diff --git a/PKG-INFO b/PKG-INFO index 49e37610..bb2635ea 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,10 +1,10 @@ Metadata-Version: 1.0 Name: swh.web -Version: 0.0.110 +Version: 0.0.111 Summary: Software Heritage Web UI Home-page: https://forge.softwareheritage.org/diffusion/DWUI/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Description: UNKNOWN Platform: UNKNOWN diff --git a/swh.web.egg-info/PKG-INFO b/swh.web.egg-info/PKG-INFO index 49e37610..bb2635ea 100644 --- a/swh.web.egg-info/PKG-INFO +++ b/swh.web.egg-info/PKG-INFO @@ -1,10 +1,10 @@ Metadata-Version: 1.0 Name: swh.web -Version: 0.0.110 +Version: 0.0.111 Summary: Software Heritage Web UI Home-page: https://forge.softwareheritage.org/diffusion/DWUI/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Description: UNKNOWN Platform: UNKNOWN diff --git a/swh/web/common/converters.py b/swh/web/common/converters.py index 25cce3f1..2cb76cde 100644 --- a/swh/web/common/converters.py +++ b/swh/web/common/converters.py @@ -1,342 +1,342 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import json from swh.model import hashutil from swh.core.utils import decode_with_escape from swh.web.api import utils def _group_checksums(data): """Groups checksums values computed from hash functions used in swh and stored in data dict under a single entry 'checksums' """ if data: checksums = {} for hash in hashutil.ALGORITHMS: if hash in data and data[hash]: checksums[hash] = data[hash] del data[hash] if len(checksums) > 0: data['checksums'] = checksums def from_swh(dict_swh, hashess={}, bytess={}, dates={}, blacklist={}, removables_if_empty={}, empty_dict={}, empty_list={}, convert={}, convert_fn=lambda x: x): """Convert from an swh dictionary to something reasonably json serializable. Args: dict_swh: the origin dictionary needed to be transformed hashess: list/set of keys representing hashes values (sha1, sha256, sha1_git, etc...) as bytes. Those need to be transformed in hexadecimal string bytess: list/set of keys representing bytes values which needs to be decoded blacklist: set of keys to filter out from the conversion convert: set of keys whose associated values need to be converted using convert_fn convert_fn: the conversion function to apply on the value of key in 'convert' The remaining keys are copied as is in the output. Returns: dictionary equivalent as dict_swh only with its keys converted. """ def convert_hashes_bytes(v): """v is supposedly a hash as bytes, returns it converted in hex. """ if isinstance(v, bytes): return hashutil.hash_to_hex(v) return v def convert_bytes(v): """v is supposedly a bytes string, decode as utf-8. FIXME: Improve decoding policy. If not utf-8, break! """ if isinstance(v, bytes): return v.decode('utf-8') return v def convert_date(v): """ Args: v (dict or datatime): either: - a dict with three keys: - timestamp (dict or integer timestamp) - offset - negative_utc - or, a datetime We convert it to a human-readable string """ if isinstance(v, datetime.datetime): return v.isoformat() tz = datetime.timezone(datetime.timedelta(minutes=v['offset'])) swh_timestamp = v['timestamp'] if isinstance(swh_timestamp, dict): date = datetime.datetime.fromtimestamp( swh_timestamp['seconds'], tz=tz) else: date = datetime.datetime.fromtimestamp( swh_timestamp, tz=tz) datestr = date.isoformat() if v['offset'] == 0 and v['negative_utc']: # remove the rightmost + and replace it with a - return '-'.join(datestr.rsplit('+', 1)) return datestr if not dict_swh: return dict_swh new_dict = {} for key, value in dict_swh.items(): if key in blacklist or (key in removables_if_empty and not value): continue if key in dates: new_dict[key] = convert_date(value) elif key in convert: new_dict[key] = convert_fn(value) elif isinstance(value, dict): new_dict[key] = from_swh(value, hashess=hashess, bytess=bytess, dates=dates, blacklist=blacklist, removables_if_empty=removables_if_empty, empty_dict=empty_dict, empty_list=empty_list, convert=convert, convert_fn=convert_fn) elif key in hashess: new_dict[key] = utils.fmap(convert_hashes_bytes, value) elif key in bytess: try: new_dict[key] = utils.fmap(convert_bytes, value) except UnicodeDecodeError: if 'decoding_failures' not in new_dict: new_dict['decoding_failures'] = [key] else: new_dict['decoding_failures'].append(key) new_dict[key] = utils.fmap(decode_with_escape, value) elif key in empty_dict and not value: new_dict[key] = {} elif key in empty_list and not value: new_dict[key] = [] else: new_dict[key] = value _group_checksums(new_dict) return new_dict def from_provenance(provenance): """Convert from a provenance information to a provenance dictionary. Args: provenance (dict): Dictionary with the following keys: - content (sha1_git): the content's identifier - revision (sha1_git): the revision the content was seen - origin (int): the origin the content was seen - visit (int): the visit it occurred - path (bytes): the path the content was seen at """ return from_swh(provenance, hashess={'content', 'revision'}, bytess={'path'}) def from_origin(origin): """Convert from an SWH origin to an origin dictionary. """ return from_swh(origin, removables_if_empty={'lister', 'project'}) def from_release(release): """Convert from an SWH release to a json serializable release dictionary. Args: release (dict): dictionary with keys: - id: identifier of the revision (sha1 in bytes) - revision: identifier of the revision the release points to (sha1 in bytes) comment: release's comment message (bytes) name: release's name (string) author: release's author identifier (swh's id) synthetic: the synthetic property (boolean) Returns: dict: Release dictionary with the following keys: - id: hexadecimal sha1 (string) - revision: hexadecimal sha1 (string) - comment: release's comment message (string) - name: release's name (string) - author: release's author identifier (swh's id) - synthetic: the synthetic property (boolean) """ return from_swh( release, hashess={'id', 'target'}, bytess={'message', 'name', 'fullname', 'email'}, dates={'date'}, ) class SWHMetadataEncoder(json.JSONEncoder): """Special json encoder for metadata field which can contain bytes encoded value. """ def default(self, obj): if isinstance(obj, bytes): return obj.decode('utf-8') # Let the base class default method raise the TypeError return json.JSONEncoder.default(self, obj) def convert_revision_metadata(metadata): """Convert json specific dict to a json serializable one. """ if not metadata: return {} return json.loads(json.dumps(metadata, cls=SWHMetadataEncoder)) def from_revision(revision): """Convert from an SWH revision to a json serializable revision dictionary. Args: revision (dict): dict with keys: - id: identifier of the revision (sha1 in bytes) - directory: identifier of the directory the revision points to (sha1 in bytes) - author_name, author_email: author's revision name and email - committer_name, committer_email: committer's revision name and email - message: revision's message - date, date_offset: revision's author date - committer_date, committer_date_offset: revision's commit date - parents: list of parents for such revision - synthetic: revision's property nature - type: revision's type (git, tar or dsc at the moment) - metadata: if the revision is synthetic, this can reference dynamic properties. Returns: dict: Revision dictionary with the same keys as inputs, except: - sha1s are in hexadecimal strings (id, directory) - bytes are decoded in string (author_name, committer_name, author_email, committer_email) Remaining keys are left as is """ revision = from_swh(revision, hashess={'id', 'directory', 'parents', 'children'}, bytess={'name', 'fullname', 'email'}, convert={'metadata'}, convert_fn=convert_revision_metadata, dates={'date', 'committer_date'}) if revision: if 'parents' in revision: revision['merge'] = len(revision['parents']) > 1 if 'message' in revision: try: revision['message'] = revision['message'].decode('utf-8') except UnicodeDecodeError: revision['message_decoding_failed'] = True revision['message'] = None return revision def from_content(content): """Convert swh content to serializable content dictionary. """ return from_swh(content, hashess={'sha1', 'sha1_git', 'sha256', 'blake2s256'}, blacklist={'ctime'}, convert={'status'}, convert_fn=lambda v: 'absent' if v == 'hidden' else v) def from_person(person): """Convert swh person to serializable person dictionary. """ return from_swh(person, bytess={'name', 'fullname', 'email'}) def from_origin_visit(visit): """Convert swh origin_visit to serializable origin_visit dictionary. """ ov = from_swh(visit, - hashess={'target'}, + hashess={'target', 'snapshot'}, bytess={'branch'}, dates={'date'}, empty_dict={'metadata'}) if ov and 'occurrences' in ov: ov['occurrences'] = { decode_with_escape(k): v for k, v in ov['occurrences'].items() } return ov def from_directory_entry(dir_entry): """Convert swh person to serializable person dictionary. """ return from_swh(dir_entry, hashess={'dir_id', 'sha1_git', 'sha1', 'sha256', 'blake2s256', 'target'}, bytess={'name'}, removables_if_empty={ 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'status'}, convert={'status'}, convert_fn=lambda v: 'absent' if v == 'hidden' else v) def from_filetype(content_entry): """Convert swh person to serializable person dictionary. """ return from_swh(content_entry, hashess={'id'}, bytess={'mimetype', 'encoding'}) diff --git a/swh/web/tests/common/test_converters.py b/swh/web/tests/common/test_converters.py index e1a1ae20..fde4081f 100644 --- a/swh/web/tests/common/test_converters.py +++ b/swh/web/tests/common/test_converters.py @@ -1,752 +1,788 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import unittest from nose.tools import istest from swh.model import hashutil from swh.web.common import converters class ConvertersTestCase(unittest.TestCase): @istest def from_swh(self): some_input = { 'a': 'something', 'b': 'someone', 'c': b'sharp-0.3.4.tgz', 'd': hashutil.hash_to_bytes( 'b04caf10e9535160d90e874b45aa426de762f19f'), 'e': b'sharp.html/doc_002dS_005fISREG.html', 'g': [b'utf-8-to-decode', b'another-one'], 'h': 'something filtered', 'i': {'e': b'something'}, 'j': { 'k': { 'l': [b'bytes thing', b'another thingy', b''], 'n': 'dont care either' }, 'm': 'dont care' }, 'o': 'something', 'p': b'foo', 'q': {'extra-headers': [['a', b'intact']]}, 'w': None, 'r': {'p': 'also intact', 'q': 'bar'}, 's': { 'timestamp': 42, 'offset': -420, 'negative_utc': None, }, 's1': { 'timestamp': {'seconds': 42, 'microseconds': 0}, 'offset': -420, 'negative_utc': None, }, 's2': datetime.datetime( 2013, 7, 1, 20, 0, 0, tzinfo=datetime.timezone.utc), 't': None, 'u': None, 'v': None, 'x': None, } expected_output = { 'a': 'something', 'b': 'someone', 'c': 'sharp-0.3.4.tgz', 'd': 'b04caf10e9535160d90e874b45aa426de762f19f', 'e': 'sharp.html/doc_002dS_005fISREG.html', 'g': ['utf-8-to-decode', 'another-one'], 'i': {'e': 'something'}, 'j': { 'k': { 'l': ['bytes thing', 'another thingy', ''] } }, 'p': 'foo', 'q': {'extra-headers': [['a', 'intact']]}, 'w': {}, 'r': {'p': 'also intact', 'q': 'bar'}, 's': '1969-12-31T17:00:42-07:00', 's1': '1969-12-31T17:00:42-07:00', 's2': '2013-07-01T20:00:00+00:00', 'u': {}, 'v': [], 'x': None, } actual_output = converters.from_swh( some_input, hashess={'d', 'o', 'x'}, bytess={'c', 'e', 'g', 'l'}, dates={'s', 's1', 's2'}, blacklist={'h', 'm', 'n', 'o'}, removables_if_empty={'t'}, empty_dict={'u'}, empty_list={'v'}, convert={'p', 'q', 'w'}, convert_fn=converters.convert_revision_metadata) self.assertEquals(expected_output, actual_output) @istest def from_swh_edge_cases_do_no_conversion_if_none_or_not_bytes(self): some_input = { 'a': 'something', 'b': None, 'c': 'someone', 'd': None, } expected_output = { 'a': 'something', 'b': None, 'c': 'someone', 'd': None, } actual_output = converters.from_swh(some_input, hashess={'a', 'b'}, bytess={'c', 'd'}) self.assertEquals(expected_output, actual_output) @istest def from_swh_edge_cases_convert_invalid_utf8_bytes(self): some_input = { 'a': 'something', 'b': 'someone', 'c': b'a name \xff', 'd': b'an email \xff', } expected_output = { 'a': 'something', 'b': 'someone', 'c': 'a name \\xff', 'd': 'an email \\xff', 'decoding_failures': ['c', 'd'] } actual_output = converters.from_swh(some_input, hashess={'a', 'b'}, bytess={'c', 'd'}) for v in ['a', 'b', 'c', 'd']: self.assertEqual(expected_output[v], actual_output[v]) self.assertEqual(len(expected_output['decoding_failures']), len(actual_output['decoding_failures'])) for v in expected_output['decoding_failures']: self.assertTrue(v in actual_output['decoding_failures']) @istest def from_swh_empty(self): # when self.assertEquals({}, converters.from_swh({})) @istest def from_swh_none(self): # when self.assertIsNone(converters.from_swh(None)) @istest def from_provenance(self): # given input_provenance = { 'origin': 10, 'visit': 1, 'content': hashutil.hash_to_bytes( '321caf10e9535160d90e874b45aa426de762f19f'), 'revision': hashutil.hash_to_bytes( '123caf10e9535160d90e874b45aa426de762f19f'), 'path': b'octave-3.4.0/doc/interpreter/octave/doc_002dS_005fISREG' } expected_provenance = { 'origin': 10, 'visit': 1, 'content': '321caf10e9535160d90e874b45aa426de762f19f', 'revision': '123caf10e9535160d90e874b45aa426de762f19f', 'path': 'octave-3.4.0/doc/interpreter/octave/doc_002dS_005fISREG' } # when actual_provenance = converters.from_provenance(input_provenance) # then self.assertEqual(actual_provenance, expected_provenance) @istest def from_origin(self): # given origin_input = { 'id': 9, 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/octave', 'project': None, 'lister': None, } expected_origin = { 'id': 9, 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/octave', } # when actual_origin = converters.from_origin(origin_input) # then self.assertEqual(actual_origin, expected_origin) + @istest + def from_origin_visit(self): + snap_hash = 'b5f0b7f716735ebffe38505c60145c4fd9da6ca3' + + for snap in [snap_hash, None]: + # given + visit = { + 'date': { + 'timestamp': datetime.datetime( + 2015, 1, 1, 22, 0, 0, + tzinfo=datetime.timezone.utc).timestamp(), + 'offset': 0, + 'negative_utc': False, + }, + 'origin': 10, + 'visit': 100, + 'metadata': None, + 'status': 'full', + 'snapshot': hashutil.hash_to_bytes(snap) if snap else snap, + } + + expected_visit = { + 'date': '2015-01-01T22:00:00+00:00', + 'origin': 10, + 'visit': 100, + 'metadata': {}, + 'status': 'full', + 'snapshot': snap_hash if snap else snap + } + + # when + actual_visit = converters.from_origin_visit(visit) + + # then + self.assertEqual(actual_visit, expected_visit) + @istest def from_release(self): release_input = { 'id': hashutil.hash_to_bytes( 'aad23fa492a0c5fed0708a6703be875448c86884'), 'target': hashutil.hash_to_bytes( '5e46d564378afc44b31bb89f99d5675195fbdf67'), 'target_type': 'revision', 'date': { 'timestamp': datetime.datetime( 2015, 1, 1, 22, 0, 0, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'author': { 'name': b'author name', 'fullname': b'Author Name author@email', 'email': b'author@email', }, 'name': b'v0.0.1', 'message': b'some comment on release', 'synthetic': True, } expected_release = { 'id': 'aad23fa492a0c5fed0708a6703be875448c86884', 'target': '5e46d564378afc44b31bb89f99d5675195fbdf67', 'target_type': 'revision', 'date': '2015-01-01T22:00:00+00:00', 'author': { 'name': 'author name', 'fullname': 'Author Name author@email', 'email': 'author@email', }, 'name': 'v0.0.1', 'message': 'some comment on release', 'target_type': 'revision', 'synthetic': True, } # when actual_release = converters.from_release(release_input) # then self.assertEqual(actual_release, expected_release) @istest def from_release_no_revision(self): release_input = { 'id': hashutil.hash_to_bytes( 'b2171ee2bdf119cd99a7ec7eff32fa8013ef9a4e'), 'target': None, 'date': { 'timestamp': datetime.datetime( 2016, 3, 2, 10, 0, 0, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': True, }, 'name': b'v0.1.1', 'message': b'comment on release', 'synthetic': False, 'author': { 'name': b'bob', 'fullname': b'Bob bob@alice.net', 'email': b'bob@alice.net', }, } expected_release = { 'id': 'b2171ee2bdf119cd99a7ec7eff32fa8013ef9a4e', 'target': None, 'date': '2016-03-02T10:00:00-00:00', 'name': 'v0.1.1', 'message': 'comment on release', 'synthetic': False, 'author': { 'name': 'bob', 'fullname': 'Bob bob@alice.net', 'email': 'bob@alice.net', }, } # when actual_release = converters.from_release(release_input) # then self.assertEqual(actual_release, expected_release) @istest def from_revision(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'directory': hashutil.hash_to_bytes( '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6'), 'author': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'committer': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'message': b'synthetic revision message', 'date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'committer_date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'synthetic': True, 'type': 'tar', 'parents': [ hashutil.hash_to_bytes( '29d8be353ed3480476f032475e7c244eff7371d5'), hashutil.hash_to_bytes( '30d8be353ed3480476f032475e7c244eff7371d5') ], 'children': [ hashutil.hash_to_bytes( '123546353ed3480476f032475e7c244eff7371d5'), ], 'metadata': { 'extra_headers': [['gpgsig', b'some-signature']], 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912', }] }, } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'directory': '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6', 'author': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'committer': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'message': 'synthetic revision message', 'date': "2000-01-17T11:23:54+00:00", 'committer_date': "2000-01-17T11:23:54+00:00", 'children': [ '123546353ed3480476f032475e7c244eff7371d5' ], 'parents': [ '29d8be353ed3480476f032475e7c244eff7371d5', '30d8be353ed3480476f032475e7c244eff7371d5' ], 'type': 'tar', 'synthetic': True, 'metadata': { 'extra_headers': [['gpgsig', 'some-signature']], 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912' }] }, 'merge': True } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) @istest def from_revision_nomerge(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'parents': [ hashutil.hash_to_bytes( '29d8be353ed3480476f032475e7c244eff7371d5') ] } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'parents': [ '29d8be353ed3480476f032475e7c244eff7371d5' ], 'merge': False } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) @istest def from_revision_noparents(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'directory': hashutil.hash_to_bytes( '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6'), 'author': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'committer': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'message': b'synthetic revision message', 'date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'committer_date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'synthetic': True, 'type': 'tar', 'children': [ hashutil.hash_to_bytes( '123546353ed3480476f032475e7c244eff7371d5'), ], 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912', }] }, } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'directory': '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6', 'author': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'committer': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'message': 'synthetic revision message', 'date': "2000-01-17T11:23:54+00:00", 'committer_date': "2000-01-17T11:23:54+00:00", 'children': [ '123546353ed3480476f032475e7c244eff7371d5' ], 'type': 'tar', 'synthetic': True, 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912' }] } } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) @istest def from_revision_invalid(self): revision_input = { 'id': hashutil.hash_to_bytes( '18d8be353ed3480476f032475e7c233eff7371d5'), 'directory': hashutil.hash_to_bytes( '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6'), 'author': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'committer': { 'name': b'Software Heritage', 'fullname': b'robot robot@softwareheritage.org', 'email': b'robot@softwareheritage.org', }, 'message': b'invalid message \xff', 'date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'committer_date': { 'timestamp': datetime.datetime( 2000, 1, 17, 11, 23, 54, tzinfo=datetime.timezone.utc).timestamp(), 'offset': 0, 'negative_utc': False, }, 'synthetic': True, 'type': 'tar', 'parents': [ hashutil.hash_to_bytes( '29d8be353ed3480476f032475e7c244eff7371d5'), hashutil.hash_to_bytes( '30d8be353ed3480476f032475e7c244eff7371d5') ], 'children': [ hashutil.hash_to_bytes( '123546353ed3480476f032475e7c244eff7371d5'), ], 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912', }] }, } expected_revision = { 'id': '18d8be353ed3480476f032475e7c233eff7371d5', 'directory': '7834ef7e7c357ce2af928115c6c6a42b7e2a44e6', 'author': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'committer': { 'name': 'Software Heritage', 'fullname': 'robot robot@softwareheritage.org', 'email': 'robot@softwareheritage.org', }, 'message': None, 'message_decoding_failed': True, 