push.c

a little DFA compiler.

	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy38;
	default:	goto yy45;
	}
yy45:
#line 245 "push.re"
	{ SEND(kReturn);         }
#line 618 "<stdout>"
yy46:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'i':	goto yy47;
	default:	goto yy39;
	}
yy47:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'l':	goto yy48;
	default:	goto yy39;
	}
yy48:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'e':	goto yy49;
	default:	goto yy39;
	}
yy49:
	++YYCURSOR;
	switch((yych = *YYCURSOR)) {
	case '0':
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':
	case '_':
	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy38;
	default:	goto yy50;
	}
yy50:
#line 244 "push.re"
	{ SEND(kWhile);          }
#line 708 "<stdout>"
yy51:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'e':	goto yy52;
	default:	goto yy39;
	}
yy52:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'a':	goto yy53;
	default:	goto yy39;
	}
yy53:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'k':	goto yy54;
	default:	goto yy39;
	}
yy54:
	++YYCURSOR;
	switch((yych = *YYCURSOR)) {
	case '0':
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':
	case '_':
	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy38;
	default:	goto yy55;
	}
yy55:
#line 243 "push.re"
	{ SEND(kBreak);          }
#line 798 "<stdout>"
yy56:
	yych = *++YYCURSOR;
	switch(yych) {
	case 't':	goto yy57;
	default:	goto yy39;
	}
yy57:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'o':	goto yy58;
	default:	goto yy39;
	}
yy58:
	++YYCURSOR;
	switch((yych = *YYCURSOR)) {
	case '0':
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':
	case '_':
	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy38;
	default:	goto yy59;
	}
yy59:
#line 242 "push.re"
	{ SEND(kGoto);           }
#line 882 "<stdout>"
yy60:
	yych = *++YYCURSOR;
	switch(yych) {
	case 's':	goto yy61;
	default:	goto yy39;
	}
yy61:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'e':	goto yy62;
	default:	goto yy39;
	}
yy62:
	++YYCURSOR;
	switch((yych = *YYCURSOR)) {
	case '0':
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':
	case '_':
	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy38;
	default:	goto yy63;
	}
yy63:
#line 241 "push.re"
	{ SEND(kElse);           }
#line 966 "<stdout>"
yy64:
	yych = *++YYCURSOR;
	switch(yych) {
	case 'r':	goto yy65;
	default:	goto yy39;
	}
yy65:
	++YYCURSOR;
	switch((yych = *YYCURSOR)) {
	case '0':
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':
	case '_':
	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy38;
	default:	goto yy66;
	}
yy66:
#line 240 "push.re"
	{ SEND(kFor);            }
#line 1044 "<stdout>"
yy67:
	++YYCURSOR;
	switch((yych = *YYCURSOR)) {
	case '0':
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
	case 'A':
	case 'B':
	case 'C':
	case 'D':
	case 'E':
	case 'F':
	case 'G':
	case 'H':
	case 'I':
	case 'J':
	case 'K':
	case 'L':
	case 'M':
	case 'N':
	case 'O':
	case 'P':
	case 'Q':
	case 'R':
	case 'S':
	case 'T':
	case 'U':
	case 'V':
	case 'W':
	case 'X':
	case 'Y':
	case 'Z':
	case '_':
	case 'a':
	case 'b':
	case 'c':
	case 'd':
	case 'e':
	case 'f':
	case 'g':
	case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':	goto yy38;
	default:	goto yy68;
	}
yy68:
#line 239 "push.re"
	{ SEND(kIf);             }
#line 1116 "<stdout>"
}
#line 261 "push.re"


    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;
}