mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +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>
37 lines
1.5 KiB
Python
37 lines
1.5 KiB
Python
import pytest
|
|
|
|
from ...util import get_doc, apply_transition_sequence
|
|
|
|
|
|
@pytest.mark.parametrize("text", ["A test sentence"])
|
|
@pytest.mark.parametrize("punct", [".", "!", "?", ""])
|
|
def test_en_sbd_single_punct(en_tokenizer, text, punct):
|
|
heads = [2, 1, 0, -1] if punct else [2, 1, 0]
|
|
deps = ["dep"] * len(heads)
|
|
tokens = en_tokenizer(text + punct)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
|
|
assert len(doc) == 4 if punct else 3
|
|
assert len(list(doc.sents)) == 1
|
|
assert sum(len(sent) for sent in doc.sents) == len(doc)
|
|
|
|
|
|
@pytest.mark.skip(
|
|
reason="The step_through API was removed (but should be brought back)"
|
|
)
|
|
def test_en_sentence_breaks(en_tokenizer, en_parser):
|
|
# fmt: off
|
|
text = "This is a sentence . This is another one ."
|
|
heads = [1, 0, 1, -2, -3, 1, 0, 1, -2, -3]
|
|
deps = ["nsubj", "ROOT", "det", "attr", "punct", "nsubj", "ROOT", "det",
|
|
"attr", "punct"]
|
|
transition = ["L-nsubj", "S", "L-det", "R-attr", "D", "R-punct", "B-ROOT",
|
|
"L-nsubj", "S", "L-attr", "R-attr", "D", "R-punct"]
|
|
# fmt: on
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
|
|
apply_transition_sequence(en_parser, doc, transition)
|
|
assert len(list(doc.sents)) == 2
|
|
for token in doc:
|
|
assert token.dep != 0 or token.is_space
|
|
assert [token.head.i for token in doc] == [1, 1, 3, 1, 1, 6, 6, 8, 6, 6]
|