Latex to MS Word tests

!Latex to MS Word tests

Hack file to get a nicer Gist name

.gitignore

## Temporary OS files
.DS_Store

## Core latex/pdflatex auxiliary files:
*.aux
*.lof
*.log
*.lot
*.fls
*.out
*.toc
*.fmt
*.fot
*.cb
*.cb2
.*.lb

## Intermediate documents:
*.dvi
*.xdv
*-converted-to.*
# these rules might exclude image files for figures etc.
# *.ps
# *.eps
# *.pdf

## Generated if empty string is given at "Please type another file name for output:"
.pdf

## Bibliography auxiliary files (bibtex/biblatex/biber):
*.bbl
*.bcf
*.blg
*-blx.aux
*-blx.bib
*.run.xml

## Build tool auxiliary files:
*.fdb_latexmk
*.synctex
*.synctex(busy)
*.synctex.gz
*.synctex.gz(busy)
*.pdfsync

## Build tool directories for auxiliary files
# latexrun
latex.out/

## Auxiliary and intermediate files from other packages:
# algorithms
*.alg
*.loa

# achemso
acs-*.bib

# amsthm
*.thm

# beamer
*.nav
*.pre
*.snm
*.vrb

# changes
*.soc

# comment
*.cut

# cprotect
*.cpt

# elsarticle (documentclass of Elsevier journals)
*.spl

# endnotes
*.ent

# fixme
*.lox

# feynmf/feynmp
*.mf
*.mp
*.t[1-9]
*.t[1-9][0-9]
*.tfm

#(r)(e)ledmac/(r)(e)ledpar
*.end
*.?end
*.[1-9]
*.[1-9][0-9]
*.[1-9][0-9][0-9]
*.[1-9]R
*.[1-9][0-9]R
*.[1-9][0-9][0-9]R
*.eledsec[1-9]
*.eledsec[1-9]R
*.eledsec[1-9][0-9]
*.eledsec[1-9][0-9]R
*.eledsec[1-9][0-9][0-9]
*.eledsec[1-9][0-9][0-9]R

# glossaries
*.acn
*.acr
*.glg
*.glo
*.gls
*.glsdefs
*.lzo
*.lzs

# uncomment this for glossaries-extra (will ignore makeindex's style files!)
# *.ist

# gnuplottex
*-gnuplottex-*

# gregoriotex
*.gaux
*.gtex

# htlatex
*.4ct
*.4tc
*.idv
*.lg
*.trc
*.xref

# hyperref
*.brf

# knitr
*-concordance.tex
# TODO Comment the next line if you want to keep your tikz graphics files
*.tikz
*-tikzDictionary

# listings
*.lol

# luatexja-ruby
*.ltjruby

# makeidx
*.idx
*.ilg
*.ind

# minitoc
*.maf
*.mlf
*.mlt
*.mtc[0-9]*
*.slf[0-9]*
*.slt[0-9]*
*.stc[0-9]*

# minted
_minted*
*.pyg

# morewrites
*.mw

# nomencl
*.nlg
*.nlo
*.nls

# pax
*.pax

# pdfpcnotes
*.pdfpc

# sagetex
*.sagetex.sage
*.sagetex.py
*.sagetex.scmd

# scrwfile
*.wrt

# sympy
*.sout
*.sympy
sympy-plots-for-*.tex/

# pdfcomment
*.upa
*.upb

# pythontex
*.pytxcode
pythontex-files-*/

# tcolorbox
*.listing

# thmtools
*.loe

# TikZ & PGF
*.dpth
*.md5
*.auxlock

# todonotes
*.tdo

# vhistory
*.hst
*.ver

# easy-todo
*.lod

# xcolor
*.xcp

# xmpincl
*.xmpi

# xindy
*.xdy

# xypic precompiled matrices and outlines
*.xyc
*.xyd

# endfloat
*.ttt
*.fff

# Latexian
TSWLatexianTemp*

## Editors:
# WinEdt
*.bak
*.sav

# Texpad
.texpadtmp

# LyX
*.lyx~

# Kile
*.backup

# gummi
.*.swp

# KBibTeX
*~[0-9]*

# TeXnicCenter
*.tps

# auto folder when using emacs and auctex
./auto/*
*.el

# expex forward references with \gathertags
*-tags.tex

# standalone packages
*.sta

# Makeindex log files
*.lpz

# REVTeX puts footnotes in the bibliography by default, unless the nofootinbib
# option is specified. Footnotes are the stored in a file with suffix Notes.bib.
# Uncomment the next line to have this generated file ignored.
#*Notes.bib

build_script.sh

#!/usr/bin/env sh

export clean_ext="aux bbl blg brf idx ilg ind lof log lol lot out toc synctex.gz fdb_latexmk fls dvi 4ct 4tc idv lg tmp xref"
export image_ext="ext png eps jpg jpeg"

# See https://github.com/michal-h21/make4ht/issues/6
for ext in $image_ext; do
     if [ -n "$(ls -A *.$ext 2> /dev/null)" ]; then
          #echo "has $ext files"
          for file in *.$ext; do
               echo "running: ebb -x $file"	
               ebb -x $file
          done
     fi
done

latexmk -pdf sample
mv sample.pdf sample-latexmk.pdf

for ext in $clean_ext; do
     echo "running:rm -f *.$ext"
     rm -f *.$ext
done

# pandoc can't take pdf as input
#pandoc -s sample-latexmk.pdf -o sample-latexmkpdf_pandoc.docx

pandoc -s sample.tex --bibliography samplebibliography.bib --filter pandoc-citeproc -o sample-tex2word_pandoc.docx

make4ht -uf html5+latexmk_build+tidy -c tex4ht.cfg sample.tex
mv sample.html sample-make4ht.html
pandoc -s sample-make4ht.html -c sample.css -o sample-make4ht_then_pandoc.docx

for ext in $clean_ext; do
     echo "running:rm -f *.$ext"
     rm -f *.$ext
done

make4ht -uf html5+latexmk_build+tidy -c tex4ht_no_css.cfg sample.tex
mv sample.html sample-make4ht_no_css.html
pandoc -s sample-make4ht_no_css.html -o sample-make4ht_no_css_then_pandoc.docx

for ext in $clean_ext; do
     echo "running:rm -f *.$ext"
     rm -f *.$ext
done

sample-image.png

sample.tex

\documentclass[pmlr]{jmlr}

% The following packages will be automatically loaded:
% jmlr, amsmath, amssymb, natbib, graphicx, url, algorithm2e
% ifoddpage, relsize and probably more
% make sure they are installed with your latex distribution

\usepackage{esvect}

\usepackage{mwe} % to get dummy images
\jmlrvolume{-- Under Review}
\jmlryear{2020}
\jmlrworkshop{Full Paper -- MIDL 2020 submission}
\editors{Under Review for MIDL 2020}

\title[Short Title]{Full Title of Article}

% Two authors with the same address
\author{\Name{Author Name1} \Email{abc@sample.edu}\and
\Name{Author Name2} \Email{xyz@sample.edu}\\
\addr Address}

\begin{document}

\maketitle

\begin{abstract}
This is a great paper and it has a concise abstract.
\end{abstract}

\begin{keywords}
List of keywords, comma separated.
\end{keywords}

\section{Introduction}

This is where the content of your paper goes.  Some random
notes:
% \footnote{Random footnote are discouraged}:
\begin{itemize}
\item You should use {\LaTeX} \cite{Lamport:Book:1989}.
\item JMLR/PMLR uses natbib for references. For simplicity, here, \verb|\cite|  defaults to
  parenthetical citations, i.e. \verb|\citep|. You can of course also
  use \verb|\citet| for textual citations.
\item You should follow the guidelines provided by the conference.
\item Read through the JMLR template documentation for specific \LaTeX
  usage questions.
\item Note that the JMLR template provides many handy functionalities
such as \verb|\figureref| to refer to a figure,
e.g. \figureref{fig:example},  \verb|\tableref| to refer to a table,
e.g. \tableref{tab:example} and \verb|\equationref| to refer to an equation,
e.g. \equationref{eq:example}.
\end{itemize}

