projects / apple / icu.git / blame
| Commit | Line | Data |
|---|---|---|
| b75a7d8f A |
1 | /* |
| 2 | ****************************************************************************** | |
| 3 | * | |
| 4 | * Copyright (C) 2003, International Business Machines | |
| 5 | * Corporation and others. All Rights Reserved. | |
| 6 | * | |
| 7 | ****************************************************************************** | |
| 8 | */ | |
| 9 | /* | |
| 10 | punycode.c from draft-ietf-idn-punycode-03 | |
| 11 | http://www.nicemice.net/idn/ | |
| 12 | Adam M. Costello | |
| 13 | http://www.nicemice.net/amc/ | |
| 14 | ||
| 15 | This is ANSI C code (C89) implementing | |
| 16 | Punycode (draft-ietf-idn-punycode-03). | |
| 17 | ||
| 18 | Disclaimer and license | |
| 19 | ||
| 20 | Regarding this entire document or any portion of it (including | |
| 21 | the pseudocode and C code), the author makes no guarantees and | |
| 22 | is not responsible for any damage resulting from its use. The | |
| 23 | author grants irrevocable permission to anyone to use, modify, | |
| 24 | and distribute it in any way that does not diminish the rights | |
| 25 | of anyone else to use, modify, and distribute it, provided that | |
| 26 | redistributed derivative works do not contain misleading author or | |
| 27 | version information. Derivative works need not be licensed under | |
| 28 | similar terms. | |
| 29 | ||
| 30 | */ | |
| 31 | #ifndef _PUNYREF_H | |
| 32 | #define _PUNYREF_H | |
| 33 | ||
| 34 | /************************************************************/ | |
| 35 | /* Public interface (would normally go in its own .h file): */ | |
| 36 | ||
| b75a7d8f A |
37 | #include "unicode/utypes.h" |
| 38 | ||
| 39 | #if !UCONFIG_NO_IDNA | |
| 40 | ||
| 41 | enum punycode_status { | |
| 42 | punycode_success, | |
| 43 | punycode_bad_input, /* Input is invalid. */ | |
| 44 | punycode_big_output, /* Output would exceed the space provided. */ | |
| 45 | punycode_overflow /* Input needs wider integers to process. */ | |
| 46 | }; | |
| 47 | ||
| 48 | ||
| 49 | typedef uint32_t punycode_uint; | |
| 50 | ||
| 51 | U_CDECL_BEGIN | |
| 52 | ||
| 53 | enum punycode_status punycode_encode( | |
| 54 | punycode_uint input_length, | |
| 55 | const punycode_uint input[], | |
| 56 | const unsigned char case_flags[], | |
| 57 | punycode_uint *output_length, | |
| 58 | char output[] ); | |
| 59 | ||
| 60 | /* punycode_encode() converts Unicode to Punycode. The input */ | |
| 61 | /* is represented as an array of Unicode code points (not code */ | |
| 62 | /* units; surrogate pairs are not allowed), and the output */ | |
| 63 | /* will be represented as an array of ASCII code points. The */ | |
| 64 | /* output string is *not* null-terminated; it will contain */ | |
| 65 | /* zeros if and only if the input contains zeros. (Of course */ | |
| 66 | /* the caller can leave room for a terminator and add one if */ | |
| 67 | /* needed.) The input_length is the number of code points in */ | |
| 68 | /* the input. The output_length is an in/out argument: the */ | |
| 69 | /* caller passes in the maximum number of code points that it */ | |
| 70 | /* can receive, and on successful return it will contain the */ | |
| 71 | /* number of code points actually output. The case_flags array */ | |
| 72 | /* holds input_length boolean values, where nonzero suggests that */ | |
| 73 | /* the corresponding Unicode character be forced to uppercase */ | |
| 74 | /* after being decoded (if possible), and zero suggests that */ | |
| 75 | /* it be forced to lowercase (if possible). ASCII code points */ | |
| 76 | /* are encoded literally, except that ASCII letters are forced */ | |
| 77 | /* to uppercase or lowercase according to the corresponding */ | |
| 78 | /* uppercase flags. If case_flags is a null pointer then ASCII */ | |
| 79 | /* letters are left as they are, and other code points are */ | |
| 80 | /* treated as if their uppercase flags were zero. The return */ | |
| 81 | /* value can be any of the punycode_status values defined above */ | |
| 82 | /* except punycode_bad_input; if not punycode_success, then */ | |
| 83 | /* output_size and output might contain garbage. */ | |
| 84 | ||
| 85 | enum punycode_status punycode_decode( | |
| 86 | punycode_uint input_length, | |
| 87 | const char input[], | |
| 88 | punycode_uint *output_length, | |
| 89 | punycode_uint output[], | |
| 90 | unsigned char case_flags[] ); | |
| 91 | ||
| 92 | /* punycode_decode() converts Punycode to Unicode. The input is */ | |
| 93 | /* represented as an array of ASCII code points, and the output */ | |
| 94 | /* will be represented as an array of Unicode code points. The */ | |
| 95 | /* input_length is the number of code points in the input. The */ | |
| 96 | /* output_length is an in/out argument: the caller passes in */ | |
| 97 | /* the maximum number of code points that it can receive, and */ | |
| 98 | /* on successful return it will contain the actual number of */ | |
| 99 | /* code points output. The case_flags array needs room for at */ | |
| 100 | /* least output_length values, or it can be a null pointer if the */ | |
| 101 | /* case information is not needed. A nonzero flag suggests that */ | |
| 102 | /* the corresponding Unicode character be forced to uppercase */ | |
| 103 | /* by the caller (if possible), while zero suggests that it be */ | |
| 104 | /* forced to lowercase (if possible). ASCII code points are */ | |
| 105 | /* output already in the proper case, but their flags will be set */ | |
| 106 | /* appropriately so that applying the flags would be harmless. */ | |
| 107 | /* The return value can be any of the punycode_status values */ | |
| 108 | /* defined above; if not punycode_success, then output_length, */ | |
| 109 | /* output, and case_flags might contain garbage. On success, the */ | |
| 110 | /* decoder will never need to write an output_length greater than */ | |
| 111 | /* input_length, because of how the encoding is defined. */ | |
| 112 | U_CDECL_END | |
| 113 | ||
| 114 | #endif /* #if !UCONFIG_NO_IDNA */ | |
| 115 | ||
| 116 | #endif |