qwörtle/filter.sh

14 lines
732 B
Bash
Raw Normal View History

2022-02-22 21:53:28 +00:00
#!/bin/sh
2022-02-23 09:38:57 +00:00
set -e
word_file=deu_news_2021_100K-words.txt
cat $word_file | head -n10000 | cut -f2 > top10000de_utf8.txt
awk '{ if (length($0) == 5) print tolower($0) }' top10000de_utf8.txt > top10000de_utf8_len5.txt
2022-02-23 10:16:34 +00:00
cat top10000de_utf8_len5.txt | rg "^([A-Za-z]|ä|ö|ü|Ä|Ö|Ü)+\$" | sort > top10000de_utf8_len5_filtered.txt
2022-02-23 09:38:57 +00:00
comm -23 top10000de_utf8_len5_filtered.txt blacklist.txt > valid_words.txt
cat $word_file | cut -f2 | awk '{ if (length($0) == 5) print tolower($0) }' - | rg "^([A-Za-z]|ä|ö|ü|Ä|Ö|Ü)+\$" | sort > valid_guesses.txt
2022-02-23 09:38:57 +00:00
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