Pylint部分：
1. 补充module docstring，即文档顶部的简要说明 （我做的说明很简陋，只是为了通过pylint的检查而为之）
2. 优化了if-else-return，即删除了不必要的elif或else
3. 拆分了所有在同一行的模块引用（不同模块的引用需要放在不同行，以便理解和阅读）
4. 删除了部分没有被使用的引用（有的引用在文件A中被使用了，但import却写在了文件B，且文件B没有使用这些引用，而文件A引用了文件B，导致文件B的所有引用也被A引用，这似乎并不合理）
5. 修改了引用的顺序（os、random等系统引用应放在自定义模块引用的上方）
6. 修改了过长的代码，注释除外（每行限制在100个字符以内）
7. 优化了条件判断的判断符号：
is和is not 用于判断两个变量是否指向同一个位置
== 和 !=用于比较两个变量
8. 为每个py文件添加了"last new line"，删除了多余的尾部空行
Pylint提示了但是没有进行的操作：
1. 将字符串改为f-string的格式
因为f-string需要python3.6以上的版本，为了防止出现版本问题，故不做修改
2. 将所有函数内的return内容改为一致的类型
因为原有的代码逻辑已经确定，修改return的类型会导致方法的无法使用，故不做修改
3. 将标识符的格式改为"snake_case naming style"
标识符的修改内容过于庞大，且可能出现程序不可预见的错误，在pylint中重要等级为0，故不做修改
JSLint Part:
1. 提高代码的可读性：将部分超过80个字符的代码行拆解开（由于文字注释的存在，很多语句仅注释就超过了80个字符，此类型的语句行不做修改）
2. 用===与！==代替==与！=的判断
3. 将i++改为i+=1
4. 分离for循环中的let与var到其他行中，以适应JSLint在循环语句中对var和let的偏好
5. 给三元表达式外围添加圆括号，避免出现优先级的问题
6. 将正则表达式修改为JSLint要求的多行模式
疑问：
形如：
for (let i = 0; i < list.length; i+=1) {
的语句，JSLint报错： [JSLint was unable to finish] Unexpected 'let'.
但是网上搜索到的结果是ES6是支持let的使用的，暂且不做修改。
Refactor_qianjunqi
parent
43c719b6b2
commit
ea16ea6673
|
|
@ -1,3 +1,6 @@
|
|||
"""
|
||||
This module provides functions about article
|
||||
"""
|
||||
from WordFreq import WordFreq
|
||||
from wordfreqCMD import youdao_link, sort_in_descending_order
|
||||
from UseSqlite import InsertQuery, RecordQuery
|
||||
|
|
@ -46,7 +49,6 @@ def get_today_article(user_word_list, articleID):
|
|||
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)
|
||||
|
||||
d = {}
|
||||
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.
|
||||
|
|
|
|||
29
app/Login.py
29
app/Login.py
|
|
@ -1,3 +1,6 @@
|
|||
"""
|
||||
This module provides methods for Login
|
||||
"""
|
||||
import hashlib
|
||||
import string
|
||||
from datetime import datetime, timedelta
|
||||
|
|
@ -7,15 +10,17 @@ 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
|
||||
|
||||
|
||||
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.instructions_with_parameters(
|
||||
"SELECT * FROM user WHERE name=:username AND password=:password",
|
||||
dict( # the named style https://docs.python.org/3/library/sqlite3.html
|
||||
username=username,
|
||||
password=password))
|
||||
rq.do_with_parameters()
|
||||
result = rq.get_results()
|
||||
return result != []
|
||||
|
|
@ -23,12 +28,19 @@ def verify_user(username, password):
|
|||
|
||||
def add_user(username, password):
|
||||
start_date = datetime.now().strftime('%Y%m%d')
|
||||
expiry_date = (datetime.now() + timedelta(days=30)).strftime('%Y%m%d') # will expire after 30 days
|
||||
# will expire after 30 days
|
||||
expiry_date = (datetime.now() + timedelta(days=30)).strftime('%Y%m%d')
|
||||
# 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.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()
|
||||
|
||||
|
||||
|
|
@ -96,7 +108,7 @@ 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']:
|
||||
return 'You used a restricted word as your user name. Please come up with a better one.'
