上传文件至 /

修改后的vocabulary.py

app/Article.py

@@ -1,8 +1,14 @@
+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
-import pickle_idea
+import random, glob
+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 UseSqlite import RecordQuery
+
 
 path_prefix = '/var/www/wordfreq/wordfreq/'
 path_prefix = './'  # comment this line in deployment
@@ -27,26 +33,19 @@ def get_article_body(s):
 
 
 def get_today_article(user_word_list, visited_articles):
-    '''
-    根据用户的单词列表和阅读过的文章返回需要的文章的全部信息
-    '''
     rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
     if visited_articles is None:
         visited_articles = {
-            "index": 0,  # 为 article_ids 的索引
+            "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")
     else:  # 生成阅读过的文章，因此查询指定 article_id 的文章
-        # 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
-        if visited_articles["article_ids"][visited_articles["index"]] == 'null':
+        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(
-            f'SELECT * FROM article WHERE article_id='
-            f'{visited_articles["article_ids"][visited_articles["index"]]}'
-        )
+        rq.instructions('SELECT * FROM article WHERE article_id=%d' % (visited_articles["article_ids"][visited_articles["index"]]))
     rq.do()
     result = rq.get_results()
     random.shuffle(result)
@@ -59,23 +58,19 @@ def get_today_article(user_word_list, visited_articles):
     d = None
     result_of_generate_article = "not found"
     d_user = load_freq_history(user_word_list)
-    # 更多的考虑，因为用户的行为是动态的。应考虑时间因素。
-    user_level = user_difficulty_level(d_user, d3)
+    user_level = user_difficulty_level(d_user, d3)  # more consideration as user's behaviour is dynamic. Time factor should be considered.
     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"])
-        amount_of_existing_articles = len(result)
-        # 如果当前阅读过的文章的数量 == 存在的文章的数量，即所有的书本都阅读过了
-        if amount_of_visited_articles == amount_of_existing_articles:
+        amount_of_existing_articles = result.__len__()
+        if amount_of_visited_articles == amount_of_existing_articles:  # 如果当前阅读过的文章的数量 == 存在的文章的数量，即所有的书本都阅读过了
             result_of_generate_article = "had read all articles"
         else:
             for k in range(3):  # 最多尝试3次
                 for reading in result:
                     text_level = text_difficulty_level(reading['text'], d3)
-                    # 从高斯分布中得出的平均值为 0.8，站位偏差为 1 的数字
-                    factor = random.gauss(0.8, 0.1)
-                    # 新的文章之前没有出现过且符合一定范围的水平
-                    if reading['article_id'] not in visited_articles["article_ids"] and within_range(text_level, user_level, (8.0 - user_level) * factor):
+                    factor = random.gauss(0.8, 0.1)  # a number drawn from Gaussian distribution with a mean of 0.8 and a stand deviation of 1
+                    if reading['article_id'] not in visited_articles["article_ids"] and within_range(text_level, user_level, (8.0 - user_level) * factor):  # 新的文章之前没有出现过且符合一定范围的水平
                         d = reading
                         visited_articles["article_ids"].append(d['article_id'])  # 列表添加新的文章id；下面进行
                         result_of_generate_article = "found"
@@ -92,8 +87,8 @@ def get_today_article(user_word_list, visited_articles):
     today_article = None
     if d:
         today_article = {
-            "user_level": f'{user_level:4.2f}',
-            "text_level": f'{text_level:4.2f}',
+            "user_level": '%4.2f' % user_level,
+            "text_level": '%4.2f' % text_level,
             "date": d['date'],
             "article_title": get_article_title(d['text']),
             "article_body": get_article_body(d['text']),

app/Login.py

@@ -1,6 +1,7 @@
 import hashlib
 import string
 from datetime import datetime, timedelta
+from UseSqlite import InsertQuery, RecordQuery
 
 def md5(s):
     '''
@@ -11,13 +12,14 @@ def md5(s):
     h = hashlib.md5(s.encode(encoding='utf-8'))
     return h.hexdigest()
 
-from app.model.user import get_user_by_username, insert_user, update_password_by_username
+# import model.user after the defination of md5(s) to avoid circular import
+from model.user import get_user_by_username, insert_user, update_password_by_username
 
 path_prefix = '/var/www/wordfreq/wordfreq/'
 path_prefix = './'  # comment this line in deployment
 
 def verify_pass(newpass,oldpass):
-    if newpass==oldpass:
+    if(newpass==oldpass):
         return True
 
 
@@ -61,7 +63,8 @@ def get_expiry_date(username):
     user = get_user_by_username(username)
     if user is None:
         return '20191024'
-    return user.expiry_date
+    else:
+        return user.expiry_date
 
 class UserName:
     def __init__(self, username):
@@ -74,7 +77,6 @@ class UserName:
             return 'Period (.) is not allowed as the first letter in the user name.'
         if ' ' in self.username: # a user name must not include a whitespace
             return 'Whitespace is not allowed in the user name.'
-
         for c in self.username: # a user name must not include special characters, except non-leading periods or underscores
             if c in string.punctuation and c != '.' and c != '_':
                 return f'{c} is not allowed in the user name.'
@@ -89,4 +91,5 @@ class WarningMessage:
         self.s = s
 
     def __str__(self):
-        return UserName(self.s).validate()
+        return UserName(self.s).validate()
+

app/WordFreq.py

@@ -2,9 +2,9 @@
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
-import string
-from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
 
+from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
+import string
 
 class WordFreq:
     def __init__(self, s):
@@ -17,7 +17,7 @@ class WordFreq:
             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.')

app/Yaml.py

@@ -6,6 +6,7 @@ Yaml.py
     ./layout/partial/footer.html
 '''
 import yaml as YAML
+import os
 
 path_prefix = './'  # comment this line in deployment
 

app/account_service.py

@@ -1,44 +1,46 @@
-from flask import Blueprint, request, render_template, jsonify,session,redirect, url_for,escape
-from Login import check_username_availability, verify_user, add_user,get_expiry_date, change_password, WarningMessage
+from flask import *
+from Login import check_username_availability, verify_user, add_user, get_expiry_date, change_password, WarningMessage
+
 
 # 初始化蓝图
 accountService = Blueprint("accountService", __name__)
 
-### sign-up, login, logout, reset###
+### Sign-up, login, logout ###
 @accountService.route("/signup", methods=['GET', 'POST'])
 def signup():
     '''
     注册
     :return: 根据注册是否成功返回不同界面
     '''
-    # GET方法直接返回注册页面
     if request.method == 'GET':
+        # GET方法直接返回注册页面
         return render_template('signup.html')
-
-    # POST方法需判断是否注册成功，再根据结果返回不同的内容
-    username = escape(request.form['username'])
-    password = escape(request.form['password'])
-    #! 添加如下代码为了过滤注册时的非法字符
-    warn = WarningMessage(username)
-    if str(warn) != 'OK':
-        return jsonify({'status': '3', 'warn': str(warn)})
-    available = check_username_availability(username)
-    # 用户名不可用
-    if not available:
-        return jsonify({'status': '0'})
-    # 用户名可用,添加账户信息
-    add_user(username, password)
-    verified = verify_user(username, password)
-    # 注册成功，写入session
-    if verified:
-        session['logged_in'] = True
-        session[username] = username
-        session['username'] = username
-        session['expiry_date'] = get_expiry_date(username)
-        session['visited_articles'] = None
-        return jsonify({'status': '2'})
-    # 验证失败
-    return jsonify({'status': '1'})
+    elif request.method == 'POST':
+        # POST方法需判断是否注册成功，再根据结果返回不同的内容
+        username = escape(request.form['username'])
+        password = escape(request.form['password'])
+        
+        #! 添加如下代码为了过滤注册时的非法字符
+        warn = WarningMessage(username)
+        if str(warn) != 'OK':
+            return jsonify({'status': '3', 'warn': str(warn)})
+        
+        available = check_username_availability(username)
+        if not available: # 用户名不可用
+            return jsonify({'status': '0'})
+        else: # 添加账户信息
+            add_user(username, password)
+            verified = verify_user(username, password)
+            if verified:
+                # 写入session
+                session['logged_in'] = True
+                session[username] = username
+                session['username'] = username
+                session['expiry_date'] = get_expiry_date(username)
+                session['visited_articles'] = None
+                return jsonify({'status': '2'})
+            else:
+                return jsonify({'status': '1'})
 
 
 
@@ -48,25 +50,26 @@ def login():
     登录
     :return: 根据登录是否成功返回不同页面
     '''
-    # GET方法直接返回登录页面
     if request.method == 'GET':
+        # GET请求
         return render_template('login.html')
-
-    # POST方法用于判断登录是否成功，检查数据库并验证用户，再根据结果返回不同的内容
-    username = escape(request.form['username'])
-    password = escape(request.form['password'])
-    verified = verify_user(username, password)
-    # 登录成功，写入session
-    if verified:
-        session['logged_in'] = True
-        session[username] = username
-        session['username'] = username
-        user_expiry_date = get_expiry_date(username)
-        session['expiry_date'] = user_expiry_date
-        session['visited_articles'] = None
-        return jsonify({'status': '1'})
-    #验证失败
-    return jsonify({'status': '0'})
+    elif request.method == 'POST':
+        # POST方法用于判断登录是否成功
+        # check database and verify user
+        username = escape(request.form['username'])
+        password = escape(request.form['password'])
+        verified = verify_user(username, password)
+        if verified:
+            # 登录成功，写入session
+            session['logged_in'] = True
+            session[username] = username
+            session['username'] = username
+            user_expiry_date = get_expiry_date(username)
+            session['expiry_date'] = user_expiry_date
+            session['visited_articles'] = None
+            return jsonify({'status': '1'})
+        else:
+            return jsonify({'status': '0'})
 
 
 @accountService.route("/logout", methods=['GET', 'POST'])
@@ -92,18 +95,16 @@ def reset():
     username = session['username']
     if username == '':
         return redirect('/login')
-
-    # GET请求返回修改密码页面
     if request.method == 'GET':
+        # GET请求返回修改密码页面
         return render_template('reset.html', username=session['username'], state='wait')
-
-    # POST请求用于提交修改后信息
-    old_password = escape(request.form['old-password'])
-    new_password = escape(request.form['new-password'])
-    flag = change_password(username, old_password, new_password) # flag表示是否修改成功
-    # 修改成功
-    if flag:
-        session['logged_in'] = False
-        return jsonify({'status':'1'})
-    # 修改失败
-    return jsonify({'status':'2'})
+    else:
+        # POST请求用于提交修改后信息
+        old_password = escape(request.form['old-password'])
+        new_password = escape(request.form['new-password'])
+        flag = change_password(username, old_password, new_password) # flag表示是否修改成功
+        if flag:
+            session['logged_in'] = False
+            return jsonify({'status':'1'})  # 修改成功
+        else:
+            return jsonify({'status':'2'})  # 修改失败

app/admin_service.py

@@ -1,17 +1,17 @@
 # System Library
-from flask import Blueprint, session, render_template, request, flash
+from flask import *
 
 # Personal library
 from Yaml import yml
-from model.user import get_users, update_password_by_username
-from model.user import update_expiry_time_by_username, get_user_by_username
-from model.article import get_number_of_articles, get_page_articles
-from model.article import delete_article_by_id, add_article
+from model.user import *
+from model.article import *
+
 ADMIN_NAME = "lanhui"  # unique admin name
 _cur_page = 1  # current article page
 _page_size = 5  # article sizes per page
 adminService = Blueprint("admin_service", __name__)
 
+
 def check_is_admin():
     # 未登录，跳转到未登录界面
     if not session.get("logged_in"):
@@ -26,10 +26,6 @@ def check_is_admin():
 
 @adminService.route("/admin", methods=["GET"])
 def admin():
-    '''
-    判断是否是管理员登录
-    ：return：不同页面
-    '''
     is_admin = check_is_admin()
     if is_admin != "pass":
         return is_admin
@@ -41,11 +37,6 @@ def admin():
 
 @adminService.route("/admin/article", methods=["GET", "POST"])
 def article():
-    '''
-    管理文章
-    可添加文章、删除文章
-    return:不同页面
-    '''
     global _cur_page, _page_size
 
     is_admin = check_is_admin()
@@ -58,15 +49,16 @@ def article():
             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)
+            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!"
+    
     _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:])
+    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:])
+    
     context = {
         "article_number": _article_number,
         "text_list": _articles,
@@ -80,19 +72,19 @@ def article():
         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]
+        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 ValueError:
+        except:
             return "Delete article ID must be int!"
         if delete_id:  # delete article
             delete_article_by_id(delete_id)
             _update_context()
-    else:
+    elif request.method == "POST":
         data = request.form
         content = data.get("content", "")
         source = data.get("source", "")
@@ -110,21 +102,17 @@ def article():
 
 @adminService.route("/admin/user", methods=["GET", "POST"])
 def user():
-    '''
-    用户管理
-    可修改用户密码，过期日期
-    return：不同页面
-    '''
     is_admin = check_is_admin()
     if is_admin != "pass":
         return is_admin
+    
     context = {
         "user_list": get_users(),
         "username": session.get("username"),
     }
     if request.method == "POST":
         data = request.form
-        username = data.get("username", "")
+        username = data.get("username","")
         new_password = data.get("new_password", "")
         expiry_time = data.get("expiry_time", "")
         if username:
@@ -139,9 +127,6 @@ def user():
 
 @adminService.route("/admin/expiry", methods=["GET"])
 def user_expiry_time():
-    '''
-    返回用户的过期日期
-    '''
     is_admin = check_is_admin()
     if is_admin != "pass":
         return is_admin
@@ -150,7 +135,8 @@ def user_expiry_time():
     if not username:
         return "Username can't be empty."
 
-    existed_user = get_user_by_username(username)
-    if not existed_user:
+    user = get_user_by_username(username)
+    if not user:
         return "User does not exist."
-    return existed_user.expiry_date
+
+    return user.expiry_date

app/difficulty.py

@@ -6,14 +6,15 @@
 # Purpose: compute difficulty level of a English text
 
 import pickle
-import snowballstemmer
+import math
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
-
+import snowballstemmer
 
 
 def load_record(pickle_fname):
-    with open(pickle_fname, 'rb') as f:
-        d = pickle.load(f)
+    f = open(pickle_fname, 'rb')
+    d = pickle.load(f)
+    f.close()
     return d
 
 
@@ -52,7 +53,9 @@ def get_difficulty_level_for_user(d1, d2):
     stemmer = snowballstemmer.stemmer('english')
 
     for k in d1:  # 用户的词
-        if k not in d2:  # 如果用户的词以原型的形式不存在于词库d2中
+        if k in d2:  # 如果用户的词以原型的形式存在于词库d2中
+            continue  # 无需评级，跳过
+        else:
             stem = stemmer.stemWord(k)
             if stem in d2:  # 如果用户的词的词根存在于词库d2的词根库中
                 d2[k] = d2[stem]  # 按照词根进行评级
@@ -85,9 +88,6 @@ def revert_dict(d):
 
 
 def user_difficulty_level(d_user, d):
-    '''
-    得到用户词汇的难度水平
-    '''
     d_user2 = revert_dict(d_user)  # key is date, and value is a list of words added in that date
     count = 0
     geometric = 1
@@ -242,7 +242,10 @@ We need — for our farmers, our manufacturers, for, frankly, unions and non-uni
 '''
 
     # f = open('bbc-fulltext/bbc/entertainment/001.txt')
-    with open('wordlist.txt', encoding='utf-8') as f:
-        s = f.read()
+    f = open('wordlist.txt')
+    s = f.read()
+    f.close()
+
+    print(text_difficulty_level(s, d3))
+
 
-    print(text_difficulty_level(s, d3))

app/main.py

@@ -1,24 +1,17 @@
 #! /usr/bin/python3
 # -*- coding: utf-8 -*-
-import os
-import random
 
 ###########################################################################
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
-import glob
-from flask import Flask, request, redirect, render_template, url_for, escape
-from WordFreq import WordFreq
-import pickle_idea
-from wordfreqCMD import  sort_in_descending_order
-from Article import load_freq_history, total_number_of_essays
+from flask 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
-
-
 app = Flask(__name__)
 app.secret_key = 'lunch.time!'
 
@@ -58,7 +51,8 @@ def appears_in_test(word, d):
     '''
     if not word in d:
         return ''
-    return ','.join(d[word])
+    else:
+        return ','.join(d[word])
 
 
 @app.route("/mark", methods=['GET', 'POST'])
@@ -76,8 +70,8 @@ def mark_word():
         d = pickle_idea.merge_frequency(lst, lst_history)
         pickle_idea.save_frequency_to_pickle(d, path_prefix + 'static/frequency/frequency.p')
         return redirect(url_for('mainpage'))
-    # 不回应GET请求
-    return 'Under construction'
+    else: # 不回应GET请求
+        return 'Under construction'
 
 
 @app.route("/", methods=['GET', 'POST'])
@@ -97,7 +91,7 @@ def mainpage():
         pickle_idea.save_frequency_to_pickle(d, path_prefix + 'static/frequency/frequency.p')
         return render_template('mainpage_post.html', lst=lst, yml=Yaml.yml)
 
-    if request.method == 'GET':  # when we load a html page
+    elif request.method == 'GET':  # when we load a html page
         random_ads = get_random_ads()
         number_of_essays = total_number_of_essays()
         d = load_freq_history(path_prefix + 'static/frequency/frequency.p')

app/pickle_idea.py

@@ -19,15 +19,15 @@ def lst2dict(lst, d):
     for x in lst:
         word = x[0]
         freq = x[1]
-        if word not in d:
-            d[word] = freq
+        if not word in d:
+            d[word] = freq 
         else:
             d[word] += freq
 
 
 def dict2lst(d):
     return list(d.items()) # a list of (key, value) pairs
-
+        
 
 def merge_frequency(lst1, lst2):
     d = {}
@@ -37,27 +37,29 @@ def merge_frequency(lst1, lst2):
 
 
 def load_record(pickle_fname):
-    with open(pickle_fname, 'rb') as f:
-        d = pickle.load(f)
+    f = open(pickle_fname, 'rb')
+    d = pickle.load(f)
+    f.close()
     return d
 
 
 def save_frequency_to_pickle(d, pickle_fname):
-    with open(pickle_fname, 'wb') as f:
-        #exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
-        exclusion_lst = []
-        d2 = {}
-        for k in d:
-            if not k in exclusion_lst and not k.isnumeric() and len(k) > 1:
-                d2[k] = d[k]
-        pickle.dump(d2, f)
+    f = open(pickle_fname, 'wb')
+    #exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
+    exclusion_lst = []
+    d2 = {}
+    for k in d:
+        if not k in exclusion_lst and not k.isnumeric() and len(k) > 1:
+            d2[k] = d[k]
+    pickle.dump(d2, f)
+    f.close()
 
 def unfamiliar(path,word):
-    with open(path,"rb") as f:
-        dic = pickle.load(f)
+    f = open(path,"rb")
+    dic = pickle.load(f)
     dic[word] += [datetime.now().strftime('%Y%m%d%H%M')]
-    with open(path,"wb") as fp:
-        pickle.dump(dic,fp)
+    fp = open(path,"wb")
+    pickle.dump(dic,fp)
 
 def familiar(path,word):
     f = open(path,"rb")
@@ -66,8 +68,8 @@ def familiar(path,word):
         del dic[word][0]
     else:
         dic.pop(word)
-    with open(path,"wb") as f:
-        pickle.dump(dic,f)
+    fp = open(path,"wb")
+    pickle.dump(dic,fp)
 
 if __name__ == '__main__':
 

app/pickle_idea2.py

@@ -33,7 +33,7 @@ def deleteRecord(path,word):
     except KeyError:
         print("sorry")
     with open(path, 'wb') as ff:
-        pickle.dump(db, ff)
+            pickle.dump(db, ff)
 
 def dict2lst(d):
     if len(d) > 0:
@@ -43,7 +43,7 @@ def dict2lst(d):
             for k in d:
                 lst.append((k, [datetime.now().strftime('%Y%m%d%H%M')]))
             return lst
-        if isinstance(d[keys[0]], list):
+        elif isinstance(d[keys[0]], list):
             return list(d.items()) # a list of (key, value) pairs
 
     return []
@@ -56,19 +56,21 @@ def merge_frequency(lst1, lst2):
 
 
 def load_record(pickle_fname):
-    with open(pickle_fname, 'rb') as f:
-        d = pickle.load(f)
+    f = open(pickle_fname, 'rb')
+    d = pickle.load(f)
+    f.close()
     return d
 
 
 def save_frequency_to_pickle(d, pickle_fname):
-    with open(pickle_fname, 'wb') as f:
-        exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
-        d2 = {}
-        for k in d:
-            if not k in exclusion_lst and not k.isnumeric() and not len(k) < 2:
-                d2[k] = list(sorted(d[k])) # 原先这里是d2[k] = list(sorted(set(d[k])))
-        pickle.dump(d2, f)
+    f = open(pickle_fname, 'wb')
+    exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
+    d2 = {}
+    for k in d:
+        if not k in exclusion_lst and not k.isnumeric() and not len(k) < 2:
+            d2[k] = list(sorted(d[k])) # 原先这里是d2[k] = list(sorted(set(d[k])))
+    pickle.dump(d2, f)
+    f.close()
 
 
 
@@ -84,4 +86,4 @@ if __name__ == '__main__':
     d = load_record('frequency.p')
     lst1 = dict2lst(d)
     d = merge_frequency(lst2, lst1)
-    print(d)
+    print(d)

app/static/js/fillword.js

@@ -29,7 +29,3 @@ function onReadClick() {
 function onChooseClick() {
     isChoose = !isChoose;
 }
-
-if (performance.navigation.type == 1) {        //如果网页刷新，停止播放声音
-    Reader.stopRead();
-}

app/static/js/highlight.js

@@ -22,19 +22,33 @@ function getWord() {
 
 function highLight() {
     if (!isHighlight) return;
-    let articleContent = document.getElementById("article").innerText;
+    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 pickedWords = document.getElementById("selected-words");  // words picked to the text area
     let dictionaryWords = document.getElementById("selected-words2"); // words appearing in the user's new words list
-    let allWords = dictionaryWords === null ? pickedWords.value + " " : pickedWords.value + " " + dictionaryWords.value;
-    const list = allWords.split(" "); // 将所有的生词放入一个list中，用于后续处理
+    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
     for (let i = 0; i < list.length; ++i) {
-        list[i] = list[i].replace(/(^\W*)|(\W*$)/g, ""); // 消除单词两边的非单词字符
-        if (list[i] != "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
-            // 返回所有匹配单词的集合, 正则表达式RegExp()中, "\b"匹配一个单词的边界, g 表示全局匹配, i 表示对大小写不敏感。
-            let matches = new Set(articleContent.match(new RegExp("\\b" + list[i] + "\\b", "gi")));
-            for (let word of matches) {
-                // 将文章中所有出现该单词word的地方改为："<mark>" + word + "<mark>"。 
-                articleContent = articleContent.replace(new RegExp("\\b" + word + "\\b", "g"), "<mark>" + word + "</mark>");
+        list[i] = list[i].replace(/(^\s*)|(\s*$)/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>");
             }
         }
     }

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'] %}
@@ -26,12 +28,40 @@
         }
 
         @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); }
+            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;
+        }
+
+        .arrow {
+            padding: 0;
+            font-size: 20px;
+            line-height: 21px;
+            display: inline-block;
+        }
+
+        .arrow:hover {
+            cursor: pointer;
+        }
+
     </style>
 </head>
 <body>
@@ -39,53 +69,70 @@
     <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 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();Reader.stopRead()"> 下一篇 Next Article </button>
-        <button class="btn btn-success" id="load_pre_article" onclick="load_pre_article();Reader.stopRead()" > 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>
-                <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/>
-            <p><small class="text-muted" id="source">{{ today_article['source'] }}</small></p><br/>
-            <p><b id="question">{{ today_article['question'] }}</b></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><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" onclick="toggleHighlighting()" checked/>生词高亮
-    <input type="checkbox" onclick="onReadClick()" checked/>大声朗读
-    <input type="checkbox" onclick="onChooseClick()" checked/>划词入库
+    <input type="checkbox" id="highlightCheckbox" onclick="toggleHighlighting()"/>生词高亮
+    <input type="checkbox" id="readCheckbox" onclick="onReadClick()"/>大声朗读
+    <input type="checkbox" id="chooseCheckbox" onclick="onChooseClick()"/>划词入库
     <div class="range">
         <div class="field">
             <div class="sliderValue">
@@ -97,8 +144,8 @@
     <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" onclick="Reader.stopRead()"/>
-        <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" onclick="clearSelectedWords()">清除</button>
     </form>
     {% if session.get['thisWord'] %}
         <script type="text/javascript">
@@ -113,7 +160,7 @@
 
     {% if d_len > 0 %}
         <p>
-            <b>我的生词簿</b> 
+            <b>我的生词簿</b>
             <label for="move_dynamiclly">
                 <input type="checkbox" name="move_dynamiclly" id="move_dynamiclly" checked>
                 允许动态调整顺序
@@ -126,9 +173,10 @@
                 {% 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>
@@ -147,60 +195,127 @@
     {% endfor %}
 {% endif %}
 <script type="text/javascript">
-    function load_next_article(){
+    window.onload = function () { // 页面加载时执行
+        const settings = {
+            // initialize settings from localStorage
+            highlightChecked: localStorage.getItem('highlightChecked') !== 'false', // localStorage stores strings, default to true. same below
+            readChecked: localStorage.getItem('readChecked') !== 'false',
+            chooseChecked: localStorage.getItem('chooseChecked') !== 'false',
+            rangeValue: localStorage.getItem('rangeValue') || '1',
+            selectedWords: localStorage.getItem('selectedWords') || ''
+        };
+
+        const elements = {
+            highlightCheckbox: document.querySelector('#highlightCheckbox'),
+            readCheckbox: document.querySelector('#readCheckbox'),
+            chooseCheckbox: document.querySelector('#chooseCheckbox'),
+            rangeComponent: document.querySelector('#rangeComponent'),
+            rangeValueDisplay: document.querySelector('#rangeValue'),
+            selectedWordsInput: document.querySelector('#selected-words')
+        };
+        // 应用设置到页面元素
+        elements.highlightCheckbox.checked = settings.highlightChecked;
+        elements.readCheckbox.checked = settings.readChecked;
+        elements.chooseCheckbox.checked = settings.chooseChecked;
+        elements.rangeComponent.value = settings.rangeValue;
+        elements.rangeValueDisplay.textContent = `${settings.rangeValue}x`;
+        elements.selectedWordsInput.value = settings.selectedWords;
+
+        // 刷新页面或进入页面时判断，若不是首篇文章，则上一篇按钮可见
+        if (sessionStorage.getItem('pre_page_button') !== 'display' && sessionStorage.getItem('pre_page_button')) {
+            $('#load_pre_article').show();
+        }
+
+        // 事件监听器
+        elements.selectedWordsInput.addEventListener('input', () => {
+            localStorage.setItem('selectedWords', elements.selectedWordsInput.value);
+        });
+
+        elements.rangeComponent.addEventListener('input', () => {
+            const rangeValue = elements.rangeComponent.value;
+            elements.rangeValueDisplay.textContent = `${rangeValue}x`;
+            localStorage.setItem('rangeValue', rangeValue);
+        });
+    };
+
+    function clearSelectedWords() {
+        localStorage.removeItem('selectedWords');
+        document.querySelector('#selected-words').value = '';
+    }
+
+
+    function load_next_article() {
+        $("#load_next_article").prop("disabled", true)
         $.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){
-        $('#user-level').html(today_article['user_level']);
+
+    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);
+        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)){
+
+    <!-- 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();
-        }else{
+            sessionStorage.setItem('pre_page_button', 'display')
+        } 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();

app/test/test_next_article.py

@@ -0,0 +1,85 @@
+''' Contributed by Lin Junhong et al. 2023-06.'''
+
+from selenium import webdriver
+from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import UnexpectedAlertPresentException, NoAlertPresentException
+import random, time
+import string
+
+# 初始化webdriver
+# driver = webdriver.Remote('http://localhost:4444/wd/hub', DesiredCapabilities.CHROME)
+# driver.implicitly_wait(10)
+driver = webdriver.Chrome("C:\\Users\\12993\AppData\Local\Programs\Python\Python38\\chromedriver.exe")
+
+
+def test_next_article():
+    try:
+        driver.get("http://118.25.96.118:90")
+        assert 'English Pal -' in driver.page_source
+        # login
+        elem = driver.find_element_by_link_text('登录')
+        elem.click()
+
+        uname = 'abcdefg'
+        password = 'abcdefg'
+        elem = driver.find_element_by_id('username')
+        elem.send_keys(uname)
+
+        elem = driver.find_element_by_id('password')
+        elem.send_keys(password)
+        elem = driver.find_element_by_xpath('/html/body/div/button')  # 找到登录按钮
+        elem.click()
+
+        time.sleep(0.5)
+        assert 'EnglishPal Study Room for ' + uname in driver.title
+        for i in range(50):
+            time.sleep(0.1)
+            # 找到固定按钮
+            elem = driver.find_element_by_xpath('//*[@id="load_next_article"]')
+            elem.click()
+    except Exception as e:
+        print(e)
+
+
+def test_local_next_article():
+    try:
+        driver.get("http://127.0.0.1:5000")
+        assert 'English Pal -' in driver.page_source
+        # login
+        elem = driver.find_element_by_link_text('注册')
+        elem.click()
+
+        uname = 'abcdefg'
+        password = 'abcdefg'
+        elem = driver.find_element_by_id('username')
+        elem.send_keys(uname)
+
+        elem = driver.find_element_by_id('password')
+        elem.send_keys(password)
+
+        elem = driver.find_element_by_id('password2')
+        elem.send_keys(password)
+
+        time.sleep(0.5)
+
+        elem = driver.find_element_by_class_name('btn')  # 找到提交按钮
+        elem.click()
+        time.sleep(0.5)
+        try:
+            WebDriverWait(driver, 1).until(EC.alert_is_present())
+            driver.switch_to.alert.accept()
+        except (UnexpectedAlertPresentException, NoAlertPresentException):
+            pass
+
+        time.sleep(0.5)
+        assert 'EnglishPal Study Room for ' + uname in driver.title
+        for i in range(50):
+            time.sleep(0.1)
+            # 找到固定按钮
+            elem = driver.find_element_by_xpath('//*[@id="load_next_article"]')
+            elem.click()
+    except Exception as e:
+        print(e)

app/user_service.py

@@ -1,10 +1,17 @@
 from datetime import datetime
-from flask import render_template, session, url_for, redirect, request, json, escape, Blueprint
 from admin_service import ADMIN_NAME
+from flask import *
+
+# from app import Yaml
+# from app.Article import get_today_article, load_freq_history
+# from app.WordFreq import WordFreq
+# from app.wordfreqCMD import sort_in_descending_order
+
 import Yaml
 from Article import get_today_article, load_freq_history
 from WordFreq import WordFreq
 from wordfreqCMD import sort_in_descending_order
+
 import pickle_idea
 import pickle_idea2
 
@@ -16,7 +23,7 @@ path_prefix = './'  # comment this line in deployment
 
 @userService.route("/get_next_article/<username>",methods=['GET','POST'])
 def get_next_article(username):
-    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_{username}.pickle'
+    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
     session['old_articleID'] = session.get('articleID')
     if request.method == 'GET':
         visited_articles = session.get("visited_articles")
@@ -37,7 +44,7 @@ def get_next_article(username):
 
 @userService.route("/get_pre_article/<username>",methods=['GET'])
 def get_pre_article(username):
-    user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
+    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
     if request.method == 'GET':
         visited_articles = session.get("visited_articles")
         if(visited_articles["index"]==0):
@@ -78,7 +85,7 @@ def familiar(username, word):
     :param word:
     :return:
     '''
-    user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
+    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
     pickle_idea.familiar(user_freq_record, word)
     session['thisWord'] = word  # 1. put a word into session
     session['time'] = 1
@@ -93,7 +100,7 @@ def deleteword(username, word):
     :param word: 单词
     :return: 重定位到用户界面
     '''
-    user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
+    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
     pickle_idea2.deleteRecord(user_freq_record, word)
     # 模板userpage_get.html中删除单词是异步执行，而flash的信息后续是同步执行的，所以注释这段代码；同时如果这里使用flash但不提取信息，则会影响 signup.html的显示。bug复现：删除单词后，点击退出，点击注册，注册页面就会出现提示信息
     # flash(f'{word} is no longer in your word list.')
@@ -119,7 +126,7 @@ def userpage(username):
     # 获取session里的用户名
     username = session.get('username')
 
-    user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
+    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'])
@@ -127,7 +134,7 @@ def userpage(username):
         lst = f.get_freq()
         return render_template('userpage_post.html',username=username,lst = lst, yml=Yaml.yml)
 
-    if request.method == 'GET':  # when we load a html page
+    elif request.method == 'GET':  # when we load a html page
         d = load_freq_history(user_freq_record)
         lst = pickle_idea2.dict2lst(d)
         lst2 = []
@@ -160,7 +167,7 @@ def user_mark_word(username):
     :return: 重定位到用户界面
     '''
     username = session[username]
-    user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
+    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
     if request.method == 'POST':
         # 提交标记的单词
         d = load_freq_history(user_freq_record)
@@ -171,11 +178,13 @@ def user_mark_word(username):
         d = pickle_idea2.merge_frequency(lst, lst_history)
         pickle_idea2.save_frequency_to_pickle(d, user_freq_record)
         return redirect(url_for('user_bp.userpage', username=username))
-    return 'Under construction'
+    else:
+        return 'Under construction'
 
 def get_time():
     '''
     获取当前时间
     :return: 当前时间
     '''
-    return datetime.now().strftime('%Y%m%d%H%M')  # upper to minutes
+    return datetime.now().strftime('%Y%m%d%H%M')  # upper to minutes
+

app/wordfreqCMD.py

@@ -5,8 +5,8 @@
 
 import collections
 import string
-import os
-import 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 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 pickle_idea
 
 def freq(fruit):
@@ -18,7 +18,7 @@ def freq(fruit):
     '''
 
     result = []
-
+    
     fruit = fruit.lower() # 字母转小写
     flst = fruit.split()  # 字符串转成list
     c = collections.Counter(flst)
@@ -32,18 +32,19 @@ def youdao_link(s): # 有道链接
 
 
 def file2str(fname):#文件转字符
-    with open(fname, encoding="utf-8") as f:
-        s = f.read()
+    f = open(fname) #打开
+    s = f.read()    #读取
+    f.close()       #关闭
     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 = r'\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
+    special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 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('--', ' ')
     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
@@ -77,10 +78,11 @@ def make_html_page(lst, fname):  # 只是在wordfreqCMD.py中的main函数中调
     count = 1
     for x in lst:
         # <a href="">word</a>
-        s += f'<p>{count} <a href="{youdao_link(x[0])}">{x[0]}</a> ({x[1]})</p>'
+        s += '<p>%d <a href="%s">%s</a> (%d)</p>' % (count, youdao_link(x[0]), x[0], x[1])
         count += 1
-    with open(fname, 'w', encoding="utf-8") as f:
-        f.write(s)
+    f = open(fname, 'w')
+    f.write(s)
+    f.close()
 
 
 ## main（程序入口）
@@ -99,10 +101,10 @@ if __name__ == '__main__':
     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(f'{x[0]}\t{x[1]}\t{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'):
@@ -116,3 +118,6 @@ if __name__ == '__main__':
     lst_history = pickle_idea.dict2lst(d)
     d = pickle_idea.merge_frequency(L, lst_history)
     pickle_idea.save_frequency_to_pickle(d, 'frequency.p')
+
+
+

requirements.txt

@@ -1,5 +1,8 @@
-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
+
+pytest~=8.1.1

test_vocabulary.py

@@ -0,0 +1,94 @@
+# Run this test script on the command line:
+#   pytest test_vocabulary.py
+#
+# Last modified by Mr Lan Hui on 2025-03-05
+
+from vocabulary import UserVocabularyLevel, ArticleVocabularyLevel
+
+
+def test_article_level_empty_content():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel('')
+    assert article.level == 0
+
+def test_article_level_punctuation_only():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel(',')
+    assert article.level == 0
+
+def test_article_level_digit_only():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel('1')
+    assert article.level == 0
+    
+def test_article_level_single_word():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel('source')
+    assert 2 <= article.level <= 4
+
+def test_article_level_subset_vs_superset():
+    ''' Boundary case test '''
+    article1 = ArticleVocabularyLevel('source')
+    article2 = ArticleVocabularyLevel('open source')
+    assert article1.level < article2.level
+    
+def test_article_level_multiple_words():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel('Producing Open Source Software - How to Run a Successful Free Software Project')
+    assert 3 <= article.level <= 5
+
+def test_article_level_short_paragraph():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel('At parties, people no longer give me a blank stare when I tell them I work in open source software. "Oh, yes — like Linux?" they say. I nod eagerly in agreement. "Yes, exactly! That\'s what I do." It\'s nice not to be completely fringe anymore. In the past, the next question was usually fairly predictable: "How do you make money doing that?" To answer, I\'d summarize the economics of free software: that there are organizations in whose interest it is to have certain software exist, but that they don\'t need to sell copies, they just want to make sure the software is available and maintained, as a tool instead of as a rentable monopoly.')
+    assert 4 <= article.level <= 6
+
+def test_article_level_medium_paragraph():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel('In considering the Origin of Species, it is quite conceivable that a naturalist, reflecting on the mutual affinities of organic beings, on their embryological relations, their geographical distribution, geological succession, and other such facts, might come to the conclusion that each species had not been independently created, but had descended, like varieties, from other species. Nevertheless, such a conclusion, even if well founded, would be unsatisfactory, until it could be shown how the innumerable species inhabiting this world have been modified, so as to acquire that perfection of structure and coadaptation which most justly excites our admiration. Naturalists continually refer to external conditions, such as climate, food, etc., as the only possible cause of variation. In one very limited sense, as we shall hereafter see, this may be true; but it is preposterous to attribute to mere external conditions, the structure, for instance, of the woodpecker, with its feet, tail, beak, and tongue, so admirably adapted to catch insects under the bark of trees. In the case of the misseltoe, which draws its nourishment from certain trees, which has seeds that must be transported by certain birds, and which has flowers with separate sexes absolutely requiring the agency of certain insects to bring pollen from one flower to the other, it is equally preposterous to account for the structure of this parasite, with its relations to several distinct organic beings, by the effects of external conditions, or of habit, or of the volition of the plant itself.')
+    assert 5 <= article.level <= 7
+    
+def test_article_level_long_paragraph():
+    ''' Boundary case test '''
+    article = ArticleVocabularyLevel('These several facts accord well with my theory. I believe in no fixed law of development, causing all the inhabitants of a country to change abruptly, or simultaneously, or to an equal degree. The process of modification must be extremely slow. The variability of each species is quite independent of that of all others. Whether such variability be taken advantage of by natural selection, and whether the variations be accumulated to a greater or lesser amount, thus causing a greater or lesser amount of modification in the varying species, depends on many complex contingencies,—on the variability being of a beneficial nature, on the power of intercrossing, on the rate of breeding, on the slowly changing physical conditions of the country, and more especially on the nature of the other inhabitants with which the varying species comes into competition. Hence it is by no means surprising that one species should retain the same identical form much longer than others; or, if changing, that it should change less. We see the same fact in geographical distribution; for instance, in the land-shells and coleopterous insects of Madeira having come to differ considerably from their nearest allies on the continent of Europe, whereas the marine shells and birds have remained unaltered. We can perhaps understand the apparently quicker rate of change in terrestrial and in more highly organised productions compared with marine and lower productions, by the more complex relations of the higher beings to their organic and inorganic conditions of life, as explained in a former chapter. When many of the inhabitants of a country have become modified and improved, we can understand, on the principle of competition, and on that of the many all-important relations of organism to organism, that any form which does not become in some degree modified and improved, will be liable to be exterminated. Hence we can see why all the species in the same region do at last, if we look to wide enough intervals of time, become modified; for those which do not change will become extinct.')
+    assert 6 <= article.level <= 8
+    
+def test_user_level_empty_dictionary():
+    ''' Boundary case test '''
+    user = UserVocabularyLevel({})
+    assert user.level == 0
+
+def test_user_level_one_simple_word():
+    ''' Boundary case test '''
+    user = UserVocabularyLevel({'simple':['202408050930']})
+    assert 0 < user.level <= 4
+    
+def test_user_level_invalid_word():
+    ''' Boundary case test '''
+    user = UserVocabularyLevel({'xyz':['202408050930']})
+    assert user.level == 0
+ 
+def test_user_level_one_hard_word():
+    ''' Boundary case test '''
+    user = UserVocabularyLevel({'pasture':['202408050930']})
+    assert 5 <= user.level <= 8
+ 
+def test_user_level_multiple_words():
+    ''' Boundary case test '''
+    user = UserVocabularyLevel(
+        {'sessile': ['202408050930'], 'putrid': ['202408050930'], 'prodigal': ['202408050930'], 'presumptuous': ['202408050930'], 'prehension': ['202408050930'], 'pied': ['202408050930'], 'pedunculated': ['202408050930'], 'pasture': ['202408050930'], 'parturition': ['202408050930'], 'ovigerous': ['202408050930'], 'ova': ['202408050930'], 'orifice': ['202408050930'], 'obliterate': ['202408050930'], 'niggard': ['202408050930'], 'neuter': ['202408050930'], 'locomotion': ['202408050930'], 'lineal': ['202408050930'], 'glottis': ['202408050930'], 'frivolous': ['202408050930'], 'frena': ['202408050930'], 'flotation': ['202408050930'], 'ductus': ['202408050930'], 'dorsal': ['202408050930'], 'dearth': ['202408050930'], 'crustacean': ['202408050930'], 'cornea': ['202408050930'], 'contrivance': ['202408050930'], 'collateral': ['202408050930'], 'cirriped': ['202408050930'], 'canon': ['202408050930'], 'branchiae': ['202408050930'], 'auditory': ['202408050930'], 'articulata': ['202408050930'], 'alimentary': ['202408050930'], 'adduce': ['202408050930'], 'aberration': ['202408050930']}        
+    )
+    assert 6 <= user.level <= 8
+ 
+def test_user_level_consider_only_most_recent_words_difficult_words_most_recent():
+    ''' Consider only the most recent three words '''
+    user = UserVocabularyLevel(
+        {'pasture':['202408050930'], 'putrid': ['202408040000'], 'frivolous':['202408030000'], 'simple':['202408020000'], 'apple':['202408010000']}
+    )
+    assert 5 <= user.level <= 8
+ 
+def test_user_level_consider_only_most_recent_words_easy_words_most_recent():
+    ''' Consider only the most recent three words '''
+    user = UserVocabularyLevel(
+        {'simple':['202408050930'], 'apple': ['202408040000'], 'happy':['202408030000'], 'pasture':['202408020000'], 'putrid':['202408010000'], 'dearth':['202407310000']}
+    )
+    assert 4 <= user.level <= 5