diff --git a/README.md b/README.md index afe94f8..acc86e2 100644 --- a/README.md +++ b/README.md @@ -1,219 +1,232 @@ 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.debian` - `swh.lister.github` - `swh.lister.gitlab` - `swh.lister.gnu` - `swh.lister.pypi` - `swh.lister.npm` - `swh.lister.phabricator` - `swh.lister.cran` 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 (`github`, `gitlab`, `debian`, `pypi`, `npm`) 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/ ~/.cache/swh/lister//` 2. create configuration file `~/.config/swh/lister_.yml` 3. Bootstrap the db instance schema ```lang=bash $ createdb lister- $ python3 -m swh.lister.cli --db-url postgres:///lister- ``` Note: This bootstraps a minimum data set needed for the lister to run. ### Configuration file sample Minimalistic configuration shared by all listers to add in file `~/.config/swh/lister_.yml`: ```lang=yml storage: cls: 'remote' args: url: 'http://localhost:5002/' scheduler: cls: 'remote' args: url: 'http://localhost:5008/' lister: cls: 'local' args: # see http://docs.sqlalchemy.org/en/latest/core/engines.html#database-urls db: 'postgresql:///lister-' credentials: [] cache_responses: True cache_dir: /home/user/.cache/swh/lister// ``` Note: This expects storage (5002) and scheduler (5008) services to run locally ## lister-github Once configured, you can execute a GitHub lister using the following instructions in a `python3` script: ```lang=python import logging from swh.lister.github.tasks import range_github_lister logging.basicConfig(level=logging.DEBUG) range_github_lister(364, 365) ... ``` ## lister-gitlab Once configured, you can execute a GitLab lister using the instructions detailed in the `python3` scripts below: ```lang=python import logging from swh.lister.gitlab.tasks import range_gitlab_lister logging.basicConfig(level=logging.DEBUG) range_gitlab_lister(1, 2, { 'instance': 'debian', 'api_baseurl': 'https://salsa.debian.org/api/v4', 'sort': 'asc', 'per_page': 20 }) ``` ```lang=python import logging from swh.lister.gitlab.tasks import full_gitlab_relister logging.basicConfig(level=logging.DEBUG) full_gitlab_relister({ 'instance': '0xacab', 'api_baseurl': 'https://0xacab.org/api/v4', 'sort': 'asc', 'per_page': 20 }) ``` ```lang=python import logging from swh.lister.gitlab.tasks import incremental_gitlab_lister logging.basicConfig(level=logging.DEBUG) incremental_gitlab_lister({ 'instance': 'freedesktop.org', 'api_baseurl': 'https://gitlab.freedesktop.org/api/v4', 'sort': 'asc', 'per_page': 20 }) ``` ## lister-debian Once configured, you can execute a Debian lister using the following instructions in a `python3` script: ```lang=python import logging from swh.lister.debian.tasks import debian_lister logging.basicConfig(level=logging.DEBUG) debian_lister('Debian') ``` ## lister-pypi Once configured, you can execute a PyPI lister using the following instructions in a `python3` script: ```lang=python import logging from swh.lister.pypi.tasks import pypi_lister logging.basicConfig(level=logging.DEBUG) pypi_lister() ``` ## lister-npm Once configured, you can execute a npm lister using the following instructions in a `python3` REPL: ```lang=python import logging from swh.lister.npm.tasks import npm_lister logging.basicConfig(level=logging.DEBUG) npm_lister() ``` ## lister-phabricator Once configured, you can execute a Phabricator lister using the following instructions in a `python3` script: ```lang=python import logging from swh.lister.phabricator.tasks import incremental_phabricator_lister logging.basicConfig(level=logging.DEBUG) incremental_phabricator_lister(forge_url='https://forge.softwareheritage.org', api_token='XXXX') ``` ## lister-gnu Once configured, you can execute a PyPI lister using the following instructions in a `python3` script: ```lang=python import logging from swh.lister.gnu.tasks import gnu_lister logging.basicConfig(level=logging.DEBUG) gnu_lister() ``` ## lister-cran Once configured, you can execute a CRAN lister using the following instructions in a `python3` script: ```lang=python import logging from swh.lister.cran.tasks import cran_lister logging.basicConfig(level=logging.DEBUG) cran_lister() ``` +## lister-cgit + +Once configured, you can execute a cgit lister using the following instructions +in a `python3` script: + +```lang=python +import logging +from swh.lister.cgit.tasks import cgit_lister + +logging.basicConfig(level=logging.DEBUG) +cgit_lister(base_url='http://git.savannah.gnu.org/cgit/') +``` + 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/requirements.txt b/requirements.txt index 3ad87c4..51e86f4 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,8 @@ SQLAlchemy arrow python_debian requests setuptools xmltodict iso8601 +beautifulsoup4 diff --git a/swh/lister/cgit/__init__.py b/swh/lister/cgit/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/swh/lister/cgit/lister.py b/swh/lister/cgit/lister.py new file mode 100644 index 0000000..a16f922 --- /dev/null +++ b/swh/lister/cgit/lister.py @@ -0,0 +1,180 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +import random +from bs4 import BeautifulSoup +from collections import defaultdict +import requests +import urllib.parse + +from .models import CGitModel + +from swh.lister.core.simple_lister import SimpleLister +from swh.lister.core.lister_transports import ListerOnePageApiTransport + + +class CGitLister(ListerOnePageApiTransport, SimpleLister): + MODEL = CGitModel + LISTER_NAME = 'cgit' + PAGE = '' + + def __init__(self, base_url, instance=None, override_config=None): + if not base_url.endswith('/'): + base_url = base_url+'/' + self.PAGE = base_url + + # This part removes any suffix from the base url and stores it in + # next_url. For example for base_url = https://git.kernel.org/pub/scm/ + # it will convert it into https://git.kernel.org and then attach + # the suffix + (part1, part2, next_url) = self.PAGE.split('/', 2) + self.next_url = part1 + '//' + next_url + + if not instance: + instance = urllib.parse.urlparse(base_url).hostname + self.instance = instance + ListerOnePageApiTransport .__init__(self) + SimpleLister.__init__(self, override_config=override_config) + + def list_packages(self, response): + """List the actual cgit instance origins from the response. + + """ + repos_details = [] + soup = BeautifulSoup(response.text, features="html.parser") \ + .find('div', {"class": "content"}) + repos = soup.find_all("tr", {"class": ""}) + for repo in repos: + repo_name = repo.a.text + repo_url = self.get_url(repo) + origin_url = find_origin_url(repo_url) + + try: + time = repo.span['title'] + except Exception: + time = None + + if origin_url is not None: + repos_details.append({ + 'name': repo_name, + 'time': time, + 'origin_url': origin_url, + }) + + random.shuffle(repos_details) + return repos_details + + def get_url(self, repo): + """Finds url of a repo page. + + Finds the url of a repo page by parsing over the html of the row of + that repo present in the base url. + + Args: + repo: a beautifulsoup object of the html code of the repo row + present in base url. + + Returns: + string: The url of a repo. + """ + suffix = repo.a['href'] + return self.next_url + suffix + + def get_model_from_repo(self, repo): + """Transform from repository representation to model. + + """ + return { + 'uid': self.PAGE + repo['name'], + 'name': repo['name'], + 'full_name': repo['name'], + 'html_url': repo['origin_url'], + 'origin_url': repo['origin_url'], + 'origin_type': 'git', + 'time_updated': repo['time'], + } + + def transport_response_simplified(self, response): + """Transform response to list for model manipulation. + + """ + return [self.get_model_from_repo(repo) for repo in response] + + +def find_origin_url(repo_url): + """Finds origin url for a repo. + + Finds the origin url for a particular repo by parsing over the page of + that repo. + + Args: + repo_url: URL of the repo. + + Returns: + string: Origin url for the repo. + + Examples: + + >>> find_origin_url( + 'http://git.savannah.gnu.org/cgit/fbvbconv-py.git/') + 'https://git.savannah.gnu.org/git/fbvbconv-py.git' + + """ + + response = requests.get(repo_url) + soup = BeautifulSoup(response.text, features="html.parser") + + origin_urls = find_all_origin_url(soup) + return priority_origin_url(origin_urls) + + +def find_all_origin_url(soup): + """ + Finds all the origin url for a particular repo by parsing over the html of + repo page. + + Args: + soup: a beautifulsoup object of the html code of the repo. + + Returns: + dictionary: All possible origin urls with their protocol as key. + + Examples: + If soup is beautifulsoup object of the html code at + http://git.savannah.gnu.org/cgit/fbvbconv-py.git/ + + >>> print(find_all_origin_url(soup)) + { 'https': 'https://git.savannah.gnu.org/git/fbvbconv-py.git', + 'ssh': 'ssh://git.savannah.gnu.org/srv/git/fbvbconv-py.git', + 'git': 'git://git.savannah.gnu.org/fbvbconv-py.git'} + """ + origin_urls = defaultdict(dict) + found_clone_word = False + + for i in soup.find_all('tr'): + if found_clone_word: + link = i.text + protocol = link[:link.find(':')] + origin_urls[protocol] = link + if i.text == 'Clone': + found_clone_word = True + + return origin_urls + + +def priority_origin_url(origin_url): + """Finds the highest priority link for a particular repo. + + Priority order is https>http>git>ssh. + + Args: + origin_urls: A dictionary of origin links with their protocol as key. + + Returns: + string: URL with the highest priority. + + """ + for protocol in ['https', 'http', 'git', 'ssh']: + if protocol in origin_url: + return origin_url[protocol] diff --git a/swh/lister/cgit/models.py b/swh/lister/cgit/models.py new file mode 100644 index 0000000..8ecf40f --- /dev/null +++ b/swh/lister/cgit/models.py @@ -0,0 +1,17 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from sqlalchemy import Column, String + +from ..core.models import ModelBase + + +class CGitModel(ModelBase): + """a CGit repository representation + + """ + __tablename__ = 'cgit_repo' + + uid = Column(String, primary_key=True) + time_updated = Column(String) diff --git a/swh/lister/cgit/tasks.py b/swh/lister/cgit/tasks.py new file mode 100644 index 0000000..af1ab63 --- /dev/null +++ b/swh/lister/cgit/tasks.py @@ -0,0 +1,23 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from swh.scheduler.celery_backend.config import app + +from .lister import CGitLister + + +def new_lister(base_url='https://git.savannah.gnu.org/cgit/', + instance='savannah-gnu', **kw): + return CGitLister(base_url=base_url, instance=instance, **kw) + + +@app.task(name=__name__ + '.CGitListerTask') +def cgit_lister(**lister_args): + lister = new_lister(**lister_args) + lister.run() + + +@app.task(name=__name__ + '.ping') +def ping(): + return 'OK' diff --git a/swh/lister/cgit/tests/__init__.py b/swh/lister/cgit/tests/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/swh/lister/cgit/tests/api_response.html b/swh/lister/cgit/tests/api_response.html new file mode 100644 index 0000000..1d34a4c --- /dev/null +++ b/swh/lister/cgit/tests/api_response.html @@ -0,0 +1,47 @@ + + + +fbvbconv-py.git - Unnamed repository; edit this file 'description' to name the repository. + + + + + + + + + + +
+ + + + +
+summaryrefslogtreecommitdiff
+ + + +
+
+
+ + + + + + + +
BranchCommit messageAuthorAge
masterinitial importJohannes Stezenbach2 years
 
 
AgeCommit messageAuthorFilesLines
2017-06-02initial importHEADmasterJohannes Stezenbach3-0/+889
 
Clone
git://git.savannah.gnu.org/fbvbconv-py.git
https://git.savannah.gnu.org/git/fbvbconv-py.git
ssh://git.savannah.gnu.org/srv/git/fbvbconv-py.git
+
generated by cgit v1.0-41-gc330 at 2019-06-19 10:51:46 +0000
+
+ + diff --git a/swh/lister/cgit/tests/conftest.py b/swh/lister/cgit/tests/conftest.py new file mode 100644 index 0000000..507fef9 --- /dev/null +++ b/swh/lister/cgit/tests/conftest.py @@ -0,0 +1 @@ +from swh.lister.core.tests.conftest import * # noqa diff --git a/swh/lister/cgit/tests/test_lister.py b/swh/lister/cgit/tests/test_lister.py new file mode 100644 index 0000000..600758a --- /dev/null +++ b/swh/lister/cgit/tests/test_lister.py @@ -0,0 +1,40 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + + +from bs4 import BeautifulSoup + +from swh.lister.cgit.lister import priority_origin_url, find_all_origin_url + + +def test_find_all_origin_url(): + f = open('swh/lister/cgit/tests/api_response.html') + soup = BeautifulSoup(f.read(), features="html.parser") + expected_output = {'https': 'https://git.savannah.gnu.org/git/' + 'fbvbconv-py.git', + 'ssh': 'ssh://git.savannah.gnu.org/srv/git/' + 'fbvbconv-py.git', + 'git': 'git://git.savannah.gnu.org/fbvbconv-py.git'} + + output = find_all_origin_url(soup) + + for protocol, url in expected_output.items(): + assert url == output[protocol] + + +def test_priority_origin_url(): + first_input = {'https': 'https://kernel.googlesource.com/pub/scm/docs/' + 'man-pages/man-pages.git', + 'git': 'git://git.kernel.org/pub/scm/docs/man-pages/' + 'man-pages.git'} + second_input = {'git': 'git://git.savannah.gnu.org/perl-pesel.git', + 'ssh': 'ssh://git.savannah.gnu.org/srv/git/perl-pesel.git'} + third_input = {} + + assert (priority_origin_url(first_input) == + 'https://kernel.googlesource.com/pub/scm/docs/man-pages/' + 'man-pages.git') + assert (priority_origin_url(second_input) == + 'git://git.savannah.gnu.org/perl-pesel.git') + assert priority_origin_url(third_input) is None diff --git a/swh/lister/cgit/tests/test_tasks.py b/swh/lister/cgit/tests/test_tasks.py new file mode 100644 index 0000000..b8faabc --- /dev/null +++ b/swh/lister/cgit/tests/test_tasks.py @@ -0,0 +1,29 @@ +from unittest.mock import patch + + +def test_ping(swh_app, celery_session_worker): + res = swh_app.send_task( + 'swh.lister.cgit.tasks.ping') + assert res + res.wait() + assert res.successful() + assert res.result == 'OK' + + +@patch('swh.lister.cgit.tasks.CGitLister') +def test_lister(lister, swh_app, celery_session_worker): + # setup the mocked CGitLister + lister.return_value = lister + lister.run.return_value = None + + res = swh_app.send_task( + 'swh.lister.cgit.tasks.CGitListerTask') + assert res + res.wait() + assert res.successful() + + lister.assert_called_once_with( + base_url='https://git.savannah.gnu.org/cgit/', + instance='savannah-gnu') + lister.db_last_index.assert_not_called() + lister.run.assert_called_once_with() diff --git a/swh/lister/cli.py b/swh/lister/cli.py index 6bf6801..bf5c439 100644 --- a/swh/lister/cli.py +++ b/swh/lister/cli.py @@ -1,150 +1,157 @@ # Copyright (C) 2018 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 click from swh.core.cli import CONTEXT_SETTINGS logger = logging.getLogger(__name__) SUPPORTED_LISTERS = ['github', 'gitlab', 'bitbucket', 'debian', 'pypi', - 'npm', 'phabricator', 'gnu', 'cran'] + 'npm', 'phabricator', 'gnu', 'cran', 'cgit'] @click.group(name='lister', context_settings=CONTEXT_SETTINGS) @click.pass_context def lister(ctx): '''Software Heritage Lister tools.''' pass @lister.command(name='db-init', context_settings=CONTEXT_SETTINGS) @click.option( '--db-url', '-d', default='postgres:///lister-gitlab.com', help='SQLAlchemy DB URL; see ' '') # noqa @click.argument('listers', required=1, nargs=-1, type=click.Choice(SUPPORTED_LISTERS + ['all'])) @click.option('--drop-tables', '-D', is_flag=True, default=False, help='Drop tables before creating the database schema') @click.pass_context def cli(ctx, db_url, listers, drop_tables): """Initialize the database model for given listers. """ override_conf = { 'lister': { 'cls': 'local', 'args': {'db': db_url} } } if 'all' in listers: listers = SUPPORTED_LISTERS for lister in listers: logger.info('Initializing lister %s', lister) insert_minimum_data = None if lister == 'github': from .github.models import IndexingModelBase as ModelBase from .github.lister import GitHubLister _lister = GitHubLister( api_baseurl='https://api.github.com', override_config=override_conf) elif lister == 'bitbucket': from .bitbucket.models import IndexingModelBase as ModelBase from .bitbucket.lister import BitBucketLister _lister = BitBucketLister( api_baseurl='https://api.bitbucket.org/2.0', override_config=override_conf) elif lister == 'gitlab': from .gitlab.models import ModelBase from .gitlab.lister import GitLabLister _lister = GitLabLister( api_baseurl='https://gitlab.com/api/v4/', override_config=override_conf) elif lister == 'debian': from .debian.lister import DebianLister ModelBase = DebianLister.MODEL # noqa _lister = DebianLister(override_config=override_conf) def insert_minimum_data(lister): from swh.storage.schemata.distribution import ( Distribution, Area) d = Distribution( name='Debian', type='deb', mirror_uri='http://deb.debian.org/debian/') lister.db_session.add(d) areas = [] for distribution_name in ['stretch']: for area_name in ['main', 'contrib', 'non-free']: areas.append(Area( name='%s/%s' % (distribution_name, area_name), distribution=d, )) lister.db_session.add_all(areas) lister.db_session.commit() elif lister == 'pypi': from .pypi.models import ModelBase from .pypi.lister import PyPILister _lister = PyPILister(override_config=override_conf) elif lister == 'npm': from .npm.models import IndexingModelBase as ModelBase from .npm.models import NpmVisitModel from .npm.lister import NpmLister _lister = NpmLister(override_config=override_conf) if drop_tables: NpmVisitModel.metadata.drop_all(_lister.db_engine) NpmVisitModel.metadata.create_all(_lister.db_engine) elif lister == 'phabricator': from .phabricator.models import IndexingModelBase as ModelBase from .phabricator.lister import PhabricatorLister _lister = PhabricatorLister( forge_url='https://forge.softwareheritage.org', api_token='', override_config=override_conf) elif lister == 'gnu': from .gnu.models import ModelBase from .gnu.lister import GNULister _lister = GNULister(override_config=override_conf) elif lister == 'cran': from .cran.models import ModelBase from .cran.lister import CRANLister _lister = CRANLister(override_config=override_conf) + elif lister == 'cgit': + from .cgit.models import ModelBase + from .cgit.lister import CGitLister + _lister = CGitLister( + base_url='http://git.savannah.gnu.org/cgit/', + override_config=override_conf) + else: raise ValueError( 'Invalid lister %s: only supported listers are %s' % (lister, SUPPORTED_LISTERS)) if drop_tables: logger.info('Dropping tables for %s', lister) ModelBase.metadata.drop_all(_lister.db_engine) logger.info('Creating tables for %s', lister) ModelBase.metadata.create_all(_lister.db_engine) if insert_minimum_data: logger.info('Inserting minimal data for %s', lister) try: insert_minimum_data(_lister) except Exception: logger.warning( 'Failed to insert minimum data in %s', lister) if __name__ == '__main__': cli() diff --git a/swh/lister/core/tests/conftest.py b/swh/lister/core/tests/conftest.py index e241d27..b8dd868 100644 --- a/swh/lister/core/tests/conftest.py +++ b/swh/lister/core/tests/conftest.py @@ -1,17 +1,18 @@ import pytest from swh.scheduler.tests.conftest import * # noqa @pytest.fixture(scope='session') def celery_includes(): return [ 'swh.lister.bitbucket.tasks', + 'swh.lister.cgit.tasks', 'swh.lister.cran.tasks', 'swh.lister.debian.tasks', 'swh.lister.github.tasks', 'swh.lister.gitlab.tasks', 'swh.lister.gnu.tasks', 'swh.lister.npm.tasks', 'swh.lister.pypi.tasks', 'swh.lister.phabricator.tasks', ]