source: main/trunk/greenstone2/perllib/plugins/WordPlugin.pm@ 21801

Last change on this file since 21801 was 21801, checked in by kjdon, 12 years ago

extended HTMLPlugin's metadata_field_separator option to Word and StructuredHTML plugins

  • Property svn:keywords set to Author Date Id Revision
File size: 8.8 KB
Line 
1###########################################################################
2#
3# WordPlugin.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###########################################################################
25package WordPlugin;
26
27use ConvertBinaryFile;
28use strict;
29no strict 'refs'; # allow filehandles to be variables and viceversa
30
31sub BEGIN {
32 @WordPlugin::ISA = ('ConvertBinaryFile');
33}
34
35my $arguments =
36 [ { 'name' => "process_exp",
37 'desc' => "{BasePlugin.process_exp}",
38 'type' => "regexp",
39 'deft' => &get_default_process_exp(),
40 'reqd' => "no" },
41 { 'name' => "description_tags",
42 'desc' => "{HTMLPlugin.description_tags}",
43 'type' => "flag" }
44 ];
45
46my $options = { 'name' => "WordPlugin",
47 'desc' => "{WordPlugin.desc}",
48 'abstract' => "no",
49 'inherits' => "yes",
50 'srcreplaceable' => "yes", # Source docs in Word can be replaced with GS-generated html
51 'args' => $arguments };
52
53sub new {
54 my ($class) = shift (@_);
55 my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
56 push(@$pluginlist, $class);
57
58 if ($ENV{'GSDLOS'} =~ m/^windows$/i) {
59 my $ws_arg = [ { 'name' => "windows_scripting",
60 'desc' => "{WordPlugin.windows_scripting}",
61 'type' => "flag",
62 'reqd' => "no" },
63 { 'name' => "metadata_fields",
64 'desc' => "{WordPlugin.metadata_fields}",
65 'type' => "string",
66 'deft' => "Title" },
67 { 'name' => "metadata_field_separator",
68 'desc' => "{HTMLPlugin.metadata_field_separator}",
69 'type' => "string",
70 'deft' => "" },
71 { 'name' => "level1_header",
72 'desc' => "{StructuredHTMLPlugin.level1_header}",
73 'type' => "regexp",
74 'reqd' => "no",
75 'deft' => "" },
76 { 'name' => "level2_header",
77 'desc' => "{StructuredHTMLPlugin.level2_header}",
78 'type' => "regexp",
79 'reqd' => "no",
80 'deft' => "" },
81 { 'name' => "level3_header",
82 'desc' => "{StructuredHTMLPlugin.level3_header}",
83 'type' => "regexp",
84 'reqd' => "no",
85 'deft' => "" },
86 { 'name' => "title_header",
87 'desc' => "{StructuredHTMLPlugin.title_header}",
88 'type' => "regexp",
89 'reqd' => "no",
90 'deft' => "" },
91 { 'name' => "delete_toc",
92 'desc' => "{StructuredHTMLPlugin.delete_toc}",
93 'type' => "flag",
94 'reqd' => "no" },
95 { 'name' => "toc_header",
96 'desc' => "{StructuredHTMLPlugin.toc_header}",
97 'type' => "regexp",
98 'reqd' => "no",
99 'deft' => "" }
100 ];
101
102 push(@$arguments,@$ws_arg);
103 }
104
105 push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
106 push(@{$hashArgOptLists->{"OptList"}},$options);
107
108 my $self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);
109
110 if ($self->{'info_only'}) {
111 # don't worry about any options etc
112 return bless $self, $class;
113 }
114
115 $self->{'filename_extension'} = "doc";
116 $self->{'file_type'} = "Word";
117
118 #this is passed through to gsConvert.pl by ConvertBinaryFile.pm
119 $self->{'convert_options'} = "-windows_scripting" if $self->{'windows_scripting'};
120
121 # we always save as utf-8
122# if ($self->{'input_encoding'} eq "auto") {
123# $self->{'input_encoding'} = "utf8";
124# }
125
126 my $secondary_plugin_options = $self->{'secondary_plugin_options'};
127 if (defined $self->{'windows_scripting'}) {
128 if (!defined $secondary_plugin_options->{'StructuredHTMLPlugin'}){
129 $secondary_plugin_options->{'StructuredHTMLPlugin'} = [];
130 my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlugin'};
131
132 # Instruct HTMLPlugin (when eventually accessed through read_into_doc_obj)
133 # to extract these metadata fields from the HEAD META fields
134 push (@$structhtml_options, "-metadata_fields","Title,GENERATOR,date,author<Creator>");
135 push (@$structhtml_options, "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
136 push (@$structhtml_options, "-description_tags") if $self->{'windows_scripting'};
137 push (@$structhtml_options, "-extract_language") if $self->{'extract_language'};
138 push (@$structhtml_options, "-delete_toc") if $self->{'delete_toc'};
139 push (@$structhtml_options, "-toc_header", $self->{'toc_header'}) if $self->{'toc_header'};
140 push (@$structhtml_options, "-title_header", $self->{'title_header'}) if $self->{'title_header'};
141 push (@$structhtml_options, "-level1_header", $self->{'level1_header'}) if $self->{'level1_header'};
142 push (@$structhtml_options, "-level2_header", $self->{'level2_header'})if $self->{'level2_header'};
143 push (@$structhtml_options, "-level3_header", $self->{'level3_header'}) if $self->{'level3_header'};
144 push (@$structhtml_options, "-metadata_fields", $self->{'metadata_fields'}) if $self->{'metadata_fields'};
145 push (@$structhtml_options, "-metadata_field_separator", $self->{'metadata_field_separator'}) if $self->{'metadata_field_separator'};
146 }
147 }
148 if (!defined $secondary_plugin_options->{'HTMLPlugin'}) {
149 $secondary_plugin_options->{'HTMLPlugin'} = [];
150 }
151 if (!defined $secondary_plugin_options->{'TextPlugin'}) {
152 $secondary_plugin_options->{'TextPlugin'} = [];
153 }
154
155 my $html_options = $secondary_plugin_options->{'HTMLPlugin'};
156 my $text_options = $secondary_plugin_options->{'TextPlugin'};
157 my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlugin'};
158 # tell the secondary plugins that they are processing tmp files
159 push(@$html_options, "-processing_tmp_files");
160 push(@$structhtml_options, "-processing_tmp_files");
161
162 # wvWare will always produce html files encoded as utf-8, so make sure the secondary HTMLPlugin knows this
163 push(@$html_options,"-input_encoding", "utf8");
164 push(@$html_options,"-extract_language") if $self->{'extract_language'};
165 push(@$html_options, "-description_tags") if $self->{'description_tags'};
166
167 # Instruct HTMLPlugin (when eventually accessed through read_into_doc_obj)
168 # to extract these metadata fields from the HEAD META fields
169 push(@$html_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
170 push(@$html_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
171
172 my $associate_tail_re = $self->{'associate_tail_re'};
173 if ((defined $associate_tail_re) && ($associate_tail_re ne "")) {
174 push(@$html_options, "-associate_tail_re", $associate_tail_re);
175 push(@$text_options, "-associate_tail_re", $associate_tail_re);
176 push(@$structhtml_options, "-associate_tail_re", $associate_tail_re) if defined $structhtml_options;
177 }
178
179 push(@$html_options, "-file_rename_method", "none");
180 push(@$text_options, "-file_rename_method", "none");
181 push(@$structhtml_options, "-file_rename_method", "none") if defined $structhtml_options;
182
183 $self = bless $self, $class;
184 $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists);
185
186 return bless $self;
187}
188
189sub get_default_process_exp {
190 my $self = shift (@_);
191
192 return q^(?i)\.(doc|dot)$^;
193}
194
195sub convert_post_process_old
196{
197 my $self = shift (@_);
198 my ($conv_filename) = @_;
199
200 my $outhandle=$self->{'outhandle'};
201
202 my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
203
204 # read in file ($text will be in utf8)
205 my $text = "";
206 $self->read_file ($conv_filename, $encoding, $language, \$text);
207
208 # turn any high bytes that aren't valid utf-8 into utf-8.
209 #unicode::ensure_utf8(\$text);
210
211 # Write it out again!
212 #$self->utf8_write_file (\$text, $conv_filename);
213}
214
215# Modified to cache HTML files for efficieny reasons rather
216# than delete all. HTML is modified not to use IE's VML.
217# VML uses WML files, so these can be deleted.
218sub cleanup_tmp_area {
219 my ($self) = @_;
220 if (defined $self->{'files_dir'}) {
221 my $html_files_dir = $self->{'files_dir'};
222
223 if (opendir(DIN,$html_files_dir)) {
224 my @wmz_files = grep( /\.wmz$/, readdir(DIN));
225 foreach my $f (@wmz_files) {
226 my $full_f = &util::filename_cat($html_files_dir,$f);
227 &util::rm($full_f);
228 }
229 closedir(DIN);
230 }
231 else {
232 # if HTML file has no supporting images, then no _files dir made
233 # => do nothing
234 }
235 }
236}
237
238
2391;
240
Note: See TracBrowser for help on using the repository browser.