Description update based on File name.py

"""
=========================================================
Description to Filename Matcher for Wikimedia Commons
=========================================================
[ SETUP & USAGE ]
1. Install reqs: pip install pywikibot
2. Login config: Ensure 'user-config.py' is set up in your directory.
3. Purpose     : Extracts the filename (without extension) and 
                 replaces the existing English description 
                 (|description={{en|...}}) with that exact filename.
4. Run         : Set TARGET_CATEGORIES below, then run the script.
=========================================================
"""

import pywikibot
from pywikibot import pagegenerators
import re
import time

# ================= CONFIGURATION =================

# 1. Target Categories
# Add the exact names of the categories you want to process
TARGET_CATEGORIES = [
    'Category:YOUR_FIRST_CATEGORY_NAME_HERE',
    'Category:YOUR_SECOND_CATEGORY_NAME_HERE'
]

# 2. Advanced Controls
PROCESS_SUBCATEGORIES = False  # Set to True if you want to process folders inside the target category
SLEEP_TIME = 1                 # Seconds to pause after each successful edit
DRY_RUN = False                # Set to True to test regex replacements without saving to the Wiki

# =================================================

def main():
    try:
        site = pywikibot.Site('commons', 'commons')
        site.login()
        print(f"Logged in as: {site.user()}")
    except Exception as e:
        print(f"Login Failed: {e}")
        return

    # Loop through each category defined in the configuration
    for cat_name in TARGET_CATEGORIES:
        print(f"\n[{'DRY RUN' if DRY_RUN else 'LIVE'}] Processing Category: {cat_name}...")
        
        try:
            cat = pywikibot.Category(site, cat_name)
            gen = pagegenerators.CategorizedPageGenerator(cat, recurse=PROCESS_SUBCATEGORIES)
        except pywikibot.exceptions.InvalidTitleError:
            print(f"[ERROR] Invalid category name: {cat_name}")
            continue

        for page in gen:
            # Skip if the page is not an actual file (e.g., a subcategory or text page)
            if not page.is_filepage():
                continue

            current_text = page.text
            
            # Extract clean title by removing the namespace (File:) and extension (.svg, .png)
            # Example: "File:Noto Serif Sinhala.svg" -> "Noto Serif Sinhala"
            file_title_full = page.title(with_ns=False)
            clean_title = file_title_full.rsplit('.', 1)[0]

            # Regex Explanation:
            # Group 1 (\1): Matches the exact string "|description = {{en|" (including spaces)
            # Group 2 (\2): Matches the existing content inside (lazy match)
            # Group 3 (\3): Matches the closing "}}"
            pattern = r'(\|description\s*=\s*\{\{en\|)(.*?)(\}\})'

            # Search for the specific Information template pattern
            if re.search(pattern, current_text):
                
                # Reconstruct the string: Keep Group 1 + Insert Clean Title + Keep Group 3
                new_text = re.sub(pattern, r'\1' + clean_title + r'\3', current_text)

                # Only proceed if a modification is actually needed
                if new_text != current_text:
                    if DRY_RUN:
                        print(f"[-] DRY RUN: Would have updated description of '{file_title_full}' to '{clean_title}'")
                        continue
                    
                    print(f"[\u2713] Updating: {file_title_full}")
                    print(f"    New Description: {clean_title}")
                    
                    page.text = new_text
                    try:
                        # Save the changes to the Wiki
                        edit_summary = f"Updated description to match filename: {clean_title}"
                        page.save(summary=edit_summary)
                        
                        # Respect server load
                        time.sleep(SLEEP_TIME)
                        
                    except pywikibot.exceptions.LockedPageError:
                        print(f"[SKIP] Page is locked: {file_title_full}")
                    except pywikibot.exceptions.OtherPageSaveError as e:
                        print(f"[ERROR] Saving {file_title_full} failed: {e}")
                    except Exception as e:
                        print(f"[ERROR] Generic error on {file_title_full}: {e}")
                else:
                    # Skip if the description is already identical to the filename
                    print(f"[SKIP] {file_title_full} (Description already matches)")
            else:
                # Skip if no description template (in English) is found
                print(f"[SKIP] {file_title_full} (Pattern |description={{en|...}} not found)")

    if DRY_RUN:
        print("\n\u2705 DRY RUN complete. No files were modified.")
    else:
        print("\n\u2705 Batch processing completed across all categories.")

if __name__ == '__main__':
    main()