Find common labels between adult and student QQ xml files

find_overlap_qqs_vs_qqa.sh

#!/usr/bin/env bash

ROOT="/home/souto/Sync/PISA25/Tech/QQ/QQ_overlap"

cd ${ROOT}

for f in $(find $ROOT -name "*.xml")
do
	f_basename="$(basename -- $f .xml)"
	output_fname=${f_basename}.txt
	cat $f | grep -Poh "(?<=<text>).+?(?=</text>)" | sort > $output_fname
	if [[ "$f_basename" == *STQ* ]] || [[ "$f_basename" == *ICQ* ]]; then
		cat $output_fname >> QS_all.txt
	else
		cat $output_fname >> QA_all.txt
	fi
done

# arch specific
perl-rename 's/PISA_2025FT_QQ_(.+)-.+.txt/$1.txt/g' *.txt

cat QS_all.txt | sort > QS_all_sorted.txt
cat QA_all.txt | sort > QA_all_sorted.txt
comm -12 QS_all_sorted.txt QA_all_sorted.txt | sort | uniq > overlap_s-vs-a_qq.txt


# cat 04_QQS_N/PISA_2025FT_QQ_ICQ-ICTQuestionnaire.xml | grep -Poh "(?<=<text>).+?(?=</text>)" > qqs_icq.txt