diff --git a/.gitignore b/.gitignore
index 413c71c..3d901ba 100644
--- a/.gitignore
+++ b/.gitignore
@@ -10,3 +10,4 @@ app/static/frequency/frequency.p
app/static/wordfreqapp.db
app/static/donate-the-author.jpg
app/static/donate-the-author-hidden.jpg
+app/model/__pycache__/
\ No newline at end of file
diff --git a/README.md b/README.md
index 29e74dd..14cc9aa 100644
--- a/README.md
+++ b/README.md
@@ -182,6 +182,7 @@ Bug report: http://118.25.96.118/bugzilla/show_bug.cgi?id=215
+
### 丁锐
修复了以下漏洞
@@ -191,4 +192,5 @@ Bug report: http://118.25.96.118/bugzilla/show_bug.cgi?id=215
Bug report: http://118.25.96.118/bugzilla/show_bug.cgi?id=489
-*Last modified on 2023-01-30*
\ No newline at end of file
+*Last modified on 2023-01-30*
+
diff --git a/app/Article.py b/app/Article.py
index 04a32ea..df9ac3a 100644
--- a/app/Article.py
+++ b/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/'
@@ -32,12 +32,20 @@ def get_article_body(s):
return '\n'.join(lst)
-def get_today_article(user_word_list, articleID):
+def get_today_article(user_word_list, visited_articles):
rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
- if articleID == None:
+ if visited_articles is None:
+ visited_articles = {
+ "index" : 0, # 为 article_ids 的索引
+ "article_ids": [] # 之前显示文章的id列表,越后越新
+ }
+ if visited_articles["index"] > len(visited_articles["article_ids"])-1: # 生成新的文章,因此查找所有的文章
rq.instructions("SELECT * FROM article")
- else:
- rq.instructions('SELECT * FROM article WHERE article_id=%d' % (articleID))
+ else: # 生成阅读过的文章,因此查询指定 article_id 的文章
+ if visited_articles["article_ids"][visited_articles["index"]] == 'null': # 可能因为直接刷新页面导致直接去查询了'null',因此当刷新的页面的时候,需要直接进行“上一篇”操作
+ visited_articles["index"] -= 1
+ visited_articles["article_ids"].pop()
+ rq.instructions('SELECT * FROM article WHERE article_id=%d' % (visited_articles["article_ids"][visited_articles["index"]]))
rq.do()
result = rq.get_results()
random.shuffle(result)
@@ -45,38 +53,51 @@ def get_today_article(user_word_list, articleID):
# 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 = {}
+ 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.
- random.shuffle(result) # shuffle list
- d = random.choice(result)
- text_level = text_difficulty_level(d['text'], d3)
- if articleID == None:
- for reading in result:
- text_level = text_difficulty_level(reading['text'], d3)
- 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 within_range(text_level, user_level, (8.0 - user_level) * factor):
- d = reading
- break
+ 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 = 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)
+ 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"
+ 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"
- s = '
According to your word list, your level is %4.2f and we have chosen an article with a difficulty level of %4.2f for you.
' % (
- user_level, text_level)
- s += 'Article added on: %s
' % (d['date'])
- s += ''
- article_title = get_article_title(d['text'])
- article_body = get_article_body(d['text'])
- s += '
%s
' % (article_title)
- s += '
%s
' % (article_body)
- s += '
%s
' % (d['source'])
- s += '
%s
' % (get_question_part(d['question']))
- s = s.replace('\n', '
')
- s += '%s' % (get_answer_part(d['question']))
- s += '
'
- session['articleID'] = d['article_id']
- return s
+ today_article = None
+ if d:
+ today_article = {
+ "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']),
+ "source": d["source"],
+ "question": get_question_part(d['question']),
+ "answer": get_answer_part(d['question'])
+ }
+
+ return visited_articles, today_article, result_of_generate_article
def load_freq_history(path):
@@ -116,21 +137,4 @@ def get_answer_part(s):
flag = 1
elif flag == 1:
result.append(line)
- # https://css-tricks.com/snippets/javascript/showhide-element/
- js = '''
-
- '''
- html_code = js
- html_code += '\n'
- html_code += 'ANSWER \n'
- html_code += '%s
\n' % ('\n'.join(result))
- return html_code
\ No newline at end of file
+ return '\n'.join(result)
diff --git a/app/Login.py b/app/Login.py
index 8e0030b..cd750d1 100644
--- a/app/Login.py
+++ b/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')
- password = md5(username + password)
- rq.instructions_with_parameters("SELECT * FROM user WHERE name=:username AND password=:password", dict(
- 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 != []
+ user = get_user_by_username(username)
+ encoded_password = md5(username + password)
+ return user is not None and user.password == encoded_password
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')
- 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()
+ insert_user(username=username, password=password, start_date=start_date, expiry_date=expiry_date)
def check_username_availability(username):
- rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
- rq.instructions_with_parameters(
- "SELECT * FROM user WHERE name=:username", dict(username=username))
- rq.do_with_parameters()
- result = rq.get_results()
- return result == []
+ existed_user = get_user_by_username(username)
+ return existed_user is None
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)
- 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()
+ update_password_by_username(username, new_password)
return True
def get_expiry_date(username):
- rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
- rq.instructions_with_parameters(
- "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:
+ user = get_user_by_username(username)
+ if user is None:
return '20191024'
-
-
-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()
-
+ else:
+ return user.expiry_date
class UserName:
def __init__(self, username):
@@ -96,9 +78,9 @@ class UserName:
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 is not '.' and c is not '_':
+ if c in string.punctuation and c != '.' and c != '_':
return f'{c} is not allowed in the user name.'
