mnemonic_port/rebuild/tools/parse_wordlist.py

#!/usr/bin/env python3
"""Parse mnemonicode mn_wordlist.c and emit the wordlist as JSON."""

import argparse
import json
import re
import sys
from pathlib import Path


def parse_wordlist(src: Path) -> dict:
  text = src.read_text()

  version_match = re.search(r'mn_wordlist_version\s*=\s*"[^"]*?([\d]+\.[\d]+)"', text)
  if not version_match:
    # Try alternate form: version embedded in longer string
    version_match = re.search(r'mn_wordlist_version\s*=\s*"[^"]*?(\d[\d.]+\d)', text)
  if not version_match:
    raise ValueError("Could not find mn_wordlist_version in source file")
  version = version_match.group(1)

  array_match = re.search(r'mn_words\[.*?\]\s*=\s*\{(.*?)\};', text, re.DOTALL)
  if not array_match:
    raise ValueError("Could not find mn_words array in source file")
  array_body = array_match.group(1)

  # All quoted strings in the array body; first element is the null sentinel (0, not a string)
  words = re.findall(r'"([^"]+)"', array_body)

  return {"version": version, "words": words}


def main():
  parser = argparse.ArgumentParser(
    description="Parse mnemonicode mn_wordlist.c and emit the wordlist as JSON"
  )
  parser.add_argument(
    "source",
    nargs="?",
    default=str(Path(__file__).parent.parent / "mnemonicode/mn_wordlist.c"),
    help="Path to mn_wordlist.c (default: ../mnemonicode/mn_wordlist.c relative to tools/)",
  )
  parser.add_argument(
    "-o", "--output",
    help="Write output to this file instead of stdout",
  )
  parser.add_argument(
    "--indent",
    type=int,
    default=2,
    help="JSON indent level (default: 2; use 0 for compact)",
  )
  args = parser.parse_args()

  src = Path(args.source)
  if not src.exists():
    print(f"error: source file not found: {src}", file=sys.stderr)
    sys.exit(1)

  result = parse_wordlist(src)

  indent = args.indent if args.indent > 0 else None
  output = json.dumps(result, indent=indent, ensure_ascii=False)

  if args.output:
    Path(args.output).write_text(output + "\n")
    print(f"wrote {len(result['words'])} words (version {result['version']}) -> {args.output}")
  else:
    print(output)


if __name__ == "__main__":
  main()