forked from mrlan/EnglishPal
refactor:pylint
parent
b22c654f0f
commit
3e0b8a0235
|
|
@ -1,20 +1,18 @@
|
|||
from WordFreq import WordFreq
|
||||
from wordfreqCMD import youdao_link, sort_in_descending_order
|
||||
from UseSqlite import InsertQuery, RecordQuery
|
||||
import pickle_idea, pickle_idea2
|
||||
import os
|
||||
import random, glob
|
||||
import hashlib
|
||||
from datetime import datetime
|
||||
from flask import Flask, request, redirect, render_template, url_for, session, abort, flash, get_flashed_messages
|
||||
import random
|
||||
import pickle_idea
|
||||
from difficulty import get_difficulty_level_for_user, text_difficulty_level, user_difficulty_level
|
||||
|
||||
from UseSqlite import RecordQuery
|
||||
|
||||
path_prefix = '/var/www/wordfreq/wordfreq/'
|
||||
path_prefix = './' # comment this line in deployment
|
||||
|
||||
|
||||
def total_number_of_essays():
|
||||
'''
|
||||
得到文章总数
|
||||
return:文章数目
|
||||
'''
|
||||
rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
|
||||
rq.instructions("SELECT * FROM article")
|
||||
rq.do()
|
||||
|
|
@ -23,29 +21,42 @@ def total_number_of_essays():
|
|||
|
||||
|
||||
def get_article_title(s):
|
||||
'''
|
||||
得到文章的标题
|
||||
'''
|
||||
return s.split('\n')[0]
|
||||
|
||||
|
||||
def get_article_body(s):
|
||||
'''
|
||||
得到文章的内容
|
||||
'''
|
||||
lst = s.split('\n')
|
||||
lst.pop(0) # remove the first line
|
||||
return '\n'.join(lst)
|
||||
|
||||
|
||||
def get_today_article(user_word_list, visited_articles):
|
||||
'''
|
||||
根据用户的单词列表和阅读过的文章返回需要的文章的全部信息
|
||||
'''
|
||||
rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
|
||||
if visited_articles is None:
|
||||
visited_articles = {
|
||||
"index" : 0, # 为 article_ids 的索引
|
||||
"index": 0, # 为 article_ids 的索引
|
||||
"article_ids": [] # 之前显示文章的id列表，越后越新
|
||||
}
|
||||
if visited_articles["index"] > len(visited_articles["article_ids"])-1: # 生成新的文章，因此查找所有的文章
|
||||
rq.instructions("SELECT * FROM article")
|
||||
else: # 生成阅读过的文章，因此查询指定 article_id 的文章
|
||||
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
|
||||
# 可能因为直接刷新页面导致直接去查询了'null'，因此当刷新的页面的时候，需要直接进行“上一篇”操作
|
||||
if visited_articles["article_ids"][visited_articles["index"]] == 'null':
|
||||
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.instructions(
|
||||
f'SELECT * FROM article WHERE article_id='
|
||||
f'{visited_articles["article_ids"][visited_articles["index"]]}'
|
||||
)
|
||||
rq.do()
|
||||
result = rq.get_results()
|
||||
random.shuffle(result)
|
||||
|
|
@ -58,19 +69,23 @@ def get_today_article(user_word_list, visited_articles):
|
|||
d = None
|
||||
result_of_generate_article = "not found"
|
||||
d_user = load_freq_history(user_word_list)
|
||||
user_level = user_difficulty_level(d_user, d3) # more consideration as user's behaviour is dynamic. Time factor should be considered.
