From 1219a5f513bf41051ed2d0bebe485c4bb7c840b4 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Thu, 2 Feb 2017 16:21:11 +0100 Subject: [PATCH] Add = to tokenizer prefixes --- spacy/language_data/punctuation.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/language_data/punctuation.py b/spacy/language_data/punctuation.py index e08065e5a..0eacb4324 100644 --- a/spacy/language_data/punctuation.py +++ b/spacy/language_data/punctuation.py @@ -72,7 +72,7 @@ HYPHENS = _HYPHENS.strip().replace(' ', '|') # Prefixes TOKENIZER_PREFIXES = ( - ['§', '%', r'\+'] + + ['§', '%', '=', r'\+'] + LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES +