Capitalization in headings - a LaTeX3 approach

Question

In the early days of this site we had a question Automatically capitalize first letters of words in titles? with one solution. Since expl3 has matured well since then I have worked out a partial solution using expl3. It fails on a couple of exceptions and I am looking at ways to improve it.

\documentclass{article}
\usepackage{expl3,xparse}
\usepackage{hyperref}
\ExplSyntaxOn
\clist_gset:Nn \title_words_not_capitalized_en 
    { a, an, the, at, by, for, in, of, on, to, up, and, as, but, it, or, nor, do, for, this, be,  
    A, An, The, At, By, For, In, Of, On, To, Up, And, As, But, It, Or, Nor, Do, For, This, Be }

\cs_new:Npn \ucfirst_aux:w #1#2 \q_stop { \uppercase { #1 } #2 }

\cs_new:Npn \ucfirst #1 {
     \exp_after:wN \ucfirst_aux:w #1 \q_stop
}

\cs_new:Npn \lowerfirst #1 {
       \tex_lowercase:D {#1}
 }

\DeclareDocumentCommand\UppercaseTitle {s +m }
    {
      \IfBooleanTF { #1 } { {\bfseries {#2} } }
        {
            \seq_set_split:Nnn \g_tmpa_seq {~} {#2}
            \seq_use:Nn   \g_tmpa_seq {~}\\

            \seq_pop_left:NN \g_tmpa_seq \l_tmpa_tl  

            {\bfseries\ucfirst \l_tmpa_tl \space} 
            \seq_map_inline:Nn \g_tmpa_seq 
               {
                  \clist_if_in:NnTF \title_words_not_capitalized_en { ##1 }
                  { {\bfseries \lowerfirst {##1}~}} { {\bfseries \ucfirst{##1}~ } }    

               }            

       }    
    } 

\ExplSyntaxOff
\begin{document}
\tableofcontents
\parindent0pt

\section{\UppercaseTitle {The l3seq package Sequence and stacks}}

 \UppercaseTitle {Top ten things to do in Paris}\\
 \UppercaseTitle {How to use {\LaTeX} sequence lists effectively}\\
 \UppercaseTitle {Senate Votes to Confirm Elena Kagan For U.S. Supreme Court}\\
 \UppercaseTitle {what would be a ``correct'' capitalization for the title of this question?}\\
 \UppercaseTitle* {How about {$e=mc^2$}? }\\

 \end{document}

Exceptions are:

• fails to capitalize words in quotes.
• Has issues with maths
• Prefer not to bracket macros (not user friendly)
• Would fail on two or more sentence titles where the first word of the second sentence starts with an exception word.
• Exceptions such as "p-th root" of a "p-adic".

Comments on LaTeX3 coding are welcome. Still a rookie!

Answer 1

Joseph mentioned an implementation I cooked up at one point in time; here it is. Warning: this is pasted from an old email and may no longer function as intended :) I can't test (easily) while I'm at work…

Feel free to incorporate any ideas into your code, or to extend it, or to ignore it, all as you see fit! (One notable feature of this code is that it is expandable — or should be.)

\documentclass[a4paper]{article}
\usepackage{expl3}
\usepackage{etoolbox}

\begin{document}

\ExplSyntaxOn

% Make some commands engine-robust
\robustify\textbf

% Set up to exclude items from case changing
\tl_put_right:Nn \l_tl_case_change_exclude_tl { \NoChangeCase }
\cs_new:Npn \NoChangeCase #1 {#1}

% First split the input string into sentence chunks, where `sentence' means anything after . ? ! : etc.

