移除代码中特殊字符

替换工程文件中特殊字符，比如某类注释或者空行的空格，用脚本就比较方便了。

例如写一个config.ini的配置文件：

[dir]
dir1 = D:/test1
dir2 = D:/test2

然后就是用configparser库去读取配置文件，re正则表达式库去匹配对应的字符串，代码如下：

import sys
import os
import re
import configparser
import commonFunc

def lineRelace(content, path):
    curPos = 0
    ret = False
    inComment = False
    
    while True:
        match = re.search(r'\s*/\* remove comment*?\*/[ \t]*', content[curPos:], re.S)
        if match is None:
            break
            
        express = match.group()
        
        content = content[:curPos + match.start()] + content[curPos + match.end():]

        curPos += match.end()

        print('%s: %d %s'%(path, content[:curPos].count('\n') + 1, express))
        ret = True  

    return content

def find_and_replace_check(filePath, encoding):

    if re.search(r'fdd', filePath):
        return
        
    with open(filePath, 'r', newline='', errors='ignore', encoding = encoding) as file:
        content = file.read()
        fileContent = lineRelace(content, filePath)
    
    with open(filePath, "w", newline='', errors='ignore', encoding=encoding) as replaceFile:
        replaceFile.write(fileContent)

    
def doSomeProc(path):
    if not os.path.exists(path):
        print('please input right path(%s)'%(path))
        return 1

    fileQueue = commonFunc.get_file_queue(path)
    
    for filePath in fileQueue:
        encoding = commonFunc.get_file_encoding(filePath)
        find_and_replace_check(filePath, encoding)
    return

def main():    
    items = commonFunc.read_cfg_dir('config-items.ini')

    for item in items:
        dir_path = item[1]
        print("dir_path:%s" % dir_path)
        doSomeProc(dir_path)

if __name__ == "__main__":
    main()
    input('\n\nplease press Enter key to exit!')

---------------
import configparser
import os

SUBFIX = ['.c', '.cpp', '.h', '.inc']

# 说明：UTF兼容ISO8859-1和ASCII，GB18030兼容GBK，GBK兼容GB2312，GB2312兼容ASCII
CODES = ['UTF-8','GB18030']
UTF_8_BOM = b'\xef\xbb\xbf'

def get_file_queue(path):
    fileQueue = []
    
    if os.path.isfile(path):
        fileQueue.append(path)
    else:
        SearchDir(path, fileQueue)
        
    return fileQueue

def SearchDir(dir, fileQueue):
    for f in os.listdir(dir):
        path = os.path.join(dir, f)
        if os.path.isfile(path):
            tmp = os.path.splitext(f)
            if tmp[-1] in SUBFIX:
                fileQueue.append(path)
        elif os.path.isdir(path):
            SearchDir(path, fileQueue)
    return

def get_file_encoding(file_path):
    with open(file_path, 'rb') as f:
        return string_encoding(f.read())
    
def string_encoding(b):
    for code in CODES:
        try:
            b.decode(encoding=code)
            if 'UTF-8' == code and b.startswith(UTF_8_BOM):
                return 'UTF-8-SIG'
            return code
        except Exception:
            continue
    return 'gbk'
    
def read_cfg_dir(fileName):
    cf = configparser.ConfigParser()

    cf.read(fileName)
    items = cf.items("cfg")
    
    return items

def read_cfg_file(fileName):
    cf = configparser.ConfigParser()

    cf.read(fileName)
    url_path = cf.get("cfg", "dir")
    print(url_path)
    
    return url_path