This is the mail archive of the gdb-patches@sourceware.org mailing list for the GDB project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [RFA] defs.h: Define GDB_DEFAULT_TARGET_[WIDE_]CHARSET for Cygwin and MingW builds


On Feb 28 17:27, Daniel Jacobowitz wrote:
> On Sun, Feb 28, 2010 at 08:21:59PM +0100, Corinna Vinschen wrote:
> > On Feb 28 13:47, Daniel Jacobowitz wrote:
> > > On Sun, Feb 28, 2010 at 04:03:18PM +0100, Corinna Vinschen wrote:
> > > > If the codeset is target-specific anyway, then the idea of the
> > > > GDB_DEFAULT_TARGET_WIDE_CHARSET and GDB_DEFAULT_TARGET_CHARSET variables
> > > > is either wrong, or it must be possible to define them somewhere
> > > > on a per-target base.  What about windows-tdep.h?
> > > 
> > > If it has to be per-target at all, it needs to go in gdbarch; it can't
> > > be a #define any more, because we support multiple compiled-in
> > > architectures.  This is going to be significantly more complicated,
> > > though; there needs to be an "auto (currently cp1252)" style setting.
> > 
> > There is already a setting for the target charsets.  We're just
> > talking about setting a sane default.
> 
> We're talking past each other.  Compare show_host_charset_name
> (which has an auto setting) to show_target_charset_name (which does
> not).
> 
> If the default becomes dependent on the target, we need to distinguish
> "user specified iso-8859-1" or "user didn't say anything, but now
> we're debugging i686-mingw32, and that usually uses cp1252".

Ok.  Would the below be sufficient for a start?


Corinna


	* charset.c (auto_target_charset_name): New variable.
	(target_charset_name): Set to "auto" by default.
	(show_target_charset_name): Take "auto" setting into account.
	(auto_target_wide_charset_name): New variable.
	(target_wide_charset_name): Set to "auto" by default.
	(show_target_wide_charset_name): Take "auto" setting into account.
	(set_be_le_names): Ditto.
	(validate): Ditto.
	(set_auto_target_wide_charset): New function to set
	auto_target_wide_charset_name.
	(set_auto_target_charset): New function to set auto_target_charset_name.
	(target_charset): Take "auto" setting into account.
	(target_wide_charset): Ditto.
	(_initialize_charset): Initialize auto_target_charset_name rather than
	target_charset_name with value of auto_host_charset_name.
	* charset.h (set_auto_target_wide_charset): Declare.
	(set_auto_target_charset): Declare.
	* windows-nat.c: Include charset.h.
	(_initialize_windows_nat): Initialize auto target charsets to sane
	values for native targets.


Index: charset.c
===================================================================
RCS file: /cvs/src/src/gdb/charset.c,v
retrieving revision 1.28
diff -u -p -r1.28 charset.c
--- charset.c	1 Jan 2010 07:31:30 -0000	1.28
+++ charset.c	1 Mar 2010 10:27:57 -0000
@@ -213,22 +213,37 @@ show_host_charset_name (struct ui_file *
     fprintf_filtered (file, _("The host character set is \"%s\".\n"), value);
 }
 
-static const char *target_charset_name = GDB_DEFAULT_TARGET_CHARSET;
+static const char *auto_target_charset_name = GDB_DEFAULT_TARGET_CHARSET;
+static const char *target_charset_name = "auto";
 static void
 show_target_charset_name (struct ui_file *file, int from_tty,
 			  struct cmd_list_element *c, const char *value)
 {
-  fprintf_filtered (file, _("The target character set is \"%s\".\n"),
-		    value);
+  if (!strcmp (value, "auto"))
+    fprintf_filtered (file,
+		      _("The target character set is \"auto; "
+		        "currently %s\".\n"),
+		      auto_target_charset_name);
+  else
+    fprintf_filtered (file, _("The target character set is \"%s\".\n"),
+		      value);
 }
 
-static const char *target_wide_charset_name = GDB_DEFAULT_TARGET_WIDE_CHARSET;
+static const char *auto_target_wide_charset_name
+				= GDB_DEFAULT_TARGET_WIDE_CHARSET;
+static const char *target_wide_charset_name = "auto";
 static void
 show_target_wide_charset_name (struct ui_file *file, int from_tty,
 			       struct cmd_list_element *c, const char *value)
 {
-  fprintf_filtered (file, _("The target wide character set is \"%s\".\n"),
-		    value);
+  if (!strcmp (value, "auto"))
+    fprintf_filtered (file,
+		      _("The target wide character set is \"auto; "
+		        "currently %s\".\n"),
+		      auto_target_wide_charset_name);
+  else
+    fprintf_filtered (file, _("The target wide character set is \"%s\".\n"),
+		      value);
 }
 
 static const char *default_charset_names[] =
@@ -252,14 +267,19 @@ static void
 set_be_le_names (void)
 {
   int i, len;
+  const char *target_wide;
 
   target_wide_charset_le_name = NULL;
   target_wide_charset_be_name = NULL;
 
-  len = strlen (target_wide_charset_name);
+  target_wide = target_wide_charset_name;
+  if (!strcmp (target_wide, "auto"))
+    target_wide = auto_target_wide_charset_name;
+
+  len = strlen (target_wide);
   for (i = 0; charset_enum[i]; ++i)
     {
-      if (strncmp (target_wide_charset_name, charset_enum[i], len))
+      if (strncmp (target_wide, charset_enum[i], len))
 	continue;
       if ((charset_enum[i][len] == 'B'
 	   || charset_enum[i][len] == 'L')
@@ -282,17 +302,21 @@ validate (void)
 {
   iconv_t desc;
   const char *host_cset = host_charset ();
+  const char *target_cset = target_charset ();
+  const char *target_wide_cset = target_wide_charset_name;
+  if (!strcmp (target_wide_cset, "auto"))
+    target_wide_cset = auto_target_wide_charset_name;
 
-  desc = iconv_open (target_wide_charset_name, host_cset);
+  desc = iconv_open (target_wide_cset, host_cset);
   if (desc == (iconv_t) -1)
     error ("Cannot convert between character sets `%s' and `%s'",
-	   target_wide_charset_name, host_cset);
+	   target_wide_cset, host_cset);
   iconv_close (desc);
 
-  desc = iconv_open (target_charset_name, host_cset);
+  desc = iconv_open (target_cset, host_cset);
   if (desc == (iconv_t) -1)
     error ("Cannot convert between character sets `%s' and `%s'",
-	   target_charset_name, host_cset);
+	   target_cset, host_cset);
   iconv_close (desc);
 
   set_be_le_names ();
@@ -342,6 +366,21 @@ show_charset (struct ui_file *file, int 
   show_target_wide_charset_name (file, from_tty, c, target_wide_charset_name);
 }
 
+/* These functions allow to set the auto target charsets.  This isn't for
+   the user, rather it's to be used to set the auto target charsets from
+   target-specific code. */
+void
+set_auto_target_wide_charset (char *charset)
+{
+  auto_target_wide_charset_name = charset;
+}
+
+void
+set_auto_target_charset (char *charset)
+{
+  auto_target_charset_name = charset;
+}
+
 
 /* Accessor functions.  */
 
@@ -356,6 +395,8 @@ host_charset (void)
 const char *
 target_charset (void)
 {
+  if (!strcmp (target_charset_name, "auto"))
+    return auto_target_charset_name;
   return target_charset_name;
 }
 
@@ -373,6 +414,8 @@ target_wide_charset (enum bfd_endian byt
 	return target_wide_charset_le_name;
     }
 
+  if (!strcmp (target_wide_charset_name, "auto"))
+    return auto_target_wide_charset_name;
   return target_wide_charset_name;
 }
 
@@ -874,7 +917,7 @@ _initialize_charset (void)
      which GNU libiconv doesn't like (infinite loop).  */
   if (!strcmp (auto_host_charset_name, "646") || !*auto_host_charset_name)
     auto_host_charset_name = "ASCII";
-  target_charset_name = auto_host_charset_name;
+  auto_target_charset_name = auto_host_charset_name;
 
   set_be_le_names ();
 #endif
Index: charset.h
===================================================================
RCS file: /cvs/src/src/gdb/charset.h,v
retrieving revision 1.10
diff -u -p -r1.10 charset.h
--- charset.h	1 Jan 2010 07:31:30 -0000	1.10
+++ charset.h	1 Mar 2010 10:27:57 -0000
@@ -36,6 +36,12 @@ const char *host_charset (void);
 const char *target_charset (void);
 const char *target_wide_charset (enum bfd_endian byte_order);
 
+/* These functions allow to set the auto target charsets.  This isn't for
+   the user, rather it's to be used to set the auto target charsets from
+   target-specific code. */
+void set_auto_target_wide_charset (char *charset);
+void set_auto_target_charset (char *charset);
+
 /* These values are used to specify the type of transliteration done
    by convert_between_encodings.  */
 enum transliterations
Index: windows-nat.c
===================================================================
RCS file: /cvs/src/src/gdb/windows-nat.c,v
retrieving revision 1.204
diff -u -p -r1.204 windows-nat.c
--- windows-nat.c	1 Mar 2010 09:09:24 -0000	1.204
+++ windows-nat.c	1 Mar 2010 10:27:57 -0000
@@ -65,6 +65,7 @@
 #include "windows-nat.h"
 #include "i386-nat.h"
 #include "complaints.h"
+#include "charset.h"
 
 #define AdjustTokenPrivileges		dyn_AdjustTokenPrivileges
 #define DebugActiveProcessStop		dyn_DebugActiveProcessStop
@@ -2296,12 +2297,20 @@ void
 _initialize_windows_nat (void)
 {
   struct cmd_list_element *c;
+#ifndef __CYGWIN__
+  static char codepage[32];
+#endif
 
   init_windows_ops ();
 
 #ifdef __CYGWIN__
   cygwin_internal (CW_SET_DOS_FILE_WARNING, 0);
+  set_auto_target_charset ("UTF-8");
+#else
+  snprintf (codepage, 32, "CP%u", GetACP ());
+  set_auto_target_charset (codepage);
 #endif
+  set_auto_target_wide_charset ("UTF-16");
 
   c = add_com ("dll-symbols", class_files, dll_symbol_command,
 	       _("Load dll library symbols from FILE."));


-- 
Corinna Vinschen
Cygwin Project Co-Leader
Red Hat


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]