def test_entity_mention_ids(self):
comm = read_test_comm()
self.assertTrue(validate_communication(comm))
self.assertTrue(validate_entity_mention_ids(comm))
comm.entitySetList[0].entityList[0].mentionIdList[
0] = concrete.UUID(uuidString='BAD_ENTITY_MENTION_UUID')
with LogCapture() as log_capture:
self.assertFalse(validate_entity_mention_ids(comm))
log_capture.check(('root', 'ERROR', StringComparison(
r'.*invalid entityMentionId.*BAD_ENTITY_MENTION_UUID')))
def test_entity_mention_tokenization():
comm = read_test_comm()
assert validate_communication(comm)
assert validate_entity_mention_ids(comm)
comm.entityMentionSetList[0].mentionList[0].tokens.tokenizationId = (
concrete.UUID(uuidString='BAD_TOKENIZATION_UUID'))
with LogCapture() as log_capture:
assert not validate_entity_mention_tokenization_ids(comm)
log_capture.check(
('root', 'ERROR',
StringComparison(r'.*invalid tokenizationId.*BAD_TOKENIZATION_UUID')))
def test_entity_mention_tokenization(self):
comm = read_test_comm()
self.assertTrue(validate_communication(comm))
self.assertTrue(validate_entity_mention_ids(comm))
comm.entityMentionSetList[0].mentionList[0].tokens.tokenizationId = (
concrete.UUID(uuidString='BAD_TOKENIZATION_UUID')
)
with LogCapture() as log_capture:
self.assertFalse(validate_entity_mention_tokenization_ids(comm))
log_capture.check(('root', 'ERROR', StringComparison(
r'.*invalid tokenizationId.*BAD_TOKENIZATION_UUID')))
def test_entity_mention_ids():
comm = read_test_comm()
assert validate_communication(comm)
assert validate_entity_mention_ids(comm)
comm.entitySetList[0].entityList[0].mentionIdList[0] = concrete.UUID(
uuidString='BAD_ENTITY_MENTION_UUID')
with LogCapture() as log_capture:
assert not validate_entity_mention_ids(comm)
log_capture.check(
('root', 'ERROR',
StringComparison(
r'.*invalid entityMentionId.*BAD_ENTITY_MENTION_UUID')))
def test_repr_on_comm(self):
"""Verify that Communications can be converted to strings.
Checks for the issue addressed in this commit:
commit 0ee3317454543b63dc7a273d92e5720bb9210b03
Author: Craig Harman <*****@*****.**>
Date: Tue Dec 16 13:08:44 2014 -0500
Fixed infinite recursion bug in Tokenization.__repr__()
The addition of an in-memory "backpointer" from a Tokenization to the
Tokenization's enclosing Sentence inadvertently broke the
(Thrift auto-generated) Tokenization.__repr__() function. Modified the
function to ignore the backpointer when generating the string
representation for a Tokenization.
"""
comm = read_test_comm()
comm.__repr__()
def test_repr_on_comm(self):
"""Verify that Communications can be converted to strings.
Checks for the issue addressed in this commit:
commit 0ee3317454543b63dc7a273d92e5720bb9210b03
Author: Craig Harman <*****@*****.**>
Date: Tue Dec 16 13:08:44 2014 -0500
Fixed infinite recursion bug in Tokenization.__repr__()
The addition of an in-memory "backpointer" from a Tokenization to the
Tokenization's enclosing Sentence inadvertently broke the
(Thrift auto-generated) Tokenization.__repr__() function. Modified the
function to ignore the backpointer when generating the string
representation for a Tokenization.
"""
comm = read_test_comm()
comm.__repr__()
def test_add_references():
comm = read_test_comm()
add_references_to_communication(comm)
def test_add_references(self):
comm = read_test_comm()
add_references_to_communication(comm)
