This document mixes HTML and FL
(a KRL, i.e., a Knowledge Representation Language; it is here used in the
preformatted text parts).
It is an input+backup+presentation file for the
Multi-Source Ontology (MSO).
The MSO i) aligns and extends several ontologies, and
ii) can be extended by Web users via the shared KB server
WebKB-2 and its
shared KB (knowledge base) editing protocols.
In this document, "/^" is used instead of "<" and "\." is used instead of ">".
The ontology in this document is original and in construction.
It is part of complementary "ontologies on formal languages".
Table of contents
1. General ontology with values for some grammars
2. Bison grammar for a generic parser of KRLs
This ontology covers the main BNF variants, e.g.,
EBNF of the W3C and
XBNF
(additional modules/documentations:
MATHS,
samples,
discussion).
See also this article that lists some grammar/BNF related notions.
Grammar_element \. excl{ (Statement_of_a_grammar //in this document "\." is used instead of ">" = excl{ Non-lexical-grammar_rule Lexical-grammar_rule }, \. Head_grammar-rule ) (Individual_gTerm_of_a_grammar \. partition { Non-lexical-grammar_individual-gTerm Lexical-grammar_individual-gTerm } ) }; Non-lexical-grammar_rule = NLG_rule, r_part: 1 NLG_rule_left-hand-side 1 NLG_expression 0..1 Statement, rc_: (a fc_list_type_(.{W3C-EBNF,ABNF,XBNF,Grammar},"","","") r_parts: .[NLG_rule_left-hand-side "::=" NLG_expression] ) //A::=B (a fc_list_type_(.{ISO-EBNF},"","","") r_parts: .[NLG_rule_left-hand-side "=" NLG_expression] ); //A = B (a fc_list_type_(.{Yacc, Bison},"","","") r_parts: .[NLG_rule_left-hand-side ":" NLG_expression Statement ";"] ); //A : B Non-lexical-grammar_individual-gTerm = NLG_individual-gTerm, \. excl { (NLG_left-hand-side \. Non-lexical-grammar_non-terminal) (NLG_expression \. excl { (NLG_or-list r_part: 2..* NLG_expression, rc_: a fc_list_type_(.{Grammar},"","|","") //A | B a fc_list_type_(.{Yacc,Bison},"","\n|","") ) (NLG_list r_part: 2..* NLG_expression, rc_: a fc_list_type_(.{Grammar},"","","") ) //A B (NLG_minus r_part: 2 NLG_expression, rc_: a fc_list_type_(.{W3C-EBNF},"","-","") //A - B (a fc_list_type_(.{Grammar},"","-","") r_parts: .[]) ) (NLG_delimited_expression r_part: 1 NLG_expression, rc_: a fc_list_type_(.{Grammar},"(","",")") ) //(A) (NLG_repeated_item r_part: 1 NLG_expression 0..1 NLG_repetition_operator 0..1 Numeral, rc_: (Zero-to-one_NLG-item r_part: 1 NLG_expression, rc_: a fc_list_type_(.{W3C-EBNF},"","","?") //A? a fc_list_type_(.{ISO-EBNF,Grammar},"[","","]") //[A] a fc_list_type_(.{XBNF},"O(","",")") //O(A) a fc_list_type_(.{ABNF},"*1","","") ) //*1A (Zero-to-many_NLG-item r_part: 1 NLG_expression, rc_: a fc_list_type_(.{W3C-EBNF},"","","*") //A* a fc_list_type_(.{ISO-EBNF,Grammar},"{","","}") //{A} a fc_list_type_(.{XBNF),"#(","",")") //#(A) a fc_list_type_(.{ABNF},"*","","") ) //*A (1-to-many_NLG-item r_part: 1 NLG_expression, rc_: a fc_list_type_(.{W3C-EBNF},"","","+") //A+ a fc_list_type_(.{ISO-EBNF,Grammar},"{","","}-") //{A}- a fc_list_type_(.{XBNF},"#(","",")") //#(A) a fc_list_type_(.{ABNF},"1*","","") ) //1*A (N_NLG-item r_part: 1 NLG_expression 1 Numeral, rc_: (a fc_list_type_(.{ISO-EBNF},"","*","") r_parts: .[numeral NLG_expression] ) //N*A (fc_list_type_({Grammar},"","","") r_parts: .[]) ) (N-to-m_NLG-item r_part: 1 NLG_expression 2 numeral, rc_: a fc_list_type_(.{ABNF},"",.[numeral "*" numeral NLG_expression],"" ) //N*M A a fc_list_type_(.{Grammar},"",.[],"") ) ) (NLG_atomic-item \. excl { (NLG_non-terminal r_part: 1..* letter, \. excl { (NLG_start_non-terminal r_part: 1 Uppercase_letter 0..* Letter, rc_: (a fc_string_type_(.{W3C-EBNF},"","") r_part: 1 Uppercase_letter 0..* Letter r_parts: .[Uppercase_letter Letter] ) ) (NLG_non-start_non-terminal rc_: a fc_string_type_({Grammar},"","") ) } ) (NLG_terminal r_part: 1..* Lexical-grammar_characters, rc_: a fc_string_type_(.{Grammar},"","") ) } ) } )//end of NLG_expression NLG_repetition_operator Numeral }; Lexical-grammar_rule r_part: 1 Lexical-grammar_expression 0..1 Statement, rc_: (a f_list_type_(.{Lexical_parser_grammar},"","","") r_parts: .[Lexical-grammar_characters Statement] ) (a f_list_type_(.{Grammar},"","","") r_parts: .[Lexical-grammar_characters]) Lexical-grammar_individual-gTerm \. excl { (Lexical-grammar_characters \. (quoted_string r_part: 1..* letter, \. (single_quoted_string rc_: (a fc_string_type_(.{Grammar},"'","'") r_part: 1..* f_character_with_escape_for("'") ) ) (double_quoted_string rc_: (a fc_string_type_(.{Grammar},'"','"') r_part: 1..* f_character_with_escape_for('"') ) ) ) (character_or-set r_part: 1..* character_range, rc_: a fc_string_type_(.{Grammar},"[","]") ) (character_exclusion r_part: 1..* character_range, rc_: a fc_string_type_(.{Grammar},"[^","]") ) (letter_or_letter-code \. (letter \. letter_range_1 letter_range_2) (letter_code \. (letter_code_with_hexadecimal r_part: 1 hexadecimal, \. letter-code__range_1 letter-code_range_2 rc_: a fc_string_type_(.{Grammar},"#","") ) ) ) ) (character_range \. (letter_range r_part: 1 letter_range_1 0..1 letter_range_2, rc_: a fc_unspaced-list_type_(.{Grammar},"","-","") ) (letter_range r_part: 1 letter-code__range_1 0..1 letter-code_range_2; rc_: a fc_unspaced-list_type_(.{Grammar},"","-","") ) ) (space_or_fully-delimited-comment \. (space rc_: a fc_character_type_(.{Grammar}," ") a fc_character_type_(.{Grammar},"\t") a fc_character_type_(.{Grammar},"\n") a fc_character_type_(.{Grammar},"\r") ) (fully-delimited-comment r_part: 0..* character, rc_: a fc_string_type_(.{Grammar},"/*","*/") ) ) (comment \. fully-delimited-comment r_part: 0..* character, (line-comment rc_: a fc_string_type_(.{Grammar},"//","")) ) //(delimitor \. (begin_mark) (end_mark) ) (character \. letter) };
The following code is not in FL but in
GNU bison.
The high level ideas for this parser are given in
this section of this article.
