summaryrefslogtreecommitdiff
path: root/stdscan.c
blob: b5e389da98491f8c66964d9fb8a4b92258942737 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
/* ----------------------------------------------------------------------- *
 *
 *   Copyright 1996-2009 The NASM Authors - All Rights Reserved
 *   See the file AUTHORS included with the NASM distribution for
 *   the specific copyright holders.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following
 *   conditions are met:
 *
 *   * Redistributions of source code must retain the above copyright
 *     notice, this list of conditions and the following disclaimer.
 *   * Redistributions in binary form must reproduce the above
 *     copyright notice, this list of conditions and the following
 *     disclaimer in the documentation and/or other materials provided
 *     with the distribution.
 *
 *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
 *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
 *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
 *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
 *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
 *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
 *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * ----------------------------------------------------------------------- */

#include "compiler.h"

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

#include "nasm.h"
#include "nasmlib.h"
#include "quote.h"
#include "stdscan.h"
#include "insns.h"

/*
 * Standard scanner routine used by parser.c and some output
 * formats. It keeps a succession of temporary-storage strings in
 * stdscan_tempstorage, which can be cleared using stdscan_reset.
 */
static char *stdscan_bufptr = NULL;
static char **stdscan_tempstorage = NULL;
static int stdscan_tempsize = 0, stdscan_templen = 0;
static int brace = 0;               /* nested brace counter */
static bool brace_opened = false;   /* if brace is just opened */
#define STDSCAN_TEMP_DELTA 256

void stdscan_set(char *str)
{
        stdscan_bufptr = str;
}

char *stdscan_get(void)
{
        return stdscan_bufptr;
}

static void stdscan_pop(void)
{
    nasm_free(stdscan_tempstorage[--stdscan_templen]);
}

void stdscan_reset(void)
{
    while (stdscan_templen > 0)
        stdscan_pop();
}

/*
 * Unimportant cleanup is done to avoid confusing people who are trying
 * to debug real memory leaks
 */
void stdscan_cleanup(void)
{
    stdscan_reset();
    nasm_free(stdscan_tempstorage);
}

static char *stdscan_copy(char *p, int len)
{
    char *text;

    text = nasm_malloc(len + 1);
    memcpy(text, p, len);
    text[len] = '\0';

    if (stdscan_templen >= stdscan_tempsize) {
        stdscan_tempsize += STDSCAN_TEMP_DELTA;
        stdscan_tempstorage = nasm_realloc(stdscan_tempstorage,
                                           stdscan_tempsize *
                                           sizeof(char *));
    }
    stdscan_tempstorage[stdscan_templen++] = text;

    return text;
}

/*
 * a token is enclosed with braces. proper token type will be assigned
 * accordingly with the token flag.
 * a closing brace is treated as an ending character of corresponding token.
 */
static int stdscan_handle_brace(struct tokenval *tv)
{
    if (!(tv->t_flag & TFLAG_BRC_ANY)) {
        /* invalid token is put inside braces */
        nasm_error(ERR_NONFATAL,
                    "%s is not a valid decorator with braces", tv->t_charptr);
        tv->t_type = TOKEN_INVALID;
    } else if (tv->t_flag & TFLAG_BRC_OPT) {
        if (is_reg_class(OPMASKREG, tv->t_integer)) {
            /* within braces, opmask register is now used as a mask */
            tv->t_type = TOKEN_OPMASK;
        }
    }

    stdscan_bufptr = nasm_skip_spaces(stdscan_bufptr);

    if (stdscan_bufptr[0] == '}') {
        stdscan_bufptr ++;      /* skip the closing brace */
        brace --;
    } else if (stdscan_bufptr[0] != ',') {
        /* treat {foo,bar} as {foo}{bar}
         * by regarding ',' as a mere separator between decorators
         */
        nasm_error(ERR_NONFATAL, "closing brace expected");
        tv->t_type = TOKEN_INVALID;
    }
    return tv->t_type;
}

int stdscan(void *private_data, struct tokenval *tv)
{
    char ourcopy[MAX_KEYWORD + 1], *r, *s;

