diff --git a/swh/model/identifiers.py b/swh/model/identifiers.py index cf3b326..c53513a 100644 --- a/swh/model/identifiers.py +++ b/swh/model/identifiers.py @@ -1,465 +1,487 @@ # Copyright (C) 2015 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 binascii import datetime from functools import lru_cache from .hashutil import hash_data, hash_git_data @lru_cache() def identifier_to_bytes(identifier): """Convert a text identifier to bytes. Args: identifier: an identifier, either a 40-char hexadecimal string or a bytes object of length 20 Returns: The length 20 bytestring corresponding to the given identifier Raises: ValueError if the identifier is of an unexpected type or length. """ if isinstance(identifier, bytes): if len(identifier) != 20: raise ValueError( 'Wrong length for bytes identifier %s, expected 20' % len(identifier)) return identifier if isinstance(identifier, str): if len(identifier) != 40: raise ValueError( 'Wrong length for str identifier %s, expected 40' % len(identifier)) return bytes.fromhex(identifier) raise ValueError('Wrong type for identifier %s, expected bytes or str' % identifier.__class__.__name__) @lru_cache() def identifier_to_str(identifier): """Convert an identifier to an hexadecimal string. Args: identifier: an identifier, either a 40-char hexadecimal string or a bytes object of length 20 Returns: The length 40 string corresponding to the given identifier, hex encoded Raises: ValueError if the identifier is of an unexpected type or length. """ if isinstance(identifier, str): if len(identifier) != 40: raise ValueError( 'Wrong length for str identifier %s, expected 40' % len(identifier)) return identifier if isinstance(identifier, bytes): if len(identifier) != 20: raise ValueError( 'Wrong length for bytes identifier %s, expected 20' % len(identifier)) return binascii.hexlify(identifier).decode() raise ValueError('Wrong type for identifier %s, expected bytes or str' % identifier.__class__.__name__) def content_identifier(content): """Return the intrinsic identifier for a content. A content's identifier is the sha1, sha1_git and sha256 checksums of its data. Args: content: a content conforming to the Software Heritage schema Returns: A dictionary with all the hashes for the data Raises: KeyError if the content doesn't have a data member. """ hashes = hash_data( content['data'], {'sha1', 'sha1_git', 'sha256'}, ) return hashes def _sort_key(entry): """The sorting key for tree entries""" if entry['type'] == 'dir': return entry['name'] + b'/' else: return entry['name'] @lru_cache() def _perms_to_bytes(perms): """Convert the perms value to its bytes representation""" oc = oct(perms)[2:] return oc.encode('ascii') def directory_identifier(directory): """Return the intrinsic identifier for a directory. A directory's identifier is the tree sha1 à la git of a directory listing, using the following algorithm, which is equivalent to the git algorithm for trees: 1. Entries of the directory are sorted using the name (or the name with '/' appended for directory entries) as key, in bytes order. 2. For each entry of the directory, the following bytes are output: - the octal representation of the permissions for the entry (stored in the 'perms' member), which is a representation of the entry type: b'100644' (int 33188) for files b'100755' (int 33261) for executable files b'120000' (int 40960) for symbolic links b'40000' (int 16384) for directories b'160000' (int 57344) for references to revisions - an ascii space (b'\x20') - the entry's name (as raw bytes), stored in the 'name' member - a null byte (b'\x00') - the 20 byte long identifier of the object pointed at by the entry, stored in the 'target' member: for files or executable files: their blob sha1_git for symbolic links: the blob sha1_git of a file containing