explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-18 12:12:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix lemma_ unicode handling

Browse Source
This commit is contained in:
Someon 2015-03-11 01:26:59 +02:00
parent ec25976416
commit 5b8e8b4f72
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/en/pos.pyx
View File

@ -335,7 +335,8 @@ cdef class EnPosTagger:
cdef unicode lemma_string cdef unicode lemma_string
lemma_strings = self.lemmatizer(py_string, pos) lemma_strings = self.lemmatizer(py_string, pos)
lemma_string = sorted(lemma_strings)[0] lemma_string = sorted(lemma_strings)[0]
lemma = self.strings.intern(lemma_string.encode('utf8'), len(lemma_string)).i raw_string = lemma_string.encode('utf8')
lemma = self.strings.intern(raw_string, len(raw_string)).i
return lemma return lemma
def load_morph_exceptions(self, dict exc): def load_morph_exceptions(self, dict exc):