#!/usr/bin/env python
# encoding: utf-8
"""
untitled.py

Created by Jun Du on 2010-04-06.
Copyright (c) 2010 Ruiking Mobile. All rights reserved.
"""

import sys,os
import getopt
import itertools
import codecs
from time import sleep

exts = ['txt']
coders = ['utf-8','gb18030','gb2312','utf-16le']

help_message = '''
The help message goes here.
'''

def utf8Detect(text):
    '''Detect if a string is utf-8 encoding'''
    lastch=0
    begin=0
    BOM=True
    BOMchs=(0xEF, 0xBB, 0xBF)
    good=0
    bad=0
    for char in text:
        ch=ord(char)
        if begin<3:
            BOM=(BOMchs[begin]==ch) and BOM
            begin += 1
            continue
        if (begin==4) and (BOM==True):
            break;
        if (ch & 0xC0) == 0x80:
            if (lastch & 0xC0) == 0xC0:
                good += 1
            elif (lastch &0x80) == 0:
                bad += 1
        elif (lastch & 0xC0) == 0xC0:
            bad += 1
        
        lastch = ch
            
    if (((begin == 4) and (BOM == True)) or
        (good >= bad)):
        return True
    else:
        return False

def anyTrue(predicate,sequence):
	return True in itertools.imap(predicate,sequence)
	
def endsWith(s,*endings):
	return anyTrue(s.endswith,endings)
	
def filterFiles(folder,exts):
	for fileName in os.listdir(folder):
		thePath = folder + '/' + fileName
		if os.path.isdir(thePath):
			filterFiles(thePath, exts)
		elif anyTrue(fileName.endswith,exts):
			# print thePath
			text = ''
			for theCoder in coders:
				try:
					theFile = codecs.open(thePath,'r',theCoder)
					text = theFile.read()
					if len(text) <> 0:
						break;
				except:
					continue
								
			f = file(thePath,'w')
			f.write(codecs.BOM_UTF8)
			f.write(text.encode('utf-8'))
			f.close()

class Usage(Exception):
	def __init__(self, msg):
		self.msg = msg


def main(argv=None):
	if argv is None:
		argv = sys.argv
	try:
		try:
			opts, args = getopt.getopt(argv[1:], "ho:v", ["help", "output="])
		except getopt.error, msg:
			raise Usage(msg)
	
		# option processing
		for option, value in opts:
			if option == "-v":
				verbose = True
			if option in ("-h", "--help"):
				raise Usage(help_message)
			if option in ("-o", "--output"):
				output = value
	
	except Usage, err:
		print >> sys.stderr, sys.argv[0].split("/")[-1] + ": " + str(err.msg)
		print >> sys.stderr, "\t for help use --help"
		return 2
		
	print 'processing...'
	rootpath = os.path.abspath('.')
	# print rootpath
	
	filterFiles(rootpath,exts)

	print 'finished.'


if __name__ == "__main__":
	sys.exit(main())