Snippet repository config

.gitignore

@@ -11,7 +11,7 @@ wheels/
 .python-version
 
 # Old python requirements
-requirements.txt
+requirements.txtq
 
 # Ort directories
 output

prek.toml

@@ -0,0 +1,77 @@
+# Configuration file for `prek`, a git hook framework written in Rust.
+# See https://prek.j178.dev for more information.
+#:schema https://www.schemastore.org/prek.json
+
+default_language_version.python = "3.13"
+default_install_hook_types = ["pre-commit", "commit-msg"]
+
+[[repos]]
+repo = "https://github.com/pre-commit/pre-commit-hooks"
+rev = "v6.0.0"
+hooks = [
+  { id = "trailing-whitespace" },
+  { id = "end-of-file-fixer" },
+  { id = "check-yaml" },
+  { id = "check-added-large-files" },
+  { id = "check-symlinks" },
+  {
+    id = "mixed-line-ending",
+    args = ["--fix=lf"]
+  }
+]
+
+[[repos]]
+repo = "https://github.com/astral-sh/ruff-pre-commit"
+rev = "v0.15.4"
+hooks = [
+  {
+    id = "ruff",
+    args = ["--fix"]
+  },
+  { id = "ruff-format" }
+]
+
+[[repos]]
+repo = "https://github.com/compilerla/conventional-pre-commit"
+rev = "v4.4.0"
+hooks = [
+  {
+    id = "conventional-pre-commit",
+    stages = ["commit-msg"]
+  }
+]
+
+[[repos]]
+repo = "https://github.com/astral-sh/uv-pre-commit"
+rev = "0.10.8"
+hooks = [
+  { id = "uv-lock" }
+]
+
+[[repos]]
+repo = "https://github.com/codespell-project/codespell"
+rev = "v2.4.1"
+hooks = [
+  { id = "codespell" }
+]
+
+[[repos]]
+repo = "https://github.com/allganize/ty-pre-commit"
+rev = "v0.0.20"
+hooks = [
+  {
+    id = "ty-check",
+    args = [
+      "--verbose",
+      "--output-format=full"
+    ],
+    additional_dependencies = [
+      "pydantic",
+      "pyyaml",
+      "pytest",
+      "packageurl-python",
+      "click",
+      "rich",
+    ]
+  }
+]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "python-ort"
-version = "0.6.5"
+version = "0.6.6"
 description = "A Python Ort model serialization library"
 readme = "README.md"
 license = "MIT"
@@ -159,9 +159,3 @@ dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
 quote-style = "double"
 indent-style = "space"
 skip-magic-trailing-comma = false
-
-[tool.pyrefly]
-project_includes = [
-    "src/ort/**",
-    "tests/**",
-]

src/ort/models/config/repository_configuration.py

@@ -11,7 +11,7 @@
 from .package_configuration import PackageConfiguration
 from .repository_analyzer_configuration import RepositoryAnalyzerConfiguration
 from .resolutions import Resolutions
-from .snippet.snippet_choice import SnippetChoice
+from .snippet_choices import SnippetChoices
 
 
 class RepositoryConfiguration(BaseModel):
@@ -60,7 +60,7 @@ class RepositoryConfiguration(BaseModel):
         None,
         description="A configuration to select a license from a multi-licensed package.",
     )
-    snippet_choices: list[SnippetChoice] = Field(
+    snippet_choices: list[SnippetChoices] = Field(
         default_factory=list,
         description="A configuration to select a snippet from a package with multiple snippet findings.",
     )

src/ort/models/config/snippet/snippet_choice.py

@@ -1,7 +1,9 @@
 # SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <heliocastro@gmail.com>
 # SPDX-License-Identifier: MIT
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+
+from ort.utils import convert_enum
 
 from ....types.purl_type import PurlType
 from ...text_location import TextLocation
@@ -44,6 +46,11 @@ class Choice(BaseModel):
         description="An optional comment describing the snippet choice.",
     )
 
+    @field_validator("reason", mode="before")
+    @classmethod
+    def validate_reason(cls, value):
+        return convert_enum(SnippetChoiceReason, value)
+
 
 class SnippetChoice(BaseModel):
     """
@@ -61,3 +68,12 @@ class SnippetChoice(BaseModel):
         ...,
         description="The snippet criteria to make the snippet choice.",
     )
+
+    # @model_validator(mode="before")
+    # @classmethod
+    # def validate_snippet_choice(cls, v):
+    #     print(v)
+    #     breakpoint()
+    #     if not isinstance(v, dict):
+    #         raise ValueError("SnippetChoice must be a dictionary.")
+    #     return v

src/ort/models/config/snippet/Provenance.py → src/ort/models/config/snippet/snippet_provenance.py

@@ -1,9 +1,10 @@
 # SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <heliocastro@gmail.com>
 # SPDX-License-Identifier: MIT
+#
 from pydantic import AnyUrl, BaseModel, ConfigDict, Field
 
 
-class Provenance(BaseModel):
+class SnippetProvenance(BaseModel):
     """
     The URL of the [RepositoryProvenance] the snippet choice applies to.
     """

src/ort/models/config/snippet_choices.py

@@ -0,0 +1,25 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <heliocastro@gmail.com>
+# SPDX-License-Identifier: MIT
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from .snippet.snippet_choice import SnippetChoice
+from .snippet.snippet_provenance import SnippetProvenance
+
+
+class SnippetChoices(BaseModel):
+    """
+    A collection of snippet choices for a given provenance.
+    """
+
+    model_config = ConfigDict(
+        extra="forbid",
+    )
+    provenance: SnippetProvenance = Field(
+        ...,
+        description="The source file for which the snippet choice is made.",
+    )
+    choices: list[SnippetChoice] = Field(
+        ...,
+        description="The snippet choice for the given source file.",
+    )

src/ort/models/provenance.py

@@ -0,0 +1,85 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <heliocastro@gmail.com>
+# SPDX-License-Identifier: MIT
+
+from pydantic import BaseModel, ConfigDict, Field, model_validator
+
+from .remote_artifact import RemoteArtifact
+from .vcsinfo import VcsInfo
+
+
+class SnippetProvenance(BaseModel):
+    """
+    Provenance information about the origin of source code.
+
+    This is a union type that can be one of the following:
+    - UnknownProvenance: No provenance information is available.
+    - ArtifactProvenance: Provenance information for a source artifact.
+    - RepositoryProvenance: Provenance information for a Version Control System location.
+    """
+
+    model_config = ConfigDict(extra="allow")
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_provenance(cls, v):
+        print(v)
+        breakpoint()
+        if not isinstance(v, dict):
+            raise ValueError("Provenance must be a dictionary.")
+        if "source_artifact" in v:
+            return ArtifactProvenance(**v)
+        elif "vcs_info" in v and "resolved_revision" in v:
+            return RepositoryProvenance(**v)
+        else:
+            return UnknownProvenance()
+
+
+class UnknownProvenance(BaseModel):
+    """
+    Provenance information about the origin of source code.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+
+class KnownProvenance(BaseModel):
+    """
+    Provenance information about the origin of source code.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+
+class RemoteProvenance(KnownProvenance):
+    """
+    Provenance information about the origin of source code.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+
+class ArtifactProvenance(RemoteProvenance):
+    """
+    Provenance information for a source artifact.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+    source_artifact: RemoteArtifact = Field(
+        description="The source artifact that was downloaded.",
+    )
+
+
+class RepositoryProvenance(BaseModel):
+    """
+    Provenance information for a Version Control System location.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+    vcs_info: VcsInfo = Field(
+        description="VCS info used to resolve the revision. May still contain a moving revision like a branch.",
+    )
+    resolved_revision: str = Field(
+        description="Resolved fixed VCS revision, not blank and not moving (e.g. Git commit SHA1)."
+    )