Fix Bug533

README.md

@@ -150,8 +150,6 @@ Run English Pal first, then run the test using pytest as follows: pytest --html=
 
 The above command will generate a HTML report file pytest_report.html after finishing executing test_add_word.py.  Note: you need to install pytest-html package first: pip install pytest-html.
 
-You may also want to use [webdriver-manager](https://pypi.org/project/webdriver-manager/) from PyPI, so that you can avoid tediously installing a web driver executable manually.  However, my experience shows that webdriver-manager is too slow.  For example, it took me 16 minutes to run 9 tests, while with the pre-installed web driver executable, it took less than 2 minutes.
-
 ## TODO
 
 

app/Article.py

@@ -1,4 +1,5 @@
 from WordFreq import WordFreq
+from app.UseSqlite import RecordQuery
 from wordfreqCMD import youdao_link, sort_in_descending_order
 import pickle_idea, pickle_idea2
 import os
@@ -14,6 +15,14 @@ path_prefix = './'
 db_path_prefix = './db/'  # comment this line in deployment
 
 
+def load_text_list_from_db(db_file):
+    rq = RecordQuery(db_file)
+    rq.instructions("SELECT text FROM article")
+    rq.do()
+    result = rq.get_results()
+    text_list = [row['text'] for row in result if 'text' in row]
+    return text_list
+
 def total_number_of_essays():
     return get_number_of_articles()
 

app/UseSqlite.py

@@ -0,0 +1,86 @@
+###########################################################################
+# Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
+# Written permission must be obtained from the author for commercial uses.
+###########################################################################
+
+
+# Reference: Dusty Phillips.  Python 3 Objected-oriented Programming Second Edition. Pages 326-328.
+# Copyright (C) 2019 Hui Lan
+
+import sqlite3
+
+class Sqlite3Template:
+    def __init__(self, db_fname):
+        self.db_fname = db_fname
+
+    def connect(self, db_fname):
+        self.conn = sqlite3.connect(self.db_fname)
+
+    def instructions(self, query_statement):
+        raise NotImplementedError()
+
+    def operate(self):
+        self.conn.row_factory = sqlite3.Row
+        self.results = self.conn.execute(self.query) # self.query is to be given in the child classes
+        self.conn.commit()
+
+    def format_results(self):
+        raise NotImplementedError()
+
+    def do(self):
+        self.connect(self.db_fname)
+        self.instructions(self.query)
+        self.operate()
+
+    def instructions_with_parameters(self, query_statement, parameters):
+        self.query = query_statement
+        self.parameters = parameters
+
+    def do_with_parameters(self):
+        self.connect(self.db_fname)
+        self.instructions_with_parameters(self.query, self.parameters)
+        self.operate_with_parameters()
+
+    def operate_with_parameters(self):
+        self.conn.row_factory = sqlite3.Row
+        self.results = self.conn.execute(self.query, self.parameters) # self.query is to be given in the child classes
+        self.conn.commit()
+
+
+class InsertQuery(Sqlite3Template):
+    def instructions(self, query):
+        self.query = query
+
+
+class RecordQuery(Sqlite3Template):
+    def instructions(self, query):
+        self.query = query
+
+    def format_results(self):
+        output = []
+        for row_dict in self.results.fetchall():
+            lst = []
+            for k in dict(row_dict):
+                lst.append( row_dict[k] )
+            output.append(', '.join(lst))
+        return '\n\n'.join(output)
+
+    def get_results(self):
+        result = []
+        for row_dict in self.results.fetchall():
+            result.append( dict(row_dict) )
+        return result
+
+
+
+if __name__ == '__main__':
+
+    #iq = InsertQuery('RiskDB.db')
+    #iq.instructions("INSERT INTO inspection Values ('FoodSupplies', 'RI2019051301', '2019-05-13', '{}')")
+    #iq.do()
+    #iq.instructions("INSERT INTO inspection Values ('CarSupplies', 'RI2019051302', '2019-05-13', '{[{\"risk_name\":\"elevator\"}]}')")
+    #iq.do()
+    rq = RecordQuery('wordfreqapp.db')
+    rq.instructions("SELECT * FROM article WHERE level=3")
+    rq.do()
+    #print(rq.format_results())

app/main.py

@@ -1,19 +1,23 @@
+#! /usr/bin/python3
+# -*- coding: utf-8 -*-
+import csv
+
 ###########################################################################
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
-from flask import abort
+from flask import escape
-from markupsafe import escape
 from Login import *
 from Article import *
 import Yaml
+from app.wordfreqCMD import sort_in_descending_order
 from user_service import userService
 from account_service import accountService
 from admin_service import adminService, ADMIN_NAME
-import os
+
 
 app = Flask(__name__)
-app.secret_key = os.urandom(32)
+app.secret_key = 'lunch.time!'
 
 # 将蓝图注册到Lab app
 app.register_blueprint(userService)
@@ -23,6 +27,17 @@ app.register_blueprint(adminService)
 path_prefix = '/var/www/wordfreq/wordfreq/'
 path_prefix = './'  # comment this line in deployment
 
+
+def load_word_list(csv_file):
+    with open(csv_file, 'r') as f:
+        reader = csv.reader(f)
+        return set(word.strip().lower() for row in reader for word in row[0].split(','))
+
+def calculate_coverage(text_list, word_set):
+    total_words = sum(len(article.split()) for article in text_list)
+    covered_words = sum(len(set(article.split()).intersection(word_set)) for article in text_list)
+    return (covered_words / total_words) * 10000 if total_words else 0
+
 def get_random_image(path):
     '''
     返回随机图
@@ -54,6 +69,7 @@ def appears_in_test(word, d):
     else:
         return ','.join(d[word])
 
+
 @app.route("/mark", methods=['GET', 'POST'])
 def mark_word():
     '''
@@ -79,6 +95,14 @@ def mainpage():
     根据GET或POST方法来返回不同的主界面
     :return: 主界面
     '''
+
+    db_file = "../db/wordfreqapp.db"
+    csv_file = "../db/The_Oxford.csv"
+    text_list = load_text_list_from_db(db_file)
+    word_set = load_word_list(csv_file)
+    coverage_percentage = "{:.2f}".format(calculate_coverage(text_list, word_set))
+
+
     if request.method == 'POST':  # when we submit a form
         content = escape(request.form['content'])
         f = WordFreq(content)
@@ -88,7 +112,7 @@ def mainpage():
         lst_history = pickle_idea.dict2lst(d)
         d = pickle_idea.merge_frequency(lst, lst_history)
         pickle_idea.save_frequency_to_pickle(d, path_prefix + 'static/frequency/frequency.p')
-        return render_template('mainpage_post.html', lst=lst, yml=Yaml.yml)
+        return render_template('mainpage_post.html', lst=lst, yml=Yaml.yml,coverage_percentage=coverage_percentage)
 
     elif request.method == 'GET':  # when we load a html page
         random_ads = get_random_ads()
@@ -102,8 +126,8 @@ def mainpage():
                                d_len=d_len,
                                lst=lst,
                                yml=Yaml.yml,
-                               number_of_essays=number_of_essays)
+                               number_of_essays=number_of_essays,
-
+                               coverage_percentage=coverage_percentage)
 
 if __name__ == '__main__':
     '''

app/static/config.yml

@@ -2,7 +2,7 @@
 css:
   item:
     - ../static/css/bootstrap.css
-    - ../static/css/highlighted.css
+
 # 全局引入的js文件地址
 js:
   head: # 在页面加载之前加载

app/static/css/highlighted.css

@@ -1,5 +0,0 @@
-
-.highlighted {
-    color: red;
-    font-weight: normal;
-}

app/static/js/fillword.js

@@ -1,5 +1,5 @@
-let isRead = localStorage.getItem('readChecked') !== 'false';  // default to true
+let isRead = true;
-let isChoose = localStorage.getItem('chooseChecked') !== 'false';
+let isChoose = true;
 
 function getWord() {
     return window.getSelection ? window.getSelection() : document.selection.createRange().text;
@@ -8,17 +8,9 @@ function getWord() {
 function fillInWord() {
     let word = getWord();
     if (isRead) Reader.read(word, inputSlider.value);
-    if (!isChoose) {
+    if (!isChoose) return;
-        if(isHighlight){
-             const element = document.getElementById("selected-words3");
-             element.value = element.value + " " + word;
-        }
-        return;
-    }
     const element = document.getElementById("selected-words");
-    localStorage.setItem('nowWords', element.value);
     element.value = element.value + " " + word;
-    localStorage.setItem('selectedWords', element.value);
 }
 
 document.getElementById("text-content").addEventListener("click", fillInWord, false);
@@ -32,16 +24,13 @@ inputSlider.oninput = () => {
 
 function onReadClick() {
     isRead = !isRead;
-    localStorage.setItem('readChecked', isRead);
 }
 
 function onChooseClick() {
     isChoose = !isChoose;
-    localStorage.setItem('chooseChecked', 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

@@ -1,4 +1,4 @@
-let isHighlight = localStorage.getItem('highlightChecked') !== 'false'; // default to true
+let isHighlight = true;
 
 function cancelBtnHandler() {
     cancelHighlighting();
@@ -22,48 +22,38 @@ function getWord() {
 
 function highLight() {
     if (!isHighlight) return;
-    let word = (getWord() + "").trim();
     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 = dictionaryWords === null ? pickedWords.value + " " : pickedWords.value + " " + dictionaryWords.value;
-    highlightWords = document.getElementById("selected-words3");
-    allWords = highlightWords == null ? allWords : allWords + " " + highlightWords.value;
     const list = allWords.split(" "); // 将所有的生词放入一个list中
-    if(word !== null && word !== "" && word !== " "){
-        let articleContent_fb2 = articleContent;
-        if(localStorage.getItem("nowWords").indexOf(word) !== -1 || localStorage.getItem("nowWords").indexOf(word.toLowerCase()) !== -1){
-            articleContent = articleContent.replace(new RegExp('<span class="highlighted">' + word + '</span>', "gi"), word);
-            pickedWords.value = localStorage.getItem("nowWords").replace(word,"");
-            document.getElementById("article").innerHTML = articleContent;
-            return;
-        }
-    }
     let totalSet = new Set();
     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('|', "");
-        list[i] = list[i].replace('?', "");
         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"<span class='highlighted'>"标签,防止标签发生嵌套
+    // 删除所有的mark标签,防止标签发生嵌套
-    articleContent = articleContent.replace(new RegExp('<span class="highlighted">',"gi"), "")
+    articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
-    articleContent = articleContent.replace(new RegExp("</span>","gi"), "");
+    articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
-    // 将文章中所有出现该单词word的地方改为："<span class='highlighted'>" + word + "</span>"。
+    // 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"), "<span class='highlighted'>" + word + "</span>");
+        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;
-    articleContent = articleContent.replace(new RegExp('<span class="highlighted">',"gi"), "")
+    articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
-    articleContent = articleContent.replace(new RegExp("</span>","gi"), "");
+    articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
     document.getElementById("article").innerHTML = articleContent;
 }
 
@@ -83,7 +73,6 @@ function toggleHighlighting() {
         isHighlight = true;
         highLight();
     }
-     localStorage.setItem('highlightChecked', isHighlight);
 }
 
 showBtnHandler();

app/templates/login.html

@@ -15,10 +15,6 @@
             alert('输入不能为空!');
             return false;
         }
-        if (password.includes(' ')) {
-            alert('输入不能包含空格!');
-            return false;
-        }
         $.post(
             "/login", {'username': username, 'password': password},
             function (response) {

app/templates/mainpage_get.html

@@ -3,7 +3,6 @@
 <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" />
-
     {{ yml['header'] | safe }}
     {% if yml['css']['item'] %}
         {% for css in yml['css']['item'] %}
@@ -31,12 +30,13 @@
             <p><a href="/login">登录</a>  <a href="/signup">注册</a> <a href="/static/usr/instructions.html">使用说明</a></p >
             <p><b> {{ random_ads }}。 <a href="/signup">试试</a>吧！</b></p>
         {% endif %}
-        <div class="alert alert-success" role="alert">共有文章 <span class="badge bg-success"> {{ number_of_essays }} </span> 篇</div>
+
-        <p>粘贴1篇文章 (English only)</p>
+        <div class="alert alert-success" role="alert">共有文章 <span class="badge bg-success"> {{ number_of_essays }} </span> 篇 &nbsp;&nbsp;&nbsp;&nbsp;其中Oxford覆盖率为: <span class="badge bg-success"> {{ coverage_percentage }}% </span></div>
+        <p>粘贴1篇文章 (<E></E>nglish only)</p>
         <form method="post" action="/">
-            <textarea name="content" id="article" rows="10" cols="120"></textarea><br/>
+            <textarea name="content" rows="10" cols="120"></textarea><br/>
             <input type="submit" value="get文章中的词频"/>
-            <input type="reset" value="清除" onclick="clearArticle()"/>
+            <input type="reset" value="清除"/>
         </form>
         {% if d_len > 0 %}
             <p><b>最常见的词</b></p>
@@ -44,7 +44,6 @@
                 <a href="http://youdao.com/w/eng/{{x[0]}}/#keyfrom=dict2.index">{{x[0]}}</a> {{x[1]}}
             {% endfor %}
         {% endif %}
-        <p class="text-muted">Version: 20230810</p>
         <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/js/bootstrap.bundle.min.js" integrity="sha384-MrcW6ZMFYlzcLA8Nl+NtUVF0sA7MsXsP1UyJoMp4YLEuNSfAP+JcXn/tWtIaxVXM" crossorigin="anonymous"></script>
     </div>
     {{ yml['footer'] | safe }}
@@ -53,22 +52,5 @@
             <script src="{{ js }}" ></script>
         {% endfor %}
     {% endif %}
-<script type="text/javascript">
-    // IIFE, avoid polluting the global scope
-    (function() {
-        const articleInput = document.querySelector('#article');
-        articleInput.value = localStorage.getItem('article') || '';
-
-        articleInput.addEventListener('input', function() {
-            localStorage.setItem('article', articleInput.value);
-        });
-
-        window.clearArticle = function() {
-            localStorage.removeItem('article');
-            articleInput.value = '';
-        };
-    })();
-
-</script>
 </body>
 </html>

app/templates/mainpage_post.html

@@ -2,7 +2,7 @@
 <html lang="en">
 <head>
     <meta charset="UTF-8">
-    <title>单词词频</title>
+    <title>Title</title>
 
     {{ yml['header'] | safe }}
     {% if yml['css']['item'] %}

app/templates/reset.html

@@ -12,10 +12,6 @@
                 alert('输入不能为空!');
                 return false;
             }
-            if (old_password.includes(' ') || new_password.includes(' ')) {
-                alert('输入不能包含空格!');
-                return false;
-            }
             if (new_password !== re_new_password) {
                 alert('新密码不匹配，请重新输入');
                 return false;

app/templates/signup.html

@@ -16,10 +16,6 @@ You're logged in already! <a href="/logout">Logout</a>.
                 alert('输入不能为空!');
                 return false;
             }
-            if (password.includes(' ') || password2.includes(' ')) {
-                alert('输入不能包含空格!');
-                return false;
-            }
             if (password !== password2) {
                 alert('确认密码与输入密码不一致！');
                 return false;

app/templates/userpage_get.html

@@ -109,22 +109,22 @@
         </div>
     </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">
                 <span id="rangeValue">1×</span>
             </div>
-            <input type="range" id="rangeComponent" min="0.5" max="2" value="1" step="0.25" />
+            <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/>
         <button class="btn btn-primary btn-lg" type="submit" onclick="Reader.stopRead()">把生词加入我的生词库</button>
-        <button class="btn btn-primary btn-lg" type="reset"  onclick="clearSelectedWords()">清除</button>
+        <button class="btn btn-primary btn-lg" type="reset">清除</button>
     </form>
     {% if session.get['thisWord'] %}
         <script type="text/javascript">
@@ -166,7 +166,6 @@
         <input id="selected-words2" type="hidden" value="{{ words }}">
     {% endif %}
 </div>
-<label id="selected-words3" type="hidden"></label>
 {{ yml['footer'] | safe }}
 {% if yml['js']['bottom'] %}
     {% for js in yml['js']['bottom'] %}
@@ -175,54 +174,11 @@
 {% 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')) {
+        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(){
         $.ajax({
             url: '/get_next_article/{{username}}',
@@ -292,7 +248,7 @@
 </body>
 <style>
     mark {
-        color: red;
+        color: #{{ yml['highlight']['color'] }};
         background-color: rgba(0, 0, 0, 0);
     }
 </style>

app/templates/userpage_post.html

@@ -1,50 +1,50 @@
 <!DOCTYPE html>
 <html lang="en">
     <head>
-       <meta charset="UTF-8">
+	<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="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" />
+	<meta name="format-detection" content="telephone=no" />
 
-       {{ yml['header'] | safe }}
+	{{ yml['header'] | safe }}
-       {% if yml['css']['item'] %}
+	{% if yml['css']['item'] %}
-         {% for css in yml['css']['item'] %}
+        {% for css in yml['css']['item'] %}
-         <link href="{{ css }}" rel="stylesheet">
+        <link href="{{ css }}" rel="stylesheet">
-         {% endfor %}
+        {% endfor %}
-        {% endif %}
+	{% endif %}
-        {% if yml['js']['head'] %}
+	{% if yml['js']['head'] %}
-         {% for js in yml['js']['head'] %}
+        {% for js in yml['js']['head'] %}
-         <script src="{{ js }}" ></script>
+        <script src="{{ js }}" ></script>
-         {% endfor %}
+        {% endfor %}
-        {% endif %}
+	{% endif %}
 
-       <title>EnglishPal Study Room for {{username}}</title>
+	<title>EnglishPal Study Room for {{username}}</title>
     </head>
     <body>
-      <div class="container-fluid">
+	<div class="container-fluid">
-          <p class="mt-md-3">
+	    <p class="mt-md-3">
-               <input type="button" id="btn-cancel-selection" value="取消勾选" onclick="toggleCheckboxSelection(false)" />
+		<input type="button" id="btn-cancel-selection" value="取消勾选" onclick="toggleCheckboxSelection(false)" />
-               <input type="button" id="btn-selection" value="全部勾选" onclick="toggleCheckboxSelection(true)" />
+		<input type="button" id="btn-selection" value="全部勾选" onclick="toggleCheckboxSelection(true)" />
-          </p>
+	    </p>
-          <form method="post" action="/{{username}}/mark">
+	    <form method="post" action="/{{username}}/mark">
-              <button type="submit" name="add-btn" class="btn btn-outline-primary btn-lg" onclick="clearSelectedWords()">加入我的生词簿</button>
+		<button type="submit" name="add-btn" class="btn btn-outline-primary btn-lg">加入我的生词簿</button>
-              {% for x in lst %}
+		{% for x in lst %}
-              {% set word = x[0]%}
+		{% set word = x[0]%}
-              <p>
+		<p>
-                    <font color="grey">{{loop.index}}</font>
+		    <font color="grey">{{loop.index}}</font>
-                    :
+		    :
-                    <a href='http://youdao.com/w/eng/{{word}}/#keyfrom=dict2.index' title={{word}}>{{word}}</a>
+		    <a href='http://youdao.com/w/eng/{{word}}/#keyfrom=dict2.index' title={{word}}>{{word}}</a>
-                    ({{x[1]}})
+		    ({{x[1]}})
-                    <input type="checkbox" name="marked" value="{{word}}" checked>
+		    <input type="checkbox" name="marked" value="{{word}}" checked>
-              </p>
+		</p>
 
-               {% endfor %}
+		{% endfor %}
-           </form>
+	    </form>
-           {{ yml['footer'] | safe }}
+	    {{ yml['footer'] | safe }}
-           {% if yml['js']['bottom'] %}
+	    {% if yml['js']['bottom'] %}
             {% for js in yml['js']['bottom'] %}
-             <script src="{{ js }}" ></script>
+            <script src="{{ js }}" ></script>
             {% endfor %}
-        {% endif %}
+	    {% endif %}
-      </div>
+	</div>
     </body>
 </html>

app/test/conftest.py

@@ -2,7 +2,6 @@ import pytest
 import sqlite3
 import time
 from selenium import webdriver
-
 from pathlib import Path
 
 @pytest.fixture
@@ -12,7 +11,7 @@ def URL():
 
 @pytest.fixture
 def driver():
-    return webdriver.Edge()  # follow the "End-to-end testing" section in README.md to install the web driver executable
+    return webdriver.Edge()  # uncomment this line if you wish to run the test on your laptop
 
 
 @pytest.fixture

app/test/test_bug528_tangjiao.py

@@ -1,95 +0,0 @@
-import pytest
-from selenium import webdriver
-from selenium.webdriver.common.by import By
-from selenium.webdriver.common.keys import Keys
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.common.exceptions import NoSuchElementException, TimeoutException
-
-
-# 测试登录页面输入密码包含空格的情况
-def test_login_password_with_space(driver, URL):
-    try:
-        driver.get(URL+"/login")
-
-        # 输入用户名
-        username_elem = driver.find_element_by_id('username')
-        username_elem.send_keys("test_user")
-
-        # 输入包含空格的密码
-        password_elem = driver.find_element_by_id('password')
-        password_elem.send_keys("password with space")
-
-        # 提交登录表单
-        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
-        elem.click()
-
-        # 显式等待直到警告框出现
-        WebDriverWait(driver, 10).until(EC.alert_is_present())
-
-        # 检查是否弹出警告框
-        alert = driver.switch_to.alert
-        assert "输入不能包含空格!" in alert.text
-    except (NoSuchElementException, TimeoutException) as e:
-        pytest.fail("页面元素未找到或超时: {}".format(e))
-
-
-# 测试注册页面输入密码包含空格的情况
-
-def test_signup_password_with_space(driver, URL):
-    try:
-        driver.get(URL+"/signup")
-
-        # 输入用户名
-        username_elem = driver.find_element_by_id('username')
-        username_elem.send_keys("new_user")
-
-        # 输入包含空格的密码
-        password_elem = driver.find_element_by_id('password')
-        password_elem.send_keys("password with space")
-
-        # 再次输入密码
-        password2_elem = driver.find_element_by_id('password2')
-        password2_elem.send_keys("password with space")
-
-        # 提交注册表单
-        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
-        elem.click()
-
-        # 显式等待直到警告框出现
-        WebDriverWait(driver, 10).until(EC.alert_is_present())
-
-        # 检查是否弹出警告框
-        alert = driver.switch_to.alert
-        assert "输入不能包含空格!" in alert.text
-    except (NoSuchElementException, TimeoutException) as e:
-        pytest.fail("页面元素未找到或超时: {}".format(e))
-
-
-
-# 测试重设密码页面输入新密码包含空格的情况
-
-def test_reset_password_with_space(driver, URL):
-    try:
-        driver.get(URL+"/reset")
-
-        # 输入用户名
-        username_elem = driver.find_element_by_id('username')
-        username_elem.send_keys("test_user")
-
-        # 输入包含空格的密码
-        password_elem = driver.find_element_by_id('password')
-        password_elem.send_keys("password with space")
-
-        # 提交重设密码表单
-        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
-        elem.click()
-
-        # 显式等待直到警告框出现
-        WebDriverWait(driver, 10).until(EC.alert_is_present())
-
-        # 检查是否弹出警告框
-        alert = driver.switch_to.alert
-        assert "输入不能包含空格!" in alert.text
-    except (NoSuchElementException, TimeoutException) as e:
-        pytest.fail("页面元素未找到或超时: {}".format(e))

app/test/test_bug544_tangxinyuan.py

@@ -1,55 +0,0 @@
-import random
-import string
-import time
-
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
-
-from helper import signup
-
-
-def has_punctuation(s):
-    return any(c in string.punctuation for c in s)
-
-
-def login(driver, home, uname, password):
-    driver.get(home)
-    WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.LINK_TEXT, '登录'))).click()
-    driver.find_element(By.ID, 'username').send_keys(uname)
-    driver.find_element(By.ID, 'password').send_keys(password)
-    driver.find_element(By.XPATH, '//button[text()="登录"]').click()
-    WebDriverWait(driver, 10).until(EC.title_is(f"EnglishPal Study Room for {uname}"))
-
-
-def select_valid_word(driver):
-    elem = driver.find_element(By.ID, 'text-content')
-    essay_content = elem.text
-    valid_word = random.choice([word for word in essay_content.split() if len(word) >= 6 and not has_punctuation(
-        word) and 'font>' not in word and 'br>' not in word and 'p>' not in word])
-    driver.find_element(By.ID, 'selected-words').send_keys(valid_word)
-    return valid_word
-
-
-def test_save_selected_word(driver, URL):
-    try:
-        username, password = signup(URL, driver)
-        word = select_valid_word(driver)
-        stored_words = driver.execute_script('return localStorage.getItem("selectedWords");')
-        assert word == stored_words, "Selected word not saved to localStorage correctly"
-        # 退出并重新登录以检查存储的单词
-        driver.find_element(By.LINK_TEXT, '退出').click()
-        driver.execute_script("window.open('');window.close();")
-
-        # 等待一会儿，让浏览器有足够的时间关闭标签页
-        WebDriverWait(driver, 2)
-
-        # 重新打开一个新的标签页
-        driver.execute_script("window.open('');")
-        driver.switch_to.window(driver.window_handles[-1])  # 切换到新打开的标签页
-
-        login(driver, URL, username, password)
-        textarea_content = driver.find_element(By.ID, 'selected-words').get_attribute('value')
-        assert word == textarea_content, "Selected word not preserved after re-login"
-    finally:
-        driver.quit()

app/test/test_bug545_HuangHuiLing.py

@@ -1,44 +0,0 @@
-import random
-import string
-import time
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.webdriver.common.action_chains import ActionChains
-
-from helper import signup
-
-def has_punctuation(s):
-    return any(c in string.punctuation for c in s)
-
-def select_one(driver):
-    elem = driver.find_element(By.ID, 'article')
-    essay_content = elem.text
-    valid_word = random.choice([word for word in essay_content.split() if len(word) >= 6 and not has_punctuation(
-        word) and 'font>' not in word and 'br>' not in word and 'p>' not in word])
-    driver.find_element(By.ID, 'selected-words').send_keys(valid_word)
-    driver.find_element(By.ID, 'article').click()
-    return valid_word
-
-def select_two(driver):
-    word = driver.find_element(By.CLASS_NAME, 'highlighted')
-
-    # 创建ActionChains对象
-    actions = ActionChains(driver)
-    actions.move_to_element(word)
-
-    # 模拟鼠标按下并拖动以选择文本
-    actions.double_click()
-    actions.perform()
-
-
-def test_selected_second_word(driver, URL):
-    try:
-        signup(URL, driver)
-        selected_words = select_one(driver);
-        assert selected_words.strip() != "", "选中的单词被放置框中"
-        select_two(driver)
-        selected_second_words = driver.find_element(By.ID, 'selected-words').get_attribute('value')
-        assert selected_second_words.strip() == "", "选中的单词被删除"
-    finally:
-        driver.quit()

app/test/test_bug546_lixiaofeng.py

@@ -1,39 +0,0 @@
-from selenium.webdriver.common.action_chains import ActionChains
-from helper import signup
-
-
-def test_highlight(driver, URL):
-    try:
-        # 打开网页
-        driver.get(URL)
-        driver.maximize_window()
-
-        # 注册
-        signup(URL, driver)
-
-        # 取消勾选“划词入库按钮”
-        highlight_checkbox = driver.find_element_by_id("chooseCheckbox")
-        driver.execute_script("arguments[0].click();", highlight_checkbox)
-
-        article = driver.find_element_by_id("article")
-
-        # 创建 ActionChains 对象
-        actions = ActionChains(driver)
-
-        # 移动鼠标到起点位置
-        actions.move_to_element(article)
-        # actions.move_to_element_with_offset(article, 50, 100)
-        # 按下鼠标左键
-        actions.click_and_hold()
-        # 拖动鼠标到结束位置
-        actions.move_by_offset(400,50)
-        # 释放鼠标左键
-        actions.release()
-        # 执行操作链
-        actions.perform()
-        # time.sleep(10)
-
-        assert driver.find_elements_by_class_name("highlighted") is not None
-    finally:
-        # 测试结束后关闭浏览器
-        driver.quit()

app/test/test_bug551_DingZeYu.py

@@ -1,37 +0,0 @@
-import time
-import pytest
-from selenium import webdriver
-from selenium.webdriver import ActionChains
-from selenium.webdriver.common.by import By
-from selenium.webdriver.common.alert import Alert
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.webdriver.support.wait import WebDriverWait
-from helper import signup
-
-def test_bug551(driver, URL):
-    driver.maximize_window()
-    driver.get(URL)
-
-    username, password = signup(URL, driver)
-
-    article = driver.find_element(By.ID, 'article')
-    actions = ActionChains(driver)
-
-    actions.move_to_element(article)
-    actions.click_and_hold()
-    actions.move_by_offset(450, 200)
-    actions.release()
-    actions.perform()
-
-    # 获取选中高亮部分的单词的元素
-    highlighted_words = driver.find_elements(By.CLASS_NAME, 'highlighted')
-
-    # 验证选中部分的单词是否同时应用了需求样式
-    expected_font_weight = "400"  
-
-    for word in highlighted_words:
-        font_weight = word.value_of_css_property("font-weight")
-        assert font_weight == expected_font_weight, f"选中部分的单词的字体样式错误"
-
-    time.sleep(5)
-    driver.quit()

