1
0
Fork 0

Compare commits

...

16 Commits

Author SHA1 Message Date
倪玲丽 e19d1ae51b pylint:fixed 2 remove redundant comments 2023-06-05 21:27:20 +08:00
倪玲丽 782783040a pylint:fixed 1 2023-06-04 01:50:13 +08:00
倪玲丽 9a95842b7c delete tanyanmei-fillword.js 2023-06-04 00:39:18 +08:00
倪玲丽 3e0b8a0235 refactor:pylint 2023-06-04 00:35:43 +08:00
Hui Lan b22c654f0f Merge branch 'Bug529-GuHan' of http://121.4.94.30:3000/mrlan/EnglishPal into Alpha-snapshot20230601 2023-06-01 07:40:27 +08:00
倪玲丽 d402bb45cb 刷新屏幕,点击上下篇,加入生词库,停止阅读(更改) 2023-05-31 18:37:05 +08:00
倪玲丽 cdf6180901 刷新屏幕,点击上下篇,加入生词库,停止阅读 2023-05-30 18:48:37 +08:00
倪玲丽 38837c9c2f 合并最新的Alpha-snapshot20230529 2023-05-30 18:45:23 +08:00
黄子睿 a0ddf4bdad 上传文件至 'app/static/js'
修复了 Bug492 选中问号出现多个问号的问题。
解决了选中紧跟标点符号的单词,单词能正常显示。
优化了选中较长的文章时页面容易出现卡顿的问题。
2023-05-27 17:33:37 +08:00
倪玲丽 df64065dcc 点击上下篇,停止阅读 2023-05-06 18:19:24 +08:00
倪玲丽 ce28b91bd5 屏幕刷新,停止阅读 2023-05-06 18:18:12 +08:00
倪玲丽 d6bd24ee1c Merge branch 'Alpha' of http://121.4.94.30:3000/mrlan/EnglishPal into Bug393-TanYanMei
merge alpha
2023-04-24 12:01:08 +08:00
Hui Lan e9e2bd3d23 Remove static\js 2023-04-24 11:43:43 +08:00
Hui Lan 320a99d479 Move Tan Yanmei's fillword.js to app/static/js/tanyanmei-fillword.js. Delete the strange folder static js. 2023-04-24 11:38:16 +08:00
Hui Lan 3eca9234a9 Merge branch 'Bug393-TanYanMei' of http://121.4.94.30:3000/mrlan/EnglishPal into Bug393-TanYanMei 2023-04-24 11:32:15 +08:00
覃艳美 8924166975 上传文件至 'static\js' 2022-06-12 21:23:34 +08:00
15 changed files with 221 additions and 232 deletions

View File

@ -1,14 +1,8 @@
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
@ -33,19 +27,26 @@ def get_article_body(s):
def get_today_article(user_word_list, visited_articles):
'''
根据用户的单词列表和阅读过的文章返回需要的文章的全部信息
'''
rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
if visited_articles is None:
visited_articles = {
"index" : 0, # 为 article_ids 的索引
"index": 0, # 为 article_ids 的索引
"article_ids": [] # 之前显示文章的id列表越后越新
}
if visited_articles["index"] > len(visited_articles["article_ids"])-1: # 生成新的文章,因此查找所有的文章
rq.instructions("SELECT * FROM article")
else: # 生成阅读过的文章,因此查询指定 article_id 的文章
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 +59,23 @@ 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 +92,8 @@ 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']),

View File

@ -1,7 +1,6 @@
import hashlib
import string
from datetime import datetime, timedelta
from UseSqlite import InsertQuery, RecordQuery
def md5(s):
'''
@ -12,14 +11,13 @@ 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
from app.model.user import get_user_by_username, insert_user, update_password_by_username
path_prefix = '/var/www/wordfreq/wordfreq/'
path_prefix = './' # comment this line in deployment
def verify_pass(newpass,oldpass):
if(newpass==oldpass):
if newpass==oldpass:
return True
@ -63,8 +61,7 @@ def get_expiry_date(username):
user = get_user_by_username(username)
if user is None:
return '20191024'
else:
return user.expiry_date
return user.expiry_date
class UserName:
def __init__(self, username):
@ -77,6 +74,7 @@ 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.'
@ -91,5 +89,4 @@ class WarningMessage:
self.s = s
def __str__(self):
return UserName(self.s).validate()
return UserName(self.s).validate()

