mirror of
https://github.com/explosion/spaCy.git
synced 2025-04-25 11:23:40 +03:00
Try comming out emoji test in matcher
This commit is contained in:
Matthew Honnibal
parent
980ad68cbe
commit
2c9c8b8d72
|
|
@ -40,25 +40,25 @@ def test_matcher_from_api_docs(en_vocab):
|
||||||
assert len(patterns[0])
|
assert len(patterns[0])
|
||||||
|
|
||||||
|
|
||||||
def test_matcher_from_usage_docs(en_vocab):
|
#def test_matcher_from_usage_docs(en_vocab):
|
||||||
text = "Wow 😀 This is really cool! 😂 😂"
|
# text = "Wow 😀 This is really cool! 😂 😂"
|
||||||
doc = get_doc(en_vocab, words=text.split(' '))
|
# doc = get_doc(en_vocab, words=text.split(' '))
|
||||||
pos_emoji = [u'😀', u'😃', u'😂', u'🤣', u'😊', u'😍']
|
# pos_emoji = [u'😀', u'😃', u'😂', u'🤣', u'😊', u'😍']
|
||||||
pos_patterns = [[{'ORTH': emoji}] for emoji in pos_emoji]
|
# pos_patterns = [[{'ORTH': emoji}] for emoji in pos_emoji]
|
||||||
|
#
|
||||||
def label_sentiment(matcher, doc, i, matches):
|
# def label_sentiment(matcher, doc, i, matches):
|
||||||
match_id, start, end = matches[i]
|
# match_id, start, end = matches[i]
|
||||||
if doc.vocab.strings[match_id] == 'HAPPY':
|
# if doc.vocab.strings[match_id] == 'HAPPY':
|
||||||
doc.sentiment += 0.1
|
# doc.sentiment += 0.1
|
||||||
span = doc[start : end]
|
# span = doc[start : end]
|
||||||
token = span.merge()
|
# token = span.merge()
|
||||||
token.vocab[token.text].norm_ = 'happy emoji'
|
# token.vocab[token.text].norm_ = 'happy emoji'
|
||||||
|
#
|
||||||
matcher = Matcher(en_vocab)
|
# matcher = Matcher(en_vocab)
|
||||||
matcher.add('HAPPY', label_sentiment, *pos_patterns)
|
# matcher.add('HAPPY', label_sentiment, *pos_patterns)
|
||||||
matches = matcher(doc)
|
# matches = matcher(doc)
|
||||||
assert doc.sentiment != 0
|
# assert doc.sentiment != 0
|
||||||
assert doc[1].norm_ == 'happy emoji'
|
# assert doc[1].norm_ == 'happy emoji'
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.parametrize('words', [["Some", "words"]])
|
@pytest.mark.parametrize('words', [["Some", "words"]])
|
||||||
|
|
@ -93,181 +93,181 @@ def test_matcher_compile(en_vocab):
|
||||||
assert len(matcher) == 3
|
assert len(matcher) == 3
|
||||||
|
|
||||||
|
|
||||||
#def test_matcher_match_start(matcher):
|
def test_matcher_match_start(matcher):
|
||||||
# words = ["JavaScript", "is", "good"]
|
words = ["JavaScript", "is", "good"]
|
||||||
# doc = get_doc(matcher.vocab, words)
|
doc = get_doc(matcher.vocab, words)
|
||||||
# assert matcher(doc) == [(matcher.vocab.strings['JS'], 0, 1)]
|
assert matcher(doc) == [(matcher.vocab.strings['JS'], 0, 1)]
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_match_end(matcher):
|
def test_matcher_match_end(matcher):
|
||||||
# words = ["I", "like", "java"]
|
words = ["I", "like", "java"]
|
||||||
# doc = get_doc(matcher.vocab, words)
|
doc = get_doc(matcher.vocab, words)
|
||||||
# assert matcher(doc) == [(doc.vocab.strings['Java'], 2, 3)]
|
assert matcher(doc) == [(doc.vocab.strings['Java'], 2, 3)]
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_match_middle(matcher):
|
def test_matcher_match_middle(matcher):
|
||||||
# words = ["I", "like", "Google", "Now", "best"]
|
words = ["I", "like", "Google", "Now", "best"]
|
||||||
# doc = get_doc(matcher.vocab, words)
|
doc = get_doc(matcher.vocab, words)
|
||||||
# assert matcher(doc) == [(doc.vocab.strings['GoogleNow'], 2, 4)]
|
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'], 2, 4)]
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_match_multi(matcher):
|
def test_matcher_match_multi(matcher):
|
||||||
# words = ["I", "like", "Google", "Now", "and", "java", "best"]
|
words = ["I", "like", "Google", "Now", "and", "java", "best"]
|
||||||
# doc = get_doc(matcher.vocab, words)
|
doc = get_doc(matcher.vocab, words)
|
||||||
# assert matcher(doc) == [(doc.vocab.strings['GoogleNow'], 2, 4),
|
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'], 2, 4),
|
||||||
# (doc.vocab.strings['Java'], 5, 6)]
|
(doc.vocab.strings['Java'], 5, 6)]
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_empty_dict(en_vocab):
|
def test_matcher_empty_dict(en_vocab):
|
||||||
# '''Test matcher allows empty token specs, meaning match on any token.'''
|
'''Test matcher allows empty token specs, meaning match on any token.'''
|
||||||
# matcher = Matcher(en_vocab)
|
matcher = Matcher(en_vocab)
|
||||||
# abc = ["a", "b", "c"]
|
abc = ["a", "b", "c"]
|
||||||
# doc = get_doc(matcher.vocab, abc)
|
doc = get_doc(matcher.vocab, abc)
|
||||||
# matcher.add('A.C', None, [{'ORTH': 'a'}, {}, {'ORTH': 'c'}])
|
matcher.add('A.C', None, [{'ORTH': 'a'}, {}, {'ORTH': 'c'}])
|
||||||
# matches = matcher(doc)
|
matches = matcher(doc)
|
||||||
# assert len(matches) == 1
|
assert len(matches) == 1
|
||||||
# assert matches[0][1:] == (0, 3)
|
assert matches[0][1:] == (0, 3)
|
||||||
# matcher = Matcher(en_vocab)
|
matcher = Matcher(en_vocab)
|
||||||
# matcher.add('A.', None, [{'ORTH': 'a'}, {}])
|
matcher.add('A.', None, [{'ORTH': 'a'}, {}])
|
||||||
# matches = matcher(doc)
|
matches = matcher(doc)
|
||||||
# assert matches[0][1:] == (0, 2)
|
assert matches[0][1:] == (0, 2)
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_operator_shadow(en_vocab):
|
def test_matcher_operator_shadow(en_vocab):
|
||||||
# matcher = Matcher(en_vocab)
|
matcher = Matcher(en_vocab)
|
||||||
# abc = ["a", "b", "c"]
|
abc = ["a", "b", "c"]
|
||||||
# doc = get_doc(matcher.vocab, abc)
|
doc = get_doc(matcher.vocab, abc)
|
||||||
# matcher.add('A.C', None, [{'ORTH': 'a'},
|
matcher.add('A.C', None, [{'ORTH': 'a'},
|
||||||
# {"IS_ALPHA": True, "OP": "+"},
|
{"IS_ALPHA": True, "OP": "+"},
|
||||||
# {'ORTH': 'c'}])
|
{'ORTH': 'c'}])
|
||||||
# matches = matcher(doc)
|
matches = matcher(doc)
|
||||||
# assert len(matches) == 1
|
assert len(matches) == 1
|
||||||
# assert matches[0][1:] == (0, 3)
|
assert matches[0][1:] == (0, 3)
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_phrase_matcher(en_vocab):
|
def test_matcher_phrase_matcher(en_vocab):
|
||||||
# words = ["Google", "Now"]
|
words = ["Google", "Now"]
|
||||||
# doc = get_doc(en_vocab, words)
|
doc = get_doc(en_vocab, words)
|
||||||
# matcher = PhraseMatcher(en_vocab)
|
matcher = PhraseMatcher(en_vocab)
|
||||||
# matcher.add('COMPANY', None, doc)
|
matcher.add('COMPANY', None, doc)
|
||||||
# words = ["I", "like", "Google", "Now", "best"]
|
words = ["I", "like", "Google", "Now", "best"]
|
||||||
# doc = get_doc(en_vocab, words)
|
doc = get_doc(en_vocab, words)
|
||||||
# assert len(matcher(doc)) == 1
|
assert len(matcher(doc)) == 1
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_phrase_matcher_length(en_vocab):
|
def test_phrase_matcher_length(en_vocab):
|
||||||
# matcher = PhraseMatcher(en_vocab)
|
matcher = PhraseMatcher(en_vocab)
|
||||||
# assert len(matcher) == 0
|
assert len(matcher) == 0
|
||||||
# matcher.add('TEST', None, get_doc(en_vocab, ['test']))
|
matcher.add('TEST', None, get_doc(en_vocab, ['test']))
|
||||||
# assert len(matcher) == 1
|
assert len(matcher) == 1
|
||||||
# matcher.add('TEST2', None, get_doc(en_vocab, ['test2']))
|
matcher.add('TEST2', None, get_doc(en_vocab, ['test2']))
|
||||||
# assert len(matcher) == 2
|
assert len(matcher) == 2
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_phrase_matcher_contains(en_vocab):
|
def test_phrase_matcher_contains(en_vocab):
|
||||||
# matcher = PhraseMatcher(en_vocab)
|
matcher = PhraseMatcher(en_vocab)
|
||||||
# matcher.add('TEST', None, get_doc(en_vocab, ['test']))
|
matcher.add('TEST', None, get_doc(en_vocab, ['test']))
|
||||||
# assert 'TEST' in matcher
|
assert 'TEST' in matcher
|
||||||
# assert 'TEST2' not in matcher
|
assert 'TEST2' not in matcher
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_match_zero(matcher):
|
def test_matcher_match_zero(matcher):
|
||||||
# words1 = 'He said , " some words " ...'.split()
|
words1 = 'He said , " some words " ...'.split()
|
||||||
# words2 = 'He said , " some three words " ...'.split()
|
words2 = 'He said , " some three words " ...'.split()
|
||||||
# pattern1 = [{'ORTH': '"'},
|
pattern1 = [{'ORTH': '"'},
|
||||||
# {'OP': '!', 'IS_PUNCT': True},
|
{'OP': '!', 'IS_PUNCT': True},
|
||||||
# {'OP': '!', 'IS_PUNCT': True},
|
{'OP': '!', 'IS_PUNCT': True},
|
||||||
# {'ORTH': '"'}]
|
{'ORTH': '"'}]
|
||||||
# pattern2 = [{'ORTH': '"'},
|
pattern2 = [{'ORTH': '"'},
|
||||||
# {'IS_PUNCT': True},
|
{'IS_PUNCT': True},
|
||||||
# {'IS_PUNCT': True},
|
{'IS_PUNCT': True},
|
||||||
# {'IS_PUNCT': True},
|
{'IS_PUNCT': True},
|
||||||
# {'ORTH': '"'}]
|
{'ORTH': '"'}]
|
||||||
#
|
|
||||||
# matcher.add('Quote', None, pattern1)
|
matcher.add('Quote', None, pattern1)
