The Tor Browser / file comparison
comparison: netwerk/dns/punycode.h
netwerk/dns/punycode.h
- changeset 1
- ca08bd8f51b2
equal
deleted
inserted
replaced
| -1:000000000000 | 0:0383f3df8391 |
|---|---|
| 1 /* | |
| 2 punycode.c from RFC 3492 | |
| 3 http://www.nicemice.net/idn/ | |
| 4 Adam M. Costello | |
| 5 http://www.nicemice.net/amc/ | |
| 6 | |
| 7 This is ANSI C code (C89) implementing Punycode (RFC 3492). | |
| 8 | |
| 9 | |
| 10 | |
| 11 C. Disclaimer and license | |
| 12 | |
| 13 Regarding this entire document or any portion of it (including | |
| 14 the pseudocode and C code), the author makes no guarantees and | |
| 15 is not responsible for any damage resulting from its use. The | |
| 16 author grants irrevocable permission to anyone to use, modify, | |
| 17 and distribute it in any way that does not diminish the rights | |
| 18 of anyone else to use, modify, and distribute it, provided that | |
| 19 redistributed derivative works do not contain misleading author or | |
| 20 version information. Derivative works need not be licensed under | |
| 21 similar terms. | |
| 22 */ | |
| 23 | |
| 24 #ifdef __cplusplus | |
| 25 extern "C" { | |
| 26 #endif /* __cplusplus */ | |
| 27 | |
| 28 /************************************************************/ | |
| 29 /* Public interface (would normally go in its own .h file): */ | |
| 30 | |
| 31 #include <limits.h> | |
| 32 | |
| 33 enum punycode_status { | |
| 34 punycode_success, | |
| 35 punycode_bad_input, /* Input is invalid. */ | |
| 36 punycode_big_output, /* Output would exceed the space provided. */ | |
| 37 punycode_overflow /* Input needs wider integers to process. */ | |
| 38 }; | |
| 39 | |
| 40 #if UINT_MAX >= (1 << 26) - 1 | |
| 41 typedef unsigned int punycode_uint; | |
| 42 #else | |
| 43 typedef unsigned long punycode_uint; | |
| 44 #endif | |
| 45 | |
| 46 enum punycode_status punycode_encode( | |
| 47 punycode_uint input_length, | |
| 48 const punycode_uint input[], | |
| 49 const unsigned char case_flags[], | |
| 50 punycode_uint *output_length, | |
| 51 char output[] ); | |
| 52 | |
| 53 /* punycode_encode() converts Unicode to Punycode. The input */ | |
| 54 /* is represented as an array of Unicode code points (not code */ | |
| 55 /* units; surrogate pairs are not allowed), and the output */ | |
| 56 /* will be represented as an array of ASCII code points. The */ | |
| 57 /* output string is *not* null-terminated; it will contain */ | |
| 58 /* zeros if and only if the input contains zeros. (Of course */ | |
| 59 /* the caller can leave room for a terminator and add one if */ | |
| 60 /* needed.) The input_length is the number of code points in */ | |
| 61 /* the input. The output_length is an in/out argument: the */ | |
| 62 /* caller passes in the maximum number of code points that it */ | |
| 63 /* can receive, and on successful return it will contain the */ | |
| 64 /* number of code points actually output. The case_flags array */ | |
| 65 /* holds input_length boolean values, where nonzero suggests that */ | |
| 66 /* the corresponding Unicode character be forced to uppercase */ | |
| 67 /* after being decoded (if possible), and zero suggests that */ | |
| 68 /* it be forced to lowercase (if possible). ASCII code points */ | |
| 69 /* are encoded literally, except that ASCII letters are forced */ | |
| 70 /* to uppercase or lowercase according to the corresponding */ | |
| 71 /* uppercase flags. If case_flags is a null pointer then ASCII */ | |
| 72 /* letters are left as they are, and other code points are */ | |
| 73 /* treated as if their uppercase flags were zero. The return */ | |
| 74 /* value can be any of the punycode_status values defined above */ | |
| 75 /* except punycode_bad_input; if not punycode_success, then */ | |
| 76 /* output_size and output might contain garbage. */ | |
| 77 | |
| 78 enum punycode_status punycode_decode( | |
| 79 punycode_uint input_length, | |
| 80 const char input[], | |
| 81 punycode_uint *output_length, | |
| 82 punycode_uint output[], | |
| 83 unsigned char case_flags[] ); | |
| 84 | |
| 85 /* punycode_decode() converts Punycode to Unicode. The input is */ | |
| 86 /* represented as an array of ASCII code points, and the output */ | |
| 87 /* will be represented as an array of Unicode code points. The */ | |
| 88 /* input_length is the number of code points in the input. The */ | |
| 89 /* output_length is an in/out argument: the caller passes in */ | |
| 90 /* the maximum number of code points that it can receive, and */ | |
| 91 /* on successful return it will contain the actual number of */ | |
| 92 /* code points output. The case_flags array needs room for at */ | |
| 93 /* least output_length values, or it can be a null pointer if the */ | |
| 94 /* case information is not needed. A nonzero flag suggests that */ | |
| 95 /* the corresponding Unicode character be forced to uppercase */ | |
| 96 /* by the caller (if possible), while zero suggests that it be */ | |
| 97 /* forced to lowercase (if possible). ASCII code points are */ | |
| 98 /* output already in the proper case, but their flags will be set */ | |
| 99 /* appropriately so that applying the flags would be harmless. */ | |
| 100 /* The return value can be any of the punycode_status values */ | |
| 101 /* defined above; if not punycode_success, then output_length, */ | |
| 102 /* output, and case_flags might contain garbage. On success, the */ | |
| 103 /* decoder will never need to write an output_length greater than */ | |
| 104 /* input_length, because of how the encoding is defined. */ | |
| 105 | |
| 106 #ifdef __cplusplus | |
| 107 } | |
| 108 #endif /* __cplusplus */ |
