RE: [RFC] Allow explicit 16 or 32 char in 'x /s'

["Pierre Muller" <pierre dot muller at ics-cnrs dot unistra dot fr>]

> -----Message d'origine-----
> De?: gdb-patches-owner@sourceware.org [mailto:gdb-patches-
> owner@sourceware.org] De la part de Eli Zaretskii
> Envoyé?: Friday, March 19, 2010 8:32 AM
> À?: tromey@redhat.com
> Cc?: pierre.muller@ics-cnrs.unistra.fr; gdb-patches@sourceware.org
> Objet?: Re: [RFC] Allow explicit 16 or 32 char in 'x /s'
> 
> > From: Tom Tromey <tromey@redhat.com>
> > Cc: <gdb-patches@sourceware.org>
> > Date: Thu, 18 Mar 2010 16:08:27 -0600
> >
> > I think the documentation should reflect that the user can't choose
> the
> > encoding used here.
> 
> I agree.  It should also say which encoding is used by GDB in this
> case.

  Not that I do not agree with you, but I would like to 
stress that how the string is displayed also depend on the current language,
so that, for C or any other language using c_printstr function,
/hs will use UTF-16LE or UTF-16BE according to current gdbarch endianess.
/ws will use UTF-32LE or UTF-32BE.

  But I don't know exactly for other languages and I would like to be sure
about
what you want me to add to the docs...
  Furthermore if you look into charset_for_string_type
function in c-lang.c source, you will see that there are two FIXME
just right at the position of these charset name settings.

  To answer Tom's concern about the change in classify_type function,
I modified my patch to change the elttype in do_examine to match exactly
what is expected by charset_for_string_type function.
Thus this new version has no modification in c-lang.c file.

  I also added a very basic check for string display using 'x /hs' and 'x
/ws'.

Pierre Muller



2010-03-22  Pierre Muller  <muller@ics.u-strasbg.fr>

	* printcmd.c (decode_format): Set char size to byte
	for strings unless explicit size is given.
	(print_formatted): Correct calculation of NEXT_ADDRESS
	for 16 or 32 bit strings.
	(do_examine): Do not force byte size for strings.
	Use 'char16_t' and 'char32_t' types to allow
	for correct recognition in classify_type.
	
2010-03-22  Pierre Muller  <muller@ics.u-strasbg.fr>

	* gdb.base/charset.c (Strin16, String32): New variables.
	* gdb.base/charset.exp (gdb_test): Test correct display
	of 16 or 32 bit strings.

Index: printcmd.c
===================================================================
RCS file: /cvs/src/src/gdb/printcmd.c,v
retrieving revision 1.173
diff -u -p -r1.173 printcmd.c
--- printcmd.c	5 Mar 2010 20:18:14 -0000	1.173
+++ printcmd.c	22 Mar 2010 22:25:34 -0000
@@ -260,6 +260,11 @@ decode_format (char **string_ptr, int of
 	/* Characters default to one byte.  */
 	val.size = osize ? 'b' : osize;
 	break;
+      case 's':
+	/* Display strings with byte size chars unless explicitly specified.
*/
+	val.size = 'b';
+	break;
+
       default:
 	/* The default is the size most recently specified.  */
 	val.size = osize;
@@ -295,7 +300,7 @@ print_formatted (struct value *val, int 
 	    next_address = (value_address (val)
 			    + val_print_string (elttype,
 						value_address (val), -1,
-						stream, options));
+						stream, options) * len);
 	  }
 	  return;
 
@@ -802,9 +807,11 @@ do_examine (struct format_data fmt, stru
   next_gdbarch = gdbarch;
   next_address = addr;
 
-  /* String or instruction format implies fetch single bytes
-     regardless of the specified size.  */
-  if (format == 's' || format == 'i')
+  /* Instruction format implies fetch single bytes
+     regardless of the specified size.
+     The case of strings is handled n decode_format, only explicit
+     size operator are not changed to 'b'.  */
+  if (format == 'i')
     size = 'b';
 
   if (size == 'a')
@@ -831,6 +838,36 @@ do_examine (struct format_data fmt, stru
   else if (size == 'g')
     val_type = builtin_type (next_gdbarch)->builtin_int64;
 
+  if (format == 's')
+    {
+      struct type *char_type;
+      if (size == 'h')
+	{
+	  char_type = lookup_typename (current_language, next_gdbarch,
+				       "char16_t", NULL, 1);
+	  if (!char_type)
+	    char_type = arch_type (next_gdbarch, TYPE_CODE_INT, 2,
"char16_t");
+	  check_typedef (char_type);
+	  if (TYPE_LENGTH (char_type) == 2)
+	    val_type = char_type;
+	}
+      else if (size == 'w')
+	{
+	  char_type = lookup_typename (current_language, next_gdbarch,
+				       "char32_t", NULL, 1);
+	  if (!char_type)
+	    char_type = arch_type (next_gdbarch, TYPE_CODE_INT, 4,
"char32_t");
+	  check_typedef (char_type);
+	  if (char_type && TYPE_LENGTH (char_type) == 4)
+	    val_type = char_type;
+	}
+      else
+        {
+	  size = 'b';
+	  val_type = builtin_type (next_gdbarch)->builtin_int8;
+        }
+    }
+
   maxelts = 8;
   if (size == 'w')
     maxelts = 4;
Index: testsuite/gdb.base/charset.c
===================================================================
RCS file: /cvs/src/src/gdb/testsuite/gdb.base/charset.c,v
retrieving revision 1.12
diff -u -p -r1.12 charset.c
--- testsuite/gdb.base/charset.c	1 Jan 2010 07:32:00 -0000	1.12
+++ testsuite/gdb.base/charset.c	22 Mar 2010 22:25:34 -0000
@@ -65,6 +65,9 @@ typedef unsigned int char32_t;
 char16_t uvar;
 char32_t Uvar;
 
+char16_t *String16;
+char32_t *String32;
+
 /* A typedef to a typedef should also work.  */
 typedef wchar_t my_wchar_t;
 my_wchar_t myvar;
Index: testsuite/gdb.base/charset.exp
===================================================================
RCS file: /cvs/src/src/gdb/testsuite/gdb.base/charset.exp,v
retrieving revision 1.21
diff -u -p -r1.21 charset.exp
--- testsuite/gdb.base/charset.exp	17 Feb 2010 22:05:58 -0000	1.21
+++ testsuite/gdb.base/charset.exp	22 Mar 2010 22:25:35 -0000
@@ -616,4 +616,21 @@ gdb_test "print 'a' == 'a' || 'b' == 'b'
   ".* = 1" \
   "EVAL_SKIP cleanup handling regression test"
 
+
+proc string_display { var_name set_prefix x_size x_type} {
+  gdb_test "set ${var_name} = ${set_prefix}\"Test String\\0with zeroes\""
"" "Assign ${var_name} with prefix ${set_prefix}"
+  gdb_test "x /2${x_size}s ${var_name}" ".* ${x_type}\"Test
String\"\[\r\n\]+.* ${x_type}\"with zeroes\"" "Display String ${var_name}
with x/${x_size}s"
+}
+
+string_display String16 u h u
+if {$wchar_size == 2} {
+  string_display String16 L h u
+}
+ 
+string_display String32 U w U
+if {$wchar_size == 4} {
+  string_display String32 L w U
+}
+
+
 gdb_exit