gdb:

2009-03-19  Tom Tromey  <tromey@redhat.com>
	    Julian Brown  <julian@codesourcery.com>

	PR i18n/7220, PR i18n/7821, PR exp/8815, PR exp/9103,
	PR i18n/9401, PR exp/9613:
	* NEWS: Update
	* value.h (value_typed_string): Declare.
	(val_print_string): Update.
	* valprint.h (print_char_chars): Update.
	* valprint.c (print_char_chars): Add type argument.  Update.
	(val_print_string): Likewise.
	* valops.c (value_typed_string): New function.
	* utils.c (host_char_to_target): New function.
	(parse_escape): Use host_char_to_target, host_hex_value.  Update.
	Remove '^' case.
	(no_control_char_error): Remove.
	* typeprint.c (print_type_scalar): Update.
	* scm-valprint.c (scm_scmval_print): Update.
	* scm-lang.h (scm_printchar, scm_printstr): Update.
	* scm-lang.c (scm_printchar): Add type argument.
	(scm_printstr): Likewise.
	* printcmd.c (print_formatted): Update.
	(print_scalar_formatted): Update.
	(printf_command) <wide_string_arg, wide_char_arg>: New constants.
	Handle '%lc' and '%ls'.
	* parser-defs.h (struct typed_stoken): New type.
	(struct stoken_vector): Likewise.
	(write_exp_string_vector): Declare.
	* parse.c (write_exp_string_vector): New function.
	* p-valprint.c (pascal_val_print): Update.
	* p-lang.h (is_pascal_string_type, pascal_printchar,
	pascal_printstr): Update.
	* p-lang.c (is_pascal_string_type): Remove 'char_size' argument.
	Add 'char_type' argument.
	(pascal_emit_char): Add type argument.
	(pascal_printchar): Likewise.
	(pascal_printstr): Likewise.
	* objc-lang.c (objc_emit_char): Add type argument.
	(objc_printchar): Likewise.
	(objc_printstr): Likewise.
	* macroexp.c (get_character_constant): Handle unicode characters.
	Use c_parse_escape.
	(get_string_literal): Handle unicode strings.  Use
	c_parse_escape.
	* m2-valprint.c (print_unpacked_pointer): Update.
	(m2_print_array_contents): Update.
	(m2_val_print): Update.
	* m2-lang.c (m2_emit_char): Add type argument.
	(m2_printchar): Likewise.
	(m2_printstr): Likewise.
	* language.h (struct language_defn) <la_printchar>: Add type
	argument.
	<la_printstr, la_emitchar>: Likewise.
	(LA_PRINT_CHAR): Likewise.
	(LA_PRINT_STRING): Likewise.
	(LA_EMIT_CHAR): Likewise.
	* language.c (unk_lang_emit_char): Add type argument.
	(unk_lang_printchar): Likewise.
	(unk_lang_printstr): Likewise.
	* jv-valprint.c (java_val_print): Update.
	* jv-lang.c (java_emit_char): Add type argument.
	* f-valprint.c (f_val_print): Update.
	* f-lang.c (f_emit_char): Add type argument.
	(f_printchar): Likewise.
	(f_printstr): Likewise.
	* expprint.c (print_subexp_standard): Update.
	* charset.h (target_wide_charset): Declare.
	(c_target_char_has_backslash_escape, c_parse_backslash,
	host_char_print_literally, host_char_to_target,
	target_char_to_host, target_char_to_control_char): Remove.
	(enum transliterations): New type.
	(convert_between_encodings): Declare.
	(HOST_ESCAPE_CHAR): New define.
	(host_letter_to_control_character, host_hex_value): Declare.
	(enum wchar_iterate_result): New enum.
	(struct wchar_iterator): Declare.
	(make_wchar_iterator, make_cleanup_wchar_iterator, wchar_iterator,
	wchar_push_back): Declare.
	* charset-list.h: New file.
	* c-valprint.c (textual_name): New function.
	(textual_element_type): Handle wide character types.
	(c_val_print): Pass original type to textual_element_type.  Handle
	wide character types.
	(c_value_print): Use textual_element_type.  Pass original type of
	value to val_print.
	* c-lang.h (enum c_string_type): New type.
	(c_printchar, c_printstr): Update.
	* c-lang.c (classify_type): New function.
	(print_wchar): Likewise.
	(c_emit_char): Add type argument.  Handle wide characters.
	(c_printchar): Likewise.
	(c_printstr): Add type argument.  Handle wide and multibyte
	character sets.
	(convert_ucn): New function.
	(emit_numeric_character): Likewise.
	(convert_octal): Likewise.
	(convert_hex): Likewise.
	(ADVANCE): New macro.
	(convert_escape): New function.
	(parse_one_string): Likewise.
	(evaluate_subexp_c): Likewise.
	(exp_descriptor_c): New global.
	(c_language_defn): Use exp_descriptor_c.
	(cplus_language_defn): Likewise.
	(asm_language_defn): Likewise.
	(minimal_language_defn): Likewise.
	(charset_for_string_type): New function.
	* c-exp.y (%union): Add 'svec' and 'tsval'.
	(CHAR): New token.
	(exp): Add CHAR production.
	(string_exp): Rewrite.
	(exp) <string_exp>: Rewrite.
	(tempbuf): Now global.
	(tempbuf_init): New global.
	(parse_string_or_char): New function.
	(yylex) <tempbuf>: Now global.
	<tokptr, tempbufindex, tempbufsize, token_string, class_prefix>:
	Remove.
	Handle 'u', 'U', and 'L' prefixes.  Call parse_string_or_char.
	(c_parse_escape): New function.
	* auxv.c (fprint_target_auxv): Update.
	* ada-valprint.c (ada_emit_char): Add type argument.
	(ada_printchar): Likewise.
	(ada_print_scalar): Update.
	(printstr): Add type argument.  Update calls to ada_emit_char.
	(ada_printstr): Add type argument.
	(ada_val_print_array): Update.
	(ada_val_print_1): Likewise.
	* ada-lang.c (emit_char): Add type argument.
	* ada-lang.h (ada_emit_char, ada_printchar, ada_printstr): Add
	type arguments.
	* gdb_locale.h: Include langinfo.h.
	* charset.c (_initialize_charset): Set default host charset from
	the locale.  Don't register charsets.  Add target-wide-charset
	commands.  Call find_charset_names.
	(struct charset, struct translation): Remove.
	(GDB_DEFAULT_HOST_CHARSET): Remove.
	(GDB_DEFAULT_TARGET_WIDE_CHARSET): New define.
	(target_wide_charset_name): New global.
	(show_host_charset_name): Handle "auto".
	(show_target_wide_charset_name): New function.
	(host_charset_enum, target_charset_enum): Remove.
	(charset_enum): New global.
	(all_charsets, register_charset, lookup_charset, all_translations,
	register_translation, lookup_translation): Remove.
	(simple_charset, ascii_print_literally, ascii_to_control): Remove.
	(iso_8859_print_literally, iso_8859_to_control,
	iso_8859_family_charset): Remove.
	(ebcdic_print_literally, ebcdic_to_control,
	ebcdic_family_charset): Remove.
	(struct cached_iconv, check_iconv_cache, cached_iconv_convert,
	register_iconv_charsets): Remove.
	(target_wide_charset_be_name, target_wide_charset_le_name): New
	globals.
	(identity_either_char_to_other): Remove.
	(set_be_le_names, validate): New functions.
	(backslashable, backslashed, represented): Remove.
	(default_c_target_char_has_backslash_escape): Remove.
	(default_c_parse_backslash, iconv_convert): Remove.
	(ascii_to_iso_8859_1_table, ascii_to_ebcdic_us_table,
	ascii_to_ibm1047_table, iso_8859_1_to_ascii_table,
	iso_8859_1_to_ebcdic_us_table, iso_8859_1_to_ibm1047_table,
	ebcdic_us_to_ascii_table, ebcdic_us_to_iso_8859_1_table,
	ebcdic_us_to_ibm1047_table, ibm1047_to_ascii_table,
	ibm1047_to_iso_8859_1_table, ibm1047_to_ebcdic_us_table): Remove.
	(table_convert_char, table_translation, simple_table_translation):
	Remove.
	(current_host_charset, current_target_charset,
	c_target_char_has_backslash_escape_func,
	c_target_char_has_backslash_escape_baton): Remove.
	(c_parse_backslash_func, c_parse_backslash_baton): Remove.
	(host_char_to_target_func, host_char_to_target_baton): Remove.
	(target_char_to_host_func, target_char_to_host_baton): Remove.
	(cached_iconv_host_to_target, cached_iconv_target_to_host):
	Remove.
	(lookup_charset_or_error, check_valid_host_charset): Remove.
	(set_host_and_target_charsets): Remove.
	(set_host_charset, set_target_charset): Remove.
	(set_host_charset_sfunc, set_target_charset_sfunc): Rewrite.
	(set_target_wide_charset_sfunc): New function.
	(show_charset): Print target wide character set.
	(host_charset, target_charset): Rewrite.
	(target_wide_charset): New function.
	(c_target_char_has_backslash_escape): Remove.
	(c_parse_backslash): Remove.
	(host_letter_to_control_character): New function.
	(host_char_print_literally): Remove.
	(host_hex_value): New function.
	(target_char_to_control_char): Remove.
	(cleanup_iconv): New function.
	(convert_between_encodings): New function.
	(target_char_to_host): Remove.
	(struct wchar_iterator): Define.
	(make_wchar_iterator, make_cleanup_wchar_iterator, wchar_iterator,
	wchar_push_back): New functions.
	(do_cleanup_iterator): New function.
	(char_ptr): New typedef.
	(charsets): New global.
	(add_one, find_charset_names): New functions.
	(default_charset_names): New global.
	(auto_host_charset_name): Likewise.
	* aclocal.m4, config.in, configure: Rebuild.
	* configure.ac: Call AM_LANGINFO_CODESET.
	(GDB_DEFAULT_HOST_CHARSET): Default to UTF-8.
	(AM_ICONV): Invoke earlier.
	* acinclude.m4: Include codeset.m4.  Subst LIBICONV_INCLUDE and
	LIBICONV_LIBDIR.  Check for libiconv in build tree.
	* Makefile.in (LIBICONV_LIBDIR, LIBICONV_INCLUDE): New macros.
	(INTERNAL_CFLAGS_BASE): Add LIBICONV_INCLUDE.
	(INTERNAL_LDFLAGS): Add LIBICONV_LIBDIR.
	* gdb_obstack.h (obstack_grow_wstr): New define.
        * gdb_wchar.h: New file.
        * defs.h: Include it.
gdb/testsuite:
	* gdb.base/store.exp: Update for change to escape output.
	* gdb.base/callfuncs.exp (fetch_all_registers): Update for change
	to escape output.
	* gdb.base/pointers.exp: Update for change to escape output.
	* gdb.base/long_long.exp (gdb_test_long_long): Update for change
	to escape output.
	* gdb.base/constvars.exp (do_constvar_tests): Update for change to
	escape output.
	* gdb.base/call-rt-st.exp (print_struct_call): Update for change
	to escape output.
	* gdb.cp/ref-types.exp (gdb_start_again): Update for change to
	escape output.
	* gdb.base/setvar.exp: Update for change to escape output.
	* lib/gdb.exp (default_gdb_start): Set LC_CTYPE to C.
	* gdb.base/printcmds.exp (test_print_all_chars): Update for change
	to escape output.
	(test_print_string_constants): Likewise.
	* gdb.base/charset.exp (valid_host_charset): Check size of
	wchar_t.  Handle UCS-2 and UCS-4.  Add tests for wide and unicode
	cases.  Handle "auto"-related output.
	* gdb.base/charset.c (char16_t, char32_t): New typedefs.
	(uvar, Uvar): New globals.
gdb/doc:
	* gdb.texinfo (Character Sets): Remove obsolete text.  Document
	set target-wide-charset.
	(Requirements): Mention iconv.

1 files changed, 112 insertions, 72 deletions

diff --git a/gdb/charset.h b/gdb/charset.h
index 21780b6..60abb18 100644
--- a/gdb/charset.h
+++ b/gdb/charset.h
@@ -19,89 +19,129 @@
 #ifndef CHARSET_H
 #define CHARSET_H
 
-
 /* If the target program uses a different character set than the host,
    GDB has some support for translating between the two; GDB converts
    characters and strings to the host character set before displaying
    them, and converts characters and strings appearing in expressions
    entered by the user to the target character set.
 
-   At the moment, GDB only supports single-byte, stateless character
-   sets.  This includes the ISO-8859 family (ASCII extended with
-   accented characters, and (I think) Cyrillic, for European
-   languages), and the EBCDIC family (used on IBM's mainframes).
-   Unfortunately, it excludes many Asian scripts, the fixed- and
-   variable-width Unicode encodings, and other desireable things.
-   Patches are welcome!  (For example, it would be nice if the Java
-   string support could simply get absorbed into some more general
-   multi-byte encoding support.)
-
-   Furthermore, GDB's code pretty much assumes that the host character
-   set is some superset of ASCII; there are plenty if ('0' + n)
-   expressions and the like.
-
-   When the `iconv' library routine supports a character set meeting
-   the requirements above, it's easy to plug an entry into GDB's table
-   that uses iconv to handle the details.  */
+   GDB's code pretty much assumes that the host character set is some
+   superset of ASCII; there are plenty if ('0' + n) expressions and
+   the like.  */
 
 /* Return the name of the current host/target character set.  The
    result is owned by the charset module; the caller should not free
    it.  */
 const char *host_charset (void);
 const char *target_charset (void);
-
-/* In general, the set of C backslash escapes (\n, \f) is specific to
-   the character set.  Not all character sets will have form feed
-   characters, for example.
-
-   The following functions allow GDB to parse and print control
-   characters in a character-set-independent way.  They are both
-   language-specific (to C and C++) and character-set-specific.
-   Putting them here is a compromise.  */
-
-
-/* If the target character TARGET_CHAR have a backslash escape in the
-   C language (i.e., a character like 'n' or 't'), return the host
-   character string that should follow the backslash.  Otherwise,
-   return zero.
-
-   When this function returns non-zero, the string it returns is
-   statically allocated; the caller is not responsible for freeing it.  */
-const char *c_target_char_has_backslash_escape (int target_char);
-
-
-/* If the host character HOST_CHAR is a valid backslash escape in the
-   C language for the target character set, return non-zero, and set
-   *TARGET_CHAR to the target character the backslash escape represents.
-   Otherwise, return zero.  */
-int c_parse_backslash (int host_char, int *target_char);
-
-
-/* Return non-zero if the host character HOST_CHAR can be printed
-   literally --- that is, if it can be readably printed as itself in a
-   character or string constant.  Return zero if it should be printed
-   using some kind of numeric escape, like '\031' in C, '^(25)' in
-   Chill, or #25 in Pascal.  */
-int host_char_print_literally (int host_char);
-
-
-/* If the host character HOST_CHAR has an equivalent in the target
-   character set, set *TARGET_CHAR to that equivalent, and return
-   non-zero.  Otherwise, return zero.  */
-int host_char_to_target (int host_char, int *target_char);
-
-
-/* If the target character TARGET_CHAR has an equivalent in the host
-   character set, set *HOST_CHAR to that equivalent, and return
-   non-zero.  Otherwise, return zero.  */
-int target_char_to_host (int target_char, int *host_char);
-
-
-/* If the target character TARGET_CHAR has a corresponding control
-   character (also in the target character set), set *TARGET_CTRL_CHAR
-   to the control character, and return non-zero.  Otherwise, return
-   zero.  */
-int target_char_to_control_char (int target_char, int *target_ctrl_char);
-
+const char *target_wide_charset (void);
+
+/* These values are used to specify the type of transliteration done
+   by convert_between_encodings.  */
+enum transliterations
+  {
+    /* Error on failure to convert.  */
+    translit_none,
+    /* Transliterate to host char.  */
+    translit_char
+  };
+
+/* Convert between two encodings.
+
+   FROM is the name of the source encoding.
+   TO is the name of the target encoding.
+   BYTES holds the bytes to convert; this is assumed to be characters
+   in the target encoding.
+   NUM_BYTES is the number of bytes.
+   WIDTH is the width of a character from the FROM charset, in bytes.
+   For a variable width encoding, WIDTH should be the size of a "base
+   character".
+   OUTPUT is an obstack where the converted data is written.  The
+   caller is responsible for initializing the obstack, and for
+   destroying the obstack should an error occur.
+   TRANSLIT specifies how invalid conversions should be handled.  */
+void convert_between_encodings (const char *from, const char *to,
+				const gdb_byte *bytes, unsigned int num_bytes,
+				int width, struct obstack *output,
+				enum transliterations translit);
+
+
+/* These values are used by wchar_iterate to report errors.  */
+enum wchar_iterate_result
+  {
+    /* Ordinary return.  */
+    wchar_iterate_ok,
+    /* Invalid input sequence.  */
+    wchar_iterate_invalid,
+    /* Incomplete input sequence at the end of the input.  */
+    wchar_iterate_incomplete,
+    /* EOF.  */
+    wchar_iterate_eof
+  };
+
+/* Declaration of the opaque wchar iterator type.  */
+struct wchar_iterator;
+
+/* Create a new character iterator which returns wchar_t's.  INPUT is
+   the input buffer.  BYTES is the number of bytes in the input
+   buffer.  CHARSET is the name of the character set in which INPUT is
+   encoded.  WIDTH is the number of bytes in a base character of
+   CHARSET.
+   
+   This function either returns a new character set iterator, or calls
+   error.  The result can be freed using a cleanup; see
+   make_cleanup_wchar_iterator.  */
+struct wchar_iterator *make_wchar_iterator (const gdb_byte *input, size_t bytes,
+					    const char *charset,
+					    size_t width);
+
+/* Return a new cleanup suitable for destroying the wchar iterator
+   ITER.  */
+struct cleanup *make_cleanup_wchar_iterator (struct wchar_iterator *iter);
+
+/* Perform a single iteration of a wchar_t iterator.
+   
+   Returns the number of characters converted.  A negative result
+   means that EOF has been reached.  A positive result indicates the
+   number of valid wchar_ts in the result; *OUT_CHARS is updated to
+   point to the first valid character.
+
+   In all cases aside from EOF, *PTR is set to point to the first
+   converted target byte.  *LEN is set to the number of bytes
+   converted.
+
+   A zero result means one of several unusual results.  *OUT_RESULT is
+   set to indicate the type of un-ordinary return.
+
+   wchar_iterate_invalid means that an invalid input character was
+   seen.  The iterator is advanced by WIDTH (the argument to
+   make_wchar_iterator) bytes.
+
+   wchar_iterate_incomplete means that an incomplete character was
+   seen at the end of the input sequence.
+   
+   wchar_iterate_eof means that all bytes were successfully
+   converted.  The other output arguments are not set.  */
+int wchar_iterate (struct wchar_iterator *iter,
+		   enum wchar_iterate_result *out_result,
+		   gdb_wchar_t **out_chars,
+		   const gdb_byte **ptr, size_t *len);
+
+
+
+/* GDB needs to know a few details of its execution character set.
+   This knowledge is isolated here and in charset.c.  */
+
+/* The escape character.  */
+#define HOST_ESCAPE_CHAR 27
+
+/* Convert a letter, like 'c', to its corresponding control
+   character.  */
+char host_letter_to_control_character (char c);
+
+/* Convert a hex digit character to its numeric value.  E.g., 'f' is
+   converted to 15.  This function assumes that C is a valid hex
+   digit.  Both upper- and lower-case letters are recognized.  */
+int host_hex_value (char c);
 
 #endif /* CHARSET_H */