fix(hashalgo): Use same aliases as Ort Kotlin upstream

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "python-ort"
-version = "0.4.0"
+version = "0.4.1"
 description = "A Python Ort model serialization library"
 readme = "README.md"
 license = "MIT"

src/ort/models/hash_algorithm.py

@@ -1,37 +1,116 @@
 # SPDX-FileCopyrightText: 2025 Helio Chissini de Castro <heliocastro@gmail.com>
-#
 # SPDX-License-Identifier: MIT
 
+from typing import ClassVar
 
-from enum import Enum
+from pydantic import BaseModel, Field, model_validator
 
 
-class HashAlgorithm(Enum):
+class HashAlgorithm(BaseModel):
     """
-    An enum of supported hash algorithms. Each algorithm has one or more [aliases] associated to it,
-    where the first alias is the definite name.
-
-    Attributes:
-        NONE: No hash algorithm.
-        UNKNOWN: An unknown hash algorithm.
-        MD5: The Message-Digest 5 hash algorithm, see [MD5](http://en.wikipedia.org/wiki/MD5).
-        SHA1: The Secure Hash Algorithm 1, see [SHA-1](https://en.wikipedia.org/wiki/SHA-1).
-        SHA256: The Secure Hash Algorithm 2 with 256 bits, see [SHA-256](https://en.wikipedia.org/wiki/SHA-256).
-        SHA384: The Secure Hash Algorithm 2 with 384 bits, see [SHA-384](https://en.wikipedia.org/wiki/SHA-384).
-        SHA512: The Secure Hash Algorithm 2 with 512 bits, see [SHA-512](https://en.wikipedia.org/wiki/SHA-512).
-        SHA1GIT: The Secure Hash Algorithm 1, but calculated on a Git "blob" object, see
-            - https://git-scm.com/book/en/v2/Git-Internals-Git-Objects#_object_storage
-            - https://docs.softwareheritage.org/devel/swh-model/persistent-identifiers.html#git-compatibility
+    A Python port of the Kotlin HashAlgorithm enum class.
+
+    Each algorithm has one or more aliases, an empty hash value,
+    and an 'is_verifiable' flag.
     """
 
-    NONE = "NONE"
-    UNKNOWN = "UNKNOWN"
-    MD5 = "MD5"
-    SHA1 = "SHA1"
-    SHA256 = "SHA256"
-    SHA384 = "SHA384"
-    SHA512 = "SHA512"
-    SHA1GIT = (
-        ["SHA-1-GIT", "SHA1-GIT", "SHA1GIT", "SWHID"],
-        "e69de29bb2d1d6434b8b29ae775ad8c2e48c5391",
-    )
+    aliases: list[str] = Field(default_factory=list)
+    empty_value: str = ""
+    is_verifiable: bool = True
+
+    # ---- known algorithms ----
+    NONE: ClassVar["HashAlgorithm"]
+    UNKNOWN: ClassVar["HashAlgorithm"]
+    MD5: ClassVar["HashAlgorithm"]
+    SHA1: ClassVar["HashAlgorithm"]
+    SHA256: ClassVar["HashAlgorithm"]
+    SHA384: ClassVar["HashAlgorithm"]
+    SHA512: ClassVar["HashAlgorithm"]
+    SHA1GIT: ClassVar["HashAlgorithm"]
+
+    # ---- derived property ----
+    @property
+    def size(self) -> int:
+        """The length of the empty hash string for this algorithm."""
+        return len(self.empty_value)
+
+    # ---- validation ----
+    @model_validator(mode="before")
+    @classmethod
+    def _from_alias(cls, value):
+        """Allow initialization from alias string."""
+        if isinstance(value, str):
+            algo = cls.from_string(value)
+            return algo.model_dump()
+        return value
+
+    # ---- class methods ----
+    @classmethod
+    def from_string(cls, alias: str) -> "HashAlgorithm":
+        """Find a HashAlgorithm by alias name (case-insensitive)."""
+        alias_upper = alias.upper()
+        for algo in cls._entries():
+            if any(a.upper() == alias_upper for a in algo.aliases):
+                return algo
+        return cls.UNKNOWN
+
+    @classmethod
+    def create(cls, value: str) -> "HashAlgorithm":
+        """
+        Create a HashAlgorithm from a hash value string, based on its length.
+        Returns NONE if value is blank, UNKNOWN otherwise.
+        """
+        if not value.strip():
+            return cls.NONE
+        for algo in cls._entries():
+            if len(value) == algo.size:
+                return algo
+        return cls.UNKNOWN
+
+    @classmethod
+    def _entries(cls) -> list["HashAlgorithm"]:
+        """Return the list of all defined algorithms."""
+        return [
+            cls.NONE,
+            cls.UNKNOWN,
+            cls.MD5,
+            cls.SHA1,
+            cls.SHA256,
+            cls.SHA384,
+            cls.SHA512,
+            cls.SHA1GIT,
+        ]
+
+    def __str__(self) -> str:
+        return self.aliases[0] if self.aliases else ""
+
+
+HashAlgorithm.NONE = HashAlgorithm(aliases=[""], empty_value="", is_verifiable=False)
+HashAlgorithm.UNKNOWN = HashAlgorithm(aliases=["UNKNOWN"], empty_value="", is_verifiable=False)
+HashAlgorithm.MD5 = HashAlgorithm(
+    aliases=["MD5"],
+    empty_value="d41d8cd98f00b204e9800998ecf8427e",
+)
+HashAlgorithm.SHA1 = HashAlgorithm(
+    aliases=["SHA-1", "SHA1"],
+    empty_value="da39a3ee5e6b4b0d3255bfef95601890afd80709",
+)
+HashAlgorithm.SHA256 = HashAlgorithm(
+    aliases=["SHA-256", "SHA256"],
+    empty_value="e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+)
+HashAlgorithm.SHA384 = HashAlgorithm(
+    aliases=["SHA-384", "SHA384"],
+    empty_value=("38b060a751ac96384cd9327eb1b1e36a21fdb71114be07434c0cc7bf63f6e1da274edebfe76f65fbd51ad2f14898b95b"),
+)
+HashAlgorithm.SHA512 = HashAlgorithm(
+    aliases=["SHA-512", "SHA512"],
+    empty_value=(
+        "cf83e1357eefb8bdf1542850d66d8007d620e4050b5715dc83f4a921d36ce9ce"
+        "47d0d13c5d85f2b0ff8318d2877eec2f63b931bd47417a81a538327af927da3e"
+    ),
+)
+HashAlgorithm.SHA1GIT = HashAlgorithm(
+    aliases=["SHA-1-GIT", "SHA1-GIT", "SHA1GIT", "SWHID"],
+    empty_value="e69de29bb2d1d6434b8b29ae775ad8c2e48c5391",
+)

tests/data/example_curations.yml

@@ -31,7 +31,7 @@
   curations:
     comment: 'Repository moved to https://gitlab.ow2.org.'
     vcs:
-      type: 'Giot'
+      type: 'Git'
       url: 'https://gitlab.ow2.org/asm/asm.git'
 
 - id: 'NPM::ast-traverse:0.1.0'

tests/data/example_simple_curation.yml

@@ -1,33 +1,33 @@
-- id: "Maven:com.example.app:example:0.0.1"
+- id: 'Maven:com.example.app:example:0.0.1'
   curations:
-    comment: "An explanation why the curation is needed or the reasoning for a license conclusion"
-    purl: "pkg:Maven/com.example.app/example@0.0.1?arch=arm64-v8a#src/main"
+    comment: 'An explanation why the curation is needed or the reasoning for a license conclusion'
+    purl: 'pkg:Maven/com.example.app/example@0.0.1?arch=arm64-v8a#src/main'
     authors:
-    - "Name of one author"
-    - "Name of another author"
-    cpe: "cpe:2.3:a:example-org:example-package:0.0.1:*:*:*:*:*:*:*"
-    concluded_license: "Valid SPDX license expression to override the license findings."
+      - 'Name of one author'
+      - 'Name of another author'
+    cpe: 'cpe:2.3:a:example-org:example-package:0.0.1:*:*:*:*:*:*:*'
+    concluded_license: 'Valid SPDX license expression to override the license findings.'
     declared_license_mapping:
-      "license a": "Apache-2.0"
-    description: "Curated description."
-    homepage_url: "http://example.com"
+      'license a': 'Apache-2.0'
+    description: 'Curated description.'
+    homepage_url: 'http://example.com'
     binary_artifact:
-      url: "http://example.com/binary.zip"
+      url: 'http://example.com/binary.zip'
       hash:
-        value: "ddce269a1e3d054cae349621c198dd52"
-        algorithm: "MD5"
+        value: 'e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855'
+        algorithm: 'SHA256'
     source_artifact:
-      url: "http://example.com/sources.zip"
+      url: 'http://example.com/sources.zip'
       hash:
-        value: "ddce269a1e3d054cae349621c198dd52"
-        algorithm: "MD5"
+        value: 'e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855'
+        algorithm: 'SHA-256'
     vcs:
-      type: "Git"
-      url: "http://example.com/repo.git"
-      revision: "1234abc"
-      path: "subdirectory"
+      type: 'Git'
+      url: 'http://example.com/repo.git'
+      revision: '1234abc'
+      path: 'subdirectory'
     is_metadata_only: true
     is_modified: true
     source_code_origins: [ARTIFACT, VCS]
     labels:
-      my-key: "my-value"
+      my-key: 'my-value'