explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 18:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix .merge tests to not use deprecated API

Browse Source
This commit is contained in:
ines 2017-11-01 16:49:11 +01:00
parent 705a4e3e4a
commit 5914faafbb
2 changed files with 21 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/tests/doc/test_doc_api.py
View File

@ -127,7 +127,8 @@ def test_doc_api_merge(en_tokenizer):
# merge 'The Beach Boys' # merge 'The Beach Boys'
doc = en_tokenizer(text) doc = en_tokenizer(text)
assert len(doc) == 9 assert len(doc) == 9
doc.merge(doc[4].idx, doc[6].idx + len(doc[6]), 'NAMED', 'LEMMA', 'TYPE') doc.merge(doc[4].idx, doc[6].idx + len(doc[6]), tag='NAMED', lemma='LEMMA',
ent_type='TYPE')
assert len(doc) == 7 assert len(doc) == 7
assert doc[4].text == 'the beach boys' assert doc[4].text == 'the beach boys'
assert doc[4].text_with_ws == 'the beach boys ' assert doc[4].text_with_ws == 'the beach boys '
@ -136,7 +137,8 @@ def test_doc_api_merge(en_tokenizer):
# merge 'all night' # merge 'all night'
doc = en_tokenizer(text) doc = en_tokenizer(text)
assert len(doc) == 9 assert len(doc) == 9
doc.merge(doc[7].idx, doc[8].idx + len(doc[8]), 'NAMED', 'LEMMA', 'TYPE') doc.merge(doc[7].idx, doc[8].idx + len(doc[8]), tag='NAMED', lemma='LEMMA',
ent_type='TYPE')
assert len(doc) == 8 assert len(doc) == 8
assert doc[7].text == 'all night' assert doc[7].text == 'all night'
assert doc[7].text_with_ws == 'all night' assert doc[7].text_with_ws == 'all night'
@ -147,7 +149,8 @@ def test_doc_api_merge_children(en_tokenizer):
text = "WKRO played songs by the beach boys all night" text = "WKRO played songs by the beach boys all night"
doc = en_tokenizer(text) doc = en_tokenizer(text)
assert len(doc) == 9 assert len(doc) == 9
doc.merge(doc[4].idx, doc[6].idx + len(doc[6]), 'NAMED', 'LEMMA', 'TYPE') doc.merge(doc[4].idx, doc[6].idx + len(doc[6]), tag='NAMED', lemma='LEMMA',
ent_type='TYPE')
for word in doc: for word in doc:
if word.i < word.head.i: if word.i < word.head.i:
@ -159,8 +162,8 @@ def test_doc_api_merge_children(en_tokenizer):
def test_doc_api_merge_hang(en_tokenizer): def test_doc_api_merge_hang(en_tokenizer):
text = "through North and South Carolina" text = "through North and South Carolina"
doc = en_tokenizer(text) doc = en_tokenizer(text)
doc.merge(18, 32, '', '', 'ORG') doc.merge(18, 32, tag='', lemma='', ent_type='ORG')
doc.merge(8, 32, '', '', 'ORG') doc.merge(8, 32, tag='', lemma='', ent_type='ORG')
def test_doc_api_sents_empty_string(en_tokenizer): def test_doc_api_sents_empty_string(en_tokenizer):
@ -188,7 +191,8 @@ def test_doc_api_runtime_error(en_tokenizer):
if len(np) > 1: if len(np) > 1:
nps.append((np.start_char, np.end_char, np.root.tag_, np.text, np.root.ent_type_)) nps.append((np.start_char, np.end_char, np.root.tag_, np.text, np.root.ent_type_))
for np in nps: for np in nps:
doc.merge(*np) start, end, tag, lemma, ent_type = np
doc.merge(start, end, tag=tag, lemma=lemma, ent_type=ent_type)
def test_doc_api_right_edge(en_tokenizer): def test_doc_api_right_edge(en_tokenizer):