\cs_new:Npn \titlecase #1
  {
    \tl_if_blank:nF {#1}
      { \titlecase_split_period:w #1 . \q_recursion_tail \q_recursion_stop }
  }

%% This is the basic idea of splitting:
%
%\cs_new:Npn \titlecase_split_period:w #1 . #2
%  {
%    \titlecase_split_colon:w #1 : \q_recursion_tail \q_recursion_stop
%    \quark_if_recursion_tail_stop:n {#2}
%    . \c_space_tl
%    \titlecase_split_period:w #2
%  }

% Use an obfuscated macro to avoid lengthy definitions:
\cs_new:Nn \titlecase_new_split_fn:NNNN
  {
    \cs_set:Npn #2 ##1 #1 ##2
      {
        #4 ##1 #3 \q_recursion_tail \q_recursion_stop
        \quark_if_recursion_tail_stop:n {##2}
        #1 \c_space_tl
        #2 ##2
      }

  }

% The reason to use an obfuscated macro is to pass in properly sanitised `characters':
% (Could possibly be done more easily with some clever expansion.)
\exp_after:wN \titlecase_new_split_fn:NNNN
\exp_after:wN .
\exp_after:wN \titlecase_split_period:w \token_to_str:N :
  \titlecase_split_colon:w
\exp_after:wN \titlecase_new_split_fn:NNNN
  \token_to_str:N : \titlecase_split_colon:w ! \titlecase_split_exclam:w
\titlecase_new_split_fn:NNNN ! \titlecase_split_exclam:w  ? \titlecase_split_question:w
\titlecase_new_split_fn:NNNN ? \titlecase_split_question:w  {~} \titlecase_first:w


%% These are the internals that do the processing of each word.

% The first and last words needs special attention;
% they should always be capitalised unless there's a special exception.
\cs_new:Npn \titlecase_firstlast:nn #1 #2
  {
    \titlecase_exact_exceptions:nn {#1} {#2}
    \tl_mixed_case:n {#1} #2
  }

\cs_new:Npn \titlecase_middle:nn #1 #2
  {
    \titlecase_exact_exceptions:nn {#1} {#2} % catch exact matches which will never change
    \titlecase_lc_exceptions:nn {#1} {#2} % catch words that should be lowercase
    \tl_mixed_case:n {#1} #2 % otherwise capitalise normally
  }


%% After all the splitting, we now enter the word-by-word titlecasing.

\cs_new:Npn \titlecase_first:w #1 ~ #2
  {
    \tl_if_blank:nT {#1} { \quark_if_recursion_tail_stop:n {#2} }
    \titlecase_catch_punct:Nn \titlecase_firstlast:nn {#1}
    \use_none_delimit_by_q_nil:w
    \q_nil
    \quark_if_recursion_tail_stop:n {#2}
    \c_space_tl
    \titlecase:w #2
  }

% The regular loop:
\cs_new:Npn \titlecase:w #1 ~ #2
  {
    \quark_if_recursion_tail_stop_do:nn {#2}
      {
        \titlecase_catch_punct:Nn \titlecase_firstlast:nn {#1}
        \use_none_delimit_by_q_nil:w
        \q_nil
      }

    \titlecase_catch_punct:Nn \titlecase_middle:nn {#1}
    \use_none_delimit_by_q_nil:w
    \q_nil
    \c_space_tl
    \titlecase:w #2
  }

\cs_new:Npn \__tl_last:n #1
  {
    \__tl_last:w #1 \q_recursion_tail \q_recursion_tail \q_recursion_stop
  }
\cs_new:Npn \__tl_last:w #1 #2
  {
    \quark_if_recursion_tail_stop_do:nn {#2} {#1}
    \__tl_last:w #2
  }

\cs_new:Npn \titlecase_catch_punct:Nn #1 #2
  {
    \str_if_eq_x:nnT { \__tl_last:n {#2} } {,}
      {
        \exp_args:No #1 { \titlecase_catch_comma:w #2 }{,}
        \use_none_delimit_by_q_nil:w
      }
    \str_if_eq_x:nnT { \__tl_last:n {#2} } {;}
      {
        \exp_args:No #1 { \titlecase_catch_semicolon:w #2 }{;}
        \use_none_delimit_by_q_nil:w
      }
    #1 {#2}
  }

\typeout{ LAST:~\__tl_last:n {foo bar .}}
\cs_new:Npn \titlecase_catch_comma:w #1, {#1}
\cs_new:Npn \titlecase_catch_semicolon:w #1; {#1}

% The exception catching functions contain series of functions like the following to match and if so jump to the end after their specific processing.

