spaCy/spacy/tests/parser/test_space_attachment.py

79 lines
2.7 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import pytest
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## 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. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
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]
tokens = en_tokenizer(text)
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## 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. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads)
2015-10-14 19:20:51 +03:00
for sent in doc.sents:
2015-10-14 19:24:57 +03:00
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)
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## 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. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps)
assert len(list(doc.sents)) == 2
@pytest.mark.xfail
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.xfail
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.xfail
def test_parser_space_attachment_space(en_tokenizer, en_parser, text, length):
doc = Doc(en_parser.vocab, words=text)
assert len(doc) == length
2018-11-30 19:43:08 +03:00
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