From 8aa76b3ee6d3a7afd04357e11dd096ee40cea987 Mon Sep 17 00:00:00 2001
From: Julian Prein <julian@druck.dev>
Date: Thu, 18 Sep 2025 23:54:21 +0200
Subject: [PATCH] bin:no-ansi: Don't just match CSI sequences

Try to match all ANSI escape sequences, not just CSI (i.e. `\e[`) - also
the ones that are followed by additional bytes (e.g. CSI, OSC).
---
 .local/bin/no-ansi | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/.local/bin/no-ansi b/.local/bin/no-ansi
index 46f54d8..76cd61c 100755
--- a/.local/bin/no-ansi
+++ b/.local/bin/no-ansi
@@ -3,5 +3,21 @@
 # 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.
+#
+# See:
+# - https://en.wikipedia.org/wiki/ANSI_escape_code
+# - https://www.ecma-international.org/wp-content/uploads/ECMA-35_6th_edition_december_1994.pdf
+#
+# TODO: which bytes do DCS, OSC, SOS, PM & APC (second pattern) actually allow?
+#   Find some documentation, since `[ -~]` is guessed.
 
-env LC_ALL=C sed "$(printf 's/\033\\[[0-?]*[ -/]*[@-~]//g')"
+env LC_ALL=C sed -E "$(printf "%b" \
+	's/' \
+	'\033\\[[0-?]*[ -/]*[@-~]' '|' \
+	'\033[]PX^_][ -~]*\033\\\\' '|' \
+	'\033[ -/]*[0-~]' \
+	'//g')"