Differences between revisions 7 and 28 (spanning 21 versions)
Revision 7 as of 2009-10-12 18:50:53
Size: 1840
Comment: added function to convert a number in a given base to decimal
Revision 28 as of 2012-01-08 21:07:32
Size: 24037
Editor: dethrophes
Comment: I added some simple test cases and discovered some weird bash behaviour, whihc I've reported as a bug. But I've added a workaround these functions.
Deletions are marked like this. Additions are marked like this.
Line 10: Line 10:
{{{
   ExpandedString=$'\x27\047\u0027\U00000027\n'
   echo -n "$ExpandedString"
}}}
Another approach `$'...'` strings are escaped before evaluation and can be embedded directly in code.
Line 12: Line 17:

 ''The following example was submitted quite recently and needs to be cleaned up and validated. In particular, the function names with periods in them are abusing an undocumented, possibly unintended bash parsing glitch.''
Line 13: Line 21:
   # POSIX
   # chr() - converts decimal value to its ASCII character representation
   # ord() - converts ASCII character to its decimal value
 
   chr() {
     printf \\$(printf '%03o' $1)
   }
 
   ord() {
     printf '%d' "'$1"
   }

   # hex() - converts ASCII character to a hexadecimal value
   # unhex() - converts a hexadecimal value to an ASCII character

   hex() {
      printf '%x' "'$1"
   }

   unhex() {
      printf \\x"$1"
   }

   todec() {
      echo $(( $1#$2 ))
   }

   # examples:
 
   chr $(ord A) # -> A
   ord $(chr 65) # -> 65

   todec 16 ffe # -> 4094
   todec 2 100100 # -> 36
        ###############################################################
        #
        # Note about Ext Ascii and UTF-8 encoding
        #
        # for values 0x00 - 0x7f Identical
        # for values 0x80 - 0xff conflict between UTF-8 & ExtAscii
        # for values 0x100 - 0xffff Only UTF-8 UTF-16 UTF-32
        # for values 0x100 - 0x7FFFFFFF Only UTF-8 UTF-32
        #
        # value EAscii UTF-8 UTF-16 UTF-32
        # 0x20 "\x20" "\x20" \u0020 \U00000020
        # 0x20 "\x7f" "\x7f" \u007f \U0000007f
        # 0x80 "\x80" "\xc2\x80" \u0080 \U00000080
        # 0xff "\xff" "\xc3\xbf" \u00ff \U000000ff
        # 0x100 N/A "\xc4\x80" \u0100 \U00000100
        # 0x1000 N/A "\xc8\x80" \u1000 \U00001000
        # 0xffff N/A "\xef\xbf\xbf" \uffff \U0000ffff
        # 0x10000 N/A "\xf0\x90\x80\x80" N/A \U00010000
        # 0xfffff N/A "\xf3\xbf\xbf\xbf" N/A \U000fffff
        # 0x10000000 N/A "\xfc\x90\x80\x80\x80\x80" N/A \U10000000
        # 0x7fffffff N/A "\xfd\xbf\xbf\xbf\xbf\xbf" N/A \U7fffffff
        # 0x80000000 N/A N/A N/A N/A
        # 0xffffffff N/A N/A N/A N/A

        ###########################################################################
        ## ord family
        ###########################################################################
        # ord <Return Variable Name> <Char to convert> [Optional Format String]
        # ord.hex <Return Variable Name> <Char to convert>
        # ord.oct <Return Variable Name> <Char to convert>
        # ord.utf8 <Return Variable Name> <Char to convert> [Optional Format String]
        # ord.eascii <Return Variable Name> <Char to convert> [Optional Format String]
        # ord.echo <Char to convert> [Optional Format String]
        # ord.hex.echo <Char to convert>
        # ord.oct.echo <Char to convert>
        # ord.utf8.echo <Char to convert> [Optional Format String]
        # ord.eascii.echo <Char to convert> [Optional Format String]
        #
        # Description:
        # converts character using native encoding to its decimal value and stores
        # it in the Variable specified
        #
        # ord
        # ord.hex output in hex
        # ord.hex output in octal
        # ord.utf8 forces UTF8 decoding
        # ord.eascii forces eascii decoding
        # ord.echo prints to stdout
        function ord {
                printf -v "${1?Missing Dest Variable}" "${3:-%d}" "'${2?Missing Char}"
        }
        function ord.oct {
                ord "${@:1:2}" "0%c"
        }
        function ord.hex {
                ord "${@:1:2}" "0x%x"
        }
        function ord.utf8 {
                LC_CTYPE=en_US.UTF8 ord "${@}"
        }
        function ord.eascii {
                LC_CTYPE=C ord "${@}"
        }
        function ord.echo {
                printf "${2:-%d}" "'${1?Missing Char}"
        }
        function ord.oct.echo {
                ord.echo "${1}" "0%o"
        }
        function ord.hex.echo {
                ord.echo "${1}" "0x%x"
        }
        function ord.utf8.echo {
                LC_CTYPE=en_US.UTF8 ord.echo "${@}"
        }
        function ord.eascii.echo {
                LC_CTYPE=C ord.echo "${@}"
        }

        ###########################################################################
        ## chr family
        ###########################################################################
        # chr.utf8 <Return Variale Name> <Integer to convert>
        # chr.eascii <Return Variale Name> <Integer to convert>
        # chr <Return Variale Name> <Integer to convert>
        # chr.oct <Return Variale Name> <Octal number to convert>
        # chr.hex <Return Variale Name> <Hex number to convert>
        # chr.utf8.echo <Integer to convert>
        # chr.eascii.echo <Integer to convert>
        # chr.echo <Integer to convert>
        # chr.oct.echo <Octal number to convert>
        # chr.hex.echo <Hex number to convert>
        #
        # Description:
        # converts decimal value to character representation an stores
        # it in the Variable specified
        #
        # chr Tries to guess output format
        # chr.utf8 forces UTF8 encoding
        # chr.eascii forces eascii encoding
        # chr.echo prints to stdout
        #
        function chr.utf8 {
                local val
                [[ ${2?Missing Ordinal Value} -lt 0x80000000 ]] || return 1

                if [[ ${2} -lt 0x100 && ${2} -ge 0x80 ]]; then
                        # some kinda weird bash? behavior
                        # treats \Uff as \xff so encode manually
                        printf -v val "\\%o\%o" $(( (${2}>>6)|0xc0 )) $(( (${2}&0x3f)|0x80 ))
                else
                        # Note in embedded cases always do \U%08x \u04x
                        # here however no need to because of the EOS
                        printf -v val '\\U%x' "${2}"
                fi
                printf -v ${1?Missing Dest Variable} ${val}
        }
        function chr.eascii {
                local val
                # Make sure value less than 0x100
                # otherwise we end up with
                # \xVVNNNNN
                # where \xVV = char && NNNNN is a number string
                # so chr "0x44321" => "D321"
                [[ ${2?Missing Ordinal Value} -lt 0x100 ]] || return 1
                printf -v val '\\x%02x' "${2}"
                printf -v ${1?Missing Dest Variable} ${val}
        }
        function chr {
                if [ "${LC_CTYPE:-${LC_ALL:-}}" = "C" ]; then
                        chr.eascii "${@}"
                else
                        chr.utf8 "${@}"
                fi
        }
        function chr.dec {
                # strip leading 0s otherwise
                # interpreted as Octal
                if shopt extglob &>/dev/null ;then
                        chr "${1}" "${2/#+(0)}"
                else
                        shopt -s extglob
                        chr "${1}" "${2/#+(0)}"
                        shopt -u extglob
                fi
        }
        function chr.oct {
                chr "${1}" "0${2}"
        }
        function chr.hex {
                chr "${1}" "0x${2}"
        }
        function chr.utf8.echo {
                local val
                [[ ${1?Missing Ordinal Value} -lt 0x80000000 ]] || return 1

                if [[ ${1} -lt 0x100 && ${1} -ge 0x80 ]]; then
                        # some kinda weird bash? behavior
                        # treats \Uff as \xff so encode manually
                        printf -v val '\\%o\\%o' $(( (${1}>>6)|0xc0 )) $(( (${1}&0x3f)|0x80 ))
                else
                        # Note in embedded cases always do \\U%08x \u04x
                        # here however no need to because of the EOS
                        printf -v val '\\U%x' "${1}"
                fi
                printf "${val}"
        }
        function chr.eascii.echo {
                local val
                # Make sure value less than 0x100
                # otherwise we end up with
                # \xVVNNNNN
                # where \xVV = char && NNNNN is a number string
                # so chr "0x44321" => "D321"
                [[ ${1?Missing Ordinal Value} -lt 0x100 ]] || return 1
                printf -v val '\\x%x' "${1}"
                printf "${val}"
        }
        function chr.echo {
                if [ "${LC_CTYPE:-${LC_ALL:-}}" = "C" ]; then
                        chr.eascii.echo "${@}"
                else
                        chr.utf8.echo "${@}"
                fi
        }
        function chr.dec.echo {
                # strip leading 0s otherwise
                # interpreted as Octal
                if shopt extglob &>/dev/null ;then
                        chr.echo "${1/#+(0)}"
                else
                        shopt -s extglob
                        chr.echo "${1/#+(0)}"
                        shopt -u extglob
                fi
        }
        function chr.oct.echo {
                chr.echo "0${1}"
        }
        function chr.hex.echo {
                chr.echo "0x${1}"
        }
   
    #
    # Simple Validation code
    #
      function test_echo_func {
        local Outcome
        local _result="$( "${1}" "${2}" )"
        if [ "${_result}" = "${3}" ]; then
          Outcome="Pass"
        else
          Outcome="Fail"
        fi
        printf "# %-20s %-6s => [ "%16q" = "%-16q"%-5s ] %s\n" "${1}" "${2}" "${_result}" "${3}" "(${3//[[:cntrl:]]/_})" "${Outcome}"
      }
      function test_value_func {
        local Outcome
        local _result
        "${1}" _result "${2}"
        if [ "${_result}" = "${3}" ]; then
          Outcome="Pass"
        else
          Outcome="Fail"
        fi
        printf "# %-20s %-6s => [ "%16q" = "%-16q"%-5s ] %s\n" "${1}" "${2}" "${_result}" "${3}" "(${3//[[:cntrl:]]/_})" "${Outcome}"
      }
    test_echo_func chr.echo "$(ord.echo A)" "A"
    test_echo_func ord.echo "$(chr.echo 65)" "65"
    test_echo_func chr.echo "$(ord.echo "ö")" "ö"
    test_value_func chr "$(ord.echo A)" "A"
    test_value_func ord "$(chr.echo 65)" "65"
    test_value_func chr "$(ord.echo "ö")" "ö"
# chr.echo 65 => [ A = A (A) ] Pass
# ord.echo A => [ 65 = 65 (65) ] Pass
# chr.echo 246 => [ $'\303\266' = $'\303\266' (ö) ] Pass
# chr 65 => [ A = A (A) ] Pass
# ord A => [ 65 = 65 (65) ] Pass
# chr 246 => [ $'\303\266' = $'\303\266' (ö) ] Pass
#


    test_echo_func chr.echo "65" A
    test_echo_func chr.echo "065" 5
    test_echo_func chr.dec.echo "065" A
    test_echo_func chr.oct.echo "65" 5
    test_echo_func chr.hex.echo "65" e
    test_value_func chr "65" A
    test_value_func chr "065" 5
    test_value_func chr.dec "065" A
    test_value_func chr.oct "65" 5
    test_value_func chr.hex "65" e
# chr.echo 65 => [ A = A (A) ] Pass
# chr.echo 065 => [ 5 = 5 (5) ] Pass
# chr.dec.echo 065 => [ A = A (A) ] Pass
# chr.oct.echo 65 => [ 5 = 5 (5) ] Pass
# chr.hex.echo 65 => [ e = e (e) ] Pass
# chr 65 => [ A = A (A) ] Pass
# chr 065 => [ 5 = 5 (5) ] Pass
# chr.dec 065 => [ A = A (A) ] Pass
# chr.oct 65 => [ 5 = 5 (5) ] Pass
# chr.hex 65 => [ e = e (e) ] Pass

    #test_value_func chr 0xff $'\xff'
    test_value_func chr.eascii 0xff $'\xff'
    test_value_func chr.utf8 0xff $'\uff' # Note this fails because bash encodes it wrong
    test_value_func chr.utf8 0xff $'\303\277'
    test_value_func chr.utf8 0x100 $'\u100'
    test_value_func chr.utf8 0x1000 $'\u1000'
    test_value_func chr.utf8 0xffff $'\uffff'
# chr.eascii 0xff => [ $'\377' = $'\377' (�) ] Pass
# chr.utf8 0xff => [ $'\303\277' = $'\377' (�) ] Fail
# chr.utf8 0xff => [ $'\303\277' = $'\303\277' (ÿ) ] Pass
# chr.utf8 0x100 => [ $'\304\200' = $'\304\200' (Ā) ] Pass
# chr.utf8 0x1000 => [ $'\341\200\200' = $'\341\200\200' (က) ] Pass
# chr.utf8 0xffff => [ $'\357\277\277' = $'\357\277\277' (���) ] Pass



  #########################################################
  # to help debug problems try this
  #########################################################
  printf "%q\n" $'\xff' # => $'\377'
  printf "%q\n" $'\uffff' # => $'\357\277\277'
  printf "%q\n" "$(chr.utf8.echo 0x100)" # => $'\304\200'
  #
  # This can help a lot when it comes to diagnosing problems
  # with read and or xterm program output
  # I use it a lot in error case to create a human readable error message
  # i.e.
  echo "Enter type to test, Enter to continue"
  while read -srN1 ; do
    ord asciiValue "${REPLY}"
    case "${asciiValue}" in
      10) echo "Goodbye" ; break ;;
      20|21|22) echo "Yay expected input" ;;
      *) printf ':( Unexpected Input 0x%02x %q "%s"\n' "${asciiValue}" "${REPLY}" "${REPLY//[[:cntrl:]]}" ;;
    esac
  done

  #########################################################
  # More exotic approach 1
  #########################################################
  # I used to use this before I figured out the LC_CTYPE=C approach
  # printf "EAsciiLookup=%q" "$(for (( x=0x0; x<0x100 ; x++)); do printf '%b' $(printf '\\x%02x' "$x"); done)"
  EAsciiLookup=$'\001\002\003\004\005\006\a\b\t\n\v\f\r\016\017\020\021\022\023\024\025\026\027\030\031\032\E\034\035\036\037 !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377'
  function ord.eascii2 {
    local idx="${EAsciiLookup%%${2:0:1}*}"
    eval ${1}'=$(( ${#idx} +1 ))'
  }

  #########################################################
  # More exotic approach 2
  #########################################################
  #printf "EAsciiLookup2=(\n %s\n)" "$(for (( x=0x1; x<0x100 ; x++)); do printf '%-18s' "$(printf '[_%q]="0x%02x"' "$(printf "%b" "$(printf '\\x%02x' "$x")")" $x )" ; [ "$(($x%6))" != "0" ] || echo -en "\n " ; done)"
  typeset -A EAsciiLookup2
  EAsciiLookup2=(
    [_$'\001']="0x01" [_$'\002']="0x02" [_$'\003']="0x03" [_$'\004']="0x04"
    [_$'\005']="0x05" [_$'\006']="0x06" [_$'\a']="0x07" [_$'\b']="0x08"
    [_$'\t']="0x09" [_'']="0x0a" [_$'\v']="0x0b" [_$'\f']="0x0c"
    [_$'\r']="0x0d" [_$'\016']="0x0e" [_$'\017']="0x0f" [_$'\020']="0x10"
    [_$'\021']="0x11" [_$'\022']="0x12" [_$'\023']="0x13" [_$'\024']="0x14"
    [_$'\025']="0x15" [_$'\026']="0x16" [_$'\027']="0x17" [_$'\030']="0x18"
    [_$'\031']="0x19" [_$'\032']="0x1a" [_$'\E']="0x1b" [_$'\034']="0x1c"
    [_$'\035']="0x1d" [_$'\036']="0x1e" [_$'\037']="0x1f" [_\ ]="0x20"
    [_\!]="0x21" [_\"]="0x22" [_\#]="0x23" [_\$]="0x24"
    [_%]="0x25" [_\&]="0x26" [_\']="0x27" [_\(]="0x28"
    [_\)]="0x29" [_\*]="0x2a" [_+]="0x2b" [_\,]="0x2c"
    [_-]="0x2d" [_.]="0x2e" [_/]="0x2f" [_0]="0x30"
    [_1]="0x31" [_2]="0x32" [_3]="0x33" [_4]="0x34"
    [_5]="0x35" [_6]="0x36" [_7]="0x37" [_8]="0x38"
    [_9]="0x39" [_:]="0x3a" [_\;]="0x3b" [_\<]="0x3c"
    [_=]="0x3d" [_\>]="0x3e" [_\?]="0x3f" [_@]="0x40"
    [_A]="0x41" [_B]="0x42" [_C]="0x43" [_D]="0x44"
    [_E]="0x45" [_F]="0x46" [_G]="0x47" [_H]="0x48"
    [_I]="0x49" [_J]="0x4a" [_K]="0x4b" [_L]="0x4c"
    [_M]="0x4d" [_N]="0x4e" [_O]="0x4f" [_P]="0x50"
    [_Q]="0x51" [_R]="0x52" [_S]="0x53" [_T]="0x54"
    [_U]="0x55" [_V]="0x56" [_W]="0x57" [_X]="0x58"
    [_Y]="0x59" [_Z]="0x5a" [_\[]="0x5b" #[_\\]="0x5c"
    #[_\]]="0x5d"
                      [_\^]="0x5e" [__]="0x5f" [_\`]="0x60"
    [_a]="0x61" [_b]="0x62" [_c]="0x63" [_d]="0x64"
    [_e]="0x65" [_f]="0x66" [_g]="0x67" [_h]="0x68"
    [_i]="0x69" [_j]="0x6a" [_k]="0x6b" [_l]="0x6c"
    [_m]="0x6d" [_n]="0x6e" [_o]="0x6f" [_p]="0x70"
    [_q]="0x71" [_r]="0x72" [_s]="0x73" [_t]="0x74"
    [_u]="0x75" [_v]="0x76" [_w]="0x77" [_x]="0x78"
    [_y]="0x79" [_z]="0x7a" [_\{]="0x7b" [_\|]="0x7c"
    [_\}]="0x7d" [_~]="0x7e" [_$'\177']="0x7f" [_$'\200']="0x80"
    [_$'\201']="0x81" [_$'\202']="0x82" [_$'\203']="0x83" [_$'\204']="0x84"
    [_$'\205']="0x85" [_$'\206']="0x86" [_$'\207']="0x87" [_$'\210']="0x88"
    [_$'\211']="0x89" [_$'\212']="0x8a" [_$'\213']="0x8b" [_$'\214']="0x8c"
    [_$'\215']="0x8d" [_$'\216']="0x8e" [_$'\217']="0x8f" [_$'\220']="0x90"
    [_$'\221']="0x91" [_$'\222']="0x92" [_$'\223']="0x93" [_$'\224']="0x94"
    [_$'\225']="0x95" [_$'\226']="0x96" [_$'\227']="0x97" [_$'\230']="0x98"
    [_$'\231']="0x99" [_$'\232']="0x9a" [_$'\233']="0x9b" [_$'\234']="0x9c"
    [_$'\235']="0x9d" [_$'\236']="0x9e" [_$'\237']="0x9f" [_$'\240']="0xa0"
    [_$'\241']="0xa1" [_$'\242']="0xa2" [_$'\243']="0xa3" [_$'\244']="0xa4"
    [_$'\245']="0xa5" [_$'\246']="0xa6" [_$'\247']="0xa7" [_$'\250']="0xa8"
    [_$'\251']="0xa9" [_$'\252']="0xaa" [_$'\253']="0xab" [_$'\254']="0xac"
    [_$'\255']="0xad" [_$'\256']="0xae" [_$'\257']="0xaf" [_$'\260']="0xb0"
    [_$'\261']="0xb1" [_$'\262']="0xb2" [_$'\263']="0xb3" [_$'\264']="0xb4"
    [_$'\265']="0xb5" [_$'\266']="0xb6" [_$'\267']="0xb7" [_$'\270']="0xb8"
    [_$'\271']="0xb9" [_$'\272']="0xba" [_$'\273']="0xbb" [_$'\274']="0xbc"
    [_$'\275']="0xbd" [_$'\276']="0xbe" [_$'\277']="0xbf" [_$'\300']="0xc0"
    [_$'\301']="0xc1" [_$'\302']="0xc2" [_$'\303']="0xc3" [_$'\304']="0xc4"
    [_$'\305']="0xc5" [_$'\306']="0xc6" [_$'\307']="0xc7" [_$'\310']="0xc8"
    [_$'\311']="0xc9" [_$'\312']="0xca" [_$'\313']="0xcb" [_$'\314']="0xcc"
    [_$'\315']="0xcd" [_$'\316']="0xce" [_$'\317']="0xcf" [_$'\320']="0xd0"
    [_$'\321']="0xd1" [_$'\322']="0xd2" [_$'\323']="0xd3" [_$'\324']="0xd4"
    [_$'\325']="0xd5" [_$'\326']="0xd6" [_$'\327']="0xd7" [_$'\330']="0xd8"
    [_$'\331']="0xd9" [_$'\332']="0xda" [_$'\333']="0xdb" [_$'\334']="0xdc"
    [_$'\335']="0xdd" [_$'\336']="0xde" [_$'\337']="0xdf" [_$'\340']="0xe0"
    [_$'\341']="0xe1" [_$'\342']="0xe2" [_$'\343']="0xe3" [_$'\344']="0xe4"
    [_$'\345']="0xe5" [_$'\346']="0xe6" [_$'\347']="0xe7" [_$'\350']="0xe8"
    [_$'\351']="0xe9" [_$'\352']="0xea" [_$'\353']="0xeb" [_$'\354']="0xec"
    [_$'\355']="0xed" [_$'\356']="0xee" [_$'\357']="0xef" [_$'\360']="0xf0"
    [_$'\361']="0xf1" [_$'\362']="0xf2" [_$'\363']="0xf3" [_$'\364']="0xf4"
    [_$'\365']="0xf5" [_$'\366']="0xf6" [_$'\367']="0xf7" [_$'\370']="0xf8"
    [_$'\371']="0xf9" [_$'\372']="0xfa" [_$'\373']="0xfb" [_$'\374']="0xfc"
    [_$'\375']="0xfd" [_$'\376']="0xfe" [_$'\377']="0xff"
  )
  function ord.eascii3 {
        local -i val="${EAsciiLookup2["_${2:0:1}"]-}"
        if [ "${val}" -eq 0 ]; then
                case "${2:0:1}" in
                        ]) val=0x5d ;;
                        \\) val=0x5c ;;
                esac
        fi
        eval "${1}"'="${val}"'
  }
  # for fun check out the following
  time for (( i=0 ; i <1000; i++ )); do ord TmpVar 'a'; done
  # real 0m0.065s
  # user 0m0.048s
  # sys 0m0.000s

  time for (( i=0 ; i <1000; i++ )); do ord.eascii TmpVar 'a'; done
  # real 0m0.239s
  # user 0m0.188s
  # sys 0m0.000s

  time for (( i=0 ; i <1000; i++ )); do ord.eascii2 TmpVar 'a'; done
  # real 0m1.507s
  # user 0m1.056s
  # sys 0m0.012s

  time for (( i=0 ; i <1000; i++ )); do ord.eascii3 TmpVar 'a'; done
  # real 0m0.147s
  # user 0m0.120s
  # sys 0m0.000s
Line 49: Line 437:
Here are some older, simpler functions that do similar things:

{{{
# POSIX
# chr() - converts decimal value to its ASCII character representation
# ord() - converts ASCII character to its decimal value

chr() {
  [ ${1} -lt 256 ] || return 1
  printf \\$(printf '%03o' $1)
}
  
# Another version doing the octal conversion with arithmetic
# faster as it avoids a subshell
chr () {
  [ ${1} -lt 256 ] || return 1
  printf \\$(($1/64*100+$1%64/8*10+$1%8))
}

# Another version using a temporary variable to avoid subshell.
# This one requires bash 3.1.
chr() {
  local tmp
  [ ${1} -lt 256 ] || return 1
  printf -v tmp '%03o' "$1"
  printf \\"$tmp"
}

ord() {
  printf '%d' "'$1"
}

# hex() - converts ASCII character to a hexadecimal value
# unhex() - converts a hexadecimal value to an ASCII character

hex() {
   printf '%x' "'$1"
}

unhex() {
   printf \\x"$1"
}

# examples:

chr $(ord A) # -> A
ord $(chr 65) # -> 65
}}}
Line 51: Line 488:
 ''Tricky? Rather, it's using a feature that I can't find documented anywhere -- putting a single quote in front of an integer. Neat effect, but how on '''earth''' did you find out about it? Source diving? -- GreyCat''

 
''It validates The Single Unix Specification: "If the leading character is a single-quote or double-quote, the value shall be the numeric value in the underlying codeset of the character following the single-quote or double-quote." (see [[http://www.opengroup.org/onlinepubs/009695399/utilities/printf.html|printf()]] to know more) -- mjf''
 . ''Tricky? Rather, it's using a feature that I can't find documented anywhere -- putting a single quote in front of an integer. Neat effect, but how on '''earth''' did you find out about it? Source diving? -- GreyCat''
  . ''It validates The Single Unix Specification: "If the leading character is a single-quote or double-quote, the value shall be the numeric value in the underlying codeset of the character following the single-quote or double-quote." (see [[http://www.opengroup.org/onlinepubs/009695399/utilities/printf.html|printf()]] to know more) -- mjf''
 $'\357\277\277'
  printf "%q\n" "$(chr.utf8.echo 0x100)" # =

How do I convert an ASCII character to its decimal (or hexadecimal) value and back?

If you have a known octal or hexadecimal value (at script-writing time), you can just use printf:

   # POSIX
   printf '\x27\047\n'

This prints two literal ' characters (27 is the hexadecimal ASCII value of the character, and 47 is the octal value) and a newline.

   ExpandedString=$'\x27\047\u0027\U00000027\n'
   echo -n "$ExpandedString"                   

Another approach $'...' strings are escaped before evaluation and can be embedded directly in code.

If you need to convert characters (or numeric ASCII values) that are not known in advance (i.e., in variables), you can use something a little more complicated:

  • The following example was submitted quite recently and needs to be cleaned up and validated. In particular, the function names with periods in them are abusing an undocumented, possibly unintended bash parsing glitch.

        ###############################################################
        #
        #       Note about Ext Ascii and UTF-8 encoding
        #
        # for values 0x00   - 0x7f        Identical
        # for values 0x80   - 0xff        conflict between UTF-8 & ExtAscii
        # for values 0x100  - 0xffff      Only UTF-8 UTF-16 UTF-32
        # for values 0x100  - 0x7FFFFFFF  Only UTF-8 UTF-32
        #
        # value         EAscii   UTF-8                          UTF-16  UTF-32
        # 0x20          "\x20"  "\x20"                          \u0020  \U00000020
        # 0x20          "\x7f"  "\x7f"                          \u007f  \U0000007f
        # 0x80          "\x80"  "\xc2\x80"                      \u0080  \U00000080
        # 0xff          "\xff"  "\xc3\xbf"                      \u00ff  \U000000ff
        # 0x100         N/A     "\xc4\x80"                      \u0100  \U00000100
        # 0x1000        N/A     "\xc8\x80"                      \u1000  \U00001000
        # 0xffff        N/A     "\xef\xbf\xbf"                  \uffff  \U0000ffff
        # 0x10000       N/A     "\xf0\x90\x80\x80"              N/A     \U00010000
        # 0xfffff       N/A     "\xf3\xbf\xbf\xbf"              N/A     \U000fffff
        # 0x10000000    N/A     "\xfc\x90\x80\x80\x80\x80"      N/A     \U10000000
        # 0x7fffffff    N/A     "\xfd\xbf\xbf\xbf\xbf\xbf"      N/A     \U7fffffff
        # 0x80000000    N/A     N/A                             N/A     N/A
        # 0xffffffff    N/A     N/A                             N/A     N/A

        ###########################################################################
        ## ord family
        ###########################################################################
        # ord        <Return Variable Name> <Char to convert> [Optional Format String]
        # ord.hex    <Return Variable Name> <Char to convert>
        # ord.oct    <Return Variable Name> <Char to convert>
        # ord.utf8   <Return Variable Name> <Char to convert> [Optional Format String]
        # ord.eascii <Return Variable Name> <Char to convert> [Optional Format String]
        # ord.echo                      <Char to convert> [Optional Format String]
        # ord.hex.echo                  <Char to convert>
        # ord.oct.echo                  <Char to convert>
        # ord.utf8.echo                 <Char to convert> [Optional Format String]
        # ord.eascii.echo               <Char to convert> [Optional Format String]
        #
        # Description:
        # converts character using native encoding to its decimal value and stores
        # it in the Variable specified
        #
        #       ord
        #       ord.hex         output in hex
        #       ord.hex         output in octal
        #       ord.utf8        forces UTF8 decoding
        #       ord.eascii      forces eascii decoding
        #       ord.echo        prints to stdout
        function ord {
                printf -v "${1?Missing Dest Variable}" "${3:-%d}" "'${2?Missing Char}"
        }
        function ord.oct {
                ord "${@:1:2}" "0%c"
        }
        function ord.hex {
                ord "${@:1:2}" "0x%x"
        }
        function ord.utf8 {
                LC_CTYPE=en_US.UTF8 ord "${@}"
        }
        function ord.eascii {
                LC_CTYPE=C ord "${@}"
        }
        function ord.echo {
                printf "${2:-%d}" "'${1?Missing Char}"
        }
        function ord.oct.echo {
                ord.echo "${1}" "0%o"
        }
        function ord.hex.echo {
                ord.echo "${1}" "0x%x"
        }
        function ord.utf8.echo {
                LC_CTYPE=en_US.UTF8 ord.echo "${@}"
        }
        function ord.eascii.echo {
                LC_CTYPE=C ord.echo "${@}"
        }

        ###########################################################################
        ## chr family
        ###########################################################################
        # chr.utf8   <Return Variale Name> <Integer to convert>
        # chr.eascii <Return Variale Name> <Integer to convert>
        # chr        <Return Variale Name> <Integer to convert>
        # chr.oct    <Return Variale Name> <Octal number to convert>
        # chr.hex    <Return Variale Name> <Hex number to convert>
        # chr.utf8.echo                  <Integer to convert>
        # chr.eascii.echo                <Integer to convert>
        # chr.echo                       <Integer to convert>
        # chr.oct.echo                   <Octal number to convert>
        # chr.hex.echo                   <Hex number to convert>
        #
        # Description:
        # converts decimal value to character representation an stores
        # it in the Variable specified
        #
        #       chr                     Tries to guess output format
        #       chr.utf8                forces UTF8 encoding
        #       chr.eascii              forces eascii encoding
        #       chr.echo                prints to stdout
        #
        function chr.utf8 {
                local val
                [[ ${2?Missing Ordinal Value} -lt 0x80000000 ]] || return 1

                if [[ ${2} -lt 0x100 && ${2} -ge 0x80 ]]; then
                        # some kinda weird bash? behavior
                        # treats \Uff as \xff so encode manually
                        printf -v val "\\%o\%o" $(( (${2}>>6)|0xc0 )) $(( (${2}&0x3f)|0x80 ))
                else
                        # Note in embedded cases always do \U%08x \u04x 
                        # here however no need to because of the EOS 
                        printf -v val '\\U%x' "${2}"
                fi
                printf -v ${1?Missing Dest Variable} ${val}
        }
        function chr.eascii {
                local val
                # Make sure value less than 0x100
                # otherwise we end up with 
                # \xVVNNNNN 
                # where \xVV = char && NNNNN is a number string
                # so chr "0x44321" => "D321"
                [[ ${2?Missing Ordinal Value} -lt 0x100 ]] || return 1
                printf -v val '\\x%02x' "${2}"
                printf -v ${1?Missing Dest Variable} ${val}
        }
        function chr {
                if [ "${LC_CTYPE:-${LC_ALL:-}}" = "C" ]; then
                        chr.eascii "${@}"
                else
                        chr.utf8 "${@}"
                fi
        }
        function chr.dec {
                # strip leading 0s otherwise 
                # interpreted as Octal
                if shopt extglob &>/dev/null ;then 
                        chr "${1}" "${2/#+(0)}"
                else
                        shopt -s extglob
                        chr "${1}" "${2/#+(0)}"
                        shopt -u extglob
                fi
        }
        function chr.oct {
                chr "${1}" "0${2}"
        }
        function chr.hex {
                chr "${1}" "0x${2}"
        }
        function chr.utf8.echo {
                local val 
                [[ ${1?Missing Ordinal Value} -lt 0x80000000 ]] || return 1

                if [[ ${1} -lt 0x100 && ${1} -ge 0x80 ]]; then
                        # some kinda weird bash? behavior
                        # treats \Uff as \xff so encode manually
                        printf -v val '\\%o\\%o' $(( (${1}>>6)|0xc0 )) $(( (${1}&0x3f)|0x80 ))
                else
                        # Note in embedded cases always do \\U%08x \u04x 
                        # here however no need to because of the EOS
                        printf -v val '\\U%x' "${1}"
                fi
                printf "${val}"
        }
        function chr.eascii.echo {
                local val
                # Make sure value less than 0x100
                # otherwise we end up with 
                # \xVVNNNNN 
                # where \xVV = char && NNNNN is a number string
                # so chr "0x44321" => "D321"
                [[ ${1?Missing Ordinal Value} -lt 0x100 ]] || return 1
                printf -v val '\\x%x' "${1}"
                printf "${val}"
        }
        function chr.echo {
                if [ "${LC_CTYPE:-${LC_ALL:-}}" = "C" ]; then
                        chr.eascii.echo "${@}"
                else
                        chr.utf8.echo "${@}"
                fi
        }
        function chr.dec.echo {
                # strip leading 0s otherwise 
                # interpreted as Octal
                if shopt extglob &>/dev/null ;then 
                        chr.echo "${1/#+(0)}"
                else
                        shopt -s extglob
                        chr.echo "${1/#+(0)}"
                        shopt -u extglob
                fi
        }
        function chr.oct.echo {
                chr.echo "0${1}"
        }
        function chr.hex.echo {
                chr.echo "0x${1}"
        }
   
    # 
    # Simple Validation code
    # 
      function test_echo_func {
        local Outcome
        local _result="$( "${1}" "${2}" )"
        if [ "${_result}" = "${3}" ]; then
          Outcome="Pass"
        else
          Outcome="Fail"
        fi
        printf "# %-20s %-6s => [ "%16q" = "%-16q"%-5s ] %s\n" "${1}" "${2}" "${_result}" "${3}" "(${3//[[:cntrl:]]/_})" "${Outcome}"
      }   
      function test_value_func {
        local Outcome
        local _result
        "${1}" _result "${2}"
        if [ "${_result}" = "${3}" ]; then
          Outcome="Pass"
        else
          Outcome="Fail"
        fi
        printf "# %-20s %-6s => [ "%16q" = "%-16q"%-5s ] %s\n" "${1}" "${2}" "${_result}" "${3}" "(${3//[[:cntrl:]]/_})" "${Outcome}"
      }   
    test_echo_func chr.echo "$(ord.echo A)"    "A"
    test_echo_func ord.echo "$(chr.echo 65)"   "65"
    test_echo_func chr.echo "$(ord.echo "ö")"  "ö"
    test_value_func chr     "$(ord.echo A)"    "A"
    test_value_func ord     "$(chr.echo 65)"   "65"
    test_value_func chr     "$(ord.echo "ö")"  "ö"
# chr.echo             65     => [                A = A               (A)   ] Pass
# ord.echo             A      => [               65 = 65              (65)  ] Pass
# chr.echo             246    => [      $'\303\266' = $'\303\266'     (ö)  ] Pass
# chr                  65     => [                A = A               (A)   ] Pass
# ord                  A      => [               65 = 65              (65)  ] Pass
# chr                  246    => [      $'\303\266' = $'\303\266'     (ö)  ] Pass
#


    test_echo_func chr.echo     "65"     A
    test_echo_func chr.echo     "065"    5
    test_echo_func chr.dec.echo "065"    A
    test_echo_func chr.oct.echo "65"     5
    test_echo_func chr.hex.echo "65"     e
    test_value_func chr          "65"     A
    test_value_func chr          "065"    5
    test_value_func chr.dec      "065"    A
    test_value_func chr.oct      "65"     5
    test_value_func chr.hex      "65"     e
# chr.echo             65     => [                A = A               (A)   ] Pass
# chr.echo             065    => [                5 = 5               (5)   ] Pass
# chr.dec.echo         065    => [                A = A               (A)   ] Pass
# chr.oct.echo         65     => [                5 = 5               (5)   ] Pass
# chr.hex.echo         65     => [                e = e               (e)   ] Pass
# chr                  65     => [                A = A               (A)   ] Pass
# chr                  065    => [                5 = 5               (5)   ] Pass
# chr.dec              065    => [                A = A               (A)   ] Pass
# chr.oct              65     => [                5 = 5               (5)   ] Pass
# chr.hex              65     => [                e = e               (e)   ] Pass

    #test_value_func chr          0xff   $'\xff'    
    test_value_func chr.eascii   0xff   $'\xff'    
    test_value_func chr.utf8     0xff   $'\uff'      # Note this fails because bash encodes it wrong
    test_value_func chr.utf8     0xff   $'\303\277'    
    test_value_func chr.utf8     0x100  $'\u100'    
    test_value_func chr.utf8     0x1000 $'\u1000'   
    test_value_func chr.utf8     0xffff $'\uffff'   
# chr.eascii           0xff   => [          $'\377' = $'\377'         (�)   ] Pass
# chr.utf8             0xff   => [      $'\303\277' = $'\377'         (�)   ] Fail
# chr.utf8             0xff   => [      $'\303\277' = $'\303\277'     (ÿ)  ] Pass
# chr.utf8             0x100  => [      $'\304\200' = $'\304\200'     (Ā)  ] Pass
# chr.utf8             0x1000 => [  $'\341\200\200' = $'\341\200\200' (က) ] Pass
# chr.utf8             0xffff => [  $'\357\277\277' = $'\357\277\277' (���) ] Pass



