Fix Bug 511

The key change is replacing "d1 = load_freq_history(path_prefix + 'static/frequency/ferquency.p)" with "d1 = load_freq_history(user_word_list)"
in function get_today_article() from Article.py.  Now, with a user_word_list of size about 500, the next article can be loaded within 100ms.
The new d1 is much smaller than the old one, therefore the following computation "d3 = get_difficulty_level_for_user(d1, d2)" is much faster.
The students did not feel that loading next article is slow; this is because their frequency.p is quite small.

Also log information in app/log.txt

.gitignore

@@ -2,12 +2,16 @@
 venv/
 app/__init__.py
 app/__pycache__/
+.DS_Store
+app/.DS_Store
 app/sqlite_commands.py
 app/static/usr/*.jpg
 app/static/img/
 app/static/frequency/frequency_*.pickle
 app/static/frequency/frequency.p
-app/static/wordfreqapp.db
+app/wordfreqapp.db
+app/db/wordfreqapp.db
 app/static/donate-the-author.jpg
 app/static/donate-the-author-hidden.jpg
-app/model/__pycache__/
+app/model/__pycache__/
+app/log.txt

Dockerfile

@@ -1,4 +1,5 @@
-FROM tiangolo/uwsgi-nginx-flask:python3.6
-COPY requirements.txt /app
-RUN pip3 install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
-COPY ./app /app
+FROM tiangolo/uwsgi-nginx-flask:python3.8-alpine
+COPY requirements.txt /tmp
+COPY ./app/ /app/
+RUN pip3 install -U pip -i https://mirrors.aliyun.com/pypi/simple/
+RUN pip3 install -r /tmp/requirements.txt -i https://mirrors.aliyun.com/pypi/simple/

Jenkinsfile

@@ -10,8 +10,8 @@ pipeline {
     stages {
         stage('MakeDatabasefile') {
 	    steps {
-	        sh 'touch ./app/static/wordfreqapp.db && rm -f ./app/static/wordfreqapp.db' 
-	        sh 'cat ./app/static/wordfreqapp.sql | sqlite3 ./app/static/wordfreqapp.db'
+	        sh 'touch ./app/wordfreqapp.db && rm -f ./app/wordfreqapp.db' 
+	        sh 'cat ./app/static/wordfreqapp.sql | sqlite3 ./app/wordfreqapp.db'
 	    }
 	}
         stage('BuildIt') {

README.md

@@ -61,15 +61,15 @@ My steps for deploying English on a Ubuntu server.
 
 
 All articles are stored in the `article` table in a SQLite file called
-`app/static/wordfreqapp.db`.
+`app/db/wordfreqapp.db`.
 
 ### Adding new articles
 
-To add articles, open and edit `app/static/wordfreqapp.db` using DB Browser for SQLite (https://sqlitebrowser.org).
+To add articles, open and edit `app/db/wordfreqapp.db` using DB Browser for SQLite (https://sqlitebrowser.org).
 
 ### Extending an account's expiry date
 
-By default, an account's expiry is 30 days after first sign-up.  To extend account's expiry date, open and edit `user` table in `app/static/wordfreqapp.db`.  Simply update field `expiry_date`.
+By default, an account's expiry is 30 days after first sign-up.  To extend account's expiry date, open and edit `user` table in `app/db/wordfreqapp.db`.  Simply update field `expiry_date`.
 
 ### Exporting the database
 
@@ -95,7 +95,7 @@ sqlite3 wordfreqapp.db`.  Delete wordfreqapp.db first if it exists.
 ### Uploading wordfreqapp.db to the server
 
 
-`pscp wordfreqapp.db lanhui@118.*.*.118:/home/lanhui/englishpal2/EnglishPal/app/static`
+`pscp wordfreqapp.db lanhui@118.*.*.118:/home/lanhui/englishpal2/EnglishPal/app/db/`
 
 
 

app/Article.py

@@ -1,6 +1,5 @@
 from WordFreq import WordFreq
 from wordfreqCMD import youdao_link, sort_in_descending_order
-from UseSqlite import InsertQuery, RecordQuery
 import pickle_idea, pickle_idea2
 import os
 import random, glob
@@ -8,18 +7,15 @@ 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 model.article import get_all_articles, get_article_by_id, get_number_of_articles
+import logging
 
