加入英语题目生成 备注下

import string
import re
from pypinyin import pinyin, lazy_pinyin, Style
from nltk.corpus import wordnet as wn



def get_all_char_pinyin():
    path = '/www/wwwroot/wonder/wonderful/output2.txt'
    pinyin_dict = {}
    with open('/www/wwwroot/wonder/wonderful/output2.txt', "r", encoding="utf-8") as f:
        for line in f.readlines():
            ch = line.strip()
            ch_pinyin = pinyin(ch, style=Style.TONE3, heteronym=False)
            # heteronym 是否启用多音字模式
            for p_li in ch_pinyin:
                for p in p_li:
                    if p not in pinyin_dict:
                        pinyin_dict[p] = [ch]
                    else:
                        pinyin_dict[p].append(ch)
    return pinyin_dict


pinyin_dict = get_all_char_pinyin()


def getsamesoundword(s):
    # 获取同音汉字
    similarity_dict = {}
    match_char = s
    ch_pinyin = pinyin(match_char, style=Style.TONE3, heteronym=False)
    res = []
    for p_li in ch_pinyin:
        for p in p_li:
            #print(p,s,'match_char')
            if match_char in pinyin_dict[p]:
                pinyin_dict[p].remove(match_char)

            res.extend(pinyin_dict[p])

    return res


def extract_and_replace(s):
    # 随机选择2-6个字符的索引范围
    start = random.randint(0, len(s))
    end = start + random.randint(0, len(s))
    # 提取字符串中的子串
    substring = s[start:end]
    # 用空括号替换子串
    s = s[:start] + '(__)' * len(substring) + s[end:]
    return [s, substring]


def replace_random_char(s):
    # 排除中英文标点符号

    exclude = set(string.punctuation + string.digits)
    # 从剩余字符中随机选取一个字符
    char = random.choice(list(set(s) - exclude))
    # 用括号替换原有位置
    s = s.replace(char, '()', 1)
    # 多个字符
    # chars = [random.choice(list(set(s) - exclude)) for _ in range(2)]
    #
    # # 用括号替换原有位置
    #
    # s = ''.join(f'({char})' if chars in chars else char for char in s)
    #
    return [s, char]


def replace_duplicates(lst):  # 去除掉重复选项
    seen = set()
    result = []
    for item in lst:
        if item not in seen:
            seen.add(item)
            result.append(item)
        else:
            result.append('-')
    return result


import random


def random_split_string(s):
    # 随机选择一个切割点
    split_point = random.randint(1, len(s) - 1)
    # 切割字符串
    first_part = s[:split_point]
    second_part = s[split_point:]
    return first_part, second_part


def addlist2(s,questionlist):
    data2 = []
    for w in questionlist:

        a1 = re.split(r'[.,、， !?]+', w)  # 两个句子 循环一下

        for q in a1:
            data = []
            answerlist = []

            word = extract_and_replace(q)  # 从句子中抽取扣空 ['嫦娥应悔偷灵()', '药']
            # print(q,word,'抽空的句子')
            if word[1] == '':  # 如果抽到空的 过滤掉
                break
            if len(word[1]) > s:  # 控制题目
                break
            data.append(word[0])
            for w in range(3):
                newword = ''
                for x in word[1]:  # 生成答案的相思答案
                    list = getsamesoundword(x)
                    if list:
                        # print(list,'这是list')
                        if len(list) > 0:
                            choose = random.choice(list)
                            # print(choose,'choose')
                        else:
                            choose = list[0]
                    else:
                        choose = '无'
                    newword += str(choose)
                answerlist.append(newword)
            answerlist.append(word[1])
            # print(answerlist,'answerlist')
            random.shuffle(answerlist)  # 重新排列ANSWERLIST
            answerlist = replace_duplicates(answerlist)
            index = answerlist.index(word[1])  # 列表中找到某个元素
            for qw in answerlist:
                data.append(qw)
            # 生成正确选项
            if index == 0:
                asd = 'a'
            elif index == 1:
                asd = 'b'
            elif index == 2:
                asd = 'c'
            elif index == 3:
                asd = 'd'
            else:
                asd = '无'
            data.append(asd)
            data.append(word[1])
            # print(data,'组的题')