- if self.username in ['signup', 'login', 'logout', 'reset', 'mark', 'back', 'unfamiliar', 'familiar', 'del']:
+ if self.username in ['signup', 'login', 'logout', 'reset', 'mark', 'back', 'unfamiliar', 'familiar', 'del', 'admin']:
return 'You used a restricted word as your user name. Please come up with a better one.'
return 'OK'
diff --git a/app/account_service.py b/app/account_service.py
index 9b1c46b..a7ed0c4 100644
--- a/app/account_service.py
+++ b/app/account_service.py
@@ -19,21 +19,15 @@ def signup():
# 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'])
- password2 = escape(request.form['password2'])
#! 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 str(warn)
+ return jsonify({'status': '3', 'warn': str(warn)})
available = check_username_availability(username)
if not available: # 用户名不可用
- flash('用户名 %s 已经被注册。' % (username))
- return render_template('signup.html')
- elif len(password.strip()) < 4: # 密码过短
- return '密码过于简单。'
- elif password != password2:
- return '确认密码与输入密码不一致!'
+ return jsonify({'status': '0'})
else: # 添加账户信息
add_user(username, password)
verified = verify_user(username, password)
@@ -43,11 +37,10 @@ def signup():
session[username] = username
session['username'] = username
session['expiry_date'] = get_expiry_date(username)
- session['articleID'] = None
- return '恭喜,你已成功注册, 你的用户名是 %s 。
\
- 开始使用 返回首页
' % (username, username, username)
+ session['visited_articles'] = None
+ return jsonify({'status': '2'})
else:
- return '用户名密码验证失败。'
+ return jsonify({'status': '1'})
@@ -59,13 +52,7 @@ def login():
'''
if request.method == 'GET':
# GET请求
- if not session.get('logged_in'):
- # 未登录,返回登录页面
- return render_template('login.html')
- else:
- # 已登录,提示信息并显示登出按钮
- return '你已登录 %s 。 登出点击这里 。' % (
- session['username'], session['username'])
+ return render_template('login.html')
elif request.method == 'POST':
# POST方法用于判断登录是否成功
# check database and verify user
@@ -79,10 +66,10 @@ def login():
session['username'] = username
user_expiry_date = get_expiry_date(username)
session['expiry_date'] = user_expiry_date
- session['articleID'] = None
- return redirect(url_for('user_bp.userpage', username=username))
+ session['visited_articles'] = None
+ return jsonify({'status': '1'})
else:
- return '无法通过验证。'
+ return jsonify({'status': '0'})
@accountService.route("/logout", methods=['GET', 'POST'])
@@ -115,31 +102,9 @@ def reset():
# 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'])
-
- re_new_password = escape(request.form['re-new-password']) # 确认新密码
- if re_new_password != new_password: #验证新密码两次输入是否相同
- return '新密码不匹配,请重新输入'
- if len(new_password) < 4: #验证新密码长度,原则参照注册模块
- return '密码过于简单。(密码长度至少4位)'
-
flag = change_password(username, old_password, new_password) # flag表示是否修改成功
if flag:
session['logged_in'] = False
- return \
-'''
-
-
-'''
-
+ return jsonify({'status':'1'}) # 修改成功
else:
- return \
-'''
-
-
-'''
+ return jsonify({'status':'2'}) # 修改失败
diff --git a/app/admin_service.py b/app/admin_service.py
new file mode 100644
index 0000000..a604b5e
--- /dev/null
+++ b/app/admin_service.py
@@ -0,0 +1,142 @@
+# System Library
+from flask import *
+
+# Personal library
+from Yaml import yml
+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"):
+ return render_template("not_login.html")
+
+ # 用户名不是admin_name
+ if session.get("username") != ADMIN_NAME:
+ return "You are not admin!"