-
-path_prefix = '/var/www/wordfreq/wordfreq/'
-path_prefix = './'  # comment this line in deployment
+path_prefix = './'
+db_path_prefix = './db/'  # comment this line in deployment
 
 
 def total_number_of_essays():
-    rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
-    rq.instructions("SELECT * FROM article")
-    rq.do()
-    result = rq.get_results()
-    return len(result)
+    return get_number_of_articles()
 
 
 def get_article_title(s):
@@ -33,32 +29,36 @@ def get_article_body(s):
 
 
 def get_today_article(user_word_list, visited_articles):
-    rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
     if visited_articles is None:
         visited_articles = {
             "index" : 0,  # 为 article_ids 的索引
             "article_ids": []  # 之前显示文章的id列表，越后越新
         }
     if visited_articles["index"] > len(visited_articles["article_ids"])-1:  # 生成新的文章，因此查找所有的文章
-        rq.instructions("SELECT * FROM article")
+        result = get_all_articles()
     else:  # 生成阅读过的文章，因此查询指定 article_id 的文章
         if visited_articles["article_ids"][visited_articles["index"]] == 'null':  # 可能因为直接刷新页面导致直接去查询了'null'，因此当刷新的页面的时候，需要直接进行“上一篇”操作
             visited_articles["index"] -= 1
             visited_articles["article_ids"].pop()
-        rq.instructions('SELECT * FROM article WHERE article_id=%d' % (visited_articles["article_ids"][visited_articles["index"]]))
-    rq.do()
-    result = rq.get_results()
+        article_id = visited_articles["article_ids"][visited_articles["index"]]
+        result = get_article_by_id(article_id)
     random.shuffle(result)
 
     # Choose article according to reader's level
-    d1 = load_freq_history(path_prefix + 'static/frequency/frequency.p')
+    logging.debug('* get_today_article(): start d1 = ... ')
+    d1 = load_freq_history(user_word_list)
     d2 = load_freq_history(path_prefix + 'static/words_and_tests.p')
+    logging.debug(' ... get_today_article(): get_difficulty_level_for_user() start')
     d3 = get_difficulty_level_for_user(d1, d2)
+    logging.debug(' ... get_today_article(): done')
 
     d = None
     result_of_generate_article = "not found"
+
     d_user = load_freq_history(user_word_list)
+    logging.debug('* get_today_article(): user_difficulty_level() start')
     user_level = user_difficulty_level(d_user, d3)  # more consideration as user's behaviour is dynamic. Time factor should be considered.
+    logging.debug('* get_today_article(): done')
     text_level = 0
     if visited_articles["index"] > len(visited_articles["article_ids"])-1:  # 生成新的文章
         amount_of_visited_articles = len(visited_articles["article_ids"])
@@ -87,8 +87,8 @@ def get_today_article(user_word_list, visited_articles):
     today_article = None
     if d:
         today_article = {
-            "user_level": '%4.2f' % user_level,
-            "text_level": '%4.2f' % text_level,
+            "user_level": '%4.1f' % user_level,
+            "text_level": '%4.1f' % text_level,
             "date": d['date'],
             "article_title": get_article_title(d['text']),
             "article_body": get_article_body(d['text']),

app/Login.py

@@ -1,7 +1,6 @@
 import hashlib
 import string
 from datetime import datetime, timedelta
-from UseSqlite import InsertQuery, RecordQuery
 
 def md5(s):
     '''

app/UseSqlite.py

@@ -1,87 +0,0 @@
-###########################################################################
-# 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/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/account_service.py

@@ -1,4 +1,5 @@
 from flask import *
+from markupsafe import escape
 from Login import check_username_availability, verify_user, add_user, get_expiry_date, change_password, WarningMessage
 
 

app/admin_service.py

@@ -1,5 +1,6 @@
 # System Library
 from flask import *
+from markupsafe import escape
 
 # Personal library
 from Yaml import yml
@@ -37,6 +38,22 @@ def admin():
 
 @adminService.route("/admin/article", methods=["GET", "POST"])
 def article():
+
+    def _make_title_and_content(article_lst):
+        for article in article_lst:
+            text = escape(article.text) # Fix XSS vulnerability, contributed by Xu Xuan
+            article.title = text.split("\n")[0]
+            article.content = '<br/>'.join(text.split("\n")[1:])
+
+
+    def _update_context():
+        article_len = get_number_of_articles()
+        context["article_number"] = article_len
+        context["text_list"] = get_page_articles(_cur_page, _page_size)
+        _articles = get_page_articles(_cur_page, _page_size)
+        _make_title_and_content(_articles)
+        context["text_list"] = _articles
+
     global _cur_page, _page_size
 
     is_admin = check_is_admin()
@@ -44,20 +61,15 @@ def article():
         return is_admin
 
     _article_number = get_number_of_articles()
+
     try:
-        _page_size = min(
-            max(1, int(request.args.get("size", 5))), _article_number
-        )  # 最小的size是1
-        _cur_page = min(
-            max(1, int(request.args.get("page", 1))), _article_number // _page_size + (_article_number % _page_size > 0)
-        )  # 最小的page是1
+        _page_size = min(max(1, int(request.args.get("size", 5))), _article_number)  # 最小的size是1
+        _cur_page = min(max(1, int(request.args.get("page", 1))), _article_number // _page_size + (_article_number % _page_size > 0))  # 最小的page是1
     except ValueError:
-        return "page parmas must be int!"
-    
+        return "page parameters must be integer!"
+
     _articles = get_page_articles(_cur_page, _page_size)
-    for article in _articles:   # 获取每篇文章的title
-        article.title = article.text.split("\n")[0]
-        article.content = '<br/>'.join(article.text.split("\n")[1:])
+    _make_title_and_content(_articles)
     
     context = {
         "article_number": _article_number,
@@ -67,23 +79,16 @@ def article():
         "username": session.get("username"),
     }
 
-    def _update_context():
-        article_len = get_number_of_articles()
-        context["article_number"] = article_len
-        context["text_list"] = get_page_articles(_cur_page, _page_size)
-        _articles = get_page_articles(_cur_page, _page_size)
-        for article in _articles:   # 获取每篇文章的title
-            article.title = article.text.split("\n")[0]
-        context["text_list"] = _articles
 
     if request.method == "GET":
         try:
             delete_id = int(request.args.get("delete_id", 0))
         except:
-            return "Delete article ID must be int!"
+            return "Delete article ID must be integer!"
         if delete_id:  # delete article
             delete_article_by_id(delete_id)
             _update_context()
+
     elif request.method == "POST":
         data = request.form
         content = data.get("content", "")
@@ -97,6 +102,7 @@ def article():
             _update_context()
             title = content.split('\n')[0]
             flash(f'Article added. Title: {title}')
+
     return render_template("admin_manage_article.html", **context)
 
 

app/db/README.txt

@@ -0,0 +1 @@
+Put wordfreqapp.db here

app/difficulty.py

@@ -18,6 +18,7 @@ def load_record(pickle_fname):
     return d
 
 
+ENGLISH_WORD_DIFFICULTY_DICT = {}
 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
@@ -39,8 +40,10 @@ def convert_test_type_to_difficulty_level(d):
         elif 'BBC' in d[k]:
             result[k] = 8
 
-    return result  # {'apple': 4, ...}
+    global ENGLISH_WORD_DIFFICULTY_DICT
+    ENGLISH_WORD_DIFFICULTY_DICT = result
 
+    return result  # {'apple': 4, ...}
 
 def get_difficulty_level_for_user(d1, d2):
     """
@@ -49,7 +52,11 @@ def get_difficulty_level_for_user(d1, d2):
     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, ...}
+    if ENGLISH_WORD_DIFFICULTY_DICT == {}:
+        d2 = convert_test_type_to_difficulty_level(d2)  # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
+    else:
+        d2 = ENGLISH_WORD_DIFFICULTY_DICT
+
     stemmer = snowballstemmer.stemmer('english')
 
     for k in d1:  # 用户的词

app/main.py

@@ -1,19 +1,19 @@
-#! /usr/bin/python3
-# -*- coding: utf-8 -*-
-
 ###########################################################################
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
-from flask import escape
+from flask import abort
+from markupsafe import escape
 from Login import *
 from Article import *
 import Yaml
 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 = 'lunch.time!'
+app.secret_key = os.urandom(32)
 
 # 将蓝图注册到Lab app
 app.register_blueprint(userService)
@@ -54,7 +54,6 @@ def appears_in_test(word, d):
     else:
         return ','.join(d[word])
 
