runtime now looks at the SVf_UTF8 bit on the SV to decide

whether to use widechar semantics; lexer and RE engine continue
to need "use utf8" to enable unicode awareness in literals
and patterns (TODO: this needs to be fixed); $1 et al are marked
SvUTF8 if the pattern was compiled for utf8 (TODO: propagating
it from the data is probably better)

p4raw-id: //depot/perl@4930

4 files changed, 6 insertions, 18 deletions

diff --git a/t/pragma/warn/doop b/t/pragma/warn/doop
index cce6bdc07c..c16e24f919 100644
--- a/t/pragma/warn/doop
+++ b/t/pragma/warn/doop
@@ -1,6 +1,6 @@
   doop.c	AOK
 
-  Malformed UTF-8 character
+  \x%s will produce malformed UTF-8 character; use \x{%s} for that
 
 
 __END__
@@ -9,7 +9,6 @@ use utf8 ;
 $_ = "\x80  \xff" ;
 chop ;
 EXPECT
-Malformed UTF-8 character at - line 4.
 ########
 # doop.c
 BEGIN {
@@ -28,4 +27,3 @@ chop ;
 EXPECT
 \x80 will produce malformed UTF-8 character; use \x{80} for that at - line 10.
 \xff will produce malformed UTF-8 character; use \x{ff} for that at - line 10.
-Malformed UTF-8 character at - line 11.
diff --git a/t/pragma/warn/pp b/t/pragma/warn/pp
index eb09e059ba..4c70fd5d6f 100644
--- a/t/pragma/warn/pp
+++ b/t/pragma/warn/pp
@@ -30,7 +30,8 @@
 
   Mandatory Warnings
   ------------------
-  Malformed UTF-8 character
+  Malformed UTF-8 character (not tested: difficult to produce with
+                             perl now)
 
 __END__
 # pp.c
@@ -109,7 +110,6 @@ use utf8 ;
 $_ = "\x80  \xff" ;
 reverse ;
 EXPECT
-Malformed UTF-8 character at - line 4.
 ########
 # pp.c
 BEGIN {
@@ -128,4 +128,3 @@ reverse ;
 EXPECT
 \x80 will produce malformed UTF-8 character; use \x{80} for that at - line 10.
 \xff will produce malformed UTF-8 character; use \x{ff} for that at - line 10.
-Malformed UTF-8 character at - line 11.
diff --git a/t/pragma/warn/sv b/t/pragma/warn/sv
index 97d61bca17..cdec48e2c2 100644
--- a/t/pragma/warn/sv
+++ b/t/pragma/warn/sv
@@ -38,8 +38,8 @@
 
   Mandatory Warnings
   ------------------
-  Malformed UTF-8 character [sv_pos_b2u]
-      my $a = rindex "a\xff bc ", "bc" ;
+  Malformed UTF-8 character [sv_pos_b2u] (not tested: difficult to produce
+                                          with perl now)
 
   Mandatory Warnings TODO
   ------------------
@@ -286,8 +286,6 @@ $^W =0 ;
 my $a = rindex "a\xff bc ", "bc" ;
 EXPECT
 \xff will produce malformed UTF-8 character; use \x{ff} for that at - line 12.
-Malformed UTF-8 character at - line 12.
-Malformed UTF-8 character at - line 16.
 ########
 # sv.c
 use warnings 'misc';
diff --git a/t/pragma/warn/utf8 b/t/pragma/warn/utf8
index 19b8d1db3a..cb1f202b8d 100644
--- a/t/pragma/warn/utf8
+++ b/t/pragma/warn/utf8
@@ -1,14 +1,13 @@
 
   utf8.c AOK
 
-  All Mandatory warnings
- 
      [utf8_to_uv]
      Malformed UTF-8 character
 	my $a = ord "\x80" ;
 
      Malformed UTF-8 character
 	my $a = ord "\xf080" ;
+     <<<<<< this warning can't be easily triggered from perl anymore
 
      [utf16_to_utf8]
      Malformed UTF-16 surrogate		
@@ -19,7 +18,6 @@ __END__
 use utf8 ;
 my $a = ord "\x80" ;
 EXPECT
-Malformed UTF-8 character at - line 3.
 ########
 # utf8.c [utf8_to_uv]
 BEGIN {
@@ -37,15 +35,12 @@ my $a = ord "\x80" ;
     my $a = ord "\x80" ;
 }
 EXPECT
-Malformed UTF-8 character at - line 9.
 \x80 will produce malformed UTF-8 character; use \x{80} for that at - line 12.
-Malformed UTF-8 character at - line 12.
 ########
 # utf8.c [utf8_to_uv]
 use utf8 ;
 my $a = ord "\xf080" ;
 EXPECT
-Malformed UTF-8 character at - line 3.
 ########
 # utf8.c [utf8_to_uv]
 BEGIN {
@@ -63,6 +58,4 @@ my $a = ord "\xf080" ;
     my $a = ord "\xf080" ;
 }
 EXPECT
-Malformed UTF-8 character at - line 9.
 \xf0 will produce malformed UTF-8 character; use \x{f0} for that at - line 12.
-Malformed UTF-8 character at - line 12.