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>
83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
import pytest
|
|
|
|
from spacy.tokens.doc import Doc
|
|
|
|
from ..util import get_doc, apply_transition_sequence
|
|
|
|
|
|
def test_parser_space_attachment(en_tokenizer):
|
|
text = "This is a test.\nTo ensure spaces are attached well."
|
|
heads = [1, 0, 1, -2, -3, -1, 1, 4, -1, 2, 1, 0, -1, -2]
|
|
deps = ["dep"] * len(heads)
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
|
|
for sent in doc.sents:
|
|
if len(sent) == 1:
|
|
assert not sent[-1].is_space
|
|
|
|
|
|
def test_parser_sentence_space(en_tokenizer):
|
|
# fmt: off
|
|
text = "I look forward to using Thingamajig. I've been told it will make my life easier..."
|
|
heads = [1, 0, -1, -2, -1, -1, -5, -1, 3, 2, 1, 0, 2, 1, -3, 1, 1, -3, -7]
|
|
deps = ["nsubj", "ROOT", "advmod", "prep", "pcomp", "dobj", "punct", "",
|
|
"nsubjpass", "aux", "auxpass", "ROOT", "nsubj", "aux", "ccomp",
|
|
"poss", "nsubj", "ccomp", "punct"]
|
|
# fmt: on
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
|
|
assert len(list(doc.sents)) == 2
|
|
|
|
|
|
@pytest.mark.skip(
|
|
reason="The step_through API was removed (but should be brought back)"
|
|
)
|
|
def test_parser_space_attachment_leading(en_tokenizer, en_parser):
|
|
text = "\t \n This is a sentence ."
|
|
heads = [1, 1, 0, 1, -2, -3]
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=text.split(" "), heads=heads)
|
|
assert doc[0].is_space
|
|
assert doc[1].is_space
|
|
assert doc[2].text == "This"
|
|
with en_parser.step_through(doc) as stepwise:
|
|
pass
|
|
assert doc[0].head.i == 2
|
|
assert doc[1].head.i == 2
|
|
assert stepwise.stack == set([2])
|
|
|
|
|
|
@pytest.mark.skip(
|
|
reason="The step_through API was removed (but should be brought back)"
|
|
)
|
|
def test_parser_space_attachment_intermediate_trailing(en_tokenizer, en_parser):
|
|
text = "This is \t a \t\n \n sentence . \n\n \n"
|
|
heads = [1, 0, -1, 2, -1, -4, -5, -1]
|
|
transition = ["L-nsubj", "S", "L-det", "R-attr", "D", "R-punct"]
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=text.split(" "), heads=heads)
|
|
assert doc[2].is_space
|
|
assert doc[4].is_space
|
|
assert doc[5].is_space
|
|
assert doc[8].is_space
|
|
assert doc[9].is_space
|
|
|
|
apply_transition_sequence(en_parser, doc, transition)
|
|
for token in doc:
|
|
assert token.dep != 0 or token.is_space
|
|
assert [token.head.i for token in doc] == [1, 1, 1, 6, 3, 3, 1, 1, 7, 7]
|
|
|
|
|
|
@pytest.mark.parametrize("text,length", [(["\n"], 1), (["\n", "\t", "\n\n", "\t"], 4)])
|
|
@pytest.mark.skip(
|
|
reason="The step_through API was removed (but should be brought back)"
|
|
)
|
|
def test_parser_space_attachment_space(en_tokenizer, en_parser, text, length):
|
|
doc = Doc(en_parser.vocab, words=text)
|
|
assert len(doc) == length
|
|
with en_parser.step_through(doc) as _: # noqa: F841
|
|
pass
|
|
assert doc[0].is_space
|
|
for token in doc:
|
|
assert token.head.i == length - 1
|