the link destination for directories: their intrinsic identifier for revisions: their intrinsic identifier (Note that there is no separator between entries) """ components = [] for entry in sorted(directory['entries'], key=_sort_key): components.extend([ _perms_to_bytes(entry['perms']), b'\x20', entry['name'], b'\x00', identifier_to_bytes(entry['target']), ]) return identifier_to_str(hash_git_data(b''.join(components), 'tree')) def format_date(date): """Convert a date object into an UTC timestamp encoded as ascii bytes. Git stores timestamps as an integer number of seconds since the UNIX epoch. However, Software Heritage stores timestamps as an integer number of microseconds (postgres type "datetime with timezone"). Therefore, we print timestamps with no microseconds as integers, and - timestamps with microseconds as floating point values. + timestamps with microseconds as floating point values. We elide the + trailing zeroes from microsecond values, to "future-proof" our + representation if we ever need more precision in timestamps. """ - if isinstance(date, datetime.datetime): - if date.microsecond == 0: - date = int(date.timestamp()) - else: - date = date.timestamp() - return str(date).encode() + if not isinstance(date, dict): + raise ValueError('format_date only supports dicts, %r received' % date) + + seconds = date.get('seconds', 0) + microseconds = date.get('microseconds', 0) + if not microseconds: + return str(seconds).encode() else: - if date == int(date): - date = int(date) - return str(date).encode() + float_value = ('%d.%06d' % (seconds, microseconds)) + return float_value.rstrip('0').encode() @lru_cache() def format_offset(offset, negative_utc=None): """Convert an integer number of minutes into an offset representation. The offset representation is [+-]hhmm where: hh is the number of hours; mm is the number of minutes. A null offset is represented as +0000. """ if offset < 0 or offset == 0 and negative_utc: sign = '-' else: sign = '+' hours = abs(offset) // 60 minutes = abs(offset) % 60 t = '%s%02d%02d' % (sign, hours, minutes) return t.encode() def normalize_timestamp(time_representation): """Normalize a time representation for processing by Software Heritage This function supports a numeric timestamp (representing a number of seconds since the UNIX epoch, 1970-01-01 at 00:00 UTC), a datetime.datetime object (with timezone information), or a normalized Software Heritage time representation (idempotency). Args: time_representation: the representation of a timestamp Returns: a normalized dictionary with three keys - - timestamp: a number of seconds since the UNIX epoch (1970-01-01 at 00:00 - UTC) + - timestamp: a dict with two optional keys: + - seconds: the integral number of seconds since the UNIX epoch + - microseconds: the integral number of microseconds - offset: the timezone offset as a number of minutes relative to UTC - negative_utc: a boolean representing whether the offset is -0000 when offset = 0. """ if time_representation is None: return None negative_utc = False if isinstance(time_representation, dict): - timestamp = time_representation['timestamp'] + ts = time_representation['timestamp'] + if isinstance(ts, dict): + seconds = ts.get('seconds', 0) + microseconds = ts.get('microseconds', 0) + elif isinstance(ts, int): + seconds = ts + microseconds = 0 + else: + raise ValueError( + 'normalize_timestamp received non-integer timestamp member:' + ' %r' % ts) offset = time_representation['offset'] if 'negative_utc' in time_representation: negative_utc = time_representation['negative_utc'] elif isinstance(time_representation, datetime.datetime): - timestamp = time_representation.timestamp() + seconds = int(time_representation.timestamp()) + microseconds = time_representation.microsecond utcoffset = time_representation.utcoffset() if utcoffset is None: raise ValueError( 'normalize_timestamp received datetime without timezone: %s' % time_representation) # utcoffset is an integer number of minutes seconds_offset = utcoffset.total_seconds() offset = int(seconds_offset) // 60 - else: - timestamp = time_representation + elif isinstance(time_representation, int): + seconds = time_representation + microseconds = 0 offset = 0 + else: + raise ValueError( + 'normalize_timestamp received non-integer timestamp:' + ' %r' % time_representation) return { - 'timestamp': timestamp, + 'timestamp': { + 'seconds': seconds, + 'microseconds': microseconds, + }, 'offset': offset, 'negative_utc': negative_utc, } def format_author(author): """Format the specification of an author. An author is either a byte string (passed unchanged), or a dict with three keys, fullname, name and email. If the fullname exists, return it; if it doesn't, we construct a fullname using the following heuristics: if the name value is None, we return the email in angle brackets, else, we return the name, a space, and the email in angle brackets. """ if isinstance(author, bytes) or author is None: return author if 'fullname' in author: return author['fullname'] ret = [] if author['name'] is not None: ret.append(author['name']) if author['email'] is not None: ret.append(b''.join([b'<', author['email'], b'>'])) return b' '.join(ret) def format_author_line(header, author, date_offset): """Format a an author line according to git standards. An author line has three components: - a header, describing the type of author (author, committer, tagger) - a name and email, which is an arbitrary bytestring - optionally, a timestamp with UTC offset specification The author line is formatted thus: `header` `name and email`[ `timestamp` `utc_offset`] The timestamp is encoded as a (decimal) number of seconds since the UNIX epoch (1970-01-01 at 00:00 UTC). As an extension to the git format, we support fractional timestamps, using a dot as the separator for the decimal part. The utc offset is a number of minutes encoded as '[+-]HHMM'. Note some tools can pass a negative offset corresponding to the UTC timezone ('-0000'), which is valid and is encoded as such. For convenience, this function returns the whole line with its trailing newline. Args: header: the header of the author line (one of 'author', 'committer', 'tagger') author: an author specification (dict with two bytes values: name and email, or byte value) date_offset: a normalized date/time representation as returned by `normalize_timestamp`. Returns: the newline-terminated byte string containing the author line """ ret = [header.encode(), b' ', format_author(author)] date_offset = normalize_timestamp(date_offset) if date_offset is not None: date_f = format_date(date_offset['timestamp']) offset_f = format_offset(date_offset['offset'], date_offset['negative_utc']) ret.extend([b' ', date_f, b' ', offset_f]) ret.append(b'\n') return b''.join(ret) def revision_identifier(revision): """Return the intrinsic identifier for a revision. The fields used for the revision identifier computation are: - directory - parents - author - author_date - committer - committer_date - metadata -> extra_headers - message A revision's identifier is the 'git'-checksum of a commit manifest constructed as follows (newlines are a single ASCII newline character): ``` tree [for each parent in parents] parent [end for each parents] author committer [for each key, value in extra_headers] [end for each extra_headers] ``` The directory identifier is the ascii representation of its hexadecimal encoding. Author and committer are formatted with the `format_author` function. Dates are formatted with the `format_date_offset` function. Extra headers are an ordered list of [key, value] pairs. Keys are strings and get encoded to utf-8 for identifier computation. Values are either byte strings, unicode strings (that get encoded to utf-8), or integers (that get encoded to their utf-8 decimal representation). Multiline extra header values are escaped by indenting the continuation lines with one ascii space. If the message is None, the manifest ends with the last header. Else, the message is appended to the headers after an empty line. The checksum of the full manifest is computed using the 'commit' git object type. """ components = [ b'tree ', identifier_to_str(revision['directory']).encode(), b'\n', ] for parent in revision['parents']: if parent: components.extend([ b'parent ', identifier_to_str(parent).encode(), b'\n', ]) components.extend([ format_author_line('author', revision['author'], revision['date']), format_author_line('committer', revision['committer'], revision['committer_date']), ]) # Handle extra headers metadata = revision.get('metadata') if not metadata: metadata = {} for key, value in metadata.get('extra_headers', []): # Integer values: decimal representation if isinstance(value, int): value = str(value).encode('utf-8') # Unicode string values: utf-8 encoding if isinstance(value, str): value = value.encode('utf-8') # multi-line values: indent continuation lines if b'\n' in value: value_chunks = value.split(b'\n') value = b'\n '.join(value_chunks) # encode the key to utf-8 components.extend([key.encode('utf-8'), b' ', value, b'\n']) if revision['message'] is not None: components.extend([b'\n', revision['message']]) commit_raw = b''.join(components) return identifier_to_str(hash_git_data(commit_raw, 'commit')) def target_type_to_git(target_type): """Convert a software heritage target type to a git object type""" return { 'content': b'blob', 'directory': b'tree', 'revision': b'commit', 'release': b'tag', }[target_type] def release_identifier(release): """Return the intrinsic identifier for a release.""" components = [ b'object ', identifier_to_str(release['target']).encode(), b'\n', b'type ', target_type_to_git(release['target_type']), b'\n', b'tag ', release['name'], b'\n', ] if 'author' in release and release['author']: components.append( format_author_line('tagger', release['author'], release['date']) ) if release['message'] is not None: components.extend([b'\n', release['message']]) return identifier_to_str(hash_git_data(b''.join(components), 'tag')) diff --git a/swh/model/tests/test_identifiers.py b/swh/model/tests/test_identifiers.py index e1adfea..16a34bb 100644 --- a/swh/model/tests/test_identifiers.py +++ b/swh/model/tests/test_identifiers.py @@ -1,641 +1,651 @@ # Copyright (C) 2015 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 binascii import datetime import unittest from nose.tools import istest from swh.model import hashutil, identifiers class UtilityFunctionsIdentifier(unittest.TestCase): def setUp(self): self.str_id = 'c2e41aae41ac17bd4a650770d6ee77f62e52235b' self.bytes_id = binascii.unhexlify(self.str_id) self.bad_type_id = object() @istest def identifier_to_bytes(self): for id in [self.str_id, self.bytes_id]: self.assertEqual(identifiers.identifier_to_bytes(id), self.bytes_id) # wrong length with self.assertRaises(ValueError) as cm: identifiers.identifier_to_bytes(id[:-2]) self.assertIn('length', str(cm.exception)) with self.assertRaises(ValueError) as cm: identifiers.identifier_to_bytes(self.bad_type_id) self.assertIn('type', str(cm.exception)) @istest def identifier_to_str(self): for id in [self.str_id, self.bytes_id]: self.assertEqual(identifiers.identifier_to_str(id), self.str_id) # wrong length with self.assertRaises(ValueError) as cm: identifiers.identifier_to_str(id[:-2]) self.assertIn('length', str(cm.exception)) with self.assertRaises(ValueError) as cm: identifiers.identifier_to_str(self.bad_type_id) self.assertIn('type', str(cm.exception)) class UtilityFunctionsDateOffset(unittest.TestCase): def setUp(self): - self.date = datetime.datetime( - 2015, 11, 22, 16, 33, 56, tzinfo=datetime.timezone.utc) - self.date_int = int(self.date.timestamp()) - self.date_repr = b'1448210036' - - self.date_microseconds = datetime.datetime( - 2015, 11, 22, 16, 33, 56, 2342, tzinfo=datetime.timezone.utc) - self.date_microseconds_float = self.date_microseconds.timestamp() - self.date_microseconds_repr = b'1448210036.002342' + self.dates = { + b'1448210036': { + 'seconds': 1448210036, + 'microseconds': 0, + }, + b'1448210036.002342': { + 'seconds': 1448210036, + 'microseconds': 2342, + }, + b'1448210036.12': { + 'seconds': 1448210036, + 'microseconds': 120000, + } + } + self.broken_dates = [ + 1448210036.12, + ] self.offsets = { 0: b'+0000', -630: b'-1030', 800: b'+1320', } @istest def format_date(self): - for date in [self.date, self.date_int]: - self.assertEqual(identifiers.format_date(date), self.date_repr) + for date_repr, date in self.dates.items(): + self.assertEqual(identifiers.format_date(date), date_repr) - for date in [self.date_microseconds, self.date_microseconds_float]: - self.assertEqual(identifiers.format_date(date), - self.date_microseconds_repr) + @istest + def format_date_fail(self): + for date in self.broken_dates: + with self.assertRaises(ValueError): + identifiers.format_date(date) @istest def format_offset(self): for offset, res in self.offsets.items(): self.assertEqual(identifiers.format_offset(offset), res) class ContentIdentifier(unittest.TestCase): def setUp(self): self.content = { 'status': 'visible', 'length': 5, 'data': b'1984\n', 'ctime': datetime.datetime(2015, 11, 22, 16, 33, 56, tzinfo=datetime.timezone.utc), } self.content_id = hashutil.hash_data(self.content['data']) @istest def content_identifier(self): self.assertEqual(identifiers.content_identifier(self.content), self.content_id) class DirectoryIdentifier(unittest.TestCase): def setUp(self): self.directory = { 'id': 'c2e41aae41ac17bd4a650770d6ee77f62e52235b', 'entries': [ { 'type': 'file', 'perms': 33188, 'name': b'README', 'target': '37ec8ea2110c0b7a32fbb0e872f6e7debbf95e21' }, { 'type': 'file', 'perms': 33188, 'name': b'Rakefile', 'target': '3bb0e8592a41ae3185ee32266c860714980dbed7' }, { 'type': 'dir', 'perms': 16384, 'name': b'app', 'target': '61e6e867f5d7ba3b40540869bc050b0c4fed9e95' }, { 'type': 'file', 'perms': 33188, 'name': b'1.megabyte', 'target': '7c2b2fbdd57d6765cdc9d84c2d7d333f11be7fb3' }, { 'type': 'dir', 'perms': 16384, 'name': b'config', 'target': '591dfe784a2e9ccc63aaba1cb68a765734310d98' }, { 'type': 'dir', 'perms': 16384, 'name': b'public', 'target': '9588bf4522c2b4648bfd1c61d175d1f88c1ad4a5' }, { 'type': 'file', 'perms': 33188, 'name': b'development.sqlite3', 'target': 'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391' }, { 'type': 'dir', 'perms': 16384, 'name': b'doc', 'target': '154705c6aa1c8ead8c99c7915373e3c44012057f' }, { 'type': 'dir', 'perms': 16384, 'name': b'db', 'target': '85f157bdc39356b7bc7de9d0099b4ced8b3b382c' }, { 'type': 'dir', 'perms': 16384, 'name': b'log', 'target': '5e3d3941c51cce73352dff89c805a304ba96fffe' }, { 'type': 'dir', 'perms': 16384, 'name': b'script', 'target': '1b278423caf176da3f3533592012502aa10f566c' }, { 'type': 'dir', 'perms': 16384, 'name': b'test', 'target': '035f0437c080bfd8711670b3e8677e686c69c763' }, { 'type': 'dir', 'perms': 16384, 'name': b'vendor', 'target': '7c0dc9ad978c1af3f9a4ce061e50f5918bd27138' }, { 'type': 'rev', 'perms': 57344, 'name': b'will_paginate', 'target': '3d531e169db92a16a9a8974f0ae6edf52e52659e' } ], } self.empty_directory = { 'id': '4b825dc642cb6eb9a060e54bf8d69288fbee4904', 'entries': [], } @istest def