unicode.c 9.2 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469
/*
 *  linux/fs/hfsplus/unicode.c
 *
 * Copyright (C) 2001
 * Brad Boyer (flar@allandria.com)
 * (C) 2003 Ardis Technologies <roman@ardistech.com>
 *
 * Handler routines for unicode strings
 */

#include <linux/types.h>
#include <linux/nls.h>
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"

/* Fold the case of a unicode char, given the 16 bit value */
/* Returns folded char, or 0 if ignorable */
static inline u16 case_fold(u16 c)
{
	u16 tmp;

	tmp = hfsplus_case_fold_table[c >> 8];
	if (tmp)
		tmp = hfsplus_case_fold_table[tmp + (c & 0xff)];
	else
		tmp = c;
	return tmp;
}

/* Compare unicode strings, return values like normal strcmp */
int hfsplus_strcasecmp(const struct hfsplus_unistr *s1,
		       const struct hfsplus_unistr *s2)
{
	u16 len1, len2, c1, c2;
	const hfsplus_unichr *p1, *p2;

	len1 = be16_to_cpu(s1->length);
	len2 = be16_to_cpu(s2->length);
	p1 = s1->unicode;
	p2 = s2->unicode;

	while (1) {
		c1 = c2 = 0;

		while (len1 && !c1) {
			c1 = case_fold(be16_to_cpu(*p1));
			p1++;
			len1--;
		}
		while (len2 && !c2) {
			c2 = case_fold(be16_to_cpu(*p2));
			p2++;
			len2--;
		}

		if (c1 != c2)
			return (c1 < c2) ? -1 : 1;
		if (!c1 && !c2)
			return 0;
	}
}

/* Compare names as a sequence of 16-bit unsigned integers */
int hfsplus_strcmp(const struct hfsplus_unistr *s1,
		   const struct hfsplus_unistr *s2)
{
	u16 len1, len2, c1, c2;
	const hfsplus_unichr *p1, *p2;
	int len;

	len1 = be16_to_cpu(s1->length);
	len2 = be16_to_cpu(s2->length);
	p1 = s1->unicode;
	p2 = s2->unicode;

	for (len = min(len1, len2); len > 0; len--) {
		c1 = be16_to_cpu(*p1);
		c2 = be16_to_cpu(*p2);
		if (c1 != c2)
			return c1 < c2 ? -1 : 1;
		p1++;
		p2++;
	}

	return len1 < len2 ? -1 :
	       len1 > len2 ? 1 : 0;
}


#define Hangul_SBase	0xac00
#define Hangul_LBase	0x1100
#define Hangul_VBase	0x1161
#define Hangul_TBase	0x11a7
#define Hangul_SCount	11172
#define Hangul_LCount	19
#define Hangul_VCount	21
#define Hangul_TCount	28
#define Hangul_NCount	(Hangul_VCount * Hangul_TCount)


static u16 *hfsplus_compose_lookup(u16 *p, u16 cc)
{
	int i, s, e;

	s = 1;
	e = p[1];
	if (!e || cc < p[s * 2] || cc > p[e * 2])
		return NULL;
	do {
		i = (s + e) / 2;
		if (cc > p[i * 2])
			s = i + 1;
		else if (cc < p[i * 2])
			e = i - 1;
		else
			return hfsplus_compose_table + p[i * 2 + 1];
	} while (s <= e);
	return NULL;
}

int hfsplus_uni2asc(struct super_block *sb,
		const struct hfsplus_unistr *ustr,
		char *astr, int *len_p)
{
	const hfsplus_unichr *ip;
	struct nls_table *nls = HFSPLUS_SB(sb)->nls;
	u8 *op;
	u16 cc, c0, c1;
	u16 *ce1, *ce2;
	int i, len, ustrlen, res, compose;

	op = astr;
	ip = ustr->unicode;
	ustrlen = be16_to_cpu(ustr->length);
	len = *len_p;
	ce1 = NULL;
	compose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);

	while (ustrlen > 0) {
		c0 = be16_to_cpu(*ip++);
		ustrlen--;
		/* search for single decomposed char */
		if (likely(compose))
			ce1 = hfsplus_compose_lookup(hfsplus_compose_table, c0);
		if (ce1)
			cc = ce1[0];
		else
			cc = 0;
		if (cc) {
			/* start of a possibly decomposed Hangul char */
			if (cc != 0xffff)
				goto done;
			if (!ustrlen)
				goto same;
			c1 = be16_to_cpu(*ip) - Hangul_VBase;
			if (c1 < Hangul_VCount) {
				/* compose the Hangul char */
				cc = (c0 - Hangul_LBase) * Hangul_VCount;
				cc = (cc + c1) * Hangul_TCount;
				cc += Hangul_SBase;
				ip++;
				ustrlen--;
				if (!ustrlen)
					goto done;
				c1 = be16_to_cpu(*ip) - Hangul_TBase;
				if (c1 > 0 && c1 < Hangul_TCount) {
					cc += c1;
					ip++;
					ustrlen--;
				}
				goto done;
			}
		}
		while (1) {
			/* main loop for common case of not composed chars */
			if (!ustrlen)
				goto same;
			c1 = be16_to_cpu(*ip);
			if (likely(compose))
				ce1 = hfsplus_compose_lookup(
					hfsplus_compose_table, c1);
			if (ce1)
				break;
			switch (c0) {
			case 0:
				c0 = 0x2400;
				break;
			case '/':
				c0 = ':';
				break;
			}
			res = nls->uni2char(c0, op, len);
			if (res < 0) {
				if (res == -ENAMETOOLONG)
					goto out;
				*op = '?';
				res = 1;
			}
			op += res;
			len -= res;
			c0 = c1;
			ip++;
			ustrlen--;
		}
		ce2 = hfsplus_compose_lookup(ce1, c0);
		if (ce2) {
			i = 1;
			while (i < ustrlen) {
				ce1 = hfsplus_compose_lookup(ce2,
					be16_to_cpu(ip[i]));
				if (!ce1)
					break;
				i++;
				ce2 = ce1;
			}
			cc = ce2[0];
			if (cc) {
				ip += i;
				ustrlen -= i;
				goto done;
			}
		}
same:
		switch (c0) {
		case 0:
			cc = 0x2400;
			break;
		case '/':
			cc = ':';
			break;
		default:
			cc = c0;
		}
done:
		res = nls->uni2char(cc, op, len);
		if (res < 0) {
			if (res == -ENAMETOOLONG)
				goto out;
			*op = '?';
			res = 1;
		}
		op += res;
		len -= res;
	}
	res = 0;
out:
	*len_p = (char *)op - astr;
	return res;
}

/*
 * Convert one or more ASCII characters into a single unicode character.
 * Returns the number of ASCII characters corresponding to the unicode char.
 */
static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
			      wchar_t *uc)
{
	int size = HFSPLUS_SB(sb)->nls->char2uni(astr, len, uc);
	if (size <= 0) {
		*uc = '?';
		size = 1;
	}
	switch (*uc) {
	case 0x2400:
		*uc = 0;
		break;
	case ':':
		*uc = '/';
		break;
	}
	return size;
}

/* Decomposes a single unicode character. */
static inline u16 *decompose_unichar(wchar_t uc, int *size)
{
	int off;

	off = hfsplus_decompose_table[(uc >> 12) & 0xf];
	if (off == 0 || off == 0xffff)
		return NULL;

	off = hfsplus_decompose_table[off + ((uc >> 8) & 0xf)];
	if (!off)
		return NULL;

	off = hfsplus_decompose_table[off + ((uc >> 4) & 0xf)];
	if (!off)
		return NULL;

	off = hfsplus_decompose_table[off + (uc & 0xf)];
	*size = off & 3;
	if (*size == 0)
		return NULL;
	return hfsplus_decompose_table + (off / 4);
}

int hfsplus_asc2uni(struct super_block *sb,
		    struct hfsplus_unistr *ustr, int max_unistr_len,
		    const char *astr, int len)
{
	int size, dsize, decompose;
	u16 *dstr, outlen = 0;
	wchar_t c;

