Fix bug 578

2024-07-04 15:04:34 +08:00 · 2024-07-04 15:04:34 +08:00 · faf5ec14a4
parent 9dab83219a 00ae770195
commit faf5ec14a4
36 changed files with 673 additions and 264 deletions
--- a/.gitignore
+++ b/.gitignore
@ -2,12 +2,20 @@
 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/test/__pycache__/
+app/test/.pytest_cache/
+app/test/pytest_report.html
+app/test/assets
+app/log.txt
--- a/9
+++ b/9
@ -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/
--- a/4
+++ b/4
@ -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') {
--- a/README.md
+++ b/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/`



@ -129,6 +129,28 @@ We welcome feedback on EnglishPal.  Feedback examples:
 EnglishPal's bugs and improvement suggestions are recorded in [Bugzilla](http://118.25.96.118/bugzilla/buglist.cgi?bug_status=__all__&list_id=1302&order=Importance&product=EnglishPal&query_format=specific).  Send (lanhui at zjnu.edu.cn) an email message for opening a Bugzilla account or reporting a bug.


+## End-to-end testing
+
+We use the Selenium test framework to test our app.
+
+In order to run the test, first we need to download a webdriver executable.
+
+Microsoft Edge's webdriver can be downloaded from [microsoft-edge-tools-webdriver](https://developer.microsoft.com/en-us/microsoft-edge/tools/webdriver/). Make sure the version we download matches the version of the web browser installed on our laptop.
+
+After extracting the downloaded zip file (e.g., edgedriver_win64.zip), rename msedgedriver.exe to MicrosoftWebDriver.exe.
+
+Add MicrosoftWebDriver.exe's path to system's PATH variable.
+
+Install the following dependencies too:
+
+- pip install -U selenium==3.141.0
+- pip install -U urllib3==1.26.2
+
+Run English Pal first, then run the test using pytest as follows: pytest --html=pytest_report.html test_add_word.py
+
+The above command will generate a HTML report file pytest_report.html after finishing executing test_add_word.py.  Note: you need to install pytest-html package first: pip install pytest-html.
+
+You may also want to use [webdriver-manager](https://pypi.org/project/webdriver-manager/) from PyPI, so that you can avoid tediously installing a web driver executable manually.  However, my experience shows that webdriver-manager is too slow.  For example, it took me 16 minutes to run 9 tests, while with the pre-installed web driver executable, it took less than 2 minutes.

 ## TODO

--- a/app/Article.py
+++ b/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']),
--- a/app/Login.py
+++ b/app/Login.py
@ -1,7 +1,6 @@
 import hashlib
 import string
 from datetime import datetime, timedelta
-from UseSqlite import InsertQuery, RecordQuery

 def md5(s):
    '''
--- a/app/UseSqlite.py
+++ b/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())
--- a/app/account_service.py
+++ b/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


--- a/app/admin_service.py
+++ b/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)


--- a/app/db/README.txt
+++ b/app/db/README.txt
@ -0,0 +1 @@
+Put wordfreqapp.db here
--- a/app/difficulty.py
+++ b/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
--- a/app/main.py
+++ b/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():
    '''
--- a/app/model/init.py
+++ b/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):
--- a/app/model/article.py
+++ b/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()]
--- a/app/static/config.yml
+++ b/app/static/config.yml
@ -2,13 +2,14 @@
 css:
  item:
    - ../static/css/bootstrap.css
-
+    - ../static/css/highlighted.css
 # 全局引入的js文件地址
 js:
  head: # 在页面加载之前加载
    - ../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
--- a/app/static/css/highlighted.css
+++ b/app/static/css/highlighted.css
@ -0,0 +1,5 @@
+
+.highlighted {
+    color: red;
+    font-weight: normal;
+}
--- a/app/static/wordfreqapp.db
+++ b/app/static/wordfreqapp.db
--- a/app/templates/login.html
+++ b/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" />
@ -15,6 +15,10 @@
            alert('输入不能为空!');
            return false;
        }
+        if (password.includes(' ')) {
+            alert('输入不能包含空格!');
+            return false;
+        }
        $.post(
            "/login", {'username': username, 'password': password},
            function (response) {
@ -32,14 +36,13 @@
 <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 %}
--- a/app/templates/mainpage_post.html
+++ b/app/templates/mainpage_post.html
@ -2,7 +2,7 @@
 <html lang="en">
 <head>
    <meta charset="UTF-8">
-    <title>Title</title>
+    <title>单词词频</title>

