[latex3-commits] [git/LaTeX3-latex3-latex2e] gh723: extend UTF-8 support for issue #723 (a1d62754)

[David Carlisle]

Repository : https://github.com/latex3/latex2e
On branch  : gh723
Link       : https://github.com/latex3/latex2e/commit/a1d62754256d2438f06a496c4644e45b8d819a60

>---------------------------------------------------------------

commit a1d62754256d2438f06a496c4644e45b8d819a60
Author: David Carlisle <d.p.carlisle at gmail.com>
Date:   Fri Dec 10 15:53:10 2021 +0000

    extend UTF-8 support for issue #723


>---------------------------------------------------------------

a1d62754256d2438f06a496c4644e45b8d819a60
 base/changes.txt                      |  4 ++++
 base/doc/ltnews35.tex                 |  8 ++++++--
 base/testfiles-legacy/github-0723.lvt | 22 ++++++++++++++++++++++
 base/testfiles-legacy/github-0723.tlg | 34 ++++++++++++++++++++++++++++++++++
 base/utf8ienc.dtx                     | 14 +++++++++++++-
 5 files changed, 79 insertions(+), 3 deletions(-)

diff --git a/base/changes.txt b/base/changes.txt
index 51e6cea9..78e92345 100644
--- a/base/changes.txt
+++ b/base/changes.txt
@@ -6,6 +6,10 @@ completeness or accuracy and it contains some references to files that
 are not part of the distribution.
 ================================================================================
 
+2021-12-10  David Carlisle  <David.Carlisle at latex-project.org>
+
+	* utf8ienc.dtx: Add inputenc UTF-8 support for for Digraphs U_01C4-U+01CC
+
 2021-12-09  Frank Mittelbach  <Frank.Mittelbach at latex-project.org>
 
 	* proc.dtx (subsection{The page style}):
diff --git a/base/doc/ltnews35.tex b/base/doc/ltnews35.tex
index 02736853..faaa69e7 100644
--- a/base/doc/ltnews35.tex
+++ b/base/doc/ltnews35.tex
@@ -254,9 +254,13 @@ displaying different data in the footer line on recto and verso pages.
 \githubissue{gh/704}
 
 
-\subsection{???}
+\subsection{Croatian character support}
 %
-\githubissue{???}
+The default \pkg{inputenc} support has been extended to support the 9 characters
+D\v Z, D\v z, d\v z, LJ, Lj, lj, NJ, Nj, nj, input as single UTF-8 codepoints
+in the range U+01C4 to U+01CC.
+%
+\githubissue{gh/723}
 
 
 
diff --git a/base/testfiles-legacy/github-0723.lvt b/base/testfiles-legacy/github-0723.lvt
new file mode 100644
index 00000000..03bdc3b5
--- /dev/null
+++ b/base/testfiles-legacy/github-0723.lvt
@@ -0,0 +1,22 @@
+\documentclass{article}
+
+% test file for Croatian (and other South Slavic) diagraph characters
+% github #723
+\input{test2e}
+
+\usepackage[T1]{fontenc}
+
+
+
+\begin{document}
+\showoutput
+\START
+
+
+
+\sbox0{[DŽ.Dž.dž.LJ.Lj.lj.NJ.Nj.nj]}
+\showbox0
+
+
+\END
+
diff --git a/base/testfiles-legacy/github-0723.tlg b/base/testfiles-legacy/github-0723.tlg
new file mode 100644
index 00000000..c572cd94
--- /dev/null
+++ b/base/testfiles-legacy/github-0723.tlg
@@ -0,0 +1,34 @@
+This is a generated file for the LaTeX2e validation system.
+Don't change this file in any respect.
+> \box...=
+\hbox(8.91449+2.49939)x121.91467
+.\T1/cmr/m/n/10 [
+.\T1/cmr/m/n/10 D
+.\T1/cmr/m/n/10 ^^9a
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 D
+.\T1/cmr/m/n/10 ^^ba
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 d
+.\T1/cmr/m/n/10 ^^ba
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 L
+.\T1/cmr/m/n/10 J
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 L
+.\T1/cmr/m/n/10 j
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 l
+.\T1/cmr/m/n/10 j
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 N
+.\T1/cmr/m/n/10 J
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 N
+.\T1/cmr/m/n/10 j
+.\T1/cmr/m/n/10 .
+.\T1/cmr/m/n/10 n
+.\T1/cmr/m/n/10 j
+.\T1/cmr/m/n/10 ]
+! OK.
+l. ...\showbox0
diff --git a/base/utf8ienc.dtx b/base/utf8ienc.dtx
index 438edb70..1067a7e6 100644
--- a/base/utf8ienc.dtx
+++ b/base/utf8ienc.dtx
@@ -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>   [2021/12/10 v1.2n UTF-8 support]
 %    \end{macrocode}
 %
 %    \begin{macrocode}
@@ -1368,6 +1368,18 @@
 %<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}