arnekeller/qwörtle
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Switch to wikipedia words

Browse Source
This commit is contained in:
Arne Keller 2022-02-28 19:30:49 +01:00
parent 85180cd926
commit 55b61ad858
5 changed files with 5000 additions and 2692 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

680
blacklist.txt
View File

File diff suppressed because it is too large Load Diff

4
filter.sh
View File

@ -1,7 +1,7 @@
#!/bin/sh #!/bin/sh
set -e set -e
word_file=deu_news_2021_100K-words.txt word_file=deu_wikipedia_2021_1M-words.txt
cat $word_file | head -n15000 | cut -f2 > top10000de_utf8.txt cat $word_file | head -n35000 | cut -f2 > top10000de_utf8.txt
awk '{ if (length($0) == 5) print tolower($0) }' top10000de_utf8.txt > top10000de_utf8_len5.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 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 comm -23 top10000de_utf8_len5_filtered.txt blacklist.txt > valid_words.txt

4
index.js
View File

File diff suppressed because one or more lines are too long

6404
valid_guesses.txt
View File

File diff suppressed because it is too large Load Diff

600
valid_words.txt
View File

File diff suppressed because it is too large Load Diff