PR 18785

libcpp:
	* charset.c (LAST_POSSIBLY_BASIC_SOURCE_CHAR): New helper macro.
	(cpp_host_to_exec_charset): New function.
	* include/cpplib.h: Declare cpp_host_to_exec_charset.

gcc:
	* langhooks.h (struct lang_hooks): Add to_target_charset.
	* langhooks.c (lhd_to_target_charset): New function.
	* langhooks-def.h: Declare lhd_to_target_charset.
	(LANG_HOOKS_TO_TARGET_CHARSET): New macro.
	(LANG_HOOKS_INITIALIZER): Update.
	* c-common.c (c_common_to_target_charset): New function.
	* c-common.h: Declare it.
	* c-objc-common.h (LANG_HOOKS_TO_TARGET_CHARSET): Set to
	c_common_to_target_charset.

	* defaults.c (TARGET_BELL, TARGET_BS, TARGET_CR, TARGET_DIGIT0)
	(TARGET_ESC, TARGET_FF, TARGET_NEWLINE, TARGET_TAB, TARGET_VT):
	Delete definitions.
	* system.h: Poison them.
	* doc/tm.texi: Don't discuss them.
	* builtins.c (fold_builtin_isdigit): Use lang_hooks.to_target_charset.
	* c-pretty-print.c (pp_c_integer_constant): Don't use pp_c_char.
	(pp_c_char): Do not attempt to generate letter escapes for
	newline, tab, etc.
	* config/arm/arm.c (output_ascii_pseudo_op): Likewise.
	* config/mips/mips.c (mips_output_ascii): Likewise.
gcc/cp:
	* cp-objcp-common.h (LANG_HOOKS_TO_TARGET_CHARSET): Set to
	c_common_to_target_charset.  Delete bogus comment.
gcc/testsuite:
	* gcc.dg/charset/builtin1.c: New test.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@95304 138bc75d-0d04-0410-961f-82ee72b054a4

3 files changed, 75 insertions, 14 deletions

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 0764fc8e4b3..5e6ad289e36 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,8 +1,15 @@
+2005-02-20  Zack Weinberg  <zack@codesourcery.com>
+
+	PR 18785
+	* charset.c (LAST_POSSIBLY_BASIC_SOURCE_CHAR): New helper macro.
+	(cpp_host_to_exec_charset): New function.
+	* include/cpplib.h: Declare cpp_host_to_exec_charset.
+
 2005-02-19  Devang Patel  <dpatel@apple.com>
 
 	* charset.c (_cpp_convert_input): Check '\r' before inserting
 	'\n' at the end.
-	
+
 2005-02-15  Eric Christopher  <echristo@redhat.com>
 
 	PR preprocessor/19077
@@ -41,7 +48,7 @@
 	* include/cpplib.h (c_lang): Fix comment to say cpp_create_reader.
 
 	* include/cpplib.h: Also update copyright years.
-	
+
 2005-01-03  Geoffrey Keating  <geoffk@apple.com>
 
 	* files.c (_cpp_find_file): Add files found by search_path_exhausted
@@ -64,7 +71,7 @@
 
 2004-11-28  Nathanael Nerode  <neroden@gcc.gnu.org>
 
-	PR preprocessor/17610 
+	PR preprocessor/17610
 	* directives.c (do_include_common): Error out if an empty filename
 	is given for #include (or #include_next or #import).
 
@@ -87,7 +94,7 @@
 	* configure: Regenerate.
 
 2004-11-23  Daniel Jacobowitz  <dan@codesourcery.com>
-            Joseph Myers  <joseph@codesourcery.com>
+	    Joseph Myers  <joseph@codesourcery.com>
 
 	* internal.h (struct lexer_state): Add in_deferred_pragma.
 	* directives.c (struct pragma_entry): Add allow_expansion.
@@ -100,7 +107,7 @@
 	* include/cpplib.h (cpp_register_pragma): Update prototype.
 
 2004-11-18  Daniel Jacobowitz  <dan@codesourcery.com>
-            Mark Mitchell  <mark@codesourcery.com>
+	    Mark Mitchell  <mark@codesourcery.com>
 
 	* configure.ac (i[34567]86-*-solaris2.1[0-9]*): Set
 	need_64bit_hwint=yes.
@@ -115,7 +122,7 @@
 	Remove local srcdir path from generated file.
 
 2004-11-04  Zack Weinberg  <zack@codesourcery.com>
-            Gerald Pfeifer  <gerald@pfeifer.com>
+	    Gerald Pfeifer  <gerald@pfeifer.com>
 
 	* internal.h (HAVE_ICONV): Undefine if we do not have HAVE_ICONV_H
 	as well.
diff --git a/libcpp/charset.c b/libcpp/charset.c
index 37859c52a31..6b6c360f73d 100644
--- a/libcpp/charset.c
+++ b/libcpp/charset.c
@@ -81,8 +81,10 @@ Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  */
 
 #if HOST_CHARSET == HOST_CHARSET_ASCII
 #define SOURCE_CHARSET "UTF-8"
+#define LAST_POSSIBLY_BASIC_SOURCE_CHAR 0x7e
 #elif HOST_CHARSET == HOST_CHARSET_EBCDIC
 #define SOURCE_CHARSET "UTF-EBCDIC"
+#define LAST_POSSIBLY_BASIC_SOURCE_CHAR 0xFF
 #else
 #error "Unrecognized basic host character set"
 #endif
@@ -714,6 +716,63 @@ _cpp_destroy_iconv (cpp_reader *pfile)
     }
 }
 
+/* Utility routine for use by a full compiler.  C is a character taken
+   from the *basic* source character set, encoded in the host's
+   execution encoding.  Convert it to (the target's) execution
+   encoding, and return that value.
+
+   Issues an internal error if C's representation in the narrow
+   execution character set fails to be a single-byte value (C99
+   5.2.1p3: "The representation of each member of the source and
+   execution character sets shall fit in a byte.")  May also issue an
+   internal error if C fails to be a member of the basic source
+   character set (testing this exactly is too hard, especially when
+   the host character set is EBCDIC).  */
+cppchar_t
+cpp_host_to_exec_charset (cpp_reader *pfile, cppchar_t c)
+{
+  uchar sbuf[1];
+  struct _cpp_strbuf tbuf;
+
+  /* This test is merely an approximation, but it suffices to catch
+     the most important thing, which is that we don't get handed a
+     character outside the unibyte range of the host character set.  */
+  if (c > LAST_POSSIBLY_BASIC_SOURCE_CHAR)
+    {
+      cpp_error (pfile, CPP_DL_ICE,
+		 "character 0x%lx is not in the basic source character set\n",
+		 (unsigned long)c);
+      return 0;
+    }
+
+  /* Being a character in the unibyte range of the host character set,
+     we can safely splat it into a one-byte buffer and trust that that
+     is a well-formed string.  */
+  sbuf[0] = c;
+
+  /* This should never need to reallocate, but just in case... */
+  tbuf.asize = 1;
+  tbuf.text = xmalloc (tbuf.asize);
+  tbuf.len = 0;
+
+  if (!APPLY_CONVERSION (pfile->narrow_cset_desc, sbuf, 1, &tbuf))
+    {
+      cpp_errno (pfile, CPP_DL_ICE, "converting to execution character set");
+      return 0;
+    }
+  if (tbuf.len != 1)
+    {
+      cpp_error (pfile, CPP_DL_ICE,
+		 "character 0x%lx is not unibyte in execution character set",
+		 (unsigned long)c);
+      return 0;
+    }
+  c = tbuf.text[0];
+  free(tbuf.text);
+  return c;
+}
+
+
 
 /* Utility routine that computes a mask of the form 0000...111... with
    WIDTH 1-bits.  */
@@ -727,8 +786,6 @@ width_to_mask (size_t width)
     return ((size_t) 1 << width) - 1;
 }
 
-
-
 /* Returns 1 if C is valid in an identifier, 2 if C is valid except at
    the start of an identifier, and 0 if C is not valid in an
    identifier.  We assume C has already gone through the checks of
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index c3814460705..70f8d895afd 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -659,6 +659,9 @@ extern bool cpp_interpret_string_notranslate (cpp_reader *,
 					      const cpp_string *, size_t,
 					      cpp_string *, bool);
 
+/* Convert a host character constant to the execution character set.  */
+extern cppchar_t cpp_host_to_exec_charset (cpp_reader *, cppchar_t);
+
 /* Used to register macros and assertions, perhaps from the command line.
    The text is the same as the command line argument.  */
 extern void cpp_define (cpp_reader *, const char *);
@@ -743,12 +746,6 @@ cpp_num cpp_num_sign_extend (cpp_num, size_t);
 #define CPP_DL_WARNING_P(l)	(CPP_DL_EXTRACT (l) >= CPP_DL_WARNING \
 				 && CPP_DL_EXTRACT (l) <= CPP_DL_PEDWARN)
 
-/* N.B. The error-message-printer prototypes have not been nicely
-   formatted because exgettext needs to see 'msgid' on the same line
-   as the name of the function in order to work properly.  Only the
-   string argument gets a name in an effort to keep the lines from
-   getting ridiculously oversized.  */
-
 /* Output a diagnostic of some kind.  */
 extern void cpp_error (cpp_reader *, int, const char *msgid, ...)
   ATTRIBUTE_PRINTF_3;