Keymagic for Normalization | Reorder

convert-correct.py

#!/usr/bin/env python3
import argparse
import pandas as pd

def to_codepoints(s: str) -> str:
    """Convert Myanmar text to Unicode codepoints with plus signs."""
    return " + ".join(f"U{ord(ch):04X}" for ch in s)

def main():
    parser = argparse.ArgumentParser(description="Convert Myanmar text pairs to Unicode codepoints mapping")
    parser.add_argument("-i", "--input", required=True, help="Input CSV file (2 columns: source,target)")
    parser.add_argument("-o", "--output", required=True, help="Output TXT file")

    args = parser.parse_args()

    # Load CSV (expect 2 columns, no header)
    df = pd.read_csv(args.input, header=None, names=["source", "target"])

    # Convert and prepare lines
    lines = []
    for _, row in df.iterrows():
        src = str(row["source"])
        tgt = str(row["target"])
        src_cp = to_codepoints(src)
        tgt_cp = to_codepoints(tgt)
        lines.append(f"{src_cp} => {tgt_cp} // {src} | {tgt}")

    # Write to TXT
    with open(args.output, "w", encoding="utf-8") as f:
        f.write("\n".join(lines))

    print(f"✅ Conversion complete. Output saved to {args.output}")

if __name__ == "__main__":
    main()