/* C language support routines for GDB, the GNU debugger.
Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2002, 2003,
- 2004, 2005, 2007, 2008, 2009 Free Software Foundation, Inc.
+ 2004, 2005, 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
This file is part of GDB.
character set name. */
static const char *
-charset_for_string_type (enum c_string_type str_type)
+charset_for_string_type (enum c_string_type str_type,
+ struct gdbarch *gdbarch)
{
switch (str_type & ~C_CHAR)
{
case C_STRING:
- return target_charset ();
+ return target_charset (gdbarch);
case C_WIDE_STRING:
- return target_wide_charset ();
+ return target_wide_charset (gdbarch);
case C_STRING_16:
- /* FIXME: UCS-2 is not always correct. */
- if (gdbarch_byte_order (current_gdbarch) == BFD_ENDIAN_BIG)
- return "UCS-2BE";
+ /* FIXME: UTF-16 is not always correct. */
+ if (gdbarch_byte_order (gdbarch) == BFD_ENDIAN_BIG)
+ return "UTF-16BE";
else
- return "UCS-2LE";
+ return "UTF-16LE";
case C_STRING_32:
- /* FIXME: UCS-4 is not always correct. */
- if (gdbarch_byte_order (current_gdbarch) == BFD_ENDIAN_BIG)
- return "UCS-4BE";
+ /* FIXME: UTF-32 is not always correct. */
+ if (gdbarch_byte_order (gdbarch) == BFD_ENDIAN_BIG)
+ return "UTF-32BE";
else
- return "UCS-4LE";
+ return "UTF-32LE";
}
internal_error (__FILE__, __LINE__, "unhandled c_string_type");
}
/* Classify ELTTYPE according to what kind of character it is. Return
the enum constant representing the character type. Also set
*ENCODING to the name of the character set to use when converting
- characters of this type to the host character set. */
+ characters of this type in target BYTE_ORDER to the host character set. */
static enum c_string_type
-classify_type (struct type *elttype, const char **encoding)
+classify_type (struct type *elttype, struct gdbarch *gdbarch,
+ const char **encoding)
{
- struct type *saved_type;
enum c_string_type result;
- /* We do one or two passes -- one on ELTTYPE, and then maybe a
- second one on a typedef target. */
- do
+ /* We loop because ELTTYPE may be a typedef, and we want to
+ successively peel each typedef until we reach a type we
+ understand. We don't use CHECK_TYPEDEF because that will strip
+ all typedefs at once -- but in C, wchar_t is itself a typedef, so
+ that would do the wrong thing. */
+ while (elttype)
{
char *name = TYPE_NAME (elttype);
goto done;
}
- saved_type = elttype;
- CHECK_TYPEDEF (elttype);
+ if (TYPE_CODE (elttype) != TYPE_CODE_TYPEDEF)
+ break;
+
+ /* Call for side effects. */
+ check_typedef (elttype);
+
+ if (TYPE_TARGET_TYPE (elttype))
+ elttype = TYPE_TARGET_TYPE (elttype);
+ else
+ {
+ /* Perhaps check_typedef did not update the target type. In
+ this case, force the lookup again and hope it works out.
+ It never will for C, but it might for C++. */
+ CHECK_TYPEDEF (elttype);
+ }
}
- while (elttype != saved_type);
/* Punt. */
result = C_CHAR;
done:
- *encoding = charset_for_string_type (result);
+ if (encoding)
+ *encoding = charset_for_string_type (result, gdbarch);
+
return result;
}
static void
print_wchar (gdb_wint_t w, const gdb_byte *orig, int orig_len,
- int width, struct obstack *output, int quoter,
- int *need_escapep)
+ int width, enum bfd_endian byte_order, struct obstack *output,
+ int quoter, int *need_escapep)
{
int need_escape = *need_escapep;
+
*need_escapep = 0;
if (gdb_iswprint (w) && (!need_escape || (!gdb_iswdigit (w)
&& w != LCST ('8')
&& w != LCST ('9'))))
{
+ gdb_wchar_t wchar = w;
+
if (w == gdb_btowc (quoter) || w == LCST ('\\'))
obstack_grow_wstr (output, LCST ("\\"));
- obstack_grow (output, &w, sizeof (gdb_wchar_t));
+ obstack_grow (output, &wchar, sizeof (gdb_wchar_t));
}
else
{
for (i = 0; i + width <= orig_len; i += width)
{
char octal[30];
- ULONGEST value = extract_unsigned_integer (&orig[i], width);
- sprintf (octal, "\\%lo", (long) value);
+ ULONGEST value;
+
+ value = extract_unsigned_integer (&orig[i], width, byte_order);
+ /* If the value fits in 3 octal digits, print it that
+ way. Otherwise, print it as a hex escape. */
+ if (value <= 0777)
+ sprintf (octal, "\\%.3o", (int) (value & 0777));
+ else
+ sprintf (octal, "\\x%lx", (long) value);
append_string_as_wide (octal, output);
}
/* If we somehow have extra bytes, print them now. */
while (i < orig_len)
{
char octal[5];
+
sprintf (octal, "\\%.3o", orig[i] & 0xff);
append_string_as_wide (octal, output);
++i;
string whose delimiter is QUOTER. Note that that format for printing
characters and strings is language specific. */
-static void
-c_emit_char (int c, struct type *type, struct ui_file *stream, int quoter)
+void
+c_emit_char (int c, struct type *type,
+ struct ui_file *stream, int quoter)
{
+ enum bfd_endian byte_order = gdbarch_byte_order (get_type_arch (type));
struct obstack wchar_buf, output;
struct cleanup *cleanups;
const char *encoding;
struct wchar_iterator *iter;
int need_escape = 0;
- classify_type (type, &encoding);
+ classify_type (type, get_type_arch (type), &encoding);
buf = alloca (TYPE_LENGTH (type));
pack_long (buf, type, c);
{
for (i = 0; i < num_chars; ++i)
print_wchar (chars[i], buf, buflen, TYPE_LENGTH (type),
- &wchar_buf, quoter, &need_escape);
+ byte_order, &wchar_buf, quoter, &need_escape);
}
}
/* This handles the NUM_CHARS == 0 case as well. */
if (print_escape)
- print_wchar (gdb_WEOF, buf, buflen, TYPE_LENGTH (type), &wchar_buf,
- quoter, &need_escape);
+ print_wchar (gdb_WEOF, buf, buflen, TYPE_LENGTH (type), byte_order,
+ &wchar_buf, quoter, &need_escape);
}
/* The output in the host encoding. */
obstack_init (&output);
make_cleanup_obstack_free (&output);
- convert_between_encodings ("wchar_t", host_charset (),
+ convert_between_encodings (INTERMEDIATE_ENCODING, host_charset (),
obstack_base (&wchar_buf),
obstack_object_size (&wchar_buf),
1, &output, translit_char);
c_printchar (int c, struct type *type, struct ui_file *stream)
{
enum c_string_type str_type;
- const char *encoding;
- str_type = classify_type (type, &encoding);
+ str_type = classify_type (type, get_type_arch (type), NULL);
switch (str_type)
{
case C_CHAR:
void
c_printstr (struct ui_file *stream, struct type *type, const gdb_byte *string,
- unsigned int length, int force_ellipses,
+ unsigned int length, const char *user_encoding, int force_ellipses,
const struct value_print_options *options)
{
+ enum bfd_endian byte_order = gdbarch_byte_order (get_type_arch (type));
unsigned int i;
unsigned int things_printed = 0;
int in_quotes = 0;
struct obstack wchar_buf, output;
struct cleanup *cleanup;
enum c_string_type str_type;
+ const char *type_encoding;
const char *encoding;
struct wchar_iterator *iter;
int finished = 0;
int need_escape = 0;
+ if (length == -1)
+ {
+ unsigned long current_char = 1;
+
+ for (i = 0; current_char; ++i)
+ {
+ QUIT;
+ current_char = extract_unsigned_integer (string + i * width,
+ width, byte_order);
+ }
+ length = i;
+ }
+
/* If the string was not truncated due to `set print elements', and
the last byte of it is a null, we don't print that, in traditional C
style. */
if (!force_ellipses
&& length > 0
- && (extract_unsigned_integer (string + (length - 1) * width, width) == 0))
+ && (extract_unsigned_integer (string + (length - 1) * width,
+ width, byte_order) == 0))
length--;
- str_type = classify_type (type, &encoding) & ~C_CHAR;
+ str_type = (classify_type (type, get_type_arch (type), &type_encoding)
+ & ~C_CHAR);
switch (str_type)
{
case C_STRING:
break;
}
+ encoding = (user_encoding && *user_encoding) ? user_encoding : type_encoding;
+
if (length == 0)
{
fputs_filtered ("\"\"", stream);
return;
}
- if (length == -1)
- {
- unsigned long current_char = 1;
- for (i = 0; current_char; ++i)
- {
- QUIT;
- current_char = extract_unsigned_integer (string + i * width, width);
- }
- length = i;
- }
-
/* Arrange to iterate over the characters, in wchar_t form. */
iter = make_wchar_iterator (string, length * width, encoding, width);
cleanup = make_cleanup_wchar_iterator (iter);
single character in isolation. This makes the code simpler
and probably does the sensible thing in the majority of
cases. */
- while (num_chars == 1)
+ while (num_chars == 1 && things_printed < options->print_max)
{
/* Count the number of repetitions. */
unsigned int reps = 0;
obstack_grow_wstr (&wchar_buf, LCST ("'"));
need_escape = 0;
print_wchar (current_char, orig_buf, orig_len, width,
- &wchar_buf, '\'', &need_escape);
+ byte_order, &wchar_buf, '\'', &need_escape);
obstack_grow_wstr (&wchar_buf, LCST ("'"));
{
/* Painful gyrations. */
int j;
char *s = xstrprintf (_(" <repeats %u times>"), reps);
+
for (j = 0; s[j]; ++j)
{
gdb_wchar_t w = gdb_btowc (s[j]);
while (reps-- > 0)
{
print_wchar (current_char, orig_buf, orig_len, width,
- &wchar_buf, '"', &need_escape);
+ byte_order, &wchar_buf, '"', &need_escape);
++things_printed;
}
}
in_quotes = 1;
}
need_escape = 0;
- print_wchar (gdb_WEOF, buf, buflen, width, &wchar_buf,
+ print_wchar (gdb_WEOF, buf, buflen, width, byte_order, &wchar_buf,
'"', &need_escape);
break;
in_quotes = 0;
}
obstack_grow_wstr (&wchar_buf, LCST (" <incomplete sequence "));
- print_wchar (gdb_WEOF, buf, buflen, width, &wchar_buf,
+ print_wchar (gdb_WEOF, buf, buflen, width, byte_order, &wchar_buf,
0, &need_escape);
obstack_grow_wstr (&wchar_buf, LCST (">"));
finished = 1;
obstack_init (&output);
make_cleanup_obstack_free (&output);
- convert_between_encodings ("wchar_t", host_charset (),
+ convert_between_encodings (INTERMEDIATE_ENCODING, host_charset (),
obstack_base (&wchar_buf),
obstack_object_size (&wchar_buf),
1, &output, translit_char);
}
/* Obtain a C string from the inferior storing it in a newly allocated
- buffer in BUFFER, which should be freed by the caller. The string is
- read until a null character is found. If VALUE is an array with known
- length, the function will not read past the end of the array. LENGTH
- will contain the size of the string in bytes (not counting the null
- character).
-
- Assumes strings are terminated by a null character. The size of a character
- is determined by the length of the target type of the pointer or array.
- This means that a null byte present in a multi-byte character will not
- terminate the string unless the whole character is null.
-
- CHARSET is always set to the target charset. */
+ buffer in BUFFER, which should be freed by the caller. If the
+ in- and out-parameter *LENGTH is specified at -1, the string is read
+ until a null character of the appropriate width is found, otherwise
+ the string is read to the length of characters specified.
+ The size of a character is determined by the length of the target
+ type of the pointer or array. If VALUE is an array with a known
+ length, the function will not read past the end of the array.
+ On completion, *LENGTH will be set to the size of the string read in
+ characters. (If a length of -1 is specified, the length returned
+ will not include the null character). CHARSET is always set to the
+ target charset. */
void
c_get_string (struct value *value, gdb_byte **buffer, int *length,
- const char **charset)
+ struct type **char_type, const char **charset)
{
int err, width;
unsigned int fetchlimit;
struct type *type = check_typedef (value_type (value));
struct type *element_type = TYPE_TARGET_TYPE (type);
+ int req_length = *length;
+ enum bfd_endian byte_order = gdbarch_byte_order (get_type_arch (type));
+ enum c_string_type kind;
if (element_type == NULL)
goto error;
/* We work only with arrays and pointers. */
goto error;
- element_type = check_typedef (element_type);
- if (TYPE_CODE (element_type) != TYPE_CODE_INT
- && TYPE_CODE (element_type) != TYPE_CODE_CHAR)
- /* If the elements are not integers or characters, we don't consider it
- a string. */
+ if (! c_textual_element_type (element_type, 0))
goto error;
-
+ kind = classify_type (element_type,
+ get_type_arch (element_type),
+ charset);
width = TYPE_LENGTH (element_type);
- /* If the string lives in GDB's memory intead of the inferior's, then we
+ /* If the string lives in GDB's memory instead of the inferior's, then we
just need to copy it to BUFFER. Also, since such strings are arrays
with known size, FETCHLIMIT will hold the size of the array. */
if ((VALUE_LVAL (value) == not_lval
int i;
const gdb_byte *contents = value_contents (value);
- /* Look for a null character. */
- for (i = 0; i < fetchlimit; i++)
- if (extract_unsigned_integer (contents + i * width, width) == 0)
- break;
-
- /* I is now either the number of non-null characters, or FETCHLIMIT. */
+ /* If a length is specified, use that. */
+ if (*length >= 0)
+ i = *length;
+ else
+ /* Otherwise, look for a null character. */
+ for (i = 0; i < fetchlimit; i++)
+ if (extract_unsigned_integer (contents + i * width, width,
+ byte_order) == 0)
+ break;
+
+ /* I is now either a user-defined length, the number of non-null
+ characters, or FETCHLIMIT. */
*length = i * width;
*buffer = xmalloc (*length);
memcpy (*buffer, contents, *length);
}
else
{
- err = read_string (value_as_address (value), -1, width, fetchlimit,
- buffer, length);
+ err = read_string (value_as_address (value), *length, width, fetchlimit,
+ byte_order, buffer, length);
if (err)
{
- xfree (buffer);
+ xfree (*buffer);
error (_("Error reading string from inferior: %s"),
safe_strerror (err));
}
}
- /* If the last character is null, subtract it from LENGTH. */
- if (*length > 0
- && extract_unsigned_integer (*buffer + *length - width, width) == 0)
- *length -= width;
-
- *charset = target_charset ();
+ /* If the LENGTH is specified at -1, we want to return the string
+ length up to the terminating null character. If an actual length
+ was specified, we want to return the length of exactly what was
+ read. */
+ if (req_length == -1)
+ /* If the last character is null, subtract it from LENGTH. */
+ if (*length > 0
+ && extract_unsigned_integer (*buffer + *length - width, width,
+ byte_order) == 0)
+ *length -= width;
+
+ /* The read_string function will return the number of bytes read.
