1 /* idna.c Convert to or from IDN strings.
2 * Copyright (C) 2002 Simon Josefsson
4 * This file is part of Libstringprep.
6 * Libstringprep is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
11 * Libstringprep is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with Libstringprep; if not, write to the Free Software
18 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
25 * @in: input array with unicode code points.
26 * @inlen: length of input array with unicode code points.
27 * @out: output zero terminated string that must have room for at
28 * least 63 characters plus the terminating zero.
29 * @allowunassigned: boolean value as per IDNA specification.
30 * @usestd3asciirules: boolean value as per IDNA specification.
32 * The ToASCII operation takes a sequence of Unicode code points that make
33 * up one label and transforms it into a sequence of code points in the
34 * ASCII range (0..7F). If ToASCII succeeds, the original sequence and the
35 * resulting sequence are equivalent labels.
37 * It is important to note that the ToASCII operation can fail. ToASCII
38 * fails if any step of it fails. If any step of the ToASCII operation
39 * fails on any label in a domain name, that domain name MUST NOT be used
40 * as an internationalized domain name. The method for deadling with this
41 * failure is application-specific.
43 * The inputs to ToASCII are a sequence of code points, the AllowUnassigned
44 * flag, and the UseSTD3ASCIIRules flag. The output of ToASCII is either a
45 * sequence of ASCII code points or a failure condition.
47 * ToASCII never alters a sequence of code points that are all in the ASCII
48 * range to begin with (although it could fail). Applying the ToASCII
49 * operation multiple times has exactly the same effect as applying it just
53 idna_to_ascii (const unsigned long *in
, size_t inlen
,
55 int allowunassigned
, int usestd3asciirules
)
61 src
= malloc(sizeof(in
[0]) * inlen
+ 1);
63 return IDNA_MALLOC_ERROR
;
65 memcpy(src
, in
, sizeof(in
[0]) * inlen
);
69 * ToASCII consists of the following steps:
71 * 1. If all code points in the sequence are in the ASCII range (0..7F)
72 * then skip to step 3.
80 for (i
= 0; src
[i
]; i
++)
88 * 2. Perform the steps specified in [NAMEPREP] and fail if there is
89 * an error. The AllowUnassigned flag is used in [NAMEPREP].
95 p
= stringprep_ucs4_to_utf8 (src
, inlen
, NULL
, NULL
);
97 return IDNA_MALLOC_ERROR
;
99 p
= realloc(p
, BUFSIZ
);
101 return IDNA_MALLOC_ERROR
;
104 rc
= stringprep_nameprep(p
, BUFSIZ
);
106 rc
= stringprep_nameprep_no_unassigned(p
, BUFSIZ
);
108 if (rc
!= STRINGPREP_OK
)
109 return IDNA_STRINGPREP_ERROR
;
113 src
= stringprep_utf8_to_ucs4(p
, -1, NULL
);
118 * 3. If the UseSTD3ASCIIRules flag is set, then perform these checks:
120 * (a) Verify the absence of non-LDH ASCII code points; that is,
121 * the absence of 0..2C, 2E..2F, 3A..40, 5B..60, and 7B..7F.
123 * (b) Verify the absence of leading and trailing hyphen-minus;
124 * that is, the absence of U+002D at the beginning and end of
128 if (usestd3asciirules
)
132 for (i
= 0; src
[i
]; i
++)
133 if (src
[i
] <= 0x2C || src
[i
] == 0x2E || src
[i
] == 0x2F ||
134 (src
[i
] >= 0x3A && src
[i
] <= 0x40) ||
135 (src
[i
] >= 0x5B && src
[i
] <= 0x60) ||
136 (src
[i
] >= 0x7B && src
[i
] <= 0x7F))
137 return IDNA_CONTAINS_LDH
;
139 if (src
[0] == 0x002D || (i
> 0 && src
[i
-1] == 0x002D))
140 return IDNA_CONTAINS_MINUS
;
144 * 4. If all code points in the sequence are in the ASCII range
145 * (0..7F), then skip to step 8.
153 for (i
= 0; src
[i
]; i
++)
161 * 5. Verify that the sequence does NOT begin with the ACE prefix.
170 * 6. Encode the sequence using the encoding algorithm in [PUNYCODE]
171 * and fail if there is an error.
173 for (len
= 0; src
[len
]; len
++)
176 outlen
= 63 - strlen(IDNA_ACE_PREFIX
);
177 rc
= punycode_encode (len
, src
, NULL
,
178 &outlen
, &out
[strlen(IDNA_ACE_PREFIX
)]);
179 if (rc
!= PUNYCODE_SUCCESS
)
180 return IDNA_PUNYCODE_ERROR
;
182 return IDNA_PUNYCODE_ERROR
;
183 out
[strlen(IDNA_ACE_PREFIX
) + outlen
] = '\0';
186 * 7. Prepend the ACE prefix.
189 memcpy(out
, IDNA_ACE_PREFIX
, strlen(IDNA_ACE_PREFIX
));
192 * 8. Verify that the number of code points is in the range 1 to 63
197 if (strlen(out
) < 1 || strlen(out
) > 63)
198 return IDNA_INVALID_LENGTH
;
204 * @in: input array with unicode code points.
205 * @inlen: length of input array with unicode code points.
206 * @out: output array with unicode code points.
207 * @outlen: on input, maximum size of output array with unicode code points,
208 * on exit, actual size of output array with unicode code points.
209 * @allowunassigned: boolean value as per IDNA specification.
210 * @usestd3asciirules: boolean value as per IDNA specification.
212 * The ToUnicode operation takes a sequence of Unicode code points
213 * that make up one label and returns a sequence of Unicode code
214 * points. If the input sequence is a label in ACE form, then the
215 * result is an equivalent internationalized label that is not in ACE
216 * form, otherwise the original sequence is returned unaltered.
218 * ToUnicode never fails. If any step fails, then the original input
219 * sequence is returned immediately in that step.
221 * The ToUnicode output never contains more code points than its
222 * input. Note that the number of octets needed to represent a
223 * sequence of code points depends on the particular character
226 * The inputs to ToUnicode are a sequence of code points, the
227 * AllowUnassigned flag, and the UseSTD3ASCIIRules flag. The output of
228 * ToUnicode is always a sequence of Unicode code points.
231 idna_to_unicode (const unsigned long *in
, size_t inlen
,
232 unsigned long *out
, size_t *outlen
,
233 int allowunassigned
, int usestd3asciirules
)
240 * 1. If all code points in the sequence are in the ASCII range (0..7F)
241 * then skip to step 3.
249 for (i
= 0; in
[i
]; i
++)
257 * 2. Perform the steps specified in [NAMEPREP] and fail if there is an
258 * error. (If step 3 of ToASCII is also performed here, it will not
259 * affect the overall behavior of ToUnicode, but it is not
260 * necessary.) The AllowUnassigned flag is used in [NAMEPREP].
263 p
= stringprep_ucs4_to_utf8 (in
, inlen
, NULL
, NULL
);
265 return IDNA_MALLOC_ERROR
;
267 p
= realloc(p
, BUFSIZ
);
269 return IDNA_MALLOC_ERROR
;
272 rc
= stringprep_nameprep(p
, BUFSIZ
);
274 rc
= stringprep_nameprep_no_unassigned(p
, BUFSIZ
);
276 if (rc
!= STRINGPREP_OK
)
277 return IDNA_STRINGPREP_ERROR
;
281 src
= stringprep_utf8_to_ucs4(p
, -1, NULL
);
283 /* 3. Verify that the sequence begins with the ACE prefix, and save a
284 * copy of the sequence.
288 if (memcmp(IDNA_ACE_PREFIX
, p
, strlen(IDNA_ACE_PREFIX
)) != 0)
289 return IDNA_NO_ACE_PREFIX
;
291 /* 4. Remove the ACE prefix.
294 memmove(p
, &p
[strlen(IDNA_ACE_PREFIX
)], strlen(p
)-strlen(IDNA_ACE_PREFIX
));
296 /* 5. Decode the sequence using the decoding algorithm in [PUNYCODE]
297 * and fail if there is an error. Save a copy of the result of
306 /* 7. Verify that the result of step 6 matches the saved copy from
307 * step 3, using a case-insensitive ASCII comparison.
310 /* 8. Return the saved copy from step 5.