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

Update matcher test, to reflect character offset return instead of token offset.

This commit is contained in:
Matthew Honnibal 2016-10-17 16:00:10 +02:00
parent 049c937540
commit f8d3e3bcfe
1 changed files with 27 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
spacy/tests/test_matcher.py
View File

@ -31,27 +31,32 @@ def test_no_match(matcher):
def test_match_start(matcher):
doc = Doc(matcher.vocab, words=['JavaScript', 'is', 'good'])
assert matcher(doc) == [(matcher.vocab.strings['JS'],
matcher.vocab.strings['PRODUCT'], 0, 1)]
matcher.vocab.strings['PRODUCT'], 0, len('JavaScript'))]
def test_match_end(matcher):
doc = Doc(matcher.vocab, words=['I', 'like', 'java'])
assert matcher(doc) == [(doc.vocab.strings['Java'],
doc.vocab.strings['PRODUCT'], 2, 3)]
doc.vocab.strings['PRODUCT'],
len('I like '), len('I like java'))]
def test_match_middle(matcher):
doc = Doc(matcher.vocab, words=['I', 'like', 'Google', 'Now', 'best'])
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
doc.vocab.strings['PRODUCT'], 2, 4)]
doc.vocab.strings['PRODUCT'], len('I like '),
len('I like Google Now'))]
def test_match_multi(matcher):
doc = Doc(matcher.vocab, words='I like Google Now and java best'.split())
assert matcher(doc) == [(doc.vocab.strings['GoogleNow'],
doc.vocab.strings['PRODUCT'], 2, 4),
doc.vocab.strings['PRODUCT'], len('I like '),
len('I like Google Now')),
(doc.vocab.strings['Java'],
doc.vocab.strings['PRODUCT'], 5, 6)]
doc.vocab.strings['PRODUCT'],
len('I like Google Now and '),
len('I like Google Now and java'))]
def test_match_zero(matcher):
matcher.add('Quote', '', {}, [
@ -87,20 +92,20 @@ def test_match_zero_plus(matcher):
assert len(matcher(doc)) == 1
#@pytest.mark.models
#def test_match_preserved(EN):
# patterns = {
# 'JS': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]],
# 'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]],
# 'Java': ['PRODUCT', {}, [[{'LOWER': 'java'}]]],
# }
# matcher = Matcher(EN.vocab, patterns)
# doc = EN.tokenizer('I like java.')
# EN.tagger(doc)
# assert len(doc.ents) == 0
# doc = EN.tokenizer('I like java.')
# doc.ents += tuple(matcher(doc))
# assert len(doc.ents) == 1
# EN.tagger(doc)
# EN.entity(doc)
# assert len(doc.ents) == 1
@pytest.mark.models
def test_match_preserved(EN):
patterns = {
'JS': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]],
'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]],
'Java': ['PRODUCT', {}, [[{'LOWER': 'java'}]]],
}
matcher = Matcher(EN.vocab, patterns)
doc = EN.tokenizer('I like java.')
EN.tagger(doc)
assert len(doc.ents) == 0
doc = EN.tokenizer('I like java.')
doc.ents += tuple(matcher(doc))
assert len(doc.ents) == 1
EN.tagger(doc)
EN.entity(doc)
assert len(doc.ents) == 1