donnaken15 · August 24, 2025 12:17
diff --git a/nwtrlz.zsh b/nwtrlz.zsh
 #!/bin/zsh -e
 # NewtraLZ / new tar.l(r)z
 set -o pipefail
 #set -x
 { # ------------ deeeefines
 	# KSH_ARRAYS DOESN'T ALLOW EXPANSION WITHOUT [@],
 	# AND (generally) CAN'T DEFINE ALIASES WITHIN BLOCKS, WTFFFFFFFFFFF
 	nul='/dev/null'; bools=(true false); LRZIP=NOCONFIG; this="$0"; best=lrzip; die() {
 		expand -t 4 <<!!
 ${this:t:r} - archive neutralizer
 	usage:
 		${this:t:r} [input file] [switches]
 	options:
 		--output,-o			- set output name
 		--transform,-f		- replace the original file directly when done,
 							  output parameter becomes the temp file, useful
 							  for retaining the creation date
 		--sanity-chk,-v		- verify checksums of source files vs recompressed files
 		--batch-size,-b		- set number of items to process at a time
 		--max-memory,-m		- limit RAM usage by hundreds of MB, for lrzip only
 		? [arg]				- pass argument to $best, for optargs, you may need
 							  to use this twice, as such: (? --window-size ? 2048)
 !!
 		exit 1
 	}
 	s() { $* >$nul 2>$nul } # silence
 	PATH=$(echo "$PATH" | sed -e 's/\(\/\(cygdrive\|mnt\)\/c\|c:\)[\\/]windows[\\/]system32[\\/]\?://gI') # i need to die
 	# grep and extract group 1
 	rip() { sed -n "s/\r//g;/$1/s/$1/\\${3:-1}/p" -- "${2:--}" }; hate() { sed '/^$/d;s/\r//g' }
 	can_run() { which "$1" >$nul 2>$nul }; sort_dirs() { hate | rev | sort | rev } # awful
 	false && {
 		free="$(((($(rip "^MemFree: \+\([0-9]\+\).*" /proc/meminfo)/1000000.0)-4.5)>>0))"
 		[ $free -le 1 ] && {
 			echo 'not enough memory'
 			exit 1
 		}
 	}
 }
 # it's actually getting hard to read these or keep of track of where stuff is, so here i am actually marking stuff |:(
 { # ------------ input check
 	inp="$1"
 	[ -z "$inp" ] && {
 		echo "input not specified"
 		die
 	}
 	s shift || die
 }
 { # ------------ arg checking
 	passthru=()
 	# why is FOSS so bad https://stackoverflow.com/questions/12022592
 	declare -A longopts=(
 		[output]=-o
 		[transform]=-f
 		[sanity-chk]=-v
 		[batch-size]=-b
 		[max-memory]=-m
 	)
 	bs=4
 	mm=10
 	vf=false
 	tf=false
 	why=false
 	for o in "$@"; do
 		shift
 		$why && {
 			why=false
 			continue
 		}
 		[ "$o" = "?" ] && {
 			passthru+=("$1")
 			why=true
 		}
 		[[ "$o" =~ ^--(.*) ]] && {
 			lo="${longopts[${match[1]}]}"
 			[ -z "$lo" ] && echo "nonexistent option $o" || o="$lo"
 		}
 		set -- "$@" "${longopts["$o"]:-"$o"}"
 	done
 	unset why
 	#(IFS=":"; echo ":${}:")
 	while getopts ':o:b:m:f' opt; do
 		case $opt in
 			o)	out="$OPTARG"	;;
 			m)	mm="$OPTARG"	;;
 			b)	bs="$OPTARG"	;;
 			f)	tf=true			;;
 			v)	vf=true			;;
 			:)	echo "Missing argument for -$OPTARG"; exit 1	;;
 			\?)	passthru+=("$OPTARG")			;;
 			*)	echo "Uncaught: $opt, $OPTARG"	;;
 		esac
 	done
 	[ -z "$out" ] && {
 		out="${inp%%.tar.*}"
 		for ext in 7z zip rar tar jar tgz ark7z arkxz arkzp zp zpaq; do
 			out="${out%.$ext}"
 		done
 		out="${out}.tar.lrz"
 	}
 }
 { # ------------ rooootines
 	tmpd="$(mktemp -d -t "nwtXXX")"
 	ktmp() { rm -rf "$tmpd" }; trap ktmp EXIT
 	piperes() {
 		local s=(${pipestatus}) x=0;
 		for ((i=1; i<=${#s[@]}; i++)); do ((x |= s[i])); done
 		return $x
 	}
 }
 { # ------------ detect type
 	# notepad++ seriously needs syntax nesting for substitutions
 	test=`if [[ "$(file -b "$inp")" =~ ^(ZPAQ|LRZIP)\  ]]; then
 		case "${match[1]}" in
 			ZPAQ)	echo 'application/x-zpaq'	;;
 			LRZIP)	echo 'application/x-lrzip'	;;
 				*)	echo 'you suck' 1>&2; exit 1;;
 		esac
 	else
 		file -b --mime-type "$inp"
 	fi`
 	test="${test#application/}"
 	declare -A arktypes=(
 		[x-bzip2]=bz
 		[x-lrzip]=lr
 		[x-lzma]=xz
 		[x-xz]=xz
 		[gzip]=gz
 		[zstd]=zs
 		[zip]=pk
 		[x-tar]=tr
 		[x-zpaq]=zp
 		[x-7z-compressed]=7z
 	)
 	type="${arktypes[${test}]}"
 	case "$type" in
 		7z)	regq() {
 				reg.exe query "$1" /v "$2" | sed -n "3s/ \{4\}.* \{4\}REG_[^ ]\+ \{4\}//;s/\\\0/\n/g;s/\\\/\//g;s/\r//g;3p" # why so autistic
 				piperes
 			}
 			can_run reg.exe && z7="$(regq 'HKCU\SOFTWARE\7-Zip' Path)/7z.exe" || {
 				z7=; for x in 7z 7za 7zr; do
 					can_run $x && { z7=$x; break }
 				done
 			}
 			[ -z "$z7" ] && { echo "7-zip not found"; exit 1 }
 			;;
 		zp)	zp=; for x in zpaq zpaqfranz zp; do # how TF do i handle versions
 				can_run $x && { zp=$x; break }
 			done
 			[ -z "$zp" ] && { echo "zpaq not found"; exit 1 }
 			;;
 		pk)	can_run unzip || type=tr
 			;&
 		*)	cmd="`realpath "${COMSPEC:-C:\\Windows\\System32\\cmd.exe}"`"
 			[ -f "$cmd" ] && {
 				winver=`"$cmd" /c ver 2>$nul | rip "^Microsoft Windows \[Version 1[01]\.[0-9]\.\([0-9]\+\)\.[0-9]\+\]$"`
 				[ ${winver:-0} -ge 17063 ] && wintar="$(dirname "$cmd")/tar.exe"
 			}
 			# make diagnostic tool offhanded? that just checks the build no. and if tar exists in system32
 			# on an installation around or a version behind minimum, for whatever reason
 			[ -n "$wintar" ] && tar="$wintar" || tar=tar
 			;;
 	esac
 	declare -A balls=( # stupid
 		[lr]=lrzip
 		[bz]=bzip2 # is the bzcat alias consistently created on all machines/envs that have bzip2
 		[gz]=gzip
 		[zs]=zstd
 		[xz]=xz # lzma/lzmadec/unlzma might be aliases, shout out Jia Tang
 		# xz/lzma are apparently distinct types but xz can handle both of them
 	)
 	exe="${balls[$type]}"
 	{ # ------------ most actually autistic pipe
 		# would be more of the case if i didn't store it in an array
 		# where it'd (pipe) be less accessible and more difficult to work with my batch idea
 		if [ -n "$exe" ]; then
 			can_run "$exe" || {
 				echo "decompressor $exe not found, exiting" >&2
 				exit 1
 			}
 			case "$exe" in
 				lrzip)	"$exe" -dqo - -m $mm "$inp"		;;
 					*)	"$exe" -qcd "$inp"				;;
 			esac | "$wintar" -tf -
 		else
 			case "$type" in
 				tr)	"$tar" -tf "$inp"				;;
 				7z)	#					atrocious
 					"$z7" l "$inp" -ba -sccUTF-8 | cut -c54- | sed 's/\r//g'	;;
 				pk)	unzip -Z1 "$inp"
 					;;
 				zp)	"$zp" l "$inp" 2>$nul | rip "-\? [0-9]\{4\}-[0-9]\{2\}-[0-9]\{2\} [0-9]\{2\}:[0-9]\{2\}:[0-9]\{2\} \+[0-9\.]\+ [A-Z]\+ \+\(.*\)" # DUMB
 					;;
 				*)	echo "why $test $type" >&2
 					exit 1
 					;;
 			esac
 		fi
 	} | sort_dirs | IFS=$'\n' read -r -d '' -A filelist # why is read returning error code
 	# AND WHY IS IT RETURNING AN EXTRA ITEM WHEN THERE'S NO NEWLINE @ END
 	echo "total files: ${#filelist}"
 	((test=pipestatus[1]|pipestatus[2])); [ $test -ne 0 ] && exit $test
 	[ "${#filelist}" = 1 -a -z "${filelist[1]}" ] && {
 		echo 'no files available' >&2; exit 1
 	}
 	# TODO: batch parameter, extract N files at once and then add for sake of dictionary reading stuff
 		zipiz_x() { file="$1" && shift && unzip "$file" "$@" -x -d "$tmpd" }
 }
 #	unzip: zip
 #	unrar: rar
 #	system32/[bsd]tar: rar, tar, zip, 7z (NO LZMA WHY!!)
 #	7z[ar]?: rar, tar, zip, 7z
 #	zpaq: zpaq :l

 # <Commands>
 #   a : Add files to archive
 #   b : Benchmark
 #   d : Delete files from archive
 #   e : Extract files from archive (without using directory names)
 #   h : Calculate hash values for files
 #   i : Show information about supported formats
 #   l : List contents of archive
 #   rn : Rename files in archive
 #   t : Test integrity of archive
 #   u : Update files to archive
 #   x : eXtract files with full paths
 # <Switches>
 #   -- : Stop switches and @listfile parsing
 #   -ai[r[-|0]][m[-|2]][w[-]]{@listfile|!wildcard} : Include archives
 #   -ax[r[-|0]][m[-|2]][w[-]]{@listfile|!wildcard} : eXclude archives
 #   -ao{a|s|t|u} : set Overwrite mode
 #   -an : disable archive_name field
 #   -bb[0-3] : set output log level
 #   -bd : disable progress indicator
 #   -bs{o|e|p}{0|1|2} : set output stream for output/error/progress line
 #   -bt : show execution time statistics
 #   -i[r[-|0]][m[-|2]][w[-]]{@listfile|!wildcard} : Include filenames
 #   -m{Parameters} : set compression Method
 #     -mmt[N] : set number of CPU threads
 #     -mx[N] : set compression level: -mx1 (fastest) ... -mx9 (ultra)
 #   -o{Directory} : set Output directory
 #   -p{Password} : set Password
 #   -r[-|0] : Recurse subdirectories for name search
 #   -sa{a|e|s} : set Archive name mode
 #   -scc{UTF-8|WIN|DOS} : set charset for console input/output
 #   -scs{UTF-8|UTF-16LE|UTF-16BE|WIN|DOS|{id}} : set charset for list files
 #   -scrc[CRC32|CRC64|SHA1|SHA256|*] : set hash function for x, e, h commands
 #   -sdel : delete files after compression
 #   -seml[.] : send archive by email
 #   -sfx[{name}] : Create SFX archive
 #   -si[{name}] : read data from stdin
 #   -slp : set Large Pages mode
 #   -slt : show technical information for l (List) command
 #   -snh : store hard links as links
 #   -snl : store symbolic links as links
 #   -sni : store NT security information
 #   -sns[-] : store NTFS alternate streams
 #   -so : write data to stdout
 #   -spd : disable wildcard matching for file names
 #   -spe : eliminate duplication of root folder for extract command
 #   -spf[2] : use fully qualified file paths
 #   -ssc[-] : set sensitive case mode
 #   -sse : stop archive creating, if it can't open some input file
 #   -ssp : do not change Last Access Time of source files while archiving
 #   -ssw : compress shared files
 #   -stl : set archive timestamp from the most recently modified file
 #   -stm{HexMask} : set CPU thread affinity mask (hexadecimal number)
 #   -stx{Type} : exclude archive type
 #   -t{Type} : Set type of archive
 #   -u[-][p#][q#][r#][x#][y#][z#][!newArchiveName] : Update options
 #   -v{Size}[b|k|m|g] : Create volumes
 #   -w[{path}] : assign Work directory. Empty path means a temporary directory
 #   -x[r[-|0]][m[-|2]][w[-]]{@listfile|!wildcard} : eXclude filenames
 #   -y : assume Yes on all queries
	#!/bin/zsh -e
	# NewtraLZ / new tar.l(r)z
	set -o pipefail
	#set -x
	{ # ------------ deeeefines
	# KSH_ARRAYS DOESN'T ALLOW EXPANSION WITHOUT [@],
	# AND (generally) CAN'T DEFINE ALIASES WITHIN BLOCKS, WTFFFFFFFFFFF
	nul='/dev/null'; bools=(true false); LRZIP=NOCONFIG; this="$0"; best=lrzip; die() {
	expand -t 4 <<!!
	${this:t:r} - archive neutralizer
	usage:
	${this:t:r} [input file] [switches]
	options:
	--output,-o - set output name
	--transform,-f - replace the original file directly when done,
	output parameter becomes the temp file, useful
	for retaining the creation date
	--sanity-chk,-v - verify checksums of source files vs recompressed files
	--batch-size,-b - set number of items to process at a time
	--max-memory,-m - limit RAM usage by hundreds of MB, for lrzip only
	? [arg] - pass argument to $best, for optargs, you may need
	to use this twice, as such: (? --window-size ? 2048)
	!!
	exit 1
	}
	s() { $* >$nul 2>$nul } # silence
	PATH=$(echo "$PATH" \| sed -e 's/\(\/\(cygdrive\\|mnt\)\/c\\|c:\)[\\/]windows[\\/]system32[\\/]\?://gI') # i need to die
	# grep and extract group 1
	rip() { sed -n "s/\r//g;/$1/s/$1/\\${3:-1}/p" -- "${2:--}" }; hate() { sed '/^$/d;s/\r//g' }
	can_run() { which "$1" >$nul 2>$nul }; sort_dirs() { hate \| rev \| sort \| rev } # awful
	false && {
	free="$(((($(rip "^MemFree: \+\([0-9]\+\).*" /proc/meminfo)/1000000.0)-4.5)>>0))"
	[ $free -le 1 ] && {
	echo 'not enough memory'
	exit 1
	}
	}
	}
	# it's actually getting hard to read these or keep of track of where stuff is, so here i am actually marking stuff \|:(
	{ # ------------ input check
	inp="$1"
	[ -z "$inp" ] && {
	echo "input not specified"
	die
	}
	s shift \|\| die
	}
	{ # ------------ arg checking
	passthru=()
	# why is FOSS so bad https://stackoverflow.com/questions/12022592
	declare -A longopts=(
	[output]=-o
	[transform]=-f
	[sanity-chk]=-v
	[batch-size]=-b
	[max-memory]=-m
	)
	bs=4
	mm=10
	vf=false
	tf=false
	why=false
	for o in "$@"; do
	shift
	$why && {
	why=false
	continue
	}
	[ "$o" = "?" ] && {
	passthru+=("$1")
	why=true
	}
	[[ "$o" =~ ^--(.*) ]] && {
	lo="${longopts[${match[1]}]}"
	[ -z "$lo" ] && echo "nonexistent option $o" \|\| o="$lo"
	}
	set -- "$@" "${longopts["$o"]:-"$o"}"
	done
	unset why
	#(IFS=":"; echo ":${}:")
	while getopts ':o:b:m:f' opt; do
	case $opt in
	o) out="$OPTARG" ;;
	m) mm="$OPTARG" ;;
	b) bs="$OPTARG" ;;
	f) tf=true ;;
	v) vf=true ;;
	:) echo "Missing argument for -$OPTARG"; exit 1 ;;
	\?) passthru+=("$OPTARG") ;;
	*) echo "Uncaught: $opt, $OPTARG" ;;
	esac
	done
	[ -z "$out" ] && {
	out="${inp%%.tar.*}"
	for ext in 7z zip rar tar jar tgz ark7z arkxz arkzp zp zpaq; do
	out="${out%.$ext}"
	done
	out="${out}.tar.lrz"
	}
	}
	{ # ------------ rooootines
	tmpd="$(mktemp -d -t "nwtXXX")"
	ktmp() { rm -rf "$tmpd" }; trap ktmp EXIT
	piperes() {
	local s=(${pipestatus}) x=0;
	for ((i=1; i<=${#s[@]}; i++)); do ((x \|= s[i])); done
	return $x
	}
	}
	{ # ------------ detect type
	# notepad++ seriously needs syntax nesting for substitutions
	test=`if [[ "$(file -b "$inp")" =~ ^(ZPAQ\|LRZIP)\ ]]; then
	case "${match[1]}" in
	ZPAQ) echo 'application/x-zpaq' ;;
	LRZIP) echo 'application/x-lrzip' ;;
	*) echo 'you suck' 1>&2; exit 1;;
	esac
	else
	file -b --mime-type "$inp"
	fi`
	test="${test#application/}"
	declare -A arktypes=(
	[x-bzip2]=bz
	[x-lrzip]=lr
	[x-lzma]=xz
	[x-xz]=xz
	[gzip]=gz
	[zstd]=zs
	[zip]=pk
	[x-tar]=tr
	[x-zpaq]=zp
	[x-7z-compressed]=7z
	)
	type="${arktypes[${test}]}"
	case "$type" in
	7z) regq() {
	reg.exe query "$1" /v "$2" \| sed -n "3s/ \{4\}.* \{4\}REG_[^ ]\+ \{4\}//;s/\\\0/\n/g;s/\\\/\//g;s/\r//g;3p" # why so autistic
	piperes
	}
	can_run reg.exe && z7="$(regq 'HKCU\SOFTWARE\7-Zip' Path)/7z.exe" \|\| {
	z7=; for x in 7z 7za 7zr; do
	can_run $x && { z7=$x; break }
	done
	}
	[ -z "$z7" ] && { echo "7-zip not found"; exit 1 }
	;;
	zp) zp=; for x in zpaq zpaqfranz zp; do # how TF do i handle versions
	can_run $x && { zp=$x; break }
	done
	[ -z "$zp" ] && { echo "zpaq not found"; exit 1 }
	;;
	pk) can_run unzip \|\| type=tr
	;&
	*) cmd="`realpath "${COMSPEC:-C:\\Windows\\System32\\cmd.exe}"`"
	[ -f "$cmd" ] && {
	winver=`"$cmd" /c ver 2>$nul \| rip "^Microsoft Windows \[Version 1[01]\.[0-9]\.\([0-9]\+\)\.[0-9]\+\]$"`
	[ ${winver:-0} -ge 17063 ] && wintar="$(dirname "$cmd")/tar.exe"
	}
	# make diagnostic tool offhanded? that just checks the build no. and if tar exists in system32
	# on an installation around or a version behind minimum, for whatever reason
	[ -n "$wintar" ] && tar="$wintar" \|\| tar=tar
	;;
	esac
	declare -A balls=( # stupid
	[lr]=lrzip
	[bz]=bzip2 # is the bzcat alias consistently created on all machines/envs that have bzip2
	[gz]=gzip
	[zs]=zstd
	[xz]=xz # lzma/lzmadec/unlzma might be aliases, shout out Jia Tang
	# xz/lzma are apparently distinct types but xz can handle both of them
	)
	exe="${balls[$type]}"
	{ # ------------ most actually autistic pipe
	# would be more of the case if i didn't store it in an array
	# where it'd (pipe) be less accessible and more difficult to work with my batch idea
	if [ -n "$exe" ]; then
	can_run "$exe" \|\| {
	echo "decompressor $exe not found, exiting" >&2
	exit 1
	}
	case "$exe" in
	lrzip) "$exe" -dqo - -m $mm "$inp" ;;
	*) "$exe" -qcd "$inp" ;;
	esac \| "$wintar" -tf -
	else
	case "$type" in
	tr) "$tar" -tf "$inp" ;;
	7z) # atrocious
	"$z7" l "$inp" -ba -sccUTF-8 \| cut -c54- \| sed 's/\r//g' ;;
	pk) unzip -Z1 "$inp"
	;;
	zp) "$zp" l "$inp" 2>$nul \| rip "-\? [0-9]\{4\}-[0-9]\{2\}-[0-9]\{2\} [0-9]\{2\}:[0-9]\{2\}:[0-9]\{2\} \+[0-9\.]\+ [A-Z]\+ \+\(.*\)" # DUMB
	;;
	*) echo "why $test $type" >&2
	exit 1
	;;
	esac
	fi
	} \| sort_dirs \| IFS=$'\n' read -r -d '' -A filelist # why is read returning error code
	# AND WHY IS IT RETURNING AN EXTRA ITEM WHEN THERE'S NO NEWLINE @ END
	echo "total files: ${#filelist}"
	((test=pipestatus[1]\|pipestatus[2])); [ $test -ne 0 ] && exit $test
	[ "${#filelist}" = 1 -a -z "${filelist[1]}" ] && {
	echo 'no files available' >&2; exit 1
	}
	# TODO: batch parameter, extract N files at once and then add for sake of dictionary reading stuff
	zipiz_x() { file="$1" && shift && unzip "$file" "$@" -x -d "$tmpd" }
	}
	# unzip: zip
	# unrar: rar
	# system32/[bsd]tar: rar, tar, zip, 7z (NO LZMA WHY!!)
	# 7z[ar]?: rar, tar, zip, 7z
	# zpaq: zpaq :l

	# <Commands>
	# a : Add files to archive
	# b : Benchmark
	# d : Delete files from archive
	# e : Extract files from archive (without using directory names)
	# h : Calculate hash values for files
	# i : Show information about supported formats
	# l : List contents of archive
	# rn : Rename files in archive
	# t : Test integrity of archive
	# u : Update files to archive
	# x : eXtract files with full paths
	# <Switches>
	# -- : Stop switches and @listfile parsing
	# -ai[r[-\|0]][m[-\|2]][w[-]]{@listfile\|!wildcard} : Include archives
	# -ax[r[-\|0]][m[-\|2]][w[-]]{@listfile\|!wildcard} : eXclude archives
	# -ao{a\|s\|t\|u} : set Overwrite mode
	# -an : disable archive_name field
	# -bb[0-3] : set output log level
	# -bd : disable progress indicator
	# -bs{o\|e\|p}{0\|1\|2} : set output stream for output/error/progress line
	# -bt : show execution time statistics
	# -i[r[-\|0]][m[-\|2]][w[-]]{@listfile\|!wildcard} : Include filenames
	# -m{Parameters} : set compression Method
	# -mmt[N] : set number of CPU threads
	# -mx[N] : set compression level: -mx1 (fastest) ... -mx9 (ultra)
	# -o{Directory} : set Output directory
	# -p{Password} : set Password
	# -r[-\|0] : Recurse subdirectories for name search
	# -sa{a\|e\|s} : set Archive name mode
	# -scc{UTF-8\|WIN\|DOS} : set charset for console input/output
	# -scs{UTF-8\|UTF-16LE\|UTF-16BE\|WIN\|DOS\|{id}} : set charset for list files
	# -scrc[CRC32\|CRC64\|SHA1\|SHA256\|*] : set hash function for x, e, h commands
	# -sdel : delete files after compression
	# -seml[.] : send archive by email
	# -sfx[{name}] : Create SFX archive
	# -si[{name}] : read data from stdin
	# -slp : set Large Pages mode
	# -slt : show technical information for l (List) command
	# -snh : store hard links as links
	# -snl : store symbolic links as links
	# -sni : store NT security information
	# -sns[-] : store NTFS alternate streams
	# -so : write data to stdout
	# -spd : disable wildcard matching for file names
	# -spe : eliminate duplication of root folder for extract command
	# -spf[2] : use fully qualified file paths
	# -ssc[-] : set sensitive case mode
	# -sse : stop archive creating, if it can't open some input file
	# -ssp : do not change Last Access Time of source files while archiving
	# -ssw : compress shared files
	# -stl : set archive timestamp from the most recently modified file
	# -stm{HexMask} : set CPU thread affinity mask (hexadecimal number)
	# -stx{Type} : exclude archive type
	# -t{Type} : Set type of archive
	# -u[-][p#][q#][r#][x#][y#][z#][!newArchiveName] : Update options
	# -v{Size}[b\|k\|m\|g] : Create volumes
	# -w[{path}] : assign Work directory. Empty path means a temporary directory
	# -x[r[-\|0]][m[-\|2]][w[-]]{@listfile\|!wildcard} : eXclude filenames
	# -y : assume Yes on all queries
No results found