From 34375958ef656c1269508d6e885b5800dac0d6dd Mon Sep 17 00:00:00 2001 From: Rob Speer Date: Wed, 26 Aug 2015 16:24:35 -0400 Subject: [PATCH] fix typo in docstring --- wordfreq/tokens.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/wordfreq/tokens.py b/wordfreq/tokens.py index d0b160d..d867d9a 100644 --- a/wordfreq/tokens.py +++ b/wordfreq/tokens.py @@ -9,7 +9,7 @@ TOKEN_RE = regex.compile(r""" # When we see characters that are Han ideographs (\p{IsIdeo}) or hiragana # \p{Script=Hiragana}, we allow a sequence of those characters to be glued # together as a single token. Without this case, the standard rule (case 2) - # would make each characte a separate token. This would be the correct + # would make each character a separate token. This would be the correct # behavior for word-wrapping, but a messy failure mode for NLP # tokenization. #