    (void)private_data;         /* Don't warn that this parameter is unused */

    stdscan_bufptr = nasm_skip_spaces(stdscan_bufptr);
    if (!*stdscan_bufptr) {
        /* nested brace shouldn't affect following lines */
        brace = 0;
        return tv->t_type = TOKEN_EOS;
    }

    /* we have a token; either an id, a number or a char */
    if (isidstart(*stdscan_bufptr) ||
        (*stdscan_bufptr == '$' && isidstart(stdscan_bufptr[1])) ||
        (brace && isidchar(*stdscan_bufptr))) {     /* because of {1to8} */
        /* now we've got an identifier */
        bool is_sym = false;
        int token_type;

        /* opening brace is followed by any letter */
        brace_opened = false;

        if (*stdscan_bufptr == '$') {
            is_sym = true;
            stdscan_bufptr++;
        }

        r = stdscan_bufptr++;
        /* read the entire buffer to advance the buffer pointer but... */
        /* {rn-sae}, {rd-sae}, {ru-sae}, {rz-sae} contain '-' in tokens. */
        while (isidchar(*stdscan_bufptr) || (brace && *stdscan_bufptr == '-'))
            stdscan_bufptr++;

        /* ... copy only up to IDLEN_MAX-1 characters */
        tv->t_charptr = stdscan_copy(r, stdscan_bufptr - r < IDLEN_MAX ?
                                     stdscan_bufptr - r : IDLEN_MAX - 1);

        if (is_sym || stdscan_bufptr - r > MAX_KEYWORD)
            return tv->t_type = TOKEN_ID;       /* bypass all other checks */

        for (s = tv->t_charptr, r = ourcopy; *s; s++)
            *r++ = nasm_tolower(*s);
        *r = '\0';
        /* right, so we have an identifier sitting in temp storage. now,
         * is it actually a register or instruction name, or what? */
        token_type = nasm_token_hash(ourcopy, tv);

        if (likely(!brace)) {
            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;
            }
        } else {
            /* handle tokens inside braces */
            return stdscan_handle_brace(tv);
        }
    } else if (*stdscan_bufptr == '$' && !isnumchar(stdscan_bufptr[1])) {
        /*
         * It's a $ sign with no following hex number; this must
         * mean it's a Here token ($), evaluating to the current
         * assembly location, or a Base token ($$), evaluating to
         * the base of the current segment.
         */
        stdscan_bufptr++;
        if (*stdscan_bufptr == '$') {
            stdscan_bufptr++;
            return tv->t_type = TOKEN_BASE;
        }
        return tv->t_type = TOKEN_HERE;
    } else if (isnumstart(*stdscan_bufptr)) {   /* now we've got a number */
        bool rn_error;
        bool is_hex = false;
        bool is_float = false;
        bool has_e = false;
        char c;

        r = stdscan_bufptr;

        if (*stdscan_bufptr == '$') {
            stdscan_bufptr++;
            is_hex = true;
        }

        for (;;) {
            c = *stdscan_bufptr++;

            if (!is_hex && (c == 'e' || c == 'E')) {
                has_e = true;
                if (*stdscan_bufptr == '+' || *stdscan_bufptr == '-') {
                    /*
                     * e can only be followed by +/- if it is either a
                     * prefixed hex number or a floating-point number
                     */
                    is_float = true;
                    stdscan_bufptr++;
                }
            } else if (c == 'H' || c == 'h' || c == 'X' || c == 'x') {
                is_hex = true;
            } else if (c == 'P' || c == 'p') {
                is_float = true;
                if (*stdscan_bufptr == '+' || *stdscan_bufptr == '-')
                    stdscan_bufptr++;
            } else if (isnumchar(c) || c == '_')
                ; /* just advance */
            else if (c == '.')
                is_float = true;
            else
                break;
        }
        stdscan_bufptr--;       /* Point to first character beyond number */