dir_identifier(self): self.assertEqual( identifiers.directory_identifier(self.directory), self.directory['id']) @istest def dir_identifier_empty_directory(self): self.assertEqual( identifiers.directory_identifier(self.empty_directory), self.empty_directory['id']) class RevisionIdentifier(unittest.TestCase): def setUp(self): linus_tz = datetime.timezone(datetime.timedelta(minutes=-420)) gpgsig = b'''\ -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.13 (Darwin) iQIcBAABAgAGBQJVJcYsAAoJEBiY3kIkQRNJVAUQAJ8/XQIfMqqC5oYeEFfHOPYZ L7qy46bXHVBa9Qd8zAJ2Dou3IbI2ZoF6/Et89K/UggOycMlt5FKV/9toWyuZv4Po L682wonoxX99qvVTHo6+wtnmYO7+G0f82h+qHMErxjP+I6gzRNBvRr+SfY7VlGdK wikMKOMWC5smrScSHITnOq1Ews5pe3N7qDYMzK0XVZmgDoaem4RSWMJs4My/qVLN e0CqYWq2A22GX7sXl6pjneJYQvcAXUX+CAzp24QnPSb+Q22Guj91TcxLFcHCTDdn qgqMsEyMiisoglwrCbO+D+1xq9mjN9tNFWP66SQ48mrrHYTBV5sz9eJyDfroJaLP CWgbDTgq6GzRMehHT3hXfYS5NNatjnhkNISXR7pnVP/obIi/vpWh5ll6Gd8q26z+ a/O41UzOaLTeNI365MWT4/cnXohVLRG7iVJbAbCxoQmEgsYMRc/pBAzWJtLfcB2G jdTswYL6+MUdL8sB9pZ82D+BP/YAdHe69CyTu1lk9RT2pYtI/kkfjHubXBCYEJSG +VGllBbYG6idQJpyrOYNRJyrDi9yvDJ2W+S0iQrlZrxzGBVGTB/y65S8C+2WTBcE lf1Qb5GDsQrZWgD+jtWTywOYHtCBwyCKSAXxSARMbNPeak9WPlcW/Jmu+fUcMe2x dg1KdHOa34shrKDaOVzW =od6m -----END PGP SIGNATURE-----''' self.revision = { 'id': 'bc0195aad0daa2ad5b0d76cce22b167bc3435590', 'directory': '85a74718d377195e1efd0843ba4f3260bad4fe07', 'parents': ['01e2d0627a9a6edb24c37db45db5ecb31e9de808'], 'author': { 'name': b'Linus Torvalds', 'email': b'torvalds@linux-foundation.org', }, 'date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'committer': { 'name': b'Linus Torvalds', 'email': b'torvalds@linux-foundation.org', }, 'committer_date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'message': b'Linux 4.2-rc2\n', } self.revision_none_metadata = { 'id': 'bc0195aad0daa2ad5b0d76cce22b167bc3435590', 'directory': '85a74718d377195e1efd0843ba4f3260bad4fe07', 'parents': ['01e2d0627a9a6edb24c37db45db5ecb31e9de808'], 'author': { 'name': b'Linus Torvalds', 'email': b'torvalds@linux-foundation.org', }, 'date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'committer': { 'name': b'Linus Torvalds', 'email': b'torvalds@linux-foundation.org', }, 'committer_date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'message': b'Linux 4.2-rc2\n', 'metadata': None, } self.synthetic_revision = { 'id': b'\xb2\xa7\xe1&\x04\x92\xe3D\xfa\xb3\xcb\xf9\x1b\xc1<\x91' b'\xe0T&\xfd', 'author': { 'name': b'Software Heritage', 'email': b'robot@softwareheritage.org', }, 'date': { - 'timestamp': 1437047495.0, + 'timestamp': {'seconds': 1437047495}, 'offset': 0, 'negative_utc': False, }, 'type': 'tar', 'committer': { 'name': b'Software Heritage', 'email': b'robot@softwareheritage.org', }, 'committer_date': 1437047495, 'synthetic': True, 'parents': [None], 'message': b'synthetic revision message\n', 'directory': b'\xd1\x1f\x00\xa6\xa0\xfe\xa6\x05SA\xd2U\x84\xb5\xa9' b'e\x16\xc0\xd2\xb8', 'metadata': {'original_artifact': [ {'archive_type': 'tar', 'name': 'gcc-5.2.0.tar.bz2', 'sha1_git': '39d281aff934d44b439730057e55b055e206a586', 'sha1': 'fe3f5390949d47054b613edc36c557eb1d51c18e', 'sha256': '5f835b04b5f7dd4f4d2dc96190ec1621b8d89f' '2dc6f638f9f8bc1b1014ba8cad'}]}, } # cat commit.txt | git hash-object -t commit --stdin self.revision_with_extra_headers = { 'id': '010d34f384fa99d047cdd5e2f41e56e5c2feee45', 'directory': '85a74718d377195e1efd0843ba4f3260bad4fe07', 'parents': ['01e2d0627a9a6edb24c37db45db5ecb31e9de808'], 'author': { 'name': b'Linus Torvalds', 'email': b'torvalds@linux-foundation.org', 'fullname': b'Linus Torvalds ', }, 'date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'committer': { 'name': b'Linus Torvalds', 'email': b'torvalds@linux-foundation.org', 'fullname': b'Linus Torvalds ', }, 'committer_date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'message': b'Linux 