aboutsummaryrefslogtreecommitdiff
path: root/src/liblzma/common/stream_encoder.c
blob: a7663bc48db30e29c41234307bacb0b033006ad8 (plain) (blame)
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
///////////////////////////////////////////////////////////////////////////////
//
/// \file       stream_encoder.c
/// \brief      Encodes .xz Streams
//
//  Author:     Lasse Collin
//
//  This file has been put into the public domain.
//  You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////

#include "block_encoder.h"
#include "index_encoder.h"


struct lzma_coder_s {
	enum {
		SEQ_STREAM_HEADER,
		SEQ_BLOCK_INIT,
		SEQ_BLOCK_HEADER,
		SEQ_BLOCK_ENCODE,
		SEQ_INDEX_ENCODE,
		SEQ_STREAM_FOOTER,
	} sequence;

	/// True if Block encoder has been initialized by
	/// stream_encoder_init() or stream_encoder_update()
	/// and thus doesn't need to be initialized in stream_encode().
	bool block_encoder_is_initialized;

	/// Block
	lzma_next_coder block_encoder;

	/// Options for the Block encoder
	lzma_block block_options;

	/// The filter chain currently in use
	lzma_filter filters[LZMA_FILTERS_MAX + 1];

	/// Index encoder. This is separate from Block encoder, because this
	/// doesn't take much memory, and when encoding multiple Streams
	/// with the same encoding options we avoid reallocating memory.
	lzma_next_coder index_encoder;

	/// Index to hold sizes of the Blocks
	lzma_index *index;

	/// Read position in buffer[]
	size_t buffer_pos;

	/// Total number of bytes in buffer[]
	size_t buffer_size;

	/// Buffer to hold Stream Header, Block Header, and Stream Footer.
	/// Block Header has biggest maximum size.
	uint8_t buffer[LZMA_BLOCK_HEADER_SIZE_MAX];
};


static lzma_ret
block_encoder_init(lzma_coder *coder, const lzma_allocator *allocator)
{
	// Prepare the Block options. Even though Block encoder doesn't need
	// compressed_size, uncompressed_size, and header_size to be
	// initialized, it is a good idea to do it here, because this way
	// we catch if someone gave us Filter ID that cannot be used in
	// Blocks/Streams.
	coder->block_options.compressed_size = LZMA_VLI_UNKNOWN;
	coder->block_options.uncompressed_size = LZMA_VLI_UNKNOWN;

	return_if_error(lzma_block_header_size(&coder->block_options));

	// Initialize the actual Block encoder.
	return lzma_block_encoder_init(&coder->block_encoder, allocator,
			&coder->block_options);
}


static lzma_ret
stream_encode(lzma_coder *coder, const lzma_allocator *allocator,
		const uint8_t *restrict in, size_t *restrict in_pos,
		size_t in_size, uint8_t *restrict out,
		size_t *restrict out_pos, size_t out_size, lzma_action action)
{
	// Main loop
	while (*out_pos < out_size)
	switch (coder->sequence) {
	case SEQ_STREAM_HEADER:
	case SEQ_BLOCK_HEADER:
	case SEQ_STREAM_FOOTER:
		lzma_bufcpy(coder->buffer, &coder->buffer_pos,
				coder->buffer_size, out, out_pos, out_size);
		if (coder->buffer_pos < coder->buffer_size)
			return LZMA_OK;

		if (coder->sequence == SEQ_STREAM_FOOTER)
			return LZMA_STREAM_END;

		coder->buffer_pos = 0;
		++coder->sequence;
		break;

	case SEQ_BLOCK_INIT: {
		if (*in_pos == in_size) {
			// If we are requested to flush or finish the current
			// Block, return LZMA_STREAM_END immediately since
			// there's nothing to do.
			if (action != LZMA_FINISH)
				return action == LZMA_RUN
						? LZMA_OK : LZMA_STREAM_END;

			// The application had used LZMA_FULL_FLUSH to finish
			// the previous Block, but now wants to finish without
			// encoding new data, or it is simply creating an
			// empty Stream with no Blocks.
			//
			// Initialize the Index encoder, and continue to
			// actually encoding the Index.
			return_if_error(lzma_index_encoder_init(
					&coder->index_encoder, allocator,
					coder->index));
			coder->sequence = SEQ_INDEX_ENCODE;
			break;
		}

		// Initialize the Block encoder unless it was already
		// initialized by stream_encoder_init() or
		// stream_encoder_update().
		if (!coder->block_encoder_is_initialized)
			return_if_error(block_encoder_init(coder, allocator));

		// Make it false so that we don't skip the initialization
		// with the next Block.
		coder->block_encoder_is_initialized = false;

		// Encode the Block Header. This shouldn't fail since we have
		// already initialized the Block encoder.
		if (lzma_block_header_encode(&coder->block_options,
				coder->buffer) != LZMA_OK)
			return LZMA_PROG_ERROR;

		coder->buffer_size = coder->block_options.header_size;
		coder->sequence = SEQ_BLOCK_HEADER;
		break;
	}

	case SEQ_BLOCK_ENCODE: {
		static const lzma_action convert[LZMA_ACTION_MAX + 1] = {
			LZMA_RUN,
			LZMA_SYNC_FLUSH,
			LZMA_FINISH,
			LZMA_FINISH,
			LZMA_FINISH,
		};

		const lzma_ret ret = coder->block_encoder.code(
				coder->block_encoder.coder, allocator,
				in, in_pos, in_size,
				out, out_pos, out_size, convert[action]);
		if (ret != LZMA_STREAM_END || action == LZMA_SYNC_FLUSH)
			return ret;

		// Add a new Index Record.
		const lzma_vli unpadded_size = lzma_block_unpadded_size(
				&coder->block_options);
		assert(unpadded_size != 0);
		return_if_error(lzma_index_append(coder->index, allocator,
				unpadded_size,
				coder->block_options.uncompressed_size));

		coder->sequence = SEQ_BLOCK_INIT;
		break;
	}

	case SEQ_INDEX_ENCODE: {
		// Call the Index encoder. It doesn't take any input, so
		// those pointers can be NULL.
		const lzma_ret ret = coder->index_encoder.code(
				coder->index_encoder.coder, allocator,
				NULL, NULL, 0,
				out, out_pos, out_size, LZMA_RUN);
		if (ret != LZMA_STREAM_END)
			return ret;

		// Encode the Stream Footer into coder->buffer.
		const lzma_stream_flags stream_flags = {
			.version = 0,
			.backward_size = lzma_index_size(coder->index),
			.check = coder->block_options.check,
		};

		if (lzma_stream_footer_encode(&stream_flags, coder->buffer)
				!= LZMA_OK)
			return LZMA_PROG_ERROR;

		coder->buffer_size = LZMA_STREAM_HEADER_SIZE;
		coder->sequence = SEQ_STREAM_FOOTER;
		break;
	}

	default:
		assert(0);
		return LZMA_PROG_ERROR;
	}

	return LZMA_OK;
}


static void
stream_encoder_end(lzma_coder *coder, const lzma_allocator *allocator)
{
	lzma_next_end(&coder->block_encoder, allocator);
	lzma_next_end(&coder->index_encoder, allocator);
	lzma_index_end(coder->index, allocator);

	for (size_t i = 0; coder->filters[i].id != LZMA_VLI_UNKNOWN; ++i)
		lzma_free(coder->filters[i].options, allocator);

	lzma_free(coder, allocator);
	return;
}


static lzma_ret
stream_encoder_update(lzma_coder *coder, const lzma_allocator *allocator,
		const lzma_filter *filters,
		const lzma_filter *reversed_filters)
{
	if (coder->sequence <= SEQ_BLOCK_INIT) {
		// There is no incomplete Block waiting to be finished,
		// thus we can change the whole filter chain. Start by
		// trying to initialize the Block encoder with the new
		// chain. This way we detect if the chain is valid.
		coder->block_encoder_is_initialized = false;
		coder->block_options.filters = (lzma_filter *)(filters);
		const lzma_ret ret = block_encoder_init(coder, allocator);
		coder->block_options.filters = coder->filters;
		if (ret != LZMA_OK)
			return ret;

		coder->block_encoder_is_initialized = true;

	} else if (coder->sequence <= SEQ_BLOCK_ENCODE) {
		// We are in the middle of a Block. Try to update only
		// the filter-specific options.
		return_if_error(coder->block_encoder.update(
				coder->block_encoder.coder, allocator,
				filters, reversed_filters));
	} else {
		// Trying to update the filter chain when we are already
		// encoding Index or Stream Footer.
		return LZMA_PROG_ERROR;
	}

	// Free the copy of the old chain and make a copy of the new chain.
	for (size_t i = 0; coder->filters[i].id != LZMA_VLI_UNKNOWN; ++i)
		lzma_free(coder->filters[i].options, allocator);

	return lzma_filters_copy(filters, coder->filters, allocator);
}


static lzma_ret
stream_encoder_init(lzma_next_coder *next, const lzma_allocator *allocator,
		const lzma_filter *filters, lzma_check check)
{
	lzma_next_coder_init(&stream_encoder_init, next, allocator);

	if (filters == NULL)
		return LZMA_PROG_ERROR;

	if (next->coder == NULL) {
		next->coder = lzma_alloc(sizeof(lzma_coder), allocator);
		if (next->coder == NULL)
			return LZMA_MEM_ERROR;

		next->code = &stream_encode;
		next->end = &stream_encoder_end;
		next->update = &stream_encoder_update;

		next->coder->filters[0].id = LZMA_VLI_UNKNOWN;
		next->coder->block_encoder = LZMA_NEXT_CODER_INIT;
		next->coder->index_encoder = LZMA_NEXT_CODER_INIT;
		next->coder->index = NULL;
	}

	// Basic initializations
	next->coder->sequence = SEQ_STREAM_HEADER;
	next->coder->block_options.version = 0;
	next->coder->block_options.check = check;

	// Initialize the Index
	lzma_index_end(next->coder->index, allocator);
	next->coder->index = lzma_index_init(allocator);
	if (next->coder->index == NULL)
		return LZMA_MEM_ERROR;

	// Encode the Stream Header
	lzma_stream_flags stream_flags = {
		.version = 0,
		.check = check,
	};
	return_if_error(lzma_stream_header_encode(
			&stream_flags, next->coder->buffer));

	next->coder->buffer_pos = 0;
	next->coder->buffer_size = LZMA_STREAM_HEADER_SIZE;

	// Initialize the Block encoder. This way we detect unsupported
	// filter chains when initializing the Stream encoder instead of
	// giving an error after Stream Header has already written out.
	return stream_encoder_update(
			next->coder, allocator, filters, NULL);
}


extern LZMA_API(lzma_ret)
lzma_stream_encoder(lzma_stream *strm,
		const lzma_filter *filters, lzma_check check)
{
	lzma_next_strm_init(stream_encoder_init, strm, filters, check);

	strm->internal->supported_actions[LZMA_RUN] = true;
	strm->internal->supported_actions[LZMA_SYNC_FLUSH] = true;
	strm->internal->supported_actions[LZMA_FULL_FLUSH] = true;
	strm->internal->supported_actions[LZMA_FULL_BARRIER] = true;
	strm->internal->supported_actions[LZMA_FINISH] = true;

	return LZMA_OK;
}