From 2f8dde4e4250f1b314e96d868e591eb22ee92f80 Mon Sep 17 00:00:00 2001
From: limengdie <2233601742@qq.com>
Date: Mon, 22 Apr 2024 22:48:24 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9A=82=E6=97=B6=E6=8F=90=E4=BA=A4=E4=B9=8B?=
 =?UTF-8?q?=E5=89=8D=E7=9A=84=E4=BF=AE=E5=A4=8D=E4=BB=A3=E7=A0=81,?=
 =?UTF-8?q?=E4=BD=86=E8=AF=A5=E4=BB=A3=E7=A0=81=E9=80=BB=E8=BE=91=E5=AD=98?=
 =?UTF-8?q?=E5=9C=A8=E7=BC=BA=E9=99=B7=EF=BC=8C=E5=BE=85=E8=A7=A3=E5=86=B3?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 app/Article.py                    |  13 +++-
 app/difficulty.py                 |  19 +++--
 app/templates/userpage_get.html   |  57 +++++++++++++++
 app/test/test_bug476_LiMengdie.py | 114 ++++++++++++++++++++++++++++++
 app/user_service.py               |  42 +++++++++--
 5 files changed, 235 insertions(+), 10 deletions(-)
 create mode 100644 app/test/test_bug476_LiMengdie.py

diff --git a/app/Article.py b/app/Article.py
index 566ceb6..f19002e 100644
--- a/app/Article.py
+++ b/app/Article.py
@@ -1,3 +1,4 @@
+
 from WordFreq import WordFreq
 from wordfreqCMD import youdao_link, sort_in_descending_order
 import pickle_idea, pickle_idea2
@@ -10,6 +11,7 @@ from difficulty import get_difficulty_level_for_user, text_difficulty_level, use
 from model.article import get_all_articles, get_article_by_id, get_number_of_articles
 import logging
 
+
 path_prefix = './'
 db_path_prefix = './db/'  # comment this line in deployment
 
@@ -28,7 +30,8 @@ def get_article_body(s):
     return '\n'.join(lst)
 
 
-def get_today_article(user_word_list, visited_articles):
+#user_articlesWithoutNewWords_record 保存前端传来的用户阅读时长超过15秒且不含高亮生词的文章索引
+def get_today_article(user_word_list, visited_articles,user_articlesWithoutNewWords_record):
     if visited_articles is None:
         visited_articles = {
             "index" : 0,  # 为 article_ids 的索引
@@ -57,7 +60,12 @@ def get_today_article(user_word_list, visited_articles):
 
     d_user = load_freq_history(user_word_list)
     logging.debug('* get_today_article(): user_difficulty_level() start')
-    user_level = user_difficulty_level(d_user, d3)  # more consideration as user's behaviour is dynamic. Time factor should be considered.
+
+    articles_id_list=None
+    if os.path.exists(user_articlesWithoutNewWords_record) != False:
+        articles_id_list = pickle_idea.load_record(user_articlesWithoutNewWords_record)
+    #将 用户阅读时长超过15秒且不含高亮生词的文章记录 传入user_difficulty_level并据此 提高用户level
+    user_level = user_difficulty_level(d_user, d3,articles_id_list)  # more consideration as user's behaviour is dynamic. Time factor should be considered.
     logging.debug('* get_today_article(): done')
     text_level = 0
     if visited_articles["index"] > len(visited_articles["article_ids"])-1:  # 生成新的文章
@@ -90,6 +98,7 @@ def get_today_article(user_word_list, visited_articles):
             "user_level": '%4.1f' % user_level,
             "text_level": '%4.1f' % text_level,
             "date": d['date'],
+            "article_id":d['article_id'],#该变量存储 用户阅读时长超过15秒且不含高亮生词的文章索引
             "article_title": get_article_title(d['text']),
             "article_body": get_article_body(d['text']),
             "source": d["source"],
diff --git a/app/difficulty.py b/app/difficulty.py
index 1bd8d68..b75db6b 100644
--- a/app/difficulty.py
+++ b/app/difficulty.py
@@ -7,6 +7,7 @@
 
 import pickle
 import math
+
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
 import snowballstemmer
 
