aboutsummaryrefslogtreecommitdiff
path: root/src/xzdec/xzdec.c
blob: d6f4252fa50adaadc2133ea404a46058f9882756 (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
///////////////////////////////////////////////////////////////////////////////
//
/// \file       xzdec.c
/// \brief      Simple single-threaded tool to uncompress .xz or .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"

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

#ifdef _WIN32
#	include <fcntl.h>
#endif

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


#ifdef LZMADEC
#	define TOOL_FORMAT "lzma"
#else
#	define TOOL_FORMAT "xz"
#endif


/// Number of bytes to use memory at maximum
static uint64_t memlimit;

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


static void lzma_attribute((noreturn))
my_exit(void)
{
	int status = EXIT_SUCCESS;

	// Close stdout. We don't care about stderr, because we write to it
	// only when an error has already occurred.
	const int ferror_err = ferror(stdout);
	const int fclose_err = fclose(stdout);

	if (ferror_err || fclose_err) {
		// If it was fclose() that failed, we have the reason
		// in errno. If only ferror() indicated an error,
		// we have no idea what the reason was.
		fprintf(stderr, "%s: Cannot write to standard output: %s\n",
				argv0, fclose_err
					? strerror(errno) : "Unknown error");
		status = EXIT_FAILURE;
	}

	exit(status);
}


static void lzma_attribute((noreturn))
help(void)
{
	printf(
"Usage: %s [OPTION]... [FILE]...\n"
"Uncompress files in the ." TOOL_FORMAT " format to the standard output.\n"
"\n"
"  -c, --stdout       (ignored)\n"
"  -d, --decompress   (ignored)\n"
"  -k, --keep         (ignored)\n"
"  -f, --force        (ignored)\n"
"  -M, --memory=NUM   use NUM bytes of memory at maximum (0 means default);\n"
"                     the suffixes k, M, G, Ki, Mi, and Gi are supported.\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, (memlimit + 512 * 1024) / (1024 * 1024));
	my_exit();
}


static void lzma_attribute((noreturn))
version(void)
{
	printf(TOOL_FORMAT "dec " PACKAGE_VERSION "\n"
			"liblzma %s\n", lzma_version_string());

	my_exit();
}


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

	if (mem == 0)
		// Cannot autodetect, use 10 MiB as the default limit.
		memlimit = (1U << 23) + (1U << 21);
	else
		// Limit is 33 % of RAM.
		memlimit = mem / 3;

	return;
}


/// \brief      Converts a string to uint64_t
///
/// This is rudely copied from src/xz/util.c and modified a little. :-(
///
static uint64_t
str_to_uint64(const char *value)
{
	uint64_t result = 0;

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

	do {
		// Don't overflow.
		if (result > (UINT64_MAX - 9) / 10)
			return UINT64_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];
			uint32_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 }
		};

		uint32_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(EXIT_FAILURE);
		}

		// Don't overflow here either.
		if (result > UINT64_MAX / multiplier)
			result = UINT64_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' },
		{ "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 'f':
		case 'k':
			break;

		case 'M':
			memlimit = str_to_uint64(optarg);
			if (memlimit == 0)
				set_default_memlimit();

			break;

		case 'h':
			help();

		case 'V':
			version();

		default:
			exit(EXIT_FAILURE);
		}
	}

	return;
}


static void
uncompress(lzma_stream *strm, FILE *file, const char *filename)
{
	lzma_ret ret;

	// Initialize the decoder
#ifdef LZMADEC
	ret = lzma_alone_decoder(strm, memlimit);
#else
	ret = lzma_stream_decoder(strm, memlimit, LZMA_CONCATENATED);
#endif

	// The only reasonable error here is LZMA_MEM_ERROR.
	// FIXME: Maybe also LZMA_MEMLIMIT_ERROR in future?
	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(EXIT_FAILURE);
	}

	// Input and output buffers
	uint8_t in_buf[BUFSIZ];
	uint8_t out_buf[BUFSIZ];

	strm->avail_in = 0;
	strm->next_out = out_buf;
	strm->avail_out = BUFSIZ;

	lzma_action action = LZMA_RUN;

	while (true) {
		if (strm->avail_in == 0) {
			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(EXIT_FAILURE);
			}

#ifndef LZMADEC
			// When using LZMA_CONCATENATED, we need to tell
			// liblzma when it has got all the input.
			if (feof(file))
				action = LZMA_FINISH;
#endif
		}

		ret = lzma_code(strm, action);

		// 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.
		if (strm->avail_out == 0 || ret != LZMA_OK) {
			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(EXIT_FAILURE);
			}

			strm->next_out = out_buf;
			strm->avail_out = BUFSIZ;
		}

		if (ret != LZMA_OK) {
			if (ret == LZMA_STREAM_END) {
#ifdef LZMADEC
				// Check that there's no trailing garbage.
				if (strm->avail_in != 0
						|| fread(in_buf, 1, 1, file)
							!= 0
						|| !feof(file))
					ret = LZMA_DATA_ERROR;
				else
					return;
#else
				// lzma_stream_decoder() already guarantees
				// that there's no trailing garbage.
				assert(strm->avail_in == 0);
				assert(action == LZMA_FINISH);
				assert(feof(file));
				return;
#endif
			}

			const char *msg;
			switch (ret) {
			case LZMA_MEM_ERROR:
				msg = strerror(ENOMEM);
				break;

			case LZMA_MEMLIMIT_ERROR:
				msg = "Memory usage limit reached";
				break;

			case LZMA_FORMAT_ERROR:
				msg = "File format not recognized";
				break;

			case LZMA_OPTIONS_ERROR:
				// FIXME: Better message?
				msg = "Unsupported compression options";
				break;

			case LZMA_DATA_ERROR:
				msg = "File is corrupt";
				break;

			case LZMA_BUF_ERROR:
				msg = "Unexpected end of input";
				break;

			default:
				msg = "Internal program error (bug)";
				break;
			}

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

			exit(EXIT_FAILURE);
		}
	}
}


int
main(int argc, char **argv)
{
	// Set the argv0 global so that we can print the command name in
	// error and help messages.
	argv0 = argv[0];

	// Detect amount of installed RAM and set the memory usage limit.
	// This is needed before parsing the command line arguments.
	set_default_memlimit();

	// Parse the command line options.
	parse_options(argc, argv);

	// The same lzma_stream is used for all files that we decode. This way
	// we don't need to reallocate memory for every file if they use same
	// compression settings.
	lzma_stream strm = LZMA_STREAM_INIT;

	// Some systems require setting stdin and stdout to binary mode.
#ifdef _WIN32
	setmode(fileno(stdin), O_BINARY);
	setmode(fileno(stdout), O_BINARY);
#endif

	if (optind == argc) {
		// No filenames given, decode from stdin.
		uncompress(&strm, stdin, "(stdin)");
	} else {
		// Loop through the filenames given on the command line.
		do {
			// "-" indicates stdin.
			if (strcmp(argv[optind], "-") == 0) {
				uncompress(&strm, stdin, "(stdin)");
			} else {
				FILE *file = fopen(argv[optind], "rb");
				if (file == NULL) {
					fprintf(stderr, "%s: %s: %s\n",
							argv0, argv[optind],
							strerror(errno));
					exit(EXIT_FAILURE);
				}

				uncompress(&strm, file, argv[optind]);
				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);
#endif

	my_exit();
}