    {{ yml['header'] | safe }}
    {% if yml['css']['item'] %}
--- a/app/templates/reset.html
+++ b/app/templates/reset.html
@ -12,6 +12,10 @@
                alert('输入不能为空!');
                return false;
            }
+            if (old_password.includes(' ') || new_password.includes(' ')) {
+                alert('输入不能包含空格!');
+                return false;
+            }
            if (new_password !== re_new_password) {
                alert('新密码不匹配，请重新输入');
                return false;
--- a/app/templates/signup.html
+++ b/app/templates/signup.html
@ -16,6 +16,10 @@ You're logged in already! <a href="/logout">Logout</a>.
                alert('输入不能为空!');
                return false;
            }
+            if (password.includes(' ') || password2.includes(' ')) {
+                alert('输入不能包含空格!');
+                return false;
+            }
            if (password !== password2) {
                alert('确认密码与输入密码不一致！');
                return false;
@ -53,7 +57,7 @@ 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>
--- a/app/templates/userpage_post.html
+++ b/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'] %}
-        {% for css in yml['css']['item'] %}
-        <link href="{{ css }}" rel="stylesheet">
-        {% endfor %}
-    {% endif %}
-    {% if yml['js']['head'] %}
-        {% for js in yml['js']['head'] %}
-            <script src="{{ js }}" ></script>
-        {% endfor %}
-    {% endif %}
+       {{ yml['header'] | safe }}
+       {% if yml['css']['item'] %}
+         {% for css in yml['css']['item'] %}
+         <link href="{{ css }}" rel="stylesheet">
+         {% endfor %}
+        {% endif %}
+        {% if yml['js']['head'] %}
+         {% for js in yml['js']['head'] %}
+         <script src="{{ js }}" ></script>
+         {% endfor %}
+        {% endif %}

-    <title>EnglishPal Study Room for {{username}}</title>
-</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" onclick="clearSelectedWords()">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'] %}
-            <script src="{{ js }}" ></script>
-        {% endfor %}
-    {% endif %}
-</body>
+               {% endfor %}
+           </form>
+           {{ yml['footer'] | safe }}
+           {% if yml['js']['bottom'] %}
+            {% for js in yml['js']['bottom'] %}
+             <script src="{{ js }}" ></script>
+            {% endfor %}
+        {% endif %}
+      </div>
+    </body>
 </html>
--- a/app/test/conftest.py
+++ b/app/test/conftest.py
@ -1,6 +1,9 @@
 import pytest
+import sqlite3
+import time
 from selenium import webdriver
-from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+
+from pathlib import Path

@pytest.fixture
 def URL():
@ -9,5 +12,24 @@ def URL():

@pytest.fixture
 def driver():
-    my_driver = webdriver.Edge()  # uncomment this line if you wish to run the test on your laptop    
-    return my_driver
+    return webdriver.Edge()  # follow the "End-to-end testing" section in README.md to install the web driver executable
+
+
+@pytest.fixture
+def restore_sqlite_database():
+    '''
+    Automatically restore SQLite database file app/db/wordfreqapp.db
+    using SQL statements from app/static/wordfreqapp.sql
+    '''
+    con = sqlite3.connect('../db/wordfreqapp.db')
+    with con:
+        con.executescript('DROP TABLE IF EXISTS user;')
+        con.executescript('DROP TABLE IF EXISTS article;')
+        con.executescript(open('../static/wordfreqapp.sql', encoding='utf8').read())
+    con.close()
+
+
+@pytest.fixture(autouse=True)
+def restart_englishpal(restore_sqlite_database):
+    (Path(__file__).parent / '../main.py').touch()
+    time.sleep(1)
--- a/app/test/helper.py
+++ b/app/test/helper.py
@ -0,0 +1,33 @@
+import uuid
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import UnexpectedAlertPresentException, NoAlertPresentException
+
+def signup(URL, driver):
+    username = 'TestUser' + str(uuid.uuid1()).split('-')[0].title()
+    password = '[Abc+123]'
+
+    driver.get(URL)
+        
+    elem = driver.find_element_by_link_text('注册')
+    elem.click()
+    
+    elem = driver.find_element_by_id('username')
+    elem.send_keys(username)
+    
+    elem = driver.find_element_by_id('password')
+    elem.send_keys(password)
+
+    elem = driver.find_element_by_id('password2')
+    elem.send_keys(password)    
+    
+    elem = driver.find_element_by_class_name('btn') # 找到"注册"按钮
+    elem.click()
+
+    try:
+        WebDriverWait(driver, 1).until(EC.alert_is_present())
+        driver.switch_to.alert.accept()
+    except (UnexpectedAlertPresentException, NoAlertPresentException):
+        pass
+    
+    return username, password
--- a/app/test/test_add_word.py
+++ b/app/test/test_add_word.py
@ -1,76 +1,31 @@
-# -*- coding: utf-8 -*-
-# Run the docker image using the following command:
-# docker run -d -p 4444:4444 selenium/standalone-chrome
-from selenium import webdriver
-from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
-
-import random, time
-import string
-
-driver = webdriver.Remote('http://localhost:4444/wd/hub', DesiredCapabilities.FIREFOX)
-driver.implicitly_wait(10)
-
-HOME_PAGE = 'http://121.4.94.30:91/'
+import time
+from helper import signup


