% cprog.tex (or cprog.sty) - formatting of C programs
% By \'Eamonn McManus <emcmanus@cs.tcd.ie>.  This file is not copyrighted.
% $Id$

% This allows C programs to be formatted directly by TeX.  It can be
% invoked by \cprogfile{filename} or (in LaTeX) \begin{cprog} ...
% \end{cprog} or (in plain TeX) \cprog ... \end{cprog}.  In LaTeX, the
% alternative form \begin{cprog*} is allowed, where spaces in C strings
% are printed using the `square u' character (like LaTeX {verbatim*}).
% In plain TeX, you have to use \csname cprog*\endcsname for this (sorry).
% If you are using \cprogfile, say \cprogttspacetrue beforehand if you
% want this effect.

% The formatting is (necessarily) simple.  C text is set in a normal Roman
% font, comments in a slanted font, and strings in a typewriter font, with
% spaces optionally made visible as the `square u' symbol.  Tabs are
% expanded to four spaces (this does not look good when comments are
% aligned to the right of program text).  Some pairs of input characters
% appear as single output characters: << <= >> >= != -> are respectively
% TeX's \ll \le \gg \ge \ne \rightarrow.  Say \cprogpairsfalse to disable
% this.

% You can escape to TeX within cprog text by defining an escape character.
% The character @ is suitable for C and Pascal.  I have not tested other
% characters so they may interact badly with their existing definitions here.
% To define @ as the escape character, do \cprogescape@.  Then within text
% you can do @ followed by TeX commands.  These commands will be in a TeX
% group with the \catcodes of \{}% as normal.  The commands are terminated
% by a newline, which is not considered part of the program text.

% The fonts below can be changed to alter the setting of the various parts
% of the program.  The \cprogbaselineskip parameter can be altered to
% change the line spacing.  LaTeX's \baselinestretch is taken into account
% too.  The indentation applied to the whole program is \cprogindent,
% initially 0.  Before and after the program there are skips of
% \beforecprogskip and \aftercprogskip; the default values are \parskip
% and 0 respectively (since there will often be a \parskip after the
% program anyway).

% If the source text is Pascal or Modula-2, say \pascaltrue or \modulatrue
% (respectively) before formatting it.  This makes (* *) be recognised for
% comments instead of /* */.  Braces {} are also recognised for Pascal.
% \pascalfalse or \modulafalse as appropriate restores the default of C.

% This package works by making a large number of characters active.  Since
% even spaces are active, it is possible to examine the next character in
% a macro by making it a parameter, rather than using \futurelet as one
% would normally do.  This is more convenient, but the coding does mean
% that if the next character itself wants to examine a character it may
% look at a token from the macro rather than the input text.  I think that
% all cases that occur in practice have been looked after.

% The macros could still do with some work.  For example, the big macro
% defined with [] taking the place of {} could be recoded to use {} and so
% be more legible.  The internal macros etc should have @ in their names,
% and should be checked against LaTeX macros for clashes.

% Allow multiple inclusion to go faster.

\ifx\undefined\cprogsetup       % The whole file.

% Define the fonts used for program text, comments, and strings.
% Note that if \it is used for \ccommentfont, something will need to
% be done about $ signs, which come out as pounds sterling.
\let\ctextfont=\rm \let\ccommentfont=\sl \let\cstringfont=\tt

% Parameters.  Unfortunately \newdimen is \outer (\outerness is a mistake)
% so we need a subterfuge in case we are skipping the file.
\csname newdimen\endcsname\cprogbaselineskip \cprogbaselineskip=\baselineskip
\csname newdimen\endcsname\cprogindent \cprogindent=0pt
\csname newdimen\endcsname\cprogwidth % Gets default=\hsize when cprog invoked.
\csname newskip\endcsname\beforecprogskip \beforecprogskip=\parskip
\csname newskip\endcsname\aftercprogskip \aftercprogskip=0pt
\csname newif\endcsname\ifcprogttspace
\csname newif\endcsname\ifcprogpairs \cprogpairstrue
\csname newif\endcsname\ifpascal
\csname newif\endcsname\ifmodula        % Same as Pascal but no {comments}.
{\def\junk{\fi\fi\fi\fi}} % If skipping.

