| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # AZList.pm --
|
|---|
| 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 | # classifier plugin for sorting alphabetically
|
|---|
| 27 |
|
|---|
| 28 | package AZList;
|
|---|
| 29 |
|
|---|
| 30 | use BasClas;
|
|---|
| 31 | use sorttools;
|
|---|
| 32 | use iso639;
|
|---|
| 33 |
|
|---|
| 34 | sub BEGIN {
|
|---|
| 35 | @ISA = ('BasClas');
|
|---|
| 36 | }
|
|---|
| 37 |
|
|---|
| 38 | sub print_usage {
|
|---|
| 39 | print STDERR "
|
|---|
| 40 | usage: classify AZList [options]
|
|---|
| 41 | options:
|
|---|
| 42 |
|
|---|
| 43 | -metadata X (required) Metadata field used for classification.
|
|---|
| 44 | List will be sorted by this element.
|
|---|
| 45 |
|
|---|
| 46 | -buttonname X (optional) Button name for this classification.
|
|---|
| 47 | defaults to metadata name.
|
|---|
| 48 |
|
|---|
| 49 | -removeprefix regex (optional) A prefix to ignore in the Metadata values
|
|---|
| 50 | for the field when sorting.
|
|---|
| 51 | ";
|
|---|
| 52 | }
|
|---|
| 53 |
|
|---|
| 54 | sub new {
|
|---|
| 55 | my $class = shift (@_);
|
|---|
| 56 | my $self = new BasClas($class, @_);
|
|---|
| 57 |
|
|---|
| 58 | my ($metaname, $title, $removeprefix);
|
|---|
| 59 |
|
|---|
| 60 | if (!parsargv::parse(\@_,
|
|---|
| 61 | q^metadata/.*/^, \$metaname,
|
|---|
| 62 | q^buttonname/.*/^, \$title,
|
|---|
| 63 | q^removeprefix/.*/^, \$removeprefix,
|
|---|
| 64 | "allow_extra_options")) {
|
|---|
| 65 |
|
|---|
| 66 | print STDERR "\nIncorrect options passed to $class, check your collect.cfg file\n";
|
|---|
| 67 | &print_usage();
|
|---|
| 68 | die "\n";
|
|---|
| 69 | }
|
|---|
| 70 |
|
|---|
| 71 | if (!defined $metaname) {
|
|---|
| 72 | &print_usage;
|
|---|
| 73 | print STDERR "AZList used with no metadata name\n";
|
|---|
| 74 | die "\n";
|
|---|
| 75 | }
|
|---|
| 76 |
|
|---|
| 77 | $title = $metaname unless ($title);
|
|---|
| 78 |
|
|---|
| 79 | $self->{'list'} = {};
|
|---|
| 80 | $self->{'metaname'} = $metaname;
|
|---|
| 81 | $self->{'title'} = $title;
|
|---|
| 82 | if (defined($removeprefix) && $removeprefix) {
|
|---|
| 83 | $removeprefix =~ s/^\^//; # don't need a leading ^
|
|---|
| 84 | $self->{'removeprefix'} = $removeprefix;
|
|---|
| 85 | }
|
|---|
| 86 |
|
|---|
| 87 | return bless $self, $class;
|
|---|
| 88 | }
|
|---|
| 89 |
|
|---|
| 90 | sub init {
|
|---|
| 91 | my $self = shift (@_);
|
|---|
| 92 |
|
|---|
| 93 | $self->{'list'} = {};
|
|---|
| 94 | }
|
|---|
| 95 |
|
|---|
| 96 | sub classify {
|
|---|
| 97 | my $self = shift (@_);
|
|---|
| 98 | my ($doc_obj) = @_;
|
|---|
| 99 |
|
|---|
| 100 | my $doc_OID = $doc_obj->get_OID();
|
|---|
| 101 | my $metavalue = $doc_obj->get_metadata_element ($doc_obj->get_top_section(),
|
|---|
| 102 | $self->{'metaname'});
|
|---|
| 103 |
|
|---|
| 104 | # if this document doesn't contain the metadata element we're
|
|---|
| 105 | # sorting by we won't include it in this classification
|
|---|
| 106 | if (defined $metavalue && $metavalue ne "") {
|
|---|
| 107 | if (defined($self->{'removeprefix'}) &&
|
|---|
| 108 | length($self->{'removeprefix'})) {
|
|---|
| 109 | $metavalue =~ s/^$self->{'removeprefix'}//;
|
|---|
| 110 | }
|
|---|
| 111 |
|
|---|
| 112 | if ($self->{'metaname'} eq 'Language') {
|
|---|
| 113 | $metavalue = $iso639::fromiso639{$metavalue};
|
|---|
| 114 | } elsif ($self->{'metaname'} eq 'Creator') {
|
|---|
| 115 | &sorttools::format_string_name_english (\$metavalue);
|
|---|
| 116 | } else {
|
|---|
| 117 | &sorttools::format_string_english (\$metavalue);
|
|---|
| 118 | }
|
|---|
| 119 | if (defined $self->{'list'}->{$doc_OID}) {
|
|---|
| 120 | my $outhandle = $self->{'outhandle'};
|
|---|
| 121 | print $outhandle "WARNING: AZList::classify called multiple times for $doc_OID\n";
|
|---|
| 122 | }
|
|---|
| 123 | if ($metavalue) {
|
|---|
| 124 | $self->{'list'}->{$doc_OID} = $metavalue;
|
|---|
| 125 | } else {
|
|---|
| 126 | my $outhandle = $self->{'outhandle'};
|
|---|
| 127 | print $outhandle "WARNING: AZList: $doc_OID metadata is empty - not classifying\n";
|
|---|
| 128 | }
|
|---|
| 129 | }
|
|---|
| 130 | }
|
|---|
| 131 |
|
|---|
| 132 | sub alpha_numeric_cmp
|
|---|
| 133 | {
|
|---|
| 134 | my ($self,$a,$b) = @_;
|
|---|
| 135 |
|
|---|
| 136 | my $title_a = $self->{'list'}->{$a};
|
|---|
| 137 | my $title_b = $self->{'list'}->{$b};
|
|---|
| 138 |
|
|---|
| 139 | if ($title_a =~ m/^(\d+(\.\d+)?)/)
|
|---|
| 140 | {
|
|---|
| 141 | my $val_a = $1;
|
|---|
| 142 | if ($title_b =~ m/^(\d+(\.\d+)?)/)
|
|---|
| 143 | {
|
|---|
| 144 | my $val_b = $1;
|
|---|
| 145 | if ($val_a != $val_b)
|
|---|
| 146 | {
|
|---|
| 147 | return ($val_a <=> $val_b);
|
|---|
| 148 | }
|
|---|
| 149 | }
|
|---|
| 150 | }
|
|---|
| 151 |
|
|---|
| 152 | return ($title_a cmp $title_b);
|
|---|
| 153 | }
|
|---|
| 154 |
|
|---|
| 155 | sub get_classify_info {
|
|---|
| 156 | my $self = shift (@_);
|
|---|
| 157 |
|
|---|
| 158 | my @classlist
|
|---|
| 159 | = sort { $self->alpha_numeric_cmp($a,$b) } keys %{$self->{'list'}};
|
|---|
| 160 |
|
|---|
| 161 | return $self->splitlist (\@classlist);
|
|---|
| 162 | }
|
|---|
| 163 |
|
|---|
| 164 | sub get_entry {
|
|---|
| 165 | my $self = shift (@_);
|
|---|
| 166 | my ($title, $childtype, $thistype) = @_;
|
|---|
| 167 |
|
|---|
| 168 | # organise into classification structure
|
|---|
| 169 | my %classifyinfo = ('childtype'=>$childtype,
|
|---|
| 170 | 'Title'=>$title,
|
|---|
| 171 | 'contains'=>[]);
|
|---|
| 172 | $classifyinfo{'thistype'} = $thistype
|
|---|
| 173 | if defined $thistype && $thistype =~ /\w/;
|
|---|
| 174 |
|
|---|
| 175 | return \%classifyinfo;
|
|---|
| 176 | }
|
|---|
| 177 |
|
|---|
| 178 | # splitlist takes an ordered list of classifications (@$classlistref) and splits it
|
|---|
| 179 | # up into alphabetical sub-sections.
