bnf.g4

grammar SQLConditions;

// Parser rules
condition
    : NOT? disjunction
    ;

disjunction
    : conjunction (OR conjunction)*
    ;

conjunction
    : predicate (AND predicate)*
    ;

predicate
    : expression
    | LPAREN condition RPAREN
    ;

expression
    : column comp_op value
    | column NOT? IN LPAREN value_list RPAREN
    | column NOT? BETWEEN value AND value
    ;

comp_op
    : EQ
    | NEQ
    | LT
    | LTE
    | GT
    | GTE
    ;

value_list
    : value (COMMA value)*
    ;

column
    : identifier
    ;

value
    : string
    | number
    | date
    | time
    | timestamp
    ;

identifier
    : IDENTIFIER
    ;

string
    : STRING
    ;

number
    : NUMBER
    ;

date
    : DATE_LITERAL
    ;

time
    : TIME_LITERAL
    ;

timestamp
    : TIMESTAMP_LITERAL
    ;

// Lexer rules
NOT         : 'NOT';
AND         : 'AND';
OR          : 'OR';
IN          : 'IN';
BETWEEN     : 'BETWEEN';

EQ          : '=';
NEQ         : '<>';
LT          : '<';
LTE         : '<=';
GT          : '>';
GTE         : '>=';

LPAREN      : '(';
RPAREN      : ')';
COMMA       : ',';

// Values
STRING
    : '\'' (~['\r\n])* '\''
    ;

NUMBER
    : DIGIT+
    ;

DATE_LITERAL
    : 'DATE' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT '\''
    ;

TIME_LITERAL
    : 'TIME' '\'' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

TIMESTAMP_LITERAL
    : 'TIMESTAMP' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT ' ' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

IDENTIFIER
    : LETTER (LETTER | DIGIT)*
    ;

fragment LETTER : [a-zA-Z];
fragment DIGIT  : [0-9];

WS
    : [ \t\r\n]+ -> skip
    ;

bnf2.g4

grammar SQLConditions1;

// ----------------- Parser Rules -----------------

condition
    : NOT? disjunction
    ;

disjunction
    : conjunction (OR conjunction)*
    ;

conjunction
    : predicate (AND predicate)*
    ;

predicate
    : expression
    | LPAREN condition RPAREN
    ;

expression
    : column comp_op value
    | column NOT? IN LPAREN value_list RPAREN
    | column NOT? BETWEEN value AND value
    ;

comp_op
    : EQ
    | NEQ
    | LT
    | LTE
    | GT
    | GTE
    ;

value_list
    : value (COMMA value)*
    ;

column
    : identifier | path_string
    ;

value
    : STRING
    | NUMBER
    | DATE_LITERAL
    | TIME_LITERAL
    | TIMESTAMP_LITERAL
    | relative
    ;

path_string
    : DOLLAR identifier DOLLAR path_part*
    ;

path_part
    : DOT identifier
    | LBRACK identifier RBRACK
    | LBRACK NUMBER RBRACK
    ;

relative
    : NUMBER TIME_UNIT
    ;

// ----------------- Lexer Rules -----------------

NOT         : 'NOT';
AND         : 'AND';
OR          : 'OR';
IN          : 'IN';
BETWEEN     : 'BETWEEN';

EQ          : '=';
NEQ         : '<>';
LT          : '<';
LTE         : '<=';
GT          : '>';
GTE         : '>=';

LPAREN      : '(';
RPAREN      : ')';
COMMA       : ',';
DOT         : '.';
LBRACK      : '[';
RBRACK      : ']';
DOLLAR      : '$';

TIME_UNIT   : [dhmMY];   // d=days, h=hours, m=minutes, M=months, Y=years

// ----------------- Literals -----------------

STRING
    : '\'' (~['\\\r\n] | ESCAPE)* '\''
    ;


NUMBER
    : '-'? INT ('.' [0-9]+)? EXP?
    ;


