Use \N{named characters} instead of \C.

To: jhi@iki.fi
Cc: larry@wall.org (Larry Wall), Tim.Bunce@ig.co.uk (Tim Bunce),
       	perl5-porters@perl.org (Mailing list Perl5)
Subject: Re: [PATCH 5.005_58] Named characters in Perl
Message-Id: <199908292046.QAA05510@monk.mps.ohio-state.edu>

p4raw-id: //depot/cfgperl@4052

8 files changed, 27 insertions, 26 deletions

diff --git a/lib/charnames.pm b/lib/charnames.pm
index e407ff7c8a..bd97983abc 100644
--- a/lib/charnames.pm
+++ b/lib/charnames.pm
@@ -60,28 +60,28 @@ __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).
 
@@ -98,7 +98,7 @@ ignored.
 
 =head1 CUSTOM TRANSLATORS
 
-The mechanism of translation is C<\C{...}> escapes is general and not
+The mechanism of translation is 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
 following magic incantation:
@@ -111,7 +111,7 @@ following magic incantation:
 
 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
+C<\N{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
 
diff --git a/lib/utf8.pm b/lib/utf8.pm
index 8f650d9d00..5ddd4ba21a 100644
--- a/lib/utf8.pm
+++ b/lib/utf8.pm
@@ -71,8 +71,9 @@ attempt to canonicalize variable names for you.)
 =item *
 
 Regular expressions match characters instead of bytes.  For instance,
-"." matches a character instead of a byte.  (However, the C<\O> pattern
-is provided to force a match a single byte ("octet", hence C<\O>).)
+"." matches a character instead of a byte.  (However, the C<\C> pattern
+is provided to force a match a single byte ("C<char>" in C, hence
+C<\C>).)
 
 =item *
 
diff --git a/pod/perldiag.pod b/pod/perldiag.pod
index cd9583bc87..2634d837fc 100644
--- a/pod/perldiag.pod
+++ b/pod/perldiag.pod
@@ -1725,9 +1725,9 @@ ended earlier on the current line.
 mentioned with the $ in Perl, unlike in the shells, where it can vary from
 one line to the next.
 
-=item Missing %sbrace%s on \C{}
+=item Missing %sbrace%s on \N{}
 
-(F) Wrong syntax of character name literal C<\C{charname}> within
+(F) Wrong syntax of character name literal C<\N{charname}> within
 double-quotish context.
 
 =item Missing comma after first argument to %s function
diff --git a/pod/perlop.pod b/pod/perlop.pod
index bd4ca1df7d..14ca6b5ec0 100644
--- a/pod/perlop.pod
+++ b/pod/perlop.pod
@@ -673,7 +673,7 @@ a transliteration, the first eleven of these sequences may be used.
     \x1b	hex char	(ESC)
     \x{263a}	wide hex char	(SMILEY)
     \c[		control char    (ESC)
-    \C{name}	named char
+    \N{name}	named char
 
     \l		lowercase next char
     \u		uppercase next char
@@ -684,7 +684,7 @@ a transliteration, the first eleven of these sequences may be used.
 
 If C<use locale> is in effect, the case map used by C<\l>, C<\L>, C<\u>
 and C<\U> is taken from the current locale.  See L<perllocale>.  For
-documentation of C<\C{name}>, see L<charnames>.
+documentation of C<\N{name}>, see L<charnames>.
 
 All systems use the virtual C<"\n"> to represent a line terminator,
 called a "newline".  There is no such thing as an unvarying, physical
diff --git a/pod/perlre.pod b/pod/perlre.pod
index a1a118f371..76f345de35 100644
--- a/pod/perlre.pod
+++ b/pod/perlre.pod
@@ -149,7 +149,7 @@ also work:
     \x1B	hex char
     \x{263a}	wide hex char         (Unicode SMILEY)
     \c[		control char
-    \C{name}	named char
+    \N{name}	named char
     \l		lowercase next char (think vi)
     \u		uppercase next char (think vi)
     \L		lowercase till \E (think vi)
@@ -159,7 +159,7 @@ also work:
 
 If C<use locale> is in effect, the case map used by C<\l>, C<\L>, C<\u>
 and C<\U> is taken from the current locale.  See L<perllocale>.  For
-documentation of C<\C{name}>, see L<charnames>.
+documentation of C<\N{name}>, see L<charnames>.
 