@@ -94,10 +95,21 @@ def revert_dict(d):
     return d2
 
 
-def user_difficulty_level(d_user, d):
+#articlesWithoutNewWords 存储用户阅读时长超过15秒且不含高亮生词的文章索引信息（用户阅读完后没有添加生词的文章）
+def user_difficulty_level(d_user, d,articlesWithoutNewWords):
     d_user2 = revert_dict(d_user)  # key is date, and value is a list of words added in that date
     count = 0
     geometric = 1
+    #传入根据用户生词计算出的用户level
+    def get_level_sum(level):
+        if articlesWithoutNewWords!=None:#若用户阅读完后没有添加生词的文章索引不为空，则根据这些文章的等级适度提高用户的level
+            for article in articlesWithoutNewWords:
+                if(level<float(article.get('text_level'))):
+                    level+=(float(article.get('text_level'))-level)/20 #根据文章等级提高用户level，用户level与用户阅读完后没有添加生词的文章level 差距越大，分数提高程度越大
+        print(f"用户等级{level}")
+        print("-----------------------------------")
+        return level
+
     for date in sorted(d_user2.keys(),
                        reverse=True):  # most recently added words are more important while determining user's level
         lst = d_user2[date]  # a list of words
@@ -115,10 +127,9 @@ def user_difficulty_level(d_user, d):
             geometric = geometric * (hard)
             count += 1
             if count >= 10:
-                return geometric ** (1 / count)
-
-    return geometric ** (1 / max(count, 1))
+                return get_level_sum(geometric ** (1 / count))
 
+    return get_level_sum(geometric ** (1 / max(count, 1)))
 
 def text_difficulty_level(s, d):
     s = remove_punctuation(s)
diff --git a/app/templates/userpage_get.html b/app/templates/userpage_get.html
index 8c684b6..4e25725 100644
--- a/app/templates/userpage_get.html
+++ b/app/templates/userpage_get.html
@@ -173,13 +173,33 @@
     {% endfor %}
 {% endif %}
 <script type="text/javascript">
+
     window.onload = function () { // 页面加载时执行
         // 刷新页面或进入页面时判断，若不是首篇文章，则上一篇按钮可见
         if(sessionStorage.getItem('pre_page_button')!="display" && sessionStorage.getItem('pre_page_button')){
             $('#load_pre_article').show();
         }
+
+        startTime=Date.now();//记录用户页面的初始时间
+        if(window.performance.navigation.type!=1){//将第一次加载页面时的文章id,level保存到本地
+             sessionStorage.setItem('article_id','{{today_article['article_id']}}');
+             sessionStorage.setItem('text_level','{{today_article['text_level']}}');
+        }
+        //
      };
     function load_next_article(){
+        //在进入下一篇之前处理
+        endTime=Date.now();//记录用户点击下一篇文章时的时间
+        spendtime=endTime-startTime;//计算出用户浏览该页面的时长，单位毫秒
+        if(spendtime/1000>15){//若浏览时长大于15，说明用户认真阅读了该篇文章（时长小于15代表用户不感兴趣，跳过，不做任何处理）
+               if(!checkMarkedWords()){//检查该篇文章是否有生词高亮，若没有将文章id,level发送到后台，保存至文件中，在计算用户level时根据文件中保存的文章等级计算
+                    $.ajax({
+                        url: '/submit_article_id_without_new_words/{{username}}/'+sessionStorage.getItem('article_id')+'/'+sessionStorage.getItem('text_level'),
+                        dataType: 'json',
+                        success: function(data) {}
+                    });
+               }
+        }
         $.ajax({
             url: '/get_next_article/{{username}}',
             dataType: 'json',
@@ -192,8 +212,21 @@
                 }
             }
         });
+         startTime=Date.now();//在页面加载完下一篇文章，记录起始时间
     }
     function load_pre_article(){
+        //在进入上一篇之前处理
+        endTime=Date.now();//记录用户点击上一篇文章时的时间
+        spendtime=endTime-startTime;//计算出用户浏览该文章的时长，单位毫秒
+        if(spendtime/1000>15){
+               if(!checkMarkedWords()){
+                    $.ajax({
+                        url: '/submit_article_id_without_new_words/{{username}}/'+sessionStorage.getItem('article_id')+'/'+sessionStorage.getItem('text_level'),
+                        dataType: 'json',
+                        success: function(data) {}
+                    });
+               }
+        }
         $.ajax({
             url: '/get_pre_article/{{username}}',
             dataType: 'json',
@@ -205,6 +238,7 @@
                 }
             }
         });
+        startTime=Date.now();//在页面加载完下一篇文章，记录起始时间
     }
     function update(today_article){
         $('#user_level').html(today_article['user_level']);
@@ -219,7 +253,30 @@
         setTimeout(() => {document.querySelector('#text_level').classList.remove('mark');}, 2000);
         document.querySelector('#user_level').classList.add('mark'); // do the same thing for user difficulty level
         setTimeout(() => {document.querySelector('#user_level').classList.remove('mark');}, 2000);
+
+        sessionStorage.setItem('article_id',today_article["article_id"]);//将更新后的文章id,level保存到本地
+        sessionStorage.setItem('text_level',today_article['text_level']);
     }
+
+    function checkMarkedWords(){//检查文章中是否有高亮生词
+        let article_title= document.getElementById("article_title").innerHTML;//从页面中获取文章名和内容
+        let article_body=document.getElementById("article").innerHTML;
+        let article=article_title+" "+article_body;
+        let pickedWords = document.getElementById("selected-words");  // words picked to the text area
+        let dictionaryWords = document.getElementById("selected-words2"); // words appearing in the user's new words list
+        let allWords = dictionaryWords === null ? pickedWords.value + " " : pickedWords.value + " " + dictionaryWords.value;
+        const list = allWords.split(" "); // 将所有的生词放入一个list中
+        for (let i = 0; i < list.length; ++i) {
+            list[i] = list[i].replace(/(^\W*)|(\W*$)/g, "");
+        }
+        for (let i=1;i<list.length-1;i++){//对list中的每个生词进行查找，判断文章中是否有该生词
+            if(article.search(list[i])!==-1){
+                   return true;
+            }
+        }
+        return false;
+    }
+    //
 <!-- 检查是否存在上一篇或下一篇，不存在则对应按钮隐藏-->
     function check_pre(visited_articles){
         if((visited_articles=='')||(visited_articles['index']<=0)){
diff --git a/app/test/test_bug476_LiMengdie.py b/app/test/test_bug476_LiMengdie.py
new file mode 100644
index 0000000..f459461
--- /dev/null
+++ b/app/test/test_bug476_LiMengdie.py
@@ -0,0 +1,114 @@
+import time
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import UnexpectedAlertPresentException, NoAlertPresentException, \
+    ElementClickInterceptedException, NoSuchElementException, TimeoutException
+from helper import signup
+
+
+def is_textarea_empty(driver):
+    # 获取<textarea>元素的内容,判断是否加入了生词
+    textarea_element = driver.find_element(By.ID, 'selected-words')
+    content = textarea_element.get_attribute("value")
+
+    return content is None or content.strip() == ""
+
+
+def get_user_level(driver):
+    return float(driver.find_element(By.ID, 'user_level').text)
+
+
+def scroll(total_time, driver):
+    try:
+        half_time = (total_time - 2) / 2  # 分成两半，一半时间滚到底，一半时间滚回顶,模拟阅读时间
+
+        # 滚动到底部
+        start_time = time.time()
+        end_time = start_time + half_time
+        while time.time() < end_time:
+            driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
+        # 确保滚动更平滑
+        time.sleep(1)
+
+        # 滚动回顶部
+        start_time = time.time()
+        end_time = start_time + half_time
+        while time.time() < end_time:
+            driver.execute_script("window.scrollTo(0, -document.body.scrollHeight);")
+        time.sleep(1)
+
+    except ElementClickInterceptedException:
+        print("加载出错")
+
+
+def read_test_with_time(driver, total_time):
+    # 获取点击前的user_level和text_level
+    before_user_level = get_user_level(driver)
+    before_text_level = float(driver.find_element(By.ID, 'text_level').text)
+
+    # 检查是否加入了生词簿
+    check = is_textarea_empty(driver)
+
+    scroll(total_time, driver)
+    # 定位“下一页”按钮
+    next_button = driver.find_element(By.ID, 'load_next_article')
+    # 模拟点击
+    next_button.click()
+
+    # 关闭弹窗
+    try:
+        WebDriverWait(driver, 1).until(EC.alert_is_present())
+        driver.switch_to.alert.accept()
+    except (UnexpectedAlertPresentException, NoAlertPresentException):
+        pass
+
+    # 等待页面加载完毕，正确地获取更新后的值
+    time.sleep(2)
+
+    # 获取点击后的user_level
+    after_user_level = get_user_level(driver)
+
+    # 等待3秒方便观察测试
+    time.sleep(3)
+
+    return before_user_level, after_user_level, before_text_level, check
+
+
+def test_score_with_enough_time(driver, URL):
+    try:
+        # 登录并跳转到测试主页面
+        signup(URL, driver)
+        # 测试阅读到足够时间的等级变化
+        before_user_level, after_user_level, before_text_level, check = read_test_with_time(driver, 18)
+
+        # print(check, before_user_level, after_user_level, before_text_level)
+
+        if before_user_level < before_text_level and check:
+            assert before_user_level < after_user_level, 'The user level dose not increase after reading an article with a high level and clicking to navigate away without adding any new vocabulary. '
+
+
+    except (NoSuchElementException, TimeoutException) as e:
+        print("Error occurs: " + str(e))
+
+    finally:
+        driver.quit()
+
+
+def test_score_without_enough_time(driver, URL):
+    try:
+        # 登录并跳转到测试主页面
+        signup(URL, driver)
+        # 测试阅读时间不足够的等级变化
+        before_user_level, after_user_level, before_text_level, check = read_test_with_time(driver, 6)
+
+        # print(check, before_user_level, after_user_level, before_text_level)
+
+        if before_user_level < before_text_level and check:
+            assert before_user_level == after_user_level, 'After the user quickly skipped through the article, the user level does not remain unchanged. '
+
+    except (NoSuchElementException, TimeoutException) as e:
+        print("Error occurs: " + str(e))
+
+    finally:
+        driver.quit()
diff --git a/app/user_service.py b/app/user_service.py
index 27323b8..9f94979 100644
--- a/app/user_service.py
+++ b/app/user_service.py
@@ -1,3 +1,5 @@
+import pickle
+import os.path
 from datetime import datetime
 from admin_service import ADMIN_NAME
 from flask import *
@@ -26,6 +28,8 @@ path_prefix = './'  # comment this line in deployment
 
 @userService.route("/get_next_article/<username>",methods=['GET','POST'])
 def get_next_article(username):
+    user_articlesWithoutNewWords_record = path_prefix + 'static/frequency/' + 'ArticlesWithoutNewWords_%s.pickle' % (username)
+
     user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
     session['old_articleID'] = session.get('articleID')
     if request.method == 'GET':
@@ -36,7 +40,7 @@ def get_next_article(username):
             visited_articles["index"] += 1
         session["visited_articles"] = visited_articles
         logging.debug('/get_next_article: start calling get_today_arcile()')
-        visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
+        visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'),user_articlesWithoutNewWords_record)
         logging.debug('/get_next_arcile: done.')
         data = {
             'visited_articles': visited_articles,
@@ -47,8 +51,37 @@ def get_next_article(username):
         return 'Under construction'
     return json.dumps(data)
 
+#保存前端传来 用户阅读时长超过15秒且不含高亮生词的文章（用户阅读完后没有添加生词的文章）的id,level
+@userService.route("/submit_article_id_without_new_words/<username>/<article_id>/<text_level>",methods=['GET'])
+def set_article_id_without_new_words(username,article_id,text_level):
+    user_articles_without_new_words_record_path = path_prefix + 'static/frequency/' + 'ArticlesWithoutNewWords_%s.pickle' % (username)
+    if os.path.exists(user_articles_without_new_words_record_path)==False: #若不存在 存储用户阅读时长超过15秒且不含高亮生词的文章索引信息的文件 则新建
+        f = open(user_articles_without_new_words_record_path, 'wb')
+        list=[]
+        pickle.dump(list,f)
+        f.close()
+
+    fp=open(user_articles_without_new_words_record_path,'rb')
+    user_article_id_record=pickle.load(fp)
+    fp.close()
+
+    dic = {}
+    dic['article_id'] = article_id
+    dic['text_level'] = text_level
+
+    if dic not in user_article_id_record: #若已存在记录（即这篇文章之前被阅读过且没有添加生词，且已加入索引信息记录文件中），则不再重复加入，避免重复刷分
+        user_article_id_record.append(dic)
+        print(f"编号为{article_id}的文章，阅读时间大于15秒且未有生词，记录于ArticlesWithoutNewWords_<username>.pickle")
+        print(user_article_id_record)
+        f=open(user_articles_without_new_words_record_path,'wb')
+        pickle.dump(user_article_id_record,f)
+        f.close()
+    return "success"
+
 @userService.route("/get_pre_article/<username>",methods=['GET'])
 def get_pre_article(username):
+    user_articlesWithoutNewWords_record = path_prefix + 'static/frequency/' + 'ArticlesWithoutNewWords_%s.pickle' % (
+        username)
     user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
     if request.method == 'GET':
         visited_articles = session.get("visited_articles")
@@ -59,7 +92,7 @@ def get_pre_article(username):
             if visited_articles['article_ids'][-1] == "null":  # 如果当前还是“null”，则将“null”pop出来
                 visited_articles['article_ids'].pop()
             session["visited_articles"] = visited_articles
-            visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
+            visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'),user_articlesWithoutNewWords_record)
             data = {
                 'visited_articles': visited_articles,
                 'today_article': today_article,
@@ -130,7 +163,8 @@ def userpage(username):
 
     # 获取session里的用户名
     username = session.get('username')
-
+    user_articlesWithoutNewWords_record = path_prefix + 'static/frequency/' + 'ArticlesWithoutNewWords_%s.pickle' % (
+        username)
     user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
 
     if request.method == 'POST':  # when we submit a form
@@ -149,7 +183,7 @@ def userpage(username):
         words = ''
         for x in lst3:
             words += x[0] + ' '
-        visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
+        visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'),user_articlesWithoutNewWords_record)
         session['visited_articles'] = visited_articles
         # 通过 today_article，加载前端的显示页面
         return render_template('userpage_get.html',