lexer grammar SolidityLexer; /** * Keywords reserved for future use in Solidity. */ ReservedKeywords: 'after' | 'alias' | 'apply' | 'auto' | 'byte' | 'case' | 'copyof' | 'default' | 'define' | 'final' | 'implements' | 'in' | 'inline' | 'let' | 'macro' | 'match' | 'mutable' | 'null' | 'of' | 'partial' | 'promise' | 'reference' | 'relocatable' | 'sealed' | 'sizeof' | 'static' | 'supports' | 'switch' | 'typedef' | 'typeof' | 'var'; Pragma: 'pragma' -> pushMode(PragmaMode); Abstract: 'abstract'; Anonymous: 'anonymous'; Address: 'address'; As: 'as'; Assembly: 'assembly' -> pushMode(AssemblyBlockMode); Bool: 'bool'; Break: 'break'; Bytes: 'bytes'; Calldata: 'calldata'; Catch: 'catch'; Constant: 'constant'; Constructor: 'constructor'; Continue: 'continue'; Contract: 'contract'; Delete: 'delete'; Do: 'do'; Else: 'else'; Emit: 'emit'; Enum: 'enum'; Error: 'error'; // not a real keyword Event: 'event'; External: 'external'; Fallback: 'fallback'; False: 'false'; Fixed: 'fixed' | ('fixed' [1-9][0-9]* 'x' [1-9][0-9]*); From: 'from'; // not a real keyword /** * Bytes types of fixed length. */ FixedBytes: 'bytes1' | 'bytes2' | 'bytes3' | 'bytes4' | 'bytes5' | 'bytes6' | 'bytes7' | 'bytes8' | 'bytes9' | 'bytes10' | 'bytes11' | 'bytes12' | 'bytes13' | 'bytes14' | 'bytes15' | 'bytes16' | 'bytes17' | 'bytes18' | 'bytes19' | 'bytes20' | 'bytes21' | 'bytes22' | 'bytes23' | 'bytes24' | 'bytes25' | 'bytes26' | 'bytes27' | 'bytes28' | 'bytes29' | 'bytes30' | 'bytes31' | 'bytes32'; For: 'for'; Function: 'function'; Hex: 'hex'; If: 'if'; Immutable: 'immutable'; Import: 'import'; Indexed: 'indexed'; Interface: 'interface'; Internal: 'internal'; Is: 'is'; Library: 'library'; Mapping: 'mapping'; Memory: 'memory'; Modifier: 'modifier'; New: 'new'; /** * Unit denomination for numbers. */ NumberUnit: 'wei' | 'gwei' | 'ether' | 'seconds' | 'minutes' | 'hours' | 'days' | 'weeks' | 'years'; Override: 'override'; Payable: 'payable'; Private: 'private'; Public: 'public'; Pure: 'pure'; Receive: 'receive'; Return: 'return'; Returns: 'returns'; /** * Sized signed integer types. * int is an alias of int256. */ SignedIntegerType: 'int' | 'int8' | 'int16' | 'int24' | 'int32' | 'int40' | 'int48' | 'int56' | 'int64' | 'int72' | 'int80' | 'int88' | 'int96' | 'int104' | 'int112' | 'int120' | 'int128' | 'int136' | 'int144' | 'int152' | 'int160' | 'int168' | 'int176' | 'int184' | 'int192' | 'int200' | 'int208' | 'int216' | 'int224' | 'int232' | 'int240' | 'int248' | 'int256'; Storage: 'storage'; String: 'string'; Struct: 'struct'; True: 'true'; Try: 'try'; Type: 'type'; Ufixed: 'ufixed' | ('ufixed' [1-9][0-9]+ 'x' [1-9][0-9]+); Unchecked: 'unchecked'; /** * Sized unsigned integer types. * uint is an alias of uint256. */ UnsignedIntegerType: 'uint' | 'uint8' | 'uint16' | 'uint24' | 'uint32' | 'uint40' | 'uint48' | 'uint56' | 'uint64' | 'uint72' | 'uint80' | 'uint88' | 'uint96' | 'uint104' | 'uint112' | 'uint120' | 'uint128' | 'uint136' | 'uint144' | 'uint152' | 'uint160' | 'uint168' | 'uint176' | 'uint184' | 'uint192' | 'uint200' | 'uint208' | 'uint216' | 'uint224' | 'uint232' | 'uint240' | 'uint248' | 'uint256'; Using: 'using'; View: 'view'; Virtual: 'virtual'; While: 'while'; LParen: '('; RParen: ')'; LBrack: '['; RBrack: ']'; LBrace: '{'; RBrace: '}'; Colon: ':'; Semicolon: ';'; Period: '.'; Conditional: '?'; DoubleArrow: '=>'; RightArrow: '->'; Assign: '='; AssignBitOr: '|='; AssignBitXor: '^='; AssignBitAnd: '&='; AssignShl: '<<='; AssignSar: '>>='; AssignShr: '>>>='; AssignAdd: '+='; AssignSub: '-='; AssignMul: '*='; AssignDiv: '/='; AssignMod: '%='; Comma: ','; Or: '||'; And: '&&'; BitOr: '|'; BitXor: '^'; BitAnd: '&'; Shl: '<<'; Sar: '>>'; Shr: '>>>'; Add: '+'; Sub: '-'; Mul: '*'; Div: '/'; Mod: '%'; Exp: '**'; Equal: '=='; NotEqual: '!='; LessThan: '<'; GreaterThan: '>'; LessThanOrEqual: '<='; GreaterThanOrEqual: '>='; Not: '!'; BitNot: '~'; Inc: '++'; Dec: '--'; /** * A single quoted string literal restricted to printable characters. */ StringLiteral: '"' DoubleQuotedStringCharacter* '"' | '\'' SingleQuotedStringCharacter* '\''; /** * A single non-empty quoted string literal. */ NonEmptyStringLiteral: '"' DoubleQuotedStringCharacter+ '"' | '\'' SingleQuotedStringCharacter+ '\''; // Note that this will also be used for Yul string literals. //@doc:inline fragment DoubleQuotedStringCharacter: DoubleQuotedPrintable | EscapeSequence; // Note that this will also be used for Yul string literals. //@doc:inline fragment SingleQuotedStringCharacter: SingleQuotedPrintable | EscapeSequence; /** * Any printable character except single quote or back slash. */ fragment SingleQuotedPrintable: [\u0020-\u0026\u0028-\u005B\u005D-\u007E]; /** * Any printable character except double quote or back slash. */ fragment DoubleQuotedPrintable: [\u0020-\u0021\u0023-\u005B\u005D-\u007E]; /** * Escape sequence. * Apart from common single character escape sequences, line breaks can be escaped * as well as four hex digit unicode escapes \\uXXXX and two digit hex escape sequences \\xXX are allowed. */ fragment EscapeSequence: '\\' ( ['"\\nrt\n\r] | 'u' HexCharacter HexCharacter HexCharacter HexCharacter | 'x' HexCharacter HexCharacter ); /** * A single quoted string literal allowing arbitrary unicode characters. */ UnicodeStringLiteral: 'unicode"' DoubleQuotedUnicodeStringCharacter* '"' | 'unicode\'' SingleQuotedUnicodeStringCharacter* '\''; //@doc:inline fragment DoubleQuotedUnicodeStringCharacter: ~["\r\n\\] | EscapeSequence; //@doc:inline fragment SingleQuotedUnicodeStringCharacter: ~['\r\n\\] | EscapeSequence; /** * Hex strings need to consist of an even number of hex digits that may be grouped using underscores. */ HexString: 'hex' (('"' EvenHexDigits? '"') | ('\'' EvenHexDigits? '\'')); /** * Hex numbers consist of a prefix and an arbitrary number of hex digits that may be delimited by underscores. */ HexNumber: '0' 'x' HexDigits; //@doc:inline fragment HexDigits: HexCharacter ('_'? HexCharacter)*; //@doc:inline fragment EvenHexDigits: HexCharacter HexCharacter ('_'? HexCharacter HexCharacter)*; //@doc:inline fragment HexCharacter: [0-9A-Fa-f]; /** * A decimal number literal consists of decimal digits that may be delimited by underscores and * an optional positive or negative exponent. * If the digits contain a decimal point, the literal has fixed point type. */ DecimalNumber: (DecimalDigits | (DecimalDigits? '.' DecimalDigits)) ([eE] '-'? DecimalDigits)?; //@doc:inline fragment DecimalDigits: [0-9] ('_'? [0-9])* ; /** * An identifier in solidity has to start with a letter, a dollar-sign or an underscore and * may additionally contain numbers after the first symbol. */ Identifier: IdentifierStart IdentifierPart*; //@doc:inline fragment IdentifierStart: [a-zA-Z$_]; //@doc:inline fragment IdentifierPart: [a-zA-Z0-9$_]; WS: [ \t\r\n\u000C]+ -> skip ; COMMENT: '/*' .*? '*/' -> channel(HIDDEN) ; LINE_COMMENT: '//' ~[\r\n]* -> channel(HIDDEN); mode AssemblyBlockMode; //@doc:inline AssemblyDialect: '"evmasm"'; AssemblyLBrace: '{' -> popMode, pushMode(YulMode); AssemblyBlockWS: [ \t\r\n\u000C]+ -> skip ; AssemblyBlockCOMMENT: '/*' .*? '*/' -> channel(HIDDEN) ; AssemblyBlockLINE_COMMENT: '//' ~[\r\n]* -> channel(HIDDEN) ; mode YulMode; YulBreak: 'break'; YulCase: 'case'; YulContinue: 'continue'; YulDefault: 'default'; YulFalse: 'false'; YulFor: 'for'; YulFunction: 'function'; YulIf: 'if'; YulLeave: 'leave'; YulLet: 'let'; YulSwitch: 'switch'; YulTrue: 'true'; /** * Builtin functions in the EVM Yul dialect. */ YulEVMBuiltin: 'stop' | 'add' | 'sub' | 'mul' | 'div' | 'sdiv' | 'mod' | 'smod' | 'exp' | 'not' | 'lt' | 'gt' | 'slt' | 'sgt' | 'eq' | 'iszero' | 'and' | 'or' | 'xor' | 'byte' | 'shl' | 'shr' | 'sar' | 'addmod' | 'mulmod' | 'signextend' | 'keccak256' | 'pop' | 'mload' | 'mstore' | 'mstore8' | 'sload' | 'sstore' | 'msize' | 'gas' | 'address' | 'balance' | 'selfbalance' | 'caller' | 'callvalue' | 'calldataload' | 'calldatasize' | 'calldatacopy' | 'extcodesize' | 'extcodecopy' | 'returndatasize' | 'returndatacopy' | 'extcodehash' | 'create' | 'create2' | 'call' | 'callcode' | 'delegatecall' | 'staticcall' | 'return' | 'revert' | 'selfdestruct' | 'invalid' | 'log0' | 'log1' | 'log2' | 'log3' | 'log4' | 'chainid' | 'origin' | 'gasprice' | 'blockhash' | 'coinbase' | 'timestamp' | 'number' | 'difficulty' | 'gaslimit'; YulLBrace: '{' -> pushMode(YulMode); YulRBrace: '}' -> popMode; YulLParen: '('; YulRParen: ')'; YulAssign: ':='; YulPeriod: '.'; YulComma: ','; YulArrow: '->'; /** * Yul identifiers consist of letters, dollar signs, underscores and numbers, but may not start with a number. * In inline assembly there cannot be dots in user-defined identifiers. Instead see yulPath for expressions * consisting of identifiers with dots. */ YulIdentifier: YulIdentifierStart YulIdentifierPart*; //@doc:inline fragment YulIdentifierStart: [a-zA-Z$_]; //@doc:inline fragment YulIdentifierPart: [a-zA-Z0-9$_]; /** * Hex literals in Yul consist of a prefix and one or more hexadecimal digits. */ YulHexNumber: '0' 'x' [0-9a-fA-F]+; /** * Decimal literals in Yul may be zero or any sequence of decimal digits without leading zeroes. */ YulDecimalNumber: '0' | ([1-9] [0-9]*); /** * String literals in Yul consist of one or more double-quoted or single-quoted strings * that may contain escape sequences and printable characters except unescaped line breaks or * unescaped double-quotes or single-quotes, respectively. */ YulStringLiteral: '"' DoubleQuotedStringCharacter* '"' | '\'' SingleQuotedStringCharacter* '\''; YulWS: [ \t\r\n\u000C]+ -> skip ; YulCOMMENT: '/*' .*? '*/' -> channel(HIDDEN) ; YulLINE_COMMENT: '//' ~[\r\n]* -> channel(HIDDEN) ; mode PragmaMode; /** * Pragma token. Can contain any kind of symbol except a semicolon. * Note that currently the solidity parser only allows a subset of this. */ //@doc:name pragma-token //@doc:no-diagram PragmaToken: ~[;]+; PragmaSemicolon: ';' -> popMode; PragmaWS: [ \t\r\n\u000C]+ -> skip ; PragmaCOMMENT: '/*' .*? '*/' -> channel(HIDDEN) ; PragmaLINE_COMMENT: '//' ~[\r\n]* -> channel(HIDDEN) ;