1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
|
/*
punycode.h from RFC 3492
http://www.nicemice.net/idn/
Adam M. Costello
http://www.nicemice.net/amc/
This is ANSI C code (C89) implementing Punycode (RFC 3492).
*/
#include <limits.h>
enum punycode_status {
punycode_success,
punycode_bad_input, /* Input is invalid. */
punycode_big_output, /* Output would exceed the space provided. */
punycode_overflow /* Input needs wider integers to process. */
};
#if UINT_MAX >= (1 << 26) - 1
typedef unsigned int punycode_uint;
#else
typedef unsigned long punycode_uint;
#endif
enum punycode_status punycode_encode(
punycode_uint input_length,
const punycode_uint input[],
const unsigned char case_flags[],
punycode_uint *output_length,
char output[] );
/* punycode_encode() converts Unicode to Punycode. The input */
/* is represented as an array of Unicode code points (not code */
/* units; surrogate pairs are not allowed), and the output */
/* will be represented as an array of ASCII code points. The */
/* output string is *not* null-terminated; it will contain */
/* zeros if and only if the input contains zeros. (Of course */
/* the caller can leave room for a terminator and add one if */
/* needed.) The input_length is the number of code points in */
/* the input. The output_length is an in/out argument: the */
/* caller passes in the maximum number of code points that it */
/* can receive, and on successful return it will contain the */
/* number of code points actually output. The case_flags array */
/* holds input_length boolean values, where nonzero suggests that */
/* the corresponding Unicode character be forced to uppercase */
/* after being decoded (if possible), and zero suggests that */
/* it be forced to lowercase (if possible). ASCII code points */
/* are encoded literally, except that ASCII letters are forced */
/* to uppercase or lowercase according to the corresponding */
/* uppercase flags. If case_flags is a null pointer then ASCII */
/* letters are left as they are, and other code points are */
/* treated as if their uppercase flags were zero. The return */
/* value can be any of the punycode_status values defined above */
/* except punycode_bad_input; if not punycode_success, then */
/* output_size and output might contain garbage. */
enum punycode_status punycode_decode(
punycode_uint input_length,
const char input[],
punycode_uint *output_length,
punycode_uint output[],
unsigned char case_flags[] );
/* punycode_decode() converts Punycode to Unicode. The input is */
/* represented as an array of ASCII code points, and the output */
/* will be represented as an array of Unicode code points. The */
/* input_length is the number of code points in the input. The */
/* output_length is an in/out argument: the caller passes in */
/* the maximum number of code points that it can receive, and */
/* on successful return it will contain the actual number of */
/* code points output. The case_flags array needs room for at */
/* least output_length values, or it can be a null pointer if the */
/* case information is not needed. A nonzero flag suggests that */
/* the corresponding Unicode character be forced to uppercase */
/* by the caller (if possible), while zero suggests that it be */
/* forced to lowercase (if possible). ASCII code points are */
/* output already in the proper case, but their flags will be set */
/* appropriately so that applying the flags would be harmless. */
/* The return value can be any of the punycode_status values */
/* defined above; if not punycode_success, then output_length, */
/* output, and case_flags might contain garbage. On success, the */
/* decoder will never need to write an output_length greater than */
/* input_length, because of how the encoding is defined. */
|
