[1676] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
[15872] | 3 | # ReferPlugin.pm - a plugin for bibliography records in Refer format
|
---|
[1676] | 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 2000 Gordon W. Paynter
|
---|
| 10 | # Copyright 1999-2000 New Zealand Digital Library Project
|
---|
| 11 | #
|
---|
| 12 | # This program is free software; you can redistribute it and/or modify
|
---|
| 13 | # it under the terms of the GNU General Public License as published by
|
---|
| 14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 15 | # (at your option) any later version.
|
---|
| 16 | #
|
---|
| 17 | # This program is distributed in the hope that it will be useful,
|
---|
| 18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 20 | # GNU General Public License for more details.
|
---|
| 21 | #
|
---|
| 22 | # You should have received a copy of the GNU General Public License
|
---|
| 23 | # along with this program; if not, write to the Free Software
|
---|
| 24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 25 | #
|
---|
| 26 | ###########################################################################
|
---|
| 27 |
|
---|
[15872] | 28 | # ReferPlugin reads bibliography files in Refer format.
|
---|
[1676] | 29 | #
|
---|
| 30 | # by Gordon W. Paynter ([email protected]), November 2000
|
---|
| 31 | #
|
---|
| 32 | # Loosely based on hcibib2Plug by Steve Jones ([email protected]).
|
---|
| 33 | # Which was based on EMAILPlug by Gordon Paynter ([email protected]).
|
---|
| 34 | # Which was based on old versions of HTMLplug and HCIBIBPlugby by Stefan
|
---|
| 35 | # Boddie and others -- it's hard to tell what came from where, now.
|
---|
| 36 | #
|
---|
| 37 | #
|
---|
[15872] | 38 | # ReferPlugin creates a document object for every reference in the file.
|
---|
| 39 | # It is a subclass of SplitTextFile, so if there are multiple records, all
|
---|
[1676] | 40 | # are read.
|
---|
| 41 | #
|
---|
| 42 | # Document text:
|
---|
| 43 | # The document text consists of the reference in Refer format
|
---|
| 44 | #
|
---|
| 45 | # Metadata:
|
---|
| 46 | # $Creator %A Author name
|
---|
| 47 | # $Title %T Title of article of book
|
---|
| 48 | # $Journal %J Title of Journal
|
---|
| 49 | # $Booktitle %B Title of book containing the publication
|
---|
| 50 | # $Report %R Type of Report, paper or thesis
|
---|
| 51 | # $Volume %V Volume Number of Journal
|
---|
| 52 | # $Number %N Number of Journal within Volume
|
---|
| 53 | # $Editor %E Editor name
|
---|
| 54 | # $Pages %P Page Number of article
|
---|
| 55 | # $Publisher %I Name of Publisher
|
---|
| 56 | # $Publisheraddr %C Publisher's address
|
---|
| 57 | # $Date %D Date of publication
|
---|
| 58 | # $Keywords %K Keywords associated with publication
|
---|
| 59 | # $Abstract %X Abstract of publication
|
---|
| 60 | # $Copyright %* Copyright information for the article
|
---|
| 61 | #
|
---|
| 62 |
|
---|
[15872] | 63 | package ReferPlugin;
|
---|
[1676] | 64 |
|
---|
[15872] | 65 | use SplitTextFile;
|
---|
[24548] | 66 | use MetadataRead;
|
---|
[10254] | 67 | use strict;
|
---|
| 68 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
[1676] | 69 |
|
---|
[31492] | 70 | # ReferPlugin is a sub-class of BaseImporter.
|
---|
[1676] | 71 | sub BEGIN {
|
---|
[24548] | 72 | @ReferPlugin::ISA = ('MetadataRead', 'SplitTextFile');
|
---|
[1676] | 73 | }
|
---|
| 74 |
|
---|
[4744] | 75 | my $arguments =
|
---|
| 76 | [ { 'name' => "process_exp",
|
---|
[31492] | 77 | 'desc' => "{BaseImporter.process_exp}",
|
---|
[6408] | 78 | 'type' => "regexp",
|
---|
[4744] | 79 | 'deft' => &get_default_process_exp(),
|
---|
[6408] | 80 | 'reqd' => "no" },
|
---|
| 81 | { 'name' => "split_exp",
|
---|
[15872] | 82 | 'desc' => "{SplitTextFile.split_exp}",
|
---|
[6408] | 83 | 'type' => "regexp",
|
---|
| 84 | 'reqd' => "no",
|
---|
| 85 | 'deft' => &get_default_split_exp() }
|
---|
| 86 | ];
|
---|
[3540] | 87 |
|
---|
[15872] | 88 | my $options = { 'name' => "ReferPlugin",
|
---|
| 89 | 'desc' => "{ReferPlugin.desc}",
|
---|
[6408] | 90 | 'abstract' => "no",
|
---|
[3540] | 91 | 'inherits' => "yes",
|
---|
[12291] | 92 | 'explodes' => "yes",
|
---|
[3540] | 93 | 'args' => $arguments };
|
---|
| 94 |
|
---|
[1676] | 95 | # This plugin processes files with the suffix ".bib"
|
---|
| 96 | sub get_default_process_exp {
|
---|
| 97 | return q^(?i)\.bib$^;
|
---|
| 98 | }
|
---|
| 99 |
|
---|
| 100 | # This plugin splits the input text at blank lines
|
---|
| 101 | sub get_default_split_exp {
|
---|
| 102 | return q^\n\s*\n^;
|
---|
| 103 | }
|
---|
| 104 |
|
---|
[3540] | 105 | sub new {
|
---|
[10218] | 106 | my ($class) = shift (@_);
|
---|
| 107 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 108 | push(@$pluginlist, $class);
|
---|
[3540] | 109 |
|
---|
[15872] | 110 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 111 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
[10218] | 112 |
|
---|
[15872] | 113 | my $self = new SplitTextFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
[10218] | 114 |
|
---|
[3540] | 115 | return bless $self, $class;
|
---|
| 116 | }
|
---|
| 117 |
|
---|
[16104] | 118 | # The process function reads a single bibliographic record and stores
|
---|
[1676] | 119 | # it as a new document.
|
---|
| 120 |
|
---|
| 121 | sub process {
|
---|
| 122 | my $self = shift (@_);
|
---|
[6332] | 123 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
[1676] | 124 | my $outhandle = $self->{'outhandle'};
|
---|
| 125 |
|
---|
| 126 | # Check that we're dealing with a valid Refer file
|
---|
| 127 | return undef unless ($$textref =~ /^\s*%/);
|
---|
| 128 |
|
---|
[10254] | 129 | my $cursection = $doc_obj->get_top_section();
|
---|
[1676] | 130 |
|
---|
| 131 | my %field = ('H', 'Header',
|
---|
| 132 | 'A', 'Creator',
|
---|
| 133 | 'T', 'Title',
|
---|
| 134 | 'J', 'Journal',
|
---|
| 135 | 'B', 'Booktitle',
|
---|
| 136 | 'R', 'Report',
|
---|
| 137 | 'V', 'Volume',
|
---|
| 138 | 'N', 'Number',
|
---|
| 139 | 'E', 'Editor',
|
---|
| 140 | 'P', 'Pages',
|
---|
| 141 | 'I', 'Publisher',
|
---|
| 142 | 'C', 'PublisherAddress',
|
---|
| 143 | 'D', 'Date',
|
---|
| 144 | 'O', 'OtherInformation',
|
---|
| 145 | 'K', 'Keywords',
|
---|
| 146 | 'X', 'Abstract',
|
---|
| 147 | '*', 'Copyright');
|
---|
| 148 |
|
---|
| 149 | # Metadata fields
|
---|
| 150 | my %metadata;
|
---|
| 151 | my ($id, $Creator, $Keywords, $text);
|
---|
| 152 | my @lines = split(/\n+/, $$textref);
|
---|
| 153 |
|
---|
| 154 |
|
---|
| 155 | # Read and process each line in the bib file.
|
---|
| 156 | # Each file consists of a set of metadata items, one to each line
|
---|
| 157 | # with the Refer key followed by a space then the associated data
|
---|
| 158 | foreach my $line (@lines) {
|
---|
| 159 |
|
---|
| 160 | # Add each line. Most lines consist of a field identifer and
|
---|
| 161 | # then data, and we simply store them, though we treat some
|
---|
| 162 | # of the fields a bit differently.
|
---|
| 163 |
|
---|
| 164 | $line =~ s/\s+/ /g;
|
---|
| 165 | $text .= "$line\n";
|
---|
[10254] | 166 | # $ReferFormat .= "$line\n"; # what is this???
|
---|
[1676] | 167 |
|
---|
| 168 | next unless ($line =~ /^%[A-Z\*]/);
|
---|
| 169 | $id = substr($line,1,1);
|
---|
| 170 | $line =~ s/^%. //;
|
---|
| 171 |
|
---|
| 172 | # Add individual authors in "Lastname, Firstname" format.
|
---|
| 173 | # (The full set of authors will be added below as "Creator".)
|
---|
| 174 | if ($id eq "A") {
|
---|
| 175 |
|
---|
| 176 | # Reformat and add author name
|
---|
| 177 | my @words = split(/ /, $line);
|
---|
| 178 | my $lastname = pop @words;
|
---|
| 179 | my $firstname = join(" ", @words);
|
---|
| 180 | my $fullname = $lastname . ", " . $firstname;
|
---|
| 181 |
|
---|
| 182 | # Add each name to set of Authors
|
---|
| 183 | if ($fullname =~ /\w/) {
|
---|
| 184 | $fullname = &text_into_html($fullname);
|
---|
| 185 | $doc_obj->add_metadata ($cursection, "Author", $fullname);
|
---|
| 186 | }
|
---|
| 187 | }
|
---|
| 188 |
|
---|
| 189 | # Add individual keywords.
|
---|
| 190 | # (The full set of authors will be added below as "Keywords".)
|
---|
| 191 | if ($id eq "K") {
|
---|
| 192 | my @keywordlist = split(/,/, $line);
|
---|
| 193 | foreach my $k (@keywordlist) {
|
---|
| 194 | $k = lc($k);
|
---|
| 195 | $k =~ s/\s*$//;
|
---|
| 196 | $k =~ s/^\s*//;
|
---|
| 197 | if ($k =~ /\w/) {
|
---|
| 198 | $k = &text_into_html($k);
|
---|
| 199 | $doc_obj->add_metadata ($cursection, "Keyword", $k);
|
---|
| 200 | }
|
---|
| 201 | }
|
---|
| 202 | }
|
---|
| 203 |
|
---|
| 204 | # Add this line of metadata
|
---|
| 205 | $metadata{$id} .= "$line\n";
|
---|
| 206 | }
|
---|
| 207 |
|
---|
| 208 |
|
---|
| 209 |
|
---|
| 210 | # Add the various field as metadata
|
---|
| 211 | my ($f, $name, $value);
|
---|
| 212 | foreach $f (keys %metadata) {
|
---|
| 213 |
|
---|
| 214 | next unless (defined $field{$f});
|
---|
| 215 | next unless (defined $metadata{$f});
|
---|
| 216 |
|
---|
| 217 | $name = $field{$f};
|
---|
| 218 | $value = $metadata{$f};
|
---|
| 219 |
|
---|
| 220 | # Add the various field as metadata
|
---|
| 221 |
|
---|
| 222 | # The Creator metadata is found by concatenating authors.
|
---|
| 223 | if ($f eq "A") {
|
---|
| 224 |
|
---|
| 225 | my @authorlist = split(/\n/, $value);
|
---|
| 226 | my $lastauthor = pop @authorlist;
|
---|
| 227 | my $Creator = "";
|
---|
| 228 | if (scalar @authorlist) {
|
---|
[12291] | 229 | $Creator = join(", ", @authorlist) . " and $lastauthor";
|
---|
[1676] | 230 | } else {
|
---|
| 231 | $Creator = $lastauthor;
|
---|
| 232 | }
|
---|
| 233 |
|
---|
| 234 | if ($Creator =~ /\w/) {
|
---|
| 235 | $Creator = &text_into_html($Creator);
|
---|
| 236 | $doc_obj->add_metadata ($cursection, "Creator", $Creator);
|
---|
| 237 | }
|
---|
| 238 | }
|
---|
| 239 |
|
---|
| 240 | # The rest are added in a standard way
|
---|
| 241 | else {
|
---|
| 242 | $value = &text_into_html($value);
|
---|
| 243 | $doc_obj->add_metadata ($cursection, $name, $value);
|
---|
| 244 | }
|
---|
| 245 |
|
---|
| 246 | # Books and Journals are additionally marked for display purposes
|
---|
| 247 | if ($f eq "B") {
|
---|
| 248 | $doc_obj->add_metadata($cursection, "BookConfOnly", 1);
|
---|
| 249 | } elsif ($f eq "J") {
|
---|
| 250 | $doc_obj->add_metadata($cursection, "JournalsOnly", 1);
|
---|
| 251 | }
|
---|
| 252 |
|
---|
| 253 |
|
---|
| 254 | }
|
---|
| 255 |
|
---|
| 256 | # Add the text in refer format(all fields)
|
---|
| 257 | if ($text =~ /\w/) {
|
---|
| 258 | $text = &text_into_html($text);
|
---|
| 259 | $doc_obj->add_text ($cursection, $text);
|
---|
| 260 | }
|
---|
[11827] | 261 | # Add FileFormat as the metadata
|
---|
| 262 | $doc_obj->add_metadata($cursection,"FileFormat","Refer");
|
---|
[1676] | 263 |
|
---|
| 264 | return 1; # processed the file
|
---|
| 265 | }
|
---|
| 266 |
|
---|
| 267 | 1;
|
---|
| 268 | #
|
---|
| 269 | # Convert a text string into HTML.
|
---|
| 270 | #
|
---|
| 271 | # The HTML is going to be inserted into a GML file, so
|
---|
| 272 | # we have to be careful not to use symbols like ">",
|
---|
| 273 | # which ocurs frequently in email messages (and use
|
---|
| 274 | # > instead.
|
---|
| 275 | #
|
---|
| 276 | # This function also turns links and email addresses into hyperlinks,
|
---|
| 277 | # and replaces carriage returns with <BR> tags (and multiple carriage
|
---|
| 278 | # returns with <P> tags).
|
---|
| 279 | #
|
---|
| 280 |
|
---|
| 281 | sub text_into_html {
|
---|
| 282 | my ($text) = @_;
|
---|
| 283 |
|
---|
| 284 |
|
---|
| 285 | # Convert problem charaters into HTML symbols
|
---|
| 286 | $text =~ s/&/&/g;
|
---|
| 287 | $text =~ s/</</g;
|
---|
| 288 | $text =~ s/>/>/g;
|
---|
| 289 | $text =~ s/\"/"/g;
|
---|
| 290 | $text =~ s/\'/ /g;
|
---|
| 291 | $text =~ s/\+/ /g;
|
---|
| 292 | $text =~ s/\(/ /g;
|
---|
| 293 | $text =~ s/\)/ /g;
|
---|
| 294 |
|
---|
| 295 | # convert email addresses and URLs into links
|
---|
| 296 | $text =~ s/([\w\d\.\-]+@[\w\d\.\-]+)/<a href=\"mailto:$1\">$1<\/a>/g;
|
---|
| 297 | $text =~ s/(http:\/\/[\w\d\.\-]+[\/\w\d\.\-]*)/<a href=\"$1">$1<\/a>/g;
|
---|
| 298 |
|
---|
| 299 | # Clean up whitespace and convert \n charaters to <BR> or <P>
|
---|
| 300 | $text =~ s/ +/ /g;
|
---|
| 301 | $text =~ s/\s*$//;
|
---|
| 302 | $text =~ s/^\s*//;
|
---|
| 303 | $text =~ s/\n/\n<BR>/g;
|
---|
| 304 | $text =~ s/<BR>\s*<BR>/<P>/g;
|
---|
| 305 |
|
---|
| 306 | return $text;
|
---|
| 307 | }
|
---|
| 308 |
|
---|
| 309 |
|
---|