mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
8fe7bdd0fa
* Fix typo in rule-based matching docs * Improve token pattern checking without validation Add more detailed token pattern checks without full JSON pattern validation and provide more detailed error messages. Addresses #4070 (also related: #4063, #4100). * Check whether top-level attributes in patterns and attr for PhraseMatcher are in token pattern schema * Check whether attribute value types are supported in general (as opposed to per attribute with full validation) * Report various internal error types (OverflowError, AttributeError, KeyError) as ValueError with standard error messages * Check for tagger/parser in PhraseMatcher pipeline for attributes TAG, POS, LEMMA, and DEP * Add error messages with relevant details on how to use validate=True or nlp() instead of nlp.make_doc() * Support attr=TEXT for PhraseMatcher * Add NORM to schema * Expand tests for pattern validation, Matcher, PhraseMatcher, and EntityRuler * Remove unnecessary .keys() * Rephrase error messages * Add another type check to Matcher Add another type check to Matcher for more understandable error messages in some rare cases. * Support phrase_matcher_attr=TEXT for EntityRuler * Don't use spacy.errors in examples and bin scripts * Fix error code * Auto-format Also try get Azure pipelines to finally start a build :( * Update errors.py Co-authored-by: Ines Montani <ines@ines.io> Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
135 lines
4.6 KiB
Python
135 lines
4.6 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.matcher import PhraseMatcher
|
|
from spacy.tokens import Doc
|
|
from ..util import get_doc
|
|
|
|
|
|
def test_matcher_phrase_matcher(en_vocab):
|
|
doc = Doc(en_vocab, words=["Google", "Now"])
|
|
matcher = PhraseMatcher(en_vocab)
|
|
matcher.add("COMPANY", None, doc)
|
|
doc = Doc(en_vocab, words=["I", "like", "Google", "Now", "best"])
|
|
assert len(matcher(doc)) == 1
|
|
|
|
|
|
def test_phrase_matcher_length(en_vocab):
|
|
matcher = PhraseMatcher(en_vocab)
|
|
assert len(matcher) == 0
|
|
matcher.add("TEST", None, Doc(en_vocab, words=["test"]))
|
|
assert len(matcher) == 1
|
|
matcher.add("TEST2", None, Doc(en_vocab, words=["test2"]))
|
|
assert len(matcher) == 2
|
|
|
|
|
|
def test_phrase_matcher_contains(en_vocab):
|
|
matcher = PhraseMatcher(en_vocab)
|
|
matcher.add("TEST", None, Doc(en_vocab, words=["test"]))
|
|
assert "TEST" in matcher
|
|
assert "TEST2" not in matcher
|
|
|
|
|
|
def test_phrase_matcher_string_attrs(en_vocab):
|
|
words1 = ["I", "like", "cats"]
|
|
pos1 = ["PRON", "VERB", "NOUN"]
|
|
words2 = ["Yes", ",", "you", "hate", "dogs", "very", "much"]
|
|
pos2 = ["INTJ", "PUNCT", "PRON", "VERB", "NOUN", "ADV", "ADV"]
|
|
pattern = get_doc(en_vocab, words=words1, pos=pos1)
|
|
matcher = PhraseMatcher(en_vocab, attr="POS")
|
|
matcher.add("TEST", None, pattern)
|
|
doc = get_doc(en_vocab, words=words2, pos=pos2)
|
|
matches = matcher(doc)
|
|
assert len(matches) == 1
|
|
match_id, start, end = matches[0]
|
|
assert match_id == en_vocab.strings["TEST"]
|
|
assert start == 2
|
|
assert end == 5
|
|
|
|
|
|
def test_phrase_matcher_string_attrs_negative(en_vocab):
|
|
"""Test that token with the control codes as ORTH are *not* matched."""
|
|
words1 = ["I", "like", "cats"]
|
|
pos1 = ["PRON", "VERB", "NOUN"]
|
|
words2 = ["matcher:POS-PRON", "matcher:POS-VERB", "matcher:POS-NOUN"]
|
|
pos2 = ["X", "X", "X"]
|
|
pattern = get_doc(en_vocab, words=words1, pos=pos1)
|
|
matcher = PhraseMatcher(en_vocab, attr="POS")
|
|
matcher.add("TEST", None, pattern)
|
|
doc = get_doc(en_vocab, words=words2, pos=pos2)
|
|
matches = matcher(doc)
|
|
assert len(matches) == 0
|
|
|
|
|
|
def test_phrase_matcher_bool_attrs(en_vocab):
|
|
words1 = ["Hello", "world", "!"]
|
|
words2 = ["No", "problem", ",", "he", "said", "."]
|
|
pattern = Doc(en_vocab, words=words1)
|
|
matcher = PhraseMatcher(en_vocab, attr="IS_PUNCT")
|
|
matcher.add("TEST", None, pattern)
|
|
doc = Doc(en_vocab, words=words2)
|
|
matches = matcher(doc)
|
|
assert len(matches) == 2
|
|
match_id1, start1, end1 = matches[0]
|
|
match_id2, start2, end2 = matches[1]
|
|
assert match_id1 == en_vocab.strings["TEST"]
|
|
assert match_id2 == en_vocab.strings["TEST"]
|
|
assert start1 == 0
|
|
assert end1 == 3
|
|
assert start2 == 3
|
|
assert end2 == 6
|
|
|
|
|
|
def test_phrase_matcher_validation(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"])
|
|
matcher = PhraseMatcher(en_vocab, validate=True)
|
|
with pytest.warns(UserWarning):
|
|
matcher.add("TEST1", None, doc1)
|
|
with pytest.warns(UserWarning):
|
|
matcher.add("TEST2", None, doc2)
|
|
with pytest.warns(None) as record:
|
|
matcher.add("TEST3", None, doc3)
|
|
assert not record.list
|
|
matcher = PhraseMatcher(en_vocab, attr="POS", validate=True)
|
|
with pytest.warns(None) as record:
|
|
matcher.add("TEST4", None, doc2)
|
|
assert not record.list
|
|
|
|
|
|
def test_attr_validation(en_vocab):
|
|
with pytest.raises(ValueError):
|
|
PhraseMatcher(en_vocab, attr="UNSUPPORTED")
|
|
|
|
|
|
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 = PhraseMatcher(en_vocab, attr="DEP")
|
|
matcher.add("TEST1", None, doc1)
|
|
with pytest.raises(ValueError):
|
|
matcher.add("TEST2", None, doc2)
|
|
with pytest.raises(ValueError):
|
|
matcher.add("TEST3", None, doc3)
|
|
# TAG, POS, LEMMA require is_tagged
|
|
for attr in ("TAG", "POS", "LEMMA"):
|
|
matcher = PhraseMatcher(en_vocab, attr=attr)
|
|
matcher.add("TEST2", None, doc2)
|
|
with pytest.raises(ValueError):
|
|
matcher.add("TEST1", None, doc1)
|
|
with pytest.raises(ValueError):
|
|
matcher.add("TEST3", None, doc3)
|
|
# TEXT/ORTH only require tokens
|
|
matcher = PhraseMatcher(en_vocab, attr="ORTH")
|
|
matcher.add("TEST3", None, doc3)
|
|
matcher = PhraseMatcher(en_vocab, attr="TEXT")
|
|
matcher.add("TEST3", None, doc3)
|