Store spaces/tabs as actives in v-type arg

base/changes.txt

@@ -6,6 +6,12 @@ to completeness or accuracy and it contains some references to files that are
 not part of the distribution.
 ================================================================================
 
+2025-01-11  Joseph Wright  <Joseph.Wright@latex-project.org>
+
+	* ltcmd.dtx:
+	Correct catcode of space/tab in v-type arg
+	Adjust handling of catcodes for letters in v-type arg
+
 2025-01-03  Frank Mittelbach  <Frank.Mittelbach@latex-project.org>
 
 	* lthooks.dtx (subsubsection{Updating code for hooks}):

base/doc/ltnews41.tex

@@ -278,6 +278,13 @@ \subsection{Tab character as a special}
 be used in for example a \texttt{v}~specification document command without
 additional steps.
 
+\subsection{Refinement of \texttt{v}~specification category codes}
+
+Work on verbatim argument handling has highlighted that storing
+all characters as \enquote{other} (category code~12) when using a
+\texttt{v}~specification in \pkg{ltcmd} was problematic. We have now
+revised this to capture letters with their original cateogry code.
+
 \subsection{Logging text command and symbol declarations}
 
 For thirty years the documentation claimed that \cs{DeclareTextSymbol},

base/doc/usrguide.tex

@@ -35,15 +35,15 @@
 \usepackage{url}
 
 \title{\LaTeX\ for authors\\ current version}
-\author{\copyright~Copyright 2020--2024, \LaTeX\ Project Team.\\
+\author{\copyright~Copyright 2020--2025, \LaTeX\ Project Team.\\
    All rights reserved.%
    \footnote{This file may be distributed and/or modified under the
      conditions of the \LaTeX{} Project Public License, either version 1.3c
      of this license or (at your option) any later version. See the source
     \texttt{usrguide.tex} for full details.}%
 }
 
-\date{2024-11-17}
+\date{2025-01-12}
 
 \NewDocumentCommand\cs{m}{\texttt{\textbackslash\detokenize{#1}}}
 \NewDocumentCommand\marg{m}{\arg{#1}}
@@ -837,10 +837,12 @@ \subsection{Using the verbatim argument types}
 
 Some additional details that may be useful for those with more \TeX{}
 knowledge: do not worry if this does not make sense to you! Spaces and tabs are
-stored as active characters. In Unicode engines, all other characters are of
-type \enquote{other}. In $8$-bit engines, the ASCII characters other than tab
-and space are of type \enquote{other}, and non-ASCII characters are active. As
-such, token-based comparisons are likely to fail unless set up properly.
+stored as active characters. In $8$-bit engines, non-ASCII characters are
+\enquote{active}, whilst other than the letters a--zA--Z, ASCII characters are
+\enquote{other}. In Unicode engines, non-ASCII codepoints will be either
+letters or \enquote{other}, based on the standard \LaTeX{} settings derived
+from Unicode data. For token-based comparisons, it is likely that the active
+spaces and tabs should be replaced: this can be done conveniently by expansion.
 
 \subsection{Typesetting verbatim-like material}
 

base/ltcmd.dtx

@@ -34,8 +34,8 @@
 %%% From File: ltcmd.dtx
 %
 %    \begin{macrocode}
-\def\ltcmdversion{v1.2f}
-\def\ltcmddate{2024-12-25}
+\def\ltcmdversion{v1.2g}
+\def\ltcmddate{2025-01-11}
 %    \end{macrocode}
 %
 %<*driver>
@@ -3663,20 +3663,37 @@
 % \end{macro}
 %
 % \begin{macro}{\@@_grab_v_aux_catcodes:}
+% \changes{v1.2g}{2025-01-11}{Store spaces and tabs as active chars}
 % \begin{macro}{\@@_grab_v_aux_abort:n}
 %   The approach for short verbatim arguments is to make the end-line
 %   character a macro parameter character: this is forbidden by the
 %   rest of the code. Then the error branch can check what caused the
 %   bail out and give the appropriate error message.
 %    \begin{macrocode}
+%<latexrelease>\IncludeInRelease{2025/06/01}{\@@_grab_v_aux_catcodes:}%
+%<latexrelease>  {Active~spaces~and~tabs}
 \cs_new_protected:Npn \@@_grab_v_aux_catcodes:
   {
     \cs_set_eq:NN \do \char_set_catcode_other:N
     \dospecials
+    \char_set_catcode_active:n { `\  }
+    \char_set_catcode_active:n { `\^^I }
     \bool_if:NTF \l_@@_long_bool
       { \char_set_catcode_other:n { \tex_endlinechar:D } }
       { \char_set_catcode_parameter:n { \tex_endlinechar:D } }
   }
+%<latexrelease>\EndIncludeInRelease
+%<latexrelease>\IncludeInRelease{2020/10/01}{\@@_grab_v_aux_catcodes:}%
+%<latexrelease>  {Active~spaces~and~tabs}
+%<latexrelease>\cs_new_protected:Npn \@@_grab_v_aux_catcodes:
+%<latexrelease>  {
+%<latexrelease>    \cs_set_eq:NN \do \char_set_catcode_other:N
+%<latexrelease>    \dospecials
+%<latexrelease>    \bool_if:NTF \l_@@_long_bool
+%<latexrelease>      { \char_set_catcode_other:n { \tex_endlinechar:D } }
+%<latexrelease>      { \char_set_catcode_parameter:n { \tex_endlinechar:D } }
+%<latexrelease>  }
+%<latexrelease>\EndIncludeInRelease
 \cs_new_protected:Npn \@@_grab_v_aux_abort:n #1
   {
     \@@_grab_v_group_end:
@@ -3703,26 +3720,38 @@
 %
 % \begin{macro}{\@@_grab_v_aux_put:N}
 % \changes{v1.2d}{2024/03/21}{Collect \cs{endlinechar} as \cs{obeyedline}}
-%   Storing one token in the collected argument. Most tokens are
-%   converted to category code $12$, with the exception of active
-%   characters, and spaces (not sure what should be done for those).
+% \changes{v1.2g}{2025-01-11}{Simplify catcode handling}
+%   Storing one token in the collected argument: everything as-is except
+%   for end-of-lines, with \cs{exp_not:N} to handle actives.
 %    \begin{macrocode}
-%<latexrelease>\IncludeInRelease{2024/06/01}{\@@_grab_v_aux_put:N}%
-%<latexrelease>  {Endlines~as~\obeyedline}
+%<latexrelease>\IncludeInRelease{2025-06-01}{\@@_grab_v_aux_put:N}%
+%<latexrelease>  {Use~more~std~catcodes}
 \cs_new_protected:Npn \@@_grab_v_aux_put:N #1
   {
     \tl_put_right:Nx \l_@@_v_arg_tl
       {
-        \token_if_active:NTF #1
+        \int_compare:nNnTF {`#1} = \tex_endlinechar:D
+          { \exp_not:N \obeyedline }
           { \exp_not:N #1 }
-          {
-            \int_compare:nNnTF {`#1} = \tex_endlinechar:D
-              { \exp_not:N \obeyedline }
-              { \token_to_str:N #1 }
-          }
       }
   }
 %<latexrelease>\EndIncludeInRelease
+%<latexrelease>\IncludeInRelease{2024/06/01}{\@@_grab_v_aux_put:N}%
+%<latexrelease>  {Endlines~as~\obeyedline}
+%<latexrelease>\cs_new_protected:Npn \@@_grab_v_aux_put:N #1
+%<latexrelease>  {
+%<latexrelease>    \tl_put_right:Nx \l_@@_v_arg_tl
+%<latexrelease>      {
+%<latexrelease>        \token_if_active:NTF #1
+%<latexrelease>          { \exp_not:N #1 }
+%<latexrelease>          {
+%<latexrelease>            \int_compare:nNnTF {`#1} = \tex_endlinechar:D
+%<latexrelease>              { \exp_not:N \obeyedline }
+%<latexrelease>              { \token_to_str:N #1 }
+%<latexrelease>          }
+%<latexrelease>      }
+%<latexrelease>  }
+%<latexrelease>\EndIncludeInRelease
 %<latexrelease>\IncludeInRelease{2020/10/01}{\@@_grab_v_aux_put:N}%
 %<latexrelease>  {Endlines~as~\obeyedline}
 %<latexrelease>\cs_new_protected:Npn \@@_grab_v_aux_put:N #1

base/testfiles-ltcmd/github-0876.tlg

@@ -1,48 +1,48 @@
 This is a generated file for the LaTeX2e validation system.
 Don't change this file in any respect.
 The token list contains the tokens:
->  b (the character b)
->  a (the character a)
->  r (the character r)
->    (blank space  )
->  b (the character b)
->  a (the character a)
->  r (the character r).
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r)
+>    (active character=macro:-> )
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r).
 <recently read> }
 l. ...bar+
          ^^M
 The token list contains the tokens:
->    (blank space  )
->  b (the character b)
->  a (the character a)
->  r (the character r)
+>    (active character=macro:-> )
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r)
 >  \obeyedline (control sequence=\protected macro:->\par )
->  b (the character b)
->  a (the character a)
->  r (the character r).
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r).
 <recently read> }
 l. ...bar+
          ^^M
 The token list contains the tokens:
->  b (the character b)
->  a (the character a)
->  r (the character r)
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r)
 >  \obeyedline (control sequence=\protected macro:->\par )
->  b (the character b)
->  a (the character a)
->  r (the character r).
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r).
 <recently read> }
 l. ...bar+
          ^^M
 The token list contains the tokens:
 >  \obeyedline (control sequence=\protected macro:->\par )
->  b (the character b)
->  a (the character a)
->  r (the character r)
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r)
 >  \obeyedline (control sequence=\protected macro:->\par )
->  b (the character b)
->  a (the character a)
->  r (the character r).
+>  b (the letter b)
+>  a (the letter a)
+>  r (the letter r).
 <recently read> }
 l. ...bar+
          ^^M

base/testfiles-ltcmd/ltcmd003.lvt

@@ -24,16 +24,10 @@
         I~got~'\token_to_str:N\foo
         \IfBooleanT #1 {*}
         \IfNoValueF {#2} {[\tl_to_str:n{#2}]}
-        -#3-
+        -[See~tokenlist~analysis~below]-
         \tl_to_str:n { {#4} }
       }
-    \IfNoValueF {#3}
-      {
-        \exp_args:No \tl_if_eq:nnF
-          { \tl_to_str:n {#3} }
-          {#3}
-          {\ERROR}
-      }
+    \tl_analysis_show:n {#3}
   }
 \foo+\foo+{}
 \foo+% ^^+^^+