[12606] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
[15872] | 3 | # MetadataCSVPlugin.pm -- A plugin for metadata in comma-separated value format
|
---|
[12606] | 4 | #
|
---|
| 5 | # A component of the Greenstone digital library software
|
---|
| 6 | # from the New Zealand Digital Library Project at the
|
---|
| 7 | # University of Waikato, New Zealand.
|
---|
| 8 | #
|
---|
| 9 | # Copyright 2006 New Zealand Digital Library Project
|
---|
| 10 | #
|
---|
| 11 | # This program is free software; you can redistribute it and/or modify
|
---|
| 12 | # it under the terms of the GNU General Public License as published by
|
---|
| 13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 14 | # (at your option) any later version.
|
---|
| 15 | #
|
---|
| 16 | # This program is distributed in the hope that it will be useful,
|
---|
| 17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 19 | # GNU General Public License for more details.
|
---|
| 20 | #
|
---|
| 21 | # You should have received a copy of the GNU General Public License
|
---|
| 22 | # along with this program; if not, write to the Free Software
|
---|
| 23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 24 | #
|
---|
| 25 | ###########################################################################
|
---|
| 26 |
|
---|
[15872] | 27 | package MetadataCSVPlugin;
|
---|
[12606] | 28 |
|
---|
| 29 |
|
---|
[31492] | 30 | use BaseImporter;
|
---|
[24547] | 31 | use MetadataRead;
|
---|
| 32 |
|
---|
[12606] | 33 | use strict;
|
---|
[22852] | 34 | no strict 'refs';
|
---|
[24951] | 35 |
|
---|
| 36 | use extrametautil;
|
---|
[17717] | 37 | use multiread;
|
---|
[24971] | 38 | use util;
|
---|
[12606] | 39 |
|
---|
[24756] | 40 | use Encode;
|
---|
[17717] | 41 |
|
---|
[24547] | 42 | # methods with identical signatures take precedence in the order given in the ISA list.
|
---|
[12606] | 43 | sub BEGIN {
|
---|
[31492] | 44 | @MetadataCSVPlugin::ISA = ('MetadataRead', 'BaseImporter');
|
---|
[12606] | 45 | }
|
---|
| 46 |
|
---|
| 47 |
|
---|
[16386] | 48 | my $arguments = [
|
---|
| 49 | { 'name' => "process_exp",
|
---|
[31492] | 50 | 'desc' => "{BaseImporter.process_exp}",
|
---|
[12606] | 51 | 'type' => "regexp",
|
---|
| 52 | 'reqd' => "no",
|
---|
[16386] | 53 | 'deft' => &get_default_process_exp() }
|
---|
[12606] | 54 |
|
---|
[16386] | 55 | ];
|
---|
[12606] | 56 |
|
---|
[16386] | 57 |
|
---|
[15872] | 58 | my $options = { 'name' => "MetadataCSVPlugin",
|
---|
| 59 | 'desc' => "{MetadataCSVPlugin.desc}",
|
---|
[12606] | 60 | 'abstract' => "no",
|
---|
| 61 | 'inherits' => "yes",
|
---|
| 62 | 'args' => $arguments };
|
---|
| 63 |
|
---|
| 64 |
|
---|
| 65 | sub new
|
---|
| 66 | {
|
---|
| 67 | my ($class) = shift (@_);
|
---|
| 68 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 69 | push(@$pluginlist, $class);
|
---|
| 70 |
|
---|
[15872] | 71 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 72 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
[12606] | 73 |
|
---|
[31492] | 74 | my $self = new BaseImporter($pluginlist, $inputargs, $hashArgOptLists);
|
---|
[12606] | 75 |
|
---|
| 76 | return bless $self, $class;
|
---|
| 77 | }
|
---|
| 78 |
|
---|
| 79 |
|
---|
| 80 | sub get_default_process_exp
|
---|
| 81 | {
|
---|
| 82 | return q^(?i)\.csv$^;
|
---|
| 83 | }
|
---|
| 84 |
|
---|
[20771] | 85 | sub file_block_read {
|
---|
| 86 | my $self = shift (@_);
|
---|
| 87 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $gli) = @_;
|
---|
| 88 |
|
---|
| 89 | my ($filename_full_path, $filename_no_path) = &util::get_full_filenames($base_dir, $file);
|
---|
| 90 |
|
---|
| 91 | if (!-f $filename_full_path || !$self->can_process_this_file($filename_full_path)) {
|
---|
| 92 | return undef; # can't recognise
|
---|
| 93 | }
|
---|
| 94 |
|
---|
| 95 | # set this so we know this is a metadata file - needed for incremental
|
---|
| 96 | # build
|
---|
| 97 | # if this file changes, then we need to reimport everything
|
---|
| 98 | $block_hash->{'metadata_files'}->{$filename_full_path} = 1;
|
---|
| 99 |
|
---|
| 100 | return 1;
|
---|
| 101 | }
|
---|
| 102 |
|
---|
[12606] | 103 | sub metadata_read
|
---|
| 104 | {
|
---|
| 105 | my $self = shift (@_);
|
---|
[19493] | 106 | my ($pluginfo, $base_dir, $file, $block_hash,
|
---|
| 107 | $extrametakeys, $extrametadata, $extrametafile,
|
---|
[23212] | 108 | $processor, $gli, $aux) = @_;
|
---|
[12606] | 109 |
|
---|
| 110 | # Read metadata from CSV files
|
---|
| 111 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
| 112 | if ($filename !~ /\.csv$/ || !-f $filename) {
|
---|
| 113 | return undef;
|
---|
| 114 | }
|
---|
[15872] | 115 | print STDERR "\n<Processing n='$file' p='MetadataCSVPlugin'>\n" if ($gli);
|
---|
| 116 | print STDERR "MetadataCSVPlugin: processing $file\n" if ($self->{'verbosity'}) > 1;
|
---|
[12606] | 117 |
|
---|
[22852] | 118 | my $outhandle = $self->{'outhandle'};
|
---|
| 119 | my $failhandle = $self->{'failhandle'};
|
---|
| 120 |
|
---|
[16386] | 121 | # add the file to the block list so that it won't be processed in read, as we will do all we can with it here
|
---|
[31480] | 122 | $self->block_raw_filename($block_hash,$filename);
|
---|
[16386] | 123 |
|
---|
[24736] | 124 |
|
---|
[12606] | 125 | # Read the CSV file to get the metadata
|
---|
| 126 | my $csv_file_content;
|
---|
| 127 | open(CSV_FILE, "$filename");
|
---|
| 128 | my $csv_file_reader = new multiread();
|
---|
[15872] | 129 | $csv_file_reader->set_handle('MetadataCSVPlugin::CSV_FILE');
|
---|
[12606] | 130 | $csv_file_reader->read_file(\$csv_file_content);
|
---|
[24736] | 131 |
|
---|
| 132 | # Would be nice if MetadataCSVPlugin was extended to support a minus
|
---|
| 133 | # option to choose the character encoding the CSV file is in
|
---|
| 134 | # For now we will assume it is always in UTF8
|
---|
| 135 | $csv_file_content = decode("utf8",$csv_file_content);
|
---|
| 136 |
|
---|
[12606] | 137 | close(CSV_FILE);
|
---|
| 138 |
|
---|
| 139 | # Split the file into lines and read the first line (contains the metadata names)
|
---|
[13173] | 140 | $csv_file_content =~ s/\r/\n/g; # Handle non-Unix line endings
|
---|
| 141 | $csv_file_content =~ s/\n+/\n/g;
|
---|
| 142 | my @csv_file_lines = split(/\n/, $csv_file_content);
|
---|
[12606] | 143 | my $csv_file_field_line = shift(@csv_file_lines);
|
---|
| 144 | my @csv_file_fields = split(/\,/, $csv_file_field_line);
|
---|
[13174] | 145 | my $found_filename_field = 0;
|
---|
[12606] | 146 | for (my $i = 0; $i < scalar(@csv_file_fields); $i++) {
|
---|
[27321] | 147 | # Remove any spaces from the field names, and surrounding quotes too
|
---|
[12606] | 148 | $csv_file_fields[$i] =~ s/ //g;
|
---|
[27321] | 149 | $csv_file_fields[$i] =~ s/^"//;
|
---|
| 150 | $csv_file_fields[$i] =~ s/"$//;
|
---|
| 151 |
|
---|
[13174] | 152 | if ($csv_file_fields[$i] eq "Filename") {
|
---|
| 153 | $found_filename_field = 1;
|
---|
| 154 | }
|
---|
[12606] | 155 | }
|
---|
| 156 |
|
---|
[13174] | 157 | if (!$found_filename_field) {
|
---|
[22852] | 158 | $self->print_error($outhandle, $failhandle, $gli, $filename, "No Filename field in CSV file");
|
---|
[13174] | 159 | return -1; # error
|
---|
| 160 | }
|
---|
[12606] | 161 | # Read each line of the file and assign the metadata appropriately
|
---|
| 162 | foreach my $csv_line (@csv_file_lines) {
|
---|
| 163 | # Ignore lines containing only whitespace
|
---|
| 164 | next if ($csv_line =~ /^\s*$/);
|
---|
[13174] | 165 | my $orig_csv_line = $csv_line;
|
---|
[12606] | 166 | # Build a hash of metadata name to metadata value for this line
|
---|
| 167 | my %csv_line_metadata;
|
---|
| 168 | my $i = 0;
|
---|
| 169 | $csv_line .= ","; # To make the regular expressions simpler
|
---|
| 170 | while ($csv_line ne "") {
|
---|
| 171 | # Metadata values containing commas are quoted
|
---|
| 172 | if ($csv_line =~ s/^\"(.*?)\"\,//) {
|
---|
| 173 | # Only bother with non-empty values
|
---|
| 174 | if ($1 ne "" && defined($csv_file_fields[$i])) {
|
---|
[13174] | 175 | if (!defined $csv_line_metadata{$csv_file_fields[$i]}) {
|
---|
| 176 | $csv_line_metadata{$csv_file_fields[$i]} = [];
|
---|
| 177 | }
|
---|
| 178 | push (@{$csv_line_metadata{$csv_file_fields[$i]}}, $1);
|
---|
[12606] | 179 | }
|
---|
| 180 | }
|
---|
| 181 | # Normal comma-separated case
|
---|
| 182 | elsif ($csv_line =~ s/^(.*?)\,//) {
|
---|
| 183 | # Only bother with non-empty values
|
---|
| 184 | if ($1 ne "" && defined($csv_file_fields[$i])) {
|
---|
[13174] | 185 | if (!defined $csv_line_metadata{$csv_file_fields[$i]}) {
|
---|
| 186 | $csv_line_metadata{$csv_file_fields[$i]} = [];
|
---|
| 187 | }
|
---|
[27321] | 188 | # remove any surrounding quotes. (When exporting to CSV, some spreadsheet
|
---|
| 189 | # programs add quotes even around field values that don't contain commas.)
|
---|
| 190 | my $value = $1;
|
---|
| 191 | $value =~ s/^"//;
|
---|
| 192 | $value =~ s/"$//;
|
---|
| 193 | push (@{$csv_line_metadata{$csv_file_fields[$i]}}, $value);
|
---|
[12606] | 194 | }
|
---|
| 195 | }
|
---|
| 196 | # The line must be formatted incorrectly
|
---|
| 197 | else {
|
---|
[22852] | 198 | $self->print_error($outhandle, $failhandle, $gli, $filename, "Badly formatted CSV line: $csv_line");
|
---|
[12606] | 199 | last;
|
---|
| 200 | }
|
---|
| 201 |
|
---|
| 202 | $i++;
|
---|
| 203 | }
|
---|
| 204 |
|
---|
| 205 | # We can't associate any metadata without knowing the file to associate it with
|
---|
[13174] | 206 | my $csv_line_filename_array = $csv_line_metadata{"Filename"};
|
---|
| 207 | if (!defined $csv_line_filename_array) {
|
---|
[22852] | 208 | $self->print_error($outhandle, $failhandle, $gli, $filename, "No Filename metadata in CSV line: $orig_csv_line");
|
---|
[12606] | 209 | next;
|
---|
| 210 | }
|
---|
[13174] | 211 | my $csv_line_filename = shift(@$csv_line_filename_array);
|
---|
[12606] | 212 | delete $csv_line_metadata{"Filename"};
|
---|
| 213 |
|
---|
[32501] | 214 | my $csv_line_section_array = $csv_line_metadata{"Section"};
|
---|
| 215 | my $section_suffix = "";
|
---|
| 216 | if (defined $csv_line_section_array) {
|
---|
| 217 | my $section_value = shift(@$csv_line_section_array);
|
---|
| 218 | if ($section_value =~ /[\d.]+/m){
|
---|
| 219 | my $section_suffix = "///Section/" . $section_value;
|
---|
| 220 | foreach my $metaname (keys %csv_line_metadata) {
|
---|
| 221 | my $new_name = $metaname . $section_suffix;
|
---|
| 222 | $csv_line_metadata{$new_name} = delete $csv_line_metadata{$metaname};
|
---|
| 223 | }
|
---|
| 224 | } else{
|
---|
| 225 | unshift(@$csv_line_section_array, $section_value);
|
---|
| 226 | }
|
---|
| 227 | }
|
---|
[20000] | 228 |
|
---|
[32501] | 229 |
|
---|
[12606] | 230 | # Associate the metadata now
|
---|
[24971] | 231 | # Indexing into the extrameta data structures requires the filename's style of slashes to be in URL format
|
---|
| 232 | # Then need to convert the filename to a regex, no longer to protect windows directory chars \, but for
|
---|
| 233 | # protecting special characters like brackets in the filepath such as "C:\Program Files (x86)\Greenstone".
|
---|
| 234 | $csv_line_filename = &util::filepath_to_url_format($csv_line_filename);
|
---|
[20000] | 235 | $csv_line_filename = &util::filename_to_regex($csv_line_filename);
|
---|
| 236 |
|
---|
[27321] | 237 | if (defined &extrametautil::getmetadata($extrametadata, $csv_line_filename)) { # merge with existing meta
|
---|
| 238 |
|
---|
| 239 | my $file_metadata_table = &extrametautil::getmetadata($extrametadata, $csv_line_filename);
|
---|
| 240 |
|
---|
| 241 | foreach my $metaname (keys %csv_line_metadata) {
|
---|
| 242 | # will create new entry if one does not already exist
|
---|
| 243 | push(@{$file_metadata_table->{$metaname}}, @{$csv_line_metadata{$metaname}});
|
---|
| 244 | }
|
---|
| 245 |
|
---|
| 246 | # no need to push $file on to $extrametakeys as it is already in the list
|
---|
| 247 | } else { # add as new meta
|
---|
| 248 |
|
---|
| 249 | &extrametautil::setmetadata($extrametadata, $csv_line_filename, \%csv_line_metadata);
|
---|
| 250 | &extrametautil::addmetakey($extrametakeys, $csv_line_filename);
|
---|
| 251 | }
|
---|
[20804] | 252 | # record which file the metadata came from
|
---|
[24951] | 253 | if (!defined &extrametautil::getmetafile($extrametafile, $csv_line_filename)) {
|
---|
| 254 | &extrametautil::setmetafile($extrametafile, $csv_line_filename, {});
|
---|
[20804] | 255 | }
|
---|
[20771] | 256 | # maps the file to full path
|
---|
[24951] | 257 | &extrametautil::setmetafile_for_named_file($extrametafile, $csv_line_filename, $file, $filename);
|
---|
[12606] | 258 | }
|
---|
| 259 | }
|
---|
| 260 |
|
---|
[22852] | 261 | sub print_error
|
---|
| 262 | {
|
---|
[12606] | 263 |
|
---|
[22852] | 264 | my $self = shift(@_);
|
---|
| 265 | my ($outhandle, $failhandle, $gli, $file, $error) = @_;
|
---|
| 266 |
|
---|
| 267 | print $outhandle "MetadataCSVPlugin Error: $file: $error\n";
|
---|
| 268 | print $failhandle "MetadataCSVPlugin Error: $file: $error\n";
|
---|
| 269 | print STDERR "<ProcessingError n='$file' r='$error'/>\n" if ($gli);
|
---|
| 270 | }
|
---|
[12606] | 271 | 1;
|
---|