iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 17:31:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

expand Greek and enable Turkish in config

Browse Source
This commit is contained in:
Rob Speer 2015-09-03 23:23:20 -04:00
parent e6a2886a66
commit a3daba81eb
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
wordfreq_builder/wordfreq_builder/config.py
View File

@ -9,14 +9,13 @@ CONFIG = {
# A list of language codes (possibly un-standardized) that we'll
# look up in filenames for these various data sources.
'twitter': [
'ar', 'de', 'en', 'es', 'fr', 'id', 'it', 'ja', 'ko', 'ms', 'nl',
'pt', 'ru',
# can be added later: 'el', 'tr'
'ar', 'de', 'el', 'en', 'es', 'fr', 'id', 'it', 'ja', 'ko', 'ms', 'nl',
'pt', 'ru', 'tr'
],
'wikipedia': [
'ar', 'de', 'en', 'es', 'fr', 'id', 'it', 'ja', 'ko', 'ms', 'nl',
'ar', 'de', 'en', 'el', 'es', 'fr', 'id', 'it', 'ja', 'ko', 'ms', 'nl',
'pt', 'ru'
# consider adding 'el' and 'tr'
# consider adding 'tr'
],
'opensubtitles': [
# All languages where the most common word in OpenSubtitles