mxml-entity.c 9.68 KB
Newer Older
1
/*
Michael Sweet's avatar
Michael Sweet committed
2
 * Character entity support code for Mini-XML, a small XML file parsing library.
3
 *
Michael Sweet's avatar
Michael Sweet committed
4
 * Copyright 2003-2017 by Michael R Sweet.
5
 *
6 7 8 9 10
 * These coded instructions, statements, and computer programs are the
 * property of Michael R Sweet and are protected by Federal copyright
 * law.  Distribution and use rights are outlined in the file "COPYING"
 * which should have been included with this file.  If this file is
 * missing or damaged, see the license at:
11
 *
Michael Sweet's avatar
Michael Sweet committed
12
 *     https://michaelrsweet.github.io/mxml
13 14 15 16 17 18
 */

/*
 * Include necessary headers...
 */

19
#include "mxml-private.h"
20 21 22 23 24 25


/*
 * 'mxmlEntityAddCallback()' - Add a callback to convert entities to Unicode.
 */

26
int					/* O - 0 on success, -1 on failure */
27
mxmlEntityAddCallback(
28
    mxml_entity_cb_t cb)		/* I - Callback function to add */
29
{
30 31 32 33 34
  _mxml_global_t *global = _mxml_global();
					/* Global data */


  if (global->num_entity_cbs < (int)(sizeof(global->entity_cbs) / sizeof(global->entity_cbs[0])))
35
  {
36 37
    global->entity_cbs[global->num_entity_cbs] = cb;
    global->num_entity_cbs ++;
38 39 40 41 42 43 44 45

    return (0);
  }
  else
  {
    mxml_error("Unable to add entity callback!");

    return (-1);
46 47 48 49
  }
}


50 51 52
/*
 * 'mxmlEntityGetName()' - Get the name that corresponds to the character value.
 *
53
 * If val does not need to be represented by a named entity, @code NULL@ is returned.
54 55
 */

56
const char *				/* O - Entity name or @code NULL@ */
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
mxmlEntityGetName(int val)		/* I - Character value */
{
  switch (val)
  {
    case '&' :
        return ("amp");

    case '<' :
        return ("lt");

    case '>' :
        return ("gt");

    case '\"' :
        return ("quot");

    default :
        return (NULL);
  }
}


/*
 * 'mxmlEntityGetValue()' - Get the character corresponding to a named entity.
 *
 * The entity name can also be a numeric constant. -1 is returned if the
 * name is not known.
 */

int					/* O - Character value or -1 on error */
mxmlEntityGetValue(const char *name)	/* I - Entity name */
88
{
89 90 91 92
  int		i;			/* Looping var */
  int		ch;			/* Character value */
  _mxml_global_t *global = _mxml_global();
					/* Global data */
93 94


95 96
  for (i = 0; i < global->num_entity_cbs; i ++)
    if ((ch = (global->entity_cbs[i])(name)) >= 0)
97 98 99 100 101 102 103 104 105 106 107
      return (ch);

  return (-1);
}


/*
 * 'mxmlEntityRemoveCallback()' - Remove a callback.
 */

void
108 109
mxmlEntityRemoveCallback(
    mxml_entity_cb_t cb)		/* I - Callback function to remove */
110
{
111 112 113
  int		i;			/* Looping var */
  _mxml_global_t *global = _mxml_global();
					/* Global data */
114 115


116 117
  for (i = 0; i < global->num_entity_cbs; i ++)
    if (cb == global->entity_cbs[i])
118 119 120 121 122
    {
     /*
      * Remove the callback...
      */

123
      global->num_entity_cbs --;
124

125 126 127
      if (i < global->num_entity_cbs)
        memmove(global->entity_cbs + i, global->entity_cbs + i + 1,
	        (global->num_entity_cbs - i) * sizeof(global->entity_cbs[0]));
128 129 130 131 132 133 134

