cpplib.h (CPP_AT_NAME, [...]): New token types.

	* cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types.
	(struct cpp_options): Add narrow_charset, wide_charset,
	bytes_big_endian fields.  Remove EBCDIC field.
	(cpp_init_iconv, cpp_interpret_string): New external interfaces.

	* cpphash.h: Include <iconv.h> if we have it, otherwise
	provide a dummy definition of iconv_t.
	(struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields.
	(_cpp_valid_ucn): Update prototype.
	(_cpp_destroy_iconv): New prototype.

	* doc/cpp.texi: Document character set handling.
	* doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=.
	* doc/extend.texi: Delete entire section on multiline strings.
	Rewrite section on __FUNCTION__ etc now that these are
	variables in C.

	* cppucnid.tab, cppucnid.pl: New files.
	* cppucnid.h: New generated file.
	* cppcharset.c: Include cppucnid.h.  Lots of commentary added.
	(iconv_open, iconv, iconv_close): Provide dummy definitions
	if !HAVE_ICONV.
	(SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv,
	_cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn,
	emit_numeric_escape, convert_hex, convert_oct, convert_escape,
	cpp_interpret_string, narrow_str_to_charconst,
	wide_str_to_charconst): New.
	(ucn_valid_in_identifier): Use a binary search through the
	ucnranges table defined in cppucnid.h, not a long chain of if
	statements.
	(_cpp_valid_ucn): Add a limit pointer.  Downgrade "universal
	character names are only valid in C++ and C99" to a warning.
	Issue the "meaning of \[uU] is different in traditional C"
	warning here.  Take care not to let iconv see an invalid UCS
	value if we get a malformed UCN.  Issue an error if we don't
	have iconv.
	(cpp_interpret_charconst): Moved here from cpplex.c.  Use
	cpp_interpret_string to do the heavy lifting.

	* cppinit.c (cpp_create_reader): Initialize bytes_big_endian,
	narrow_charset, wide_charset fields of options structure.
	(cpp_destroy): Call _cpp_destroy_iconv.
	* cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn.
	(maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete.
	(cpp_interpret_charconst): Moved to cppcharset.c.
	* cpplib.c (dequote_string): Delete.
	(interpret_string_notranslate): New.
	(do_line, do_linemarker): Use interpret_string_notranslate.

	* Makefile.in (cppcharset.o): Depend on cppucnid.h.

	* c-common.c (fname_string, combine_strings): Delete.
	* c-common.h (fname_string, combine_strings): Delete prototypes.
	* c-lex.c (ignore_escape_flag): Delete.
	(cb_ident): Use cpp_interpret_string, not lex_string.
	(get_nonpadding_token): New function.
	(c_lex): Handle Objective-C @-prefixed identifiers and strings here.
	Adjust calls to lex_string.  Don't write *value twice.
	(lex_string): Now handles string constant concatenation.
	Most of the work handed off to cpp_interpret_string.
	Call fix_string_type here.
	* c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with
	FUNC_NAME, throughout.
	(OBJC_STRING): New token type.
	(primary:STRING): No need to call fix_string_type here.
	(primary:objc_string): Make that OBJC_STRING.
	(objc_string nonterminal): Delete.
	(yylexname): Delete code to handle fake string constants.
	(yylexstring): Delete entirely.
	(_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING.  No need
	to handle CPP_ATSIGN.

	* c.opt (-fexec-charset=, -fwide-exec-charset=): New options.
	* c-opts.c (missing_arg, c_common_handle_option): Handle
	OPT_fexec_charset_ and OPT_fwide_exec_charset_.
	(c_common_init): Set cpp_opts->bytes_big_endian, not
	cpp_opts->EBCDIC.  Call cpp_init_iconv.
	(print_help): Document -fexec-charset= and -fexec-wide-charset=.
	(TARGET_EBCDIC): Delete default definition.

	* objc/objc-act.c (build_objc_string_object): No need to
	handle string constant concatenation.

cp:
	* parser.c (cp_lexer_read_token): No need to handle string
	constant concatenation.

testsuite:
	* gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c
	everywhere.
	* gcc.dg/concat.c: Concatenation of string constants with
	__FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error.
	* gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp.
	* gcc.dg/cpp/escape-2.c: Use wide character constants where
	necessary to avoid multi-character character constant warning.
	* gcc.dg/cpp/escape.c: Likewise.
	* gcc.dg/cpp/ucs.c: Likewise.
	Remove backslashes from dg-bogus comments, as they confuse Tcl.
	Fix a typo.

libstdc++-v3:
	* testsuite/22_locale/collate/compare/wchar_t/2.cc
	* testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc
	* testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc
	* testsuite/22_locale/collate/hash/wchar_t/2.cc
	* testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc
	* testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc
	* testsuite/22_locale/collate/transform/wchar_t/2.cc
	* testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc
	* testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc:
	XFAIL on all targets.

From-SVN: r68952

2 files changed, 39 insertions, 78 deletions

diff --git a/gcc/cp/ChangeLog b/gcc/cp/ChangeLog
index 076dcbd..8776631 100644
--- a/gcc/cp/ChangeLog
+++ b/gcc/cp/ChangeLog
@@ -1,3 +1,8 @@
+2003-07-04  Zack Weinberg  <zack@codesourcery.com>
+
+	* parser.c (cp_lexer_read_token): No need to handle string
+	constant concatenation.
+
 2003-07-03  Kaveh R. Ghazi  <ghazi@caip.rutgers.edu>
 
 	* cp-tree.h (GCC_DIAG_STYLE, ATTRIBUTE_GCC_CXXDIAG): Define.
@@ -51,7 +56,7 @@
 	(convert_for_initialization): Likewise.
 	* typeck2.c (build_x_arrow): Likewise.
 	(build_m_component_ref): Simplify.
-	
+
 	* call.c (build_scoped_method_call): Use convert_to_void.
 	(build_method_call): Likewise.
 	* class.c (check_field_decls): Remove dead code.
@@ -63,7 +68,7 @@
 	(build_vec_delete_1): Use convert_to_void.
 	* mangle.c (write_type): Avoid relying on POINTER_TYPE over OFFSET_TYPE
 	as pointer-to-member representation.
-	
+
 2003-07-03  Nathan Sidwell  <nathan@codesourcery.com>
 
 	PR c++/9162
@@ -145,10 +150,10 @@ Wed Jul  2 00:36:48 CEST 2003  Jan Hubicka  <jh@suse.cz>
 	is a class type.
 
 2003-07-01  Giovanni Bajo  <giovannibajo@libero.it>
-	
-        PR c++/8046
-        * error.c (dump_decl): Handle BIT_NOT_EXPR as
-        pseudo destructor calls.
+
+	PR c++/8046
+	* error.c (dump_decl): Handle BIT_NOT_EXPR as
+	pseudo destructor calls.
 
 2003-07-01  Nathan Sidwell  <nathan@codesourcery.com>
 
@@ -176,28 +181,28 @@ Wed Jul  2 00:36:48 CEST 2003  Jan Hubicka  <jh@suse.cz>
 
 2003-06-30  Giovanni Bajo  <giovannibajo@libero.it>
 
-        PR c++/4933
-        * error.c (dump_expr): Support correctly the COMPOUND_EXPR
-        tree generated within a template. Use dump_expr to dump an
-        expression sizeof.
+	PR c++/4933
+	* error.c (dump_expr): Support correctly the COMPOUND_EXPR
+	tree generated within a template. Use dump_expr to dump an
+	expression sizeof.
 
 2003-06-30  Giovanni Bajo  <giovannibajo@libero.it>
 
-        * mangle.c (write_expression): Exit gracefully when trying to
-        mangle a CALL_EXPR.
+	* mangle.c (write_expression): Exit gracefully when trying to
+	mangle a CALL_EXPR.
 
 2003-06-30  Giovanni Bajo  <giovannibajo@libero.it>
 
-        PR c++/10750
-        * parser.c (cp_parser_primary_expression): A VAR_DECL with a
-        (value- or type-) dependent expression as DECL_INITIAL is a
-        valid constant-expression (at parser time).
+	PR c++/10750
+	* parser.c (cp_parser_primary_expression): A VAR_DECL with a
+	(value- or type-) dependent expression as DECL_INITIAL is a
+	valid constant-expression (at parser time).
 
