Outputs XML content of PowerPoint slides for use by "git diff"

pptx-to-text

#!/usr/bin/env python

"""Outputs XML content of PowerPoint slides.

See the following for how to make "git diff" work with PowerPoint files.

In "~/.gitconfig", append:

    [diff "pptx"]
        textconv = pptx-to-text

In the repository's ".gitattributes", append:

    *.pptx diff=pptx

"""

import argparse
import re
import sys
import xml.dom.minidom
import zipfile


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('filename')
    args = parser.parse_args()

    with zipfile.ZipFile(args.filename, 'r') as input_file:
        for name in sorted(input_file.namelist()):
            if re.match('ppt/.*/.*\.xml$', name):
                raw_xml_content = input_file.read(name)

                xml_content = xml.dom.minidom.parseString(
                    raw_xml_content).toprettyxml(indent='  ')

                print(xml_content, end='')


if __name__ == '__main__':
    sys.exit(main())