diff --git a/swh/model/identifiers.py b/swh/model/identifiers.py index 372bc7c..e1cf0df 100644 --- a/swh/model/identifiers.py +++ b/swh/model/identifiers.py @@ -1,859 +1,862 @@ # Copyright (C) 2015-2019 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 hashlib from functools import lru_cache from typing import Any, Dict, Union import attr from deprecated import deprecated from .collections import ImmutableDict from .exceptions import ValidationError from .fields.hashes import validate_sha1 from .hashutil import hash_git_data, hash_to_hex, MultiHash ORIGIN = "origin" SNAPSHOT = "snapshot" REVISION = "revision" RELEASE = "release" DIRECTORY = "directory" CONTENT = "content" SWHID_NAMESPACE = "swh" SWHID_VERSION = 1 SWHID_TYPES = ["ori", "snp", "rel", "rev", "dir", "cnt"] SWHID_SEP = ":" SWHID_CTXT_SEP = ";" # deprecated variables PID_NAMESPACE = SWHID_NAMESPACE PID_VERSION = SWHID_VERSION PID_TYPES = SWHID_TYPES PID_SEP = SWHID_SEP PID_CTXT_SEP = SWHID_CTXT_SEP @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. """ return MultiHash.from_data(content["data"]).digest() def directory_entry_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 escape_newlines(snippet): """Escape the newlines present in snippet according to git rules. New lines in git manifests are escaped by indenting the next line by one space. """ if b"\n" in snippet: return b"\n ".join(snippet.split(b"\n")) else: return snippet 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=directory_entry_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. We elide the trailing zeroes from microsecond values, to "future-proof" our representation if we ever need more precision in timestamps. """ 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: 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 :obj:`datetime.datetime` object (with timezone information), or a normalized Software Heritage time representation (idempotency). Args: time_representation: the representation of a timestamp Returns: dict: a normalized dictionary with three keys: - 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): 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"] if negative_utc is None: negative_utc = False elif isinstance(time_representation, datetime.datetime): 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 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": {"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 :func:`normalize_timestamp`. Returns: the newline-terminated byte string containing the author line """ ret = [header.encode(), b" ", escape_newlines(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 - extra_headers or 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 :func:`format_author` function. Dates are formatted with the :func:`format_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") or {} extra_headers = revision.get("extra_headers", ()) if not extra_headers and "extra_headers" in metadata: extra_headers = metadata["extra_headers"] for key, value in extra_headers: components.extend([key, b" ", escape_newlines(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", "snapshot": b"refs", }[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")) def snapshot_identifier(snapshot, *, ignore_unresolved=False): """Return the intrinsic identifier for a snapshot. Snapshots are a set of named branches, which are pointers to objects at any level of the Software Heritage DAG. As well as pointing to other objects in the Software Heritage DAG, branches can also be *alias*es, in which case their target is the name of another branch in the same snapshot, or *dangling*, in which case the target is unknown (and represented by the ``None`` value). A snapshot identifier is a salted sha1 (using the git hashing algorithm with the ``snapshot`` object type) of a manifest following the algorithm: 1. Branches are sorted using the name as key, in bytes order. 