为系统添加一个全局变量记录数据库的单词及其等级，使得数据库单词等级只需在登录时进行一次评级，大致能将点击下一篇的时间缩减为原来的10^-15次以下，感谢章翊、赵煜涵、唐伟、宋江涛同学的建议，没有他们我懒得改的

修复了 Bug492 选中问号出现多个问号的问题。
解决了选中紧跟标点符号的单词，单词能正常显示。
优化了选中较长的文章时页面容易出现卡顿的问题。

app/difficulty.py

@@ -6,10 +6,14 @@
 # Purpose: compute difficulty level of a English text
 
 import pickle
-import math
-from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
+import time
+
 import snowballstemmer
 
+from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
+
+# 定义一个全局的res_d， 记录数据库单词评级之后的单词及其等级
+res_d = {}
 
 def load_record(pickle_fname):
     f = open(pickle_fname, 'rb')
@@ -24,6 +28,7 @@ def convert_test_type_to_difficulty_level(d):
     :param d: 存储了单词库pickle文件中的单词的字典
     :return:
     """
+    time_start = time.time()
     result = {}
     L = list(d.keys())  # in d, we have test types (e.g., CET4,CET6,BBC) for each word
 
@@ -38,7 +43,10 @@ def convert_test_type_to_difficulty_level(d):
             result[k] = 7
         elif 'BBC' in d[k]:
             result[k] = 8
-
+    time_end = time.time()
+    print('convert_test_type_to_difficulty_level totally cost', time_end - time_start)
+    global res_d
+    res_d = result
     return result  # {'apple': 4, ...}
 
 
@@ -48,8 +56,12 @@ def get_difficulty_level_for_user(d1, d2):
     d1 用户不会的词
     在d2的后面添加单词，没有新建一个新的字典
     """
+    time_start = time.time()
     # TODO: convert_test_type_to_difficulty_level() should not be called every time.  Each word's difficulty level should be pre-computed.
-    d2 = convert_test_type_to_difficulty_level(d2)  # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
+    if res_d == {}:
+        d2 = convert_test_type_to_difficulty_level(d2)  # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
+    else:
+        d2 = res_d
     stemmer = snowballstemmer.stemmer('english')
 
     for k in d1:  # 用户的词
@@ -61,6 +73,8 @@ def get_difficulty_level_for_user(d1, d2):
                 d2[k] = d2[stem]  # 按照词根进行评级
             else:
                 d2[k] = 3  # 如果k的词根都不在，那么就当认为是3级
+    time_end = time.time()
+    print('get_difficulty_level_for_user totally cost', time_end - time_start)
     return d2
 
 

app/static/js/fillword.js

@@ -29,3 +29,8 @@ function onReadClick() {
 function onChooseClick() {
     isChoose = !isChoose;
 }
+
+// 如果网页刷新，停止播放声音
+if (performance.getEntriesByType("navigation")[0].type == "reload") {
+    Reader.stopRead();
+}

app/static/js/highlight.js

@@ -22,62 +22,38 @@ function getWord() {
 
 function highLight() {
     if (!isHighlight) return;
-    let articleContent = document.getElementById("article").innerText; //将原来的.innerText改为.innerHtml，使用innerText会把原文章中所包含的<br>标签去除，导致处理后的文章内容失去了原来的格式
+    let articleContent = document.getElementById("article").innerHTML; // innerHTML保留HTML标签来保持部分格式，且适配不同的浏览器
     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 = "";  //初始化allWords的值，避免进入判断后编译器认为allWords未初始化的问题
-    if(dictionaryWords != null){//增加一个判断，检查生词本里面是否为空，如果为空，allWords只添加选中的单词
-        allWords = pickedWords.value + " " + dictionaryWords.value;
-    }
-    else{
-        allWords = pickedWords.value + " ";
-    }
-    const list = allWords.split(" ");//将所有的生词放入一个list中，用于后续处理
+    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
+    let totalSet = new Set();
     for (let i = 0; i < list.length; ++i) {
-        list[i] = list[i].replace(/(^\s*)|(\s*$)/g, ""); //消除单词两边的空字符
-        list[i] = list[i].replace('|', "");
-        list[i] = list[i].replace('?', "");
-        if (list[i] !== "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
-           //将文章中所有出现该单词word的地方改为："<mark>" + word + "<mark>"。 正则表达式RegExp()中，"\\b"代表单词边界匹配。
-
-            //修改代码
-            let articleContent_fb = articleContent;  //文章副本
-            while(articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase()) !== -1 && list[i]!=""){
-                //找到副本中和list[i]匹配的第一个单词(第一种匹配情况),并赋值给list[i]。
-                const index = articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase());
-                list[i] = articleContent_fb.substring(index, index + list[i].length);
-
-                articleContent_fb = articleContent_fb.substring(index + list[i].length);    // 使用副本中list[i]之后的子串替换掉副本
-                articleContent = articleContent.replace(new RegExp("\\b"+list[i]+"\\b","g"),"<mark>" + list[i] + "</mark>");
+        list[i] = list[i].replace(/(^\W*)|(\W*$)/g, ""); // 消除单词两边的非单词字符
+        if (list[i] != "" && !totalSet.has(list[i])) {
+            // 返回所有匹配单词的集合, 正则表达式RegExp()中, "\b"匹配一个单词的边界, g 表示全局匹配, i 表示对大小写不敏感。
+            let matches = new Set(articleContent.match(new RegExp("\\b" + list[i] + "\\b", "gi")));
+            if (matches.has("mark")) {
+                // 优先处理单词为 "mark" 的情况
+                totalSet = new Set(["mark", ...totalSet]);
             }
+            totalSet = new Set([...totalSet, ...matches]);
         }
     } 
+    // 删除所有的mark标签,防止标签发生嵌套
+    articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
+    articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
+    // 将文章中所有出现该单词word的地方改为："<mark>" + word + "<mark>"。
+    for (let word of totalSet) {
+        articleContent = articleContent.replace(new RegExp("\\b" + word + "\\b", "g"), "<mark>" + word + "</mark>");
+    }
     document.getElementById("article").innerHTML = articleContent;
 }
 
 function cancelHighlighting() {
-    let articleContent = document.getElementById("article").innerText;//将原来的.innerText改为.innerHtml，原因同上
-    let pickedWords = document.getElementById("selected-words");
-    const dictionaryWords = document.getElementById("selected-words2");    
-    const list = pickedWords.value.split(" ");    
-    if (pickedWords != null) {
-        for (let i = 0; i < list.length; ++i) {
-            list[i] = list[i].replace(/(^\s*)|(\s*$)/g, "");
-            if (list[i] !== "") { //原来判断的代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
-                articleContent = articleContent.replace(new RegExp("<mark>"+list[i]+"</mark>", "g"), list[i]);
-            }
-        }
-    }
-    if (dictionaryWords != null) {
-        let list2 = pickedWords.value.split(" ");
-        for (let i = 0; i < list2.length; ++i) {
-            list2 = dictionaryWords.value.split(" ");
-            list2[i] = list2[i].replace(/(^\s*)|(\s*$)/g, "");
-            if (list2[i] !== "") { //原来代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
-                articleContent = articleContent.replace(new RegExp("<mark>"+list2[i]+"</mark>", "g"), list2[i]);
-            }
-        }
-    }
+    let articleContent = document.getElementById("article").innerHTML;
+    articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
+    articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
     document.getElementById("article").innerHTML = articleContent;
 }
 

app/static/js/read.js

@@ -9,7 +9,7 @@ var Reader = (function() {
         msg.rate = rate;
         msg.lang = "en-US";
         msg.onboundary = ev => {
-            if (ev.name == "word") {
+            if (ev.name === "word") {
                 current_position = ev.charIndex;
             }
         }
@@ -32,4 +32,4 @@ var Reader = (function() {
         read: read,
         stopRead: stopRead
     };
-})();
+}) ();

app/static/js/word_operation.js

@@ -5,15 +5,14 @@ function familiar(theWord) {
     $.ajax({
         type:"GET",
         url:"/" + username + "/" + word + "/familiar",
-        success:function(response){
+        success:function(response) {
             let new_freq = freq - 1;
             const allow_move = document.getElementById("move_dynamiclly").checked;
             if (allow_move) {
-
                 if (new_freq <= 0) {
                     removeWord(theWord);
                 } else {
-                    renderWord({ word: theWord, freq: new_freq });
+                    renderWord({word: theWord, freq: new_freq});
                 }
             } else {
                 if(new_freq <1) {
@@ -33,11 +32,11 @@ function unfamiliar(theWord) {
     $.ajax({
         type:"GET",
         url:"/" + username + "/" + word + "/unfamiliar",
-        success:function(response){
+        success:function(response) {
             let new_freq = parseInt(freq) + 1;
             const allow_move = document.getElementById("move_dynamiclly").checked;
             if (allow_move) {
-                renderWord({ word: theWord, freq: new_freq });
+                renderWord({word: theWord, freq: new_freq});
             } else {
                 $("#freq_" + theWord).text(new_freq);
             }
@@ -51,7 +50,7 @@ function delete_word(theWord) {
     $.ajax({
         type:"GET",
         url:"/" + username + "/" + word + "/del",
-        success:function(response){
+        success:function(response) {
             const allow_move = document.getElementById("move_dynamiclly").checked;
             if (allow_move) {
                 removeWord(theWord);
@@ -114,7 +113,7 @@ function removeWord(word) {
     // 根据词频信息删除元素
     word = word.replace('&amp;', '&');
     const element_to_remove = document.getElementById(`p_${word}`);
-    if (element_to_remove != null) {
+    if (element_to_remove !== null) {
         element_to_remove.remove();
     }
 }
@@ -129,7 +128,7 @@ function renderWord(word) {
     for (const current of container.children) {
         const cur_word = parseWord(current);
         // 找到第一个词频比它小的元素，插入到这个元素前面
-        if (compareWord(cur_word, word) == -1) {
+        if (compareWord(cur_word, word) === -1) {
             container.insertBefore(new_element, current);
             inserted = true;
             break;
@@ -165,17 +164,11 @@ function elementFromString(string) {
  *  当first大于second时返回1
  */
 function compareWord(first, second) {
-    if (first.freq < second.freq) {
-        return -1;
+    if (first.freq !== second.freq) {
+        return first.freq < second.freq ? -1 : 1;
     }
-    if (first.freq > second.freq) {
-        return 1;
-    }
-    if (first.word < second.word) {
-        return -1;
-    }
-    if (first.word > second.word) {
-        return 1;
+    if (first.word !== second.word) {
+        return first.word < second.word ? -1 : 1;
     }
     return 0;
 }

app/templates/userpage_get.html

@@ -32,6 +32,17 @@
             40%, 60% { transform: translate3d(+4px, 0, 0); }
             50% { transform: translate3d(-4px, 0, 0); }
         }
+
+        .lead{
+            font-size: 17px;
+            font-family: Arial, Helvetica, sans-serif;
+        }
+
+        .display-5{
+            font-size: 30px;
+        }
+
+
     </style>
 </head>
 <body>
@@ -49,18 +60,22 @@
 {#        <div class="alert alert-warning" role="alert">Congratulations! {{ message }}</div>#}
 {#    {% endfor %}#}
 
-        <button class="btn btn-success" id="load_next_article" onclick="load_next_article()"> 下一篇 Next Article </button>
-        <button class="btn btn-success" id="load_pre_article" onclick="load_pre_article()" > 上一篇 Previous Article </button>
+        <button class="btn btn-success" id="load_next_article" onclick="load_next_article();Reader.stopRead()"> 下一篇 Next Article </button>
+        <button class="btn btn-success" id="load_pre_article" onclick="load_pre_article();Reader.stopRead()" > 上一篇 Previous Article </button>
 
     <p><b>阅读文章并回答问题</b></p>
     <div id="text-content">
         <div id="found">
             <div class="alert alert-success" role="alert">According to your word list, your level is <span class="badge bg-success" id="user-level">{{ today_article["user_level"] }}</span>  and we have chosen an article with a difficulty level of <span class="badge bg-success" id="text_level">{{ today_article["text_level"] }}</span> for you.</div>
                 <p class="text-muted" id="date">Article added on: {{ today_article["date"] }}</p><br/>
-            <div class="p-3 mb-2 bg-light text-dark"><br/>
+            <div class="p-3 mb-2 bg-light text-dark" style="margin: 0 0.5%;"><br/>
             <p class="display-5" id="article_title">{{ today_article["article_title"] }}</p><br/>
-            <p class="lead"><font id="article" size=2>{{ today_article["article_body"] }}</font></p><br/>
-            <p><small class="text-muted" id="source">{{ today_article['source'] }}</small></p><br/>
+            <p class="lead"><font id="article">{{ today_article["article_body"] }}</font></p><br/>
+            <div>
+                <h6>source: </h6>
+                <p><small class="text-muted" id="source">{{ today_article['source'] }}</small></p><br/>
+            </div>
+            
             <p><b id="question">{{ today_article['question'] }}</b></p><br/>
                 <script type="text/javascript">
                     function toggle_visibility(id) { {# https://css-tricks.com/snippets/javascript/showhide-element/#}
@@ -97,7 +112,7 @@
     <p><b>收集生词吧</b> （可以在正文中划词，也可以复制黏贴）</p>
     <form method="post" action="/{{ username }}/userpage">
         <textarea name="content" id="selected-words" rows="10" cols="120"></textarea><br/>
-        <input type="submit" value="把生词加入我的生词库"/>
+        <input type="submit" value="把生词加入我的生词库" onclick="Reader.stopRead()"/>
         <input type="reset" value="清除"/>
     </form>
     {% if session.get['thisWord'] %}