\begin{table}[htbp]
 % The first argument is the label.
 % The caption goes in the second argument, and the table contents
 % go in the third argument.
\floatconts
  {tab:example}%
  {\caption{An Example Table}}%
  {\begin{tabular}{ll}
  \bfseries Dataset & \bfseries Result\\
  Data1 & 0.12345\\
  Data2 & 0.67890\\
  Data3 & 0.54321\\
  Data4 & 0.09876
  \end{tabular}}
\end{table}

\begin{figure}[htbp]
 % Caption and label go in the first argument and the figure contents
 % go in the second argument
\floatconts
  {fig:example}
  {\caption{Example Image}}
  {\includegraphics[width=0.5\linewidth]{sample-image}}
\end{figure}

\begin{algorithm2e}
\caption{Computing Net Activation}
\label{alg:net}
 % older versions of algorithm2e have \dontprintsemicolon instead
 % of the following:
 %\DontPrintSemicolon
 % older versions of algorithm2e have \linesnumbered instead of the
 % following:
 %\LinesNumbered
\KwIn{$x_1, \ldots, x_n, w_1, \ldots, w_n$}
\KwOut{$y$, the net activation}
$y\leftarrow 0$\;
\For{$i\leftarrow 1$ \KwTo $n$}{
  $y \leftarrow y + w_i*x_i$\;
}
\end{algorithm2e}



% Testing math from http://www.maths.adelaide.edu.au/anthony.roberts/LaTeX/Src/maths.tex
\section{Math example from Tony Roberts}

See \url{http://www.maths.adelaide.edu.au/anthony.roberts/LaTeX/Src/maths.tex}.

\section{Delimiters}

See how the delimiters are of reasonable size in these examples
\[
	\left(a+b\right)\left[1-\frac{b}{a+b}\right]=a\,,
\]
\[
	\sqrt{|xy|}\leq\left|\frac{x+y}{2}\right|,
\]
even when there is no matching delimiter
\[
	\int_a^bu\frac{d^2v}{dx^2}\,dx
	=\left.u\frac{dv}{dx}\right|_a^b
	-\int_a^b\frac{du}{dx}\frac{dv}{dx}\,dx.
\]






\section{Spacing}

Differentials often need a bit of help with their spacing as in
\[
	\iint xy^2\,dx\,dy 
	=\frac{1}{6}x^2y^3,
\]
whereas vector problems often lead to statements such as
\[
	u=\frac{-y}{x^2+y^2}\,,\quad
	v=\frac{x}{x^2+y^2}\,,\quad\text{and}\quad
	w=0\,.
\]
Occasionally one gets horrible line breaks when using a list in mathematics such as listing the first twelve primes  \(2,3,5,7,11,13,17,19,23,29,31,37\)\,.
In such cases, perhaps include \verb|\mathcode`\,="213B| inside the inline maths environment so that the list breaks: \(\mathcode`\,="213B 2,3,5,7,11,13,17,19,23,29,31,37\)\,.
Be discerning about when to do this as the spacing is different.






\section{Arrays}

Arrays of mathematics are typeset using one of the matrix environments as 
in
\[
	\begin{bmatrix}
		1 & x & 0 \\
		0 & 1 & -1
	\end{bmatrix}\begin{bmatrix}
		1  \\
		y  \\
		1
	\end{bmatrix}
	=\begin{bmatrix}
		1+xy  \\
		y-1
	\end{bmatrix}.
\]
Case statements use cases:
\[
	|x|=\begin{cases}
		x, & \text{if }x\geq 0\,,  \\
		-x, & \text{if }x< 0\,.
	\end{cases}
\]
Many arrays have lots of dots all over the place as in
\[
	\begin{matrix}
		-2 & 1 & 0 & 0 & \cdots & 0  \\
		1 & -2 & 1 & 0 & \cdots & 0  \\
		0 & 1 & -2 & 1 & \cdots & 0  \\
		0 & 0 & 1 & -2 & \ddots & \vdots \\
		\vdots & \vdots & \vdots & \ddots & \ddots & 1  \\
		0 & 0 & 0 & \cdots & 1 & -2
	\end{matrix}
\]






\section{Equation arrays}

In the flow of a fluid film we may report
\begin{eqnarray}
	u_\alpha & = & \epsilon^2 \kappa_{xxx} 
	\left( y-\frac{1}{2}y^2 \right),
	\label{equ}  \\
	v & = & \epsilon^3 \kappa_{xxx} y\,,
	\label{eqv}  \\
	p & = & \epsilon \kappa_{xx}\,.
	\label{eqp}
\end{eqnarray}
Alternatively, the curl of a vector field $(u,v,w)$ may be written 
with only one equation number:
\begin{eqnarray}
	\omega_1 & = &
	\frac{\partial w}{\partial y}-\frac{\partial v}{\partial z}\,,
	\nonumber  \\
	\omega_2 & = & 
	\frac{\partial u}{\partial z}-\frac{\partial w}{\partial x}\,,
	\label{eqcurl}  \\
	\omega_3 & = & 
	\frac{\partial v}{\partial x}-\frac{\partial u}{\partial y}\,.
	\nonumber
\end{eqnarray}
Whereas a derivation may look like
\begin{eqnarray*}
	(p\wedge q)\vee(p\wedge\neg q) & = & p\wedge(q\vee\neg q)
	\quad\text{by distributive law}  \\
	 & = & p\wedge T \quad\text{by excluded middle}  \\
	 & = & p \quad\text{by identity}
\end{eqnarray*}






\section{Functions}

Observe that trigonometric and other elementary functions are typeset 
properly, even to the extent of providing a thin space if followed by 
a single letter argument:
\[
	\exp(i\theta)=\cos\theta +i\sin\theta\,,\quad
	\sinh(\log x)=\frac{1}{2}\left( x-\frac{1}{x} \right).
\]
With sub- and super-scripts placed properly on more complicated 
functions,
\[
	\lim_{q\to\infty}\|f(x)\|_q 
	=\max_{x}|f(x)|,
\]
and large operators, such as integrals and
\begin{eqnarray*}
	e^x & = & \sum_{n=0}^\infty \frac{x^n}{n!}
	\quad\text{where }n!=\prod_{i=1}^n i\,,  \\
	\overline{U_\alpha} & = & \bigcap_\alpha U_\alpha\,.
\end{eqnarray*}
In inline mathematics the scripts are correctly placed to the side in 
order to conserve vertical space, as in
\(
	1/(1-x)=\sum_{n=0}^\infty x^n.
\)






\section{Accents}

Mathematical accents are performed by a short command with one 
argument, such as
\[
	\tilde f(\omega)=\frac{1}{2\pi}
	\int_{-\infty}^\infty f(x)e^{-i\omega x}\,dx\,,
\]
or
\[
	\dot{\vec \omega}=\vec r\times\vec I\,.
\]





\section{Command definition}

\newcommand{\Ai}{\operatorname{Ai}} 
The Airy function, $\Ai(x)$, may be incorrectly defined as this 
integral
\[
	\Ai(x)=\int\exp(s^3+isx)\,ds\,.
\]

\newcommand{\D}[2]{\frac{\partial #2}{\partial #1}}
\newcommand{\DD}[2]{\frac{\partial^2 #2}{\partial #1^2}}
\renewcommand{\vec}[1]{\boldsymbol{#1}}

This vector identity serves nicely to illustrate two of the new 
commands:
\[
	\vec\nabla\times\vec q
	=\vec i\left(\D yw-\D zv\right)
	+\vec j\left(\D zu-\D xw\right)
	+\vec k\left(\D xv-\D yu\right).
\]