            if data:
                # print(data,'data')
                data2.append(data)
    return data2
    # with open("new.csv", "a", encoding='utf-8') as csvfile:
    #     writer = csv.writer(csvfile, lineterminator='\n')
    #     writer.writerows([data])


def addlist3(questionlist):
    data2 = []
    for w in questionlist:
        a1 = re.split(r'[.,、， !?]+', w)  # 两个句子 循环一下
        data1 = []
        for q in a1:

            while True:
                answerlist = []
                data = []
                s1, s2 = random_split_string(q)  # 将一个诗句分成两段
                #print(s1, s2, 'newword')
                index = random.randint(0, len(s1) - 1)  # 获取第一段的一个随机汉字
                newword = getsamesoundword(s1[index])  # 创造一个同声字
                #print(newword)
                if len(newword) > 0:
                    b1 = s1[:index] + newword[0] + s1[index + 1:]  # 制造一个被替换同声字的混淆答案
                else:
                    b1='-'
                    pass

                index2 = random.randint(0, len(s2) - 1)
                newword2 = getsamesoundword(s2[index2])
                if len(newword2) > 0:
                    b2 = s2[:index2] + newword2[0] + s2[index2 + 1:]
                else:
                    b2 = '-'
                    pass
                # print(newword, 'newword')
                if len(newword) > 0 and s1[index] != newword[0]:
                    answerlist.append(s1)
                    answerlist.append(b1)
                    answerlist.append(s2)
                    answerlist.append(b2)

                    random.shuffle(answerlist)
                    data.append('请选择两个能连成正确的诗句')
                    for x in answerlist:
                            data.append(x)
                    index_s1 = data.index(s1)
                    index_s2 = data.index(s2)
                    if index_s1 == 1:
                            asd = 'a'
                    elif index_s1 == 2:
                            asd = 'b'
                    elif index_s1 == 3:
                            asd = 'c'
                    elif index_s1 == 4:
                            asd = 'd'
                    else:
                            asd = '无'
                    if index_s2 == 1:
                            asd2 = 'a'
                    elif index_s2 == 2:
                            asd2 = 'b'
                    elif index_s2 == 3:
                        asd2 = 'c'
                    elif index_s2 == 4:
                            asd2 = 'd'
                    else:
                            asd2 = '无'
                    data.append(asd)
                    data.append(asd2)
                    data.append(s1 + s2)
                    data2.append(data)
                        # print(data2,'打印的')
    
                    break

    return data2
    # print(data, 'datalist')
def remove_random_letter(word):  

    if not word:  # 如果单词为空，则返回一个空字符串和 None  
        return "", None  
    letter = random.choice(word)  # 从单词中随机选择一个字母  
    new_word = word.replace(letter, "(__)", 1)  # 将该字母替换为 "（_）"  

    return new_word, letter 
def split_word_randomly(word): #单词截成两个 
    if len(word) == 1:  
        return word, ""  
      
    split_point = random.randint(1, len(word) - 1)  
    part1 = word[:split_point]  
    part2 = word[split_point:]  
    return part1, part2  
    
    
def creatbreakletter(word):#创建一个
    questdata = {
                'id': 0,
                'type': 'checkbox',
                'number': 0,
                'title': '听单词选择正确的单词',
                'question_option': [
                    {'id': 1, 'name': 'A', 'content': 0, 'active': 0},
                    {'id': 2, 'name': 'B', 'content': 0, 'active': 0},
                    {'id': 3, 'name': 'C', 'content': 0, 'active': 0},
                    {'id': 4, 'name': 'D', 'content': '-', 'active': 0}
                ],
                'answer1':0,
                'answer2':0,
            }
    wordlist = []
    part1,part2 = split_word_randomly(word)
    print(part1,part2)
    fake1 = replace_random_letter(part1)
    fake2 = replace_random_letter(part2)
    wordlist = [fake1,fake2,part1,part2]
    random.shuffle(wordlist)
    index_s1 = wordlist.index(part1)
    index_s2 = wordlist.index(part2)
    if index_s1 == 0:
        asd = 'a'
    elif index_s1 == 1:
        asd = 'b'
    elif index_s1 == 2:
        asd = 'c'
    elif index_s1 == 3:
        asd = 'd'
    else:
        asd2 = '无'
    if index_s2 == 0:
        asd2 = 'a'
    elif index_s2 == 1:
        asd2 = 'b'
    elif index_s2 == 2:
        asd2 = 'c'
    elif index_s2 == 3:
        asd2 = 'd'
    else:
        asd2 = '无'
    

