explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix doc class

Browse Source
This commit is contained in:
Matthew Honnibal 2016-10-17 15:23:47 +02:00
parent 6cbdc94959
commit 9b60186266
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/tokens/doc.pyx
View File

@ -117,7 +117,7 @@ cdef class Doc:
self.is_parsed = False self.is_parsed = False
self.getters_for_tokens = {} self.getters_for_tokens = {}
self.getters_for_spans = {} self.getters_for_spans = {}
self.tensor = np.zeros((0,), dtype='float32') self.tensor = numpy.zeros((0,), dtype='float32')
self.user_data = {} self.user_data = {}
self._py_tokens = [] self._py_tokens = []
self._vector = None self._vector = None
@ -599,9 +599,9 @@ cdef class Doc:
if len(args) == 3: if len(args) == 3:
# TODO: Warn deprecation # TODO: Warn deprecation
tag, lemma, ent_type = args tag, lemma, ent_type = args
attributes[TAG] = self.strings[tag] attributes[TAG] = self.vocab.strings[tag]
attributes[LEMMA] = self.strings[lemma] attributes[LEMMA] = self.vocab.strings[lemma]
attributes[ENT_TYPE] = self.strings[ent_type] attributes[ENT_TYPE] = self.vocab.strings[ent_type]
elif args: elif args:
raise ValueError( raise ValueError(
"Doc.merge received %d non-keyword arguments. " "Doc.merge received %d non-keyword arguments. "
@ -618,9 +618,9 @@ cdef class Doc:
# Currently we have the token index, we want the range-end index # Currently we have the token index, we want the range-end index
end += 1 end += 1
cdef Span span = self[start:end] cdef Span span = self[start:end]
tag = self.strings[attributes.get(TAG, span.root.tag)] tag = self.vocab.strings[attributes.get(TAG, span.root.tag)]
lemma = self.strings[attributes.get(LEMMA, span.root.lemma)] lemma = self.vocab.strings[attributes.get(LEMMA, span.root.lemma)]
ent_type = self.strings[attributes.get(ENT_TYPE, span.root.ent_type)] ent_type = self.vocab.strings[attributes.get(ENT_TYPE, span.root.ent_type)]
# Get LexemeC for newly merged token # Get LexemeC for newly merged token
new_orth = ''.join([t.text_with_ws for t in span]) new_orth = ''.join([t.text_with_ws for t in span])