Back to index

glibc  2.9
punycode.h
Go to the documentation of this file.
00001 /* punycode.h Declarations for punycode functions.
00002  * Copyright (C) 2002, 2003  Simon Josefsson
00003  *
00004  * This file is part of GNU Libidn.
00005  *
00006  * GNU Libidn is free software; you can redistribute it and/or
00007  * modify it under the terms of the GNU Lesser General Public
00008  * License as published by the Free Software Foundation; either
00009  * version 2.1 of the License, or (at your option) any later version.
00010  *
00011  * GNU Libidn is distributed in the hope that it will be useful,
00012  * but WITHOUT ANY WARRANTY; without even the implied warranty of
00013  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
00014  * Lesser General Public License for more details.
00015  *
00016  * You should have received a copy of the GNU Lesser General Public
00017  * License along with GNU Libidn; if not, write to the Free Software
00018  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
00019  *
00020  */
00021 
00022 /*
00023  * This file is derived from RFC 3492bis written by Adam M. Costello.
00024  *
00025  * Disclaimer and license: Regarding this entire document or any
00026  * portion of it (including the pseudocode and C code), the author
00027  * makes no guarantees and is not responsible for any damage resulting
00028  * from its use.  The author grants irrevocable permission to anyone
00029  * to use, modify, and distribute it in any way that does not diminish
00030  * the rights of anyone else to use, modify, and distribute it,
00031  * provided that redistributed derivative works do not contain
00032  * misleading author or version information.  Derivative works need
00033  * not be licensed under similar terms.
00034  *
00035  * Copyright (C) The Internet Society (2003).  All Rights Reserved.
00036  *
00037  * This document and translations of it may be copied and furnished to
00038  * others, and derivative works that comment on or otherwise explain it
00039  * or assist in its implementation may be prepared, copied, published
00040  * and distributed, in whole or in part, without restriction of any
00041  * kind, provided that the above copyright notice and this paragraph are
00042  * included on all such copies and derivative works.  However, this
00043  * document itself may not be modified in any way, such as by removing
00044  * the copyright notice or references to the Internet Society or other
00045  * Internet organizations, except as needed for the purpose of
00046  * developing Internet standards in which case the procedures for
00047  * copyrights defined in the Internet Standards process must be
00048  * followed, or as required to translate it into languages other than
00049  * English.
00050  *
00051  * The limited permissions granted above are perpetual and will not be
00052  * revoked by the Internet Society or its successors or assigns.
00053  *
00054  * This document and the information contained herein is provided on an
00055  * "AS IS" basis and THE INTERNET SOCIETY AND THE INTERNET ENGINEERING
00056  * TASK FORCE DISCLAIMS ALL WARRANTIES, EXPRESS OR IMPLIED, INCLUDING
00057  * BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE INFORMATION
00058  * HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED WARRANTIES OF
00059  * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.
00060  */
00061 
00062 #ifndef _PUNYCODE_H
00063 #define _PUNYCODE_H
00064 
00065 #ifdef __cplusplus
00066 extern "C"
00067 {
00068 #endif
00069 
00070 #include <stddef.h>         /* size_t */
00071 #include <stdint.h>         /* uint32_t */
00072 
00073   enum punycode_status
00074   {
00075     punycode_success = 0,
00076     punycode_bad_input = 1, /* Input is invalid.                       */
00077     punycode_big_output = 2,       /* Output would exceed the space provided. */
00078     punycode_overflow = 3   /* Wider integers needed to process input. */
00079   };
00080 
00081   typedef enum
00082   {
00083     PUNYCODE_SUCCESS = punycode_success,
00084     PUNYCODE_BAD_INPUT = punycode_bad_input,
00085     PUNYCODE_BIG_OUTPUT = punycode_big_output,
00086     PUNYCODE_OVERFLOW = punycode_overflow
00087   } Punycode_status;
00088 
00089 /* punycode_uint needs to be unsigned and needs to be */
00090 /* at least 26 bits wide.                             */
00091 
00092   typedef uint32_t punycode_uint;
00093 
00094   extern int punycode_encode (size_t input_length,
00095                            const punycode_uint input[],
00096                            const unsigned char case_flags[],
00097                            size_t * output_length, char output[]);
00098 
00099 /*
00100     punycode_encode() converts a sequence of code points (presumed to be
00101     Unicode code points) to Punycode.
00102 
00103     Input arguments (to be supplied by the caller):
00104 
00105         input_length
00106             The number of code points in the input array and the number
00107             of flags in the case_flags array.
00108 
00109         input
00110             An array of code points.  They are presumed to be Unicode
00111             code points, but that is not strictly REQUIRED.  The
00112             array contains code points, not code units.  UTF-16 uses
00113             code units D800 through DFFF to refer to code points
00114             10000..10FFFF.  The code points D800..DFFF do not occur in
00115             any valid Unicode string.  The code points that can occur in
00116             Unicode strings (0..D7FF and E000..10FFFF) are also called
00117             Unicode scalar values.
00118 
00119         case_flags
00120             A null pointer or an array of boolean values parallel to
00121             the input array.  Nonzero (true, flagged) suggests that the
00122             corresponding Unicode character be forced to uppercase after
00123             being decoded (if possible), and zero (false, unflagged)
00124             suggests that it be forced to lowercase (if possible).
00125             ASCII code points (0..7F) are encoded literally, except that
00126             ASCII letters are forced to uppercase or lowercase according
00127             to the corresponding case flags.  If case_flags is a null
00128             pointer then ASCII letters are left as they are, and other
00129             code points are treated as unflagged.
00130 
00131     Output arguments (to be filled in by the function):
00132 
00133         output
00134             An array of ASCII code points.  It is *not* null-terminated;
00135             it will contain zeros if and only if the input contains
00136             zeros.  (Of course the caller can leave room for a
00137             terminator and add one if needed.)
00138 
00139     Input/output arguments (to be supplied by the caller and overwritten
00140     by the function):
00141 
00142         output_length
00143             The caller passes in the maximum number of ASCII code points
00144             that it can receive.  On successful return it will contain
00145             the number of ASCII code points actually output.
00146 
00147     Return value:
00148 
00149         Can be any of the punycode_status values defined above except
00150         punycode_bad_input.  If not punycode_success, then output_size
00151         and output might contain garbage.
00152 */
00153 
00154   extern int punycode_decode (size_t input_length,
00155                            const char input[],
00156                            size_t * output_length,
00157                            punycode_uint output[],
00158                            unsigned char case_flags[]);
00159 
00160 /*
00161     punycode_decode() converts Punycode to a sequence of code points
00162     (presumed to be Unicode code points).
00163 
00164     Input arguments (to be supplied by the caller):
00165 
00166         input_length
00167             The number of ASCII code points in the input array.
00168 
00169         input
00170             An array of ASCII code points (0..7F).
00171 
00172     Output arguments (to be filled in by the function):
00173 
00174         output
00175             An array of code points like the input argument of
00176             punycode_encode() (see above).
00177 
00178         case_flags
00179             A null pointer (if the flags are not needed by the caller)
00180             or an array of boolean values parallel to the output array.
00181             Nonzero (true, flagged) suggests that the corresponding
00182             Unicode character be forced to uppercase by the caller (if
00183             possible), and zero (false, unflagged) suggests that it
00184             be forced to lowercase (if possible).  ASCII code points
00185             (0..7F) are output already in the proper case, but their
00186             flags will be set appropriately so that applying the flags
00187             would be harmless.
00188 
00189     Input/output arguments (to be supplied by the caller and overwritten
00190     by the function):
00191 
00192         output_length
00193             The caller passes in the maximum number of code points
00194             that it can receive into the output array (which is also
00195             the maximum number of flags that it can receive into the
00196             case_flags array, if case_flags is not a null pointer).  On
00197             successful return it will contain the number of code points
00198             actually output (which is also the number of flags actually
00199             output, if case_flags is not a null pointer).  The decoder
00200             will never need to output more code points than the number
00201             of ASCII code points in the input, because of the way the
00202             encoding is defined.  The number of code points output
00203             cannot exceed the maximum possible value of a punycode_uint,
00204             even if the supplied output_length is greater than that.
00205 
00206     Return value:
00207 
00208         Can be any of the punycode_status values defined above.  If not
00209         punycode_success, then output_length, output, and case_flags
00210         might contain garbage.
00211 */
00212 
00213 #ifdef __cplusplus
00214 }
00215 #endif
00216 #endif                      /* _PUNYCODE_H */