EnglishPal/app/Article.py

112 lines
3.4 KiB
Python
Raw Permalink Normal View History

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)
2022-01-27 17:01:03 +08:00
user_level = user_difficulty_level(d_user, d3) # more consideration as user's behaviour is dynamic. Time factor should be considered.
random.shuffle(result) # shuffle list
d = random.choice(result)
text_level = text_difficulty_level(d['text'], d3)
if articleID == None:
for reading in result:
text_level = text_difficulty_level(reading['text'], d3)
factor = random.gauss(0.8,
0.1) # a number drawn from Gaussian distribution with a mean of 0.8 and a stand deviation of 1
if within_range(text_level, user_level, (8.0 - user_level) * factor):
d = reading
break
article_date = d['date']
article_title = get_article_title(d['text'])
article_body = get_article_body(d['text'])
question_part = get_question_part(d['question'])
answer_part = get_answer_part(d['question'])
return user_level,text_level,article_date,article_title,article_body,question_part,answer_part
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 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/
return result