explode and reformat docx

copy.xslt

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="2.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:fo="http://www.w3.org/1999/XSL/Format">
    <xsl:output method="xml" encoding="UTF-8" indent="yes"/>
    <!-- Copy everything -->
    <xsl:template match="@*|node()|text()|comment()|processing-instruction()">
        <xsl:copy>
            <xsl:apply-templates select="@*|node()|text()|comment()|processing-instruction()"/>
        </xsl:copy>
    </xsl:template>
</xsl:stylesheet>

explode-docx

#!/bin/sh


# this scripts unpacks and reformat docx files
#
# you need xslt processor (Transform) in your path
# /c/Program Files/Saxonica/SaxonHE9.4N/bin/Transform
#
# make sure to copy remove-rsid.xslt and copy.xslt
if [ "$1" = "-r" ]; then
    remove_rsid=1
    shift
fi

if [ "$1" = "" ]; then
    echo expected name of the word document to be exploded
    exit 1
fi
suffix=${1##*.}
name="$1"

if [ "$suffix" = "xml" ]; then
    suffix=docx
    name=${1/%.xml/.docx}
fi

if [ "$suffix" = "$1" ]; then
    suffix=docx
    name=$1.docx
fi


corename=$(basename "$name" .$suffix)
if [ -z "$corename" ]; then
    echo can not work with empty name
    exit 1
fi

DIR="$( cd "$( dirname "$0" )" && pwd )"
DOSDIR=$(cygpath -m $DIR)
FLAT=/tmp/flat.$$
FLATOUT=/tmp/flat.$$.out


if [ "$remove_rsid" == "1" ]; then
    transform=$DOSDIR/remove-rsid.xslt
else
    transform=$DOSDIR/copy.xslt
fi

# $1 - file name
# 
# formats file as xml
_reformat_xml() {
    echo $1
    xmllint --format $1 -o $1.new
    mv $1.new $1
}

flaten() {
    # xml
    xmls=""
    for f in $(find . -name '*.xml'); do  
        ff=$(echo ${f#./} | tr '/' 'Ø')
        mv $f $FLAT/$ff
        xmls="$xmls $ff"
    done

    # for rels, rename into .xml
    rels=""
    for f in $(find . -name '*.rels'); do  
        ff=$(echo ${f#./} | tr '/' 'Ø')
        rels="$rels $ff.xml"
        mv $f $FLAT/$ff.xml
    done
}

expand_dirs() {
    target_dir=$(pwd)
    cd $FLATOUT

    for f in $rels ; do
        ff=$(echo ${f%.xml} | tr 'Ø' '/')
        mv $f "$target_dir/$ff"
    done

    for f in $xmls ; do
        ff=$(echo $f | tr 'Ø' '/')
        mv $f "$target_dir/$ff"
    done
    cd "$target_dir"
}

if [ -e "$corename" ]; then
    if [ -e "$corename.bak" ];then
        # echo removing $corename.bak
        rm -rf "$corename.bak"
    fi
    # echo backing up $corename
    mv "$corename" "$corename.bak"
fi 


mkdir "$corename"
cd "$corename"
unzip -q "../$name"

if [ -a $FLAT ]; then
    rm -rf $FLAT
fi
mkdir $FLAT

flaten

if [ -a $FLATOUT ]; then
    rm -rf $FLATOUT
fi
mkdir $FLATOUT

dosflat=$(cygpath -m $FLAT)
Transform -xsl:$transform -s:$dosflat -o:$dosflat.out
expand_dirs

rm -rf $FLAT $FLATOUT

remove-rsid.xslt

<?xml version="1.0" encoding="UTF-8"?>
    <!-- Remove unwanted attributes or/and nodes -->
<xsl:stylesheet version="2.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:fo="http://www.w3.org/1999/XSL/Format"
    xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
    <xsl:output method="xml" encoding="UTF-8" indent="yes"/>

    <!-- Copy everything -->
    <xsl:template match="@*|node()|text()|comment()|processing-instruction()">
        <xsl:copy>
            <xsl:apply-templates select="@*|node()|text()|comment()|processing-instruction()"/>
        </xsl:copy>
    </xsl:template>

    <xsl:template match="w:rsid"/>
    <xsl:template match="@w:rsidDel"/>
    <xsl:template match="@w:rsidP"/>
    <xsl:template match="@w:rsidR"/>
    <xsl:template match="@w:rsidRDefault"/>
    <xsl:template match="@w:rsidRPr"/>
    <xsl:template match="@w:rsidSect"/>
    <xsl:template match="@w:rsidTr"/>
    <xsl:template match="w:proofErr"/>
    <xsl:template match="w:lang"/>


</xsl:stylesheet>