app/test/test_bug553_LinShan.py

@@ -1,58 +0,0 @@
-from selenium import webdriver
-from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
-from selenium.webdriver.support import expected_conditions as EC
-from selenium import webdriver
-from selenium.webdriver.support.wait import WebDriverWait
-from selenium.webdriver.common.by import By
-from selenium.webdriver.common.keys import Keys
-import logging
-import time
-import pytest
-
-@pytest.mark.parametrize("test_input,expected",
-                         [("‘test1’", "test1"),
-                          ("'test2'", "test2"),
-                          ("“test3”", "test3"),
-                          ("it's", "it's"),
-                          ("hello,I'm linshan", ["hello","i'm","linshan"]),
-                          ("Happy New Year！？", ["happy","new","year"]),
-                          ("My favorite book is 《Harry Potter》。", ["potter","harry","my","favorite","book","is"])])
-def test_bug553_LinShan(test_input,expected, driver, URL):
-    try:
-        # 打开对应地址的网页
-        driver.get(URL)
-
-        # 浏览器最大窗口化
-        driver.maximize_window()
-
-        # 判断网页源代码中是否有English Pal -文字
-        assert 'English Pal -' in driver.page_source
-
-        # 将测试的数据输入到主页的textarea里
-        driver.find_element_by_xpath("//textarea[@name='content']").send_keys(Keys.CONTROL, "a")
-        driver.find_element_by_xpath("//textarea[@name='content']").send_keys(test_input)
-        time.sleep(1)
-
-        # 点击按钮获取单词
-        driver.find_element_by_xpath("//input[@value='get文章中的词频']").click()
-        time.sleep(1)
-
-        # 获取筛选后的单词
-        words = driver.find_elements_by_xpath("//p/a")
-
-        # 遍历获取到的单词，并判断单词与预期的相同
-        for word in words:
-            # 判断单词是否在预期结果中
-            assert word.text in expected
-            
-        # 返回上一页网页
-        driver.find_element_by_xpath("//input[@value='确定并返回']").click()
-        time.sleep(0.1)
-
-    except Exception as e:
-        # 输出异常信息
-        logging.error(e)
-        # 关闭浏览器
-        driver.quit()
-    finally:
-        driver.quit()

app/test/test_coverage_percentage.py

@@ -0,0 +1,23 @@
+
+from app.Article import load_text_list_from_db
+from app.main import load_word_list, calculate_coverage
+
+
+def test_coverage_percentage():
+    try:
+        db_file = 'static/wordfreqapp.db'
+        csv_file = 'static/The_Oxford.csv'
+        text_list = load_text_list_from_db(db_file)
+        word_set = load_word_list(csv_file)
+        coverage_percentage = "{:.2f}".format(calculate_coverage(text_list, word_set))
+        print("coverage_percentage:", coverage_percentage);
+    except Exception as e:
+        print(e)
+
+if __name__ == '__main__':
+    test_coverage_percentage();
+
+
+
+
+

app/user_service.py

@@ -47,6 +47,8 @@ def get_next_article(username):
         return 'Under construction'
     return json.dumps(data)
 
+
+
 @userService.route("/get_pre_article/<username>",methods=['GET'])
 def get_pre_article(username):
     user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)

app/wordfreqCMD.py

@@ -4,7 +4,6 @@
 ###########################################################################
 
 import collections
-import html
 import string
 import operator
 import os, sys # 引入模块sys，因为我要用里面的sys.argv列表中的信息来读取命令行参数。
@@ -40,8 +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
-    s = html.unescape(s) # 将HTML实体转换为对应的字符，比如<会被识别为小于号
     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

@@ -4,5 +4,3 @@ PyYAML~=6.0
 pony==0.7.16
 snowballstemmer==2.2.0
 Werkzeug==2.2.2
-
-pytest~=8.1.1