\cs_new:Npn \titlecase_exception:nnn #1 #2 #3
  {
    \str_if_eq_x:nnT { \tl_lower_case:n {#1} } {#3}
      { \tl_lower_case:n {#1} #2 \use_none_delimit_by_q_nil:w }
  }

\cs_new:Npn \titlecase_exact_exception:nnn #1 #2 #3
  {
    \str_if_eq:nnT {#1} {#3}
      { #1 #2 \use_none_delimit_by_q_nil:w }
  }

% These are the functions to define the exception catching functions.

\cs_new:Npn \titlecase_set_small_exceptions:n #1
  {
    \seq_set_from_clist:Nn \l_titlecase_seq {#1}
    \cs_set:Npx \titlecase_lc_exceptions:nn ##1 ##2
      {
        \seq_map_function:NN \l_titlecase_seq \titlecase_small_except:n
      }
  }

\cs_new:Npn \titlecase_set_exact_exceptions:n #1
  {
    \seq_set_from_clist:Nn \l_titlecase_seq {#1}
    \cs_set:Npx \titlecase_exact_exceptions:nn ##1 ##2
      {
        \seq_map_function:NN \l_titlecase_seq \titlecase_exact_except:n
      }
  }

\cs_new:Npn \titlecase_small_except:n #1
  {
    \exp_not:N \titlecase_exception:nnn {\exp_not:N ## 1} {\exp_not:N ## 2} {#1}
  }

\cs_new:Npn \titlecase_exact_except:n #1
  {
    \exp_not:N \titlecase_exact_exception:nnn {\exp_not:N ## 1} {\exp_not:N ## 2} {#1}
  }

\titlecase_set_small_exceptions:n {a,an,and,as,at,but,by,en,for,if,in,of,on,or,the,to,v,via,vs}
\titlecase_set_exact_exceptions:n {TV,iTunes,iPhone}% an example only

\ExplSyntaxOff

\def\TCTEST#1{{\titlecase{#1}}\par\bigskip}
%\def\TCTEST#1{\typeout{\titlecase{#1}}}

\TCTEST{Modern words like \NoChangeCase{\textbf{iPhone}} and iTunes, \NoChangeCase{eyeTV}, and even just TV are annoying}
\TCTEST{This is a sentence. But this is capitalised.}
\TCTEST{iTunes, here to stay like iPhone}
\TCTEST{Hello friends of the world, whom I am also friends of}
\TCTEST{}
\TCTEST{ }
\TCTEST{and}
\TCTEST{and and}
\TCTEST{and and and}
\TCTEST{This Was All Capitalised But Some Words Shouldn't Be If They're Small}
\TCTEST{Colon test: An example of an exception}
\TCTEST{A Question? An answer?}
\TCTEST{A Question! An answer!}
\TCTEST{iTunes and TV}
\TCTEST{David v Goliath and Goliath vs Mittelbach}
\TCTEST{Hard to say whether `quotes are too hard'}

\ExplSyntaxOn
\typeout{ [This~ is~ plain~ title_case~ with~ quotes]~ \tl_mixed_case:n {`Hello'} }

[This~ is~ plain~ title_case~ with~ quotes]~ \tl_mixed_case:n {`Hello'}

\par\bigskip [This~ is~ plain~ title_case~ with~ braces]~ \tl_mixed_case:n {{`Hello'}}

\par\bigskip [This~ is~ plain~ title_case~ with~ bold]~ \tl_mixed_case:n {\textbf{`Hello'}}

\par\bigskip [This~ is~ plain~ title_case~ with~ bold~ and~ braces]~ \tl_mixed_case:n {{\textbf{`Hello'}}}

\ExplSyntaxOff

\end{document}