summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/source/latex/base/utf8ienc.dtx
diff options
context:
space:
mode:
Diffstat (limited to 'Master/texmf-dist/source/latex/base/utf8ienc.dtx')
-rw-r--r--Master/texmf-dist/source/latex/base/utf8ienc.dtx80
1 files changed, 57 insertions, 23 deletions
diff --git a/Master/texmf-dist/source/latex/base/utf8ienc.dtx b/Master/texmf-dist/source/latex/base/utf8ienc.dtx
index 75990d1b036..363998a8538 100644
--- a/Master/texmf-dist/source/latex/base/utf8ienc.dtx
+++ b/Master/texmf-dist/source/latex/base/utf8ienc.dtx
@@ -1,6 +1,6 @@
% \iffalse meta-comment
%
-% Copyright (C) 1993-2021
+% Copyright (C) 1993-2022
% The LaTeX Project and any individual authors listed elsewhere
% in this file.
%
@@ -190,7 +190,7 @@
% information.
%
%
-% \StopEventually{}
+% \MaybeStop{}
%
%
%
@@ -216,7 +216,7 @@
%<+ts1> \ProvidesFile{ts1enc.dfu}
%<+x2> \ProvidesFile{x2enc.dfu}
%<+all> \ProvidesFile{utf8enc.dfu}
-%<-utf8-2018> [2021/06/21 v1.2n UTF-8 support]
+%<-utf8-2018> [2022/06/07 v1.3c UTF-8 support]
% \end{macrocode}
%
% \begin{macrocode}
@@ -363,11 +363,12 @@
% \begin{macro}{\UTFviii@two@octets@noexpand}
% \begin{macro}{\UTFviii@three@octets@noexpand}
% \begin{macro}{\UTFviii@four@octets@noexpand}
+% \changes{v1.3a}{2022/02/19}{Use \cs{unexpanded} rather than \cs{noexpand} so only takes one expansion step}%
% These temporarily prevent the active chars from expanding.
% \begin{macrocode}
-\long\def\UTF@two@octets@noexpand#1#2{\noexpand#2\noexpand}
-\long\def\UTF@three@octets@noexpand#1#2#3{\noexpand#2\noexpand#3\noexpand}
-\long\def\UTF@four@octets@noexpand#1#2#3#4{\noexpand#2\noexpand#3\noexpand#4\noexpand}
+\long\def\UTF@two@octets@noexpand#1#2#3{\unexpanded{#2#3}}
+\long\def\UTF@three@octets@noexpand#1#2#3#4{\unexpanded{#2#3#4}}
+\long\def\UTF@four@octets@noexpand#1#2#3#4#5{\unexpanded{#2#3#4#5}}
% \end{macrocode}
% \end{macro}
% \end{macro}
@@ -376,11 +377,12 @@
% \begin{macro}{\UTFviii@two@octets@string}
% \begin{macro}{\UTFviii@three@octets@string}
% \begin{macro}{\UTFviii@four@octets@string}
+% \changes{v1.3a}{2022/02/19}{Use \cs{detokenize} rather than \cs{string} so only takes one expansion step}%
% And the same with \cs{string} for use in \cs{csname} constructions.
% \begin{macrocode}
-\long\def\UTF@two@octets@string#1#2{\string#2\string}
-\long\def\UTF@three@octets@string#1#2#3{\string#2\string#3\string}
-\long\def\UTF@four@octets@string#1#2#3#4{\string#2\string#3\string#4\string}
+\long\def\UTF@two@octets@string#1#2#3{\detokenize{#2#3}}
+\long\def\UTF@three@octets@string#1#2#3#4{\detokenize{#2#3#4}}
+\long\def\UTF@four@octets@string#1#2#3#4#5{\detokenize{#2#3#4#5}}
% \end{macrocode}
% \end{macro}
% \end{macro}
@@ -542,15 +544,24 @@
% |\count@| and ending at |\@tempcnta|${} - 1$, each time executing
% the code in |\UTFviii@tmp|.
%
-% All this is done in a group so that temporary catcode changes
-% etc.~vanish after everything is set up.
+% Store current settings so can restore after the loops without using a group (gh/762).
+%
+% \begin{macrocode}
+\edef\reserved@a{%
+\catcode`\noexpand\~=\the\catcode`\~\relax
+\catcode`\noexpand\"=\the\catcode`\"\relax
+\uccode`\noexpand\~=\the\uccode`\~\relax
+\count@=\the\count@\relax
+\@tempcnta=\the\@tempcnta\relax
+\let\noexpand\reserved@a\relax}
+% \end{macrocode}
%
% \begin{macrocode}
-\begingroup
\catcode`\~13
\catcode`\"12
% \end{macrocode}
%
+% \changes{v1.3a}{2022/02/19}{Use local protected definitions in the character definitions}%
% \begin{macrocode}
\def\UTFviii@loop{%
\uccode`\~\count@
@@ -566,7 +577,7 @@
% C0 controls are valid UTF-8 but defined to give the ``Character not defined error''
% They may be defined with |\DeclareUnicodeCharacter|.
% \begin{macrocode}
- \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@undefined@err{:\string~}}}
+ \def\UTFviii@tmp{\protected\edef~{\noexpand\UTFviii@undefined@err{:\string~}}}
% 0 ^^@ null
\count@"1
\@tempcnta9
@@ -588,7 +599,7 @@
% \begin{macrocode}
\count@"80
\@tempcnta"C2
- \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@invalid@err\string~}}
+ \def\UTFviii@tmp{\protected\edef~{\noexpand\UTFviii@invalid@err\string~}}
\UTFviii@loop
% \end{macrocode}
%
@@ -597,7 +608,7 @@
% \begin{macrocode}
\count@"C2
\@tempcnta"E0
- \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@two@octets\noexpand~}}
+ \def\UTFviii@tmp{\protected\edef~{\noexpand\UTFviii@two@octets\noexpand~}}
\UTFviii@loop
% \end{macrocode}
%
@@ -605,7 +616,7 @@
% \begin{macrocode}
\count@"E0
\@tempcnta"F0
- \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@three@octets\noexpand~}}
+ \def\UTFviii@tmp{\protected\edef~{\noexpand\UTFviii@three@octets\noexpand~}}
\UTFviii@loop
% \end{macrocode}
%
@@ -614,7 +625,7 @@
% \begin{macrocode}
\count@"F0
\@tempcnta"F5
- \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@four@octets\noexpand~}}
+ \def\UTFviii@tmp{\protected\edef~{\noexpand\UTFviii@four@octets\noexpand~}}
\UTFviii@loop
% \end{macrocode}
%
@@ -623,12 +634,13 @@
% \begin{macrocode}
\count@"F5
\@tempcnta"100
- \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@invalid@err\string~}}
+ \def\UTFviii@tmp{\protected\edef~{\noexpand\UTFviii@invalid@err\string~}}
\UTFviii@loop
% \end{macrocode}
%
+% Restore values after the loops.
% \begin{macrocode}
-\endgroup
+\reserved@a
% \end{macrocode}
%
% \end{macro}
@@ -773,12 +785,13 @@
% looks slightly strange but is designed for the sequence of |\expandafter|
% in |\DeclareUnicodeCharacter|.
