def test_overlap_diff_metadata(self):
"""
Merge with overlap in utterance id and utterance has same data but diff metadata
Second corpus utterance metadata should override if the keys are the same.
"""
corpus1 = Corpus(utterances=[
Utterance(id="0", text="hello world", user=User(id="alice")),
Utterance(id="1", text="my name is bob", user=User(id="bob")),
Utterance(id="2",
text="this is a test",
user=User(id="charlie"),
meta={
'hey': 'jude',
'the': 'beatles'
}),
])
corpus2 = Corpus(utterances=[
Utterance(id="2",
text="this is a test",
user=User(id="charlie"),
meta={
'hey': 'jude',
'the': 'ringo',
'let it': 'be'
}),
Utterance(id="4", text="this is a sentence", user=User(id="echo")),
Utterance(id="5", text="goodbye", user=User(id="foxtrot")),
])
merged = corpus1.merge(corpus2)
self.assertEqual(len(list(merged.iter_utterances())), 5)
self.assertEqual(len(list(merged.iter_users())), 5)
self.assertEqual(len(merged.get_utterance("2").meta), 3)
self.assertEqual(merged.get_utterance("2").meta['the'], 'ringo')
def test_no_overlap(self):
"""
Basic merge: no overlap in utterance id
"""
corpus1 = Corpus(utterances=[
Utterance(id="0", text="hello world", speaker=Speaker(id="alice")),
Utterance(id="1", text="my name is bob", speaker=Speaker(
id="bob")),
Utterance(
id="2", text="this is a test", speaker=Speaker(id="charlie")),
])
corpus2 = Corpus(utterances=[
Utterance(id="3", text="i like pie", speaker=Speaker(id="delta")),
Utterance(
id="4", text="this is a sentence", speaker=Speaker(id="echo")),
Utterance(id="5", text="goodbye", speaker=Speaker(id="foxtrot")),
])
merged = corpus1.merge(corpus2)
self.assertEqual(len(list(merged.iter_utterances())), 6)
self.assertEqual(len(list(merged.iter_speakers())), 6)
self.assertEqual(len(list(corpus1.iter_utterances())), 3)
self.assertEqual(len(list(corpus2.iter_utterances())), 3)
def test_with_overlap(self):
"""
Basic merge: with overlap in utterance id (but utterance has same data & metadata)
"""
corpus1 = Corpus(utterances=[
Utterance(id="0", text="hello world", user=User(name="alice")),
Utterance(id="1", text="my name is bob", user=User(name="bob")),
Utterance(id="2", text="this is a test", user=User(
name="charlie")),
])
corpus2 = Corpus(utterances=[
Utterance(id="2", text="this is a test", user=User(
name="charlie")),
Utterance(
id="4", text="this is a sentence", user=User(name="echo")),
Utterance(id="5", text="goodbye", user=User(name="foxtrot")),
])
merged = corpus1.merge(corpus2)
self.assertEqual(len(list(merged.iter_utterances())), 5)
self.assertEqual(len(list(merged.iter_users())), 5)
self.assertEqual(len(list(corpus1.iter_utterances())), 3)
self.assertEqual(len(list(corpus2.iter_utterances())), 3)
def setUp(self) -> None:
"""
Basic Conversation tree (left to right within subtree => earliest to latest)
0
1 2 3
4 5 6 7 8 9
10 11
"""
self.corpus = Corpus(utterances=[
Utterance(id="0",
reply_to=None,
root="0",
speaker=Speaker(id="alice"),
timestamp=0),
Utterance(id="2",
reply_to="0",
root="0",
speaker=Speaker(id="alice"),
timestamp=2),
Utterance(id="1",
reply_to="0",
root="0",
speaker=Speaker(id="alice"),
timestamp=1),
Utterance(id="3",
reply_to="0",
root="0",
speaker=Speaker(id="alice"),
timestamp=3),
Utterance(id="4",
reply_to="1",
root="0",
speaker=Speaker(id="alice"),
timestamp=4),
Utterance(id="5",
reply_to="1",
root="0",
speaker=Speaker(id="alice"),
timestamp=5),
Utterance(id="6",
reply_to="1",
root="0",
speaker=Speaker(id="alice"),
timestamp=6),
Utterance(id="7",
reply_to="2",
root="0",
speaker=Speaker(id="alice"),
timestamp=4),
Utterance(id="8",
reply_to="2",
root="0",
speaker=Speaker(id="alice"),
timestamp=5),
Utterance(id="9",
reply_to="3",
root="0",
speaker=Speaker(id="alice"),
timestamp=4),
Utterance(id="10",
reply_to="4",
root="0",
speaker=Speaker(id="alice"),
timestamp=5),
Utterance(id="11",
reply_to="9",
root="0",
speaker=Speaker(id="alice"),
timestamp=10),
Utterance(id="other",
reply_to=None,
root="other",
speaker=Speaker(id="alice"),
timestamp=99)
])
self.corpus.get_conversation("0").meta['hey'] = 'jude'
self.corpus.meta['foo'] = 'bar'
