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

* Add string decode and encode helpers to string_tools

This commit is contained in:
Matthew Honnibal 2014-08-15 23:57:27 +02:00
parent 7fd9b2f1f8
commit 213a440ffc
2 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/string_tools.pxd
View File

@ -1,3 +1,7 @@
cpdef bytes to_bytes(unicode string)
cpdef unicode from_bytes(bytes string)
cpdef unicode substr(unicode string, int start, int end, size_t length) cpdef unicode substr(unicode string, int start, int end, size_t length)
cdef bint is_whitespace(Py_UNICODE c) cdef bint is_whitespace(Py_UNICODE c)

8
spacy/string_tools.pyx
View File

@ -1,6 +1,14 @@
# cython: profile=True # cython: profile=True
cpdef bytes to_bytes(unicode string):
return string.encode('utf8')
cpdef unicode from_bytes(bytes string):
return string.decode('utf8')
cpdef unicode substr(unicode string, int start, int end, size_t length): cpdef unicode substr(unicode string, int start, int end, size_t length):
if end >= length: if end >= length:
end = -1 end = -1