本文实例讲述了python实现JAVA源代码从ANSI到UTF-8的批量转换方法。分享给大家供大家参考。具体如下:
喜欢用eclipse的大神们,可能一不小心代码就变成ANSI码了,需要转换成utf-8嘛,一个文件一个文件的在Notepad2或者notepad++里面转换么?不,这里有批量转换的程序,python实现,需要的拿去用吧。
ansi2utf8.py:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
|
#-*- coding: utf-8 -*-
import codecs
import os
import shutil
import re
import chardet
def convert_encoding(filename, target_encoding):
# Backup the origin file.
shutil.copyfile(filename, filename + '.bak' )
# convert file from the source encoding to target encoding
content = codecs. open (filename, 'r' ).read()
source_encoding = chardet.detect(content)[ 'encoding' ]
print source_encoding, filename
content = content.decode(source_encoding) #.encode(source_encoding)
codecs. open (filename, 'w' , encoding = target_encoding).write(content)
def main():
for root, dirs, files in os.walk(os.getcwd()):
for f in files:
if f.lower().endswith( '.java' ):
filename = os.path.join(root, f)
try :
convert_encoding(filename, 'utf-8' )
except Exception, e:
print filename
def process_bak_files(action = 'restore' ):
for root, dirs, files in os.walk(os.getcwd()):
for f in files:
if f.lower().endswith( '.java.bak' ):
source = os.path.join(root, f)
target = os.path.join(root, re.sub( '\.java\.bak$' , '.java' , f, flags = re.IGNORECASE))
try :
if action = = 'restore' :
shutil.move(source, target)
elif action = = 'clear' :
os.remove(source)
except Exception, e:
print source
if __name__ = = '__main__' :
# process_bak_files(action='clear')
main()
|
把程序拷贝到java源文件所在目录下运行就好了。
希望本文所述对大家的Python程序设计有所帮助。