busybox/archival/bzip2.c

246 lines
7.2 KiB
C
Raw Normal View History

/*
* Copyright (C) 2007 Denys Vlasenko <vda.linux@googlemail.com>
*
* This file uses bzip2 library code which is written
* by Julian Seward <jseward@bzip.org>.
* See README and LICENSE files in bz/ directory for more information
* about bzip2 library code.
*/
//config:config BZIP2
//config: bool "bzip2 (16 kb)"
//config: default y
//config: help
//config: bzip2 is a compression utility using the Burrows-Wheeler block
//config: sorting text compression algorithm, and Huffman coding. Compression
//config: is generally considerably better than that achieved by more
//config: conventional LZ77/LZ78-based compressors, and approaches the
//config: performance of the PPM family of statistical compressors.
//config:
//config: Unless you have a specific application which requires bzip2, you
//config: should probably say N here.
//config:
//config:config BZIP2_SMALL
//config: int "Trade bytes for speed (0:fast, 9:small)"
//config: default 8 # all "fast or small" options default to small
//config: range 0 9
//config: depends on BZIP2
//config: help
//config: Trade code size versus speed.
//config: Approximate values with gcc-6.3.0 "bzip -9" compressing
//config: linux-4.15.tar were:
//config: value time (sec) code size (386)
//config: 9 (smallest) 70.11 7687
//config: 8 67.93 8091
//config: 7 67.88 8405
//config: 6 67.78 8624
//config: 5 67.05 9427
//config: 4-0 (fastest) 64.14 12083
//config:
//config:config FEATURE_BZIP2_DECOMPRESS
//config: bool "Enable decompression"
//config: default y
//config: depends on BZIP2 || BUNZIP2 || BZCAT
//config: help
//config: Enable -d (--decompress) and -t (--test) options for bzip2.
//config: This will be automatically selected if bunzip2 or bzcat is
//config: enabled.
//applet:IF_BZIP2(APPLET(bzip2, BB_DIR_USR_BIN, BB_SUID_DROP))
//kbuild:lib-$(CONFIG_BZIP2) += bzip2.o
//usage:#define bzip2_trivial_usage
//usage: "[OPTIONS] [FILE]..."
//usage:#define bzip2_full_usage "\n\n"
//usage: "Compress FILEs (or stdin) with bzip2 algorithm\n"
//usage: "\n -1..9 Compression level"
//usage: IF_FEATURE_BZIP2_DECOMPRESS(
//usage: "\n -d Decompress"
//usage: "\n -t Test file integrity"
//usage: )
//usage: "\n -c Write to stdout"
//usage: "\n -f Force"
//usage: "\n -k Keep input files"
#include "libbb.h"
#include "bb_archive.h"
#if CONFIG_BZIP2_SMALL >= 4
#define BZIP2_SPEED (9 - CONFIG_BZIP2_SMALL)
#else
#define BZIP2_SPEED 5
#endif
/* Speed test:
* Compiled with gcc 4.2.1, run on Athlon 64 1800 MHz (512K L2 cache).
* Stock bzip2 is 26.4% slower than bbox bzip2 at SPEED 1
* (time to compress gcc-4.2.1.tar is 126.4% compared to bbox).
* At SPEED 5 difference is 32.7%.
*
* Test run of all BZIP2_SPEED values on a 11Mb text file:
* Size Time (3 runs)
* 0: 10828 4.145 4.146 4.148
* 1: 11097 3.845 3.860 3.861
* 2: 11392 3.763 3.767 3.768
* 3: 11892 3.722 3.724 3.727
* 4: 12740 3.637 3.640 3.644
* 5: 17273 3.497 3.509 3.509
*/
#define BZ_DEBUG 0
/* Takes ~300 bytes, detects corruption caused by bad RAM etc */
#define BZ_LIGHT_DEBUG 0
#include "libarchive/bz/bzlib.h"
#include "libarchive/bz/bzlib_private.h"
#include "libarchive/bz/blocksort.c"
#include "libarchive/bz/bzlib.c"
#include "libarchive/bz/compress.c"
#include "libarchive/bz/huffman.c"
/* No point in being shy and having very small buffer here.
* bzip2 internal buffers are much bigger anyway, hundreds of kbytes.
* If iobuf is several pages long, malloc() may use mmap,
* making iobuf page aligned and thus (maybe) have one memcpy less
* if kernel is clever enough.
*/
enum {
IOBUF_SIZE = 8 * 1024
};
/* NB: compressStream() has to return -1 on errors, not die.
* bbunpack() will correctly clean up in this case
* (delete incomplete .bz2 file)
*/
/* Returns:
* -1 on errors
* total written bytes so far otherwise
*/
static
IF_DESKTOP(long long) int bz_write(bz_stream *strm, void* rbuf, ssize_t rlen, void *wbuf)
{
int n, n2, ret;
strm->avail_in = rlen;
strm->next_in = rbuf;
while (1) {
strm->avail_out = IOBUF_SIZE;
strm->next_out = wbuf;
ret = BZ2_bzCompress(strm, rlen ? BZ_RUN : BZ_FINISH);
if (ret != BZ_RUN_OK /* BZ_RUNning */
&& ret != BZ_FINISH_OK /* BZ_FINISHing, but not done yet */
&& ret != BZ_STREAM_END /* BZ_FINISHed */
) {
bb_error_msg_and_die("internal error %d", ret);
}
n = IOBUF_SIZE - strm->avail_out;
if (n) {
n2 = full_write(STDOUT_FILENO, wbuf, n);
if (n2 != n) {
if (n2 >= 0)
errno = 0; /* prevent bogus error message */
libbb: reduce the overhead of single parameter bb_error_msg() calls Back in 2007, commit 0c97c9d43707 ("'simple' error message functions by Loic Grenie") introduced bb_simple_perror_msg() to allow for a lower overhead call to bb_perror_msg() when only a string was being printed with no parameters. This saves space for some CPU architectures because it avoids the overhead of a call to a variadic function. However there has never been a simple version of bb_error_msg(), and since 2007 many new calls to bb_perror_msg() have been added that only take a single parameter and so could have been using bb_simple_perror_message(). This changeset introduces 'simple' versions of bb_info_msg(), bb_error_msg(), bb_error_msg_and_die(), bb_herror_msg() and bb_herror_msg_and_die(), and replaces all calls that only take a single parameter, or use something like ("%s", arg), with calls to the corresponding 'simple' version. Since it is likely that single parameter calls to the variadic functions may be accidentally reintroduced in the future a new debugging config option WARN_SIMPLE_MSG has been introduced. This uses some macro magic which will cause any such calls to generate a warning, but this is turned off by default to avoid use of the unpleasant macros in normal circumstances. This is a large changeset due to the number of calls that have been replaced. The only files that contain changes other than simple substitution of function calls are libbb.h, libbb/herror_msg.c, libbb/verror_msg.c and libbb/xfuncs_printf.c. In miscutils/devfsd.c, networking/udhcp/common.h and util-linux/mdev.c additonal macros have been added for logging so that single parameter and multiple parameter logging variants exist. The amount of space saved varies considerably by architecture, and was found to be as follows (for 'defconfig' using GCC 7.4): Arm: -92 bytes MIPS: -52 bytes PPC: -1836 bytes x86_64: -938 bytes Note that for the MIPS architecture only an exception had to be made disabling the 'simple' calls for 'udhcp' (in networking/udhcp/common.h) because it made these files larger on MIPS. Signed-off-by: James Byrne <james.byrne@origamienergy.com> Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2019-07-02 15:05:03 +05:30
bb_simple_perror_msg(n2 >= 0 ? "short write" : bb_msg_write_error);
return -1;
}
}
if (ret == BZ_STREAM_END)
break;
if (rlen && strm->avail_in == 0)
break;
}
return 0 IF_DESKTOP( + strm->total_out );
}
static
IF_DESKTOP(long long) int FAST_FUNC compressStream(transformer_state_t *xstate UNUSED_PARAM)
{
IF_DESKTOP(long long) int total;
unsigned opt, level;
ssize_t count;
bz_stream bzs; /* it's small */
#define strm (&bzs)
char *iobuf;
#define rbuf iobuf
#define wbuf (iobuf + IOBUF_SIZE)
iobuf = xmalloc(2 * IOBUF_SIZE);
opt = option_mask32 >> (BBUNPK_OPTSTRLEN IF_FEATURE_BZIP2_DECOMPRESS(+ 2) + 2);
/* skipped BBUNPK_OPTSTR, "dt" and "zs" bits */
opt |= 0x100; /* if nothing else, assume -9 */
level = 0;
for (;;) {
level++;
if (opt & 1) break;
opt >>= 1;
}
BZ2_bzCompressInit(strm, level);
while (1) {
count = full_read(STDIN_FILENO, rbuf, IOBUF_SIZE);
if (count < 0) {
libbb: reduce the overhead of single parameter bb_error_msg() calls Back in 2007, commit 0c97c9d43707 ("'simple' error message functions by Loic Grenie") introduced bb_simple_perror_msg() to allow for a lower overhead call to bb_perror_msg() when only a string was being printed with no parameters. This saves space for some CPU architectures because it avoids the overhead of a call to a variadic function. However there has never been a simple version of bb_error_msg(), and since 2007 many new calls to bb_perror_msg() have been added that only take a single parameter and so could have been using bb_simple_perror_message(). This changeset introduces 'simple' versions of bb_info_msg(), bb_error_msg(), bb_error_msg_and_die(), bb_herror_msg() and bb_herror_msg_and_die(), and replaces all calls that only take a single parameter, or use something like ("%s", arg), with calls to the corresponding 'simple' version. Since it is likely that single parameter calls to the variadic functions may be accidentally reintroduced in the future a new debugging config option WARN_SIMPLE_MSG has been introduced. This uses some macro magic which will cause any such calls to generate a warning, but this is turned off by default to avoid use of the unpleasant macros in normal circumstances. This is a large changeset due to the number of calls that have been replaced. The only files that contain changes other than simple substitution of function calls are libbb.h, libbb/herror_msg.c, libbb/verror_msg.c and libbb/xfuncs_printf.c. In miscutils/devfsd.c, networking/udhcp/common.h and util-linux/mdev.c additonal macros have been added for logging so that single parameter and multiple parameter logging variants exist. The amount of space saved varies considerably by architecture, and was found to be as follows (for 'defconfig' using GCC 7.4): Arm: -92 bytes MIPS: -52 bytes PPC: -1836 bytes x86_64: -938 bytes Note that for the MIPS architecture only an exception had to be made disabling the 'simple' calls for 'udhcp' (in networking/udhcp/common.h) because it made these files larger on MIPS. Signed-off-by: James Byrne <james.byrne@origamienergy.com> Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2019-07-02 15:05:03 +05:30
bb_simple_perror_msg(bb_msg_read_error);
total = -1;
break;
}
/* if count == 0, bz_write finalizes compression */
total = bz_write(strm, rbuf, count, wbuf);
if (count == 0 || total < 0)
break;
}
/* Can't be conditional on ENABLE_FEATURE_CLEAN_UP -
* we are called repeatedly
*/
BZ2_bzCompressEnd(strm);
free(iobuf);
return total;
}
int bzip2_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
2008-07-05 14:48:54 +05:30
int bzip2_main(int argc UNUSED_PARAM, char **argv)
{
unsigned opt;
/* standard bzip2 flags
* -d --decompress force decompression
* -z --compress force compression
* -k --keep keep (don't delete) input files
* -f --force overwrite existing output files
* -t --test test compressed file integrity
* -c --stdout output to standard out
* -q --quiet suppress noncritical error messages
* -v --verbose be verbose (a 2nd -v gives more)
* -s --small use less memory (at most 2500k)
* -1 .. -9 set block size to 100k .. 900k
* --fast alias for -1
* --best alias for -9
*/
getopt32: remove opt_complementary function old new delta vgetopt32 1318 1392 +74 runsvdir_main 703 713 +10 bb_make_directory 423 425 +2 collect_cpu 546 545 -1 opt_chars 3 - -3 opt_complementary 4 - -4 tftpd_main 567 562 -5 ntp_init 476 471 -5 zcip_main 1266 1256 -10 xxd_main 428 418 -10 whois_main 140 130 -10 who_main 463 453 -10 which_main 212 202 -10 wget_main 2535 2525 -10 watchdog_main 291 281 -10 watch_main 222 212 -10 vlock_main 399 389 -10 uuencode_main 332 322 -10 uudecode_main 316 306 -10 unlink_main 45 35 -10 udhcpd_main 1482 1472 -10 udhcpc_main 2762 2752 -10 tune2fs_main 290 280 -10 tunctl_main 366 356 -10 truncate_main 218 208 -10 tr_main 518 508 -10 time_main 1134 1124 -10 tftp_main 286 276 -10 telnetd_main 1873 1863 -10 tcpudpsvd_main 1785 1775 -10 taskset_main 521 511 -10 tar_main 1009 999 -10 tail_main 1644 1634 -10 syslogd_main 1967 1957 -10 switch_root_main 368 358 -10 svlogd_main 1454 1444 -10 sv 1296 1286 -10 stat_main 104 94 -10 start_stop_daemon_main 1028 1018 -10 split_main 542 532 -10 sort_main 796 786 -10 slattach_main 624 614 -10 shuf_main 504 494 -10 setsid_main 96 86 -10 setserial_main 1132 1122 -10 setfont_main 388 378 -10 setconsole_main 78 68 -10 sendmail_main 1209 1199 -10 sed_main 677 667 -10 script_main 1077 1067 -10 run_parts_main 325 315 -10 rtcwake_main 454 444 -10 rm_main 175 165 -10 reformime_main 119 109 -10 readlink_main 123 113 -10 rdate_main 246 236 -10 pwdx_main 189 179 -10 pstree_main 317 307 -10 pscan_main 663 653 -10 popmaildir_main 818 808 -10 pmap_main 80 70 -10 nc_main 1042 1032 -10 mv_main 558 548 -10 mountpoint_main 477 467 -10 mount_main 1264 1254 -10 modprobe_main 768 758 -10 modinfo_main 333 323 -10 mktemp_main 200 190 -10 mkswap_main 324 314 -10 mkfs_vfat_main 1489 1479 -10 microcom_main 715 705 -10 md5_sha1_sum_main 521 511 -10 man_main 867 857 -10 makedevs_main 1052 1042 -10 ls_main 563 553 -10 losetup_main 432 422 -10 loadfont_main 89 79 -10 ln_main 524 514 -10 link_main 75 65 -10 ipcalc_main 544 534 -10 iostat_main 2397 2387 -10 install_main 768 758 -10 id_main 480 470 -10 i2cset_main 1239 1229 -10 i2cget_main 380 370 -10 i2cdump_main 1482 1472 -10 i2cdetect_main 682 672 -10 hwclock_main 406 396 -10 httpd_main 741 731 -10 grep_main 837 827 -10 getty_main 1559 1549 -10 fuser_main 297 287 -10 ftpgetput_main 345 335 -10 ftpd_main 2232 2222 -10 fstrim_main 251 241 -10 fsfreeze_main 77 67 -10 fsck_minix_main 2921 2911 -10 flock_main 314 304 -10 flashcp_main 740 730 -10 flash_eraseall_main 833 823 -10 fdformat_main 532 522 -10 expand_main 680 670 -10 eject_main 335 325 -10 dumpleases_main 630 620 -10 du_main 314 304 -10 dos2unix_main 441 431 -10 diff_main 1350 1340 -10 df_main 1064 1054 -10 date_main 1095 1085 -10 cut_main 961 951 -10 cryptpw_main 228 218 -10 crontab_main 575 565 -10 crond_main 1149 1139 -10 cp_main 370 360 -10 common_traceroute_main 3834 3824 -10 common_ping_main 1767 1757 -10 comm_main 239 229 -10 cmp_main 655 645 -10 chrt_main 379 369 -10 chpst_main 704 694 -10 chpasswd_main 308 298 -10 chown_main 171 161 -10 chmod_main 158 148 -10 cat_main 428 418 -10 bzip2_main 120 110 -10 blkdiscard_main 264 254 -10 base64_main 221 211 -10 arping_main 1665 1655 -10 ar_main 556 546 -10 adjtimex_main 406 396 -10 adduser_main 882 872 -10 addgroup_main 411 401 -10 acpid_main 1198 1188 -10 optstring 11 - -11 opt_string 18 - -18 OPT_STR 25 - -25 ubi_tools_main 1288 1258 -30 ls_options 31 - -31 ------------------------------------------------------------------------------ (add/remove: 0/6 grow/shrink: 3/129 up/down: 86/-1383) Total: -1297 bytes text data bss dec hex filename 915428 485 6876 922789 e14a5 busybox_old 914629 485 6872 921986 e1182 busybox_unstripped Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2017-08-09 01:25:02 +05:30
opt = getopt32(argv, "^"
/* Must match BBUNPK_foo constants! */
BBUNPK_OPTSTR IF_FEATURE_BZIP2_DECOMPRESS("dt") "zs123456789"
getopt32: remove opt_complementary function old new delta vgetopt32 1318 1392 +74 runsvdir_main 703 713 +10 bb_make_directory 423 425 +2 collect_cpu 546 545 -1 opt_chars 3 - -3 opt_complementary 4 - -4 tftpd_main 567 562 -5 ntp_init 476 471 -5 zcip_main 1266 1256 -10 xxd_main 428 418 -10 whois_main 140 130 -10 who_main 463 453 -10 which_main 212 202 -10 wget_main 2535 2525 -10 watchdog_main 291 281 -10 watch_main 222 212 -10 vlock_main 399 389 -10 uuencode_main 332 322 -10 uudecode_main 316 306 -10 unlink_main 45 35 -10 udhcpd_main 1482 1472 -10 udhcpc_main 2762 2752 -10 tune2fs_main 290 280 -10 tunctl_main 366 356 -10 truncate_main 218 208 -10 tr_main 518 508 -10 time_main 1134 1124 -10 tftp_main 286 276 -10 telnetd_main 1873 1863 -10 tcpudpsvd_main 1785 1775 -10 taskset_main 521 511 -10 tar_main 1009 999 -10 tail_main 1644 1634 -10 syslogd_main 1967 1957 -10 switch_root_main 368 358 -10 svlogd_main 1454 1444 -10 sv 1296 1286 -10 stat_main 104 94 -10 start_stop_daemon_main 1028 1018 -10 split_main 542 532 -10 sort_main 796 786 -10 slattach_main 624 614 -10 shuf_main 504 494 -10 setsid_main 96 86 -10 setserial_main 1132 1122 -10 setfont_main 388 378 -10 setconsole_main 78 68 -10 sendmail_main 1209 1199 -10 sed_main 677 667 -10 script_main 1077 1067 -10 run_parts_main 325 315 -10 rtcwake_main 454 444 -10 rm_main 175 165 -10 reformime_main 119 109 -10 readlink_main 123 113 -10 rdate_main 246 236 -10 pwdx_main 189 179 -10 pstree_main 317 307 -10 pscan_main 663 653 -10 popmaildir_main 818 808 -10 pmap_main 80 70 -10 nc_main 1042 1032 -10 mv_main 558 548 -10 mountpoint_main 477 467 -10 mount_main 1264 1254 -10 modprobe_main 768 758 -10 modinfo_main 333 323 -10 mktemp_main 200 190 -10 mkswap_main 324 314 -10 mkfs_vfat_main 1489 1479 -10 microcom_main 715 705 -10 md5_sha1_sum_main 521 511 -10 man_main 867 857 -10 makedevs_main 1052 1042 -10 ls_main 563 553 -10 losetup_main 432 422 -10 loadfont_main 89 79 -10 ln_main 524 514 -10 link_main 75 65 -10 ipcalc_main 544 534 -10 iostat_main 2397 2387 -10 install_main 768 758 -10 id_main 480 470 -10 i2cset_main 1239 1229 -10 i2cget_main 380 370 -10 i2cdump_main 1482 1472 -10 i2cdetect_main 682 672 -10 hwclock_main 406 396 -10 httpd_main 741 731 -10 grep_main 837 827 -10 getty_main 1559 1549 -10 fuser_main 297 287 -10 ftpgetput_main 345 335 -10 ftpd_main 2232 2222 -10 fstrim_main 251 241 -10 fsfreeze_main 77 67 -10 fsck_minix_main 2921 2911 -10 flock_main 314 304 -10 flashcp_main 740 730 -10 flash_eraseall_main 833 823 -10 fdformat_main 532 522 -10 expand_main 680 670 -10 eject_main 335 325 -10 dumpleases_main 630 620 -10 du_main 314 304 -10 dos2unix_main 441 431 -10 diff_main 1350 1340 -10 df_main 1064 1054 -10 date_main 1095 1085 -10 cut_main 961 951 -10 cryptpw_main 228 218 -10 crontab_main 575 565 -10 crond_main 1149 1139 -10 cp_main 370 360 -10 common_traceroute_main 3834 3824 -10 common_ping_main 1767 1757 -10 comm_main 239 229 -10 cmp_main 655 645 -10 chrt_main 379 369 -10 chpst_main 704 694 -10 chpasswd_main 308 298 -10 chown_main 171 161 -10 chmod_main 158 148 -10 cat_main 428 418 -10 bzip2_main 120 110 -10 blkdiscard_main 264 254 -10 base64_main 221 211 -10 arping_main 1665 1655 -10 ar_main 556 546 -10 adjtimex_main 406 396 -10 adduser_main 882 872 -10 addgroup_main 411 401 -10 acpid_main 1198 1188 -10 optstring 11 - -11 opt_string 18 - -18 OPT_STR 25 - -25 ubi_tools_main 1288 1258 -30 ls_options 31 - -31 ------------------------------------------------------------------------------ (add/remove: 0/6 grow/shrink: 3/129 up/down: 86/-1383) Total: -1297 bytes text data bss dec hex filename 915428 485 6876 922789 e14a5 busybox_old 914629 485 6872 921986 e1182 busybox_unstripped Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2017-08-09 01:25:02 +05:30
"\0" "s2" /* -s means -2 (compatibility) */
);
#if ENABLE_FEATURE_BZIP2_DECOMPRESS /* bunzip2_main may not be visible... */
if (opt & (BBUNPK_OPT_DECOMPRESS|BBUNPK_OPT_TEST)) /* -d and/or -t */
return bunzip2_main(argc, argv);
#else
/* clear "decompress" and "test" bits (or bbunpack() can get confused) */
/* in !BZIP2_DECOMPRESS config, these bits are -zs and are unused */
option_mask32 = opt & ~(BBUNPK_OPT_DECOMPRESS|BBUNPK_OPT_TEST);
#endif
argv += optind;
return bbunpack(argv, compressStream, append_ext, "bz2");
}