Merge pull request 'WIP：Bug529-GuHan' (#88) from Bug529-GuHan into master

Reviewed-on: http://121.4.94.30:3000/mrlan/EnglishPal/pulls/88

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, text_difficulty_level, user_difficulty_level
+from difficulty import get_difficulty_level_for_user, 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(d1, d2)
+    d3 = get_difficulty_level_for_user(d1, d2)
 
     d = None
     result_of_generate_article = "not found"

app/difficulty.py

@@ -8,6 +8,7 @@
 import pickle
 import math
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
+import snowballstemmer
 
 
 def load_record(pickle_fname):
@@ -17,41 +18,51 @@ def load_record(pickle_fname):
     return d
 
 
-def difficulty_level_from_frequency(word, d):
-    level = 1
-    if not word in d:
-        return level
-    
-    if 'what' in d:
-        ratio = (d['what']+1)/(d[word]+1) # what is a frequent word
-        level = math.log( max(ratio, 1), 2)
+def convert_test_type_to_difficulty_level(d):
+    """
+    对原本的单词库中的单词进行难度评级
+    :param d: 存储了单词库pickle文件中的单词的字典
+    :return:
+    """
+    result = {}
+    L = list(d.keys())  # in d, we have test types (e.g., CET4,CET6,BBC) for each word
 
-    level = min(level, 8) 
-    return level
+    for k in L:
+        if 'CET4' in d[k]:
+            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(d1, d2):
-    d = {}
-    L = list(d1.keys())  # in d1, we have freuqence for each word
-    L2 = list(d2.keys()) # in d2, we have test types (e.g., CET4,CET6,BBC) for each word
-    L.extend(L2)
-    L3 = list(set(L)) # L3 contains all words
-    for k in L3:
-        if k in d2:
-            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)
+def get_difficulty_level_for_user(d1, d2):
+    """
+    d2 来自于词库的35511个已标记单词
+    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
+    """
+    # 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, ...}
+    stemmer = snowballstemmer.stemmer('english')
 
-    return d
+    for k in d1:  # 用户的词
+        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):
     '''
@@ -62,12 +73,13 @@ 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[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. 
+        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.
             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:
@@ -76,42 +88,44 @@ def revert_dict(d):
 
 
 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(), reverse=True): # most recently added words are more important while determining user's level
-        lst = d_user2[date] # a list of words
-        lst2 = [] # a list of tuples, (word, difficulty level)
-        for  word in lst:
+    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
+        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
-        #print(lst3)
+        lst3 = sort_in_ascending_order(lst2)  # easiest tuple first
+        # 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 in d:
+        if word not in stop_words and word in d:
             lst.append((word, d[word]))
 
-    lst2 = sort_in_descending_order(lst) # most difficult words on top
-    #print(lst2)
+    lst2 = sort_in_descending_order(lst)  # most difficult words on top
+    # print(lst2)
     count = 0
     geometric = 1
     for t in lst2:
@@ -119,24 +133,20 @@ def text_difficulty_level(s, d):
         hard = t[1]
         geometric = geometric * (hard)
         count += 1
-        if count >= 20: # we look for n most difficult words
-            return geometric**(1/count)
-        
-    return geometric**(1/max(count,1))
+        if count >= 20:  # we look for n most difficult words
+            return geometric ** (1 / count)
 
+    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(d1, d2)
+    d3 = get_difficulty_level_for_user(d1, d2)
 
     s = '''
 South Lawn
@@ -197,7 +207,6 @@ 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)
 
@@ -218,7 +227,6 @@ 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.
 
@@ -233,17 +241,11 @@ 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

@@ -7,6 +7,7 @@ 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

@@ -1,40 +1,31 @@
-var isRead = true;
-var isChoose = true;
-const reader = window.speechSynthesis; // 全局定义朗读者，以便朗读和暂停
-//获取字符
+let isRead = true;
+let isChoose = true;
+
 function getWord() {
-  return window.getSelection
-    ? window.getSelection()
-    : document.selection.createRange().text;
+    return window.getSelection ? window.getSelection() : document.selection.createRange().text;
 }
-//填充字符
-function fillingWord() {
-  let word = getWord();
-  if (isRead) read(word);
-  if (!isChoose) return;
-  let element = document.getElementById("selected-words");
-  element.value = element.value + " " + word;
+
+function fillInWord() {
+    let word = getWord();
+    if (isRead) Reader.read(word, inputSlider.value);
+    if (!isChoose) return;
+    const element = document.getElementById("selected-words");
+    element.value = element.value + " " + word;
 }
-document
-  .getElementById("text-content")
-  .addEventListener("click", fillingWord, false);
-//朗读单词
-//@word 要朗读的单词
-function read(word) {
-  //关闭当前正在读的单词
-  reader.cancel();
-  //创建新的朗读任务
-  let msg = new SpeechSynthesisUtterance(word);
-  reader.speak(msg);
-}
-//关闭正在读的单词
+
+document.getElementById("text-content").addEventListener("click", fillInWord, false);
+
+const sliderValue = document.getElementById("rangeValue");
+const inputSlider = document.getElementById("rangeComponent");
+inputSlider.oninput = () => {
+    let value = inputSlider.value;
+    sliderValue.textContent = value + '×';
+};
+
 function onReadClick() {
-  let isRead = !isRead;
-  if (!isRead) {
-    reader.cancel();
-  }
+    isRead = !isRead;
 }
-//取消当前选择
+
 function onChooseClick() {
-  isChoose = !isChoose;
+    isChoose = !isChoose;
 }

app/static/js/read.js

@@ -0,0 +1,35 @@
+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

@@ -62,6 +62,13 @@ function delete_word(theWord) {
     });
 }
 
+function read_word(theWord) {
+    let to_speak = $("#word_" + theWord).text();
+    original_position = 0;
+    current_position = 0;
+    Reader.read(to_speak, inputSlider.value);
+}
+
 /* 
  * interface Word {
  *   word: string,
@@ -95,6 +102,7 @@ function wordTemplate(word) {
         <a class="btn btn-success" onclick="familiar('${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

@@ -1,347 +1,218 @@
 <!DOCTYPE html>
 <html lang="en">
-  <head>
-    <meta charset="UTF-8" />
-    <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" />
+<head>
+    <meta charset="UTF-8">
+    <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"/>
 
-    {{ yml['header'] | safe }} {% if yml['css']['item'] %} {% for css in
-    yml['css']['item'] %}
-    <link href="{{ css }}" rel="stylesheet" />
-    {% endfor %} {% endif %} {% if yml['js']['head'] %} {% for js in
-    yml['js']['head'] %}
-    <script src="{{ js }}"></script>
-    {% endfor %} {% endif %}
+    {{ yml['header'] | safe }}
+    {% if yml['css']['item'] %}
+        {% for css in yml['css']['item'] %}
+            <link href="{{ css }}" rel="stylesheet">
+        {% endfor %}
+    {% endif %}
+    {% if yml['js']['head'] %}
+        {% for js in yml['js']['head'] %}
+            <script src="{{ js }}"></script>
+        {% endfor %}
+    {% endif %}
 
     <title>EnglishPal Study Room for {{ username }}</title>
 
     <style>
-      .shaking {
-        animation: shakes 1600ms ease-in-out;
-      }
+        .shaking {
+            animation: shakes 1600ms ease-in-out;
+        }
 
-      @keyframes shakes {
-        10%,
-        90% {
-          transform: translate3d(-1px, 0, 0);
+        @keyframes shakes {
+            10%, 90% { transform: translate3d(-1px, 0, 0); }
+            20%, 50% { transform: translate3d(+2px, 0, 0); }
+            30%, 70% { transform: translate3d(-4px, 0, 0); }
+            40%, 60% { transform: translate3d(+4px, 0, 0); }
+            50% { transform: translate3d(-4px, 0, 0); }
         }
-        20%,
-        50% {
-          transform: translate3d(+2px, 0, 0);
-        }
-        30%,
-        70% {
-          transform: translate3d(-4px, 0, 0);
-        }
-        40%,
-        60% {
-          transform: translate3d(+4px, 0, 0);
-        }
-        50% {
-          transform: translate3d(-4px, 0, 0);
-        }
-      }
     </style>
-  </head>
-  <body>
-    <div class="container-fluid">
-      <p>
-        <b
-          >English Pal for
-          <font id="username" color="red">{{ username }}</font></b
-        >
+</head>
+<body>
+<div class="container-fluid">
+    <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
-        >
+        {% if username ==  admin_name %}
+        <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 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" role="alert">
-        Congratulations! {{ message }}
-      </div>
-      #} {# {% endfor %}#}
+        <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>
 
-      <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>
+    </p>
+{#    {% 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" role="alert">Congratulations! {{ message }}</div>#}
+{#    {% endfor %}#}
 
