harfbuzz/test/shaping/hb-unicode-prettyname

#!/usr/bin/python

import sys
import re
import unicodedata

shorthands = {
	"ZERO WIDTH NON-JOINER": "ZWNJ",
	"ZERO WIDTH JOINER": "ZWJ",
	"NARROW NO-BREAK SPACE": "NNBSP",
	"COMBINING GRAPHEME JOINER": "CGJ",
	"LEFT-TO-RIGHT MARK": "LRM",
	"RIGHT-TO-LEFT MARK": "RLM",
	"LEFT-TO-RIGHT EMBEDDING": "LRE",
	"RIGHT-TO-LEFT EMBEDDING": "RLE",
	"POP DIRECTIONAL FORMATTING": "PDF",
	"LEFT-TO-RIGHT OVERRIDE": "LRO",
	"RIGHT-TO-LEFT OVERRIDE": "RLO",
}
def pretty_name (x):
	try:
		s = unicodedata.name (x)
	except ValueError:
		return "XXX"
	s = re.sub (".* LETTER ", "", s)
	s = re.sub (".* VOWEL SIGN (.*)", r"\1-MATRA", s)
	s = re.sub (".* SIGN ", "", s)
	s = re.sub (".* COMBINING ", "", s)
	if re.match (".* VIRAMA", s):
		s = "HALANT"
	if s in shorthands:
		s = shorthands[s]
	return s


def pretty_names (s):
	s = re.sub (r"[<+>\\uU]", " ", s)
	s = re.sub (r"0[xX]", " ", s)
	s = [unichr (int (x, 16)) for x in re.split ('[, \n]', s) if len (x)]
	return ' + '.join (pretty_name (x) for x in s)

if __name__ == '__main__':

	if len (sys.argv) == 1 or ('--stdin' in sys.argv and len (sys.argv) != 2):
		print "Usage:\n  %s UNICODE_CODEPOINTS...\nor:\n  %s --stdin" % (sys.argv[0], sys.argv[0])
		sys.exit (1)

	if '--stdin' in sys.argv:
		sys.argv.remove ('--stdin')
		for line in sys.stdin.readlines ():
			print pretty_names (line)
	else:
		print pretty_names (','.join (sys.argv[1:]))