refactor(code): 优化代码，提高可读性和效率

.gitignore

@@ -1,4 +1,4 @@
 log.txt
 /test
 /.venv
-*/__pycache__
+__pycache__

A 代码模式/10 一盘大棋/1 最基础的写法.py

@@ -7,7 +7,6 @@ with open(stopwordfilepath, encoding='utf-8') as f:
 for letter in 'abcdefghijklmnopqrstuvwxyz':
     stop_words.append(letter)
 
-
 # 读文件，逐行扫描文本，发现词，确定不是停用词，计数
 word_freqs = []
 for line in open(testfilepath, encoding='utf-8'):
@@ -46,7 +45,6 @@ for i in range(n):
         if word_freqs[j][1] < word_freqs[j + 1][1]:
             word_freqs[j], word_freqs[j + 1] = word_freqs[j + 1], word_freqs[j]
 
-
 # 打印频率最高的前10个词
 for tf in word_freqs[:10]:
     print(tf[0], '-', tf[1])

A 代码模式/10 一盘大棋/2 加入语言特性.py

@@ -23,7 +23,6 @@ with open(testfilepath,encoding = 'utf8') as f:
 # 打印前10个最常见的单词
 for word, freq in word_freqs.most_common(10):
     print(f"{word}-{freq}")
-
 '''
 相比 A01
 使用collections.Counter来计数单词频率，从而简化了代码并提高了效率。

A 代码模式/10 一盘大棋/3 Hacker.py

@@ -1,11 +1,13 @@
-import re, collections
+import re
+import collections
 from cppy.cp_util import stopwordfilepath, testfilepath
 
 stopwords = set(open(stopwordfilepath, encoding='utf8').read().split(','))
-words = re.findall('[a-z]{2,}', open( testfilepath,encoding = 'utf8').read().lower())
+words = re.findall('[a-z]{2,}',
+                   open(testfilepath, encoding='utf8').read().lower())
 counts = collections.Counter(w for w in words if w not in stopwords)
-for (w, c) in counts.most_common(10) :  print(w, '-', c)
-
+for (w, c) in counts.most_common(10):
+    print(w, '-', c)
 '''
 熟练的软件工程师，会如此简单完成任务
 后面的例子，我们必须变的啰嗦一些，不能用这种太 hacker 的写法

A 代码模式/cppy/cp_util.py

@@ -1,4 +1,3 @@
-
 import site
 import os, re, time
 import string, operator
@@ -28,48 +27,59 @@ def read_file(path_to_file):
         data = f.read()
     return data
 
+
 def re_split(data):
     pattern = re.compile('[\W_]+')
     data = pattern.sub(' ', data).lower()
     return data.split()
 
+
 def get_stopwords(path_to_file=stopwordfilepath):
     with open(path_to_file, encoding='utf-8') as f:
         data = f.read().split(',')
     data.extend(list(string.ascii_lowercase))
     return data
 
+
 def get_chunks(file_path=testfilepath, chunk_size=1000):
     # 读取文件内容，分割文件内容为多个块，每个块由一个进程处理
     # 可以根据实际情况调整块大小
     content = re_split(read_file(file_path))
-    chunks = [content[i:i + chunk_size] for i in range(0, len(content), chunk_size)]
+    chunks = [
+        content[i:i + chunk_size] for i in range(0, len(content), chunk_size)
+    ]
     return chunks
 
+
 def extract_file_words(path_to_file):
     word_list = re_split(read_file(path_to_file))
     stop_words = get_stopwords()
     return [w for w in word_list if (not w in stop_words) and len(w) >= 3]
 
+
 def extract_str_words(data_str):
     word_list = re_split(data_str)
     stop_words = get_stopwords()
     return [w for w in word_list if (not w in stop_words) and len(w) >= 3]
 
+
 def count_word(word, word_freqs, stopwords):
     if word not in stopwords:
         word_freqs[word] = word_freqs.get(word, 0) + 1
 
+
 def get_frequencies(word_list):
     word_freqs = {}
     for word in word_list:
         word_freqs[word] = word_freqs.get(word, 0) + 1
     return word_freqs
 
+
 def sort_dict(word_freq):
     return sorted(word_freq.items(), key=operator.itemgetter(1), reverse=True)
     # return sorted( word_freq, key=lambda x: x[1], reverse=True )
 
+
 def print_word_freqs(word_freqs, n=10):
     for (w, c) in word_freqs[:n]:
         print(w, '-', c)
@@ -79,7 +89,9 @@ def print_word_freqs( word_freqs, n = 10):
 #  通用工具
 ################################################################################
 
+
 def timing_decorator(func):
+
     def wrapper(*args, **kwargs):
         start_time = time.time()  # 记录开始时间
         result = func(*args, **kwargs)  # 调用原始函数
@@ -87,7 +99,9 @@ def timing_decorator(func):
         run_time = end_time - start_time  # 计算运行时间
         print(f"{func.__name__} 运行时间: {run_time*1000:.2f} 秒")
         return result
+
     return wrapper
 
+
 def test():
     print('cppy welcome')