[2981] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # PPTPlug.pm -- plugin for importing Microsoft PowerPoint files.
|
---|
| 4 | # (currently only versions 95 and 97)
|
---|
| 5 | #
|
---|
| 6 | # A component of the Greenstone digital library software
|
---|
| 7 | # from the New Zealand Digital Library Project at the
|
---|
| 8 | # University of Waikato, New Zealand.
|
---|
| 9 | #
|
---|
| 10 | # Copyright (C) 2002 New Zealand Digital Library Project
|
---|
| 11 | #
|
---|
| 12 | # This program is free software; you can redistribute it and/or modify
|
---|
| 13 | # it under the terms of the GNU General Public License as published by
|
---|
| 14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 15 | # (at your option) any later version.
|
---|
| 16 | #
|
---|
| 17 | # This program is distributed in the hope that it will be useful,
|
---|
| 18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 20 | # GNU General Public License for more details.
|
---|
| 21 | #
|
---|
| 22 | # You should have received a copy of the GNU General Public License
|
---|
| 23 | # along with this program; if not, write to the Free Software
|
---|
| 24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 25 | #
|
---|
| 26 | ###########################################################################
|
---|
| 27 |
|
---|
| 28 | package PPTPlug;
|
---|
| 29 |
|
---|
| 30 | use ConvertToPlug;
|
---|
[10254] | 31 | use strict;
|
---|
| 32 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
[2981] | 33 |
|
---|
| 34 | sub BEGIN {
|
---|
[10254] | 35 | @PPTPlug::ISA = ('ConvertToPlug');
|
---|
[2981] | 36 | }
|
---|
| 37 |
|
---|
[6408] | 38 | my $arguments =
|
---|
| 39 | [ { 'name' => "process_exp",
|
---|
| 40 | 'desc' => "{BasPlug.process_exp}",
|
---|
| 41 | 'type' => "regexp",
|
---|
| 42 | 'reqd' => "no",
|
---|
[10275] | 43 | 'deft' => &get_default_process_exp()}
|
---|
[6408] | 44 | ];
|
---|
| 45 |
|
---|
[4744] | 46 | my $options = { 'name' => "PPTPlug",
|
---|
[5680] | 47 | 'desc' => "{PPTPlug.desc}",
|
---|
[6408] | 48 | 'abstract' => "no",
|
---|
| 49 | 'inherits' => "Yes",
|
---|
| 50 | 'args' => $arguments };
|
---|
[4744] | 51 |
|
---|
[2981] | 52 | sub new {
|
---|
[10218] | 53 | my ($class) = shift (@_);
|
---|
| 54 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 55 | push(@$pluginlist, $class);
|
---|
[2981] | 56 |
|
---|
[10275] | 57 | if ($ENV{'GSDLOS'} =~ m/^windows$/i) {
|
---|
| 58 | my $ws_arg = { 'name' => "windows_scripting",
|
---|
| 59 | 'desc' => "PPTPlug.windows_scripting}",
|
---|
| 60 | 'type' => "flag",
|
---|
| 61 | 'reqd' => "no" };
|
---|
| 62 | push(@$arguments,$ws_arg);
|
---|
| 63 | }
|
---|
| 64 |
|
---|
[10218] | 65 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
---|
| 66 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
---|
| 67 |
|
---|
| 68 | my $self = (defined $hashArgOptLists)? new ConvertToPlug($pluginlist,$inputargs,$hashArgOptLists): new ConvertToPlug($pluginlist,$inputargs);
|
---|
[10275] | 69 |
|
---|
| 70 | # ppthtml outputs utf-8 already.
|
---|
| 71 | #these are passed through to gsConvert.pl by ConvertToPlug.pm
|
---|
| 72 | $self->{'convert_options'} = "-windows_scripting" if $self->{'window_scripting'};
|
---|
| 73 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
---|
[10218] | 74 |
|
---|
[10275] | 75 | if ($self->{'windows_scripting'} && ($self->{'convert_to'} eq "PagedImg")) {
|
---|
| 76 | $secondary_plugin_options->{'PagedImgPlug'} = [];
|
---|
| 77 | } else {
|
---|
| 78 | $secondary_plugin_options->{'HTMLPlug'} = [];
|
---|
| 79 | }
|
---|
| 80 | my $html_options = $secondary_plugin_options->{'HTMLPlug'};
|
---|
| 81 | my $pageimg_options = $secondary_plugin_options->{'PagedImgPlug'};
|
---|
| 82 |
|
---|
[2981] | 83 | if ($self->{'input_encoding'} eq "auto") {
|
---|
| 84 | $self->{'input_encoding'} = "utf8";
|
---|
[10275] | 85 | $self->{'extract_language'} = 1;
|
---|
| 86 | if (defined $secondary_plugin_options->{'HTMLPlug'}){
|
---|
| 87 | push(@$html_options,"-input_encoding", "utf8");
|
---|
| 88 | push(@$html_options,"-extract_language");
|
---|
| 89 |
|
---|
| 90 | # Instruct HTMLPlug (when eventually accessed through read_into_doc_obj)
|
---|
| 91 | # to extract these metadata fields from the HEAD META fields
|
---|
| 92 | push(@$html_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
|
---|
| 93 | #push(@$html_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
---|
| 94 | }
|
---|
| 95 | if (defined $secondary_plugin_options->{'PagedImgPlug'}){
|
---|
| 96 | push(@$pageimg_options,"-input_encoding", "utf8");
|
---|
| 97 | push(@$pageimg_options,"-extract_language");
|
---|
| 98 | }
|
---|
[2981] | 99 | }
|
---|
| 100 |
|
---|
[10275] | 101 | $self = bless $self, $class;
|
---|
| 102 |
|
---|
| 103 | $self->load_secondary_plugins($class,$secondary_plugin_options);
|
---|
| 104 | return $self;
|
---|
[2981] | 105 | }
|
---|
| 106 |
|
---|
| 107 | sub get_default_process_exp {
|
---|
| 108 | my $self = shift (@_);
|
---|
| 109 | return q^(?i)\.ppt$^;
|
---|
| 110 | }
|
---|
[10275] | 111 |
|
---|
| 112 | sub get_file_type {
|
---|
[2981] | 113 | my $self = shift (@_);
|
---|
[10275] | 114 | my $file_type = "PPT";
|
---|
| 115 | return $file_type;
|
---|
| 116 | }
|
---|
[2981] | 117 |
|
---|
[10275] | 118 | sub convert_post_process
|
---|
| 119 | {
|
---|
| 120 | my $self = shift (@_);
|
---|
| 121 | my ($conv_filename) = @_;
|
---|
[2981] | 122 |
|
---|
[10275] | 123 | my $outhandle=$self->{'outhandle'};
|
---|
| 124 | my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
|
---|
| 125 | # read in file ($text will be in utf8)
|
---|
| 126 | my $text = "";
|
---|
| 127 | $self->read_file ($conv_filename, $encoding, $language, \$text);
|
---|
| 128 |
|
---|
| 129 | # turn any high bytes that aren't valid utf-8 into utf-8.
|
---|
| 130 | unicode::ensure_utf8(\$text);
|
---|
| 131 | # Write it out again!
|
---|
| 132 | $self->utf8_write_file (\$text, $conv_filename);
|
---|
[2981] | 133 | }
|
---|
| 134 |
|
---|
[10275] | 135 | sub process {
|
---|
| 136 | my $self = shift (@_);
|
---|
| 137 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
| 138 |
|
---|
| 139 | return $self->process_type("ppt",$base_dir,$file,$doc_obj);
|
---|
| 140 | }
|
---|
| 141 |
|
---|
[2981] | 142 | 1;
|
---|
[10275] | 143 |
|
---|