if obj.object_type == "origin_visit": swh_storage.origin_add([Origin(url=obj.origin)]) visit = OriginVisit(origin=obj.origin, date=obj.date, type=obj.type,) swh_storage.origin_visit_add([visit]) else: method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass diff --git a/swh/storage/tests/test_retry.py b/swh/storage/tests/test_retry.py index d58aac44..132acdad 100644 --- a/swh/storage/tests/test_retry.py +++ b/swh/storage/tests/test_retry.py @@ -1,837 +1,197 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from unittest.mock import call import attr import psycopg2 import pytest -from swh.model.model import MetadataTargetType from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.utils import now @pytest.fixture def monkeypatch_sleep(monkeypatch, swh_storage): """In test context, we don't want to wait, make test faster """ from swh.storage.retry import RetryingProxyStorage for method_name, method in RetryingProxyStorage.__dict__.items(): if "_add" in method_name or "_update" in method_name: monkeypatch.setattr(method.retry, "sleep", lambda x: None) return monkeypatch @pytest.fixture def fake_hash_collision(sample_data): return HashCollision("sha1", "38762cf7f55934b34d179ae6a4c80cadccbb7f0a", []) @pytest.fixture def swh_storage_backend_config(): yield { "cls": "pipeline", "steps": [{"cls": "retry"}, {"cls": "memory"},], } def test_retrying_proxy_storage_content_add(swh_storage, sample_data): """Standard content_add works as before """ sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None s = swh_storage.content_add([sample_content]) assert s == { "content:add": 1, "content:add:bytes": sample_content.length, } content = swh_storage.content_get_data(sample_content.sha1) assert content == sample_content.data def test_retrying_proxy_storage_content_add_with_retry( monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision, ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("content already inserted"), # ok then! {"content:add": 1}, ] sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None s = swh_storage.content_add([sample_content]) assert s == {"content:add": 1} mock_memory.assert_has_calls( [call([sample_content]), call([sample_content]), call([sample_content]),] ) def test_retrying_proxy_swh_storage_content_add_failure( swh_storage, sample_data, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = StorageArgumentException("Refuse to add content always!") sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.content_add([sample_content]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_content_add_metadata(swh_storage, sample_data): """Standard content_add_metadata works as before """ sample_content = sample_data.content content = attr.evolve(sample_content, data=None) pk = content.sha1 content_metadata = swh_storage.content_get([pk]) assert content_metadata == [None] s = swh_storage.content_add_metadata([attr.evolve(content, ctime=now())]) assert s == { "content:add": 1, } content_metadata = swh_storage.content_get([pk]) assert len(content_metadata) == 1 assert content_metadata[0].sha1 == pk def test_retrying_proxy_storage_content_add_metadata_with_retry( monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.content_add_metadata" ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("content_metadata already inserted"), # ok then! {"content:add": 1}, ] sample_content = sample_data.content content = attr.evolve(sample_content, data=None) s = swh_storage.content_add_metadata([content]) assert s == {"content:add": 1} mock_memory.assert_has_calls( [call([content]), call([content]), call([content]),] ) def test_retrying_proxy_swh_storage_content_add_metadata_failure( swh_storage, sample_data, mocker ): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.content_add_metadata" ) mock_memory.side_effect = StorageArgumentException( "Refuse to add content_metadata!" ) sample_content = sample_data.content content = attr.evolve(sample_content, data=None) with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.content_add_metadata([content]) assert mock_memory.call_count == 1 -def test_retrying_proxy_storage_skipped_content_add(swh_storage, sample_data): - """Standard skipped_content_add works as before - - """ - sample_content = sample_data.skipped_content - sample_content_dict = sample_content.to_dict() - - skipped_contents = list(swh_storage.skipped_content_missing([sample_content_dict])) - assert len(skipped_contents) == 1 - - s = swh_storage.skipped_content_add([sample_content]) - assert s == { - "skipped_content:add": 1, - } - - skipped_content = list(swh_storage.skipped_content_missing([sample_content_dict])) - assert len(skipped_content) == 0 - - -def test_retrying_proxy_storage_skipped_content_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.skipped_content_add" - ) - mock_memory.side_effect = [ - # 1st & 2nd try goes ko - fake_hash_collision, - psycopg2.IntegrityError("skipped_content already inserted"), - # ok then! - {"skipped_content:add": 1}, - ] - - sample_content = sample_data.skipped_content - - s = swh_storage.skipped_content_add([sample_content]) - assert s == {"skipped_content:add": 1} - - mock_memory.assert_has_calls( - [call([sample_content]), call([sample_content]), call([sample_content]),] - ) - - -def test_retrying_proxy_swh_storage_skipped_content_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.skipped_content_add" - ) - mock_memory.side_effect = StorageArgumentException( - "Refuse to add content_metadata!" - ) - - sample_content = sample_data.skipped_content - sample_content_dict = sample_content.to_dict() - - skipped_contents = list(swh_storage.skipped_content_missing([sample_content_dict])) - assert len(skipped_contents) == 1 - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.skipped_content_add([sample_content]) - - skipped_contents = list(swh_storage.skipped_content_missing([sample_content_dict])) - assert len(skipped_contents) == 1 - - assert mock_memory.call_count == 1 - - -def test_retrying_proxy_swh_storage_origin_visit_add(swh_storage, sample_data): - """Standard origin_visit_add works as before - - """ - origin = sample_data.origin - visit = sample_data.origin_visit - assert visit.origin == origin.url - - swh_storage.origin_add([origin]) - - origins = swh_storage.origin_visit_get(origin.url).results - assert not origins - - origin_visit = swh_storage.origin_visit_add([visit])[0] - assert origin_visit.origin == origin.url - assert isinstance(origin_visit.visit, int) - - actual_visit = swh_storage.origin_visit_get(origin.url).results[0] - assert actual_visit == visit - - -def test_retrying_proxy_swh_storage_origin_visit_add_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - origin = sample_data.origin - visit = sample_data.origin_visit - assert visit.origin == origin.url - - swh_storage.origin_add([origin]) - - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.origin_visit_add") - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("origin already inserted"), - # ok then! - [visit], - ] - - origins = swh_storage.origin_visit_get(origin.url).results - assert not origins - - r = swh_storage.origin_visit_add([visit]) - assert r == [visit] - - mock_memory.assert_has_calls( - [call([visit]), call([visit]), call([visit]),] - ) - - -def test_retrying_proxy_swh_storage_origin_visit_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.origin_visit_add") - mock_memory.side_effect = StorageArgumentException("Refuse to add origin always!") - - origin = sample_data.origin - visit = sample_data.origin_visit - assert visit.origin == origin.url - - origins = swh_storage.origin_visit_get(origin.url).results - assert not origins - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.origin_visit_add([visit]) - - mock_memory.assert_has_calls( - [call([visit]),] - ) - - -def test_retrying_proxy_storage_metadata_fetcher_add(swh_storage, sample_data): - """Standard metadata_fetcher_add works as before - - """ - fetcher = sample_data.metadata_fetcher - - metadata_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) - assert not metadata_fetcher - - swh_storage.metadata_fetcher_add([fetcher]) - - actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) - assert actual_fetcher == fetcher - - -def test_retrying_proxy_storage_metadata_fetcher_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision, -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - fetcher = sample_data.metadata_fetcher - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.metadata_fetcher_add" - ) - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("metadata_fetcher already inserted"), - # ok then! - [fetcher], - ] - - actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) - assert not actual_fetcher - - swh_storage.metadata_fetcher_add([fetcher]) - - mock_memory.assert_has_calls( - [call([fetcher]), call([fetcher]), call([fetcher]),] - ) - - -def test_retrying_proxy_swh_storage_metadata_fetcher_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.metadata_fetcher_add" - ) - mock_memory.side_effect = StorageArgumentException( - "Refuse to add metadata_fetcher always!" - ) - - fetcher = sample_data.metadata_fetcher - - actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) - assert not actual_fetcher - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.metadata_fetcher_add([fetcher]) - - assert mock_memory.call_count == 1 - - -def test_retrying_proxy_storage_metadata_authority_add(swh_storage, sample_data): - """Standard metadata_authority_add works as before - - """ - authority = sample_data.metadata_authority - - assert not swh_storage.metadata_authority_get(authority.type, authority.url) - - swh_storage.metadata_authority_add([authority]) - - actual_authority = swh_storage.metadata_authority_get(authority.type, authority.url) - assert actual_authority == authority - - -def test_retrying_proxy_storage_metadata_authority_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision, -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - authority = sample_data.metadata_authority - - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.metadata_authority_add" - ) - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("foo bar"), - # ok then! - None, - ] - - assert not swh_storage.metadata_authority_get(authority.type, authority.url) - - swh_storage.metadata_authority_add([authority]) - - mock_memory.assert_has_calls( - [call([authority]), call([authority]), call([authority])] - ) - - -def test_retrying_proxy_swh_storage_metadata_authority_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.metadata_authority_add" - ) - mock_memory.side_effect = StorageArgumentException( - "Refuse to add authority_id always!" - ) - - authority = sample_data.metadata_authority - - swh_storage.metadata_authority_get(authority.type, authority.url) - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.metadata_authority_add([authority]) - - assert mock_memory.call_count == 1 - - -def test_retrying_proxy_storage_raw_extrinsic_metadata_add(swh_storage, sample_data): - """Standard raw_extrinsic_metadata_add works as before - - """ - origin = sample_data.origin - ori_meta = sample_data.origin_metadata1 - assert origin.url == ori_meta.target - swh_storage.origin_add([origin]) - swh_storage.metadata_authority_add([sample_data.metadata_authority]) - swh_storage.metadata_fetcher_add([sample_data.metadata_fetcher]) - - origin_metadata = swh_storage.raw_extrinsic_metadata_get( - MetadataTargetType.ORIGIN, ori_meta.target, ori_meta.authority - ) - assert origin_metadata.next_page_token is None - assert not origin_metadata.results - - swh_storage.raw_extrinsic_metadata_add([ori_meta]) - - origin_metadata = swh_storage.raw_extrinsic_metadata_get( - MetadataTargetType.ORIGIN, ori_meta.target, ori_meta.authority - ) - assert origin_metadata - - -def test_retrying_proxy_storage_raw_extrinsic_metadata_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision, -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - origin = sample_data.origin - ori_meta = sample_data.origin_metadata1 - assert origin.url == ori_meta.target - swh_storage.origin_add([origin]) - swh_storage.metadata_authority_add([sample_data.metadata_authority]) - swh_storage.metadata_fetcher_add([sample_data.metadata_fetcher]) - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.raw_extrinsic_metadata_add" - ) - - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("foo bar"), - # ok then! - None, - ] - - # No exception raised as insertion finally came through - swh_storage.raw_extrinsic_metadata_add([ori_meta]) - - mock_memory.assert_has_calls( - [ # 3 calls, as long as error raised - call([ori_meta]), - call([ori_meta]), - call([ori_meta]), - ] - ) - - -def test_retrying_proxy_swh_storage_raw_extrinsic_metadata_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch( - "swh.storage.in_memory.InMemoryStorage.raw_extrinsic_metadata_add" - ) - mock_memory.side_effect = StorageArgumentException("Refuse to add always!") - - origin = sample_data.origin - ori_meta = sample_data.origin_metadata1 - assert origin.url == ori_meta.target - swh_storage.origin_add([origin]) - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.raw_extrinsic_metadata_add([ori_meta]) - - assert mock_memory.call_count == 1 - - -def test_retrying_proxy_storage_directory_add(swh_storage, sample_data): - """Standard directory_add works as before - - """ - sample_dir = sample_data.directory - - s = swh_storage.directory_add([sample_dir]) - assert s == { - "directory:add": 1, - } - - directory_id = swh_storage.directory_get_random() # only 1 - assert directory_id == sample_dir.id - - -def test_retrying_proxy_storage_directory_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.directory_add") - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("directory already