push.re

a little DFA compiler.

/*
 *  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:

        /*!re2c

            eol = "\n";
            eof = "\000";
            digit = [0-9];
            integer = digit+;
            alpha = [A-Za-z_];
            any = [\000-\0377];
            space = [ \h\t\v\f\r];

            "if"                    { SEND(kIf);             }
            "for"                   { SEND(kFor);            }
            "else"                  { SEND(kElse);           }
            "goto"                  { SEND(kGoto);           }
            "break"                 { SEND(kBreak);          }
            "while"                 { SEND(kWhile);          }
            "return"                { SEND(kReturn);         }
            alpha (alpha|digit)*    { SEND(kIdentifier);     }
            integer                 { SEND(kDecimalConstant);}

            "="                     { SEND(kEqual);          }
            "("                     { SEND(kLeftParen);      }
            ")"                     { SEND(kRightParen);     }
            "-"                     { SEND(kMinus);          }
            "+"                     { SEND(kPlus);           }
            "*"                     { SEND(kStar);           }
            "/"                     { SEND(kSlash);          }

            eol                     { SKIP();                }
            space                   { SKIP();                }
            eof                     { send(kEOF); return 1;  }
            any                     { SEND(kUnknown);        }
        */

    fill:
        ssize_t unfinishedSize = cursor-start;
        printf(
            "scanner needs a refill. Exiting for now with:\n"
            "    saved fill state = %d\n"
            "    unfinished token size = %d\n",
            state,
            unfinishedSize
        );

        if(0<unfinishedSize && start<limit)
        {
            printf("    unfinished token is :");
            fwrite(start, 1, cursor-start, stdout);
            putchar('\n');
        }
        putchar('\n');

        /*
         * Once we get here, we can get rid of
         * everything before start and after limit.
         */
        if(eof==true) goto start;
        if(buffer<start)
        {
            size_t startOffset = start-buffer;
            memmove(buffer, start, limit-start);
            marker -= startOffset;
            cursor -= startOffset;
            limit -= startOffset;
            start -= startOffset;
        }
        return 0;
    }
};

// ----------------------------------------------------------------------
int main(
    int     argc,
    char    **argv
)
{
    // Parse cmd line
    int input = 0;
    if(1<argc)
    {
        input = open(argv[1], O_RDONLY | O_BINARY);
        if(input<0)
        {
            fprintf(
                stderr,
                "could not open file %s\n",
                argv[1]
            );
            exit(1);
        }
    }

    /*
     * Tokenize input file by pushing batches
     * of data one by one into the scanner.
     */
    const size_t batchSize = 256;
    uint8_t buffer[batchSize];
    PushScanner scanner;
    while(1)
    {
        ssize_t n = read(input, buffer, batchSize);
        scanner.push(buffer, n);
        if(n<batchSize) break;
    }
    scanner.push(0, -1);
    close(input);

    // Done
    return 0;
}