app/difficulty.py

@@ -6,14 +6,10 @@
 # Purpose: compute difficulty level of a English text
 
 import pickle
-import time
+import math
-
+from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
 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')
@@ -28,7 +24,6 @@ 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
 
@@ -43,10 +38,7 @@ 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, ...}
 
 
@@ -56,12 +48,8 @@ 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.
-    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
@@ -73,8 +61,6 @@ 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

@@ -29,8 +29,3 @@ 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

@@ -22,38 +22,62 @@ function getWord() {
 
 function highLight() {
     if (!isHighlight) return;
-    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 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 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;
+    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
-    const list = allWords.split(" "); // 将所有的生词放入一个list中
+    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
-    let totalSet = new Set();
+        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
     for (let i = 0; i < list.length; ++i) {
-        list[i] = list[i].replace(/(^\W*)|(\W*$)/g, ""); // 消除单词两边的非单词字符
+        list[i] = list[i].replace(/(^\s*)|(\s*$)/g, ""); //消除单词两边的空字符
-        if (list[i] != "" && !totalSet.has(list[i])) {
+        list[i] = list[i].replace('|', "");
-            // 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。
+        list[i] = list[i].replace('?', "");
-            let matches = new Set(articleContent.match(new RegExp("\\b" + list[i] + "\\b", "gi")));
+        if (list[i] !== "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
-            if (matches.has("mark")) {
+           //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。
-                // 优先处理单词为 "mark" 的情况
+
-                totalSet = new Set(["mark", ...totalSet]);
+            //修改代码
-            }
+            let articleContent_fb = articleContent;  //文章副本
-            totalSet = new Set([...totalSet, ...matches]);
+            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>");
             }
         }
-    // 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").innerHTML;
+    let articleContent = document.getElementById("article").innerText;//将原来的.innerText改为.innerHtml，原因同上
-    articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
+    let pickedWords = document.getElementById("selected-words");
-    articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
+    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]);
+            }
+        }
+    }
     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;
             }
         }

app/static/js/word_operation.js

@@ -9,6 +9,7 @@ function familiar(theWord) {
             let new_freq = freq - 1;
             const allow_move = document.getElementById("move_dynamiclly").checked;
             if (allow_move) {
+
                 if (new_freq <= 0) {
                     removeWord(theWord);
                 } else {
@@ -113,7 +114,7 @@ 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();
     }
 }
@@ -128,7 +129,7 @@ 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;
@@ -164,11 +165,17 @@ function elementFromString(string) {
  *  当first大于second时返回1
  */
 function compareWord(first, second) {
-    if (first.freq !== second.freq) {
+    if (first.freq < second.freq) {
-        return first.freq < second.freq ? -1 : 1;
+        return -1;
     }
-    if (first.word !== second.word) {
+    if (first.freq > second.freq) {
-        return first.word < second.word ? -1 : 1;
+        return 1;
+    }
+    if (first.word < second.word) {
+        return -1;
+    }
+    if (first.word > second.word) {
+        return 1;
     }
     return 0;
 }

app/templates/userpage_get.html

@@ -32,17 +32,6 @@
             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>
@@ -60,22 +49,18 @@
 {#        <div class="alert alert-warning" role="alert">Congratulations! {{ message }}</div>#}
 {#    {% endfor %}#}
 
-        <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_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();Reader.stopRead()" > 上一篇 Previous Article </button>
+        <button class="btn btn-success" id="load_pre_article" onclick="load_pre_article()" > 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" style="margin: 0 0.5%;"><br/>
+            <div class="p-3 mb-2 bg-light text-dark"><br/>
             <p class="display-5" id="article_title">{{ today_article["article_title"] }}</p><br/>
-            <p class="lead"><font id="article">{{ today_article["article_body"] }}</font></p><br/>
+            <p class="lead"><font id="article" size=2>{{ 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/#}
@@ -112,7 +97,7 @@
     <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" onclick="Reader.stopRead()"/>
+        <input type="submit" value="把生词加入我的生词库"/>
         <input type="reset" value="清除"/>
     </form>
     {% if session.get['thisWord'] %}