Tax File Renamer

import os
import fitz
from datetime import datetime

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
LOG_FILE = os.path.join(BASE_DIR, "skipped_files_log.txt")

rename_mapping = {
    "formw2": ("0010", "W-2"),
    "w2statement": ("0010", "W-2"),
    "w2g": ("0015", "W-2G"),
    "ssa1099": ("0030", "SSA"),
    "form1099r": ("0020", "1099-R"),
    "1099r": ("0020", "1099-R"),
    "k-1": ("0050", "K-1"),
    "form1095c": ("0065", "HEALTH"),
    "1095c": ("0065", "HEALTH"),
    "form1095a": ("0065", "HEALTH"),
    "1095a": ("0065", "HEALTH"),
    "form1099int": ("0040", "INT DIV SCH D"),
    "form1099div": ("0040", "INT DIV SCH D"),
    "form1099b": ("0040", "INT DIV SCH D"),
    "interestincome": ("0040", "INT DIV SCH D"),
    "ordinarydividends": ("0040", "INT DIV SCH D"),
    "proceedsfrombroker": ("0040", "INT DIV SCH D"),
    "healthequity": ("0060", "HSA"),
    "hsastatement": ("0060", "HSA"),
    "1099sa": ("0060", "HSA"),
    "form1099sa": ("0060", "HSA"),
    "form5498sa": ("0060", "HSA"),
    "1098t": ("0070", "EDUCATION"),
    "1099q": ("0070", "EDUCATION"),
    "1098e": ("0070", "EDUCATION"),
    "mortgageinterest": ("1000", "SCH A - MORTGAGE"),
    "formptc": ("0080", "NE PTC"),
    "registration": ("1010", "SCH A - VEHICLE"),
    "ptclookup": ("0080", "NE PTC"),
    "donationreceipt": ("1020", "SCH A - DONATIONS"),
    "giftstatement": ("1020", "SCH A - DONATIONS"),
    "donation": ("1020", "SCH A - DONATIONS"),
    "charitable": ("1020", "SCH A - DONATIONS"),
    "501c": ("1020", "SCH A - DONATIONS"),
}

file_counters = {}
renamed_total = 0
skipped_total = 0
skipped_files = []

with open(LOG_FILE, "w") as log:
    log.write(f"Skipped Files Log - {datetime.now()}\n")
    log.write("=" * 40 + "\n")

for filename in os.listdir(BASE_DIR):
    if not filename.lower().endswith(".pdf"):
        continue

    full_path = os.path.join(BASE_DIR, filename)
    print(f"\n📄 Checking: {filename}")

    try:
        doc = fitz.open(full_path)
        full_text = "".join([page.get_text() for page in doc])
        doc.close()
    except Exception as e:
        reason = f"Error reading PDF: {e}"
        print(f"❌ {reason}")
        skipped_files.append((filename, reason))
        skipped_total += 1
        continue

    normalized_text = full_text.lower().replace(" ", "").replace("-", "").replace("\n", "")

    renamed = False
    for keyword, (prefix, label) in rename_mapping.items():
        if keyword in normalized_text:
            file_counters.setdefault(prefix, 0)
            file_counters[prefix] += 1
            new_filename = f"{prefix}.{file_counters[prefix]} {label}.pdf"
            new_path = os.path.join(BASE_DIR, new_filename)

            if os.path.exists(new_path):
                reason = "Target file already exists"
                print(f"⚠️ Skipped {filename}: {reason}")
                skipped_files.append((filename, reason))
                skipped_total += 1
                renamed = True
                break

            os.rename(full_path, new_path)
            print(f"✅ Renamed: {filename} → {new_filename}")
            renamed = True
            renamed_total += 1
            break

    if not renamed:
        reason = "No keyword match"
        print(f"⚠️ Skipped: {filename} - {reason}")
        skipped_files.append((filename, reason))
        skipped_total += 1

with open(LOG_FILE, "a") as log:
    for file, reason in skipped_files:
        log.write(f"{file}: {reason}\n")

print(f"\n✅ Done. Renamed: {renamed_total} | Skipped: {skipped_total}")
print(f"📝 Log saved to: {LOG_FILE}")