* charset.c (iconv_open): New define.

	(iconv): Likewise.
	(iconv_close): Likewise.
	(phony_iconv_open): Add "phony_" prefix.
	(phony_iconv_close): Likewise.
	(phony_iconv): Likewise.
	* gdb_wchar.h: Check _LIBICONV_VERSION, __STDC_ISO_10646__.
	Change how INTERMEDIATE_ENCODING is defined.

1 files changed, 47 insertions, 11 deletions

diff --git a/gdb/gdb_wchar.h b/gdb/gdb_wchar.h
index fca3fe4..80c595f 100644
--- a/gdb/gdb_wchar.h
+++ b/gdb/gdb_wchar.h
@@ -23,20 +23,24 @@
    
    Capable systems have the full suite: wchar_t support and iconv
    (perhaps via GNU libiconv).  On these machines, full functionality
-   is available.
+   is available.  Note that full functionality is dependent on us
+   being able to convert from an arbitrary encoding to wchar_t.  In
+   practice this means we look for __STDC_ISO_10646__ (where we know
+   the name of the wchar_t encoding) or GNU libiconv, where we can use
+   "wchar_t".
    
    DJGPP is known to have libiconv but not wchar_t support.  On
    systems like this, we use the narrow character functions.  The full
    functionality is available to the user, but many characters (those
    outside the narrow range) will be displayed as escapes.
    
-   Finally, some systems do not have iconv.  Here we provide a phony
-   iconv which only handles a single character set, and we provide
-   wrappers for the wchar_t functionality we use.  */
+   Finally, some systems do not have iconv, or are really broken
+   (e.g., Solaris, which almost has all of this working, but where
+   just enough is broken to make it too hard to use).  Here we provide
+   a phony iconv which only handles a single character set, and we
+   provide wrappers for the wchar_t functionality we use.  */
 
 
-#define INTERMEDIATE_ENCODING "wchar_t"
-
 #if defined (HAVE_ICONV)
 #include <iconv.h>
 #else
@@ -45,9 +49,15 @@
 #define PHONY_ICONV
 #endif
 
-/* We use "btowc" as a sentinel to detect functioning wchar_t
-   support.  */
-#if defined (HAVE_ICONV) && defined (HAVE_WCHAR_H) && defined (HAVE_BTOWC)
+/* We use "btowc" as a sentinel to detect functioning wchar_t support.
+   We check for either __STDC_ISO_10646__ or a new-enough libiconv in
+   order to ensure we can convert to and from wchar_t.  We choose
+   libiconv version 0x10D because it was reported that earlier
+   versions do not always accept "wchar_t" as an encoding
+   argument.  */
+#if defined (HAVE_ICONV) && defined (HAVE_WCHAR_H) && defined (HAVE_BTOWC) \
+  && (defined (__STDC_ISO_10646__) \
+      || (defined (_LIBICONV_VERSION) && _LIBICONV_VERSION >= 0x10D))
 
 #include <wchar.h>
 #include <wctype.h>
@@ -63,7 +73,32 @@ typedef wint_t gdb_wint_t;
 
 #define LCST(X) L ## X
 
+/* If __STDC_ISO_10646__ is defined, then the host wchar_t is UCS-4.
+   We exploit this fact in the hope that there are hosts that define
+   this but which do not support "wchar_t" as an encoding argument to
+   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
+#elif defined (_LIBICONV_VERSION) && _LIBICONV_VERSION >= 0x10D
+#define INTERMEDIATE_ENCODING "wchar_t"
+#else
+/* This shouldn't happen, because the earlier #if should have filtered
+   out this case.  */
+#error "Neither __STDC_ISO_10646__ nor _LIBICONV_VERSION defined"
+#endif
+
+#else
+
+/* If we got here and have wchar_t support, we might be on a system
+   with some problem.  So, we just disable everything.  */
+#if defined (HAVE_WCHAR_H) && defined (HAVE_BTOWC)
+#define PHONY_ICONV
+#endif
 
 typedef char gdb_wchar_t;
 typedef int gdb_wint_t;
@@ -80,8 +115,9 @@ typedef int gdb_wint_t;
    narrow encoding as our intermediate encoding.  However, if we are
    also providing a phony iconv, we might as well just stick with
    "wchar_t".  */
-#ifndef PHONY_ICONV
-#undef INTERMEDIATE_ENCODING
+#ifdef PHONY_ICONV
+#define INTERMEDIATE_ENCODING "wchar_t"
+#else
 #define INTERMEDIATE_ENCODING host_charset ()
 #endif