-def has_punctuation(s):
-    return [c for c in s if c in string.punctuation] != []
-    
-def test_add_word():
+def test_add_word(URL, driver):
    try:
-        driver.get(HOME_PAGE)
-        assert 'English Pal -' in driver.page_source
-    
-        # login
-        elem = driver.find_element_by_link_text('登录')
-        elem.click()
-    
-        uname = 'lanhui'
-        password = 'l0ve1t'
-        elem = driver.find_element_by_name('username')
-        elem.send_keys(uname)
-    
-        elem = driver.find_element_by_name('password')
-        elem.send_keys(password)
-        
-        elem = driver.find_element_by_xpath('//form[1]/p[3]/input[1]') # 找到登录按钮
-        elem.click()
-    
-        assert 'EnglishPal Study Room for ' + uname in  driver.title
-    
-        # get essay content
-        elem = driver.find_element_by_id('text-content')
-        essay_content = elem.text
-    
-        elem = driver.find_element_by_id('selected-words')
-        word = random.choice(essay_content.split())
-        while 'font>' in word or 'br>' in word or 'p>' in word or len(word) < 6 or has_punctuation(word):
-            word = random.choice(essay_content.split())
+        username, password = signup(URL, driver) # sign up a new account and automatically log in
+        time.sleep(1)

+        # enter the word in the text area
+        elem = driver.find_element_by_id('selected-words')
+        word = 'devour'
        elem.send_keys(word)

-        elem = driver.find_element_by_xpath('//form[1]//input[1]') # 找到get所有词频按钮
-        elem.click()
-    
-        elems = driver.find_elements_by_xpath("//input[@type='checkbox']")
-        for elem in elems:
-            if elem.get_attribute('name') == 'marked':
-                elem.click()
-    
-        elem = driver.find_element_by_name('add-btn') # 找到加入我的生词簿按钮
+        elem = driver.find_element_by_xpath('//form[1]//button[1]') # 找到"把生词加入我的生词库"按钮
+        elem.click()
+
+        elem = driver.find_element_by_name('add-btn') # 找到"加入我的生词簿"按钮
        elem.click()

