lib/punycode.h

   1 /* punycode.h --- Declarations for punycode functions.
   2  * Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007  Simon Josefsson
   3  *
   4  * This file is part of GNU Libidn.
   5  *
   6  * GNU Libidn is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU Lesser General Public
   8  * License as published by the Free Software Foundation; either
   9  * version 2.1 of the License, or (at your option) any later version.
  10  *
  11  * GNU Libidn is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14  * Lesser General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU Lesser General Public
  17  * License along with GNU Libidn; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
  19  *
  20  */
  21
  22 /*
  23  * This file is derived from RFC 3492bis written by Adam M. Costello.
  24  *
  25  * Disclaimer and license: Regarding this entire document or any
  26  * portion of it (including the pseudocode and C code), the author
  27  * makes no guarantees and is not responsible for any damage resulting
  28  * from its use.  The author grants irrevocable permission to anyone
  29  * to use, modify, and distribute it in any way that does not diminish
  30  * the rights of anyone else to use, modify, and distribute it,
  31  * provided that redistributed derivative works do not contain
  32  * misleading author or version information.  Derivative works need
  33  * not be licensed under similar terms.
  34  *
  35  * Copyright (C) The Internet Society (2003).  All Rights Reserved.
  36  *
  37  * This document and translations of it may be copied and furnished to
  38  * others, and derivative works that comment on or otherwise explain it
  39  * or assist in its implementation may be prepared, copied, published
  40  * and distributed, in whole or in part, without restriction of any
  41  * kind, provided that the above copyright notice and this paragraph are
  42  * included on all such copies and derivative works.  However, this
  43  * document itself may not be modified in any way, such as by removing
  44  * the copyright notice or references to the Internet Society or other
  45  * Internet organizations, except as needed for the purpose of
  46  * developing Internet standards in which case the procedures for
  47  * copyrights defined in the Internet Standards process must be
  48  * followed, or as required to translate it into languages other than
  49  * English.
  50  *
  51  * The limited permissions granted above are perpetual and will not be
  52  * revoked by the Internet Society or its successors or assigns.
  53  *
  54  * This document and the information contained herein is provided on an
  55  * "AS IS" basis and THE INTERNET SOCIETY AND THE INTERNET ENGINEERING
  56  * TASK FORCE DISCLAIMS ALL WARRANTIES, EXPRESS OR IMPLIED, INCLUDING
  57  * BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE INFORMATION
  58  * HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED WARRANTIES OF
  59  * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.
  60  */
  61
  62 #ifndef _PUNYCODE_H
  63 #define _PUNYCODE_H
  64
  65 #ifdef __cplusplus
  66 extern "C"
  67 {
  68 #endif
  69
  70 #include <stddef.h>             /* size_t */
  71 #include <idn-int.h>            /* uint32_t */
  72
  73   enum punycode_status
  74   {
  75     punycode_success = 0,
  76     punycode_bad_input = 1,     /* Input is invalid.                       */
  77     punycode_big_output = 2,    /* Output would exceed the space provided. */
  78     punycode_overflow = 3       /* Wider integers needed to process input. */
  79   };
  80
  81   typedef enum
  82   {
  83     PUNYCODE_SUCCESS = punycode_success,
  84     PUNYCODE_BAD_INPUT = punycode_bad_input,
  85     PUNYCODE_BIG_OUTPUT = punycode_big_output,
  86     PUNYCODE_OVERFLOW = punycode_overflow
  87   } Punycode_status;
  88
  89   extern const char *punycode_strerror (Punycode_status rc);
  90
  91 /* punycode_uint needs to be unsigned and needs to be */
  92 /* at least 26 bits wide.                             */
  93
  94   typedef uint32_t punycode_uint;
  95
  96   extern int punycode_encode (size_t input_length,
  97                               const punycode_uint input[],
  98                               const unsigned char case_flags[],
  99                               size_t * output_length, char output[]);
 100
 101 /*
 102     punycode_encode() converts a sequence of code points (presumed to be
 103     Unicode code points) to Punycode.
 104
 105     Input arguments (to be supplied by the caller):
 106
 107         input_length
 108             The number of code points in the input array and the number
 109             of flags in the case_flags array.
 110
 111         input
 112             An array of code points.  They are presumed to be Unicode
 113             code points, but that is not strictly REQUIRED.  The
 114             array contains code points, not code units.  UTF-16 uses
 115             code units D800 through DFFF to refer to code points
 116             10000..10FFFF.  The code points D800..DFFF do not occur in
 117             any valid Unicode string.  The code points that can occur in
 118             Unicode strings (0..D7FF and E000..10FFFF) are also called
 119             Unicode scalar values.
 120
 121         case_flags
 122             A null pointer or an array of boolean values parallel to
 123             the input array.  Nonzero (true, flagged) suggests that the
 124             corresponding Unicode character be forced to uppercase after
 125             being decoded (if possible), and zero (false, unflagged)
 126             suggests that it be forced to lowercase (if possible).
 127             ASCII code points (0..7F) are encoded literally, except that
 128             ASCII letters are forced to uppercase or lowercase according
 129             to the corresponding case flags.  If case_flags is a null
 130             pointer then ASCII letters are left as they are, and other
 131             code points are treated as unflagged.
 132
 133     Output arguments (to be filled in by the function):
 134
 135         output
 136             An array of ASCII code points.  It is *not* null-terminated;
 137             it will contain zeros if and only if the input contains
 138             zeros.  (Of course the caller can leave room for a
 139             terminator and add one if needed.)
 140
 141     Input/output arguments (to be supplied by the caller and overwritten
 142     by the function):
 143
 144         output_length
 145             The caller passes in the maximum number of ASCII code points
 146             that it can receive.  On successful return it will contain
 147             the number of ASCII code points actually output.
 148
 149     Return value:
 150
 151         Can be any of the punycode_status values defined above except
 152         punycode_bad_input.  If not punycode_success, then output_size
 153         and output might contain garbage.
 154 */
 155
 156   extern int punycode_decode (size_t input_length,
 157                               const char input[],
 158                               size_t * output_length,
 159                               punycode_uint output[],
 160                               unsigned char case_flags[]);
 161
 162 /*
 163     punycode_decode() converts Punycode to a sequence of code points
 164     (presumed to be Unicode code points).
 165
 166     Input arguments (to be supplied by the caller):
 167
 168         input_length
 169             The number of ASCII code points in the input array.
 170
 171         input
 172             An array of ASCII code points (0..7F).
 173
 174     Output arguments (to be filled in by the function):
 175
 176         output
 177             An array of code points like the input argument of
 178             punycode_encode() (see above).
 179
 180         case_flags
 181             A null pointer (if the flags are not needed by the caller)
 182             or an array of boolean values parallel to the output array.
 183             Nonzero (true, flagged) suggests that the corresponding
 184             Unicode character be forced to uppercase by the caller (if
 185             possible), and zero (false, unflagged) suggests that it
 186             be forced to lowercase (if possible).  ASCII code points
 187             (0..7F) are output already in the proper case, but their
 188             flags will be set appropriately so that applying the flags
 189             would be harmless.
 190
 191     Input/output arguments (to be supplied by the caller and overwritten
 192     by the function):
 193
 194         output_length
 195             The caller passes in the maximum number of code points
 196             that it can receive into the output array (which is also
 197             the maximum number of flags that it can receive into the
 198             case_flags array, if case_flags is not a null pointer).  On
 199             successful return it will contain the number of code points
 200             actually output (which is also the number of flags actually
 201             output, if case_flags is not a null pointer).  The decoder
 202             will never need to output more code points than the number
 203             of ASCII code points in the input, because of the way the
 204             encoding is defined.  The number of code points output
 205             cannot exceed the maximum possible value of a punycode_uint,
 206             even if the supplied output_length is greater than that.
 207
 208     Return value:
 209
 210         Can be any of the punycode_status values defined above.  If not
 211         punycode_success, then output_length, output, and case_flags
 212         might contain garbage.
 213 */
 214
 215 #ifdef __cplusplus
 216 }
 217 #endif
 218 #endif                          /* _PUNYCODE_H */