[WIP] OCTO-11566 Create code checks script(pre-commit + ruff)

.github/workflows/release.yml

@@ -17,6 +17,9 @@ jobs:
     steps:
     - uses: actions/checkout@v7
 
+    - name: Code checks
+      run: ./scripts/code_checks/run_code_checks.sh --show-diff-on-failure
+
     - name: Set up Python
       uses: actions/setup-python@v6
       with:

.github/workflows/release_test_pypi.yml

@@ -17,6 +17,9 @@ jobs:
     steps:
     - uses: actions/checkout@v7
 
+    - name: Code checks
+      run: ./scripts/code_checks/run_code_checks.sh --show-diff-on-failure
+
     - name: Set up Python
       uses: actions/setup-python@v6
       with:

.github/workflows/unit_tests.yml

@@ -28,7 +28,7 @@ jobs:
       - name: Run Test
         id: tests
         run: |
-          ./run_tests.sh test_${{ matrix.python-version }} 
+          ./run_tests.sh test_${{ matrix.python-version }}
         continue-on-error: true
 
       - name: Archive production artifacts

.pre-commit-config.yaml

@@ -1,17 +1,28 @@
+default_stages: [pre-commit, pre-push]
+
+exclude: |
+    (?x)(
+        ^tests/fixtures/|
+        ^ai_artifacts/|
+        ^.claude/
+    )
+
 repos:
--   repo: git://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
     hooks:
-    -   id: end-of-file-fixer
+    -   id: check-toml
+    -   id: check-xml
+    -   id: check-yaml
     -   id: trailing-whitespace
-    -   id: debug-statements
+    -   id: requirements-txt-fixer
+    -   id: sort-simple-yaml
+    -   id: end-of-file-fixer
+    -   id: check-ast
 
--   repo: git://github.com/PyCQA/flake8
-    rev: 3.9.2
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.16.5
     hooks:
-    -   id: flake8
-        args: [
-                '--exclude=tests/fixtures*',
-                '--ignore=W503,C901',
-                '--max-line-length=80',
-        ]
+    -   id: ruff
+        args: [--fix]
+    -   id: ruff-format

.readthedocs.yaml

@@ -12,4 +12,4 @@ sphinx:
 # Explicitly set the version of Python and its requirements
 python:
   install:
-    - requirements: docs/requirements.txt
+    - requirements: docs/requirements.txt

Dockerfile_precommit

@@ -0,0 +1,15 @@
+# minimum supported version
+FROM python:3.10-slim-bookworm
+
+WORKDIR /pycaption
+
+ADD ./.pre-commit-config.yaml /pycaption/
+ADD ./ruff.toml /pycaption/
+
+RUN apt-get -y update && \
+    apt-get -y install git && \
+    git init && \
+    pip install pre-commit==4.6.2 && \
+    pre-commit install --install-hooks
+
+RUN git config --global --add safe.directory /pycaption

ai_artifacts/project_understanding.md

@@ -15,7 +15,7 @@ and web caption formats. It is the caption ingestion engine behind PBS's video p
 | Language | Python (see `setup.py` for version bounds) |
 | Framework | None (pure library) |
 | Testing | pytest, pytest-lazy-fixture |
-| Linting | flake8, pre-commit hooks |
+| Linting | ruff (lint + format), pre-commit hooks |
 | Packaging | setuptools (setup.py) |
 | Dependencies | beautifulsoup4, lxml, cssutils |
 | Optional | nltk (transcript features) |
@@ -91,7 +91,8 @@ pycaption/
 ├── examples/                     # Sample caption files
 ├── docs/                         # Sphinx documentation (introduction.rst)
 ├── setup.py                      # Package config (version here)
-├── .pre-commit-config.yaml       # Linting: end-of-file-fixer, trailing-whitespace, flake8
+├── .pre-commit-config.yaml       # Hook definitions (pre-commit-hooks + ruff)
+├── ruff.toml                     # Ruff lint/format rules
 └── README.rst                    # Project readme
 ```
 

docker-compose.yml

@@ -35,4 +35,4 @@ services:
       pytest -vvvv --color=yes --junit-xml=junit.xml --cov=pycaption --cov-report xml:coverage.xml;
       "
     volumes:
-      - .:/pycaption
+      - .:/pycaption

docs/changelog.rst

@@ -1,5 +1,10 @@
 Changelog
 ---------
+2.3.11
+^^^^^^
+  - Replaced the existing linting tools with Ruff
+  - Added a linting check to the PyPI publishing workflow
+
 2.3.10
 ^^^^^^^
   - Fix ``WebVTTWriter`` producing unparseable output when a single

docs/conf.py

@@ -13,6 +13,7 @@
 
 import sphinx_rtd_theme
 
+
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
@@ -45,17 +46,16 @@
 
 # General information about the project.
 project = "pycaption"
-copyright = "2012-2026, PBS.org " \
-            "(available under the Apache License, Version 2.0)"
+copyright = "2012-2026, PBS.org (available under the Apache License, Version 2.0)"
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
 # built documents.
 #
 # The short X.Y version.
-version = "2.3.10.dev1"
+version = "2.3.11.dev1"
 # The full version, including alpha/beta/rc tags.
-release = "2.3.10.dev1"
+release = "2.3.11.dev1"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/requirements.txt

@@ -1,3 +1,3 @@
+readthedocs-sphinx-search==0.3.2
 sphinx==7.2.6
 sphinx_rtd_theme==1.3.0
-readthedocs-sphinx-search==0.3.2

pycaption/__init__.py

@@ -21,6 +21,7 @@
 from .transcript import TranscriptWriter
 from .webvtt import WebVTTReader, WebVTTWriter
 
+
 __all__ = [
     "CaptionConverter",
     "DFXPReader",

pycaption/base.py

@@ -7,11 +7,13 @@
 
 import logging
 import os
+
 from datetime import timedelta
 from numbers import Number
 
 from .exceptions import CaptionReadError, CaptionReadTimingError, InvalidInputError
 
+
 logger = logging.getLogger(__name__)
 
 # `und` a special identifier for an undetermined language according to ISO 639-2
@@ -40,8 +42,7 @@ def read(self, content, caption_reader):
         """
         if not hasattr(caption_reader, "read"):
             raise InvalidInputError(
-                "The caption_reader must be a BaseReader instance "
-                "with a read() method."
+                "The caption_reader must be a BaseReader instance with a read() method."
             )
         self.captions = caption_reader.read(content)
         return self

pycaption/dfxp/constants.py

@@ -8,6 +8,7 @@
 
 from ..geometry import Alignment, HorizontalAlignmentEnum, Layout, VerticalAlignmentEnum
 
+
 DFXP_BASE_MARKUP = """
 <tt xmlns="http://www.w3.org/ns/ttml"
     xmlns:tts="http://www.w3.org/ns/ttml#styling">

pycaption/dfxp/extras.py

@@ -13,6 +13,7 @@
 from .constants import DFXP_DEFAULT_REGION
 from .writer import DFXPWriter
 
+
 LEGACY_DFXP_BASE_MARKUP = """
 <tt xmlns="http://www.w3.org/ns/ttml"
     xmlns:tts="http://www.w3.org/ns/ttml#styling">
@@ -255,7 +256,7 @@ def _recreate_span(self, line, node, dfxp):
 
         return line
 
-    def _recreate_style(self, content, dfxp):
+    def _recreate_style(self, content, dfxp):  # noqa: C901
         """Convert an internal style dict to DFXP/TTS attributes.
 
         :type content: dict

pycaption/dfxp/reader.py

@@ -47,6 +47,7 @@
     VERTICAL_ALIGNMENT_TO_DFXP,
 )
 
+
 _LEADING_WHITESPACE_RE = re.compile("^(?:[\n\r]+\\s*)?(.+)")
 
 _DFXP_WRITING_MODE_MAP = {
@@ -147,7 +148,8 @@ def read(self, content):
                     style_dict[id_] = self._convert_style(style)
 
         caption_set = CaptionSet(
-            caption_dict, styles=style_dict,
+            caption_dict,
+            styles=style_dict,
             visual_alignment_default=HorizontalAlignmentEnum.START,
         )
 
@@ -179,8 +181,7 @@ def _resolve_explicit_tickrate(self, tt_attrs):
             tickrate = float(tt_attrs["ttp:tickrate"])
         except ValueError:
             raise CaptionReadSyntaxError(
-                f"ttp:tickRate must be a number, "
-                f"got '{tt_attrs['ttp:tickrate']}'"
+                f"ttp:tickRate must be a number, got '{tt_attrs['ttp:tickrate']}'"
             )
         if tickrate <= 0:
             raise CaptionReadSyntaxError(
@@ -203,8 +204,7 @@ def _resolve_default_tickrate(self, tt_attrs, framerate_str):
             framerate_int = int(framerate_str)
         except ValueError:
             raise CaptionReadSyntaxError(
-                f"ttp:frameRate must be a positive integer, "
-                f"got '{framerate_str}'"
+                f"ttp:frameRate must be a positive integer, got '{framerate_str}'"
             )
         self.tickrate = float(framerate_int * sub_framerate)
 
@@ -396,7 +396,7 @@ def _convert_span_to_nodes(self, tag):
                 self._convert_tag_to_node(a)
 
     @staticmethod
-    def _convert_style(tag):
+    def _convert_style(tag):  # noqa: C901
         """Convert DFXP/TTS style attributes on a tag to an internal style dict.
 
         Maps tts:fontStyle, tts:fontWeight, tts:textDecoration, tts:textAlign,

pycaption/dfxp/writer.py

@@ -5,6 +5,7 @@
 """
 
 import re
+
 from copy import deepcopy
 from xml.sax.saxutils import escape
 
@@ -26,6 +27,7 @@
     _create_external_alignment,
 )
 
+
 _WRITING_DIRECTION_TO_DFXP = {
     WritingDirectionEnum.VERTICAL_RL: "tbrl",
     WritingDirectionEnum.VERTICAL_LR: "tblr",
@@ -491,7 +493,7 @@ def _text_shadow_to_outline(value):
     return thickness
 
 
-def _recreate_style(content, dfxp):
+def _recreate_style(content, dfxp):  # noqa: C901
     """Convert an internal style dict to DFXP/TTS style attributes.
 
     Maps pycaption's internal keys (class, italics, bold, underline, color,
@@ -542,7 +544,7 @@ def _recreate_style(content, dfxp):
     return dfxp_style
 
 
-def _convert_layout_to_attributes(layout, fallback_alignment=None):
+def _convert_layout_to_attributes(layout, fallback_alignment=None):  # noqa: C901
     """Convert a Layout object to a dict of DFXP region attributes.
 
     Maps origin, extent, padding, alignment, and writing_direction to their

pycaption/geometry.py

@@ -7,12 +7,15 @@
   responsible for the recalculation should return a new object with the
   necessary modifications.
 """
+
 import re
+
 from enum import Enum
 from functools import total_ordering
 
 from .exceptions import CaptionReadSyntaxError, RelativizationError
 
+
 _UNIT_MISMATCH_MSG = "The sizes should have the same measure units."
 
 

pycaption/microdvd.py

@@ -5,6 +5,7 @@
 """
 
 import re
+
 from copy import deepcopy
 
 from .base import (

pycaption/sami/constants.py

@@ -10,6 +10,7 @@
 
 from ..geometry import HorizontalAlignmentEnum
 
+
 log.setLevel(FATAL)
 
 SAMI_BASE_MARKUP = """

pycaption/sami/reader.py

@@ -11,6 +11,7 @@
 from ..geometry import Alignment, HorizontalAlignmentEnum, Layout, Padding, Size
 from .parser import SAMIParser
 
+
 _TAG_TO_STYLE = {"i": "italics", "b": "bold", "u": "underline"}
 
 

pycaption/sami/writer.py

@@ -13,6 +13,7 @@
 from ..geometry import HorizontalAlignmentEnum
 from .constants import HORIZONTAL_ALIGNMENT_MAP, SAMI_BASE_MARKUP
 
+
 _NON_CSS_KEYS = frozenset(
     {
         "classes",

pycaption/scc/__init__.py

@@ -3,4 +3,5 @@
 from .reader import SCCReader
 from .writer import SCC_TOKENS_PER_CAPTION_MAX, SCCWriter
 
+
 __all__ = ["SCCReader", "SCCWriter", "SCC_TOKENS_PER_CAPTION_MAX"]

pycaption/scc/constants.py

@@ -7,8 +7,10 @@
 """
 
 import re as _re
+
 from itertools import product
 
+
 COMMANDS = {
     "9420": "",
     "9429": "",

pycaption/scc/reader.py

@@ -78,6 +78,7 @@
 """
 
 import re
+
 from collections import deque
 from copy import deepcopy
 
@@ -108,6 +109,7 @@
 )
 from .state_machines import DefaultProvidingPositionTracker
 
+
 _TIMECODE_RE = re.compile(r"\d{2}:\d{2}:\d{2}[:;](\d{1,2})")
 
 

pycaption/scc/specialized_collections.py

@@ -29,6 +29,7 @@
     UNDERLINE_COMMANDS,
 )
 
+
 PopOnCue = collections.namedtuple("PopOnCue", "buffer, start, end")
 
 # First two hex chars of SCC codes that produce punctuation ['.', '!', '?', ',']