cpphash.h (struct lexer_state): Remove line_extension member.

	* cpphash.h (struct lexer_state): Remove line_extension member.
	* cpplib.c (dequote_string, do_linemarker): New functions.
	(linemarker_dir): New data object.
	(DIRECTIVE_TABLE): No longer need to interpret #line in
	preprocessed source.  Delete obsolete comment about return
	values of handlers.
	(end_directive, directive_diagnostics, _cpp_handle_directive):
	Don't muck with line_extension.
	(directive_diagnostics): No need to issue warnings for
	linemarkers here.
	(_cpp_handle_directive): Issue warnings for linemarkers here,
	when appropriate.  Dispatch linemarkers to do_linemarker, not
	do_line.
	(do_line): Code to handle linemarkers split out to do_linemarker.
	Convert escape sequences in filename argument, both places.

	* cppmacro.c (quote_string): Rename cpp_quote_string and
	export.  All callers changed.
	* cpplib.h (cpp_quote_string): Prototype.
	* cppmain.c (print_line): Call cpp_quote_string on to_file
	before printing it.

	* doc/cpp.texi: Document that escapes are now interpreted in
	#line and in linemarkers, and that non-printing characters are
	converted to octal escapes when linemarkers are generated.

From-SVN: r50779

gcc/cpphash.h

@@ -152,9 +152,6 @@ struct lexer_state
 
   /* Nonzero when parsing arguments to a function-like macro.  */
   unsigned char parsing_args;
-
-  /* Nonzero when in a # NUMBER directive.  */
-  unsigned char line_extension;
 };
 
 /* Special nodes - identifiers with predefined significance.  */

gcc/cpplib.h

@@ -592,6 +592,9 @@ extern void cpp_forall_identifiers	PARAMS ((cpp_reader *,
 /* In cppmacro.c */
 extern void cpp_scan_nooutput		PARAMS ((cpp_reader *));
 extern int  cpp_sys_macro_p		PARAMS ((cpp_reader *));
+extern unsigned char *cpp_quote_string	PARAMS ((unsigned char *,
+						 const unsigned char *,
+						 unsigned int));
 
 /* In cppfiles.c */
 extern int cpp_included	PARAMS ((cpp_reader *, const char *));

gcc/cppmacro.c

@@ -64,9 +64,6 @@ static cpp_context *next_context PARAMS ((cpp_reader *));
 static const cpp_token *padding_token
   PARAMS ((cpp_reader *, const cpp_token *));
 static void expand_arg PARAMS ((cpp_reader *, macro_arg *));
-static unsigned char *quote_string PARAMS ((unsigned char *,
-					    const unsigned char *,
-					    unsigned int));
 static const cpp_token *new_string_token PARAMS ((cpp_reader *, U_CHAR *,
 						  unsigned int));
 static const cpp_token *new_number_token PARAMS ((cpp_reader *, unsigned int));
@@ -164,7 +161,7 @@ builtin_macro (pfile, node)
 	name = map->to_file;
 	len = strlen (name);
 	buf = _cpp_unaligned_alloc (pfile, len * 4 + 1);
-	len = quote_string (buf, (const unsigned char *) name, len) - buf;
+	len = cpp_quote_string (buf, (const unsigned char *) name, len) - buf;
 
 	result = new_string_token (pfile, buf, len);
       }
@@ -244,9 +241,10 @@ builtin_macro (pfile, node)
 
 /* Copies SRC, of length LEN, to DEST, adding backslashes before all
    backslashes and double quotes.  Non-printable characters are
-   converted to octal.  DEST must be of sufficient size.  */
-static U_CHAR *
-quote_string (dest, src, len)
+   converted to octal.  DEST must be of sufficient size.  Returns
+   a pointer to the end of the string.  */
+U_CHAR *
+cpp_quote_string (dest, src, len)
      U_CHAR *dest;
      const U_CHAR *src;
      unsigned int len;
@@ -331,7 +329,7 @@ stringify_arg (pfile, arg)
 	  _cpp_buff *buff = _cpp_get_buff (pfile, len);
 	  unsigned char *buf = BUFF_FRONT (buff);
 	  len = cpp_spell_token (pfile, token, buf) - buf;
-	  dest = quote_string (dest, buf, len);
+	  dest = cpp_quote_string (dest, buf, len);
 	  _cpp_release_buff (pfile, buff);
 	}
       else

gcc/cppmain.c

@@ -321,8 +321,17 @@ print_line (map, line, special_flags)
   print.line = line;
   if (! options->no_line_commands)
     {
+      size_t to_file_len = strlen (map->to_file);
+      unsigned char *to_file_quoted = alloca (to_file_len * 4 + 1);
+      unsigned char *p;
+      
+      /* cpp_quote_string does not nul-terminate, so we have to do it
+	 ourselves.  */
+      p = cpp_quote_string (to_file_quoted,
+			    (unsigned char *)map->to_file, to_file_len);
+      *p = '\0';
       fprintf (print.outf, "# %u \"%s\"%s",
-	       SOURCE_LINE (map, print.line), map->to_file, special_flags);
+	       SOURCE_LINE (map, print.line), to_file_quoted, special_flags);
 
       if (map->sysp == 2)
 	fputs (" 3 4", print.outf);

gcc/doc/cpp.texi

@@ -3087,6 +3087,13 @@ input.  Subsequent lines are counted from @var{linenum}.
 effect.  In addition, @var{filename} is a string constant.  The
 following line and all subsequent lines are reported to come from the
 file it specifies, until something else happens to change that.
+@var{filename} is interpreted according to the normal rules for a string
+constant: backslash escapes are interpreted.  This is different from
+@samp{#include}.
+
+Previous versions of GNU CPP did not interpret escapes in @samp{#line};
+we have changed it because the standard requires they be interpreted,
+and most other compilers do.
 
 @item #line @var{anything else}
 @var{anything else} is checked for macro calls, which are expanded.
@@ -3304,7 +3311,8 @@ of the form
 These are called @dfn{linemarkers}.  They are inserted as needed into
 the output (but never within a string or character constant).  They mean
 that the following line originated in file @var{filename} at line
-@var{linenum}.
+@var{linenum}.  @var{filename} will never contain any non-printing
+characters; they are replaced with octal escape sequences.
 
 After the file name comes zero or more flags, which are @samp{1},
 @samp{2}, @samp{3}, or @samp{4}.  If there are multiple flags, spaces
@@ -3868,6 +3876,17 @@ The @samp{#line} directive used to change GCC's notion of the
 a double-quoted header file name.  In 3.0 and later, it does not.
 @xref{Line Control}, for further explanation.
 
+@item Syntax of @samp{#line}
+
+In GCC 2.95 and previous, the string constant argument to @samp{#line}
+was treated the same way as the argument to @samp{#include}: backslash
+escapes were not honored, and the string ended at the second @samp{"}.
+This is not compliant with the C standard.  In GCC 3.0, an attempt was
+made to correct the behavior, so that the string was treated as a real
+string constant, but it turned out to be buggy.  In 3.1, the bugs have
+been fixed.  (We are not fixing the bugs in 3.0 because they affect
+relatively few people and the fix is quite invasive.)
+
 @end itemize
 
 @node Invocation