glsl/glcpp: Correctly parse directives with intervening comments

It's legal (though highly bizarre) for a pre-processor directive to look like
this:

	#  /* why? */ define FOO bar

This behavior comes about since the specification defines separate logical
phases in a precise order, and comment-removal occurs in a phase before the
identification of directives.

Our implementation does not use an actual separate phase for comment removal,
so some extra care is necessary to correctly parse this. What we want is for
'#' to introduce a directive iff it is the first token on a line, (ignoring
whitespace and comments). Previously, we had a lexical rule that worked only
for whitespace (not comments) with the following regular expression to find a
directive-introducing '#' at the beginning of a line:

	HASH		^{HSPACE}*#{HSPACE}*

In this commit, we switch to instead use a simple literal match of '#' to
return a HASH_TOKEN token and add a new <HASH> start condition for whenever
the HASH_TOKEN is the first non-space token of a line. This requires the
addition of the new bit of state: first_non_space_token_this_line.

This approach has a couple of implications on the glcpp parser:

	1. The parser now sees two separate tokens, (such as HASH_TOKEN and
	   HASH_DEFINE) where it previously saw one token (HASH_DEFINE) for
	   the sequence "#define". This is a straightforward change throughout
	   the grammar.

	2. The parser may now see a SPACE token before the HASH_TOKEN token of
	   a directive. Previously the lexical regular expression for {HASH}
	   would eat up the space and there would be no SPACE token.

This second implication is a bit of a nuisance for the parser. It causes a
SPACE token to appear in a production of the grammar with the following two
definitions of a control_line:

	control_line
	SPACE control_line

This is really ugly, since normally a space would simply be a token
separator, so it wouldn't appear in the tokens of a production. This leads to
a further problem with interleaved spaces and comments:

	/* ... */    /* ... */ #define /* ..*/

For this, we must not return several consecutive SPACE tokens, or else we would need an arbitrary number of new productions:

	SPACE SPACE control_line
	SPACE SPACE SPACE control_line
	ad nauseam

To avoid this problem, in this commit we also change the lexer to emit only a
single SPACE token for any series of consecutive spaces, (whether from actual
whitespace or comments). For this compression, we add a new bit of parser
state: last_token_was_space. And we also update the expected results of all
necessary test cases for the new compression of space tokens.

Fortunately, the compression of spaces should not lead to any semantic changes
in terms of what the eventual GLSL compiler sees.

So there's a lot happening in this commit, (particularly for such a tiny
feature). But fortunately, the lexer itself is looking cleaner than ever. The
only ugly bit is all the state updating, but it is at least isolated to a
single shared function.

Of course, a new "make check" test is added for the new feature, (directives
with comments and whitespace interleaved in many combinations).

And this commit fixes the following Khronos GLES3 CTS tests:

	function_definition_with_comments_vertex
	function_definition_with_comments_fragment

Reviewed-by: Jordan Justen <[email protected]>

1 files changed, 64 insertions, 51 deletions

diff --git a/src/glsl/glcpp/glcpp-parse.y b/src/glsl/glcpp/glcpp-parse.y
index 7454fb0112f..2952bf84d8d 100644
--- a/src/glsl/glcpp/glcpp-parse.y
+++ b/src/glsl/glcpp/glcpp-parse.y
@@ -167,11 +167,11 @@ add_builtin_define(glcpp_parser_t *parser, const char *name, int value);
 
 	/* We use HASH_TOKEN, not HASH to avoid a conflict with the <HASH>
          * start condition in the lexer. */
-%token COMMA_FINAL DEFINED ELIF_EXPANDED HASH_TOKEN HASH_DEFINE FUNC_IDENTIFIER OBJ_IDENTIFIER HASH_ELIF HASH_ELSE HASH_ENDIF HASH_IF HASH_IFDEF HASH_IFNDEF HASH_LINE HASH_UNDEF HASH_VERSION IDENTIFIER IF_EXPANDED INTEGER INTEGER_STRING LINE_EXPANDED NEWLINE OTHER PLACEHOLDER SPACE
+%token COMMA_FINAL DEFINED ELIF_EXPANDED HASH_TOKEN HASH_DEFINE FUNC_IDENTIFIER OBJ_IDENTIFIER HASH_ELIF HASH_ELSE HASH_ENDIF HASH_ERROR HASH_IF HASH_IFDEF HASH_IFNDEF HASH_LINE HASH_PRAGMA HASH_UNDEF HASH_VERSION HASH_GARBAGE IDENTIFIER IF_EXPANDED INTEGER INTEGER_STRING LINE_EXPANDED NEWLINE OTHER PLACEHOLDER SPACE
 %token PASTE
 %type <ival> INTEGER operator SPACE integer_constant
 %type <expression_value> expression
-%type <str> IDENTIFIER FUNC_IDENTIFIER OBJ_IDENTIFIER INTEGER_STRING OTHER
+%type <str> IDENTIFIER FUNC_IDENTIFIER OBJ_IDENTIFIER INTEGER_STRING OTHER HASH_ERROR HASH_PRAGMA
 %type <string_list> identifier_list
 %type <token> preprocessing_token conditional_token
 %type <token_list> pp_tokens replacement_list text_line conditional_tokens
@@ -197,27 +197,14 @@ input:
 ;
 
 line:
-	control_line {
-		ralloc_asprintf_rewrite_tail (&parser->output, &parser->output_length, "\n");
-	}
-|	HASH_LINE {
-		glcpp_parser_resolve_implicit_version(parser);
-	} pp_tokens NEWLINE {
-
-		if (parser->skip_stack == NULL ||
-		    parser->skip_stack->type == SKIP_NO_SKIP)
-		{
-			_glcpp_parser_expand_and_lex_from (parser,
-							   LINE_EXPANDED, $3);
-		}
-	}
+	control_line
+|	SPACE control_line
 |	text_line {
 		_glcpp_parser_print_expanded_token_list (parser, $1);
 		ralloc_asprintf_rewrite_tail (&parser->output, &parser->output_length, "\n");
 		ralloc_free ($1);
 	}
 |	expanded_line
-|	HASH_TOKEN non_directive
 ;
 
 expanded_line:
@@ -264,27 +251,45 @@ define:
 ;
 
 control_line:
-	HASH_DEFINE {
+	control_line_success {
+		ralloc_asprintf_rewrite_tail (&parser->output, &parser->output_length, "\n");
+	}
+|	control_line_error
+|	HASH_TOKEN HASH_LINE {
+		glcpp_parser_resolve_implicit_version(parser);
+	} pp_tokens NEWLINE {
+
+		if (parser->skip_stack == NULL ||
+		    parser->skip_stack->type == SKIP_NO_SKIP)
+		{
+			_glcpp_parser_expand_and_lex_from (parser,
+							   LINE_EXPANDED, $4);
+		}
+	}
+;
+
+control_line_success:
+	HASH_TOKEN HASH_DEFINE {
 		glcpp_parser_resolve_implicit_version(parser);
 	} define
-|	HASH_UNDEF {
+|	HASH_TOKEN HASH_UNDEF {
 		glcpp_parser_resolve_implicit_version(parser);
 	} IDENTIFIER NEWLINE {
 		macro_t *macro;
-		if (strcmp("__LINE__", $3) == 0
-		    || strcmp("__FILE__", $3) == 0
-		    || strcmp("__VERSION__", $3) == 0)
+		if (strcmp("__LINE__", $4) == 0
+		    || strcmp("__FILE__", $4) == 0
+		    || strcmp("__VERSION__", $4) == 0)
 			glcpp_error(& @1, parser, "Built-in (pre-defined)"
 				    " macro names can not be undefined.");
 
-		macro = hash_table_find (parser->defines, $3);
+		macro = hash_table_find (parser->defines, $4);
 		if (macro) {
-			hash_table_remove (parser->defines, $3);
+			hash_table_remove (parser->defines, $4);
 			ralloc_free (macro);
 		}
-		ralloc_free ($3);
+		ralloc_free ($4);
 	}
-|	HASH_IF {
+|	HASH_TOKEN HASH_IF {
 		glcpp_parser_resolve_implicit_version(parser);
 	} conditional_tokens NEWLINE {
 		/* Be careful to only evaluate the 'if' expression if
@@ -298,7 +303,7 @@ control_line:
 		    parser->skip_stack->type == SKIP_NO_SKIP)
 		{
 			_glcpp_parser_expand_and_lex_from (parser,
-							   IF_EXPANDED, $3);
+							   IF_EXPANDED, $4);
 		}	
 		else
 		{
@@ -306,7 +311,7 @@ control_line:
 			parser->skip_stack->type = SKIP_TO_ENDIF;
 		}
 	}
-|	HASH_IF NEWLINE {
+|	HASH_TOKEN HASH_IF NEWLINE {
 		/* #if without an expression is only an error if we
 		 *  are not skipping */
 		if (parser->skip_stack == NULL ||
@@ -316,21 +321,21 @@ control_line:
 		}	
 		_glcpp_parser_skip_stack_push_if (parser, & @1, 0);
 	}
-|	HASH_IFDEF {
+|	HASH_TOKEN HASH_IFDEF {
 		glcpp_parser_resolve_implicit_version(parser);
 	} IDENTIFIER junk NEWLINE {
-		macro_t *macro = hash_table_find (parser->defines, $3);
-		ralloc_free ($3);
+		macro_t *macro = hash_table_find (parser->defines, $4);
+		ralloc_free ($4);
 		_glcpp_parser_skip_stack_push_if (parser, & @1, macro != NULL);
 	}
-|	HASH_IFNDEF {
+|	HASH_TOKEN HASH_IFNDEF {
 		glcpp_parser_resolve_implicit_version(parser);
 	} IDENTIFIER junk NEWLINE {
-		macro_t *macro = hash_table_find (parser->defines, $3);
-		ralloc_free ($3);
-		_glcpp_parser_skip_stack_push_if (parser, & @2, macro == NULL);
+		macro_t *macro = hash_table_find (parser->defines, $4);
+		ralloc_free ($4);
+		_glcpp_parser_skip_stack_push_if (parser, & @3, macro == NULL);
 	}
-|	HASH_ELIF conditional_tokens NEWLINE {
+|	HASH_TOKEN HASH_ELIF conditional_tokens NEWLINE {
 		/* Be careful to only evaluate the 'elif' expression
 		 * if we are not skipping. When we are skipping, we
 		 * simply change to a 0-valued 'elif' on the skip
@@ -342,7 +347,7 @@ control_line:
 		    parser->skip_stack->type == SKIP_TO_ELSE)
 		{
 			_glcpp_parser_expand_and_lex_from (parser,
-							   ELIF_EXPANDED, $2);
+							   ELIF_EXPANDED, $3);
 		}
 		else if (parser->skip_stack &&
 		    parser->skip_stack->has_else)
@@ -355,7 +360,7 @@ control_line:
 							    "elif", 0);
 		}
 	}
-|	HASH_ELIF NEWLINE {
+|	HASH_TOKEN HASH_ELIF NEWLINE {
 		/* #elif without an expression is an error unless we
 		 * are skipping. */
 		if (parser->skip_stack &&
@@ -375,7 +380,7 @@ control_line:
 			glcpp_warning(& @1, parser, "ignoring illegal #elif without expression");
 		}
 	}
-|	HASH_ELSE { parser->lexing_directive = 1; } NEWLINE {
+|	HASH_TOKEN HASH_ELSE { parser->lexing_directive = 1; } NEWLINE {
 		if (parser->skip_stack &&
 		    parser->skip_stack->has_else)
 		{
@@ -388,24 +393,36 @@ control_line:
 				parser->skip_stack->has_else = true;
 		}
 	}
-|	HASH_ENDIF {
+|	HASH_TOKEN HASH_ENDIF {
 		_glcpp_parser_skip_stack_pop (parser, & @1);
 	} NEWLINE
-|	HASH_VERSION integer_constant NEWLINE {
+|	HASH_TOKEN HASH_VERSION integer_constant NEWLINE {
 		if (parser->version_resolved) {
 			glcpp_error(& @1, parser, "#version must appear on the first line");
 		}
-		_glcpp_parser_handle_version_declaration(parser, $2, NULL, true);
+		_glcpp_parser_handle_version_declaration(parser, $3, NULL, true);
 	}
-|	HASH_VERSION integer_constant IDENTIFIER NEWLINE {
+|	HASH_TOKEN HASH_VERSION integer_constant IDENTIFIER NEWLINE {
 		if (parser->version_resolved) {
 			glcpp_error(& @1, parser, "#version must appear on the first line");
 		}
-		_glcpp_parser_handle_version_declaration(parser, $2, $3, true);
+		_glcpp_parser_handle_version_declaration(parser, $3, $4, true);
 	}
 |	HASH_TOKEN NEWLINE {
 		glcpp_parser_resolve_implicit_version(parser);
 	}
+|	HASH_TOKEN HASH_PRAGMA NEWLINE {
+		ralloc_asprintf_rewrite_tail (&parser->output, &parser->output_length, "#%s", $2);
+	}
+;
+
+control_line_error:
+	HASH_TOKEN HASH_ERROR NEWLINE {
+		glcpp_error(& @1, parser, "#%s", $2);
+	}
+|	HASH_TOKEN HASH_GARBAGE pp_tokens NEWLINE  {
+		glcpp_error (& @1, parser, "Illegal non-directive after #");
+	}
 ;
 
 integer_constant:
@@ -617,12 +634,6 @@ text_line:
 |	pp_tokens NEWLINE
 ;
 
-non_directive:
-	pp_tokens NEWLINE {
-		yyerror (& @1, parser, "Invalid tokens after #");
-	}
-;
-
 replacement_list:
 	/* empty */ { $$ = NULL; }
 |	pp_tokens
@@ -1313,7 +1324,9 @@ glcpp_parser_create (const struct gl_extensions *extensions, gl_api api)
 	parser->active = NULL;
 	parser->lexing_directive = 0;
 	parser->space_tokens = 1;
-        parser->last_token_was_newline = 0;
+	parser->last_token_was_newline = 0;
+	parser->last_token_was_space = 0;
+	parser->first_non_space_token_this_line = 1;
 	parser->newline_as_space = 0;
 	parser->in_control_line = 0;
 	parser->paren_count = 0;