parser.c

nasm的全套源代码,有些我做了些修改,以方便您更方便更容易调试成功,方便学习做编译器

/* parser.c   source line parser for the Netwide Assembler
 *
 * The Netwide Assembler is copyright (C) 1996 Simon Tatham and
 * Julian Hall. All rights reserved. The software is
 * redistributable under the licence given in the file "Licence"
 * distributed in the NASM archive.
 *
 * initial version 27/iii/95 by Simon Tatham
 */

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

#include "nasm.h"
#include "insns.h"
#include "nasmlib.h"
#include "parser.h"
#include "float.h"

extern int in_abs_seg;          /* ABSOLUTE segment flag */
extern long abs_seg;            /* ABSOLUTE segment */
extern long abs_offset;         /* ABSOLUTE segment offset */

#include "regflags.c"           /* List of register flags */

enum {                          /* special tokens */
    S_BYTE, S_DWORD, S_FAR, S_LONG, S_NEAR, S_NOSPLIT, S_QWORD,
    S_SHORT, S_STRICT, S_TO, S_TWORD, S_WORD
};

static int is_comma_next(void);

static int i;
static struct tokenval tokval;
static efunc error;
static struct ofmt *outfmt;     /* Structure of addresses of output routines */
static loc_t *location;         /* Pointer to current line's segment,offset */

void parser_global_info(struct ofmt *output, loc_t * locp)
{
    outfmt = output;
    location = locp;
}

insn *parse_line(int pass, char *buffer, insn * result,
                 efunc errfunc, evalfunc evaluate, ldfunc ldef)
{
    int operand;
    int critical;
    struct eval_hints hints;

    result->forw_ref = FALSE;
    error = errfunc;

    stdscan_reset();
    stdscan_bufptr = buffer;
    i = stdscan(NULL, &tokval);

    result->label = NULL;       /* Assume no label */
    result->eops = NULL;        /* must do this, whatever happens */
    result->operands = 0;       /* must initialise this */

    if (i == 0) {               /* blank line - ignore */
        result->opcode = -1;    /* and no instruction either */
        return result;
    }
    if (i != TOKEN_ID && i != TOKEN_INSN && i != TOKEN_PREFIX &&
        (i != TOKEN_REG || (REG_SREG & ~reg_flags[tokval.t_integer]))) {
        error(ERR_NONFATAL, "label or instruction expected"
              " at start of line");
        result->opcode = -1;
        return result;
    }

    if (i == TOKEN_ID) {        /* there's a label here */
        result->label = tokval.t_charptr;
        i = stdscan(NULL, &tokval);
        if (i == ':') {         /* skip over the optional colon */
            i = stdscan(NULL, &tokval);
        } else if (i == 0) {
            error(ERR_WARNING | ERR_WARN_OL | ERR_PASS1,
                  "label alone on a line without a colon might be in error");
        }
        if (i != TOKEN_INSN || tokval.t_integer != I_EQU) {
            /*
             * FIXME: location->segment could be NO_SEG, in which case
             * it is possible we should be passing 'abs_seg'. Look into this.
             * Work out whether that is *really* what we should be doing.
             * Generally fix things. I think this is right as it is, but
             * am still not certain.
             */
            ldef(result->label, in_abs_seg ? abs_seg : location->segment,
                 location->offset, NULL, TRUE, FALSE, outfmt, errfunc);
        }
    }

    if (i == 0) {
        result->opcode = -1;    /* this line contains just a label */
        return result;
    }

    result->nprefix = 0;
    result->times = 1L;

    while (i == TOKEN_PREFIX ||
           (i == TOKEN_REG && !(REG_SREG & ~reg_flags[tokval.t_integer])))
    {
        /*
         * Handle special case: the TIMES prefix.
         */
        if (i == TOKEN_PREFIX && tokval.t_integer == P_TIMES) {
            expr *value;

            i = stdscan(NULL, &tokval);
            value =
                evaluate(stdscan, NULL, &tokval, NULL, pass0, error, NULL);
            i = tokval.t_type;
            if (!value) {       /* but, error in evaluator */
                result->opcode = -1;    /* unrecoverable parse error: */
                return result;  /* ignore this instruction */
            }
            if (!is_simple(value)) {
                error(ERR_NONFATAL,
                      "non-constant argument supplied to TIMES");
                result->times = 1L;
            } else {
                result->times = value->value;
                if (value->value < 0) {
                    error(ERR_NONFATAL, "TIMES value %d is negative",
                          value->value);
                    result->times = 0;
                }
            }
        } else {
            if (result->nprefix == MAXPREFIX)
                error(ERR_NONFATAL,
                      "instruction has more than %d prefixes", MAXPREFIX);
            else
                result->prefixes[result->nprefix++] = tokval.t_integer;
            i = stdscan(NULL, &tokval);
        }
    }

    if (i != TOKEN_INSN) {
        if (result->nprefix > 0 && i == 0) {
            /*
             * Instruction prefixes are present, but no actual
             * instruction. This is allowed: at this point we
             * invent a notional instruction of RESB 0.
             */
            result->opcode = I_RESB;
            result->operands = 1;
            result->oprs[0].type = IMMEDIATE;
            result->oprs[0].offset = 0L;
            result->oprs[0].segment = result->oprs[0].wrt = NO_SEG;
            return result;
        } else {
            error(ERR_NONFATAL, "parser: instruction expected");
            result->opcode = -1;
            return result;
        }
    }

    result->opcode = tokval.t_integer;
    result->condition = tokval.t_inttwo;

    /*
     * RESB, RESW and RESD cannot be satisfied with incorrectly
     * evaluated operands, since the correct values _must_ be known
     * on the first pass. Hence, even in pass one, we set the
     * `critical' flag on calling evaluate(), so that it will bomb
     * out on undefined symbols. Nasty, but there's nothing we can
     * do about it.
     *
     * For the moment, EQU has the same difficulty, so we'll
     * include that.
     */
    if (result->opcode == I_RESB || result->opcode == I_RESW || result->opcode == I_RESD || result->opcode == I_RESQ || result->opcode == I_REST || result->opcode == I_EQU || result->opcode == I_INCBIN) {    /* fbk */
        critical = pass0;
    } else
        critical = (pass == 2 ? 2 : 0);

    if (result->opcode == I_DB ||
        result->opcode == I_DW ||
        result->opcode == I_DD ||
        result->opcode == I_DQ ||
        result->opcode == I_DT || result->opcode == I_INCBIN) {
        extop *eop, **tail = &result->eops, **fixptr;
        int oper_num = 0;

        result->eops_float = FALSE;

        /*
         * Begin to read the DB/DW/DD/DQ/DT/INCBIN operands.
         */
        while (1) {
            i = stdscan(NULL, &tokval);
            if (i == 0)
                break;
            fixptr = tail;
            eop = *tail = nasm_malloc(sizeof(extop));
            tail = &eop->next;
            eop->next = NULL;
            eop->type = EOT_NOTHING;
            oper_num++;

            if (i == TOKEN_NUM && tokval.t_charptr && is_comma_next()) {
                eop->type = EOT_DB_STRING;
                eop->stringval = tokval.t_charptr;
                eop->stringlen = tokval.t_inttwo;
                i = stdscan(NULL, &tokval);     /* eat the comma */
                continue;
            }

            if ((i == TOKEN_FLOAT && is_comma_next()) || i == '-') {
                long sign = +1L;

                if (i == '-') {
                    char *save = stdscan_bufptr;
                    i = stdscan(NULL, &tokval);
                    sign = -1L;
                    if (i != TOKEN_FLOAT || !is_comma_next()) {
                        stdscan_bufptr = save;
                        i = tokval.t_type = '-';
                    }
                }

                if (i == TOKEN_FLOAT) {
                    eop->type = EOT_DB_STRING;
                    result->eops_float = TRUE;
                    if (result->opcode == I_DD)
                        eop->stringlen = 4;
                    else if (result->opcode == I_DQ)
                        eop->stringlen = 8;
                    else if (result->opcode == I_DT)
                        eop->stringlen = 10;
                    else {
                        error(ERR_NONFATAL, "floating-point constant"
                              " encountered in `D%c' instruction",
                              result->opcode == I_DW ? 'W' : 'B');
                        /*
                         * fix suggested by Pedro Gimeno... original line
                         * was:
                         * eop->type = EOT_NOTHING;
                         */
                        eop->stringlen = 0;
                    }
                    eop =
                        nasm_realloc(eop, sizeof(extop) + eop->stringlen);
                    tail = &eop->next;
                    *fixptr = eop;
                    eop->stringval = (char *)eop + sizeof(extop);
                    if (eop->stringlen < 4 ||
                        !float_const(tokval.t_charptr, sign,
                                     (unsigned char *)eop->stringval,
                                     eop->stringlen, error))
                        eop->type = EOT_NOTHING;