Concatenate Text V2 (Additional debug output, better file handling)

concatenate-text-v2.py

import os
import mimetypes
import datetime

def is_text_file(file_path):
    # First, try using mimetypes
    mime_type, _ = mimetypes.guess_type(file_path)
    if mime_type and mime_type.startswith('text/'):
        return True
    
    # If mimetypes fails, check the file extension. Feel free to add more languages here
    text_extensions = {'.txt', '.md', '.mdx', '.py', '.js', '.html', '.css', '.json', '.xml', '.yml', '.yaml', '.go', '.rs', '.sol', '.sh', '.bat', '.ps1'}
    file_extension = os.path.splitext(file_path)[1].lower()
    return file_extension in text_extensions

# Specify the folder path containing the text files. Can be a relative or absolute path
folder_path = "/Users/your-username/path/goes/here"

# Specify the output file path
output_file = "concatenated_text.txt"

# Open the output file in write mode (this will overwrite the file if it exists)
with open(output_file, "w", encoding="utf-8") as outfile:
    # Write header information
    outfile.write(f"Concatenated Text File\n")
    outfile.write(f"Generated on: {datetime.datetime.now()}\n")
    outfile.write(f"Source folder: {folder_path}\n\n")
    outfile.write("=" * 80 + "\n\n")

    # Iterate over each directory and subdirectory using os.walk()
    for root, dirs, files in os.walk(folder_path):
        # Iterate over each file
        for file in files:
            file_path = os.path.join(root, file)
            
            # Debug output: Print the file path
            print(f"File: {file_path}")
            
            # Check if it's a text file using our custom function
            if is_text_file(file_path):
                print("Detected as text file. Processing...")
                # Open the text file in read mode
                try:
                    with open(file_path, "r", encoding="utf-8") as infile:
                        # Write the relative path to the file as a heading
                        relative_path = os.path.relpath(file_path, folder_path)
                        outfile.write(f"File: {relative_path}\n")
                        outfile.write(f"Full path: {file_path}\n")
                        outfile.write("-" * 80 + "\n\n")

                        # Write the contents of the text file to the output file
                        outfile.write(infile.read())

                        # Add a line break between files
                        outfile.write("\n\n" + "=" * 80 + "\n\n")
                except UnicodeDecodeError:
                    print(f"Error: Unable to read {file_path} as text. Skipping.")
            else:
                print("Not detected as text file. Skipping.")
            
            print("------------------------")

print("Concatenation complete. Output file:", output_file)