Class MultiCheckerFileProcessor

ci/util/check_files.py:151–229

Processor that can run multiple checkers on files. Caches file content across process_files_with_checkers() calls so that files read in one scope are not re-read when processed in another scope.

class MultiCheckerFileProcessor:
    """Processor that can run multiple checkers on files.

    Caches file content across process_files_with_checkers() calls so that
    files read in one scope are not re-read when processed in another scope.
    """

    def __init__(self):
        self._file_cache: dict[str, FileContent] = {}

    def _get_file_content(self, file_path: str) -> FileContent:
        """Read file content, using cache to avoid redundant I/O.

        Args:
            file_path: Path to the file to read

        Returns:
            Cached or freshly-read FileContent object

        Raises:
            OSError: If the file cannot be read
        """
        if file_path not in self._file_cache:
            with open(file_path, "r", encoding="utf-8") as f:
                content = f.read()
            self._file_cache[file_path] = FileContent(
                path=file_path, content=content, lines=content.splitlines()
            )
        return self._file_cache[file_path]

    def process_files_with_checkers(
        self, file_paths: list[str], checkers: list[FileContentChecker]
    ) -> dict[str, list[str]]:
        """Process files with multiple checkers.

        Args:
            file_paths: List of file paths to process
            checkers: List of checker instances to run on the files

        Returns:
            Dictionary mapping checker class name to list of issues found
        """
        # Initialize results dictionary for each checker
        results: dict[str, list[str]] = {}
        for checker in checkers:
            checker_name = checker.__class__.__name__
            results[checker_name] = []

        # Process each file
        for file_path in file_paths:
            # Check if any checker wants to process this file
            interested_checkers = [
                checker
                for checker in checkers
                if checker.should_process_file(file_path)
            ]

            # If any checker is interested, read the file once (or use cache)