#!/bin/sh

for i in $(ls sessions/*.xml)
do
        cat $i \
        | xmlstarlet sel --encode utf-8 --template \
                --match "/session/chapter/turn/speaker[text[@language='en']/p[@type='speech'] and text[@language='fr']/p[@type='speech']]" \
                --output "@@@" \
                --copy-of "text[@language='en']/p" \
                --output "@@@" \
                --copy-of "text[@language='fr']/p" \
                --output "@#@" \
        | tr -d "\n" \
        | sed -r -e "s/@#@/\n/g" \
                -e "s/<\/p><p type=\"speech\">/|/g" \
                -e "s/<\/p>@@@<p type=\"speech\">/\t/g" \
                -e "s/@@@<p type=\"speech\">//g" \
                -e "s/<\/p>//g" \
        | grep -v "<quote " \
        | grep -v "<ellipsis/>" \
        | sed -r -e "s/<\/?\w+\/?>//g" -e "s/\|/ /g" \
        | awk 'BEGIN{FS="\t"}{if((length($1) < 20) && (length($2) < 20)) print}'
done