#!/usr/local/bin/perl -p

# print non-ASCII codes from UTF-8 stream

s/([\xC0-\xDF])([\x80-\xBF])/sprintf("<U%04X>",
unpack("c",$1)<<6&0x07C0|unpack("c",$2)&0x003F)/ge;
s/([\xE0-\xEF])([\x80-\xBF])([\x80-\xBF])/sprintf("<U%04X>",
unpack("c",$1)<<12&0xF000|unpack("c",$2)<<6&0x0FC0|unpack("c",$3)&0x003F)/ge;
s/([\xF0-\xF7])([\x80-\xBF])([\x80-\xBF])([\x80-\xBF])/sprintf("<U%08X>",
unpack("c",$1)<<18&0x1C0000|unpack("c",$2)<<12&0x3F000|
unpack("c",$3)<<6&0x0FC0|unpack("c",$4)&0x003F)/ge;
