diff --git a/PKG-INFO b/PKG-INFO index 2d53f760..eb6b26fa 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,10 +1,10 @@ Metadata-Version: 1.0 Name: swh.deposit -Version: 0.0.56 +Version: 0.0.57 Summary: Software Heritage Deposit Server Home-page: https://forge.softwareheritage.org/source/swh-deposit/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Description: UNKNOWN Platform: UNKNOWN diff --git a/bin/Makefile b/bin/Makefile index 03834dc2..7a8898ff 100644 --- a/bin/Makefile +++ b/bin/Makefile @@ -1,45 +1,45 @@ DEPOSIT_ID=1 ARCHIVE=../../swh-deposit.zip ARCHIVE2=../../swh-model.zip -STATUS=false -PARTIAL_STATUS=true +STATUS=--no-partial +PARTIAL_STATUS=--partial UPDATE_STATUS='done' ATOM_ENTRY=../../atom-entry.xml EXTERNAL_ID='external-id' create-archives: 7z a $(ARCHIVE) $(FOLDER) 7z a $(ARCHIVE2) $(FOLDER2) new: ./create_deposit.sh $(ARCHIVE) $(STATUS) new-complete: ./create_deposit_with_metadata.sh $(ARCHIVE) $(ATOM_ENTRY) $(STATUS) $(EXTERNAL_ID) new-partial: make new STATUS=$(PARTIAL_STATUS) ARCHIVE=$(ARCHIVE) update: ./update-deposit-with-another-archive.sh $(DEPOSIT_ID) $(ARCHIVE2) $(STATUS) update-partial: make update DEPOSIT_ID=$(DEPOSIT_ID) ARCHIVE2=$(ARCHIVE2) STATUS=$(PARTIAL_STATUS) replace: ./replace-deposit-archive.sh $(ARCHIVE2) $(DEPOSIT_ID) download: ./download-deposit-archive.sh $(DEPOSIT_ID) status: ./status.sh $(DEPOSIT_ID) service-document: ./service-document.sh home: ./home.sh update-status: ./update-status.sh $(DEPOSIT_ID) $(UPDATE_STATUS) diff --git a/bin/create_deposit.sh b/bin/create_deposit.sh index 183f114a..41e4010b 100755 --- a/bin/create_deposit.sh +++ b/bin/create_deposit.sh @@ -1,21 +1,16 @@ #!/usr/bin/env bash . ./default-setup ARCHIVE=${1-'../../deposit.zip'} -NAME=$(basename ${ARCHIVE}) -MD5=$(md5sum ${ARCHIVE} | cut -f 1 -d' ') +STATUS=${2-'--no-partial'} -PROGRESS=${2-'false'} -TYPE=${3-'application/zip'} - -curl -i -u "$CREDS" \ - -X POST \ - --data-binary @${ARCHIVE} \ - -H "In-Progress: ${PROGRESS}" \ - -H "Content-MD5: ${MD5}" \ - -H "Content-Disposition: attachment; filename=${NAME}" \ - -H 'Slug: external-id' \ - -H "Content-type: ${TYPE}" \ - ${SERVER}/1/${COLLECTION}/ +./swh-deposit \ + --username ${USER} \ + --password ${PASSWORD} \ + --collection ${COLLECTION} \ + --archive-deposit \ + --archive ${ARCHIVE} \ + ${STATUS} \ + --url ${SERVER}/1 diff --git a/bin/create_deposit_with_metadata.sh b/bin/create_deposit_with_metadata.sh index 92034750..d93a85bc 100755 --- a/bin/create_deposit_with_metadata.sh +++ b/bin/create_deposit_with_metadata.sh @@ -1,20 +1,21 @@ #!/usr/bin/env bash . ./default-setup ARCHIVE=${1-'../../swh-deposit.zip'} ATOM_ENTRY=${2-'../../atom-entry.xml'} -NAME=$(basename $ARCHIVE) -MD5=$(md5sum $ARCHIVE | cut -f 1 -d' ') - -PROGRESS=${3-'false'} +STATUS=${3-'--no-partial'} EXTERNAL_ID=${4-'external-id'} -set -x -curl -i --user "${CREDS}" \ - -H "In-Progress: ${PROGRESS}" \ - -H "Slug: ${EXTERNAL_ID}" \ - -F "file=@${ARCHIVE};type=application/zip" \ - -F "atom=@${ATOM_ENTRY};type=application/atom+xml;type=entry" \ - -XPOST ${SERVER}/1/${COLLECTION}/ +./swh-deposit \ + --username ${USER} \ + --password ${PASSWORD} \ + --collection ${COLLECTION} \ + --archive-deposit \ + --archive ${ARCHIVE} \ + --metadata-deposit \ + --metadata ${ATOM_ENTRY} \ + --slug ${EXTERNAL_ID} \ + ${STATUS} \ + --url ${SERVER}/1 diff --git a/bin/default-setup b/bin/default-setup index a8fccdca..c27054f9 100644 --- a/bin/default-setup +++ b/bin/default-setup @@ -1,3 +1,5 @@ SERVER=http://127.0.0.1:5006 -CREDS='hal:hal' +USER='hal' +PASSWORD='hal' COLLECTION=hal +CREDS="$USER:$PASSWORD" diff --git a/bin/status.sh b/bin/status.sh index 80687885..6d3662d1 100755 --- a/bin/status.sh +++ b/bin/status.sh @@ -1,7 +1,13 @@ #!/usr/bin/env bash . ./default-setup DEPOSIT_ID=${1-1} -curl -i -u "${CREDS}" ${SERVER}/1/${COLLECTION}/${DEPOSIT_ID}/status/ +./swh-deposit \ + --username ${USER} \ + --password ${PASSWORD} \ + --collection ${COLLECTION} \ + --status \ + --deposit-id ${DEPOSIT_ID} \ + --url ${SERVER}/1 diff --git a/debian/control b/debian/control index d9e6b216..381b7e14 100644 --- a/debian/control +++ b/debian/control @@ -1,56 +1,55 @@ 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.model (>= 0.0.25~), python3-swh.loader.core (>= 0.0.32~), python3-swh.loader.tar (>= 0.0.35~), python3-swh.scheduler (>= 0.0.26~), python3-django, python3-click, python3-vcversioner, python3-djangorestframework, python3-requests, - python3-lxml, python3-xmltodict, patool 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.model (>= 0.0.25~), python3-swh.scheduler (>= 0.0.26~), patool, ${misc:Depends}, ${python3:Depends} Description: Software Heritage Deposit Server Package: python3-swh.deposit.client Architecture: all Depends: python3-swh.core (>= 0.0.36~), python3-swh.model (>= 0.0.25~), python3-requests, - python3-lxml, + python3-xmltodict, ${misc:Depends}, ${python3:Depends} Description: Software Heritage Deposit Api Client Package: python3-swh.deposit.loader Conflict: python3-swh.deposit.injection Architecture: all Depends: python3-swh.deposit.client (= ${binary:Version}), python3-swh.core (>= 0.0.36~), python3-swh.model (>= 0.0.25~), python3-swh.loader.core (>= 0.0.32~), python3-swh.loader.tar (>= 0.0.35~), python3-swh.scheduler (>= 0.0.26~), ${misc:Depends}, ${python3:Depends} Description: Software Heritage Deposit Loader diff --git a/requirements.txt b/requirements.txt index b3db84ea..40c6d884 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,6 +1,5 @@ vcversioner click Django djangorestframework -lxml xmltodict diff --git a/swh.deposit.egg-info/PKG-INFO b/swh.deposit.egg-info/PKG-INFO index 2d53f760..eb6b26fa 100644 --- a/swh.deposit.egg-info/PKG-INFO +++ b/swh.deposit.egg-info/PKG-INFO @@ -1,10 +1,10 @@ Metadata-Version: 1.0 Name: swh.deposit -Version: 0.0.56 +Version: 0.0.57 Summary: Software Heritage Deposit Server Home-page: https://forge.softwareheritage.org/source/swh-deposit/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Description: UNKNOWN Platform: UNKNOWN diff --git a/swh.deposit.egg-info/SOURCES.txt b/swh.deposit.egg-info/SOURCES.txt index d3fa130b..7e2c8117 100644 --- a/swh.deposit.egg-info/SOURCES.txt +++ b/swh.deposit.egg-info/SOURCES.txt @@ -1,154 +1,156 @@ .gitignore AUTHORS LICENSE MANIFEST.in Makefile Makefile.local README.md requirements-swh.txt requirements.txt setup.py version.txt bin/Makefile bin/content.sh bin/create_deposit.sh bin/create_deposit_atom.sh bin/create_deposit_with_metadata.sh bin/default-setup bin/download-deposit-archive.sh bin/home.sh bin/replace-deposit-archive.sh bin/service-document.sh bin/status.sh bin/swh-deposit bin/update-deposit-with-another-archive.sh bin/update-status.sh debian/changelog debian/compat debian/control debian/copyright debian/rules debian/source/format docs/.gitignore docs/Makefile docs/blueprint.rst docs/conf.py docs/dev-info.rst docs/getting-started.rst docs/index.rst docs/metadata.rst docs/spec-api.rst docs/spec-loading.rst docs/sys-info.rst docs/_static/.placeholder docs/_templates/.placeholder docs/endpoints/collection.rst docs/endpoints/content.rst docs/endpoints/service-document.rst docs/endpoints/status.rst docs/endpoints/update-media.rst docs/endpoints/update-metadata.rst docs/images/deposit-create-chart.png docs/images/deposit-delete-chart.png docs/images/deposit-update-chart.png resources/deposit/server.yml swh/__init__.py swh/manage.py swh.deposit.egg-info/PKG-INFO swh.deposit.egg-info/SOURCES.txt swh.deposit.egg-info/dependency_links.txt swh.deposit.egg-info/requires.txt swh.deposit.egg-info/top_level.txt swh/deposit/__init__.py swh/deposit/apps.py swh/deposit/auth.py swh/deposit/config.py swh/deposit/create_user.py swh/deposit/errors.py swh/deposit/models.py swh/deposit/parsers.py swh/deposit/signals.py swh/deposit/urls.py swh/deposit/wsgi.py swh/deposit/api/__init__.py swh/deposit/api/common.py swh/deposit/api/deposit.py swh/deposit/api/deposit_content.py swh/deposit/api/deposit_status.py swh/deposit/api/deposit_update.py swh/deposit/api/service_document.py swh/deposit/api/urls.py swh/deposit/api/private/__init__.py swh/deposit/api/private/deposit_check.py swh/deposit/api/private/deposit_read.py swh/deposit/api/private/deposit_update_status.py swh/deposit/api/private/urls.py swh/deposit/client/__init__.py swh/deposit/client/cli.py swh/deposit/fixtures/__init__.py swh/deposit/fixtures/deposit_data.yaml swh/deposit/loader/__init__.py swh/deposit/loader/checker.py swh/deposit/loader/loader.py swh/deposit/loader/scheduler.py swh/deposit/loader/tasks.py swh/deposit/migrations/0001_initial.py swh/deposit/migrations/0002_depositrequest_archive.py swh/deposit/migrations/0003_temporaryarchive.py swh/deposit/migrations/0004_delete_temporaryarchive.py swh/deposit/migrations/0005_auto_20171019_1436.py swh/deposit/migrations/0006_depositclient_url.py swh/deposit/migrations/0007_auto_20171129_1609.py swh/deposit/migrations/0008_auto_20171130_1513.py swh/deposit/migrations/0009_deposit_parent.py swh/deposit/migrations/0010_auto_20180110_0953.py swh/deposit/migrations/0011_auto_20180115_1510.py swh/deposit/migrations/0012_deposit_status_detail.py +swh/deposit/migrations/0013_depositrequest_raw_metadata.py +swh/deposit/migrations/0014_auto_20180720_1221.py swh/deposit/migrations/__init__.py swh/deposit/settings/__init__.py swh/deposit/settings/common.py swh/deposit/settings/development.py swh/deposit/settings/production.py swh/deposit/settings/testing.py swh/deposit/static/robots.txt swh/deposit/static/css/bootstrap-responsive.min.css swh/deposit/static/css/style.css swh/deposit/static/img/arrow-up-small.png swh/deposit/static/img/swh-logo-deposit.png swh/deposit/static/img/swh-logo-deposit.svg swh/deposit/static/img/icons/swh-logo-32x32.png swh/deposit/static/img/icons/swh-logo-deposit-180x180.png swh/deposit/static/img/icons/swh-logo-deposit-192x192.png swh/deposit/static/img/icons/swh-logo-deposit-270x270.png swh/deposit/templates/__init__.py swh/deposit/templates/homepage.html swh/deposit/templates/layout.html swh/deposit/templates/deposit/__init__.py swh/deposit/templates/deposit/content.xml swh/deposit/templates/deposit/deposit_receipt.xml swh/deposit/templates/deposit/error.xml swh/deposit/templates/deposit/service_document.xml swh/deposit/templates/deposit/status.xml swh/deposit/templates/rest_framework/api.html swh/deposit/tests/__init__.py swh/deposit/tests/common.py swh/deposit/tests/api/__init__.py swh/deposit/tests/api/test_common.py swh/deposit/tests/api/test_deposit.py swh/deposit/tests/api/test_deposit_atom.py swh/deposit/tests/api/test_deposit_binary.py swh/deposit/tests/api/test_deposit_check.py swh/deposit/tests/api/test_deposit_delete.py swh/deposit/tests/api/test_deposit_multipart.py swh/deposit/tests/api/test_deposit_read_archive.py swh/deposit/tests/api/test_deposit_read_metadata.py swh/deposit/tests/api/test_deposit_status.py swh/deposit/tests/api/test_deposit_update.py swh/deposit/tests/api/test_deposit_update_status.py swh/deposit/tests/api/test_parser.py swh/deposit/tests/api/test_service_document.py swh/deposit/tests/loader/__init__.py swh/deposit/tests/loader/common.py swh/deposit/tests/loader/test_checker.py swh/deposit/tests/loader/test_client.py swh/deposit/tests/loader/test_loader.py \ No newline at end of file diff --git a/swh.deposit.egg-info/requires.txt b/swh.deposit.egg-info/requires.txt index 43355e1b..7f689b4e 100644 --- a/swh.deposit.egg-info/requires.txt +++ b/swh.deposit.egg-info/requires.txt @@ -1,11 +1,10 @@ Django click djangorestframework -lxml swh.core>=0.0.36 swh.loader.core>=0.0.32 swh.loader.tar>=0.0.35 swh.model>=0.0.25 swh.scheduler>=0.0.26 vcversioner xmltodict diff --git a/swh/deposit/api/common.py b/swh/deposit/api/common.py index e2574ea2..2694fd61 100644 --- a/swh/deposit/api/common.py +++ b/swh/deposit/api/common.py @@ -1,861 +1,883 @@ # Copyright (C) 2017-2018 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 hashlib from abc import ABCMeta, abstractmethod from django.core.urlresolvers import reverse from django.http import HttpResponse from django.shortcuts import render from django.utils import timezone from rest_framework import status from rest_framework.authentication import BasicAuthentication from rest_framework.permissions import IsAuthenticated, AllowAny from rest_framework.views import APIView from swh.model import hashutil -from ..config import SWHDefaultConfig, EDIT_SE_IRI, EM_IRI, CONT_FILE_IRI -from ..config import ARCHIVE_KEY, METADATA_KEY, STATE_IRI -from ..config import DEPOSIT_STATUS_DEPOSITED, DEPOSIT_STATUS_PARTIAL -from ..config import DEPOSIT_STATUS_LOAD_SUCCESS -from ..errors import MAX_UPLOAD_SIZE_EXCEEDED, BAD_REQUEST, ERROR_CONTENT -from ..errors import CHECKSUM_MISMATCH, make_error_dict, MEDIATION_NOT_ALLOWED -from ..errors import make_error_response_from_dict, FORBIDDEN -from ..errors import NOT_FOUND, make_error_response, METHOD_NOT_ALLOWED -from ..models import Deposit, DepositRequest, DepositCollection -from ..models import DepositRequestType, DepositClient +from ..config import ( + SWHDefaultConfig, EDIT_SE_IRI, EM_IRI, CONT_FILE_IRI, + ARCHIVE_KEY, METADATA_KEY, RAW_METADATA_KEY, STATE_IRI, + DEPOSIT_STATUS_DEPOSITED, DEPOSIT_STATUS_PARTIAL, + DEPOSIT_STATUS_LOAD_SUCCESS +) +from ..errors import ( + MAX_UPLOAD_SIZE_EXCEEDED, BAD_REQUEST, ERROR_CONTENT, + CHECKSUM_MISMATCH, make_error_dict, MEDIATION_NOT_ALLOWED, + make_error_response_from_dict, FORBIDDEN, + NOT_FOUND, make_error_response, METHOD_NOT_ALLOWED +) +from ..models import ( + Deposit, DepositRequest, DepositCollection, DepositRequestType, + DepositClient +) from ..parsers import parse_xml ACCEPT_PACKAGINGS = ['http://purl.org/net/sword/package/SimpleZip'] ACCEPT_ARCHIVE_CONTENT_TYPES = ['application/zip', 'application/x-tar'] class SWHAPIView(APIView): """Mixin intended as a based API view to enforce the basic authentication check """ authentication_classes = (BasicAuthentication, ) permission_classes = (IsAuthenticated, ) class SWHPrivateAPIView(SWHAPIView): """Mixin intended as private api (so no authentication) based API view (for the private ones). """ authentication_classes = () permission_classes = (AllowAny, ) class SWHBaseDeposit(SWHDefaultConfig, SWHAPIView, metaclass=ABCMeta): """Base deposit request class sharing multiple common behaviors. """ def __init__(self): super().__init__() deposit_request_types = DepositRequestType.objects.all() self.deposit_request_types = { type.name: type for type in deposit_request_types } def _read_headers(self, req): """Read and unify the necessary headers from the request (those are not stored in the same location or not properly formatted). Args: req (Request): Input request Returns: Dictionary with the following keys (some associated values may be None): - content-type - content-length - in-progress - content-disposition - packaging - slug - on-behalf-of """ meta = req._request.META content_type = req.content_type content_length = meta.get('CONTENT_LENGTH') if content_length and isinstance(content_length, str): content_length = int(content_length) # final deposit if not provided in_progress = meta.get('HTTP_IN_PROGRESS', False) content_disposition = meta.get('HTTP_CONTENT_DISPOSITION') if isinstance(in_progress, str): in_progress = in_progress.lower() == 'true' content_md5sum = meta.get('HTTP_CONTENT_MD5') if content_md5sum: content_md5sum = bytes.fromhex(content_md5sum) packaging = meta.get('HTTP_PACKAGING') slug = meta.get('HTTP_SLUG') on_behalf_of = meta.get('HTTP_ON_BEHALF_OF') metadata_relevant = meta.get('HTTP_METADATA_RELEVANT') return { 'content-type': content_type, 'content-length': content_length, 'in-progress': in_progress, 'content-disposition': content_disposition, 'content-md5sum': content_md5sum, 'packaging': packaging, 'slug': slug, 'on-behalf-of': on_behalf_of, 'metadata-relevant': metadata_relevant, } def _compute_md5(self, filehandler): """Compute uploaded file's md5 sum. Args: filehandler (InMemoryUploadedFile): the file to compute the md5 hash Returns: the md5 checksum (str) """ h = hashlib.md5() for chunk in filehandler: h.update(chunk) return h.digest() def _deposit_put(self, deposit_id=None, in_progress=False, external_id=None): """Save/Update a deposit in db. Args: deposit_id (int): deposit identifier in_progress (dict): The deposit's status external_id (str): The external identifier to associate to the deposit Returns: The Deposit instance saved or updated. """ if in_progress is False: complete_date = timezone.now() status_type = DEPOSIT_STATUS_DEPOSITED else: complete_date = None status_type = DEPOSIT_STATUS_PARTIAL if not deposit_id: try: # find a deposit parent (same external id, status load # to success) deposit_parent = Deposit.objects.filter( external_id=external_id, status=DEPOSIT_STATUS_LOAD_SUCCESS).order_by('-id')[0:1].get() # noqa except Deposit.DoesNotExist: deposit_parent = None deposit = Deposit(collection=self._collection, external_id=external_id, complete_date=complete_date, status=status_type, client=self._client, parent=deposit_parent) else: deposit = Deposit.objects.get(pk=deposit_id) # update metadata deposit.complete_date = complete_date deposit.status = status_type deposit.save() return deposit def _deposit_request_put(self, deposit, deposit_request_data, replace_metadata=False, replace_archives=False): """Save a deposit request with metadata attached to a deposit. Args: deposit (Deposit): The deposit concerned by the request deposit_request_data (dict): The dictionary with at most 2 deposit request types (archive, metadata) to associate to the deposit replace_metadata (bool): Flag defining if we add or update existing metadata to the deposit replace_archives (bool): Flag defining if we add or update archives to existing deposit Returns: None """ if replace_metadata: DepositRequest.objects.filter( deposit=deposit, type=self.deposit_request_types[METADATA_KEY]).delete() if replace_archives: DepositRequest.objects.filter( deposit=deposit, type=self.deposit_request_types[ARCHIVE_KEY]).delete() deposit_request = None archive_file = deposit_request_data.get(ARCHIVE_KEY) if archive_file: deposit_request = DepositRequest( type=self.deposit_request_types[ARCHIVE_KEY], deposit=deposit, archive=archive_file) deposit_request.save() metadata = deposit_request_data.get(METADATA_KEY) if metadata: + raw_metadata = deposit_request_data.get(RAW_METADATA_KEY) deposit_request = DepositRequest( type=self.deposit_request_types[METADATA_KEY], deposit=deposit, - metadata=metadata) + metadata=metadata, + raw_metadata=raw_metadata) deposit_request.save() assert deposit_request is not None def _delete_archives(self, collection_name, deposit_id): """Delete archives reference from the deposit id. """ try: deposit = Deposit.objects.get(pk=deposit_id) except Deposit.DoesNotExist: return make_error_dict( NOT_FOUND, 'The deposit %s does not exist' % deposit_id) DepositRequest.objects.filter( deposit=deposit, type=self.deposit_request_types[ARCHIVE_KEY]).delete() return {} def _delete_deposit(self, collection_name, deposit_id): """Delete deposit reference. Args: collection_name (str): Client's name deposit_id (id): The deposit to delete Returns Empty dict when ok. Dict with error key to describe the failure. """ try: deposit = Deposit.objects.get(pk=deposit_id) except Deposit.DoesNotExist: return make_error_dict( NOT_FOUND, 'The deposit %s does not exist' % deposit_id) if deposit.collection.name != collection_name: summary = 'Cannot delete a deposit from another collection' description = "Deposit %s does not belong to the collection %s" % ( deposit_id, collection_name) return make_error_dict( BAD_REQUEST, summary=summary, verbose_description=description) DepositRequest.objects.filter(deposit=deposit).delete() deposit.delete() return {} def _check_preconditions_on(self, filehandler, md5sum, content_length=None): """Check preconditions on provided file are respected. That is the length and/or the md5sum hash match the file's content. Args: filehandler (InMemoryUploadedFile): The file to check md5sum (hex str): md5 hash expected from the file's content content_length (int): the expected length if provided. Returns: Either none if no error or a dictionary with a key error detailing the problem. """ if content_length: if content_length > self.config['max_upload_size']: return make_error_dict( MAX_UPLOAD_SIZE_EXCEEDED, 'Upload size limit exceeded (max %s bytes).' % self.config['max_upload_size'], 'Please consider sending the archive in ' 'multiple steps.') length = filehandler.size if length != content_length: return make_error_dict(status.HTTP_412_PRECONDITION_FAILED, 'Wrong length') if md5sum: _md5sum = self._compute_md5(filehandler) if _md5sum != md5sum: return make_error_dict( CHECKSUM_MISMATCH, 'Wrong md5 hash', 'The checksum sent %s and the actual checksum ' '%s does not match.' % (hashutil.hash_to_hex(md5sum), hashutil.hash_to_hex(_md5sum))) return None def _binary_upload(self, req, headers, collection_name, deposit_id=None, replace_metadata=False, replace_archives=False): """Binary upload routine. Other than such a request, a 415 response is returned. Args: req (Request): the request holding information to parse and inject in db headers (dict): request headers formatted collection_name (str): the associated client deposit_id (id): deposit identifier if provided replace_metadata (bool): 'Update or add' request to existing deposit. If False (default), this adds new metadata request to existing ones. Otherwise, this will replace existing metadata. replace_archives (bool): 'Update or add' request to existing deposit. If False (default), this adds new archive request to existing ones. Otherwise, this will replace existing archives. ones. Returns: In the optimal case a dict with the following keys: - deposit_id (int): Deposit identifier - deposit_date (date): Deposit date - archive: None (no archive is provided here) Otherwise, a dictionary with the key error and the associated failures, either: - 400 (bad request) if the request is not providing an external identifier - 413 (request entity too large) if the length of the archive exceeds the max size configured - 412 (precondition failed) if the length or md5 hash provided mismatch the reality of the archive - 415 (unsupported media type) if a wrong media type is provided """ content_length = headers['content-length'] if not content_length: return make_error_dict( BAD_REQUEST, 'CONTENT_LENGTH header is mandatory', 'For archive deposit, the ' 'CONTENT_LENGTH header must be sent.') content_disposition = headers['content-disposition'] if not content_disposition: return make_error_dict( BAD_REQUEST, 'CONTENT_DISPOSITION header is mandatory', 'For archive deposit, the ' 'CONTENT_DISPOSITION header must be sent.') packaging = headers['packaging'] if packaging and packaging not in ACCEPT_PACKAGINGS: return make_error_dict( BAD_REQUEST, 'Only packaging %s is supported' % ACCEPT_PACKAGINGS, 'The packaging provided %s is not supported' % packaging) filehandler = req.FILES['file'] precondition_status_response = self._check_preconditions_on( filehandler, headers['content-md5sum'], content_length) if precondition_status_response: return precondition_status_response external_id = headers['slug'] # actual storage of data archive_metadata = filehandler deposit = self._deposit_put(deposit_id=deposit_id, in_progress=headers['in-progress'], external_id=external_id) self._deposit_request_put( deposit, {ARCHIVE_KEY: archive_metadata}, replace_metadata=replace_metadata, replace_archives=replace_archives) return { 'deposit_id': deposit.id, 'deposit_date': deposit.reception_date, 'status': deposit.status, 'archive': filehandler.name, } + def _read_metadata(self, metadata_stream): + """Given a metadata stream, reads the metadata and returns both the + parsed and the raw metadata. + + """ + raw_metadata = metadata_stream.read() + metadata = parse_xml(raw_metadata) + return raw_metadata, metadata + def _multipart_upload(self, req, headers, collection_name, deposit_id=None, replace_metadata=False, replace_archives=False): """Multipart upload supported with exactly: - 1 archive (zip) - 1 atom entry Other than such a request, a 415 response is returned. Args: req (Request): the request holding information to parse and inject in db headers (dict): request headers formatted collection_name (str): the associated client deposit_id (id): deposit identifier if provided replace_metadata (bool): 'Update or add' request to existing deposit. If False (default), this adds new metadata request to existing ones. Otherwise, this will replace existing metadata. replace_archives (bool): 'Update or add' request to existing deposit. If False (default), this adds new archive request to existing ones. Otherwise, this will replace existing archives. ones. Returns: In the optimal case a dict with the following keys: - deposit_id (int): Deposit identifier - deposit_date (date): Deposit date - archive: None (no archive is provided here) Otherwise, a dictionary with the key error and the associated failures, either: - 400 (bad request) if the request is not providing an external identifier - 412 (precondition failed) if the potentially md5 hash provided mismatch the reality of the archive - 413 (request entity too large) if the length of the archive exceeds the max size configured - 415 (unsupported media type) if a wrong media type is provided """ external_id = headers['slug'] content_types_present = set() data = { 'application/zip': None, # expected either zip 'application/x-tar': None, # or x-tar 'application/atom+xml': None, } for key, value in req.FILES.items(): fh = value if fh.content_type in content_types_present: return make_error_dict( ERROR_CONTENT, 'Only 1 application/zip (or application/x-tar) archive ' 'and 1 atom+xml entry is supported (as per sword2.0 ' 'specification)', 'You provided more than 1 application/(zip|x-tar) ' 'or more than 1 application/atom+xml content-disposition ' 'header in the multipart deposit') content_types_present.add(fh.content_type) data[fh.content_type] = fh if len(content_types_present) != 2: return make_error_dict( ERROR_CONTENT, 'You must provide both 1 application/zip (or ' 'application/x-tar) and 1 atom+xml entry for multipart ' 'deposit', 'You need to provide only 1 application/(zip|x-tar) ' 'and 1 application/atom+xml content-disposition header ' 'in the multipart deposit') filehandler = data['application/zip'] if not filehandler: filehandler = data['application/x-tar'] precondition_status_response = self._check_preconditions_on( filehandler, headers['content-md5sum']) if precondition_status_response: return precondition_status_response + raw_metadata, metadata = self._read_metadata( + data['application/atom+xml']) + # actual storage of data - atom_metadata = parse_xml(data['application/atom+xml']) deposit = self._deposit_put(deposit_id=deposit_id, in_progress=headers['in-progress'], external_id=external_id) deposit_request_data = { ARCHIVE_KEY: filehandler, - METADATA_KEY: atom_metadata, + METADATA_KEY: metadata, + RAW_METADATA_KEY: raw_metadata, } self._deposit_request_put( deposit, deposit_request_data, replace_metadata, replace_archives) return { 'deposit_id': deposit.id, 'deposit_date': deposit.reception_date, 'archive': filehandler.name, 'status': deposit.status, } def _atom_entry(self, req, headers, collection_name, deposit_id=None, replace_metadata=False, replace_archives=False): """Atom entry deposit. Args: req (Request): the request holding information to parse and inject in db headers (dict): request headers formatted collection_name (str): the associated client deposit_id (id): deposit identifier if provided replace_metadata (bool): 'Update or add' request to existing deposit. If False (default), this adds new metadata request to existing ones. Otherwise, this will replace existing metadata. replace_archives (bool): 'Update or add' request to existing deposit. If False (default), this adds new archive request to existing ones. Otherwise, this will replace existing archives. ones. Returns: In the optimal case a dict with the following keys: - deposit_id: deposit id associated to the deposit - deposit_date: date of the deposit - archive: None (no archive is provided here) Otherwise, a dictionary with the key error and the associated failures, either: - 400 (bad request) if the request is not providing an external identifier - 400 (bad request) if the request's body is empty - 415 (unsupported media type) if a wrong media type is provided """ - if not req.data: + raw_metadata, metadata = self._read_metadata(req.data) + if not metadata: return make_error_dict( BAD_REQUEST, 'Empty body request is not supported', 'Atom entry deposit is supposed to send for metadata. ' 'If the body is empty, there is no metadata.') - external_id = req.data.get('external_identifier', headers['slug']) + external_id = metadata.get('external_identifier', headers['slug']) deposit = self._deposit_put(deposit_id=deposit_id, in_progress=headers['in-progress'], external_id=external_id) + self._deposit_request_put( - deposit, {METADATA_KEY: req.data}, + deposit, {METADATA_KEY: metadata, RAW_METADATA_KEY: raw_metadata}, replace_metadata, replace_archives) return { 'deposit_id': deposit.id, 'deposit_date': deposit.reception_date, 'archive': None, 'status': deposit.status, } def _empty_post(self, req, headers, collection_name, deposit_id): """Empty post to finalize an empty deposit. Args: req (Request): the request holding information to parse and inject in db headers (dict): request headers formatted collection_name (str): the associated client deposit_id (id): deposit identifier Returns: Dictionary of result with the deposit's id, the date it was completed and no archive. """ deposit = Deposit.objects.get(pk=deposit_id) deposit.complete_date = timezone.now() deposit.status = DEPOSIT_STATUS_DEPOSITED deposit.save() return { 'deposit_id': deposit_id, 'deposit_date': deposit.complete_date, 'status': deposit.status, 'archive': None, } def _make_iris(self, req, collection_name, deposit_id): """Define the IRI endpoints Args: req (Request): The initial request collection_name (str): client/collection's name deposit_id (id): Deposit identifier Returns: Dictionary of keys with the iris' urls. """ args = [collection_name, deposit_id] return { iri: req.build_absolute_uri(reverse(iri, args=args)) for iri in [EM_IRI, EDIT_SE_IRI, CONT_FILE_IRI, STATE_IRI] } def additional_checks(self, req, headers, collection_name, deposit_id=None): """Permit the child class to enrich additional checks. Returns: dict with 'error' detailing the problem. """ return {} def checks(self, req, collection_name, deposit_id=None): try: self._collection = DepositCollection.objects.get( name=collection_name) except DepositCollection.DoesNotExist: return make_error_dict( NOT_FOUND, 'Unknown collection name %s' % collection_name) username = req.user.username if username: # unauthenticated request can have the username empty try: self._client = DepositClient.objects.get(username=username) except DepositClient.DoesNotExist: return make_error_dict(NOT_FOUND, 'Unknown client name %s' % username) if self._collection.id not in self._client.collections: return make_error_dict( FORBIDDEN, 'Client %s cannot access collection %s' % ( username, collection_name)) if deposit_id: try: deposit = Deposit.objects.get(pk=deposit_id) except Deposit.DoesNotExist: return make_error_dict( NOT_FOUND, 'Deposit with id %s does not exist' % deposit_id) checks = self.restrict_access(req, deposit) if checks: return checks headers = self._read_headers(req) if headers['on-behalf-of']: return make_error_dict(MEDIATION_NOT_ALLOWED, 'Mediation is not supported.') checks = self.additional_checks(req, headers, collection_name, deposit_id) if 'error' in checks: return checks return {'headers': headers} def restrict_access(self, req, deposit=None): if deposit: if (req.method != 'GET' and deposit.status != DEPOSIT_STATUS_PARTIAL): summary = "You can only act on deposit with status '%s'" % ( DEPOSIT_STATUS_PARTIAL, ) description = "This deposit has status '%s'" % deposit.status return make_error_dict( BAD_REQUEST, summary=summary, verbose_description=description) def _basic_not_allowed_method(self, req, method): return make_error_response( req, METHOD_NOT_ALLOWED, '%s method is not supported on this endpoint' % method) def get(self, req, *args, **kwargs): return self._basic_not_allowed_method(req, 'GET') def post(self, req, *args, **kwargs): return self._basic_not_allowed_method(req, 'POST') def put(self, req, *args, **kwargs): return self._basic_not_allowed_method(req, 'PUT') def delete(self, req, *args, **kwargs): return self._basic_not_allowed_method(req, 'DELETE') class SWHGetDepositAPI(SWHBaseDeposit, metaclass=ABCMeta): """Mixin for class to support GET method. """ def get(self, req, collection_name, deposit_id, format=None): """Endpoint to create/add resources to deposit. Returns: 200 response when no error during routine occurred 400 if the deposit does not belong to the collection 404 if the deposit or the collection does not exist """ checks = self.checks(req, collection_name, deposit_id) if 'error' in checks: return make_error_response_from_dict(req, checks['error']) r = self.process_get( req, collection_name, deposit_id) if isinstance(r, tuple): status, content, content_type = r return HttpResponse(content, status=status, content_type=content_type) return r @abstractmethod def process_get(self, req, collection_name, deposit_id): """Routine to deal with the deposit's get processing. Returns: Tuple status, stream of content, content-type """ pass class SWHPostDepositAPI(SWHBaseDeposit, metaclass=ABCMeta): """Mixin for class to support DELETE method. """ def post(self, req, collection_name, deposit_id=None, format=None): """Endpoint to create/add resources to deposit. Returns: 204 response when no error during routine occurred. 400 if the deposit does not belong to the collection 404 if the deposit or the collection does not exist """ checks = self.checks(req, collection_name, deposit_id) if 'error' in checks: return make_error_response_from_dict(req, checks['error']) headers = checks['headers'] _status, _iri_key, data = self.process_post( req, headers, collection_name, deposit_id) error = data.get('error') if error: return make_error_response_from_dict(req, error) data['packagings'] = ACCEPT_PACKAGINGS iris = self._make_iris(req, collection_name, data['deposit_id']) data.update(iris) response = render(req, 'deposit/deposit_receipt.xml', context=data, content_type='application/xml', status=_status) response._headers['location'] = 'Location', data[_iri_key] return response @abstractmethod def process_post(self, req, headers, collection_name, deposit_id=None): """Routine to deal with the deposit's processing. Returns Tuple of: - response status code (200, 201, etc...) - key iri (EM_IRI, EDIT_SE_IRI, etc...) - dictionary of the processing result """ pass class SWHPutDepositAPI(SWHBaseDeposit, metaclass=ABCMeta): """Mixin for class to support PUT method. """ def put(self, req, collection_name, deposit_id, format=None): """Endpoint to update deposit resources. Returns: 204 response when no error during routine occurred. 400 if the deposit does not belong to the collection 404 if the deposit or the collection does not exist """ checks = self.checks(req, collection_name, deposit_id) if 'error' in checks: return make_error_response_from_dict(req, checks['error']) headers = checks['headers'] data = self.process_put(req, headers, collection_name, deposit_id) error = data.get('error') if error: return make_error_response_from_dict(req, error) return HttpResponse(status=status.HTTP_204_NO_CONTENT) @abstractmethod def process_put(self, req, headers, collection_name, deposit_id): """Routine to deal with updating a deposit in some way. Returns dictionary of the processing result """ pass class SWHDeleteDepositAPI(SWHBaseDeposit, metaclass=ABCMeta): """Mixin for class to support DELETE method. """ def delete(self, req, collection_name, deposit_id): """Endpoint to delete some deposit's resources (archives, deposit). Returns: 204 response when no error during routine occurred. 400 if the deposit does not belong to the collection 404 if the deposit or the collection does not exist """ checks = self.checks(req, collection_name, deposit_id) if 'error' in checks: return make_error_response_from_dict(req, checks['error']) data = self.process_delete(req, collection_name, deposit_id) error = data.get('error') if error: return make_error_response_from_dict(req, error) return HttpResponse(status=status.HTTP_204_NO_CONTENT) @abstractmethod def process_delete(self, req, collection_name, deposit_id): """Routine to delete a resource. This is mostly not allowed except for the EM_IRI (cf. .api.deposit_update.SWHUpdateArchiveDeposit) """ pass diff --git a/swh/deposit/api/deposit_status.py b/swh/deposit/api/deposit_status.py index 52930a6d..e212f0ed 100644 --- a/swh/deposit/api/deposit_status.py +++ b/swh/deposit/api/deposit_status.py @@ -1,111 +1,120 @@ # Copyright (C) 2017-2018 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 from django.shortcuts import render from rest_framework import status from .common import SWHBaseDeposit from ..errors import NOT_FOUND, make_error_response from ..errors import make_error_response_from_dict from ..models import DEPOSIT_STATUS_DETAIL, Deposit def convert_status_detail(status_detail): """Given a status_detail dict, transforms it into a human readable string. Dict has the following form (all first level keys are optional): { 'url': { 'summary': , 'fields': }, 'metadata': [{ 'summary': , 'fields': , }], 'archive': [{ 'summary': , 'fields': , }] } Args: status_detail (dict): Returns: Status detail as inlined string. """ if not status_detail: return None msg = [] for key in ['metadata', 'archive']: _detail = status_detail.get(key) if _detail: for data in _detail: suffix_msg = '' fields = data.get('fields') if fields: suffix_msg = ' (%s)' % ', '.join(fields) msg.append('- %s%s\n' % (data['summary'], suffix_msg)) _detail = status_detail.get('url') if _detail: fields = _detail.get('fields') suffix_msg = '' if fields: suffix_msg = ' (%s)' % ', '.join(fields) msg.append('- %s%s\n' % (_detail['summary'], suffix_msg)) if not msg: return None return ''.join(msg) class SWHDepositStatus(SWHBaseDeposit): """Deposit status. What's known as 'State IRI' in the sword specification. HTTP verbs supported: GET """ def get(self, req, collection_name, deposit_id, format=None): checks = self.checks(req, collection_name, deposit_id) if 'error' in checks: return make_error_response_from_dict(req, checks['error']) try: deposit = Deposit.objects.get(pk=deposit_id) if deposit.collection.name != collection_name: raise Deposit.DoesNotExist except Deposit.DoesNotExist: return make_error_response( req, NOT_FOUND, 'deposit %s does not belong to collection %s' % ( deposit_id, collection_name)) status_detail = convert_status_detail(deposit.status_detail) if not status_detail: status_detail = DEPOSIT_STATUS_DETAIL[deposit.status] context = { 'deposit_id': deposit.id, 'status': deposit.status, 'status_detail': status_detail, 'swh_id': None, + 'swh_id_context': None, + 'swh_anchor_id': None, + 'swh_anchor_id_context': None, } if deposit.swh_id: context['swh_id'] = deposit.swh_id + if deposit.swh_id_context: + context['swh_id_context'] = deposit.swh_id_context + if deposit.swh_anchor_id: + context['swh_anchor_id'] = deposit.swh_anchor_id + if deposit.swh_anchor_id_context: + context['swh_anchor_id_context'] = deposit.swh_anchor_id_context return render(req, 'deposit/status.xml', context=context, content_type='application/xml', status=status.HTTP_200_OK) diff --git a/swh/deposit/api/private/deposit_update_status.py b/swh/deposit/api/private/deposit_update_status.py index cbb8ccce..8b907a4c 100644 --- a/swh/deposit/api/private/deposit_update_status.py +++ b/swh/deposit/api/private/deposit_update_status.py @@ -1,74 +1,89 @@ # Copyright (C) 2017-2018 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 from rest_framework.parsers import JSONParser -from swh.model.identifiers import persistent_identifier, REVISION +from swh.model.identifiers import ( + persistent_identifier, REVISION, DIRECTORY +) from ..common import SWHPutDepositAPI, SWHPrivateAPIView from ...errors import make_error_dict, BAD_REQUEST from ...models import Deposit, DEPOSIT_STATUS_DETAIL from ...models import DEPOSIT_STATUS_LOAD_SUCCESS class SWHUpdateStatusDeposit(SWHPutDepositAPI, SWHPrivateAPIView): """Deposit request class to update the deposit's status. HTTP verbs supported: PUT """ parser_classes = (JSONParser, ) def additional_checks(self, req, headers, collection_name, deposit_id=None): """Enrich existing checks to the default ones. New checks: - Ensure the status is provided - Ensure it exists """ data = req.data status = data.get('status') if not status: msg = 'The status key is mandatory with possible values %s' % list( DEPOSIT_STATUS_DETAIL.keys()) return make_error_dict(BAD_REQUEST, msg) if status not in DEPOSIT_STATUS_DETAIL: msg = 'Possible status in %s' % list(DEPOSIT_STATUS_DETAIL.keys()) return make_error_dict(BAD_REQUEST, msg) if status == DEPOSIT_STATUS_LOAD_SUCCESS: swh_id = data.get('revision_id') if not swh_id: msg = 'Updating status to %s requires a revision_id key' % ( status, ) return make_error_dict(BAD_REQUEST, msg) return {} def restrict_access(self, req, deposit=None): """Remove restriction modification to 'partial' deposit. Update is possible regardless of the existing status. """ return None def process_put(self, req, headers, collection_name, deposit_id): """Update the deposit's status Returns: 204 No content """ deposit = Deposit.objects.get(pk=deposit_id) deposit.status = req.data['status'] # checks already done before - swh_id = req.data.get('revision_id') - if swh_id: - deposit.swh_id = persistent_identifier(REVISION, {'id': swh_id}) + + origin_url = req.data.get('origin_url') + + dir_id = req.data.get('directory_id') + if dir_id: + deposit.swh_id = persistent_identifier(DIRECTORY, dir_id) + deposit.swh_id_context = persistent_identifier( + DIRECTORY, dir_id, metadata={'origin': origin_url}) + + rev_id = req.data.get('revision_id') + if rev_id: + deposit.swh_anchor_id = persistent_identifier( + REVISION, rev_id) + deposit.swh_anchor_id_context = persistent_identifier( + REVISION, rev_id, metadata={'origin': origin_url}) + deposit.save() return {} diff --git a/swh/deposit/client/__init__.py b/swh/deposit/client/__init__.py index b7712efd..a1296b10 100644 --- a/swh/deposit/client/__init__.py +++ b/swh/deposit/client/__init__.py @@ -1,595 +1,574 @@ # Copyright (C) 2017-2018 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 """Module in charge of defining an swh-deposit client """ import hashlib import os import requests +import xmltodict from abc import ABCMeta, abstractmethod -from lxml import etree from swh.core.config import SWHConfig +def _parse(stream, encoding='utf-8'): + """Given a xml stream, parse the result. + + Args: + stream (bytes/text): The stream to parse + encoding (str): The encoding to use if to decode the bytes + stream + + Returns: + A dict of values corresponding to the parsed xml + + """ + if isinstance(stream, bytes): + stream = stream.decode(encoding) + data = xmltodict.parse(stream, encoding=encoding, process_namespaces=False) + if 'entry' in data: + data = data['entry'] + return dict(data) + + +def _parse_with_filter(stream, encoding='utf-8', keys=[]): + """Given a xml stream, parse the result and filter with keys. + + Args: + stream (bytes/text): The stream to parse + encoding (str): The encoding to use if to decode the bytes + stream + keys ([str]): Keys to filter the parsed result + + Returns: + A dict of values corresponding to the parsed xml filtered by + the keys provided. + + """ + data = _parse(stream, encoding=encoding) + m = {} + for key in keys: + m[key] = data.get(key) + return m + + class BaseApiDepositClient(SWHConfig): """Deposit client base class """ CONFIG_BASE_FILENAME = 'deposit/client' DEFAULT_CONFIG = { 'url': ('str', 'http://localhost:5006'), 'auth': ('dict', {}), # with optional 'username'/'password' keys } def __init__(self, config=None, _client=requests): super().__init__() if config is None: self.config = super().parse_config_file() else: self.config = config self._client = _client self.base_url = self.config['url'] auth = self.config['auth'] if auth == {}: self.auth = None else: self.auth = (auth['username'], auth['password']) def do(self, method, url, *args, **kwargs): """Internal method to deal with requests, possibly with basic http authentication. Args: method (str): supported http methods as in self._methods' keys Returns: The request's execution """ if hasattr(self._client, method): method_fn = getattr(self._client, method) else: raise ValueError('Development error, unsupported method %s' % ( method)) if self.auth: kwargs['auth'] = self.auth full_url = '%s%s' % (self.base_url.rstrip('/'), url) return method_fn(full_url, *args, **kwargs) class PrivateApiDepositClient(BaseApiDepositClient): """Private API deposit client to: - read a given deposit's archive(s) - read a given deposit's metadata - update a given deposit's status """ def archive_get(self, archive_update_url, archive_path, log=None): """Retrieve the archive from the deposit to a local directory. Args: archive_update_url (str): The full deposit archive(s)'s raw content to retrieve locally archive_path (str): the local archive's path where to store the raw content Returns: The archive path to the local archive to load. Or None if any problem arose. """ r = self.do('get', archive_update_url, stream=True) if r.ok: with open(archive_path, 'wb') as f: for chunk in r.iter_content(): f.write(chunk) return archive_path msg = 'Problem when retrieving deposit archive at %s' % ( archive_update_url, ) if log: log.error(msg) raise ValueError(msg) def metadata_get(self, metadata_url, log=None): """Retrieve the metadata information on a given deposit. Args: metadata_url (str): The full deposit metadata url to retrieve locally Returns: The dictionary of metadata for that deposit or None if any problem arose. """ r = self.do('get', metadata_url) if r.ok: return r.json() msg = 'Problem when retrieving metadata at %s' % metadata_url if log: log.error(msg) raise ValueError(msg) def status_update(self, update_status_url, status, - revision_id=None): + revision_id=None, directory_id=None, origin_url=None): """Update the deposit's status. Args: update_status_url (str): the full deposit's archive status (str): The status to update the deposit with revision_id (str/None): the revision's identifier to update to + directory_id (str/None): the directory's identifier to update to + origin_url (str/None): deposit's associated origin url """ payload = {'status': status} if revision_id: payload['revision_id'] = revision_id + if directory_id: + payload['directory_id'] = directory_id + if origin_url: + payload['origin_url'] = origin_url self.do('put', update_status_url, json=payload) def check(self, check_url, log=None): """Check the deposit's associated data (metadata, archive(s)) Args: check_url (str): the full deposit's check url """ r = self.do('get', check_url) if r.ok: data = r.json() return data['status'] msg = 'Problem when checking deposit %s' % check_url if log: log.error(msg) raise ValueError(msg) class BaseDepositClient(BaseApiDepositClient, metaclass=ABCMeta): """Base Deposit client to access the public api. """ def __init__(self, config, error_msg=None, empty_result={}): super().__init__(config) self.error_msg = error_msg self.empty_result = empty_result @abstractmethod def compute_url(self, *args, **kwargs): """Compute api url endpoint to query.""" pass @abstractmethod def compute_method(self, *args, **kwargs): """Http method to use on the url""" pass @abstractmethod def parse_result_ok(self, xml_content): """Given an xml result from the api endpoint, parse it and returns a dict. """ pass def compute_information(self, *args, **kwargs): """Compute some more information given the inputs (e.g http headers, ...) """ return {} def parse_result_error(self, xml_content): """Given an error response in xml, parse it into a dict. Returns: dict with following keys: 'error': The error message 'detail': Some more detail about the error if any """ - tree = etree.fromstring(xml_content.encode('utf-8')) - vals = tree.xpath('/x:error/y:summary', namespaces={ - 'x': 'http://purl.org/net/sword/', - 'y': 'http://www.w3.org/2005/Atom' - }) - summary = vals[0].text - if summary: - summary = summary.strip() - - vals = tree.xpath( - '/x:error/x:verboseDescription', - namespaces={'x': 'http://purl.org/net/sword/'}) - if vals: - detail = vals[0].text.strip() - else: - detail = None - - return {'error': summary, 'detail': detail} + return _parse_with_filter(xml_content, keys=['summary', 'detail']) def do_execute(self, method, url, info): """Execute the http query to url using method and info information. By default, execute a simple query to url with the http method. Override this in daughter class to improve the default behavior if needed. """ return self.do(method, url) def execute(self, *args, **kwargs): """Main endpoint to prepare and execute the http query to the api. """ url = self.compute_url(*args, **kwargs) method = self.compute_method(*args, **kwargs) info = self.compute_information(*args, **kwargs) try: r = self.do_execute(method, url, info) except Exception as e: msg = self.error_msg % (url, e) r = self.empty_result r.update({ 'error': msg, }) return r else: if r.ok: if int(r.status_code) == 204: # 204 returns no body return {'status': r.status_code} else: return self.parse_result_ok(r.text) else: error = self.parse_result_error(r.text) empty = self.empty_result error.update(empty) error.update({ 'status': r.status_code, }) return error class ServiceDocumentDepositClient(BaseDepositClient): """Service Document information retrieval. """ def __init__(self, config): super().__init__(config, error_msg='Service document failure at %s: %s', empty_result={'collection': None}) def compute_url(self, *args, **kwargs): return '/servicedocument/' def compute_method(self, *args, **kwargs): return 'get' def parse_result_ok(self, xml_content): """Parse service document's success response. """ - tree = etree.fromstring(xml_content.encode('utf-8')) - collections = tree.xpath( - '/x:service/x:workspace/x:collection/y:name', - namespaces={'x': 'http://www.w3.org/2007/app', - 'y': 'http://purl.org/net/sword/terms/'}) - if collections: - collection = collections[0].text - else: - collection = None - - return { - 'collection': collection - } + return _parse_with_filter(xml_content, keys=['collection']) class StatusDepositClient(BaseDepositClient): """Status information on a deposit. """ def __init__(self, config): super().__init__(config, error_msg='Status check failure at %s: %s', empty_result={ 'deposit_status': None, 'deposit_status_detail': None, 'deposit_swh_id': None, }) def compute_url(self, collection, deposit_id): return '/%s/%s/status/' % (collection, deposit_id) def compute_method(self, *args, **kwargs): return 'get' def parse_result_ok(self, xml_content): """Given an xml content as string, returns a deposit dict. """ - tree = etree.fromstring(xml_content.encode('utf-8')) - vals = tree.xpath( - '/x:entry/x:deposit_id', - namespaces={'x': 'http://www.w3.org/2005/Atom'}) - deposit_id = vals[0].text - - vals = tree.xpath( - '/x:entry/x:deposit_status', - namespaces={'x': 'http://www.w3.org/2005/Atom'}) - deposit_status = vals[0].text - - vals = tree.xpath( - '/x:entry/x:deposit_status_detail', - namespaces={'x': 'http://www.w3.org/2005/Atom'}) - deposit_status_detail = vals[0].text - - vals = tree.xpath( - '/x:entry/x:deposit_swh_id', - namespaces={'x': 'http://www.w3.org/2005/Atom'}) - if vals: - deposit_swh_id = vals[0].text - else: - deposit_swh_id = None - - return { - 'deposit_id': deposit_id, - 'deposit_status': deposit_status, - 'deposit_status_detail': deposit_status_detail, - 'deposit_swh_id': deposit_swh_id, - } + return _parse_with_filter(xml_content, keys=[ + 'deposit_id', + 'deposit_status', + 'deposit_status_detail', + 'deposit_swh_id', + 'deposit_swh_id_context', + 'deposit_swh_anchor_id', + 'deposit_swh_anchor_id_context']) class BaseCreateDepositClient(BaseDepositClient): """Deposit client base class to post new deposit. """ def __init__(self, config): super().__init__(config, error_msg='Post Deposit failure at %s: %s', empty_result={ 'deposit_id': None, 'deposit_status': None, }) def compute_url(self, collection, *args, **kwargs): return '/%s/' % collection def compute_method(self, *args, **kwargs): return 'post' def parse_result_ok(self, xml_content): """Given an xml content as string, returns a deposit dict. """ - tree = etree.fromstring(xml_content.encode('utf-8')) - vals = tree.xpath( - '/x:entry/x:deposit_id', - namespaces={'x': 'http://www.w3.org/2005/Atom'}) - deposit_id = vals[0].text - - vals = tree.xpath( - '/x:entry/x:deposit_status', - namespaces={'x': 'http://www.w3.org/2005/Atom'}) - deposit_status = vals[0].text - - vals = tree.xpath( - '/x:entry/x:deposit_date', - namespaces={'x': 'http://www.w3.org/2005/Atom'}) - deposit_date = vals[0].text - - return { - 'deposit_id': deposit_id, - 'deposit_status': deposit_status, - 'deposit_date': deposit_date, - } + return _parse_with_filter(xml_content, keys=['deposit_id', + 'deposit_status', + 'deposit_status_detail', + 'deposit_date']) def _compute_information(self, collection, filepath, in_progress, slug, is_archive=True): """Given a filepath, compute necessary information on that file. Args: filepath (str): Path to a file is_archive (bool): is it an archive or not? Returns: dict with keys: 'content-type': content type associated 'md5sum': md5 sum 'filename': filename """ filename = os.path.basename(filepath) if is_archive: md5sum = hashlib.md5(open(filepath, 'rb').read()).hexdigest() extension = filename.split('.')[-1] if 'zip' in extension: content_type = 'application/zip' else: content_type = 'application/x-tar' else: content_type = None md5sum = None return { 'slug': slug, 'in_progress': in_progress, 'content-type': content_type, 'md5sum': md5sum, 'filename': filename, 'filepath': filepath, } def compute_information(self, collection, filepath, in_progress, slug, is_archive=True, **kwargs): info = self._compute_information(collection, filepath, in_progress, slug, is_archive=is_archive) info['headers'] = self.compute_headers(info) return info def do_execute(self, method, url, info): with open(info['filepath'], 'rb') as f: return self.do(method, url, data=f, headers=info['headers']) class CreateArchiveDepositClient(BaseCreateDepositClient): """Post an archive (binary) deposit client.""" def compute_headers(self, info): return { 'SLUG': info['slug'], 'CONTENT_MD5': info['md5sum'], 'IN-PROGRESS': str(info['in_progress']), 'CONTENT-TYPE': info['content-type'], 'CONTENT-DISPOSITION': 'attachment; filename=%s' % ( info['filename'], ), } class UpdateArchiveDepositClient(CreateArchiveDepositClient): """Update (add/replace) an archive (binary) deposit client.""" def compute_url(self, collection, *args, deposit_id=None, **kwargs): return '/%s/%s/media/' % (collection, deposit_id) def compute_method(self, *args, replace=False, **kwargs): return 'put' if replace else 'post' class CreateMetadataDepositClient(BaseCreateDepositClient): """Post a metadata deposit client.""" def compute_headers(self, info): return { 'SLUG': info['slug'], 'IN-PROGRESS': str(info['in_progress']), 'CONTENT-TYPE': 'application/atom+xml;type=entry', } class UpdateMetadataDepositClient(CreateMetadataDepositClient): """Update (add/replace) a metadata deposit client.""" def compute_url(self, collection, *args, deposit_id=None, **kwargs): return '/%s/%s/metadata/' % (collection, deposit_id) def compute_method(self, *args, replace=False, **kwargs): return 'put' if replace else 'post' class CreateMultipartDepositClient(BaseCreateDepositClient): """Create a multipart deposit client.""" def _multipart_info(self, info, info_meta): files = [ ('file', (info['filename'], open(info['filepath'], 'rb'), info['content-type'])), ('atom', (info_meta['filename'], open(info_meta['filepath'], 'rb'), 'application/atom+xml')), ] headers = { 'SLUG': info['slug'], 'CONTENT_MD5': info['md5sum'], 'IN-PROGRESS': str(info['in_progress']), } return files, headers def compute_information(self, collection, archive_path, metadata_path, in_progress, slug, **kwargs): info = self._compute_information( collection, archive_path, in_progress, slug) info_meta = self._compute_information( collection, metadata_path, in_progress, slug, is_archive=False) files, headers = self._multipart_info(info, info_meta) return {'files': files, 'headers': headers} def do_execute(self, method, url, info): return self.do( method, url, files=info['files'], headers=info['headers']) class UpdateMultipartDepositClient(CreateMultipartDepositClient): """Update a multipart deposit client.""" def compute_url(self, collection, *args, deposit_id=None, **kwargs): return '/%s/%s/metadata/' % (collection, deposit_id) def compute_method(self, *args, replace=False, **kwargs): return 'put' if replace else 'post' class PublicApiDepositClient(BaseApiDepositClient): """Public api deposit client.""" def service_document(self, log=None): """Retrieve service document endpoint's information.""" return ServiceDocumentDepositClient(self.config).execute() def deposit_status(self, collection, deposit_id, log=None): """Retrieve status information on a deposit.""" return StatusDepositClient(self.config).execute( collection, deposit_id) def deposit_create(self, collection, slug, archive_path=None, metadata_path=None, in_progress=False, log=None): """Create a new deposit (archive, metadata, both as multipart).""" if archive_path and not metadata_path: return CreateArchiveDepositClient(self.config).execute( collection, archive_path, in_progress, slug) elif not archive_path and metadata_path: return CreateMetadataDepositClient(self.config).execute( collection, metadata_path, in_progress, slug, is_archive=False) else: return CreateMultipartDepositClient(self.config).execute( collection, archive_path, metadata_path, in_progress, slug) def deposit_update(self, collection, deposit_id, slug, archive_path=None, metadata_path=None, in_progress=False, replace=False, log=None): """Update (add/replace) existing deposit (archive, metadata, both).""" r = self.deposit_status(collection, deposit_id, log=log) if 'error' in r: return r status = r['deposit_status'] if status != 'partial': return { 'error': "You can only act on deposit with status 'partial'", 'detail': "The deposit %s has status '%s'" % ( deposit_id, status), 'deposit_status': status, 'deposit_id': deposit_id, } if archive_path and not metadata_path: r = UpdateArchiveDepositClient(self.config).execute( collection, archive_path, in_progress, slug, deposit_id=deposit_id, replace=replace, log=log) elif not archive_path and metadata_path: r = UpdateMetadataDepositClient(self.config).execute( collection, metadata_path, in_progress, slug, deposit_id=deposit_id, replace=replace, log=log) else: r = UpdateMultipartDepositClient(self.config).execute( collection, archive_path, metadata_path, in_progress, slug, deposit_id=deposit_id, replace=replace, log=log) if 'error' in r: return r return self.deposit_status(collection, deposit_id, log=log) diff --git a/swh/deposit/config.py b/swh/deposit/config.py index 999a20ae..fca74e40 100644 --- a/swh/deposit/config.py +++ b/swh/deposit/config.py @@ -1,99 +1,100 @@ # Copyright (C) 2017-2018 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 os import logging from swh.core.config import SWHConfig from swh.scheduler import get_scheduler # IRIs (Internationalized Resource identifier) sword 2.0 specified EDIT_SE_IRI = 'edit_se_iri' EM_IRI = 'em_iri' CONT_FILE_IRI = 'cont_file_iri' SD_IRI = 'servicedocument' COL_IRI = 'upload' STATE_IRI = 'state_iri' PRIVATE_GET_RAW_CONTENT = 'private-download' PRIVATE_CHECK_DEPOSIT = 'check-deposit' PRIVATE_PUT_DEPOSIT = 'private-update' PRIVATE_GET_DEPOSIT_METADATA = 'private-read' ARCHIVE_KEY = 'archive' METADATA_KEY = 'metadata' +RAW_METADATA_KEY = 'raw-metadata' ARCHIVE_TYPE = 'archive' METADATA_TYPE = 'metadata' AUTHORIZED_PLATFORMS = ['development', 'production', 'testing'] DEPOSIT_STATUS_REJECTED = 'rejected' DEPOSIT_STATUS_PARTIAL = 'partial' DEPOSIT_STATUS_DEPOSITED = 'deposited' DEPOSIT_STATUS_VERIFIED = 'verified' DEPOSIT_STATUS_LOAD_SUCCESS = 'done' DEPOSIT_STATUS_LOAD_FAILURE = 'failed' # Revision author for deposit SWH_PERSON = { 'name': 'Software Heritage', 'fullname': 'Software Heritage', 'email': 'robot@softwareheritage.org' } def setup_django_for(platform): """Setup function for command line tools (swh.deposit.create_user, swh.deposit.scheduler.cli) to initialize the needed db access. Note: Do not import any django related module prior to this function call. Otherwise, this will raise an django.core.exceptions.ImproperlyConfigured error message. Args: platform (str): the platform the scheduling is running Raises: ValueError in case of wrong platform inputs. """ if platform not in AUTHORIZED_PLATFORMS: raise ValueError('Platform should be one of %s' % AUTHORIZED_PLATFORMS) os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'swh.deposit.settings.%s' % platform) import django django.setup() class SWHDefaultConfig(SWHConfig): """Mixin intended to enrich views with SWH configuration. """ CONFIG_BASE_FILENAME = 'deposit/server' DEFAULT_CONFIG = { 'max_upload_size': ('int', 209715200), 'checks': ('bool', True), 'scheduler': ('dict', { 'cls': 'remote', 'args': { 'url': 'http://localhost:5008/' } }) } ADDITIONAL_CONFIG = {} def __init__(self, **config): super().__init__() self.config = self.parse_config_file( additional_configs=[self.ADDITIONAL_CONFIG]) self.config.update(config) self.log = logging.getLogger('swh.deposit') if self.config['checks']: self.scheduler = get_scheduler(**self.config['scheduler']) diff --git a/swh/deposit/loader/loader.py b/swh/deposit/loader/loader.py index 5e1601b2..d640bfbb 100644 --- a/swh/deposit/loader/loader.py +++ b/swh/deposit/loader/loader.py @@ -1,130 +1,141 @@ # Copyright (C) 2017-2018 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 os import tempfile from swh.model import hashutil from swh.loader.tar import loader from swh.loader.core.loader import SWHLoader from ..client import PrivateApiDepositClient class DepositLoader(loader.TarLoader): """Deposit loader implementation. This is a subclass of the :class:TarLoader as the main goal of this class is to first retrieve the deposit's tarball contents as one and its associated metadata. Then provide said tarball to be loaded by the TarLoader. This will: - retrieves the deposit's archive locally - provide the archive to be loaded by the tar loader - clean up the temporary location used to retrieve the archive locally - update the deposit's status accordingly """ CONFIG_BASE_FILENAME = 'loader/deposit' ADDITIONAL_CONFIG = { 'extraction_dir': ('str', '/tmp/swh.deposit.loader/'), } def __init__(self, client=None): super().__init__( logging_class='swh.deposit.loader.loader.DepositLoader') self.client = client if client else PrivateApiDepositClient() def load(self, *, archive_url, deposit_meta_url, deposit_update_url): return SWHLoader.load( self, archive_url=archive_url, deposit_meta_url=deposit_meta_url, deposit_update_url=deposit_update_url) def prepare_origin_visit(self, *, deposit_meta_url, **kwargs): self.metadata = self.client.metadata_get( deposit_meta_url, log=self.log) self.origin = self.metadata['origin'] self.visit_date = None def prepare(self, *, archive_url, deposit_meta_url, deposit_update_url): """Prepare the loading by first retrieving the deposit's raw archive content. """ self.deposit_update_url = deposit_update_url self.client.status_update(deposit_update_url, 'loading') temporary_directory = tempfile.TemporaryDirectory() self.temporary_directory = temporary_directory archive_path = os.path.join(temporary_directory.name, 'archive.zip') archive = self.client.archive_get( archive_url, archive_path, log=self.log) metadata = self.metadata revision = metadata['revision'] branch_name = metadata['branch_name'] self.origin_metadata = metadata['origin_metadata'] self.prepare_metadata() super().prepare(tar_path=archive, origin=self.origin, revision=revision, branch_name=branch_name) def store_metadata(self): """Storing the origin_metadata during the load processus. Provider_id and tool_id are resolved during the prepare() method. """ origin_id = self.origin_id visit_date = self.visit_date provider_id = self.origin_metadata['provider']['provider_id'] tool_id = self.origin_metadata['tool']['tool_id'] metadata = self.origin_metadata['metadata'] try: self.send_origin_metadata(origin_id, visit_date, provider_id, tool_id, metadata) except Exception: self.log.exception('Problem when storing origin_metadata') raise def post_load(self, success=True): """Updating the deposit's status according to its loading status. If not successful, we update its status to 'failed'. Otherwise, we update its status to 'done' and pass along its associated revision. """ try: if not success: self.client.status_update(self.deposit_update_url, status='failed') return - # first retrieve the new revision - [rev_id] = self.objects['revision'].keys() + + revisions = self.objects['revision'] + # Retrieve the revision + [rev_id] = revisions.keys() + rev = revisions[rev_id] if rev_id: - rev_id_hex = hashutil.hash_to_hex(rev_id) - # then update the deposit's status to success with its - # revision-id - self.client.status_update(self.deposit_update_url, - status='done', - revision_id=rev_id_hex) + rev_id = hashutil.hash_to_hex(rev_id) + + dir_id = rev['directory'] + if dir_id: + dir_id = hashutil.hash_to_hex(dir_id) + + # update the deposit's status to success with its + # revision-id and directory-id + self.client.status_update( + self.deposit_update_url, + status='done', + revision_id=rev_id, + directory_id=dir_id, + origin_url=self.origin['url']) except Exception: self.log.exception( 'Problem when trying to update the deposit\'s status') def cleanup(self): """Clean up temporary directory where we retrieved the tarball. """ super().cleanup() self.temporary_directory.cleanup() diff --git a/swh/deposit/migrations/0013_depositrequest_raw_metadata.py b/swh/deposit/migrations/0013_depositrequest_raw_metadata.py new file mode 100644 index 00000000..4d0f0ea9 --- /dev/null +++ b/swh/deposit/migrations/0013_depositrequest_raw_metadata.py @@ -0,0 +1,20 @@ +# -*- coding: utf-8 -*- +# Generated by Django 1.11.14 on 2018-07-19 13:07 +from __future__ import unicode_literals + +from django.db import migrations, models + + +class Migration(migrations.Migration): + + dependencies = [ + ('deposit', '0012_deposit_status_detail'), + ] + + operations = [ + migrations.AddField( + model_name='depositrequest', + name='raw_metadata', + field=models.TextField(null=True), + ), + ] diff --git a/swh/deposit/migrations/0014_auto_20180720_1221.py b/swh/deposit/migrations/0014_auto_20180720_1221.py new file mode 100644 index 00000000..50d4d9a8 --- /dev/null +++ b/swh/deposit/migrations/0014_auto_20180720_1221.py @@ -0,0 +1,30 @@ +# -*- coding: utf-8 -*- +# Generated by Django 1.11.14 on 2018-07-20 12:21 +from __future__ import unicode_literals + +from django.db import migrations, models + + +class Migration(migrations.Migration): + + dependencies = [ + ('deposit', '0013_depositrequest_raw_metadata'), + ] + + operations = [ + migrations.AddField( + model_name='deposit', + name='swh_anchor_id', + field=models.TextField(blank=True, null=True), + ), + migrations.AddField( + model_name='deposit', + name='swh_anchor_id_context', + field=models.TextField(blank=True, null=True), + ), + migrations.AddField( + model_name='deposit', + name='swh_id_context', + field=models.TextField(blank=True, null=True), + ), + ] diff --git a/swh/deposit/models.py b/swh/deposit/models.py index df8cfc9f..ba6d9320 100644 --- a/swh/deposit/models.py +++ b/swh/deposit/models.py @@ -1,217 +1,221 @@ # Copyright (C) 2017-2018 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 # Generated from: # cd swh_deposit && \ # python3 -m manage inspectdb from django.contrib.postgres.fields import JSONField, ArrayField from django.contrib.auth.models import User, UserManager from django.db import models from django.utils.timezone import now from .config import ( DEPOSIT_STATUS_VERIFIED, DEPOSIT_STATUS_DEPOSITED, DEPOSIT_STATUS_PARTIAL, DEPOSIT_STATUS_LOAD_SUCCESS, DEPOSIT_STATUS_LOAD_FAILURE, DEPOSIT_STATUS_REJECTED ) class Dbversion(models.Model): """Db version """ version = models.IntegerField(primary_key=True) release = models.DateTimeField(default=now, null=True) description = models.TextField(blank=True, null=True) class Meta: db_table = 'dbversion' def __str__(self): return str({ 'version': self.version, 'release': self.release, 'description': self.description }) """Possible status""" DEPOSIT_STATUS = [ (DEPOSIT_STATUS_PARTIAL, DEPOSIT_STATUS_PARTIAL), ('expired', 'expired'), (DEPOSIT_STATUS_DEPOSITED, DEPOSIT_STATUS_DEPOSITED), (DEPOSIT_STATUS_VERIFIED, DEPOSIT_STATUS_VERIFIED), (DEPOSIT_STATUS_REJECTED, DEPOSIT_STATUS_REJECTED), ('loading', 'loading'), (DEPOSIT_STATUS_LOAD_SUCCESS, DEPOSIT_STATUS_LOAD_SUCCESS), (DEPOSIT_STATUS_LOAD_FAILURE, DEPOSIT_STATUS_LOAD_FAILURE), ] """Possible status and the detailed meaning.""" DEPOSIT_STATUS_DETAIL = { DEPOSIT_STATUS_PARTIAL: 'Deposit is partially received. To finalize it, ' 'In-Progress header should be false', 'expired': 'Deposit has been there too long and is now ' 'deemed ready to be garbage collected', DEPOSIT_STATUS_DEPOSITED: 'Deposit is ready for additional checks ' '(tarball ok, metadata, etc...)', DEPOSIT_STATUS_VERIFIED: 'Deposit is fully received, checked, and ' 'ready for loading', DEPOSIT_STATUS_REJECTED: 'Deposit failed the checks', 'loading': "Loading is ongoing on swh's side", DEPOSIT_STATUS_LOAD_SUCCESS: 'The deposit has been successfully ' 'loaded into the Software Heritage archive', DEPOSIT_STATUS_LOAD_FAILURE: 'The deposit loading into the ' 'Software Heritage archive failed', } class DepositClient(User): """Deposit client """ collections = ArrayField(models.IntegerField(), null=True) objects = UserManager() provider_url = models.TextField(null=False) domain = models.TextField(null=False) class Meta: db_table = 'deposit_client' def __str__(self): return str({ 'id': self.id, 'collections': self.collections, 'username': super().username, 'domain': self.domain, 'provider_url': self.provider_url, }) class Deposit(models.Model): """Deposit reception table """ id = models.BigAutoField(primary_key=True) # First deposit reception date reception_date = models.DateTimeField(auto_now_add=True) # Date when the deposit is deemed complete and ready for loading complete_date = models.DateTimeField(null=True) # collection concerned by the deposit collection = models.ForeignKey( 'DepositCollection', models.DO_NOTHING) # Deposit's external identifier external_id = models.TextField() # Deposit client client = models.ForeignKey('DepositClient', models.DO_NOTHING) # SWH's loading result identifier swh_id = models.TextField(blank=True, null=True) + swh_id_context = models.TextField(blank=True, null=True) + swh_anchor_id = models.TextField(blank=True, null=True) + swh_anchor_id_context = models.TextField(blank=True, null=True) # Deposit's status regarding loading status = models.TextField( choices=DEPOSIT_STATUS, default=DEPOSIT_STATUS_PARTIAL) status_detail = JSONField(null=True) # deposit can have one parent parent = models.ForeignKey('self', null=True) class Meta: db_table = 'deposit' def __str__(self): d = { 'id': self.id, 'reception_date': self.reception_date, 'collection': self.collection.name, 'external_id': self.external_id, 'client': self.client.username, 'status': self.status, } if self.status in (DEPOSIT_STATUS_REJECTED): d['status_detail'] = self.status_detail return str(d) class DepositRequestType(models.Model): """Deposit request type made by clients (either archive or metadata) """ id = models.BigAutoField(primary_key=True) name = models.TextField() class Meta: db_table = 'deposit_request_type' def __str__(self): return str({'id': self.id, 'name': self.name}) def client_directory_path(instance, filename): """Callable to upload archive in MEDIA_ROOT/user_/ Args: instance (DepositRequest): DepositRequest concerned by the upload filename (str): Filename of the uploaded file Returns: A path to be prefixed by the MEDIA_ROOT to access physically to the file uploaded. """ return 'client_{0}/{1}'.format(instance.deposit.client.id, filename) class DepositRequest(models.Model): """Deposit request associated to one deposit. """ id = models.BigAutoField(primary_key=True) # Deposit concerned by the request deposit = models.ForeignKey(Deposit, models.DO_NOTHING) date = models.DateTimeField(auto_now_add=True) # Deposit request information on the data to inject # this can be null when type is 'archive' metadata = JSONField(null=True) + raw_metadata = models.TextField(null=True) # this can be null when type is 'metadata' archive = models.FileField(null=True, upload_to=client_directory_path) type = models.ForeignKey( 'DepositRequestType', models.DO_NOTHING) class Meta: db_table = 'deposit_request' def __str__(self): meta = None if self.metadata: from json import dumps meta = dumps(self.metadata) archive_name = None if self.archive: archive_name = self.archive.name return str({ 'id': self.id, 'deposit': self.deposit, 'metadata': meta, 'archive': archive_name }) class DepositCollection(models.Model): id = models.BigAutoField(primary_key=True) # Human readable name for the collection type e.g HAL, arXiv, etc... name = models.TextField() class Meta: db_table = 'deposit_collection' def __str__(self): return str({'id': self.id, 'name': self.name}) diff --git a/swh/deposit/parsers.py b/swh/deposit/parsers.py index ce231c87..52fcc10b 100644 --- a/swh/deposit/parsers.py +++ b/swh/deposit/parsers.py @@ -1,76 +1,83 @@ # Copyright (C) 2017-2018 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 """Module in charge of defining parsers with SWORD 2.0 supported mediatypes. """ import xmltodict from django.conf import settings from rest_framework.parsers import BaseParser from rest_framework.parsers import FileUploadParser from rest_framework.parsers import MultiPartParser class SWHFileUploadZipParser(FileUploadParser): """File upload parser limited to zip archive. """ media_type = 'application/zip' class SWHFileUploadTarParser(FileUploadParser): """File upload parser limited to tarball (tar, tar.gz, tar.*) archives. """ media_type = 'application/x-tar' class SWHXMLParser(BaseParser): """ XML parser. """ media_type = 'application/xml' def parse(self, stream, media_type=None, parser_context=None): """ Parses the incoming bytestream as XML and returns the resulting data. """ parser_context = parser_context or {} encoding = parser_context.get('encoding', settings.DEFAULT_CHARSET) data = xmltodict.parse(stream, encoding=encoding, process_namespaces=False) if 'entry' in data: data = data['entry'] return data class SWHAtomEntryParser(SWHXMLParser): """Atom entry parser limited to specific mediatype """ media_type = 'application/atom+xml;type=entry' + def parse(self, stream, media_type=None, parser_context=None): + # We do not actually want to parse the stream yet + # because we want to keep the raw data as well + # this is done later in the atom entry call + # (cf. swh.deposit.api.common.SWHBaseDeposit._atom_entry) + return stream + class SWHMultiPartParser(MultiPartParser): """Multipart parser limited to a subset of mediatypes. """ media_type = 'multipart/*; *' def parse_xml(raw_content): """Parse xml body. Args: raw_content (bytes): The content to parse Returns: content parsed as dict. """ return SWHXMLParser().parse(raw_content) diff --git a/swh/deposit/templates/deposit/status.xml b/swh/deposit/templates/deposit/status.xml index 25b1a6f5..a8378ef7 100644 --- a/swh/deposit/templates/deposit/status.xml +++ b/swh/deposit/templates/deposit/status.xml @@ -1,8 +1,11 @@ {{ deposit_id }} {{ status }} {{ status_detail }} {% if swh_id is not None %}{{ swh_id }}{% endif %} + {% if swh_id_context is not None %}{{ swh_id_context }}{% endif %} + {% if swh_anchor_id is not None %}{{ swh_anchor_id }}{% endif %} + {% if swh_anchor_id_context is not None %}{{ swh_anchor_id_context }}{% endif %} diff --git a/swh/deposit/tests/api/test_deposit_atom.py b/swh/deposit/tests/api/test_deposit_atom.py index 09ba9a8b..b4096b80 100644 --- a/swh/deposit/tests/api/test_deposit_atom.py +++ b/swh/deposit/tests/api/test_deposit_atom.py @@ -1,517 +1,538 @@ # Copyright (C) 2017-2018 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 from django.core.urlresolvers import reverse from io import BytesIO from nose.tools import istest from rest_framework import status from rest_framework.test import APITestCase from swh.deposit.config import COL_IRI, DEPOSIT_STATUS_DEPOSITED from swh.deposit.models import Deposit, DepositRequest from swh.deposit.parsers import parse_xml from ..common import BasicTestCase, WithAuthTestCase class DepositAtomEntryTestCase(APITestCase, WithAuthTestCase, BasicTestCase): """Try and post atom entry deposit. """ def setUp(self): super().setUp() self.atom_entry_data0 = b""" Awesome Compiler hal urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a %s 2017-10-07T15:17:08Z some awesome author something awesome-compiler This is an awesome compiler destined to awesomely compile stuff and other stuff compiler,programming,language 2005-10-07T17:17:08Z 2005-10-07T17:17:08Z release note related link Awesome https://hoster.org/awesome-compiler GNU/Linux 0.0.1 running all """ self.atom_entry_data1 = b""" hal urn:uuid:2225c695-cfb8-4ebb-aaaa-80da344efa6a 2017-10-07T15:17:08Z some awesome author something awesome-compiler This is an awesome compiler destined to awesomely compile stuff and other stuff compiler,programming,language 2005-10-07T17:17:08Z 2005-10-07T17:17:08Z release note related link Awesome https://hoster.org/awesome-compiler GNU/Linux 0.0.1 running all """ self.atom_entry_data2 = b""" %s """ self.atom_entry_data_empty_body = b""" """ self.atom_entry_data3 = b""" something """ self.atom_entry_data_atom_only = b""" Awesome Compiler urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a 1785io25c695 2017-10-07T15:17:08Z some awesome author """ self.atom_entry_data_codemeta = b""" Awesome Compiler urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a 1785io25c695 1785io25c695 origin url other identifier, DOI, ARK Domain description key-word 1 key-word 2 creation date publication date comment article name article id Collaboration/Projet project name id see also Sponsor A Sponsor B Platform/OS dependencies Version active license url spdx .Net Framework 3.0 Python2.3 author1 Inria UPMC author2 Inria UPMC http://code.com language 1 language 2 http://issuetracker.com """ # noqa self.atom_entry_data_dc_codemeta = b""" %s hal-01587361 https://hal.inria.fr/hal-01587361 https://hal.inria.fr/hal-01587361/document https://hal.inria.fr/hal-01587361/file/AffectationRO-v1.0.0.zip doi:10.5281/zenodo.438684 The assignment problem AffectationRO Gruenpeter, Morane [INFO] Computer Science [cs] [INFO.INFO-RO] Computer Science [cs]/Operations Research [cs.RO] SOFTWARE Project in OR: The assignment problemA java implementation for the assignment problem first release description fr 2015-06-01 2017-10-19 en url stable Version sur hal Version entre par lutilisateur Mots-cls Commentaire Rfrence interne Collaboration/Projet nom du projet id Voir aussi Financement Projet ANR Projet Europen Platform/OS Dpendances Etat du dveloppement license url spdx Outils de dveloppement- outil no1 Outils de dveloppement- outil no2 http://code.com language 1 language 2 """ # noqa self.atom_entry_tei = b"""HAL TEI export of hal-01587083CCSDDistributed under a Creative Commons Attribution 4.0 International License

