Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Handle lemmatization for unknown string IDs

This commit is contained in:
Matthew Honnibal 2017-09-24 05:01:31 -05:00
parent 204b58c864
commit 72bbcc0871
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/morphology.pyx
View File

@ -146,6 +146,8 @@ cdef class Morphology:
self.add_special_case(tag_str, form_str, attrs) self.add_special_case(tag_str, form_str, attrs)
def lemmatize(self, const univ_pos_t univ_pos, attr_t orth, morphology): def lemmatize(self, const univ_pos_t univ_pos, attr_t orth, morphology):
if orth not in self.strings:
return orth
cdef unicode py_string = self.strings[orth] cdef unicode py_string = self.strings[orth]
if self.lemmatizer is None: if self.lemmatizer is None:
return self.strings.add(py_string.lower()) return self.strings.add(py_string.lower())