| 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 |
|
|---|
| 27 | package WordPlug;
|
|---|
| 28 |
|
|---|
| 29 | use ConvertToPlug;
|
|---|
| 30 | use strict;
|
|---|
| 31 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
|---|
| 32 |
|
|---|
| 33 | sub BEGIN {
|
|---|
| 34 | @WordPlug::ISA = ('ConvertToPlug');
|
|---|
| 35 | }
|
|---|
| 36 |
|
|---|
| 37 | my $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 |
|
|---|
| 48 | my $options = { 'name' => "WordPlug",
|
|---|
| 49 | 'desc' => "{WordPlug.desc}",
|
|---|
| 50 | 'abstract' => "no",
|
|---|
| 51 | 'inherits' => "yes",
|
|---|
| 52 | 'args' => $arguments };
|
|---|
| 53 |
|
|---|
| 54 | sub new {
|
|---|
| 55 | my ($class) = shift (@_);
|
|---|
| 56 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 57 | push(@$pluginlist, $class);
|
|---|
| 58 |
|
|---|
| 59 | if ($ENV{'GSDLOS'} =~ m/^windows$/i) {
|
|---|
| 60 | my $ws_arg = [ { 'name' => "windows_scripting",
|
|---|
| 61 | 'desc' => "{WordPlug.windows_scripting}",
|
|---|
| 62 | 'type' => "flag",
|
|---|
| 63 | 'reqd' => "no" },
|
|---|
| 64 | { 'name' => "delete_toc",
|
|---|
| 65 | 'desc' => "{StructuredHTMLPlug.delete_toc}",
|
|---|
| 66 | 'type' => "flag",
|
|---|
| 67 | 'reqd' => "no",
|
|---|
| 68 | # set the mode so this doesn't show up unless
|
|---|
| 69 | # all the following ones do
|
|---|
| 70 | 'modegli' => "3"},
|
|---|
| 71 | { 'name' => "level1_header",
|
|---|
| 72 | 'desc' => "{StructuredHTMLPlug.level1_header}",
|
|---|
| 73 | 'type' => "regexp",
|
|---|
| 74 | 'reqd' => "no",
|
|---|
| 75 | 'deft' => "" },
|
|---|
| 76 | { 'name' => "level2_header",
|
|---|
| 77 | 'desc' => "{StructuredHTMLPlug.level2_header}",
|
|---|
| 78 | 'type' => "regexp",
|
|---|
| 79 | 'reqd' => "no",
|
|---|
| 80 | 'deft' => "" },
|
|---|
| 81 | { 'name' => "level3_header",
|
|---|
| 82 | 'desc' => "{StructuredHTMLPlug.level3_header}",
|
|---|
| 83 | 'type' => "regexp",
|
|---|
| 84 | 'reqd' => "no",
|
|---|
| 85 | 'deft' => "" },
|
|---|
| 86 | { 'name' => "title_header",
|
|---|
| 87 | 'desc' => "{StructuredHTMLPlug.title_header}",
|
|---|
| 88 | 'type' => "regexp",
|
|---|
| 89 | 'reqd' => "no",
|
|---|
| 90 | 'deft' => "" },
|
|---|
| 91 | { 'name' => "toc_header",
|
|---|
| 92 | 'desc' => "{StructuredHTMLPlug.toc_header}",
|
|---|
| 93 | 'type' => "regexp",
|
|---|
| 94 | 'reqd' => "no",
|
|---|
| 95 | 'deft' => "" },
|
|---|
| 96 | { 'name' => "tof_header",
|
|---|
| 97 | 'desc' => "{StructuredHTMLPlug.tof_header}",
|
|---|
| 98 | 'type' => "regexp",
|
|---|
| 99 | 'reqd' => "no",
|
|---|
| 100 | 'deft' => "" },
|
|---|
| 101 | { 'name' => "metadata_fields",
|
|---|
| 102 | 'type' => "string",
|
|---|
| 103 | 'deft' => "Title"}];
|
|---|
| 104 |
|
|---|
| 105 | push(@$arguments,@$ws_arg);
|
|---|
| 106 | }
|
|---|
| 107 |
|
|---|
| 108 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
|---|
| 109 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
|---|
| 110 |
|
|---|
| 111 | my $self = (defined $hashArgOptLists)? new ConvertToPlug($pluginlist,$inputargs,$hashArgOptLists): new ConvertToPlug($pluginlist,$inputargs);
|
|---|
| 112 |
|
|---|
| 113 | if ($self->{'info_only'}) {
|
|---|
| 114 | # don't worry about any options etc
|
|---|
| 115 | return bless $self, $class;
|
|---|
| 116 | }
|
|---|
| 117 |
|
|---|
