请老师查阅我们组更新的vocabulary.py

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(2).py

@@ -0,0 +1,117 @@
+import pickle
+import string
+import os
+
+
+def read_pickle(file_name):
+    """Read data from a pickle file if it exists."""
+    if not os.path.isfile(file_name):
+        print(f"File {file_name} does not exist.")
+        return {}
+    with open(file_name, 'rb') as f:
+        return pickle.load(f)
+
+
+class VocabularyLevelEstimator:
+    # Load the word database for testing
+    _word_db = read_pickle('words_and_tests.p')
+
+    def evaluate_word_difficulty(self, word):
+        """Evaluate the difficulty level of a word."""
+        # Handle empty strings, punctuation only, or purely numeric strings.
+        if not word or all(ch in string.punctuation for ch in word) or word.isdigit():
+            return 0
+        return 5 if word in self._word_db else 0
+
+    @property
+    def difficulty_level(self):
+        return self.calculate_longest_words_level()
+
+
+class UserVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, vocab_dict):
+        self.vocab_dict = vocab_dict
+        # Use the last three words from the vocabulary dictionary.
+        self.recent_words = list(vocab_dict.keys())[-3:]
+
+    @property
+    def level(self):
+        """Calculate the user's vocabulary level considering word validity."""
+        valid_words = [word for word in self.recent_words if self.evaluate_word_difficulty(word) > 0]
+        valid_count = len(valid_words)
+
+        if valid_count == 0:
+            return 0
+
+        # Score for a single valid word
+        if valid_count == 1:
+            return self.score_single_word(valid_words[0])
+
+        # Logic for scoring multiple valid words
+        return self.score_multiple_words(valid_words)
+
+    def score_single_word(self, word):
+        """Evaluate the score of a single word."""
+        length = len(word)
+        if length < 7:
+            return 2
+        elif 7 <= length < 8:
+            return 5
+        return 6
+
+    def score_multiple_words(self, valid_words):
+        """Calculate the score for multiple valid words."""
+        total_score = 0
+        for word in valid_words:
+            length = len(word)
+            if length < 5:
+                total_score += 1
+            elif 5 <= length < 8:
+                total_score += 3
+            else:
+                total_score += 5
+
+        average_score = total_score / len(valid_words)
+        return min(int(average_score * 1.6), 8)
+
+
+class ArticleVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, article_text):
+        self.article_text = article_text
+        # Extract valid words and strip punctuation.
+        self.words = [
+            word.strip(string.punctuation)
+            for word in article_text.lower().split()
+            if word.strip(string.punctuation)
+        ]
+
+    @property
+    def level(self):
+        """Evaluate the article difficulty based on the longest ten valid words."""
+        valid_words = [word for word in self.words if self.evaluate_word_difficulty(word) > 0]
+        longest_words = sorted(valid_words, key=len, reverse=True)[:10]
+        if not longest_words:
+            return 0
+
+        difficulty_ratings = []
+        for word in longest_words:
+            length = len(word)
+            if length < 5:
+                difficulty_ratings.append(0.1)
+            elif 5 <= length < 8:
+                difficulty_ratings.append(0.2)
+            elif 8 <= length < 11:
+                difficulty_ratings.append(0.3)
+            else:
+                difficulty_ratings.append(0.5)
+
+        return sum(difficulty_ratings) + 2
+
+
+if __name__ == '__main__':
+    vocab_dict = read_pickle('frequency_mrlan85.pickle')
+    print(vocab_dict)
+    user = UserVocabularyLevel(vocab_dict)
+    print(user.level)
+    article = ArticleVocabularyLevel('This is an interesting article.')
+    print(article.level)