P4 enroute to P5.bash

This is a bash shell script for executing all of the various P4 to P5 stylesheets in a row. It is intended for use in Mac OS X, Debian GNU/Linux, or similar system.

---

#! /bin/bash

# P4_enroute_to_P5.bash
#
# Driver script to automate a large portion of the process to convert
# a TEI P4 (XML) instance into a TEI P5 instance.
#
# This script has been tested on only a Mac OS X and a Debian
# GNU/Linux system. It is not intended to run on any other, but it
# might.
#
# Copyleft 2006 by Syd Bauman and the Text Encoding Initiative
# Consortium

#set -o xtrace

# set up various constants for use later NB: Dot-two.xslt should be LAST!
STYLESHEETS=' Id-to-xml-id.xslt DateStructLess.xslt Change2change.xslt Remove-Default-Attributes.xsl Janus.xslt IDREFs2bareNames.xslt DescAttribute2Element.xslt Dot-two.xslt '
TMP=/tmp
TEMP=$TMP/`basename $0 .bash`_$$
TMPIN=${TEMP}_in
TMPOUT=${TEMP}_out
DEBUG=false

# initialize variables
N=0
time=""

# establish an error exit procedure
function error {
    echo "---------"
    D=`date "+%FT%T"`
    echo "fatal error at $D: $@."
    exit 1
}

# subroutine to derive an output filename from the input
# Note: this routine has the side-effect of setting $OUT
function outPath {
    case "${1##*.}" in
	xml   ) OUT=`basename $1 .xml`.tei ;;
	teip4 ) OUT=`basename $1 .teip4`.teip5 ;;
	p4    ) OUT=`basename $1 .p4`.p5 ;;
	tei   ) OUT=`basename $1 .tei`.teip5 ;;
        *     ) OUT="${1}.xml" ;;
    esac
}

# subroutine to execute one stylesheet
# presume input is in TMPIN, and return
# the output there. If debugging, also
# leave the output in an audit-trail file.
function transform {
    N=$(($N+1))
    if [ "$DEBUG" = "true" ] ; then
	echo "xsltproc $1 $TMPIN > $TMPOUT"
    else
	echo "$1 ..."
    fi
    $time xsltproc $1 $TMPIN > $TMPOUT
    if [ "$DEBUG" = "true" ] ; then
	echo "leaving output in ${TEMP}_${N}_${1}.out"
	cp $TMPOUT ${TEMP}_${N}_${1}.out
    fi
    mv $TMPOUT $TMPIN
    }

# ensure that we have a working xsltproc
echo "Checking for executable \"xsltproc\":"
which xsltproc || error "I could not find an `xsltproc` command to run, so I'm giving up"

# process options
# Currently, there is only 1 option: -d for debug
while getopts ":d" opt; do
    case $opt in
	d ) DEBUG=true ;;
	* ) echo "usge: $0 [-d] path/to/input [path/to/output]"
	    echo "(Any names can be used if both input & output"
	    echo "are specified; if input ends in a recognized"
	    echo "extension, the output is the same file with a"
	    echo "modified extension:"
	    echo " IN	  OUT"
	    echo ".xml   .tei"
	    echo ".teip4 .teip5"
	    echo ".p4    .p5"
	    echo ".tei   .teip5"
	    echo "If input extension is not recognized, output"
	    echo "has extension '.xml' appended"
	    exit 1
    esac
done
shift $(( $OPTIND -1 ))

# ensure that we have the right number of arguments (1 or 2),
# and create an output filepath
case "$#" in 
    0 ) error "Input file not specified" ;;
    1 ) outPath $1 ;;
    2 ) OUT=$2 ;;
    * ) error "Extraneous operand(s) ($2 $3 $4 ...)" ;;
esac

# Now that we've handled the arguments, get down to work

if [ "$DEBUG" = "true" ] ; then
    which time && time=`which time`
fi

if [ ! -r $1 ] ; then
    error "File $1 is not readable"
fi
if [ ! -s $1 ] ; then
    error "File $1 is empty"
fi

cp $1 $TMPIN
for s in $STYLESHEETS ; do
    if [ -r $s ] ; then
	transform $s
    else
	echo "WARNING: skipping '$s' as I can't find it!!!"
    fi
done
mv $TMPIN $OUT