Recall that typesetting multi-line mathematics is an art normally too hard for computer recipes.  Nonetheless, if you need to be automatically flexible about multi-line mathematics, and you do not mind some rough typesetting, then perhaps invoke \verb|\parbox| to help as follows: 
% The \verb|breqn| package is not yet reliable enough for general use.
\newcommand{\parmath}[2][0.8\linewidth]{\parbox[t]{#1}%
    {\raggedright\linespread{1.2}\selectfont\(#2\)}}
\[
u_1=\parmath{ -2 \gamma  \epsilon^{2} s_{2}+\mu  \epsilon^{3} \big( \frac{3}{8} s_{2}+\frac{1}{8} s_{1} i\big)+\epsilon^{3} \big( -\frac{81}{32} s_{4} s_{2}^{2}-\frac{27}{16} s_{4} s_{2} s_{1} i+\frac{9}{32} s_{4} s_{1}^{2}+\frac{27}{32} s_{3} s_{2}^{2} i-\frac{9}{16} s_{3} s_{2} s_{1}-\frac{3}{32} s_{3} s_{1}^{2} i\big) +\int_a^b 1-2x+3x^2-4x^3\,dx }
\]
Also, sometimes use \verb|\parbox| to typeset multiline entries in tables.


\section{Theorems et al.}

%\newtheorem{theorem}{Theorem}
%\newtheorem{corollary}[theorem]{Corollary}
%\newtheorem{lemma}[theorem]{Lemma}
%\newtheorem{definition}[theorem]{Definition}

\begin{definition}[right-angled triangles] \label{def:tri}
A \emph{right-angled triangle} is a triangle whose sides of length~\(a\), \(b\) and~\(c\), in some permutation of order, satisfies \(a^2+b^2=c^2\).
\end{definition}

\begin{lemma} 
The triangle with sides of length~\(3\), \(4\) and~\(5\) is right-angled.
\end{lemma}

This lemma follows from the Definition~\ref{def:tri} as \(3^2+4^2=9+16=25=5^2\).

\begin{theorem}[Pythagorean triplets] \label{thm:py}
Triangles with sides of length \(a=p^2-q^2\), \(b=2pq\) and \(c=p^2+q^2\) are right-angled triangles.
\end{theorem}

Prove this Theorem~\ref{thm:py} by the algebra \(a^2+b^2 =(p^2-q^2)^2+(2pq)^2
=p^4-2p^2q^2+q^4+4p^2q^2
=p^4+2p^2q^2+q^4
=(p^2+q^2)^2 =c^2\).


% Acknowledgments---Will not appear in anonymized version
\acks{We thank a bunch of people.}


\bibliography{samplebibliography}


\appendix

\section{Proof of Theorem 1}

This is a boring technical proof of
\begin{equation}\label{eq:example}
\cos^2\theta + \sin^2\theta \equiv 1.
\end{equation}

\section{Proof of Theorem 2}

This is a complete version of a proof sketched in the main text with
some inline math $\cos^2\theta + \sin^2\theta \equiv 1$ and $\vv{AB}$.

\end{document}

samplebibliography.bib

@book{Lamport:Book:1989,
 author = {Lamport, Leslie},
 title = {Latex: A Document Preparation System},
 year = {1986},
 isbn = {0-201-15790-X},
 publisher = {Addison-Wesley Longman Publishing Co., Inc.},
 address = {Boston, MA, USA},
}

tex4ht.cfg

\Preamble{xhtml,mathml,mathjax,fn-in}

\begin{document}

\EndPreamble

tex4ht_no_css.cfg

\Preamble{xhtml,mathml,mathjax,fn-in,NoFonts,-css}

% Provide configurations for em and textit, as they are by default dealt only by css
% See https://tex.stackexchange.com/questions/70059/generation-of-simple-css-less-html-with-htlatex/70061#70061
\Configure{emph}{\ifvmode\ShowPar\fi\HCode{<em>}}{\HCode{</em>}}
\Configure{textbf}{\ifvmode\ShowPar\fi\HCode{<b>}}{\HCode{</b>}}

\begin{document}

\EndPreamble