Convert small base64 encoded string to hexadecimal
1. Reducing forks
Accepted answer do offer a solution with a lot of forks! I hate useless forks!
There is my short base64 to hexadecimal converter:
b64toHex() {
local _arLines
mapfile -t _arLines < <(base64 -d <<< "$2" | xxd -p)
printf -v "${1:-hexString}" %s "${_arLines[@]}"
}
In order to avoid fork like myVar=$(myFunc args), this function will only populate a variable and won't print out anything.
b64toHex myVar "OQbb8rXnj/DwvglW018uP/1tqldwiJMbjxBhX7ZqwTw="
echo $myVar
3906dbf2b5e78ff0f0be0956d35f2e3ffd6daa577088931b8f10615fb66ac13c
Then you could use:
b64toHex iv_hex "${iv}"
b64toHex key_hex "${key}"
See at bottom of this for execution time comparison.
2. Pure bash way:
This don't depend on xxd or base64 to be installed. (And without forks, will
be significantly quicker than running 3 forks! Keep in mind, if you plan to run this repetitively!)
From this: Bash script - decode encoded string to byte array, on my website: base64decoder.sh.txt, base64decoder.sh, with a very small modification**:
**At line 41:
- ((_ar==0)) && printf -v _res %b "${_res[@]/#/\\x}"
+ ((_ar==0)) && printf -v _res %s "${_res[@]}"
First prepare a read-only array as:
declare -a B64=( {A..Z} {a..z} {0..9} + / '=' )
declare -Ai 'B64R=()'
for i in "${!B64[@]}"; do B64R["${B64[i]}"]=i%64; done
declare -r B64R
unset B64
Then b64ToHex function:
b64ToHex() {
local _4B _Tail _hVal _v _opt OPTIND
local -i iFd _24b _ar
while getopts "av:" _opt; do case $_opt in
a) _ar=1;; v) _v=${OPTARG};; *) return 1;; esac; done
shift $((OPTIND-1))
if [[ $_v ]];then local -n _res=${_v}; else local _res; fi
if [[ $1 ]]; then exec {iFd}<<<"$1" # Open Input FD from string
else exec {iFd}<&0 ; fi # Open Input FD from STDIN
_res=()
while read -rn4 -u $iFd _4B; do
if [[ "$_4B" ]]; then
_Tail=$_4B
_24b=" B64R['${_4B::1}'] << 18 | B64R['${_4B:1:1}'] << 12 |
B64R['${_4B:2:1}'] << 6 | B64R['${_4B:3:1}'] "
printf -v _hval %02x\ $((_24b>>16)) $((_24b>>8&255)) $((_24b&255))
read -ra _hval <<<"$_hval"
_res+=("${_hval[@]}")
fi
done
exec {iFd}<&-
_Tail=${_Tail##*([^=])}
while [[ $_Tail ]]; do
unset "_res[-1]"
_Tail=${_Tail:1}
done
((_ar==0)) && printf -v _res %s "${_res[@]}" && _res=("${_res[0]}")
[[ -z $_v ]] && echo "${_res[@]}"
}
If bash loop are known to be slow, doing a loop over only 32 byte will be significantly quicker and less system expansive than running four forks!
Usage from STDIN:
b64ToHex <<<"OQbb8rXnj/DwvglW018uP/1tqldwiJMbjxBhX7ZqwTw="
3906dbf2b5e78ff0f0be0956d35f2e3ffd6daa577088931b8f10615fb66ac13c
From an argument:
b64ToHex "OQbb8rXnj/DwvglW018uP/1tqldwiJMbjxBhX7ZqwTw="
3906dbf2b5e78ff0f0be0956d35f2e3ffd6daa577088931b8f10615fb66ac13c
Assign a variable:
b64ToHex -v someVar "OQbb8rXnj/DwvglW018uP/1tqldwiJMbjxBhX7ZqwTw="
echo "$someVar"
3906dbf2b5e78ff0f0be0956d35f2e3ffd6daa577088931b8f10615fb66ac13c
Then from, to variables:
b64ToHex -v iv_hex "${iv}"
b64ToHex -v key_hex "${key}"
Note: this is done without any fork.
For fun: retrieving original base64 string, with bash V5.1+, you could:
shopt -s extglob
printf %b ${someVar//??/\\x& } | base64
OQbb8rXnj/DwvglW018uP/1tqldwiJMbjxBhX7ZqwTw=
3. Pure bash way, but usign bash V5.2+
Same script, but by using patsub_replacement and mapfile, I could do this without any bash loop!
declare -a B64=( {A..Z} {a..z} {0..9} + / '=' )
printf -v _b64_tstr '["\44{B64[%d]}"]=%%d%%%%64 ' {0..64}
# shellcheck disable=SC2059 # format is variable.
printf -v _b64_tstr "$_b64_tstr" {0..64}
declare -Ai "B64R=($_b64_tstr)"
unset B64 _b64_tstr
declare -r B64R
b64ToHex52() {
local _line _Tail _v _opt OPTIND _resArry
local -i iFd _ar
while getopts "av:" _opt; do case $_opt in
a) _ar=1;; v) _v=${OPTARG};; *) return 1;; esac; done
shift $((OPTIND-1))
if [[ $_v ]];then local -n _res=${_v}; else local _res; fi
if [[ $1 ]]; then exec {iFd}<<<"$1" # Open Input FD from string
else exec {iFd}<&0 ; fi # Open Input FD from STDIN
mapfile -tu $iFd _lines
read -ra _resArry <<<"${_lines[*]//?/& }"
printf -v _tmpStr '"B64R[%s]<<18|B64R[%s]<<12|B64R[%s]<<6|B64R[%s]" ' \
"${_resArry[@]}"
local -ia "_tmpArry=($_tmpStr)"
printf -v _tmpStr '%06x' "${_tmpArry[@]}"
read -ra _res <<<"${_tmpStr//??/& }"
exec {iFd}<&-
_Tail=${_lines[-1]##*([^=])}
_res=("${_res[@]::${#_res[@]}-${#_Tail}}")
((_ar==0)) && printf -v _res %s "${_res[@]}" && _res=("${_res[0]}")
[[ -z $_v ]] && echo "${_res[@]}"
}
4. Execution time comparison
Well, now a little comparison test by doing repetitively same conversion to compute execution time.
I now have 4 functions:
b64toHex My version using base64 and xxd
b64ToHex My pure bash version (notice upper T)
b64ToHex52 My pure bash using bash version 5.2+
base64_to_hex from accepted answer.
Here's my little test function:
testB64decoders(){
local TIMEFORMAT='r %3lR, u %3lU, s %3lS, p %P' bunch \
inString="${2:-SGVsbG8gd29ybGQhIFRoaXMgaXMgYSB0ZXN0IHN0cmluZy4=}"
printf -v bunch '%*s' ${1:-100} ''
mapfile -t bunch <<<"${bunch// /$'\n'}"
printf ' - %-29s: ' "3 fork (base64 | xxd)";
time for i in "${bunch[@]}"; do b64toHex hx "$inString"; done
printf ' - %-29s: ' "Pure bash";
time for i in "${bunch[@]}"; do b64ToHex -v Hx "$inString"; done;
printf ' - %-29s: ' "Pure bash V5.2+";
time for i in "${bunch[@]}"; do b64ToHex52 -v Hx5 "$inString"; done;
printf ' - %-29s: ' "5 fork =\$(echo| base64 | xxd)";
time for i in "${bunch[@]}"; do hex=$(base64_to_hex "$inString"); done;
[[ $hx == "$hex" ]] && [[ $Hx == "$hx" ]] && [[ $Hx5 == "$hx" ]] &&
printf -v inString '%b' ${hx//??/\\x&} &&
printf 'Hopefully result strings are same (%s).\n' "${inString@Q}"
}
Let's show with a small thousand of operation:
testB64decoders 1000
Could produce something like:
- 3 fork (base64 | xxd) : r 0m2.032s, u 0m2.315s, s 0m0.699s, p 148.32
- Pure bash : r 0m0.965s, u 0m0.735s, s 0m0.213s, p 98.14
- Pure bash V5.2+ : r 0m0.571s, u 0m0.477s, s 0m0.088s, p 98.91
- 5 fork =$(echo| base64 | xxd): r 0m2.433s, u 0m3.242s, s 0m0.989s, p 173.92
Where r for real, u: user, s: system time and p: cpu percentage is: 100 * ( u + s ) / r
- pure bash method is quicker,
- pure bash method using bash 5.2+ is significantly quicker,
- version using
xxd and base64 with only two fork will even be a little quicker than
- version using four forks (a subshell to run three more forks to
xxd, base64 and tr). They are the slowest, and yes: two more forks do have system footprint.
Note: on a multicore system, user time is bigger than real time, thanks to parallelization
On my Raspberry-Pi II model B, I had to reduce my test down to 20 loops.
testB64decoders 20
Did produce on my RPi II:
- 3 fork (base64 | xxd) : r 0m2.134s, u 0m0.289s, s 0m0.704s, p 46.55
- Pure bash : r 0m1.931s, u 0m0.890s, s 0m0.104s, p 51.49
- Pure bash V5.2+ : r 0m0.874s, u 0m0.354s, s 0m0.078s, p 49.36
- 5 fork =$(echo| base64 | xxd): r 0m3.399s, u 0m0.787s, s 0m0.847s, p 48.06
Hopefully result strings are same ('Hello world! This is a test string.').
-c <number>option forxxd; with a large enough value (eg, in this case-c 64) thexxdoutput shows up on a single line; you can also go larger (eg,-c 100) without negative issues (ie, it'll still print the 64 characters on a single line); someone else asked a similar/related question a couple days ago; similarly for theiv_hexkey, use-c 32