gistfile1.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# Author: Viktor Stískala
# Contact: viktor (at) stiskala.cz
# Copyright: This module has been placed in the public domain.

"""
This module removes language specific characters from file name
and makes it more usable for web. Can be also used as nautilus user script
when placed inside ~/.gnome2/nautilus-scripts
"""

import re
import os, sys

# transliteration table
conversion = {
	u'ä' : 'a',	u'Ä' : 'A',	u'á' : 'a',	u'Á' : 'A',	u'à' : 'a',	u'À' : 'A',	u'ã' : 'a',
	u'Ã' : 'A',	u'â' : 'a',	u'Â' : 'A',	u'č' : 'c',	u'Č' : 'C',	u'ć' : 'c',	u'Ć' : 'C',
	u'ď' : 'd',	u'Ď' : 'D',	u'ě' : 'e',	u'Ě' : 'E',	u'é' : 'e',	u'É' : 'E',	u'ë' : 'e',
	u'Ë' : 'E',	u'è' : 'e',	u'È' : 'E',	u'ê' : 'e',	u'Ê' : 'E',	u'í' : 'i',	u'Í' : 'I',
	u'ï' : 'i',	u'Ï' : 'I',	u'ì' : 'i',	u'Ì' : 'I',	u'î' : 'i',	u'Î' : 'I',	u'ľ' : 'l',
	u'Ľ' : 'L',	u'ĺ' : 'l',	u'Ĺ' : 'L',	u'ń' : 'n',	u'Ń' : 'N',	u'ň' : 'n',	u'Ň' : 'N',
	u'ñ' : 'n',	u'Ñ' : 'N',	u'ó' : 'o',	u'Ó' : 'O',	u'ö' : 'o',	u'Ö' : 'O',	u'ô' : 'o',
	u'Ô' : 'O',	u'ò' : 'o',	u'Ò' : 'O',	u'õ' : 'o',	u'Õ' : 'O',	u'ő' : 'o',	u'Ő' : 'O',
	u'ř' : 'r',	u'Ř' : 'R',	u'ŕ' : 'r',	u'Ŕ' : 'R',	u'š' : 's',	u'Š' : 'S',	u'ś' : 's',
	u'Ś' : 'S',	u'ť' : 't',	u'Ť' : 'T',	u'ú' : 'u',	u'Ú' : 'U',	u'ů' : 'u',	u'Ů' : 'U',
	u'ü' : 'u',	u'Ü' : 'U',	u'ù' : 'u',	u'Ù' : 'U',	u'ũ' : 'u',	u'Ũ' : 'U',	u'û' : 'u',
	u'Û' : 'U',	u'ý' : 'y',	u'Ý' : 'Y',	u'ž' : 'z',	u'Ž' : 'Z',	u'ź' : 'z',	u'Ź' : 'Z'
};

def convert (text):
	ret = ""

	# find suffix
	rsuffix = re.compile(r'\.[a-z]+$', re.IGNORECASE)
	suffix = rsuffix.search(text)
	if suffix:
		suffix = suffix.group(0)
		text = text[:-len(suffix)]

	for c in text:
		try:
			c = conversion[c]
		except KeyError:
			pass
		ret += c

	space = re.compile(r'[\s]+', re.IGNORECASE)

	# all characters that doesn't match this pattern will be deleted
	nonalpha = re.compile(r'[^a-z0-9_\.\-\\(\\)]+', re.IGNORECASE)
	# remove multiple occurences, such as __ or --
	multiple = re.compile(r'([-_\.]){1}\1+')
	end = re.compile(r'[_\.-]+$')
	start = re.compile(r'^[_\.-]+')

	# replace spaces with _
	ret = space.sub('_', ret)
	ret = nonalpha.sub('', ret)
	ret = multiple.sub('\\1', ret)
	ret = end.sub('', ret)
	ret = start.sub('', ret)

	# add suffix if present
	if suffix:
		ret += suffix

	return ret.lower()

def main():
	"""Reads all filenames from parameters and performs conversion"""
	for i in range(1, len(sys.argv)):
		name = os.path.basename(sys.argv[i]).decode('utf-8')
		new_name = os.path.dirname(sys.argv[i]).decode('utf-8') + convert(name)

		# rename if name changed
		if sys.argv[i].decode('utf-8') != new_name:
			try:
				os.rename(sys.argv[i], new_name)
			except OSError:
				print "Cannot rename file " + sys.argv[i].decode('utf-8') + ". Does it exists?"

if __name__ == "__main__":
    main()