From 617155fe562652c859a380d85cc5710783d79448 Mon Sep 17 00:00:00 2001 From: Kelly Rauchenberger Date: Mon, 1 Feb 2016 09:30:04 -0500 Subject: Added emoji freevar Strings of emojis are tokenized separately from anything else, and added to an emoticon freevar, which is mixed in with regular emoticons like :P. This breaks old-style freevars like $name$ and $noun$ so some legacy support for compatibility is left in but eventually $name$ should be made into an actual new freevar. Emoji data is from gemoji (https://github.com/github/gemoji). --- kgramstats.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kgramstats.h') diff --git a/kgramstats.h b/kgramstats.h index a97d7bf..4acde65 100644 --- a/kgramstats.h +++ b/kgramstats.h @@ -112,8 +112,11 @@ private: int maxK; std::map > stats; - word hashtags {"#hashtag"}; + + // Words std::map words; + word hashtags {"#hashtag"}; + word emoticons {"👌"}; }; void printKgram(kgram k); -- cgit 1.4.1