|
||||
# 更多的考虑，因为用户的行为是动态的。应考虑时间因素。
|
||||
user_level = user_difficulty_level(d_user, d3)
|
||||
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
|
||||
amount_of_existing_articles = len(result)
|
||||
# 如果当前阅读过的文章的数量 == 存在的文章的数量，即所有的书本都阅读过了
|
||||
if amount_of_visited_articles == amount_of_existing_articles:
|
||||
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
|
||||
# 从高斯分布中得出的平均值为 0.8，站位偏差为 1 的数字
|
||||
factor = random.gauss(0.8, 0.1)
|
||||
# 新的文章之前没有出现过且符合一定范围的水平
|
||||
if reading['article_id'] not in visited_articles["article_ids"] and within_range(text_level, user_level, (8.0 - user_level) * factor):
|
||||
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"
|
||||
|
|
@ -87,8 +102,8 @@ def get_today_article(user_word_list, visited_articles):
|
|||
today_article = None
|
||||
if d:
|
||||
today_article = {
|
||||
"user_level": '%4.2f' % user_level,
|
||||
"text_level": '%4.2f' % text_level,
|
||||
"user_level": f'{user_level:4.2f}',
|
||||
"text_level": f'{text_level:4.2f}',
|
||||
"date": d['date'],
|
||||
"article_title": get_article_title(d['text']),
|
||||
"article_body": get_article_body(d['text']),
|
||||
|
|
@ -101,6 +116,9 @@ def get_today_article(user_word_list, visited_articles):
|
|||
|
||||
|
||||
def load_freq_history(path):
|
||||
'''
|
||||
加载历史路径
|
||||
'''
|
||||
d = {}
|
||||
if os.path.exists(path):
|
||||
d = pickle_idea.load_record(path)
|
||||
|
|
@ -108,10 +126,16 @@ def load_freq_history(path):
|
|||
|
||||
|
||||
def within_range(x, y, r):
|
||||
'''
|
||||
判断x>y并且x-y<=r
|
||||
'''
|
||||
return x > y and abs(x - y) <= r
|
||||
|
||||
|
||||
def get_question_part(s):
|
||||
'''
|
||||
得到问题部分
|
||||
'''
|
||||
s = s.strip()
|
||||
result = []
|
||||
flag = 0
|
||||
|
|
@ -128,6 +152,9 @@ def get_question_part(s):
|
|||
|
||||
|
||||
def get_answer_part(s):
|
||||
'''
|
||||
得到答案部分
|
||||
'''
|
||||
s = s.strip()
|
||||
result = []
|
||||
flag = 0
|
||||
|
|
|
|||
27
app/Login.py
27
app/Login.py
|
|
@ -1,8 +1,7 @@
|
|||
import hashlib
|
||||
import string
|
||||
from datetime import datetime, timedelta
|
||||
from UseSqlite import InsertQuery, RecordQuery
|
||||
|
||||
from model.user import get_user_by_username, insert_user, update_password_by_username
|
||||
def md5(s):
|
||||
'''
|
||||
MD5摘要
|
||||
|
|
@ -12,24 +11,33 @@ def md5(s):
|
|||
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
|
||||
|
||||
def verify_pass(newpass,oldpass):
|
||||
if(newpass==oldpass):
|
||||
'''
|
||||
判断新旧密码是否相同
|
||||
'''
|
||||
if newpass==oldpass:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def verify_user(username, password):
|
||||
'''
|
||||
判断用户名密码是否正确
|
||||
'''
|
||||
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):
|
||||
'''
|
||||
添加新用户
|
||||
'''
|
||||
start_date = datetime.now().strftime('%Y%m%d')
|
||||
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
|
||||
|
|
@ -38,6 +46,9 @@ def add_user(username, password):
|
|||
|
||||
|
||||
def check_username_availability(username):
|
||||
'''
|
||||
检查用户名是否可用
|
||||
'''
|
||||
existed_user = get_user_by_username(username)
|
||||
return existed_user is None
|
||||
|
||||
|
|
@ -60,10 +71,12 @@ def change_password(username, old_password, new_password):
|
|||
|
||||
|
||||
def get_expiry_date(username):
|
||||
'''
|
||||
获得过期日期
|
||||
'''
|
||||
user = get_user_by_username(username)
|
||||
if user is None:
|
||||
return '20191024'
|
||||
else:
|
||||
return user.expiry_date
|
||||
|
||||
class UserName:
|
||||
|
|
@ -77,6 +90,7 @@ class UserName:
|
|||
return 'Period (.) is not allowed as the first letter in the user name.'
|
||||
if ' ' in self.username: # a user name must not include a whitespace
|
||||
return 'Whitespace is not allowed in the user name.'
|
||||
|
||||
for c in self.username: # a user name must not include special characters, except non-leading periods or underscores
|
||||
if c in string.punctuation and c != '.' and c != '_':
|
||||
return f'{c} is not allowed in the user name.'
|
||||
|
|
@ -92,4 +106,3 @@ class WarningMessage:
|
|||
|
||||
def __str__(self):
|
||||
return UserName(self.s).validate()
|
||||
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ class Sqlite3Template:
|
|||
def __init__(self, db_fname):
|
||||
self.db_fname = db_fname
|
||||
|
||||
def connect(self, db_fname):
|
||||
def connect(self):
|
||||
self.conn = sqlite3.connect(self.db_fname)
|
||||
|
||||
def instructions(self, query_statement):
|
||||
|
|
|
|||
|
|
@ -2,9 +2,9 @@
|
|||
# Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
|
||||
# Written permission must be obtained from the author for commercial uses.
|
||||
###########################################################################
|
||||
|
||||
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
|
||||
import string
|
||||
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
|
||||
|
||||
|
||||
class WordFreq:
|
||||
def __init__(self, s):
|
||||
|
|
|
|||
|
|
@ -6,7 +6,6 @@ Yaml.py
|
|||
./layout/partial/footer.html
|
||||
'''
|
||||
import yaml as YAML
|
||||
import os
|
||||
|
||||
path_prefix = './' # comment this line in deployment
|
||||
|
||||
|
|
|
|||
|
|
@ -1,45 +1,43 @@
|
|||
from flask import *
|
||||
from Login import check_username_availability, verify_user, add_user, get_expiry_date, change_password, WarningMessage
|
||||
|
||||
from flask import Blueprint, request, render_template, jsonify,session,redirect, url_for,escape
|
||||
from Login import check_username_availability, verify_user, add_user,get_expiry_date, change_password, WarningMessage
|
||||
|
||||
# 初始化蓝图
|
||||
accountService = Blueprint("accountService", __name__)
|
||||
|
||||
### Sign-up, login, logout ###
|
||||
### sign-up, login, logout, reset###
|
||||
@accountService.route("/signup", methods=['GET', 'POST'])
|
||||
def signup():
|
||||
'''
|
||||
注册
|
||||
:return: 根据注册是否成功返回不同界面
|
||||
'''
|
||||
if request.method == 'GET':
|
||||
# GET方法直接返回注册页面
|
||||
if request.method == 'GET':
|
||||
return render_template('signup.html')
|
||||
elif request.method == 'POST':
|
||||
|
||||
# POST方法需判断是否注册成功，再根据结果返回不同的内容
|
||||
username = escape(request.form['username'])
|
||||
password = escape(request.form['password'])
|
||||
|
||||
#! 添加如下代码为了过滤注册时的非法字符
|
||||
warn = WarningMessage(username)
|
||||
if str(warn) != 'OK':
|
||||
return jsonify({'status': '3', 'warn': str(warn)})
|
||||
|
||||
available = check_username_availability(username)
|
||||
if not available: # 用户名不可用
|
||||
# 用户名不可用
|
||||
if not available:
|
||||
return jsonify({'status': '0'})
|
||||
else: # 添加账户信息
|
||||
# 用户名可用,添加账户信息
|
||||
add_user(username, password)
|
||||
verified = verify_user(username, password)
|
||||
# 注册成功，写入session
|
||||
if verified:
|
||||
# 写入session
|
||||
session['logged_in'] = True
|
||||
session[username] = username
|
||||
session['username'] = username
|
||||
session['expiry_date'] = get_expiry_date(username)
|
||||
session['visited_articles'] = None
|
||||
return jsonify({'status': '2'})
|
||||
else:
|
||||
# 验证失败
|
||||
return jsonify({'status': '1'})
|
||||
|
||||
|
||||
|
|
@ -50,17 +48,16 @@ def login():
|
|||
登录
|
||||
:return: 根据登录是否成功返回不同页面
|
||||
'''
|
||||
# GET方法直接返回登录页面
|
||||
if request.method == 'GET':
|
||||
# GET请求
|
||||
return render_template('login.html')
|
||||
elif request.method == 'POST':
|
||||
# POST方法用于判断登录是否成功
|
||||
# check database and verify user
|
||||
|
||||
# POST方法用于判断登录是否成功，检查数据库并验证用户，再根据结果返回不同的内容
|
||||
username = escape(request.form['username'])
|
||||
password = escape(request.form['password'])
|
||||
verified = verify_user(username, password)
|
||||
if verified:
|
||||
# 登录成功，写入session
|
||||
if verified:
|
||||
session['logged_in'] = True
|
||||
session[username] = username
|
||||
session['username'] = username
|
||||
|
|
@ -68,7 +65,7 @@ def login():
|
|||
session['expiry_date'] = user_expiry_date
|
||||
session['visited_articles'] = None
|
||||
return jsonify({'status': '1'})
|
||||
else:
|
||||
#验证失败
|
||||
return jsonify({'status': '0'})
|
||||
|
||||
|
||||
|
|
@ -95,16 +92,18 @@ def reset():
|
|||
username = session['username']
|
||||
if username == '':
|
||||
return redirect('/login')
|
||||
if request.method == 'GET':
|
||||
|
||||
# GET请求返回修改密码页面
|
||||
if request.method == 'GET':
|
||||
return render_template('reset.html', username=session['username'], state='wait')
|
||||
else:
|
||||
|
||||
# POST请求用于提交修改后信息
|
||||
old_password = escape(request.form['old-password'])
|
||||
new_password = escape(request.form['new-password'])
|
||||
flag = change_password(username, old_password, new_password) # flag表示是否修改成功
|
||||
# 修改成功
|
||||
if flag:
|
||||
session['logged_in'] = False
|
||||
return jsonify({'status':'1'}) # 修改成功
|
||||
else:
|
||||
return jsonify({'status':'2'}) # 修改失败
|
||||
return jsonify({'status':'1'})
|
||||
# 修改失败
|
||||
return jsonify({'status':'2'})
|
||||
|
|
|
|||
|
|
@ -1,18 +1,22 @@
|
|||
# System Library
|
||||
from flask import *
|
||||
from flask import Blueprint, session, render_template, request, flash
|
||||
|
||||
# Personal library
|
||||
from Yaml import yml
|
||||
from model.user import *
|
||||
from model.article import *
|
||||
|
||||
from model.user import get_users, update_password_by_username
|
||||
from model.user import update_expiry_time_by_username, get_user_by_username
|
||||
from model.article import get_number_of_articles, get_page_articles
|
||||
from model.article import delete_article_by_id, add_article
|
||||
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():
|
||||
'''
|
||||
判断是否是管理员登录
|
||||
：return：不同页面和结果
|
||||
'''
|
||||
# 未登录，跳转到未登录界面
|
||||
if not session.get("logged_in"):
|
||||
return render_template("not_login.html")
|
||||
|
|
@ -26,6 +30,10 @@ def check_is_admin():
|
|||
|
||||
@adminService.route("/admin", methods=["GET"])
|
||||
def admin():
|
||||
'''
|
||||
判断是否是管理员登录
|
||||
：return：不同页面
|
||||
'''
|
||||
is_admin = check_is_admin()
|
||||
if is_admin != "pass":
|
||||
return is_admin
|
||||
|
|
@ -37,6 +45,11 @@ def admin():
|
|||
|
||||
@adminService.route("/admin/article", methods=["GET", "POST"])
|
||||
def article():
|
||||
'''
|
||||
管理文章
|
||||
可添加文章、删除文章
|
||||
return:不同页面
|
||||
'''
|
||||
global _cur_page, _page_size
|
||||
|
||||
is_admin = check_is_admin()
|
||||
|
|
@ -49,16 +62,15 @@ def article():
|
|||
max(1, int(request.args.get("size", 5))), _article_number
|
||||
) # 最小的size是1
|
||||
_cur_page = min(
|
||||
max(1, int(request.args.get("page", 1))), _article_number // _page_size + (_article_number % _page_size > 0)
|
||||
max(1, int(request.args.get("page", 1))),
|
||||
_article_number // _page_size + (_article_number % _page_size > 0)
|
||||
) # 最小的page是1
|
||||
except ValueError:
|
||||
return "page parmas must be int!"
|
||||
|
||||
_articles = get_page_articles(_cur_page, _page_size)
|
||||
for article in _articles: # 获取每篇文章的title
|
||||
article.title = article.text.split("\n")[0]
|
||||
article.content = '<br/>'.join(article.text.split("\n")[1:])
|
||||
|
||||
for _article in _articles: # 获取每篇文章的title
|
||||
_article.title = _article.text.split("\n")[0]
|
||||
_article.content = '<br/>'.join(_article.text.split("\n")[1:])
|
||||
context = {
|
||||
"article_number": _article_number,
|
||||
"text_list": _articles,
|
||||
|
|
@ -72,19 +84,19 @@ def article():
|
|||
context["article_number"] = article_len
|
||||
context["text_list"] = get_page_articles(_cur_page, _page_size)
|
||||
_articles = get_page_articles(_cur_page, _page_size)
|
||||
for article in _articles: # 获取每篇文章的title
|
||||
article.title = article.text.split("\n")[0]
|
||||
for _article in _articles: # 获取每篇文章的title
|
||||
_article.title = _article.text.split("\n")[0]
|
||||
context["text_list"] = _articles
|
||||
|
||||
if request.method == "GET":
|
||||
try:
|
||||
delete_id = int(request.args.get("delete_id", 0))
|
||||
except:
|
||||
except ValueError:
|
||||
return "Delete article ID must be int!"
|
||||
if delete_id: # delete article
|
||||
delete_article_by_id(delete_id)
|
||||
_update_context()
|
||||
elif request.method == "POST":
|
||||
else:
|
||||
data = request.form
|
||||
content = data.get("content", "")
|
||||
source = data.get("source", "")
|
||||
|
|
@ -102,17 +114,21 @@ def article():
|
|||
|
||||
@adminService.route("/admin/user", methods=["GET", "POST"])
|
||||
def user():
|
||||
'''
|
||||
用户管理
|
||||
可修改用户密码，过期日期
|
||||
return：不同页面
|
||||
'''
|
||||
is_admin = check_is_admin()
|
||||
if is_admin != "pass":
|
||||
return is_admin
|
||||
|
||||
context = {
|
||||
"user_list": get_users(),
|
||||
"username": session.get("username"),
|
||||
}
|
||||
if request.method == "POST":
|
||||
data = request.form
|
||||
username = data.get("username","")
|
||||
username = data.get("username", "")
|
||||
new_password = data.get("new_password", "")
|
||||
expiry_time = data.get("expiry_time", "")
|
||||
if username:
|
||||
|
|
@ -127,6 +143,9 @@ def user():
|
|||
|
||||
@adminService.route("/admin/expiry", methods=["GET"])
|
||||
def user_expiry_time():
|
||||
'''
|
||||
返回用户的过期日期
|
||||
'''
|
||||
is_admin = check_is_admin()
|
||||
if is_admin != "pass":
|
||||
return is_admin
|
||||
|
|
@ -135,8 +154,7 @@ def user_expiry_time():
|
|||
if not username:
|
||||
return "Username can't be empty."
|
||||
|
||||
user = get_user_by_username(username)
|
||||
if not user:
|
||||
existed_user = get_user_by_username(username)
|
||||
if not existed_user:
|
||||
return "User does not exist."
|
||||
|
||||
return user.expiry_date
|
||||
return existed_user.expiry_date
|
||||
|
|
|
|||
|
|
@ -6,15 +6,17 @@
|
|||
# Purpose: compute difficulty level of a English text
|
||||
|
||||
import pickle
|
||||
import math
|
||||
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
|
||||
import snowballstemmer
|
||||
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
|
||||
|
||||
|
||||
|
||||
def load_record(pickle_fname):
|
||||
f = open(pickle_fname, 'rb')
|
||||
'''
|
||||
得到特定pickle文件中的数据
|
||||
'''
|
||||
with open(pickle_fname, 'rb') as f:
|
||||
d = pickle.load(f)
|
||||
f.close()
|
||||
return d
|
||||
|
||||
|
||||
|
|
@ -53,9 +55,7 @@ def get_difficulty_level_for_user(d1, d2):
|
|||
stemmer = snowballstemmer.stemmer('english')
|
||||
|
||||
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:
|
||||
if k not in d2: # 如果用户的词以原型的形式不存在于词库d2中
|
||||
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
|
||||
|
|
@ -88,6 +88,9 @@ def revert_dict(d):
|
|||
|
||||
|
||||
def user_difficulty_level(d_user, d):
|
||||
'''
|
||||
得到用户词汇的难度水平
|
||||
'''
|
||||
d_user2 = revert_dict(d_user) # key is date, and value is a list of words added in that date
|
||||
count = 0
|
||||
geometric = 1
|
||||
|
|
@ -114,6 +117,9 @@ def user_difficulty_level(d_user, d):
|
|||
|
||||
|
||||
def text_difficulty_level(s, d):
|
||||
'''
|
||||
得到用文章的难度水平
|
||||
'''
|
||||
s = remove_punctuation(s)
|
||||
L = freq(s)
|
||||
|
||||
|
|
@ -242,10 +248,7 @@ We need — for our farmers, our manufacturers, for, frankly, unions and non-uni
|
|||
'''
|
||||
|
||||
# f = open('bbc-fulltext/bbc/entertainment/001.txt')
|
||||
f = open('wordlist.txt')
|
||||
with open('wordlist.txt', encoding='utf-8') as f:
|
||||
s = f.read()
|
||||
f.close()
|
||||
|
||||
print(text_difficulty_level(s, d3))
