mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 01:48:04 +03:00
7e4cd7575c
* Refactor Docs.is_ flags
* Add derived `Doc.has_annotation` method
* `Doc.has_annotation(attr)` returns `True` for partial annotation
* `Doc.has_annotation(attr, require_complete=True)` returns `True` for
complete annotation
* Add deprecation warnings to `is_tagged`, `is_parsed`, `is_sentenced`
and `is_nered`
* Add `Doc._get_array_attrs()`, which returns a full list of `Doc` attrs
for use with `Doc.to_array`, `Doc.to_bytes` and `Doc.from_docs`. The
list is the `DocBin` attributes list plus `SPACY` and `LENGTH`.
Notes on `Doc.has_annotation`:
* `HEAD` is converted to `DEP` because heads don't have an unset state
* Accept `IS_SENT_START` as a synonym of `SENT_START`
Additional changes:
* Add `NORM`, `ENT_ID` and `SENT_START` to default attributes for
`DocBin`
* In `Doc.from_array()` the presence of `DEP` causes `HEAD` to override
`SENT_START`
* In `Doc.from_array()` using `attrs` other than
`Doc._get_array_attrs()` (i.e., a user's custom list rather than our
default internal list) with both `HEAD` and `SENT_START` shows a warning
that `HEAD` will override `SENT_START`
* `set_children_from_heads` does not require dependency labels to set
sentence boundaries and sets `sent_start` for all non-sentence starts to
`-1`
* Fix call to set_children_form_heads
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
75 lines
2.1 KiB
Python
75 lines
2.1 KiB
Python
import pytest
|
|
from spacy.pipeline.functions import merge_subtokens
|
|
from spacy.language import Language
|
|
from spacy.tokens import Span
|
|
|
|
from ..util import get_doc
|
|
|
|
|
|
@pytest.fixture
|
|
def doc(en_tokenizer):
|
|
# fmt: off
|
|
text = "This is a sentence. This is another sentence. And a third."
|
|
heads = [1, 0, 1, -2, -3, 1, 0, 1, -2, -3, 1, 1, 1, 0]
|
|
deps = ["nsubj", "ROOT", "subtok", "attr", "punct", "nsubj", "ROOT",
|
|
"subtok", "attr", "punct", "subtok", "subtok", "subtok", "ROOT"]
|
|
# fmt: on
|
|
tokens = en_tokenizer(text)
|
|
return get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
|
|
|
|
|
|
@pytest.fixture
|
|
def doc2(en_tokenizer):
|
|
text = "I like New York in Autumn."
|
|
heads = [1, 0, 1, -2, -3, -1, -5]
|
|
tags = ["PRP", "IN", "NNP", "NNP", "IN", "NNP", "."]
|
|
pos = ["PRON", "VERB", "PROPN", "PROPN", "ADP", "PROPN", "PUNCT"]
|
|
deps = ["ROOT", "prep", "compound", "pobj", "prep", "pobj", "punct"]
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(
|
|
tokens.vocab,
|
|
words=[t.text for t in tokens],
|
|
heads=heads,
|
|
tags=tags,
|
|
pos=pos,
|
|
deps=deps,
|
|
)
|
|
doc.ents = [Span(doc, 2, 4, doc.vocab.strings["GPE"])]
|
|
return doc
|
|
|
|
|
|
def test_merge_subtokens(doc):
|
|
doc = merge_subtokens(doc)
|
|
# get_doc() doesn't set spaces, so the result is "And a third ."
|
|
assert [t.text for t in doc] == [
|
|
"This",
|
|
"is",
|
|
"a sentence",
|
|
".",
|
|
"This",
|
|
"is",
|
|
"another sentence",
|
|
".",
|
|
"And a third .",
|
|
]
|
|
|
|
|
|
def test_factories_merge_noun_chunks(doc2):
|
|
assert len(doc2) == 7
|
|
nlp = Language()
|
|
merge_noun_chunks = nlp.create_pipe("merge_noun_chunks")
|
|
merge_noun_chunks(doc2)
|
|
assert len(doc2) == 6
|
|
assert doc2[2].text == "New York"
|
|
|
|
|
|
def test_factories_merge_ents(doc2):
|
|
assert len(doc2) == 7
|
|
assert len(list(doc2.ents)) == 1
|
|
nlp = Language()
|
|
merge_entities = nlp.create_pipe("merge_entities")
|
|
merge_entities(doc2)
|
|
assert len(doc2) == 6
|
|
assert len(list(doc2.ents)) == 1
|
|
assert doc2[2].text == "New York"
|