Listings: consistently colouring numbers

Question

I have been using this solution found here at LaTeX Stack Exchange for colouring numbers in my code excerpts:

\documentclass{article}
\usepackage{listings}
\usepackage{xcolor}

\makeatletter

%%% Copied from https://tex.stackexchange.com/a/500690/23765
% Some conditional tests
\def\@genericif#1{#1\expandafter\@firstoftwo\else\expandafter\@secondoftwo\fi}
\def\@ifdigit#1{\@genericif{\ifnum1<1\noexpand#1\relax}}
\def\@ifempty#1{\@genericif{\if\relax\detokenize{#1}\relax}}

% The main parsing macros
\def\parse@num#1{%
    \@ifempty{#1}%
        {\parse@num@false}%
        {\@genericif{\parsesign}%
            {\parse@num@sign#1{}\@end}%
            {\parse@num@dig#1{}\@end}%
        }%
}
% Parse sign
\def\parse@num@sign#1#2\@end{%
    \@genericif{\ifx\parse@num@minus#1}%
        {\@ifempty{#2}{\parse@num@false}{\parse@num@dig#2\@end}}%
        {\@genericif{\ifx\parse@num@plus#1}%
            {\@ifempty{#2}{\parse@num@false}{\parse@num@dig#2\@end}}%
            {\parse@num@dig#1#2\@end}%
        }%
}
% Parse first digit
\def\parse@num@dig#1#2\@end{%
    \@ifdigit{#1}%
        {\@ifempty{#2}{\parse@num@true}{\parse@num@digs#2\@end}}%
        {\parse@num@false}%
}
% Parse optional following digits
\def\parse@num@digs#1#2\@end{%
    \@ifdigit{#1}{%
        \@ifempty{#2}%
            {\parse@num@true}%
            {\parse@num@digs#2\@end}%
    }{%
        \@genericif{\parsefloat}{%
            \@genericif{\ifx\parse@num@point#1}%
                {\@ifempty{#2}{\parse@num@false}{\parse@num@decs#2\@end}}%
                {\parse@num@false}%
        }{\parse@num@false}%
    }%
}
% Parse decimal places
\def\parse@num@decs#1#2\@end{%
    \@ifdigit{#1}{%
        \@ifempty{#2}%
            {\parse@num@true}%
            {\parse@num@decs#2\@end}%
    }{\parse@num@false}%
}

% User interface
\newcommand\ifnumber[4][]{%
    \begingroup
    \let\parsesign=\iftrue
    \let\parsefloat=\iftrue
    \let\parse@num@minus=-%
    \let\parse@num@plus=+%
    \let\parse@num@point=.%
    #1%
    \def\parse@num@true{\endgroup#3}%
    \def\parse@num@false{\endgroup#4}%
    \parse@num{#2}%
}   


%%% Additions to the listings package
\lst@Key{numbersstyle}{}{\def\lst@numbersstyle{#1}}
\lst@Key{parsenumbers}{false}[t]{\lstKV@SetIf{#1}\lst@ifparsenumbers}

\lst@AddToHook{OutputOther}{%
    \lst@ifparsenumbers
        % Only if mode changes are not prohibited
        \lst@ifmode\else
            \expandafter\@hook@ifnumber\the\lst@token\@end
                {\let\lst@thestyle=\lst@numbersstyle}%
                {}%
        \fi
    \fi
}
\def\@hook@ifnumber#1#2\@end{%
    \@genericif{\ifx\lst@nolig#1}%
        {\@hook@ifnumber@{#2}}%
        {\@hook@ifnumber@{#1#2}}%
}
\def\@hook@ifnumber@{%
    \ifnumber[\expandafter\let\expandafter\parse@num@minus\csname lst@um-\endcsname]%
}

\makeatother

%%% Example document
\lstset{
    basicstyle = \ttfamily,
    identifierstyle = \color{blue},
    keywordstyle = \color{green!80!black},
    keywords = {foo},
    moredelim = [il][]{**},
    moredelim = [l][\color{gray}]{/},
    morestring = [d][\color{gray}]{"},
    morestring = *[d][\color{gray}\itshape]{!},
    morestring = **[d][\color{gray}\itshape]{?},
    % Apply new number coloring routine
    parsenumbers = true,
    numbersstyle = {\color{magenta}}
}

It works fairly well but unfortunately it also does have some issues. Appending this above my minimal example below...:

\begin{document}

\section{Python}

\begin{lstlisting}
def foobar(self):
    var = 123 + 456
    var_2 = 4.56
    var3 = 789
    for _ in range(3):
        print(test)
    if var_2 > 1.23:
        print(1024)
    elif (var3 <= 1000 and var_2 is None):
        print(0)
\end{lstlisting}