2. For each branch, the following bytes are output: - the type of the branch target: - ``content``, ``directory``, ``revision``, ``release`` or ``snapshot`` for the corresponding entries in the DAG; - ``alias`` for branches referencing another branch; - ``dangling`` for dangling branches - an ascii space (``\\x20``) - the branch name (as raw bytes) - a null byte (``\\x00``) - the length of the target identifier, as an ascii-encoded decimal number (``20`` for current intrinsic identifiers, ``0`` for dangling branches, the length of the target branch name for branch aliases) - a colon (``:``) - the identifier of the target object pointed at by the branch, stored in the 'target' member: - for contents: their *sha1_git* - for directories, revisions, releases or snapshots: their intrinsic identifier - for branch aliases, the name of the target branch (as raw bytes) - for dangling branches, the empty string Note that, akin to directory manifests, there is no separator between entries. Because of symbolic branches, identifiers are of arbitrary length but are length-encoded to avoid ambiguity. Args: snapshot (dict): the snapshot of which to compute the identifier. A single entry is needed, ``'branches'``, which is itself a :class:`dict` mapping each branch to its target ignore_unresolved (bool): if `True`, ignore unresolved branch aliases. Returns: str: the intrinsic identifier for `snapshot` """ unresolved = [] lines = [] for name, target in sorted(snapshot["branches"].items()): if not target: target_type = b"dangling" target_id = b"" elif target["target_type"] == "alias": target_type = b"alias" target_id = target["target"] if target_id not in snapshot["branches"] or target_id == name: unresolved.append((name, target_id)) else: target_type = target["target_type"].encode() target_id = identifier_to_bytes(target["target"]) lines.extend( [ target_type, b"\x20", name, b"\x00", ("%d:" % len(target_id)).encode(), target_id, ] ) if unresolved and not ignore_unresolved: raise ValueError( "Branch aliases unresolved: %s" % ", ".join("%s -> %s" % x for x in unresolved), unresolved, ) return identifier_to_str(hash_git_data(b"".join(lines), "snapshot")) def origin_identifier(origin): """Return the intrinsic identifier for an origin. An origin's identifier is the sha1 checksum of the entire origin URL """ return hashlib.sha1(origin["url"].encode("utf-8")).hexdigest() _object_type_map = { ORIGIN: {"short_name": "ori", "key_id": "id"}, SNAPSHOT: {"short_name": "snp", "key_id": "id"}, RELEASE: {"short_name": "rel", "key_id": "id"}, REVISION: {"short_name": "rev", "key_id": "id"}, DIRECTORY: {"short_name": "dir", "key_id": "id"}, CONTENT: {"short_name": "cnt", "key_id": "sha1_git"}, } @attr.s(frozen=True) class SWHID: """ Named tuple holding the relevant info associated to a SoftWare Heritage persistent IDentifier (SWHID) Args: namespace (str): the namespace of the identifier, defaults to ``swh`` scheme_version (int): the scheme version of the identifier, defaults to 1 object_type (str): the type of object the identifier points to, either ``content``, ``directory``, ``release``, ``revision`` or ``snapshot`` object_id (str): object's identifier metadata (dict): optional dict filled with metadata related to pointed object Raises: swh.model.exceptions.ValidationError: In case of invalid object type or id Once created, it contains the following attributes: Attributes: namespace (str): the namespace of the identifier scheme_version (int): the scheme version of the identifier object_type (str): the type of object the identifier points to object_id (str): hexadecimal representation of the object hash metadata (dict): metadata related to the pointed object To get the raw SWHID string from an instance of this named tuple, use the :func:`str` function:: swhid = SWHID( object_type='content', object_id='8ff44f081d43176474b267de5451f2c2e88089d0' ) swhid_str = str(swhid) # 'swh:1:cnt:8ff44f081d43176474b267de5451f2c2e88089d0' """ namespace = attr.ib(type=str, default="swh") scheme_version = attr.ib(type=int, default=1) object_type = attr.ib(type=str, default="") object_id = attr.ib(type=str, converter=hash_to_hex, default="") # type: ignore metadata = attr.ib( type=ImmutableDict[str, Any], converter=ImmutableDict, default=ImmutableDict() ) @namespace.validator def check_namespace(self, attribute, value): if value != SWHID_NAMESPACE: raise ValidationError( "Wrong format: only supported namespace is '%s'" % SWHID_NAMESPACE ) @scheme_version.validator def check_scheme_version(self, attribute, value): if value != SWHID_VERSION: raise ValidationError( "Wrong format: only supported version is %d" % SWHID_VERSION ) @object_type.validator def check_object_type(self, attribute, value): if value not in _object_type_map: raise ValidationError( "Wrong input: Supported types are %s" % (list(_object_type_map.keys())) ) @object_id.validator def check_object_id(self, attribute, value): validate_sha1(value) # can raise if invalid hash + def to_dict(self) -> Dict[str, Any]: + return attr.asdict(self) + def __str__(self) -> str: o = _object_type_map.get(self.object_type) assert o swhid = SWHID_SEP.join( [self.namespace, str(self.scheme_version), o["short_name"], self.object_id] ) if self.metadata: for k, v in self.metadata.items(): swhid += "%s%s=%s" % (SWHID_CTXT_SEP, k, v) return swhid @deprecated("Use swh.model.identifiers.SWHID instead") class PersistentId(SWHID): """ Named tuple holding the relevant info associated to a SoftWare Heritage persistent IDentifier. .. deprecated:: 0.3.8 Use :class:`swh.model.identifiers.SWHID` instead """ pass def swhid( object_type: str, object_id: Union[str, Dict[str, Any]], scheme_version: int = 1, metadata: Union[ImmutableDict[str, Any], Dict[str, Any]] = ImmutableDict(), ) -> str: """Compute :ref:`persistent-identifiers` Args: object_type: object's type, either ``content``, ``directory``, ``release``, ``revision`` or ``snapshot`` object_id: object's identifier scheme_version: SWHID scheme version, defaults to 1 metadata: metadata related to the pointed object Raises: swh.model.exceptions.ValidationError: In case of invalid object type or id Returns: the SWHID of the object """ if isinstance(object_id, dict): o = _object_type_map[object_type] object_id = object_id[o["key_id"]] swhid = SWHID( scheme_version=scheme_version, object_type=object_type, object_id=object_id, metadata=metadata, # type: ignore # mypy can't properly unify types ) return str(swhid) @deprecated("Use swh.model.identifiers.swhid instead") def persistent_identifier(*args, **kwargs) -> str: """Compute :ref:`persistent-identifiers` .. deprecated:: 0.3.8 Use :func:`swh.model.identifiers.swhid` instead """ return swhid(*args, **kwargs) def parse_swhid(swhid: str) -> SWHID: """Parse :ref:`persistent-identifiers`. Args: swhid (str): A persistent identifier Raises: swh.model.exceptions.ValidationError: in case of: * missing mandatory values (4) * invalid namespace supplied * invalid version supplied * invalid type supplied * missing hash * invalid hash identifier supplied Returns: a named tuple holding the parsing result """ # ; swhid_parts = swhid.split(SWHID_CTXT_SEP) swhid_data = swhid_parts.pop(0).split(":") if len(swhid_data) != 4: raise ValidationError("Wrong format: There should be 4 mandatory values") # Checking for parsing errors _ns, _version, _type, _id = swhid_data for otype, data in _object_type_map.items(): if _type == data["short_name"]: _type = otype break if not _id: raise ValidationError("Wrong format: Identifier should be present") _metadata = {} for part in swhid_parts: try: key, val = part.split("=") _metadata[key] = val except Exception: msg = "Contextual data is badly formatted, form key=val expected" raise ValidationError(msg) return SWHID( _ns, int(_version), _type, _id, _metadata, # type: ignore # mypy can't properly unify types ) @deprecated("Use swh.model.identifiers.parse_swhid instead") def parse_persistent_identifier(persistent_id: str) -> PersistentId: """Parse :ref:`persistent-identifiers`. .. deprecated:: 0.3.8 Use :func:`swh.model.identifiers.parse_swhid` instead """ - return PersistentId(**attr.asdict(parse_swhid(persistent_id))) + return PersistentId(**parse_swhid(persistent_id).to_dict()) diff --git a/swh/model/tests/test_identifiers.py b/swh/model/tests/test_identifiers.py index c03b9ef..5acbd2d 100644 --- a/swh/model/tests/test_identifiers.py +++ b/swh/model/tests/test_identifiers.py @@ -1,1066 +1,1076 @@ # Copyright (C) 2015-2018 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 binascii import datetime import pytest import unittest from swh.model import hashutil, identifiers from swh.model.exceptions import ValidationError from swh.model.hashutil import hash_to_bytes as _x from swh.model.identifiers import ( CONTENT, DIRECTORY, RELEASE, REVISION, SNAPSHOT, SWHID, normalize_timestamp, ) class UtilityFunctionsIdentifier(unittest.TestCase): def setUp(self): self.str_id = "c2e41aae41ac17bd4a650770d6ee77f62e52235b" self.bytes_id = binascii.unhexlify(self.str_id) self.bad_type_id = object() def test_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)) def test_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.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", } def test_format_date(self): for date_repr, date in self.dates.items(): self.assertEqual(identifiers.format_date(date), date_repr) def test_format_date_fail(self): for date in self.broken_dates: with self.assertRaises(ValueError): identifiers.format_date(date) def test_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.MultiHash.from_data(self.content["data"]).digest() def test_content_identifier(self): self.assertEqual(identifiers.content_identifier(self.content), self.content_id) directory_example = { "id": "d7ed3d2c31d608823be58b1cbe57605310615231", "entries": [ { "type": "file", "perms": 33188, "name": b"README", "target": _x("37ec8ea2110c0b7a32fbb0e872f6e7debbf95e21"), }, { "type": "file", "perms": 33188, "name": b"Rakefile", "target": _x("3bb0e8592a41ae3185ee32266c860714980dbed7"), }, { "type": "dir", "perms": 16384, "name": b"app", "target": _x("61e6e867f5d7ba3b40540869bc050b0c4fed9e95"), }, { "type": "file", "perms": 33188, "name": b"1.megabyte", "target": _x("7c2b2fbdd57d6765cdc9d84c2d7d333f11be7fb3"), }, { "type": "dir", "perms": 16384, "name": b"config", "target": _x("591dfe784a2e9ccc63aaba1cb68a765734310d98"), }, { "type": "dir", "perms": 16384, "name": b"public", "target": _x("9588bf4522c2b4648bfd1c61d175d1f88c1ad4a5"), }, { "type": "file", "perms": 33188, "name": b"development.sqlite3", "target": _x("e69de29bb2d1d6434b8b29ae775ad8c2e48c5391"), }, { "type": "dir", "perms": 16384, "name": b"doc", "target": _x("154705c6aa1c8ead8c99c7915373e3c44012057f"), }, { "type": "dir", "perms": 16384, "name": b"db", "target": _x("85f157bdc39356b7bc7de9d0099b4ced8b3b382c"), }, { "type": "dir", "perms": 16384, "name": b"log", "target": _x("5e3d3941c51cce73352dff89c805a304ba96fffe"), }, { "type": "dir", "perms": 16384, "name": b"script", "target": _x("1b278423caf176da3f3533592012502aa10f566c"), }, { "type": "dir", "perms": 16384, "name": b"test", "target": _x("035f0437c080bfd8711670b3e8677e686c69c763"), }, { "type": "dir", "perms": 16384, "name": b"vendor", "target": _x("7c0dc9ad978c1af3f9a4ce061e50f5918bd27138"), }, { "type": "rev", "perms": 57344, "name": b"will_paginate", "target": _x("3d531e169db92a16a9a8974f0ae6edf52e52659e"), }, # in git order, the dir named "order" should be between the files # named "order." and "order0" { "type": "dir", "perms": 16384, "name": b"order", "target": _x("62cdb7020ff920e5aa642c3d4066950dd1f01f4d"), }, { "type": "file", "perms": 16384, "name": b"order.", "target": _x("0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33"), }, { "type": "file", "perms": 16384, "name": b"order0", "target": _x("bbe960a25ea311d21d40669e93df2003ba9b90a2"), }, ], } class DirectoryIdentifier(unittest.TestCase): def setUp(self): self.directory = directory_example self.empty_directory = { "id": "4b825dc642cb6eb9a060e54bf8d69288fbee4904", "entries": [], } def test_dir_identifier(self): self.assertEqual( identifiers.directory_identifier(self.directory), self.directory["id"] ) def test_dir_identifier_entry_order(self): # Reverse order of entries, check the id is still the same. directory = {"entries": reversed(self.directory["entries"])} self.assertEqual( identifiers.directory_identifier(directory), self.directory["id"] ) def test_dir_identifier_empty_directory(self): self.assertEqual( identifiers.directory_identifier(self.empty_directory), self.empty_directory["id"], ) linus_tz = datetime.timezone(datetime.timedelta(minutes=-420)) revision_example = { "id": "bc0195aad0daa2ad5b0d76cce22b167bc3435590", "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("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", "type": "git", "synthetic": False, } class RevisionIdentifier(unittest.TestCase): def setUp(self): 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 = revision_example self.revision_none_metadata = { "id": "bc0195aad0daa2ad5b0d76cce22b167bc3435590", "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("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": {"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": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("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", "extra_headers": ( (b"svn-repo-uuid", b"046f1af7-66c2-d61b-5410-ce57b7db7bff"), (b"svn-revision", b"10"), ), } self.revision_with_gpgsig = { "id": "44cc742a8ca17b9c279be4cc195a93a6ef7a320e", "directory": _x("b134f9b7dc434f593c0bab696345548b37de0558"), "parents": [ _x("689664ae944b4692724f13b709a4e4de28b54e57"), _x("c888305e1efbaa252d01b4e5e6b778f865a97514"), ], "author": { "name": b"Jiang Xin", "email": b"worldhello.net@gmail.com", "fullname": b"Jiang Xin ", }, "date": {"timestamp": 1428538899, "offset": 480,}, "committer": {"name": b"Jiang Xin", "email": b"worldhello.net@gmail.com",}, "committer_date": {"timestamp": 1428538899, "offset": 480,}, "extra_headers": ((b"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": _x("b134f9b7dc434f593c0bab696345548b37de0558"), "parents": [ _x("689664ae944b4692724f13b709a4e4de28b54e57"), _x("c888305e1efbaa252d01b4e5e6b778f865a97514"), ], "author": { "name": b"Jiang Xin", "email": b"worldhello.net@gmail.com", "fullname": b"Jiang Xin ", }, "date": {"timestamp": 1428538899, "offset": 480,}, "committer": {"name": b"Jiang Xin", "email": b"worldhello.net@gmail.com",}, "committer_date": {"timestamp": 1428538899, "offset": 480,}, "message": None, } self.revision_empty_message = { "id": "7442cd78bd3b4966921d6a7f7447417b7acb15eb", "directory": _x("b134f9b7dc434f593c0bab696345548b37de0558"), "parents": [ _x("689664ae944b4692724f13b709a4e4de28b54e57"), _x("c888305e1efbaa252d01b4e5e6b778f865a97514"), ], "author": { "name": b"Jiang Xin", "email": b"worldhello.net@gmail.com", "fullname": b"Jiang Xin ", }, "date": {"timestamp": 1428538899, "offset": 480,}, "committer": {"name": b"Jiang Xin", "email": b"worldhello.net@gmail.com",}, "committer_date": {"timestamp": 1428538899, "offset": 480,}, "message": b"", } self.revision_only_fullname = { "id": "010d34f384fa99d047cdd5e2f41e56e5c2feee45", "directory": _x("85a74718d377195e1efd0843ba4f3260bad4fe07"), "parents": [_x("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", "extra_headers": ( (b"svn-repo-uuid", b"046f1af7-66c2-d61b-5410-ce57b7db7bff"), (b"svn-revision", b"10"), ), } def test_revision_identifier(self): self.assertEqual( identifiers.revision_identifier(self.revision), identifiers.identifier_to_str(self.revision["id"]), ) def test_revision_identifier_none_metadata(self): self.assertEqual( identifiers.revision_identifier(self.revision_none_metadata), identifiers.identifier_to_str(self.revision_none_metadata["id"]), ) def test_revision_identifier_synthetic(self): self.assertEqual( identifiers.revision_identifier(self.synthetic_revision), identifiers.identifier_to_str(self.synthetic_revision["id"]), ) def test_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"]), ) def test_revision_identifier_with_gpgsig(self): self.assertEqual( identifiers.revision_identifier(self.revision_with_gpgsig), identifiers.identifier_to_str(self.revision_with_gpgsig["id"]), ) def test_revision_identifier_no_message(self): self.assertEqual( identifiers.revision_identifier(self.revision_no_message), identifiers.identifier_to_str(self.revision_no_message["id"]), ) def test_revision_identifier_empty_message(self): self.assertEqual( identifiers.revision_identifier(self.revision_empty_message), identifiers.identifier_to_str(self.revision_empty_message["id"]), ) def test_revision_identifier_only_fullname(self): self.assertEqual( identifiers.revision_identifier(self.revision_only_fullname), identifiers.identifier_to_str(self.revision_only_fullname["id"]), ) release_example = { "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", "fullname": b"Linus Torvalds ", }, "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, } class ReleaseIdentifier(unittest.TestCase): def setUp(self): linus_tz = datetime.timezone(datetime.timedelta(minutes=-420)) self.release = release_example 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": {"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", } self.release_newline_in_author = { "author": { "email": b"esycat@gmail.com", "fullname": b"Eugene Janusov\n", "name": b"Eugene Janusov\n", }, "date": { "negative_utc": None, "offset": 600, "timestamp": {"microseconds": 0, "seconds": 1377480558,}, }, "id": b"\\\x98\xf5Y\xd04\x16-\xe2->\xbe\xb9T3\xe6\xf8\x88R1", "message": b"Release of v0.3.2.", "name": b"0.3.2", "synthetic": False, "target": (b"\xc0j\xa3\xd9;x\xa2\x86\\I5\x17" b"\x000\xf8\xc2\xd79o\xd3"), "target_type": "revision", } self.release_snapshot_target = dict(self.release) self.release_snapshot_target["target_type"] = "snapshot" self.release_snapshot_target["id"] = "c29c3ddcc6769a04e54dd69d63a6fdcbc566f850" def test_release_identifier(self): self.assertEqual( identifiers.release_identifier(self.release), identifiers.identifier_to_str(self.release["id"]), ) def test_release_identifier_no_author(self): self.assertEqual( identifiers.release_identifier(self.release_no_author), identifiers.identifier_to_str(self.release_no_author["id"]), ) def test_release_identifier_no_message(self): self.assertEqual( identifiers.release_identifier(self.release_no_message), identifiers.identifier_to_str(self.release_no_message["id"]), ) def test_release_identifier_empty_message(self): self.assertEqual( identifiers.release_identifier(self.release_empty_message), identifiers.identifier_to_str(self.release_empty_message["id"]), ) def test_release_identifier_negative_utc(self): self.assertEqual( identifiers.release_identifier(self.release_negative_utc), identifiers.identifier_to_str(self.release_negative_utc["id"]), ) def test_release_identifier_newline_in_author(self): self.assertEqual( identifiers.release_identifier(self.release_newline_in_author), identifiers.identifier_to_str(self.release_newline_in_author["id"]), ) def test_release_identifier_snapshot_target(self): self.assertEqual( identifiers.release_identifier(self.release_snapshot_target), identifiers.identifier_to_str(self.release_snapshot_target["id"]), ) snapshot_example = { "id": _x("6e65b86363953b780d92b0a928f3e8fcdd10db36"), "branches": { b"directory": { "target": _x("1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8"), "target_type": "directory", }, b"content": { "target": _x("fe95a46679d128ff167b7c55df5d02356c5a1ae1"), "target_type": "content", }, b"alias": {"target": b"revision", "target_type": "alias",}, b"revision": { "target": _x("aafb16d69fd30ff58afdd69036a26047f3aebdc6"), "target_type": "revision", }, b"release": { "target": _x("7045404f3d1c54e6473c71bbb716529fbad4be24"), "target_type": "release", }, b"snapshot": { "target": _x("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), "target_type": "snapshot", }, b"dangling": None, }, } class SnapshotIdentifier(unittest.TestCase): def setUp(self): super().setUp() self.empty = { "id": "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e", "branches": {}, } self.dangling_branch = { "id": "c84502e821eb21ed84e9fd3ec40973abc8b32353", "branches": {b"HEAD": None,}, } self.unresolved = { "id": "84b4548ea486e4b0a7933fa541ff1503a0afe1e0", "branches": {b"foo": {"target": b"bar", "target_type": "alias",},}, } self.all_types = snapshot_example def test_empty_snapshot(self): self.assertEqual( identifiers.snapshot_identifier(self.empty), identifiers.identifier_to_str(self.empty["id"]), ) def test_dangling_branch(self): self.assertEqual( identifiers.snapshot_identifier(self.dangling_branch), identifiers.identifier_to_str(self.dangling_branch["id"]), ) def test_unresolved(self): with self.assertRaisesRegex(ValueError, "b'foo' -> b'bar'"): identifiers.snapshot_identifier(self.unresolved) def test_unresolved_force(self): self.assertEqual( identifiers.snapshot_identifier(self.unresolved, ignore_unresolved=True,), identifiers.identifier_to_str(self.unresolved["id"]), ) def test_all_types(self): self.assertEqual( identifiers.snapshot_identifier(self.all_types), identifiers.identifier_to_str(self.all_types["id"]), ) def test_swhid(self): _snapshot_id = _x("c7c108084bc0bf3d81436bf980b46e98bd338453") _release_id = "22ece559cc7cc2364edc5e5593d63ae8bd229f9f" _revision_id = "309cf2674ee7a0749978cf8265ab91a60aea0f7d" _directory_id = "d198bc9d7a6bcf6db04f476d29314f157507d505" _content_id = "94a9ed024d3859793618152ea559a168bbcbb5e2" _snapshot = {"id": _snapshot_id} _release = {"id": _release_id} _revision = {"id": _revision_id} _directory = {"id": _directory_id} _content = {"sha1_git": _content_id} for full_type, _hash, expected_swhid, version, _meta in [ ( SNAPSHOT, _snapshot_id, "swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453", None, {}, ), ( RELEASE, _release_id, "swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f", 1, {}, ), ( REVISION, _revision_id, "swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d", None, {}, ), ( DIRECTORY, _directory_id, "swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505", None, {}, ), ( CONTENT, _content_id, "swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2", 1, {}, ), ( SNAPSHOT, _snapshot, "swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453", None, {}, ), ( RELEASE, _release, "swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f", 1, {}, ), ( REVISION, _revision, "swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d", None, {}, ), ( DIRECTORY, _directory, "swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505", None, {}, ), ( CONTENT, _content, "swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2", 1, {}, ), ( CONTENT, _content, "swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2;origin=1", 1, {"origin": "1"}, ), ]: if version: actual_value = identifiers.swhid( full_type, _hash, version, metadata=_meta ) else: actual_value = identifiers.swhid(full_type, _hash, metadata=_meta) self.assertEqual(actual_value, expected_swhid) def test_swhid_wrong_input(self): _snapshot_id = "notahash4bc0bf3d81436bf980b46e98bd338453" _snapshot = {"id": _snapshot_id} for _type, _hash in [ (SNAPSHOT, _snapshot_id), (SNAPSHOT, _snapshot), ("foo", ""), ]: with self.assertRaises(ValidationError): identifiers.swhid(_type, _hash) def test_parse_swhid(self): for swhid, _type, _version, _hash in [ ( "swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2", CONTENT, 1, "94a9ed024d3859793618152ea559a168bbcbb5e2", ), ( "swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505", DIRECTORY, 1, "d198bc9d7a6bcf6db04f476d29314f157507d505", ), ( "swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d", REVISION, 1, "309cf2674ee7a0749978cf8265ab91a60aea0f7d", ), ( "swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f", RELEASE, 1, "22ece559cc7cc2364edc5e5593d63ae8bd229f9f", ), ( "swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453", SNAPSHOT, 1, "c7c108084bc0bf3d81436bf980b46e98bd338453", ), ]: expected_result = SWHID( namespace="swh", scheme_version=_version, object_type=_type, object_id=_hash, metadata={}, ) actual_result = identifiers.parse_swhid(swhid) self.assertEqual(actual_result, expected_result) for swhid, _type, _version, _hash, _metadata in [ ( "swh:1:cnt:9c95815d9e9d91b8dae8e05d8bbc696fe19f796b;lines=1-18;origin=https://github.com/python/cpython", # noqa CONTENT, 1, "9c95815d9e9d91b8dae8e05d8bbc696fe19f796b", {"lines": "1-18", "origin": "https://github.com/python/cpython"}, ), ( "swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;origin=deb://Debian/packages/linuxdoc-tools", # noqa DIRECTORY, 1, "0b6959356d30f1a4e9b7f6bca59b9a336464c03d", {"origin": "deb://Debian/packages/linuxdoc-tools"}, ), ]: expected_result = SWHID( namespace="swh", scheme_version=_version, object_type=_type, object_id=_hash, metadata=_metadata, ) actual_result = identifiers.parse_swhid(swhid) self.assertEqual(actual_result, expected_result) + self.assertEqual( + expected_result.to_dict(), + { + "namespace": "swh", + "scheme_version": _version, + "object_type": _type, + "object_id": _hash, + "metadata": _metadata, + }, + ) def test_parse_swhid_parsing_error(self): for swhid in [ ("swh:1:cnt"), ("swh:1:"), ("swh:"), ("swh:1:cnt:"), ("foo:1:cnt:abc8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh:2:dir:def8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh:1:foo:fed8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh:1:dir:0b6959356d30f1a4e9b7f6bca59b9a336464c03d;invalid;" "malformed"), ("swh:1:snp:gh6959356d30f1a4e9b7f6bca59b9a336464c03d"), ("swh:1:snp:foo"), ]: with self.assertRaises(ValidationError): identifiers.parse_swhid(swhid) def test_persistentid_class_validation_error(self): for _ns, _version, _type, _id in [ ("foo", 1, CONTENT, "abc8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh", 2, DIRECTORY, "def8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh", 1, "foo", "fed8bc9d7a6bcf6db04f476d29314f157507d505"), ("swh", 1, SNAPSHOT, "gh6959356d30f1a4e9b7f6bca59b9a336464c03d"), ]: with self.assertRaises(ValidationError): SWHID( namespace=_ns, scheme_version=_version, object_type=_type, object_id=_id, ) class OriginIdentifier(unittest.TestCase): def setUp(self): self.origin = { "url": "https://github.com/torvalds/linux", } def test_content_identifier(self): self.assertEqual( identifiers.origin_identifier(self.origin), "b63a575fe3faab7692c9f38fb09d4bb45651bb0f", ) TS_DICTS = [ ( {"timestamp": 12345, "offset": 0}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": False}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": False}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": None}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": {"seconds": 12345}, "offset": 0, "negative_utc": None}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": None, }, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ( { "timestamp": {"seconds": 12345, "microseconds": 100}, "offset": 0, "negative_utc": None, }, { "timestamp": {"seconds": 12345, "microseconds": 100}, "offset": 0, "negative_utc": False, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": True}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": True, }, ), ( {"timestamp": 12345, "offset": 0, "negative_utc": None}, { "timestamp": {"seconds": 12345, "microseconds": 0}, "offset": 0, "negative_utc": False, }, ), ] @pytest.mark.parametrize("dict_input,expected", TS_DICTS) def test_normalize_timestamp_dict(dict_input, expected): assert normalize_timestamp(dict_input) == expected TS_DICTS_INVALID_TIMESTAMP = [ {"timestamp": 1.2, "offset": 0}, {"timestamp": "1", "offset": 0}, # these below should really also trigger a ValueError... # {"timestamp": {"seconds": "1"}, "offset": 0}, # {"timestamp": {"seconds": 1.2}, "offset": 0}, # {"timestamp": {"seconds": 1.2}, "offset": 0}, ] @pytest.mark.parametrize("dict_input", TS_DICTS_INVALID_TIMESTAMP) def test_normalize_timestamp_dict_invalid_timestamp(dict_input): with pytest.raises(ValueError, match="non-integer timestamp"): normalize_timestamp(dict_input)