#!/bin/sh
# SPDX-License-Identifier: MIT
# Copyright (c) 2025 Julian Prein
#
# Remove ANSI escape sequences.
#
# Additionally to the general form `\e[ -/]*[0-~]` this also tries to cover
# sequences that are followed by additional bytes (e.g. CSI, OSC). This script
# covers no C1 sequences.
#
# The patterns cover the following escape sequences (from top to bottom):
# - CSI
# - OSC, DCS, PM & APC
# - SOS
# - All remaining sequences
#
# See:
# - https://en.wikipedia.org/wiki/ANSI_escape_code
# - https://www.ecma-international.org/wp-content/uploads/ECMA-35_6th_edition_december_1994.pdf
# - https://www.ecma-international.org/wp-content/uploads/ECMA-48_5th_edition_june_1991.pdf

env LC_ALL=C sed -E "$(printf "%b" \
	's/' \
	'\033\\[[0-?]*[ -/]*[@-~]' '|' \
	'\033[]P^_][\010-\015 -~]*\033\\\\' '|' \
	'\033X([^\033]|\033+[^\033X\\])*\033+\\\\' '|' \
	'\033[ -/]*[0-~]' \
	'//g')"