The R Project SVN R

#! @PERL@ 
#-*- perl -*- (for html2dos.in ..)

# Convert a html directory with long filenames to DOS 8.3 filenames

# Copyright (C) 1997,1998 Friedrich Leisch
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
# 
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# General Public License for more details. 
# 
# A copy of the GNU General Public License is available via WWW at
# http://www.gnu.org/copyleft/gpl.html.  You can also obtain it by
# writing to the Free Software Foundation, Inc., 675 Mass Ave,
# Cambridge, MA 02139, USA.

use File::Basename;
use Cwd;
use Getopt::Long;

GetOptions ("keep") || usage();

undef $/;

format STDOUT =
@<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< @<<<<<<<<<<<<<<<<<< 
$unixn,                          $dosn,              
.

$root = getcwd();
    
foreach $d (@ARGV) {

    chdir $root;
    chdir $d or die "Can't change to dir $d\n";

    print "******* Converting files in $d *******\n";
    
    opendir dir, '.';
    @dir = readdir(dir);

    undef %filenames;
    undef %namecount;

    foreach $unixn (@dir) {
    if($unixn =~ /\.html$/i){
        $dosn = basename($unixn, (".html", ".HTML"));
        $dosn = substr($dosn, 0, 5);
        $dosn =~ s/\./_/g;
        $dosn =~ s/(.*)/\L$1/;
        $namecount{$dosn}++;
        if($namecount{$dosn}>1){
        $dosn = "$dosn-$namecount{$dosn}";
        }
        
        $dosn = $dosn . ".htm";
        $filenames{$unixn} = $dosn;
    }
    }
    
    foreach $unixn (sort(keys(%filenames))) {
    
    $dosn = $filenames{$unixn};
    
    open uf, "<$unixn";
    open df, ">$dosn";
    
    $html = <uf>;
    $html =~ s/<a href\s*=\s*\"\.\.\/index\.html\">/<a href=\"..\/index.htm\">/g;
    $html =~ s/<a href\s*=\s*\"index\.html\">/<a href=\"index.htm\">/g;
    
    $html =~ s/<A HREF\s*=\s*\"\.\.\/index\.html\">/<a href=\"..\/index.htm\">/g;
    $html =~ s/<A HREF\s*=\s*\"index\.html\">/<a href=\"index.htm\">/g;
    
    foreach $link (keys(%filenames)) {
        $html =~ s/<a href\s*=\s*\"\s*$link\s*\">/<a href=\"$filenames{$link}\">/g;
        $html =~ s/<A HREF\s*=\s*\"\s*$link\s*\">/<a href=\"$filenames{$link}\">/g;
    }
    
    print df $html;
    write;
    close uf;
    close df;
    unlink $unixn unless $opt_keep;
    }
}


sub usage {

    print "Usage:  html2dos [--keep] dir1 [dir2 ...]\n\n" .
      "        --keep:  Don't remove original files (long names)\n\n";

    exit 0;
}