2 * Copyright notice from original mutt:
3 * Copyright (C) 2000 Edmund Grimley Evans <edmundo@rano.org>
5 * This file is part of mutt-ng, see http://www.muttng.org/.
6 * It's licensed under the GNU General Public License,
7 * please see the file GPL in the top level source directory.
16 #include "imap_private.h"
18 static int Index_64[128] = {
19 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
20 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
21 -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, 63, -1, -1, -1,
22 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1,
23 -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
24 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, -1, -1, -1, -1, -1,
25 -1, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40,
26 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, -1, -1, -1, -1, -1
29 static char B64Chars[64] = {
30 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
31 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd',
32 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's',
33 't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7',
38 * Convert the data (u7,u7len) from RFC 2060's UTF-7 to UTF-8.
39 * The result is null-terminated and returned, and also stored
40 * in (*u8,*u8len) if u8 or u8len is non-zero.
41 * If input data is invalid, return 0 and don't store anything.
42 * RFC 2060 obviously intends the encoding to be unique (see
43 * point 5 in section 5.1.3), so we reject any non-canonical
44 * form, such as &ACY- (instead of &-) or &AMA-&AMA- (instead
47 static char *utf7_to_utf8 (const char *u7, size_t u7len, char **u8,
53 p = buf = safe_malloc (u7len + u7len / 8 + 1);
55 for (; u7len; u7++, u7len--) {
59 if (u7len && *u7 == '-') {
66 for (; u7len; u7++, u7len--) {
67 if ((*u7 & 0x80) || (b = Index_64[(int) *u7]) == -1)
76 if (0x20 <= ch && ch < 0x7f)
77 /* Printable US-ASCII */
81 else if (ch < 0x800) {
82 *p++ = 0xc0 | (ch >> 6);
83 *p++ = 0x80 | (ch & 0x3f);
86 *p++ = 0xe0 | (ch >> 12);
87 *p++ = 0x80 | ((ch >> 6) & 0x3f);
88 *p++ = 0x80 | (ch & 0x3f);
90 ch = (b << (16 + k)) & 0xffff;
95 /* Non-zero or too many extra bits */
97 if (!u7len || *u7 != '-')
98 /* BASE64 not properly terminated */
100 if (u7len > 2 && u7[1] == '&' && u7[2] != '-')
101 /* Adjacent BASE64 sections */
104 else if (*u7 < 0x20 || *u7 >= 0x7f)
105 /* Not printable US-ASCII */
114 safe_realloc (&buf, p - buf);
125 * Convert the data (u8,u8len) from UTF-8 to RFC 2060's UTF-7.
126 * The result is null-terminated and returned, and also stored
127 * in (*u7,*u7len) if u7 or u7len is non-zero.
128 * Unicode characters above U+FFFF are replaced by U+FFFE.
129 * If input data is invalid, return 0 and don't store anything.
131 static char *utf8_to_utf7 (const char *u8, size_t u8len, char **u7,
136 int n, i, b = 0, k = 0;
140 * In the worst case we convert 2 chars to 7 chars. For example:
141 * "\x10&\x10&..." -> "&ABA-&-&ABA-&-...".
143 p = buf = safe_malloc ((u8len / 2) * 7 + 6);
146 unsigned char c = *u8;
153 ch = c & 0x1f, n = 1;
155 ch = c & 0x0f, n = 2;
157 ch = c & 0x07, n = 3;
159 ch = c & 0x03, n = 4;
161 ch = c & 0x01, n = 5;
168 for (i = 0; i < n; i++) {
169 if ((u8[i] & 0xc0) != 0x80)
171 ch = (ch << 6) | (u8[i] & 0x3f);
173 if (n > 1 && !(ch >> (n * 5 + 1)))
177 if (ch < 0x20 || ch >= 0x7f) {
186 *p++ = B64Chars[b | ch >> k];
188 for (; k >= 0; k -= 6)
189 *p++ = B64Chars[(ch >> k) & 0x3f];
190 b = (ch << (-k)) & 0x3f;
220 safe_realloc (&buf, p - buf);
230 void imap_utf7_encode (char **s)
233 char *t = safe_strdup (*s);
235 if (!mutt_convert_string (&t, Charset, "UTF-8", 0))
236 utf8_to_utf7 (t, mutt_strlen (t), s, 0);
241 void imap_utf7_decode (char **s)
244 char *t = utf7_to_utf8 (*s, mutt_strlen (*s), 0, 0);
246 if (t && !mutt_convert_string (&t, "UTF-8", Charset, 0)) {