From 52d8c12e45a725adc50975b30111d32707d71920 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E4=BD=99=E5=BF=86=E5=BC=80?= <余忆开@2291723778@qq.com>
Date: Mon, 3 Jun 2024 11:32:49 +0800
Subject: [PATCH] Fix bug 533

---
 app/Article.py                  | 20 +++++++++++++-------
 app/WordFreq.py                 |  2 +-
 app/difficulty.py               |  2 +-
 app/main.py                     |  1 +
 app/test/test_bug533_Yuyikai.py | 26 ++++++++++----------------
 app/wordfreqCMD.py              |  2 +-
 6 files changed, 27 insertions(+), 26 deletions(-)

diff --git a/app/Article.py b/app/Article.py
index 216c413..58335ec 100644
--- a/app/Article.py
+++ b/app/Article.py
@@ -1,16 +1,16 @@
 import csv
 
-from WordFreq import WordFreq
+from app.WordFreq import WordFreq
 from app.UseSqlite import RecordQuery
-from wordfreqCMD import youdao_link, sort_in_descending_order
-import pickle_idea, pickle_idea2
+from app.wordfreqCMD import youdao_link, sort_in_descending_order
+from app 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_for_user, text_difficulty_level, user_difficulty_level
-from model.article import get_all_articles, get_article_by_id, get_number_of_articles
+from app.difficulty import get_difficulty_level_for_user, text_difficulty_level, user_difficulty_level
+from app.model.article import get_all_articles, get_article_by_id, get_number_of_articles
 import logging
 import re
 
@@ -29,8 +29,14 @@ def load_text_list_from_db(db_file):
 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())
+        word_set = set()
+        for row in reader:
+            for word in row[0].split(','):
+                clean_word = re.sub(r'\W+', '', word.strip().lower())
+                if clean_word:
+                    word_set.add(clean_word)
+        return word_set
+
 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)
diff --git a/app/WordFreq.py b/app/WordFreq.py
index 3620a41..90a462e 100644
--- a/app/WordFreq.py
+++ b/app/WordFreq.py
@@ -3,7 +3,7 @@
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
 
-from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
+from app.wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
 import string
 
 class WordFreq:
diff --git a/app/difficulty.py b/app/difficulty.py
index 1bd8d68..12db1c5 100644
--- a/app/difficulty.py
+++ b/app/difficulty.py
@@ -7,7 +7,7 @@
 
 import pickle
 import math
-from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
+from app.wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
 import snowballstemmer
 
 
diff --git a/app/main.py b/app/main.py
index ff65b62..8af545f 100644
--- a/app/main.py
+++ b/app/main.py
@@ -9,6 +9,7 @@ from flask import escape
 from Login import *
 from Article import *
 import Yaml
+from app import pickle_idea
 from app.wordfreqCMD import sort_in_descending_order
 from user_service import userService
 from account_service import accountService
diff --git a/app/test/test_bug533_Yuyikai.py b/app/test/test_bug533_Yuyikai.py
index 2ba4d5c..afde736 100644
--- a/app/test/test_bug533_Yuyikai.py
+++ b/app/test/test_bug533_Yuyikai.py
@@ -1,23 +1,17 @@
-
-from app.Article import load_text_list_from_db
-from app.main import load_word_list, calculate_coverage
+from app.Article import load_text_list_from_db, load_word_list, calculate_coverage
 
 
 def test_coverage_percentage():
     try:
-        db_file = "db\wordfreqapp.db"
-        csv_file = "db\The_Oxford.csv"
-        text_list = load_text_list_from_db(db_file)
-        word_set = load_word_list(csv_file)
-        coverage_percentage = "{:.2f}".format(calculate_coverage(text_list, word_set))
-        print("coverage_percentage:", coverage_percentage);
+        text_list = load_text_list_from_db("db\wordfreqapp.db")
+        word_set = load_word_list("db\The_Oxford.csv")
+        coverage_percentage = calculate_coverage(text_list, word_set)
+
+        assert 0 <= coverage_percentage <= 100, "Coverage percentage is not within the range [0, 100]"
+
+        print("coverage_percentage:", coverage_percentage)
     except Exception as e:
         print(e)
 
-if __name__ == '__main__':
-    test_coverage_percentage();
-
-
-
-
-
+if __name__ == "__main__":
+    test_coverage_percentage()
\ No newline at end of file
diff --git a/app/wordfreqCMD.py b/app/wordfreqCMD.py
index dcee74e..8ec00ec 100644
--- a/app/wordfreqCMD.py
+++ b/app/wordfreqCMD.py
@@ -7,7 +7,7 @@ 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 pickle_idea
+from app import pickle_idea
 
 def freq(fruit):
     '''