Perl中文/unicode/utf8/GB2312編碼之間的轉換是一件很讓人頭疼的事情,我總結了以下主要的轉換方法,供大家瞭解參考。
# author: jiangyujie<br />use utf8;<br />use Encode;<br />use URI::Escape;</p><p>$/ = "/n";</p><p>#從unicode得到utf8編碼<br />$str = '%u6536';<br />$str =~ s//%u([0-9a-fA-F]{4})/pack("U",hex($1))/eg;<br />$str = encode( "utf8", $str );<br />print uc unpack( "H*", $str );</p><p># 從unicode得到gb2312編碼<br />$str = '%u6536';<br />$str =~ s//%u([0-9a-fA-F]{4})/pack("U",hex($1))/eg;<br />$str = encode( "gb2312", $str );<br />print uc unpack( "H*", $str );</p><p># 從中文得到utf8編碼<br />$str = "收";<br />print uri_escape($str);</p><p># 從utf8編碼得到中文<br />$utf8_str = uri_escape("收");<br />print uri_unescape($str);</p><p># 從中文得到perl unicode<br />utf8::decode($str);<br />@chars = split //, $str;<br />foreach (@chars) {<br /> printf "%x ", ord($_);<br />}</p><p># 從中文得到標準unicode<br />$a = "漢語";<br />$a = decode( "utf8", $a );<br />map { print "//u", sprintf( "%x", $_ ) } unpack( "U*", $a );</p><p># 從標準unicode得到中文<br />$str = '%u6536';<br />$str =~ s//%u([0-9a-fA-F]{4})/pack("U",hex($1))/eg;<br />$str = encode( "utf8", $str );<br />print $str;</p><p># 從perl unicode得到中文<br />my $unicode = "/x{505c}/x{8f66}";<br />print encode( "utf8", $unicode );