Fix bug 533

app/Article.py

@@ -1,3 +1,5 @@
+import csv
+
 from WordFreq import WordFreq
 from app.UseSqlite import RecordQuery
 from wordfreqCMD import youdao_link, sort_in_descending_order
@@ -10,6 +12,7 @@ from flask import Flask, request, redirect, render_template, url_for, session, a
 from difficulty import get_difficulty_level_for_user, text_difficulty_level, user_difficulty_level
 from model.article import get_all_articles, get_article_by_id, get_number_of_articles
 import logging
+import re
 
 path_prefix = './'
 db_path_prefix = './db/'  # comment this line in deployment
@@ -23,6 +26,17 @@ def load_text_list_from_db(db_file):
     text_list = [row['text'] for row in result if 'text' in row]
     return text_list
 
+def load_word_list(csv_file):
+    with open(csv_file, 'r', encoding='utf-8') as f:
+        reader = csv.reader(f)
+        # 使用正则表达式匹配只包含字母的单词
+        return set(re.sub(r'\W+', '', word.strip().lower()) for row in reader for word in row[0].split(',') if word.strip())
+def calculate_coverage(text_list, word_set):
+    total_words = sum(len(article.split()) for article in text_list)
+    covered_words = sum(len(set(article.split()).intersection(word_set)) for article in text_list)
+    return (covered_words / total_words) * 10000 if total_words else 0
+
+
 def total_number_of_essays():
     return get_number_of_articles()
 

app/main.py

@@ -1,6 +1,5 @@
 #! /usr/bin/python3
 # -*- coding: utf-8 -*-
-import csv
 
 ###########################################################################
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
@@ -28,16 +27,6 @@ path_prefix = '/var/www/wordfreq/wordfreq/'
 path_prefix = './'  # comment this line in deployment
 
 
-def load_word_list(csv_file):
-    with open(csv_file, 'r', encoding='utf-8') as f:  # 添加encoding参数指定编码方式
-        reader = csv.reader(f)
-        return set(word.strip().lower() for row in reader for word in row[0].split(','))
-
-def calculate_coverage(text_list, word_set):
-    total_words = sum(len(article.split()) for article in text_list)
-    covered_words = sum(len(set(article.split()).intersection(word_set)) for article in text_list)
-    return (covered_words / total_words) * 10000 if total_words else 0
-
 def get_random_image(path):
     '''
     返回随机图
@@ -103,6 +92,7 @@ def mainpage():
     coverage_percentage = "{:.2f}".format(calculate_coverage(text_list, word_set))
 
 
+
     if request.method == 'POST':  # when we submit a form
         content = escape(request.form['content'])
         f = WordFreq(content)

app/model/article.py

@@ -1,4 +1,4 @@
-from model import *
+from app.model import *
 from datetime import datetime
 
 def add_article(content, source="manual_input", level="5", question="No question"):

app/model/user.py

@@ -1,4 +1,4 @@
-from model import *
+from app.model import *
 from Login import md5
 from pony import orm