|
||||||
# doc = get_doc(matcher.vocab, words1)
|
doc = get_doc(matcher.vocab, words1)
|
||||||
# assert len(matcher(doc)) == 1
|
assert len(matcher(doc)) == 1
|
||||||
#
|
|
||||||
# doc = get_doc(matcher.vocab, words2)
|
doc = get_doc(matcher.vocab, words2)
|
||||||
# assert len(matcher(doc)) == 0
|
assert len(matcher(doc)) == 0
|
||||||
# matcher.add('Quote', None, pattern2)
|
matcher.add('Quote', None, pattern2)
|
||||||
# assert len(matcher(doc)) == 0
|
assert len(matcher(doc)) == 0
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_match_zero_plus(matcher):
|
def test_matcher_match_zero_plus(matcher):
|
||||||
# words = 'He said , " some words " ...'.split()
|
words = 'He said , " some words " ...'.split()
|
||||||
# pattern = [{'ORTH': '"'},
|
pattern = [{'ORTH': '"'},
|
||||||
# {'OP': '*', 'IS_PUNCT': False},
|
{'OP': '*', 'IS_PUNCT': False},
|
||||||
# {'ORTH': '"'}]
|
{'ORTH': '"'}]
|
||||||
# matcher = Matcher(matcher.vocab)
|
matcher = Matcher(matcher.vocab)
|
||||||
# matcher.add('Quote', None, pattern)
|
matcher.add('Quote', None, pattern)
|
||||||
# doc = get_doc(matcher.vocab, words)
|
doc = get_doc(matcher.vocab, words)
|
||||||
# assert len(matcher(doc)) == 1
|
assert len(matcher(doc)) == 1
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_match_one_plus(matcher):
|
def test_matcher_match_one_plus(matcher):
|
||||||
# control = Matcher(matcher.vocab)
|
control = Matcher(matcher.vocab)
|
||||||
# control.add('BasicPhilippe', None, [{'ORTH': 'Philippe'}])
|
control.add('BasicPhilippe', None, [{'ORTH': 'Philippe'}])
|
||||||
# doc = get_doc(control.vocab, ['Philippe', 'Philippe'])
|
doc = get_doc(control.vocab, ['Philippe', 'Philippe'])
|
||||||
# m = control(doc)
|
m = control(doc)
|
||||||
# assert len(m) == 2
|
assert len(m) == 2
|
||||||
# matcher.add('KleenePhilippe', None, [{'ORTH': 'Philippe', 'OP': '1'},
|
matcher.add('KleenePhilippe', None, [{'ORTH': 'Philippe', 'OP': '1'},
|
||||||
# {'ORTH': 'Philippe', 'OP': '+'}])
|
{'ORTH': 'Philippe', 'OP': '+'}])
|
||||||
# m = matcher(doc)
|
m = matcher(doc)
|
||||||
# assert len(m) == 1
|
assert len(m) == 1
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_operator_combos(matcher):
|
def test_operator_combos(matcher):
|
||||||
# cases = [
|
cases = [
|
||||||
# ('aaab', 'a a a b', True),
|
('aaab', 'a a a b', True),
|
||||||
# ('aaab', 'a+ b', True),
|
('aaab', 'a+ b', True),
|
||||||
# ('aaab', 'a+ a+ b', True),
|
('aaab', 'a+ a+ b', True),
|
||||||
# ('aaab', 'a+ a+ a b', True),
|
('aaab', 'a+ a+ a b', True),
|
||||||
# ('aaab', 'a+ a+ a+ b', True),
|
('aaab', 'a+ a+ a+ b', True),
|
||||||
# ('aaab', 'a+ a a b', True),
|
('aaab', 'a+ a a b', True),
|
||||||
# ('aaab', 'a+ a a', True),
|
('aaab', 'a+ a a', True),
|
||||||
# ('aaab', 'a+', True),
|
('aaab', 'a+', True),
|
||||||
# ('aaa', 'a+ b', False),
|
('aaa', 'a+ b', False),
|
||||||
