Add an ExtID object

this object aims at being able to keep in the SWH Archive an
  SWHID <-> External object ID
map, e.g. to be able to keep track of Mercurial ids so the Mercurial
loader can be made more efficient.

Related to T2849.

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:

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)

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,
@@ -1096,3 +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()))

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,