| 1 |
/* LibTomCrypt, modular cryptographic library -- Tom St Denis */ |
| 2 |
/* SPDX-License-Identifier: Unlicense */ |
| 3 |
#include "tomcrypt_private.h" |
| 4 |
|
| 5 |
/** |
| 6 |
@file der_decode_utf8_string.c |
| 7 |
ASN.1 DER, encode a UTF8 STRING, Tom St Denis |
| 8 |
*/ |
| 9 |
|
| 10 |
|
| 11 |
#ifdef LTC_DER |
| 12 |
|
| 13 |
/** |
| 14 |
Decode a UTF8 STRING and recover an array of unicode characters. |
| 15 |
@param in The DER encoded UTF8 STRING |
| 16 |
@param inlen The size of the DER UTF8 STRING |
| 17 |
@param out [out] The array of unicode characters (wchar_t*) |
| 18 |
@param outlen [in/out] The number of unicode characters in the array |
| 19 |
@return CRYPT_OK if successful |
| 20 |
*/ |
| 21 |
int der_decode_utf8_string(const unsigned char *in, unsigned long inlen, |
| 22 |
wchar_t *out, unsigned long *outlen) |
| 23 |
{ |
| 24 |
wchar_t tmp; |
| 25 |
unsigned long x, y, z, len; |
| 26 |
int err; |
| 27 |
|
| 28 |
LTC_ARGCHK(in != NULL); |
| 29 |
LTC_ARGCHK(out != NULL); |
| 30 |
LTC_ARGCHK(outlen != NULL); |
| 31 |
|
| 32 |
/* must have header at least */ |
| 33 |
if (inlen < 2) { |
| 34 |
return CRYPT_INVALID_PACKET; |
| 35 |
} |
| 36 |
|
| 37 |
/* check for 0x0C */ |
| 38 |
if ((in[0] & 0x1F) != 0x0C) { |
| 39 |
return CRYPT_INVALID_PACKET; |
| 40 |
} |
| 41 |
x = 1; |
| 42 |
|
| 43 |
/* get the length of the data */ |
| 44 |
y = inlen - x; |
| 45 |
if ((err = der_decode_asn1_length(in + x, &y, &len)) != CRYPT_OK) { |
| 46 |
return err; |
| 47 |
} |
| 48 |
x += y; |
| 49 |
|
| 50 |
if (len > (inlen - x)) { |
| 51 |
return CRYPT_INVALID_PACKET; |
| 52 |
} |
| 53 |
|
| 54 |
/* proceed to recover unicode characters from utf8 data. |
| 55 |
for reference see Section 3 of RFC 3629: |
| 56 |
|
| 57 |
https://tools.ietf.org/html/rfc3629#section-3 |
| 58 |
*/ |
| 59 |
len += x; |
| 60 |
for (y = 0; x < len; ) { |
| 61 |
/* read first byte */ |
| 62 |
tmp = in[x++]; |
| 63 |
|
| 64 |
/* a unicode character is recovered from a sequence of 1 to 4 utf8 bytes. |
| 65 |
the form of those bytes must match a row in the following table: |
| 66 |
|
| 67 |
0xxxxxxx |
| 68 |
110xxxxx 10xxxxxx |
| 69 |
1110xxxx 10xxxxxx 10xxxxxx |
| 70 |
11110xxx 10xxxxxx 10xxxxxx 10xxxxxx |
| 71 |
|
| 72 |
the number of leading ones in the first byte (0,2,3,4) determines the |
| 73 |
number of remaining bytes to read (0,1,2,3) |
| 74 |
*/ |
| 75 |
|
| 76 |
/* determine z, the number of leading ones. |
| 77 |
this is done by left-shifting tmp, which clears the ms-bits */ |
| 78 |
for (z = 0; (tmp & 0x80) && (z <= 4); z++, tmp = (tmp << 1) & 0xFF); |
| 79 |
|
| 80 |
/* z should be in {0,2,3,4} */ |
| 81 |
if (z == 1 || z > 4) { |
| 82 |
return CRYPT_INVALID_PACKET; |
| 83 |
} |
| 84 |
|
| 85 |
/* right-shift tmp to restore least-sig bits */ |
| 86 |
tmp >>= z; |
| 87 |
|
| 88 |
/* now update z so it equals the number of additional bytes to read */ |
| 89 |
if (z > 0) { --z; } |
| 90 |
|
| 91 |
if (x + z > len) { |
| 92 |
return CRYPT_INVALID_PACKET; |
| 93 |
} |
| 94 |
|
| 95 |
/* read remaining bytes */ |
| 96 |
while (z-- != 0) { |
| 97 |
if ((in[x] & 0xC0) != 0x80) { |
| 98 |
return CRYPT_INVALID_PACKET; |
| 99 |
} |
| 100 |
tmp = (tmp << 6) | ((wchar_t)in[x++] & 0x3F); |
| 101 |
} |
| 102 |
|
| 103 |
if (y < *outlen) { |
| 104 |
out[y] = tmp; |
| 105 |
} |
| 106 |
y++; |
| 107 |
} |
| 108 |
if (y > *outlen) { |
| 109 |
err = CRYPT_BUFFER_OVERFLOW; |
| 110 |
} else { |
| 111 |
err = CRYPT_OK; |
| 112 |
} |
| 113 |
*outlen = y; |
| 114 |
|
| 115 |
return err; |
| 116 |
} |
| 117 |
|
| 118 |
#endif |