    questdata['title'] = '请选择两个单词元素组成单词'
    questdata['question_option'][0]['content'] = wordlist[0].lower() 
    questdata['question_option'][1]['content'] = wordlist[1].lower() 
    questdata['question_option'][2]['content'] = wordlist[2].lower() 
    questdata['question_option'][3]['content'] = wordlist[3].lower() 
    questdata['answer1'] = asd
    questdata['answer2'] = asd2
    # print(questdata,'打印的混淆项目')
    return questdata
    
def createmissingletter(word):#创建一个
    questdata = {
                'id': 0,
                'type': 'radio',
                'number': 0,
                'title': '听单词选择正确的单词',
                'question_option': [
                    {'id': 1, 'name': 'A', 'content': 0, 'active': 0},
                    {'id': 2, 'name': 'B', 'content': 0, 'active': 0},
                    {'id': 3, 'name': 'C', 'content': 0, 'active': 0},
                    {'id': 4, 'name': 'D', 'content': '-', 'active': 0}
                ],
                'answer1':0,
            }
    wordlist = []
    new_word,letter = remove_random_letter(word)
    print(new_word,letter)
    while True:
        # 生成包含所有大小写字母的列表  
        
        letters = list(string.ascii_letters)  
        # 随机选择一个字母  
        random_letter = random.choice(letters)  
        # 输出随机选择的字母  
        print("随机给出的字母是:", random_letter)
        
        if random_letter in wordlist or random_letter==word:
            pass
        else:
            wordlist.append(random_letter)
        if len(wordlist) > 2:
            break
    
    
    wordlist.append(letter)
    random.shuffle(wordlist)
    index_s1 = wordlist.index(letter)
    # #print(wordlist,index_s1)
                    
    if index_s1 == 0:
        asd = 'a'
    elif index_s1 == 1:
        asd = 'b'
    elif index_s1 == 2:
        asd = 'c'
    elif index_s1 == 3:
        asd = 'd'
    questdata['title'] = '请选择丢失的字母'+new_word
    questdata['question_option'][0]['content'] = wordlist[0].lower() 
    questdata['question_option'][1]['content'] = wordlist[1].lower() 
    questdata['question_option'][2]['content'] = wordlist[2].lower() 
    questdata['question_option'][3]['content'] = wordlist[3].lower() 
    questdata['answer1'] = asd
    # print(questdata,'打印的混淆项目')
    return questdata
def createmissingword(word):#创建一个
    questdata = {
                'id': 0,
                'type': 'radio',
                'number': 0,
                'title': '听单词选择正确的单词',
                'question_option': [
                    {'id': 1, 'name': 'A', 'content': 0, 'active': 0},
                    {'id': 2, 'name': 'B', 'content': 0, 'active': 0},
                    {'id': 3, 'name': 'C', 'content': 0, 'active': 0},
                    {'id': 4, 'name': 'D', 'content': '-', 'active': 0}
                ],
                'answer1':0,
            }
    wordlist = []
    while True:
        newword = replace_random_letter(word)
        if newword in wordlist:
            pass
        else:
            wordlist.append(newword)
        if len(wordlist) > 2:
            break
    
    wordlist.append(word)
    random.shuffle(wordlist)
    index_s1 = wordlist.index(word)
    #print(wordlist,index_s1)
                    
    if index_s1 == 0:
        asd = 'a'
    elif index_s1 == 1:
        asd = 'b'
    elif index_s1 == 2:
        asd = 'c'
    elif index_s1 == 3:
        asd = 'd'
    questdata['question_option'][0]['content'] = wordlist[0]
    questdata['question_option'][1]['content'] = wordlist[1]
    questdata['question_option'][2]['content'] = wordlist[2]
    questdata['question_option'][3]['content'] = wordlist[3]
    questdata['answer1'] = asd
    print(questdata,'打印的混淆项目')
    return questdata

