push.fg.c

a little DFA compiler.

/* Generated by re2c */
#line 1 "push.fg.re"
/*
 *  A push-model scanner example for re2c -f
 *  Written Mon Apr 11 2005 by [e-mail]
 *  This file is in the public domain.
 *
 */

// ----------------------------------------------------------------------

#include <fcntl.h>
#include <stdio.h>
#include <stddef.h>
#include <stdlib.h>
#include <string.h>

#if defined(WIN32)

    typedef signed char     int8_t;
    typedef signed short    int16_t;
    typedef signed int      int32_t;

    typedef unsigned char   uint8_t;
    typedef unsigned short  uint16_t;
    typedef unsigned int    uint32_t;

#else

    #include <stdint.h>
    #include <unistd.h>

    #ifndef O_BINARY
        #define O_BINARY 0
    #endif

#endif

// ----------------------------------------------------------------------
#define TOKENS              \
                            \
    TOK(kEOF)               \
    TOK(kEOL)               \
    TOK(kUnknown)           \
    TOK(kIdentifier)        \
    TOK(kDecimalConstant)   \
                            \
    TOK(kEqual)             \
    TOK(kLeftParen)         \
    TOK(kRightParen)        \
    TOK(kMinus)             \
    TOK(kPlus)              \
    TOK(kStar)              \
    TOK(kSlash)             \
                            \
    TOK(kIf)                \
    TOK(kFor)               \
    TOK(kElse)              \
    TOK(kGoto)              \
    TOK(kBreak)             \
    TOK(kWhile)             \
    TOK(kReturn)            \


// ----------------------------------------------------------------------
static const char *tokenNames[] =
{
    #define TOK(x) #x,
        TOKENS
    #undef TOK
};

// ----------------------------------------------------------------------
class PushScanner
{
public:

    enum Token
    {
        #define TOK(x) x,
            TOKENS
        #undef TOK
    };

private:

    bool        eof;
    int32_t     state;

    uint8_t     *limit;
    uint8_t     *start;
    uint8_t     *cursor;
    uint8_t     *marker;

    uint8_t     *buffer;
    uint8_t     *bufferEnd;

    uint8_t     yych;
    uint32_t    yyaccept;

public:

    // ----------------------------------------------------------------------
    PushScanner()
    {
        limit = 0;
        start = 0;
        state = -1;
        cursor = 0;
        marker = 0;
        buffer = 0;
        eof = false;
        bufferEnd = 0;
    }

    // ----------------------------------------------------------------------
    ~PushScanner()
    {
    }

    // ----------------------------------------------------------------------
    void send(
        Token token
    )
    {
        size_t tokenSize = cursor-start;
        const char *tokenName = tokenNames[token];
        printf(
            "scanner is pushing out a token of type %d (%s)",
            token,
            tokenName
        );

        if(token==kEOF) putchar('\n');
        else
        {
            size_t tokenNameSize = strlen(tokenNames[token]);
            size_t padSize = 20-(20<tokenNameSize ? 20 : tokenNameSize);
            for(size_t i=0; i<padSize; ++i) putchar(' ');
            printf(" : ---->");

            fwrite(
                start,
                tokenSize,
                1,
                stdout
            );

            printf("<----\n");
        }
    }

    // ----------------------------------------------------------------------
    uint32_t push(
        const void  *input,
        ssize_t     inputSize
    )
    {
        printf(
            "scanner is receiving a new data batch of length %d\n"
            "scanner continues with saved state = %d\n",
            inputSize,
            state
        );

        /*
         * Data source is signaling end of file when batch size
         * is less than maxFill. This is slightly annoying because
         * maxFill is a value that can only be known after re2c does
         * its thing. Practically though, maxFill is never bigger than
         * the longest keyword, so given our grammar, 32 is a safe bet.
         */
        uint8_t null[64];
        const ssize_t maxFill = 32;
        if(inputSize<maxFill)
        {
            eof = true;
            input = null;
            inputSize = sizeof(null);
            memset(null, 0, sizeof(null));
        }

