Created
April 18, 2012 15:30
-
-
Save dmerand/2414353 to your computer and use it in GitHub Desktop.
BASH/AWK/SED script to convert Dokuwiki to Latex format. Flawed in many ways, but functional
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#! /bin/sh | |
#doku-tex - take a dokuwiki/notational velocty syntax file, and convert it to latex | |
#author: donald l. merand | |
echo "\documentclass{article}" | |
echo "\pagestyle{empty}" | |
echo "\setlength{\parindent}{0pt}" | |
echo "\setlength{\parskip}{1ex plus 0.5ex minus 0.2ex}" | |
echo "\usepackage{ulem}" | |
echo "\usepackage[pdftex]{hyperref}" | |
echo "\hypersetup{colorlinks=true}" | |
echo "\setcounter{secnumdepth}{-1}" | |
echo "\\\begin{document}" | |
echo "" | |
awk ' | |
/^ [\*|-] / { | |
sub(/^ [\*|-] /, "\t\t\t\\item ") | |
if (list4) { print $0 } else { | |
list4 = 1 | |
print "\t\t\t\\begin{itemize}" | |
print $0 | |
} | |
next | |
} | |
list4 { | |
list4=0 | |
print "\t\t\t\\end{itemize}" | |
} | |
/^ [\*|-] / { | |
sub(/^ [\*|-] /, "\t\t\\item ") | |
if (list3) { print $0 } else { | |
list3 = 1 | |
print "\t\t\\begin{itemize}" | |
print $0 | |
} | |
next | |
} | |
list3 { | |
list3=0 | |
print "\t\t\\end{itemize}" | |
} | |
/^ [\*|-] / { | |
sub(/^ [\*|-] /, "\t\\item ") | |
if (list2) { print $0 } else { | |
list2 = 1 | |
print "\t\\begin{itemize}" | |
print $0 | |
} | |
next | |
} | |
list2 { | |
list2=0 | |
print "\t\\end{itemize}" | |
} | |
/^ [\*|-] / { | |
sub(/^ [\*|-] /, "\\item ") | |
if (list1) { print $0 } else { | |
list1 = 1 | |
print "\\begin{itemize}" | |
print $0 | |
} | |
next | |
} | |
list1 { | |
list1=0 | |
print "\\end{itemize}" | |
} | |
#default case | |
{ print } | |
#catch itemize at the end of the file | |
END { if (list1==1 || list2==2 || list3==2 || list==2) print "\\end{itemize}" } | |
' "$1" | | |
sed -e " | |
s/======\(.*\)======/\\\section{\1}/ | |
s/=====\(.*\)=====/\\\subsection{\1}/ | |
s/====\(.*\)====/\\\subsubsection{\1}/ | |
#remaining headers do not translate to latex. Just make them bold | |
s/==*\(.*\)==*/\\\textbf\{\1\}/g | |
#bold, underline, italic | |
s/\*\*\(.*\)\*\*/\\\textbf\{\1\}/g | |
s/__\(.*\)__/\\\underline\{\1\}/g | |
s|\/\/\(.*\)\/\/|\\\emph\{\1\}|g | |
#footnotes | |
s|((\(.*\)))|\\\footnote\{\1\}|g | |
#ellipses | |
s|\.\.\.|\\\ldots |g | |
#double-single quotes (remember LONGEST MATCH) | |
s|''\(.*\)''|\`\`\1''|g | |
#quote character | |
s|"\""\(.*\)"\""|\`\`\1''|g | |
#arrows | |
s|->|---|g | |
#underscores do not work unless escaped | |
s|\_|\\\_|g | |
#special cases for @done for strikethrough | |
s|item \(.*\)@done$|\\item \\\sout\{\1\}|g | |
s|\(.*\)@done$|\\\sout\{\1\}|g | |
#fractions, numbers | |
s| \([0-9][0-9]*\)/\([0-9][0-9]*\) | \$\\\frac\{\1\}\{\2\}\$ |g | |
s| \([0-9][0-9]*\) | \$\1\$ |g | |
s|\$ \$||g | |
#link. no special character at end. matches file:///syntax, and allows spaces as a result | |
s?\(https*:\/\/[-a-zA-Z0-9.&_=/\\\?]*[a-zA-Z0-9]\)? \\\url\{\1\}? | |
s?file:\/\/\/\([-a-zA-Z0-9 .\/\\]*\)? \\\url\{\/\1\}? | |
" | |
echo "\\end{document}" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment