From: Rafael Garcia-Suarez <rgs@consttype.org>
Date: Sat, 3 Oct 2009 07:56:42 +0000 (+0200)
Subject: Change warning "Unicode character is illegal" to more accurate description
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=6f6ac1dea8501596050bc974dc468632797d51eb;p=p5sagit%2Fp5-mst-13.2.git

Change warning "Unicode character is illegal" to more accurate description

That now reads "Unicode non-character is illegal in interchange" and the
perldiag documentation is expanded a bit.
---

diff --git a/pod/perldiag.pod b/pod/perldiag.pod
index 606426f..fb00adc 100644
--- a/pod/perldiag.pod
+++ b/pod/perldiag.pod
@@ -4339,11 +4339,13 @@ Check the #! line, or manually feed your script into Perl yourself.
 (F) The unexec() routine failed for some reason.  See your local FSF
 representative, who probably put it there in the first place.
 
-=item Unicode character %s is illegal
+=item Unicode non-character %s is illegal for interchange
 
-(W utf8) Certain Unicode characters have been designated off-limits by
-the Unicode standard and should not be generated.  If you really know
-what you are doing you can turn off this warning by C<no warnings 'utf8';>.
+(W utf8) Certain codepoints, such as U+FFFE and U+FFFF, are defined by the
+Unicode standard to be non-characters. Those are legal codepoints, but are
+reserved for internal use; so, applications shouldn't attempt to exchange
+them. If you know what you are doing you can turn off this warning by
+C<no warnings 'utf8';>.
 
 =item Unknown BYTEORDER
 
diff --git a/t/lib/warnings/utf8 b/t/lib/warnings/utf8
index 6635f02..be49ae9 100644
--- a/t/lib/warnings/utf8
+++ b/t/lib/warnings/utf8
@@ -62,10 +62,10 @@ my $max   = chr(0x10FFFF);
 EXPECT
 UTF-16 surrogate 0xd800 at - line 3.
 UTF-16 surrogate 0xdfff at - line 4.
-Unicode character 0xfffe is illegal at - line 8.
-Unicode character 0xffff is illegal at - line 9.
-Unicode character 0x10fffe is illegal at - line 12.
-Unicode character 0x10ffff is illegal at - line 13.
+Unicode non-character 0xfffe is illegal for interchange at - line 8.
+Unicode non-character 0xffff is illegal for interchange at - line 9.
+Unicode non-character 0x10fffe is illegal for interchange at - line 12.
+Unicode non-character 0x10ffff is illegal for interchange at - line 13.
 ########
 use warnings 'utf8';
 my $d7ff  = pack("U", 0xD7FF);
@@ -96,10 +96,10 @@ my $max   = pack("U", 0x10FFFF);
 EXPECT
 UTF-16 surrogate 0xd800 at - line 3.
 UTF-16 surrogate 0xdfff at - line 4.
-Unicode character 0xfffe is illegal at - line 8.
-Unicode character 0xffff is illegal at - line 9.
-Unicode character 0x10fffe is illegal at - line 12.
-Unicode character 0x10ffff is illegal at - line 13.
+Unicode non-character 0xfffe is illegal for interchange at - line 8.
+Unicode non-character 0xffff is illegal for interchange at - line 9.
+Unicode non-character 0x10fffe is illegal for interchange at - line 12.
+Unicode non-character 0x10ffff is illegal for interchange at - line 13.
 ########
 use warnings 'utf8';
 my $d7ff  = "\x{D7FF}";
@@ -130,7 +130,7 @@ my $max   = "\x{10FFFF}";
 EXPECT
 UTF-16 surrogate 0xd800 at - line 3.
 UTF-16 surrogate 0xdfff at - line 4.
-Unicode character 0xfffe is illegal at - line 8.
-Unicode character 0xffff is illegal at - line 9.
-Unicode character 0x10fffe is illegal at - line 12.
-Unicode character 0x10ffff is illegal at - line 13.
+Unicode non-character 0xfffe is illegal for interchange at - line 8.
+Unicode non-character 0xffff is illegal for interchange at - line 9.
+Unicode non-character 0x10fffe is illegal for interchange at - line 12.
+Unicode non-character 0x10ffff is illegal for interchange at - line 13.
diff --git a/t/porting/diag.t b/t/porting/diag.t
index 573450d..a9db20c 100644
--- a/t/porting/diag.t
+++ b/t/porting/diag.t
@@ -351,7 +351,7 @@ U0 mode on a byte string
 Unbalanced string table refcount: (%d) for "%s"
 Undefined top format called
 Unexpected constant lvalue entersub entry via type/targ %d:%d
-Unicode character 0x%04
+Unicode non-character 0x%04
 Unknown PerlIO layer "scalar"
 Unknown Unicode option letter '%c'
 unrecognised control character '%c'
diff --git a/utf8.c b/utf8.c
index a68af53..c154fdb 100644
--- a/utf8.c
+++ b/utf8.c
@@ -127,7 +127,7 @@ Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags)
 		   !(flags & UNICODE_ALLOW_SUPER))
 		  )
 	      Perl_warner(aTHX_ packWARN(WARN_UTF8),
-			 "Unicode character 0x%04"UVxf" is illegal", uv);
+		      "Unicode non-character 0x%04"UVxf" is illegal for interchange", uv);
     }
     if (UNI_IS_INVARIANT(uv)) {
 	*d++ = (U8)UTF_TO_NATIVE(uv);