commit e0d87452da86dd8a57838bcaa8b8c817def194b0 parent ad95b9aa5689e07c7febceddbc9db5e8574f2699 Author: Christoph Lohmann <20h@r-36.net> Date: Sun, 13 Jun 2021 14:41:14 +0200 Add pptx2md converter. Diffstat:
| Makefile | | | 1 | + |
| bin/pptx2md | | | 55 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| examples/pptx/example.pptx | | | 0 |
3 files changed, 56 insertions(+), 0 deletions(-)
diff --git a/Makefile b/Makefile @@ -21,6 +21,7 @@ install: install -m 755 bin/dir2point $(DESTDIR)$(PREFIX)/bin/dir2point install -m 755 bin/md2point $(DESTDIR)$(PREFIX)/bin/md2point install -m 755 bin/point2pdf $(DESTDIR)$(PREFIX)/bin/point2pdf + install -m 755 bin/pptx2md $(DESTDIR)$(PREFIX)/bin/pptx2md mkdir -p $(DESTDIR)$(MANPREFIX)/man1 install -m 644 md2point.1 $(DESTDIR)$(MANPREFIX)/man1/md2point.1 diff --git a/bin/pptx2md b/bin/pptx2md @@ -0,0 +1,55 @@ +#!/bin/sh +# +# See LICENSE for license details. +# +# This is based on: +# https://github.com/revan/pptx2md +# +# The algorithm was simplified to the essence of what the ugly +# pptx format is capable of. Microsoft amateurs are unable to use +# XML properly. +# +# Requires: xml2tsv (git://bitreich.org/xml2tsv) +# + +if [ $# -lt 1 ]; +then + printf "usage: %s file.pptx\n" "$(basename "$0")" >&2 + exit 1 +fi + +pptxfile="$1" +mdfile="$1.md" +tmpdir="$(mktemp -u)" + +unzip -oq -d "${tmpdir}" "${pptxfile}" +if [ $? -ne 0 ]; +then + printf "Failed to extract %s.\n" "${pptxfile}" + exit 1 +fi + +for slidefile in ${tmpdir}/ppt/slides/*.xml; +do + linenum=0 + cat "${slidefile}" \ + | xml2tsv 2>/dev/null \ + | grep a:r/a:t \ + | cut -s -f 2 \ + | while read -r line; + do + if [ $linenum -eq 0 ]; + then + printf "## %s\n" "${line}" >> "${mdfile}" + else + printf "%s\n" "${line}" >> "${mdfile}" + fi + linenum=1 + done + printf "\n" >> "${mdfile}" +done + + +rm -r "$tmpdir" +exit 0 + diff --git a/examples/pptx/example.pptx b/examples/pptx/example.pptx Binary files differ.