source: trunk/gsdl/perllib/plugins/WordPlug.pm@ 10279

###########################################################################
#
# WordPlug.pm -- plugin for importing Microsoft Word documents
# A component of the Greenstone digital library software
# from the New Zealand Digital Library Project at the 
# University of Waikato, New Zealand.
#
# Copyright (C) 1999 New Zealand Digital Library Project
#
# 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 of the License, 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.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
#
###########################################################################

# 12/05/02 Added usage datastructure - John Thompson

package WordPlug;

use ConvertToPlug;
require StructuredHTMLPlug;
use strict;
no strict 'refs'; # allow filehandles to be variables and viceversa


sub BEGIN {
    @WordPlug::ISA = ('ConvertToPlug','StructuredHTMLPlug');
}

my $arguments =
    [ { 'name' => "process_exp",
    'desc' => "{BasPlug.process_exp}",
    'type' => "regexp",
    'deft' => &get_default_process_exp(),
    'reqd' => "no" },
      { 'name' => "title_header",
    'desc' => "{WordPlug.title_header}",
    'type' => "string" },
      { 'name' => "check_toc",
    'desc' => "{WordPlug.check_toc}",
    'type' => "flag" },
      { 'name' => "toc_header",
    'desc' => "{WordPlug.toc_header}",
    'type' => "string" },
      { 'name' => "tof_header",
    'desc' => "{WordPlug.tof_header}",
    'type' => "string" },
      { 'name' => "level1_header",
    'desc' => "{WordPlug.level1_header}",
    'type' => "string" },
      { 'name' => "level2_header",
    'desc' => "{WordPlug.level2_header}",
    'type' => "string" },     
      { 'name' => "level3_header",
    'desc' => "{WordPlug.level3_header}",
    'type' => "string" }];

my $options = { 'name'     => "WordPlug",
        'desc'     => "{WordPlug.desc}",
        'abstract' => "no",
        'inherits' => "yes",
        'args'     => $arguments };

sub new {
    my ($class) = shift (@_);
    my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
    push(@$pluginlist, $class);

    if ($ENV{'GSDLOS'} =~ m/^windows$/i) {
    my $ws_arg = { 'name' => "windows_scripting",
               'desc' => "{WordPlug.windows_scripting}",
               'type' => "flag" };
    push(@$arguments,$ws_arg);
    }

    if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
    if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};

    my $self = (defined $hashArgOptLists)? new ConvertToPlug($pluginlist,$inputargs,$hashArgOptLists): new ConvertToPlug($pluginlist,$inputargs);

    #this is passed through to gsConvert.pl by ConvertToPlug.pm
    $self->{'convert_options'} = "-windows_scripting" if $self->{'windows_scripting'};
    
    my $secondary_plugin_options = $self->{'secondary_plugin_options'};
    
    if (!defined $secondary_plugin_options->{'HTMLPlug'}) {
    $secondary_plugin_options->{'HTMLPlug'} = [];
    }
    if (!defined $secondary_plugin_options->{'TEXTPlug'}) {
    $secondary_plugin_options->{'TEXTPlug'} = [];
    }

    my $html_options = $secondary_plugin_options->{'HTMLPlug'};
    my $text_options = $secondary_plugin_options->{'TextPlug'};
    
    # wvWare will always produce html files encoded as utf-8
    if ($self->{'input_encoding'} eq "auto") {
    $self->{'input_encoding'} = "utf8";
    $self->{'extract_language'} = 1;
    push(@$html_options,"-input_encoding", "utf8");
    push(@$html_options,"-extract_language");
    
    # Instruct HTMLPlug (when eventually accessed through read_into_doc_obj)
    # to extract these metadata fields from the HEAD META fields
    push(@$html_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
    #push(@$html_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
    }
    
    $self = bless $self, $class;
    
    $self->load_secondary_plugins($class,$secondary_plugin_options);

    #return bless $self, $class;
    return bless $self;
}

sub get_default_process_exp {
    my $self = shift (@_);

    return q^(?i)\.(doc|dot)$^;
}

sub convert_post_process
{
    my $self = shift (@_);
    my ($conv_filename) = @_;

    my $outhandle=$self->{'outhandle'};

    my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);

    # read in file ($text will be in utf8)
    my $text = "";
    $self->read_file ($conv_filename, $encoding, $language, \$text);

    # turn any high bytes that aren't valid utf-8 into utf-8.
    unicode::ensure_utf8(\$text);

    # Write it out again!
}

sub get_file_type {
    my $self = shift (@_);
    my $file_type = "Word";
    return $file_type;
}

# Modified to cache HTML files for efficieny reasons rather
# than delete all.  HTML is modified not to use IE's VML.
# VML uses WML files, so these can be deleted.
sub cleanup_tmp_area {
    my ($self) = @_;
    if (defined $self->{'files_dir'}) {
    my $html_files_dir = $self->{'files_dir'};

    if (opendir(DIN,$html_files_dir)) {
        my @wmz_files = grep( /\.wmz$/, readdir(DIN));
        foreach my $f (@wmz_files) {
        my $full_f = &util::filename_cat($html_files_dir,$f);
        &util::rm($full_f);
        }
        closedir(DIN);
    }
    else {
        # if HTML file has no supporting images, then no _files dir made
        # => do nothing
    }
    }
}

# do plugin specific processing of doc_obj for HTML type
sub process {
    my $self = shift (@_);
    my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
   
    return $self->process_type("doc", $base_dir, $file, $doc_obj);
}

1;