Ruff processors #32

ulgens · 2026-01-03T00:25:51Z

No description provided.

codecov · 2026-01-03T00:26:41Z

❌ 2 Tests Failed:

Tests completed	Failed	Passed	Skipped
76	2	74	0

View the top 2 failed test(s) by shortest run time

tests/test_ruffen_docs.py::test_integration_modifies

Stack Traces | 0.004s run time

tmp_path = PosixPath('.../pytest-of-runner/pytest-0/test_integration_modifies0')
capsys = <_pytest.capture.CaptureFixture object at 0x7f5fc2eeab60>

    def test_integration_modifies(tmp_path, capsys):
        f = tmp_path / "f.md"
        f.write_text(
            "```python\nf(1,2,3)\n```\n",
        )
    
        result = run_black((str(f),))
    
        assert result == 1
        out, _ = capsys.readouterr()
>       assert out == f"{f}: Rewriting...\n"
E       AssertionError: assert '/tmp/pytest-...ewriting...\n' == '/tmp/pytest-...ewriting...\n'
E         
E         Skipping 52 identical leading characters in diff, use -v to show
E         - fies0/f.md: Rewriting...
E         + fies0/f.md
E         + .../pytest-of-runner/pytest-0/test_integration_modifies0/f.md: Rewriting...

tests/test_ruffen_docs.py:904: AssertionError

tests/test_ruffen_docs.py::test_integration_syntax_error

Stack Traces | 0.005s run time

tmp_path = PosixPath('.../pytest-of-runner/pytest-0/test_integration_syntax_error0')
capsys = <_pytest.capture.CaptureFixture object at 0x7f5fc3181690>

    def test_integration_syntax_error(tmp_path, capsys):
        f = tmp_path / "f.md"
        f.write_text(
            "```python\nf(\n```\n",
        )
    
        result = run_black((str(f),))
    
        assert result == 2
        out, _ = capsys.readouterr()
>       assert out.startswith(f"{f}:1: code block parse error")
E       AssertionError: assert False
E        +  where False = <built-in method startswith of str object at 0x7f5fc3062ef0>('.../pytest-of-runner/pytest-0/test_integration_syntax_error0/f.md:1: code block parse error')
E        +    where <built-in method startswith of str object at 0x7f5fc3062ef0> = '.../pytest-of-runner/pytest-0/test_integration_syntax_error0/f.md\n.../pytest-of-runner/pytest-0/test_integration_syntax_error0/f.md:1: code block parse error Cannot parse: 1:2: Unexpected EOF in multi-line statement\n'.startswith

tests/test_ruffen_docs.py:1106: AssertionError

To view more test analytics, go to the Test Analytics Dashboard
_{📋 Got 3 mins? Take this short survey to help us improve Test Analytics.}

Copilot

Pull request overview

This PR adds Ruff support to ruffen-docs by introducing two new processor classes (RuffChecker and RuffFormatter) alongside the existing BlackFormatter. The module is renamed from formatters to processors to better reflect its expanded purpose.

Key Changes:

Added RuffChecker and RuffFormatter processor classes that use subprocess to call ruff commands
Renamed module from formatters to processors and updated imports
Added two new pre-commit hooks: ruffen-docs-check and ruffen-docs-format

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
`src/ruffen_docs/processors.py`	Added subprocess import, ruff.main import, and two new processor classes (RuffChecker and RuffFormatter)
`src/ruffen_docs/__init__.py`	Updated import to use processors module instead of formatters
`tests/test_ruffen_docs.py`	Updated import to use processors module instead of formatters
`.pre-commit-config.yaml`	Added two new pre-commit hooks for ruffen-docs-check and ruffen-docs-format with ruff 0.14.10 dependency

Comments suppressed due to low confidence (6)

src/ruffen_docs/processors.py:364

The commented out check=True parameter should either be removed or uncommented with proper error handling. If check=True is uncommented, subprocess.run will raise CalledProcessError automatically on non-zero exit, making the subsequent check_returncode() call redundant. Currently, using check_returncode() separately is correct, but the commented code creates ambiguity about the intended approach.
src/ruffen_docs/processors.py:337
The init methods in both RuffChecker and RuffFormatter are redundant as they only call super().init() without adding any initialization logic. These methods can be removed to simplify the code.
src/ruffen_docs/processors.py:355
The init methods in both RuffChecker and RuffFormatter are redundant as they only call super().init() without adding any initialization logic. These methods can be removed to simplify the code.
src/ruffen_docs/processors.py:350
The RuffChecker.process_code_block method returns result.stdout, but ruff check does not output the formatted code to stdout - it outputs diagnostic messages. The process_code_block method should return the original code_block unchanged since ruff check is meant to validate, not transform the code. This is a fundamental difference from ruff format which actually outputs the formatted code.
src/ruffen_docs/processors.py:368
The newly added RuffChecker and RuffFormatter classes lack test coverage. Since the existing BlackFormatter has comprehensive test coverage (as seen in tests/test_ruffen_docs.py with numerous test functions), these new processor classes should also have corresponding tests to verify their behavior with various code block formats (markdown, RST, pycon, etc.).
src/ruffen_docs/processors.py:346
The commented out check=True parameter should either be removed or uncommented with proper error handling. If check=True is uncommented, subprocess.run will raise CalledProcessError automatically on non-zero exit, making the subsequent check_returncode() call redundant. Currently, using check_returncode() separately is correct, but the commented code creates ambiguity about the intended approach.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

"formatter" is not the best term to cover ruff's "check" and "format" behaviour together

Copilot

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated 7 comments.

Comments suppressed due to low confidence (6)

src/ruffen_docs/processors.py:368

The new RuffChecker and RuffFormatter classes lack test coverage. Similar tests should be added for these new processors, following the same pattern as the existing BlackFormatter tests in this file.
src/ruffen_docs/processors.py:348
The subprocess call does not specify a timeout parameter, which could cause the process to hang indefinitely if ruff encounters an issue. Consider adding a timeout to prevent the process from blocking forever.
src/ruffen_docs/processors.py:349
Calling check_returncode() will raise a CalledProcessError when ruff check finds linting violations (non-zero exit code), which will be caught by the _collect_error context manager and treated as a processing error. For a checker, this is incorrect behavior - finding linting violations should not be treated as a processing error. The method should handle the return code appropriately and return the original code_block unchanged.
src/ruffen_docs/processors.py:350
The RuffChecker.process_code_block method returns result.stdout, but ruff check typically outputs diagnostics to stderr and returns an empty stdout for valid code. This will likely return an empty string even when the check passes, which may not be the intended behavior. Consider returning the original code_block when the check passes, or handle the output differently.
src/ruffen_docs/processors.py:366
The subprocess call does not specify a timeout parameter, which could cause the process to hang indefinitely if ruff encounters an issue. Consider adding a timeout to prevent the process from blocking forever.
src/ruffen_docs/processors.py:364
These commented-out lines should either be removed if they're not needed, or uncommented and implemented if they are. Leaving commented code in the codebase reduces clarity about what the intended behavior should be.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-01-03T10:27:08Z

src/ruffen_docs/__init__.py


    retv = 0
    for filename in args.filenames:
+        print(filename)


This debug print statement should be removed. It appears to have been added during development and will output filenames to stdout during normal operation, which could interfere with the tool's output and usage in automated environments.

Suggested change

print(filename)

Copilot · 2026-01-03T10:27:08Z

src/ruffen_docs/__init__.py

+    filenames = []
+
+    retv = 0
+
+    for filename in filenames:


The filenames list is initialized as empty but is never populated with args.filenames. This means the loop will never execute, and no files will be processed. You should use args.filenames directly in the loop, similar to how run_check and run_black are implemented.

Suggested change

filenames = []

retv = 0

for filename in filenames:

retv = 0

for filename in args.filenames:

Copilot · 2026-01-03T10:27:09Z

src/ruffen_docs/__init__.py

+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-l",
+        "--line-length",
+        type=int,
+        default=DEFAULT_LINE_LENGTH,
+    )
+    parser.add_argument(
+        "-S",
+        "--skip-string-normalization",
+        action="store_true",
+    )
+    parser.add_argument("-E", "--skip-errors", action="store_true")
+    parser.add_argument("filenames", nargs="*")
+    args = parser.parse_args(argv)


The run_check and run_format functions accept line-length and skip-string-normalization arguments that are parsed but never used. These parameters should either be passed to the RuffChecker and RuffFormatter constructors (if they support configuration), or the argument parsing should be removed to avoid misleading users.

Copilot · 2026-01-03T10:27:09Z

src/ruffen_docs/__init__.py

+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-l",
+        "--line-length",
+        type=int,
+        default=DEFAULT_LINE_LENGTH,
+    )
+    parser.add_argument(
+        "-S",
+        "--skip-string-normalization",
+        action="store_true",
+    )
+    parser.add_argument("-E", "--skip-errors", action="store_true")
+    parser.add_argument("filenames", nargs="*")
+    args = parser.parse_args(argv)
+
+    retv = 0
+
+    for filename in args.filenames:
+        formatter = RuffChecker()
+        retv |= formatter.format_file(
+            filename,
+            skip_errors=args.skip_errors,
+            # rst_literal_blocks=args.rst_literal_blocks,
+            # check_only=args.check,
+        )
+
+    return retv


 def run_format(argv: Sequence[str] | None = None) -> int:
-    ...
-    return 1
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-l",
+        "--line-length",
+        type=int,
+        default=DEFAULT_LINE_LENGTH,
+    )
+    parser.add_argument(
+        "-S",
+        "--skip-string-normalization",
+        action="store_true",
+    )
+    parser.add_argument("-E", "--skip-errors", action="store_true")
+    parser.add_argument("filenames", nargs="*")
+    args = parser.parse_args(argv)


The argument parsing code in run_check and run_format is largely duplicated from run_black. Consider extracting this into a shared helper function to reduce code duplication and improve maintainability.

Copilot · 2026-01-03T10:27:09Z

src/ruffen_docs/__init__.py

+            # rst_literal_blocks=args.rst_literal_blocks,
+            # check_only=args.check,
+        )


These commented-out lines should either be removed if they're not needed, or uncommented and implemented if they are. Leaving commented code in the codebase reduces clarity about what the intended behavior should be.

Copilot · 2026-01-03T10:27:09Z

src/ruffen_docs/__init__.py

+        formatter = RuffChecker()
+        retv |= formatter.format_file(


The variable name 'formatter' is misleading when the instance is actually a RuffChecker, not a formatter. Consider renaming to 'checker' for clarity and consistency with the class name.

Suggested change

formatter = RuffChecker()

retv |= formatter.format_file(

checker = RuffChecker()

retv |= checker.format_file(

Copilot · 2026-01-03T10:27:09Z

src/ruffen_docs/__init__.py

+            # rst_literal_blocks=args.rst_literal_blocks,
+            # check_only=args.check,
+        )


These commented-out lines should either be removed if they're not needed, or uncommented and implemented if they are. Leaving commented code in the codebase reduces clarity about what the intended behavior should be.

ulgens requested a review from Copilot January 3, 2026 00:25

Copilot started reviewing on behalf of ulgens January 3, 2026 00:26 View session

Copilot AI reviewed Jan 3, 2026

View reviewed changes

ulgens added 3 commits January 3, 2026 03:52

Rename file

2a9d3a5

"formatter" is not the best term to cover ruff's "check" and "format" behaviour together

Add ruff processors

5221ec5

Dump

fbb9e4d

ulgens force-pushed the ruff-processors branch from ed011b3 to fbb9e4d Compare January 3, 2026 10:07

ulgens requested a review from Copilot January 3, 2026 10:23

Copilot started reviewing on behalf of ulgens January 3, 2026 10:24 View session

Copilot AI reviewed Jan 3, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Ruff processors #32

Ruff processors #32

Uh oh!

ulgens commented Jan 3, 2026

Uh oh!

codecov bot commented Jan 3, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Jan 3, 2026

Uh oh!

Copilot AI Jan 3, 2026

Uh oh!

Copilot AI Jan 3, 2026

Uh oh!

Copilot AI Jan 3, 2026

Uh oh!

Copilot AI Jan 3, 2026

Uh oh!

Copilot AI Jan 3, 2026

Uh oh!

Copilot AI Jan 3, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Ruff processors #32

Are you sure you want to change the base?

Ruff processors #32

Uh oh!

Conversation

ulgens commented Jan 3, 2026

Uh oh!

codecov bot commented Jan 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

❌ 2 Tests Failed:

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Jan 3, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 3, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 3, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 3, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 3, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 3, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 3, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

codecov bot commented Jan 3, 2026 •

edited

Loading