* 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.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@68952 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 22 insertions, 28 deletions

diff --git a/gcc/cpplib.c b/gcc/cpplib.c
index af32705856f..2fac44e62fd 100644
--- a/gcc/cpplib.c
+++ b/gcc/cpplib.c
@@ -106,7 +106,6 @@ static char *glue_header_name (cpp_reader *);
 static const char *parse_include (cpp_reader *, int *);
 static void push_conditional (cpp_reader *, int, int, const cpp_hashnode *);
 static unsigned int read_flag (cpp_reader *, unsigned int);
-static uchar *dequote_string (cpp_reader *, const uchar *, unsigned int);
 static int strtoul_for_line (const uchar *, unsigned int, unsigned long *);
 static void do_diagnostic (cpp_reader *, int, int);
 static cpp_hashnode *lex_macro_node (cpp_reader *);
@@ -714,29 +713,6 @@ read_flag (cpp_reader *pfile, unsigned int last)
   return 0;
 }
 
-/* Subroutine of do_line and do_linemarker.  Returns a version of STR
-   which has a NUL terminator and all escape sequences converted to
-   their equivalents.  Temporary, hopefully.  */
-static uchar *
-dequote_string (cpp_reader *pfile, const uchar *str, unsigned int len)
-{
-  uchar *result = _cpp_unaligned_alloc (pfile, len + 1);
-  uchar *dst = result;
-  const uchar *limit = str + len;
-  cppchar_t c;
-
-  while (str < limit)
-    {
-      c = *str++;
-      if (c != '\\')
-	*dst++ = c;
-      else
-	*dst++ = cpp_parse_escape (pfile, &str, limit, 0);
-    }
-  *dst++ = '\0';
-  return result;
-}
-
 /* Subroutine of do_line and do_linemarker.  Convert a number in STR,
    of length LEN, to binary; store it in NUMP, and return 0 if the
    number was well-formed, 1 if not.  Temporary, hopefully.  */
@@ -757,6 +733,21 @@ strtoul_for_line (const uchar *str, unsigned int len, long unsigned int *nump)
   return 0;
 }
 
+/* Subroutine of do_line and do_linemarker.  Convert escape sequences
+   in a string, but do not perform character set conversion.  */
+static bool
+interpret_string_notranslate (cpp_reader *pfile, const cpp_string *in,
+			      cpp_string *out)
+{
+  iconv_t save_narrow_cset_desc = pfile->narrow_cset_desc;
+  bool retval;
+
+  pfile->narrow_cset_desc = (iconv_t) -1;
+  retval = cpp_interpret_string (pfile, in, 1, out, false);
+  pfile->narrow_cset_desc = save_narrow_cset_desc;
+  return retval;
+}
+
 /* Interpret #line command.
    Note that the filename string (if any) is a true string constant
    (escapes are interpreted), unlike in #line.  */
@@ -788,8 +779,9 @@ do_line (cpp_reader *pfile)
   token = cpp_get_token (pfile);
   if (token->type == CPP_STRING)
     {
-      new_file = (const char *) dequote_string (pfile, token->val.str.text + 1,
-						token->val.str.len - 2);
+      cpp_string s = { 0, 0 };
+      if (interpret_string_notranslate (pfile, &token->val.str, &s))
+	new_file = (const char *)s.text;
       check_eol (pfile);
     }
   else if (token->type != CPP_EOF)
@@ -836,8 +828,10 @@ do_linemarker (cpp_reader *pfile)
   token = cpp_get_token (pfile);
   if (token->type == CPP_STRING)
     {
-      new_file = (const char *) dequote_string (pfile, token->val.str.text + 1,
-						token->val.str.len - 2);
+      cpp_string s = { 0, 0 };
+      if (interpret_string_notranslate (pfile, &token->val.str, &s))
+	new_file = (const char *)s.text;
+      
       new_sysp = 0;
       flag = read_flag (pfile, 0);
       if (flag == 1)