| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # PostScriptPlugin.pm -- plugin to process PostScript files
|
|---|
| 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 |
|
|---|
| 26 | package PostScriptPlugin;
|
|---|
| 27 |
|
|---|
| 28 | use ConvertBinaryFile;
|
|---|
| 29 | use ReadTextFile; # for read_file in convert_post_process. do we need it?
|
|---|
| 30 | use sorttools;
|
|---|
| 31 |
|
|---|
| 32 | use strict;
|
|---|
| 33 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
|---|
| 34 |
|
|---|
| 35 | sub BEGIN {
|
|---|
| 36 | @PostScriptPlugin::ISA = ('ConvertBinaryFile', 'ReadTextFile');
|
|---|
| 37 | }
|
|---|
| 38 |
|
|---|
| 39 | my $convert_to_list =
|
|---|
| 40 | [ { 'name' => "auto",
|
|---|
| 41 | 'desc' => "{ConvertBinaryFile.convert_to.auto}" },
|
|---|
| 42 | { 'name' => "text",
|
|---|
| 43 | 'desc' => "{ConvertBinaryFile.convert_to.text}" },
|
|---|
| 44 | { 'name' => "pagedimg_jpg",
|
|---|
| 45 | 'desc' => "{ConvertBinaryFile.convert_to.pagedimg_jpg}" },
|
|---|
| 46 | { 'name' => "pagedimg_gif",
|
|---|
| 47 | 'desc' => "{ConvertBinaryFile.convert_to.pagedimg_gif}" },
|
|---|
| 48 | { 'name' => "pagedimg_png",
|
|---|
| 49 | 'desc' => "{ConvertBinaryFile.convert_to.pagedimg_png}" }
|
|---|
| 50 | ];
|
|---|
| 51 |
|
|---|
| 52 | my $arguments =
|
|---|
| 53 | [ { 'name' => "convert_to",
|
|---|
| 54 | 'desc' => "{ConvertBinaryFile.convert_to}",
|
|---|
| 55 | 'type' => "enum",
|
|---|
| 56 | 'reqd' => "yes",
|
|---|
| 57 | 'list' => $convert_to_list,
|
|---|
| 58 | 'deft' => "text" },
|
|---|
| 59 | { 'name' => "process_exp",
|
|---|
| 60 | 'desc' => "{BasePlugin.process_exp}",
|
|---|
| 61 | 'type' => "regexp",
|
|---|
| 62 | 'deft' => &get_default_process_exp(),
|
|---|
| 63 | 'reqd' => "no" },
|
|---|
| 64 | { 'name' => "block_exp",
|
|---|
| 65 | 'desc' => "{BasePlugin.block_exp}",
|
|---|
| 66 | 'type' => 'regexp',
|
|---|
| 67 | 'deft' => &get_default_block_exp() },
|
|---|
| 68 | { 'name' => "extract_date",
|
|---|
| 69 | 'desc' => "{PostScriptPlugin.extract_date}",
|
|---|
| 70 | 'type' => "flag" },
|
|---|
| 71 | { 'name' => "extract_pages",
|
|---|
| 72 | 'desc' => "{PostScriptPlugin.extract_pages}",
|
|---|
| 73 | 'type' => "flag" },
|
|---|
| 74 | { 'name' => "extract_title",
|
|---|
| 75 | 'desc' => "{PostScriptPlugin.extract_title}",
|
|---|
| 76 | 'type' => "flag" } ];
|
|---|
| 77 |
|
|---|
| 78 | my $options = { 'name' => "PostScriptPlugin",
|
|---|
| 79 | 'desc' => "{PostScriptPlugin.desc}",
|
|---|
| 80 | 'abstract' => "no",
|
|---|
| 81 | 'inherits' => "yes",
|
|---|
| 82 | 'srcreplaceable' => "yes", # Source docs in postscript format can be replaced with GS-generated html
|
|---|
| 83 | 'args' => $arguments };
|
|---|
| 84 |
|
|---|
| 85 | sub new {
|
|---|
| 86 | my ($class) = shift (@_);
|
|---|
| 87 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
|---|
| 88 | push(@$pluginlist, $class);
|
|---|
| 89 |
|
|---|
| 90 | #push(@$inputargs,"-convert_to");
|
|---|
| 91 | #push(@$inputargs,"text");
|
|---|
| 92 | push(@$inputargs,"-title_sub");
|
|---|
| 93 | push(@$inputargs,'^(Page\s+\d+)?(\s*1\s+)?');
|
|---|
| 94 |
|
|---|
| 95 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
|---|
| 96 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
|---|
| 97 |
|
|---|
| 98 | my $self = new ConvertBinaryFile($pluginlist, $inputargs, $hashArgOptLists);
|
|---|
| 99 |
|
|---|
| 100 | if ($self->{'info_only'}) {
|
|---|
| 101 | # don't worry about any options etc
|
|---|
| 102 | return bless $self, $class;
|
|---|
| 103 | }
|
|---|
| 104 |
|
|---|
| 105 | $self->{'filename_extension'} = "ps";
|
|---|
| 106 | $self->{'file_type'} = "PS";
