178 lines
6.5 KiB
Python
178 lines
6.5 KiB
Python
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
|
||
from difficulty import get_difficulty_level, text_difficulty_level, user_difficulty_level
|
||
|
||
|
||
path_prefix = '/var/www/wordfreq/wordfreq/'
|
||
path_prefix = './' # comment this line in deployment
|
||
|
||
|
||
def total_number_of_essays():
|
||
rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
|
||
rq.instructions("SELECT * FROM article")
|
||
rq.do()
|
||
result = rq.get_results()
|
||
return len(result)
|
||
|
||
|
||
def get_article_title(s):
|
||
return s.split('\n')[0]
|
||
|
||
|
||
def get_article_body(s):
|
||
lst = s.split('\n')
|
||
lst.pop(0) # remove the first line
|
||
return '\n'.join(lst)
|
||
|
||
|
||
def get_today_article(user_word_list, articleID):
|
||
rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
|
||
if articleID == None:
|
||
rq.instructions("SELECT * FROM article")
|
||
else:
|
||
rq.instructions('SELECT * FROM article WHERE article_id=%d' % (articleID))
|
||
rq.do()
|
||
result = rq.get_results()
|
||
random.shuffle(result)
|
||
|
||
# Choose article according to reader's level
|
||
d1 = load_freq_history(path_prefix + 'static/frequency/frequency.p')
|
||
d2 = load_freq_history(path_prefix + 'static/words_and_tests.p')
|
||
d3 = get_difficulty_level(d1, d2)
|
||
|
||
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.
|
||
random.shuffle(result) # shuffle list
|
||
d = random.choice(result)
|
||
text_level = text_difficulty_level(d['text'], d3)
|
||
if articleID == None:
|
||
# print('result = ', len(result), sep=' ')
|
||
p = False
|
||
for reading in result:
|
||
text_level = text_difficulty_level(reading['text'], d3)
|
||
factor = random.gauss(0.8, 0.1) # a number drawn from Gaussian distribution with a mean of 0.8 and a stand deviation of 1
|
||
if within_range(text_level, user_level, (8.0 - user_level) * factor):
|
||
list = session.get('articleIdList')
|
||
if list == None:
|
||
d = reading
|
||
list = [reading['article_id']]
|
||
session['articleIdList'] = list
|
||
p = True
|
||
break
|
||
|
||
exist = False
|
||
for i in list:
|
||
if reading['article_id'] == i:
|
||
exist = True
|
||
break
|
||
if exist == False:
|
||
d = reading
|
||
list.append(reading['article_id'])
|
||
session['articleIdList']=list
|
||
p = True
|
||
break
|
||
if p == False:
|
||
session['articleIdList'] = None
|
||
p = True
|
||
while p:
|
||
for reading in result:
|
||
text_level = text_difficulty_level(reading['text'], d3)
|
||
factor = random.gauss(0.8, 0.1) # a number drawn from Gaussian distribution with a mean of 0.8 and a stand deviation of 1
|
||
if within_range(text_level, user_level, (8.0 - user_level) * factor):
|
||
if reading['article_id'] != session['prearticleID']:
|
||
d = reading
|
||
p = False
|
||
'''
|
||
测试代码：
|
||
print(session['articleIdList'])
|
||
print(session['prearticleID'], d['article_id'], sep=' ')
|
||
|
||
问题描述：选择下一篇文章时，由于没有考虑选择文章时会重复选择当前文章，可能会导致重复进入某一篇文章
|
||
解决方法：选择下一篇文章时，将选择的文章ID和当前文章ID比较，若重复则换一个
|
||
进一步优化：
|
||
问题描述：利用上述方法可以满足不重复进入某一篇文章，但是可能两篇文章会反复出现
|
||
解决方法：记录一个队列，用来保存出现过的文章ID
|
||
选择文章时，若文章Id出现在队列中，则放弃；
|
||
若都出现过，则清空队列，随机选择一个不与当前文章重复的文章
|
||
'''
|
||
|
||
s = '<div class="alert alert-success" role="alert">According to your word list, your level is <span class="badge bg-success">%4.2f</span> and we have chosen an article with a difficulty level of <span class="badge bg-success">%4.2f</span> for you.</div>' % (
|
||
user_level, text_level)
|
||
s += '<p class="text-muted">Article added on: %s</p>' % (d['date'])
|
||
s += '<div class="p-3 mb-2 bg-light text-dark">'
|
||
article_title = get_article_title(d['text'])
|
||
article_body = get_article_body(d['text'])
|
||
s += '<p class="display-3">%s</p>' % (article_title)
|
||
s += '<p class="lead"><font id="article" size=2>%s</font></p>' % (article_body)
|
||
s += '<p><small class="text-muted">%s</small></p>' % (d['source'])
|
||
s += '<p><b>%s</b></p>' % (get_question_part(d['question']))
|
||
s = s.replace('\n', '<br/>')
|
||
s += '%s' % (get_answer_part(d['question']))
|
||
s += '</div>'
|
||
session['articleID'] = d['article_id']
|
||
return s
|
||
|
||
|
||
def load_freq_history(path):
|
||
d = {}
|
||
if os.path.exists(path):
|
||
d = pickle_idea.load_record(path)
|
||
return d
|
||
|
||
|
||
def within_range(x, y, r):
|
||
return x > y and abs(x - y) <= r
|
||
|
||
|
||
def get_question_part(s):
|
||
s = s.strip()
|
||
result = []
|
||
flag = 0
|
||
for line in s.split('\n'):
|
||
line = line.strip()
|
||
if line == 'QUESTION':
|
||
result.append(line)
|
||
flag = 1
|
||
elif line == 'ANSWER':
|
||
flag = 0
|
||
elif flag == 1:
|
||
result.append(line)
|
||
return '\n'.join(result)
|
||
|
||
|
||
def get_answer_part(s):
|
||
s = s.strip()
|
||
result = []
|
||
flag = 0
|
||
for line in s.split('\n'):
|
||
line = line.strip()
|
||
if line == 'ANSWER':
|
||
flag = 1
|
||
elif flag == 1:
|
||
result.append(line)
|
||
# https://css-tricks.com/snippets/javascript/showhide-element/
|
||
js = '''
|
||
<script type="text/javascript">
|
||
|
||
function toggle_visibility(id) {
|
||
var e = document.getElementById(id);
|
||
if(e.style.display == 'block')
|
||
e.style.display = 'none';
|
||
else
|
||
e.style.display = 'block';
|
||
}
|
||
</script>
|
||
'''
|
||
html_code = js
|
||
html_code += '\n'
|
||
html_code += '<button onclick="toggle_visibility(\'answer\');">ANSWER</button>\n'
|
||
html_code += '<div id="answer" style="display:none;">%s</div>\n' % ('\n'.join(result))
|
||
return html_code |