|
||||
|
||||
|
||||
|
|
|
|||
18
app/main.py
18
app/main.py
|
|
@ -1,17 +1,24 @@
|
|||
#! /usr/bin/python3
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import random
|
||||
|
||||
###########################################################################
|
||||
# Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
|
||||
# Written permission must be obtained from the author for commercial uses.
|
||||
###########################################################################
|
||||
from flask import escape
|
||||
from Login import *
|
||||
from Article import *
|
||||
import glob
|
||||
from flask import Flask, request, redirect, render_template, url_for, escape
|
||||
from WordFreq import WordFreq
|
||||
import pickle_idea
|
||||
from wordfreqCMD import sort_in_descending_order
|
||||
from Article import load_freq_history, total_number_of_essays
|
||||
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!'
|
||||
|
||||
|
|
@ -51,7 +58,6 @@ def appears_in_test(word, d):
|
|||
'''
|
||||
if not word in d:
|
||||
return ''
|
||||
else:
|
||||
return ','.join(d[word])
|
||||
|
||||
|
||||
|
|
@ -70,7 +76,7 @@ def mark_word():
|
|||
d = pickle_idea.merge_frequency(lst, lst_history)
|
||||
pickle_idea.save_frequency_to_pickle(d, path_prefix + 'static/frequency/frequency.p')
|
||||
return redirect(url_for('mainpage'))
|
||||
else: # 不回应GET请求
|
||||
# 不回应GET请求
|
||||
return 'Under construction'
|
||||
|
||||
|
||||
|
|
@ -91,7 +97,7 @@ def mainpage():
|
|||
pickle_idea.save_frequency_to_pickle(d, path_prefix + 'static/frequency/frequency.p')
|
||||
return render_template('mainpage_post.html', lst=lst, yml=Yaml.yml)
|
||||
|
||||
elif request.method == 'GET': # when we load a html page
|
||||
if request.method == 'GET': # when we load a html page
|
||||
random_ads = get_random_ads()
|
||||
number_of_essays = total_number_of_essays()
|
||||
d = load_freq_history(path_prefix + 'static/frequency/frequency.p')
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ def lst2dict(lst, d):
|
|||
for x in lst:
|
||||
word = x[0]
|
||||
freq = x[1]
|
||||
if not word in d:
|
||||
if word not in d:
|
||||
d[word] = freq
|
||||
else:
|
||||
d[word] += freq
|
||||
|
|
@ -37,14 +37,14 @@ def merge_frequency(lst1, lst2):
|
|||
|
||||
|
||||
def load_record(pickle_fname):
|
||||
f = open(pickle_fname, 'rb')
|
||||
d = pickle.load(f)
|
||||
with open(pickle_fname, 'rb') as f:
|
||||
pickle.load(f)
|
||||
f.close()
|
||||
return d
|
||||
|
||||
|
||||
def save_frequency_to_pickle(d, pickle_fname):
|
||||
f = open(pickle_fname, 'wb')
|
||||
with open(pickle_fname, 'wb') as f:
|
||||
#exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
|
||||
exclusion_lst = []
|
||||
d2 = {}
|
||||
|
|
@ -52,7 +52,6 @@ def save_frequency_to_pickle(d, pickle_fname):
|
|||
if not k in exclusion_lst and not k.isnumeric() and len(k) > 1:
|
||||
d2[k] = d[k]
|
||||
pickle.dump(d2, f)
|
||||
f.close()
|
||||
|
||||
def unfamiliar(path,word):
|
||||
f = open(path,"rb")
|
||||
|
|
@ -68,8 +67,8 @@ def familiar(path,word):
|
|||
del dic[word][0]
|
||||
else:
|
||||
dic.pop(word)
|
||||
fp = open(path,"wb")
|
||||
pickle.dump(dic,fp)
|
||||
with open(path,"wb") as f:
|
||||
pickle.dump(dic,f)
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ def dict2lst(d):
|
|||
for k in d:
|
||||
lst.append((k, [datetime.now().strftime('%Y%m%d%H%M')]))
|
||||
return lst
|
||||
