diff --git a/MANIFEST.in b/MANIFEST.in index 7ccb237..05c933e 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,7 +1,8 @@ include Makefile include README include requirements.txt include requirements-swh.txt include requirements-test.txt include version.txt +include swh/lister/cran/list_all_packages.R recursive-include swh/lister/*/tests/ *.json diff --git a/README.md b/README.md index 73dc022..b1f1609 100644 --- a/README.md +++ b/README.md @@ -1,206 +1,218 @@ 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 RCRAN 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() ``` 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. \ No newline at end of file diff --git a/swh/lister/cli.py b/swh/lister/cli.py index 22b520c..6bf6801 100644 --- a/swh/lister/cli.py +++ b/swh/lister/cli.py @@ -1,145 +1,150 @@ # 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'] + 'npm', 'phabricator', 'gnu', 'cran'] @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) + 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 94482e4..e241d27 100644 --- a/swh/lister/core/tests/conftest.py +++ b/swh/lister/core/tests/conftest.py @@ -1,16 +1,17 @@ import pytest from swh.scheduler.tests.conftest import * # noqa @pytest.fixture(scope='session') def celery_includes(): return [ 'swh.lister.bitbucket.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', ] diff --git a/swh/lister/cran/__init__.py b/swh/lister/cran/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/swh/lister/cran/list_all_packages.R b/swh/lister/cran/list_all_packages.R new file mode 100755 index 0000000..e2825f4 --- /dev/null +++ b/swh/lister/cran/list_all_packages.R @@ -0,0 +1,9 @@ +#!/usr/bin/Rscript + +# This R script calls the buildin API to get list of +# all the packages of R and their description, then convert the API +# response to JSON string and print it + +db <- tools::CRAN_package_db()[, c("Package", "Version", "Title", "Description")] +dbjson <- jsonlite::toJSON(db) +print(dbjson) \ No newline at end of file diff --git a/swh/lister/cran/lister.py b/swh/lister/cran/lister.py new file mode 100644 index 0000000..4277e14 --- /dev/null +++ b/swh/lister/cran/lister.py @@ -0,0 +1,119 @@ +# 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 subprocess +import json +import logging +import pkg_resources + +from swh.lister.cran.models import CRANModel + +from swh.scheduler.utils import create_task_dict +from swh.core import utils +from swh.lister.core.simple_lister import SimpleLister + + +class CRANLister(SimpleLister): + MODEL = CRANModel + LISTER_NAME = 'cran' + instance = 'cran' + + def task_dict(self, origin_type, origin_url, **kwargs): + """Return task format dict + + This is overridden from the lister_base as more information is + needed for the ingestion task creation. + """ + return create_task_dict( + 'load-%s' % origin_type, 'recurring', + kwargs.get('name'), origin_url, kwargs.get('version'), + project_metadata=kwargs.get('description')) + + def r_script_request(self): + """Runs R script which uses inbuilt API to return a json + response containing data about all the R packages + + Returns: + List of dictionaries + example + [ + {'Package': 'A3', + 'Version': '1.0.0', + 'Title': + 'Accurate, Adaptable, and Accessible Error Metrics for + Predictive\nModels', + 'Description': + 'Supplies tools for tabulating and analyzing the results + of predictive models. The methods employed are ... ' + } + {'Package': 'abbyyR', + 'Version': '0.5.4', + 'Title': + 'Access to Abbyy Optical Character Recognition (OCR) API', + 'Description': 'Get text from images of text using Abbyy + Cloud Optical Character\n ...' + } + ... + ] + """ + file_path = pkg_resources.resource_filename('swh.lister.cran', + 'list_all_packages.R') + response = subprocess.run(file_path, stdout=subprocess.PIPE, + shell=False) + return json.loads(response.stdout) + + def get_model_from_repo(self, repo): + """Transform from repository representation to model + + """ + project_url = 'https://cran.r-project.org/src/contrib' \ + '/%(Package)s_%(Version)s.tar.gz' % repo + return { + 'uid': repo["Package"], + 'name': repo["Package"], + 'full_name': repo["Title"], + 'version': repo["Version"], + 'html_url': project_url, + 'origin_url': project_url, + 'origin_type': 'cran', + 'description': repo["Description"] + } + + 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 ingest_data(self, identifier, checks=False): + """Rework the base ingest_data. + Request server endpoint which gives all in one go. + + Simplify and filter response list of repositories. Inject + repo information into local db. Queue loader tasks for + linked repositories. + + Args: + identifier: Resource identifier (unused) + checks (bool): Additional checks required (unused) + + """ + response = self.r_script_request() + if not response: + return response, [] + models_list = self.transport_response_simplified(response) + models_list = self.filter_before_inject(models_list) + all_injected = [] + for models in utils.grouper(models_list, n=10000): + models = list(models) + logging.debug('models: %s' % len(models)) + # inject into local db + injected = self.inject_repo_data_into_db(models) + # queue workers + self.create_missing_origins_and_tasks(models, injected) + all_injected.append(injected) + # flush + self.db_session.commit() + self.db_session = self.mk_session() + + return response, all_injected diff --git a/swh/lister/cran/models.py b/swh/lister/cran/models.py new file mode 100644 index 0000000..3fe94d9 --- /dev/null +++ b/swh/lister/cran/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 swh.lister.core.models import ModelBase + + +class CRANModel(ModelBase): + """a CRAN repository representation + + """ + __tablename__ = 'cran_repo' + + uid = Column(String, primary_key=True) + version = Column(String) diff --git a/swh/lister/cran/tasks.py b/swh/lister/cran/tasks.py new file mode 100644 index 0000000..f7098a1 --- /dev/null +++ b/swh/lister/cran/tasks.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 swh.scheduler.celery_backend.config import app + +from swh.lister.cran.lister import CRANLister + + +@app.task(name=__name__ + '.CRANListerTask') +def cran_lister(**lister_args): + CRANLister(**lister_args).run() + + +@app.task(name=__name__ + '.ping') +def ping(): + return 'OK' diff --git a/swh/lister/cran/tests/__init__.py b/swh/lister/cran/tests/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/swh/lister/cran/tests/conftest.py b/swh/lister/cran/tests/conftest.py new file mode 100644 index 0000000..507fef9 --- /dev/null +++ b/swh/lister/cran/tests/conftest.py @@ -0,0 +1 @@ +from swh.lister.core.tests.conftest import * # noqa diff --git a/swh/lister/cran/tests/test_tasks.py b/swh/lister/cran/tests/test_tasks.py new file mode 100644 index 0000000..1a0b95a --- /dev/null +++ b/swh/lister/cran/tests/test_tasks.py @@ -0,0 +1,27 @@ +from unittest.mock import patch + + +def test_ping(swh_app, celery_session_worker): + res = swh_app.send_task( + 'swh.lister.cran.tasks.ping') + assert res + res.wait() + assert res.successful() + assert res.result == 'OK' + + +@patch('swh.lister.cran.tasks.CRANLister') +def test_lister(lister, swh_app, celery_session_worker): + # setup the mocked CRANLister + lister.return_value = lister + lister.run.return_value = None + + res = swh_app.send_task( + 'swh.lister.cran.tasks.CRANListerTask') + assert res + res.wait() + assert res.successful() + + lister.assert_called_once_with() + lister.db_last_index.assert_not_called() + lister.run.assert_called_once_with()