convert.py

#!/usr/bin/env python3
"""Convert the Riverstone English/ language pack to JSON.

Usage:
    python convert.py            # English/ -> English_JSON/
    python convert.py SRC DST    # custom source / destination dirs
"""

import json
import sys
from pathlib import Path

from converter.utils import is_skippable, toSafeEntityName
from converter.docs import readLocalDoc
from converter.sheets import readLocalSheet


def _file_path_key(rel: Path) -> str:
  """Compute the normalised path key used by splitMarkers / avoidTransformMarkers."""
  parts = [toSafeEntityName(p) for p in rel.with_suffix("").parts]
  return "/".join(parts)


def main() -> None:
  base = Path(__file__).resolve().parent
  src_dir = Path(sys.argv[1]) if len(sys.argv) > 1 else base / "English"
  dst_dir = Path(sys.argv[2]) if len(sys.argv) > 2 else base / "English_JSON"

  n_docx = n_xlsx = n_skipped = 0

  for path in sorted(src_dir.rglob("*")):
    if not path.is_file():
      continue
    ext = path.suffix.lower()
    if path.name.startswith("~$") or ext not in (".docx", ".xlsx"):
      continue
    if is_skippable(path.name):
      n_skipped += 1
      continue

    rel = path.relative_to(src_dir)
    file_path = _file_path_key(rel)

    if ext == ".docx":
      data = readLocalDoc(path, file_path)
      n_docx += 1
    else:
      data = readLocalSheet(path, file_path)
      n_xlsx += 1

    out_path = dst_dir / rel.with_suffix(".json")
    out_path.parent.mkdir(parents=True, exist_ok=True)
    out_path.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")

  total = n_docx + n_xlsx
  print(f"Converted {n_docx} docx + {n_xlsx} xlsx = {total} files  ({n_skipped} skipped)")
  print(f"Output: {dst_dir}")


if __name__ == "__main__":
  main()