meowgorithm/dotfiles

"""Simplify tracked changes by merging adjacent w:ins or w:del elements.

Merges adjacent <w:ins> elements from the same author into a single element.
Same for <w:del> elements. This makes heavily-redlined documents easier to
work with by reducing the number of tracked change wrappers.

Rules:
- Only merges w:ins with w:ins, w:del with w:del (same element type)
- Only merges if same author (ignores timestamp differences)
- Only merges if truly adjacent (only whitespace between them)
"""

import xml.etree.ElementTree as ET
import zipfile
from pathlib import Path

import defusedxml.minidom

WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"


def simplify_redlines(input_dir: str) -> tuple[int, str]:
    doc_xml = Path(input_dir) / "word" / "document.xml"

    if not doc_xml.exists():
        return 0, f"Error: {doc_xml} not found"

    try:
        dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8"))
        root = dom.documentElement

        merge_count = 0

        containers = _find_elements(root, "p") + _find_elements(root, "tc")

        for container in containers:
            merge_count += _merge_tracked_changes_in(container, "ins")
            merge_count += _merge_tracked_changes_in(container, "del")

        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))