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

* Removing happax stuff. Added length

Browse Source
This commit is contained in:
Matthew Honnibal 2014-08-02 20:45:12 +01:00
parent fc7c10d7f8
commit edd38a84b1
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/spacy.pyx
View File

@ -138,7 +138,7 @@ cdef class Language:
return <Lexeme_addr>word_ptr
cdef int _happax_to_vocab(self, StringHash hashed, Lexeme_addr word_ptr):
self.vocab[0][hashed] = <Lexeme_addr>word_ptr
self.vocab[0][hashed] = word_ptr
self.happax.erase(hashed)
cdef Lexeme* _add(self, StringHash hashed, unicode string, int split, size_t length):
@ -146,7 +146,8 @@ cdef class Language:
word = self.init_lexeme(string, hashed, split, length)
cdef Lexeme* clobbered = <Lexeme*>self.happax.insert(hashed, <size_t>word)
if clobbered != NULL:
free(clobbered)
#free(clobbered)
pass
self.bacov[hashed] = string
return word
@ -219,7 +220,8 @@ cdef class Language:
orth.first = <Py_UNICODE>lex[0]
cdef int length = len(lex)
orth.length = length
orth.flags = set_orth_flags(lex, length)
cdef unicode last3 = substr(lex, length - 3, length, length)