+
+ return "pass"
+
+
+@adminService.route("/admin", methods=["GET"])
+def admin():
+ is_admin = check_is_admin()
+ if is_admin != "pass":
+ return is_admin
+
+ return render_template(
+ "admin_index.html", yml=yml, username=session.get("username")
+ )
+
+
+@adminService.route("/admin/article", methods=["GET", "POST"])
+def article():
+ global _cur_page, _page_size
+
+ is_admin = check_is_admin()
+ if is_admin != "pass":
+ return is_admin
+
+ _article_number = get_number_of_articles()
+ try:
+ _page_size = min(
+ max(1, int(request.args.get("size", 5))), _article_number
+ ) # 最小的size是1
+ _cur_page = min(
+ max(1, int(request.args.get("page", 1))), _article_number // _page_size + (_article_number % _page_size > 0)
+ ) # 最小的page是1
+ 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 = ' '.join(article.text.split("\n")[1:])
+
+ context = {
+ "article_number": _article_number,
+ "text_list": _articles,
+ "page_size": _page_size,
+ "cur_page": _cur_page,
+ "username": session.get("username"),
+ }
+
+ def _update_context():
+ article_len = get_number_of_articles()
+ context["article_number"] = article_len
+ context["text_list"] = get_page_articles(_cur_page, _page_size)
+ _articles = get_page_articles(_cur_page, _page_size)
+ for article in _articles: # 获取每篇文章的title
+ article.title = article.text.split("\n")[0]
+ context["text_list"] = _articles
+
+ if request.method == "GET":
+ try:
+ delete_id = int(request.args.get("delete_id", 0))
+ except:
+ return "Delete article ID must be int!"
+ if delete_id: # delete article
+ delete_article_by_id(delete_id)
+ _update_context()
+ elif request.method == "POST":
+ data = request.form
+ content = data.get("content", "")
+ source = data.get("source", "")
+ question = data.get("question", "")
+ level = data.get("level", "4")
+ if content:
+ if level not in ['1', '2', '3', '4']:
+ return "Level must be between 1 and 4."
+ add_article(content, source, level, question)
+ _update_context()
+ title = content.split('\n')[0]
+ flash(f'Article added. Title: {title}')
+ return render_template("admin_manage_article.html", **context)
+
+
+@adminService.route("/admin/user", methods=["GET", "POST"])
+def user():
+ 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","")
+ new_password = data.get("new_password", "")
+ expiry_time = data.get("expiry_time", "")
+ if username:
+ if new_password:
+ update_password_by_username(username, new_password)
+ flash(f'Password updated to {new_password}')
+ if expiry_time:
+ update_expiry_time_by_username(username, "".join(expiry_time.split("-")))
+ flash(f'Expiry date updated to {expiry_time}.')
+ return render_template("admin_manage_user.html", **context)
+
+
+@adminService.route("/admin/expiry", methods=["GET"])
+def user_expiry_time():
+ is_admin = check_is_admin()
+ if is_admin != "pass":
+ return is_admin
+
+ username = request.args.get("username", "")
+ if not username:
+ return "Username can't be empty."
+
+ user = get_user_by_username(username)
+ if not user:
+ return "User does not exist."
+
+ return user.expiry_date
diff --git a/app/difficulty.py b/app/difficulty.py
index 50aa179..cb93768 100644
--- a/app/difficulty.py
+++ b/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):
@@ -17,41 +18,51 @@ def load_record(pickle_fname):
return d
-def difficulty_level_from_frequency(word, d):
- level = 1
- if not word in d:
- return level
-
- if 'what' in d:
- ratio = (d['what']+1)/(d[word]+1) # what is a frequent word
- level = math.log( max(ratio, 1), 2)
+def convert_test_type_to_difficulty_level(d):
+ """
+ 对原本的单词库中的单词进行难度评级
+ :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
- level = min(level, 8)
- return level
+ for k in L:
+ if 'CET4' in d[k]:
+ 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
+
+ return result # {'apple': 4, ...}
-def get_difficulty_level(d1, d2):
- d = {}
- L = list(d1.keys()) # in d1, we have freuqence for each word
- L2 = list(d2.keys()) # in d2, we have test types (e.g., CET4,CET6,BBC) for each word
- L.extend(L2)
- L3 = list(set(L)) # L3 contains all words
- for k in L3:
- if k in d2:
- if 'CET4' in d2[k]:
- 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)
+def get_difficulty_level_for_user(d1, d2):
+ """
+ d2 来自于词库的35511个已标记单词
+ d1 用户不会的词
+ 在d2的后面添加单词,没有新建一个新的字典
+ """
+ # TODO: convert_test_type_to_difficulty_level() should not be called every time. Each word's difficulty level should be pre-computed.
+ d2 = convert_test_type_to_difficulty_level(d2) # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
+ stemmer = snowballstemmer.stemmer('english')
- 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
- lst = d_user2[date] # a list of words
- lst2 = [] # a list of tuples, (word, difficulty level)
- for word in lst:
+ for date in sorted(d_user2.keys(),
+ reverse=True): # most recently added words are more important while determining user's level
+ lst = d_user2[date] # a list of words
+ 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
- #print(lst3)
+ lst3 = sort_in_ascending_order(lst2) # easiest tuple first
+ # 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
- #print(lst2)
+ lst2 = sort_in_descending_order(lst) # most difficult words on top
+ # 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
- return geometric**(1/count)
-
- return geometric**(1/max(count,1))
+ if count >= 20: # we look for n most difficult words
+ return geometric ** (1 / count)
+ 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(d1, d2)
+ d3 = get_difficulty_level_for_user(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))
-
+
diff --git a/app/main.py b/app/main.py
index e311bb0..4e3f829 100644
--- a/app/main.py
+++ b/app/main.py
@@ -5,24 +5,24 @@
# Copyright 2019 (C) Hui Lan
# Written permission must be obtained from the author for commercial uses.
###########################################################################
-
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!'
# 将蓝图注册到Lab app
app.register_blueprint(userService)
app.register_blueprint(accountService)
+app.register_blueprint(adminService)
path_prefix = '/var/www/wordfreq/wordfreq/'
path_prefix = './' # comment this line in deployment
-
def get_random_image(path):
'''
返回随机图
@@ -39,8 +39,7 @@ def get_random_ads():
返回随机广告
:return: 一个广告(包含HTML标签)
'''
- ads = random.choice(['个性化分析精准提升', '你的专有单词本', '智能捕捉阅读弱点,针对性提高你的阅读水平'])
- return ads + '。 试试 吧!'
+ return random.choice(['个性化分析精准提升', '你的专有单词本', '智能捕捉阅读弱点,针对性提高你的阅读水平'])
def appears_in_test(word, d):
@@ -98,9 +97,13 @@ def mainpage():
d = load_freq_history(path_prefix + 'static/frequency/frequency.p')
d_len = len(d)
lst = sort_in_descending_order(pickle_idea.dict2lst(d))
- return render_template('mainpage_get.html', random_ads=random_ads, number_of_essays=number_of_essays,
- d_len=d_len, lst=lst, yml=Yaml.yml)
-
+ return render_template('mainpage_get.html',
+ admin_name=ADMIN_NAME,
+ random_ads=random_ads,
+ d_len=d_len,
+ lst=lst,
+ yml=Yaml.yml,
+ number_of_essays=number_of_essays)
if __name__ == '__main__':
diff --git a/app/model/__init__.py b/app/model/__init__.py
new file mode 100644
index 0000000..9526313
--- /dev/null
+++ b/app/model/__init__.py
@@ -0,0 +1,30 @@
+from pony.orm import *
+
+db = Database()
+db.bind("sqlite", "../static/wordfreqapp.db", create_db=True) # bind sqlite file
+
+
+class User(db.Entity):
+ _table_ = "user" # table name
+ name = PrimaryKey(str)
+ password = Optional(str)
+ start_date = Optional(str)
+ expiry_date = Optional(str)
+
+
+class Article(db.Entity):
+ _table_ = "article" # table name
+ article_id = PrimaryKey(int, auto=True)
+ text = Optional(str)
+ source = Optional(str)
+ date = Optional(str)
+ level = Optional(str)
+ question = Optional(str)
+
+
+db.generate_mapping(create_tables=True) # must mapping after class declaration
+
+
+if __name__ == "__main__":
+ with db_session:
+ print(Article[2].text) # test get article which id=2 text content
diff --git a/app/model/article.py b/app/model/article.py
new file mode 100644
index 0000000..a3b4bf7
--- /dev/null
+++ b/app/model/article.py
@@ -0,0 +1,34 @@
+from model import *
+from datetime import datetime
+
+def add_article(content, source="manual_input", level="5", question="No question"):
+ with db_session:
+ # add one article to sqlite
+ Article(
+ text=content,
+ source=source,
+ date=datetime.now().strftime("%-d %b %Y"), # format style of `5 Oct 2022`
+ level=level,
+ question=question,
+ )
+
+
+def delete_article_by_id(article_id):
+ article_id &= 0xFFFFFFFF # max 32 bits
+ with db_session:
+ article = Article.select(article_id=article_id)
+ if article:
+ article.first().delete()
+
+
+def get_number_of_articles():
+ with db_session:
+ return len(Article.select()[:])
+
+
+def get_page_articles(num, size):
+ with db_session:
+ return [
+ x
+ for x in Article.select().order_by(desc(Article.article_id)).page(num, size)
+ ]
diff --git a/app/model/user.py b/app/model/user.py
new file mode 100644
index 0000000..d684332
--- /dev/null
+++ b/app/model/user.py
@@ -0,0 +1,30 @@
+from model import *
+from Login import md5
+from pony import orm
+
+def get_users():
+ with db_session:
+ return User.select().order_by(User.name)[:]
+
+def get_user_by_username(username):
+ with db_session:
+ user = User.select(name=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)
+ if user:
+ user.first().password = md5(username + password)
+
+def update_expiry_time_by_username(username, expiry_time="20230323"):
+ with db_session:
+ user = User.select(name=username)
+ if user:
+ user.first().expiry_date = expiry_time
diff --git a/app/pickle_idea2.py b/app/pickle_idea2.py
index 4055fc4..0da55bc 100644
--- a/app/pickle_idea2.py
+++ b/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()
diff --git a/app/static/config.yml b/app/static/config.yml
index 20aa396..285f31f 100644
--- a/app/static/config.yml
+++ b/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/word_operation.js
+ - ../static/js/jquery.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/highlight.js
+ - ../static/js/fillword.js
+ - ../static/js/highlight.js
# 高亮样式,目前仅支持修改颜色
highlight:
diff --git a/app/static/js/fillword.js b/app/static/js/fillword.js
index ba249dd..b967633 100644
--- a/app/static/js/fillword.js
+++ b/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;
@@ -19,50 +15,17 @@ function fillInWord() {
document.getElementById("text-content").addEventListener("click", fillInWord, false);
-function makeUtterance(str, rate) {
- let msg = new SpeechSynthesisUtterance(str);
- 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
+const sliderValue = document.getElementById("rangeValue");
+const inputSlider = document.getElementById("rangeComponent");
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();
-}
\ No newline at end of file
diff --git a/app/static/js/highlight.js b/app/static/js/highlight.js
index 5ec9663..0cea31a 100644
--- a/app/static/js/highlight.js
+++ b/app/static/js/highlight.js
@@ -38,8 +38,18 @@ function highLight() {
list[i] = list[i].replace('|', "");
list[i] = list[i].replace('?', "");
if (list[i] !== "" && "".indexOf(list[i]) === -1 && " ".indexOf(list[i]) === -1) {
- //将文章中所有出现该单词word的地方改为:" " + word + " "。 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。
- articleContent = articleContent.replace(new RegExp("\\s"+list[i]+"\\s", "g"), " " + list[i] + " ");
+ //将文章中所有出现该单词word的地方改为:"" + word + ""。 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"),"" + list[i] + " ");
+ }
}
}
document.getElementById("article").innerHTML = articleContent;
diff --git a/app/static/js/read.js b/app/static/js/read.js
new file mode 100644
index 0000000..814f627
--- /dev/null
+++ b/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
+ };
+})();
diff --git a/app/static/js/word_operation.js b/app/static/js/word_operation.js
index ea6a6e8..f043cce 100644
--- a/app/static/js/word_operation.js
+++ b/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) {
熟悉
不熟悉
删除
+ 朗读
`;
}
diff --git a/app/static/words_and_tests.p b/app/static/words_and_tests.p
index 62afd6d..5c46c5a 100644
Binary files a/app/static/words_and_tests.p and b/app/static/words_and_tests.p differ
diff --git a/app/templates/admin_index.html b/app/templates/admin_index.html
new file mode 100644
index 0000000..f62a137
--- /dev/null
+++ b/app/templates/admin_index.html
@@ -0,0 +1,55 @@
+
+
+
+
+
+
+
+ {{ yml['header'] | safe }}
+ {% if yml['css']['item'] %}
+ {% for css in yml['css']['item'] %}
+
+ {% endfor %}
+ {% endif %}
+ {% if yml['js']['head'] %}
+ {% for js in yml['js']['head'] %}
+
+ {% endfor %}
+ {% endif %}
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/app/templates/admin_manage_article.html b/app/templates/admin_manage_article.html
new file mode 100644
index 0000000..272b54e
--- /dev/null
+++ b/app/templates/admin_manage_article.html
@@ -0,0 +1,103 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ {% for message in get_flashed_messages() %}
+
+ {{ message }}
+
+ {% endfor %}
+
+
+ {% if tips %}
+
+ {{ tips }}
+
+ {% endif %}
+
+
+
+
+
文章列表
+
+ {% for text in text_list %}
+
+
+
+
{{ text.title }}
+
+
{{ text.source }}
+
+ Level: {{text.level }}
+ Date: {{ text.date }}
+
+ {{ text.content | safe }}
+
+ {% endfor %}
+
+
+
+
+
+
+
+
diff --git a/app/templates/admin_manage_user.html b/app/templates/admin_manage_user.html
new file mode 100644
index 0000000..cee4667
--- /dev/null
+++ b/app/templates/admin_manage_user.html
@@ -0,0 +1,99 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ {% for message in get_flashed_messages() %}
+
+ {{ message }}
+
+ {% endfor %}
+
+
+
重置选中用户的信息
+
+
+
用户
+
+ 选择用户
+ {% for user in user_list %}
+ {{ user.name }}
+ {% endfor %}
+
+
+
修改密码
+
+ 获取12位随机密码
+
+
+
+
过期时间
+
+
+
+
+
+
+ 更新用户信息
+
+
+
+
+
+
+
+
diff --git a/app/templates/login.html b/app/templates/login.html
index a347e22..2507f75 100644
--- a/app/templates/login.html
+++ b/app/templates/login.html
@@ -1,28 +1,47 @@
{% block body %}
{% if session['logged_in'] %}
-You're logged in already!
+你已登录 {{ session['username'] }} 。 登出点击这里 。
{% else %}
-
+
+
-注册
-
{% endif %}
{% endblock %}
diff --git a/app/templates/mainpage_get.html b/app/templates/mainpage_get.html
index cbb51a6..344943d 100644
--- a/app/templates/mainpage_get.html
+++ b/app/templates/mainpage_get.html
@@ -23,12 +23,15 @@
diff --git a/app/templates/userpage_get.html b/app/templates/userpage_get.html
index dc0d497..68997ef 100644
--- a/app/templates/userpage_get.html
+++ b/app/templates/userpage_get.html
@@ -37,20 +37,51 @@
English Pal for {{ username }}
- 退出
- 重设密码
-
- {{ flashed_messages|safe }}
-
下一篇 Next Article
- {% if session.get('articleID') != session.get('old_articleID') %}
- {% if session.get('old_articleID') != None %}
-
上一篇 Previous Article
- {% endif%}
- {% endif %}
+ {% if username == admin_name %}
+
管理
+ {% endif %}
+
退出
+
重设密码
+
+
+{# {% 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 #}
+{#
Congratulations! {{ message }}
#}
+{# {% endfor %}#}
+
+
下一篇 Next Article
+
上一篇 Previous Article
阅读文章并回答问题
-
{{ today_article|safe }}
+
+
+
According to your word list, your level is {{ today_article["user_level"] }} and we have chosen an article with a difficulty level of {{ today_article["text_level"] }} for you.
+
Article added on: {{ today_article["date"] }}
+
+
{{ today_article["article_title"] }}
+
{{ today_article["article_body"] }}
+
{{ today_article['source'] }}
+
{{ today_article['question'] }}
+
+
ANSWER
+
{{ today_article['answer'] }}
+
+
+
+
Notes: 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.
+
+
+
Notes: You've read all the articles.
+
+
生词高亮
大声朗读
@@ -60,11 +91,11 @@
1×
-
+
-
+
收集生词吧 (可以在正文中划词,也可以复制黏贴)
-
+
@@ -102,6 +133,7 @@
熟悉
不熟悉
删除
+ 朗读
{% endfor %}
@@ -114,12 +146,73 @@
{% endfor %}
{% endif %}
+