[01/32] langhooks

Message ID 1310e4bd-0a39-2245-4360-d4546cf4eb14@acm.org
State New
Headers show
Series
  • C++ 20 Modules
Related show

Commit Message

Nathan Sidwell Nov. 3, 2020, 9:13 p.m.
I needed a set of hook interfacing the preprocessor to the language. 
they get called from pieces in c-family.

preprocess_main_file:  we need to know when any forced headers have been 
parsed in order to deal with linemaps and macro visibility

preprocess_options: A way for the language to adjust any preprocessor 
options and alter direct callbacks

preprocess_undef: We need visibility of #undefs

preprocess_deferred_macro: macros from header-units are instantiated 
lazily.  This is the hook for the preprocessor to get that done.

preprocess_token: Even in -E processing, we need to observe the token 
stream in order to load up the macro tables of header units.

c-family's c-lex.c, c-opts.c & c-ppoutput.c get to call these hooks in 
various cases

-- 
Nathan Sidwell

Comments

Martin Sebor via Gcc-patches Nov. 6, 2020, 7:58 p.m. | #1
On 11/3/20 2:13 PM, Nathan Sidwell wrote:
> I needed a set of hook interfacing the preprocessor to the language.

> they get called from pieces in c-family.

>

> preprocess_main_file:  we need to know when any forced headers have

> been parsed in order to deal with linemaps and macro visibility

>

> preprocess_options: A way for the language to adjust any preprocessor

> options and alter direct callbacks

>

> preprocess_undef: We need visibility of #undefs

>

> preprocess_deferred_macro: macros from header-units are instantiated

> lazily.  This is the hook for the preprocessor to get that done.

>

> preprocess_token: Even in -E processing, we need to observe the token

> stream in order to load up the macro tables of header units.

>

> c-family's c-lex.c, c-opts.c & c-ppoutput.c get to call these hooks in

> various cases


LGTM.

jeff

Patch

diff --git c/gcc/c-family/c-lex.c w/gcc/c-family/c-lex.c
index e81e16ddc26..44575473719 100644
--- c/gcc/c-family/c-lex.c
+++ w/gcc/c-family/c-lex.c
@@ -28,7 +28,7 @@  along with GCC; see the file COPYING3.  If not see
 #include "c-pragma.h"
 #include "debug.h"
 #include "file-prefix-map.h" /* remap_macro_filename()  */
-
+#include "langhooks.h"
 #include "attribs.h"
 
 /* We may keep statistics about how long which files took to compile.  */
@@ -274,9 +274,11 @@  cb_define (cpp_reader *pfile, location_t loc, cpp_hashnode *node)
 
 /* #undef callback for DWARF and DWARF2 debug info.  */
 static void
-cb_undef (cpp_reader * ARG_UNUSED (pfile), location_t loc,
-	  cpp_hashnode *node)
+cb_undef (cpp_reader *pfile, location_t loc, cpp_hashnode *node)
 {
+  if (lang_hooks.preprocess_undef)
+    lang_hooks.preprocess_undef (pfile, loc, node);
+
   const struct line_map *map = linemap_lookup (line_table, loc);
   (*debug_hooks->undef) (SOURCE_LINE (linemap_check_ordinary (map), loc),
 			 (const char *) NODE_NAME (node));
diff --git c/gcc/c-family/c-opts.c w/gcc/c-family/c-opts.c
index 120f4489f6c..c8f08d9e014 100644
--- c/gcc/c-family/c-opts.c
+++ w/gcc/c-family/c-opts.c
@@ -1105,9 +1116,11 @@  c_common_post_options (const char **pfilename)
       input_location = UNKNOWN_LOCATION;
     }
 
-  struct cpp_callbacks *cb = cpp_get_callbacks (parse_in);
+  struct cpp_callbacks *cb = cpp_get_callbacks (parse_in);
   cb->file_change = cb_file_change;
   cb->dir_change = cb_dir_change;
+  if (lang_hooks.preprocess_options)
+    lang_hooks.preprocess_options (parse_in);
   cpp_post_options (parse_in);
   init_global_opts_from_cpp (&global_options, cpp_get_options (parse_in));
 
@@ -1169,6 +1182,11 @@  c_common_init (void)
   /* Has to wait until now so that cpplib has its hash table.  */
   init_pragma ();
 
