Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update matcher tests

This commit is contained in:
Matthew Honnibal 2016-10-17 01:53:24 +02:00
parent 0cf4aff470
commit 8951bf6989
1 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
spacy/tests/test_matcher.py
View File

@ -24,30 +24,30 @@ def test_compile(matcher):
def test_no_match(matcher): def test_no_match(matcher):
doc = Doc(matcher.vocab, ['I', 'like', 'cheese', '.']) doc = Doc(matcher.vocab, words=['I', 'like', 'cheese', '.'])
assert matcher(doc) == [] assert matcher(doc) == []
def test_match_start(matcher): def test_match_start(matcher):
doc = Doc(matcher.vocab, ['JavaScript', 'is', 'good']) doc = Doc(matcher.vocab, words=['JavaScript', 'is', 'good'])
assert matcher(doc) == [(matcher.vocab.strings['JS'], assert matcher(doc) == [(matcher.vocab.strings['JS'],
matcher.vocab.strings['PRODUCT'], 0, 1)] matcher.vocab.strings['PRODUCT'], 0, 1)]
def test_match_end(matcher): def test_match_end(matcher):
doc = Doc(matcher.vocab, ['I', 'like', 'java']) doc = Doc(matcher.vocab, words=['I', 'like', 'java'])
assert matcher(doc) == [(doc.vocab.strings['Java'], assert matcher(doc) == [(doc.vocab.strings['Java'],
doc.vocab.strings['PRODUCT'], 2, 3)] doc.vocab.strings['PRODUCT'], 2, 3)]
def test_match_middle(matcher): def test_match_middle(matcher):
doc = Doc(matcher.vocab, ['I', 'like', 'Google', 'Now', 'best']) doc = Doc(matcher.vocab, words=['I', 'like', 'Google', 'Now', 'best'])
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'], assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
doc.vocab.strings['PRODUCT'], 2, 4)] doc.vocab.strings['PRODUCT'], 2, 4)]
def test_match_multi(matcher): def test_match_multi(matcher):
doc = Doc(matcher.vocab, 'I like Google Now and java best'.split()) doc = Doc(matcher.vocab, words='I like Google Now and java best'.split())
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'], assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
doc.vocab.strings['PRODUCT'], 2, 4), doc.vocab.strings['PRODUCT'], 2, 4),
(doc.vocab.strings['Java'], (doc.vocab.strings['Java'],
@ -61,9 +61,9 @@ def test_match_zero(matcher):
{'OP': '!', 'IS_PUNCT': True}, {'OP': '!', 'IS_PUNCT': True},
{'ORTH': '"'} {'ORTH': '"'}
]]) ]])
doc = Doc(matcher.vocab, 'He said , " some words " ...'.split()) doc = Doc(matcher.vocab, words='He said , " some words " ...'.split())
assert len(matcher(doc)) == 1 assert len(matcher(doc)) == 1
doc = Doc(matcher.vocab, 'He said , " some three words " ...'.split()) doc = Doc(matcher.vocab, words='He said , " some three words " ...'.split())
assert len(matcher(doc)) == 0 assert len(matcher(doc)) == 0
matcher.add('Quote', '', {}, [ matcher.add('Quote', '', {}, [
[ [
@ -83,24 +83,24 @@ def test_match_zero_plus(matcher):
{'OP': '*', 'IS_PUNCT': False}, {'OP': '*', 'IS_PUNCT': False},
{'ORTH': '"'} {'ORTH': '"'}
]]) ]])
doc = Doc(matcher.vocab, 'He said , " some words " ...'.split()) doc = Doc(matcher.vocab, words='He said , " some words " ...'.split())
assert len(matcher(doc)) == 1 assert len(matcher(doc)) == 1
@pytest.mark.models #@pytest.mark.models
def test_match_preserved(EN): #def test_match_preserved(EN):
patterns = { # patterns = {
'JS': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]], # 'JS': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]],
'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]], # 'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]],
'Java': ['PRODUCT', {}, [[{'LOWER': 'java'}]]], # 'Java': ['PRODUCT', {}, [[{'LOWER': 'java'}]]],
} # }
matcher = Matcher(EN.vocab, patterns) # matcher = Matcher(EN.vocab, patterns)
doc = EN.tokenizer('I like java.') # doc = EN.tokenizer('I like java.')
EN.tagger(doc) # EN.tagger(doc)
assert len(doc.ents) == 0 # assert len(doc.ents) == 0
doc = EN.tokenizer('I like java.') # doc = EN.tokenizer('I like java.')
doc.ents += tuple(matcher(doc)) # doc.ents += tuple(matcher(doc))
assert len(doc.ents) == 1 # assert len(doc.ents) == 1
EN.tagger(doc) # EN.tagger(doc)
EN.entity(doc) # EN.entity(doc)
assert len(doc.ents) == 1 # assert len(doc.ents) == 1