diff --git a/PKG-INFO b/PKG-INFO index 0910bdaa..c1816fd8 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,216 +1,216 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.0.193 +Version: 0.1.0 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 `/usr/sbin/cassandra` to exist. 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 args: db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing args: 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 args: url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local args: db: service=swh-dev objstorage: cls: pathslicing args: 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 240f265a..c75dc12c 100644 --- a/requirements-swh-journal.txt +++ b/requirements-swh-journal.txt @@ -1 +1 @@ -swh.journal >= 0.1.0 +swh.journal >= 0.2 diff --git a/requirements-swh.txt b/requirements-swh.txt index 9bc0a0f1..665c1326 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,3 +1,3 @@ swh.core[db,http] >= 0.0.94 -swh.model >= 0.0.66 +swh.model >= 0.3 swh.objstorage >= 0.0.40 diff --git a/sql/upgrades/151.sql b/sql/upgrades/151.sql index 3399d014..4af0220c 100644 --- a/sql/upgrades/151.sql +++ b/sql/upgrades/151.sql @@ -1,15 +1,13 @@ -- SWH DB schema upgrade -- from_version: 150 -- to_version: 151 -- description: Drop unused functions -- latest schema version insert into dbversion(version, release, description) values(151, now(), 'Work In Progress'); -drop function swh_skipped_content_missing; drop function swh_content_find; drop function swh_directory_missing; -drop function swh_directory_entry_add; drop function swh_revision_walk; drop function swh_revision_list_children; diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index 0910bdaa..c1816fd8 100644 --- a/swh.storage.egg-info/PKG-INFO +++ b/swh.storage.egg-info/PKG-INFO @@ -1,216 +1,216 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 0.0.193 +Version: 0.1.0 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 `/usr/sbin/cassandra` to exist. 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 args: db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing args: 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 args: url: http://localhost:5002/ ``` You could directly define a local storage with the following snippet: ``` storage: cls: local args: db: service=swh-dev objstorage: cls: pathslicing args: 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/SOURCES.txt b/swh.storage.egg-info/SOURCES.txt index c9e02d96..297bb051 100644 --- a/swh.storage.egg-info/SOURCES.txt +++ b/swh.storage.egg-info/SOURCES.txt @@ -1,260 +1,258 @@ MANIFEST.in Makefile Makefile.local README.md pyproject.toml pytest.ini setup.cfg setup.py tox.ini version.txt ./requirements-swh-journal.txt ./requirements-swh.txt ./requirements-test.txt ./requirements.txt bin/swh-storage-add-dir sql/.gitignore sql/Makefile sql/TODO sql/clusters.dot sql/bin/db-upgrade sql/bin/dot_add_content sql/doc/json/.gitignore sql/doc/json/Makefile sql/doc/json/entity.lister_metadata.schema.json sql/doc/json/entity.metadata.schema.json sql/doc/json/entity_history.lister_metadata.schema.json sql/doc/json/entity_history.metadata.schema.json sql/doc/json/fetch_history.result.schema.json sql/doc/json/list_history.result.schema.json sql/doc/json/listable_entity.list_params.schema.json sql/doc/json/origin_visit.metadata.json sql/doc/json/tool.tool_configuration.schema.json sql/json/.gitignore sql/json/Makefile sql/json/entity.lister_metadata.schema.json sql/json/entity.metadata.schema.json sql/json/entity_history.lister_metadata.schema.json sql/json/entity_history.metadata.schema.json sql/json/fetch_history.result.schema.json sql/json/list_history.result.schema.json sql/json/listable_entity.list_params.schema.json sql/json/origin_visit.metadata.json sql/json/tool.tool_configuration.schema.json sql/upgrades/015.sql sql/upgrades/016.sql sql/upgrades/017.sql sql/upgrades/018.sql sql/upgrades/019.sql sql/upgrades/020.sql sql/upgrades/021.sql sql/upgrades/022.sql sql/upgrades/023.sql sql/upgrades/024.sql sql/upgrades/025.sql sql/upgrades/026.sql sql/upgrades/027.sql sql/upgrades/028.sql sql/upgrades/029.sql sql/upgrades/030.sql sql/upgrades/032.sql sql/upgrades/033.sql sql/upgrades/034.sql sql/upgrades/035.sql sql/upgrades/036.sql sql/upgrades/037.sql sql/upgrades/038.sql sql/upgrades/039.sql sql/upgrades/040.sql sql/upgrades/041.sql sql/upgrades/042.sql sql/upgrades/043.sql sql/upgrades/044.sql sql/upgrades/045.sql sql/upgrades/046.sql sql/upgrades/047.sql sql/upgrades/048.sql sql/upgrades/049.sql sql/upgrades/050.sql sql/upgrades/051.sql sql/upgrades/052.sql sql/upgrades/053.sql sql/upgrades/054.sql sql/upgrades/055.sql sql/upgrades/056.sql sql/upgrades/057.sql sql/upgrades/058.sql sql/upgrades/059.sql sql/upgrades/060.sql sql/upgrades/061.sql sql/upgrades/062.sql sql/upgrades/063.sql sql/upgrades/064.sql sql/upgrades/065.sql sql/upgrades/066.sql sql/upgrades/067.sql sql/upgrades/068.sql sql/upgrades/069.sql sql/upgrades/070.sql sql/upgrades/071.sql sql/upgrades/072.sql sql/upgrades/073.sql sql/upgrades/074.sql sql/upgrades/075.sql sql/upgrades/076.sql sql/upgrades/077.sql sql/upgrades/078.sql sql/upgrades/079.sql sql/upgrades/080.sql sql/upgrades/081.sql sql/upgrades/082.sql sql/upgrades/083.sql sql/upgrades/084.sql sql/upgrades/085.sql sql/upgrades/086.sql sql/upgrades/087.sql sql/upgrades/088.sql sql/upgrades/089.sql sql/upgrades/090.sql sql/upgrades/091.sql sql/upgrades/092.sql sql/upgrades/093.sql sql/upgrades/094.sql sql/upgrades/095.sql sql/upgrades/096.sql sql/upgrades/097.sql sql/upgrades/098.sql sql/upgrades/099.sql sql/upgrades/100.sql sql/upgrades/101.sql sql/upgrades/102.sql sql/upgrades/103.sql sql/upgrades/104.sql sql/upgrades/105.sql sql/upgrades/106.sql sql/upgrades/107.sql sql/upgrades/108.sql sql/upgrades/109.sql sql/upgrades/110.sql sql/upgrades/111.sql sql/upgrades/112.sql sql/upgrades/113.sql sql/upgrades/114.sql sql/upgrades/115.sql sql/upgrades/116.sql sql/upgrades/117.sql sql/upgrades/118.sql sql/upgrades/119.sql sql/upgrades/120.sql sql/upgrades/121.sql sql/upgrades/122.sql sql/upgrades/123.sql sql/upgrades/124.sql sql/upgrades/125.sql sql/upgrades/126.sql sql/upgrades/127.sql sql/upgrades/128.sql sql/upgrades/129.sql sql/upgrades/130.sql sql/upgrades/131.sql sql/upgrades/132.sql sql/upgrades/133.sql sql/upgrades/134.sql sql/upgrades/135.sql sql/upgrades/136.sql sql/upgrades/137.sql sql/upgrades/138.sql sql/upgrades/139.sql sql/upgrades/140.sql sql/upgrades/141.sql sql/upgrades/142.sql sql/upgrades/143.sql sql/upgrades/144.sql sql/upgrades/145.sql sql/upgrades/146.sql sql/upgrades/147.sql sql/upgrades/148.sql sql/upgrades/149.sql sql/upgrades/150.sql sql/upgrades/151.sql sql/upgrades/152.sql swh/__init__.py swh.storage.egg-info/PKG-INFO swh.storage.egg-info/SOURCES.txt swh.storage.egg-info/dependency_links.txt swh.storage.egg-info/entry_points.txt swh.storage.egg-info/requires.txt swh.storage.egg-info/top_level.txt swh/storage/__init__.py swh/storage/backfill.py swh/storage/buffer.py swh/storage/cli.py swh/storage/common.py swh/storage/converters.py swh/storage/db.py swh/storage/exc.py swh/storage/filter.py swh/storage/fixer.py swh/storage/in_memory.py swh/storage/interface.py swh/storage/metrics.py swh/storage/objstorage.py swh/storage/py.typed swh/storage/replay.py swh/storage/retry.py swh/storage/storage.py swh/storage/utils.py swh/storage/validate.py swh/storage/writer.py swh/storage/algos/__init__.py swh/storage/algos/diff.py swh/storage/algos/dir_iterators.py swh/storage/algos/origin.py swh/storage/algos/revisions_walker.py swh/storage/algos/snapshot.py swh/storage/api/__init__.py swh/storage/api/client.py swh/storage/api/serializers.py swh/storage/api/server.py swh/storage/cassandra/__init__.py swh/storage/cassandra/common.py swh/storage/cassandra/converters.py swh/storage/cassandra/cql.py swh/storage/cassandra/schema.py swh/storage/cassandra/storage.py swh/storage/sql/10-swh-init.sql swh/storage/sql/20-swh-enums.sql swh/storage/sql/30-swh-schema.sql swh/storage/sql/40-swh-func.sql swh/storage/sql/60-swh-indexes.sql swh/storage/tests/__init__.py swh/storage/tests/conftest.py swh/storage/tests/generate_data_test.py swh/storage/tests/storage_data.py swh/storage/tests/test_api_client.py -swh/storage/tests/test_api_client_dicts.py swh/storage/tests/test_backfill.py swh/storage/tests/test_buffer.py swh/storage/tests/test_cassandra.py swh/storage/tests/test_cassandra_converters.py swh/storage/tests/test_cli.py swh/storage/tests/test_converters.py swh/storage/tests/test_db.py swh/storage/tests/test_exception.py swh/storage/tests/test_filter.py swh/storage/tests/test_in_memory.py swh/storage/tests/test_init.py swh/storage/tests/test_kafka_writer.py swh/storage/tests/test_metrics.py swh/storage/tests/test_replay.py swh/storage/tests/test_retry.py swh/storage/tests/test_server.py swh/storage/tests/test_storage.py swh/storage/tests/test_utils.py -swh/storage/tests/test_write_replay.py swh/storage/tests/algos/__init__.py swh/storage/tests/algos/test_diff.py swh/storage/tests/algos/test_dir_iterator.py swh/storage/tests/algos/test_origin.py swh/storage/tests/algos/test_revisions_walker.py swh/storage/tests/algos/test_snapshot.py \ No newline at end of file diff --git a/swh.storage.egg-info/requires.txt b/swh.storage.egg-info/requires.txt index 3019a805..98e23a3c 100644 --- a/swh.storage.egg-info/requires.txt +++ b/swh.storage.egg-info/requires.txt @@ -1,28 +1,28 @@ click flask psycopg2 python-dateutil vcversioner aiohttp tenacity cassandra-driver!=3.21.0,>=3.19.0 swh.core[db,http]>=0.0.94 -swh.model>=0.0.66 +swh.model>=0.3 swh.objstorage>=0.0.40 [journal] -swh.journal>=0.1.0 +swh.journal>=0.2 [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>=0.1.0 +swh.journal>=0.2 diff --git a/swh/storage/cassandra/converters.py b/swh/storage/cassandra/converters.py index fb931cf2..aa3980a6 100644 --- a/swh/storage/cassandra/converters.py +++ b/swh/storage/cassandra/converters.py @@ -1,73 +1,73 @@ # 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 from copy import deepcopy import json -from typing import Any, Dict, List +from typing import Any, Dict, Tuple import attr from swh.model.model import ( RevisionType, ObjectType, Revision, Release, Sha1Git, ) from swh.model.hashutil import DEFAULT_ALGORITHMS from ..converters import git_headers_to_db, db_to_git_headers from .common import Row def revision_to_db(revision: Revision) -> Dict[str, Any]: # we use a deepcopy of the dict because we do not want to recurse the # Model->dict conversion (to keep Timestamp & al. entities), BUT we do not # want to modify original metadata (embedded in the Model entity), so we # non-recursively convert it as a dict but make a deep copy. db_revision = deepcopy(attr.asdict(revision, recurse=False)) metadata = revision.metadata if metadata and "extra_headers" in metadata: db_revision["metadata"]["extra_headers"] = git_headers_to_db( metadata["extra_headers"] ) db_revision["metadata"] = json.dumps(db_revision["metadata"]) db_revision["type"] = db_revision["type"].value return db_revision -def revision_from_db(db_revision: Row, parents: List[Sha1Git]) -> Revision: +def revision_from_db(db_revision: Row, parents: Tuple[Sha1Git]) -> Revision: revision = db_revision._asdict() # type: ignore metadata = json.loads(revision.pop("metadata", None)) if metadata and "extra_headers" in metadata: extra_headers = db_to_git_headers(metadata["extra_headers"]) metadata["extra_headers"] = extra_headers return Revision( parents=parents, type=RevisionType(revision.pop("type")), metadata=metadata, **revision, ) def release_to_db(release: Release) -> Dict[str, Any]: db_release = attr.asdict(release, recurse=False) db_release["target_type"] = db_release["target_type"].value return db_release def release_from_db(db_release: Row) -> Release: release = db_release._asdict() # type: ignore return Release(target_type=ObjectType(release.pop("target_type")), **release,) def row_to_content_hashes(row: Row) -> Dict[str, bytes]: """Convert cassandra row to a content hashes """ hashes = {} for algo in DEFAULT_ALGORITHMS: hashes[algo] = getattr(row, algo) return hashes diff --git a/swh/storage/cassandra/cql.py b/swh/storage/cassandra/cql.py index 5b0b29a5..c18de97b 100644 --- a/swh/storage/cassandra/cql.py +++ b/swh/storage/cassandra/cql.py @@ -1,904 +1,904 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import functools import json import logging import random from typing import ( Any, Callable, Dict, Iterable, Iterator, List, Optional, Tuple, TypeVar, ) from cassandra import CoordinationFailure from cassandra.cluster import Cluster, EXEC_PROFILE_DEFAULT, ExecutionProfile, ResultSet from cassandra.policies import DCAwareRoundRobinPolicy, TokenAwarePolicy from cassandra.query import PreparedStatement, BoundStatement from tenacity import ( retry, stop_after_attempt, wait_random_exponential, retry_if_exception_type, ) from swh.model.model import ( Sha1Git, TimestampWithTimezone, Timestamp, Person, Content, SkippedContent, OriginVisit, OriginVisitStatus, Origin, ) from .common import Row, TOKEN_BEGIN, TOKEN_END, hash_url from .schema import CREATE_TABLES_QUERIES, HASH_ALGORITHMS logger = logging.getLogger(__name__) _execution_profiles = { EXEC_PROFILE_DEFAULT: ExecutionProfile( load_balancing_policy=TokenAwarePolicy(DCAwareRoundRobinPolicy()) ), } # Configuration for cassandra-driver's access to servers: # * hit the right server directly when sending a query (TokenAwarePolicy), # * if there's more than one, then pick one at random that's in the same # datacenter as the client (DCAwareRoundRobinPolicy) def create_keyspace( hosts: List[str], keyspace: str, port: int = 9042, *, durable_writes=True ): cluster = Cluster(hosts, port=port, execution_profiles=_execution_profiles) session = cluster.connect() extra_params = "" if not durable_writes: extra_params = "AND durable_writes = false" session.execute( """CREATE KEYSPACE IF NOT EXISTS "%s" WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' : 1 } %s; """ % (keyspace, extra_params) ) session.execute('USE "%s"' % keyspace) for query in CREATE_TABLES_QUERIES: session.execute(query) T = TypeVar("T") def _prepared_statement(query: str) -> Callable[[Callable[..., T]], Callable[..., T]]: """Returns a decorator usable on methods of CqlRunner, to inject them with a 'statement' argument, that is a prepared statement corresponding to the query. This only works on methods of CqlRunner, as preparing a statement requires a connection to a Cassandra server.""" def decorator(f): @functools.wraps(f) def newf(self, *args, **kwargs) -> T: if f.__name__ not in self._prepared_statements: statement: PreparedStatement = self._session.prepare(query) self._prepared_statements[f.__name__] = statement return f( self, *args, **kwargs, statement=self._prepared_statements[f.__name__] ) return newf return decorator def _prepared_insert_statement(table_name: str, columns: List[str]): """Shorthand for using `_prepared_statement` for `INSERT INTO` statements.""" return _prepared_statement( "INSERT INTO %s (%s) VALUES (%s)" % (table_name, ", ".join(columns), ", ".join("?" for _ in columns),) ) def _prepared_exists_statement(table_name: str): """Shorthand for using `_prepared_statement` for queries that only check which ids in a list exist in the table.""" return _prepared_statement(f"SELECT id FROM {table_name} WHERE id IN ?") class CqlRunner: """Class managing prepared statements and building queries to be sent to Cassandra.""" def __init__(self, hosts: List[str], keyspace: str, port: int): self._cluster = Cluster( hosts, port=port, execution_profiles=_execution_profiles ) self._session = self._cluster.connect(keyspace) self._cluster.register_user_type( keyspace, "microtimestamp_with_timezone", TimestampWithTimezone ) self._cluster.register_user_type(keyspace, "microtimestamp", Timestamp) self._cluster.register_user_type(keyspace, "person", Person) self._prepared_statements: Dict[str, PreparedStatement] = {} ########################## # Common utility functions ########################## MAX_RETRIES = 3 @retry( wait=wait_random_exponential(multiplier=1, max=10), stop=stop_after_attempt(MAX_RETRIES), retry=retry_if_exception_type(CoordinationFailure), ) def _execute_with_retries(self, statement, args) -> ResultSet: return self._session.execute(statement, args, timeout=1000.0) @_prepared_statement( "UPDATE object_count SET count = count + ? " "WHERE partition_key = 0 AND object_type = ?" ) def _increment_counter( self, object_type: str, nb: int, *, statement: PreparedStatement ) -> None: self._execute_with_retries(statement, [nb, object_type]) def _add_one(self, statement, object_type: str, obj, keys: List[str]) -> None: self._increment_counter(object_type, 1) self._execute_with_retries(statement, [getattr(obj, key) for key in keys]) def _get_random_row(self, statement) -> Optional[Row]: """Takes a prepared statement of the form "SELECT * FROM WHERE token() > ? LIMIT 1" and uses it to return a random row""" token = random.randint(TOKEN_BEGIN, TOKEN_END) rows = self._execute_with_retries(statement, [token]) if not rows: # There are no row with a greater token; wrap around to get # the row with the smallest token rows = self._execute_with_retries(statement, [TOKEN_BEGIN]) if rows: return rows.one() else: return None def _missing(self, statement, ids): res = self._execute_with_retries(statement, [ids]) found_ids = {id_ for (id_,) in res} return [id_ for id_ in ids if id_ not in found_ids] ########################## # 'content' table ########################## _content_pk = ["sha1", "sha1_git", "sha256", "blake2s256"] _content_keys = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "ctime", "status", ] def _content_add_finalize(self, statement: BoundStatement) -> None: """Returned currified by content_add_prepare, to be called when the content row should be added to the primary table.""" self._execute_with_retries(statement, None) self._increment_counter("content", 1) @_prepared_insert_statement("content", _content_keys) def content_add_prepare( self, content, *, statement ) -> Tuple[int, Callable[[], None]]: """Prepares insertion of a Content to the main 'content' table. Returns a token (to be used in secondary tables), and a function to be called to perform the insertion in the main table.""" statement = statement.bind( [getattr(content, key) for key in self._content_keys] ) # Type used for hashing keys (usually, it will be # cassandra.metadata.Murmur3Token) token_class = self._cluster.metadata.token_map.token_class # Token of the row when it will be inserted. This is equivalent to # "SELECT token({', '.join(self._content_pk)}) FROM content WHERE ..." # after the row is inserted; but we need the token to insert in the # index tables *before* inserting to the main 'content' table token = token_class.from_key(statement.routing_key).value assert TOKEN_BEGIN <= token <= TOKEN_END # Function to be called after the indexes contain their respective # row finalizer = functools.partial(self._content_add_finalize, statement) return (token, finalizer) @_prepared_statement( "SELECT * FROM content WHERE " + " AND ".join(map("%s = ?".__mod__, HASH_ALGORITHMS)) ) def content_get_from_pk( self, content_hashes: Dict[str, bytes], *, statement ) -> Optional[Row]: rows = list( self._execute_with_retries( statement, [content_hashes[algo] for algo in HASH_ALGORITHMS] ) ) assert len(rows) <= 1 if rows: return rows[0] else: return None @_prepared_statement( "SELECT * FROM content WHERE token(" + ", ".join(_content_pk) + ") = ?" ) def content_get_from_token(self, token, *, statement) -> Iterable[Row]: return self._execute_with_retries(statement, [token]) @_prepared_statement( "SELECT * FROM content WHERE token(%s) > ? LIMIT 1" % ", ".join(_content_pk) ) def content_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) @_prepared_statement( ( "SELECT token({0}) AS tok, {1} FROM content " "WHERE token({0}) >= ? AND token({0}) <= ? LIMIT ?" ).format(", ".join(_content_pk), ", ".join(_content_keys)) ) def content_get_token_range( self, start: int, end: int, limit: int, *, statement - ) -> Row: + ) -> Iterable[Row]: return self._execute_with_retries(statement, [start, end, limit]) ########################## # 'content_by_*' tables ########################## @_prepared_statement( "SELECT sha1_git FROM content_by_sha1_git " "WHERE sha1_git IN ?" ) def content_missing_by_sha1_git( self, ids: List[bytes], *, statement ) -> List[bytes]: return self._missing(statement, ids) def content_index_add_one(self, algo: str, content: Content, token: int) -> None: """Adds a row mapping content[algo] to the token of the Content in the main 'content' table.""" query = ( f"INSERT INTO content_by_{algo} ({algo}, target_token) " f"VALUES (%s, %s)" ) self._execute_with_retries(query, [content.get_hash(algo), token]) def content_get_tokens_from_single_hash( self, algo: str, hash_: bytes ) -> Iterable[int]: assert algo in HASH_ALGORITHMS query = f"SELECT target_token FROM content_by_{algo} WHERE {algo} = %s" return (tok for (tok,) in self._execute_with_retries(query, [hash_])) ########################## # 'skipped_content' table ########################## _skipped_content_pk = ["sha1", "sha1_git", "sha256", "blake2s256"] _skipped_content_keys = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "ctime", "status", "reason", "origin", ] _magic_null_pk = b"" """ NULLs (or all-empty blobs) are not allowed in primary keys; instead use a special value that can't possibly be a valid hash. """ def _skipped_content_add_finalize(self, statement: BoundStatement) -> None: """Returned currified by skipped_content_add_prepare, to be called when the content row should be added to the primary table.""" self._execute_with_retries(statement, None) self._increment_counter("skipped_content", 1) @_prepared_insert_statement("skipped_content", _skipped_content_keys) def skipped_content_add_prepare( self, content, *, statement ) -> Tuple[int, Callable[[], None]]: """Prepares insertion of a Content to the main 'skipped_content' table. Returns a token (to be used in secondary tables), and a function to be called to perform the insertion in the main table.""" # Replace NULLs (which are not allowed in the partition key) with # an empty byte string content = content.to_dict() for key in self._skipped_content_pk: if content[key] is None: content[key] = self._magic_null_pk statement = statement.bind( [content.get(key) for key in self._skipped_content_keys] ) # Type used for hashing keys (usually, it will be # cassandra.metadata.Murmur3Token) token_class = self._cluster.metadata.token_map.token_class # Token of the row when it will be inserted. This is equivalent to # "SELECT token({', '.join(self._content_pk)}) # FROM skipped_content WHERE ..." # after the row is inserted; but we need the token to insert in the # index tables *before* inserting to the main 'skipped_content' table token = token_class.from_key(statement.routing_key).value assert TOKEN_BEGIN <= token <= TOKEN_END # Function to be called after the indexes contain their respective # row finalizer = functools.partial(self._skipped_content_add_finalize, statement) return (token, finalizer) @_prepared_statement( "SELECT * FROM skipped_content WHERE " + " AND ".join(map("%s = ?".__mod__, HASH_ALGORITHMS)) ) def skipped_content_get_from_pk( self, content_hashes: Dict[str, bytes], *, statement ) -> Optional[Row]: rows = list( self._execute_with_retries( statement, [ content_hashes[algo] or self._magic_null_pk for algo in HASH_ALGORITHMS ], ) ) assert len(rows) <= 1 if rows: # TODO: convert _magic_null_pk back to None? return rows[0] else: return None ########################## # 'skipped_content_by_*' tables ########################## def skipped_content_index_add_one( self, algo: str, content: SkippedContent, token: int ) -> None: """Adds a row mapping content[algo] to the token of the SkippedContent in the main 'skipped_content' table.""" query = ( f"INSERT INTO skipped_content_by_{algo} ({algo}, target_token) " f"VALUES (%s, %s)" ) self._execute_with_retries( query, [content.get_hash(algo) or self._magic_null_pk, token] ) ########################## # 'revision' table ########################## _revision_keys = [ "id", "date", "committer_date", "type", "directory", "message", "author", "committer", "synthetic", "metadata", ] @_prepared_exists_statement("revision") def revision_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) @_prepared_insert_statement("revision", _revision_keys) def revision_add_one(self, revision: Dict[str, Any], *, statement) -> None: self._execute_with_retries( statement, [revision[key] for key in self._revision_keys] ) self._increment_counter("revision", 1) @_prepared_statement("SELECT id FROM revision WHERE id IN ?") def revision_get_ids(self, revision_ids, *, statement) -> ResultSet: return self._execute_with_retries(statement, [revision_ids]) @_prepared_statement("SELECT * FROM revision WHERE id IN ?") def revision_get(self, revision_ids, *, statement) -> ResultSet: return self._execute_with_retries(statement, [revision_ids]) @_prepared_statement("SELECT * FROM revision WHERE token(id) > ? LIMIT 1") def revision_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'revision_parent' table ########################## _revision_parent_keys = ["id", "parent_rank", "parent_id"] @_prepared_insert_statement("revision_parent", _revision_parent_keys) def revision_parent_add_one( self, id_: Sha1Git, parent_rank: int, parent_id: Sha1Git, *, statement ) -> None: self._execute_with_retries(statement, [id_, parent_rank, parent_id]) @_prepared_statement("SELECT parent_id FROM revision_parent WHERE id = ?") def revision_parent_get(self, revision_id: Sha1Git, *, statement) -> ResultSet: return self._execute_with_retries(statement, [revision_id]) ########################## # 'release' table ########################## _release_keys = [ "id", "target", "target_type", "date", "name", "message", "author", "synthetic", ] @_prepared_exists_statement("release") def release_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) @_prepared_insert_statement("release", _release_keys) def release_add_one(self, release: Dict[str, Any], *, statement) -> None: self._execute_with_retries( statement, [release[key] for key in self._release_keys] ) self._increment_counter("release", 1) @_prepared_statement("SELECT * FROM release WHERE id in ?") def release_get(self, release_ids: List[str], *, statement) -> None: return self._execute_with_retries(statement, [release_ids]) @_prepared_statement("SELECT * FROM release WHERE token(id) > ? LIMIT 1") def release_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'directory' table ########################## _directory_keys = ["id"] @_prepared_exists_statement("directory") def directory_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) @_prepared_insert_statement("directory", _directory_keys) def directory_add_one(self, directory_id: Sha1Git, *, statement) -> None: """Called after all calls to directory_entry_add_one, to commit/finalize the directory.""" self._execute_with_retries(statement, [directory_id]) self._increment_counter("directory", 1) @_prepared_statement("SELECT * FROM directory WHERE token(id) > ? LIMIT 1") def directory_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'directory_entry' table ########################## _directory_entry_keys = ["directory_id", "name", "type", "target", "perms"] @_prepared_insert_statement("directory_entry", _directory_entry_keys) def directory_entry_add_one(self, entry: Dict[str, Any], *, statement) -> None: self._execute_with_retries( statement, [entry[key] for key in self._directory_entry_keys] ) @_prepared_statement("SELECT * FROM directory_entry " "WHERE directory_id IN ?") def directory_entry_get(self, directory_ids, *, statement) -> ResultSet: return self._execute_with_retries(statement, [directory_ids]) ########################## # 'snapshot' table ########################## _snapshot_keys = ["id"] @_prepared_exists_statement("snapshot") def snapshot_missing(self, ids: List[bytes], *, statement) -> List[bytes]: return self._missing(statement, ids) @_prepared_insert_statement("snapshot", _snapshot_keys) def snapshot_add_one(self, snapshot_id: Sha1Git, *, statement) -> None: self._execute_with_retries(statement, [snapshot_id]) self._increment_counter("snapshot", 1) @_prepared_statement("SELECT * FROM snapshot " "WHERE id = ?") def snapshot_get(self, snapshot_id: Sha1Git, *, statement) -> ResultSet: return self._execute_with_retries(statement, [snapshot_id]) @_prepared_statement("SELECT * FROM snapshot WHERE token(id) > ? LIMIT 1") def snapshot_get_random(self, *, statement) -> Optional[Row]: return self._get_random_row(statement) ########################## # 'snapshot_branch' table ########################## _snapshot_branch_keys = ["snapshot_id", "name", "target_type", "target"] @_prepared_insert_statement("snapshot_branch", _snapshot_branch_keys) def snapshot_branch_add_one(self, branch: Dict[str, Any], *, statement) -> None: self._execute_with_retries( statement, [branch[key] for key in self._snapshot_branch_keys] ) @_prepared_statement( "SELECT ascii_bins_count(target_type) AS counts " "FROM snapshot_branch " "WHERE snapshot_id = ? " ) def snapshot_count_branches(self, snapshot_id: Sha1Git, *, statement) -> ResultSet: return self._execute_with_retries(statement, [snapshot_id]) @_prepared_statement( "SELECT * FROM snapshot_branch " "WHERE snapshot_id = ? AND name >= ?" "LIMIT ?" ) def snapshot_branch_get( self, snapshot_id: Sha1Git, from_: bytes, limit: int, *, statement ) -> None: return self._execute_with_retries(statement, [snapshot_id, from_, limit]) ########################## # 'origin' table ########################## origin_keys = ["sha1", "url", "type", "next_visit_id"] @_prepared_statement( "INSERT INTO origin (sha1, url, next_visit_id) " "VALUES (?, ?, 1) IF NOT EXISTS" ) def origin_add_one(self, origin: Origin, *, statement) -> None: self._execute_with_retries(statement, [hash_url(origin.url), origin.url]) self._increment_counter("origin", 1) @_prepared_statement("SELECT * FROM origin WHERE sha1 = ?") def origin_get_by_sha1(self, sha1: bytes, *, statement) -> ResultSet: return self._execute_with_retries(statement, [sha1]) def origin_get_by_url(self, url: str) -> ResultSet: return self.origin_get_by_sha1(hash_url(url)) @_prepared_statement( f'SELECT token(sha1) AS tok, {", ".join(origin_keys)} ' f"FROM origin WHERE token(sha1) >= ? LIMIT ?" ) def origin_list(self, start_token: int, limit: int, *, statement) -> ResultSet: return self._execute_with_retries(statement, [start_token, limit]) @_prepared_statement("SELECT * FROM origin") def origin_iter_all(self, *, statement) -> ResultSet: return self._execute_with_retries(statement, []) @_prepared_statement("SELECT next_visit_id FROM origin WHERE sha1 = ?") def _origin_get_next_visit_id(self, origin_sha1: bytes, *, statement) -> int: rows = list(self._execute_with_retries(statement, [origin_sha1])) assert len(rows) == 1 # TODO: error handling return rows[0].next_visit_id @_prepared_statement( "UPDATE origin SET next_visit_id=? " "WHERE sha1 = ? IF next_visit_id=?" ) def origin_generate_unique_visit_id(self, origin_url: str, *, statement) -> int: origin_sha1 = hash_url(origin_url) next_id = self._origin_get_next_visit_id(origin_sha1) while True: res = list( self._execute_with_retries( statement, [next_id + 1, origin_sha1, next_id] ) ) assert len(res) == 1 if res[0].applied: # No data race return next_id else: # Someone else updated it before we did, let's try again next_id = res[0].next_visit_id # TODO: abort after too many attempts return next_id ########################## # 'origin_visit' table ########################## _origin_visit_keys = [ "origin", "visit", "type", "date", "status", "metadata", "snapshot", ] _origin_visit_update_keys = ["type", "date", "status", "metadata", "snapshot"] @_prepared_statement("SELECT * FROM origin_visit " "WHERE origin = ? AND visit > ?") def _origin_visit_get_no_limit( self, origin_url: str, last_visit: int, *, statement ) -> ResultSet: return self._execute_with_retries(statement, [origin_url, last_visit]) @_prepared_statement( "SELECT * FROM origin_visit " "WHERE origin = ? AND visit > ? LIMIT ?" ) def _origin_visit_get_limit( self, origin_url: str, last_visit: int, limit: int, *, statement ) -> ResultSet: return self._execute_with_retries(statement, [origin_url, last_visit, limit]) def origin_visit_get( self, origin_url: str, last_visit: Optional[int], limit: Optional[int] ) -> ResultSet: if last_visit is None: last_visit = -1 if limit is None: return self._origin_visit_get_no_limit(origin_url, last_visit) else: return self._origin_visit_get_limit(origin_url, last_visit, limit) @_prepared_insert_statement("origin_visit", _origin_visit_keys) def origin_visit_add_one(self, visit: OriginVisit, *, statement) -> None: self._add_one(statement, "origin_visit", visit, self._origin_visit_keys) _origin_visit_status_keys = [ "origin", "visit", "date", "status", "snapshot", "metadata", ] @_prepared_insert_statement("origin_visit_status", _origin_visit_status_keys) def origin_visit_status_add_one( self, visit_update: OriginVisitStatus, *, statement ) -> None: assert self._origin_visit_status_keys[-1] == "metadata" keys = self._origin_visit_status_keys metadata = json.dumps(visit_update.metadata) self._execute_with_retries( statement, [getattr(visit_update, key) for key in keys[:-1]] + [metadata] ) def _format_origin_visit_status_row( self, visit_status: ResultSet ) -> Dict[str, Any]: """Format a row visit_status into an origin_visit_status dict """ return { **visit_status._asdict(), "origin": visit_status.origin, "date": visit_status.date.replace(tzinfo=datetime.timezone.utc), "metadata": ( json.loads(visit_status.metadata) if visit_status.metadata else None ), } @_prepared_statement( "SELECT * FROM origin_visit_status " "WHERE origin = ? AND visit = ? " "ORDER BY date DESC " "LIMIT 1" ) def origin_visit_status_get_latest( self, origin: str, visit: int, *, statement ) -> Optional[Dict[str, Any]]: """Given an origin visit id, return its latest origin_visit_status """ rows = list(self._execute_with_retries(statement, [origin, visit])) if rows: return self._format_origin_visit_status_row(rows[0]) else: return None @_prepared_statement( "UPDATE origin_visit SET " + ", ".join("%s = ?" % key for key in _origin_visit_update_keys) + " WHERE origin = ? AND visit = ?" ) def origin_visit_upsert(self, visit: OriginVisit, *, statement) -> None: args: List[Any] = [] for column in self._origin_visit_update_keys: if column == "metadata": args.append(json.dumps(visit.metadata)) else: args.append(getattr(visit, column)) self._execute_with_retries(statement, args + [visit.origin, visit.visit]) # TODO: check if there is already one self._increment_counter("origin_visit", 1) @_prepared_statement("SELECT * FROM origin_visit " "WHERE origin = ? AND visit = ?") def origin_visit_get_one( self, origin_url: str, visit_id: int, *, statement ) -> Optional[Row]: # TODO: error handling rows = list(self._execute_with_retries(statement, [origin_url, visit_id])) if rows: return rows[0] else: return None @_prepared_statement("SELECT * FROM origin_visit " "WHERE origin = ?") def origin_visit_get_all(self, origin_url: str, *, statement) -> ResultSet: return self._execute_with_retries(statement, [origin_url]) @_prepared_statement("SELECT * FROM origin_visit WHERE token(origin) >= ?") def _origin_visit_iter_from(self, min_token: int, *, statement) -> Iterator[Row]: yield from self._execute_with_retries(statement, [min_token]) @_prepared_statement("SELECT * FROM origin_visit WHERE token(origin) < ?") def _origin_visit_iter_to(self, max_token: int, *, statement) -> Iterator[Row]: yield from self._execute_with_retries(statement, [max_token]) def origin_visit_iter(self, start_token: int) -> Iterator[Row]: """Returns all origin visits in order from this token, and wraps around the token space.""" yield from self._origin_visit_iter_from(start_token) yield from self._origin_visit_iter_to(start_token) ########################## # 'metadata_authority' table ########################## _metadata_authority_keys = ["url", "type", "metadata"] @_prepared_insert_statement("metadata_authority", _metadata_authority_keys) def metadata_authority_add(self, url, type, metadata, *, statement): return self._execute_with_retries(statement, [url, type, metadata]) @_prepared_statement("SELECT * from metadata_authority WHERE type = ? AND url = ?") def metadata_authority_get(self, type, url, *, statement) -> Optional[Row]: return next(iter(self._execute_with_retries(statement, [type, url])), None) ########################## # 'metadata_fetcher' table ########################## _metadata_fetcher_keys = ["name", "version", "metadata"] @_prepared_insert_statement("metadata_fetcher", _metadata_fetcher_keys) def metadata_fetcher_add(self, name, version, metadata, *, statement): return self._execute_with_retries(statement, [name, version, metadata]) @_prepared_statement( "SELECT * from metadata_fetcher WHERE name = ? AND version = ?" ) def metadata_fetcher_get(self, name, version, *, statement) -> Optional[Row]: return next(iter(self._execute_with_retries(statement, [name, version])), None) ########################## # 'origin_metadata' table ########################## _origin_metadata_keys = [ "origin", "authority_type", "authority_url", "discovery_date", "fetcher_name", "fetcher_version", "format", "metadata", ] @_prepared_insert_statement("origin_metadata", _origin_metadata_keys) def origin_metadata_add( self, origin, authority_type, authority_url, discovery_date, fetcher_name, fetcher_version, format, metadata, *, statement, ): return self._execute_with_retries( statement, [ origin, authority_type, authority_url, discovery_date, fetcher_name, fetcher_version, format, metadata, ], ) @_prepared_statement( "SELECT * from origin_metadata " "WHERE origin=? AND authority_url=? AND discovery_date>=? " "AND authority_type=?" ) def origin_metadata_get_after( self, origin, authority_type, authority_url, after, *, statement ): return self._execute_with_retries( statement, [origin, authority_url, after, authority_type] ) @_prepared_statement( "SELECT * from origin_metadata " "WHERE origin=? AND authority_url=? AND authority_type=?" ) def origin_metadata_get( self, origin, authority_type, authority_url, *, statement ) -> Iterable[Row]: return self._execute_with_retries( statement, [origin, authority_url, authority_type] ) ########################## # Miscellaneous ########################## @_prepared_statement("SELECT uuid() FROM revision LIMIT 1;") def check_read(self, *, statement): self._execute_with_retries(statement, []) @_prepared_statement( "SELECT object_type, count FROM object_count " "WHERE partition_key=0" ) def stat_counters(self, *, statement) -> ResultSet: return self._execute_with_retries(statement, []) diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py index ca4cb687..67dd2402 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,1170 +1,1170 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import itertools import json import random import re from typing import Any, Dict, List, Iterable, Optional, Union import attr import dateutil from swh.model.model import ( Revision, Release, Directory, DirectoryEntry, Content, SkippedContent, OriginVisit, OriginVisitStatus, Snapshot, Origin, ) from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.storage.objstorage import ObjStorage from swh.storage.writer import JournalWriter from swh.storage.validate import convert_validation_exceptions from swh.storage.utils import now from ..exc import StorageArgumentException, HashCollision from .common import TOKEN_BEGIN, TOKEN_END from .converters import ( revision_to_db, revision_from_db, release_to_db, release_from_db, ) from .cql import CqlRunner from .schema import HASH_ALGORITHMS # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 class CassandraStorage: def __init__(self, hosts, keyspace, objstorage, port=9042, journal_writer=None): self._cql_runner = CqlRunner(hosts, keyspace, port) self.journal_writer = JournalWriter(journal_writer) self.objstorage = ObjStorage(objstorage) def check_config(self, *, check_write): self._cql_runner.check_read() return True def _content_get_from_hash(self, algo, hash_) -> Iterable: """From the name of a hash algorithm and a value of that hash, looks up the "hash -> token" secondary table (content_by_{algo}) to get tokens. Then, looks up the main table (content) to get all contents with that token, and filters out contents whose hash doesn't match.""" found_tokens = self._cql_runner.content_get_tokens_from_single_hash(algo, hash_) for token in found_tokens: # Query the main table ('content'). res = self._cql_runner.content_get_from_token(token) for row in res: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) == hash_: yield row def _content_add(self, contents: List[Content], with_data: bool) -> Dict: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.content_get_from_pk(c.to_dict()) ] self.journal_writer.content_add(contents) if with_data: # First insert to the objstorage, if the endpoint is # `content_add` (as opposed to `content_add_metadata`). # TODO: this should probably be done in concurrently to inserting # in index tables (but still before the main table; so an entry is # only added to the main table after everything else was # successfully inserted. summary = self.objstorage.content_add( c for c in contents if c.status != "absent" ) content_add_bytes = summary["content:add:bytes"] content_add = 0 for content in contents: content_add += 1 # Check for sha1 or sha1_git collisions. This test is not atomic # with the insertion, so it won't detect a collision if both # contents are inserted at the same time, but it's good enough. # # The proper way to do it would probably be a BATCH, but this # would be inefficient because of the number of partitions we # need to affect (len(HASH_ALGORITHMS)+1, which is currently 5) for algo in {"sha1", "sha1_git"}: collisions = [] # Get tokens of 'content' rows with the same value for # sha1/sha1_git rows = self._content_get_from_hash(algo, content.get_hash(algo)) for row in rows: if getattr(row, algo) != content.get_hash(algo): # collision of token(partition key), ignore this # row continue for algo in HASH_ALGORITHMS: if getattr(row, algo) != content.get_hash(algo): # This hash didn't match; discard the row. collisions.append( {algo: getattr(row, algo) for algo in HASH_ALGORITHMS} ) if collisions: collisions.append(content.hashes()) raise HashCollision(algo, content.get_hash(algo), collisions) (token, insertion_finalizer) = self._cql_runner.content_add_prepare(content) # Then add to index tables for algo in HASH_ALGORITHMS: self._cql_runner.content_index_add_one(algo, content, token) # Then to the main table insertion_finalizer() summary = { "content:add": content_add, } if with_data: summary["content:add:bytes"] = content_add_bytes return summary def content_add(self, content: Iterable[Content]) -> Dict: contents = [attr.evolve(c, ctime=now()) for c in content] return self._content_add(list(contents), with_data=True) def content_update(self, content, keys=[]): raise NotImplementedError( "content_update is not supported by the Cassandra backend" ) def content_add_metadata(self, content: Iterable[Content]) -> Dict: return self._content_add(list(content), with_data=False) def content_get(self, content): if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX ) yield from self.objstorage.content_get(content) def content_get_partition( self, partition_id: int, nb_partitions: int, limit: int = 1000, page_token: str = None, ): if limit is None: raise StorageArgumentException("limit should not be None") # Compute start and end of the range of tokens covered by the # requested partition partition_size = (TOKEN_END - TOKEN_BEGIN) // nb_partitions range_start = TOKEN_BEGIN + partition_id * partition_size range_end = TOKEN_BEGIN + (partition_id + 1) * partition_size # offset the range start according to the `page_token`. if page_token is not None: if not (range_start <= int(page_token) <= range_end): raise StorageArgumentException("Invalid page_token.") range_start = int(page_token) # Get the first rows of the range rows = self._cql_runner.content_get_token_range(range_start, range_end, limit) rows = list(rows) if len(rows) == limit: next_page_token: Optional[str] = str(rows[-1].tok + 1) else: next_page_token = None return { "contents": [row._asdict() for row in rows if row.status != "absent"], "next_page_token": next_page_token, } def content_get_metadata(self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: result: Dict[bytes, List[Dict]] = {sha1: [] for sha1 in contents} for sha1 in contents: # Get all (sha1, sha1_git, sha256, blake2s256) whose sha1 # matches the argument, from the index table ('content_by_sha1') for row in self._content_get_from_hash("sha1", sha1): content_metadata = row._asdict() content_metadata.pop("ctime") result[content_metadata["sha1"]].append(content_metadata) return result def content_find(self, content): # Find an algorithm that is common to all the requested contents. # It will be used to do an initial filtering efficiently. filter_algos = list(set(content).intersection(HASH_ALGORITHMS)) if not filter_algos: raise StorageArgumentException( "content keys must contain at least one of: " "%s" % ", ".join(sorted(HASH_ALGORITHMS)) ) common_algo = filter_algos[0] results = [] rows = self._content_get_from_hash(common_algo, content[common_algo]) for row in rows: # Re-check all the hashes, in case of collisions (either of the # hash of the partition key, or the hashes in it) for algo in HASH_ALGORITHMS: if content.get(algo) and getattr(row, algo) != content[algo]: # This hash didn't match; discard the row. break else: # All hashes match, keep this row. results.append( { **row._asdict(), "ctime": row.ctime.replace(tzinfo=datetime.timezone.utc), } ) return results def content_missing(self, content, key_hash="sha1"): for cont in content: res = self.content_find(cont) if not res: yield cont[key_hash] if any(c["status"] == "missing" for c in res): yield cont[key_hash] def content_missing_per_sha1(self, contents): return self.content_missing([{"sha1": c for c in contents}]) def content_missing_per_sha1_git(self, contents): return self.content_missing( [{"sha1_git": c for c in contents}], key_hash="sha1_git" ) def content_get_random(self): return self._cql_runner.content_get_random().sha1_git def _skipped_content_get_from_hash(self, algo, hash_) -> Iterable: """From the name of a hash algorithm and a value of that hash, looks up the "hash -> token" secondary table (skipped_content_by_{algo}) to get tokens. Then, looks up the main table (content) to get all contents with that token, and filters out contents whose hash doesn't match.""" found_tokens = self._cql_runner.skipped_content_get_tokens_from_single_hash( algo, hash_ ) for token in found_tokens: # Query the main table ('content'). res = self._cql_runner.skipped_content_get_from_token(token) for row in res: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) == hash_: yield row def _skipped_content_add(self, contents: Iterable[SkippedContent]) -> Dict: # Filter-out content already in the database. contents = [ c for c in contents if not self._cql_runner.skipped_content_get_from_pk(c.to_dict()) ] self.journal_writer.skipped_content_add(contents) for content in contents: # Compute token of the row in the main table (token, insertion_finalizer) = self._cql_runner.skipped_content_add_prepare( content ) # Then add to index tables for algo in HASH_ALGORITHMS: self._cql_runner.skipped_content_index_add_one(algo, content, token) # Then to the main table insertion_finalizer() return {"skipped_content:add": len(contents)} def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: contents = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(contents) def skipped_content_missing(self, contents): for content in contents: if not self._cql_runner.skipped_content_get_from_pk(content): yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} def directory_add(self, directories: Iterable[Directory]) -> Dict: directories = list(directories) # Filter out directories that are already inserted. missing = self.directory_missing([dir_.id for dir_ in directories]) directories = [dir_ for dir_ in directories if dir_.id in missing] self.journal_writer.directory_add(directories) for directory in directories: # Add directory entries to the 'directory_entry' table for entry in directory.entries: self._cql_runner.directory_entry_add_one( {**entry.to_dict(), "directory_id": directory.id} ) # Add the directory *after* adding all the entries, so someone # calling snapshot_get_branch in the meantime won't end up # with half the entries. self._cql_runner.directory_add_one(directory.id) return {"directory:add": len(missing)} def directory_missing(self, directories): return self._cql_runner.directory_missing(directories) def _join_dentry_to_content(self, dentry): keys = ( "status", "sha1", "sha1_git", "sha256", "length", ) ret = dict.fromkeys(keys) ret.update(dentry.to_dict()) if ret["type"] == "file": content = self.content_find({"sha1_git": ret["target"]}) if content: content = content[0] for key in keys: ret[key] = content[key] return ret def _directory_ls(self, directory_id, recursive, prefix=b""): if self.directory_missing([directory_id]): return rows = list(self._cql_runner.directory_entry_get([directory_id])) for row in rows: # Build and yield the directory entry dict entry = row._asdict() del entry["directory_id"] entry = DirectoryEntry.from_dict(entry) ret = self._join_dentry_to_content(entry) ret["name"] = prefix + ret["name"] ret["dir_id"] = directory_id yield ret if recursive and ret["type"] == "dir": yield from self._directory_ls( ret["target"], True, prefix + ret["name"] + b"/" ) def directory_entry_get_by_path(self, directory, paths): return self._directory_entry_get_by_path(directory, paths, b"") def _directory_entry_get_by_path(self, directory, paths, prefix): if not paths: return contents = list(self.directory_ls(directory)) if not contents: return def _get_entry(entries, name): """Finds the entry with the requested name, prepends the prefix (to get its full path), and returns it. If no entry has that name, returns None.""" for entry in entries: if entry["name"] == name: entry = entry.copy() entry["name"] = prefix + entry["name"] return entry first_item = _get_entry(contents, paths[0]) if len(paths) == 1: return first_item if not first_item or first_item["type"] != "dir": return return self._directory_entry_get_by_path( first_item["target"], paths[1:], prefix + paths[0] + b"/" ) def directory_ls(self, directory, recursive=False): yield from self._directory_ls(directory, recursive) def directory_get_random(self): return self._cql_runner.directory_get_random().id def revision_add(self, revisions: Iterable[Revision]) -> Dict: revisions = list(revisions) # Filter-out revisions already in the database missing = self.revision_missing([rev.id for rev in revisions]) revisions = [rev for rev in revisions if rev.id in missing] self.journal_writer.revision_add(revisions) for revision in revisions: revobject = revision_to_db(revision) if revobject: # Add parents first for (rank, parent) in enumerate(revobject["parents"]): self._cql_runner.revision_parent_add_one( revobject["id"], rank, parent ) # Then write the main revision row. # Writing this after all parents were written ensures that # read endpoints don't return a partial view while writing # the parents self._cql_runner.revision_add_one(revobject) return {"revision:add": len(revisions)} def revision_missing(self, revisions): return self._cql_runner.revision_missing(revisions) def revision_get(self, revisions): rows = self._cql_runner.revision_get(revisions) revs = {} for row in rows: # TODO: use a single query to get all parents? # (it might have lower latency, but requires more code and more # bandwidth, because revision id would be part of each returned # row) parent_rows = self._cql_runner.revision_parent_get(row.id) # parent_rank is the clustering key, so results are already # sorted by rank. - parents = [row.parent_id for row in parent_rows] + parents = tuple(row.parent_id for row in parent_rows) rev = revision_from_db(row, parents=parents) revs[rev.id] = rev.to_dict() for rev_id in revisions: yield revs.get(rev_id) def _get_parent_revs(self, rev_ids, seen, limit, short): if limit and len(seen) >= limit: return rev_ids = [id_ for id_ in rev_ids if id_ not in seen] if not rev_ids: return seen |= set(rev_ids) # We need this query, even if short=True, to return consistent # results (ie. not return only a subset of a revision's parents # if it is being written) if short: rows = self._cql_runner.revision_get_ids(rev_ids) else: rows = self._cql_runner.revision_get(rev_ids) for row in rows: # TODO: use a single query to get all parents? # (it might have less latency, but requires less code and more # bandwidth (because revision id would be part of each returned # row) parent_rows = self._cql_runner.revision_parent_get(row.id) # parent_rank is the clustering key, so results are already # sorted by rank. - parents = [row.parent_id for row in parent_rows] + parents = tuple(row.parent_id for row in parent_rows) if short: yield (row.id, parents) else: rev = revision_from_db(row, parents=parents) yield rev.to_dict() yield from self._get_parent_revs(parents, seen, limit, short) def revision_log(self, revisions, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, False) def revision_shortlog(self, revisions, limit=None): seen = set() yield from self._get_parent_revs(revisions, seen, limit, True) def revision_get_random(self): return self._cql_runner.revision_get_random().id def release_add(self, releases: Iterable[Release]) -> Dict: missing = self.release_missing([rel.id for rel in releases]) releases = [rel for rel in releases if rel.id in missing] self.journal_writer.release_add(releases) for release in releases: if release: self._cql_runner.release_add_one(release_to_db(release)) return {"release:add": len(missing)} def release_missing(self, releases): return self._cql_runner.release_missing(releases) def release_get(self, releases): rows = self._cql_runner.release_get(releases) rels = {} for row in rows: release = release_from_db(row) rels[row.id] = release.to_dict() for rel_id in releases: yield rels.get(rel_id) def release_get_random(self): return self._cql_runner.release_get_random().id def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: missing = self._cql_runner.snapshot_missing([snp.id for snp in snapshots]) snapshots = [snp for snp in snapshots if snp.id in missing] for snapshot in snapshots: self.journal_writer.snapshot_add([snapshot]) # Add branches for (branch_name, branch) in snapshot.branches.items(): if branch is None: target_type = None target = None else: target_type = branch.target_type.value target = branch.target self._cql_runner.snapshot_branch_add_one( { "snapshot_id": snapshot.id, "name": branch_name, "target_type": target_type, "target": target, } ) # Add the snapshot *after* adding all the branches, so someone # calling snapshot_get_branch in the meantime won't end up # with half the branches. self._cql_runner.snapshot_add_one(snapshot.id) return {"snapshot:add": len(snapshots)} def snapshot_missing(self, snapshots): return self._cql_runner.snapshot_missing(snapshots) def snapshot_get(self, snapshot_id): return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): try: visit = self.origin_visit_get_by(origin, visit) except IndexError: return None return self.snapshot_get(visit["snapshot"]) def snapshot_get_latest(self, origin, allowed_statuses=None): visit = self.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=True ) if visit: assert visit["snapshot"] if self._cql_runner.snapshot_missing([visit["snapshot"]]): raise StorageArgumentException("Visit references unknown snapshot") return self.snapshot_get_branches(visit["snapshot"]) def snapshot_count_branches(self, snapshot_id): if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None rows = list(self._cql_runner.snapshot_count_branches(snapshot_id)) assert len(rows) == 1 (nb_none, counts) = rows[0].counts counts = dict(counts) if nb_none: counts[None] = nb_none return counts def snapshot_get_branches( self, snapshot_id, branches_from=b"", branches_count=1000, target_types=None ): if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None branches = [] while len(branches) < branches_count + 1: new_branches = list( self._cql_runner.snapshot_branch_get( snapshot_id, branches_from, branches_count + 1 ) ) if not new_branches: break branches_from = new_branches[-1].name new_branches_filtered = new_branches # Filter by target_type if target_types: new_branches_filtered = [ branch for branch in new_branches_filtered if branch.target is not None and branch.target_type in target_types ] branches.extend(new_branches_filtered) if len(new_branches) < branches_count + 1: break if len(branches) > branches_count: last_branch = branches.pop(-1).name else: last_branch = None branches = { branch.name: {"target": branch.target, "target_type": branch.target_type,} if branch.target else None for branch in branches } return { "id": snapshot_id, "branches": branches, "next_branch": last_branch, } def snapshot_get_random(self): return self._cql_runner.snapshot_get_random().id def object_find_by_sha1_git(self, ids): results = {id_: [] for id_ in ids} missing_ids = set(ids) # Mind the order, revision is the most likely one for a given ID, # so we check revisions first. queries = [ ("revision", self._cql_runner.revision_missing), ("release", self._cql_runner.release_missing), ("content", self._cql_runner.content_missing_by_sha1_git), ("directory", self._cql_runner.directory_missing), ] for (object_type, query_fn) in queries: found_ids = missing_ids - set(query_fn(missing_ids)) for sha1_git in found_ids: results[sha1_git].append( {"sha1_git": sha1_git, "type": object_type,} ) missing_ids.remove(sha1_git) if not missing_ids: # We found everything, skipping the next queries. break return results def origin_get(self, origins): if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False if any("id" in origin for origin in origins): raise StorageArgumentException("Origin ids are not supported.") results = [self.origin_get_one(origin) for origin in origins] if return_single: assert len(results) == 1 return results[0] else: return results def origin_get_one(self, origin: Dict[str, Any]) -> Optional[Dict[str, Any]]: if "id" in origin: raise StorageArgumentException("Origin ids are not supported.") if "url" not in origin: raise StorageArgumentException("Missing origin url") rows = self._cql_runner.origin_get_by_url(origin["url"]) rows = list(rows) if rows: assert len(rows) == 1 result = rows[0]._asdict() return { "url": result["url"], } else: return None def origin_get_by_sha1(self, sha1s): results = [] for sha1 in sha1s: rows = self._cql_runner.origin_get_by_sha1(sha1) if rows: results.append({"url": rows.one().url}) else: results.append(None) return results def origin_list(self, page_token: Optional[str] = None, limit: int = 100) -> dict: # Compute what token to begin the listing from start_token = TOKEN_BEGIN if page_token: start_token = int(page_token) if not (TOKEN_BEGIN <= start_token <= TOKEN_END): raise StorageArgumentException("Invalid page_token.") rows = self._cql_runner.origin_list(start_token, limit) rows = list(rows) if len(rows) == limit: next_page_token: Optional[str] = str(rows[-1].tok + 1) else: next_page_token = None return { "origins": [{"url": row.url} for row in rows], "next_page_token": next_page_token, } def origin_search( self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False ): # TODO: remove this endpoint, swh-search should be used instead. origins = self._cql_runner.origin_iter_all() if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.search(orig.url)] else: origins = [orig for orig in origins if url_pattern in orig.url] if with_visit: origins = [orig for orig in origins if orig.next_visit_id > 1] return [{"url": orig.url,} for orig in origins[offset : offset + limit]] def origin_add(self, origins: Iterable[Origin]) -> List[Dict]: results = [] for origin in origins: self.origin_add_one(origin) results.append(origin.to_dict()) return results def origin_add_one(self, origin: Origin) -> str: known_origin = self.origin_get_one(origin.to_dict()) if known_origin: origin_url = known_origin["url"] else: self.journal_writer.origin_add([origin]) self._cql_runner.origin_add_one(origin) origin_url = origin.url return origin_url def origin_visit_add( self, origin_url: str, date: Union[str, datetime.datetime], type: str ) -> OriginVisit: if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): raise StorageArgumentException("Date must be a datetime or a string") if not self.origin_get_one({"url": origin_url}): raise StorageArgumentException("Unknown origin %s", origin_url) visit_id = self._cql_runner.origin_generate_unique_visit_id(origin_url) visit_state = "ongoing" with convert_validation_exceptions(): visit = OriginVisit.from_dict( { "origin": origin_url, "date": date, "type": type, "status": visit_state, "snapshot": None, "metadata": None, "visit": visit_id, } ) self.journal_writer.origin_visit_add([visit]) self._cql_runner.origin_visit_add_one(visit) with convert_validation_exceptions(): visit_status = OriginVisitStatus( origin=origin_url, visit=visit_id, date=date, status=visit_state, snapshot=None, metadata=None, ) self._origin_visit_status_add(visit_status) return visit def _origin_visit_status_add(self, visit_status: OriginVisitStatus) -> None: """Add an origin visit status""" self._cql_runner.origin_visit_status_add_one(visit_status) def origin_visit_update( self, origin: str, visit_id: int, status: str, metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None, date: Optional[datetime.datetime] = None, ): origin_url = origin # TODO: rename the argument # Get the existing data of the visit visit_ = self.origin_visit_get_by(origin_url, visit_id) if not visit_: raise StorageArgumentException("This origin visit does not exist.") with convert_validation_exceptions(): visit = OriginVisit.from_dict(visit_) updates: Dict[str, Any] = {"status": status} if metadata and metadata != visit.metadata: updates["metadata"] = metadata if snapshot and snapshot != visit.snapshot: updates["snapshot"] = snapshot with convert_validation_exceptions(): visit = attr.evolve(visit, **updates) self.journal_writer.origin_visit_update([visit]) last_visit_update = self._origin_visit_get_updated(visit.origin, visit.visit) assert last_visit_update is not None with convert_validation_exceptions(): visit_status = OriginVisitStatus( origin=origin_url, visit=visit_id, date=date or now(), status=status, snapshot=snapshot or last_visit_update["snapshot"], metadata=metadata or last_visit_update["metadata"], ) self._origin_visit_status_add(visit_status) def _origin_visit_merge( self, visit: Dict[str, Any], visit_status: Dict[str, Any] ) -> Dict[str, Any]: """Merge origin_visit and visit_status together. """ return OriginVisit.from_dict( { # default to the values in visit **visit, # override with the last update **visit_status, # visit['origin'] is the URL (via a join), while # visit_status['origin'] is only an id. "origin": visit["origin"], # but keep the date of the creation of the origin visit "date": visit["date"], } ).to_dict() def _origin_visit_apply_last_status(self, visit: Dict[str, Any]) -> Dict[str, Any]: """Retrieve the latest visit status information for the origin visit. Then merge it with the visit and return it. """ visit_status = self._cql_runner.origin_visit_status_get_latest( visit["origin"], visit["visit"] ) assert visit_status is not None return self._origin_visit_merge(visit, visit_status) def _origin_visit_get_updated(self, origin: str, visit_id: int) -> Dict[str, Any]: """Retrieve origin visit and latest origin visit status and merge them into an origin visit. """ row_visit = self._cql_runner.origin_visit_get_one(origin, visit_id) assert row_visit is not None visit = self._format_origin_visit_row(row_visit) return self._origin_visit_apply_last_status(visit) def origin_visit_upsert(self, visits: Iterable[OriginVisit]) -> None: for visit in visits: if visit.visit is None: raise StorageArgumentException(f"Missing visit id for visit {visit}") self.journal_writer.origin_visit_upsert(visits) for visit in visits: assert visit.visit is not None self._cql_runner.origin_visit_upsert(visit) with convert_validation_exceptions(): visit_status = OriginVisitStatus( origin=visit.origin, visit=visit.visit, date=now(), status=visit.status, snapshot=visit.snapshot, metadata=visit.metadata, ) self._origin_visit_status_add(visit_status) @staticmethod def _format_origin_visit_row(visit): return { **visit._asdict(), "origin": visit.origin, "date": visit.date.replace(tzinfo=datetime.timezone.utc), "metadata": (json.loads(visit.metadata) if visit.metadata else None), } def origin_visit_get( self, origin: str, last_visit: Optional[int] = None, limit: Optional[int] = None ) -> Iterable[Dict[str, Any]]: rows = self._cql_runner.origin_visit_get(origin, last_visit, limit) for row in rows: visit = self._format_origin_visit_row(row) yield self._origin_visit_apply_last_status(visit) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime ) -> Optional[Dict[str, Any]]: # Iterator over all the visits of the origin # This should be ok for now, as there aren't too many visits # per origin. rows = list(self._cql_runner.origin_visit_get_all(origin)) def key(visit): dt = visit.date.replace(tzinfo=datetime.timezone.utc) - visit_date return (abs(dt), -visit.visit) if rows: row = min(rows, key=key) visit = self._format_origin_visit_row(row) return self._origin_visit_apply_last_status(visit) return None def origin_visit_get_by(self, origin: str, visit: int) -> Optional[Dict[str, Any]]: row = self._cql_runner.origin_visit_get_one(origin, visit) if row: visit_ = self._format_origin_visit_row(row) return self._origin_visit_apply_last_status(visit_) return None def origin_visit_get_latest( self, origin: str, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[Dict[str, Any]]: # TODO: Do not fetch all visits rows = self._cql_runner.origin_visit_get_all(origin) latest_visit = None for row in rows: visit = self._format_origin_visit_row(row) updated_visit = self._origin_visit_apply_last_status(visit) if allowed_statuses and updated_visit["status"] not in allowed_statuses: continue if require_snapshot and updated_visit["snapshot"] is None: continue # updated_visit is a candidate if latest_visit is not None: if updated_visit["date"] < latest_visit["date"]: continue if updated_visit["visit"] < latest_visit["visit"]: continue latest_visit = updated_visit return latest_visit def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: back_in_the_day = now() - datetime.timedelta(weeks=12) # 3 months back # Random position to start iteration at start_token = random.randint(TOKEN_BEGIN, TOKEN_END) # Iterator over all visits, ordered by token(origins) then visit_id rows = self._cql_runner.origin_visit_iter(start_token) for row in rows: visit = self._format_origin_visit_row(row) visit_status = self._origin_visit_apply_last_status(visit) if ( visit_status["date"] > back_in_the_day and visit_status["status"] == "full" ): return visit_status else: return None def stat_counters(self): rows = self._cql_runner.stat_counters() keys = ( "content", "directory", "origin", "origin_visit", "release", "revision", "skipped_content", "snapshot", ) stats = {key: 0 for key in keys} stats.update({row.object_type: row.count for row in rows}) return stats def refresh_stat_counters(self): pass def origin_metadata_add( self, origin_url: str, discovery_date: datetime.datetime, authority: Dict[str, Any], fetcher: Dict[str, Any], format: str, metadata: bytes, ) -> None: if not isinstance(origin_url, str): raise StorageArgumentException( "origin_id must be str, not %r" % (origin_url,) ) if not self._cql_runner.metadata_authority_get(**authority): raise StorageArgumentException(f"Unknown authority {authority}") if not self._cql_runner.metadata_fetcher_get(**fetcher): raise StorageArgumentException(f"Unknown fetcher {fetcher}") try: self._cql_runner.origin_metadata_add( origin_url, authority["type"], authority["url"], discovery_date, fetcher["name"], fetcher["version"], format, metadata, ) except TypeError as e: raise StorageArgumentException(*e.args) def origin_metadata_get( self, origin_url: str, authority: Dict[str, str], after: Optional[datetime.datetime] = None, limit: Optional[int] = None, ) -> List[Dict[str, Any]]: if not isinstance(origin_url, str): raise TypeError("origin_url must be str, not %r" % (origin_url,)) if after is None: entries = self._cql_runner.origin_metadata_get( origin_url, authority["type"], authority["url"] ) else: entries = self._cql_runner.origin_metadata_get_after( origin_url, authority["type"], authority["url"], after ) if limit: entries = itertools.islice(entries, 0, limit) results = [] for entry in entries: discovery_date = entry.discovery_date.replace(tzinfo=datetime.timezone.utc) results.append( { "origin_url": entry.origin, "authority": { "type": entry.authority_type, "url": entry.authority_url, }, "fetcher": { "name": entry.fetcher_name, "version": entry.fetcher_version, }, "discovery_date": discovery_date, "format": entry.format, "metadata": entry.metadata, } ) return results def metadata_fetcher_add( self, name: str, version: str, metadata: Dict[str, Any] ) -> None: self._cql_runner.metadata_fetcher_add(name, version, json.dumps(metadata)) def metadata_fetcher_get(self, name: str, version: str) -> Optional[Dict[str, Any]]: fetcher = self._cql_runner.metadata_fetcher_get(name, version) if fetcher: return { "name": fetcher.name, "version": fetcher.version, "metadata": json.loads(fetcher.metadata), } else: return None def metadata_authority_add( self, type: str, url: str, metadata: Dict[str, Any] ) -> None: self._cql_runner.metadata_authority_add(url, type, json.dumps(metadata)) def metadata_authority_get(self, type: str, url: str) -> Optional[Dict[str, Any]]: authority = self._cql_runner.metadata_authority_get(type, url) if authority: return { "type": authority.type, "url": authority.url, "metadata": json.loads(authority.metadata), } else: return None def clear_buffers(self, object_types: Optional[Iterable[str]] = None) -> None: """Do nothing """ return None def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: return {} diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py index 4851fb67..047688de 100644 --- a/swh/storage/in_memory.py +++ b/swh/storage/in_memory.py @@ -1,1200 +1,1201 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import re import bisect import dateutil import collections import copy import datetime import itertools import random from collections import defaultdict from datetime import timedelta from typing import ( Any, Callable, Dict, Generic, Hashable, Iterable, Iterator, List, Optional, Tuple, TypeVar, Union, ) import attr from swh.model.model import ( BaseContent, Content, SkippedContent, Directory, Revision, Release, Snapshot, OriginVisit, OriginVisitStatus, Origin, SHA1_SIZE, ) from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.storage.objstorage import ObjStorage from swh.storage.validate import convert_validation_exceptions from swh.storage.utils import now from .exc import StorageArgumentException, HashCollision from .converters import origin_url_to_sha1 from .utils import get_partition_bounds_bytes from .writer import JournalWriter # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 SortedListItem = TypeVar("SortedListItem") SortedListKey = TypeVar("SortedListKey") class SortedList(collections.UserList, Generic[SortedListKey, SortedListItem]): data: List[Tuple[SortedListKey, SortedListItem]] # https://github.com/python/mypy/issues/708 # key: Callable[[SortedListItem], SortedListKey] def __init__( self, data: List[SortedListItem] = None, key: Optional[Callable[[SortedListItem], SortedListKey]] = None, ): if key is None: def key(item): return item assert key is not None # for mypy super().__init__(sorted((key(x), x) for x in data or [])) self.key: Callable[[SortedListItem], SortedListKey] = key def add(self, item: SortedListItem): k = self.key(item) bisect.insort(self.data, (k, item)) def __iter__(self) -> Iterator[SortedListItem]: for (k, item) in self.data: yield item def iter_from(self, start_key: SortedListKey) -> Iterator[SortedListItem]: """Returns an iterator over all the elements whose key is greater or equal to `start_key`. (This is an efficient equivalent to: `(x for x in L if key(x) >= start_key)`) """ from_index = bisect.bisect_left(self.data, (start_key,)) for (k, item) in itertools.islice(self.data, from_index, None): yield item class InMemoryStorage: def __init__(self, journal_writer=None): self.reset() self.journal_writer = JournalWriter(journal_writer) def reset(self): self._contents = {} self._content_indexes = defaultdict(lambda: defaultdict(set)) self._skipped_contents = {} self._skipped_content_indexes = defaultdict(lambda: defaultdict(set)) self._directories = {} self._revisions = {} self._releases = {} self._snapshots = {} self._origins = {} self._origins_by_id = [] self._origins_by_sha1 = {} self._origin_visits = {} self._origin_visit_statuses: Dict[Tuple[str, int], List[OriginVisitStatus]] = {} self._persons = [] # {origin_url: {authority: [metadata]}} self._origin_metadata: Dict[ str, Dict[Hashable, SortedList[datetime.datetime, Dict[str, Any]]] ] = defaultdict( lambda: defaultdict(lambda: SortedList(key=lambda x: x["discovery_date"])) ) # noqa self._metadata_fetchers: Dict[Hashable, Dict[str, Any]] = {} self._metadata_authorities: Dict[Hashable, Dict[str, Any]] = {} self._objects = defaultdict(list) self._sorted_sha1s = SortedList[bytes, bytes]() self.objstorage = ObjStorage({"cls": "memory", "args": {}}) def check_config(self, *, check_write): return True def _content_add(self, contents: Iterable[Content], with_data: bool) -> Dict: self.journal_writer.content_add(contents) content_add = 0 if with_data: summary = self.objstorage.content_add( c for c in contents if c.status != "absent" ) content_add_bytes = summary["content:add:bytes"] for content in contents: key = self._content_key(content) if key in self._contents: continue for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) if hash_ in self._content_indexes[algorithm] and ( algorithm not in {"blake2s256", "sha256"} ): colliding_content_hashes = [] # Add the already stored contents for content_hashes_set in self._content_indexes[algorithm][hash_]: hashes = dict(content_hashes_set) colliding_content_hashes.append(hashes) # Add the new colliding content colliding_content_hashes.append(content.hashes()) raise HashCollision(algorithm, hash_, colliding_content_hashes) for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(key) self._objects[content.sha1_git].append(("content", content.sha1)) self._contents[key] = content self._sorted_sha1s.add(content.sha1) self._contents[key] = attr.evolve(self._contents[key], data=None) content_add += 1 summary = { "content:add": content_add, } if with_data: summary["content:add:bytes"] = content_add_bytes return summary def content_add(self, content: Iterable[Content]) -> Dict: content = [attr.evolve(c, ctime=now()) for c in content] return self._content_add(content, with_data=True) def content_update(self, content, keys=[]): self.journal_writer.content_update(content) for cont_update in content: cont_update = cont_update.copy() sha1 = cont_update.pop("sha1") for old_key in self._content_indexes["sha1"][sha1]: old_cont = self._contents.pop(old_key) for algorithm in DEFAULT_ALGORITHMS: hash_ = old_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].remove(old_key) new_cont = attr.evolve(old_cont, **cont_update) new_key = self._content_key(new_cont) self._contents[new_key] = new_cont for algorithm in DEFAULT_ALGORITHMS: hash_ = new_cont.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(new_key) def content_add_metadata(self, content: Iterable[Content]) -> Dict: return self._content_add(content, with_data=False) def content_get(self, content): # FIXME: Make this method support slicing the `data`. if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise StorageArgumentException( "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX ) yield from self.objstorage.content_get(content) def content_get_range(self, start, end, limit=1000): if limit is None: raise StorageArgumentException("limit should not be None") sha1s = ( (sha1, content_key) for sha1 in self._sorted_sha1s.iter_from(start) for content_key in self._content_indexes["sha1"][sha1] ) matched = [] next_content = None for sha1, key in sha1s: if sha1 > end: break if len(matched) >= limit: next_content = sha1 break matched.append(self._contents[key].to_dict()) return { "contents": matched, "next": next_content, } def content_get_partition( self, partition_id: int, nb_partitions: int, limit: int = 1000, page_token: str = None, ): if limit is None: raise StorageArgumentException("limit should not be None") (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE ) if page_token: start = hash_to_bytes(page_token) if end is None: end = b"\xff" * SHA1_SIZE result = self.content_get_range(start, end, limit) result2 = { "contents": result["contents"], "next_page_token": None, } if result["next"]: result2["next_page_token"] = hash_to_hex(result["next"]) return result2 def content_get_metadata(self, contents: List[bytes]) -> Dict[bytes, List[Dict]]: result: Dict = {sha1: [] for sha1 in contents} for sha1 in contents: if sha1 in self._content_indexes["sha1"]: objs = self._content_indexes["sha1"][sha1] # only 1 element as content_add_metadata would have raised a # hash collision otherwise for key in objs: d = self._contents[key].to_dict() del d["ctime"] if "data" in d: del d["data"] result[sha1].append(d) return result def content_find(self, content): if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( "content keys must contain at least one of: %s" % ", ".join(sorted(DEFAULT_ALGORITHMS)) ) found = [] for algo in DEFAULT_ALGORITHMS: hash = content.get(algo) if hash and hash in self._content_indexes[algo]: found.append(self._content_indexes[algo][hash]) if not found: return [] keys = list(set.intersection(*found)) return [self._contents[key].to_dict() for key in keys] def content_missing(self, content, key_hash="sha1"): for cont in content: for (algo, hash_) in cont.items(): if algo not in DEFAULT_ALGORITHMS: continue if hash_ not in self._content_indexes.get(algo, []): yield cont[key_hash] break else: for result in self.content_find(cont): if result["status"] == "missing": yield cont[key_hash] def content_missing_per_sha1(self, contents): for content in contents: if content not in self._content_indexes["sha1"]: yield content def content_missing_per_sha1_git(self, contents): for content in contents: if content not in self._content_indexes["sha1_git"]: yield content def content_get_random(self): return random.choice(list(self._content_indexes["sha1_git"])) def _skipped_content_add(self, contents: List[SkippedContent]) -> Dict: self.journal_writer.skipped_content_add(contents) summary = {"skipped_content:add": 0} missing_contents = self.skipped_content_missing([c.hashes() for c in contents]) missing = {self._content_key(c) for c in missing_contents} contents = [c for c in contents if self._content_key(c) in missing] for content in contents: key = self._content_key(content) for algo in DEFAULT_ALGORITHMS: if content.get_hash(algo): self._skipped_content_indexes[algo][content.get_hash(algo)].add(key) self._skipped_contents[key] = content summary["skipped_content:add"] += 1 return summary def skipped_content_add(self, content: Iterable[SkippedContent]) -> Dict: content = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(content) def skipped_content_missing(self, contents): for content in contents: matches = list(self._skipped_contents.values()) for (algorithm, key) in self._content_key(content): if algorithm == "blake2s256": continue # Filter out skipped contents with the same hash matches = [ match for match in matches if match.get_hash(algorithm) == key ] # if none of the contents match if not matches: yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} def directory_add(self, directories: Iterable[Directory]) -> Dict: directories = [dir_ for dir_ in directories if dir_.id not in self._directories] self.journal_writer.directory_add(directories) count = 0 for directory in directories: count += 1 self._directories[directory.id] = directory self._objects[directory.id].append(("directory", directory.id)) return {"directory:add": count} def directory_missing(self, directories): for id in directories: if id not in self._directories: yield id def _join_dentry_to_content(self, dentry): keys = ( "status", "sha1", "sha1_git", "sha256", "length", ) ret = dict.fromkeys(keys) ret.update(dentry) if ret["type"] == "file": # TODO: Make it able to handle more than one content content = self.content_find({"sha1_git": ret["target"]}) if content: content = content[0] for key in keys: ret[key] = content[key] return ret def _directory_ls(self, directory_id, recursive, prefix=b""): if directory_id in self._directories: for entry in self._directories[directory_id].entries: ret = self._join_dentry_to_content(entry.to_dict()) ret["name"] = prefix + ret["name"] ret["dir_id"] = directory_id yield ret if recursive and ret["type"] == "dir": yield from self._directory_ls( ret["target"], True, prefix + ret["name"] + b"/" ) def directory_ls(self, directory, recursive=False): yield from self._directory_ls(directory, recursive) def directory_entry_get_by_path(self, directory, paths): return self._directory_entry_get_by_path(directory, paths, b"") def directory_get_random(self): if not self._directories: return None return random.choice(list(self._directories)) def _directory_entry_get_by_path(self, directory, paths, prefix): if not paths: return contents = list(self.directory_ls(directory)) if not contents: return def _get_entry(entries, name): for entry in entries: if entry["name"] == name: entry = entry.copy() entry["name"] = prefix + entry["name"] return entry first_item = _get_entry(contents, paths[0]) if len(paths) == 1: return first_item if not first_item or first_item["type"] != "dir": return return self._directory_entry_get_by_path( first_item["target"], paths[1:], prefix + paths[0] + b"/" ) def revision_add(self, revisions: Iterable[Revision]) -> Dict: revisions = [rev for rev in revisions if rev.id not in self._revisions] self.journal_writer.revision_add(revisions) count = 0 for revision in revisions: revision = attr.evolve( revision, committer=self._person_add(revision.committer), author=self._person_add(revision.author), ) self._revisions[revision.id] = revision self._objects[revision.id].append(("revision", revision.id)) count += 1 return {"revision:add": count} def revision_missing(self, revisions): for id in revisions: if id not in self._revisions: yield id def revision_get(self, revisions): for id in revisions: if id in self._revisions: yield self._revisions.get(id).to_dict() else: yield None def _get_parent_revs(self, rev_id, seen, limit): if limit and len(seen) >= limit: return if rev_id in seen or rev_id not in self._revisions: return seen.add(rev_id) yield self._revisions[rev_id].to_dict() for parent in self._revisions[rev_id].parents: yield from self._get_parent_revs(parent, seen, limit) def revision_log(self, revisions, limit=None): seen = set() for rev_id in revisions: yield from self._get_parent_revs(rev_id, seen, limit) def revision_shortlog(self, revisions, limit=None): yield from ( (rev["id"], rev["parents"]) for rev in self.revision_log(revisions, limit) ) def revision_get_random(self): return random.choice(list(self._revisions)) def release_add(self, releases: Iterable[Release]) -> Dict: releases = [rel for rel in releases if rel.id not in self._releases] self.journal_writer.release_add(releases) count = 0 for rel in releases: if rel.author: self._person_add(rel.author) self._objects[rel.id].append(("release", rel.id)) self._releases[rel.id] = rel count += 1 return {"release:add": count} def release_missing(self, releases): yield from (rel for rel in releases if rel not in self._releases) def release_get(self, releases): for rel_id in releases: if rel_id in self._releases: yield self._releases[rel_id].to_dict() else: yield None def release_get_random(self): return random.choice(list(self._releases)) def snapshot_add(self, snapshots: Iterable[Snapshot]) -> Dict: count = 0 snapshots = (snap for snap in snapshots if snap.id not in self._snapshots) for snapshot in snapshots: self.journal_writer.snapshot_add([snapshot]) sorted_branch_names = sorted(snapshot.branches) self._snapshots[snapshot.id] = (snapshot, sorted_branch_names) self._objects[snapshot.id].append(("snapshot", snapshot.id)) count += 1 return {"snapshot:add": count} def snapshot_missing(self, snapshots): for id in snapshots: if id not in self._snapshots: yield id def