feat(curations): Minor fix and tests (heliocastro#12)

Author: heliocastro

.github/workflows/build.yml

@@ -46,6 +46,3 @@ jobs:
         shell: bash
         run: |
           uv build
-
-      - name: Test with python ${{ matrix.python-version }}
-        run: uv run --frozen pytest

.github/workflows/testing.yml

@@ -0,0 +1,28 @@
+name: pytest
+
+on: [pull_request, workflow_dispatch]
+
+jobs:
+  test-optima:
+    name: Run python-optima tests
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12', '3.13', '3.14']
+
+    steps:
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+      - uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6.8.0
+        with:
+          enable-cache: true
+
+      - uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install the project
+        run: uv sync --locked --all-extras --dev
+
+      - name: Test with python ${{ matrix.python-version }}
+        run: uv run --frozen pytest

pyproject.toml

@@ -2,12 +2,9 @@
 requires = ["uv_build>=0.8.12,<0.10.0"]
 build-backend = "uv_build"
 
-[tool.hatch.build.targets.wheel]
-packages = ["src/ort"]
-
 [project]
 name = "python-ort"
-version = "0.3.0"
+version = "0.3.1"
 description = "A Python Ort model serialization library"
 readme = "README.md"
 license = "MIT"
@@ -39,6 +36,7 @@ dev = [
     "pycodestyle>=2.14.0",
     "pyrefly>=0.40.0",
     "pytest>=8.4.2",
+    "rich>=14.2.0",
     "ruff>=0.14.4",
     "types-pyyaml>=6.0.12.20250915",
 ]
@@ -47,7 +45,8 @@ dev = [
 addopts = ["--import-mode=importlib"]
 log_cli = true
 log_cli_level = "INFO"
-pythonpath = "src"
+pythonpath = ["src"]
+testpaths = ["tests"]
 
 [tool.pylint.messages_control]
 disable = [

src/ort/models/package_curation_data.py

@@ -7,7 +7,7 @@
 
 from .hash import Hash
 from .source_code_origin import SourceCodeOrigin
-from .vcsinfo import VcsInfo
+from .vcsinfo_curation_data import VcsInfoCurationData
 
 
 class CurationArtifact(BaseModel):
@@ -28,7 +28,7 @@ class PackageCurationData(BaseModel):
     homepage_url: str | None = None
     binary_artifact: CurationArtifact | None = None
     source_artifact: CurationArtifact | None = None
-    vcs: VcsInfo | None = None
+    vcs: VcsInfoCurationData | None = None
     is_metadata_only: bool | None = None
     is_modified: bool | None = None
     declared_license_mapping: dict[str, Any] = Field(default_factory=dict)

src/ort/models/vcsinfo_curation_data.py

@@ -0,0 +1,37 @@
+# SPDX-FileCopyrightText: 2025 Helio Chissini de Castro <heliocastro@gmail.com>
+# SPDX-License-Identifier: MIT
+
+from pydantic import AnyUrl, BaseModel, Field
+
+from .vcstype import VcsType
+
+
+class VcsInfoCurationData(BaseModel):
+    """
+    Bundles general Version Control System information.
+
+    Attributes:
+        type(VcsType): The type of the VCS, for example Git, GitRepo, Mercurial, etc.
+        url(AnyUrl): The URL to the VCS repository.
+        revision(str): The VCS-specific revision (tag, branch, SHA1) that the version of the package maps to.
+        path(str): The path inside the VCS to take into account.
+            If the VCS supports checking out only a subdirectory, only this path is checked out.
+    """
+
+    type: VcsType | None = Field(
+        default=None,
+        description="The type of the VCS, for example Git, GitRepo, Mercurial, etc.",
+    )
+    url: AnyUrl | None = Field(
+        default=None,
+        description="The URL to the VCS repository.",
+    )
+    revision: str | None = Field(
+        default=None,
+        description="The VCS-specific revision (tag, branch, SHA1) that the version of the package maps to.",
+    )
+    path: str | None = Field(
+        default=None,
+        description="The path inside the VCS to take into account."
+        "If the VCS supports checking out only a subdirectory, only this path is checked out.",
+    )

src/ort/models/vcstype.py

@@ -3,6 +3,14 @@
 
 from pydantic import BaseModel, Field, model_validator
 
+# Define known VCS types as constants
+GIT = ["Git", "GitHub", "GitLab"]
+GIT_REPO = ["GitRepo", "git-repo", "repo"]
+MERCURIAL = ["Mercurial", "hg"]
+SUBVERSION = ["Subversion", "svn"]
+
+KNOWN_TYPES = GIT + GIT_REPO + MERCURIAL + SUBVERSION
+
 
 class VcsType(BaseModel):
     """
@@ -12,35 +20,26 @@ class VcsType(BaseModel):
     alias for the string representation.
 
     Attributes:
-        aliases(list[str]): Primary name and aliases
+        name(str): Primary name and aliases
     """
 
-    aliases: list[str] = Field(default_factory=list, description="Primary name and aliases")
-
-    @model_validator(mode="after")
-    def ensure_non_empty(self):
-        """Ensure the aliases list is never empty."""
-        if not self.aliases:
-            self.aliases = [""]
-        return self
-
-    def __str__(self):
-        return self.aliases[0] if self.aliases else ""
+    name: str = Field(default_factory=str)
 
+    @model_validator(mode="before")
     @classmethod
-    def for_name(cls, name: str) -> "VcsType":
-        """Lookup known type by name, or create a new instance."""
-        for t in KNOWN_TYPES:
-            if any(alias.lower() == name.lower() for alias in t.aliases):
-                return t
-        return cls(aliases=[name])
-
-
-# Define known VCS types as constants
-GIT = VcsType(aliases=["Git", "GitHub", "GitLab"])
-GIT_REPO = VcsType(aliases=["GitRepo", "git-repo", "repo"])
-MERCURIAL = VcsType(aliases=["Mercurial", "hg"])
-SUBVERSION = VcsType(aliases=["Subversion", "svn"])
-UNKNOWN = VcsType(aliases=[""])
-
-KNOWN_TYPES = [GIT, GIT_REPO, MERCURIAL, SUBVERSION]
+    def _forName(cls, value):
+        # Allow direct string input (e.g., "Git" or "gitlab")
+        if isinstance(value, str):
+            if any(item.lower() == value.lower() for item in KNOWN_TYPES):
+                return {"name": value}
+            else:
+                # Not a known type → default to empty string
+                return {"name": ""}
+        # Allow dict input or existing model
+        elif isinstance(value, dict):
+            name = value.get("name", "")
+            if any(item.lower() == name.lower() for item in KNOWN_TYPES):
+                return value
+            else:
+                return {"name": ""}
+        return {"name": ""}

tests/data/example_curations.yml

@@ -0,0 +1,89 @@
+---
+# Example for a complete curation object:
+#- id: "Maven:org.hamcrest:hamcrest-core:1.3"
+#  curations:
+#    comment: "An explanation why the curation is needed or the reasoning for a license conclusion."
+#    concluded_license: "Apache-2.0 OR BSD-3-Clause" # Valid SPDX license expression to override the license findings.
+#    declared_license_mapping:
+#      "Copyright (C) 2013, Martin Journois": "NONE"
+#      "BSD": "BSD-3-Clause"
+#    description: "Curated description."
+#    homepage_url: "http://example.com"
+#    binary_artifact:
+#      url: "http://example.com/binary.zip"
+#      hash:
+#        value: "ddce269a1e3d054cae349621c198dd52"
+#        algorithm: "MD5"
+#    source_artifact:
+#      url: "http://example.com/sources.zip"
+#      hash:
+#        value: "ddce269a1e3d054cae349621c198dd52"
+#        algorithm: "MD5"
+#    vcs:
+#      type: "Git"
+#      url: "http://example.com/repo.git"
+#      revision: "1234abc"
+#      path: "subdirectory"
+#    is_metadata_only: true # Whether the package is metadata only.
+#    is_modified: true # Whether the package is modified compared to the original source.
+
+- id: 'Maven:asm:asm' # No version means the curation will be applied to all versions of the package.
+  curations:
+    comment: 'Repository moved to https://gitlab.ow2.org.'
+    vcs:
+      type: 'Giot'
+      url: 'https://gitlab.ow2.org/asm/asm.git'
+
+- id: 'NPM::ast-traverse:0.1.0'
+  curations:
+    comment: 'Revision found by comparing the NPM package with the sources from https://github.com/olov/ast-traverse.'
+    vcs:
+      revision: 'f864d24ba07cde4b79f16999b1c99bfb240a441e'
+
+- id: 'NPM::ast-traverse:0.1.1'
+  curations:
+    comment: 'Revision found by comparing the NPM package with the sources from https://github.com/olov/ast-traverse.'
+    vcs:
+      revision: '73f2b3c319af82fd8e490d40dd89a15951069b0d'
+
+- id: 'NPM::ramda:[0.21.0,0.25.0]' # Ivy-style version matchers are supported.
+  curations:
+    comment: >-
+      The package is licensed under MIT per `LICENSE` and `dist/ramda.js`. The project logo is CC-BY-NC-SA-3.0 but it is
+      not part of the distributed .tar.gz package, see the `README.md` which says:
+      "Ramda logo artwork © 2014 J. C. Phillipps. Licensed Creative Commons CC BY-NC-SA 3.0."
+    concluded_license: 'MIT'
+
+- id: 'Maven:org.jetbrains.kotlin:kotlin-bom'
+  curations:
+    comment: 'The package is a Maven BOM file and thus is metadata only.'
+    is_metadata_only: true
+
+- id: 'PyPI::pyramid-workflow:1.0.0'
+  curations:
+    comment: 'The package has an unmappable declared license entry.'
+    declared_license_mapping:
+      'BSD-derived (http://www.repoze.org/LICENSE.txt)': 'LicenseRef-scancode-repoze'
+
+- id: 'PyPI::branca'
+  curations:
+    comment: 'A copyright statement was used to declare the license.'
+    declared_license_mapping:
+      'Copyright (C) 2013, Martin Journois': 'NONE'
+
+- id: 'Maven:androidx.collection:collection:'
+  curations:
+    comment: 'Scan the source artifact, because the VCS revision and path are hard to figure out.'
+    source_code_origins: [ARTIFACT]
+
+- id: 'Maven:androidx.collection:collection:'
+  curations:
+    comment: 'Specify the platform for use within policy rules.'
+    labels:
+      platform: 'android'
+
+- id: 'NPM:@types:mime-types:2.1.0'
+  curations:
+    comment: 'Retrieve the vulnerabilities from Black Duck by the provided origin-id instead of by the purl.'
+    labels:
+      black-duck:origin-id: 'npmjs:@types/mime-types/2.1.0'

tests/data/example_simple_curation.yml

@@ -0,0 +1,33 @@
+- 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"
+    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."
+    declared_license_mapping:
+      "license a": "Apache-2.0"
+    description: "Curated description."
+    homepage_url: "http://example.com"
+    binary_artifact:
+      url: "http://example.com/binary.zip"
+      hash:
+        value: "ddce269a1e3d054cae349621c198dd52"
+        algorithm: "MD5"
+    source_artifact:
+      url: "http://example.com/sources.zip"
+      hash:
+        value: "ddce269a1e3d054cae349621c198dd52"
+        algorithm: "MD5"
+    vcs:
+      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"

tests/test_ort_repository_configuration.py

@@ -2,42 +2,30 @@
 # SPDX-License-Identifier: MIT
 
 from pathlib import Path
-from typing import Any
 
 import pytest
-import yaml
 
 from ort.models.repository_configuration import (
     OrtRepositoryConfiguration,
     OrtRepositoryConfigurationIncludes,
     OrtRepositoryConfigurationIncludesPath,
     PathIncludeReason,
 )
+from tests.utils.load_yaml_config import load_yaml_config  # type: ignore
 
 REPO_CONFIG_DIR = Path(__file__).parent / "data" / "repo_config"
 
 
-def load_yaml_config(filename) -> Any:
-    """
-    Load a YAML configuration file from the REPO_CONFIG_DIR directory.
-
-    Args:
-        filename (str): The name of the YAML file to load.
-
-    Returns:
-        object: The parsed YAML data as a Python object (usually dict).
-    """
-    with (REPO_CONFIG_DIR / filename).open() as f:
-        return yaml.safe_load(f)
-
-
 def test_only_include_valid():
     """
     Test that a valid repository configuration with a single path include is loaded correctly.
     Verifies that the pattern, reason, and comment fields are present and have expected values,
     and that the model objects are instantiated without error and contain the correct data.
     """
-    config_data = load_yaml_config("only_include.yml")
+    config_data = load_yaml_config(
+        filename="only_include.yml",
+        data_dir=REPO_CONFIG_DIR,
+    )
     includes = config_data.get("includes", {})
     if "paths" not in includes:
         pytest.fail("Missing 'paths' in includes")
@@ -80,7 +68,7 @@ def test_only_include_reason_fail():
     raises a ValueError when instantiating OrtRepositoryConfigurationIncludesPath.
     The test expects failure when 'reason' is not a valid PathIncludeReason enum.
     """
-    config_data = load_yaml_config("only_include_reason_fail.yml")
+    config_data = load_yaml_config("only_include_reason_fail.yml", REPO_CONFIG_DIR)
     includes = config_data.get("includes", {})
     if "paths" not in includes:
         pytest.fail("Missing 'paths' in includes")