1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/netwerk/dns/punycode.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,108 @@
1.4 +/*
1.5 +punycode.c from RFC 3492
1.6 +http://www.nicemice.net/idn/
1.7 +Adam M. Costello
1.8 +http://www.nicemice.net/amc/
1.9 +
1.10 +This is ANSI C code (C89) implementing Punycode (RFC 3492).
1.11 +
1.12 +
1.13 +
1.14 +C. Disclaimer and license
1.15 +
1.16 + Regarding this entire document or any portion of it (including
1.17 + the pseudocode and C code), the author makes no guarantees and
1.18 + is not responsible for any damage resulting from its use. The
1.19 + author grants irrevocable permission to anyone to use, modify,
1.20 + and distribute it in any way that does not diminish the rights
1.21 + of anyone else to use, modify, and distribute it, provided that
1.22 + redistributed derivative works do not contain misleading author or
1.23 + version information. Derivative works need not be licensed under
1.24 + similar terms.
1.25 +*/
1.26 +
1.27 +#ifdef __cplusplus
1.28 +extern "C" {
1.29 +#endif /* __cplusplus */
1.30 +
1.31 +/************************************************************/
1.32 +/* Public interface (would normally go in its own .h file): */
1.33 +
1.34 +#include <limits.h>
1.35 +
1.36 +enum punycode_status {
1.37 + punycode_success,
1.38 + punycode_bad_input, /* Input is invalid. */
1.39 + punycode_big_output, /* Output would exceed the space provided. */
1.40 + punycode_overflow /* Input needs wider integers to process. */
1.41 +};
1.42 +
1.43 +#if UINT_MAX >= (1 << 26) - 1
1.44 +typedef unsigned int punycode_uint;
1.45 +#else
1.46 +typedef unsigned long punycode_uint;
1.47 +#endif
1.48 +
1.49 +enum punycode_status punycode_encode(
1.50 + punycode_uint input_length,
1.51 + const punycode_uint input[],
1.52 + const unsigned char case_flags[],
1.53 + punycode_uint *output_length,
1.54 + char output[] );
1.55 +
1.56 + /* punycode_encode() converts Unicode to Punycode. The input */
1.57 + /* is represented as an array of Unicode code points (not code */
1.58 + /* units; surrogate pairs are not allowed), and the output */
1.59 + /* will be represented as an array of ASCII code points. The */
1.60 + /* output string is *not* null-terminated; it will contain */
1.61 + /* zeros if and only if the input contains zeros. (Of course */
1.62 + /* the caller can leave room for a terminator and add one if */
1.63 + /* needed.) The input_length is the number of code points in */
1.64 + /* the input. The output_length is an in/out argument: the */
1.65 + /* caller passes in the maximum number of code points that it */
1.66 + /* can receive, and on successful return it will contain the */
1.67 + /* number of code points actually output. The case_flags array */
1.68 + /* holds input_length boolean values, where nonzero suggests that */
1.69 + /* the corresponding Unicode character be forced to uppercase */
1.70 + /* after being decoded (if possible), and zero suggests that */
1.71 + /* it be forced to lowercase (if possible). ASCII code points */
1.72 + /* are encoded literally, except that ASCII letters are forced */
1.73 + /* to uppercase or lowercase according to the corresponding */
1.74 + /* uppercase flags. If case_flags is a null pointer then ASCII */
1.75 + /* letters are left as they are, and other code points are */
1.76 + /* treated as if their uppercase flags were zero. The return */
1.77 + /* value can be any of the punycode_status values defined above */
1.78 + /* except punycode_bad_input; if not punycode_success, then */
1.79 + /* output_size and output might contain garbage. */
1.80 +
1.81 +enum punycode_status punycode_decode(
1.82 + punycode_uint input_length,
1.83 + const char input[],
1.84 + punycode_uint *output_length,
1.85 + punycode_uint output[],
1.86 + unsigned char case_flags[] );
1.87 +
1.88 + /* punycode_decode() converts Punycode to Unicode. The input is */
1.89 + /* represented as an array of ASCII code points, and the output */
1.90 + /* will be represented as an array of Unicode code points. The */
1.91 + /* input_length is the number of code points in the input. The */
1.92 + /* output_length is an in/out argument: the caller passes in */
1.93 + /* the maximum number of code points that it can receive, and */
1.94 + /* on successful return it will contain the actual number of */
1.95 + /* code points output. The case_flags array needs room for at */
1.96 + /* least output_length values, or it can be a null pointer if the */
1.97 + /* case information is not needed. A nonzero flag suggests that */
1.98 + /* the corresponding Unicode character be forced to uppercase */
1.99 + /* by the caller (if possible), while zero suggests that it be */
1.100 + /* forced to lowercase (if possible). ASCII code points are */
1.101 + /* output already in the proper case, but their flags will be set */
1.102 + /* appropriately so that applying the flags would be harmless. */
1.103 + /* The return value can be any of the punycode_status values */
1.104 + /* defined above; if not punycode_success, then output_length, */
1.105 + /* output, and case_flags might contain garbage. On success, the */
1.106 + /* decoder will never need to write an output_length greater than */
1.107 + /* input_length, because of how the encoding is defined. */
1.108 +
1.109 +#ifdef __cplusplus
1.110 +}
1.111 +#endif /* __cplusplus */
