spaCy/spacy/tests/matcher/test_matcher_api.py

413 lines
13 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import pytest
2018-09-05 06:53:21 +03:00
import re
from spacy.matcher import Matcher, DependencyMatcher
from spacy.tokens import Doc, Token
@pytest.fixture
2017-01-13 00:23:11 +03:00
def matcher(en_vocab):
rules = {
"JS": [[{"ORTH": "JavaScript"}]],
"GoogleNow": [[{"ORTH": "Google"}, {"ORTH": "Now"}]],
"Java": [[{"LOWER": "java"}]],
}
2017-05-22 13:59:50 +03:00
matcher = Matcher(en_vocab)
for key, patterns in rules.items():
matcher.add(key, None, *patterns)
return matcher
2017-01-13 00:23:11 +03:00
def test_matcher_from_api_docs(en_vocab):
matcher = Matcher(en_vocab)
pattern = [{"ORTH": "test"}]
assert len(matcher) == 0
matcher.add("Rule", None, pattern)
assert len(matcher) == 1
matcher.remove("Rule")
assert "Rule" not in matcher
matcher.add("Rule", None, pattern)
assert "Rule" in matcher
on_match, patterns = matcher.get("Rule")
assert len(patterns[0])
def test_matcher_from_usage_docs(en_vocab):
text = "Wow 😀 This is really cool! 😂 😂"
doc = Doc(en_vocab, words=text.split(" "))
pos_emoji = ["😀", "😃", "😂", "🤣", "😊", "😍"]
pos_patterns = [[{"ORTH": emoji}] for emoji in pos_emoji]
def label_sentiment(matcher, doc, i, matches):
match_id, start, end = matches[i]
if doc.vocab.strings[match_id] == "HAPPY":
doc.sentiment += 0.1
span = doc[start:end]
with doc.retokenize() as retokenizer:
retokenizer.merge(span)
token = doc[start]
token.vocab[token.text].norm_ = "happy emoji"
matcher = Matcher(en_vocab)
matcher.add("HAPPY", label_sentiment, *pos_patterns)
2018-11-30 19:43:08 +03:00
matcher(doc)
assert doc.sentiment != 0
assert doc[1].norm_ == "happy emoji"
💫 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
def test_matcher_len_contains(matcher):
assert len(matcher) == 3
matcher.add("TEST", None, [{"ORTH": "test"}])
assert "TEST" in matcher
assert "TEST2" not in matcher
def test_matcher_no_match(matcher):
💫 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 = Doc(matcher.vocab, words=["I", "like", "cheese", "."])
assert matcher(doc) == []
def test_matcher_match_start(matcher):
💫 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 = Doc(matcher.vocab, words=["JavaScript", "is", "good"])
assert matcher(doc) == [(matcher.vocab.strings["JS"], 0, 1)]
def test_matcher_match_end(matcher):
words = ["I", "like", "java"]
💫 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 = Doc(matcher.vocab, words=words)
assert matcher(doc) == [(doc.vocab.strings["Java"], 2, 3)]
def test_matcher_match_middle(matcher):
words = ["I", "like", "Google", "Now", "best"]
💫 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 = Doc(matcher.vocab, words=words)
assert matcher(doc) == [(doc.vocab.strings["GoogleNow"], 2, 4)]
def test_matcher_match_multi(matcher):
words = ["I", "like", "Google", "Now", "and", "java", "best"]
💫 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 = Doc(matcher.vocab, words=words)
assert matcher(doc) == [
(doc.vocab.strings["GoogleNow"], 2, 4),
(doc.vocab.strings["Java"], 5, 6),
]
def test_matcher_empty_dict(en_vocab):
💫 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
"""Test matcher allows empty token specs, meaning match on any token."""
matcher = Matcher(en_vocab)
💫 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 = Doc(matcher.vocab, words=["a", "b", "c"])
matcher.add("A.C", None, [{"ORTH": "a"}, {}, {"ORTH": "c"}])
matches = matcher(doc)
assert len(matches) == 1
assert matches[0][1:] == (0, 3)
matcher = Matcher(en_vocab)
matcher.add("A.", None, [{"ORTH": "a"}, {}])
matches = matcher(doc)
assert matches[0][1:] == (0, 2)
def test_matcher_operator_shadow(en_vocab):
matcher = Matcher(en_vocab)
💫 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 = Doc(matcher.vocab, words=["a", "b", "c"])
pattern = [{"ORTH": "a"}, {"IS_ALPHA": True, "OP": "+"}, {"ORTH": "c"}]
matcher.add("A.C", None, pattern)
matches = matcher(doc)
assert len(matches) == 1
assert matches[0][1:] == (0, 3)
def test_matcher_match_zero(matcher):
words1 = 'He said , " some words " ...'.split()
words2 = 'He said , " some three words " ...'.split()
pattern1 = [
{"ORTH": '"'},
{"OP": "!", "IS_PUNCT": True},
{"OP": "!", "IS_PUNCT": True},
{"ORTH": '"'},
]
pattern2 = [
{"ORTH": '"'},
{"IS_PUNCT": True},
{"IS_PUNCT": True},
{"IS_PUNCT": True},
{"ORTH": '"'},
]
matcher.add("Quote", None, pattern1)
💫 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 = Doc(matcher.vocab, words=words1)
assert len(matcher(doc)) == 1
💫 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 = Doc(matcher.vocab, words=words2)
assert len(matcher(doc)) == 0
matcher.add("Quote", None, pattern2)
assert len(matcher(doc)) == 0
def test_matcher_match_zero_plus(matcher):
words = 'He said , " some words " ...'.split()
pattern = [{"ORTH": '"'}, {"OP": "*", "IS_PUNCT": False}, {"ORTH": '"'}]
matcher = Matcher(matcher.vocab)
matcher.add("Quote", None, pattern)
💫 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 = Doc(matcher.vocab, words=words)
assert len(matcher(doc)) == 1
def test_matcher_match_one_plus(matcher):
control = Matcher(matcher.vocab)
control.add("BasicPhilippe", None, [{"ORTH": "Philippe"}])
doc = Doc(control.vocab, words=["Philippe", "Philippe"])
m = control(doc)
assert len(m) == 2
matcher.add(
"KleenePhilippe",
None,
[{"ORTH": "Philippe", "OP": "1"}, {"ORTH": "Philippe", "OP": "+"}],
)
m = matcher(doc)
assert len(m) == 1
2017-10-16 14:38:01 +03:00
def test_matcher_any_token_operator(en_vocab):
"""Test that patterns with "any token" {} work with operators."""
matcher = Matcher(en_vocab)
matcher.add("TEST", None, [{"ORTH": "test"}, {"OP": "*"}])
doc = Doc(en_vocab, words=["test", "hello", "world"])
matches = [doc[start:end].text for _, start, end in matcher(doc)]
assert len(matches) == 3
assert matches[0] == "test"
assert matches[1] == "test hello"
assert matches[2] == "test hello world"
2018-09-05 06:53:21 +03:00
def test_matcher_extension_attribute(en_vocab):
matcher = Matcher(en_vocab)
2019-02-06 15:32:18 +03:00
get_is_fruit = lambda token: token.text in ("apple", "banana")
Token.set_extension("is_fruit", getter=get_is_fruit, force=True)
pattern = [{"ORTH": "an"}, {"_": {"is_fruit": True}}]
matcher.add("HAVING_FRUIT", None, pattern)
doc = Doc(en_vocab, words=["an", "apple"])
matches = matcher(doc)
assert len(matches) == 1
2019-02-06 15:32:18 +03:00
doc = Doc(en_vocab, words=["an", "aardvark"])
matches = matcher(doc)
assert len(matches) == 0
def test_matcher_set_value(en_vocab):
matcher = Matcher(en_vocab)
2019-02-06 15:32:18 +03:00
pattern = [{"ORTH": {"IN": ["an", "a"]}}]
matcher.add("A_OR_AN", None, pattern)
doc = Doc(en_vocab, words=["an", "a", "apple"])
matches = matcher(doc)
assert len(matches) == 2
2019-02-06 15:32:18 +03:00
doc = Doc(en_vocab, words=["aardvark"])
matches = matcher(doc)
assert len(matches) == 0
def test_matcher_set_value_operator(en_vocab):
matcher = Matcher(en_vocab)
pattern = [{"ORTH": {"IN": ["a", "the"]}, "OP": "?"}, {"ORTH": "house"}]
matcher.add("DET_HOUSE", None, pattern)
doc = Doc(en_vocab, words=["In", "a", "house"])
matches = matcher(doc)
assert len(matches) == 2
doc = Doc(en_vocab, words=["my", "house"])
matches = matcher(doc)
assert len(matches) == 1
def test_matcher_regex(en_vocab):
matcher = Matcher(en_vocab)
2019-02-06 15:32:18 +03:00
pattern = [{"ORTH": {"REGEX": r"(?:a|an)"}}]
matcher.add("A_OR_AN", None, pattern)
doc = Doc(en_vocab, words=["an", "a", "hi"])
matches = matcher(doc)
assert len(matches) == 2
2019-02-06 15:32:18 +03:00
doc = Doc(en_vocab, words=["bye"])
matches = matcher(doc)
assert len(matches) == 0
2019-02-06 15:32:18 +03:00
def test_matcher_regex_shape(en_vocab):
matcher = Matcher(en_vocab)
2019-02-06 15:32:18 +03:00
pattern = [{"SHAPE": {"REGEX": r"^[^x]+$"}}]
matcher.add("NON_ALPHA", None, pattern)
doc = Doc(en_vocab, words=["99", "problems", "!"])
matches = matcher(doc)
assert len(matches) == 2
2019-02-06 15:32:18 +03:00
doc = Doc(en_vocab, words=["bye"])
matches = matcher(doc)
assert len(matches) == 0
2019-02-06 15:32:18 +03:00
def test_matcher_compare_length(en_vocab):
matcher = Matcher(en_vocab)
2019-02-06 15:32:18 +03:00
pattern = [{"LENGTH": {">=": 2}}]
matcher.add("LENGTH_COMPARE", None, pattern)
doc = Doc(en_vocab, words=["a", "aa", "aaa"])
matches = matcher(doc)
assert len(matches) == 2
2019-02-06 15:32:18 +03:00
doc = Doc(en_vocab, words=["a"])
matches = matcher(doc)
assert len(matches) == 0
def test_matcher_extension_set_membership(en_vocab):
matcher = Matcher(en_vocab)
2019-02-06 15:32:18 +03:00
get_reversed = lambda token: "".join(reversed(token.text))
Token.set_extension("reversed", getter=get_reversed, force=True)
pattern = [{"_": {"reversed": {"IN": ["eyb", "ih"]}}}]
matcher.add("REVERSED", None, pattern)
doc = Doc(en_vocab, words=["hi", "bye", "hello"])
matches = matcher(doc)
assert len(matches) == 2
2019-02-06 15:32:18 +03:00
doc = Doc(en_vocab, words=["aardvark"])
matches = matcher(doc)
assert len(matches) == 0
2018-09-05 06:53:21 +03:00
@pytest.fixture
def text():
return "The quick brown fox jumped over the lazy fox"
2018-09-05 06:53:21 +03:00
@pytest.fixture
def heads():
return [3, 2, 1, 1, 0, -1, 2, 1, -3]
2018-09-05 06:53:21 +03:00
@pytest.fixture
def deps():
return ["det", "amod", "amod", "nsubj", "prep", "pobj", "det", "amod"]
2018-09-05 06:53:21 +03:00
@pytest.fixture
def dependency_matcher(en_vocab):
def is_brown_yellow(text):
return bool(re.compile(r"brown|yellow|over").match(text))
2019-07-11 13:02:25 +03:00
2018-09-05 06:53:21 +03:00
IS_BROWN_YELLOW = en_vocab.add_flag(is_brown_yellow)
2018-09-05 06:53:21 +03:00
pattern1 = [
{"SPEC": {"NODE_NAME": "fox"}, "PATTERN": {"ORTH": "fox"}},
2019-07-11 13:02:25 +03:00
{
"SPEC": {"NODE_NAME": "q", "NBOR_RELOP": ">", "NBOR_NAME": "fox"},
"PATTERN": {"ORTH": "quick", "DEP": "amod"},
},
{
"SPEC": {"NODE_NAME": "r", "NBOR_RELOP": ">", "NBOR_NAME": "fox"},
"PATTERN": {IS_BROWN_YELLOW: True},
},
2018-09-05 06:53:21 +03:00
]
pattern2 = [
{"SPEC": {"NODE_NAME": "jumped"}, "PATTERN": {"ORTH": "jumped"}},
2019-07-11 13:02:25 +03:00
{
"SPEC": {"NODE_NAME": "fox", "NBOR_RELOP": ">", "NBOR_NAME": "jumped"},
"PATTERN": {"ORTH": "fox"},
},
{
"SPEC": {"NODE_NAME": "quick", "NBOR_RELOP": ".", "NBOR_NAME": "jumped"},
"PATTERN": {"ORTH": "fox"},
},
]
pattern3 = [
{"SPEC": {"NODE_NAME": "jumped"}, "PATTERN": {"ORTH": "jumped"}},
2019-07-11 13:02:25 +03:00
{
"SPEC": {"NODE_NAME": "fox", "NBOR_RELOP": ">", "NBOR_NAME": "jumped"},
"PATTERN": {"ORTH": "fox"},
},
{
"SPEC": {"NODE_NAME": "r", "NBOR_RELOP": ">>", "NBOR_NAME": "fox"},
"PATTERN": {"ORTH": "brown"},
},
2018-09-05 06:53:21 +03:00
]
matcher = DependencyMatcher(en_vocab)
matcher.add("pattern1", None, pattern1)
matcher.add("pattern2", None, pattern2)
matcher.add("pattern3", None, pattern3)
2018-09-05 06:53:21 +03:00
return matcher
def test_dependency_matcher_compile(dependency_matcher):
assert len(dependency_matcher) == 3
2018-09-05 06:53:21 +03:00
2019-07-11 13:02:25 +03:00
# def test_dependency_matcher(dependency_matcher, text, heads, deps):
# doc = get_doc(dependency_matcher.vocab, text.split(), heads=heads, deps=deps)
# matches = dependency_matcher(doc)
# assert matches[0][1] == [[3, 1, 2]]
# assert matches[1][1] == [[4, 3, 3]]
# assert matches[2][1] == [[4, 3, 2]]
def test_attr_pipeline_checks(en_vocab):
doc1 = Doc(en_vocab, words=["Test"])
doc1.is_parsed = True
doc2 = Doc(en_vocab, words=["Test"])
doc2.is_tagged = True
doc3 = Doc(en_vocab, words=["Test"])
# DEP requires is_parsed
matcher = Matcher(en_vocab)
matcher.add("TEST", None, [{"DEP": "a"}])
matcher(doc1)
with pytest.raises(ValueError):
matcher(doc2)
with pytest.raises(ValueError):
matcher(doc3)
# TAG, POS, LEMMA require is_tagged
for attr in ("TAG", "POS", "LEMMA"):
matcher = Matcher(en_vocab)
matcher.add("TEST", None, [{attr: "a"}])
matcher(doc2)
with pytest.raises(ValueError):
matcher(doc1)
with pytest.raises(ValueError):
matcher(doc3)
# TEXT/ORTH only require tokens
matcher = Matcher(en_vocab)
matcher.add("TEST", None, [{"ORTH": "a"}])
matcher(doc1)
matcher(doc2)
matcher(doc3)
matcher = Matcher(en_vocab)
matcher.add("TEST", None, [{"TEXT": "a"}])
matcher(doc1)
matcher(doc2)
matcher(doc3)
@pytest.mark.parametrize(
"pattern,text",
[
([{"IS_ALPHA": True}], "a"),
([{"IS_ASCII": True}], "a"),
([{"IS_DIGIT": True}], "1"),
([{"IS_LOWER": True}], "a"),
([{"IS_UPPER": True}], "A"),
([{"IS_TITLE": True}], "Aaaa"),
([{"IS_PUNCT": True}], "."),
([{"IS_SPACE": True}], "\n"),
([{"IS_BRACKET": True}], "["),
2019-08-31 14:39:06 +03:00
([{"IS_QUOTE": True}], '"'),
([{"IS_LEFT_PUNCT": True}], "``"),
([{"IS_RIGHT_PUNCT": True}], "''"),
([{"IS_STOP": True}], "the"),
([{"LIKE_NUM": True}], "1"),
([{"LIKE_URL": True}], "http://example.com"),
([{"LIKE_EMAIL": True}], "mail@example.com"),
],
)
def test_matcher_schema_token_attributes(en_vocab, pattern, text):
matcher = Matcher(en_vocab)
2019-08-31 14:39:06 +03:00
doc = Doc(en_vocab, words=text.split(" "))
matcher.add("Rule", None, pattern)
assert len(matcher) == 1
matches = matcher(doc)
assert len(matches) == 1