diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index d853f823..1ead4950 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,47 +1,41 @@ repos: - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v4.1.0 + rev: v4.3.0 hooks: - id: trailing-whitespace - id: check-json - id: check-yaml - - repo: https://gitlab.com/pycqa/flake8 - rev: 4.0.1 + - repo: https://github.com/pycqa/flake8 + rev: 5.0.4 hooks: - id: flake8 - additional_dependencies: [flake8-bugbear==22.3.23] + additional_dependencies: [flake8-bugbear==22.9.23] - repo: https://github.com/codespell-project/codespell - rev: v2.1.0 + rev: v2.2.2 hooks: - id: codespell name: Check source code spelling args: [-L iff, -L gae, -L sur] stages: [commit] - repo: local hooks: - id: mypy name: mypy entry: mypy args: [swh] pass_filenames: false language: system types: [python] - - id: check-bumped-dbversion - name: check-bumped-dbversion - files: 'sql/upgrades/.*\.sql' - entry: grep - args: ["insert into dbversion"] - language: system - repo: https://github.com/PyCQA/isort rev: 5.10.1 hooks: - id: isort - repo: https://github.com/python/black - rev: 22.3.0 + rev: 22.10.0 hooks: - id: black diff --git a/PKG-INFO b/PKG-INFO index 8d55c604..d94d6ef5 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,246 +1,246 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 1.6.0 +Version: 1.7.1 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr 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/ 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: journal License-File: LICENSE License-File: AUTHORS swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects the path to `cassandra` to either be unspecified, it is then looked up at `/usr/sbin/cassandra`, either specified through the environment variable `SWH_CASSANDRA_BIN`. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` Note: it is possible to set the `JAVA_HOME` environment variable to specify the version of the JVM to be used by Cassandra. For example, at the time of writing this, Cassandra does not support java 14, so one may want to use for example java 11: ``` (swh) :~/swh-storage$ export JAVA_HOME=/usr/lib/jvm/java-14-openjdk-amd64/bin/java (swh) :~/swh-storage$ tox [...] ``` ## 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: postgresql db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing root: /tmp/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to `softwareheritage-dev` local instance, - the objstorage uses a local objstorage instance whose: - `root` path is /tmp/swh-storage, - slicing scheme is `0:2/2:4/4:6`. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the `root` path should exist on disk before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

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

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote url: http://localhost:5002/ ``` You could directly define a postgresql storage with the following snippet: ``` storage: cls: postgresql db: service=swh-dev objstorage: cls: pathslicing root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` ## Cassandra As an alternative to PostgreSQL, swh-storage can use Cassandra as a database backend. It can be used like this: ``` storage: cls: cassandra hosts: - localhost objstorage: cls: pathslicing root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` The Cassandra swh-storage implementation supports both Cassandra >= 4.0-alpha2 and ScyllaDB >= 4.4 (and possibly earlier versions, but this is untested). While the main code supports both transparently, running tests or configuring the schema requires specific code when using ScyllaDB, enabled by setting the `SWH_USE_SCYLLADB=1` environment variable. diff --git a/debian/changelog b/debian/changelog index 371ae75f..e3a477f5 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,2957 +1,2974 @@ -swh-storage (1.6.0-1~swh1~bpo10+1) buster-swh; urgency=medium +swh-storage (1.7.1-1~swh1) unstable-swh; urgency=medium - * Rebuild for buster-swh + * New upstream release 1.7.1 - (tagged by Antoine Lambert + on 2022-10-19 14:38:46 +0200) + * Upstream changes: - version 1.7.1 - -- Software Heritage autobuilder (on jenkins-debian1) Tue, 16 Aug 2022 12:46:24 +0000 + -- Software Heritage autobuilder (on jenkins-debian1) Wed, 19 Oct 2022 12:55:26 +0000 + +swh-storage (1.7.0-1~swh1) unstable-swh; urgency=medium + + * New upstream release 1.7.0 - (tagged by Valentin Lorentz + on 2022-10-10 13:45:10 +0200) + * Upstream changes: - v1.7.0 - Error handling: - * retry: + Do not retry on SystemExit exceptions - * Raise + StorageArgumentException on ProgramLimitExceeded - Docs: - * + docs: Update archive stats - * mention metadata formats for Gogs + and Gitea - Misc: - * Fix various crashes - * Add date- + based index to origin_visit - * Improve performance of + origin_visit_get_latest - This release contains SQL migrations + (functions and index), but no - schema change + + -- Software Heritage autobuilder (on jenkins-debian1) Mon, 10 Oct 2022 12:05:01 +0000 swh-storage (1.6.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.6.0 - (tagged by Valentin Lorentz on 2022-08-16 14:21:35 +0200) * Upstream changes: - v1.6.0 - * Add anchor extrinsic-metadata- original-artifacts-json - * Convert psycopg2 errors to TransientRemoteException instead of RemoteException - * retry: Add constant 10s wait when retrying transient exceptions -- Software Heritage autobuilder (on jenkins-debian1) Tue, 16 Aug 2022 12:36:51 +0000 swh-storage (1.5.1-1~swh1) unstable-swh; urgency=medium * New upstream release 1.5.1 - (tagged by Valentin Lorentz on 2022-08-05 13:59:15 +0200) * Upstream changes: - v1.5.1 - * Fix flaky tests - * cassandra: Make origin_visit_status_get_random's interval consistent with postgresql -- Software Heritage autobuilder (on jenkins-debian1) Fri, 05 Aug 2022 12:17:23 +0000 swh-storage (1.5.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.5.0 - (tagged by Valentin Lorentz on 2022-08-05 10:28:27 +0200) * Upstream changes: - v1.5.0 - * postgresql: Stop logging and sending timeouts to Sentry - * cassandra: Fix warnings - * Fix flaky test - * cassandra: document UPSERT behavior in a test -- Software Heritage autobuilder (on jenkins-debian1) Fri, 05 Aug 2022 08:44:42 +0000 swh-storage (1.4.2-1~swh1) unstable-swh; urgency=medium * New upstream release 1.4.2 - (tagged by Antoine R. Dumont (@ardumont) on 2022-08-04 09:57:35 +0200) * Upstream changes: - v1.4.2 - postgresql: Increase some timeouts to get origin visits - backfill: Add support for directories with duplicated entries - cli: move an import statement in the cli command - do not always auto-create an OriginVisitStatus object in origin_visit_add() - Add a Storage.flavor property to the postgresql backend - Update pytest_plugin for swh.core 2.10 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 04 Aug 2022 08:13:25 +0000 swh-storage (1.4.1-1~swh1) unstable-swh; urgency=medium * New upstream release 1.4.1 - (tagged by Antoine R. Dumont (@ardumont) on 2022-06-03 15:52:27 +0200) * Upstream changes: - v1.4.1 - Set current_version attribute to postgresql datastore - origin/master pytest_plugin: use the stock pytest_postgresql postgresql factory - Add missing __init__.py in proxies/ - docs: Describe metadata formats more precisely, and mention github and gitlab's - add strict asyncio_mode in pytest.ini -- Software Heritage autobuilder (on jenkins-debian1) Fri, 03 Jun 2022 15:25:19 +0000 swh-storage (1.4.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.4.0 - (tagged by Valentin Lorentz on 2022-05-03 11:43:34 +0200) * Upstream changes: - v1.4.0 - * Add function storage.algos.directory.directory_get - * Fix deprecation warnings -- Software Heritage autobuilder (on jenkins-debian1) Tue, 03 May 2022 09:55:07 +0000 swh-storage (1.3.2-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.2 - (tagged by Antoine R. Dumont (@ardumont) on 2022-04-25 14:22:19 +0200) * Upstream changes: - v1.3.2 - retry: re-raise original exception instead of a RetryError - Use logger everywhere in tenacious.py - pre-commit: Remove codespell commit-msg hook -- Software Heritage autobuilder (on jenkins-debian1) Mon, 25 Apr 2022 12:33:52 +0000 swh-storage (1.3.1-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.1 - (tagged by Antoine Lambert on 2022-04-12 14:36:22 +0200) * Upstream changes: - version 1.3.1 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 12 Apr 2022 12:48:04 +0000 swh-storage (1.3.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.0 - (tagged by Antoine R. Dumont (@ardumont) on 2022-04-11 14:23:42 +0200) * Upstream changes: - v1.3.0 - interface: Add new method origin_visit_get_with_statuses - Make postgresql's Storage client options configurable from config - requirements-test: Remove pytest pinning to < 7 - Add .git-blame-ignore-revs file with automatic reformatting commits - python: Reformat code with black 22.3.0 - pre-commit, tox: Bump black from 19.10b0 to 22.3.0 -- Software Heritage autobuilder (on jenkins-debian1) Mon, 11 Apr 2022 12:37:01 +0000 swh-storage (1.2.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.2.0 - (tagged by Nicolas Dandrimont on 2022-03-23 16:49:10 +0100) * Upstream changes: - Release swh.storage 1.2.0 - Compatibility with swh.model 6 -- Software Heritage autobuilder (on jenkins-debian1) Wed, 23 Mar 2022 16:00:33 +0000 swh-storage (1.1.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.1.0 - (tagged by Valentin Lorentz on 2022-03-16 16:09:49 +0100) * Upstream changes: - v1.1.0 - * postgresql: Increase timeouts that often fail - * origin_visit_get_latest: Order by visit id instead of date - * postgresql: Remove unused listener code from db.py - * backfill: Make integer_ranges() work on str args + add typing to RANGE_GENERATORS - * backfill: Add missing raw_manifest to directories -- Software Heritage autobuilder (on jenkins-debian1) Wed, 23 Mar 2022 15:01:47 +0000 swh-storage (1.0.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.0.0 - (tagged by David Douard on 2022-02-24 11:32:18 +0100) * Upstream changes: - v1.0.0 - add support for `swh db upgrade`, aka updated for swh core 2.0.0 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 24 Feb 2022 11:13:57 +0000 swh-storage (0.43.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.43.1 - (tagged by Valentin Lorentz on 2022-02-08 10:21:59 +0100) * Upstream changes: - v0.43.1 - * Add typing to revision_walker.py and make the state a dataclass - * revision_walker: Add support for ignore_displayname. -- Software Heritage autobuilder (on jenkins-debian1) Tue, 08 Feb 2022 09:31:33 +0000 swh-storage (0.43.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.43.0 - (tagged by Nicolas Dandrimont on 2022-02-02 18:46:15 +0100) * Upstream changes: - Release swh.storage 0.43.0 - Add a displayname field to the person table in PostgreSQL - Use the displayname field in returned results for revision_get, - revision_log and release_get -- Software Heritage autobuilder (on jenkins-debian1) Wed, 02 Feb 2022 17:56:33 +0000 swh-storage (0.42.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.42.0 - (tagged by Valentin Lorentz on 2022-01-25 16:44:35 +0100) * Upstream changes: - v0.42.0 - * Remove 'offset' and 'negative_utc' for the TimestampWithTimezone constructor call - * Stop using the deprecated 'TimestampWithTimezone.offset' attribute - * Fix directory_add to actually insert the manifest + add directory_get_raw_manifest -- Software Heritage autobuilder (on jenkins-debian1) Tue, 25 Jan 2022 15:54:46 +0000 swh-storage (0.41.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.41.1 - (tagged by David Douard on 2022-01-04 15:46:41 +0100) * Upstream changes: - v0.41.1 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 04 Jan 2022 14:55:33 +0000 swh-storage (0.41.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.41.0 - (tagged by Nicolas Dandrimont on 2021-12-22 15:24:31 +0100) * Upstream changes: - Release swh.storage v0.41.0 - add support for storing odd-shaped git objects enabled in swh.model 4.0.0 - drop workarounds for old versions of tenacity -- Software Heritage autobuilder (on jenkins-debian1) Wed, 22 Dec 2021 15:22:18 +0000 swh-storage (0.40.0-2~swh1) unstable-swh; urgency=medium * Update dependencies in d/control. -- David Douard Tue, 16 Nov 2021 14:37:20 +0100 swh-storage (0.40.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.40.0 - (tagged by David Douard on 2021-11-16 10:11:25 +0100) * Upstream changes: - v0.40.0 - Add support for a redis-based reporting for invalid mirrorred objects - Remove now useless fixers in storage/fixer.py - Add a new --type option to 'swh strorage repay' - Update extrinsic metadata specs -- Software Heritage autobuilder (on jenkins-debian1) Tue, 16 Nov 2021 09:45:39 +0000 swh-storage (0.39.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.39.0 - (tagged by Antoine Lambert on 2021-10-28 17:09:40 +0200) * Upstream changes: - version 0.39.0 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 29 Oct 2021 09:17:36 +0000 swh-storage (0.38.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.38.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-10-11 13:28:27 +0200) * Upstream changes: - v0.38.0 - buffer: add some debug logging for number of objects sent - buffer: add a threshold for the estimated size of revision and release batches - buffer: add a threshold for the number of revision parents in one batch - buffer: add a threshold for the number of directory entries in one batch - filter: add filtering for release_add - filter: do not call the underlying functions if there's nothing to add - buffer: Ensure that we don't send data from empty buffers -- Software Heritage autobuilder (on jenkins-debian1) Mon, 11 Oct 2021 14:58:23 +0000 swh-storage (0.37.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.37.1 - (tagged by David Douard on 2021-09-29 11:31:33 +0200) * Upstream changes: - v0.37.1 -- Software Heritage autobuilder (on jenkins-debian1) Wed, 29 Sep 2021 10:12:31 +0000 swh-storage (0.37.0-1~swh2) unstable-swh; urgency=medium * Bump new release -- Antoine R. Dumont (@ardumont) Thu, 16 Sep 2021 09:51:51 +0200 swh-storage (0.37.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.37.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-09-15 18:44:19 +0200) * Upstream changes: - v0.37.0 - Allow filtering extids per extid_version/extid_type when reading - migrate_extrinsic_metadata: Fix edge cases (missing f- stringification, remaining pypi - issues, ...) - cassandra: Make directory_ls fetch contents in batch instead of one-by-one - cassandra: Add option to select (hopefully) more efficient batch insertion algos - cassandra: Remove stat_counters. - cassandra: generate statsd metrics on method calls - content_get: Fetch rows concurrently - directory_entry_add_batch: Remove the temporary prepared statement entirely - directory_entry_add_batch: Reduce churn of prepared statements - postgresql: Fix a column order mismatch between the query and object builder - Add counting storage proxy -- Software Heritage autobuilder (on jenkins-debian1) Thu, 16 Sep 2021 06:42:23 +0000 swh-storage (0.36.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.36.0 - (tagged by Vincent SELLIER on 2021-08-24 16:51:07 +0200) * Upstream changes: - v0.36.0 - changelog: - Add cvs as supported revision_type - Add test for origin_visit_get_latest in presence of mismatched id and date orders - cassandra: Bump next_visit_id when origin_visit_add is called by a replayer - cassandra: Make content_missing query in batches - backfill: add extra where clause to use the right index for extid requests -- Software Heritage autobuilder (on jenkins-debian1) Tue, 24 Aug 2021 15:01:32 +0000 swh-storage (0.35.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.35.1 - (tagged by Valentin Lorentz on 2021-08-20 11:53:33 +0200) * Upstream changes: - v0.35.1 - * cassandra: Fix crash when using _missing() functions with more than 100 ids with ScyllaDB. -- Software Heritage autobuilder (on jenkins-debian1) Fri, 20 Aug 2021 10:01:16 +0000 swh-storage (0.35.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.35.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-07-28 10:36:09 +0200) * Upstream changes: - v0.35.0 - Implement storage of the ExtID.extid_version field -- Software Heritage autobuilder (on jenkins-debian1) Wed, 28 Jul 2021 08:43:06 +0000 swh-storage (0.34.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.34.0 - (tagged by Vincent SELLIER on 2021-07-07 18:22:00 +0200) * Upstream changes: - v0.34.0 - cassandra: allow to configure the consistency level -- Software Heritage autobuilder (on jenkins-debian1) Wed, 07 Jul 2021 16:58:42 +0000 swh-storage (0.33.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.33.0 - (tagged by Valentin Lorentz on 2021-07-05 16:48:16 +0200) * Upstream changes: - v0.33.0 - * Add endpoint raw_extrinsic_metadata_get_authorities -- Software Heritage autobuilder (on jenkins-debian1) Mon, 05 Jul 2021 15:00:12 +0000 swh-storage (0.32.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.32.0 - (tagged by Vincent SELLIER on 2021-06-28 15:35:44 +0200) * Upstream changes: - v0.32.0 - * cassandra: Add support for non-ASCII origin 'URLs'. -- Software Heritage autobuilder (on jenkins-debian1) Mon, 28 Jun 2021 16:20:21 +0000 swh-storage (0.31.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.31.0 - (tagged by Valentin Lorentz on 2021-06-25 11:17:50 +0200) * Upstream changes: - v0.31.0 - * cassandra: Add partial support for ScyllaDB - * mypy: Fix errors with release >= v0.900 (but breaks older mypy versions) - * Add endpoints to access REMD by id -- Software Heritage autobuilder (on jenkins-debian1) Fri, 25 Jun 2021 09:26:09 +0000 swh-storage (0.30.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.30.1 - (tagged by Antoine R. Dumont (@ardumont) on 2021-05-21 10:09:02 +0200) * Upstream changes: - v0.30.1 - Finalize the config "local" deprecation in favor of "postgresql" - tests: Make test parameters order deterministic, so they don't crash pytest-xdist - test_cassandra: Improve error when the process is started but not listening -- Software Heritage autobuilder (on jenkins-debian1) Fri, 21 May 2021 08:22:33 +0000 swh-storage (0.30.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.30.0 - (tagged by David Douard on 2021-05-18 16:34:25 +0200) * Upstream changes: - v0.30.0 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 18 May 2021 14:45:21 +0000 swh-storage (0.29.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.29.1 - (tagged by Nicolas Dandrimont on 2021-05-14 18:31:52 +0200) * Upstream changes: - Release swh.storage 0.29.1 - Add missing db migration -- Software Heritage autobuilder (on jenkins-debian1) Fri, 14 May 2021 16:59:42 +0000 swh-storage (0.29.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.29.0 - (tagged by Valentin Lorentz on 2021-05-11 15:04:58 +0200) * Upstream changes: - v0.29.0 - * Make the TenaciousProxyStorage retry when a single object add fails - * Move all proxy storages in swh/storage/proxies/ - * Deprecate the "local" storage cls in favor of "postgresql" - * cassandra: Add tests checking directory_add and snapshot_add are atomic. - * Add endpoint directory_get_entries, to quickly list a directory's entries - * content_get: Add support for queries by sha1_git -- Software Heritage autobuilder (on jenkins-debian1) Tue, 11 May 2021 13:12:42 +0000 swh-storage (0.28.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.28.0 - (tagged by Valentin Lorentz on 2021-05-06 15:52:03 +0200) * Upstream changes: - v0.28.0 - * Normalize all Storage.xxx_add() methods to return a summary - * cassandra: Add 'check_missing' option, to allow updating objects - * cassandra: Add a test of a 'complex' migration, with a PK update - * Add a new TenaciousProxyStorage - * Make postgresql's origin_add not raise an error in case of conflict - * Stop storing authority/fetcher metadata. - * tenacious: Document potential issues about objects being dropped - * Use swh.core 0.14 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 06 May 2021 14:06:51 +0000 swh-storage (0.27.4-1~swh1) unstable-swh; urgency=medium * New upstream release 0.27.4 - (tagged by Antoine Lambert on 2021-04-29 14:38:49 +0200) * Upstream changes: - version 0.27.4 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 29 Apr 2021 13:04:46 +0000 swh-storage (0.27.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.27.3 - (tagged by Antoine Lambert on 2021-04-09 14:59:36 +0200) * Upstream changes: - version 0.27.3 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 09 Apr 2021 13:06:58 +0000 swh-storage (0.27.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.27.2 - (tagged by David Douard on 2021-04-07 15:06:41 +0200) * Upstream changes: - v0.27.2 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 08 Apr 2021 08:05:43 +0000 swh-storage (0.27.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.27.1 - (tagged by Valentin Lorentz on 2021-03-30 17:47:03 +0200) * Upstream changes: - v0.27.1 - * buffer: Add support for 'extid' -- Software Heritage autobuilder (on jenkins-debian1) Tue, 30 Mar 2021 15:59:01 +0000 swh-storage (0.27.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.27.0 - (tagged by Valentin Lorentz on 2021-03-29 14:33:24 +0200) * Upstream changes: - v0.27.0 - * origin_visit_status_add: Fix inconsistent/incorrect errors when type is None and visit is missing. - * extid: remove unicity on (extid_type, extid) and (target_type, target) -- Software Heritage autobuilder (on jenkins-debian1) Mon, 29 Mar 2021 12:44:14 +0000 swh-storage (0.26.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.26.0 - (tagged by Nicolas Dandrimont on 2021-03-22 14:44:35 +0100) * Upstream changes: - Release swh.storage v0.26.0 - Move raw_extrinsic_metadata deduplication to use a new id column. -- Software Heritage autobuilder (on jenkins-debian1) Mon, 22 Mar 2021 21:53:39 +0000 swh-storage (0.25.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.25.0 - (tagged by Antoine Lambert on 2021-03-18 13:55:10 +0100) * Upstream changes: - version 0.25.0 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 18 Mar 2021 13:02:02 +0000 swh-storage (0.24.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.24.1 - (tagged by Valentin Lorentz on 2021-03-04 23:32:36 +0100) * Upstream changes: - v0.24.1 - * tests: Drop hypothesis < 6 requirement - * Remove the remaining references to the deprecated SWHID class - * postgresql: Ensure a minimum limit for the snapshot branches query -- Software Heritage autobuilder (on jenkins-debian1) Thu, 04 Mar 2021 22:39:03 +0000 swh-storage (0.24.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.24.0 - (tagged by Valentin Lorentz on 2021-03-02 10:00:23 +0100) * Upstream changes: - v0.24.0 - * storage_tests: recompute ids when evolving RawExtrinsicMetadata objects. - * RawExtrinsicMetadata: update to use the API in swh-model 1.0.0 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 02 Mar 2021 09:11:15 +0000 swh-storage (0.23.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.23.2 - (tagged by Antoine Lambert on 2021-02-19 11:47:03 +0100) * Upstream changes: - version 0.23.2 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 19 Feb 2021 10:58:50 +0000 swh-storage (0.23.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.23.1 - (tagged by Antoine R. Dumont (@ardumont) on 2021-02-16 17:19:00 +0100) * Upstream changes: - v0.23.1 - Switch anonymized replayer test to use pytest parametrization -- Software Heritage autobuilder (on jenkins-debian1) Tue, 16 Feb 2021 16:28:25 +0000 swh-storage (0.23.0-1~swh2) unstable-swh; urgency=medium * Fix dependency issue -- Antoine R. Dumont (@ardumont) Tue, 16 Feb 2021 14:34:57 +0100 swh-storage (0.23.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.23.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-02-15 15:20:21 +0100) * Upstream changes: - v0.23.0 - storage: Refactor OriginVisitStatus instantiation - db: Unify sql joins on origin_visit_status using "USING" - storage.postgresql: Use origin_visit_status.type value as source - test_replay: Fix hang since confluent-kafka 1.6 release - postgresql: Fix dbversion() to return the max version instead of a random one. - buffer: ensure objects are flushed in topological order - Return an accurate summary from buffer's flush() method - buffer: add support for snapshots - buffer: add type annotations for tests -- Software Heritage autobuilder (on jenkins-debian1) Mon, 15 Feb 2021 14:39:04 +0000 swh-storage (0.22.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.22.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-02-03 12:09:29 +0100) * Upstream changes: - v0.22.0 - storage: Make origin_get_latest_visit_status return OriginVisitStatus - storage: Change origin_visit_status_get_random interface to return visit_status - Write introduction to swh-storage -- Software Heritage autobuilder (on jenkins-debian1) Wed, 03 Feb 2021 11:15:27 +0000 swh-storage (0.21.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.21.1 - (tagged by Vincent SELLIER on 2021-01-28 14:11:26 +0100) * Upstream changes: - v0.21.1 - * Correctly return origin_visit_status.type value everywhere -- Software Heritage autobuilder (on jenkins-debian1) Thu, 28 Jan 2021 13:19:24 +0000 swh-storage (0.21.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.21.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-20 15:42:40 +0100) * Upstream changes: - v0.21.0 - db: Allow new status values not_found, failed to OriginVisitStatus -- Software Heritage autobuilder (on jenkins-debian1) Wed, 20 Jan 2021 14:52:20 +0000 swh-storage (0.20.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.20.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-20 10:24:00 +0100) * Upstream changes: - v0.20.0 - storage: Add persistence of the field OriginVisitStatus.type - backfiller: Add type to the origin_visit_status topic - tests: Make test_content_add_race fail for the right reason. -- Software Heritage autobuilder (on jenkins-debian1) Wed, 20 Jan 2021 09:29:54 +0000 swh-storage (0.19.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.19.0 - (tagged by Vincent SELLIER on 2021-01-14 11:09:17 +0100) * Upstream changes: - v0.19.0 - * 2021-01-12 Adapt cassandra storage to ignore the new OriginVisitStatus.type field - * 2021- 01-08 Allow to use the JAVA_HOME environment for cassandra tests - * 2021-01-13 Enforce hypothesis <6 to prevent test breakage - * 2021-01-08 Make the CREATE_TABLES_QUERIES in cassandra/schema.py an explicit list - * 2020-12-18 Add a cli section in the doc - * 2020-11-24 storage.backfill: Allow cli run for origin_visit_status as well - * 2020-11-24 conftest: Reference swh.core.db.pytest_plugin -- Software Heritage autobuilder (on jenkins-debian1) Thu, 14 Jan 2021 10:18:31 +0000 swh-storage (0.18.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.18.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-11-23 14:46:41 +0100) * Upstream changes: - v0.18.0 - requirements-test.txt: Drop no longer needed pytest-postgresql requirement - backfill: Reverse flawed logic in SnapshotBranch generation - migrate_extrinsic_metadata: don't crash when deb revisions aren't referenced by any snapshot -- Software Heritage autobuilder (on jenkins-debian1) Mon, 23 Nov 2020 13:52:32 +0000 swh-storage (0.17.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.17.2 - (tagged by Nicolas Dandrimont on 2020-11-13 11:56:37 +0100) * Upstream changes: - Release swh.storage 0.17.2 - Future- proof get_journal_writer by setting the value_sanitizer argument - migrate_extrinsic_metadata improvements - backfill: only flush on every batch -- Software Heritage autobuilder (on jenkins-debian1) Fri, 13 Nov 2020 11:05:35 +0000 swh-storage (0.17.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.17.1 - (tagged by Antoine Lambert on 2020-11-05 13:50:35 +0100) * Upstream changes: - version 0.17.1 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 05 Nov 2020 12:56:53 +0000 swh-storage (0.17.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.17.0 - (tagged by Nicolas Dandrimont on 2020-11-03 18:09:53 +0100) * Upstream changes: - Release swh.storage v0.17.0 - Migrate all raw extrinsic metadata attributes from id to target - Add an `algos` function to resolve branch aliases - Prepare updates to make swh.journal more generic - Improve api server initialization - Various updates to the migrate_extrinsic_metadata script, notably writing - most metadata on directories instead of revisions -- Software Heritage autobuilder (on jenkins-debian1) Tue, 03 Nov 2020 17:20:45 +0000 swh-storage (0.16.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.16.0 - (tagged by Nicolas Dandrimont on 2020-10-09 18:23:24 +0200) * Upstream changes: - Release swh.storage v0.16.0 - Updates to the intrinsic metadata migration script - Various improvements to the buffer storage - Update swh storage backfill to use common configuration keys -- Software Heritage autobuilder (on jenkins-debian1) Fri, 09 Oct 2020 16:33:11 +0000 swh-storage (0.15.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.15.3 - (tagged by Nicolas Dandrimont on 2020-09-24 20:14:39 +0200) * Upstream changes: - Release swh.storage v0.15.3 - hopefully fix the documentation build -- Software Heritage autobuilder (on jenkins-debian1) Thu, 24 Sep 2020 18:24:14 +0000 swh-storage (0.15.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.15.2 - (tagged by Nicolas Dandrimont on 2020-09-24 19:22:11 +0200) * Upstream changes: - Release swh.storage v0.15.2 - no change rebuild to clean up jenkins fsckup accumulating old files. -- Software Heritage autobuilder (on jenkins-debian1) Thu, 24 Sep 2020 17:28:22 +0000 swh-storage (0.15.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.15.1 - (tagged by Nicolas Dandrimont on 2020-09-24 18:34:54 +0200) * Upstream changes: - Release swh.storage v0.15.1 - Restore buffer proxy behavior with default arguments -- Software Heritage autobuilder (on jenkins-debian1) Thu, 24 Sep 2020 16:44:22 +0000 swh-storage (0.15.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.15.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-09-24 16:54:07 +0200) * Upstream changes: - v0.15.0 - Support different database flavors in the SQL scripts - Add the SQL commands used to set up the logical replication publication - Output a warning when the version of the database is different than expected - Improve code quality and doc in BufferedProxyStorage - Adapt cli declaration entrypoint to swh.core 0.3 - Add warning about skipped_content (sneaking into the 'content' topics) - graph- replayer: fix to prevent wrong warning - pre-commit: Add isort hook and reorder imports with isort - pytest_plugin: Change dbname to storage to avoid clash in tests - pytest_plugin: Use psql to load SQL files instead of connecting with psycopg2 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 24 Sep 2020 15:03:58 +0000 swh-storage (0.14.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.14.3 - (tagged by David Douard on 2020-09-17 16:58:59 +0200) * Upstream changes: - v0.14.3 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 17 Sep 2020 16:53:56 +0000 swh-storage (0.14.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.14.2 - (tagged by David Douard on 2020-09-11 15:31:22 +0200) * Upstream changes: - v0.14.2 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 11 Sep 2020 13:37:11 +0000 swh-storage (0.14.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.14.1 - (tagged by Antoine R. Dumont (@ardumont) on 2020-09-04 15:43:51 +0200) * Upstream changes: - v0.14.1 - algos.diff: Add missed revision_get conversion -- Software Heritage autobuilder (on jenkins-debian1) Fri, 04 Sep 2020 13:52:17 +0000 swh-storage (0.14.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.14.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-09-04 12:23:52 +0200) * Upstream changes: - v0.14.0 - Refactor revision_get storage API to return Revision objects - cassandra: Discard Content ctime field in content_get_partition -- Software Heritage autobuilder (on jenkins-debian1) Fri, 04 Sep 2020 10:59:54 +0000 swh-storage (0.13.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.13.3 - (tagged by Antoine R. Dumont (@ardumont) on 2020-09-01 14:34:57 +0200) * Upstream changes: - v0.13.3 - storage*: release_get(...) -> List[Optional[Release]] - Make StorageInterface a Protocol. - Add a validating storage proxy, to check ids before insertion. - Add a --check-config option for cli commands - Remove the deprecated config-path option from `swh storage rpc-serve` command - Add support for a new "check_config" config option in get_storage() - Check for db version mismatch in PgStorage.check_config() - Add a check_dbversion() method to the Db class - Fix pytest_plugin's database janitor: do not truncate the dbversion table - algos.snapshot: Add visits_and_snapshots_get_from_revision - storage/interface: Remove deprecated diff endpoints - storage_tests: Remove duplicated postgresql-specific tests. - Move postgresql-related files to swh/storage/postgresql/ -- Software Heritage autobuilder (on jenkins-debian1) Tue, 01 Sep 2020 12:40:29 +0000 swh-storage (0.13.2-1~swh2) unstable-swh; urgency=medium * Add mypy-extensions to build-dependencies -- Nicolas Dandrimont Fri, 21 Aug 2020 12:17:05 +0200 swh-storage (0.13.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.13.2 - (tagged by Valentin Lorentz on 2020-08-20 08:59:39 +0200) * Upstream changes: - v0.13.2 - * pg: Fix crash in snapshot_get when the snapshot does not exist. - * cassandra: fix signatures - * in_memory: rewrite as a backend for the cassandra storage - * remove endpoint snapshot_get_by_origin_visit. - * pg: rewrite converters to work with model objects -- Software Heritage autobuilder (on jenkins-debian1) Thu, 20 Aug 2020 07:18:50 +0000 swh-storage (0.13.1-1~swh3) unstable-swh; urgency=medium * Update dependencies -- Antoine R. Dumont (@ardumont) Fri, 07 Aug 2020 21:17:01 +0000 swh-storage (0.13.1-1~swh2) unstable-swh; urgency=medium * Update dependencies -- Antoine R. Dumont (@ardumont) Fri, 07 Aug 2020 21:02:01 +0000 swh-storage (0.13.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.13.1 - (tagged by Valentin Lorentz on 2020-08-07 18:14:32 +0200) * Upstream changes: - v0.13.1 - * Make snapshot_get_branches return a TypedDict containing SnapshotBranch objects. -- Software Heritage autobuilder (on jenkins-debian1) Fri, 07 Aug 2020 16:23:01 +0000 swh-storage (0.13.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.13.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-08-07 12:38:47 +0200) * Upstream changes: - v0.13.0 - storage*: Rename and type content_get(List[Sha1]) -> List[Optional[Content]] - storage*: Rename content_get_data(Sha1) -> Optional[bytes] - Simplify as Content.ctime None is popped out of a to_dict call in recent model - cassandra.storage: Use next token for pagination instead of computing it -- Software Heritage autobuilder (on jenkins-debian1) Fri, 07 Aug 2020 10:49:28 +0000 swh-storage (0.12.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.12.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-08-06 08:50:17 +0200) * Upstream changes: - v0.12.0 - Type storage endpoints - Drop content_get_range endpoint in favor of content_get_partition -- Software Heritage autobuilder (on jenkins-debian1) Thu, 06 Aug 2020 06:55:26 +0000 swh-storage (0.11.10-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.10 - (tagged by Antoine R. Dumont (@ardumont) on 2020-08-04 14:10:21 +0200) * Upstream changes: - v0.11.10 - tests: Improve coverage on directory_ls endpoints - storage*: Type content_find(...) -> List[Content] - storage*: Type {cnt,dir,rev,rel,snp}_get_random(...) -> Sha1Git -- Software Heritage autobuilder (on jenkins-debian1) Tue, 04 Aug 2020 12:15:21 +0000 swh-storage (0.11.9-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.9 - (tagged by Antoine R. Dumont (@ardumont) on 2020-08-03 11:55:10 +0200) * Upstream changes: - v0.11.9 - storage*: Drop origin-get- range in favor of origin-list - storage*: Do not allow unknown visit status in origin_visit*_get_latest - storage*: Add type annotation to origin_count - Reuse swh.core stream_results function -- Software Heritage autobuilder (on jenkins-debian1) Mon, 03 Aug 2020 10:02:56 +0000 swh-storage (0.11.8-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.8 - (tagged by Valentin Lorentz on 2020-07-31 14:57:09 +0200) * Upstream changes: - v0.11.8 - * test_replay: update for swh.journal 0.4.1. - * Add support for metadata-related object types to the backfiller and replayer. - * pg: Rewrite _origin_query to force the query planner to filter on URLs before filtering on visits. - * Make raw_extrinsic_metadata_get return PagedResult instead of Dict. - * Rename argument 'object_type' of raw_extrinsic_metadata_get to 'type'. -- Software Heritage autobuilder (on jenkins-debian1) Fri, 31 Jul 2020 13:17:40 +0000 swh-storage (0.11.6-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.6 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-30 16:20:48 +0200) * Upstream changes: - v0.11.6 - storage*: Adapt origin_list(...) -> PagedResult[Origin] - algos.snapshot: Open snapshot_id_get_from_revision - storage*: add origin_visit_status_get(...) -> PagedResult[OriginVisitStatus] - Add type annotations on get_storage. - buffer: Pass lists to backend functions, not iterables. - storage*: Simplify next-page- token computation - filter: Fix types passed to the proxied storage. - Fix upcoming type warning with swh.core > v0.1.2. - Make API endpoints take Lists instead of Iterables as arguments - storage*: use an enum to explicit the order in origin_visit_get - storage*: origin_visit_get(...) -> PagedResult[OriginVisit] - Write metadata + metadata authorities/fetchers to the journal. -- Software Heritage autobuilder (on jenkins-debian1) Thu, 30 Jul 2020 14:29:10 +0000 swh-storage (0.11.5-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.5 - (tagged by Valentin Lorentz on 2020-07-28 09:55:34 +0200) * Upstream changes: - v0.11.5 - in_memory: fix tie-breaking when two visits have the same date. -- Software Heritage autobuilder (on jenkins-debian1) Tue, 28 Jul 2020 08:10:21 +0000 swh-storage (0.11.4-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.4 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-27 16:08:42 +0200) * Upstream changes: - v0.11.4 - Rename object_metadata to raw_extrinsic_metadata - metadata_{authority,fetcher}_add: Fix crash when the iterable argument is empty - storage*: origin_visit_get_by -> Optional[OriginVisit] - storage*: origin_visit_find_by_date -> Optional[OriginVisit] - storage*: type origin_visit_get_latest endpoint result - algos.origin: Simplify origin_get_latest_visit_status function -- Software Heritage autobuilder (on jenkins-debian1) Mon, 27 Jul 2020 14:16:18 +0000 swh-storage (0.11.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.3 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-27 08:01:03 +0200) * Upstream changes: - v0.11.3 - storage*: origin_get(Iterable[str]) -> Iterable[Optional[Origin]] - storage*.origin_visit_get_random: Read model objects -- Software Heritage autobuilder (on jenkins-debian1) Mon, 27 Jul 2020 06:08:55 +0000 swh-storage (0.11.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.2 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-23 12:09:51 +0200) * Upstream changes: - v0.11.2 - pgstorage: Drop unnecessary indirection from reading origin_visit - pytest-plugin: Make sample_data return data model objects - tests: Use only model objects for testing - Drop validate storage proxy -- Software Heritage autobuilder (on jenkins-debian1) Thu, 23 Jul 2020 10:18:15 +0000 swh-storage (0.11.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.1 - (tagged by Valentin Lorentz on 2020-07-20 13:01:20 +0200) * Upstream changes: - v0.11.1 - * Use model objects in tests - * Rename 'deposit' authority type to 'deposit_client'. -- Software Heritage autobuilder (on jenkins-debian1) Mon, 20 Jul 2020 11:14:39 +0000 swh-storage (0.11.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.11.0 - (tagged by Valentin Lorentz on 2020-07-20 11:01:10 +0200) * Upstream changes: - v0.11.0 - * Make metadata-related endpoints consistent with other endpoints by using Iterables of swh- model objects instead of a dict. - * Update tests to use model objects -- Software Heritage autobuilder (on jenkins-debian1) Mon, 20 Jul 2020 09:12:25 +0000 swh-storage (0.10.6-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.6 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-16 15:31:19 +0200) * Upstream changes: - v0.10.6 - pytest_plugin: Ensure fixture instantiates correctly -- Software Heritage autobuilder (on jenkins-debian1) Thu, 16 Jul 2020 13:36:34 +0000 swh-storage (0.10.5-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.5 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-16 14:24:50 +0200) * Upstream changes: - v0.10.5 - pytest_plugin: Do not expose the validate proxy storage - pytest-plugin: Expose a sample_data_model fixture - tests: Start using model objects and drop validate proxy when possible -- Software Heritage autobuilder (on jenkins-debian1) Thu, 16 Jul 2020 12:34:44 +0000 swh-storage (0.10.4-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.4 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-16 11:25:25 +0200) * Upstream changes: - v0.10.4 - pytest_plugin: Avoid fixture client to declare optional dependency - Allow cassandra binary path to be configured through env variable - 158: Make schema and migration converge so the migration works -- Software Heritage autobuilder (on jenkins-debian1) Thu, 16 Jul 2020 09:37:24 +0000 swh-storage (0.10.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.3 - (tagged by Antoine Lambert on 2020-07-10 16:26:27 +0200) * Upstream changes: - version 0.10.3 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 10 Jul 2020 14:40:28 +0000 swh-storage (0.10.2-1~swh2) unstable-swh; urgency=medium * Fix debian rules to avoid double pytest-plugin loading clash -- Antoine R. Dumont (@ardumont) Fri, 10 Jul 2020 09:21:14 +0200 swh-storage (0.10.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.2 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-10 08:30:37 +0200) * Upstream changes: - v0.10.2 - tests: Do no expose the pytest- plugin through setuptools entry - Convert ImmutableDict to dict before passing it to json.dumps - docs: Rework dia -> pdf pipeline for inkscape 1.0 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 10 Jul 2020 06:52:42 +0000 swh-storage (0.10.1-1~swh2) unstable-swh; urgency=medium * Update runtime dependencies -- Antoine R. Dumont (@ardumont) Wed, 08 Jul 2020 14:56:01 +0200 swh-storage (0.10.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.1 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-08 14:32:52 +0200) * Upstream changes: - v0.10.1 - extract-pytest-fixture Move shareable fixtures out of conftest into a dedicated pytest plugin - Migrate from vcversioner to setuptools-scm -- Software Heritage autobuilder (on jenkins-debian1) Wed, 08 Jul 2020 12:39:15 +0000 swh-storage (0.10.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.0 - (tagged by David Douard on 2020-07-08 09:20:49 +0200) * Upstream changes: - v0.10.0 -- Software Heritage autobuilder (on jenkins-debian1) Wed, 08 Jul 2020 10:11:09 +0000 swh-storage (0.9.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.9.3 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-06 09:55:56 +0200) * Upstream changes: - v0.9.3 - storage: Send metrics from the origin_add endpoint -- Software Heritage autobuilder (on jenkins-debian1) Mon, 06 Jul 2020 08:06:13 +0000 swh-storage (0.9.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.9.2 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-03 18:48:39 +0200) * Upstream changes: - v0.9.2 - pg-storage: Add missing cur parameter passing -- Software Heritage autobuilder (on jenkins-debian1) Fri, 03 Jul 2020 16:54:13 +0000 swh-storage (0.9.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.9.1 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-03 16:50:45 +0200) * Upstream changes: - v0.9.1 - storage.db: Drop db.origin_visit_upsert behavior -- Software Heritage autobuilder (on jenkins-debian1) Fri, 03 Jul 2020 15:00:32 +0000 swh-storage (0.9.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.9.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-07-01 09:53:34 +0200) * Upstream changes: - v0.9.0 - storage*: Drop intermediary conversion step into OriginVisit - pg: use 'on conflict do nothing' strategy for duplicate metadata rows. - Make the code location of metadata endpoints consistent across backends. - Add content_metadata_{add,get}. - Add context columns to object_metadata table and object_metadata_{add,get}. - Generalize origin_metadata to allow support for other object types in the future. - Work around the segmentation faults caused by pytest-coverage + multiprocessing. -- Software Heritage autobuilder (on jenkins-debian1) Wed, 01 Jul 2020 08:02:08 +0000 swh-storage (0.8.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.8.1 - (tagged by David Douard on 2020-06-30 10:08:21 +0200) * Upstream changes: - v0.8.1 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 30 Jun 2020 08:36:45 +0000 swh-storage (0.8.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.8.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-06-29 09:33:12 +0200) * Upstream changes: - v0.8.0 - Iterate over paginated visits in batches to retrieve latest visit/snapshot - storage*: Open order parameter to origin-visit-get endpoint - tests/replayer/storage*: Drop obsolete origin visit fields - Relax checks on journal writes regarding origin-visit* - replayer: Fix isoformat datetime string for origin-visit - Deprecate the origin_add_one() endpoint - test_storage: Add missing tests on origin_visit_get method -- Software Heritage autobuilder (on jenkins-debian1) Mon, 29 Jun 2020 07:44:00 +0000 swh-storage (0.7.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.7.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-06-22 15:42:25 +0200) * Upstream changes: - v0.7.0 - test_origin: Rename appropriately tests - algos: Improve origin visit get latest visit status algorithm - test_snapshot: Do not use origin_visit_add returned result - algos.snapshot: Fix edge case when snapshot is not resolved - Ensure ids are correct in tests' storage_data - Fix tests' storage_data revisions - SQL: replace the hash(url) index by a unique btree(url) on the origin table - Make sure the pagination in swh_snapshot_get_by_id uses the proper indexes -- Software Heritage autobuilder (on jenkins-debian1) Mon, 22 Jun 2020 14:09:33 +0000 swh-storage (0.6.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.6.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-06-19 11:29:42 +0200) * Upstream changes: - v0.6.0 - Move deprecated endpoint snapshot_get_latest from api endpoint to algos - algos.origin: Open origin-get-latest-visit-status function - storage*: Allow origin-visit-get-latest to filter on type - test_origin: Align storage initialization within tests -- Software Heritage autobuilder (on jenkins-debian1) Fri, 19 Jun 2020 12:45:32 +0000 swh-storage (0.5.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.5.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-06-17 16:03:15 +0200) * Upstream changes: - v0.5.0 - test_storage: Fix flakiness in round to milliseconds test util method - storage*: Add origin- visit-status-get-latest endpoint - Fix/update the backfiller - validate: accept model objects as well as dicts on all add endpoints - cql: Fix blackified strings - storage: Add missing cur parameter - Fix db_to_author() converter to return None is all fields are None -- Software Heritage autobuilder (on jenkins-debian1) Wed, 17 Jun 2020 14:19:37 +0000 swh-storage (0.4.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.4.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-06-16 09:50:25 +0200) * Upstream changes: - v0.4.0 - ardumont/master storage*: Drop leftover code - storage*: Drop origin_visit_upsert endpoint - storage*: Remove origin-visit-update endpoint - replay: Replay origin-visit and origin-visit-status - in_memory: Make origin- visit-status-add respect "on conflict ignore" policy - test_storage: Add journal behavior coverage for origin-visit-*add - Start migrating the validate proxy toward using BaseModel objects - storage*: Do not write twice origin-visit-status in journal -- Software Heritage autobuilder (on jenkins-debian1) Tue, 16 Jun 2020 07:58:23 +0000 swh-storage (0.3.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.3.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-06-12 09:08:23 +0200) * Upstream changes: - v0.3.0 - origin-visit-add storage*: Align origin-visit-add to take iterable of OriginVisit objects -- Software Heritage autobuilder (on jenkins-debian1) Fri, 12 Jun 2020 07:22:03 +0000 swh-storage (0.2.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.2.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-06-10 11:51:30 +0200) * Upstream changes: - v0.2.0 - origin-visit-upsert: Write visit status objects to the journal - origin-visit-update: Write visit status objects to the journal - origin-visit-add: Write visit status to the journal - Add pagination to origin_metadata_get. - Deduplicate origin-metadata when they have the same authority + discovery_date + fetcher. - Open `origin_visit_status_add` endpoint to add origin visit statuses - Add a replayer test for anonymized journal topics - Small refactoring of the InMemoryStorage to make it more consistent -- Software Heritage autobuilder (on jenkins-debian1) Wed, 10 Jun 2020 10:02:45 +0000 swh-storage (0.1.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.1.1 - (tagged by Nicolas Dandrimont on 2020-06-04 16:49:22 +0200) * Upstream changes: - Release swh.storage v0.1.1 - Work around tests hanging during Debian build -- Software Heritage autobuilder (on jenkins-debian1) Thu, 04 Jun 2020 14:56:54 +0000 swh-storage (0.1.0-2~swh1) unstable-swh; urgency=medium * Update dependencies. -- David Douard Thu, 04 Jun 2020 13:40:52 +0200 swh-storage (0.1.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.1.0 - (tagged by David Douard on 2020-06-04 12:08:46 +0200) * Upstream changes: - v0.1.0 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 04 Jun 2020 10:28:43 +0000 swh-storage (0.0.193-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.193 - (tagged by Antoine R. Dumont (@ardumont) on 2020-05-28 14:28:54 +0200) * Upstream changes: - v0.0.193 - pg: Write origin visit updates & status, read from origin_visit_status - Make content.blake2s256 not null. - Remove unused SQL functions. - README: Update necessary dependencies for test purposes - Add a pre-commit hook to check there are version bumps in sql/upgrades/*.sql - Add missing dbversion bump in 150.sql. - Add artifact metadata to the extrinsic metadata storage specification. - Add not null constraints to metadata_authority/origin_metadata - Realign schema with latest 149 migration script -- Software Heritage autobuilder (on jenkins-debian1) Thu, 28 May 2020 12:37:58 +0000 swh-storage (0.0.192-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.192 - (tagged by Valentin Lorentz on 2020-05-19 18:42:00 +0200) * Upstream changes: - v0.0.192 - * origin_metadata_add: Reject non-bytes types for 'metadata'. -- Software Heritage autobuilder (on jenkins-debian1) Tue, 19 May 2020 16:54:00 +0000 swh-storage (0.0.191-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.191 - (tagged by Valentin Lorentz on 2020-05-19 13:43:35 +0200) * Upstream changes: - v0.0.191 - * Implement the new extrinsic metadata specification/vocabulary. -- Software Heritage autobuilder (on jenkins-debian1) Tue, 19 May 2020 11:52:00 +0000 swh-storage (0.0.190-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.190 - (tagged by Antoine R. Dumont (@ardumont) on 2020-05-18 14:10:39 +0200) * Upstream changes: - v0.0.190 - storage: metadata_provider: Ensure idempotency when creating provider - journal: add a skipped_content topic dedicated to SkippedContent objects - Add missing return annotations on JournalWriter methods - Improve a bit the exception message of JournalWriter.content_update - Refactor the JournalWriter class to normalize its methods - tests: fix test_replay; do only use aware datetime objects - test_kafka_writer: Add missing object type skipped_content -- Software Heritage autobuilder (on jenkins-debian1) Mon, 18 May 2020 12:18:09 +0000 swh-storage (0.0.189-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.189 - (tagged by Antoine R. Dumont (@ardumont) on 2020-04-30 14:50:54 +0200) * Upstream changes: - v0.0.189 - pg: Write both origin visit updates & status, read from origin_visit - pg-storage: Add new created state - setup.py: add documentation link - metadata spec: Fix title hierarchy - tests: Use aware datetimes instead of naive ones. - cassandra: Adapt internal implementations to use origin visit status - in_memory: Adapt internal implementations to use origin visit status -- Software Heritage autobuilder (on jenkins-debian1) Thu, 30 Apr 2020 12:58:57 +0000 swh-storage (0.0.188-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.188 - (tagged by David Douard on 2020-04-28 13:44:20 +0200) * Upstream changes: - v0.0.188 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 28 Apr 2020 11:52:08 +0000 swh-storage (0.0.187-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.187 - (tagged by Antoine R. Dumont (@ardumont) on 2020-04-14 18:13:08 +0200) * Upstream changes: - v0.0.187 - storage.interface: Actually define the remote flush operation -- Software Heritage autobuilder (on jenkins-debian1) Tue, 14 Apr 2020 16:23:41 +0000 swh-storage (0.0.186-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.186 - (tagged by Nicolas Dandrimont on 2020-04-14 17:09:22 +0200) * Upstream changes: - Release swh.storage v0.0.186 - Drop backwards-compatibility code with swh.journal < 0.0.30 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 14 Apr 2020 15:20:57 +0000 swh-storage (0.0.185-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.185 - (tagged by Antoine R. Dumont (@ardumont) on 2020-04-14 14:15:32 +0200) * Upstream changes: - v0.0.185 - storage.filter: Remove internal state - test: update storage tests to (future) swh.journal 0.0.30 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 14 Apr 2020 12:22:06 +0000 swh-storage (0.0.184-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.184 - (tagged by Antoine R. Dumont (@ardumont) on 2020-04-10 16:07:32 +0200) * Upstream changes: - v0.0.184 - storage*: Add flush endpoints to storage implems (backend, proxy) - test_retry: Add missing skipped_content_add tests -- Software Heritage autobuilder (on jenkins-debian1) Fri, 10 Apr 2020 14:14:20 +0000 swh-storage (0.0.183-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.183 - (tagged by Antoine R. Dumont (@ardumont) on 2020-04-09 12:35:53 +0200) * Upstream changes: - v0.0.183 - proxy storage: Add a clear_buffers endpoint - buffer proxy storage: Filter out duplicate objects prior to storage write - storage: Prevent erroneous HashCollisions by using the same ctime for all rows. - Enable black - origin_visit_update: ensure it raises a StorageArgumentException - Adapt cassandra backend to validating model types - tests: many refactoring improvements - tests: Shut down cassandra connection before closing the fixture down - Add more type annotations -- Software Heritage autobuilder (on jenkins-debian1) Thu, 09 Apr 2020 10:46:29 +0000 swh-storage (0.0.182-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.182 - (tagged by Antoine R. Dumont (@ardumont) on 2020-03-27 07:02:13 +0100) * Upstream changes: - v0.0.182 - storage*: Update origin_visit_update to make status parameter mandatory - test: Adapt origin validation test according to latest model changes - Respec discovery_date as a Python datetime instead of an ISO string. - origin_visit_add: Add missing db/cur argument to call to origin_get. -- Software Heritage autobuilder (on jenkins-debian1) Fri, 27 Mar 2020 06:13:17 +0000 swh-storage (0.0.181-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.181 - (tagged by Antoine R. Dumont (@ardumont) on 2020-03-25 09:50:49 +0100) * Upstream changes: - v0.0.181 - storage*: Hex encode content hashes in HashCollision exception - Add format of discovery_date in the metadata specification. - Store the value of token(partition_key) in skipped_content_by_* table, instead of three hashes. - Store the value of token(partition_key) in content_by_* table, instead of three hashes. -- Software Heritage autobuilder (on jenkins-debian1) Wed, 25 Mar 2020 09:03:43 +0000 swh-storage (0.0.180-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.180 - (tagged by Nicolas Dandrimont on 2020-03-18 18:24:41 +0100) * Upstream changes: - Release swh.storage v0.0.180 - Stop counting origin additions multiple times in statsd -- Software Heritage autobuilder (on jenkins-debian1) Wed, 18 Mar 2020 17:45:36 +0000 swh-storage (0.0.179-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.179 - (tagged by Nicolas Dandrimont on 2020-03-18 16:05:13 +0100) * Upstream changes: - Release swh.storage v0.0.179. - fix requirements-swh.txt to use proper version restriction - reduce the transaction load for content writes and reads -- Software Heritage autobuilder (on jenkins-debian1) Wed, 18 Mar 2020 15:50:50 +0000 swh-storage (0.0.178-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.178 - (tagged by Antoine R. Dumont (@ardumont) on 2020-03-16 12:51:28 +0100) * Upstream changes: - v0.0.178 - origin_visit_add: Adapt endpoint signature to return OriginVisit - origin_visit_upsert: Use OriginVisit object as input - storage/writer: refactor JournalWriter.content_add to send model objects -- Software Heritage autobuilder (on jenkins-debian1) Mon, 16 Mar 2020 11:59:18 +0000 swh-storage (0.0.177-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.177 - (tagged by Antoine R. Dumont (@ardumont) on 2020-03-10 11:37:33 +0100) * Upstream changes: - v0.0.177 - storage: Identify and provide the collision hashes in exception - Guarantee the order of results for revision_get and release_get - tests: Improve test speed - sql: do not attempt to create the plpgsql lang if already exists - Update requirement on swh.core for RPCClient method overrides -- Software Heritage autobuilder (on jenkins-debian1) Tue, 10 Mar 2020 10:48:11 +0000 swh-storage (0.0.176-1~swh2) unstable-swh; urgency=medium * Update build dependencies -- Antoine R. Dumont (@ardumont) Mon, 02 Mar 2020 14:36:00 +0100 swh-storage (0.0.176-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.176 - (tagged by Valentin Lorentz on 2020-02-28 14:44:10 +0100) * Upstream changes: - v0.0.176 - * Accept cassandra-driver >= 3.22. - * Make the RPC client and objstorage helper fetch Content.data from lazy - contents. - * Move ctime out of the validation proxy. -- Software Heritage autobuilder (on jenkins-debian1) Fri, 28 Feb 2020 15:21:27 +0000 swh-storage (0.0.175-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.175 - (tagged by Antoine Lambert on 2020-02-20 13:51:40 +0100) * Upstream changes: - version 0.0.175 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 20 Feb 2020 13:18:34 +0000 swh-storage (0.0.174-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.174 - (tagged by Valentin Lorentz on 2020-02-19 14:18:59 +0100) * Upstream changes: - v0.0.174 - * Fix inconsistent behavior of skipped_content_missing across backends. - * Fix FilteringProxy to not drop skipped-contents with a missing sha1_git. - * Make storage proxies use swh-model objects instead of dicts. - * Add support for (de)serializing swh-model in RPC calls. -- Software Heritage autobuilder (on jenkins-debian1) Wed, 19 Feb 2020 15:00:32 +0000 swh-storage (0.0.172-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.172 - (tagged by Valentin Lorentz on 2020-02-12 14:00:04 +0100) * Upstream changes: - v0.0.172 - * Unify exception raised by invalid input to API endpoints. - * Add a validation proxy for _add() methods. This proxy is *required* - in front of all backends whose _add() methods may be called or they'll - crash at runtime. - * Fix RecursionError when storage proxies are deepcopied or unpickled. - * storages: Refactor objstorage operations with a dedicated collaborator - * storages: Refactor journal operations with a dedicated writer collab -- Software Heritage autobuilder (on jenkins-debian1) Wed, 12 Feb 2020 13:13:47 +0000 swh-storage (0.0.171-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.171 - (tagged by Valentin Lorentz on 2020-02-06 14:46:05 +0100) * Upstream changes: - v0.0.171 - * Split 'content_add' method into 'content_add' and 'skipped_content_add'. - * Increase Cassandra requests timeout to 1 second. -- Software Heritage autobuilder (on jenkins-debian1) Thu, 06 Feb 2020 14:07:37 +0000 swh-storage (0.0.170-1~swh3) unstable-swh; urgency=medium * Update build dependencies -- Antoine R. Dumont (@ardumont) Mon, 03 Feb 2020 17:30:38 +0100 swh-storage (0.0.170-1~swh2) unstable-swh; urgency=medium * Update build dependencies -- Antoine R. Dumont (@ardumont) Mon, 03 Feb 2020 16:00:39 +0100 swh-storage (0.0.170-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.170 - (tagged by Antoine R. Dumont (@ardumont) on 2020-02-03 14:11:53 +0100) * Upstream changes: - v0.0.170 - swh.storage.cassandra: Add Cassandra backend implementation -- Software Heritage autobuilder (on jenkins-debian1) Mon, 03 Feb 2020 13:23:48 +0000 swh-storage (0.0.169-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.169 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-30 13:40:00 +0100) * Upstream changes: - v0.0.169 - retry: Add retry behavior on pipeline storage with flushing failure -- Software Heritage autobuilder (on jenkins-debian1) Thu, 30 Jan 2020 13:26:23 +0000 swh-storage (0.0.168-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.168 - (tagged by Valentin Lorentz on 2020-01-30 11:19:31 +0100) * Upstream changes: - v0.0.168 - * Implement content_update for the in-mem storage. - * Remove cur/db arguments from the in- mem storage. - * Move Storage documentation and endpoint paths to a new StorageInterface class - * Rename in_memory.Storage to in_memory.InMemoryStorage. - * CONTRIBUTORS: add Daniele Serafini -- Software Heritage autobuilder (on jenkins-debian1) Thu, 30 Jan 2020 10:25:30 +0000 swh-storage (0.0.167-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.167 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-24 14:55:57 +0100) * Upstream changes: - v0.0.167 - pgstorage: Empty temp tables instead of dropping them -- Software Heritage autobuilder (on jenkins-debian1) Fri, 24 Jan 2020 14:01:57 +0000 swh-storage (0.0.166-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.166 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-24 09:51:52 +0100) * Upstream changes: - v0.0.166 - storage: Add endpoint to get missing content (by sha1_git) and missing snapshot - Remove redundant config checks in load_and_check_config - Remove 'id' and 'object_id' from the output of object_find_by_sha1_git - Make origin_visit_get_random return None instead of {} if there are no results - docs: Fix sphinx warnings -- Software Heritage autobuilder (on jenkins-debian1) Fri, 24 Jan 2020 09:00:12 +0000 swh-storage (0.0.165-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.165 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-17 14:04:53 +0100) * Upstream changes: - v0.0.165 - storage.retry: Fix objects loading when using generator parameters -- Software Heritage autobuilder (on jenkins-debian1) Fri, 17 Jan 2020 13:09:39 +0000 swh-storage (0.0.164-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.164 - (tagged by Antoine Lambert on 2020-01-16 17:54:40 +0100) * Upstream changes: - version 0.0.164 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 16 Jan 2020 17:05:02 +0000 swh-storage (0.0.163-1~swh2) unstable-swh; urgency=medium * Fix test dependency -- Antoine R. Dumont (@ardumont) Tue, 14 Jan 2020 17:26:08 +0100 swh-storage (0.0.163-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.163 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-14 17:12:03 +0100) * Upstream changes: - v0.0.163 - retry: Improve proxy storage for add endpoints - in_memory: Make directory_get_random return None when storage empty - storage: Change content_get_metadata api to return Dict[bytes, List[Dict]] - storage: Add content_get_partition endpoint to replace content_get_range - storage: Add endpoint origin_list to replace origin_get_range -- Software Heritage autobuilder (on jenkins-debian1) Tue, 14 Jan 2020 16:17:45 +0000 swh-storage (0.0.162-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.162 - (tagged by Valentin Lorentz on 2019-12-16 14:37:44 +0100) * Upstream changes: - v0.0.162 - Add {content,directory,revision,release,snapshot}_get_random. -- Software Heritage autobuilder (on jenkins-debian1) Mon, 16 Dec 2019 13:41:39 +0000 swh-storage (0.0.161-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.161 - (tagged by Antoine R. Dumont (@ardumont) on 2019-12-10 15:03:28 +0100) * Upstream changes: - v0.0.161 - storage: Add endpoint to randomly pick an origin -- Software Heritage autobuilder (on jenkins-debian1) Tue, 10 Dec 2019 14:08:15 +0000 swh-storage (0.0.160-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.160 - (tagged by Antoine R. Dumont (@ardumont) on 2019-12-06 11:15:48 +0100) * Upstream changes: - v0.0.160 - storage.buffer: Buffer release objects as well - storage.tests: Unify tests sample data - Implement origin lookup by sha1 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 06 Dec 2019 10:23:44 +0000 swh-storage (0.0.159-1~swh2) unstable-swh; urgency=medium * Force fast hypothesis profile when running tests -- Antoine R. Dumont (@ardumont) Tue, 26 Nov 2019 17:08:16 +0100 swh-storage (0.0.159-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.159 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-22 11:05:41 +0100) * Upstream changes: - v0.0.159 - Add 'pipeline' storage "class" for more readable configurations. - tests: Improve tests environments configuration - Fix a few typos reported by codespell - Add a pre-commit-hooks.yaml config file - Remove utils/(dump|fix)_revisions scripts -- Software Heritage autobuilder (on jenkins-debian1) Fri, 22 Nov 2019 10:10:31 +0000 swh-storage (0.0.158-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.158 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-14 13:33:00 +0100) * Upstream changes: - v0.0.158 - Drop schemata module (migrated back to swh-lister) -- Software Heritage autobuilder (on jenkins-debian1) Thu, 14 Nov 2019 12:37:18 +0000 swh-storage (0.0.157-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.157 - (tagged by Nicolas Dandrimont on 2019-11-13 13:22:39 +0100) * Upstream changes: - Release swh.storage 0.0.157 - schemata.distribution: Fix bogus NotImplementedError on Area.index_uris -- Software Heritage autobuilder (on jenkins-debian1) Wed, 13 Nov 2019 12:27:07 +0000 swh-storage (0.0.156-1~swh2) unstable-swh; urgency=medium * Add version constraint on psycopg2 -- Nicolas Dandrimont Wed, 30 Oct 2019 18:21:34 +0100 swh-storage (0.0.156-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.156 - (tagged by Valentin Lorentz on 2019-10-30 15:12:10 +0100) * Upstream changes: - v0.0.156 - * Stop supporting origin ids in API (except in origin_get_range). - * Make visit['origin'] a string everywhere (instead of a dict). -- Software Heritage autobuilder (on jenkins-debian1) Wed, 30 Oct 2019 14:29:28 +0000 swh-storage (0.0.155-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.155 - (tagged by David Douard on 2019-10-30 12:14:14 +0100) * Upstream changes: - v0.0.155 -- Software Heritage autobuilder (on jenkins-debian1) Wed, 30 Oct 2019 11:18:37 +0000 swh-storage (0.0.154-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.154 - (tagged by Antoine R. Dumont (@ardumont) on 2019-10-17 13:47:57 +0200) * Upstream changes: - v0.0.154 - Fix tests in debian build -- Software Heritage autobuilder (on jenkins-debian1) Thu, 17 Oct 2019 11:52:46 +0000 swh-storage (0.0.153-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.153 - (tagged by Antoine R. Dumont (@ardumont) on 2019-10-17 13:21:00 +0200) * Upstream changes: - v0.0.153 - Deploy new test fixture -- Software Heritage autobuilder (on jenkins-debian1) Thu, 17 Oct 2019 11:26:12 +0000 swh-storage (0.0.152-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.152 - (tagged by Antoine R. Dumont (@ardumont) on 2019-10-08 16:55:43 +0200) * Upstream changes: - v0.0.152 - swh.storage.buffer: Add buffering proxy storage implementation - swh.storage.filter: Add filtering storage implementation - swh.storage.tests: Improve db transaction handling - swh.storage.tests: Add more tests - swh.storage.storage: introduce a db() context manager -- Software Heritage autobuilder (on jenkins-debian1) Tue, 08 Oct 2019 15:03:16 +0000 swh-storage (0.0.151-1~swh2) unstable-swh; urgency=medium * Add missing build-dependency on python3-swh.journal -- Nicolas Dandrimont Tue, 01 Oct 2019 18:28:19 +0200 swh-storage (0.0.151-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.151 - (tagged by Stefano Zacchiroli on 2019-10-01 10:04:36 +0200) * Upstream changes: - v0.0.151 - * tox: anticipate mypy run to just after flake8 - * mypy.ini: be less flaky w.r.t. the packages installed in tox - * storage.py: ignore typing of optional get_journal_writer import - * mypy: ignore swh.journal to work-around dependency loop - * init.py: switch to documented way of extending path - * typing: minimal changes to make a no- op mypy run pass - * Write objects to the journal only if they don't exist yet. - * Use origin URLs for skipped_content['origin'] instead of origin ids. - * Properly mock get_journal_writer for the remote-pg-storage tests. - * journal_writer: use journal writer from swh.journal - * fix typos in docstrings and sample paths - * storage.origin_visit_add: Remove deprecated 'ts' parameter - * click "required" param wants bool, not int -- Software Heritage autobuilder (on jenkins-debian1) Tue, 01 Oct 2019 08:09:53 +0000 swh-storage (0.0.150-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.150 - (tagged by Antoine R. Dumont (@ardumont) on 2019-09-04 16:09:59 +0200) * Upstream changes: - v0.0.150 - tests/test_storage: Remove failing assertion after swh-model update - tests/test_storage: Fix tests execution with psycopg2 < 2.8 -- Software Heritage autobuilder (on jenkins-debian1) Wed, 04 Sep 2019 14:16:09 +0000 swh-storage (0.0.149-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.149 - (tagged by Antoine R. Dumont (@ardumont) on 2019-09-03 14:00:57 +0200) * Upstream changes: - v0.0.149 - Add support for origin_url in origin_metadata_* - Make origin_add/origin_visit_update validate their input - Make snapshot_add validate its input - Make revision_add and release_add validate their input - Make directory_add validate its input - Make content_add validate its input using swh-model -- Software Heritage autobuilder (on jenkins-debian1) Tue, 03 Sep 2019 12:27:51 +0000 swh-storage (0.0.148-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.148 - (tagged by Valentin Lorentz on 2019-08-23 10:33:02 +0200) * Upstream changes: - v0.0.148 - Tests improvements: - * Remove 'next_branch' from test input data. - * Fix off-by-one error when using origin_visit_upsert on with an unknown visit id. - * Use explicit arguments for origin_visit_add. - * Remove test_content_missing__marked_missing, it makes no sense. - Drop person ids: - * Stop leaking person ids. - * Remove person_get endpoint. - Logging fixes: - * Enforce log level for the werkzeug logger. - * Eliminate warnings about %TYPE. - * api: use RPCServerApp and RPCClient instead of deprecated classes - Other: - * Add support for skipped content in in- memory storage -- Software Heritage autobuilder (on jenkins-debian1) Fri, 23 Aug 2019 08:48:21 +0000 swh-storage (0.0.147-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.147 - (tagged by Valentin Lorentz on 2019-07-18 12:11:37 +0200) * Upstream changes: - Make origin_get ignore the `type` argument -- Software Heritage autobuilder (on jenkins-debian1) Thu, 18 Jul 2019 10:16:16 +0000 swh-storage (0.0.146-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.146 - (tagged by Valentin Lorentz on 2019-07-18 10:46:21 +0200) * Upstream changes: - Progress toward getting rid of origin ids - * Less dependency on origin ids in the in-mem storage - * add the SWH_STORAGE_IN_MEMORY_ENABLE_ORIGIN_IDS env var - * Remove legacy behavior of snapshot_add -- Software Heritage autobuilder (on jenkins-debian1) Thu, 18 Jul 2019 08:52:09 +0000 swh-storage (0.0.145-1~swh3) unstable-swh; urgency=medium * Properly rebuild for unstable-swh -- Nicolas Dandrimont Thu, 11 Jul 2019 14:03:30 +0200 swh-storage (0.0.145-1~swh2) buster-swh; urgency=medium * Remove useless swh.scheduler dependency -- Nicolas Dandrimont Thu, 11 Jul 2019 13:53:45 +0200 swh-storage (0.0.145-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.145 - (tagged by Valentin Lorentz on 2019-07-02 12:00:53 +0200) * Upstream changes: - v0.0.145 - Add an 'origin_visit_find_by_date' endpoint. - Add support for origin urls in all endpoints -- Software Heritage autobuilder (on jenkins-debian1) Tue, 02 Jul 2019 10:19:19 +0000 swh-storage (0.0.143-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.143 - (tagged by Valentin Lorentz on 2019-06-05 13:18:14 +0200) * Upstream changes: - Add test for snapshot/release counters. -- Software Heritage autobuilder (on jenkins-debian1) Mon, 01 Jul 2019 12:38:40 +0000 swh-storage (0.0.142-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.142 - (tagged by Valentin Lorentz on 2019-06-11 15:24:49 +0200) * Upstream changes: - Mark network tests, so they can be disabled. -- Software Heritage autobuilder (on jenkins-debian1) Tue, 11 Jun 2019 13:44:19 +0000 swh-storage (0.0.141-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.141 - (tagged by Valentin Lorentz on 2019-06-06 17:05:03 +0200) * Upstream changes: - Add support for using URL instead of ID in snapshot_get_latest. -- Software Heritage autobuilder (on jenkins-debian1) Tue, 11 Jun 2019 10:36:32 +0000 swh-storage (0.0.140-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.140 - (tagged by mihir(faux__) on 2019-03-24 21:47:31 +0530) * Upstream changes: - Changes the output of content_find method to a list in case of hash collisions and makes the sql query on python side and added test duplicate input, colliding sha256 and colliding blake2s256 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 16 May 2019 12:09:04 +0000 swh-storage (0.0.139-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.139 - (tagged by Nicolas Dandrimont on 2019-04-18 17:57:57 +0200) * Upstream changes: - Release swh.storage v0.0.139 - Backwards- compatibility improvements for snapshot_add - Better transactionality in revision_add/release_add - Fix backwards metric names - Handle shallow histories properly -- Software Heritage autobuilder (on jenkins-debian1) Thu, 18 Apr 2019 16:08:28 +0000 swh-storage (0.0.138-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.138 - (tagged by Valentin Lorentz on 2019-04-09 16:40:49 +0200) * Upstream changes: - Use the db_transaction decorator on all _add() methods. - So they gracefully release the connection on error instead - of relying on reference-counting to call the Db's `__del__` - (which does not happen in Hypothesis tests) because a ref - to it is kept via the traceback object. -- Software Heritage autobuilder (on jenkins-debian1) Tue, 09 Apr 2019 16:50:48 +0000 swh-storage (0.0.137-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.137 - (tagged by Valentin Lorentz on 2019-04-08 15:40:24 +0200) * Upstream changes: - Make test_origin_get_range run faster. -- Software Heritage autobuilder (on jenkins-debian1) Mon, 08 Apr 2019 13:56:16 +0000 swh-storage (0.0.135-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.135 - (tagged by Valentin Lorentz on 2019-04-04 20:42:32 +0200) * Upstream changes: - Make content_add_metadata require a ctime argument. - This makes Python set the ctime instead of pgsql. -- Software Heritage autobuilder (on jenkins-debian1) Fri, 05 Apr 2019 14:43:28 +0000 swh-storage (0.0.134-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.134 - (tagged by Valentin Lorentz on 2019-04-03 13:38:58 +0200) * Upstream changes: - Don't leak origin ids to the journal. -- Software Heritage autobuilder (on jenkins-debian1) Thu, 04 Apr 2019 10:16:09 +0000 swh-storage (0.0.132-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.132 - (tagged by Valentin Lorentz on 2019-04-01 11:50:30 +0200) * Upstream changes: - Use sha1 instead of bigint as FK from origin_visit to snapshot (part 1: add new column) -- Software Heritage autobuilder (on jenkins-debian1) Mon, 01 Apr 2019 13:30:48 +0000 swh-storage (0.0.131-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.131 - (tagged by Nicolas Dandrimont on 2019-03-28 17:24:44 +0100) * Upstream changes: - Release swh.storage v0.0.131 - Add statsd metrics to storage RPC backend - Clean up snapshot_add/origin_visit_update - Uniformize RPC backend to use POSTs everywhere -- Software Heritage autobuilder (on jenkins-debian1) Thu, 28 Mar 2019 16:34:07 +0000 swh-storage (0.0.130-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.130 - (tagged by Valentin Lorentz on 2019-02-26 10:50:44 +0100) * Upstream changes: - Add an helper function to list all origins in the storage. -- Software Heritage autobuilder (on jenkins-debian1) Wed, 13 Mar 2019 14:01:04 +0000 swh-storage (0.0.129-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.129 - (tagged by Valentin Lorentz on 2019-02-27 10:42:29 +0100) * Upstream changes: - Double the timeout of revision_get. - Metadata indexers often hit the limit. -- Software Heritage autobuilder (on jenkins-debian1) Fri, 01 Mar 2019 10:11:28 +0000 swh-storage (0.0.128-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.128 - (tagged by Antoine R. Dumont (@ardumont) on 2019-02-21 14:59:22 +0100) * Upstream changes: - v0.0.128 - api.server: Fix wrong exception type - storage.cli: Fix cli entry point name to the expected name (setup.py) -- Software Heritage autobuilder (on jenkins-debian1) Thu, 21 Feb 2019 14:07:23 +0000 swh-storage (0.0.127-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.127 - (tagged by Antoine R. Dumont (@ardumont) on 2019-02-21 13:34:19 +0100) * Upstream changes: - v0.0.127 - api.wsgi: Open wsgi entrypoint and check config at startup time - api.server: Make the api server load and check its configuration - swh.storage.cli: Migrate the api server startup in swh.storage.cli -- Software Heritage autobuilder (on jenkins-debian1) Thu, 21 Feb 2019 12:59:48 +0000 swh-storage (0.0.126-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.126 - (tagged by Valentin Lorentz on 2019-02-21 10:18:26 +0100) * Upstream changes: - Double the timeout of snapshot_get_latest. - Metadata indexers often hit the limit. -- Software Heritage autobuilder (on jenkins-debian1) Thu, 21 Feb 2019 11:24:52 +0000 swh-storage (0.0.125-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.125 - (tagged by Antoine R. Dumont (@ardumont) on 2019-02-14 10:13:31 +0100) * Upstream changes: - v0.0.125 - api/server: Do not read configuration at each request -- Software Heritage autobuilder (on jenkins-debian1) Thu, 14 Feb 2019 16:57:01 +0000 swh-storage (0.0.124-1~swh3) unstable-swh; urgency=low * New upstream release, fixing the distribution this time -- Antoine R. Dumont (@ardumont) Thu, 14 Feb 2019 17:51:29 +0100 swh-storage (0.0.124-1~swh2) unstable; urgency=medium * New upstream release for dependency fix reasons -- Antoine R. Dumont (@ardumont) Thu, 14 Feb 2019 09:27:55 +0100 swh-storage (0.0.124-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.124 - (tagged by Antoine Lambert on 2019-02-12 14:40:53 +0100) * Upstream changes: - version 0.0.124 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 12 Feb 2019 13:46:08 +0000 swh-storage (0.0.123-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.123 - (tagged by Antoine R. Dumont (@ardumont) on 2019-02-08 15:06:49 +0100) * Upstream changes: - v0.0.123 - Make Storage.origin_get support a list of origins, like other - Storage.*_get methods. - Stop using _to_bytes functions. - Use the BaseDb (and friends) from swh-core -- Software Heritage autobuilder (on jenkins-debian1) Fri, 08 Feb 2019 14:14:18 +0000 swh-storage (0.0.122-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.122 - (tagged by Antoine Lambert on 2019-01-28 11:57:27 +0100) * Upstream changes: - version 0.0.122 -- Software Heritage autobuilder (on jenkins-debian1) Mon, 28 Jan 2019 11:02:45 +0000 swh-storage (0.0.121-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.121 - (tagged by Antoine Lambert on 2019-01-28 11:31:48 +0100) * Upstream changes: - version 0.0.121 -- Software Heritage autobuilder (on jenkins-debian1) Mon, 28 Jan 2019 10:36:40 +0000 swh-storage (0.0.120-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.120 - (tagged by Antoine Lambert on 2019-01-17 12:04:27 +0100) * Upstream changes: - version 0.0.120 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 17 Jan 2019 11:12:47 +0000 swh-storage (0.0.119-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.119 - (tagged by Antoine R. Dumont (@ardumont) on 2019-01-11 11:57:13 +0100) * Upstream changes: - v0.0.119 - listener: Notify Kafka when an origin visit is updated -- Software Heritage autobuilder (on jenkins-debian1) Fri, 11 Jan 2019 11:02:07 +0000 swh-storage (0.0.118-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.118 - (tagged by Antoine Lambert on 2019-01-09 16:59:15 +0100) * Upstream changes: - version 0.0.118 -- Software Heritage autobuilder (on jenkins-debian1) Wed, 09 Jan 2019 18:51:34 +0000 swh-storage (0.0.117-1~swh1) unstable-swh; urgency=medium * v0.0.117 * listener: Adapt decoding behavior depending on the object type -- Antoine R. Dumont (@ardumont) Thu, 20 Dec 2018 14:48:44 +0100 swh-storage (0.0.116-1~swh1) unstable-swh; urgency=medium * v0.0.116 * Update requirements to latest swh.core -- Antoine R. Dumont (@ardumont) Fri, 14 Dec 2018 15:57:04 +0100 swh-storage (0.0.115-1~swh1) unstable-swh; urgency=medium * version 0.0.115 -- Antoine Lambert Fri, 14 Dec 2018 15:47:52 +0100 swh-storage (0.0.114-1~swh1) unstable-swh; urgency=medium * version 0.0.114 -- Antoine Lambert Wed, 05 Dec 2018 10:59:49 +0100 swh-storage (0.0.113-1~swh1) unstable-swh; urgency=medium * v0.0.113 * in-memory storage: Add recursive argument to directory_ls endpoint -- Antoine R. Dumont (@ardumont) Fri, 30 Nov 2018 11:56:44 +0100 swh-storage (0.0.112-1~swh1) unstable-swh; urgency=medium * v0.0.112 * in-memory storage: Align with existing storage * docstring: Improvements and adapt according to api * doc: update index to match new swh-doc format * Increase test coverage for stat_counters + fix its bugs. -- Antoine R. Dumont (@ardumont) Fri, 30 Nov 2018 10:28:02 +0100 swh-storage (0.0.111-1~swh1) unstable-swh; urgency=medium * v0.0.111 * Move generative tests in their own module * Open in-memory storage implementation -- Antoine R. Dumont (@ardumont) Wed, 21 Nov 2018 08:55:14 +0100 swh-storage (0.0.110-1~swh1) unstable-swh; urgency=medium * v0.0.110 * storage: Open content_get_range endpoint * tests: Start using hypothesis for tests generation * Improvements: Remove SQLisms from the tests and API * docs: Document metadata providers -- Antoine R. Dumont (@ardumont) Fri, 16 Nov 2018 11:53:14 +0100 swh-storage (0.0.109-1~swh1) unstable-swh; urgency=medium * version 0.0.109 -- Antoine Lambert Mon, 12 Nov 2018 14:11:09 +0100 swh-storage (0.0.108-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.108 * Add a function to get a full snapshot from the paginated view -- Nicolas Dandrimont Thu, 18 Oct 2018 18:32:10 +0200 swh-storage (0.0.107-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.107 * Enable pagination of snapshot branches * Drop occurrence-related tables * Drop entity-related tables -- Nicolas Dandrimont Wed, 17 Oct 2018 15:06:07 +0200 swh-storage (0.0.106-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.106 * Fix origin_visit_get_latest_snapshot logic * Improve directory iterator * Drop backwards compatibility between snapshots and occurrences * Drop the occurrence table -- Nicolas Dandrimont Mon, 08 Oct 2018 17:03:54 +0200 swh-storage (0.0.105-1~swh1) unstable-swh; urgency=medium * v0.0.105 * Increase directory_ls endpoint to 20 seconds * Add snapshot to the stats endpoint * Improve documentation -- Antoine R. Dumont (@ardumont) Mon, 10 Sep 2018 11:36:27 +0200 swh-storage (0.0.104-1~swh1) unstable-swh; urgency=medium * version 0.0.104 -- Antoine Lambert Wed, 29 Aug 2018 15:55:37 +0200 swh-storage (0.0.103-1~swh1) unstable-swh; urgency=medium * v0.0.103 * swh.storage.storage: origin_add returns updated list of dict with id -- Antoine R. Dumont (@ardumont) Mon, 30 Jul 2018 11:47:53 +0200 swh-storage (0.0.102-1~swh1) unstable-swh; urgency=medium * Release swh-storage v0.0.102 * Stop using temporary tables for read-only queries * Add timeouts for some read-only queries -- Nicolas Dandrimont Tue, 05 Jun 2018 14:06:54 +0200 swh-storage (0.0.101-1~swh1) unstable-swh; urgency=medium * v0.0.101 * swh.storage.api.client: Permit to specify the query timeout option -- Antoine R. Dumont (@ardumont) Thu, 24 May 2018 12:13:51 +0200 swh-storage (0.0.100-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.100 * remote api: only instantiate storage once per import * add thread-awareness to the storage implementation * properly cleanup after tests * parallelize objstorage and storage additions -- Nicolas Dandrimont Sat, 12 May 2018 18:12:40 +0200 swh-storage (0.0.99-1~swh1) unstable-swh; urgency=medium * v0.0.99 * storage: Add methods to compute directories/revisions diff * Add a new table for "bucketed" object counts * doc: update table clusters in SQL diagram * swh.storage.content_missing: Improve docstring -- Antoine R. Dumont (@ardumont) Tue, 20 Feb 2018 13:32:25 +0100 swh-storage (0.0.98-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.98 * Switch backwards compatibility for snapshots off -- Nicolas Dandrimont Tue, 06 Feb 2018 15:27:15 +0100 swh-storage (0.0.97-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.97 * refactor database initialization * use a separate thread instead of a temporary file for COPY operations * add more snapshot-related endpoints -- Nicolas Dandrimont Tue, 06 Feb 2018 14:07:07 +0100 swh-storage (0.0.96-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.96 * Add snapshot models * Add support for hg revision type -- Nicolas Dandrimont Tue, 19 Dec 2017 16:25:57 +0100 swh-storage (0.0.95-1~swh1) unstable-swh; urgency=medium * v0.0.95 * swh.storage: Rename indexer_configuration to tool * swh.storage: Migrate indexer model to its own model -- Antoine R. Dumont (@ardumont) Thu, 07 Dec 2017 09:56:31 +0100 swh-storage (0.0.94-1~swh1) unstable-swh; urgency=medium * v0.0.94 * Open searching origins methods to storage -- Antoine R. Dumont (@ardumont) Tue, 05 Dec 2017 12:32:57 +0100 swh-storage (0.0.93-1~swh1) unstable-swh; urgency=medium * v0.0.93 * swh.storage: Open indexer_configuration_add endpoint * swh-data: Update content mimetype indexer configuration * origin_visit_get: make order repeatable * db: Make unique indices actually unique and vice versa * Add origin_metadata endpoints (add, get, etc...) * cleanup: Remove unused content provenance cache tables -- Antoine R. Dumont (@ardumont) Fri, 24 Nov 2017 11:14:11 +0100 swh-storage (0.0.92-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.92 * make swh.storage.schemata work on SQLAlchemy 1.0 -- Nicolas Dandrimont Thu, 12 Oct 2017 19:51:24 +0200 swh-storage (0.0.91-1~swh1) unstable-swh; urgency=medium * Release swh.storage version 0.0.91 * Update packaging runes -- Nicolas Dandrimont Thu, 12 Oct 2017 18:41:46 +0200 swh-storage (0.0.90-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.90 * Remove leaky dependency on python3-kafka -- Nicolas Dandrimont Wed, 11 Oct 2017 18:53:22 +0200 swh-storage (0.0.89-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.89 * Add new package for ancillary schemata * Add new metadata-related entry points * Update for new swh.model -- Nicolas Dandrimont Wed, 11 Oct 2017 17:39:29 +0200 swh-storage (0.0.88-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.88 * Move the archiver to its own module * Prepare building for stretch -- Nicolas Dandrimont Fri, 30 Jun 2017 14:52:12 +0200 swh-storage (0.0.87-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.87 * update tasks to new swh.scheduler api -- Nicolas Dandrimont Mon, 12 Jun 2017 17:54:11 +0200 swh-storage (0.0.86-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.86 * archiver updates -- Nicolas Dandrimont Tue, 06 Jun 2017 18:43:43 +0200 swh-storage (0.0.85-1~swh1) unstable-swh; urgency=medium * v0.0.85 * Improve license endpoint's unknown license policy -- Antoine R. Dumont (@ardumont) Tue, 06 Jun 2017 17:55:40 +0200 swh-storage (0.0.84-1~swh1) unstable-swh; urgency=medium * v0.0.84 * Update indexer endpoints to use indexer configuration id * Add indexer configuration endpoint -- Antoine R. Dumont (@ardumont) Fri, 02 Jun 2017 16:16:47 +0200 swh-storage (0.0.83-1~swh1) unstable-swh; urgency=medium * v0.0.83 * Add blake2s256 new hash computation on content -- Antoine R. Dumont (@ardumont) Fri, 31 Mar 2017 12:27:09 +0200 swh-storage (0.0.82-1~swh1) unstable-swh; urgency=medium * v0.0.82 * swh.storage.listener: Subscribe to new origin notifications * sql/swh-func: improve equality check on the three columns for swh_content_missing * swh.storage: add length to directory listing primitives * refactoring: Migrate from swh.core.hashutil to swh.model.hashutil * swh.storage.archiver.updater: Create a content updater journal client * vault: add a git fast-import cooker * vault: generic cache to allow multiple cooker types and formats -- Antoine R. Dumont (@ardumont) Tue, 21 Mar 2017 14:50:16 +0100 swh-storage (0.0.81-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.81 * archiver improvements for mass injection in azure -- Nicolas Dandrimont Thu, 09 Mar 2017 11:15:28 +0100 swh-storage (0.0.80-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.80 * archiver improvements related to the mass injection of contents in azure * updates to the vault cooker -- Nicolas Dandrimont Tue, 07 Mar 2017 15:12:35 +0100 swh-storage (0.0.79-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.79 * archiver: keep counts of objects in each archive * converters: normalize timestamps using swh.model -- Nicolas Dandrimont Tue, 14 Feb 2017 19:37:36 +0100 swh-storage (0.0.78-1~swh1) unstable-swh; urgency=medium * v0.0.78 * Refactoring some common code into swh.core + adaptation api calls in * swh.objstorage and swh.storage (storage and vault) -- Antoine R. Dumont (@ardumont) Thu, 26 Jan 2017 15:08:03 +0100 swh-storage (0.0.77-1~swh1) unstable-swh; urgency=medium * v0.0.77 * Paginate results for origin_visits endpoint -- Antoine R. Dumont (@ardumont) Thu, 19 Jan 2017 14:41:49 +0100 swh-storage (0.0.76-1~swh1) unstable-swh; urgency=medium * v0.0.76 * Unify storage and objstorage configuration and instantiation functions -- Antoine R. Dumont (@ardumont) Thu, 15 Dec 2016 18:25:58 +0100 swh-storage (0.0.75-1~swh1) unstable-swh; urgency=medium * v0.0.75 * Add information on indexer tools (T610) -- Antoine R. Dumont (@ardumont) Fri, 02 Dec 2016 18:21:36 +0100 swh-storage (0.0.74-1~swh1) unstable-swh; urgency=medium * v0.0.74 * Use strict equality for content ctags' symbols search -- Antoine R. Dumont (@ardumont) Tue, 29 Nov 2016 17:25:29 +0100 swh-storage (0.0.73-1~swh1) unstable-swh; urgency=medium * v0.0.73 * Improve ctags search query for edge cases -- Antoine R. Dumont (@ardumont) Mon, 28 Nov 2016 16:34:55 +0100 swh-storage (0.0.72-1~swh1) unstable-swh; urgency=medium * v0.0.72 * Permit pagination on content_ctags_search api endpoint -- Antoine R. Dumont (@ardumont) Thu, 24 Nov 2016 14:19:29 +0100 swh-storage (0.0.71-1~swh1) unstable-swh; urgency=medium * v0.0.71 * Open full-text search endpoint on ctags -- Antoine R. Dumont (@ardumont) Wed, 23 Nov 2016 17:33:51 +0100 swh-storage (0.0.70-1~swh1) unstable-swh; urgency=medium * v0.0.70 * Add new license endpoints (add/get) * Update ctags endpoints to align update conflict policy -- Antoine R. Dumont (@ardumont) Thu, 10 Nov 2016 17:27:49 +0100 swh-storage (0.0.69-1~swh1) unstable-swh; urgency=medium * v0.0.69 * storage: Open ctags entry points (missing, add, get) * storage: allow adding several origins at once -- Antoine R. Dumont (@ardumont) Thu, 20 Oct 2016 16:07:07 +0200 swh-storage (0.0.68-1~swh1) unstable-swh; urgency=medium * v0.0.68 * indexer: Open mimetype/language get endpoints * indexer: Add the mimetype/language add function with conflict_update flag * archiver: Extend worker-to-backend to transmit messages to another * queue (once done) -- Antoine R. Dumont (@ardumont) Thu, 13 Oct 2016 15:30:21 +0200 swh-storage (0.0.67-1~swh1) unstable-swh; urgency=medium * v0.0.67 * Fix provenance storage init function -- Antoine R. Dumont (@ardumont) Wed, 12 Oct 2016 02:24:12 +0200 swh-storage (0.0.66-1~swh1) unstable-swh; urgency=medium * v0.0.66 * Improve provenance configuration format -- Antoine R. Dumont (@ardumont) Wed, 12 Oct 2016 01:39:26 +0200 swh-storage (0.0.65-1~swh1) unstable-swh; urgency=medium * v0.0.65 * Open api entry points for swh.indexer about content mimetype and * language * Update schema graph to latest version -- Antoine R. Dumont (@ardumont) Sat, 08 Oct 2016 10:00:30 +0200 swh-storage (0.0.64-1~swh1) unstable-swh; urgency=medium * v0.0.64 * Fix: Missing incremented version 5 for archiver.dbversion * Retrieve information on a content cached * sql/swh-func: content cache populates lines in deterministic order -- Antoine R. Dumont (@ardumont) Thu, 29 Sep 2016 21:50:59 +0200 swh-storage (0.0.63-1~swh1) unstable-swh; urgency=medium * v0.0.63 * Make the 'worker to backend' destination agnostic (message parameter) * Improve 'unknown sha1' policy (archiver db can lag behind swh db) * Improve 'force copy' policy -- Antoine R. Dumont (@ardumont) Fri, 23 Sep 2016 12:29:50 +0200 swh-storage (0.0.62-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.62 * Updates to the provenance cache to reduce churn on the main tables -- Nicolas Dandrimont Thu, 22 Sep 2016 18:54:52 +0200 swh-storage (0.0.61-1~swh1) unstable-swh; urgency=medium * v0.0.61 * Handle copies of unregistered sha1 in archiver db * Fix copy to only the targeted destination * Update to latest python3-swh.core dependency -- Antoine R. Dumont (@ardumont) Thu, 22 Sep 2016 13:44:05 +0200 swh-storage (0.0.60-1~swh1) unstable-swh; urgency=medium * v0.0.60 * Update archiver dependencies -- Antoine R. Dumont (@ardumont) Tue, 20 Sep 2016 16:46:48 +0200 swh-storage (0.0.59-1~swh1) unstable-swh; urgency=medium * v0.0.59 * Unify configuration property between director/worker * Deal with potential missing contents in the archiver db * Improve get_contents_error implementation * Remove dead code in swh.storage.db about archiver -- Antoine R. Dumont (@ardumont) Sat, 17 Sep 2016 12:50:14 +0200 swh-storage (0.0.58-1~swh1) unstable-swh; urgency=medium * v0.0.58 * ArchiverDirectorToBackend reads sha1 from stdin and sends chunks of sha1 * for archival. -- Antoine R. Dumont (@ardumont) Fri, 16 Sep 2016 22:17:14 +0200 swh-storage (0.0.57-1~swh1) unstable-swh; urgency=medium * v0.0.57 * Update swh.storage.archiver -- Antoine R. Dumont (@ardumont) Thu, 15 Sep 2016 16:30:11 +0200 swh-storage (0.0.56-1~swh1) unstable-swh; urgency=medium * v0.0.56 * Vault: Add vault implementation (directory cooker & cache * implementation + its api) * Archiver: Add another archiver implementation (direct to backend) -- Antoine R. Dumont (@ardumont) Thu, 15 Sep 2016 10:56:35 +0200 swh-storage (0.0.55-1~swh1) unstable-swh; urgency=medium * v0.0.55 * Fix origin_visit endpoint -- Antoine R. Dumont (@ardumont) Thu, 08 Sep 2016 15:21:28 +0200 swh-storage (0.0.54-1~swh1) unstable-swh; urgency=medium * v0.0.54 * Open origin_visit_get_by entry point -- Antoine R. Dumont (@ardumont) Mon, 05 Sep 2016 12:36:34 +0200 swh-storage (0.0.53-1~swh1) unstable-swh; urgency=medium * v0.0.53 * Add cache about content provenance * debian: fix python3-swh.storage.archiver runtime dependency * debian: create new package python3-swh.storage.provenance -- Antoine R. Dumont (@ardumont) Fri, 02 Sep 2016 11:14:09 +0200 swh-storage (0.0.52-1~swh1) unstable-swh; urgency=medium * v0.0.52 * Package python3-swh.storage.archiver -- Antoine R. Dumont (@ardumont) Thu, 25 Aug 2016 14:55:23 +0200 swh-storage (0.0.51-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.51 * Add new metadata column to origin_visit * Update swh-add-directory script for updated API -- Nicolas Dandrimont Wed, 24 Aug 2016 14:36:03 +0200 swh-storage (0.0.50-1~swh1) unstable-swh; urgency=medium * v0.0.50 * Add a function to pull (only) metadata for a list of contents * Update occurrence_add api entry point to properly deal with origin_visit * Add origin_visit api entry points to create/update origin_visit -- Antoine R. Dumont (@ardumont) Tue, 23 Aug 2016 16:29:26 +0200 swh-storage (0.0.49-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.49 * Proper dependency on python3-kafka -- Nicolas Dandrimont Fri, 19 Aug 2016 13:45:52 +0200 swh-storage (0.0.48-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.48 * Updates to the archiver * Notification support for new object creations -- Nicolas Dandrimont Fri, 19 Aug 2016 12:13:50 +0200 swh-storage (0.0.47-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.47 * Update storage archiver to new schemaless schema -- Nicolas Dandrimont Fri, 22 Jul 2016 16:59:19 +0200 swh-storage (0.0.46-1~swh1) unstable-swh; urgency=medium * v0.0.46 * Update archiver bootstrap -- Antoine R. Dumont (@ardumont) Wed, 20 Jul 2016 19:04:42 +0200 swh-storage (0.0.45-1~swh1) unstable-swh; urgency=medium * v0.0.45 * Separate swh.storage.archiver's db from swh.storage.storage -- Antoine R. Dumont (@ardumont) Tue, 19 Jul 2016 15:05:36 +0200 swh-storage (0.0.44-1~swh1) unstable-swh; urgency=medium * v0.0.44 * Open listing visits per origin api -- Quentin Campos Fri, 08 Jul 2016 11:27:10 +0200 swh-storage (0.0.43-1~swh1) unstable-swh; urgency=medium * v0.0.43 * Extract objstorage to its own package swh.objstorage -- Quentin Campos Mon, 27 Jun 2016 14:57:12 +0200 swh-storage (0.0.42-1~swh1) unstable-swh; urgency=medium * Add an object storage multiplexer to allow transition between multiple versions of object storages. -- Quentin Campos Tue, 21 Jun 2016 15:03:52 +0200 swh-storage (0.0.41-1~swh1) unstable-swh; urgency=medium * Refactoring of the object storage in order to allow multiple versions of it, as well as a multiplexer for version transition. -- Quentin Campos Thu, 16 Jun 2016 15:54:16 +0200 swh-storage (0.0.40-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.40: * Refactor objstorage to allow for different implementations * Updates to the checker functionality * Bump swh.core dependency to v0.0.20 -- Nicolas Dandrimont Tue, 14 Jun 2016 17:25:42 +0200 swh-storage (0.0.39-1~swh1) unstable-swh; urgency=medium * v0.0.39 * Add run_from_webserver function for objstorage api server * Add unique identifier message on default api server route endpoints -- Antoine R. Dumont (@ardumont) Fri, 20 May 2016 15:27:34 +0200 swh-storage (0.0.38-1~swh1) unstable-swh; urgency=medium * v0.0.38 * Add an http api for object storage * Implement an archiver to perform backup copies -- Quentin Campos Fri, 20 May 2016 14:40:14 +0200 swh-storage (0.0.37-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.37 * Add fullname to person table * Add svn as a revision type -- Nicolas Dandrimont Fri, 08 Apr 2016 16:44:24 +0200 swh-storage (0.0.36-1~swh1) unstable-swh; urgency=medium * Release swh.storage v0.0.36 * Add json-schema documentation for the jsonb fields * Overhaul entity handling -- Nicolas Dandrimont Wed, 16 Mar 2016 17:27:17 +0100 swh-storage (0.0.35-1~swh1) unstable-swh; urgency=medium * Release swh-storage v0.0.35 * Factor in temporary tables with only an id (db v059) * Allow generic object search by sha1_git (db v060) -- Nicolas Dandrimont Thu, 25 Feb 2016 16:21:01 +0100 swh-storage (0.0.34-1~swh1) unstable-swh; urgency=medium * Release swh.storage version 0.0.34 * occurrence improvements * commit metadata improvements -- Nicolas Dandrimont Fri, 19 Feb 2016 18:20:07 +0100 swh-storage (0.0.33-1~swh1) unstable-swh; urgency=medium * Bump swh.storage to version 0.0.33 -- Nicolas Dandrimont Fri, 05 Feb 2016 11:17:00 +0100 swh-storage (0.0.32-1~swh1) unstable-swh; urgency=medium * v0.0.32 * Let the person's id flow * sql/upgrades/051: 050->051 schema change * sql/upgrades/050: 049->050 schema change - Clean up obsolete functions * sql/upgrades/049: Final take for 048->049 schema change. * sql: Use a new schema for occurrences -- Antoine R. Dumont (@ardumont) Fri, 29 Jan 2016 17:44:27 +0100 swh-storage (0.0.31-1~swh1) unstable-swh; urgency=medium * v0.0.31 * Deal with occurrence_history.branch, occurrence.branch, release.name as bytes -- Antoine R. Dumont (@ardumont) Wed, 27 Jan 2016 15:45:53 +0100 swh-storage (0.0.30-1~swh1) unstable-swh; urgency=medium * Prepare swh.storage v0.0.30 release * type-agnostic occurrences and revisions -- Nicolas Dandrimont Tue, 26 Jan 2016 07:36:43 +0100 swh-storage (0.0.29-1~swh1) unstable-swh; urgency=medium * v0.0.29 * New: * Upgrade sql schema to 041→043 * Deal with communication downtime between clients and storage * Open occurrence_get(origin_id) to retrieve latest occurrences per origin * Open release_get_by to retrieve a release by origin * Open directory_get to retrieve information on directory by id * Open entity_get to retrieve information on entity + hierarchy from its uuid * Open directory_get that retrieve information on directory per id * Update: * directory_get/directory_ls: Rename to directory_ls * revision_log: update to retrieve logs from multiple root revisions * revision_get_by: branch name filtering is now optional -- Antoine R. Dumont (@ardumont) Wed, 20 Jan 2016 16:15:50 +0100 swh-storage (0.0.28-1~swh1) unstable-swh; urgency=medium * v0.0.28 * Open entity_get api -- Antoine R. Dumont (@ardumont) Fri, 15 Jan 2016 16:37:27 +0100 swh-storage (0.0.27-1~swh1) unstable-swh; urgency=medium * v0.0.27 * Open directory_entry_get_by_path api * Improve get_revision_by api performance * sql/swh-schema: add index on origin(type, url) --> improve origin lookup api * Bump to 039 db version -- Antoine R. Dumont (@ardumont) Fri, 15 Jan 2016 12:42:47 +0100 swh-storage (0.0.26-1~swh1) unstable-swh; urgency=medium * v0.0.26 * Open revision_get_by to retrieve a revision by occurrence criterion filtering * sql/upgrades/036: add 035→036 upgrade script -- Antoine R. Dumont (@ardumont) Wed, 13 Jan 2016 12:46:44 +0100 swh-storage (0.0.25-1~swh1) unstable-swh; urgency=medium * v0.0.25 * Limit results in swh_revision_list* * Create the package to align the current db production version on https://archive.softwareheritage.org/ -- Antoine R. Dumont (@ardumont) Fri, 08 Jan 2016 11:33:08 +0100 swh-storage (0.0.24-1~swh1) unstable-swh; urgency=medium * Prepare swh.storage release v0.0.24 * Add a limit argument to revision_log -- Nicolas Dandrimont Wed, 06 Jan 2016 15:12:53 +0100 swh-storage (0.0.23-1~swh1) unstable-swh; urgency=medium * v0.0.23 * Protect against overflow, wrapped in ValueError for client * Fix relative path import for remote storage. * api to retrieve revision_log is now 'parents' aware -- Antoine R. Dumont (@ardumont) Wed, 06 Jan 2016 11:30:58 +0100 swh-storage (0.0.22-1~swh1) unstable-swh; urgency=medium * Release v0.0.22 * Fix relative import for remote storage -- Nicolas Dandrimont Wed, 16 Dec 2015 16:04:48 +0100 swh-storage (0.0.21-1~swh1) unstable-swh; urgency=medium * Prepare release v0.0.21 * Protect the storage api client from overflows * Add a get_storage function mapping to local or remote storage -- Nicolas Dandrimont Wed, 16 Dec 2015 13:34:46 +0100 swh-storage (0.0.20-1~swh1) unstable-swh; urgency=medium * v0.0.20 * allow numeric timestamps with offset * Open revision_log api * start migration to swh.model -- Antoine R. Dumont (@ardumont) Mon, 07 Dec 2015 15:20:36 +0100 swh-storage (0.0.19-1~swh1) unstable-swh; urgency=medium * v0.0.19 * Improve directory listing with content data * Open person_get * Open release_get data reading * Improve origin_get api * Effort to unify api output on dict (for read) * Migrate backend to 032 -- Antoine R. Dumont (@ardumont) Fri, 27 Nov 2015 13:33:34 +0100 swh-storage (0.0.18-1~swh1) unstable-swh; urgency=medium * v0.0.18 * Improve origin_get to permit retrieval per id * Update directory_get implementation (add join from * directory_entry_file to content) * Open release_get : [sha1] -> [Release] -- Antoine R. Dumont (@ardumont) Thu, 19 Nov 2015 11:18:35 +0100 swh-storage (0.0.17-1~swh1) unstable-swh; urgency=medium * Prepare deployment of swh.storage v0.0.17 * Add some entity related entry points -- Nicolas Dandrimont Tue, 03 Nov 2015 16:40:59 +0100 swh-storage (0.0.16-1~swh1) unstable-swh; urgency=medium * v0.0.16 * Add metadata column in revision (db version 29) * cache http connection for remote storage client -- Antoine R. Dumont (@ardumont) Thu, 29 Oct 2015 10:29:00 +0100 swh-storage (0.0.15-1~swh1) unstable-swh; urgency=medium * Prepare deployment of swh.storage v0.0.15 * Allow population of fetch_history * Update organizations / projects as entities * Use schema v028 for directory addition -- Nicolas Dandrimont Tue, 27 Oct 2015 11:43:39 +0100 swh-storage (0.0.14-1~swh1) unstable-swh; urgency=medium * Prepare swh.storage v0.0.14 deployment -- Nicolas Dandrimont Fri, 16 Oct 2015 15:34:08 +0200 swh-storage (0.0.13-1~swh1) unstable-swh; urgency=medium * Prepare deploying swh.storage v0.0.13 -- Nicolas Dandrimont Fri, 16 Oct 2015 14:51:44 +0200 swh-storage (0.0.12-1~swh1) unstable-swh; urgency=medium * Prepare deploying swh.storage v0.0.12 -- Nicolas Dandrimont Tue, 13 Oct 2015 12:39:18 +0200 swh-storage (0.0.11-1~swh1) unstable-swh; urgency=medium * Preparing deployment of swh.storage v0.0.11 -- Nicolas Dandrimont Fri, 09 Oct 2015 17:44:51 +0200 swh-storage (0.0.10-1~swh1) unstable-swh; urgency=medium * Prepare deployment of swh.storage v0.0.10 -- Nicolas Dandrimont Tue, 06 Oct 2015 17:37:00 +0200 swh-storage (0.0.9-1~swh1) unstable-swh; urgency=medium * Prepare deployment of swh.storage v0.0.9 -- Nicolas Dandrimont Thu, 01 Oct 2015 19:03:00 +0200 swh-storage (0.0.8-1~swh1) unstable-swh; urgency=medium * Prepare deployment of swh.storage v0.0.8 -- Nicolas Dandrimont Thu, 01 Oct 2015 11:32:46 +0200 swh-storage (0.0.7-1~swh1) unstable-swh; urgency=medium * Prepare deployment of swh.storage v0.0.7 -- Nicolas Dandrimont Tue, 29 Sep 2015 16:52:54 +0200 swh-storage (0.0.6-1~swh1) unstable-swh; urgency=medium * Prepare deployment of swh.storage v0.0.6 -- Nicolas Dandrimont Tue, 29 Sep 2015 16:43:24 +0200 swh-storage (0.0.5-1~swh1) unstable-swh; urgency=medium * Prepare deploying swh.storage v0.0.5 -- Nicolas Dandrimont Tue, 29 Sep 2015 16:27:00 +0200 swh-storage (0.0.1-1~swh1) unstable-swh; urgency=medium * Initial release * swh.storage.api: Properly escape arbitrary byte sequences in arguments -- Nicolas Dandrimont Tue, 22 Sep 2015 17:02:34 +0200 diff --git a/docs/archive-copies.rst b/docs/archive-copies.rst index 09f2ea40..75f1ed0d 100644 --- a/docs/archive-copies.rst +++ b/docs/archive-copies.rst @@ -1,48 +1,48 @@ :orphan: .. _archive-copies: Archive copies ============== .. _swh-storage-copies-layout: .. figure:: images/swh-archive-copies.svg :width: 1024px :align: center Layout of Software Heritage archive copies (click to zoom). The Software Heritage archive exists in several copies, to minimize the risk of losing archived source code artifacts. The layout of existing copies, their relationships, as well as their geographical and administrative domains are shown in the layout diagram above. We recall that the archive is conceptually organized as a graph, and specifically a Merkle DAG, see :ref:`data model ` for more information. Ingested source code artifacts land directly on the **primary copy**, which is updated live and also used as reference for deduplication purposes. There, different parts of the Merkle DAG as stored using different backend technologies. The leaves of the graph, i.e., *content objects* (or "blobs"), are stored in a key-value object storage, using their SHA1 identifiers as keys (see :ref:`persistent identifiers `). SHA1 collision avoidance is enforced by the :mod:`swh.storage` module. The *rest of the graph* is stored in a Postgres database (see :ref:`SQL storage `). -At the time of writing, the primary object storage contains about 5 billion +At of 2022-09-27, the primary object storage contains about 12 billion blobs with a median size of 3 KB---yes, that is *a lot of very small -files*---for a total compressed size of about 200 TB. The Postgres database -takes about 8 TB, half of which required by indexes. In terms of graph metrics, -the Merkle DAG has about 10 B nodes and 100 B edges. +files*---for a total compressed size of about 800 TB. The Postgres database +takes about 8 TB (compressed), half of which is used by indexes. In terms of +graph metrics, the Merkle DAG has about 26 B nodes and 370 B edges. The **secondary copy** is hosted on Microsoft Azure cloud, using its native blob storage for the object storage and a large virtual machine to run a Postgres instance there. The database is kept up-to-date w.r.t. the primary copy using Postgres WAL replication. The object storage is kept up-to-date using :mod:`swh.archiver`. Archive copies (as opposed to archive mirrors) are operated by the Software Heritage Team at Inria. The primary archived copy is geographically located at Rocquencourt, France; the secondary copy hosted in the Europe West region of the Azure cloud. diff --git a/docs/extrinsic-metadata-specification.rst b/docs/extrinsic-metadata-specification.rst index a9c7fa90..d1b0b8e4 100644 --- a/docs/extrinsic-metadata-specification.rst +++ b/docs/extrinsic-metadata-specification.rst @@ -1,355 +1,365 @@ :orphan: .. _extrinsic-metadata-specification: Extrinsic metadata specification ================================ :term:`Extrinsic metadata` is information about software that is not part of the source code itself but still closely related to the software. Typical sources for extrinsic metadata are: the hosting place of a repository, which can offer metadata via its web view or API; external registries like collaborative curation initiatives; and out-of-band information available at source code archival time. Since they are not part of the source code, a dedicated mechanism to fetch and store them is needed. This specification assumes the reader is familiar with Software Heritage's :ref:`architecture` and :ref:`data-model`. Metadata sources ---------------- Authorities ^^^^^^^^^^^ Metadata authorities are entities that provide metadata about an :term:`origin`. Metadata authorities include: code hosting places, :term:`deposit` submitters, and registries (eg. Wikidata). An authority is uniquely defined by these properties: * its type, representing the kind of authority, which is one of these values: * ``deposit_client``, for metadata pushed to Software Heritage at the same time as a software artifact * ``forge``, for metadata pulled from the same source as the one hosting the software artifacts (which includes package managers) * ``registry``, for metadata pulled from a third-party * its URL, which unambiguously identifies an instance of the authority type. Examples: =============== ================================= type url =============== ================================= deposit_client https://hal.archives-ouvertes.fr/ deposit_client https://hal.inria.fr/ deposit_client https://software.intel.com/ forge https://gitlab.com/ forge https://gitlab.inria.fr/ forge https://0xacab.org/ forge https://github.com/ registry https://www.wikidata.org/ registry https://swmath.org/ registry https://ascl.net/ =============== ================================= Metadata fetchers ^^^^^^^^^^^^^^^^^ Metadata fetchers are software components used to fetch metadata from a metadata authority, and ingest them into the Software Heritage archive. A metadata fetcher is uniquely defined by these properties: * its type * its version Examples: * :term:`loaders `, which may either discover metadata as a side-effect of loading source code, or be dedicated to fetching metadata. * :term:`listers `, which may discover metadata as a side-effect of discovering origins. * :term:`deposit` submitters, which push metadata to SWH from a third-party; usually at the same time as a :term:`software artifact` * crawlers, which fetch metadata from an authority in a way that is none of the above (eg. by querying a specific API of the origin's forge). Storage API ----------- Authorities and metadata fetchers ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Data model ~~~~~~~~~~ The :term:`storage` API uses these structures to represent metadata authorities and metadata fetchers (simplified Python code):: class