18
spacy/tests/spans/test_merge.py
View File

@ -14,7 +14,7 @@ def test_spans_merge_tokens(en_tokenizer):
assert len(doc) == 4 assert len(doc) == 4
assert doc[0].head.text == 'Angeles' assert doc[0].head.text == 'Angeles'
assert doc[1].head.text == 'start' assert doc[1].head.text == 'start'
doc.merge(0, len('Los Angeles'), 'NNP', 'Los Angeles', 'GPE') doc.merge(0, len('Los Angeles'), tag='NNP', lemma='Los Angeles', ent_type='GPE')
assert len(doc) == 3 assert len(doc) == 3
assert doc[0].text == 'Los Angeles' assert doc[0].text == 'Los Angeles'
assert doc[0].head.text == 'start' assert doc[0].head.text == 'start'
@ -36,7 +36,8 @@ def test_spans_merge_heads(en_tokenizer):
doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads) doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads)
assert len(doc) == 8 assert len(doc) == 8
doc.merge(doc[3].idx, doc[4].idx + len(doc[4]), doc[4].tag_, 'pilates class', 'O') doc.merge(doc[3].idx, doc[4].idx + len(doc[4]), tag=doc[4].tag_,
lemma='pilates class', ent_type='O')
assert len(doc) == 7 assert len(doc) == 7
assert doc[0].head.i == 1 assert doc[0].head.i == 1
assert doc[1].head.i == 1 assert doc[1].head.i == 1
@ -53,7 +54,8 @@ def test_span_np_merges(en_tokenizer):
doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads) doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads)
assert doc[4].head.i == 1 assert doc[4].head.i == 1
doc.merge(doc[2].idx, doc[4].idx + len(doc[4]), 'NP', 'tool', 'O') doc.merge(doc[2].idx, doc[4].idx + len(doc[4]), tag='NP', lemma='tool',
ent_type='O')
assert doc[2].head.i == 1 assert doc[2].head.i == 1
text = "displaCy is a lightweight and modern dependency parse tree visualization tool built with CSS3 and JavaScript." text = "displaCy is a lightweight and modern dependency parse tree visualization tool built with CSS3 and JavaScript."
@ -63,7 +65,7 @@ def test_span_np_merges(en_tokenizer):
ents = [(e[0].idx, e[-1].idx + len(e[-1]), e.label_, e.lemma_) for e in doc.ents] ents = [(e[0].idx, e[-1].idx + len(e[-1]), e.label_, e.lemma_) for e in doc.ents]
for start, end, label, lemma in ents: for start, end, label, lemma in ents:
merged = doc.merge(start, end, label, lemma, label) merged = doc.merge(start, end, tag=label, lemma=lemma, ent_type=label)
assert merged != None, (start, end, label, lemma) assert merged != None, (start, end, label, lemma)
@ -88,7 +90,7 @@ def test_spans_entity_merge(en_tokenizer):
assert len(doc) == 17 assert len(doc) == 17
for ent in doc.ents: for ent in doc.ents:
label, lemma, type_ = (ent.root.tag_, ent.root.lemma_, max(w.ent_type_ for w in ent)) label, lemma, type_ = (ent.root.tag_, ent.root.lemma_, max(w.ent_type_ for w in ent))
ent.merge(label, lemma, type_) ent.merge(label=label, lemma=lemma, ent_type=type_)
# check looping is ok # check looping is ok
assert len(doc) == 15 assert len(doc) == 15
@ -105,8 +107,8 @@ def test_spans_sentence_update_after_merge(en_tokenizer):
sent1, sent2 = list(doc.sents) sent1, sent2 = list(doc.sents)
init_len = len(sent1) init_len = len(sent1)
init_len2 = len(sent2) init_len2 = len(sent2)
doc[0:2].merge('none', 'none', 'none') doc[0:2].merge(label='none', lemma='none', ent_type='none')
doc[-2:].merge('none', 'none', 'none') doc[-2:].merge(label='none', lemma='none', ent_type='none')
assert len(sent1) == init_len - 1 assert len(sent1) == init_len - 1
assert len(sent2) == init_len2 - 1 assert len(sent2) == init_len2 - 1
@ -122,5 +124,5 @@ def test_spans_subtree_size_check(en_tokenizer):
doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps) doc = get_doc(tokens.vocab, [t.text for t in tokens], heads=heads, deps=deps)
sent1 = list(doc.sents)[0] sent1 = list(doc.sents)[0]
init_len = len(list(sent1.root.subtree)) init_len = len(list(sent1.root.subtree))
doc[0:2].merge('none', 'none', 'none') doc[0:2].merge(label='none', lemma='none', ent_type='none')
assert len(list(sent1.root.subtree)) == init_len - 1 assert len(list(sent1.root.subtree)) == init_len - 1