Hi all
I am back to playing with parrot for a while.
Discovered that the UTF8 encoding function was producing
garbage courtesy of two macros in unicode.h; I have fixed
these and added a test to string.t that does a transcode to
UTF8.
Patch below - but has already been committed, since nobody
ever seems to have cancelled my privileges :-)
--
Peter Gibbs
EmKel Systems
Index: include/parrot/unicode.h
===================================================================
RCS file: /cvs/public/parrot/include/parrot/unicode.h,v
retrieving revision 1.5
diff -u -r1.5 unicode.h
--- include/parrot/unicode.h 21 Jul 2003 18:00:42 -0000 1.5
+++ include/parrot/unicode.h 20 Aug 2003 09:41:18 -0000
@@ -68,8 +68,8 @@
#define UTF8_IS_CONTINUATION(c) ((c) >= 0x80u && (c) <= 0xBFu)
#define UTF8_IS_CONTINUED(c) ((c) & 0x80u)
-#define UTF8_START_MARK(len) (0xFEu << (7-len))
-#define UTF8_START_MASK(len) (0x1Fu >> (len-2))
+#define UTF8_START_MARK(len) (len == 1 ? 0 : 0x7Eu << (7-len))
+#define UTF8_START_MASK(len) (len == 1 ? 0x7Fu : 0x1Fu >> (len-2))
#define UTF8_CONTINUATION_MARK 0x80u
#define UTF8_ACCUMULATION_SHIFT 6
Index: t/op/string.t
===================================================================
RCS file: /cvs/public/parrot/t/op/string.t,v
retrieving revision 1.53
diff -u -r1.53 string.t
--- t/op/string.t 8 Aug 2003 08:44:15 -0000 1.53
+++ t/op/string.t 20 Aug 2003 09:41:19 -0000
@@ -1,6 +1,6 @@
#! perl -w
-use Parrot::Test tests => 116;
+use Parrot::Test tests => 117;
use Test::More;
output_is( <<'CODE', <<OUTPUT, "set_s_s|sc" );
@@ -1976,6 +1976,18 @@
ABCY
abc
Y
+OUTPUT
+
+output_is( <<'CODE', <<OUTPUT, "transcode to utf8");
+ set S1, "ASCII is the same as UTF8\n"
+ find_encoding I1, "utf8"
+ transcode S2, S1, I1
+ print S1
+ print S2
+ end
+CODE
+ASCII is the same as UTF8
+ASCII is the same as UTF8
OUTPUT
# Set all string registers to values given by &$_[0](reg num)