	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
	while (outlen < max_unistr_len && len > 0) {
		size = asc2unichar(sb, astr, len, &c);

		if (decompose)
			dstr = decompose_unichar(c, &dsize);
		else
			dstr = NULL;
		if (dstr) {
			if (outlen + dsize > max_unistr_len)
				break;
			do {
				ustr->unicode[outlen++] = cpu_to_be16(*dstr++);
			} while (--dsize > 0);
		} else
			ustr->unicode[outlen++] = cpu_to_be16(c);

		astr += size;
		len -= size;
	}
	ustr->length = cpu_to_be16(outlen);
	if (len > 0)
		return -ENAMETOOLONG;
	return 0;
}

/*
 * Hash a string to an integer as appropriate for the HFS+ filesystem.
 * Composed unicode characters are decomposed and case-folding is performed
 * if the appropriate bits are (un)set on the superblock.
 */
int hfsplus_hash_dentry(const struct dentry *dentry, struct qstr *str)
{
	struct super_block *sb = dentry->d_sb;
	const char *astr;
	const u16 *dstr;
	int casefold, decompose, size, len;
	unsigned long hash;
	wchar_t c;
	u16 c2;

	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
	hash = init_name_hash();
	astr = str->name;
	len = str->len;
	while (len > 0) {
		int uninitialized_var(dsize);
		size = asc2unichar(sb, astr, len, &c);
		astr += size;
		len -= size;

		if (decompose)
			dstr = decompose_unichar(c, &dsize);
		else
			dstr = NULL;
		if (dstr) {
			do {
				c2 = *dstr++;
				if (casefold)
					c2 = case_fold(c2);
				if (!casefold || c2)
					hash = partial_name_hash(c2, hash);
			} while (--dsize > 0);
		} else {
			c2 = c;
			if (casefold)
				c2 = case_fold(c2);
			if (!casefold || c2)
				hash = partial_name_hash(c2, hash);
		}
	}
	str->hash = end_name_hash(hash);

	return 0;
}

/*
 * Compare strings with HFS+ filename ordering.
 * Composed unicode characters are decomposed and case-folding is performed
 * if the appropriate bits are (un)set on the superblock.
 */
int hfsplus_compare_dentry(const struct dentry *parent, const struct dentry *dentry,
		unsigned int len, const char *str, const struct qstr *name)
{
	struct super_block *sb = parent->d_sb;
	int casefold, decompose, size;
	int dsize1, dsize2, len1, len2;
	const u16 *dstr1, *dstr2;
	const char *astr1, *astr2;
	u16 c1, c2;
	wchar_t c;

	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
	astr1 = str;
	len1 = len;
	astr2 = name->name;
	len2 = name->len;
	dsize1 = dsize2 = 0;
	dstr1 = dstr2 = NULL;

	while (len1 > 0 && len2 > 0) {
		if (!dsize1) {
			size = asc2unichar(sb, astr1, len1, &c);
			astr1 += size;
			len1 -= size;

			if (decompose)
				dstr1 = decompose_unichar(c, &dsize1);
			if (!decompose || !dstr1) {
				c1 = c;
				dstr1 = &c1;
				dsize1 = 1;
			}
		}

		if (!dsize2) {
			size = asc2unichar(sb, astr2, len2, &c);
			astr2 += size;
			len2 -= size;

			if (decompose)
				dstr2 = decompose_unichar(c, &dsize2);
			if (!decompose || !dstr2) {
				c2 = c;
				dstr2 = &c2;
				dsize2 = 1;
			}
		}

		c1 = *dstr1;
		c2 = *dstr2;
		if (casefold) {
			c1 = case_fold(c1);
			if (!c1) {
				dstr1++;
				dsize1--;
				continue;
			}
			c2 = case_fold(c2);
			if (!c2) {
				dstr2++;
				dsize2--;
				continue;
			}
		}
		if (c1 < c2)
			return -1;
		else if (c1 > c2)
			return 1;

		dstr1++;
		dsize1--;
		dstr2++;
		dsize2--;
	}

	if (len1 < len2)
		return -1;
	if (len1 > len2)
		return 1;
	return 0;
}