snapshot_get(self, snapshot_id): return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): origin_url = self._get_origin_url(origin) if not origin_url: return if origin_url not in self._origins or visit > len( self._origin_visits[origin_url] ): return None visit = self._origin_visit_get_updated(origin_url, visit) snapshot_id = visit.snapshot if snapshot_id: return self.snapshot_get(snapshot_id) else: return None def snapshot_get_latest(self, origin, allowed_statuses=None): origin_url = self._get_origin_url(origin) if not origin_url: return visit = self.origin_visit_get_latest( origin_url, allowed_statuses=allowed_statuses, require_snapshot=True ) if visit and visit["snapshot"]: snapshot = self.snapshot_get(visit["snapshot"]) if not snapshot: raise StorageArgumentException( "last origin visit references an unknown snapshot" ) return snapshot def snapshot_count_branches(self, snapshot_id): (snapshot, _) = self._snapshots[snapshot_id] return collections.Counter( branch.target_type.value if branch else None for branch in snapshot.branches.values() ) def snapshot_get_branches( self, snapshot_id, branches_from=b"", branches_count=1000, target_types=None ): res = self._snapshots.get(snapshot_id) if res is None: return None (snapshot, sorted_branch_names) = res from_index = bisect.bisect_left(sorted_branch_names, branches_from) if target_types: next_branch = None branches = {} for branch_name in sorted_branch_names[from_index:]: branch = snapshot.branches[branch_name] if branch and branch.target_type.value in target_types: if len(branches) < branches_count: branches[branch_name] = branch else: next_branch = branch_name break else: # As there is no 'target_types', we can do that much faster to_index = from_index + branches_count returned_branch_names = sorted_branch_names[from_index:to_index] branches = { branch_name: snapshot.branches[branch_name] for branch_name in returned_branch_names } if to_index >= len(sorted_branch_names): next_branch = None else: next_branch = sorted_branch_names[to_index] branches = { name: branch.to_dict() if branch else None for (name, branch) in branches.items() } return { "id": snapshot_id, "branches": branches, "next_branch": next_branch, } def snapshot_get_random(self): return random.choice(list(self._snapshots)) def object_find_by_sha1_git(self, ids): ret = {} for id_ in ids: objs = self._objects.get(id_, []) ret[id_] = [{"sha1_git": id_, "type": obj[0],} for obj in objs] return ret def _convert_origin(self, t): if t is None: return None return t.to_dict() def origin_get(self, origins): if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False # Sanity check to be error-compatible with the pgsql backend if any("id" in origin for origin in origins) and not all( "id" in origin for origin in origins ): raise StorageArgumentException( 'Either all origins or none at all should have an "id".' ) if any("url" in origin for origin in origins) and not all( "url" in origin for origin in origins ): raise StorageArgumentException( "Either all origins or none at all should have " 'an "url" key.' ) results = [] for origin in origins: result = None if "url" in origin: if origin["url"] in self._origins: result = self._origins[origin["url"]] else: raise StorageArgumentException("Origin must have an url.") results.append(self._convert_origin(result)) if return_single: assert len(results) == 1 return results[0] else: return results def origin_get_by_sha1(self, sha1s): return [self._convert_origin(self._origins_by_sha1.get(sha1)) for sha1 in sha1s] def origin_get_range(self, origin_from=1, origin_count=100): origin_from = max(origin_from, 1) if origin_from <= len(self._origins_by_id): max_idx = origin_from + origin_count - 1 if max_idx > len(self._origins_by_id): max_idx = len(self._origins_by_id) for idx in range(origin_from - 1, max_idx): origin = self._convert_origin(self._origins[self._origins_by_id[idx]]) yield {"id": idx + 1, **origin} def origin_list(self, page_token: Optional[str] = None, limit: int = 100) -> dict: origin_urls = sorted(self._origins) if page_token: from_ = bisect.bisect_left(origin_urls, page_token) else: from_ = 0 result = { "origins": [ {"url": origin_url} for origin_url in origin_urls[from_ : from_ + limit] ] } if from_ + limit < len(origin_urls): result["next_page_token"] = origin_urls[from_ + limit] return result def origin_search( self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False ): origins = map(self._convert_origin, self._origins.values()) if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.search(orig["url"])] else: origins = [orig for orig in origins if url_pattern in orig["url"]] if with_visit: filtered_origins = [] for orig in origins: visits = ( self._origin_visit_get_updated(ov.origin, ov.visit) for ov in self._origin_visits[orig["url"]] ) for ov in visits: if ov.snapshot and ov.snapshot in self._snapshots: filtered_origins.append(orig) break else: filtered_origins = origins return filtered_origins[offset : offset + limit] def origin_count(self, url_pattern, regexp=False, with_visit=False): return len( self.origin_search( url_pattern, regexp=regexp, with_visit=with_visit, limit=len(self._origins), ) ) def origin_add(self, origins: Iterable[Origin]) -> List[Dict]: origins = copy.deepcopy(list(origins)) for origin in origins: self.origin_add_one(origin) return [origin.to_dict() for origin in origins] def origin_add_one(self, origin: Origin) -> str: if origin.url not in self._origins: self.journal_writer.origin_add([origin]) # generate an origin_id because it is needed by origin_get_range. # TODO: remove this when we remove origin_get_range origin_id = len(self._origins) + 1 self._origins_by_id.append(origin.url) assert len(self._origins_by_id) == origin_id self._origins[origin.url] = origin self._origins_by_sha1[origin_url_to_sha1(origin.url)] = origin self._origin_visits[origin.url] = [] self._objects[origin.url].append(("origin", origin.url)) return origin.url def origin_visit_add( self, origin_url: str, date: Union[str, datetime.datetime], type: str ) -> OriginVisit: if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): raise StorageArgumentException("Date must be a datetime or a string") origin = self.origin_get({"url": origin_url}) if not origin: # Cannot add a visit without an origin raise StorageArgumentException("Unknown origin %s", origin_url) if origin_url in self._origins: origin = self._origins[origin_url] # visit ids are in the range [1, +inf[ visit_id = len(self._origin_visits[origin_url]) + 1 status = "ongoing" with convert_validation_exceptions(): visit = OriginVisit( origin=origin_url, date=date, type=type, # TODO: Remove when we remove those fields from the model status=status, snapshot=None, metadata=None, visit=visit_id, ) self._origin_visits[origin_url].append(visit) assert visit.visit is not None visit_key = (origin_url, visit.visit) with convert_validation_exceptions(): visit_update = OriginVisitStatus( origin=origin_url, visit=visit_id, date=date, status=status, snapshot=None, metadata=None, ) self._origin_visit_statuses[visit_key] = [visit_update] self._objects[visit_key].append(("origin_visit", None)) self.journal_writer.origin_visit_add([visit]) # return last visit return visit def origin_visit_update( self, origin: str, visit_id: int, status: str, metadata: Optional[Dict] = None, snapshot: Optional[bytes] = None, date: Optional[datetime.datetime] = None, ): origin_url = self._get_origin_url(origin) if origin_url is None: raise StorageArgumentException("Unknown origin.") try: visit = self._origin_visits[origin_url][visit_id - 1] except IndexError: raise StorageArgumentException("Unknown visit_id for this origin") from None # Retrieve the previous visit status assert visit.visit is not None visit_key = (origin_url, visit.visit) last_visit_update = max( self._origin_visit_statuses[visit_key], key=lambda v: v.date ) with convert_validation_exceptions(): visit_update = OriginVisitStatus( origin=origin_url, visit=visit_id, date=date or now(), status=status, snapshot=snapshot or last_visit_update.snapshot, metadata=metadata or last_visit_update.metadata, ) self._origin_visit_statuses[visit_key].append(visit_update) self.journal_writer.origin_visit_update( [self._origin_visit_get_updated(origin_url, visit_id)] ) self._origin_visits[origin_url][visit_id - 1] = visit def origin_visit_upsert(self, visits: Iterable[OriginVisit]) -> None: for visit in visits: if visit.visit is None: raise StorageArgumentException(f"Missing visit id for visit {visit}") self.journal_writer.origin_visit_upsert(visits) date = now() for visit in visits: assert visit.visit is not None + assert visit.visit > 0 origin_url = visit.origin origin = self.origin_get({"url": origin_url}) if not origin: # Cannot add a visit without an origin raise StorageArgumentException("Unknown origin %s", origin_url) if origin_url in self._origins: origin = self._origins[origin_url] # visit ids are in the range [1, +inf[ assert visit.visit is not None visit_key = (origin_url, visit.visit) with convert_validation_exceptions(): visit_update = OriginVisitStatus( origin=origin_url, visit=visit.visit, date=date, status=visit.status, snapshot=visit.snapshot, metadata=visit.metadata, ) self._origin_visit_statuses.setdefault(visit_key, []) - while len(self._origin_visits[origin_url]) <= visit.visit: + while len(self._origin_visits[origin_url]) < visit.visit: self._origin_visits[origin_url].append(None) self._origin_visits[origin_url][visit.visit - 1] = visit self._origin_visit_statuses[visit_key].append(visit_update) self._objects[visit_key].append(("origin_visit", None)) def _origin_visit_get_updated(self, origin: str, visit_id: int) -> OriginVisit: """Merge origin visit and latest origin visit status """ assert visit_id >= 1 visit = self._origin_visits[origin][visit_id - 1] assert visit is not None visit_key = (origin, visit_id) visit_update = max(self._origin_visit_statuses[visit_key], key=lambda v: v.date) return OriginVisit.from_dict( { # default to the values in visit **visit.to_dict(), # override with the last update **visit_update.to_dict(), # but keep the date of the creation of the origin visit "date": visit.date, } ) def origin_visit_get( self, origin: str, last_visit: Optional[int] = None, limit: Optional[int] = None ) -> Iterable[Dict[str, Any]]: origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] if last_visit is not None: visits = visits[last_visit:] if limit is not None: visits = visits[:limit] for visit in visits: if not visit: continue visit_id = visit.visit visit_update = self._origin_visit_get_updated(origin_url, visit_id) assert visit_update is not None yield visit_update.to_dict() def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime ) -> Optional[Dict[str, Any]]: origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] visit = min(visits, key=lambda v: (abs(v.date - visit_date), -v.visit)) visit_update = self._origin_visit_get_updated(origin, visit.visit) assert visit_update is not None return visit_update.to_dict() return None def origin_visit_get_by(self, origin: str, visit: int) -> Optional[Dict[str, Any]]: origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits and visit <= len( self._origin_visits[origin_url] ): visit_update = self._origin_visit_get_updated(origin_url, visit) assert visit_update is not None return visit_update.to_dict() return None def origin_visit_get_latest( self, origin: str, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[Dict[str, Any]]: ori = self._origins.get(origin) if not ori: return None visits = self._origin_visits[ori.url] visits = [ self._origin_visit_get_updated(visit.origin, visit.visit) for visit in visits if visit is not None ] if allowed_statuses is not None: visits = [visit for visit in visits if visit.status in allowed_statuses] if require_snapshot: visits = [visit for visit in visits if visit.snapshot] visit = max(visits, key=lambda v: (v.date, v.visit), default=None) if visit is None: return None return visit.to_dict() def _select_random_origin_visit_by_type(self, type: str) -> str: while True: url = random.choice(list(self._origin_visits.keys())) random_origin_visits = self._origin_visits[url] if random_origin_visits[0].type == type: return url def origin_visit_get_random(self, type: str) -> Optional[Dict[str, Any]]: url = self._select_random_origin_visit_by_type(type) random_origin_visits = copy.deepcopy(self._origin_visits[url]) random_origin_visits.reverse() back_in_the_day = now() - timedelta(weeks=12) # 3 months back # This should be enough for tests for visit in random_origin_visits: updated_visit = self._origin_visit_get_updated(url, visit.visit) assert updated_visit is not None if updated_visit.date > back_in_the_day and updated_visit.status == "full": return updated_visit.to_dict() else: return None def stat_counters(self): keys = ( "content", "directory", "origin", "origin_visit", "person", "release", "revision", "skipped_content", "snapshot", ) stats = {key: 0 for key in keys} stats.update( collections.Counter( obj_type for (obj_type, obj_id) in itertools.chain(*self._objects.values()) ) ) return stats def refresh_stat_counters(self): pass def origin_metadata_add( self, origin_url: str, discovery_date: datetime.datetime, authority: Dict[str, Any], fetcher: Dict[str, Any], format: str, metadata: bytes, ) -> None: if not isinstance(origin_url, str): raise StorageArgumentException( "origin_id must be str, not %r" % (origin_url,) ) if not isinstance(metadata, bytes): raise StorageArgumentException( "metadata must be bytes, not %r" % (metadata,) ) authority_key = self._metadata_authority_key(authority) if authority_key not in self._metadata_authorities: raise StorageArgumentException(f"Unknown authority {authority}") fetcher_key = self._metadata_fetcher_key(fetcher) if fetcher_key not in self._metadata_fetchers: raise StorageArgumentException(f"Unknown fetcher {fetcher}") origin_metadata = { "origin_url": origin_url, "discovery_date": discovery_date, "authority": authority_key, "fetcher": fetcher_key, "format": format, "metadata": metadata, } self._origin_metadata[origin_url][authority_key].add(origin_metadata) return None def origin_metadata_get( self, origin_url: str, authority: Dict[str, str], after: Optional[datetime.datetime] = None, limit: Optional[int] = None, ) -> List[Dict[str, Any]]: if not isinstance(origin_url, str): raise TypeError("origin_url must be str, not %r" % (origin_url,)) authority_key = self._metadata_authority_key(authority) if after is None: entries = iter(self._origin_metadata[origin_url][authority_key]) else: entries = self._origin_metadata[origin_url][authority_key].iter_from(after) if limit: entries = itertools.islice(entries, 0, limit) results = [] for entry in entries: authority = self._metadata_authorities[entry["authority"]] fetcher = self._metadata_fetchers[entry["fetcher"]] results.append( { **entry, "authority": {"type": authority["type"], "url": authority["url"],}, "fetcher": { "name": fetcher["name"], "version": fetcher["version"], }, } ) return results def metadata_fetcher_add( self, name: str, version: str, metadata: Dict[str, Any] ) -> None: fetcher = { "name": name, "version": version, "metadata": metadata, } key = self._metadata_fetcher_key(fetcher) if key not in self._metadata_fetchers: self._metadata_fetchers[key] = fetcher def metadata_fetcher_get(self, name: str, version: str) -> Optional[Dict[str, Any]]: return self._metadata_fetchers.get( self._metadata_fetcher_key({"name": name, "version": version}) ) def metadata_authority_add( self, type: str, url: str, metadata: Dict[str, Any] ) -> None: authority = { "type": type, "url": url, "metadata": metadata, } key = self._metadata_authority_key(authority) self._metadata_authorities[key] = authority def metadata_authority_get(self, type: str, url: str) -> Optional[Dict[str, Any]]: return self._metadata_authorities.get( self._metadata_authority_key({"type": type, "url": url}) ) def _get_origin_url(self, origin): if isinstance(origin, str): return origin else: raise TypeError("origin must be a string.") def _person_add(self, person): key = ("person", person.fullname) if key not in self._objects: person_id = len(self._persons) + 1 self._persons.append(person) self._objects[key].append(("person", person_id)) else: person_id = self._objects[key][0][1] person = self._persons[person_id - 1] return person @staticmethod def _content_key(content): """ A stable key and the algorithm for a content""" if isinstance(content, BaseContent): content = content.to_dict() return tuple((key, content.get(key)) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _metadata_fetcher_key(fetcher: Dict) -> Hashable: return (fetcher["name"], fetcher["version"]) @staticmethod def _metadata_authority_key(authority: Dict) -> Hashable: return (authority["type"], authority["url"]) def diff_directories(self, from_dir, to_dir, track_renaming=False): raise NotImplementedError("InMemoryStorage.diff_directories") def diff_revisions(self, from_rev, to_rev, track_renaming=False): raise NotImplementedError("InMemoryStorage.diff_revisions") def diff_revision(self, revision, track_renaming=False): raise NotImplementedError("InMemoryStorage.diff_revision") def clear_buffers(self, object_types: Optional[Iterable[str]] = None) -> None: """Do nothing """ return None def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: return {} diff --git a/swh/storage/tests/storage_data.py b/swh/storage/tests/storage_data.py index a3174ea9..fdf1c911 100644 --- a/swh/storage/tests/storage_data.py +++ b/swh/storage/tests/storage_data.py @@ -1,520 +1,522 @@ # Copyright (C) 2015-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime from swh.model.hashutil import hash_to_bytes from swh.model import from_disk class StorageData: def __getattr__(self, key): try: v = globals()[key] except KeyError as e: raise AttributeError(e.args[0]) if hasattr(v, "copy"): return v.copy() return v data = StorageData() cont = { "data": b"42\n", "length": 3, "sha1": hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4689"), "sha1_git": hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), "sha256": hash_to_bytes( "673650f936cb3b0a2f93ce09d81be10748b1b203c19e8176b4eefc1964a0cf3a" ), "blake2s256": hash_to_bytes( "d5fe1939576527e42cfd76a9455a2432fe7f56669564577dd93c4280e76d661d" ), "status": "visible", } cont2 = { "data": b"4242\n", "length": 5, "sha1": hash_to_bytes("61c2b3a30496d329e21af70dd2d7e097046d07b7"), "sha1_git": hash_to_bytes("36fade77193cb6d2bd826161a0979d64c28ab4fa"), "sha256": hash_to_bytes( "859f0b154fdb2d630f45e1ecae4a862915435e663248bb8461d914696fc047cd" ), "blake2s256": hash_to_bytes( "849c20fad132b7c2d62c15de310adfe87be94a379941bed295e8141c6219810d" ), "status": "visible", } cont3 = { "data": b"424242\n", "length": 7, "sha1": hash_to_bytes("3e21cc4942a4234c9e5edd8a9cacd1670fe59f13"), "sha1_git": hash_to_bytes("c932c7649c6dfa4b82327d121215116909eb3bea"), "sha256": hash_to_bytes( "92fb72daf8c6818288a35137b72155f507e5de8d892712ab96277aaed8cf8a36" ), "blake2s256": hash_to_bytes( "76d0346f44e5a27f6bafdd9c2befd304aff83780f93121d801ab6a1d4769db11" ), "status": "visible", "ctime": "2019-12-01 00:00:00Z", } contents = (cont, cont2, cont3) missing_cont = { "data": b"missing\n", "length": 8, "sha1": hash_to_bytes("f9c24e2abb82063a3ba2c44efd2d3c797f28ac90"), "sha1_git": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8919"), "sha256": hash_to_bytes( "6bbd052ab054ef222c1c87be60cd191addedd24cc882d1f5f7f7be61dc61bb3a" ), "blake2s256": hash_to_bytes( "306856b8fd879edb7b6f1aeaaf8db9bbecc993cd7f776c333ac3a782fa5c6eba" ), "status": "absent", } skipped_cont = { "length": 1024 * 1024 * 200, "sha1_git": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8920"), "sha1": hash_to_bytes("43e45d56f88993aae6a0198013efa80716fd8920"), "sha256": hash_to_bytes( "7bbd052ab054ef222c1c87be60cd191addedd24cc882d1f5f7f7be61dc61bb3a" ), "blake2s256": hash_to_bytes( "ade18b1adecb33f891ca36664da676e12c772cc193778aac9a137b8dc5834b9b" ), "reason": "Content too long", "status": "absent", "origin": "file:///dev/zero", } skipped_cont2 = { "length": 1024 * 1024 * 300, "sha1_git": hash_to_bytes("44e45d56f88993aae6a0198013efa80716fd8921"), "sha1": hash_to_bytes("54e45d56f88993aae6a0198013efa80716fd8920"), "sha256": hash_to_bytes( "8cbd052ab054ef222c1c87be60cd191addedd24cc882d1f5f7f7be61dc61bb3a" ), "blake2s256": hash_to_bytes( "9ce18b1adecb33f891ca36664da676e12c772cc193778aac9a137b8dc5834b9b" ), "reason": "Content too long", "status": "absent", } dir = { "id": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), - "entries": [ + "entries": ( { "name": b"foo", "type": "file", "target": hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), # cont "perms": from_disk.DentryPerms.content, }, { "name": b"bar\xc3", "type": "dir", "target": b"12345678901234567890", "perms": from_disk.DentryPerms.directory, }, - ], + ), } dir2 = { "id": hash_to_bytes("340133423253310030f531e632a733ff37c3a935"), - "entries": [ + "entries": ( { "name": b"oof", "type": "file", "target": hash_to_bytes( # cont2 "36fade77193cb6d2bd826161a0979d64c28ab4fa" ), "perms": from_disk.DentryPerms.content, - } - ], + }, + ), } dir3 = { "id": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8921"), - "entries": [ + "entries": ( { "name": b"foo", "type": "file", "target": hash_to_bytes("d81cc0710eb6cf9efd5b920a8453e1e07157b6cd"), # cont "perms": from_disk.DentryPerms.content, }, { "name": b"subdir", "type": "dir", "target": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), # dir "perms": from_disk.DentryPerms.directory, }, { "name": b"hello", "type": "file", "target": b"12345678901234567890", "perms": from_disk.DentryPerms.content, }, - ], + ), } dir4 = { "id": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8922"), - "entries": [ + "entries": ( { "name": b"subdir1", "type": "dir", "target": hash_to_bytes("33e45d56f88993aae6a0198013efa80716fd8921"), # dir3 "perms": from_disk.DentryPerms.directory, }, - ], + ), } dierctories = (dir, dir2, dir3, dir4) minus_offset = datetime.timezone(datetime.timedelta(minutes=-120)) plus_offset = datetime.timezone(datetime.timedelta(minutes=120)) revision = { "id": b"56789012345678901234", "message": b"hello", "author": { "name": b"Nicolas Dandrimont", "email": b"nicolas@example.com", "fullname": b"Nicolas Dandrimont ", }, "date": { "timestamp": {"seconds": 1234567890, "microseconds": 0}, "offset": 120, "negative_utc": False, }, "committer": { "name": b"St\xc3fano Zacchiroli", "email": b"stefano@example.com", "fullname": b"St\xc3fano Zacchiroli ", }, "committer_date": { "timestamp": {"seconds": 1123456789, "microseconds": 0}, "offset": 0, "negative_utc": True, }, - "parents": [b"01234567890123456789", b"23434512345123456789"], + "parents": (b"01234567890123456789", b"23434512345123456789"), "type": "git", "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), # dir "metadata": { "checksums": {"sha1": "tarball-sha1", "sha256": "tarball-sha256",}, "signed-off-by": "some-dude", "extra_headers": [ ["gpgsig", b"test123"], ["mergetags", [b"foo\\bar", b"\x22\xaf\x89\x80\x01\x00"]], ], }, "synthetic": True, } revision2 = { "id": b"87659012345678904321", "message": b"hello again", "author": { "name": b"Roberto Dicosmo", "email": b"roberto@example.com", "fullname": b"Roberto Dicosmo ", }, "date": { "timestamp": {"seconds": 1234567843, "microseconds": 220000,}, "offset": -720, "negative_utc": False, }, "committer": { "name": b"tony", "email": b"ar@dumont.fr", "fullname": b"tony ", }, "committer_date": { "timestamp": {"seconds": 1123456789, "microseconds": 0}, "offset": 0, "negative_utc": False, }, - "parents": [b"01234567890123456789"], + "parents": (b"01234567890123456789",), "type": "git", "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a935"), # dir2 "metadata": None, "synthetic": False, } revision3 = { "id": hash_to_bytes("7026b7c1a2af56521e951c01ed20f255fa054238"), "message": b"a simple revision with no parents this time", "author": { "name": b"Roberto Dicosmo", "email": b"roberto@example.com", "fullname": b"Roberto Dicosmo ", }, "date": { "timestamp": {"seconds": 1234567843, "microseconds": 220000,}, "offset": -720, "negative_utc": False, }, "committer": { "name": b"tony", "email": b"ar@dumont.fr", "fullname": b"tony ", }, "committer_date": { "timestamp": {"seconds": 1127351742, "microseconds": 0}, "offset": 0, "negative_utc": False, }, - "parents": [], + "parents": (), "type": "git", "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a935"), # dir2 "metadata": None, "synthetic": True, } revision4 = { "id": hash_to_bytes("368a48fe15b7db2383775f97c6b247011b3f14f4"), "message": b"parent of self.revision2", "author": { "name": b"me", "email": b"me@soft.heri", "fullname": b"me ", }, "date": { "timestamp": {"seconds": 1244567843, "microseconds": 220000,}, "offset": -720, "negative_utc": False, }, "committer": { "name": b"committer-dude", "email": b"committer@dude.com", "fullname": b"committer-dude ", }, "committer_date": { "timestamp": {"seconds": 1244567843, "microseconds": 220000,}, "offset": -720, "negative_utc": False, }, - "parents": [hash_to_bytes("7026b7c1a2af56521e951c01ed20f255fa054238")], # revision3 + "parents": ( + hash_to_bytes("7026b7c1a2af56521e951c01ed20f255fa054238"), + ), # revision3 "type": "git", "directory": hash_to_bytes("340133423253310030f531e632a733ff37c3a930"), # dir "metadata": None, "synthetic": False, } revisions = (revision, revision2, revision3, revision4) origin = { "url": "file:///dev/null", } origin2 = { "url": "file:///dev/zero", } origins = (origin, origin2) metadata_authority = { "type": "deposit", "url": "http://hal.inria.example.com/", "metadata": {"location": "France"}, } metadata_authority2 = { "type": "registry", "url": "http://wikidata.example.com/", "metadata": {}, } metadata_fetcher = { "name": "swh-deposit", "version": "0.0.1", "metadata": {"sword_version": "2"}, } metadata_fetcher2 = { "name": "swh-example", "version": "0.0.1", "metadata": {}, } date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) type_visit1 = "git" date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) type_visit2 = "hg" date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) type_visit3 = "deb" release = { "id": b"87659012345678901234", "name": b"v0.0.1", "author": { "name": b"olasd", "email": b"nic@olasd.fr", "fullname": b"olasd ", }, "date": { "timestamp": {"seconds": 1234567890, "microseconds": 0}, "offset": 42, "negative_utc": False, }, "target": b"43210987654321098765", "target_type": "revision", "message": b"synthetic release", "synthetic": True, } release2 = { "id": b"56789012348765901234", "name": b"v0.0.2", "author": { "name": b"tony", "email": b"ar@dumont.fr", "fullname": b"tony ", }, "date": { "timestamp": {"seconds": 1634366813, "microseconds": 0}, "offset": -120, "negative_utc": False, }, "target": b"432109\xa9765432\xc309\x00765", "target_type": "revision", "message": b"v0.0.2\nMisc performance improvements + bug fixes", "synthetic": False, } release3 = { "id": b"87659012345678904321", "name": b"v0.0.2", "author": { "name": b"tony", "email": b"tony@ardumont.fr", "fullname": b"tony ", }, "date": { "timestamp": {"seconds": 1634336813, "microseconds": 0}, "offset": 0, "negative_utc": False, }, "target": b"87659012345678904321", # revision2 "target_type": "revision", "message": b"yet another synthetic release", "synthetic": True, } releases = (release, release2, release3) snapshot = { "id": hash_to_bytes("2498dbf535f882bc7f9a18fb16c9ad27fda7bab7"), "branches": { b"master": { "target": b"56789012345678901234", # revision "target_type": "revision", }, }, } empty_snapshot = { "id": hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), "branches": {}, } complete_snapshot = { "id": hash_to_bytes("6e65b86363953b780d92b0a928f3e8fcdd10db36"), "branches": { b"directory": { "target": hash_to_bytes("1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8"), "target_type": "directory", }, b"directory2": { "target": hash_to_bytes("1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8"), "target_type": "directory", }, b"content": { "target": hash_to_bytes("fe95a46679d128ff167b7c55df5d02356c5a1ae1"), "target_type": "content", }, b"alias": {"target": b"revision", "target_type": "alias",}, b"revision": { "target": hash_to_bytes("aafb16d69fd30ff58afdd69036a26047f3aebdc6"), "target_type": "revision", }, b"release": { "target": hash_to_bytes("7045404f3d1c54e6473c71bbb716529fbad4be24"), "target_type": "release", }, b"snapshot": { "target": hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), "target_type": "snapshot", }, b"dangling": None, }, } origin_metadata = { "origin_url": origin["url"], "discovery_date": datetime.datetime( 2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc ), "authority": { "type": metadata_authority["type"], "url": metadata_authority["url"], }, "fetcher": { "name": metadata_fetcher["name"], "version": metadata_fetcher["version"], }, "format": "json", "metadata": b'{"foo": "bar"}', } origin_metadata2 = { "origin_url": origin["url"], "discovery_date": datetime.datetime( 2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc ), "authority": { "type": metadata_authority["type"], "url": metadata_authority["url"], }, "fetcher": { "name": metadata_fetcher["name"], "version": metadata_fetcher["version"], }, "format": "yaml", "metadata": b"foo: bar", } origin_metadata3 = { "origin_url": origin["url"], "discovery_date": datetime.datetime( 2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc ), "authority": { "type": metadata_authority2["type"], "url": metadata_authority2["url"], }, "fetcher": { "name": metadata_fetcher2["name"], "version": metadata_fetcher2["version"], }, "format": "yaml", "metadata": b"foo: bar", } person = { "name": b"John Doe", "email": b"john.doe@institute.org", "fullname": b"John Doe ", } diff --git a/swh/storage/tests/test_api_client_dicts.py b/swh/storage/tests/test_api_client_dicts.py deleted file mode 100644 index a59ab7af..00000000 --- a/swh/storage/tests/test_api_client_dicts.py +++ /dev/null @@ -1,51 +0,0 @@ -# Copyright (C) 2015-2020 The Software Heritage developers -# See the AUTHORS file at the top-level directory of this distribution -# License: GNU General Public License version 3, or any later version -# See top-level LICENSE file for more information - -from unittest.mock import patch - -import pytest - -from swh.storage.api.client import RemoteStorage -import swh.storage.api.server as server -import swh.storage.storage -from swh.storage.tests.test_storage import TestStorageGeneratedData # noqa -from swh.storage.tests.test_storage import TestStorage as _TestStorage -from swh.storage.tests.test_api_client import swh_storage # noqa - -# tests are executed using imported classes (TestStorage and -# TestStorageGeneratedData) using overloaded swh_storage fixture -# below - - -@pytest.fixture -def app_server(): - storage_config = { - "cls": "validate", - "storage": {"cls": "memory", "journal_writer": {"cls": "memory",},}, - } - server.storage = swh.storage.get_storage(**storage_config) - yield server - - -@pytest.fixture -def app(app_server): - return app_server.app - - -@pytest.fixture -def swh_rpc_client_class(): - return RemoteStorage - - -class TestStorage(_TestStorage): - def test_content_update(self, swh_storage, app_server): # noqa - # TODO, journal_writer not supported - swh_storage.journal_writer.journal = None - with patch.object(server.storage.journal_writer, "journal", None): - super().test_content_update(swh_storage) - - @pytest.mark.skip("non-applicable test") - def test_content_add_from_lazy_content(self): - pass diff --git a/swh/storage/tests/test_replay.py b/swh/storage/tests/test_replay.py index d31c57a7..670d7431 100644 --- a/swh/storage/tests/test_replay.py +++ b/swh/storage/tests/test_replay.py @@ -1,465 +1,269 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import functools -import random import logging -import dateutil -from typing import Dict, List - -from confluent_kafka import Producer +from typing import Container, Dict, Optional import pytest from swh.model.hashutil import hash_to_hex, MultiHash, DEFAULT_ALGORITHMS from swh.model.model import Content from swh.storage import get_storage +from swh.storage.in_memory import InMemoryStorage from swh.storage.replay import process_replay_objects from swh.journal.serializers import key_to_kafka, value_to_kafka from swh.journal.client import JournalClient -from swh.journal.tests.utils import MockedJournalClient, MockedKafkaWriter -from swh.journal.tests.conftest import ( - TEST_OBJECT_DICTS, +from swh.journal.tests.journal_data import ( + TEST_OBJECTS, DUPLICATE_CONTENTS, ) UTC = datetime.timezone.utc -storage_config = {"cls": "pipeline", "steps": [{"cls": "memory"},]} - -def test_storage_play( - kafka_prefix: str, kafka_consumer_group: str, kafka_server: str, caplog, +@pytest.fixture() +def replayer_storage_and_client( + kafka_prefix: str, kafka_consumer_group: str, kafka_server: str ): + journal_writer_config = { + "cls": "kafka", + "brokers": [kafka_server], + "client_id": "kafka_writer", + "prefix": kafka_prefix, + } + storage_config = { + "cls": "memory", + "journal_writer": journal_writer_config, + } + storage = get_storage(**storage_config) + replayer = JournalClient( + brokers=kafka_server, + group_id=kafka_consumer_group, + prefix=kafka_prefix, + stop_on_eof=True, + ) + + yield storage, replayer + + +def test_storage_replayer(replayer_storage_and_client, caplog): """Optimal replayer scenario. This: - - writes objects to the topic + - writes objects to a source storage - replayer consumes objects from the topic and replay them + - a destination storage is filled from this + In the end, both storages should have the same content. """ - kafka_prefix += ".swh.journal.objects" + src, replayer = replayer_storage_and_client - storage = get_storage(**storage_config) - - producer = Producer( - { - "bootstrap.servers": kafka_server, - "client.id": "test producer", - "acks": "all", - } - ) - - now = datetime.datetime.now(tz=UTC) - - # Fill Kafka + # Fill Kafka using a source storage nb_sent = 0 - nb_visits = 0 - for object_type, objects in TEST_OBJECT_DICTS.items(): - topic = f"{kafka_prefix}.{object_type}" - for object_ in objects: - key = bytes(random.randint(0, 255) for _ in range(40)) - object_ = object_.copy() - if object_type == "content": - object_["ctime"] = now - elif object_type == "origin_visit": - nb_visits += 1 - object_["visit"] = nb_visits - producer.produce( - topic=topic, key=key_to_kafka(key), value=value_to_kafka(object_), - ) - nb_sent += 1 - - producer.flush() + for object_type, objects in TEST_OBJECTS.items(): + if object_type == "origin_visit": + # src.origin_visit_upsert(objects) + for visit in objects: + src.origin_visit_add( + origin_url=visit.origin, date=visit.date, type=visit.type + ) + else: + method = getattr(src, object_type + "_add") + method(objects) + nb_sent += len(objects) caplog.set_level(logging.ERROR, "swh.journal.replay") - # Fill the storage from Kafka - replayer = JournalClient( - brokers=kafka_server, - group_id=kafka_consumer_group, - prefix=kafka_prefix, - stop_after_objects=nb_sent, - ) - worker_fn = functools.partial(process_replay_objects, storage=storage) - nb_inserted = 0 - while nb_inserted < nb_sent: - nb_inserted += replayer.process(worker_fn) - assert nb_sent == nb_inserted - # Check the objects were actually inserted in the storage - assert TEST_OBJECT_DICTS["revision"] == list( - storage.revision_get([rev["id"] for rev in TEST_OBJECT_DICTS["revision"]]) - ) - assert TEST_OBJECT_DICTS["release"] == list( - storage.release_get([rel["id"] for rel in TEST_OBJECT_DICTS["release"]]) - ) + # Fill the destination storage from Kafka + dst = get_storage(cls="memory") + worker_fn = functools.partial(process_replay_objects, storage=dst) + nb_inserted = replayer.process(worker_fn) + assert nb_sent == nb_inserted - origins = list(storage.origin_get([orig for orig in TEST_OBJECT_DICTS["origin"]])) - assert TEST_OBJECT_DICTS["origin"] == [{"url": orig["url"]} for orig in origins] - for origin in origins: - origin_url = origin["url"] - expected_visits = [ - { - **visit, - "origin": origin_url, - "date": dateutil.parser.parse(visit["date"]), - } - for visit in TEST_OBJECT_DICTS["origin_visit"] - if visit["origin"] == origin["url"] - ] - actual_visits = list(storage.origin_visit_get(origin_url)) - for visit in actual_visits: - del visit["visit"] # opaque identifier - assert expected_visits == actual_visits - - input_contents = TEST_OBJECT_DICTS["content"] - contents = storage.content_get_metadata([cont["sha1"] for cont in input_contents]) - assert len(contents) == len(input_contents) - assert contents == {cont["sha1"]: [cont] for cont in input_contents} + _check_replayed(src, dst) collision = 0 for record in caplog.records: logtext = record.getMessage() if "Colliding contents:" in logtext: collision += 1 assert collision == 0, "No collision should be detected" -def test_storage_play_with_collision( - kafka_prefix: str, kafka_consumer_group: str, kafka_server: str, caplog, -): +def test_storage_play_with_collision(replayer_storage_and_client, caplog): """Another replayer scenario with collisions. This: - writes objects to the topic, including colliding contents - replayer consumes objects from the topic and replay them - This drops the colliding contents from the replay when detected """ - kafka_prefix += ".swh.journal.objects" - - storage = get_storage(**storage_config) - - producer = Producer( - { - "bootstrap.servers": kafka_server, - "client.id": "test producer", - "enable.idempotence": "true", - } - ) + src, replayer = replayer_storage_and_client - now = datetime.datetime.now(tz=UTC) - - # Fill Kafka + # Fill Kafka using a source storage nb_sent = 0 - nb_visits = 0 - for object_type, objects in TEST_OBJECT_DICTS.items(): - topic = f"{kafka_prefix}.{object_type}" - for object_ in objects: - key = bytes(random.randint(0, 255) for _ in range(40)) - object_ = object_.copy() - if object_type == "content": - object_["ctime"] = now - elif object_type == "origin_visit": - nb_visits += 1 - object_["visit"] = nb_visits - producer.produce( - topic=topic, key=key_to_kafka(key), value=value_to_kafka(object_), - ) - nb_sent += 1 + for object_type, objects in TEST_OBJECTS.items(): + if object_type == "origin_visit": + for visit in objects: + src.origin_visit_add( + origin_url=visit.origin, date=visit.date, type=visit.type + ) + else: + method = getattr(src, object_type + "_add") + method(objects) + nb_sent += len(objects) # Create collision in input data - # They are not written in the destination + # These should not be written in the destination + producer = src.journal_writer.journal.producer + prefix = src.journal_writer.journal._prefix for content in DUPLICATE_CONTENTS: - topic = f"{kafka_prefix}.content" + topic = f"{prefix}.content" + key = content["sha1"] producer.produce( topic=topic, key=key_to_kafka(key), value=value_to_kafka(content), ) - nb_sent += 1 producer.flush() caplog.set_level(logging.ERROR, "swh.journal.replay") - # Fill the storage from Kafka - replayer = JournalClient( - brokers=kafka_server, - group_id=kafka_consumer_group, - prefix=kafka_prefix, - stop_after_objects=nb_sent, - ) - worker_fn = functools.partial(process_replay_objects, storage=storage) - nb_inserted = 0 - while nb_inserted < nb_sent: - nb_inserted += replayer.process(worker_fn) - assert nb_sent == nb_inserted - - # Check the objects were actually inserted in the storage - assert TEST_OBJECT_DICTS["revision"] == list( - storage.revision_get([rev["id"] for rev in TEST_OBJECT_DICTS["revision"]]) - ) - assert TEST_OBJECT_DICTS["release"] == list( - storage.release_get([rel["id"] for rel in TEST_OBJECT_DICTS["release"]]) - ) - origins = list(storage.origin_get([orig for orig in TEST_OBJECT_DICTS["origin"]])) - assert TEST_OBJECT_DICTS["origin"] == [{"url": orig["url"]} for orig in origins] - for origin in origins: - origin_url = origin["url"] - expected_visits = [ - { - **visit, - "origin": origin_url, - "date": dateutil.parser.parse(visit["date"]), - } - for visit in TEST_OBJECT_DICTS["origin_visit"] - if visit["origin"] == origin["url"] - ] - actual_visits = list(storage.origin_visit_get(origin_url)) - for visit in actual_visits: - del visit["visit"] # opaque identifier - assert expected_visits == actual_visits - - input_contents = TEST_OBJECT_DICTS["content"] - contents = storage.content_get_metadata([cont["sha1"] for cont in input_contents]) - assert len(contents) == len(input_contents) - assert contents == {cont["sha1"]: [cont] for cont in input_contents} + # Fill the destination storage from Kafka + dst = get_storage(cls="memory") + worker_fn = functools.partial(process_replay_objects, storage=dst) + nb_inserted = replayer.process(worker_fn) + assert nb_sent == nb_inserted + # check the logs for the collision being properly detected nb_collisions = 0 - actual_collision: Dict for record in caplog.records: logtext = record.getMessage() if "Collision detected:" in logtext: nb_collisions += 1 actual_collision = record.args["collision"] assert nb_collisions == 1, "1 collision should be detected" algo = "sha1" assert actual_collision["algo"] == algo expected_colliding_hash = hash_to_hex(DUPLICATE_CONTENTS[0][algo]) assert actual_collision["hash"] == expected_colliding_hash actual_colliding_hashes = actual_collision["objects"] assert len(actual_colliding_hashes) == len(DUPLICATE_CONTENTS) for content in DUPLICATE_CONTENTS: expected_content_hashes = { k: hash_to_hex(v) for k, v in Content.from_dict(content).hashes().items() } assert expected_content_hashes in actual_colliding_hashes + # all objects from the src should exists in the dst storage + _check_replayed(src, dst, exclude=["contents"]) + # but the dst has one content more (one of the 2 colliding ones) + assert len(src._contents) == len(dst._contents) - 1 -def _test_write_replay_origin_visit(visits: List[Dict]): - """Helper function to write tests for origin_visit. - - Each visit (a dict) given in the 'visits' argument will be sent to - a (mocked) kafka queue, which a in-memory-storage backed replayer is - listening to. - - Check that corresponding origin visits entities are present in the storage - and have correct values if they are not skipped. - - """ - queue: List = [] - replayer = MockedJournalClient(queue) - writer = MockedKafkaWriter(queue) - - # Note that flipping the order of these two insertions will crash - # the test, because the legacy origin_format does not allow to create - # the origin when needed (type is missing) - writer.send( - "origin", - "foo", - { - "url": "http://example.com/", - "type": "git", # test the legacy origin format is accepted - }, - ) - for visit in visits: - writer.send("origin_visit", "foo", visit) - - queue_size = len(queue) - assert replayer.stop_after_objects is None - replayer.stop_after_objects = queue_size - - storage = get_storage(**storage_config) - worker_fn = functools.partial(process_replay_objects, storage=storage) - - replayer.process(worker_fn) - actual_visits = list(storage.origin_visit_get("http://example.com/")) - - assert len(actual_visits) == len(visits), actual_visits +def test_replay_skipped_content(replayer_storage_and_client): + """Test the 'skipped_content' topic is properly replayed.""" + src, replayer = replayer_storage_and_client + _check_replay_skipped_content(src, replayer, "skipped_content") - for vin, vout in zip(visits, actual_visits): - vin = vin.copy() - vout = vout.copy() - assert vout.pop("origin") == "http://example.com/" - vin.pop("origin") - vin.setdefault("type", "git") - vin.setdefault("metadata", None) - assert vin == vout +def test_replay_skipped_content_bwcompat(replayer_storage_and_client): + """Test the 'content' topic can be used to replay SkippedContent objects.""" + src, replayer = replayer_storage_and_client + _check_replay_skipped_content(src, replayer, "content") -def test_write_replay_origin_visit(kafka_server): - """Test origin_visit when the 'origin' is just a string.""" - now = datetime.datetime.now(tz=UTC) - visits = [ - { - "visit": 1, - "origin": "http://example.com/", - "date": now, - "type": "git", - "status": "partial", - "snapshot": None, - } - ] - _test_write_replay_origin_visit(visits) +# utility functions -def test_write_replay_legacy_origin_visit1(): - """Origin_visit with no types should make the replayer crash - We expect the journal's origin_visit topic to no longer reference such - visits. If it does, the replayer must crash so we can fix the journal's - topic. +def _check_replayed( + src: InMemoryStorage, dst: InMemoryStorage, exclude: Optional[Container] = None +): + """Simple utility function to compare the content of 2 in_memory storages """ - now = datetime.datetime.now(tz=UTC) - visit = { - "visit": 1, - "origin": "http://example.com/", - "date": now, - "status": "partial", - "snapshot": None, - } - now2 = datetime.datetime.now(tz=UTC) - visit2 = { - "visit": 2, - "origin": {"url": "http://example.com/"}, - "date": now2, - "status": "partial", - "snapshot": None, - } - - for origin_visit in [visit, visit2]: - with pytest.raises(ValueError, match="Old origin visit format"): - _test_write_replay_origin_visit([origin_visit]) - - -def test_write_replay_legacy_origin_visit2(): - """Test origin_visit when 'type' is missing from the visit, but not - from the origin.""" - now = datetime.datetime.now(tz=UTC) - visits = [ - { - "visit": 1, - "origin": {"url": "http://example.com/", "type": "git",}, - "date": now, - "type": "git", - "status": "partial", - "snapshot": None, - } - ] - _test_write_replay_origin_visit(visits) - - -def test_write_replay_legacy_origin_visit3(): - """Test origin_visit when the origin is a dict""" - now = datetime.datetime.now(tz=UTC) - visits = [ - { - "visit": 1, - "origin": {"url": "http://example.com/",}, - "date": now, - "type": "git", - "status": "partial", - "snapshot": None, - } - ] - _test_write_replay_origin_visit(visits) - - -def test_replay_skipped_content(kafka_server, kafka_prefix): - """Test the 'skipped_content' topic is properly replayed.""" - _check_replay_skipped_content(kafka_server, kafka_prefix, "skipped_content") - - -def test_replay_skipped_content_bwcompat(kafka_server, kafka_prefix): - """Test the 'content' topic can be used to replay SkippedContent objects.""" - _check_replay_skipped_content(kafka_server, kafka_prefix, "content") - - -def _check_replay_skipped_content(kafka_server, kafka_prefix, topic): + expected_persons = set(src._persons) + got_persons = set(dst._persons) + assert got_persons == expected_persons + + for attr in ( + "contents", + "skipped_contents", + "directories", + "revisions", + "releases", + "snapshots", + "origins", + "origin_visits", + ): + if exclude and attr in exclude: + continue + expected_objects = sorted(getattr(src, f"_{attr}").items()) + got_objects = sorted(getattr(dst, f"_{attr}").items()) + assert got_objects == expected_objects, f"Mismatch object list for {attr}" + + +def _check_replay_skipped_content(storage, replayer, topic): skipped_contents = _gen_skipped_contents(100) nb_sent = len(skipped_contents) - - producer = Producer( - { - "bootstrap.servers": kafka_server, - "client.id": "test producer", - "acks": "all", - } - ) - replayer = JournalClient( - brokers=[kafka_server], - group_id="test consumer", - prefix=kafka_prefix, - stop_after_objects=nb_sent, - ) - assert f"{kafka_prefix}.skipped_content" in replayer.subscription + producer = storage.journal_writer.journal.producer + prefix = storage.journal_writer.journal._prefix for i, obj in enumerate(skipped_contents): - obj.pop("data", None) producer.produce( - topic=f"{kafka_prefix}.{topic}", + topic=f"{prefix}.{topic}", key=key_to_kafka({"sha1": obj["sha1"]}), value=value_to_kafka(obj), ) producer.flush() - storage = get_storage(cls="memory") - - worker_fn = functools.partial(process_replay_objects, storage=storage) + dst_storage = get_storage(cls="memory") + worker_fn = functools.partial(process_replay_objects, storage=dst_storage) nb_inserted = replayer.process(worker_fn) + assert nb_sent == nb_inserted for content in skipped_contents: assert not storage.content_find({"sha1": content["sha1"]}) # no skipped_content_find API endpoint, so use this instead - assert not list(storage.skipped_content_missing(skipped_contents)) + assert not list(dst_storage.skipped_content_missing(skipped_contents)) def _updated(d1, d2): d1.update(d2) d1.pop("data", None) return d1 def _gen_skipped_contents(n=10): # we do not use the hypothesis strategy here because this does not play well with # pytest fixtures, and it makes test execution very slow algos = DEFAULT_ALGORITHMS | {"length"} now = datetime.datetime.now(tz=UTC) return [ _updated( MultiHash.from_data(data=f"foo{i}".encode(), hash_names=algos).digest(), { "status": "absent", "reason": "why not", "origin": f"https://somewhere/{i}", "ctime": now, }, ) for i in range(n) ] diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index 87a9da67..26730e7f 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,3808 +1,3809 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy from contextlib import contextmanager import datetime import inspect import itertools import math import queue import random import threading from collections import defaultdict from datetime import timedelta from unittest.mock import Mock import psycopg2 import pytest from hypothesis import given, strategies, settings, HealthCheck from typing import ClassVar, Optional from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.model.model import ( Content, Directory, Origin, OriginVisit, Release, Revision, Snapshot, ) from swh.model.hypothesis_strategies import objects from swh.model.hashutil import hash_to_hex from swh.storage import get_storage from swh.storage.converters import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.interface import StorageInterface from swh.storage.utils import content_hex_hashes from .storage_data import data @contextmanager def db_transaction(storage): with storage.db() as db: with db.transaction() as cur: yield db, cur def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ("date", "committer_date"): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity def transform_entries(dir_, *, prefix=b""): for ent in dir_["entries"]: yield { "dir_id": dir_["id"], "type": ent["type"], "target": ent["target"], "name": prefix + ent["name"], "perms": ent["perms"], "status": None, "sha1": None, "sha1_git": None, "sha256": None, "length": None, } def cmpdir(directory): return (directory["type"], directory["dir_id"]) def short_revision(revision): return [revision["id"], revision["parents"]] 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": data.cont["data"]}) def now(): return datetime.datetime.now(tz=datetime.timezone.utc) class TestStorage: """Main class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ maxDiff = None # type: ClassVar[Optional[int]] def test_types(self, swh_storage_backend_config): """Checks all methods of StorageInterface are implemented by this backend, and that they have the same signature.""" # Create an instance of the protocol (which cannot be instantiated # directly, so this creates a subclass, then instantiates it) interface = type("_", (StorageInterface,), {})() storage = get_storage(**swh_storage_backend_config) assert "content_add" in dir(interface) missing_methods = [] for meth_name in dir(interface): if meth_name.startswith("_"): continue interface_meth = getattr(interface, meth_name) try: concrete_meth = getattr(storage, meth_name) except AttributeError: if not getattr(interface_meth, "deprecated_endpoint", False): # The backend is missing a (non-deprecated) endpoint missing_methods.append(meth_name) continue expected_signature = inspect.signature(interface_meth) actual_signature = inspect.signature(concrete_meth) assert expected_signature == actual_signature, meth_name assert missing_methods == [] def test_check_config(self, swh_storage): assert swh_storage.check_config(check_write=True) assert swh_storage.check_config(check_write=False) def test_content_add(self, swh_storage): cont = data.cont insertion_start_time = now() actual_result = swh_storage.content_add([cont]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont["length"], } assert list(swh_storage.content_get([cont["sha1"]])) == [ {"sha1": cont["sha1"], "data": cont["data"]} ] expected_cont = data.cont del expected_cont["data"] 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 obj_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_generator(self, swh_storage): def _cnt_gen(): yield data.cont actual_result = swh_storage.content_add(_cnt_gen()) assert actual_result == { "content:add": 1, "content:add:bytes": data.cont["length"], } swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_lazy_content(self, swh_storage): lazy_content = LazyContent.from_dict({**data.cont, "data": b"nope",}) insertion_start_time = now() # bypass the validation proxy for now, to directly put a dict actual_result = swh_storage.storage.content_add([lazy_content]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": data.cont["length"], } # the fact that we retrieve the content object from the storage with # the correct 'data' field ensures it has been 'called' assert list(swh_storage.content_get([data.cont["sha1"]])) == [ {"sha1": data.cont["sha1"], "data": data.cont["data"]} ] expected_cont = data.cont del expected_cont["data"] 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 obj_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_validation(self, swh_storage): cont = data.cont with pytest.raises(StorageArgumentException, match="status"): swh_storage.content_add([{**cont, "status": "absent"}]) with pytest.raises(StorageArgumentException, match="status"): swh_storage.content_add([{**cont, "status": "foobar"}]) with pytest.raises(StorageArgumentException, match="(?i)length"): swh_storage.content_add([{**cont, "length": -2}]) with pytest.raises(StorageArgumentException, match="reason"): swh_storage.content_add([{**cont, "reason": "foobar"}]) def test_skipped_content_add_validation(self, swh_storage): cont = data.cont.copy() del cont["data"] with pytest.raises(StorageArgumentException, match="status"): swh_storage.skipped_content_add([{**cont, "status": "visible"}]) with pytest.raises(StorageArgumentException, match="reason") as cm: swh_storage.skipped_content_add([{**cont, "status": "absent"}]) if type(cm.value) == psycopg2.IntegrityError: assert cm.exception.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION def test_content_get_missing(self, swh_storage): cont = data.cont swh_storage.content_add([cont]) # Query a single missing content results = list(swh_storage.content_get([data.cont2["sha1"]])) assert results == [None] # Check content_get does not abort after finding a missing content results = list(swh_storage.content_get([data.cont["sha1"], data.cont2["sha1"]])) assert results == [{"sha1": cont["sha1"], "data": cont["data"]}, None] # Check content_get does not discard found countent when it finds # a missing content. results = list(swh_storage.content_get([data.cont2["sha1"], data.cont["sha1"]])) assert results == [None, {"sha1": cont["sha1"], "data": cont["data"]}] def test_content_add_different_input(self, swh_storage): cont = data.cont cont2 = data.cont2 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): actual_result = swh_storage.content_add([data.cont]) assert actual_result == { "content:add": 1, "content:add:bytes": data.cont["length"], } assert len(swh_storage.journal_writer.journal.objects) == 1 actual_result = swh_storage.content_add([data.cont, data.cont2]) assert actual_result == { "content:add": 1, "content:add:bytes": data.cont2["length"], } assert 2 <= len(swh_storage.journal_writer.journal.objects) <= 3 assert len(swh_storage.content_find(data.cont)) == 1 assert len(swh_storage.content_find(data.cont2)) == 1 def test_content_add_collision(self, swh_storage): cont1 = data.