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

* Fix inefficiency in StringStore.dump function

This commit is contained in:
Matthew Honnibal 2015-07-16 17:34:32 +02:00
parent b59d271510
commit a9c3863665
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/strings.pyx
View File

@ -108,15 +108,15 @@ cdef class StringStore:
return &self.strings[i] return &self.strings[i]
def dump(self, loc): def dump(self, loc):
strings = []
cdef Utf8Str* string cdef Utf8Str* string
cdef bytes py_string cdef bytes py_string
cdef int i
with codecs.open(loc, 'w', 'utf8') as file_:
for i in range(self.size): for i in range(self.size):
string = &self.strings[i] string = &self.strings[i]
py_string = string.chars[:string.length] py_string = string.chars[:string.length]
strings.append(py_string.decode('utf8')) file_.write(py_string.decode('utf8'))
with codecs.open(loc, 'w', 'utf8') as file_: file_.write(SEPARATOR)
file_.write(SEPARATOR.join(strings))
def load(self, loc): def load(self, loc):
with codecs.open(loc, 'r', 'utf8') as file_: with codecs.open(loc, 'r', 'utf8') as file_: