def create_sentence(sen_text, sen_start, sen_end, aug, metadata_tool,
metadata_timestamp, annotation_level):
'''
Create sentence from provided text and metadata.
Lower-level routine (called indirectly by create_comm).
'''
sections = (annotation_level is not None) and (annotation_level != AL_NONE)
sentences = sections and (annotation_level != AL_SECTION)
tokens = sentences and (annotation_level != AL_SENTENCE)
return Sentence(
uuid=aug.next(),
textSpan=TextSpan(sen_start, sen_end),
tokenization=Tokenization(
uuid=aug.next(),
kind=TokenizationKind.TOKEN_LIST,
metadata=AnnotationMetadata(
tool=metadata_tool,
timestamp=metadata_timestamp,
),
tokenList=TokenList(tokenList=[
Token(
tokenIndex=i,
text=tok_text,
) for (i, tok_text) in enumerate(sen_text.split())
]),
) if tokens else None,
)
def create_section_with_sentence(section_start, section_ending, sentence_start,
sentence_ending):
sentence_textspan = TextSpan(start=sentence_start, ending=sentence_ending)
sentence = Sentence(textSpan=sentence_textspan, uuid='TEST_SENTENCE')
section_textspan = TextSpan(start=section_start, ending=section_ending)
section = Section(sentenceList=[sentence],
textSpan=section_textspan,
uuid='TEST_SECTION')
return section
def create_sentence_with_token(sentence_start, sentence_ending, token_start,
token_ending):
token_textspan = TextSpan(start=token_start, ending=token_ending)
token = Token(textSpan=token_textspan)
tokenization = Tokenization(tokenList=TokenList(tokenList=[token]))
sentence_textspan = TextSpan(start=sentence_start, ending=sentence_ending)
sentence = Sentence(tokenization=tokenization,
textSpan=sentence_textspan,
uuid='TEST')
return sentence
def create_simple_comm(comm_id, sentence_string="Super simple sentence ."):
"""Create a simple (valid) Communication suitable for testing purposes
The Communication will have a single Section containing a single
Sentence.
Args:
- `comm_id`: A string specifying a Communication ID
- `sentence_string`: A string to be used for the sentence text.
The string will be whitespace-tokenized.
Returns:
- A Concrete Communication object
"""
logging.warning('create_simple_comm will be removed in a future'
' release, please use create_comm instead')
toolname = "TEST"
timestamp = int(time.time())
augf = AnalyticUUIDGeneratorFactory()
aug = augf.create()
comm = Communication(id=comm_id,
metadata=AnnotationMetadata(tool=toolname,
timestamp=timestamp),
type=toolname,
uuid=aug.next())
tokenization = Tokenization(kind=TokenizationKind.TOKEN_LIST,
metadata=AnnotationMetadata(
tool=toolname, timestamp=timestamp),
tokenList=TokenList(tokenList=[]),
uuid=aug.next())
token_string_list = sentence_string.split()
for i, token_string in enumerate(token_string_list):
tokenization.tokenList.tokenList.append(
Token(text=token_string, tokenIndex=i))
sentence = Sentence(textSpan=TextSpan(0, len(sentence_string)),
tokenization=tokenization,
uuid=aug.next())
section = Section(kind="SectionKind",
sentenceList=[sentence],
textSpan=TextSpan(0, len(sentence_string)),
uuid=aug.next())
comm.sectionList = [section]
comm.text = sentence_string
return comm
def json_to_concrete(doc: Dict) -> Communication:
metadata = AnnotationMetadata(
tool="BlingBLing",
timestamp=int(datetime.datetime.now().timestamp())
)
comm: Communication = Communication(
uuid=augf.next(),
id=doc['doc_key'],
type="aida",
metadata=metadata,
lidList=[LanguageIdentification(
uuid=augf.next(),
metadata=metadata,
languageToProbabilityMap={doc['language_id']: 1.0}
)],
sectionList=[Section(
uuid=augf.next(),
kind="passage",
sentenceList=[
Sentence(
uuid=augf.next(),
tokenization=Tokenization(
uuid=augf.next(),
kind=TokenizationKind.TOKEN_LIST,
metadata=metadata,
tokenList=TokenList(
tokenList=[
Token(
tokenIndex=i,
text=t
)
for i, t in enumerate(get_flatten_sentence(doc))
]
)
)
)
]
)],
entityMentionSetList=[EntityMentionSet(
uuid=augf.next(),
metadata=metadata,
mentionList=[]
)],
situationMentionSetList=[SituationMentionSet(
uuid=augf.next(),
metadata=metadata,
mentionList=[]
)]
)
return comm
def _comm_with_properties(num_properties):
ts = 17
meta_tokn = AnnotationMetadata(tool='tokn-tool', timestamp=ts)
toks = TokenList(tokenList=[
Token(tokenIndex=0, text='text', textSpan=TextSpan(start=0, ending=1))
])
tokn = Tokenization(uuid=generate_UUID(),
metadata=meta_tokn,
kind=TokenizationKind.TOKEN_LIST,
tokenList=toks)
sentence = Sentence(uuid=generate_UUID(), tokenization=tokn)
section = Section(uuid=generate_UUID(),
kind='kind',
label='label',
sentenceList=[sentence])
trfs = TokenRefSequence(tokenizationId=tokn.uuid,
tokenIndexList=[0],
anchorTokenIndex=0)
em = EntityMention(uuid=generate_UUID(),
entityType='entityType',
text='text',
tokens=trfs)
meta_ems = AnnotationMetadata(tool='ems-tool', timestamp=ts)
ems = EntityMentionSet(uuid=generate_UUID(),
metadata=meta_ems,
mentionList=[em])
meta_prop = AnnotationMetadata(tool='Annotator1', timestamp=ts)
props = list(
Property(value="Property%d" % i, metadata=meta_prop, polarity=4.0)
for i in range(num_properties))
am = MentionArgument(role='role',
entityMentionId=em.uuid,
propertyList=props)
sm = SituationMention(uuid=generate_UUID(), tokens=trfs, argumentList=[am])
meta_sms = AnnotationMetadata(tool='sms-tool', timestamp=ts)
sms = SituationMentionSet(uuid=generate_UUID(),
metadata=meta_sms,
mentionList=[sm])
meta_comm = AnnotationMetadata(tool='tool', timestamp=ts)
comm = Communication(uuid=generate_UUID(),
id='id',
text='text',
type='type',
metadata=meta_comm,
sectionList=[section],
situationMentionSetList=[sms],
entityMentionSetList=[ems])
add_references_to_communication(comm)
return comm
def annotate(self, communication):
augf = AnalyticUUIDGeneratorFactory(communication)
aug = augf.create()
for section in communication.sectionList:
text = communication.text[section.textSpan.start:section.textSpan.ending]
current_offset = section.textSpan.start
for sent in nltk.sent_tokenize(text):
logging.info("Found sentence %s", sent)
initial = text.find(sent)
s = Sentence(uuid=aug.next(),
textSpan=TextSpan(start=current_offset + initial, ending=current_offset + initial + len(sent)))
section.sentenceList.append(s)
current_offset = current_offset + initial + len(sent)
text = communication.text[current_offset:]
return communication