More valid guesses

This commit is contained in:
Arne Keller 2022-02-28 19:32:48 +01:00
parent 55b61ad858
commit 21eb168143
3 changed files with 23433 additions and 2 deletions

View File

@ -6,7 +6,7 @@ awk '{ if (length($0) == 5) print tolower($0) }' top10000de_utf8.txt > top10000d
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
cat $word_file | 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

File diff suppressed because one or more lines are too long

File diff suppressed because it is too large Load Diff