 2003-06-30  Giovanni Bajo <giovannibajo@libero.it>
 
-        PR c++/11106
-        * error.c (dump_decl): Call dump_decl to dump the DECL_NAME for a
-        USING_DECL, instead of print_tree_identifier.
+	PR c++/11106
+	* error.c (dump_decl): Call dump_decl to dump the DECL_NAME for a
+	USING_DECL, instead of print_tree_identifier.
 
 2003-06-29  Gabriel Dos Reis  <gdr@integrable-solutions.net>
 
diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index d19e4038..1f48466 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -479,66 +479,22 @@ cp_lexer_read_token (cp_lexer* lexer)
   /* Increment LAST_TOKEN.  */
   lexer->last_token = cp_lexer_next_token (lexer, token);
 
-  /* The preprocessor does not yet do translation phase six, i.e., the
-     combination of adjacent string literals.  Therefore, we do it
-     here.  */
-  if (token->type == CPP_STRING || token->type == CPP_WSTRING)
-    {
-      ptrdiff_t delta;
-      int i;
-
-      /* When we grow the buffer, we may invalidate TOKEN.  So, save
-	 the distance from the beginning of the BUFFER so that we can
-	 recaulate it.  */
-      delta = cp_lexer_token_difference (lexer, lexer->buffer, token);
-      /* Make sure there is room in the buffer for another token.  */
-      cp_lexer_maybe_grow_buffer (lexer);
-      /* Restore TOKEN.  */
-      token = lexer->buffer;
-      for (i = 0; i < delta; ++i)
-	token = cp_lexer_next_token (lexer, token);
-
-      VARRAY_PUSH_TREE (lexer->string_tokens, token->value);
-      while (true)
-	{
-	  /* Read the token after TOKEN.  */
-	  cp_lexer_get_preprocessor_token (lexer, lexer->last_token);
-	  /* See whether it's another string constant.  */
-	  if (lexer->last_token->type != token->type)
-	    {
-	      /* If not, then it will be the next real token.  */
-	      lexer->last_token = cp_lexer_next_token (lexer, 
-						       lexer->last_token);
-	      break;
-	    }
-
-	  /* Chain the strings together.  */
-	  VARRAY_PUSH_TREE (lexer->string_tokens, 
-			    lexer->last_token->value);
-	}
-
-      /* Create a single STRING_CST.  Curiously we have to call
-	 combine_strings even if there is only a single string in
-	 order to get the type set correctly.  */
-      token->value = combine_strings (lexer->string_tokens);
-      VARRAY_CLEAR (lexer->string_tokens);
-      token->value = fix_string_type (token->value);
-      /* Strings should have type `const char []'.  Right now, we will
-	 have an ARRAY_TYPE that is constant rather than an array of
-	 constant elements.  */
-      if (flag_const_strings)
-	{
-	  tree type;
+  /* Strings should have type `const char []'.  Right now, we will
+     have an ARRAY_TYPE that is constant rather than an array of
+     constant elements.
+     FIXME: Make fix_string_type get this right in the first place.  */
+  if ((token->type == CPP_STRING || token->type == CPP_WSTRING)
+      && flag_const_strings)
+    {
+      tree type;
 
-	  /* Get the current type.  It will be an ARRAY_TYPE.  */
-	  type = TREE_TYPE (token->value);
-	  /* Use build_cplus_array_type to rebuild the array, thereby
-	     getting the right type.  */
-	  type = build_cplus_array_type (TREE_TYPE (type),
-					 TYPE_DOMAIN (type));
-	  /* Reset the type of the token.  */
-	  TREE_TYPE (token->value) = type;
-	}
+      /* Get the current type.  It will be an ARRAY_TYPE.  */
+      type = TREE_TYPE (token->value);
+      /* Use build_cplus_array_type to rebuild the array, thereby
+	 getting the right type.  */
+      type = build_cplus_array_type (TREE_TYPE (type), TYPE_DOMAIN (type));
+      /* Reset the type of the token.  */
+      TREE_TYPE (token->value) = type;
     }
 
   return token;