File: message-decoder.c

package info (click to toggle)
dovecot 1:2.2.13-12~deb8u4
  • links: PTS, VCS
  • area: main
  • in suites: jessie
  • size: 38,792 kB
  • sloc: ansic: 341,472; sh: 16,920; makefile: 5,393; cpp: 1,474; perl: 265; xml: 44; python: 34; pascal: 27
file content (417 lines) | stat: -rw-r--r-- 11,387 bytes parent folder | download
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
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
/* Copyright (c) 2006-2014 Dovecot authors, see the included COPYING file */

#include "lib.h"
#include "buffer.h"
#include "base64.h"
#include "str.h"
#include "unichar.h"
#include "charset-utf8.h"
#include "quoted-printable.h"
#include "rfc822-parser.h"
#include "rfc2231-parser.h"
#include "message-parser.h"
#include "message-header-decode.h"
#include "message-decoder.h"

/* base64 takes max 4 bytes per character, q-p takes max 3. */
#define MAX_ENCODING_BUF_SIZE 3

/* UTF-8 takes max 5 bytes per character. Not sure about others, but I'd think
   10 is more than enough for everyone.. */
#define MAX_TRANSLATION_BUF_SIZE 10

struct message_decoder_context {
	enum message_decoder_flags flags;
	normalizer_func_t *normalizer;
	struct message_part *prev_part;

	struct message_header_line hdr;
	buffer_t *buf, *buf2;

	char *charset_trans_charset;
	struct charset_translation *charset_trans;
	char translation_buf[MAX_TRANSLATION_BUF_SIZE];
	unsigned int translation_size;

	buffer_t *encoding_buf;

	char *content_charset;
	enum message_cte message_cte;

	unsigned int charset_utf8:1;
	unsigned int binary_input:1;
};

static void
message_decode_body_init_charset(struct message_decoder_context *ctx,
				 struct message_part *part);

struct message_decoder_context *
message_decoder_init(normalizer_func_t *normalizer,
		     enum message_decoder_flags flags)
{
	struct message_decoder_context *ctx;

	ctx = i_new(struct message_decoder_context, 1);
	ctx->flags = flags;
	ctx->normalizer = normalizer;
	ctx->buf = buffer_create_dynamic(default_pool, 8192);
	ctx->buf2 = buffer_create_dynamic(default_pool, 8192);
	ctx->encoding_buf = buffer_create_dynamic(default_pool, 128);
	return ctx;
}

void message_decoder_deinit(struct message_decoder_context **_ctx)
{
	struct message_decoder_context *ctx = *_ctx;

	*_ctx = NULL;

	if (ctx->charset_trans != NULL)
		charset_to_utf8_end(&ctx->charset_trans);

	buffer_free(&ctx->encoding_buf);
	buffer_free(&ctx->buf);
	buffer_free(&ctx->buf2);
	i_free(ctx->charset_trans_charset);
	i_free(ctx->content_charset);
	i_free(ctx);
}

void message_decoder_set_return_binary(struct message_decoder_context *ctx,
				       bool set)
{
	if (set)
		ctx->flags |= MESSAGE_DECODER_FLAG_RETURN_BINARY;
	else
		ctx->flags &= ~MESSAGE_DECODER_FLAG_RETURN_BINARY;
	message_decode_body_init_charset(ctx, ctx->prev_part);
}

enum message_cte message_decoder_parse_cte(struct message_header_line *hdr)
{
	struct rfc822_parser_context parser;
	enum message_cte message_cte;
	string_t *value;

	value = t_str_new(64);
	rfc822_parser_init(&parser, hdr->full_value, hdr->full_value_len, NULL);

	rfc822_skip_lwsp(&parser);
	(void)rfc822_parse_mime_token(&parser, value);

	message_cte = MESSAGE_CTE_UNKNOWN;
	switch (str_len(value)) {
	case 4:
		if (i_memcasecmp(str_data(value), "7bit", 4) == 0 ||
		    i_memcasecmp(str_data(value), "8bit", 4) == 0)
			message_cte = MESSAGE_CTE_78BIT;
		break;
	case 6:
		if (i_memcasecmp(str_data(value), "base64", 6) == 0)
			message_cte = MESSAGE_CTE_BASE64;
		else if (i_memcasecmp(str_data(value), "binary", 6) == 0)
			message_cte = MESSAGE_CTE_BINARY;
		break;
	case 16:
		if (i_memcasecmp(str_data(value), "quoted-printable", 16) == 0)
			message_cte = MESSAGE_CTE_QP;
		break;
	}
	rfc822_parser_deinit(&parser);
	return message_cte;
}

static void
parse_content_type(struct message_decoder_context *ctx,
		   struct message_header_line *hdr)
{
	struct rfc822_parser_context parser;
	const char *const *results;
	string_t *str;

	if (ctx->content_charset != NULL)
		return;

