source: gsdl/trunk/perllib/plugins/WordPlugin.pm@ 15918

###########################################################################
#
# WordPlugin.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.
#
###########################################################################
package WordPlugin;

use ConvertBinaryFile;
use strict;
no strict 'refs'; # allow filehandles to be variables and viceversa

sub BEGIN {
    @WordPlugin::ISA = ('ConvertBinaryFile');
}

my $arguments =
    [ { 'name' => "process_exp",
    'desc' => "{BasePlugin.process_exp}",
    'type' => "regexp",
    'deft' => &get_default_process_exp(),
    'reqd' => "no" },
      { 'name' => "description_tags",
    'desc' => "{HTMLPlugin.description_tags}",
    'type' => "flag" }
      ];

my $options = { 'name'     => "WordPlugin",
        'desc'     => "{WordPlugin.desc}",
        'abstract' => "no",
        'inherits' => "yes",
        'srcreplaceable' => "yes", # Source docs in Word can be replaced with GS-generated html
        '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' => "{WordPlugin.windows_scripting}",
             'type' => "flag",
                 'reqd' => "no" },
               { 'name' => "metadata_fields",
             'type' => "string",
             'deft' => "Title" },
               { 'name' => "level1_header",
             'desc' => "{StructuredHTMLPlugin.level1_header}",
             'type' => "regexp",
             'reqd' => "no",
             'deft' => "" },
               { 'name' => "level2_header",
             'desc' => "{StructuredHTMLPlugin.level2_header}",
             'type' => "regexp",
             'reqd' => "no",
             'deft' => "" },
               { 'name' => "level3_header",
             'desc' => "{StructuredHTMLPlugin.level3_header}",
             'type' => "regexp",
             'reqd' => "no",
             'deft' => "" },
               { 'name' => "title_header",
             'desc' => "{StructuredHTMLPlugin.title_header}",
             'type' => "regexp",
             'reqd' => "no",
             'deft' => "" },
               { 'name' => "delete_toc",
             'desc' => "{StructuredHTMLPlugin.delete_toc}",
             'type' => "flag",
             'reqd' => "no",
             # set the mode so this doesn't show up unless 
             # all the following ones do
             'modegli' => "3"},
               { 'name' => "toc_header",
             'desc' => "{StructuredHTMLPlugin.toc_header}",
             'type' => "regexp",
             'reqd' => "no",
             'deft' => "" }
               ];
    
    push(@$arguments,@$ws_arg);
    }

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

    my $self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);

    if ($self->{'info_only'}) {
    # don't worry about any options etc
    return bless $self, $class;
    }

    $self->{'filename_extension'} = "doc";
    $self->{'file_type'} = "Word";

    #this is passed through to gsConvert.pl by ConvertBinaryFile.pm
    $self->{'convert_options'} = "-windows_scripting" if $self->{'windows_scripting'};

    # we always save as utf-8
#    if ($self->{'input_encoding'} eq "auto") {
#   $self->{'input_encoding'} = "utf8";
#    }

    my $secondary_plugin_options = $self->{'secondary_plugin_options'};
    if (defined $self->{'windows_scripting'}) { 
    if (!defined $secondary_plugin_options->{'StructuredHTMLPlugin'}){
        $secondary_plugin_options->{'StructuredHTMLPlugin'} = [];
        my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlugin'};
        
        # Instruct HTMLPlugin (when eventually accessed through read_into_doc_obj)
        # to extract these metadata fields from the HEAD META fields
        push (@$structhtml_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
        push (@$structhtml_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
        push (@$structhtml_options, "-description_tags") if $self->{'windows_scripting'};
        push(@$structhtml_options,"-extract_language") if $self->{'extract_language'};
        push (@$structhtml_options, "-delete_toc") if $self->{'delete_toc'};
        push (@$structhtml_options, "-toc_header", $self->{'toc_header'}) if $self->{'toc_header'};
        push (@$structhtml_options, "-title_header", $self->{'title_header'}) if $self->{'title_header'};
        push (@$structhtml_options, "-level1_header", $self->{'level1_header'}) if $self->{'level1_header'};
        push (@$structhtml_options, "-level2_header", $self->{'level2_header'})if $self->{'level2_header'};
        push (@$structhtml_options, "-level3_header", $self->{'level3_header'}) if $self->{'level3_header'};
        push (@$structhtml_options, "-metadata_fields", $self->{'metadata_fields'}) if $self->{'metadata_fields'};
    }
    }
    if (!defined $secondary_plugin_options->{'HTMLPlugin'}) {
    $secondary_plugin_options->{'HTMLPlugin'} = [];
    }
    if (!defined $secondary_plugin_options->{'TextPlugin'}) {
    $secondary_plugin_options->{'TextPlugin'} = [];
    }

    my $html_options = $secondary_plugin_options->{'HTMLPlugin'};
    my $text_options = $secondary_plugin_options->{'TextPlugin'};
    my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlugin'};    
    # wvWare will always produce html files encoded as utf-8, so make sure the secondary HTMLPlugin knows this
    push(@$html_options,"-input_encoding", "utf8");
    push(@$html_options,"-extract_language") if $self->{'extract_language'};
    push(@$html_options, "-description_tags") if $self->{'description_tags'};

    # Instruct HTMLPlugin (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+)?');

    my $associate_tail_re = $self->{'associate_tail_re'};
    if ((defined $associate_tail_re) && ($associate_tail_re ne "")) {
    push(@$html_options, "-associate_tail_re", $associate_tail_re);
    push(@$text_options, "-associate_tail_re", $associate_tail_re);
    push(@$structhtml_options, "-associate_tail_re", $associate_tail_re);
    }
       
    $self = bless $self, $class;
    $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists);

    return bless $self;
}

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

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

sub convert_post_process_old
{
    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!
    #$self->utf8_write_file (\$text, $conv_filename);
}

# 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
    }
    }
}


1;