1 /* ----------------------------------------------------------------------- *
3 * Copyright 1996-2018 The NASM Authors - All Rights Reserved
4 * See the file AUTHORS included with the NASM distribution for
5 * the specific copyright holders.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following
11 * * Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * * Redistributions in binary form must reproduce the above
14 * copyright notice, this list of conditions and the following
15 * disclaimer in the documentation and/or other materials provided
16 * with the distribution.
18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
19 * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
20 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
21 * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
22 * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
23 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
25 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
26 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
28 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
29 * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
30 * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32 * ----------------------------------------------------------------------- */
46 * Standard scanner routine used by parser.c and some output
47 * formats. It keeps a succession of temporary-storage strings in
48 * stdscan_tempstorage, which can be cleared using stdscan_reset.
50 static char *stdscan_bufptr
= NULL
;
51 static char **stdscan_tempstorage
= NULL
;
52 static int stdscan_tempsize
= 0, stdscan_templen
= 0;
53 #define STDSCAN_TEMP_DELTA 256
55 void stdscan_set(char *str
)
60 char *stdscan_get(void)
62 return stdscan_bufptr
;
65 static void stdscan_pop(void)
67 nasm_free(stdscan_tempstorage
[--stdscan_templen
]);
70 void stdscan_reset(void)
72 while (stdscan_templen
> 0)
77 * Unimportant cleanup is done to avoid confusing people who are trying
78 * to debug real memory leaks
80 void stdscan_cleanup(void)
83 nasm_free(stdscan_tempstorage
);
86 static char *stdscan_copy(char *p
, int len
)
90 text
= nasm_malloc(len
+ 1);
94 if (stdscan_templen
>= stdscan_tempsize
) {
95 stdscan_tempsize
+= STDSCAN_TEMP_DELTA
;
96 stdscan_tempstorage
= nasm_realloc(stdscan_tempstorage
,
100 stdscan_tempstorage
[stdscan_templen
++] = text
;
106 * a token is enclosed with braces. proper token type will be assigned
107 * accordingly with the token flag.
109 static int stdscan_handle_brace(struct tokenval
*tv
)
111 if (!(tv
->t_flag
& TFLAG_BRC_ANY
)) {
112 /* invalid token is put inside braces */
113 nasm_nonfatal("`%s' is not a valid decorator with braces", tv
->t_charptr
);
114 tv
->t_type
= TOKEN_INVALID
;
115 } else if (tv
->t_flag
& TFLAG_BRC_OPT
) {
116 if (is_reg_class(OPMASKREG
, tv
->t_integer
)) {
117 /* within braces, opmask register is now used as a mask */
118 tv
->t_type
= TOKEN_OPMASK
;
125 int stdscan(void *private_data
, struct tokenval
*tv
)
127 char ourcopy
[MAX_KEYWORD
+ 1], *r
, *s
;
129 (void)private_data
; /* Don't warn that this parameter is unused */
131 stdscan_bufptr
= nasm_skip_spaces(stdscan_bufptr
);
132 if (!*stdscan_bufptr
)
133 return tv
->t_type
= TOKEN_EOS
;
135 /* we have a token; either an id, a number or a char */
136 if (nasm_isidstart(*stdscan_bufptr
) ||
137 (*stdscan_bufptr
== '$' && nasm_isidstart(stdscan_bufptr
[1]))) {
138 /* now we've got an identifier */
142 if (*stdscan_bufptr
== '$') {
147 r
= stdscan_bufptr
++;
148 /* read the entire buffer to advance the buffer pointer but... */
149 while (nasm_isidchar(*stdscan_bufptr
))
152 /* ... copy only up to IDLEN_MAX-1 characters */
153 tv
->t_charptr
= stdscan_copy(r
, stdscan_bufptr
- r
< IDLEN_MAX
?
154 stdscan_bufptr
- r
: IDLEN_MAX
- 1);
156 if (is_sym
|| stdscan_bufptr
- r
> MAX_KEYWORD
)
157 return tv
->t_type
= TOKEN_ID
; /* bypass all other checks */
159 for (s
= tv
->t_charptr
, r
= ourcopy
; *s
; s
++)
160 *r
++ = nasm_tolower(*s
);
162 /* right, so we have an identifier sitting in temp storage. now,
163 * is it actually a register or instruction name, or what? */
164 token_type
= nasm_token_hash(ourcopy
, tv
);
166 if (unlikely(tv
->t_flag
& TFLAG_WARN
)) {
168 *!ptr [on] non-NASM keyword used in other assemblers
169 *! warns about keywords used in other assemblers that might
170 *! indicate a mistake in the source code. Currently only the MASM
171 *! \c{PTR} keyword is recognized.
173 nasm_warn(WARN_PTR
, "`%s' is not a NASM keyword",
177 if (likely(!(tv
->t_flag
& TFLAG_BRC
))) {
178 /* most of the tokens fall into this case */
181 return tv
->t_type
= TOKEN_ID
;
183 } else if (*stdscan_bufptr
== '$' && !nasm_isnumchar(stdscan_bufptr
[1])) {
185 * It's a $ sign with no following hex number; this must
186 * mean it's a Here token ($), evaluating to the current
187 * assembly location, or a Base token ($$), evaluating to
188 * the base of the current segment.
191 if (*stdscan_bufptr
== '$') {
193 return tv
->t_type
= TOKEN_BASE
;
195 return tv
->t_type
= TOKEN_HERE
;
196 } else if (nasm_isnumstart(*stdscan_bufptr
)) { /* now we've got a number */
199 bool is_float
= false;
205 if (*stdscan_bufptr
== '$') {
211 c
= *stdscan_bufptr
++;
213 if (!is_hex
&& (c
== 'e' || c
== 'E')) {
215 if (*stdscan_bufptr
== '+' || *stdscan_bufptr
== '-') {
217 * e can only be followed by +/- if it is either a
218 * prefixed hex number or a floating-point number
223 } else if (c
== 'H' || c
== 'h' || c
== 'X' || c
== 'x') {
225 } else if (c
== 'P' || c
== 'p') {
227 if (*stdscan_bufptr
== '+' || *stdscan_bufptr
== '-')
229 } else if (nasm_isnumchar(c
))
236 stdscan_bufptr
--; /* Point to first character beyond number */
238 if (has_e
&& !is_hex
) {
239 /* 1e13 is floating-point, but 1e13h is not */
244 tv
->t_charptr
= stdscan_copy(r
, stdscan_bufptr
- r
);
245 return tv
->t_type
= TOKEN_FLOAT
;
247 r
= stdscan_copy(r
, stdscan_bufptr
- r
);
248 tv
->t_integer
= readnum(r
, &rn_error
);
251 /* some malformation occurred */
252 return tv
->t_type
= TOKEN_ERRNUM
;
254 tv
->t_charptr
= NULL
;
255 return tv
->t_type
= TOKEN_NUM
;
257 } else if (*stdscan_bufptr
== '\'' || *stdscan_bufptr
== '"' ||
258 *stdscan_bufptr
== '`') {
259 /* a quoted string */
260 char start_quote
= *stdscan_bufptr
;
261 tv
->t_charptr
= stdscan_bufptr
;
262 tv
->t_inttwo
= nasm_unquote(tv
->t_charptr
, &stdscan_bufptr
);
263 if (*stdscan_bufptr
!= start_quote
)
264 return tv
->t_type
= TOKEN_ERRSTR
;
265 stdscan_bufptr
++; /* Skip final quote */
266 return tv
->t_type
= TOKEN_STR
;
267 } else if (*stdscan_bufptr
== '{') {
268 /* now we've got a decorator */
271 stdscan_bufptr
= nasm_skip_spaces(stdscan_bufptr
);
273 r
= ++stdscan_bufptr
;
275 * read the entire buffer to advance the buffer pointer
276 * {rn-sae}, {rd-sae}, {ru-sae}, {rz-sae} contain '-' in tokens.
278 while (nasm_isbrcchar(*stdscan_bufptr
))
281 token_len
= stdscan_bufptr
- r
;
283 /* ... copy only up to DECOLEN_MAX-1 characters */
284 tv
->t_charptr
= stdscan_copy(r
, token_len
< DECOLEN_MAX
?
285 token_len
: DECOLEN_MAX
- 1);
287 stdscan_bufptr
= nasm_skip_spaces(stdscan_bufptr
);
288 /* if brace is not closed properly or token is too long */
289 if ((*stdscan_bufptr
!= '}') || (token_len
> MAX_KEYWORD
)) {
290 nasm_nonfatal("invalid decorator token inside braces");
291 return tv
->t_type
= TOKEN_INVALID
;
294 stdscan_bufptr
++; /* skip closing brace */
296 for (s
= tv
->t_charptr
, r
= ourcopy
; *s
; s
++)
297 *r
++ = nasm_tolower(*s
);
300 /* right, so we have a decorator sitting in temp storage. */
301 nasm_token_hash(ourcopy
, tv
);
303 /* handle tokens inside braces */
304 return stdscan_handle_brace(tv
);
305 } else if (*stdscan_bufptr
== ';') {
306 /* a comment has happened - stay */
307 return tv
->t_type
= TOKEN_EOS
;
308 } else if (stdscan_bufptr
[0] == '>' && stdscan_bufptr
[1] == '>') {
309 if (stdscan_bufptr
[2] == '>') {
311 return tv
->t_type
= TOKEN_SAR
;
314 return tv
->t_type
= TOKEN_SHR
;
316 } else if (stdscan_bufptr
[0] == '<' && stdscan_bufptr
[1] == '<') {
317 stdscan_bufptr
+= stdscan_bufptr
[2] == '<' ? 3 : 2;
318 return tv
->t_type
= TOKEN_SHL
;
319 } else if (stdscan_bufptr
[0] == '/' && stdscan_bufptr
[1] == '/') {
321 return tv
->t_type
= TOKEN_SDIV
;
322 } else if (stdscan_bufptr
[0] == '%' && stdscan_bufptr
[1] == '%') {
324 return tv
->t_type
= TOKEN_SMOD
;
325 } else if (stdscan_bufptr
[0] == '=' && stdscan_bufptr
[1] == '=') {
327 return tv
->t_type
= TOKEN_EQ
;
328 } else if (stdscan_bufptr
[0] == '<' && stdscan_bufptr
[1] == '>') {
330 return tv
->t_type
= TOKEN_NE
;
331 } else if (stdscan_bufptr
[0] == '!' && stdscan_bufptr
[1] == '=') {
333 return tv
->t_type
= TOKEN_NE
;
334 } else if (stdscan_bufptr
[0] == '<' && stdscan_bufptr
[1] == '=') {
336 return tv
->t_type
= TOKEN_LE
;
337 } else if (stdscan_bufptr
[0] == '>' && stdscan_bufptr
[1] == '=') {
339 return tv
->t_type
= TOKEN_GE
;
340 } else if (stdscan_bufptr
[0] == '&' && stdscan_bufptr
[1] == '&') {
342 return tv
->t_type
= TOKEN_DBL_AND
;
343 } else if (stdscan_bufptr
[0] == '^' && stdscan_bufptr
[1] == '^') {
345 return tv
->t_type
= TOKEN_DBL_XOR
;
346 } else if (stdscan_bufptr
[0] == '|' && stdscan_bufptr
[1] == '|') {
348 return tv
->t_type
= TOKEN_DBL_OR
;
349 } else /* just an ordinary char */
350 return tv
->t_type
= (uint8_t)(*stdscan_bufptr
++);