1 /* ----------------------------------------------------------------------- *
3 * Copyright 1996-2009 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 * ----------------------------------------------------------------------- */
49 * Standard scanner routine used by parser.c and some output
50 * formats. It keeps a succession of temporary-storage strings in
51 * stdscan_tempstorage, which can be cleared using stdscan_reset.
53 static char *stdscan_bufptr
= NULL
;
54 static char **stdscan_tempstorage
= NULL
;
55 static int stdscan_tempsize
= 0, stdscan_templen
= 0;
56 #define STDSCAN_TEMP_DELTA 256
58 void stdscan_set(char *str
)
63 char *stdscan_get(void)
65 return stdscan_bufptr
;
68 static void stdscan_pop(void)
70 nasm_free(stdscan_tempstorage
[--stdscan_templen
]);
73 void stdscan_reset(void)
75 while (stdscan_templen
> 0)
80 * Unimportant cleanup is done to avoid confusing people who are trying
81 * to debug real memory leaks
83 void stdscan_cleanup(void)
86 nasm_free(stdscan_tempstorage
);
89 static char *stdscan_copy(char *p
, int len
)
93 text
= nasm_malloc(len
+ 1);
97 if (stdscan_templen
>= stdscan_tempsize
) {
98 stdscan_tempsize
+= STDSCAN_TEMP_DELTA
;
99 stdscan_tempstorage
= nasm_realloc(stdscan_tempstorage
,
103 stdscan_tempstorage
[stdscan_templen
++] = text
;
108 int stdscan(void *private_data
, struct tokenval
*tv
)
110 char ourcopy
[MAX_KEYWORD
+ 1], *r
, *s
;
112 (void)private_data
; /* Don't warn that this parameter is unused */
114 stdscan_bufptr
= nasm_skip_spaces(stdscan_bufptr
);
115 if (!*stdscan_bufptr
)
116 return tv
->t_type
= TOKEN_EOS
;
118 /* we have a token; either an id, a number or a char */
119 if (isidstart(*stdscan_bufptr
) ||
120 (*stdscan_bufptr
== '$' && isidstart(stdscan_bufptr
[1]))) {
121 /* now we've got an identifier */
124 if (*stdscan_bufptr
== '$') {
129 r
= stdscan_bufptr
++;
130 /* read the entire buffer to advance the buffer pointer but... */
131 while (isidchar(*stdscan_bufptr
))
134 /* ... copy only up to IDLEN_MAX-1 characters */
135 tv
->t_charptr
= stdscan_copy(r
, stdscan_bufptr
- r
< IDLEN_MAX
?
136 stdscan_bufptr
- r
: IDLEN_MAX
- 1);
138 if (is_sym
|| stdscan_bufptr
- r
> MAX_KEYWORD
)
139 return tv
->t_type
= TOKEN_ID
; /* bypass all other checks */
141 for (s
= tv
->t_charptr
, r
= ourcopy
; *s
; s
++)
142 *r
++ = nasm_tolower(*s
);
144 /* right, so we have an identifier sitting in temp storage. now,
145 * is it actually a register or instruction name, or what? */
146 return nasm_token_hash(ourcopy
, tv
);
147 } else if (*stdscan_bufptr
== '$' && !isnumchar(stdscan_bufptr
[1])) {
149 * It's a $ sign with no following hex number; this must
150 * mean it's a Here token ($), evaluating to the current
151 * assembly location, or a Base token ($$), evaluating to
152 * the base of the current segment.
155 if (*stdscan_bufptr
== '$') {
157 return tv
->t_type
= TOKEN_BASE
;
159 return tv
->t_type
= TOKEN_HERE
;
160 } else if (isnumstart(*stdscan_bufptr
)) { /* now we've got a number */
163 bool is_float
= false;
169 if (*stdscan_bufptr
== '$') {
175 c
= *stdscan_bufptr
++;
177 if (!is_hex
&& (c
== 'e' || c
== 'E')) {
179 if (*stdscan_bufptr
== '+' || *stdscan_bufptr
== '-') {
181 * e can only be followed by +/- if it is either a
182 * prefixed hex number or a floating-point number
187 } else if (c
== 'H' || c
== 'h' || c
== 'X' || c
== 'x') {
189 } else if (c
== 'P' || c
== 'p') {
191 if (*stdscan_bufptr
== '+' || *stdscan_bufptr
== '-')
193 } else if (isnumchar(c
) || c
== '_')
200 stdscan_bufptr
--; /* Point to first character beyond number */
202 if (has_e
&& !is_hex
) {
203 /* 1e13 is floating-point, but 1e13h is not */
208 tv
->t_charptr
= stdscan_copy(r
, stdscan_bufptr
- r
);
209 return tv
->t_type
= TOKEN_FLOAT
;
211 r
= stdscan_copy(r
, stdscan_bufptr
- r
);
212 tv
->t_integer
= readnum(r
, &rn_error
);
215 /* some malformation occurred */
216 return tv
->t_type
= TOKEN_ERRNUM
;
218 tv
->t_charptr
= NULL
;
219 return tv
->t_type
= TOKEN_NUM
;
221 } else if (*stdscan_bufptr
== '\'' || *stdscan_bufptr
== '"' ||
222 *stdscan_bufptr
== '`') {
223 /* a quoted string */
224 char start_quote
= *stdscan_bufptr
;
225 tv
->t_charptr
= stdscan_bufptr
;
226 tv
->t_inttwo
= nasm_unquote(tv
->t_charptr
, &stdscan_bufptr
);
227 if (*stdscan_bufptr
!= start_quote
)
228 return tv
->t_type
= TOKEN_ERRSTR
;
229 stdscan_bufptr
++; /* Skip final quote */
230 return tv
->t_type
= TOKEN_STR
;
231 } else if (*stdscan_bufptr
== ';') {
232 /* a comment has happened - stay */
233 return tv
->t_type
= TOKEN_EOS
;
234 } else if (stdscan_bufptr
[0] == '>' && stdscan_bufptr
[1] == '>') {
236 return tv
->t_type
= TOKEN_SHR
;
237 } else if (stdscan_bufptr
[0] == '<' && stdscan_bufptr
[1] == '<') {
239 return tv
->t_type
= TOKEN_SHL
;
240 } else if (stdscan_bufptr
[0] == '/' && stdscan_bufptr
[1] == '/') {
242 return tv
->t_type
= TOKEN_SDIV
;
243 } else if (stdscan_bufptr
[0] == '%' && stdscan_bufptr
[1] == '%') {
245 return tv
->t_type
= TOKEN_SMOD
;
246 } else if (stdscan_bufptr
[0] == '=' && stdscan_bufptr
[1] == '=') {
248 return tv
->t_type
= TOKEN_EQ
;
249 } else if (stdscan_bufptr
[0] == '<' && stdscan_bufptr
[1] == '>') {
251 return tv
->t_type
= TOKEN_NE
;
252 } else if (stdscan_bufptr
[0] == '!' && stdscan_bufptr
[1] == '=') {
254 return tv
->t_type
= TOKEN_NE
;
255 } else if (stdscan_bufptr
[0] == '<' && stdscan_bufptr
[1] == '=') {
257 return tv
->t_type
= TOKEN_LE
;
258 } else if (stdscan_bufptr
[0] == '>' && stdscan_bufptr
[1] == '=') {
260 return tv
->t_type
= TOKEN_GE
;
261 } else if (stdscan_bufptr
[0] == '&' && stdscan_bufptr
[1] == '&') {
263 return tv
->t_type
= TOKEN_DBL_AND
;
264 } else if (stdscan_bufptr
[0] == '^' && stdscan_bufptr
[1] == '^') {
266 return tv
->t_type
= TOKEN_DBL_XOR
;
267 } else if (stdscan_bufptr
[0] == '|' && stdscan_bufptr
[1] == '|') {
269 return tv
->t_type
= TOKEN_DBL_OR
;
270 } else /* just an ordinary char */
271 return tv
->t_type
= (uint8_t)(*stdscan_bufptr
++);