root/trunk/gsdl/perllib/plugins/WordPlug.pm @ 11122

Revision 11122, 8.6 KB (checked in by davidb, 14 years ago)

Introduction of -associate_tail_re option to BasPlug?. This is a generalisation
of the associate_ext (in fact associate_ext is now mapped into the equivalent
assoicate_tail_re expression). To work properly, plugins that use the
secondary plugin mechanism (such as PDFPlug) need to duplicate the
associate_tail_re value secondary plug ins too.

  • Property svn:keywords set to Author Date Id Revision
Line 
1###########################################################################
2#
3# WordPlug.pm -- plugin for importing Microsoft Word documents
4# A component of the Greenstone digital library software
5# from the New Zealand Digital Library Project at the
6# University of Waikato, New Zealand.
7#
8# Copyright (C) 1999 New Zealand Digital Library Project
9#
10# This program is free software; you can redistribute it and/or modify
11# it under the terms of the GNU General Public License as published by
12# the Free Software Foundation; either version 2 of the License, or
13# (at your option) any later version.
14#
15# This program is distributed in the hope that it will be useful,
16# but WITHOUT ANY WARRANTY; without even the implied warranty of
17# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
18# GNU General Public License for more details.
19#
20# You should have received a copy of the GNU General Public License
21# along with this program; if not, write to the Free Software
22# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
23#
24###########################################################################
25# 12/05/02 Added usage datastructure - John Thompson
26
27package WordPlug;
28
29use ConvertToPlug;
30use strict;
31no strict 'refs'; # allow filehandles to be variables and viceversa
32
33sub BEGIN {
34    @WordPlug::ISA = ('ConvertToPlug');
35}
36
37my $arguments =
38    [ { 'name' => "process_exp",
39    'desc' => "{BasPlug.process_exp}",
40    'type' => "regexp",
41    'deft' => &get_default_process_exp(),
42    'reqd' => "no" },
43      { 'name' => "description_tags",
44    'desc' => "{HTMLPlug.description_tags}",
45    'type' => "flag" }
46      ];
47
48my $options = { 'name'     => "WordPlug",
49        'desc'     => "{WordPlug.desc}",
50        'abstract' => "no",
51        'inherits' => "yes",
52        'args'     => $arguments };
53
54sub new {
55    my ($class) = shift (@_);
56    my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
57    push(@$pluginlist, $class);
58
59    if ($ENV{'GSDLOS'} =~ m/^windows$/i) {
60    my $ws_arg = [ { 'name' => "windows_scripting",
61             'desc' => "{WordPlug.windows_scripting}",
62             'type' => "flag",
63                 'reqd' => "no" },
64               { 'name' => "delete_toc",
65             'desc' => "{WordPlug.delete_toc}",
66             'type' => "flag",
67             'reqd' => "no"},
68               { 'name' => "level1_header",
69             'desc' => "{WordPlug.level1_header}",
70             'type' => "regexp",
71             'reqd' => "no",
72             'deft' => "" },
73               { 'name' => "level2_header",
74             'desc' => "{WordPlug.level2_header}",
75             'type' => "regexp",
76             'reqd' => "no",
77             'deft' => "" },
78               { 'name' => "level3_header",
79             'desc' => "{WordPlug.level3_header}",
80             'type' => "regexp",
81             'reqd' => "no",
82             'deft' => "" },
83               { 'name' => "title_header",
84             'desc' => "{WordPlug.title_header}",
85             'type' => "regexp",
86             'reqd' => "no",
87             'deft' => "" },
88               { 'name' => "toc_header",
89             'desc' => "{WordPlug.toc_header}",
90             'type' => "regexp",
91             'reqd' => "no",
92             'deft' => "" },
93               { 'name' => "tof_header",
94             'desc' => "{WordPlug.tof_header}",
95             'type' => "regexp",
96             'reqd' => "no",
97             'deft' => "" },
98               { 'name' => "metadata_fields",
99             'type' => "string",
100             'deft' => "Title"}];
101   
102    push(@$arguments,@$ws_arg);
103    }
104
105    if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
106    if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
107
108    my $self = (defined $hashArgOptLists)? new ConvertToPlug($pluginlist,$inputargs,$hashArgOptLists): new ConvertToPlug($pluginlist,$inputargs);
109
110    if ($self->{'info_only'}) {
111    # don't worry about any options etc
112    return bless $self, $class;
113    }
114
115    #this is passed through to gsConvert.pl by ConvertToPlug.pm
116    $self->{'convert_options'} = "-windows_scripting" if $self->{'windows_scripting'};
117
118    my $secondary_plugin_options = $self->{'secondary_plugin_options'};
119    if (defined $self->{'windows_scripting'}) {
120    if (!defined $secondary_plugin_options->{'StructuredHTMLPlug'}){
121        $secondary_plugin_options->{'StructuredHTMLPlug'} = [];
122        my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlug'};
123        if ($self->{'input_encoding'} eq "auto") {
124        $self->{'input_encoding'} = "utf8";
125        $self->{'extract_language'} = 1;
126        push(@$structhtml_options,"-input_encoding", "utf8");
127        push(@$structhtml_options,"-extract_language");
128        }
129               
130        # Instruct HTMLPlug (when eventually accessed through read_into_doc_obj)
131        # to extract these metadata fields from the HEAD META fields
132        push (@$structhtml_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
133        push (@$structhtml_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
134        push (@$structhtml_options, "-description_tags") if $self->{'windows_scripting'};
135        push (@$structhtml_options, "-delete_toc") if $self->{'delete_toc'};
136        push (@$structhtml_options, "-toc_header", $self->{'toc_header'}) if $self->{'toc_header'};
137        push (@$structhtml_options, "-tof_header", $self->{'tof_header'}) if $self->{'tof_header'};
138        push (@$structhtml_options, "-title_header", $self->{'title_header'}) if $self->{'title_header'};
139        push (@$structhtml_options, "-level1_header", $self->{'level1_header'}) if $self->{'level1_header'};
140        push (@$structhtml_options, "-level2_header", $self->{'level2_header'})if $self->{'level2_header'};
141        push (@$structhtml_options, "-level3_header", $self->{'level3_header'}) if $self->{'level3_header'};
142        push (@$structhtml_options, "-metadata_fields", $self->{'metadata_fields'}) if $self->{'metadata_fields'};
143    }
144    }
145    if (!defined $secondary_plugin_options->{'HTMLPlug'}) {
146    $secondary_plugin_options->{'HTMLPlug'} = [];
147    }
148    if (!defined $secondary_plugin_options->{'TEXTPlug'}) {
149    $secondary_plugin_options->{'TEXTPlug'} = [];
150    }
151
152    my $html_options = $secondary_plugin_options->{'HTMLPlug'};
153    my $text_options = $secondary_plugin_options->{'TextPlug'};
154    my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlug'};   
155    # wvWare will always produce html files encoded as utf-8, so make sure the secondary HTMLPlug knows this
156    push(@$html_options,"-input_encoding", "utf8");
157
158    if ($self->{'input_encoding'} eq "auto") {
159    $self->{'input_encoding'} = "utf8";
160    $self->{'extract_language'} = 1;
161    push(@$html_options,"-extract_language");
162    }
163    if ($self->{'description_tags'} == 1) {
164    push(@$html_options, "-description_tags");
165    }
166    # Instruct HTMLPlug (when eventually accessed through read_into_doc_obj)
167    # to extract these metadata fields from the HEAD META fields
168    push(@$html_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
169    push(@$html_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
170
171    my $associate_tail_re = $self->{'associate_tail_re'};
172    if ((defined $associate_tail_re) && ($associate_tail_re ne "")) {
173    push(@$html_options, "-associate_tail_re", $associate_tail_re);
174    push(@$text_options, "-associate_tail_re", $associate_tail_re);
175    push(@$structhtml_options, "-associate_tail_re", $associate_tail_re);
176    }
177       
178    $self = bless $self, $class;
179    $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists);
180
181    return bless $self;
182}
183
184sub get_default_process_exp {
185    my $self = shift (@_);
186
187    return q^(?i)\.(doc|dot)$^;
188}
189
190sub convert_post_process
191{
192    my $self = shift (@_);
193    my ($conv_filename) = @_;
194
195    my $outhandle=$self->{'outhandle'};
196     
197    my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
198
199    # read in file ($text will be in utf8)
200    my $text = "";
201    $self->read_file ($conv_filename, $encoding, $language, \$text);
202
203    # turn any high bytes that aren't valid utf-8 into utf-8.
204    #unicode::ensure_utf8(\$text);
205   
206    # Write it out again!
207    #$self->utf8_write_file (\$text, $conv_filename);
208}
209
210sub get_file_type {
211    my $self = shift (@_);
212    my $file_type = "Word";
213    return $file_type;
214}
215
216# Modified to cache HTML files for efficieny reasons rather
217# than delete all.  HTML is modified not to use IE's VML.
218# VML uses WML files, so these can be deleted.
219sub cleanup_tmp_area {
220    my ($self) = @_;
221    if (defined $self->{'files_dir'}) {
222    my $html_files_dir = $self->{'files_dir'};
223
224    if (opendir(DIN,$html_files_dir)) {
225        my @wmz_files = grep( /\.wmz$/, readdir(DIN));
226        foreach my $f (@wmz_files) {
227        my $full_f = &util::filename_cat($html_files_dir,$f);
228        &util::rm($full_f);
229        }
230        closedir(DIN);
231    }
232    else {
233        # if HTML file has no supporting images, then no _files dir made
234        # => do nothing
235    }
236    }
237}
238
239# do plugin specific processing of doc_obj for HTML type
240sub process {
241    my $self = shift (@_);
242    my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
243
244    return $self->process_type("doc", $base_dir, $file, $doc_obj);
245}
246
2471;
248
Note: See TracBrowser for help on using the browser.