\let\cprogesc\relax
\begingroup \catcode`~=\active
\gdef\cprogescape#1{%
    {\catcode`~=\active \uccode`~=`#1 \aftergroup\cprogescont
     \uppercase{\aftergroup~}}}
\gdef\cprogescont#1{%
    \def\cprogesc{%
        \makeactive#1\def#1{%
           \begingroup \catcode`\\0 \catcode`{1 \catcode`}2 \catcode`\%14
           \catcode` 10 \clinegroup{}}}}
\endgroup

\def\makeactive#1{\catcode`#1=\active} \def\makeother#1{\catcode`#1=12}
{\obeyspaces\gdef\activespace{ } \obeylines\gdef\activecr{^^M}}
{\catcode`|=\catcode`\\ \makeactive\\ |gdef|activebackslash{\}}
{\catcode9=\active \gdef\activetab{^^I}}

% The following group makes many characters active, so that their catcodes
% in the \cprogchars macro are active, allowing them to be defined.  We
% could alternatively define more stuff like \activebackslash and use
% \expandafter or (carefully) \edef to expand these in the macro.
\begingroup
\catcode`[=\catcode`{ \catcode`]=\catcode`}
\makeactive! \makeactive" \makeactive' \makeactive( \makeactive* \makeactive-
\makeactive/ \makeactive< \makeactive> \makeactive? \makeactive^ \makeactive_
\makeactive\{ \makeactive| \makeactive\}
\gdef\activestar[*]
\gdef\cprogchars[%
    \makeother##\makeother$\makeother&\makeother\%\makeother^%
    \makeactive"\makeactive'\makeactive*\makeactive?\makeactive{\makeactive}%
    \makeactive}\makeactive\\\makeactive_\expandafter\makeactive\activetab%
    \makeactive!\makeactive<\makeactive>\makeactive-\makeactive|%
    \ifcprogpairs
      \def!##1[\ifx=##1$\ne$\else\string!\null##1\fi]%
      \def-##1[\ifx>##1$\rightarrow$\else$\string-$##1\fi]%
      % We use \aftergroup in < and > to deal with the fact that #1 might
      % itself examine the following character.
      \def<##1[[$\ifx<##1\ll$\else\ifx=##1\le$\else
        \ifx>##1\ifpascal\ne$\else\string<$\aftergroup>\fi
        \else \string<$\aftergroup##1\fi\fi\fi]]%
      \def>##1[[$\ifx>##1\gg$\else\ifx=##1\ge$\else
        \string>$\aftergroup##1\fi\fi]]%
    \else \def![\string!\null]% Avoid !` ligature.
      \def-[$\string-$]\def<[$\string<$]\def>[$\string>$]%
    \fi
    \def?[\string?\null]% Avoid ?` ligature.
    \def"[\cquote"[\tt\string"]]\def'[\cquote'[\tt\ttquote]]\def*[$\string*$]%
    \ifmodula \pascaltrue \fi   % Except that {...} is used for sets.
    \ifpascal
      \ifmodula \dulllbrace \else
        \def{[\begingroup \dulllbrace{\ccommentsetup\def}[\/\endgroup }]]%
      \fi \makeactive(\let(=\pascalcomment \makeactive^\def^[$\uparrow$]%
    \else \dulllbrace\makeactive/\let/=\ccomment
    \fi
    \def}[$\}$]\def|[$\string|$]\def~[$\sim$]\let_\_%
    \expandafter\def\activebackslash[$\backslash$]%
    \obeyspaces \expandafter\def\activespace[\leavevmode\space]%
    \expandafter\def\activetab[\ \ \ \ ]%
    \obeylines \expandafter\def\activecr[\strut\par]]
\gdef\cprogarg[\expandafter\def\activebackslash##1[\ifx##1e\let\next\cprogend
    \else$\backslash$\let\next##1\fi\next]\eatcr]
\gdef\cprogend nd#1{cprog#2}[\endcprogarg]      % #1 can be space, #2 *.
\gdef\dulllbrace[\def{[$\{$]]
\endgroup

\chardef\ttquote=13     % Undirected single quote.
\begingroup \makeactive" \makeactive' \makeactive!
\gdef\cquote#1#2{% #1 is the quote, " or ', #2 how to set it.
    \begingroup #2\cstringfont \makeactive\\%
    \ifpascal \makeother\\\makeother^%
    \else \expandafter\let\activebackslash\quotebackslash
    \fi
    \expandafter\edef\activespace{\ifcprogttspace\char`\ \else\ \fi}%
    \expandafter\let\activecr=\unclosedstring
    \def!{\string!\null}% No !` ligature.
    \makeother*\makeother-\makeother/\makeother<\makeother>%
    \makeother_\makeother\{\makeother\}\makeother|\makeother~%
    \ifx"#1\let'\ttquote \else \makeother"\fi
    \def#1{#2\endgroup}}
\endgroup
\csname newhelp\endcsname\cprogunclosedstr{%
A string or character constant earlier in the line was unclosed.^^JSo
I'm closing it now.}
\def\unclosedstring{%
    \escapechar-1%
    \errhelp\cprogunclosedstr
    \errmessage{Unclosed string}%
    \endgroup}
\newlinechar=`^^J
\def\quotebackslash#1{\char`\\%
    \expandafter\ifx\activecr#1\strut\par
    \else\if'\noexpand#1\ttquote\else\string#1\fi\fi}

% In a comment, we shrink the width of the opening / to that of a space so
% that the stars in multiline comments will line up.  We also shrink the
% closing * for symmetry, but not in Pascal where it looks nasty.
% Note that \end{cprog} is not recognised in strings or comments.
\def\spacebox#1{\leavevmode \hbox to \spaceskip{#1\hss}}

\begingroup \makeactive* \makeactive! \makeother/
\gdef\ccommentsetup{\ccommentfont \makeother-\makeother'\makeother"\makeother/%
     \def!{\string!\null}\expandafter\def\activebackslash{$\backslash$}}
\gdef\ccomment#1{%
     \let\next\relax
     \ifx#1*\bgroup \ccommentsetup
       \spacebox{\ctextfont\string/}*%
       \makeactive*\def*{\commentstar/}%
     \else\if\noexpand#1/\begingroup //\ccommentsetup \clinegroup\activecr
     \else \string/\let\next#1%
     \fi\fi\next}
\gdef\pascalcomment#1{%
     \ifx#1*\bgroup \ccommentsetup \let\next\dulllbrace \makeother(%
       \spacebox{\ctextfont\string(}*\makeactive*\def*{\commentstar)}%
     \else (\let\next#1\fi \next}
\obeylines \long\gdef\clinegroup#1#2^^M{#2\endgroup#1}%
\endgroup
\def\commentstar#1#2{%
    {\if#1\noexpand#2\egroup \ifpascal\else\aftergroup\spacebox\fi\fi}{$*$}#2}

% We usually have an active ^^M after \cprog or \begin{cprog}.
\def\eatcr#1{{\expandafter\ifx\activecr#1\else\aftergroup#1\fi}}

% Expand to stretch and shrink (plus and minus) of parameter #1.
\def\stretchshrink#1{\expandafter\eatdimenpart\the#1 \end}
\def\eatdimenpart#1 #2\end{#2}

\ifx\undefined\baselinestretch \def\baselinestretch{1}\fi

\def\cprogsetup{\ctextfont \cprogchars \parskip=0pt\stretchshrink\parskip
    \ifdim \cprogwidth=0pt \else \hsize\cprogwidth \fi
    \cprogesc \spaceskip\fontdimen2\font \xspaceskip\spaceskip
    \baselineskip=\baselinestretch\cprogbaselineskip \parindent=\cprogindent
    \vskip\beforecprogskip}
\def\endcprog{\endgroup \vskip\aftercprogskip}
\def\cprogfile#1{\begingroup \cprogsetup \input#1\endcprog}
\def\cprog{\begingroup \cprogttspacefalse \cprogsetup \cprogarg}
% Like {verbatim*}, {cprog*} uses `square u' for spaces in quoted strings.
\expandafter\def\csname cprog*\endcsname{%
        \begingroup \cprogttspacetrue \cprogsetup \cprogarg}
\expandafter\let\csname endcprog*\endcsname=\endcprog
% In LaTeX we need to call \end{cprog} properly to close the environment,
% whereas in plain TeX this will end the job.  The test for LaTeX is not
% bulletproof, but most plain TeX documents don't refer to the LaTeX logo.
\ifx\undefined\LaTeX \let\endcprogarg=\endcprog
\else \def\endcprogarg{\ifcprogttspace\end{cprog*}\else\end{cprog}\fi}
\fi

\fi     % \ifx\undefined\cprogsetup

\endinput