diff --git a/debian/control b/debian/control index bf63c944..004b80cf 100644 --- a/debian/control +++ b/debian/control @@ -1,41 +1,41 @@ Source: swh-deposit Maintainer: Software Heritage developers Section: python Priority: optional Build-Depends: debhelper (>= 9), dh-python (>= 2), python3-setuptools, python3-all, python3-nose, python3-django-nose, python3-vcversioner, python3-swh.core (>= 0.0.36~), - python3-swh.loader.core (>= 0.0.26~), + python3-swh.loader.core (>= 0.0.27~), python3-swh.loader.tar (>= 0.0.32~), python3-swh.scheduler (>= 0.0.19~), python3-django, python3-click, python3-vcversioner, python3-djangorestframework, python3-djangorestframework-xml, python3-requests Standards-Version: 3.9.6 Homepage: https://forge.softwareheritage.org/source/swh-deposit/ Package: python3-swh.deposit Architecture: all Depends: python3-swh.core (>= 0.0.36~), python3-swh.scheduler (>= 0.0.19~), ${misc:Depends}, ${python3:Depends} Description: Software Heritage Deposit Server Package: python3-swh.deposit.loader Conflict: python3-swh.deposit.injection Architecture: all Depends: python3-swh.core (>= 0.0.36~), - python3-swh.loader.core (>= 0.0.26~), + python3-swh.loader.core (>= 0.0.27~), python3-swh.loader.tar (>= 0.0.32~), python3-swh.scheduler (>= 0.0.19~), python3-requests, ${misc:Depends}, ${python3:Depends} Description: Software Heritage Deposit Loader diff --git a/requirements-swh.txt b/requirements-swh.txt index cc996a85..0f21a5f2 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,4 +1,4 @@ swh.core >= 0.0.36 swh.loader.tar >= 0.0.32 -swh.loader.core >= 0.0.26 +swh.loader.core >= 0.0.27 swh.scheduler >= 0.0.19 diff --git a/swh/deposit/api/private/deposit_read.py b/swh/deposit/api/private/deposit_read.py index 3413419a..20b24a32 100644 --- a/swh/deposit/api/private/deposit_read.py +++ b/swh/deposit/api/private/deposit_read.py @@ -1,228 +1,228 @@ # Copyright (C) 2017 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 json import os import shutil import tempfile from contextlib import contextmanager from django.http import FileResponse from rest_framework import status from swh.core import tarball from swh.model import identifiers from ...config import SWH_PERSON from ..common import SWHGetDepositAPI, SWHPrivateAPIView from ...models import Deposit, DepositRequest @contextmanager def aggregate_tarballs(extraction_dir, archive_paths): """Aggregate multiple tarballs into one and returns this new archive's path. Args: extraction_dir (path): Path to use for the tarballs computation archive_paths ([str]): Deposit's archive paths Returns: Tuple (directory to clean up, archive path (aggregated or not)) """ if len(archive_paths) > 1: # need to rebuild one archive # from multiple ones os.makedirs(extraction_dir, 0o755, exist_ok=True) dir_path = tempfile.mkdtemp(prefix='swh.deposit-', dir=extraction_dir) # root folder to build an aggregated tarball aggregated_tarball_rootdir = os.path.join(dir_path, 'aggregate') os.makedirs(aggregated_tarball_rootdir, 0o755, exist_ok=True) # uncompress in a temporary location all archives for archive_path in archive_paths: tarball.uncompress(archive_path, aggregated_tarball_rootdir) # Aggregate into one big tarball the multiple smaller ones temp_tarpath = tarball.compress( aggregated_tarball_rootdir + '.zip', nature='zip', dirpath_or_files=aggregated_tarball_rootdir) # can already clean up temporary directory shutil.rmtree(aggregated_tarball_rootdir) try: yield temp_tarpath finally: shutil.rmtree(dir_path) else: # only 1 archive, no need to do fancy actions (and no cleanup step) yield archive_paths[0] class SWHDepositReadArchives(SWHGetDepositAPI, SWHPrivateAPIView): """Dedicated class to read a deposit's raw archives content. Only GET is supported. """ ADDITIONAL_CONFIG = { 'extraction_dir': ('str', '/tmp/swh-deposit/archive/'), } def __init__(self): super().__init__() self.extraction_dir = self.config['extraction_dir'] if not os.path.exists(self.extraction_dir): os.makedirs(self.extraction_dir) def retrieve_archives(self, deposit_id): """Given a deposit identifier, returns its associated archives' path. Yields: path to deposited archives """ deposit = Deposit.objects.get(pk=deposit_id) deposit_requests = DepositRequest.objects.filter( deposit=deposit, type=self.deposit_request_types['archive']).order_by('id') for deposit_request in deposit_requests: yield deposit_request.archive.path def process_get(self, req, collection_name, deposit_id): """Build a unique tarball from the multiple received and stream that content to the client. Args: req (Request): collection_name (str): Collection owning the deposit deposit_id (id): Deposit concerned by the reading Returns: Tuple status, stream of content, content-type """ archive_paths = list(self.retrieve_archives(deposit_id)) with aggregate_tarballs(self.extraction_dir, archive_paths) as path: return FileResponse(open(path, 'rb'), status=status.HTTP_200_OK, content_type='application/octet-stream') class SWHDepositReadMetadata(SWHGetDepositAPI, SWHPrivateAPIView): """Class in charge of aggregating metadata on a deposit. """ ADDITIONAL_CONFIG = { 'provider': ('dict', { # 'provider_name': '', # those are not set since read from the # 'provider_url': '', # deposit's client 'provider_type': 'deposit_client', 'metadata': {} }), 'tool': ('dict', { - 'tool_name': 'swh-deposit', - 'tool_version': '0.0.1', - 'tool_configuration': { + 'name': 'swh-deposit', + 'version': '0.0.1', + 'configuration': { 'sword_version': '2' } }) } def __init__(self): super().__init__() self.provider = self.config['provider'] self.tool = self.config['tool'] def _aggregate_metadata(self, deposit, metadata_requests): """Retrieve and aggregates metadata information. """ metadata = {} for req in metadata_requests: metadata.update(req.metadata) return metadata def aggregate(self, deposit, requests): """Aggregate multiple data on deposit into one unified data dictionary. Args: deposit (Deposit): Deposit concerned by the data aggregation. requests ([DepositRequest]): List of associated requests which need aggregation. Returns: Dictionary of data representing the deposit to inject in swh. """ data = {} # Retrieve tarballs/metadata information metadata = self._aggregate_metadata(deposit, requests) # Read information metadata data['origin'] = { 'type': 'deposit', 'url': os.path.join(deposit.client.url.rstrip('/'), deposit.external_id), } # revision fullname = deposit.client.get_full_name() author_committer = SWH_PERSON # metadata provider self.provider['provider_name'] = deposit.client.last_name self.provider['provider_url'] = deposit.client.url revision_type = 'tar' revision_msg = '%s: Deposit %s in collection %s' % ( fullname, deposit.id, deposit.collection.name) complete_date = identifiers.normalize_timestamp(deposit.complete_date) data['revision'] = { 'synthetic': True, 'date': complete_date, 'committer_date': complete_date, 'author': author_committer, 'committer': author_committer, 'type': revision_type, 'message': revision_msg, 'metadata': metadata, } if deposit.parent: parent_revision = deposit.parent.swh_id data['revision']['parents'] = [parent_revision] data['occurrence'] = { 'branch': 'master' } data['origin_metadata'] = { 'provider': self.provider, 'tool': self.tool, 'metadata': metadata } return data def process_get(self, req, collection_name, deposit_id): deposit = Deposit.objects.get(pk=deposit_id) requests = DepositRequest.objects.filter( deposit=deposit, type=self.deposit_request_types['metadata']) data = self.aggregate(deposit, requests) d = {} if data: d = json.dumps(data) return status.HTTP_200_OK, d, 'application/json'