cifs_unicode.h 9.1 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387
  1. /*
  2. * cifs_unicode: Unicode kernel case support
  3. *
  4. * Function:
  5. * Convert a unicode character to upper or lower case using
  6. * compressed tables.
  7. *
  8. * Copyright (c) International Business Machines Corp., 2000,2009
  9. *
  10. * This program is free software; you can redistribute it and/or modify
  11. * it under the terms of the GNU General Public License as published by
  12. * the Free Software Foundation; either version 2 of the License, or
  13. * (at your option) any later version.
  14. *
  15. * This program is distributed in the hope that it will be useful,
  16. * but WITHOUT ANY WARRANTY; without even the implied warranty of
  17. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
  18. * the GNU General Public License for more details.
  19. *
  20. * You should have received a copy of the GNU General Public License
  21. * along with this program; if not, write to the Free Software
  22. * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  23. *
  24. *
  25. * Notes:
  26. * These APIs are based on the C library functions. The semantics
  27. * should match the C functions but with expanded size operands.
  28. *
  29. * The upper/lower functions are based on a table created by mkupr.
  30. * This is a compressed table of upper and lower case conversion.
  31. *
  32. */
  33. #ifndef _CIFS_UNICODE_H
  34. #define _CIFS_UNICODE_H
  35. #include <asm/byteorder.h>
  36. #include <linux/types.h>
  37. #include <linux/nls.h>
  38. #define UNIUPR_NOLOWER /* Example to not expand lower case tables */
  39. /*
  40. * Windows maps these to the user defined 16 bit Unicode range since they are
  41. * reserved symbols (along with \ and /), otherwise illegal to store
  42. * in filenames in NTFS
  43. */
  44. #define UNI_ASTERISK (__u16) ('*' + 0xF000)
  45. #define UNI_QUESTION (__u16) ('?' + 0xF000)
  46. #define UNI_COLON (__u16) (':' + 0xF000)
  47. #define UNI_GRTRTHAN (__u16) ('>' + 0xF000)
  48. #define UNI_LESSTHAN (__u16) ('<' + 0xF000)
  49. #define UNI_PIPE (__u16) ('|' + 0xF000)
  50. #define UNI_SLASH (__u16) ('\\' + 0xF000)
  51. /* Just define what we want from uniupr.h. We don't want to define the tables
  52. * in each source file.
  53. */
  54. #ifndef UNICASERANGE_DEFINED
  55. struct UniCaseRange {
  56. wchar_t start;
  57. wchar_t end;
  58. signed char *table;
  59. };
  60. #endif /* UNICASERANGE_DEFINED */
  61. #ifndef UNIUPR_NOUPPER
  62. extern signed char CifsUniUpperTable[512];
  63. extern const struct UniCaseRange CifsUniUpperRange[];
  64. #endif /* UNIUPR_NOUPPER */
  65. #ifndef UNIUPR_NOLOWER
  66. extern signed char CifsUniLowerTable[512];
  67. extern const struct UniCaseRange CifsUniLowerRange[];
  68. #endif /* UNIUPR_NOLOWER */
  69. #ifdef __KERNEL__
  70. int cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
  71. const struct nls_table *codepage, bool mapchar);
  72. int cifs_utf16_bytes(const __le16 *from, int maxbytes,
  73. const struct nls_table *codepage);
  74. int cifs_strtoUTF16(__le16 *, const char *, int, const struct nls_table *);
  75. char *cifs_strndup_from_utf16(const char *src, const int maxlen,
  76. const bool is_unicode,
  77. const struct nls_table *codepage);
  78. extern int cifsConvertToUTF16(__le16 *target, const char *source, int maxlen,
  79. const struct nls_table *cp, int mapChars);
  80. #ifdef CONFIG_CIFS_SMB2
  81. extern __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen,
  82. int *utf16_len, const struct nls_table *cp,
  83. int remap);
  84. #endif /* CONFIG_CIFS_SMB2 */
  85. #endif
  86. /*
  87. * UniStrcat: Concatenate the second string to the first
  88. *
  89. * Returns:
  90. * Address of the first string
  91. */
  92. static inline wchar_t *
  93. UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
  94. {
  95. wchar_t *anchor = ucs1; /* save a pointer to start of ucs1 */
  96. while (*ucs1++) ; /* To end of first string */
  97. ucs1--; /* Return to the null */
  98. while ((*ucs1++ = *ucs2++)) ; /* copy string 2 over */
  99. return anchor;
  100. }
  101. /*
  102. * UniStrchr: Find a character in a string
  103. *
  104. * Returns:
  105. * Address of first occurrence of character in string
  106. * or NULL if the character is not in the string
  107. */
  108. static inline wchar_t *
  109. UniStrchr(const wchar_t *ucs, wchar_t uc)
  110. {
  111. while ((*ucs != uc) && *ucs)
  112. ucs++;
  113. if (*ucs == uc)
  114. return (wchar_t *) ucs;
  115. return NULL;
  116. }
  117. /*
  118. * UniStrcmp: Compare two strings
  119. *
  120. * Returns:
  121. * < 0: First string is less than second
  122. * = 0: Strings are equal
  123. * > 0: First string is greater than second
  124. */
  125. static inline int
  126. UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2)
  127. {
  128. while ((*ucs1 == *ucs2) && *ucs1) {
  129. ucs1++;
  130. ucs2++;
  131. }
  132. return (int) *ucs1 - (int) *ucs2;
  133. }
  134. /*
  135. * UniStrcpy: Copy a string
  136. */
  137. static inline wchar_t *
  138. UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2)
  139. {
  140. wchar_t *anchor = ucs1; /* save the start of result string */
  141. while ((*ucs1++ = *ucs2++)) ;
  142. return anchor;
  143. }
  144. /*
  145. * UniStrlen: Return the length of a string (in 16 bit Unicode chars not bytes)
  146. */
  147. static inline size_t
  148. UniStrlen(const wchar_t *ucs1)
  149. {
  150. int i = 0;
  151. while (*ucs1++)
  152. i++;
  153. return i;
  154. }
  155. /*
  156. * UniStrnlen: Return the length (in 16 bit Unicode chars not bytes) of a
  157. * string (length limited)
  158. */
  159. static inline size_t
  160. UniStrnlen(const wchar_t *ucs1, int maxlen)
  161. {
  162. int i = 0;
  163. while (*ucs1++) {
  164. i++;
  165. if (i >= maxlen)
  166. break;
  167. }
  168. return i;
  169. }
  170. /*
  171. * UniStrncat: Concatenate length limited string
  172. */
  173. static inline wchar_t *
  174. UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  175. {
  176. wchar_t *anchor = ucs1; /* save pointer to string 1 */
  177. while (*ucs1++) ;
  178. ucs1--; /* point to null terminator of s1 */
  179. while (n-- && (*ucs1 = *ucs2)) { /* copy s2 after s1 */
  180. ucs1++;
  181. ucs2++;
  182. }
  183. *ucs1 = 0; /* Null terminate the result */
  184. return (anchor);
  185. }
  186. /*
  187. * UniStrncmp: Compare length limited string
  188. */
  189. static inline int
  190. UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  191. {
  192. if (!n)
  193. return 0; /* Null strings are equal */
  194. while ((*ucs1 == *ucs2) && *ucs1 && --n) {
  195. ucs1++;
  196. ucs2++;
  197. }
  198. return (int) *ucs1 - (int) *ucs2;
  199. }
  200. /*
  201. * UniStrncmp_le: Compare length limited string - native to little-endian
  202. */
  203. static inline int
  204. UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  205. {
  206. if (!n)
  207. return 0; /* Null strings are equal */
  208. while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) {
  209. ucs1++;
  210. ucs2++;
  211. }
  212. return (int) *ucs1 - (int) __le16_to_cpu(*ucs2);
  213. }
  214. /*
  215. * UniStrncpy: Copy length limited string with pad
  216. */
  217. static inline wchar_t *
  218. UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  219. {
  220. wchar_t *anchor = ucs1;
  221. while (n-- && *ucs2) /* Copy the strings */
  222. *ucs1++ = *ucs2++;
  223. n++;
  224. while (n--) /* Pad with nulls */
  225. *ucs1++ = 0;
  226. return anchor;
  227. }
  228. /*
  229. * UniStrncpy_le: Copy length limited string with pad to little-endian
  230. */
  231. static inline wchar_t *
  232. UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  233. {
  234. wchar_t *anchor = ucs1;
  235. while (n-- && *ucs2) /* Copy the strings */
  236. *ucs1++ = __le16_to_cpu(*ucs2++);
  237. n++;
  238. while (n--) /* Pad with nulls */
  239. *ucs1++ = 0;
  240. return anchor;
  241. }
  242. /*
  243. * UniStrstr: Find a string in a string
  244. *
  245. * Returns:
  246. * Address of first match found
  247. * NULL if no matching string is found
  248. */
  249. static inline wchar_t *
  250. UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2)
  251. {
  252. const wchar_t *anchor1 = ucs1;
  253. const wchar_t *anchor2 = ucs2;
  254. while (*ucs1) {
  255. if (*ucs1 == *ucs2) {
  256. /* Partial match found */
  257. ucs1++;
  258. ucs2++;
  259. } else {
  260. if (!*ucs2) /* Match found */
  261. return (wchar_t *) anchor1;
  262. ucs1 = ++anchor1; /* No match */
  263. ucs2 = anchor2;
  264. }
  265. }
  266. if (!*ucs2) /* Both end together */
  267. return (wchar_t *) anchor1; /* Match found */
  268. return NULL; /* No match */
  269. }
  270. #ifndef UNIUPR_NOUPPER
  271. /*
  272. * UniToupper: Convert a unicode character to upper case
  273. */
  274. static inline wchar_t
  275. UniToupper(register wchar_t uc)
  276. {
  277. register const struct UniCaseRange *rp;
  278. if (uc < sizeof(CifsUniUpperTable)) {
  279. /* Latin characters */
  280. return uc + CifsUniUpperTable[uc]; /* Use base tables */
  281. } else {
  282. rp = CifsUniUpperRange; /* Use range tables */
  283. while (rp->start) {
  284. if (uc < rp->start) /* Before start of range */
  285. return uc; /* Uppercase = input */
  286. if (uc <= rp->end) /* In range */
  287. return uc + rp->table[uc - rp->start];
  288. rp++; /* Try next range */
  289. }
  290. }
  291. return uc; /* Past last range */
  292. }
  293. /*
  294. * UniStrupr: Upper case a unicode string
  295. */
  296. static inline wchar_t *
  297. UniStrupr(register wchar_t *upin)
  298. {
  299. register wchar_t *up;
  300. up = upin;
  301. while (*up) { /* For all characters */
  302. *up = UniToupper(*up);
  303. up++;
  304. }
  305. return upin; /* Return input pointer */
  306. }
  307. #endif /* UNIUPR_NOUPPER */
  308. #ifndef UNIUPR_NOLOWER
  309. /*
  310. * UniTolower: Convert a unicode character to lower case
  311. */
  312. static inline wchar_t
  313. UniTolower(register wchar_t uc)
  314. {
  315. register const struct UniCaseRange *rp;
  316. if (uc < sizeof(CifsUniLowerTable)) {
  317. /* Latin characters */
  318. return uc + CifsUniLowerTable[uc]; /* Use base tables */
  319. } else {
  320. rp = CifsUniLowerRange; /* Use range tables */
  321. while (rp->start) {
  322. if (uc < rp->start) /* Before start of range */
  323. return uc; /* Uppercase = input */
  324. if (uc <= rp->end) /* In range */
  325. return uc + rp->table[uc - rp->start];
  326. rp++; /* Try next range */
  327. }
  328. }
  329. return uc; /* Past last range */
  330. }
  331. /*
  332. * UniStrlwr: Lower case a unicode string
  333. */
  334. static inline wchar_t *
  335. UniStrlwr(register wchar_t *upin)
  336. {
  337. register wchar_t *up;
  338. up = upin;
  339. while (*up) { /* For all characters */
  340. *up = UniTolower(*up);
  341. up++;
  342. }
  343. return upin; /* Return input pointer */
  344. }
  345. #endif
  346. #endif /* _CIFS_UNICODE_H */