-
Notifications
You must be signed in to change notification settings - Fork 11
/
utf7.c
337 lines (297 loc) · 9.87 KB
/
utf7.c
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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
/* UTF-7 stream encoder and decoder written in ANSI C
* This is free and unencumbered software released into the public domain.
*
* To avoid any dependence on the character set or locale used by the
* compiler, this source file must not use any character or string
* literals. Everything is hard-coded to ASCII, as required for UTF-7.
*/
#include "utf7.h"
#define UTF7_F_OPEN (1U << 0) /* a shifted encoding is open */
#define UTF7_F_USED (1U << 1) /* something has been encoded */
static int
utf7_isdirect(const struct utf7 *ctx, long c)
{
return c <= 127 && ((ctx->direct[c / 16] >> (c % 16)) & 1U);
}
void
utf7_init(struct utf7 *ctx, const char *indirect)
{
struct utf7 zero = {
0, 0, 0, 0, 0, 0,
{0x2600, 0x0000, 0xF7FF, 0xFFFF, 0xFFFF, 0xEFFF, 0xFFFF, 0x3FFF}
};
*ctx = zero;
if (indirect) {
for (; *indirect; indirect++) {
int c = *indirect;
if (c < 128)
ctx->direct[c / 16] &= ~(1U << (c % 16));
}
}
}
static int
utf7_base64e(int v)
{
static const char set[] = {
0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, 0x50,
0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58,
0x59, 0x5a, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66,
0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e,
0x6f, 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76,
0x77, 0x78, 0x79, 0x7a, 0x30, 0x31, 0x32, 0x33,
0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x2b, 0x2f
};
return set[v];
}
static int
utf7_base64d(int v)
{
static const signed char inv[] = {
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, 0x3e, -1, -1, -1, 0x3f,
0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b,
0x3c, 0x3d, -1, -1, -1, -1, -1, -1,
-1, 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06,
0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e,
0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16,
0x17, 0x18, 0x19, -1, -1, -1, -1, -1,
-1, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20,
0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28,
0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, 0x30,
0x31, 0x32, 0x33, -1, -1, -1, -1, -1
};
return v < 128 ? inv[v] : -1;
}
/* Write out as much as possible without efficiency loss. */
static int
utf7_partial(struct utf7 *ctx)
{
while (ctx->bits >= 6) {
int a = (ctx->accum >> (ctx->bits - 6)) & 0x3fUL;
if (!ctx->len)
return UTF7_FULL;
*ctx->buf++ = utf7_base64e(a);
ctx->len--;
ctx->bits -= 6;
}
return UTF7_OK;
}
/* Force close the current shifted encoding stream. */
static int
utf7_close(struct utf7 *ctx, int next)
{
if (ctx->flags & UTF7_F_OPEN) {
/* An encoding is currently open */
if (!ctx->len)
return UTF7_FULL;
/* Flush remaining bits */
if (ctx->bits) {
int a = (ctx->accum << (6 - ctx->bits)) & 0x3fUL;
*ctx->buf++ = utf7_base64e(a);
ctx->len--;
ctx->bits = 0;
}
/* Close the encoding */
if (next == 0x2d || utf7_base64d(next) != -1) {
if (!ctx->len)
return UTF7_FULL;
*ctx->buf++ = 0x2d; /* '-' */
ctx->len--;
}
ctx->flags &= ~UTF7_F_OPEN;
}
return UTF7_OK;
}
int
utf7_encode(struct utf7 *ctx, long c)
{
/* flush crumbs left from last code point */
if (utf7_partial(ctx) != UTF7_OK)
return UTF7_FULL;
if (c == UTF7_FLUSH)
return utf7_close(ctx, 0x2d);
if (!utf7_isdirect(ctx, c)) {
/* use an indirect encoding */
/* Start encoding if not already */
if (!(ctx->flags & UTF7_F_OPEN)) {
if (!ctx->len)
return UTF7_FULL;
ctx->flags &= ~UTF7_F_USED;
