Merge pull request #9412 from ethereum/unicode-string

[BREAKING] Support unicode string literal type
This commit is contained in:
chriseth 2020-07-28 11:42:23 +02:00 committed by GitHub
commit 53d497fc31
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
32 changed files with 794 additions and 29 deletions

View File

@ -7,6 +7,8 @@ Breaking changes:
* JSON AST: Remove members with ``null`` value from JSON output.
* Parser: Disallow ``gwei`` as identifier.
* Parser: Disallow dot syntax for ``value`` and ``gas``.
* Parser: Disallow non-printable characters in string literals.
* Parser: Introduce Unicode string literals: ``unicode"😃"``.
* Parser: NatSpec comments on variables are only allowed for public state variables.
* Parser: Remove the ``finney`` and ``szabo`` denominations.
* Parser: Remove the identifier ``now`` (replaced by ``block.timestamp``).

View File

@ -25,16 +25,24 @@ Changes to the Syntax
* In external function and contract creation calls, Ether and gas is now specified using a new syntax:
``x.f{gas: 10000, value: 2 ether}(arg1, arg2)``.
The old syntax -- ``x.f.gas(10000).value(2 ether)(arg1, arg2)`` -- will cause an error.
* The global variable ``now`` is deprecated, ``block.timestamp`` should be used instead.
The single identifier ``now`` is too generic for a global variable and could give the impression
that it changes during transaction processing, whereas ``block.timestamp`` correctly
reflects the fact that it is just a property of the block.
* NatSpec comments on variables are only allowed for public state variables and not
for local or internal variables.
* The token ``gwei`` is a keyword now (used to specify, e.g. ``2 gwei`` as a number)
and cannot be used as an identifier.
* String literals now can only contain printable ASCII characters and this also includes a variety of
escape sequences, such as hexadecimal (``\xff``) and unicode escapes (``\u20ac``).
* Unicode string literals are supported now to accommodate valid UTF-8 sequences. They are identified
with the ``unicode`` prefix: ``unicode"Hello 😃"``.
* State Mutability: The state mutability of functions can now be restricted during inheritance:
Functions with default state mutability can be overridden by ``pure`` and ``view`` functions
while ``view`` functions can be overridden by ``pure`` functions.

View File

@ -253,6 +253,7 @@ primaryExpression
| numberLiteral
| hexLiteral
| stringLiteral
| unicodeStringLiteral
| identifier ('[' ']')?
| TypeKeyword
| tupleExpression
@ -461,6 +462,13 @@ StringLiteralFragment
: '"' DoubleQuotedStringCharacter* '"'
| '\'' SingleQuotedStringCharacter* '\'' ;
unicodeStringLiteral
: UnicodeStringLiteralFragment+ ;
UnicodeStringLiteralFragment
: 'unicode"' DoubleQuotedStringCharacter* '"'
| 'unicode\'' SingleQuotedStringCharacter* '\'' ;
fragment
DoubleQuotedStringCharacter
: ~["\r\n\\] | ('\\' .) ;

View File

@ -484,7 +484,9 @@ String literals are written with either double or single-quotes (``"foo"`` or ``
For example, with ``bytes32 samevar = "stringliteral"`` the string literal is interpreted in its raw byte form when assigned to a ``bytes32`` type.
String literals support the following escape characters:
String literals can only contain printable ASCII characters, which means the characters between and including 0x1F .. 0x7E.
Additionally, string literals also support the following escape characters:
- ``\<newline>`` (escapes an actual newline)
- ``\\`` (backslash)
@ -511,9 +513,19 @@ character sequence ``abcdef``.
"\n\"\'\\abc\
def"
Any unicode line terminator which is not a newline (i.e. LF, VF, FF, CR, NEL, LS, PS) is considered to
Any Unicode line terminator which is not a newline (i.e. LF, VF, FF, CR, NEL, LS, PS) is considered to
terminate the string literal. Newline only terminates the string literal if it is not preceded by a ``\``.
Unicode Literals
----------------
While regular string literals can only contain ASCII, Unicode literals prefixed with the keyword ``unicode`` can contain any valid UTF-8 sequence.
They also support the very same escape sequences as regular string literals.
::
string memory a = unicode"Hello 😃";
.. index:: literal, bytes
Hexadecimal Literals