-        driver.refresh()
-        driver.refresh()
-        driver.refresh()        
        elems = driver.find_elements_by_xpath("//p[@class='new-word']/a")
-    
+
        found = 0
        for elem in elems:
            if word in elem.text:
                found = 1
                break
-    
+
        assert found == 1
-    finally:    
+    finally:
        driver.quit()
--- a/app/test/test_bug528_tangjiao.py
+++ b/app/test/test_bug528_tangjiao.py
@ -0,0 +1,95 @@
+import pytest
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import NoSuchElementException, TimeoutException
+
+
+# 测试登录页面输入密码包含空格的情况
+def test_login_password_with_space(driver, URL):
+    try:
+        driver.get(URL+"/login")
+
+        # 输入用户名
+        username_elem = driver.find_element_by_id('username')
+        username_elem.send_keys("test_user")
+
+        # 输入包含空格的密码
+        password_elem = driver.find_element_by_id('password')
+        password_elem.send_keys("password with space")
+
+        # 提交登录表单
+        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
+        elem.click()
+
+        # 显式等待直到警告框出现
+        WebDriverWait(driver, 10).until(EC.alert_is_present())
+
+        # 检查是否弹出警告框
+        alert = driver.switch_to.alert
+        assert "输入不能包含空格!" in alert.text
+    except (NoSuchElementException, TimeoutException) as e:
+        pytest.fail("页面元素未找到或超时: {}".format(e))
+
+
+# 测试注册页面输入密码包含空格的情况
+
+def test_signup_password_with_space(driver, URL):
+    try:
+        driver.get(URL+"/signup")
+
+        # 输入用户名
+        username_elem = driver.find_element_by_id('username')
+        username_elem.send_keys("new_user")
+
+        # 输入包含空格的密码
+        password_elem = driver.find_element_by_id('password')
+        password_elem.send_keys("password with space")
+
+        # 再次输入密码
+        password2_elem = driver.find_element_by_id('password2')
+        password2_elem.send_keys("password with space")
+
+        # 提交注册表单
+        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
+        elem.click()
+
+        # 显式等待直到警告框出现
+        WebDriverWait(driver, 10).until(EC.alert_is_present())
+
+        # 检查是否弹出警告框
+        alert = driver.switch_to.alert
+        assert "输入不能包含空格!" in alert.text
+    except (NoSuchElementException, TimeoutException) as e:
+        pytest.fail("页面元素未找到或超时: {}".format(e))
+
+
+
+# 测试重设密码页面输入新密码包含空格的情况
+
+def test_reset_password_with_space(driver, URL):
+    try:
+        driver.get(URL+"/reset")
+
+        # 输入用户名
+        username_elem = driver.find_element_by_id('username')
+        username_elem.send_keys("test_user")
+
+        # 输入包含空格的密码
+        password_elem = driver.find_element_by_id('password')
+        password_elem.send_keys("password with space")
+
+        # 提交重设密码表单
+        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
+        elem.click()
+
+        # 显式等待直到警告框出现
+        WebDriverWait(driver, 10).until(EC.alert_is_present())
+
+        # 检查是否弹出警告框
+        alert = driver.switch_to.alert
+        assert "输入不能包含空格!" in alert.text
+    except (NoSuchElementException, TimeoutException) as e:
+        pytest.fail("页面元素未找到或超时: {}".format(e))
--- a/app/test/test_bug544_tangxinyuan.py
+++ b/app/test/test_bug544_tangxinyuan.py
@ -0,0 +1,55 @@
+import random
+import string
+import time
+
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+
+from helper import signup
+
+
+def has_punctuation(s):
+    return any(c in string.punctuation for c in s)
+
+
+def login(driver, home, uname, password):
+    driver.get(home)
+    WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.LINK_TEXT, '登录'))).click()
+    driver.find_element(By.ID, 'username').send_keys(uname)
+    driver.find_element(By.ID, 'password').send_keys(password)
+    driver.find_element(By.XPATH, '//button[text()="登录"]').click()
+    WebDriverWait(driver, 10).until(EC.title_is(f"EnglishPal Study Room for {uname}"))
+
+
+def select_valid_word(driver):
+    elem = driver.find_element(By.ID, 'text-content')
+    essay_content = elem.text
+    valid_word = random.choice([word for word in essay_content.split() if len(word) >= 6 and not has_punctuation(
+        word) and 'font>' not in word and 'br>' not in word and 'p>' not in word])
+    driver.find_element(By.ID, 'selected-words').send_keys(valid_word)
+    return valid_word
+
+
+def test_save_selected_word(driver, URL):
+    try:
+        username, password = signup(URL, driver)
+        word = select_valid_word(driver)
+        stored_words = driver.execute_script('return localStorage.getItem("selectedWords");')
+        assert word == stored_words, "Selected word not saved to localStorage correctly"
+        # 退出并重新登录以检查存储的单词
+        driver.find_element(By.LINK_TEXT, '退出').click()
+        driver.execute_script("window.open('');window.close();")
+
+        # 等待一会儿，让浏览器有足够的时间关闭标签页
+        WebDriverWait(driver, 2)
+
+        # 重新打开一个新的标签页
+        driver.execute_script("window.open('');")
+        driver.switch_to.window(driver.window_handles[-1])  # 切换到新打开的标签页
+
+        login(driver, URL, username, password)
+        textarea_content = driver.find_element(By.ID, 'selected-words').get_attribute('value')
+        assert word == textarea_content, "Selected word not preserved after re-login"
+    finally:
+        driver.quit()
--- a/app/test/test_bug545_HuangHuiLing.py
+++ b/app/test/test_bug545_HuangHuiLing.py
@ -0,0 +1,44 @@
+import random
+import string
+import time
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.common.action_chains import ActionChains
+
+from helper import signup
+
+def has_punctuation(s):
+    return any(c in string.punctuation for c in s)
+
+def select_one(driver):
+    elem = driver.find_element(By.ID, 'article')
+    essay_content = elem.text
+    valid_word = random.choice([word for word in essay_content.split() if len(word) >= 6 and not has_punctuation(
+        word) and 'font>' not in word and 'br>' not in word and 'p>' not in word])
+    driver.find_element(By.ID, 'selected-words').send_keys(valid_word)
+    driver.find_element(By.ID, 'article').click()
+    return valid_word
+
+def select_two(driver):
+    word = driver.find_element(By.CLASS_NAME, 'highlighted')
+
+    # 创建ActionChains对象
+    actions = ActionChains(driver)
+    actions.move_to_element(word)
+
+    # 模拟鼠标按下并拖动以选择文本
+    actions.double_click()
+    actions.perform()
+
+
+def test_selected_second_word(driver, URL):
+    try:
+        signup(URL, driver)
+        selected_words = select_one(driver);
+        assert selected_words.strip() != "", "选中的单词被放置框中"
+        select_two(driver)
+        selected_second_words = driver.find_element(By.ID, 'selected-words').get_attribute('value')
+        assert selected_second_words.strip() == "", "选中的单词被删除"
+    finally:
+        driver.quit()
--- a/app/test/test_bug546_lixiaofeng.py
+++ b/app/test/test_bug546_lixiaofeng.py
@ -0,0 +1,39 @@
+from selenium.webdriver.common.action_chains import ActionChains
+from helper import signup
+
+
+def test_highlight(driver, URL):
+    try:
+        # 打开网页
+        driver.get(URL)
+        driver.maximize_window()
+
+        # 注册
+        signup(URL, driver)
+
+        # 取消勾选“划词入库按钮”
+        highlight_checkbox = driver.find_element_by_id("chooseCheckbox")
+        driver.execute_script("arguments[0].click();", highlight_checkbox)
+
+        article = driver.find_element_by_id("article")
+
+        # 创建 ActionChains 对象
+        actions = ActionChains(driver)
+
+        # 移动鼠标到起点位置
+        actions.move_to_element(article)
+        # actions.move_to_element_with_offset(article, 50, 100)
+        # 按下鼠标左键
+        actions.click_and_hold()
+        # 拖动鼠标到结束位置
+        actions.move_by_offset(400,50)
+        # 释放鼠标左键
+        actions.release()
+        # 执行操作链
+        actions.perform()
+        # time.sleep(10)
+
+        assert driver.find_elements_by_class_name("highlighted") is not None
+    finally:
+        # 测试结束后关闭浏览器
+        driver.quit()
--- a/app/test/test_bug551_DingZeYu.py
+++ b/app/test/test_bug551_DingZeYu.py
@ -0,0 +1,37 @@
+import time
+import pytest
+from selenium import webdriver
+from selenium.webdriver import ActionChains
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.alert import Alert
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.wait import WebDriverWait
+from helper import signup
+
+def test_bug551(driver, URL):
+    driver.maximize_window()
+    driver.get(URL)
+
+    username, password = signup(URL, driver)
+
+    article = driver.find_element(By.ID, 'article')
+    actions = ActionChains(driver)
+
+    actions.move_to_element(article)
+    actions.click_and_hold()
+    actions.move_by_offset(450, 200)
+    actions.release()
+    actions.perform()
+
+    # 获取选中高亮部分的单词的元素
+    highlighted_words = driver.find_elements(By.CLASS_NAME, 'highlighted')
+
+    # 验证选中部分的单词是否同时应用了需求样式
+    expected_font_weight = "400"  
+
+    for word in highlighted_words:
+        font_weight = word.value_of_css_property("font-weight")
+        assert font_weight == expected_font_weight, f"选中部分的单词的字体样式错误"
+
+    time.sleep(5)
+    driver.quit()
--- a/app/test/test_bug553_LinShan.py
+++ b/app/test/test_bug553_LinShan.py
@ -0,0 +1,58 @@
+from selenium import webdriver
+from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+from selenium.webdriver.support import expected_conditions as EC
+from selenium import webdriver
+from selenium.webdriver.support.wait import WebDriverWait
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+import logging
+import time
+import pytest
+
+@pytest.mark.parametrize("test_input,expected",
+                         [("‘test1’", "test1"),
+                          ("'test2'", "test2"),
+                          ("“test3”", "test3"),
+                          ("it's", "it's"),
+                          ("hello,I'm linshan", ["hello","i'm","linshan"]),
+                          ("Happy New Year！？", ["happy","new","year"]),
+                          ("My favorite book is 《Harry Potter》。", ["potter","harry","my","favorite","book","is"])])
+def test_bug553_LinShan(test_input,expected, driver, URL):
+    try:
+        # 打开对应地址的网页
+        driver.get(URL)
+
+        # 浏览器最大窗口化
+        driver.maximize_window()
+
+        # 判断网页源代码中是否有English Pal -文字
+        assert 'English Pal -' in driver.page_source
+
+        # 将测试的数据输入到主页的textarea里
+        driver.find_element_by_xpath("//textarea[@name='content']").send_keys(Keys.CONTROL, "a")
+        driver.find_element_by_xpath("//textarea[@name='content']").send_keys(test_input)
+        time.sleep(1)
+
+        # 点击按钮获取单词
+        driver.find_element_by_xpath("//input[@value='get文章中的词频']").click()
+        time.sleep(1)
+
+        # 获取筛选后的单词
+        words = driver.find_elements_by_xpath("//p/a")
+
+        # 遍历获取到的单词，并判断单词与预期的相同
+        for word in words:
+            # 判断单词是否在预期结果中
+            assert word.text in expected
+            
+        # 返回上一页网页
+        driver.find_element_by_xpath("//input[@value='确定并返回']").click()
+        time.sleep(0.1)
+
+    except Exception as e:
+        # 输出异常信息
+        logging.error(e)
+        # 关闭浏览器
+        driver.quit()
+    finally:
+        driver.quit()
--- a/app/test/test_bug561_LiangZiyue.py
+++ b/app/test/test_bug561_LiangZiyue.py
@ -0,0 +1,27 @@
+import random
+import string
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+
+
+def test_bug561_LiangZiyue(driver, URL):
+    try:
+        driver.get(home)
+        WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.LINK_TEXT, '登录'))).click()
+        driver.find_element(By.ID, 'username').send_keys("wrr")
+        driver.find_element(By.ID, 'password').send_keys("1234")
+        driver.find_element(By.XPATH, '//button[text()="登录"]').click()
+        ele = driver.find_element(By.XPATH,'//font[@id="article"]')
+        driver.execute_script('arguments[0].scrollIntoView();',ele)
+        action = ActionChains(driver)
+        action.click_and_hold(ele)
+        action.move_by_offset(0,500)
+        action.perform()
+        next_ele = driver.find_element(By.ID,'//button[@id="load_next_article"]')
+        driver.execute_script('arguments[0].scrollIntoView();',next_ele)
+        next_ele.click()
+        driver.execute_script('arguments[0].scrollIntoView();',ele)
+        ele.click()
+    finally:
+        driver.quit()
--- a/app/test/test_stress.py
+++ b/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()
--- a/app/user_service.py
+++ b/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'
--- a/app/wordfreqCMD.py
+++ b/app/wordfreqCMD.py
@ -4,6 +4,7 @@
 ###########################################################################

 import collections
+import html
 import string
 import operator
 import os, sys # 引入模块sys，因为我要用里面的sys.argv列表中的信息来读取命令行参数。
@ -39,7 +40,8 @@ def file2str(fname):#文件转字符


 def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
-    special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
+    special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|，。？！￥……（）、《》：；·' # 把里面的字符都去掉
+    s = html.unescape(s) # 将HTML实体转换为对应的字符，比如<会被识别为小于号
    for c in special_characters:
        s = s.replace(c, ' ') # 防止出现把 apple,apple 移掉逗号后变成 appleapple 情况
    s = s.replace('--', ' ')
@ -104,7 +106,7 @@ if __name__ == '__main__':
        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'):
--- a/build.sh
+++ b/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