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 = '' % ( - 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 += '\n' - html_code += '\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 %} + + + + + + +
+
+ 请选择您需要的操作 +
+ +
+ + + 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() %} + + {% endfor %} + +
+ {% if tips %} + + {% endif %} +
+
录入文章
+
+
+ + + + + + + + +
+ +
+
+
+ +
+
文章列表
+
+ {% for text in text_list %} +
+
+ 删除 +
+
+
{{ 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() %} + + {% endfor %} + +
+
重置选中用户的信息
+
+
+ + + + +
+ + +
+ + +
+ +
+ +
+ + +
+
+ + + + + + 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 %} - + +

Sign In

-
- - - -
+ + + + 注册
-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 @@

English Pal - Learn English smartly!

{% if session['logged_in'] %} - {{session['username']}}

+ {{ session['username'] }} + {% if session['username'] == admin_name %} + 管理

+ {% endif %} {% else %}

登录 注册 使用说明

-

{{random_ads|safe}}

+

{{ random_ads }}。 试试吧!

{% endif %} - +

粘贴1篇文章 (English only)


diff --git a/app/templates/reset.html b/app/templates/reset.html index 902d046..3425c97 100644 --- a/app/templates/reset.html +++ b/app/templates/reset.html @@ -2,6 +2,38 @@ + +
@@ -9,14 +41,11 @@

Reset Password

- - - - - - - + + + + +
{% endblock %} \ No newline at end of file diff --git a/app/templates/signup.html b/app/templates/signup.html index 1fd05f0..9030d41 100644 --- a/app/templates/signup.html +++ b/app/templates/signup.html @@ -6,6 +6,47 @@ You're logged in already! Logout. {% else %} + +

{{ get_flashed_messages()[0] | safe }}

@@ -15,12 +56,10 @@ You're logged in already! Logout.

Sign Up

-
-

-

-

- -
+

+

+

+
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 #} +{# #} +{# {% endfor %}#} + + +

阅读文章并回答问题

-
{{ today_article|safe }}
+
+
+ +

Article added on: {{ today_article["date"] }}


+

+

{{ today_article["article_title"] }}


+

{{ today_article["article_body"] }}


+

{{ today_article['source'] }}


+

{{ today_article['question'] }}


+ + +
+
+
+ + +
生词高亮 大声朗读 @@ -60,11 +91,11 @@
- +
- +

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 %} + diff --git a/app/user_service.py b/app/user_service.py index 2d10404..2e5feed 100644 --- a/app/user_service.py +++ b/app/user_service.py @@ -1,5 +1,5 @@ from datetime import datetime - +from admin_service import ADMIN_NAME from flask import * # from app import Yaml @@ -21,33 +21,46 @@ userService = Blueprint("user_bp", __name__) path_prefix = '/var/www/wordfreq/wordfreq/' path_prefix = './' # comment this line in deployment - -@userService.route("//reset", methods=['GET', 'POST']) -def user_reset(username): - ''' - 用户界面 - :param username: 用户名 - :return: 返回页面内容 - ''' +@userService.route("/get_next_article/",methods=['GET','POST']) +def get_next_article(username): + user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username) session['old_articleID'] = session.get('articleID') if request.method == 'GET': - session['articleID'] = None - return redirect(url_for('user_bp.userpage', username=username)) + visited_articles = session.get("visited_articles") + if visited_articles['article_ids'][-1] == "null": # 如果当前还是“null”,则将“null”pop出来,无需index+=1 + visited_articles['article_ids'].pop() + 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("//back", methods=['GET']) -def user_back(username): - ''' - 用户界面 - :param username: 用户名 - :return: 返回页面内容 - ''' +@userService.route("/get_pre_article/",methods=['GET']) +def get_pre_article(username): + user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username) if request.method == 'GET': - session['articleID'] = session.get('old_articleID') - return redirect(url_for('user_bp.userpage', username=username)) - - + visited_articles = session.get("visited_articles") + if(visited_articles["index"]==0): + data='' + 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("///unfamiliar", methods=['GET', 'POST']) def unfamiliar(username, word): @@ -89,11 +102,12 @@ def deleteword(username, word): ''' user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username) pickle_idea2.deleteRecord(user_freq_record, word) - flash(f'{word} is no longer in your word list.') + # 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.') return "success" -@userService.route("/", methods=['GET', 'POST']) +@userService.route("//userpage", methods=['GET', 'POST']) def userpage(username): ''' 用户界面 @@ -130,20 +144,21 @@ def userpage(username): words = '' for x in lst3: words += x[0] + ' ' + visited_articles, today_article, result_of_generate_article = get_today_article(user_freq_record, session.get('visited_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, username=username, session=session, - flashed_messages=get_flashed_messages_if_any(), - today_article=get_today_article(user_freq_record, session['articleID']), + # 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("//mark", methods=['GET', 'POST']) def user_mark_word(username): ''' @@ -173,15 +188,3 @@ def get_time(): ''' return datetime.now().strftime('%Y%m%d%H%M') # upper to minutes -def get_flashed_messages_if_any(): - ''' - 在用户界面显示黄色提示信息 - :return: 包含HTML标签的提示信息 - ''' - messages = get_flashed_messages() - s = '' - for message in messages: - s += '' - return s diff --git a/app/wordfreqCMD.py b/app/wordfreqCMD.py index c4f8a63..dcee74e 100644 --- a/app/wordfreqCMD.py +++ b/app/wordfreqCMD.py @@ -39,7 +39,7 @@ def file2str(fname):#文件转字符 def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。 - special_characters = '\_©~<=>+-/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉 + special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉 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('--', ' ') @@ -70,7 +70,7 @@ def sort_in_ascending_order(lst):# 单词按频率降序排列 return lst2 -def make_html_page(lst, fname): +def make_html_page(lst, fname): # 只是在wordfreqCMD.py中的main函数中调用,所以不做修改 ''' 功能:把lst的信息存到fname中,以html格式。 ''' diff --git a/build.sh b/build.sh index 4348b2f..e313fce 100755 --- a/build.sh +++ b/build.sh @@ -3,6 +3,10 @@ DEPLOYMENT_DIR=/home/lanhui/englishpal2/EnglishPal cd $DEPLOYMENT_DIR +# Install dependencies + +pip3 install -r requirements.txt + # Stop service sudo docker stop EnglishPal sudo docker rm EnglishPal diff --git a/requirements.txt b/requirements.txt index 2746a3b..338b71c 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,5 @@ Flask==1.1.2 selenium==3.141.0 PyYAML~=6.0 +pony==0.7.16 +snowballstemmer==2.2.0