/* Character set conversion support for GDB.
- Copyright (C) 2001, 2003, 2007, 2008, 2009 Free Software Foundation, Inc.
+ Copyright (C) 2001, 2003, 2007, 2008, 2009, 2010
+ Free Software Foundation, Inc.
This file is part of GDB.
#include "gdb_wait.h"
#include "charset-list.h"
#include "vec.h"
+#include "environ.h"
+#include "arch-utils.h"
#include <stddef.h>
#include "gdb_string.h"
#include <ctype.h>
+#ifdef USE_WIN32API
+#include <windows.h>
+#endif
\f
/* How GDB's character set support works
#undef iconv_t
#define iconv_t int
#undef iconv_open
+#define iconv_open phony_iconv_open
#undef iconv
+#define iconv phony_iconv
#undef iconv_close
+#define iconv_close phony_iconv_close
#undef ICONV_CONST
#define ICONV_CONST const
#endif
iconv_t
-iconv_open (const char *to, const char *from)
+phony_iconv_open (const char *to, const char *from)
{
/* We allow conversions from UTF-32BE, wchar_t, and the host charset.
We allow conversions to wchar_t and the host charset. */
}
int
-iconv_close (iconv_t arg)
+phony_iconv_close (iconv_t arg)
{
return 0;
}
size_t
-iconv (iconv_t utf_flag, const char **inbuf, size_t *inbytesleft,
- char **outbuf, size_t *outbytesleft)
+phony_iconv (iconv_t utf_flag, const char **inbuf, size_t *inbytesleft,
+ char **outbuf, size_t *outbytesleft)
{
if (utf_flag)
{
/* In all other cases we simply copy input bytes to the
output. */
size_t amt = *inbytesleft;
+
if (amt > *outbytesleft)
amt = *outbytesleft;
memcpy (*outbuf, *inbuf, amt);
fprintf_filtered (file, _("The host character set is \"%s\".\n"), value);
}
-static const char *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"),
+ gdbarch_auto_charset (get_current_arch ()));
+ 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 *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"),
+ gdbarch_auto_wide_charset (get_current_arch ()));
+ else
+ fprintf_filtered (file, _("The target wide character set is \"%s\".\n"),
+ value);
}
static const char *default_charset_names[] =
static const char *target_wide_charset_be_name;
static const char *target_wide_charset_le_name;
-/* A helper function for validate which sets the target wide big- and
- little-endian character set names, if possible. */
+/* The architecture for which the BE- and LE-names are valid. */
+static struct gdbarch *be_le_arch;
+
+/* A helper function which sets the target wide big- and little-endian
+ character set names, if possible. */
static void
-set_be_le_names (void)
+set_be_le_names (struct gdbarch *gdbarch)
{
int i, len;
+ const char *target_wide;
+
+ if (be_le_arch == gdbarch)
+ return;
+ be_le_arch = gdbarch;
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 = gdbarch_auto_wide_charset (gdbarch);
+
+ 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')
target-wide-charset', 'set charset' sfunc's. */
static void
-validate (void)
+validate (struct gdbarch *gdbarch)
{
iconv_t desc;
const char *host_cset = host_charset ();
+ const char *target_cset = target_charset (gdbarch);
+ const char *target_wide_cset = target_wide_charset_name;
+
+ if (!strcmp (target_wide_cset, "auto"))
+ target_wide_cset = gdbarch_auto_wide_charset (gdbarch);
- 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 ();
+ /* Clear the cache. */
+ be_le_arch = NULL;
}
/* This is the sfunc for the 'set charset' command. */
{
/* CAREFUL: set the target charset here as well. */
target_charset_name = host_charset_name;
- validate ();
+ validate (get_current_arch ());
}
/* 'set host-charset' command sfunc. We need a wrapper here because
set_host_charset_sfunc (char *charset, int from_tty,
struct cmd_list_element *c)
{
- validate ();
+ validate (get_current_arch ());
}
/* Wrapper for the 'set target-charset' command. */
set_target_charset_sfunc (char *charset, int from_tty,
struct cmd_list_element *c)
{
- validate ();
+ validate (get_current_arch ());
}
/* Wrapper for the 'set target-wide-charset' command. */
set_target_wide_charset_sfunc (char *charset, int from_tty,
struct cmd_list_element *c)
{
- validate ();
+ validate (get_current_arch ());
}
/* sfunc for the 'show charset' command. */
}
const char *
-target_charset (void)
+target_charset (struct gdbarch *gdbarch)
{
+ if (!strcmp (target_charset_name, "auto"))
+ return gdbarch_auto_charset (gdbarch);
return target_charset_name;
}
const char *
-target_wide_charset (enum bfd_endian byte_order)
+target_wide_charset (struct gdbarch *gdbarch)
{
+ enum bfd_endian byte_order = gdbarch_byte_order (gdbarch);
+
+ set_be_le_names (gdbarch);
if (byte_order == BFD_ENDIAN_BIG)
{
if (target_wide_charset_be_name)
return target_wide_charset_le_name;
}
+ if (!strcmp (target_wide_charset_name, "auto"))
+ return gdbarch_auto_wide_charset (gdbarch);
+
return target_wide_charset_name;
}
size_t orig_in = iter->bytes;
size_t out_avail = out_request * sizeof (gdb_wchar_t);
size_t num;
- gdb_wchar_t result;
-
size_t r = iconv (iter->desc,
(ICONV_CONST char **) &iter->input, &iter->bytes,
&outptr, &out_avail);
+
if (r == (size_t) -1)
{
switch (errno)
{
case EILSEQ:
- /* Invalid input sequence. Skip it, and let the caller
- know about it. */
+ /* Invalid input sequence. We still might have converted a
+ character; if so, return it. */
+ if (out_avail < out_request * sizeof (gdb_wchar_t))
+ break;
+
+ /* Otherwise skip the first invalid character, and let the
+ caller know about it. */
*out_result = wchar_iterate_invalid;
*ptr = iter->input;
*len = iter->width;
extern initialize_file_ftype _initialize_charset; /* -Wmissing-prototype */
-typedef char *char_ptr;
DEF_VEC_P (char_ptr);
static VEC (char_ptr) *charsets;
#else
+/* Return non-zero if LINE (output from iconv) should be ignored.
+ Older iconv programs (e.g. 2.2.2) include the human readable
+ introduction even when stdout is not a tty. Newer versions omit
+ the intro if stdout is not a tty. */
+
+static int
+ignore_line_p (const char *line)
+{
+ /* This table is used to filter the output. If this text appears
+ anywhere in the line, it is ignored (strstr is used). */
+ static const char * const ignore_lines[] =
+ {
+ "The following",
+ "not necessarily",
+ "the FROM and TO",
+ "listed with several",
+ NULL
+ };
+ int i;
+
+ for (i = 0; ignore_lines[i] != NULL; ++i)
+ {
+ if (strstr (line, ignore_lines[i]) != NULL)
+ return 1;
+ }
+
+ return 0;
+}
+
static void
find_charset_names (void)
{
char *args[3];
int err, status;
int fail = 1;
+ struct gdb_environ *iconv_env;
+
+ /* Older iconvs, e.g. 2.2.2, don't omit the intro text if stdout is not
+ a tty. We need to recognize it and ignore it. This text is subject
+ to translation, so force LANGUAGE=C. */
+ iconv_env = make_environ ();
+ init_environ (iconv_env);
+ set_in_environ (iconv_env, "LANGUAGE", "C");
+ set_in_environ (iconv_env, "LC_ALL", "C");
- child = pex_init (0, "iconv", NULL);
+ child = pex_init (PEX_USE_PIPES, "iconv", NULL);
args[0] = "iconv";
args[1] = "-l";
args[2] = NULL;
/* Note that we simply ignore errors here. */
- if (!pex_run (child, PEX_SEARCH | PEX_STDERR_TO_STDOUT, "iconv",
- args, NULL, NULL, &err))
+ if (!pex_run_in_environment (child, PEX_SEARCH | PEX_STDERR_TO_STDOUT,
+ "iconv", args, environ_vector (iconv_env),
+ NULL, NULL, &err))
{
FILE *in = pex_read_output (child, 0);
/* POSIX says that iconv -l uses an unspecified format. We
parse the glibc and libiconv formats; feel free to add others
as needed. */
+
