From bcb28afc532c6defc36fd52db211f3a785a8a6ef Mon Sep 17 00:00:00 2001
From: Pierre Muller <muller@sourceware.org>
Date: Thu, 21 Apr 2011 14:26:38 +0000
Subject: [PATCH] 	* gdb_wchar.h (USE_INTERMEDIATE_ENCODING_FUNCTION):
 New macro. 	(INTERMEDIATE_ENCODING): Change value to intermediate_encoding
 	function call if __STDC_ISO_10646__ macro is defined. 
 (intermediate_encoding): New prototype. 	* charset.c
 (your_gdb_wchar_t_is_bogus): New extern test variable 	to generate compile
 time error for unsupported gdb_wchar_t size. 	(ENDIAN_SUFFIX): New macro. 
 (intermediate_encoding): New function.

---
 gdb/ChangeLog   | 11 +++++++++
 gdb/charset.c   | 66 +++++++++++++++++++++++++++++++++++++++++++++++++
 gdb/gdb_wchar.h |  9 +++----
 3 files changed, 81 insertions(+), 5 deletions(-)

diff --git a/gdb/ChangeLog b/gdb/ChangeLog
index e8c38605f8..4c81d3a200 100644
--- a/gdb/ChangeLog
+++ b/gdb/ChangeLog
@@ -1,3 +1,14 @@
+2011-04-21  Pierre Muller  <muller@ics.u-strasbg.fr>
+
+	* gdb_wchar.h (USE_INTERMEDIATE_ENCODING_FUNCTION): New macro.
+	(INTERMEDIATE_ENCODING): Change value to intermediate_encoding
+	function call if __STDC_ISO_10646__ macro is defined.
+	(intermediate_encoding): New prototype.
+	* charset.c (your_gdb_wchar_t_is_bogus): New extern test variable
+	to generate compile time error for unsupported gdb_wchar_t size.
+	(ENDIAN_SUFFIX): New macro.
+	(intermediate_encoding): New function.
+
 2011-04-20  Jan Kratochvil  <jan.kratochvil@redhat.com>
 
 	* ada-lang.c (struct add_partial_datum): Update the comment for
diff --git a/gdb/charset.c b/gdb/charset.c
index 41cbc435f3..a84085ac3a 100644
--- a/gdb/charset.c
+++ b/gdb/charset.c
@@ -922,6 +922,72 @@ default_auto_wide_charset (void)
   return GDB_DEFAULT_TARGET_WIDE_CHARSET;
 }
 
+
+#ifdef USE_INTERMEDIATE_ENCODING_FUNCTION
+/* Macro used for UTF or UCS endianness suffix.  */
+#if WORDS_BIGENDIAN
+#define ENDIAN_SUFFIX "BE"
+#else
+#define ENDIAN_SUFFIX "LE"
+#endif
+
+/* The code below serves to generate a compile time error if
+   gdb_wchar_t type is not of size 2 nor 4, despite the fact that
+   macro __STDC_ISO_10646__ is defined.
+   This is better than a gdb_assert call, because GDB cannot handle
+   strings correctly if this size is different.  */
+
+extern char your_gdb_wchar_t_is_bogus[(sizeof (gdb_wchar_t) == 2
+				       || sizeof (gdb_wchar_t) == 4)
+				      ? 1 : -1];
+
+/* intermediate_encoding returns the charset unsed internally by
+   GDB to convert between target and host encodings. As the test above
+   compiled, sizeof (gdb_wchar_t) is either 2 or 4 bytes.
+   UTF-16/32 is tested first, UCS-2/4 is tested as a second option,
+   otherwise an error is generated.  */
+
+const char *
+intermediate_encoding (void)
+{
+  iconv_t desc;
+  static const char *stored_result = NULL;
+  char *result;
+  int i;
+
+  if (stored_result)
+    return stored_result;
+  result = xstrprintf ("UTF-%d%s", (int) (sizeof (gdb_wchar_t) * 8),
+		       ENDIAN_SUFFIX);
+  /* Check that the name is supported by iconv_open.  */
+  desc = iconv_open (result, host_charset ());
+  if (desc != (iconv_t) -1)
+    {
+      iconv_close (desc);
+      stored_result = result;
+      return result;
+    }
+  /* Not valid, free the allocated memory.  */
+  xfree (result);
+  /* Second try, with UCS-2 type.  */
+  result = xstrprintf ("UCS-%d%s", (int) sizeof (gdb_wchar_t),
+		       ENDIAN_SUFFIX);
+  /* Check that the name is supported by iconv_open.  */
+  desc = iconv_open (result, host_charset ());
+  if (desc != (iconv_t) -1)
+    {
+      iconv_close (desc);
+      stored_result = result;
+      return result;
+    }
+  /* Not valid, free the allocated memory.  */
+  xfree (result);
+  /* No valid charset found, generate error here.  */
+  error (_("Unable to find a vaild charset for string conversions"));
+}
+
+#endif /* USE_INTERMEDIATE_ENCODING_FUNCTION */
+
 void
 _initialize_charset (void)
 {
diff --git a/gdb/gdb_wchar.h b/gdb/gdb_wchar.h
index 4c1b795d8a..daf64bad89 100644
--- a/gdb/gdb_wchar.h
+++ b/gdb/gdb_wchar.h
@@ -78,11 +78,10 @@ typedef wint_t gdb_wint_t;
    iconv_open.  We put the endianness into the encoding name to avoid
    hosts that emit a BOM when the unadorned name is used.  */
 #if defined (__STDC_ISO_10646__)
-#if WORDS_BIGENDIAN
-#define INTERMEDIATE_ENCODING "UCS-4BE"
-#else
-#define INTERMEDIATE_ENCODING "UCS-4LE"
-#endif
+#define USE_INTERMEDIATE_ENCODING_FUNCTION
+#define INTERMEDIATE_ENCODING intermediate_encoding ()
+const char *intermediate_encoding (void);
+
 #elif defined (_LIBICONV_VERSION) && _LIBICONV_VERSION >= 0x108
 #define INTERMEDIATE_ENCODING "wchar_t"
 #else
-- 
2.34.1