Introduce hex literals (#832)

* Introduce hex keyword token

* Support hex literals

* Include tests for hex literals

* Document hex literals

5 files changed, 82 insertions, 0 deletions

diff --git a/docs/types.rst b/docs/types.rst
index 12a35aaf..31f6b53d 100644
--- a/docs/types.rst
+++ b/docs/types.rst
@@ -218,6 +218,15 @@ String literals are written with either double or single-quotes (``"foo"`` or ``
 
 String literals support escape characters, such as ``\n``, ``\xNN`` and ``\uNNNN``. ``\xNN`` takes a hex value and inserts the appropriate byte, while ``\uNNNN`` takes a Unicode codepoint and inserts an UTF-8 sequence.
 
+.. index:: literal, bytes
+
+Hexadecimal Literals
+--------------------
+
+Hexademical Literals are prefixed with the keyword ``hex`` and are enclosed in double or single-quotes (``hex"001122FF"``). Their content must be a hexadecimal string and their value will be the binary representation of those values.
+
+Hexademical Literals behave like String Literals and have the same convertibility restrictions.
+
 .. index:: enum
 
 .. _enums:
diff --git a/libsolidity/parsing/Scanner.cpp b/libsolidity/parsing/Scanner.cpp
index d730210a..603f3e42 100644
--- a/libsolidity/parsing/Scanner.cpp
+++ b/libsolidity/parsing/Scanner.cpp
@@ -591,7 +591,23 @@ void Scanner::scanToken()
 			break;
 		default:
 			if (isIdentifierStart(m_char))
+			{
 				tie(token, m, n) = scanIdentifierOrKeyword();
+
+				// Special case for hexademical literals
+				if (token == Token::Hex)
+				{
+					// reset
+					m = 0;
+					n = 0;
+
+					// Special quoted hex string must follow
+					if (m_char == '"' || m_char == '\'')
+						token = scanHexString();
+					else
+						token = Token::Illegal;
+				}
+			}
 			else if (isDecimalDigit(m_char))
 				token = scanNumber();
 			else if (skipWhitespace())
@@ -684,6 +700,25 @@ Token::Value Scanner::scanString()
 	return Token::StringLiteral;
 }
 
+Token::Value Scanner::scanHexString()
+{
+	char const quote = m_char;
+	advance();  // consume quote
+	LiteralScope literal(this, LITERAL_TYPE_STRING);
+	while (m_char != quote && !isSourcePastEndOfInput() && !isLineTerminator(m_char))
+	{
+		char c = m_char;
+		if (!scanHexByte(c))
+			return Token::Illegal;
+		addLiteralChar(c);
+	}
+	if (m_char != quote)
+		return Token::Illegal;
+	literal.complete();
+	advance();  // consume quote
+	return Token::StringLiteral;
+}
+
 void Scanner::scanDecimalDigits()
 {
 	while (isDecimalDigit(m_char))
diff --git a/libsolidity/parsing/Scanner.h b/libsolidity/parsing/Scanner.h
index 708adf8f..36cba112 100644
--- a/libsolidity/parsing/Scanner.h
+++ b/libsolidity/parsing/Scanner.h
@@ -203,6 +203,7 @@ private:
 	std::tuple<Token::Value, unsigned, unsigned> scanIdentifierOrKeyword();
 
 	Token::Value scanString();
+	Token::Value scanHexString();
 	Token::Value scanSingleLineDocComment();
 	Token::Value scanMultiLineDocComment();
 	/// Scans a slash '/' and depending on the characters returns the appropriate token
diff --git a/libsolidity/parsing/Token.h b/libsolidity/parsing/Token.h
index f4de74c7..007baef4 100644
--- a/libsolidity/parsing/Token.h
+++ b/libsolidity/parsing/Token.h
@@ -155,6 +155,7 @@ namespace solidity
 	K(External, "external", 0)                                         \
 	K(For, "for", 0)                                                   \
 	K(Function, "function", 0)                                         \
+	K(Hex, "hex", 0)                                                   \
 	K(If, "if", 0)                                                     \
 	K(Indexed, "indexed", 0)                                           \
 	K(Internal, "internal", 0)                                         \
diff --git a/test/libsolidity/SolidityScanner.cpp b/test/libsolidity/SolidityScanner.cpp
index 624614d2..31b75f25 100644
--- a/test/libsolidity/SolidityScanner.cpp
+++ b/test/libsolidity/SolidityScanner.cpp
@@ -324,6 +324,42 @@ BOOST_AUTO_TEST_CASE(invalid_short_unicode_string_escape)
 	BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal);
 }
 
+BOOST_AUTO_TEST_CASE(valid_hex_literal)
+{
+	Scanner scanner(CharStream("{ hex\"00112233FF\""));
+	BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
+	BOOST_CHECK_EQUAL(scanner.next(), Token::StringLiteral);
+	BOOST_CHECK_EQUAL(scanner.currentLiteral(), std::string("\x00\x11\x22\x33\xFF", 5));
+}
+
+BOOST_AUTO_TEST_CASE(invalid_short_hex_literal)
+{
+	Scanner scanner(CharStream("{ hex\"00112233F\""));
+	BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
+	BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal);
+}
+
+BOOST_AUTO_TEST_CASE(invalid_hex_literal_with_space)
+{
+	Scanner scanner(CharStream("{ hex\"00112233FF \""));
+	BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
+	BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal);
+}
+
+BOOST_AUTO_TEST_CASE(invalid_hex_literal_with_wrong_quotes)
+{
+	Scanner scanner(CharStream("{ hex\"00112233FF'"));
+	BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
+	BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal);
+}
+
+BOOST_AUTO_TEST_CASE(invalid_hex_literal_nonhex_string)
+{
+	Scanner scanner(CharStream("{ hex\"hello\""));
+	BOOST_CHECK_EQUAL(scanner.currentToken(), Token::LBrace);
+	BOOST_CHECK_EQUAL(scanner.next(), Token::Illegal);
+}
+
 
 BOOST_AUTO_TEST_SUITE_END()