        /*
         * When we get here, we have a partially
         * consumed buffer which is in the following state:
         *                                                                last valid char        last valid buffer spot
         *                                                                v                      v
         * +-------------------+-------------+---------------+-------------+----------------------+
         * ^                   ^             ^               ^             ^                      ^
         * buffer              start         marker          cursor        limit                  bufferEnd
         * 
         * We need to stretch the buffer and concatenate the new chunk of input to it
         *
         */
        size_t used = limit-buffer;
        size_t needed = used+inputSize;
        size_t allocated = bufferEnd-buffer;
        if(allocated<needed)
        {
            size_t limitOffset = limit-buffer;
            size_t startOffset = start-buffer;
            size_t markerOffset = marker-buffer;
            size_t cursorOffset = cursor-buffer;

                buffer = (uint8_t*)realloc(buffer, needed);
                bufferEnd = needed+buffer;

            marker = markerOffset + buffer;
            cursor = cursorOffset + buffer;
            start = buffer + startOffset;
            limit = limitOffset + buffer;
        }
        memcpy(limit, input, inputSize);
        limit += inputSize;

        // The scanner starts here
        #define YYLIMIT         limit
        #define YYCURSOR        cursor
        #define YYMARKER        marker
        #define YYCTYPE         uint8_t

        #define SKIP(x)         { start = cursor; goto yy0; }
        #define SEND(x)         { send(x); SKIP();          }
        #define YYFILL(n)       { goto fill;                }

        #define YYGETSTATE()    state
        #define YYSETSTATE(x)   { state = (x);  }

    start:

        {
	static const unsigned char yybm[] = {
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		192, 192, 192, 192, 192, 192, 192, 192, 
		192, 192,   0,   0,   0,   0,   0,   0, 
		  0, 128, 128, 128, 128, 128, 128, 128, 
		128, 128, 128, 128, 128, 128, 128, 128, 
		128, 128, 128, 128, 128, 128, 128, 128, 
		128, 128, 128,   0,   0,   0,   0, 128, 
		  0, 128, 128, 128, 128, 128, 128, 128, 
		128, 128, 128, 128, 128, 128, 128, 128, 
		128, 128, 128, 128, 128, 128, 128, 128, 
		128, 128, 128,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
		  0,   0,   0,   0,   0,   0,   0,   0, 
	};

#line 268 "<stdout>"
	{

		switch(YYGETSTATE()) {
		default: goto yy0;
		case 0: goto yyFillLabel0;
		case 1: goto yyFillLabel1;
		case 2: goto yyFillLabel2;
		}
yy0:
		YYSETSTATE(0);
		if((YYLIMIT - YYCURSOR) < 7) YYFILL(7);
yyFillLabel0:
		yych = *YYCURSOR;
		{
			static void *yytarget[256] = {
				&&yy32, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy30, &&yy28, &&yy30, &&yy30, &&yy30, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy30, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy16, &&yy18, &&yy24, &&yy22, &&yy34, &&yy20, &&yy34, &&yy26,
				&&yy12, &&yy12, &&yy12, &&yy12, &&yy12, &&yy12, &&yy12, &&yy12,
				&&yy12, &&yy12, &&yy34, &&yy34, &&yy34, &&yy14, &&yy34, &&yy34,
				&&yy34, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10,
				&&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10,
				&&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10,
				&&yy10, &&yy10, &&yy10, &&yy34, &&yy34, &&yy34, &&yy34, &&yy10,
				&&yy34, &&yy10, &&yy7,  &&yy10, &&yy10, &&yy5,  &&yy4,  &&yy6,
				&&yy11, &&yy2,  &&yy10, &&yy10, &&yy10, &&yy10, &&yy10, &&yy10,
				&&yy10, &&yy10, &&yy9,  &&yy10, &&yy10, &&yy10, &&yy10, &&yy8,
				&&yy10, &&yy10, &&yy10, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,
				&&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34, &&yy34,