Remove uniocde symbols & emoji from a file; see hinell/dotfiles/bash-scripts for up-to date version

unicode-emoji-remove.sh

#!/usr/bin/env -S bash
# Title.......: unicode-emoji-remove.sh
# Summary.....: Unicode tool to strip emoji & icons from textual file
# Version.....: 1.0.0
# Created.....: September 18, 2023 
# Authors.....: Alex A. Davronov <[email protected]> (2023-)
# Repository..: N/A
# Description.: Strip emoji & icons from textual file
# Thanks to Marc Durdin (https://stackoverflow.com/a/67495684)
# Usage.......: Use --help
set -u # unset vars are reported as error
COMMAND_NAME=$(basename $0)
main-version(){ echo 1.0.0; }

main-help(){
	cat <<-EOL
	Usage: main [OPTIONS] [FILE]
	 
	Strip/remove emojis from given input FILE;
	use '-' (dash) to read from stdin
		
	OPTIONS:
	-i					remove emoji in place (see sed -i) 
	-v, --version		print script version
	-h, --help		print help
	EOL
}

# ----------------------------------------------------------------main
main(){
	local SED=sed
	local SED_ARGS=()
	local FILE
	test $# -eq 0 && {
		main-help
		return
	}
	while test $# -gt 0; do
		case "${1}" in
			(-v|--version)
				main-version
				return
			;;
			(-h|--help)
				main-help
				return
			;;
			(-i)
				SED_ARGS+=(-i)
				shift
			;;
			(-)
				: # Read from stdin
				break
			;;
			(*)
				if test -f "${1}";
				then
					FILE="${1}"
				else
					main-help
				fi
				break
			;;
			# switch.stub
		esac
	done;

	local emoji=("\U1f300-\U1f5ff"
		"\U1f900-\U1f9ff"
		"\U1f600-\U1f64f"
		"\U1f680-\U1f6ff"
		"\U2600-\U26ff"
		"\U2700-\U27bf"
		"\U1f1e6-\U1f1ff"
		"\U1f191-\U1f251"
		"\U1f004\U1f0cf"
		"\U1f170-\U1f171"
		"\U1f17e-\U1f17f"
		"\U1f18e\U3030\U2b50\U2b55"
		"\U2934-\U2935\U2b05-\U2b07"
		"\U2b1b-\U2b1c\U3297\U3299\U303d\U00a9\U00ae\U2122\U23f3\U24c2"
		"\U23e9-\U23ef\U25b6"
		"\U23f8-\U23fa"
	)
	
	LC_ALL=UTF-8 ${SED} ${SED_ARGS[@]} -e "s/[$(printf $emoji)]//g" $1

} # main end
main "${@}"
unset -f main

Unfortunatly it remove non-english letter too

@gyroing You are right. It's a bug for sure. 😄