	rfc822_parser_init(&parser, hdr->full_value, hdr->full_value_len, NULL);
	rfc822_skip_lwsp(&parser);
	str = t_str_new(64);
	if (rfc822_parse_content_type(&parser, str) <= 0) {
		rfc822_parser_deinit(&parser);
		return;
	}

	rfc2231_parse(&parser, &results);
	for (; *results != NULL; results += 2) {
		if (strcasecmp(results[0], "charset") == 0) {
			ctx->content_charset = i_strdup(results[1]);
			ctx->charset_utf8 = charset_is_utf8(results[1]);
			break;
		}
	}
	rfc822_parser_deinit(&parser);
}

static bool message_decode_header(struct message_decoder_context *ctx,
				  struct message_header_line *hdr,
				  struct message_block *output)
{
	size_t value_len;

	if (hdr->continues) {
		hdr->use_full_value = TRUE;
		return FALSE;
	}

	T_BEGIN {
		if (hdr->name_len == 12 &&
		    strcasecmp(hdr->name, "Content-Type") == 0)
			parse_content_type(ctx, hdr);
		if (hdr->name_len == 25 &&
		    strcasecmp(hdr->name, "Content-Transfer-Encoding") == 0)
			ctx->message_cte = message_decoder_parse_cte(hdr);
	} T_END;

	buffer_set_used_size(ctx->buf, 0);
	message_header_decode_utf8(hdr->full_value, hdr->full_value_len,
				   ctx->buf, ctx->normalizer);
	value_len = ctx->buf->used;

	if (ctx->normalizer != NULL) {
		(void)ctx->normalizer(hdr->name, hdr->name_len, ctx->buf);
		buffer_append_c(ctx->buf, '\0');
	} else {
		if (!uni_utf8_get_valid_data((const unsigned char *)hdr->name,
					     hdr->name_len, ctx->buf))
			buffer_append_c(ctx->buf, '\0');
	}

	ctx->hdr = *hdr;
	ctx->hdr.full_value = ctx->buf->data;
	ctx->hdr.full_value_len = value_len;
	ctx->hdr.value_len = 0;
	if (ctx->buf->used != value_len) {
		ctx->hdr.name = CONST_PTR_OFFSET(ctx->buf->data,
						 ctx->hdr.full_value_len);
		ctx->hdr.name_len = ctx->buf->used - 1 - value_len;
	}

	output->hdr = &ctx->hdr;
	return TRUE;
}

static void translation_buf_decode(struct message_decoder_context *ctx,
				   const unsigned char **data, size_t *size)
{
	unsigned char trans_buf[MAX_TRANSLATION_BUF_SIZE+1];
	unsigned int data_wanted, skip;
	size_t trans_size, orig_size;

	/* @UNSAFE: move the previously untranslated bytes to trans_buf
	   and see if we have now enough data to get the next character
	   translated */
	memcpy(trans_buf, ctx->translation_buf, ctx->translation_size);
	data_wanted = sizeof(trans_buf) - ctx->translation_size;
	if (data_wanted > *size)
		data_wanted = *size;
	memcpy(trans_buf + ctx->translation_size, *data, data_wanted);

	orig_size = trans_size = ctx->translation_size + data_wanted;
	(void)charset_to_utf8(ctx->charset_trans, trans_buf,
			      &trans_size, ctx->buf2);

	if (trans_size <= ctx->translation_size) {
		/* need more data to finish the translation. */
		i_assert(orig_size < MAX_TRANSLATION_BUF_SIZE);
		memcpy(ctx->translation_buf, trans_buf, orig_size);
		ctx->translation_size = orig_size;
		*data += *size;
		*size = 0;
		return;
	}
	skip = trans_size - ctx->translation_size;

	i_assert(*size >= skip);
	*data += skip;
	*size -= skip;

	ctx->translation_size = 0;
}

static void
message_decode_body_init_charset(struct message_decoder_context *ctx,
				 struct message_part *part)
{
	ctx->binary_input = ctx->content_charset == NULL &&
		(ctx->flags & MESSAGE_DECODER_FLAG_RETURN_BINARY) != 0 &&
		(part->flags & (MESSAGE_PART_FLAG_TEXT |
				MESSAGE_PART_FLAG_MESSAGE_RFC822)) == 0;

	if (ctx->charset_utf8 || ctx->binary_input)
		return;

	if (ctx->charset_trans != NULL && ctx->content_charset != NULL &&
	    strcasecmp(ctx->content_charset, ctx->charset_trans_charset) == 0) {
		/* already have the correct translation selected */
		return;
	}

	if (ctx->charset_trans != NULL)
		charset_to_utf8_end(&ctx->charset_trans);
	i_free_and_null(ctx->charset_trans_charset);

	ctx->charset_trans_charset = i_strdup(ctx->content_charset != NULL ?
					      ctx->content_charset : "UTF-8");
	if (charset_to_utf8_begin(ctx->charset_trans_charset, ctx->normalizer,
				  &ctx->charset_trans) < 0)
		ctx->charset_trans = NULL;
}