+ If length returned from read_string was > 0, return the number of
+ characters read by dividing the number of bytes by width. */
+ if (*length != 0)
+ *length = *length / width;
+
+ *char_type = element_type;
return;
result >>= 8;
}
- convert_between_encodings ("UCS-4BE", dest_charset, data, 4, 4, output,
+ convert_between_encodings ("UTF-32BE", dest_charset, data, 4, 4, output,
translit_none);
return p;
static char *
convert_octal (struct type *type, char *p, char *limit, struct obstack *output)
{
+ int i;
unsigned long value = 0;
- while (p < limit && isdigit (*p) && *p != '8' && *p != '9')
+ for (i = 0;
+ i < 3 && p < limit && isdigit (*p) && *p != '8' && *p != '9';
+ ++i)
{
value = 8 * value + host_hex_value (*p);
++p;
case 'U':
{
int length = *p == 'u' ? 4 : 8;
+
ADVANCE;
if (!isxdigit (*p))
error (_("\\u used with no following hex digits"));
while (data < limit)
{
char *p = data;
+
/* Look for next escape, or the end of the input. */
while (p < limit && *p != '\\')
++p;
switch (dest_type & ~C_CHAR)
{
case C_STRING:
- type = language_string_char_type (current_language,
- current_gdbarch);
+ type = language_string_char_type (exp->language_defn,
+ exp->gdbarch);
break;
case C_WIDE_STRING:
- type = lookup_typename ("wchar_t", NULL, 0);
+ type = lookup_typename (exp->language_defn, exp->gdbarch,
+ "wchar_t", NULL, 0);
break;
case C_STRING_16:
- type = lookup_typename ("char16_t", NULL, 0);
+ type = lookup_typename (exp->language_defn, exp->gdbarch,
+ "char16_t", NULL, 0);
break;
case C_STRING_32:
- type = lookup_typename ("char32_t", NULL, 0);
+ type = lookup_typename (exp->language_defn, exp->gdbarch,
+ "char32_t", NULL, 0);
break;
default:
internal_error (__FILE__, __LINE__, "unhandled c_string_type");
}
- dest_charset = charset_for_string_type (dest_type);
+
+ /* Ensure TYPE_LENGTH is valid for TYPE. */
+ check_typedef (type);
+
+ dest_charset = charset_for_string_type (dest_type, exp->gdbarch);
++*pos;
while (*pos < limit)
*pos += 2;
if (noside == EVAL_SKIP)
- return NULL;
+ {
+ /* Return a dummy value of the appropriate type. */
+ if ((dest_type & C_CHAR) != 0)
+ result = allocate_value (type);
+ else
+ result = value_cstring ("", 0, type);
+ do_cleanups (cleanup);
+ return result;
+ }
if ((dest_type & C_CHAR) != 0)
{
else
{
int i;
+
/* Write the terminating character. */
for (i = 0; i < TYPE_LENGTH (type); ++i)
obstack_1grow (&output, 0);
- result = value_typed_string (obstack_base (&output),
- obstack_object_size (&output),
- type);
+ result = value_cstring (obstack_base (&output),
+ obstack_object_size (&output),
+ type);
}
do_cleanups (cleanup);
return result;
struct language_arch_info *lai)
{
const struct builtin_type *builtin = builtin_type (gdbarch);
+
lai->string_char_type = builtin->builtin_char;
lai->primitive_type_vector
= GDBARCH_OBSTACK_CALLOC (gdbarch, nr_c_primitive_types + 1,
lai->bool_type_default = builtin->builtin_int;
}
-static const struct exp_descriptor exp_descriptor_c =
+const struct exp_descriptor exp_descriptor_c =
{
print_subexp_standard,
operator_length_standard,
+ operator_check_standard,
op_name_standard,
dump_subexp_body_standard,
evaluate_subexp_c
struct language_arch_info *lai)
{
const struct builtin_type *builtin = builtin_type (gdbarch);
+
lai->string_char_type = builtin->builtin_char;
lai->primitive_type_vector
= GDBARCH_OBSTACK_CALLOC (gdbarch, nr_cplus_primitive_types + 1,