solidity/liblangutil/Scanner.h

249 lines
8.6 KiB
C
Raw Normal View History

2014-10-20 14:37:04 +00:00
/*
This file is part of solidity.
2014-10-20 14:37:04 +00:00
solidity is free software: you can redistribute it and/or modify
2014-10-20 14:37:04 +00:00
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
solidity is distributed in the hope that it will be useful,
2014-10-20 14:37:04 +00:00
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with solidity. If not, see <http://www.gnu.org/licenses/>.
2014-10-20 14:37:04 +00:00
This file is derived from the file "scanner.h", which was part of the
V8 project. The original copyright header follows:
Copyright 2006-2012, the V8 project authors. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following
disclaimer in the documentation and/or other materials provided
with the distribution.
* Neither the name of Google Inc. nor the names of its
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/**
* @author Christian <c@ethdev.com>
* @date 2014
* Solidity scanner.
*/
#pragma once
#include <liblangutil/Token.h>
2018-11-14 14:18:55 +00:00
#include <liblangutil/CharStream.h>
#include <liblangutil/SourceLocation.h>
#include <libdevcore/Common.h>
#include <libdevcore/CommonData.h>
#include <iosfwd>
namespace langutil
2014-10-16 12:08:54 +00:00
{
class AstRawString;
class AstValueFactory;
class ParserRecorder;
enum class ScannerError
{
NoError,
IllegalToken,
IllegalHexString,
IllegalHexDigit,
IllegalCommentTerminator,
IllegalEscapeSequence,
IllegalStringEndQuote,
IllegalNumberSeparator,
IllegalExponent,
IllegalNumberEnd,
OctalNotAllowed,
};
std::string to_string(ScannerError _errorCode);
std::ostream& operator<<(std::ostream& os, ScannerError _errorCode);
2014-10-16 12:08:54 +00:00
class Scanner
{
2014-11-30 22:25:42 +00:00
friend class LiteralScope;
public:
explicit Scanner(CharStream _source = CharStream(), std::string _sourceName = "") { reset(std::move(_source), std::move(_sourceName)); }
2014-10-09 10:28:37 +00:00
2016-11-14 10:46:43 +00:00
std::string source() const { return m_source.source(); }
/// Resets the scanner as if newly constructed with _source and _sourceName as input.
void reset(CharStream _source, std::string _sourceName);
/// Resets scanner to the start of input.
void reset();
2014-10-09 10:28:37 +00:00
/// @returns the next token and advances input
Token next();
2014-10-16 21:49:45 +00:00
///@{
///@name Information about the current token
2014-10-16 21:49:45 +00:00
/// @returns the current token
Token currentToken() const
{
return m_currentToken.token;
}
ElementaryTypeNameToken currentElementaryTypeNameToken() const
{
unsigned firstSize;
unsigned secondSize;
std::tie(firstSize, secondSize) = m_currentToken.extendedTokenInfo;
return ElementaryTypeNameToken(m_currentToken.token, firstSize, secondSize);
}
2015-08-31 16:44:29 +00:00
SourceLocation currentLocation() const { return m_currentToken.location; }
std::string const& currentLiteral() const { return m_currentToken.literal; }
std::tuple<unsigned, unsigned> const& currentTokenInfo() const { return m_currentToken.extendedTokenInfo; }
/// Retrieves the last error that occurred during lexical analysis.
/// @note If no error occurred, the value is undefined.
ScannerError currentError() const noexcept { return m_currentToken.error; }
///@}
///@{
///@name Information about the current comment token
2015-08-31 16:44:29 +00:00
SourceLocation currentCommentLocation() const { return m_skippedComment.location; }
std::string const& currentCommentLiteral() const { return m_skippedComment.literal; }
/// Called by the parser during FunctionDefinition parsing to clear the current comment
void clearCurrentCommentLiteral() { m_skippedComment.literal.clear(); }
///@}
///@{
///@name Information about the next token
2014-10-09 10:28:37 +00:00
/// @returns the next token without advancing input.
Token peekNextToken() const { return m_nextToken.token; }
SourceLocation peekLocation() const { return m_nextToken.location; }
std::string const& peekLiteral() const { return m_nextToken.literal; }
///@}
2014-10-09 10:28:37 +00:00
2015-08-31 16:44:29 +00:00
std::shared_ptr<std::string const> const& sourceName() const { return m_sourceName; }
///@{
///@name Error printing helper functions
/// Functions that help pretty-printing parse errors
2014-10-09 10:28:37 +00:00
/// Do only use in error cases, they are quite expensive.