%
+% \changes{v1.2o}{2021/12/13}{Use 80 not A0 to test for single byte UTF-8}
% \begin{macrocode}
- \ifnum\count@<"A0\relax
+ \ifnum\count@<"80\relax
\ifnum\catcode\count@=13
\uccode`\~=\count@\uppercase{\def\UTFviii@tmp{\@empty\@empty~}}%
\else
- \@latex@error{Cannot define non-active Unicode char value < 00A0}%
+ \@latex@error{Cannot define non-active Unicode char value < 0080}%
\@eha
\def\UTFviii@tmp{\UTFviii@tmp}%
\fi
@@ -1139,6 +1152,7 @@
% \changes{v1.1r}{2015/12/03}{Add some more ogonek cases}
% \changes{v1.1s}{2016/01/11}{Add some more caron and acute}
% \changes{v1.1t}{2017/01/28}{Add caron combinations for GgYy}
+% \changes{v1.3c}{2022/06/07}{Fix \cs{guillemetleft} and \cs{guillemetright} also in dfu files (gh/65)}%
% \begin{macrocode}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00A0}{\nobreakspace}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00A1}{\textexclamdown}
@@ -1152,7 +1166,8 @@
%<all,ts1,utf8>\DeclareUnicodeCharacter{00A9}{\textcopyright}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00AA}{\textordfeminine}
%<*all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
-\DeclareUnicodeCharacter{00AB}{\guillemotleft}
+%\DeclareUnicodeCharacter{00AB}{\guillemotleft} % wrong Adobe name
+\DeclareUnicodeCharacter{00AB}{\guillemetleft}
%</all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
%<all,ts1>\DeclareUnicodeCharacter{00AC}{\textlnot}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00AD}{\-}
@@ -1170,7 +1185,8 @@
%<all,ts1>\DeclareUnicodeCharacter{00B9}{\textonesuperior}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00BA}{\textordmasculine}
%<*all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
-\DeclareUnicodeCharacter{00BB}{\guillemotright}
+%\DeclareUnicodeCharacter{00BB}{\guillemotright} % wrong Adobe name
+\DeclareUnicodeCharacter{00BB}{\guillemetright}
%</all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BC}{\textonequarter}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BD}{\textonehalf}
@@ -1368,6 +1384,18 @@
%<all,t1,ly1>\DeclareUnicodeCharacter{017E}{\v z}
%<all,ts1,ly1>\DeclareUnicodeCharacter{0192}{\textflorin}
% \end{macrocode}
+% \changes{v1.2n}{2021/12/10}{add 01C4-01CC}
+% \begin{macrocode}
+%<all,t1>\DeclareUnicodeCharacter{01C4}{D\v Z}
+%<all,t1>\DeclareUnicodeCharacter{01C5}{D\v z}
+%<all,t1>\DeclareUnicodeCharacter{01C6}{d\v z}
+%<all,t1>\DeclareUnicodeCharacter{01C7}{LJ}
+%<all,t1>\DeclareUnicodeCharacter{01C8}{Lj}
+%<all,t1>\DeclareUnicodeCharacter{01C9}{lj}
+%<all,t1>\DeclareUnicodeCharacter{01CA}{NJ}
+%<all,t1>\DeclareUnicodeCharacter{01CB}{Nj}
+%<all,t1>\DeclareUnicodeCharacter{01CC}{nj}
+% \end{macrocode}
% \changes{v1.1s}{2016/01/11}{add 01CD-01F4}
% \begin{macrocode}
%<all,t1>\DeclareUnicodeCharacter{01CD}{\v A}
@@ -1795,8 +1823,14 @@
%<all,ts1>\DeclareUnicodeCharacter{2191}{\textuparrow}
%<all,ts1>\DeclareUnicodeCharacter{2192}{\textrightarrow}
%<all,ts1>\DeclareUnicodeCharacter{2193}{\textdownarrow}
+% \end{macrocode}
+% \changes{v1.3b}{2022/05/08}{Declare Unicode codepoints U+3008/U+3009 to
+% better support normalized documents}
+% \begin{macrocode}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{2329}{\textlangle}
+%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{3008}{\textlangle}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{232A}{\textrangle}
+%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{3009}{\textrangle}
%<all,ts1>\DeclareUnicodeCharacter{2422}{\textblank}
%<all,x2,t2c,t2b,t2a,t1,utf8>\DeclareUnicodeCharacter{2423}{\textvisiblespace}
%<all,ts1>\DeclareUnicodeCharacter{25E6}{\textopenbullet}