stopwords =[]

with open('stopwords', 'r', encoding='utf-8')as f:
    for i in f:
        word = i.strip()
        stopwords.append(word)

filename = 'test.txt'

filename1 = 'test_cws.txt'
# 写入分词
def write_cws():
    num = 0 # 这个是文件id值，如果本身就有，这个可以更改为你自己的，我这里只是简单的计数作为id值
    writing = open(filename1, 'a+', encoding='utf-8')
    with open(filename, 'r', encoding='utf-8')as f:
        for line in f:
            content = line.strip()
            content = content.replace(' ', '')
            seg = jieba.cut(content)
            test =''
            for i in seg:
                if i not in stopwords:
                    test += i+' '
            writing.write(str(num)+"    "+test+'\n')
            num += 1
    writing.close()

filename2 = 'zhengxiang.txt'
def zhengxiang():

    all_words = []
    all = {}
    file2 = open(filename2, 'a+', encoding='utf-8')
    with open(filename1, 'r', encoding='utf-8')as f:
        for line in f:
            line = line.strip()
            # print(line)
            content = line.split('    ')[1]

            num = line.split('    ')[0]
            words = content.split(' ')
            for word in words:
                word_num =[num]
                if word not in all_words:
                    all_words.append(word)
                    all[word] = word_num
                else:
                    if num not in all[word]:
                        all[word].append(num)


    for word, nums in all.items():
        file2.write(word+'    ')
        for i in range(len(nums)):
            if i ==0:
                file2.write(nums[i])
            else:
                file2.write(','+nums[i])
        file2.write('\n')

    file2.close()

# 倒排索引
filename3 = 'daopai.txt'
def daopai():
    with open(filename2, 'r', encoding='utf-8')as f:
        for line in f:
            try:#这个异常处理是我数据有点问题，如果你本身数据和我上面截图的语料库数据一样，应该不会报错
                word_dict = {}# 单词的字典，字典格式，方便存取
                word_list =[] # 存放这个单词的情况
                syc = [] # 存放单词以及单词在所有文件出现的次数，在一个文件出现就加1，不管其中出现多少次

                Aword = line.strip()# Aword 是 all_word
                word = Aword.split('    ')[0]
                print(word)
                nums = Aword.split('    ')[1]
                count = len(nums.split(','))
                syc.append(word+' '+str(count))
                word_list.append(syc)
                with open(filename1, 'r', encoding='utf-8') as r:
                    for line1 in r:
                        acount = 0 # 这个单词在这行中出现的个数
                        words = line1.strip().split('    ')[1].split(' ')
                        num = line1.strip().split('    ')[0]
                        if word in words: # 判断这个单词在不在这个句子
                            for aword in words:
                                if word == aword:
                                    acount += 1
                            temp1 = [num, acount]# 用于存放单词出现的地方以及它的次数
                            word_list.append(temp1)
                word_dict[word] = word_list
                with open(filename3, 'a', encoding='utf-8')as f:
                    json.dump(word_dict,f,ensure_ascii=False)
                    f.write(',')
                    f.write('\n')
            except Exception as e:
                print(line)
                print(e)