qwörtle/filter.sh

5 lines
252 B
Bash
Raw Normal View History

2022-02-22 21:53:28 +00:00
#!/bin/sh
iconv -f ISO-8859-1 -t UTF-8 top10000de.txt > top10000de_utf8.txt
awk '{ if (length($0) == 5) print }' top10000de_utf8.txt > top10000de_utf8_len5.txt
cat top10000de_utf8_len5.txt | rg --invert-match "'|ß" > top10000de_utf8_len5_filtered.txt