spaCy/spacy/pipeline/functions.py
Ines Montani a9c6104047 Component decorator and component analysis (#4517)
* Add work in progress

* Update analysis helpers and component decorator

* Fix porting of docstrings for Python 2

* Fix docstring stuff on Python 2

* Support meta factories when loading model

* Put auto pipeline analysis behind flag for now

* Analyse pipes on remove_pipe and replace_pipe

* Move analysis to root for now

Try to find a better place for it, but it needs to go for now to avoid circular imports

* Simplify decorator

Don't return a wrapped class and instead just write to the object

* Update existing components and factories

* Add condition in factory for classes vs. functions

* Add missing from_nlp classmethods

* Add "retokenizes" to printed overview

* Update assigns/requires declarations of builtins

* Only return data if no_print is enabled

* Use multiline table for overview

* Don't support Span

* Rewrite errors/warnings and move them to spacy.errors
2019-10-27 13:35:49 +01:00

68 lines
1.9 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from ..language import component
from ..matcher import Matcher
@component(
"merge_noun_chunks",
requires=["token.dep", "token.tag", "token.pos"],
retokenizes=True,
)
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
@component(
"merge_entities",
requires=["doc.ents", "token.ent_iob", "token.ent_type"],
retokenizes=True,
)
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
@component("merge_subtokens", requires=["token.dep"], retokenizes=True)
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