Merge pull request #185 from nationalarchives/FCL-343-add-typing-and-…

…type-checking-to-utils

[FCL-343] Add typing to utils

.pre-commit-config.yaml

@@ -1,3 +1,4 @@
+exclude: courts_schema_types_autogenerated\.py
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.6.0
@@ -14,11 +15,44 @@ repos:
       - id: no-commit-to-branch
       - id: trailing-whitespace
 
+  # There is a bug with upstream which means the imports are
+  # not sorted -- this should do for now
+  - repo: https://github.com/camptocamp/jsonschema-gentypes
+    rev: 2.8.1
+    hooks:
+      - id: jsonschema-gentypes
+        files: src/ds_caselaw_utils/data/schema/courts.schema.json
+        language_version: python3.9
+
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.6.8
     hooks:
+      - id: ruff
+        args:
+          - --fix
+          - --exit-non-zero-on-fix
       - id: ruff-format
 
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.11.2
+    hooks:
+      - id: mypy
+        name: mypy-src
+        additional_dependencies:
+          - types-PyYAML
+          - ruamel.yaml
+        args:
+          - --strict
+        files: ^(src/ds_caselaw_utils|scripts)
+        exclude: (?:test_|factory.py)
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.11.2
+    hooks:
+      - id: mypy
+        name: mypy-tests
+        files: ^src/ds_caselaw_utils/test_
+
   - repo: https://github.com/python-jsonschema/check-jsonschema
     rev: 0.29.2
     hooks:

jsonschema-gentypes.yaml

@@ -0,0 +1,22 @@
+headers: >
+  # Automatically generated file from a JSON schema
+# Used to correctly format the generated file
+# callbacks:
+#   - - black
+#   - - isort
+generate:
+  - # JSON schema file path
+    source: src/ds_caselaw_utils/data/schema/courts.schema.json
+    # Python file path
+    destination: src/ds_caselaw_utils/courts_schema_types_autogenerated.py
+    # The name of the root element
+    root_name: RawCourtRepository
+    # Argument passed to the API
+    api_arguments:
+      additional_properties: Only explicit
+    # Rename an element
+    name_mapping: {}
+    # The minimum Python version that the code should support. By default the
+    # currently executing Python version is chosen. Note that the output
+    # may require typing_extensions to be installed.
+    python_version: "3.9"

pyproject.toml

@@ -12,33 +12,23 @@ readme = "README.md"
 [tool.poetry.dependencies]
 python = "^3.9"
 "ruamel.yaml" = "^0.18.0"
+typing-extensions = "^4.12.2"
 
 [tool.poetry.dev-dependencies]
 
 [tool.ruff]
 line-length = 120
 
 [tool.ruff.lint]
-ignore = ["E501", "G004", "PLR2004", "RUF005", "RUF012", "UP040"] # long lines, fstrings in logs, magic values, consider not concat, mutable classbits, type instead of TypeAlias
-extend-select = ["W", "B", "Q", "C90", "I", "UP", "YTT", "ASYNC", "S", "BLE", "A", "COM", "C4", "DTZ", "T10", "DJ", "EM", "EXE", "FA",
-                 "ISC", "ICN", "G", "INP", "PIE", "T20", "PYI", "PT", "Q", "RSE", "RET", "SLF", "SLOT", "SIM", "TID", "TCH", "INT", "PTH",
-                 "FIX", "PGH", "PL", "TRY", "FLY", "PERF", "RUF"]
+ignore = ["E501", "G004", "PLR2004", "RUF005", "RUF012", "UP040"] # longlines, fstrings in logs, magic values, consider not concat, mutable classbits, type instead of TypeAlias
+extend-select = ["W", "I", ]
+# extend-select = [ "SLF", "SIM", "B", "Q", "C90", "I", "UP", "YTT", "ASYNC", "S", "BLE", "A", "COM", "C4", "DTZ", "T10", "DJ", "EM", "EXE", "FA",
+#                  "ISC", "ICN", "G", "INP", "PIE", "T20", "PYI", "PT", "Q", "RSE", "RET", "SLOT", "TID", "TCH", "INT", "PTH",
+#                  "FIX", "PGH", "PL", "TRY", "FLY", "PERF", "RUF"]
 unfixable = ["ERA"]
 
-# things skipped:
-# N: naming, possibly good
-# D: docstrings missing throughout
-# ANN: annotations missing throughout
-# FBT: not convinced boolean trap worth auto-banning.
-# CPY: copyright at top of each file
-# G: logging warnings -- fstrings bad?
-# ARG: sometimes you need to accept arguments.
-# TD: somewhat finicky details about formatting TODOs
-# FIX: flags todos: possible to add -- skipped for now
-# ERA: lots of false positives, not a good autofix
-# PD, NPY, AIR: ignored, panda / numpy / airflow specific
-# FURB: not yet out of preview
-
+[tool.ruff.lint.extend-per-file-ignores]
+"test_*" = ["S101"]  # `assert` is fine in tests
 
 [tool.commitizen]
 name = "cz_conventional_commits"

scripts/build_courts_list

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 
 from pathlib import Path
+
 import yaml
 
 print("Loading courts...")

src/ds_caselaw_utils/__init__.py

@@ -1,2 +1,4 @@
 from .courts import courts
-from .neutral import neutral_url as neutral_url
+from .neutral import neutral_url
+
+__all__ = ["courts", "neutral_url"]