Fix Bug533

app/Article.py

@@ -9,10 +9,32 @@ 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
+oxford_words_path='./db/oxford_words.txt'
 
+def count_oxford_words(text, oxford_words):
+    words = re.findall(r'\b\w+\b', text.lower())
+    total_words = len(words)
+    oxford_word_count = sum(1 for word in words if word in oxford_words)
+    return oxford_word_count, total_words
+
+def calculate_ratio(oxford_word_count, total_words):
+    if total_words == 0:
+        return 0
+    return oxford_word_count / total_words
+
+def load_oxford_words(file_path):
+    oxford_words = {}
+    with open(file_path, 'r', encoding='utf-8') as file:
+        for line in file:
+            parts = line.strip().split()
+            word = parts[0]
+            pos = parts[1]
+            level = parts[2]
+            oxford_words[word] = {'pos': pos, 'level': level}
+    return oxford_words
 
 def total_number_of_essays():
     return get_number_of_articles()
@@ -86,6 +108,9 @@ def get_today_article(user_word_list, visited_articles):
 
     today_article = None
     if d:
+        oxford_words = load_oxford_words(oxford_words_path)
+        oxford_word_count, total_words = count_oxford_words(d['text'],oxford_words)
+        ratio = calculate_ratio(oxford_word_count,total_words)
         today_article = {
             "user_level": '%4.1f' % user_level,
             "text_level": '%4.1f' % text_level,
@@ -94,7 +119,8 @@ def get_today_article(user_word_list, visited_articles):
             "article_body": get_article_body(d['text']),
             "source": d["source"],
             "question": get_question_part(d['question']),
-            "answer": get_answer_part(d['question'])
+            "answer": get_answer_part(d['question']),
+            "ratio" : ratio
         }
 
     return visited_articles, today_article, result_of_generate_article

app/main.py

@@ -79,6 +79,19 @@ def mainpage():
     根据GET或POST方法来返回不同的主界面
     :return: 主界面
     '''
+
+    article_text = get_all_articles()
+    texts = [item['text'] for item in article_text]
+    oxford_words = load_oxford_words(oxford_words_path)  
+
+    # 提取所有单词
+    all_words = []
+    for text in texts:
+        words = re.findall(r'\b\w+\b', text.lower())
+        all_words.extend(words)
+    oxford_word_count = sum(1 for word in all_words if word in oxford_words)
+    ratio = calculate_ratio(oxford_word_count, len(all_words))
+
     if request.method == 'POST':  # when we submit a form
         content = escape(request.form['content'])
         f = WordFreq(content)
@@ -102,7 +115,8 @@ def mainpage():
                                d_len=d_len,
                                lst=lst,
                                yml=Yaml.yml,
-                               number_of_essays=number_of_essays)
+                               number_of_essays=number_of_essays,
+                               ratio = ratio)
 
 
 if __name__ == '__main__':

app/templates/mainpage_get.html

@@ -31,7 +31,7 @@
             <p><a href="/login">登录</a>  <a href="/signup">注册</a> <a href="/static/usr/instructions.html">使用说明</a></p >
             <p><b> {{ random_ads }}。 <a href="/signup">试试</a>吧！</b></p>
         {% endif %}
-        <div class="alert alert-success" role="alert">共有文章 <span class="badge bg-success"> {{ number_of_essays }} </span> 篇</div>
+        <div class="alert alert-success" role="alert">共有文章 <span class="badge bg-success"> {{ number_of_essays }} </span> 篇 &nbsp;&nbsp;&nbsp;&nbsp;其中Oxford单词覆盖率为: <span class="badge bg-success"> {{ (ratio * 100) | int }}%  </span></div>
         <p>粘贴1篇文章 (English only)</p>
         <form method="post" action="/">
             <textarea name="content" id="article" rows="10" cols="120"></textarea><br/>

app/templates/userpage_get.html

@@ -96,7 +96,7 @@
                     class="text-decoration-underline" id="user_level">{{ today_article["user_level"] }}</span> and we
                 have chosen an article with a difficulty level of <span class="text-decoration-underline"
                                                                         id="text_level">{{ today_article["text_level"] }}</span>
-                for you.
+                for you.The Oxford word coverage is <span class="text-decoration-underline" id="ratio">{{ (today_article["ratio"] * 100) | int }}%</span>
             </div>
             <p class="text-muted" id="date">Article added on: {{ today_article["date"] }}</p><br/>
             <div class="p-3 mb-2 bg-light text-dark" style="margin: 0 0.5%;"><br/>
@@ -286,6 +286,7 @@
         $('#source').html(today_article['source']);
         $('#question').html(today_article["question"]);
         $('#answer').html(today_article["answer"]);
+        $('#ratio').html(Math.round(today_article["ratio"] * 100) + '%');
         document.querySelector('#text_level').classList.add('mark'); // highlight text difficult level for 2 seconds
         setTimeout(() => {
             document.querySelector('#text_level').classList.remove('mark');