-
 @app.route("/mark", methods=['GET', 'POST'])
 def mark_word():
     '''

app/model/__init__.py

@@ -1,7 +1,7 @@
 from pony.orm import *
 
 db = Database()
-db.bind("sqlite", "../static/wordfreqapp.db", create_db=True)  # bind sqlite file
+db.bind("sqlite", "../db/wordfreqapp.db", create_db=True)  # bind sqlite file
 
 
 class User(db.Entity):

app/model/article.py

@@ -7,7 +7,7 @@ def add_article(content, source="manual_input", level="5", question="No question
         Article(
             text=content,
             source=source,
-            date=datetime.now().strftime("%-d %b %Y"),  # format style of `5 Oct 2022`
+            date=datetime.now().strftime("%d %b %Y"),  # format style of `5 Oct 2022`
             level=level,
             question=question,
         )
@@ -32,3 +32,17 @@ def get_page_articles(num, size):
             x
             for x in Article.select().order_by(desc(Article.article_id)).page(num, size)
         ]
+
+
+def get_all_articles():
+    articles = []
+    with db_session:
+        for article in Article.select():
+            articles.append(article.to_dict())
+    return articles
+
+
+def get_article_by_id(article_id):
+    with db_session:
+        article = Article.get(article_id=article_id)
+    return [article.to_dict()]

app/static/config.yml

@@ -9,6 +9,7 @@ js:
     - ../static/js/jquery.js
     - ../static/js/read.js
     - ../static/js/word_operation.js
+    - ../static/js/checkboxes.js
   bottom: # 在页面加载完之后加载
     - ../static/js/fillword.js
     - ../static/js/highlight.js

app/static/js/checkboxes.js

@@ -0,0 +1,5 @@
+function toggleCheckboxSelection(checkStatus) {
+    // used in userpage_post.html
+    const checkBoxes = document.getElementsByName('marked');
+    checkBoxes.forEach((checkbox) => { checkbox.checked = checkStatus;} );
+}

app/static/js/fillword.js

@@ -29,3 +29,8 @@ function onReadClick() {
 function onChooseClick() {
     isChoose = !isChoose;
 }
+
+// 如果网页刷新，停止播放声音
+if (performance.getEntriesByType("navigation")[0].type == "reload") {
+    Reader.stopRead();
+}

app/static/js/highlight.js

@@ -22,62 +22,38 @@ function getWord() {
 
 function highLight() {
     if (!isHighlight) return;
-    let articleContent = document.getElementById("article").innerText; //将原来的.innerText改为.innerHtml，使用innerText会把原文章中所包含的<br>标签去除，导致处理后的文章内容失去了原来的格式
+    let 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 = "";  //初始化allWords的值，避免进入判断后编译器认为allWords未初始化的问题
-    if(dictionaryWords != null){//增加一个判断，检查生词本里面是否为空，如果为空，allWords只添加选中的单词
-        allWords = pickedWords.value + " " + dictionaryWords.value;
-    }
-    else{
-        allWords = pickedWords.value + " ";
-    }
-    const list = allWords.split(" ");//将所有的生词放入一个list中，用于后续处理
+    let allWords = dictionaryWords === null ? pickedWords.value + " " : pickedWords.value + " " + dictionaryWords.value;
+    const list = allWords.split(" "); // 将所有的生词放入一个list中
+    let totalSet = new Set();
     for (let i = 0; i < list.length; ++i) {
-        list[i] = list[i].replace(/(^\s*)|(\s*$)/g, ""); //消除单词两边的空字符
-        list[i] = list[i].replace('|', "");
-        list[i] = list[i].replace('?', "");
-        if (list[i] !== "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
-           //将文章中所有出现该单词word的地方改为："<mark>" + word + "<mark>"。 正则表达式RegExp()中，"\\b"代表单词边界匹配。
-
-            //修改代码
-            let articleContent_fb = articleContent;  //文章副本
-            while(articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase()) !== -1 && list[i]!=""){
-                //找到副本中和list[i]匹配的第一个单词(第一种匹配情况),并赋值给list[i]。
-                const index = articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase());
-                list[i] = articleContent_fb.substring(index, index + list[i].length);
-
-                articleContent_fb = articleContent_fb.substring(index + list[i].length);    // 使用副本中list[i]之后的子串替换掉副本
-                articleContent = articleContent.replace(new RegExp("\\b"+list[i]+"\\b","g"),"<mark>" + list[i] + "</mark>");
+        list[i] = list[i].replace(/(^\W*)|(\W*$)/g, ""); // 消除单词两边的非单词字符
+        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mark标签,防止标签发生嵌套
+    articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
+    articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
+    // 将文章中所有出现该单词word的地方改为："<mark>" + word + "<mark>"。
+    for (let word of totalSet) {
+        articleContent = articleContent.replace(new RegExp("\\b" + word + "\\b", "g"), "<mark>" + word + "</mark>");
     }
     document.getElementById("article").innerHTML = articleContent;
 }
 
 function cancelHighlighting() {
-    let articleContent = document.getElementById("article").innerText;//将原来的.innerText改为.innerHtml，原因同上
-    let pickedWords = document.getElementById("selected-words");
-    const dictionaryWords = document.getElementById("selected-words2");    
-    const list = pickedWords.value.split(" ");    
-    if (pickedWords != null) {
-        for (let i = 0; i < list.length; ++i) {
-            list[i] = list[i].replace(/(^\s*)|(\s*$)/g, "");
-            if (list[i] !== "") { //原来判断的代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
-                articleContent = articleContent.replace(new RegExp("<mark>"+list[i]+"</mark>", "g"), list[i]);
-            }
-        }
-    }
-    if (dictionaryWords != null) {
-        let list2 = pickedWords.value.split(" ");
-        for (let i = 0; i < list2.length; ++i) {
-            list2 = dictionaryWords.value.split(" ");
-            list2[i] = list2[i].replace(/(^\s*)|(\s*$)/g, "");
-            if (list2[i] !== "") { //原来代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
-                articleContent = articleContent.replace(new RegExp("<mark>"+list2[i]+"</mark>", "g"), list2[i]);
-            }
-        }
-    }
+    let articleContent = document.getElementById("article").innerHTML;
+    articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
+    articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
     document.getElementById("article").innerHTML = articleContent;
 }
 
@@ -99,4 +75,4 @@ function toggleHighlighting() {
     }
 }
 
-showBtnHandler();
+showBtnHandler();

app/static/js/read.js

@@ -9,7 +9,7 @@ var Reader = (function() {
         msg.rate = rate;
         msg.lang = "en-US";
         msg.onboundary = ev => {
-            if (ev.name == "word") {
+            if (ev.name === "word") {
                 current_position = ev.charIndex;
             }
         }
@@ -32,4 +32,4 @@ var Reader = (function() {
         read: read,
         stopRead: stopRead
     };
-})();
+}) ();

app/static/js/word_operation.js

@@ -5,15 +5,14 @@ function familiar(theWord) {
     $.ajax({
         type:"GET",
         url:"/" + username + "/" + word + "/familiar",
-        success:function(response){
+        success:function(response) {
             let new_freq = freq - 1;
             const allow_move = document.getElementById("move_dynamiclly").checked;
             if (allow_move) {
-
                 if (new_freq <= 0) {
                     removeWord(theWord);
                 } else {
-                    renderWord({ word: theWord, freq: new_freq });
+                    renderWord({word: theWord, freq: new_freq});
                 }
             } else {
                 if(new_freq <1) {
@@ -33,11 +32,11 @@ function unfamiliar(theWord) {
     $.ajax({
         type:"GET",
         url:"/" + username + "/" + word + "/unfamiliar",
-        success:function(response){
+        success:function(response) {
             let new_freq = parseInt(freq) + 1;
             const allow_move = document.getElementById("move_dynamiclly").checked;
             if (allow_move) {
-                renderWord({ word: theWord, freq: new_freq });
+                renderWord({word: theWord, freq: new_freq});
             } else {
                 $("#freq_" + theWord).text(new_freq);
             }
@@ -51,7 +50,7 @@ function delete_word(theWord) {
     $.ajax({
         type:"GET",
         url:"/" + username + "/" + word + "/del",
-        success:function(response){
+        success:function(response) {
             const allow_move = document.getElementById("move_dynamiclly").checked;
             if (allow_move) {
                 removeWord(theWord);
@@ -114,7 +113,7 @@ function removeWord(word) {
     // 根据词频信息删除元素
     word = word.replace('&amp;', '&');
     const element_to_remove = document.getElementById(`p_${word}`);
-    if (element_to_remove != null) {
+    if (element_to_remove !== null) {
         element_to_remove.remove();
     }
 }
@@ -129,7 +128,7 @@ function renderWord(word) {
     for (const current of container.children) {
         const cur_word = parseWord(current);
         // 找到第一个词频比它小的元素，插入到这个元素前面
-        if (compareWord(cur_word, word) == -1) {
+        if (compareWord(cur_word, word) === -1) {
             container.insertBefore(new_element, current);
             inserted = true;
             break;
@@ -165,17 +164,11 @@ function elementFromString(string) {
  *  当first大于second时返回1
  */
 function compareWord(first, second) {
-    if (first.freq < second.freq) {
-        return -1;
+    if (first.freq !== second.freq) {
+        return first.freq < second.freq ? -1 : 1;
     }
-    if (first.freq > second.freq) {
-        return 1;
-    }
-    if (first.word < second.word) {
-        return -1;
-    }
-    if (first.word > second.word) {
-        return 1;
+    if (first.word !== second.word) {
+        return first.word < second.word ? -1 : 1;
     }
     return 0;
-}
+}

