volksdata/src/codec/grammar_ttl.y

%include {

/** @brief Lemon parser grammar for Turtle.
 *
 * The `lemon' parser generator executable must be in your PATH:
 * https://sqlite.org/src/doc/trunk/doc/lemon.html
 *
 * To generate the parser, run: `make parsers'
 *
 * TTL EBNF: https://www.w3.org/TeamSubmission/turtle/#sec-grammar-grammar
 */

#include "codec.h"
}

%name TTLParse

%stack_overflow {
    log_error ("Stack oveflow in TTL parsing.");
    state->rc = LSUP_MEM_ERR;
}

%parse_failure {
    log_error ("TTL parse error. Cannot continue.");
    state->rc = LSUP_PARSE_ERR;
}

%syntax_error {
    log_warn ("Syntax error. Attempting recovery.");
}

%stack_size CHUNK_SIZE

/*
%syntax_error {
    if (TOKEN[0]) log_error ("near \"%T\": syntax error", &TOKEN);
    else log_error ("incomplete input");
}
*/

%token_prefix "T_"
%token_type { char * }
%token_destructor { free ($$); }

/* NULL-terminated array of object term handles. */
%type objList           { LSUP_Term ** }
%destructor objList     {
    for (size_t i = 0; $$[i]; i++) {
        LSUP_term_free ($$[i]);
    }
}

%default_type           { char * }

%extra_argument         { LSUP_TTLParserState *state }

%left WS .
%left EOS .
%left SEMICOLON .
%left COMMA .
%nonassoc PFX .
%nonassoc COLON .

/*
 * Rules.
 */

turtleDoc   ::= statements EOF .

statements  ::= statements statement .
statements  ::= .

statement   ::= directive .
statement   ::= triples .

directive 	::= prefixID EOS .
directive   ::= base EOS .

prefixID    ::= PREFIX PFX(P) IRIREF(N) . {
                LSUP_nsmap_add (state->nsm, P, N);
            }
prefixID    ::= PREFIX COLON IRIREF(N) . {
                LSUP_nsmap_add (state->nsm, "", N);
            }

base        ::= BASE IRIREF(D) . {
                state->base = LSUP_iriref_new (D, NULL);
            }

triples 	::= subject(S) predObjList(L) EOS . {
                size_t ct = LSUP_spo_list_add_triples (state->it, S, L);
                state->ct += ct;
                state->rc = LSUP_OK;
                log_trace ("Added %lu triples.", ct);
                LSUP_term_free (S);
                LSUP_pred_obj_list_free (L);
            }

%type predObjList       { LSUP_PredObjList * }
%destructor predObjList { LSUP_pred_obj_list_free ($$); }
predObjList(A) ::= predicate(P) objectList(O) SEMICOLON . {
                A = LSUP_pred_obj_list_new();
                LSUP_pred_obj_list_add (A, P, O);
            }
predObjList(A) ::= predicate(P) objectList(O) . [SEMICOLON] {
                A = LSUP_pred_obj_list_new();
                LSUP_pred_obj_list_add (A, P, O);
            }
predObjList(A) ::= predObjList(L) SEMICOLON predicate(P) objectList(O) . {
                LSUP_pred_obj_list_add (L, P, O);
                A = L;
            }

%type objectList { LSUP_Term ** }
objectList(A) ::= objectList(L) COMMA object(O) . [COMMA] {
                A = LSUP_obj_list_add (L, O);
            }
objectList(A) ::= object(O) . [COMMA] {
                A = calloc (sizeof (*A), 2);
                A[0] = O;
            }

%type subject { LSUP_Term * }
subject 	::= resource .
subject 	::= blank .

%type predicate { LSUP_Term * }
// Leading WS is counted as part of the RDF_TYPE ('a') token.
predicate   ::= resource .
predicate(A)::= RDF_TYPE . { A = LSUP_iriref_new ("rdf:type", state->nsm); }

%type object { LSUP_Term * }
object 	    ::= resource .
object 	    ::= blank .
object 	    ::= literal .

%type literal { LSUP_Term * }
literal(A)  ::= STRING(D) . {
                A = LSUP_term_new (LSUP_TERM_LITERAL, D, NULL);
            }
literal(A)  ::= STRING(D) LANGTAG(L) . {
                A = LSUP_term_new (LSUP_TERM_LT_LITERAL, D, L);
            }
literal(A)  ::= STRING(D) DTYPE_MARKER resource(M) . {
                A = LSUP_term_new (LSUP_TERM_LITERAL, D, M);
            }
literal(A)  ::= INTEGER(D) . {
                A = LSUP_term_new (
                    LSUP_TERM_LITERAL, D,
                    LSUP_iriref_new ("xsd:integer", state->nsm));
            }
literal(A)  ::= DOUBLE(D) . {
                A = LSUP_term_new (
                    LSUP_TERM_LITERAL, D,
                    LSUP_iriref_new ("xsd:double", state->nsm));
            }
literal(A)  ::= DECIMAL(D) . {
                A = LSUP_term_new (
                    LSUP_TERM_LITERAL, D,
                    LSUP_iriref_new ("xsd:decimal", state->nsm));
            }
literal(A)  ::= BOOLEAN(D) . {
                A = LSUP_term_new (
                    LSUP_TERM_LITERAL, D,
                    LSUP_iriref_new ("xsd:boolean", state->nsm));
            }

%type blank { LSUP_Term * }
blank(A)    ::= BNODE_ID(D) . {
                A = LSUP_term_new (LSUP_TERM_BNODE, D, NULL);
            }
blank(A)    ::= LBRACKET RBRACKET . {
                A = LSUP_term_new (LSUP_TERM_BNODE, NULL, NULL);
            }
blank(A)    ::= LBRACKET predObjList(L) RBRACKET . {
                A = LSUP_term_new (LSUP_TERM_BNODE, NULL, NULL);
                state->ct += LSUP_spo_list_add_triples (state->it, A, L);

                LSUP_pred_obj_list_free (L);
            }
blank       ::= collection .
blank(A)    ::= LPAREN RPAREN . {
                A = LSUP_iriref_new ("rdf:nil", state->nsm);
            }

// "collection" is the subject of the first collection item.
%type collection { LSUP_Term * }
// Collection triples are added here to the graph.
collection(A) ::= LPAREN itemList(L) RPAREN . {
                A = LSUP_bnode_add_collection (state->it, L);
            }

%type itemList { LSUP_Term ** }
// Freed when the item list in the collection gets added to the graph.
%destructor itemList {}
itemList(A) ::= itemList(L) object(O) . { A = LSUP_obj_list_add (L, O); }
itemList(A) ::= object(O) . {
                A = calloc (sizeof (*A), 2);
                A[0] = O;
            }

%type resource { LSUP_Term * }
resource(A) ::= IRIREF(D) . {
                LSUP_Term *rel_iri = LSUP_iriref_new (D, NULL);
                free (D);
                if (state->base) {
                    A = LSUP_iriref_absolute (rel_iri, state->base);
                    LSUP_term_free (rel_iri);
                } else {
                    A = rel_iri;
                }
            }
resource(A) ::= qname(D) . { A = LSUP_iriref_new (D, state->nsm); }

qname(A)    ::= PFX(P) IDNAME(D) . {
                A = malloc (strlen (P) + strlen (D) + 2);
                sprintf (A, "%s:%s", P, D);
            }
qname(A)    ::= COLON IDNAME(D) . {
                A = malloc (strlen (D) + 2);
                sprintf (A, ":%s", D);
            }
qname(A)    ::= COLON . { A = strndup (":", 2); }

/*
 * This has been adapted from
 * https://www.w3.org/TeamSubmission/turtle/#sec-grammar-grammar :


[1]	turtleDoc 	::= 	statement*
[2]	statement 	::= 	directive '.' | triples '.' | ws+
[3]	directive 	::= 	prefixID | base
[4]	prefixID 	::= 	'@prefix' ws+ prefixName? ':' uriref
[5]	base 	::= 	'@base' ws+ uriref
[6]	triples 	::= 	subject predicateObjectList
[7]	predicateObjectList 	::= 	verb objectList ( ';' verb objectList )* ( ';')?
[8]	objectList 	::= 	object ( ',' object)*
[9]	verb 	::= 	predicate | 'a'
[10]	comment 	::= 	'#' ( [^#xA#xD] )*
[11]	subject 	::= 	resource | blank
[12]	predicate 	::= 	resource
[13]	object 	::= 	resource | blank | literal
[14]	literal 	::= 	quotedString ( '@' language )? | datatypeString | integer | double | decimal | boolean
[15]	datatypeString 	::= 	quotedString '^^' resource
[16]	integer 	::= 	('-' | '+') ? [0-9]+
[17]	double 	::= 	('-' | '+') ? ( [0-9]+ '.' [0-9]* exponent | '.' ([0-9])+ exponent | ([0-9])+ exponent )
[18]	decimal 	::= 	('-' | '+')? ( [0-9]+ '.' [0-9]* | '.' ([0-9])+ | ([0-9])+ )
[19]	exponent 	::= 	[eE] ('-' | '+')? [0-9]+
[20]	boolean 	::= 	'true' | 'false'
[21]	blank 	::= 	nodeID | '[]' | '[' predicateObjectList ']' | collection
[22]	itemList 	::= 	object+
[23]	collection 	::= 	'(' itemList? ')'
[24]	ws 	::= 	#x9 | #xA | #xD | #x20 | comment
[25]	resource 	::= 	uriref | qname
[26]	nodeID 	::= 	'_:' name
[27]	qname 	::= 	prefixName? ':' name?
[28]	uriref 	::= 	'<' relativeURI '>'
[29]	language 	::= 	[a-z]+ ('-' [a-z0-9]+ )*
[30]	nameStartChar 	::= 	[A-Z] | "_" | [a-z] | [#x00C0-#x00D6] | [#x00D8-#x00F6] | [#x00F8-#x02FF] | [#x0370-#x037D] | [#x037F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] | [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] | [#x10000-#xEFFFF]
[31]	nameChar 	::= 	nameStartChar | '-' | [0-9] | #x00B7 | [#x0300-#x036F] | [#x203F-#x2040]
[32]	name 	::= 	nameStartChar nameChar*
[33]	prefixName 	::= 	( nameStartChar - '_' ) nameChar*
[34]	relativeURI 	::= 	ucharacter*
[35]	quotedString 	::= 	string | longString
[36]	string 	::= 	#x22 scharacter* #x22
[37]	longString 	::= 	#x22 #x22 #x22 lcharacter* #x22 #x22 #x22
[38]	character 	::= 	'\u' hex hex hex hex |
'\U' hex hex hex hex hex hex hex hex |
'\\' |
[#x20-#x5B] | [#x5D-#x10FFFF]
[39]	echaracter 	::= 	character | '\t' | '\n' | '\r'
[40]	hex 	::= 	[#x30-#x39] | [#x41-#x46]
[41]	ucharacter 	::= 	( character - #x3E ) | '\>'
[42]	scharacter 	::= 	( echaracter - #x22 ) | '\"'
[43]	lcharacter 	::= 	echaracter | '\"' | #x9 | #xA | #xD 



*/