explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 12:18:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Upd tests

Browse Source
This commit is contained in:
Matthew Honnibal 2015-09-06 05:40:10 +02:00
parent 5edac11225
commit 571b6eda88
2 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/parser/test_initial_actions_parse.py
View File

@ -4,7 +4,10 @@ import pytest
def test_initial(EN): def test_initial(EN):
doc = EN.tokenizer(u'I ate the pizza with anchovies.') doc = EN.tokenizer(u'I ate the pizza with anchovies.')
EN.tagger(doc) EN.tagger(doc)
next_actions = EN.parser.partial(doc, ['L-nsubj', 'S', 'L-det']) with EN.parser.step_through(doc) as stepwise:
stepwise.transition('L-nsubj')
stepwise.transition('S')
stepwise.transition('L-det')
assert doc[0].head.i == 1 assert doc[0].head.i == 1
assert doc[1].head.i == 1 assert doc[1].head.i == 1
assert doc[2].head.i == 3 assert doc[2].head.i == 3

12
tests/test_matcher.py
View File

@ -3,7 +3,7 @@ import pytest
from spacy.strings import StringStore from spacy.strings import StringStore
from spacy.matcher import * from spacy.matcher import *
from spacy.attrs import ORTH from spacy.attrs import LOWER
from spacy.tokens.doc import Doc from spacy.tokens.doc import Doc
from spacy.vocab import Vocab from spacy.vocab import Vocab
@ -13,7 +13,7 @@ def matcher(EN):
patterns = { patterns = {
'Javascript': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]], 'Javascript': ['PRODUCT', {}, [[{'ORTH': 'JavaScript'}]]],
'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]], 'GoogleNow': ['PRODUCT', {}, [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]]],
'Java': ['PRODUCT', {}, [[{'ORTH': 'Java'}]]], 'Java': ['PRODUCT', {}, [[{'LOWER': 'java'}]]],
} }
return Matcher(EN.vocab, patterns) return Matcher(EN.vocab, patterns)
@ -33,7 +33,7 @@ def test_match_start(matcher, EN):
def test_match_end(matcher, EN): def test_match_end(matcher, EN):
tokens = EN('I like Java') tokens = EN('I like java')
assert matcher(tokens) == [(EN.vocab.strings['PRODUCT'], 2, 3)] assert matcher(tokens) == [(EN.vocab.strings['PRODUCT'], 2, 3)]
@ -43,17 +43,17 @@ def test_match_middle(matcher, EN):
def test_match_multi(matcher, EN): def test_match_multi(matcher, EN):
tokens = EN('I like Google Now and Java best') tokens = EN('I like Google Now and java best')
assert matcher(tokens) == [(EN.vocab.strings['PRODUCT'], 2, 4), assert matcher(tokens) == [(EN.vocab.strings['PRODUCT'], 2, 4),
(EN.vocab.strings['PRODUCT'], 5, 6)] (EN.vocab.strings['PRODUCT'], 5, 6)]
def test_match_preserved(matcher, EN): def test_match_preserved(matcher, EN):
doc = EN.tokenizer('I like Java') doc = EN.tokenizer('I like java')
EN.tagger(doc) EN.tagger(doc)
EN.entity(doc) EN.entity(doc)
assert len(doc.ents) == 0 assert len(doc.ents) == 0
doc = EN.tokenizer('I like Java') doc = EN.tokenizer('I like java')
matcher(doc) matcher(doc)
assert len(doc.ents) == 1 assert len(doc.ents) == 1
EN.tagger(doc) EN.tagger(doc)