app/WordFreq.py

@@ -2,24 +2,24 @@
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
-
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
 import string
 
+
 class WordFreq:
-    def __init__(self, s):
+    def __init__(self, s, max_word_length=30):
         self.s = remove_punctuation(s)
+        self.max_word_length = max_word_length
 
     def get_freq(self):
         lst = []
-        for t in freq(self.s):
+        for t in freq(self.s, self.max_word_length):
             word = t[0]
             if len(word) > 0 and word[0] in string.ascii_letters:
                 lst.append(t)
         return sort_in_descending_order(lst)
-    
+
 
 if __name__ == '__main__':
-    f = WordFreq('BANANA; Banana, apple ORANGE Banana banana.')
+    f = WordFreq('BANANA; Banana, apple ORANGE Banana banana.', max_word_length=30)
     print(f.get_freq())
-

app/templates/userpage_get.html

@@ -86,7 +86,7 @@
             <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/#}
@@ -109,22 +109,22 @@
         </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
+    <input type="checkbox" id="highlightCheckbox" onclick="toggleHighlighting()" />生词高亮
+    <input type="checkbox" id="readCheckbox" onclick="onReadClick()" />大声朗读
+    <input type="checkbox" id="chooseCheckbox" onclick="onChooseClick()" />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">清除</button>
+        <button class="btn btn-primary btn-lg" type="reset"  onclick="clearSelectedWords()">清除</button>
     </form>
     {% if session.get['thisWord'] %}
         <script type="text/javascript">
@@ -139,7 +139,7 @@
 
     {% 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
@@ -174,11 +174,54 @@
 {% 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}}',
@@ -248,7 +291,7 @@
 </body>
 <style>
     mark {
-        color: #{{ yml['highlight']['color'] }};
+        color: red;
         background-color: rgba(0, 0, 0, 0);
     }
 </style>

app/test/test_next_article.py

@@ -0,0 +1,85 @@
+''' 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/test_bug511_Bosh.py

@@ -0,0 +1,56 @@
+###########################################################################
+# Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
+# Written permission must be obtained from the author for commercial uses.
+###########################################################################
+import unittest
+from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
+from WordFreq import WordFreq
+
+
+class TestWordFrequency(unittest.TestCase):
+
+    def test_word_frequency_normal_case(self):
+        text = "BANANA; Banana, apple ORANGE Banana banana."
+        wf = WordFreq(text)
+        result = wf.get_freq()
+        expected = [('banana', 4), ('orange', 1), ('apple', 1)]
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_with_long_word(self):
+        text = "apple banana " + "a" * 31 + " orange banana apple"
+        wf = WordFreq(text, max_word_length=30)
+        result = wf.get_freq()
+        expected = [('banana', 2), ('apple', 2), ('orange', 1)]
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_all_long_words(self):
+        text = "a" * 31 + " " + "b" * 32 + " " + "c" * 33
+        wf = WordFreq(text, max_word_length=30)
+        result = wf.get_freq()
+        expected = []
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_with_punctuation(self):
+        text = "Hello, world! Hello... hello; 'hello' --world--"
+        wf = WordFreq(text)
+        result = wf.get_freq()
+        expected = [('hello', 4), ('world', 2)]
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_empty_string(self):
+        text = ""
+        wf = WordFreq(text)
+        result = wf.get_freq()
+        expected = []
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_with_max_length_parameter(self):
+        text = "apple banana apple"
+        wf = WordFreq(text, max_word_length=5)
+        result = wf.get_freq()
+        expected = [('apple', 2)]
+        self.assertEqual(result, expected)
+
+
+if __name__ == '__main__':
+    unittest.main()

app/wordfreqCMD.py

@@ -2,56 +2,56 @@
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
-
 import collections
 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。
+import os
+import sys
 import pickle_idea
 
-def freq(fruit):
+
+def freq(fruit, max_word_length=30):
     '''
     功能： 把字符串转成列表。 目的是得到每个单词的频率。
     输入： 字符串
     输出： 列表， 列表里包含一组元组，每个元组包含单词与单词的频率。 比如 [('apple', 2), ('banana', 1)]
-    注意事项： 首先要把字符串转成小写。原因是。。。
+    注意事项： 首先要把字符串转小写。
     '''
 
     result = []
-    
-    fruit = fruit.lower() # 字母转小写
+
+    fruit = fruit.lower()  # 字母转小写
     flst = fruit.split()  # 字符串转成list
     c = collections.Counter(flst)
-    result = c.most_common()
+    for word, count in c.most_common():
+        if len(word) <= max_word_length:
+            result.append((word, count))
     return result
 
-
-def youdao_link(s): # 有道链接
-    link = 'http://youdao.com/w/eng/' + s + '/#keyfrom=dict2.index'# 网址
+def youdao_link(s):  # 有道链接
+    link = 'http://youdao.com/w/eng/' + s + '/#keyfrom=dict2.index'  # 网址
     return link
 
 
-def file2str(fname):#文件转字符
-    f = open(fname) #打开
-    s = f.read()    #读取
-    f.close()       #关闭
+def file2str(fname):  # 文件转字符
+    with open(fname) as f:  # 使用with打开文件
+        s = f.read()  # 读取
     return s
 
 
-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 = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
+def remove_punctuation(s):  # 这里是s是形参(parameter)。函数被调用时才给s赋值。
+    special_characters = r'\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|'  # 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(c, ' ')  # 防止出现把 apple,apple 移掉逗号后变成 appleapple 情况
     s = s.replace('--', ' ')
-    s = s.strip() # 去除前后的空格
-    
+    s = s.strip()  # 去除前后的空格
+
     if '\'' in s:
         n = len(s)
-        t = '' # 用来收集我需要保留的字符
-        for i in range(n): # 只有单引号前后都有英文字符，才保留
+        t = ''  # 用来收集我需要保留的字符
+        for i in range(n):  # 只有单引号前后都有英文字符，才保留
             if s[i] == '\'':
                 i_is_ok = i - 1 >= 0 and i + 1 < n
-                if i_is_ok and s[i-1] in string.ascii_letters and s[i+1] in string.ascii_letters:
+                if i_is_ok and s[i - 1] in string.ascii_letters and s[i + 1] in string.ascii_letters:
                     t += s[i]
             else:
                 t += s[i]
@@ -60,12 +60,12 @@ def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用
         return s
 
 
-def sort_in_descending_order(lst):# 单词按频率降序排列
+def sort_in_descending_order(lst):  # 单词按频率降序排列
     lst2 = sorted(lst, reverse=True, key=lambda x: (x[1], x[0]))
     return lst2
 
 
-def sort_in_ascending_order(lst):# 单词按频率降序排列
+def sort_in_ascending_order(lst):  # 单词按频率降序排列
     lst2 = sorted(lst, reverse=False, key=lambda x: (x[1], x[0]))
     return lst2
 
@@ -80,31 +80,30 @@ def make_html_page(lst, fname):  # 只是在wordfreqCMD.py中的main函数中调
         # <a href="">word</a>
         s += '<p>%d <a href="%s">%s</a> (%d)</p>' % (count, youdao_link(x[0]), x[0], x[1])
         count += 1
-    f = open(fname, 'w')
-    f.write(s)
-    f.close()
+    with open(fname, 'w') as f:
+        f.write(s)
 
 
 ## main（程序入口）
 if __name__ == '__main__':
     num = len(sys.argv)
 
-    if num == 1: # 从键盘读入字符串
+    if num == 1:  # 从键盘读入字符串
         s = input()
-    elif num == 2: # 从文件读入字符串
+    elif num == 2:  # 从文件读入字符串
         fname = sys.argv[1]
         s = file2str(fname)
     else:
         print('I can accept at most 2 arguments.')
-        sys.exit()# 结束程序运行， 下面的代码不会被执行了。
+        sys.exit()  # 结束程序运行，下面的代码不会被执行了。
 
-    s = remove_punctuation(s) # 这里是s是实参(argument)，里面有值
+    s = remove_punctuation(s)  # 这里是s是实参(argument)，里面有值
     L = freq(s)
     for x in sort_in_descending_order(L):
-        print('%s\t%d\t%s' % (x[0], x[1], youdao_link(x[0])))#函数导出
+        print('%s\t%d\t%s' % (x[0], x[1], youdao_link(x[0])))  # 函数导出
 
     # 把频率的结果放result.html中
-    make_html_page(sort_in_descending_order(L), 'result.html') 
+    make_html_page(sort_in_descending_order(L), 'result.html')
 
     print('\nHistory:\n')
     if os.path.exists('frequency.p'):
@@ -120,4 +119,3 @@ if __name__ == '__main__':
     pickle_idea.save_frequency_to_pickle(d, 'frequency.p')
 
 
-

requirements.txt

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