mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 21:57:15 +03:00
75f3234404
## 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.
71 lines
3.0 KiB
Python
71 lines
3.0 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...util import get_doc
|
|
|
|
|
|
def test_en_parser_noun_chunks_standard(en_tokenizer):
|
|
text = "A base phrase should be recognized."
|
|
heads = [2, 1, 3, 2, 1, 0, -1]
|
|
tags = ['DT', 'JJ', 'NN', 'MD', 'VB', 'VBN', '.']
|
|
deps = ['det', 'amod', 'nsubjpass', 'aux', 'auxpass', 'ROOT', 'punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], tags=tags, deps=deps, heads=heads)
|
|
chunks = list(doc.noun_chunks)
|
|
assert len(chunks) == 1
|
|
assert chunks[0].text_with_ws == "A base phrase "
|
|
|
|
|
|
def test_en_parser_noun_chunks_coordinated(en_tokenizer):
|
|
text = "A base phrase and a good phrase are often the same."
|
|
heads = [2, 1, 5, -1, 2, 1, -4, 0, -1, 1, -3, -4]
|
|
tags = ['DT', 'NN', 'NN', 'CC', 'DT', 'JJ', 'NN', 'VBP', 'RB', 'DT', 'JJ', '.']
|
|
deps = ['det', 'compound', 'nsubj', 'cc', 'det', 'amod', 'conj', 'ROOT', 'advmod', 'det', 'attr', 'punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], tags=tags, deps=deps, heads=heads)
|
|
chunks = list(doc.noun_chunks)
|
|
assert len(chunks) == 2
|
|
assert chunks[0].text_with_ws == "A base phrase "
|
|
assert chunks[1].text_with_ws == "a good phrase "
|
|
|
|
|
|
def test_en_parser_noun_chunks_pp_chunks(en_tokenizer):
|
|
text = "A phrase with another phrase occurs."
|
|
heads = [1, 4, -1, 1, -2, 0, -1]
|
|
tags = ['DT', 'NN', 'IN', 'DT', 'NN', 'VBZ', '.']
|
|
deps = ['det', 'nsubj', 'prep', 'det', 'pobj', 'ROOT', 'punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], tags=tags, deps=deps, heads=heads)
|
|
chunks = list(doc.noun_chunks)
|
|
assert len(chunks) == 2
|
|
assert chunks[0].text_with_ws == "A phrase "
|
|
assert chunks[1].text_with_ws == "another phrase "
|
|
|
|
|
|
def test_en_parser_noun_chunks_appositional_modifiers(en_tokenizer):
|
|
text = "Sam, my brother, arrived to the house."
|
|
heads = [5, -1, 1, -3, -4, 0, -1, 1, -2, -4]
|
|
tags = ['NNP', ',', 'PRP$', 'NN', ',', 'VBD', 'IN', 'DT', 'NN', '.']
|
|
deps = ['nsubj', 'punct', 'poss', 'appos', 'punct', 'ROOT', 'prep', 'det', 'pobj', 'punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], tags=tags, deps=deps, heads=heads)
|
|
chunks = list(doc.noun_chunks)
|
|
assert len(chunks) == 3
|
|
assert chunks[0].text_with_ws == "Sam "
|
|
assert chunks[1].text_with_ws == "my brother "
|
|
assert chunks[2].text_with_ws == "the house "
|
|
|
|
|
|
def test_en_parser_noun_chunks_dative(en_tokenizer):
|
|
text = "She gave Bob a raise."
|
|
heads = [1, 0, -1, 1, -3, -4]
|
|
tags = ['PRP', 'VBD', 'NNP', 'DT', 'NN', '.']
|
|
deps = ['nsubj', 'ROOT', 'dative', 'det', 'dobj', 'punct']
|
|
tokens = en_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], tags=tags, deps=deps, heads=heads)
|
|
chunks = list(doc.noun_chunks)
|
|
assert len(chunks) == 3
|
|
assert chunks[0].text_with_ws == "She "
|
|
assert chunks[1].text_with_ws == "Bob "
|
|
assert chunks[2].text_with_ws == "a raise "
|