From: Robin Houston <robin@cpan.org>
Date: Tue, 17 Apr 2001 22:29:36 +0000 (+0100)
Subject: utf8 literal strings (and possibly a unicode/regex bug)
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=746698c5cdd2d4018ecb993f14f3e3d945860a1e;p=p5sagit%2Fp5-mst-13.2.git

utf8 literal strings (and possibly a unicode/regex bug)
Message-ID: <20010417222936.A6644@puffinry.freeserve.co.uk>

p4raw-id: //depot/perl@9730
---

diff --git a/ext/B/B.xs b/ext/B/B.xs
index 39b579f..35e3233 100644
--- a/ext/B/B.xs
+++ b/ext/B/B.xs
@@ -911,6 +911,7 @@ SvPV(sv)
     CODE:
 	ST(0) = sv_newmortal();
 	sv_setpvn(ST(0), SvPVX(sv), SvCUR(sv));
+	SvFLAGS(ST(0)) |= SvUTF8(sv);
 
 STRLEN
 SvLEN(sv)
diff --git a/ext/B/B/Deparse.pm b/ext/B/B/Deparse.pm
index fa58808..cdb6fa6 100644
--- a/ext/B/B/Deparse.pm
+++ b/ext/B/B/Deparse.pm
@@ -2473,8 +2473,9 @@ sub re_uninterp {
 }
 
 # character escapes, but not delimiters that might need to be escaped
-sub escape_str { # ASCII
+sub escape_str { # ASCII, UTF8
     my($str) = @_;
+    $str =~ s/(.)/ord($1)>255 ? sprintf("\\x{%x}", ord($1)) : $1/eg;
     $str =~ s/\a/\\a/g;
 #    $str =~ s/\cH/\\b/g; # \b means someting different in a regex 
     $str =~ s/\t/\\t/g;