meowgorithm/dotfiles

"""Unpack Office files (DOCX, PPTX, XLSX) for editing.

Extracts the ZIP archive, pretty-prints XML files, and optionally:
- Merges adjacent runs with identical formatting (DOCX only)
- Simplifies adjacent tracked changes from same author (DOCX only)

Usage:
    python unpack.py <office_file> <output_dir> [options]

Examples:
    python unpack.py document.docx unpacked/
    python unpack.py presentation.pptx unpacked/
    python unpack.py document.docx unpacked/ --merge-runs false
"""

import argparse
import sys
import zipfile
from pathlib import Path

import defusedxml.minidom

from helpers.merge_runs import merge_runs as do_merge_runs
from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines

SMART_QUOTE_REPLACEMENTS = {
    "\u201c": "&#x201C;",  
    "\u201d": "&#x201D;",  
    "\u2018": "&#x2018;",  
    "\u2019": "&#x2019;",  
}


def unpack(
    input_file: str,
    output_directory: str,
    merge_runs: bool = True,
    simplify_redlines: bool = True,
) -> tuple[None, str]:
    input_path = Path(input_file)