babel (15oct19)

git-svn-id: svn://tug.org/texlive/trunk@52400 c570f23f-e606-0410-a88d-b1316a301751

1 files changed, 113 insertions, 71 deletions

diff --git a/Master/texmf-dist/source/latex/babel/babel.dtx b/Master/texmf-dist/source/latex/babel/babel.dtx
index 86d4890e348..398c5e4ae3b 100644
--- a/Master/texmf-dist/source/latex/babel/babel.dtx
+++ b/Master/texmf-dist/source/latex/babel/babel.dtx
@@ -31,7 +31,7 @@
 %
 % \iffalse
 %<*filedriver>
-\ProvidesFile{babel.dtx}[2019/09/27 v3.34 The Babel package]
+\ProvidesFile{babel.dtx}[2019/10/15 v3.35 The Babel package]
 \documentclass{ltxdoc}
 \GetFileInfo{babel.dtx}
 \usepackage{fontspec}
@@ -1023,11 +1023,13 @@ using them; see above.
 shorthands is safe. With \texttt{safe=bib} only |\nocite|, |\bibcite|
 and |\bibitem| are redefined. With |safe=ref| only |\newlabel|, |\ref|
 and |\pageref| are redefined (as well as a few macros from
-\textsf{varioref} and \textsf{ifthen}). With |safe=none| no macro is
-redefined. This option is strongly recommended, because a good deal of
-incompatibilities and errors are related to these redefinitions -- of
-course, in such a case you cannot use shorthands in these macros, but
-this is not a real problem (just use ``allowed'' characters).
+\textsf{varioref} and \textsf{ifthen}).
+
+With |safe=none| no macro is redefined. This option is strongly
+recommended, because a good deal of incompatibilities and errors are
+related to these redefinitions. As of \New{3.34}, in $\epsilon$\TeX{}
+based engines (ie, almost every engine except the oldest ones)
+shorthands can be used in these macros (formerly you could not).
 