|
|---|
| 180 | sub splitlist {
|
|---|
| 181 | my $self = shift (@_);
|
|---|
| 182 | my ($classlistref) = @_;
|
|---|
| 183 | my $classhash = {};
|
|---|
| 184 |
|
|---|
| 185 | # top level
|
|---|
| 186 | my $childtype = "HList";
|
|---|
| 187 | if (scalar (@$classlistref) <= 39) {$childtype = "VList";}
|
|---|
| 188 | my $classifyinfo = $self->get_entry ($self->{'title'}, $childtype, "Invisible");
|
|---|
| 189 |
|
|---|
| 190 | # don't need to do any splitting if there are less than 39 (max + min -1) classifications
|
|---|
| 191 | if ((scalar @$classlistref) <= 39) {
|
|---|
| 192 | foreach $subOID (@$classlistref) {
|
|---|
| 193 | push (@{$classifyinfo->{'contains'}}, {'OID'=>$subOID});
|
|---|
| 194 | }
|
|---|
| 195 | return $classifyinfo;
|
|---|
| 196 | }
|
|---|
| 197 |
|
|---|
| 198 | # first split up the list into separate A-Z and 0-9 classifications
|
|---|
| 199 | foreach $classification (@$classlistref) {
|
|---|
| 200 | my $title = $self->{'list'}->{$classification};
|
|---|
| 201 |
|
|---|
| 202 | $title =~ s/^(&.{1,6};|<[^>]>|[^a-zA-Z0-9])//g; # remove any unwanted stuff
|
|---|
| 203 | # only need first char for classification
|
|---|
| 204 | $title =~ m/^(.)/; $title=$1;
|
|---|
| 205 | $title =~ tr/[a-z]/[A-Z]/;
|
|---|
| 206 | if ($title =~ /^[0-9]$/) {$title = '0-9';}
|
|---|
| 207 | elsif ($title !~ /^[A-Z]$/) {
|
|---|
| 208 | my $outhandle = $self->{'outhandle'};
|
|---|
| 209 | print $outhandle "AZList: WARNING $classification has badly formatted title ($title)\n";
|
|---|
| 210 | }
|
|---|
| 211 | $classhash->{$title} = [] unless defined $classhash->{$title};
|
|---|
| 212 | push (@{$classhash->{$title}}, $classification);
|
|---|
| 213 | }
|
|---|
| 214 | $classhash = $self->compactlist ($classhash);
|
|---|
| 215 |
|
|---|
| 216 | my @tmparr = ();
|
|---|
| 217 | foreach $subsection (sort keys (%$classhash)) {
|
|---|
| 218 | push (@tmparr, $subsection);
|
|---|
| 219 | }
|
|---|
| 220 |
|
|---|
| 221 | # if there's a 0-9 section it will have been sorted to the beginning
|
|---|
| 222 | # but we want it at the end
|
|---|
| 223 | if ($tmparr[0] eq '0-9') {
|
|---|
| 224 | shift @tmparr;
|
|---|
| 225 | push (@tmparr, '0-9');
|
|---|
| 226 | }
|
|---|
| 227 |
|
|---|
| 228 | foreach $subclass (@tmparr) {
|
|---|
| 229 | my $tempclassify = $self->get_entry($subclass, "VList");
|
|---|
| 230 | foreach $subsubOID (@{$classhash->{$subclass}}) {
|
|---|
| 231 | push (@{$tempclassify->{'contains'}}, {'OID'=>$subsubOID});
|
|---|
| 232 | }
|
|---|
| 233 | push (@{$classifyinfo->{'contains'}}, $tempclassify);
|
|---|
| 234 | }
|
|---|
| 235 |
|
|---|
| 236 | return $classifyinfo;
|
|---|
| 237 | }
|
|---|
| 238 |
|
|---|
| 239 | sub compactlist {
|
|---|
| 240 | my $self = shift (@_);
|
|---|
| 241 | my ($classhashref) = @_;
|
|---|
| 242 | my $compactedhash = {};
|
|---|
| 243 | my @currentOIDs = ();
|
|---|
| 244 | my $currentfirstletter = "";
|
|---|
| 245 | my $currentlastletter = "";
|
|---|
| 246 | my $lastkey = "";
|
|---|
| 247 |
|
|---|
| 248 | # minimum and maximum documents to be displayed per page.
|
|---|
| 249 | # the actual maximum will be max + (min-1).
|
|---|
| 250 | # the smallest sub-section is a single letter at present
|
|---|
| 251 | # so in this case there may be many times max documents
|
|---|
| 252 | # displayed on a page.
|
|---|
| 253 | my $min = 10;
|
|---|
| 254 | my $max = 30;
|
|---|
| 255 |
|
|---|
| 256 | foreach $subsection (sort keys %$classhashref) {
|
|---|
| 257 | if ($subsection eq '0-9') {
|
|---|
| 258 | @{$compactedhash->{$subsection}} = @{$classhashref->{$subsection}};
|
|---|
| 259 | next;
|
|---|
| 260 | }
|
|---|
| 261 | $currentfirstletter = $subsection if $currentfirstletter eq "";
|
|---|
| 262 | if ((scalar (@currentOIDs) < $min) ||
|
|---|
| 263 | ((scalar (@currentOIDs) + scalar (@{$classhashref->{$subsection}})) <= $max)) {
|
|---|
| 264 | push (@currentOIDs, @{$classhashref->{$subsection}});
|
|---|
| 265 | $currentlastletter = $subsection;
|
|---|
| 266 | } else {
|
|---|
| 267 |
|
|---|
| 268 | if ($currentfirstletter eq $currentlastletter) {
|
|---|
| 269 | @{$compactedhash->{$currentfirstletter}} = @currentOIDs;
|
|---|
| 270 | $lastkey = $currentfirstletter;
|
|---|
| 271 | } else {
|
|---|
| 272 | @{$compactedhash->{"$currentfirstletter-$currentlastletter"}} = @currentOIDs;
|
|---|
| 273 | $lastkey = "$currentfirstletter-$currentlastletter";
|
|---|
| 274 | }
|
|---|
| 275 | if (scalar (@{$classhashref->{$subsection}}) >= $max) {
|
|---|
| 276 | $compactedhash->{$subsection} = $classhashref->{$subsection};
|
|---|
| 277 | @currentOIDs = ();
|
|---|
| 278 | $currentfirstletter = "";
|
|---|
| 279 | $lastkey = $subsection;
|
|---|
| 280 | } else {
|
|---|
| 281 | @currentOIDs = @{$classhashref->{$subsection}};
|
|---|
| 282 | $currentfirstletter = $subsection;
|
|---|
| 283 | $currentlastletter = $subsection;
|
|---|
| 284 | }
|
|---|
| 285 | }
|
|---|
| 286 | }
|
|---|
| 287 |
|
|---|
| 288 | # add final OIDs to last sub-classification if there aren't many otherwise
|
|---|
| 289 | # add final sub-classification
|
|---|
| 290 | if (scalar (@currentOIDs) < $min) {
|
|---|
| 291 | my ($newkey) = $lastkey =~ /^(.)/;
|
|---|
| 292 | @currentOIDs = (@{$compactedhash->{$lastkey}}, @currentOIDs);
|
|---|
| 293 | delete $compactedhash->{$lastkey};
|
|---|
| 294 | @{$compactedhash->{"$newkey-$currentlastletter"}} = @currentOIDs;
|
|---|
| 295 | } else {
|
|---|
| 296 | if ($currentfirstletter eq $currentlastletter) {
|
|---|
| 297 | @{$compactedhash->{$currentfirstletter}} = @currentOIDs;
|
|---|
| 298 | } else {
|
|---|
| 299 | @{$compactedhash->{"$currentfirstletter-$currentlastletter"}} = @currentOIDs;
|
|---|
| 300 | }
|
|---|
| 301 | }
|
|---|
| 302 |
|
|---|
| 303 | return $compactedhash;
|
|---|
| 304 | }
|
|---|
| 305 |
|
|---|
| 306 | 1;
|
|---|