| 118 | #this is passed through to gsConvert.pl by ConvertToPlug.pm
|
|---|
| 119 | $self->{'convert_options'} = "-windows_scripting" if $self->{'windows_scripting'};
|
|---|
| 120 |
|
|---|
| 121 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
|---|
| 122 | if (defined $self->{'windows_scripting'}) {
|
|---|
| 123 | if (!defined $secondary_plugin_options->{'StructuredHTMLPlug'}){
|
|---|
| 124 | $secondary_plugin_options->{'StructuredHTMLPlug'} = [];
|
|---|
| 125 | my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlug'};
|
|---|
| 126 | if ($self->{'input_encoding'} eq "auto") {
|
|---|
| 127 | $self->{'input_encoding'} = "utf8";
|
|---|
| 128 | $self->{'extract_language'} = 1;
|
|---|
| 129 | #push(@$structhtml_options,"-input_encoding", "utf8");
|
|---|
| 130 | push(@$structhtml_options,"-extract_language");
|
|---|
| 131 | }
|
|---|
| 132 |
|
|---|
| 133 | # Instruct HTMLPlug (when eventually accessed through read_into_doc_obj)
|
|---|
| 134 | # to extract these metadata fields from the HEAD META fields
|
|---|
| 135 | push (@$structhtml_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
|
|---|
| 136 | push (@$structhtml_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
|---|
| 137 | push (@$structhtml_options, "-description_tags") if $self->{'windows_scripting'};
|
|---|
| 138 | push (@$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, "-tof_header", $self->{'tof_header'}) if $self->{'tof_header'};
|
|---|
| 141 | push (@$structhtml_options, "-title_header", $self->{'title_header'}) if $self->{'title_header'};
|
|---|
| 142 | push (@$structhtml_options, "-level1_header", $self->{'level1_header'}) if $self->{'level1_header'};
|
|---|
| 143 | push (@$structhtml_options, "-level2_header", $self->{'level2_header'})if $self->{'level2_header'};
|
|---|
| 144 | push (@$structhtml_options, "-level3_header", $self->{'level3_header'}) if $self->{'level3_header'};
|
|---|
| 145 | push (@$structhtml_options, "-metadata_fields", $self->{'metadata_fields'}) if $self->{'metadata_fields'};
|
|---|
| 146 | }
|
|---|
| 147 | }
|
|---|
| 148 | if (!defined $secondary_plugin_options->{'HTMLPlug'}) {
|
|---|
| 149 | $secondary_plugin_options->{'HTMLPlug'} = [];
|
|---|
| 150 | }
|
|---|
| 151 | if (!defined $secondary_plugin_options->{'TEXTPlug'}) {
|
|---|
| 152 | $secondary_plugin_options->{'TEXTPlug'} = [];
|
|---|
| 153 | }
|
|---|
| 154 |
|
|---|
| 155 | my $html_options = $secondary_plugin_options->{'HTMLPlug'};
|
|---|
| 156 | my $text_options = $secondary_plugin_options->{'TextPlug'};
|
|---|
| 157 | my $structhtml_options = $secondary_plugin_options->{'StructuredHTMLPlug'};
|
|---|
| 158 | # wvWare will always produce html files encoded as utf-8, so make sure the secondary HTMLPlug knows this
|
|---|
| 159 | push(@$html_options,"-input_encoding", "utf8");
|
|---|
| 160 |
|
|---|
| 161 | if ($self->{'input_encoding'} eq "auto") {
|
|---|
| 162 | $self->{'input_encoding'} = "utf8";
|
|---|
| 163 | $self->{'extract_language'} = 1;
|
|---|
| 164 | push(@$html_options,"-extract_language");
|
|---|
| 165 | }
|
|---|
| 166 | if ($self->{'description_tags'} == 1) {
|
|---|
| 167 | push(@$html_options, "-description_tags");
|
|---|
| 168 | }
|
|---|
| 169 | # Instruct HTMLPlug (when eventually accessed through read_into_doc_obj)
|
|---|
| 170 | # to extract these metadata fields from the HEAD META fields
|
|---|
| 171 | push(@$html_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
|
|---|
| 172 | push(@$html_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
|---|
| 173 |
|
|---|
| 174 | my $associate_tail_re = $self->{'associate_tail_re'};
|
|---|
| 175 | if ((defined $associate_tail_re) && ($associate_tail_re ne "")) {
|
|---|
| 176 | push(@$html_options, "-associate_tail_re", $associate_tail_re);
|
|---|
| 177 | push(@$text_options, "-associate_tail_re", $associate_tail_re);
|
|---|
| 178 | push(@$structhtml_options, "-associate_tail_re", $associate_tail_re);
|
|---|
| 179 | }
|
|---|
| 180 |
|
|---|
| 181 | $self = bless $self, $class;
|
|---|
| 182 | $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists);
|
|---|
| 183 |
|
|---|
| 184 | return bless $self;
|
|---|
| 185 | }
|
|---|
| 186 |
|
|---|
| 187 | sub get_default_process_exp {
|
|---|
| 188 | my $self = shift (@_);
|
|---|
| 189 |
|
|---|
| 190 | return q^(?i)\.(doc|dot)$^;
|
|---|
| 191 | }
|
|---|
| 192 |
|
|---|
| 193 | sub convert_post_process
|
|---|
| 194 | {
|
|---|
| 195 | my $self = shift (@_);
|
|---|
| 196 | my ($conv_filename) = @_;
|
|---|
| 197 |
|
|---|
| 198 | my $outhandle=$self->{'outhandle'};
|
|---|
| 199 |
|
|---|
| 200 | my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
|
|---|
| 201 |
|
|---|
| 202 | # read in file ($text will be in utf8)
|
|---|
| 203 | my $text = "";
|
|---|
| 204 | $self->read_file ($conv_filename, $encoding, $language, \$text);
|
|---|
| 205 |
|
|---|
| 206 | # turn any high bytes that aren't valid utf-8 into utf-8.
|
|---|
| 207 | #unicode::ensure_utf8(\$text);
|
|---|
| 208 |
|
|---|
| 209 | # Write it out again!
|
|---|
| 210 | #$self->utf8_write_file (\$text, $conv_filename);
|
|---|
| 211 | }
|
|---|
| 212 |
|
|---|
| 213 | sub get_file_type {
|
|---|
| 214 | my $self = shift (@_);
|
|---|
| 215 | my $file_type = "Word";
|
|---|
| 216 | return $file_type;
|
|---|
| 217 | }
|
|---|
| 218 |
|
|---|
| 219 | # Modified to cache HTML files for efficieny reasons rather
|
|---|
| 220 | # than delete all. HTML is modified not to use IE's VML.
|
|---|
| 221 | # VML uses WML files, so these can be deleted.
|
|---|
| 222 | sub cleanup_tmp_area {
|
|---|
| 223 | my ($self) = @_;
|
|---|
| 224 | if (defined $self->{'files_dir'}) {
|
|---|
| 225 | my $html_files_dir = $self->{'files_dir'};
|
|---|
| 226 |
|
|---|
| 227 | if (opendir(DIN,$html_files_dir)) {
|
|---|
| 228 | my @wmz_files = grep( /\.wmz$/, readdir(DIN));
|
|---|
| 229 | foreach my $f (@wmz_files) {
|
|---|
| 230 | my $full_f = &util::filename_cat($html_files_dir,$f);
|
|---|
| 231 | &util::rm($full_f);
|
|---|
| 232 | }
|
|---|
| 233 | closedir(DIN);
|
|---|
| 234 | }
|
|---|
| 235 | else {
|
|---|
| 236 | # if HTML file has no supporting images, then no _files dir made
|
|---|
| 237 | # => do nothing
|
|---|
| 238 | }
|
|---|
| 239 | }
|
|---|
| 240 | }
|
|---|
| 241 |
|
|---|
| 242 | # do plugin specific processing of doc_obj for HTML type
|
|---|
| 243 | sub process {
|
|---|
| 244 | my $self = shift (@_);
|
|---|
| 245 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
|---|
| 246 |
|
|---|
| 247 | return $self->process_type("doc", $base_dir, $file, $doc_obj);
|
|---|
| 248 | }
|
|---|
| 249 |
|
|---|
| 250 | 1;
|
|---|
| 251 |
|
|---|