View File

@ -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):
@ -17,7 +17,7 @@ class WordFreq:
if len(word) > 0 and word[0] in string.ascii_letters:
lst.append(t)
return sort_in_descending_order(lst)
if __name__ == '__main__':
f = WordFreq('BANANA; Banana, apple ORANGE Banana banana.')

View File

@ -6,7 +6,6 @@ Yaml.py
./layout/partial/footer.html
'''
import yaml as YAML
import os
path_prefix = './' # comment this line in deployment

View File

@ -1,46 +1,44 @@
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
'''
# GET方法直接返回注册页面
if request.method == 'GET':
# GET方法直接返回注册页面
return render_template('signup.html')
elif request.method == 'POST':
# POST方法需判断是否注册成功再根据结果返回不同的内容
username = escape(request.form['username'])
password = escape(request.form['password'])
#! 添加如下代码为了过滤注册时的非法字符
warn = WarningMessage(username)
if str(warn) != 'OK':
return jsonify({'status': '3', 'warn': str(warn)})
available = check_username_availability(username)
if not available: # 用户名不可用
return jsonify({'status': '0'})
else: # 添加账户信息
add_user(username, password)
verified = verify_user(username, password)
if verified:
# 写入session
session['logged_in'] = True
session[username] = username
session['username'] = username
session['expiry_date'] = get_expiry_date(username)
session['visited_articles'] = None
return jsonify({'status': '2'})
else:
return jsonify({'status': '1'})
# POST方法需判断是否注册成功再根据结果返回不同的内容
username = escape(request.form['username'])
password = escape(request.form['password'])
#! 添加如下代码为了过滤注册时的非法字符
warn = WarningMessage(username)
if str(warn) != 'OK':
return jsonify({'status': '3', 'warn': str(warn)})
available = check_username_availability(username)
# 用户名不可用
if not available:
return jsonify({'status': '0'})
# 用户名可用,添加账户信息
add_user(username, password)
verified = verify_user(username, password)
# 注册成功写入session
if verified:
session['logged_in'] = True
session[username] = username
session['username'] = username
session['expiry_date'] = get_expiry_date(username)
session['visited_articles'] = None
return jsonify({'status': '2'})
# 验证失败
return jsonify({'status': '1'})
@ -50,26 +48,25 @@ 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
username = escape(request.form['username'])
password = escape(request.form['password'])
verified = verify_user(username, password)
if verified:
# 登录成功写入session
session['logged_in'] = True
session[username] = username
session['username'] = username
user_expiry_date = get_expiry_date(username)
session['expiry_date'] = user_expiry_date
session['visited_articles'] = None
return jsonify({'status': '1'})
else:
return jsonify({'status': '0'})
# POST方法用于判断登录是否成功检查数据库并验证用户再根据结果返回不同的内容
username = escape(request.form['username'])
password = escape(request.form['password'])
verified = verify_user(username, password)
# 登录成功写入session
if verified:
session['logged_in'] = True
session[username] = username
session['username'] = username
user_expiry_date = get_expiry_date(username)
session['expiry_date'] = user_expiry_date
session['visited_articles'] = None
return jsonify({'status': '1'})
#验证失败
return jsonify({'status': '0'})
@accountService.route("/logout", methods=['GET', 'POST'])
@ -95,16 +92,18 @@ def reset():
username = session['username']
if username == '':
return redirect('/login')
# GET请求返回修改密码页面
if request.method == 'GET':
# GET请求返回修改密码页面
return render_template('reset.html', username=session['username'], state='wait')
else:
# POST请求用于提交修改后信息
old_password = escape(request.form['old-password'])
new_password = escape(request.form['new-password'])
flag = change_password(username, old_password, new_password) # flag表示是否修改成功
if flag:
session['logged_in'] = False
return jsonify({'status':'1'}) # 修改成功
else:
return jsonify({'status':'2'}) # 修改失败
# POST请求用于提交修改后信息
old_password = escape(request.form['old-password'])
new_password = escape(request.form['new-password'])
flag = change_password(username, old_password, new_password) # flag表示是否修改成功
# 修改成功
if flag:
session['logged_in'] = False
return jsonify({'status':'1'})
# 修改失败
return jsonify({'status':'2'})

View File

@ -1,17 +1,17 @@
# 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():
# 未登录,跳转到未登录界面
if not session.get("logged_in"):
@ -26,6 +26,10 @@ 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 +41,11 @@ 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 +58,15 @@ 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 +80,19 @@ 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 +110,21 @@ 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 +139,9 @@ 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 +150,7 @@ 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

View File

@ -6,15 +6,14 @@
# 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')
d = pickle.load(f)
f.close()
with open(pickle_fname, 'rb') as f:
d = pickle.load(f)
return d
@ -53,9 +52,7 @@ 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 +85,9 @@ 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
@ -242,10 +242,7 @@ 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')
s = f.read()
f.close()
print(text_difficulty_level(s, d3))
with open('wordlist.txt', encoding='utf-8') as f:
s = f.read()
print(text_difficulty_level(s, d3))

View File

@ -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!'
@ -51,8 +58,7 @@ def appears_in_test(word, d):
'''
if not word in d:
return ''
else:
return ','.join(d[word])
return ','.join(d[word])
@app.route("/mark", methods=['GET', 'POST'])
@ -70,8 +76,8 @@ def mark_word():
d = pickle_idea.merge_frequency(lst, lst_history)
pickle_idea.save_frequency_to_pickle(d, path_prefix + 'static/frequency/frequency.p')
return redirect(url_for('mainpage'))
else: # 不回应GET请求
return 'Under construction'
# 不回应GET请求
return 'Under construction'
@app.route("/", methods=['GET', 'POST'])
@ -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')

View File

@ -19,15 +19,15 @@ def lst2dict(lst, d):
for x in lst:
word = x[0]
freq = x[1]
if not word in d:
d[word] = freq
if word not in d:
d[word] = freq
else:
d[word] += freq
def dict2lst(d):
return list(d.items()) # a list of (key, value) pairs
def merge_frequency(lst1, lst2):
d = {}
@ -37,29 +37,27 @@ def merge_frequency(lst1, lst2):
def load_record(pickle_fname):
f = open(pickle_fname, 'rb')
d = pickle.load(f)
f.close()
with open(pickle_fname, 'rb') as f:
d = pickle.load(f)
return d
def save_frequency_to_pickle(d, pickle_fname):
f = open(pickle_fname, 'wb')
#exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
exclusion_lst = []
d2 = {}
for k in d:
if not k in exclusion_lst and not k.isnumeric() and len(k) > 1:
d2[k] = d[k]
pickle.dump(d2, f)
f.close()
with open(pickle_fname, 'wb') as f:
#exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
exclusion_lst = []
d2 = {}
for k in d:
if not k in exclusion_lst and not k.isnumeric() and len(k) > 1:
d2[k] = d[k]
pickle.dump(d2, f)
def unfamiliar(path,word):
f = open(path,"rb")
dic = pickle.load(f)
with open(path,"rb") as f:
dic = pickle.load(f)
dic[word] += [datetime.now().strftime('%Y%m%d%H%M')]
fp = open(path,"wb")
pickle.dump(dic,fp)
with open(path,"wb") as fp:
pickle.dump(dic,fp)
def familiar(path,word):
f = open(path,"rb")
@ -68,8 +66,8 @@ 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__':

View File

@ -33,7 +33,7 @@ def deleteRecord(path,word):
except KeyError:
print("sorry")
with open(path, 'wb') as ff:
pickle.dump(db, ff)
pickle.dump(db, ff)
def dict2lst(d):
if len(d) > 0:
@ -43,7 +43,7 @@ def dict2lst(d):
for k in d:
lst.append((k, [datetime.now().strftime('%Y%m%d%H%M')]))
return lst
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')
d = pickle.load(f)
f.close()
with open(pickle_fname, 'rb') as f:
d = pickle.load(f)
return d
def save_frequency_to_pickle(d, pickle_fname):
f = open(pickle_fname, 'wb')
exclusion_lst = ['one', 'no', 'has', 'had', 'do', 'that', 'have', 'by', 'not', 'but', 'we', 'this', 'my', 'him', 'so', 'or', 'as', 'are', 'it', 'from', 'with', 'be', 'can', 'for', 'an', 'if', 'who', 'whom', 'whose', 'which', 'the', 'to', 'a', 'of', 'and', 'you', 'i', 'he', 'she', 'they', 'me', 'was', 'were', 'is', 'in', 'at', 'on', 'their', 'his', 'her', 's', 'said', 'all', 'did', 'been', 'w']
d2 = {}
for k in d:
if not k in exclusion_lst and not k.isnumeric() and not len(k) < 2:
d2[k] = list(sorted(d[k])) # 原先这里是d2[k] = list(sorted(set(d[k])))
pickle.dump(d2, f)
f.close()
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)
@ -86,4 +84,4 @@ if __name__ == '__main__':
d = load_record('frequency.p')
lst1 = dict2lst(d)
d = merge_frequency(lst2, lst1)
print(d)
print(d)

View File

@ -29,3 +29,7 @@ function onReadClick() {
function onChooseClick() {
isChoose = !isChoose;
}
if (performance.navigation.type == 1) { //如果网页刷新,停止播放声音
Reader.stopRead();
}

View File

@ -22,33 +22,19 @@ function getWord() {
function highLight() {
if (!isHighlight) return;
let articleContent = document.getElementById("article").innerText; //将原来的.innerText改为.innerHtml使用innerText会把原文章中所包含的<br>标签去除,导致处理后的文章内容失去了原来的格式
let articleContent = document.getElementById("article").innerText;
let pickedWords = document.getElementById("selected-words"); // words picked to the text area
let dictionaryWords = document.getElementById("selected-words2"); // words appearing in the user's new words list
let allWords = ""; //初始化allWords的值避免进入判断后编译器认为allWords未初始化的问题
if(dictionaryWords != null){//增加一个判断检查生词本里面是否为空如果为空allWords只添加选中的单词
allWords = pickedWords.value + " " + dictionaryWords.value;
}
else{
allWords = pickedWords.value + " ";
}
const list = allWords.split(" ");//将所有的生词放入一个list中用于后续处理
let allWords = dictionaryWords === null ? pickedWords.value + " " : pickedWords.value + " " + dictionaryWords.value;
const list = allWords.split(" "); // 将所有的生词放入一个list中用于后续处理
for (let i = 0; i < list.length; ++i) {
list[i] = list[i].replace(/(^\s*)|(\s*$)/g, ""); //消除单词两边的空字符
list[i] = list[i].replace('|', "");
list[i] = list[i].replace('?', "");
if (list[i] !== "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
//将文章中所有出现该单词word的地方改为"<mark>" + word + "<mark>"。 正则表达式RegExp()中,"\\b"代表单词边界匹配。
//修改代码
let articleContent_fb = articleContent; //文章副本
while(articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase()) !== -1 && list[i]!=""){
//找到副本中和list[i]匹配的第一个单词(第一种匹配情况),并赋值给list[i]。
const index = articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase());
list[i] = articleContent_fb.substring(index, index + list[i].length);
articleContent_fb = articleContent_fb.substring(index + list[i].length); // 使用副本中list[i]之后的子串替换掉副本
articleContent = articleContent.replace(new RegExp("\\b"+list[i]+"\\b","g"),"<mark>" + list[i] + "</mark>");
list[i] = list[i].replace(/(^\W*)|(\W*$)/g, ""); // 消除单词两边的非单词字符
if (list[i] != "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
// 返回所有匹配单词的集合, 正则表达式RegExp()中, "\b"匹配一个单词的边界, g 表示全局匹配, i 表示对大小写不敏感。
let matches = new Set(articleContent.match(new RegExp("\\b" + list[i] + "\\b", "gi")));
for (let word of matches) {
// 将文章中所有出现该单词word的地方改为"<mark>" + word + "<mark>"。
articleContent = articleContent.replace(new RegExp("\\b" + word + "\\b", "g"), "<mark>" + word + "</mark>");
}
}
}

View File

@ -49,8 +49,8 @@
{# <div class="alert alert-warning" role="alert">Congratulations! {{ message }}</div>#}
{# {% endfor %}#}
<button class="btn btn-success" id="load_next_article" onclick="load_next_article()"> 下一篇 Next Article </button>
<button class="btn btn-success" id="load_pre_article" onclick="load_pre_article()" > 上一篇 Previous Article </button>
<button class="btn btn-success" id="load_next_article" onclick="load_next_article();Reader.stopRead()"> 下一篇 Next Article </button>
<button class="btn btn-success" id="load_pre_article" onclick="load_pre_article();Reader.stopRead()" > 上一篇 Previous Article </button>
<p><b>阅读文章并回答问题</b></p>
<div id="text-content">
@ -97,7 +97,7 @@
<p><b>收集生词吧</b> (可以在正文中划词,也可以复制黏贴)</p>
<form method="post" action="/{{ username }}/userpage">
<textarea name="content" id="selected-words" rows="10" cols="120"></textarea><br/>
<input type="submit" value="把生词加入我的生词库"/>
<input type="submit" value="把生词加入我的生词库" onclick="Reader.stopRead()"/>
<input type="reset" value="清除"/>
</form>
{% if session.get['thisWord'] %}

View File

@ -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 +16,7 @@ path_prefix = './' # comment this line in deployment
@userService.route("/get_next_article/<username>",methods=['GET','POST'])
def get_next_article(username):
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
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 +37,7 @@ def get_next_article(username):
@userService.route("/get_pre_article/<username>",methods=['GET'])
def get_pre_article(username):
user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
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 +78,7 @@ 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 +93,7 @@ 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 +119,7 @@ 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 +127,7 @@ 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 +160,7 @@ 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)
@ -178,13 +171,11 @@ 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'
return 'Under construction'
def get_time():
'''
获取当前时间
:return: 当前时间
'''
return datetime.now().strftime('%Y%m%d%H%M') # upper to minutes
return datetime.now().strftime('%Y%m%d%H%M') # upper to minutes

View File

@ -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):
@ -18,7 +18,7 @@ def freq(fruit):
'''
result = []
fruit = fruit.lower() # 字母转小写
flst = fruit.split() # 字符串转成list
c = collections.Counter(flst)
@ -32,19 +32,18 @@ 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 = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
special_characters = r'\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 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('--', ' ')
s = s.strip() # 去除前后的空格
if '\'' in s:
n = len(s)
t = '' # 用来收集我需要保留的字符
@ -78,11 +77,10 @@ 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')
f.write(s)
f.close()
with open(fname, 'w', encoding="utf-8") as f:
f.write(s)
## main程序入口
@ -101,10 +99,10 @@ if __name__ == '__main__':
s = remove_punctuation(s) # 这里是s是实参(argument),里面有值
L = freq(s)
for x in sort_in_descending_order(L):
print('%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')
make_html_page(sort_in_descending_order(L), 'result.html')
print('\nHistory:\n')
if os.path.exists('frequency.p'):
@ -118,6 +116,3 @@ 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')