combine_words_through_grammar replaced with stem_words function using nltk stemmer

app/Article.py

@@ -7,7 +7,7 @@ import random, glob
 import hashlib
 from datetime import datetime
 from flask import Flask, request, redirect, render_template, url_for, session, abort, flash, get_flashed_messages
-from difficulty import get_difficulty_level_for_user, text_difficulty_level, user_difficulty_level
+from difficulty import get_difficulty_level, text_difficulty_level, user_difficulty_level
 
 
 path_prefix = '/var/www/wordfreq/wordfreq/'
@@ -53,7 +53,7 @@ def get_today_article(user_word_list, visited_articles):
     # Choose article according to reader's level
     d1 = load_freq_history(path_prefix + 'static/frequency/frequency.p')
     d2 = load_freq_history(path_prefix + 'static/words_and_tests.p')
-    d3 = get_difficulty_level_for_user(d1, d2)
+    d3 = get_difficulty_level(d1, d2)
 
     d = None
     result_of_generate_article = "not found"

app/difficulty.py

@@ -7,8 +7,8 @@
 
 import pickle
 import math
+from nltk.stem import WordNetLemmatizer # using WordNetLemmatizer for better performance
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
-import snowballstemmer
 
 
 def load_record(pickle_fname):
@@ -18,51 +18,41 @@ def load_record(pickle_fname):
     return d
 
 
-def convert_test_type_to_difficulty_level(d):
+def difficulty_level_from_frequency(word, d):
-    """
+    level = 1
-    对原本的单词库中的单词进行难度评级
+    if not word in d:
-    :param d: 存储了单词库pickle文件中的单词的字典
+        return level
-    :return:
+    
-    """
+    if 'what' in d:
-    result = {}
+        ratio = (d['what']+1)/(d[word]+1) # what is a frequent word
-    L = list(d.keys())  # in d, we have test types (e.g., CET4,CET6,BBC) for each word
+        level = math.log( max(ratio, 1), 2)
 
-    for k in L:
+    level = min(level, 8) 
-        if 'CET4' in d[k]:
+    return level
-            result[k] = 4  # CET4 word has level 4
-        elif 'OXFORD3000' in d[k]:
-            result[k] = 5
-        elif 'CET6' in d[k] or 'GRADUATE' in d[k]:
-            result[k] = 6
-        elif 'OXFORD5000' in d[k] or 'IELTS' in d[k]:
-            result[k] = 7
-        elif 'BBC' in d[k]:
-            result[k] = 8
-
-    return result  # {'apple': 4, ...}
 
 
-def get_difficulty_level_for_user(d1, d2):
+def get_difficulty_level(d1, d2):
-    """
+    d = {}
-    d2 来自于词库的35511个已标记单词
+    L = list(d1.keys())  # in d1, we have freuqence for each word
-    d1 用户不会的词
+    L2 = list(d2.keys()) # in d2, we have test types (e.g., CET4,CET6,BBC) for each word
-    在d2的后面添加单词，没有新建一个新的字典
+    L.extend(L2)
-    """
+    L3 = list(set(L)) # L3 contains all words
-    # TODO: convert_test_type_to_difficulty_level() should not be called every time.  Each word's difficulty level should be pre-computed.
+    for k in L3:
-    d2 = convert_test_type_to_difficulty_level(d2)  # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
+        if k in d2:
-    stemmer = snowballstemmer.stemmer('english')
+            if 'CET4' in d2[k]:
+                d[k] = 4 # CET4 word has level 4
+            elif 'CET6' in d2[k]:
+                d[k] = 6
+            elif 'BBC' in d2[k]:
+                d[k] = 8
+                if k in d1: # BBC could contain easy words that are not in CET4 or CET6.  So 4 is not reasonable.  Recompute difficulty level.
+                    d[k] = min(difficulty_level_from_frequency(k, d1), d[k])
+        elif k in d1:
+            d[k] = difficulty_level_from_frequency(k, d1)
 
-    for k in d1:  # 用户的词
+    return d
-        if k in d2:  # 如果用户的词以原型的形式存在于词库d2中
-            continue  # 无需评级，跳过
-        else:
-            stem = stemmer.stemWord(k)
-            if stem in d2:  # 如果用户的词的词根存在于词库d2的词根库中
-                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
-    return d2
 
