aniani/nasm
0
0
Fork 1
mirror of https://github.com/netwide-assembler/nasm.git synced 2025-10-10 00:25:06 -04:00
Code Activity

stdscan: handle $-escaped symbols starting with $

Browse Source 
For a symbol to start with $, it needs to be escaped with a second
dollar sign: $$. This was not handled correctly, instead $$ was seen
as TOKEN_BASE.

Fix this.

Reported-by: E. C. Masloch <pushbx@ulukai.org>
Fixes: https://bugzilla.nasm.us/show_bug.cgi?id=3392922
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
This commit is contained in:
H. Peter Anvin
2025-09-02 17:55:22 -07:00
parent 5201aab90f
commit 9c3d6ff000
1 changed files with 64 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

110
asm/stdscan.c
View File

@@ -312,68 +312,86 @@ int stdscan(void *private_data, struct tokenval *tv)
return i; return i;
} }
/* Skip id chars and return an appropriate string */
static int stdscan_symbol(struct tokenval *tv)
{
char *p = scan.bufptr;
const char *r = p;
size_t len;
p++; /* Leading character already verified */
/* Skip the entire symbol but only copy up to IDLEN_MAX characters */
while (nasm_isidchar(*p))
p++;
scan.bufptr = p;
len = p - r;
if (len >= IDLEN_MAX)
len = IDLEN_MAX - 1;
tv->t_len = len;
tv->t_charptr = stdscan_copy(r, len);
return tv->t_type = TOKEN_ID;
}
static int stdscan_token(struct tokenval *tv) static int stdscan_token(struct tokenval *tv)
{ {
const char *r; const char *r;
/* we have a token; either an id, a number, operator or char */ /* we have a token; either an id, a number, operator or char */
if (nasm_isidstart(*scan.bufptr) || if (nasm_isidstart(*scan.bufptr)) {
(*scan.bufptr == '$' && nasm_isidstart(scan.bufptr[1]))) {
/* now we've got an identifier */
bool is_sym = false;
int token_type; int token_type;
if (*scan.bufptr == '$') { stdscan_symbol(tv);
is_sym = true;
scan.bufptr++; if (tv->t_len <= MAX_KEYWORD) {
} /* Check to see if it is a keyword of some kind */
r = scan.bufptr++; token_type = nasm_token_hash(tv->t_charptr, tv);
/* read the entire buffer to advance the buffer pointer but... */ if (unlikely(tv->t_flag & TFLAG_WARN)) {
while (nasm_isidchar(*scan.bufptr)) /*! ptr [on] non-NASM keyword used in other assemblers
scan.bufptr++; *! warns about keywords used in other assemblers that
*! might indicate a mistake in the source code.
/* ... copy only up to IDLEN_MAX-1 characters */ *! Currently only the MASM \c{PTR} keyword is
tv->t_charptr = stdscan_copy(r, scan.bufptr - r < IDLEN_MAX ? *! recognized. If (limited) MASM compatibility is
scan.bufptr - r : IDLEN_MAX - 1); *! desired, the \c{%use masm} macro package is
*! available, see \k{pkg_masm}; however, carefully note
if (is_sym || scan.bufptr - r > MAX_KEYWORD) *! the caveats listed.
return tv->t_type = TOKEN_ID; /* bypass all other checks */ */
nasm_warn(WARN_PTR, "`%s' is not a NASM keyword",
token_type = nasm_token_hash(tv->t_charptr, tv); tv->t_charptr);
if (unlikely(tv->t_flag & TFLAG_WARN)) { }
/*! ptr [on] non-NASM keyword used in other assemblers
*! warns about keywords used in other assemblers that if (likely(!(tv->t_flag & TFLAG_BRC))) {
*! might indicate a mistake in the source code. /* most of the tokens fall into this case */
*! Currently only the MASM \c{PTR} keyword is return token_type;
*! recognized. If (limited) MASM compatibility is }
*! desired, the \c{%use masm} macro package is
*! available, see \k{pkg_masm}; however, carefully note
*! the caveats listed.
*/
nasm_warn(WARN_PTR, "`%s' is not a NASM keyword",
tv->t_charptr);
}
if (likely(!(tv->t_flag & TFLAG_BRC))) {
/* most of the tokens fall into this case */
return token_type;
} else {
return tv->t_type = TOKEN_ID;
} }
return tv->t_type = TOKEN_ID;
} else if (*scan.bufptr == '$' && !nasm_isnumchar(scan.bufptr[1])) { } else if (*scan.bufptr == '$' && !nasm_isnumchar(scan.bufptr[1])) {
/* /*
* It's a $ sign with no following hex number; this must * It's a $ sign with no following hex number; this must
* mean it's a Here token ($), evaluating to the current * mean it's a Here token ($), evaluating to the current
* assembly location, or a Base token ($$), evaluating to * assembly location, a Base token ($$), evaluating to
* the base of the current segment. * the base of the current segment, or an identifier beginning
* with $ (escaped by a previous $).
*/ */
scan.bufptr++; scan.bufptr++;
if (*scan.bufptr == '$') { if (*scan.bufptr == '$') {
scan.bufptr++; if (nasm_isidchar(scan.bufptr[1])) {
return tv->t_type = TOKEN_BASE; /* $-escaped symbol starting with $ */
return stdscan_symbol(tv);
} else {
scan.bufptr++;
return tv->t_type = TOKEN_BASE;
}
} else if (nasm_isidstart(*scan.bufptr)) {
/* $-escaped symbol that does NOT start with $ */
return stdscan_symbol(tv);
} else {
return tv->t_type = TOKEN_HERE;
} }
return tv->t_type = TOKEN_HERE;
} else if (nasm_isnumstart(*scan.bufptr)) { /* now we've got a number */ } else if (nasm_isnumstart(*scan.bufptr)) { /* now we've got a number */
bool rn_error; bool rn_error;
bool is_hex = false; bool is_hex = false;