$title

#!/usr/local/bin/perl.exe -w use strict; # Laola2html.pl # hacked up by Greg Holmes, 3 July 2001 # based on # pdf2html.pl # Version 1.0 25-May-2001 # Written by David Adams # # Uses laola (specifically lhalw and ldat) # to read an MS-Word file and produce HTML output. # # Can be called directly from htdig as an external converter, # or may be called by doc2html.pl converter script. # ####--- Configuration ---#### # Full paths of lhalw and ldat # (get the loala library from http://user.cs.tu-berlin.de/~schwartz/pmh/): #### YOU MUST SET THESE #### my $DOCTOTEXT = "/usr/bin/lhalw"; my $DOCINFO = "/usr/bin/ldat"; # # De-hyphenation option (only affects end-of-line hyphens): my $Dehyphenate = 1; # # Set title to be used when none is found: my $Default_title = "Microsoft Word Document"; # # make portable to win32 platform or unix: my $null = "/dev/null"; if ($^O eq "MSWin32") {$null = "nul";} ####--- End of configuration ---### if (! -x $DOCTOTEXT) { die "Unable to execute lhalw" } my $Input = $ARGV[0] || die "Usage: loala2html.pl filename [mime-type] [URL]"; my $MIME_type = $ARGV[1] || ''; if ($MIME_type and ($MIME_type !~ m#^application/msword#i)) { die "MIME/type $MIME_type wrong"; } my $Name = $ARGV[2] || ''; $Name =~ s#^.*/##; &doc_head; &doc_body; exit; #------------------------------------------------------------------------------ sub doc_head { # # Contributed to pdf2html by Greg Holmes and Michael Fuller # (any errors by David Adams) # (any new errors by Greg Holmes) # my $title = ''; my $subject = ''; my $keywords = ''; if (open(INFO, "$DOCINFO -a -d '$Input' 2>$null |")) { while () { if (m/\"title\"/i) { s/^.*$string$\s+\"//i; s/\"\s+//i; $title = &clean_doc($_); } elsif (m/\"subject\"/i) { s/^.*$string$\s+\"//i; s/\"\s+//i; $subject = &clean_doc($_); } elsif (m/\"keywords\"/i) { s/^.*$string$\s+\"//i; s/\"\s+//i; $keywords = &clean_doc($_); } } close INFO; } else { warn "cannot execute ldat" } if (not length $title) { if ($Name) { $title = '[' . $Name . ']'; } else { $title = $Default_title; } } print "\n\n"; print "$title\n"; if (length $subject) { print '\n"; } if (length $keywords) { print '\n"; } print "\n"; ###print STDERR "\n$Name:\n"; ###print STDERR "\tTitle:\t$title\n"; ###print STDERR "\tDescription:\t$subject\n"; ###print STDERR "\tKeywords:\t$keywords\n"; } #------------------------------------------------------------------------------ sub doc_body { my $bline = ''; open(CAT, "$DOCTOTEXT -F -N '$Input' |") || die "$DOCTOTEXT doesn't want to be opened using pipe\n"; print "\n"; while () { while ( m/[A-Za-z\300-\377]-\s*$/ && $Dehyphenate) { $_ .= ; last if eof; s/([A-Za-z\300-\377])-\s*\n\s*([A-Za-z\300-\377])/$1$2/s; } s/\255/-/g; # replace dashes with hyphens # replace bell, backspace, tab. etc. with single space: s/[\000-\040]+/ /g; $_ = &HTML($_); if (length) { print $bline, $_, "\n"; $bline = "
\n"; } else { $bline = "

\n"; } } close CAT; print "\n\n"; return; } #------------------------------------------------------------------------------ sub HTML { my $text = shift; $text =~ s/\f/\n/gs; # replace form feed $text =~ s/\s+/ /g; # replace multiple spaces, etc. with a single space $text =~ s/\s+$//gm; # remove trailing space $text =~ s/&/&/g; $text =~ s//>/g; chomp $text; return $text; } #------------------------------------------------------------------------------ sub clean_doc { # removes odd pair of characters that may be in ldat output # Any double quotes are replaced with single my $text = shift; chomp $text; $text =~ s/\376\377//g; $text =~ s/\"/\'/g; return $text; }