Simple Email Validator in Bash

email_validator_regex.sh

#!/usr/bin/env bash

#
# RFC standard of the email address could be found in rfc5322, rfc6854, etc.
#
# however, it is hard to escape all the special characters in the bash
# so, in this script, it will only check for the address syntax only
# having some valid/invalid inputs to test its result
#
# please be noted that, it is not design to detect mailbox deliverability
#

regex="^(([A-Za-z0-9]+((\.|\-|\_|\+)?[A-Za-z0-9]?)*[A-Za-z0-9]+)|[A-Za-z0-9]+)@(([A-Za-z0-9]+)+((\.|\-|\_)?([A-Za-z0-9]+)+)*)+\.([A-Za-z]{2,})+$"

valid_inputs=(
  "v@example.com"
  "v@e.com"
  "v@e.me"
  "valid@123.com"
  "valid@example.com"
  "valid+1@example.com"
  "valid+1@ex.ample.com"
  "valid+1@ex-ample.com"
  "valid+1@ex_ample.com"
  "valid+01@example.com"
  "valid+01@ex.ample.com"
  "valid+01@ex-ample.com"
  "valid+01@ex_ample.com"
  "vali.d@example.com"
  "va-lid@example.com"
  "v-a-l-i-d@example.com"
  "v.a-lid@example.com"
  "v.ali-d@example.com"
  "v_ali-d@example.com"
  "va_li-d@example.com"
  "v_a_li_d@example.com"
  "v.ali-d@example.com"
  "v.ali.d@example.com"
  "v0.ali.d@example.com"
  "v0.ali.d1@example.com"
  "valid@e-x_ample.com"
  "valid@e.x-ample.c.om"
  "valid+alias@example.com"
  "valid+1+alias@example.com"
  "valid+alias+user@example.com"
  "valid+xyz+alias@example.com"
  "valid01@example.com"
  "valid-01@example.com"
  "valid_01@example.com"
  "valid.01@example.com"
  "va-lid-0-1@example.com"
  "va.lid-0-1@example.com"
  "val-id.0-1@example.com"
  "0.vali.d@example.com"
  "0.vali.1@example.com"
  "valid++alias@example.com"
  "valid..alias@example.com"
  "valid--alias@example.com"
  "valid__alias@example.com"
  "v.-alid@example.com"
  "v-.-alid@example.com"
  "vali-.-d@example.com"
  "val..id@example.com"
  "va--lid@example.com"
  "val_-id@example.com"
  "val-.id@example.com"
  "valid..2020@example.com"
  "valid__2020@example.com"
  "valid+-2020@example.com"
)

invalid_inputs=(
  "invalid-@example.com"
  "invalid.@example.com"
  "invalid_@example.com"
  "invalid+@example.com"
  "-invalid@example.com"
  ".invalid@example.com"
  "_invalid@example.com"
  "+invalid@example.com"
  "inv alid@example.com"
  "invalid@exa mple.com"
  "invalid@e.xample.c.o"
  "invalid@_"
  "invalid@com"
  "invalid@example.c-.om"
  "invalid@example._com"
  "invalid@e-x._ample.com"
  "invalid@e-.x_ample.com"
  "invalid@e.-x_ample.com"
  "invalid@example.c"
  "invalid@example._"
  "invalid@example.-"
  "invalid@example.+"
  "invalid@exampl.0e"
  "invalid@exampl.e1"
  "invalid@exampl.1"
  "invalid@example."
  "invalid@example.com."
  "+alias@example.com"
  "invalid@-.com"
  "invalid@_.com"
  "invalid@.com"
  "invalid@com"
  "invalid@.com"
  "invalid@+com"
  "invalid@-com"
  "invalid@_com"
  "invalid@."
  "invalid@_"
  "invalid@-"
  "invalid@...com"
  "@"
  ".@."
  "-@-"
  "_@_"
  "+@+"
  "a.@.."
  "@com"
  "@example.com"
  "_@example.com"
  ".@example.com"
  "invalid@_123.com"
  "invalid@example.123"
  "invalid@example.123.456"
)

function validator {
  if [[ $1 =~ ${regex} ]]; then
    printf "* %-48s \e[1;32m[pass]\e[m\n" "${1}"
  else
    printf "* %-48s \e[1;31m[fail]\e[m\n" "${1}"
  fi
}

cat <<-EOF
a simple email address validator in bash

online validator: http://emailregex.com/

RFC Standards for email address
- https://tools.ietf.org/html/rfc821
- https://tools.ietf.org/html/rfc5322
- https://tools.ietf.org/html/rfc6854
- https://tools.ietf.org/html/rfc5321
- https://tools.ietf.org/html/rfc5322#section-3.4

References:
- http://emailregex.com/email-validation-summary/
EOF

echo
echo "### expected result: valid"
echo

for input in "${valid_inputs[@]}"; do
  validator "${input}"
done

echo
echo "### expected result: invalid"
echo

for input in "${invalid_inputs[@]}"; do
  validator "${input}"
done

@guessi according to this, you can have a valid email address with multiple @ characters in it.

@phpmoli interesting fact, but I'd prefer not to change this script for now. for the normal use case, we don't use multiple "@" in email address?

anyway, thanks for let me know 👍

Hey guys this is nice code :-) i find another bug :-)

He report this is wrong e-mail :-)
test@xn--db-pla.eu
test@sport.xn--dbrowa-w0a.pl
test@xn--niadek-2ib.pl

Best Regards
TaKeN

invalid@user_in_domain.com is showing up as valid.

this fixed the problem:
regex="^(([A-Za-z0-9]+((.|-|_|+)?[A-Za-z0-9]?)[A-Za-z0-9]+)|[A-Za-z0-9]+)@(([A-Za-z0-9]+)+((.|-)?([A-Za-z0-9]+)+))+.([A-Za-z]{2,})+$"