[TOC]

参考

1. Python实现递归遍历文件夹并删除文件
2. Python实现递归遍历文件夹并删除文件 别人博客
3. GBK编码的java文件批量转换为utf-8

Eclipse workspace 工程java文件编码问题

解决问题：eclipse workspaces中的项目有的是GBK编码，如果导入到workspaces的默认编码为utf-8编码的话中文会出现乱码。
下面python3的方式递归变量当前目录以及子目录，把目录中的*.java文件由gbk转换为utf-8，注意只能用一次，一次之后当前目录以及子目录下的文件编码均会由gbk转为utf-8。

import codecs
def ReadFile(filePath,encoding="gbk"):
    with codecs.open(filePath,"r",encoding) as f:
        return f.read()
 
def WriteFile(filePath,u,encoding="utf-8"):
    with codecs.open(filePath,"w",encoding) as f:
        f.write(u)
 
def UTF8_2_GBK(src,dst):
    content = ReadFile(src,encoding="gbk")
    WriteFile(dst,content,encoding="utf-8")

import os
import os.path
# 递归遍历rootdir目录，把目录中的*.java编码由gbk转换为utf-8
def ReadDirectoryFile(rootdir):
    for parent,dirnames,filenames in os.walk(rootdir):
            #case 1:
            for dirname in dirnames:
                    print("parent folder is:" + parent)
                    print("dirname is:" + dirname)
            #case 2
            for filename in filenames:    
                    print("parent folder is:" + parent)
                    print("filename with full path:"+ os.path.join(parent,filename))
                    if filename.endswith(".java"):
                            UTF8_2_GBK(os.path.join(parent,filename),os.path.join(parent,filename))
                            print("Java文件")
if __name__=="__main__":
    ReadDirectoryFile(".")

eclipse 工程jsp文件编码以及头

<%@page contentType="text/html;charset=gbk"%>批量转换为<%@page contentType="text/html;charset=UTF-8"%>
大部分和上面编码类似，只是多了一个字符串的替换，重写了ReadFile方法，按行读取，然后替换字符"charset=gbk"-->"charset=UTF-8"

import codecs
def ReadFile(filePath,encoding="gbk"):
    try:
        strfile=""
        f = codecs.open(filePath,"r",encoding)
        line = f.readline()
        while(line):
            line=line.replace("charset=gbk","charset=UTF-8")#
            line=line.replace("charset=GBK","charset=UTF-8")#
            line=line.replace("charset=gb2312","charset=UTF-8")#
            strfile+=line
            line=f.readline()
        f.close()
        return strfile
    except Exception:
        return None
    

def WriteFile(filePath,u,encoding="utf-8"):
    with codecs.open(filePath,"w",encoding) as f:
        f.write(u)

def UTF8_2_GBK(src,dst):
    content = ReadFile(src,encoding="gbk")
    #print(content)
    WriteFile(dst,content,encoding="utf-8")

import os
import os.path
# 递归遍历rootdir目录，把目录中的*.java编码由gbk转换为utf-8
def ReadDirectoryFile(rootdir):
    for parent,dirnames,filenames in os.walk(rootdir):
            #case 1:
            for dirname in dirnames:
                    print("parent folder is:" + parent)
                    print("dirname is:" + dirname)
            #case 2
            for filename in filenames:    
                    print("parent folder is:" + parent)
                    print("filename with full path:"+ os.path.join(parent,filename))
                    if filename.endswith(".jsp"):
                            UTF8_2_GBK(os.path.join(parent,filename),os.path.join(parent,filename))
                            print("jsp文件")
if __name__=="__main__":
    ReadDirectoryFile(".")

为文件添加行号

#####################
#   为文件添加行号   #
#####################
import codecs
old_filename = "wordcount.py"
new_filename = "newwordcount.py"
fnew = codecs.open(new_filename,'w','utf-8')
with codecs.open(old_filename,'r','utf-8') as f:
    number = 1
    for line in f:
        fnew.write(str(number)+' ' + line)
        number = number + 1
    fnew.close()