diff --git a/PKG-INFO b/PKG-INFO index 35d33b3..6bbaf3d 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,125 +1,125 @@ Metadata-Version: 2.1 Name: swh.lister -Version: 3.0.0 +Version: 3.0.1 Summary: Software Heritage lister Home-page: https://forge.softwareheritage.org/diffusion/DLSGH/ 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-lister Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-lister/ 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 License-File: LICENSE swh-lister ========== This component from the Software Heritage stack aims to produce listings of software origins and their urls hosted on various public developer platforms or package managers. As these operations are quite similar, it provides a set of Python modules abstracting common software origins listing behaviors. It also provides several lister implementations, contained in the following Python modules: - `swh.lister.bitbucket` - `swh.lister.cgit` - `swh.lister.cran` - `swh.lister.debian` - `swh.lister.gitea` - `swh.lister.github` - `swh.lister.gitlab` - `swh.lister.gnu` - `swh.lister.golang` - `swh.lister.launchpad` - `swh.lister.maven` - `swh.lister.npm` - `swh.lister.packagist` - `swh.lister.phabricator` - `swh.lister.pypi` - `swh.lister.tuleap` - `swh.lister.gogs` Dependencies ------------ All required dependencies can be found in the `requirements*.txt` files located at the root of the repository. Local deployment ---------------- ## lister configuration Each lister implemented so far by Software Heritage (`bitbucket`, `cgit`, `cran`, `debian`, `gitea`, `github`, `gitlab`, `gnu`, `golang`, `launchpad`, `npm`, `packagist`, `phabricator`, `pypi`, `tuleap`, `maven`) must be configured by following the instructions below (please note that you have to replace `` by one of the lister name introduced above). ### Preparation steps 1. `mkdir ~/.config/swh/` 2. create configuration file `~/.config/swh/listers.yml` ### Configuration file sample Minimalistic configuration shared by all listers to add in file `~/.config/swh/listers.yml`: ```lang=yml scheduler: cls: 'remote' args: url: 'http://localhost:5008/' credentials: {} ``` Note: This expects scheduler (5008) service to run locally ## Executing a lister Once configured, a lister can be executed by using the `swh` CLI tool with the following options and commands: ``` $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister [lister_parameters] ``` Examples: ``` $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister bitbucket $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister cran $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister gitea url=https://codeberg.org/api/v1/ $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister gitlab url=https://salsa.debian.org/api/v4/ $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister npm $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister pypi ``` Licensing --------- This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. See top-level LICENSE file for the full text of the GNU General Public License along with this program. diff --git a/debian/changelog b/debian/changelog index 42f729d..9030c6e 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,1217 +1,1223 @@ -swh-lister (3.0.0-1~swh2~bpo10+1) buster-swh; urgency=medium +swh-lister (3.0.1-1~swh1) unstable-swh; urgency=medium - * Rebuild for buster-swh + * New upstream release 3.0.1 - (tagged by Antoine R. Dumont + (@ardumont) on 2022-09-20 11:32:36 + +0200) + * Upstream changes: - v3.0.1 - golang: Update lister name - + arch: Set log level to debug for URL requests - arch: Use + tempfile module to create temporary directory - pubdev.lister: + Decrease verbosity - -- Software Heritage autobuilder (on jenkins-debian1) Thu, 08 Sep 2022 10:01:11 +0000 + -- Software Heritage autobuilder (on jenkins-debian1) Tue, 20 Sep 2022 09:39:07 +0000 swh-lister (3.0.0-1~swh2) unstable-swh; urgency=medium * Fix build dependencies and bump new release -- Antoine R. Dumont (@ardumont) Thu, 08 Sep 2022 11:57:38 +0200 swh-lister (3.0.0-1~swh1) unstable-swh; urgency=medium * New upstream release 3.0.0 - (tagged by Antoine R. Dumont (@ardumont) on 2022-09-08 11:19:49 +0200) * Upstream changes: - v3.0.0 - Add new lister pubdev (Dart, Flutter) - Add new lister Arch User Repository (AUR) - Add new lister Golang - Add new lister Bower - Add new lister Gogs - maven: Use BeautifulSoup instead of xmltodict for parsing pom files - crates.lister: Implement incremental mode -- Software Heritage autobuilder (on jenkins-debian1) Thu, 08 Sep 2022 09:27:56 +0000 swh-lister (2.9.3-1~swh1) unstable-swh; urgency=medium * New upstream release 2.9.3 - (tagged by Antoine R. Dumont (@ardumont) on 2022-05-23 15:39:15 +0200) * Upstream changes: - v2.9.3 - Adapt maven lister to list canonical gh urls if any - Use swh.core.github.pytest_plugin in github tests -- Software Heritage autobuilder (on jenkins-debian1) Mon, 23 May 2022 13:47:34 +0000 swh-lister (2.9.2-1~swh1) unstable-swh; urgency=medium * New upstream release 2.9.2 - (tagged by Antoine R. Dumont (@ardumont) on 2022-05-10 10:22:12 +0200) * Upstream changes: - v2.9.2 - maven: Prevent UnicodeDecodeError when processing pom file -- Software Heritage autobuilder (on jenkins-debian1) Tue, 10 May 2022 08:27:22 +0000 swh-lister (2.9.1-1~swh1) unstable-swh; urgency=medium * New upstream release 2.9.1 - (tagged by Antoine R. Dumont (@ardumont) on 2022-04-29 14:45:18 +0200) * Upstream changes: - v2.9.1 - crates: Create one origin per package instead of per version - maven: Handle null mtime value in index for jar archive - maven: Remove extraction of groupId and artifactId from pom files - maven: Create one origin per package instead of one per package version - Bump mypy to v0.942 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 29 Apr 2022 12:50:29 +0000 swh-lister (2.9.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.9.0 - (tagged by Valentin Lorentz on 2022-04-26 11:28:55 +0200) * Upstream changes: - v2.9.0 - * github: Remove dead code - * github: Refactor rate-limiting out of the GitHubLister class - * maven: Remove duplicated code related to setting instance from netloc -- Software Heritage autobuilder (on jenkins-debian1) Tue, 26 Apr 2022 09:34:54 +0000 swh-lister (2.8.2-1~swh1) unstable-swh; urgency=medium * New upstream release 2.8.2 - (tagged by Antoine R. Dumont (@ardumont) on 2022-04-25 12:34:14 +0200) * Upstream changes: - v2.8.2 - sourceforge: Fix listing of bzr projects - sourceforge: Do not consider Attic as a valid CVS module -- Software Heritage autobuilder (on jenkins-debian1) Mon, 25 Apr 2022 10:39:18 +0000 swh-lister (2.8.1-1~swh1) unstable-swh; urgency=medium * New upstream release 2.8.1 - (tagged by Antoine R. Dumont (@ardumont) on 2022-04-14 15:56:17 +0200) * Upstream changes: - v2.8.1 - maven: Fix argument of type 'NoneType' is not iterable -- Software Heritage autobuilder (on jenkins-debian1) Thu, 14 Apr 2022 14:01:42 +0000 swh-lister (2.8.0-1~swh2) unstable-swh; urgency=medium * Bump new release (fix build dep) -- Antoine R. Dumont (@ardumont) Thu, 14 Apr 2022 14:51:05 +0200 swh-lister (2.8.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.8.0 - (tagged by Antoine R. Dumont (@ardumont) on 2022-04-14 11:42:16 +0200) * Upstream changes: - v2.8.0 - lister: Add new rust crates lister - maven: Continue listing if unable to retrieve pom information - maven: log error message when not able to retrieve the index to read -- Software Heritage autobuilder (on jenkins-debian1) Thu, 14 Apr 2022 09:50:25 +0000 swh-lister (2.7.2-1~swh1) unstable-swh; urgency=medium * New upstream release 2.7.2 - (tagged by Antoine Lambert on 2022-03-11 13:34:15 +0100) * Upstream changes: - version 2.7.2 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 11 Mar 2022 12:38:38 +0000 swh-lister (2.7.1-1~swh1) unstable-swh; urgency=medium * New upstream release 2.7.1 - (tagged by Antoine R. Dumont (@ardumont) on 2022-02-18 10:42:52 +0100) * Upstream changes: - v2.7.1 - launchpad: Ignore erratic page and continue listing next page -- Software Heritage autobuilder (on jenkins-debian1) Fri, 18 Feb 2022 09:46:37 +0000 swh-lister (2.7.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.7.0 - (tagged by Antoine R. Dumont (@ardumont) on 2022-02-17 13:56:23 +0100) * Upstream changes: - v2.7.0 - launchpad: Allow bzr origins listing - launchpad: Manage unhandled exceptions when listing - sourceforge: Fix origin URLs for CVS projects -- Software Heritage autobuilder (on jenkins-debian1) Thu, 17 Feb 2022 13:02:22 +0000 swh-lister (2.6.4-1~swh1) unstable-swh; urgency=medium * New upstream release 2.6.4 - (tagged by Antoine R. Dumont (@ardumont) on 2022-02-14 16:57:38 +0100) * Upstream changes: - v2.6.4 - sourceforge: fix support for listing bzr origins -- Software Heritage autobuilder (on jenkins-debian1) Mon, 14 Feb 2022 16:01:23 +0000 swh-lister (2.6.3-1~swh1) unstable-swh; urgency=medium * New upstream release 2.6.3 - (tagged by Antoine R. Dumont (@ardumont) on 2022-02-09 17:20:28 +0100) * Upstream changes: - v2.6.3 - maven: Fix last update datetime -- Software Heritage autobuilder (on jenkins-debian1) Wed, 09 Feb 2022 16:24:11 +0000 swh-lister (2.6.2-1~swh1) unstable-swh; urgency=medium * New upstream release 2.6.2 - (tagged by Antoine R. Dumont (@ardumont) on 2022-02-08 10:39:05 +0100) * Upstream changes: - v2.6.2 - Remove no longer needed tenacity workarounds - maven: Fix undef last_update in ListedOrigins. - maven: dismiss origins if they are malformed - e.g. wrong pom scm format, add test. - maven: Let logging instruction do the formatting - maven: Add more debug logging instruction - maven: Pass the base URL of the Maven instance to the loader - docs: Fix ReST syntax and sphinx warnings - Pin mypy and drop type annotations which makes mypy unhappy - requirements-test: Pin pytest to < 7.0.0 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 08 Feb 2022 09:43:37 +0000 swh-lister (2.6.1-1~swh1) unstable-swh; urgency=medium * New upstream release 2.6.1 - (tagged by Antoine Lambert on 2021-12-06 10:47:19 +0100) * Upstream changes: - version 2.6.1 -- Software Heritage autobuilder (on jenkins-debian1) Mon, 06 Dec 2021 09:51:07 +0000 swh-lister (2.6.