%token BOOLEAN_LIKE_VALUE NUMBER STRING TIME COORDINATE_LIKE_NUMBER
%token ID NAME VAR TOKEN_OPERATOR
%token TOP_PHRASE_begin TOP_PHRASE_end
%token INDIVIDUAL_TERM_begin INDIVIDUAL_TERM_end PHRASE_TERM_begin PHRASE_TERM_end
%token PREFIX_FCT_LIKE_TERM_ARGS_begin PREFIX_FCT_LIKE_TERM_ARGS_end
%token PREFIX_FCT_LIKE_TERM_ARG_begin PREFIX_FCT_LIKE_TERM_ARG_end
%token PREFIX_LIST_LIKE_TERM_begin PREFIX_LIST_LIKE_TERM_end
%token POSTFIX_FCT_LIKE_TERM_ARGS_begin POSTFIX_FCT_LIKE_TERM_ARGS_end
%token POSTFIX_LIST_LIKE_TERM_ARGS_begin POSTFIX_LIST_LIKE_TERM_ARGS_end
%token KEYED_INFIX_TERM_begin KEYED_INFIX_TERM_end
%token COLLECTION_begin COLLECTION_end ARGS_sep
%token MARKUP_TYPE_begin MARKUP_TYPE_end MARKUP_VALUE_begin MARKUP_ATTRS_end
%nonassoc NON_ASSOC_OPERATOR_LEVEL_5
%nonassoc NON_ASSOC_OPERATOR_LEVEL_4
%nonassoc NON_ASSOC_OPERATOR_LEVEL_3 /* e.g., VAR__SET_TO */
%nonassoc NON_ASSOC_OPERATOR_LEVEL_2
%nonassoc NON_ASSOC_OPERATOR_LEVEL_1
%right RIGHT_ASSOC_OPERATOR_LEVEL_5
%right RIGHT_ASSOC_OPERATOR_LEVEL_4
%right RIGHT_ASSOC_OPERATOR_LEVEL_3 THEN ELSE
%right RIGHT_ASSOC_OPERATOR_LEVEL_2
%right RIGHT_ASSOC_OPERATOR_LEVEL_1
%left LEFT_ASSOC_OPERATOR_LEVEL_9
%left LEFT_ASSOC_OPERATOR_LEVEL_8 /* e.g., "<=>" "<=" "=>" */
%left LEFT_ASSOC_OPERATOR_LEVEL_7 /* e.g., "or" */
%left LEFT_ASSOC_OPERATOR_LEVEL_6 /* e.g., "and" */
%left LEFT_ASSOC_OPERATOR_LEVEL_5 /* e.g., '<' '>' '=' "=<" ">=" "!=" */
%left LEFT_ASSOC_OPERATOR_LEVEL_4 /* e.g., '+' '-' */
%left LEFT_ASSOC_OPERATOR_LEVEL_3 /* e.g., '*' '/' '%' */
%left LEFT_ASSOC_OPERATOR_LEVEL_2 /* e.g., '!' NOT */
%left LEFT_ASSOC_OPERATOR_LEVEL_1
%left UMINUS
%expect 0
%start _TOP_PHRASES
%%
_TOP_PHRASES : | TOP_PHRASE | TOP_PHRASE TOP_PHRASE_sep ;
TOP_PHRASES : TOP_PHRASE
| TOP_PHRASES TOP_PHRASE_bce
| TOP_PHRASES TOP_PHRASE_sep TOP_PHRASE_bce
| TOP_PHRASES TOP_PHRASE_sep TERM_not1 ;
;
TOP_PHRASE : TOP_PHRASE_bce | TERM ;
TOP_PHRASE_bce: TOP_PHRASE_begin TERM TOP_PHRASE_end | TERM_bce ;
TERM : TERM_1 | TERM_not1 ;
TERM_1 : TERM_bce | TOKEN ;
TERM_not1: OPERATOR_bceOrToken ARGS_c %prec UMINUS
| TERM_1 PREFIX_FCT_LIKE_TERM_ARGS_bce
| TERM_1 OPERATOR_bceOrToken ARGS
| TERM_1 ARGS_sep ARGS ;
TERM_bce : INDIVIDUAL_TERM_begin TERM INDIVIDUAL_TERM_end /* (...) */
| PHRASE_TERM_begin TERM PHRASE_TERM_end /* [...] */
| PREFIX_LIST_LIKE_TERM_bce | POSTFIX_FCT_LIKE_TERM_bce/* (_. ..) | (_ ...) */
| POSTFIX_LIST_LIKE_TERM_bce | KEYED_INFIX_TERM_bce /* (._ ..) | (@..@op..)*/
| COLLECTION_bce /* .(...) .{...} */
| MARKUP_bce ; /* parts */
PREFIX_FCT_LIKE_TERM_ARGS_bce:
PREFIX_FCT_LIKE_TERM_ARGS_begin ARGS_Nsup1 PREFIX_FCT_LIKE_TERM_ARGS_end
| PREFIX_FCT_LIKE_TERM_ARG_begin ARG_TERM_1 PREFIX_FCT_LIKE_TERM_ARG_end
| PREFIX_FCT_LIKE_TERM_ARG_begin ARG_TERM_1 ;
PREFIX_LIST_LIKE_TERM_bce : PREFIX_LIST_LIKE_TERM_begin TERM_1_AS_OPERATOR ARGS/*(_. ...)*/
PREFIX_LIST_LIKE_TERM_end ;
POSTFIX_FCT_LIKE_TERM_bce : POSTFIX_FCT_LIKE_TERM_ARGS_begin ARGS /*(_ ...)*/
POSTFIX_FCT_LIKE_TERM_ARGS_end TERM_1_AS_OPERATOR ;
POSTFIX_LIST_LIKE_TERM_bce: POSTFIX_LIST_LIKE_TERM_ARGS_begin ARGS TERM_1_AS_OPERATOR
POSTFIX_LIST_LIKE_TERM_ARGS_end ; /*(._ ...)*/
KEYED_INFIX_TERM_bce : KEYED_INFIX_TERM_begin ARGS KEYED_OPERATOR ARGS
KEYED_INFIX_TERM_end ;
COLLECTION_bce : COLLECTION_begin ARGS COLLECTION_end ; /*.(...) .{...}*/
MARKUP_bce : MARKUP_TYPE_begin/*e.g. ""*/
MARKUP_PARTS MARKUP_TYPE_end /* e.g. " " */ ;
MARKUP_ATTRS: MARKUP_ATTRS MARKUP_ATTR ;
MARKUP_ATTR: ID MARKUP_VALUE_begin CONSTANT ;
MARKUP_PARTS: MARKUP_PARTS MARKUP_bce ;
KEYED_OPERATOR : KEYED_OPERATOR_be | KEYED_OPERATOR_c ;
KEYED_OPERATOR_be: KEYED_OPERATOR_begin KEYED_OPERATOR_c _KEYED_OPERATOR_end ;
KEYED_OPERATOR_c : KEY TERM_1_AS_OPERATOR ;
KEY : REFERENCE ;
ARGS_Nsup1 : ARG_TERM_1 ARGS_sep ARGS_cs | ARG_TERM_1 ARGS_c ;
ARGS : ARGS_cs | ARGS_c ;
ARGS_cs : ARG | ARGS_cs ARGS_sep ARG_TERM_1 ;
ARGS_c : ARG_bce | ARGS_c ARG_bce ;
ARG_TERM_1: ARG_bce | ARG_1c ; /*fct def/call such as isolated or not key + param name */
ARG_bce : ARG_begin ARG_c ARG_end;
ARG_1c : TERM_1
TERM_1_AS_OPERATOR : TERM_1 ;
OPERATOR_bceOrToken: OPERATOR_bce | OPERATOR_TOKEN ;
OPERATOR_bce : OPERATOR_begin TERM OPERATOR_end | OPERATOR_prefix TERM_1 ;
OPERATOR_TOKEN: NON_ASSOC_OPERATOR_LEVEL_5 | NON_ASSOC_OPERATOR_LEVEL_4
| NON_ASSOC_OPERATOR_LEVEL_3 | NON_ASSOC_OPERATOR_LEVEL_2
| NON_ASSOC_OPERATOR_LEVEL_1
| RIGHT_ASSOC_OPERATOR_LEVEL_5 | RIGHT_ASSOC_OPERATOR_LEVEL_4
| RIGHT_ASSOC_OPERATOR_LEVEL_3 | RIGHT_ASSOC_OPERATOR_LEVEL_2
| RIGHT_ASSOC_OPERATOR_LEVEL_1
| LEFT_ASSOC_OPERATOR_LEVEL_9 | LEFT_ASSOC_OPERATOR_LEVEL_8
| LEFT_ASSOC_OPERATOR_LEVEL_7 | LEFT_ASSOC_OPERATOR_LEVEL_6
| LEFT_ASSOC_OPERATOR_LEVEL_5 | LEFT_ASSOC_OPERATOR_LEVEL_4
| LEFT_ASSOC_OPERATOR_LEVEL_3 | LEFT_ASSOC_OPERATOR_LEVEL_2
| LEFT_ASSOC_OPERATOR_LEVEL_1 ;
TOKEN : OPERATOR_TOKEN | TOKEN_NOT_OPERATOR ;
TOKEN_NOT_OPERATOR: REFERENCE | CONSTANT /*CONCRETE_VALUE*/;
REFERENCE : ID | NAME | VAR ;
CONSTANT : BOOLEAN_LIKE_VALUE | NUMBER | STRING | TIME
| COORDINATE_LIKE_NUMBER ;
%%