Created
September 12, 2024 09:13
-
-
Save yiyuezhuo/86ce4ccbf823abb6364f8caf0571fbf0 to your computer and use it in GitHub Desktop.
Increase outline level
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| <w:outlineLvl w:val="4"/> | |
| """ | |
| import re | |
| def transform(text: str, inc: int): | |
| return re.sub(r'w:outlineLvl w:val="(\d)"', lambda exp: f'w:outlineLvl w:val="{int(exp.groups()[0]) + inc}"', text) | |
| # return re.sub(r'w:pStyle w:val="(\d)"', lambda exp: f'w:pStyle w:val="{int(exp.groups()[0])+inc}"', text) | |
| zip_doc_path = "word/document.xml" | |
| def read_document(doc_path: str) -> str: | |
| with zipfile.ZipFile(doc_path, "r") as zin: | |
| b = zin.read(zip_doc_path) | |
| return b.decode('utf-8') | |
| # https://stackoverflow.com/questions/25738523/how-to-update-one-file-inside-zip-file | |
| import os | |
| import zipfile | |
| import tempfile | |
| def updateZip(zipname, filename, data): | |
| # generate a temp file | |
| tmpfd, tmpname = tempfile.mkstemp(dir=os.path.dirname(zipname)) | |
| os.close(tmpfd) | |
| # create a temp copy of the archive without filename | |
| with zipfile.ZipFile(zipname, 'r') as zin: | |
| with zipfile.ZipFile(tmpname, 'w') as zout: | |
| zout.comment = zin.comment # preserve the comment | |
| for item in zin.infolist(): | |
| if item.filename != filename: | |
| zout.writestr(item, zin.read(item.filename)) | |
| # replace with the temp archive | |
| os.remove(zipname) | |
| os.rename(tmpname, zipname) | |
| # now add filename with its new data | |
| with zipfile.ZipFile(zipname, mode='a', compression=zipfile.ZIP_DEFLATED) as zf: | |
| zf.writestr(filename, data) | |
| # msg = 'This data did not exist in a file before being added to the ZIP file' | |
| # updateZip('1.zip', 'index.html', msg) | |
| def apply_inc_to_docx(doc_path: str, inc: int): | |
| xml = read_document(doc_path) | |
| xml_transformed = transform(xml, inc) | |
| updateZip(doc_path, zip_doc_path, xml_transformed) | |
| import argparse | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("doc_path") | |
| parser.add_argument("inc", type=int) | |
| args = parser.parse_args() | |
| apply_inc_to_docx(args.doc_path, args.inc) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment