explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 01:16:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Refine the way the is_parsed attribute is set by from_array

Browse Source
This commit is contained in:
Matthew Honnibal 2016-02-06 14:44:35 +01:00
parent 161b01d4c0
commit af8514cb0c
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/tokens/doc.pyx
View File

@ -397,14 +397,10 @@ cdef class Doc:
tokens[i + values[i]].l_kids += 1 tokens[i + values[i]].l_kids += 1
elif values[i] < 0: elif values[i] < 0:
tokens[i + values[i]].r_kids += 1 tokens[i + values[i]].r_kids += 1
if not self.is_parsed and tokens[i].head != 0:
self.is_parsed = True
elif attr_id == TAG: elif attr_id == TAG:
for i in range(length): for i in range(length):
self.vocab.morphology.assign_tag(&tokens[i], self.vocab.morphology.assign_tag(&tokens[i],
self.vocab.morphology.reverse_index[values[i]]) self.vocab.morphology.reverse_index[values[i]])
if not self.is_tagged and tokens[i].tag != 0:
self.is_tagged = True
elif attr_id == POS: elif attr_id == POS:
for i in range(length): for i in range(length):
tokens[i].pos = <univ_pos_t>values[i] tokens[i].pos = <univ_pos_t>values[i]
@ -420,6 +416,9 @@ cdef class Doc:
else: else:
raise ValueError("Unknown attribute ID: %d" % attr_id) raise ValueError("Unknown attribute ID: %d" % attr_id)
set_children_from_heads(self.c, self.length) set_children_from_heads(self.c, self.length)
self.is_parsed = bool(HEAD in attrs or DEP in attrs)
self.is_tagged = bool(TAG in attrs or POS in attrs)
return self return self
def to_bytes(self): def to_bytes(self):