diff --git a/PKG-INFO b/PKG-INFO
index f75cd2d814b892d329431a068cc4b69bb83c5d34..3f04287e2c1bb13d17d1ec6385cde12aa43133bd 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: swh.model
-Version: 2.0.0
+Version: 2.1.0
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/swh.model.egg-info/PKG-INFO b/swh.model.egg-info/PKG-INFO
index f75cd2d814b892d329431a068cc4b69bb83c5d34..3f04287e2c1bb13d17d1ec6385cde12aa43133bd 100644
--- a/swh.model.egg-info/PKG-INFO
+++ b/swh.model.egg-info/PKG-INFO
@@ -1,6 +1,6 @@
Metadata-Version: 2.1
Name: swh.model
-Version: 2.0.0
+Version: 2.1.0
Summary: Software Heritage data model
Home-page: https://forge.softwareheritage.org/diffusion/DMOD/
Author: Software Heritage developers
diff --git a/swh/model/hashutil.py b/swh/model/hashutil.py
index 908b736bd1d09b842c951ca9f0240774a0814a52..e332c23bc885e887c104387418cbc4af7e0b296a 100644
--- a/swh/model/hashutil.py
+++ b/swh/model/hashutil.py
@@ -296,6 +296,7 @@ def hash_git_data(data, git_type, base_algo="sha1"):
"tag",
"snapshot",
"raw_extrinsic_metadata",
+ "extid",
}
if git_type not in git_object_types:
diff --git a/swh/model/identifiers.py b/swh/model/identifiers.py
index 434f3c815becb09e19e57f1e2e95f8398bbc330a..c9f20dcb7b52b83dbd13f42a633822f87c961222 100644
--- a/swh/model/identifiers.py
+++ b/swh/model/identifiers.py
@@ -823,6 +823,37 @@ def raw_extrinsic_metadata_identifier(metadata: Dict[str, Any]) -> str:
)
+def extid_identifier(extid: Dict[str, Any]) -> str:
+ """Return the intrinsic identifier for an ExtID object.
+
+ An ExtID identifier is a salted sha1 (using the git hashing algorithm with
+ the ``extid`` object type) of a manifest following the format:
+
+ ```
+ extid_type $StrWithoutSpaces
+ extid $Bytes
+ target $CoreSwhid
+ ```
+
+ $StrWithoutSpaces is an ASCII string, and may not contain spaces.
+
+ Newlines in $Bytes are escaped as with other git fields, ie. by adding a
+ space after them.
+
+ Returns:
+ str: the intrinsic identifier for `extid`
+
+ """
+
+ headers = [
+ (b"extid_type", extid["extid_type"].encode("ascii")),
+ (b"extid", extid["extid"]),
+ (b"target", str(extid["target"]).encode("ascii")),
+ ]
+
+ return identifier_to_str(hash_manifest("extid", headers))
+
+
# type of the "object_type" attribute of the SWHID class; either
# ObjectType or ExtendedObjectType
_TObjectType = TypeVar("_TObjectType", ObjectType, ExtendedObjectType)
diff --git a/swh/model/model.py b/swh/model/model.py
index 6df310a0f35ce769ccf21305814691c514b662f9..da0547186bc54cbeb30df7570e8bb1c3a44cb3f8 100644
--- a/swh/model/model.py
+++ b/swh/model/model.py
@@ -19,6 +19,7 @@ from .collections import ImmutableDict
from .hashutil import DEFAULT_ALGORITHMS, MultiHash, hash_to_bytes
from .identifiers import (
directory_identifier,
+ extid_identifier,
normalize_timestamp,
origin_identifier,
raw_extrinsic_metadata_identifier,
@@ -848,7 +849,10 @@ class MetadataAuthority(BaseModel):
@classmethod
def from_dict(cls, d):
- d["type"] = MetadataAuthorityType(d["type"])
+ d = {
+ **d,
+ "type": MetadataAuthorityType(d["type"]),
+ }
return super().from_dict(d)
def unique_key(self) -> KeyType:
@@ -1093,3 +1097,25 @@ class RawExtrinsicMetadata(HashableObject, BaseModel):
d[swhid_key] = CoreSWHID.from_string(d[swhid_key])
return super().from_dict(d)
+
+
+@attr.s(frozen=True, slots=True)
+class ExtID(HashableObject, BaseModel):
+ object_type: Final = "extid"
+
+ extid_type = attr.ib(type=str, validator=type_validator())
+ extid = attr.ib(type=bytes, validator=type_validator())
+ target = attr.ib(type=CoreSWHID, validator=type_validator())
+
+ id = attr.ib(type=Sha1Git, validator=type_validator(), default=b"")
+
+ @classmethod
+ def from_dict(cls, d):
+ return cls(
+ extid=d["extid"],
+ extid_type=d["extid_type"],
+ target=CoreSWHID.from_string(d["target"]),
+ )
+
+ def compute_hash(self) -> bytes:
+ return hash_to_bytes(extid_identifier(self.to_dict()))
diff --git a/swh/model/tests/swh_model_data.py b/swh/model/tests/swh_model_data.py
index ae6f9635e8013ead488c5d489772751dabc5e458..c4700cba3475382deffb45160cbdf8a88dfb0176 100644
--- a/swh/model/tests/swh_model_data.py
+++ b/swh/model/tests/swh_model_data.py
@@ -15,6 +15,7 @@ from swh.model.model import (
Content,
Directory,
DirectoryEntry,
+ ExtID,
MetadataAuthority,
MetadataAuthorityType,
MetadataFetcher,
@@ -131,6 +132,11 @@ REVISIONS = [
),
]
+EXTIDS = [
+ ExtID(extid_type="git256", extid=b"\x03" * 32, target=REVISIONS[0].swhid(),),
+ ExtID(extid_type="hg", extid=b"\x04" * 20, target=REVISIONS[1].swhid(),),
+]
+
RELEASES = [
Release(
id=hash_to_bytes("8059dc4e17fcd0e51ca3bcd6b80f4577d281fd08"),
@@ -330,6 +336,7 @@ RAW_EXTRINSIC_METADATA = [
TEST_OBJECTS: Dict[str, Sequence[BaseModel]] = {
"content": CONTENTS,
"directory": DIRECTORIES,
+ "extid": EXTIDS,
"metadata_authority": METADATA_AUTHORITIES,
"metadata_fetcher": METADATA_FETCHERS,
"origin": ORIGINS,
diff --git a/swh/model/tests/test_model.py b/swh/model/tests/test_model.py
index 2c84d714e882fc76e024d78fdf1e5443a33f190c..bf9725c628c337b8d701ad73ee7b39dba25d060e 100644
--- a/swh/model/tests/test_model.py
+++ b/swh/model/tests/test_model.py
@@ -45,6 +45,7 @@ from swh.model.model import (
Timestamp,
TimestampWithTimezone,
)
+from swh.model.tests.swh_model_data import TEST_OBJECTS
from swh.model.tests.test_identifiers import (
content_example,
directory_example,
@@ -78,6 +79,17 @@ def test_todict_inverse_fromdict(objtype_and_obj):
assert obj_as_dict == type(obj).from_dict(obj_as_dict).to_dict()
+@pytest.mark.parametrize("object_type, objects", TEST_OBJECTS.items())
+def test_swh_model_todict_fromdict(object_type, objects):
+ """checks model objects in swh_model_data are in correct shape"""
+ assert objects
+ for obj in objects:
+ # Check the composition of from_dict and to_dict is the identity
+ obj_as_dict = obj.to_dict()
+ assert obj == type(obj).from_dict(obj_as_dict)
+ assert obj_as_dict == type(obj).from_dict(obj_as_dict).to_dict()
+
+
def test_unique_key():
url = "http://example.org/"
date = datetime.datetime.now(tz=datetime.timezone.utc)