Bash urlencode and urldecode

gistfile1.sh

urlencode() {
    # urlencode <string>

    old_lc_collate=$LC_COLLATE
    LC_COLLATE=C

    local length="${#1}"
    for (( i = 0; i < length; i++ )); do
        local c="${1:$i:1}"
        case $c in
            [a-zA-Z0-9.~_-]) printf '%s' "$c" ;;
            *) printf '%%%02X' "'$c" ;;
        esac
    done

    LC_COLLATE=$old_lc_collate
}

urldecode() {
    # urldecode <string>

    local url_encoded="${1//+/ }"
    printf '%b' "${url_encoded//%/\\x}"
}

@cjplay02 I'm pretty sure the issue is elsewhere.

$ urldecode() {
    # urldecode <string>

    local url_encoded="${1//+/ }"
    printf '%b' "${url_encoded//%/\\x}"
}
$ urldecode 'foo%20%20%20%20%20bar'
foo     bar

Good call @cdown. I had the urldecode call in a command substitution - urldecoded=$(urldecode 's3://...'). Once I removed the function call from the command substitution, the spaces were retained from the encoding. Now I just need to find a better way to declare the result as a variable...

Edit. Double Quoting around the variable's presentation in downstream commands fixed my issue. Ie echo "$varname"

just a brief nod to mawk
which is five times faster in my tests
(indeed, often faster than sed)

I know it's not a de facto standard like bash
i.e. installed by default on so many systems
but it should be and it is on my systems

I also notice that bash seems to be catching up with ksh93

One line implementation, suitable for storing in .bashrc

urle () { [[ "${1}" ]] || return 1; local LANG=C i x; for (( i = 0; i < ${#1}; i++ )); do x="${1:i:1}"; [[ "${x}" == [a-zA-Z0-9.~_-] ]] && echo -n "${x}" || printf '%%%02X' "'${x}"; done; echo; }
urld () { [[ "${1}" ]] || return 1; : "${1//+/ }"; echo -e "${_//%/\\x}"; }

Thanks for it!

Thanks for this.
Could you please also license this code of yours?

Thanks for the script, but i don't know why when calling urlencode i got in the encoded data a : % at the end !

i had to add a check for systems where collate is not set

if [ -n "$old_lc_collate" ] ; then LC_COLLATE=$old_lc_collate ; fi

LC_ALL=C is needed to support unicode = loop bytes, not characters.
LC_COLLATE=C or LANG=C do not work.
this also must be set before ${#1} to get the length of $1 in bytes

#!/usr/bin/env bash
# MIT License

# encode special characters per RFC 3986
urlencode() {
    local LC_ALL=C # support unicode = loop bytes, not characters
    local c i n=${#1}
    for (( i=0; i<n; i++ )); do
        c="${1:i:1}"
        case "$c" in
            [-_.~A-Za-z0-9]) # also encode ;,/?:@&=+$!*'()# == encodeURIComponent in javascript
            #[-_.~A-Za-z0-9\;,/?:@\&=+\$!*\'\(\)#]) # dont encode ;,/?:@&=+$!*'()# == encodeURI in javascript
               printf '%s' "$c" ;;
            *) printf '%%%02X' "'$c" ;;
        esac
    done
    echo
}

_test_urlencode() {
  local fname=urlencode
  local auml=$'\xC3\xA4' # ä = %C3%A4
  local euro=$'\xE2\x82\xAC' # € = %E2%82%AC
  local tick=$'\x60' # ` = %60
  local backtick=$'\xC2\xB4' # ´ = %C2%B4
  local input="a:/b c?d=e&f#g-+-;-,-@-\$-!-*-'-(-)-#-$tick-$backtick-$auml-$euro"
  # note: we expect uppercase hex codes from %02X format string
  local expected="a%3A%2Fb%20c%3Fd%3De%26f%23g-%2B-%3B-%2C-%40-%24-%21-%2A-%27-%28-%29-%23-%60-%C2%B4-%C3%A4-%E2%82%AC" # also encode ;,/?:@&=+$!*'()#
  #local expected="a:/b%20c?d=e&f#g-+-;-,-@-\$-!-*-'-(-)-#-%60-%C2%B4-%C3%A4-%E2%82%AC" # dont encode ;,/?:@&=+$!*'()#
  local actual="$($fname "$input")"
  if [[ "$actual" != "$expected" ]]; then
    echo "error in $fname"
    # debug
    echo "input: $input"
    echo "input hex:"; echo -n "$input" | hexdump -v -e '/1 "%02X"' | sed 's/\(..\)/\\x\1/g'; echo
    echo "input hexdump:"; echo -n "$input" | hexdump -C
    printf "actual:   "; echo "$actual"
    printf "expected: "; echo "$expected"
    exit 1
  fi
}
_test_urlencode

This works for me.

https://stackoverflow.com/questions/296536/how-to-urlencode-data-for-curl-command

rawurlencode() {
  local string="${1}"
  local strlen=${#string}
  local encoded=""
  local pos c o

  for (( pos=0 ; pos<strlen ; pos++ )); do
     c=${string:$pos:1}
     case "$c" in
        [-_.~a-zA-Z0-9] ) o="${c}" ;;
        * )               printf -v o '%%%02x' "'$c"
     esac
     encoded+="${o}"
  done
  echo "${encoded}"    # You can either set a return variable (FASTER) 
  REPLY="${encoded}"   #+or echo the result (EASIER)... or both... :p
}

@ThePredators this breaks on unicode

input: a:/b c?d=e&f#g-+-`-´-ä-€
input hex:
\x61\x3A\x2F\x62\x20\x63\x3F\x64\x3D\x65\x26\x66\x23\x67\x2D\x2B\x2D\x60\x2D\xC2\xB4\x2D\xC3\xA4\x2D\xE2\x82\xAC
input hexdump:
00000000  61 3a 2f 62 20 63 3f 64  3d 65 26 66 23 67 2d 2b  |a:/b c?d=e&f#g-+|
00000010  2d 60 2d c2 b4 2d c3 a4  2d e2 82 ac              |-`-..-..-...|
0000001c
actual:   a%3A%2Fb%20c%3Fd%3De%26f%23g-%2B-%60-%B4-%E4-%20AC
expected: a%3A%2Fb%20c%3Fd%3De%26f%23g-%2B-%60-%C2%B4-%C3%A4-%E2%82%AC

see my updated answer

@ThePredators works like a charm 👍

Hi,

Characters used in France are not taken into account: (é è à ù ê â û ...) if you work in fr_FR locale.

You need to convert your data source from Windows-1252 to UTF-8 before entering in the function ::

data_utf8=$(echo "$data_ISO" | iconv -f iso8859-1 -t utf-8)

#!/bin/bash
 
 ## Written by Adam Danischewski 08/04/2024

declare CURR_ORD 

str="${1:-😄.mp4}"

function ord() {
    printf -v CURR_ORD "%d" "\"$1"
}

function has_unicode() { 
 local input="$1"
 local -i charcnt=$(wc -m <<<"$input")
 local -i bytecnt=$(wc -c <<<"$input")
 ((charcnt!=bytecnt))
 return $?
}

function urlencode() {
    sed "s/\x25/%25/g;s/\x20/%20/g;s/\x21/%21/g;s/\x22/%22/g;s/\x23/%23/g;s/\x5c\x24/%24/g;\
        s/\x26/%26/g;s/\x27/%27/g;s/\x28/%28/g;s/\x29/%29/g;s/\x2A/%2A/g;s/\x2B/%2B/g;\
        s/\x2C/%2C/g;s/\x2D/%2D/g;s/\x3A/%3A/g;s/\x3F/%3F/g;s/\x7C/%7C/g;s/\x5c\x5B/%5B/g"
}

function encode_unicode() { 
for ((i=0;i<${#str};i++)); do
    char=${str:i:1}
    ord "$char"
    if ((${#CURR_ORD}>3)); then 
     od -t x1 <<< "$char" | awk '{$1="";gsub("^[[:space:]]*","");for(i=1;i<NF;i++) printf "%%" toupper($i);}'
    else 
     printf "%s" "$char" 
    fi 
done
}

## Tokenize percents before encoding unicode 
function tokenize_orig_pcts() {
  sed 's/%/\x01/g'
} 

## Tokenize percents after encoding unicode, since this is urlencoded..  
function tokenize_pcts() {
  sed 's/%/\x02/g'
} 

function detokenize_orig_pcts() {
  sed 's/\x01/%/g'
} 

function detokenize_pcts() {
  sed 's/\x02/%/g'
} 

function urlencode() { 
 sed "s/\x25/%25/g;s/\x20/%20/g;s/\x21/%21/g;s/\x22/%22/g;s/\x23/%23/g;s/\x5c\x24/%24/g;\
        s/\x26/%26/g;s/\x27/%27/g;s/\x28/%28/g;s/\x29/%29/g;s/\x2A/%2A/g;s/\x2B/%2B/g;\
        s/\x2C/%2C/g;s/\x3A/%3A/g;s/\x3F/%3F/g;s/\x7C/%7C/g;s/\x5c\x5B/%5B/g"
}

function main() { 
  if has_unicode "$str"; then 
    str=$(tokenize_orig_pcts <<< "$str")
    str=$(encode_unicode)
    str=$(tokenize_pcts <<< "$str")
    str=$(detokenize_orig_pcts <<< "$str")
    str=$(urlencode <<< "$str")
    detokenize_pcts <<< "$str"
  else 
    urlencode <<< "$str"
  fi  
}

main

This matches (according to my tests) the output from: jq -jRr '@uri'

Great functions 👍

Unfortunately none of the decode options work with German Umlauts:

Example:
Encode: Günther -> G%FCnther
Decode: G%FCnther -> G�nther

It seems to be something with the encoding. I tried to add "| iconv -f iso8859-1 -t utf-8" as @Twibow says to the decode function from start post but it changes nothing.

Any help appreciated 😄