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 #include <inttypes.h>
  41
  42 #include "nasm.h"
  43 #include "nasmlib.h"
  44 #include "quote.h"
  45 #include "stdscan.h"
  46 #include "insns.h"
  47
  48 /*
  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.
  52  */
  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
  57
  58 void stdscan_set(char *str)
  59 {
  60         stdscan_bufptr = str;
  61 }
  62
  63 char *stdscan_get(void)
  64 {
  65         return stdscan_bufptr;
  66 }
  67
  68 static void stdscan_pop(void)
  69 {
  70     nasm_free(stdscan_tempstorage[--stdscan_templen]);
  71 }
  72
  73 void stdscan_reset(void)
  74 {
  75     while (stdscan_templen > 0)
  76         stdscan_pop();
  77 }
  78
  79 /*
  80  * Unimportant cleanup is done to avoid confusing people who are trying
  81  * to debug real memory leaks
  82  */
  83 void stdscan_cleanup(void)
  84 {
  85     stdscan_reset();
  86     nasm_free(stdscan_tempstorage);
  87 }
  88
  89 static char *stdscan_copy(char *p, int len)
  90 {
  91     char *text;
  92
  93     text = nasm_malloc(len + 1);
  94     memcpy(text, p, len);
  95     text[len] = '\0';
  96
  97     if (stdscan_templen >= stdscan_tempsize) {
  98         stdscan_tempsize += STDSCAN_TEMP_DELTA;
  99         stdscan_tempstorage = nasm_realloc(stdscan_tempstorage,
 100                                            stdscan_tempsize *
 101                                            sizeof(char *));
 102     }
 103     stdscan_tempstorage[stdscan_templen++] = text;
 104
 105     return text;
 106 }
 107
 108 int stdscan(void *private_data, struct tokenval *tv)
 109 {
 110     char ourcopy[MAX_KEYWORD + 1], *r, *s;
 111
 112     (void)private_data;         /* Don't warn that this parameter is unused */
 113
 114     while (nasm_isspace(*stdscan_bufptr))
 115         stdscan_bufptr++;
 116     if (!*stdscan_bufptr)
 117         return tv->t_type = 0;
 118
 119     /* we have a token; either an id, a number or a char */
 120     if (isidstart(*stdscan_bufptr) ||
 121         (*stdscan_bufptr == '$' && isidstart(stdscan_bufptr[1]))) {
 122         /* now we've got an identifier */
 123         bool is_sym = false;
 124
 125         if (*stdscan_bufptr == '$') {
 126             is_sym = true;
 127             stdscan_bufptr++;
 128         }
 129
 130         r = stdscan_bufptr++;
 131         /* read the entire buffer to advance the buffer pointer but... */
 132         while (isidchar(*stdscan_bufptr))
 133             stdscan_bufptr++;
 134
 135         /* ... copy only up to IDLEN_MAX-1 characters */
 136         tv->t_charptr = stdscan_copy(r, stdscan_bufptr - r < IDLEN_MAX ?
 137                                      stdscan_bufptr - r : IDLEN_MAX - 1);
 138
 139         if (is_sym || stdscan_bufptr - r > MAX_KEYWORD)
 140             return tv->t_type = TOKEN_ID;       /* bypass all other checks */
 141
 142         for (s = tv->t_charptr, r = ourcopy; *s; s++)
 143             *r++ = nasm_tolower(*s);
 144         *r = '\0';
 145         /* right, so we have an identifier sitting in temp storage. now,
 146          * is it actually a register or instruction name, or what? */
 147         return nasm_token_hash(ourcopy, tv);
 148     } else if (*stdscan_bufptr == '$' && !isnumchar(stdscan_bufptr[1])) {
 149         /*
 150          * It's a $ sign with no following hex number; this must
 151          * mean it's a Here token ($), evaluating to the current
 152          * assembly location, or a Base token ($$), evaluating to
 153          * the base of the current segment.
 154          */
 155         stdscan_bufptr++;
 156         if (*stdscan_bufptr == '$') {
 157             stdscan_bufptr++;
 158             return tv->t_type = TOKEN_BASE;
 159         }
 160         return tv->t_type = TOKEN_HERE;
 161     } else if (isnumstart(*stdscan_bufptr)) {   /* now we've got a number */
 162         bool rn_error;
 163         bool is_hex = false;
 164         bool is_float = false;
 165         bool has_e = false;
 166         char c;
 167
 168         r = stdscan_bufptr;
 169
 170         if (*stdscan_bufptr == '$') {
 171             stdscan_bufptr++;
 172             is_hex = true;
 173         }
 174
 175         for (;;) {
 176             c = *stdscan_bufptr++;
 177
 178             if (!is_hex && (c == 'e' || c == 'E')) {
 179                 has_e = true;
 180                 if (*stdscan_bufptr == '+' || *stdscan_bufptr == '-') {
 181                     /*
 182                      * e can only be followed by +/- if it is either a
 183                      * prefixed hex number or a floating-point number
 184                      */
 185                     is_float = true;
 186                     stdscan_bufptr++;
 187                 }
 188             } else if (c == 'H' || c == 'h' || c == 'X' || c == 'x') {
 189                 is_hex = true;
 190             } else if (c == 'P' || c == 'p') {
 191                 is_float = true;
 192                 if (*stdscan_bufptr == '+' || *stdscan_bufptr == '-')
 193                     stdscan_bufptr++;
 194             } else if (isnumchar(c) || c == '_')
 195                 ; /* just advance */
 196             else if (c == '.')
 197                 is_float = true;
 198             else
 199                 break;
 200         }
 201         stdscan_bufptr--;       /* Point to first character beyond number */
 202
 203         if (has_e && !is_hex) {
 204             /* 1e13 is floating-point, but 1e13h is not */
 205             is_float = true;
 206         }
 207
 208         if (is_float) {
 209             tv->t_charptr = stdscan_copy(r, stdscan_bufptr - r);
 210             return tv->t_type = TOKEN_FLOAT;
 211         } else {
 212             r = stdscan_copy(r, stdscan_bufptr - r);
 213             tv->t_integer = readnum(r, &rn_error);
 214             stdscan_pop();
 215             if (rn_error) {
 216                 /* some malformation occurred */
 217                 return tv->t_type = TOKEN_ERRNUM;
 218             }
 219             tv->t_charptr = NULL;
 220             return tv->t_type = TOKEN_NUM;
 221         }
 222     } else if (*stdscan_bufptr == '\'' || *stdscan_bufptr == '"' ||
 223                *stdscan_bufptr == '`') {
 224         /* a quoted string */
 225         char start_quote = *stdscan_bufptr;
 226         tv->t_charptr = stdscan_bufptr;
 227         tv->t_inttwo = nasm_unquote(tv->t_charptr, &stdscan_bufptr);
 228         if (*stdscan_bufptr != start_quote)
 229             return tv->t_type = TOKEN_ERRSTR;
 230         stdscan_bufptr++;       /* Skip final quote */
 231         return tv->t_type = TOKEN_STR;
 232     } else if (*stdscan_bufptr == ';') {
 233         /* a comment has happened - stay */
 234         return tv->t_type = 0;
 235     } else if (stdscan_bufptr[0] == '>' && stdscan_bufptr[1] == '>') {
 236         stdscan_bufptr += 2;
 237         return tv->t_type = TOKEN_SHR;
 238     } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '<') {
 239         stdscan_bufptr += 2;
 240         return tv->t_type = TOKEN_SHL;
 241     } else if (stdscan_bufptr[0] == '/' && stdscan_bufptr[1] == '/') {
 242         stdscan_bufptr += 2;
 243         return tv->t_type = TOKEN_SDIV;
 244     } else if (stdscan_bufptr[0] == '%' && stdscan_bufptr[1] == '%') {
 245         stdscan_bufptr += 2;
 246         return tv->t_type = TOKEN_SMOD;
 247     } else if (stdscan_bufptr[0] == '=' && stdscan_bufptr[1] == '=') {
 248         stdscan_bufptr += 2;
 249         return tv->t_type = TOKEN_EQ;
 250     } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '>') {
 251         stdscan_bufptr += 2;
 252         return tv->t_type = TOKEN_NE;
 253     } else if (stdscan_bufptr[0] == '!' && stdscan_bufptr[1] == '=') {
 254         stdscan_bufptr += 2;
 255         return tv->t_type = TOKEN_NE;
 256     } else if (stdscan_bufptr[0] == '<' && stdscan_bufptr[1] == '=') {
 257         stdscan_bufptr += 2;
 258         return tv->t_type = TOKEN_LE;
 259     } else if (stdscan_bufptr[0] == '>' && stdscan_bufptr[1] == '=') {
 260         stdscan_bufptr += 2;
 261         return tv->t_type = TOKEN_GE;
 262     } else if (stdscan_bufptr[0] == '&' && stdscan_bufptr[1] == '&') {
 263         stdscan_bufptr += 2;
 264         return tv->t_type = TOKEN_DBL_AND;
 265     } else if (stdscan_bufptr[0] == '^' && stdscan_bufptr[1] == '^') {
 266         stdscan_bufptr += 2;
 267         return tv->t_type = TOKEN_DBL_XOR;
 268     } else if (stdscan_bufptr[0] == '|' && stdscan_bufptr[1] == '|') {
 269         stdscan_bufptr += 2;
 270         return tv->t_type = TOKEN_DBL_OR;
 271     } else                      /* just an ordinary char */
 272         return tv->t_type = (uint8_t)(*stdscan_bufptr++);
 273 }