You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
62 lines
1.2 KiB
62 lines
1.2 KiB
|
|
import SentSeg
|
|
|
|
|
|
sent_seg = SentSeg.SentSeg('de')
|
|
|
|
|
|
sentences = sent_seg.ReadDoc2Sent('test2')
|
|
|
|
print('sentences after ReadDoc2Sent', sentences)
|
|
|
|
|
|
sent_seg.LoadSentGlueSGDandGSUtils()
|
|
|
|
#sentences = sent_seg.CommaSentenceOrNot(sentences)
|
|
|
|
#print('sentences after CommaSentenceOrNot', sentences)
|
|
|
|
|
|
#sentences = sent_seg.GetUtteranceNumber(sentences)
|
|
|
|
#print('sentences after GetUtteranceNumber', sentences)
|
|
|
|
#sentences = sent_seg.GetQuestionOrNot(sentences)
|
|
#print( 'sentences after GetQuestionOrNot', sentences)
|
|
|
|
|
|
|
|
|
|
##print(sent_seg.AndOrSolver(sentences))
|
|
|
|
#print('sentences', sentences)
|
|
|
|
|
|
#sentences = sent_seg.EnumerationSolver(sentences)
|
|
|
|
#print('sent 2 ', sentences)
|
|
|
|
sentences = sent_seg.CommaSentenceOrNot(sentences)
|
|
|
|
print('sentences after CommaSentenceOrNot', sentences)
|
|
|
|
|
|
sentences = sent_seg.GetUtteranceNumber(sentences)
|
|
|
|
print('sentences after GetUtteranceNumber', sentences)
|
|
|
|
sentences = sent_seg.GetQuestionOrNot(sentences)
|
|
print( 'sentences after GetQuestionOrNot', sentences)
|
|
|
|
|
|
#sent_seg.LoadBoWModelAndDatabaseOnesZeros()
|
|
|
|
|
|
|
|
sentences1 = sent_seg.SplitSentencesIntoHauptNebenTuple(sentences)
|
|
|
|
|
|
print('sentences after Split into Hauptnebentuple ',sentences1)
|
|
|
|
print(sent_seg.SplitCommatas(sentences1))
|
|
|