stopWords = [' ', '!', ',', '.', '?', '！', '？', '，', '。', '\n', '\t', '\b', '"', '“', '”', '：', '《', '》', '<', '>']
splitWords = jieba.lcut(source)
splitWords = del_stopWords(splitWords, stopWords)
#删除停用词
def del_stopWords(split_sentence, stopWords):
    i = 0
    while (len(split_sentence) != 0):
        
        if (i >= len(split_sentence)):
            break
        
        #匹配停用词
        tmp = False
        for n in stopWords:
            if (split_sentence[i] == n):
                tmp = True
                break       

        if (tmp):
            split_sentence.pop(i)
            continue

        i += 1

    return split_sentence

# 哈希函数，输入单个分词
def string_hash(source):
        if source == "":
            return 0
        else:
            x = ord(source[0]) << 7
            m = 1000003
            mask = 2**128 - 1
            for c in source:
                x = ((x*m)^ord(c)) & mask
            x ^= len(source)
            if x == -1:
                x = -2
            x = bin(x).replace('0b', '').zfill(64)[-64:]
            
            return str(x)

#计算权重并加权，输入分词列表，可以去重并重新排序
def count_weight(split_sentence, listSize):
    keyWords = jieba.analyse.extract_tags("|".join(split_sentence), topK=listSize, withWeight=True)    
    list_weightPluse = list()
    a = list(map(int, string_hash(keyWords[0][0])))

    for index in range(len(keyWords)):
        tmp = list(map(int, string_hash(keyWords[index][0])))        
        tmp = np.subtract(np.multiply(tmp, 2), 1)   #把0 1转换为-1 1             
        list_weightPluse.append(np.multiply(tmp, keyWords[index][1]))
    
    return list_weightPluse

#合并加权后的哈希值，输入加权哈希值列表
def mergeHash(list_weightPluse):
    mergeHash_list = [0] * 64
    for index in range(len(list_weightPluse)):
        mergeHash_list = np.add(mergeHash_list, list_weightPluse[index])

    return mergeHash_list

#降维，大于0的输出1，小于等于0的输出0
def reduction(mergeHash_list):
    reduction_list = list()
    for index in range(len(mergeHash_list)):
        if (mergeHash_list[index] > 0):
            reduction_list.append(1)
        else:
            reduction_list.append(0)
    
    return reduction_list

#海明距离
def getDistance(list_1, list_2):
    distance = 0

    for index in range(len(list_1)):
        if (list_1[index] ^ list_2[index] == 1):
            distance += 1

    return distance
	
#将汉明距离转换为相似度
similarity = round((64 - hanmingDistance) / 64 * 100, 2)

address_orig = sys.argv[1]
address_copy = sys.argv[2]
address_out = sys.argv[3]
#读入并计算源文件的simhash
file_1 = open(address_orig, encoding= 'UTF-8')
s1 = file_1.read()

list_1 = simhash(s1, stopWords)

#print(list_1)

file_1.close()

#将相似度写入新建文件
file_3 = open(address_out, 'w', encoding= 'UTF-8')

file_3.write(str(similarity))

file_3.close()