explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-07 13:44:55 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix py3 incompatibility

Browse Source
This commit is contained in:
Andreas Grivas 2015-11-02 19:40:37 +02:00
parent 8edd58492e
commit b5ce7a6e96
3 changed files with 20 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/tokens/doc.pyx
View File

@ -7,6 +7,7 @@ import numpy.linalg
import struct import struct
cimport numpy as np cimport numpy as np
import math import math
import six
from ..lexeme cimport Lexeme from ..lexeme cimport Lexeme
from ..lexeme cimport EMPTY_LEXEME from ..lexeme cimport EMPTY_LEXEME
@ -117,11 +118,16 @@ cdef class Doc:
def __unicode__(self): def __unicode__(self):
return u''.join([t.string for t in self]) return u''.join([t.string for t in self])
def __str__(self): def __bytes__(self):
return u''.join([t.string for t in self]).encode('utf-8') return u''.join([t.string for t in self]).encode('utf-8')
def __str__(self):
if six.PY3:
return self.__unicode__()
return self.__bytes__()
def __repr__(self): def __repr__(self):
return u''.join([t.string for t in self]).encode('utf-8') return self.__str__()
def similarity(self, other): def similarity(self, other):
if self.vector_norm == 0 or other.vector_norm == 0: if self.vector_norm == 0 or other.vector_norm == 0:

8
spacy/tokens/spans.pyx
View File

@ -4,6 +4,7 @@ import numpy
import numpy.linalg import numpy.linalg
cimport numpy as np cimport numpy as np
import math import math
import six
from ..structs cimport TokenC, LexemeC from ..structs cimport TokenC, LexemeC
from ..typedefs cimport flags_t, attr_t from ..typedefs cimport flags_t, attr_t
@ -47,10 +48,9 @@ cdef class Span:
return self.end - self.start return self.end - self.start
def __repr__(self): def __repr__(self):
text = self.text_with_ws if six.PY3:
if self[-1].whitespace_: return self.text
text = text[:-1] return self.text.encode('utf-8')
return text.encode('utf-8')
def __getitem__(self, object i): def __getitem__(self, object i):
if isinstance(i, slice): if isinstance(i, slice):

10
spacy/tokens/token.pyx
View File

@ -6,6 +6,7 @@ cimport numpy as np
np.import_array() np.import_array()
import numpy import numpy
import six
from ..lexeme cimport Lexeme from ..lexeme cimport Lexeme
@ -40,11 +41,16 @@ cdef class Token:
def __unicode__(self): def __unicode__(self):
return self.string return self.string
def __str__(self): def __bytes__(self):
return self.string.encode('utf-8') return self.string.encode('utf-8')
def __str__(self):
if six.PY3:
return self.__unicode__()
return self.__bytes__()
def __repr__(self): def __repr__(self):
return self.string.encode('utf-8') return self.__str__()
cpdef bint check_flag(self, attr_id_t flag_id) except -1: cpdef bint check_flag(self, attr_id_t flag_id) except -1:
return Lexeme.c_check_flag(self.c.lex, flag_id) return Lexeme.c_check_flag(self.c.lex, flag_id)