/* Character set conversion support for GDB.
- Copyright (C) 2001, 2003, 2007, 2008, 2009, 2010, 2011
- Free Software Foundation, Inc.
+ Copyright (C) 2001-2015 Free Software Foundation, Inc.
This file is part of GDB.
#include "defs.h"
#include "charset.h"
#include "gdbcmd.h"
-#include "gdb_assert.h"
#include "gdb_obstack.h"
#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 "gdb_vecs.h"
#include <ctype.h>
#ifdef USE_WIN32API
#undef ICONV_CONST
#define ICONV_CONST const
-/* Some systems don't have EILSEQ, so we define it here, but not as
- EINVAL, because callers of `iconv' want to distinguish EINVAL and
- EILSEQ. This is what iconv.h from libiconv does as well. Note
- that wchar.h may also define EILSEQ, so this needs to be after we
- include wchar.h, which happens in defs.h through gdb_wchar.h. */
-#ifndef EILSEQ
-#define EILSEQ ENOENT
-#endif
-
-iconv_t
+static iconv_t
phony_iconv_open (const char *to, const char *from)
{
/* We allow conversions from UTF-32BE, wchar_t, and the host charset.
return !strcmp (from, "UTF-32BE");
}
-int
+static int
phony_iconv_close (iconv_t arg)
{
return 0;
}
-size_t
+static size_t
phony_iconv (iconv_t utf_flag, const char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft)
{
return 0;
}
-#endif
+#else /* PHONY_ICONV */
+
+/* On systems that don't have EILSEQ, GNU iconv's iconv.h defines it
+ to ENOENT, while gnulib defines it to a different value. Always
+ map ENOENT to gnulib's EILSEQ, leaving callers agnostic. */
+
+static size_t
+gdb_iconv (iconv_t utf_flag, ICONV_CONST char **inbuf, size_t *inbytesleft,
+ char **outbuf, size_t *outbytesleft)
+{
+ size_t ret;
+ ret = iconv (utf_flag, inbuf, inbytesleft, outbuf, outbytesleft);
+ if (errno == ENOENT)
+ errno = EILSEQ;
+ return ret;
+}
+
+#undef iconv
+#define iconv gdb_iconv
+
+#endif /* PHONY_ICONV */
\f
/* The global lists of character sets and translations. */
desc = iconv_open (target_wide_cset, host_cset);
if (desc == (iconv_t) -1)
- error ("Cannot convert between character sets `%s' and `%s'",
+ error (_("Cannot convert between character sets `%s' and `%s'"),
target_wide_cset, host_cset);
iconv_close (desc);
desc = iconv_open (target_cset, host_cset);
if (desc == (iconv_t) -1)
- error ("Cannot convert between character sets `%s' and `%s'",
+ error (_("Cannot convert between character sets `%s' and `%s'"),
target_cset, host_cset);
iconv_close (desc);
iconv_t desc;
struct cleanup *cleanups;
size_t inleft;
- char *inp;
+ ICONV_CONST char *inp;
unsigned int space_request;
/* Often, the host and target charsets will be the same. */
desc = iconv_open (to, from);
if (desc == (iconv_t) -1)
- perror_with_name ("Converting character sets");
+ perror_with_name (_("Converting character sets"));
cleanups = make_cleanup (cleanup_iconv, &desc);
inleft = num_bytes;
- inp = (char *) bytes;
+ inp = (ICONV_CONST char *) bytes;
space_request = num_bytes;
old_size = obstack_object_size (output);
obstack_blank (output, space_request);
- outp = obstack_base (output) + old_size;
+ outp = (char *) obstack_base (output) + old_size;
outleft = space_request;
- r = iconv (desc, (ICONV_CONST char **) &inp, &inleft, &outp, &outleft);
+ r = iconv (desc, &inp, &inleft, &outp, &outleft);
/* Now make sure that the object on the obstack only includes
bytes we have converted. */
- obstack_blank (output, - (int) outleft);
+ obstack_blank_fast (output, -outleft);
if (r == (size_t) -1)
{
{
char octal[5];
- sprintf (octal, "\\%.3o", *inp & 0xff);
+ xsnprintf (octal, sizeof (octal), "\\%.3o", *inp & 0xff);
obstack_grow_str (output, octal);
++inp;
break;
default:
- perror_with_name ("Internal error while "
- "converting character sets");
+ perror_with_name (_("Internal error while "
+ "converting character sets"));
}
}
}
iconv_t desc;
/* The input string. This is updated as convert characters. */
- char *input;
+ const gdb_byte *input;
/* The number of bytes remaining in the input. */
size_t bytes;
desc = iconv_open (INTERMEDIATE_ENCODING, charset);
if (desc == (iconv_t) -1)
- perror_with_name ("Converting character sets");
+ perror_with_name (_("Converting character sets"));
result = XNEW (struct wchar_iterator);
result->desc = desc;
- result->input = (char *) input;
+ result->input = input;
result->bytes = bytes;
result->width = width;
out_request = 1;
while (iter->bytes > 0)
{
+ ICONV_CONST char *inptr = (ICONV_CONST char *) iter->input;
char *outptr = (char *) &iter->out[0];
- char *orig_inptr = iter->input;
+ const gdb_byte *orig_inptr = iter->input;
size_t orig_in = iter->bytes;
size_t out_avail = out_request * sizeof (gdb_wchar_t);
size_t num;
- size_t r = iconv (iter->desc,
- (ICONV_CONST char **) &iter->input,
- &iter->bytes, &outptr, &out_avail);
+ size_t r = iconv (iter->desc, &inptr, &iter->bytes, &outptr, &out_avail);
+
+ iter->input = (gdb_byte *) inptr;
if (r == (size_t) -1)
{
return 0;
default:
- perror_with_name ("Internal error while "
- "converting character sets");
+ perror_with_name (_("Internal error while "
+ "converting character sets"));
}
}
extern initialize_file_ftype _initialize_charset; /* -Wmissing-prototype */
-DEF_VEC_P (char_ptr);
-
static VEC (char_ptr) *charsets;
#ifdef PHONY_ICONV
char *args[3];
int err, status;
int fail = 1;
+ int flags;
struct gdb_environ *iconv_env;
+ char *iconv_program;
/* 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
child = pex_init (PEX_USE_PIPES, "iconv", NULL);
- args[0] = "iconv";
+#ifdef ICONV_BIN
+ {
+ char *iconv_dir = relocate_gdb_directory (ICONV_BIN,
+ ICONV_BIN_RELOCATABLE);
+ iconv_program = concat (iconv_dir, SLASH_STRING, "iconv", NULL);
+ xfree (iconv_dir);
+ }
+#else
+ iconv_program = xstrdup ("iconv");
+#endif
+ args[0] = iconv_program;
args[1] = "-l";
args[2] = NULL;
+ flags = PEX_STDERR_TO_STDOUT;
+#ifndef ICONV_BIN
+ flags |= PEX_SEARCH;
+#endif
/* Note that we simply ignore errors here. */
- if (!pex_run_in_environment (child, PEX_SEARCH | PEX_STDERR_TO_STDOUT,
- "iconv", args, environ_vector (iconv_env),
+ if (!pex_run_in_environment (child, flags,
+ args[0], args, environ_vector (iconv_env),
NULL, NULL, &err))
{
FILE *in = pex_read_output (child, 0);
parse the glibc and libiconv formats; feel free to add others
as needed. */
- while (!feof (in))
+ while (in != NULL && !feof (in))
{
/* The size of buf is chosen arbitrarily. */
char buf[1024];
}
+ xfree (iconv_program);
pex_free (child);
free_environ (iconv_env);
if (fail)
{
/* Some error occurred, so drop the vector. */
- int ix;
- char *elt;
- for (ix = 0; VEC_iterate (char_ptr, charsets, ix, elt); ++ix)
- xfree (elt);
- VEC_truncate (char_ptr, charsets, 0);
+ free_char_ptr_vec (charsets);
+ charsets = NULL;
}
else
VEC_safe_push (char_ptr, charsets, NULL);
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 used 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;
+
+ 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)
{
Show the target character set."), _("\
The `target character set' is the one used by the program being debugged.\n\
GDB translates characters and strings between the host and target\n\
-character sets as needed.\n
+character sets as needed.\n\
To see a list of the character sets GDB supports, type `set target-charset'<TAB>"),
set_target_charset_sfunc,
show_target_charset_name,