stdscan.c

   1 /* ----------------------------------------------------------------------- *
   2  *
   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.
   6  *
   7  *   Redistribution and use in source and binary forms, with or without
   8  *   modification, are permitted provided that the following
   9  *   conditions are met:
  10  *
  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.
  17  *
  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.
  31  *
  32  * ----------------------------------------------------------------------- */
  33
  34 #include "compiler.h"
  35
  36 #include <stdio.h>
  37 #include <stdlib.h>
  38 #include <string.h>
  39 #include <ctype.h>
  40
  41 #include "nasm.h"
  42 #include "nasmlib.h"
  43 #include "quote.h"
  44 #include "stdscan.h"
  45 #include "insns.h"
  46
  47 /*
  48  * Standard scanner routine used by parser.c and some output
  49  * formats. It keeps a succession of temporary-storage strings in
  50  * stdscan_tempstorage, which can be cleared using stdscan_reset.
  51  */
  52 static char *stdscan_bufptr = NULL;
  53 static char **stdscan_tempstorage = NULL;
  54 static int stdscan_tempsize = 0, stdscan_templen = 0;
  55 #define STDSCAN_TEMP_DELTA 256
  56
  57 void stdscan_set(char *str)
  58 {
  59         stdscan_bufptr = str;
  60 }
  61
  62 char *stdscan_get(void)
  63 {
  64         return stdscan_bufptr;
  65 }
  66
  67 static void stdscan_pop(void)
  68 {
  69     nasm_free(stdscan_tempstorage[--stdscan_templen]);
  70 }
  71
  72 void stdscan_reset(void)
  73 {
  74     while (stdscan_templen > 0)
  75         stdscan_pop();
  76 }
  77
  78 /*
  79  * Unimportant cleanup is done to avoid confusing people who are trying
  80  * to debug real memory leaks
  81  */
  82 void stdscan_cleanup(void)
  83 {
  84     stdscan_reset();
  85     nasm_free(stdscan_tempstorage);
  86 }
  87
  88 static char *stdscan_copy(char *p, int len)
  89 {
  90     char *text;
  91
  92     text = nasm_malloc(len + 1);
  93     memcpy(text, p, len);
  94     text[len] = '\0';
  95
  96     if (stdscan_templen >= stdscan_tempsize) {
  97         stdscan_tempsize += STDSCAN_TEMP_DELTA;
  98         stdscan_tempstorage = nasm_realloc(stdscan_tempstorage,
  99                                            stdscan_tempsize *
 100                                            sizeof(char *));
 101     }
 102     stdscan_tempstorage[stdscan_templen++] = text;
 103
 104     return text;
 105 }
 106
 107 /*
 108  * a token is enclosed with braces. proper token type will be assigned
 109  * accordingly with the token flag.
 110  */
 111 static int stdscan_handle_brace(struct tokenval *tv)
 112 {
 113     if (!(tv->t_flag & TFLAG_BRC_ANY)) {
 114         /* invalid token is put inside braces */
 115         nasm_error(ERR_NONFATAL,
 116                     "%s is not a valid decorator with braces", tv->t_charptr);
 117         tv->t_type = TOKEN_INVALID;
 118     } else if (tv->t_flag & TFLAG_BRC_OPT) {
 119         if (is_reg_class(OPMASKREG, tv->t_integer)) {
 120             /* within braces, opmask register is now used as a mask */
 121             tv->t_type = TOKEN_OPMASK;
 122         }
 123     }
 124
 125     return tv->t_type;
 126 }
 127
 128 int stdscan(void *private_data, struct tokenval *tv)
 129 {
 130     char ourcopy[MAX_KEYWORD + 1], *r, *s;
 131
 132     (void)private_data;         /* Don't warn that this parameter is unused */
 133
 134     stdscan_bufptr = nasm_skip_spaces(stdscan_bufptr);
 135     if (!*stdscan_bufptr)
 136         return tv->t_type = TOKEN_EOS;
 137
 138     /* we have a token; either an id, a number or a char */
 139     if (isidstart(*stdscan_bufptr) ||
 140         (*stdscan_bufptr == '$' && isidstart(stdscan_bufptr[1]))) {
 141         /* now we've got an identifier */
 142         bool is_sym = false;
 143         int token_type;
 144
 145         if (*stdscan_bufptr == '$') {
 146             is_sym = true;
 147             stdscan_bufptr++;
 148         }
 149
 150         r = stdscan_bufptr++;
 151         /* read the entire buffer to advance the buffer pointer but... */
 152         while (isidchar(*stdscan_bufptr))
 153             stdscan_bufptr++;
 154
 155         /* ... copy only up to IDLEN_MAX-1 characters */
 156         tv->t_charptr = stdscan_copy(r, stdscan_bufptr - r < IDLEN_MAX ?
 157                                      stdscan_bufptr - r : IDLEN_MAX - 1);
 158
 159         if (is_sym || stdscan_bufptr - r > MAX_KEYWORD)
 160             return tv->t_type = TOKEN_ID;       /* bypass all other checks */
 161
 162         for (s = tv->t_charptr, r = ourcopy; *s; s++)
 163             *r++ = nasm_tolower(*s);
 164         *r = '\0';
 165         /* right, so we have an identifier sitting in temp storage. now,
 166          * is it actually a register or instruction name, or what? */
 167         token_type = nasm_token_hash(ourcopy, tv);
 168
 169         if (likely(!(tv->t_flag & TFLAG_BRC))) {
 170             /* most of the tokens fall into this case */
 171             return token_type;
 172         } else {
 173             return tv->t_type = TOKEN_ID;
 174         }
 175     } else if (*stdscan_bufptr == '$' && !isnumchar(stdscan_bufptr[1])) {
 176         /*
 177          * It's a $ sign with no following hex number; this must
 178          * mean it's a Here token ($), evaluating to the current
 179          * assembly location, or a Base token ($$), evaluating to
 180          * the base of the current segment.
 181          */
 182         stdscan_bufptr++;
 183         if (*stdscan_bufptr == '$') {
 184             stdscan_bufptr++;
 185             return tv->t_type = TOKEN_BASE;
 186         }
 187         return tv->t_type = TOKEN_HERE;
 188     } else if (isnumstart(*stdscan_bufptr)) {   /* now we've got a number */
 189         bool rn_error;
 190         bool is_hex = false;
 191         bool is_float = false;
 192         bool has_e = false;
 193         char c;
 194
 195         r = stdscan_bufptr;
 196
 197         if (*stdscan_bufptr == '$') {
 198             stdscan_bufptr++;
 199             is_hex = true;
 200         }
 201
 202         for (;;) {
 203             c = *stdscan_bufptr++;
 204
 205             if (!is_hex && (c == 'e' || c == 'E')) {
 206                 has_e = true;
 207                 if (*stdscan_bufptr == '+' || *stdscan_bufptr == '-') {
 208                     /*
 209                      * e can only be followed by +/- if it is either a
 210                      * prefixed hex number or a floating-point number
 211                      */
 212                     is_float = true;
 213                     stdscan_bufptr++;
 214                 }
 215             } else if (c == 'H' || c == 'h' || c == 'X' || c == 'x') {
 216                 is_hex = true;
 217             } else if (c == 'P' || c == 'p') {
 218                 is_float = true;
 219                 if (*stdscan_bufptr == '+' || *stdscan_bufptr == '-')
 220                     stdscan_bufptr++;
 221             } else if (isnumchar(c) || c == '_')
 222                 ; /* just advance */
 223             else if (c == '.')
 224                 is_float = true;
 225             else
 226                 break;
 227         }
 228         stdscan_bufptr--;       /* Point to first character beyond number */
 229
 230         if (has_e && !is_hex) {
 231             /* 1e13 is floating-point, but 1e13h is not */
 232             is_float = true;
 233         }
 234
 235         if (is_float) {
 236             tv->t_charptr = stdscan_copy(r, stdscan_bufptr - r);
 237             return tv->t_type = TOKEN_FLOAT;
 238         } else {
 239             r = stdscan_copy(r, stdscan_bufptr - r);
 240             tv->t_integer = readnum(r, &rn_error);
 241             stdscan_pop();
 242             if (rn_error) {
 243                 /* some malformation occurred */
 244                 return tv->t_type = TOKEN_ERRNUM;
 245             }
 246             tv->t_charptr = NULL;
 247             return tv->t_type = TOKEN_NUM;
 248         }
 249     } else if (*stdscan_bufptr == '\'' || *stdscan_bufptr == '"' ||
 250                *stdscan_bufptr == '`') {
 251         /* a quoted string */
 252         char start_quote = *stdscan_bufptr;
 253         tv->t_charptr = stdscan_bufptr;
 254         tv->t_inttwo = nasm_unquote(tv->t_charptr, &stdscan_bufptr);
 255         if (*stdscan_bufptr != start_quote)
 256             return tv->t_type = TOKEN_ERRSTR;
 257         stdscan_bufptr++;       /* Skip final quote */
 258         return tv->t_type = TOKEN_STR;
 259     } else if (*stdscan_bufptr == '{') {
 260         /* now we've got a decorator */
 261         int token_len;
 262
 263         stdscan_bufptr = nasm_skip_spaces(stdscan_bufptr);
 264
 265         r = ++stdscan_bufptr;
 266         /*
 267          * read the entire buffer to advance the buffer pointer
 268          * {rn-sae}, {rd-sae}, {ru-sae}, {rz-sae} contain '-' in tokens.
 269          */
 270         while (isbrcchar(*stdscan_bufptr))
 271             stdscan_bufptr++;
 272
 273         token_len = stdscan_bufptr - r;
 274
 275         /* ... copy only up to DECOLEN_MAX-1 characters */
 276         tv->t_charptr = stdscan_copy(r, token_len < DECOLEN_MAX ?
 277                                         token_len : DECOLEN_MAX - 1);
 278
 279         stdscan_bufptr = nasm_skip_spaces(stdscan_bufptr);
 280         /* if brace is not closed properly or token is too long  */
 281         if ((*stdscan_bufptr != '}') || (token_len > MAX_KEYWORD)) {
 282             nasm_error(ERR_NONFATAL,
 283                        "invalid decorator token inside braces");
 284             return tv->t_type = TOKEN_INVALID;
 285         }
 286
 287         stdscan_bufptr++;       /* skip closing brace */
 288
 289         for (s = tv->t_charptr, r = ourcopy; *s; s++)
 290             *r++ = nasm_tolower(*s);
 291         *r = '\0';
 292
 293         /* right, so we have a decorator sitting in temp storage. */
 294         nasm_token_hash(ourcopy, tv);
 295
 296         /* handle tokens inside braces */
 297         return stdscan_handle_brace(tv);
 298     } else if (*stdscan_bufptr == ';') {
 299         /* a comment has happened - stay */
 300         return tv->t_type = TOKEN_EOS;
 301     } else if (stdscan_bufptr[0] == '>' && stdscan_bufptr[1] == '>') {
 302         stdscan_bufptr += 2;
 303         return tv->t_type = TOKEN_SHR;
 304     } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '<') {
 305         stdscan_bufptr += 2;
 306         return tv->t_type = TOKEN_SHL;
 307     } else if (stdscan_bufptr[0] == '/' && stdscan_bufptr[1] == '/') {
 308         stdscan_bufptr += 2;
 309         return tv->t_type = TOKEN_SDIV;
 310     } else if (stdscan_bufptr[0] == '%' && stdscan_bufptr[1] == '%') {
 311         stdscan_bufptr += 2;
 312         return tv->t_type = TOKEN_SMOD;
 313     } else if (stdscan_bufptr[0] == '=' && stdscan_bufptr[1] == '=') {
 314         stdscan_bufptr += 2;
 315         return tv->t_type = TOKEN_EQ;
 316     } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '>') {
 317         stdscan_bufptr += 2;
 318         return tv->t_type = TOKEN_NE;
 319     } else if (stdscan_bufptr[0] == '!' && stdscan_bufptr[1] == '=') {
 320         stdscan_bufptr += 2;
 321         return tv->t_type = TOKEN_NE;
 322     } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '=') {
 323         stdscan_bufptr += 2;
 324         return tv->t_type = TOKEN_LE;
 325     } else if (stdscan_bufptr[0] == '>' && stdscan_bufptr[1] == '=') {
 326         stdscan_bufptr += 2;
 327         return tv->t_type = TOKEN_GE;
 328     } else if (stdscan_bufptr[0] == '&' && stdscan_bufptr[1] == '&') {
 329         stdscan_bufptr += 2;
 330         return tv->t_type = TOKEN_DBL_AND;
 331     } else if (stdscan_bufptr[0] == '^' && stdscan_bufptr[1] == '^') {
 332         stdscan_bufptr += 2;
 333         return tv->t_type = TOKEN_DBL_XOR;
 334     } else if (stdscan_bufptr[0] == '|' && stdscan_bufptr[1] == '|') {
 335         stdscan_bufptr += 2;
 336         return tv->t_type = TOKEN_DBL_OR;
 337     } else                      /* just an ordinary char */
 338         return tv->t_type = (uint8_t)(*stdscan_bufptr++);
 339 }