| {"instruction": "What does the command `sha384sum` do?", "output": "sha384sum - compute and check SHA384 message digest"} | |
| {"instruction": "How is the `sha384sum` used?", "output": "sha384sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `sha384sum`?", "output": "Print or check SHA384 (384-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n -b, --binary\n read in binary mode\n\n -c, --check\n read checksums from the FILEs and check them\n\n --tag create a BSD-style checksum\n\n -t, --text\n read in text mode (default)\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The sums are computed as described in FIPS-180-2. When checking, the input should be a former output of this\n program. The default mode is to print a line with: checksum, a space, a character indicating input mode ('*'\n for binary, ' ' for text or where binary is insignificant), and name for each FILE.\n\n Note: There is no difference between binary mode and text mode on GNU systems."} | |
| {"instruction": "What does the command `realpath` do?", "output": "realpath - print the resolved path"} | |
| {"instruction": "How is the `realpath` used?", "output": "realpath [OPTION]... FILE..."} | |
| {"instruction": "What is the detailed desciption of the `realpath`?", "output": "Print the resolved absolute file name; all but the last component must exist\n\n -e, --canonicalize-existing\n all components of the path must exist\n\n -m, --canonicalize-missing\n no path components need exist or be a directory\n\n -L, --logical\n resolve '..' components before symlinks\n\n -P, --physical\n resolve symlinks as encountered (default)\n\n -q, --quiet\n suppress most error messages\n\n --relative-to=DIR\n print the resolved path relative to DIR\n\n --relative-base=DIR\n print absolute paths unless paths below DIR\n\n -s, --strip, --no-symlinks\n don't expand symlinks\n\n -z, --zero\n end each output line with NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `expr` do?", "output": "expr - evaluate expressions"} | |
| {"instruction": "How is the `expr` used?", "output": "expr EXPRESSION\n expr OPTION"} | |
| {"instruction": "What is the detailed desciption of the `expr`?", "output": "--help display this help and exit\n\n --version\n output version information and exit\n\n Print the value of EXPRESSION to standard output. A blank line below separates increasing precedence groups.\n EXPRESSION may be:\n\n ARG1 | ARG2\n ARG1 if it is neither null nor 0, otherwise ARG2\n\n ARG1 & ARG2\n ARG1 if neither argument is null or 0, otherwise 0\n\n ARG1 < ARG2\n ARG1 is less than ARG2\n\n ARG1 <= ARG2\n ARG1 is less than or equal to ARG2\n\n ARG1 = ARG2\n ARG1 is equal to ARG2\n\n ARG1 != ARG2\n ARG1 is unequal to ARG2\n\n ARG1 >= ARG2\n ARG1 is greater than or equal to ARG2\n\n ARG1 > ARG2\n ARG1 is greater than ARG2\n\n ARG1 + ARG2\n arithmetic sum of ARG1 and ARG2\n\n ARG1 - ARG2\n arithmetic difference of ARG1 and ARG2\n\n ARG1 * ARG2\n arithmetic product of ARG1 and ARG2\n\n ARG1 / ARG2\n arithmetic quotient of ARG1 divided by ARG2\n\n ARG1 % ARG2\n arithmetic remainder of ARG1 divided by ARG2\n\n STRING : REGEXP\n anchored pattern match of REGEXP in STRING\n\n match STRING REGEXP\n same as STRING : REGEXP\n\n substr STRING POS LENGTH\n substring of STRING, POS counted from 1\n\n index STRING CHARS\n index in STRING where any CHARS is found, or 0\n\n length STRING\n length of STRING\n\n + TOKEN\n interpret TOKEN as a string, even if it is a\n\n keyword like 'match' or an operator like '/'\n\n ( EXPRESSION )\n value of EXPRESSION\n\n Beware that many operators need to be escaped or quoted for shells. Comparisons are arithmetic if both ARGs are\n numbers, else lexicographical. Pattern matches return the string matched between \\( and \\) or null; if \\( and\n \\) are not used, they return the number of characters matched or 0.\n\n Exit status is 0 if EXPRESSION is neither null nor 0, 1 if EXPRESSION is null or 0, 2 if EXPRESSION is syntacti\u2010\n cally invalid, and 3 if an error occurred."} | |
| {"instruction": "What does the command `wc` do?", "output": "wc - print newline, word, and byte counts for each file"} | |
| {"instruction": "How is the `wc` used?", "output": "wc [OPTION]... [FILE]...\n wc [OPTION]... --files0-from=F"} | |
| {"instruction": "What is the detailed desciption of the `wc`?", "output": "Print newline, word, and byte counts for each FILE, and a total line if more than one FILE is specified. A word\n is a non-zero-length sequence of printable characters delimited by white space.\n\n With no FILE, or when FILE is -, read standard input.\n\n The options below may be used to select which counts are printed, always in the following order: newline, word,\n character, byte, maximum line length.\n\n -c, --bytes\n print the byte counts\n\n -m, --chars\n print the character counts\n\n -l, --lines\n print the newline counts\n\n --files0-from=F\n read input from the files specified by NUL-terminated names in file F; If F is - then read names from\n standard input\n\n -L, --max-line-length\n print the maximum display width\n\n -w, --words\n print the word counts\n\n --total=WHEN\n when to print a line with total counts; WHEN can be: auto, always, only, never\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `nproc` do?", "output": "nproc - print the number of processing units available"} | |
| {"instruction": "How is the `nproc` used?", "output": "nproc [OPTION]..."} | |
| {"instruction": "What is the detailed desciption of the `nproc`?", "output": "Print the number of processing units available to the current process, which may be less than the number of on\u2010\n line processors\n\n --all print the number of installed processors\n\n --ignore=N\n if possible, exclude N processing units\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `fold` do?", "output": "fold - wrap each input line to fit in specified width"} | |
| {"instruction": "How is the `fold` used?", "output": "fold [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `fold`?", "output": "Wrap input lines in each FILE, writing to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -b, --bytes\n count bytes rather than columns\n\n -s, --spaces\n break at spaces\n\n -w, --width=WIDTH\n use WIDTH columns instead of 80\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `logname` do?", "output": "logname - print user\u00b4s login name"} | |
| {"instruction": "How is the `logname` used?", "output": "logname [OPTION]"} | |
| {"instruction": "What is the detailed desciption of the `logname`?", "output": "Print the user's login name.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `expand` do?", "output": "expand - convert tabs to spaces"} | |
| {"instruction": "How is the `expand` used?", "output": "expand [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `expand`?", "output": "Convert tabs in each FILE to spaces, writing to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -i, --initial\n do not convert tabs after non blanks\n\n -t, --tabs=N\n have tabs N characters apart, not 8\n\n -t, --tabs=LIST\n use comma separated list of tab positions. The last specified position can be prefixed with '/' to spec\u2010\n ify a tab size to use after the last explicitly specified tab stop. Also a prefix of '+' can be used to\n align remaining tab stops relative to the last specified tab stop instead of the first column\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `uptime` do?", "output": "uptime - Tell how long the system has been running."} | |
| {"instruction": "How is the `uptime` used?", "output": "uptime [options]"} | |
| {"instruction": "What is the detailed desciption of the `uptime`?", "output": "uptime gives a one line display of the following information. The current time, how long the system has been\n running, how many users are currently logged on, and the system load averages for the past 1, 5, and 15 minutes.\n\n This is the same information contained in the header line displayed by w(1).\n\n System load averages is the average number of processes that are either in a runnable or uninterruptable state.\n A process in a runnable state is either using the CPU or waiting to use the CPU. A process in uninterruptable\n state is waiting for some I/O access, eg waiting for disk. The averages are taken over the three time inter\u2010\n vals. Load averages are not normalized for the number of CPUs in a system, so a load average of 1 means a sin\u2010\n gle CPU system is loaded all the time while on a 4 CPU system it means it was idle 75% of the time."} | |
| {"instruction": "What does the command `md5sum` do?", "output": "md5sum - compute and check MD5 message digest"} | |
| {"instruction": "How is the `md5sum` used?", "output": "md5sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `md5sum`?", "output": "Print or check MD5 (128-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n -b, --binary\n read in binary mode\n\n -c, --check\n read checksums from the FILEs and check them\n\n --tag create a BSD-style checksum\n\n -t, --text\n read in text mode (default)\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The sums are computed as described in RFC 1321. When checking, the input should be a former output of this pro\u2010\n gram. The default mode is to print a line with: checksum, a space, a character indicating input mode ('*' for\n binary, ' ' for text or where binary is insignificant), and name for each FILE.\n\n Note: There is no difference between binary mode and text mode on GNU systems."} | |
| {"instruction": "What does the command `dd` do?", "output": "dd - convert and copy a file"} | |
| {"instruction": "How is the `dd` used?", "output": "dd [OPERAND]...\n dd OPTION"} | |
| {"instruction": "What is the detailed desciption of the `dd`?", "output": "Copy a file, converting and formatting according to the operands.\n\n bs=BYTES\n read and write up to BYTES bytes at a time (default: 512); overrides ibs and\n obs\n\n cbs=BYTES\n convert BYTES bytes at a time\n\n conv=CONVS\n convert the file as per the comma separated symbol list\n\n count=N\n copy only N input blocks\n\n ibs=BYTES\n read up to BYTES bytes at a time (default: 512)\n\n if=FILE\n read from FILE instead of stdin\n\n iflag=FLAGS\n read as per the comma separated symbol list\n\n obs=BYTES\n write BYTES bytes at a time (default: 512)\n\n of=FILE\n write to FILE instead of stdout\n\n oflag=FLAGS\n write as per the comma separated symbol list\n\n seek=N (or oseek=N) skip N obs-sized output blocks\n\n skip=N (or iseek=N) skip N ibs-sized input blocks\n\n status=LEVEL\n The LEVEL of information to print to stderr; 'none' suppresses everything but\n error messages, 'noxfer' suppresses the final transfer statistics, 'progress'\n shows periodic transfer statistics\n\n N and BYTES may be followed by the following multiplicative suffixes: c=1, w=2,\n b=512, kB=1000, K=1024, MB=1000*1000, M=1024*1024, xM=M, GB=1000*1000*1000,\n G=1024*1024*1024, and so on for T, P, E, Z, Y, R, Q. Binary prefixes can be used,\n too: KiB=K, MiB=M, and so on. If N ends in 'B', it counts bytes not blocks.\n\n Each CONV symbol may be:\n\n ascii from EBCDIC to ASCII\n\n ebcdic from ASCII to EBCDIC\n\n ibm from ASCII to alternate EBCDIC\n\n block pad newline-terminated records with spaces to cbs-size\n\n unblock\n replace trailing spaces in cbs-size records with newline\n\n lcase change upper case to lower case\n\n ucase change lower case to upper case\n\n sparse try to seek rather than write all-NUL output blocks\n\n swab swap every pair of input bytes\n\n sync pad every input block with NULs to ibs-size; when used with block or unblock,\n pad with spaces rather than NULs\n\n excl fail if the output file already exists\n\n nocreat\n do not create the output file\n\n notrunc\n do not truncate the output file\n\n noerror\n continue after read errors\n\n fdatasync\n physically write output file data before finishing\n\n fsync likewise, but also write metadata\n\n Each FLAG symbol may be:\n\n append append mode (makes sense only for output; conv=notrunc suggested)\n\n direct use direct I/O for data\n\n directory\n fail unless a directory\n\n dsync use synchronized I/O for data\n\n sync likewise, but also for metadata\n\n fullblock\n accumulate full blocks of input (iflag only)\n\n nonblock\n use non-blocking I/O\n\n noatime\n do not update access time\n\n nocache\n Request to drop cache. See also oflag=sync\n\n noctty do not assign controlling terminal from file\n\n nofollow\n do not follow symlinks\n\n Sending a USR1 signal to a running 'dd' process makes it print I/O statistics to\n standard error and then resume copying.\n\n Options are:\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `mknod` do?", "output": "mknod - make block or character special files"} | |
| {"instruction": "How is the `mknod` used?", "output": "mknod [OPTION]... NAME TYPE [MAJOR MINOR]"} | |
| {"instruction": "What is the detailed desciption of the `mknod`?", "output": "Create the special file NAME of the given TYPE.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -m, --mode=MODE\n set file permission bits to MODE, not a=rw - umask\n\n -Z set the SELinux security context to default type\n\n --context[=CTX]\n like -Z, or if CTX is specified then set the SELinux or SMACK security context to CTX\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Both MAJOR and MINOR must be specified when TYPE is b, c, or u, and they must be omitted when TYPE is p. If MA\u2010\n JOR or MINOR begins with 0x or 0X, it is interpreted as hexadecimal; otherwise, if it begins with 0, as octal;\n otherwise, as decimal. TYPE may be:\n\n b create a block (buffered) special file\n\n c, u create a character (unbuffered) special file\n\n p create a FIFO\n\n NOTE: your shell may have its own version of mknod, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `unlink` do?", "output": "unlink - call the unlink function to remove the specified file"} | |
| {"instruction": "How is the `unlink` used?", "output": "unlink FILE\n unlink OPTION"} | |
| {"instruction": "What is the detailed desciption of the `unlink`?", "output": "Call the unlink function to remove the specified FILE.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `[` do?", "output": "test - check file types and compare values"} | |
| {"instruction": "How is the `[` used?", "output": "test EXPRESSION\n test\n [ EXPRESSION ]\n [ ]\n [ OPTION"} | |
| {"instruction": "What is the detailed desciption of the `[`?", "output": "Exit with the status determined by EXPRESSION.\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n An omitted EXPRESSION defaults to false. Otherwise, EXPRESSION is true or false and sets exit status. It is\n one of:\n\n ( EXPRESSION )\n EXPRESSION is true\n\n ! EXPRESSION\n EXPRESSION is false\n\n EXPRESSION1 -a EXPRESSION2\n both EXPRESSION1 and EXPRESSION2 are true\n\n EXPRESSION1 -o EXPRESSION2\n either EXPRESSION1 or EXPRESSION2 is true\n\n -n STRING\n the length of STRING is nonzero\n\n STRING equivalent to -n STRING\n\n -z STRING\n the length of STRING is zero\n\n STRING1 = STRING2\n the strings are equal\n\n STRING1 != STRING2\n the strings are not equal\n\n INTEGER1 -eq INTEGER2\n INTEGER1 is equal to INTEGER2\n\n INTEGER1 -ge INTEGER2\n INTEGER1 is greater than or equal to INTEGER2\n\n INTEGER1 -gt INTEGER2\n INTEGER1 is greater than INTEGER2\n\n INTEGER1 -le INTEGER2\n INTEGER1 is less than or equal to INTEGER2\n\n INTEGER1 -lt INTEGER2\n INTEGER1 is less than INTEGER2\n\n INTEGER1 -ne INTEGER2\n INTEGER1 is not equal to INTEGER2\n\n FILE1 -ef FILE2\n FILE1 and FILE2 have the same device and inode numbers\n\n FILE1 -nt FILE2\n FILE1 is newer (modification date) than FILE2\n\n FILE1 -ot FILE2\n FILE1 is older than FILE2\n\n -b FILE\n FILE exists and is block special\n\n -c FILE\n FILE exists and is character special\n\n -d FILE\n FILE exists and is a directory\n\n -e FILE\n FILE exists\n\n -f FILE\n FILE exists and is a regular file\n\n -g FILE\n FILE exists and is set-group-ID\n\n -G FILE\n FILE exists and is owned by the effective group ID\n\n -h FILE\n FILE exists and is a symbolic link (same as -L)\n\n -k FILE\n FILE exists and has its sticky bit set\n\n -L FILE\n FILE exists and is a symbolic link (same as -h)\n\n -N FILE\n FILE exists and has been modified since it was last read\n\n -O FILE\n FILE exists and is owned by the effective user ID\n\n -p FILE\n FILE exists and is a named pipe\n\n -r FILE\n FILE exists and the user has read access\n\n -s FILE\n FILE exists and has a size greater than zero\n\n -S FILE\n FILE exists and is a socket\n\n -t FD file descriptor FD is opened on a terminal\n\n -u FILE\n FILE exists and its set-user-ID bit is set\n\n -w FILE\n FILE exists and the user has write access\n\n -x FILE\n FILE exists and the user has execute (or search) access\n\n Except for -h and -L, all FILE-related tests dereference symbolic links. Beware that parentheses need to be es\u2010\n caped (e.g., by backslashes) for shells. INTEGER may also be -l STRING, which evaluates to the length of\n STRING.\n\n NOTE: Binary -a and -o are inherently ambiguous. Use 'test EXPR1 && test EXPR2' or 'test EXPR1 || test EXPR2'\n instead.\n\n NOTE: [ honors the --help and --version options, but test does not. test treats each of those as it treats any\n other nonempty STRING.\n\n NOTE: your shell may have its own version of test and/or [, which usually supersedes the version described here.\n Please refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `chown` do?", "output": "chown - change file owner and group"} | |
| {"instruction": "How is the `chown` used?", "output": "chown [OPTION]... [OWNER][:[GROUP]] FILE...\n chown [OPTION]... --reference=RFILE FILE..."} | |
| {"instruction": "What is the detailed desciption of the `chown`?", "output": "This manual page documents the GNU version of chown. chown changes the user and/or\n group ownership of each given file. If only an owner (a user name or numeric user\n ID) is given, that user is made the owner of each given file, and the files' group\n is not changed. If the owner is followed by a colon and a group name (or numeric\n group ID), with no spaces between them, the group ownership of the files is changed\n as well. If a colon but no group name follows the user name, that user is made the\n owner of the files and the group of the files is changed to that user's login group.\n If the colon and group are given, but the owner is omitted, only the group of the\n files is changed; in this case, chown performs the same function as chgrp. If only\n a colon is given, or if the entire operand is empty, neither the owner nor the group\n is changed."} | |
| {"instruction": "What does the command `basename` do?", "output": "basename - strip directory and suffix from filenames"} | |
| {"instruction": "How is the `basename` used?", "output": "basename NAME [SUFFIX]\n basename OPTION... NAME..."} | |
| {"instruction": "What is the detailed desciption of the `basename`?", "output": "Print NAME with any leading directory components removed. If specified, also remove a trailing SUFFIX.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --multiple\n support multiple arguments and treat each as a NAME\n\n -s, --suffix=SUFFIX\n remove a trailing SUFFIX; implies -a\n\n -z, --zero\n end each output line with NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `pr` do?", "output": "pr - convert text files for printing"} | |
| {"instruction": "How is the `pr` used?", "output": "pr [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `pr`?", "output": "Paginate or columnate FILE(s) for printing.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n +FIRST_PAGE[:LAST_PAGE], --pages=FIRST_PAGE[:LAST_PAGE]\n begin [stop] printing with page FIRST_[LAST_]PAGE\n\n -COLUMN, --columns=COLUMN\n output COLUMN columns and print columns down, unless -a is used. Balance number of lines in the columns\n on each page\n\n -a, --across\n print columns across rather than down, used together with -COLUMN\n\n -c, --show-control-chars\n use hat notation (^G) and octal backslash notation\n\n -d, --double-space\n double space the output\n\n -D, --date-format=FORMAT\n use FORMAT for the header date\n\n -e[CHAR[WIDTH]], --expand-tabs[=CHAR[WIDTH]]\n expand input CHARs (TABs) to tab WIDTH (8)\n\n -F, -f, --form-feed\n use form feeds instead of newlines to separate pages (by a 3-line page header with -F or a 5-line header\n and trailer without -F)\n\n -h, --header=HEADER\n use a centered HEADER instead of filename in page header, -h \"\" prints a blank line, don't use -h\"\"\n\n -i[CHAR[WIDTH]], --output-tabs[=CHAR[WIDTH]]\n replace spaces with CHARs (TABs) to tab WIDTH (8)\n\n -J, --join-lines\n merge full lines, turns off -W line truncation, no column alignment, --sep-string[=STRING] sets separa\u2010\n tors\n\n -l, --length=PAGE_LENGTH\n set the page length to PAGE_LENGTH (66) lines (default number of lines of text 56, and with -F 63). im\u2010\n plies -t if PAGE_LENGTH <= 10\n\n -m, --merge\n print all files in parallel, one in each column, truncate lines, but join lines of full length with -J\n\n -n[SEP[DIGITS]], --number-lines[=SEP[DIGITS]]\n number lines, use DIGITS (5) digits, then SEP (TAB), default counting starts with 1st line of input file\n\n -N, --first-line-number=NUMBER\n start counting with NUMBER at 1st line of first page printed (see +FIRST_PAGE)\n\n -o, --indent=MARGIN\n offset each line with MARGIN (zero) spaces, do not affect -w or -W, MARGIN will be added to PAGE_WIDTH\n\n -r, --no-file-warnings\n omit warning when a file cannot be opened\n\n -s[CHAR], --separator[=CHAR]\n separate columns by a single character, default for CHAR is the <TAB> character without -w and 'no char'\n with -w. -s[CHAR] turns off line truncation of all 3 column options (-COLUMN|-a -COLUMN|-m) except -w is\n set\n\n -S[STRING], --sep-string[=STRING]\n separate columns by STRING, without -S: Default separator <TAB> with -J and <space> otherwise (same as\n -S\" \"), no effect on column options\n\n -t, --omit-header\n omit page headers and trailers; implied if PAGE_LENGTH <= 10\n\n -T, --omit-pagination\n omit page headers and trailers, eliminate any pagination by form feeds set in input files\n\n -v, --show-nonprinting\n use octal backslash notation\n\n -w, --width=PAGE_WIDTH\n set page width to PAGE_WIDTH (72) characters for multiple text-column output only, -s[char] turns off\n (72)\n\n -W, --page-width=PAGE_WIDTH\n set page width to PAGE_WIDTH (72) characters always, truncate lines, except -J option is set, no inter\u2010\n ference with -S or -s\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `fmt` do?", "output": "fmt - simple optimal text formatter"} | |
| {"instruction": "How is the `fmt` used?", "output": "fmt [-WIDTH] [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `fmt`?", "output": "Reformat each paragraph in the FILE(s), writing to standard output. The option -WIDTH is an abbreviated form of\n --width=DIGITS.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -c, --crown-margin\n preserve indentation of first two lines\n\n -p, --prefix=STRING\n reformat only lines beginning with STRING, reattaching the prefix to reformatted lines\n\n -s, --split-only\n split long lines, but do not refill\n\n -t, --tagged-paragraph\n indentation of first line different from second\n\n -u, --uniform-spacing\n one space between words, two after sentences\n\n -w, --width=WIDTH\n maximum line width (default of 75 columns)\n\n -g, --goal=WIDTH\n goal width (default of 93% of width)\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `who` do?", "output": "who - show who is logged on"} | |
| {"instruction": "How is the `who` used?", "output": "who [OPTION]... [ FILE | ARG1 ARG2 ]"} | |
| {"instruction": "What is the detailed desciption of the `who`?", "output": "Print information about users who are currently logged in.\n\n -a, --all\n same as -b -d --login -p -r -t -T -u\n\n -b, --boot\n time of last system boot\n\n -d, --dead\n print dead processes\n\n -H, --heading\n print line of column headings\n\n -l, --login\n print system login processes\n\n --lookup\n attempt to canonicalize hostnames via DNS\n\n -m only hostname and user associated with stdin\n\n -p, --process\n print active processes spawned by init\n\n -q, --count\n all login names and number of users logged on\n\n -r, --runlevel\n print current runlevel\n\n -s, --short\n print only name, line, and time (default)\n\n -t, --time\n print last system clock change\n\n -T, -w, --mesg\n add user's message status as +, - or ?\n\n -u, --users\n list users logged in\n\n --message\n same as -T\n\n --writable\n same as -T\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If FILE is not specified, use /var/run/utmp. /var/log/wtmp as FILE is common. If ARG1 ARG2 given, -m presumed:\n 'am i' or 'mom likes' are usual."} | |
| {"instruction": "What does the command `id` do?", "output": "id - print real and effective user and group IDs"} | |
| {"instruction": "How is the `id` used?", "output": "id [OPTION]... [USER]..."} | |
| {"instruction": "What is the detailed desciption of the `id`?", "output": "Print user and group information for each specified USER, or (when USER omitted) for the current process.\n\n -a ignore, for compatibility with other versions\n\n -Z, --context\n print only the security context of the process\n\n -g, --group\n print only the effective group ID\n\n -G, --groups\n print all group IDs\n\n -n, --name\n print a name instead of a number, for -ugG\n\n -r, --real\n print the real ID instead of the effective ID, with -ugG\n\n -u, --user\n print only the effective user ID\n\n -z, --zero\n delimit entries with NUL characters, not whitespace;\n\n not permitted in default format\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Without any OPTION, print some useful set of identified information."} | |
| {"instruction": "What does the command `mkdir` do?", "output": "mkdir - make directories"} | |
| {"instruction": "How is the `mkdir` used?", "output": "mkdir [OPTION]... DIRECTORY..."} | |
| {"instruction": "What is the detailed desciption of the `mkdir`?", "output": "Create the DIRECTORY(ies), if they do not already exist.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -m, --mode=MODE\n set file mode (as in chmod), not a=rwx - umask\n\n -p, --parents\n no error if existing, make parent directories as needed, with their file modes unaffected by any -m op\u2010\n tion.\n\n -v, --verbose\n print a message for each created directory\n\n -Z set SELinux security context of each created directory to the default type\n\n --context[=CTX]\n like -Z, or if CTX is specified then set the SELinux or SMACK security context to CTX\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `head` do?", "output": "head - output the first part of files"} | |
| {"instruction": "How is the `head` used?", "output": "head [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `head`?", "output": "Print the first 10 lines of each FILE to standard output. With more than one FILE, precede each with a header\n giving the file name.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -c, --bytes=[-]NUM\n print the first NUM bytes of each file; with the leading '-', print all but the last NUM bytes of each\n file\n\n -n, --lines=[-]NUM\n print the first NUM lines instead of the first 10; with the leading '-', print all but the last NUM lines\n of each file\n\n -q, --quiet, --silent\n never print headers giving file names\n\n -v, --verbose\n always print headers giving file names\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n NUM may have a multiplier suffix: b 512, kB 1000, K 1024, MB 1000*1000, M 1024*1024, GB 1000*1000*1000, G\n 1024*1024*1024, and so on for T, P, E, Z, Y, R, Q. Binary prefixes can be used, too: KiB=K, MiB=M, and so on."} | |
| {"instruction": "What does the command `date` do?", "output": "date - print or set the system date and time"} | |
| {"instruction": "How is the `date` used?", "output": "date [OPTION]... [+FORMAT]\n date [-u|--utc|--universal] [MMDDhhmm[[CC]YY][.ss]]"} | |
| {"instruction": "What is the detailed desciption of the `date`?", "output": "Display date and time in the given FORMAT. With -s, or with [MMDDhhmm[[CC]YY][.ss]], set the date and time.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -d, --date=STRING\n display time described by STRING, not 'now'\n\n --debug\n annotate the parsed date, and warn about questionable usage to stderr\n\n -f, --file=DATEFILE\n like --date; once for each line of DATEFILE\n\n -I[FMT], --iso-8601[=FMT]\n output date/time in ISO 8601 format. FMT='date' for date only (the default), 'hours', 'minutes', 'sec\u2010\n onds', or 'ns' for date and time to the indicated precision. Example: 2006-08-14T02:34:56-06:00\n\n --resolution\n output the available resolution of timestamps Example: 0.000000001\n\n -R, --rfc-email\n output date and time in RFC 5322 format. Example: Mon, 14 Aug 2006 02:34:56 -0600\n\n --rfc-3339=FMT\n output date/time in RFC 3339 format. FMT='date', 'seconds', or 'ns' for date and time to the indicated\n precision. Example: 2006-08-14 02:34:56-06:00\n\n -r, --reference=FILE\n display the last modification time of FILE\n\n -s, --set=STRING\n set time described by STRING\n\n -u, --utc, --universal\n print or set Coordinated Universal Time (UTC)\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n All options that specify the date to display are mutually exclusive. I.e.: --date, --file, --reference, --reso\u2010\n lution.\n\n FORMAT controls the output. Interpreted sequences are:\n\n %% a literal %\n\n %a locale's abbreviated weekday name (e.g., Sun)\n\n %A locale's full weekday name (e.g., Sunday)\n\n %b locale's abbreviated month name (e.g., Jan)\n\n %B locale's full month name (e.g., January)\n\n %c locale's date and time (e.g., Thu Mar 3 23:05:25 2005)\n\n %C century; like %Y, except omit last two digits (e.g., 20)\n\n %d day of month (e.g., 01)\n\n %D date; same as %m/%d/%y\n\n %e day of month, space padded; same as %_d\n\n %F full date; like %+4Y-%m-%d\n\n %g last two digits of year of ISO week number (see %G)\n\n %G year of ISO week number (see %V); normally useful only with %V\n\n %h same as %b\n\n %H hour (00..23)\n\n %I hour (01..12)\n\n %j day of year (001..366)\n\n %k hour, space padded ( 0..23); same as %_H\n\n %l hour, space padded ( 1..12); same as %_I\n\n %m month (01..12)\n\n %M minute (00..59)\n\n %n a newline\n\n %N nanoseconds (000000000..999999999)\n\n %p locale's equivalent of either AM or PM; blank if not known\n\n %P like %p, but lower case\n\n %q quarter of year (1..4)\n\n %r locale's 12-hour clock time (e.g., 11:11:04 PM)\n\n %R 24-hour hour and minute; same as %H:%M\n\n %s seconds since the Epoch (1970-01-01 00:00 UTC)\n\n %S second (00..60)\n\n %t a tab\n\n %T time; same as %H:%M:%S\n\n %u day of week (1..7); 1 is Monday\n\n %U week number of year, with Sunday as first day of week (00..53)\n\n %V ISO week number, with Monday as first day of week (01..53)\n\n %w day of week (0..6); 0 is Sunday\n\n %W week number of year, with Monday as first day of week (00..53)\n\n %x locale's date representation (e.g., 12/31/99)\n\n %X locale's time representation (e.g., 23:13:48)\n\n %y last two digits of year (00..99)\n\n %Y year\n\n %z +hhmm numeric time zone (e.g., -0400)\n\n %:z +hh:mm numeric time zone (e.g., -04:00)\n\n %::z +hh:mm:ss numeric time zone (e.g., -04:00:00)\n\n %:::z numeric time zone with : to necessary precision (e.g., -04, +05:30)\n\n %Z alphabetic time zone abbreviation (e.g., EDT)\n\n By default, date pads numeric fields with zeroes. The following optional flags may follow '%':\n\n - (hyphen) do not pad the field\n\n _ (underscore) pad with spaces\n\n 0 (zero) pad with zeros\n\n + pad with zeros, and put '+' before future years with >4 digits\n\n ^ use upper case if possible\n\n # use opposite case if possible\n\n After any flags comes an optional field width, as a decimal number; then an optional modifier, which is either E\n to use the locale's alternate representations if available, or O to use the locale's alternate numeric symbols\n if available."} | |
| {"instruction": "What does the command `sync` do?", "output": "sync - Synchronize cached writes to persistent storage"} | |
| {"instruction": "How is the `sync` used?", "output": "sync [OPTION] [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `sync`?", "output": "Synchronize cached writes to persistent storage\n\n If one or more files are specified, sync only them, or their containing file systems.\n\n -d, --data\n sync only file data, no unneeded metadata\n\n -f, --file-system\n sync the file systems that contain the files\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `nohup` do?", "output": "nohup - run a command immune to hangups, with output to a non-tty"} | |
| {"instruction": "How is the `nohup` used?", "output": "nohup COMMAND [ARG]...\n nohup OPTION"} | |
| {"instruction": "What is the detailed desciption of the `nohup`?", "output": "Run COMMAND, ignoring hangup signals.\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If standard input is a terminal, redirect it from an unreadable file. If standard output is a terminal, append\n output to 'nohup.out' if possible, '$HOME/nohup.out' otherwise. If standard error is a terminal, redirect it to\n standard output. To save output to FILE, use 'nohup COMMAND > FILE'.\n\n NOTE: your shell may have its own version of nohup, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports.\n\n Exit status:\n 125 if the nohup command itself fails\n\n 126 if COMMAND is found but cannot be invoked\n\n 127 if COMMAND cannot be found\n\n - the exit status of COMMAND otherwise"} | |
| {"instruction": "What does the command `ls` do?", "output": "ls - list directory contents"} | |
| {"instruction": "How is the `ls` used?", "output": "ls [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `ls`?", "output": "List information about the FILEs (the current directory by default). Sort entries alphabetically if none of\n -cftuvSUX nor --sort is specified.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --all\n do not ignore entries starting with .\n\n -A, --almost-all\n do not list implied . and ..\n\n --author\n with -l, print the author of each file\n\n -b, --escape\n print C-style escapes for nongraphic characters\n\n --block-size=SIZE\n with -l, scale sizes by SIZE when printing them; e.g., '--block-size=M'; see SIZE format below\n\n -B, --ignore-backups\n do not list implied entries ending with ~\n\n -c with -lt: sort by, and show, ctime (time of last change of file status information); with -l: show ctime\n and sort by name; otherwise: sort by ctime, newest first\n\n -C list entries by columns\n\n --color[=WHEN]\n color the output WHEN; more info below\n\n -d, --directory\n list directories themselves, not their contents\n\n -D, --dired\n generate output designed for Emacs' dired mode\n\n -f list all entries in directory order\n\n -F, --classify[=WHEN]\n append indicator (one of */=>@|) to entries WHEN\n\n --file-type\n likewise, except do not append '*'\n\n --format=WORD\n across -x, commas -m, horizontal -x, long -l, single-column -1, verbose -l, vertical -C\n\n --full-time\n like -l --time-style=full-iso\n\n -g like -l, but do not list owner\n\n --group-directories-first\n group directories before files; can be augmented with a --sort option, but any use of --sort=none (-U)\n disables grouping\n\n -G, --no-group\n in a long listing, don't print group names\n\n -h, --human-readable\n with -l and -s, print sizes like 1K 234M 2G etc.\n\n --si likewise, but use powers of 1000 not 1024\n\n -H, --dereference-command-line\n follow symbolic links listed on the command line\n\n --dereference-command-line-symlink-to-dir\n follow each command line symbolic link that points to a directory\n\n --hide=PATTERN\n do not list implied entries matching shell PATTERN (overridden by -a or -A)\n\n --hyperlink[=WHEN]\n hyperlink file names WHEN\n\n --indicator-style=WORD\n append indicator with style WORD to entry names: none (default), slash (-p), file-type (--file-type),\n classify (-F)\n\n -i, --inode\n print the index number of each file\n\n -I, --ignore=PATTERN\n do not list implied entries matching shell PATTERN\n\n -k, --kibibytes\n default to 1024-byte blocks for file system usage; used only with -s and per directory totals\n\n -l use a long listing format\n\n -L, --dereference\n when showing file information for a symbolic link, show information for the file the link references\n rather than for the link itself\n\n -m fill width with a comma separated list of entries\n\n -n, --numeric-uid-gid\n like -l, but list numeric user and group IDs\n\n -N, --literal\n print entry names without quoting\n\n -o like -l, but do not list group information\n\n -p, --indicator-style=slash\n append / indicator to directories\n\n -q, --hide-control-chars\n print ? instead of nongraphic characters\n\n --show-control-chars\n show nongraphic characters as-is (the default, unless program is 'ls' and output is a terminal)\n\n -Q, --quote-name\n enclose entry names in double quotes\n\n --quoting-style=WORD\n use quoting style WORD for entry names: literal, locale, shell, shell-always, shell-escape, shell-es\u2010\n cape-always, c, escape (overrides QUOTING_STYLE environment variable)\n\n -r, --reverse\n reverse order while sorting\n\n -R, --recursive\n list subdirectories recursively\n\n -s, --size\n print the allocated size of each file, in blocks\n\n -S sort by file size, largest first\n\n --sort=WORD\n sort by WORD instead of name: none (-U), size (-S), time (-t), version (-v), extension (-X), width\n\n --time=WORD\n select which timestamp used to display or sort; access time (-u): atime, access, use; metadata change\n time (-c): ctime, status; modified time (default): mtime, modification; birth time: birth, creation;\n\n with -l, WORD determines which time to show; with --sort=time, sort by WORD (newest first)\n\n --time-style=TIME_STYLE\n time/date format with -l; see TIME_STYLE below\n\n -t sort by time, newest first; see --time\n\n -T, --tabsize=COLS\n assume tab stops at each COLS instead of 8\n\n -u with -lt: sort by, and show, access time; with -l: show access time and sort by name; otherwise: sort by\n access time, newest first\n\n -U do not sort; list entries in directory order\n\n -v natural sort of (version) numbers within text\n\n -w, --width=COLS\n set output width to COLS. 0 means no limit\n\n -x list entries by lines instead of by columns\n\n -X sort alphabetically by entry extension\n\n -Z, --context\n print any security context of each file\n\n --zero end each output line with NUL, not newline\n\n -1 list one file per line\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The SIZE argument is an integer and optional unit (example: 10K is 10*1024). Units are K,M,G,T,P,E,Z,Y,R,Q\n (powers of 1024) or KB,MB,... (powers of 1000). Binary prefixes can be used, too: KiB=K, MiB=M, and so on.\n\n The TIME_STYLE argument can be full-iso, long-iso, iso, locale, or +FORMAT. FORMAT is interpreted like in\n date(1). If FORMAT is FORMAT1<newline>FORMAT2, then FORMAT1 applies to non-recent files and FORMAT2 to recent\n files. TIME_STYLE prefixed with 'posix-' takes effect only outside the POSIX locale. Also the TIME_STYLE envi\u2010\n ronment variable sets the default style to use.\n\n The WHEN argument defaults to 'always' and can also be 'auto' or 'never'.\n\n Using color to distinguish file types is disabled both by default and with --color=never. With --color=auto, ls\n emits color codes only when standard output is connected to a terminal. The LS_COLORS environment variable can\n change the settings. Use the dircolors(1) command to set it.\n\n Exit status:\n 0 if OK,\n\n 1 if minor problems (e.g., cannot access subdirectory),\n\n 2 if serious trouble (e.g., cannot access command-line argument)."} | |
| {"instruction": "What does the command `readlink` do?", "output": "readlink - print resolved symbolic links or canonical file names"} | |
| {"instruction": "How is the `readlink` used?", "output": "readlink [OPTION]... FILE..."} | |
| {"instruction": "What is the detailed desciption of the `readlink`?", "output": "Note realpath(1) is the preferred command to use for canonicalization functionality.\n\n Print value of a symbolic link or canonical file name\n\n -f, --canonicalize\n canonicalize by following every symlink in every component of the given name recursively; all but the\n last component must exist\n\n -e, --canonicalize-existing\n canonicalize by following every symlink in every component of the given name recursively, all components\n must exist\n\n -m, --canonicalize-missing\n canonicalize by following every symlink in every component of the given name recursively, without re\u2010\n quirements on components existence\n\n -n, --no-newline\n do not output the trailing delimiter\n\n -q, --quiet\n\n -s, --silent\n suppress most error messages (on by default)\n\n -v, --verbose\n report error messages\n\n -z, --zero\n end each output line with NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `chmod` do?", "output": "chmod - change file mode bits"} | |
| {"instruction": "How is the `chmod` used?", "output": "chmod [OPTION]... MODE[,MODE]... FILE...\n chmod [OPTION]... OCTAL-MODE FILE...\n chmod [OPTION]... --reference=RFILE FILE..."} | |
| {"instruction": "What is the detailed desciption of the `chmod`?", "output": "This manual page documents the GNU version of chmod. chmod changes the file mode\n bits of each given file according to mode, which can be either a symbolic represen\u2010\n tation of changes to make, or an octal number representing the bit pattern for the\n new mode bits.\n\n The format of a symbolic mode is [ugoa...][[-+=][perms...]...], where perms is ei\u2010\n ther zero or more letters from the set rwxXst, or a single letter from the set ugo.\n Multiple symbolic modes can be given, separated by commas.\n\n A combination of the letters ugoa controls which users' access to the file will be\n changed: the user who owns it (u), other users in the file's group (g), other users\n not in the file's group (o), or all users (a). If none of these are given, the ef\u2010\n fect is as if (a) were given, but bits that are set in the umask are not affected.\n\n The operator + causes the selected file mode bits to be added to the existing file\n mode bits of each file; - causes them to be removed; and = causes them to be added\n and causes unmentioned bits to be removed except that a directory's unmentioned set\n user and group ID bits are not affected.\n\n The letters rwxXst select file mode bits for the affected users: read (r), write\n (w), execute (or search for directories) (x), execute/search only if the file is a\n directory or already has execute permission for some user (X), set user or group ID\n on execution (s), restricted deletion flag or sticky bit (t). Instead of one or\n more of these letters, you can specify exactly one of the letters ugo: the permis\u2010\n sions granted to the user who owns the file (u), the permissions granted to other\n users who are members of the file's group (g), and the permissions granted to users\n that are in neither of the two preceding categories (o).\n\n A numeric mode is from one to four octal digits (0-7), derived by adding up the bits\n with values 4, 2, and 1. Omitted digits are assumed to be leading zeros. The first\n digit selects the set user ID (4) and set group ID (2) and restricted deletion or\n sticky (1) attributes. The second digit selects permissions for the user who owns\n the file: read (4), write (2), and execute (1); the third selects permissions for\n other users in the file's group, with the same values; and the fourth for other\n users not in the file's group, with the same values.\n\n chmod never changes the permissions of symbolic links; the chmod system call cannot\n change their permissions. This is not a problem since the permissions of symbolic\n links are never used. However, for each symbolic link listed on the command line,\n chmod changes the permissions of the pointed-to file. In contrast, chmod ignores\n symbolic links encountered during recursive directory traversals."} | |
| {"instruction": "What does the command `csplit` do?", "output": "csplit - split a file into sections determined by context lines"} | |
| {"instruction": "How is the `csplit` used?", "output": "csplit [OPTION]... FILE PATTERN..."} | |
| {"instruction": "What is the detailed desciption of the `csplit`?", "output": "Output pieces of FILE separated by PATTERN(s) to files 'xx00', 'xx01', ..., and output byte counts of each piece\n to standard output.\n\n Read standard input if FILE is -\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -b, --suffix-format=FORMAT\n use sprintf FORMAT instead of %02d\n\n -f, --prefix=PREFIX\n use PREFIX instead of 'xx'\n\n -k, --keep-files\n do not remove output files on errors\n\n --suppress-matched\n suppress the lines matching PATTERN\n\n -n, --digits=DIGITS\n use specified number of digits instead of 2\n\n -s, --quiet, --silent\n do not print counts of output file sizes\n\n -z, --elide-empty-files\n suppress empty output files\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Each PATTERN may be:"} | |
| {"instruction": "What does the command `true` do?", "output": "true - do nothing, successfully"} | |
| {"instruction": "How is the `true` used?", "output": "true [ignored command line arguments]\n true OPTION"} | |
| {"instruction": "What is the detailed desciption of the `true`?", "output": "Exit with a status code indicating success.\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n NOTE: your shell may have its own version of true, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `sort` do?", "output": "sort - sort lines of text files"} | |
| {"instruction": "How is the `sort` used?", "output": "sort [OPTION]... [FILE]...\n sort [OPTION]... --files0-from=F"} | |
| {"instruction": "What is the detailed desciption of the `sort`?", "output": "Write sorted concatenation of all FILE(s) to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too. Ordering options:\n\n -b, --ignore-leading-blanks\n ignore leading blanks\n\n -d, --dictionary-order\n consider only blanks and alphanumeric characters\n\n -f, --ignore-case\n fold lower case to upper case characters\n\n -g, --general-numeric-sort\n compare according to general numerical value\n\n -i, --ignore-nonprinting\n consider only printable characters\n\n -M, --month-sort\n compare (unknown) < 'JAN' < ... < 'DEC'\n\n -h, --human-numeric-sort\n compare human readable numbers (e.g., 2K 1G)\n\n -n, --numeric-sort\n compare according to string numerical value\n\n -R, --random-sort\n shuffle, but group identical keys. See shuf(1)\n\n --random-source=FILE\n get random bytes from FILE\n\n -r, --reverse\n reverse the result of comparisons\n\n --sort=WORD\n sort according to WORD: general-numeric -g, human-numeric -h, month -M, numeric -n, random -R, version -V\n\n -V, --version-sort\n natural sort of (version) numbers within text\n\n Other options:\n\n --batch-size=NMERGE\n merge at most NMERGE inputs at once; for more use temp files\n\n -c, --check, --check=diagnose-first\n check for sorted input; do not sort\n\n -C, --check=quiet, --check=silent\n like -c, but do not report first bad line\n\n --compress-program=PROG\n compress temporaries with PROG; decompress them with PROG -d\n\n --debug\n annotate the part of the line used to sort, and warn about questionable usage to stderr\n\n --files0-from=F\n read input from the files specified by NUL-terminated names in file F; If F is - then read names from\n standard input\n\n -k, --key=KEYDEF\n sort via a key; KEYDEF gives location and type\n\n -m, --merge\n merge already sorted files; do not sort\n\n -o, --output=FILE\n write result to FILE instead of standard output\n\n -s, --stable\n stabilize sort by disabling last-resort comparison\n\n -S, --buffer-size=SIZE\n use SIZE for main memory buffer\n\n -t, --field-separator=SEP\n use SEP instead of non-blank to blank transition\n\n -T, --temporary-directory=DIR\n use DIR for temporaries, not $TMPDIR or /tmp; multiple options specify multiple directories\n\n --parallel=N\n change the number of sorts run concurrently to N\n\n -u, --unique\n with -c, check for strict ordering; without -c, output only the first of an equal run\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n KEYDEF is F[.C][OPTS][,F[.C][OPTS]] for start and stop position, where F is a field number and C a character po\u2010\n sition in the field; both are origin 1, and the stop position defaults to the line's end. If neither -t nor -b\n is in effect, characters in a field are counted from the beginning of the preceding whitespace. OPTS is one or\n more single-letter ordering options [bdfgiMhnRrV], which override global ordering options for that key. If no\n key is given, use the entire line as the key. Use --debug to diagnose incorrect key usage.\n\n SIZE may be followed by the following multiplicative suffixes: % 1% of memory, b 1, K 1024 (default), and so on\n for M, G, T, P, E, Z, Y, R, Q.\n\n *** WARNING *** The locale specified by the environment affects sort order. Set LC_ALL=C to get the traditional\n sort order that uses native byte values."} | |
| {"instruction": "What does the command `ln` do?", "output": "ln - make links between files"} | |
| {"instruction": "How is the `ln` used?", "output": "ln [OPTION]... [-T] TARGET LINK_NAME\n ln [OPTION]... TARGET\n ln [OPTION]... TARGET... DIRECTORY\n ln [OPTION]... -t DIRECTORY TARGET..."} | |
| {"instruction": "What is the detailed desciption of the `ln`?", "output": "In the 1st form, create a link to TARGET with the name LINK_NAME. In the 2nd form, create a link to TARGET in\n the current directory. In the 3rd and 4th forms, create links to each TARGET in DIRECTORY. Create hard links\n by default, symbolic links with --symbolic. By default, each destination (name of new link) should not already\n exist. When creating hard links, each TARGET must exist. Symbolic links can hold arbitrary text; if later re\u2010\n solved, a relative link is interpreted in relation to its parent directory.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n --backup[=CONTROL]\n make a backup of each existing destination file\n\n -b like --backup but does not accept an argument\n\n -d, -F, --directory\n allow the superuser to attempt to hard link directories (note: will probably fail due to system restric\u2010\n tions, even for the superuser)\n\n -f, --force\n remove existing destination files\n\n -i, --interactive\n prompt whether to remove destinations\n\n -L, --logical\n dereference TARGETs that are symbolic links\n\n -n, --no-dereference\n treat LINK_NAME as a normal file if it is a symbolic link to a directory\n\n -P, --physical\n make hard links directly to symbolic links\n\n -r, --relative\n with -s, create links relative to link location\n\n -s, --symbolic\n make symbolic links instead of hard links\n\n -S, --suffix=SUFFIX\n override the usual backup suffix\n\n -t, --target-directory=DIRECTORY\n specify the DIRECTORY in which to create the links\n\n -T, --no-target-directory\n treat LINK_NAME as a normal file always\n\n -v, --verbose\n print name of each linked file\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The backup suffix is '~', unless set with --suffix or SIMPLE_BACKUP_SUFFIX. The version control method may be\n selected via the --backup option or through the VERSION_CONTROL environment variable. Here are the values:\n\n none, off\n never make backups (even if --backup is given)\n\n numbered, t\n make numbered backups\n\n existing, nil\n numbered if numbered backups exist, simple otherwise\n\n simple, never\n always make simple backups\n\n Using -s ignores -L and -P. Otherwise, the last option specified controls behavior when a TARGET is a symbolic\n link, defaulting to -P."} | |
| {"instruction": "What does the command `tty` do?", "output": "tty - print the file name of the terminal connected to standard input"} | |
| {"instruction": "How is the `tty` used?", "output": "tty [OPTION]..."} | |
| {"instruction": "What is the detailed desciption of the `tty`?", "output": "Print the file name of the terminal connected to standard input.\n\n -s, --silent, --quiet\n print nothing, only return an exit status\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `rm` do?", "output": "rm - remove files or directories"} | |
| {"instruction": "How is the `rm` used?", "output": "rm [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `rm`?", "output": "This manual page documents the GNU version of rm. rm removes each specified file. By default, it does not re\u2010\n move directories.\n\n If the -I or --interactive=once option is given, and there are more than three files or the -r, -R, or --recur\u2010\n sive are given, then rm prompts the user for whether to proceed with the entire operation. If the response is\n not affirmative, the entire command is aborted.\n\n Otherwise, if a file is unwritable, standard input is a terminal, and the -f or --force option is not given, or\n the -i or --interactive=always option is given, rm prompts the user for whether to remove the file. If the re\u2010\n sponse is not affirmative, the file is skipped."} | |
| {"instruction": "What does the command `base64` do?", "output": "base64 - base64 encode/decode data and print to standard output"} | |
| {"instruction": "How is the `base64` used?", "output": "base64 [OPTION]... [FILE]"} | |
| {"instruction": "What is the detailed desciption of the `base64`?", "output": "Base64 encode or decode FILE, or standard input, to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -d, --decode\n decode data\n\n -i, --ignore-garbage\n when decoding, ignore non-alphabet characters\n\n -w, --wrap=COLS\n wrap encoded lines after COLS character (default 76). Use 0 to disable line wrapping\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The data are encoded as described for the base64 alphabet in RFC 4648. When decoding, the input may contain\n newlines in addition to the bytes of the formal base64 alphabet. Use --ignore-garbage to attempt to recover\n from any other non-alphabet bytes in the encoded stream."} | |
| {"instruction": "What does the command `shuf` do?", "output": "shuf - generate random permutations"} | |
| {"instruction": "How is the `shuf` used?", "output": "shuf [OPTION]... [FILE]\n shuf -e [OPTION]... [ARG]...\n shuf -i LO-HI [OPTION]..."} | |
| {"instruction": "What is the detailed desciption of the `shuf`?", "output": "Write a random permutation of the input lines to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -e, --echo\n treat each ARG as an input line\n\n -i, --input-range=LO-HI\n treat each number LO through HI as an input line\n\n -n, --head-count=COUNT\n output at most COUNT lines\n\n -o, --output=FILE\n write result to FILE instead of standard output\n\n --random-source=FILE\n get random bytes from FILE\n\n -r, --repeat\n output lines can be repeated\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `cut` do?", "output": "cut - remove sections from each line of files"} | |
| {"instruction": "How is the `cut` used?", "output": "cut OPTION... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `cut`?", "output": "Print selected parts of lines from each FILE to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -b, --bytes=LIST\n select only these bytes\n\n -c, --characters=LIST\n select only these characters\n\n -d, --delimiter=DELIM\n use DELIM instead of TAB for field delimiter\n\n -f, --fields=LIST\n select only these fields; also print any line that contains no delimiter character, unless the -s option\n is specified\n\n -n (ignored)\n\n --complement\n complement the set of selected bytes, characters or fields\n\n -s, --only-delimited\n do not print lines not containing delimiters\n\n --output-delimiter=STRING\n use STRING as the output delimiter the default is to use the input delimiter\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Use one, and only one of -b, -c or -f. Each LIST is made up of one range, or many ranges separated by commas.\n Selected input is written in the same order that it is read, and is written exactly once. Each range is one of:\n\n N N'th byte, character or field, counted from 1\n\n N- from N'th byte, character or field, to end of line\n\n N-M from N'th to M'th (included) byte, character or field\n\n -M from first to M'th (included) byte, character or field"} | |
| {"instruction": "What does the command `paste` do?", "output": "paste - merge lines of files"} | |
| {"instruction": "How is the `paste` used?", "output": "paste [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `paste`?", "output": "Write lines consisting of the sequentially corresponding lines from each FILE, separated by TABs, to standard\n output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -d, --delimiters=LIST\n reuse characters from LIST instead of TABs\n\n -s, --serial\n paste one file at a time instead of in parallel\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `ptx` do?", "output": "ptx - produce a permuted index of file contents"} | |
| {"instruction": "How is the `ptx` used?", "output": "ptx [OPTION]... [INPUT]... (without -G)\n ptx -G [OPTION]... [INPUT [OUTPUT]]"} | |
| {"instruction": "What is the detailed desciption of the `ptx`?", "output": "Output a permuted index, including context, of the words in the input files.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -A, --auto-reference\n output automatically generated references\n\n -G, --traditional\n behave more like System V 'ptx'\n\n -F, --flag-truncation=STRING\n use STRING for flagging line truncations. The default is '/'\n\n -M, --macro-name=STRING\n macro name to use instead of 'xx'\n\n -O, --format=roff\n generate output as roff directives\n\n -R, --right-side-refs\n put references at right, not counted in -w\n\n -S, --sentence-regexp=REGEXP\n for end of lines or end of sentences\n\n -T, --format=tex\n generate output as TeX directives\n\n -W, --word-regexp=REGEXP\n use REGEXP to match each keyword\n\n -b, --break-file=FILE\n word break characters in this FILE\n\n -f, --ignore-case\n fold lower case to upper case for sorting\n\n -g, --gap-size=NUMBER\n gap size in columns between output fields\n\n -i, --ignore-file=FILE\n read ignore word list from FILE\n\n -o, --only-file=FILE\n read only word list from this FILE\n\n -r, --references\n first field of each line is a reference\n\n -t, --typeset-mode - not implemented -\n\n -w, --width=NUMBER\n output width in columns, reference excluded\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `unexpand` do?", "output": "unexpand - convert spaces to tabs"} | |
| {"instruction": "How is the `unexpand` used?", "output": "unexpand [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `unexpand`?", "output": "Convert blanks in each FILE to tabs, writing to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --all\n convert all blanks, instead of just initial blanks\n\n --first-only\n convert only leading sequences of blanks (overrides -a)\n\n -t, --tabs=N\n have tabs N characters apart instead of 8 (enables -a)\n\n -t, --tabs=LIST\n use comma separated list of tab positions. The last specified position can be prefixed with '/' to spec\u2010\n ify a tab size to use after the last explicitly specified tab stop. Also a prefix of '+' can be used to\n align remaining tab stops relative to the last specified tab stop instead of the first column\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `sha1sum` do?", "output": "sha1sum - compute and check SHA1 message digest"} | |
| {"instruction": "How is the `sha1sum` used?", "output": "sha1sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `sha1sum`?", "output": "Print or check SHA1 (160-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n -b, --binary\n read in binary mode\n\n -c, --check\n read checksums from the FILEs and check them\n\n --tag create a BSD-style checksum\n\n -t, --text\n read in text mode (default)\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The sums are computed as described in FIPS-180-1. When checking, the input should be a former output of this\n program. The default mode is to print a line with: checksum, a space, a character indicating input mode ('*'\n for binary, ' ' for text or where binary is insignificant), and name for each FILE.\n\n Note: There is no difference between binary mode and text mode on GNU systems."} | |
| {"instruction": "What does the command `test` do?", "output": "test - check file types and compare values"} | |
| {"instruction": "How is the `test` used?", "output": "test EXPRESSION\n test\n [ EXPRESSION ]\n [ ]\n [ OPTION"} | |
| {"instruction": "What is the detailed desciption of the `test`?", "output": "Exit with the status determined by EXPRESSION.\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n An omitted EXPRESSION defaults to false. Otherwise, EXPRESSION is true or false and sets exit status. It is\n one of:\n\n ( EXPRESSION )\n EXPRESSION is true\n\n ! EXPRESSION\n EXPRESSION is false\n\n EXPRESSION1 -a EXPRESSION2\n both EXPRESSION1 and EXPRESSION2 are true\n\n EXPRESSION1 -o EXPRESSION2\n either EXPRESSION1 or EXPRESSION2 is true\n\n -n STRING\n the length of STRING is nonzero\n\n STRING equivalent to -n STRING\n\n -z STRING\n the length of STRING is zero\n\n STRING1 = STRING2\n the strings are equal\n\n STRING1 != STRING2\n the strings are not equal\n\n INTEGER1 -eq INTEGER2\n INTEGER1 is equal to INTEGER2\n\n INTEGER1 -ge INTEGER2\n INTEGER1 is greater than or equal to INTEGER2\n\n INTEGER1 -gt INTEGER2\n INTEGER1 is greater than INTEGER2\n\n INTEGER1 -le INTEGER2\n INTEGER1 is less than or equal to INTEGER2\n\n INTEGER1 -lt INTEGER2\n INTEGER1 is less than INTEGER2\n\n INTEGER1 -ne INTEGER2\n INTEGER1 is not equal to INTEGER2\n\n FILE1 -ef FILE2\n FILE1 and FILE2 have the same device and inode numbers\n\n FILE1 -nt FILE2\n FILE1 is newer (modification date) than FILE2\n\n FILE1 -ot FILE2\n FILE1 is older than FILE2\n\n -b FILE\n FILE exists and is block special\n\n -c FILE\n FILE exists and is character special\n\n -d FILE\n FILE exists and is a directory\n\n -e FILE\n FILE exists\n\n -f FILE\n FILE exists and is a regular file\n\n -g FILE\n FILE exists and is set-group-ID\n\n -G FILE\n FILE exists and is owned by the effective group ID\n\n -h FILE\n FILE exists and is a symbolic link (same as -L)\n\n -k FILE\n FILE exists and has its sticky bit set\n\n -L FILE\n FILE exists and is a symbolic link (same as -h)\n\n -N FILE\n FILE exists and has been modified since it was last read\n\n -O FILE\n FILE exists and is owned by the effective user ID\n\n -p FILE\n FILE exists and is a named pipe\n\n -r FILE\n FILE exists and the user has read access\n\n -s FILE\n FILE exists and has a size greater than zero\n\n -S FILE\n FILE exists and is a socket\n\n -t FD file descriptor FD is opened on a terminal\n\n -u FILE\n FILE exists and its set-user-ID bit is set\n\n -w FILE\n FILE exists and the user has write access\n\n -x FILE\n FILE exists and the user has execute (or search) access\n\n Except for -h and -L, all FILE-related tests dereference symbolic links. Beware that parentheses need to be es\u2010\n caped (e.g., by backslashes) for shells. INTEGER may also be -l STRING, which evaluates to the length of\n STRING.\n\n NOTE: Binary -a and -o are inherently ambiguous. Use 'test EXPR1 && test EXPR2' or 'test EXPR1 || test EXPR2'\n instead.\n\n NOTE: [ honors the --help and --version options, but test does not. test treats each of those as it treats any\n other nonempty STRING.\n\n NOTE: your shell may have its own version of test and/or [, which usually supersedes the version described here.\n Please refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `tsort` do?", "output": "tsort - perform topological sort"} | |
| {"instruction": "How is the `tsort` used?", "output": "tsort [OPTION] [FILE]"} | |
| {"instruction": "What is the detailed desciption of the `tsort`?", "output": "Write totally ordered list consistent with the partial ordering in FILE.\n\n With no FILE, or when FILE is -, read standard input.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `pathchk` do?", "output": "pathchk - check whether file names are valid or portable"} | |
| {"instruction": "How is the `pathchk` used?", "output": "pathchk [OPTION]... NAME..."} | |
| {"instruction": "What is the detailed desciption of the `pathchk`?", "output": "Diagnose invalid or non-portable file names.\n\n -p check for most POSIX systems\n\n -P check for empty names and leading \"-\"\n\n --portability\n check for all POSIX systems (equivalent to -p -P)\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `od` do?", "output": "od - dump files in octal and other formats"} | |
| {"instruction": "How is the `od` used?", "output": "od [OPTION]... [FILE]...\n od [-abcdfilosx]... [FILE] [[+]OFFSET[.][b]]\n od --traditional [OPTION]... [FILE] [[+]OFFSET[.][b] [+][LABEL][.][b]]"} | |
| {"instruction": "What is the detailed desciption of the `od`?", "output": "Write an unambiguous representation, octal bytes by default, of FILE to standard output. With more than one\n FILE argument, concatenate them in the listed order to form the input.\n\n With no FILE, or when FILE is -, read standard input.\n\n If first and second call formats both apply, the second format is assumed if the last operand begins with + or\n (if there are 2 operands) a digit. An OFFSET operand means -j OFFSET. LABEL is the pseudo-address at first\n byte printed, incremented when dump is progressing. For OFFSET and LABEL, a 0x or 0X prefix indicates hexadeci\u2010\n mal; suffixes may be . for octal and b for multiply by 512.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -A, --address-radix=RADIX\n output format for file offsets; RADIX is one of [doxn], for Decimal, Octal, Hex or None\n\n --endian={big|little}\n swap input bytes according the specified order\n\n -j, --skip-bytes=BYTES\n skip BYTES input bytes first\n\n -N, --read-bytes=BYTES\n limit dump to BYTES input bytes\n\n -S BYTES, --strings[=BYTES]\n show only NUL terminated strings of at least BYTES (3) printable characters\n\n -t, --format=TYPE\n select output format or formats\n\n -v, --output-duplicates\n do not use * to mark line suppression\n\n -w[BYTES], --width[=BYTES]\n output BYTES bytes per output line; 32 is implied when BYTES is not specified\n\n --traditional\n accept arguments in third form above\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Traditional format specifications may be intermixed; they accumulate:\n -a same as -t a, select named characters, ignoring high-order bit\n\n -b same as -t o1, select octal bytes\n\n -c same as -t c, select printable characters or backslash escapes\n\n -d same as -t u2, select unsigned decimal 2-byte units\n\n -f same as -t fF, select floats\n\n -i same as -t dI, select decimal ints\n\n -l same as -t dL, select decimal longs\n\n -o same as -t o2, select octal 2-byte units\n\n -s same as -t d2, select decimal 2-byte units\n\n -x same as -t x2, select hexadecimal 2-byte units\n\n TYPE is made up of one or more of these specifications:\n a named character, ignoring high-order bit\n\n c printable character or backslash escape\n\n d[SIZE]\n signed decimal, SIZE bytes per integer\n\n f[SIZE]\n floating point, SIZE bytes per float\n\n o[SIZE]\n octal, SIZE bytes per integer\n\n u[SIZE]\n unsigned decimal, SIZE bytes per integer\n\n x[SIZE]\n hexadecimal, SIZE bytes per integer\n\n SIZE is a number. For TYPE in [doux], SIZE may also be C for sizeof(char), S for sizeof(short), I for\n sizeof(int) or L for sizeof(long). If TYPE is f, SIZE may also be F for sizeof(float), D for sizeof(double) or\n L for sizeof(long double).\n\n Adding a z suffix to any type displays printable characters at the end of each output line.\n\n BYTES is hex with 0x or 0X prefix, and may have a multiplier suffix:\n b 512\n\n KB 1000\n\n K 1024\n\n MB 1000*1000\n\n M 1024*1024\n\n and so on for G, T, P, E, Z, Y, R, Q. Binary prefixes can be used, too: KiB=K, MiB=M, and so on."} | |
| {"instruction": "What does the command `link` do?", "output": "link - call the link function to create a link to a file"} | |
| {"instruction": "How is the `link` used?", "output": "link FILE1 FILE2\n link OPTION"} | |
| {"instruction": "What is the detailed desciption of the `link`?", "output": "Call the link function to create a link named FILE2 to an existing FILE1.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `tee` do?", "output": "tee - read from standard input and write to standard output and files"} | |
| {"instruction": "How is the `tee` used?", "output": "tee [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `tee`?", "output": "Copy standard input to each FILE, and also to standard output.\n\n -a, --append\n append to the given FILEs, do not overwrite\n\n -i, --ignore-interrupts\n ignore interrupt signals\n\n -p operate in a more appropriate MODE with pipes.\n\n --output-error[=MODE]\n set behavior on write error. See MODE below\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n MODE determines behavior with write errors on the outputs:\n warn diagnose errors writing to any output\n\n warn-nopipe\n diagnose errors writing to any output not a pipe\n\n exit exit on error writing to any output\n\n exit-nopipe\n exit on error writing to any output not a pipe\n\n The default MODE for the -p option is 'warn-nopipe'. With \"nopipe\" MODEs, exit immediately if all outputs be\u2010\n come broken pipes. The default operation when --output-error is not specified, is to exit immediately on error\n writing to a pipe, and diagnose errors writing to non pipe outputs."} | |
| {"instruction": "What does the command `cksum` do?", "output": "cksum - compute and verify file checksums"} | |
| {"instruction": "How is the `cksum` used?", "output": "cksum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `cksum`?", "output": "Print or verify checksums. By default use the 32 bit CRC algorithm.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --algorithm=TYPE\n select the digest type to use. See DIGEST below.\n\n --base64\n emit base64-encoded digests, not hexadecimal\n\n -c, --check\n read checksums from the FILEs and check them\n\n -l, --length=BITS\n digest length in bits; must not exceed the max for the blake2 algorithm and must be a multiple of 8\n\n --raw emit a raw binary digest, not hexadecimal\n\n --tag create a BSD-style checksum (the default)\n\n --untagged\n create a reversed style checksum, without digest type\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --debug\n indicate which implementation used\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n DIGEST determines the digest algorithm and default output format:\n sysv (equivalent to sum -s)\n\n bsd (equivalent to sum -r)\n\n crc (equivalent to cksum)\n\n md5 (equivalent to md5sum)\n\n sha1 (equivalent to sha1sum)\n\n sha224 (equivalent to sha224sum)\n\n sha256 (equivalent to sha256sum)\n\n sha384 (equivalent to sha384sum)\n\n sha512 (equivalent to sha512sum)\n\n blake2b\n (equivalent to b2sum)\n\n sm3 (only available through cksum)\n\n When checking, the input should be a former output of this program, or equivalent standalone program."} | |
| {"instruction": "What does the command `timeout` do?", "output": "timeout - run a command with a time limit"} | |
| {"instruction": "How is the `timeout` used?", "output": "timeout [OPTION] DURATION COMMAND [ARG]...\n timeout [OPTION]"} | |
| {"instruction": "What is the detailed desciption of the `timeout`?", "output": "Start COMMAND, and kill it if still running after DURATION.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n --preserve-status\n\n exit with the same status as COMMAND, even when the\n\n command times out\n\n --foreground\n\n when not running timeout directly from a shell prompt,\n\n allow COMMAND to read from the TTY and get TTY signals; in this mode, children of COMMAND will not be\n timed out\n\n -k, --kill-after=DURATION\n\n also send a KILL signal if COMMAND is still running\n\n this long after the initial signal was sent\n\n -s, --signal=SIGNAL\n\n specify the signal to be sent on timeout;\n\n SIGNAL may be a name like 'HUP' or a number; see 'kill -l' for a list of signals\n\n -v, --verbose\n diagnose to stderr any signal sent upon timeout\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n DURATION is a floating point number with an optional suffix: 's' for seconds (the default), 'm' for minutes, 'h'\n for hours or 'd' for days. A duration of 0 disables the associated timeout.\n\n Upon timeout, send the TERM signal to COMMAND, if no other SIGNAL specified. The TERM signal kills any process\n that does not block or catch that signal. It may be necessary to use the KILL signal, since this signal can't\n be caught.\n\n Exit status:\n 124 if COMMAND times out, and --preserve-status is not specified\n\n 125 if the timeout command itself fails\n\n 126 if COMMAND is found but cannot be invoked\n\n 127 if COMMAND cannot be found\n\n 137 if COMMAND (or timeout itself) is sent the KILL (9) signal (128+9)\n\n - the exit status of COMMAND otherwise"} | |
| {"instruction": "What does the command `factor` do?", "output": "factor - factor numbers"} | |
| {"instruction": "How is the `factor` used?", "output": "factor [OPTION] [NUMBER]..."} | |
| {"instruction": "What is the detailed desciption of the `factor`?", "output": "Print the prime factors of each specified integer NUMBER. If none are specified on the command line, read them\n from standard input.\n\n -h, --exponents\n print repeated factors in form p^e unless e is 1\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `df` do?", "output": "df - report file system space usage"} | |
| {"instruction": "How is the `df` used?", "output": "df [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `df`?", "output": "This manual page documents the GNU version of df. df displays the amount of space\n available on the file system containing each file name argument. If no file name is\n given, the space available on all currently mounted file systems is shown. Space is\n shown in 1K blocks by default, unless the environment variable POSIXLY_CORRECT is\n set, in which case 512-byte blocks are used.\n\n If an argument is the absolute file name of a device node containing a mounted file\n system, df shows the space available on that file system rather than on the file\n system containing the device node. This version of df cannot show the space avail\u2010\n able on unmounted file systems, because on most kinds of systems doing so requires\n non-portable intimate knowledge of file system structures."} | |
| {"instruction": "What does the command `cp` do?", "output": "cp - copy files and directories"} | |
| {"instruction": "How is the `cp` used?", "output": "cp [OPTION]... [-T] SOURCE DEST\n cp [OPTION]... SOURCE... DIRECTORY\n cp [OPTION]... -t DIRECTORY SOURCE..."} | |
| {"instruction": "What is the detailed desciption of the `cp`?", "output": "Copy SOURCE to DEST, or multiple SOURCE(s) to DIRECTORY.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --archive\n same as -dR --preserve=all\n\n --attributes-only\n don't copy the file data, just the attributes\n\n --backup[=CONTROL]\n make a backup of each existing destination file\n\n -b like --backup but does not accept an argument\n\n --copy-contents\n copy contents of special files when recursive\n\n -d same as --no-dereference --preserve=links\n\n --debug\n explain how a file is copied. Implies -v\n\n -f, --force\n if an existing destination file cannot be opened, remove it and try again\n (this option is ignored when the -n option is also used)\n\n -i, --interactive\n prompt before overwrite (overrides a previous -n option)\n\n -H follow command-line symbolic links in SOURCE\n\n -l, --link\n hard link files instead of copying\n\n -L, --dereference\n always follow symbolic links in SOURCE\n\n -n, --no-clobber\n do not overwrite an existing file and do not fail (overrides a -u or previous\n -i option). See also --update; equivalent to --update=none.\n\n -P, --no-dereference\n never follow symbolic links in SOURCE\n\n -p same as --preserve=mode,ownership,timestamps\n\n --preserve[=ATTR_LIST]\n preserve the specified attributes\n\n --no-preserve=ATTR_LIST\n don't preserve the specified attributes\n\n --parents\n use full source file name under DIRECTORY\n\n -R, -r, --recursive\n copy directories recursively\n\n --reflink[=WHEN]\n control clone/CoW copies. See below\n\n --remove-destination\n remove each existing destination file before attempting to open it (contrast\n with --force)\n\n --sparse=WHEN\n control creation of sparse files. See below\n\n --strip-trailing-slashes\n remove any trailing slashes from each SOURCE argument\n\n -s, --symbolic-link\n make symbolic links instead of copying\n\n -S, --suffix=SUFFIX\n override the usual backup suffix\n\n -t, --target-directory=DIRECTORY\n copy all SOURCE arguments into DIRECTORY\n\n -T, --no-target-directory\n treat DEST as a normal file\n\n --update[=UPDATE]\n control which existing files are updated; UPDATE={all,none,older(default)}.\n See below\n\n -u equivalent to --update[=older]\n\n -v, --verbose\n explain what is being done\n\n -x, --one-file-system\n stay on this file system\n\n -Z set SELinux security context of destination file to default type\n\n --context[=CTX]\n like -Z, or if CTX is specified then set the SELinux or SMACK security con\u2010\n text to CTX\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n ATTR_LIST is a comma-separated list of attributes. Attributes are 'mode' for permis\u2010\n sions (including any ACL and xattr permissions), 'ownership' for user and group,\n 'timestamps' for file timestamps, 'links' for hard links, 'context' for security\n context, 'xattr' for extended attributes, and 'all' for all attributes.\n\n By default, sparse SOURCE files are detected by a crude heuristic and the corre\u2010\n sponding DEST file is made sparse as well. That is the behavior selected by\n --sparse=auto. Specify --sparse=always to create a sparse DEST file whenever the\n SOURCE file contains a long enough sequence of zero bytes. Use --sparse=never to\n inhibit creation of sparse files.\n\n UPDATE controls which existing files in the destination are replaced. 'all' is the\n default operation when an --update option is not specified, and results in all ex\u2010\n isting files in the destination being replaced. 'none' is similar to the --no-clob\u2010\n ber option, in that no files in the destination are replaced, but also skipped files\n do not induce a failure. 'older' is the default operation when --update is speci\u2010\n fied, and results in files being replaced if they're older than the corresponding\n source file.\n\n When --reflink[=always] is specified, perform a lightweight copy, where the data\n blocks are copied only when modified. If this is not possible the copy fails, or if\n --reflink=auto is specified, fall back to a standard copy. Use --reflink=never to\n ensure a standard copy is performed.\n\n The backup suffix is '~', unless set with --suffix or SIMPLE_BACKUP_SUFFIX. The\n version control method may be selected via the --backup option or through the VER\u2010\n SION_CONTROL environment variable. Here are the values:\n\n none, off\n never make backups (even if --backup is given)\n\n numbered, t\n make numbered backups\n\n existing, nil\n numbered if numbered backups exist, simple otherwise\n\n simple, never\n always make simple backups\n\n As a special case, cp makes a backup of SOURCE when the force and backup options are\n given and SOURCE and DEST are the same name for an existing, regular file."} | |
| {"instruction": "What does the command `join` do?", "output": "join - join lines of two files on a common field"} | |
| {"instruction": "How is the `join` used?", "output": "join [OPTION]... FILE1 FILE2"} | |
| {"instruction": "What is the detailed desciption of the `join`?", "output": "For each pair of input lines with identical join fields, write a line to standard output. The default join\n field is the first, delimited by blanks.\n\n When FILE1 or FILE2 (not both) is -, read standard input.\n\n -a FILENUM\n also print unpairable lines from file FILENUM, where FILENUM is 1 or 2, corresponding to FILE1 or FILE2\n\n -e STRING\n replace missing (empty) input fields with STRING; I.e., missing fields specified with '-12jo' options\n\n -i, --ignore-case\n ignore differences in case when comparing fields\n\n -j FIELD\n equivalent to '-1 FIELD -2 FIELD'\n\n -o FORMAT\n obey FORMAT while constructing output line\n\n -t CHAR\n use CHAR as input and output field separator\n\n -v FILENUM\n like -a FILENUM, but suppress joined output lines\n\n -1 FIELD\n join on this FIELD of file 1\n\n -2 FIELD\n join on this FIELD of file 2\n\n --check-order\n check that the input is correctly sorted, even if all input lines are pairable\n\n --nocheck-order\n do not check that the input is correctly sorted\n\n --header\n treat the first line in each file as field headers, print them without trying to pair them\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Unless -t CHAR is given, leading blanks separate fields and are ignored, else fields are separated by CHAR. Any\n FIELD is a field number counted from 1. FORMAT is one or more comma or blank separated specifications, each be\u2010\n ing 'FILENUM.FIELD' or '0'. Default FORMAT outputs the join field, the remaining fields from FILE1, the remain\u2010\n ing fields from FILE2, all separated by CHAR. If FORMAT is the keyword 'auto', then the first line of each file\n determines the number of fields output for each line.\n\n Important: FILE1 and FILE2 must be sorted on the join fields. E.g., use \"sort -k 1b,1\" if 'join' has no op\u2010\n tions, or use \"join -t ''\" if 'sort' has no options. Note, comparisons honor the rules specified by 'LC_COL\u2010\n LATE'. If the input is not sorted and some lines cannot be joined, a warning message will be given."} | |
| {"instruction": "What does the command `sha256sum` do?", "output": "sha256sum - compute and check SHA256 message digest"} | |
| {"instruction": "How is the `sha256sum` used?", "output": "sha256sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `sha256sum`?", "output": "Print or check SHA256 (256-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n -b, --binary\n read in binary mode\n\n -c, --check\n read checksums from the FILEs and check them\n\n --tag create a BSD-style checksum\n\n -t, --text\n read in text mode (default)\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The sums are computed as described in FIPS-180-2. When checking, the input should be a former output of this\n program. The default mode is to print a line with: checksum, a space, a character indicating input mode ('*'\n for binary, ' ' for text or where binary is insignificant), and name for each FILE.\n\n Note: There is no difference between binary mode and text mode on GNU systems."} | |
| {"instruction": "What does the command `uniq` do?", "output": "uniq - report or omit repeated lines"} | |
| {"instruction": "How is the `uniq` used?", "output": "uniq [OPTION]... [INPUT [OUTPUT]]"} | |
| {"instruction": "What is the detailed desciption of the `uniq`?", "output": "Filter adjacent matching lines from INPUT (or standard input), writing to OUTPUT (or standard output).\n\n With no options, matching lines are merged to the first occurrence.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -c, --count\n prefix lines by the number of occurrences\n\n -d, --repeated\n only print duplicate lines, one for each group\n\n -D print all duplicate lines\n\n --all-repeated[=METHOD]\n like -D, but allow separating groups with an empty line; METHOD={none(default),prepend,separate}\n\n -f, --skip-fields=N\n avoid comparing the first N fields\n\n --group[=METHOD]\n show all items, separating groups with an empty line; METHOD={separate(default),prepend,append,both}\n\n -i, --ignore-case\n ignore differences in case when comparing\n\n -s, --skip-chars=N\n avoid comparing the first N characters\n\n -u, --unique\n only print unique lines\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n -w, --check-chars=N\n compare no more than N characters in lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n A field is a run of blanks (usually spaces and/or TABs), then non-blank characters. Fields are skipped before\n chars.\n\n Note: 'uniq' does not detect repeated lines unless they are adjacent. You may want to sort the input first, or\n use 'sort -u' without 'uniq'."} | |
| {"instruction": "What does the command `sha512sum` do?", "output": "sha512sum - compute and check SHA512 message digest"} | |
| {"instruction": "How is the `sha512sum` used?", "output": "sha512sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `sha512sum`?", "output": "Print or check SHA512 (512-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n -b, --binary\n read in binary mode\n\n -c, --check\n read checksums from the FILEs and check them\n\n --tag create a BSD-style checksum\n\n -t, --text\n read in text mode (default)\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The sums are computed as described in FIPS-180-2. When checking, the input should be a former output of this\n program. The default mode is to print a line with: checksum, a space, a character indicating input mode ('*'\n for binary, ' ' for text or where binary is insignificant), and name for each FILE.\n\n Note: There is no difference between binary mode and text mode on GNU systems."} | |
| {"instruction": "What does the command `base32` do?", "output": "base32 - base32 encode/decode data and print to standard output"} | |
| {"instruction": "How is the `base32` used?", "output": "base32 [OPTION]... [FILE]"} | |
| {"instruction": "What is the detailed desciption of the `base32`?", "output": "Base32 encode or decode FILE, or standard input, to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -d, --decode\n decode data\n\n -i, --ignore-garbage\n when decoding, ignore non-alphabet characters\n\n -w, --wrap=COLS\n wrap encoded lines after COLS character (default 76). Use 0 to disable line wrapping\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The data are encoded as described for the base32 alphabet in RFC 4648. When decoding, the input may contain\n newlines in addition to the bytes of the formal base32 alphabet. Use --ignore-garbage to attempt to recover\n from any other non-alphabet bytes in the encoded stream."} | |
| {"instruction": "What does the command `dirname` do?", "output": "dirname - strip last component from file name"} | |
| {"instruction": "How is the `dirname` used?", "output": "dirname [OPTION] NAME..."} | |
| {"instruction": "What is the detailed desciption of the `dirname`?", "output": "Output each NAME with its last non-slash component and trailing slashes removed; if NAME contains no /'s, output\n '.' (meaning the current directory).\n\n -z, --zero\n end each output line with NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `numfmt` do?", "output": "numfmt - Convert numbers from/to human-readable strings"} | |
| {"instruction": "How is the `numfmt` used?", "output": "numfmt [OPTION]... [NUMBER]..."} | |
| {"instruction": "What is the detailed desciption of the `numfmt`?", "output": "Reformat NUMBER(s), or the numbers from standard input if none are specified.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n --debug\n print warnings about invalid input\n\n -d, --delimiter=X\n use X instead of whitespace for field delimiter\n\n --field=FIELDS\n replace the numbers in these input fields (default=1); see FIELDS below\n\n --format=FORMAT\n use printf style floating-point FORMAT; see FORMAT below for details\n\n --from=UNIT\n auto-scale input numbers to UNITs; default is 'none'; see UNIT below\n\n --from-unit=N\n specify the input unit size (instead of the default 1)\n\n --grouping\n use locale-defined grouping of digits, e.g. 1,000,000 (which means it has no effect in the C/POSIX lo\u2010\n cale)\n\n --header[=N]\n print (without converting) the first N header lines; N defaults to 1 if not specified\n\n --invalid=MODE\n failure mode for invalid numbers: MODE can be: abort (default), fail, warn, ignore\n\n --padding=N\n pad the output to N characters; positive N will right-align; negative N will left-align; padding is ig\u2010\n nored if the output is wider than N; the default is to automatically pad if a whitespace is found\n\n --round=METHOD\n use METHOD for rounding when scaling; METHOD can be: up, down, from-zero (default), towards-zero, nearest\n\n --suffix=SUFFIX\n add SUFFIX to output numbers, and accept optional SUFFIX in input numbers\n\n --to=UNIT\n auto-scale output numbers to UNITs; see UNIT below\n\n --to-unit=N\n the output unit size (instead of the default 1)\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n UNIT options:\n none no auto-scaling is done; suffixes will trigger an error\n\n auto accept optional single/two letter suffix:\n\n 1K = 1000, 1Ki = 1024, 1M = 1000000, 1Mi = 1048576,\n\n si accept optional single letter suffix:\n\n 1K = 1000, 1M = 1000000, ...\n\n iec accept optional single letter suffix:\n\n 1K = 1024, 1M = 1048576, ...\n\n iec-i accept optional two-letter suffix:\n\n 1Ki = 1024, 1Mi = 1048576, ...\n\n FIELDS supports cut(1) style field ranges:\n N N'th field, counted from 1\n\n N- from N'th field, to end of line\n\n N-M from N'th to M'th field (inclusive)\n\n -M from first to M'th field (inclusive)\n\n - all fields\n\n Multiple fields/ranges can be separated with commas\n\n FORMAT must be suitable for printing one floating-point argument '%f'. Optional quote (%'f) will enable\n --grouping (if supported by current locale). Optional width value (%10f) will pad output. Optional zero (%010f)\n width will zero pad the number. Optional negative values (%-10f) will left align. Optional precision (%.1f)\n will override the input determined precision.\n\n Exit status is 0 if all input numbers were successfully converted. By default, numfmt will stop at the first\n conversion error with exit status 2. With --invalid='fail' a warning is printed for each conversion error and\n the exit status is 2. With --invalid='warn' each conversion error is diagnosed, but the exit status is 0. With\n --invalid='ignore' conversion errors are not diagnosed and the exit status is 0."} | |
| {"instruction": "What does the command `dir` do?", "output": "dir - list directory contents"} | |
| {"instruction": "How is the `dir` used?", "output": "dir [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `dir`?", "output": "List information about the FILEs (the current directory by default). Sort entries\n alphabetically if none of -cftuvSUX nor --sort is specified.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --all\n do not ignore entries starting with .\n\n -A, --almost-all\n do not list implied . and ..\n\n --author\n with -l, print the author of each file\n\n -b, --escape\n print C-style escapes for nongraphic characters\n\n --block-size=SIZE\n with -l, scale sizes by SIZE when printing them; e.g., '--block-size=M'; see\n SIZE format below\n\n -B, --ignore-backups\n do not list implied entries ending with ~\n\n -c with -lt: sort by, and show, ctime (time of last change of file status infor\u2010\n mation); with -l: show ctime and sort by name; otherwise: sort by ctime,\n newest first\n\n -C list entries by columns\n\n --color[=WHEN]\n color the output WHEN; more info below\n\n -d, --directory\n list directories themselves, not their contents\n\n -D, --dired\n generate output designed for Emacs' dired mode\n\n -f list all entries in directory order\n\n -F, --classify[=WHEN]\n append indicator (one of */=>@|) to entries WHEN\n\n --file-type\n likewise, except do not append '*'\n\n --format=WORD\n across -x, commas -m, horizontal -x, long -l, single-column -1, verbose -l,\n vertical -C\n\n --full-time\n like -l --time-style=full-iso\n\n -g like -l, but do not list owner\n\n --group-directories-first\n group directories before files; can be augmented with a --sort option, but\n any use of --sort=none (-U) disables grouping\n\n -G, --no-group\n in a long listing, don't print group names\n\n -h, --human-readable\n with -l and -s, print sizes like 1K 234M 2G etc.\n\n --si likewise, but use powers of 1000 not 1024\n\n -H, --dereference-command-line\n follow symbolic links listed on the command line\n\n --dereference-command-line-symlink-to-dir\n follow each command line symbolic link that points to a directory\n\n --hide=PATTERN\n do not list implied entries matching shell PATTERN (overridden by -a or -A)\n\n --hyperlink[=WHEN]\n hyperlink file names WHEN\n\n --indicator-style=WORD\n append indicator with style WORD to entry names: none (default), slash (-p),\n file-type (--file-type), classify (-F)\n\n -i, --inode\n print the index number of each file\n\n -I, --ignore=PATTERN\n do not list implied entries matching shell PATTERN\n\n -k, --kibibytes\n default to 1024-byte blocks for file system usage; used only with -s and per\n directory totals\n\n -l use a long listing format\n\n -L, --dereference\n when showing file information for a symbolic link, show information for the\n file the link references rather than for the link itself\n\n -m fill width with a comma separated list of entries\n\n -n, --numeric-uid-gid\n like -l, but list numeric user and group IDs\n\n -N, --literal\n print entry names without quoting\n\n -o like -l, but do not list group information\n\n -p, --indicator-style=slash\n append / indicator to directories\n\n -q, --hide-control-chars\n print ? instead of nongraphic characters\n\n --show-control-chars\n show nongraphic characters as-is (the default, unless program is 'ls' and\n output is a terminal)\n\n -Q, --quote-name\n enclose entry names in double quotes\n\n --quoting-style=WORD\n use quoting style WORD for entry names: literal, locale, shell, shell-always,\n shell-escape, shell-escape-always, c, escape (overrides QUOTING_STYLE envi\u2010\n ronment variable)\n\n -r, --reverse\n reverse order while sorting\n\n -R, --recursive\n list subdirectories recursively\n\n -s, --size\n print the allocated size of each file, in blocks\n\n -S sort by file size, largest first\n\n --sort=WORD\n sort by WORD instead of name: none (-U), size (-S), time (-t), version (-v),\n extension (-X), width\n\n --time=WORD\n select which timestamp used to display or sort; access time (-u): atime, ac\u2010\n cess, use; metadata change time (-c): ctime, status; modified time (default):\n mtime, modification; birth time: birth, creation;\n\n with -l, WORD determines which time to show; with --sort=time, sort by WORD\n (newest first)\n\n --time-style=TIME_STYLE\n time/date format with -l; see TIME_STYLE below\n\n -t sort by time, newest first; see --time\n\n -T, --tabsize=COLS\n assume tab stops at each COLS instead of 8\n\n -u with -lt: sort by, and show, access time; with -l: show access time and sort\n by name; otherwise: sort by access time, newest first\n\n -U do not sort; list entries in directory order\n\n -v natural sort of (version) numbers within text\n\n -w, --width=COLS\n set output width to COLS. 0 means no limit\n\n -x list entries by lines instead of by columns\n\n -X sort alphabetically by entry extension\n\n -Z, --context\n print any security context of each file\n\n --zero end each output line with NUL, not newline\n\n -1 list one file per line\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The SIZE argument is an integer and optional unit (example: 10K is 10*1024). Units\n are K,M,G,T,P,E,Z,Y,R,Q (powers of 1024) or KB,MB,... (powers of 1000). Binary pre\u2010\n fixes can be used, too: KiB=K, MiB=M, and so on.\n\n The TIME_STYLE argument can be full-iso, long-iso, iso, locale, or +FORMAT. FORMAT\n is interpreted like in date(1). If FORMAT is FORMAT1<newline>FORMAT2, then FORMAT1\n applies to non-recent files and FORMAT2 to recent files. TIME_STYLE prefixed with\n 'posix-' takes effect only outside the POSIX locale. Also the TIME_STYLE environ\u2010\n ment variable sets the default style to use.\n\n The WHEN argument defaults to 'always' and can also be 'auto' or 'never'.\n\n Using color to distinguish file types is disabled both by default and with\n --color=never. With --color=auto, ls emits color codes only when standard output is\n connected to a terminal. The LS_COLORS environment variable can change the set\u2010\n tings. Use the dircolors(1) command to set it.\n\n Exit status:\n 0 if OK,\n\n 1 if minor problems (e.g., cannot access subdirectory),\n\n 2 if serious trouble (e.g., cannot access command-line argument)."} | |
| {"instruction": "What does the command `groups` do?", "output": "groups - print the groups a user is in"} | |
| {"instruction": "How is the `groups` used?", "output": "groups [OPTION]... [USERNAME]..."} | |
| {"instruction": "What is the detailed desciption of the `groups`?", "output": "Print group memberships for each USERNAME or, if no USERNAME is specified, for the current process (which may\n differ if the groups database has changed).\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `printenv` do?", "output": "printenv - print all or part of environment"} | |
| {"instruction": "How is the `printenv` used?", "output": "printenv [OPTION]... [VARIABLE]..."} | |
| {"instruction": "What is the detailed desciption of the `printenv`?", "output": "Print the values of the specified environment VARIABLE(s). If no VARIABLE is specified, print name and value\n pairs for them all.\n\n -0, --null\n end each output line with NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n NOTE: your shell may have its own version of printenv, which usually supersedes the version described here.\n Please refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `shred` do?", "output": "shred - overwrite a file to hide its contents, and optionally delete it"} | |
| {"instruction": "How is the `shred` used?", "output": "shred [OPTION]... FILE..."} | |
| {"instruction": "What is the detailed desciption of the `shred`?", "output": "Overwrite the specified FILE(s) repeatedly, in order to make it harder for even very expensive hardware probing\n to recover the data.\n\n If FILE is -, shred standard output.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -f, --force\n change permissions to allow writing if necessary\n\n -n, --iterations=N\n overwrite N times instead of the default (3)\n\n --random-source=FILE\n get random bytes from FILE\n\n -s, --size=N\n shred this many bytes (suffixes like K, M, G accepted)\n\n -u deallocate and remove file after overwriting\n\n --remove[=HOW]\n like -u but give control on HOW to delete; See below\n\n -v, --verbose\n show progress\n\n -x, --exact\n do not round file sizes up to the next full block;\n\n this is the default for non-regular files\n\n -z, --zero\n add a final overwrite with zeros to hide shredding\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Delete FILE(s) if --remove (-u) is specified. The default is not to remove the files because it is common to\n operate on device files like /dev/hda, and those files usually should not be removed. The optional HOW parame\u2010\n ter indicates how to remove a directory entry: 'unlink' => use a standard unlink call. 'wipe' => also first ob\u2010\n fuscate bytes in the name. 'wipesync' => also sync each obfuscated byte to the device. The default mode is\n 'wipesync', but note it can be expensive.\n\n CAUTION: shred assumes the file system and hardware overwrite data in place. Although this is common, many\n platforms operate otherwise. Also, backups and mirrors may contain unremovable copies that will let a shredded\n file be recovered later. See the GNU coreutils manual for details."} | |
| {"instruction": "What does the command `du` do?", "output": "du - estimate file space usage"} | |
| {"instruction": "How is the `du` used?", "output": "du [OPTION]... [FILE]...\n du [OPTION]... --files0-from=F"} | |
| {"instruction": "What is the detailed desciption of the `du`?", "output": "Summarize device usage of the set of FILEs, recursively for directories.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -0, --null\n end each output line with NUL, not newline\n\n -a, --all\n write counts for all files, not just directories\n\n --apparent-size\n print apparent sizes rather than device usage; although the apparent size is usually smaller, it may be\n larger due to holes in ('sparse') files, internal fragmentation, indirect blocks, and the like\n\n -B, --block-size=SIZE\n scale sizes by SIZE before printing them; e.g., '-BM' prints sizes in units of 1,048,576 bytes; see SIZE\n format below\n\n -b, --bytes\n equivalent to '--apparent-size --block-size=1'\n\n -c, --total\n produce a grand total\n\n -D, --dereference-args\n dereference only symlinks that are listed on the command line\n\n -d, --max-depth=N\n print the total for a directory (or file, with --all) only if it is N or fewer levels below the command\n line argument; --max-depth=0 is the same as --summarize\n\n --files0-from=F\n summarize device usage of the NUL-terminated file names specified in file F; if F is -, then read names\n from standard input\n\n -H equivalent to --dereference-args (-D)\n\n -h, --human-readable\n print sizes in human readable format (e.g., 1K 234M 2G)\n\n --inodes\n list inode usage information instead of block usage\n\n -k like --block-size=1K\n\n -L, --dereference\n dereference all symbolic links\n\n -l, --count-links\n count sizes many times if hard linked\n\n -m like --block-size=1M\n\n -P, --no-dereference\n don't follow any symbolic links (this is the default)\n\n -S, --separate-dirs\n for directories do not include size of subdirectories\n\n --si like -h, but use powers of 1000 not 1024\n\n -s, --summarize\n display only a total for each argument\n\n -t, --threshold=SIZE\n exclude entries smaller than SIZE if positive, or entries greater than SIZE if negative\n\n --time show time of the last modification of any file in the directory, or any of its subdirectories\n\n --time=WORD\n show time as WORD instead of modification time: atime, access, use, ctime or status\n\n --time-style=STYLE\n show times using STYLE, which can be: full-iso, long-iso, iso, or +FORMAT; FORMAT is interpreted like in\n 'date'\n\n -X, --exclude-from=FILE\n exclude files that match any pattern in FILE\n\n --exclude=PATTERN\n exclude files that match PATTERN\n\n -x, --one-file-system\n skip directories on different file systems\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Display values are in units of the first available SIZE from --block-size, and the DU_BLOCK_SIZE, BLOCK_SIZE and\n BLOCKSIZE environment variables. Otherwise, units default to 1024 bytes (or 512 if POSIXLY_CORRECT is set).\n\n The SIZE argument is an integer and optional unit (example: 10K is 10*1024). Units are K,M,G,T,P,E,Z,Y,R,Q\n (powers of 1024) or KB,MB,... (powers of 1000). Binary prefixes can be used, too: KiB=K, MiB=M, and so on."} | |
| {"instruction": "What does the command `sha224sum` do?", "output": "sha224sum - compute and check SHA224 message digest"} | |
| {"instruction": "How is the `sha224sum` used?", "output": "sha224sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `sha224sum`?", "output": "Print or check SHA224 (224-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n -b, --binary\n read in binary mode\n\n -c, --check\n read checksums from the FILEs and check them\n\n --tag create a BSD-style checksum\n\n -t, --text\n read in text mode (default)\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The sums are computed as described in RFC 3874. When checking, the input should be a former output of this pro\u2010\n gram. The default mode is to print a line with: checksum, a space, a character indicating input mode ('*' for\n binary, ' ' for text or where binary is insignificant), and name for each FILE.\n\n Note: There is no difference between binary mode and text mode on GNU systems."} | |
| {"instruction": "What does the command `chgrp` do?", "output": "chgrp - change group ownership"} | |
| {"instruction": "How is the `chgrp` used?", "output": "chgrp [OPTION]... GROUP FILE...\n chgrp [OPTION]... --reference=RFILE FILE..."} | |
| {"instruction": "What is the detailed desciption of the `chgrp`?", "output": "Change the group of each FILE to GROUP. With --reference, change the group of each\n FILE to that of RFILE.\n\n -c, --changes\n like verbose but report only when a change is made\n\n -f, --silent, --quiet\n suppress most error messages\n\n -v, --verbose\n output a diagnostic for every file processed\n\n --dereference\n affect the referent of each symbolic link (this is the default), rather than\n the symbolic link itself\n\n -h, --no-dereference\n affect symbolic links instead of any referenced file (useful only on systems\n that can change the ownership of a symlink)\n\n --no-preserve-root\n do not treat '/' specially (the default)\n\n --preserve-root\n fail to operate recursively on '/'\n\n --reference=RFILE\n use RFILE's group rather than specifying a GROUP. RFILE is always derefer\u2010\n enced if a symbolic link.\n\n -R, --recursive\n operate on files and directories recursively\n\n The following options modify how a hierarchy is traversed when the -R option is also\n specified. If more than one is specified, only the final one takes effect.\n\n -H if a command line argument is a symbolic link to a directory, traverse it\n\n -L traverse every symbolic link to a directory encountered\n\n -P do not traverse any symbolic links (default)\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `touch` do?", "output": "touch - change file timestamps"} | |
| {"instruction": "How is the `touch` used?", "output": "touch [OPTION]... FILE..."} | |
| {"instruction": "What is the detailed desciption of the `touch`?", "output": "Update the access and modification times of each FILE to the current time.\n\n A FILE argument that does not exist is created empty, unless -c or -h is supplied.\n\n A FILE argument string of - is handled specially and causes touch to change the times of the file associated\n with standard output.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a change only the access time\n\n -c, --no-create\n do not create any files\n\n -d, --date=STRING\n parse STRING and use it instead of current time\n\n -f (ignored)\n\n -h, --no-dereference\n affect each symbolic link instead of any referenced file (useful only on systems that can change the\n timestamps of a symlink)\n\n -m change only the modification time\n\n -r, --reference=FILE\n use this file's times instead of current time\n\n -t STAMP\n use [[CC]YY]MMDDhhmm[.ss] instead of current time\n\n --time=WORD\n change the specified time: WORD is access, atime, or use: equivalent to -a WORD is modify or mtime:\n equivalent to -m\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Note that the -d and -t options accept different time-date formats."} | |
| {"instruction": "What does the command `runcon` do?", "output": "runcon - run command with specified security context"} | |
| {"instruction": "How is the `runcon` used?", "output": "runcon CONTEXT COMMAND [args]\n runcon [ -c ] [-u USER] [-r ROLE] [-t TYPE] [-l RANGE] COMMAND [args]"} | |
| {"instruction": "What is the detailed desciption of the `runcon`?", "output": "Run COMMAND with completely-specified CONTEXT, or with current or transitioned security context modified by one\n or more of LEVEL, ROLE, TYPE, and USER.\n\n If none of -c, -t, -u, -r, or -l, is specified, the first argument is used as the complete context. Any addi\u2010\n tional arguments after COMMAND are interpreted as arguments to the command.\n\n Note that only carefully-chosen contexts are likely to successfully run.\n\n Run a program in a different SELinux security context. With neither CONTEXT nor COMMAND, print the current se\u2010\n curity context.\n\n Mandatory arguments to long options are mandatory for short options too."} | |
| {"instruction": "What does the command `stat` do?", "output": "stat - display file or file system status"} | |
| {"instruction": "How is the `stat` used?", "output": "stat [OPTION]... FILE..."} | |
| {"instruction": "What is the detailed desciption of the `stat`?", "output": "Display file or file system status.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -L, --dereference\n follow links\n\n -f, --file-system\n display file system status instead of file status\n\n --cached=MODE\n specify how to use cached attributes; useful on remote file systems. See MODE below\n\n -c --format=FORMAT\n use the specified FORMAT instead of the default; output a newline after each use of FORMAT\n\n --printf=FORMAT\n like --format, but interpret backslash escapes, and do not output a mandatory trailing newline; if you\n want a newline, include \\n in FORMAT\n\n -t, --terse\n print the information in terse form\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The MODE argument of --cached can be: always, never, or default. 'always' will use cached attributes if avail\u2010\n able, while 'never' will try to synchronize with the latest attributes, and 'default' will leave it up to the\n underlying file system.\n\n The valid format sequences for files (without --file-system):\n\n %a permission bits in octal (note '#' and '0' printf flags)\n\n %A permission bits and file type in human readable form\n\n %b number of blocks allocated (see %B)\n\n %B the size in bytes of each block reported by %b\n\n %C SELinux security context string\n\n %d device number in decimal (st_dev)\n\n %D device number in hex (st_dev)\n\n %Hd major device number in decimal\n\n %Ld minor device number in decimal\n\n %f raw mode in hex\n\n %F file type\n\n %g group ID of owner\n\n %G group name of owner\n\n %h number of hard links\n\n %i inode number\n\n %m mount point\n\n %n file name\n\n %N quoted file name with dereference if symbolic link\n\n %o optimal I/O transfer size hint\n\n %s total size, in bytes\n\n %r device type in decimal (st_rdev)\n\n %R device type in hex (st_rdev)\n\n %Hr major device type in decimal, for character/block device special files\n\n %Lr minor device type in decimal, for character/block device special files\n\n %t major device type in hex, for character/block device special files\n\n %T minor device type in hex, for character/block device special files\n\n %u user ID of owner\n\n %U user name of owner\n\n %w time of file birth, human-readable; - if unknown\n\n %W time of file birth, seconds since Epoch; 0 if unknown\n\n %x time of last access, human-readable\n\n %X time of last access, seconds since Epoch\n\n %y time of last data modification, human-readable\n\n %Y time of last data modification, seconds since Epoch\n\n %z time of last status change, human-readable\n\n %Z time of last status change, seconds since Epoch\n\n Valid format sequences for file systems:\n\n %a free blocks available to non-superuser\n\n %b total data blocks in file system\n\n %c total file nodes in file system\n\n %d free file nodes in file system\n\n %f free blocks in file system\n\n %i file system ID in hex\n\n %l maximum length of filenames\n\n %n file name\n\n %s block size (for faster transfers)\n\n %S fundamental block size (for block counts)\n\n %t file system type in hex\n\n %T file system type in human readable form\n\n --terse is equivalent to the following FORMAT:\n %n %s %b %f %u %g %D %i %h %t %T %X %Y %Z %W %o %C\n\n --terse --file-system is equivalent to the following FORMAT:\n %n %i %l %t %s %S %b %f %a %c %d\n\n NOTE: your shell may have its own version of stat, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `sleep` do?", "output": "sleep - delay for a specified amount of time"} | |
| {"instruction": "How is the `sleep` used?", "output": "sleep NUMBER[SUFFIX]...\n sleep OPTION"} | |
| {"instruction": "What is the detailed desciption of the `sleep`?", "output": "Pause for NUMBER seconds. SUFFIX may be 's' for seconds (the default), 'm' for minutes, 'h' for hours or 'd'\n for days. NUMBER need not be an integer. Given two or more arguments, pause for the amount of time specified\n by the sum of their values.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `pwd` do?", "output": "pwd - print name of current/working directory"} | |
| {"instruction": "How is the `pwd` used?", "output": "pwd [OPTION]..."} | |
| {"instruction": "What is the detailed desciption of the `pwd`?", "output": "Print the full filename of the current working directory.\n\n -L, --logical\n use PWD from environment, even if it contains symlinks\n\n -P, --physical\n avoid all symlinks\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If no option is specified, -P is assumed.\n\n NOTE: your shell may have its own version of pwd, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `nice` do?", "output": "nice - run a program with modified scheduling priority"} | |
| {"instruction": "How is the `nice` used?", "output": "nice [OPTION] [COMMAND [ARG]...]"} | |
| {"instruction": "What is the detailed desciption of the `nice`?", "output": "Run COMMAND with an adjusted niceness, which affects process scheduling. With no COMMAND, print the current\n niceness. Niceness values range from -20 (most favorable to the process) to 19 (least favorable to the\n process).\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -n, --adjustment=N\n add integer N to the niceness (default 10)\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n NOTE: your shell may have its own version of nice, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports.\n\n Exit status:\n 125 if the nice command itself fails\n\n 126 if COMMAND is found but cannot be invoked\n\n 127 if COMMAND cannot be found\n\n - the exit status of COMMAND otherwise"} | |
| {"instruction": "What does the command `chcon` do?", "output": "chcon - change file security context"} | |
| {"instruction": "How is the `chcon` used?", "output": "chcon [OPTION]... CONTEXT FILE...\n chcon [OPTION]... [-u USER] [-r ROLE] [-l RANGE] [-t TYPE] FILE...\n chcon [OPTION]... --reference=RFILE FILE..."} | |
| {"instruction": "What is the detailed desciption of the `chcon`?", "output": "Change the SELinux security context of each FILE to CONTEXT. With --reference,\n change the security context of each FILE to that of RFILE.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n --dereference\n affect the referent of each symbolic link (this is the default), rather than\n the symbolic link itself\n\n -h, --no-dereference\n affect symbolic links instead of any referenced file\n\n -u, --user=USER\n set user USER in the target security context\n\n -r, --role=ROLE\n set role ROLE in the target security context\n\n -t, --type=TYPE\n set type TYPE in the target security context\n\n -l, --range=RANGE\n set range RANGE in the target security context\n\n --no-preserve-root\n do not treat '/' specially (the default)\n\n --preserve-root\n fail to operate recursively on '/'\n\n --reference=RFILE\n use RFILE's security context rather than specifying a CONTEXT value\n\n -R, --recursive\n operate on files and directories recursively\n\n -v, --verbose\n output a diagnostic for every file processed\n\n The following options modify how a hierarchy is traversed when the -R option is also\n specified. If more than one is specified, only the final one takes effect.\n\n -H if a command line argument is a symbolic link to a directory, traverse it\n\n -L traverse every symbolic link to a directory encountered\n\n -P do not traverse any symbolic links (default)\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `tail` do?", "output": "tail - output the last part of files"} | |
| {"instruction": "How is the `tail` used?", "output": "tail [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `tail`?", "output": "Print the last 10 lines of each FILE to standard output. With more than one FILE, precede each with a header\n giving the file name.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -c, --bytes=[+]NUM\n output the last NUM bytes; or use -c +NUM to output starting with byte NUM of each file\n\n -f, --follow[={name|descriptor}]\n output appended data as the file grows;\n\n an absent option argument means 'descriptor'\n\n -F same as --follow=name --retry\n\n -n, --lines=[+]NUM\n output the last NUM lines, instead of the last 10; or use -n +NUM to skip NUM-1 lines at the start\n\n --max-unchanged-stats=N\n with --follow=name, reopen a FILE which has not\n\n changed size after N (default 5) iterations to see if it has been unlinked or renamed (this is the usual\n case of rotated log files); with inotify, this option is rarely useful\n\n --pid=PID\n with -f, terminate after process ID, PID dies\n\n -q, --quiet, --silent\n never output headers giving file names\n\n --retry\n keep trying to open a file if it is inaccessible\n\n -s, --sleep-interval=N\n with -f, sleep for approximately N seconds (default 1.0) between iterations; with inotify and --pid=P,\n check process P at least once every N seconds\n\n -v, --verbose\n always output headers giving file names\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n NUM may have a multiplier suffix: b 512, kB 1000, K 1024, MB 1000*1000, M 1024*1024, GB 1000*1000*1000, G\n 1024*1024*1024, and so on for T, P, E, Z, Y, R, Q. Binary prefixes can be used, too: KiB=K, MiB=M, and so on.\n\n With --follow (-f), tail defaults to following the file descriptor, which means that even if a tail'ed file is\n renamed, tail will continue to track its end. This default behavior is not desirable when you really want to\n track the actual name of the file, not the file descriptor (e.g., log rotation). Use --follow=name in that\n case. That causes tail to track the named file in a way that accommodates renaming, removal and creation."} | |
| {"instruction": "What does the command `false` do?", "output": "false - do nothing, unsuccessfully"} | |
| {"instruction": "How is the `false` used?", "output": "false [ignored command line arguments]\n false OPTION"} | |
| {"instruction": "What is the detailed desciption of the `false`?", "output": "Exit with a status code indicating failure.\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n NOTE: your shell may have its own version of false, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `cat` do?", "output": "cat - concatenate files and print on the standard output"} | |
| {"instruction": "How is the `cat` used?", "output": "cat [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `cat`?", "output": "Concatenate FILE(s) to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n -A, --show-all\n equivalent to -vET\n\n -b, --number-nonblank\n number nonempty output lines, overrides -n\n\n -e equivalent to -vE\n\n -E, --show-ends\n display $ at end of each line\n\n -n, --number\n number all output lines\n\n -s, --squeeze-blank\n suppress repeated empty output lines\n\n -t equivalent to -vT\n\n -T, --show-tabs\n display TAB characters as ^I\n\n -u (ignored)\n\n -v, --show-nonprinting\n use ^ and M- notation, except for LFD and TAB\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `env` do?", "output": "env - run a program in a modified environment"} | |
| {"instruction": "How is the `env` used?", "output": "env [OPTION]... [-] [NAME=VALUE]... [COMMAND [ARG]...]"} | |
| {"instruction": "What is the detailed desciption of the `env`?", "output": "Set each NAME to VALUE in the environment and run COMMAND.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -i, --ignore-environment\n start with an empty environment\n\n -0, --null\n end each output line with NUL, not newline\n\n -u, --unset=NAME\n remove variable from the environment\n\n -C, --chdir=DIR\n change working directory to DIR\n\n -S, --split-string=S\n process and split S into separate arguments; used to pass multiple arguments on shebang lines\n\n --block-signal[=SIG]\n block delivery of SIG signal(s) to COMMAND\n\n --default-signal[=SIG]\n reset handling of SIG signal(s) to the default\n\n --ignore-signal[=SIG]\n set handling of SIG signal(s) to do nothing\n\n --list-signal-handling\n list non default signal handling to stderr\n\n -v, --debug\n print verbose information for each processing step\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n A mere - implies -i. If no COMMAND, print the resulting environment.\n\n SIG may be a signal name like 'PIPE', or a signal number like '13'. Without SIG, all known signals are in\u2010\n cluded. Multiple signals can be comma-separated. An empty SIG argument is a no-op.\n\n Exit status:\n 125 if the env command itself fails\n\n 126 if COMMAND is found but cannot be invoked\n\n 127 if COMMAND cannot be found\n\n - the exit status of COMMAND otherwise"} | |
| {"instruction": "What does the command `printf` do?", "output": "printf - format and print data"} | |
| {"instruction": "How is the `printf` used?", "output": "printf FORMAT [ARGUMENT]...\n printf OPTION"} | |
| {"instruction": "What is the detailed desciption of the `printf`?", "output": "Print ARGUMENT(s) according to FORMAT, or execute according to OPTION:\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n FORMAT controls the output as in C printf. Interpreted sequences are:\n\n \\\" double quote\n\n \\\\ backslash\n\n \\a alert (BEL)\n\n \\b backspace\n\n \\c produce no further output\n\n \\e escape\n\n \\f form feed\n\n \\n new line\n\n \\r carriage return\n\n \\t horizontal tab\n\n \\v vertical tab\n\n \\NNN byte with octal value NNN (1 to 3 digits)\n\n \\xHH byte with hexadecimal value HH (1 to 2 digits)\n\n \\uHHHH Unicode (ISO/IEC 10646) character with hex value HHHH (4 digits)\n\n \\UHHHHHHHH\n Unicode character with hex value HHHHHHHH (8 digits)\n\n %% a single %\n\n %b ARGUMENT as a string with '\\' escapes interpreted, except that octal escapes are of the form \\0 or \\0NNN\n\n %q ARGUMENT is printed in a format that can be reused as shell input, escaping non-printable characters with\n the proposed POSIX $'' syntax.\n\n and all C format specifications ending with one of diouxXfeEgGcs, with ARGUMENTs converted to proper type first.\n Variable widths are handled.\n\n NOTE: your shell may have its own version of printf, which usually supersedes the version described here.\n Please refer to your shell's documentation for details about the options it supports."} | |
| {"instruction": "What does the command `tr` do?", "output": "tr - translate or delete characters"} | |
| {"instruction": "How is the `tr` used?", "output": "tr [OPTION]... STRING1 [STRING2]"} | |
| {"instruction": "What is the detailed desciption of the `tr`?", "output": "Translate, squeeze, and/or delete characters from standard input, writing to standard output. STRING1 and\n STRING2 specify arrays of characters ARRAY1 and ARRAY2 that control the action.\n\n -c, -C, --complement\n use the complement of ARRAY1\n\n -d, --delete\n delete characters in ARRAY1, do not translate\n\n -s, --squeeze-repeats\n replace each sequence of a repeated character that is listed in the last specified ARRAY, with a single\n occurrence of that character\n\n -t, --truncate-set1\n first truncate ARRAY1 to length of ARRAY2\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n ARRAYs are specified as strings of characters. Most represent themselves. Interpreted sequences are:\n\n \\NNN character with octal value NNN (1 to 3 octal digits)\n\n \\\\ backslash\n\n \\a audible BEL\n\n \\b backspace\n\n \\f form feed\n\n \\n new line\n\n \\r return\n\n \\t horizontal tab\n\n \\v vertical tab\n\n CHAR1-CHAR2\n all characters from CHAR1 to CHAR2 in ascending order\n\n [CHAR*]\n in ARRAY2, copies of CHAR until length of ARRAY1\n\n [CHAR*REPEAT]\n REPEAT copies of CHAR, REPEAT octal if starting with 0\n\n [:alnum:]\n all letters and digits\n\n [:alpha:]\n all letters\n\n [:blank:]\n all horizontal whitespace\n\n [:cntrl:]\n all control characters\n\n [:digit:]\n all digits\n\n [:graph:]\n all printable characters, not including space\n\n [:lower:]\n all lower case letters\n\n [:print:]\n all printable characters, including space\n\n [:punct:]\n all punctuation characters\n\n [:space:]\n all horizontal or vertical whitespace\n\n [:upper:]\n all upper case letters\n\n [:xdigit:]\n all hexadecimal digits\n\n [=CHAR=]\n all characters which are equivalent to CHAR\n\n Translation occurs if -d is not given and both STRING1 and STRING2 appear. -t is only significant when trans\u2010\n lating. ARRAY2 is extended to length of ARRAY1 by repeating its last character as necessary. Excess characters\n of ARRAY2 are ignored. Character classes expand in unspecified order; while translating, [:lower:] and [:up\u2010\n per:] may be used in pairs to specify case conversion. Squeezing occurs after translation or deletion."} | |
| {"instruction": "What does the command `vdir` do?", "output": "vdir - list directory contents"} | |
| {"instruction": "How is the `vdir` used?", "output": "vdir [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `vdir`?", "output": "List information about the FILEs (the current directory by default). Sort entries alphabetically if none of\n -cftuvSUX nor --sort is specified.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --all\n do not ignore entries starting with .\n\n -A, --almost-all\n do not list implied . and ..\n\n --author\n with -l, print the author of each file\n\n -b, --escape\n print C-style escapes for nongraphic characters\n\n --block-size=SIZE\n with -l, scale sizes by SIZE when printing them; e.g., '--block-size=M'; see SIZE format below\n\n -B, --ignore-backups\n do not list implied entries ending with ~\n\n -c with -lt: sort by, and show, ctime (time of last change of file status information); with -l: show ctime\n and sort by name; otherwise: sort by ctime, newest first\n\n -C list entries by columns\n\n --color[=WHEN]\n color the output WHEN; more info below\n\n -d, --directory\n list directories themselves, not their contents\n\n -D, --dired\n generate output designed for Emacs' dired mode\n\n -f list all entries in directory order\n\n -F, --classify[=WHEN]\n append indicator (one of */=>@|) to entries WHEN\n\n --file-type\n likewise, except do not append '*'\n\n --format=WORD\n across -x, commas -m, horizontal -x, long -l, single-column -1, verbose -l, vertical -C\n\n --full-time\n like -l --time-style=full-iso\n\n -g like -l, but do not list owner\n\n --group-directories-first\n group directories before files; can be augmented with a --sort option, but any use of --sort=none (-U)\n disables grouping\n\n -G, --no-group\n in a long listing, don't print group names\n\n -h, --human-readable\n with -l and -s, print sizes like 1K 234M 2G etc.\n\n --si likewise, but use powers of 1000 not 1024\n\n -H, --dereference-command-line\n follow symbolic links listed on the command line\n\n --dereference-command-line-symlink-to-dir\n follow each command line symbolic link that points to a directory\n\n --hide=PATTERN\n do not list implied entries matching shell PATTERN (overridden by -a or -A)\n\n --hyperlink[=WHEN]\n hyperlink file names WHEN\n\n --indicator-style=WORD\n append indicator with style WORD to entry names: none (default), slash (-p), file-type (--file-type),\n classify (-F)\n\n -i, --inode\n print the index number of each file\n\n -I, --ignore=PATTERN\n do not list implied entries matching shell PATTERN\n\n -k, --kibibytes\n default to 1024-byte blocks for file system usage; used only with -s and per directory totals\n\n -l use a long listing format\n\n -L, --dereference\n when showing file information for a symbolic link, show information for the file the link references\n rather than for the link itself\n\n -m fill width with a comma separated list of entries\n\n -n, --numeric-uid-gid\n like -l, but list numeric user and group IDs\n\n -N, --literal\n print entry names without quoting\n\n -o like -l, but do not list group information\n\n -p, --indicator-style=slash\n append / indicator to directories\n\n -q, --hide-control-chars\n print ? instead of nongraphic characters\n\n --show-control-chars\n show nongraphic characters as-is (the default, unless program is 'ls' and output is a terminal)\n\n -Q, --quote-name\n enclose entry names in double quotes\n\n --quoting-style=WORD\n use quoting style WORD for entry names: literal, locale, shell, shell-always, shell-escape, shell-es\u2010\n cape-always, c, escape (overrides QUOTING_STYLE environment variable)\n\n -r, --reverse\n reverse order while sorting\n\n -R, --recursive\n list subdirectories recursively\n\n -s, --size\n print the allocated size of each file, in blocks\n\n -S sort by file size, largest first\n\n --sort=WORD\n sort by WORD instead of name: none (-U), size (-S), time (-t), version (-v), extension (-X), width\n\n --time=WORD\n select which timestamp used to display or sort; access time (-u): atime, access, use; metadata change\n time (-c): ctime, status; modified time (default): mtime, modification; birth time: birth, creation;\n\n with -l, WORD determines which time to show; with --sort=time, sort by WORD (newest first)\n\n --time-style=TIME_STYLE\n time/date format with -l; see TIME_STYLE below\n\n -t sort by time, newest first; see --time\n\n -T, --tabsize=COLS\n assume tab stops at each COLS instead of 8\n\n -u with -lt: sort by, and show, access time; with -l: show access time and sort by name; otherwise: sort by\n access time, newest first\n\n -U do not sort; list entries in directory order\n\n -v natural sort of (version) numbers within text\n\n -w, --width=COLS\n set output width to COLS. 0 means no limit\n\n -x list entries by lines instead of by columns\n\n -X sort alphabetically by entry extension\n\n -Z, --context\n print any security context of each file\n\n --zero end each output line with NUL, not newline\n\n -1 list one file per line\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The SIZE argument is an integer and optional unit (example: 10K is 10*1024). Units are K,M,G,T,P,E,Z,Y,R,Q\n (powers of 1024) or KB,MB,... (powers of 1000). Binary prefixes can be used, too: KiB=K, MiB=M, and so on.\n\n The TIME_STYLE argument can be full-iso, long-iso, iso, locale, or +FORMAT. FORMAT is interpreted like in\n date(1). If FORMAT is FORMAT1<newline>FORMAT2, then FORMAT1 applies to non-recent files and FORMAT2 to recent\n files. TIME_STYLE prefixed with 'posix-' takes effect only outside the POSIX locale. Also the TIME_STYLE envi\u2010\n ronment variable sets the default style to use.\n\n The WHEN argument defaults to 'always' and can also be 'auto' or 'never'.\n\n Using color to distinguish file types is disabled both by default and with --color=never. With --color=auto, ls\n emits color codes only when standard output is connected to a terminal. The LS_COLORS environment variable can\n change the settings. Use the dircolors(1) command to set it.\n\n Exit status:\n 0 if OK,\n\n 1 if minor problems (e.g., cannot access subdirectory),\n\n 2 if serious trouble (e.g., cannot access command-line argument)."} | |
| {"instruction": "What does the command `mv` do?", "output": "mv - move (rename) files"} | |
| {"instruction": "How is the `mv` used?", "output": "mv [OPTION]... [-T] SOURCE DEST\n mv [OPTION]... SOURCE... DIRECTORY\n mv [OPTION]... -t DIRECTORY SOURCE..."} | |
| {"instruction": "What is the detailed desciption of the `mv`?", "output": "Rename SOURCE to DEST, or move SOURCE(s) to DIRECTORY.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n --backup[=CONTROL]\n make a backup of each existing destination file\n\n -b like --backup but does not accept an argument\n\n --debug\n explain how a file is copied. Implies -v\n\n -f, --force\n do not prompt before overwriting\n\n -i, --interactive\n prompt before overwrite\n\n -n, --no-clobber\n do not overwrite an existing file\n\n If you specify more than one of -i, -f, -n, only the final one takes effect.\n\n --no-copy\n do not copy if renaming fails\n\n --strip-trailing-slashes\n remove any trailing slashes from each SOURCE argument\n\n -S, --suffix=SUFFIX\n override the usual backup suffix\n\n -t, --target-directory=DIRECTORY\n move all SOURCE arguments into DIRECTORY\n\n -T, --no-target-directory\n treat DEST as a normal file\n\n --update[=UPDATE]\n control which existing files are updated; UPDATE={all,none,older(default)}. See below\n\n -u equivalent to --update[=older]\n\n -v, --verbose\n explain what is being done\n\n -Z, --context\n set SELinux security context of destination file to default type\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n UPDATE controls which existing files in the destination are replaced. 'all' is the default operation when an\n --update option is not specified, and results in all existing files in the destination being replaced. 'none'\n is similar to the --no-clobber option, in that no files in the destination are replaced, but also skipped files\n do not induce a failure. 'older' is the default operation when --update is specified, and results in files be\u2010\n ing replaced if they're older than the corresponding source file.\n\n The backup suffix is '~', unless set with --suffix or SIMPLE_BACKUP_SUFFIX. The version control method may be\n selected via the --backup option or through the VERSION_CONTROL environment variable. Here are the values:\n\n none, off\n never make backups (even if --backup is given)\n\n numbered, t\n make numbered backups\n\n existing, nil\n numbered if numbered backups exist, simple otherwise\n\n simple, never\n always make simple backups"} | |
| {"instruction": "What does the command `seq` do?", "output": "seq - print a sequence of numbers"} | |
| {"instruction": "How is the `seq` used?", "output": "seq [OPTION]... LAST\n seq [OPTION]... FIRST LAST\n seq [OPTION]... FIRST INCREMENT LAST"} | |
| {"instruction": "What is the detailed desciption of the `seq`?", "output": "Print numbers from FIRST to LAST, in steps of INCREMENT.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -f, --format=FORMAT\n use printf style floating-point FORMAT\n\n -s, --separator=STRING\n use STRING to separate numbers (default: \\n)\n\n -w, --equal-width\n equalize width by padding with leading zeroes\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If FIRST or INCREMENT is omitted, it defaults to 1. That is, an omitted INCREMENT defaults to 1 even when LAST\n is smaller than FIRST. The sequence of numbers ends when the sum of the current number and INCREMENT would be\u2010\n come greater than LAST. FIRST, INCREMENT, and LAST are interpreted as floating point values. INCREMENT is usu\u2010\n ally positive if FIRST is smaller than LAST, and INCREMENT is usually negative if FIRST is greater than LAST.\n INCREMENT must not be 0; none of FIRST, INCREMENT and LAST may be NaN. FORMAT must be suitable for printing one\n argument of type 'double'; it defaults to %.PRECf if FIRST, INCREMENT, and LAST are all fixed point decimal num\u2010\n bers with maximum precision PREC, and to %g otherwise."} | |
| {"instruction": "What does the command `stty` do?", "output": "stty - change and print terminal line settings"} | |
| {"instruction": "How is the `stty` used?", "output": "stty [-F DEVICE | --file=DEVICE] [SETTING]...\n stty [-F DEVICE | --file=DEVICE] [-a|--all]\n stty [-F DEVICE | --file=DEVICE] [-g|--save]"} | |
| {"instruction": "What is the detailed desciption of the `stty`?", "output": "Print or change terminal characteristics.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --all\n print all current settings in human-readable form\n\n -g, --save\n print all current settings in a stty-readable form\n\n -F, --file=DEVICE\n open and use the specified DEVICE instead of stdin\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Optional - before SETTING indicates negation. An * marks non-POSIX settings. The underlying system defines\n which settings are available.\n\n Special characters:\n * discard CHAR\n CHAR will toggle discarding of output\n\n eof CHAR\n CHAR will send an end of file (terminate the input)\n\n eol CHAR\n CHAR will end the line\n\n * eol2 CHAR\n alternate CHAR for ending the line\n\n erase CHAR\n CHAR will erase the last character typed\n\n intr CHAR\n CHAR will send an interrupt signal\n\n kill CHAR\n CHAR will erase the current line\n\n * lnext CHAR\n CHAR will enter the next character quoted\n\n quit CHAR\n CHAR will send a quit signal\n\n * rprnt CHAR\n CHAR will redraw the current line\n\n start CHAR\n CHAR will restart the output after stopping it\n\n stop CHAR\n CHAR will stop the output\n\n susp CHAR\n CHAR will send a terminal stop signal\n\n * swtch CHAR\n CHAR will switch to a different shell layer\n\n * werase CHAR\n CHAR will erase the last word typed\n\n Special settings:\n N set the input and output speeds to N bauds\n\n * cols N\n tell the kernel that the terminal has N columns\n\n * columns N\n same as cols N\n\n * [-]drain\n wait for transmission before applying settings (on by default)\n\n ispeed N\n set the input speed to N\n\n * line N\n use line discipline N\n\n min N with -icanon, set N characters minimum for a completed read\n\n ospeed N\n set the output speed to N\n\n * rows N\n tell the kernel that the terminal has N rows\n\n * size print the number of rows and columns according to the kernel\n\n speed print the terminal speed\n\n time N with -icanon, set read timeout of N tenths of a second\n\n Control settings:\n [-]clocal\n disable modem control signals\n\n [-]cread\n allow input to be received\n\n * [-]crtscts\n enable RTS/CTS handshaking\n\n csN set character size to N bits, N in [5..8]\n\n [-]cstopb\n use two stop bits per character (one with '-')\n\n [-]hup send a hangup signal when the last process closes the tty\n\n [-]hupcl\n same as [-]hup\n\n [-]parenb\n generate parity bit in output and expect parity bit in input\n\n [-]parodd\n set odd parity (or even parity with '-')\n\n * [-]cmspar\n use \"stick\" (mark/space) parity\n\n Input settings:\n [-]brkint\n breaks cause an interrupt signal\n\n [-]icrnl\n translate carriage return to newline\n\n [-]ignbrk\n ignore break characters\n\n [-]igncr\n ignore carriage return\n\n [-]ignpar\n ignore characters with parity errors\n\n * [-]imaxbel\n beep and do not flush a full input buffer on a character\n\n [-]inlcr\n translate newline to carriage return\n\n [-]inpck\n enable input parity checking\n\n [-]istrip\n clear high (8th) bit of input characters\n\n * [-]iutf8\n assume input characters are UTF-8 encoded\n\n * [-]iuclc\n translate uppercase characters to lowercase\n\n * [-]ixany\n let any character restart output, not only start character\n\n [-]ixoff\n enable sending of start/stop characters\n\n [-]ixon\n enable XON/XOFF flow control\n\n [-]parmrk\n mark parity errors (with a 255-0-character sequence)\n\n [-]tandem\n same as [-]ixoff\n\n Output settings:\n * bsN backspace delay style, N in [0..1]\n\n * crN carriage return delay style, N in [0..3]\n\n * ffN form feed delay style, N in [0..1]\n\n * nlN newline delay style, N in [0..1]\n\n * [-]ocrnl\n translate carriage return to newline\n\n * [-]ofdel\n use delete characters for fill instead of NUL characters\n\n * [-]ofill\n use fill (padding) characters instead of timing for delays\n\n * [-]olcuc\n translate lowercase characters to uppercase\n\n * [-]onlcr\n translate newline to carriage return-newline\n\n * [-]onlret\n newline performs a carriage return\n\n * [-]onocr\n do not print carriage returns in the first column\n\n [-]opost\n postprocess output\n\n * tabN horizontal tab delay style, N in [0..3]\n\n * tabs same as tab0\n\n * -tabs\n same as tab3\n\n * vtN vertical tab delay style, N in [0..1]\n\n Local settings:\n [-]crterase\n echo erase characters as backspace-space-backspace\n\n * crtkill\n kill all line by obeying the echoprt and echoe settings\n\n * -crtkill\n kill all line by obeying the echoctl and echok settings\n\n * [-]ctlecho\n echo control characters in hat notation ('^c')\n\n [-]echo\n echo input characters\n\n * [-]echoctl\n same as [-]ctlecho\n\n [-]echoe\n same as [-]crterase\n\n [-]echok\n echo a newline after a kill character\n\n * [-]echoke\n same as [-]crtkill\n\n [-]echonl\n echo newline even if not echoing other characters\n\n * [-]echoprt\n echo erased characters backward, between '\\' and '/'\n\n * [-]extproc\n enable \"LINEMODE\"; useful with high latency links\n\n * [-]flusho\n discard output\n\n [-]icanon\n enable special characters: erase, kill, werase, rprnt\n\n [-]iexten\n enable non-POSIX special characters\n\n [-]isig\n enable interrupt, quit, and suspend special characters\n\n [-]noflsh\n disable flushing after interrupt and quit special characters\n\n * [-]prterase\n same as [-]echoprt\n\n * [-]tostop\n stop background jobs that try to write to the terminal\n\n * [-]xcase\n with icanon, escape with '\\' for uppercase characters\n\n Combination settings:\n * [-]LCASE\n same as [-]lcase\n\n cbreak same as -icanon\n\n -cbreak\n same as icanon\n\n cooked same as brkint ignpar istrip icrnl ixon opost isig icanon, eof and eol characters to their default values\n\n -cooked\n same as raw\n\n crt same as echoe echoctl echoke\n\n dec same as echoe echoctl echoke -ixany intr ^c erase 0177 kill ^u\n\n * [-]decctlq\n same as [-]ixany\n\n ek erase and kill characters to their default values\n\n evenp same as parenb -parodd cs7\n\n -evenp same as -parenb cs8\n\n * [-]lcase\n same as xcase iuclc olcuc\n\n litout same as -parenb -istrip -opost cs8\n\n -litout\n same as parenb istrip opost cs7\n\n nl same as -icrnl -onlcr\n\n -nl same as icrnl -inlcr -igncr onlcr -ocrnl -onlret\n\n oddp same as parenb parodd cs7\n\n -oddp same as -parenb cs8\n\n [-]parity\n same as [-]evenp\n\n pass8 same as -parenb -istrip cs8\n\n -pass8 same as parenb istrip cs7\n\n raw same as -ignbrk -brkint -ignpar -parmrk -inpck -istrip -inlcr -igncr -icrnl -ixon -ixoff -icanon -opost\n -isig -iuclc -ixany -imaxbel -xcase min 1 time 0\n\n -raw same as cooked\n\n sane same as cread -ignbrk brkint -inlcr -igncr icrnl icanon iexten echo echoe echok -echonl -noflsh -ixoff\n -iutf8 -iuclc -ixany imaxbel -xcase -olcuc -ocrnl opost -ofill onlcr -onocr -onlret nl0 cr0 tab0 bs0 vt0\n ff0 isig -tostop -ofdel -echoprt echoctl echoke -extproc -flusho, all special characters to their default\n values\n\n Handle the tty line connected to standard input. Without arguments, prints baud rate, line discipline, and de\u2010\n viations from stty sane. In settings, CHAR is taken literally, or coded as in ^c, 0x37, 0177 or 127; special\n values ^- or undef used to disable special characters."} | |
| {"instruction": "What does the command `rmdir` do?", "output": "rmdir - remove empty directories"} | |
| {"instruction": "How is the `rmdir` used?", "output": "rmdir [OPTION]... DIRECTORY..."} | |
| {"instruction": "What is the detailed desciption of the `rmdir`?", "output": "Remove the DIRECTORY(ies), if they are empty.\n\n --ignore-fail-on-non-empty\n ignore each failure to remove a non-empty directory\n\n -p, --parents\n remove DIRECTORY and its ancestors; e.g., 'rmdir -p a/b' is similar to 'rmdir a/b a'\n\n -v, --verbose\n output a diagnostic for every directory processed\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `mkfifo` do?", "output": "mkfifo - make FIFOs (named pipes)"} | |
| {"instruction": "How is the `mkfifo` used?", "output": "mkfifo [OPTION]... NAME..."} | |
| {"instruction": "What is the detailed desciption of the `mkfifo`?", "output": "Create named pipes (FIFOs) with the given NAMEs.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -m, --mode=MODE\n set file permission bits to MODE, not a=rw - umask\n\n -Z set the SELinux security context to default type\n\n --context[=CTX]\n like -Z, or if CTX is specified then set the SELinux or SMACK security context to CTX\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `basenc` do?", "output": "basenc - Encode/decode data and print to standard output"} | |
| {"instruction": "How is the `basenc` used?", "output": "basenc [OPTION]... [FILE]"} | |
| {"instruction": "What is the detailed desciption of the `basenc`?", "output": "basenc encode or decode FILE, or standard input, to standard output.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n --base64\n same as 'base64' program (RFC4648 section 4)\n\n --base64url\n file- and url-safe base64 (RFC4648 section 5)\n\n --base32\n same as 'base32' program (RFC4648 section 6)\n\n --base32hex\n extended hex alphabet base32 (RFC4648 section 7)\n\n --base16\n hex encoding (RFC4648 section 8)\n\n --base2msbf\n bit string with most significant bit (msb) first\n\n --base2lsbf\n bit string with least significant bit (lsb) first\n\n -d, --decode\n decode data\n\n -i, --ignore-garbage\n when decoding, ignore non-alphabet characters\n\n -w, --wrap=COLS\n wrap encoded lines after COLS character (default 76). Use 0 to disable line wrapping\n\n --z85 ascii85-like encoding (ZeroMQ spec:32/Z85); when encoding, input length must be a multiple of 4; when de\u2010\n coding, input length must be a multiple of 5\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n When decoding, the input may contain newlines in addition to the bytes of the formal alphabet. Use --ig\u2010\n nore-garbage to attempt to recover from any other non-alphabet bytes in the encoded stream."} | |
| {"instruction": "What does the command `tac` do?", "output": "tac - concatenate and print files in reverse"} | |
| {"instruction": "How is the `tac` used?", "output": "tac [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `tac`?", "output": "Write each FILE to standard output, last line first.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -b, --before\n attach the separator before instead of after\n\n -r, --regex\n interpret the separator as a regular expression\n\n -s, --separator=STRING\n use STRING as the separator instead of newline\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `hostid` do?", "output": "hostid - print the numeric identifier for the current host"} | |
| {"instruction": "How is the `hostid` used?", "output": "hostid [OPTION]"} | |
| {"instruction": "What is the detailed desciption of the `hostid`?", "output": "Print the numeric identifier (in hexadecimal) for the current host.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `stdbuf` do?", "output": "stdbuf - Run COMMAND, with modified buffering operations for its standard streams."} | |
| {"instruction": "How is the `stdbuf` used?", "output": "stdbuf OPTION... COMMAND"} | |
| {"instruction": "What is the detailed desciption of the `stdbuf`?", "output": "Run COMMAND, with modified buffering operations for its standard streams.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -i, --input=MODE\n adjust standard input stream buffering\n\n -o, --output=MODE\n adjust standard output stream buffering\n\n -e, --error=MODE\n adjust standard error stream buffering\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If MODE is 'L' the corresponding stream will be line buffered. This option is invalid with standard input.\n\n If MODE is '0' the corresponding stream will be unbuffered.\n\n Otherwise MODE is a number which may be followed by one of the following: KB 1000, K 1024, MB 1000*1000, M\n 1024*1024, and so on for G,T,P,E,Z,Y,R,Q. Binary prefixes can be used, too: KiB=K, MiB=M, and so on. In this\n case the corresponding stream will be fully buffered with the buffer size set to MODE bytes.\n\n NOTE: If COMMAND adjusts the buffering of its standard streams ('tee' does for example) then that will override\n corresponding changes by 'stdbuf'. Also some filters (like 'dd' and 'cat' etc.) don't use streams for I/O, and\n are thus unaffected by 'stdbuf' settings.\n\n Exit status:\n 125 if the stdbuf command itself fails\n\n 126 if COMMAND is found but cannot be invoked\n\n 127 if COMMAND cannot be found\n\n - the exit status of COMMAND otherwise"} | |
| {"instruction": "What does the command `dircolors` do?", "output": "dircolors - color setup for ls"} | |
| {"instruction": "How is the `dircolors` used?", "output": "dircolors [OPTION]... [FILE]"} | |
| {"instruction": "What is the detailed desciption of the `dircolors`?", "output": "Output commands to set the LS_COLORS environment variable.\n\n Determine format of output:\n -b, --sh, --bourne-shell\n output Bourne shell code to set LS_COLORS\n\n -c, --csh, --c-shell\n output C shell code to set LS_COLORS\n\n -p, --print-database\n output defaults\n\n --print-ls-colors\n output fully escaped colors for display\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If FILE is specified, read it to determine which colors to use for which file types and extensions. Otherwise,\n a precompiled database is used. For details on the format of these files, run 'dircolors --print-database'."} | |
| {"instruction": "What does the command `uname` do?", "output": "uname - print system information"} | |
| {"instruction": "How is the `uname` used?", "output": "uname [OPTION]..."} | |
| {"instruction": "What is the detailed desciption of the `uname`?", "output": "Print certain system information. With no OPTION, same as -s.\n\n -a, --all\n print all information, in the following order, except omit -p and -i if unknown:\n\n -s, --kernel-name\n print the kernel name\n\n -n, --nodename\n print the network node hostname\n\n -r, --kernel-release\n print the kernel release\n\n -v, --kernel-version\n print the kernel version\n\n -m, --machine\n print the machine hardware name\n\n -p, --processor\n print the processor type (non-portable)\n\n -i, --hardware-platform\n print the hardware platform (non-portable)\n\n -o, --operating-system\n print the operating system\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `sum` do?", "output": "sum - checksum and count the blocks in a file"} | |
| {"instruction": "How is the `sum` used?", "output": "sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `sum`?", "output": "Print or check BSD (16-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n -r use BSD sum algorithm (the default), use 1K blocks\n\n -s, --sysv\n use System V sum algorithm, use 512 bytes blocks\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `whoami` do?", "output": "whoami - print effective user name"} | |
| {"instruction": "How is the `whoami` used?", "output": "whoami [OPTION]..."} | |
| {"instruction": "What is the detailed desciption of the `whoami`?", "output": "Print the user name associated with the current effective user ID. Same as id -un.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `truncate` do?", "output": "truncate - shrink or extend the size of a file to the specified size"} | |
| {"instruction": "How is the `truncate` used?", "output": "truncate OPTION... FILE..."} | |
| {"instruction": "What is the detailed desciption of the `truncate`?", "output": "Shrink or extend the size of each FILE to the specified size\n\n A FILE argument that does not exist is created.\n\n If a FILE is larger than the specified size, the extra data is lost. If a FILE is shorter, it is extended and\n the sparse extended part (hole) reads as zero bytes.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -c, --no-create\n do not create any files\n\n -o, --io-blocks\n treat SIZE as number of IO blocks instead of bytes\n\n -r, --reference=RFILE\n base size on RFILE\n\n -s, --size=SIZE\n set or adjust the file size by SIZE bytes\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The SIZE argument is an integer and optional unit (example: 10K is 10*1024). Units are K,M,G,T,P,E,Z,Y,R,Q\n (powers of 1024) or KB,MB,... (powers of 1000). Binary prefixes can be used, too: KiB=K, MiB=M, and so on.\n\n SIZE may also be prefixed by one of the following modifying characters: '+' extend by, '-' reduce by, '<' at\n most, '>' at least, '/' round down to multiple of, '%' round up to multiple of."} | |
| {"instruction": "What does the command `install` do?", "output": "install - copy files and set attributes"} | |
| {"instruction": "How is the `install` used?", "output": "install [OPTION]... [-T] SOURCE DEST\n install [OPTION]... SOURCE... DIRECTORY\n install [OPTION]... -t DIRECTORY SOURCE...\n install [OPTION]... -d DIRECTORY..."} | |
| {"instruction": "What is the detailed desciption of the `install`?", "output": "This install program copies files (often just compiled) into destination locations you choose. If you want to\n download and install a ready-to-use package on a GNU/Linux system, you should instead be using a package manager\n like yum(1) or apt-get(1).\n\n In the first three forms, copy SOURCE to DEST or multiple SOURCE(s) to the existing DIRECTORY, while setting\n permission modes and owner/group. In the 4th form, create all components of the given DIRECTORY(ies).\n\n Mandatory arguments to long options are mandatory for short options too.\n\n --backup[=CONTROL]\n make a backup of each existing destination file\n\n -b like --backup but does not accept an argument\n\n -c (ignored)\n\n -C, --compare\n compare content of source and destination files, and if no change to content, ownership, and permissions,\n do not modify the destination at all\n\n -d, --directory\n treat all arguments as directory names; create all components of the specified directories\n\n -D create all leading components of DEST except the last, or all components of --target-directory, then copy\n SOURCE to DEST\n\n --debug\n explain how a file is copied. Implies -v\n\n -g, --group=GROUP\n set group ownership, instead of process' current group\n\n -m, --mode=MODE\n set permission mode (as in chmod), instead of rwxr-xr-x\n\n -o, --owner=OWNER\n set ownership (super-user only)\n\n -p, --preserve-timestamps\n apply access/modification times of SOURCE files to corresponding destination files\n\n -s, --strip\n strip symbol tables\n\n --strip-program=PROGRAM\n program used to strip binaries\n\n -S, --suffix=SUFFIX\n override the usual backup suffix\n\n -t, --target-directory=DIRECTORY\n copy all SOURCE arguments into DIRECTORY\n\n -T, --no-target-directory\n treat DEST as a normal file\n\n -v, --verbose\n print the name of each created file or directory\n\n --preserve-context\n preserve SELinux security context\n\n -Z set SELinux security context of destination file and each created directory to default type\n\n --context[=CTX]\n like -Z, or if CTX is specified then set the SELinux or SMACK security context to CTX\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The backup suffix is '~', unless set with --suffix or SIMPLE_BACKUP_SUFFIX. The version control method may be\n selected via the --backup option or through the VERSION_CONTROL environment variable. Here are the values:\n\n none, off\n never make backups (even if --backup is given)\n\n numbered, t\n make numbered backups\n\n existing, nil\n numbered if numbered backups exist, simple otherwise\n\n simple, never\n always make simple backups"} | |
| {"instruction": "What does the command `nl` do?", "output": "nl - number lines of files"} | |
| {"instruction": "How is the `nl` used?", "output": "nl [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `nl`?", "output": "Write each FILE to standard output, with line numbers added.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -b, --body-numbering=STYLE\n use STYLE for numbering body lines\n\n -d, --section-delimiter=CC\n use CC for logical page delimiters\n\n -f, --footer-numbering=STYLE\n use STYLE for numbering footer lines\n\n -h, --header-numbering=STYLE\n use STYLE for numbering header lines\n\n -i, --line-increment=NUMBER\n line number increment at each line\n\n -l, --join-blank-lines=NUMBER\n group of NUMBER empty lines counted as one\n\n -n, --number-format=FORMAT\n insert line numbers according to FORMAT\n\n -p, --no-renumber\n do not reset line numbers for each section\n\n -s, --number-separator=STRING\n add STRING after (possible) line number\n\n -v, --starting-line-number=NUMBER\n first line number for each section\n\n -w, --number-width=NUMBER\n use NUMBER columns for line numbers\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Default options are: -bt -d'\\:' -fn -hn -i1 -l1 -n'rn' -s<TAB> -v1 -w6\n\n CC are two delimiter characters used to construct logical page delimiters; a missing second character implies\n ':'. As a GNU extension one can specify more than two characters, and also specifying the empty string (-d '')\n disables section matching.\n\n STYLE is one of:\n\n a number all lines\n\n t number only nonempty lines\n\n n number no lines\n\n pBRE number only lines that contain a match for the basic regular expression, BRE\n\n FORMAT is one of:\n\n ln left justified, no leading zeros\n\n rn right justified, no leading zeros\n\n rz right justified, leading zeros"} | |
| {"instruction": "What does the command `echo` do?", "output": "echo - display a line of text"} | |
| {"instruction": "How is the `echo` used?", "output": "echo [SHORT-OPTION]... [STRING]...\n echo LONG-OPTION"} | |
| {"instruction": "What is the detailed desciption of the `echo`?", "output": "Echo the STRING(s) to standard output.\n\n -n do not output the trailing newline\n\n -e enable interpretation of backslash escapes\n\n -E disable interpretation of backslash escapes (default)\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If -e is in effect, the following sequences are recognized:\n\n \\\\ backslash\n\n \\a alert (BEL)\n\n \\b backspace\n\n \\c produce no further output\n\n \\e escape\n\n \\f form feed\n\n \\n new line\n\n \\r carriage return\n\n \\t horizontal tab\n\n \\v vertical tab\n\n \\0NNN byte with octal value NNN (1 to 3 digits)\n\n \\xHH byte with hexadecimal value HH (1 to 2 digits)\n\n NOTE: your shell may have its own version of echo, which usually supersedes the version described here. Please\n refer to your shell's documentation for details about the options it supports.\n\n NOTE: printf(1) is a preferred alternative, which does not have issues outputting option-like strings."} | |
| {"instruction": "What does the command `chroot` do?", "output": "chroot - run command or interactive shell with special root directory"} | |
| {"instruction": "How is the `chroot` used?", "output": "chroot [OPTION] NEWROOT [COMMAND [ARG]...]\n chroot OPTION"} | |
| {"instruction": "What is the detailed desciption of the `chroot`?", "output": "Run COMMAND with root directory set to NEWROOT.\n\n --groups=G_LIST\n specify supplementary groups as g1,g2,..,gN\n\n --userspec=USER:GROUP\n specify user and group (ID or name) to use\n\n --skip-chdir\n do not change working directory to '/'\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n If no command is given, run '\"$SHELL\" -i' (default: '/bin/sh -i').\n\n Exit status:\n 125 if the chroot command itself fails\n\n 126 if COMMAND is found but cannot be invoked\n\n 127 if COMMAND cannot be found\n\n - the exit status of COMMAND otherwise"} | |
| {"instruction": "What does the command `comm` do?", "output": "comm - compare two sorted files line by line"} | |
| {"instruction": "How is the `comm` used?", "output": "comm [OPTION]... FILE1 FILE2"} | |
| {"instruction": "What is the detailed desciption of the `comm`?", "output": "Compare sorted files FILE1 and FILE2 line by line.\n\n When FILE1 or FILE2 (not both) is -, read standard input.\n\n With no options, produce three-column output. Column one contains lines unique to FILE1, column two contains\n lines unique to FILE2, and column three contains lines common to both files.\n\n -1 suppress column 1 (lines unique to FILE1)\n\n -2 suppress column 2 (lines unique to FILE2)\n\n -3 suppress column 3 (lines that appear in both files)\n\n --check-order\n check that the input is correctly sorted, even if all input lines are pairable\n\n --nocheck-order\n do not check that the input is correctly sorted\n\n --output-delimiter=STR\n separate columns with STR\n\n --total\n output a summary\n\n -z, --zero-terminated\n line delimiter is NUL, not newline\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n Note, comparisons honor the rules specified by 'LC_COLLATE'."} | |
| {"instruction": "What does the command `pinky` do?", "output": "pinky - lightweight finger"} | |
| {"instruction": "How is the `pinky` used?", "output": "pinky [OPTION]... [USER]..."} | |
| {"instruction": "What is the detailed desciption of the `pinky`?", "output": "-l produce long format output for the specified USERs\n\n -b omit the user's home directory and shell in long format\n\n -h omit the user's project file in long format\n\n -p omit the user's plan file in long format\n\n -s do short format output, this is the default\n\n -f omit the line of column headings in short format\n\n -w omit the user's full name in short format\n\n -i omit the user's full name and remote host in short format\n\n -q omit the user's full name, remote host and idle time in short format\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n A lightweight 'finger' program; print user information. The utmp file will be /var/run/utmp."} | |
| {"instruction": "What does the command `b2sum` do?", "output": "b2sum - compute and check BLAKE2 message digest"} | |
| {"instruction": "How is the `b2sum` used?", "output": "b2sum [OPTION]... [FILE]..."} | |
| {"instruction": "What is the detailed desciption of the `b2sum`?", "output": "Print or check BLAKE2b (512-bit) checksums.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -b, --binary\n read in binary mode\n\n -c, --check\n read checksums from the FILEs and check them\n\n -l, --length=BITS\n digest length in bits; must not exceed the max for the blake2 algorithm and must be a multiple of 8\n\n --tag create a BSD-style checksum\n\n -t, --text\n read in text mode (default)\n\n -z, --zero\n end each output line with NUL, not newline, and disable file name escaping\n\n The following five options are useful only when verifying checksums:\n --ignore-missing\n don't fail or report status for missing files\n\n --quiet\n don't print OK for each successfully verified file\n\n --status\n don't output anything, status code shows success\n\n --strict\n exit non-zero for improperly formatted checksum lines\n\n -w, --warn\n warn about improperly formatted checksum lines\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The sums are computed as described in RFC 7693. When checking, the input should be a former output of this pro\u2010\n gram. The default mode is to print a line with: checksum, a space, a character indicating input mode ('*' for\n binary, ' ' for text or where binary is insignificant), and name for each FILE.\n\n Note: There is no difference between binary mode and text mode on GNU systems."} | |
| {"instruction": "What does the command `arch` do?", "output": "arch - print machine hardware name (same as uname -m)"} | |
| {"instruction": "How is the `arch` used?", "output": "arch [OPTION]..."} | |
| {"instruction": "What is the detailed desciption of the `arch`?", "output": "Print machine architecture.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `mktemp` do?", "output": "mktemp - create a temporary file or directory"} | |
| {"instruction": "How is the `mktemp` used?", "output": "mktemp [OPTION]... [TEMPLATE]"} | |
| {"instruction": "What is the detailed desciption of the `mktemp`?", "output": "Create a temporary file or directory, safely, and print its name. TEMPLATE must contain at least 3 consecutive\n 'X's in last component. If TEMPLATE is not specified, use tmp.XXXXXXXXXX, and --tmpdir is implied. Files are\n created u+rw, and directories u+rwx, minus umask restrictions.\n\n -d, --directory\n create a directory, not a file\n\n -u, --dry-run\n do not create anything; merely print a name (unsafe)\n\n -q, --quiet\n suppress diagnostics about file/dir-creation failure\n\n --suffix=SUFF\n append SUFF to TEMPLATE; SUFF must not contain a slash. This option is implied if TEMPLATE does not end\n in X\n\n -p DIR, --tmpdir[=DIR]\n interpret TEMPLATE relative to DIR; if DIR is not specified, use $TMPDIR if set, else /tmp. With this\n option, TEMPLATE must not be an absolute name; unlike with -t, TEMPLATE may contain slashes, but mktemp\n creates only the final component\n\n -t interpret TEMPLATE as a single file name component, relative to a directory: $TMPDIR, if set; else the\n directory specified via -p; else /tmp [deprecated]\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `split` do?", "output": "split - split a file into pieces"} | |
| {"instruction": "How is the `split` used?", "output": "split [OPTION]... [FILE [PREFIX]]"} | |
| {"instruction": "What is the detailed desciption of the `split`?", "output": "Output pieces of FILE to PREFIXaa, PREFIXab, ...; default size is 1000 lines, and default PREFIX is 'x'.\n\n With no FILE, or when FILE is -, read standard input.\n\n Mandatory arguments to long options are mandatory for short options too.\n\n -a, --suffix-length=N\n generate suffixes of length N (default 2)\n\n --additional-suffix=SUFFIX\n append an additional SUFFIX to file names\n\n -b, --bytes=SIZE\n put SIZE bytes per output file\n\n -C, --line-bytes=SIZE\n put at most SIZE bytes of records per output file\n\n -d use numeric suffixes starting at 0, not alphabetic\n\n --numeric-suffixes[=FROM]\n same as -d, but allow setting the start value\n\n -x use hex suffixes starting at 0, not alphabetic\n\n --hex-suffixes[=FROM]\n same as -x, but allow setting the start value\n\n -e, --elide-empty-files\n do not generate empty output files with '-n'\n\n --filter=COMMAND\n write to shell COMMAND; file name is $FILE\n\n -l, --lines=NUMBER\n put NUMBER lines/records per output file\n\n -n, --number=CHUNKS\n generate CHUNKS output files; see explanation below\n\n -t, --separator=SEP\n use SEP instead of newline as the record separator; '\\0' (zero) specifies the NUL character\n\n -u, --unbuffered\n immediately copy input to output with '-n r/...'\n\n --verbose\n print a diagnostic just before each output file is opened\n\n --help display this help and exit\n\n --version\n output version information and exit\n\n The SIZE argument is an integer and optional unit (example: 10K is 10*1024). Units are K,M,G,T,P,E,Z,Y,R,Q\n (powers of 1024) or KB,MB,... (powers of 1000). Binary prefixes can be used, too: KiB=K, MiB=M, and so on.\n\n CHUNKS may be:\n N split into N files based on size of input\n\n K/N output Kth of N to stdout\n\n l/N split into N files without splitting lines/records\n\n l/K/N output Kth of N to stdout without splitting lines/records\n\n r/N like 'l' but use round robin distribution\n\n r/K/N likewise but only output Kth of N to stdout"} | |
| {"instruction": "What does the command `yes` do?", "output": "yes - output a string repeatedly until killed"} | |
| {"instruction": "How is the `yes` used?", "output": "yes [STRING]...\n yes OPTION"} | |
| {"instruction": "What is the detailed desciption of the `yes`?", "output": "Repeatedly output a line with all specified STRING(s), or 'y'.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |
| {"instruction": "What does the command `users` do?", "output": "users - print the user names of users currently logged in to the current host"} | |
| {"instruction": "How is the `users` used?", "output": "users [OPTION]... [FILE]"} | |
| {"instruction": "What is the detailed desciption of the `users`?", "output": "Output who is currently logged in according to FILE. If FILE is not specified, use /var/run/utmp.\n /var/log/wtmp as FILE is common.\n\n --help display this help and exit\n\n --version\n output version information and exit"} | |