implement safer UTF-8 decoder, including system override hook

unicodedomino.sty

@@ -47,6 +47,9 @@
 \ifx\UTFviii@check@three\@undefined%
  \input{unicodedomino_kernel_fixup_f4_and_checkseq.def}%
 \fi%
+\ifx\UTFviii@decode\@undefined%
+ \input{unicodedomino_kernel_better_decode.def}%
+\fi%
 \input{unicodedomino_kernel_cosmetics.def}%
 \input{unicodedomino_compat.def}%
 

unicodedomino_kernel_better_decode.def

+% -*- mode: tex -*-
+%-
+% Copyright © 2018
+%	mirabilos <t.glaser@tarent.de>
+%
+% Provided that these terms and disclaimer and all copyright notices
+% are retained or reproduced in an accompanying document, permission
+% is granted to deal in this work without restriction, including un‐
+% limited rights to use, publicly perform, distribute, sell, modify,
+% merge, give away, or sublicence.
+%
+% This work is provided “AS IS” and WITHOUT WARRANTY of any kind, to
+% the utmost extent permitted by applicable law, neither express nor
+% implied; without malicious intent or gross negligence. In no event
+% may a licensor, author or contributor be held liable for indirect,
+% direct, other damage, loss, or other issues arising in any way out
+% of dealing in the work, even if advised of the possibility of such
+% damage or existence of a defect, except proven that it results out
+% of said person’s immediate fault when using the work as intended.
+%
+% This file is dual-licenced under the LPPL version 1.3c or later.
+%-
+% Improved Unicode decoding using the fixed-up checkseq code.
+
+% override stock function, calling safer decode below
+\gdef\decode@UTFviii#1\relax{%
+ \the\numexpr(\UTFviii@decode0:#1\relax)%
+}%
+
+% safer decode, returns 0x1FFFFF for illegal sequences
+\gdef\UTFviii@decode#1\relax{%
+ \if\relax\expandafter\UTFviii@checkseq\string#1\empty\relax%
+  \UTFviii@dec@lead#1\relax%
+ \else%
+  2097151%
+ \fi%
+}%
+
+\gdef\UTFviii@dec@lead#1:#2#3\relax{%
+ % we know #2 is in 00..7F, C2..F4
+ \ifnum`#2<"80 %
+  `#2%
+ \else%
+  \ifnum`#2<"E0 %
+   (`#2-"C0%
+  \else%
+   \ifnum`#2<"F0 %
+    ((`#2-"E0%
+   \else%
+    (((`#2-"F0%
+   \fi%
+  \fi%
+  \UTFviii@dec@trail#3\relax%
+ \fi%
+}%
+
+\gdef\UTFviii@dec@trail#1#2\relax{%
+ )*64+(`#1-"80)%
+ \ifx\relax#2\else\UTFviii@dec@trail#2\relax\fi%
+}%