From 25e24f9c328904f6516de833ada6193fa3c34324 Mon Sep 17 00:00:00 2001
From: Rob Speer <rob@luminoso.com>
Date: Fri, 4 Sep 2015 01:50:15 -0400
Subject: [PATCH] Note on next languages to support

Former-commit-id: 531db642880cbf646edb1a63026b85446c04e78f
---
 wordfreq_builder/wordfreq_builder/config.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/wordfreq_builder/wordfreq_builder/config.py b/wordfreq_builder/wordfreq_builder/config.py
index 142c7ab..044f987 100644
--- a/wordfreq_builder/wordfreq_builder/config.py
+++ b/wordfreq_builder/wordfreq_builder/config.py
@@ -8,6 +8,11 @@ CONFIG = {
     'sources': {
         # A list of language codes (possibly un-standardized) that we'll
         # look up in filenames for these various data sources.
+        #
+        # Consider adding:
+        # 'th' when we get tokenization for it
+        # 'hi' when we stop messing up its tokenization
+        # 'tl' because it's probably ready right now
         'twitter': [
             'ar', 'de', 'el', 'en', 'es', 'fr', 'id', 'it', 'ja', 'ko', 'ms', 'nl',
             'pt', 'ru', 'tr'