elif isinstance(d[keys[0]], list):
|
||||
if isinstance(d[keys[0]], list):
|
||||
return list(d.items()) # a list of (key, value) pairs
|
||||
|
||||
return []
|
||||
|
|
@ -56,21 +56,19 @@ def merge_frequency(lst1, lst2):
|
|||
|
||||
|
||||
def load_record(pickle_fname):
|
||||
f = open(pickle_fname, 'rb')
|
||||
with open(pickle_fname, 'rb') as f:
|
||||
d = pickle.load(f)
|
||||
f.close()
|
||||
return d
|
||||
|
||||
|
||||
def save_frequency_to_pickle(d, pickle_fname):
|
||||
f = open(pickle_fname, 'wb')
|
||||
with open(pickle_fname, 'wb') as f:
|
||||
exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
|
||||
d2 = {}
|
||||
for k in d:
|
||||
if not k in exclusion_lst and not k.isnumeric() and not len(k) < 2:
|
||||
d2[k] = list(sorted(d[k])) # 原先这里是d2[k] = list(sorted(set(d[k])))
|
||||
pickle.dump(d2, f)
|
||||
f.close()
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,17 +1,10 @@
|
|||
from datetime import datetime
|
||||
from flask import render_template, session, url_for, redirect, request, json, escape, Blueprint
|
||||
from admin_service import ADMIN_NAME
|
||||
from flask import *
|
||||
|
||||
# from app import Yaml
|
||||
# from app.Article import get_today_article, load_freq_history
|
||||
# from app.WordFreq import WordFreq
|
||||
# from app.wordfreqCMD import sort_in_descending_order
|
||||
|
||||
import Yaml
|
||||
from Article import get_today_article, load_freq_history
|
||||
from WordFreq import WordFreq
|
||||
from wordfreqCMD import sort_in_descending_order
|
||||
|
||||
import pickle_idea
|
||||
import pickle_idea2
|
||||
|
||||
|
|
@ -23,7 +16,10 @@ path_prefix = './' # comment this line in deployment
|
|||
|
||||
@userService.route("/get_next_article/<username>",methods=['GET','POST'])
|
||||
def get_next_article(username):
|
||||
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
|
||||
'''
|
||||
得到下一篇文章
|
||||
'''
|
||||
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_{username}.pickle'
|
||||
session['old_articleID'] = session.get('articleID')
|
||||
if request.method == 'GET':
|
||||
visited_articles = session.get("visited_articles")
|
||||
|
|
@ -44,7 +40,10 @@ def get_next_article(username):
|
|||
|
||||
@userService.route("/get_pre_article/<username>",methods=['GET'])
|
||||
def get_pre_article(username):
|
||||
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
|
||||
'''
|
||||
得到上一篇文章
|
||||
'''
|
||||
user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
|
||||
if request.method == 'GET':
|
||||
visited_articles = session.get("visited_articles")
|
||||
if(visited_articles["index"]==0):
|
||||
|
|
@ -85,7 +84,7 @@ def familiar(username, word):
|
|||
:param word:
|
||||
:return:
|
||||
'''
|
||||
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
|
||||
user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
|
||||
pickle_idea.familiar(user_freq_record, word)
|
||||
session['thisWord'] = word # 1. put a word into session
|
||||
session['time'] = 1
|
||||
|
|
@ -100,7 +99,7 @@ def deleteword(username, word):
|
|||
:param word: 单词
|
||||
:return: 重定位到用户界面
|
||||
'''
|
||||
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
|
||||
user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
|
||||
pickle_idea2.deleteRecord(user_freq_record, word)
|
||||
# 模板userpage_get.html中删除单词是异步执行，而flash的信息后续是同步执行的，所以注释这段代码；同时如果这里使用flash但不提取信息，则会影响 signup.html的显示。bug复现：删除单词后，点击退出，点击注册，注册页面就会出现提示信息
|
||||
# flash(f'{word} is no longer in your word list.')
|
||||
|
|
@ -126,7 +125,7 @@ def userpage(username):
|
|||
# 获取session里的用户名
|
||||
username = session.get('username')
|
||||
|
||||
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
|
||||
user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
|
||||
|
||||
if request.method == 'POST': # when we submit a form
|
||||
content = escape(request.form['content'])
|
||||
|
|
@ -134,7 +133,7 @@ def userpage(username):
|
|||
lst = f.get_freq()
|
||||
return render_template('userpage_post.html',username=username,lst = lst, yml=Yaml.yml)
|
||||
|
||||
elif request.method == 'GET': # when we load a html page
|
||||
if request.method == 'GET': # when we load a html page
|
||||
d = load_freq_history(user_freq_record)
|
||||
lst = pickle_idea2.dict2lst(d)
|
||||
lst2 = []
|
||||
|
|
@ -167,7 +166,7 @@ def user_mark_word(username):
|
|||
:return: 重定位到用户界面
|
||||
'''
|
||||
username = session[username]
|
||||
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
|
||||
user_freq_record = path_prefix + 'static/frequency/' + f'frequency_{username}.pickle'
|
||||
if request.method == 'POST':
|
||||
# 提交标记的单词
|
||||
d = load_freq_history(user_freq_record)
|
||||
|
|
@ -178,7 +177,6 @@ def user_mark_word(username):
|
|||
d = pickle_idea2.merge_frequency(lst, lst_history)
|
||||
pickle_idea2.save_frequency_to_pickle(d, user_freq_record)
|
||||
return redirect(url_for('user_bp.userpage', username=username))
|
||||
else:
|
||||
return 'Under construction'
|
||||
|
||||
def get_time():
|
||||
|
|
@ -187,4 +185,3 @@ def get_time():
|
|||
:return: 当前时间
|
||||
'''
|
||||
return datetime.now().strftime('%Y%m%d%H%M') # upper to minutes
|
||||
|
||||
|
|
|
|||
|
|
@ -5,8 +5,8 @@
|
|||
|
||||
import collections
|
||||
import string
|
||||
import operator
|
||||
import os, sys # 引入模块sys，因为我要用里面的sys.argv列表中的信息来读取命令行参数。
|
||||
import os
|
||||
import sys # 引入模块sys，因为我要用里面的sys.argv列表中的信息来读取命令行参数。
|
||||
import pickle_idea
|
||||
|
||||
def freq(fruit):
|
||||
|
|
@ -32,14 +32,16 @@ def youdao_link(s): # 有道链接
|
|||
|
||||
|
||||
def file2str(fname):#文件转字符
|
||||
f = open(fname) #打开
|
||||
s = f.read() #读取
|
||||
f.close() #关闭
|
||||
with open(fname, encoding="utf-8") as f:
|
||||
s = f.read()
|
||||
return s
|
||||
|
||||
|
||||
def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
|
||||
special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
|
||||
'''
|
||||
删除文本里的标点符号
|
||||
'''
|
||||
special_characters = r'\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 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('--', ' ')
|
||||
|
|
@ -78,11 +80,10 @@ def make_html_page(lst, fname): # 只是在wordfreqCMD.py中的main函数中调
|
|||
count = 1
|
||||
for x in lst:
|
||||
# <a href="">word</a>
|
||||
s += '<p>%d <a href="%s">%s</a> (%d)</p>' % (count, youdao_link(x[0]), x[0], x[1])
|
||||
s += f'<p>{count} <a href="{youdao_link(x[0])}">{x[0]}</a> ({x[1]})</p>'
|
||||
count += 1
|
||||
f = open(fname, 'w')
|
||||
with open(fname, 'w', encoding="utf-8") as f:
|
||||
f.write(s)
|
||||
f.close()
|
||||
|
||||
|
||||
## main（程序入口）
|
||||
|
|
@ -101,7 +102,7 @@ if __name__ == '__main__':
|
|||
s = remove_punctuation(s) # 这里是s是实参(argument)，里面有值
|
||||
L = freq(s)
|
||||
for x in sort_in_descending_order(L):
|
||||
print('%s\t%d\t%s' % (x[0], x[1], youdao_link(x[0])))#函数导出
|
||||
print(f'{x[0]}\t{x[1]}\t{youdao_link(x[0])}' )#函数导出
|
||||
|
||||
# 把频率的结果放result.html中
|
||||
make_html_page(sort_in_descending_order(L), 'result.html')
|
||||
|
|
@ -118,6 +119,3 @@ if __name__ == '__main__':
|
|||
lst_history = pickle_idea.dict2lst(d)
|
||||
d = pickle_idea.merge_frequency(L, lst_history)
|
||||
pickle_idea.save_frequency_to_pickle(d, 'frequency.p')
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue