Method process_batch

paper2slides/raganything/batch_parser.py:201–317

Process multiple files in parallel Args: file_paths: List of file paths or directories to process output_dir: Base output directory parse_method: Parsing method for all files recursive: Whether to search directories recursively

(
        self,
        file_paths: List[str],
        output_dir: str,
        parse_method: str = "auto",
        recursive: bool = True,
        **kwargs,
    )

            return False, file_path, error_msg

    def process_batch(
        self,
        file_paths: List[str],
        output_dir: str,
        parse_method: str = "auto",
        recursive: bool = True,
        **kwargs,
    ) -> BatchProcessingResult:
        """
        Process multiple files in parallel

        Args:
            file_paths: List of file paths or directories to process
            output_dir: Base output directory
            parse_method: Parsing method for all files
            recursive: Whether to search directories recursively
            **kwargs: Additional parser arguments

        Returns:
            BatchProcessingResult with processing statistics
        """
        start_time = time.time()

        # Filter to supported files
        supported_files = self.filter_supported_files(file_paths, recursive)

        if not supported_files:
            self.logger.warning("No supported files found to process")
            return BatchProcessingResult(
                successful_files=[],
                failed_files=[],
                total_files=0,
                processing_time=0.0,
                errors={},
                output_dir=output_dir,
            )

        self.logger.info(f"Found {len(supported_files)} files to process")

        # Create output directory
        output_path = Path(output_dir)
        output_path.mkdir(parents=True, exist_ok=True)

        # Process files in parallel
        successful_files = []
        failed_files = []
        errors = {}

        # Create progress bar if requested
        pbar = None
        if self.show_progress:
            pbar = tqdm(
                total=len(supported_files),
                desc=f"Processing files ({self.parser_type})",
                unit="file",
            )

        try: