Fix ImportError: cannot import name 'url_quote'

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/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/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.
+    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;
 }
 

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

@@ -5,6 +5,8 @@
     <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"/>
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.1/dist/css/bootstrap.min.css" rel="stylesheet">
+    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.1/dist/js/bootstrap.bundle.min.js"></script>
 
     {{ yml['header'] | safe }}
     {% if yml['css']['item'] %}
@@ -32,6 +34,24 @@
           40%, 60% { transform: translate3d(+4px, 0, 0); }
           50% { transform: translate3d(-4px, 0, 0); }
       }
+
+      .lead{
+          font-size: 22px;
+          font-family: Helvetica, sans-serif;
+          white-space: pre-wrap;
+      }
+
+      .arrow {
+	  padding: 0;
+	  font-size: 20px;
+	  line-height: 21px;
+	  display: inline-block;
+      }
+
+      .arrow:hover {
+	  cursor: pointer;
+      }
+
     </style>
 </head>
 <body>
@@ -45,22 +65,28 @@
         <a class="btn btn-secondary" href="/reset" role="button" onclick="stopRead()">重设密码</a>
 
     </p>
-{#    {% for message in flashed_messages %}#} {# 根据user_service.userpage,取消了参数flashed_messages，因此注释了这段代码 #}
-{#        <div class="alert alert-warning" role="alert">Congratulations! {{ message }}</div>#}
-{#    {% endfor %}#}
+    {% 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>
+    {% endfor %}
 
-        <button class="btn btn-success" id="load_next_article" onclick="load_next_article()"> 下一篇 Next Article </button>
-        <button class="btn btn-success" id="load_pre_article" onclick="load_pre_article()" > 上一篇 Previous Article </button>
+        <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="badge bg-success" id="user-level">{{ today_article["user_level"] }}</span>  and we have chosen an article with a difficulty level of <span class="badge bg-success" id="text_level">{{ today_article["text_level"] }}</span> for you.</div>
+            <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"><br/>
-            <p class="display-5" id="article_title">{{ today_article["article_title"] }}</p><br/>
-            <p class="lead"><font id="article" size=2>{{ today_article["article_body"] }}</font></p><br/>
+            <div class="p-3 mb-2 bg-light text-dark" style="margin: 0 0.5%;"><br/>
+            <p class="display-6" id="article_title">{{ today_article["article_title"] }}</p><br/>
+            <p class="lead"><font id="article">{{ today_article["article_body"] }}</font></p><br/>
+            <div>
                 <p><small class="text-muted" id="source">{{ today_article['source'] }}</small></p><br/>
+            </div>
+            
             <p><b id="question">{{ today_article['question'] }}</b></p><br/>
                 <script type="text/javascript">
                     function toggle_visibility(id) { {# https://css-tricks.com/snippets/javascript/showhide-element/#}
@@ -97,8 +123,8 @@
     <p><b>收集生词吧</b> （可以在正文中划词，也可以复制黏贴）</p>
     <form method="post" action="/{{ username }}/userpage">
         <textarea name="content" id="selected-words" rows="10" cols="120"></textarea><br/>
-        <input type="submit" value="把生词加入我的生词库"/>
-        <input type="reset" value="清除"/>
+        <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>
     </form>
     {% if session.get['thisWord'] %}
         <script type="text/javascript">
@@ -147,6 +173,12 @@
     {% endfor %}
 {% endif %}
 <script type="text/javascript">
+    window.onload = function () { // 页面加载时执行
+        // 刷新页面或进入页面时判断，若不是首篇文章，则上一篇按钮可见
+        if(sessionStorage.getItem('pre_page_button')!="display" && sessionStorage.getItem('pre_page_button')){
+            $('#load_pre_article').show();
+        }
+     };
     function load_next_article(){
         $.ajax({
             url: '/get_next_article/{{username}}',
@@ -175,7 +207,7 @@
         });
     }
     function update(today_article){
-        $('#user-level').html(today_article['user_level']);
+        $('#user_level').html(today_article['user_level']);
         $('#text_level').html(today_article["text_level"]);
         $('#date').html('Article added on: '+today_article["date"]);
         $('#article_title').html(today_article["article_title"]);
@@ -183,13 +215,19 @@
         $('#source').html(today_article['source']);
         $('#question').html(today_article["question"]);
         $('#answer').html(today_article["answer"]);
+        document.querySelector('#text_level').classList.add('mark'); // highlight text difficult level for 2 seconds
+        setTimeout(() => {document.querySelector('#text_level').classList.remove('mark');}, 2000);
+        document.querySelector('#user_level').classList.add('mark'); // do the same thing for user difficulty level
+        setTimeout(() => {document.querySelector('#user_level').classList.remove('mark');}, 2000);
     }
 <!-- 检查是否存在上一篇或下一篇，不存在则对应按钮隐藏-->
     function check_pre(visited_articles){
         if((visited_articles=='')||(visited_articles['index']<=0)){
             $('#load_pre_article').hide();
+            sessionStorage.setItem('pre_page_button', 'display')
         }else{
             $('#load_pre_article').show();
+            sessionStorage.setItem('pre_page_button', 'show')
         }
     }
     function check_next(result_of_generate_article){

app/templates/userpage_post.html

@@ -1,6 +1,6 @@
 <!DOCTYPE html>
 <html lang="en">
-<head>
+    <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" />
@@ -18,11 +18,15 @@
 	{% endif %}
 
 	<title>EnglishPal Study Room for {{username}}</title>
-</head>
-<body>
-     <p>取消勾选认识的单词</p>
+    </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">
-       <input type="submit" name="add-btn" value="加入我的生词簿"/>
+		<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>
@@ -41,5 +45,6 @@
             <script src="{{ js }}" ></script>
             {% endfor %}
 	    {% endif %}
-</body>
+	</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/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)
+        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'

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

@@ -1,5 +1,6 @@
-Flask==1.1.2
+Flask==2.0.3
 selenium==3.141.0
 PyYAML~=6.0
 pony==0.7.16
 snowballstemmer==2.2.0
+Werkzeug==2.2.2