def test_parse_sentences_with_dash_and_space():
assert Parser().parse('''\
1
00:01:00,000 --> 00:01:03,000
- I hope to see my friend.
- And shake his hand.
''') == [
Sentence('I hope to see my friend.', timedelta(minutes=1)),
Sentence('And shake his hand.', timedelta(minutes=1))
]
def test_parse_two_sentences():
assert Parser().parse('''\
1
00:01:00,000 --> 00:01:03,000
I hope to see my friend.
And shake his hand!
''') == [
Sentence('I hope to see my friend.', timedelta(minutes=1)),
Sentence('And shake his hand!', timedelta(minutes=1))
]
def test_exerpt_nearby_sentences():
sentences = [
Sentence("Duty calls.", td(seconds=25)),
Sentence("Gentlemen.", td(seconds=30)),
Sentence("I'll never understand.", td(seconds=31)),
Sentence("All these books, a world of knowledge, and what do you do?",
td(seconds=32)),
Sentence("Play poker all night.", td(seconds=33)),
Sentence("We got culture.", td(seconds=34)),
Sentence("We got culture coming out our asses.", td(seconds=35)),
Sentence("How's this for culture?", td(seconds=36)),
Sentence("Phone.", td(seconds=40))
]
excerptor = Excerptor(td(seconds=5))
excerpt = excerptor.excerpt(sentences, 3, 'knowledge')
assert excerpt == Excerpt([
sentences[1],
sentences[2],
sentences[3],
sentences[4],
sentences[5],
sentences[6],
sentences[7],
], 'knowledge')
def test_parse_two_sentences_across_multiple_lines():
assert Parser().parse('''\
1
00:01:00,000 --> 00:01:03,000
I hope to see my friend.
2
00:02:00,000 --> 00:02:03,000
And shake his hand.
''') == [
Sentence('I hope to see my friend.', timedelta(minutes=1)),
Sentence('And shake his hand.', timedelta(minutes=2))
]
def test_exerpt_nearby_sentences_at_end():
sentences = [
Sentence("Roads?", td(minutes=90)),
Sentence("Where we're going we don't need roads.", td(minutes=90))
]
excerptor = Excerptor(td(seconds=5))
excerpt = excerptor.excerpt(sentences, 1, 'roads')
assert excerpt == Excerpt([
sentences[0],
sentences[1],
], 'roads')
def test_exerpt_nearby_sentences_at_start():
sentences = [
Sentence("All right, there are five billion people on earth.",
td(seconds=0)),
Sentence("When I was a kid there were three.", td(seconds=1))
]
excerptor = Excerptor(td(seconds=5))
excerpt = excerptor.excerpt(sentences, 0, 'billion')
assert excerpt == Excerpt([
sentences[0],
sentences[1],
], 'billion')
def test_parse_simple_multiline_sentence():
assert Parser().parse('''\
1
00:01:00,000 --> 00:01:03,000
I hope to see my friend
and shake his hand.
''') == [
Sentence('I hope to see my friend and shake his hand.',
timedelta(minutes=1))
]
def test_parse_sentence_connected_with_ellipses():
assert Parser().parse('''\
1
00:01:00,000 --> 00:01:03,000
I hope to see my friend...
2
00:01:00,000 --> 00:01:03,000
...and shake his hand.
''') == [
Sentence('I hope to see my friend and shake his hand.',
timedelta(minutes=1))
]
def test_analysis_yields_excerpts():
text = '''\
1
02:11:39,473 --> 02:11:42,375
I hoped to see my friend.
I hoped.
'''
_, analysis = cached_analyse(text)
s1 = Sentence('I hoped to see my friend.', timedelta(0, 7899, 473000))
s2 = Sentence('I hoped.', timedelta(0, 7899, 473000))
assert dict(analysis.word_with_excerpts) == {
Word('I', PartOfSpeach.OTHER):
[Excerpt([s1, s2], 'I'),
Excerpt([s1, s2], 'I')],
Word('hop', PartOfSpeach.VERB):
[Excerpt([s1, s2], 'hoped'),
Excerpt([s1, s2], 'hoped')],
Word('to', PartOfSpeach.OTHER): [Excerpt([s1, s2], 'to')],
Word('see', PartOfSpeach.VERB): [Excerpt([s1, s2], 'see')],
Word('my', PartOfSpeach.OTHER): [Excerpt([s1, s2], 'my')],
Word('friend', PartOfSpeach.NOUN): [Excerpt([s1, s2], 'friend')]
}
def test_parse_sentences_with_html():
assert Parser().parse('''\
1
00:01:00,000 --> 00:01:03,000
<i>I hope to see my friend.</i>
''') == [Sentence('I hope to see my friend.', timedelta(minutes=1))]