explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fiddle with the way strings are interned in lexeme

Browse Source
This commit is contained in:
Matthew Honnibal 2014-09-15 06:34:45 +02:00
parent 0bb547ab98
commit c396581a0b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/lexeme.pyx
View File

@ -24,8 +24,8 @@ cdef int lexeme_free(LexemeC* lexeme) except -1:
cdef char* intern_and_encode(unicode string, size_t* length): cdef char* intern_and_encode(unicode string, size_t* length):
global _strings cdef bytes byte_string = string.encode('utf8')
cdef bytes utf8_string = intern(string.encode('utf8')) cdef bytes utf8_string = intern(byte_string)
Py_INCREF(utf8_string) Py_INCREF(utf8_string)
length[0] = len(utf8_string) length[0] = len(utf8_string)
return <char*>utf8_string return <char*>utf8_string