chore: Move formatting and linting to Ruff

Replace Black, isort, Flake8, flynt, and pylint with Ruff.

Author: adamchainz

.github/dependabot.yml

@@ -8,12 +8,7 @@ updates:
   ignore:
   # Ignore all tooling (it can get old, it's mature enough)
   - dependency-name: selenium
-  - dependency-name: black
-  - dependency-name: pylint
-  - dependency-name: flake8
-  - dependency-name: isort
   - dependency-name: mypy
-  - dependency-name: flynt
   # Ignore all patch updates.
   - dependency-name: '*'
     update-types: ["version-update:semver-patch"]

.github/workflows/lint.yml

@@ -11,6 +11,8 @@ jobs:
         with:
           python-version: "3.9"
 
+      - uses: pre-commit/[email protected]
+
       - name: Install Poetry
         uses: snok/[email protected]
         with:
@@ -19,7 +21,7 @@ jobs:
 
       - name: Load cached venv
         id: cached-poetry-dependencies
-        uses: actions/cache@v2
+        uses: actions/cache@v4
         with:
           path: .venv
           key: venv-${{ runner.os }}-${{ hashFiles('**/poetry.lock') }}
@@ -34,21 +36,5 @@ jobs:
           echo "PYTHONPATH=$GITHUB_WORKSPACE" >> $GITHUB_ENV
           echo "$GITHUB_WORKSPACE/.venv/bin" >> $GITHUB_PATH
 
-      - name: Black Code Formatter
-        uses: psf/black@stable
-
-      - name: isort Import Sorter
-        uses: isort/[email protected]
-
-      - name: pylint Error Checker
-        run: pylint -E -f colorized xray
-
       - name: mypy Static Type Checker
         run: mypy .
-
-      - name: Flynt f-string Formatter
-        run: >
-          flynt .
-          --line-length=79
-          --transform-concats
-          --fail-on-change

.pre-commit-config.yaml

@@ -5,7 +5,7 @@ ci:
   autoupdate_schedule: quarterly
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
      - id: check-added-large-files
        args: [--maxkb=5000]
@@ -24,28 +24,9 @@ repos:
      - id: trailing-whitespace
        args: [--markdown-linebreak-ext=md]
 
-  - repo: https://github.com/ikamensh/flynt/
-    rev: '1.0.1'
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.8
     hooks:
-     - id: flynt
-       args: [--line-length=79, --transform-concats]
-
-  - repo: https://github.com/psf/black
-    rev: 24.4.2
-    hooks:
-     - id: black
-
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.13.2
-    hooks:
-     - id: isort
-       name: isort (python)
-
-#
-# Tried and Failed
-#
-# 1. I tried doing mypy too, but it was a mess because it runs in its own
-#   isolated environment, that lacks all our dependencies.
-# 2. We might want flake8 someday. It's easy to turn on, but it's so noisy on
-#    our current code that it'd take some fine-tuning to get it right.
-# 3. semgrep was too slow and had to be moved to a github action.
+      - id: ruff
+        args: [ --fix ]
+      - id: ruff-format

poetry.lock

@@ -45,32 +45,43 @@ requests = "^2.26.0"
 types-requests = "^2.26.0"
 
 [tool.poetry.dev-dependencies]
-black = "^23.1"
-isort = "^5.12.0"
 mypy = "^0.910"
-pylint = "^2.7.1"
 wheel = "^0.38.2"
-flynt = "^0.69"
 pre-commit = "^3.3.3"
 ipython = "^8.12.0"
 
-[tool.black]
-include = '''.*\.pyi?$'''
+[tool.ruff]
 line-length = 79
-
-[tool.isort]
-force_grid_wrap = 0
-include_trailing_comma = true
-known_third_party = []
-line_length = 79
-multi_line_output = 3
-use_parentheses = true
-
-[tool.pylint.messages_control]
-disable = "C0330, C0326"
-
-[tool.pylint.format]
-max-line-length = "79"
+lint.select = [
+  # flake8-bugbear
+  "B",
+  # flake8-comprehensions
+  "C4",
+  # pycodestyle
+  "E",
+  # Pyflakes errors
+  "F",
+  # isort
+  "I",
+  # flake8-simplify
+  "SIM",
+  # flake8-tidy-imports
+  "TID",
+  # pyupgrade
+  "UP",
+  # Pyflakes warnings
+  "W",
+]
+lint.ignore = [
+  # flake8-bugbear opinionated rules
+  "B9",
+  # line-too-long
+  "E501",
+  # suppressible-exception
+  "SIM105",
+  # if-else-block-instead-of-if-exp
+  "SIM108",
+]
 
 [build-system]
 build-backend = "poetry.core.masonry.api"

pyproject.toml

@@ -1,15 +1,4 @@
-# Flake8 does not yet support pyproject.toml.
-# Issue: https://gitlab.com/pycqa/flake8/-/issues/428
-
-[flake8]
-max-line-length = 79
-extend-ignore = E203, W503
-exclude = .git,__pycache__,docs/source/conf.py,old,build,dist,.eggs,.env,.venv
-
-# Neither does mypy, but this is in progress.
-# See:
-# - https://github.com/python/mypy/issues/5205
-# - https://github.com/python/mypy/pull/5208
+# Mypy configuration pending move to pyproject.toml
 
 [mypy]
 warn_return_any = True

setup.cfg

@@ -61,7 +61,7 @@
 
         if r.is_empty:  # do not rely on meaningful rects
             print(
-                "skipping text of empty rect at (%g, %g) on page %i"
+                "skipping text of empty rect at (%g, %g) on page %i"  # noqa: UP031
                 % (r.x0, r.y0, page1.number)
             )
         else:

tools/layout-analyzer.py

@@ -24,9 +24,9 @@ def inspect(file: Union[str, bytes, Path]) -> PdfRedactionsDict:
     :return: A dict with the bad redaction information. If no bad redactions
     are found, returns an empty dict.
     """
-    if type(file) == bytes:
+    if isinstance(file, bytes):
         pdf = Document(stream=file, filetype="pdf")
-    elif type(file) == str and file.startswith("https://"):
+    elif isinstance(file, str) and file.startswith("https://"):
         r = requests.get(file, timeout=10)
         r.raise_for_status()
         pdf = Document(stream=r.content, filetype="pdf")

xray/__init__.py

@@ -104,9 +104,9 @@ def intersects(
     else False.
     """
     for rect in rectangles + [text_rect]:
-        assert all(
-            [hasattr(rect, "seqno"), hasattr(rect, "fill")]
-        ), "Rectangle lacks required 'seqno' or 'fill' attribute."
+        assert all([hasattr(rect, "seqno"), hasattr(rect, "fill")]), (
+            "Rectangle lacks required 'seqno' or 'fill' attribute."
+        )
 
     overlapping_areas = []
     for rect in rectangles:
@@ -128,9 +128,7 @@ def intersects(
     area_of_bbox = abs(text_rect.get_area())
 
     percent_occluded = greatest_occluded / area_of_bbox
-    if percent_occluded > occlusion_threshold:
-        return True
-    return False
+    return percent_occluded > occlusion_threshold
 
 
 def get_intersecting_chars(

xray/pdf_utils.py

@@ -17,11 +17,8 @@ def is_repeated_chars(text: str) -> bool:
     if len(text) <= 1:
         return False
 
-    if len(set(text)) == 1:
-        # There's only one unique character in the string
-        return True
-
-    return False
+    # Return True if there's only one unique character in the string
+    return len(set(text)) == 1
 
 
 def is_ok_words(text: str) -> bool: