#!/bin/sh
set -e
word_file=deu_news_2021_100K-words.txt
cat $word_file | head -n15000 | cut -f2 > top10000de_utf8.txt
awk '{ if (length($0) == 5) print tolower($0) }' top10000de_utf8.txt > top10000de_utf8_len5.txt
cat top10000de_utf8_len5.txt | rg "^([A-Za-z]|ä|ö|ü|Ä|Ö|Ü)+\$" | sort | uniq > top10000de_utf8_len5_filtered.txt
comm -23 top10000de_utf8_len5_filtered.txt blacklist.txt > valid_words.txt

cat $word_file | head -n150000 | cut -f2 | awk '{ if (length($0) == 5) print tolower($0) }' - | rg "^([A-Za-z]|ä|ö|ü|Ä|Ö|Ü)+\$" | sort | uniq > valid_guesses.txt
comm -23 valid_guesses.txt blacklist.txt > valid_guesses2.txt
mv valid_guesses2.txt valid_guesses.txt

rm top10000de_utf8.txt top10000de_utf8_len5.txt top10000de_utf8_len5_filtered.txt