mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
296446a1c8
<!--- Provide a general summary of your changes in the title. --> ## Description * tidy up and adjust Cython code to code style * improve docstrings and make calling `help()` nicer * add URLs to new docs pages to docstrings wherever possible, mostly to user-facing objects * fix various typos and inconsistencies in docs ### Types of change enhancement, docs ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
56 lines
1.6 KiB
Python
56 lines
1.6 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..matcher import Matcher
|
|
|
|
|
|
def merge_noun_chunks(doc):
|
|
"""Merge noun chunks into a single token.
|
|
|
|
doc (Doc): The Doc object.
|
|
RETURNS (Doc): The Doc object with merged noun chunks.
|
|
|
|
DOCS: https://spacy.io/api/pipeline-functions#merge_noun_chunks
|
|
"""
|
|
if not doc.is_parsed:
|
|
return doc
|
|
with doc.retokenize() as retokenizer:
|
|
for np in doc.noun_chunks:
|
|
attrs = {"tag": np.root.tag, "dep": np.root.dep}
|
|
retokenizer.merge(np, attrs=attrs)
|
|
return doc
|
|
|
|
|
|
def merge_entities(doc):
|
|
"""Merge entities into a single token.
|
|
|
|
doc (Doc): The Doc object.
|
|
RETURNS (Doc): The Doc object with merged entities.
|
|
|
|
DOCS: https://spacy.io/api/pipeline-functions#merge_entities
|
|
"""
|
|
with doc.retokenize() as retokenizer:
|
|
for ent in doc.ents:
|
|
attrs = {"tag": ent.root.tag, "dep": ent.root.dep, "ent_type": ent.label}
|
|
retokenizer.merge(ent, attrs=attrs)
|
|
return doc
|
|
|
|
|
|
def merge_subtokens(doc, label="subtok"):
|
|
"""Merge subtokens into a single token.
|
|
|
|
doc (Doc): The Doc object.
|
|
label (unicode): The subtoken dependency label.
|
|
RETURNS (Doc): The Doc object with merged subtokens.
|
|
|
|
DOCS: https://spacy.io/api/pipeline-functions#merge_subtokens
|
|
"""
|
|
merger = Matcher(doc.vocab)
|
|
merger.add("SUBTOK", None, [{"DEP": label, "op": "+"}])
|
|
matches = merger(doc)
|
|
spans = [doc[start : end + 1] for _, start, end in matches]
|
|
with doc.retokenize() as retokenizer:
|
|
for span in spans:
|
|
retokenizer.merge(span)
|
|
return doc
|