watch.py 文件源码

def buildGraph(text):
    vertices = [] 
    sentences = sent_tokenize(text, language='english')
    for sentence_raw in sentences:  
        sentence_processed = sub("[^a-zA-Z ]+", '', sentence_raw).lower()          
        words = word_tokenize(sentence_processed, language='english')
        vertices.append(vertex(sentence_raw, sentence_processed, words))

    for v1 in vertices:
        for v2 in vertices:
            if v1.order != v2.order:                
                v1.scores.append(overlap(v1.words, v2.words))
        v1.averageScores()
    return vertices