explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Make vocab always own lexemes

Browse Source
This commit is contained in:
Matthew Honnibal 2021-01-25 00:23:02 +11:00
parent 4048ca01eb
commit 6117adcd6d
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/vocab.pyx
View File

@ -161,8 +161,11 @@ cdef class Vocab:
return self._new_lexeme(mem, self.strings[orth]) return self._new_lexeme(mem, self.strings[orth])
cdef const LexemeC* _new_lexeme(self, Pool mem, unicode string) except NULL: cdef const LexemeC* _new_lexeme(self, Pool mem, unicode string) except NULL:
if len(string) < 3 or self.length < 10000: #if len(string) < 3 or self.length < 10000:
mem = self.mem # mem = self.mem
# TODO: Experiment with never allowing the Doc to own lexemes, to see
# if it solves the Doc.copy() issue.
mem = self.mem
cdef bint is_oov = mem is not self.mem cdef bint is_oov = mem is not self.mem
lex = <LexemeC*>mem.alloc(1, sizeof(LexemeC)) lex = <LexemeC*>mem.alloc(1, sizeof(LexemeC))
lex.orth = self.strings.add(string) lex.orth = self.strings.add(string)