sanitize.sh

# 1. Put items in brackets on new lines "xxx ([email protected]" -> "xxx \[email protected]"
# 2. Get only email addresses (contains "@")
# 3. Get rid of placeholders ("*")
# 4. Remove all spaces
# 5. Convert uppercase to lowercase
# 6. Sort and remove duplicates
sanitized_input=$(sed -e 's/(/\n/g' -e 's/)//g' "$1" | grep -F '@' | grep -F -v '*' | sed 's/ //g' | tr '[:upper:]' '[:lower:]' | sort -u)

# Get all Google accounts (without the @domain part)
google_accs=$(echo "${sanitized_input}" | grep -F -i -e '@gmail.com' -e '@googlemail.com' | sed -e 's/@googlemail.com//g' -e 's/@gmail.com//g' | sort -u)

# Add @gmail.com and @googlemail.com
gmail=$(echo "${google_accs}" | sed -e 's/$/@gmail.com/')
googlemail=$(echo "${google_accs}" | sed -e 's/$/@googlemail.com/')

# Add modified Google accounts back to the input (echo weirdness because of newlines between the variables)
sanitized_input=$(echo "${sanitized_input}" && echo "${gmail}" && echo "${googlemail}")

# Sort again
sanitized_input=$(echo "${sanitized_input}" | sort -u)

echo "${sanitized_input}"