\section{Processing}

\begin{lstlisting}
void setup() {
  size(300, 300);
  background(0, 200, 0);
}

void draw() {
  drawFlower(150, 150, 100);
  for (int i = 0; i < 80; i = i+5) {
    line(30, i, 80, i);
  }
  x = x + 0.1;
  y = 0.1 + y;
  if (x > 1.23) {
    x = 0;
    y = 0 ;
  }
}
\end{lstlisting}

\end{document}

...results in:

The results are not bad, and it's particularly good that that solution handles numbers in variable names regardless if they are followed by an underline or not (e.g. var_2 and var3). But the example above also show a couple of problems which I have not been able to fix:

• It's possible to see that numbers preceded by a ( or immediately followed by ) are not coloured, e.g. range(3), size(300, 300)
• numbers touching signs such as commas, colons, or semicolons are not coloured either; e.g. the middle number in background(0, 200, 0);, or the numbers in x = x + 0.1; or if var_2 > 1.23:
• on the other hand, having spaces around them result in proper highlight, e.g. y = 0 ; (with space before semicolon) or the number 1000 in elif (var3 <= 1000 and var_2 is None):

Would anyone be able to help me tweak this snippet so that the numbers are consistently highlighted in these situations while still not being highlighted in variable and function names?

Edit: in a nutshell, I would like numbers to be highlighted if:

• they come after any of the following characters: , ., (, {,[, :
• they come before any of the following characters: , ., ), }, ], :, ;
• but definitely not include _ in either group as that might break the variable naming convention in many snippets of code (even though Python does accept _ in numbers to aid the visual identification of groups of 10^3, as in x = 1_000_000.

Currently, the code above only correctly identifies and . from all the characters mentioned in the bullet points above.

Edit: unfortunately minted is not an option for me, it does not play along well with my dissertation file.

Answer 1

Consider using minted and customize the stylesheets.

\documentclass{article}
\usepackage[T1]{fontenc}
\usepackage{minted}

\usemintedstyle{colorful}

\begin{document}

\begin{minted}{python}
def foobar(self):
    var = 123 + 456
    var_2 = 4.56
    var3 = 789
    for _ in range(3):
        print(test)
    if var_2 > 1.23:
        print(1024)
    elif (var3 <= 1000 and var_2 is None):
        print(0)
\end{minted}

\begin{minted}{c}
void setup() {
  size(300, 300);
  background(0, 200, 0);
}

void draw() {
  drawFlower(150, 150, 100);
  for (int i = 0; i < 80; i = i+5) {
    line(30, i, 80, i);
  }
  x = x + 0.1;
  y = 0.1 + y;
  if (x > 1.23) {
    x = 0;
    y = 0 ;
  }
}
\end{minted}

\end{document}

Answer 2

If I understood the question you want to color all digits unless they are in keywords or identifiers. You could do this by using as base font a font which has colored digits, and a different font for the keywords. With lualatex this here is possible:

\documentclass{article}
\usepackage{listings,xcolor}
\usepackage{fontspec}

\directlua{
 luaotfload.add_colorscheme("colordigits",
   {
    ["FF00FF"] = {"one","two","three","four","five","six","seven","eight","nine","zero"},
   })}

\newfontfamily\colordigits{Latin Modern Mono}[RawFeature={color=colordigits}]

\lstset{
    basicstyle = \colordigits,
    identifierstyle = \ttfamily\color{blue},
    keywordstyle = \ttfamily\color{green!80!black},
    keywords = {foo},
    moredelim = [il][]{**},
    moredelim = [l][\color{gray}]{/},
    morestring = [d][\color{gray}]{"},
    morestring = *[d][\color{gray}\itshape]{!},
    morestring = **[d][\color{gray}\itshape]{?},
}
%
\begin{document}

\begin{lstlisting}
def foobar(self):
    var = 123 + 456
    var_2 = 4.56
    var3 = 789
    for _ in range(3):
        print(test)
    if var_2 > 1.23:
        print(1024)
    elif (var3 <= 1000 and var_2 is None):
        print(0)
\end{lstlisting}

\section{Processing}

\begin{lstlisting}
void setup() {
  size(300, 300);
  background(0, 200, 0);
}

void draw() {
  drawFlower(150, 150, 100);
  for (int i = 0; i < 80; i = i+5) {
    line(30, i, 80, i);
  }
  x = x + 0.1;
  y = 0.1 + y;
  if (x > 1.23) {
    x = 0;
    y = 0 ;
  }
}
\end{lstlisting}

\end{document}

Answer 3

For completeness, a non-Lua solution using interchartoks in xetex fails at the last moment because lstlistings inserts glue between tokens. Glue is seen as an interword-boundary marker by interchartoks.

So not an answer (without a package re-write (using zero-width joiners?), even if the pdflatex scenario were surmountable.

To illustrate the transitions between token classes:

red is word-boundary to digit transition.

MWE

\documentclass{article}
\XeTeXinterchartokenstate=1
\usepackage{listings,xcolor}
\usepackage{fontspec}

\newXeTeXintercharclass\LetterClass

%from:
%https://tex.stackexchange.com/questions/411846/xelatex-minion-pro-and-italian-apostrophe-kerning/411850#411850
\makeatletter
\@tempcnta=`\A
\loop\unless\ifnum\@tempcnta>`\Z
  \XeTeXcharclass \@tempcnta \LetterClass
  \advance \@tempcnta by 1
\repeat
\@tempcnta=`\a
\loop\unless\ifnum\@tempcnta>`\z
  \XeTeXcharclass \@tempcnta \LetterClass
  \advance \@tempcnta by 1
\repeat
  \XeTeXcharclass `\_ \LetterClass


\makeatother


% char class for digits
\newXeTeXintercharclass \mydigitsclass
\XeTeXcharclass `\0 \mydigitsclass
\XeTeXcharclass `\1 \mydigitsclass
\XeTeXcharclass `\2 \mydigitsclass
\XeTeXcharclass `\3 \mydigitsclass
\XeTeXcharclass `\4 \mydigitsclass
\XeTeXcharclass `\5 \mydigitsclass
\XeTeXcharclass `\6 \mydigitsclass
\XeTeXcharclass `\7 \mydigitsclass
\XeTeXcharclass `\8 \mydigitsclass
\XeTeXcharclass `\9 \mydigitsclass

% def interchartokes

\XeTeXinterchartoks \LetterClass \mydigitsclass = {\begingroup\huge}
\XeTeXinterchartoks \mydigitsclass \LetterClass  = {\endgroup}

\XeTeXinterchartoks 0 \mydigitsclass = {\begingroup\color{green}}
\XeTeXinterchartoks \mydigitsclass 0  = {\endgroup}
\XeTeXinterchartoks 4095 \mydigitsclass = {\begingroup\color{red}}
\XeTeXinterchartoks \mydigitsclass 4095  = {\endgroup}


\lstset{
%    basicstyle = \colordigits,
    identifierstyle = \ttfamily\color{blue},
    keywordstyle = \ttfamily\color{green!80!black},
    keywords = {foo},
    moredelim = [il][]{**},
    moredelim = [l][\color{gray}]{/},
    morestring = [d][\color{gray}]{"},
    morestring = *[d][\color{gray}\itshape]{!},
    morestring = **[d][\color{gray}\itshape]{?},
}


\begin{document}
\XeTeXinterchartokenstate=0
\section{Test}
\XeTeXinterchartokenstate=1
abc 012 345 678 9 xyz


[The lstlisting environment adds "\textbackslash glue 0 plus 1fil minus 1fil" betweeen every token]

%https://tex.stackexchange.com/questions/281566/xetex-special-xetexcharclass-needed-for-null-glues/321664#321664
\XeTeXinterchartokenstate=0
\subsection{Inline}
\XeTeXinterchartokenstate=1
def foobar(self):
    var = 123 + 456
    var\_2 = 4.56
    var3 = 789
    for \_ in range(3):
        print(test)
    if var\_2 > 1.23:
        print(1024)

\XeTeXinterchartokenstate=0
\subsection{Verbatim}
\XeTeXinterchartokenstate=1
\begin{verbatim}
def foobar(self):
    var = 123 + 456
    var_2 = 4.56
    var3 = 789
    for _ in range(3):
        print(test)
    if var_2 > 1.23:
        print(1024)
\end{verbatim}

\XeTeXinterchartokenstate=0
\subsection{Listing}
\XeTeXinterchartokenstate=1
\begin{lstlisting}
def foobar(self):
    var = 123 + 456
    var_2 = 4.56
    var3 = 789
    for _ in range(3):
        print(test)
    if var_2 > 1.23:
        print(1024)
    elif (var3 <= 1000 and var_2 is None):
        print(0)
\end{lstlisting}

\XeTeXinterchartokenstate=0
\section{Processing}
\XeTeXinterchartokenstate=1

\begin{lstlisting}
void setup() {
  size(300, 300);
  background(0, 200, 0);
}

void draw() {
  drawFlower(150, 150, 100);
  for (int i = 0; i < 80; i = i+5) {
    line(30, i, 80, i);
  }
  x = x + 0.1;
  y = 0.1 + y;
  if (x > 1.23) {
    x = 0;
    y = 0 ;
  }
}
\end{lstlisting}


\end{document}