ctx->flags |= UTF7_F_OPEN;
*ctx->buf++ = 0x2b; /* '+' */
ctx->len--;
}
if (c >= 0x10000L) {
/* create a surrogate pair */
unsigned long x = c - 0x10000L;
unsigned long xh = 0xd800UL + (x >> 10);
unsigned long xl = 0xdc00UL + (x & 0x3ffUL);
/* require at least byte to spare */
if (!ctx->len)
return UTF7_FULL;
/* codepoint can now be fully consumed */
ctx->flags |= UTF7_F_USED;
ctx->accum <<= 16;
ctx->accum |= xh;
ctx->bits += 16;
utf7_partial(ctx); /* flush any leftovers */
ctx->accum <<= 16;
ctx->accum |= xl;
ctx->bits += 16;
return UTF7_OK; /* successfully consumed */
} else if (c == 0x2b && !(ctx->flags & UTF7_F_USED)) {
/* '+' special case */
if (!ctx->len)
return UTF7_FULL;
*ctx->buf++ = 0x2d; /* '-' */
ctx->len--;
ctx->flags &= ~UTF7_F_OPEN;
return UTF7_OK; /* successfully consumed */
} else {
/* plain old encoding */
ctx->accum <<= 16;
ctx->accum |= c;
ctx->bits += 16;
ctx->flags |= UTF7_F_USED;
return UTF7_OK; /* successfully consumed */
}
} else {
/* use a direct encoding */
/* close any open encodings first */
if (utf7_close(ctx, c) != UTF7_OK)
return UTF7_FULL;
/* direct character write */
if (!ctx->len)
return UTF7_FULL;
*ctx->buf++ = (char)c;
ctx->len--;
return UTF7_OK;
}
}
static int
utf7_ishigh(long c)
{
return c >= 0xd800L && c <= 0xdbffL;
}
static int
utf7_islow(long c)
{
return c >= 0xdc00L && c <= 0xdfffL;
}
long
utf7_decode(struct utf7 *ctx)
{
while (ctx->len) {
int c = *ctx->buf++;
ctx->len--;
if (c < 0 || c > 127) {
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
}
if (ctx->flags & UTF7_F_OPEN) {
/* currently shift decoding */
int v;
if (!(ctx->flags & UTF7_F_USED) && c == 0x2d) {
/* "+-" encoding for '+' */
ctx->flags &= ~UTF7_F_OPEN;
return 0x2b;
}
/* continue decoding as base64 */
v = utf7_base64d(c);
if (v < 0) {
/* end of encoding */
unsigned long mask;
if (ctx->bits >= 6) {
/* too many bits in accumulation buffer */
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
}
mask = (1UL << ctx->bits) - 1;
if (ctx->accum & mask) {
/* non-zero trailing base64 bits */
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
}
ctx->flags &= ~UTF7_F_OPEN;
/* consume closing '-' if present */
if (c != 0x2d) {
if (ctx->high) {
/* unpaired high surrogate */
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
} else if (ctx->flags & UTF7_F_USED) {
/* valid ending for shift encoding */
return c;
} else {
/* shift encoded ended without being used */
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
}
}
} else {
/* accumulate more base64 bits */
ctx->flags |= UTF7_F_USED;
ctx->accum = (ctx->accum << 6) | v;
ctx->bits += 6;
if (ctx->bits >= 16) {
/* extract a code point */
ctx->bits -= 16;
c = (ctx->accum >> ctx->bits) & 0xffff;
if (ctx->high) {
/* next code point must be low surrogate */
unsigned long h = ctx->high;
if (!utf7_islow(c)) {
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
}
ctx->high = 0;
c = ((h - 0xd800UL) * 0x400UL) +
((c - 0xdc00UL) + 0x10000UL);
} else if (utf7_ishigh(c)) {
/* recurse to look for low surrogate */
ctx->high = c;
return utf7_decode(ctx);
}
else if (utf7_islow(c)) {
/* unpaired low surrogate */
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
}
/* not a surrogate */
return c;
}
}
} else if (c == 0x2b) {
/* begin decoding base64 */
ctx->flags |= UTF7_F_OPEN;
ctx->flags &= ~UTF7_F_USED;
ctx->bits = 0;
} else {
/* direct encoded character */
if (ctx->high) {
/* there was an unpaired high surrogate */
ctx->buf--;
ctx->len++;
return UTF7_INVALID;
}
return c;
}
}
if (ctx->flags & UTF7_F_OPEN)
return UTF7_INCOMPLETE;
if (ctx->high)
return UTF7_INCOMPLETE;
return UTF7_OK;
}