 \Describe{math=}{\texttt{active} $\string|$ \texttt{normal}}
 Shorthands are mainly intended for text, not for math. By setting this
@@ -4071,8 +4073,8 @@ help from Bernd Raichle, for which I am grateful.
 % \section{Tools}
 %
 %    \begin{macrocode}
-%<<version=3.34>>
-%<<date=2019/09/27>>
+%<<version=3.35>>
+%<<date=2019/10/15>>
 %    \end{macrocode}
 %
 % \textbf{Do not use the following macros in \texttt{ldf} files. They
@@ -4210,25 +4212,30 @@ help from Bernd Raichle, for which I am grateful.
 %   it is based on |\ifcsname|, which is more efficient, and do not
 %   waste memory.
 %
+% \changes{babel~3.35}{2019/09/22}{Inside a group, so that \cs{ifcsname}
+%   is still undefined.}
+%
 %    \begin{macrocode}
-\def\bbl@ifunset#1{%
-  \expandafter\ifx\csname#1\endcsname\relax
-    \expandafter\@firstoftwo
-  \else
-    \expandafter\@secondoftwo
-  \fi}
-\bbl@ifunset{ifcsname}%
-  {}%
-  {\def\bbl@ifunset#1{%
-     \ifcsname#1\endcsname
-       \expandafter\ifx\csname#1\endcsname\relax
-         \bbl@afterelse\expandafter\@firstoftwo
+\begingroup
+  \gdef\bbl@ifunset#1{%
+    \expandafter\ifx\csname#1\endcsname\relax
+      \expandafter\@firstoftwo
+    \else
+      \expandafter\@secondoftwo
+    \fi}
+  \bbl@ifunset{ifcsname}%
+    {}%
+    {\gdef\bbl@ifunset#1{%
+       \ifcsname#1\endcsname
+         \expandafter\ifx\csname#1\endcsname\relax
+           \bbl@afterelse\expandafter\@firstoftwo
+         \else
+           \bbl@afterfi\expandafter\@secondoftwo
+         \fi
        \else
-         \bbl@afterfi\expandafter\@secondoftwo
-       \fi
-     \else
-       \expandafter\@firstoftwo
-     \fi}}
+         \expandafter\@firstoftwo
+       \fi}}
+\endgroup
 %    \end{macrocode}
 % \end{macro}
 %
@@ -6079,28 +6086,43 @@ help from Bernd Raichle, for which I am grateful.
 %    The command |\active@prefix| which is used in the expansion of
 %    active characters has a function similar to |\OT1-cmd| in that it
 %    |\protect|s the active character whenever |\protect| is
-%    \emph{not} |\@typeset@protect|.
-%
-%    \begin{macrocode}
-\def\active@prefix#1{%
-  \ifx\protect\@typeset@protect
-  \else
-%    \end{macrocode}
-%
-%    When |\protect| is set to |\@unexpandable@protect| we make sure
-%    that the active character is als \emph{not} expanded by inserting
-%    |\noexpand| in front of it. The |\@gobble| is needed to remove
+%    \emph{not} |\@typeset@protect|. The |\@gobble| is needed to remove
 %    a token such as |\activechar:| (when the double colon was the
-%    active character to be dealt with).
+%    active character to be dealt with). There are two definitions,
+%    depending of |\ifincsname| is available. If there is, the
+%    expansion will be more robust.
+%
+% \changes{babel 3.35}{2019/09/18}{Added \cs{ifincsname} test.}
 %
 %    \begin{macrocode}
-    \ifx\protect\@unexpandable@protect
-      \noexpand#1%
-    \else
-      \protect#1%
-    \fi
-    \expandafter\@gobble
-  \fi}
+\begingroup
+\bbl@ifunset{ifincsname}%
+  {\gdef\active@prefix#1{%
+     \ifx\protect\@typeset@protect
+     \else
+       \ifx\protect\@unexpandable@protect
+         \noexpand#1%
+       \else
+         \protect#1%
+       \fi
+       \expandafter\@gobble
+     \fi}}
+  {\gdef\active@prefix#1{%
+     \ifincsname
+       \string#1%
+       \expandafter\@gobble
+     \else
+       \ifx\protect\@typeset@protect
+       \else
+         \ifx\protect\@unexpandable@protect
+           \noexpand#1%
+         \else
+           \protect#1%
+         \fi
+         \expandafter\expandafter\expandafter\@gobble
+       \fi
+     \fi}}
+\endgroup
 %    \end{macrocode}
 %
 %  \end{macro}
@@ -8060,7 +8082,13 @@ help from Bernd Raichle, for which I am grateful.
   \let\bbl@KVP@mapdigits\@nil
   \let\bbl@KVP@intraspace\@nil
   \let\bbl@KVP@intrapenalty\@nil
-  \bbl@forkv{#1}{\bbl@csarg\def{KVP@##1}{##2}}%  TODO - error handling
+  \bbl@forkv{#1}{%  TODO - error handling
+    \in@{/}{##1}%
+    \ifin@
+      \bbl@renewinikey##1\@@{##2}%
+    \else
+      \bbl@csarg\def{KVP@##1}{##2}%
+    \fi}%
   \ifx\bbl@KVP@import\@nil\else
     \bbl@exp{\\\bbl@ifblank{\bbl@KVP@import}}%
       {\begingroup
@@ -8432,10 +8460,7 @@ help from Bernd Raichle, for which I am grateful.
       % Move trims here ??
       \bbl@ifunset{bbl@KVP@\bbl@section/\bbl@tempa}%
         {\expandafter\bbl@inireader\bbl@tempa=##2\@@}%
-        {\def\bbl@tempc{\expandafter\bbl@inireader\bbl@tempa=}%
-         \expandafter\expandafter\expandafter
-         \bbl@tempc\csname bbl@KVP@\bbl@section/\bbl@tempa\endcsname\@@}%
-         \global\bbl@csarg\let{KVP@\bbl@section/\bbl@tempa}\relax}%
+        {}}%
     \let\bbl@inireader\bbl@iniskip
     \bbl@info{Importing data from babel-#1.ini for \languagename}%
     \loop
@@ -8460,9 +8485,15 @@ help from Bernd Raichle, for which I am grateful.