 You cannot include a literal C<$> or C<@> within a C<\Q> sequence.
 An unescaped C<$> or C<@> interpolates the corresponding variable,
@@ -178,7 +178,7 @@ In addition, Perl defines the following:
     \PP	Match non-P
     \X	Match eXtended Unicode "combining character sequence",
         equivalent to C<(?:\PM\pM*)>
-    \O	Match a single C char (octet) even under utf8.
+    \C	Match a single C char (octet) even under utf8.
 
 A C<\w> matches a single alphanumeric character, not a whole word.
 Use C<\w+> to match a string of Perl-identifier characters (which isn't 
diff --git a/regcomp.c b/regcomp.c
index 9846022186..fe54a6c45a 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -1780,7 +1780,7 @@ tryagain:
 	    PL_seen_zerolen++;		/* Do not optimize RE away */
 	    nextchar();
 	    break;
-	case 'O':
+	case 'C':
 	    ret = reg_node(SANY);
 	    *flagp |= HASWIDTH|SIMPLE;
 	    nextchar();
diff --git a/t/lib/charnames.t b/t/lib/charnames.t
index 860cc03c75..8d5c8db384 100644
--- a/t/lib/charnames.t
+++ b/t/lib/charnames.t
@@ -12,13 +12,13 @@ print "1..5\n";
 
 use charnames ':full';
 
-print "not " unless "Here\C{EXCLAMATION MARK}?" eq 'Here!?';
+print "not " unless "Here\N{EXCLAMATION MARK}?" eq 'Here!?';
 print "ok 1\n";
 
 print "# \$res=$res \$\@='$@'\nnot "
   if $res = eval <<'EOE'
 use charnames ":full";
-"Here: \C{CYRILLIC SMALL LETTER BE}!";
+"Here: \N{CYRILLIC SMALL LETTER BE}!";
 1
 EOE
   or $@ !~ /above 0xFF/;
@@ -28,7 +28,7 @@ print "ok 2\n";
 print "# \$res=$res \$\@='$@'\nnot "
   if $res = eval <<'EOE'
 use charnames 'cyrillic';
-"Here: \C{Be}!";
+"Here: \N{Be}!";
 1
 EOE
   or $@ !~ /CYRILLIC CAPITAL LETTER BE.*above 0xFF/;
@@ -42,12 +42,12 @@ $encoded_bet = "\327\221";
   use charnames ':full';
   use utf8;
 
-  print "not " unless "\C{CYRILLIC SMALL LETTER BE}" eq $encoded_be;
+  print "not " unless "\N{CYRILLIC SMALL LETTER BE}" eq $encoded_be;
   print "ok 4\n";
 
   use charnames qw(cyrillic greek :short);
 
-  print "not " unless "\C{be},\C{alpha},\C{hebrew:bet}" 
+  print "not " unless "\N{be},\N{alpha},\N{hebrew:bet}" 
     eq "$encoded_be,$encoded_alpha,$encoded_bet";
   print "ok 5\n";
 }
diff --git a/toke.c b/toke.c
index 326c284ff5..f68e97503a 100644
--- a/toke.c
+++ b/toke.c
@@ -1151,7 +1151,7 @@ S_scan_const(pTHX_ char *start)
 	: UTF;
     char *leaveit =			/* set of acceptably-backslashed characters */
 	PL_lex_inpat
-	    ? "\\.^$@AGZdDwWsSbBpPXO+*?|()-nrtfeaxcz0123456789[{]} \t\n\r\f\v#"
+	    ? "\\.^$@AGZdDwWsSbBpPXC+*?|()-nrtfeaxcz0123456789[{]} \t\n\r\f\v#"
 	    : "";
 
     while (s < send || dorange) {
@@ -1372,8 +1372,8 @@ S_scan_const(pTHX_ char *start)
 		}
 		continue;
 
- 	    /* \C{latin small letter a} is a named character */
- 	    case 'C':
+ 	    /* \N{latin small letter a} is a named character */
+ 	    case 'N':
  		++s;
  		if (*s == '{') {
  		    char* e = strchr(s, '}');