From 980ad68cbe26a62c337bbf58dfce13e283013fe7 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Fri, 23 Feb 2018 21:27:53 +0100 Subject: [PATCH] Try to find test that fails on appveyor --- spacy/tests/test_matcher.py | 134 ++++++++++++++++++------------------ 1 file changed, 67 insertions(+), 67 deletions(-) diff --git a/spacy/tests/test_matcher.py b/spacy/tests/test_matcher.py index f191506f3..a690464bb 100644 --- a/spacy/tests/test_matcher.py +++ b/spacy/tests/test_matcher.py @@ -26,73 +26,73 @@ def matcher(en_vocab): return matcher -#def test_matcher_from_api_docs(en_vocab): -# matcher = Matcher(en_vocab) -# pattern = [{'ORTH': 'test'}] -# assert len(matcher) == 0 -# matcher.add('Rule', None, pattern) -# assert len(matcher) == 1 -# matcher.remove('Rule') -# assert 'Rule' not in matcher -# matcher.add('Rule', None, pattern) -# assert 'Rule' in matcher -# on_match, patterns = matcher.get('Rule') -# assert len(patterns[0]) -# -# -#def test_matcher_from_usage_docs(en_vocab): -# text = "Wow 😀 This is really cool! 😂 😂" -# doc = get_doc(en_vocab, words=text.split(' ')) -# pos_emoji = [u'😀', u'😃', u'😂', u'🤣', u'😊', u'😍'] -# pos_patterns = [[{'ORTH': emoji}] for emoji in pos_emoji] -# -# def label_sentiment(matcher, doc, i, matches): -# match_id, start, end = matches[i] -# if doc.vocab.strings[match_id] == 'HAPPY': -# doc.sentiment += 0.1 -# span = doc[start : end] -# token = span.merge() -# token.vocab[token.text].norm_ = 'happy emoji' -# -# matcher = Matcher(en_vocab) -# matcher.add('HAPPY', label_sentiment, *pos_patterns) -# matches = matcher(doc) -# assert doc.sentiment != 0 -# assert doc[1].norm_ == 'happy emoji' -# -# -#@pytest.mark.parametrize('words', [["Some", "words"]]) -#def test_matcher_init(en_vocab, words): -# matcher = Matcher(en_vocab) -# doc = get_doc(en_vocab, words) -# assert len(matcher) == 0 -# assert matcher(doc) == [] -# -# -#def test_matcher_contains(matcher): -# matcher.add('TEST', None, [{'ORTH': 'test'}]) -# assert 'TEST' in matcher -# assert 'TEST2' not in matcher -# -# -#def test_matcher_no_match(matcher): -# words = ["I", "like", "cheese", "."] -# doc = get_doc(matcher.vocab, words) -# assert matcher(doc) == [] -# -# -#def test_matcher_compile(en_vocab): -# rules = { -# 'JS': [[{'ORTH': 'JavaScript'}]], -# 'GoogleNow': [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]], -# 'Java': [[{'LOWER': 'java'}]] -# } -# matcher = Matcher(en_vocab) -# for key, patterns in rules.items(): -# matcher.add(key, None, *patterns) -# assert len(matcher) == 3 -# -# +def test_matcher_from_api_docs(en_vocab): + matcher = Matcher(en_vocab) + pattern = [{'ORTH': 'test'}] + assert len(matcher) == 0 + matcher.add('Rule', None, pattern) + assert len(matcher) == 1 + matcher.remove('Rule') + assert 'Rule' not in matcher + matcher.add('Rule', None, pattern) + assert 'Rule' in matcher + on_match, patterns = matcher.get('Rule') + assert len(patterns[0]) + + +def test_matcher_from_usage_docs(en_vocab): + text = "Wow 😀 This is really cool! 😂 😂" + doc = get_doc(en_vocab, words=text.split(' ')) + pos_emoji = [u'😀', u'😃', u'😂', u'🤣', u'😊', u'😍'] + pos_patterns = [[{'ORTH': emoji}] for emoji in pos_emoji] + + def label_sentiment(matcher, doc, i, matches): + match_id, start, end = matches[i] + if doc.vocab.strings[match_id] == 'HAPPY': + doc.sentiment += 0.1 + span = doc[start : end] + token = span.merge() + token.vocab[token.text].norm_ = 'happy emoji' + + matcher = Matcher(en_vocab) + matcher.add('HAPPY', label_sentiment, *pos_patterns) + matches = matcher(doc) + assert doc.sentiment != 0 + assert doc[1].norm_ == 'happy emoji' + + +@pytest.mark.parametrize('words', [["Some", "words"]]) +def test_matcher_init(en_vocab, words): + matcher = Matcher(en_vocab) + doc = get_doc(en_vocab, words) + assert len(matcher) == 0 + assert matcher(doc) == [] + + +def test_matcher_contains(matcher): + matcher.add('TEST', None, [{'ORTH': 'test'}]) + assert 'TEST' in matcher + assert 'TEST2' not in matcher + + +def test_matcher_no_match(matcher): + words = ["I", "like", "cheese", "."] + doc = get_doc(matcher.vocab, words) + assert matcher(doc) == [] + + +def test_matcher_compile(en_vocab): + rules = { + 'JS': [[{'ORTH': 'JavaScript'}]], + 'GoogleNow': [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]], + 'Java': [[{'LOWER': 'java'}]] + } + matcher = Matcher(en_vocab) + for key, patterns in rules.items(): + matcher.add(key, None, *patterns) + assert len(matcher) == 3 + + #def test_matcher_match_start(matcher): # words = ["JavaScript", "is", "good"] # doc = get_doc(matcher.vocab, words)