+        
 
 def revert_dict(d):
     '''
@@ -73,13 +63,12 @@ def revert_dict(d):
     for k in d:
         if type(d[k]) is list:  # d[k] is a list of dates.
             lst = d[k]
-        elif type(d[
+        elif type(d[k]) is int: # for backward compatibility.  d was sth like {'word':1}.  The value d[k] is not a list of dates, but a number representing how frequent this word had been added to the new word book. 
-                      k]) is int:  # for backward compatibility.  d was sth like {'word':1}.  The value d[k] is not a list of dates, but a number representing how frequent this word had been added to the new word book.
             freq = d[k]
-            lst = freq * ['2021082019']  # why choose this date?  No particular reasons.  I fix the bug in this date.
+            lst = freq*['2021082019'] # why choose this date?  No particular reasons.  I fix the bug in this date.
 
         for time_info in lst:
-            date = time_info[:10]  # until hour
+            date = time_info[:10] # until hour
             if not date in d2:
                 d2[date] = [k]
             else:
@@ -87,45 +76,52 @@ def revert_dict(d):
     return d2
 
 
+def stem_words(list_of_words):  # It reduces words to the root word (eg. ate, eaten -> eat; leaves, leaf -> leaf)
+    wnl = WordNetLemmatizer()
+    lst1 = [wnl.lemmatize(w) for w in list_of_words]
+    return [wnl.lemmatize(w, pos='v') for w in lst1]  # stem by verb: 'v' represents verb
+
+
 def user_difficulty_level(d_user, d):
-    d_user2 = revert_dict(d_user)  # key is date, and value is a list of words added in that date
+    d_user2 = revert_dict(d_user) # key is date, and value is a list of words added in that date
     count = 0
     geometric = 1
-    for date in sorted(d_user2.keys(),
+    for date in sorted(d_user2.keys(), reverse=True): # most recently added words are more important while determining user's level
-                       reverse=True):  # most recently added words are more important while determining user's level
+        lst = d_user2[date] # a list of words
-        lst = d_user2[date]  # a list of words
+        #print(lst)
-        lst2 = []  # a list of tuples, (word, difficulty level)
+        lst = stem_words(lst) # this call returns a list of words reduced to root word
-        for word in lst:
+        #print(lst)
+        lst2 = [] # a list of tuples, (word, difficulty level)
+        for  word in lst:
             if word in d:
                 lst2.append((word, d[word]))
 
-        lst3 = sort_in_ascending_order(lst2)  # easiest tuple first
+        lst3 = sort_in_ascending_order(lst2) # easiest tuple first
-        # print(lst3)
+        #print(lst3)
         for t in lst3:
             word = t[0]
             hard = t[1]
-            # print('WORD %s HARD %4.2f' % (word, hard))
+            print('WORD %s HARD %4.2f' % (word, hard))
             geometric = geometric * (hard)
             count += 1
             if count >= 10:
-                return geometric ** (1 / count)
+                return geometric**(1/count)
 
-    return geometric ** (1 / max(count, 1))
+    return geometric**(1/max(count,1))
 
 
 def text_difficulty_level(s, d):
     s = remove_punctuation(s)
     L = freq(s)
 
-    lst = []  # a list of tuples, each tuple being (word, difficulty level)
+    lst = [] # a list of tuples, each tuple being (word, difficulty level)
-    stop_words = {'the':1, 'and':1, 'of':1, 'to':1, 'what':1, 'in':1, 'there':1, 'when':1, 'them':1, 'would':1, 'will':1, 'out':1, 'his':1, 'mr':1, 'that':1, 'up':1, 'more':1, 'your':1, 'it':1, 'now':1, 'very':1, 'then':1, 'could':1, 'he':1, 'any':1, 'some':1, 'with':1, 'into':1, 'you':1, 'our':1, 'man':1, 'other':1, 'time':1, 'was':1, 'than':1, 'know':1, 'about':1, 'only':1, 'like':1, 'how':1, 'see':1, 'is':1, 'before':1, 'such':1, 'little':1, 'two':1, 'its':1, 'as':1, 'these':1, 'may':1, 'much':1, 'down':1, 'for':1, 'well':1, 'should':1, 'those':1, 'after':1, 'same':1, 'must':1, 'say':1, 'first':1, 'again':1, 'us':1, 'great':1, 'where':1, 'being':1, 'come':1, 'over':1, 'good':1, 'himself':1, 'am':1, 'never':1, 'on':1, 'old':1, 'here':1, 'way':1, 'at':1, 'go':1, 'upon':1, 'have':1, 'had':1, 'without':1, 'my':1, 'day':1, 'be':1, 'but':1, 'though':1, 'from':1, 'not':1, 'too':1, 'another':1, 'this':1, 'even':1, 'still':1, 'her':1, 'yet':1, 'under':1, 'by':1, 'let':1, 'just':1, 'all':1, 'because':1, 'we':1, 'always':1, 'off':1, 'yes':1, 'so':1, 'while':1, 'why':1, 'which':1, 'me':1, 'are':1, 'or':1, 'no':1, 'if':1, 'an':1, 'also':1, 'thus':1, 'who':1, 'cannot':1, 'she':1, 'whether':1} # ignore these words while computing the artile's difficulty level
     for x in L:
         word = x[0]
-        if word not in stop_words and word in d:
+        if word in d:
             lst.append((word, d[word]))
 
-    lst2 = sort_in_descending_order(lst)  # most difficult words on top
+    lst2 = sort_in_descending_order(lst) # most difficult words on top
-    # print(lst2)
+    #print(lst2)
     count = 0
     geometric = 1
     for t in lst2:
@@ -133,20 +129,24 @@ def text_difficulty_level(s, d):
         hard = t[1]
         geometric = geometric * (hard)
         count += 1
-        if count >= 20:  # we look for n most difficult words
+        if count >= 20: # we look for n most difficult words
-            return geometric ** (1 / count)
+            return geometric**(1/count)
+        
+    return geometric**(1/max(count,1))
 
-    return geometric ** (1 / max(count, 1))
 
 
 if __name__ == '__main__':
+
+
     d1 = load_record('frequency.p')
-    # print(d1)
+    #print(d1)
 
     d2 = load_record('words_and_tests.p')
-    # print(d2)
+    #print(d2)
 
-    d3 = get_difficulty_level_for_user(d1, d2)
+
+    d3 = get_difficulty_level(d1, d2)
 
     s = '''
 South Lawn
@@ -207,6 +207,7 @@ Amidst the aftermath of this shocking referendum vote, there is great uncertaint
 
 '''
 
+
     s = '''
 British Prime Minister Boris Johnson walks towards a voting station during the Brexit referendum in Britain, June 23, 2016. (Photo: EPA-EFE)
 
@@ -227,6 +228,7 @@ The prime minister was forced to ask for an extension to Britain's EU departure
 Johnson has repeatedly pledged to finalize the first stage, a transition deal, of Britain's EU divorce battle by Oct. 31. A second stage will involve negotiating its future relationship with the EU on trade, security and other salient issues.
 '''
 
+
     s = '''
 Thank you very much. We have a Cabinet meeting. We’ll have a few questions after grace. And, if you would, Ben, please do the honors.
 
@@ -241,11 +243,17 @@ We need — for our farmers, our manufacturers, for, frankly, unions and non-uni
 
 '''
 
-    # f = open('bbc-fulltext/bbc/entertainment/001.txt')
+
+
+
+    #f = open('bbc-fulltext/bbc/entertainment/001.txt')
     f = open('wordlist.txt')
     s = f.read()
     f.close()
 
+
+
+    
     print(text_difficulty_level(s, d3))
 
-
+            

app/static/config.yml

@@ -7,7 +7,6 @@ css:
 js:
   head: # 在页面加载之前加载
     - ../static/js/jquery.js
-    - ../static/js/read.js
     - ../static/js/word_operation.js
   bottom: # 在页面加载完之后加载
     - ../static/js/fillword.js

app/static/js/fillword.js

@@ -1,5 +1,9 @@
 let isRead = true;
 let isChoose = true;
+let reader = window.speechSynthesis; // 全局定义朗读者，以便朗读和暂停
+let current_position = 0; // 朗读文本的当前位置
+let original_position = 0; // 朗读文本的初始位置
+let to_speak = ""; // 朗读的初始内容
 
 function getWord() {
     return window.getSelection ? window.getSelection() : document.selection.createRange().text;
@@ -7,7 +11,7 @@ function getWord() {
 
 function fillInWord() {
     let word = getWord();
-    if (isRead) Reader.read(word, inputSlider.value);
+    if (isRead) read(word);
     if (!isChoose) return;
     const element = document.getElementById("selected-words");
     element.value = element.value + " " + word;
@@ -15,17 +19,50 @@ function fillInWord() {
 
 document.getElementById("text-content").addEventListener("click", fillInWord, false);
 
-const sliderValue = document.getElementById("rangeValue");
+function makeUtterance(str, rate) {
-const inputSlider = document.getElementById("rangeComponent");
+    let msg = new SpeechSynthesisUtterance(str);
+    msg.rate = rate;
+    msg.lang = "en-US"; // TODO: add language options menu
+    msg.onboundary = ev => {
+        if (ev.name == "word") {
+            current_position = ev.charIndex;
+        }
+    }
+    return msg;
+}
+
+const sliderValue = document.getElementById("rangeValue"); // 显示值
+const inputSlider = document.getElementById("rangeComponent"); // 滑块元素
 inputSlider.oninput = () => {
-    let value = inputSlider.value;
+    let value = inputSlider.value; // 获取滑块的值
     sliderValue.textContent = value + '×';
+    if (!reader.speaking) return;
+    reader.cancel();
+    let msg = makeUtterance(to_speak.substring(original_position + current_position), value);
+    original_position = original_position + current_position;
+    current_position = 0;
+    reader.speak(msg);
 };
 
+function read(s) {
+    to_speak = s.toString();
+    original_position = 0;
+    current_position = 0;
+    let msg = makeUtterance(to_speak, inputSlider.value);
+    reader.speak(msg);
+}
+
 function onReadClick() {
     isRead = !isRead;
+    if (!isRead) {
+        reader.cancel();
+    }
 }
 
 function onChooseClick() {
     isChoose = !isChoose;
 }
+
+function stopRead() {
+    reader.cancel();
+}

app/static/js/read.js

@@ -1,35 +0,0 @@
-var Reader = (function() {
-    let reader = window.speechSynthesis;
-    let current_position = 0;
-    let original_position = 0;
-    let to_speak = "";
-
-    function makeUtterance(str, rate) {
-        let msg = new SpeechSynthesisUtterance(str);
-        msg.rate = rate;
-        msg.lang = "en-US";
-        msg.onboundary = ev => {
-            if (ev.name == "word") {
-                current_position = ev.charIndex;
-            }
-        }
-        return msg;
-    }
-
-    function read(s, rate) {
-        to_speak = s.toString();
-        original_position = 0;
-        current_position = 0;
-        let msg = makeUtterance(to_speak, rate);
-        reader.speak(msg);
-    }
-
-    function stopRead() {
-        reader.cancel();
-    }
-
-    return {
-        read: read,
-        stopRead: stopRead
-    };
-})();

app/static/js/word_operation.js

@@ -62,13 +62,6 @@ function delete_word(theWord) {
     });
 }
 
-function read_word(theWord) {
-    let to_speak = $("#word_" + theWord).text();
-    original_position = 0;
-    current_position = 0;
-    Reader.read(to_speak, inputSlider.value);
-}
-
 /* 
  * interface Word {
  *   word: string,
@@ -102,7 +95,6 @@ function wordTemplate(word) {
         <a class="btn btn-success" onclick="familiar('${word.word}')" role="button">熟悉</a>
         <a class="btn btn-warning" onclick="unfamiliar('${word.word}')" role="button">不熟悉</a>
         <a class="btn btn-danger" onclick="delete_word('${word.word}')" role="button">删除</a>
-        <a class="btn btn-info" onclick="read_word('${word.word}')" role="button">朗读</a>
     </p>`;
 }
 

app/templates/userpage_get.html

@@ -5,8 +5,6 @@
     <meta name="viewport"
           content="width=device-width, initial-scale=1.0, minimum-scale=0.5, maximum-scale=3.0, user-scalable=yes"/>
     <meta name="format-detection" content="telephone=no"/>
-    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.1/dist/css/bootstrap.min.css" rel="stylesheet">
-    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.1/dist/js/bootstrap.bundle.min.js"></script>
 
     {{ yml['header'] | safe }}
     {% if yml['css']['item'] %}
@@ -28,40 +26,12 @@
         }
 
         @keyframes shakes {
-            10%, 90% {
+            10%, 90% { transform: translate3d(-1px, 0, 0); }
-                transform: translate3d(-1px, 0, 0);
+            20%, 50% { transform: translate3d(+2px, 0, 0); }
-            }
+            30%, 70% { transform: translate3d(-4px, 0, 0); }
-            20%, 50% {
+            40%, 60% { transform: translate3d(+4px, 0, 0); }
-                transform: translate3d(+2px, 0, 0);
+            50% { transform: translate3d(-4px, 0, 0); }
-            }
-            30%, 70% {
-                transform: translate3d(-4px, 0, 0);
-            }
-            40%, 60% {
-                transform: translate3d(+4px, 0, 0);
-            }
-            50% {
-                transform: translate3d(-4px, 0, 0);
-            }
         }
-
-        .lead {
-            font-size: 22px;
-            font-family: Helvetica, sans-serif;
-            white-space: pre-wrap;
-        }
-
-        .arrow {
-            padding: 0;
-            font-size: 20px;
-            line-height: 21px;
-            display: inline-block;
-        }
-
-        .arrow:hover {
-            cursor: pointer;
-        }
-
     </style>
 </head>
 <body>
@@ -69,70 +39,59 @@
     <p><b>English Pal for <font id="username" color="red">{{ username }}</font></b>
 
         {% if username ==  admin_name %}
-            <a class="btn btn-secondary" href="/admin" role="button" onclick="stopRead()">管理</a>
+        <a class="btn btn-secondary" href="/admin" role="button" onclick="stopRead()">管理</a>
         {% endif %}
         <a id="quit" class="btn btn-secondary" href="/logout" role="button" onclick="stopRead()">退出</a>
         <a class="btn btn-secondary" href="/reset" role="button" onclick="stopRead()">重设密码</a>
 
     </p>
-    {% for message in get_flashed_messages() %}
+{#    {% for message in flashed_messages %}#} {# 根据user_service.userpage,取消了参数flashed_messages，因此注释了这段代码 #}
-        <div class="alert alert-warning alert-dismissible fade show" role="alert">
+{#        <div class="alert alert-warning" role="alert">Congratulations! {{ message }}</div>#}
-            {{ message }}
+{#    {% endfor %}#}
-            <button type="button" class="btn-close" data-bs-dismiss="alert" aria-label="Close"></button>
-        </div>
-    {% endfor %}
 
-    <button class="arrow" id="load_next_article" onclick="load_next_article();Reader.stopRead()"
+    {% if result_of_generate_article != "had read all articles" %}
-            title="下一篇 Next Article">⇨
+        <a id="next_btn" class="btn btn-success" href="/{{ username }}/reset" role="button"> 下一篇 Next Article </a>
-    </button>
+    {% endif %}
-    <button class="arrow" id="load_pre_article" onclick="load_pre_article();Reader.stopRead()" style="display: none"
+    {% if session.get('visited_articles') and session.get('visited_articles')['index']>0 %}
-            title="上一篇 Previous Article">⇦
+        <a id="pre_btn" class="btn btn-success" href="/{{ username }}/back" role="button"> 上一篇 Previous Article </a>
-    </button>
+    {% endif %}
 
     <p><b>阅读文章并回答问题</b></p>
     <div id="text-content">
-        <div id="found">
+        {% if result_of_generate_article == 'found' %}
-            <div class="alert alert-success" role="alert">According to your word list, your level is <span
+            <div class="alert alert-success" role="alert">According to your word list, your level is <span class="badge bg-success">{{ today_article["user_level"] }}</span>  and we have chosen an article with a difficulty level of <span class="badge bg-success">{{ today_article["text_level"] }}</span> for you.</div>
-                    class="text-decoration-underline" id="user_level">{{ today_article["user_level"] }}</span> and we
+                <p class="text-muted">Article added on: {{ today_article["date"] }}</p><br/>
-                have chosen an article with a difficulty level of <span class="text-decoration-underline"
+            <div class="p-3 mb-2 bg-light text-dark"><br/>
-                                                                        id="text_level">{{ today_article["text_level"] }}</span>
+            <p class="display-5">{{ today_article["article_title"] }}</p><br/>
-                for you.
+            <p class="lead"><font id="article" size=2>{{ today_article["article_body"] }}</font></p><br/>
-            </div>
+            <p><small class="text-muted">{{ today_article['source'] }}</small></p><br/>
-            <p class="text-muted" id="date">Article added on: {{ today_article["date"] }}</p><br/>
+            <p><b>{{ today_article['question'] }}</b></p><br/>
-            <div class="p-3 mb-2 bg-light text-dark" style="margin: 0 0.5%;"><br/>
-                <p class="display-6" id="article_title">{{ today_article["article_title"] }}</p><br/>
-                <p class="lead"><font id="article">{{ today_article["article_body"] }}</font></p><br/>
-                <div>
-                    <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/#}
                         const e = document.getElementById(id);
-                        if (e.style.display === 'block')
+                        if(e.style.display === 'block')
                             e.style.display = 'none';
                         else
                             e.style.display = 'block';
                     }
                 </script>
                 <button onclick="toggle_visibility('answer');">ANSWER</button>
-                <div id="answer" style="display:none;">{{ today_article['answer'] }}</div>
+                <div id="answer" style="display:none;">{{ today_article['answer'] }}</div><br/>
-                <br/>
             </div>
-        </div>
+        {% elif result_of_generate_article == "not found" %}
-        <div class="alert alert-success" role="alert" id="not_found" style="display:none;">
+            <div class="alert alert-success" role="alert">
-            <p class="text-muted"><span class="badge bg-success">Notes:</span><br>No article is currently available for
+                <p class="text-muted"><span class="badge bg-success">Notes:</span><br>No article is currently available for you. You can try again a few times or mark new words in the passage to improve your level.</p>
-                you. You can try again a few times or mark new words in the passage to improve your level.</p>
+            </div>
-        </div>
+        {% elif result_of_generate_article == "had read all articles" %}
-        <div class="alert alert-success" role="alert" id="read_all" style="display:none;">
+            <div class="alert alert-success" role="alert">
-            <p class="text-muted"><span class="badge bg-success">Notes:</span><br>You've read all the articles.</p>
+                <p class="text-muted"><span class="badge bg-success">Notes:</span><br>You've read all the articles.</p>
-        </div>
+            </div>
+        {% endif %}
     </div>
 
-    <input type="checkbox" id="highlightCheckbox" onclick="toggleHighlighting()"/>生词高亮
+    <input type="checkbox" onclick="toggleHighlighting()" checked/>生词高亮
-    <input type="checkbox" id="readCheckbox" onclick="onReadClick()"/>大声朗读
+    <input type="checkbox" onclick="onReadClick()" checked/>大声朗读
-    <input type="checkbox" id="chooseCheckbox" onclick="onChooseClick()"/>划词入库
+    <input type="checkbox" onclick="onChooseClick()" checked/>划词入库
     <div class="range">
         <div class="field">
             <div class="sliderValue">
@@ -144,8 +103,8 @@
     <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/>
-        <button class="btn btn-primary btn-lg" type="submit" onclick="Reader.stopRead()">把生词加入我的生词库</button>
+        <input type="submit" value="把生词加入我的生词库"/>
-        <button class="btn btn-primary btn-lg" type="reset" onclick="clearSelectedWords()">清除</button>
+        <input type="reset" value="清除"/>
     </form>
     {% if session.get['thisWord'] %}
         <script type="text/javascript">
@@ -160,7 +119,7 @@
 
     {% if d_len > 0 %}
         <p>
-            <b>我的生词簿</b>
+            <b>我的生词簿</b> 
             <label for="move_dynamiclly">
                 <input type="checkbox" name="move_dynamiclly" id="move_dynamiclly" checked>
                 允许动态调整顺序
@@ -173,15 +132,13 @@
                 {% set freq = x[1] %}
                 {% if session.get('thisWord') == x[0] and session.get('time') == 1 %}
                 {% endif %}
-                <p id='p_{{ word }}' class="new-word">
+                <p id='p_{{ word }}' class="new-word" >
-                    <a id="word_{{ word }}" class="btn btn-light"
+                    <a id="word_{{ word }}"  class="btn btn-light" href='http://youdao.com/w/eng/{{ word }}/#keyfrom=dict2.index'
-                       href='http://youdao.com/w/eng/{{ word }}/#keyfrom=dict2.index'
+                    role="button">{{ word }}</a>
-                       role="button">{{ word }}</a>
                     ( <a id="freq_{{ word }}" title="{{ word }}">{{ freq }}</a> )
                     <a class="btn btn-success" onclick="familiar('{{ word }}')" role="button">熟悉</a>
                     <a class="btn btn-warning" onclick="unfamiliar('{{ word }}')" role="button">不熟悉</a>
                     <a class="btn btn-danger" onclick="delete_word('{{ word }}')" role="button">删除</a>
-                    <a class="btn btn-info" onclick="read_word('{{ word }}')" role="button">朗读</a>
                 </p>
             {% endfor %}
         </div>
@@ -194,134 +151,6 @@
         <script src="{{ js }}"></script>
     {% endfor %}
 {% endif %}
-<script type="text/javascript">
-    window.onload = function () { // 页面加载时执行
-        const settings = {
-            // initialize settings from localStorage
-            highlightChecked: localStorage.getItem('highlightChecked') !== 'false', // localStorage stores strings, default to true. same below
-            readChecked: localStorage.getItem('readChecked') !== 'false',
-            chooseChecked: localStorage.getItem('chooseChecked') !== 'false',
-            rangeValue: localStorage.getItem('rangeValue') || '1',
-            selectedWords: localStorage.getItem('selectedWords') || ''
-        };
-
-        const elements = {
-            highlightCheckbox: document.querySelector('#highlightCheckbox'),
-            readCheckbox: document.querySelector('#readCheckbox'),
-            chooseCheckbox: document.querySelector('#chooseCheckbox'),
-            rangeComponent: document.querySelector('#rangeComponent'),
-            rangeValueDisplay: document.querySelector('#rangeValue'),
-            selectedWordsInput: document.querySelector('#selected-words')
-        };
-        // 应用设置到页面元素
-        elements.highlightCheckbox.checked = settings.highlightChecked;
-        elements.readCheckbox.checked = settings.readChecked;
-        elements.chooseCheckbox.checked = settings.chooseChecked;
-        elements.rangeComponent.value = settings.rangeValue;
-        elements.rangeValueDisplay.textContent = `${settings.rangeValue}x`;
-        elements.selectedWordsInput.value = settings.selectedWords;
-
-        // 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')) {
-            $('#load_pre_article').show();
-        }
-
-        // 事件监听器
-        elements.selectedWordsInput.addEventListener('input', () => {
-            localStorage.setItem('selectedWords', elements.selectedWordsInput.value);
-        });
-
-        elements.rangeComponent.addEventListener('input', () => {
-            const rangeValue = elements.rangeComponent.value;
-            elements.rangeValueDisplay.textContent = `${rangeValue}x`;
-            localStorage.setItem('rangeValue', rangeValue);
-        });
-    };
-
-    function clearSelectedWords() {
-        localStorage.removeItem('selectedWords');
-        document.querySelector('#selected-words').value = '';
-    }
-
-
-    function load_next_article() {
-        $("#load_next_article").prop("disabled", true)
-        $.ajax({
-            url: '/get_next_article/{{username}}',
-            dataType: 'json',
-            success: function (data) {
-                // 更新页面内容
-                if (data['today_article']) {
-                    update(data['today_article']);
-                    check_pre(data['visited_articles']);
-                    check_next(data['result_of_generate_article']);
-                }
-            }, complete: function (xhr, status) {
-                $("#load_next_article").prop("disabled", false)
-            }
-        });
-    }
-
-    function load_pre_article() {
-        $.ajax({
-            url: '/get_pre_article/{{username}}',
-            dataType: 'json',
-            success: function (data) {
-                // 更新页面内容
-                if (data['today_article']) {
-                    update(data['today_article']);
-                    check_pre(data['visited_articles']);
-                }
-            }
-        });
-    }
-
-    function update(today_article) {
-        $('#user_level').html(today_article['user_level']);
-        $('#text_level').html(today_article["text_level"]);
-        $('#date').html('Article added on: ' + today_article["date"]);
-        $('#article_title').html(today_article["article_title"]);
-        $('#article').html(today_article["article_body"]);
-        $('#source').html(today_article['source']);
-        $('#question').html(today_article["question"]);
-        $('#answer').html(today_article["answer"]);
-        document.querySelector('#text_level').classList.add('mark'); // highlight text difficult level for 2 seconds
-        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);
-    }
-
-    <!-- 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)) {
-            $('#load_pre_article').hide();
-            sessionStorage.setItem('pre_page_button', 'display')
-        } else {
-            $('#load_pre_article').show();
-            sessionStorage.setItem('pre_page_button', 'show')
-        }
-    }
-
-    function check_next(result_of_generate_article) {
-        if (result_of_generate_article == "found") {
-            $('#found').show();
-            $('#not_found').hide();
-            $('#read_all').hide();
-        } else if (result_of_generate_article == "not found") {
-            $('#found').hide();
-            $('#not_found').show();
-            $('#read_all').hide();
-        } else {
-            $('#found').hide();
-            $('#not_found').hide();
-            $('#read_all').show();
-        }
-    }
-</script>
 </body>
 <style>
     mark {

app/test/test_next_article.py

@@ -1,85 +0,0 @@
-''' Contributed by Lin Junhong et al. 2023-06.'''
-
-from selenium import webdriver
-from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
-
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.common.exceptions import UnexpectedAlertPresentException, NoAlertPresentException
-import random, time
-import string
-
-# 初始化webdriver
-# driver = webdriver.Remote('http://localhost:4444/wd/hub', DesiredCapabilities.CHROME)
-# driver.implicitly_wait(10)
-driver = webdriver.Chrome("C:\\Users\\12993\AppData\Local\Programs\Python\Python38\\chromedriver.exe")
-
-
-def test_next_article():
-    try:
-        driver.get("http://118.25.96.118:90")
-        assert 'English Pal -' in driver.page_source
-        # login
-        elem = driver.find_element_by_link_text('登录')
-        elem.click()
-
-        uname = 'abcdefg'
-        password = 'abcdefg'
-        elem = driver.find_element_by_id('username')
-        elem.send_keys(uname)
-
-        elem = driver.find_element_by_id('password')
-        elem.send_keys(password)
-        elem = driver.find_element_by_xpath('/html/body/div/button')  # 找到登录按钮
-        elem.click()
-
-        time.sleep(0.5)
-        assert 'EnglishPal Study Room for ' + uname in driver.title
-        for i in range(50):
-            time.sleep(0.1)
-            # 找到固定按钮
-            elem = driver.find_element_by_xpath('//*[@id="load_next_article"]')
-            elem.click()
-    except Exception as e:
-        print(e)
-
-
-def test_local_next_article():
-    try:
-        driver.get("http://127.0.0.1:5000")
-        assert 'English Pal -' in driver.page_source
-        # login
-        elem = driver.find_element_by_link_text('注册')
-        elem.click()
-
-        uname = 'abcdefg'
-        password = 'abcdefg'
-        elem = driver.find_element_by_id('username')
-        elem.send_keys(uname)
-
-        elem = driver.find_element_by_id('password')
-        elem.send_keys(password)
-
-        elem = driver.find_element_by_id('password2')
-        elem.send_keys(password)
-
-        time.sleep(0.5)
-
-        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
-        elem.click()
-        time.sleep(0.5)
-        try:
-            WebDriverWait(driver, 1).until(EC.alert_is_present())
-            driver.switch_to.alert.accept()
-        except (UnexpectedAlertPresentException, NoAlertPresentException):
-            pass
-
-        time.sleep(0.5)
-        assert 'EnglishPal Study Room for ' + uname in driver.title
-        for i in range(50):
-            time.sleep(0.1)
-            # 找到固定按钮
-            elem = driver.find_element_by_xpath('//*[@id="load_next_article"]')
-            elem.click()
-    except Exception as e:
-        print(e)

app/user_service.py

@@ -21,10 +21,14 @@ userService = Blueprint("user_bp", __name__)
 path_prefix = '/var/www/wordfreq/wordfreq/'
 path_prefix = './'  # comment this line in deployment
 
-@userService.route("/get_next_article/<username>",methods=['GET','POST'])
+
-def get_next_article(username):
+@userService.route("/<username>/reset", methods=['GET', 'POST'])
-    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
+def user_reset(username):
-    session['old_articleID'] = session.get('articleID')
+    '''
+    用户界面
+    :param username: 用户名
+    :return: 返回页面内容
+    '''
     if request.method == 'GET':
         visited_articles = session.get("visited_articles")
         if visited_articles['article_ids'][-1] == "null":  # 如果当前还是“null”，则将“null”pop出来,无需index+=1
@@ -32,35 +36,26 @@ def get_next_article(username):
         else:  # 当前不为“null”，直接 index+=1
             visited_articles["index"] += 1
         session["visited_articles"] = visited_articles
-        visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
+        return redirect(url_for('user_bp.userpage', username=username))
-        data = {
-            'visited_articles': visited_articles,
-            'today_article': today_article,
-            'result_of_generate_article': result_of_generate_article
-        }
     else:
         return 'Under construction'
-    return json.dumps(data)
 
-@userService.route("/get_pre_article/<username>",methods=['GET'])
+@userService.route("/<username>/back", methods=['GET'])
-def get_pre_article(username):
+def user_back(username):
-    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
+    '''
+    用户界面
+    :param username: 用户名
+    :return: 返回页面内容
+    '''
     if request.method == 'GET':
         visited_articles = session.get("visited_articles")
-        if(visited_articles["index"]==0):
+        visited_articles["index"] -= 1  # 上一篇，index-=1
-            data=''
+        if visited_articles['article_ids'][-1] == "null":  # 如果当前还是“null”，则将“null”pop出来
-        else:
+            visited_articles['article_ids'].pop()
-            visited_articles["index"] -= 1  # 上一篇，index-=1
+        session["visited_articles"] = visited_articles
-            if visited_articles['article_ids'][-1] == "null":  # 如果当前还是“null”，则将“null”pop出来
+        return redirect(url_for('user_bp.userpage', username=username))
-                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'))
-            data = {
-                'visited_articles': visited_articles,
-                'today_article': today_article,
-                'result_of_generate_article':result_of_generate_article
-            }
-        return json.dumps(data)
 
 @userService.route("/<username>/<word>/unfamiliar", methods=['GET', 'POST'])
 def unfamiliar(username, word):
@@ -159,6 +154,10 @@ def userpage(username):
                                yml=Yaml.yml,
                                words=words)
 
+
+
+
+
 @userService.route("/<username>/mark", methods=['GET', 'POST'])
 def user_mark_word(username):
     '''

app/wordfreqCMD.py

@@ -39,7 +39,7 @@ def file2str(fname):#文件转字符
 
 
 def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
-    special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
+    special_characters = '\_©~<=>+-/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
     for c in special_characters:
         s = s.replace(c, ' ') # 防止出现把 apple,apple 移掉逗号后变成 appleapple 情况
     s = s.replace('--', ' ')

requirements.txt

@@ -1,8 +1,4 @@
-Flask==2.0.3
+Flask==1.1.2
 selenium==3.141.0
 PyYAML~=6.0
 pony==0.7.16
-snowballstemmer==2.2.0
-Werkzeug==2.2.2
-
-pytest~=8.1.1