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b["sha256"]) sha256_array[0] += 1 cont1b["sha256"] = bytes(sha256_array) with pytest.raises(HashCollision) as cm: swh_storage.content_add([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == hash_to_hex(cont1[actual_algo]) collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(Content.from_dict(cont1).hashes()), content_hex_hashes(Content.from_dict(cont1b).hashes()), ] assert exc.colliding_content_hashes() == [ Content.from_dict(cont1).hashes(), Content.from_dict(cont1b).hashes(), ] def test_content_add_duplicate(self, swh_storage): swh_storage.content_add([data.cont, data.cont]) assert list(swh_storage.content_get([data.cont["sha1"]])) == [ {"sha1": data.cont["sha1"], "data": data.cont["data"]} ] def test_content_update(self, swh_storage): if hasattr(swh_storage, "storage"): swh_storage.journal_writer.journal = None # TODO, not supported cont = copy.deepcopy(data.cont) swh_storage.content_add([cont]) # alter the sha1_git for example cont["sha1_git"] = hash_to_bytes("3a60a5275d0333bf13468e8b3dcab90f4046e654") swh_storage.content_update([cont], keys=["sha1_git"]) results = swh_storage.content_get_metadata([cont["sha1"]]) del cont["data"] - assert results == {cont["sha1"]: [cont]} + assert tuple(results[cont["sha1"]]) == (cont,) def test_content_add_metadata(self, swh_storage): cont = data.cont del cont["data"] cont["ctime"] = now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } expected_cont = cont.copy() del expected_cont["ctime"] - assert swh_storage.content_get_metadata([cont["sha1"]]) == { - cont["sha1"]: [expected_cont] - } + assert tuple( + swh_storage.content_get_metadata([cont["sha1"]])[cont["sha1"]] + ) == (expected_cont,) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: obj_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont def test_content_add_metadata_different_input(self, swh_storage): cont = data.cont del cont["data"] cont["ctime"] = now() cont2 = data.cont2 del cont2["data"] cont2["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): cont1 = data.cont del cont1["data"] cont1["ctime"] = now() # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha1_git_array = bytearray(cont1b["sha256"]) sha1_git_array[0] += 1 cont1b["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 == hash_to_hex(cont1[actual_algo]) collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(Content.from_dict(cont1).hashes()), content_hex_hashes(Content.from_dict(cont1b).hashes()), ] assert exc.colliding_content_hashes() == [ Content.from_dict(cont1).hashes(), Content.from_dict(cont1b).hashes(), ] def test_skipped_content_add(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2["blake2s256"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [ { "sha1": cont["sha1"], "sha1_git": cont["sha1_git"], "blake2s256": cont["blake2s256"], "sha256": cont["sha256"], }, { "sha1": cont2["sha1"], "sha1_git": cont2["sha1_git"], "blake2s256": cont2["blake2s256"], "sha256": cont2["sha256"], }, ] 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([cont, cont2])) assert missing == [] def test_skipped_content_add_missing_hashes(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont["sha1_git"] = cont2["sha1_git"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) 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([cont, cont2])) assert missing == [] def test_skipped_content_missing_partial_hash(self, swh_storage): cont = data.skipped_cont cont2 = cont.copy() cont2["sha1_git"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) 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([cont, cont2])) assert missing == [ { "sha1": cont2["sha1"], "sha1_git": cont2["sha1_git"], "blake2s256": cont2["blake2s256"], "sha256": cont2["sha256"], } ] @pytest.mark.property_based @settings(deadline=None) # this test is very slow @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing(self, swh_storage, algos): algos |= {"sha1"} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_cont.copy() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == set( missing_per_hash["sha1"] ) for hash in algos: assert set( swh_storage.content_missing(test_contents, key_hash=hash) ) == set(missing_per_hash[hash]) @pytest.mark.property_based @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing_unknown_algo(self, swh_storage, algos): algos |= {"sha1"} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_cont.copy() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_content["nonexisting_algo"] = b"\x00" test_contents.append(test_content) 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): # given cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) # when gen = swh_storage.content_missing_per_sha1( [cont2["sha1"], missing_cont["sha1"]] ) # then assert list(gen) == [missing_cont["sha1"]] def test_content_missing_per_sha1_git(self, swh_storage): cont = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont, cont2]) contents = [cont["sha1_git"], cont2["sha1_git"], missing_cont["sha1_git"]] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont["sha1_git"]] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [c for c in swh_contents if c["status"] != "absent"] actual_contents = [] for i in range(16): actual_result = swh_storage.content_get_partition(i, 16) assert actual_result["next_page_token"] is None actual_contents.extend(actual_result["contents"]) assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents""" expected_contents = [c for c in swh_contents if c["status"] != "absent"] actual_result = swh_storage.content_get_partition(0, 1) assert actual_result["next_page_token"] is None actual_contents = actual_result["contents"] assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_partition_empty(self, swh_storage, swh_contents): """content_get_partition when at least one of the partitions is empty""" expected_contents = { cont["sha1"] for cont in swh_contents if cont["status"] != "absent" } # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1) seen_sha1s = [] for i in range(nb_partitions): actual_result = swh_storage.content_get_partition( i, nb_partitions, limit=len(swh_contents) + 1 ) for cont in actual_result["contents"]: seen_sha1s.append(cont["sha1"]) # Limit is higher than the max number of results assert actual_result["next_page_token"] is None assert set(seen_sha1s) == expected_contents def test_content_get_partition_limit_none(self, swh_storage): """content_get_partition call with wrong limit input should fail""" with pytest.raises(StorageArgumentException) as e: swh_storage.content_get_partition(1, 16, limit=None) assert e.value.args == ("limit should not be None",) def test_generate_content_get_partition_pagination(self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [c for c in swh_contents if c["status"] != "absent"] # retrieve contents actual_contents = [] for i in range(4): page_token = None while True: actual_result = swh_storage.content_get_partition( i, 4, limit=3, page_token=page_token ) actual_contents.extend(actual_result["contents"]) page_token = actual_result["next_page_token"] if page_token is None: break assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_metadata(self, swh_storage): cont1 = data.cont cont2 = data.cont2 swh_storage.content_add([cont1, cont2]) actual_md = swh_storage.content_get_metadata([cont1["sha1"], cont2["sha1"]]) # we only retrieve the metadata cont1.pop("data") cont2.pop("data") - assert actual_md[cont1["sha1"]] == [cont1] - assert actual_md[cont2["sha1"]] == [cont2] + assert tuple(actual_md[cont1["sha1"]]) == (cont1,) + assert tuple(actual_md[cont2["sha1"]]) == (cont2,) assert len(actual_md.keys()) == 2 def test_content_get_metadata_missing_sha1(self, swh_storage): cont1 = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get_metadata([missing_cont["sha1"]]) - assert actual_contents == {missing_cont["sha1"]: []} + assert len(actual_contents) == 1 + assert tuple(actual_contents[missing_cont["sha1"]]) == () def test_content_get_random(self, swh_storage): swh_storage.content_add([data.cont, data.cont2, data.cont3]) assert swh_storage.content_get_random() in { data.cont["sha1_git"], data.cont2["sha1_git"], data.cont3["sha1_git"], } def test_directory_add(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir["id"]])) assert [data.dir["id"]] == init_missing actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)) ] actual_data = list(swh_storage.directory_ls(data.dir["id"])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) after_missing = list(swh_storage.directory_missing([data.dir["id"]])) assert after_missing == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_from_generator(self, swh_storage): def _dir_gen(): yield data.dir actual_result = swh_storage.directory_add(directories=_dir_gen()) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)) ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_validation(self, swh_storage): dir_ = copy.deepcopy(data.dir) dir_["entries"][0]["type"] = "foobar" with pytest.raises(StorageArgumentException, match="type.*foobar"): swh_storage.directory_add([dir_]) dir_ = copy.deepcopy(data.dir) del dir_["entries"][0]["target"] with pytest.raises(StorageArgumentException, match="target") as cm: swh_storage.directory_add([dir_]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION def test_directory_add_twice(self, swh_storage): actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)) ] actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {"directory:add": 0} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)) ] def test_directory_get_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir["id"]])) assert init_missing == [data.dir["id"]] actual_result = swh_storage.directory_add([data.dir, data.dir2, data.dir3]) assert actual_result == {"directory:add": 3} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)), ("directory", Directory.from_dict(data.dir2)), ("directory", Directory.from_dict(data.dir3)), ] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(data.dir["id"], recursive=True)) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(data.dir2["id"], recursive=True)) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # be both those of the directory and of the subdir actual_data = list(swh_storage.directory_ls(data.dir3["id"], recursive=True)) expected_data = list( itertools.chain( transform_entries(data.dir3), transform_entries(data.dir, prefix=b"subdir/"), ) ) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) def test_directory_get_non_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir["id"]])) assert init_missing == [data.dir["id"]] actual_result = swh_storage.directory_add([data.dir, data.dir2, data.dir3]) assert actual_result == {"directory:add": 3} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)), ("directory", Directory.from_dict(data.dir2)), ("directory", Directory.from_dict(data.dir3)), ] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(data.dir["id"])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory contaiining a single file actual_data = list(swh_storage.directory_ls(data.dir2["id"])) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(swh_storage.directory_ls(data.dir3["id"])) expected_data = list(transform_entries(data.dir3)) assert sorted(expected_data, key=cmpdir) == sorted(actual_data, key=cmpdir) def test_directory_entry_get_by_path(self, swh_storage): # given init_missing = list(swh_storage.directory_missing([data.dir3["id"]])) assert [data.dir3["id"]] == init_missing actual_result = swh_storage.directory_add([data.dir3, data.dir4]) assert actual_result == {"directory:add": 2} expected_entries = [ { "dir_id": data.dir3["id"], "name": b"foo", "type": "file", "target": data.cont["sha1_git"], "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.content, "length": None, }, { "dir_id": data.dir3["id"], "name": b"subdir", "type": "dir", "target": data.dir["id"], "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.directory, "length": None, }, { "dir_id": data.dir3["id"], "name": b"hello", "type": "file", "target": b"12345678901234567890", "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.content, "length": None, }, ] # when (all must be found here) for entry, expected_entry in zip(data.dir3["entries"], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir3["id"], [entry["name"]] ) assert actual_entry == expected_entry # same, but deeper for entry, expected_entry in zip(data.dir3["entries"], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir4["id"], [b"subdir1", entry["name"]] ) expected_entry = expected_entry.copy() expected_entry["name"] = b"subdir1/" + expected_entry["name"] assert actual_entry == expected_entry # when (nothing should be found here since data.dir is not persisted.) for entry in data.dir["entries"]: actual_entry = swh_storage.directory_entry_get_by_path( data.dir["id"], [entry["name"]] ) assert actual_entry is None def test_directory_get_random(self, swh_storage): swh_storage.directory_add([data.dir, data.dir2, data.dir3]) assert swh_storage.directory_get_random() in { data.dir["id"], data.dir2["id"], data.dir3["id"], } def test_revision_add(self, swh_storage): init_missing = swh_storage.revision_missing([data.revision["id"]]) assert list(init_missing) == [data.revision["id"]] actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([data.revision["id"]]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", Revision.from_dict(data.revision)) ] # already there so nothing added actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {"revision:add": 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_from_generator(self, swh_storage): def _rev_gen(): yield data.revision actual_result = swh_storage.revision_add(_rev_gen()) assert actual_result == {"revision:add": 1} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_validation(self, swh_storage): rev = copy.deepcopy(data.revision) rev["date"]["offset"] = 2 ** 16 with pytest.raises(StorageArgumentException, match="offset") as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev["committer_date"]["offset"] = 2 ** 16 with pytest.raises(StorageArgumentException, match="offset") as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev["type"] = "foobar" with pytest.raises(StorageArgumentException, match="(?i)type") as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_revision_add_twice(self, swh_storage): actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", Revision.from_dict(data.revision)) ] actual_result = swh_storage.revision_add([data.revision, data.revision2]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", Revision.from_dict(data.revision)), ("revision", Revision.from_dict(data.revision2)), ] def test_revision_add_name_clash(self, swh_storage): revision1 = data.revision revision2 = data.revision2 revision1["author"] = { "fullname": b"John Doe ", "name": b"John Doe", "email": b"john.doe@example.com", } revision2["author"] = { "fullname": b"John Doe ", "name": b"John Doe ", "email": b"john.doe@example.com ", } actual_result = swh_storage.revision_add([revision1, revision2]) assert actual_result == {"revision:add": 2} def test_revision_get_order(self, swh_storage): add_result = swh_storage.revision_add([data.revision, data.revision2]) assert add_result == {"revision:add": 2} # order 1 res1 = swh_storage.revision_get([data.revision["id"], data.revision2["id"]]) assert list(res1) == [data.revision, data.revision2] # order 2 res2 = swh_storage.revision_get([data.revision2["id"], data.revision["id"]]) assert list(res2) == [data.revision2, data.revision] def test_revision_log(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_log([data.revision4["id"]])) # hack: ids generated for actual_result in actual_results: if "id" in actual_result["author"]: del actual_result["author"]["id"] if "id" in actual_result["committer"]: del actual_result["committer"]["id"] assert len(actual_results) == 2 # rev4 -child-> rev3 assert actual_results[0] == normalize_entity(data.revision4) assert actual_results[1] == normalize_entity(data.revision3) assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", Revision.from_dict(data.revision3)), ("revision", Revision.from_dict(data.revision4)), ] def test_revision_log_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_log([data.revision4["id"]], 1)) # hack: ids generated for actual_result in actual_results: if "id" in actual_result["author"]: del actual_result["author"]["id"] if "id" in actual_result["committer"]: del actual_result["committer"]["id"] assert len(actual_results) == 1 assert actual_results[0] == data.revision4 def test_revision_log_unknown_revision(self, swh_storage): rev_log = list(swh_storage.revision_log([data.revision["id"]])) assert rev_log == [] def test_revision_shortlog(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_shortlog([data.revision4["id"]])) assert len(actual_results) == 2 # rev4 -child-> rev3 assert list(actual_results[0]) == short_revision(data.revision4) assert list(actual_results[1]) == short_revision(data.revision3) def test_revision_shortlog_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_shortlog([data.revision4["id"]], 1)) assert len(actual_results) == 1 assert list(actual_results[0]) == short_revision(data.revision4) def test_revision_get(self, swh_storage): swh_storage.revision_add([data.revision]) actual_revisions = list( swh_storage.revision_get([data.revision["id"], data.revision2["id"]]) ) # when if "id" in actual_revisions[0]["author"]: del actual_revisions[0]["author"]["id"] # hack: ids are generated if "id" in actual_revisions[0]["committer"]: del actual_revisions[0]["committer"]["id"] assert len(actual_revisions) == 2 assert actual_revisions[0] == normalize_entity(data.revision) assert actual_revisions[1] is None def test_revision_get_no_parents(self, swh_storage): swh_storage.revision_add([data.revision3]) get = list(swh_storage.revision_get([data.revision3["id"]])) assert len(get) == 1 - assert get[0]["parents"] == [] # no parents on this one + assert get[0]["parents"] == () # no parents on this one def test_revision_get_random(self, swh_storage): swh_storage.revision_add([data.revision, data.revision2, data.revision3]) assert swh_storage.revision_get_random() in { data.revision["id"], data.revision2["id"], data.revision3["id"], } def test_release_add(self, swh_storage): init_missing = swh_storage.release_missing( [data.release["id"], data.release2["id"]] ) assert [data.release["id"], data.release2["id"]] == list(init_missing) actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {"release:add": 2} end_missing = swh_storage.release_missing( [data.release["id"], data.release2["id"]] ) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", Release.from_dict(data.release)), ("release", Release.from_dict(data.release2)), ] # already present so nothing added actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {"release:add": 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 def test_release_add_from_generator(self, swh_storage): def _rel_gen(): yield data.release yield data.release2 actual_result = swh_storage.release_add(_rel_gen()) assert actual_result == {"release:add": 2} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", Release.from_dict(data.release)), ("release", Release.from_dict(data.release2)), ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 def test_release_add_no_author_date(self, swh_storage): release = data.release release["author"] = None release["date"] = None actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} end_missing = swh_storage.release_missing([data.release["id"]]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", Release.from_dict(release)) ] def test_release_add_validation(self, swh_storage): rel = copy.deepcopy(data.release) rel["date"]["offset"] = 2 ** 16 with pytest.raises(StorageArgumentException, match="offset") as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rel = copy.deepcopy(data.release) rel["author"] = None with pytest.raises(StorageArgumentException, match="date") as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.CHECK_VIOLATION def test_release_add_validation_type(self, swh_storage): rel = copy.deepcopy(data.release) rel["date"]["offset"] = "toto" with pytest.raises(StorageArgumentException): swh_storage.release_add([rel]) def test_release_add_twice(self, swh_storage): actual_result = swh_storage.release_add([data.release]) assert actual_result == {"release:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", Release.from_dict(data.release)) ] actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {"release:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", Release.from_dict(data.release)), ("release", Release.from_dict(data.release2)), ] def test_release_add_name_clash(self, swh_storage): release1 = data.release.copy() release2 = data.release2.copy() release1["author"] = { "fullname": b"John Doe ", "name": b"John Doe", "email": b"john.doe@example.com", } release2["author"] = { "fullname": b"John Doe ", "name": b"John Doe ", "email": b"john.doe@example.com ", } actual_result = swh_storage.release_add([release1, release2]) assert actual_result == {"release:add": 2} def test_release_get(self, swh_storage): # given swh_storage.release_add([data.release, data.release2]) # when actual_releases = list( swh_storage.release_get([data.release["id"], data.release2["id"]]) ) # then for actual_release in actual_releases: if "id" in actual_release["author"]: del actual_release["author"]["id"] # hack: ids are generated assert [normalize_entity(data.release), normalize_entity(data.release2)] == [ actual_releases[0], actual_releases[1], ] unknown_releases = list(swh_storage.release_get([data.release3["id"]])) assert unknown_releases[0] is None def test_release_get_order(self, swh_storage): add_result = swh_storage.release_add([data.release, data.release2]) assert add_result == {"release:add": 2} # order 1 res1 = swh_storage.release_get([data.release["id"], data.release2["id"]]) assert list(res1) == [data.release, data.release2] # order 2 res2 = swh_storage.release_get([data.release2["id"], data.release["id"]]) assert list(res2) == [data.release2, data.release] def test_release_get_random(self, swh_storage): swh_storage.release_add([data.release, data.release2, data.release3]) assert swh_storage.release_get_random() in { data.release["id"], data.release2["id"], data.release3["id"], } def test_origin_add_one(self, swh_storage): origin0 = swh_storage.origin_get(data.origin) assert origin0 is None id = swh_storage.origin_add_one(data.origin) actual_origin = swh_storage.origin_get({"url": data.origin["url"]}) assert actual_origin["url"] == data.origin["url"] id2 = swh_storage.origin_add_one(data.origin) assert id == id2 def test_origin_add(self, swh_storage): origin0 = swh_storage.origin_get([data.origin])[0] assert origin0 is None origin1, origin2 = swh_storage.origin_add([data.origin, data.origin2]) actual_origin = swh_storage.origin_get([{"url": data.origin["url"],}])[0] assert actual_origin["url"] == origin1["url"] actual_origin2 = swh_storage.origin_get([{"url": data.origin2["url"],}])[0] assert actual_origin2["url"] == origin2["url"] if "id" in actual_origin: del actual_origin["id"] del actual_origin2["id"] assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(actual_origin)), ("origin", Origin.from_dict(actual_origin2)), ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_from_generator(self, swh_storage): def _ori_gen(): yield data.origin yield data.origin2 origin1, origin2 = swh_storage.origin_add(_ori_gen()) actual_origin = swh_storage.origin_get([{"url": data.origin["url"],}])[0] assert actual_origin["url"] == origin1["url"] actual_origin2 = swh_storage.origin_get([{"url": data.origin2["url"],}])[0] assert actual_origin2["url"] == origin2["url"] if "id" in actual_origin: del actual_origin["id"] del actual_origin2["id"] assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(actual_origin)), ("origin", Origin.from_dict(actual_origin2)), ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_twice(self, swh_storage): add1 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin", Origin.from_dict(data.origin2)), ] add2 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin", Origin.from_dict(data.origin2)), ] assert add1 == add2 def test_origin_add_validation(self, swh_storage): """Incorrect formatted origin should fail the validation """ with pytest.raises(StorageArgumentException, match="url"): swh_storage.origin_add([{}]) with pytest.raises( StorageArgumentException, match="unexpected keyword argument" ): swh_storage.origin_add([{"ul": "mistyped url key"}]) def test_origin_get_legacy(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get({"url": data.origin["url"]}) assert actual_origin0["url"] == data.origin["url"] def test_origin_get(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get([{"url": data.origin["url"]}]) assert len(actual_origin0) == 1 assert actual_origin0[0]["url"] == data.origin["url"] def _generate_random_visits(self, nb_visits=100, start=0, end=7): """Generate random visits within the last 2 months (to avoid computations) """ visits = [] today = 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_random(self, swh_storage): swh_storage.origin_add(data.origins) # Add some random visits within the selection range visits = self._generate_random_visits() visit_type = "git" # Add visits to those origins for origin in data.origins: origin_url = origin["url"] for date_visit in visits: visit = swh_storage.origin_visit_add( origin_url, date=date_visit, type=visit_type ) swh_storage.origin_visit_update( origin_url, visit_id=visit.visit, status="full" ) swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(data.origins) assert stats["origin_visit"] == len(data.origins) * len(visits) random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit assert random_origin_visit["origin"] is not None original_urls = [o["url"] for o in data.origins] assert random_origin_visit["origin"] in original_urls def test_origin_visit_get_random_nothing_found(self, swh_storage): swh_storage.origin_add(data.origins) visit_type = "hg" # Add some visits outside of the random generation selection so nothing # will be found by the random selection visits = self._generate_random_visits(nb_visits=3, start=13, end=24) for origin in data.origins: origin_url = origin["url"] for date_visit in visits: visit = swh_storage.origin_visit_add( origin_url, date=date_visit, type=visit_type ) swh_storage.origin_visit_update(origin_url, visit.visit, status="full") random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit is None def test_origin_get_by_sha1(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) origins = list(swh_storage.origin_get_by_sha1([sha1(data.origin["url"])])) assert len(origins) == 1 assert origins[0]["url"] == data.origin["url"] def test_origin_get_by_sha1_not_found(self, swh_storage): assert swh_storage.origin_get(data.origin) is None origins = list(swh_storage.origin_get_by_sha1([sha1(data.origin["url"])])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage): found_origins = list(swh_storage.origin_search(data.origin["url"])) assert len(found_origins) == 0 found_origins = list(swh_storage.origin_search(data.origin["url"], regexp=True)) assert len(found_origins) == 0 swh_storage.origin_add_one(data.origin) origin_data = {"url": data.origin["url"]} found_origins = list(swh_storage.origin_search(data.origin["url"])) assert len(found_origins) == 1 if "id" in found_origins[0]: del found_origins[0]["id"] assert found_origins[0] == origin_data found_origins = list( swh_storage.origin_search("." + data.origin["url"][1:-1] + ".", regexp=True) ) assert len(found_origins) == 1 if "id" in found_origins[0]: del found_origins[0]["id"] assert found_origins[0] == origin_data swh_storage.origin_add_one(data.origin2) origin2_data = {"url": data.origin2["url"]} found_origins = list(swh_storage.origin_search(data.origin2["url"])) assert len(found_origins) == 1 if "id" in found_origins[0]: del found_origins[0]["id"] assert found_origins[0] == origin2_data found_origins = list( swh_storage.origin_search( "." + data.origin2["url"][1:-1] + ".", regexp=True ) ) assert len(found_origins) == 1 if "id" in found_origins[0]: del found_origins[0]["id"] assert found_origins[0] == origin2_data def test_origin_search_no_regexp(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({"url": data.origin["url"]}) origin2 = swh_storage.origin_get({"url": data.origin2["url"]}) # no pagination found_origins = list(swh_storage.origin_search("/")) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search("/", offset=0, limit=1)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search("/", offset=1, limit=1)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_substring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({"url": data.origin["url"]}) origin2 = swh_storage.origin_get({"url": data.origin2["url"]}) # no pagination found_origins = list(swh_storage.origin_search("/", regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list( swh_storage.origin_search("/", offset=0, limit=1, regexp=True) ) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list( swh_storage.origin_search("/", offset=1, limit=1, regexp=True) ) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_fullstring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({"url": data.origin["url"]}) origin2 = swh_storage.origin_get({"url": data.origin2["url"]}) # no pagination found_origins = list(swh_storage.origin_search(".*/.*", regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list( swh_storage.origin_search(".*/.*", offset=0, limit=1, regexp=True) ) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list( swh_storage.origin_search(".*/.*", offset=1, limit=1, regexp=True) ) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_visit_add(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) date_visit = now() # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) # when origin_visit = swh_storage.origin_visit_add( origin_url, type=data.type_visit1, date=date_visit ) expected_origin_visit = { "origin": origin_url, "date": date_visit, "visit": origin_visit.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } assert origin_visit == OriginVisit.from_dict(expected_origin_visit) actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) assert expected_origin_visit in actual_origin_visits objects = list(swh_storage.journal_writer.journal.objects) assert ("origin", Origin.from_dict(data.origin2)) in objects assert ("origin_visit", OriginVisit.from_dict(expected_origin_visit)) in objects def test_origin_visit_get__unknown_origin(self, swh_storage): assert [] == list(swh_storage.origin_visit_get("foo")) def test_origin_visit_add_default_type(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when date_visit = now() date_visit2 = date_visit + datetime.timedelta(minutes=1) # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( microsecond=round(date_visit2.microsecond, -3) ) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) # then assert origin_visit1.origin == origin_url assert origin_visit1.visit is not None actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) expected_visits = [ { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, }, { "origin": origin_url, "date": date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, }, ] assert len(expected_visits) == len(actual_origin_visits) for visit in expected_visits: assert visit in actual_origin_visits objects = list(swh_storage.journal_writer.journal.objects) assert ("origin", Origin.from_dict(data.origin2)) in objects for visit in expected_visits: assert ("origin_visit", OriginVisit.from_dict(visit)) in objects def test_origin_visit_add_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin2) with pytest.raises(StorageArgumentException) as cm: swh_storage.origin_visit_add(origin_url, date=[b"foo"], type="git") if type(cm.value) == psycopg2.ProgrammingError: assert cm.value.pgcode == psycopg2.errorcodes.UNDEFINED_FUNCTION def test_origin_visit_update(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) origin_url2 = swh_storage.origin_add_one(data.origin2) # date_visit < date_visit2 date_visit = data.date_visit1 date_visit2 = data.date_visit2 # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( microsecond=round(date_visit2.microsecond, -3) ) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) origin_visit3 = swh_storage.origin_visit_add( origin_url2, date=date_visit2, type=data.type_visit3 ) # when visit1_metadata = { "contents": 42, "directories": 22, } swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="full", metadata=visit1_metadata ) swh_storage.origin_visit_update( origin_url2, origin_visit3.visit, status="partial" ) # then actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) expected_visits = [ { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": visit1_metadata, "snapshot": None, }, { "origin": origin_url, "date": date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, }, ] for visit in expected_visits: assert visit in actual_origin_visits actual_origin_visits_bis = list( swh_storage.origin_visit_get(origin_url, limit=1) ) assert actual_origin_visits_bis == [ { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": visit1_metadata, "snapshot": None, } ] actual_origin_visits_ter = list( swh_storage.origin_visit_get(origin_url, last_visit=origin_visit1.visit) ) assert actual_origin_visits_ter == [ { "origin": origin_url, "date": date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, } ] actual_origin_visits2 = list(swh_storage.origin_visit_get(origin_url2)) assert actual_origin_visits2 == [ { "origin": origin_url2, "date": date_visit2, "visit": origin_visit3.visit, "type": data.type_visit3, "status": "partial", "metadata": None, "snapshot": None, } ] data1 = { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, } data3 = { "origin": origin_url2, "date": date_visit2, "visit": origin_visit3.visit, "type": data.type_visit3, "status": "ongoing", "metadata": None, "snapshot": None, } data4 = { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "metadata": visit1_metadata, "status": "full", "snapshot": None, } data5 = { "origin": origin_url2, "date": date_visit2, "visit": origin_visit3.visit, "type": data.type_visit3, "status": "partial", "metadata": None, "snapshot": None, } objects = list(swh_storage.journal_writer.journal.objects) assert ("origin", Origin.from_dict(data.origin)) in objects assert ("origin", Origin.from_dict(data.origin2)) in objects assert ("origin_visit", OriginVisit.from_dict(data1)) in objects assert ("origin_visit", OriginVisit.from_dict(data2)) in objects assert ("origin_visit", OriginVisit.from_dict(data3)) in objects assert ("origin_visit", OriginVisit.from_dict(data4)) in objects assert ("origin_visit", OriginVisit.from_dict(data5)) in objects def test_origin_visit_update_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) with pytest.raises( (StorageArgumentException, ValueError), match="status" ) as cm: swh_storage.origin_visit_update(origin_url, visit.visit, status="foobar") if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_origin_visit_find_by_date(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit3, type=data.type_visit2 ) origin_visit3 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit3 ) # Simple case visit = swh_storage.origin_visit_find_by_date(origin_url, data.date_visit3) assert visit["visit"] == origin_visit2.visit # There are two visits at the same date, the latest must be returned visit = swh_storage.origin_visit_find_by_date(origin_url, data.date_visit2) assert visit["visit"] == origin_visit3.visit def test_origin_visit_find_by_date__unknown_origin(self, swh_storage): swh_storage.origin_visit_find_by_date("foo", data.date_visit2) def test_origin_visit_update_missing_snapshot(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) origin_visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) # when swh_storage.origin_visit_update( origin_url, origin_visit.visit, status="ongoing", snapshot=data.snapshot["id"], ) # snapshot does not exist yet # then actual_origin_visit = swh_storage.origin_visit_get_by( origin_url, origin_visit.visit ) assert actual_origin_visit["snapshot"] == data.snapshot["id"] # when swh_storage.snapshot_add([data.snapshot]) assert actual_origin_visit["snapshot"] == data.snapshot["id"] def test_origin_visit_get_by(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_url2 = swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.snapshot["id"], ) # Add some other {origin, visit} entries swh_storage.origin_visit_add( origin_url, date=data.date_visit3, type=data.type_visit3 ) swh_storage.origin_visit_add( origin_url2, date=data.date_visit3, type=data.type_visit3 ) # when visit1_metadata = { "contents": 42, "directories": 22, } swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="full", metadata=visit1_metadata ) expected_origin_visit = origin_visit1.to_dict() expected_origin_visit.update( { "origin": origin_url, "visit": origin_visit1.visit, "date": data.date_visit2, "type": data.type_visit2, "metadata": visit1_metadata, "status": "full", "snapshot": data.snapshot["id"], } ) # when actual_origin_visit1 = swh_storage.origin_visit_get_by( origin_url, origin_visit1.visit ) # then assert actual_origin_visit1 == expected_origin_visit def test_origin_visit_get_by__unknown_origin(self, swh_storage): assert swh_storage.origin_visit_get_by("foo", 10) is None def test_origin_visit_upsert_new(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when swh_storage.origin_visit_upsert( [ OriginVisit.from_dict( { "origin": origin_url, "date": data.date_visit2, "visit": 123, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, } ), OriginVisit.from_dict( { "origin": origin_url, "date": "2018-01-01 23:00:00+00", "visit": 1234, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, } ), ] ) # then actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) assert actual_origin_visits == [ { "origin": origin_url, "date": data.date_visit2, "visit": 123, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, }, { "origin": origin_url, "date": data.date_visit3, "visit": 1234, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, }, ] data1 = { "origin": origin_url, "date": data.date_visit2, "visit": 123, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": data.date_visit3, "visit": 1234, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, } assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin2)), ("origin_visit", OriginVisit.from_dict(data1)), ("origin_visit", OriginVisit.from_dict(data2)), ] def test_origin_visit_upsert_existing(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1 ) swh_storage.origin_visit_upsert( [ OriginVisit.from_dict( { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } ) ] ) # then assert origin_visit1.origin == origin_url assert origin_visit1.visit is not None actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) assert actual_origin_visits == [ { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } ] data1 = { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin2)), ("origin_visit", OriginVisit.from_dict(data1)), ("origin_visit", OriginVisit.from_dict(data2)), ] def test_origin_visit_upsert_missing_visit_id(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # then with pytest.raises(StorageArgumentException, match="Missing visit id"): swh_storage.origin_visit_upsert( [ OriginVisit.from_dict( { "origin": origin_url, "date": data.date_visit2, "visit": None, # <- make the test raise "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } ) ] ) assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin2)) ] def test_origin_visit_get_by_no_result(self, swh_storage): swh_storage.origin_add([data.origin]) actual_origin_visit = swh_storage.origin_visit_get_by(data.origin["url"], 999) assert actual_origin_visit is None def test_origin_visit_get_latest(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) ov1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) ov2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) # Add a visit with the same date as the previous one ov3 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) origin_visit1 = swh_storage.origin_visit_get_by(origin_url, ov1.visit) origin_visit2 = swh_storage.origin_visit_get_by(origin_url, ov2.visit) origin_visit3 = swh_storage.origin_visit_get_by(origin_url, ov3.visit) # Two visits, both with no snapshot assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) assert ( swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) is None ) # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, ov1.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) assert { **origin_visit1, "snapshot": data.complete_snapshot["id"], } == swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no visit # returned assert ( swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) is None ) # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update(origin_url, ov1.visit, status="full") assert { **origin_visit1, "snapshot": data.complete_snapshot["id"], "status": "full", } == swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, ov2.visit, status="ongoing", snapshot=data.empty_snapshot["id"] ) assert { **origin_visit2, "snapshot": data.empty_snapshot["id"], } == swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Check that the status filter is still working assert { **origin_visit1, "snapshot": data.complete_snapshot["id"], "status": "full", } == swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) # Add snapshot to visit3 (same date as visit2) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, ov3.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) assert { **origin_visit1, "snapshot": data.complete_snapshot["id"], "status": "full", } == swh_storage.origin_visit_get_latest(origin_url, allowed_statuses=["full"]) assert { **origin_visit1, "snapshot": data.complete_snapshot["id"], "status": "full", } == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=["full"], require_snapshot=True ) assert { **origin_visit3, "snapshot": data.complete_snapshot["id"], } == swh_storage.origin_visit_get_latest(origin_url) assert { **origin_visit3, "snapshot": data.complete_snapshot["id"], } == swh_storage.origin_visit_get_latest(origin_url, require_snapshot=True) def test_person_fullname_unicity(self, swh_storage): # given (person injection through revisions for example) revision = data.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(data.revision2) revision2["committer"] = dict(revision["committer"]) revision2["committer"]["email"] = None revision2["committer"]["name"] = None swh_storage.revision_add([revision]) swh_storage.revision_add([revision2]) # when getting added revisions revisions = list(swh_storage.revision_get([revision["id"], revision2["id"]])) # then # check committers are the same assert revisions[0]["committer"] == revisions[1]["committer"] def test_snapshot_add_get_empty(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) visit_id = origin_visit1.visit actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {"snapshot:add": 1} swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.empty_snapshot["id"], ) by_id = swh_storage.snapshot_get(data.empty_snapshot["id"]) assert by_id == {**data.empty_snapshot, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.empty_snapshot, "next_branch": None} data1 = { "origin": origin_url, "date": data.date_visit1, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": data.date_visit1, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": data.empty_snapshot["id"], } assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin_visit", OriginVisit.from_dict(data1)), ("snapshot", Snapshot.from_dict(data.empty_snapshot)), ("origin_visit", OriginVisit.from_dict(data2)), ] def test_snapshot_add_get_complete(self, swh_storage): origin_url = data.origin["url"] origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) visit_id = origin_visit1.visit actual_result = swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) assert actual_result == {"snapshot:add": 1} by_id = swh_storage.snapshot_get(data.complete_snapshot["id"]) assert by_id == {**data.complete_snapshot, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.complete_snapshot, "next_branch": None} def test_snapshot_add_many(self, swh_storage): actual_result = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot] ) assert actual_result == {"snapshot:add": 2} assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get(data.complete_snapshot["id"]) assert {**data.snapshot, "next_branch": None} == swh_storage.snapshot_get( data.snapshot["id"] ) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_from_generator(self, swh_storage): def _snp_gen(): yield data.snapshot yield data.complete_snapshot actual_result = swh_storage.snapshot_add(_snp_gen()) assert actual_result == {"snapshot:add": 2} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_incremental(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {"snapshot:add": 1} actual_result2 = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot] ) assert actual_result2 == {"snapshot:add": 1} assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get(data.complete_snapshot["id"]) assert {**data.snapshot, "next_branch": None} == swh_storage.snapshot_get( data.snapshot["id"] ) def test_snapshot_add_twice(self, swh_storage): actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", Snapshot.from_dict(data.empty_snapshot)) ] actual_result = swh_storage.snapshot_add([data.snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", Snapshot.from_dict(data.empty_snapshot)), ("snapshot", Snapshot.from_dict(data.snapshot)), ] def test_snapshot_add_validation(self, swh_storage): snap = copy.deepcopy(data.snapshot) snap["branches"][b"foo"] = {"target_type": "revision"} with pytest.raises(StorageArgumentException, match="target"): swh_storage.snapshot_add([snap]) snap = copy.deepcopy(data.snapshot) snap["branches"][b"foo"] = {"target": b"\x42" * 20} with pytest.raises(StorageArgumentException, match="target_type"): swh_storage.snapshot_add([snap]) def test_snapshot_add_count_branches(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {"snapshot:add": 1} snp_id = data.complete_snapshot["id"] snp_size = swh_storage.snapshot_count_branches(snp_id) expected_snp_size = { "alias": 1, "content": 1, "directory": 2, "release": 1, "revision": 1, "snapshot": 1, None: 1, } assert snp_size == expected_snp_size def test_snapshot_add_get_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot["id"] branches = data.complete_snapshot["branches"] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches(snp_id, branches_from=b"release") rel_idx = branch_names.index(b"release") expected_snapshot = { "id": snp_id, "branches": {name: branches[name] for name in branch_names[rel_idx:]}, "next_branch": None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches(snp_id, branches_count=1) expected_snapshot = { "id": snp_id, "branches": {branch_names[0]: branches[branch_names[0]],}, "next_branch": b"content", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b"directory", branches_count=3 ) dir_idx = branch_names.index(b"directory") expected_snapshot = { "id": snp_id, "branches": { name: branches[name] for name in branch_names[dir_idx : dir_idx + 3] }, "next_branch": branch_names[dir_idx + 3], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) snp_id = data.complete_snapshot["id"] branches = data.complete_snapshot["branches"] snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["release", "revision"] ) expected_snapshot = { "id": snp_id, "branches": { name: tgt for name, tgt in branches.items() if tgt and tgt["target_type"] in ["release", "revision"] }, "next_branch": None, } assert snapshot == expected_snapshot snapshot = swh_storage.snapshot_get_branches(snp_id, target_types=["alias"]) expected_snapshot = { "id": snp_id, "branches": { name: tgt for name, tgt in branches.items() if tgt and tgt["target_type"] == "alias" }, "next_branch": None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot["id"] branches = data.complete_snapshot["branches"] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2" ) expected_snapshot = { "id": snp_id, "branches": {name: branches[name] for name in (b"directory2", b"release")}, "next_branch": None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=1 ) expected_snapshot = { "id": snp_id, "branches": {b"directory": branches[b"directory"]}, "next_branch": b"directory2", } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=2 ) expected_snapshot = { "id": snp_id, "branches": { name: branches[name] for name in (b"directory", b"directory2") }, "next_branch": b"release", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2", branches_count=1, ) dir_idx = branch_names.index(b"directory2") expected_snapshot = { "id": snp_id, "branches": {branch_names[dir_idx]: branches[branch_names[dir_idx]],}, "next_branch": b"release", } assert snapshot == expected_snapshot def test_snapshot_add_get(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) visit_id = origin_visit1.visit swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.snapshot["id"], ) by_id = swh_storage.snapshot_get(data.snapshot["id"]) assert by_id == {**data.snapshot, "next_branch": None} by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.snapshot, "next_branch": None} origin_visit_info = swh_storage.origin_visit_get_by(origin_url, visit_id) assert origin_visit_info["snapshot"] == data.snapshot["id"] def test_snapshot_add_nonexistent_visit(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) # unknown visit visit_id = 54164461156 swh_storage.journal_writer.journal.objects[:] = [] swh_storage.snapshot_add([data.snapshot]) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_update( origin_url, visit_id, status="ongoing", snapshot=data.snapshot["id"] ) assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", Snapshot.from_dict(data.snapshot)) ] def test_snapshot_add_twice__by_origin_visit(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) visit1_id = origin_visit1.visit swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.snapshot["id"], ) by_ov1 = swh_storage.snapshot_get_by_origin_visit(origin_url, visit1_id) assert by_ov1 == {**data.snapshot, "next_branch": None} origin_visit2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) visit2_id = origin_visit2.visit swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit2.visit, status="ongoing", snapshot=data.snapshot["id"], ) by_ov2 = swh_storage.snapshot_get_by_origin_visit(origin_url, visit2_id) assert by_ov2 == {**data.snapshot, "next_branch": None} data1 = { "origin": origin_url, "date": data.date_visit1, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": data.date_visit1, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": data.snapshot["id"], } data3 = { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, } data4 = { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": data.snapshot["id"], } assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin_visit", OriginVisit.from_dict(data1)), ("snapshot", Snapshot.from_dict(data.snapshot)), ("origin_visit", OriginVisit.from_dict(data2)), ("origin_visit", OriginVisit.from_dict(data3)), ("origin_visit", OriginVisit.from_dict(data4)), ] def test_snapshot_get_latest(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit3 ) # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add snapshot to visit1, latest snapshot = visit 1 snapshot swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no snapshot # returned assert ( swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) is None ) # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update(origin_url, origin_visit1.visit, status="full") assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit2.visit, status="ongoing", snapshot=data.empty_snapshot["id"], ) assert { **data.empty_snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url) # Check that the status filter is still working assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit3.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_latest__missing_snapshot(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) assert swh_storage.snapshot_get_latest(origin_url) is None origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add unknown snapshot to visit1, check that the inconsistency is # detected swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) with pytest.raises(Exception): # XXX: should the exception be more specific than this? swh_storage.snapshot_get_latest(origin_url) # Status filter: both visits are status=ongoing, so no snapshot # returned assert ( swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]) is None ) # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update(origin_url, origin_visit1.visit, status="full") with pytest.raises(Exception): # XXX: should the exception be more specific than this? swh_storage.snapshot_get_latest(origin_url, allowed_statuses=["full"]), # Actually add the snapshot and check status filter again swh_storage.snapshot_add([data.complete_snapshot]) assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url) # Add unknown snapshot to visit2 and check that the inconsistency # is detected swh_storage.origin_visit_update( origin_url, origin_visit2.visit, status="ongoing", snapshot=data.snapshot["id"], ) with pytest.raises(Exception): # XXX: should the exception be more specific than this? swh_storage.snapshot_get_latest(origin_url) # Actually add that snapshot and check that the new one is returned swh_storage.snapshot_add([data.snapshot]) assert { **data.snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_random(self, swh_storage): swh_storage.snapshot_add( [data.snapshot, data.empty_snapshot, data.complete_snapshot] ) assert swh_storage.snapshot_get_random() in { data.snapshot["id"], data.empty_snapshot["id"], data.complete_snapshot["id"], } def test_snapshot_missing(self, swh_storage): snap = data.snapshot missing_snap = data.empty_snapshot snapshots = [snap["id"], missing_snap["id"]] swh_storage.snapshot_add([snap]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snap["id"]] def test_stat_counters(self, swh_storage): expected_keys = ["content", "directory", "origin", "revision"] # Initially, all counters are 0 swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: assert counters[key] == 0 # Add a content. Only the content counter should increase. swh_storage.content_add([data.cont]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: if key != "content": assert counters[key] == 0 assert counters["content"] == 1 # Add other objects. Check their counter increased as well. origin_url = swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.snapshot["id"], ) swh_storage.directory_add([data.dir]) swh_storage.revision_add([data.revision]) swh_storage.release_add([data.release]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert counters["content"] == 1 assert counters["directory"] == 1 assert counters["snapshot"] == 1 assert counters["origin"] == 1 assert counters["origin_visit"] == 1 assert counters["revision"] == 1 assert counters["release"] == 1 assert counters["snapshot"] == 1 if "person" in counters: assert counters["person"] == 3 def test_content_find_ctime(self, swh_storage): cont = data.cont.copy() del cont["data"] ctime = now() cont["ctime"] = ctime swh_storage.content_add_metadata([cont]) actually_present = swh_storage.content_find({"sha1": cont["sha1"]}) # check ctime up to one second dt = actually_present[0]["ctime"] - ctime assert abs(dt.total_seconds()) <= 1 del actually_present[0]["ctime"] assert actually_present[0] == { "sha1": cont["sha1"], "sha256": cont["sha256"], "sha1_git": cont["sha1_git"], "blake2s256": cont["blake2s256"], "length": cont["length"], "status": "visible", } def test_content_find_with_present_content(self, swh_storage): # 1. with something to find cont = data.cont swh_storage.content_add([cont, data.cont2]) actually_present = swh_storage.content_find({"sha1": cont["sha1"]}) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == { "sha1": cont["sha1"], "sha256": cont["sha256"], "sha1_git": cont["sha1_git"], "blake2s256": cont["blake2s256"], "length": cont["length"], "status": "visible", } # 2. with something to find actually_present = swh_storage.content_find({"sha1_git": cont["sha1_git"]}) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == { "sha1": cont["sha1"], "sha256": cont["sha256"], "sha1_git": cont["sha1_git"], "blake2s256": cont["blake2s256"], "length": cont["length"], "status": "visible", } # 3. with something to find actually_present = swh_storage.content_find({"sha256": cont["sha256"]}) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == { "sha1": cont["sha1"], "sha256": cont["sha256"], "sha1_git": cont["sha1_git"], "blake2s256": cont["blake2s256"], "length": cont["length"], "status": "visible", } # 4. with something to find actually_present = swh_storage.content_find( { "sha1": cont["sha1"], "sha1_git": cont["sha1_git"], "sha256": cont["sha256"], "blake2s256": cont["blake2s256"], } ) assert 1 == len(actually_present) actually_present[0].pop("ctime") assert actually_present[0] == { "sha1": cont["sha1"], "sha256": cont["sha256"], "sha1_git": cont["sha1_git"], "blake2s256": cont["blake2s256"], "length": cont["length"], "status": "visible", } def test_content_find_with_non_present_content(self, swh_storage): # 1. with something that does not exist missing_cont = data.missing_cont actually_present = swh_storage.content_find({"sha1": missing_cont["sha1"]}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {"sha1_git": missing_cont["sha1_git"]} ) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find({"sha256": missing_cont["sha256"]}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont["sha1"]) sha1_array[0] += 1 duplicate_cont["sha1"] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont["sha1_git"]) sha1git_array[0] += 1 duplicate_cont["sha1_git"] = bytes(sha1git_array) # Inject the data swh_storage.content_add([cont1, duplicate_cont]) finder = { "blake2s256": duplicate_cont["blake2s256"], "sha256": duplicate_cont["sha256"], } actual_result = list(swh_storage.content_find(finder)) cont1.pop("data") duplicate_cont.pop("data") actual_result[0].pop("ctime") actual_result[1].pop("ctime") expected_result = [cont1, duplicate_cont] for result in expected_result: assert result in actual_result def test_content_find_with_duplicate_sha256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 for hashalgo in ("sha1", "sha1_git", "blake2s256"): value = bytearray(duplicate_cont[hashalgo]) value[0] += 1 duplicate_cont[hashalgo] = bytes(value) swh_storage.content_add([cont1, duplicate_cont]) finder = {"sha256": duplicate_cont["sha256"]} actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 2 cont1.pop("data") duplicate_cont.pop("data") actual_result[0].pop("ctime") actual_result[1].pop("ctime") expected_result = [cont1, duplicate_cont] assert expected_result == sorted(actual_result, key=lambda x: x["sha1"]) # Find with both sha256 and blake2s256 finder = { "sha256": duplicate_cont["sha256"], "blake2s256": duplicate_cont["blake2s256"], } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 1 actual_result[0].pop("ctime") expected_result = [duplicate_cont] assert actual_result[0] == duplicate_cont def test_content_find_with_duplicate_blake2s256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont["sha1"]) sha1_array[0] += 1 duplicate_cont["sha1"] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont["sha1_git"]) sha1git_array[0] += 1 duplicate_cont["sha1_git"] = bytes(sha1git_array) sha256_array = bytearray(duplicate_cont["sha256"]) sha256_array[0] += 1 duplicate_cont["sha256"] = bytes(sha256_array) swh_storage.content_add([cont1, duplicate_cont]) finder = {"blake2s256": duplicate_cont["blake2s256"]} actual_result = list(swh_storage.content_find(finder)) cont1.pop("data") duplicate_cont.pop("data") actual_result[0].pop("ctime") actual_result[1].pop("ctime") expected_result = [cont1, duplicate_cont] for result in expected_result: assert result in actual_result # Find with both sha256 and blake2s256 finder = { "sha256": duplicate_cont["sha256"], "blake2s256": duplicate_cont["blake2s256"], } actual_result = list(swh_storage.content_find(finder)) actual_result[0].pop("ctime") expected_result = [duplicate_cont] assert expected_result == actual_result def test_content_find_bad_input(self, swh_storage): # 1. with bad input with pytest.raises(StorageArgumentException): swh_storage.content_find({}) # empty is bad # 2. with bad input with pytest.raises(StorageArgumentException): swh_storage.content_find({"unknown-sha1": "something"}) # not the right key def test_object_find_by_sha1_git(self, swh_storage): sha1_gits = [b"00000000000000000000"] expected = { b"00000000000000000000": [], } swh_storage.content_add([data.cont]) sha1_gits.append(data.cont["sha1_git"]) expected[data.cont["sha1_git"]] = [ {"sha1_git": data.cont["sha1_git"], "type": "content",} ] swh_storage.directory_add([data.dir]) sha1_gits.append(data.dir["id"]) expected[data.dir["id"]] = [{"sha1_git": data.dir["id"], "type": "directory",}] swh_storage.revision_add([data.revision]) sha1_gits.append(data.revision["id"]) expected[data.revision["id"]] = [ {"sha1_git": data.revision["id"], "type": "revision",} ] swh_storage.release_add([data.release]) sha1_gits.append(data.release["id"]) expected[data.release["id"]] = [ {"sha1_git": data.release["id"], "type": "release",} ] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_metadata_fetcher_add_get(self, swh_storage): actual_fetcher = swh_storage.metadata_fetcher_get( data.metadata_fetcher["name"], data.metadata_fetcher["version"] ) assert actual_fetcher is None # does not exist swh_storage.metadata_fetcher_add(**data.metadata_fetcher) res = swh_storage.metadata_fetcher_get( data.metadata_fetcher["name"], data.metadata_fetcher["version"] ) assert res is not data.metadata_fetcher assert res == data.metadata_fetcher def test_metadata_authority_add_get(self, swh_storage): actual_authority = swh_storage.metadata_authority_get( data.metadata_authority["type"], data.metadata_authority["url"] ) assert actual_authority is None # does not exist swh_storage.metadata_authority_add(**data.metadata_authority) res = swh_storage.metadata_authority_get( data.metadata_authority["type"], data.metadata_authority["url"] ) assert res is not data.metadata_authority assert res == data.metadata_authority def test_origin_metadata_add(self, swh_storage): origin = data.origin fetcher = data.metadata_fetcher authority = data.metadata_authority swh_storage.origin_add([origin])[0] swh_storage.metadata_fetcher_add(**fetcher) swh_storage.metadata_authority_add(**authority) swh_storage.origin_metadata_add(**data.origin_metadata) swh_storage.origin_metadata_add(**data.origin_metadata2) swh_storage.origin_metadata_get(origin["url"], authority) assert [data.origin_metadata, data.origin_metadata2] == list( sorted( swh_storage.origin_metadata_get(origin["url"], authority), key=lambda x: x["discovery_date"], ) ) def test_origin_metadata_add_dict(self, swh_storage): origin = data.origin fetcher = data.metadata_fetcher authority = data.metadata_authority swh_storage.origin_add([origin])[0] swh_storage.metadata_fetcher_add(**fetcher) swh_storage.metadata_authority_add(**authority) kwargs = data.origin_metadata.copy() kwargs["metadata"] = {"foo": "bar"} with pytest.raises(StorageArgumentException): swh_storage.origin_metadata_add(**kwargs) def test_origin_metadata_get(self, swh_storage): authority = data.metadata_authority fetcher = data.metadata_fetcher authority2 = data.metadata_authority2 fetcher2 = data.metadata_fetcher2 origin_url1 = data.origin["url"] origin_url2 = data.origin2["url"] swh_storage.origin_add([data.origin]) swh_storage.origin_add([data.origin2]) origin1_metadata1 = data.origin_metadata origin1_metadata2 = data.origin_metadata2 origin1_metadata3 = data.origin_metadata3 origin2_metadata = {**data.origin_metadata2, "origin_url": origin_url2} swh_storage.metadata_authority_add(**authority) swh_storage.metadata_fetcher_add(**fetcher) swh_storage.metadata_authority_add(**authority2) swh_storage.metadata_fetcher_add(**fetcher2) swh_storage.origin_metadata_add(**origin1_metadata1) swh_storage.origin_metadata_add(**origin1_metadata2) swh_storage.origin_metadata_add(**origin1_metadata3) swh_storage.origin_metadata_add(**origin2_metadata) assert [origin1_metadata1, origin1_metadata2] == list( sorted( swh_storage.origin_metadata_get(origin_url1, authority), key=lambda x: x["discovery_date"], ) ) assert [origin1_metadata3] == list( sorted( swh_storage.origin_metadata_get(origin_url1, authority2), key=lambda x: x["discovery_date"], ) ) assert [origin2_metadata] == list( swh_storage.origin_metadata_get(origin_url2, authority) ) class TestStorageGeneratedData: def test_generate_content_get(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c["status"] != "absent"] # input the list of sha1s we want from storage get_sha1s = [c["sha1"] for c in contents_with_data] # retrieve contents actual_contents = list(swh_storage.content_get(get_sha1s)) assert None not in actual_contents assert_contents_ok(contents_with_data, actual_contents) def test_generate_content_get_metadata(self, swh_storage, swh_contents): # input the list of sha1s we want from storage expected_contents = [c for c in swh_contents if c["status"] != "absent"] get_sha1s = [c["sha1"] for c in expected_contents] # retrieve contents meta_contents = swh_storage.content_get_metadata(get_sha1s) assert len(list(meta_contents)) == len(get_sha1s) actual_contents = [] for contents in meta_contents.values(): actual_contents.extend(contents) keys_to_check = {"length", "status", "sha1", "sha1_git", "sha256", "blake2s256"} assert_contents_ok( expected_contents, actual_contents, keys_to_check=keys_to_check ) def test_generate_content_get_range(self, swh_storage, swh_contents): """content_get_range returns complete range""" present_contents = [c for c in swh_contents if c["status"] != "absent"] get_sha1s = sorted([c["sha1"] for c in swh_contents if c["status"] != "absent"]) start = get_sha1s[2] end = get_sha1s[-2] actual_result = swh_storage.content_get_range(start, end) assert actual_result["next"] is None actual_contents = actual_result["contents"] expected_contents = [c for c in present_contents if start <= c["sha1"] <= end] if expected_contents: assert_contents_ok(expected_contents, actual_contents, ["sha1"]) else: assert actual_contents == [] def test_generate_content_get_range_full(self, swh_storage, swh_contents): """content_get_range for a full range returns all available contents""" present_contents = [c for c in swh_contents if c["status"] != "absent"] start = b"0" * 40 end = b"f" * 40 actual_result = swh_storage.content_get_range(start, end) assert actual_result["next"] is None actual_contents = actual_result["contents"] expected_contents = [c for c in present_contents if start <= c["sha1"] <= end] if expected_contents: assert_contents_ok(expected_contents, actual_contents, ["sha1"]) else: assert actual_contents == [] def test_generate_content_get_range_empty(self, swh_storage, swh_contents): """content_get_range for an empty range returns nothing""" start = b"0" * 40 end = b"f" * 40 actual_result = swh_storage.content_get_range(end, start) assert actual_result["next"] is None assert len(actual_result["contents"]) == 0 def test_generate_content_get_range_limit_none(self, swh_storage): """content_get_range call with wrong limit input should fail""" with pytest.raises(StorageArgumentException) as e: swh_storage.content_get_range(start=None, end=None, limit=None) assert e.value.args == ("limit should not be None",) def test_generate_content_get_range_no_limit(self, swh_storage, swh_contents): """content_get_range returns contents within range provided""" # input the list of sha1s we want from storage get_sha1s = sorted([c["sha1"] for c in swh_contents if c["status"] != "absent"]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = swh_storage.content_get_range(start, end) actual_contents = actual_result["contents"] assert actual_result["next"] is None assert len(actual_contents) == len(get_sha1s) expected_contents = [c for c in swh_contents if c["status"] != "absent"] assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_generate_content_get_range_limit(self, swh_storage, swh_contents): """content_get_range paginates results if limit exceeded""" contents_map = {c["sha1"]: c for c in swh_contents} # input the list of sha1s we want from storage get_sha1s = sorted([c["sha1"] for c in swh_contents if c["status"] != "absent"]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to n-1 results limited_results = len(get_sha1s) - 1 actual_result = swh_storage.content_get_range(start, end, limit=limited_results) actual_contents = actual_result["contents"] assert actual_result["next"] == get_sha1s[-1] assert len(actual_contents) == limited_results expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] assert_contents_ok(expected_contents, actual_contents, ["sha1"]) # retrieve next part actual_results2 = swh_storage.content_get_range(start=end, end=end) assert actual_results2["next"] is None actual_contents2 = actual_results2["contents"] assert len(actual_contents2) == 1 assert_contents_ok([contents_map[get_sha1s[-1]]], actual_contents2, ["sha1"]) def test_origin_get_range_from_zero(self, swh_storage, swh_origins): actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=0) ) assert len(actual_origins) == 0 actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=1) ) assert len(actual_origins) == 1 assert actual_origins[0]["id"] == 1 assert actual_origins[0]["url"] == swh_origins[0]["url"] @pytest.mark.parametrize( "origin_from,origin_count", [(1, 1), (1, 10), (1, 20), (1, 101), (11, 0), (11, 10), (91, 11)], ) def test_origin_get_range( self, swh_storage, swh_origins, origin_from, origin_count ): actual_origins = list( swh_storage.origin_get_range( origin_from=origin_from, origin_count=origin_count ) ) origins_with_id = list(enumerate(swh_origins, start=1)) expected_origins = [ {"url": origin["url"], "id": origin_id,} for (origin_id, origin) in origins_with_id[ origin_from - 1 : origin_from + origin_count - 1 ] ] assert actual_origins == expected_origins @pytest.mark.parametrize("limit", [1, 7, 10, 100, 1000]) def test_origin_list(self, swh_storage, swh_origins, limit): returned_origins = [] page_token = None i = 0 while True: result = swh_storage.origin_list(page_token=page_token, limit=limit) assert len(result["origins"]) <= limit returned_origins.extend(origin["url"] for origin in result["origins"]) i += 1 page_token = result.get("next_page_token") if page_token is None: assert i * limit >= len(swh_origins) break else: assert len(result["origins"]) == limit expected_origins = [origin["url"] for origin in swh_origins] assert sorted(returned_origins) == sorted(expected_origins) ORIGINS = [ "https://github.com/user1/repo1", "https://github.com/user2/repo1", "https://github.com/user3/repo1", "https://gitlab.com/user1/repo1", "https://gitlab.com/user2/repo1", "https://forge.softwareheritage.org/source/repo1", ] def test_origin_count(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) assert swh_storage.origin_count("github") == 3 assert swh_storage.origin_count("gitlab") == 2 assert swh_storage.origin_count(".*user.*", regexp=True) == 5 assert swh_storage.origin_count(".*user.*", regexp=False) == 0 assert swh_storage.origin_count(".*user1.*", regexp=True) == 2 assert swh_storage.origin_count(".*user1.*", regexp=False) == 0 def test_origin_count_with_visit_no_visits(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) # none of them have visits, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=False, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=False, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_no_snapshot(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) origin_url = "https://github.com/user1/repo1" swh_storage.origin_visit_add(origin_url, date=now(), type="git") assert swh_storage.origin_count("github", with_visit=False) == 3 # it has a visit, but no snapshot, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=False) == 2 # these gitlab origins have no visit assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 0 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_and_snapshot(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) swh_storage.snapshot_add([data.snapshot]) origin_url = "https://github.com/user1/repo1" visit = swh_storage.origin_visit_add(origin_url, date=now(), type="git") swh_storage.origin_visit_update( origin_url, visit.visit, status="ongoing", snapshot=data.snapshot["id"] ) assert swh_storage.origin_count("github", with_visit=False) == 3 # github/user1 has a visit and a snapshot, so with_visit=True => 1 assert swh_storage.origin_count("github", with_visit=True) == 1 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 1 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 1 @settings(suppress_health_check=[HealthCheck.too_slow]) @given(strategies.lists(objects(), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: obj = obj.to_dict() if obj_type == "origin_visit": origin_url = obj.pop("origin") swh_storage.origin_add_one({"url": origin_url}) if "visit" in obj: del obj["visit"] swh_storage.origin_visit_add(origin_url, obj["date"], obj["type"]) elif obj_type == "origin_visit_update": # internal object for now, they don't have a storage # endpoint yet continue else: if obj_type == "content" and obj["status"] == "absent": obj_type = "skipped_content" method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self, swh_storage): swh_storage.objstorage.content_add = Mock( side_effect=Exception("mocked broken objstorage") ) with pytest.raises(Exception) as e: swh_storage.content_add([data.cont]) assert e.value.args == ("mocked broken objstorage",) missing = list(swh_storage.content_missing([data.cont])) assert missing == [data.cont["sha1"]] @pytest.mark.db class TestStorageRaceConditions: @pytest.mark.xfail def test_content_add_race(self, swh_storage): results = queue.Queue() def thread(): try: with db_transaction(swh_storage) as (db, cur): ret = swh_storage.content_add([data.cont], db=db, cur=cur) results.put((threading.get_ident(), "data", ret)) except Exception as e: results.put((threading.get_ident(), "exc", e)) t1 = threading.Thread(target=thread) t2 = threading.Thread(target=thread) t1.start() # this avoids the race condition # import time # time.sleep(1) t2.start() t1.join() t2.join() r1 = results.get(block=False) r2 = results.get(block=False) with pytest.raises(queue.Empty): results.get(block=False) assert r1[0] != r2[0] assert r1[1] == "data", "Got exception %r in Thread%s" % (r1[2], r1[0]) assert r2[1] == "data", "Got exception %r in Thread%s" % (r2[2], r2[0]) @pytest.mark.db class TestPgStorage: """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update_with_new_cols(self, swh_storage): swh_storage.journal_writer.journal = None # TODO, not supported with db_transaction(swh_storage) as (_, cur): cur.execute( """alter table content add column test text default null, add column test2 text default null""" ) cont = copy.deepcopy(data.cont2) swh_storage.content_add([cont]) cont["test"] = "value-1" cont["test2"] = "value-2" swh_storage.content_update([cont], keys=["test", "test2"]) with db_transaction(swh_storage) as (_, cur): cur.execute( """SELECT sha1, sha1_git, sha256, length, status, test, test2 FROM content WHERE sha1 = %s""", (cont["sha1"],), ) datum = cur.fetchone() assert datum == ( cont["sha1"], cont["sha1_git"], cont["sha256"], cont["length"], "visible", cont["test"], cont["test2"], ) with db_transaction(swh_storage) as (_, cur): cur.execute( """alter table content drop column test, drop column test2""" ) def test_content_add_db(self, swh_storage): cont = data.cont actual_result = swh_storage.content_add([cont]) assert actual_result == { "content:add": 1, "content:add:bytes": cont["length"], } if hasattr(swh_storage, "objstorage"): assert cont["sha1"] in swh_storage.objstorage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute( "SELECT sha1, sha1_git, sha256, length, status" " FROM content WHERE sha1 = %s", (cont["sha1"],), ) datum = cur.fetchone() assert datum == ( cont["sha1"], cont["sha1_git"], cont["sha256"], cont["length"], "visible", ) expected_cont = cont.copy() del expected_cont["data"] 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_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont def test_content_add_metadata_db(self, swh_storage): cont = data.cont del cont["data"] cont["ctime"] = now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } if hasattr(swh_storage, "objstorage"): assert cont["sha1"] not in swh_storage.objstorage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute( "SELECT sha1, sha1_git, sha256, length, status" " FROM content WHERE sha1 = %s", (cont["sha1"],), ) datum = cur.fetchone() assert datum == ( cont["sha1"], cont["sha1_git"], cont["sha256"], cont["length"], "visible", ) 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_d = obj.to_dict() assert obj_d == cont def test_skipped_content_add_db(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2["blake2s256"] = None actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} with db_transaction(swh_storage) as (_, cur): cur.execute( "SELECT sha1, sha1_git, sha256, blake2s256, " "length, status, reason " "FROM skipped_content ORDER BY sha1_git" ) dbdata = cur.fetchall() assert len(dbdata) == 2 assert dbdata[0] == ( cont["sha1"], cont["sha1_git"], cont["sha256"], cont["blake2s256"], cont["length"], "absent", "Content too long", ) assert dbdata[1] == ( cont2["sha1"], cont2["sha1_git"], cont2["sha256"], cont2["blake2s256"], cont2["length"], "absent", "Content too long", ) def test_clear_buffers(self, swh_storage): """Calling clear buffers on real storage does nothing """ assert swh_storage.clear_buffers() is None def test_flush(self, swh_storage): """Calling clear buffers on real storage does nothing """ assert swh_storage.flush() == {} diff --git a/swh/storage/tests/test_write_replay.py b/swh/storage/tests/test_write_replay.py deleted file mode 100644 index c78efe28..00000000 --- a/swh/storage/tests/test_write_replay.py +++ /dev/null @@ -1,112 +0,0 @@ -# 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 functools -from unittest.mock import patch - -import attr -from hypothesis import given, settings, HealthCheck -from hypothesis.strategies import lists - -from swh.model.hypothesis_strategies import objects -from swh.model.model import Origin -from swh.storage import get_storage -from swh.storage.exc import HashCollision - -from swh.storage.replay import process_replay_objects - -from swh.journal.tests.utils import MockedJournalClient, MockedKafkaWriter - - -storage_config = { - "cls": "memory", - "journal_writer": {"cls": "memory"}, -} - - -def empty_person_name_email(rev_or_rel): - """Empties the 'name' and 'email' fields of the author/committer fields - of a revision or release; leaving only the fullname.""" - if getattr(rev_or_rel, "author", None): - rev_or_rel = attr.evolve( - rev_or_rel, author=attr.evolve(rev_or_rel.author, name=b"", email=b"",) - ) - - if getattr(rev_or_rel, "committer", None): - rev_or_rel = attr.evolve( - rev_or_rel, - committer=attr.evolve(rev_or_rel.committer, name=b"", email=b"",), - ) - - return rev_or_rel - - -@given(lists(objects(blacklist_types=("origin_visit_status",)), min_size=1)) -@settings(suppress_health_check=[HealthCheck.too_slow]) -def test_write_replay_same_order_batches(objects): - queue = [] - replayer = MockedJournalClient(queue) - - with patch( - "swh.journal.writer.inmemory.InMemoryJournalWriter", - return_value=MockedKafkaWriter(queue), - ): - storage1 = get_storage(**storage_config) - - # Write objects to storage1 - for (obj_type, obj) in objects: - if obj_type == "content" and obj.status == "absent": - obj_type = "skipped_content" - - if obj_type == "origin_visit": - storage1.origin_add_one(Origin(url=obj.origin)) - storage1.origin_visit_upsert([obj]) - else: - method = getattr(storage1, obj_type + "_add") - try: - method([obj]) - except HashCollision: - pass - - # Bail out early if we didn't insert any relevant objects... - queue_size = len(queue) - assert queue_size != 0, "No test objects found; hypothesis strategy bug?" - - assert replayer.stop_after_objects is None - replayer.stop_after_objects = queue_size - - storage2 = get_storage(**storage_config) - worker_fn = functools.partial(process_replay_objects, storage=storage2) - - replayer.process(worker_fn) - - assert replayer.consumer.committed - - for attr_name in ( - "_contents", - "_directories", - "_snapshots", - "_origin_visits", - "_origins", - ): - assert getattr(storage1, attr_name) == getattr(storage2, attr_name), attr_name - - # When hypothesis generates a revision and a release with same - # author (or committer) fullname but different name or email, then - # the storage will use the first name/email it sees. - # This first one will be either the one from the revision or the release, - # and since there is no order guarantees, storage2 has 1/2 chance of - # not seeing the same order as storage1, therefore we need to strip - # them out before comparing. - for attr_name in ("_revisions", "_releases"): - items1 = { - k: empty_person_name_email(v) - for (k, v) in getattr(storage1, attr_name).items() - } - items2 = { - k: empty_person_name_email(v) - for (k, v) in getattr(storage2, attr_name).items() - } - assert items1 == items2, attr_name diff --git a/swh/storage/validate.py b/swh/storage/validate.py index b6250576..d51c07b7 100644 --- a/swh/storage/validate.py +++ b/swh/storage/validate.py @@ -1,115 +1,138 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import contextlib -from typing import Dict, Iterable, Optional, List +from typing import Dict, Iterable, Iterator, List, Optional, Tuple from swh.model.model import ( BaseModel, SkippedContent, Content, Directory, Revision, Release, Snapshot, OriginVisit, Origin, ) from . import get_storage from .exc import StorageArgumentException VALIDATION_EXCEPTIONS = [ KeyError, TypeError, ValueError, ] @contextlib.contextmanager def convert_validation_exceptions(): """Catches validation errors arguments, and re-raises a StorageArgumentException.""" try: yield except tuple(VALIDATION_EXCEPTIONS) as e: raise StorageArgumentException(str(e)) class ValidatingProxyStorage: """Storage implementation converts dictionaries to swh-model objects before calling its backend, and back to dicts before returning results """ def __init__(self, storage): self.storage = get_storage(**storage) def __getattr__(self, key): if key == "storage": raise AttributeError(key) return getattr(self.storage, key) def content_add(self, content: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): contents = [Content.from_dict(c) for c in content] return self.storage.content_add(contents) def content_add_metadata(self, content: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): contents = [Content.from_dict(c) for c in content] return self.storage.content_add_metadata(contents) def skipped_content_add(self, content: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): contents = [SkippedContent.from_dict(c) for c in content] return self.storage.skipped_content_add(contents) def directory_add(self, directories: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): directories = [Directory.from_dict(d) for d in directories] return self.storage.directory_add(directories) def revision_add(self, revisions: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): revisions = [Revision.from_dict(r) for r in revisions] return self.storage.revision_add(revisions) + def revision_get(self, revisions: Iterable[bytes]) -> Iterator[Optional[Dict]]: + rev_dicts = self.storage.revision_get(revisions) + with convert_validation_exceptions(): + for rev_dict in rev_dicts: + if rev_dict is None: + yield None + else: + yield Revision.from_dict(rev_dict).to_dict() + + def revision_log( + self, revisions: Iterable[bytes], limit: Optional[int] = None + ) -> Iterator[Dict]: + for rev_dict in self.storage.revision_log(revisions, limit): + with convert_validation_exceptions(): + rev_obj = Revision.from_dict(rev_dict) + yield rev_obj.to_dict() + + def revision_shortlog( + self, revisions: Iterable[bytes], limit: Optional[int] = None + ) -> Iterator[Tuple[bytes, Tuple]]: + for rev, parents in self.storage.revision_shortlog(revisions, limit): + yield (rev, tuple(parents)) + def release_add(self, releases: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): releases = [Release.from_dict(r) for r in releases] return self.storage.release_add(releases) def snapshot_add(self, snapshots: Iterable[Dict]) -> Dict: with convert_validation_exceptions(): snapshots = [Snapshot.from_dict(s) for s in snapshots] return self.storage.snapshot_add(snapshots) def origin_visit_add( self, origin_url: str, date: datetime.datetime, type: str ) -> Dict[str, BaseModel]: with convert_validation_exceptions(): visit = OriginVisit( origin=origin_url, date=date, type=type, status="ongoing", snapshot=None ) return self.storage.origin_visit_add(visit.origin, visit.date, visit.type) def origin_add(self, origins: Iterable[Dict]) -> List[Dict]: with convert_validation_exceptions(): origins = [Origin.from_dict(o) for o in origins] return self.storage.origin_add(origins) def origin_add_one(self, origin: Dict) -> int: with convert_validation_exceptions(): origin = Origin.from_dict(origin) return self.storage.origin_add_one(origin) def clear_buffers(self, object_types: Optional[Iterable[str]] = None) -> None: return self.storage.clear_buffers(object_types) def flush(self, object_types: Optional[Iterable[str]] = None) -> Dict: return self.storage.flush(object_types) diff --git a/version.txt b/version.txt index 6653bdcd..22ba6855 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.193-0-g2209d31 \ No newline at end of file +v0.1.0-0-gf9b2ca3 \ No newline at end of file