static bool message_decode_body(struct message_decoder_context *ctx,
				struct message_block *input,
				struct message_block *output)
{
	const unsigned char *data = NULL;
	size_t pos = 0, size = 0;
	int ret;

	if (ctx->encoding_buf->used != 0) {
		/* @UNSAFE */
		buffer_append(ctx->encoding_buf, input->data, input->size);
	}

	switch (ctx->message_cte) {
	case MESSAGE_CTE_UNKNOWN:
		/* just skip this body */
		return FALSE;

	case MESSAGE_CTE_78BIT:
	case MESSAGE_CTE_BINARY:
		data = input->data;
		size = pos = input->size;
		break;
	case MESSAGE_CTE_QP:
		buffer_set_used_size(ctx->buf, 0);
		if (ctx->encoding_buf->used != 0) {
			(void)quoted_printable_decode(ctx->encoding_buf->data,
						      ctx->encoding_buf->used,
						      &pos, ctx->buf);
		} else {
			(void)quoted_printable_decode(input->data, input->size,
						      &pos, ctx->buf);
		}
		data = ctx->buf->data;
		size = ctx->buf->used;
		break;
	case MESSAGE_CTE_BASE64:
		buffer_set_used_size(ctx->buf, 0);
		if (ctx->encoding_buf->used != 0) {
			ret = base64_decode(ctx->encoding_buf->data,
					    ctx->encoding_buf->used,
					    &pos, ctx->buf);
		} else {
			ret = base64_decode(input->data, input->size,
					    &pos, ctx->buf);
		}
		if (ret < 0) {
			/* corrupted base64 data, don't bother with
			   the rest of it */
			return FALSE;
		}
		if (ret == 0) {
			/* end of base64 input */
			pos = input->size;
			buffer_set_used_size(ctx->encoding_buf, 0);
		}
		data = ctx->buf->data;
		size = ctx->buf->used;
		break;
	}

	if (ctx->encoding_buf->used != 0)
		buffer_delete(ctx->encoding_buf, 0, pos);
	else if (pos != input->size) {
		buffer_append(ctx->encoding_buf,
			      input->data + pos, input->size - pos);
	}

	if (ctx->binary_input) {
		output->data = data;
		output->size = size;
	} else if (ctx->charset_utf8) {
		buffer_set_used_size(ctx->buf2, 0);
		if (ctx->normalizer != NULL) {
			(void)ctx->normalizer(data, size, ctx->buf2);
			output->data = ctx->buf2->data;
			output->size = ctx->buf2->used;
		} else if (uni_utf8_get_valid_data(data, size, ctx->buf2)) {
			output->data = data;
			output->size = size;
		} else {
			output->data = ctx->buf2->data;
			output->size = ctx->buf2->used;
		}
	} else if (ctx->charset_trans == NULL) {
		/* unknown charset */
		buffer_set_used_size(ctx->buf2, 0);
		if (uni_utf8_get_valid_data(data, size, ctx->buf2)) {
			output->data = data;
			output->size = size;
		} else {
			output->data = ctx->buf2->data;
			output->size = ctx->buf2->used;
		}
	} else {
		buffer_set_used_size(ctx->buf2, 0);
		if (ctx->translation_size != 0)
			translation_buf_decode(ctx, &data, &size);

		pos = size;
		(void)charset_to_utf8(ctx->charset_trans,
				      data, &pos, ctx->buf2);
		if (pos != size) {
			ctx->translation_size = size - pos;
			i_assert(ctx->translation_size <=
				 sizeof(ctx->translation_buf));
			memcpy(ctx->translation_buf, data + pos,
			       ctx->translation_size);
		}
		output->data = ctx->buf2->data;
		output->size = ctx->buf2->used;
	}

	output->hdr = NULL;
	return TRUE;
}

bool message_decoder_decode_next_block(struct message_decoder_context *ctx,
				       struct message_block *input,
				       struct message_block *output)
{
	if (input->part != ctx->prev_part) {
		/* MIME part changed. */
		message_decoder_decode_reset(ctx);
	}

	output->part = input->part;
	ctx->prev_part = input->part;

	if (input->hdr != NULL)
		return message_decode_header(ctx, input->hdr, output);
	else if (input->size != 0)
		return message_decode_body(ctx, input, output);
	else {
		output->hdr = NULL;
		output->size = 0;
		message_decode_body_init_charset(ctx, input->part);
		return TRUE;
	}
}

void message_decoder_decode_reset(struct message_decoder_context *ctx)
{
	i_free_and_null(ctx->content_charset);
	ctx->message_cte = MESSAGE_CTE_78BIT;
	ctx->charset_utf8 = TRUE;
	buffer_set_used_size(ctx->encoding_buf, 0);
}