app/templates/login.html

@@ -1,7 +1,7 @@
 {% block body %}
 {% if session['logged_in'] %}
 
-你已登录 <a href="/{{ session['username'] }}">{{ session['username'] }}</a>。 登出点击<a href="/logout">这里</a>。
+你已登录 <a href="/{{ session['username'] }}/userpage">{{ session['username'] }}</a>。 登出点击<a href="/logout">这里</a>。
 
 {% else %}
 <meta charset="utf-8" name="viewport" content="width=device-width, initial-scale=1.0, minimum-scale=0.5, maximum-scale=3.0, user-scalable=yes" />
@@ -32,14 +32,13 @@
 <div class="container">
 
   <section class="signin-heading">
-    <h1>Sign In</h1>
+    <h1>Sign in</h1>
   </section>
 
   <input type="text" placeholder="用户名" class="username" id="username">
   <input type="password" placeholder="密码" class="password"  id="password">
   <button type="button" class="btn" onclick="login()">登录</button>
   <a class="signup" href="/signup">注册</a>
-
 </div>
 
 {% endif %}

app/templates/mainpage_get.html

@@ -44,6 +44,7 @@
                 <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 }}

app/templates/signup.html

@@ -53,7 +53,7 @@ You're logged in already! <a href="/logout">Logout</a>.
 <div class="container">
 
   <section class="signin-heading">
-    <h1>Sign Up</h1>
+    <h1>Sign up</h1>
   </section>
 
   <p><input type="username" id="username" placeholder="输入用户名" class="username"></p>

app/templates/userpage_get.html

@@ -23,44 +23,34 @@
     <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);
-            }
-            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);
-            }
-        }
+      @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); }
+      }
 
-        .lead {
-            font-size: 22px;
-            font-family: Helvetica, sans-serif;
-            white-space: pre-wrap;
-        }
+      .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 {
+	  padding: 0;
+	  font-size: 20px;
+	  line-height: 21px;
+	  display: inline-block;
+      }
 
-        .arrow:hover {
-            cursor: pointer;
-        }
+      .arrow:hover {
+	  cursor: pointer;
+      }
 
     </style>
 </head>
@@ -69,83 +59,72 @@
     <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() %}
-        <div class="alert alert-warning alert-dismissible fade show" role="alert">
-            {{ message }}
-            <button type="button" class="btn-close" data-bs-dismiss="alert" aria-label="Close"></button>
-        </div>
+    <div class="alert alert-warning alert-dismissible fade show" role="alert">
+	{{ message }}
+	<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()"
-            title="下一篇 Next Article">⇨
-    </button>
-    <button class="arrow" id="load_pre_article" onclick="load_pre_article();Reader.stopRead()" style="display: none"
-            title="上一篇 Previous Article">⇦
-    </button>
+        <button class="arrow" id="load_next_article" onclick="load_next_article();Reader.stopRead()" title="下一篇 Next Article">⇨</button>
+        <button class="arrow" id="load_pre_article" onclick="load_pre_article();Reader.stopRead()" style="display: none" title="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="text-decoration-underline" id="user_level">{{ today_article["user_level"] }}</span> and we
-                have chosen an article with a difficulty level of <span class="text-decoration-underline"
-                                                                        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="alert alert-success" role="alert">According to your word list, your level is <span class="text-decoration-underline" id="user_level">{{ today_article["user_level"] }}</span>  and we have chosen an article with a difficulty level of <span class="text-decoration-underline" id="text_level">{{ today_article["text_level"] }}</span> for you.</div>
+                <p class="text-muted" id="date">Article added on: {{ today_article["date"] }}</p><br/>
             <div class="p-3 mb-2 bg-light text-dark" style="margin: 0 0.5%;"><br/>
-                <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 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/>
+            <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>
-                <br/>
+                <div id="answer" style="display:none;">{{ today_article['answer'] }}</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>
+            <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>
     </div>
 
-    <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
+    <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" onclick="clearSelectedWords()">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">
@@ -173,10 +152,9 @@
                 {% 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>
+                <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>
@@ -244,78 +222,66 @@
     }
 
 
-    function load_next_article() {
-        $("#load_next_article").prop("disabled", true)
+    function load_next_article(){
         $.ajax({
             url: '/get_next_article/{{username}}',
             dataType: 'json',
-            success: function (data) {
+            success: function(data) {
                 // 更新页面内容
-                if (data['today_article']) {
+                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() {
+    function load_pre_article(){
         $.ajax({
             url: '/get_pre_article/{{username}}',
             dataType: 'json',
-            success: function (data) {
+            success: function(data) {
                 // 更新页面内容
-                if (data['today_article']) {
+                if(data['today_article']){
                     update(data['today_article']);
                     check_pre(data['visited_articles']);
                 }
             }
         });
     }
-
-    function update(today_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"]);
+        $('#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);
+        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);
+        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)) {
+<!-- 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 {
+        }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();
+    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") {
+        }else if(result_of_generate_article == "not found"){
             $('#found').hide();
             $('#not_found').show();
             $('#read_all').hide();
-        } else {
+        }else{
             $('#found').hide();
             $('#not_found').hide();
             $('#read_all').show();
@@ -325,7 +291,7 @@
 </body>
 <style>
     mark {
-        color: #{{ yml['highlight']['color'] }};
+        color: red;
         background-color: rgba(0, 0, 0, 0);
     }
 </style>

app/templates/userpage_post.html

@@ -1,45 +1,50 @@
 <!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'] %}
+	{{ yml['header'] | safe }}
+	{% if yml['css']['item'] %}
         {% for css in yml['css']['item'] %}
         <link href="{{ css }}" rel="stylesheet">
         {% endfor %}
-    {% endif %}
-    {% if yml['js']['head'] %}
+	{% endif %}
+	{% if yml['js']['head'] %}
         {% for js in yml['js']['head'] %}
-            <script src="{{ js }}" ></script>
+        <script src="{{ js }}" ></script>
         {% endfor %}
-    {% endif %}
+	{% endif %}
 
-    <title>EnglishPal Study Room for {{username}}</title>
-</head>
-<body>
-     <p>取消勾选认识的单词</p>
-      <form method="post" action="/{{username}}/mark">
-       <input type="submit" name="add-btn" value="加入我的生词簿"/>
-       {% for x in lst %}
-          {% set word = x[0]%}
-        <p>
-            <font color="grey">{{loop.index}}</font>
-            :
-            <a href='http://youdao.com/w/eng/{{word}}/#keyfrom=dict2.index' title={{word}}>{{word}}</a>
-            ({{x[1]}})
-            <input type="checkbox" name="marked" value="{{word}}" checked>
-        </p>
+	<title>EnglishPal Study Room for {{username}}</title>
+    </head>
+    <body>
+	<div class="container-fluid">
+	    <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-selection" value="全部勾选" onclick="toggleCheckboxSelection(true)" />
+	    </p>
+	    <form method="post" action="/{{username}}/mark">
+		<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 %}
+		{% set word = x[0]%}
+		<p>
+		    <font color="grey">{{loop.index}}</font>
+		    :
+		    <a href='http://youdao.com/w/eng/{{word}}/#keyfrom=dict2.index' title={{word}}>{{word}}</a>
+		    ({{x[1]}})
+		    <input type="checkbox" name="marked" value="{{word}}" checked>
+		</p>
 
-       {% endfor %}
-       </form>
-    {{ yml['footer'] | safe }}
-    {% if yml['js']['bottom'] %}
-        {% for js in yml['js']['bottom'] %}
+		{% endfor %}
+	    </form>
+	    {{ yml['footer'] | safe }}
+	    {% if yml['js']['bottom'] %}
+            {% for js in yml['js']['bottom'] %}
             <script src="{{ js }}" ></script>
-        {% endfor %}
-    {% endif %}
-</body>
+            {% endfor %}
+	    {% endif %}
+	</div>
+    </body>
 </html>

app/test/test_stress.py

@@ -0,0 +1,43 @@
+''' Contributed by Lin Junhong et al. 2023-06.'''
+
+import requests
+import multiprocessing
+import time
+
+def stress(username):
+    try:
+        data = {
+            'username': username,
+            'password': '123123'
+        }
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.36 Edg/114.0.1823.51'
+        }
+        session = requests.session()
+        response = session.post(url='http://127.0.0.1:5000/signup', data=data, headers=headers)
+        print('Sign up ', response.status_code)
+        time.sleep(0.5)
+        response = session.post(url='http://127.0.0.1:5000/login', data=data, headers=headers)
+        print('Sign in ', response.status_code)
+        time.sleep(0.5)
+        response = session.get(url=f'http://127.0.0.1:5000/{username}/userpage', headers=headers)
+        print('User page', response.status_code)
+        time.sleep(0.5)
+        print(session.cookies)
+        for i in range(5):
+            response = session.get(url=f'http://127.0.0.1:5000/get_next_article/{username}', headers=headers, cookies=session.cookies)
+            time.sleep(0.5)
+            print(f'Next page ({i}) [{username}]')
+            print(response.status_code)
+            print(response.json()['today_article']['article_title'])
+    except Exception as e:
+        print(e)
+
+
+if __name__ == '__main__':
+    username = 'Learner'
+    pool = multiprocessing.Pool(processes=10)
+    for i in range(10):
+        pool.apply_async(stress, (f'{username}{i}',))
+    pool.close()
+    pool.join()

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/user_service.py

@@ -15,6 +15,9 @@ from wordfreqCMD import sort_in_descending_order
 import pickle_idea
 import pickle_idea2
 
+import logging
+logging.basicConfig(filename='log.txt', format='%(asctime)s %(message)s', level=logging.DEBUG)
+
 # 初始化蓝图
 userService = Blueprint("user_bp", __name__)
 
@@ -32,7 +35,9 @@ def get_next_article(username):
         else:  # 当前不为“null”，直接 index+=1
             visited_articles["index"] += 1
         session["visited_articles"] = visited_articles
+        logging.debug('/get_next_article: start calling get_today_arcile()')
         visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
+        logging.debug('/get_next_arcile: done.')
         data = {
             'visited_articles': visited_articles,
             'today_article': today_article,
@@ -129,7 +134,7 @@ def userpage(username):
     user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
 
     if request.method == 'POST':  # when we submit a form
-        content = escape(request.form['content'])
+        content = request.form['content']
         f = WordFreq(content)
         lst = f.get_freq()
         return render_template('userpage_post.html',username=username,lst = lst, yml=Yaml.yml)
@@ -176,7 +181,11 @@ def user_mark_word(username):
         for word in request.form.getlist('marked'):
             lst.append((word, [get_time()]))
         d = pickle_idea2.merge_frequency(lst, lst_history)
-        pickle_idea2.save_frequency_to_pickle(d, user_freq_record)
+        if len(lst_history) > 999:
+            flash('You have way too many words in your difficult-words book. Delete some first.')
+        else:
+            pickle_idea2.save_frequency_to_pickle(d, user_freq_record)
+            flash('Added %s.' % (', '.join(request.form.getlist('marked'))))
         return redirect(url_for('user_bp.userpage', username=username))
     else:
         return 'Under construction'

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')
 
 
-

build.sh

@@ -2,10 +2,7 @@
 
 DEPLOYMENT_DIR=/home/lanhui/englishpal2/EnglishPal
 cd $DEPLOYMENT_DIR
-
-# Install dependencies
-
-pip3 install -r requirements.txt
+pwd
 
 # Stop service
 sudo docker stop EnglishPal
@@ -15,7 +12,7 @@ sudo docker rm EnglishPal
 sudo docker build -t englishpal .
 
 # Run the application
-sudo docker run --restart=always -d --name EnglishPal -p 90:80 -v ${DEPLOYMENT_DIR}/app/static/frequency:/app/static/frequency -v ${DEPLOYMENT_DIR}/app/static/:/app/static/ -t englishpal  # for permanently saving data
+sudo docker run --restart=always -d --name EnglishPal -p 90:80  -v ${DEPLOYMENT_DIR}/app/static/frequency:/app/static/frequency --mount type=volume,src=englishpal-db,target=/app/db -t englishpal # for permanently saving data
 
 # Save space.  Run it after sudo docker run
 sudo docker system prune -a -f

requirements.txt

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