Skip to content

Instantly share code, notes, and snippets.

@junaidpv
Created September 20, 2013 03:38
Show Gist options
  • Select an option

  • Save junaidpv/6633007 to your computer and use it in GitHub Desktop.

Select an option

Save junaidpv/6633007 to your computer and use it in GitHub Desktop.
Replace old chills with new atomic chills. To read more about chills see: http://www.unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters
#!python
"""
Replace old chills with new atomic chills.
To read more about chills see: http://www.unicode.org/versions/Unicode5.1.0/#Malayalam_Chillu_Characters
"""
import unicodedata
import codecs
import sys
import os.path
# Chill pairs
chills = {
u'\u0D23\u0D4D\u200D': u'\u0D7A', # new chillu NN
u'\u0D28\u0D4D\u200D': u'\u0D7B', # new chillu N
u'\u0d30\u0d4d\u200d': u'\u0d7c', # new chillu R
u'\u0D32\u0D4D\u200D': u'\u0D7D', # new chillu L
u'\u0D33\u0D4D\u200D': u'\u0D7E', # new chillu LL
u'\u0d15\u0D4D\u200D': u'\u0D7F', # new chillu K
}
#oldNT = u'\u0d28\u0d4d\u0D31'
#newNT = u'\u0D7B\u0D4D\u0D31'
# function to replace old chills with new ones
def replace_chills(string):
for old_chill, new_chill in chills.iteritems():
string=string.replace(old_chill, new_chill)
return string
if __name__ =='__main__':
input_filename = sys.argv[1]
output_filename = sys.argv[2]
input_file = codecs.open(input_filename, mode='r', encoding='utf-8')
output_file = codecs.open(output_filename, mode='w+', encoding='utf-8')
# Read entire text and convert.
output_file.write(replace_chills(input_file.read()))
output_file.flush()
output_file.close()
input_file.close()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment