Merge pull request 'WIP：Bug529-GuHan' (#88) from Bug529-GuHan into master

Reviewed-on: http://121.4.94.30:3000/mrlan/EnglishPal/pulls/88

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

@@ -49,8 +49,8 @@
 {#        <div class="alert alert-warning" role="alert">Congratulations! {{ message }}</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="btn btn-success" id="load_next_article" onclick="load_next_article()"> 下一篇 Next Article </button>
+        <button class="btn btn-success" id="load_pre_article" onclick="load_pre_article()" > 上一篇 Previous Article </button>
 
     <p><b>阅读文章并回答问题</b></p>
     <div id="text-content">
@@ -97,7 +97,7 @@
     <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="submit" value="把生词加入我的生词库"/>
         <input type="reset" value="清除"/>
     </form>
     {% if session.get['thisWord'] %}

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')
+
+
+