cpplexer.cpp

qt-x11-opensource-src-4.1.4.tar.gz源码

/****************************************************************************
**
** Copyright (C) 2004-2006 Trolltech ASA. All rights reserved.
** Copyright (C) 2001-2004 Roberto Raggi
**
** This file is part of the qt3to4 porting application of the Qt Toolkit.
**
** This file may be used under the terms of the GNU General Public
** License version 2.0 as published by the Free Software Foundation
** and appearing in the file LICENSE.GPL included in the packaging of
** this file.  Please review the following information to ensure GNU
** General Public Licensing requirements will be met:
** http://www.trolltech.com/products/qt/opensource.html
**
** If you are unsure which license is appropriate for your use, please
** review the following information:
** http://www.trolltech.com/products/qt/licensing.html or contact the
** sales department at [e-mail].
**
** This file is provided AS IS with NO WARRANTY OF ANY KIND, INCLUDING THE
** WARRANTY OF DESIGN, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
**
****************************************************************************/

#include "cpplexer.h"
#include <QChar>
#include <ctype.h>

using namespace TokenEngine;

CppLexer::CppLexer()
{
    setupScanTable();
}

void CppLexer::setupScanTable()
{
    s_scan_keyword_table[0] = &CppLexer::scanKeyword0;
    s_scan_keyword_table[1] = &CppLexer::scanKeyword0;
    s_scan_keyword_table[2] = &CppLexer::scanKeyword2;
    s_scan_keyword_table[3] = &CppLexer::scanKeyword3;
    s_scan_keyword_table[4] = &CppLexer::scanKeyword4;
    s_scan_keyword_table[5] = &CppLexer::scanKeyword5;
    s_scan_keyword_table[6] = &CppLexer::scanKeyword6;
    s_scan_keyword_table[7] = &CppLexer::scanKeyword7;
    s_scan_keyword_table[8] = &CppLexer::scanKeyword8;
    s_scan_keyword_table[9] = &CppLexer::scanKeyword9;
    s_scan_keyword_table[10] = &CppLexer::scanKeyword10;
    s_scan_keyword_table[11] = &CppLexer::scanKeyword11;
    s_scan_keyword_table[12] = &CppLexer::scanKeyword12;
    s_scan_keyword_table[13] = &CppLexer::scanKeyword0;
    s_scan_keyword_table[14] = &CppLexer::scanKeyword14;
    s_scan_keyword_table[15] = &CppLexer::scanKeyword0;
    s_scan_keyword_table[16] = &CppLexer::scanKeyword16;

    memset(s_attr_table, 0, 256);

    for (int i=0; i<128; ++i) {
        switch (i) {
        case ':':
        case '*':
        case '/':
        case '%':
        case '^':
        case '=':
        case '!':
        case '&':
        case '|':
        case '+':
        case '<':
        case '>':
        case '-':
        case '.':
            s_scan_table[i] = &CppLexer::scanOperator;
            break;

        case '\r':
        case '\n':
            s_scan_table[i] = &CppLexer::scanNewline;
            break;

        case '\'':
            s_scan_table[i] = &CppLexer::scanCharLiteral;
            break;

        case '"':
            s_scan_table[i] = &CppLexer::scanStringLiteral;
            break;

        default:
            if (isspace(i)) {
                s_scan_table[i] = &CppLexer::scanWhiteSpaces;
                s_attr_table[i] |= A_Whitespace;
            } else if (isalpha(i) || i == '_') {
                s_scan_table[i] = &CppLexer::scanIdentifier;
                s_attr_table[i] |= A_Alpha;
            } else if (isdigit(i)) {
                s_scan_table[i] = &CppLexer::scanNumberLiteral;
                s_attr_table[i] |= A_Digit;
            } else
                s_scan_table[i] = &CppLexer::scanChar;
        }
    }

    s_scan_table[128] = &CppLexer::scanUnicodeChar;
}

QVector<Type> CppLexer::lex(TokenSectionSequence tokenSectionSequence)
{
    QVector<Type> tokenTypes;
    tokenTypes.reserve(tokenSectionSequence.count());
    TokenSectionSequenceIterator it(tokenSectionSequence);
    while(it.nextToken()) {
        tokenTypes.append(identify(it.tokenTempRef()));
    }
    return tokenTypes;
}

Type CppLexer::identify(const TokenTempRef &tokenTempRef)
{
    Q_ASSERT(tokenTempRef.length() >= 0 );
    m_buffer = tokenTempRef.constData();
    m_len = tokenTempRef.length();
    m_ptr = 0;
    const unsigned char ch = m_buffer[0];
    int kind = 0;
    (this->*s_scan_table[ch < 128 ? ch : 128])(&kind);
    return (Type)kind;
}

void CppLexer::scanKeyword0(int *kind)
{
    *kind = Token_identifier;
}

void CppLexer::scanKeyword2(int *kind)
{
    switch (m_buffer[m_ptr]) {
        case 'i':
        if (m_buffer[m_ptr+1] == 'f')
        {
            *kind = Token_if;
            return;
        }
        break;

        case 'd':
        if (m_buffer[m_ptr+1] == 'o')
        {
            *kind = Token_do;
            return;
        }
        break;

        case 'o':
        if (m_buffer[m_ptr+1] == 'r')
        {
            *kind = Token_or;
            return;
        }
        break;

    }
    *kind = Token_identifier;
}

void CppLexer::scanKeyword3(int *kind)
{
    switch (m_buffer[m_ptr]) {
        case 'a':
        if (m_buffer[m_ptr+1] == 'n' &&
            m_buffer[m_ptr+2] == 'd')
        {
            *kind = Token_and;
            return;
        }
        if (m_buffer[m_ptr+1] == 's' &&
            m_buffer[m_ptr+2] == 'm')
        {
            *kind = Token_asm;
            return;
        }
        break;

        case 'f':
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 'r')
        {
            *kind = Token_for;
            return;
        }
        break;

        case 'i':
        if (m_buffer[m_ptr+1] == 'n' &&
            m_buffer[m_ptr+2] == 't')
        {
            *kind = Token_int;
            return;
        }
        break;

        case 'n':
        if (m_buffer[m_ptr+1] == 'e' &&
            m_buffer[m_ptr+2] == 'w')
        {
            *kind = Token_new;
            return;
        }
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 't')
        {
            *kind = Token_not;
            return;
        }
        break;

        case 't':
        if (m_buffer[m_ptr+1] == 'r' &&
            m_buffer[m_ptr+2] == 'y')
        {
            *kind = Token_try;
            return;
        }
        break;

         case 'x':
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 'r')
        {
            *kind = Token_xor;
            return;
        }
        break;

    }
    *kind = Token_identifier;
}

void CppLexer::scanKeyword4(int *kind)
{
    switch (m_buffer[m_ptr]) {
        case 'a':
        if (m_buffer[m_ptr+1] == 'u' &&
            m_buffer[m_ptr+2] == 't' &&
            m_buffer[m_ptr+3] == 'o')
        {
            *kind = Token_auto;
            return;
        }
        break;

        case 'c':
        if (m_buffer[m_ptr+1] == 'a' &&
            m_buffer[m_ptr+2] == 's' &&
            m_buffer[m_ptr+3] == 'e')
        {
            *kind = Token_case;
            return;
        }
        if (m_buffer[m_ptr+1] == 'h' &&
            m_buffer[m_ptr+2] == 'a' &&
            m_buffer[m_ptr+3] == 'r')
        {
            *kind = Token_char;
            return;
        }
        break;

        case 'b':
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 'o' &&
            m_buffer[m_ptr+3] == 'l')
        {
            *kind = Token_bool;
            return;
        }
        break;

        case 'e':
        if (m_buffer[m_ptr+1] == 'l' &&
            m_buffer[m_ptr+2] == 's' &&
            m_buffer[m_ptr+3] == 'e')
        {
            *kind = Token_else;
            return;
        }
        if (m_buffer[m_ptr+1] == 'm' &&
            m_buffer[m_ptr+2] == 'i' &&
            m_buffer[m_ptr+3] == 't')
        {
            *kind = Token_emit;
            return;
        }
        if (m_buffer[m_ptr+1] == 'n' &&
            m_buffer[m_ptr+2] == 'u' &&
            m_buffer[m_ptr+3] == 'm')
        {
            *kind = Token_enum;
            return;
        }
        break;

        case 'g':
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 't' &&
            m_buffer[m_ptr+3] == 'o')
        {
            *kind = Token_goto;
             return;
        }
        break;

        case 'l':
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 'n' &&
            m_buffer[m_ptr+3] == 'g')
        {
            *kind = Token_long;
            return;
        }
        break;

        case 't':
        if (m_buffer[m_ptr+1] == 'h' &&
            m_buffer[m_ptr+2] == 'i' &&
            m_buffer[m_ptr+3] == 's')
        {
            *kind = Token_this;
            return;
        }
        break;

        case 'v':
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 'i' &&
            m_buffer[m_ptr+3] == 'd')
        {
            *kind = Token_void;
            return;
        }
        break;

    }
    *kind = Token_identifier;
}

void CppLexer::scanKeyword5(int *kind)
{
    switch (m_buffer[m_ptr]) {
        case 'c':
        if (m_buffer[m_ptr+1] == 'a' &&
            m_buffer[m_ptr+2] == 't' &&
            m_buffer[m_ptr+3] == 'c' &&
            m_buffer[m_ptr+4] == 'h')
        {
            *kind = Token_catch;
            return;
        }
        if (m_buffer[m_ptr+1] == 'l' &&
            m_buffer[m_ptr+2] == 'a' &&
            m_buffer[m_ptr+3] == 's' &&
            m_buffer[m_ptr+4] == 's')
        {
            *kind = Token_class;
            return;
        }
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 'm' &&
            m_buffer[m_ptr+3] == 'p' &&
            m_buffer[m_ptr+4] == 'l')
        {
            *kind = Token_compl;
            return;
        }
        if (m_buffer[m_ptr+1] == 'o' &&
            m_buffer[m_ptr+2] == 'n' &&
            m_buffer[m_ptr+3] == 's' &&
            m_buffer[m_ptr+4] == 't')
        {
            *kind = Token_const;
            return;
        }
        break;

        case 'b':
        if (m_buffer[m_ptr+1] == 'i' &&
            m_buffer[m_ptr+2] == 't' &&
            m_buffer[m_ptr+3] == 'o' &&
            m_buffer[m_ptr+4] == 'r')
        {
            *kind = Token_bitor;
            return;
        }
        if (m_buffer[m_ptr+1] == 'r' &&
            m_buffer[m_ptr+2] == 'e' &&
            m_buffer[m_ptr+3] == 'a' &&
            m_buffer[m_ptr+4] == 'k')
        {
            *kind = Token_break;
            return;
        }
        break;

        case 'f':
        if (m_buffer[m_ptr+1] == 'l' &&
            m_buffer[m_ptr+2] == 'o' &&
            m_buffer[m_ptr+3] == 'a' &&
            m_buffer[m_ptr+4] == 't')
        {
            *kind = Token_float;
            return;
        }
        break;

        case 'o':
        if (m_buffer[m_ptr+1] == 'r' &&
            m_buffer[m_ptr+2] == '_' &&
            m_buffer[m_ptr+3] == 'e' &&
            m_buffer[m_ptr+4] == 'q')
        {
            *kind = Token_or_eq;
            return;
        }
        break;