|
|---|
| 107 |
|
|---|
| 108 | my $secondary_plugin_options = $self->{'secondary_plugin_options'};
|
|---|
| 109 |
|
|---|
| 110 | if (!defined $secondary_plugin_options->{'TextPlugin'}) {
|
|---|
| 111 | $secondary_plugin_options->{'TextPlugin'} = [];
|
|---|
| 112 | }
|
|---|
| 113 |
|
|---|
| 114 | if (!defined $secondary_plugin_options->{'HTMLPlugin'}) {
|
|---|
| 115 | $secondary_plugin_options->{'HTMLPlugin'} = [];
|
|---|
| 116 | }
|
|---|
| 117 |
|
|---|
| 118 | my $text_options = $secondary_plugin_options->{'TextPlugin'};
|
|---|
| 119 | my $html_options = $secondary_plugin_options->{'HTMLPlugin'};
|
|---|
| 120 |
|
|---|
| 121 | if (defined $self->{'convert_to'} && $self->{'convert_to'} =~ m/(pagedimage|pagedimg).*/i) {
|
|---|
| 122 | if (!defined $secondary_plugin_options->{'PagedImagePlugin'}){
|
|---|
| 123 | $secondary_plugin_options->{'PagedImagePlugin'} = [];
|
|---|
| 124 | my $pagedimg_options = $secondary_plugin_options->{'PagedImagePlugin'};
|
|---|
| 125 | push(@$pagedimg_options, "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
|---|
| 126 | push(@$pagedimg_options, "-file_rename_method", "none");
|
|---|
| 127 | }
|
|---|
| 128 | }
|
|---|
| 129 | # following title_sub removes "Page 1" added by ps2ascii, and a leading
|
|---|
| 130 | # "1", which is often the page number at the top of the page. Bad Luck
|
|---|
| 131 | # if your document title actually starts with "1 " - is there a better way?
|
|---|
| 132 | #$self->{'input_encoding'} = "utf8";
|
|---|
| 133 | #$self->{'extract_language'} = 1;
|
|---|
| 134 | push(@$text_options, "-input_encoding", "utf8");
|
|---|
| 135 | push(@$text_options,"-extract_language") if $self->{'extract_language'};
|
|---|
| 136 | push(@$text_options , "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
|---|
| 137 |
|
|---|
| 138 | push(@$text_options, "-file_rename_method", "none");
|
|---|
| 139 | push(@$html_options, "-file_rename_method", "none");
|
|---|
| 140 |
|
|---|
| 141 | $self = bless $self, $class;
|
|---|
| 142 | # used for convert_post_process
|
|---|
| 143 | $self->{'input_encoding'} = "auto";
|
|---|
| 144 | $self->{'default_encoding'} = "utf8";
|
|---|
| 145 |
|
|---|
| 146 | $self->load_secondary_plugins($class,$secondary_plugin_options, $hashArgOptLists);
|
|---|
| 147 |
|
|---|
| 148 | return $self;
|
|---|
| 149 | }
|
|---|
| 150 |
|
|---|
| 151 |
|
|---|
| 152 | sub get_default_block_exp {
|
|---|
| 153 | my $self = shift (@_);
|
|---|
| 154 |
|
|---|
| 155 | return q^(?i)\.(eps)$^;
|
|---|
| 156 | }
|
|---|
| 157 |
|
|---|
| 158 | sub get_default_process_exp {
|
|---|
| 159 | my $self = shift (@_);
|
|---|
| 160 |
|
|---|
| 161 | return q^(?i)\.ps$^;
|
|---|
| 162 | }
|
|---|
| 163 |
|
|---|
| 164 | # this has been commented out in other plugins. do we need it here?
|
|---|
| 165 | # ps files are converted to images (item file should be in utf8) or text (uses pstoascii), so we shouldn't need to ensure utf8
|
|---|
| 166 | sub convert_post_process
|
|---|
| 167 | {
|
|---|
| 168 | my $self = shift (@_);
|
|---|
| 169 | my ($conv_filename) = @_;
|
|---|
| 170 |
|
|---|
| 171 | my $outhandle=$self->{'outhandle'};
|
|---|
| 172 |
|
|---|
| 173 | my ($language, $encoding) = $self->textcat_get_language_encoding ($conv_filename);
|
|---|
| 174 |
|
|---|
| 175 | # read in file ($text will be in utf8)
|
|---|
| 176 | my $text = "";
|
|---|
| 177 | $self->read_file ($conv_filename, $encoding, $language, \$text);
|
|---|
| 178 |
|
|---|
| 179 | # turn any high bytes that aren't valid utf-8 into utf-8.
|
|---|
| 180 | unicode::ensure_utf8(\$text);
|
|---|
| 181 |
|
|---|
| 182 | # Write it out again!
|
|---|
| 183 | $self->utf8_write_file (\$text, $conv_filename);
|
|---|
| 184 | }
|
|---|
| 185 |
|
|---|
| 186 | sub extract_metadata_from_postscript {
|
|---|
| 187 | my $self = shift (@_);
|
|---|
| 188 |
|
|---|
| 189 | my ($filename,$doc) = @_;
|
|---|
| 190 |
|
|---|
| 191 | my $section = $doc->get_top_section();
|
|---|
| 192 |
|
|---|
| 193 | my $title_found = 0;
|
|---|
| 194 | my $pages_found = 0;
|
|---|
| 195 | my $date_found = 0;
|
|---|
| 196 |
|
|---|
| 197 | print STDERR "PostScriptPlugin: extracting PostScript metadata from \"$filename\"\n"
|
|---|
| 198 | if $self->{'verbosity'} > 1;
|
|---|
| 199 |
|
|---|
| 200 | open(INPUT, "<$filename");
|
|---|
| 201 | my $date;
|
|---|
| 202 |
|
|---|
| 203 | while(my $line =<INPUT>) {
|
|---|
| 204 | if ($self->{'extract_title'} && !$title_found) {
|
|---|
| 205 | foreach my $word ($line =~ m|Title: ([-A-Za-z0-9@/\/\(\):,. ]*)|g) {
|
|---|
| 206 | my $new_word = $word;
|
|---|
| 207 | $new_word =~ s/\(Untitled\)//i;
|
|---|
| 208 | $new_word =~ s/\(Microsoft Word\)//i;
|
|---|
| 209 | $new_word =~ s/Microsoft Word//i;
|
|---|
| 210 | $new_word =~ s/^\(//i;
|
|---|
| 211 | $new_word =~ s/\)$//i;
|
|---|
| 212 | $new_word =~ s/^ - //i;
|
|---|
| 213 | if ($new_word ne "") {
|
|---|
| 214 | $doc->add_utf8_metadata($section, "Title", $new_word );
|
|---|
| 215 | $title_found = 1;
|
|---|
| 216 | }
|
|---|
| 217 | }
|
|---|
| 218 | }
|
|---|
| 219 | if ($self->{'extract_date'} && !$date_found) {
|
|---|
| 220 | foreach my $word ($line =~ m/(Creation[-A-Za-z0-9@\/\(\):,. ]*)/g) {
|
|---|
| 221 | if ($word =~ m/ ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) ?[0-9: ]+ ([0-9]{4})/) {
|
|---|
| 222 | $date = &sorttools::format_date($2,$1,$3);
|
|---|
| 223 | if (defined $date) {
|
|---|
| 224 | $doc->add_utf8_metadata($section, "Date", $date );
|
|---|
| 225 | }
|
|---|
| 226 | }
|
|---|
| 227 | if ($word =~ m/D:([0-9]{4})([0-9]{2})([0-9]{2})[0-9]{6}\)/) {
|
|---|
| 228 | $date = &sorttools::format_date($3,$2,$1);
|
|---|
| 229 | if (defined $date) {
|
|---|
| 230 | $doc->add_utf8_metadata($section, "Date", $date );
|
|---|
| 231 | }
|
|---|
| 232 | }
|
|---|
| 233 | if ($word =~ m/CreationDate: ([0-9]{4}) ([A-Za-z][A-Za-z][A-Za-z]) ([0-9 ][0-9]) [0-9:]*/) {
|
|---|
| 234 | $date = &sorttools::format_date($3,$2,$1);
|
|---|
| 235 | if (defined $date) {
|
|---|
| 236 | $doc->add_utf8_metadata($section, "Date", $date );
|
|---|
| 237 | }
|
|---|
| 238 | }
|
|---|
| 239 | $date_found = 1;
|
|---|
| 240 | }
|
|---|
| 241 | }
|
|---|
| 242 | if ($self->{'extract_pages'} && !$pages_found) {
|
|---|
| 243 | foreach my $word ($line =~ m/(Pages: [0-9]*)/g) {
|
|---|
| 244 | my $digits = $word;
|
|---|
| 245 | $digits =~ s/[^0-9]//g;
|
|---|
| 246 | if ($digits ne "" && $digits ne "0") {
|
|---|
| 247 | $doc->add_utf8_metadata($section, "Pages", $digits );
|
|---|
| 248 | $pages_found = 1;
|
|---|
| 249 | }
|
|---|
| 250 | }
|
|---|
| 251 | }
|
|---|
| 252 | }
|
|---|
| 253 | }
|
|---|
| 254 |
|
|---|
| 255 | # do plugin specific processing of doc_obj
|
|---|
| 256 | sub process {
|
|---|
| 257 | my $self = shift (@_);
|
|---|
| 258 | my ($pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
|---|
| 259 |
|
|---|
| 260 | my $filename = &util::filename_cat($base_dir,$file);
|
|---|
| 261 | $self->extract_metadata_from_postscript($filename, $doc_obj);
|
|---|
| 262 |
|
|---|
| 263 | return $self->SUPER::process(@_);
|
|---|
| 264 |
|
|---|
| 265 | }
|
|---|
| 266 |
|
|---|
| 267 |
|
|---|
| 268 | 1;
|
|---|
| 269 |
|
|---|