      return;
    }
}


/*
135
 * '_mxml_entity_cb()' - Lookup standard (X)HTML entities.
136 137
 */

138 139
int					/* O - Unicode value or -1 */
_mxml_entity_cb(const char *name)	/* I - Entity name */
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
{
  int	diff,				/* Difference between names */
	current,			/* Current entity in search */
	first,				/* First entity in search */
	last;				/* Last entity in search */
  static const struct
  {
    const char	*name;			/* Entity name */
    int		val;			/* Character value */
  }	entities[] =
  {
    { "AElig",		198 },
    { "Aacute",		193 },
    { "Acirc",		194 },
    { "Agrave",		192 },
    { "Alpha",		913 },
    { "Aring",		197 },
    { "Atilde",		195 },
    { "Auml",		196 },
    { "Beta",		914 },
    { "Ccedil",		199 },
    { "Chi",		935 },
    { "Dagger",		8225 },
    { "Delta",		916 },
    { "Dstrok",		208 },
    { "ETH",		208 },
    { "Eacute",		201 },
    { "Ecirc",		202 },
    { "Egrave",		200 },
    { "Epsilon",	917 },
    { "Eta",		919 },
    { "Euml",		203 },
    { "Gamma",		915 },
    { "Iacute",		205 },
    { "Icirc",		206 },
    { "Igrave",		204 },
    { "Iota",		921 },
    { "Iuml",		207 },
    { "Kappa",		922 },
    { "Lambda",		923 },
    { "Mu",		924 },
    { "Ntilde",		209 },
    { "Nu",		925 },
    { "OElig",		338 },
    { "Oacute",		211 },
    { "Ocirc",		212 },
    { "Ograve",		210 },
    { "Omega",		937 },
    { "Omicron",	927 },
    { "Oslash",		216 },
    { "Otilde",		213 },
    { "Ouml",		214 },
    { "Phi",		934 },
    { "Pi",		928 },
    { "Prime",		8243 },
    { "Psi",		936 },
    { "Rho",		929 },
    { "Scaron",		352 },
    { "Sigma",		931 },
    { "THORN",		222 },
    { "Tau",		932 },
    { "Theta",		920 },
    { "Uacute",		218 },
    { "Ucirc",		219 },
    { "Ugrave",		217 },
    { "Upsilon",	933 },
    { "Uuml",		220 },
    { "Xi",		926 },
    { "Yacute",		221 },
    { "Yuml",		376 },
    { "Zeta",		918 },
    { "aacute",		225 },
    { "acirc",		226 },
    { "acute",		180 },
    { "aelig",		230 },
    { "agrave",		224 },
    { "alefsym",	8501 },
    { "alpha",		945 },
    { "amp",		'&' },
    { "and",		8743 },
    { "ang",		8736 },
221
    { "apos",           '\'' },
222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410
    { "aring",		229 },
    { "asymp",		8776 },
    { "atilde",		227 },
    { "auml",		228 },
    { "bdquo",		8222 },
    { "beta",		946 },
    { "brkbar",		166 },
    { "brvbar",		166 },
    { "bull",		8226 },
    { "cap",		8745 },
    { "ccedil",		231 },
    { "cedil",		184 },
    { "cent",		162 },
    { "chi",		967 },
    { "circ",		710 },
    { "clubs",		9827 },
    { "cong",		8773 },
    { "copy",		169 },
    { "crarr",		8629 },
    { "cup",		8746 },
    { "curren",		164 },
    { "dArr",		8659 },
    { "dagger",		8224 },
    { "darr",		8595 },
    { "deg",		176 },
    { "delta",		948 },
    { "diams",		9830 },
    { "die",		168 },
    { "divide",		247 },
    { "eacute",		233 },
    { "ecirc",		234 },
    { "egrave",		232 },
    { "empty",		8709 },
    { "emsp",		8195 },
    { "ensp",		8194 },
    { "epsilon",	949 },
    { "equiv",		8801 },
    { "eta",		951 },
    { "eth",		240 },
    { "euml",		235 },
    { "euro",		8364 },
    { "exist",		8707 },
    { "fnof",		402 },
    { "forall",		8704 },
    { "frac12",		189 },
    { "frac14",		188 },
    { "frac34",		190 },
    { "frasl",		8260 },
    { "gamma",		947 },
    { "ge",		8805 },
    { "gt",		'>' },
    { "hArr",		8660 },
    { "harr",		8596 },
    { "hearts",		9829 },
    { "hellip",		8230 },
    { "hibar",		175 },
    { "iacute",		237 },
    { "icirc",		238 },
    { "iexcl",		161 },
    { "igrave",		236 },
    { "image",		8465 },
    { "infin",		8734 },
    { "int",		8747 },
    { "iota",		953 },
    { "iquest",		191 },
    { "isin",		8712 },
    { "iuml",		239 },
    { "kappa",		954 },
    { "lArr",		8656 },
    { "lambda",		955 },
    { "lang",		9001 },
    { "laquo",		171 },
    { "larr",		8592 },
    { "lceil",		8968 },
    { "ldquo",		8220 },
    { "le",		8804 },
    { "lfloor",		8970 },
    { "lowast",		8727 },
    { "loz",		9674 },
    { "lrm",		8206 },
    { "lsaquo",		8249 },
    { "lsquo",		8216 },
    { "lt",		'<' },
    { "macr",		175 },
    { "mdash",		8212 },
    { "micro",		181 },
    { "middot",		183 },
    { "minus",		8722 },
    { "mu",		956 },
    { "nabla",		8711 },
    { "nbsp",		160 },
    { "ndash",		8211 },
    { "ne",		8800 },
    { "ni",		8715 },
    { "not",		172 },
    { "notin",		8713 },
    { "nsub",		8836 },
    { "ntilde",		241 },
    { "nu",		957 },
    { "oacute",		243 },
    { "ocirc",		244 },
    { "oelig",		339 },
    { "ograve",		242 },
    { "oline",		8254 },
    { "omega",		969 },
    { "omicron",	959 },
    { "oplus",		8853 },
    { "or",		8744 },
    { "ordf",		170 },
    { "ordm",		186 },
    { "oslash",		248 },
    { "otilde",		245 },
    { "otimes",		8855 },
    { "ouml",		246 },
    { "para",		182 },
    { "part",		8706 },
    { "permil",		8240 },
    { "perp",		8869 },
    { "phi",		966 },
    { "pi",		960 },
    { "piv",		982 },
    { "plusmn",		177 },
    { "pound",		163 },
    { "prime",		8242 },
    { "prod",		8719 },
    { "prop",		8733 },
    { "psi",		968 },
    { "quot",		'\"' },
    { "rArr",		8658 },
    { "radic",		8730 },
    { "rang",		9002 },
    { "raquo",		187 },
    { "rarr",		8594 },
    { "rceil",		8969 },
    { "rdquo",		8221 },
    { "real",		8476 },
    { "reg",		174 },
    { "rfloor",		8971 },
    { "rho",		961 },
    { "rlm",		8207 },
    { "rsaquo",		8250 },
    { "rsquo",		8217 },
    { "sbquo",		8218 },
    { "scaron",		353 },
    { "sdot",		8901 },
    { "sect",		167 },
    { "shy",		173 },
    { "sigma",		963 },
    { "sigmaf",		962 },
    { "sim",		8764 },
    { "spades",		9824 },
    { "sub",		8834 },
    { "sube",		8838 },
    { "sum",		8721 },
    { "sup",		8835 },
    { "sup1",		185 },
    { "sup2",		178 },
    { "sup3",		179 },
    { "supe",		8839 },
    { "szlig",		223 },
    { "tau",		964 },
    { "there4",		8756 },
    { "theta",		952 },
    { "thetasym",	977 },
    { "thinsp",		8201 },
    { "thorn",		254 },
    { "tilde",		732 },
    { "times",		215 },
    { "trade",		8482 },
    { "uArr",		8657 },
    { "uacute",		250 },
    { "uarr",		8593 },
    { "ucirc",		251 },
    { "ugrave",		249 },
    { "uml",		168 },
    { "upsih",		978 },
    { "upsilon",	965 },
    { "uuml",		252 },
    { "weierp",		8472 },
    { "xi",		958 },
    { "yacute",		253 },
    { "yen",		165 },
    { "yuml",		255 },
    { "zeta",		950 },
    { "zwj",		8205 },
    { "zwnj",		8204 }
  };


411 412 413 414
 /*
  * Do a binary search for the named entity...
  */

415 416 417
  first = 0;
  last  = (int)(sizeof(entities) / sizeof(entities[0]) - 1);

418
  while ((last - first) > 1)
419 420 421 422 423 424 425 426 427 428 429
  {
    current = (first + last) / 2;

    if ((diff = strcmp(name, entities[current].name)) == 0)
      return (entities[current].val);
    else if (diff < 0)
      last = current;
    else
      first = current;
  }

430 431 432 433
 /*
  * If we get here, there is a small chance that there is still
  * a match; check first and last...
  */
434

435 436 437 438
  if (!strcmp(name, entities[first].name))
    return (entities[first].val);
  else if (!strcmp(name, entities[last].name))
    return (entities[last].val);
439 440 441
  else
    return (-1);
}