+  struct cpp_callbacks *cb = cpp_get_callbacks (parse_in);
+  cb->user_deferred_macro = lang_hooks.preprocess_deferred_macro;
+  if (!cb->undef)
+    cb->undef = lang_hooks.preprocess_undef;
+
   if (flag_preprocess_only)
     {
       c_finish_options ();
@@ -1550,7 +1568,13 @@  push_command_line_include (void)
       cpp_opts->warn_unused_macros = cpp_warn_unused_macros;
       /* Restore the line map back to the main file.  */
       if (!cpp_opts->preprocessed)
-	cpp_change_file (parse_in, LC_RENAME, this_input_filename);
+	{
+	  cpp_change_file (parse_in, LC_RENAME, this_input_filename);
+	  if (lang_hooks.preprocess_main_file)
+	    /* We're starting the main file.  Inform the FE of that.  */
+	    lang_hooks.preprocess_main_file
+	      (parse_in, line_table, LINEMAPS_LAST_ORDINARY_MAP (line_table));
+	}
 
       /* Set this here so the client can change the option if it wishes,
 	 and after stacking the main file so we don't trace the main file.  */
@@ -1560,14 +1584,19 @@  push_command_line_include (void)
 
 /* File change callback.  Has to handle -include files.  */
 static void
-cb_file_change (cpp_reader * ARG_UNUSED (pfile),
-		const line_map_ordinary *new_map)
+cb_file_change (cpp_reader *reader, const line_map_ordinary *new_map)
 {
   if (flag_preprocess_only)
     pp_file_change (new_map);
   else
     fe_file_change (new_map);
 
+  if (new_map && cpp_opts->preprocessed
+      && lang_hooks.preprocess_main_file && MAIN_FILE_P (new_map)
+      && ORDINARY_MAP_STARTING_LINE_NUMBER (new_map))
+    /* We're starting the main file.  Inform the FE of that.  */
+    lang_hooks.preprocess_main_file (reader, line_table, new_map);
+
   if (new_map 
       && (new_map->reason == LC_ENTER || new_map->reason == LC_RENAME))
     {
diff --git c/gcc/c-family/c-ppoutput.c w/gcc/c-family/c-ppoutput.c
index 44c6f30e06b..e3e0e59fcc7 100644
--- c/gcc/c-family/c-ppoutput.c
+++ w/gcc/c-family/c-ppoutput.c
@@ -21,6 +21,7 @@ 
 #include "coretypes.h"
 #include "c-common.h"		/* For flags.  */
 #include "../libcpp/internal.h"
+#include "langhooks.h"
 #include "c-pragma.h"		/* For parse_in.  */
 #include "file-prefix-map.h"    /* remap_macro_filename()  */
 
@@ -301,125 +302,48 @@  token_streamer::stream (cpp_reader *pfile, const cpp_token *token,
 
 /* Writes out the preprocessed file, handling spacing and paste
    avoidance issues.  */
+
 static void
 scan_translation_unit (cpp_reader *pfile)
 {
-  bool avoid_paste = false;
-  bool do_line_adjustments
-    = cpp_get_options (parse_in)->lang != CLK_ASM
-      && !flag_no_line_commands;
-  bool in_pragma = false;
-  bool line_marker_emitted = false;
+  token_streamer streamer (pfile);
+  uintptr_t filter = 0;
+
+  if (lang_hooks.preprocess_token)
+    filter = lang_hooks.preprocess_token (pfile, NULL, filter);
 
   print.source = NULL;
   for (;;)
     {
-      location_t loc;
-      const cpp_token *token = cpp_get_token_with_location (pfile, &loc);
+      location_t spelling_loc;
+      const cpp_token *token
+	= cpp_get_token_with_location (pfile, &spelling_loc);
 
-      if (token->type == CPP_PADDING)
+      streamer.stream (pfile, token, spelling_loc);
+      if (filter)
 	{
-	  avoid_paste = true;
-	  if (print.source == NULL
-	      || (!(print.source->flags & PREV_WHITE)
-		  && token->val.source == NULL))
-	    print.source = token->val.source;
-	  continue;
+	  unsigned flags = lang_hooks.preprocess_token (pfile, token, filter);
+	  if (flags & lang_hooks::PT_begin_pragma)
+	    streamer.begin_pragma ();
 	}
-
       if (token->type == CPP_EOF)
 	break;
+    }
 
-      /* Subtle logic to output a space if and only if necessary.  */
-      if (avoid_paste)
-	{
-	  int src_line = LOCATION_LINE (loc);
-
-	  if (print.source == NULL)
-	    print.source = token;
-
-	  if (src_line != print.src_line
-	      && do_line_adjustments
-	      && !in_pragma)
-	    {
-	      line_marker_emitted = do_line_change (pfile, token, loc, false);
-	      putc (' ', print.outf);
-	      print.printed = true;
-	    }
-	  else if (print.source->flags & PREV_WHITE
-		   || (print.prev
-		       && cpp_avoid_paste (pfile, print.prev, token))
-		   || (print.prev == NULL && token->type == CPP_HASH))
-	    {
-	      putc (' ', print.outf);
-	      print.printed = true;
-	    }
-	}
-      else if (token->flags & PREV_WHITE)
-	{
-	  int src_line = LOCATION_LINE (loc);
-
-	  if (src_line != print.src_line
-	      && do_line_adjustments
-	      && !in_pragma)
-	    line_marker_emitted = do_line_change (pfile, token, loc, false);
-	  putc (' ', print.outf);
-	  print.printed = true;
-	}
+  if (filter)
+    lang_hooks.preprocess_token (pfile, NULL, filter);
+}
 
-      avoid_paste = false;
-      print.source = NULL;
-      print.prev = token;
-      if (token->type == CPP_PRAGMA)
-	{
-	  const char *space;
-	  const char *name;
-
-	  line_marker_emitted = maybe_print_line (token->src_loc);
-	  fputs ("#pragma ", print.outf);
-	  c_pp_lookup_pragma (token->val.pragma, &space, &name);
-	  if (space)
-	    fprintf (print.outf, "%s %s", space, name);
-	  else
-	    fprintf (print.outf, "%s", name);
-	  print.printed = true;
-	  in_pragma = true;
-	}
-      else if (token->type == CPP_PRAGMA_EOL)
-	{
-	  maybe_print_line (token->src_loc);
-	  in_pragma = false;
-	}
-      else
-	{
-	  if (cpp_get_options (parse_in)->debug)
-	    linemap_dump_location (line_table, token->src_loc, print.outf);
-
-	  if (do_line_adjustments
-	      && !in_pragma
-	      && !line_marker_emitted
-	      && print.prev_was_system_token != !!in_system_header_at (loc)
-	      && !is_location_from_builtin_token (loc))
-	    /* The system-ness of this token is different from the one
-	       of the previous token.  Let's emit a line change to
-	       mark the new system-ness before we emit the token.  */
-	    {
-	      do_line_change (pfile, token, loc, false);
-	      print.prev_was_system_token = !!in_system_header_at (loc);
-	    }
-	  cpp_output_token (token, print.outf);
-	  line_marker_emitted = false;
-	  print.printed = true;
-	}
+class do_streamer : public token_streamer
+{
+ public:
+  uintptr_t filter;
 
-      /* CPP_COMMENT tokens and raw-string literal tokens can
-	 have embedded new-line characters.  Rather than enumerating
-	 all the possible token types just check if token uses
-	 val.str union member.  */
-      if (cpp_token_val_index (token) == CPP_TOKEN_FLD_STR)
-	account_for_newlines (token->val.str.text, token->val.str.len);
+  do_streamer (cpp_reader *pfile, uintptr_t filter)
+    :token_streamer (pfile), filter (filter)
+    {
     }
-}
+};
 
 static void
 directives_only_cb (cpp_reader *pfile, CPP_DO_task task, void *data_, ...)
@@ -427,7 +351,7 @@  directives_only_cb (cpp_reader *pfile, CPP_DO_task task, void *data_, ...)
   va_list args;
   va_start (args, data_);
 
-  token_streamer *streamer = reinterpret_cast <token_streamer *> (data_);
+  do_streamer *streamer = reinterpret_cast <do_streamer *> (data_);
   switch (task)
     {
     default:
@@ -452,6 +376,13 @@  directives_only_cb (cpp_reader *pfile, CPP_DO_task task, void *data_, ...)
 	const cpp_token *token = va_arg (args, const cpp_token *);
 	location_t spelling_loc = va_arg (args, location_t);
 	streamer->stream (pfile, token, spelling_loc);
+	if (streamer->filter)
+	  {
+	    unsigned flags = lang_hooks.preprocess_token
+	      (pfile, token, streamer->filter);
+	    if (flags & lang_hooks::PT_begin_pragma)
+	      streamer->begin_pragma ();
+	  }
       }
       break;
     }
@@ -464,8 +395,13 @@  directives_only_cb (cpp_reader *pfile, CPP_DO_task task, void *data_, ...)
 static void
 scan_translation_unit_directives_only (cpp_reader *pfile)
 {
-  token_streamer streamer (pfile);
+  uintptr_t filter = 0;
+  if (lang_hooks.preprocess_token)
+    filter = lang_hooks.preprocess_token (pfile, NULL, filter);
+  do_streamer streamer (pfile, filter);
   cpp_directive_only_process (pfile, &streamer, directives_only_cb);
+  if (streamer.filter)
+    lang_hooks.preprocess_token (pfile, NULL, streamer.filter);
 }
 
 /* Adjust print.src_line for newlines embedded in output.  */
@@ -564,15 +500,16 @@  print_line_1 (location_t src_loc, const char *special_flags, FILE *stream)
       unsigned char *to_file_quoted =
          (unsigned char *) alloca (to_file_len * 4 + 1);
 
-      print.src_line = LOCATION_LINE (src_loc);
-      print.src_file = file_path;
-
       /* cpp_quote_string does not nul-terminate, so we have to do it
 	 ourselves.  */
       unsigned char *p = cpp_quote_string (to_file_quoted,
 					   (const unsigned char *) file_path,
 					   to_file_len);
       *p = '\0';
+
+      print.src_line = LOCATION_LINE (src_loc);
+      print.src_file = file_path;
+
       fprintf (stream, "# %u \"%s\"%s",
 	       print.src_line, to_file_quoted, special_flags);
 
@@ -678,9 +615,10 @@  cb_define (cpp_reader *pfile, location_t line, cpp_hashnode *node)
 }
 
 static void
-cb_undef (cpp_reader *pfile ATTRIBUTE_UNUSED, location_t line,
-	  cpp_hashnode *node)
+cb_undef (cpp_reader *pfile, location_t line, cpp_hashnode *node)
 {
+  if (lang_hooks.preprocess_undef)
+    lang_hooks.preprocess_undef (pfile, line, node);
   maybe_print_line (line);
   fprintf (print.outf, "#undef %s\n", NODE_NAME (node));
   print.src_line++;
diff --git c/gcc/langhooks-def.h w/gcc/langhooks-def.h
index a909915d018..1285d548050 100644
--- c/gcc/langhooks-def.h
+++ w/gcc/langhooks-def.h
@@ -103,6 +103,11 @@  extern void lhd_finalize_early_debug (void);
 #define LANG_HOOKS_INIT_OPTIONS_STRUCT	hook_void_gcc_optionsp
 #define LANG_HOOKS_INIT_OPTIONS		lhd_init_options
 #define LANG_HOOKS_INITIALIZE_DIAGNOSTICS lhd_initialize_diagnostics
+#define LANG_HOOKS_PREPROCESS_MAIN_FILE NULL
+#define LANG_HOOKS_PREPROCESS_OPTIONS NULL
+#define LANG_HOOKS_PREPROCESS_UNDEF NULL
+#define LANG_HOOKS_PREPROCESS_DEFERRED_MACRO NULL
+#define LANG_HOOKS_PREPROCESS_TOKEN NULL
 #define LANG_HOOKS_REGISTER_DUMPS	lhd_register_dumps
 #define LANG_HOOKS_COMPLAIN_WRONG_LANG_P lhd_complain_wrong_lang_p
 #define LANG_HOOKS_HANDLE_OPTION	lhd_handle_option
@@ -317,6 +322,11 @@  extern void lhd_end_section (void);
   LANG_HOOKS_INIT_OPTIONS_STRUCT, \
   LANG_HOOKS_INIT_OPTIONS, \
   LANG_HOOKS_INITIALIZE_DIAGNOSTICS, \
+  LANG_HOOKS_PREPROCESS_MAIN_FILE, \
+  LANG_HOOKS_PREPROCESS_OPTIONS, \
+  LANG_HOOKS_PREPROCESS_UNDEF, \
+  LANG_HOOKS_PREPROCESS_DEFERRED_MACRO, \
+  LANG_HOOKS_PREPROCESS_TOKEN, \
   LANG_HOOKS_REGISTER_DUMPS, \
   LANG_HOOKS_COMPLAIN_WRONG_LANG_P, \
   LANG_HOOKS_HANDLE_OPTION, \
diff --git c/gcc/langhooks.h w/gcc/langhooks.h
index a35cf21b673..c70c2317c32 100644
--- c/gcc/langhooks.h
+++ w/gcc/langhooks.h
@@ -356,6 +356,29 @@  struct lang_hooks
      global diagnostic context structure.  */
   void (*initialize_diagnostics) (diagnostic_context *);
 
+  /* Beginning the main source file.  */
+  void (*preprocess_main_file) (cpp_reader *, line_maps *,
+				const line_map_ordinary *);
+
+  /* Adjust libcpp options and callbacks.  */
+  void (*preprocess_options) (cpp_reader *);
+
+  /* Undefining a macro.  */
+  void (*preprocess_undef) (cpp_reader *, location_t, cpp_hashnode *);
+
+  /* Define a deferred macro.  */
+  struct cpp_macro *(*preprocess_deferred_macro) (cpp_reader *, location_t,
+						  cpp_hashnode *);
+
+  /* Observer for preprocessing stream.  */
+  uintptr_t (*preprocess_token) (cpp_reader *, const cpp_token *, uintptr_t);
+  /* Various flags it can return about the token.  */
+  enum PT_flags
+    {
+     PT_begin_pragma = 1 << 0
+    };
+  
+
   /* Register language-specific dumps.  */
   void (*register_dumps) (gcc::dump_manager *);