View File

@ -73,6 +73,7 @@ string to_string(ScannerError _errorCode)
case ScannerError::IllegalHexDigit: return "Hexadecimal digit missing or invalid.";
case ScannerError::IllegalCommentTerminator: return "Expected multi-line comment-terminator.";
case ScannerError::IllegalEscapeSequence: return "Invalid escape sequence.";
case ScannerError::IllegalCharacterInString: return "Invalid character in string.";
case ScannerError::IllegalStringEndQuote: return "Expected string end-quote.";
case ScannerError::IllegalNumberSeparator: return "Invalid use of number separator '_'.";
case ScannerError::IllegalExponent: return "Invalid exponent.";
@ -508,7 +509,7 @@ void Scanner::scanToken()
{
case '"':
case '\'':
token = scanString();
token = scanString(false);
break;
case '<':
// < <= << <<=
@ -683,6 +684,18 @@ void Scanner::scanToken()
else
token = setError(ScannerError::IllegalToken);
}
else if (token == Token::Unicode)
{
// reset
m = 0;
n = 0;
// Special quoted hex string must follow
if (m_char == '"' || m_char == '\'')
token = scanString(true);
else
token = setError(ScannerError::IllegalToken);
}
}
else if (isDecimalDigit(m_char))
token = scanNumber();
@ -774,7 +787,7 @@ bool Scanner::isUnicodeLinebreak()
return false;
}
Token Scanner::scanString()
Token Scanner::scanString(bool const _isUnicode)
{
char const quote = m_char;
advance(); // consume quote
@ -789,13 +802,23 @@ Token Scanner::scanString()
return setError(ScannerError::IllegalEscapeSequence);
}
else
{
// Report error on non-printable characters in string literals, however
// allow anything for unicode string literals, because their validity will
// be verified later (in the syntax checker).
//
// We are using a manual range and not isprint() to avoid
// any potential complications with locale.
if (!_isUnicode && (static_cast<unsigned>(c) <= 0x1f || static_cast<unsigned>(c) >= 0x7f))
return setError(ScannerError::IllegalCharacterInString);
addLiteralChar(c);
}
}
if (m_char != quote)
return setError(ScannerError::IllegalStringEndQuote);
literal.complete();
advance(); // consume quote
return Token::StringLiteral;
return _isUnicode ? Token::UnicodeStringLiteral : Token::StringLiteral;
}
Token Scanner::scanHexString()

View File

@ -77,6 +77,7 @@ enum class ScannerError
IllegalHexDigit,
IllegalCommentTerminator,
IllegalEscapeSequence,
IllegalCharacterInString,
IllegalStringEndQuote,
IllegalNumberSeparator,
IllegalExponent,
@ -228,7 +229,7 @@ private:
Token scanNumber(char _charSeen = 0);
std::tuple<Token, unsigned, unsigned> scanIdentifierOrKeyword();
Token scanString();
Token scanString(bool const _isUnicode);
Token scanHexString();
/// Scans a single line comment and returns its corrected end position.
size_t scanSingleLineDocComment();

View File

@ -190,6 +190,7 @@ namespace solidity::langutil
K(Throw, "throw", 0) \
K(Try, "try", 0) \
K(Type, "type", 0) \
K(Unicode, "unicode", 0) \
K(Using, "using", 0) \
K(View, "view", 0) \
K(Virtual, "virtual", 0) \
@ -227,6 +228,7 @@ namespace solidity::langutil
K(FalseLiteral, "false", 0) \
T(Number, nullptr, 0) \
T(StringLiteral, nullptr, 0) \
T(UnicodeStringLiteral, nullptr, 0) \
T(HexStringLiteral, nullptr, 0) \
T(CommentLiteral, nullptr, 0) \
\

View File

@ -28,6 +28,8 @@
#include <liblangutil/ErrorReporter.h>
#include <liblangutil/SemVerHandler.h>
#include <libsolutil/UTF8.h>
#include <boost/algorithm/string.hpp>
#include <memory>
@ -37,7 +39,7 @@ using namespace std;
using namespace solidity;
using namespace solidity::langutil;
using namespace solidity::frontend;
using namespace solidity::util;
bool SyntaxChecker::checkSyntax(ASTNode const& _astRoot)
{
@ -217,6 +219,13 @@ bool SyntaxChecker::visit(Throw const& _throwStatement)
bool SyntaxChecker::visit(Literal const& _literal)
{
if ((_literal.token() == Token::UnicodeStringLiteral) && !validateUTF8(_literal.value()))
m_errorReporter.syntaxError(
8452_error,
_literal.location(),
"Invalid UTF-8 sequence found"
);
if (_literal.token() != Token::Number)
return true;

View File

@ -920,6 +920,8 @@ string ASTJsonConverter::literalTokenKind(Token _token)
return "number";
case Token::StringLiteral:
return "string";
case Token::UnicodeStringLiteral:
return "unicodeString";
case Token::HexStringLiteral:
return "hexString";
case Token::TrueLiteral:

View File

@ -943,6 +943,8 @@ Token ASTJsonImporter::literalTokenKind(Json::Value const& _node)
tok = Token::Number;
else if (_node["kind"].asString() == "string")
tok = Token::StringLiteral;
else if (_node["kind"].asString() == "unicodeString")
tok = Token::UnicodeStringLiteral;
else if (_node["kind"].asString() == "hexString")
tok = Token::HexStringLiteral;
else if (_node["kind"].asString() == "bool")

View File

@ -349,6 +349,7 @@ TypePointer TypeProvider::forLiteral(Literal const& _literal)
case Token::Number:
return rationalNumber(_literal);
case Token::StringLiteral:
case Token::UnicodeStringLiteral:
case Token::HexStringLiteral:
return stringLiteral(_literal.value());
default:

View File

@ -1408,7 +1408,7 @@ BoolResult StringLiteralType::isImplicitlyConvertibleTo(Type const& _convertTo)
return
arrayType->isByteArray() &&
!(arrayType->dataStoredIn(DataLocation::Storage) && arrayType->isPointer()) &&
!(arrayType->isString() && !isValidUTF8());
!(arrayType->isString() && !util::validateUTF8(value()));
else
return false;
}
@ -1442,11 +1442,6 @@ TypePointer StringLiteralType::mobileType() const
return TypeProvider::stringMemory();
}
bool StringLiteralType::isValidUTF8() const
{
return util::validateUTF8(m_value);
}
FixedBytesType::FixedBytesType(unsigned _bytes): m_bytes(_bytes)
{
solAssert(

View File

@ -629,8 +629,6 @@ public:
std::string toString(bool) const override;
TypePointer mobileType() const override;
bool isValidUTF8() const;
std::string const& value() const { return m_value; }
protected:

View File

@ -1782,6 +1782,7 @@ ASTPointer<Expression> Parser::parsePrimaryExpression()
}
break;
case Token::StringLiteral:
case Token::UnicodeStringLiteral:
case Token::HexStringLiteral:
{
string literal = m_scanner->currentLiteral();

View File

@ -7,29 +7,30 @@ Warning: Source file does not specify required compiler version!
Warning: Statement has no effect.
--> message_format_utf8/input.sol:2:51:
|
2 | /* ©©©©ᄅ©©©©© 2017 */ constructor () { "©©©©ᄅ©©©©©" ; }
| ^^^^^^^^^^^^
2 | /* ©©©©ᄅ©©©©© 2017 */ constructor () { unicode"©©©©ᄅ©©©©©" ; }
| ^^^^^^^^^^^^^^^^^^^
Warning: Statement has no effect.
--> message_format_utf8/input.sol:6:25:
|
6 | "S = π × r²";
| ^^^^^^^^^^^^
6 | unicode"S = π × r²";
| ^^^^^^^^^^^^^^^^^^^
Warning: Statement has no effect.
--> message_format_utf8/input.sol:7:39:
|
7 | /* ₀₁₂₃₄⁵⁶⁷⁸⁹ */ "∑ 1/n! ≈ 2.7"; // tabs in-between
| ^^^^^^^^^^^^^^
7 | /* ₀₁₂₃₄⁵⁶⁷⁸⁹ */ unicode"∑ 1/n! ≈ 2.7"; // tabs in-between
| ^^^^^^^^^^^^^^^^^^^^^
Warning: Statement has no effect.
--> message_format_utf8/input.sol:8:30:
|
8 | /* Ŀŏŗėɯ ïƥŝʉɱ */ "μὴ χεῖρον βέλτιστον"; // tabs in-between and inside
| ^^^ ^^^^^^ ^^^^^^^^^^
8 | /* Ŀŏŗėɯ ïƥŝʉɱ */ unicode"μὴ χεῖρον βέλτιστον"; // tabs in-between and inside
| ^^^^^^^^^^ ^^^^^^ ^^^^^^^^^^
Warning: Function state mutability can be restricted to pure
--> message_format_utf8/input.sol:12:2:
|
12 | function selector() public returns(uint) { // starts with tab
| ^ (Relevant source part starts here and spans across multiple lines).

View File

@ -1,11 +1,11 @@
contract Foo {
/* ©©©©ᄅ©©©©© 2017 */ constructor () { "©©©©ᄅ©©©©©" ; }
/* ©©©©ᄅ©©©©© 2017 */ constructor () { unicode"©©©©ᄅ©©©©©" ; }
function f() public pure {
"S = π ×";
/* ₀₁₂₃₄⁵⁶⁷⁸⁹ */ "∑ 1/n! ≈ 2.7"; // tabs in-between
/* Ŀŏŗėɯ ïƥŝʉɱ */ "μὴ χεῖρον βέλτιστον"; // tabs in-between and inside
unicode"S = π ×";
/* ₀₁₂₃₄⁵⁶⁷⁸⁹ */ unicode"∑ 1/n! ≈ 2.7"; // tabs in-between
/* Ŀŏŗėɯ ïƥŝʉɱ */ unicode"μὴ χεῖρον βέλτιστον"; // tabs in-between and inside
}

