合并最新的Alpha-snapshot20230529

app/Article.py

@@ -7,7 +7,7 @@ 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, text_difficulty_level, user_difficulty_level
+from difficulty import get_difficulty_level_for_user, text_difficulty_level, user_difficulty_level
 
 
 path_prefix = '/var/www/wordfreq/wordfreq/'
@@ -32,17 +32,20 @@ def get_article_body(s):
     return '\n'.join(lst)
 
 
-def get_today_article(user_word_list, existing_articles):
+def get_today_article(user_word_list, visited_articles):
     rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
-    if existing_articles is None:
+    if visited_articles is None:
-        existing_articles = {
+        visited_articles = {
             "index" : 0,  # 为 article_ids 的索引
             "article_ids": []  # 之前显示文章的id列表，越后越新
         }
-    if existing_articles["index"] > len(existing_articles["article_ids"])-1:
+    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:
+    else:  # 生成阅读过的文章，因此查询指定 article_id 的文章
-        rq.instructions('SELECT * FROM article WHERE article_id=%d' % (existing_articles["article_ids"][existing_articles["index"]]))
+        if visited_articles["article_ids"][visited_articles["index"]] == 'null':  # 可能因为直接刷新页面导致直接去查询了'null'，因此当刷新的页面的时候，需要直接进行“上一篇”操作
+            visited_articles["index"] -= 1
+            visited_articles["article_ids"].pop()
+        rq.instructions('SELECT * FROM article WHERE article_id=%d' % (visited_articles["article_ids"][visited_articles["index"]]))
     rq.do()
     result = rq.get_results()
     random.shuffle(result)
@@ -50,28 +53,36 @@ def get_today_article(user_word_list, existing_articles):
     # Choose article according to reader's level
     d1 = load_freq_history(path_prefix + 'static/frequency/frequency.p')
     d2 = load_freq_history(path_prefix + 'static/words_and_tests.p')
-    d3 = get_difficulty_level(d1, d2)
+    d3 = get_difficulty_level_for_user(d1, d2)
 
     d = None
+    result_of_generate_article = "not found"
     d_user = load_freq_history(user_word_list)
     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 existing_articles["index"] > len(existing_articles["article_ids"])-1:  # 下一篇
+    if visited_articles["index"] > len(visited_articles["article_ids"])-1:  # 生成新的文章
-        flag_get_article = False
+        amount_of_visited_articles = len(visited_articles["article_ids"])
-        for reading in result:
+        amount_of_existing_articles = result.__len__()
-            text_level = text_difficulty_level(reading['text'], d3)
+        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
-            factor = random.gauss(0.8,
+            result_of_generate_article = "had read all articles"
-                                  0.1)  # a number drawn from Gaussian distribution with a mean of 0.8 and a stand deviation of 1
+        else:
-            if reading['article_id'] not in existing_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
+            for k in range(3):  # 最多尝试3次
-                d = reading
+                for reading in result:
-                existing_articles["article_ids"].append(d['article_id'])  # 列表添加新的文章id；下面进行
+                    text_level = text_difficulty_level(reading['text'], d3)
-                flag_get_article = True
+                    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
-                break
+                    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
-        if not flag_get_article:
+                        d = reading
-            existing_articles["index"] -= 1
+                        visited_articles["article_ids"].append(d['article_id'])  # 列表添加新的文章id；下面进行
-    else:  # 上一篇
+                        result_of_generate_article = "found"
+                        break
+                if result_of_generate_article == "found":  # 用于成功找到文章后及时退出外层循环
+                    break
+        if result_of_generate_article != "found":  # 阅读完所有文章，或者循环3次没有找到适合的文章，则放入空（“null”）
+            visited_articles["article_ids"].append('null')
+    else:  # 生成已经阅读过的文章
         d = random.choice(result)
         text_level = text_difficulty_level(d['text'], d3)
+        result_of_generate_article = "found"
 
     today_article = None
     if d:
@@ -86,7 +97,7 @@ def get_today_article(user_word_list, existing_articles):
             "answer": get_answer_part(d['question'])
         }
 
-    return existing_articles, today_article
+    return visited_articles, today_article, result_of_generate_article
 
 
 def load_freq_history(path):

app/Login.py

@@ -3,6 +3,18 @@ import string
 from datetime import datetime, timedelta
 from UseSqlite import InsertQuery, RecordQuery
 
+def md5(s):
+    '''
+    MD5摘要
+    :param str: 字符串
+    :return: 经MD5以后的字符串
+    '''
+    h = hashlib.md5(s.encode(encoding='utf-8'))
+    return h.hexdigest()
+
+# 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
 
@@ -12,13 +24,9 @@ def verify_pass(newpass,oldpass):
 
 
 def verify_user(username, password):
-    rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
+    user = get_user_by_username(username)
-    password = md5(username + password)
+    encoded_password = md5(username + password)
-    rq.instructions_with_parameters("SELECT * FROM user WHERE name=:username AND password=:password", dict(
+    return user is not None and user.password == encoded_password
-        username=username, password=password))  # the named style https://docs.python.org/3/library/sqlite3.html
-    rq.do_with_parameters()
-    result = rq.get_results()
-    return result != []
 
 
 def add_user(username, password):
@@ -26,19 +34,12 @@ def add_user(username, password):
     expiry_date = (datetime.now() + timedelta(days=30)).strftime('%Y%m%d') # will expire after 30 days
     # 将用户名和密码一起加密，以免暴露不同用户的相同密码
     password = md5(username + password)
-    rq = InsertQuery(path_prefix + 'static/wordfreqapp.db')
+    insert_user(username=username, password=password, start_date=start_date, expiry_date=expiry_date)
-    rq.instructions_with_parameters("INSERT INTO user VALUES (:username, :password, :start_date, :expiry_date)", dict(
-        username=username, password=password, start_date=start_date, expiry_date=expiry_date))
-    rq.do_with_parameters()
 
 
 def check_username_availability(username):
-    rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
+    existed_user = get_user_by_username(username)
-    rq.instructions_with_parameters(
+    return existed_user is None
-        "SELECT * FROM user WHERE name=:username", dict(username=username))
-    rq.do_with_parameters()
-    result = rq.get_results()
-    return result == []
 
 
 def change_password(username, old_password, new_password):
@@ -54,35 +55,16 @@ def change_password(username, old_password, new_password):
     # 将用户名和密码一起加密，以免暴露不同用户的相同密码
     if verify_pass(new_password,old_password): #新旧密码一致
         return False
-    password = md5(username + new_password)
+    update_password_by_username(username, new_password)
-    rq = InsertQuery(path_prefix + 'static/wordfreqapp.db')
-    rq.instructions_with_parameters("UPDATE user SET password=:password WHERE name=:username", dict(
-        password=password, username=username))
-    rq.do_with_parameters()
     return True
 
 
 def get_expiry_date(username):
-    rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
+    user = get_user_by_username(username)
-    rq.instructions_with_parameters(
+    if user is None:
-        "SELECT expiry_date FROM user WHERE name=:username", dict(username=username))
-    rq.do_with_parameters()
-    result = rq.get_results()
-    if len(result) > 0:
-        return result[0]['expiry_date']
-    else:
         return '20191024'
-
+    else:
-
+        return user.expiry_date
-def md5(s):
-    '''
-    MD5摘要
-    :param str: 字符串
-    :return: 经MD5以后的字符串
-    '''
-    h = hashlib.md5(s.encode(encoding='utf-8'))
-    return h.hexdigest()
-
 
 class UserName:
     def __init__(self, username):

app/account_service.py

@@ -37,7 +37,7 @@ def signup():
                 session[username] = username
                 session['username'] = username
                 session['expiry_date'] = get_expiry_date(username)
-                session['existing_articles'] = None
+                session['visited_articles'] = None
                 return jsonify({'status': '2'})
             else:
                 return jsonify({'status': '1'})
@@ -66,7 +66,7 @@ def login():
             session['username'] = username
             user_expiry_date = get_expiry_date(username)
             session['expiry_date'] = user_expiry_date
-            session['existing_articles'] = None
+            session['visited_articles'] = None
             return jsonify({'status': '1'})
         else:
             return jsonify({'status': '0'})

app/admin_service.py

@@ -91,10 +91,7 @@ def article():
         question = data.get("question", "")
         level = data.get("level", "4")
         if content:
-            try:  # check level
+            if level not in ['1', '2', '3', '4']:
-                if level not in ['1', '2', '3', '4']:
-                    raise ValueError
-            except ValueError:
                 return "Level must be between 1 and 4."
             add_article(content, source, level, question)
             _update_context()

app/difficulty.py

@@ -8,6 +8,7 @@
 import pickle
 import math
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
+import snowballstemmer
 
 
 def load_record(pickle_fname):
@@ -17,40 +18,50 @@ def load_record(pickle_fname):
     return d
 
 
-def difficulty_level_from_frequency(word, d):
+def convert_test_type_to_difficulty_level(d):
-    level = 1
+    """
-    if not word in d:
+    对原本的单词库中的单词进行难度评级
-        return level
+    :param d: 存储了单词库pickle文件中的单词的字典
+    :return:
+    """
+    result = {}
+    L = list(d.keys())  # in d, we have test types (e.g., CET4,CET6,BBC) for each word
 
-    if 'what' in d:
+    for k in L:
-        ratio = (d['what']+1)/(d[word]+1) # what is a frequent word
+        if 'CET4' in d[k]:
-        level = math.log( max(ratio, 1), 2)
+            result[k] = 4  # CET4 word has level 4
+        elif 'OXFORD3000' in d[k]:
+            result[k] = 5
+        elif 'CET6' in d[k] or 'GRADUATE' in d[k]:
+            result[k] = 6
+        elif 'OXFORD5000' in d[k] or 'IELTS' in d[k]:
+            result[k] = 7
+        elif 'BBC' in d[k]:
+            result[k] = 8
 
-    level = min(level, 8) 
+    return result  # {'apple': 4, ...}
-    return level
 
 
-def get_difficulty_level(d1, d2):
+def get_difficulty_level_for_user(d1, d2):
-    d = {}
+    """
-    L = list(d1.keys())  # in d1, we have freuqence for each word
+    d2 来自于词库的35511个已标记单词
-    L2 = list(d2.keys()) # in d2, we have test types (e.g., CET4,CET6,BBC) for each word
+    d1 用户不会的词
-    L.extend(L2)
+    在d2的后面添加单词，没有新建一个新的字典
-    L3 = list(set(L)) # L3 contains all words
+    """
-    for k in L3:
+    # TODO: convert_test_type_to_difficulty_level() should not be called every time.  Each word's difficulty level should be pre-computed.
-        if k in d2:
+    d2 = convert_test_type_to_difficulty_level(d2)  # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
-            if 'CET4' in d2[k]:
+    stemmer = snowballstemmer.stemmer('english')
-                d[k] = 4 # CET4 word has level 4
-            elif 'CET6' in d2[k]:
-                d[k] = 6
-            elif 'BBC' in d2[k]:
-                d[k] = 8
-                if k in d1: # BBC could contain easy words that are not in CET4 or CET6.  So 4 is not reasonable.  Recompute difficulty level.
-                    d[k] = min(difficulty_level_from_frequency(k, d1), d[k])
-        elif k in d1:
-            d[k] = difficulty_level_from_frequency(k, d1)
-
-    return d
 
+    for k in d1:  # 用户的词
+        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
+            else:
+                d2[k] = 3  # 如果k的词根都不在，那么就当认为是3级
+    return d2
 
 
 def revert_dict(d):
@@ -62,12 +73,13 @@ def revert_dict(d):
     for k in d:
         if type(d[k]) is list:  # d[k] is a list of dates.
             lst = d[k]
-        elif type(d[k]) is int: # for backward compatibility.  d was sth like {'word':1}.  The value d[k] is not a list of dates, but a number representing how frequent this word had been added to the new word book. 
+        elif type(d[
+                      k]) is int:  # for backward compatibility.  d was sth like {'word':1}.  The value d[k] is not a list of dates, but a number representing how frequent this word had been added to the new word book.
             freq = d[k]
-            lst = freq*['2021082019'] # why choose this date?  No particular reasons.  I fix the bug in this date.
+            lst = freq * ['2021082019']  # why choose this date?  No particular reasons.  I fix the bug in this date.
 
         for time_info in lst:
-            date = time_info[:10] # until hour
+            date = time_info[:10]  # until hour
             if not date in d2:
                 d2[date] = [k]
             else:
@@ -76,42 +88,44 @@ def revert_dict(d):
 
 
 def user_difficulty_level(d_user, d):
-    d_user2 = revert_dict(d_user) # key is date, and value is a list of words added in that date
+    d_user2 = revert_dict(d_user)  # key is date, and value is a list of words added in that date
     count = 0
     geometric = 1
-    for date in sorted(d_user2.keys(), reverse=True): # most recently added words are more important while determining user's level
+    for date in sorted(d_user2.keys(),
-        lst = d_user2[date] # a list of words
+                       reverse=True):  # most recently added words are more important while determining user's level
-        lst2 = [] # a list of tuples, (word, difficulty level)
+        lst = d_user2[date]  # a list of words
-        for  word in lst:
+        lst2 = []  # a list of tuples, (word, difficulty level)
+        for word in lst:
             if word in d:
                 lst2.append((word, d[word]))
 
-        lst3 = sort_in_ascending_order(lst2) # easiest tuple first
+        lst3 = sort_in_ascending_order(lst2)  # easiest tuple first
-        #print(lst3)
+        # print(lst3)
         for t in lst3:
             word = t[0]
             hard = t[1]
-            #print('WORD %s HARD %4.2f' % (word, hard))
+            # print('WORD %s HARD %4.2f' % (word, hard))
             geometric = geometric * (hard)
             count += 1
             if count >= 10:
-                return geometric**(1/count)
+                return geometric ** (1 / count)
 
-    return geometric**(1/max(count,1))
+    return geometric ** (1 / max(count, 1))
 
 
 def text_difficulty_level(s, d):
     s = remove_punctuation(s)
     L = freq(s)
 
-    lst = [] # a list of tuples, each tuple being (word, difficulty level)
+    lst = []  # a list of tuples, each tuple being (word, difficulty level)
+    stop_words = {'the':1, 'and':1, 'of':1, 'to':1, 'what':1, 'in':1, 'there':1, 'when':1, 'them':1, 'would':1, 'will':1, 'out':1, 'his':1, 'mr':1, 'that':1, 'up':1, 'more':1, 'your':1, 'it':1, 'now':1, 'very':1, 'then':1, 'could':1, 'he':1, 'any':1, 'some':1, 'with':1, 'into':1, 'you':1, 'our':1, 'man':1, 'other':1, 'time':1, 'was':1, 'than':1, 'know':1, 'about':1, 'only':1, 'like':1, 'how':1, 'see':1, 'is':1, 'before':1, 'such':1, 'little':1, 'two':1, 'its':1, 'as':1, 'these':1, 'may':1, 'much':1, 'down':1, 'for':1, 'well':1, 'should':1, 'those':1, 'after':1, 'same':1, 'must':1, 'say':1, 'first':1, 'again':1, 'us':1, 'great':1, 'where':1, 'being':1, 'come':1, 'over':1, 'good':1, 'himself':1, 'am':1, 'never':1, 'on':1, 'old':1, 'here':1, 'way':1, 'at':1, 'go':1, 'upon':1, 'have':1, 'had':1, 'without':1, 'my':1, 'day':1, 'be':1, 'but':1, 'though':1, 'from':1, 'not':1, 'too':1, 'another':1, 'this':1, 'even':1, 'still':1, 'her':1, 'yet':1, 'under':1, 'by':1, 'let':1, 'just':1, 'all':1, 'because':1, 'we':1, 'always':1, 'off':1, 'yes':1, 'so':1, 'while':1, 'why':1, 'which':1, 'me':1, 'are':1, 'or':1, 'no':1, 'if':1, 'an':1, 'also':1, 'thus':1, 'who':1, 'cannot':1, 'she':1, 'whether':1} # ignore these words while computing the artile's difficulty level
     for x in L:
         word = x[0]
-        if word in d:
+        if word not in stop_words and word in d:
             lst.append((word, d[word]))
 
-    lst2 = sort_in_descending_order(lst) # most difficult words on top
+    lst2 = sort_in_descending_order(lst)  # most difficult words on top
-    #print(lst2)
+    # print(lst2)
     count = 0
     geometric = 1
     for t in lst2:
@@ -119,24 +133,20 @@ def text_difficulty_level(s, d):
         hard = t[1]
         geometric = geometric * (hard)
         count += 1
-        if count >= 20: # we look for n most difficult words
+        if count >= 20:  # we look for n most difficult words
-            return geometric**(1/count)
+            return geometric ** (1 / count)
-        
-    return geometric**(1/max(count,1))
 
+    return geometric ** (1 / max(count, 1))
 
 
 if __name__ == '__main__':
-
-
     d1 = load_record('frequency.p')
-    #print(d1)
+    # print(d1)
 
     d2 = load_record('words_and_tests.p')
-    #print(d2)
+    # print(d2)
 
-
+    d3 = get_difficulty_level_for_user(d1, d2)
-    d3 = get_difficulty_level(d1, d2)
 
     s = '''
 South Lawn
@@ -197,7 +207,6 @@ Amidst the aftermath of this shocking referendum vote, there is great uncertaint
 
 '''
 
-
     s = '''
 British Prime Minister Boris Johnson walks towards a voting station during the Brexit referendum in Britain, June 23, 2016. (Photo: EPA-EFE)
 
@@ -218,7 +227,6 @@ The prime minister was forced to ask for an extension to Britain's EU departure
 Johnson has repeatedly pledged to finalize the first stage, a transition deal, of Britain's EU divorce battle by Oct. 31. A second stage will involve negotiating its future relationship with the EU on trade, security and other salient issues.
 '''
 
-
     s = '''
 Thank you very much. We have a Cabinet meeting. We’ll have a few questions after grace. And, if you would, Ben, please do the honors.
 
@@ -233,17 +241,11 @@ We need — for our farmers, our manufacturers, for, frankly, unions and non-uni
 
 '''
 
-
+    # f = open('bbc-fulltext/bbc/entertainment/001.txt')
-
-
-    #f = open('bbc-fulltext/bbc/entertainment/001.txt')
     f = open('wordlist.txt')
     s = f.read()
     f.close()
 
-
-
-    
     print(text_difficulty_level(s, d3))
 
 

app/model/user.py

@@ -1,5 +1,6 @@
 from model import *
 from Login import md5
+from pony import orm
 
 def get_users():
     with db_session:
@@ -11,6 +12,11 @@ def get_user_by_username(username):
         if user:
             return user.first()
 
+def insert_user(username, password, start_date, expiry_date):
+    with db_session:
+        user = User(name=username, password=password, start_date=start_date, expiry_date=expiry_date)
+        orm.commit()
+
 def update_password_by_username(username, password="123456"):
     with db_session:
         user = User.select(name=username)

app/pickle_idea2.py

@@ -68,7 +68,7 @@ def save_frequency_to_pickle(d, pickle_fname):
     d2 = {}
     for k in d:
         if not k in exclusion_lst and not k.isnumeric() and not len(k) < 2:
-            d2[k] = list(sorted(set(d[k])))
+            d2[k] = list(sorted(d[k])) # 原先这里是d2[k] = list(sorted(set(d[k])))
     pickle.dump(d2, f)
     f.close()
 

app/static/config.yml

@@ -1,16 +1,17 @@
 # 全局引入的css文件地址
 css:
   item:
-    - static/css/bootstrap.css
+    - ../static/css/bootstrap.css
 
 # 全局引入的js文件地址
 js:
   head: # 在页面加载之前加载
-    - static/js/jquery.js
+    - ../static/js/jquery.js
-    - static/js/word_operation.js
+    - ../static/js/read.js
+    - ../static/js/word_operation.js
   bottom: # 在页面加载完之后加载
-    - static/js/fillword.js
+    - ../static/js/fillword.js
-    - static/js/highlight.js
+    - ../static/js/highlight.js
 
 # 高亮样式，目前仅支持修改颜色
 highlight:

app/static/js/fillword.js

@@ -1,9 +1,5 @@
 let isRead = true;
 let isChoose = true;
-let reader = window.speechSynthesis; // 全局定义朗读者，以便朗读和暂停
-let current_position = 0; // 朗读文本的当前位置
-let original_position = 0; // 朗读文本的初始位置
-let to_speak = ""; // 朗读的初始内容
 
 function getWord() {
     return window.getSelection ? window.getSelection() : document.selection.createRange().text;
@@ -11,7 +7,7 @@ function getWord() {
 
 function fillInWord() {
     let word = getWord();
-    if (isRead) read(word);
+    if (isRead) Reader.read(word, inputSlider.value);
     if (!isChoose) return;
     const element = document.getElementById("selected-words");
     element.value = element.value + " " + word;
@@ -19,53 +15,17 @@ function fillInWord() {
 
 document.getElementById("text-content").addEventListener("click", fillInWord, false);
 
-function makeUtterance(str, rate) {
+const sliderValue = document.getElementById("rangeValue");
-    let msg = new SpeechSynthesisUtterance(str);
+const inputSlider = document.getElementById("rangeComponent");
-    msg.rate = rate;
-    msg.lang = "en-US"; // TODO: add language options menu
-    msg.onboundary = ev => {
-        if (ev.name == "word") {
-            current_position = ev.charIndex;
-        }
-    }
-    return msg;
-}
-
-const sliderValue = document.getElementById("rangeValue"); // 显示值
-const inputSlider = document.getElementById("rangeComponent"); // 滑块元素
 inputSlider.oninput = () => {
-    let value = inputSlider.value; // 获取滑块的值
+    let value = inputSlider.value;
     sliderValue.textContent = value + '×';
-    if (!reader.speaking) return;
-    reader.cancel();
-    let msg = makeUtterance(to_speak.substring(original_position + current_position), value);
-    original_position = original_position + current_position;
-    current_position = 0;
-    reader.speak(msg);
 };
 
-function read(s) {
-    to_speak = s.toString();
-    original_position = 0;
-    current_position = 0;
-    let msg = makeUtterance(to_speak, inputSlider.value);
-    reader.speak(msg);
-}
-
 function onReadClick() {
     isRead = !isRead;
-    if (!isRead) {
-        reader.cancel();
-    }
 }
 
 function onChooseClick() {
     isChoose = !isChoose;
 }
-
-function stopRead() {
-    reader.cancel();
-}
-if (performance.navigation.type == 1) {        //如果网页刷新，停止播放声音
-    stopRead()
-  }

