ContendSplit.py 文件源码

def jieba_contend_split(contend):
    punctuation = [u'?', u'/', u'?', u'?', u'?', u' ', u'\'']
    wordSequenceList = []  # ???? [[(id,comtend),()....]] ???????????????????
    seg_list = jieba.cut(self.commentSentence)
    segmentedComment = [item for item in seg_list]
    segmentedCommentTuple = list(enumerate(segmentedComment))
    subWordSequenceList = []
    for wordTuple in segmentedCommentTuple:
        if wordTuple[1] in punctuation:
            if subWordSequenceList:
                wordSequenceList.append(subWordSequenceList)
                subWordSequenceList = []
        else:
            subWordSequenceList.append(wordTuple)
    if subWordSequenceList:
        wordSequenceList.append(subWordSequenceList)
    return wordSequenceList