Created
June 6, 2020 10:05
-
-
Save danielnaber/79907f27e272fa43a4fa23b400a9fbd4 to your computer and use it in GitHub Desktop.
extract sentences from Tatoeba, naming them with the 2-character code used by LanguageTool
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/bin/bash | |
| result=tatoeba-sentences | |
| function extract { | |
| echo "extract to >$result-$2-20191014.txt" | |
| grep " $1 " sentences.csv | awk -F '\t' '{print $3}' >$result-$2-20191014.txt | |
| shuf $result-$2-20191014.txt | head -n 1000 >sentences-$2-20191014-top1000.txt | |
| } | |
| extract "ara" "ar" | |
| extract "ast" "ast" | |
| extract "bel" "be" | |
| extract "bre" "br" | |
| extract "cat" "ca" | |
| extract "cmn" "zh" | |
| extract "dan" "da" | |
| extract "nld" "nl" | |
| extract "eng" "en" | |
| extract "epo" "eo" | |
| extract "fra" "fr" | |
| extract "glg" "gl" | |
| extract "deu" "de" | |
| extract "ell" "el" | |
| extract "glg" "gl" | |
| extract "ita" "it" | |
| extract "jpn" "ja" | |
| extract "khm" "km" | |
| extract "pes" "fa" | |
| extract "pol" "pl" | |
| extract "por" "pt" | |
| extract "ron" "ro" | |
| extract "rus" "ru" | |
| extract "slk" "sk" | |
| extract "slv" "sl" | |
| extract "spa" "es" | |
| extract "swe" "sv" | |
| extract "tgl" "tl" | |
| extract "tam" "ta" | |
| extract "ukr" "uk" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment