Misapplied regex optimizations when \C is present.

[p5sagit/p5-mst-13.2.git] / lib / utf8.pm

diff --git a/lib/utf8.pm b/lib/utf8.pm
index be7cc0b..f06b893 100644 (file)
--- a/lib/utf8.pm
+++ b/lib/utf8.pm
@@ -1,20 +1,26 @@
 package utf8;
 
-$^U = 1 if caller and caller eq 'main';        # they are unicode aware
-                                       # XXX split this out?
+if (ord('A') != 193) { # make things more pragmatic for EBCDIC folk
+
+$utf8::hint_bits = 0x00800000;
+
+our $VERSION = '1.00';
 
 sub import {
-    $^H |= 0x00800000;
+    $^H |= $utf8::hint_bits;
     $enc{caller()} = $_[1] if $_[1];
 }
 
 sub unimport {
-    $^H &= ~0x00800000;
+    $^H &= ~$utf8::hint_bits;
 }
 
 sub AUTOLOAD {
     require "utf8_heavy.pl";
-    goto &$AUTOLOAD;
+    goto &$AUTOLOAD if defined &$AUTOLOAD;
+    Carp::croak("Undefined subroutine $AUTOLOAD called");
+}
+
 }
 
 1;
@@ -32,7 +38,7 @@ utf8 - Perl pragma to enable/disable UTF-8 in source code
 =head1 DESCRIPTION
 
 WARNING: The implementation of Unicode support in Perl is incomplete.
-Expect sudden and unannounced changes!
+See L<perlunicode> for the exact details.
 
 The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the
 program text in the current lexical scope.  The C<no utf8> pragma
@@ -45,7 +51,9 @@ in future we would like to standardize on the UTF-8 encoding for
 source text.  Until UTF-8 becomes the default format for source
 text, this pragma should be used to recognize UTF-8 in the source.
 When UTF-8 becomes the standard source format, this pragma will
-effectively become a no-op.
+effectively become a no-op.  This pragma already is a no-op on
+EBCDIC platforms (where it is alright to code perl in EBCDIC 
+rather than UTF-8).
 
 Enabling the C<utf8> pragma has the following effects:
 
@@ -60,15 +68,6 @@ and package names.
 
 =item *
 
-As a side effect, when this pragma is used within the main package,
-it also enables Unicode character semantics for the entire program.
-See L<perlunicode> for more on that.
-
-[XXX: split this out into separate "pragma" and/or -C command-line
-switch?]
-
-=item *
-
 In the absence of inputs marked as UTF-8, regular expressions within the
 scope of this pragma will default to using character semantics instead
 of byte semantics.
@@ -80,11 +79,8 @@ of byte semantics.
        @chars = split //, $data;       # splits characters
     }
 
-[XXX: Should this should be enabled like chr()/sprintf("%c") by looking
-at $^U instead?]
-
 =head1 SEE ALSO
 
-L<perlunicode>, L<byte>
+L<perlunicode>, L<bytes>
 
 =cut