请老师看我们的vocabulary.py文件

README.md

@@ -18,7 +18,7 @@ picked from articles selected for him to read according his vocabulary level.  E
 
 `python3 main.py`
 
-Make sure you have put the SQLite database file in the path `app/db` (see below).
+Make sure you have put the SQLite database file in the path `app/static` (see below).
 
 
 ## Run it as a Docker container
@@ -214,5 +214,5 @@ Bug report: http://118.25.96.118/bugzilla/show_bug.cgi?id=215
 Bug report: http://118.25.96.118/bugzilla/show_bug.cgi?id=489
 
 
-*Last modified on 2026-03-12*
+*Last modified on 2023-01-30*
 

app/Article.py

@@ -106,7 +106,7 @@ def get_today_article(user_word_list, visited_articles):
         text_level = text_difficulty_level(d['text'], d3)
         result_of_generate_article = "found"
 
-    today_article = {}
+    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)

app/main.py

@@ -144,8 +144,8 @@ if __name__ == '__main__':
     运行程序
     '''
     # app.secret_key = os.urandom(16)
-    app.run(debug=True, port=5000)
+    # app.run(debug=False, port='6000')
-    # app.run(debug=True)
+    app.run(debug=True)
     # app.run(debug=True, port='6000')
     # app.run(host='0.0.0.0', debug=True, port='6000')
     # print(mod5('123'))

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，Oxford 5000 单词占比 <span class="badge bg-success"> {{ (ratio * 100) | int }}%  </span> </div>
+        <div class="alert alert-success" role="alert">共有文章 <span class="badge bg-success"> {{ number_of_essays }} </span> 篇，覆盖 <span class="badge bg-success"> {{ (ratio * 100) | int }}%  </span> 的 Oxford5000 单词</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

@@ -87,7 +87,7 @@
 
     <div id="text-content">
         <div id="found">
-          <div class="alert alert-success" role="alert">According to your word list, your level is <span 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. <span class="text-decoration-underline" id="ratio">{{ (today_article["ratio"] * 100) | int }}%</span> of the words in this article are in Oxford Word 5000.</div>
+          <div class="alert alert-success" role="alert">According to your word list, your level is <span 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. 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/>
 
 	    <button onclick="saveArticle()" >标记文章</button>

app/vocabulary.py

@@ -0,0 +1,91 @@
+'''
+   Estimate a user's vocabulary level given his vocabulary data
+   Estimate an English article's difficulty level given its content
+   Preliminary design
+
+   Hui, 2024-09-23
+   Last upated: 2024-09-25, 2024-09-30
+'''
+
+import pickle
+
+import nltk
+
+DIFFICULTY_MAPPING = {
+    'BBC': 2,       # 基础词汇
+    'CET4': 3,      # 四级（大学英语）
+    'CET6': 4,      # 六级
+    'GRADUATE': 5,  # 考研词汇
+    'IELTS': 6,     # 雅思
+    'OXFORD3000': 4, # 牛津3000核心词
+    'OXFORD5000': 7 # 牛津5000词
+}
+
+
+def load_record(pickle_fname):
+    with open(pickle_fname, 'rb') as f:
+        d = pickle.load(f)
+    return d
+
+
+class VocabularyLevelEstimator:
+    _test = load_record('words_and_tests.p') # map a word to the sources where it appears
+
+    @property
+    def level(self):
+        if not self.word_lst:  # 检查是否有有效词汇
+            return 0.0  # 或根据需求返回默认值
+        total = 0.0
+        valid_words = 0
+        for word in self.word_lst:
+            if word in self._test:
+                sources = self._test[word]
+                total += max(DIFFICULTY_MAPPING.get(src, 0) for src in sources)
+                valid_words += 1
+        return total / valid_words if valid_words > 0 else 0.0
+
+
+class UserVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, d, recent_n=3):
+        self.d = d
+        self.recent_n = recent_n
+        # 按时间戳降序排序，取前recent_n个单词
+        sorted_words = sorted(d.keys(), key=lambda word: d[word][-1], reverse=True)
+        self.word_lst = sorted_words[:recent_n]
+
+
+class ArticleVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, content):
+        self.content = content
+        # 预处理：分词、小写、去标点、去停用词
+        import re
+        from nltk.corpus import stopwords
+        nltk.download('stopwords')
+        stop_words = set(stopwords.words('english'))
+        words = re.findall(r'\b\w+\b', content.lower())
+        self.word_lst = [word for word in words if word not in stop_words]
+        # 按难度分筛选前10个最难的单词
+        self.word_lst = sorted(
+            self.word_lst,
+            key=lambda w: self._get_difficulty(w),
+            reverse=True
+        )[:10]
+
+    def _get_difficulty(self, word):
+        if word in self._test:
+            return max(DIFFICULTY_MAPPING.get(src, 0) for src in self._test[word])
+        return 0
+
+
+if __name__ == '__main__':
+    d = load_record('frequency_mrlan85.pickle')
+    print(d)
+    print("======================================================")
+    user = UserVocabularyLevel(d)
+    print(user.level) # level is a property
+    print("======================================================")
+    article = ArticleVocabularyLevel('This is an interesting article')
+    print(article.level)
+
+
+