4.2-rc2\n', 'metadata': { 'extra_headers': [ ['svn-repo-uuid', '046f1af7-66c2-d61b-5410-ce57b7db7bff'], ['svn-revision', 10], ] } } self.revision_with_gpgsig = { 'id': '44cc742a8ca17b9c279be4cc195a93a6ef7a320e', 'directory': 'b134f9b7dc434f593c0bab696345548b37de0558', 'parents': ['689664ae944b4692724f13b709a4e4de28b54e57', 'c888305e1efbaa252d01b4e5e6b778f865a97514'], 'author': { 'name': b'Jiang Xin', 'email': b'worldhello.net@gmail.com', 'fullname': b'Jiang Xin ', }, 'date': { - 'timestamp': '1428538899', + 'timestamp': 1428538899, 'offset': 480, }, 'committer': { 'name': b'Jiang Xin', 'email': b'worldhello.net@gmail.com', }, 'committer_date': { - 'timestamp': '1428538899', + 'timestamp': 1428538899, 'offset': 480, }, 'metadata': { 'extra_headers': [ ['gpgsig', gpgsig], ], }, 'message': b'''Merge branch 'master' of git://github.com/alexhenrie/git-po * 'master' of git://github.com/alexhenrie/git-po: l10n: ca.po: update translation ''' } self.revision_no_message = { 'id': '4cfc623c9238fa92c832beed000ce2d003fd8333', 'directory': 'b134f9b7dc434f593c0bab696345548b37de0558', 'parents': ['689664ae944b4692724f13b709a4e4de28b54e57', 'c888305e1efbaa252d01b4e5e6b778f865a97514'], 'author': { 'name': b'Jiang Xin', 'email': b'worldhello.net@gmail.com', 'fullname': b'Jiang Xin ', }, 'date': { - 'timestamp': '1428538899', + 'timestamp': 1428538899, 'offset': 480, }, 'committer': { 'name': b'Jiang Xin', 'email': b'worldhello.net@gmail.com', }, 'committer_date': { - 'timestamp': '1428538899', + 'timestamp': 1428538899, 'offset': 480, }, 'message': None, } self.revision_empty_message = { 'id': '7442cd78bd3b4966921d6a7f7447417b7acb15eb', 'directory': 'b134f9b7dc434f593c0bab696345548b37de0558', 'parents': ['689664ae944b4692724f13b709a4e4de28b54e57', 'c888305e1efbaa252d01b4e5e6b778f865a97514'], 'author': { 'name': b'Jiang Xin', 'email': b'worldhello.net@gmail.com', 'fullname': b'Jiang Xin ', }, 'date': { - 'timestamp': '1428538899', + 'timestamp': 1428538899, 'offset': 480, }, 'committer': { 'name': b'Jiang Xin', 'email': b'worldhello.net@gmail.com', }, 'committer_date': { - 'timestamp': '1428538899', + 'timestamp': 1428538899, 'offset': 480, }, 'message': b'', } self.revision_only_fullname = { 'id': '010d34f384fa99d047cdd5e2f41e56e5c2feee45', 'directory': '85a74718d377195e1efd0843ba4f3260bad4fe07', 'parents': ['01e2d0627a9a6edb24c37db45db5ecb31e9de808'], 'author': { 'fullname': b'Linus Torvalds ', }, 'date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'committer': { 'fullname': b'Linus Torvalds ', }, 'committer_date': datetime.datetime(2015, 7, 12, 15, 10, 30, tzinfo=linus_tz), 'message': b'Linux 4.2-rc2\n', 'metadata': { 'extra_headers': [ ['svn-repo-uuid', '046f1af7-66c2-d61b-5410-ce57b7db7bff'], ['svn-revision', 10], ] } } @istest def revision_identifier(self): self.assertEqual( identifiers.revision_identifier(self.revision), identifiers.identifier_to_str(self.revision['id']), ) @istest def revision_identifier_none_metadata(self): self.assertEqual( identifiers.revision_identifier(self.revision_none_metadata), identifiers.identifier_to_str(self.revision_none_metadata['id']), ) @istest def revision_identifier_synthetic(self): self.assertEqual( identifiers.revision_identifier(self.synthetic_revision), identifiers.identifier_to_str(self.synthetic_revision['id']), ) @istest def revision_identifier_with_extra_headers(self): self.assertEqual( identifiers.revision_identifier( self.revision_with_extra_headers), identifiers.identifier_to_str( self.revision_with_extra_headers['id']), ) @istest def revision_identifier_with_gpgsig(self): self.assertEqual( identifiers.revision_identifier( self.revision_with_gpgsig), identifiers.identifier_to_str( self.revision_with_gpgsig['id']), ) @istest def revision_identifier_no_message(self): self.assertEqual( identifiers.revision_identifier( self.revision_no_message), identifiers.identifier_to_str( self.revision_no_message['id']), ) @istest def revision_identifier_empty_message(self): self.assertEqual( identifiers.revision_identifier( self.revision_empty_message), identifiers.identifier_to_str( self.revision_empty_message['id']), ) @istest def revision_identifier_only_fullname(self): self.assertEqual( identifiers.revision_identifier( self.revision_only_fullname), identifiers.identifier_to_str( self.revision_only_fullname['id']), ) class ReleaseIdentifier(unittest.TestCase): def setUp(self): linus_tz = datetime.timezone(datetime.timedelta(minutes=-420)) self.release = { 'id': '2b10839e32c4c476e9d94492756bb1a3e1ec4aa8', 'target': b't\x1b"R\xa5\xe1Ml`\xa9\x13\xc7z`\x99\xab\xe7:\x85J', 'target_type': 'revision', 'name': b'v2.6.14', 'author': { 'name': b'Linus Torvalds', 'email': b'torvalds@g5.osdl.org', }, 'date': datetime.datetime(2005, 10, 27, 17, 2, 33, tzinfo=linus_tz), 'message': b'''\ Linux 2.6.14 release -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (GNU/Linux) iD8DBQBDYWq6F3YsRnbiHLsRAmaeAJ9RCez0y8rOBbhSv344h86l/VVcugCeIhO1 wdLOnvj91G4wxYqrvThthbE= =7VeT -----END PGP SIGNATURE----- ''', 'synthetic': False, } self.release_no_author = { 'id': b'&y\x1a\x8b\xcf\x0em3\xf4:\xefv\x82\xbd\xb5U#mV\xde', 'target': '9ee1c939d1cb936b1f98e8d81aeffab57bae46ab', 'target_type': 'revision', 'name': b'v2.6.12', 'message': b'''\ This is the final 2.6.12 release -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.4 (GNU/Linux) iD8DBQBCsykyF3YsRnbiHLsRAvPNAJ482tCZwuxp/bJRz7Q98MHlN83TpACdHr37 o6X/3T+vm8K3bf3driRr34c= =sBHn -----END PGP SIGNATURE----- ''', 'synthetic': False, } self.release_no_message = { 'id': 'b6f4f446715f7d9543ef54e41b62982f0db40045', 'target': '9ee1c939d1cb936b1f98e8d81aeffab57bae46ab', 'target_type': 'revision', 'name': b'v2.6.12', 'author': { 'name': b'Linus Torvalds', 'email': b'torvalds@g5.osdl.org', }, 'date': datetime.datetime(2005, 10, 27, 17, 2, 33, tzinfo=linus_tz), 'message': None, } self.release_empty_message = { 'id': '71a0aea72444d396575dc25ac37fec87ee3c6492', 'target': '9ee1c939d1cb936b1f98e8d81aeffab57bae46ab', 'target_type': 'revision', 'name': b'v2.6.12', 'author': { 'name': b'Linus Torvalds', 'email': b'torvalds@g5.osdl.org', }, 'date': datetime.datetime(2005, 10, 27, 17, 2, 33, tzinfo=linus_tz), 'message': b'', } self.release_negative_utc = { 'id': '97c8d2573a001f88e72d75f596cf86b12b82fd01', 'name': b'20081029', 'target': '54e9abca4c77421e2921f5f156c9fe4a9f7441c7', 'target_type': 'revision', 'date': { - 'timestamp': 1225281976.0, + 'timestamp': {'seconds': 1225281976}, 'offset': 0, 'negative_utc': True, }, 'author': { 'name': b'Otavio Salvador', 'email': b'otavio@debian.org', 'id': 17640, }, 'synthetic': False, 'message': b'tagging version 20081029\n\nr56558\n', } @istest def release_identifier(self): self.assertEqual( identifiers.release_identifier(self.release), identifiers.identifier_to_str(self.release['id']) ) @istest def release_identifier_no_author(self): self.assertEqual( identifiers.release_identifier(self.release_no_author), identifiers.identifier_to_str(self.release_no_author['id']) ) @istest def release_identifier_no_message(self): self.assertEqual( identifiers.release_identifier(self.release_no_message), identifiers.identifier_to_str(self.release_no_message['id']) ) @istest def release_identifier_empty_message(self): self.assertEqual( identifiers.release_identifier(self.release_empty_message), identifiers.identifier_to_str(self.release_empty_message['id']) ) @istest def release_identifier_negative_utc(self): self.assertEqual( identifiers.release_identifier(self.release_negative_utc), identifiers.identifier_to_str(self.release_negative_utc['id']) )