[1676] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
[15871] | 3 | # SplitTextFile.pm - a plugin for splitting input files into segments that
|
---|
[1676] | 4 | # will then be individually processed.
|
---|
| 5 | #
|
---|
| 6 | #
|
---|
| 7 | # Copyright 2000 Gordon W. Paynter ([email protected])
|
---|
| 8 | # Copyright 2000 The New Zealand Digital Library Project
|
---|
| 9 | #
|
---|
| 10 | # A component of the Greenstone digital library software
|
---|
| 11 | # from the New Zealand Digital Library Project at the
|
---|
| 12 | # University of Waikato, New Zealand.
|
---|
| 13 | #
|
---|
| 14 | # This program is free software; you can redistribute it and/or modify
|
---|
| 15 | # it under the terms of the GNU General Public License as published by
|
---|
| 16 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 17 | # (at your option) any later version.
|
---|
| 18 | #
|
---|
| 19 | # This program is distributed in the hope that it will be useful,
|
---|
| 20 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 21 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 22 | # GNU General Public License for more details.
|
---|
| 23 | #
|
---|
| 24 | # You should have received a copy of the GNU General Public License
|
---|
| 25 | # along with this program; if not, write to the Free Software
|
---|
| 26 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 27 | #
|
---|
| 28 | ###########################################################################
|
---|
| 29 |
|
---|
| 30 |
|
---|
[15871] | 31 | # SplitTextFile is a plugin for splitting input files into segments that will
|
---|
[1676] | 32 | # then be individually processed.
|
---|
| 33 |
|
---|
| 34 | # This plugin should not be called directly. Instead, if you need to
|
---|
| 35 | # process input files that contain several documents, you should write a
|
---|
| 36 | # plugin with a process function that will handle one of those documents
|
---|
[15871] | 37 | # and have it inherit from SplitTextFile. See ReferPlug for an example.
|
---|
[1676] | 38 |
|
---|
| 39 |
|
---|
[15871] | 40 | package SplitTextFile;
|
---|
[1676] | 41 |
|
---|
[15871] | 42 | use ReadTextFile;
|
---|
[7830] | 43 | use gsprintf 'gsprintf';
|
---|
[1676] | 44 | use util;
|
---|
| 45 |
|
---|
[10254] | 46 | use strict;
|
---|
| 47 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
| 48 |
|
---|
[16700] | 49 | # SplitTextFile is a sub-class of ReadTextFile
|
---|
[8716] | 50 | sub BEGIN {
|
---|
[15871] | 51 | @SplitTextFile::ISA = ('ReadTextFile');
|
---|
[8716] | 52 | }
|
---|
[1676] | 53 |
|
---|
| 54 |
|
---|
[4744] | 55 | my $arguments =
|
---|
| 56 | [ { 'name' => "split_exp",
|
---|
[15871] | 57 | 'desc' => "{SplitTextFile.split_exp}",
|
---|
[6408] | 58 | 'type' => "regexp",
|
---|
[10218] | 59 | #'deft' => &get_default_split_exp(),
|
---|
| 60 | 'deft' => "",
|
---|
[4873] | 61 | 'reqd' => "no" } ];
|
---|
[4744] | 62 |
|
---|
[15871] | 63 | my $options = { 'name' => "SplitTextFile",
|
---|
| 64 | 'desc' => "{SplitTextFile.desc}",
|
---|
[6408] | 65 | 'abstract' => "yes",
|
---|
[4744] | 66 | 'inherits' => "yes",
|
---|
| 67 | 'args' => $arguments };
|
---|
[3540] | 68 |
|
---|
| 69 |
|
---|
[1676] | 70 | sub new {
|
---|
[10218] | 71 | my ($class) = shift (@_);
|
---|
| 72 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 73 | push(@$pluginlist, $class);
|
---|
[1676] | 74 |
|
---|
[15871] | 75 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 76 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
[1676] | 77 |
|
---|
[15871] | 78 | my $self = new ReadTextFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
[10218] | 79 |
|
---|
[9357] | 80 | $self->{'textcat_store'} = {};
|
---|
| 81 | $self->{'metapass_srcdoc'} = {}; # which segments have valid metadata_srcdoc
|
---|
[1676] | 82 | return bless $self, $class;
|
---|
| 83 | }
|
---|
| 84 |
|
---|
| 85 | sub init {
|
---|
| 86 | my $self = shift (@_);
|
---|
[3094] | 87 | my ($verbosity, $outhandle, $failhandle) = @_;
|
---|
[1676] | 88 |
|
---|
[15871] | 89 | $self->ReadTextFile::init($verbosity, $outhandle, $failhandle);
|
---|
[1676] | 90 |
|
---|
[15871] | 91 | # why is this is init and not in new??
|
---|
[2007] | 92 | if ((!defined $self->{'process_exp'}) || ($self->{'process_exp'} eq "")) {
|
---|
| 93 |
|
---|
| 94 | $self->{'process_exp'} = $self->get_default_process_exp ();
|
---|
| 95 | if ($self->{'process_exp'} eq "") {
|
---|
[11090] | 96 | warn ref($self) . " Warning: plugin has no process_exp\n";
|
---|
[2007] | 97 | }
|
---|
| 98 | }
|
---|
| 99 |
|
---|
| 100 |
|
---|
[1676] | 101 | # set split_exp to default unless explicitly set
|
---|
| 102 | if (!$self->{'split_exp'}) {
|
---|
| 103 | $self->{'split_exp'} = $self->get_default_split_exp ();
|
---|
| 104 | }
|
---|
| 105 |
|
---|
| 106 | }
|
---|
| 107 |
|
---|
| 108 | # This plugin recurs over the segments it finds
|
---|
| 109 | sub is_recursive {
|
---|
| 110 | return 1;
|
---|
| 111 | }
|
---|
| 112 |
|
---|
| 113 | # By default, we split the input text at blank lines
|
---|
| 114 | sub get_default_split_exp {
|
---|
| 115 | return q^\n\s*\n^;
|
---|
| 116 | }
|
---|
| 117 |
|
---|
[9357] | 118 | sub metadata_read {
|
---|
| 119 | my $self = shift (@_);
|
---|
[17300] | 120 | my ($pluginfo, $base_dir, $file, $block_hash, $extrametakeys, $extrametadata, $processor, $maxdocs, $gli) = @_;
|
---|
[1676] | 121 |
|
---|
[15871] | 122 | # returns 1 if matches process_exp, and has done blocking in the meantime
|
---|
[16392] | 123 | my $matched = $self->SUPER::metadata_read($pluginfo, $base_dir, $file,
|
---|
| 124 | $block_hash,
|
---|
[17300] | 125 | $extrametakeys,
|
---|
[9357] | 126 | $extrametadata, $processor,
|
---|
| 127 | $maxdocs, $gli);
|
---|
[10254] | 128 | my $split_matched = undef;
|
---|
[9357] | 129 |
|
---|
| 130 | if ($matched) {
|
---|
| 131 |
|
---|
| 132 | my $outhandle = $self->{'outhandle'};
|
---|
| 133 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
| 134 |
|
---|
| 135 | my $plugin_name = ref ($self);
|
---|
| 136 | $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
---|
| 137 |
|
---|
| 138 | $self->{'metapass_srcdoc'}->{$file} = {};
|
---|
| 139 |
|
---|
| 140 | # Do encoding stuff
|
---|
| 141 | my ($language, $encoding) = $self->textcat_get_language_encoding ($filename);
|
---|
| 142 | my $le_rec = { 'language' => $language, 'encoding' => $encoding };
|
---|
| 143 | $self->{'textcat_store'}->{$file} = $le_rec;
|
---|
| 144 |
|
---|
| 145 | # Read in file ($text will be in utf8)
|
---|
| 146 | my $text = "";
|
---|
| 147 | $self->read_file ($filename, $encoding, $language, \$text);
|
---|
| 148 |
|
---|
[13197] | 149 |
|
---|
[9357] | 150 | if ($text !~ /\w/) {
|
---|
[15871] | 151 | gsprintf($outhandle, "$plugin_name: {ReadTextFile.file_has_no_text}\n",
|
---|
[9357] | 152 | $file)
|
---|
| 153 | if $self->{'verbosity'};
|
---|
| 154 |
|
---|
| 155 | my $failhandle = $self->{'failhandle'};
|
---|
| 156 | print $failhandle "$file: " . ref($self) . ": file contains no text\n";
|
---|
| 157 | $self->{'num_not_processed'} ++;
|
---|
| 158 |
|
---|
| 159 | $self->{'textcat_store'}->{$file} = undef;
|
---|
| 160 |
|
---|
| 161 | return 0;
|
---|
| 162 | }
|
---|
| 163 |
|
---|
| 164 |
|
---|
| 165 | # Split the text into several smaller segments
|
---|
| 166 | my $split_exp = $self->{'split_exp'};
|
---|
[13197] | 167 | my @tmp = split(/$split_exp/i, $text);
|
---|
| 168 | my @segments =();
|
---|
| 169 | ## get rid of empty segments
|
---|
| 170 | foreach my $seg (@tmp){
|
---|
| 171 | if ($seg ne ""){
|
---|
| 172 | push @segments, $seg;
|
---|
| 173 | }
|
---|
| 174 | }
|
---|
| 175 |
|
---|
[15871] | 176 | print $outhandle "SplitTextFile found " . (scalar @segments) . " documents in $filename\n"
|
---|
[9357] | 177 | if $self->{'verbosity'};
|
---|
| 178 |
|
---|
[9493] | 179 | $self->{'split_segments'}->{$file} = \@segments;
|
---|
[9357] | 180 | $split_matched = scalar(@segments);
|
---|
| 181 | }
|
---|
| 182 |
|
---|
| 183 | return $split_matched;
|
---|
| 184 | }
|
---|
| 185 |
|
---|
| 186 |
|
---|
| 187 |
|
---|
[1676] | 188 | # The read function opens a file and splits it into parts.
|
---|
| 189 | # Each part is sent to the process function
|
---|
| 190 | #
|
---|
| 191 | # Returns: Number of document objects created (or undef if it fails)
|
---|
| 192 |
|
---|
| 193 | sub read {
|
---|
| 194 | my $self = shift (@_);
|
---|
[16392] | 195 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
[1676] | 196 | my $outhandle = $self->{'outhandle'};
|
---|
| 197 | my $verbosity = $self->{'verbosity'};
|
---|
| 198 |
|
---|
[16392] | 199 | # can we process this file??
|
---|
| 200 | my ($filename_full_path, $filename_no_path) = &util::get_full_filenames($base_dir, $file);
|
---|
| 201 | return undef unless $self->can_process_this_file($filename_full_path);
|
---|
[11090] | 202 |
|
---|
[1676] | 203 | $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
---|
[1894] | 204 |
|
---|
[9357] | 205 | my $le_rec = $self->{'textcat_store'}->{$file};
|
---|
| 206 | if (!defined $le_rec) {
|
---|
| 207 | # means no text was found;
|
---|
| 208 | return 0; # not processed but no point in passing it on
|
---|
| 209 | }
|
---|
[2845] | 210 |
|
---|
[16104] | 211 | print STDERR "<Processing n='$file' p='$self->{'plugin_type'}'>\n" if ($gli);
|
---|
| 212 | print $outhandle "$self->{'plugin_type'} processing $file\n"
|
---|
| 213 | if $self->{'verbosity'} > 1;
|
---|
| 214 |
|
---|
[9357] | 215 | my $language = $le_rec->{'language'};
|
---|
| 216 | my $encoding = $le_rec->{'encoding'};
|
---|
| 217 | $self->{'textcat_store'}->{$file} = undef;
|
---|
[1676] | 218 |
|
---|
[9493] | 219 | my $segments = $self->{'split_segments'}->{$file};
|
---|
| 220 | $self->{'split_segments'}->{$file} = undef;
|
---|
[2845] | 221 |
|
---|
[1676] | 222 | # Process each segment in turn
|
---|
| 223 | my ($count, $segment, $segtext, $status, $id);
|
---|
| 224 | $segment = 0;
|
---|
| 225 | $count = 0;
|
---|
[9357] | 226 | foreach $segtext (@$segments) {
|
---|
[13197] | 227 | $segment++;
|
---|
[2845] | 228 |
|
---|
[9357] | 229 | if (defined $self->{'metapass_srcdoc'}->{$file}->{$segment}) {
|
---|
| 230 | # metadata is attached to a srcdoc
|
---|
| 231 | next;
|
---|
| 232 | }
|
---|
| 233 |
|
---|
[1676] | 234 | # create a new document
|
---|
[18327] | 235 | my $doc_obj = new doc ($filename_full_path, "indexed_doc", $self->{'file_rename_method'});
|
---|
[1894] | 236 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Language", $language);
|
---|
| 237 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Encoding", $encoding);
|
---|
[2845] | 238 | my ($filemeta) = $file =~ /([^\\\/]+)$/;
|
---|
[15871] | 239 | $self->set_Source_metadata($doc_obj, $filemeta, $encoding);
|
---|
[6137] | 240 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "SourceSegment", "$segment");
|
---|
[2845] | 241 | if ($self->{'cover_image'}) {
|
---|
[16392] | 242 | $self->associate_cover_image($doc_obj, $filename_full_path);
|
---|
[2845] | 243 | }
|
---|
[7508] | 244 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Plugin", "$self->{'plugin_type'}");
|
---|
[8121] | 245 | #$doc_obj->add_metadata($doc_obj->get_top_section(), "FileFormat", "Split");
|
---|
| 246 |
|
---|
[1676] | 247 | # Calculate a "base" document ID.
|
---|
| 248 | if (!defined $id) {
|
---|
[17026] | 249 | $id = $self->get_base_OID($doc_obj);
|
---|
[1676] | 250 | }
|
---|
| 251 |
|
---|
| 252 | # include any metadata passed in from previous plugins
|
---|
| 253 | # note that this metadata is associated with the top level section
|
---|
| 254 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
---|
| 255 |
|
---|
| 256 | # do plugin specific processing of doc_obj
|
---|
[16104] | 257 | print $outhandle "segment $segment\n" if ($self->{'verbosity'});
|
---|
[11335] | 258 | $status = $self->process (\$segtext, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli);
|
---|
[1676] | 259 | if (!defined $status) {
|
---|
| 260 | print $outhandle "WARNING - no plugin could process segment $segment of $file\n"
|
---|
| 261 | if ($verbosity >= 2);
|
---|
| 262 | next;
|
---|
| 263 | }
|
---|
[3537] | 264 | # If the plugin returned 0, it threw away this part
|
---|
| 265 | if ($status == 0) {
|
---|
| 266 | next;
|
---|
| 267 | }
|
---|
[1676] | 268 | $count += $status;
|
---|
| 269 |
|
---|
| 270 | # do any automatic metadata extraction
|
---|
| 271 | $self->auto_extract_metadata ($doc_obj);
|
---|
| 272 |
|
---|
| 273 | # add an OID
|
---|
[17026] | 274 | $self->add_OID($doc_obj, $id, $segment);
|
---|
[2484] | 275 |
|
---|
[1676] | 276 | # process the document
|
---|
| 277 | $processor->process($doc_obj);
|
---|
[2845] | 278 |
|
---|
| 279 | $self->{'num_processed'} ++;
|
---|
[1676] | 280 | }
|
---|
| 281 |
|
---|
[9357] | 282 | delete $self->{'metapass_srcdoc'}->{$file};
|
---|
| 283 |
|
---|
[1676] | 284 | # Return number of document objects produced
|
---|
| 285 | return $count;
|
---|
| 286 | }
|
---|
| 287 |
|
---|
[17026] | 288 | sub get_base_OID {
|
---|
| 289 | my $self = shift(@_);
|
---|
| 290 | my ($doc_obj) = @_;
|
---|
| 291 |
|
---|
| 292 | $self->SUPER::add_OID($doc_obj);
|
---|
| 293 | return $doc_obj->get_OID();
|
---|
| 294 | }
|
---|
| 295 |
|
---|
| 296 | sub add_OID {
|
---|
[2484] | 297 | my $self = shift (@_);
|
---|
[17026] | 298 | my ($doc_obj, $id, $segment) = @_;
|
---|
| 299 |
|
---|
| 300 | my $full_id = $id . "s" . $segment;
|
---|
| 301 | if ($self->{'OIDtype'} eq "assigned") {
|
---|
| 302 | my $identifier = $doc_obj->get_metadata_element ($doc_obj->get_top_section(), $self->{'OIDmetadata'});
|
---|
| 303 | if (defined $identifier && $identifier ne "") {
|
---|
| 304 | $full_id = $identifier;
|
---|
[17033] | 305 | $full_id =~ s/\.//g; #remove any periods
|
---|
[17026] | 306 | if ($full_id =~ /^[\d]*$/) {
|
---|
| 307 | $full_id = "D" . $full_id;
|
---|
| 308 | print STDERR "OID only contains numbers, adding a D\n";
|
---|
| 309 | }
|
---|
| 310 | }
|
---|
| 311 | }
|
---|
| 312 | $doc_obj->set_OID($full_id);
|
---|
[2484] | 313 | }
|
---|
| 314 |
|
---|
[17026] | 315 |
|
---|
[1676] | 316 | 1;
|
---|