DATE_LITERAL
    : 'DATE' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT '\''
    ;

TIME_LITERAL
    : 'TIME' '\'' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

TIMESTAMP_LITERAL
    : 'TIMESTAMP' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT ' ' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

identifier
    : IDENTIFIER
    ;

IDENTIFIER
    : LETTER (LETTER | DIGIT)*
    ;

// ----------------- Fragments -----------------

fragment LETTER : [a-zA-Z];
fragment DIGIT  : [0-9];
fragment HEX    : [0-9a-fA-F];


fragment ESCAPE
    : '\\' (['"\\/bfnrt] | 'u' HEX HEX HEX HEX)
    ;

fragment INT
    : '0'
    | [1-9] [0-9]*
    ;

fragment EXP
    : [Ee] [+-]? [0-9]+
    ;
// ----------------- Whitespace -----------------

WS
    : [ \t\r\n]+ -> skip
    ;

Postgreql Query Language frontend

<condition>   ::= [ "NOT" ] <disjunction>

<disjunction> ::= <conjunction> { "OR" <conjunction> }

<conjunction> ::= <predicate> { "AND" <predicate> }

<predicate>   ::= <expression>
                | "(" <condition> ")"

<expression>  ::= <column> <comp_op> <value>
                | <column> [ "NOT" ] "IN" "(" <value_list> ")"
                | <column> [ "NOT" ] "BETWEEN" <value> "AND" <value>

<comp_op>     ::= "=" | "<>" | "<" | "<=" | ">" | ">="

<value_list>  ::= <value> { "," <value> }

<column>      ::= <identifier>

<value>       ::= <string> 
                | <number> 
                | <date> 
                | <time> 
                | <timestamp>

<identifier>  ::= <letter> { <letter_or_digit> }

<string>       ::= "'" { <any_char_except_quote> } "'"
<number>       ::= <digit> { <digit> }
<date>         ::= "DATE" "'" <date_literal> "'"
<time>         ::= "TIME" "'" <time_literal> "'"
<timestamp>    ::= "TIMESTAMP" "'" <timestamp_literal> "'"

<date_literal>     ::= <digit><digit><digit><digit> "-" <digit><digit> "-" <digit><digit>
<time_literal>     ::= <digit><digit> ":" <digit><digit> [ ":" <digit><digit> ]
<timestamp_literal>::= <date_literal> " " <time_literal>

<letter>       ::= "A" | ... | "Z" | "a" | ... | "z"
<letter_or_digit> ::= <letter> | <digit>
<digit>        ::= "0" | ... | "9"
<any_char_except_quote> ::= any character except "'"

SPQL.g4

grammar SPQL;
condition
    : NOT? disjunction
    ;

disjunction
    : conjunction (OR conjunction)*
    ;

conjunction
    : predicate (AND predicate)*
    ;

predicate
    : expression
    | LPAREN condition RPAREN
    ;

expression
    : column comp_op value
    | column NOT? IN LPAREN value_list RPAREN
    | column NOT? BETWEEN value AND value
    ;

comp_op
    : EQ
    | NEQ
    | LT
    | LTE
    | GT
    | GTE
    ;

column
    : UNQUOTED_STRING | path_string
    ;

path_string
    : DOLLAR UNQUOTED_STRING DOLLAR path_part*
    ;

path_part
    : DOT UNQUOTED_STRING
    | LBRACK UNQUOTED_STRING RBRACK
    | LBRACK NUMBER RBRACK
    ;

value_list
    : value (COMMA value)*
    ;

value
    : QUOTED_STRING
    | NUMBER
    | DATE_LITERAL
    | TIME_LITERAL
    | TIMESTAMP_LITERAL
    | relative_time
    ;

relative_time
    : NUMBER RELATIVE_TIME_UNIT
    ;


// Lexer rule
NOT         : 'NOT';
AND         : 'AND';
OR          : 'OR';
IN          : 'IN';
BETWEEN     : 'BETWEEN';

EQ          : '=';
NEQ         : '<>';
LT          : '<';
LTE         : '<=';
GT          : '>';
GTE         : '>=';

LPAREN      : '(';
RPAREN      : ')';
COMMA       : ',';
DOT         : '.';
LBRACK      : '[';
RBRACK      : ']';
DOLLAR      : '$';
// date

RELATIVE_TIME_UNIT   : [dhmMY];   // d=days, h=hours, m=minutes, M=months, Y=years

DATE_LITERAL
    : 'DATE' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT '\''
    ;

TIME_LITERAL
    : 'TIME' '\'' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

TIMESTAMP_LITERAL
    : 'TIMESTAMP' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT ' ' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

// number
NUMBER
    : '-'? INT ('.' [0-9]+)? EXP?
    ;

// string
QUOTED_STRING
    : '"' (ESC | ~["\\\r\n])* '"'
    ;

UNQUOTED_STRING
    : UNQUOTED_CHAR+
    ;

// ---- Fragments ----


// Number

fragment INT
    : '0'
    | [1-9] [0-9]*
    ;

fragment EXP
    : [Ee] [+-]? [0-9]+
    ;

// String

fragment UNQUOTED_CHAR
    : LETTER
    | DIGIT
    | SYMBOL
    ;

fragment LETTER
    : [a-zA-Z]
    ;

fragment DIGIT
    : [0-9]
    ;

fragment SYMBOL
    : [_]   //  DSL needs
    ;

fragment ESC
    : '\\' (["\\/bfnrt] | UNICODE)
    ;

fragment UNICODE
    : 'u' HEX HEX HEX HEX
    ;

fragment HEX
    : [0-9a-fA-F]
    ;

SQLConditions.g4

grammar SQLConditions;

// Parser rules
condition
    : NOT? disjunction
    ;

disjunction
    : conjunction (OR conjunction)*
    ;

conjunction
    : predicate (AND predicate)*
    ;

predicate
    : expression
    | LPAREN condition RPAREN
    ;

expression
    : column comp_op value
    | column NOT? IN LPAREN value_list RPAREN
    | column NOT? BETWEEN value AND value
    ;

comp_op
    : EQ
    | NEQ
    | LT
    | LTE
    | GT
    | GTE
    ;

value_list
    : value (COMMA value)*
    ;

column
    : identifier
    ;

value
    : path_string
    | string
    | number
    | date
    | time
    | timestamp
    ;

path_string
    : DOLLAR string DOLLAR path_part*
    ;

path_part
    : DOT identifier
    | LBRACK string RBRACK
    | LBRACK number RBRACK
    ;

// Lexer rules
NOT         : 'NOT';
AND         : 'AND';
OR          : 'OR';
IN          : 'IN';
BETWEEN     : 'BETWEEN';

EQ          : '=';
NEQ         : '<>';
LT          : '<';
LTE         : '<=';
GT          : '>';
GTE         : '>=';

LPAREN      : '(';
RPAREN      : ')';
COMMA       : ',';
DOT         : '.';
LBRACK      : '[';
RBRACK      : ']';
DOLLAR      : '$';

// Values
STRING
    : '\'' (~['\r\n])* '\''
    ;

NUMBER
    : DIGIT+
    ;

DATE_LITERAL
    : 'DATE' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT '\''
    ;

TIME_LITERAL
    : 'TIME' '\'' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

TIMESTAMP_LITERAL
    : 'TIMESTAMP' '\'' DIGIT DIGIT DIGIT DIGIT '-' DIGIT DIGIT '-' DIGIT DIGIT ' ' DIGIT DIGIT ':' DIGIT DIGIT (':' DIGIT DIGIT)? '\''
    ;

IDENTIFIER
    : LETTER (LETTER | DIGIT)*
    ;

fragment LETTER : [a-zA-Z];
fragment DIGIT  : [0-9];

WS
    : [ \t\r\n]+ -> skip
    ;