From a3daba81eb29d0c71be31066f82f6401e28cefb4 Mon Sep 17 00:00:00 2001 From: Rob Speer Date: Thu, 3 Sep 2015 23:23:20 -0400 Subject: [PATCH] expand Greek and enable Turkish in config --- wordfreq_builder/wordfreq_builder/config.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/wordfreq_builder/wordfreq_builder/config.py b/wordfreq_builder/wordfreq_builder/config.py index 7c523fb..8ccb317 100644 --- a/wordfreq_builder/wordfreq_builder/config.py +++ b/wordfreq_builder/wordfreq_builder/config.py @@ -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