Dirty hacks to check and reset (rebase) the Powerpoint Slide-Ids (sldIds) from 256 onwards in a given pptx presentation.

pptx-reset-slide-ids.py

#!/usr/bin/env python3

import argparse
import traceback
from io import BytesIO
from zipfile import ZipFile, ZIP_DEFLATED
import lxml.etree as ET


xslt_src = """<xsl:stylesheet
    version="1.0"
    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main"
    xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"
    >

    <xsl:output method="xml" />
    <xsl:strip-space elements="*"/>

     <xsl:key name="mapping" match="/p:presentation/p:sldIdLst/p:sldId" use="@id"/>

    <xsl:template match="@*|node()">
        <xsl:copy>
            <xsl:apply-templates select="@*|node()"/>
        </xsl:copy>
    </xsl:template>

    <xsl:template match="/p:presentation/p:sldIdLst/p:sldId">
        <p:sldId id="{256 + count(key('mapping', @id)/preceding-sibling::*)}" r:id="{@r:id}"/>
    </xsl:template>

    <!-- reuse same new ids in sections -->
    <xsl:template match="*[local-name()='sldId' and not (name()=p:sldId)]">
        <p:sldId id="{256 + count(key('mapping', @id)/preceding-sibling::*)}"/>
    </xsl:template>

</xsl:stylesheet>"""


def parse_arguments():
    """
        Purpose: parse and return all arguments
    """
    parser = argparse.ArgumentParser(
        description='Extracts slide Ids from a pptx Powerpoint presentation'
    )
    parser.add_argument('-i', '--input',  help='Powerpoint input file',  dest='input',  required=True)
    parser.add_argument('-o', '--output', help='Powerpoint output file', dest='output', required=True)

    return parser.parse_args()


def read_zip(file_name):
    bio = BytesIO(open(file_name, 'rb').read())
    archive = ZipFile(bio, 'r')
    content = {n: archive.read(n) for n in archive.namelist()}
    archive.close()

    return content


def write_zip(file_name, content):
    bio = BytesIO()
    archive = ZipFile(bio, 'w', ZIP_DEFLATED)
    for name, data in content.items():
        archive.writestr(name, data)
    archive.close()
    open(file_name, 'wb').write(bio.getvalue())


def reset_slide_ids(content):
    input_dom = ET.fromstring(content['ppt/presentation.xml'])
    transformer = ET.XSLT(ET.fromstring(xslt_src))
    content['ppt/presentation.xml'] = ET.tostring(transformer(input_dom), encoding='utf-8')

    return content


def main():
    """
    The main sequence of calls
    :return:
    """
    try:
        args = parse_arguments()
    except Exception:
        print("Error parsing command line")
        traceback.print_exc()
        return

    try:
        write_zip(args.output, reset_slide_ids(read_zip(args.input)))
    except Exception:
        print("Error rewriting zipfile")
        traceback.print_exc()
        return


if __name__ == "__main__":
    main()

pptx-slide-ids.py

#!/usr/bin/env python3

import argparse
import traceback
from io import BytesIO
from zipfile import ZipFile
import lxml.etree as ET


xslt_src = """<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main">
    <xsl:output method="text" />
    <xsl:strip-space elements="*"/>
    <xsl:template match="/p:presentation/p:sldIdLst/p:sldId"><xsl:value-of select="@id"/> - <xsl:value-of select="2147483647 - @id"/> Ids left.<xsl:text>&#10;</xsl:text></xsl:template>
</xsl:stylesheet>"""


def parse_arguments():
    """
        Purpose: parse and return all arguments
    """
    parser = argparse.ArgumentParser(
        description='Extracts slide Ids from a pptx Powerpoint presentation'
    )
    parser.add_argument('-p', '--pptx', help='Powerpoint input file', dest='pptx', required=True)

    return parser.parse_args()


def main():
    """
    The main sequence of calls
    :return:
    """
    try:
        args = parse_arguments()
    except Exception:
        print("Error parsing command line")
        traceback.print_exc()
        return

    with open(args.pptx, "rb") as fh:
        archive = ZipFile(BytesIO(fh.read()))
        presentation = archive.read('ppt/presentation.xml')
        dom = ET.fromstring(presentation)
        xslt = ET.fromstring(xslt_src)
        transform = ET.XSLT(xslt)
        print(transform(dom))


if __name__ == "__main__":
    main()