cifs_unicode.h 8.8 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380
  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_ASTERIK (__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_ucs2(char *to, const __le16 *from, int tolen, int fromlen,
  71. const struct nls_table *codepage, bool mapchar);
  72. int cifs_ucs2_bytes(const __le16 *from, int maxbytes,
  73. const struct nls_table *codepage);
  74. int cifs_strtoUCS(__le16 *, const char *, int, const struct nls_table *);
  75. char *cifs_strndup_from_ucs(const char *src, const int maxlen,
  76. const bool is_unicode,
  77. const struct nls_table *codepage);
  78. #endif
  79. /*
  80. * UniStrcat: Concatenate the second string to the first
  81. *
  82. * Returns:
  83. * Address of the first string
  84. */
  85. static inline wchar_t *
  86. UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
  87. {
  88. wchar_t *anchor = ucs1; /* save a pointer to start of ucs1 */
  89. while (*ucs1++) ; /* To end of first string */
  90. ucs1--; /* Return to the null */
  91. while ((*ucs1++ = *ucs2++)) ; /* copy string 2 over */
  92. return anchor;
  93. }
  94. /*
  95. * UniStrchr: Find a character in a string
  96. *
  97. * Returns:
  98. * Address of first occurrence of character in string
  99. * or NULL if the character is not in the string
  100. */
  101. static inline wchar_t *
  102. UniStrchr(const wchar_t *ucs, wchar_t uc)
  103. {
  104. while ((*ucs != uc) && *ucs)
  105. ucs++;
  106. if (*ucs == uc)
  107. return (wchar_t *) ucs;
  108. return NULL;
  109. }
  110. /*
  111. * UniStrcmp: Compare two strings
  112. *
  113. * Returns:
  114. * < 0: First string is less than second
  115. * = 0: Strings are equal
  116. * > 0: First string is greater than second
  117. */
  118. static inline int
  119. UniStrcmp(const wchar_t *ucs1, const wchar_t *ucs2)
  120. {
  121. while ((*ucs1 == *ucs2) && *ucs1) {
  122. ucs1++;
  123. ucs2++;
  124. }
  125. return (int) *ucs1 - (int) *ucs2;
  126. }
  127. /*
  128. * UniStrcpy: Copy a string
  129. */
  130. static inline wchar_t *
  131. UniStrcpy(wchar_t *ucs1, const wchar_t *ucs2)
  132. {
  133. wchar_t *anchor = ucs1; /* save the start of result string */
  134. while ((*ucs1++ = *ucs2++)) ;
  135. return anchor;
  136. }
  137. /*
  138. * UniStrlen: Return the length of a string (in 16 bit Unicode chars not bytes)
  139. */
  140. static inline size_t
  141. UniStrlen(const wchar_t *ucs1)
  142. {
  143. int i = 0;
  144. while (*ucs1++)
  145. i++;
  146. return i;
  147. }
  148. /*
  149. * UniStrnlen: Return the length (in 16 bit Unicode chars not bytes) of a
  150. * string (length limited)
  151. */
  152. static inline size_t
  153. UniStrnlen(const wchar_t *ucs1, int maxlen)
  154. {
  155. int i = 0;
  156. while (*ucs1++) {
  157. i++;
  158. if (i >= maxlen)
  159. break;
  160. }
  161. return i;
  162. }
  163. /*
  164. * UniStrncat: Concatenate length limited string
  165. */
  166. static inline wchar_t *
  167. UniStrncat(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  168. {
  169. wchar_t *anchor = ucs1; /* save pointer to string 1 */
  170. while (*ucs1++) ;
  171. ucs1--; /* point to null terminator of s1 */
  172. while (n-- && (*ucs1 = *ucs2)) { /* copy s2 after s1 */
  173. ucs1++;
  174. ucs2++;
  175. }
  176. *ucs1 = 0; /* Null terminate the result */
  177. return (anchor);
  178. }
  179. /*
  180. * UniStrncmp: Compare length limited string
  181. */
  182. static inline int
  183. UniStrncmp(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  184. {
  185. if (!n)
  186. return 0; /* Null strings are equal */
  187. while ((*ucs1 == *ucs2) && *ucs1 && --n) {
  188. ucs1++;
  189. ucs2++;
  190. }
  191. return (int) *ucs1 - (int) *ucs2;
  192. }
  193. /*
  194. * UniStrncmp_le: Compare length limited string - native to little-endian
  195. */
  196. static inline int
  197. UniStrncmp_le(const wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  198. {
  199. if (!n)
  200. return 0; /* Null strings are equal */
  201. while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) {
  202. ucs1++;
  203. ucs2++;
  204. }
  205. return (int) *ucs1 - (int) __le16_to_cpu(*ucs2);
  206. }
  207. /*
  208. * UniStrncpy: Copy length limited string with pad
  209. */
  210. static inline wchar_t *
  211. UniStrncpy(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  212. {
  213. wchar_t *anchor = ucs1;
  214. while (n-- && *ucs2) /* Copy the strings */
  215. *ucs1++ = *ucs2++;
  216. n++;
  217. while (n--) /* Pad with nulls */
  218. *ucs1++ = 0;
  219. return anchor;
  220. }
  221. /*
  222. * UniStrncpy_le: Copy length limited string with pad to little-endian
  223. */
  224. static inline wchar_t *
  225. UniStrncpy_le(wchar_t *ucs1, const wchar_t *ucs2, size_t n)
  226. {
  227. wchar_t *anchor = ucs1;
  228. while (n-- && *ucs2) /* Copy the strings */
  229. *ucs1++ = __le16_to_cpu(*ucs2++);
  230. n++;
  231. while (n--) /* Pad with nulls */
  232. *ucs1++ = 0;
  233. return anchor;
  234. }
  235. /*
  236. * UniStrstr: Find a string in a string
  237. *
  238. * Returns:
  239. * Address of first match found
  240. * NULL if no matching string is found
  241. */
  242. static inline wchar_t *
  243. UniStrstr(const wchar_t *ucs1, const wchar_t *ucs2)
  244. {
  245. const wchar_t *anchor1 = ucs1;
  246. const wchar_t *anchor2 = ucs2;
  247. while (*ucs1) {
  248. if (*ucs1 == *ucs2) {
  249. /* Partial match found */
  250. ucs1++;
  251. ucs2++;
  252. } else {
  253. if (!*ucs2) /* Match found */
  254. return (wchar_t *) anchor1;
  255. ucs1 = ++anchor1; /* No match */
  256. ucs2 = anchor2;
  257. }
  258. }
  259. if (!*ucs2) /* Both end together */
  260. return (wchar_t *) anchor1; /* Match found */
  261. return NULL; /* No match */
  262. }
  263. #ifndef UNIUPR_NOUPPER
  264. /*
  265. * UniToupper: Convert a unicode character to upper case
  266. */
  267. static inline wchar_t
  268. UniToupper(register wchar_t uc)
  269. {
  270. register const struct UniCaseRange *rp;
  271. if (uc < sizeof(CifsUniUpperTable)) {
  272. /* Latin characters */
  273. return uc + CifsUniUpperTable[uc]; /* Use base tables */
  274. } else {
  275. rp = CifsUniUpperRange; /* Use range tables */
  276. while (rp->start) {
  277. if (uc < rp->start) /* Before start of range */
  278. return uc; /* Uppercase = input */
  279. if (uc <= rp->end) /* In range */
  280. return uc + rp->table[uc - rp->start];
  281. rp++; /* Try next range */
  282. }
  283. }
  284. return uc; /* Past last range */
  285. }
  286. /*
  287. * UniStrupr: Upper case a unicode string
  288. */
  289. static inline wchar_t *
  290. UniStrupr(register wchar_t *upin)
  291. {
  292. register wchar_t *up;
  293. up = upin;
  294. while (*up) { /* For all characters */
  295. *up = UniToupper(*up);
  296. up++;
  297. }
  298. return upin; /* Return input pointer */
  299. }
  300. #endif /* UNIUPR_NOUPPER */
  301. #ifndef UNIUPR_NOLOWER
  302. /*
  303. * UniTolower: Convert a unicode character to lower case
  304. */
  305. static inline wchar_t
  306. UniTolower(register wchar_t uc)
  307. {
  308. register const struct UniCaseRange *rp;
  309. if (uc < sizeof(CifsUniLowerTable)) {
  310. /* Latin characters */
  311. return uc + CifsUniLowerTable[uc]; /* Use base tables */
  312. } else {
  313. rp = CifsUniLowerRange; /* Use range tables */
  314. while (rp->start) {
  315. if (uc < rp->start) /* Before start of range */
  316. return uc; /* Uppercase = input */
  317. if (uc <= rp->end) /* In range */
  318. return uc + rp->table[uc - rp->start];
  319. rp++; /* Try next range */
  320. }
  321. }
  322. return uc; /* Past last range */
  323. }
  324. /*
  325. * UniStrlwr: Lower case a unicode string
  326. */
  327. static inline wchar_t *
  328. UniStrlwr(register wchar_t *upin)
  329. {
  330. register wchar_t *up;
  331. up = upin;
  332. while (*up) { /* For all characters */
  333. *up = UniTolower(*up);
  334. up++;
  335. }
  336. return upin; /* Return input pointer */
  337. }
  338. #endif
  339. #endif /* _CIFS_UNICODE_H */