 %    \begin{macrocode}
 \def\bbl@iniskip#1\@@{}%      if starts with ;
 \def\bbl@inisec[#1]#2\@@{%    if starts with opening bracket
+  \def\bbl@elt##1##2{\bbl@inireader##1=##2\@@}%
+  \@nameuse{bbl@renew@\bbl@section}%
+  \global\bbl@csarg\let{renew@\bbl@section}\relax
   \@nameuse{bbl@secpost@\bbl@section}%  ends previous section
   \def\bbl@section{#1}%
-  \@nameuse{bbl@secpre@\bbl@section}%   starts current section
+  \def\bbl@elt##1##2{%
+    \@namedef{bbl@KVP@#1/##1}{}}%
+  \@nameuse{bbl@renew@#1}%
+  \@nameuse{bbl@secpre@#1}%   starts current section
   \bbl@ifunset{bbl@inikv@#1}%
     {\let\bbl@inireader\bbl@iniskip}%
     {\bbl@exp{\let\\\bbl@inireader\<bbl@inikv@#1>}}}
@@ -9067,6 +9098,9 @@ help from Bernd Raichle, for which I am grateful.
 %    the mark are not disabled by the output routine kicking in while
 %    \cs{@safe@activestrue} is in effect.
 %
+% \changes{babel~3.35}{2019/10/11}{Now \cs{markboth} is protected.
+%    Consider this case.}
+%
 %    \begin{macrocode}
 \bbl@trace{Marks}
 \IfBabelLayout{sectioning}
@@ -9079,7 +9113,8 @@ help from Bernd Raichle, for which I am grateful.
          \noexpand\babelsublr{\unexpanded\expandafter{\thepage}}}}%
    \fi}
   {\ifbbl@single\else
-     \bbl@redefine\markright#1{%
+     \bbl@ifunset{markright }\bbl@redefine\bbl@redefinerobust
+     \markright#1{%
        \bbl@ifblank{#1}%
          {\org@markright{}}%
          {\toks@{#1}%
@@ -9098,7 +9133,9 @@ help from Bernd Raichle, for which I am grateful.
 %    headings for the page. While doing so they also store a copy of
 %    |\markboth| in |\@mkboth|. Therefore we need to check whether
 %    |\@mkboth| has already been set. If so we neeed to do that again
-%    with the new definition of |\markboth|.
+%    with the new definition of |\markboth|. (As of Oct 2019, \LaTeX{}
+%    stores the definition in an intermediate macros, so it's not
+%    necessary anymore, but it's preserved for older versions.)
 %
 %    \begin{macrocode}
      \ifx\@mkboth\markboth
@@ -9106,12 +9143,8 @@ help from Bernd Raichle, for which I am grateful.
      \else
        \def\bbl@tempc{}
      \fi
-%    \end{macrocode}
-%
-%    Now we can start the new definition of |\markboth|
-%
-%    \begin{macrocode}
-     \bbl@redefine\markboth#1#2{%
+     \bbl@ifunset{markboth }\bbl@redefine\bbl@redefinerobust
+     \markboth#1#2{%
        \protected@edef\bbl@tempb##1{%
          \protect\foreignlanguage
          {\languagename}{\protect\bbl@restore@actives##1}}%
@@ -9122,11 +9155,6 @@ help from Bernd Raichle, for which I am grateful.
          {\@temptokena{}}%
          {\@temptokena\expandafter{\bbl@tempb{#2}}}%
        \bbl@exp{\\\org@markboth{\the\toks@}{\the\@temptokena}}}
-%    \end{macrocode}
-%
-%    and copy it to |\@mkboth| if necessary.
-%
-%    \begin{macrocode}
        \bbl@tempc
      \fi}  % end ifbbl@single, end \IfBabelLayout
 %    \end{macrocode}
@@ -9386,10 +9414,11 @@ help from Bernd Raichle, for which I am grateful.
 % \changes{babel~3.9j}{2014/03/17}{Moved misplaced code - it should be
 %    executed only with LaTeX}
 % \changes{babel~3.23}{2018/08/28}{Added TS1, T3, TS3}
+% \changes{babel~3.35}{2019/10/01}{Added PU, PD1}
 %
 %    \begin{macrocode}
 \bbl@trace{Encoding and fonts}
-\newcommand\BabelNonASCII{LGR,X2,OT2,OT3,OT6,LHE,LWN,LMA,LMC,LMS,LMU}
+\newcommand\BabelNonASCII{LGR,X2,OT2,OT3,OT6,LHE,LWN,LMA,LMC,LMS,LMU,PU,PD1}
 \newcommand\BabelNonText{TS1,T3,TS3}
 \let\org@TeX\TeX
 \let\org@LaTeX\LaTeX
@@ -11272,9 +11301,12 @@ help from Bernd Raichle, for which I am grateful.
      \bbl@warning{The current font is not a babel standard family:\\%
        #1%
        \fontname\font\\%
-       There is nothing intrinsically wrong with it, but\\%
-       'babel' will no set Script and Language. Consider\\%
-       defining a new family with \string\babelfont.\\%
+       There is nothing intrinsically wrong with this warning, and\\%
+       you can ignore it altogether if you do not need these\\%
+       families. But if they are used in the document, you should be\\%
+       aware 'babel' will no set Script and Language for them, so\\%
+       you may consider defining a new family with \string\babelfont.\\%
+       See the manual for further details about \string\babelfont.\\%
        Reported}}
    {}}%
 \gdef\bbl@switchfont{%
@@ -12504,6 +12536,8 @@ help from Bernd Raichle, for which I am grateful.
 % \subsection{Auto bidi with \texttt{basic} and \texttt{basic-r}}
 %
 % \changes{babel~3.14}{2017/09/30}{LuaTeX - support for R/AL texts - basic-r}
+% \changes{babel~3.35}{2019/10/11}{Hack for unboxed boxes - The PUAs
+%   are `on'.}
 %
 % The file \textsf{babel-data-bidi.lua} currently only contains data. It is
 % a large and boring file and it's not shown here. See the generated
@@ -12515,19 +12549,24 @@ help from Bernd Raichle, for which I am grateful.
 
 Babel = Babel or {}
 
+-- TODO: merge ranges into characters, as meta index
+
 Babel.ranges={
  {0x0590, 0x05FF, 'r'},
  {0x0600, 0x07BF, 'al'},
  {0x07C0, 0x085F, 'r'},
  {0x0860, 0x086F, 'al'},
  {0x08A0, 0x08FF, 'al'},
+ {0xE000, 0xF8FF, 'on'}, -- PUA
  {0xFB1D, 0xFB4F, 'r'},
  {0xFB50, 0xFDFF, 'al'},
  {0xFE70, 0xFEFF, 'al'},
  {0x10800, 0x10C4F, 'r'},
  {0x1E800, 0x1E8DF, 'r'},
  {0x1E900, 0x1E95F, 'r'},
- {0x1F300, 0x1F9FF, 'on'}
+ {0x1F300, 0x1F9FF, 'on'},
+ {0xF0000, 0xFFFFD, 'on'}, -- PUA
+ {0x100000, 0x10FFFD, 'on'} -- PUA
 }
 
 Babel.characters={
@@ -18854,7 +18893,7 @@ function Babel.bidi(head, ispar)
       if mir == 'rrr' or mir == 'lrr' or mir == 'rrl' or mir == 'rlr' then
         for ch in node.traverse(node.next(last_lr)) do
           if ch == item then break end
-          if ch.id == node.id'glyph' then
+          if ch.id == node.id'glyph' and characters[ch.char] then
             ch.char = characters[ch.char].m or ch.char
           end
         end
@@ -18883,7 +18922,9 @@ function Babel.bidi(head, ispar)
 %    \begin{macrocode}
   if last_lr and outer == 'r' then
     for ch in node.traverse_id(node.id'glyph', node.next(last_lr)) do
-      ch.char = characters[ch.char].m or ch.char
+      if characters[ch.char] then
+        ch.char = characters[ch.char].m or ch.char
+      end
     end
   end
   if first_n then
@@ -19215,7 +19256,8 @@ function Babel.bidi(head, ispar, hdir)
       for r = first_on, q - 1 do
         nodes[r][2] = temp
         item = nodes[r][1]    -- MIRRORING
-        if Babel.mirroring_enabled and item.id == GLYPH and temp == 'r' then
+        if Babel.mirroring_enabled and item.id == GLYPH
+             and temp == 'r' and characters[item.char] then
           item.char = characters[item.char].m or item.char
         end
       end