explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-27 09:44:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove old tests

Browse Source
This commit is contained in:
Ines Montani 2017-01-13 01:34:48 +01:00
parent 12eb8edf26
commit a308703f47
7 changed files with 0 additions and 129 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
setup.py
View File

@ -37,7 +37,6 @@ PACKAGES = [
'spacy.munge', 'spacy.munge',
'spacy.tests', 'spacy.tests',
'spacy.tests.matcher', 'spacy.tests.matcher',
'spacy.tests.munge',
'spacy.tests.parser', 'spacy.tests.parser',
'spacy.tests.serialize', 'spacy.tests.serialize',
'spacy.tests.spans', 'spacy.tests.spans',

0
spacy/tests/munge/__init__.py
View File

32
spacy/tests/munge/test_align.py
View File

@ -1,32 +0,0 @@
from spacy.deprecated import align_tokens
def test_perfect_align():
ref = ['I', 'align', 'perfectly']
indices = []
i = 0
for token in ref:
indices.append((i, i + len(token)))
i += len(token)
aligned = list(align_tokens(ref, indices))
assert aligned[0] == ('I', [(0, 1)])
assert aligned[1] == ('align', [(1, 6)])
assert aligned[2] == ('perfectly', [(6, 15)])
def test_hyphen_align():
ref = ['I', 'must', 're-align']
indices = [(0, 1), (1, 5), (5, 7), (7, 8), (8, 13)]
aligned = list(align_tokens(ref, indices))
assert aligned[0] == ('I', [(0, 1)])
assert aligned[1] == ('must', [(1, 5)])
assert aligned[2] == ('re-align', [(5, 7), (7, 8), (8, 13)])
def test_align_continue():
ref = ['I', 'must', 're-align', 'and', 'continue']
indices = [(0, 1), (1, 5), (5, 7), (7, 8), (8, 13), (13, 16), (16, 24)]
aligned = list(align_tokens(ref, indices))
assert aligned[2] == ('re-align', [(5, 7), (7, 8), (8, 13)])
assert aligned[3] == ('and', [(13, 16)])
assert aligned[4] == ('continue', [(16, 24)])

59
spacy/tests/munge/test_bad_periods.py
View File

@ -1,59 +0,0 @@
import spacy.munge.read_conll
hongbin_example = """
1 2. 0. LS _ 24 meta _ _ _
2 . . . _ 1 punct _ _ _
3 Wang wang NNP _ 4 compound _ _ _
4 Hongbin hongbin NNP _ 16 nsubj _ _ _
5 , , , _ 4 punct _ _ _
6 the the DT _ 11 det _ _ _
7 " " `` _ 11 punct _ _ _
8 communist communist JJ _ 11 amod _ _ _
9 trail trail NN _ 11 compound _ _ _
10 - - HYPH _ 11 punct _ _ _
11 blazer blazer NN _ 4 appos _ _ _
12 , , , _ 16 punct _ _ _
13 " " '' _ 16 punct _ _ _
14 has have VBZ _ 16 aux _ _ _
15 not not RB _ 16 neg _ _ _
16 turned turn VBN _ 24 ccomp _ _ _
17 into into IN syn=CLR 16 prep _ _ _
18 a a DT _ 19 det _ _ _
19 capitalist capitalist NN _ 17 pobj _ _ _
20 ( ( -LRB- _ 24 punct _ _ _
21 he he PRP _ 24 nsubj _ _ _
22 does do VBZ _ 24 aux _ _ _
23 n't not RB _ 24 neg _ _ _
24 have have VB _ 0 root _ _ _
25 any any DT _ 26 det _ _ _
26 shares share NNS _ 24 dobj _ _ _
27 , , , _ 24 punct _ _ _
28 does do VBZ _ 30 aux _ _ _
29 n't not RB _ 30 neg _ _ _
30 have have VB _ 24 conj _ _ _
31 any any DT _ 32 det _ _ _
32 savings saving NNS _ 30 dobj _ _ _
33 , , , _ 30 punct _ _ _
34 does do VBZ _ 36 aux _ _ _
35 n't not RB _ 36 neg _ _ _
36 have have VB _ 30 conj _ _ _
37 his his PRP$ _ 39 poss _ _ _
38 own own JJ _ 39 amod _ _ _
39 car car NN _ 36 dobj _ _ _
40 , , , _ 36 punct _ _ _
41 and and CC _ 36 cc _ _ _
42 does do VBZ _ 44 aux _ _ _
43 n't not RB _ 44 neg _ _ _
44 have have VB _ 36 conj _ _ _
45 a a DT _ 46 det _ _ _
46 mansion mansion NN _ 44 dobj _ _ _
47 ; ; . _ 24 punct _ _ _
""".strip()
def test_hongbin():
words, annot = spacy.munge.read_conll.parse(hongbin_example, strip_bad_periods=True)
assert words[annot[0]['head']] == 'have'
assert words[annot[1]['head']] == 'Hongbin'

21
spacy/tests/munge/test_detokenize.py
View File

@ -1,21 +0,0 @@
from spacy.deprecated import detokenize
def test_punct():
tokens = 'Pierre Vinken , 61 years old .'.split()
detoks = [(0,), (1, 2), (3,), (4,), (5, 6)]
token_rules = ('<SEP>,', '<SEP>.')
assert detokenize(token_rules, tokens) == detoks
def test_contractions():
tokens = "I ca n't even".split()
detoks = [(0,), (1, 2), (3,)]
token_rules = ("ca<SEP>n't",)
assert detokenize(token_rules, tokens) == detoks
def test_contractions_punct():
tokens = "I ca n't !".split()
detoks = [(0,), (1, 2, 3)]
token_rules = ("ca<SEP>n't", '<SEP>!')
assert detokenize(token_rules, tokens) == detoks

16
spacy/tests/munge/test_onto_ner.py
View File

@ -1,16 +0,0 @@
from spacy.munge.read_ner import _get_text, _get_tag
def test_get_text():
assert _get_text('asbestos') == 'asbestos'
assert _get_text('<ENAMEX TYPE="ORG">Lorillard</ENAMEX>') == 'Lorillard'
assert _get_text('<ENAMEX TYPE="DATE">more') == 'more'
assert _get_text('ago</ENAMEX>') == 'ago'
def test_get_tag():
assert _get_tag('asbestos', None) == ('O', None)
assert _get_tag('asbestos', 'PER') == ('I-PER', 'PER')
assert _get_tag('<ENAMEX TYPE="ORG">Lorillard</ENAMEX>', None) == ('U-ORG', None)
assert _get_tag('<ENAMEX TYPE="DATE">more', None) == ('B-DATE', 'DATE')
assert _get_tag('ago</ENAMEX>', 'DATE') == ('L-DATE', None)

0
spacy/tests/unit/__init__.py
View File