busybox/coreutils/expand.c

254 lines
6.2 KiB
C
Raw Normal View History

/* expand - convert tabs to spaces
* unexpand - convert spaces to tabs
*
* Copyright (C) 89, 91, 1995-2006 Free Software Foundation, Inc.
*
* Licensed under GPLv2 or later, see file LICENSE in this source tree.
*
* David MacKenzie <djm@gnu.ai.mit.edu>
*
* Options for expand:
* -t num --tabs NUM Convert tabs to num spaces (default 8 spaces).
* -i --initial Only convert initial tabs on each line to spaces.
*
* Options for unexpand:
* -a --all Convert all blanks, instead of just initial blanks.
* -f --first-only Convert only leading sequences of blanks (default).
* -t num --tabs NUM Have tabs num characters apart instead of 8.
*
* Busybox version (C) 2007 by Tito Ragusa <farmatito@tiscali.it>
*
* Caveat: this versions of expand and unexpand don't accept tab lists.
*/
//config:config EXPAND
//config: bool "expand (5.1 kb)"
//config: default y
//config: help
//config: By default, convert all tabs to spaces.
//config:
//config:config UNEXPAND
//config: bool "unexpand (5.3 kb)"
//config: default y
//config: help
//config: By default, convert only leading sequences of blanks to tabs.
//applet:IF_EXPAND(APPLET(expand, BB_DIR_USR_BIN, BB_SUID_DROP))
// APPLET_ODDNAME:name main location suid_type help
//applet:IF_UNEXPAND(APPLET_ODDNAME(unexpand, expand, BB_DIR_USR_BIN, BB_SUID_DROP, unexpand))
//kbuild:lib-$(CONFIG_EXPAND) += expand.o
//kbuild:lib-$(CONFIG_UNEXPAND) += expand.o
//usage:#define expand_trivial_usage
//usage: "[-i] [-t N] [FILE]..."
//usage:#define expand_full_usage "\n\n"
//usage: "Convert tabs to spaces, writing to stdout\n"
//usage: "\n -i Don't convert tabs after non blanks"
//usage: "\n -t Tabstops every N chars"
//usage:#define unexpand_trivial_usage
//usage: "[-fa][-t N] [FILE]..."
//usage:#define unexpand_full_usage "\n\n"
//usage: "Convert spaces to tabs, writing to stdout\n"
//usage: "\n -a Convert all blanks"
//usage: "\n -f Convert only leading blanks"
//usage: "\n -t N Tabstops every N chars"
#include "libbb.h"
#include "unicode.h"
enum {
OPT_INITIAL = 1 << 0,
OPT_TABS = 1 << 1,
OPT_ALL = 1 << 2,
};
//FIXME: does not work properly with input containing NULs
//coreutils 8.30 preserves NULs but treats them as chars of width zero:
//AB<nul><tab>C will expand <tab> to 6 spaces, not 5.
#if ENABLE_EXPAND
static void expand(FILE *file, unsigned tab_size, unsigned opt)
{
for (;;) {
char *line;
char *ptr;
char *ptr_strbeg;
//commented-out code handles NULs, +90 bytes of code, not tested much
// size_t linelen;
// unsigned len = 0;
// linelen = 1024 * 1024;
// line = xmalloc_fgets_str_len(file, "\n", &linelen);
line = xmalloc_fgets(file); //
if (!line)
break;
ptr = ptr_strbeg = line;
for (;;) {
unsigned char c = *ptr;
if (c == '\0') {
// size_t rem = line + linelen - ptr;
// if (rem > 0) {
//# if ENABLE_UNICODE_SUPPORT
// len += unicode_strwidth(ptr_strbeg);
//# else
// len += ptr - ptr_strbeg;
//# endif
// printf("%s%c", ptr_strbeg, '\0');
// memmove(ptr, ptr + 1, rem + 1);
// ptr_strbeg = ptr;
// linelen--;
// continue;
// }
break;
}
if ((opt & OPT_INITIAL) && !isblank(c)) {
/* not space or tab */
break;
}
if (c == '\t') {
unsigned len = 0; //
*ptr = '\0';
# if ENABLE_UNICODE_SUPPORT
len += unicode_strwidth(ptr_strbeg);
# else
len += ptr - ptr_strbeg;
# endif
len = tab_size - (len % tab_size);
/*while (ptr[1] == '\t') { ptr++; len += tab_size; } - can handle many tabs at once */
printf("%s%*s", ptr_strbeg, len, "");
// len = 0;
ptr_strbeg = ptr + 1;
}
ptr++;
}
fputs(ptr_strbeg, stdout);
free(line);
}
}
#endif
#if ENABLE_UNEXPAND
static void unexpand(FILE *file, unsigned tab_size, unsigned opt)
{
char *line;
while ((line = xmalloc_fgets(file)) != NULL) {
char *ptr = line;
unsigned column = 0;
while (*ptr) {
unsigned n;
unsigned len = 0;
while (*ptr == ' ') {
ptr++;
len++;
}
column += len;
if (*ptr == '\t') {
column += tab_size - (column % tab_size);
ptr++;
continue;
}
n = column / tab_size;
if (n) {
len = column = column % tab_size;
while (n--)
putchar('\t');
}
if (!(opt & OPT_ALL) && ptr != line) {
printf("%*s%s", len, "", ptr);
break;
}
n = strcspn(ptr, "\t ");
printf("%*s%.*s", len, "", n, ptr);
# if ENABLE_UNICODE_SUPPORT
{
char c = ptr[n];
ptr[n] = '\0';
len = unicode_strwidth(ptr);
ptr[n] = c;
}
# else
len = n;
# endif
ptr += n;
column = (column + len) % tab_size;
}
free(line);
}
}
#endif
int expand_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
2008-07-05 14:48:54 +05:30
int expand_main(int argc UNUSED_PARAM, char **argv)
{
/* Default 8 spaces for 1 tab */
const char *opt_t = "8";
FILE *file;
unsigned tab_size;
unsigned opt;
int exit_status = EXIT_SUCCESS;
init_unicode();
if (ENABLE_EXPAND && (!ENABLE_UNEXPAND || applet_name[0] == 'e')) {
getopt32: remove applet_long_options FEATURE_GETOPT_LONG made dependent on LONG_OPTS. The folloving options are removed, now LONG_OPTS enables long options for affected applets: FEATURE_ENV_LONG_OPTIONS FEATURE_EXPAND_LONG_OPTIONS FEATURE_UNEXPAND_LONG_OPTIONS FEATURE_MKDIR_LONG_OPTIONS FEATURE_MV_LONG_OPTIONS FEATURE_RMDIR_LONG_OPTIONS FEATURE_ADDGROUP_LONG_OPTIONS FEATURE_ADDUSER_LONG_OPTIONS FEATURE_HWCLOCK_LONG_OPTIONS FEATURE_NSENTER_LONG_OPTS FEATURE_CHCON_LONG_OPTIONS FEATURE_RUNCON_LONG_OPTIONS They either had a small number of long options, or their long options are essential. Example: upstream addgroup and adduser have ONLY longopts, we should probably go further and get rid of non-standard short options. To this end, make addgroup and adduser "select LONG_OPTS". We had this breakage caused by us even in our own package! #if ENABLE_LONG_OPTS || !ENABLE_ADDGROUP /* We try to use --gid, not -g, because "standard" addgroup * has no short option -g, it has only long --gid. */ argv[1] = (char*)"--gid"; #else /* Breaks if system in fact does NOT use busybox addgroup */ argv[1] = (char*)"-g"; #endif xargs: its lone longopt no longer depends on DESKTOP, only on LONG_OPTS. hwclock TODO: get rid of incompatible -t, -l aliases to --systz, --localtime Shorten help texts by omitting long option when short opt alternative exists. Reduction of size comes from the fact that store of an immediate (an address of longopts) to a fixed address (global variable) is a longer insn than pushing that immediate or passing it in a register. This effect is CPU-agnostic. function old new delta getopt32 1350 22 -1328 vgetopt32 - 1318 +1318 getopt32long - 24 +24 tftpd_main 562 567 +5 scan_recursive 376 380 +4 collect_cpu 545 546 +1 date_main 1096 1095 -1 hostname_main 262 259 -3 uname_main 259 255 -4 setpriv_main 362 358 -4 rmdir_main 191 187 -4 mv_main 562 558 -4 ipcalc_main 548 544 -4 ifenslave_main 641 637 -4 gzip_main 192 188 -4 gunzip_main 77 73 -4 fsfreeze_main 81 77 -4 flock_main 318 314 -4 deluser_main 337 333 -4 cp_main 374 370 -4 chown_main 175 171 -4 applet_long_options 4 - -4 xargs_main 894 889 -5 wget_main 2540 2535 -5 udhcpc_main 2767 2762 -5 touch_main 436 431 -5 tar_main 1014 1009 -5 start_stop_daemon_main 1033 1028 -5 sed_main 682 677 -5 script_main 1082 1077 -5 run_parts_main 330 325 -5 rtcwake_main 459 454 -5 od_main 2169 2164 -5 nl_main 201 196 -5 modprobe_main 773 768 -5 mkdir_main 160 155 -5 ls_main 568 563 -5 install_main 773 768 -5 hwclock_main 411 406 -5 getopt_main 622 617 -5 fstrim_main 256 251 -5 env_main 198 193 -5 dumpleases_main 635 630 -5 dpkg_main 3991 3986 -5 diff_main 1355 1350 -5 cryptpw_main 233 228 -5 cpio_main 593 588 -5 conspy_main 1135 1130 -5 chpasswd_main 313 308 -5 adduser_main 887 882 -5 addgroup_main 416 411 -5 ftpgetput_main 351 345 -6 get_terminal_width_height 242 234 -8 expand_main 690 680 -10 static.expand_longopts 18 - -18 static.unexpand_longopts 27 - -27 mkdir_longopts 28 - -28 env_longopts 30 - -30 static.ifenslave_longopts 34 - -34 mv_longopts 46 - -46 static.rmdir_longopts 48 - -48 packed_usage 31739 31687 -52 ------------------------------------------------------------------------------ (add/remove: 2/8 grow/shrink: 3/49 up/down: 1352/-1840) Total: -488 bytes text data bss dec hex filename 915681 485 6880 923046 e15a6 busybox_old 915428 485 6876 922789 e14a5 busybox_unstripped Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2017-08-08 20:08:18 +05:30
opt = getopt32long(argv, "it:",
"initial\0" No_argument "i"
"tabs\0" Required_argument "t"
, &opt_t
);
} else {
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 = getopt32long(argv, "^"
"ft:a"
"\0"
"ta" /* -t NUM sets -a */,
"first-only\0" No_argument "f"
getopt32: remove applet_long_options FEATURE_GETOPT_LONG made dependent on LONG_OPTS. The folloving options are removed, now LONG_OPTS enables long options for affected applets: FEATURE_ENV_LONG_OPTIONS FEATURE_EXPAND_LONG_OPTIONS FEATURE_UNEXPAND_LONG_OPTIONS FEATURE_MKDIR_LONG_OPTIONS FEATURE_MV_LONG_OPTIONS FEATURE_RMDIR_LONG_OPTIONS FEATURE_ADDGROUP_LONG_OPTIONS FEATURE_ADDUSER_LONG_OPTIONS FEATURE_HWCLOCK_LONG_OPTIONS FEATURE_NSENTER_LONG_OPTS FEATURE_CHCON_LONG_OPTIONS FEATURE_RUNCON_LONG_OPTIONS They either had a small number of long options, or their long options are essential. Example: upstream addgroup and adduser have ONLY longopts, we should probably go further and get rid of non-standard short options. To this end, make addgroup and adduser "select LONG_OPTS". We had this breakage caused by us even in our own package! #if ENABLE_LONG_OPTS || !ENABLE_ADDGROUP /* We try to use --gid, not -g, because "standard" addgroup * has no short option -g, it has only long --gid. */ argv[1] = (char*)"--gid"; #else /* Breaks if system in fact does NOT use busybox addgroup */ argv[1] = (char*)"-g"; #endif xargs: its lone longopt no longer depends on DESKTOP, only on LONG_OPTS. hwclock TODO: get rid of incompatible -t, -l aliases to --systz, --localtime Shorten help texts by omitting long option when short opt alternative exists. Reduction of size comes from the fact that store of an immediate (an address of longopts) to a fixed address (global variable) is a longer insn than pushing that immediate or passing it in a register. This effect is CPU-agnostic. function old new delta getopt32 1350 22 -1328 vgetopt32 - 1318 +1318 getopt32long - 24 +24 tftpd_main 562 567 +5 scan_recursive 376 380 +4 collect_cpu 545 546 +1 date_main 1096 1095 -1 hostname_main 262 259 -3 uname_main 259 255 -4 setpriv_main 362 358 -4 rmdir_main 191 187 -4 mv_main 562 558 -4 ipcalc_main 548 544 -4 ifenslave_main 641 637 -4 gzip_main 192 188 -4 gunzip_main 77 73 -4 fsfreeze_main 81 77 -4 flock_main 318 314 -4 deluser_main 337 333 -4 cp_main 374 370 -4 chown_main 175 171 -4 applet_long_options 4 - -4 xargs_main 894 889 -5 wget_main 2540 2535 -5 udhcpc_main 2767 2762 -5 touch_main 436 431 -5 tar_main 1014 1009 -5 start_stop_daemon_main 1033 1028 -5 sed_main 682 677 -5 script_main 1082 1077 -5 run_parts_main 330 325 -5 rtcwake_main 459 454 -5 od_main 2169 2164 -5 nl_main 201 196 -5 modprobe_main 773 768 -5 mkdir_main 160 155 -5 ls_main 568 563 -5 install_main 773 768 -5 hwclock_main 411 406 -5 getopt_main 622 617 -5 fstrim_main 256 251 -5 env_main 198 193 -5 dumpleases_main 635 630 -5 dpkg_main 3991 3986 -5 diff_main 1355 1350 -5 cryptpw_main 233 228 -5 cpio_main 593 588 -5 conspy_main 1135 1130 -5 chpasswd_main 313 308 -5 adduser_main 887 882 -5 addgroup_main 416 411 -5 ftpgetput_main 351 345 -6 get_terminal_width_height 242 234 -8 expand_main 690 680 -10 static.expand_longopts 18 - -18 static.unexpand_longopts 27 - -27 mkdir_longopts 28 - -28 env_longopts 30 - -30 static.ifenslave_longopts 34 - -34 mv_longopts 46 - -46 static.rmdir_longopts 48 - -48 packed_usage 31739 31687 -52 ------------------------------------------------------------------------------ (add/remove: 2/8 grow/shrink: 3/49 up/down: 1352/-1840) Total: -488 bytes text data bss dec hex filename 915681 485 6880 923046 e15a6 busybox_old 915428 485 6876 922789 e14a5 busybox_unstripped Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
2017-08-08 20:08:18 +05:30
"tabs\0" Required_argument "t"
"all\0" No_argument "a"
, &opt_t
);
/* -t implies -a, but an explicit -f overrides */
if (opt & OPT_INITIAL) opt &= ~OPT_ALL;
}
tab_size = xatou_range(opt_t, 1, UINT_MAX);
argv += optind;
if (!*argv) {
*--argv = (char*)bb_msg_standard_input;
}
do {
file = fopen_or_warn_stdin(*argv);
if (!file) {
exit_status = EXIT_FAILURE;
continue;
}
if (ENABLE_EXPAND && (!ENABLE_UNEXPAND || applet_name[0] == 'e'))
IF_EXPAND(expand(file, tab_size, opt));
else
IF_UNEXPAND(unexpand(file, tab_size, opt));
/* Check and close the file */
if (fclose_if_not_stdin(file)) {
bb_simple_perror_msg(*argv);
exit_status = EXIT_FAILURE;
}
/* If stdin also clear EOF */
2007-08-16 16:05:17 +05:30
if (file == stdin)
clearerr(file);
} while (*++argv);
/* Now close stdin also */
/* (if we didn't read from it, it's a no-op) */
if (fclose(stdin))
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_and_die(bb_msg_standard_input);
fflush_stdout_and_exit(exit_status);
}