Modify a column with awk and a bash script

You can do it all just with AWK. This sample uses Bash just to glue things together:

#!/usr/bin/env bash

set -euo pipefail

declare -r awk_program='
  $2  ~ /^[146]$/ { $2 = $2 "_PLUS" } # add suffix if it matches
  $2 !~ /^[146]$/ { $2 = ""         } # remove if it does not match
                  { print $0        } # print the modified line
'

awk -F, -vOFS=, "$awk_program" <<SAMPLE
a,1,A
b,2,B
c,3,C
d,4,D
e,5,E
f,6,F
SAMPLE

Outputs:

a,1_PLUS,A
b,,B
c,,C
d,4_PLUS,D
e,,E
f,6_PLUS,F

Using any awk:

$ awk 'BEGIN{FS=OFS=","} {$2 = (($2 ~ /^[146]$/) ? $2"_PLUS" : "")} 1' test.txt
a,1_PLUS,A
b,,B
c,,C
d,4_PLUS,D
e,,E
f,6_PLUS,F

If you WERE going to implement this as a shell script called from awk (but DO NOT DO THIS as it requires a lot more code, more complicated code, and will run orders of magnitude slower than doing it all in a single awk script as it'll spawn a subshell for every input line) as you intended then the syntax to do that robustly would be:

$ cat test.sh
#!/usr/bin/env bash

item=$1
case $item in
  1)
    loc=1_PLUS
    ;;
  4)
    loc=4_PLUS
    ;;
  6)
    loc=6_PLUS
    ;;
  *)
    loc=
    ;;
esac
printf '%s\n' "$loc"

$ awk '
    BEGIN { FS=OFS="," }
    {
        cmd = "./test.sh \047" $2 "\047"
        if ( (cmd | getline line) > 0 ) {
            $2 = line
        }
        close(cmd)
        print
    }
' test.txt
a,1_PLUS,A
b,,B
c,,C
d,4_PLUS,D
e,,E
f,6_PLUS,F

References:

1. Please read why-is-using-a-shell-loop-to-process-text-considered-bad-practice to learn some of the reasons not to do this using a shell script, and awk is not a shell so don't use it to call other tools unless there's a very specific reason to do so (which is not the case here).
2. See https://awk.freeshell.org/AllAboutGetline (or its archive if that site is unavailable) for information on why I'm calling to use getline that way though I could have just done cmd | getline $2 in this case since we want $2 unchanged if/when getline fails.
3. See Correct Bash and shell script variable capitalization for why I made your shell variables lower case.
4. The \047s (single quote escape sequences) around $2 are to ensure that $2 is quoted when passed to the shell, see https://mywiki.wooledge.org/Quotes.
5. I used printf instead of echo in the shell to ensure it'll work robustly, see why-is-printf-better-than-echo, though it's not strictly necessary given your scripts few possible output values.
6. I added a shebang at the top of the shell script to ensure which shell it runs in and to allow you to modify the shell by changing PATH, see Why is #!/usr/bin/env bash superior to #!/bin/bash?.

Using awk , check whether the second field is either 1 or 4 or 6 and if so append _PLUS to it, otherwise unset it:

$ awk 'BEGIN {FS=OFS=","}{if ($2 == "1" || $2 == "4" || $2 == "6"){$2 = $2"_PLUS"} else {$2=""}}1' file
a,1_PLUS,A
b,,B
c,,C
d,4_PLUS,D
e,,E
f,6_PLUS,F

I would harness GNU AWK for this task following way, let file.txt content be

a,1,A
b,2,B
c,3,C
d,4,D
e,5,E
f,6,F

then

awk 'BEGIN{FS=OFS=",";arr[1];arr[4];arr[6]}{$2=($2 in arr)?$2"_PLUS":"";print}' file.txt

gives output

a,1_PLUS,A
b,,B
c,,C
d,4_PLUS,D
e,,E
f,6_PLUS,F

Explanation: I inform GNU AWK to use comma as both field separator and output field separator, then I place numbers, which should be replace with number_PLUS as keys of array arr. For each line I use so-called ternary operator condition?valueiftrue:valueiffalse and check for presence of 2nd field value ($2) in keys of arrays arr, if is there I put that value concatenated with _PLUS otherwise empty string, then I print whole line.

(tested in GNU Awk 5.3.1)

Use this Perl one-liner:

perl -F',' -lane 'BEGIN { %val = map { $_ => "${_}_PLUS" } qw( 1 4 6 ); } print join ",", $F[0], $val{ $F[1] }, $F[2];' test.txt > out.txt

To modify the input file in-place, use:

perl -i.bak -F',' -lane 'BEGIN { %val = map { $_ => "${_}_PLUS" } qw( 1 4 6 ); } print join ",", $F[0], $val{ $F[1] }, $F[2];' test.txt

The Perl one-liner uses these command line flags:
-e : Tells Perl to look for code in-line, instead of in a file.
-n : Loop over the input one line at a time, assigning it to $_ by default.
-l : Strip the input line separator ("\n" on *NIX by default) before executing the code in-line, and append it when printing.
-a : Split $_ into array @F on whitespace or on the regex specified in -F option.
-F',' : Split into @F on comma, rather than on whitespace. -F implicitly sets both "-a" and "-n".
-i.bak : Edit input files in-place (overwrite the input file). Before overwriting, save a backup copy of the original file by appending to its name the extension .bak. If you want to skip writing a backup file, just use -i and skip the extension.

BEGIN { ... } : Execute the code ... before iterating over the input file.
qw( 1 4 6 ) : Array of 3 elements, same as (1, 4, 6).
%val = map { $_ => "${_}_PLUS" } qw( 1 4 6 ); : Create hash %val, with keys being 1, 4, 6, and values being "1_PLUS", "4_PLUS", "6_PLUS".
$val{ $F[1] } : Change the 2nd element of array @F (array in Perl are 0-indexed) using the hash %val, so 1 becomes 1_PLUS, etc. Note that the values for the keys not listed in %val will be undef, which in string context evaluates to an empty string.

See also:

• perldoc perlrun: how to execute the Perl interpreter: command line switches
• perldoc perlvar: Perl predefined variables

For a simple task of "find and replace", on a small quantity of data, there is no really need for an external tool. Pure bash will most likely be faster (if speed is important for you). So here is a pure bash solution for this (could be improved, even simplified, but a good enough starting point).

set -eu

# Contains the element to look for and the value
# to replace them with
declare -A DICT
DICT[1]=1_PLUS
DICT[4]=4_PLUS
DICT[6]=6_PLUS

FIELD_SEPARATOR=","

while read _line; do
    # Split the line into an array
    IFS=$FIELD_SEPARATOR read -ra _line_fields <<< "$_line"

    _field_value=${_line_fields[1]}

    # Check if the value of the line is in the dictionnary
    # :- means use empty string if not defined
    if [[ -n ${DICT[$_field_value]:-} ]]; then
        # Replace the old value with the new value
        _line_fields[1]=${DICT[$_field_value]}
    else
        _line_fields[1]=""
    fi
    # You may find a more elegant solution to print
    # the final output
    printf '%s%s%s%s%s%s\n' ${_line_fields[0]} $FIELD_SEPARATOR\
        ${_line_fields[1]} $FIELD_SEPARATOR\
        ${_line_fields[2]}
done < input.txt

$ bash test.sh
a,1_PLUS,A
b,,B
c,,C
d,4_PLUS,D
e,,E
f,6_PLUS,F