inserted"), - # ok then! - {"directory:add": 1}, - ] - - sample_dir = sample_data.directories[1] - - s = swh_storage.directory_add([sample_dir]) - assert s == { - "directory:add": 1, - } - - mock_memory.assert_has_calls( - [call([sample_dir]), call([sample_dir]), call([sample_dir]),] - ) - - -def test_retrying_proxy_swh_storage_directory_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.directory_add") - mock_memory.side_effect = StorageArgumentException( - "Refuse to add directory always!" - ) - - sample_dir = sample_data.directory - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.directory_add([sample_dir]) - - assert mock_memory.call_count == 1 - - -def test_retrying_proxy_storage_revision_add(swh_storage, sample_data): - """Standard revision_add works as before - - """ - sample_rev = sample_data.revision - - revision = swh_storage.revision_get([sample_rev.id])[0] - assert revision is None - - s = swh_storage.revision_add([sample_rev]) - assert s == { - "revision:add": 1, - } - - revision = swh_storage.revision_get([sample_rev.id])[0] - assert revision == sample_rev - - -def test_retrying_proxy_storage_revision_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.revision_add") - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("revision already inserted"), - # ok then! - {"revision:add": 1}, - ] - - sample_rev = sample_data.revision - - revision = swh_storage.revision_get([sample_rev.id])[0] - assert revision is None - - s = swh_storage.revision_add([sample_rev]) - assert s == { - "revision:add": 1, - } - - mock_memory.assert_has_calls( - [call([sample_rev]), call([sample_rev]), call([sample_rev]),] - ) - - -def test_retrying_proxy_swh_storage_revision_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.revision_add") - mock_memory.side_effect = StorageArgumentException("Refuse to add revision always!") - - sample_rev = sample_data.revision - - revision = swh_storage.revision_get([sample_rev.id])[0] - assert revision is None - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.revision_add([sample_rev]) - - assert mock_memory.call_count == 1 - - -def test_retrying_proxy_storage_release_add(swh_storage, sample_data): - """Standard release_add works as before - - """ - sample_rel = sample_data.release - - release = swh_storage.release_get([sample_rel.id])[0] - assert release is None - - s = swh_storage.release_add([sample_rel]) - assert s == { - "release:add": 1, - } - - release = swh_storage.release_get([sample_rel.id])[0] - assert release == sample_rel - - -def test_retrying_proxy_storage_release_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.release_add") - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("release already inserted"), - # ok then! - {"release:add": 1}, - ] - - sample_rel = sample_data.release - - release = swh_storage.release_get([sample_rel.id])[0] - assert release is None - - s = swh_storage.release_add([sample_rel]) - assert s == { - "release:add": 1, - } - - mock_memory.assert_has_calls( - [call([sample_rel]), call([sample_rel]), call([sample_rel]),] - ) - - -def test_retrying_proxy_swh_storage_release_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.release_add") - mock_memory.side_effect = StorageArgumentException("Refuse to add release always!") - - sample_rel = sample_data.release - - release = swh_storage.release_get([sample_rel.id])[0] - assert release is None - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.release_add([sample_rel]) - - assert mock_memory.call_count == 1 - - -def test_retrying_proxy_storage_snapshot_add(swh_storage, sample_data): - """Standard snapshot_add works as before - - """ - sample_snap = sample_data.snapshot - - snapshot = swh_storage.snapshot_get(sample_snap.id) - assert not snapshot - - s = swh_storage.snapshot_add([sample_snap]) - assert s == { - "snapshot:add": 1, - } - - snapshot = swh_storage.snapshot_get(sample_snap.id) - assert snapshot["id"] == sample_snap.id - - -def test_retrying_proxy_storage_snapshot_add_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision -): - """Multiple retries for hash collision and psycopg2 error but finally ok - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.snapshot_add") - mock_memory.side_effect = [ - # first try goes ko - fake_hash_collision, - # second try goes ko - psycopg2.IntegrityError("snapshot already inserted"), - # ok then! - {"snapshot:add": 1}, - ] - - sample_snap = sample_data.snapshot - - snapshot = swh_storage.snapshot_get(sample_snap.id) - assert not snapshot - - s = swh_storage.snapshot_add([sample_snap]) - assert s == { - "snapshot:add": 