Further consolidated C23

Author: james-pre

grammars/c23/language.bnf renamed to grammars/c23.bnf

@@ -47,8 +47,6 @@ keyword = "alignas" | "alignof" | "auto" | "bool"
 
 universal_character_name = "\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}";
 
-identifier = "[_a-zA-Z]\w*";
-
 constant =
 | integer_constant 
 | floating_constant 
@@ -447,7 +445,6 @@ iteration_statement =
 
 jump_statement = (("goto" identifier) | "continue" | "break" | ("return" expression?)) ";";
 
-##root translation_unit
 translation_unit = external_declaration;
 
 external_declaration = function_definition | declaration;
@@ -460,3 +457,158 @@ n_char_sequence = {digit | nondigit};
 n_wchar_sequence = {digit | nondigit};
 d_char_sequence = {digit | nondigit};
 d_wchar_sequence = {digit | nondigit};
+
+group_part =
+| control_line
+| if_section
+| text_line
+| ("#" non_directive);
+
+if_section = if_group elif_group* else_group? endif_line;
+
+if_group =
+| ("#if\b" constant_expression group_part*)
+| ("#ifdef\b" identifier group_part*)
+| ("#ifndef\b" identifier group_part*);
+##groups if_group %#if %#ifdef %#ifndef
+
+elif_group =
+| ("#elif\b" constant_expression group_part*)
+| ("#elifdef\b" identifier group_part*)
+| ("#elifndef\b" identifier group_part*);
+##groups elif_group %#elif %#elifdef %#elifndef
+
+else_group = "#else\b" group_part*;
+
+endif_line = "#endif\b";
+
+control_line = "#" (
+| ("include\b" header_name)
+| ("embed\b" header_name)
+| ("define\b" identifier replacement_list)
+| ("define\b" identifier "\(" identifier_list? "\)" replacement_list)
+| ("define\b" identifier "\(" "\.\.\." "\)" replacement_list)
+| ("define\b" identifier "\(" identifier_list "," "\.\.\." "\)" replacement_list)
+| ("undef\b" identifier)
+| ("line\b" pp_tokens)
+| ("error\b" preprocessing_token*)
+| ("warning\b" preprocessing_token*)
+| ("pragma\b" preprocessing_token*)
+);
+
+text_line = pp_tokens;
+
+non_directive = pp_tokens;
+
+# a ( character not immediately preceded by white space
+# TODO: Actually do a look-behind and use this
+# lparen = "\(";
+
+replacement_list = preprocessing_token*;
+
+pp_tokens = preprocessing_token preprocessing_token*;
+
+identifier_list = identifier {"," identifier};
+
+pp_parameter = pp_parameter_name pp_parameter_clause?;
+
+pp_parameter_name = pp_standard_parameter | pp_prefixed_parameter;
+
+pp_standard_parameter = identifier;
+
+pp_prefixed_parameter = identifier "::" identifier;
+
+pp_parameter_clause = "\(" pp_balanced_token* "\)";
+
+pp_balanced_token =
+| __pp_token_no_grouping
+| ("\(" pp_balanced_token* "\)")
+| ("\[" pp_balanced_token* "\]")
+| ("\{" pp_balanced_token* "\}");
+
+# any pp_token other than a parenthesis, a bracket, or a brace
+__pp_token_no_grouping =
+| __pp_token_base
+| __punctuator_base
+| __punctuator_angle_brackets;
+
+embed_parameter_sequence = pp_parameter*;
+
+defined_macro_expression = "defined\b" (identifier | ("\(" identifier "\)"));
+
+# any preprocessing_token other than >
+h_preprocessing_token = 
+| __pp_token_base
+| __punctuator_base
+| __punctuator_grouping;
+
+h_pp_tokens = h_preprocessing_token*;
+
+header_name_tokens = string_literal | ("<" h_pp_tokens ">");
+
+has_include_expression = "__has_include\b" "\(" (header_name | header_name_tokens) "\)";
+
+has_embed_expression =
+| ("__has_embed\b" "\(" (header_name embed_parameter_sequence?) "\)")
+| ("__has_embed\b" "\(" (header_name_tokens pp_balanced_token*) "\)");
+
+has_c_attribute_express = "__has_c_attribute\b" "\(" pp_tokens "\)";
+
+va_opt_replacement = "__VA_OPT__\b" "\(" preprocessing_token* "\)";
+
+standard_pragma = "#" "pragma\b" "STDC\b" (
+| ("FP_CONTRACT\b" on_off_switch)
+| ("FENV_ACCESS\b" on_off_switch)
+| ("FENV_DEC_ROUND\b" dec_direction)
+| ("FENV_ROUND\b" direction)
+| ("CX_LIMITED_RANGE\b" on_off_switch)
+);
+
+on_off_switch = "ON\b" | "OFF\b" | "DEFAULT\b";
+
+direction =
+| "FE_DOWNWARD\b"
+| "FE_TONEAREST\b"
+| "FE_TONEARESTFROMZERO\b" 
+| "FE_TOWARDZERO\b"
+| "FE_UPWARD\b"
+| "FE_DYNAMIC\b";
+
+dec_direction =
+| "FE_DEC_DOWNWARD\b"
+| "FE_DEC_TONEAREST\b"
+| "FE_DEC_TONEARESTFROMZERO\b" 
+| "FE_DEC_TOWARDZERO\b"
+| "FE_DEC_UPWARD\b"
+| "FE_DEC_DYNAMIC\b";
+
+preprocessing_token = __pp_token_base | punctuator;
+#| each universal_character_name that cannot be one of the above 
+#| each non_white_space character that cannot be one of the above
+
+__pp_token_base =
+| header_name
+| identifier
+| pp_number 
+| character_constant
+| string_literal;
+
+header_name = __header_name | string_literal;
+
+__header_name = '<[^\n>]*>|"[^\n\"]*"';
+
+# header_name = ("<" h_char_sequence ">") | ('"' q_char_sequence '"');
+
+# h_char_sequence = h_char*;
+
+# # any member of the source character set except the character and >
+# h_char = digit | nondigit | __punctuator_base | __punctuator_grouping | __punctuator_left_angle_brackets;
+
+# q_char_sequence = q_char*;
+
+# # any member of the source character set except the character and "
+# q_char = digit | nondigit | punctuator;
+
+pp_number = "\.?[0-9](['\w]|(e|E|p|P)(\+|-)|\.)*";
+
+identifier = "[_a-zA-Z]\w*";