explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-02 04:03:19 +03:00
Code Issues Packages Projects Releases Wiki Activity

changed head.__set__ to make it simpler

Browse Source
This commit is contained in:
Wolfgang Seeker 2016-03-14 13:43:48 +01:00
parent 46e3f979f1
commit 2ae253ef5b
1 changed files with 25 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
spacy/tokens/token.pyx
View File

@ -285,9 +285,8 @@ cdef class Token:
# is the new head a descendant of the old head # is the new head a descendant of the old head
cdef bint is_desc = old_head.is_ancestor_of(new_head) cdef bint is_desc = old_head.is_ancestor_of(new_head)
cdef int token_i
cdef int new_edge cdef int new_edge
cdef Token anc cdef Token anc, child
# update number of deps of old head # update number of deps of old head
if self.c.head > 0: # left dependent if self.c.head > 0: # left dependent
@ -297,23 +296,18 @@ cdef class Token:
# may change when the token is reattached # may change when the token is reattached
# it may not change if the new head is a descendant of the current head # it may not change if the new head is a descendant of the current head
# find new l_edge if new head is not a descendant of old head
# a new l_edge is any token between l_edge and old_head
# that is a descendant of old_head but not of self
new_edge = self.c.l_edge new_edge = self.c.l_edge
# the new l_edge is the left-most l_edge on any of the other dependents
# where the l_edge is left of the head, otherwise it is the head
if not is_desc: if not is_desc:
for token_i in range(old_head.l_edge+1,old_head.i):
if self.doc.c[token_i].l_kids == 0: # only a token without left deps can be a left edge
if self.is_ancestor_of(self.doc[token_i]):
continue
if old_head.is_ancestor_of(self.doc[token_i]):
new_edge = token_i
break
else: # set the new l_edge to old_head if no other was found
new_edge = old_head.i new_edge = old_head.i
for child in old_head.children:
# assign new l_edge to old_head if child == self:
continue
if child.c.l_edge < new_edge:
new_edge = child.c.l_edge
old_head.c.l_edge = new_edge old_head.c.l_edge = new_edge
# walk up the tree from old_head and assign new l_edge to ancestors # walk up the tree from old_head and assign new l_edge to ancestors
# until an ancestor already has an l_edge that's further left # until an ancestor already has an l_edge that's further left
for anc in old_head.ancestors: for anc in old_head.ancestors:
@ -326,17 +320,16 @@ cdef class Token:
# do the same thing as for l_edge # do the same thing as for l_edge
if self.c.r_edge == old_head.c.r_edge: if self.c.r_edge == old_head.c.r_edge:
new_edge = self.c.r_edge new_edge = self.c.r_edge
if not is_desc: if not is_desc:
for token_i in range(old_head.r_edge-1,old_head.i,-1):
if self.doc.c[token_i].r_kids == 0:
if self.is_ancestor_of(self.doc[token_i]):
continue
if old_head.is_ancestor_of(self.doc[token_i]):
new_edge = token_i
break
else:
new_edge = old_head.i new_edge = old_head.i
for child in old_head.children:
if child == self:
continue
if child.c.r_edge > new_edge:
new_edge = child.c.r_edge
old_head.c.r_edge = new_edge old_head.c.r_edge = new_edge
for anc in old_head.ancestors: for anc in old_head.ancestors:
if anc.c.r_edge >= new_edge: if anc.c.r_edge >= new_edge:
break break
@ -348,23 +341,21 @@ cdef class Token:
# walk up the tree from new head and set l_edge to self.l_edge # walk up the tree from new head and set l_edge to self.l_edge
# until you hit a token with an l_edge further to the left # until you hit a token with an l_edge further to the left
if self.c.l_edge < new_head.c.l_edge: if self.c.l_edge < new_head.c.l_edge:
new_edge = self.c.l_edge new_head.c.l_edge = self.c.l_edge
new_head.c.l_edge = new_edge
for anc in new_head.ancestors: for anc in new_head.ancestors:
if anc.c.l_edge <= new_edge: if anc.c.l_edge <= self.c.l_edge:
break break
anc.c.l_edge = new_edge anc.c.l_edge = self.c.l_edge
elif rel_newhead_i < 0: # right dependent elif rel_newhead_i < 0: # right dependent
new_head.c.r_kids += 1 new_head.c.r_kids += 1
# do the same as for l_edge # do the same as for l_edge
if self.c.r_edge > new_head.c.r_edge: if self.c.r_edge > new_head.c.r_edge:
new_edge = self.c.r_edge new_head.c.r_edge = self.c.r_edge
new_head.c.r_edge = new_edge
for anc in new_head.ancestors: for anc in new_head.ancestors:
if anc.c.r_edge >= new_edge: if anc.c.r_edge >= self.c.r_edge:
break break
anc.c.r_edge = new_edge anc.c.r_edge = self.c.r_edge
# set new head # set new head
self.c.head = rel_newhead_i self.c.head = rel_newhead_i