View File

@ -0,0 +1,131 @@
{
"absolutePath": "a",
"exportedSymbols":
{
"C":
[
9
]
},
"id": 10,
"nodeType": "SourceUnit",
"nodes":
[
{
"abstract": false,
"baseContracts": [],
"contractDependencies": [],
"contractKind": "contract",
"fullyImplemented": true,
"id": 9,
"linearizedBaseContracts":
[
9
],
"name": "C",
"nodeType": "ContractDefinition",
"nodes":
[
{
"body":
{
"id": 7,
"nodeType": "Block",
"src": "33:36:1",
"statements":
[
{
"assignments":
[
4
],
"declarations":
[
{
"constant": false,
"id": 4,
"mutability": "mutable",
"name": "x",
"nodeType": "VariableDeclaration",
"scope": 7,
"src": "35:15:1",
"stateVariable": false,
"storageLocation": "memory",
"typeDescriptions":
{
"typeIdentifier": "t_string_memory_ptr",
"typeString": "string"
},
"typeName":
{
"id": 3,
"name": "string",
"nodeType": "ElementaryTypeName",
"src": "35:6:1",
"typeDescriptions":
{
"typeIdentifier": "t_string_storage_ptr",
"typeString": "string"
}
},
"visibility": "internal"
}
],
"id": 6,
"initialValue":
{
"hexValue": "48656c6c6f20576f726c64",
"id": 5,
"isConstant": false,
"isLValue": false,
"isPure": true,
"kind": "string",
"lValueRequested": false,
"nodeType": "Literal",
"src": "53:13:1",
"typeDescriptions":
{
"typeIdentifier": "t_stringliteral_592fa743889fc7f92ac2a37bb1f5ba1daf2a5c84741ca0e0061d243a2e6707ba",
"typeString": "literal_string \"Hello World\""
},
"value": "Hello World"
},
"nodeType": "VariableDeclarationStatement",
"src": "35:31:1"
}
]
},
"functionSelector": "26121ff0",
"id": 8,
"implemented": true,
"kind": "function",
"modifiers": [],
"name": "f",
"nodeType": "FunctionDefinition",
"parameters":
{
"id": 1,
"nodeType": "ParameterList",
"parameters": [],
"src": "23:2:1"
},
"returnParameters":
{
"id": 2,
"nodeType": "ParameterList",
"parameters": [],
"src": "33:0:1"
},
"scope": 9,
"src": "13:56:1",
"stateMutability": "nonpayable",
"virtual": false,
"visibility": "public"
}
],
"scope": 10,
"src": "0:71:1"
}
],
"src": "0:72:1"
}

View File

@ -0,0 +1,3 @@
contract C { function f() public { string memory x = "Hello World"; } }
// ----

View File

@ -0,0 +1,165 @@
{
"attributes":
{
"absolutePath": "a",
"exportedSymbols":
{
"C":
[
9
]
}
},
"children":
[
{
"attributes":
{
"abstract": false,
"baseContracts":
[
null
],
"contractDependencies":
[
null
],
"contractKind": "contract",
"fullyImplemented": true,
"linearizedBaseContracts":
[
9
],
"name": "C",
"scope": 10
},
"children":
[
{
"attributes":
{
"functionSelector": "26121ff0",
"implemented": true,
"isConstructor": false,
"kind": "function",
"modifiers":
[
null
],
"name": "f",
"scope": 9,
"stateMutability": "nonpayable",
"virtual": false,
"visibility": "public"
},
"children":
[
{
"attributes":
{
"parameters":
[
null
]
},
"children": [],
"id": 1,
"name": "ParameterList",
"src": "23:2:1"
},
{
"attributes":
{
"parameters":
[
null
]
},
"children": [],
"id": 2,
"name": "ParameterList",
"src": "33:0:1"
},
{
"children":
[
{
"attributes":
{
"assignments":
[
4
]
},
"children":
[
{
"attributes":
{
"constant": false,
"mutability": "mutable",
"name": "x",
"scope": 7,
"stateVariable": false,
"storageLocation": "memory",
"type": "string",
"visibility": "internal"
},
"children":
[
{
"attributes":
{
"name": "string",
"type": "string"
},
"id": 3,
"name": "ElementaryTypeName",
"src": "35:6:1"
}
],
"id": 4,
"name": "VariableDeclaration",
"src": "35:15:1"
},
{
"attributes":
{
"hexvalue": "48656c6c6f20576f726c64",
"isConstant": false,
"isLValue": false,
"isPure": true,
"lValueRequested": false,
"token": "string",
"type": "literal_string \"Hello World\"",
"value": "Hello World"
},
"id": 5,
"name": "Literal",
"src": "53:13:1"
}
],
"id": 6,
"name": "VariableDeclarationStatement",
"src": "35:31:1"
}
],
"id": 7,
"name": "Block",
"src": "33:36:1"
}
],
"id": 8,
"name": "FunctionDefinition",
"src": "13:56:1"
}
],
"id": 9,
"name": "ContractDefinition",
"src": "0:71:1"
}
],
"id": 10,
"name": "SourceUnit",
"src": "0:72:1"
}

View File

@ -0,0 +1,131 @@
{
"absolutePath": "a",
"exportedSymbols":
{
"C":
[
9
]
},
"id": 10,
"nodeType": "SourceUnit",
"nodes":
[
{
"abstract": false,
"baseContracts": [],
"contractDependencies": [],
"contractKind": "contract",
"fullyImplemented": true,
"id": 9,
"linearizedBaseContracts":
[
9
],
"name": "C",
"nodeType": "ContractDefinition",
"nodes":
[
{
"body":
{
"id": 7,
"nodeType": "Block",
"src": "33:42:1",
"statements":
[
{
"assignments":
[
4
],
"declarations":
[
{
"constant": false,
"id": 4,
"mutability": "mutable",
"name": "x",
"nodeType": "VariableDeclaration",
"scope": 7,
"src": "35:15:1",
"stateVariable": false,
"storageLocation": "memory",
"typeDescriptions":
{
"typeIdentifier": "t_string_memory_ptr",
"typeString": "string"
},
"typeName":
{
"id": 3,
"name": "string",
"nodeType": "ElementaryTypeName",
"src": "35:6:1",
"typeDescriptions":
{
"typeIdentifier": "t_string_storage_ptr",
"typeString": "string"
}
},
"visibility": "internal"
}
],
"id": 6,
"initialValue":
{
"hexValue": "48656c6c6f20f09f9883",
"id": 5,
"isConstant": false,
"isLValue": false,
"isPure": true,
"kind": "unicodeString",
"lValueRequested": false,
"nodeType": "Literal",
"src": "53:19:1",
"typeDescriptions":
{
"typeIdentifier": "t_stringliteral_cd7a99177cebb3d14b8cc54e313dbf76867c71cd6fbb9a33ce3870dc80e9992b",
"typeString": "literal_string \"Hello \ud83d\ude03\""
},
"value": "Hello \ud83d\ude03"
},
"nodeType": "VariableDeclarationStatement",
"src": "35:37:1"
}
]
},
"functionSelector": "26121ff0",
"id": 8,
"implemented": true,
"kind": "function",
"modifiers": [],
"name": "f",
"nodeType": "FunctionDefinition",
"parameters":
{
"id": 1,
"nodeType": "ParameterList",
"parameters": [],
"src": "23:2:1"
},
"returnParameters":
{
"id": 2,
"nodeType": "ParameterList",
"parameters": [],
"src": "33:0:1"
},
"scope": 9,
"src": "13:62:1",
"stateMutability": "nonpayable",
"virtual": false,
"visibility": "public"
}
],
"scope": 10,
"src": "0:77:1"
}
],
"src": "0:78:1"
}

View File

@ -0,0 +1,3 @@
contract C { function f() public { string memory x = unicode"Hello 😃"; } }
// ----

