diff --git a/unicodedomino.sty b/unicodedomino.sty
index 0c7d25571678ecb3f094efb2d843fcacf42d5fc0..d9aa05ef8b6daf190ff72bdd9d1449be0d885542 100644
--- a/unicodedomino.sty
+++ b/unicodedomino.sty
@@ -40,102 +40,15 @@
\ifx\decode@UTFviii\@undefined%
\PackageError{unicodedomino}%
{Your utf8.def is too old, consider updating it}%
- {You will need Debian stretch or newer}%
+ {You will need v1.1o 2015/08/28, Debian stretch or newer}%
\fi%
% pull code from other files
\input{unicodedomino_kernel_fixup.def}%
+\input{unicodedomino_kernel_cosmetics.def}%
+\input{unicodedomino_compat.def}%
-% nicer printing of codepoint hex numbers, not strictly necessary
-\def\unicodedomino@codepoint#1{%
- \ifnum#1>1048575%
- U-00%
- \else\ifnum#1>65535%
- U-000%
- \else\ifnum#1>4095%
- U+%
- \else\ifnum#1>255%
- U+0%
- \else\ifnum#1>15%
- U+00%
- \else%
- U+000%
- \fi\fi\fi\fi\fi%
- \expandafter\UTFviii@hexnumber\expandafter{#1}%
-}%
-
-% same for bytes
-\def\unicodedomino@bytehex#1{%
- \expandafter\UTFviii@hexdigit\expandafter{\the\numexpr(#1-8)/16\relax}%
- \UTFviii@hexdigit{\numexpr#1\ifnum#1>0-((#1-8)/16)*16\fi\relax}%
-}%
-
-% override to beautify the output, not strictly necessary but requested
-\gdef\UTFviii@splitcsname#1:#2\relax{%
- #2 (\expandafter\unicodedomino@codepoint\expandafter{%
- \the\numexpr\decode@UTFviii#2\relax})%
-}%
-\def\UTFviii@invalid@err#1{%
- \PackageError{inputenc}{%
- Invalid UTF-8 byte 0x\unicodedomino@bytehex{\number`#1}%
- }\UTFviii@invalid@help%
-}%
-
-% for invalid encoding output
-\gdef\unicodedomino@splith@x#1#2\relax{%
- \space 0x\UTFviii@hexnumber{`#1}%
- \ifx\relax#2\relax\else\unicodedomino@splith@x#2\relax\fi%
-}%
-\gdef\unicodedomino@splithex#1:#2\relax{%
- \unicodedomino@splith@x#2\relax%
-}%
-
-% render the actual domino piece
-\def\unicodedomino@box#1#2{%
- \begingroup%
- \fboxsep=.1em%
- \fboxrule=.4pt%
- \texttt{\fbox{\makebox[0pt][l]{\textsuperscript{#1}}\textsubscript{#2}}}%
- \endgroup%
-}%
-
-% expand one hex nybble
-\def\unicodedomino@hex@ne#1{%
- \ifnum#1>15 %
- \expandafter\unicodedomino@hex@ne\expandafter{\the\numexpr(#1-8)/16\relax}%
- \fi%
- \UTFviii@hexdigit{\numexpr#1\ifnum#1>0-((#1-8)/16)*16\fi\relax}.%
-}%
-% expand all hex nybbles, zero-padded
-\def\unicodedomino@hex@ll#1{%
- \ifnum#1<1048576 0.\fi%
- \ifnum#1<65536 0.\fi%
- \ifnum#1<4096 0.\fi%
- \ifnum#1<256 0.\fi%
- \ifnum#1<16 0.\fi%
- \expandafter\unicodedomino@hex@ne\expandafter{#1}%
-}%
-% call the appropriate box function
-\def\unicodedomino@hex@do#1.#2.#3.#4.#5.#6.{%
- \ifnum"#1#2=0%
- \unicodedomino@box{#3#4}{#5#6}%
- \else%
- \unicodedomino@box{#1#2#3}{#4#5#6}%
- \fi%
-}%
-% split nybbles and pass on
-\protected\def\unicodedomino@hex#1{%
- \edef\unicodedomino@tmp{\expandafter\unicodedomino@hex@ll\expandafter{#1}}%
- \expandafter\unicodedomino@hex@do\unicodedomino@tmp\relax%
-}%
-% split, decode and pass on
-\def\unicodedomino@decode#1:#2\relax{%
- \expandafter\unicodedomino@hex\expandafter{%
- \the\numexpr\decode@UTFviii#2\relax%
- }%
-}%
-
-% retrieve the last octet (lstlistings compatibility)
+% retrieve the last octet
\def\unicodedomino@last#1{%
\expandafter\unicodedomino@l@st#1\empty\empty\empty%
}%
@@ -147,12 +60,7 @@
\fi%
}%
-% handle trimmed octets
-\def\unicodedomino@octets#1\empty{%
- \expandafter\UTFviii@defined\csname u8:#1\endcsname%
-}%
-
-% collect octet tokens, trim them, pass on to handler
+% collect octet tokens, trim them and pass them on to handler
\long\def\UTFviii@two@octets#1#2{%
\edef\unicodedomino@tmp{#1\unicodedomino@last{\string#2}}%
\expandafter\unicodedomino@octets\unicodedomino@tmp\empty%
@@ -166,38 +74,79 @@
\expandafter\unicodedomino@octets\unicodedomino@tmp\empty%
}%
+% handle trimmed octets
+\def\unicodedomino@octets#1\empty{%
+ \expandafter\UTFviii@defined\csname u8:#1\endcsname%
+}%
+
% main handler
\def\UTFviii@defined#1{%
\ifx#1\relax%
\if\relax\expandafter\UTFviii@checkseq\string#1\empty\relax%
- % unknown char
+ % unknown character but valid codepoint
\ifx\protect\@typeset@protect%
- % not protected
+ % not protected, replace by domino
\PackageWarning{inputenc}{%
- Unicode\space char\space\expandafter\UTFviii@splitcsname\string#1\relax%
- \space not\space set\space up\space for\space use\MessageBreak with\space%
- LaTeX, replacing%
+ Unicode character \expandafter\UTFviii@splitcsname\string#1\relax\space%
+ not set up for use\MessageBreak with LaTeX, replacing%
}%
- % note: same warning as in \UTFviii@undefined@err in utf8.def v1.2c,
- % except adding “, replacing†at the end and not being an error
- \expandafter\unicodedomino@decode\string#1\relax%
+ % note: warning is the same as in utf8ienc.dtx v1.2d except
+ % with the string “, replacing†added at the end
+ \expandafter\unicodedomino@domino\string#1\relax%
\else%
% protected, just write the original character
\expandafter\@gobblefour\string#1%
\fi%
\else%
- % invalid encoding
- \PackageError{inputenc}{%
- Invalid\space UTF-8\space byte\space sequence:%
- \expandafter\unicodedomino@splithex\string#1\relax%
- }{Do ensure the source document is saved in UTF-8 encoding}%
+ \PackageError{inputenc}{Invalid UTF-8 byte sequence:%
+ \expandafter\UTFviii@splitseq\string#1\relax}%
+ \UTFviii@invalid@help
\fi%
\else%
- % known char, expand
+ % known character, expand
+ %XXX perhaps do not expand it when protected?
\expandafter#1%
\fi%
}%
+% prepare for outputting the domino block
+\def\unicodedomino@domino#1:#2\relax{%
+ \edef\unicodedomino@tmp{%
+ \expandafter\unicodedomino@domino@hex\expandafter{%
+ \the\numexpr\decode@UTFviii#2\relax%
+ }%
+ }%
+ \expandafter\unicodedomino@domino@switch\unicodedomino@tmp%
+}%
+
+% convert to six nybbles
+\def\unicodedomino@domino@hex#1{%
+ \ifnum#1<1048576 0\fi%
+ \ifnum#1<65536 0\fi%
+ \ifnum#1<4096 0\fi%
+ \ifnum#1<256 0\fi%
+ \ifnum#1<16 0\fi%
+ \UTFviii@hexnumber{#1}%
+}%
+
+% decide whether to output a BMP or astral planes block
+\def\unicodedomino@domino@switch#1#2#3#4#5#6{%
+ \ifnum"#1#2=0%
+ \unicodedomino@box{#3#4}{#5#6}%
+ \else%
+ \unicodedomino@box{#1#2#3}{#4#5#6}%
+ \fi%
+}%
+
+% render the actual domino piece
+\def\unicodedomino@box#1#2{%
+ \begingroup%
+ \fboxsep=.1em%
+ \fboxrule=.4pt%
+ \texttt{\fbox{\makebox[0pt][l]{\textsuperscript{#1}}\textsubscript{#2}}}%
+ \endgroup%
+}%
+
% clean up after ourselves
\makeatother%
\endinput
diff --git a/unicodedomino_compat.def b/unicodedomino_compat.def
new file mode 100644
index 0000000000000000000000000000000000000000..1beff1822af6182268e72ef00ad05b7aa62aafe9
--- /dev/null
+++ b/unicodedomino_compat.def
@@ -0,0 +1,27 @@
+% -*- mode: tex -*-
+%-
+% Copyright © 2018
+% mirabilos <m@mirbsd.org>
+%
+% 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 unâ€
+% 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.
+%-
+% Compatibility code with older utf8.def versions
+
+\ifx\UTFviii@invalid@help\@undefined%
+ \def\UTFviii@invalid@help{%
+ Do ensure the source document is saved in UTF-8 encoding%
+ }%
+\fi%
diff --git a/unicodedomino_kernel_cosmetics.def b/unicodedomino_kernel_cosmetics.def
new file mode 100644
index 0000000000000000000000000000000000000000..5928c0658372b9702ee8a43f233bc6bb88c64e0b
--- /dev/null
+++ b/unicodedomino_kernel_cosmetics.def
@@ -0,0 +1,70 @@
+% -*- mode: tex -*-
+%-
+% Copyright © 2017, 2018
+% mirabilos <m@mirbsd.org>
+%
+% 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 unâ€
+% 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.
+%-
+% Improve error and warning formatting.
+
+% format a number as two-digit hex
+\ifx\UTFviii@hexbyte\@undefined%
+ \def\UTFviii@hexbyte#1{%
+ \ifnum#1<16 0\fi%
+ \UTFviii@hexnumber{#1}%
+ }%
+\fi%
+
+% format a number as Unicode codepoint hex
+\ifx\UTFviii@hexcodepoint\@undefined%
+ \def\UTFviii@hexcodepoint#1{%
+ \ifnum#1<16 U+000%
+ \else\ifnum#1<256 U+00%
+ \else\ifnum#1<4096 U+0%
+ \else\ifnum#1<65536 U+%
+ \else\ifnum#1<1048576 U-000%
+ \else U-00%
+ \fi\fi\fi\fi\fi%
+ \UTFviii@hexnumber{#1}%
+ }%
+\fi%
+
+% split an invalid byte sequence for output
+\ifx\UTFviii@splitseq\@undefined%
+ \gdef\UTFviii@splitseq#1:#2\relax{%
+ \UTFviii@hexseq#2\relax%
+ }%
+ \gdef\UTFviii@hexseq#1#2\relax{%
+ % display first octet
+ \space 0x\UTFviii@hexbyte{`#1}%
+ % recursively handle remaining octets
+ \ifx\relax#2\relax\else\UTFviii@hexseq#2\relax\fi%
+ }%
+\fi%
+
+% override message to give the byte in hex
+\def\UTFviii@invalid@err#1{%
+ \PackageError{inputenc}{Invalid UTF-8 byte 0x\UTFviii@hexbyte{`#1}}%
+ \UTFviii@invalid@help%
+}%
+
+% override message to format the codepoint correctly
+\gdef\UTFviii@splitcsname#1:#2\relax{%
+ #2 (\expandafter\UTFviii@hexcodepoint\expandafter{%
+ \the\numexpr\decode@UTFviii#2\relax})%
+}%