        if (has_e && !is_hex) {
            /* 1e13 is floating-point, but 1e13h is not */
            is_float = true;
        }

        if (is_float) {
            tv->t_charptr = stdscan_copy(r, stdscan_bufptr - r);
            return tv->t_type = TOKEN_FLOAT;
        } else {
            r = stdscan_copy(r, stdscan_bufptr - r);
            tv->t_integer = readnum(r, &rn_error);
            stdscan_pop();
            if (rn_error) {
                /* some malformation occurred */
                return tv->t_type = TOKEN_ERRNUM;
            }
            tv->t_charptr = NULL;
            return tv->t_type = TOKEN_NUM;
        }
    } else if (*stdscan_bufptr == '\'' || *stdscan_bufptr == '"' ||
               *stdscan_bufptr == '`') {
        /* a quoted string */
        char start_quote = *stdscan_bufptr;
        tv->t_charptr = stdscan_bufptr;
        tv->t_inttwo = nasm_unquote(tv->t_charptr, &stdscan_bufptr);
        if (*stdscan_bufptr != start_quote)
            return tv->t_type = TOKEN_ERRSTR;
        stdscan_bufptr++;       /* Skip final quote */
        return tv->t_type = TOKEN_STR;
    } else if (*stdscan_bufptr == ';') {
        /* a comment has happened - stay */
        return tv->t_type = TOKEN_EOS;
    } else if (stdscan_bufptr[0] == '>' && stdscan_bufptr[1] == '>') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_SHR;
    } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '<') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_SHL;
    } else if (stdscan_bufptr[0] == '/' && stdscan_bufptr[1] == '/') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_SDIV;
    } else if (stdscan_bufptr[0] == '%' && stdscan_bufptr[1] == '%') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_SMOD;
    } else if (stdscan_bufptr[0] == '=' && stdscan_bufptr[1] == '=') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_EQ;
    } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '>') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_NE;
    } else if (stdscan_bufptr[0] == '!' && stdscan_bufptr[1] == '=') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_NE;
    } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '=') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_LE;
    } else if (stdscan_bufptr[0] == '>' && stdscan_bufptr[1] == '=') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_GE;
    } else if (stdscan_bufptr[0] == '&' && stdscan_bufptr[1] == '&') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_DBL_AND;
    } else if (stdscan_bufptr[0] == '^' && stdscan_bufptr[1] == '^') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_DBL_XOR;
    } else if (stdscan_bufptr[0] == '|' && stdscan_bufptr[1] == '|') {
        stdscan_bufptr += 2;
        return tv->t_type = TOKEN_DBL_OR;
    } else if (stdscan_bufptr[0] == '{') {
        stdscan_bufptr ++;      /* skip the opening brace */
        brace ++;               /* in case of nested braces */
        brace_opened = true;    /* brace is just opened */
        return stdscan(private_data, tv);
    } else if (stdscan_bufptr[0] == ',' && brace) {
        /*
         * a comma inside braces should be treated just as a separator.
         * this is almost same as an opening brace except increasing counter.
         */
        stdscan_bufptr ++;
        brace_opened = true;    /* brace is just opened */
        return stdscan(private_data, tv);
    } else if (stdscan_bufptr[0] == '}') {
        stdscan_bufptr ++;      /* skip the closing brace */
        if (brace) {
            /* unhandled nested closing brace */
            brace --;
            /* if brace is closed without any content in it */
            if (brace_opened) {
                brace_opened = false;
                nasm_error(ERR_NONFATAL, "nothing inside braces");
            }
            return stdscan(private_data, tv);
        } else {
            /* redundant closing brace */
            return tv->t_type = TOKEN_INVALID;
        }
        return stdscan(private_data, tv);
    } else                      /* just an ordinary char */
        return tv->t_type = (uint8_t)(*stdscan_bufptr++);
}