From 864a8f45d8921f98d788a5d52e478bbe311279c1 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Thu, 5 Nov 2015 11:32:19 +0000 Subject: [PATCH] * Use unicode in StringStore.intern, instead of unreliably casting to bytes. --- spacy/strings.pxd | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/spacy/strings.pxd b/spacy/strings.pxd index 759057035..6ba86d2ce 100644 --- a/spacy/strings.pxd +++ b/spacy/strings.pxd @@ -20,7 +20,7 @@ cdef class StringStore: cdef Utf8Str* c cdef int64_t size - cdef PreshMap _map - cdef size_t _resize_at + cdef public PreshMap _map + cdef int64_t _resize_at - cdef const Utf8Str* intern(self, unsigned char* chars, int length) except NULL + cdef const Utf8Str* intern(self, unicode py_string) except NULL