HAL API platform

questionnaire software metadataMoraneGruenpeter7de56c632362954fa84172cad80afe4einria.fr1556733MoraneGruenpeterf85a43a5fb4a2e0778a77e017f28c8fdgmail.com2017-09-29 11:21:322017-10-03 17:20:132017-10-03 17:20:132017-09-292017-09-29contributorMoraneGruenpeterf85a43a5fb4a2e0778a77e017f28c8fdgmail.comCCSDhal-01587083https://hal.inria.fr/hal-01587083gruenpeter:hal-0158708320172017questionnaire software metadataMoraneGruenpeter7de56c632362954fa84172cad80afe4einria.fr1556733EnglishComputer Science [cs]SoftwareIRILLInitiative pour la Recherche et l'Innovation sur le Logiciel Libre
https://www.irill.org/Universite Pierre et Marie Curie - Paris 6UPMC
4 place Jussieu - 75005 Paris
http://www.upmc.fr/Institut National de Recherche en Informatique et en AutomatiqueInria
Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex
http://www.inria.fr/en/Universite Paris Diderot - Paris 7UPD7
5 rue Thomas-Mann - 75205 Paris cedex 13
http://www.univ-paris-diderot.fr""" # noqa self.atom_entry_data_badly_formatted = b""" """ self.atom_error_with_decimal = b""" Composing a Web of Audio Applications hal hal-01243065 hal-01243065 https://hal-test.archives-ouvertes.fr/hal-01243065 test DSP programming,Web,Composability,Faust 2017-05-03T16:08:47+02:00 The Web offers a great opportunity to share, deploy and use programs without installation difficulties. In this article we explore the idea of freely combining/composing real-time audio applications deployed on the Web using Faust audio DSP language. 1 10.4 phpstorm stable linux php python C GNU General Public License v3.0 only CeCILL Free Software License Agreement v1.1 HAL hal@ccsd.cnrs.fr Someone Nice someone@nice.fr FFJ """ # noqa @istest def post_deposit_atom_entry_serialization_error(self): """Posting an initial atom entry should return 201 with deposit receipt """ # given # when response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=self.atom_error_with_decimal, HTTP_SLUG='external-id', HTTP_IN_PROGRESS='false') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) dr = DepositRequest.objects.get(deposit=deposit) self.assertIsNotNone(dr.metadata) sw_version = dr.metadata.get('codemeta:softwareVersion') self.assertEquals(sw_version, '10.4') @istest def post_deposit_atom_empty_body_request(self): """Posting empty body request should return a 400 response """ response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=self.atom_entry_data_empty_body) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) @istest def post_deposit_atom_badly_formatted_is_a_bad_request(self): """Posting a badly formatted atom should return a 400 response """ response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=self.atom_entry_data_badly_formatted) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) @istest def post_deposit_atom_without_slug_header_is_bad_request(self): """Posting an atom entry without a slug header should return a 400 """ url = reverse(COL_IRI, args=[self.collection.name]) # when response = self.client.post( url, content_type='application/atom+xml;type=entry', data=self.atom_entry_data0, # + headers HTTP_IN_PROGRESS='false') self.assertIn(b'Missing SLUG header', response.content) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) @istest def post_deposit_atom_unknown_collection(self): """Posting an atom entry to an unknown collection should return a 404 """ response = self.client.post( reverse(COL_IRI, args=['unknown-one']), content_type='application/atom+xml;type=entry', data=self.atom_entry_data3, HTTP_SLUG='something') self.assertEqual(response.status_code, status.HTTP_404_NOT_FOUND) @istest def post_deposit_atom_entry_initial(self): """Posting an initial atom entry should return 201 with deposit receipt """ # given external_id = 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a' with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) atom_entry_data = self.atom_entry_data0 % external_id.encode('utf-8') # when response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=atom_entry_data, HTTP_SLUG='external-id', HTTP_IN_PROGRESS='false') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.client, self.user) # one associated request to a deposit deposit_request = DepositRequest.objects.get(deposit=deposit) self.assertIsNotNone(deposit_request.metadata) + self.assertEquals( + deposit_request.raw_metadata, atom_entry_data.decode('utf-8')) self.assertFalse(bool(deposit_request.archive)) @istest def post_deposit_atom_entry_with_codemeta(self): """Posting an initial atom entry should return 201 with deposit receipt """ # given external_id = 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a' with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) atom_entry_data = self.atom_entry_data_dc_codemeta % ( external_id.encode('utf-8'), ) # when response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=atom_entry_data, HTTP_SLUG='external-id', HTTP_IN_PROGRESS='false') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.client, self.user) # one associated request to a deposit deposit_request = DepositRequest.objects.get(deposit=deposit) self.assertIsNotNone(deposit_request.metadata) + self.assertEquals( + deposit_request.raw_metadata, atom_entry_data.decode('utf-8')) self.assertFalse(bool(deposit_request.archive)) @istest def test_post_deposit_atom_entry_tei(self): """Posting initial atom entry as TEI should return 201 with receipt """ # given external_id = 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a' with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) atom_entry_data = self.atom_entry_tei # when response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=atom_entry_data, HTTP_SLUG=external_id, HTTP_IN_PROGRESS='false') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.client, self.user) # one associated request to a deposit deposit_request = DepositRequest.objects.get(deposit=deposit) self.assertIsNotNone(deposit_request.metadata) + self.assertEquals( + deposit_request.raw_metadata, atom_entry_data.decode('utf-8')) self.assertFalse(bool(deposit_request.archive)) @istest def post_deposit_atom_entry_multiple_steps(self): """After initial deposit, updating a deposit should return a 201 """ # given external_id = 'urn:uuid:2225c695-cfb8-4ebb-aaaa-80da344efa6a' with self.assertRaises(Deposit.DoesNotExist): deposit = Deposit.objects.get(external_id=external_id) # when response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=self.atom_entry_data1, HTTP_IN_PROGRESS='True', HTTP_SLUG=external_id) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = int(response_content['deposit_id']) deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.status, 'partial') self.assertEqual(deposit.client, self.user) # one associated request to a deposit deposit_requests = DepositRequest.objects.filter(deposit=deposit) self.assertEqual(len(deposit_requests), 1) atom_entry_data = self.atom_entry_data2 % external_id.encode('utf-8') update_uri = response._headers['location'][1] # when updating the first deposit post response = self.client.post( update_uri, content_type='application/atom+xml;type=entry', data=atom_entry_data, HTTP_IN_PROGRESS='False') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = int(response_content['deposit_id']) deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.client, self.user) self.assertEqual(len(Deposit.objects.all()), 1) # now 2 associated requests to a same deposit - deposit_requests = DepositRequest.objects.filter(deposit=deposit) + deposit_requests = DepositRequest.objects.filter( + deposit=deposit).order_by('id') self.assertEqual(len(deposit_requests), 2) - for deposit_request in deposit_requests: + expected_meta = [ + { + 'metadata': parse_xml(self.atom_entry_data1), + 'raw_metadata': self.atom_entry_data1.decode('utf-8'), + }, + { + 'metadata': parse_xml(atom_entry_data), + 'raw_metadata': atom_entry_data.decode('utf-8'), + } + ] + + for i, deposit_request in enumerate(deposit_requests): actual_metadata = deposit_request.metadata - self.assertIsNotNone(actual_metadata) + self.assertEquals(actual_metadata, + expected_meta[i]['metadata']) + self.assertEquals(deposit_request.raw_metadata, + expected_meta[i]['raw_metadata']) self.assertFalse(bool(deposit_request.archive)) diff --git a/swh/deposit/tests/api/test_deposit_binary.py b/swh/deposit/tests/api/test_deposit_binary.py index 469f8e6e..73734396 100644 --- a/swh/deposit/tests/api/test_deposit_binary.py +++ b/swh/deposit/tests/api/test_deposit_binary.py @@ -1,652 +1,656 @@ # Copyright (C) 2017-2018 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 from django.core.files.uploadedfile import InMemoryUploadedFile from django.core.urlresolvers import reverse from io import BytesIO from nose.tools import istest from rest_framework import status from rest_framework.test import APITestCase from swh.deposit.tests import TEST_CONFIG from swh.deposit.config import COL_IRI, EM_IRI from swh.deposit.config import DEPOSIT_STATUS_DEPOSITED from swh.deposit.models import Deposit, DepositRequest from swh.deposit.parsers import parse_xml -from ..common import BasicTestCase, WithAuthTestCase, create_arborescence_archive -from ..common import FileSystemCreationRoutine +from ..common import ( + BasicTestCase, WithAuthTestCase, create_arborescence_archive, + FileSystemCreationRoutine +) class DepositTestCase(APITestCase, WithAuthTestCase, BasicTestCase, FileSystemCreationRoutine): """Try and upload one single deposit """ def setUp(self): super().setUp() self.atom_entry_data0 = b""" Awesome Compiler hal urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a %s 2017-10-07T15:17:08Z some awesome author something awesome-compiler This is an awesome compiler destined to awesomely compile stuff and other stuff compiler,programming,language 2005-10-07T17:17:08Z 2005-10-07T17:17:08Z release note related link Awesome https://hoster.org/awesome-compiler GNU/Linux 0.0.1 running all """ self.atom_entry_data1 = b""" hal urn:uuid:2225c695-cfb8-4ebb-aaaa-80da344efa6a 2017-10-07T15:17:08Z some awesome author something awesome-compiler This is an awesome compiler destined to awesomely compile stuff and other stuff compiler,programming,language 2005-10-07T17:17:08Z 2005-10-07T17:17:08Z release note related link Awesome https://hoster.org/awesome-compiler GNU/Linux 0.0.1 running all """ self.atom_entry_data2 = b""" %s """ self.atom_entry_data_empty_body = b""" """ self.atom_entry_data3 = b""" something """ self.data_atom_entry_ok = b""" Title urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a 2005-10-07T17:17:08Z Contributor The abstract The abstract Access Rights Alternative Title Date Available Bibliographic Citation # noqa Contributor Description Has Part Has Version Identifier Is Part Of Publisher References Rights Holder Source Title Type """ @istest def post_deposit_binary_without_slug_header_is_bad_request(self): """Posting a binary deposit without slug header should return 400 """ url = reverse(COL_IRI, args=[self.collection.name]) # when response = self.client.post( url, content_type='application/zip', # as zip data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') self.assertIn(b'Missing SLUG header', response.content) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) @istest def post_deposit_binary_upload_final_and_status_check(self): """Binary upload with correct headers should return 201 with receipt """ # given url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id-1' # when response = self.client.post( url, content_type='application/zip', # as zip data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], # other headers needs HTTP_ prefix to be taken into account HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=%s' % ( self.archive['name'], )) # then response_content = parse_xml(BytesIO(response.content)) self.assertEqual(response.status_code, status.HTTP_201_CREATED) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_request = DepositRequest.objects.get(deposit=deposit) self.assertEquals(deposit_request.deposit, deposit) self.assertRegex(deposit_request.archive.name, self.archive['name']) + self.assertIsNone(deposit_request.metadata) + self.assertIsNone(deposit_request.raw_metadata) response_content = parse_xml(BytesIO(response.content)) self.assertEqual(response_content['deposit_archive'], self.archive['name']) self.assertEqual(int(response_content['deposit_id']), deposit.id) self.assertEqual(response_content['deposit_status'], deposit.status) edit_se_iri = reverse('edit_se_iri', args=[self.collection.name, deposit.id]) self.assertEqual(response._headers['location'], ('Location', 'http://testserver' + edit_se_iri)) @istest def post_deposit_binary_upload_supports_zip_or_tar(self): """Binary upload with content-type not in [zip,x-tar] should return 415 """ # given url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id-1' # when response = self.client.post( url, content_type='application/octet-stream', data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') # then self.assertEqual(response.status_code, status.HTTP_415_UNSUPPORTED_MEDIA_TYPE) with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) @istest def post_deposit_binary_fails_if_unsupported_packaging_header( self): """Bin deposit without supported content_disposition header returns 400 """ # given url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id' # when response = self.client.post( url, content_type='application/zip', data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='something-unsupported', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') # then self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) @istest def post_deposit_binary_upload_fail_if_no_content_disposition_header( self): """Binary upload without content_disposition header should return 400 """ # given url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id' # when response = self.client.post( url, content_type='application/zip', data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false') # then self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) @istest def post_deposit_mediation_not_supported(self): """Binary upload with mediation should return a 412 response """ # given url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id-1' # when response = self.client.post( url, content_type='application/zip', data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_ON_BEHALF_OF='someone', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') # then self.assertEqual(response.status_code, status.HTTP_412_PRECONDITION_FAILED) with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) @istest def post_deposit_binary_upload_fail_if_upload_size_limit_exceeded( self): """Binary upload must not exceed the limit set up... """ # given url = reverse(COL_IRI, args=[self.collection.name]) archive = create_arborescence_archive( self.root_path, 'archive2', 'file2', b'some content in file', up_to_size=TEST_CONFIG['max_upload_size']) external_id = 'some-external-id' # when response = self.client.post( url, content_type='application/zip', data=archive['data'], # + headers CONTENT_LENGTH=archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') # then self.assertEqual(response.status_code, status.HTTP_413_REQUEST_ENTITY_TOO_LARGE) self.assertRegex(response.content, b'Upload size limit exceeded') with self.assertRaises(Deposit.DoesNotExist): Deposit.objects.get(external_id=external_id) @istest def post_deposit_2_post_2_different_deposits(self): """2 posting deposits should return 2 different 201 with receipt """ url = reverse(COL_IRI, args=[self.collection.name]) # when response = self.client.post( url, content_type='application/zip', # as zip data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG='some-external-id-1', HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) deposits = Deposit.objects.all() self.assertEqual(len(deposits), 1) self.assertEqual(deposits[0], deposit) # second post response = self.client.post( url, content_type='application/x-tar', # as zip data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG='another-external-id', HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename1') self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id2 = response_content['deposit_id'] deposit2 = Deposit.objects.get(pk=deposit_id2) self.assertNotEqual(deposit, deposit2) deposits = Deposit.objects.all().order_by('id') self.assertEqual(len(deposits), 2) self.assertEqual(list(deposits), [deposit, deposit2]) @istest def post_deposit_binary_and_post_to_add_another_archive(self): """Updating a deposit should return a 201 with receipt """ # given url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id-1' # when response = self.client.post( url, content_type='application/zip', # as zip data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='true', HTTP_CONTENT_DISPOSITION='attachment; filename=%s' % ( self.archive['name'], )) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, 'partial') self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_request = DepositRequest.objects.get(deposit=deposit) self.assertEquals(deposit_request.deposit, deposit) self.assertEquals(deposit_request.type.name, 'archive') self.assertRegex(deposit_request.archive.name, self.archive['name']) # 2nd archive to upload archive2 = create_arborescence_archive( self.root_path, 'archive2', 'file2', b'some other content in file') # uri to update the content update_uri = reverse(EM_IRI, args=[self.collection.name, deposit_id]) # adding another archive for the deposit and finalizing it response = self.client.post( update_uri, content_type='application/zip', # as zip data=archive2['data'], # + headers CONTENT_LENGTH=archive2['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=archive2['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_CONTENT_DISPOSITION='attachment; filename=%s' % ( archive2['name'])) self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_requests = list(DepositRequest.objects.filter(deposit=deposit). order_by('id')) # 2 deposit requests for the same deposit self.assertEquals(len(deposit_requests), 2) self.assertEquals(deposit_requests[0].deposit, deposit) self.assertEquals(deposit_requests[0].type.name, 'archive') self.assertRegex(deposit_requests[0].archive.name, self.archive['name']) self.assertEquals(deposit_requests[1].deposit, deposit) self.assertEquals(deposit_requests[1].type.name, 'archive') self.assertRegex(deposit_requests[1].archive.name, archive2['name']) # only 1 deposit in db deposits = Deposit.objects.all() self.assertEqual(len(deposits), 1) @istest def post_deposit_then_post_or_put_is_refused_when_status_ready(self): """Updating a deposit with status 'ready' should return a 400 """ url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id-1' # when response = self.client.post( url, content_type='application/zip', # as zip data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_request = DepositRequest.objects.get(deposit=deposit) self.assertEquals(deposit_request.deposit, deposit) self.assertRegex(deposit_request.archive.name, 'filename0') # updating/adding is forbidden # uri to update the content edit_se_iri = reverse( 'edit_se_iri', args=[self.collection.name, deposit_id]) em_iri = reverse( 'em_iri', args=[self.collection.name, deposit_id]) # Testing all update/add endpoint should fail # since the status is ready archive2 = create_arborescence_archive( self.root_path, 'archive2', 'file2', b'some content in file 2') # replacing file is no longer possible since the deposit's # status is ready r = self.client.put( em_iri, content_type='application/zip', data=archive2['data'], CONTENT_LENGTH=archive2['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=archive2['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') self.assertEquals(r.status_code, status.HTTP_400_BAD_REQUEST) # adding file is no longer possible since the deposit's status # is ready r = self.client.post( em_iri, content_type='application/zip', data=archive2['data'], CONTENT_LENGTH=archive2['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=archive2['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') self.assertEquals(r.status_code, status.HTTP_400_BAD_REQUEST) # replacing metadata is no longer possible since the deposit's # status is ready r = self.client.put( edit_se_iri, content_type='application/atom+xml;type=entry', data=self.data_atom_entry_ok, CONTENT_LENGTH=len(self.data_atom_entry_ok), HTTP_SLUG=external_id) self.assertEquals(r.status_code, status.HTTP_400_BAD_REQUEST) # adding new metadata is no longer possible since the # deposit's status is ready r = self.client.post( edit_se_iri, content_type='application/atom+xml;type=entry', data=self.data_atom_entry_ok, CONTENT_LENGTH=len(self.data_atom_entry_ok), HTTP_SLUG=external_id) self.assertEquals(r.status_code, status.HTTP_400_BAD_REQUEST) archive_content = b'some content representing archive' archive = InMemoryUploadedFile( BytesIO(archive_content), field_name='archive0', name='archive0', content_type='application/zip', size=len(archive_content), charset=None) atom_entry = InMemoryUploadedFile( BytesIO(self.data_atom_entry_ok), field_name='atom0', name='atom0', content_type='application/atom+xml; charset="utf-8"', size=len(self.data_atom_entry_ok), charset='utf-8') # replacing multipart metadata is no longer possible since the # deposit's status is ready r = self.client.put( edit_se_iri, format='multipart', data={ 'archive': archive, 'atom_entry': atom_entry, }) self.assertEquals(r.status_code, status.HTTP_400_BAD_REQUEST) # adding new metadata is no longer possible since the # deposit's status is ready r = self.client.post( edit_se_iri, format='multipart', data={ 'archive': archive, 'atom_entry': atom_entry, }) self.assertEquals(r.status_code, status.HTTP_400_BAD_REQUEST) diff --git a/swh/deposit/tests/api/test_deposit_multipart.py b/swh/deposit/tests/api/test_deposit_multipart.py index a53b5696..8388d2ec 100644 --- a/swh/deposit/tests/api/test_deposit_multipart.py +++ b/swh/deposit/tests/api/test_deposit_multipart.py @@ -1,395 +1,408 @@ # Copyright (C) 2017-2018 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 from django.core.files.uploadedfile import InMemoryUploadedFile from django.core.urlresolvers import reverse from io import BytesIO from nose.tools import istest from rest_framework import status from rest_framework.test import APITestCase from swh.deposit.config import COL_IRI from swh.deposit.config import DEPOSIT_STATUS_DEPOSITED from swh.deposit.models import Deposit, DepositRequest from swh.deposit.parsers import parse_xml from ..common import BasicTestCase, WithAuthTestCase from ..common import FileSystemCreationRoutine class DepositMultipartTestCase(APITestCase, WithAuthTestCase, BasicTestCase, FileSystemCreationRoutine): """Post multipart deposit scenario """ def setUp(self): super().setUp() self.data_atom_entry_ok = b""" Title urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a 2005-10-07T17:17:08Z Contributor The abstract The abstract Access Rights Alternative Title Date Available Bibliographic Citation # noqa Contributor Description Has Part Has Version Identifier Is Part Of Publisher References Rights Holder Source Title Type """ self.data_atom_entry_update_in_place = """ urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa7b Title Type """ @istest def post_deposit_multipart_without_slug_header_is_bad_request(self): # given url = reverse(COL_IRI, args=[self.collection.name]) data_atom_entry = self.data_atom_entry_ok archive_content = b'some content representing archive' archive = InMemoryUploadedFile( BytesIO(archive_content), field_name='archive0', name='archive0', content_type='application/zip', size=len(archive_content), charset=None) atom_entry = InMemoryUploadedFile( BytesIO(data_atom_entry), field_name='atom0', name='atom0', content_type='application/atom+xml; charset="utf-8"', size=len(data_atom_entry), charset='utf-8') # when response = self.client.post( url, format='multipart', data={ 'archive': archive, 'atom_entry': atom_entry, }, # + headers HTTP_IN_PROGRESS='false') self.assertIn(b'Missing SLUG header', response.content) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) @istest def post_deposit_multipart_zip(self): """one multipart deposit (zip+xml) should be accepted """ # given url = reverse(COL_IRI, args=[self.collection.name]) # from django.core.files import uploadedfile data_atom_entry = self.data_atom_entry_ok archive = InMemoryUploadedFile( BytesIO(self.archive['data']), field_name=self.archive['name'], name=self.archive['name'], content_type='application/zip', size=self.archive['length'], charset=None) atom_entry = InMemoryUploadedFile( BytesIO(data_atom_entry), field_name='atom0', name='atom0', content_type='application/atom+xml; charset="utf-8"', size=len(data_atom_entry), charset='utf-8') external_id = 'external-id' # when response = self.client.post( url, format='multipart', data={ 'archive': archive, 'atom_entry': atom_entry, }, # + headers HTTP_IN_PROGRESS='false', HTTP_SLUG=external_id) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_requests = DepositRequest.objects.filter(deposit=deposit) self.assertEquals(len(deposit_requests), 2) for deposit_request in deposit_requests: self.assertEquals(deposit_request.deposit, deposit) if deposit_request.type.name == 'archive': self.assertRegex(deposit_request.archive.name, self.archive['name']) + self.assertIsNone(deposit_request.metadata) + self.assertIsNone(deposit_request.raw_metadata) else: self.assertEquals( deposit_request.metadata['id'], 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a') + self.assertEquals(deposit_request.raw_metadata, + data_atom_entry.decode('utf-8')) @istest def post_deposit_multipart_tar(self): """one multipart deposit (tar+xml) should be accepted """ # given url = reverse(COL_IRI, args=[self.collection.name]) # from django.core.files import uploadedfile data_atom_entry = self.data_atom_entry_ok archive = InMemoryUploadedFile( BytesIO(self.archive['data']), field_name=self.archive['name'], name=self.archive['name'], content_type='application/x-tar', size=self.archive['length'], charset=None) atom_entry = InMemoryUploadedFile( BytesIO(data_atom_entry), field_name='atom0', name='atom0', content_type='application/atom+xml; charset="utf-8"', size=len(data_atom_entry), charset='utf-8') external_id = 'external-id' # when response = self.client.post( url, format='multipart', data={ 'archive': archive, 'atom_entry': atom_entry, }, # + headers HTTP_IN_PROGRESS='false', HTTP_SLUG=external_id) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_requests = DepositRequest.objects.filter(deposit=deposit) self.assertEquals(len(deposit_requests), 2) for deposit_request in deposit_requests: self.assertEquals(deposit_request.deposit, deposit) if deposit_request.type.name == 'archive': self.assertRegex(deposit_request.archive.name, self.archive['name']) + self.assertIsNone(deposit_request.metadata) + self.assertIsNone(deposit_request.raw_metadata) else: self.assertEquals( deposit_request.metadata['id'], 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a') + self.assertEquals(deposit_request.raw_metadata, + data_atom_entry.decode('utf-8')) @istest def post_deposit_multipart_put_to_replace_metadata(self): """One multipart deposit followed by a metadata update should be accepted """ # given url = reverse(COL_IRI, args=[self.collection.name]) data_atom_entry = self.data_atom_entry_ok archive = InMemoryUploadedFile( BytesIO(self.archive['data']), field_name=self.archive['name'], name=self.archive['name'], content_type='application/zip', size=self.archive['length'], charset=None) atom_entry = InMemoryUploadedFile( BytesIO(data_atom_entry), field_name='atom0', name='atom0', content_type='application/atom+xml; charset="utf-8"', size=len(data_atom_entry), charset='utf-8') external_id = 'external-id' # when response = self.client.post( url, format='multipart', data={ 'archive': archive, 'atom_entry': atom_entry, }, # + headers HTTP_IN_PROGRESS='true', HTTP_SLUG=external_id) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) deposit_id = response_content['deposit_id'] deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, 'partial') self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_requests = DepositRequest.objects.filter(deposit=deposit) self.assertEquals(len(deposit_requests), 2) for deposit_request in deposit_requests: self.assertEquals(deposit_request.deposit, deposit) if deposit_request.type.name == 'archive': self.assertRegex(deposit_request.archive.name, self.archive['name']) else: self.assertEquals( deposit_request.metadata['id'], 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a') + self.assertEquals(deposit_request.raw_metadata, + data_atom_entry.decode('utf-8')) replace_metadata_uri = response._headers['location'][1] response = self.client.put( replace_metadata_uri, content_type='application/atom+xml;type=entry', data=self.data_atom_entry_update_in_place, HTTP_IN_PROGRESS='false') self.assertEqual(response.status_code, status.HTTP_204_NO_CONTENT) # deposit_id did not change deposit = Deposit.objects.get(pk=deposit_id) self.assertEqual(deposit.status, DEPOSIT_STATUS_DEPOSITED) self.assertEqual(deposit.external_id, external_id) self.assertEqual(deposit.collection, self.collection) self.assertEqual(deposit.client, self.user) self.assertIsNone(deposit.swh_id) deposit_requests = DepositRequest.objects.filter(deposit=deposit) self.assertEquals(len(deposit_requests), 2) for deposit_request in deposit_requests: self.assertEquals(deposit_request.deposit, deposit) if deposit_request.type.name == 'archive': self.assertRegex(deposit_request.archive.name, self.archive['name']) else: self.assertEquals( deposit_request.metadata['id'], 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa7b') + self.assertEquals( + deposit_request.raw_metadata, + self.data_atom_entry_update_in_place) # FAILURE scenarios @istest def post_deposit_multipart_only_archive_and_atom_entry(self): """Multipart deposit only accepts one archive and one atom+xml""" # given url = reverse(COL_IRI, args=[self.collection.name]) archive_content = b'some content representing archive' archive = InMemoryUploadedFile(BytesIO(archive_content), field_name='archive0', name='archive0', content_type='application/x-tar', size=len(archive_content), charset=None) other_archive_content = b"some-other-content" other_archive = InMemoryUploadedFile(BytesIO(other_archive_content), field_name='atom0', name='atom0', content_type='application/x-tar', size=len(other_archive_content), charset='utf-8') # when response = self.client.post( url, format='multipart', data={ 'archive': archive, 'atom_entry': other_archive, }, # + headers HTTP_IN_PROGRESS='false', HTTP_SLUG='external-id') # then self.assertEqual(response.status_code, status.HTTP_415_UNSUPPORTED_MEDIA_TYPE) self.assertTrue( 'Only 1 application/zip (or application/x-tar) archive' in response.content.decode('utf-8')) # when archive.seek(0) response = self.client.post( url, format='multipart', data={ 'archive': archive, }, # + headers HTTP_IN_PROGRESS='false', HTTP_SLUG='external-id') # then self.assertEqual(response.status_code, status.HTTP_415_UNSUPPORTED_MEDIA_TYPE) self.assertTrue( 'You must provide both 1 application/zip (or ' 'application/x-tar) and 1 atom+xml entry for ' 'multipart deposit' in response.content.decode('utf-8') ) diff --git a/swh/deposit/tests/api/test_deposit_read_metadata.py b/swh/deposit/tests/api/test_deposit_read_metadata.py index 2fe4ec6d..a55018f5 100644 --- a/swh/deposit/tests/api/test_deposit_read_metadata.py +++ b/swh/deposit/tests/api/test_deposit_read_metadata.py @@ -1,211 +1,211 @@ # Copyright (C) 2017-2018 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 json from django.core.urlresolvers import reverse from nose.tools import istest from rest_framework import status from rest_framework.test import APITestCase from swh.deposit.models import Deposit from swh.deposit.config import PRIVATE_GET_DEPOSIT_METADATA from swh.deposit.config import DEPOSIT_STATUS_LOAD_SUCCESS from swh.deposit.config import DEPOSIT_STATUS_PARTIAL from ...config import SWH_PERSON from ..common import BasicTestCase, WithAuthTestCase, CommonCreationRoutine class DepositReadMetadataTest(APITestCase, WithAuthTestCase, BasicTestCase, CommonCreationRoutine): """Deposit access to read metadata information on deposit. """ @istest def read_metadata(self): """Private metadata read api to existing deposit should return metadata """ deposit_id = self.create_deposit_partial() url = reverse(PRIVATE_GET_DEPOSIT_METADATA, args=[self.collection.name, deposit_id]) response = self.client.get(url) self.assertEqual(response.status_code, status.HTTP_200_OK) self.assertEquals(response._headers['content-type'][1], 'application/json') data = json.loads(response.content.decode('utf-8')) expected_meta = { 'origin': { 'url': 'https://hal-test.archives-ouvertes.fr/' + 'some-external-id', 'type': 'deposit' }, 'origin_metadata': { 'metadata': { '@xmlns': 'http://www.w3.org/2005/Atom', 'author': 'some awesome author', - 'external_identifier':'some-external-id', + 'external_identifier': 'some-external-id', 'url': 'https://hal-test.archives-ouvertes.fr/' + 'some-external-id' }, 'provider': { 'provider_name': 'hal', 'provider_type': 'deposit_client', 'provider_url': 'https://hal-test.archives-ouvertes.fr/', 'metadata': {} }, 'tool': { 'tool_name': 'swh-deposit', 'tool_version': '0.0.1', 'tool_configuration': { 'sword_version': '2' } } }, 'revision': { 'synthetic': True, 'committer_date': None, 'message': 'hal: Deposit %s in collection hal' % deposit_id, 'author': SWH_PERSON, 'committer': SWH_PERSON, 'date': None, 'metadata': { '@xmlns': 'http://www.w3.org/2005/Atom', 'author': 'some awesome author', 'external_identifier': 'some-external-id', 'url': 'https://hal-test.archives-ouvertes.fr/' + 'some-external-id' }, 'type': 'tar' }, 'branch_name': 'master', } self.assertEquals(data, expected_meta) @istest def read_metadata_revision_with_parent(self): """Private read metadata to a deposit (with parent) returns metadata """ swh_id = 'da78a9d4cf1d5d29873693fd496142e3a18c20fa' swh_persistent_id = 'swh:1:rev:%s' % swh_id deposit_id1 = self.create_deposit_with_status( status=DEPOSIT_STATUS_LOAD_SUCCESS, external_id='some-external-id', swh_id=swh_persistent_id) deposit_parent = Deposit.objects.get(pk=deposit_id1) self.assertEquals(deposit_parent.swh_id, swh_persistent_id) self.assertEquals(deposit_parent.external_id, 'some-external-id') self.assertEquals(deposit_parent.status, DEPOSIT_STATUS_LOAD_SUCCESS) deposit_id = self.create_deposit_partial( external_id='some-external-id') deposit = Deposit.objects.get(pk=deposit_id) self.assertEquals(deposit.external_id, 'some-external-id') self.assertEquals(deposit.swh_id, None) self.assertEquals(deposit.parent, deposit_parent) self.assertEquals(deposit.status, DEPOSIT_STATUS_PARTIAL) url = reverse(PRIVATE_GET_DEPOSIT_METADATA, args=[self.collection.name, deposit_id]) response = self.client.get(url) self.assertEqual(response.status_code, status.HTTP_200_OK) self.assertEquals(response._headers['content-type'][1], 'application/json') data = json.loads(response.content.decode('utf-8')) expected_meta = { 'origin': { 'url': 'https://hal-test.archives-ouvertes.fr/' + 'some-external-id', 'type': 'deposit' }, 'origin_metadata': { 'metadata': { '@xmlns': 'http://www.w3.org/2005/Atom', 'author': 'some awesome author', 'external_identifier': 'some-external-id', 'url': 'https://hal-test.archives-ouvertes.fr/' + 'some-external-id' }, 'provider': { 'provider_name': 'hal', 'provider_type': 'deposit_client', 'provider_url': 'https://hal-test.archives-ouvertes.fr/', 'metadata': {} }, 'tool': { 'tool_name': 'swh-deposit', 'tool_version': '0.0.1', 'tool_configuration': { 'sword_version': '2' } } }, 'revision': { 'synthetic': True, 'date': None, 'committer_date': None, 'author': SWH_PERSON, 'committer': SWH_PERSON, 'type': 'tar', 'message': 'hal: Deposit %s in collection hal' % deposit_id, 'metadata': { '@xmlns': 'http://www.w3.org/2005/Atom', 'author': 'some awesome author', 