feat(scanner): Add scan result parser

Signed-off-by: Helio Chissini de Castro <dev@heliocastro.info>
Signed-off-by: Helio Chissini de Castro <helio.chissini.de.castro@cariad.technology>

Author: heliocastro

README.md

@@ -1,3 +1,28 @@
 # Python-Ort
 
-Python-Ort is a pydantic based library to serialize OSS Review Toolkit generated reports using the default models.
+Python-Ort is a pydantic v2 based library to serialize [OSS Review Toolkit](https://oss-review-toolkit.org/ort/) generated reports using the default models.
+
+## Install
+
+```bash
+pip install python-ort
+```
+
+## Simple usage example based on a report in yml format:
+
+```python
+import pprint
+from pathlib import Path
+from pydantic import ValidationError
+
+from ort import OrtResult, ort_yaml_load
+
+
+try:
+    with Path("some-result.yml").open() as fd:
+        data = ort_yaml_load(fd)
+    parsed = OrtResult(**data)
+    pprint(parsed)
+except ValidationError as e:
+    print(e)
+```

prek.toml

@@ -22,7 +22,7 @@ hooks = [
 
 [[repos]]
 repo = "https://github.com/astral-sh/ruff-pre-commit"
-rev = "v0.15.4"
+rev = "v0.15.6"
 hooks = [
   {
     id = "ruff",
@@ -43,21 +43,21 @@ hooks = [
 
 [[repos]]
 repo = "https://github.com/astral-sh/uv-pre-commit"
-rev = "0.10.8"
+rev = "0.10.9"
 hooks = [
   { id = "uv-lock" }
 ]
 
 [[repos]]
 repo = "https://github.com/codespell-project/codespell"
-rev = "v2.4.1"
+rev = "v2.4.2"
 hooks = [
   { id = "codespell" }
 ]
 
 [[repos]]
 repo = "https://github.com/allganize/ty-pre-commit"
-rev = "v0.0.20"
+rev = "v0.0.22"
 hooks = [
   {
     id = "ty-check",
@@ -72,6 +72,7 @@ hooks = [
       "packageurl-python",
       "click",
       "rich",
+      "license-expression",
     ]
   }
 ]

pyproject.toml

@@ -4,13 +4,15 @@ build-backend = "uv_build"
 
 [project]
 name = "python-ort"
-version = "0.7.0"
+version = "0.8.0"
 description = "A Python Ort model serialization library"
 readme = "README.md"
 license = "MIT"
 license-files = ["LICENSE"]
 requires-python = ">=3.10"
 dependencies = [
+    "license>=0.1a3",
+    "license-expression>=30.4.4",
     "packageurl-python>=0.17.6",
     "pydantic>=2.12.5",
 ]
@@ -38,8 +40,8 @@ dev = [
     "datamodel-code-generator[http]>=0.55.0",
     "pytest>=9.0.2",
     "rich>=14.3.3",
-    "ruff>=0.15.5",
-    "ty>=0.0.21",
+    "ruff>=0.15.6",
+    "ty>=0.0.22",
     "types-pyyaml>=6.0.12.20250915",
 ]
 
@@ -144,9 +146,7 @@ extend-select = [
     "S",   # bandit
 ]
 ignore = [
-    'N802',   # function name should be lowercase
     'SIM105', # Suggest contextlib instead of try/except with pass
-    'A004',  # Python shadow builtins
 ]
 # Unlike Flake8, default to a complexity level of 10.
 mccabe.max-complexity = 10

src/ort/models/base_run.py

@@ -1,4 +1,5 @@
-# SPDX-FileCopyrightText: 2025 Helio Chissini de Castro <heliocastro@gmail.com>
+# SPDX-FileCopyrightText: 2025 Helio Chissini de Castro <dev@heliocastro.info>
+# # SPDX-FileCopyrightText: 2026 CARIAD SE
 # SPDX-License-Identifier: MIT
 
 from datetime import datetime

src/ort/models/config/file_archiver_configuration.py

@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <dev@heliocastro.info>
+# SPDX-FileCopyrightText: 2026 CARIAD SE
+# SPDX-License-Identifier: MIT
+
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from .file_storage_configuration import FileStorageConfiguration
+from .scan_storage_configuration import PostgresStorageConfiguration
+
+
+class FileArchiverConfiguration(BaseModel):
+    """
+    The configuration model for a FileArchiver.
+    """
+
+    model_config = ConfigDict(
+        extra="forbid",
+    )
+
+    enabled: bool = Field(
+        default=True,
+        description="Toggle to enable or disable the file archiver functionality altogether.",
+    )
+    file_storage: FileStorageConfiguration | None = Field(
+        default=None,
+        description="Configuration of the FileStorage used for archiving the files.",
+    )
+    postgres_storage: PostgresStorageConfiguration | None = Field(
+        default=None,
+        description="Configuration of the PostgresProvenanceFileStorage used for archiving the files.",
+    )

src/ort/models/config/file_list_storage_configuration.py

@@ -0,0 +1,26 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <dev@heliocastro.info>
+# SPDX-FileCopyrightText: 2026 CARIAD SE
+# SPDX-License-Identifier: MIT
+
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from .file_storage_configuration import FileStorageConfiguration
+from .scan_storage_configuration import PostgresStorageConfiguration
+
+
+class FileListStorageConfiguration(BaseModel):
+    """
+    Configuration for the storage backends used for persisting file lists.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+    file_storage: FileStorageConfiguration | None = Field(
+        default=None,
+        description=("Configuration of the FileStorage used for storing the file lists."),
+    )
+    postgres_storage: PostgresStorageConfiguration | None = Field(
+        default=None,
+        description="Configuration of the PostgresProvenanceFileStorage used for storing the file lists.",
+    )

src/ort/models/config/file_storage_configuration.py

@@ -0,0 +1,34 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <dev@heliocastro.info>
+# SPDX-FileCopyrightText: 2026 CARIAD SE
+# SPDX-License-Identifier: MIT
+
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from .http_file_storage_configuration import HttpFileStorageConfiguration
+from .local_file_storage_configuration import LocalFileStorageConfiguration
+from .s3_file_storage_configuration import S3FileStorageConfiguration
+
+
+class FileStorageConfiguration(BaseModel):
+    """
+    The configuration model for a FileStorage. Only one of the storage options
+    can be configured.
+    """
+
+    model_config = ConfigDict(
+        extra="forbid",
+    )
+
+    http_file_storage: HttpFileStorageConfiguration | None = Field(
+        default=None,
+        description="The configuration of a HttpFileStorage.",
+    )
+    local_file_storage: LocalFileStorageConfiguration | None = Field(
+        default=None,
+        description="The configuration of a LocalFileStorage.",
+    )
+    s3_file_storage: S3FileStorageConfiguration | None = Field(
+        default=None,
+        description="The configuration of a S3FileStorage.",
+    )

src/ort/models/config/http_file_storage_configuration.py

@@ -0,0 +1,25 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <dev@heliocastro.info>
+# SPDX-FileCopyrightText: 2026 CARIAD SE
+# SPDX-License-Identifier: MIT
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class HttpFileStorageConfiguration(BaseModel):
+    """
+    Configuration for HTTP-based file storage.
+    """
+
+    url: str = Field(
+        description='The URL of the HTTP server, e.g. "https://example.com/storage".',
+    )
+    query: str = Field(
+        default="",
+        description='Query string appended to the URL and path. Can contain auth data, e.g. "?user=standard&pwd=123".',
+    )
+    headers: dict[str, str] = Field(
+        default_factory=dict,
+        description="Custom headers added to all HTTP requests. Values may contain credentials.",
+    )
+
+    model_config = ConfigDict(extra="forbid")

src/ort/models/config/local_file_storage_configuration.py

@@ -0,0 +1,22 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <dev@heliocastro.info>
+# SPDX-FileCopyrightText: 2026 CARIAD SE
+# SPDX-License-Identifier: MIT
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class LocalFileStorageConfiguration(BaseModel):
+    """
+    A class to hold the configuration for using local files as a storage.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+    directory: str = Field(
+        ...,
+        description="The directory to use as a storage root.",
+    )
+    compression: bool = Field(
+        default=True,
+        description="Whether to use compression for storing files or not. Defaults to true.",
+    )

src/ort/models/config/postgres_connection.py

@@ -0,0 +1,97 @@
+# SPDX-FileCopyrightText: 2026 Helio Chissini de Castro <heliocastro@gmail.com>
+# SPDX-FileCopyrightText: 2026 CARIAD SE
+# SPDX-License-Identifier: MIT
+
+
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class PostgresConnection(BaseModel):
+    """
+    PostgreSQL connection configuration and HikariCP pool settings.
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+    url: str = Field(
+        ...,
+        description=("The database URL in JDBC format."),
+    )
+
+    provider_schema: str = Field(
+        default="public",
+        alias="schema",
+        description=("The name of the database to use."),
+    )
+
+    username: str = Field(
+        ...,
+        description=("The username to use for authentication."),
+    )
+
+    password: str = Field(
+        default_factory=str,
+        description=("The password to use for authentication."),
+    )
+
+    sslmode: str = Field(
+        default="verify-full",
+        description='The SSL mode to use, one of "disable", "allow", "prefer", "require", '
+        '"verify-ca" or "verify-full". See: '
+        "https://jdbc.postgresql.org/documentation/ssl/#configuring-the-client",
+    )
+
+    sslcert: str | None = Field(
+        None,
+        description="The full path of the certificate file. See: https://jdbc.postgresql.org/documentation/head/connect.html",
+    )
+
+    sslkey: str | None = Field(
+        None,
+        description="The full path of the key file. See: https://jdbc.postgresql.org/documentation/head/connect.html",
+    )
+
+    sslrootcert: str | None = Field(
+        None,
+        description="The full path of the root certificate file. See: "
+        "https://jdbc.postgresql.org/documentation/head/connect.html",
+    )
+
+    connection_timeout: int | None = Field(
+        None,
+        description="Maximum milliseconds to wait for connections from the pool. See: "
+        "https://github.com/brettwooldridge/HikariCP#frequently-used",
+    )
+
+    idle_timeout: int | None = Field(
+        None,
+        description="Maximum milliseconds a connection may sit idle in the pool. Requires "
+        "minimum_idle < maximum_pool_size. See: "
+        "https://github.com/brettwooldridge/HikariCP#frequently-used",
+    )
+
+    keepalive_time: int | None = Field(
+        None,
+        description="Frequency in milliseconds that the pool will keep an idle connection "
+        "alive. Must be lower than max_lifetime. See: "
+        "https://github.com/brettwooldridge/HikariCP#frequently-used",
+    )
+
+    max_lifetime: int | None = Field(
+        None,
+        description=(
+            "Maximum lifetime of a connection in milliseconds. See: "
+            "https://github.com/brettwooldridge/HikariCP#frequently-used"
+        ),
+    )
+
+    maximum_pool_size: int | None = Field(
+        None,
+        description="Maximum size of the connection pool. See: https://github.com/brettwooldridge/HikariCP#frequently-used",
+    )
+
+    minimum_idle: int | None = Field(
+        None,
+        description="Minimum number of idle connections that the pool tries to maintain. "
+        "See: https://github.com/brettwooldridge/HikariCP#frequently-used",
+    )