Merge pull request #33 from bjhargrave/taxonomy-reading

Taxonomy reading API

Author: bjhargrave

.github/dependabot.yml

@@ -13,3 +13,10 @@ updates:
     directory: "/.github/workflows"
     schedule:
       interval: "daily"
+
+  # Maintain dependencies for Python code
+  - package-ecosystem: "pip"
+    directory: "/"
+    versioning-strategy: "increase-if-necessary"
+    schedule:
+      interval: "daily"

.github/workflows/lint.yml

@@ -48,7 +48,7 @@ jobs:
               tox -e jsonschema
           - name: "ruff"
             commands: |
-              tox -e ruff -- check
+              tox -e ruffcheck
           - name: "pylint"
             commands: |
               echo "::add-matcher::.github/workflows/matchers/pylint.json"

.github/workflows/test.yml

@@ -41,7 +41,6 @@ jobs:
     strategy:
       matrix:
         python:
-          - "3.9"
           - "3.10"
           - "3.11"
           - "3.12"

README.md

@@ -1,5 +1,6 @@
 # Taxonomy Schema
 
-This Python package defines the JSON schema for the InstructLab [Taxonomy](https://github.com/instructlab/taxonomy) YAML.
+This Python package defines the JSON schema and a parser for the InstructLab [Taxonomy](https://github.com/instructlab/taxonomy) YAML.
 
-Consumers of this schema can `pip install instructlab-schema`, and access the schema files using `importlib.resources` on the `instructlab.schema` package.
+Consumers of this schema can `pip install instructlab-schema`, and use the `instructlab.schema.taxonomy.TaxonomyParser` class to parse and validate `qna.yaml` taxonomy files.
+Schema files can be directly accessed using the `instructlab.schema.schema_base()` method to get access the base of the schema resources.

pyproject.toml

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 [build-system]
-requires = ["setuptools>=64", "setuptools_scm>=8"]
+requires = ["setuptools>=70.1.0", "setuptools_scm>=8"]
 build-backend = "setuptools.build_meta"
 
 [project]
@@ -10,19 +10,26 @@ authors = [{ name = "InstructLab", email = "[email protected]" }]
 description = "InstructLab Taxonomy Schema"
 readme = "README.md"
 license = { text = "Apache-2.0" }
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 classifiers = [
     "Development Status :: 4 - Beta",
     "License :: OSI Approved :: Apache Software License",
     "Operating System :: OS Independent",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
 ]
-dynamic = ["dependencies", "optional-dependencies", "version"]
+dependencies = [
+    "typing_extensions",
+    "jsonschema>=4.22.0",
+    "PyYAML>=6.0.0",
+    # The below library should NOT be imported into any python files
+    # We only use the command via subprocess
+    "yamllint>=1.35.1",
+]
+dynamic = ["version"]
 
 [project.urls]
 homepage = "https://instructlab.ai"
@@ -34,13 +41,14 @@ version_file = "src/instructlab/schema/_version.py"
 local_scheme = "no-local-version"                   # do not include +gREV local version, required for Test PyPI upload
 
 [tool.mypy]
-python_version = "3.9"
+python_version = "3.10"
 exclude = ["^src/instructlab/schema/_version\\.py$"]
 
 [tool.ruff]
-target-version = "py39"
+target-version = "py310"
 src = ["src", "tests"]
 extend-exclude = ["src/instructlab/schema/_version.py"]
+line-length = 180
 
 [tool.ruff.lint]
 select = [
@@ -54,11 +62,23 @@ select = [
     "TID", # flake8-tidy-imports
 ]
 
+[tool.ruff.lint.flake8-tidy-imports.banned-api]
+"yamllint".msg = "yamllint is for use as a command via subprocess."
+
 [tool.pylint.main]
-py-version = "3.9"
+py-version = "3.10"
 source-roots = ["src", "tests"]
 ignore = ["_version.py"]
 
+[tool.pylint.design]
+max-branches = 20
+max-line-length = 180
+max-locals = 20
+min-public-methods = 1
+
+[tool.pylint.format]
+max-args = 8
+
 [tool.pylint."messages control"]
 disable = [
     "missing-class-docstring",

scripts/ruff.sh

@@ -1,14 +1,22 @@
+# SPDX-License-Identifier: Apache-2.0
+
 """InstructLab Taxonomy Schema"""
 
 # Standard
-from importlib import resources
+import importlib.resources
+from importlib.abc import Traversable
+
+__all__ = ["schema_base", "schema_versions"]
+
 
-try:
-    from importlib.resources.abc import Traversable  # type: ignore[import-not-found]
-except ImportError:  # python>=3.9,<3.11
-    from importlib.abc import Traversable
+def schema_base() -> Traversable:
+    """Return the schema base.
 
-__all__ = ["schema_versions"]
+    Returns:
+        Traversable: The base for the schema versions.
+    """
+    base = importlib.resources.files(__name__)
+    return base
 
 
 def schema_versions() -> list[Traversable]:
@@ -17,9 +25,8 @@ def schema_versions() -> list[Traversable]:
     Returns:
         list[Traversable]: A sorted list of schema versions.
     """
-    schema_base = resources.files(__package__)
     versions = sorted(
-        (v for v in schema_base.iterdir() if v.name[0] == "v" and v.name[1:].isdigit()),
+        (v for v in schema_base().iterdir() if v.name[0] == "v" and v.name[1:].isdigit()),
         key=lambda k: int(k.name[1:]),
     )
     return versions