X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2Fcharnames.pm;h=934fafddd5ff8f5e0e95edaa6d3702d3376c51cd;hb=92dffb52e8549d6a194db47a2e5b989b8338a19a;hp=e407ff7c8af8eaeb59ba1e621f7ac9c958c02ec7;hpb=423cee853811c26846bd1948939b85f9866dfb4a;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/lib/charnames.pm b/lib/charnames.pm
index e407ff7..934fafd 100644
--- a/lib/charnames.pm
+++ b/lib/charnames.pm
@@ -1,6 +1,11 @@
 package charnames;
 
-my $fname = 'unicode/UnicodeData-Latest.txt';
+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
@@ -29,29 +34,34 @@ sub charnames {
   }
   die "Unknown charname '$name'" unless @off;
   
-  # use caller 'encoding';	# Does not work at compile time?
-
   my $ord = hex substr $txt, $off[0] - 4, 4;
-  if ($^H & 0x8) {
-    use utf8;
-    return chr $ord;
+  if ($^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 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 "No scripts for `use charnames'" unless @_;
-  $^H |= 0x20000;
+  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 "unicode/Name.pl" unless $txt;
+    for (@{$^H{charnames_scripts}}) {
+        warnings::warn('utf8',  "No such script: '$_'") unless
+	    $txt =~ m/\t\t$_ (?:CAPITAL |SMALL )?LETTER /;
+	}
+  }
 }
 
 
@@ -60,68 +70,71 @@ __END__
 
 =head1 NAME
 
-charnames - define character names for C<\C{named}> string literal escape.
+charnames - define character names for C<\N{named}> string literal escape.
 
 =head1 SYNOPSIS
 
   use charnames ':full';
-  print "\C{GREEK SMALL LETTER SIGMA} is called sigma.\n";
+  print "\N{GREEK SMALL LETTER SIGMA} is called sigma.\n";
 
   use charnames ':short';
-  print "\C{greek:Sigma} is an upper-case sigma.\n";
+  print "\N{greek:Sigma} is an upper-case sigma.\n";
 
   use charnames qw(cyrillic greek);
-  print "\C{sigma} is Greek sigma, and \C{be} is Cyrillic b.\n";
+  print "\N{sigma} is Greek sigma, and \N{be} is Cyrillic b.\n";
 
 =head1 DESCRIPTION
 
 Pragma C<use charnames> supports arguments C<:full>, C<:short> and
 script names.  If C<:full> is present, for expansion of
-C<\C{CHARNAME}}> string C<CHARNAME> is first looked in the list of
+C<\N{CHARNAME}}> string C<CHARNAME> is first looked in the list of
 standard Unicode names of chars.  If C<:short> is present, and
 C<CHARNAME> has the form C<SCRIPT:CNAME>, then C<CNAME> is looked up
 as a letter in script C<SCRIPT>.  If pragma C<use charnames> is used
-with script name arguments, then for C<\C{CHARNAME}}> the name
+with script name arguments, then for C<\N{CHARNAME}}> the name
 C<CHARNAME> is looked up as a letter in the given scripts (in the
 specified order).
 
 For lookup of C<CHARNAME> inside a given script C<SCRIPTNAME>
-F<charcodes.pm> looks for the names
+this pragma looks for the names
 
   SCRIPTNAME CAPITAL LETTER CHARNAME
   SCRIPTNAME SMALL LETTER CHARNAME
   SCRIPTNAME LETTER CHARNAME
 
 in the table of standard Unicode names.  If C<CHARNAME> is lowercase,
-then the C<CAPITAL> variant is ignored, otherwise C<SMALL> variant is
+then the C<CAPITAL> variant is ignored, otherwise the C<SMALL> variant is
 ignored.
 
 =head1 CUSTOM TRANSLATORS
 
-The mechanism of translation is C<\C{...}> escapes is general and not
+The mechanism of translation of C<\N{...}> escapes is general and not
 hardwired into F<charnames.pm>.  A module can install custom
-translations (inside the scope which C<use>s the module) by the
+translations (inside the scope which C<use>s the module) with the
 following magic incantation:
 
-  sub import {
-    shift;
-    $^H |= 0x20000;
-    $^H{charnames} = \&translator;
-  }
+    use charnames ();		# for $charnames::hint_bits
+    sub import {
+	shift;
+	$^H |= $charnames::hint_bits;
+	$^H{charnames} = \&translator;
+    }
 
 Here translator() is a subroutine which takes C<CHARNAME> as an
 argument, and returns text to insert into the string instead of the
-C<\C{CHARNAME}> escape.  Since the text to insert should be different
-in C<utf8> mode and out of it, the function should check the current
-state of C<utf8>-flag as in
-
-  sub translator {
-    if ($^H & 0x8) {
-      return utf_translator(@_);
-    } else {
-      return no_utf_translator(@_);
+C<\N{CHARNAME}> escape.  Since the text to insert should be different
+in C<bytes> mode and out of it, the function should check the current
+state of C<bytes>-flag as in:
+
+    use bytes ();			# for $bytes::hint_bits
+    sub translator {
+	if ($^H & $bytes::hint_bits) {
+	    return bytes_translator(@_);
+	}
+	else {
+	    return utf8_translator(@_);
+	}
     }
-  }
 
 =head1 BUGS
 
@@ -131,4 +144,3 @@ do any C<eval>s or C<require>s.  This restriction should be lifted in
 a future version of Perl.
 
 =cut
-