package charnames; our $VERSION = '1.00'; use bytes (); # for $bytes::hint_bits use warnings(); $charnames::hint_bits = 0x20000; my $txt; # This is not optimized in any way yet sub charnames { $name = shift; $txt = do "unicore/Name.pl" unless $txt; my @off; if ($^H{charnames_full} and $txt =~ /\t\t$name$/m) { @off = ($-[0], $+[0]); } unless (@off) { if ($^H{charnames_short} and $name =~ /^(.*?):(.*)/s) { my ($script, $cname) = ($1,$2); my $case = ( $cname =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL"); if ($txt =~ m/\t\t\U$script\E (?:$case )?LETTER \U$cname$/m) { @off = ($-[0], $+[0]); } } } unless (@off) { my $case = ( $name =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL"); for ( @{$^H{charnames_scripts}} ) { (@off = ($-[0], $+[0])), last if $txt =~ m/\t\t$_ (?:$case )?LETTER \U$name$/m; } } die "Unknown charname '$name'" unless @off; my $hexlen = 4; # Unicode guarantees 4-, 5-, or 6-digit format $hexlen++ while $hexlen < 6 && substr($txt, $off[0] - $hexlen - 1, 1) =~ /[0-9a-f]/; my $ord = hex substr $txt, $off[0] - $hexlen, $hexlen; if ($^H & $bytes::hint_bits) { # "use bytes" in effect? use bytes; return chr $ord if $ord <= 255; my $hex = sprintf '%X=0%o', $ord, $ord; my $fname = substr $txt, $off[0] + 2, $off[1] - $off[0] - 2; die "Character 0x$hex with name '$fname' is above 0xFF"; } return chr $ord; } sub import { shift; die "`use charnames' needs explicit imports list" unless @_; $^H |= $charnames::hint_bits; $^H{charnames} = \&charnames ; my %h; @h{@_} = (1) x @_; $^H{charnames_full} = delete $h{':full'}; $^H{charnames_short} = delete $h{':short'}; $^H{charnames_scripts} = [map uc, keys %h]; if (warnings::enabled('utf8') && @{$^H{charnames_scripts}}) { $txt = do "unicore/Name.pl" unless $txt; for (@{$^H{charnames_scripts}}) { warnings::warn('utf8', "No such script: '$_'") unless $txt =~ m/\t\t$_ (?:CAPITAL |SMALL )?LETTER /; } } } 1; __END__ =head1 NAME charnames - define character names for C<\N{named}> string literal escape. =head1 SYNOPSIS use charnames ':full'; print "\N{GREEK SMALL LETTER SIGMA} is called sigma.\n"; use charnames ':short'; print "\N{greek:Sigma} is an upper-case sigma.\n"; use charnames qw(cyrillic greek); print "\N{sigma} is Greek sigma, and \N{be} is Cyrillic b.\n"; =head1 DESCRIPTION Pragma C supports arguments C<:full>, C<:short> and script names. If C<:full> is present, for expansion of C<\N{CHARNAME}}> string C is first looked in the list of standard Unicode names of chars. If C<:short> is present, and C has the form C, then C is looked up as a letter in script C