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 formatting

Browse Source
This commit is contained in:
ines 2017-05-13 12:32:06 +02:00
parent 2e4db1beb9
commit 293ee359c5
2 changed files with 19 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/tokens/doc.pyx
View File

@ -638,7 +638,7 @@ cdef class Doc:
orth_ = text[start:end] orth_ = text[start:end]
lex = self.vocab.get(self.mem, orth_) lex = self.vocab.get(self.mem, orth_)
self.push_back(lex, has_space) self.push_back(lex, has_space)
start = end + has_space start = end + has_space
self.from_array([TAG,LEMMA,HEAD,DEP,ENT_IOB,ENT_TYPE], self.from_array([TAG,LEMMA,HEAD,DEP,ENT_IOB,ENT_TYPE],
attrs[:, 2:]) attrs[:, 2:])

24
spacy/tokens/printers.py
View File

@ -1,13 +1,20 @@
from copy import deepcopy from copy import deepcopy
# coding: utf8
from __future__ import unicode_literals
def merge_ents(doc): def merge_ents(doc):
'''Helper: merge adjacent entities into single tokens; modifies the doc.''' """
Helper: merge adjacent entities into single tokens; modifies the doc.
"""
for ent in doc.ents: for ent in doc.ents:
ent.merge(ent.root.tag_, ent.text, ent.label_) ent.merge(ent.root.tag_, ent.text, ent.label_)
return doc return doc
def format_POS(token, light, flat): def format_POS(token, light, flat):
'''helper: form the POS output for a token''' """
Helper: form the POS output for a token.
"""
subtree = dict([ subtree = dict([
("word", token.text), ("word", token.text),
("lemma", token.lemma_), # trigger ("lemma", token.lemma_), # trigger
@ -26,16 +33,21 @@ def format_POS(token, light, flat):
return subtree return subtree
def POS_tree(root, light, flat): def POS_tree(root, light, flat):
'''Helper: generate a POS tree for a root token.
The doc must have merge_ents(doc) ran on it. """
''' Helper: generate a POS tree for a root token. The doc must have
merge_ents(doc) ran on it.
"""
subtree = format_POS(root, light=light, flat=flat) subtree = format_POS(root, light=light, flat=flat)
for c in root.children: for c in root.children:
subtree["modifiers"].append(POS_tree(c)) subtree["modifiers"].append(POS_tree(c))
return subtree return subtree
def parse_tree(doc, light=False, flat=False): def parse_tree(doc, light=False, flat=False):
"""Makes a copy of the doc, then construct a syntactic parse tree, similar to the one used in displaCy. Generates the POS tree for all sentences in a doc """
Makes a copy of the doc, then construct a syntactic parse tree, similar to
the one used in displaCy. Generates the POS tree for all sentences in a doc.
Args: Args:
doc: The doc for parsing. doc: The doc for parsing.