mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
* Delete ununused _split method
This commit is contained in:
parent
a4863686ec
commit
8b20e9ad97
|
@ -79,5 +79,4 @@ cdef class Language:
|
||||||
cpdef Lexeme lookup(self, unicode text)
|
cpdef Lexeme lookup(self, unicode text)
|
||||||
|
|
||||||
cdef int _tokenize(self, Tokens tokens, Py_UNICODE* characters, size_t length) except -1
|
cdef int _tokenize(self, Tokens tokens, Py_UNICODE* characters, size_t length) except -1
|
||||||
cdef list _split(self, unicode string)
|
|
||||||
cdef int _split_one(self, unicode word)
|
cdef int _split_one(self, unicode word)
|
||||||
|
|
|
@ -134,28 +134,6 @@ cdef class Language:
|
||||||
node = node.tail
|
node = node.tail
|
||||||
break
|
break
|
||||||
|
|
||||||
cdef list _split(self, unicode string):
|
|
||||||
"""Find how to split a contiguous span of non-space characters into substrings.
|
|
||||||
|
|
||||||
This method calls find_split repeatedly. Most languages will want to
|
|
||||||
override _split_one, but it may be useful to override this instead.
|
|
||||||
|
|
||||||
Args:
|
|
||||||
chunk (unicode): The string to be split, e.g. u"Mike's!"
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
substrings (list): The component substrings, e.g. [u"Mike", "'s", "!"].
|
|
||||||
"""
|
|
||||||
substrings = []
|
|
||||||
while string:
|
|
||||||
split = self._split_one(string)
|
|
||||||
if split == 0:
|
|
||||||
substrings.append(string)
|
|
||||||
break
|
|
||||||
substrings.append(string[:split])
|
|
||||||
string = string[split:]
|
|
||||||
return substrings
|
|
||||||
|
|
||||||
cdef int _split_one(self, unicode word):
|
cdef int _split_one(self, unicode word):
|
||||||
return len(word)
|
return len(word)
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue
Block a user