修 12

15 工程化/类属性 .py

@@ -0,0 +1,36 @@
+from cppy.cp_util import *
+from dataclasses import dataclass
+from collections import Counter
+import re
+
+@dataclass
+class WordFrequency:
+    text: str
+    stop_words: set = None
+
+    def __post_init__(self):
+        # 如果未提供停用词表
+        if self.stop_words is None:
+            self.stop_words = get_stopwords()
+
+    def tokenize(self):
+        # 分词并去除停用词
+        words = re.findall(r'\b\w+\b', self.text.lower())
+        filtered_words = [word for word in words if word not in self.stop_words and len(word)>2]
+        return filtered_words
+    
+    def get_top_n(self, n=10):
+        # 计算词频
+        word_freqs = Counter(self.tokenize())
+        return word_freqs.most_common(n)
+
+
+# 使用示例
+if __name__ == '__main__':
+    # 创建WordFrequency实例
+    text = read_file()    
+    word_freq = WordFrequency( text )
+
+    # 获取并打印词频
+    top_words = word_freq.get_top_n()
+    print_word_freqs(top_words) 

16 其它/对象设计模式/享元.py

@@ -19,9 +19,9 @@ class WordFrequencyControllerFactory():
     def get_WordFrequencyController(self, number,testfilepath):
         if number not in self.types:
             self.types[number] = WordFrequencyController(number,testfilepath) # 创建新的对象
-            print('new obj',number,'*'*30)                        
+            print('new obj: ','*'*30,number)                        
         else:
-            print('ref obj','*'*30)
+            print('ref obj: ','*'*30,number)
         return self.types[number] # 重复使用已存在的对象
 
 
@@ -29,5 +29,6 @@ if __name__ == "__main__":
     factory = WordFrequencyControllerFactory()
     for number in [ 1,3,5,3,5,7 ]:
         WordFrequency = factory.get_WordFrequencyController(number,testfilepath)
+        # print(flush=True)
         WordFrequency.print_word_freqs()
     

16 其它/对象设计模式/观察者.py

@@ -16,8 +16,6 @@ class WordFrequencyObserver(Observer):
     def update(self, word):  
         self.word_count[word] += 1  
 
-    def get_top_n(self,n):  
-        return self.word_count.most_common(n)  
   
 # 定义主题类  
 class WordSubject:  
@@ -48,7 +46,7 @@ def main(testfilepath, top_n = 10 ):
             subject.notify(word)  # 触发
   
     # 打印最高的N个词频  
-    top_words = observer.get_top_n(top_n)  
+    top_words = observer.word_count.most_common(top_n) 
     print_word_freqs(top_words)