From mboxrd@z Thu Jan 1 00:00:00 1970 X-Msuck: nntp://news.gmane.io/gmane.comp.tex.context/8517 Path: main.gmane.org!not-for-mail From: Henning Hraban Ramm Newsgroups: gmane.comp.tex.context Subject: Re: Converting to ConTeXt from other formats Date: Mon, 1 Jul 2002 19:06:43 +0200 Sender: owner-ntg-context@let.uu.nl Message-ID: <200207011906.43561.angerweit@gmx.net> References: <20020701154125.38069.qmail@web10005.mail.yahoo.com> NNTP-Posting-Host: coloc-standby.netfonds.no Mime-Version: 1.0 Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_77YKRN4H8AL2QBR0QL0F" X-Trace: main.gmane.org 1035398913 28178 80.91.224.250 (23 Oct 2002 18:48:33 GMT) X-Complaints-To: usenet@main.gmane.org NNTP-Posting-Date: Wed, 23 Oct 2002 18:48:33 +0000 (UTC) Original-To: ntg-context@let.uu.nl In-Reply-To: <20020701154125.38069.qmail@web10005.mail.yahoo.com> Xref: main.gmane.org gmane.comp.tex.context:8517 X-Report-Spam: http://spam.gmane.org/gmane.comp.tex.context:8517 --------------Boundary-00=_77YKRN4H8AL2QBR0QL0F Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Am Montag, 1. Juli 2002 17:41 schrieb Christopher Cardinale: > Are there any programs for converting RTF or HTML documents into > ConTeXt? Here's a crude script for HTML attached. Axel Rose is on enhancing it. Gr=FC=DFlis vom Hraban! --=20 http://www.fiee.net/texnique/ --- --------------Boundary-00=_77YKRN4H8AL2QBR0QL0F Content-Type: text/x-perl; charset="iso-8859-1"; name="html2context.pl" Content-Transfer-Encoding: quoted-printable Content-Disposition: attachment; filename="html2context.pl" #!/usr/bin/perl -w=0D =0D print "\nThis is HTML2ConTeXt. Version 2002-05-15\n";=0D print "I'll try to convert your HTML file for ConTeXt.\n";=0D print "copyleft Henning Hraban Ramm, http://www.fiee.net/texnique/\n\n";=0D =0D unless ($ARGV[0]) {die "You must name a file to convert! $!"};=0D my $HTMLDatei =3D $ARGV[0];=0D unless (-T $HTMLDatei) {=0D =09print "$HTMLDatei not found!\n";=0D =09if (-T $HTMLDatei.'.htm') { $HTMLDatei .=3D ".htm"; }=0D =09if (-T $HTMLDatei.'.html') { $HTMLDatei .=3D ".html"; }=0D } # unless=0D $HTMLDatei =3D~ s/\\/\//g;=0D =0D my $Table=3D"n";=0D my $Encod=3D"win";=0D =0D open (QUELLE, $HTMLDatei) or die "Can't open $HTMLDatei! $!";=0D =0D my $TeXDatei =3D $HTMLDatei;=0D $TeXDatei =3D~ s/\.htm$/\.tex/i;=0D print $TeXDatei."\n";=0D open (ZIEL, ">".$TeXDatei) or die "Can't make $TeXDatei! $!";=0D =0D while () {=0D # single entities and chars=0D =09s=A7&(.)uml;=A7\\\"$1=A7g;=0D =09s=A7&(.)acute;=A7\\=B4$1=A7g;=0D =09s=A7&(.)grave;=A7\\`$1=A7g;=0D =09s=A7&(.)circ;=A7\\^$1=A7g;=0D =09s=A7&(.)ring;=A7\\=B0$1=A7g;=0D if ($Encod eq "win") {=0D =09s=A7ß=A7=DF=A7g;=0D } else {=0D =09s=A7ß=A7\\ss{}=A7g;=0D } # if Encoding=0D =09s=A7&(\#150|endash);=A7--=A7g;=09# endash=0D =09s=A7 - =A7 -- =A7g;=09=09=09# endash=0D =09s=A7 =A7~=A7g;=09# non breaking space=0D =09s=A7"([^<>]*)"=A7\\quotation{$1}=A7g;=0D =09s=A7&(r|l)aquo;([^<>]*)&(l|r)aquo;=A7\\quotation{$2}=A7g;=0D =09s=A7&\#132;([^<>]*)"=A7\\quotation{$1}=A7g;=0D =09s=A7&\#132;([^<>]*)$=A7\\quotation{$1=A7g; # uncompleted line=0D =09s=A7\s("|\")=A7 \\quotation{=A7g;=09# begin quote=0D =09s=A7"\s=A7} =A7g;=09# end quote=0D =09s=A7"=A7\"=A7g;=09=09# quote=0D =09s=A7([^\\=3D\s])\"=A7$1}=A7g;=09# end quote=0D =09s=A7%=A7|~|\\%{}=A7g;=09# percent=0D =09s=A7<=A7<=A7g;=0D =09s=A7>=A7>=A7g;=0D =09s=A7&=A7\&=A7g;=0D =09s=A7&sup(.);=A7^$1=A7g;=0D =09s=A7&frac(.)(.);=A7\\frac{$1}{$2}=A7g;=0D =09s=A7&\#133;=A7 =A7g;=0D #=09s=A7=A7=A7g;=0D #=09s=A7=A7=A7g;=0D =0D # TeX words and marks=0D =09s=A7TEX=A7TeX=A7g;=0D =09s=A7pdfTeX=A7\\pdfTeX{}=A7gi;=0D =09s=A7ppchTeX=A7\\pdfTeX{}=A7gi;=0D =09s=A7ConTeXt=A7\\ConTeXt{}=A7g;=0D =09s=A7CONTEXT=A7\\ConTeXt{}=A7g;=0D =09s=A7(\s)TeX=A7$1\\TeX{}=A7g;=0D =0D # environments=0D =09s=A7]*>=A7\\starttext=A7gi;=0D =09s=A7=A7\\stoptext=A7gi;=0D =09s=A7(
|)=A7\\startquotation=A7gi;=0D =09s=A7(<\/BLOCKQUOTE>|<\/QUOTE>)=A7\\stopquotation=A7gi;=0D =09s=A7]*>=A7=A7gi;=09# delete all divs=0D =09s=A7]*(>|$)=A7=A7gi;=09# delete all font tags=0D =0D # Headers=0D =09s=A7

=A7\\chapter{=A7gi;=0D =09s=A7

=A7\\section{=A7gi;=0D =09s=A7

=A7\\subsection{=A7gi;=0D =09s=A7

=A7\\subsubsection{=A7gi;=0D =09s=A7=A7}=A7gi;=0D =0D # Links=0D =09s=A7(.*)=A7\\goto{$3}[URL($2)]=A7gi;=0D =09s=A7(.*)=A7\\reference[$2]{$3}=A7gi;=0D =0D # Tables=0D if ($Table eq "y") {=0D =09s=A7]*)>=A7\\bTABLE \%$1 =A7gi;=0D =09s=A7=A7\\eTABLE=A7gi;=0D =09s=A7=A7\\eTD =A7gi;=0D =09s=A7]*)>=A7\\bTD =A7gi;=0D =09s=A7=A7\\eTR =A7gi;=0D =09s=A7]*)>=A7\\bTR =A7gi;=0D } else {=0D =09s=A7]*>=A7=A7gi;=09# delete all table tags=0D } # if Table=0D =0D # Images=0D =09s=A7]*)>=A7\\externalfigure[$1]=A7gi;=0D =09s=A7]*)\"([^<>]*)$=A7\\externalfigure[$2]= \t\% $1 $3=A7gi;=0D =0D # Lists=0D =09s=A7
    =A7\\startitemize\[1\]=A7gi;=0D =09s=A7
      =A7\\startitemize\[n\]=A7gi;=0D =09s=A7
      =A7\\startitemize\[1\]=A7gi; # ?=0D =09s=A7=A7\\stopitemize=A7gi;=0D =09s=A7
    1. =A7\\item =A7gi;=0D =09s=A7
      =A7\\item =A7gi; #=0D =09s=A7
      =A7\\item =A7gi; #=0D =09s=A7
    2. =A7=A7gi;=0D =0D =0D =09s=A7]*>=A7=A7gi;=0D #=09s=A7

      =A7\\par=A7gi;=0D =09s=A7

      =A7\n\n=A7gi;=0D =09s=A7]*>=A7\n=A7gi;=0D =09s=A7]*>=A7\\blank =A7gi;=0D =0D =09s=A7<(PRE|TT|CODE)>=A7\\type{=A7gi;=0D =09s=A7<(STRONG|B)>=A7{\\bf =A7gi;=0D =09s=A7<(EM|I|U)>=A7{\\em =A7gi;=0D =0D =09s=A7^$=A7\\stop$1=A7gi;=0D =09s=A7^<([^\s]*)([^<>]*)>$=A7\\start$1\[$2\]=A7gi;=0D =09s=A7=A7}=A7gi; # all other closing tags become }=0D =09s=A7<([^\s]*)(\s)(.*)>=A7\\$1\[$3\]\{=A7gi; # all other opening tags b= ecome {=0D =09s=A7<([^\s]*)>=A7\\$1\{=A7gi; # all other opening tags become {=0D =0D =09s=A7^\s*=A7=A7g;=09# remove trailing spaces=0D =0D =09print ZIEL;=0D =09print ".";=0D } # while=0D print "\n";=0D =0D close (ZIEL);=0D close (QUELLE);=0D =0D =0D # \goto{text}[URL(Link)] --------------Boundary-00=_77YKRN4H8AL2QBR0QL0F--