explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 19:39:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Set left and right children when loading parse from byte string

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-28 21:03:18 +02:00
parent 6609fcf4b2
commit b5132bed7d
1 changed files with 18 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
spacy/tokens/doc.pyx
View File

@ -279,9 +279,12 @@ cdef class Doc:
for col, attr_id in enumerate(attrs): for col, attr_id in enumerate(attrs):
values = array[:, col] values = array[:, col]
if attr_id == HEAD: if attr_id == HEAD:
# TODO: Set left and right children
for i in range(length): for i in range(length):
tokens[i].head = values[i] tokens[i].head = values[i]
if values[i] >= 1:
tokens[i + values[i]].l_kids += 1
elif values[i] < 0:
tokens[i + values[i]].r_kids += 1
elif attr_id == TAG: elif attr_id == TAG:
for i in range(length): for i in range(length):
tokens[i].tag = values[i] tokens[i].tag = values[i]
@ -294,6 +297,20 @@ cdef class Doc:
elif attr_id == ENT_TYPE: elif attr_id == ENT_TYPE:
for i in range(length): for i in range(length):
tokens[i].ent_type = values[i] tokens[i].ent_type = values[i]
cdef TokenC* head
cdef TokenC* child
# Set left edges
for i in range(length):
child = &tokens[i]
head = &tokens[i + child.head]
if child < head and child.l_edge < head.l_edge:
head.l_edge = child.l_edge
# Set right edges --- same as above, but iterate in reverse
for i in range(length-1, -1, -1):
child = &tokens[i]
head = &tokens[i + child.head]
if child > head and child.r_edge > head.r_edge:
head.r_edge = child.r_edge
return self return self
def to_bytes(self): def to_bytes(self):