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.6.0 - (tagged by Antoine Lambert on 2021-12-03 16:17:52 +0100) * Upstream changes: - version 2.6.0 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 03 Dec 2021 15:22:00 +0000 swh-lister (2.5.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.5.0 - (tagged by Antoine Lambert on 2021-12-03 14:44:36 +0100) * Upstream changes: - version 2.5.0 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 03 Dec 2021 13:48:49 +0000 swh-lister (2.4.0-1~swh3) unstable-swh; urgency=medium * Fix changelog error and actual correct release -- Antoine R. Dumont (@ardumont) Fri, 03 Dec 2021 12:45:00 +0100 swh.lister (2.4.0-1~swh2) unstable-swh; urgency=medium * Update missing deps and release -- Antoine R. Dumont (@ardumont) Fri, 03 Dec 2021 12:37:13 +0100 swh-lister (2.4.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.4.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-12-03 12:17:36 +0100) * Upstream changes: - v2.4.0 - debian: Update extra_loader_arguments dict produced ListedOrigin models - debian: Add missing file URIs in lister output - Deduplicate origins in the GitHub lister - lister: Add new maven lister -- Software Heritage autobuilder (on jenkins-debian1) Fri, 03 Dec 2021 11:21:58 +0000 swh-lister (2.3.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.3.0 - (tagged by Valentin Lorentz on 2021-11-10 13:44:49 +0100) * Upstream changes: - v2.3.0 - * cran: Pass the package name to the loader -- Software Heritage autobuilder (on jenkins-debian1) Wed, 10 Nov 2021 13:03:02 +0000 swh-lister (2.2.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.2.0 - (tagged by Antoine Lambert on 2021-10-22 15:16:48 +0200) * Upstream changes: - version 2.2.0 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 22 Oct 2021 13:23:02 +0000 swh-lister (2.1.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.1.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-10-13 10:16:37 +0200) * Upstream changes: - v2.1.0 - Let sourceforge origins be listed "enabled" by default - docs: Add a save forge documentation - docs: Explain task type registering to complete the save forge doc -- Software Heritage autobuilder (on jenkins-debian1) Wed, 13 Oct 2021 08:21:42 +0000 swh-lister (2.0.0-1~swh1) unstable-swh; urgency=medium * New upstream release 2.0.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-09-29 09:21:37 +0200) * Upstream changes: - v2.0.0 - opam: Share opam root directory even on multiple instances -- Software Heritage autobuilder (on jenkins-debian1) Wed, 29 Sep 2021 07:31:03 +0000 swh-lister (1.9.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.9.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-09-21 11:23:23 +0200) * Upstream changes: - v1.9.0 - gnu: Respect the pattern docstring about state initialization - opam: Allow defining where to actually install the opam_root folder - opam: Make the instance optional and derived from the url - opam: Move the state initialization into the get_pages method -- Software Heritage autobuilder (on jenkins-debian1) Tue, 21 Sep 2021 09:29:04 +0000 swh-lister (1.8.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.8.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-09-17 15:44:00 +0200) * Upstream changes: - v1.8.0 - Allow gitlab lister's name to be overridden by task arguments -- Software Heritage autobuilder (on jenkins-debian1) Fri, 17 Sep 2021 13:47:58 +0000 swh-lister (1.7.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.7.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-09-17 13:37:22 +0200) * Upstream changes: - v1.7.0 - gitlab: Allow ingestion of hg_git origins as hg ones (some instance can list tose e.g - foss.heptapod.net) -- Software Heritage autobuilder (on jenkins-debian1) Fri, 17 Sep 2021 11:41:52 +0000 swh-lister (1.6.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.6.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-09-17 10:50:28 +0200) * Upstream changes: - v1.6.0 - gitlab: Allow listing of instances providing multiple vcs_type -- Software Heritage autobuilder (on jenkins-debian1) Fri, 17 Sep 2021 08:55:14 +0000 swh-lister (1.5.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.5.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-07-23 16:28:50 +0200) * Upstream changes: - v1.5.0 - gitlab: Handle HTTP status code 500 when listing projects - gitlab: Update requests query parameters - gitlab: Adapt requests retry policy to consider HTTP 50x status codes - opam: Directly use the --root flag instead of using an env variable - pattern: Use URL network location as instance name when not provided -- Software Heritage autobuilder (on jenkins-debian1) Fri, 23 Jul 2021 14:32:51 +0000 swh-lister (1.4.0-1~swh2) unstable-swh; urgency=medium * Bump new release -- Antoine R. Dumont (@ardumont) Fri, 09 Jul 2021 13:17:00 +0200 swh-lister (1.4.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.4.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-07-09 13:01:04 +0200) * Upstream changes: - v1.4.0 - New Tuleap lister - New Opam lister - Make PyPI lister incremental - Make PyPI lister complete the information on origins -- Software Heritage autobuilder (on jenkins-debian1) Fri, 09 Jul 2021 11:06:37 +0000 swh-lister (1.3.6-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.6 - (tagged by Antoine R. Dumont (@ardumont) on 2021-06-04 11:59:24 +0200) * Upstream changes: - v1.3.6 - sourceforge: use http:// for Mercurial (as workaround) -- Software Heritage autobuilder (on jenkins-debian1) Fri, 04 Jun 2021 10:03:14 +0000 swh-lister (1.3.5-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.5 - (tagged by Antoine R. Dumont (@ardumont) on 2021-06-03 10:22:17 +0200) * Upstream changes: - v1.3.5 - sourceforge: set the protocol for origin urls -- Software Heritage autobuilder (on jenkins-debian1) Thu, 03 Jun 2021 08:26:13 +0000 swh-lister (1.3.4-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.4 - (tagged by Antoine R. Dumont (@ardumont) on 2021-05-31 16:54:37 +0200) * Upstream changes: - v1.3.4 - Disable the sourceforge lister origins (so they can be listed) -- Software Heritage autobuilder (on jenkins-debian1) Mon, 31 May 2021 15:08:17 +0000 swh-lister (1.3.3-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.3 - (tagged by Antoine R. Dumont (@ardumont) on 2021-05-28 14:18:53 +0200) * Upstream changes: - v1.3.3 - cgit/lister: Fix error when a missing version is not provided -- Software Heritage autobuilder (on jenkins-debian1) Fri, 28 May 2021 12:39:52 +0000 swh-lister (1.3.2-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.2 - (tagged by Antoine R. Dumont (@ardumont) on 2021-05-26 12:43:45 +0200) * Upstream changes: - v1.3.2 - sourceforge: retry for all retryable exceptions -- Software Heritage autobuilder (on jenkins-debian1) Wed, 26 May 2021 10:48:22 +0000 swh-lister (1.3.1-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.1 - (tagged by Antoine R. Dumont (@ardumont) on 2021-05-19 11:25:59 +0200) * Upstream changes: - v1.3.1 - sourceforge: don't abort on error for project -- Software Heritage autobuilder (on jenkins-debian1) Wed, 19 May 2021 09:30:14 +0000 swh-lister (1.3.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.3.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-05-07 17:17:50 +0200) * Upstream changes: - v1.3.0 - sourceforge/tasks: Allow incremental listing - sourceforge/lister: Add credentials parameter -- Software Heritage autobuilder (on jenkins-debian1) Fri, 07 May 2021 15:24:27 +0000 swh-lister (1.2.2-1~swh1) unstable-swh; urgency=medium * New upstream release 1.2.2 - (tagged by Antoine Lambert on 2021-05-07 14:43:24 +0200) * Upstream changes: - version 1.2.2 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 07 May 2021 12:50:12 +0000 swh-lister (1.2.1-1~swh1) unstable-swh; urgency=medium * New upstream release 1.2.1 - (tagged by Antoine Lambert on 2021-05-07 14:10:36 +0200) * Upstream changes: - version 1.2.1 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 07 May 2021 12:17:16 +0000 swh-lister (1.2.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.2.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-05-06 15:17:51 +0200) * Upstream changes: - v1.2.0 - Make the SourceForge lister incremental -- Software Heritage autobuilder (on jenkins-debian1) Fri, 07 May 2021 10:43:11 +0000 swh-lister (1.1.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.1.0 - (tagged by Antoine Lambert on 2021-04-29 14:29:27 +0200) * Upstream changes: - version 1.1.0 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 29 Apr 2021 12:33:59 +0000 swh-lister (1.0.0-1~swh1) unstable-swh; urgency=medium * New upstream release 1.0.0 - (tagged by Nicolas Dandrimont on 2021-03-22 10:56:04 +0100) * Upstream changes: - Release swh.lister v1.0.0 - All listers have been rewritten and are ready to be used in production - with the most recent version of the swh.scheduler APIs. -- Software Heritage autobuilder (on jenkins-debian1) Mon, 22 Mar 2021 10:13:35 +0000 swh-lister (0.10.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.10.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-03-01 09:59:16 +0100) * Upstream changes: - v0.10.0 - docs: Add new "howto write a lister tutorial" with unified lister api -- Software Heritage autobuilder (on jenkins-debian1) Mon, 01 Mar 2021 09:01:54 +0000 swh-lister (0.9.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.9.1 - (tagged by Antoine R. Dumont (@ardumont) on 2021-02-08 14:09:27 +0100) * Upstream changes: - v0.9.1 - debian: Update archive mirror URL templates to process -- Software Heritage autobuilder (on jenkins-debian1) Mon, 08 Feb 2021 13:12:05 +0000 swh-lister (0.9.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.9.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-02-08 08:50:07 +0100) * Upstream changes: - v0.9.0 - docs: Update listers execution instructions - cran: Prevent multiple listing of an origin - cran: Add support for parsing date with milliseconds - pypi: Use BeautifulSoup for parsing HTML instead of xmltodict -- Software Heritage autobuilder (on jenkins-debian1) Mon, 08 Feb 2021 07:52:57 +0000 swh-lister (0.8.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.8.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-02-03 11:12:52 +0100) * Upstream changes: - v0.8.0 - packagist: Reimplement lister using new Lister API - gnu: Remove dependency on pytz - Remove no longer used models field in dict returned by register - Remove no longer used legacy Lister API and update CLI options -- Software Heritage autobuilder (on jenkins-debian1) Wed, 03 Feb 2021 10:15:54 +0000 swh-lister (0.7.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.7.1 - (tagged by Vincent SELLIER on 2021-02-01 17:52:33 +0100) * Upstream changes: - v0.7.1 - * cgit: remove the repository urls's trailing / -- Software Heritage autobuilder (on jenkins-debian1) Mon, 01 Feb 2021 16:56:35 +0000 swh-lister (0.7.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.7.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-02-01 09:31:30 +0100) * Upstream changes: - v0.7.0 - pattern: Bump packet split to chunk of 1000 records - cgit: Compute origin urls out of a base git url when provided. - gnu: Reimplement lister using new Lister API -- Software Heritage autobuilder (on jenkins-debian1) Mon, 01 Feb 2021 08:35:14 +0000 swh-lister (0.6.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.6.1 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-29 09:07:21 +0100) * Upstream changes: - v0.6.1 - launchpad: Remove call to dataclasses.asdict on lister state - launchpad: Prevent error due to origin listed twice - Make debian lister constructors compatible with credentials - launchpad/tasks: Fix ping task function name - pattern: Make lister flush regularly origins to scheduler -- Software Heritage autobuilder (on jenkins-debian1) Fri, 29 Jan 2021 08:11:13 +0000 swh-lister (0.6.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.6.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-28 15:48:32 +0100) * Upstream changes: - v0.6.0 - launchpad: Reimplement lister using new Lister API - Make stateless lister constructors compatible with credentials -- Software Heritage autobuilder (on jenkins-debian1) Thu, 28 Jan 2021 14:52:49 +0000 swh-lister (0.5.4-1~swh1) unstable-swh; urgency=medium * New upstream release 0.5.4 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-28 11:23:29 +0100) * Upstream changes: - v0.5.4 - gitlab: Deal with missing or trailing / in url input - tox.ini: Work around build failure due to upstream release -- Software Heritage autobuilder (on jenkins-debian1) Thu, 28 Jan 2021 10:27:59 +0000 swh-lister (0.5.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.5.2 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-27 17:19:10 +0100) * Upstream changes: - v0.5.2 - test_cli: Drop launchpad lister from the test_get_lister -- Software Heritage autobuilder (on jenkins-debian1) Wed, 27 Jan 2021 16:25:31 +0000 swh-lister (0.5.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.5.1 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-27 16:39:20 +0100) * Upstream changes: - v0.5.1 - launchpad: Actually mock the anonymous login to launchpad - Drop no longer swh.lister.core.{indexing,page_by_page}_lister - tests: Drop unneeded reset instruction - cgit: Don't stop the listing when a repository page is not available -- Software Heritage autobuilder (on jenkins-debian1) Wed, 27 Jan 2021 15:47:39 +0000 swh-lister (0.5.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.5.0 - (tagged by Antoine R. Dumont (@ardumont) on 2021-01-27 14:33:24 +0100) * Upstream changes: - v0.5.0 - cgit: Add support for last_update information during listing - Port Debian lister to new lister api - gitlab: Implement keyset-based pagination listing - cran: Retrieve last update date for each listed package - Port CRAN lister to new lister api - gitlab: Add support for last_update information during listing - Port Gitea lister to new lister api - Port cgit lister to the new lister api - bitbucket: Pick random credentials in configuration and improve logging - Port Gitlab lister to the new lister api - Port Npm lister to new lister api - Port PyPI lister to new lister api - Port Bitbucket lister to new lister api - Port Phabricator lister to new lister api - Port GitHub lister to new lister api - Introduce a simpler base pattern for lister implementations -- Software Heritage autobuilder (on jenkins-debian1) Wed, 27 Jan 2021 13:40:34 +0000 swh-lister (0.4.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.4.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-11-23 15:47:05 +0100) * Upstream changes: - v0.4.0 - requirements: Rework dependencies - tests: Reduce db initialization fixtures to a minimum - Create listing task with a default of 3 if unspecified - lister.pytest_plugin: Simplify fixture setup - tests: Clarify listers test configuration -- Software Heritage autobuilder (on jenkins-debian1) Mon, 23 Nov 2020 14:52:03 +0000 swh-lister (0.3.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.3.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-10-19 09:50:43 +0200) * Upstream changes: - v0.3.0 - lister.config: Adapt scheduler configuration structure - drop mock_get_scheduler which creates indirection for no good reason -- Software Heritage autobuilder (on jenkins-debian1) Mon, 19 Oct 2020 07:56:17 +0000 swh-lister (0.2.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.2.1 - (tagged by Antoine R. Dumont (@ardumont) on 2020-10-07 14:02:42 +0200) * Upstream changes: - v0.2.1 - lister_base: Drop leftover mixin SWHConfig which is no longer used -- Software Heritage autobuilder (on jenkins-debian1) Wed, 07 Oct 2020 12:07:43 +0000 swh-lister (0.2.0-1~swh1) unstable-swh; urgency=medium * New upstream release 0.2.0 - (tagged by Antoine R. Dumont (@ardumont) on 2020-10-06 09:33:33 +0200) * Upstream changes: - v0.2.0 - lister*: Migrate away from SWHConfig mixin - tox.ini: pin black to the pre-commit version (19.10b0) to avoid flip-flops - Run isort after the CLI import changes -- Software Heritage autobuilder (on jenkins-debian1) Tue, 06 Oct 2020 07:36:07 +0000 swh-lister (0.1.5-1~swh1) unstable-swh; urgency=medium * New upstream release 0.1.5 - (tagged by David Douard on 2020-09-25 11:51:57 +0200) * Upstream changes: - v0.1.5 -- Software Heritage autobuilder (on jenkins-debian1) Fri, 25 Sep 2020 09:55:44 +0000 swh-lister (0.1.4-1~swh1) unstable-swh; urgency=medium * New upstream release 0.1.4 - (tagged by Antoine R. Dumont (@ardumont) on 2020-09-10 11:32:46 +0200) * Upstream changes: - v0.1.4 - gitea.lister: Fix uid to be unique across instance - utils.split_range: Split into not overlapping ranges - gitea.tasks: Fix parameter name from 'sort' to 'order' -- Software Heritage autobuilder (on jenkins-debian1) Thu, 10 Sep 2020 09:35:53 +0000 swh-lister (0.1.3-1~swh1) unstable-swh; urgency=medium * New upstream release 0.1.3 - (tagged by Vincent SELLIER on 2020-09-08 14:48:08 +0200) * Upstream changes: - v0.1.3 - Launchpad: rename task name to match conventions - tests: Separate lister instantiations -- Software Heritage autobuilder (on jenkins-debian1) Tue, 08 Sep 2020 12:53:22 +0000 swh-lister (0.1.2-1~swh1) unstable-swh; urgency=medium * New upstream release 0.1.2 - (tagged by Antoine R. Dumont (@ardumont) on 2020-09-02 13:07:30 +0200) * Upstream changes: - v0.1.2 - pytest_plugin: Instantiate only lister with no particular setup - pytest: Define plugin and declare it in the root conftest -- Software Heritage autobuilder (on jenkins-debian1) Wed, 02 Sep 2020 11:10:14 +0000 swh-lister (0.1.1-1~swh1) unstable-swh; urgency=medium * New upstream release 0.1.1 - (tagged by Antoine R. Dumont (@ardumont) on 2020-09-01 16:08:48 +0200) * Upstream changes: - v0.1.1 - test_cli: Exclude launchpad lister from the check -- Software Heritage autobuilder (on jenkins-debian1) Tue, 01 Sep 2020 14:11:46 +0000 swh-lister (0.1.0-1~swh2) unstable-swh; urgency=medium * Update dependencies -- Antoine R. Dumont (@ardumont) Wed, 26 Aug 2020 16:05:03 +0000 swh-lister (0.1.0-1~swh1) unstable-swh; urgency=medium [ Nicolas Dandrimont ] * Use setuptools-scm instead of vcversioner [ Software Heritage autobuilder (on jenkins-debian1) ] * New upstream release 0.1.0 - (tagged by David Douard on 2020-08-25 18:33:55 +0200) * Upstream changes: - v0.1.0 -- Software Heritage autobuilder (on jenkins-debian1) Tue, 25 Aug 2020 16:39:28 +0000 swh-lister (0.0.50-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.50 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-20 10:44:57 +0100) * Upstream changes: - v0.0.50 - github.lister: Filter out partial repositories which break listing - docs: Fix sphinx warnings - core.lister_base: Improve slightly docs and types -- Software Heritage autobuilder (on jenkins-debian1) Mon, 20 Jan 2020 09:51:23 +0000 swh-lister (0.0.49-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.49 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-17 14:20:35 +0100) * Upstream changes: - v0.0.49 - github.lister: Use Retry-After header when rate limit reached -- Software Heritage autobuilder (on jenkins-debian1) Fri, 17 Jan 2020 13:27:56 +0000 swh-lister (0.0.48-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.48 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-16 13:56:12 +0100) * Upstream changes: - v0.0.48 - cran.lister: Use cran's canonical url for origin url - cran.lister: Version uid so we can list new package versions - cran.lister: Adapt docstring sample accordingly -- Software Heritage autobuilder (on jenkins-debian1) Thu, 16 Jan 2020 13:03:54 +0000 swh-lister (0.0.47-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.47 - (tagged by Antoine R. Dumont (@ardumont) on 2020-01-09 10:26:18 +0100) * Upstream changes: - v0.0.47 - cran.lister: Align loading tasks' with loader's expectation -- Software Heritage autobuilder (on jenkins-debian1) Thu, 09 Jan 2020 09:34:26 +0000 swh-lister (0.0.46-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.46 - (tagged by Antoine R. Dumont (@ardumont) on 2019-12-19 14:09:45 +0100) * Upstream changes: - v0.0.46 - lister.debian: Make debian init step idempotent and up-to-date - lister_base: Split into chunks the tasks prior to creation -- Software Heritage autobuilder (on jenkins-debian1) Thu, 19 Dec 2019 13:16:45 +0000 swh-lister (0.0.45-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.45 - (tagged by Antoine R. Dumont (@ardumont) on 2019-12-10 11:27:17 +0100) * Upstream changes: - v0.0.45 - core: Align listers' task output (hg/git tasks) with expected format - npm: Align lister's loader output tasks with expected format - lister/tasks: Standardize return statements -- Software Heritage autobuilder (on jenkins-debian1) Tue, 10 Dec 2019 10:32:45 +0000 swh-lister (0.0.44-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.44 - (tagged by Nicolas Dandrimont on 2019-11-22 16:15:54 +0100) * Upstream changes: - Release swh.lister v0.0.44 - Define proper User Agents everywhere -- Software Heritage autobuilder (on jenkins-debian1) Fri, 22 Nov 2019 15:31:33 +0000 swh-lister (0.0.43-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.43 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-21 18:46:35 +0100) * Upstream changes: - v0.0.43 - lister.pypi: Align lister with pypi package loader - lister.npm: Align lister with npm package loader - lister.tests: Avoid duplication setup step - Fix typos (and trailing ws) reported by codespell - Add a pre-commit config file -- Software Heritage autobuilder (on jenkins-debian1) Thu, 21 Nov 2019 17:56:34 +0000 swh-lister (0.0.42-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.42 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-21 13:52:16 +0100) * Upstream changes: - v0.0.42 - cran/gnu: Rename task_type to load-archive-files - lister.tests: Add missing task_type for package listers - Migrate tox.ini to extras = xxx instead of deps = .[testing] - Merge tox environments - Include all requirements in MANIFEST.in - lister.cli: Remove task type register cli -- Software Heritage autobuilder (on jenkins-debian1) Thu, 21 Nov 2019 13:00:29 +0000 swh-lister (0.0.41-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.41 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-15 12:02:13 +0100) * Upstream changes: - v0.0.41 - simple_lister: Flush to db more frequently - gnu.lister: Use url as primary key - gnu.lister.tests: Add missing assertion - gnu.lister: Add missing retries_left parameter - debian.models: Migrate tests from storage to debian lister model -- Software Heritage autobuilder (on jenkins-debian1) Fri, 15 Nov 2019 11:06:35 +0000 swh-lister (0.0.40-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.40 - (tagged by Nicolas Dandrimont on 2019-11-13 13:54:38 +0100) * Upstream changes: - Release swh.lister 0.0.40 - Fix bogus NotImplementedError on Area.index_uris -- Software Heritage autobuilder (on jenkins-debian1) Wed, 13 Nov 2019 13:02:08 +0000 swh-lister (0.0.39-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.39 - (tagged by Nicolas Dandrimont on 2019-11-13 13:23:31 +0100) * Upstream changes: - Release swh.lister 0.0.39 - Properly register all tasks - Fix up db_partition_indices to avoid expensive scans -- Software Heritage autobuilder (on jenkins-debian1) Wed, 13 Nov 2019 12:28:33 +0000 swh-lister (0.0.38-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.38 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-06 15:55:46 +0100) * Upstream changes: - v0.0.38 - Remove swh.storage.schemata remnants -- Software Heritage autobuilder (on jenkins-debian1) Wed, 06 Nov 2019 15:00:16 +0000 swh-lister (0.0.37-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.37 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-06 15:06:51 +0100) * Upstream changes: - v0.0.37 - Update swh-core dependency -- Software Heritage autobuilder (on jenkins-debian1) Wed, 06 Nov 2019 14:18:31 +0000 swh-lister (0.0.36-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.36 - (tagged by Antoine R. Dumont (@ardumont) on 2019-11-06 11:33:33 +0100) * Upstream changes: - v0.0.36 - lister.*.tests: Add at least one integration test - gnu.lister: Move gnu listers specifity within the lister's scope - debian/lister: Use url parameter name instead of origin - debian/model: Install lister model within the lister repository - lister.*.tasks: Stop binding tasks to a specific instance of the - celery app - cran.lister: Refactor and fix cran lister - github/lister: Prevent erroneous scheduler tasks disabling - phabricator/lister: Fix lister - setup.py: Kill deprecated swh- lister command - Bootstrap typing annotations -- Software Heritage autobuilder (on jenkins-debian1) Wed, 06 Nov 2019 10:55:41 +0000 swh-lister (0.0.35-1~swh4) unstable-swh; urgency=medium * Fix runtime dependencies -- Antoine R. Dumont (@ardumont) Wed, 11 Sep 2019 10:58:01 +0200 swh-lister (0.0.35-1~swh3) unstable-swh; urgency=medium * Bump dh-python to >= 3 for pybuild.testfiles. -- Nicolas Dandrimont Tue, 10 Sep 2019 14:58:11 +0200 swh-lister (0.0.35-1~swh2) unstable-swh; urgency=medium * Add egg-info to pybuild.testfiles. Close T1995. -- Nicolas Dandrimont Tue, 10 Sep 2019 14:36:22 +0200 swh-lister (0.0.35-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.35 - (tagged by Antoine R. Dumont (@ardumont) on 2019-09-09 12:14:42 +0200) * Upstream changes: - v0.0.35 - Fix debian package -- Software Heritage autobuilder (on jenkins-debian1) Mon, 09 Sep 2019 10:19:02 +0000 swh-lister (0.0.34-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.34 - (tagged by Antoine R. Dumont (@ardumont) on 2019-09-06 14:03:39 +0200) * Upstream changes: - v0.0.34 - listers: Implement listers as plugins - cgit: rewrite the CGit lister (and add more tests) - listers: simplify and unify constructor use - phabricator: randomly select the API token in the provided list - docs: Fix toc -- Software Heritage autobuilder (on jenkins-debian1) Fri, 06 Sep 2019 12:09:13 +0000 swh-lister (0.0.33-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.33 - (tagged by Antoine R. Dumont (@ardumont) on 2019-08-29 10:23:20 +0200) * Upstream changes: - v0.0.33 - lister.cli: Allow to list forges with policy and priority - listers: Add New packagist lister - listers: Allow to override policy and priority for scheduled tasks - tests: Add tests to cli, pypi and improve lister core's - docs: Add code of conduct document -- Software Heritage autobuilder (on jenkins-debian1) Thu, 29 Aug 2019 08:28:23 +0000 swh-lister (0.0.32-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.32 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-28 18:21:50 +0200) * Upstream changes: - v0.0.32 - Clean up dead code - Add missing *.html sample for tests to run in packaging -- Software Heritage autobuilder (on jenkins-debian1) Fri, 28 Jun 2019 16:42:05 +0000 swh-lister (0.0.31-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.31 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-28 17:57:48 +0200) * Upstream changes: - v0.0.31 - Add cgit instance lister - Add back description in cran lister - Update contributors -- Software Heritage autobuilder (on jenkins-debian1) Fri, 28 Jun 2019 16:06:25 +0000 swh-lister (0.0.30-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.30 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-26 14:52:13 +0200) * Upstream changes: - v0.0.30 - Drop last description mentions for gitlab and cran listers. -- Software Heritage autobuilder (on jenkins-debian1) Wed, 26 Jun 2019 13:02:11 +0000 swh-lister (0.0.29-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.29 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-26 12:37:14 +0200) * Upstream changes: - v0.0.29 - lister: Fix bitbucket lister -- Software Heritage autobuilder (on jenkins-debian1) Wed, 26 Jun 2019 10:47:20 +0000 swh-lister (0.0.28-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.28 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-20 12:00:09 +0200) * Upstream changes: - v0.0.28 - listers: Remove unused columns `origin_id` / `description` - gnu-lister: Use origin-type as 'tar' (and not 'gnu') - phabricator: Remove unused code -- Software Heritage autobuilder (on jenkins-debian1) Thu, 20 Jun 2019 10:07:48 +0000 swh-lister (0.0.27-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.27 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-18 10:27:09 +0200) * Upstream changes: - v0.0.27 - Unify lister tablenames to use consistently singular - Add missing instance field to phabricator repository model -- Software Heritage autobuilder (on jenkins-debian1) Tue, 18 Jun 2019 08:44:38 +0000 swh-lister (0.0.26-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.26 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-17 17:53:33 +0200) * Upstream changes: - v0.0.26 - phabricator.lister: Use credentials setup from configuration file - gitlab.lister: Remove request_params method override -- Software Heritage autobuilder (on jenkins-debian1) Mon, 17 Jun 2019 16:05:05 +0000 swh-lister (0.0.25-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.25 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-13 15:54:42 +0200) * Upstream changes: - v0.0.25 - Add new cran lister - listers: Stop creating origins when scheduling new tasks -- Software Heritage autobuilder (on jenkins-debian1) Thu, 13 Jun 2019 13:59:30 +0000 swh-lister (0.0.24-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.24 - (tagged by Antoine R. Dumont (@ardumont) on 2019-06-12 12:02:54 +0200) * Upstream changes: - v0.0.24 - swh.lister.gnu: Add new gnu lister -- Software Heritage autobuilder (on jenkins-debian1) Wed, 12 Jun 2019 10:10:56 +0000 swh-lister (0.0.23-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.23 - (tagged by Antoine R. Dumont (@ardumont) on 2019-05-29 14:04:22 +0200) * Upstream changes: - v0.0.23 - lister: Unify credentials structure between listers -- Software Heritage autobuilder (on jenkins-debian1) Wed, 29 May 2019 12:10:51 +0000 swh-lister (0.0.22-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.22 - (tagged by Antoine Lambert on 2019-05-23 10:59:39 +0200) * Upstream changes: - version 0.0.22 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 23 May 2019 09:05:34 +0000 swh-lister (0.0.21-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.21 - (tagged by Antoine Lambert on 2019-04-11 11:00:55 +0200) * Upstream changes: - version 0.0.21 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 11 Apr 2019 09:05:30 +0000 swh-lister (0.0.20-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.20 - (tagged by Antoine R. Dumont (@ardumont) on 2019-02-14 10:50:06 +0100) * Upstream changes: - v0.0.20 - d/*: debian packaging files migrated to separated branches - lister.cli: Fix spelling typo -- Software Heritage autobuilder (on jenkins-debian1) Thu, 14 Feb 2019 09:59:29 +0000 swh-lister (0.0.19-1~swh1) unstable-swh; urgency=medium * New upstream release 0.0.19 - (tagged by David Douard on 2019-02-07 17:36:33 +0100) * Upstream changes: - v0.0.19 -- Software Heritage autobuilder (on jenkins-debian1) Thu, 07 Feb 2019 16:42:39 +0000 swh-lister (0.0.18-1~swh1) unstable-swh; urgency=medium * v0.0.18 * docs: add title and brief module description * gitlab.lister: Break asap when problem exists during fetch info * gitlab.lister: Do not expect gitlab instances to have credentials * setup: prepare for pypi upload * gitlab/models.py: drop unused import -- Antoine R. Dumont (@ardumont) Mon, 08 Oct 2018 15:54:12 +0200 swh-lister (0.0.17-1~swh1) unstable-swh; urgency=medium * v0.0.17 * Change pypi project url to use the /project api -- Antoine R. Dumont (@ardumont) Tue, 18 Sep 2018 11:35:25 +0200 swh-lister (0.0.16-1~swh1) unstable-swh; urgency=medium * v0.0.16 * Normalize PyPI name -- Antoine R. Dumont (@ardumont) Fri, 14 Sep 2018 13:25:56 +0200 swh-lister (0.0.15-1~swh1) unstable-swh; urgency=medium * v0.0.15 * Add pypi lister -- Antoine R. Dumont (@ardumont) Thu, 06 Sep 2018 17:09:25 +0200 swh-lister (0.0.14-1~swh1) unstable-swh; urgency=medium * v0.0.14 * core.lister_base: Batch create origins (storage) & tasks (scheduler) * swh.lister.cli: Add debian lister to the list of supported listers * README.md: Update to demo the lister debian run -- Antoine R. Dumont (@ardumont) Tue, 31 Jul 2018 15:46:12 +0200 swh-lister (0.0.13-1~swh1) unstable-swh; urgency=medium * v0.0.13 * Fix missing use cases when unable to retrieve information from the api * server * gitlab/lister: Allow specifying the number of elements to * read (default is 20, same as the current gitlab api) -- Antoine R. Dumont (@ardumont) Fri, 20 Jul 2018 13:46:04 +0200 swh-lister (0.0.12-1~swh1) unstable-swh; urgency=medium * v0.0.12 * swh.lister.gitlab.tasks: Use gitlab as instance name for gitlab.com * README.md: Add gitlab to the lister implementations referenced * core/lister_base: Remove unused import -- Antoine R. Dumont (@ardumont) Thu, 19 Jul 2018 11:29:14 +0200 swh-lister (0.0.11-1~swh1) unstable-swh; urgency=medium * v0.0.11 * lister/gitlab: Add gitlab lister * docs: Update documentation to demonstrate how to run a lister locally * core/lister: Make the listers' scheduler configuration adaptable * debian/*: Fix debian packaging tests -- Antoine R. Dumont (@ardumont) Wed, 18 Jul 2018 14:16:56 +0200 swh-lister (0.0.10-1~swh1) unstable-swh; urgency=medium * Release swh.lister v0.0.10 * Add missing task_queue attribute for debian listing tasks * Make sure tests run during build * Clean up runtime dependencies -- Nicolas Dandrimont Mon, 30 Oct 2017 17:37:25 +0100 swh-lister (0.0.9-1~swh1) unstable-swh; urgency=medium * Release swh.lister v0.0.9 * Add tasks for the Debian lister -- Nicolas Dandrimont Mon, 30 Oct 2017 14:20:58 +0100 swh-lister (0.0.8-1~swh1) unstable-swh; urgency=medium * Release swh.lister v0.0.8 * Add versioned dependency on sqlalchemy -- Nicolas Dandrimont Fri, 13 Oct 2017 12:15:38 +0200 swh-lister (0.0.7-1~swh1) unstable-swh; urgency=medium * Release swh.lister version 0.0.7 * Update packaging runes -- Nicolas Dandrimont Thu, 12 Oct 2017 18:07:52 +0200 swh-lister (0.0.6-1~swh1) unstable-swh; urgency=medium * Release swh.lister v0.0.6 * Add new debian lister -- Nicolas Dandrimont Wed, 11 Oct 2017 17:59:47 +0200 swh-lister (0.0.5-1~swh1) unstable-swh; urgency=medium * Release swh.lister 0.0.5 * Make the lister more generic * Add bitbucket lister * Update tasks to new swh.scheduler API -- Nicolas Dandrimont Mon, 12 Jun 2017 18:22:13 +0200 swh-lister (0.0.4-1~swh1) unstable-swh; urgency=medium * v0.0.4 * Update storage configuration reading -- Antoine R. Dumont (@ardumont) Thu, 15 Dec 2016 19:07:24 +0100 swh-lister (0.0.3-1~swh1) unstable-swh; urgency=medium * Release swh.lister.github v0.0.3 * Generate swh.scheduler tasks and swh.storage origins on the fly * Use celery tasks to schedule own work -- Nicolas Dandrimont Thu, 20 Oct 2016 17:30:39 +0200 swh-lister (0.0.2-1~swh1) unstable-swh; urgency=medium * Release swh.lister.github 0.0.2 * Move constants to a constants module to avoid circular imports -- Nicolas Dandrimont Thu, 17 Mar 2016 20:35:11 +0100 swh-lister (0.0.1-1~swh1) unstable-swh; urgency=medium * Initial release * Release swh.lister.github v0.0.1 -- Nicolas Dandrimont Thu, 17 Mar 2016 19:01:20 +0100 diff --git a/swh.lister.egg-info/PKG-INFO b/swh.lister.egg-info/PKG-INFO index 35d33b3..6bbaf3d 100644 --- a/swh.lister.egg-info/PKG-INFO +++ b/swh.lister.egg-info/PKG-INFO @@ -1,125 +1,125 @@ Metadata-Version: 2.1 Name: swh.lister -Version: 3.0.0 +Version: 3.0.1 Summary: Software Heritage lister Home-page: https://forge.softwareheritage.org/diffusion/DLSGH/ 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-lister Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-lister/ 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 License-File: LICENSE swh-lister ========== This component from the Software Heritage stack aims to produce listings of software origins and their urls hosted on various public developer platforms or package managers. As these operations are quite similar, it provides a set of Python modules abstracting common software origins listing behaviors. It also provides several lister implementations, contained in the following Python modules: - `swh.lister.bitbucket` - `swh.lister.cgit` - `swh.lister.cran` - `swh.lister.debian` - `swh.lister.gitea` - `swh.lister.github` - `swh.lister.gitlab` - `swh.lister.gnu` - `swh.lister.golang` - `swh.lister.launchpad` - `swh.lister.maven` - `swh.lister.npm` - `swh.lister.packagist` - `swh.lister.phabricator` - `swh.lister.pypi` - `swh.lister.tuleap` - `swh.lister.gogs` Dependencies ------------ All required dependencies can be found in the `requirements*.txt` files located at the root of the repository. Local deployment ---------------- ## lister configuration Each lister implemented so far by Software Heritage (`bitbucket`, `cgit`, `cran`, `debian`, `gitea`, `github`, `gitlab`, `gnu`, `golang`, `launchpad`, `npm`, `packagist`, `phabricator`, `pypi`, `tuleap`, `maven`) must be configured by following the instructions below (please note that you have to replace `` by one of the lister name introduced above). ### Preparation steps 1. `mkdir ~/.config/swh/` 2. create configuration file `~/.config/swh/listers.yml` ### Configuration file sample Minimalistic configuration shared by all listers to add in file `~/.config/swh/listers.yml`: ```lang=yml scheduler: cls: 'remote' args: url: 'http://localhost:5008/' credentials: {} ``` Note: This expects scheduler (5008) service to run locally ## Executing a lister Once configured, a lister can be executed by using the `swh` CLI tool with the following options and commands: ``` $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister [lister_parameters] ``` Examples: ``` $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister bitbucket $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister cran $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister gitea url=https://codeberg.org/api/v1/ $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister gitlab url=https://salsa.debian.org/api/v4/ $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister npm $ swh --log-level DEBUG lister -C ~/.config/swh/listers.yml run --lister pypi ``` Licensing --------- This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. See top-level LICENSE file for the full text of the GNU General Public License along with this program. diff --git a/swh/lister/arch/lister.py b/swh/lister/arch/lister.py index 58e5371..af3a3d8 100644 --- a/swh/lister/arch/lister.py +++ b/swh/lister/arch/lister.py @@ -1,500 +1,501 @@ # Copyright (C) 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 from pathlib import Path import re import tarfile +import tempfile from typing import Any, Dict, Iterator, List, Optional from urllib.parse import unquote, urljoin from bs4 import BeautifulSoup import requests from tenacity.before_sleep import before_sleep_log from swh.lister.utils import throttling_retry from swh.model.hashutil import hash_to_hex from swh.scheduler.interface import SchedulerInterface from swh.scheduler.model import ListedOrigin from .. import USER_AGENT from ..pattern import CredentialsType, StatelessLister logger = logging.getLogger(__name__) # Aliasing the page results returned by `get_pages` method from the lister. ArchListerPage = List[Dict[str, Any]] def size_to_bytes(size: str) -> int: """Convert human readable file size to bytes. Resulting value is an approximation as input value is in most case rounded. Args: size: A string representing a human readable file size (eg: '500K') Returns: A decimal representation of file size Examples:: >>> size_to_bytes("500") 500 >>> size_to_bytes("1K") 1000 """ units = { "K": 1000, "M": 1000**2, "G": 1000**3, "T": 1000**4, "P": 1000**5, "E": 1000**6, "Z": 1000**7, "Y": 1000**8, } if size.endswith(tuple(units)): v, u = (size[:-1], size[-1]) return int(v) * units[u] else: return int(size) class ArchLister(StatelessLister[ArchListerPage]): """List Arch linux origins from 'core', 'extra', and 'community' repositories For 'official' Arch Linux it downloads core.tar.gz, extra.tar.gz and community.tar.gz from https://archive.archlinux.org/repos/last/ extract to a temp directory and then walks through each 'desc' files. Each 'desc' file describe the latest released version of a package and helps to build an origin url from where scrapping artifacts metadata. For 'arm' Arch Linux it follow the same discovery process parsing 'desc' files. The main difference is that we can't get existing versions of an arm package because https://archlinuxarm.org does not have an 'archive' website or api. """ LISTER_NAME = "arch" VISIT_TYPE = "arch" INSTANCE = "arch" - DESTINATION_PATH = Path("/tmp/archlinux_archive") - ARCH_PACKAGE_URL_PATTERN = "{base_url}/packages/{repo}/{arch}/{pkgname}" ARCH_PACKAGE_VERSIONS_URL_PATTERN = "{base_url}/packages/{pkgname[0]}/{pkgname}" ARCH_PACKAGE_DOWNLOAD_URL_PATTERN = ( "{base_url}/packages/{pkgname[0]}/{pkgname}/{filename}" ) ARCH_API_URL_PATTERN = "{base_url}/packages/{repo}/{arch}/{pkgname}/json" ARM_PACKAGE_URL_PATTERN = "{base_url}/packages/{arch}/{pkgname}" ARM_PACKAGE_DOWNLOAD_URL_PATTERN = "{base_url}/{arch}/{repo}/{filename}" def __init__( self, scheduler: SchedulerInterface, credentials: Optional[CredentialsType] = None, flavours: Dict[str, Any] = { "official": { "archs": ["x86_64"], "repos": ["core", "extra", "community"], "base_info_url": "https://archlinux.org", "base_archive_url": "https://archive.archlinux.org", "base_mirror_url": "", "base_api_url": "https://archlinux.org", }, "arm": { "archs": ["armv7h", "aarch64"], "repos": ["core", "extra", "community"], "base_info_url": "https://archlinuxarm.org", "base_archive_url": "", "base_mirror_url": "https://uk.mirror.archlinuxarm.org", "base_api_url": "", }, }, ): super().__init__( scheduler=scheduler, credentials=credentials, url=flavours["official"]["base_info_url"], instance=self.INSTANCE, ) self.flavours = flavours self.session = requests.Session() self.session.headers.update( { "User-Agent": USER_AGENT, } ) @throttling_retry(before_sleep=before_sleep_log(logger, logging.WARNING)) def request_get(self, url: str, params: Dict[str, Any]) -> requests.Response: - logger.info("Fetching URL %s with params %s", url, params) + logger.debug("Fetching URL %s with params %s", url, params) response = self.session.get(url, params=params) if response.status_code != 200: logger.warning( "Unexpected HTTP status code %s on %s: %s", response.status_code, response.url, response.content, ) response.raise_for_status() return response def scrap_package_versions( self, name: str, repo: str, base_url: str ) -> List[Dict[str, Any]]: """Given a package 'name' and 'repo', make an http call to origin url and parse its content to get package versions artifacts data. That method is suitable only for 'official' Arch Linux, not 'arm'. Args: name: Package name repo: The repository the package belongs to (one of self.repos) Returns: A list of dict of version Example:: [ {"url": "https://archive.archlinux.org/packages/d/dialog/dialog-1:1.3_20190211-1-x86_64.pkg.tar.xz", # noqa: B950 "arch": "x86_64", "repo": "core", "name": "dialog", "version": "1:1.3_20190211-1", "length": 180000, "filename": "dialog-1:1.3_20190211-1-x86_64.pkg.tar.xz", "last_modified": "2019-02-13T08:36:00"}, ] """ url = self.ARCH_PACKAGE_VERSIONS_URL_PATTERN.format( pkgname=name, base_url=base_url ) response = self.request_get(url=url, params={}) soup = BeautifulSoup(response.text, "html.parser") links = soup.find_all("a", href=True) # drop the first line (used to go to up directory) if links[0].attrs["href"] == "../": links.pop(0) versions = [] for link in links: # filename displayed can be cropped if name is too long, get it from href instead filename = unquote(link.attrs["href"]) if filename.endswith((".tar.xz", ".tar.zst")): # Extract arch from filename arch_rex = re.compile( rf"^{re.escape(name)}-(?P.*)-(?Pany|i686|x86_64)" rf"(.pkg.tar.(?:zst|xz))$" ) m = arch_rex.match(filename) if m is None: logger.error( "Can not find a match for architecture in %(filename)s", dict(filename=filename), ) else: arch = m.group("arch") version = m.group("version") # Extract last_modified and an approximate file size raw_text = link.next_sibling raw_text_rex = re.compile( r"^(?P\d+-\w+-\d+ \d\d:\d\d)\s+(?P\w+)$" ) s = raw_text_rex.search(raw_text.strip()) if s is None: logger.error( "Can not find a match for 'last_modified' and/or " "'size' in '%(raw_text)s'", dict(raw_text=raw_text), ) else: assert s.groups() assert len(s.groups()) == 2 last_modified_str, size = s.groups() # format as expected last_modified = datetime.datetime.strptime( last_modified_str, "%d-%b-%Y %H:%M" ).isoformat() length = size_to_bytes(size) # we want bytes # link url is relative, format a canonical one url = self.ARCH_PACKAGE_DOWNLOAD_URL_PATTERN.format( base_url=base_url, pkgname=name, filename=filename ) versions.append( dict( name=name, version=version, repo=repo, arch=arch, filename=filename, url=url, last_modified=last_modified, length=length, ) ) return versions def get_repo_archive(self, url: str, destination_path: Path) -> Path: """Given an url and a destination path, retrieve and extract .tar.gz archive which contains 'desc' file for each package. Each .tar.gz archive corresponds to an Arch Linux repo ('core', 'extra', 'community'). Args: url: url of the .tar.gz archive to download destination_path: the path on disk where to extract archive Returns: a directory Path where the archive has been extracted to. """ res = self.request_get(url=url, params={}) destination_path.parent.mkdir(parents=True, exist_ok=True) destination_path.write_bytes(res.content) extract_to = Path(str(destination_path).split(".tar.gz")[0]) tar = tarfile.open(destination_path) tar.extractall(path=extract_to) tar.close() return extract_to def parse_desc_file( self, path: Path, repo: str, base_url: str, dl_url_fmt: str, ) -> Dict[str, Any]: """Extract package information from a 'desc' file. There are subtle differences between parsing 'official' and 'arm' des files Args: path: A path to a 'desc' file on disk repo: The repo the package belongs to Returns: A dict of metadata Example:: {'api_url': 'https://archlinux.org/packages/core/x86_64/dialog/json', 'arch': 'x86_64', 'base': 'dialog', 'builddate': '1650081535', 'csize': '203028', 'desc': 'A tool to display dialog boxes from shell scripts', 'filename': 'dialog-1:1.3_20220414-1-x86_64.pkg.tar.zst', 'isize': '483988', 'license': 'LGPL2.1', 'md5sum': '06407c0cb11c50d7bf83d600f2e8107c', 'name': 'dialog', 'packager': 'Evangelos Foutras ', 'pgpsig': 'pgpsig content xxx', 'project_url': 'https://invisible-island.net/dialog/', 'provides': 'libdialog.so=15-64', 'repo': 'core', 'sha256sum': 'ef8c8971f591de7db0f455970ef5d81d5aced1ddf139f963f16f6730b1851fa7', 'url': 'https://archive.archlinux.org/packages/.all/dialog-1:1.3_20220414-1-x86_64.pkg.tar.zst', # noqa: B950 'version': '1:1.3_20220414-1'} """ rex = re.compile(r"^\%(?P\w+)\%\n(?P.*)\n$", re.M) with path.open("rb") as content: parsed = rex.findall(content.read().decode()) data = {entry[0].lower(): entry[1] for entry in parsed} if "url" in data.keys(): data["project_url"] = data["url"] assert data["name"] assert data["filename"] assert data["arch"] data["repo"] = repo data["url"] = urljoin( base_url, dl_url_fmt.format( base_url=base_url, pkgname=data["name"], filename=data["filename"], arch=data["arch"], repo=repo, ), ) assert data["md5sum"] assert data["sha256sum"] data["checksums"] = { "md5sum": hash_to_hex(data["md5sum"]), "sha256sum": hash_to_hex(data["sha256sum"]), } return data def get_pages(self) -> Iterator[ArchListerPage]: """Yield an iterator sorted by name in ascending order of pages. Each page is a list of package belonging to a flavour ('official', 'arm'), and a repo ('core', 'extra', 'community') """ for name, flavour in self.flavours.items(): for arch in flavour["archs"]: for repo in flavour["repos"]: yield self._get_repo_page(name, flavour, arch, repo) def _get_repo_page( self, name: str, flavour: Dict[str, Any], arch: str, repo: str ) -> ArchListerPage: - page = [] - if name == "official": - prefix = urljoin(flavour["base_archive_url"], "/repos/last/") - filename = f"{repo}.files.tar.gz" - archive_url = urljoin(prefix, f"{repo}/os/{arch}/{filename}") - destination_path = Path(self.DESTINATION_PATH, arch, filename) - base_url = flavour["base_archive_url"] - dl_url_fmt = self.ARCH_PACKAGE_DOWNLOAD_URL_PATTERN - base_info_url = flavour["base_info_url"] - info_url_fmt = self.ARCH_PACKAGE_URL_PATTERN - elif name == "arm": - filename = f"{repo}.files.tar.gz" - archive_url = urljoin( - flavour["base_mirror_url"], f"{arch}/{repo}/{filename}" + with tempfile.TemporaryDirectory() as tmpdir: + page = [] + if name == "official": + prefix = urljoin(flavour["base_archive_url"], "/repos/last/") + filename = f"{repo}.files.tar.gz" + archive_url = urljoin(prefix, f"{repo}/os/{arch}/{filename}") + destination_path = Path(tmpdir, arch, filename) + base_url = flavour["base_archive_url"] + dl_url_fmt = self.ARCH_PACKAGE_DOWNLOAD_URL_PATTERN + base_info_url = flavour["base_info_url"] + info_url_fmt = self.ARCH_PACKAGE_URL_PATTERN + elif name == "arm": + filename = f"{repo}.files.tar.gz" + archive_url = urljoin( + flavour["base_mirror_url"], f"{arch}/{repo}/{filename}" + ) + destination_path = Path(tmpdir, arch, filename) + base_url = flavour["base_mirror_url"] + dl_url_fmt = self.ARM_PACKAGE_DOWNLOAD_URL_PATTERN + base_info_url = flavour["base_info_url"] + info_url_fmt = self.ARM_PACKAGE_URL_PATTERN + + archive = self.get_repo_archive( + url=archive_url, destination_path=destination_path ) - destination_path = Path(self.DESTINATION_PATH, arch, filename) - base_url = flavour["base_mirror_url"] - dl_url_fmt = self.ARM_PACKAGE_DOWNLOAD_URL_PATTERN - base_info_url = flavour["base_info_url"] - info_url_fmt = self.ARM_PACKAGE_URL_PATTERN - - archive = self.get_repo_archive( - url=archive_url, destination_path=destination_path - ) - - assert archive - - packages_desc = list(archive.glob("**/desc")) - logger.debug( - "Processing %(instance)s source packages info from " - "%(flavour)s %(arch)s %(repo)s repository, " - "(%(qty)s packages).", - dict( - instance=self.instance, - flavour=name, - arch=arch, - repo=repo, - qty=len(packages_desc), - ), - ) - for package_desc in packages_desc: - data = self.parse_desc_file( - path=package_desc, - repo=repo, - base_url=base_url, - dl_url_fmt=dl_url_fmt, + assert archive + + packages_desc = list(archive.glob("**/desc")) + logger.debug( + "Processing %(instance)s source packages info from " + "%(flavour)s %(arch)s %(repo)s repository, " + "(%(qty)s packages).", + dict( + instance=self.instance, + flavour=name, + arch=arch, + repo=repo, + qty=len(packages_desc), + ), ) - assert data["builddate"] - last_modified = datetime.datetime.fromtimestamp( - float(data["builddate"]), tz=datetime.timezone.utc - ) + for package_desc in packages_desc: + data = self.parse_desc_file( + path=package_desc, + repo=repo, + base_url=base_url, + dl_url_fmt=dl_url_fmt, + ) - assert data["name"] - assert data["filename"] - assert data["arch"] - url = info_url_fmt.format( - base_url=base_info_url, - pkgname=data["name"], - filename=data["filename"], - repo=repo, - arch=data["arch"], - ) + assert data["builddate"] + last_modified = datetime.datetime.fromtimestamp( + float(data["builddate"]), tz=datetime.timezone.utc + ) - assert data["version"] - if name == "official": - # find all versions of a package scrapping archive - versions = self.scrap_package_versions( - name=data["name"], repo=repo, base_url=base_url + assert data["name"] + assert data["filename"] + assert data["arch"] + url = info_url_fmt.format( + base_url=base_info_url, + pkgname=data["name"], + filename=data["filename"], + repo=repo, + arch=data["arch"], ) - elif name == "arm": - # There is no way to get related versions of a package, - # but 'data' represents the latest released version, - # use it in this case - assert data["builddate"] - assert data["csize"] - assert data["url"] - versions = [ - dict( - name=data["name"], - version=data["version"], - repo=repo, - arch=data["arch"], - filename=data["filename"], - url=data["url"], - last_modified=last_modified.replace(tzinfo=None).isoformat( - timespec="seconds" - ), - length=int(data["csize"]), - ) - ] - package = { - "name": data["name"], - "version": data["version"], - "last_modified": last_modified, - "url": url, - "versions": versions, - "data": data, - } - page.append(package) - return page + assert data["version"] + if name == "official": + # find all versions of a package scrapping archive + versions = self.scrap_package_versions( + name=data["name"], repo=repo, base_url=base_url + ) + elif name == "arm": + # There is no way to get related versions of a package, + # but 'data' represents the latest released version, + # use it in this case + assert data["builddate"] + assert data["csize"] + assert data["url"] + versions = [ + dict( + name=data["name"], + version=data["version"], + repo=repo, + arch=data["arch"], + filename=data["filename"], + url=data["url"], + last_modified=last_modified.replace(tzinfo=None).isoformat( + timespec="seconds" + ), + length=int(data["csize"]), + ) + ] + + package = { + "name": data["name"], + "version": data["version"], + "last_modified": last_modified, + "url": url, + "versions": versions, + "data": data, + } + page.append(package) + return page def get_origins_from_page(self, page: ArchListerPage) -> Iterator[ListedOrigin]: """Iterate on all arch pages and yield ListedOrigin instances.""" assert self.lister_obj.id is not None for origin in page: artifacts = [] arch_metadata = [] for version in origin["versions"]: artifacts.append( { "version": version["version"], "filename": version["filename"], "url": version["url"], "length": version["length"], } ) arch_metadata.append( { "version": version["version"], "name": version["name"], "arch": version["arch"], "repo": version["repo"], "last_modified": version["last_modified"], } ) yield ListedOrigin( lister_id=self.lister_obj.id, visit_type=self.VISIT_TYPE, url=origin["url"], last_update=origin["last_modified"], extra_loader_arguments={ "artifacts": artifacts, "arch_metadata": arch_metadata, }, ) diff --git a/swh/lister/golang/lister.py b/swh/lister/golang/lister.py index 0d6b2b9..0a2f141 100644 --- a/swh/lister/golang/lister.py +++ b/swh/lister/golang/lister.py @@ -1,188 +1,188 @@ # Copyright (C) 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 dataclasses import dataclass from datetime import datetime import json import logging from typing import Any, Dict, Iterator, List, Optional, Tuple import iso8601 import requests from tenacity import before_sleep_log from swh.lister.utils import retry_policy_generic, throttling_retry from swh.scheduler.interface import SchedulerInterface from swh.scheduler.model import ListedOrigin from .. import USER_AGENT from ..pattern import CredentialsType, Lister logger = logging.getLogger(__name__) @dataclass class GolangStateType: last_seen: Optional[datetime] = None """Last timestamp of a package version we have saved. Used as a starting point for an incremental listing.""" GolangPageType = List[Dict[str, Any]] class GolangLister(Lister[GolangStateType, GolangPageType]): """ List all Golang modules and send associated origins to scheduler. The lister queries the Golang module index, whose documentation can be found at https://index.golang.org """ GOLANG_MODULES_INDEX_URL = "https://index.golang.org/index" # `limit` seems to be... limited to 2000. GOLANG_MODULES_INDEX_LIMIT = 2000 - LISTER_NAME = "Golang" + LISTER_NAME = "golang" def __init__( self, scheduler: SchedulerInterface, incremental: bool = False, credentials: CredentialsType = None, ): super().__init__( scheduler=scheduler, url=self.GOLANG_MODULES_INDEX_URL, - instance="Golang", + instance=self.LISTER_NAME, credentials=credentials, ) self.session = requests.Session() self.session.headers.update( {"Accept": "application/json", "User-Agent": USER_AGENT} ) self.incremental = incremental def state_from_dict(self, d: Dict[str, Any]) -> GolangStateType: as_string = d.get("last_seen") last_seen = iso8601.parse_date(as_string) if as_string is not None else None return GolangStateType(last_seen=last_seen) def state_to_dict(self, state: GolangStateType) -> Dict[str, Any]: return { "last_seen": state.last_seen.isoformat() if state.last_seen is not None else None } def finalize(self): if self.incremental and self.state.last_seen is not None: scheduler_state = self.get_state_from_scheduler() if ( scheduler_state.last_seen is None or self.state.last_seen > scheduler_state.last_seen ): self.updated = True @throttling_retry( retry=retry_policy_generic, before_sleep=before_sleep_log(logger, logging.WARNING), ) def api_request(self, url: str) -> List[str]: logger.debug("Fetching URL %s", url) response = self.session.get(url) if response.status_code not in (200, 304): # Log response content to ease debugging logger.warning( "Unexpected HTTP status code %s for URL %s", response.status_code, response.url, ) response.raise_for_status() return response.text.split() def get_single_page( self, since: Optional[datetime] = None ) -> Tuple[GolangPageType, Optional[datetime]]: """Return a page from the API and the timestamp of its last entry. Since all entries are sorted by chronological order, the timestamp is useful both for pagination and later for incremental runs.""" url = f"{self.url}?limit={self.GOLANG_MODULES_INDEX_LIMIT}" if since is not None: # The Golang index does not understand `+00:00` for some reason # and expects the "timezone zero" notation instead. This works # because all times are UTC. utc_offset = since.utcoffset() assert ( utc_offset is not None and utc_offset.total_seconds() == 0 ), "Non-UTC datetime" as_date = since.isoformat().replace("+00:00", "Z") url = f"{url}&since={as_date}" entries = self.api_request(url) page: GolangPageType = [] if not entries: return page, since for as_json in entries: entry = json.loads(as_json) timestamp = iso8601.parse_date(entry["Timestamp"]) # We've already parsed it and we'll need the datetime later, save it entry["Timestamp"] = timestamp page.append(entry) # The index is guaranteed to be sorted in chronological order since = timestamp return page, since def get_pages(self) -> Iterator[GolangPageType]: since = None if self.incremental: since = self.state.last_seen page, since = self.get_single_page(since=since) if since == self.state.last_seen: # The index returns packages whose timestamp are greater or # equal to the date provided as parameter, which will create # an infinite loop if not stopped here. return [], since if since is not None: self.state.last_seen = since while page: yield page page, since = self.get_single_page(since=since) if since == self.state.last_seen: return [], since if since is not None: self.state.last_seen = since def get_origins_from_page(self, page: GolangPageType) -> Iterator[ListedOrigin]: """ Iterate on all Golang projects and yield ListedOrigin instances. """ assert self.lister_obj.id is not None for module in page: path = module["Path"] # The loader will be expected to use the golang proxy to do the # actual downloading. We're using `pkg.go.dev` so that the URL points # to somewhere useful for a human instead of an (incomplete) API path. origin_url = f"https://pkg.go.dev/{path}" # Since the Go index lists versions and not just packages, there will # be duplicates. Fortunately, `ListedOrigins` are "upserted" server-side, # so only the last timestamp will be used, with no duplicates. # Performance should not be an issue as they are sent to the db in bulk. yield ListedOrigin( lister_id=self.lister_obj.id, url=origin_url, visit_type="golang", last_update=module["Timestamp"], ) diff --git a/swh/lister/pubdev/lister.py b/swh/lister/pubdev/lister.py index 8abb582..a17ad0e 100644 --- a/swh/lister/pubdev/lister.py +++ b/swh/lister/pubdev/lister.py @@ -1,125 +1,125 @@ # Copyright (C) 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 logging from typing import Any, Dict, Iterator, List, Optional import iso8601 import requests from requests.exceptions import HTTPError from tenacity.before_sleep import before_sleep_log from swh.lister.utils import throttling_retry from swh.scheduler.interface import SchedulerInterface from swh.scheduler.model import ListedOrigin from .. import __version__ from ..pattern import CredentialsType, StatelessLister # https://github.com/dart-lang/pub/blob/master/doc/repository-spec-v2.md#metadata-headers USER_AGENT = ( f"Software Heritage PubDev Lister v{__version__} " "(+https://www.softwareheritage.org/contact)" ) logger = logging.getLogger(__name__) # Aliasing the page results returned by `get_pages` method from the lister. PubDevListerPage = List[str] class PubDevLister(StatelessLister[PubDevListerPage]): """List pub.dev (Dart, Flutter) origins.""" LISTER_NAME = "pubdev" VISIT_TYPE = "pubdev" INSTANCE = "pubdev" BASE_URL = "https://pub.dev/" PACKAGE_NAMES_URL_PATTERN = "{base_url}api/package-names" PACKAGE_INFO_URL_PATTERN = "{base_url}api/packages/{pkgname}" ORIGIN_URL_PATTERN = "{base_url}packages/{pkgname}" def __init__( self, scheduler: SchedulerInterface, credentials: Optional[CredentialsType] = None, ): super().__init__( scheduler=scheduler, credentials=credentials, instance=self.INSTANCE, url=self.BASE_URL, ) self.session = requests.Session() self.session.headers.update( { "Accept": "application/json", "User-Agent": USER_AGENT, } ) @throttling_retry(before_sleep=before_sleep_log(logger, logging.WARNING)) def page_request(self, url: str, params: Dict[str, Any]) -> requests.Response: - logger.info("Fetching URL %s with params %s", url, params) + logger.debug("Fetching URL %s with params %s", url, params) response = self.session.get(url, params=params) if response.status_code != 200: logger.warning( "Unexpected HTTP status code %s on %s: %s", response.status_code, response.url, response.content, ) response.raise_for_status() return response def get_pages(self) -> Iterator[PubDevListerPage]: """Yield an iterator which returns 'page' It uses the api provided by https://pub.dev/api/ to find Dart and Flutter package origins. The http api call get "{base_url}package-names" to retrieve a sorted list of all package names. There is only one page that list all origins url based on "{base_url}packages/{pkgname}" """ response = self.page_request( url=self.PACKAGE_NAMES_URL_PATTERN.format(base_url=self.url), params={} ) yield response.json()["packages"] def get_origins_from_page(self, page: PubDevListerPage) -> Iterator[ListedOrigin]: """Iterate on all pages and yield ListedOrigin instances.""" assert self.lister_obj.id is not None for pkgname in page: package_info_url = self.PACKAGE_INFO_URL_PATTERN.format( base_url=self.url, pkgname=pkgname ) try: response = self.page_request(url=package_info_url, params={}) except HTTPError: logger.warning( "Failed to fetch metadata for package %s, skipping it from listing.", pkgname, ) continue package_metadata = response.json() package_versions = package_metadata["versions"] last_published = max( package_version["published"] for package_version in package_versions ) origin_url = self.ORIGIN_URL_PATTERN.format( base_url=self.url, pkgname=pkgname ) yield ListedOrigin( lister_id=self.lister_obj.id, visit_type=self.VISIT_TYPE, url=origin_url, last_update=iso8601.parse_date(last_published), )