* Rename Span.head to Span.root.

This commit is contained in:
Matthew Honnibal 2015-07-09 17:30:58 +02:00
parent c0255ed7d8
commit 53d1f5b2eb
2 changed files with 62 additions and 21 deletions

View File

@ -5,6 +5,10 @@ from collections import defaultdict
cdef class Span:
"""A slice from a Doc object."""
def __cinit__(self, Doc tokens, int start, int end, int label=0):
if start < 0:
start = tokens.length - start
if end < 0:
end = tokens.length - end
self._seq = tokens
self.start = start
self.end = end
@ -37,20 +41,48 @@ cdef class Span:
for i in range(self.start, self.end):
yield self._seq[i]
property head:
"""The highest Token in the dependency tree in the Span, or None if
the Span is not internally connected (i.e. there are multiple heads).
property root:
"""The first ancestor of the first word of the span that has its head
outside the span.
For example:
>>> toks = nlp(u'I like New York in Autumn.')
Let's name the indices --- easier than writing "toks[4]" etc.
>>> i, like, new, york, in_, autumn, dot = range(len(toks))
The head of 'new' is 'York', and the head of 'York' is 'like'
>>> toks[new].head.orth_
'York'
>>> toks[york].head.orth_
'like'
Create a span for "New York". Its root is "York".
>>> new_york = toks[new:york+1]
>>> new_york.root.orth_
'York'
When there are multiple words with external dependencies, we take the first:
>>> toks[autumn].head.orth_, toks[dot].head.orth_
('in', like')
>>> autumn_dot = toks[autumn:]
>>> autumn_dot.root.orth_
'Autumn'
"""
def __get__(self):
heads = []
for token in self:
head_i = token.head.i
if token.head is token or head_i >= self.end or head_i < self.start:
heads.append(token)
if len(heads) != 1:
return None
else:
return heads[0]
# This should probably be called 'head', and the other one called
# 'gov'. But we went with 'head' elsehwhere, and now we're stuck =/
cdef const TokenC* start = &self._seq.data[self.start]
cdef const TokenC* end = &self._seq.data[self.end]
head = start
while start <= (head + head.head) < end and head.head != 0:
head += head.head
return self[head - self._seq.data]
property lefts:
"""Tokens that are to the left of the Span, whose head is within the Span."""
@ -68,6 +100,14 @@ cdef class Span:
if right.i >= self.end:
yield right
property subtree:
def __get__(self):
for word in self.lefts:
yield from word.subtree
yield from self
for word in self.rights:
yield from word.subtree
property orth_:
def __get__(self):
return ''.join([t.string for t in self]).strip()
@ -84,10 +124,3 @@ cdef class Span:
def __get__(self):
return self._seq.vocab.strings[self.label]
property subtree:
def __get__(self):
for word in self.lefts:
yield from word.subtree
yield from self
for word in self.rights:
yield from word.subtree

View File

@ -5,8 +5,8 @@ import pytest
@pytest.fixture
def doc(en_nlp):
return en_nlp('This is a sentence. This is another sentence. And a third.')
def doc(EN):
return EN('This is a sentence. This is another sentence. And a third.')
def test_sent_spans(doc):
@ -15,3 +15,11 @@ def test_sent_spans(doc):
assert sents[0].end == 5
assert len(sents) == 3
assert sum(len(sent) for sent in sents) == len(doc)
def test_root(doc):
np = doc[2:4]
assert len(np) == 2
assert np.orth_ == 'a sentence'
assert np.root.orth_ == 'sentence'
assert nlp.root.head.orth_ == 'is'