def addlist(questionlist):
    for w in questionlist:
        data = []
        answerlist = []
        # print(replace_random_char(w))
        word = replace_random_char(w)
        print(word[1] + '的形近字，答案最多3个汉字,用逗号隔开，必须不是词语，不要陈述问题，不要解析，答案之间不能重复')
        answer = sparkWeb.chat(word[1] + '的形近字，答案只给我3个字,用逗号隔开，不可以是词语，不要陈述问题，不要解析，答案之间不能重复')
        list = re.split(r'[.,、， !?]+', answer)
        print(list, '这是list')
        # data.append('选择对应的汉字填入古诗' + word[1])

        if answer:
            for x in list:
                answerlist.append(x)
        else:
            data.append('无答案')
        answerlist.append(word[1])
        random.shuffle(answerlist)  # 重新排列ANSWERLIST

        index = answerlist.index(word[1])  # 列表中找到某个元素
        # 生成正确选项
        if index == 0:
            choose = 'a'
        if index == 1:
            choose = 'b'
        if index == 2:
            choose = 'c'
        if index == 3:
            choose = 'd'
        data.append('选择对应的汉字填入古诗中，' + word[0])
        for x in answerlist:
            data.append(x)
        data.append(choose)
        data.append(word[1])

        # with open("new.csv", "a", encoding='utf-8') as csvfile:
        #     writer = csv.writer(csvfile, lineterminator='\n')
        #     writer.writerows([data])


def check_elements(lst, element1, element2, element3):
    return all(element in lst for element in [element1, element2, element3])


tempdata = []


def checklist2(word):  # 查询是否重复
    for x in tempdata:
        # print(findaldata, word[0], x[0], '对比')
        if word[0] == x[0]:
            return 1


def checklist(word, list):  # 查询是否重复
    for x in list:
        print(word,x[1],x,'checklist')
        if word == x[1]:
            return 1


# {
# 						id:1, //题目id
# 						type:'radio',//单选 checkbox - 多选 ； write - 填空
# 						number:1, //题目序号 - 非必要
# 						title:'生物灭绝又叫生物绝种。历史上一共有几次大灭绝？', //题目名称
# 						imageList:['https://ss0.bdstatic.com/94oJfD_bAAcT8t7mm9GUKT-xh_/timg?image&quality=100&size=b4000_4000&sec=1588056060&di=67dc5595a44e90101f524bae2273cc0a&src=http://a3.att.hudong.com/14/75/01300000164186121366756803686.jpg'], //图片地址
# 						question_option:[
# 							{
# 								id:1,//答案id
# 								name:'A',//答案选项名
# 								content:'一次',//答案内容
# 								active:0//选中状态
# 							},
# 							{id:2,name:'B',content:'二次',active:0},
# 							{id:3,name:'C',content:'三次',active:0},
# 							{id:4,name:'D',content:'四次',active:0},
# 							]//选项集
# 					},
def getenglishwordquestions(word):#英语单词的题目生成
    finaldata = []
    for i in range(6):
        item = createmissingword(word)
        finaldata.append(item)
    #print(finaldata)
    for i in range(10):
        item1 = createmissingletter(word)
        finaldata.append(item1)
    for i in range(10):
        item2 = creatbreakletter(word)
        finaldata.append(item2)
    
    return finaldata
    
def replace_random_letter(word):  #随机替换一个字母

    # 随机选择一个字母的索引  
    index = random.randint(0, len(word) - 1)  
    # 生成一个包含26个英文字母的列表  
    letters = list(string.ascii_lowercase)  
    # 从列表中随机选择一个字母  
    random_letter = random.choice(letters)  
    # 替换选定的字母  
    new_word = word[:index] + random_letter + word[index+1:]  
    return new_word
    
    
def getquestions(qlist,all_added_questions):
    questionlist = qlist

    findaldata = []
    tempquestions = []
    id = 0

    print(  len(all_added_questions),'诗句匹配题目')
    for x in all_added_questions:#增加了选择诗句题目
        id += 1
        x['id']=id

        findaldata.append(x)
    #print(findaldata,'!!!finaldata')
    for i in range(8):
        item = addlist3(questionlist)
        for x in item:

            tempquestions.append(x)
    random_elements = random.sample(tempquestions, 10)
    for x in random_elements:
        print(x)
        id += 1
        questdata = {
            'id': id,
            'type': 'checkbox',
            'number': id,
            'title': x[0],
            'question_option': [
                {'id': 1, 'name': 'A', 'content': x[1], 'active': 0},
                {'id': 2, 'name': 'B', 'content': x[2], 'active': 0},
                {'id': 3, 'name': 'C', 'content': x[3], 'active': 0},
                {'id': 4, 'name': 'D', 'content': x[4], 'active': 0}
            ],
            'answer1': x[5],
            'answer2': x[6],

        }
        findaldata.append(questdata)
    # print(findaldata)

    tempdata3 = []
    for i in range(30):
        new = addlist2(1,questionlist)
        if new:
            #print(new)
            identify = 0
            if tempdata3:
                for x in tempdata3:
                    checkitem = check_elements(new[0], '无', '-', '-')
                    if checkitem:
                        #print(new[0],'发现空答案')
                        identify = 1
                    #print(new[0][0], x['title'], '发现答案出现重复')
                    if new[0][0] == x['title']:
                        identify = 1
                       #print(new[0][0], x['title'], '发现答案出现重复')

            if identify == 0:
                    #print(new[0])
                    id += 1
                    questdata2 = {
                        'id': id,
                        'type': 'radio',
                        'number': id,
                        'title': new[0][0],
                        'question_option': [
                            {'id': 1, 'name': 'A', 'content': new[0][1], 'active': 0},
                            {'id': 2, 'name': 'B', 'content': new[0][2], 'active': 0},
                            {'id': 3, 'name': 'C', 'content': new[0][3], 'active': 0},
                            {'id': 4, 'name': 'D', 'content': new[0][4], 'active': 0}
                        ],
                        'answer1': new[0][5],
                        'disp': new[0][6],

                    }
                    #print(questdata2,'添加的questdata2')

                    tempdata3.append(questdata2)

    random.shuffle(tempdata3)
    #print(tempdata3,'tempdata3')
    if len(tempdata3) < 10:
        random_elements2 = random.sample(tempdata3, len(tempdata3))
        for x in random_elements2:
            findaldata.append(x)
    else:
        random_elements2 = random.sample(tempdata3, 10)
        for x in random_elements2:
            findaldata.append(x)
    #print(findaldata)
    tempdata2 = []
    for i in range(30):
        new = addlist2(3,questionlist)
        if new:
            identify = 0
            for x in tempdata2:
                if new[0][0] == x['title']:
                    identify = 1
                    # print(new[0][0], x[0], '发现重复')
                    break
            if identify == 0:
                id += 1
                questdata2 = {
                    'id': id,
                    'type': 'radio',
                    'number': id,
                    'title': new[0][0],
                    'question_option': [
                        {'id': 1, 'name': 'A', 'content': new[0][1], 'active': 0},
                        {'id': 2, 'name': 'B', 'content': new[0][2], 'active': 0},
                        {'id': 3, 'name': 'C', 'content': new[0][3], 'active': 0},
                        {'id': 4, 'name': 'D', 'content': new[0][4], 'active': 0}
                    ],
                    'answer1': new[0][5],
                    'disp': new[0][6],

                }

                tempdata2.append(questdata2)
    #print(len(tempdata2),'第二梯队题目数量')
    if len(tempdata2) < 10:  # 有时候抽不到那么多题会报错
        random.shuffle(tempdata2)
        # print(tempdata2)
        random_elements3 = random.sample(tempdata2, len(tempdata2))
        for x in random_elements2:
            findaldata.append(x)
    else:
        random.shuffle(tempdata2)
        # print(tempdata2)
        random_elements3 = random.sample(tempdata2, 10)
        for x in random_elements3:
            findaldata.append(x)
    #print(findaldata)
    return findaldata