app/static/js/highlight.js

@@ -22,24 +22,20 @@ function getWord() {
 
 function highLight() {
     if (!isHighlight) return;
-    let articleContent = document.getElementById("article").innerText; //将原来的.innerText改为.innerHtml，使用innerText会把原文章中所包含的<br>标签去除，导致处理后的文章内容失去了原来的格式
+    let articleContent = document.getElementById("article").innerText;
     let pickedWords = document.getElementById("selected-words");  // words picked to the text area
     let dictionaryWords = document.getElementById("selected-words2"); // words appearing in the user's new words list
-    let allWords = "";  //初始化allWords的值，避免进入判断后编译器认为allWords未初始化的问题
+    let allWords = dictionaryWords === null ? pickedWords.value + " " : pickedWords.value + " " + dictionaryWords.value;
-    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
+    const list = allWords.split(" "); // 将所有的生词放入一个list中，用于后续处理
-        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(/(^\s*)|(\s*$)/g, ""); //消除单词两边的空字符
+        list[i] = list[i].replace(/(^\W*)|(\W*$)/g, ""); // 消除单词两边的非单词字符
-        list[i] = list[i].replace('|', "");
+        if (list[i] != "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
-        list[i] = list[i].replace('?', "");
+            // 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。
-        if (list[i] !== "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
+            let matches = new Set(articleContent.match(new RegExp("\\b" + list[i] + "\\b", "gi")));
-	    //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，"\\s"代表单词前后必须要有空格，以防止只对单词中的部分字符高亮的情况出现。
+            for (let word of matches) {
-            articleContent = articleContent.replace(new RegExp("\\s"+list[i]+"\\s", "g"), " <mark>" + list[i] + "</mark> ");
+                // 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>");
+            }
         }
     }
     document.getElementById("article").innerHTML = articleContent;

app/static/js/read.js

@@ -0,0 +1,35 @@
+var Reader = (function() {
+    let reader = window.speechSynthesis;
+    let current_position = 0;
+    let original_position = 0;
+    let to_speak = "";
+
+    function makeUtterance(str, rate) {
+        let msg = new SpeechSynthesisUtterance(str);
+        msg.rate = rate;
+        msg.lang = "en-US";
+        msg.onboundary = ev => {
+            if (ev.name == "word") {
+                current_position = ev.charIndex;
+            }
+        }
+        return msg;
+    }
+
+    function read(s, rate) {
+        to_speak = s.toString();
+        original_position = 0;
+        current_position = 0;
+        let msg = makeUtterance(to_speak, rate);
+        reader.speak(msg);
+    }
+
+    function stopRead() {
+        reader.cancel();
+    }
+
+    return {
+        read: read,
+        stopRead: stopRead
+    };
+})();

app/static/js/word_operation.js

@@ -62,6 +62,13 @@ function delete_word(theWord) {
     });
 }
 
+function read_word(theWord) {
+    let to_speak = $("#word_" + theWord).text();
+    original_position = 0;
+    current_position = 0;
+    Reader.read(to_speak, inputSlider.value);
+}
+
 /* 
  * interface Word {
  *   word: string,
@@ -95,6 +102,7 @@ function wordTemplate(word) {
         <a class="btn btn-success" onclick="familiar('${word.word}')" role="button">熟悉</a>
         <a class="btn btn-warning" onclick="unfamiliar('${word.word}')" role="button">不熟悉</a>
         <a class="btn btn-danger" onclick="delete_word('${word.word}')" role="button">删除</a>
+        <a class="btn btn-info" onclick="read_word('${word.word}')" role="button">朗读</a>
     </p>`;
 }
 

app/templates/admin_index.html

@@ -30,7 +30,7 @@
             <div class="collapse navbar-collapse" id="navbarNav">
                 <ul class="navbar-nav">
                     <li class="nav-item">
-                        <a class="nav-link" href="/{{ username }}">返回 {{ username }}</a>
+                        <a class="nav-link" href="/{{ username }}/userpage">返回 {{ username }}</a>
                     </li>
                 </ul>
             </div>

app/templates/admin_manage_user.html

@@ -68,9 +68,9 @@
 <script>
     // 密码生成器
     function generatePassword(length) {
-        var charset = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789!@#$%^&*()_+~`|}{[]\:;?><,./-=";
+        const charset = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789!@#$%^*()_+~`|}{[]\:;?,./-=";
-        var password = "";
+        let password = "";
-        for (var i = 0; i < length; i++) {
+        for (let i = 0; i < length; i++) {
             password += charset.charAt(Math.floor(Math.random() * charset.length));
         }
         return password;

app/templates/login.html

@@ -22,7 +22,7 @@
                     alert('无法通过验证。');
                     window.location.href = "/login";
                 } else if (response.status === '1') {
-                    window.location.href = "/"+username;
+                    window.location.href = "/"+username+"/userpage";
                 }
             }
         )

app/templates/mainpage_get.html

@@ -23,7 +23,7 @@
     <div class="container-fluid">
         <p><b><font size="+3" color="red">English Pal - Learn English smartly!</font></b></p>
         {% if session['logged_in'] %}
-            <a href="/{{ session['username'] }}">{{ session['username'] }}</a>
+            <a href="/{{ session['username'] }}/userpage">{{ session['username'] }}</a>
             {% if session['username'] == admin_name %}
             <a href="/admin">管理</a></p>
             {% endif %}

app/templates/reset.html

@@ -45,7 +45,7 @@
         <input type="password" placeholder="新密码" class="new-password" name="new-password" id="new-password"/>
         <input type="password" placeholder="确认新密码" class="re-new-password" name="re-new-password" id="re-new-password"/>
         <button id="submit" class="btn" onclick="reset()">提交</button>
-        <button class="btn" onclick="window.location.href='/{{ username }}'">放弃修改</button>
+        <button class="btn" onclick="window.location.href='/{{ username }}/userpage'">放弃修改</button>
 
     </div>
 {% endblock %}

app/templates/signup.html

@@ -35,7 +35,7 @@ You're logged in already! <a href="/logout">Logout</a>.
                     } else if (response.status === '2') {
                         let f = confirm("恭喜，你已成功注册，你的用户名是"+username+'.\n点击“确认”开始使用，或点击“取消”返回首页');
                         if (f) {
-                            window.location.href = '/'+username;
+                            window.location.href = '/'+username+'/userpage';
                         } else {
                             window.location.href = '/';
                         }

app/templates/userpage_get.html

@@ -37,31 +37,31 @@
 <body>
 <div class="container-fluid">
     <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>
         {% endif %}
-        <a class="btn btn-secondary" href="/logout" role="button" onclick="stopRead()">退出</a>
+        <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 %}#}
 
-    <a class="btn btn-success" href="/{{ username }}/reset" role="button" onclick="stopRead()"> 下一篇 Next Article </a>
+        <button class="btn btn-success" id="load_next_article" onclick="load_next_article()"> 下一篇 Next Article </button>
-    {% if session.get('existing_articles') != None and session.get('existing_articles')["index"] !=0 %}
+        <button class="btn btn-success" id="load_pre_article" onclick="load_pre_article()" > 上一篇 Previous Article </button>
-        <a class="btn btn-success" href="/{{ username }}/back" role="button" onclick="stopRead()"> 上一篇 Previous Article </a>
-    {% endif %}
 
     <p><b>阅读文章并回答问题</b></p>
     <div id="text-content">
-        {% if today_article %}
+        <div id="found">
-            <div class="alert alert-success" role="alert">According to your word list, your level is <span class="badge bg-success">{{ today_article["user_level"] }}</span>  and we have chosen an article with a difficulty level of <span class="badge bg-success">{{ today_article["text_level"] }}</span> for you.</div>
+            <div class="alert alert-success" role="alert">According to your word list, your level is <span class="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">Article added on: {{ today_article["date"] }}</p><br/>
+                <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">{{ today_article["article_title"] }}</p><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">{{ today_article['source'] }}</small></p><br/>
+            <p><small class="text-muted" id="source">{{ today_article['source'] }}</small></p><br/>
-            <p><b>{{ today_article['question'] }}</b></p><br/>
+            <p><b id="question">{{ today_article['question'] }}</b></p><br/>
                 <script type="text/javascript">
                     function toggle_visibility(id) { {# https://css-tricks.com/snippets/javascript/showhide-element/#}
                         const e = document.getElementById(id);
@@ -74,11 +74,13 @@
                 <button onclick="toggle_visibility('answer');">ANSWER</button>
                 <div id="answer" style="display:none;">{{ today_article['answer'] }}</div><br/>
             </div>
-        {% else %}
+        </div>
-            <div class="alert alert-success" role="alert">
+        <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>
-        {% endif %}
+        <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
@@ -93,7 +95,7 @@
         </div>
     </div>
     <p><b>收集生词吧</b> （可以在正文中划词，也可以复制黏贴）</p>
-    <form method="post" action="/{{ username }}">
+    <form method="post" action="/{{ username }}/userpage">
         <textarea name="content" id="selected-words" rows="10" cols="120"></textarea><br/>
         <input type="submit" value="把生词加入我的生词库"/>
         <input type="reset" value="清除"/>
@@ -131,6 +133,7 @@
                     <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>
                     <a class="btn btn-danger" onclick="delete_word('{{ word }}')" role="button">删除</a>
+                    <a class="btn btn-info" onclick="read_word('{{ word }}')" role="button">朗读</a>
                 </p>
             {% endfor %}
         </div>
@@ -143,6 +146,67 @@
         <script src="{{ js }}"></script>
     {% endfor %}
 {% endif %}
+<script type="text/javascript">
+    function load_next_article(){
+        $.ajax({
+            url: '/get_next_article/{{username}}',
+            dataType: 'json',
+            success: function(data) {
+                // 更新页面内容
+                if(data['today_article']){
+                    update(data['today_article']);
+                    check_pre(data['visited_articles']);
+                    check_next(data['result_of_generate_article']);
+                }
+            }
+        });
+    }
+    function load_pre_article(){
+        $.ajax({
+            url: '/get_pre_article/{{username}}',
+            dataType: 'json',
+            success: function(data) {
+                // 更新页面内容
+                if(data['today_article']){
+                    update(data['today_article']);
+                    check_pre(data['visited_articles']);
+                }
+            }
+        });
+    }
+    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"]);
+        $('#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"]);
+    }
+<!-- 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{
+            $('#load_pre_article').show();
+        }
+    }
+    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"){
+            $('#found').hide();
+            $('#not_found').show();
+            $('#read_all').hide();
+        }else{
+            $('#found').hide();
+            $('#not_found').hide();
+            $('#read_all').show();
+        }
+    }
+</script>
 </body>
 <style>
     mark {

app/user_service.py

@@ -21,36 +21,46 @@ userService = Blueprint("user_bp", __name__)
 path_prefix = '/var/www/wordfreq/wordfreq/'
 path_prefix = './'  # comment this line in deployment
 
-
+@userService.route("/get_next_article/<username>",methods=['GET','POST'])
-@userService.route("/<username>/reset", methods=['GET', 'POST'])
+def get_next_article(username):
-def user_reset(username):
+    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
-    '''
+    session['old_articleID'] = session.get('articleID')
-    用户界面
-    :param username: 用户名
-    :return: 返回页面内容
-    '''
     if request.method == 'GET':
-        existing_articles = session.get("existing_articles")
+        visited_articles = session.get("visited_articles")
-        existing_articles["index"] += 1
+        if visited_articles['article_ids'][-1] == "null":  # 如果当前还是“null”，则将“null”pop出来,无需index+=1
-        session["existing_articles"] = existing_articles
+            visited_articles['article_ids'].pop()
-        return redirect(url_for('user_bp.userpage', username=username))
+        else:  # 当前不为“null”，直接 index+=1
+            visited_articles["index"] += 1
+        session["visited_articles"] = visited_articles
+        visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
+        data = {
+            'visited_articles': visited_articles,
+            'today_article': today_article,
+            'result_of_generate_article': result_of_generate_article
+        }
     else:
         return 'Under construction'
+    return json.dumps(data)
 
-@userService.route("/<username>/back", methods=['GET'])
+@userService.route("/get_pre_article/<username>",methods=['GET'])
-def user_back(username):
+def get_pre_article(username):
-    '''
+    user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
-    用户界面
-    :param username: 用户名
-    :return: 返回页面内容
-    '''
     if request.method == 'GET':
-        existing_articles = session.get("existing_articles")
+        visited_articles = session.get("visited_articles")
-        existing_articles["index"] -= 1
+        if(visited_articles["index"]==0):
-        session["existing_articles"] = existing_articles
+            data=''
-        return redirect(url_for('user_bp.userpage', username=username))
+        else:
-
+            visited_articles["index"] -= 1  # 上一篇，index-=1
-
+            if visited_articles['article_ids'][-1] == "null":  # 如果当前还是“null”，则将“null”pop出来
+                visited_articles['article_ids'].pop()
+            session["visited_articles"] = visited_articles
+            visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
+            data = {
+                'visited_articles': visited_articles,
+                'today_article': today_article,
+                'result_of_generate_article':result_of_generate_article
+            }
+        return json.dumps(data)
 
 @userService.route("/<username>/<word>/unfamiliar", methods=['GET', 'POST'])
 def unfamiliar(username, word):
@@ -97,7 +107,7 @@ def deleteword(username, word):
     return "success"
 
 
-@userService.route("/<username>", methods=['GET', 'POST'])
+@userService.route("/<username>/userpage", methods=['GET', 'POST'])
 def userpage(username):
     '''
     用户界面
@@ -134,8 +144,8 @@ def userpage(username):
         words = ''
         for x in lst3:
             words += x[0] + ' '
-        existing_articles, today_article = get_today_article(user_freq_record, session.get('existing_articles'))
+        visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_articles'))
-        session['existing_articles'] = existing_articles
+        session['visited_articles'] = visited_articles
         # 通过 today_article，加载前端的显示页面
         return render_template('userpage_get.html',
                                admin_name=ADMIN_NAME,
@@ -143,15 +153,12 @@ def userpage(username):
                                session=session,
                                # flashed_messages=get_flashed_messages(), 仅有删除单词的时候使用到flash，而删除单词是异步执行，这里的信息提示是同步执行，所以就没有存在的必要了
                                today_article=today_article,
+                               result_of_generate_article=result_of_generate_article,
                                d_len=len(d),
                                lst3=lst3,
                                yml=Yaml.yml,
                                words=words)
 
-
-
-
-
 @userService.route("/<username>/mark", methods=['GET', 'POST'])
 def user_mark_word(username):
     '''

requirements.txt

@@ -2,3 +2,4 @@ Flask==1.1.2
 selenium==3.141.0
 PyYAML~=6.0
 pony==0.7.16
+snowballstemmer==2.2.0