bsd/sys/utfconv.h

   1 /*
   2  * Copyright (c) 2000-2005 Apple Computer, Inc. All rights reserved.
   3  *
   4  * @APPLE_OSREFERENCE_LICENSE_HEADER_START@
   5  *
   6  * This file contains Original Code and/or Modifications of Original Code
   7  * as defined in and that are subject to the Apple Public Source License
   8  * Version 2.0 (the 'License'). You may not use this file except in
   9  * compliance with the License. The rights granted to you under the License
  10  * may not be used to create, or enable the creation or redistribution of,
  11  * unlawful or unlicensed copies of an Apple operating system, or to
  12  * circumvent, violate, or enable the circumvention or violation of, any
  13  * terms of an Apple operating system software license agreement.
  14  *
  15  * Please obtain a copy of the License at
  16  * http://www.opensource.apple.com/apsl/ and read it before using this file.
  17  *
  18  * The Original Code and all software distributed under the License are
  19  * distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
  20  * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
  21  * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
  22  * FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
  23  * Please see the License for the specific language governing rights and
  24  * limitations under the License.
  25  *
  26  * @APPLE_OSREFERENCE_LICENSE_HEADER_END@
  27  */
  28
  29 #ifndef _SYS_UTFCONV_H_
  30 #define _SYS_UTFCONV_H_
  31
  32 #include <sys/appleapiopts.h>
  33 #include <sys/cdefs.h>
  34
  35 #ifdef KERNEL
  36 #ifdef __APPLE_API_UNSTABLE
  37
  38 /*
  39  * UTF-8 encode/decode flags
  40  */
  41 #define UTF_REVERSE_ENDIAN   0x0001   /* reverse UCS-2 byte order */
  42 #define UTF_NO_NULL_TERM     0x0002   /* do not add null termination */
  43 #define UTF_DECOMPOSED       0x0004   /* generate fully decomposed UCS-2 */
  44 #define UTF_PRECOMPOSED      0x0008   /* generate precomposed UCS-2 */
  45 #define UTF_ESCAPE_ILLEGAL   0x0010   /* escape illegal UTF-8 */
  46 #define UTF_SFM_CONVERSIONS  0x0020   /* Use SFM mappings for illegal NTFS chars */
  47
  48 #define UTF_BIG_ENDIAN       \
  49         ((BYTE_ORDER == BIG_ENDIAN) ? 0 : UTF_REVERSE_ENDIAN)
  50
  51 #define UTF_LITTLE_ENDIAN    \
  52         ((BYTE_ORDER == LITTLE_ENDIAN) ? 0 : UTF_REVERSE_ENDIAN)
  53
  54 __BEGIN_DECLS
  55
  56 /*
  57  * utf8_encodelen - Calculate the UTF-8 encoding length
  58  *
  59  * This function takes an Unicode input string, ucsp, of ucslen bytes
  60  * and calculates the size of the UTF-8 output in bytes (not including
  61  * a NULL termination byte). The string must reside in kernel memory.
  62  *
  63  * FLAGS
  64  *    UTF_REVERSE_ENDIAN:  Unicode byte order is opposite current runtime
  65  *
  66  *    UTF_BIG_ENDIAN:  Unicode byte order is always big endian
  67  *
  68  *    UTF_LITTLE_ENDIAN:  Unicode byte order is always little endian
  69  *
  70  *    UTF_DECOMPOSED:  assume fully decomposed output
  71  *
  72  * ERRORS
  73  *    None
  74  */
  75 size_t
  76 utf8_encodelen(const u_int16_t * ucsp, size_t ucslen, u_int16_t altslash,
  77                int flags);
  78
  79
  80 /*
  81  * utf8_encodestr - Encodes a Unicode string into UTF-8
  82  *
  83  * This function takes an Unicode input string, ucsp, of ucslen bytes
  84  * and produces the UTF-8 output into a buffer of buflen bytes pointed
  85  * to by utf8p. The size of the output in bytes (not including a NULL
  86  * termination byte) is returned in utf8len. The UTF-8 string output
  87  * is NULL terminated. Both buffers must reside in kernel memory.
  88  *
  89  * If '/' chars are possible in the Unicode input then an alternate
  90  * (replacement) char must be provided in altslash.
  91  *
  92  * FLAGS
  93  *    UTF_REVERSE_ENDIAN:  Unicode byte order is opposite current runtime
  94  *
  95  *    UTF_BIG_ENDIAN:  Unicode byte order is always big endian
  96  *
  97  *    UTF_LITTLE_ENDIAN:  Unicode byte order is always little endian
  98  *
  99  *    UTF_NO_NULL_TERM:  do not add null termination to output string
 100  *
 101  *    UTF_DECOMPOSED:  generate fully decomposed output
 102  *
 103  * ERRORS
 104  *    ENAMETOOLONG:  output did not fit; only utf8len bytes were encoded
 105  *
 106  *    EINVAL:  illegal Unicode char encountered
 107  */
 108 int
 109 utf8_encodestr(const u_int16_t * ucsp, size_t ucslen, u_int8_t * utf8p,
 110                size_t * utf8len, size_t buflen, u_int16_t altslash, int flags);
 111
 112
 113 /*
 114  * utf8_decodestr - Decodes a UTF-8 string into Unicode
 115  *
 116  * This function takes an UTF-8 input string, utf8p, of utf8len bytes
 117  * and produces the Unicode output into a buffer of buflen bytes pointed
 118  * to by ucsp. The size of the output in bytes (not including a NULL
 119  * termination byte) is returned in ucslen. Both buffers must reside
 120  * in kernel memory.
 121  *
 122  * If '/' chars are allowed in the Unicode output then an alternate
 123  * (replacement) char must be provided in altslash.
 124  *
 125  * FLAGS
 126  *    UTF_REV_ENDIAN:  Unicode byte order is opposite current runtime
 127  *
 128  *    UTF_BIG_ENDIAN:  Unicode byte order is always big endian
 129  *
 130  *    UTF_LITTLE_ENDIAN:  Unicode byte order is always little endian
 131  *
 132  *    UTF_DECOMPOSED:  generate fully decomposed output (NFD)
 133  *
 134  *    UTF_PRECOMPOSED:  generate precomposed output (NFC)
 135  *
 136  *    UTF_ESCAPE_ILLEGAL:  percent escape any illegal UTF-8 input
 137  *
 138  * ERRORS
 139  *    ENAMETOOLONG:  output did not fit; only ucslen bytes were decoded.
 140  *
 141  *    EINVAL:  illegal UTF-8 sequence encountered.
 142  */
 143 int
 144 utf8_decodestr(const u_int8_t* utf8p, size_t utf8len, u_int16_t* ucsp,
 145                size_t *ucslen, size_t buflen, u_int16_t altslash, int flags);
 146
 147
 148 /*
 149  * utf8_normalizestr - Normalize a UTF-8 string (NFC or NFD)
 150  *
 151  * This function takes an UTF-8 input string, instr, of inlen bytes
 152  * and produces normalized UTF-8 output into a buffer of buflen bytes
 153  * pointed to by outstr. The size of the output in bytes (not including
 154  * a NULL termination byte) is returned in outlen. In-place conversions
 155  * are not supported (i.e. instr != outstr).  Both buffers must reside
 156  * in kernel memory.
 157  *
 158  * FLAGS
 159  *    UTF_DECOMPOSED:  output string will be fully decomposed (NFD)
 160  *
 161  *    UTF_PRECOMPOSED:  output string will be precomposed (NFC)
 162  *
 163  *    UTF_NO_NULL_TERM:  do not add null termination to output string
 164  *
 165  *    UTF_ESCAPE_ILLEGAL:  percent escape any illegal UTF-8 input
 166  *
 167  * ERRORS
 168  *    ENAMETOOLONG:  output did not fit or input exceeded MAXPATHLEN bytes
 169  *
 170  *    EINVAL:  illegal UTF-8 sequence encountered or invalid flags
 171  */
 172 int
 173 utf8_normalizestr(const u_int8_t* instr, size_t inlen, u_int8_t* outstr,
 174                   size_t *outlen, size_t buflen, int flags);
 175
 176
 177 /*
 178  * utf8_validatestr - validates a UTF-8 string
 179  *
 180  * This function takes an UTF-8 input string, utf8p, of utf8len bytes
 181  * and determines if its valid UTF-8.  The string must reside in kernel
 182  * memory.
 183  *
 184  * ERRORS
 185  *    EINVAL:  illegal UTF-8 sequence encountered.
 186  */
 187 int
 188 utf8_validatestr(const u_int8_t* utf8p, size_t utf8len);
 189
 190
 191 __END_DECLS
 192
 193 #endif /* __APPLE_API_UNSTABLE */
 194 #endif /* KERNEL */
 195
 196 #endif /* !_SYS_UTFCONV_H_ */