| 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 | ###########################################################################
|
|---|
| 25 | package WordPlugin;
|
|---|
| 26 |
|
|---|
| 27 | use strict;
|
|---|
| 28 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
|---|
| 29 | no strict 'subs';
|
|---|
| 30 |
|
|---|
| 31 | use gsprintf 'gsprintf';
|
|---|
| 32 |
|
|---|
| 33 | use AutoloadConverterScripting;
|
|---|
| 34 |
|
|---|
| 35 | @WordPlugin::ISA = ('AutoloadConverterScripting');
|
|---|
| 36 |
|
|---|
| 37 |
|
|---|
| 38 | my $arguments =
|
|---|
| 39 | [ { 'name' => "process_exp",
|
|---|
| 40 | 'desc' => "{BasePlugin.process_exp}",
|
|---|
| 41 | 'type' => "regexp",
|
|---|
| 42 | 'deft' => "&get_default_process_exp(\$self)", # delayed (see below)
|
|---|
| 43 | 'reqd' => "no" },
|
|---|
| 44 | { 'name' => "description_tags",
|
|---|
| 45 | 'desc' => "{HTMLPlugin.description_tags}",
|
|---|
| 46 | 'type' => "flag" }
|
|---|
| 47 | ];
|
|---|
| 48 |
|
|---|
| 49 |
|
|---|
| 50 | my $opt_windows_args = [ { 'name' => "windows_scripting",
|
|---|
| 51 | 'desc' => "{WordPlugin.windows_scripting}",
|
|---|
| 52 | 'type' => "flag",
|
|---|
| 53 | 'reqd' => "no" } ];
|
|---|
| 54 |
|
|---|
| 55 | my $opt_office_args = [ { 'name' => "metadata_fields",
|
|---|
| 56 | 'desc' => "{WordPlugin.metadata_fields}",
|
|---|
| 57 | 'type' => "string",
|
|---|
| 58 | 'deft' => "Title" },
|
|---|
| 59 | { 'name' => "level1_header",
|
|---|
| 60 | 'desc' => "{StructuredHTMLPlugin.level1_header}",
|
|---|
| 61 | 'type' => "regexp",
|
|---|
| 62 | 'reqd' => "no",
|
|---|
| 63 | 'deft' => "" },
|
|---|
| 64 | { 'name' => "level2_header",
|
|---|
| 65 | 'desc' => "{StructuredHTMLPlugin.level2_header}",
|
|---|
| 66 | 'type' => "regexp",
|
|---|
| 67 | 'reqd' => "no",
|
|---|
| 68 | 'deft' => "" },
|
|---|
| 69 | { 'name' => "level3_header",
|
|---|
| 70 | 'desc' => "{StructuredHTMLPlugin.level3_header}",
|
|---|
| 71 | 'type' => "regexp",
|
|---|
| 72 | 'reqd' => "no",
|
|---|
| 73 | 'deft' => "" },
|
|---|
| 74 | { 'name' => "title_header",
|
|---|
| 75 | 'desc' => "{StructuredHTMLPlugin.title_header}",
|
|---|
| 76 | 'type' => "regexp",
|
|---|
| 77 | 'reqd' => "no",
|
|---|
| 78 | 'deft' => "" },
|
|---|
| 79 | { 'name' => "delete_toc",
|
|---|
| 80 | 'desc' => "{StructuredHTMLPlugin.delete_toc}",
|
|---|
| 81 | 'type' => "flag",
|
|---|
| 82 | 'reqd' => "no" },
|
|---|
| 83 | { 'name' => "toc_header",
|
|---|
| 84 | 'desc' => "{StructuredHTMLPlugin.toc_header}",
|
|---|
| 85 | 'type' => "regexp",
|
|---|
| 86 | 'reqd' => "no",
|
|---|
| 87 | 'deft' => "" } ];
|
|---|
| 88 |
|
|---|
| 89 |
|
|---|
| 90 | my $options = { 'name' => "WordPlugin",
|
|---|
| 91 | 'desc' => "{WordPlugin.desc}",
|
|---|
| 92 | 'abstract' => "no",
|
|---|
| 93 | 'inherits' => "yes",
|
|---|
| 94 | 'srcreplaceable' => "yes", # Source docs in Word can be replaced with GS-generated html
|
|---|
| 95 | 'args' => $arguments };
|
|---|
| 96 |
|
|---|
| 97 | sub new {
|
|---|
| 98 | my ($class) = shift (@_);
|
|---|
| 99 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 100 | push(@$pluginlist, $class);
|
|---|
| 101 |
|
|---|
| 102 | my $office_capable = 0;
|
|---|
| 103 | if ($ENV{'GSDLOS'} =~ m/^windows$/i) {
|
|---|
| 104 | push(@$arguments,@$opt_windows_args);
|
|---|
| 105 | $office_capable = 1;
|
|---|
| 106 | }
|
|---|
| 107 | if ($AutoloadConverterScripting::openoffice_ext_working) {
|
|---|
| 108 | $office_capable = 1;
|
|---|
| 109 | }
|
|---|
| 110 | # these office args apply to windows scripting or to openoffice scripting
|
|---|
| 111 | if ($office_capable) {
|
|---|
| 112 | push(@$arguments,@$opt_office_args);
|
|---|
| 113 | }
|
|---|
| 114 |
|
|---|
| 115 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
|---|
| 116 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
|---|
| 117 |
|
|---|
| 118 | my $self
|
|---|
| 119 | = new AutoloadConverterScripting("OpenOfficeConverter",$pluginlist,
|
|---|
| 120 | $inputargs, $hashArgOptLists);
|
|---|
| 121 |
|
|---|
| 122 | # plugin's process_exp can only be correctly determined once autoloading
|
|---|
| 123 | # has taken place
|
|---|
| 124 | my $plug_options = $self->{'option_list'}->[0];
|
|---|
| 125 | my $plug_args = $plug_options->{'args'};
|
|---|
| 126 |
|
|---|
| 127 | foreach my $a (@$plug_args) {
|
|---|
| 128 | # consider changing this to search for all values that are
|
|---|
| 129 | # tagged as 'deft-delayed' = 1 ?!?
|
|---|
| 130 |
|
|---|
| 131 | if ($a->{'name'} eq "process_exp") {
|
|---|
| 132 | my $eval_expr = $a->{'deft'};
|
|---|
| 133 | $a->{'deft'} = eval "$eval_expr";
|
|---|
| 134 |
|
|---|
| 135 | # Now see if process_exp needs updating
|
|---|
| 136 | my $process_exp = $self->{'process_exp'};
|
|---|
| 137 | if (!$self->{'info_only'} && ($process_exp eq $eval_expr)) {
|
|---|
| 138 | # process_exp is only defined if not 'info_only'
|
|---|
| 139 | #
|
|---|
| 140 | # if it does exist and it equals the unevaluated $eval_expr
|
|---|
| 141 | # then it was set to the default (rather than overriden by
|
|---|
| 142 | # the collect.cfg file)
|
|---|
| 143 |
|
|---|
| 144 | $self->{'process_exp'} = $a->{'deft'};
|
|---|
| 145 | }
|
|---|
| 146 | }
|
|---|
| 147 | }
|
|---|
| 148 |
|
|---|
| 149 |
|
|---|
| 150 | if ($self->{'info_only'}) {
|
|---|
| 151 | # don't worry about any options etc
|
|---|
| 152 | return bless $self, $class;
|
|---|
| 153 | }
|
|---|
| 154 |
|
|---|
| 155 | $self->{'filename_extension'} = "doc";
|
|---|
| 156 | $self->{'file_type'} = "Word";
|
|---|
| 157 |
|
|---|
| 158 | my $outhandle = $self->{'outhandle'};
|
|---|
| 159 |
|
|---|
| 160 | if ($self->{'windows_scripting'}) {
|
|---|
| 161 | $self->{'convert_options'} = "-windows_scripting";
|
|---|
| 162 | $self->{'office_scripting'} = 1;
|
|---|
| 163 | }
|
|---|
| 164 | if ($self->{'openoffice_scripting'}) {
|
|---|
| 165 | if ($self->{'windows_scripting'}) {
|
|---|
| 166 | print $outhandle "Warning: Cannot have -windows_scripting and -openoffice_scripting\n";
|
|---|
| 167 | print $outhandle " on at the same time. Defaulting to -windows_scripting\n";
|
|---|
| 168 | $self->{'openoffice_scripting'} = 0;
|
|---|
| 169 | }
|
|---|
| 170 | else {
|
|---|
| 171 | $self->{'office_scripting'} = 1;
|
|---|
| 172 | }
|
|---|
| 173 | }
|
|---|
| 174 |
|
|---|
| 175 | # check convert_to
|
|---|
| 176 | if ($self->{'convert_to'} eq "auto") {
|
|---|
| 177 | $self->{'convert_to'} = "html";
|
|---|
| 178 | }
|
|---|
| 179 | # windows or open office scripting, outputs structuredHTML
|
|---|
| 180 | if (defined $self->{'office_scripting'}) {
|
|---|
| 181 | $self->{'convert_to'} = "structuredhtml";
|
|---|
| 182 | }
|
|---|
| 183 |
|
|---|
| 184 | # set convert_to_plugin and convert_to_ext
|
|---|
| 185 | $self->set_standard_convert_settings();
|
|---|
| 186 |
|
|---|
| 187 | my $secondary_plugin_name = $self->{'convert_to_plugin'};
|
|---|
| 188 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
|---|
| 189 |
|
|---|
| 190 | if (!defined $secondary_plugin_options->{$secondary_plugin_name}) {
|
|---|
| 191 | $secondary_plugin_options->{$secondary_plugin_name} = [];
|
|---|
| 192 | }
|
|---|
| 193 | my $specific_options = $secondary_plugin_options->{$secondary_plugin_name};
|
|---|
| 194 |
|
|---|
| 195 | # following title_sub removes "Page 1" and a leading
|
|---|
| 196 | # "1", which is often the page number at the top of the page. Bad Luck
|
|---|
| 197 | # if your document title actually starts with "1 " - is there a better way?
|
|---|
| 198 | push(@$specific_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
|---|
| 199 |
|
|---|
| 200 | my $associate_tail_re = $self->{'associate_tail_re'};
|
|---|
| 201 | if ((defined $associate_tail_re) && ($associate_tail_re ne "")) {
|
|---|
| 202 | push(@$specific_options, "-associate_tail_re", $associate_tail_re);
|
|---|
| 203 | }
|
|---|
| 204 | push(@$specific_options, "-file_rename_method", "none");
|
|---|
| 205 |
|
|---|
| 206 | if ($secondary_plugin_name eq "StructuredHTMLPlugin") {
|
|---|
| 207 | # Instruct HTMLPlugin (when eventually accessed through read_into_doc_obj)
|
|---|
| 208 | # to extract these metadata fields from the HEAD META fields
|
|---|
| 209 | push (@$specific_options, "-metadata_fields","Title,GENERATOR,date,author<Creator>");
|
|---|
| 210 | push (@$specific_options, "-description_tags") if $self->{'office_scripting'};
|
|---|
| 211 | push (@$specific_options, "-extract_language") if $self->{'extract_language'};
|
|---|
| 212 | push (@$specific_options, "-delete_toc") if $self->{'delete_toc'};
|
|---|
| 213 | push (@$specific_options, "-toc_header", $self->{'toc_header'}) if $self->{'toc_header'};
|
|---|
| 214 | push (@$specific_options, "-title_header", $self->{'title_header'}) if $self->{'title_header'};
|
|---|
| 215 | push (@$specific_options, "-level1_header", $self->{'level1_header'}) if $self->{'level1_header'};
|
|---|
| 216 | push (@$specific_options, "-level2_header", $self->{'level2_header'})if $self->{'level2_header'};
|
|---|
| 217 | push (@$specific_options, "-level3_header", $self->{'level3_header'}) if $self->{'level3_header'};
|
|---|
| 218 | push (@$specific_options, "-metadata_fields", $self->{'metadata_fields'}) if $self->{'metadata_fields'};
|
|---|
| 219 | push (@$specific_options, "-metadata_field_separator", $self->{'metadata_field_separator'}) if $self->{'metadata_field_separator'};
|
|---|
| 220 | push(@$specific_options, "-processing_tmp_files");
|
|---|
| 221 |
|
|---|
| 222 | }
|
|---|
| 223 |
|
|---|
| 224 | elsif ($secondary_plugin_name eq "HTMLPlugin") {
|
|---|
| 225 | push(@$specific_options, "-processing_tmp_files");
|
|---|
| 226 | push(@$specific_options,"-input_encoding", "utf8");
|
|---|
| 227 | push(@$specific_options,"-extract_language") if $self->{'extract_language'};
|
|---|
| 228 | push(@$specific_options, "-description_tags") if $self->{'description_tags'};
|
|---|
| 229 | # Instruct HTMLPlugin (when eventually accessed through read_into_doc_obj)
|
|---|
| 230 | # to extract these metadata fields from the HEAD META fields
|
|---|
| 231 | push(@$specific_options,"-metadata_fields","Title,GENERATOR,date,author<Creator>");
|
|---|
| 232 | }
|
|---|
| 233 |
|
|---|
| 234 | $self->load_secondary_plugins($class,$secondary_plugin_options,$hashArgOptLists);
|
|---|
| 235 |
|
|---|
| 236 | return bless $self, $class;
|
|---|
| 237 | }
|
|---|
| 238 |
|
|---|
| 239 | sub get_default_process_exp {
|
|---|
| 240 | my $self = shift (@_);
|
|---|
| 241 | if ($self->{'scripting_ext_working'}) {
|
|---|
| 242 | return q^(?i)\.(doc|dot|docx|odt)$^;
|
|---|
| 243 | }
|
|---|
| 244 | return q^(?i)\.(doc|dot)$^;
|
|---|
| 245 | }
|
|---|
| 246 |
|
|---|
| 247 | sub convert_post_process_old
|
|---|
| 248 | {
|
|---|
| 249 | my $self = shift (@_);
|
|---|
| 250 | my ($conv_filename) = @_;
|
|---|
| 251 |
|
|---|
| 252 | my $outhandle=$self->{'outhandle'};
|
|---|
| 253 |
|
|---|
| 254 | my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
|
|---|
| 255 |
|
|---|
| 256 | # read in file ($text will be in utf8)
|
|---|
| 257 | my $text = "";
|
|---|
| 258 | $self->read_file ($conv_filename, $encoding, $language, \$text);
|
|---|
| 259 |
|
|---|
| 260 | # turn any high bytes that aren't valid utf-8 into utf-8.
|
|---|
| 261 | #unicode::ensure_utf8(\$text);
|
|---|
| 262 |
|
|---|
| 263 | # Write it out again!
|
|---|
| 264 | #$self->utf8_write_file (\$text, $conv_filename);
|
|---|
| 265 | }
|
|---|
| 266 |
|
|---|
| 267 | # Modified to cache HTML files for efficieny reasons rather
|
|---|
| 268 | # than delete all. HTML is modified not to use IE's VML.
|
|---|
| 269 | # VML uses WML files, so these can be deleted.
|
|---|
| 270 | sub cleanup_tmp_area {
|
|---|
| 271 | my ($self) = @_;
|
|---|
| 272 | if (defined $self->{'files_dir'}) {
|
|---|
| 273 | my $html_files_dir = $self->{'files_dir'};
|
|---|
| 274 |
|
|---|
| 275 | if (opendir(DIN,$html_files_dir)) {
|
|---|
| 276 | my @wmz_files = grep( /\.wmz$/, readdir(DIN));
|
|---|
| 277 | foreach my $f (@wmz_files) {
|
|---|
| 278 | my $full_f = &util::filename_cat($html_files_dir,$f);
|
|---|
| 279 | &util::rm($full_f);
|
|---|
| 280 | }
|
|---|
| 281 | closedir(DIN);
|
|---|
| 282 | }
|
|---|
| 283 | else {
|
|---|
| 284 | # if HTML file has no supporting images, then no _files dir made
|
|---|
| 285 | # => do nothing
|
|---|
| 286 | }
|
|---|
| 287 | }
|
|---|
| 288 | }
|
|---|
| 289 |
|
|---|
| 290 |
|
|---|
| 291 | 1;
|
|---|
| 292 |
|
|---|