1, - } - - mock_memory.assert_has_calls( - [call([sample_snap]), call([sample_snap]), call([sample_snap]),] - ) - - -def test_retrying_proxy_swh_storage_snapshot_add_failure( - swh_storage, sample_data, mocker -): - """Unfiltered errors are raising without retry - - """ - mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.snapshot_add") - mock_memory.side_effect = StorageArgumentException("Refuse to add snapshot always!") - - sample_snap = sample_data.snapshot - - snapshot = swh_storage.snapshot_get(sample_snap.id) - assert not snapshot - - with pytest.raises(StorageArgumentException, match="Refuse to add"): - swh_storage.snapshot_add([sample_snap]) - - assert mock_memory.call_count == 1 - - def test_retrying_proxy_swh_storage_keyboardinterrupt(swh_storage, sample_data, mocker): """Unfiltered errors are raising without retry """ mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = KeyboardInterrupt() sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None with pytest.raises(KeyboardInterrupt): swh_storage.content_add([sample_content]) assert mock_memory.call_count == 1 diff --git a/swh/storage/writer.py b/swh/storage/writer.py index fe2a49db..1c89b965 100644 --- a/swh/storage/writer.py +++ b/swh/storage/writer.py @@ -1,102 +1,117 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from typing import Any, Dict, Iterable from attr import evolve from swh.model.model import ( Content, Directory, MetadataAuthority, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, SkippedContent, Snapshot, ) try: from swh.journal.writer import get_journal_writer except ImportError: get_journal_writer = None # type: ignore # mypy limitation, see https://github.com/python/mypy/issues/1153 +def model_object_dict_sanitizer( + object_type: str, object_dict: Dict[str, Any] +) -> Dict[str, str]: + object_dict = object_dict.copy() + if object_type == "content": + object_dict.pop("data", None) + return object_dict + + class JournalWriter: """Journal writer storage collaborator. It's in charge of adding objects to the journal. """ def __init__(self, journal_writer): if journal_writer: if get_journal_writer is None: raise EnvironmentError( "You need the swh.journal package to use the " "journal_writer feature" ) - self.journal = get_journal_writer(**journal_writer) + self.journal = get_journal_writer( + value_sanitizer=model_object_dict_sanitizer, **journal_writer + ) else: self.journal = None - def write_additions(self, obj_type, values) -> None: + def write_addition(self, object_type, value) -> None: + if self.journal: + self.journal.write_addition(object_type, value) + + def write_additions(self, object_type, values) -> None: if self.journal: - self.journal.write_additions(obj_type, values) + self.journal.write_additions(object_type, values) def content_add(self, contents: Iterable[Content]) -> None: """Add contents to the journal. Drop the data field if provided. """ contents = [evolve(item, data=None) for item in contents] self.write_additions("content", contents) def content_update(self, contents: Iterable[Dict[str, Any]]) -> None: if self.journal: raise NotImplementedError("content_update is not supported by the journal.") def content_add_metadata(self, contents: Iterable[Content]) -> None: self.content_add(contents) def skipped_content_add(self, contents: Iterable[SkippedContent]) -> None: self.write_additions("skipped_content", contents) def directory_add(self, directories: Iterable[Directory]) -> None: self.write_additions("directory", directories) def revision_add(self, revisions: Iterable[Revision]) -> None: self.write_additions("revision", revisions) def release_add(self, releases: Iterable[Release]) -> None: self.write_additions("release", releases) def snapshot_add(self, snapshots: Iterable[Snapshot]) -> None: self.write_additions("snapshot", snapshots) def origin_visit_add(self, visits: Iterable[OriginVisit]) -> None: self.write_additions("origin_visit", visits) def origin_visit_status_add( self, visit_statuses: Iterable[OriginVisitStatus] ) -> None: self.write_additions("origin_visit_status", visit_statuses) def origin_add(self, origins: Iterable[Origin]) -> None: self.write_additions("origin", origins) def raw_extrinsic_metadata_add( self, metadata: Iterable[RawExtrinsicMetadata] ) -> None: self.write_additions("raw_extrinsic_metadata", metadata) def metadata_fetcher_add(self, fetchers: Iterable[MetadataFetcher]) -> None: self.write_additions("metadata_fetcher", fetchers) def metadata_authority_add(self, authorities: Iterable[MetadataAuthority]) -> None: self.write_additions("metadata_authority", authorities)