cpphash.h (HASHSTEP): Take character rather than pointer to character.

	* cpphash.h (HASHSTEP): Take character rather than pointer
	to character.
	(_cpp_check_directive, _cpp_check_linemarker): Update prototypes.

	* cpphash.c (cpp_loookup): Update for new HASHSTEP.

	* cpplex.c (auto_expand_name_space, trigraph_replace,
	backslash_start, handle_newline, parse_name, INIT_TOKEN_STR,
	IMMED_TOKEN, PREV_TOKEN_TYPE, PUSH_TOKEN, REVISE_TOKEN,
	BACKUP_TOKEN, BACKUP_TRIGRAPH, MIGHT_BE_DIRECTIVE,
	KNOWN_DIRECTIVE): Delete.

	(handle_newline, check_long_token, skip_escaped_newlines,
	unterminated): New functions.
	(ACCEPT_CHAR, SAVE_STATE, RESTORE_STATE): New macros.

	(parse_identifier): Was parse_name, new implementation.
	(skip_line_comment, skip_block_comment, skip_whitespace,
	parse_number, parse_string, trigraph_ok, save_comment,
	adjust_column, _cpp_get_line): New implementations.

	(lex_token): New function.  Lexes a token at a time, looking
	forwards.  Contains most of the guts of the old lex_line.
	(lex_line): New implementation, using lex_token to obtain
	individual tokens.
	(cpp_scan_buffer): Use the token's line, not the list's line.

	* cpplib.c (_cpp_check_directive, _cpp_check_linemarker):
	 New implementations.
	(do_assert): Don't bother setting the answer's list's line.
	(cpp_push_buffer): Initialise new pfile and read_ahead members
	of struct cpp_buffer.

	* cpplib.h (cppchar_t): New typedef.
	(struct cpp_buffer): read_ahead, pfile and col_adjust are
	new members.
	(struct lexer_state): New structure that determines the state
	and behaviour of the lexer.
	(IN_DIRECTIVE, KNOWN_DIRECTIVE): New macros.
	(struct cpp_reader): New member "state". Rename
	multiline_string_line and multiline_string_column. Delete
	col_adjust, in_lex_line members.
	(CPP_BUF_COLUMN): Update.

	* gcc.dg/cpp/cmdlne-C.c: Remove bogus warning test.

From-SVN: r36509

1 files changed, 44 insertions, 11 deletions

diff --git a/gcc/cpplib.h b/gcc/cpplib.h
index 9793bc0..7511537 100644
--- a/gcc/cpplib.h
+++ b/gcc/cpplib.h
@@ -215,15 +215,22 @@ struct cpp_toklist
   unsigned short flags;
 };
 
+/* A standalone character.  We may want to make it unsigned for the
+   same reason we use unsigned char - to avoid signedness issues.  */
+typedef int cppchar_t;
+
 struct cpp_buffer
 {
   const unsigned char *cur;	 /* current position */
   const unsigned char *rlimit; /* end of valid data */
-  const unsigned char *buf;	 /* entire buffer */
   const unsigned char *line_base; /* start of current line */
+  cppchar_t read_ahead;		/* read ahead character */
 
+  struct cpp_reader *pfile;	/* Owns this buffer.  */
   struct cpp_buffer *prev;
 
+  const unsigned char *buf;	 /* entire buffer */
+
   /* Filename specified with #line command.  */
   const char *nominal_fname;
 
@@ -238,6 +245,9 @@ struct cpp_buffer
      Used to prohibit unmatched #endif (etc) in an include file.  */
   struct if_stack *if_stack;
 
+  /* Token column position adjustment owing to tabs in whitespace.  */
+  unsigned int col_adjust;
+
   /* Line number at line_base (above). */
   unsigned int lineno;
 
@@ -431,6 +441,31 @@ struct cpp_options
   unsigned char show_column;
 };
 
+struct lexer_state
+{
+  /* Nonzero if first token on line is CPP_HASH.  */
+  unsigned char in_directive;
+
+  /* Nonzero if the directive's # was not in the first column.  Used
+     by -Wtraditional.  */
+  unsigned char indented;
+
+  /* Nonzero if in a directive that takes angle-bracketed headers.  */
+  unsigned char angled_headers;
+
+  /* Nonzero to save comments.  Turned off if discard_comments, and in
+     all directives apart from #define.  */
+  unsigned char save_comments;
+
+  /* Nonzero to get force the lexer to skip newlines.  */
+  unsigned char skip_newlines;
+
+  /* If we're in the subroutine lex_line.  */
+  unsigned char in_lex_line;
+};
+#define IN_DIRECTIVE(pfile) (pfile->state.in_directive)
+#define KNOWN_DIRECTIVE(list) (list->directive != 0)
+
 /* A cpp_reader encapsulates the "state" of a pre-processor run.
    Applying cpp_get_token repeatedly yields a stream of pre-processor
    tokens.  Usually, there is only one cpp_reader object active. */
@@ -440,12 +475,16 @@ struct cpp_reader
   /* Top of buffer stack.  */
   cpp_buffer *buffer;
 
+  /* Lexer state.  */
+  struct lexer_state state;
+
   /* Error counter for exit code */
   unsigned int errors;
 
-  /* Line and column where a newline was first seen in a string constant.  */
-  unsigned int multiline_string_line;
-  unsigned int multiline_string_column;
+  /* Line and column where a newline was first seen in a string
+     constant (multi-line strings).  */
+  unsigned int mls_line;
+  unsigned int mls_column;
 
   /* Current depth in #include directives that use <...>.  */
   unsigned int system_include_depth;
@@ -475,9 +514,6 @@ struct cpp_reader
      be one at a time, so it is per-reader not per-buffer.  */
   const cpp_hashnode *potential_control_macro;
 
-  /* Token column position adjustment owing to tabs in whitespace.  */
-  unsigned int col_adjust;
-
   /* Token list used to store logical lines with new lexer.  */
   cpp_toklist token_list;
 
@@ -557,9 +593,6 @@ struct cpp_reader
      or we might need to write out definitions.  */
   unsigned char save_parameter_spellings;
 
-  /* If we're in lex_line.  */
-  unsigned char in_lex_line;
-
   /* True if output_line_command needs to output a newline.  */
   unsigned char need_newline;
 
@@ -586,7 +619,7 @@ struct cpp_printer
 #define CPP_OPTION(PFILE, OPTION) ((PFILE)->opts.OPTION)
 #define CPP_BUFFER(PFILE) ((PFILE)->buffer)
 #define CPP_BUF_LINE(BUF) ((BUF)->lineno)
-#define CPP_BUF_COLUMN(BUF, CUR) ((CUR) - (BUF)->line_base + pfile->col_adjust)
+#define CPP_BUF_COLUMN(BUF, CUR) ((CUR) - (BUF)->line_base + (BUF)->col_adjust)
 #define CPP_BUF_COL(BUF) CPP_BUF_COLUMN(BUF, (BUF)->cur)
 
 /* Name under which this program was invoked.  */