'date': "2000-01-17T11:23:54+00:00", 'committer_date': "2000-01-17T11:23:54+00:00", 'children': [ '123546353ed3480476f032475e7c244eff7371d5' ], 'parents': [ '29d8be353ed3480476f032475e7c244eff7371d5', '30d8be353ed3480476f032475e7c244eff7371d5' ], 'type': 'tar', 'synthetic': True, 'metadata': { 'original_artifact': [{ 'archive_type': 'tar', 'name': 'webbase-5.7.0.tar.gz', 'sha1': '147f73f369733d088b7a6fa9c4e0273dcd3c7ccd', 'sha1_git': '6a15ea8b881069adedf11feceec35588f2cfe8f1', 'sha256': '401d0df797110bea805d358b85bcc1ced29549d3d73f' '309d36484e7edf7bb912' }] }, 'merge': True } # when actual_revision = converters.from_revision(revision_input) # then self.assertEqual(actual_revision, expected_revision) @istest def from_content_none(self): self.assertIsNone(converters.from_content(None)) @istest def from_content(self): content_input = { 'sha1': hashutil.hash_to_bytes( '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5'), 'sha256': hashutil.hash_to_bytes( '39007420ca5de7cb3cfc15196335507e' 'e76c98930e7e0afa4d2747d3bf96c926'), 'blake2s256': hashutil.hash_to_bytes( '49007420ca5de7cb3cfc15196335507e' 'e76c98930e7e0afa4d2747d3bf96c926'), 'sha1_git': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'ctime': 'something-which-is-filtered-out', 'data': b'data in bytes', 'length': 10, 'status': 'hidden', } # 'status' is filtered expected_content = { 'checksums': { 'sha1': '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5', 'sha256': '39007420ca5de7cb3cfc15196335507ee76c98' '930e7e0afa4d2747d3bf96c926', 'blake2s256': '49007420ca5de7cb3cfc15196335507ee7' '6c98930e7e0afa4d2747d3bf96c926', 'sha1_git': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', }, 'data': b'data in bytes', 'length': 10, 'status': 'absent', } # when actual_content = converters.from_content(content_input) # then self.assertEqual(actual_content, expected_content) @istest def from_person(self): person_input = { 'id': 10, 'anything': 'else', 'name': b'bob', 'fullname': b'bob bob@alice.net', 'email': b'bob@foo.alice', } expected_person = { 'id': 10, 'anything': 'else', 'name': 'bob', 'fullname': 'bob bob@alice.net', 'email': 'bob@foo.alice', } # when actual_person = converters.from_person(person_input) # then self.assertEqual(actual_person, expected_person) @istest def from_directory_entries(self): dir_entries_input = { 'sha1': hashutil.hash_to_bytes( '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5'), 'sha256': hashutil.hash_to_bytes( '39007420ca5de7cb3cfc15196335507e' 'e76c98930e7e0afa4d2747d3bf96c926'), 'sha1_git': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'blake2s256': hashutil.hash_to_bytes( '685395c5dc57cada459364f0946d3dd45bad5fcbab' 'c1048edb44380f1d31d0aa'), 'target': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'dir_id': hashutil.hash_to_bytes( '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03'), 'name': b'bob', 'type': 10, 'status': 'hidden', } expected_dir_entries = { 'checksums': { 'sha1': '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5', 'sha256': '39007420ca5de7cb3cfc15196335507ee76c98' '930e7e0afa4d2747d3bf96c926', 'sha1_git': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', 'blake2s256': '685395c5dc57cada459364f0946d3dd45bad5f' 'cbabc1048edb44380f1d31d0aa', }, 'target': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', 'dir_id': '40e71b8614fcd89ccd17ca2b1d9e66c5b00a6d03', 'name': 'bob', 'type': 10, 'status': 'absent', } # when actual_dir_entries = converters.from_directory_entry(dir_entries_input) # then self.assertEqual(actual_dir_entries, expected_dir_entries) @istest def from_filetype(self): content_filetype = { 'id': hashutil.hash_to_bytes( '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5'), 'encoding': b'utf-8', 'mimetype': b'text/plain', } expected_content_filetype = { 'id': '5c6f0e2750f48fa0bd0c4cf5976ba0b9e02ebda5', 'encoding': 'utf-8', 'mimetype': 'text/plain', } # when actual_content_filetype = converters.from_filetype(content_filetype) # then self.assertEqual(actual_content_filetype, expected_content_filetype) diff --git a/version.txt b/version.txt index 51cd6cf4..00e3ae09 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.110-0-g11b2f55 \ No newline at end of file +v0.0.111-0-g8e8df4b \ No newline at end of file