Add standalone CLI converters

Readme.md

@@ -224,6 +224,7 @@ client.process(
     markdown_output=True
 )
 
+```python
 # Process citation lists
 client.process(
     service="processCitationList",
@@ -232,6 +233,32 @@ client.process(
 )
 ```
 
+### Standalone Conversion Tools
+
+The library includes standalone scripts to convert TEI XML files to other formats without using the main client or server.
+
+#### TEI to JSON Converter
+
+Converts TEI XML files to the structured JSON format (similar to `--json` option).
+
+```bash
+# Convert a single file
+python -m grobid_client.format.TEI2LossyJSON_cli --input path/to/file.tei.xml --output path/to/output.json
+
+# Convert with verbose logging
+python -m grobid_client.format.TEI2LossyJSON_cli --input path/to/file.tei.xml --verbose
+```
+
+#### TEI to Markdown Converter
+
+Converts TEI XML files to Markdown format (similar to `--markdown` option).
+
+```bash
+# Convert a single file
+python -m grobid_client.format.TEI2Markdown_cli --input path/to/file.tei.xml --output path/to/output.md
+```
+
+
 ## ⚙️ Configuration
 
 Configuration can be provided via a JSON file. When using the CLI, the `--server` argument overrides the config file

grobid_client/format/TEI2LossyJSON_cli.py

@@ -0,0 +1,131 @@
+#!/usr/bin/env python3
+"""
+Standalone CLI for TEI2LossyJSON converter.
+
+This script provides a command-line interface for converting TEI XML files to JSON format
+using the TEI2LossyJSONConverter.
+"""
+import argparse
+import json
+import logging
+import sys
+from pathlib import Path
+
+from .TEI2LossyJSON import TEI2LossyJSONConverter
+
+
+def setup_logging(verbose: bool = False):
+    """Setup logging configuration."""
+    level = logging.INFO if verbose else logging.WARNING
+    logging.basicConfig(
+        level=level,
+        format='%(asctime)s - %(levelname)s - %(message)s',
+        datefmt='%Y-%m-%d %H:%M:%S'
+    )
+
+
+def convert_single_file(input_file: Path, output_file: Path, verbose: bool = False) -> bool:
+    """Convert a single TEI file to JSON format."""
+    try:
+        if verbose:
+            logging.info(f"Converting {input_file} to {output_file}")
+
+        converter = TEI2LossyJSONConverter()
+        result = converter.convert_tei_file(input_file, stream=False)
+
+        if result is None:
+            logging.error(f"Failed to convert {input_file}: TEI file is not well-formed or empty")
+            return False
+
+        # Ensure output directory exists
+        output_file.parent.mkdir(parents=True, exist_ok=True)
+
+        # Write JSON output
+        with open(output_file, 'w', encoding='utf-8') as f:
+            json.dump(result, f, indent=2, ensure_ascii=False)
+
+        if verbose:
+            logging.info(f"Successfully converted {input_file} to {output_file}")
+
+        return True
+
+    except Exception as e:
+        logging.error(f"Error converting {input_file}: {str(e)}")
+        return False
+
+
+def main():
+    """Main CLI entry point."""
+    parser = argparse.ArgumentParser(
+        description="Convert TEI XML files to JSON format using TEI2LossyJSON converter",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Convert a single TEI file
+  python -m grobid_client.format.TEI2LossyJSON --input input.tei.xml --output output.json
+
+  # Convert with verbose logging
+  python -m grobid_client.format.TEI2LossyJSON --input input.tei.xml --output output.json --verbose
+
+  # Convert and output to stdout
+  python -m grobid_client.format.TEI2LossyJSON --input input.tei.xml
+        """
+    )
+
+    parser.add_argument(
+        "--input", "-i",
+        type=Path,
+        required=True,
+        help="Input TEI XML file to convert"
+    )
+
+    parser.add_argument(
+        "--output", "-o",
+        type=Path,
+        help="Output JSON file (if not specified, prints to stdout)"
+    )
+
+    parser.add_argument(
+        "--verbose", "-v",
+        action="store_true",
+        help="Enable verbose logging"
+    )
+
+    args = parser.parse_args()
+
+    # Setup logging
+    setup_logging(args.verbose)
+
+    # Validate input file
+    if not args.input.exists():
+        logging.error(f"Input file does not exist: {args.input}")
+        sys.exit(1)
+
+    if not args.input.is_file():
+        logging.error(f"Input path is not a file: {args.input}")
+        sys.exit(1)
+
+    # Convert the file
+    if args.output:
+        success = convert_single_file(args.input, args.output, args.verbose)
+        sys.exit(0 if success else 1)
+    else:
+        # Output to stdout
+        try:
+            converter = TEI2LossyJSONConverter()
+            result = converter.convert_tei_file(args.input, stream=False)
+
+            if result is None:
+                logging.error(f"Failed to convert {args.input}: TEI file is not well-formed or empty")
+                sys.exit(1)
+
+            # Print JSON to stdout
+            print(json.dumps(result, indent=2, ensure_ascii=False))
+
+        except Exception as e:
+            logging.error(f"Error converting {args.input}: {str(e)}")
+            sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

grobid_client/format/TEI2Markdown_cli.py

@@ -0,0 +1,130 @@
+#!/usr/bin/env python3
+"""
+Standalone CLI for TEI2Markdown converter.
+
+This script provides a command-line interface for converting TEI XML files to Markdown format
+using the TEI2MarkdownConverter.
+"""
+import argparse
+import logging
+import sys
+from pathlib import Path
+
+from .TEI2Markdown import TEI2MarkdownConverter
+
+
+def setup_logging(verbose: bool = False):
+    """Setup logging configuration."""
+    level = logging.INFO if verbose else logging.WARNING
+    logging.basicConfig(
+        level=level,
+        format='%(asctime)s - %(levelname)s - %(message)s',
+        datefmt='%Y-%m-%d %H:%M:%S'
+    )
+
+
+def convert_single_file(input_file: Path, output_file: Path, verbose: bool = False) -> bool:
+    """Convert a single TEI file to Markdown format."""
+    try:
+        if verbose:
+            logging.info(f"Converting {input_file} to {output_file}")
+
+        converter = TEI2MarkdownConverter()
+        result = converter.convert_tei_file(input_file)
+
+        if result is None:
+            logging.error(f"Failed to convert {input_file}: TEI file is not well-formed or empty")
+            return False
+
+        # Ensure output directory exists
+        output_file.parent.mkdir(parents=True, exist_ok=True)
+
+        # Write Markdown output
+        with open(output_file, 'w', encoding='utf-8') as f:
+            f.write(result)
+
+        if verbose:
+            logging.info(f"Successfully converted {input_file} to {output_file}")
+
+        return True
+
+    except Exception as e:
+        logging.error(f"Error converting {input_file}: {str(e)}")
+        return False
+
+
+def main():
+    """Main CLI entry point."""
+    parser = argparse.ArgumentParser(
+        description="Convert TEI XML files to Markdown format using TEI2Markdown converter",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Convert a single TEI file
+  python -m grobid_client.format.TEI2Markdown --input input.tei.xml --output output.md
+
+  # Convert with verbose logging
+  python -m grobid_client.format.TEI2Markdown --input input.tei.xml --output output.md --verbose
+
+  # Convert and output to stdout
+  python -m grobid_client.format.TEI2Markdown --input input.tei.xml
+        """
+    )
+
+    parser.add_argument(
+        "--input", "-i",
+        type=Path,
+        required=True,
+        help="Input TEI XML file to convert"
+    )
+
+    parser.add_argument(
+        "--output", "-o",
+        type=Path,
+        help="Output Markdown file (if not specified, prints to stdout)"
+    )
+
+    parser.add_argument(
+        "--verbose", "-v",
+        action="store_true",
+        help="Enable verbose logging"
+    )
+
+    args = parser.parse_args()
+
+    # Setup logging
+    setup_logging(args.verbose)
+
+    # Validate input file
+    if not args.input.exists():
+        logging.error(f"Input file does not exist: {args.input}")
+        sys.exit(1)
+
+    if not args.input.is_file():
+        logging.error(f"Input path is not a file: {args.input}")
+        sys.exit(1)
+
+    # Convert the file
+    if args.output:
+        success = convert_single_file(args.input, args.output, args.verbose)
+        sys.exit(0 if success else 1)
+    else:
+        # Output to stdout
+        try:
+            converter = TEI2MarkdownConverter()
+            result = converter.convert_tei_file(args.input)
+
+            if result is None:
+                logging.error(f"Failed to convert {args.input}: TEI file is not well-formed or empty")
+                sys.exit(1)
+
+            # Print Markdown to stdout
+            print(result)
+
+        except Exception as e:
+            logging.error(f"Error converting {args.input}: {str(e)}")
+            sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

grobid_client/format/__main__.py

@@ -0,0 +1,48 @@
+"""
+Package entry point for format converters.
+
+This provides a menu to choose between TEI2LossyJSON and TEI2Markdown converters.
+"""
+import argparse
+import sys
+
+
+def main():
+    """Main entry point that provides a menu for converter selection."""
+
+    # Check if a converter was specified
+    if len(sys.argv) < 2:
+        print("GROBID format converters - Choose a converter to run")
+        print("\nUsage:")
+        print("  python -m grobid_client.format <converter> [options]")
+        print("\nAvailable converters:")
+        print("  TEI2LossyJSON  - Convert TEI XML to JSON format")
+        print("  TEI2Markdown   - Convert TEI XML to Markdown format")
+        print("\nExamples:")
+        print("  python -m grobid_client.format TEI2LossyJSON --input file.tei.xml --output output.json")
+        print("  python -m grobid_client.format TEI2Markdown --input file.tei.xml --output output.md")
+        print("\nGet help for specific converter:")
+        print("  python -m grobid_client.format TEI2LossyJSON --help")
+        print("  python -m grobid_client.format TEI2Markdown --help")
+        sys.exit(1)
+
+    converter = sys.argv[1]
+
+    if converter == "TEI2LossyJSON":
+        from .TEI2LossyJSON_cli import main as lossy_main
+        # Replace sys.argv to pass remaining args to the converter
+        sys.argv = ["TEI2LossyJSON"] + sys.argv[2:]
+        lossy_main()
+    elif converter == "TEI2Markdown":
+        from .TEI2Markdown_cli import main as markdown_main
+        # Replace sys.argv to pass remaining args to the converter
+        sys.argv = ["TEI2Markdown"] + sys.argv[2:]
+        markdown_main()
+    else:
+        print(f"Unknown converter: {converter}")
+        print("Available converters: TEI2LossyJSON, TEI2Markdown")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()