# ('aaa', 'a+ a+ b', False),
|
('aaa', 'a+ a+ b', False),
|
||||||
# ('aaa', 'a+ a+ a+ b', False),
|
('aaa', 'a+ a+ a+ b', False),
|
||||||
# ('aaa', 'a+ a b', False),
|
('aaa', 'a+ a b', False),
|
||||||
# ('aaa', 'a+ a a b', False),
|
('aaa', 'a+ a a b', False),
|
||||||
# ('aaab', 'a+ a a', True),
|
('aaab', 'a+ a a', True),
|
||||||
# ('aaab', 'a+', True),
|
('aaab', 'a+', True),
|
||||||
# ('aaab', 'a+ a b', True),
|
('aaab', 'a+ a b', True),
|
||||||
# ]
|
]
|
||||||
# for string, pattern_str, result in cases:
|
for string, pattern_str, result in cases:
|
||||||
# matcher = Matcher(matcher.vocab)
|
matcher = Matcher(matcher.vocab)
|
||||||
# doc = get_doc(matcher.vocab, words=list(string))
|
doc = get_doc(matcher.vocab, words=list(string))
|
||||||
# pattern = []
|
pattern = []
|
||||||
# for part in pattern_str.split():
|
for part in pattern_str.split():
|
||||||
# if part.endswith('+'):
|
if part.endswith('+'):
|
||||||
# pattern.append({'ORTH': part[0], 'op': '+'})
|
pattern.append({'ORTH': part[0], 'op': '+'})
|
||||||
# else:
|
else:
|
||||||
# pattern.append({'ORTH': part})
|
pattern.append({'ORTH': part})
|
||||||
# matcher.add('PATTERN', None, pattern)
|
matcher.add('PATTERN', None, pattern)
|
||||||
# matches = matcher(doc)
|
matches = matcher(doc)
|
||||||
# if result:
|
if result:
|
||||||
# assert matches, (string, pattern_str)
|
assert matches, (string, pattern_str)
|
||||||
# else:
|
else:
|
||||||
# assert not matches, (string, pattern_str)
|
assert not matches, (string, pattern_str)
|
||||||
#
|
|
||||||
#
|
|
||||||
#def test_matcher_end_zero_plus(matcher):
|
def test_matcher_end_zero_plus(matcher):
|
||||||
# '''Test matcher works when patterns end with * operator. (issue 1450)'''
|
'''Test matcher works when patterns end with * operator. (issue 1450)'''
|
||||||
# matcher = Matcher(matcher.vocab)
|
matcher = Matcher(matcher.vocab)
|
||||||
# matcher.add(
|
matcher.add(
|
||||||
# "TSTEND",
|
"TSTEND",
|
||||||
# None,
|
None,
|
||||||
# [
|
[
|
||||||
# {'ORTH': "a"},
|
{'ORTH': "a"},
|
||||||
# {'ORTH': "b", 'OP': "*"}
|
{'ORTH': "b", 'OP': "*"}
|
||||||
# ]
|
]
|
||||||
# )
|
)
|
||||||
# nlp = lambda string: Doc(matcher.vocab, words=string.split())
|
nlp = lambda string: Doc(matcher.vocab, words=string.split())
|
||||||
# assert len(matcher(nlp(u'a'))) == 1
|
assert len(matcher(nlp(u'a'))) == 1
|
||||||
# assert len(matcher(nlp(u'a b'))) == 2
|
assert len(matcher(nlp(u'a b'))) == 2
|
||||||
# assert len(matcher(nlp(u'a c'))) == 1
|
assert len(matcher(nlp(u'a c'))) == 1
|
||||||
# assert len(matcher(nlp(u'a b c'))) == 2
|
assert len(matcher(nlp(u'a b c'))) == 2
|
||||||
# assert len(matcher(nlp(u'a b b c'))) == 3
|
assert len(matcher(nlp(u'a b b c'))) == 3
|
||||||
# assert len(matcher(nlp(u'a b b'))) == 3
|
assert len(matcher(nlp(u'a b b'))) == 3
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user