diff --git a/debian/control b/debian/control index f933007..670467b 100644 --- a/debian/control +++ b/debian/control @@ -1,24 +1,24 @@ Source: swh-indexer Maintainer: Software Heritage developers Section: python Priority: optional Build-Depends: debhelper (>= 9), dh-python, python3-all, python3-nose, python3-setuptools, python3-swh.core (>= 0.0.27~), - python3-swh.storage (>= 0.0.69~), + python3-swh.storage (>= 0.0.70~), python3-swh.objstorage (>= 0.0.13~), python3-swh.scheduler (>= 0.0.9~), python3-chardet (>= 2.3.0~), python3-click, python3-pygments, python3-vcversioner Standards-Version: 3.9.6 Homepage: https://forge.softwareheritage.org/diffusion/78/ Package: python3-swh.indexer Architecture: all Depends: universal-ctags (>= 0.8~), ${misc:Depends}, ${python3:Depends} Description: Software Heritage Content Indexer diff --git a/requirements.txt b/requirements.txt index fa37ebe..c00e8a9 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,12 +1,12 @@ # Add here external Python modules dependencies, one per line. Module names # should match https://pypi.python.org/pypi names. For the full spec or # dependency lines, see https://pip.readthedocs.org/en/1.1/requirements.html vcversioner pygments click chardet swh.core >= 0.0.27 -swh.storage >= 0.0.69 +swh.storage >= 0.0.70 swh.objstorage >= 0.0.13 swh.scheduler >= 0.0.9 diff --git a/swh/indexer/license.py b/swh/indexer/license.py index 5ee2e3d..8091677 100644 --- a/swh/indexer/license.py +++ b/swh/indexer/license.py @@ -1,119 +1,119 @@ # Copyright (C) 2016 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 click import subprocess from swh.core import hashutil from .indexer import BaseIndexer, DiskIndexer def compute_license(tool, path): """Determine license from file at path. Args: path: filepath to determine the license Returns: A dict with 'licenses' and 'path' key and corresponding values. """ properties = subprocess.check_output([tool, path]) if properties: res = properties.rstrip().split(b' contains license(s) ') licenses = res[1].split(b',') if licenses == [b'No_license_found']: licenses = [] return { 'licenses': licenses, 'path': path } class ContentLicenseIndexer(BaseIndexer, DiskIndexer): """Indexer in charge of: - filtering out content already indexed - reading content from objstorage per the content's id (sha1) - computing {license, encoding} from that content - store result in storage """ ADDITIONAL_CONFIG = { 'workdir': ('str', '/tmp/swh/indexer.license'), 'tool': ('str', '/usr/local/bin/nomossa') } CONFIG_BASE_FILENAME = 'indexer/license' def __init__(self): super().__init__() self.working_directory = self.config['workdir'] self.tool = self.config['tool'] def filter_contents(self, sha1s): """Filter out known sha1s and return only missing ones. """ - # yield from self.storage.content_license_missing(sha1s) - pass + yield from self.storage.content_license_missing(sha1s) def index_content(self, sha1, content): """Index sha1s' content and store result. Args: sha1 (bytes): content's identifier content (bytes): raw content in bytes Returns: A dict, representing a content_license, with keys: - id (bytes): content's identifier (sha1) - license (bytes): license in bytes - path (bytes): path """ filename = hashutil.hash_to_hex(sha1) content_path = self.write_to_temp( filename=filename, data=content) properties = compute_license(self.tool, path=content_path) properties.update({ 'id': sha1, }) + self.log.info('Licenses: %s' % properties['licenses']) + self.cleanup(content_path) return properties def persist_index_computations(self, results, policy_update): """Persist the results in storage. Args: results ([dict]): list of content_license, dict with the following keys: - id (bytes): content's identifier (sha1) - license (bytes): license in bytes - path (bytes): path policy_update ([str]): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them """ - pass - # self.storage.content_license_add( - # results, conflict_update=(policy_update == 'update-dups')) + self.storage.content_license_add( + results, conflict_update=(policy_update == 'update-dups')) @click.command(help='Compute license for path using tool') @click.option('--tool', default='nomossa', help="Path to tool") @click.option('--path', required=1, help="Path to execute index on") def main(tool, path): print(compute_license(tool, path)) if __name__ == '__main__': main()