2015-08-31 16:44:29 +00:00
std::string lineAtPosition(int _position) const { return m_source.lineAtPosition(_position); }
2014-10-16 21:49:45 +00:00
std::tuple<int, int> translatePositionToLineColumn(int _position) const { return m_source.translatePositionToLineColumn(_position); }
std::string sourceAt(SourceLocation const& _location) const
{
solAssert(!_location.isEmpty(), "");
solAssert(m_sourceName && _location.sourceName, "");
solAssert(*m_sourceName == *_location.sourceName, "");
return m_source.source().substr(_location.start, _location.end - _location.start);
}
///@}
2014-10-09 10:28:37 +00:00
private:
inline Token setError(ScannerError _error) noexcept
{
m_nextToken.error = _error;
return Token::Illegal;
}
2014-11-20 21:08:16 +00:00
/// Used for the current and look-ahead token and comments
2014-10-16 12:08:54 +00:00
struct TokenDesc
{
Token token;
SourceLocation location;
2014-10-09 10:28:37 +00:00
std::string literal;
ScannerError error = ScannerError::NoError;
std::tuple<unsigned, unsigned> extendedTokenInfo;
2014-10-09 10:28:37 +00:00
};
///@{
///@name Literal buffer support
inline void addLiteralChar(char c) { m_nextToken.literal.push_back(c); }
inline void addCommentLiteralChar(char c) { m_nextSkippedComment.literal.push_back(c); }
2014-10-16 12:08:54 +00:00
inline void addLiteralCharAndAdvance() { addLiteralChar(m_char); advance(); }
void addUnicodeAsUTF8(unsigned codepoint);
///@}
2014-10-09 10:28:37 +00:00
bool advance() { m_char = m_source.advanceAndGet(); return !m_source.isPastEndOfInput(); }
2014-10-16 21:49:45 +00:00
void rollback(int _amount) { m_char = m_source.rollback(_amount); }
2014-10-09 10:28:37 +00:00
inline Token selectErrorToken(ScannerError _err) { advance(); return setError(_err); }
inline Token selectToken(Token _tok) { advance(); return _tok; }
2014-10-16 21:49:45 +00:00
/// If the next character is _next, advance and return _then, otherwise return _else.
inline Token selectToken(char _next, Token _then, Token _else);
2014-10-09 10:28:37 +00:00
2014-11-05 13:20:56 +00:00
bool scanHexByte(char& o_scannedByte);
bool scanUnicode(unsigned& o_codepoint);
2014-10-09 10:28:37 +00:00
/// Scans a single Solidity token.
void scanToken();
2014-10-09 10:28:37 +00:00
/// Skips all whitespace and @returns true if something was skipped.
2014-10-09 10:28:37 +00:00
bool skipWhitespace();
/// Skips all whitespace that are neither '\r' nor '\n'.
void skipWhitespaceExceptUnicodeLinebreak();
Token skipSingleLineComment();
Token skipMultiLineComment();
2014-10-09 10:28:37 +00:00
void scanDecimalDigits();
Token scanNumber(char _charSeen = 0);
std::tuple<Token, unsigned, unsigned> scanIdentifierOrKeyword();
2014-10-09 10:28:37 +00:00
Token scanString();
Token scanHexString();
Token scanSingleLineDocComment();
Token scanMultiLineDocComment();
/// Scans a slash '/' and depending on the characters returns the appropriate token
Token scanSlash();
2014-10-09 10:28:37 +00:00
2014-10-16 21:49:45 +00:00
/// Scans an escape-sequence which is part of a string and adds the
/// decoded character to the current literal. Returns true if a pattern
/// is scanned.
2014-10-09 10:28:37 +00:00
bool scanEscape();
/// @returns true iff we are currently positioned at a unicode line break.
bool isUnicodeLinebreak();
2014-10-16 21:49:45 +00:00
/// Return the current source position.
int sourcePos() const { return m_source.position(); }
bool isSourcePastEndOfInput() const { return m_source.isPastEndOfInput(); }
2014-10-09 10:28:37 +00:00
TokenDesc m_skippedComment; // desc for current skipped comment
TokenDesc m_nextSkippedComment; // desc for next skipped comment
TokenDesc m_currentToken; // desc for current token (as returned by Next())
TokenDesc m_nextToken; // desc for next token (one token look-ahead)
2014-10-09 10:28:37 +00:00
CharStream m_source;
std::shared_ptr<std::string const> m_sourceName;
2014-10-09 10:28:37 +00:00
2014-10-16 21:49:45 +00:00
/// one character look-ahead, equals 0 at end of input
2014-10-09 10:28:37 +00:00
char m_char;
};
2014-10-16 12:08:54 +00:00
}