MetadataAuthorityType(Enum): DEPOSIT_CLIENT = "deposit_client" FORGE = "forge" REGISTRY = "registry" class MetadataAuthority(BaseModel): """Represents an entity that provides metadata about an origin or software artifact.""" object_type = "metadata_authority" type: MetadataAuthorityType url: str class MetadataFetcher(BaseModel): """Represents a software component used to fetch metadata from a metadata authority, and ingest them into the Software Heritage archive.""" object_type = "metadata_fetcher" name: str version: str Storage API ~~~~~~~~~~~ * ``metadata_authority_add(authorities: List[MetadataAuthority])`` which adds a list of ``MetadataAuthority`` to the storage. * ``metadata_authority_get(type: MetadataAuthorityType, url: str) -> Optional[MetadataAuthority]`` which looks up a known authority (there is at most one) and if it is known, returns the corresponding ``MetadataAuthority`` * ``metadata_fetcher_add(fetchers: List[MetadataFetcher])`` which adds a list of ``MetadataFetcher`` to the storage. * ``metadata_fetcher_get(name: str, version: str) -> Optional[MetadataFetcher]`` which looks up a known fetcher (there is at most one) and if it is known, returns the corresponding ``MetadataFetcher`` Artifact metadata ^^^^^^^^^^^^^^^^^ Data model ~~~~~~~~~~ The storage database stores metadata on origins, and all software artifacts supported by the data model. They are represented using this structure (simplified Python code):: class RawExtrinsicMetadata(HashableObject, BaseModel): object_type = "raw_extrinsic_metadata" # target object target: ExtendedSWHID # source discovery_date: datetime.datetime authority: MetadataAuthority fetcher: MetadataFetcher # the metadata itself format: str metadata: bytes # context origin: Optional[str] = None visit: Optional[int] = None snapshot: Optional[CoreSWHID] = None release: Optional[CoreSWHID] = None revision: Optional[CoreSWHID] = None path: Optional[bytes] = None directory: Optional[CoreSWHID] = None id: Sha1Git The ``target`` may be: * a regular :ref:`core SWHID `, * a SWHID-like string with type ``ori`` and the SHA1 of an origin URL * a SWHID-like string with type ``emd`` and the SHA1 of an other ``RawExtrinsicMetadata`` object (to represent metadata on metadata objects) ``id`` is a sha1 hash of the ``RawExtrinsicMetadata`` object itself; it may be used in other ``RawExtrinsicMetadata`` as target. ``discovery_date`` is a Python datetime. ``authority`` must be a dict containing keys ``type`` and ``url``, and ``fetcher`` a dict containing keys ``name`` and ``version``. The authority and fetcher must be known to the storage before using this endpoint. ``format`` is a text field indicating the format of the content of the ``metadata`` byte string, see `extrinsic-metadata-formats`_. ``metadata`` is a byte array. Its format is specific to each authority; and is treated as an opaque value by the storage. Unifying these various formats into a common language is outside the scope of this specification. Finally, the remaining fields allow metadata can be given on a specific artifact within a specified context (for example: a directory in a specific revision from a specific visit on a specific origin) which will be stored along the metadata itself. For example, two origins may develop the same file independently; the information about authorship, licensing or even description may vary about the same artifact in a different context. This is why it is important to qualify the metadata with the complete context for which it is intended, if any. The allowed context fields for each ``target`` type are: * for ``emd`` (extrinsic metadata) and ``ori`` (origin): none * for ``snp`` (snapshot): ``origin`` (a URL) and ``visit`` (an integer) * for ``rel`` (release): those above, plus ``snapshot`` (the core SWHID of a snapshot) * for ``rev`` (revision): all those above, plus ``release`` (the core SWHID of a release) * for ``dir`` (directory): all those above, plus ``revision`` (the core SWHID of a revision) and ``path`` (a byte string), representing the path to this directory from the root of the ``revision`` * for ``cnt`` (content): all those above, plus ``directory`` (the core SWHID of a directory) All keys are optional, but should be provided whenever possible. The dictionary may be empty, if metadata is fully independent from context. In all cases, ``visit`` should only be provided if ``origin`` is (as visit ids are only unique with respect to an origin). Storage API ~~~~~~~~~~~ The storage API offers three endpoints to manipulate origin metadata: * Adding metadata:: raw_extrinsic_metadata_add(metadata: List[RawExtrinsicMetadata]) which adds a list of ``RawExtrinsicMetadata`` objects, whose ``metadata`` field is a byte string obtained from a given authority and associated to the ``target``. * Getting all metadata:: raw_extrinsic_metadata_get( target: ExtendedSWHID, authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, ) -> PagedResult[RawExtrinsicMetadata]: returns a list of ``RawExtrinsicMetadata`` with the given ``target`` and from the given ``authority``. If ``after`` is provided, only objects whose discovery date is more recent are returnered. ``PagedResult`` is a structure containing the results themselves, and a ``next_page_token`` used to fetch the next list of results, if any .. _extrinsic-metadata-formats: Extrinsic metadata formats -------------------------- Formats are identified by an opaque string. When possible, it should be the MIME type already in use to describe the metadata format outside Software Heritage. Otherwise it should be unambiguous, printable ASCII without spaces, and human-readable. Here is a list of all the metadata format stored: ``application/vnd.github.v3+json`` The metadata is the response of an API call to GitHub. +``cpan-release-json`` + The metadata is the response of an API call to `CPAN's /release/{author}/{release} + `_ endpoint. ``gitlab-project-json`` - The metadata is the response of an API call to a Gitlab instance. + The metadata is the response of an API call to `Gitlab's /api/v4/projects/:id + `_ endpoint. +``gitea-project-json`` + The metadata is the response of an API call to `Gitea's /api/v1/repos/{owner}/{repo} + `_ endpoint. +``gogs-project-json`` + The metadata is the response of an API call to `Gogs's /api/v1/repos/:owner/:repo + `_ endpoint. ``pypi-project-json`` The metadata is a release entry from a PyPI project's JSON file, extracted and re-serialized. ``replicate-npm-package-json`` ditto, but from a replicate.npmjs.com project ``nixguix-sources-json`` ditto, but from https://nix-community.github.io/nixpkgs-swh/ ``original-artifacts-json`` tarball data, see below ``sword-v2-atom-codemeta`` XML Atom document, with Codemeta metadata, as sent by a deposit client, see the :ref:`Deposit protocol reference `. ``sword-v2-atom-codemeta-v2`` Deprecated alias of ``sword-v2-atom-codemeta`` ``sword-v2-atom-codemeta-v2-in-json`` Deprecated, JSON serialization of a ``sword-v2-atom-codemeta`` document. ``xml-deposit-info`` Information about a deposit, to identify the provenance of a metadata object sent via swh-deposit, see below Details on some of these formats: .. _extrinsic-metadata-original-artifacts-json: original-artifacts-json ^^^^^^^^^^^^^^^^^^^^^^^ This is a loosely defined format, originally used as a ``metadata`` column on the ``revision`` table that changed over the years. It is a JSON array, and each entry is a JSON object representing an archive (tarball, zipball, ...) that was unpackaged by the SWH loader before loading its content in Software Heritage. When writing this specification, it was stabilized to this format:: [ { "length": , "filename": "", "checksums": { "sha1": "", "sha256": "", }, "url": "" }, ... ] Older ``original-artifacts-json`` were migrated to use this format, but may be missing some of the keys. xml-deposit-info ^^^^^^^^^^^^^^^^ Deposits with code objects are loaded as their own origin, so we can look them up in the deposit database from their metadata (which hold the origin as a context). This is not true for metadata-only deposits, because we don't create an origin for them; so we need to store this information somewhere. The naive solution would be to insert them in the Atom entry provided by the client, but it means altering a document before we archive it, which potentially corrupts it or loses part of the data. Therefore, on each metadata-only deposit, the deposit creates an extra "metametadata" object, with the original metadata object as target, and using this format:: {{ deposit.id }} {{ deposit.client.provider_url }} {{ deposit.collection.name }} diff --git a/swh.storage.egg-info/PKG-INFO b/swh.storage.egg-info/PKG-INFO index 8d55c604..d94d6ef5 100644 --- a/swh.storage.egg-info/PKG-INFO +++ b/swh.storage.egg-info/PKG-INFO @@ -1,246 +1,246 @@ Metadata-Version: 2.1 Name: swh.storage -Version: 1.6.0 +Version: 1.7.1 Summary: Software Heritage storage manager Home-page: https://forge.softwareheritage.org/diffusion/DSTO/ Author: Software Heritage developers Author-email: swh-devel@inria.fr 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/ 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: journal License-File: LICENSE License-File: AUTHORS swh-storage =========== Abstraction layer over the archive, allowing to access all stored source code artifacts as well as their metadata. See the [documentation](https://docs.softwareheritage.org/devel/swh-storage/index.html) for more details. ## Quick start ### Dependencies Python tests for this module include tests that cannot be run without a local Postgresql database, so you need the Postgresql server executable on your machine (no need to have a running Postgresql server). They also expect a cassandra server. #### Debian-like host ``` $ sudo apt install libpq-dev postgresql-11 cassandra ``` #### Non Debian-like host The tests expects the path to `cassandra` to either be unspecified, it is then looked up at `/usr/sbin/cassandra`, either specified through the environment variable `SWH_CASSANDRA_BIN`. Optionally, you can avoid running the cassandra tests. ``` (swh) :~/swh-storage$ tox -- -m 'not cassandra' ``` ### Installation It is strongly recommended to use a virtualenv. In the following, we consider you work in a virtualenv named `swh`. See the [developer setup guide](https://docs.softwareheritage.org/devel/developer-setup.html#developer-setup) for a more details on how to setup a working environment. You can install the package directly from [pypi](https://pypi.org/p/swh.storage): ``` (swh) :~$ pip install swh.storage [...] ``` Or from sources: ``` (swh) :~$ git clone https://forge.softwareheritage.org/source/swh-storage.git [...] (swh) :~$ cd swh-storage (swh) :~/swh-storage$ pip install . [...] ``` Then you can check it's properly installed: ``` (swh) :~$ swh storage --help Usage: swh storage [OPTIONS] COMMAND [ARGS]... Software Heritage Storage tools. Options: -h, --help Show this message and exit. Commands: rpc-serve Software Heritage Storage RPC server. ``` ## Tests The best way of running Python tests for this module is to use [tox](https://tox.readthedocs.io/). ``` (swh) :~$ pip install tox ``` ### tox From the sources directory, simply use tox: ``` (swh) :~/swh-storage$ tox [...] ========= 315 passed, 6 skipped, 15 warnings in 40.86 seconds ========== _______________________________ summary ________________________________ flake8: commands succeeded py3: commands succeeded congratulations :) ``` Note: it is possible to set the `JAVA_HOME` environment variable to specify the version of the JVM to be used by Cassandra. For example, at the time of writing this, Cassandra does not support java 14, so one may want to use for example java 11: ``` (swh) :~/swh-storage$ export JAVA_HOME=/usr/lib/jvm/java-14-openjdk-amd64/bin/java (swh) :~/swh-storage$ tox [...] ``` ## 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: postgresql db: "dbname=softwareheritage-dev user= password=" objstorage: cls: pathslicing root: /tmp/swh-storage/ slicing: 0:2/2:4/4:6 ``` which means, this uses: - a local storage instance whose db connection is to `softwareheritage-dev` local instance, - the objstorage uses a local objstorage instance whose: - `root` path is /tmp/swh-storage, - slicing scheme is `0:2/2:4/4:6`. This means that the identifier of the content (sha1) which will be stored on disk at first level with the first 2 hex characters, the second level with the next 2 hex characters and the third level with the next 2 hex characters. And finally the complete hash file holding the raw content. For example: 00062f8bd330715c4f819373653d97b3cd34394c will be stored at 00/06/2f/00062f8bd330715c4f819373653d97b3cd34394c Note that the `root` path should exist on disk before starting the server. ### Starting the storage server If the python package has been properly installed (e.g. in a virtual env), you should be able to use the command: ``` (swh) :~/swh-storage$ swh storage rpc-serve storage.yml ``` This runs a local swh-storage api at 5002 port. ``` (swh) :~/swh-storage$ curl http://127.0.0.1:5002 Software Heritage storage server

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

``` ### And then what? In your upper layer ([loader-git](https://forge.softwareheritage.org/source/swh-loader-git/), [loader-svn](https://forge.softwareheritage.org/source/swh-loader-svn/), etc...), you can define a remote storage with this snippet of yaml configuration. ``` storage: cls: remote url: http://localhost:5002/ ``` You could directly define a postgresql storage with the following snippet: ``` storage: cls: postgresql db: service=swh-dev objstorage: cls: pathslicing root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` ## Cassandra As an alternative to PostgreSQL, swh-storage can use Cassandra as a database backend. It can be used like this: ``` storage: cls: cassandra hosts: - localhost objstorage: cls: pathslicing root: /home/storage/swh-storage/ slicing: 0:2/2:4/4:6 ``` The Cassandra swh-storage implementation supports both Cassandra >= 4.0-alpha2 and ScyllaDB >= 4.4 (and possibly earlier versions, but this is untested). While the main code supports both transparently, running tests or configuring the schema requires specific code when using ScyllaDB, enabled by setting the `SWH_USE_SCYLLADB=1` environment variable. diff --git a/swh.storage.egg-info/SOURCES.txt b/swh.storage.egg-info/SOURCES.txt index e9d59b35..9629cade 100644 --- a/swh.storage.egg-info/SOURCES.txt +++ b/swh.storage.egg-info/SOURCES.txt @@ -1,344 +1,347 @@ .git-blame-ignore-revs .gitignore .pre-commit-config.yaml AUTHORS CODE_OF_CONDUCT.md CONTRIBUTORS LICENSE MANIFEST.in Makefile Makefile.local README.md conftest.py mypy.ini pyproject.toml pytest.ini requirements-swh-journal.txt requirements-swh.txt requirements-test.txt requirements.txt setup.cfg setup.py tox.ini ./requirements-swh-journal.txt ./requirements-swh.txt ./requirements-test.txt ./requirements.txt bin/swh-storage-add-dir docs/.gitignore docs/Makefile docs/Makefile.local docs/archive-copies.rst docs/cli.rst docs/conf.py docs/extrinsic-metadata-specification.rst docs/index.rst docs/sql-storage.rst docs/_static/.placeholder docs/_templates/.placeholder docs/images/.gitignore docs/images/Makefile docs/images/swh-archive-copies.dia sql/.gitignore sql/Makefile sql/TODO sql/clusters.dot sql/bin/db-upgrade sql/bin/dot_add_content sql/doc/json 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 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/cli.py swh/storage/common.py swh/storage/exc.py swh/storage/fixer.py swh/storage/in_memory.py swh/storage/interface.py swh/storage/metrics.py swh/storage/migrate_extrinsic_metadata.py swh/storage/objstorage.py swh/storage/py.typed swh/storage/pytest_plugin.py swh/storage/replay.py swh/storage/utils.py swh/storage/writer.py swh/storage/algos/__init__.py swh/storage/algos/diff.py swh/storage/algos/dir_iterators.py swh/storage/algos/directory.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/model.py swh/storage/cassandra/schema.py swh/storage/cassandra/storage.py swh/storage/postgresql/__init__.py swh/storage/postgresql/converters.py swh/storage/postgresql/db.py swh/storage/postgresql/storage.py swh/storage/proxies/__init__.py swh/storage/proxies/buffer.py swh/storage/proxies/counter.py swh/storage/proxies/filter.py swh/storage/proxies/retry.py swh/storage/proxies/tenacious.py swh/storage/proxies/validate.py swh/storage/sql/10-superuser-init.sql swh/storage/sql/15-flavor.sql swh/storage/sql/20-enums.sql swh/storage/sql/30-schema.sql swh/storage/sql/40-funcs.sql swh/storage/sql/60-indexes.sql swh/storage/sql/logical_replication/replication_source.sql swh/storage/sql/upgrades/015.sql swh/storage/sql/upgrades/016.sql swh/storage/sql/upgrades/017.sql swh/storage/sql/upgrades/018.sql swh/storage/sql/upgrades/019.sql swh/storage/sql/upgrades/020.sql swh/storage/sql/upgrades/021.sql swh/storage/sql/upgrades/022.sql swh/storage/sql/upgrades/023.sql swh/storage/sql/upgrades/024.sql swh/storage/sql/upgrades/025.sql swh/storage/sql/upgrades/026.sql swh/storage/sql/upgrades/027.sql swh/storage/sql/upgrades/028.sql swh/storage/sql/upgrades/029.sql swh/storage/sql/upgrades/030.sql swh/storage/sql/upgrades/032.sql swh/storage/sql/upgrades/033.sql swh/storage/sql/upgrades/034.sql swh/storage/sql/upgrades/035.sql swh/storage/sql/upgrades/036.sql swh/storage/sql/upgrades/037.sql swh/storage/sql/upgrades/038.sql swh/storage/sql/upgrades/039.sql swh/storage/sql/upgrades/040.sql swh/storage/sql/upgrades/041.sql swh/storage/sql/upgrades/042.sql swh/storage/sql/upgrades/043.sql swh/storage/sql/upgrades/044.sql swh/storage/sql/upgrades/045.sql swh/storage/sql/upgrades/046.sql swh/storage/sql/upgrades/047.sql swh/storage/sql/upgrades/048.sql swh/storage/sql/upgrades/049.sql swh/storage/sql/upgrades/050.sql swh/storage/sql/upgrades/051.sql swh/storage/sql/upgrades/052.sql swh/storage/sql/upgrades/053.sql swh/storage/sql/upgrades/054.sql swh/storage/sql/upgrades/055.sql swh/storage/sql/upgrades/056.sql swh/storage/sql/upgrades/057.sql swh/storage/sql/upgrades/058.sql swh/storage/sql/upgrades/059.sql swh/storage/sql/upgrades/060.sql swh/storage/sql/upgrades/061.sql swh/storage/sql/upgrades/062.sql swh/storage/sql/upgrades/063.sql swh/storage/sql/upgrades/064.sql swh/storage/sql/upgrades/065.sql swh/storage/sql/upgrades/066.sql swh/storage/sql/upgrades/067.sql swh/storage/sql/upgrades/068.sql swh/storage/sql/upgrades/069.sql swh/storage/sql/upgrades/070.sql swh/storage/sql/upgrades/071.sql swh/storage/sql/upgrades/072.sql swh/storage/sql/upgrades/073.sql swh/storage/sql/upgrades/074.sql swh/storage/sql/upgrades/075.sql swh/storage/sql/upgrades/076.sql swh/storage/sql/upgrades/077.sql swh/storage/sql/upgrades/078.sql swh/storage/sql/upgrades/079.sql swh/storage/sql/upgrades/080.sql swh/storage/sql/upgrades/081.sql swh/storage/sql/upgrades/082.sql swh/storage/sql/upgrades/083.sql swh/storage/sql/upgrades/084.sql swh/storage/sql/upgrades/085.sql swh/storage/sql/upgrades/086.sql swh/storage/sql/upgrades/087.sql swh/storage/sql/upgrades/088.sql swh/storage/sql/upgrades/089.sql swh/storage/sql/upgrades/090.sql swh/storage/sql/upgrades/091.sql swh/storage/sql/upgrades/092.sql swh/storage/sql/upgrades/093.sql swh/storage/sql/upgrades/094.sql swh/storage/sql/upgrades/095.sql swh/storage/sql/upgrades/096.sql swh/storage/sql/upgrades/097.sql swh/storage/sql/upgrades/098.sql swh/storage/sql/upgrades/099.sql swh/storage/sql/upgrades/100.sql swh/storage/sql/upgrades/101.sql swh/storage/sql/upgrades/102.sql swh/storage/sql/upgrades/103.sql swh/storage/sql/upgrades/104.sql swh/storage/sql/upgrades/105.sql swh/storage/sql/upgrades/106.sql swh/storage/sql/upgrades/107.sql swh/storage/sql/upgrades/108.sql swh/storage/sql/upgrades/109.sql swh/storage/sql/upgrades/110.sql swh/storage/sql/upgrades/111.sql swh/storage/sql/upgrades/112.sql swh/storage/sql/upgrades/113.sql swh/storage/sql/upgrades/114.sql swh/storage/sql/upgrades/115.sql swh/storage/sql/upgrades/116.sql swh/storage/sql/upgrades/117.sql swh/storage/sql/upgrades/118.sql swh/storage/sql/upgrades/119.sql swh/storage/sql/upgrades/120.sql swh/storage/sql/upgrades/121.sql swh/storage/sql/upgrades/122.sql swh/storage/sql/upgrades/123.sql swh/storage/sql/upgrades/124.sql swh/storage/sql/upgrades/125.sql swh/storage/sql/upgrades/126.sql swh/storage/sql/upgrades/127.sql swh/storage/sql/upgrades/128.sql swh/storage/sql/upgrades/129.sql swh/storage/sql/upgrades/130.sql swh/storage/sql/upgrades/131.sql swh/storage/sql/upgrades/132.sql swh/storage/sql/upgrades/133.sql swh/storage/sql/upgrades/134.sql swh/storage/sql/upgrades/135.sql swh/storage/sql/upgrades/136.sql swh/storage/sql/upgrades/137.sql swh/storage/sql/upgrades/138.sql swh/storage/sql/upgrades/139.sql swh/storage/sql/upgrades/140.sql swh/storage/sql/upgrades/141.sql swh/storage/sql/upgrades/142.sql swh/storage/sql/upgrades/143.sql swh/storage/sql/upgrades/144.sql swh/storage/sql/upgrades/145.sql swh/storage/sql/upgrades/146.sql swh/storage/sql/upgrades/147.sql swh/storage/sql/upgrades/148.sql swh/storage/sql/upgrades/149.sql swh/storage/sql/upgrades/150.sql swh/storage/sql/upgrades/151.sql swh/storage/sql/upgrades/152.sql swh/storage/sql/upgrades/153.sql swh/storage/sql/upgrades/154.sql swh/storage/sql/upgrades/155.sql swh/storage/sql/upgrades/156.sql swh/storage/sql/upgrades/157.sql swh/storage/sql/upgrades/158.sql swh/storage/sql/upgrades/159.sql swh/storage/sql/upgrades/160.sql swh/storage/sql/upgrades/161.sql swh/storage/sql/upgrades/162.sql swh/storage/sql/upgrades/163.sql swh/storage/sql/upgrades/164.sql swh/storage/sql/upgrades/165.sql swh/storage/sql/upgrades/166.sql swh/storage/sql/upgrades/167.sql swh/storage/sql/upgrades/168.sql swh/storage/sql/upgrades/169.sql swh/storage/sql/upgrades/170.sql swh/storage/sql/upgrades/171.sql swh/storage/sql/upgrades/172.sql swh/storage/sql/upgrades/173.sql swh/storage/sql/upgrades/174.sql swh/storage/sql/upgrades/175.sql swh/storage/sql/upgrades/176.sql swh/storage/sql/upgrades/177.sql swh/storage/sql/upgrades/178.sql swh/storage/sql/upgrades/179.sql swh/storage/sql/upgrades/180.sql swh/storage/sql/upgrades/181.sql swh/storage/sql/upgrades/182.sql swh/storage/sql/upgrades/183.sql +swh/storage/sql/upgrades/184.sql +swh/storage/sql/upgrades/185.sql +swh/storage/sql/upgrades/186.sql swh/storage/tests/__init__.py swh/storage/tests/conftest.py swh/storage/tests/storage_data.py swh/storage/tests/storage_tests.py swh/storage/tests/test_api_client.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_cassandra_migration.py swh/storage/tests/test_cli.py swh/storage/tests/test_counter.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_postgresql.py swh/storage/tests/test_postgresql_converters.py swh/storage/tests/test_postgresql_flavor_mirror.py swh/storage/tests/test_postgresql_flavor_readreplica.py swh/storage/tests/test_pytest_plugin.py swh/storage/tests/test_replay.py swh/storage/tests/test_retry.py swh/storage/tests/test_revision_bw_compat.py swh/storage/tests/test_serializers.py swh/storage/tests/test_server.py swh/storage/tests/test_storage_data.py swh/storage/tests/test_tenacious.py swh/storage/tests/test_utils.py swh/storage/tests/test_validate.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_directory.py swh/storage/tests/algos/test_origin.py swh/storage/tests/algos/test_revisions_walker.py swh/storage/tests/algos/test_snapshot.py swh/storage/tests/data/storage.yml swh/storage/tests/migrate_extrinsic_metadata/test_cran.py swh/storage/tests/migrate_extrinsic_metadata/test_debian.py swh/storage/tests/migrate_extrinsic_metadata/test_deposit.py swh/storage/tests/migrate_extrinsic_metadata/test_gnu.py swh/storage/tests/migrate_extrinsic_metadata/test_nixguix.py swh/storage/tests/migrate_extrinsic_metadata/test_npm.py swh/storage/tests/migrate_extrinsic_metadata/test_pypi.py \ No newline at end of file diff --git a/swh/storage/cassandra/storage.py b/swh/storage/cassandra/storage.py index e233e555..7af48053 100644 --- a/swh/storage/cassandra/storage.py +++ b/swh/storage/cassandra/storage.py @@ -1,1758 +1,1763 @@ # Copyright (C) 2019-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import base64 from collections import defaultdict import datetime import itertools import operator import random import re from typing import ( Any, Callable, Counter, Dict, Iterable, List, Optional, Sequence, Set, Tuple, Union, ) import attr from swh.core.api.classes import stream_results from swh.core.api.serializers import msgpack_dumps, msgpack_loads from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_hex from swh.model.model import ( Content, Directory, DirectoryEntry, ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1Git, SkippedContent, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID from swh.model.swhids import ObjectType as SwhidObjectType from swh.storage.interface import ( VISIT_STATUSES, ListOrder, OriginVisitWithStatuses, PagedResult, PartialBranches, Sha1, ) from swh.storage.objstorage import ObjStorage from swh.storage.utils import map_optional, now from swh.storage.writer import JournalWriter from . import converters from ..exc import HashCollision, StorageArgumentException from ..utils import remove_keys from .common import TOKEN_BEGIN, TOKEN_END, hash_url from .cql import CqlRunner from .model import ( ContentRow, DirectoryEntryRow, DirectoryRow, ExtIDByTargetRow, ExtIDRow, MetadataAuthorityRow, MetadataFetcherRow, OriginRow, OriginVisitRow, OriginVisitStatusRow, RawExtrinsicMetadataByIdRow, RawExtrinsicMetadataRow, RevisionParentRow, SkippedContentRow, SnapshotBranchRow, SnapshotRow, ) from .schema import HASH_ALGORITHMS # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 DIRECTORY_ENTRIES_INSERT_ALGOS = ["one-by-one", "concurrent", "batch"] class CassandraStorage: def __init__( self, hosts, keyspace, objstorage, port=9042, journal_writer=None, allow_overwrite=False, consistency_level="ONE", directory_entries_insert_algo="one-by-one", ): """ A backend of swh-storage backed by Cassandra Args: hosts: Seed Cassandra nodes, to start connecting to the cluster keyspace: Name of the Cassandra database to use objstorage: Passed as argument to :class:`ObjStorage` port: Cassandra port journal_writer: Passed as argument to :class:`JournalWriter` allow_overwrite: Whether ``*_add`` functions will check if an object already exists in the database before sending it in an INSERT. ``False`` is the default as it is more efficient when there is a moderately high probability the object is already known, but ``True`` can be useful to overwrite existing objects (eg. when applying a schema update), or when the database is known to be mostly empty. Note that a ``False`` value does not guarantee there won't be any overwrite. consistency_level: The default read/write consistency to use directory_entries_insert_algo: Must be one of: * one-by-one: naive, one INSERT per directory entry, serialized * concurrent: one INSERT per directory entry, concurrent * batch: using UNLOGGED BATCH to insert many entries in a few statements """ self._hosts = hosts self._keyspace = keyspace self._port = port self._consistency_level = consistency_level self._set_cql_runner() self.journal_writer: JournalWriter = JournalWriter(journal_writer) self.objstorage: ObjStorage = ObjStorage(objstorage) self._allow_overwrite = allow_overwrite if directory_entries_insert_algo not in DIRECTORY_ENTRIES_INSERT_ALGOS: raise ValueError( f"directory_entries_insert_algo must be one of: " f"{', '.join(DIRECTORY_ENTRIES_INSERT_ALGOS)}" ) self._directory_entries_insert_algo = directory_entries_insert_algo def _set_cql_runner(self): """Used by tests when they need to reset the CqlRunner""" self._cql_runner: CqlRunner = CqlRunner( self._hosts, self._keyspace, self._port, self._consistency_level ) def check_config(self, *, check_write: bool) -> bool: self._cql_runner.check_read() return True def _content_get_from_hashes(self, algo, hashes: List[bytes]) -> Iterable: """From the name of a hash algorithm and a value of that hash, looks up the "hash -> token" secondary table (content_by_{algo}) to get tokens. Then, looks up the main table (content) to get all contents with that token, and filters out contents whose hash doesn't match.""" found_tokens = list( self._cql_runner.content_get_tokens_from_single_algo(algo, hashes) ) assert all(isinstance(token, int) for token in found_tokens) # Query the main table ('content'). rows = self._cql_runner.content_get_from_tokens(found_tokens) for row in rows: # re-check the the hash (in case of murmur3 collision) if getattr(row, algo) in hashes: yield row def _content_add(self, contents: List[Content], with_data: bool) -> Dict[str, int]: # Filter-out content already in the database. if not self._allow_overwrite: contents = [ c for c in contents if not self._cql_runner.content_get_from_pk(c.to_dict()) ] if with_data: # First insert to the objstorage, if the endpoint is # `content_add` (as opposed to `content_add_metadata`). # Must add to the objstorage before the DB and journal. Otherwise: # 1. in case of a crash the DB may "believe" we have the content, but # we didn't have time to write to the objstorage before the crash # 2. the objstorage mirroring, which reads from the journal, may attempt to # read from the objstorage before we finished writing it summary = self.objstorage.content_add( c for c in contents if c.status != "absent" ) content_add_bytes = summary["content:add:bytes"] self.journal_writer.content_add(contents) content_add = 0 for content in contents: content_add += 1 # Check for sha1 or sha1_git collisions. This test is not atomic # with the insertion, so it won't detect a collision if both # contents are inserted at the same time, but it's good enough. # # The proper way to do it would probably be a BATCH, but this # would be inefficient because of the number of partitions we # need to affect (len(HASH_ALGORITHMS)+1, which is currently 5) if not self._allow_overwrite: for algo in {"sha1", "sha1_git"}: collisions = [] # Get tokens of 'content' rows with the same value for # sha1/sha1_git # TODO: batch these requests, instead of sending them one by one rows = self._content_get_from_hashes(algo, [content.get_hash(algo)]) for row in rows: if getattr(row, algo) != content.get_hash(algo): # collision of token(partition key), ignore this # row continue for other_algo in HASH_ALGORITHMS: if getattr(row, other_algo) != content.get_hash(other_algo): # This hash didn't match; discard the row. collisions.append( {k: getattr(row, k) for k in HASH_ALGORITHMS} ) if collisions: collisions.append(content.hashes()) raise HashCollision(algo, content.get_hash(algo), collisions) (token, insertion_finalizer) = self._cql_runner.content_add_prepare( ContentRow(**remove_keys(content.to_dict(), ("data",))) ) # Then add to index tables for algo in HASH_ALGORITHMS: self._cql_runner.content_index_add_one(algo, content, token) # Then to the main table insertion_finalizer() summary = { "content:add": content_add, } if with_data: summary["content:add:bytes"] = content_add_bytes return summary def content_add(self, content: List[Content]) -> Dict[str, int]: to_add = { (c.sha1, c.sha1_git, c.sha256, c.blake2s256): c for c in content }.values() contents = [attr.evolve(c, ctime=now()) for c in to_add] return self._content_add(list(contents), with_data=True) def content_update( self, contents: List[Dict[str, Any]], keys: List[str] = [] ) -> None: raise NotImplementedError( "content_update is not supported by the Cassandra backend" ) def content_add_metadata(self, content: List[Content]) -> Dict[str, int]: return self._content_add(content, with_data=False) def content_get_data(self, content: Sha1) -> Optional[bytes]: # FIXME: Make this method support slicing the `data` return self.objstorage.content_get(content) def content_get_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, ) -> PagedResult[Content]: if limit is None: raise StorageArgumentException("limit should not be None") # Compute start and end of the range of tokens covered by the # requested partition partition_size = (TOKEN_END - TOKEN_BEGIN) // nb_partitions range_start = TOKEN_BEGIN + partition_id * partition_size range_end = TOKEN_BEGIN + (partition_id + 1) * partition_size # offset the range start according to the `page_token`. if page_token is not None: if not (range_start <= int(page_token) <= range_end): raise StorageArgumentException("Invalid page_token.") range_start = int(page_token) next_page_token: Optional[str] = None rows = self._cql_runner.content_get_token_range( range_start, range_end, limit + 1 ) contents = [] for counter, (tok, row) in enumerate(rows): if row.status == "absent": continue row_d = row.to_dict() if counter >= limit: next_page_token = str(tok) break row_d.pop("ctime") contents.append(Content(**row_d)) assert len(contents) <= limit return PagedResult(results=contents, next_page_token=next_page_token) def content_get( self, contents: List[bytes], algo: str = "sha1" ) -> List[Optional[Content]]: if algo not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "algo should be one of {','.join(DEFAULT_ALGORITHMS)}" ) key = operator.attrgetter(algo) contents_by_hash: Dict[Sha1, Optional[Content]] = {} for row in self._content_get_from_hashes(algo, contents): # Get all (sha1, sha1_git, sha256, blake2s256) whose sha1/sha1_git # matches the argument, from the index table ('content_by_*') row_d = row.to_dict() row_d.pop("ctime") content = Content(**row_d) contents_by_hash[key(content)] = content return [contents_by_hash.get(hash_) for hash_ in contents] def content_find(self, content: Dict[str, Any]) -> List[Content]: return self._content_find_many([content]) def _content_find_many(self, contents: List[Dict[str, Any]]) -> List[Content]: # Find an algorithm that is common to all the requested contents. # It will be used to do an initial filtering efficiently. # TODO: prioritize sha256, we can do more efficient lookups from this hash. filter_algos = set(HASH_ALGORITHMS) for content in contents: filter_algos &= set(content) if not filter_algos: raise StorageArgumentException( "content keys must contain at least one " f"of: {', '.join(sorted(HASH_ALGORITHMS))}" ) common_algo = list(filter_algos)[0] results = [] rows = self._content_get_from_hashes( common_algo, [content[common_algo] for content in contents] ) for row in rows: # Re-check all the hashes, in case of collisions (either of the # hash of the partition key, or the hashes in it) for content in contents: for algo in HASH_ALGORITHMS: if content.get(algo) and getattr(row, algo) != content[algo]: # This hash didn't match; discard the row. break else: # All hashes match, keep this row. row_d = row.to_dict() row_d["ctime"] = row.ctime.replace(tzinfo=datetime.timezone.utc) results.append(Content(**row_d)) break else: # No content matched; skip it pass return results def content_missing( self, contents: List[Dict[str, Any]], key_hash: str = "sha1" ) -> Iterable[bytes]: if key_hash not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "key_hash should be one of {','.join(DEFAULT_ALGORITHMS)}" ) contents_with_all_hashes = [] contents_with_missing_hashes = [] for content in contents: if DEFAULT_ALGORITHMS <= set(content): contents_with_all_hashes.append(content) else: contents_with_missing_hashes.append(content) # These contents can be queried efficiently directly in the main table for content in self._cql_runner.content_missing_from_all_hashes( contents_with_all_hashes ): yield content[key_hash] if contents_with_missing_hashes: # For these, we need the expensive index lookups + main table. # Get all contents in the database that match (at least) one of the # requested contents, concurrently. found_contents = self._content_find_many(contents_with_missing_hashes) # Bucket the known contents by hash found_contents_by_hash: Dict[str, Dict[str, list]] = { algo: defaultdict(list) for algo in DEFAULT_ALGORITHMS } for found_content in found_contents: for algo in DEFAULT_ALGORITHMS: found_contents_by_hash[algo][found_content.get_hash(algo)].append( found_content ) # For each of the requested contents, check if they are in the # 'found_contents' set (via 'found_contents_by_hash' for efficient access, # since we need to check using dict inclusion instead of hash+equality) for missing_content in contents_with_missing_hashes: # Pick any of the algorithms provided in missing_content algo = next(algo for (algo, hash_) in missing_content.items() if hash_) # Get the list of found_contents that match this hash in the # missing_content. (its length is at most 1, unless there is a # collision) found_contents_with_same_hash = found_contents_by_hash[algo][ missing_content[algo] ] # Check if there is a found_content that matches all hashes in the # missing_content. # This is functionally equivalent to 'for found_content in # found_contents', but runs almost in constant time (it is linear # in the number of hash collisions) instead of linear. # This allows this function to run in linear time overall instead of # quadratic. for found_content in found_contents_with_same_hash: # check if the found_content.hashes() dictionary contains a superset # of the (key, value) pairs in missing_content if missing_content.items() <= found_content.hashes().items(): # Found! break else: # Not found yield missing_content[key_hash] def content_missing_per_sha1(self, contents: List[bytes]) -> Iterable[bytes]: return self.content_missing([{"sha1": c} for c in contents]) def content_missing_per_sha1_git( self, contents: List[Sha1Git] ) -> Iterable[Sha1Git]: return self.content_missing( [{"sha1_git": c} for c in contents], key_hash="sha1_git" ) def content_get_random(self) -> Sha1Git: content = self._cql_runner.content_get_random() assert content, "Could not find any content" return content.sha1_git def _skipped_content_add(self, contents: List[SkippedContent]) -> Dict[str, int]: # Filter-out content already in the database. if not self._allow_overwrite: contents = [ c for c in contents if not self._cql_runner.skipped_content_get_from_pk(c.to_dict()) ] self.journal_writer.skipped_content_add(contents) for content in contents: # Compute token of the row in the main table (token, insertion_finalizer) = self._cql_runner.skipped_content_add_prepare( SkippedContentRow.from_dict({"origin": None, **content.to_dict()}) ) # Then add to index tables for algo in HASH_ALGORITHMS: self._cql_runner.skipped_content_index_add_one(algo, content, token) # Then to the main table insertion_finalizer() return {"skipped_content:add": len(contents)} def skipped_content_add(self, content: List[SkippedContent]) -> Dict[str, int]: contents = [attr.evolve(c, ctime=now()) for c in content] return self._skipped_content_add(contents) def skipped_content_missing( self, contents: List[Dict[str, Any]] ) -> Iterable[Dict[str, Any]]: for content in contents: if not self._cql_runner.skipped_content_get_from_pk(content): yield {algo: content[algo] for algo in DEFAULT_ALGORITHMS} def directory_add(self, directories: List[Directory]) -> Dict[str, int]: to_add = {d.id: d for d in directories}.values() if not self._allow_overwrite: # Filter out directories that are already inserted. missing = self.directory_missing([dir_.id for dir_ in to_add]) directories = [dir_ for dir_ in directories if dir_.id in missing] self.journal_writer.directory_add(directories) for directory in directories: # Add directory entries to the 'directory_entry' table rows = [ DirectoryEntryRow(directory_id=directory.id, **entry.to_dict()) for entry in directory.entries ] if self._directory_entries_insert_algo == "one-by-one": for row in rows: self._cql_runner.directory_entry_add_one(row) elif self._directory_entries_insert_algo == "concurrent": self._cql_runner.directory_entry_add_concurrent(rows) elif self._directory_entries_insert_algo == "batch": self._cql_runner.directory_entry_add_batch(rows) else: raise ValueError( f"Unexpected value for directory_entries_insert_algo: " f"{self._directory_entries_insert_algo}" ) # Add the directory *after* adding all the entries, so someone # calling snapshot_get_branch in the meantime won't end up # with half the entries. self._cql_runner.directory_add_one( DirectoryRow(id=directory.id, raw_manifest=directory.raw_manifest) ) return {"directory:add": len(directories)} def directory_missing(self, directories: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.directory_missing(directories) def _join_dentry_to_content( self, dentry: DirectoryEntry, contents: List[Content] ) -> Dict[str, Any]: content: Union[None, Content, SkippedContentRow] keys = ( "status", "sha1", "sha1_git", "sha256", "length", ) ret = dict.fromkeys(keys) ret.update(dentry.to_dict()) if ret["type"] == "file": for content in contents: if dentry.target == content.sha1_git: break else: target = ret["target"] assert target is not None tokens = list( self._cql_runner.skipped_content_get_tokens_from_single_hash( "sha1_git", target ) ) if tokens: content = list( self._cql_runner.skipped_content_get_from_token(tokens[0]) )[0] else: content = None if content: for key in keys: ret[key] = getattr(content, key) return ret def _directory_ls( self, directory_id: Sha1Git, recursive: bool, prefix: bytes = b"" ) -> Iterable[Dict[str, Any]]: if self.directory_missing([directory_id]): return rows = list(self._cql_runner.directory_entry_get([directory_id])) # TODO: dedup to be fast in case the directory contains the same subdir/file # multiple times contents = self._content_find_many([{"sha1_git": row.target} for row in rows]) for row in rows: entry_d = row.to_dict() # Build and yield the directory entry dict del entry_d["directory_id"] entry = DirectoryEntry.from_dict(entry_d) ret = self._join_dentry_to_content(entry, contents) ret["name"] = prefix + ret["name"] ret["dir_id"] = directory_id yield ret if recursive and ret["type"] == "dir": yield from self._directory_ls( ret["target"], True, prefix + ret["name"] + b"/" ) def directory_entry_get_by_path( self, directory: Sha1Git, paths: List[bytes] ) -> Optional[Dict[str, Any]]: return self._directory_entry_get_by_path(directory, paths, b"") def _directory_entry_get_by_path( self, directory: Sha1Git, paths: List[bytes], prefix: bytes ) -> Optional[Dict[str, Any]]: if not paths: return None contents = list(self.directory_ls(directory)) if not contents: return None def _get_entry(entries, name): """Finds the entry with the requested name, prepends the prefix (to get its full path), and returns it. If no entry has that name, returns None.""" for entry in entries: if entry["name"] == name: entry = entry.copy() entry["name"] = prefix + entry["name"] return entry first_item = _get_entry(contents, paths[0]) if len(paths) == 1: return first_item if not first_item or first_item["type"] != "dir": return None return self._directory_entry_get_by_path( first_item["target"], paths[1:], prefix + paths[0] + b"/" ) def directory_ls( self, directory: Sha1Git, recursive: bool = False ) -> Iterable[Dict[str, Any]]: yield from self._directory_ls(directory, recursive) def directory_get_entries( self, directory_id: Sha1Git, page_token: Optional[bytes] = None, limit: int = 1000, ) -> Optional[PagedResult[DirectoryEntry]]: if self.directory_missing([directory_id]): return None entries_from: bytes = page_token or b"" rows = self._cql_runner.directory_entry_get_from_name( directory_id, entries_from, limit + 1 ) entries = [ DirectoryEntry.from_dict(remove_keys(row.to_dict(), ("directory_id",))) for row in rows ] if len(entries) > limit: last_entry = entries.pop() next_page_token = last_entry.name else: next_page_token = None return PagedResult(results=entries, next_page_token=next_page_token) def directory_get_raw_manifest( self, directory_ids: List[Sha1Git] ) -> Dict[Sha1Git, Optional[bytes]]: return { dir_.id: dir_.raw_manifest for dir_ in self._cql_runner.directory_get(directory_ids) } def directory_get_random(self) -> Sha1Git: directory = self._cql_runner.directory_get_random() assert directory, "Could not find any directory" return directory.id def revision_add(self, revisions: List[Revision]) -> Dict[str, int]: # Filter-out revisions already in the database if not self._allow_overwrite: to_add = {r.id: r for r in revisions}.values() missing = self.revision_missing([rev.id for rev in to_add]) revisions = [rev for rev in revisions if rev.id in missing] self.journal_writer.revision_add(revisions) for revision in revisions: revobject = converters.revision_to_db(revision) if revobject: # Add parents first for (rank, parent) in enumerate(revision.parents): self._cql_runner.revision_parent_add_one( RevisionParentRow( id=revobject.id, parent_rank=rank, parent_id=parent ) ) # Then write the main revision row. # Writing this after all parents were written ensures that # read endpoints don't return a partial view while writing # the parents self._cql_runner.revision_add_one(revobject) return {"revision:add": len(revisions)} def revision_missing(self, revisions: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.revision_missing(revisions) def revision_get( self, revision_ids: List[Sha1Git], ignore_displayname: bool = False ) -> List[Optional[Revision]]: rows = self._cql_runner.revision_get(revision_ids) revisions: Dict[Sha1Git, Revision] = {} for row in rows: # TODO: use a single query to get all parents? # (it might have lower latency, but requires more code and more # bandwidth, because revision id would be part of each returned # row) parents = tuple(self._cql_runner.revision_parent_get(row.id)) # parent_rank is the clustering key, so results are already # sorted by rank. rev = converters.revision_from_db(row, parents=parents) revisions[rev.id] = rev return [revisions.get(rev_id) for rev_id in revision_ids] def _get_parent_revs( self, rev_ids: Iterable[Sha1Git], seen: Set[Sha1Git], limit: Optional[int], short: bool, ) -> Union[ Iterable[Dict[str, Any]], Iterable[Tuple[Sha1Git, Tuple[Sha1Git, ...]]], ]: if limit and len(seen) >= limit: return rev_ids = [id_ for id_ in rev_ids if id_ not in seen] if not rev_ids: return seen |= set(rev_ids) # We need this query, even if short=True, to return consistent # results (ie. not return only a subset of a revision's parents # if it is being written) if short: ids = self._cql_runner.revision_get_ids(rev_ids) for id_ in ids: # TODO: use a single query to get all parents? # (it might have less latency, but requires less code and more # bandwidth (because revision id would be part of each returned # row) parents = tuple(self._cql_runner.revision_parent_get(id_)) # parent_rank is the clustering key, so results are already # sorted by rank. yield (id_, parents) yield from self._get_parent_revs(parents, seen, limit, short) else: rows = self._cql_runner.revision_get(rev_ids) for row in rows: # TODO: use a single query to get all parents? # (it might have less latency, but requires less code and more # bandwidth (because revision id would be part of each returned # row) parents = tuple(self._cql_runner.revision_parent_get(row.id)) # parent_rank is the clustering key, so results are already # sorted by rank. rev = converters.revision_from_db(row, parents=parents) yield rev.to_dict() yield from self._get_parent_revs(parents, seen, limit, short) def revision_log( self, revisions: List[Sha1Git], ignore_displayname: bool = False, limit: Optional[int] = None, ) -> Iterable[Optional[Dict[str, Any]]]: seen: Set[Sha1Git] = set() yield from self._get_parent_revs(revisions, seen, limit, False) def revision_shortlog( self, revisions: List[Sha1Git], limit: Optional[int] = None ) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]: seen: Set[Sha1Git] = set() yield from self._get_parent_revs(revisions, seen, limit, True) def revision_get_random(self) -> Sha1Git: revision = self._cql_runner.revision_get_random() assert revision, "Could not find any revision" return revision.id def release_add(self, releases: List[Release]) -> Dict[str, int]: if not self._allow_overwrite: to_add = {r.id: r for r in releases}.values() missing = set(self.release_missing([rel.id for rel in to_add])) releases = [rel for rel in to_add if rel.id in missing] self.journal_writer.release_add(releases) for release in releases: if release: self._cql_runner.release_add_one(converters.release_to_db(release)) return {"release:add": len(releases)} def release_missing(self, releases: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.release_missing(releases) def release_get( self, releases: List[Sha1Git], ignore_displayname: bool = False ) -> List[Optional[Release]]: rows = self._cql_runner.release_get(releases) rels: Dict[Sha1Git, Release] = {} for row in rows: release = converters.release_from_db(row) rels[row.id] = release return [rels.get(rel_id) for rel_id in releases] def release_get_random(self) -> Sha1Git: release = self._cql_runner.release_get_random() assert release, "Could not find any release" return release.id def snapshot_add(self, snapshots: List[Snapshot]) -> Dict[str, int]: if not self._allow_overwrite: to_add = {s.id: s for s in snapshots}.values() missing = self._cql_runner.snapshot_missing([snp.id for snp in to_add]) snapshots = [snp for snp in snapshots if snp.id in missing] for snapshot in snapshots: self.journal_writer.snapshot_add([snapshot]) # Add branches for (branch_name, branch) in snapshot.branches.items(): if branch is None: target_type: Optional[str] = None target: Optional[bytes] = None else: target_type = branch.target_type.value target = branch.target self._cql_runner.snapshot_branch_add_one( SnapshotBranchRow( snapshot_id=snapshot.id, name=branch_name, target_type=target_type, target=target, ) ) # Add the snapshot *after* adding all the branches, so someone # calling snapshot_get_branch in the meantime won't end up # with half the branches. self._cql_runner.snapshot_add_one(SnapshotRow(id=snapshot.id)) return {"snapshot:add": len(snapshots)} def snapshot_missing(self, snapshots: List[Sha1Git]) -> Iterable[Sha1Git]: return self._cql_runner.snapshot_missing(snapshots) def snapshot_get(self, snapshot_id: Sha1Git) -> Optional[Dict[str, Any]]: d = self.snapshot_get_branches(snapshot_id) if d is None: return None return { "id": d["id"], "branches": { name: branch.to_dict() if branch else None for (name, branch) in d["branches"].items() }, "next_branch": d["next_branch"], } def snapshot_count_branches( self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None, ) -> Optional[Dict[Optional[str], int]]: if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None return self._cql_runner.snapshot_count_branches( snapshot_id, branch_name_exclude_prefix ) def snapshot_get_branches( self, snapshot_id: Sha1Git, branches_from: bytes = b"", branches_count: int = 1000, target_types: Optional[List[str]] = None, branch_name_include_substring: Optional[bytes] = None, branch_name_exclude_prefix: Optional[bytes] = None, ) -> Optional[PartialBranches]: if self._cql_runner.snapshot_missing([snapshot_id]): # Makes sure we don't fetch branches for a snapshot that is # being added. return None branches: List = [] while len(branches) < branches_count + 1: new_branches = list( self._cql_runner.snapshot_branch_get( snapshot_id, branches_from, branches_count + 1, branch_name_exclude_prefix, ) ) if not new_branches: break branches_from = new_branches[-1].name new_branches_filtered = new_branches # Filter by target_type if target_types: new_branches_filtered = [ branch for branch in new_branches_filtered if branch.target is not None and branch.target_type in target_types ] # Filter by branches_name_pattern if branch_name_include_substring: new_branches_filtered = [ branch for branch in new_branches_filtered if branch.name is not None and ( branch_name_include_substring is None or branch_name_include_substring in branch.name ) ] branches.extend(new_branches_filtered) if len(new_branches) < branches_count + 1: break if len(branches) > branches_count: last_branch = branches.pop(-1).name else: last_branch = None return PartialBranches( id=snapshot_id, branches={ branch.name: None if branch.target is None else SnapshotBranch( target=branch.target, target_type=TargetType(branch.target_type) ) for branch in branches }, next_branch=last_branch, ) def snapshot_get_random(self) -> Sha1Git: snapshot = self._cql_runner.snapshot_get_random() assert snapshot, "Could not find any snapshot" return snapshot.id def object_find_by_sha1_git(self, ids: List[Sha1Git]) -> Dict[Sha1Git, List[Dict]]: results: Dict[Sha1Git, List[Dict]] = {id_: [] for id_ in ids} missing_ids = set(ids) # Mind the order, revision is the most likely one for a given ID, # so we check revisions first. queries: List[Tuple[str, Callable[[List[Sha1Git]], Iterable[Sha1Git]]]] = [ ("revision", self._cql_runner.revision_missing), ("release", self._cql_runner.release_missing), ("content", self.content_missing_per_sha1_git), ("directory", self._cql_runner.directory_missing), ] for (object_type, query_fn) in queries: found_ids = missing_ids - set(query_fn(list(missing_ids))) for sha1_git in found_ids: results[sha1_git].append( { "sha1_git": sha1_git, "type": object_type, } ) missing_ids.remove(sha1_git) if not missing_ids: # We found everything, skipping the next queries. break return results def origin_get(self, origins: List[str]) -> Iterable[Optional[Origin]]: return [self.origin_get_one(origin) for origin in origins] def origin_get_one(self, origin_url: str) -> Optional[Origin]: """Given an origin url, return the origin if it exists, None otherwise""" rows = list(self._cql_runner.origin_get_by_url(origin_url)) if rows: assert len(rows) == 1 return Origin(url=rows[0].url) else: return None def origin_get_by_sha1(self, sha1s: List[bytes]) -> List[Optional[Dict[str, Any]]]: results = [] for sha1 in sha1s: rows = list(self._cql_runner.origin_get_by_sha1(sha1)) origin = {"url": rows[0].url} if rows else None results.append(origin) return results def origin_list( self, page_token: Optional[str] = None, limit: int = 100 ) -> PagedResult[Origin]: # Compute what token to begin the listing from start_token = TOKEN_BEGIN if page_token: start_token = int(page_token) if not (TOKEN_BEGIN <= start_token <= TOKEN_END): raise StorageArgumentException("Invalid page_token.") next_page_token = None origins = [] # Take one more origin so we can reuse it as the next page token if any for (tok, row) in self._cql_runner.origin_list(start_token, limit + 1): origins.append(Origin(url=row.url)) # keep reference of the last id for pagination purposes last_id = tok if len(origins) > limit: # last origin id is the next page token next_page_token = str(last_id) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) def origin_search( self, url_pattern: str, page_token: Optional[str] = None, limit: int = 50, regexp: bool = False, with_visit: bool = False, visit_types: Optional[List[str]] = None, ) -> PagedResult[Origin]: # TODO: remove this endpoint, swh-search should be used instead. next_page_token = None offset = int(page_token) if page_token else 0 origin_rows = [row for row in self._cql_runner.origin_iter_all()] if regexp: pat = re.compile(url_pattern) origin_rows = [row for row in origin_rows if pat.search(row.url)] else: origin_rows = [row for row in origin_rows if url_pattern in row.url] if with_visit: origin_rows = [row for row in origin_rows if row.next_visit_id > 1] if visit_types: def _has_visit_types(origin, visit_types): for origin_visit in stream_results(self.origin_visit_get, origin): if origin_visit.type in visit_types: return True return False origin_rows = [ row for row in origin_rows if _has_visit_types(row.url, visit_types) ] origins = [Origin(url=row.url) for row in origin_rows] origins = origins[offset : offset + limit + 1] if len(origins) > limit: # next offset next_page_token = str(offset + limit) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) def origin_count( self, url_pattern: str, regexp: bool = False, with_visit: bool = False ) -> int: raise NotImplementedError( "The Cassandra backend does not implement origin_count" ) def origin_snapshot_get_all(self, origin_url: str) -> List[Sha1Git]: return list(self._cql_runner.origin_snapshot_get_all(origin_url)) def origin_add(self, origins: List[Origin]) -> Dict[str, int]: if not self._allow_overwrite: to_add = {o.url: o for o in origins}.values() origins = [ori for ori in to_add if self.origin_get_one(ori.url) is None] self.journal_writer.origin_add(origins) for origin in origins: self._cql_runner.origin_add_one( OriginRow(sha1=hash_url(origin.url), url=origin.url, next_visit_id=1) ) return {"origin:add": len(origins)} def origin_visit_add(self, visits: List[OriginVisit]) -> Iterable[OriginVisit]: for visit in visits: origin = self.origin_get_one(visit.origin) if not origin: # Cannot add a visit without an origin raise