|
||||
|
|
@ -110,4 +122,3 @@ class WarningMessage:
|
|||
|
||||
def __str__(self):
|
||||
return UserName(self.s).validate()
|
||||
|
||||
|
|
|
|||
|
|
@ -2,9 +2,12 @@
|
|||
# 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
|
||||
"""
|
||||
This module produces word frequency
|
||||
"""
|
||||
import string
|
||||
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
|
||||
|
||||
|
||||
class WordFreq:
|
||||
def __init__(self, s):
|
||||
|
|
@ -22,4 +25,3 @@ class WordFreq:
|
|||
if __name__ == '__main__':
|
||||
f = WordFreq('BANANA; Banana, apple ORANGE Banana banana.')
|
||||
print(f.get_freq())
|
||||
|
||||
|
|
|
|||
|
|
@ -1,54 +1,54 @@
|
|||
"""
|
||||
This module provides services about account.
|
||||
"""
|
||||
from flask import *
|
||||
from Login import check_username_availability, verify_user, add_user, get_expiry_date, change_password, WarningMessage
|
||||
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
|
||||
@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':
|
||||
if 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'])
|
||||
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)
|
||||
|
||||
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
|
||||
if len(password.strip()) < 4: # 密码过短
|
||||
return '密码过于简单。'
|
||||
elif password != password2:
|
||||
if password != password2:
|
||||
return '确认密码与输入密码不一致！'
|
||||
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['articleID'] = None
|
||||
return '<p>恭喜，你已成功注册， 你的用户名是 <a href="%s">%s</a>。</p>\
|
||||
<p><a href="/%s">开始使用</a> <a href="/">返回首页</a><p/>' % (username, username, username)
|
||||
else:
|
||||
return '用户名密码验证失败。'
|
||||
|
||||
add_user(username, password)# 添加账户信息
|
||||
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['articleID'] = None
|
||||
return '<p>恭喜，你已成功注册， 你的用户名是 <a href="%s">%s</a>。</p>\
|
||||
<p><a href="/%s">开始使用</a> <a href="/">返回首页</a><p/>' % (username, username, username)
|
||||
return '用户名密码验证失败。'
|
||||
|
||||
|
||||
@accountService.route("/login", methods=['GET', 'POST'])
|
||||
|
|
@ -62,11 +62,10 @@ def login():
|
|||
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 <a href="/%s">%s</a>。 登出点击<a href="/logout">这里</a>。' % (
|
||||
# 已登录，提示信息并显示登出按钮
|
||||
return '你已登录 <a href="/%s">%s</a>。 登出点击<a href="/logout">这里</a>。' % (
|
||||
session['username'], session['username'])
|
||||
elif request.method == 'POST':
|
||||
if 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'])
|
||||
|
|
@ -81,8 +80,7 @@ def login():
|
|||
session['expiry_date'] = user_expiry_date
|
||||
session['articleID'] = None
|
||||
return redirect(url_for('user_bp.userpage', username=username))
|
||||
else:
|
||||
return '无法通过验证。'
|
||||
return '无法通过验证。'
|
||||
|
||||
|
||||
@accountService.route("/logout", methods=['GET', 'POST'])
|
||||
|
|
@ -111,21 +109,18 @@ def reset():
|
|||
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'])
|
||||
|
||||
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 \
|
||||
# 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 \
|
||||
'''
|
||||
<script>
|
||||
alert('密码修改成功，请重新登录。');
|
||||
|
|
@ -134,8 +129,7 @@ window.location.href="/login";
|
|||
|
||||
'''
|
||||
|
||||
else:
|
||||
return \
|
||||
|
||||
'''
|
||||
<script>
|
||||
alert('密码修改失败');
|
||||
|
|
|
|||
|
|
@ -3,8 +3,10 @@
|
|||
# Written permission must be obtained from the author for commercial uses.
|
||||
###########################################################################
|
||||
|
||||
# Purpose: compute difficulty level of a English text
|
||||
|
||||
"""
|
||||
This module provides functions for calculating user words difficulty
|
||||
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
|
||||
|
|
@ -23,8 +25,8 @@ def difficulty_level_from_frequency(word, 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)
|
||||
ratio = (d['what'] + 1) / (d[word] + 1) # what is a frequent word
|
||||
level = math.log(max(ratio, 1), 2)
|
||||
|
||||
level = min(level, 8)
|
||||
return level
|
||||
|
|
@ -33,18 +35,18 @@ def difficulty_level_from_frequency(word, d):
|
|||
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
|
||||
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
|
||||
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
|
||||
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.
|
||||
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)
|
||||
|
|
@ -52,7 +54,6 @@ def get_difficulty_level(d1, d2):
|
|||
return d
|
||||
|
||||
|
||||
|
||||
def revert_dict(d):
|
||||
'''
|
||||
In d, word is the key, and value is a list of dates.
|
||||
|
|
@ -62,12 +63,13 @@ 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 +78,43 @@ 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)
|
||||
for x in L:
|
||||
word = x[0]
|
||||
if 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:
|
||||
|
|
@ -119,22 +122,18 @@ 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)
|
||||
|
||||
|
|
@ -197,7 +196,6 @@ 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 +216,6 @@ 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 +230,9 @@ 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')
|
||||
# f = open('bbc-fulltext/bbc/entertainment/001.txt')
|
||||
f = open('wordlist.txt',encoding="utf-8")
|
||||
s = f.read()
|
||||
f.close()
|
||||
|
||||
|
||||
|
||||
|
||||
print(text_difficulty_level(s, d3))
|
||||
|
||||
|
||||
|
|
|
|||
10
app/main.py
10
app/main.py
|
|
@ -52,8 +52,7 @@ 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'])
|
||||
|
|
@ -71,8 +70,8 @@ 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'])
|
||||
|
|
@ -92,7 +91,7 @@ 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')
|
||||
|
|
@ -102,7 +101,6 @@ def mainpage():
|
|||
d_len=d_len, lst=lst, yml=Yaml.yml)
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
'''
|
||||
运行程序
|
||||
|
|
|
|||
|
|
@ -3,9 +3,10 @@
|
|||
# Written permission must be obtained from the author for commercial uses.
|
||||
###########################################################################
|
||||
|
||||
# Purpose: dictionary & pickle as a simple means of database.
|
||||
# Task: incorporate the functions into wordfreqCMD.py such that it will also show cumulative frequency.
|
||||
|
||||
"""
|
||||
Purpose: dictionary & pickle as a simple means of database.
|
||||
Task: incorporate the functions into wordfreqCMD.py such that it will also show cumulative frequency.
|
||||
"""
|
||||
import pickle
|
||||
from datetime import datetime
|
||||
|
||||
|
|
|
|||
|
|
@ -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 []
|
||||
|
|
|
|||
|
|
@ -11,34 +11,39 @@ function getWord() {
|
|||
|
||||
function fillInWord() {
|
||||
let word = getWord();
|
||||
if (isRead) read(word);
|
||||
if (!isChoose) return;
|
||||
if (isRead) {read(word);}
|
||||
if (!isChoose) {return;}
|
||||
const element = document.getElementById("selected-words");
|
||||
element.value = element.value + " " + word;
|
||||
}
|
||||
|
||||
document.getElementById("text-content").addEventListener("click", fillInWord, false);
|
||||
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") {
|
||||
msg.onboundary = function(ev) {
|
||||
if (ev.name === "word") {
|
||||
current_position = ev.charIndex;
|
||||
}
|
||||
}
|
||||
};
|
||||
return msg;
|
||||
}
|
||||
|
||||
const sliderValue = document.getElementById("rangeValue"); // 显示值
|
||||
const inputSlider = document.getElementById("rangeComponent"); // 滑块元素
|
||||
inputSlider.oninput = () => {
|
||||
inputSlider.oninput = function(){
|
||||
let value = inputSlider.value; // 获取滑块的值
|
||||
sliderValue.textContent = value + '×';
|
||||
if (!reader.speaking) return;
|
||||
sliderValue.textContent = value + "×";
|
||||
if (!reader.speaking) {return;}
|
||||
reader.cancel();
|
||||
let msg = makeUtterance(to_speak.substring(original_position + current_position), value);
|
||||
let msg = makeUtterance(
|
||||
to_speak.substring(original_position + current_position),
|
||||
value
|
||||
);
|
||||
original_position = original_position + current_position;
|
||||
current_position = 0;
|
||||
reader.speak(msg);
|
||||
|
|
|
|||
|
|
@ -2,44 +2,60 @@ let isHighlight = true;
|
|||
|
||||
function cancelBtnHandler() {
|
||||
cancelHighlighting();
|
||||
document.getElementById("text-content").removeEventListener("click", fillInWord, false);
|
||||
document.getElementById("text-content").removeEventListener("touchstart", fillInWord, false);
|
||||
document.getElementById("text-content").addEventListener("click", fillInWord2, false);
|
||||
document.getElementById("text-content").addEventListener("touchstart", fillInWord2, false);
|
||||
document
|
||||
.getElementById("text-content")
|
||||
.removeEventListener("click", fillInWord, false);
|
||||
document.getElementById("text-content")
|
||||
.removeEventListener("touchstart", fillInWord, false);
|
||||
document.getElementById("text-content")
|
||||
.addEventListener("click", fillInWord2, false);
|
||||
document.getElementById("text-content")
|
||||
.addEventListener("touchstart", fillInWord2, false);
|
||||
}
|
||||
|
||||
function showBtnHandler() {
|
||||
document.getElementById("text-content").removeEventListener("click", fillInWord2, false);
|
||||
document.getElementById("text-content").removeEventListener("touchstart", fillInWord2, false);
|
||||
document.getElementById("text-content").addEventListener("click", fillInWord, false);
|
||||
document.getElementById("text-content").addEventListener("touchstart", fillInWord, false);
|
||||
document.getElementById("text-content")
|
||||
.removeEventListener("click", fillInWord2, false);
|
||||
document.getElementById("text-content")
|
||||
.removeEventListener("touchstart", fillInWord2, false);
|
||||
document.getElementById("text-content")
|
||||
.addEventListener("click", fillInWord, false);
|
||||
document.getElementById("text-content")
|
||||
.addEventListener("touchstart", fillInWord, false);
|
||||
highLight();
|
||||
}
|
||||
|
||||
function getWord() {
|
||||
return window.getSelection ? window.getSelection() : document.selection.createRange().text;
|
||||
return (window.getSelection ?
|
||||
window.getSelection() :
|
||||
document.selection.createRange().text);
|
||||
}
|
||||
|
||||
function highLight() {
|
||||
if (!isHighlight) return;
|
||||
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 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
|
||||
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
|
||||
for (let i = 0; i < list.length; ++i) {
|
||||
list[i] = list[i].replace(/(^\s*)|(\s*$)/g, ""); //消除单词两边的空字符
|
||||
list[i] = list[i].replace('|', "");
|
||||
list[i] = list[i].replace('?', "");
|
||||
if (list[i] !== "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
|
||||
//将文章中所有出现该单词word的地方改为：" <mark>" + word + "<mark> "。 正则表达式RegExp()中，"\\s"代表单词前后必须要有空格，以防止只对单词中的部分字符高亮的情况出现。
|
||||
articleContent = articleContent.replace(new RegExp("\\s"+list[i]+"\\s", "g"), " <mark>" + list[i] + "</mark> ");
|
||||
for (let i = 0; i < list.length; i+=1) {
|
||||
list[i] = list[i].replace(/(^\s*)|(\s*$)/gm, ""); //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，"\\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"),
|
||||
" <mark>" + list[i] + "</mark> ");
|
||||
}
|
||||
}
|
||||
document.getElementById("article").innerHTML = articleContent;
|
||||
|
|
@ -50,21 +66,27 @@ function cancelHighlighting() {
|
|||
let pickedWords = document.getElementById("selected-words");
|
||||
const dictionaryWords = document.getElementById("selected-words2");
|
||||
const list = pickedWords.value.split(" ");
|
||||
if (pickedWords != null) {
|
||||
for (let i = 0; i < list.length; ++i) {
|
||||
list[i] = list[i].replace(/(^\s*)|(\s*$)/g, "");
|
||||
if (pickedWords !== null) {
|
||||
for (let i = 0; i < list.length; i+=1) {
|
||||
list[i] = list[i].replace(/(^\s*)|(\s*$)/gm, "");
|
||||
if (list[i] !== "") { //原来判断的代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
|
||||
articleContent = articleContent.replace(new RegExp("<mark>"+list[i]+"</mark>", "g"), list[i]);
|
||||
articleContent = articleContent.replace(
|
||||
new RegExp("<mark>"+list[i]+"</mark>", "g"),
|
||||
list[i]
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
if (dictionaryWords != null) {
|
||||
if (dictionaryWords !== null) {
|
||||
let list2 = pickedWords.value.split(" ");
|
||||
for (let i = 0; i < list2.length; ++i) {
|
||||
for (let i = 0; i < list2.length; i+=1) {
|
||||
list2 = dictionaryWords.value.split(" ");
|
||||
list2[i] = list2[i].replace(/(^\s*)|(\s*$)/g, "");
|
||||
list2[i] = list2[i].replace(/(^\s*)|(\s*$)/gm, "");
|
||||
if (list2[i] !== "") { //原来代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
|
||||
articleContent = articleContent.replace(new RegExp("<mark>"+list2[i]+"</mark>", "g"), list2[i]);
|
||||
articleContent = articleContent.replace(
|
||||
new RegExp("<mark>"+list2[i]+"</mark>", "g"),
|
||||
list2[i]
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -3,17 +3,17 @@ function familiar(theWord) {
|
|||
let word = $("#word_" + theWord).text();
|
||||
let freq = $("#freq_" + theWord).text();
|
||||
$.ajax({
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/familiar",
|
||||
success:function(response){
|
||||
let new_freq = freq - 1;
|
||||
const allow_move = document.getElementById("move_dynamiclly").checked;
|
||||
const allow_move = document
|
||||
.getElementById("move_dynamiclly")
|
||||
.checked;
|
||||
if (allow_move) {
|
||||
|
||||
if (new_freq <= 0) {
|
||||
removeWord(theWord);
|
||||
} else {
|
||||
renderWord({ word: theWord, freq: new_freq });
|
||||
renderWord({ freq: new_freq,word: theWord });
|
||||
}
|
||||
} else {
|
||||
if(new_freq <1) {
|
||||
|
|
@ -22,7 +22,9 @@ function familiar(theWord) {
|
|||
$("#freq_" + theWord).text(new_freq);
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/familiar"
|
||||
});
|
||||
}
|
||||
|
||||
|
|
@ -31,34 +33,38 @@ function unfamiliar(theWord) {
|
|||
let word = $("#word_" + theWord).text();
|
||||
let freq = $("#freq_" + theWord).text();
|
||||
$.ajax({
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/unfamiliar",
|
||||
success:function(response){
|
||||
let new_freq = parseInt(freq) + 1;
|
||||
const allow_move = document.getElementById("move_dynamiclly").checked;
|
||||
const allow_move = document
|
||||
.getElementById("move_dynamiclly")
|
||||
.checked;
|
||||
if (allow_move) {
|
||||
renderWord({ word: theWord, freq: new_freq });
|
||||
renderWord({ freq: new_freq,word: theWord });
|
||||
} else {
|
||||
$("#freq_" + theWord).text(new_freq);
|
||||
}
|
||||
}
|
||||
},
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/unfamiliar"
|
||||
});
|
||||
}
|
||||
|
||||
function delete_word(theWord) {
|
||||
let username = $("#username").text();
|
||||
let word = theWord.replace('&', '&');
|
||||
let word = theWord.replace("&", "&");
|
||||
$.ajax({
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/del",
|
||||
success:function(response){
|
||||
const allow_move = document.getElementById("move_dynamiclly").checked;
|
||||
const allow_move = document
|
||||
.getElementById("move_dynamiclly")
|
||||
.checked;
|
||||
if (allow_move) {
|
||||
removeWord(theWord);
|
||||
} else {
|
||||
$("#p_" + theWord).remove();
|
||||
}
|
||||
}
|
||||
},
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/del"
|
||||
});
|
||||
}
|
||||
|
||||
|
|
@ -75,11 +81,12 @@ function delete_word(theWord) {
|
|||
function parseWord(element) {
|
||||
const word = element
|
||||
.querySelector("a.btn.btn-light[role=button]") // 获取当前词频元素的词汇元素
|
||||
.innerText // 获取词汇值;
|
||||
const freq = Number.parseInt(element.querySelector(`#freq_${word}`).innerText); // 获取词汇的数量
|
||||
.innerText; // 获取词汇值;
|
||||
const freq = Number// 获取词汇的数量
|
||||
.parseInt(element.querySelector(`#freq_${word}`).innerText);
|
||||
return {
|
||||
word,
|
||||
freq
|
||||
freq,
|
||||
word
|
||||
};
|
||||
}
|
||||
|
||||
|
|
@ -104,7 +111,7 @@ function wordTemplate(word) {
|
|||
*/
|
||||
function removeWord(word) {
|
||||
// 根据词频信息删除元素
|
||||
word = word.replace('&', '&');
|
||||
word = word.replace("&", "&");
|
||||
const element_to_remove = document.getElementById(`p_${word}`);
|
||||
if (element_to_remove != null) {
|
||||
element_to_remove.remove();
|
||||
|
|
@ -134,7 +141,11 @@ function renderWord(word) {
|
|||
// 让发生变化的元素抖动
|
||||
new_element.classList.add("shaking");
|
||||
// 移动到该元素
|
||||
new_element.scrollIntoView({behavior: "smooth", block: "center", inline: "nearest"});
|
||||
new_element.scrollIntoView({
|
||||
behavior: "smooth",
|
||||
block: "center",
|
||||
inline: "nearest"
|
||||
});
|
||||
// 抖动完毕后删除抖动类
|
||||
setTimeout(() => {
|
||||
new_element.classList.remove("shaking");
|
||||
|
|
@ -145,7 +156,7 @@ function renderWord(word) {
|
|||
* 从string中创建一个HTML元素并返回
|
||||
*/
|
||||
function elementFromString(string) {
|
||||
const d = document.createElement('div');
|
||||
const d = document.createElement("div");
|
||||
d.innerHTML = string;
|
||||
return d.children.item(0);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,5 +1,7 @@
|
|||
"""
|
||||
This module provides methods for user_services
|
||||
"""
|
||||
from datetime import datetime
|
||||
|
||||
from flask import *
|
||||
|
||||
# from app import Yaml
|
||||
|
|
@ -36,6 +38,7 @@ def user_reset(username):
|
|||
else:
|
||||
return 'Under construction'
|
||||
|
||||
|
||||
@userService.route("/<username>/back", methods=['GET'])
|
||||
def user_back(username):
|
||||
'''
|
||||
|
|
@ -48,7 +51,6 @@ def user_back(username):
|
|||
return redirect(url_for('user_bp.userpage', username=username))
|
||||
|
||||
|
||||
|
||||
@userService.route("/<username>/<word>/unfamiliar", methods=['GET', 'POST'])
|
||||
def unfamiliar(username, word):
|
||||
'''
|
||||
|
|
@ -141,9 +143,6 @@ def userpage(username):
|
|||
words=words)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@userService.route("/<username>/mark", methods=['GET', 'POST'])
|
||||
def user_mark_word(username):
|
||||
'''
|
||||
|
|
|
|||
|
|
@ -2,13 +2,16 @@
|
|||
# Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
|
||||
# Written permission must be obtained from the author for commercial uses.
|
||||
###########################################################################
|
||||
|
||||
"""
|
||||
This Module produces word frequency
|
||||
"""
|
||||
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, 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):
|
||||
'''
|
||||
功能： 把字符串转成列表。 目的是得到每个单词的频率。
|
||||
|
|
@ -18,40 +21,39 @@ def freq(fruit):
|
|||
'''
|
||||
|
||||
result = []
|
||||
|
||||
fruit = fruit.lower() # 字母转小写
|
||||
fruit = fruit.lower() # 字母转小写
|
||||
flst = fruit.split() # 字符串转成list
|
||||
c = collections.Counter(flst)
|
||||
result = c.most_common()
|
||||
return result
|
||||
|
||||
|
||||
def youdao_link(s): # 有道链接
|
||||
link = 'http://youdao.com/w/eng/' + s + '/#keyfrom=dict2.index'# 网址
|
||||
def youdao_link(s): # 有道链接
|
||||
link = 'http://youdao.com/w/eng/' + s + '/#keyfrom=dict2.index' # 网址
|
||||
return link
|
||||
|
||||
|
||||
def file2str(fname):#文件转字符
|
||||
f = open(fname) #打开
|
||||
s = f.read() #读取
|
||||
f.close() #关闭
|
||||
def file2str(fname): # 文件转字符
|
||||
f = open(fname) # 打开
|
||||
s = f.read() # 读取
|
||||
f.close() # 关闭
|
||||
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 = '\_©~<=>+-/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
|
||||
def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
|
||||
special_characters = '\_©~<=>+-/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
|
||||
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(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
|
||||
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
|
||||
for i in range(n): # 只有单引号前后都有英文字符，才保留
|
||||
t = '' # 用来收集我需要保留的字符
|
||||
for i in range(n): # 只有单引号前后都有英文字符，才保留
|
||||
if s[i] == '\'':
|
||||
i_is_ok = i - 1 >= 0 and i + 1 < n
|
||||
if i_is_ok and s[i-1] in string.ascii_letters and s[i+1] in string.ascii_letters:
|
||||
if i_is_ok and s[i - 1] in string.ascii_letters and s[i + 1] in string.ascii_letters:
|
||||
t += s[i]
|
||||
else:
|
||||
t += s[i]
|
||||
|
|
@ -60,12 +62,12 @@ def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用
|
|||
return s
|
||||
|
||||
|
||||
def sort_in_descending_order(lst):# 单词按频率降序排列
|
||||
def sort_in_descending_order(lst): # 单词按频率降序排列
|
||||
lst2 = sorted(lst, reverse=True, key=lambda x: (x[1], x[0]))
|
||||
return lst2
|
||||
|
||||
|
||||
def sort_in_ascending_order(lst):# 单词按频率降序排列
|
||||
def sort_in_ascending_order(lst): # 单词按频率降序排列
|
||||
lst2 = sorted(lst, reverse=False, key=lambda x: (x[1], x[0]))
|
||||
return lst2
|
||||
|
||||
|
|
@ -85,39 +87,30 @@ def make_html_page(lst, fname):
|
|||
f.close()
|
||||
|
||||
|
||||
## main（程序入口）
|
||||
# main（程序入口）
|
||||
if __name__ == '__main__':
|
||||
num = len(sys.argv)
|
||||
|
||||
if num == 1: # 从键盘读入字符串
|
||||
if num == 1: # 从键盘读入字符串
|
||||
s = input()
|
||||
elif num == 2: # 从文件读入字符串
|
||||
elif num == 2: # 从文件读入字符串
|
||||
fname = sys.argv[1]
|
||||
s = file2str(fname)
|
||||
else:
|
||||
print('I can accept at most 2 arguments.')
|
||||
sys.exit()# 结束程序运行， 下面的代码不会被执行了。
|
||||
|
||||
s = remove_punctuation(s) # 这里是s是实参(argument)，里面有值
|
||||
sys.exit() # 结束程序运行， 下面的代码不会被执行了。
|
||||
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('%s\t%d\t%s' % (x[0], x[1], 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')
|
||||
|
||||
print('\nHistory:\n')
|
||||
if os.path.exists('frequency.p'):
|
||||
d = pickle_idea.load_record('frequency.p')
|
||||
else:
|
||||
d = {}
|
||||
|
||||
print(sort_in_descending_order(pickle_idea.dict2lst(d)))
|
||||
|
||||
# 合并频率
|
||||
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