aboutsummaryrefslogtreecommitdiff
path: root/src/lzmadec/lzmadec.c
blob: 1fc561b7ede59c789837f065b75e3c12dd1d9422 (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
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
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
///////////////////////////////////////////////////////////////////////////////
//
/// \file       lzmadec.c
/// \brief      Simple single-threaded tool to uncompress .lzma files
//
//  Copyright (C) 2007 Lasse Collin
//
//  This program is free software; you can redistribute it and/or
//  modify it under the terms of the GNU Lesser General Public
//  License as published by the Free Software Foundation; either
//  version 2.1 of the License, or (at your option) any later version.
//
//  This program is distributed in the hope that it will be useful,
//  but WITHOUT ANY WARRANTY; without even the implied warranty of
//  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
//  Lesser General Public License for more details.
//
///////////////////////////////////////////////////////////////////////////////

#include "sysdefs.h"

#ifdef HAVE_ERRNO_H
#	include <errno.h>
#else
extern int errno;
#endif

#include <stdio.h>
#include <unistd.h>

#ifdef WIN32
#	include <fcntl.h>
#endif

#include "getopt.h"
#include "physmem.h"


enum return_code {
	SUCCESS,
	ERROR,
	WARNING,
};


enum format_type {
	FORMAT_AUTO,
	FORMAT_NATIVE,
	FORMAT_ALONE,
};


enum {
	OPTION_FORMAT = INT_MIN,
};


/// Input buffer
static uint8_t in_buf[BUFSIZ];

/// Output buffer
static uint8_t out_buf[BUFSIZ];

/// Decoder
static lzma_stream strm = LZMA_STREAM_INIT;

/// Number of bytes to use memory at maximum
static size_t mem_limit;

/// Memory allocation hooks
static lzma_allocator allocator = {
	.alloc = (void *(*)(void *, size_t, size_t))(&lzma_memlimit_alloc),
	.free = (void (*)(void *, void *))(&lzma_memlimit_free),
	.opaque = NULL,
};

/// Program name to be shown in error messages
static const char *argv0;

/// File currently being processed
static FILE *file;

/// Name of the file currently being processed
static const char *filename;

static enum return_code exit_status = SUCCESS;

static enum format_type format_type = FORMAT_AUTO;

static bool force = false;


static void lzma_attribute((noreturn))
help(void)
{
	printf(
"Usage: %s [OPTION]... [FILE]...\n"
"Uncompress files in the .lzma format to the standard output.\n"
"\n"
"  -c, --stdout       (ignored)\n"
"  -d, --decompress   (ignored)\n"
"  -k, --keep         (ignored)\n"
"  -f, --force        allow reading compressed data from a terminal\n"
"  -M, --memory=NUM   use NUM bytes of memory at maximum; the suffixes\n"
"                     k, M, G, Ki, Mi, and Gi are supported.\n"
"      --format=FMT   accept only files in the given file format;\n"
"                     possible FMTs are `auto', `native', `single',\n"
"                     `multi', and `alone', of which `single' and `multi'\n"
"                     are aliases for `native'\n"
"  -h, --help         display this help and exit\n"
"  -V, --version      display version and license information and exit\n"
"\n"
"With no FILE, or when FILE is -, read standard input.\n"
"\n"
"On this configuration, the tool will use about %" PRIu64
		" MiB of memory at maximum.\n"
"\n"
"Report bugs to <" PACKAGE_BUGREPORT "> (in English or Finnish).\n",
		argv0, ((uint64_t)(mem_limit) + 512 * 1024) / (1024 * 1024));
		// Using PRIu64 above instead of %zu to support pre-C99 libc.
	exit(0);
}


static void lzma_attribute((noreturn))
version(void)
{
	printf(
"lzmadec (LZMA Utils) " PACKAGE_VERSION "\n"
"\n"
"Copyright (C) 1999-2006 Igor Pavlov\n"
"Copyright (C) 2007 Lasse Collin\n"
"\n"
"This program is free software; you can redistribute it and/or\n"
"modify it under the terms of the GNU Lesser General Public\n"
"License as published by the Free Software Foundation; either\n"
"version 2.1 of the License, or (at your option) any later version.\n"
"\n"
"This program is distributed in the hope that it will be useful,\n"
"but WITHOUT ANY WARRANTY; without even the implied warranty of\n"
"MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU\n"
"Lesser General Public License for more details.\n"
"\n");
	exit(0);
}


/// Finds out the amount of physical memory in the system, and sets
/// a default memory usage limit.
static void
set_default_mem_limit(void)
{
	uint64_t mem = physmem();
	if (mem != 0) {
		mem /= 3;

#if UINT64_MAX > SIZE_MAX
		if (mem > SIZE_MAX)
			mem = SIZE_MAX;
#endif

		mem_limit = mem / 3;
	} else {
		// Cannot autodetect, use 10 MiB as the default limit.
		mem_limit = (1U << 23) + (1U << 21);
	}

	return;
}


/// \brief      Converts a string to size_t
///
/// This is rudely copied from src/lzma/util.c and modified a little. :-(
///
static size_t
str_to_size(const char *value)
{
	size_t result = 0;

	if (*value < '0' || *value > '9') {
		fprintf(stderr, "%s: %s: Not a number", argv0, value);
		exit(ERROR);
	}

	do {
		// Don't overflow.
		if (result > (SIZE_MAX - 9) / 10)
			return SIZE_MAX;

		result *= 10;
		result += *value - '0';
		++value;
	} while (*value >= '0' && *value <= '9');

	if (*value != '\0') {
		// Look for suffix.
		static const struct {
			const char name[4];
			size_t multiplier;
		} suffixes[] = {
			{ "k",   1000 },
			{ "kB",  1000 },
			{ "M",   1000000 },
			{ "MB",  1000000 },
			{ "G",   1000000000 },
			{ "GB",  1000000000 },
			{ "Ki",  1024 },
			{ "KiB", 1024 },
			{ "Mi",  1048576 },
			{ "MiB", 1048576 },
			{ "Gi",  1073741824 },
			{ "GiB", 1073741824 }
		};

		size_t multiplier = 0;
		for (size_t i = 0; i < ARRAY_SIZE(suffixes); ++i) {
			if (strcmp(value, suffixes[i].name) == 0) {
				multiplier = suffixes[i].multiplier;
				break;
			}
		}

		if (multiplier == 0) {
			fprintf(stderr, "%s: %s: Invalid suffix",
					argv0, value);
			exit(ERROR);
		}

		// Don't overflow here either.
		if (result > SIZE_MAX / multiplier)
			result = SIZE_MAX;
		else
			result *= multiplier;
	}

	return result;
}


/// Parses command line options.
static void
parse_options(int argc, char **argv)
{
	static const char short_opts[] = "cdkfM:hV";
	static const struct option long_opts[] = {
		{ "stdout",       no_argument,         NULL, 'c' },
		{ "to-stdout",    no_argument,         NULL, 'c' },
		{ "decompress",   no_argument,         NULL, 'd' },
		{ "uncompress",   no_argument,         NULL, 'd' },
		{ "force",        no_argument,         NULL, 'f' },
		{ "keep",         no_argument,         NULL, 'k' },
		{ "memory",       required_argument,   NULL, 'M' },
		{ "format",       required_argument,   NULL, OPTION_FORMAT },
		{ "help",         no_argument,         NULL, 'h' },
		{ "version",      no_argument,         NULL, 'V' },
		{ NULL,           0,                   NULL, 0   }
	};

	int c;

	while ((c = getopt_long(argc, argv, short_opts, long_opts, NULL))
			!= -1) {
		switch (c) {
		case 'c':
		case 'd':
		case 'k':
			break;

		case 'f':
			force = true;
			break;

		case 'M':
			mem_limit = str_to_size(optarg);
			break;

		case 'h':
			help();

		case 'V':
			version();

		case OPTION_FORMAT: {
			if (strcmp("auto", optarg) == 0) {
				format_type = FORMAT_AUTO;
			} else if (strcmp("native", optarg) == 0) {
				format_type = FORMAT_NATIVE;
			} else if (strcmp("alone", optarg) == 0) {
				format_type = FORMAT_ALONE;
			} else {
				fprintf(stderr, "%s: %s: Unknown file format "
						"name\n", argv0, optarg);
				exit(ERROR);
			}
			break;
		}

		default:
			exit(ERROR);
		}
	}

	return;
}


/// Initializes lzma_stream structure for decoding of a new Stream.
static void
init(void)
{
	lzma_ret ret;

	switch (format_type) {
	case FORMAT_AUTO:
		ret = lzma_auto_decoder(&strm);
		break;

	case FORMAT_NATIVE:
		ret = lzma_stream_decoder(&strm);
		break;

	case FORMAT_ALONE:
		ret = lzma_alone_decoder(&strm);
		break;

	default:
		assert(0);
		ret = LZMA_PROG_ERROR;
	}

	if (ret != LZMA_OK) {
		fprintf(stderr, "%s: ", argv0);

		if (ret == LZMA_MEM_ERROR)
			fprintf(stderr, "%s\n", strerror(ENOMEM));
		else
			fprintf(stderr, "Internal program error (bug)\n");

		exit(ERROR);
	}

	return;
}


static void
read_input(void)
{
	strm.next_in = in_buf;
	strm.avail_in = fread(in_buf, 1, BUFSIZ, file);

	if (ferror(file)) {
		// POSIX says that fread() sets errno if an error occurred.
		// ferror() doesn't touch errno.
		fprintf(stderr, "%s: %s: Error reading input file: %s\n",
				argv0, filename, strerror(errno));
		exit(ERROR);
	}

	return;
}


static bool
skip_padding(void)
{
	// Handle concatenated Streams. There can be arbitrary number of
	// nul-byte padding between the Streams, which must be ignored.
	//
	// NOTE: Concatenating LZMA_Alone files works only if at least
	// one of lc, lp, and pb is non-zero. Using the concatenation
	// on LZMA_Alone files is strongly discouraged.
	while (true) {
		while (strm.avail_in > 0) {
			if (*strm.next_in != '\0')
				return true;

			++strm.next_in;
			--strm.avail_in;
		}

		if (feof(file))
			return false;

		read_input();
	}
}


static void
uncompress(void)
{
	if (file == stdin && !force && isatty(STDIN_FILENO)) {
		fprintf(stderr, "%s: Compressed data not read from "
				"a terminal.\n%s: Use `-f' to force reading "
				"from a terminal, or `-h' for help.\n",
				argv0, argv0);
		exit(ERROR);
	}

	init();
	strm.avail_in = 0;

	while (true) {
		if (strm.avail_in == 0)
			read_input();

		strm.next_out = out_buf;
		strm.avail_out = BUFSIZ;

		const lzma_ret ret = lzma_code(&strm, LZMA_RUN);

		// Write and check write error before checking decoder error.
		// This way as much data as possible gets written to output
		// even if decoder detected an error. Checking write error
		// needs to be done before checking decoder error due to
		// how concatenated Streams are handled a few lines later.
		const size_t write_size = BUFSIZ - strm.avail_out;
		if (fwrite(out_buf, 1, write_size, stdout) != write_size) {
			// Wouldn't be a surprise if writing to stderr would
			// fail too but at least try to show an error message.
			fprintf(stderr, "%s: Cannot write to "
					"standard output: %s\n", argv0,
					strerror(errno));
			exit(ERROR);
		}

		if (ret != LZMA_OK) {
			if (ret == LZMA_STREAM_END) {
				if (skip_padding()) {
					init();
					continue;
				}

				return;
			}

			fprintf(stderr, "%s: %s: ", argv0, filename);

			switch (ret) {
			case LZMA_DATA_ERROR:
				fprintf(stderr, "File is corrupt\n");
				exit(ERROR);

			case LZMA_HEADER_ERROR:
				fprintf(stderr, "Unsupported file "
						"format or filters\n");
				exit(ERROR);

			case LZMA_MEM_ERROR:
				fprintf(stderr, "%s\n", strerror(ENOMEM));
				exit(ERROR);

			case LZMA_BUF_ERROR:
				fprintf(stderr, "Unexpected end of input\n");
				exit(ERROR);

			case LZMA_UNSUPPORTED_CHECK:
				fprintf(stderr, "Unsupported type of "
						"integrity check; not "
						"verifying file integrity\n");
				exit_status = WARNING;
				break;

			case LZMA_PROG_ERROR:
			default:
				fprintf(stderr, "Internal program "
						"error (bug)\n");
				exit(ERROR);
			}
		}
	}
}


int
main(int argc, char **argv)
{
	argv0 = argv[0];

	set_default_mem_limit();

	parse_options(argc, argv);

	lzma_init_decoder();

	lzma_memlimit *mem_limiter = lzma_memlimit_create(mem_limit);
	if (mem_limiter == NULL) {
		fprintf(stderr, "%s: %s\n", argv0, strerror(ENOMEM));
		exit(ERROR);
	}

	assert(lzma_memlimit_count(mem_limiter) == 0);

	allocator.opaque = mem_limiter;
	strm.allocator = &allocator;

#ifdef WIN32
	setmode(fileno(stdin), O_BINARY);
	setmode(fileno(stdout), O_BINARY);
#endif

	if (optind == argc) {
		file = stdin;
		filename = "(stdin)";
		uncompress();
	} else {
		do {
			if (strcmp(argv[optind], "-") == 0) {
				file = stdin;
				filename = "(stdin)";
				uncompress();
			} else {
				filename = argv[optind];
				file = fopen(filename, "rb");
				if (file == NULL) {
					fprintf(stderr, "%s: %s: %s\n",
							argv0, filename,
							strerror(errno));
					exit(ERROR);
				}

				uncompress();
				fclose(file);
			}
		} while (++optind < argc);
	}

#ifndef NDEBUG
	// Free the memory only when debugging. Freeing wastes some time,
	// but allows detecting possible memory leaks with Valgrind.
	lzma_end(&strm);
	assert(lzma_memlimit_count(mem_limiter) == 0);
	lzma_memlimit_end(mem_limiter, false);
#endif

	return exit_status;
}