StorageArgumentException("Unknown origin %s", visit.origin) all_visits = [] for visit in visits: if visit.visit: # Set origin.next_visit_id = max(origin.next_visit_id, visit.visit+1) # so the next loader run does not reuse the id. self._cql_runner.origin_bump_next_visit_id(visit.origin, visit.visit) add_status = False else: visit_id = self._cql_runner.origin_generate_unique_visit_id( visit.origin ) visit = attr.evolve(visit, visit=visit_id) add_status = True self.journal_writer.origin_visit_add([visit]) self._cql_runner.origin_visit_add_one(OriginVisitRow(**visit.to_dict())) assert visit.visit is not None all_visits.append(visit) if add_status: self._origin_visit_status_add( OriginVisitStatus( origin=visit.origin, visit=visit.visit, date=visit.date, type=visit.type, status="created", snapshot=None, ) ) return all_visits def _origin_visit_status_add(self, visit_status: OriginVisitStatus) -> None: """Add an origin visit status""" if visit_status.type is None: visit_row = self._cql_runner.origin_visit_get_one( visit_status.origin, visit_status.visit ) if visit_row is None: raise StorageArgumentException( f"Unknown origin visit {visit_status.visit} " f"of origin {visit_status.origin}" ) visit_status = attr.evolve(visit_status, type=visit_row.type) self.journal_writer.origin_visit_status_add([visit_status]) self._cql_runner.origin_visit_status_add_one( converters.visit_status_to_row(visit_status) ) def origin_visit_status_add( self, visit_statuses: List[OriginVisitStatus] ) -> Dict[str, int]: # First round to check existence (fail early if any is ko) for visit_status in visit_statuses: origin_url = self.origin_get_one(visit_status.origin) if not origin_url: raise StorageArgumentException(f"Unknown origin {visit_status.origin}") for visit_status in visit_statuses: self._origin_visit_status_add(visit_status) return {"origin_visit_status:add": len(visit_statuses)} def _origin_visit_apply_status( self, visit: Dict[str, Any], visit_status: OriginVisitStatusRow ) -> Dict[str, Any]: """Retrieve the latest visit status information for the origin visit. Then merge it with the visit and return it. """ return { # default to the values in visit **visit, # override with the last update **visit_status.to_dict(), # visit['origin'] is the URL (via a join), while # visit_status['origin'] is only an id. "origin": visit["origin"], # but keep the date of the creation of the origin visit "date": visit["date"], # We use the visit type from origin visit # if it's not present on the origin visit status "type": visit_status.type or visit["type"], } def _origin_visit_get_latest_status(self, visit: OriginVisit) -> OriginVisitStatus: """Retrieve the latest visit status information for the origin visit object.""" assert visit.visit row = self._cql_runner.origin_visit_status_get_latest(visit.origin, visit.visit) assert row is not None visit_status = converters.row_to_visit_status(row) return attr.evolve(visit_status, origin=visit.origin) @staticmethod def _format_origin_visit_row(visit): return { **visit.to_dict(), "origin": visit.origin, "date": visit.date.replace(tzinfo=datetime.timezone.utc), } def origin_visit_get( self, origin: str, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, ) -> PagedResult[OriginVisit]: if not isinstance(order, ListOrder): raise StorageArgumentException("order must be a ListOrder value") if page_token and not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") next_page_token = None visit_from = None if page_token is None else int(page_token) visits: List[OriginVisit] = [] extra_limit = limit + 1 rows = self._cql_runner.origin_visit_get(origin, visit_from, extra_limit, order) for row in rows: visits.append(converters.row_to_visit(row)) assert len(visits) <= extra_limit if len(visits) == extra_limit: visits = visits[:limit] next_page_token = str(visits[-1].visit) return PagedResult(results=visits, next_page_token=next_page_token) def origin_visit_get_with_statuses( self, origin: str, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, ) -> PagedResult[OriginVisitWithStatuses]: next_page_token = None visit_from = None if page_token is None else int(page_token) extra_limit = limit + 1 # First get visits (plus one so we can use it as the next page token if any) rows = self._cql_runner.origin_visit_get(origin, visit_from, extra_limit, order) visits: List[OriginVisit] = [converters.row_to_visit(row) for row in rows] if visits: assert visits[0].visit is not None assert visits[-1].visit is not None visit_from = min(visits[0].visit, visits[-1].visit) visit_to = max(visits[0].visit, visits[-1].visit) # Then, fetch all statuses associated to these visits statuses_rows = self._cql_runner.origin_visit_status_get_all_range( origin, visit_from, visit_to ) visit_statuses: Dict[int, List[OriginVisitStatus]] = defaultdict(list) for status_row in statuses_rows: if allowed_statuses and status_row.status not in allowed_statuses: continue if require_snapshot and status_row.snapshot is None: continue visit_status = converters.row_to_visit_status(status_row) visit_statuses[visit_status.visit].append(visit_status) # Add pagination if there are more visits assert len(visits) <= extra_limit if len(visits) == extra_limit: # excluding that visit from the result to respect the limit size visits = visits[:limit] # last visit id is the next page token next_page_token = str(visits[-1].visit) results = [ OriginVisitWithStatuses(visit=visit, statuses=visit_statuses[visit.visit]) for visit in visits if visit.visit is not None ] return PagedResult(results=results, next_page_token=next_page_token) def origin_visit_status_get( self, origin: str, visit: int, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, ) -> PagedResult[OriginVisitStatus]: next_page_token = None date_from = None if page_token is not None: - date_from = datetime.datetime.fromisoformat(page_token) + try: + date_from = datetime.datetime.fromisoformat(page_token) + except ValueError: + raise StorageArgumentException( + "Invalid page_token argument to origin_visit_status_get." + ) from None # Take one more visit status so we can reuse it as the next page token if any rows = self._cql_runner.origin_visit_status_get_range( origin, visit, date_from, limit + 1, order ) visit_statuses = [converters.row_to_visit_status(row) for row in rows] if len(visit_statuses) > limit: # last visit status date is the next page token next_page_token = str(visit_statuses[-1].date) # excluding that visit status from the result to respect the limit size visit_statuses = visit_statuses[:limit] return PagedResult(results=visit_statuses, next_page_token=next_page_token) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime ) -> Optional[OriginVisit]: # Iterator over all the visits of the origin # This should be ok for now, as there aren't too many visits # per origin. rows = list(self._cql_runner.origin_visit_iter_all(origin)) def key(visit): dt = visit.date.replace(tzinfo=datetime.timezone.utc) - visit_date return (abs(dt), -visit.visit) if rows: return converters.row_to_visit(min(rows, key=key)) return None def origin_visit_get_by(self, origin: str, visit: int) -> Optional[OriginVisit]: row = self._cql_runner.origin_visit_get_one(origin, visit) if row: return converters.row_to_visit(row) return None def origin_visit_get_latest( self, origin: str, type: Optional[str] = None, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[OriginVisit]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) rows = self._cql_runner.origin_visit_iter_all(origin) for row in rows: visit = self._format_origin_visit_row(row) for status_row in self._cql_runner.origin_visit_status_get( origin, visit["visit"] ): updated_visit = self._origin_visit_apply_status(visit, status_row) if type is not None and updated_visit["type"] != type: continue if allowed_statuses and updated_visit["status"] not in allowed_statuses: continue if require_snapshot and updated_visit["snapshot"] is None: continue return OriginVisit( origin=visit["origin"], visit=visit["visit"], date=visit["date"], type=visit["type"], ) return None def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, ) -> Optional[OriginVisitStatus]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) rows = list(self._cql_runner.origin_visit_status_get(origin_url, visit)) # filtering is done python side as we cannot do it server side if allowed_statuses: rows = [row for row in rows if row.status in allowed_statuses] if require_snapshot: rows = [row for row in rows if row.snapshot is not None] if not rows: return None return converters.row_to_visit_status(rows[0]) def origin_visit_status_get_random(self, type: str) -> Optional[OriginVisitStatus]: back_in_the_day = now() - datetime.timedelta(weeks=13) # 3 months back # Random position to start iteration at start_token = random.randint(TOKEN_BEGIN, TOKEN_END) # Iterator over all visits, ordered by token(origins) then visit_id rows = self._cql_runner.origin_visit_iter(start_token) for row in rows: visit = converters.row_to_visit(row) visit_status = self._origin_visit_get_latest_status(visit) if visit.date > back_in_the_day and visit_status.status == "full": return visit_status return None def stat_counters(self): rows = self._cql_runner.stat_counters() keys = ( "content", "directory", "origin", "origin_visit", "release", "revision", "skipped_content", "snapshot", ) stats = {key: 0 for key in keys} stats.update({row.object_type: row.count for row in rows}) return stats def refresh_stat_counters(self): pass def raw_extrinsic_metadata_add( self, metadata: List[RawExtrinsicMetadata] ) -> Dict[str, int]: self.journal_writer.raw_extrinsic_metadata_add(metadata) counter = Counter[ExtendedObjectType]() for metadata_entry in metadata: if not self._cql_runner.metadata_authority_get( metadata_entry.authority.type.value, metadata_entry.authority.url ): raise StorageArgumentException( f"Unknown authority {metadata_entry.authority}" ) if not self._cql_runner.metadata_fetcher_get( metadata_entry.fetcher.name, metadata_entry.fetcher.version ): raise StorageArgumentException( f"Unknown fetcher {metadata_entry.fetcher}" ) try: row = RawExtrinsicMetadataRow( id=metadata_entry.id, type=metadata_entry.target.object_type.name.lower(), target=str(metadata_entry.target), authority_type=metadata_entry.authority.type.value, authority_url=metadata_entry.authority.url, discovery_date=metadata_entry.discovery_date, fetcher_name=metadata_entry.fetcher.name, fetcher_version=metadata_entry.fetcher.version, format=metadata_entry.format, metadata=metadata_entry.metadata, origin=metadata_entry.origin, visit=metadata_entry.visit, snapshot=map_optional(str, metadata_entry.snapshot), release=map_optional(str, metadata_entry.release), revision=map_optional(str, metadata_entry.revision), path=metadata_entry.path, directory=map_optional(str, metadata_entry.directory), ) except TypeError as e: raise StorageArgumentException(*e.args) # Add to the index first self._cql_runner.raw_extrinsic_metadata_by_id_add( RawExtrinsicMetadataByIdRow( id=row.id, target=row.target, authority_type=row.authority_type, authority_url=row.authority_url, ) ) # Then to the main table self._cql_runner.raw_extrinsic_metadata_add(row) counter[metadata_entry.target.object_type] += 1 return { f"{type.value}_metadata:add": count for (type, count) in counter.items() } def raw_extrinsic_metadata_get( self, target: ExtendedSWHID, authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, ) -> PagedResult[RawExtrinsicMetadata]: if page_token is not None: (after_date, id_) = msgpack_loads(base64.b64decode(page_token)) if after and after_date < after: raise StorageArgumentException( "page_token is inconsistent with the value of 'after'." ) entries = self._cql_runner.raw_extrinsic_metadata_get_after_date_and_id( str(target), authority.type.value, authority.url, after_date, id_, ) elif after is not None: entries = self._cql_runner.raw_extrinsic_metadata_get_after_date( str(target), authority.type.value, authority.url, after ) else: entries = self._cql_runner.raw_extrinsic_metadata_get( str(target), authority.type.value, authority.url ) if limit: entries = itertools.islice(entries, 0, limit + 1) results = [] for entry in entries: assert str(target) == entry.target results.append(converters.row_to_raw_extrinsic_metadata(entry)) if len(results) > limit: results.pop() assert len(results) == limit last_result = results[-1] next_page_token: Optional[str] = base64.b64encode( msgpack_dumps( ( last_result.discovery_date, last_result.id, ) ) ).decode() else: next_page_token = None return PagedResult( next_page_token=next_page_token, results=results, ) def raw_extrinsic_metadata_get_by_ids( self, ids: List[Sha1Git] ) -> List[RawExtrinsicMetadata]: keys = self._cql_runner.raw_extrinsic_metadata_get_by_ids(ids) results: Set[RawExtrinsicMetadata] = set() for key in keys: candidates = self._cql_runner.raw_extrinsic_metadata_get( key.target, key.authority_type, key.authority_url ) candidates = [ candidate for candidate in candidates if candidate.id == key.id ] if len(candidates) > 1: raise Exception( "Found multiple RawExtrinsicMetadata objects with the same id: " + hash_to_hex(key.id) ) results.update(map(converters.row_to_raw_extrinsic_metadata, candidates)) return list(results) def raw_extrinsic_metadata_get_authorities( self, target: ExtendedSWHID ) -> List[MetadataAuthority]: return [ MetadataAuthority( type=MetadataAuthorityType(authority_type), url=authority_url ) for (authority_type, authority_url) in set( self._cql_runner.raw_extrinsic_metadata_get_authorities(str(target)) ) ] def metadata_fetcher_add(self, fetchers: List[MetadataFetcher]) -> Dict[str, int]: self.journal_writer.metadata_fetcher_add(fetchers) for fetcher in fetchers: self._cql_runner.metadata_fetcher_add( MetadataFetcherRow( name=fetcher.name, version=fetcher.version, ) ) return {"metadata_fetcher:add": len(fetchers)} def metadata_fetcher_get( self, name: str, version: str ) -> Optional[MetadataFetcher]: fetcher = self._cql_runner.metadata_fetcher_get(name, version) if fetcher: return MetadataFetcher( name=fetcher.name, version=fetcher.version, ) else: return None def metadata_authority_add( self, authorities: List[MetadataAuthority] ) -> Dict[str, int]: self.journal_writer.metadata_authority_add(authorities) for authority in authorities: self._cql_runner.metadata_authority_add( MetadataAuthorityRow( url=authority.url, type=authority.type.value, ) ) return {"metadata_authority:add": len(authorities)} def metadata_authority_get( self, type: MetadataAuthorityType, url: str ) -> Optional[MetadataAuthority]: authority = self._cql_runner.metadata_authority_get(type.value, url) if authority: return MetadataAuthority( type=MetadataAuthorityType(authority.type), url=authority.url, ) else: return None # ExtID tables def extid_add(self, ids: List[ExtID]) -> Dict[str, int]: if not self._allow_overwrite: extids = [ extid for extid in ids if not self._cql_runner.extid_get_from_pk( extid_type=extid.extid_type, extid_version=extid.extid_version, extid=extid.extid, target=extid.target, ) ] else: extids = list(ids) self.journal_writer.extid_add(extids) inserted = 0 for extid in extids: target_type = extid.target.object_type.value target = extid.target.object_id extid_version = extid.extid_version extid_type = extid.extid_type extidrow = ExtIDRow( extid_type=extid_type, extid_version=extid_version, extid=extid.extid, target_type=target_type, target=target, ) (token, insertion_finalizer) = self._cql_runner.extid_add_prepare(extidrow) indexrow = ExtIDByTargetRow( target_type=target_type, target=target, target_token=token, ) self._cql_runner.extid_index_add_one(indexrow) insertion_finalizer() inserted += 1 return {"extid:add": inserted} def extid_get_from_extid( self, id_type: str, ids: List[bytes], version: Optional[int] = None ) -> List[ExtID]: result: List[ExtID] = [] for extid in ids: if version is not None: extidrows = self._cql_runner.extid_get_from_extid_and_version( id_type, extid, version ) else: extidrows = self._cql_runner.extid_get_from_extid(id_type, extid) result.extend( ExtID( extid_type=extidrow.extid_type, extid_version=extidrow.extid_version, extid=extidrow.extid, target=CoreSWHID( object_type=extidrow.target_type, object_id=extidrow.target, ), ) for extidrow in extidrows ) return result def extid_get_from_target( self, target_type: SwhidObjectType, ids: List[Sha1Git], extid_type: Optional[str] = None, extid_version: Optional[int] = None, ) -> List[ExtID]: if (extid_version is not None and extid_type is None) or ( extid_version is None and extid_type is not None ): raise ValueError("You must provide both extid_type and extid_version") result: List[ExtID] = [] for target in ids: extidrows = self._cql_runner.extid_get_from_target( target_type.value, target, extid_type=extid_type, extid_version=extid_version, ) result.extend( ExtID( extid_type=extidrow.extid_type, extid_version=extidrow.extid_version, extid=extidrow.extid, target=CoreSWHID( object_type=SwhidObjectType(extidrow.target_type), object_id=extidrow.target, ), ) for extidrow in extidrows ) return result # Misc def clear_buffers(self, object_types: Sequence[str] = ()) -> None: """Do nothing""" return None def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]: return {} diff --git a/swh/storage/postgresql/db.py b/swh/storage/postgresql/db.py index 9edf8b94..7fdac184 100644 --- a/swh/storage/postgresql/db.py +++ b/swh/storage/postgresql/db.py @@ -1,1543 +1,1545 @@ # Copyright (C) 2015-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import logging import random from typing import Any, Dict, Iterable, List, Optional, Tuple from swh.core.db import BaseDb from swh.core.db.db_utils import execute_values_generator from swh.core.db.db_utils import jsonize as _jsonize from swh.core.db.db_utils import stored_procedure from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.model.model import SHA1_SIZE, OriginVisit, OriginVisitStatus, Sha1Git from swh.model.swhids import ObjectType from swh.storage.interface import ListOrder logger = logging.getLogger(__name__) def jsonize(d): return _jsonize(dict(d) if d is not None else None) class Db(BaseDb): """Proxy to the SWH DB, with wrappers around stored procedures""" def mktemp_dir_entry(self, entry_type, cur=None): self._cursor(cur).execute( "SELECT swh_mktemp_dir_entry(%s)", (("directory_entry_%s" % entry_type),) ) @stored_procedure("swh_mktemp_revision") def mktemp_revision(self, cur=None): pass @stored_procedure("swh_mktemp_release") def mktemp_release(self, cur=None): pass @stored_procedure("swh_mktemp_snapshot_branch") def mktemp_snapshot_branch(self, cur=None): pass @stored_procedure("swh_content_add") def content_add_from_temp(self, cur=None): pass @stored_procedure("swh_directory_add") def directory_add_from_temp(self, cur=None): pass @stored_procedure("swh_skipped_content_add") def skipped_content_add_from_temp(self, cur=None): pass @stored_procedure("swh_revision_add") def revision_add_from_temp(self, cur=None): pass @stored_procedure("swh_extid_add") def extid_add_from_temp(self, cur=None): pass @stored_procedure("swh_release_add") def release_add_from_temp(self, cur=None): pass def content_update_from_temp(self, keys_to_update, cur=None): cur = self._cursor(cur) cur.execute( """select swh_content_update(ARRAY[%s] :: text[])""" % keys_to_update ) content_get_metadata_keys = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "status", ] content_add_keys = content_get_metadata_keys + ["ctime"] skipped_content_keys = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "reason", "status", "origin", ] def content_get_metadata_from_hashes( self, hashes: List[bytes], algo: str, cur=None ): cur = self._cursor(cur) assert algo in DEFAULT_ALGORITHMS query = f""" select {", ".join(self.content_get_metadata_keys)} from (values %s) as t (hash) inner join content on (content.{algo}=hash) """ yield from execute_values_generator( cur, query, ((hash_,) for hash_ in hashes), ) def content_get_range(self, start, end, limit=None, cur=None): """Retrieve contents within range [start, end].""" cur = self._cursor(cur) query = """select %s from content where %%s <= sha1 and sha1 <= %%s order by sha1 limit %%s""" % ", ".join( self.content_get_metadata_keys ) cur.execute(query, (start, end, limit)) yield from cur content_hash_keys = ["sha1", "sha1_git", "sha256", "blake2s256"] def content_missing_from_list(self, contents, cur=None): cur = self._cursor(cur) keys = ", ".join(self.content_hash_keys) equality = " AND ".join( ("t.%s = c.%s" % (key, key)) for key in self.content_hash_keys ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(%s) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE %s ) """ % (keys, keys, equality), (tuple(c[key] for key in self.content_hash_keys) for c in contents), ) def content_missing_per_sha1(self, sha1s, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT t.sha1 FROM (VALUES %s) AS t(sha1) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE c.sha1 = t.sha1 )""", ((sha1,) for sha1 in sha1s), ) def content_missing_per_sha1_git(self, contents, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT t.sha1_git FROM (VALUES %s) AS t(sha1_git) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE c.sha1_git = t.sha1_git )""", ((sha1,) for sha1 in contents), ) def skipped_content_missing(self, contents, cur=None): if not contents: return [] cur = self._cursor(cur) query = """SELECT * FROM (VALUES %s) AS t (%s) WHERE not exists (SELECT 1 FROM skipped_content s WHERE s.sha1 is not distinct from t.sha1::sha1 and s.sha1_git is not distinct from t.sha1_git::sha1 and s.sha256 is not distinct from t.sha256::bytea);""" % ( (", ".join("%s" for _ in contents)), ", ".join(self.content_hash_keys), ) cur.execute( query, [tuple(cont[key] for key in self.content_hash_keys) for cont in contents], ) yield from cur def snapshot_exists(self, snapshot_id, cur=None): """Check whether a snapshot with the given id exists""" cur = self._cursor(cur) cur.execute("""SELECT 1 FROM snapshot where id=%s""", (snapshot_id,)) return bool(cur.fetchone()) def snapshot_missing_from_list(self, snapshots, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM snapshot d WHERE d.id = t.id ) """, ((id,) for id in snapshots), ) def snapshot_add(self, snapshot_id, cur=None): """Add a snapshot from the temporary table""" cur = self._cursor(cur) cur.execute("""SELECT swh_snapshot_add(%s)""", (snapshot_id,)) snapshot_count_cols = ["target_type", "count"] def snapshot_count_branches( self, snapshot_id, branch_name_exclude_prefix=None, cur=None, ): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_count_branches(%%s, %%s) """ % ", ".join( self.snapshot_count_cols ) cur.execute(query, (snapshot_id, branch_name_exclude_prefix)) yield from cur snapshot_get_cols = ["snapshot_id", "name", "target", "target_type"] def snapshot_get_by_id( self, snapshot_id, branches_from=b"", branches_count=None, target_types=None, branch_name_include_substring=None, branch_name_exclude_prefix=None, cur=None, ): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_get_by_id(%%s, %%s, %%s, %%s :: snapshot_target[], %%s, %%s) """ % ", ".join( self.snapshot_get_cols ) cur.execute( query, ( snapshot_id, branches_from, branches_count, target_types, branch_name_include_substring, branch_name_exclude_prefix, ), ) yield from cur def snapshot_get_random(self, cur=None): return self._get_random_row_from_table("snapshot", ["id"], "id", cur) content_find_cols = [ "sha1", "sha1_git", "sha256", "blake2s256", "length", "ctime", "status", ] def content_find( self, sha1: Optional[bytes] = None, sha1_git: Optional[bytes] = None, sha256: Optional[bytes] = None, blake2s256: Optional[bytes] = None, cur=None, ): """Find the content optionally on a combination of the following checksums sha1, sha1_git, sha256 or blake2s256. Args: sha1: sha1 content git_sha1: the sha1 computed `a la git` sha1 of the content sha256: sha256 content blake2s256: blake2s256 content Returns: The tuple (sha1, sha1_git, sha256, blake2s256) if found or None. """ cur = self._cursor(cur) checksum_dict = { "sha1": sha1, "sha1_git": sha1_git, "sha256": sha256, "blake2s256": blake2s256, } query_parts = [f"SELECT {','.join(self.content_find_cols)} FROM content WHERE "] query_params = [] where_parts = [] # Adds only those keys which have values exist for algorithm in checksum_dict: if checksum_dict[algorithm] is not None: where_parts.append(f"{algorithm} = %s") query_params.append(checksum_dict[algorithm]) query_parts.append(" AND ".join(where_parts)) query = "\n".join(query_parts) cur.execute(query, query_params) content = cur.fetchall() return content def content_get_random(self, cur=None): return self._get_random_row_from_table("content", ["sha1_git"], "sha1_git", cur) def directory_missing_from_list(self, directories, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM directory d WHERE d.id = t.id ) """, ((id,) for id in directories), ) directory_ls_cols = [ "dir_id", "type", "target", "name", "perms", "status", "sha1", "sha1_git", "sha256", "length", ] def directory_walk_one(self, directory, cur=None): cur = self._cursor(cur) cols = ", ".join(self.directory_ls_cols) query = "SELECT %s FROM swh_directory_walk_one(%%s)" % cols cur.execute(query, (directory,)) yield from cur def directory_walk(self, directory, cur=None): cur = self._cursor(cur) cols = ", ".join(self.directory_ls_cols) query = "SELECT %s FROM swh_directory_walk(%%s)" % cols cur.execute(query, (directory,)) yield from cur def directory_entry_get_by_path(self, directory, paths, cur=None): """Retrieve a directory entry by path.""" cur = self._cursor(cur) cols = ", ".join(self.directory_ls_cols) query = "SELECT %s FROM swh_find_directory_entry_by_path(%%s, %%s)" % cols cur.execute(query, (directory, paths)) data = cur.fetchone() if set(data) == {None}: return None return data directory_get_entries_cols = ["type", "target", "name", "perms"] def directory_get_entries(self, directory: Sha1Git, cur=None) -> List[Tuple]: cur = self._cursor(cur) cur.execute( "SELECT * FROM swh_directory_get_entries(%s::sha1_git)", (directory,) ) return list(cur) def directory_get_raw_manifest( self, directory_ids: List[Sha1Git], cur=None ) -> Iterable[Tuple[Sha1Git, bytes]]: cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT t.id, raw_manifest FROM (VALUES %s) as t(id) INNER JOIN directory ON (t.id=directory.id) """, ((id_,) for id_ in directory_ids), ) def directory_get_random(self, cur=None): return self._get_random_row_from_table("directory", ["id"], "id", cur) def revision_missing_from_list(self, revisions, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM revision r WHERE r.id = t.id ) """, ((id,) for id in revisions), ) revision_add_cols = [ "id", "date", "date_offset", "date_neg_utc_offset", "date_offset_bytes", "committer_date", "committer_date_offset", "committer_date_neg_utc_offset", "committer_date_offset_bytes", "type", "directory", "message", "author_fullname", "author_name", "author_email", "committer_fullname", "committer_name", "committer_email", "metadata", "synthetic", "extra_headers", "raw_manifest", ] revision_get_cols = revision_add_cols + ["parents"] def origin_visit_add(self, origin, ts, type, cur=None): """Add a new origin_visit for origin origin at timestamp ts. Args: origin: origin concerned by the visit ts: the date of the visit type: type of loader for the visit Returns: The new visit index step for that origin """ cur = self._cursor(cur) self._cursor(cur).execute( "SELECT swh_origin_visit_add(%s, %s, %s)", (origin, ts, type) ) return cur.fetchone()[0] origin_visit_status_cols = [ "origin", "visit", "date", "type", "status", "snapshot", "metadata", ] def origin_visit_status_add( self, visit_status: OriginVisitStatus, cur=None ) -> None: """Add new origin visit status""" assert self.origin_visit_status_cols[0] == "origin" assert self.origin_visit_status_cols[-1] == "metadata" cols = self.origin_visit_status_cols[1:-1] cur = self._cursor(cur) cur.execute( f"WITH origin_id as (select id from origin where url=%s) " f"INSERT INTO origin_visit_status " f"(origin, {', '.join(cols)}, metadata) " f"VALUES ((select id from origin_id), " f"{', '.join(['%s']*len(cols))}, %s) " f"ON CONFLICT (origin, visit, date) do nothing", [visit_status.origin] + [getattr(visit_status, key) for key in cols] + [jsonize(visit_status.metadata)], ) origin_visit_cols = ["origin", "visit", "date", "type"] def origin_visit_add_with_id(self, origin_visit: OriginVisit, cur=None) -> None: """Insert origin visit when id are already set""" ov = origin_visit assert ov.visit is not None cur = self._cursor(cur) query = """INSERT INTO origin_visit ({cols}) VALUES ((select id from origin where url=%s), {values}) ON CONFLICT (origin, visit) DO NOTHING""".format( cols=", ".join(self.origin_visit_cols), values=", ".join("%s" for col in self.origin_visit_cols[1:]), ) cur.execute(query, (ov.origin, ov.visit, ov.date, ov.type)) origin_visit_get_cols = [ "origin", "visit", "date", "type", "status", "metadata", "snapshot", ] origin_visit_select_cols = [ "o.url AS origin", "ov.visit", "ov.date", "ov.type AS type", "ovs.status", "ovs.snapshot", "ovs.metadata", ] origin_visit_status_select_cols = [ "o.url AS origin", "ovs.visit", "ovs.date", "ovs.type AS type", "ovs.status", "ovs.snapshot", "ovs.metadata", ] def _make_origin_visit_status( self, row: Optional[Tuple[Any]] ) -> Optional[Dict[str, Any]]: """Make an origin_visit_status dict out of a row""" if not row: return None return dict(zip(self.origin_visit_status_cols, row)) def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, cur=None, ) -> Optional[Dict[str, Any]]: """Given an origin visit id, return its latest origin_visit_status""" cur = self._cursor(cur) query_parts = [ "SELECT %s" % ", ".join(self.origin_visit_status_select_cols), "FROM origin_visit_status ovs ", "INNER JOIN origin o ON o.id = ovs.origin", ] query_parts.append("WHERE o.url = %s") query_params: List[Any] = [origin_url] query_parts.append("AND ovs.visit = %s") query_params.append(visit) if require_snapshot: query_parts.append("AND ovs.snapshot is not null") if allowed_statuses: query_parts.append("AND ovs.status IN %s") query_params.append(tuple(allowed_statuses)) query_parts.append("ORDER BY ovs.date DESC LIMIT 1") query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) row = cur.fetchone() return self._make_origin_visit_status(row) def origin_visit_status_get_range( self, origin: str, visit: int, date_from: Optional[datetime.datetime], order: ListOrder, limit: int, cur=None, ): """Retrieve visit_status rows for visit (origin, visit) in a paginated way.""" cur = self._cursor(cur) query_parts = [ f"SELECT {', '.join(self.origin_visit_status_select_cols)} " "FROM origin_visit_status ovs ", "INNER JOIN origin o ON o.id = ovs.origin ", ] query_parts.append("WHERE o.url = %s AND ovs.visit = %s ") query_params: List[Any] = [origin, visit] if date_from is not None: op_comparison = ">=" if order == ListOrder.ASC else "<=" query_parts.append(f"and ovs.date {op_comparison} %s ") query_params.append(date_from) if order == ListOrder.ASC: query_parts.append("ORDER BY ovs.date ASC ") elif order == ListOrder.DESC: query_parts.append("ORDER BY ovs.date DESC ") else: assert False query_parts.append("LIMIT %s") query_params.append(limit) query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) yield from cur def origin_visit_get_range( self, origin: str, visit_from: int, order: ListOrder, limit: int, cur=None, ): cur = self._cursor(cur) origin_visit_cols = ["o.url as origin", "ov.visit", "ov.date", "ov.type"] query_parts = [ f"SELECT {', '.join(origin_visit_cols)} FROM origin_visit ov ", "INNER JOIN origin o ON o.id = ov.origin ", ] query_parts.append("WHERE ov.origin = (select id from origin where url = %s)") query_params: List[Any] = [origin] if visit_from > 0: op_comparison = ">" if order == ListOrder.ASC else "<" query_parts.append(f"and ov.visit {op_comparison} %s") query_params.append(visit_from) if order == ListOrder.ASC: query_parts.append("ORDER BY ov.visit ASC") elif order == ListOrder.DESC: query_parts.append("ORDER BY ov.visit DESC") query_parts.append("LIMIT %s") query_params.append(limit) query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) yield from cur def origin_visit_status_get_all_in_range( self, origin: str, allowed_statuses: Optional[List[str]], require_snapshot: bool, visit_from: int, visit_to: int, cur=None, ): cur = self._cursor(cur) query_parts = [ f"SELECT {', '.join(self.origin_visit_status_select_cols)}", " FROM origin_visit_status ovs", " INNER JOIN origin o ON o.id = ovs.origin", ] query_parts.append("WHERE ovs.origin = (select id from origin where url = %s)") query_params: List[Any] = [origin] assert visit_from <= visit_to query_parts.append("AND ovs.visit >= %s") query_params.append(visit_from) query_parts.append("AND ovs.visit <= %s") query_params.append(visit_to) if require_snapshot: query_parts.append("AND ovs.snapshot is not null") if allowed_statuses: query_parts.append("AND ovs.status IN %s") query_params.append(tuple(allowed_statuses)) query_parts.append("ORDER BY ovs.visit ASC, ovs.date ASC") query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) yield from cur def origin_visit_get(self, origin_id, visit_id, cur=None): """Retrieve information on visit visit_id of origin origin_id. Args: origin_id: the origin concerned visit_id: The visit step for that origin Returns: The origin_visit information """ cur = self._cursor(cur) query = """\ SELECT %s FROM origin_visit ov INNER JOIN origin o ON o.id = ov.origin INNER JOIN origin_visit_status ovs USING (origin, visit) WHERE ov.origin = (select id from origin where url = %%s) AND ov.visit = %%s ORDER BY ovs.date DESC LIMIT 1 """ % ( ", ".join(self.origin_visit_select_cols) ) cur.execute(query, (origin_id, visit_id)) r = cur.fetchall() if not r: return None return r[0] def origin_visit_find_by_date(self, origin, visit_date, cur=None): cur = self._cursor(cur) cur.execute( "SELECT * FROM swh_visit_find_by_date(%s, %s)", (origin, visit_date) ) rows = cur.fetchall() if rows: visit = dict(zip(self.origin_visit_get_cols, rows[0])) visit["origin"] = origin return visit def origin_visit_exists(self, origin_id, visit_id, cur=None): """Check whether an origin visit with the given ids exists""" cur = self._cursor(cur) query = "SELECT 1 FROM origin_visit where origin = %s AND visit = %s" cur.execute(query, (origin_id, visit_id)) return bool(cur.fetchone()) def origin_visit_get_latest( self, origin_id: str, type: Optional[str], allowed_statuses: Optional[Iterable[str]], require_snapshot: bool, cur=None, ): """Retrieve the most recent origin_visit of the given origin, with optional filters. Args: origin_id: the origin concerned type: Optional visit type to filter on allowed_statuses: the visit statuses allowed for the returned visit require_snapshot (bool): If True, only a visit with a known snapshot will be returned. Returns: The origin_visit information, or None if no visit matches. """ cur = self._cursor(cur) + # using 'LEFT JOIN origin_visit' instead of an INNER JOIN as a query + # optimization; end results are equivalent. query_parts = [ "SELECT %s" % ", ".join(self.origin_visit_select_cols), - "FROM origin_visit ov ", - "INNER JOIN origin o ON o.id = ov.origin", - "INNER JOIN origin_visit_status ovs USING (origin, visit)", + "FROM origin_visit_status ovs ", + "INNER JOIN origin o ON o.id = ovs.origin", + "LEFT JOIN origin_visit ov USING (origin, visit)", ] query_parts.append( - "WHERE ov.origin = (SELECT id FROM origin o WHERE o.url = %s)" + "WHERE ovs.origin = (SELECT id FROM origin o WHERE o.url = %s)" ) query_params: List[Any] = [origin_id] if type is not None: - query_parts.append("AND ov.type = %s") + query_parts.append("AND ovs.type = %s") query_params.append(type) if require_snapshot: query_parts.append("AND ovs.snapshot is not null") if allowed_statuses: query_parts.append("AND ovs.status IN %s") query_params.append(tuple(allowed_statuses)) - query_parts.append("ORDER BY ov.visit DESC, ovs.date DESC LIMIT 1") + query_parts.append("ORDER BY ovs.visit DESC, ovs.date DESC LIMIT 1") query = "\n".join(query_parts) cur.execute(query, tuple(query_params)) r = cur.fetchone() if not r: return None return r def origin_visit_get_random(self, type, cur=None): """Randomly select one origin visit that was full and in the last 3 months """ cur = self._cursor(cur) columns = ",".join(self.origin_visit_select_cols) query = f"""select {columns} from origin_visit ov inner join origin o on ov.origin=o.id inner join origin_visit_status ovs using (origin, visit) where ovs.status='full' and ov.type=%s and ov.date > now() - '3 months'::interval and random() < 0.1 limit 1 """ cur.execute(query, (type,)) return cur.fetchone() @staticmethod def mangle_query_key(key, main_table, ignore_displayname=False): if key == "id": return "t.id" if key == "parents": return """ ARRAY( SELECT rh.parent_id::bytea FROM revision_history rh WHERE rh.id = t.id ORDER BY rh.parent_rank )""" if "_" not in key: return f"{main_table}.{key}" head, tail = key.split("_", 1) if head not in ("author", "committer") or tail not in ( "name", "email", "id", "fullname", ): return f"{main_table}.{key}" if ignore_displayname: return f"{head}.{tail}" else: if tail == "id": return f"{head}.{tail}" elif tail in ("name", "email"): # These fields get populated again from fullname by # converters.db_to_author if they're None, so we can just NULLify them # when displayname is set. return ( f"CASE" f" WHEN {head}.displayname IS NULL THEN {head}.{tail} " f" ELSE NULL " f"END AS {key}" ) elif tail == "fullname": return f"COALESCE({head}.displayname, {head}.fullname) AS {key}" assert False, "All cases should have been handled here" def revision_get_from_list(self, revisions, ignore_displayname=False, cur=None): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "revision", ignore_displayname) for k in self.revision_get_cols ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(sortkey, id) LEFT JOIN revision ON t.id = revision.id LEFT JOIN person author ON revision.author = author.id LEFT JOIN person committer ON revision.committer = committer.id ORDER BY sortkey """ % query_keys, ((sortkey, id) for sortkey, id in enumerate(revisions)), ) extid_cols = ["extid", "extid_version", "extid_type", "target", "target_type"] def extid_get_from_extid_list( self, extid_type: str, ids: List[bytes], version: Optional[int] = None, cur=None ): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "extid") for k in self.extid_cols ) filter_query = "" if version is not None: filter_query = cur.mogrify( f"WHERE extid_version={version}", (version,) ).decode() sql = f""" SELECT {query_keys} FROM (VALUES %s) as t(sortkey, extid, extid_type) LEFT JOIN extid USING (extid, extid_type) {filter_query} ORDER BY sortkey """ yield from execute_values_generator( cur, sql, (((sortkey, extid, extid_type) for sortkey, extid in enumerate(ids))), ) def extid_get_from_swhid_list( self, target_type: str, ids: List[bytes], extid_version: Optional[int] = None, extid_type: Optional[str] = None, cur=None, ): cur = self._cursor(cur) target_type = ObjectType( target_type ).name.lower() # aka "rev" -> "revision", ... query_keys = ", ".join( self.mangle_query_key(k, "extid") for k in self.extid_cols ) filter_query = "" if extid_version is not None and extid_type is not None: filter_query = cur.mogrify( "WHERE extid_version=%s AND extid_type=%s", ( extid_version, extid_type, ), ).decode() sql = f""" SELECT {query_keys} FROM (VALUES %s) as t(sortkey, target, target_type) LEFT JOIN extid USING (target, target_type) {filter_query} ORDER BY sortkey """ yield from execute_values_generator( cur, sql, (((sortkey, target, target_type) for sortkey, target in enumerate(ids))), template=b"(%s,%s,%s::object_type)", ) def revision_log( self, root_revisions, ignore_displayname=False, limit=None, cur=None ): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_revision_log( "root_revisions" := %%s, num_revs := %%s, "ignore_displayname" := %%s )""" % ", ".join( self.revision_get_cols ) cur.execute(query, (root_revisions, limit, ignore_displayname)) yield from cur revision_shortlog_cols = ["id", "parents"] def revision_shortlog(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_list(%%s, %%s) """ % ", ".join( self.revision_shortlog_cols ) cur.execute(query, (root_revisions, limit)) yield from cur def revision_get_random(self, cur=None): return self._get_random_row_from_table("revision", ["id"], "id", cur) def release_missing_from_list(self, releases, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM release r WHERE r.id = t.id ) """, ((id,) for id in releases), ) object_find_by_sha1_git_cols = ["sha1_git", "type"] def object_find_by_sha1_git(self, ids, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ WITH t (sha1_git) AS (VALUES %s), known_objects as (( select id as sha1_git, 'release'::object_type as type, object_id from release r where exists (select 1 from t where t.sha1_git = r.id) ) union all ( select id as sha1_git, 'revision'::object_type as type, object_id from revision r where exists (select 1 from t where t.sha1_git = r.id) ) union all ( select id as sha1_git, 'directory'::object_type as type, object_id from directory d where exists (select 1 from t where t.sha1_git = d.id) ) union all ( select sha1_git as sha1_git, 'content'::object_type as type, object_id from content c where exists (select 1 from t where t.sha1_git = c.sha1_git) )) select t.sha1_git as sha1_git, k.type from t left join known_objects k on t.sha1_git = k.sha1_git """, ((id,) for id in ids), ) def stat_counters(self, cur=None): cur = self._cursor(cur) cur.execute("SELECT * FROM swh_stat_counters()") yield from cur def origin_add(self, url, cur=None): """Insert a new origin and return the new identifier.""" insert = """INSERT INTO origin (url) values (%s) ON CONFLICT DO NOTHING """ cur.execute(insert, (url,)) return cur.rowcount origin_cols = ["url"] def origin_get_by_url(self, origins, cur=None): """Retrieve origin `(type, url)` from urls if found.""" cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(url) LEFT JOIN origin ON t.url = origin.url """ % ",".join( "origin." + col for col in self.origin_cols ) yield from execute_values_generator(cur, query, ((url,) for url in origins)) def origin_get_by_sha1(self, sha1s, cur=None): """Retrieve origin urls from sha1s if found.""" cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(sha1) LEFT JOIN origin ON t.sha1 = digest(origin.url, 'sha1') """ % ",".join( "origin." + col for col in self.origin_cols ) yield from execute_values_generator(cur, query, ((sha1,) for sha1 in sha1s)) def origin_id_get_by_url(self, origins, cur=None): """Retrieve origin `(type, url)` from urls if found.""" cur = self._cursor(cur) query = """SELECT id FROM (VALUES %s) as t(url) LEFT JOIN origin ON t.url = origin.url """ for row in execute_values_generator(cur, query, ((url,) for url in origins)): yield row[0] origin_get_range_cols = ["id", "url"] def origin_get_range(self, origin_from: int = 1, origin_count: int = 100, cur=None): """Retrieve ``origin_count`` origins whose ids are greater or equal than ``origin_from``. Origins are sorted by id before retrieving them. Args: origin_from: the minimum id of origins to retrieve origin_count: the maximum number of origins to retrieve """ cur = self._cursor(cur) query = """SELECT %s FROM origin WHERE id >= %%s ORDER BY id LIMIT %%s """ % ",".join( self.origin_get_range_cols ) cur.execute(query, (origin_from, origin_count)) yield from cur def _origin_query( self, url_pattern, count=False, offset=0, limit=50, regexp=False, with_visit=False, visit_types=None, cur=None, ): """ Method factorizing query creation for searching and counting origins. """ cur = self._cursor(cur) if count: origin_cols = "COUNT(*)" order_clause = "" else: origin_cols = ",".join(self.origin_cols) order_clause = "ORDER BY id" if not regexp: operator = "ILIKE" query_params = [f"%{url_pattern}%"] else: operator = "~*" query_params = [url_pattern] query = f""" WITH filtered_origins AS ( SELECT * FROM origin WHERE url {operator} %s {order_clause} ) SELECT {origin_cols} FROM filtered_origins AS o """ if with_visit or visit_types: visit_predicat = ( """ INNER JOIN origin_visit_status ovs USING (origin, visit) INNER JOIN snapshot ON ovs.snapshot=snapshot.id """ if with_visit else "" ) type_predicat = ( f"AND ov.type=any(ARRAY{visit_types})" if visit_types else "" ) query += f""" WHERE EXISTS ( SELECT 1 FROM origin_visit ov {visit_predicat} WHERE ov.origin=o.id {type_predicat} ) """ if not count: query += "OFFSET %s LIMIT %s" query_params.extend([offset, limit]) cur.execute(query, query_params) def origin_search( self, url_pattern: str, offset: int = 0, limit: int = 50, regexp: bool = False, with_visit: bool = False, visit_types: Optional[List[str]] = None, cur=None, ): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. Args: url_pattern: the string pattern to search for in origin urls offset: number of found origins to skip before returning results limit: the maximum number of found origins to return regexp: if True, consider the provided pattern as a regular expression and returns origins whose urls match it with_visit: if True, filter out origins with no visit """ self._origin_query( url_pattern, offset=offset, limit=limit, regexp=regexp, with_visit=with_visit, visit_types=visit_types, cur=cur, ) yield from cur def origin_count(self, url_pattern, regexp=False, with_visit=False, cur=None): """Count origins whose urls contain a provided string pattern or match a provided regular expression. The pattern search in origin urls is performed in a case insensitive way. Args: url_pattern (str): the string pattern to search for in origin urls regexp (bool): if True, consider the provided pattern as a regular expression and returns origins whose urls match it with_visit (bool): if True, filter out origins with no visit """ self._origin_query( url_pattern, count=True, regexp=regexp, with_visit=with_visit, cur=cur ) return cur.fetchone()[0] release_add_cols = [ "id", "target", "target_type", "date", "date_offset", "date_neg_utc_offset", "date_offset_bytes", "name", "comment", "synthetic", "raw_manifest", "author_fullname", "author_name", "author_email", ] release_get_cols = release_add_cols def origin_snapshot_get_all(self, origin_url: str, cur=None) -> Iterable[Sha1Git]: cur = self._cursor(cur) query = f"""\ SELECT DISTINCT snapshot FROM origin_visit_status ovs INNER JOIN origin o ON o.id = ovs.origin WHERE o.url = '{origin_url}' and snapshot IS NOT NULL; """ cur.execute(query) yield from map(lambda row: row[0], cur) def release_get_from_list(self, releases, ignore_displayname=False, cur=None): cur = self._cursor(cur) query_keys = ", ".join( self.mangle_query_key(k, "release", ignore_displayname) for k in self.release_get_cols ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(sortkey, id) LEFT JOIN release ON t.id = release.id LEFT JOIN person author ON release.author = author.id ORDER BY sortkey """ % query_keys, ((sortkey, id) for sortkey, id in enumerate(releases)), ) def release_get_random(self, cur=None): return self._get_random_row_from_table("release", ["id"], "id", cur) _raw_extrinsic_metadata_context_cols = [ "origin", "visit", "snapshot", "release", "revision", "path", "directory", ] """The list of context columns for all artifact types.""" _raw_extrinsic_metadata_insert_cols = [ "id", "type", "target", "authority_id", "fetcher_id", "discovery_date", "format", "metadata", *_raw_extrinsic_metadata_context_cols, ] """List of columns of the raw_extrinsic_metadata table, used when writing metadata.""" _raw_extrinsic_metadata_insert_query = f""" INSERT INTO raw_extrinsic_metadata ({', '.join(_raw_extrinsic_metadata_insert_cols)}) VALUES ({', '.join('%s' for _ in _raw_extrinsic_metadata_insert_cols)}) ON CONFLICT (id) DO NOTHING """ raw_extrinsic_metadata_get_cols = [ "raw_extrinsic_metadata.target", "raw_extrinsic_metadata.type", "discovery_date", "metadata_authority.type", "metadata_authority.url", "metadata_fetcher.id", "metadata_fetcher.name", "metadata_fetcher.version", *_raw_extrinsic_metadata_context_cols, "format", "raw_extrinsic_metadata.metadata", ] """List of columns of the raw_extrinsic_metadata, metadata_authority, and metadata_fetcher tables, used when reading object metadata.""" _raw_extrinsic_metadata_select_query = f""" SELECT {', '.join(raw_extrinsic_metadata_get_cols)} FROM raw_extrinsic_metadata INNER JOIN metadata_authority ON (metadata_authority.id=authority_id) INNER JOIN metadata_fetcher ON (metadata_fetcher.id=fetcher_id) """ def raw_extrinsic_metadata_add( self, id: bytes, type: str, target: str, discovery_date: datetime.datetime, authority_id: int, fetcher_id: int, format: str, metadata: bytes, origin: Optional[str], visit: Optional[int], snapshot: Optional[str], release: Optional[str], revision: Optional[str], path: Optional[bytes], directory: Optional[str], cur, ): query = self._raw_extrinsic_metadata_insert_query args: Dict[str, Any] = dict( id=id, type=type, target=target, authority_id=authority_id, fetcher_id=fetcher_id, discovery_date=discovery_date, format=format, metadata=metadata, origin=origin, visit=visit, snapshot=snapshot, release=release, revision=revision, path=path, directory=directory, ) params = [args[col] for col in self._raw_extrinsic_metadata_insert_cols] cur.execute(query, params) def raw_extrinsic_metadata_get( self, target: str, authority_id: int, after_time: Optional[datetime.datetime], after_fetcher: Optional[int], limit: int, cur, ): query_parts = [self._raw_extrinsic_metadata_select_query] query_parts.append("WHERE raw_extrinsic_metadata.target=%s AND authority_id=%s") args = [target, authority_id] if after_fetcher is not None: assert after_time query_parts.append("AND (discovery_date, fetcher_id) > (%s, %s)") args.extend([after_time, after_fetcher]) elif after_time is not None: query_parts.append("AND discovery_date > %s") args.append(after_time) query_parts.append("ORDER BY discovery_date, fetcher_id") if limit: query_parts.append("LIMIT %s") args.append(limit) cur.execute(" ".join(query_parts), args) yield from cur def raw_extrinsic_metadata_get_by_ids(self, ids: List[Sha1Git], cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, self._raw_extrinsic_metadata_select_query + "INNER JOIN (VALUES %s) AS t(id) ON t.id = raw_extrinsic_metadata.id", [(id_,) for id_ in ids], ) def raw_extrinsic_metadata_get_authorities(self, id: str, cur=None): cur = self._cursor(cur) cur.execute( """ SELECT DISTINCT metadata_authority.type, metadata_authority.url FROM raw_extrinsic_metadata INNER JOIN metadata_authority ON (metadata_authority.id=authority_id) WHERE raw_extrinsic_metadata.target = %s """, (id,), ) yield from cur metadata_fetcher_cols = ["name", "version"] def metadata_fetcher_add(self, name: str, version: str, cur=None) -> None: cur = self._cursor(cur) cur.execute( "INSERT INTO metadata_fetcher (name, version) " "VALUES (%s, %s) ON CONFLICT DO NOTHING", (name, version), ) def metadata_fetcher_get(self, name: str, version: str, cur=None): cur = self._cursor(cur) cur.execute( f"SELECT {', '.join(self.metadata_fetcher_cols)} " f"FROM metadata_fetcher " f"WHERE name=%s AND version=%s", (name, version), ) return cur.fetchone() def metadata_fetcher_get_id( self, name: str, version: str, cur=None ) -> Optional[int]: cur = self._cursor(cur) cur.execute( "SELECT id FROM metadata_fetcher WHERE name=%s AND version=%s", (name, version), ) row = cur.fetchone() if row: return row[0] else: return None metadata_authority_cols = ["type", "url"] def metadata_authority_add(self, type: str, url: str, cur=None) -> None: cur = self._cursor(cur) cur.execute( "INSERT INTO metadata_authority (type, url) " "VALUES (%s, %s) ON CONFLICT DO NOTHING", (type, url), ) def metadata_authority_get(self, type: str, url: str, cur=None): cur = self._cursor(cur) cur.execute( f"SELECT {', '.join(self.metadata_authority_cols)} " f"FROM metadata_authority " f"WHERE type=%s AND url=%s", (type, url), ) return cur.fetchone() def metadata_authority_get_id(self, type: str, url: str, cur=None) -> Optional[int]: cur = self._cursor(cur) cur.execute( "SELECT id FROM metadata_authority WHERE type=%s AND url=%s", (type, url) ) row = cur.fetchone() if row: return row[0] else: return None def _get_random_row_from_table(self, table_name, cols, id_col, cur=None): random_sha1 = bytes(random.randint(0, 255) for _ in range(SHA1_SIZE)) cur = self._cursor(cur) query = """ (SELECT {cols} FROM {table} WHERE {id_col} >= %s ORDER BY {id_col} LIMIT 1) UNION (SELECT {cols} FROM {table} WHERE {id_col} < %s ORDER BY {id_col} DESC LIMIT 1) LIMIT 1 """.format( cols=", ".join(cols), table=table_name, id_col=id_col ) cur.execute(query, (random_sha1, random_sha1)) row = cur.fetchone() if row: return row[0] diff --git a/swh/storage/postgresql/storage.py b/swh/storage/postgresql/storage.py index c40aea3a..e83a33bc 100644 --- a/swh/storage/postgresql/storage.py +++ b/swh/storage/postgresql/storage.py @@ -1,1702 +1,1711 @@ # Copyright (C) 2015-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import base64 from collections import defaultdict import contextlib from contextlib import contextmanager import datetime import itertools import logging import operator from typing import Any, Counter, Dict, Iterable, List, Optional, Sequence, Tuple import attr import psycopg2 import psycopg2.errors import psycopg2.pool from swh.core.api.serializers import msgpack_dumps, msgpack_loads from swh.core.db.common import db_transaction, db_transaction_generator from swh.core.db.db_utils import swh_db_flavor, swh_db_version from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes, hash_to_hex from swh.model.model import ( SHA1_SIZE, Content, Directory, DirectoryEntry, ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1, Sha1Git, SkippedContent, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.exc import HashCollision, StorageArgumentException, StorageDBError from swh.storage.interface import ( VISIT_STATUSES, ListOrder, OriginVisitWithStatuses, PagedResult, PartialBranches, ) from swh.storage.objstorage import ObjStorage from swh.storage.utils import ( extract_collision_hash, get_partition_bounds_bytes, map_optional, now, ) from swh.storage.writer import JournalWriter from . import converters from .db import Db logger = logging.getLogger(__name__) # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 EMPTY_SNAPSHOT_ID = hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e") """Identifier for the empty snapshot""" VALIDATION_EXCEPTIONS = ( KeyError, TypeError, ValueError, psycopg2.errors.CheckViolation, psycopg2.errors.IntegrityError, psycopg2.errors.InvalidTextRepresentation, psycopg2.errors.NotNullViolation, psycopg2.errors.NumericValueOutOfRange, psycopg2.errors.UndefinedFunction, # (raised on wrong argument typs) + psycopg2.errors.ProgramLimitExceeded, # typically person_name_idx ) """Exceptions raised by postgresql when validation of the arguments failed.""" @contextlib.contextmanager def convert_validation_exceptions(): """Catches postgresql errors related to invalid arguments, and re-raises a StorageArgumentException.""" try: yield except psycopg2.errors.UniqueViolation: # This only happens because of concurrent insertions, but it is # a subclass of IntegrityError; so we need to catch and reraise it # before the next clause converts it to StorageArgumentException. raise except VALIDATION_EXCEPTIONS as e: raise StorageArgumentException(str(e)) class Storage: """SWH storage datastore proxy, encompassing DB and object storage""" - current_version: int = 183 + current_version: int = 186 def __init__( self, db, objstorage, min_pool_conns=1, max_pool_conns=10, journal_writer=None, query_options=None, ): """Instantiate a storage instance backed by a PostgreSQL database and an objstorage. When ``db`` is passed as a connection string, then this module automatically manages a connection pool between ``min_pool_conns`` and ``max_pool_conns``. When ``db`` is an explicit psycopg2 connection, then ``min_pool_conns`` and ``max_pool_conns`` are ignored and the connection is used directly. Args: db: either a libpq connection string, or a psycopg2 connection objstorage: configuration for the backend :class:`ObjStorage` min_pool_conns: min number of connections in the psycopg2 pool max_pool_conns: max number of connections in the psycopg2 pool journal_writer: configuration for the :class:`JournalWriter` query_options: configuration for the sql connections; keys of the dict are the method names decorated with :func:`db_transaction` or :func:`db_transaction_generator` (eg. :func:`content_find`), and values are dicts (config_name, config_value) used to configure the sql connection for the method_name. For example, using:: {"content_get": {"statement_timeout": 5000}} will override the default statement timeout for the :func:`content_get` endpoint from 500ms to 5000ms. See :mod:`swh.core.db.common` for more details. """ try: if isinstance(db, psycopg2.extensions.connection): self._pool = None self._db = Db(db) # See comment below self._db.cursor().execute("SET TIME ZONE 'UTC'") else: self._pool = psycopg2.pool.ThreadedConnectionPool( min_pool_conns, max_pool_conns, db ) self._db = None except psycopg2.OperationalError as e: raise StorageDBError(e) self.journal_writer = JournalWriter(journal_writer) self.objstorage = ObjStorage(objstorage) self.query_options = query_options self._flavor: Optional[str] = None def get_db(self): if self._db: return self._db else: db = Db.from_pool(self._pool) # Workaround for psycopg2 < 2.9.0 not handling fractional timezones, # which may happen on old revision/release dates on systems configured # with non-UTC timezones. # https://www.psycopg.org/docs/usage.html#time-zones-handling db.cursor().execute("SET TIME ZONE 'UTC'") return db def put_db(self, db): if db is not self._db: db.put_conn() @contextmanager def db(self): db = None try: db = self.get_db() yield db finally: if db: self.put_db(db) @db_transaction() def get_flavor(self, *, db: Db, cur=None) -> str: flavor = swh_db_flavor(db.conn.dsn) assert flavor is not None return flavor @property def flavor(self) -> str: if self._flavor is None: self._flavor = self.get_flavor() assert self._flavor is not None return self._flavor @db_transaction() def check_config(self, *, check_write: bool, db: Db, cur=None) -> bool: if not self.objstorage.check_config(check_write=check_write): return False dbversion = swh_db_version(db.conn.dsn) if dbversion != self.current_version: logger.warning( "database dbversion (%s) != %s current_version (%s)", dbversion, __name__, self.current_version, ) return False # Check permissions on one of the tables check = "INSERT" if check_write else "SELECT" cur.execute("select has_table_privilege(current_user, 'content', %s)", (check,)) return cur.fetchone()[0] def _content_unique_key(self, hash, db): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ keys = db.content_hash_keys if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) def _content_add_metadata(self, db, cur, content): """Add content to the postgresql database but not the object storage.""" # create temporary table for metadata injection db.mktemp("content", cur) db.copy_to( (c.to_dict() for c in content), "tmp_content", db.content_add_keys, cur ) # move metadata in place try: db.content_add_from_temp(cur) except psycopg2.IntegrityError as e: if e.diag.sqlstate == "23505" and e.diag.table_name == "content": message_detail = e.diag.message_detail if message_detail: hash_name, hash_id = extract_collision_hash(message_detail) collision_contents_hashes = [ c.hashes() for c in content if c.get_hash(hash_name) == hash_id ] else: constraint_to_hash_name = { "content_pkey": "sha1", "content_sha1_git_idx": "sha1_git", "content_sha256_idx": "sha256", } hash_name = constraint_to_hash_name.get(e.diag.constraint_name) hash_id = None collision_contents_hashes = None raise HashCollision( hash_name, hash_id, collision_contents_hashes ) from None else: raise def content_add(self, content: List[Content]) -> Dict[str, int]: ctime = now() contents = [attr.evolve(c, ctime=ctime) for c in content] # Must add to the objstorage before the DB and journal. Otherwise: # 1. in case of a crash the DB may "believe" we have the content, but # we didn't have time to write to the objstorage before the crash # 2. the objstorage mirroring, which reads from the journal, may attempt to # read from the objstorage before we finished writing it objstorage_summary = self.objstorage.content_add(contents) with self.db() as db: with db.transaction() as cur: missing = list( self.content_missing( map(Content.to_dict, contents), key_hash="sha1_git", db=db, cur=cur, ) ) contents = [c for c in contents if c.sha1_git in missing] self.journal_writer.content_add(contents) self._content_add_metadata(db, cur, contents) return { "content:add": len(contents), "content:add:bytes": objstorage_summary["content:add:bytes"], } @db_transaction() def content_update( self, contents: List[Dict[str, Any]], keys: List[str] = [], *, db: Db, cur=None ) -> None: # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. self.journal_writer.content_update(contents) db.mktemp("content", cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) with convert_validation_exceptions(): db.copy_to(contents, "tmp_content", select_keys, cur) db.content_update_from_temp(keys_to_update=keys, cur=cur) @db_transaction() def content_add_metadata( self, content: List[Content], *, db: Db, cur=None ) -> Dict[str, int]: missing = self.content_missing( (c.to_dict() for c in content), key_hash="sha1_git", db=db, cur=cur, ) contents = [c for c in content if c.sha1_git in missing] self.journal_writer.content_add_metadata(contents) self._content_add_metadata(db, cur, contents) return { "content:add": len(contents), } def content_get_data(self, content: Sha1) -> Optional[bytes]: # FIXME: Make this method support slicing the `data` return self.objstorage.content_get(content) @db_transaction() def content_get_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, *, db: Db, cur=None, ) -> PagedResult[Content]: if limit is None: raise StorageArgumentException("limit should not be None") (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE ) if page_token: start = hash_to_bytes(page_token) if end is None: end = b"\xff" * SHA1_SIZE next_page_token: Optional[str] = None contents = [] for counter, row in enumerate(db.content_get_range(start, end, limit + 1, cur)): row_d = dict(zip(db.content_get_metadata_keys, row)) content = Content(**row_d) if counter >= limit: # take the last content for the next page starting from this next_page_token = hash_to_hex(content.sha1) break contents.append(content) assert len(contents) <= limit return PagedResult(results=contents, next_page_token=next_page_token) @db_transaction(statement_timeout=500) def content_get( self, contents: List[bytes], algo: str = "sha1", *, db: Db, cur=None ) -> List[Optional[Content]]: contents_by_hash: Dict[bytes, Optional[Content]] = {} if algo not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "algo should be one of {','.join(DEFAULT_ALGORITHMS)}" ) rows = db.content_get_metadata_from_hashes(contents, algo, cur) key = operator.attrgetter(algo) for row in rows: row_d = dict(zip(db.content_get_metadata_keys, row)) content = Content(**row_d) contents_by_hash[key(content)] = content return [contents_by_hash.get(sha1) for sha1 in contents] @db_transaction_generator() def content_missing( self, contents: List[Dict[str, Any]], key_hash: str = "sha1", *, db: Db, cur=None, ) -> Iterable[bytes]: if key_hash not in DEFAULT_ALGORITHMS: raise StorageArgumentException( "key_hash should be one of {','.join(DEFAULT_ALGORITHMS)}" ) keys = db.content_hash_keys key_hash_idx = keys.index(key_hash) for obj in db.content_missing_from_list(contents, cur): yield obj[key_hash_idx] @db_transaction_generator() def content_missing_per_sha1( self, contents: List[bytes], *, db: Db, cur=None ) -> Iterable[bytes]: for obj in db.content_missing_per_sha1(contents, cur): yield obj[0] @db_transaction_generator() def content_missing_per_sha1_git( self, contents: List[bytes], *, db: Db, cur=None ) -> Iterable[Sha1Git]: for obj in db.content_missing_per_sha1_git(contents, cur): yield obj[0] @db_transaction() def content_find( self, content: Dict[str, Any], *, db: Db, cur=None ) -> List[Content]: if not set(content).intersection(DEFAULT_ALGORITHMS): raise StorageArgumentException( "content keys must contain at least one " f"of: {', '.join(sorted(DEFAULT_ALGORITHMS))}" ) rows = db.content_find( sha1=content.get("sha1"), sha1_git=content.get("sha1_git"), sha256=content.get("sha256"), blake2s256=content.get("blake2s256"), cur=cur, ) contents = [] for row in rows: row_d = dict(zip(db.content_find_cols, row)) contents.append(Content(**row_d)) return contents @db_transaction() def content_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.content_get_random(cur) @staticmethod def _skipped_content_normalize(d): d = d.copy() if d.get("status") is None: d["status"] = "absent" if d.get("length") is None: d["length"] = -1 return d def _skipped_content_add_metadata(self, db, cur, content: List[SkippedContent]): origin_ids = db.origin_id_get_by_url([cont.origin for cont in content], cur=cur) content = [ attr.evolve(c, origin=origin_id) for (c, origin_id) in zip(content, origin_ids) ] db.mktemp("skipped_content", cur) db.copy_to( [c.to_dict() for c in content], "tmp_skipped_content", db.skipped_content_keys, cur, ) # move metadata in place db.skipped_content_add_from_temp(cur) @db_transaction() def skipped_content_add( self, content: List[SkippedContent], *, db: Db, cur=None ) -> Dict[str, int]: ctime = now() content = [attr.evolve(c, ctime=ctime) for c in content] missing_contents = self.skipped_content_missing( (c.to_dict() for c in content), db=db, cur=cur, ) content = [ c for c in content if any( all( c.get_hash(algo) == missing_content.get(algo) for algo in DEFAULT_ALGORITHMS ) for missing_content in missing_contents ) ] self.journal_writer.skipped_content_add(content) self._skipped_content_add_metadata(db, cur, content) return { "skipped_content:add": len(content), } @db_transaction_generator() def skipped_content_missing( self, contents: List[Dict[str, Any]], *, db: Db, cur=None ) -> Iterable[Dict[str, Any]]: contents = list(contents) for content in db.skipped_content_missing(contents, cur): yield dict(zip(db.content_hash_keys, content)) @db_transaction() def directory_add( self, directories: List[Directory], *, db: Db, cur=None ) -> Dict[str, int]: summary = {"directory:add": 0} dirs = set() dir_entries: Dict[str, defaultdict] = { "file": defaultdict(list), "dir": defaultdict(list), "rev": defaultdict(list), } for cur_dir in directories: dir_id = cur_dir.id dirs.add(dir_id) for src_entry in cur_dir.entries: entry = src_entry.to_dict() entry["dir_id"] = dir_id dir_entries[entry["type"]][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs, db=db, cur=cur)) if not dirs_missing: return summary self.journal_writer.directory_add( dir_ for dir_ in directories if dir_.id in dirs_missing ) # Copy directory metadata dirs_missing_dict = ( {"id": dir_.id, "raw_manifest": dir_.raw_manifest} for dir_ in directories if dir_.id in dirs_missing ) db.mktemp("directory", cur) db.copy_to(dirs_missing_dict, "tmp_directory", ["id", "raw_manifest"], cur) # Copy entries for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing ) db.mktemp_dir_entry(entry_type) db.copy_to( entries, "tmp_directory_entry_%s" % entry_type, ["target", "name", "perms", "dir_id"], cur, ) # Do the final copy db.directory_add_from_temp(cur) summary["directory:add"] = len(dirs_missing) return summary @db_transaction_generator() def directory_missing( self, directories: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: for obj in db.directory_missing_from_list(directories, cur): yield obj[0] @db_transaction_generator(statement_timeout=20000) def directory_ls( self, directory: Sha1Git, recursive: bool = False, *, db: Db, cur=None ) -> Iterable[Dict[str, Any]]: if recursive: res_gen = db.directory_walk(directory, cur=cur) else: res_gen = db.directory_walk_one(directory, cur=cur) for line in res_gen: yield dict(zip(db.directory_ls_cols, line)) @db_transaction(statement_timeout=4000) def directory_entry_get_by_path( self, directory: Sha1Git, paths: List[bytes], *, db: Db, cur=None ) -> Optional[Dict[str, Any]]: res = db.directory_entry_get_by_path(directory, paths, cur) return dict(zip(db.directory_ls_cols, res)) if res else None @db_transaction() def directory_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.directory_get_random(cur) @db_transaction() def directory_get_entries( self, directory_id: Sha1Git, page_token: Optional[bytes] = None, limit: int = 1000, *, db: Db, cur=None, ) -> Optional[PagedResult[DirectoryEntry]]: if list(self.directory_missing([directory_id], db=db, cur=cur)): return None if page_token is not None: raise StorageArgumentException("Unsupported page token") # TODO: actually paginate rows = db.directory_get_entries(directory_id, cur=cur) return PagedResult( results=[ DirectoryEntry(**dict(zip(db.directory_get_entries_cols, row))) for row in rows ], next_page_token=None, ) @db_transaction() def directory_get_raw_manifest( self, directory_ids: List[Sha1Git], *, db: Db, cur=None ) -> Dict[Sha1Git, Optional[bytes]]: return dict(db.directory_get_raw_manifest(directory_ids, cur=cur)) @db_transaction() def revision_add( self, revisions: List[Revision], *, db: Db, cur=None ) -> Dict[str, int]: summary = {"revision:add": 0} revisions_missing = set( self.revision_missing( set(revision.id for revision in revisions), db=db, cur=cur ) ) if not revisions_missing: return summary db.mktemp_revision(cur) revisions_filtered = [ revision for revision in revisions if revision.id in revisions_missing ] self.journal_writer.revision_add(revisions_filtered) db_revisions_filtered = list(map(converters.revision_to_db, revisions_filtered)) parents_filtered: List[Dict[str, Any]] = [] with convert_validation_exceptions(): db.copy_to( db_revisions_filtered, "tmp_revision", db.revision_add_cols, cur, lambda rev: parents_filtered.extend(rev["parents"]), ) db.revision_add_from_temp(cur) db.copy_to( parents_filtered, "revision_history", ["id", "parent_id", "parent_rank"], cur, ) return {"revision:add": len(revisions_missing)} @db_transaction_generator() def revision_missing( self, revisions: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: if not revisions: return None for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @db_transaction(statement_timeout=2000) def revision_get( self, revision_ids: List[Sha1Git], ignore_displayname: bool = False, *, db: Db, cur=None, ) -> List[Optional[Revision]]: revisions = [] for line in db.revision_get_from_list(revision_ids, ignore_displayname, cur): revision = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) revisions.append(revision) return revisions @db_transaction_generator(statement_timeout=2000) def revision_log( self, revisions: List[Sha1Git], ignore_displayname: bool = False, limit: Optional[int] = None, *, db: Db, cur=None, ) -> Iterable[Optional[Dict[str, Any]]]: for line in db.revision_log( revisions, ignore_displayname=ignore_displayname, limit=limit, cur=cur ): data = converters.db_to_revision(dict(zip(db.revision_get_cols, line))) if not data: yield None continue yield data.to_dict() @db_transaction_generator(statement_timeout=2000) def revision_shortlog( self, revisions: List[Sha1Git], limit: Optional[int] = None, *, db: Db, cur=None ) -> Iterable[Optional[Tuple[Sha1Git, Tuple[Sha1Git, ...]]]]: yield from db.revision_shortlog(revisions, limit, cur) @db_transaction() def revision_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.revision_get_random(cur) @db_transaction() def extid_get_from_extid( self, id_type: str, ids: List[bytes], version: Optional[int] = None, *, db: Db, cur=None, ) -> List[ExtID]: extids = [] for row in db.extid_get_from_extid_list(id_type, ids, version=version, cur=cur): if row[0] is not None: extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row)))) return extids @db_transaction() def extid_get_from_target( self, target_type: ObjectType, ids: List[Sha1Git], extid_type: Optional[str] = None, extid_version: Optional[int] = None, *, db: Db, cur=None, ) -> List[ExtID]: extids = [] if (extid_version is not None and extid_type is None) or ( extid_version is None and extid_type is not None ): raise ValueError("You must provide both extid_type and extid_version") for row in db.extid_get_from_swhid_list( target_type.value, ids, extid_version=extid_version, extid_type=extid_type, cur=cur, ): if row[0] is not None: extids.append(converters.db_to_extid(dict(zip(db.extid_cols, row)))) return extids @db_transaction() def extid_add(self, ids: List[ExtID], *, db: Db, cur=None) -> Dict[str, int]: extid = [ { "extid": extid.extid, "extid_type": extid.extid_type, "extid_version": getattr(extid, "extid_version", 0), "target": extid.target.object_id, "target_type": extid.target.object_type.name.lower(), # arghh } for extid in ids ] db.mktemp("extid", cur) self.journal_writer.extid_add(ids) db.copy_to(extid, "tmp_extid", db.extid_cols, cur) # move metadata in place db.extid_add_from_temp(cur) return {"extid:add": len(extid)} @db_transaction() def release_add( self, releases: List[Release], *, db: Db, cur=None ) -> Dict[str, int]: summary = {"release:add": 0} release_ids = set(release.id for release in releases) releases_missing = set(self.release_missing(release_ids, db=db, cur=cur)) if not releases_missing: return summary db.mktemp_release(cur) releases_filtered = [ release for release in releases if release.id in releases_missing ] self.journal_writer.release_add(releases_filtered) db_releases_filtered = list(map(converters.release_to_db, releases_filtered)) with convert_validation_exceptions(): db.copy_to(db_releases_filtered, "tmp_release", db.release_add_cols, cur) db.release_add_from_temp(cur) return {"release:add": len(releases_missing)} @db_transaction_generator() def release_missing( self, releases: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @db_transaction(statement_timeout=1000) def release_get( self, releases: List[Sha1Git], ignore_displayname: bool = False, *, db: Db, cur=None, ) -> List[Optional[Release]]: rels = [] for release in db.release_get_from_list(releases, ignore_displayname, cur): data = converters.db_to_release(dict(zip(db.release_get_cols, release))) rels.append(data if data else None) return rels @db_transaction() def release_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.release_get_random(cur) @db_transaction() def snapshot_add( self, snapshots: List[Snapshot], *, db: Db, cur=None ) -> Dict[str, int]: created_temp_table = False count = 0 for snapshot in snapshots: if not db.snapshot_exists(snapshot.id, cur): if not created_temp_table: db.mktemp_snapshot_branch(cur) created_temp_table = True with convert_validation_exceptions(): db.copy_to( ( { "name": name, "target": info.target if info else None, "target_type": ( info.target_type.value if info else None ), } for name, info in snapshot.branches.items() ), "tmp_snapshot_branch", ["name", "target", "target_type"], cur, ) self.journal_writer.snapshot_add([snapshot]) db.snapshot_add(snapshot.id, cur) count += 1 return {"snapshot:add": count} @db_transaction_generator() def snapshot_missing( self, snapshots: List[Sha1Git], *, db: Db, cur=None ) -> Iterable[Sha1Git]: for obj in db.snapshot_missing_from_list(snapshots, cur): yield obj[0] @db_transaction(statement_timeout=2000) def snapshot_get( self, snapshot_id: Sha1Git, *, db: Db, cur=None ) -> Optional[Dict[str, Any]]: d = self.snapshot_get_branches(snapshot_id) if d is None: return d return { "id": d["id"], "branches": { name: branch.to_dict() if branch else None for (name, branch) in d["branches"].items() }, "next_branch": d["next_branch"], } @db_transaction(statement_timeout=2000) def snapshot_count_branches( self, snapshot_id: Sha1Git, branch_name_exclude_prefix: Optional[bytes] = None, *, db: Db, cur=None, ) -> Optional[Dict[Optional[str], int]]: return dict( [ bc for bc in db.snapshot_count_branches( snapshot_id, branch_name_exclude_prefix, cur, ) ] ) @db_transaction(statement_timeout=2000) def snapshot_get_branches( self, snapshot_id: Sha1Git, branches_from: bytes = b"", branches_count: int = 1000, target_types: Optional[List[str]] = None, branch_name_include_substring: Optional[bytes] = None, branch_name_exclude_prefix: Optional[bytes] = None, *, db: Db, cur=None, ) -> Optional[PartialBranches]: if snapshot_id == EMPTY_SNAPSHOT_ID: return PartialBranches( id=snapshot_id, branches={}, next_branch=None, ) if list(self.snapshot_missing([snapshot_id])): return None branches = {} next_branch = None fetched_branches = list( db.snapshot_get_by_id( snapshot_id, branches_from=branches_from, # the underlying SQL query can be quite expensive to execute for small # branches_count value, so we ensure a minimum branches limit of 10 for # optimal performances branches_count=max(branches_count + 1, 10), target_types=target_types, branch_name_include_substring=branch_name_include_substring, branch_name_exclude_prefix=branch_name_exclude_prefix, cur=cur, ) ) for row in fetched_branches[:branches_count]: branch_d = dict(zip(db.snapshot_get_cols, row)) del branch_d["snapshot_id"] name = branch_d.pop("name") if branch_d["target"] is None and branch_d["target_type"] is None: branch = None else: assert branch_d["target_type"] is not None branch = SnapshotBranch( target=branch_d["target"], target_type=TargetType(branch_d["target_type"]), ) branches[name] = branch if len(fetched_branches) > branches_count: next_branch = dict( zip(db.snapshot_get_cols, fetched_branches[branches_count]) )["name"] return PartialBranches( id=snapshot_id, branches=branches, next_branch=next_branch, ) @db_transaction() def snapshot_get_random(self, *, db: Db, cur=None) -> Sha1Git: return db.snapshot_get_random(cur) @db_transaction() def origin_visit_add( self, visits: List[OriginVisit], *, db: Db, cur=None ) -> Iterable[OriginVisit]: for visit in visits: origin = self.origin_get([visit.origin], db=db, cur=cur)[0] if not origin: # Cannot add a visit without an origin raise StorageArgumentException("Unknown origin %s", visit.origin) all_visits = [] for visit in visits: if visit.visit: self.journal_writer.origin_visit_add([visit]) db.origin_visit_add_with_id(visit, cur=cur) else: # visit_id is not given, it needs to be set by the db with convert_validation_exceptions(): visit_id = db.origin_visit_add( visit.origin, visit.date, visit.type, cur=cur ) visit = attr.evolve(visit, visit=visit_id) # Forced to write in the journal after the db (since its the db # call that set the visit id) self.journal_writer.origin_visit_add([visit]) # In this case, we also want to create the initial OVS object visit_status = OriginVisitStatus( origin=visit.origin, visit=visit_id, date=visit.date, type=visit.type, status="created", snapshot=None, ) self._origin_visit_status_add(visit_status, db=db, cur=cur) assert visit.visit is not None all_visits.append(visit) return all_visits def _origin_visit_status_add( self, visit_status: OriginVisitStatus, db, cur ) -> None: """Add an origin visit status""" self.journal_writer.origin_visit_status_add([visit_status]) db.origin_visit_status_add(visit_status, cur=cur) @db_transaction() def origin_visit_status_add( self, visit_statuses: List[OriginVisitStatus], *, db: Db, cur=None, ) -> Dict[str, int]: visit_statuses_ = [] # First round to check existence (fail early if any is ko) for visit_status in visit_statuses: origin_url = self.origin_get([visit_status.origin], db=db, cur=cur)[0] if not origin_url: raise StorageArgumentException(f"Unknown origin {visit_status.origin}") if visit_status.type is None: origin_visit = self.origin_visit_get_by( visit_status.origin, visit_status.visit, db=db, cur=cur ) if origin_visit is None: raise StorageArgumentException( f"Unknown origin visit {visit_status.visit} " f"of origin {visit_status.origin}" ) origin_visit_status = attr.evolve(visit_status, type=origin_visit.type) else: origin_visit_status = visit_status visit_statuses_.append(origin_visit_status) for visit_status in visit_statuses_: self._origin_visit_status_add(visit_status, db, cur) return {"origin_visit_status:add": len(visit_statuses_)} @db_transaction() def origin_visit_status_get_latest( self, origin_url: str, visit: int, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, *, db: Db, cur=None, ) -> Optional[OriginVisitStatus]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) row_d = db.origin_visit_status_get_latest( origin_url, visit, allowed_statuses, require_snapshot, cur=cur ) if not row_d: return None return OriginVisitStatus(**row_d) @db_transaction(statement_timeout=500) def origin_visit_get( self, origin: str, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, *, db: Db, cur=None, ) -> PagedResult[OriginVisit]: page_token = page_token or "0" if not isinstance(order, ListOrder): raise StorageArgumentException("order must be a ListOrder value") if not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") next_page_token = None visit_from = int(page_token) visits: List[OriginVisit] = [] extra_limit = limit + 1 for row in db.origin_visit_get_range( origin, visit_from=visit_from, order=order, limit=extra_limit, cur=cur ): row_d = dict(zip(db.origin_visit_cols, row)) visits.append( OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) ) assert len(visits) <= extra_limit if len(visits) == extra_limit: visits = visits[:limit] next_page_token = str(visits[-1].visit) return PagedResult(results=visits, next_page_token=next_page_token) @db_transaction(statement_timeout=2000) def origin_visit_get_with_statuses( self, origin: str, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, *, db: Db, cur=None, ) -> PagedResult[OriginVisitWithStatuses]: page_token = page_token or "0" if not isinstance(order, ListOrder): raise StorageArgumentException("order must be a ListOrder value") if not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") # First get visits (plus one so we can use it as the next page token if any) visits_page = self.origin_visit_get( origin=origin, page_token=page_token, order=order, limit=limit, db=db, cur=cur, ) visits = visits_page.results next_page_token = visits_page.next_page_token if visits: visit_from = min(visits[0].visit, visits[-1].visit) visit_to = max(visits[0].visit, visits[-1].visit) # Then, fetch all statuses associated to these visits visit_statuses: Dict[int, List[OriginVisitStatus]] = defaultdict(list) for row in db.origin_visit_status_get_all_in_range( origin, allowed_statuses, require_snapshot, visit_from=visit_from, visit_to=visit_to, cur=cur, ): row_d = dict(zip(db.origin_visit_status_cols, row)) visit_statuses[row_d["visit"]].append(OriginVisitStatus(**row_d)) results = [ OriginVisitWithStatuses(visit=visit, statuses=visit_statuses[visit.visit]) for visit in visits ] return PagedResult(results=results, next_page_token=next_page_token) @db_transaction(statement_timeout=2000) def origin_visit_find_by_date( self, origin: str, visit_date: datetime.datetime, *, db: Db, cur=None ) -> Optional[OriginVisit]: row_d = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if not row_d: return None return OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) @db_transaction(statement_timeout=500) def origin_visit_get_by( self, origin: str, visit: int, *, db: Db, cur=None ) -> Optional[OriginVisit]: row = db.origin_visit_get(origin, visit, cur) if row: row_d = dict(zip(db.origin_visit_get_cols, row)) return OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) return None @db_transaction(statement_timeout=4000) def origin_visit_get_latest( self, origin: str, type: Optional[str] = None, allowed_statuses: Optional[List[str]] = None, require_snapshot: bool = False, *, db: Db, cur=None, ) -> Optional[OriginVisit]: if allowed_statuses and not set(allowed_statuses).intersection(VISIT_STATUSES): raise StorageArgumentException( f"Unknown allowed statuses {','.join(allowed_statuses)}, only " f"{','.join(VISIT_STATUSES)} authorized" ) row = db.origin_visit_get_latest( origin, type=type, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, cur=cur, ) if row: row_d = dict(zip(db.origin_visit_get_cols, row)) + assert ( + row_d["visit"] is not None + ), "origin_visit_status LEFT JOIN origin_visit returned NULL" visit = OriginVisit( origin=row_d["origin"], visit=row_d["visit"], date=row_d["date"], type=row_d["type"], ) return visit return None @db_transaction(statement_timeout=500) def origin_visit_status_get( self, origin: str, visit: int, page_token: Optional[str] = None, order: ListOrder = ListOrder.ASC, limit: int = 10, *, db: Db, cur=None, ) -> PagedResult[OriginVisitStatus]: next_page_token = None date_from = None if page_token is not None: - date_from = datetime.datetime.fromisoformat(page_token) + try: + date_from = datetime.datetime.fromisoformat(page_token) + except ValueError: + raise StorageArgumentException( + "Invalid page_token argument to origin_visit_status_get." + ) from None visit_statuses: List[OriginVisitStatus] = [] # Take one more visit status so we can reuse it as the next page token if any for row in db.origin_visit_status_get_range( origin, visit, date_from=date_from, order=order, limit=limit + 1, cur=cur, ): row_d = dict(zip(db.origin_visit_status_cols, row)) visit_statuses.append(OriginVisitStatus(**row_d)) if len(visit_statuses) > limit: # last visit status date is the next page token next_page_token = str(visit_statuses[-1].date) # excluding that visit status from the result to respect the limit size visit_statuses = visit_statuses[:limit] return PagedResult(results=visit_statuses, next_page_token=next_page_token) @db_transaction() def origin_visit_status_get_random( self, type: str, *, db: Db, cur=None ) -> Optional[OriginVisitStatus]: row = db.origin_visit_get_random(type, cur) if row is not None: row_d = dict(zip(db.origin_visit_status_cols, row)) return OriginVisitStatus(**row_d) return None @db_transaction(statement_timeout=2000) def object_find_by_sha1_git( self, ids: List[Sha1Git], *, db: Db, cur=None ) -> Dict[Sha1Git, List[Dict]]: ret: Dict[Sha1Git, List[Dict]] = {id: [] for id in ids} for retval in db.object_find_by_sha1_git(ids, cur=cur): if retval[1]: ret[retval[0]].append( dict(zip(db.object_find_by_sha1_git_cols, retval)) ) return ret @db_transaction(statement_timeout=1000) def origin_get( self, origins: List[str], *, db: Db, cur=None ) -> Iterable[Optional[Origin]]: rows = db.origin_get_by_url(origins, cur) result: List[Optional[Origin]] = [] for row in rows: origin_d = dict(zip(db.origin_cols, row)) url = origin_d["url"] result.append(None if url is None else Origin(url=url)) return result @db_transaction(statement_timeout=1000) def origin_get_by_sha1( self, sha1s: List[bytes], *, db: Db, cur=None ) -> List[Optional[Dict[str, Any]]]: return [ dict(zip(db.origin_cols, row)) if row[0] else None for row in db.origin_get_by_sha1(sha1s, cur) ] @db_transaction_generator() def origin_get_range(self, origin_from=1, origin_count=100, *, db: Db, cur=None): for origin in db.origin_get_range(origin_from, origin_count, cur): yield dict(zip(db.origin_get_range_cols, origin)) @db_transaction() def origin_list( self, page_token: Optional[str] = None, limit: int = 100, *, db: Db, cur=None ) -> PagedResult[Origin]: page_token = page_token or "0" if not isinstance(page_token, str): raise StorageArgumentException("page_token must be a string.") origin_from = int(page_token) next_page_token = None origins: List[Origin] = [] # Take one more origin so we can reuse it as the next page token if any for row_d in self.origin_get_range(origin_from, limit + 1, db=db, cur=cur): origins.append(Origin(url=row_d["url"])) # keep the last_id for the pagination if needed last_id = row_d["id"] if len(origins) > limit: # data left for subsequent call # last origin id is the next page token next_page_token = str(last_id) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @db_transaction() def origin_search( self, url_pattern: str, page_token: Optional[str] = None, limit: int = 50, regexp: bool = False, with_visit: bool = False, visit_types: Optional[List[str]] = None, *, db: Db, cur=None, ) -> PagedResult[Origin]: next_page_token = None offset = int(page_token) if page_token else 0 origins = [] # Take one more origin so we can reuse it as the next page token if any for origin in db.origin_search( url_pattern, offset, limit + 1, regexp, with_visit, visit_types, cur ): row_d = dict(zip(db.origin_cols, origin)) origins.append(Origin(url=row_d["url"])) if len(origins) > limit: # next offset next_page_token = str(offset + limit) # excluding that origin from the result to respect the limit size origins = origins[:limit] assert len(origins) <= limit return PagedResult(results=origins, next_page_token=next_page_token) @db_transaction() def origin_count( self, url_pattern: str, regexp: bool = False, with_visit: bool = False, *, db: Db, cur=None, ) -> int: return db.origin_count(url_pattern, regexp, with_visit, cur) @db_transaction() def origin_snapshot_get_all( self, origin_url: str, *, db: Db, cur=None ) -> List[Sha1Git]: return list(db.origin_snapshot_get_all(origin_url, cur)) @db_transaction() def origin_add(self, origins: List[Origin], *, db: Db, cur=None) -> Dict[str, int]: urls = [o.url for o in origins] known_origins = set(url for (url,) in db.origin_get_by_url(urls, cur)) # keep only one occurrence of each given origin while keeping the list # sorted as originally given to_add = sorted(set(urls) - known_origins, key=urls.index) self.journal_writer.origin_add([Origin(url=url) for url in to_add]) added = 0 for url in to_add: if db.origin_add(url, cur): added += 1 return {"origin:add": added} @db_transaction(statement_timeout=500) def stat_counters(self, *, db: Db, cur=None): return {k: v for (k, v) in db.stat_counters()} @db_transaction() def refresh_stat_counters(self, *, db: Db, cur=None): keys = [ "content", "directory", "directory_entry_dir", "directory_entry_file", "directory_entry_rev", "origin", "origin_visit", "person", "release", "revision", "revision_history", "skipped_content", "snapshot", ] for key in keys: cur.execute("select * from swh_update_counter(%s)", (key,)) @db_transaction() def raw_extrinsic_metadata_add( self, metadata: List[RawExtrinsicMetadata], db, cur, ) -> Dict[str, int]: metadata = list(metadata) self.journal_writer.raw_extrinsic_metadata_add(metadata) counter = Counter[ExtendedObjectType]() for metadata_entry in metadata: authority_id = self._get_authority_id(metadata_entry.authority, db, cur) fetcher_id = self._get_fetcher_id(metadata_entry.fetcher, db, cur) db.raw_extrinsic_metadata_add( id=metadata_entry.id, type=metadata_entry.target.object_type.name.lower(), target=str(metadata_entry.target), discovery_date=metadata_entry.discovery_date, authority_id=authority_id, fetcher_id=fetcher_id, format=metadata_entry.format, metadata=metadata_entry.metadata, origin=metadata_entry.origin, visit=metadata_entry.visit, snapshot=map_optional(str, metadata_entry.snapshot), release=map_optional(str, metadata_entry.release), revision=map_optional(str, metadata_entry.revision), path=metadata_entry.path, directory=map_optional(str, metadata_entry.directory), cur=cur, ) counter[metadata_entry.target.object_type] += 1 return { f"{type.value}_metadata:add": count for (type, count) in counter.items() } @db_transaction() def raw_extrinsic_metadata_get( self, target: ExtendedSWHID, authority: MetadataAuthority, after: Optional[datetime.datetime] = None, page_token: Optional[bytes] = None, limit: int = 1000, *, db: Db, cur=None, ) -> PagedResult[RawExtrinsicMetadata]: if page_token: (after_time, after_fetcher) = msgpack_loads(base64.b64decode(page_token)) if after and after_time < after: raise StorageArgumentException( "page_token is inconsistent with the value of 'after'." ) else: after_time = after after_fetcher = None authority_id = self._get_authority_id(authority, db, cur) if not authority_id: return PagedResult( next_page_token=None, results=[], ) rows = db.raw_extrinsic_metadata_get( str(target), authority_id, after_time, after_fetcher, limit + 1, cur, ) rows = [dict(zip(db.raw_extrinsic_metadata_get_cols, row)) for row in rows] results = [] for row in rows: assert str(target) == row["raw_extrinsic_metadata.target"] results.append(converters.db_to_raw_extrinsic_metadata(row)) if len(results) > limit: results.pop() assert len(results) == limit last_returned_row = rows[-2] # rows[-1] corresponds to the popped result next_page_token: Optional[str] = base64.b64encode( msgpack_dumps( ( last_returned_row["discovery_date"], last_returned_row["metadata_fetcher.id"], ) ) ).decode() else: next_page_token = None return PagedResult( next_page_token=next_page_token, results=results, ) @db_transaction() def raw_extrinsic_metadata_get_by_ids( self, ids: List[Sha1Git], *, db: Db, cur=None, ) -> List[RawExtrinsicMetadata]: return [ converters.db_to_raw_extrinsic_metadata( dict(zip(db.raw_extrinsic_metadata_get_cols, row)) ) for row in db.raw_extrinsic_metadata_get_by_ids(ids) ] @db_transaction() def raw_extrinsic_metadata_get_authorities( self, target: ExtendedSWHID, *, db: Db, cur=None, ) -> List[MetadataAuthority]: return [ MetadataAuthority( type=MetadataAuthorityType(authority_type), url=authority_url ) for ( authority_type, authority_url, ) in db.raw_extrinsic_metadata_get_authorities(str(target), cur) ] @db_transaction() def metadata_fetcher_add( self, fetchers: List[MetadataFetcher], *, db: Db, cur=None ) -> Dict[str, int]: fetchers = list(fetchers) self.journal_writer.metadata_fetcher_add(fetchers) count = 0 for fetcher in fetchers: db.metadata_fetcher_add(fetcher.name, fetcher.version, cur=cur) count += 1 return {"metadata_fetcher:add": count} @db_transaction(statement_timeout=500) def metadata_fetcher_get( self, name: str, version: str, *, db: Db, cur=None ) -> Optional[MetadataFetcher]: row = db.metadata_fetcher_get(name, version, cur=cur) if not row: return None return MetadataFetcher.from_dict(dict(zip(db.metadata_fetcher_cols, row))) @db_transaction() def metadata_authority_add( self, authorities: List[MetadataAuthority], *, db: Db, cur=None ) -> Dict[str, int]: authorities = list(authorities) self.journal_writer.metadata_authority_add(authorities) count = 0 for authority in authorities: db.metadata_authority_add(authority.type.value, authority.url, cur=cur) count += 1 return {"metadata_authority:add": count} @db_transaction() def metadata_authority_get( self, type: MetadataAuthorityType, url: str, *, db: Db, cur=None ) -> Optional[MetadataAuthority]: row = db.metadata_authority_get(type.value, url, cur=cur) if not row: return None return MetadataAuthority.from_dict(dict(zip(db.metadata_authority_cols, row))) def clear_buffers(self, object_types: Sequence[str] = ()) -> None: """Do nothing""" return None def flush(self, object_types: Sequence[str] = ()) -> Dict[str, int]: return {} def _get_authority_id(self, authority: MetadataAuthority, db, cur): authority_id = db.metadata_authority_get_id( authority.type.value, authority.url, cur ) if not authority_id: raise StorageArgumentException(f"Unknown authority {authority}") return authority_id def _get_fetcher_id(self, fetcher: MetadataFetcher, db, cur): fetcher_id = db.metadata_fetcher_get_id(fetcher.name, fetcher.version, cur) if not fetcher_id: raise StorageArgumentException(f"Unknown fetcher {fetcher}") return fetcher_id diff --git a/swh/storage/proxies/retry.py b/swh/storage/proxies/retry.py index 99756ae2..f58af3c9 100644 --- a/swh/storage/proxies/retry.py +++ b/swh/storage/proxies/retry.py @@ -1,101 +1,101 @@ # Copyright (C) 2019-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import logging import traceback from tenacity import RetryCallState, retry, stop_after_attempt, wait_random_exponential from tenacity.wait import wait_base from swh.core.api import TransientRemoteException from swh.storage import get_storage from swh.storage.exc import StorageArgumentException from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) def should_retry_adding(retry_state: RetryCallState) -> bool: """Retry if the error/exception is (probably) not about a caller error""" attempt = retry_state.outcome assert attempt if attempt.failed: error = attempt.exception() if isinstance(error, StorageArgumentException): # Exception is due to an invalid argument return False - elif isinstance(error, KeyboardInterrupt): + elif isinstance(error, (KeyboardInterrupt, SystemExit)): return False else: # Other exception module = getattr(error, "__module__", None) if module: error_name = error.__module__ + "." + error.__class__.__name__ else: error_name = error.__class__.__name__ logger.warning( "Retrying RPC call", exc_info=False, extra={ "swh_type": "storage_retry", "swh_exception_type": error_name, "swh_exception": traceback.format_exc(), }, ) return True else: # No exception return False class wait_transient_exceptions(wait_base): """Wait longer when servers return HTTP 503.""" def __init__(self, wait: float) -> None: self.wait = wait def __call__(self, retry_state: RetryCallState) -> float: attempt = retry_state.outcome assert attempt if attempt.failed and isinstance(attempt.exception(), TransientRemoteException): return self.wait else: return 0.0 swh_retry = retry( retry=should_retry_adding, wait=wait_random_exponential(multiplier=1, max=10) + wait_transient_exceptions(10), stop=stop_after_attempt(3), reraise=True, ) def retry_function(storage, attribute_name): @swh_retry def newf(*args, **kwargs): return getattr(storage, attribute_name)(*args, **kwargs) return newf class RetryingProxyStorage: """Storage implementation which retries adding objects when it specifically fails (hash collision, integrity error). """ def __init__(self, storage): self.storage: StorageInterface = get_storage(**storage) for attribute_name in dir(StorageInterface): if attribute_name.startswith("_"): continue attribute = getattr(self.storage, attribute_name) if hasattr(attribute, "__call__"): setattr( self, attribute_name, retry_function(self.storage, attribute_name) ) diff --git a/swh/storage/sql/40-funcs.sql b/swh/storage/sql/40-funcs.sql index f87caaae..ce3a298d 100644 --- a/swh/storage/sql/40-funcs.sql +++ b/swh/storage/sql/40-funcs.sql @@ -1,1024 +1,1031 @@ create or replace function hash_sha1(text) returns text as $$ select encode(digest($1, 'sha1'), 'hex') $$ language sql strict immutable; comment on function hash_sha1(text) is 'Compute SHA1 hash as text'; -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: -- tblname: name of the table to mimic create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table if not exists tmp_%1$I (like %1$I including defaults) on commit delete rows; alter table tmp_%1$I drop column if exists object_id; ', tblname); return; end $$; -- create a temporary table for directory entries called tmp_TBLNAME, -- mimicking existing table TBLNAME with an extra dir_id (sha1_git) -- column, and dropping the id column. -- -- This is used to create the tmp_directory_entry_ tables. -- -- Args: -- tblname: name of the table to mimic create or replace function swh_mktemp_dir_entry(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table if not exists tmp_%1$I (like %1$I including defaults, dir_id sha1_git) on commit delete rows; alter table tmp_%1$I drop column if exists id; ', tblname); return; end $$; -- create a temporary table for revisions called tmp_revisions, -- mimicking existing table revision, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_revision() returns void language sql as $$ create temporary table if not exists tmp_revision ( like revision including defaults, author_fullname bytea, author_name bytea, author_email bytea, committer_fullname bytea, committer_name bytea, committer_email bytea ) on commit delete rows; alter table tmp_revision drop column if exists author; alter table tmp_revision drop column if exists committer; alter table tmp_revision drop column if exists object_id; $$; -- create a temporary table for releases called tmp_release, -- mimicking existing table release, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_release() returns void language sql as $$ create temporary table if not exists tmp_release ( like release including defaults, author_fullname bytea, author_name bytea, author_email bytea ) on commit delete rows; alter table tmp_release drop column if exists author; alter table tmp_release drop column if exists object_id; $$; -- create a temporary table for the branches of a snapshot create or replace function swh_mktemp_snapshot_branch() returns void language sql as $$ create temporary table if not exists tmp_snapshot_branch ( name bytea not null, target bytea, target_type snapshot_target ) on commit delete rows; $$; -- a content signature is a set of cryptographic checksums that we use to -- uniquely identify content, for the purpose of verifying if we already have -- some content or not during content injection create type content_signature as ( sha1 sha1, sha1_git sha1_git, sha256 sha256, blake2s256 blake2s256 ); -- check which entries of tmp_skipped_content are missing from skipped_content -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_missing() returns setof content_signature language plpgsql as $$ begin return query select sha1, sha1_git, sha256, blake2s256 from tmp_skipped_content t where not exists (select 1 from skipped_content s where s.sha1 is not distinct from t.sha1 and s.sha1_git is not distinct from t.sha1_git and s.sha256 is not distinct from t.sha256); return; end $$; -- add tmp_content entries to content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content, -- 2. call this function create or replace function swh_content_add() returns void language plpgsql as $$ begin insert into content (sha1, sha1_git, sha256, blake2s256, length, status, ctime) select distinct sha1, sha1_git, sha256, blake2s256, length, status, ctime from tmp_content; return; end $$; -- add tmp_skipped_content entries to skipped_content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_add() returns void language plpgsql as $$ begin insert into skipped_content (sha1, sha1_git, sha256, blake2s256, length, status, reason, origin) select distinct sha1, sha1_git, sha256, blake2s256, length, status, reason, origin from tmp_skipped_content where (coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '')) in ( select coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '') from swh_skipped_content_missing() ); -- TODO XXX use postgres 9.5 "UPSERT" support here, when available. -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid -- the extra swh_skipped_content_missing() query here. return; end $$; -- Update content entries from temporary table. -- (columns are potential new columns added to the schema, this cannot be empty) -- create or replace function swh_content_update(columns_update text[]) returns void language plpgsql as $$ declare query text; tmp_array text[]; begin if array_length(columns_update, 1) = 0 then raise exception 'Please, provide the list of column names to update.'; end if; tmp_array := array(select format('%1$s=t.%1$s', unnest) from unnest(columns_update)); query = format('update content set %s from tmp_content t where t.sha1 = content.sha1', array_to_string(tmp_array, ', ')); execute query; return; end $$; comment on function swh_content_update(text[]) IS 'Update existing content''s columns'; create type directory_entry_type as enum('file', 'dir', 'rev'); -- Add tmp_directory_entry_* entries to directory_entry_* and directory, -- skipping duplicates in directory_entry_*. This is a generic function that -- works on all kind of directory entries. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_*'), 1 COPY to -- tmp_directory_entry_*, 2. call this function -- -- Assumption: this function is used in the same transaction that inserts the -- context directory in table "directory". create or replace function swh_directory_entry_add(typ directory_entry_type) returns void language plpgsql as $$ begin execute format(' insert into directory_entry_%1$s (target, name, perms) select distinct t.target, t.name, t.perms from tmp_directory_entry_%1$s t where not exists ( select 1 from directory_entry_%1$s i where t.target = i.target and t.name = i.name and t.perms = i.perms) ', typ); execute format(' with new_entries as ( select t.dir_id, array_agg(i.id) as entries from tmp_directory_entry_%1$s t inner join directory_entry_%1$s i using (target, name, perms) group by t.dir_id ) update tmp_directory as d set %1$s_entries = new_entries.entries from new_entries where d.id = new_entries.dir_id ', typ); return; end $$; -- Insert the data from tmp_directory, tmp_directory_entry_file, -- tmp_directory_entry_dir, tmp_directory_entry_rev into their final -- tables. -- -- Prerequisites: -- directory ids in tmp_directory -- entries in tmp_directory_entry_{file,dir,rev} -- create or replace function swh_directory_add() returns void language plpgsql as $$ begin perform swh_directory_entry_add('file'); perform swh_directory_entry_add('dir'); perform swh_directory_entry_add('rev'); insert into directory (id, dir_entries, file_entries, rev_entries, raw_manifest) select id, dir_entries, file_entries, rev_entries, raw_manifest from tmp_directory t where not exists ( select 1 from directory d where d.id = t.id); return; end $$; -- a directory listing entry with all the metadata -- -- can be used to list a directory, and retrieve all the data in one go. create type directory_entry as ( dir_id sha1_git, -- id of the parent directory type directory_entry_type, -- type of entry target sha1_git, -- id of target name unix_path, -- path name, relative to containing dir perms file_perms, -- unix-like permissions status content_status, -- visible or absent sha1 sha1, -- content if sha1 if type is not dir sha1_git sha1_git, -- content's sha1 git if type is not dir sha256 sha256, -- content's sha256 if type is not dir length bigint -- content length if type is not dir ); -- List a single level of directory walked_dir_id -- FIXME: order by name is not correct. For git, we need to order by -- lexicographic order but as if a trailing / is present in directory -- name create or replace function swh_directory_walk_one(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with dir as ( select id as dir_id, dir_entries, file_entries, rev_entries from directory where id = walked_dir_id), ls_d as (select dir_id, unnest(dir_entries) as entry_id from dir), ls_f as (select dir_id, unnest(file_entries) as entry_id from dir), ls_r as (select dir_id, unnest(rev_entries) as entry_id from dir) (select dir_id, 'dir'::directory_entry_type as type, e.target, e.name, e.perms, NULL::content_status, NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint from ls_d left join directory_entry_dir e on ls_d.entry_id = e.id) union (with known_contents as (select dir_id, 'file'::directory_entry_type as type, e.target, e.name, e.perms, c.status, c.sha1, c.sha1_git, c.sha256, c.length from ls_f left join directory_entry_file e on ls_f.entry_id = e.id inner join content c on e.target = c.sha1_git) select * from known_contents union (select dir_id, 'file'::directory_entry_type as type, e.target, e.name, e.perms, c.status, c.sha1, c.sha1_git, c.sha256, c.length from ls_f left join directory_entry_file e on ls_f.entry_id = e.id left join skipped_content c on e.target = c.sha1_git where not exists (select 1 from known_contents where known_contents.sha1_git=e.target))) union (select dir_id, 'rev'::directory_entry_type as type, e.target, e.name, e.perms, NULL::content_status, NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint from ls_r left join directory_entry_rev e on ls_r.entry_id = e.id) order by name; $$; -- List recursively the revision directory arborescence create or replace function swh_directory_walk(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with recursive entries as ( select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length from swh_directory_walk_one(walked_dir_id) union all select dir_id, type, target, (dirname || '/' || name)::unix_path as name, perms, status, sha1, sha1_git, sha256, length from (select (swh_directory_walk_one(dirs.target)).*, dirs.name as dirname from (select target, name from entries where type = 'dir') as dirs) as with_parent ) select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length from entries $$; -- Find a directory entry by its path create or replace function swh_find_directory_entry_by_path( walked_dir_id sha1_git, dir_or_content_path bytea[]) returns directory_entry language plpgsql as $$ declare end_index integer; paths bytea default ''; path bytea; res bytea[]; r record; begin end_index := array_upper(dir_or_content_path, 1); res[1] := walked_dir_id; for i in 1..end_index loop path := dir_or_content_path[i]; -- concatenate path for patching the name in the result record (if we found it) if i = 1 then paths = path; else paths := paths || '/' || path; -- concatenate paths end if; if i <> end_index then select * from swh_directory_walk_one(res[i] :: sha1_git) where name=path and type = 'dir' limit 1 into r; else select * from swh_directory_walk_one(res[i] :: sha1_git) where name=path limit 1 into r; end if; -- find the path if r is null then return null; else -- store the next dir to lookup the next local path from res[i+1] := r.target; end if; end loop; -- at this moment, r is the result. Patch its 'name' with the full path before returning it. r.name := paths; return r; end $$; -- Returns the entries in a directory, without joining with their target tables create or replace function swh_directory_get_entries(dir_id sha1_git) returns table ( dir_id directory_entry_type, target sha1_git, name unix_path, perms file_perms ) language sql stable as $$ with dir as ( select id as dir_id, dir_entries, file_entries, rev_entries from directory where id = dir_id), ls_d as (select dir_id, unnest(dir_entries) as entry_id from dir), ls_f as (select dir_id, unnest(file_entries) as entry_id from dir), ls_r as (select dir_id, unnest(rev_entries) as entry_id from dir) (select 'dir'::directory_entry_type, e.target, e.name, e.perms from ls_d left join directory_entry_dir e on ls_d.entry_id = e.id) union (select 'file'::directory_entry_type, e.target, e.name, e.perms from ls_f left join directory_entry_file e on ls_f.entry_id = e.id) union (select 'rev'::directory_entry_type, e.target, e.name, e.perms from ls_r left join directory_entry_rev e on ls_r.entry_id = e.id) $$; -- List all revision IDs starting from a given revision, going back in time -- -- TODO ordering: should be breadth-first right now (what do we want?) -- TODO ordering: ORDER BY parent_rank somewhere? create or replace function swh_revision_list(root_revisions bytea[], num_revs bigint default NULL) returns table (id sha1_git, parents bytea[]) language sql stable as $$ with recursive full_rev_list(id) as ( (select id from revision where id = ANY(root_revisions)) union (select h.parent_id from revision_history as h join full_rev_list on h.id = full_rev_list.id) ), rev_list as (select id from full_rev_list limit num_revs) select rev_list.id as id, array(select rh.parent_id::bytea from revision_history rh where rh.id = rev_list.id order by rh.parent_rank ) as parent from rev_list; $$; -- Detailed entry for a revision create type revision_entry as ( id sha1_git, date timestamptz, date_offset smallint, date_neg_utc_offset boolean, date_offset_bytes bytea, committer_date timestamptz, committer_date_offset smallint, committer_date_neg_utc_offset boolean, committer_date_offset_bytes bytea, type revision_type, directory sha1_git, message bytea, author_id bigint, author_fullname bytea, author_name bytea, author_email bytea, committer_id bigint, committer_fullname bytea, committer_name bytea, committer_email bytea, metadata jsonb, synthetic boolean, parents bytea[], object_id bigint, extra_headers bytea[][], raw_manifest bytea ); create or replace function swh_revision_log(root_revisions bytea[], num_revs bigint default NULL, ignore_displayname boolean default false) returns setof revision_entry language sql stable as $$ -- when name and email are null, swh.storage.postgresql.converters.db_to_author() -- parses fullname to populate them, so we can just drop them here select t.id, r.date, r.date_offset, r.date_neg_utc_offset, r.date_offset_bytes, r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.committer_date_offset_bytes, r.type, r.directory, r.message, a.id, case when ignore_displayname or a.displayname is null then a.fullname else a.displayname end, case when ignore_displayname or a.displayname is null then a.name else null end, case when ignore_displayname or a.displayname is null then a.email else null end, c.id, case when ignore_displayname or c.displayname is null then c.fullname else c.displayname end, case when ignore_displayname or c.displayname is null then c.name else null end, case when ignore_displayname or c.displayname is null then c.email else null end, r.metadata, r.synthetic, t.parents, r.object_id, r.extra_headers, r.raw_manifest from swh_revision_list(root_revisions, num_revs) as t left join revision r on t.id = r.id left join person a on a.id = r.author left join person c on c.id = r.committer; $$; comment on function swh_revision_log(root_revisions bytea[], num_revs bigint, ignore_displayname boolean) is '"git style" revision log. Similar to swh_revision_list(), but returning ' 'all information associated to each revision, and expanding authors/committers'; -- Detailed entry for a release create type release_entry as ( id sha1_git, target sha1_git, target_type object_type, date timestamptz, date_offset smallint, date_neg_utc_offset boolean, name bytea, comment bytea, synthetic boolean, author_id bigint, author_fullname bytea, author_name bytea, author_email bytea, object_id bigint ); -- Create entries in person from tmp_revision create or replace function swh_person_add_from_revision() returns void language plpgsql as $$ begin with t as ( select author_fullname as fullname, author_name as name, author_email as email from tmp_revision union select committer_fullname as fullname, committer_name as name, committer_email as email from tmp_revision ) insert into person (fullname, name, email) select distinct on (fullname) fullname, name, email from t where t.fullname is not null and not exists ( select 1 from person p where t.fullname = p.fullname ); return; end $$; -- Create entries in revision from tmp_revision create or replace function swh_revision_add() returns void language plpgsql as $$ begin perform swh_person_add_from_revision(); insert into revision (id, date, date_offset, date_neg_utc_offset, date_offset_bytes, committer_date, committer_date_offset, committer_date_neg_utc_offset, committer_date_offset_bytes, type, directory, message, author, committer, metadata, synthetic, extra_headers, raw_manifest) select t.id, t.date, t.date_offset, t.date_neg_utc_offset, t.date_offset_bytes, t.committer_date, t.committer_date_offset, t.committer_date_neg_utc_offset, t.committer_date_offset_bytes, t.type, t.directory, t.message, a.id, c.id, t.metadata, t.synthetic, t.extra_headers, t.raw_manifest from tmp_revision t left join person a on a.fullname = t.author_fullname left join person c on c.fullname = t.committer_fullname; return; end $$; -- Create entries in extid from tmp_extid -- operates in bulk: 0. swh_mktemp(extid), 1. COPY to tmp_extid, -- 2. call this function create or replace function swh_extid_add() returns void language plpgsql as $$ begin insert into extid (extid_type, extid, extid_version, target_type, target) select distinct t.extid_type, t.extid, t.extid_version, t.target_type, t.target from tmp_extid t on conflict do nothing; return; end $$; -- Create entries in person from tmp_release create or replace function swh_person_add_from_release() returns void language plpgsql as $$ begin with t as ( select distinct author_fullname as fullname, author_name as name, author_email as email from tmp_release where author_fullname is not null ) insert into person (fullname, name, email) select distinct on (fullname) fullname, name, email from t where not exists ( select 1 from person p where t.fullname = p.fullname ); return; end $$; -- Create entries in release from tmp_release create or replace function swh_release_add() returns void language plpgsql as $$ begin perform swh_person_add_from_release(); insert into release (id, target, target_type, date, date_offset, date_neg_utc_offset, date_offset_bytes, name, comment, author, synthetic, raw_manifest) select distinct t.id, t.target, t.target_type, t.date, t.date_offset, t.date_neg_utc_offset, t.date_offset_bytes, t.name, t.comment, a.id, t.synthetic, t.raw_manifest from tmp_release t left join person a on a.fullname = t.author_fullname where not exists (select 1 from release where t.id = release.id); return; end $$; -- add a new origin_visit for origin origin_id at date. -- -- Returns the new visit id. create or replace function swh_origin_visit_add(origin_url text, date timestamptz, type text) returns bigint language sql as $$ with origin_id as ( select id from origin where url = origin_url ), last_known_visit as ( - select coalesce(max(visit), 0) as visit - from origin_visit - where origin = (select id from origin_id) + select coalesce( + ( + select visit + from origin_visit + where origin = (select id from origin_id) + order by visit desc + limit 1 + for update + ), + 0) as visit ) insert into origin_visit (origin, date, type, visit) values ((select id from origin_id), date, type, (select visit from last_known_visit) + 1) returning visit; $$; create or replace function swh_snapshot_add(snapshot_id sha1_git) returns void language plpgsql as $$ declare snapshot_object_id snapshot.object_id%type; begin select object_id from snapshot where id = snapshot_id into snapshot_object_id; if snapshot_object_id is null then insert into snapshot (id) values (snapshot_id) returning object_id into snapshot_object_id; insert into snapshot_branch (name, target_type, target) select name, target_type, target from tmp_snapshot_branch tmp where not exists ( select 1 from snapshot_branch sb where sb.name = tmp.name and sb.target = tmp.target and sb.target_type = tmp.target_type ) on conflict do nothing; insert into snapshot_branches (snapshot_id, branch_id) select snapshot_object_id, sb.object_id as branch_id from tmp_snapshot_branch tmp join snapshot_branch sb using (name, target, target_type) where tmp.target is not null and tmp.target_type is not null union select snapshot_object_id, sb.object_id as branch_id from tmp_snapshot_branch tmp join snapshot_branch sb using (name) where tmp.target is null and tmp.target_type is null and sb.target is null and sb.target_type is null; end if; truncate table tmp_snapshot_branch; end; $$; create type snapshot_result as ( snapshot_id sha1_git, name bytea, target bytea, target_type snapshot_target ); create or replace function swh_snapshot_get_by_id(id sha1_git, branches_from bytea default '', branches_count bigint default null, target_types snapshot_target[] default NULL, branch_name_include_substring bytea default NULL, branch_name_exclude_prefix bytea default NULL) returns setof snapshot_result language sql stable as $$ -- with small limits, the "naive" version of this query can degenerate into -- using the deduplication index on snapshot_branch (name, target, -- target_type); The planner happily scans several hundred million rows. -- Do the query in two steps: first pull the relevant branches for the given -- snapshot (filtering them by type), then do the limiting. This two-step -- process guides the planner into using the proper index. with filtered_snapshot_branches as ( select swh_snapshot_get_by_id.id as snapshot_id, name, target, target_type from snapshot_branches inner join snapshot_branch on snapshot_branches.branch_id = snapshot_branch.object_id where snapshot_id = (select object_id from snapshot where snapshot.id = swh_snapshot_get_by_id.id) and (target_types is null or target_type = any(target_types)) order by name ) select snapshot_id, name, target, target_type from filtered_snapshot_branches where name >= branches_from and (branch_name_include_substring is null or name like '%'||branch_name_include_substring||'%') and (branch_name_exclude_prefix is null or name not like branch_name_exclude_prefix||'%') order by name limit branches_count; $$; create type snapshot_size as ( target_type snapshot_target, count bigint ); create or replace function swh_snapshot_count_branches(id sha1_git, branch_name_exclude_prefix bytea default NULL) returns setof snapshot_size language sql stable as $$ SELECT target_type, count(name) from swh_snapshot_get_by_id(swh_snapshot_count_branches.id, branch_name_exclude_prefix => swh_snapshot_count_branches.branch_name_exclude_prefix) group by target_type; $$; -- Absolute path: directory reference + complete path relative to it create type content_dir as ( directory sha1_git, path unix_path ); -- Find the containing directory of a given content, specified by sha1 -- (note: *not* sha1_git). -- -- Return a pair (dir_it, path) where path is a UNIX path that, from the -- directory root, reach down to a file with the desired content. Return NULL -- if no match is found. -- -- In case of multiple paths (i.e., pretty much always), an arbitrary one is -- chosen. create or replace function swh_content_find_directory(content_id sha1) returns content_dir language sql stable as $$ with recursive path as ( -- Recursively build a path from the requested content to a root -- directory. Each iteration returns a pair (dir_id, filename) where -- filename is relative to dir_id. Stops when no parent directory can -- be found. (select dir.id as dir_id, dir_entry_f.name as name, 0 as depth from directory_entry_file as dir_entry_f join content on content.sha1_git = dir_entry_f.target join directory as dir on dir.file_entries @> array[dir_entry_f.id] where content.sha1 = content_id limit 1) union all (select dir.id as dir_id, (dir_entry_d.name || '/' || path.name)::unix_path as name, path.depth + 1 from path join directory_entry_dir as dir_entry_d on dir_entry_d.target = path.dir_id join directory as dir on dir.dir_entries @> array[dir_entry_d.id] limit 1) ) select dir_id, name from path order by depth desc limit 1; $$; -- Find the visit of origin closest to date visit_date -- Breaks ties by selecting the largest visit id create or replace function swh_visit_find_by_date(origin_url text, visit_date timestamptz default NOW()) returns setof origin_visit language plpgsql stable as $$ declare origin_id bigint; begin select id into origin_id from origin where url=origin_url; return query with closest_two_visits as (( - select ov, (date - visit_date), visit as interval + select ov, (date - visit_date) as interval, visit from origin_visit ov where ov.origin = origin_id and ov.date >= visit_date order by ov.date asc, ov.visit desc limit 1 ) union ( - select ov, (visit_date - date), visit as interval + select ov, (visit_date - date) as interval, visit from origin_visit ov where ov.origin = origin_id and ov.date < visit_date order by ov.date desc, ov.visit desc limit 1 )) select (ov).* from closest_two_visits order by interval, visit limit 1; end $$; -- Object listing by object_id create or replace function swh_content_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof content language sql stable as $$ select * from content where object_id > min_excl and object_id <= max_incl order by object_id; $$; create or replace function swh_revision_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof revision_entry language sql stable as $$ with revs as ( select * from revision where object_id > min_excl and object_id <= max_incl ) select r.id, r.date, r.date_offset, r.date_neg_utc_offset, r.date_offset_bytes, r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.committer_date_offset_bytes, r.type, r.directory, r.message, a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic, array(select rh.parent_id::bytea from revision_history rh where rh.id = r.id order by rh.parent_rank) as parents, r.object_id, r.extra_headers, r.raw_manifest from revs r left join person a on a.id = r.author left join person c on c.id = r.committer order by r.object_id; $$; create or replace function swh_release_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof release_entry language sql stable as $$ with rels as ( select * from release where object_id > min_excl and object_id <= max_incl ) select r.id, r.target, r.target_type, r.date, r.date_offset, r.date_neg_utc_offset, r.name, r.comment, r.synthetic, p.id as author_id, p.fullname as author_fullname, p.name as author_name, p.email as author_email, r.object_id from rels r left join person p on p.id = r.author order by r.object_id; $$; -- simple counter mapping a textual label to an integer value create type counter as ( label text, value bigint ); -- return statistics about the number of tuples in various SWH tables -- -- Note: the returned values are based on postgres internal statistics -- (pg_class table), which are only updated daily (by autovacuum) or so create or replace function swh_stat_counters() returns setof counter language sql stable as $$ select object_type as label, value as value from object_counts where object_type in ( 'content', 'directory', 'directory_entry_dir', 'directory_entry_file', 'directory_entry_rev', 'origin', 'origin_visit', 'person', 'release', 'revision', 'revision_history', 'skipped_content', 'snapshot' ); $$; create or replace function swh_update_counter(object_type text) returns void language plpgsql as $$ begin execute format(' insert into object_counts (value, last_update, object_type) values ((select count(*) from %1$I), NOW(), %1$L) on conflict (object_type) do update set value = excluded.value, last_update = excluded.last_update', object_type); return; end; $$; create or replace function swh_update_counter_bucketed() returns void language plpgsql as $$ declare query text; line_to_update int; new_value bigint; begin select object_counts_bucketed.line, format( 'select count(%I) from %I where %s', coalesce(identifier, '*'), object_type, coalesce( concat_ws( ' and ', case when bucket_start is not null then format('%I >= %L', identifier, bucket_start) -- lower bound condition, inclusive end, case when bucket_end is not null then format('%I < %L', identifier, bucket_end) -- upper bound condition, exclusive end ), 'true' ) ) from object_counts_bucketed order by coalesce(last_update, now() - '1 month'::interval) asc limit 1 into line_to_update, query; execute query into new_value; update object_counts_bucketed set value = new_value, last_update = now() where object_counts_bucketed.line = line_to_update; END $$; create or replace function swh_update_counters_from_buckets() returns trigger language plpgsql as $$ begin with to_update as ( select object_type, sum(value) as value, max(last_update) as last_update from object_counts_bucketed ob1 where not exists ( select 1 from object_counts_bucketed ob2 where ob1.object_type = ob2.object_type and value is null ) group by object_type ) update object_counts set value = to_update.value, last_update = to_update.last_update from to_update where object_counts.object_type = to_update.object_type and object_counts.value != to_update.value; return null; end $$; create trigger update_counts_from_bucketed after insert or update on object_counts_bucketed for each row when (NEW.line % 256 = 0) execute procedure swh_update_counters_from_buckets(); diff --git a/swh/storage/sql/60-indexes.sql b/swh/storage/sql/60-indexes.sql index 7ce81e85..c26c40d7 100644 --- a/swh/storage/sql/60-indexes.sql +++ b/swh/storage/sql/60-indexes.sql @@ -1,326 +1,323 @@ -- psql variables to get the current database flavor select swh_get_dbflavor() = 'read_replica' as dbflavor_read_replica \gset select swh_get_dbflavor() != 'read_replica' as dbflavor_does_deduplication \gset select swh_get_dbflavor() = 'mirror' as dbflavor_mirror \gset select swh_get_dbflavor() = 'default' as dbflavor_default \gset -- content create unique index concurrently content_pkey on content(sha1); alter table content add primary key using index content_pkey; \if :dbflavor_does_deduplication create unique index concurrently on content(sha1_git); \else create index concurrently on content(sha1_git); \endif create index concurrently on content(sha256); create index concurrently on content(blake2s256); \if :dbflavor_default create unique index concurrently on content(object_id); -- to be reviewed create index concurrently on content(ctime); -- to be reviewed \endif -- origin create unique index concurrently origin_pkey on origin(id); alter table origin add primary key using index origin_pkey; \if :dbflavor_does_deduplication create unique index concurrently on origin using btree(url); \else create index concurrently on origin using btree(url); \endif create index concurrently on origin using gin (url gin_trgm_ops); create index concurrently on origin using btree(digest(url, 'sha1')); -- skipped_content \if :dbflavor_does_deduplication alter table skipped_content add constraint skipped_content_sha1_sha1_git_sha256_key unique (sha1, sha1_git, sha256); \endif create index concurrently on skipped_content(sha1); create index concurrently on skipped_content(sha1_git); create index concurrently on skipped_content(sha256); create index concurrently on skipped_content(blake2s256); create unique index concurrently on skipped_content(object_id); \if :dbflavor_default alter table skipped_content add constraint skipped_content_origin_fkey foreign key (origin) references origin(id) not valid; alter table skipped_content validate constraint skipped_content_origin_fkey; \endif -- directory create unique index concurrently directory_pkey on directory(id); alter table directory add primary key using index directory_pkey; \if :dbflavor_default create index concurrently on directory using gin (dir_entries); -- to be reviewed create index concurrently on directory using gin (file_entries); -- to be reviewed create index concurrently on directory using gin (rev_entries); -- to be reviewed create unique index concurrently on directory(object_id); -- to be reviewed create index concurrently directory_raw_manifest_not_null on directory(id) where raw_manifest is not null; -- allows keeping track of the few directories that could not be parsed \endif -- directory_entry_dir create unique index concurrently directory_entry_dir_pkey on directory_entry_dir(id); alter table directory_entry_dir add primary key using index directory_entry_dir_pkey; \if :dbflavor_does_deduplication create unique index concurrently on directory_entry_dir(target, name, perms); \endif -- directory_entry_file create unique index concurrently directory_entry_file_pkey on directory_entry_file(id); alter table directory_entry_file add primary key using index directory_entry_file_pkey; \if :dbflavor_does_deduplication create unique index concurrently on directory_entry_file(target, name, perms); \endif -- directory_entry_rev create unique index concurrently directory_entry_rev_pkey on directory_entry_rev(id); alter table directory_entry_rev add primary key using index directory_entry_rev_pkey; \if :dbflavor_does_deduplication create unique index concurrently on directory_entry_rev(target, name, perms); \endif -- person create unique index concurrently person_pkey on person(id); alter table person add primary key using index person_pkey; \if :dbflavor_does_deduplication create unique index concurrently on person(fullname); \else create index concurrently on person(fullname); -- to be reviewed \endif \if :dbflavor_default create index concurrently on person(name); -- to be reviewed create index concurrently on person(email); -- to be reviewed \endif -- revision create unique index concurrently revision_pkey on revision(id); alter table revision add primary key using index revision_pkey; \if :dbflavor_does_deduplication alter table revision add constraint revision_author_fkey foreign key (author) references person(id) not valid; alter table revision validate constraint revision_author_fkey; alter table revision add constraint revision_committer_fkey foreign key (committer) references person(id) not valid; alter table revision validate constraint revision_committer_fkey; alter table revision add constraint revision_date_neg_utc_offset_not_null check (date is null or date_neg_utc_offset is not null) not valid; alter table revision add constraint revision_committer_date_neg_utc_offset_not_null check (committer_date is null or committer_date_neg_utc_offset is not null) not valid; alter table revision add constraint revision_date_offset_not_null check (date is null or date_offset_bytes is not null) not valid; alter table revision add constraint revision_committer_date_offset_not_null check (committer_date is null or committer_date_offset_bytes is not null) not valid; alter table revision validate constraint revision_date_neg_utc_offset_not_null; alter table revision validate constraint revision_committer_date_neg_utc_offset_not_null; alter table revision validate constraint revision_date_offset_not_null; alter table revision validate constraint revision_committer_date_offset_not_null; -- if the author is null, then the date must be null alter table revision add constraint revision_author_date_check check ((date is null) or (author is not null)) not valid; alter table revision validate constraint revision_author_date_check; -- if the committer is null, then the committer_date must be null alter table revision add constraint revision_committer_date_check check ((committer_date is null) or (committer is not null)) not valid; alter table revision validate constraint revision_committer_date_check; \endif \if :dbflavor_default create index concurrently on revision(directory); -- to be reviewed create unique index concurrently on revision(object_id); -- to be reviewed create index concurrently revision_raw_manifest_not_null on revision(id) where raw_manifest is not null; -- allows keeping track of the few revisions that could not be parsed \endif -- revision_history create unique index concurrently revision_history_pkey on revision_history(id, parent_rank); alter table revision_history add primary key using index revision_history_pkey; \if :dbflavor_default create index concurrently on revision_history(parent_id); -- to be reviewed \endif \if :dbflavor_does_deduplication alter table revision_history add constraint revision_history_id_fkey foreign key (id) references revision(id) not valid; alter table revision_history validate constraint revision_history_id_fkey; \endif -- snapshot create unique index concurrently snapshot_pkey on snapshot(object_id); alter table snapshot add primary key using index snapshot_pkey; \if :dbflavor_does_deduplication create unique index concurrently on snapshot(id); \else create index concurrently on snapshot(id); \endif -- snapshot_branch create unique index concurrently snapshot_branch_pkey on snapshot_branch(object_id); alter table snapshot_branch add primary key using index snapshot_branch_pkey; \if :dbflavor_does_deduplication create unique index concurrently on snapshot_branch (target_type, target, name); alter table snapshot_branch add constraint snapshot_branch_target_check check ((target_type is null) = (target is null)) not valid; alter table snapshot_branch validate constraint snapshot_branch_target_check; alter table snapshot_branch add constraint snapshot_target_check check (target_type not in ('content', 'directory', 'revision', 'release', 'snapshot') or length(target) = 20) not valid; alter table snapshot_branch validate constraint snapshot_target_check; create unique index concurrently on snapshot_branch (name) where target_type is null and target is null; \endif -- snapshot_branches create unique index concurrently snapshot_branches_pkey on snapshot_branches(snapshot_id, branch_id); alter table snapshot_branches add primary key using index snapshot_branches_pkey; \if :dbflavor_does_deduplication alter table snapshot_branches add constraint snapshot_branches_snapshot_id_fkey foreign key (snapshot_id) references snapshot(object_id) not valid; alter table snapshot_branches validate constraint snapshot_branches_snapshot_id_fkey; alter table snapshot_branches add constraint snapshot_branches_branch_id_fkey foreign key (branch_id) references snapshot_branch(object_id) not valid; alter table snapshot_branches validate constraint snapshot_branches_branch_id_fkey; \endif -- origin_visit create unique index concurrently origin_visit_pkey on origin_visit(origin, visit); alter table origin_visit add primary key using index origin_visit_pkey; -\if :dbflavor_default - create index concurrently on origin_visit(date); -- to be reviewed - create index concurrently origin_visit_type_date on origin_visit(type, date); -- to be reviewed -\endif +create index concurrently origin_visit_origin_date_idx on origin_visit (origin, date); \if :dbflavor_does_deduplication alter table origin_visit add constraint origin_visit_origin_fkey foreign key (origin) references origin(id) not valid; alter table origin_visit validate constraint origin_visit_origin_fkey; \endif -- origin_visit_status create unique index concurrently origin_visit_status_pkey on origin_visit_status(origin, visit, date); alter table origin_visit_status add primary key using index origin_visit_status_pkey; \if :dbflavor_default alter table origin_visit_status add constraint origin_visit_status_origin_visit_fkey foreign key (origin, visit) references origin_visit(origin, visit) not valid; alter table origin_visit_status validate constraint origin_visit_status_origin_visit_fkey; \endif -- release create unique index concurrently release_pkey on release(id); alter table release add primary key using index release_pkey; \if :dbflavor_default create index concurrently on release(target, target_type); -- to be reviewed create unique index concurrently on release(object_id); -- to be reviewed create index concurrently release_raw_manifest_not_null on release(id) where raw_manifest is not null; -- allows keeping track of the few releases that could not be parsed \endif \if :dbflavor_does_deduplication alter table release add constraint release_author_fkey foreign key (author) references person(id) not valid; alter table release validate constraint release_author_fkey; alter table release add constraint release_date_neg_utc_offset_not_null check (date is null or date_neg_utc_offset is not null) not valid; alter table release add constraint release_date_offset_not_null check (date is null or date_offset_bytes is not null) not valid; alter table release validate constraint release_date_neg_utc_offset_not_null; alter table release validate constraint release_date_offset_not_null; -- if the author is null, then the date must be null alter table release add constraint release_author_date_check check ((date is null) or (author is not null)) not valid; alter table release validate constraint release_author_date_check; \endif -- metadata_fetcher create unique index metadata_fetcher_pkey on metadata_fetcher(id); alter table metadata_fetcher add primary key using index metadata_fetcher_pkey; \if :dbflavor_does_deduplication create unique index metadata_fetcher_name_version on metadata_fetcher(name, version); \else create index metadata_fetcher_name_version on metadata_fetcher(name, version); \endif -- metadata_authority create unique index concurrently metadata_authority_pkey on metadata_authority(id); alter table metadata_authority add primary key using index metadata_authority_pkey; \if :dbflavor_does_deduplication create unique index concurrently metadata_authority_type_url on metadata_authority(type, url); \else create index concurrently metadata_authority_type_url on metadata_authority(type, url); \endif -- raw_extrinsic_metadata create unique index concurrently raw_extrinsic_metadata_pkey on raw_extrinsic_metadata(id); alter table raw_extrinsic_metadata add primary key using index raw_extrinsic_metadata_pkey; create index concurrently raw_extrinsic_metadata_content_authority_date on raw_extrinsic_metadata(target, authority_id, discovery_date); \if :dbflavor_default alter table raw_extrinsic_metadata add constraint raw_extrinsic_metadata_authority_fkey foreign key (authority_id) references metadata_authority(id) not valid; alter table raw_extrinsic_metadata validate constraint raw_extrinsic_metadata_authority_fkey; alter table raw_extrinsic_metadata add constraint raw_extrinsic_metadata_fetcher_fkey foreign key (fetcher_id) references metadata_fetcher(id) not valid; alter table raw_extrinsic_metadata validate constraint raw_extrinsic_metadata_fetcher_fkey; \endif -- object_counts create unique index concurrently object_counts_pkey on object_counts(object_type); alter table object_counts add primary key using index object_counts_pkey; -- object_counts_bucketed create unique index concurrently object_counts_bucketed_pkey on object_counts_bucketed(line); alter table object_counts_bucketed add primary key using index object_counts_bucketed_pkey; -- extid -- used to query by (extid_type, extid) + to deduplicate the whole row create unique index concurrently on extid(extid_type, extid, extid_version, target_type, target); create index concurrently on extid(target_type, target); diff --git a/swh/storage/sql/upgrades/184.sql b/swh/storage/sql/upgrades/184.sql new file mode 100644 index 00000000..42150172 --- /dev/null +++ b/swh/storage/sql/upgrades/184.sql @@ -0,0 +1,33 @@ +-- SWH DB schema upgrade +-- from_version: 183 +-- to_version: 184 +-- description: origin_visit_add: Fix crash when adding multiple visits to the same origin simultaneously + +insert into dbversion(version, release, description) + values(184, now(), 'Work In Progress'); + +create or replace function swh_origin_visit_add(origin_url text, date timestamptz, type text) + returns bigint + language sql +as $$ + with origin_id as ( + select id + from origin + where url = origin_url + ), last_known_visit as ( + select coalesce( + ( + select visit + from origin_visit + where origin = (select id from origin_id) + order by visit desc + limit 1 + for update + ), + 0) as visit + ) + insert into origin_visit (origin, date, type, visit) + values ((select id from origin_id), date, type, + (select visit from last_known_visit) + 1) + returning visit; +$$; diff --git a/swh/storage/sql/upgrades/185.sql b/swh/storage/sql/upgrades/185.sql new file mode 100644 index 00000000..fdb7a804 --- /dev/null +++ b/swh/storage/sql/upgrades/185.sql @@ -0,0 +1,35 @@ +-- SWH DB schema upgrade +-- from_version: 184 +-- to_version: 185 +-- description: origin_visit_find_by_date: Fix invalid alias in query which could lead to wrong visit being returned + +insert into dbversion(version, release, description) + values(185, now(), 'Work In Progress'); + +create or replace function swh_visit_find_by_date(origin_url text, visit_date timestamptz default NOW()) + returns setof origin_visit + language plpgsql + stable +as $$ +declare + origin_id bigint; +begin + select id into origin_id from origin where url=origin_url; + return query + with closest_two_visits as (( + select ov, (date - visit_date) as interval, visit + from origin_visit ov + where ov.origin = origin_id + and ov.date >= visit_date + order by ov.date asc, ov.visit desc + limit 1 + ) union ( + select ov, (visit_date - date) as interval, visit + from origin_visit ov + where ov.origin = origin_id + and ov.date < visit_date + order by ov.date desc, ov.visit desc + limit 1 + )) select (ov).* from closest_two_visits order by interval, visit limit 1; +end +$$; \ No newline at end of file diff --git a/swh/storage/sql/upgrades/186.sql b/swh/storage/sql/upgrades/186.sql new file mode 100644 index 00000000..7348f99c --- /dev/null +++ b/swh/storage/sql/upgrades/186.sql @@ -0,0 +1,9 @@ +-- SWH DB schema upgrade +-- from_version: 185 +-- to_version: 186 +-- description: Clean up indexes on origin_visit and add proper index for origin_visit_find_by_date + +drop index if exists origin_visit_date_idx; +drop index if exists origin_visit_type_date; + +create index concurrently if not exists origin_visit_origin_date_idx on origin_visit(origin, date); diff --git a/swh/storage/tests/conftest.py b/swh/storage/tests/conftest.py index d8817936..1bb2e01b 100644 --- a/swh/storage/tests/conftest.py +++ b/swh/storage/tests/conftest.py @@ -1,76 +1,77 @@ # 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 multiprocessing.util from hypothesis import HealthCheck, settings import pytest try: + import pytest_cov import pytest_cov.embed except ImportError: pytest_cov = None from typing import Iterable from swh.model.model import BaseContent, Origin from swh.model.tests.generate_testdata import gen_contents, gen_origins from swh.storage.interface import StorageInterface # we use getattr here to keep mypy happy regardless hypothesis version function_scoped_fixture_check = ( [getattr(HealthCheck, "function_scoped_fixture")] if hasattr(HealthCheck, "function_scoped_fixture") else [] ) # define tests profile. Full documentation is at: # https://hypothesis.readthedocs.io/en/latest/settings.html#settings-profiles settings.register_profile("fast", max_examples=5, deadline=5000) settings.register_profile("slow", max_examples=20, deadline=5000) # Load the fast profile by default to overcome default hypothesis values # (max_examples=100, deadline=200) that are unsuitable for our tests. # This can still be overloaded via the --hypothesis-profile option. settings.load_profile("fast") -if pytest_cov is not None: +if pytest_cov is not None and int(pytest_cov.__version__.split(".")[0]) < 4: # pytest_cov + multiprocessing can cause a segmentation fault when starting # the child process ; so we're # removing pytest-coverage's hook that runs when a child process starts. # This means code run in child processes won't be counted in the coverage # report, but this is not an issue because the only code that runs only in # child processes is the RPC server. for (key, value) in multiprocessing.util._afterfork_registry.items(): if value is pytest_cov.embed.multiprocessing_start: del multiprocessing.util._afterfork_registry[key] break else: assert False, "missing pytest_cov.embed.multiprocessing_start?" @pytest.fixture def swh_storage_backend_config(swh_storage_backend_config): """storage should test with its journal writer collaborator on""" yield { **swh_storage_backend_config, "journal_writer": { "cls": "memory", }, } @pytest.fixture def swh_contents(swh_storage: StorageInterface) -> Iterable[BaseContent]: contents = [BaseContent.from_dict(c) for c in gen_contents(n=20)] swh_storage.content_add([c for c in contents if c.status != "absent"]) swh_storage.skipped_content_add([c for c in contents if c.status == "absent"]) return contents @pytest.fixture def swh_origins(swh_storage: StorageInterface) -> Iterable[Origin]: origins = [Origin.from_dict(o) for o in gen_origins(n=100)] swh_storage.origin_add(origins) return origins diff --git a/swh/storage/tests/storage_tests.py b/swh/storage/tests/storage_tests.py index dedd268a..b6bfa63d 100644 --- a/swh/storage/tests/storage_tests.py +++ b/swh/storage/tests/storage_tests.py @@ -1,5653 +1,5677 @@ # Copyright (C) 2015-2022 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import defaultdict import datetime from datetime import timedelta import inspect import itertools import math import random from typing import Any, ClassVar, Dict, Iterator, Optional from unittest.mock import MagicMock import attr from hypothesis import HealthCheck, given, settings, strategies import pytest from swh.core.api import RemoteException from swh.core.api.classes import stream_results from swh.model import from_disk, hypothesis_strategies from swh.model.hashutil import DEFAULT_ALGORITHMS, hash_to_bytes from swh.model.model import ( Content, Directory, DirectoryEntry, ExtID, Origin, OriginVisit, OriginVisitStatus, Person, RawExtrinsicMetadata, Revision, RevisionType, SkippedContent, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) from swh.model.swhids import CoreSWHID, ObjectType from swh.storage import get_storage from swh.storage.cassandra.storage import CassandraStorage from swh.storage.common import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.in_memory import InMemoryStorage from swh.storage.interface import ( ListOrder, OriginVisitWithStatuses, PagedResult, StorageInterface, ) from swh.storage.tests.conftest import function_scoped_fixture_check from swh.storage.utils import ( content_hex_hashes, now, remove_keys, round_to_milliseconds, ) def transform_entries( storage: StorageInterface, dir_: Directory, *, prefix: bytes = b"" ) -> Iterator[Dict[str, Any]]: """Iterate through a directory's entries, and yields the items 'directory_ls' is expected to return; including content metadata for file entries.""" for ent in dir_.entries: if ent.type == "dir": yield { "dir_id": dir_.id, "type": ent.type, "target": ent.target, "name": prefix + ent.name, "perms": ent.perms, "status": None, "sha1": None, "sha1_git": None, "sha256": None, "length": None, } elif ent.type == "file": contents = storage.content_find({"sha1_git": ent.target}) assert contents ent_dict = contents[0].to_dict() for key in ["ctime", "blake2s256"]: ent_dict.pop(key, None) ent_dict.update( { "dir_id": dir_.id, "type": ent.type, "target": ent.target, "name": prefix + ent.name, "perms": ent.perms, } ) yield ent_dict def assert_contents_ok( expected_contents, actual_contents, keys_to_check={"sha1", "data"} ): """Assert that a given list of contents matches on a given set of keys.""" for k in keys_to_check: expected_list = set([c.get(k) for c in expected_contents]) actual_list = set([c.get(k) for c in actual_contents]) assert actual_list == expected_list, k class LazyContent(Content): def with_data(self): return Content.from_dict({**self.to_dict(), "data": b"42\n"}) class TestStorage: """Main class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ maxDiff = None # type: ClassVar[Optional[int]] def test_types(self, swh_storage_backend_config): """Checks all methods of StorageInterface are implemented by this backend, and that they have the same signature.""" # Create an instance of the protocol (which cannot be instantiated # directly, so this creates a subclass, then instantiates it) interface = type("_", (StorageInterface,), {})() storage = get_storage(**swh_storage_backend_config) assert "content_add" in dir(interface) missing_methods = [] for meth_name in dir(interface): if meth_name.startswith("_"): continue interface_meth = getattr(interface, meth_name) try: concrete_meth = getattr(storage, meth_name) except AttributeError: if not getattr(interface_meth, "deprecated_endpoint", False): # The backend is missing a (non-deprecated) endpoint missing_methods.append(meth_name) continue expected_signature = inspect.signature(interface_meth) actual_signature = inspect.signature(concrete_meth) assert expected_signature == actual_signature, meth_name assert missing_methods == [] # If all the assertions above succeed, then this one should too. # But there's no harm in double-checking. # And we could replace the assertions above by this one, but unlike # the assertions above, it doesn't explain what is missing. assert isinstance(storage, StorageInterface) def test_check_config(self, swh_storage): assert swh_storage.check_config(check_write=True) assert swh_storage.check_config(check_write=False) def test_content_add(self, swh_storage, sample_data): cont = sample_data.content insertion_start_time = now() actual_result = swh_storage.content_add([cont]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } assert swh_storage.content_get_data(cont.sha1) == cont.data expected_cont = attr.evolve(cont, data=None) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time assert obj == expected_cont if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_lazy_content(self, swh_storage, sample_data): cont = sample_data.content lazy_content = LazyContent.from_dict(cont.to_dict()) insertion_start_time = now() actual_result = swh_storage.content_add([lazy_content]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } # the fact that we retrieve the content object from the storage with # the correct 'data' field ensures it has been 'called' assert swh_storage.content_get_data(cont.sha1) == cont.data expected_cont = attr.evolve(lazy_content, data=None, ctime=None) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time assert attr.evolve(obj, ctime=None).to_dict() == expected_cont.to_dict() if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_get_data_missing(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] swh_storage.content_add([cont]) # Query a single missing content actual_content_data = swh_storage.content_get_data(cont2.sha1) assert actual_content_data is None # Check content_get does not abort after finding a missing content actual_content_data = swh_storage.content_get_data(cont.sha1) assert actual_content_data == cont.data actual_content_data = swh_storage.content_get_data(cont2.sha1) assert actual_content_data is None def test_content_add_different_input(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { "content:add": 2, "content:add:bytes": cont.length + cont2.length, } def test_content_add_twice(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] actual_result = swh_storage.content_add([cont]) assert actual_result == { "content:add": 1, "content:add:bytes": cont.length, } assert len(swh_storage.journal_writer.journal.objects) == 1 actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { "content:add": 1, "content:add:bytes": cont2.length, } assert 2 <= len(swh_storage.journal_writer.journal.objects) <= 3 assert len(swh_storage.content_find(cont.to_dict())) == 1 assert len(swh_storage.content_find(cont2.to_dict())) == 1 def test_content_add_collision(self, swh_storage, sample_data): cont1 = sample_data.content # create (corrupted) content with same sha1{,_git} but != sha256 sha256_array = bytearray(cont1.sha256) sha256_array[0] += 1 cont1b = attr.evolve(cont1, sha256=bytes(sha256_array)) with pytest.raises(HashCollision) as cm: swh_storage.content_add([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git"] actual_id = exc.hash_id assert actual_id == getattr(cont1, actual_algo).hex() collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(cont1.hashes()), content_hex_hashes(cont1b.hashes()), ] assert exc.colliding_content_hashes() == [ cont1.hashes(), cont1b.hashes(), ] def test_content_add_duplicate(self, swh_storage, sample_data): cont = sample_data.content swh_storage.content_add([cont, cont]) assert swh_storage.content_get_data(cont.sha1) == cont.data def test_content_update(self, swh_storage, sample_data): cont1 = sample_data.content if hasattr(swh_storage, "journal_writer"): swh_storage.journal_writer.journal = None # TODO, not supported swh_storage.content_add([cont1]) # alter the sha1_git for example cont1b = attr.evolve( cont1, sha1_git=hash_to_bytes("3a60a5275d0333bf13468e8b3dcab90f4046e654") ) swh_storage.content_update([cont1b.to_dict()], keys=["sha1_git"]) actual_contents = swh_storage.content_get([cont1.sha1]) expected_content = attr.evolve(cont1b, data=None) assert actual_contents == [expected_content] def test_content_add_metadata(self, swh_storage, sample_data): cont = attr.evolve(sample_data.content, data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } expected_cont = cont assert swh_storage.content_get([cont.sha1]) == [expected_cont] contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: obj = attr.evolve(obj, ctime=None) assert obj == cont def test_content_add_metadata_different_input(self, swh_storage, sample_data): contents = sample_data.contents[:2] cont = attr.evolve(contents[0], data=None, ctime=now()) cont2 = attr.evolve(contents[1], data=None, ctime=now()) actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { "content:add": 2, } def test_content_add_metadata_collision(self, swh_storage, sample_data): cont1 = attr.evolve(sample_data.content, data=None, ctime=now()) # create (corrupted) content with same sha1{,_git} but != sha256 sha1_git_array = bytearray(cont1.sha256) sha1_git_array[0] += 1 cont1b = attr.evolve(cont1, sha256=bytes(sha1_git_array)) with pytest.raises(HashCollision) as cm: swh_storage.content_add_metadata([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == getattr(cont1, actual_algo).hex() collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(cont1.hashes()), content_hex_hashes(cont1b.hashes()), ] assert exc.colliding_content_hashes() == [ cont1.hashes(), cont1b.hashes(), ] def test_content_add_objstorage_first(self, swh_storage, sample_data): """Tests the objstorage is written to before the DB and journal""" cont = sample_data.content swh_storage.objstorage.content_add = MagicMock(side_effect=Exception("Oops")) # Try to add, but the objstorage crashes try: swh_storage.content_add([cont]) except Exception: pass # The DB must be written to after the objstorage, so the DB should be # unchanged if the objstorage crashed assert swh_storage.content_get_data(cont.sha1) is None # The journal too assert list(swh_storage.journal_writer.journal.objects) == [] def test_skipped_content_add(self, swh_storage, sample_data): contents = sample_data.skipped_contents[:2] cont = contents[0] cont2 = attr.evolve(contents[1], blake2s256=None) contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [cont.hashes(), cont2.hashes()] actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [] def test_skipped_content_add_missing_hashes(self, swh_storage, sample_data): cont, cont2 = [ attr.evolve(c, sha1_git=None) for c in sample_data.skipped_contents[:2] ] contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [] def test_skipped_content_missing_partial_hash(self, swh_storage, sample_data): cont = sample_data.skipped_content cont2 = attr.evolve(cont, sha1_git=None) contents_dict = [c.to_dict() for c in [cont, cont2]] missing = list(swh_storage.skipped_content_missing(contents_dict)) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont]) assert actual_result.pop("skipped_content:add") == 1 assert actual_result == {} missing = list(swh_storage.skipped_content_missing(contents_dict)) assert missing == [cont2.hashes()] @pytest.mark.property_based @settings( deadline=None, # this test is very slow suppress_health_check=function_scoped_fixture_check, ) @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing(self, swh_storage, sample_data, algos): algos |= {"sha1"} content, missing_content = [sample_data.content2, sample_data.skipped_content] swh_storage.content_add([content]) test_contents = [content.to_dict()] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_content.to_dict() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == set( missing_per_hash["sha1"] ) for hash in algos: assert set( swh_storage.content_missing(test_contents, key_hash=hash) ) == set(missing_per_hash[hash]) @pytest.mark.property_based @settings( suppress_health_check=function_scoped_fixture_check, ) @given( strategies.sets( elements=strategies.sampled_from(["sha256", "sha1_git", "blake2s256"]), min_size=0, ) ) def test_content_missing_unknown_algo(self, swh_storage, sample_data, algos): algos |= {"sha1"} content, missing_content = [sample_data.content2, sample_data.skipped_content] swh_storage.content_add([content]) test_contents = [content.to_dict()] missing_per_hash = defaultdict(list) for i in range(16): test_content = missing_content.to_dict() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_content["nonexisting_algo"] = b"\x00" test_contents.append(test_content) assert set(swh_storage.content_missing(test_contents)) == set( missing_per_hash["sha1"] ) for hash in algos: assert set( swh_storage.content_missing(test_contents, key_hash=hash) ) == set(missing_per_hash[hash]) def test_content_missing_per_sha1(self, swh_storage, sample_data): # given cont = sample_data.content cont2 = sample_data.content2 missing_cont = sample_data.skipped_content missing_cont2 = sample_data.skipped_content2 swh_storage.content_add([cont, cont2]) # when gen = swh_storage.content_missing_per_sha1( [cont.sha1, missing_cont.sha1, cont2.sha1, missing_cont2.sha1] ) # then assert list(gen) == [missing_cont.sha1, missing_cont2.sha1] def test_content_missing_per_sha1_git(self, swh_storage, sample_data): cont, cont2 = sample_data.contents[:2] missing_cont = sample_data.skipped_content missing_cont2 = sample_data.skipped_content2 swh_storage.content_add([cont, cont2]) contents = [ cont.sha1_git, cont2.sha1_git, missing_cont.sha1_git, missing_cont2.sha1_git, ] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont.sha1_git, missing_cont2.sha1_git] missing_contents = swh_storage.content_missing_per_sha1_git([]) assert list(missing_contents) == [] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] actual_contents = [] for i in range(16): actual_result = swh_storage.content_get_partition(i, 16) assert actual_result.next_page_token is None actual_contents.extend(actual_result.results) assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents assert content.ctime is None def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents""" expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] actual_result = swh_storage.content_get_partition(0, 1) assert actual_result.next_page_token is None actual_contents = actual_result.results assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents def test_content_get_partition_empty(self, swh_storage, swh_contents): """content_get_partition when at least one of the partitions is empty""" expected_contents = { cont.sha1 for cont in swh_contents if cont.status != "absent" } # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1) seen_sha1s = [] for i in range(nb_partitions): actual_result = swh_storage.content_get_partition( i, nb_partitions, limit=len(swh_contents) + 1 ) for content in actual_result.results: seen_sha1s.append(content.sha1) # Limit is higher than the max number of results assert actual_result.next_page_token is None assert set(seen_sha1s) == expected_contents def test_content_get_partition_limit_none(self, swh_storage): """content_get_partition call with wrong limit input should fail""" with pytest.raises(StorageArgumentException, match="limit should not be None"): swh_storage.content_get_partition(1, 16, limit=None) def test_content_get_partition_pagination_generate(self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] # retrieve contents actual_contents = [] for i in range(4): page_token = None while True: actual_result = swh_storage.content_get_partition( i, 4, limit=3, page_token=page_token ) actual_contents.extend(actual_result.results) page_token = actual_result.next_page_token if page_token is None: break assert len(actual_contents) == len(expected_contents) for content in actual_contents: assert content in expected_contents @pytest.mark.parametrize("algo", sorted(DEFAULT_ALGORITHMS)) def test_content_get(self, swh_storage, sample_data, algo): cont1, cont2 = sample_data.contents[:2] swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get( [getattr(cont1, algo), getattr(cont2, algo)], algo ) # we only retrieve the metadata so no data nor ctime within expected_contents = [attr.evolve(c, data=None) for c in [cont1, cont2]] assert actual_contents == expected_contents for content in actual_contents: assert content.ctime is None @pytest.mark.parametrize("algo", sorted(DEFAULT_ALGORITHMS)) def test_content_get_missing(self, swh_storage, sample_data, algo): cont1, cont2 = sample_data.contents[:2] assert cont1.sha1 != cont2.sha1 missing_cont = sample_data.skipped_content swh_storage.content_add([cont1, cont2]) actual_contents = swh_storage.content_get( [getattr(cont1, algo), getattr(cont2, algo), getattr(missing_cont, algo)], algo, ) expected_contents = [ attr.evolve(c, data=None) if c else None for c in [cont1, cont2, None] ] assert actual_contents == expected_contents def test_content_get_random(self, swh_storage, sample_data): cont, cont2, cont3 = sample_data.contents[:3] swh_storage.content_add([cont, cont2, cont3]) assert swh_storage.content_get_random() in { cont.sha1_git, cont2.sha1_git, cont3.sha1_git, } def test_directory_add(self, swh_storage, sample_data): content = sample_data.content directory = sample_data.directory assert directory.entries[0].target == content.sha1_git swh_storage.content_add([content]) init_missing = list(swh_storage.directory_missing([directory.id])) assert [directory.id] == init_missing actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 1} assert ("directory", directory) in list( swh_storage.journal_writer.journal.objects ) actual_data = list(swh_storage.directory_ls(directory.id)) expected_data = list(transform_entries(swh_storage, directory)) for data in actual_data: assert data in expected_data after_missing = list(swh_storage.directory_missing([directory.id])) assert after_missing == [] if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_with_raw_manifest(self, swh_storage, sample_data): content = sample_data.content directory = sample_data.directory directory = attr.evolve(directory, raw_manifest=b"foo") directory = attr.evolve(directory, id=directory.compute_hash()) assert directory.entries[0].target == content.sha1_git swh_storage.content_add([content]) init_missing = list(swh_storage.directory_missing([directory.id])) assert [directory.id] == init_missing assert swh_storage.directory_get_raw_manifest([directory.id]) == {} actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 1} assert ("directory", directory) in list( swh_storage.journal_writer.journal.objects ) actual_data = list(swh_storage.directory_ls(directory.id)) expected_data = list(transform_entries(swh_storage, directory)) for data in actual_data: assert data in expected_data after_missing = list(swh_storage.directory_missing([directory.id])) assert after_missing == [] assert swh_storage.directory_get_raw_manifest([directory.id]) == { directory.id: b"foo" } directory2 = attr.evolve(directory, raw_manifest=b"bar") directory2 = attr.evolve(directory2, id=directory2.compute_hash()) swh_storage.directory_add([directory2]) assert swh_storage.directory_get_raw_manifest( [directory.id, directory2.id] ) == {directory.id: b"foo", directory2.id: b"bar"} @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists( hypothesis_strategies.directories(), min_size=1, max_size=10, unique_by=lambda directory: directory.id, ) ) def test_directory_add_get_arbitrary(self, swh_storage, directories): swh_storage.directory_add(directories) for directory in directories: actual_directory = Directory( id=directory.id, entries=tuple( stream_results(swh_storage.directory_get_entries, directory.id) ), raw_manifest=swh_storage.directory_get_raw_manifest([directory.id])[ directory.id ], ) if directory.raw_manifest is None: assert directory == actual_directory else: assert directory.raw_manifest == actual_directory.raw_manifest # we can't compare the other fields, because they become non-intrinsic, # so they may clash between hypothesis runs def test_directory_add_twice(self, swh_storage, sample_data): directory = sample_data.directories[1] actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", directory) ] actual_result = swh_storage.directory_add([directory]) assert actual_result == {"directory:add": 0} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", directory) ] def test_directory_add_raw_manifest__different_entries( self, swh_storage, check_ls=True ): """Add two directories with the same raw_manifest (and therefore, same id) but different entries. """ dir1 = Directory( entries=( DirectoryEntry( name=b"name1", type="file", target=b"\x00" * 20, perms=0o100000 ), ), raw_manifest=b"abc", ) dir2 = Directory( entries=( DirectoryEntry( name=b"name2", type="file", target=b"\x00" * 20, perms=0o100000 ), ), raw_manifest=b"abc", ) assert dir1.id == dir2.id # because it is computed from the raw_manifest only assert swh_storage.directory_add([dir1])["directory:add"] == 1 assert swh_storage.directory_add([dir2])["directory:add"] in (0, 1) if check_ls: # This assertion is skipped when running from # test_directory_add_raw_manifest__different_entries__allow_overwrite assert [entry["name"] for entry in swh_storage.directory_ls(dir1.id)] == ( [b"name1"] ) # used in TestCassandraStorage by # test_directory_add_raw_manifest__different_entries__allow_overwrite return dir1.id def test_directory_ls_recursive(self, swh_storage, sample_data): # create consistent dataset regarding the directories we want to list content, content2 = sample_data.contents[:2] swh_storage.content_add([content, content2]) dir1, dir2, dir3 = sample_data.directories[:3] dir_ids = [d.id for d in [dir1, dir2, dir3]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir1, dir2, dir3]) assert actual_result == {"directory:add": 3} # List directory containing one file actual_data = list(swh_storage.directory_ls(dir1.id, recursive=True)) expected_data = list(transform_entries(swh_storage, dir1)) for data in actual_data: assert data in expected_data # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir2.id, recursive=True)) expected_data = list(transform_entries(swh_storage, dir2)) for data in actual_data: assert data in expected_data # List directory containing both a known and unknown subdirectory, entries # should be both those of the directory and of the known subdir (up to contents) actual_data = list(swh_storage.directory_ls(dir3.id, recursive=True)) expected_data = list( itertools.chain( transform_entries(swh_storage, dir3), transform_entries(swh_storage, dir2, prefix=b"subdir/"), ) ) for data in actual_data: assert data in expected_data def test_directory_ls_non_recursive(self, swh_storage, sample_data): # create consistent dataset regarding the directories we want to list content, content2 = sample_data.contents[:2] swh_storage.content_add([content, content2]) dir1, dir2, dir3, _, dir5 = sample_data.directories[:5] dir_ids = [d.id for d in [dir1, dir2, dir3, dir5]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir1, dir2, dir3, dir5]) assert actual_result == {"directory:add": 4} # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(dir1.id)) expected_data = list(transform_entries(swh_storage, dir1)) for data in actual_data: assert data in expected_data # List directory containing a single file actual_data = list(swh_storage.directory_ls(dir2.id)) expected_data = list(transform_entries(swh_storage, dir2)) for data in actual_data: assert data in expected_data # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(swh_storage.directory_ls(dir3.id)) expected_data = list(transform_entries(swh_storage, dir3)) for data in actual_data: assert data in expected_data def test_directory_ls_missing_content(self, swh_storage, sample_data): swh_storage.directory_add([sample_data.directory2]) assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [ { "dir_id": sample_data.directory2.id, "length": None, "name": b"oof", "perms": 33188, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "target": sample_data.directory2.entries[0].target, "type": "file", }, ] def test_directory_ls_skipped_content(self, swh_storage, sample_data): swh_storage.directory_add([sample_data.directory2]) cont = SkippedContent( sha1_git=sample_data.directory2.entries[0].target, sha1=b"c" * 20, sha256=None, blake2s256=None, length=42, status="absent", reason="You need a premium subscription to access this content", ) swh_storage.skipped_content_add([cont]) assert list(swh_storage.directory_ls(sample_data.directory2.id)) == [ { "dir_id": sample_data.directory2.id, "length": 42, "name": b"oof", "perms": 33188, "sha1": b"c" * 20, "sha1_git": sample_data.directory2.entries[0].target, "sha256": None, "status": "absent", "target": sample_data.directory2.entries[0].target, "type": "file", }, ] def test_directory_entry_get_by_path(self, swh_storage, sample_data): cont, content2 = sample_data.contents[:2] dir1, dir2, dir3, dir4, dir5 = sample_data.directories[:5] # given dir_ids = [d.id for d in [dir1, dir2, dir3, dir4, dir5]] init_missing = list(swh_storage.directory_missing(dir_ids)) assert init_missing == dir_ids actual_result = swh_storage.directory_add([dir3, dir4]) assert actual_result == {"directory:add": 2} expected_entries = [ { "dir_id": dir3.id, "name": b"foo", "type": "file", "target": cont.sha1_git, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.content, "length": None, }, { "dir_id": dir3.id, "name": b"subdir", "type": "dir", "target": dir2.id, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.directory, "length": None, }, { "dir_id": dir3.id, "name": b"hello", "type": "file", "target": content2.sha1_git, "sha1": None, "sha1_git": None, "sha256": None, "status": None, "perms": from_disk.DentryPerms.content, "length": None, }, ] # when (all must be found here) for entry, expected_entry in zip(dir3.entries, expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( dir3.id, [entry.name] ) assert actual_entry == expected_entry # same, but deeper for entry, expected_entry in zip(dir3.entries, expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( dir4.id, [b"subdir1", entry.name] ) expected_entry = expected_entry.copy() expected_entry["name"] = b"subdir1/" + expected_entry["name"] assert actual_entry == expected_entry # when (nothing should be found here since `dir` is not persisted.) for entry in dir2.entries: actual_entry = swh_storage.directory_entry_get_by_path( dir2.id, [entry.name] ) assert actual_entry is None def test_directory_get_entries_pagination(self, swh_storage, sample_data): dir_ = sample_data.directory3 entries = sorted(dir_.entries, key=lambda entry: entry.name) swh_storage.directory_add(sample_data.directories) # No pagination needed actual_data = swh_storage.directory_get_entries(dir_.id) assert sorted(actual_data.results) == sorted(entries) assert actual_data.next_page_token is None, actual_data # A little pagination actual_data = swh_storage.directory_get_entries(dir_.id, limit=2) assert len(actual_data.results) == 2, actual_data assert actual_data.next_page_token is not None, actual_data all_results = list(actual_data.results) actual_data = swh_storage.directory_get_entries( dir_.id, page_token=actual_data.next_page_token ) assert len(actual_data.results) == len(entries) - 2, actual_data assert actual_data.next_page_token is None, actual_data all_results.extend(actual_data.results) assert sorted(all_results) == sorted(entries) @pytest.mark.parametrize("limit", [1, 2, 3, 4, 5]) def test_directory_get_entries(self, swh_storage, sample_data, limit): dir_ = sample_data.directory3 swh_storage.directory_add(sample_data.directories) actual_data = list( stream_results( swh_storage.directory_get_entries, dir_.id, limit=limit, ) ) assert sorted(actual_data) == sorted(dir_.entries) def test_directory_get_random(self, swh_storage, sample_data): dir1, dir2, dir3 = sample_data.directories[:3] swh_storage.directory_add([dir1, dir2, dir3]) assert swh_storage.directory_get_random() in { dir1.id, dir2.id, dir3.id, } def test_revision_add(self, swh_storage, sample_data): revision = sample_data.revision init_missing = swh_storage.revision_missing([revision.id]) assert list(init_missing) == [revision.id] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([revision.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] # already there so nothing added actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 0} if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_twice(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] actual_result = swh_storage.revision_add([revision, revision2]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision), ("revision", revision2), ] def test_revision_add_fractional_timezone(self, swh_storage, sample_data): # When reading a date from this time period on systems configured with # timezone Europe/Paris, postgresql returns them with UTC+00:09:21 as timezone, # but psycopg2 < 2.9.0 had to truncate them. # https://www.psycopg.org/docs/usage.html#time-zones-handling # # There is a workaround in swh.storage.postgresql.storage.Storage.get_db, # to set the timezone to UTC so it works on all psycopg2 versions. # # Therefore, this test always succeeds in tox (because psycopg2 >= 2.9.0) # and on the CI (both because psycopg2 >= 2.9.0 and TZ=UTC); but which means # this test is only useful on machines with older psycopg2 versions and # TZ=Europe/Paris. But the workaround is also only needed on this kind of # configuration, so this is good enough. revision = attr.evolve( sample_data.revision, date=TimestampWithTimezone( timestamp=Timestamp(seconds=-1855958962, microseconds=0), offset_bytes=b"+0000", ), ) init_missing = swh_storage.revision_missing([revision.id]) assert list(init_missing) == [revision.id] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([revision.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] assert swh_storage.revision_get([revision.id])[0] == revision def test_revision_add_with_raw_manifest(self, swh_storage, sample_data): revision = sample_data.revision revision = attr.evolve(revision, raw_manifest=b"foo") revision = attr.evolve(revision, id=revision.compute_hash()) init_missing = swh_storage.revision_missing([revision.id]) assert list(init_missing) == [revision.id] actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([revision.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] assert swh_storage.revision_get([revision.id]) == [revision] @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists( hypothesis_strategies.revisions(), min_size=1, max_size=10, unique_by=lambda rev: rev.id, ) ) def test_revision_add_get_arbitrary(self, swh_storage, revisions): # remove non-intrinsic data, so releases inserted with different hypothesis # data can't clash with each other revisions = [ attr.evolve( revision, synthetic=False, metadata=None, author=None if revision.author is None else Person.from_fullname(revision.author.fullname), committer=None if revision.committer is None else Person.from_fullname(revision.committer.fullname), type=RevisionType.GIT, ) for revision in revisions ] swh_storage.revision_add(revisions) for revision in revisions: (rev,) = swh_storage.revision_get([revision.id]) if rev.raw_manifest is None: assert rev == revision else: assert rev.raw_manifest == revision.raw_manifest # we can't compare the other fields, because they become non-intrinsic, # so they may clash between hypothesis runs def test_revision_add_name_clash(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] revision1 = attr.evolve( revision, author=Person( fullname=b"John Doe ", name=b"John Doe", email=b"john.doe@example.com", ), ) revision2 = attr.evolve( revision2, author=Person( fullname=b"John Doe ", name=b"John Doe ", email=b"john.doe@example.com ", ), ) actual_result = swh_storage.revision_add([revision1, revision2]) assert actual_result == {"revision:add": 2} def test_revision_get_order(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] add_result = swh_storage.revision_add([revision, revision2]) assert add_result == {"revision:add": 2} # order 1 actual_revisions = swh_storage.revision_get([revision.id, revision2.id]) assert actual_revisions == [revision, revision2] # order 2 actual_revisions2 = swh_storage.revision_get([revision2.id, revision.id]) assert actual_revisions2 == [revision2, revision] def test_revision_log(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # rev4 -is-child-of-> rev3 -> rev1, (rev2 -> rev1) swh_storage.revision_add([revision1, revision2, revision3, revision4]) # when results = list(swh_storage.revision_log([revision4.id])) # for comparison purposes actual_results = [Revision.from_dict(r) for r in results] assert len(actual_results) == 4 # rev4 -child-> rev3 -> rev1, (rev2 -> rev1) assert actual_results == [revision4, revision3, revision1, revision2] def test_revision_log_with_limit(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # revision4 -is-child-of-> revision3 swh_storage.revision_add([revision3, revision4]) results = list(swh_storage.revision_log([revision4.id], limit=1)) actual_results = [Revision.from_dict(r) for r in results] assert len(actual_results) == 1 assert actual_results[0] == revision4 def test_revision_log_unknown_revision(self, swh_storage, sample_data): revision = sample_data.revision rev_log = list(swh_storage.revision_log([revision.id])) assert rev_log == [] def test_revision_shortlog(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # rev4 -is-child-of-> rev3 -> (rev1, rev2); rev2 -> rev1 swh_storage.revision_add([revision1, revision2, revision3, revision4]) results = list(swh_storage.revision_shortlog([revision4.id])) actual_results = [[id, tuple(parents)] for (id, parents) in results] assert len(actual_results) == 4 assert actual_results == [ [revision4.id, revision4.parents], [revision3.id, revision3.parents], [revision1.id, revision1.parents], [revision2.id, revision2.parents], ] def test_revision_shortlog_with_limit(self, swh_storage, sample_data): revision1, revision2, revision3, revision4 = sample_data.revisions[:4] # revision4 -is-child-of-> revision3 swh_storage.revision_add([revision1, revision2, revision3, revision4]) results = list(swh_storage.revision_shortlog([revision4.id], 1)) actual_results = [[id, tuple(parents)] for (id, parents) in results] assert len(actual_results) == 1 assert list(actual_results[0]) == [revision4.id, revision4.parents] def test_revision_get(self, swh_storage, sample_data): revision, revision2 = sample_data.revisions[:2] swh_storage.revision_add([revision]) actual_revisions = swh_storage.revision_get([revision.id, revision2.id]) assert len(actual_revisions) == 2 assert actual_revisions == [revision, None] def test_revision_get_no_parents(self, swh_storage, sample_data): revision = sample_data.revision swh_storage.revision_add([revision]) actual_revision = swh_storage.revision_get([revision.id])[0] assert revision.parents == () assert actual_revision.parents == () # no parents on this one def test_revision_get_random(self, swh_storage, sample_data): revision1, revision2, revision3 = sample_data.revisions[:3] swh_storage.revision_add([revision1, revision2, revision3]) assert swh_storage.revision_get_random() in { revision1.id, revision2.id, revision3.id, } def test_revision_missing_many(self, swh_storage, sample_data): """Large number of revision ids to check can cause ScyllaDB to reject queries.""" revision = sample_data.revision ids = [bytes([b1, b2]) * 10 for b1 in range(256) for b2 in range(10)] ids.append(revision.id) ids.sort() init_missing = swh_storage.revision_missing(ids) assert set(init_missing) == set(ids) actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing(ids) assert set(end_missing) == set(ids) - {revision.id} def test_revision_add_no_author_or_date(self, swh_storage, sample_data): full_revision = sample_data.revision revision = attr.evolve(full_revision, author=None, date=None) revision = attr.evolve(revision, id=revision.compute_hash()) actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([revision.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] assert swh_storage.revision_get([revision.id]) == [revision] def test_revision_add_no_committer_or_date(self, swh_storage, sample_data): full_revision = sample_data.revision revision = attr.evolve(full_revision, committer=None, committer_date=None) revision = attr.evolve(revision, id=revision.compute_hash()) actual_result = swh_storage.revision_add([revision]) assert actual_result == {"revision:add": 1} end_missing = swh_storage.revision_missing([revision.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", revision) ] assert swh_storage.revision_get([revision.id]) == [revision] def test_extid_add_git(self, swh_storage, sample_data): gitids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=gitid, extid_type="git", target=CoreSWHID( object_id=gitid, object_type=ObjectType.REVISION, ), ) for gitid in gitids ] assert swh_storage.extid_get_from_extid("git", gitids) == [] assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == [] summary = swh_storage.extid_add(extids) assert summary == {"extid:add": len(gitids)} assert swh_storage.extid_get_from_extid("git", gitids) == extids assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids assert swh_storage.extid_get_from_extid("hg", gitids) == [] assert swh_storage.extid_get_from_target(ObjectType.RELEASE, gitids) == [] # check ExtIDs have been added to the journal extids_in_journal = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "extid" ] assert extids == extids_in_journal def test_extid_add_hg(self, swh_storage, sample_data): def get_node(revision): node = None if revision.extra_headers: node = dict(revision.extra_headers).get(b"node") if node is None and revision.metadata: node = hash_to_bytes(revision.metadata.get("node")) return node swhids = [ revision.id for revision in sample_data.revisions if revision.type.value == "hg" ] extids = [ get_node(revision) for revision in sample_data.revisions if revision.type.value == "hg" ] assert swh_storage.extid_get_from_extid("hg", extids) == [] assert swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == [] extid_objs = [ ExtID( extid=hgid, extid_type="hg", extid_version=1, target=CoreSWHID( object_id=swhid, object_type=ObjectType.REVISION, ), ) for hgid, swhid in zip(extids, swhids) ] summary = swh_storage.extid_add(extid_objs) assert summary == {"extid:add": len(swhids)} assert swh_storage.extid_get_from_extid("hg", extids) == extid_objs assert ( swh_storage.extid_get_from_target(ObjectType.REVISION, swhids) == extid_objs ) assert swh_storage.extid_get_from_extid("git", extids) == [] assert swh_storage.extid_get_from_target(ObjectType.RELEASE, swhids) == [] # check ExtIDs have been added to the journal extids_in_journal = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "extid" ] assert extid_objs == extids_in_journal def test_extid_add_twice(self, swh_storage, sample_data): gitids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=gitid, extid_type="git", target=CoreSWHID( object_id=gitid, object_type=ObjectType.REVISION, ), ) for gitid in gitids ] summary = swh_storage.extid_add(extids) assert summary == {"extid:add": len(gitids)} # add them again, should be noop summary = swh_storage.extid_add(extids) # assert summary == {"extid:add": 0} assert swh_storage.extid_get_from_extid("git", gitids) == extids assert swh_storage.extid_get_from_target(ObjectType.REVISION, gitids) == extids def test_extid_add_extid_multicity(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=extid, extid_type="git", extid_version=2, target=CoreSWHID( object_id=extid, object_type=ObjectType.REVISION, ), ) for extid in ids ] swh_storage.extid_add(extids) # try to add "modified-extid" versions, should be added extids2 = [ ExtID( extid=extid, extid_type="hg", extid_version=2, target=CoreSWHID( object_id=extid, object_type=ObjectType.REVISION, ), ) for extid in ids ] swh_storage.extid_add(extids2) assert swh_storage.extid_get_from_extid("git", ids) == extids assert swh_storage.extid_get_from_extid("hg", ids) == extids2 assert set(swh_storage.extid_get_from_target(ObjectType.REVISION, ids)) == { *extids, *extids2, } def test_extid_add_target_multicity(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] extids = [ ExtID( extid=extid, extid_type="git", target=CoreSWHID( object_id=extid, object_type=ObjectType.REVISION, ), ) for extid in ids ] swh_storage.extid_add(extids) # try to add "modified" versions, should be added extids2 = [ ExtID( extid=extid, extid_type="git", target=CoreSWHID( object_id=extid, object_type=ObjectType.RELEASE, ), ) for extid in ids ] swh_storage.extid_add(extids2) assert set(swh_storage.extid_get_from_extid("git", ids)) == {*extids, *extids2} assert swh_storage.extid_get_from_target(ObjectType.REVISION, ids) == extids assert swh_storage.extid_get_from_target(ObjectType.RELEASE, ids) == extids2 def test_extid_version_behavior(self, swh_storage, sample_data): ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] # Insert extids with several different versions extids = [ ExtID( extid=extid, extid_type="git", extid_version=0, target=CoreSWHID( object_id=extid, object_type=ObjectType.REVISION, ), ) for extid in ids ] + [ ExtID( extid=extid, extid_type="git", extid_version=1, target=CoreSWHID( object_id=extid, object_type=ObjectType.REVISION, ), ) for extid in ids ] swh_storage.extid_add(extids) # Check that both versions get returned for git_id in ids: objs = swh_storage.extid_get_from_extid("git", [git_id]) assert len(objs) == 2 assert set(obj.extid_version for obj in objs) == {0, 1} for swhid in ids: objs = swh_storage.extid_get_from_target(ObjectType.REVISION, [swhid]) assert len(objs) == 2 assert set(obj.extid_version for obj in objs) == {0, 1} for version in [0, 1]: for git_id in ids: objs = swh_storage.extid_get_from_extid( "git", [git_id], version=version ) assert len(objs) == 1 assert objs[0].extid_version == version for swhid in ids: objs = swh_storage.extid_get_from_target( ObjectType.REVISION, [swhid], extid_version=version, extid_type="git", ) assert len(objs) == 1 assert objs[0].extid_version == version assert objs[0].extid_type == "git" def test_extid_version_behavior_failure(self, swh_storage, sample_data): """Calls with wrong input should raise""" ids = [ revision.id for revision in sample_data.revisions if revision.type.value == "git" ] # Other edge cases with pytest.raises( (ValueError, RemoteException), match="both extid_type and extid_version" ): swh_storage.extid_get_from_target( ObjectType.REVISION, [ids[0]], extid_version=0 ) with pytest.raises( (ValueError, RemoteException), match="both extid_type and extid_version" ): swh_storage.extid_get_from_target( ObjectType.REVISION, [ids[0]], extid_type="git" ) def test_release_add(self, swh_storage, sample_data): release, release2 = sample_data.releases[:2] init_missing = swh_storage.release_missing([release.id, release2.id]) assert list(init_missing) == [release.id, release2.id] actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 2} end_missing = swh_storage.release_missing([release.id, release2.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release), ("release", release2), ] # already present so nothing added actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 0} if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 def test_release_add_with_raw_manifest(self, swh_storage, sample_data): release = sample_data.releases[0] release = attr.evolve(release, raw_manifest=b"foo") release = attr.evolve(release, id=release.compute_hash()) init_missing = swh_storage.release_missing([release.id]) assert list(init_missing) == [release.id] actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} end_missing = swh_storage.release_missing([release.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release), ] assert swh_storage.release_get([release.id]) == [release] @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists( hypothesis_strategies.releases(), min_size=1, max_size=10, unique_by=lambda rel: rel.id, ) ) def test_release_add_get_arbitrary(self, swh_storage, releases): # remove non-intrinsic data, so releases inserted with different hypothesis # data can't clash with each other releases = [ attr.evolve( release, synthetic=False, metadata=None, author=Person.from_fullname(release.author.fullname) if release.author else None, ) for release in releases ] swh_storage.release_add(releases) for release in releases: (rev,) = swh_storage.release_get([release.id]) if rev.raw_manifest is None: assert rev == release else: assert rev.raw_manifest == release.raw_manifest # we can't compare the other fields, because they become non-intrinsic, # so they may clash between hypothesis runs def test_release_add_no_author_date(self, swh_storage, sample_data): full_release = sample_data.release release = attr.evolve(full_release, author=None, date=None) actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} end_missing = swh_storage.release_missing([release.id]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release) ] def test_release_add_twice(self, swh_storage, sample_data): release, release2 = sample_data.releases[:2] actual_result = swh_storage.release_add([release]) assert actual_result == {"release:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", release) ] actual_result = swh_storage.release_add([release, release2, release, release2]) assert actual_result == {"release:add": 1} assert set(swh_storage.journal_writer.journal.objects) == set( [ ("release", release), ("release", release2), ] ) def test_release_add_name_clash(self, swh_storage, sample_data): release, release2 = [ attr.evolve( c, author=Person( fullname=b"John Doe ", name=b"John Doe", email=b"john.doe@example.com", ), ) for c in sample_data.releases[:2] ] actual_result = swh_storage.release_add([release, release2]) assert actual_result == {"release:add": 2} def test_release_get(self, swh_storage, sample_data): release, release2, release3 = sample_data.releases[:3] # given swh_storage.release_add([release, release2]) # when actual_releases = swh_storage.release_get([release.id, release2.id]) # then assert actual_releases == [release, release2] unknown_releases = swh_storage.release_get([release3.id]) assert unknown_releases[0] is None def test_release_get_order(self, swh_storage, sample_data): release, release2 = sample_data.releases[:2] add_result = swh_storage.release_add([release, release2]) assert add_result == {"release:add": 2} # order 1 actual_releases = swh_storage.release_get([release.id, release2.id]) assert actual_releases == [release, release2] # order 2 actual_releases2 = swh_storage.release_get([release2.id, release.id]) assert actual_releases2 == [release2, release] def test_release_get_random(self, swh_storage, sample_data): release, release2, release3 = sample_data.releases[:3] swh_storage.release_add([release, release2, release3]) assert swh_storage.release_get_random() in { release.id, release2.id, release3.id, } def test_origin_add(self, swh_storage, sample_data): origins = list(sample_data.origins) origin_urls = [o.url for o in origins] assert swh_storage.origin_get(origin_urls) == [None] * len(origins) stats = swh_storage.origin_add(origins) assert stats == {"origin:add": len(origin_urls)} actual_origins = swh_storage.origin_get(origin_urls) assert actual_origins == origins assert set(swh_storage.journal_writer.journal.objects) == set( [("origin", origin) for origin in origins] ) if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == len(origins) def test_origin_add_twice(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] add1 = swh_storage.origin_add([origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [ ("origin", origin), ("origin", origin2), ] ) assert add1 == {"origin:add": 2} add2 = swh_storage.origin_add([origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [ ("origin", origin), ("origin", origin2), ] ) assert add2 == {"origin:add": 0} def test_origin_add_twice_at_once(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] add1 = swh_storage.origin_add([origin, origin2, origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [ ("origin", origin), ("origin", origin2), ] ) assert add1 == {"origin:add": 2} add2 = swh_storage.origin_add([origin, origin2, origin, origin2]) assert set(swh_storage.journal_writer.journal.objects) == set( [ ("origin", origin), ("origin", origin2), ] ) assert add2 == {"origin:add": 0} def test_origin_get(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] assert swh_storage.origin_get([origin.url]) == [None] swh_storage.origin_add([origin]) actual_origins = swh_storage.origin_get([origin.url]) assert actual_origins == [origin] actual_origins = swh_storage.origin_get([origin.url, "not://exists"]) assert actual_origins == [origin, None] def _generate_random_visits(self, nb_visits=100, start=0, end=7): """Generate random visits within the last 2 months (to avoid computations) """ visits = [] today = now() for weeks in range(nb_visits, 0, -1): hours = random.randint(0, 24) minutes = random.randint(0, 60) seconds = random.randint(0, 60) days = random.randint(0, 28) weeks = random.randint(start, end) date_visit = today - timedelta( weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days ) visits.append(date_visit) return visits def test_origin_visit_get__unknown_origin(self, swh_storage): actual_page = swh_storage.origin_visit_get("foo") assert actual_page.next_page_token is None assert actual_page.results == [] assert actual_page == PagedResult() def test_origin_visit_get__validation_failure(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) with pytest.raises( StorageArgumentException, match="page_token must be a string" ): swh_storage.origin_visit_get(origin.url, page_token=10) # not bytes with pytest.raises( StorageArgumentException, match="order must be a ListOrder value" ): swh_storage.origin_visit_get(origin.url, order="foobar") # wrong order def test_origin_visit_get_all(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) ov1, ov2, ov3 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) # order asc, no token, no limit actual_page = swh_storage.origin_visit_get(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [ov1, ov2, ov3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get(origin.url, limit=2) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov1, ov2] # order asc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ov3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get(origin.url, limit=1) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov1] # order asc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov3] # order asc, token, limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=2 ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov3] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov2] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [ov3] # order desc, no token, no limit actual_page = swh_storage.origin_visit_get(origin.url, order=ListOrder.DESC) assert actual_page.next_page_token is None assert actual_page.results == [ov3, ov2, ov1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get( origin.url, limit=2, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov3, ov2] # order desc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get( origin.url, limit=1, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov3] # order desc, token, no limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov2, ov1] # order desc, token, limit actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ov2] actual_page = swh_storage.origin_visit_get( origin.url, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ov1] @pytest.mark.parametrize( "allowed_statuses,require_snapshot", [ ([], False), (["failed"], False), (["failed", "full"], False), ([], True), (["failed"], True), (["failed", "full"], True), ], ) def test_origin_visit_get_with_statuses( self, swh_storage, sample_data, allowed_statuses, require_snapshot ): origin = sample_data.origin swh_storage.origin_add([origin]) ov1, ov2, ov3 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=sample_data.date_visit1 + datetime.timedelta(hours=1), type=sample_data.type_visit1, status="failed", snapshot=None, ), OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=sample_data.date_visit2 + datetime.timedelta(hours=1), type=sample_data.type_visit2, status="failed", snapshot=None, ), OriginVisitStatus( origin=origin.url, visit=ov3.visit, date=sample_data.date_visit2 + datetime.timedelta(hours=1), type=sample_data.type_visit2, status="failed", snapshot=None, ), ] ) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=sample_data.date_visit1 + datetime.timedelta(hours=2), type=sample_data.type_visit1, status="full", snapshot=sample_data.snapshots[0].id, ), OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=sample_data.date_visit2 + datetime.timedelta(hours=2), type=sample_data.type_visit2, status="full", snapshot=sample_data.snapshots[1].id, ), OriginVisitStatus( origin=origin.url, visit=ov3.visit, date=sample_data.date_visit2 + datetime.timedelta(hours=2), type=sample_data.type_visit2, status="full", snapshot=sample_data.snapshots[2].id, ), ] ) ov1_statuses = swh_storage.origin_visit_status_get( origin.url, visit=ov1.visit ).results ov2_statuses = swh_storage.origin_visit_status_get( origin.url, visit=ov2.visit ).results ov3_statuses = swh_storage.origin_visit_status_get( origin.url, visit=ov3.visit ).results def _filter_statuses(ov_statuses): if allowed_statuses: ov_statuses = [ ovs for ovs in ov_statuses if ovs.status in allowed_statuses ] assert [ovs.status for ovs in ov_statuses] == allowed_statuses else: assert [ovs.status for ovs in ov_statuses] == [ "created", "failed", "full", ] if require_snapshot: ov_statuses = [ovs for ovs in ov_statuses if ovs.snapshot is not None] return ov_statuses ov1_statuses = _filter_statuses(ov1_statuses) ov2_statuses = _filter_statuses(ov2_statuses) ov3_statuses = _filter_statuses(ov3_statuses) ovws1 = OriginVisitWithStatuses(visit=ov1, statuses=ov1_statuses) ovws2 = OriginVisitWithStatuses(visit=ov2, statuses=ov2_statuses) ovws3 = OriginVisitWithStatuses(visit=ov3, statuses=ov3_statuses) # order asc, no token, no limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws1, ovws2, ovws3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, limit=2, ) next_page_token = actual_page.next_page_token assert len(actual_page.results) == 2 assert next_page_token is not None assert actual_page.results == [ovws1, ovws2] # order asc, token, no limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws3] # order asc, no token, limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, limit=1, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovws1] # order asc, token, no limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws2, ovws3] # order asc, token, limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, limit=2, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws2, ovws3] actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, limit=1, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovws2] actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, limit=1, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws3] # order desc, no token, no limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, order=ListOrder.DESC, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws3, ovws2, ovws1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, limit=2, order=ListOrder.DESC, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovws3, ovws2] # order desc, token, no limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, order=ListOrder.DESC, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws1] # order desc, no token, limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, limit=1, order=ListOrder.DESC, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovws3] # order desc, token, no limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, order=ListOrder.DESC, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws2, ovws1] # order desc, token, limit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, order=ListOrder.DESC, limit=1, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovws2] actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=next_page_token, order=ListOrder.DESC, ) assert actual_page.next_page_token is None assert actual_page.results == [ovws1] # should return empty results if page_token is last visit actual_page = swh_storage.origin_visit_get_with_statuses( origin.url, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, page_token=str(ov3.visit), ) assert actual_page.next_page_token is None assert actual_page.results == [] def test_origin_visit_status_get__unknown_cases(self, swh_storage, sample_data): origin = sample_data.origin actual_page = swh_storage.origin_visit_status_get("foobar", 1) assert actual_page.next_page_token is None assert actual_page.results == [] actual_page = swh_storage.origin_visit_status_get(origin.url, 1) assert actual_page.next_page_token is None assert actual_page.results == [] origin = sample_data.origin swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), ] )[0] actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit + 10) assert actual_page.next_page_token is None assert actual_page.results == [] def test_origin_visit_status_add_unknown_type(self, swh_storage, sample_data): ov = OriginVisit( origin=sample_data.origin.url, date=now(), type=sample_data.type_visit1, visit=0, ) ovs = OriginVisitStatus( origin=ov.origin, visit=1, date=now(), status="created", snapshot=None, ) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_status_add([ovs]) swh_storage.origin_add([sample_data.origin]) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_status_add([ovs]) swh_storage.origin_visit_add([ov]) swh_storage.origin_visit_status_add([ovs]) def test_origin_visit_status_get_all(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) date_visit3 = round_to_milliseconds(now()) date_visit1 = date_visit3 - datetime.timedelta(hours=2) date_visit2 = date_visit3 - datetime.timedelta(hours=1) assert date_visit1 < date_visit2 < date_visit3 ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=date_visit1, type=sample_data.type_visit1, ), ] )[0] ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit1, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit2, type=ov1.type, status="partial", snapshot=None, ) ovs3 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit3, type=ov1.type, status="full", snapshot=sample_data.snapshot.id, metadata={}, ) swh_storage.origin_visit_status_add([ovs2, ovs3]) # order asc, no token, no limit actual_page = swh_storage.origin_visit_status_get(origin.url, ov1.visit) assert actual_page.next_page_token is None assert actual_page.results == [ovs1, ovs2, ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1, ovs2] # order asc, token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs3] # order asc, token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, limit=2 ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs3] # order asc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs1, ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3] # order desc, no token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs3, ovs2, ovs1] # order desc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, limit=2, order=ListOrder.DESC ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs3, ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs1] # order desc, no token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, order=ListOrder.DESC, limit=1 ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs3] # order desc, token, no limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs2, ovs1] # order desc, token, limit actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC, limit=1, ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [ovs2] actual_page = swh_storage.origin_visit_status_get( origin.url, ov1.visit, page_token=next_page_token, order=ListOrder.DESC ) assert actual_page.next_page_token is None assert actual_page.results == [ovs1] def test_origin_visit_status_get_random(self, swh_storage, sample_data): origins = sample_data.origins[:2] swh_storage.origin_add(origins) # Add some random visits within the selection range visits = self._generate_random_visits() visit_type = "git" # Add visits to those origins for origin in origins: for date_visit in visits: visit = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=date_visit, type=visit_type, ) ] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=hash_to_bytes( "9b922e6d8d5b803c1582aabe5525b7b91150788e" ), ) ] ) if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(origins) assert stats["origin_visit"] == len(origins) * len(visits) random_ovs = swh_storage.origin_visit_status_get_random(visit_type) assert random_ovs assert random_ovs.origin is not None assert random_ovs.origin in [o.url for o in origins] assert random_ovs.type is not None def test_origin_visit_status_get_random_nothing_found( self, swh_storage, sample_data ): origins = sample_data.origins swh_storage.origin_add(origins) visit_type = "hg" # Add some visits older than 3 months so they are excluded from the random # selection visits = self._generate_random_visits(nb_visits=100, start=14, end=24) for origin in origins: for date_visit in visits: visit = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=date_visit, type=visit_type, ) ] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=None, ) ] ) random_origin_visit = swh_storage.origin_visit_status_get_random(visit_type) assert random_origin_visit is None def test_origin_snapshot_get_all(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) # add some random visits within the selection range visits = self._generate_random_visits() visit_type = "git" # set first visit to a null snapshot visit = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=visits[0], type=visit_type, ) ] )[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="created", snapshot=None, ) ] ) # add visits to origin snapshots = set() for date_visit in visits[1:]: visit = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=date_visit, type=visit_type, ) ] )[0] # pick a random snapshot and keep track of it snapshot = random.choice(sample_data.snapshots).id snapshots.add(snapshot) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=visit.visit, date=now(), status="full", snapshot=snapshot, ) ] ) # check expected snapshots are returned assert set(swh_storage.origin_snapshot_get_all(origin.url)) == snapshots def test_origin_get_by_sha1(self, swh_storage, sample_data): origin = sample_data.origin assert swh_storage.origin_get([origin.url])[0] is None swh_storage.origin_add([origin]) origins = list(swh_storage.origin_get_by_sha1([sha1(origin.url)])) assert len(origins) == 1 assert origins[0]["url"] == origin.url def test_origin_get_by_sha1_not_found(self, swh_storage, sample_data): unknown_origin = sample_data.origin assert swh_storage.origin_get([unknown_origin.url])[0] is None origins = list(swh_storage.origin_get_by_sha1([sha1(unknown_origin.url)])) assert len(origins) == 1 assert origins[0] is None def test_origin_search_single_result(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] actual_page = swh_storage.origin_search(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [] actual_page = swh_storage.origin_search(origin.url, regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [] swh_storage.origin_add([origin]) actual_page = swh_storage.origin_search(origin.url) assert actual_page.next_page_token is None assert actual_page.results == [origin] actual_page = swh_storage.origin_search(f".{origin.url[1:-1]}.", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin] swh_storage.origin_add([origin2]) actual_page = swh_storage.origin_search(origin2.url) assert actual_page.next_page_token is None assert actual_page.results == [origin2] actual_page = swh_storage.origin_search(f".{origin2.url[1:-1]}.", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_no_regexp(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search("/") assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search("/", page_token=None, limit=1) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( "/", page_token=next_page_token, limit=1 ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_regexp_substring(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search("/", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search( "/", page_token=None, limit=1, regexp=True ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( "/", page_token=next_page_token, limit=1, regexp=True ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_regexp_fullstring(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) # no pagination actual_page = swh_storage.origin_search(".*/.*", regexp=True) assert actual_page.next_page_token is None assert actual_page.results == [origin, origin2] # offset=0 actual_page = swh_storage.origin_search( ".*/.*", page_token=None, limit=1, regexp=True ) next_page_token = actual_page.next_page_token assert next_page_token is not None assert actual_page.results == [origin] # offset=1 actual_page = swh_storage.origin_search( ".*/.*", page_token=next_page_token, limit=1, regexp=True ) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_no_visit_types(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) actual_page = swh_storage.origin_search(origin.url, visit_types=["git"]) assert actual_page.next_page_token is None assert actual_page.results == [] def test_origin_search_with_visit_types(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] swh_storage.origin_add([origin, origin2]) swh_storage.origin_visit_add( [ OriginVisit(origin=origin.url, date=now(), type="git"), OriginVisit(origin=origin2.url, date=now(), type="svn"), ] ) actual_page = swh_storage.origin_search(origin.url, visit_types=["git"]) assert actual_page.next_page_token is None assert actual_page.results == [origin] actual_page = swh_storage.origin_search(origin2.url, visit_types=["svn"]) assert actual_page.next_page_token is None assert actual_page.results == [origin2] def test_origin_search_multiple_visit_types(self, swh_storage, sample_data): origin = sample_data.origins[0] swh_storage.origin_add([origin]) def _add_visit_type(visit_type): swh_storage.origin_visit_add( [OriginVisit(origin=origin.url, date=now(), type=visit_type)] ) def _check_visit_types(visit_types): actual_page = swh_storage.origin_search(origin.url, visit_types=visit_types) assert actual_page.next_page_token is None assert actual_page.results == [origin] _add_visit_type("git") _check_visit_types(["git"]) _check_visit_types(["git", "hg"]) _add_visit_type("hg") _check_visit_types(["hg"]) _check_visit_types(["git", "hg"]) def test_origin_visit_add(self, swh_storage, sample_data): origin1 = sample_data.origins[1] swh_storage.origin_add([origin1]) date_visit = now() date_visit2 = date_visit + datetime.timedelta(minutes=1) date_visit = round_to_milliseconds(date_visit) date_visit2 = round_to_milliseconds(date_visit2) visit1 = OriginVisit( origin=origin1.url, date=date_visit, type=sample_data.type_visit1, ) visit2 = OriginVisit( origin=origin1.url, date=date_visit2, type=sample_data.type_visit2, ) # add once ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2]) # then again (will be ignored as they already exist) origin_visit1, origin_visit2 = swh_storage.origin_visit_add([ov1, ov2]) assert ov1 == origin_visit1 assert ov2 == origin_visit2 assert ov1.visit == 1 assert ov2.visit == 2 ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_visit2, type=ov2.type, status="created", snapshot=None, ) actual_visits = swh_storage.origin_visit_get(origin1.url).results expected_visits = [ov1, ov2] assert len(expected_visits) == len(actual_visits) for visit in expected_visits: assert visit in actual_visits actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = list( [("origin", origin1)] + [("origin_visit", visit) for visit in expected_visits] * 2 + [("origin_visit_status", ovs) for ovs in [ovs1, ovs2]] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_add_replayed(self, swh_storage, sample_data): """Tests adding a visit with an id makes sure the next id is higher""" origin1 = sample_data.origins[1] swh_storage.origin_add([origin1]) date_visit = now() date_visit2 = date_visit + datetime.timedelta(minutes=1) date_visit = round_to_milliseconds(date_visit) date_visit2 = round_to_milliseconds(date_visit2) visit1 = OriginVisit( origin=origin1.url, date=date_visit, type=sample_data.type_visit1, visit=42 ) visit2 = OriginVisit( origin=origin1.url, date=date_visit2, type=sample_data.type_visit2, ) # add once ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2]) # then again (will be ignored as they already exist) origin_visit1, origin_visit2 = swh_storage.origin_visit_add([ov1, ov2]) assert ov1 == origin_visit1 assert ov2 == origin_visit2 assert ov1.visit == 42 assert ov2.visit == 43 # check OriginVisitStatus objects ovs1 = swh_storage.origin_visit_status_get(ov1.origin, visit=ov1.visit).results assert not ovs1, f"There should be no OriginVisitStatus for visit {ov1}" ovs2 = swh_storage.origin_visit_status_get(ov2.origin, visit=ov2.visit).results assert len(ovs2) == 1 assert ovs2[0].status == "created" assert ovs2[0].type == ov2.type visit3 = OriginVisit( origin=origin1.url, date=date_visit, type=sample_data.type_visit1, visit=12 ) visit4 = OriginVisit( origin=origin1.url, date=date_visit2, type=sample_data.type_visit2, ) # add once ov3, ov4 = swh_storage.origin_visit_add([visit3, visit4]) # then again (will be ignored as they already exist) origin_visit3, origin_visit4 = swh_storage.origin_visit_add([ov3, ov4]) assert ov3 == origin_visit3 assert ov4 == origin_visit4 assert ov3.visit == 12 assert ov4.visit == 44 def test_origin_visit_add_validation(self, swh_storage, sample_data): """Unknown origin when adding visits should raise""" visit = attr.evolve(sample_data.origin_visit, origin="something-unknonw") with pytest.raises(StorageArgumentException, match="Unknown origin"): swh_storage.origin_visit_add([visit]) objects = list(swh_storage.journal_writer.journal.objects) assert not objects def test_origin_visit_status_add_validation(self, swh_storage): """Wrong origin_visit_status input should raise storage argument error""" date_visit = now() visit_status1 = OriginVisitStatus( origin="unknown-origin-url", visit=10, date=date_visit, status="full", snapshot=None, ) with pytest.raises(StorageArgumentException, match="Unknown origin"): swh_storage.origin_visit_status_add([visit_status1]) objects = list(swh_storage.journal_writer.journal.objects) assert not objects def test_origin_visit_status_add(self, swh_storage, sample_data): """Correct origin visit statuses should add a new visit status""" snapshot = sample_data.snapshot origin1 = sample_data.origins[1] origin2 = Origin(url="new-origin") swh_storage.origin_add([origin1, origin2]) ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin2.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="created", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=sample_data.date_visit2, type=ov2.type, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, type=ov1.type, status="full", snapshot=snapshot.id, ) date_visit_now = round_to_milliseconds(now()) visit_status2 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_visit_now, type=ov2.type, status="ongoing", snapshot=None, metadata={"intrinsic": "something"}, ) stats = swh_storage.origin_visit_status_add([visit_status1, visit_status2]) assert stats == {"origin_visit_status:add": 2} visit = swh_storage.origin_visit_get_latest(origin1.url, require_snapshot=True) visit_status = swh_storage.origin_visit_status_get_latest( origin1.url, visit.visit, require_snapshot=True ) assert visit_status == visit_status1 visit = swh_storage.origin_visit_get_latest(origin2.url, require_snapshot=False) visit_status = swh_storage.origin_visit_status_get_latest( origin2.url, visit.visit, require_snapshot=False ) assert origin2.url != origin1.url assert visit_status == visit_status2 actual_objects = list(swh_storage.journal_writer.journal.objects) expected_origins = [origin1, origin2] expected_visits = [ov1, ov2] expected_visit_statuses = [ovs1, ovs2, visit_status1, visit_status2] expected_objects = ( [("origin", o) for o in expected_origins] + [("origin_visit", v) for v in expected_visits] + [("origin_visit_status", ovs) for ovs in expected_visit_statuses] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_status_add_twice(self, swh_storage, sample_data): """Correct origin visit statuses should add a new visit status""" snapshot = sample_data.snapshot origin1 = sample_data.origins[1] swh_storage.origin_add([origin1]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), ] )[0] ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="created", snapshot=None, ) date_visit_now = round_to_milliseconds(now()) visit_status1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_visit_now, type=ov1.type, status="full", snapshot=snapshot.id, ) stats = swh_storage.origin_visit_status_add([visit_status1]) assert stats == {"origin_visit_status:add": 1} # second call will ignore existing entries (will send to storage though) stats = swh_storage.origin_visit_status_add([visit_status1]) # ...so the storage still returns it as an addition assert stats == {"origin_visit_status:add": 1} visit_status = swh_storage.origin_visit_status_get_latest(ov1.origin, ov1.visit) assert visit_status == visit_status1 actual_objects = list(swh_storage.journal_writer.journal.objects) expected_origins = [origin1] expected_visits = [ov1] expected_visit_statuses = [ovs1, visit_status1, visit_status1] # write twice in the journal expected_objects = ( [("origin", o) for o in expected_origins] + [("origin_visit", v) for v in expected_visits] + [("origin_visit_status", ovs) for ovs in expected_visit_statuses] ) for obj in expected_objects: assert obj in actual_objects def test_origin_visit_find_by_date(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit1, ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit3, type=sample_data.type_visit2, ) visit3 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit3, ) ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) ovs1 = OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) ovs2 = OriginVisitStatus( origin=origin.url, visit=ov2.visit, date=sample_data.date_visit3, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=origin.url, visit=ov3.visit, date=sample_data.date_visit2, status="ongoing", snapshot=None, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3]) # Simple case actual_visit = swh_storage.origin_visit_find_by_date( origin.url, sample_data.date_visit3 ) assert actual_visit == ov2 # There are two visits at the same date, the latest must be returned actual_visit = swh_storage.origin_visit_find_by_date( origin.url, sample_data.date_visit2 ) assert actual_visit == ov3 + def test_origin_visit_find_by_date_latest_visit(self, swh_storage, sample_data): + first_visit_date = sample_data.date_visit2 + second_visit_date = first_visit_date + timedelta(days=10) + + origin = sample_data.origin + swh_storage.origin_add([origin]) + visit1 = OriginVisit( + origin=origin.url, + date=first_visit_date, + type=sample_data.type_visit2, + ) + visit2 = OriginVisit( + origin=origin.url, + date=second_visit_date, + type=sample_data.type_visit2, + ) + visit1, visit2 = swh_storage.origin_visit_add([visit1, visit2]) + + # should return the second visit + actual_visit = swh_storage.origin_visit_find_by_date( + origin.url, second_visit_date + ) + assert actual_visit == visit2 + def test_origin_visit_find_by_date__unknown_origin(self, swh_storage, sample_data): actual_visit = swh_storage.origin_visit_find_by_date( "foo", sample_data.date_visit2 ) assert actual_visit is None def test_origin_visit_get_by(self, swh_storage, sample_data): snapshot = sample_data.snapshot origins = sample_data.origins[:2] swh_storage.origin_add(origins) origin_url, origin_url2 = [o.url for o in origins] visit = OriginVisit( origin=origin_url, date=sample_data.date_visit2, type=sample_data.type_visit2, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) # Add some other {origin, visit} entries visit2 = OriginVisit( origin=origin_url, date=sample_data.date_visit3, type=sample_data.type_visit3, ) visit3 = OriginVisit( origin=origin_url2, date=sample_data.date_visit3, type=sample_data.type_visit3, ) swh_storage.origin_visit_add([visit2, visit3]) # when visit1_metadata = { "contents": 42, "directories": 22, } swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=origin_visit1.visit, date=now(), status="full", snapshot=snapshot.id, metadata=visit1_metadata, ) ] ) actual_visit = swh_storage.origin_visit_get_by(origin_url, origin_visit1.visit) assert actual_visit == origin_visit1 def test_origin_visit_get_by__no_result(self, swh_storage, sample_data): actual_visit = swh_storage.origin_visit_get_by("unknown", 10) # unknown origin assert actual_visit is None origin = sample_data.origin swh_storage.origin_add([origin]) actual_visit = swh_storage.origin_visit_get_by(origin.url, 999) # unknown visit assert actual_visit is None def test_origin_visit_get_latest_edge_cases(self, swh_storage, sample_data): # unknown origin so no result assert swh_storage.origin_visit_get_latest("unknown-origin") is None # unknown type so no result origin = sample_data.origin swh_storage.origin_add([origin]) assert swh_storage.origin_visit_get_latest(origin.url, type="unknown") is None # unknown allowed statuses should raise with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"): swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["unknown"] ) def test_origin_visit_get_latest_filter_type(self, swh_storage, sample_data): """Filtering origin visit get latest with filter type should be ok""" origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type="hg", ) date_now = round_to_milliseconds(now()) visit3 = OriginVisit( origin=origin.url, date=date_now, type="hg", ) assert sample_data.date_visit1 < sample_data.date_visit2 assert sample_data.date_visit2 < date_now ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) # Check type filter is ok actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="git") assert actual_visit == ov1 actual_visit = swh_storage.origin_visit_get_latest(origin.url, type="hg") assert actual_visit == ov3 actual_visit_unknown_type = swh_storage.origin_visit_get_latest( origin.url, type="npm", # no visit matching that type ) assert actual_visit_unknown_type is None def test_origin_visit_get_latest(self, swh_storage, sample_data): empty_snapshot, complete_snapshot = sample_data.snapshots[1:3] origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type="hg", ) date_now = round_to_milliseconds(now()) visit3 = OriginVisit( origin=origin.url, date=date_now, type="hg", ) assert visit1.date < visit2.date assert visit2.date < visit3.date ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) # no filters, latest visit is the last one (whose date is most recent) actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # 3 visits, none has snapshot so nothing is returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit is None # visit are created with "created" status, so nothing will get returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["partial"] ) assert actual_visit is None # visit are created with "created" status, so most recent again actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["created"] ) assert actual_visit == ov3 # Add snapshot to visit1; require_snapshot=True makes it return first visit swh_storage.snapshot_add([complete_snapshot]) visit_status_with_snapshot = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=round_to_milliseconds(now()), type=ov1.type, status="ongoing", snapshot=complete_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status_with_snapshot]) # only the first visit has a snapshot now actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit == ov1 # only the first visit has a status ongoing now actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["ongoing"] ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, require_snapshot=True ) assert actual_visit_status == visit_status_with_snapshot # ... and require_snapshot=False (defaults) still returns latest visit (3rd) actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=False ) assert actual_visit == ov3 # no specific filter, this returns as before the latest visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # Status filter: all three visits are status=ongoing, so no visit # returned actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit is None visit_status1_full = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=round_to_milliseconds(now()), type=ov1.type, status="full", snapshot=complete_snapshot.id, ) # Mark the first visit as completed and check status filter again swh_storage.origin_visit_status_add([visit_status1_full]) # only the first visit has the full status actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, allowed_statuses=["full"] ) assert actual_visit_status == visit_status1_full # no specific filter, this returns as before the latest visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([empty_snapshot]) visit_status2_full = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=round_to_milliseconds(now()), type=ov2.type, status="ongoing", snapshot=empty_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status2_full]) actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) # 2nd visit is most recent with a snapshot assert actual_visit == ov2 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov2.visit, require_snapshot=True ) assert actual_visit_status == visit_status2_full # no specific filter, this returns as before the latest visit, 3rd one actual_origin = swh_storage.origin_visit_get_latest(origin.url) assert actual_origin == ov3 # full status is still the first visit actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"] ) assert actual_visit == ov1 # Add snapshot to visit3 (same date as visit2) visit_status3_with_snapshot = OriginVisitStatus( origin=ov3.origin, visit=ov3.visit, date=round_to_milliseconds(now()), type=ov3.type, status="ongoing", snapshot=complete_snapshot.id, ) swh_storage.origin_visit_status_add([visit_status3_with_snapshot]) # full status is still the first visit actual_visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["full"], require_snapshot=True, ) assert actual_visit == ov1 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, visit=actual_visit.visit, allowed_statuses=["full"], require_snapshot=True, ) assert actual_visit_status == visit_status1_full # most recent is still the 3rd visit actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 # 3rd visit has a snapshot now, so it's elected actual_visit = swh_storage.origin_visit_get_latest( origin.url, require_snapshot=True ) assert actual_visit == ov3 actual_visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov3.visit, require_snapshot=True ) assert actual_visit_status == visit_status3_with_snapshot def test_origin_visit_get_latest__same_date(self, swh_storage, sample_data): empty_snapshot, complete_snapshot = sample_data.snapshots[1:3] origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) visit2 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="hg", ) ov1, ov2 = swh_storage.origin_visit_add([visit1, visit2]) # ties should be broken by using the visit id actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov2 def test_origin_visit_get_latest_order(self, swh_storage, sample_data): origin = sample_data.origin id1 = 2 id2 = 1 id3 = 3 date1 = datetime.datetime(2021, 8, 2, tzinfo=datetime.timezone.utc) date2 = datetime.datetime(2021, 8, 3, tzinfo=datetime.timezone.utc) date3 = datetime.datetime(2021, 8, 1, tzinfo=datetime.timezone.utc) swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, visit=id1, date=date1, type="git", ) visit2 = OriginVisit( origin=origin.url, visit=id2, date=date2, type="hg", ) visit3 = OriginVisit( origin=origin.url, visit=id3, date=date3, type="tar", ) ov1, ov2, ov3 = swh_storage.origin_visit_add([visit1, visit2, visit3]) ovs = [ OriginVisitStatus( origin=origin.url, visit=ov.visit, date=ov.date, type=ov.type, status="created", snapshot=None, ) for ov in [ov1, ov2, ov3] ] swh_storage.origin_visit_status_add(ovs) # no filters actual_visit = swh_storage.origin_visit_get_latest(origin.url) assert actual_visit == ov3 def test_origin_visit_get_latest__not_last(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) (date1, date2, date3, date4) = [ datetime.datetime(2021, 8, i, tzinfo=datetime.timezone.utc) for i in range(1, 5) ] visit1 = OriginVisit( origin=origin.url, visit=0, date=date1, type="git", ) swh_storage.origin_visit_add([visit1]) ov1 = swh_storage.origin_visit_get_latest(origin.url) # Add a snapshot, but do not attach it to visit1 for now complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date2, status="partial", snapshot=None, ) ] ) # no snapshot is associated to the visit, so None visit = swh_storage.origin_visit_get_latest( origin.url, allowed_statuses=["partial"], require_snapshot=True, ) assert visit is None # attach the visit to the snapshot swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=date3, status="full", snapshot=complete_snapshot.id, ) ] ) # and add a visit later on ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=date4, type=visit1.type, ) ] )[0] # so now the returned visit should be ov1 (because ov2 has no shapshot, # so it won't be returned when require_snapshot is True) visit = swh_storage.origin_visit_get_latest(origin.url, require_snapshot=True) assert visit == ov1 # but without require_snapshot, ov2 is returned visit = swh_storage.origin_visit_get_latest(origin.url, require_snapshot=False) assert visit == ov2 def test_origin_visit_status_get_latest__validation(self, swh_storage, sample_data): origin = sample_data.origin swh_storage.origin_add([origin]) visit1 = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type="git", ) # unknown allowed statuses should raise with pytest.raises(StorageArgumentException, match="Unknown allowed statuses"): swh_storage.origin_visit_status_get_latest( origin.url, visit1.visit, allowed_statuses=["unknown"] ) def test_origin_visit_status_get_latest(self, swh_storage, sample_data): snapshot = sample_data.snapshots[2] origin1 = sample_data.origin swh_storage.origin_add([origin1]) # to have some reference visits ov1, ov2 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin1.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ), OriginVisit( origin=origin1.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ), ] ) swh_storage.snapshot_add([snapshot]) date_now = round_to_milliseconds(now()) assert sample_data.date_visit1 < sample_data.date_visit2 assert sample_data.date_visit2 < date_now ovs1 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit1, type=ov1.type, status="partial", snapshot=None, ) ovs2 = OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=sample_data.date_visit2, type=ov1.type, status="ongoing", snapshot=None, ) ovs3 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=sample_data.date_visit2 + datetime.timedelta(minutes=1), # to not be ignored type=ov2.type, status="ongoing", snapshot=None, ) ovs4 = OriginVisitStatus( origin=ov2.origin, visit=ov2.visit, date=date_now, type=ov2.type, status="full", snapshot=snapshot.id, metadata={"something": "wicked"}, ) swh_storage.origin_visit_status_add([ovs1, ovs2, ovs3, ovs4]) # unknown origin so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( "unknown-origin", ov1.visit ) assert actual_origin_visit is None # unknown visit so no result actual_origin_visit = swh_storage.origin_visit_status_get_latest( ov1.origin, ov1.visit + 10 ) assert actual_origin_visit is None # Two visits, both with no snapshot, take the most recent actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit ) assert isinstance(actual_origin_visit2, OriginVisitStatus) assert actual_origin_visit2 == ovs2 assert ovs2.origin == origin1.url assert ovs2.visit == ov1.visit actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, require_snapshot=True ) # there is no visit with snapshot yet for that visit assert actual_origin_visit is None actual_origin_visit2 = swh_storage.origin_visit_status_get_latest( origin1.url, ov1.visit, allowed_statuses=["partial", "ongoing"] ) # visit status with partial status visit elected assert actual_origin_visit2 == ovs2 assert actual_origin_visit2.status == "ongoing" actual_origin_visit4 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True ) assert actual_origin_visit4 == ovs4 assert actual_origin_visit4.snapshot == snapshot.id actual_origin_visit = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, require_snapshot=True, allowed_statuses=["ongoing"] ) # nothing matches so nothing assert actual_origin_visit is None # there is no visit with status full actual_origin_visit3 = swh_storage.origin_visit_status_get_latest( origin1.url, ov2.visit, allowed_statuses=["ongoing"] ) assert actual_origin_visit3 == ovs3 def test_person_fullname_unicity(self, swh_storage, sample_data): revision, rev2 = sample_data.revisions[0:2] # create a revision with same committer fullname but wo name and email revision2 = attr.evolve( rev2, committer=Person( fullname=revision.committer.fullname, name=None, email=None ), ) swh_storage.revision_add([revision, revision2]) # when getting added revisions revisions = swh_storage.revision_get([revision.id, revision2.id]) # then check committers are the same assert revisions[0].committer == revisions[1].committer def test_snapshot_add_get_empty(self, swh_storage, sample_data): empty_snapshot = sample_data.snapshots[1] empty_snapshot_dict = empty_snapshot.to_dict() origin = sample_data.origin swh_storage.origin_add([origin]) ov1 = swh_storage.origin_visit_add( [ OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) ] )[0] actual_result = swh_storage.snapshot_add([empty_snapshot]) assert actual_result == {"snapshot:add": 1} date_now = now() swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=ov1.origin, visit=ov1.visit, date=date_now, type=ov1.type, status="full", snapshot=empty_snapshot.id, ) ] ) by_id = swh_storage.snapshot_get(empty_snapshot.id) assert by_id == {**empty_snapshot_dict, "next_branch": None} ovs1 = OriginVisitStatus.from_dict( { "origin": ov1.origin, "date": sample_data.date_visit1, "type": ov1.type, "visit": ov1.visit, "status": "created", "snapshot": None, "metadata": None, } ) ovs2 = OriginVisitStatus.from_dict( { "origin": ov1.origin, "date": date_now, "type": ov1.type, "visit": ov1.visit, "status": "full", "metadata": None, "snapshot": empty_snapshot.id, } ) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("origin", origin), ("origin_visit", ov1), ( "origin_visit_status", ovs1, ), ("snapshot", empty_snapshot), ( "origin_visit_status", ovs2, ), ] for obj in expected_objects: assert obj in actual_objects def test_snapshot_add_get_complete(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] complete_snapshot_dict = complete_snapshot.to_dict() origin = sample_data.origin swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] actual_result = swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) assert actual_result == {"snapshot:add": 1} by_id = swh_storage.snapshot_get(complete_snapshot.id) assert by_id == {**complete_snapshot_dict, "next_branch": None} @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists( hypothesis_strategies.snapshots(), min_size=1, max_size=10, unique_by=lambda snp: snp.id, ) ) def test_snapshot_add_get_arbitrary(self, swh_storage, snapshots): swh_storage.snapshot_add(snapshots) for snapshot in snapshots: assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } def test_snapshot_add_many(self, swh_storage, sample_data): snapshot, _, complete_snapshot = sample_data.snapshots[:3] actual_result = swh_storage.snapshot_add([snapshot, complete_snapshot]) assert actual_result == {"snapshot:add": 2} assert swh_storage.snapshot_get(complete_snapshot.id) == { **complete_snapshot.to_dict(), "next_branch": None, } assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } if isinstance(swh_storage, InMemoryStorage) or not isinstance( swh_storage, CassandraStorage ): swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_incremental(self, swh_storage, sample_data): snapshot, _, complete_snapshot = sample_data.snapshots[:3] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} actual_result2 = swh_storage.snapshot_add([snapshot, complete_snapshot]) assert actual_result2 == {"snapshot:add": 1} assert swh_storage.snapshot_get(complete_snapshot.id) == { **complete_snapshot.to_dict(), "next_branch": None, } assert swh_storage.snapshot_get(snapshot.id) == { **snapshot.to_dict(), "next_branch": None, } def test_snapshot_add_twice(self, swh_storage, sample_data): snapshot, empty_snapshot = sample_data.snapshots[:2] actual_result = swh_storage.snapshot_add([empty_snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", empty_snapshot) ] actual_result = swh_storage.snapshot_add([snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", empty_snapshot), ("snapshot", snapshot), ] def test_snapshot_add_count_branches(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} snp_size = swh_storage.snapshot_count_branches(complete_snapshot.id) expected_snp_size = { "alias": 1, "content": 1, "directory": 2, "release": 1, "revision": 1, "snapshot": 1, None: 1, } assert snp_size == expected_snp_size def test_snapshot_add_count_branches_with_filtering(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] actual_result = swh_storage.snapshot_add([complete_snapshot]) assert actual_result == {"snapshot:add": 1} snp_size = swh_storage.snapshot_count_branches( complete_snapshot.id, branch_name_exclude_prefix=b"release" ) expected_snp_size = { "alias": 1, "content": 1, "directory": 2, "revision": 1, "snapshot": 1, None: 1, } assert snp_size == expected_snp_size def test_snapshot_add_count_branches_with_filtering_edge_cases( self, swh_storage, sample_data ): snapshot = Snapshot( branches={ b"\xaa\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xaa\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff": SnapshotBranch( target=sample_data.release.id, target_type=TargetType.RELEASE, ), b"\xff\xff\x00": SnapshotBranch( target=sample_data.release.id, target_type=TargetType.RELEASE, ), b"dangling": None, }, ) swh_storage.snapshot_add([snapshot]) assert swh_storage.snapshot_count_branches( snapshot.id, branch_name_exclude_prefix=b"\xaa\xff" ) == {None: 1, "release": 2} assert swh_storage.snapshot_count_branches( snapshot.id, branch_name_exclude_prefix=b"\xff\xff" ) == {None: 1, "revision": 2} def test_snapshot_add_get_paginated(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.branches branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches(snp_id, branches_from=b"release") rel_idx = branch_names.index(b"release") expected_snapshot = { "id": snp_id, "branches": {name: branches[name] for name in branch_names[rel_idx:]}, "next_branch": None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches(snp_id, branches_count=1) expected_snapshot = { "id": snp_id, "branches": { branch_names[0]: branches[branch_names[0]], }, "next_branch": b"content", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, branches_from=b"directory", branches_count=3 ) dir_idx = branch_names.index(b"directory") expected_snapshot = { "id": snp_id, "branches": { name: branches[name] for name in branch_names[dir_idx : dir_idx + 3] }, "next_branch": branch_names[dir_idx + 3], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage, sample_data): origin = sample_data.origin complete_snapshot = sample_data.snapshots[2] swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([complete_snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=complete_snapshot.id, ) ] ) snp_id = complete_snapshot.id branches = complete_snapshot.branches snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["release", "revision"] ) expected_snapshot = { "id": snp_id, "branches": { name: tgt for name, tgt in branches.items() if tgt and tgt.target_type in [TargetType.RELEASE, TargetType.REVISION] }, "next_branch": None, } assert snapshot == expected_snapshot snapshot = swh_storage.snapshot_get_branches(snp_id, target_types=["alias"]) expected_snapshot = { "id": snp_id, "branches": { name: tgt for name, tgt in branches.items() if tgt and tgt.target_type == TargetType.ALIAS }, "next_branch": None, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] swh_storage.snapshot_add([complete_snapshot]) snp_id = complete_snapshot.id branches = complete_snapshot.branches branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2" ) expected_snapshot = { "id": snp_id, "branches": {name: branches[name] for name in (b"directory2", b"release")}, "next_branch": None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=1 ) expected_snapshot = { "id": snp_id, "branches": {b"directory": branches[b"directory"]}, "next_branch": b"directory2", } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_count=2 ) expected_snapshot = { "id": snp_id, "branches": { name: branches[name] for name in (b"directory", b"directory2") }, "next_branch": b"release", } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=["directory", "release"], branches_from=b"directory2", branches_count=1, ) dir_idx = branch_names.index(b"directory2") expected_snapshot = { "id": snp_id, "branches": { branch_names[dir_idx]: branches[branch_names[dir_idx]], }, "next_branch": b"release", } assert snapshot == expected_snapshot def test_snapshot_add_get_branch_by_type(self, swh_storage, sample_data): complete_snapshot = sample_data.snapshots[2] snapshot = complete_snapshot.to_dict() alias1 = b"alias1" alias2 = b"alias2" target1 = random.choice(list(snapshot["branches"].keys())) target2 = random.choice(list(snapshot["branches"].keys())) snapshot["branches"][alias2] = { "target": target2, "target_type": "alias", } snapshot["branches"][alias1] = { "target": target1, "target_type": "alias", } new_snapshot = Snapshot.from_dict(snapshot) swh_storage.snapshot_add([new_snapshot]) branches = swh_storage.snapshot_get_branches( new_snapshot.id, target_types=["alias"], branches_from=alias1, branches_count=1, )["branches"] assert len(branches) == 1 assert alias1 in branches def test_snapshot_add_get_by_branches_name_pattern(self, swh_storage, sample_data): snapshot = Snapshot( branches={ b"refs/heads/master": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/heads/incoming": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/pull/1": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"refs/pull/2": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"dangling": None, b"\xaa\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xaa\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), b"\xff\xff\x00": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot]) for include_pattern, exclude_prefix, nb_results in ( (b"pull", None, 2), (b"incoming", None, 1), (b"dangling", None, 1), (None, b"refs/heads/", 7), (b"refs", b"refs/heads/master", 3), (b"refs", b"refs/heads/master", 3), (None, b"\xaa\xff", 7), (None, b"\xff\xff", 7), ): branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=include_pattern, branch_name_exclude_prefix=exclude_prefix, )["branches"] expected_branches = [ branch_name for branch_name in snapshot.branches if (include_pattern is None or include_pattern in branch_name) and ( exclude_prefix is None or not branch_name.startswith(exclude_prefix) ) ] assert sorted(branches) == sorted(expected_branches) assert len(branches) == nb_results def test_snapshot_add_get_by_branches_name_pattern_filtered_paginated( self, swh_storage, sample_data ): pattern = b"foo" nb_branches_by_target_type = 10 branches = {} for i in range(nb_branches_by_target_type): branches[f"branch/directory/bar{i}".encode()] = SnapshotBranch( target=sample_data.directory.id, target_type=TargetType.DIRECTORY, ) branches[f"branch/revision/bar{i}".encode()] = SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ) branches[f"branch/directory/{pattern}{i}".encode()] = SnapshotBranch( target=sample_data.directory.id, target_type=TargetType.DIRECTORY, ) branches[f"branch/revision/{pattern}{i}".encode()] = SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ) snapshot = Snapshot(branches=branches) swh_storage.snapshot_add([snapshot]) branches_count = nb_branches_by_target_type // 2 for target_type in ( TargetType.DIRECTORY, TargetType.REVISION, ): target_type_str = target_type.value partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=pattern, target_types=[target_type_str], branches_count=branches_count, ) branches = partial_branches["branches"] expected_branches = [ branch_name for branch_name, branch_data in snapshot.branches.items() if pattern in branch_name and branch_data.target_type == target_type ][:branches_count] assert sorted(branches) == sorted(expected_branches) assert ( partial_branches["next_branch"] == f"branch/{target_type_str}/{pattern}{branches_count}".encode() ) partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branch_name_include_substring=pattern, target_types=[target_type_str], branches_from=partial_branches["next_branch"], ) branches = partial_branches["branches"] expected_branches = [ branch_name for branch_name, branch_data in snapshot.branches.items() if pattern in branch_name and branch_data.target_type == target_type ][branches_count:] assert sorted(branches) == sorted(expected_branches) assert partial_branches["next_branch"] is None def test_snapshot_get_branches_from_no_result(self, swh_storage, sample_data): snapshot = Snapshot( branches={ b"refs/heads/master": SnapshotBranch( target=sample_data.revision.id, target_type=TargetType.REVISION, ), }, ) swh_storage.snapshot_add([snapshot]) partial_branches = swh_storage.snapshot_get_branches( snapshot.id, branches_from=b"s", ) assert partial_branches is not None assert partial_branches["branches"] == {} @settings( suppress_health_check=function_scoped_fixture_check, ) @given(hypothesis_strategies.snapshots(min_size=1)) def test_snapshot_get_unknown_snapshot(self, swh_storage, unknown_snapshot): assert swh_storage.snapshot_get(unknown_snapshot.id) is None assert swh_storage.snapshot_get_branches(unknown_snapshot.id) is None def test_snapshot_add_get(self, swh_storage, sample_data): snapshot = sample_data.snapshot origin = sample_data.origin swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit1, type=sample_data.type_visit1, ) ov1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=ov1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) expected_snapshot = {**snapshot.to_dict(), "next_branch": None} by_id = swh_storage.snapshot_get(snapshot.id) assert by_id == expected_snapshot actual_visit = swh_storage.origin_visit_get_by(origin.url, ov1.visit) assert actual_visit == ov1 visit_status = swh_storage.origin_visit_status_get_latest( origin.url, ov1.visit, require_snapshot=True ) assert visit_status.snapshot == snapshot.id def test_snapshot_get_random(self, swh_storage, sample_data): snapshot, empty_snapshot, complete_snapshot = sample_data.snapshots[:3] swh_storage.snapshot_add([snapshot, empty_snapshot, complete_snapshot]) assert swh_storage.snapshot_get_random() in { snapshot.id, empty_snapshot.id, complete_snapshot.id, } def test_snapshot_missing(self, swh_storage, sample_data): snapshot, missing_snapshot = sample_data.snapshots[:2] snapshots = [snapshot.id, missing_snapshot.id] swh_storage.snapshot_add([snapshot]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snapshot.id] def test_stat_counters(self, swh_storage, sample_data): if isinstance(swh_storage, CassandraStorage) and not isinstance( swh_storage, InMemoryStorage ): pytest.skip("Cassandra backend does not support stat counters") origin = sample_data.origin snapshot = sample_data.snapshot revision = sample_data.revision release = sample_data.release directory = sample_data.directory content = sample_data.content expected_keys = ["content", "directory", "origin", "revision"] # Initially, all counters are 0 swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: assert counters[key] == 0 # Add a content. Only the content counter should increase. swh_storage.content_add([content]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: if key != "content": assert counters[key] == 0 assert counters["content"] == 1 # Add other objects. Check their counter increased as well. swh_storage.origin_add([origin]) visit = OriginVisit( origin=origin.url, date=sample_data.date_visit2, type=sample_data.type_visit2, ) origin_visit1 = swh_storage.origin_visit_add([visit])[0] swh_storage.snapshot_add([snapshot]) swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin.url, visit=origin_visit1.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) swh_storage.directory_add([directory]) swh_storage.revision_add([revision]) swh_storage.release_add([release]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert counters["content"] == 1 assert counters["directory"] == 1 assert counters["snapshot"] == 1 assert counters["origin"] == 1 assert counters["origin_visit"] == 1 assert counters["revision"] == 1 assert counters["release"] == 1 assert counters["snapshot"] == 1 if "person" in counters: assert counters["person"] == 3 def test_content_find_ctime(self, swh_storage, sample_data): origin_content = sample_data.content ctime = round_to_milliseconds(now()) content = attr.evolve(origin_content, data=None, ctime=ctime) swh_storage.content_add_metadata([content]) actually_present = swh_storage.content_find({"sha1": content.sha1}) assert actually_present[0] == content assert actually_present[0].ctime is not None assert actually_present[0].ctime.tzinfo is not None def test_content_find_with_present_content(self, swh_storage, sample_data): content = sample_data.content expected_content = attr.evolve(content, data=None) # 1. with something to find swh_storage.content_add([content]) actually_present = swh_storage.content_find({"sha1": content.sha1}) assert 1 == len(actually_present) assert actually_present[0] == expected_content # 2. with something to find actually_present = swh_storage.content_find({"sha1_git": content.sha1_git}) assert 1 == len(actually_present) assert actually_present[0] == expected_content # 3. with something to find actually_present = swh_storage.content_find({"sha256": content.sha256}) assert 1 == len(actually_present) assert actually_present[0] == expected_content # 4. with something to find actually_present = swh_storage.content_find(content.hashes()) assert 1 == len(actually_present) assert actually_present[0] == expected_content def test_content_find_with_non_present_content(self, swh_storage, sample_data): missing_content = sample_data.skipped_content # 1. with something that does not exist actually_present = swh_storage.content_find({"sha1": missing_content.sha1}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {"sha1_git": missing_content.sha1_git} ) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find({"sha256": missing_content.sha256}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage, sample_data): content = sample_data.content # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(content.sha1) sha1_array[0] += 1 sha1git_array = bytearray(content.sha1_git) sha1git_array[0] += 1 duplicated_content = attr.evolve( content, sha1=bytes(sha1_array), sha1_git=bytes(sha1git_array) ) # Inject the data swh_storage.content_add([content, duplicated_content]) actual_result = swh_storage.content_find( { "blake2s256": duplicated_content.blake2s256, "sha256": duplicated_content.sha256, } ) expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] def test_content_find_with_duplicate_sha256(self, swh_storage, sample_data): content = sample_data.content hashes = {} # Create fake data with colliding sha256 for hashalgo in ("sha1", "sha1_git", "blake2s256"): value = bytearray(getattr(content, hashalgo)) value[0] += 1 hashes[hashalgo] = bytes(value) duplicated_content = attr.evolve( content, sha1=hashes["sha1"], sha1_git=hashes["sha1_git"], blake2s256=hashes["blake2s256"], ) swh_storage.content_add([content, duplicated_content]) actual_result = swh_storage.content_find({"sha256": duplicated_content.sha256}) assert len(actual_result) == 2 expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] # Find with both sha256 and blake2s256 actual_result = swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) assert len(actual_result) == 1 assert actual_result == [expected_duplicated_content] def test_content_find_with_duplicate_blake2s256(self, swh_storage, sample_data): content = sample_data.content # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(content.sha1) sha1_array[0] += 1 sha1git_array = bytearray(content.sha1_git) sha1git_array[0] += 1 sha256_array = bytearray(content.sha256) sha256_array[0] += 1 duplicated_content = attr.evolve( content, sha1=bytes(sha1_array), sha1_git=bytes(sha1git_array), sha256=bytes(sha256_array), ) swh_storage.content_add([content, duplicated_content]) actual_result = swh_storage.content_find( {"blake2s256": duplicated_content.blake2s256} ) expected_content = attr.evolve(content, data=None) expected_duplicated_content = attr.evolve(duplicated_content, data=None) for result in actual_result: assert result in [expected_content, expected_duplicated_content] # Find with both sha256 and blake2s256 actual_result = swh_storage.content_find( { "sha256": duplicated_content.sha256, "blake2s256": duplicated_content.blake2s256, } ) assert actual_result == [expected_duplicated_content] def test_content_find_bad_input(self, swh_storage): # 1. with no hash to lookup with pytest.raises(StorageArgumentException): swh_storage.content_find({}) # need at least one hash # 2. with bad hash with pytest.raises(StorageArgumentException): swh_storage.content_find({"unknown-sha1": "something"}) # not the right key def test_object_find_by_sha1_git(self, swh_storage, sample_data): content = sample_data.content directory = sample_data.directory revision = sample_data.revision release = sample_data.release sha1_gits = [b"00000000000000000000"] expected = { b"00000000000000000000": [], } swh_storage.content_add([content]) sha1_gits.append(content.sha1_git) expected[content.sha1_git] = [ { "sha1_git": content.sha1_git, "type": "content", } ] swh_storage.directory_add([directory]) sha1_gits.append(directory.id) expected[directory.id] = [ { "sha1_git": directory.id, "type": "directory", } ] swh_storage.revision_add([revision]) sha1_gits.append(revision.id) expected[revision.id] = [ { "sha1_git": revision.id, "type": "revision", } ] swh_storage.release_add([release]) sha1_gits.append(release.id) expected[release.id] = [ { "sha1_git": release.id, "type": "release", } ] ret = swh_storage.object_find_by_sha1_git(sha1_gits) assert expected == ret def test_metadata_fetcher_add_get(self, swh_storage, sample_data): fetcher = sample_data.metadata_fetcher actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert actual_fetcher is None # does not exist swh_storage.metadata_fetcher_add([fetcher]) res = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert res == fetcher actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_fetcher", fetcher), ] for obj in expected_objects: assert obj in actual_objects def test_metadata_fetcher_add_zero(self, swh_storage, sample_data): fetcher = sample_data.metadata_fetcher actual_fetcher = swh_storage.metadata_fetcher_get(fetcher.name, fetcher.version) assert actual_fetcher is None # does not exist swh_storage.metadata_fetcher_add([]) def test_metadata_authority_add_get(self, swh_storage, sample_data): authority = sample_data.metadata_authority actual_authority = swh_storage.metadata_authority_get( authority.type, authority.url ) assert actual_authority is None # does not exist swh_storage.metadata_authority_add([authority]) res = swh_storage.metadata_authority_get(authority.type, authority.url) assert res == authority actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ] for obj in expected_objects: assert obj in actual_objects def test_metadata_authority_add_zero(self, swh_storage, sample_data): authority = sample_data.metadata_authority actual_authority = swh_storage.metadata_authority_get( authority.type, authority.url ) assert actual_authority is None # does not exist swh_storage.metadata_authority_add([]) def test_content_metadata_add(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add(content_metadata) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None assert list( sorted( result.results, key=lambda x: x.discovery_date, ) ) == list(content_metadata) actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ("metadata_fetcher", fetcher), ] + [("raw_extrinsic_metadata", item) for item in content_metadata] for obj in expected_objects: assert obj in actual_objects def test_content_metadata_add_duplicate(self, swh_storage, sample_data): """Duplicates should be silently ignored.""" content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_add([content_metadata2, content_metadata]) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None expected_results = (content_metadata, content_metadata2) assert ( tuple( sorted( result.results, key=lambda x: x.discovery_date, ) ) == expected_results ) def test_content_metadata_get(self, swh_storage, sample_data): content, content2 = sample_data.contents[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( content1_metadata1, content1_metadata2, content1_metadata3, ) = sample_data.content_metadata[:3] content2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "target": str(content2.swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority ) assert result.next_page_token is None assert [content1_metadata1, content1_metadata2] == list( sorted( result.results, key=lambda x: x.discovery_date, ) ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority2 ) assert result.next_page_token is None assert [content1_metadata3] == list( sorted( result.results, key=lambda x: x.discovery_date, ) ) result = swh_storage.raw_extrinsic_metadata_get( content2.swhid().to_extended(), authority ) assert result.next_page_token is None assert [content2_metadata] == list( result.results, ) def test_content_metadata_get_after(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, after=content_metadata.discovery_date - timedelta(seconds=1), ) assert result.next_page_token is None assert [content_metadata, content_metadata2] == list( sorted( result.results, key=lambda x: x.discovery_date, ) ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, after=content_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [content_metadata2] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, after=content_metadata2.discovery_date, ) assert result.next_page_token is None assert result.results == [] def test_content_metadata_get_paginate(self, swh_storage, sample_data): content = sample_data.content fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([content_metadata, content_metadata2]) swh_storage.raw_extrinsic_metadata_get(content.swhid().to_extended(), authority) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [content_metadata2] def test_content_metadata_get_paginate_same_date(self, swh_storage, sample_data): content = sample_data.content fetcher1, fetcher2 = sample_data.fetchers[:2] authority = sample_data.metadata_authority content_metadata, content_metadata2 = sample_data.content_metadata[:2] swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_content_metadata2 = RawExtrinsicMetadata.from_dict( { **remove_keys(content_metadata2.to_dict(), ("id",)), # recompute id "discovery_date": content_metadata2.discovery_date, "fetcher": attr.evolve(fetcher2, metadata=None).to_dict(), } ) swh_storage.raw_extrinsic_metadata_add( [content_metadata, new_content_metadata2] ) result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [content_metadata] result = swh_storage.raw_extrinsic_metadata_get( content.swhid().to_extended(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results[0].to_dict() == new_content_metadata2.to_dict() assert result.results == [new_content_metadata2] def test_content_metadata_get_by_ids(self, swh_storage, sample_data): content, content2 = sample_data.contents[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( content1_metadata1, content1_metadata2, content1_metadata3, ) = sample_data.content_metadata[:3] content2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "target": str(content2.swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) assert set( swh_storage.raw_extrinsic_metadata_get_by_ids( [content1_metadata1.id, b"\x00" * 20, content2_metadata.id] ) ) == {content1_metadata1, content2_metadata} def test_content_metadata_get_authorities(self, swh_storage, sample_data): content1, content2, content3 = sample_data.contents[:3] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( content1_metadata1, content1_metadata2, content1_metadata3, ) = sample_data.content_metadata[:3] content2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "target": str(content2.swhid()), } ) content1_metadata2 = RawExtrinsicMetadata.from_dict( { **remove_keys(content1_metadata2.to_dict(), ("id",)), # recompute id "authority": authority2.to_dict(), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [ content1_metadata1, content1_metadata2, content1_metadata3, content2_metadata, ] ) assert swh_storage.raw_extrinsic_metadata_get_authorities(content1.swhid()) in ( [authority, authority2], [authority2, authority], ) assert swh_storage.raw_extrinsic_metadata_get_authorities(content2.swhid()) == [ authority ] assert ( swh_storage.raw_extrinsic_metadata_get_authorities(content3.swhid()) == [] ) def test_origin_metadata_add(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date)) == [ origin_metadata, origin_metadata2, ] actual_objects = list(swh_storage.journal_writer.journal.objects) expected_objects = [ ("metadata_authority", authority), ("metadata_fetcher", fetcher), ("raw_extrinsic_metadata", origin_metadata), ("raw_extrinsic_metadata", origin_metadata2), ] for obj in expected_objects: assert obj in actual_objects def test_origin_metadata_add_duplicate(self, swh_storage, sample_data): """Duplicates should be silently updated.""" origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) swh_storage.raw_extrinsic_metadata_add([origin_metadata2, origin_metadata]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None # which of the two behavior happens is backend-specific. expected_results = (origin_metadata, origin_metadata2) assert ( tuple( sorted( result.results, key=lambda x: x.discovery_date, ) ) == expected_results ) def test_origin_metadata_get(self, swh_storage, sample_data): origin, origin2 = sample_data.origins[:2] fetcher, fetcher2 = sample_data.fetchers[:2] authority, authority2 = sample_data.authorities[:2] ( origin1_metadata1, origin1_metadata2, origin1_metadata3, ) = sample_data.origin_metadata[:3] assert swh_storage.origin_add([origin, origin2]) == {"origin:add": 2} origin2_metadata = RawExtrinsicMetadata.from_dict( { **remove_keys(origin1_metadata2.to_dict(), ("id",)), # recompute id "target": str(Origin(origin2.url).swhid()), } ) swh_storage.metadata_authority_add([authority, authority2]) swh_storage.metadata_fetcher_add([fetcher, fetcher2]) swh_storage.raw_extrinsic_metadata_add( [origin1_metadata1, origin1_metadata2, origin1_metadata3, origin2_metadata] ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority ) assert result.next_page_token is None assert [origin1_metadata1, origin1_metadata2] == list( sorted( result.results, key=lambda x: x.discovery_date, ) ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority2 ) assert result.next_page_token is None assert [origin1_metadata3] == list( sorted( result.results, key=lambda x: x.discovery_date, ) ) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin2.url).swhid(), authority ) assert result.next_page_token is None assert [origin2_metadata] == list( result.results, ) def test_origin_metadata_get_after(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, after=origin_metadata.discovery_date - timedelta(seconds=1), ) assert result.next_page_token is None assert list(sorted(result.results, key=lambda x: x.discovery_date,)) == [ origin_metadata, origin_metadata2, ] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, after=origin_metadata.discovery_date, ) assert result.next_page_token is None assert result.results == [origin_metadata2] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, after=origin_metadata2.discovery_date, ) assert result.next_page_token is None assert result.results == [] def test_origin_metadata_get_paginate(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) swh_storage.metadata_authority_add([authority]) swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) swh_storage.raw_extrinsic_metadata_get(Origin(origin.url).swhid(), authority) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [origin_metadata2] def test_origin_metadata_get_paginate_same_date(self, swh_storage, sample_data): origin = sample_data.origin fetcher1, fetcher2 = sample_data.fetchers[:2] authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher1, fetcher2]) swh_storage.metadata_authority_add([authority]) new_origin_metadata2 = RawExtrinsicMetadata.from_dict( { **remove_keys(origin_metadata2.to_dict(), ("id",)), # recompute id "discovery_date": origin_metadata2.discovery_date, "fetcher": attr.evolve(fetcher2, metadata=None).to_dict(), } ) swh_storage.raw_extrinsic_metadata_add([origin_metadata, new_origin_metadata2]) result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1 ) assert result.next_page_token is not None assert result.results == [origin_metadata] result = swh_storage.raw_extrinsic_metadata_get( Origin(origin.url).swhid(), authority, limit=1, page_token=result.next_page_token, ) assert result.next_page_token is None assert result.results == [new_origin_metadata2] def test_origin_metadata_add_missing_authority(self, swh_storage, sample_data): origin = sample_data.origin fetcher = sample_data.metadata_fetcher origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_fetcher_add([fetcher]) with pytest.raises(StorageArgumentException, match="authority"): swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) def test_origin_metadata_add_missing_fetcher(self, swh_storage, sample_data): origin = sample_data.origin authority = sample_data.metadata_authority origin_metadata, origin_metadata2 = sample_data.origin_metadata[:2] assert swh_storage.origin_add([origin]) == {"origin:add": 1} swh_storage.metadata_authority_add([authority]) with pytest.raises(StorageArgumentException, match="fetcher"): swh_storage.raw_extrinsic_metadata_add([origin_metadata, origin_metadata2]) class TestStorageGeneratedData: def test_generate_content_get_data(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c.status != "absent"] # retrieve contents for content in contents_with_data: actual_content_data = swh_storage.content_get_data(content.sha1) assert actual_content_data is not None assert actual_content_data == content.data def test_generate_content_get(self, swh_storage, swh_contents): expected_contents = [ attr.evolve(c, data=None) for c in swh_contents if c.status != "absent" ] actual_contents = swh_storage.content_get([c.sha1 for c in expected_contents]) assert len(actual_contents) == len(expected_contents) assert actual_contents == expected_contents @pytest.mark.parametrize("limit", [1, 7, 10, 100, 1000]) def test_origin_list(self, swh_storage, swh_origins, limit): returned_origins = [] page_token = None i = 0 while True: actual_page = swh_storage.origin_list(page_token=page_token, limit=limit) assert len(actual_page.results) <= limit returned_origins.extend(actual_page.results) i += 1 page_token = actual_page.next_page_token if page_token is None: assert i * limit >= len(swh_origins) break else: assert len(actual_page.results) == limit assert sorted(returned_origins) == sorted(swh_origins) def test_origin_count(self, swh_storage, sample_data): swh_storage.origin_add(sample_data.origins) assert swh_storage.origin_count("github") == 3 assert swh_storage.origin_count("gitlab") == 2 assert swh_storage.origin_count(".*user.*", regexp=True) == 5 assert swh_storage.origin_count(".*user.*", regexp=False) == 0 assert swh_storage.origin_count(".*user1.*", regexp=True) == 2 assert swh_storage.origin_count(".*user1.*", regexp=False) == 0 def test_origin_count_with_visit_no_visits(self, swh_storage, sample_data): swh_storage.origin_add(sample_data.origins) # none of them have visits, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=False, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=False, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_no_snapshot( self, swh_storage, sample_data ): swh_storage.origin_add(sample_data.origins) origin_url = "https://github.com/user1/repo1" visit = OriginVisit( origin=origin_url, date=now(), type="git", ) swh_storage.origin_visit_add([visit]) assert swh_storage.origin_count("github", with_visit=False) == 3 # it has a visit, but no snapshot, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=False) == 2 # these gitlab origins have no visit assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 0 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_and_snapshot( self, swh_storage, sample_data ): snapshot = sample_data.snapshot swh_storage.origin_add(sample_data.origins) swh_storage.snapshot_add([snapshot]) origin_url = "https://github.com/user1/repo1" visit = OriginVisit( origin=origin_url, date=now(), type="git", ) visit = swh_storage.origin_visit_add([visit])[0] swh_storage.origin_visit_status_add( [ OriginVisitStatus( origin=origin_url, visit=visit.visit, date=now(), status="ongoing", snapshot=snapshot.id, ) ] ) assert swh_storage.origin_count("github", with_visit=False) == 3 # github/user1 has a visit and a snapshot, so with_visit=True => 1 assert swh_storage.origin_count("github", with_visit=True) == 1 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 1 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 1 @settings( suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large] + function_scoped_fixture_check, ) @given( strategies.lists(hypothesis_strategies.objects(split_content=True), max_size=2) ) def test_add_arbitrary(self, swh_storage, objects): # Deduplicate based on ids if any objects = list( {obj.id: obj for obj in objects if hasattr(obj, "id")}.values() ) + [obj for obj in objects if not hasattr(obj, "id")] random.shuffle(objects) for (obj_type, obj) in objects: if obj.object_type == "origin_visit": swh_storage.origin_add([Origin(url=obj.origin)]) visit = OriginVisit( origin=obj.origin, date=obj.date, type=obj.type, ) swh_storage.origin_visit_add([visit]) elif obj.object_type == "raw_extrinsic_metadata": swh_storage.metadata_authority_add([obj.authority]) swh_storage.metadata_fetcher_add([obj.fetcher]) swh_storage.raw_extrinsic_metadata_add([obj]) else: method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass diff --git a/swh/storage/tests/test_retry.py b/swh/storage/tests/test_retry.py index dde53861..33800a1f 100644 --- a/swh/storage/tests/test_retry.py +++ b/swh/storage/tests/test_retry.py @@ -1,267 +1,270 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from unittest.mock import call import attr import psycopg2 import pytest from swh.core.api import TransientRemoteException from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.utils import now @pytest.fixture -def monkeypatch_sleep(monkeypatch, swh_storage): - """In test context, we don't want to wait, make test faster""" - from swh.storage.proxies.retry import RetryingProxyStorage - - for method_name, method in RetryingProxyStorage.__dict__.items(): +def storage_retry_sleep_mocks(mocker, swh_storage): + """In test context, we don't want to wait, make test faster by mocking + the sleep function from retryable storage methods""" + mocks = {} + for method_name in dir( + swh_storage + ): # swh_storage is an instance of RetryingProxyStorage if "_add" in method_name or "_update" in method_name: - monkeypatch.setattr(method.retry, "sleep", lambda x: None) + method = getattr(swh_storage, method_name) + mocks[method_name] = mocker.patch.object(method.retry, "sleep") - return monkeypatch + return mocks @pytest.fixture def fake_hash_collision(sample_data): return HashCollision("sha1", "38762cf7f55934b34d179ae6a4c80cadccbb7f0a", []) @pytest.fixture def swh_storage_backend_config(): yield { "cls": "pipeline", "steps": [ {"cls": "retry"}, {"cls": "memory"}, ], } def test_retrying_proxy_storage_content_add(swh_storage, sample_data): """Standard content_add works as before""" sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None s = swh_storage.content_add([sample_content]) assert s == { "content:add": 1, "content:add:bytes": sample_content.length, } content = swh_storage.content_get_data(sample_content.sha1) assert content == sample_content.data def test_retrying_proxy_storage_content_add_with_retry( - monkeypatch_sleep, + storage_retry_sleep_mocks, swh_storage, sample_data, mocker, fake_hash_collision, ): """Multiple retries for hash collision and psycopg2 error but finally ok""" mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("content already inserted"), # ok then! {"content:add": 1}, ] sample_content = sample_data.content - sleep = mocker.patch("time.sleep") + sleep = storage_retry_sleep_mocks["content_add"] content = swh_storage.content_get_data(sample_content.sha1) assert content is None s = swh_storage.content_add([sample_content]) assert s == {"content:add": 1} mock_memory.assert_has_calls( [ call([sample_content]), call([sample_content]), call([sample_content]), ] ) assert len(sleep.mock_calls) == 2 - (_name, args1, _kwargs) = sleep.mock_calls[0] - (_name, args2, _kwargs) = sleep.mock_calls[1] + (_, args1, _) = sleep.mock_calls[0] + (_, args2, _) = sleep.mock_calls[1] assert 0 < args1[0] < 1 assert 0 < args2[0] < 2 def test_retrying_proxy_storage_content_add_with_retry_of_transient( - monkeypatch_sleep, + storage_retry_sleep_mocks, swh_storage, sample_data, mocker, ): """Multiple retries for hash collision and psycopg2 error but finally ok after many attempts""" mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = [ TransientRemoteException("temporary failure"), TransientRemoteException("temporary failure"), # ok then! {"content:add": 1}, ] sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None - sleep = mocker.patch("time.sleep") + sleep = storage_retry_sleep_mocks["content_add"] s = swh_storage.content_add([sample_content]) assert s == {"content:add": 1} mock_memory.assert_has_calls( [ call([sample_content]), call([sample_content]), call([sample_content]), ] ) assert len(sleep.mock_calls) == 2 - (_name, args1, _kwargs) = sleep.mock_calls[0] - (_name, args2, _kwargs) = sleep.mock_calls[1] + (_, args1, _) = sleep.mock_calls[0] + (_, args2, _) = sleep.mock_calls[1] assert 10 < args1[0] < 11 assert 10 < args2[0] < 12 def test_retrying_proxy_swh_storage_content_add_failure( swh_storage, sample_data, mocker ): """Unfiltered errors are raising without retry""" mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = StorageArgumentException("Refuse to add content always!") sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.content_add([sample_content]) assert mock_memory.call_count == 1 def test_retrying_proxy_storage_content_add_metadata(swh_storage, sample_data): """Standard content_add_metadata works as before""" sample_content = sample_data.content content = attr.evolve(sample_content, data=None) pk = content.sha1 content_metadata = swh_storage.content_get([pk]) assert content_metadata == [None] s = swh_storage.content_add_metadata([attr.evolve(content, ctime=now())]) assert s == { "content:add": 1, } content_metadata = swh_storage.content_get([pk]) assert len(content_metadata) == 1 assert content_metadata[0].sha1 == pk def test_retrying_proxy_storage_content_add_metadata_with_retry( - monkeypatch_sleep, swh_storage, sample_data, mocker, fake_hash_collision + storage_retry_sleep_mocks, swh_storage, sample_data, mocker, fake_hash_collision ): """Multiple retries for hash collision and psycopg2 error but finally ok""" mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.content_add_metadata" ) mock_memory.side_effect = [ # first try goes ko fake_hash_collision, # second try goes ko psycopg2.IntegrityError("content_metadata already inserted"), # ok then! {"content:add": 1}, ] sample_content = sample_data.content content = attr.evolve(sample_content, data=None) s = swh_storage.content_add_metadata([content]) assert s == {"content:add": 1} mock_memory.assert_has_calls( [ call([content]), call([content]), call([content]), ] ) def test_retrying_proxy_swh_storage_content_add_metadata_failure( swh_storage, sample_data, mocker ): """Unfiltered errors are raising without retry""" mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.content_add_metadata" ) mock_memory.side_effect = StorageArgumentException( "Refuse to add content_metadata!" ) sample_content = sample_data.content content = attr.evolve(sample_content, data=None) with pytest.raises(StorageArgumentException, match="Refuse to add"): swh_storage.content_add_metadata([content]) assert mock_memory.call_count == 1 def test_retrying_proxy_swh_storage_keyboardinterrupt(swh_storage, sample_data, mocker): """Unfiltered errors are raising without retry""" mock_memory = mocker.patch("swh.storage.in_memory.InMemoryStorage.content_add") mock_memory.side_effect = KeyboardInterrupt() sample_content = sample_data.content content = swh_storage.content_get_data(sample_content.sha1) assert content is None with pytest.raises(KeyboardInterrupt): swh_storage.content_add([sample_content]) assert mock_memory.call_count == 1 def test_retrying_proxy_swh_storage_content_add_metadata_retry_failed( swh_storage, sample_data, mocker ): """When retrying fails every time, the last exception gets re-raised instead of a RetryError""" mock_memory = mocker.patch( "swh.storage.in_memory.InMemoryStorage.content_add_metadata" ) mock_memory.side_effect = [ ValueError(f"This will get raised eventually (attempt {i})") for i in range(1, 10) ] sample_content = sample_data.content content = attr.evolve(sample_content, data=None) with pytest.raises(ValueError, match="(attempt 3)"): swh_storage.content_add_metadata([content]) assert mock_memory.call_count == 3 diff --git a/tox.ini b/tox.ini index 7d233f81..49a9fcdc 100644 --- a/tox.ini +++ b/tox.ini @@ -1,84 +1,85 @@ [tox] envlist=black,flake8,mypy,py3 [testenv] extras = testing deps = pytest-cov dev: ipdb passenv = SWH_CASSANDRA_BIN SWH_CASSANDRA_LOG JAVA_HOME commands = pytest \ !slow: --hypothesis-profile=fast \ slow: --hypothesis-profile=slow \ --cov={envsitepackagesdir}/swh/storage \ {envsitepackagesdir}/swh/storage \ --doctest-modules \ --cov-branch {posargs} [testenv:black] skip_install = true deps = - black==22.3.0 + black==22.10.0 commands = {envpython} -m black --check swh [testenv:flake8] skip_install = true deps = - flake8==4.0.1 - flake8-bugbear==22.3.23 + flake8==5.0.4 + flake8-bugbear==22.9.23 + pycodestyle==2.9.1 commands = {envpython} -m flake8 [testenv:mypy] extras = testing deps = mypy==0.942 commands = mypy swh # build documentation outside swh-environment using the current # git HEAD of swh-docs, is executed on CI for each diff to prevent # breaking doc build [testenv:sphinx] whitelist_externals = make usedevelop = true extras = testing deps = # fetch and install swh-docs in develop mode -e git+https://forge.softwareheritage.org/source/swh-docs#egg=swh.docs pifpaf setenv = SWH_PACKAGE_DOC_TOX_BUILD = 1 # turn warnings into errors SPHINXOPTS = -W commands = {envpython} -m pifpaf run postgresql -- make -I ../.tox/sphinx/src/swh-docs/swh/ -C docs # build documentation only inside swh-environment using local state # of swh-docs package [testenv:sphinx-dev] whitelist_externals = make usedevelop = true extras = testing deps = # install swh-docs in develop mode -e ../swh-docs pifpaf setenv = SWH_PACKAGE_DOC_TOX_BUILD = 1 # turn warnings into errors SPHINXOPTS = -W commands = {envpython} -m pifpaf run postgresql -- make -I ../.tox/sphinx-dev/src/swh-docs/swh/ -C docs