priyanka_to_unicode.py

# -*- coding: utf-8 -*-

my_map = {
	"B": u"\u0901",
	"Q": u"\u0948\u0902",
	"R": u"\u0940\u0902",
	"W": u"\u0902",
	"b": u"\u0902",
	"D": u"\u0905",
	"F": u"\u0907",
	"F&": u"\u0908",
	"G": u"\u0909",
	"S": u"\u090f",
	"Ss": u"\u0910",
	"k": u"\u0915",
	"K": u"\u0916",
	"i": u"\u0917",
	"Û": u"\u091a",
	"Ú": u"\u091c",
	"p": u"\u091c",
	"š": u"\u091f",
	"[": u"\u0921",
	"l": u"\u0924",
	"eòe": u"\u0924\u094d\u0924",
	"L": u"\u0925",
	"o": u"\u0926",
	"O": u"\u0927",
	"v": u"\u0928",
	"h": u"\u092a",
	"H": u"\u092b",
	"y": u"\u092c",
	"Y": u"\u092d",
	"c": u"\u092e",
	"Ù": u"\u092f",
	"j": u"\u0930",
	"&": u"\u0930\u094d",
	"u": u"\u0932",
	"J": u"\u0935",
	"M": u"\u0936",
	"m": u"\u0938",
	"n": u"\u0939",
	"eâe": u"\u093e",
	"ef": u"\u093f",
	"r": u"\u093f",
	"eer": u"\u0940",
	"g": u"\u0941",
	"t": u"\u0942",
	"eâs": u"\u0947",
	"eâ": "",
	"es": u"\u0947",
	"s": u"\u0947",
	"ew": u"\u0948",
	"w": u"\u0948",
	"ees": u"\u094b",
	"eeW": u"\u094b\u0902",
	"eew": u"\u094c",
	"ew": u"\u094c",
	"â": u"\u094d",
	"eä": u"\u094d",
	"~": u"\u0964",
	"$": u"\u0924\u094d\u0930", # tra
	"ßeer": u'\u0936\u094d\u0930\u0940' # shree
}

with open("sample2.txt", "r") as infile:
	intxt = infile.read()

for key_len in (5, 4, 3, 2, 1):
	for key in my_map:
		if len(key)==key_len:
			intxt = intxt.replace(key, my_map[key].encode("utf-8"))
			
# all double ee's are aa
intxt = intxt.replace("ee", u"\u093e".encode("utf-8"))

# empty plain matra "e" not required in unicode
intxt = intxt.replace("e", "")

# switch the small ee matras (?)

# switch half-r to front (0930, 094d)

print intxt