  #########################################################
  # to help debug problems try this
  #########################################################
  printf "%q\n" $'\xff'                  # => $'\377'
  printf "%q\n" $'\uffff'                # => $'\357\277\277'
  printf "%q\n" "$(chr.utf8.echo 0x100)" # => $'\304\200'
  #
  # This can help a lot when it comes to diagnosing problems 
  # with read and or xterm program output 
  # I use it a lot in error case to create a human readable error message
  # i.e. 
  echo "Enter type to test, Enter to continue"
  while read -srN1 ; do
    ord asciiValue "${REPLY}"
    case "${asciiValue}" in
      10) echo "Goodbye" ; break ;;
      20|21|22) echo "Yay expected input" ;;
      *) printf ':( Unexpected Input 0x%02x %q "%s"\n' "${asciiValue}" "${REPLY}" "${REPLY//[[:cntrl:]]}" ;;
    esac
  done

  #########################################################
  # More exotic approach 1
  #########################################################
  # I used to use this before I figured out the LC_CTYPE=C approach
  # printf "EAsciiLookup=%q" "$(for (( x=0x0; x<0x100 ; x++)); do printf '%b' $(printf '\\x%02x' "$x"); done)"
  EAsciiLookup=$'\001\002\003\004\005\006\a\b\t\n\v\f\r\016\017\020\021\022\023\024\025\026\027\030\031\032\E\034\035\036\037 !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377'
  function ord.eascii2 {
    local idx="${EAsciiLookup%%${2:0:1}*}"
    eval ${1}'=$(( ${#idx} +1 ))'
  }

  #########################################################
  # More exotic approach 2
  #########################################################
  #printf "EAsciiLookup2=(\n    %s\n)" "$(for (( x=0x1; x<0x100 ; x++)); do printf '%-18s'  "$(printf '[_%q]="0x%02x"' "$(printf "%b" "$(printf '\\x%02x' "$x")")" $x )" ; [ "$(($x%6))" != "0" ] || echo -en "\n    " ; done)"
  typeset -A EAsciiLookup2
  EAsciiLookup2=(
    [_$'\001']="0x01" [_$'\002']="0x02" [_$'\003']="0x03" [_$'\004']="0x04" 
    [_$'\005']="0x05" [_$'\006']="0x06" [_$'\a']="0x07"   [_$'\b']="0x08"   
    [_$'\t']="0x09"   [_'']="0x0a"      [_$'\v']="0x0b"   [_$'\f']="0x0c"   
    [_$'\r']="0x0d"   [_$'\016']="0x0e" [_$'\017']="0x0f" [_$'\020']="0x10" 
    [_$'\021']="0x11" [_$'\022']="0x12" [_$'\023']="0x13" [_$'\024']="0x14" 
    [_$'\025']="0x15" [_$'\026']="0x16" [_$'\027']="0x17" [_$'\030']="0x18" 
    [_$'\031']="0x19" [_$'\032']="0x1a" [_$'\E']="0x1b"   [_$'\034']="0x1c" 
    [_$'\035']="0x1d" [_$'\036']="0x1e" [_$'\037']="0x1f" [_\ ]="0x20"      
    [_\!]="0x21"      [_\"]="0x22"      [_\#]="0x23"      [_\$]="0x24"      
    [_%]="0x25"       [_\&]="0x26"      [_\']="0x27"      [_\(]="0x28"      
    [_\)]="0x29"      [_\*]="0x2a"      [_+]="0x2b"       [_\,]="0x2c"      
    [_-]="0x2d"       [_.]="0x2e"       [_/]="0x2f"       [_0]="0x30"       
    [_1]="0x31"       [_2]="0x32"       [_3]="0x33"       [_4]="0x34"       
    [_5]="0x35"       [_6]="0x36"       [_7]="0x37"       [_8]="0x38"       
    [_9]="0x39"       [_:]="0x3a"       [_\;]="0x3b"      [_\<]="0x3c"      
    [_=]="0x3d"       [_\>]="0x3e"      [_\?]="0x3f"      [_@]="0x40"       
    [_A]="0x41"       [_B]="0x42"       [_C]="0x43"       [_D]="0x44"       
    [_E]="0x45"       [_F]="0x46"       [_G]="0x47"       [_H]="0x48"       
    [_I]="0x49"       [_J]="0x4a"       [_K]="0x4b"       [_L]="0x4c"       
    [_M]="0x4d"       [_N]="0x4e"       [_O]="0x4f"       [_P]="0x50"       
    [_Q]="0x51"       [_R]="0x52"       [_S]="0x53"       [_T]="0x54"       
    [_U]="0x55"       [_V]="0x56"       [_W]="0x57"       [_X]="0x58"       
    [_Y]="0x59"       [_Z]="0x5a"       [_\[]="0x5b"      #[_\\]="0x5c"      
    #[_\]]="0x5d"      
                      [_\^]="0x5e"      [__]="0x5f"       [_\`]="0x60"      
    [_a]="0x61"       [_b]="0x62"       [_c]="0x63"       [_d]="0x64"       
    [_e]="0x65"       [_f]="0x66"       [_g]="0x67"       [_h]="0x68"       
    [_i]="0x69"       [_j]="0x6a"       [_k]="0x6b"       [_l]="0x6c"       
    [_m]="0x6d"       [_n]="0x6e"       [_o]="0x6f"       [_p]="0x70"       
    [_q]="0x71"       [_r]="0x72"       [_s]="0x73"       [_t]="0x74"       
    [_u]="0x75"       [_v]="0x76"       [_w]="0x77"       [_x]="0x78"       
    [_y]="0x79"       [_z]="0x7a"       [_\{]="0x7b"      [_\|]="0x7c"      
    [_\}]="0x7d"      [_~]="0x7e"       [_$'\177']="0x7f" [_$'\200']="0x80" 
    [_$'\201']="0x81" [_$'\202']="0x82" [_$'\203']="0x83" [_$'\204']="0x84" 
    [_$'\205']="0x85" [_$'\206']="0x86" [_$'\207']="0x87" [_$'\210']="0x88" 
    [_$'\211']="0x89" [_$'\212']="0x8a" [_$'\213']="0x8b" [_$'\214']="0x8c" 
    [_$'\215']="0x8d" [_$'\216']="0x8e" [_$'\217']="0x8f" [_$'\220']="0x90" 
    [_$'\221']="0x91" [_$'\222']="0x92" [_$'\223']="0x93" [_$'\224']="0x94" 
    [_$'\225']="0x95" [_$'\226']="0x96" [_$'\227']="0x97" [_$'\230']="0x98" 
    [_$'\231']="0x99" [_$'\232']="0x9a" [_$'\233']="0x9b" [_$'\234']="0x9c" 
    [_$'\235']="0x9d" [_$'\236']="0x9e" [_$'\237']="0x9f" [_$'\240']="0xa0" 
    [_$'\241']="0xa1" [_$'\242']="0xa2" [_$'\243']="0xa3" [_$'\244']="0xa4" 
    [_$'\245']="0xa5" [_$'\246']="0xa6" [_$'\247']="0xa7" [_$'\250']="0xa8" 
    [_$'\251']="0xa9" [_$'\252']="0xaa" [_$'\253']="0xab" [_$'\254']="0xac" 
    [_$'\255']="0xad" [_$'\256']="0xae" [_$'\257']="0xaf" [_$'\260']="0xb0" 
    [_$'\261']="0xb1" [_$'\262']="0xb2" [_$'\263']="0xb3" [_$'\264']="0xb4" 
    [_$'\265']="0xb5" [_$'\266']="0xb6" [_$'\267']="0xb7" [_$'\270']="0xb8" 
    [_$'\271']="0xb9" [_$'\272']="0xba" [_$'\273']="0xbb" [_$'\274']="0xbc" 
    [_$'\275']="0xbd" [_$'\276']="0xbe" [_$'\277']="0xbf" [_$'\300']="0xc0" 
    [_$'\301']="0xc1" [_$'\302']="0xc2" [_$'\303']="0xc3" [_$'\304']="0xc4" 
    [_$'\305']="0xc5" [_$'\306']="0xc6" [_$'\307']="0xc7" [_$'\310']="0xc8" 
    [_$'\311']="0xc9" [_$'\312']="0xca" [_$'\313']="0xcb" [_$'\314']="0xcc" 
    [_$'\315']="0xcd" [_$'\316']="0xce" [_$'\317']="0xcf" [_$'\320']="0xd0" 
    [_$'\321']="0xd1" [_$'\322']="0xd2" [_$'\323']="0xd3" [_$'\324']="0xd4" 
    [_$'\325']="0xd5" [_$'\326']="0xd6" [_$'\327']="0xd7" [_$'\330']="0xd8" 
    [_$'\331']="0xd9" [_$'\332']="0xda" [_$'\333']="0xdb" [_$'\334']="0xdc" 
    [_$'\335']="0xdd" [_$'\336']="0xde" [_$'\337']="0xdf" [_$'\340']="0xe0" 
    [_$'\341']="0xe1" [_$'\342']="0xe2" [_$'\343']="0xe3" [_$'\344']="0xe4" 
    [_$'\345']="0xe5" [_$'\346']="0xe6" [_$'\347']="0xe7" [_$'\350']="0xe8" 
    [_$'\351']="0xe9" [_$'\352']="0xea" [_$'\353']="0xeb" [_$'\354']="0xec" 
    [_$'\355']="0xed" [_$'\356']="0xee" [_$'\357']="0xef" [_$'\360']="0xf0" 
    [_$'\361']="0xf1" [_$'\362']="0xf2" [_$'\363']="0xf3" [_$'\364']="0xf4" 
    [_$'\365']="0xf5" [_$'\366']="0xf6" [_$'\367']="0xf7" [_$'\370']="0xf8" 
    [_$'\371']="0xf9" [_$'\372']="0xfa" [_$'\373']="0xfb" [_$'\374']="0xfc" 
    [_$'\375']="0xfd" [_$'\376']="0xfe" [_$'\377']="0xff" 
  )
  function ord.eascii3 {
        local -i val="${EAsciiLookup2["_${2:0:1}"]-}"
        if [ "${val}" -eq 0 ]; then
                case "${2:0:1}" in 
                        ])  val=0x5d ;;
                        \\) val=0x5c ;;
                esac
        fi
        eval "${1}"'="${val}"'
  }
  # for fun check out the following
  time for (( i=0 ; i <1000; i++ )); do ord TmpVar 'a'; done   
  #  real 0m0.065s
  #  user 0m0.048s
  #  sys  0m0.000s

  time for (( i=0 ; i <1000; i++ )); do ord.eascii TmpVar 'a'; done   
  #  real 0m0.239s
  #  user 0m0.188s
  #  sys  0m0.000s

  time for (( i=0 ; i <1000; i++ )); do ord.eascii2 TmpVar 'a'; done   
  #  real 0m1.507s
  #  user 0m1.056s
  #  sys  0m0.012s

  time for (( i=0 ; i <1000; i++ )); do ord.eascii3 TmpVar 'a'; done      
  #  real 0m0.147s
  #  user 0m0.120s
  #  sys  0m0.000s

Here are some older, simpler functions that do similar things:

# POSIX
# chr() - converts decimal value to its ASCII character representation
# ord() - converts ASCII character to its decimal value

chr() {
  [ ${1} -lt 256 ] || return 1
  printf \\$(printf '%03o' $1)
}
  
# Another version doing the octal conversion with arithmetic 
# faster as it avoids a subshell
chr () {
  [ ${1} -lt 256 ] || return 1
  printf \\$(($1/64*100+$1%64/8*10+$1%8))
}

# Another version using a temporary variable to avoid subshell.
# This one requires bash 3.1.
chr() {
  local tmp
  [ ${1} -lt 256 ] || return 1
  printf -v tmp '%03o' "$1"
  printf \\"$tmp"
}

ord() {
  printf '%d' "'$1"
}

# hex() - converts ASCII character to a hexadecimal value
# unhex() - converts a hexadecimal value to an ASCII character

hex() {
   printf '%x' "'$1"
}

unhex() {
   printf \\x"$1"
}

# examples:

chr $(ord A)    # -> A
ord $(chr 65)   # -> 65

The ord function above is quite tricky.

  • Tricky? Rather, it's using a feature that I can't find documented anywhere -- putting a single quote in front of an integer. Neat effect, but how on earth did you find out about it? Source diving? -- GreyCat

    • It validates The Single Unix Specification: "If the leading character is a single-quote or double-quote, the value shall be the numeric value in the underlying codeset of the character following the single-quote or double-quote." (see printf() to know more) -- mjf

    $'\357\277\277'
    • printf "%q\n" "$(chr.utf8.echo 0x100)" # =

BashFAQ/071 (last edited 2021-02-08 16:03:51 by GreyCat)