explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 16:07:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
This reverts commit f8d3e3bcfe.
This commit is contained in:
Matthew Honnibal 2016-10-17 16:49:49 +02:00
parent 4bf2c53c13
commit 7d446e5094
1 changed files with 22 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
spacy/tests/test_matcher.py
View File

@ -31,32 +31,27 @@ def test_no_match(matcher):
def test_match_start(matcher): def test_match_start(matcher):
doc = Doc(matcher.vocab, words=['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, len('JavaScript'))] matcher.vocab.strings['PRODUCT'], 0, 1)]
def test_match_end(matcher): def test_match_end(matcher):
doc = Doc(matcher.vocab, words=['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'], doc.vocab.strings['PRODUCT'], 2, 3)]
len('I like '), len('I like java'))]
def test_match_middle(matcher): def test_match_middle(matcher):
doc = Doc(matcher.vocab, words=['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'], len('I like '), doc.vocab.strings['PRODUCT'], 2, 4)]
len('I like Google Now'))]
def test_match_multi(matcher): def test_match_multi(matcher):
doc = Doc(matcher.vocab, words='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'], len('I like '), doc.vocab.strings['PRODUCT'], 2, 4),
len('I like Google Now')),
(doc.vocab.strings['Java'], (doc.vocab.strings['Java'],
doc.vocab.strings['PRODUCT'], doc.vocab.strings['PRODUCT'], 5, 6)]
len('I like Google Now and '),
len('I like Google Now and java'))]
def test_match_zero(matcher): def test_match_zero(matcher):
matcher.add('Quote', '', {}, [ matcher.add('Quote', '', {}, [
@ -92,20 +87,20 @@ def test_match_zero_plus(matcher):
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