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

* Fix unicode error for Python3

This commit is contained in:
Matthew Honnibal 2015-07-23 19:36:21 +02:00
parent dbda6c27fa
commit 1406e24327
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/serialize/bits.pyx
View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
from libc.string cimport memcpy from libc.string cimport memcpy
# Note that we're setting the most significant bits here first, when in practice # Note that we're setting the most significant bits here first, when in practice
@ -14,7 +16,7 @@ cdef Code bit_append(Code code, bint bit) nogil:
cdef class BitArray: cdef class BitArray:
def __init__(self, data=b''): def __init__(self, bytes data=b''):
self.data = data self.data = data
self.byte = 0 self.byte = 0
self.bit_of_byte = 0 self.bit_of_byte = 0
@ -78,8 +80,15 @@ cdef class BitArray:
return output return output
def as_bytes(self): def as_bytes(self):
cdef unsigned char byte
if self.bit_of_byte != 0: if self.bit_of_byte != 0:
return self.data + chr(self.byte) byte = chr(self.byte)
# Jump through some hoops for Python3
if isinstance(byte, unicode):
byte_char = <unsigned char>byte
return self.data + <bytes>&byte_char
else:
return self.data + chr(self.byte)
else: else:
return self.data return self.data