'external_identifier': 'some-external-id', 'url': 'https://hal-test.archives-ouvertes.fr/' + 'some-external-id' }, 'parents': [swh_id] }, 'branch_name': 'master', } self.assertEquals(data, expected_meta) @istest def access_to_nonexisting_deposit_returns_404_response(self): """Read unknown collection should return a 404 response """ unknown_id = '999' url = reverse(PRIVATE_GET_DEPOSIT_METADATA, args=[self.collection.name, unknown_id]) response = self.client.get(url) self.assertEqual(response.status_code, status.HTTP_404_NOT_FOUND) self.assertIn('Deposit with id %s does not exist' % unknown_id, response.content.decode('utf-8')) @istest def access_to_nonexisting_collection_returns_404_response(self): """Read unknown deposit should return a 404 response """ collection_name = 'non-existing' deposit_id = self.create_deposit_partial() url = reverse(PRIVATE_GET_DEPOSIT_METADATA, args=[collection_name, deposit_id]) response = self.client.get(url) self.assertEqual(response.status_code, status.HTTP_404_NOT_FOUND) self.assertIn('Unknown collection name %s' % collection_name, response.content.decode('utf-8'),) diff --git a/swh/deposit/tests/api/test_deposit_status.py b/swh/deposit/tests/api/test_deposit_status.py index ced39896..abbe07ff 100644 --- a/swh/deposit/tests/api/test_deposit_status.py +++ b/swh/deposit/tests/api/test_deposit_status.py @@ -1,230 +1,242 @@ # Copyright (C) 2017-2018 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 from django.core.urlresolvers import reverse from io import BytesIO from nose.tools import istest from rest_framework import status from rest_framework.test import APITestCase from swh.deposit.api.deposit_status import convert_status_detail from swh.deposit.config import (COL_IRI, STATE_IRI, DEPOSIT_STATUS_DEPOSITED, DEPOSIT_STATUS_REJECTED) from swh.deposit.models import Deposit, DEPOSIT_STATUS_DETAIL from swh.deposit.models import DEPOSIT_STATUS_LOAD_SUCCESS from swh.deposit.parsers import parse_xml from ..common import BasicTestCase, WithAuthTestCase, FileSystemCreationRoutine from ..common import CommonCreationRoutine class DepositStatusTestCase(APITestCase, WithAuthTestCase, BasicTestCase, FileSystemCreationRoutine, CommonCreationRoutine): """Status on deposit """ @istest def post_deposit_with_status_check(self): """Binary upload should be accepted """ # given url = reverse(COL_IRI, args=[self.collection.name]) external_id = 'some-external-id-1' # when response = self.client.post( url, content_type='application/zip', # as zip data=self.archive['data'], # + headers CONTENT_LENGTH=self.archive['length'], HTTP_SLUG=external_id, HTTP_CONTENT_MD5=self.archive['md5sum'], HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_IN_PROGRESS='false', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) deposit = Deposit.objects.get(external_id=external_id) status_url = reverse(STATE_IRI, args=[self.collection.name, deposit.id]) # check status status_response = self.client.get(status_url) self.assertEqual(status_response.status_code, status.HTTP_200_OK) r = parse_xml(BytesIO(status_response.content)) self.assertEqual(int(r['deposit_id']), deposit.id) self.assertEqual(r['deposit_status'], DEPOSIT_STATUS_DEPOSITED) self.assertEqual(r['deposit_status_detail'], DEPOSIT_STATUS_DETAIL[DEPOSIT_STATUS_DEPOSITED]) @istest - def status_with_swh_id(self): + def status_with_swh_information(self): _status = DEPOSIT_STATUS_LOAD_SUCCESS - _swh_id = '548b3c0a2bb43e1fca191e24b5803ff6b3bc7c10' + _context = 'https://hal.archives-ouvertes.fr/hal-01727745' + _swh_id = 'swh:1:dir:42a13fc721c8716ff695d0d62fc851d641f3a12b' + _swh_id_context = '%s;%s' % (_swh_id, _context) + _swh_anchor_id = 'swh:rev:1:548b3c0a2bb43e1fca191e24b5803ff6b3bc7c10' + _swh_anchor_id_context = '%s;%s' % (_swh_anchor_id, _context) # given deposit_id = self.create_deposit_with_status( status=_status, - swh_id=_swh_id) + swh_id=_swh_id, + swh_id_context=_swh_id_context, + swh_anchor_id=_swh_anchor_id, + swh_anchor_id_context=_swh_anchor_id_context + ) url = reverse(STATE_IRI, args=[self.collection.name, deposit_id]) # when status_response = self.client.get(url) # then self.assertEqual(status_response.status_code, status.HTTP_200_OK) r = parse_xml(BytesIO(status_response.content)) self.assertEqual(int(r['deposit_id']), deposit_id) self.assertEqual(r['deposit_status'], _status) self.assertEqual(r['deposit_status_detail'], DEPOSIT_STATUS_DETAIL[DEPOSIT_STATUS_LOAD_SUCCESS]) self.assertEqual(r['deposit_swh_id'], _swh_id) + self.assertEqual(r['deposit_swh_id_context'], _swh_id_context) + self.assertEqual(r['deposit_swh_anchor_id'], _swh_anchor_id) + self.assertEqual(r['deposit_swh_anchor_id_context'], + _swh_anchor_id_context) @istest def status_on_unknown_deposit(self): """Asking for the status of unknown deposit returns 404 response""" status_url = reverse(STATE_IRI, args=[self.collection.name, 999]) status_response = self.client.get(status_url) self.assertEqual(status_response.status_code, status.HTTP_404_NOT_FOUND) @istest def status_with_http_accept_header_should_not_break(self): """Asking deposit status with Accept header should return 200 """ deposit_id = self.create_deposit_partial() status_url = reverse(STATE_IRI, args=[ self.collection.name, deposit_id]) response = self.client.get( status_url, HTTP_ACCEPT='text/html,application/xml;q=9,*/*,q=8') self.assertEqual(response.status_code, status.HTTP_200_OK) @istest def convert_status_detail_empty(self): actual_status_detail = convert_status_detail({}) self.assertIsNone(actual_status_detail) actual_status_detail = convert_status_detail({'dummy-keys': []}) self.assertIsNone(actual_status_detail) actual_status_detail = convert_status_detail(None) self.assertIsNone(actual_status_detail) @istest def convert_status_detail(self): status_detail = { 'url': { 'summary': "At least one url field must be compatible with the client\'s domain name. The following url fields failed the check", # noqa 'fields': ['blahurl', 'testurl'], }, 'metadata': [ { 'summary': 'Mandatory fields missing', 'fields': ['url', 'title'], }, { 'summary': 'Alternate fields missing', 'fields': ['name or title', 'url or badurl'] } ], 'archive': [{ 'summary': 'Unreadable archive', 'fields': ['1'], }], } expected_status_detail = '''- Mandatory fields missing (url, title) - Alternate fields missing (name or title, url or badurl) - Unreadable archive (1) - At least one url field must be compatible with the client's domain name. The following url fields failed the check (blahurl, testurl) ''' # noqa actual_status_detail = convert_status_detail(status_detail) self.assertEqual(actual_status_detail, expected_status_detail) @istest def convert_status_detail_2(self): status_detail = { 'url': { 'summary': 'At least one compatible url field. Failed', 'fields': ['testurl'], }, 'metadata': [ { 'summary': 'Mandatory fields missing', 'fields': ['name'], }, ], 'archive': [ { 'summary': 'Invalid archive', 'fields': ['2'], }, { 'summary': 'Unsupported archive', 'fields': ['1'], } ], } expected_status_detail = '''- Mandatory fields missing (name) - Invalid archive (2) - Unsupported archive (1) - At least one compatible url field. Failed (testurl) ''' actual_status_detail = convert_status_detail(status_detail) self.assertEqual(actual_status_detail, expected_status_detail) @istest def convert_status_detail_3(self): status_detail = { 'url': { 'summary': 'At least one compatible url field', }, } expected_status_detail = '- At least one compatible url field\n' actual_status_detail = convert_status_detail(status_detail) self.assertEqual(actual_status_detail, expected_status_detail) @istest def status_on_deposit_rejected(self): _status = DEPOSIT_STATUS_REJECTED _swh_id = '548b3c0a2bb43e1fca191e24b5803ff6b3bc7c10' _status_detail = {'url': {'summary': 'Wrong url'}} # given deposit_id = self.create_deposit_with_status( status=_status, swh_id=_swh_id, status_detail=_status_detail) url = reverse(STATE_IRI, args=[self.collection.name, deposit_id]) # when status_response = self.client.get(url) # then self.assertEqual(status_response.status_code, status.HTTP_200_OK) r = parse_xml(BytesIO(status_response.content)) self.assertEqual(int(r['deposit_id']), deposit_id) self.assertEqual(r['deposit_status'], _status) self.assertEqual(r['deposit_status_detail'], '- Wrong url') self.assertEqual(r['deposit_swh_id'], _swh_id) diff --git a/swh/deposit/tests/api/test_deposit_update_status.py b/swh/deposit/tests/api/test_deposit_update_status.py index 3d6cc2da..23f35052 100644 --- a/swh/deposit/tests/api/test_deposit_update_status.py +++ b/swh/deposit/tests/api/test_deposit_update_status.py @@ -1,123 +1,136 @@ # Copyright (C) 2017-2018 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 json from django.core.urlresolvers import reverse from nose.tools import istest from rest_framework import status from rest_framework.test import APITestCase from swh.deposit.models import Deposit, DEPOSIT_STATUS_DETAIL from swh.deposit.config import PRIVATE_PUT_DEPOSIT, DEPOSIT_STATUS_VERIFIED from swh.deposit.config import DEPOSIT_STATUS_LOAD_SUCCESS from ..common import BasicTestCase class UpdateDepositStatusTest(APITestCase, BasicTestCase): """Update the deposit's status scenario """ def setUp(self): super().setUp() deposit = Deposit(status=DEPOSIT_STATUS_VERIFIED, collection=self.collection, client=self.user) deposit.save() self.deposit = Deposit.objects.get(pk=deposit.id) assert self.deposit.status == DEPOSIT_STATUS_VERIFIED @istest def update_deposit_status(self): """Existing status for update should return a 204 response """ url = reverse(PRIVATE_PUT_DEPOSIT, args=[self.collection.name, self.deposit.id]) possible_status = set(DEPOSIT_STATUS_DETAIL.keys()) - set( [DEPOSIT_STATUS_LOAD_SUCCESS]) for _status in possible_status: response = self.client.put( url, content_type='application/json', data=json.dumps({'status': _status})) self.assertEqual(response.status_code, status.HTTP_204_NO_CONTENT) deposit = Deposit.objects.get(pk=self.deposit.id) self.assertEquals(deposit.status, _status) @istest - def update_deposit_with_success_loading_and_swh_id(self): - """Existing status for update should return a 204 response + def update_deposit_status_with_info(self): + """Existing status for update with info should return a 204 response """ url = reverse(PRIVATE_PUT_DEPOSIT, args=[self.collection.name, self.deposit.id]) expected_status = DEPOSIT_STATUS_LOAD_SUCCESS + origin_url = 'something' + directory_id = '42a13fc721c8716ff695d0d62fc851d641f3a12b' revision_id = '47dc6b4636c7f6cba0df83e3d5490bf4334d987e' - expected_id = 'swh:1:rev:%s' % revision_id + expected_swh_id = 'swh:1:dir:%s' % directory_id + expected_swh_id_context = 'swh:1:dir:%s;origin=%s' % ( + directory_id, origin_url) + expected_swh_anchor_id = 'swh:1:rev:%s' % revision_id + expected_swh_anchor_id_context = 'swh:1:rev:%s;origin=%s' % ( + revision_id, origin_url) response = self.client.put( url, content_type='application/json', data=json.dumps({ 'status': expected_status, 'revision_id': revision_id, + 'directory_id': directory_id, + 'origin_url': origin_url, })) self.assertEqual(response.status_code, status.HTTP_204_NO_CONTENT) deposit = Deposit.objects.get(pk=self.deposit.id) self.assertEquals(deposit.status, expected_status) - self.assertEquals(deposit.swh_id, expected_id) + self.assertEquals(deposit.swh_id, expected_swh_id) + self.assertEquals(deposit.swh_id_context, expected_swh_id_context) + self.assertEquals(deposit.swh_anchor_id, expected_swh_anchor_id) + self.assertEquals(deposit.swh_anchor_id_context, + expected_swh_anchor_id_context) @istest def update_deposit_status_will_fail_with_unknown_status(self): """Unknown status for update should return a 400 response """ url = reverse(PRIVATE_PUT_DEPOSIT, args=[self.collection.name, self.deposit.id]) response = self.client.put( url, content_type='application/json', data=json.dumps({'status': 'unknown'})) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) @istest def update_deposit_status_will_fail_with_no_status_key(self): """No status provided for update should return a 400 response """ url = reverse(PRIVATE_PUT_DEPOSIT, args=[self.collection.name, self.deposit.id]) response = self.client.put( url, content_type='application/json', data=json.dumps({'something': 'something'})) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) @istest def update_deposit_status_success_without_swh_id_fail(self): """Providing successful status without swh_id should return a 400 """ url = reverse(PRIVATE_PUT_DEPOSIT, args=[self.collection.name, self.deposit.id]) response = self.client.put( url, content_type='application/json', data=json.dumps({'status': DEPOSIT_STATUS_LOAD_SUCCESS})) self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST) diff --git a/swh/deposit/tests/common.py b/swh/deposit/tests/common.py index 76a4f067..e595a783 100644 --- a/swh/deposit/tests/common.py +++ b/swh/deposit/tests/common.py @@ -1,562 +1,572 @@ # Copyright (C) 2017-2018 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 base64 import hashlib import os import shutil import tarfile import tempfile from django.core.urlresolvers import reverse from django.test import TestCase from io import BytesIO from nose.plugins.attrib import attr from rest_framework import status from swh.deposit.config import (COL_IRI, EM_IRI, EDIT_SE_IRI, DEPOSIT_STATUS_PARTIAL, DEPOSIT_STATUS_VERIFIED, DEPOSIT_STATUS_REJECTED, DEPOSIT_STATUS_DEPOSITED) from swh.deposit.models import DepositClient, DepositCollection, Deposit from swh.deposit.models import DepositRequest from swh.deposit.models import DepositRequestType from swh.deposit.parsers import parse_xml from swh.deposit.settings.testing import MEDIA_ROOT from swh.core import tarball def compute_info(archive_path): """Given a path, compute information on path. """ with open(archive_path, 'rb') as f: length = 0 sha1sum = hashlib.sha1() md5sum = hashlib.md5() data = b'' for chunk in f: sha1sum.update(chunk) md5sum.update(chunk) length += len(chunk) data += chunk return { 'dir': os.path.dirname(archive_path), 'name': os.path.basename(archive_path), 'path': archive_path, 'length': length, 'sha1sum': sha1sum.hexdigest(), 'md5sum': md5sum.hexdigest(), 'data': data } def _compress(path, extension, dir_path): """Compress path according to extension """ if extension == 'zip' or extension == 'tar': return tarball.compress(path, extension, dir_path) elif '.' in extension: split_ext = extension.split('.') if split_ext[0] != 'tar': raise ValueError( 'Development error, only zip or tar archive supported, ' '%s not supported' % extension) # deal with specific tar mode = split_ext[1] supported_mode = ['xz', 'gz', 'bz2'] if mode not in supported_mode: raise ValueError( 'Development error, only %s supported, %s not supported' % ( supported_mode, mode)) files = tarball._ls(dir_path) with tarfile.open(path, 'w:%s' % mode) as t: for fpath, fname in files: t.add(fpath, arcname=fname, recursive=False) return path def create_arborescence_archive(root_path, archive_name, filename, content, up_to_size=None, extension='zip'): """Build an archive named archive_name in the root_path. This archive contains one file named filename with the content content. Args: root_path (str): Location path of the archive to create archive_name (str): Archive's name (without extension) filename (str): Archive's content is only one filename content (bytes): Content of the filename up_to_size (int | None): Fill in the blanks size to oversize or complete an archive's size extension (str): Extension of the archive to write (default is zip) Returns: dict with the keys: - dir: the directory of that archive - path: full path to the archive - sha1sum: archive's sha1sum - length: archive's length """ os.makedirs(root_path, exist_ok=True) archive_path_dir = tempfile.mkdtemp(dir=root_path) dir_path = os.path.join(archive_path_dir, archive_name) os.mkdir(dir_path) filepath = os.path.join(dir_path, filename) _length = len(content) count = 0 batch_size = 128 with open(filepath, 'wb') as f: f.write(content) if up_to_size: # fill with blank content up to a given size count += _length while count < up_to_size: f.write(b'0'*batch_size) count += batch_size _path = '%s.%s' % (dir_path, extension) _path = _compress(_path, extension, dir_path) return compute_info(_path) def create_archive_with_archive(root_path, name, archive): """Create an archive holding another. """ invalid_archive_path = os.path.join(root_path, name) with tarfile.open(invalid_archive_path, 'w:gz') as _archive: _archive.add(archive['path'], arcname=archive['name']) return compute_info(invalid_archive_path) @attr('fs') class FileSystemCreationRoutine(TestCase): """Mixin intended for tests needed to tamper with archives. """ def setUp(self): """Define the test client and other test variables.""" super().setUp() self.root_path = '/tmp/swh-deposit/test/build-zip/' os.makedirs(self.root_path, exist_ok=True) self.archive = create_arborescence_archive( self.root_path, 'archive1', 'file1', b'some content in file') self.atom_entry = b""" Awesome Compiler urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a 1785io25c695 2017-10-07T15:17:08Z some awesome author https://hal-test.archives-ouvertes.fr """ def tearDown(self): super().tearDown() shutil.rmtree(self.root_path) def create_simple_binary_deposit(self, status_partial=True): response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/zip', data=self.archive['data'], CONTENT_LENGTH=self.archive['length'], HTTP_MD5SUM=self.archive['md5sum'], HTTP_SLUG='external-id', HTTP_IN_PROGRESS=status_partial, HTTP_CONTENT_DISPOSITION='attachment; filename=%s' % ( self.archive['name'], )) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) _status = response_content['deposit_status'] if status_partial: expected_status = DEPOSIT_STATUS_PARTIAL else: expected_status = DEPOSIT_STATUS_VERIFIED self.assertEqual(_status, expected_status) deposit_id = int(response_content['deposit_id']) return deposit_id def create_complex_binary_deposit(self, status_partial=False): deposit_id = self.create_simple_binary_deposit( status_partial=True) # Add a second archive to the deposit # update its status to DEPOSIT_STATUS_VERIFIED response = self.client.post( reverse(EM_IRI, args=[self.collection.name, deposit_id]), content_type='application/zip', data=self.archive2['data'], CONTENT_LENGTH=self.archive2['length'], HTTP_MD5SUM=self.archive2['md5sum'], HTTP_SLUG='external-id', HTTP_IN_PROGRESS=status_partial, HTTP_CONTENT_DISPOSITION='attachment; filename=filename1.zip') # then assert response.status_code == status.HTTP_201_CREATED response_content = parse_xml(BytesIO(response.content)) deposit_id = int(response_content['deposit_id']) return deposit_id def create_deposit_archive_with_archive(self, archive_extension): # we create the holding archive to a given extension archive = create_arborescence_archive( self.root_path, 'archive1', 'file1', b'some content in file', extension=archive_extension) # now we create an archive holding the first created archive invalid_archive = create_archive_with_archive( self.root_path, 'invalid.tar.gz', archive) # we deposit it response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/x-tar', data=invalid_archive['data'], CONTENT_LENGTH=invalid_archive['length'], HTTP_MD5SUM=invalid_archive['md5sum'], HTTP_SLUG='external-id', HTTP_IN_PROGRESS=False, HTTP_CONTENT_DISPOSITION='attachment; filename=%s' % ( invalid_archive['name'], )) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) _status = response_content['deposit_status'] self.assertEqual(_status, DEPOSIT_STATUS_DEPOSITED) deposit_id = int(response_content['deposit_id']) return deposit_id def update_binary_deposit(self, deposit_id, status_partial=False): # update existing deposit with atom entry metadata response = self.client.post( reverse(EDIT_SE_IRI, args=[self.collection.name, deposit_id]), content_type='application/atom+xml;type=entry', data=self.codemeta_entry_data1, HTTP_SLUG='external-id', HTTP_IN_PROGRESS=status_partial) # then self.assertEqual(response.status_code, status.HTTP_201_CREATED) response_content = parse_xml(BytesIO(response.content)) _status = response_content['deposit_status'] if status_partial: expected_status = DEPOSIT_STATUS_PARTIAL else: expected_status = DEPOSIT_STATUS_DEPOSITED self.assertEqual(_status, expected_status) deposit_id = int(response_content['deposit_id']) return deposit_id @attr('fs') class BasicTestCase(TestCase): """Mixin intended for data setup purposes (user, collection, etc...) """ def setUp(self): """Define the test client and other test variables.""" super().setUp() # expanding diffs in tests self.maxDiff = None # basic minimum test data deposit_request_types = {} # Add deposit request types for deposit_request_type in ['archive', 'metadata']: drt = DepositRequestType(name=deposit_request_type) drt.save() deposit_request_types[deposit_request_type] = drt _name = 'hal' _provider_url = 'https://hal-test.archives-ouvertes.fr/' _domain = 'archives-ouvertes.fr/' # set collection up _collection = DepositCollection(name=_name) _collection.save() # set user/client up _client = DepositClient.objects.create_user(username=_name, password=_name, provider_url=_provider_url, domain=_domain) _client.collections = [_collection.id] _client.last_name = _name _client.save() self.collection = _collection self.user = _client self.username = _name self.userpass = _name self.deposit_request_types = deposit_request_types def tearDown(self): super().tearDown() # Clean up uploaded files in temporary directory (tests have # their own media root folder) if os.path.exists(MEDIA_ROOT): for d in os.listdir(MEDIA_ROOT): shutil.rmtree(os.path.join(MEDIA_ROOT, d)) class WithAuthTestCase(TestCase): """Mixin intended for testing the api with basic authentication. """ def setUp(self): super().setUp() _token = '%s:%s' % (self.username, self.userpass) token = base64.b64encode(_token.encode('utf-8')) authorization = 'Basic %s' % token.decode('utf-8') self.client.credentials(HTTP_AUTHORIZATION=authorization) def tearDown(self): super().tearDown() self.client.credentials() class CommonCreationRoutine(TestCase): """Mixin class to share initialization routine. cf: `class`:test_deposit_update.DepositReplaceExistingDataTest `class`:test_deposit_update.DepositUpdateDepositWithNewDataTest `class`:test_deposit_update.DepositUpdateFailuresTest `class`:test_deposit_delete.DepositDeleteTest """ def setUp(self): super().setUp() self.atom_entry_data0 = b""" some-external-id https://hal-test.archives-ouvertes.fr/some-external-id """ self.atom_entry_data1 = b""" some awesome author """ self.atom_entry_data2 = b""" Awesome Compiler urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a 1785io25c695 2017-10-07T15:17:08Z some awesome author https://hal-test.archives-ouvertes.fr/id """ self.codemeta_entry_data0 = b""" Awesome Compiler https://hal-test.archives-ouvertes.fr/1785io25c695 urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a 1785io25c695 2017-10-07T15:17:08Z some awesome author description key-word 1 """ self.codemeta_entry_data1 = b""" Composing a Web of Audio Applications hal hal-01243065 hal-01243065 https://hal-test.archives-ouvertes.fr/hal-01243065 test DSP programming,Web 2017-05-03T16:08:47+02:00 this is the description 1 phpstorm stable php python C GNU General Public License v3.0 only CeCILL Free Software License Agreement v1.1 HAL hal@ccsd.cnrs.fr Morane Gruenpeter """ def create_deposit_with_invalid_archive(self, external_id='some-external-id-1'): url = reverse(COL_IRI, args=[self.collection.name]) data = b'some data which is clearly not a zip file' md5sum = hashlib.md5(data).hexdigest() # when response = self.client.post( url, content_type='application/zip', # as zip data=data, # + headers CONTENT_LENGTH=len(data), # other headers needs HTTP_ prefix to be taken into account HTTP_SLUG=external_id, HTTP_CONTENT_MD5=md5sum, HTTP_PACKAGING='http://purl.org/net/sword/package/SimpleZip', HTTP_CONTENT_DISPOSITION='attachment; filename=filename0') response_content = parse_xml(BytesIO(response.content)) deposit_id = int(response_content['deposit_id']) return deposit_id def create_deposit_with_status( self, status, - external_id='some-external-id-1', swh_id=None, status_detail=None): + external_id='some-external-id-1', + swh_id=None, + swh_id_context=None, + swh_anchor_id=None, + swh_anchor_id_context=None, + status_detail=None): # create an invalid deposit which we will update further down the line deposit_id = self.create_deposit_with_invalid_archive(external_id) # We cannot create some form of deposit with a given status in # test context ('rejected' for example). Update in place the # deposit with such status to permit some further tests. deposit = Deposit.objects.get(pk=deposit_id) if status == DEPOSIT_STATUS_REJECTED: deposit.status_detail = status_detail deposit.status = status if swh_id: deposit.swh_id = swh_id + if swh_id_context: + deposit.swh_id_context = swh_id_context + if swh_anchor_id: + deposit.swh_anchor_id = swh_anchor_id + if swh_anchor_id_context: + deposit.swh_anchor_id_context = swh_anchor_id_context deposit.save() - return deposit_id def create_simple_deposit_partial(self, external_id='some-external-id'): """Create a simple deposit (1 request) in `partial` state and returns its new identifier. Returns: deposit id """ response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=self.atom_entry_data0, HTTP_SLUG=external_id, HTTP_IN_PROGRESS='true') assert response.status_code == status.HTTP_201_CREATED response_content = parse_xml(BytesIO(response.content)) deposit_id = int(response_content['deposit_id']) return deposit_id def create_deposit_partial_with_data_in_args(self, data): """Create a simple deposit (1 request) in `partial` state with the data or metadata as an argument and returns its new identifier. Args: data: atom entry Returns: deposit id """ response = self.client.post( reverse(COL_IRI, args=[self.collection.name]), content_type='application/atom+xml;type=entry', data=data, HTTP_SLUG='external-id', HTTP_IN_PROGRESS='true') assert response.status_code == status.HTTP_201_CREATED response_content = parse_xml(BytesIO(response.content)) deposit_id = int(response_content['deposit_id']) return deposit_id def _update_deposit_with_status(self, deposit_id, status_partial=False): """Add to a given deposit another archive and update its current status to `deposited` (by default). Returns: deposit id """ # when response = self.client.post( reverse(EDIT_SE_IRI, args=[self.collection.name, deposit_id]), content_type='application/atom+xml;type=entry', data=self.atom_entry_data1, HTTP_SLUG='external-id', HTTP_IN_PROGRESS=status_partial) # then assert response.status_code == status.HTTP_201_CREATED return deposit_id def create_deposit_ready(self, external_id='some-external-id'): """Create a complex deposit (2 requests) in status `deposited`. """ deposit_id = self.create_simple_deposit_partial( external_id=external_id) deposit_id = self._update_deposit_with_status(deposit_id) return deposit_id def create_deposit_partial(self, external_id='some-external-id'): """Create a complex deposit (2 requests) in status `partial`. """ deposit_id = self.create_simple_deposit_partial( external_id=external_id) deposit_id = self._update_deposit_with_status( deposit_id, status_partial=True) return deposit_id def add_metadata_to_deposit(self, deposit_id, status_partial=False): """Add metadata to deposit. """ # when response = self.client.post( reverse(EDIT_SE_IRI, args=[self.collection.name, deposit_id]), content_type='application/atom+xml;type=entry', data=self.codemeta_entry_data1, HTTP_SLUG='external-id', HTTP_IN_PROGRESS=status_partial) assert response.status_code == status.HTTP_201_CREATED # then deposit = Deposit.objects.get(pk=deposit_id) assert deposit is not None deposit_requests = DepositRequest.objects.filter(deposit=deposit) assert deposit_requests is not [] for dr in deposit_requests: if dr.type.name == 'metadata': assert deposit_requests[0].metadata is not {} return deposit_id diff --git a/swh/deposit/tests/loader/common.py b/swh/deposit/tests/loader/common.py index 389a1d47..60eaeb65 100644 --- a/swh/deposit/tests/loader/common.py +++ b/swh/deposit/tests/loader/common.py @@ -1,49 +1,54 @@ # Copyright (C) 2017-2018 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 json from swh.deposit.client import PrivateApiDepositClient CLIENT_TEST_CONFIG = { 'url': 'http://nowhere:9000/', 'auth': {}, # no authentication in test scenario } class SWHDepositTestClient(PrivateApiDepositClient): """Deposit test client to permit overriding the default request client. """ def __init__(self, client, config): super().__init__(config=config) self.client = client def archive_get(self, archive_update_url, archive_path, log=None): r = self.client.get(archive_update_url) with open(archive_path, 'wb') as f: for chunk in r.streaming_content: f.write(chunk) return archive_path def metadata_get(self, metadata_url, log=None): r = self.client.get(metadata_url) return json.loads(r.content.decode('utf-8')) - def status_update(self, update_status_url, status, revision_id=None): + def status_update(self, update_status_url, status, + revision_id=None, directory_id=None, origin_url=None): payload = {'status': status} if revision_id: payload['revision_id'] = revision_id + if directory_id: + payload['directory_id'] = directory_id + if origin_url: + payload['origin_url'] = origin_url self.client.put(update_status_url, content_type='application/json', data=json.dumps(payload)) def check(self, check_url): r = self.client.get(check_url) data = json.loads(r.content.decode('utf-8')) return data['status'] diff --git a/swh/deposit/tests/loader/test_loader.py b/swh/deposit/tests/loader/test_loader.py index 221329a3..8b7e646c 100644 --- a/swh/deposit/tests/loader/test_loader.py +++ b/swh/deposit/tests/loader/test_loader.py @@ -1,294 +1,308 @@ # Copyright (C) 2017-2018 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 os import unittest import shutil from nose.tools import istest from nose.plugins.attrib import attr from rest_framework.test import APITestCase from swh.model import hashutil +from swh.deposit.models import Deposit from swh.deposit.loader import loader -from swh.deposit.config import PRIVATE_GET_RAW_CONTENT -from swh.deposit.config import PRIVATE_GET_DEPOSIT_METADATA -from swh.deposit.config import PRIVATE_PUT_DEPOSIT +from swh.deposit.config import ( + PRIVATE_GET_RAW_CONTENT, PRIVATE_GET_DEPOSIT_METADATA, PRIVATE_PUT_DEPOSIT +) from django.core.urlresolvers import reverse + from .common import SWHDepositTestClient, CLIENT_TEST_CONFIG from .. import TEST_LOADER_CONFIG -from ..common import BasicTestCase, WithAuthTestCase, CommonCreationRoutine -from ..common import FileSystemCreationRoutine +from ..common import (BasicTestCase, WithAuthTestCase, + CommonCreationRoutine, + FileSystemCreationRoutine) TOOL_ID = 99 PROVIDER_ID = 12 class DepositLoaderInhibitsStorage: """Mixin class to inhibit the persistence and keep in memory the data sent for storage. cf. SWHDepositLoaderNoStorage """ def __init__(self, client=None): # client is not used here, transit it nonetheless to other mixins super().__init__(client=client) # typed data self.state = { 'origin': [], 'origin_visit': [], 'origin_metadata': [], 'content': [], 'directory': [], 'revision': [], 'release': [], 'snapshot': [], 'tool': [], 'provider': [] } def _add(self, type, l): """Add without duplicates and keeping the insertion order. Args: type (str): Type of objects concerned by the action l ([object]): List of 'type' object """ col = self.state[type] for o in l: if o in col: continue col.extend([o]) def send_origin(self, origin): origin.update({'id': 1}) self._add('origin', [origin]) return origin['id'] def send_origin_visit(self, origin_id, visit_date): origin_visit = { 'origin': origin_id, 'visit_date': visit_date, 'visit': 1, } self._add('origin_visit', [origin_visit]) return origin_visit def send_origin_metadata(self, origin_id, visit_date, provider_id, tool_id, metadata): origin_metadata = { 'origin_id': origin_id, 'visit_date': visit_date, 'provider_id': provider_id, 'tool_id': tool_id, 'metadata': metadata } self._add('origin_metadata', [origin_metadata]) return origin_metadata def send_tool(self, tool): tool = { 'tool_name': tool['tool_name'], 'tool_version': tool['tool_version'], 'tool_configuration': tool['tool_configuration'] } self._add('tool', [tool]) tool_id = TOOL_ID return tool_id def send_provider(self, provider): provider = { 'provider_name': provider['provider_name'], 'provider_type': provider['provider_type'], 'provider_url': provider['provider_url'], 'metadata': provider['metadata'] } self._add('provider', [provider]) provider_id = PROVIDER_ID return provider_id def maybe_load_contents(self, contents): self._add('content', contents) def maybe_load_directories(self, directories): self._add('directory', directories) def maybe_load_revisions(self, revisions): self._add('revision', revisions) def maybe_load_releases(self, releases): self._add('release', releases) def maybe_load_snapshot(self, snapshot): self._add('snapshot', [snapshot]) def open_fetch_history(self): pass def close_fetch_history_failure(self, fetch_history_id): pass def close_fetch_history_success(self, fetch_history_id): pass def update_origin_visit(self, origin_id, visit, status): self.status = status # Override to do nothing at the end def close_failure(self): pass def close_success(self): pass class TestLoaderUtils(unittest.TestCase): def assertRevisionsOk(self, expected_revisions): # noqa: N802 """Check the loader's revisions match the expected revisions. Expects self.loader to be instantiated and ready to be inspected (meaning the loading took place). Args: expected_revisions (dict): Dict with key revision id, value the targeted directory id. """ # The last revision being the one used later to start back from for rev in self.loader.state['revision']: rev_id = hashutil.hash_to_hex(rev['id']) directory_id = hashutil.hash_to_hex(rev['directory']) self.assertEquals(expected_revisions[rev_id], directory_id) class SWHDepositLoaderNoStorage(DepositLoaderInhibitsStorage, loader.DepositLoader): """Loader to test. It inherits from the actual deposit loader to actually test its correct behavior. It also inherits from DepositLoaderInhibitsStorage so that no persistence takes place. """ pass @attr('fs') class DepositLoaderScenarioTest(APITestCase, WithAuthTestCase, BasicTestCase, CommonCreationRoutine, FileSystemCreationRoutine, TestLoaderUtils): def setUp(self): super().setUp() # create the extraction dir used by the loader os.makedirs(TEST_LOADER_CONFIG['extraction_dir'], exist_ok=True) # 1. create a deposit with archive and metadata self.deposit_id = self.create_simple_binary_deposit() # 2. Sets a basic client which accesses the test data loader_client = SWHDepositTestClient(self.client, config=CLIENT_TEST_CONFIG) # 3. setup loader with no persistence and that client self.loader = SWHDepositLoaderNoStorage(client=loader_client) def tearDown(self): super().tearDown() shutil.rmtree(TEST_LOADER_CONFIG['extraction_dir']) @istest def inject_deposit_ready(self): """Load a deposit which is ready """ args = [self.collection.name, self.deposit_id] archive_url = reverse(PRIVATE_GET_RAW_CONTENT, args=args) deposit_meta_url = reverse(PRIVATE_GET_DEPOSIT_METADATA, args=args) deposit_update_url = reverse(PRIVATE_PUT_DEPOSIT, args=args) # when self.loader.load(archive_url=archive_url, deposit_meta_url=deposit_meta_url, deposit_update_url=deposit_update_url) # then self.assertEquals(len(self.loader.state['content']), 1) self.assertEquals(len(self.loader.state['directory']), 1) self.assertEquals(len(self.loader.state['revision']), 1) self.assertEquals(len(self.loader.state['release']), 0) self.assertEquals(len(self.loader.state['snapshot']), 1) @istest def inject_deposit_verify_metadata(self): """Load a deposit with metadata, test metadata integrity """ self.deposit_metadata_id = self.add_metadata_to_deposit( self.deposit_id) args = [self.collection.name, self.deposit_metadata_id] archive_url = reverse(PRIVATE_GET_RAW_CONTENT, args=args) deposit_meta_url = reverse(PRIVATE_GET_DEPOSIT_METADATA, args=args) deposit_update_url = reverse(PRIVATE_PUT_DEPOSIT, args=args) # when self.loader.load(archive_url=archive_url, deposit_meta_url=deposit_meta_url, deposit_update_url=deposit_update_url) # then self.assertEquals(len(self.loader.state['content']), 1) self.assertEquals(len(self.loader.state['directory']), 1) self.assertEquals(len(self.loader.state['revision']), 1) self.assertEquals(len(self.loader.state['release']), 0) self.assertEquals(len(self.loader.state['snapshot']), 1) self.assertEquals(len(self.loader.state['origin_metadata']), 1) self.assertEquals(len(self.loader.state['tool']), 1) self.assertEquals(len(self.loader.state['provider']), 1) codemeta = 'codemeta:' + origin_url = 'https://hal-test.archives-ouvertes.fr/hal-01243065' expected_origin_metadata = { '@xmlns': 'http://www.w3.org/2005/Atom', '@xmlns:codemeta': 'https://doi.org/10.5063/SCHEMA/CODEMETA-2.0', 'author': { 'email': 'hal@ccsd.cnrs.fr', 'name': 'HAL' }, - codemeta + 'url': - 'https://hal-test.archives-ouvertes.fr/hal-01243065', + codemeta + 'url': origin_url, codemeta + 'runtimePlatform': 'phpstorm', codemeta + 'license': [ { codemeta + 'name': 'GNU General Public License v3.0 only' }, { codemeta + 'name': 'CeCILL Free Software License Agreement v1.1' # noqa } ], codemeta + 'author': { codemeta + 'name': 'Morane Gruenpeter' }, codemeta + 'programmingLanguage': ['php', 'python', 'C'], codemeta + 'applicationCategory': 'test', codemeta + 'dateCreated': '2017-05-03T16:08:47+02:00', codemeta + 'version': '1', 'external_identifier': 'hal-01243065', 'title': 'Composing a Web of Audio Applications', codemeta + 'description': 'this is the description', 'id': 'hal-01243065', 'client': 'hal', codemeta + 'keywords': 'DSP programming,Web', codemeta + 'developmentStatus': 'stable' } result = self.loader.state['origin_metadata'][0] self.assertEquals(result['metadata'], expected_origin_metadata) self.assertEquals(result['tool_id'], TOOL_ID) self.assertEquals(result['provider_id'], PROVIDER_ID) + + deposit = Deposit.objects.get(pk=self.deposit_id) + + self.assertRegex(deposit.swh_id, r'^swh:1:dir:.*') + self.assertEquals(deposit.swh_id_context, '%s;origin=%s' % ( + deposit.swh_id, origin_url + )) + self.assertRegex(deposit.swh_anchor_id, r'^swh:1:rev:.*') + self.assertEquals(deposit.swh_anchor_id_context, '%s;origin=%s' % ( + deposit.swh_anchor_id, origin_url + )) diff --git a/version.txt b/version.txt index 34dba199..37513ea7 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.56-0-g6367c2e \ No newline at end of file +v0.0.57-0-g2c4c484 \ No newline at end of file