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

@@ -7,10 +7,9 @@ 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' ):
+for line in open(testfilepath, encoding='utf-8'):
     start_char = None
     i = 0
     for c in line:
@@ -42,10 +41,9 @@ for line in open( testfilepath, encoding='utf-8' ):
 # 使用冒泡排序对词频进行排序
 n = len(word_freqs)
 for i in range(n):
-    for j in range(0, n-i-1):
+    for j in range(0, n - i - 1):
-        if word_freqs[j][1] < word_freqs[j+1][1]:
+        if word_freqs[j][1] < word_freqs[j + 1][1]:
-            word_freqs[j], word_freqs[j+1] = word_freqs[j+1], word_freqs[j]            
+            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]:

A 代码模式/10 一盘大棋/2 加入语言特性.py

@@ -1,4 +1,4 @@
-from cppy.cp_util import stopwordfilepath,testfilepath
+from cppy.cp_util import stopwordfilepath, testfilepath
 import string
 from collections import Counter
 
@@ -8,7 +8,7 @@ stop_words.update(list(string.ascii_lowercase))
 
 # 读取文件并计算单词频率
 word_freqs = Counter()
-with open(testfilepath,encoding = 'utf8') as f:
+with open(testfilepath, encoding='utf8') as f:
     for line_num, line in enumerate(f, 1):
         start_char = None
         for i, c in enumerate(line):
@@ -23,10 +23,9 @@ 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。
 使用enumerate来获取行号和行内容，使用set来存储停用词，都有助于提高代码的性能和可读性。
 使用most_common方法来获取最常见的单词，使输出更为简洁。
-'''
+'''

A 代码模式/10 一盘大棋/3 Hacker.py

@@ -1,12 +1,14 @@
-import re, collections
+import re
-from cppy.cp_util import stopwordfilepath,testfilepath
+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())
-counts = collections.Counter( w for w in words if w not in stopwords )
-for (w, c) in counts.most_common(10) :  print(w, '-', c)
 
+stopwords = set(open(stopwordfilepath, encoding='utf8').read().split(','))
+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)
 '''
 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

@@ -1,7 +1,6 @@
-
 import site
-import os,re,time
+import os, re, time
-import string,operator
+import string, operator
 
 ################################################################################
 #  变量
@@ -10,76 +9,89 @@ testfilename = 'test.txt'
 testfilename = 'pride-and-prejudice.txt'
 testfilename = 'Prey.txt'
 
-db_filename = "tf.db"  
+db_filename = "tf.db"
 
 site_packages = site.getsitepackages()
 for package in site_packages:
-    if 'package' in  package:
+    if 'package' in package:
         basePath = package
-stopwordfilepath = os.path.join(basePath, 'cppy','data','stop_words.txt')
+stopwordfilepath = os.path.join(basePath, 'cppy', 'data', 'stop_words.txt')
-testfilepath = os.path.join(basePath, 'cppy','data',testfilename )
+testfilepath = os.path.join(basePath, 'cppy', 'data', testfilename)
 
 
 ################################################################################
 #  项目函数
 ################################################################################
-def read_file(path_to_file):    
+def read_file(path_to_file):
-    with open(path_to_file,encoding='utf-8') as f:
+    with open(path_to_file, encoding='utf-8') as f:
         data = f.read()
     return data
 
-def re_split( 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:
+def get_stopwords(path_to_file=stopwordfilepath):
-        data = f.read().split(',')        
+    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):
+
+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))         
+    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) )
+    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 ]
+    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 )
+    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 ]
+    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 = {}  
+def get_frequencies(word_list):
-    for word in word_list:  
+    word_freqs = {}
-        word_freqs[word] = word_freqs.get(word, 0) + 1    
+    for word in word_list:
+        word_freqs[word] = word_freqs.get(word, 0) + 1
     return word_freqs
 
-def sort_dict (word_freq):
+
+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 ]:
+def print_word_freqs(word_freqs, n=10):
-        print( w, '-', c )
+    for (w, c) in word_freqs[:n]:
+        print(w, '-', c)
 
 
 ################################################################################
 #  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' )
+def test():
+    print('cppy welcome')