View File

@ -0,0 +1,165 @@
{
"attributes":
{
"absolutePath": "a",
"exportedSymbols":
{
"C":
[
9
]
}
},
"children":
[
{
"attributes":
{
"abstract": false,
"baseContracts":
[
null
],
"contractDependencies":
[
null
],
"contractKind": "contract",
"fullyImplemented": true,
"linearizedBaseContracts":
[
9
],
"name": "C",
"scope": 10
},
"children":
[
{
"attributes":
{
"functionSelector": "26121ff0",
"implemented": true,
"isConstructor": false,
"kind": "function",
"modifiers":
[
null
],
"name": "f",
"scope": 9,
"stateMutability": "nonpayable",
"virtual": false,
"visibility": "public"
},
"children":
[
{
"attributes":
{
"parameters":
[
null
]
},
"children": [],
"id": 1,
"name": "ParameterList",
"src": "23:2:1"
},
{
"attributes":
{
"parameters":
[
null
]
},
"children": [],
"id": 2,
"name": "ParameterList",
"src": "33:0:1"
},
{
"children":
[
{
"attributes":
{
"assignments":
[
4
]
},
"children":
[
{
"attributes":
{
"constant": false,
"mutability": "mutable",
"name": "x",
"scope": 7,
"stateVariable": false,
"storageLocation": "memory",
"type": "string",
"visibility": "internal"
},
"children":
[
{
"attributes":
{
"name": "string",
"type": "string"
},
"id": 3,
"name": "ElementaryTypeName",
"src": "35:6:1"
}
],
"id": 4,
"name": "VariableDeclaration",
"src": "35:15:1"
},
{
"attributes":
{
"hexvalue": "48656c6c6f20f09f9883",
"isConstant": false,
"isLValue": false,
"isPure": true,
"lValueRequested": false,
"token": "unicodeString",
"type": "literal_string \"Hello \ud83d\ude03\"",
"value": "Hello \ud83d\ude03"
},
"id": 5,
"name": "Literal",
"src": "53:19:1"
}
],
"id": 6,
"name": "VariableDeclarationStatement",
"src": "35:37:1"
}
],
"id": 7,
"name": "Block",
"src": "33:42:1"
}
],
"id": 8,
"name": "FunctionDefinition",
"src": "13:62:1"
}
],
"id": 9,
"name": "ContractDefinition",
"src": "0:77:1"
}
],
"id": 10,
"name": "SourceUnit",
"src": "0:78:1"
}

View File

@ -81,6 +81,45 @@ BOOST_AUTO_TEST_CASE(assembly_multiple_assign)
BOOST_CHECK_EQUAL(scanner.next(), Token::EOS);
}
BOOST_AUTO_TEST_CASE(string_printable)
{
for (unsigned v = 0x20; v < 0x7e; v++) {
string lit{static_cast<char>(v)};
// Escape \ and " (since we are quoting with ")
if (v == '\\' || v == '"')
lit = string{'\\'} + lit;
Scanner scanner(CharStream(" { \"" + lit + "\"", ""));
BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
BOOST_CHECK_EQUAL(scanner.next(), Token::StringLiteral);
BOOST_CHECK_EQUAL(scanner.currentLiteral(), string{static_cast<char>(v)});
BOOST_CHECK_EQUAL(scanner.next(), Token::EOS);
}
// Special case of unescaped " for strings quoted with '
Scanner scanner(CharStream(" { '\"'", ""));
BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
BOOST_CHECK_EQUAL(scanner.next(), Token::StringLiteral);
BOOST_CHECK_EQUAL(scanner.currentLiteral(), "\"");
BOOST_CHECK_EQUAL(scanner.next(), Token::EOS);
}
BOOST_AUTO_TEST_CASE(string_nonprintable)
{
for (unsigned v = 0; v < 0xff; v++) {
// Skip the valid ones
if (v >= 0x20 && v <= 0x7e)
continue;
string lit{static_cast<char>(v)};
Scanner scanner(CharStream(" { \"" + lit + "\"", ""));
BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal);
if (v == '\n' || v == '\v' || v == '\f' || v == '\r')
BOOST_CHECK_EQUAL(scanner.currentError(), ScannerError::IllegalStringEndQuote);
else
BOOST_CHECK_EQUAL(scanner.currentError(), ScannerError::IllegalCharacterInString);
BOOST_CHECK_EQUAL(scanner.currentLiteral(), "");
}
}
BOOST_AUTO_TEST_CASE(string_escapes)
{
Scanner scanner(CharStream(" { \"a\\x61\"", ""));
@ -506,6 +545,8 @@ BOOST_AUTO_TEST_CASE(empty_comment)
}
// Unicode string escapes
BOOST_AUTO_TEST_CASE(valid_unicode_string_escape)
{
Scanner scanner(CharStream("{ \"\\u00DAnicode\"", ""));
@ -545,6 +586,25 @@ BOOST_AUTO_TEST_CASE(invalid_short_unicode_string_escape)
BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal);
}
// Unicode string literal
BOOST_AUTO_TEST_CASE(valid_unicode_literal)
{
Scanner scanner(CharStream("{ unicode\"Hello 😃\"", ""));
BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
BOOST_CHECK_EQUAL(scanner.next(), Token::UnicodeStringLiteral);
BOOST_CHECK_EQUAL(scanner.currentLiteral(), std::string("Hello \xf0\x9f\x98\x83", 10));
}
BOOST_AUTO_TEST_CASE(valid_nonprintable_in_unicode_literal)
{
// Non-printable characters are allowed in unicode strings...
Scanner scanner(CharStream("{ unicode\"Hello \007😃\"", ""));
BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
BOOST_CHECK_EQUAL(scanner.next(), Token::UnicodeStringLiteral);
BOOST_CHECK_EQUAL(scanner.currentLiteral(), std::string("Hello \x07\xf0\x9f\x98\x83", 11));
}
// HEX STRING LITERAL
BOOST_AUTO_TEST_CASE(valid_hex_literal)

