#!/usr/bin/perl use warnings; use strict; try_test($ARGV[0], $ARGV[1]); exit; my $text; sub try_test { my $usemytext = shift; my $applyfix = shift; $text = "\x0a \xe2\x84\xa2"; utf8::decode($text); print "is utf8\n" if utf8::is_utf8($text); print "valid utf8\n" if utf8::valid($text); run_regexp($text); print "[$text]\n"; } sub text { $text .= shift; } sub run_regexp { # use encoding 'utf8'; my $t = shift; $t =~ / ( d| )( [s5]| \xC5[\x9A-\xA1]| \xD0\x85| \xD1\x95| \xD5\x8F ) /six; }