#!/bin/sh
# This file is part of curtin. See LICENSE file for copyright and license info.

# smtar (smart tar)
# GNU Tar can only determine the compression type if input is a local file.
# If input is a pipe, it will not even attempt.
#
# This works around that limitation by using 'file' to determine
# the compression format via a local temp file of BUFLEN (1024) bytes.
# After determining format, it passes the correct flag to tar.
#
# Compression format determination is done with 'file' via use of a temp file
#
#  The following are supported:
#
#    # compression option provided explicitly: just exec tar
#    $ ./smtar -tvz < my.tar.gz
#
#    # file argument provided, tar can determine: just exec tar
#    $ ./smtar -tvf my.tar.gz 
#    $ ./smtar -tvf my.tar
#
#    # input from stdin. determine the appropriate compress flag and execute
#    $ ./smtar -tv < my.tar.bz2
#    $ ./smtar -tv < my.tar.bz2
#    $ cat my.tar.xz | ./smtar -tv -f -
#    $ wget http://some.tar | ./smtar -tv -f -
#
#
TEMPF=""
BUFLEN="1024"
cleanup() { [ -z "$TEMPF" ] || rm -f "$TEMPF"; }
error() { echo "$@" 1>&2; }
fail() { [ $# -eq 0 ] || error "$@"; exit 1; }
find_tar_filearg() {
    # walk through list of args, return the 'file' argument in _RET
    local cur="" next=""
    while [ $# -ne 0 ]; do
        cur="$1"
        next="$2"
        case "$cur" in
            --file=*) _RET=${cur#*=}; return 0;;
            --file) _RET=$next; return 0;;
            --*=*) :;;
            *-f) _RET="$next"; return 0;;
            --) _RET=""; return 0;;
        esac
        shift
    done
    return 1
}

tar_has_compress_opt() {
    # this isnt perfect, but catch common ways
    # without fully parsing the args, we risk interpreting
    #   tar -xvf -J
    # as bzip2 compression, where in reality its a file name '-J'
    local cur="" next=""
    while [ $# -ne 0 ]; do
        cur="$1"
        next="$2"
        case "$cur" in
            -z|--gzip|--gunzip|--ungzip) return 0;;
            -j|--bzip2) return 0;;
            -J|--xz) return 0;;
            -Z|--compress|--uncompress) return 0;;
            --) return 1;;
        esac
        shift
    done
    return 1
}

# see if we can get out without reading anything
if [ -t 0 ] || tar_has_compress_opt; then
    # input is a terminal, or args contain a compress option
    exec tar "$@"
fi

# if there was a compression arg in input, then let it be
find_tar_filearg "$@"
if ! [ "$_RET" = "/dev/stdin" -o "$_RET" = "-" -o -z "$_RET" ]; then
   exec "tar" "$@"
fi

# now we have work to do
zopt=""
TEMPF=$(mktemp) || fail "mktemp failed"
trap cleanup EXIT
head -c "$BUFLEN" > "$TEMPF" || fail "FAILED: head -c '$BUFLEN'"
size=$(stat --format="%s" "$TEMPF")
file_out=$(LANG=C file --mime-type "$TEMPF")
# my.tar: application/x-tar
# my.tar.bz2: application/x-bzip2
# my.tar.gz: application/gzip
# my.tar.xz: application/x-xz
# my.tar.Z:  application/x-compress
if [ $? -eq 0 ]; then
    case "$file_out" in
        */x-bzip2|*/bzip2) zopt="--bzip2";;
        */x-gzip|*/gzip) zopt="--gzip";;
        */x-xz|*/xz) zopt="--xz";;
        */x-compress|*/compress) zopt="--compress";;
        *) zopt="";;
    esac
else
    error "WARN: 'file' failed on input"
fi
if [ "$size" -lt "$BUFLEN" ]; then
    # input was less than BUFLEN chars, so we just exec tar with input from it
    exec < "$TEMPF"
    rm -f "$TEMPF"
    exec tar $zopt "$@"
else
    ( cat "$TEMPF" && rm "$TEMPF" && exec cat ) | exec tar $zopt "$@"
fi

# vi: ts=4 expandtab syntax=sh