-      <p><b>阅读文章并回答问题</b></p>
-      <div id="text-content">
+        <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>
+
+    <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 />
-            <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><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')
-                      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 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/>
+            <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><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')
+                            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><br/>
             </div>
-            <br />
-          </div>
         </div>
-        <div
-          class="alert alert-success"
-          role="alert"
-          id="not_found"
-          style="display: none"
-        >
-          <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>
+        <div class="alert alert-success" role="alert" id="not_found" style="display:none;">
+            <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>
         </div>
-        <div
-          class="alert alert-success"
-          role="alert"
-          id="read_all"
-          style="display: none"
-        >
-          <p class="text-muted">
-            <span class="badge bg-success">Notes:</span><br />You've read all
-            the articles.
-          </p>
+        <div class="alert alert-success" role="alert" id="read_all" style="display:none;">
+            <p class="text-muted"><span class="badge bg-success">Notes:</span><br>You've read all the articles.</p>
         </div>
-      </div>
-
-      <input type="checkbox" onclick="toggleHighlighting()" checked />生词高亮
-      <input type="checkbox" onclick="onReadClick()" checked />大声朗读
-      <input type="checkbox" onclick="onChooseClick()" checked />划词入库
-      <div class="range">
-        <div class="field">
-          <div class="sliderValue">
-            <span id="rangeValue">1×</span>
-          </div>
-          <input
-            type="range"
-            id="rangeComponent"
-            min="0.5"
-            max="2"
-            value="1"
-            step="0.25"
-          />
-        </div>
-      </div>
-      <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="reset" value="清除" />
-      </form>
-      {% if session.get['thisWord'] %}
-      <script type="text/javascript">
-        //point to the anchor in the page whose id is aaa if it exists
-        window.onload = function () {
-          var element = document.getElementsByName("aaa");
-          if (element != null)
-            document.getElementsByName("aaa")[0].scrollIntoView(true);
-        };
-      </script>
-      {% endif %} {% if d_len > 0 %}
-      <p>
-        <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
-        </label>
-      </p>
-      <a name="aaa"></a>
-      <div class="word-container">
-        {% for x in lst3 %} {% set word = x[0] %} {% set freq = x[1] %} {% if
-        session.get('thisWord') == x[0] and session.get('time') == 1 %} {% endif
-        %}
-        <p id="p_{{ word }}" class="new-word">
-          <a
-            id="word_{{ word }}"
-            class="btn btn-light"
-            href="http://youdao.com/w/eng/{{ word }}/#keyfrom=dict2.index"
-            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
-          >
-        </p>
-        {% endfor %}
-      </div>
-      <input id="selected-words2" type="hidden" value="{{ words }}" />
-      {% endif %}
     </div>
-    {{ yml['footer'] | safe }} {% if yml['js']['bottom'] %} {% for js in
-    yml['js']['bottom'] %}
-    <script src="{{ js }}"></script>
-    {% endfor %} {% endif %}
-    <script type="text/javascript">
-      function load_next_article() {
-        $.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"]);
+
+    <input type="checkbox" onclick="toggleHighlighting()" checked/>生词高亮
+    <input type="checkbox" onclick="onReadClick()" checked/>大声朗读
+    <input type="checkbox" onclick="onChooseClick()" checked/>划词入库
+    <div class="range">
+        <div class="field">
+            <div class="sliderValue">
+                <span id="rangeValue">1×</span>
+            </div>
+            <input type="range" id="rangeComponent" min="0.5" max="2" value="1" step="0.25"/>
+        </div>
+    </div>
+    <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="reset" value="清除"/>
+    </form>
+    {% if session.get['thisWord'] %}
+        <script type="text/javascript">
+            //point to the anchor in the page whose id is aaa if it exists
+            window.onload = function () {
+                var element = document.getElementsByName("aaa");
+                if (element != null)
+                    document.getElementsByName("aaa")[0].scrollIntoView(true);
             }
-          },
-        });
-      }
-      function load_pre_article() {
+        </script>
+    {% endif %}
+
+    {% if d_len > 0 %}
+        <p>
+            <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
+            </label>
+        </p>
+        <a name="aaa"></a>
+        <div class="word-container">
+            {% for x in lst3 %}
+                {% set word = x[0] %}
+                {% set freq = x[1] %}
+                {% if session.get('thisWord') == x[0] and session.get('time') == 1 %}
+                {% endif %}
+                <p id='p_{{ word }}' class="new-word" >
+                    <a id="word_{{ word }}"  class="btn btn-light" href='http://youdao.com/w/eng/{{ word }}/#keyfrom=dict2.index'
+                    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>
+        <input id="selected-words2" type="hidden" value="{{ words }}">
+    {% endif %}
+</div>
+{{ yml['footer'] | safe }}
+{% if yml['js']['bottom'] %}
+    {% for js in yml['js']['bottom'] %}
+        <script src="{{ js }}"></script>
+    {% endfor %}
+{% endif %}
+<script type="text/javascript">
+    function load_next_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"]);
+            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']);
+                }
             }
-          },
         });
-      }
-      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"]);
-      }
-      <!-- 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();
-        } else {
-          $("#load_pre_article").show();
+    }
+    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"]);
+    }
+<!-- 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();
+        }else{
+            $('#load_pre_article').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();
+    }
+    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>
+    }
+</script>
+</body>
+<style>
     mark {
         color: #{{ yml['highlight']['color'] }};
         background-color: rgba(0, 0, 0, 0);
     }
-  </style>
+</style>
+
 </html>

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

@@ -2,3 +2,4 @@ Flask==1.1.2
 selenium==3.141.0
 PyYAML~=6.0
 pony==0.7.16
+snowballstemmer==2.2.0