spacepaste

#!/usr/bin/python
# -*- coding: utf-8 -*-
"""A small filter that converts between various byte-encodings of Unicode text.
Default behavior translates Unicode-escaped text ("\u2603") to UTF-8 ("☃") to
better read Python repr() output.
"""
from __future__ import unicode_literals
import io
import optparse
import sys
def getopt():
parser = optparse.OptionParser(__doc__)
parser.add_option(
'-i',
'--input',
dest='input_encoding',
default='utf-8',
help='Input encoding. [default: %default]',
)
parser.add_option(
'-o',
'--output',
dest='output_encoding',
default='utf-8',
help='Output encoding. [default: %default]',
)
options, args = parser.parse_args()
if not args:
args = ['/dev/stdin']
return args, options
def show_unicode(infiles, input_encoding='utf-8', output_encoding='utf-8'):
output = io.open(sys.stdout.fileno(), 'w', encoding=output_encoding)
for arg in infiles:
input = io.open(arg, 'r', encoding=input_encoding)
for line in input:
line = line.encode('ascii', 'backslashreplace')
line = line.decode('unicode_escape')
output.write(line)
output.flush()
def main():
args, options = getopt()
return show_unicode(args, **vars(options))
if __name__ == '__main__':
exit(main())