View File

@ -1,9 +1,14 @@
contract C {
function f() public pure returns (string memory) {
return "😃, 😭, and 😈";
return unicode"😃, 😭, and 😈";
}
function g() public pure returns (string memory) {
return unicode"😃, 😭,\
and 😈";
}
}
// ====
// compileViaYul: also
// ----
// f() -> 0x20, 0x14, "\xf0\x9f\x98\x83, \xf0\x9f\x98\xad, and \xf0\x9f\x98\x88"
// g() -> 0x20, 0x14, "\xf0\x9f\x98\x83, \xf0\x9f\x98\xad, and \xf0\x9f\x98\x88"

View File

@ -1,4 +1,7 @@
contract test {
function fixedBytesHex() public returns(bytes32 ret) {
return hex"aabb00ff";
}
function fixedBytes() public returns(bytes32 ret) {
return "abc\x00\xff__";
}
@ -11,5 +14,6 @@ contract test {
// ====
// compileViaYul: also
// ----
// fixedBytesHex() -> "\xaa\xbb\0\xff"
// fixedBytes() -> "abc\0\xff__"
// pipeThrough(bytes2, bool): "\0\x02", true -> "\0\x2", true

View File

@ -1,3 +1,4 @@
contract C {
string s = "\xf0\x9f\xa6\x84";
}
// ----

View File

@ -0,0 +1,9 @@
contract test {
function f() public pure returns (string memory) {
return "hello world";
}
function g() public pure returns (string memory) {
return unicode"hello world";
}
}
// ----

View File

@ -0,0 +1,7 @@
contract test {
function f() public pure returns (bytes32) {
bytes32 escapeCharacters = unicode"foo" unicode"😃, 😭, and 😈" unicode"!";
return escapeCharacters;
}
}
// ----

View File

@ -0,0 +1,8 @@
contract test {
function f() public pure returns (bytes32) {
bytes32 escapeCharacters = "foo" hex"aa" unicode"😃, 😭, and 😈" "!" hex"00";
return escapeCharacters;
}
}
// ----
// ParserError 2314: (106-113): Expected ';' but got 'HexStringLiteral'

View File

@ -1,6 +1,6 @@
contract test {
function f() public pure returns (string memory) {
return "😃, 😭, and 😈";
return unicode"😃, 😭, and 😈";
}
}
// ----

View File

@ -0,0 +1,7 @@
contract test {
function f() public pure returns (string memory) {
return "😃, 😭, and 😈";
}
}
// ----
// ParserError 8936: (86-88): Invalid character in string.

View File

@ -19,3 +19,4 @@ contract test {
return res;
}
}
// ----