Add optional arg. to case commands and keyval BCP47 interface (#936)

latex3 · Oct 26, 2022 · 7447e93 · 7447e93
1 parent e0f0d7e
commit 7447e93
Show file tree

Hide file tree

Showing 32 changed files with 404 additions and 328 deletions.
diff --git a/base/changes.txt b/base/changes.txt
@@ -6,6 +6,13 @@ completeness or accuracy and it contains some references to files that
 are not part of the distribution.
 ================================================================================
 
+2022-10-26  Joseph Wright  <Joseph.Wright@latex-project.org>
+
+	* ltfinal.dtx:
+	Introduce optional argument for case-changing commands
+	Make case changing commands language-aware
+	Auto-detect babel locale for case changing
+
 2022-10-22  David Carlisle  <David.Carlisle@latex-project.org>
 
 	* ltclass.dtx, ltdefns.dtx: Further \protect guards for gh/932

diff --git a/base/doc/ltnews36.tex b/base/doc/ltnews36.tex
@@ -221,10 +221,26 @@ \subsection{Encoding subsets for \texttt{TS1} encoded fonts}
 %
 \githubissue{905}
 
-
-
-%\section{New or improved commands}
-
+\section{New or improved commands}
+
+\subsection{Better language handling for case-changing commands}
+
+The commands \cs{MakeUppercase}, \cs{MakeLowercase} and \cs{MakeTitlecase} now
+automatically detect the locale currently in use when \pkg{babel} is loaded.
+This allows automatic adjustment of letter mappings where appropriate. They
+also accept a leading optional argument. This accepts a key--value list of
+control settings. At present, there is one key available: \texttt{locale},
+which can also be accessed via the alias \texttt{lang}. This are intended to
+allow local setting of the language, which can be done using a BCP-47
+descriptor. For example, this could be used to force Turkic case changing in
+otherwise English input
+\begin{verbatim}
+  \MakeUppercase[lang = tr]{Ragıp Hulûsi Özdem}
+\end{verbatim}
+yields
+\begin{quotation}
+  \MakeUppercase[lang = tr]{Ragıp Hulûsi Özdem}.
+\end{quotation}
 
 \section{Code improvements}
 

diff --git a/base/doc/usrguide.tex b/base/doc/usrguide.tex
@@ -1166,6 +1166,13 @@ \section{Case changing}
   \end{tabular}
 \end{quotation}
 
+The case-changing commands take an optional argument which can be used to
+tailor the output. This optional argument accepts the key \texttt{locale},
+also available under the alias \texttt{lang},
+which can be used to give a language identifier in BCP-47
+format. This is then applied to select language-specific features during
+case-changing.
+
 The input given to these commands is `expanded' before case changing is
 applied. This means that any commands within the input that convert to pure
 text will be case changed. Mathematical content is automatically excluded, as

diff --git a/base/ltfinal.dtx b/base/ltfinal.dtx
@@ -33,7 +33,7 @@
 %<*driver>
 % \fi
 \ProvidesFile{ltfinal.dtx}
-             [2022/08/29 v2.2w LaTeX Kernel (Final Settings)]
+             [2022/10/26 v2.2x LaTeX Kernel (Final Settings)]
 % \iffalse
 \documentclass{ltxdoc}
 \GetFileInfo{ltfinal.dtx}
@@ -1085,6 +1085,9 @@
 % \changes{v2.2t}{2022/04/21}{Support \cs{noexpand} in argument of \cs{@expl@text@uppercase@@n}}
 % \changes{v2.2v}{2022/06/30}{Just use \cs{text_lowercase:n} without \cs{protectd@edf} gh/881x}%
 % \changes{v2.2w}{2022/07/04}{Introduced \cs{CaseSwitch}, \cs{DeclareCaseChangeEquivalent} and \cs{MakeTitlecase} to support hooking into case changing gh/889}%
+% \changes{v2.2x}{2022/10/26}{Introduce optional argument for case-changing commands}
+% \changes{v2.2x}{2022/10/26}{Make case changing commands language-aware}
+% \changes{v2.2x}{2022/10/26}{Auto-detect \pkg{babel} locale}
 % Wrappers around the L3 case changing functions.
 % |\protected| to make them mostly safe as replacements for |uppercase|
 % and |\lowercase|.  
@@ -1109,12 +1112,55 @@
 % functions.
 %    \begin{macrocode}
 \ExplSyntaxOn
-\cs_new_protected_nopar:cpn{MakeUppercase~}{\text_uppercase:n}
-\cs_set_nopar:Npx\MakeUppercase#1{\use:c{MakeUppercase~}{#1}}
-\cs_new_protected_nopar:cpn{MakeLowercase~}{\text_lowercase:n}
-\cs_set_nopar:Npx\MakeLowercase#1{\use:c{MakeLowercase~}{#1}}
-\cs_new_protected_nopar:cpn{MakeTitlecase~}{\text_titlecase:n}
-\cs_set_nopar:Npx\MakeTitlecase#1{\use:c{MakeTitlecase~}{#1}}
+\keys_define:nn { __kernel }
+  {
+    lang   .str_set:N = \reserved@a ,
+    locale .str_set:N = \reserved@a
+  }
+\cs_new_protected:Npn \@@text@case@aux #1#2#3
+  {
+    \cs_set_nopar:Npn \reserved@a { }
+    \tl_if_blank:nTF {#2}
+      { \@@text@case@aux@ }
+      { \keys_set:nn { __kernel } {#2} }
+    \use:c { text_ #1 case:Vn } \reserved@a {#3}
+  }
+\cs_new_protected:Npn \@@text@case@aux@ { }
+\tl_gput_right:Nn \@kernel@after@begindocument
+  {
+    \@ifpackageloaded { babel }
+      {
+        \@ifpackagelater { babel } { 2020-01-15 }
+          {
+            \cs_gset_protected:Npn \@@text@case@aux@
+              {
+                \str_set:Nx \reserved@a
+                  { \localeinfo* { tag.bcp47 } }
+              }
+          }
+          { }
+      }
+      { }
+  }
+\exp_args_generate:n { cnx }
+%    \end{macrocode}
+% The odd use of \emph{three} spaces here is needed as \pkg{ltcmd} uses the
+% name with one and two spaces to give a `friendly' error message for a runaway
+% argument: that means we can't use it here.
+%    \begin{macrocode}
+\cs_set_protected:Npn \reserved@a #1
+  {
+    \cs_generate_variant:cn { text_ \str_lowercase:n {#1} case:nn } { V }
+    \cs_new_protected:cpx { Make#1case \c_space_tl \c_space_tl \c_space_tl } [##1] ##2
+      { \exp_not:N \@@text@case@aux { \str_lowercase:n {#1} } {##1} {##2} }
+     \ExpandArgs { cnx } \NewExpandableDocumentCommand
+       { Make#1case }
+       { O{} +m }
+       { \exp_not:c { Make#1case \c_space_tl \c_space_tl \c_space_tl } [####1] {####2} }
+  }
+\reserved@a { Upper }
+\reserved@a { Lower }
+\reserved@a { Title }
 %    \end{macrocode}
 %
 % \changes{v2.2u}{2022/06/02}{Add \cs{NoCaseChange}}

diff --git a/base/testfiles-lthooks/ltcmdhooks-001.tlg b/base/testfiles-lthooks/ltcmdhooks-001.tlg
@@ -58,7 +58,7 @@ l. ...\ShowHook{cmd/foo/after}
 #1#2->FOO #1 #2.
 l. ...\show\foo
 > \@kernel@after@begindocument=macro:
-->\prop_map_inline:Nn \l_keys_usage_preamble_prop {\clist_map_inline:nn {##2}{\keys_define:nn {##1}{####1.code:n=\msg_error:nnn {keys}{preamble-only}{####1}}}}\__hook_cmd_begindocument_code: \bool_gset_true:N \g__pdf_init_bool \group_begin: \cs_set_protected:Npn \__text_tmp:w ##1{\tl_clear:N \l_text_expand_exclude_tl \tl_map_inline:nn {##1}{\bool_lazy_any:nF {{\token_if_protected_macro_p:N ####1}{\token_if_protected_long_macro_p:N ####1}{\str_if_eq_p:ee {\cs_replacement_spec:N ####1}{\exp_not:n {\protect ####1}\c_space_tl }}}{\tl_put_right:Nn \l_text_expand_exclude_tl {####1}}}}\exp_args:NV \__text_tmp:w \l_text_expand_exclude_tl \exp_args:NNNV \group_end: \tl_set:Nn \l_text_expand_exclude_tl \l_text_expand_exclude_tl \group_begin: \cs_set_protected:Npn \__text_change_case_setup:Nn ##1##2{\quark_if_recursion_tail_stop:N ##1\tl_if_single_token:nT {##2}{\cs_if_exist:cF {c__text_uppercase_\token_to_str:N ##1_tl}{\tl_const:cn {c__text_uppercase_\token_to_str:N ##1_tl}{##2}}\cs_if_exist:cF {c__text_lowercase_\token_to_str:N ##2_tl}{\tl_const:cn {c__text_lowercase_\token_to_str:N ##2_tl}{##1}}}\__text_change_case_setup:Nn }\exp_after:wN \__text_change_case_setup:Nn \@uclclist \q_recursion_tail ?\q_recursion_stop \group_end: .
+->\prop_map_inline:Nn \l_keys_usage_preamble_prop {\clist_map_inline:nn {##2}{\keys_define:nn {##1}{####1.code:n=\msg_error:nnn {keys}{preamble-only}{####1}}}}\__hook_cmd_begindocument_code: \bool_gset_true:N \g__pdf_init_bool \group_begin: \cs_set_protected:Npn \__text_tmp:w ##1{\tl_clear:N \l_text_expand_exclude_tl \tl_map_inline:nn {##1}{\bool_lazy_any:nF {{\token_if_protected_macro_p:N ####1}{\token_if_protected_long_macro_p:N ####1}{\str_if_eq_p:ee {\cs_replacement_spec:N ####1}{\exp_not:n {\protect ####1}\c_space_tl }}}{\tl_put_right:Nn \l_text_expand_exclude_tl {####1}}}}\exp_args:NV \__text_tmp:w \l_text_expand_exclude_tl \exp_args:NNNV \group_end: \tl_set:Nn \l_text_expand_exclude_tl \l_text_expand_exclude_tl \group_begin: \cs_set_protected:Npn \__text_change_case_setup:Nn ##1##2{\quark_if_recursion_tail_stop:N ##1\tl_if_single_token:nT {##2}{\cs_if_exist:cF {c__text_uppercase_\token_to_str:N ##1_tl}{\tl_const:cn {c__text_uppercase_\token_to_str:N ##1_tl}{##2}}\cs_if_exist:cF {c__text_lowercase_\token_to_str:N ##2_tl}{\tl_const:cn {c__text_lowercase_\token_to_str:N ##2_tl}{##1}}}\__text_change_case_setup:Nn }\exp_after:wN \__text_change_case_setup:Nn \@uclclist \q_recursion_tail ?\q_recursion_stop \group_end: \@ifpackageloaded {babel}{\@ifpackagelater {babel}{....-..-..}{\cs_gset_protected:Npn \@@text@case@aux@ {\str_set:Nx \reserved@a {\localeinfo *{tag.bcp47}}}}{}}{}.
 l. ...\show\@kernel@after@begindocument
 Update code for hook 'para/before' on input line ...:
 Update code for hook 'para/after' on input line ...: