From 27791acf505cebdb72e07b545764f6a9ab7e153c Mon Sep 17 00:00:00 2001
From: Julian Prein <julian@druck.dev>
Date: Fri, 19 Sep 2025 00:51:47 +0200
Subject: [PATCH] bin:no-ansi: Correct allowed byte ranges

Correct the allowed byte ranges of the APC, DCS, OSC, PM & SOS
sequences. All but the SOS sequence allow additionally the bytes in the
range `0x8 - 0xD` and SOS may be followed by any sequence of bytes
except for SOS and ST (i.e. `\eX` & `\e\\`).

Link: https://www.ecma-international.org/wp-content/uploads/ECMA-48_5th_edition_june_1991.pdf#page=27
---
 .local/bin/no-ansi | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/.local/bin/no-ansi b/.local/bin/no-ansi
index 76cd61c..c74812b 100755
--- a/.local/bin/no-ansi
+++ b/.local/bin/no-ansi
@@ -11,13 +11,12 @@
 # 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.
+# - 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[]PX^_][ -~]*\033\\\\' '|' \
+	'\033[]P^_][\010-\015 -~]*\033\\\\' '|' \
+	'\033X([^\033]|\033+[^\033X\\])*\033+\\\\' '|' \
 	'\033[ -/]*[0-~]' \
 	'//g')"