Differences between revisions 21 and 22
⇤ ← Revision 21 as of 2012-01-07 02:00:28 →
Size: 7360
Editor: GreyCat
Comment: restore old content (down below new content), and warn about new content
← Revision 22 as of 2012-01-07 23:47:41 → ⇥
Size: 8817
Editor: dethrophes
Comment: Added input limit checks on the chr functions. Added alternative option for inlining escape sequences, Added some example code for helping debug problems.
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 $'' strings are escaped before evaluation and can be embedded directly in code.
Line 82: Line 87:
  ord.echo "${@:1:1}" "%o"   ord.echo "${1}" "%o"
Line 85: Line 90:
  ord.echo "${@:1:1}" "%x"   ord.echo "${1}" "%x"
Line 119: Line 124:
  # 0x7FFFFFFF=2147483647
  [ ${1} -lt 2147483648 ] || return 1
Line 124: Line 131:
  [ ${1} -lt 0x100 ] || return 1   # 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} -lt 256 ] || return 1
Line 149: Line 161:
  printf -v ${val} "%08x" "${1?Missing Value}"
  printf \\U${val}		   # 0x7FFFFFFF=2147483647
  [ ${1} -lt 2147483648 ] || return 1
 printf -v ${val} '\\U%08x' "${1?Missing Value}"
  printf ${val}
Line 154: Line 168:
  printf -v ${val} "%02x" "${1?Missing Value}"   # 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} -lt 256 ] || return 1
  printf -v ${val} '\\x%02x' "${1?Missing Value}"
Line 176: Line 196:
   chr.echo $(ord.echo A) # -> A
   ord.echo $(chr.echo 65) # -> 65		    chr.echo "$(ord.echo A)" # -> A
   ord.echo "$(chr.echo 65)" # -> 65

  # 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)" # => $'\304\200'
  #
  # This can help a lot when it comes to diagnosing problems
  # with read and or xterm program output
  # I use it a lot in error case to create a human readable error message
  # i.e.
  while read -srN1 ; do
    ord asciiValue "${REPLY}"
    case "${asciiValue}" in
      20|21|22) echo "Yay expected input" ;;
      *) printf ':( Unexpected Input 0x%02x %q "%s"' "${asciiValue}" "${REPLY}" "${REPLY//[[:cntrl:]]}"
  done
Line 188: Line 224:
  [ ${1} -lt 256 ] || return 1
Line 194: Line 231:
 printf \\$(($1/64*100+$1%64/8*10+$1%8))   [ ${1} -lt 256 ] || return 1
  printf \\$(($1/64*100+$1%64/8*10+$1%8))
Line 201: Line 239:
  [ ${1} -lt 256 ] || return 1

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 - 0x00 conflict between UTF-8 & ExtAscii
        # 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}" "%c"
        }
        function ord.hex {
                ord "${@:1:2}" "%x"
        }
        function ord.utf8 {
                LC_CTYPE=en_US.UTF8 ord "${@}"
        }
        function ord.eascii {
                LC_CTYPE=C ord "${@}"
        }
        function ord.echo {
                printf "${2:-%d}" "'${1?Missing Char}"
        }
        function ord.oct.echo {
                ord.echo "${1}" "%o"
        }
        function ord.hex.echo {
                ord.echo "${1}" "%x"
        }
        function ord.utf8.echo {
                LC_CTYPE=en_US.UTF8 ord.echo "${@}"
        }
        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
                # 0x7FFFFFFF=2147483647
                [ ${1} -lt 2147483648 ] || return 1
                printf -v ${val} '\\U%08x' "${2?Missing Value}"
                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"
                [ ${1} -lt 256 ] || return 1
                printf -v ${val} '\\x%02x' "${2?Missing Value}"
                printf -v ${1?Missing Dest Variable} ${val}
        }
        function chr {
                if [ ${1} -lt 0x80 ]; then
                        chr.eascii "${@}"
                elif [ ${1} -lt 0x100 ]; then
                        if [ "${LC_CTYPE:-${LC_ALL:-}}" = "C" ]; then
                                chr.eascii "${@}"
                        else
                                chr.utf8 "${@}"
                        fi
                else
                        chr.utf8 "${@}"
                fi
        }
        function chr.oct {
                chr "${1}" "0${2}"
        }
        function chr.hex {
                chr "${1}" "0x${2}"
        }
        function chr.utf8.echo {
                local val
                # 0x7FFFFFFF=2147483647
                [ ${1} -lt 2147483648 ] || return 1
                printf -v ${val} '\\U%08x' "${1?Missing Value}"
                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} -lt 256 ] || return 1
                printf -v ${val} '\\x%02x' "${1?Missing Value}"
                printf \\x${val}
        }
        function chr.echo {
                if [ ${1} -lt 0x80 ]; then
                        chr.eascii.echo "${@}"
                elif [ ${1} -lt 0x100 ]; then
                        if [ "${LC_CTYPE:-${LC_ALL:-}}" = "C" ]; then
                                chr.eascii.echo "${@}"
                        else
                                chr.utf8.echo "${@}"
                        fi
                else
                        chr.utf8.echo "${@}"
                fi
        }
        function chr.oct.echo {
                chr.echo "${1}" "0${2}"
        }
        function chr.hex.echo {
                chr.echo "${1}" "0x${2}"
        }
   chr.echo "$(ord.echo A)"    # -> A
   ord.echo "$(chr.echo 65)"   # -> 65

  # 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)" # => $'\304\200'
  #
  # This can help a lot when it comes to diagnosing problems 
  # with read and or xterm program output 
  # I use it a lot in error case to create a human readable error message
  # i.e. 
  while read -srN1 ; do
    ord asciiValue "${REPLY}"
    case "${asciiValue}" in
      20|21|22) echo "Yay expected input" ;;
      *) printf ':( Unexpected Input 0x%02x %q "%s"' "${asciiValue}" "${REPLY}" "${REPLY//[[:cntrl:]]}"
  done

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

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