explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 03:19:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Rename 'tokens' variable 'doc' in tokenizer

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-17 18:21:41 +02:00
parent 839de87ca9
commit f45973848c
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
spacy/tokenizer.pyx
View File

@ -79,9 +79,9 @@ cdef class Tokenizer:
"String is too long: %d characters. Max is 2**30." % len(string)
)
cdef int length = len(string)
cdef Doc tokens = Doc(self.vocab)
cdef Doc doc = Doc(self.vocab)
if length == 0:
return tokens
return doc
cdef int i = 0
cdef int start = 0
cdef bint cache_hit
@ -100,11 +100,11 @@ cdef class Tokenizer:
# we don't have to create the slice when we hit the cache.
span = string[start:i]
key = hash_string(span)
cache_hit = self._try_cache(key, tokens)
cache_hit = self._try_cache(key, doc)
if not cache_hit:
self._tokenize(tokens, span, key)
self._tokenize(doc, span, key)
if uc == ' ':
tokens.c[tokens.length - 1].spacy = True
doc.c[doc.length - 1].spacy = True
start = i + 1
else:
start = i
@ -113,11 +113,11 @@ cdef class Tokenizer:
if start < i:
span = string[start:]
key = hash_string(span)
cache_hit = self._try_cache(key, tokens)
cache_hit = self._try_cache(key, doc)
if not cache_hit:
self._tokenize(tokens, span, key)
tokens.c[tokens.length - 1].spacy = string[-1] == ' ' and not in_ws
return tokens
self._tokenize(doc, span, key)
doc.c[doc.length - 1].spacy = string[-1] == ' ' and not in_ws
return doc
def pipe(self, texts, batch_size=1000, n_threads=2):
"""Tokenize a stream of texts.