[Fwd: [PATCH] Pod::Find should ignore SCM files and dirs]

[perl5.git] / lib / charnames.pm

diff --git a/lib/charnames.pm b/lib/charnames.pm
index 7b39cee..4f7fdeb 100644 (file)
--- a/lib/charnames.pm
+++ b/lib/charnames.pm
@@ -3,7 +3,7 @@ use strict;
 use warnings;
 use Carp;
 use File::Spec;
-our $VERSION = '1.02';
+our $VERSION = '1.03';
 
 use bytes ();          # for $bytes::hint_bits
 $charnames::hint_bits = 0x20000; # HINT_LOCALIZE_HH
@@ -107,7 +107,7 @@ sub charnames
     ## @off will hold the index into the code/name string of the start and
     ## end of the name as we find it.
 
-    ## If :full, look for the the name exactly
+    ## If :full, look for the name exactly
     if ($^H{charnames_full} and $txt =~ /\t\t\Q$name\E$/m) {
       @off = ($-[0], $+[0]);
     }
@@ -238,7 +238,19 @@ sub import
   }
 } # import
 
-require Unicode::UCD; # for Unicode::UCD::_getcode()
+# this comes actually from Unicode::UCD, but it avoids the
+# overhead of loading it
+sub _getcode {
+    my $arg = shift;
+
+    if ($arg =~ /^[1-9]\d*$/) {
+       return $arg;
+    } elsif ($arg =~ /^(?:[Uu]\+|0[xX])?([[:xdigit:]]+)$/) {
+       return hex($1);
+    }
+
+    return;
+}
 
 my %viacode;
 
@@ -250,7 +262,7 @@ sub viacode
   }
 
   my $arg = shift;
-  my $code = Unicode::UCD::_getcode($arg);
+  my $code = _getcode($arg);
 
   my $hex;
 
@@ -333,9 +345,10 @@ charnames - define character names for C<\N{named}> string literal escapes
 
   use charnames ":full", ":alias" => {
     e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
-    };
+  };
   print "\N{e_ACUTE} is a small letter e with an acute.\n";
 
+  use charnames ();
   print charnames::viacode(0x1234); # prints "ETHIOPIC SYLLABLE SEE"
   printf "%04X", charnames::vianame("GOTHIC LETTER AHSA"); # prints "10330"
 
@@ -343,8 +356,8 @@ charnames - define character names for C<\N{named}> string literal escapes
 
 Pragma C<use charnames> supports arguments C<:full>, C<:short>, script
 names and customized aliases.  If C<:full> is present, for expansion 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<\N{CHARNAME}>, the string C<CHARNAME> is first looked up in the list of
+standard Unicode character names.  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<\N{CHARNAME}> the name