while (!feof (in))
{
/* The size of buf is chosen arbitrarily. */
char buf[1024];
char *start, *r;
- int len, keep_going;
+ int len;
r = fgets (buf, sizeof (buf), in);
if (!r)
len = strlen (r);
if (len <= 3)
continue;
+ if (ignore_line_p (r))
+ continue;
+
/* Strip off the newline. */
--len;
/* Strip off one or two '/'s. glibc will print lines like
buf[len] = '\0';
/* libiconv will print multiple entries per line, separated
- by spaces. */
+ by spaces. Older iconvs will print multiple entries per line,
+ indented by two spaces, and separated by ", "
+ (i.e. the human readable form). */
start = buf;
while (1)
{
int keep_going;
char *p;
- /* Find the next space, or end-of-line. */
- for (p = start; *p && *p != ' '; ++p)
+ /* Skip leading blanks. */
+ for (p = start; *p && *p == ' '; ++p)
+ ;
+ start = p;
+ /* Find the next space, comma, or end-of-line. */
+ for ( ; *p && *p != ' ' && *p != ','; ++p)
;
/* Ignore an empty result. */
if (p == start)
}
pex_free (child);
+ free_environ (iconv_env);
if (fail)
{
#endif /* HAVE_ICONVLIST || HAVE_LIBICONVLIST */
#endif /* PHONY_ICONV */
+/* The "auto" target charset used by default_auto_charset. */
+static const char *auto_target_charset_name = GDB_DEFAULT_TARGET_CHARSET;
+
+const char *
+default_auto_charset (void)
+{
+ return auto_target_charset_name;
+}
+
+const char *
+default_auto_wide_charset (void)
+{
+ return GDB_DEFAULT_TARGET_WIDE_CHARSET;
+}
+
void
_initialize_charset (void)
{
- struct cmd_list_element *new_cmd;
-
- /* The first element is always "auto"; then we skip it for the
- commands where it is not allowed. */
+ /* The first element is always "auto". */
VEC_safe_push (char_ptr, charsets, xstrdup ("auto"));
find_charset_names ();
#ifndef PHONY_ICONV
#ifdef HAVE_LANGINFO_CODESET
- auto_host_charset_name = nl_langinfo (CODESET);
+ /* The result of nl_langinfo may be overwritten later. This may
+ leak a little memory, if the user later changes the host charset,
+ but that doesn't matter much. */
+ auto_host_charset_name = xstrdup (nl_langinfo (CODESET));
/* Solaris will return `646' here -- but the Solaris iconv then
- does not accept this. */
- if (!strcmp (auto_host_charset_name, "646"))
+ does not accept this. Darwin (and maybe FreeBSD) may return "" here,
+ 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;
-
- set_be_le_names ();
+ auto_target_charset_name = auto_host_charset_name;
+#elif defined (USE_WIN32API)
+ {
+ static char w32_host_default_charset[16]; /* "CP" + x<=5 digits + paranoia. */
+
+ snprintf (w32_host_default_charset, sizeof w32_host_default_charset,
+ "CP%d", GetACP());
+ auto_host_charset_name = w32_host_default_charset;
+ auto_target_charset_name = auto_host_charset_name;
+ }
#endif
#endif
add_setshow_enum_cmd ("charset", class_support,
- &charset_enum[1], &host_charset_name, _("\
+ charset_enum, &host_charset_name, _("\
Set the host and target character sets."), _("\
Show the host and target character sets."), _("\
The `host character set' is the one used by the system GDB is running on.\n\
&setlist, &showlist);
add_setshow_enum_cmd ("target-charset", class_support,
- &charset_enum[1], &target_charset_name, _("\
+ charset_enum, &target_charset_name, _("\
Set the target character set."), _("\
Show the target character set."), _("\
The `target character set' is the one used by the program being debugged.\n\
&setlist, &showlist);
add_setshow_enum_cmd ("target-wide-charset", class_support,
- &charset_enum[1], &target_wide_charset_name,
+ charset_enum, &target_wide_charset_name,
_("\
Set the target wide character set."), _("\
Show the target wide character set."), _("\
projects / deliverable / binutils-gdb.git / blobdiff