Am Donnerstag, 23. Mai 2002 06:50 schrieb Denis B. Roegel:
> \begin{itemize} by \startitemize, etc. Many of these things could
> be automated, and I wonder if someone already wrote a script for that?Try the attached one. It's everything other than sophisticated or complete, but it does some nasty work. Gr��lis vom Hraban! -- http://www.fiee.net/texnique/ ---
#!/usr/bin/perl -w print "\nThis is HTML2ConTeXt. Version 2002-05-15\n"; print "I'll try to convert your HTML file for ConTeXt.\n"; print "copyleft Henning Hraban Ramm, http://www.fiee.net/texnique/\n\n";; unless ($ARGV[0]) {die "You must name a file to convert! $!"}; my $HTMLDatei = $ARGV[0]; unless (-T $HTMLDatei) { print "$HTMLDatei not found!\n"; if (-T $HTMLDatei.'.htm') { $HTMLDatei .= ".htm"; } if (-T $HTMLDatei.'.html') { $HTMLDatei .= ".html"; } } # unless $HTMLDatei =~ s/\\/\//g; my $Table="n"; my $Encod="win"; open (QUELLE, $HTMLDatei) or die "Can't open $HTMLDatei! $!"; my $TeXDatei = $HTMLDatei; $TeXDatei =~ s/\.htm$/\.tex/i; print $TeXDatei."\n"; open (ZIEL, ">".$TeXDatei) or die "Can't make $TeXDatei! $!"; while (<QUELLE>) { # single entities and chars s�&(.)uml;�\\\"$1�g; s�&(.)acute;�\\�$1�g; s�&(.)grave;�\\`$1�g; s�&(.)circ;�\\^$1�g; s�&(.)ring;�\\�$1�g; if ($Encod eq "win") { s�ß�ߧg; } else { s�ß�\\ss{}�g; } # if Encoding s�&(\#150|endash);�--�g; # endash s� - � -- �g; # endash s� �~�g; # non breaking space s�"([^<>]*)"�\\quotation{$1}�g; s�&(r|l)aquo;([^<>]*)&(l|r)aquo;�\\quotation{$2}�g; s�&\#132;([^<>]*)"�\\quotation{$1}�g; s�&\#132;([^<>]*)$�\\quotation{$1�g; # uncompleted line s�\s("|\")� \\quotation{�g; # begin quote s�"\s�} �g; # end quote s�"�\"�g; # quote s�([^\\=\s])\"�$1}�g; # end quote s�%�|~|\\%{}�g; # percent s�<�<�g; s�>�>�g; s�&�\&�g; s�&sup(.);�^$1�g; s�&frac(.)(.);�\\frac{$1}{$2}�g; s�&\#133;� �g; # s���g; # s���g; # TeX words and marks s�T<SUB>E</SUB>X�TeX�g; s�pdfTeX�\\pdfTeX{}�gi; s�ppchTeX�\\pdfTeX{}�gi; s�ConTeXt�\\ConTeXt{}�g; s�CONTEXT�\\ConTeXt{}�g; s�(\s)TeX�$1\\TeX{}�g; # environments s�<BODY[^<>]*>�\\starttext�gi; s�</BODY>�\\stoptext�gi; s�(<BLOCKQUOTE>|<QUOTE>)�\\startquotation�gi; s�(<\/BLOCKQUOTE>|<\/QUOTE>)�\\stopquotation�gi; s�</*DIV[^<>]*>��gi; # delete all divs s�</*FONT[^<>]*(>|$)��gi; # delete all font tags # Headers s�<H1>�\\chapter{�gi; s�<H2>�\\section{�gi; s�<H3>�\\subsection{�gi; s�<H4>�\\subsubsection{�gi; s�</H.>�}�gi; # Links s�<A\s(.*)HREF=\"(.*)\">(.*)</A>�\\goto{$3}[URL($2)]�gi; s�<A\s(.*)NAME=\"(.*)\">(.*)</A>�\\reference[$2]{$3}�gi; # Tables if ($Table eq "y") { s�<TABLE([^<>]*)>�\\bTABLE \%$1 �gi; s�</TABLE>�\\eTABLE�gi; s�</TD>�\\eTD �gi; s�<TD([^<>]*)>�\\bTD �gi; s�</TR>�\\eTR �gi; s�<TR([^<>]*)>�\\bTR �gi; } else { s�</*T(ABLE|D|R|BODY)[^<>]*>��gi; # delete all table tags } # if Table # Images s�<IMG\s([^<>]*)>�\\externalfigure[$1]�gi; s�<IMG\s([^"=]*)src=\"([^<>]*)\"([^<>]*)$�\\externalfigure[$2]\t\% $1 $3�gi; # Lists s�<UL>�\\startitemize\[1\]�gi; s�<OL>�\\startitemize\[n\]�gi; s�<DL>�\\startitemize\[1\]�gi; # ? s�</.L>�\\stopitemize�gi; s�<LI>�\\item �gi; s�<DT>�\\item �gi; # s�<DD>�\\item �gi; # s�</LI>��gi; s�<P[^<>]*>��gi; # s�</P>�\\par�gi; s�</P>�\n\n�gi; s�<BR[^<>]*>�\n�gi; s�<HR[^<>]*>�\\blank �gi; s�<(PRE|TT|CODE)>�\\type{�gi; s�<(STRONG|B)>�{\\bf �gi; s�<(EM|I|U)>�{\\em �gi; s�^</([^\s]*)>$�\\stop$1�gi; s�^<([^\s]*)([^<>]*)>$�\\start$1\[$2\]�gi; s�</.*>�}�gi; # all other closing tags become } s�<([^\s]*)(\s)(.*)>�\\$1\[$3\]\{�gi; # all other opening tags become { s�<([^\s]*)>�\\$1\{�gi; # all other opening tags become { s�^\s*��g; # remove trailing spaces print ZIEL; print "."; } # while print "\n"; close (ZIEL); close (QUELLE); # \goto{text}[URL(Link)]
#!/usr/bin/perl -w print "\nThis is LaTeX2ConTeXt. Version 2002-03-13\n"; print "I'll try to convert your LaTeX file for ConTeXt.\n"; print "copyleft Henning Hraban Ramm, http://www.fiee.net/texnique/\n\n";; unless ($ARGV[0]) {die "You must name a file to convert! $!"}; my $LaTeXDatei = $ARGV[0]; unless (-T $LaTeXDatei) { print "$LaTeXDatei not found!\n"; if (-T $LaTeXDatei.'.tex') { $LaTeXDatei .= ".tex"; } } # unless $LaTeXDatei =~ s/\\/\//g; rename ($LaTeXDatei, $LaTeXDatei.".bak"); open (QUELLE, $LaTeXDatei.".bak") or die "Can't open $LaTeXDatei! $!"; my $ConTeXtDatei = $LaTeXDatei; open (ZIEL, ">".$ConTeXtDatei) or die "Can't make $ConTeXtDatei! $!"; # Header (should be an extra file) print ZIEL "% interface=english output=pdftex\n"; print ZIEL "%D this \\ConTeXt\\ file is automatically converted from \\LaTeX.\n"; print ZIEL "\\enableregime[windows]\n"; print ZIEL "\\mainlanguage[de]\n"; print ZIEL "\\setupencoding[default=texnansi]\n"; print ZIEL "\n"; while (<QUELLE>) { # disable LaTeX header and some other commands s�^%!�%%% �; s�^(|\s)(\\document)(style|class)�%%% $2$3�g; s�^(|\s)(\\usepackage|\\setlength|\\addtolength|\\normalfont)�%%% $2�g; # s�^(|\s)(\\addtolength)�%%% $2�g; unless (m/^%/) { # if no comment line # raw convert environments s�\\begin{([^{}]*)}�\\start$1 �g; # \begin{environment} --> \startenvironment s�\\end{([^{}]*)}�\\stop$1 �g; # \end{environment} --> \stopenvironment s�\\begingroup�\\bgroup�g; s�\\endgroup�\\egroup�g; s�\\include(\s*){([^{}<>\[\]]*)}�\\input $2 �g; # \include{} --> \input # convert single commands s�\\newcommand�\\def�g; # \newcommand --> \def s�\\new(environment)(\s*){([^{}]*)}�\\define$1\[$3\]�g; # \newenvironment{} --> \defineenvironment[] s�\\label�\\reference�g; # \label --> \reference s�\\\\\*�\\\\�g; # \\* --> \\ s�\\(big|small)skip�\\blank\[$1\]�g; # \...skip --> \blank[...] s�\"`(.*)\"'�\\quote{$1}�g; s�``(.*)''�\\quotation{$1}�g; s�\\select(language){([^{}]*)}�\\$1\[$2\]�g; # \selectlanguage{lang} --> \language[lang] s�\\new(page)�\\$1�g; # \newpage --> \page s�\\(|this)pagestyle{empty}�\\setupheaders[state=stop]�g; s�\\(|this)pagestyle{([^{}]*)}�\\setupheaders[state=start] \% $2�g; s�\\areaset{([^{}]*)}{([^{}]*)}�\\setuplayout[width=$1, height=$2]�g; # s�LaTeX�ConTeXt�gi; # correct environments s�\\(start|stop)document�\\$1text�g; s�(\\startitemize)�$1\[1\]�g; s�\\(start|stop)enumeration�\\$1itemize[n]�g; s�\\(start|stop)(verbatim|alltt)�\\$1typing�g; s�\\(start|stop)verse�\\$1lines�g; s�\\(start|stop)center�\\$1centered�g; s�\\(start|stop)tabular(x*)�\\$1tabulate�g; s�\\(start|stop)long(table)�\\$1$2�g; s�\\(start|stop)multicols(\s*){(0-9)}�\\$1columns[n=$3]�g; s�\\twocolumn�\\startcolumns[n=2]�g; s�\\onecolumn�\\stopcolumns�g; # correct titles s�(\\part)(\**)�$1�g; # \part* --> \part s�\\chapter\*�\\title�g; s�\\(|sub)section\*�\\$1subject�g; s�\\paragraph�\\subsubsubsection�g; # s���g; # s���g; # correct tables s�(\\starttabulate)(\s*){([^{}]*)}�$1$2\[\|$3\|\]�g; s�&�\\NC �g; s�\\hline�\\HL�g; s�\\(top|bottom|mid)rule�\\HL�g; # correct typography s�\\verb(\||\+)([^\|]*)(\||\+)�\\type{$2}�g; s�\\verb�\\type�g; s�\\type{\\�\\tex{�g; s�\\texttt�\\type�g; s�\\emph{�{\\em �g; s�\\text(bf|sc|it|sl){�{\\$1 �g; s�\\(rm|ss|tt)family�\\switchtobodyfont\[$1\]�g; s�\\small �\\tfx �g; s�\\Small �\\tfxx �g; s�\\large �\\tfa �g; s�\\Large �\\tfb �g; } # unless comment line print ZIEL; print "."; } # while print "\n"; close (ZIEL); close (QUELLE);
