Fix ChatGPT hyphens and spaces

clean_text.py

#!/usr/bin/env -S uv --quiet run --script
# /// script
# requires-python = ">=3.11"
# dependencies = [
#     "typer",
# ]
# ///
"""
Clean Text: Unicode Hyphen and Space Normalizer

This utility normalizes "bad" Unicode hyphens and non-breaking spaces in text files.

Purpose:
    - Converts various Unicode hyphens (U+00AD, U+2010-U+2015, U+2212) to standard ASCII hyphens (-)
    - Converts various non-breaking spaces (U+00A0, U+202F, U+2007) to standard spaces
    - Scans directories recursively for specified file types
    - Reports only files that were actually changed
    - Shows detailed statistics about replaced characters

Usage:
    clean_text.py [OPTIONS] PATHS...
    
    PATHS: One or more directories to search for files
    
Options:
    -e, --ext TEXT  File extensions to process (defaults to py, md, markdown)
    --help          Show help message and exit

Examples:
    # Process Python and Markdown files in multiple directories
    clean_text.py ./docs/ ./src/ ./tests/
    
    # Process specific file types in a single directory
    clean_text.py ./content/ -e html -e txt -e rst
    
Exit Status:
    0 - Success (files processed without errors)
    1 - Error (invalid path or file operations failed)

Author: Ian Maurer
Version: 0.1
License: MIT
"""


import re
from pathlib import Path
from typing import List

import typer


def main(
    paths: List[str] = typer.Argument(..., help="Directories to search for files"),
    extensions: List[str] = typer.Option(
        ["py", "md", "markdown"], "--ext", "-e", help="File extensions to process"
    ),
):
    """
    Clean up bad hyphens and non-breaking spaces in text files.

    Replaces Unicode hyphens with standard ASCII hyphens.
    Replaces non-breaking spaces with regular spaces.
    Only reports files that were actually changed.
    """
    # Compile regex patterns
    hyphen_pattern = re.compile(r"[\u00AD\u2010-\u2015\u2212]")
    space_pattern = re.compile(r"[\u00A0\u202F\u2007]")

    # Set of valid extensions
    valid_exts = set(f".{ext}" for ext in extensions)

    # Count of total files changed
    total_files_changed = 0

    # Process each directory
    for path_str in paths:
        path = Path(path_str)
        if not path.exists():
            typer.echo(f"Warning: Path '{path}' does not exist. Skipping.", err=True)
            continue

        # Find all files with the specified extensions
        for file_path in path.glob("**/*"):
            if file_path.is_file() and file_path.suffix in valid_exts:
                # Read the file
                try:
                    with open(file_path, "r", encoding="utf-8") as f:
                        content = f.read()
                except Exception as e:
                    typer.echo(f"Error reading {file_path}: {e}", err=True)
                    continue

                # Apply replacements
                new_content, hyphen_count = hyphen_pattern.subn("-", content)
                new_content, space_count = space_pattern.subn(" ", new_content)

                # Total changes
                total_changes = hyphen_count + space_count

                # If changes were made, write back to file
                if total_changes > 0:
                    try:
                        with open(file_path, "w", encoding="utf-8") as f:
                            f.write(new_content)
                        typer.echo(
                            f"Modified: {file_path} ({total_changes} replacements: {hyphen_count} hyphens, {space_count} spaces)"
                        )
                        total_files_changed += 1
                    except Exception as e:
                        typer.echo(f"Error writing {file_path}: {e}", err=True)

    # Print summary
    if total_files_changed > 0:
        typer.echo(f"\nTotal files modified: {total_files_changed}")
    else:
        typer.echo("No files were modified.")


if __name__ == "__main__":
    typer.run(main)