#!/bin/sh

# Usage: $0 Surname1.pdf.xoj

# Extracts all text fields from the 'xournal' (*.xoj) annotation
# files.

zcat ${1+"$@"} \
    | perl -0777 -ne 'while( /<text\s+.*?>(.*?)<\/text>/gsm ){ print $1, "\n\n" }' \
    | perl -0777 -pe 's/\n(?=[^\n])/ /g' \
    | perl -pe 's/^\s+-- /-- /' \
    | grep '^-- ' \
    | grep . \
    | perl -pe 's/\n/\n\n/' \
    | fold -w 80 -s \
#
