initial commit with WIP claude code in src

config.yaml

@@ -0,0 +1,13 @@
+max_workers: 4
+batch_size: 10
+timeout: 300
+retry_count: 3
+
+ocr:
+  language: eng
+  psm: 3
+  oem: 3
+  char_whitelist: abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
+  additional_params:
+    preserve_interword_spaces: 1
+    textord_heavy_nr: 1

output/corrections/1000_WinningTheGeneticLottery_corrections.json

@@ -0,0 +1,5 @@
+{
+  "document": "input/1000_WinningTheGeneticLottery.pdf",
+  "timestamp": "2024-12-01T06:44:09.284220",
+  "corrections": {}
+}

output/ocr_results/1000_WinningTheGeneticLottery_ocr_results.json

@@ -0,0 +1,32 @@
+{
+  "0": {
+    "status": "success",
+    "corrections": [],
+    "confidence": 3.0
+  },
+  "1": {
+    "status": "success",
+    "corrections": [],
+    "confidence": 0
+  },
+  "2": {
+    "status": "success",
+    "corrections": [],
+    "confidence": 19.5
+  },
+  "3": {
+    "status": "success",
+    "corrections": [],
+    "confidence": 43.8955223880597
+  },
+  "4": {
+    "status": "success",
+    "corrections": [],
+    "confidence": 46.30434782608695
+  },
+  "5": {
+    "status": "success",
+    "corrections": [],
+    "confidence": 39.833333333333336
+  }
+}

requirements.txt

@@ -0,0 +1,9 @@
+PyMuPDF==1.23.7  # For PDF processing
+numpy>=1.21.0
+pandas>=1.3.0
+pytesseract>=0.3.8
+opencv-python>=4.5.0
+Pillow>=8.0.0
+pdf2image>=1.16.0
+tqdm>=4.62.0
+pyyaml>=5.4.0

setup.py

@@ -0,0 +1,8 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="accessibility_checker",
+    version="0.1",
+    packages=find_packages(),
+    package_dir={'': 'src'},
+)

src/accessibility_checker.egg-info/PKG-INFO

@@ -0,0 +1,3 @@
+Metadata-Version: 2.1
+Name: accessibility_checker
+Version: 0.1

src/accessibility_checker.egg-info/SOURCES.txt

@@ -0,0 +1,5 @@
+setup.py
+src/accessibility_checker.egg-info/PKG-INFO
+src/accessibility_checker.egg-info/SOURCES.txt
+src/accessibility_checker.egg-info/dependency_links.txt
+src/accessibility_checker.egg-info/top_level.txt

src/accessibility_checker.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

src/accessibility_checker.egg-info/top_level.txt

@@ -0,0 +1 @@
+

src/main.py

@@ -0,0 +1,142 @@
+from pathlib import Path
+import argparse
+import yaml
+import logging
+from datetime import datetime
+import sys
+
+# Add the src directory to Python path
+sys.path.append(str(Path(__file__).parent))
+
+from processor.batch import BatchPDFProcessor
+from processor.accessibility import AccessibilityDocumentProcessor
+from processor.enhance import EnhancedAccessibilityChecker
+from processor.retry import RetryHandler, RetryConfig, ProcessingError, OCRError, OCRTimeoutError
+from processor.ocr import OCRProcessor
+from processor.config import ConfigurationManager
+
+def setup_logging(log_dir: Path) -> None:
+    """Set up logging configuration."""
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    log_file = log_dir / f"accessibility_checker_{timestamp}.log"
+
+    logging.basicConfig(
+        level=logging.INFO,
+        format='%(asctime)s - %(levelname)s - %(message)s',
+        handlers=[
+            logging.FileHandler(log_file),
+            logging.StreamHandler()
+        ]
+    )
+
+def parse_arguments():
+    """Parse command line arguments."""
+    parser = argparse.ArgumentParser(description='PDF Accessibility Checker')
+
+    parser.add_argument(
+        '--input-dir',
+        type=str,
+        required=True,
+        help='Directory containing PDF files to process'
+    )
+
+    parser.add_argument(
+        '--output-dir',
+        type=str,
+        required=True,
+        help='Directory for output files and reports'
+    )
+
+    parser.add_argument(
+        '--config',
+        type=str,
+        default='config.yaml',
+        help='Path to configuration file'
+    )
+
+    parser.add_argument(
+        '--workers',
+        type=int,
+        help='Number of worker processes (overrides config file)'
+    )
+
+    parser.add_argument(
+        '--ocr-timeout',
+        type=int,
+        default=30,
+        help='Timeout in seconds for OCR processing'
+    )
+
+    return parser.parse_args()
+
+def main():
+    # Parse command line arguments
+    args = parse_arguments()
+
+    # Create output directory structure
+    output_dir = Path(args.output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    # Set up logging
+    log_dir = output_dir / "logs"
+    log_dir.mkdir(exist_ok=True)
+    setup_logging(log_dir)
+
+    try:
+        # Load configuration
+        logging.info(f"Loading configuration from {args.config}")
+        config_manager = ConfigurationManager(args.config)
+        processing_config = config_manager.get_processing_config()
+
+        # Override max_workers if specified in command line arguments
+        if args.workers:
+            processing_config.max_workers = args.workers
+
+        # Initialize processors with retry capability
+        retry_handler = RetryHandler(RetryConfig(
+            max_attempts=processing_config.retry_count,
+            base_delay=2.0,
+            max_delay=30.0,
+            jitter=True
+        ))
+
+        # Initialize OCR processor with retry and timeout
+        ocr_processor = OCRProcessor(
+            config=processing_config.ocr_settings,
+            retry_handler=retry_handler,
+            timeout=30
+        )
+
+        # Initialize batch processor with OCR capability
+        processor = BatchPDFProcessor(
+            input_dir=args.input_dir,
+            output_dir=args.output_dir,
+            max_workers=processing_config.max_workers,
+            ocr_processor=ocr_processor,
+            retry_handler=retry_handler
+        )
+
+        # Process files
+        logging.info("Starting batch processing")
+        summary_df = processor.process_directory()
+
+        # Print processing summary
+        success_count = sum(summary_df['status'] == 'success')
+        failed_count = sum(summary_df['status'] == 'failed')
+        ocr_count = sum(summary_df.get('ocr_applied', False))
+
+        print("\nProcessing Summary:")
+        print(f"Total files processed: {len(summary_df)}")
+        print(f"Successfully processed: {success_count}")
+        print(f"Failed: {failed_count}")
+        print(f"OCR applied: {ocr_count}")
+        print(f"\nOutput files located in: {args.output_dir}")
+
+        logging.info("Processing completed successfully")
+
+    except Exception as e:
+        logging.error(f"Error in main process: {str(e)}", exc_info=True)
+        raise
+
+if __name__ == "__main__":
+    main()