opac/opac-search.pl

   1 #!/usr/bin/perl
   2
   3 # Script to perform searching
   4 # For documentation try 'perldoc /path/to/search'
   5 #
   6 # $Header$
   7 #
   8 # Copyright 2006 LibLime
   9 #
  10 # This file is part of Koha
  11 #
  12 # Koha is free software; you can redistribute it and/or modify it under the
  13 # terms of the GNU General Public License as published by the Free Software
  14 # Foundation; either version 2 of the License, or (at your option) any later
  15 # version.
  16 #
  17 # Koha is distributed in the hope that it will be useful, but WITHOUT ANY
  18 # WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
  19 # A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
  20 #
  21 # You should have received a copy of the GNU General Public License along with
  22 # Koha; if not, write to the Free Software Foundation, Inc., 59 Temple Place,
  23 # Suite 330, Boston, MA  02111-1307 USA
  24
  25 =head1 NAME
  26
  27 search - a search script for finding records in a Koha system (Version 2.4)
  28
  29 =head1 OVERVIEW
  30
  31 This script contains a demonstration of a new search API for Koha 2.4. It is
  32 designed to be simple to use and configure, yet capable of performing feats
  33 like stemming, field weighting, relevance ranking, support for multiple
  34 query language formats (CCL, CQL, PQF), full or nearly full support for the
  35 bib1 attribute set, extended attribute sets defined in Zebra profiles, access
  36 to the full range of Z39.50 query options, federated searches on Z39.50
  37 targets, etc.
  38
  39 I believe the API as represented in this script is mostly sound, even if the
  40 individual functions in Search.pm and Koha.pm need to be cleaned up. Of course,
  41 you are free to disagree :-)
  42
  43 I will attempt to describe what is happening at each part of this script.
  44 -- JF
  45
  46 =head2 INTRO
  47
  48 This script performs two functions:
  49
  50 =over
  51
  52 =item 1. interacts with Koha to retrieve and display the results of a search
  53
  54 =item 2. loads the advanced search page
  55
  56 =back
  57
  58 These two functions share many of the same variables and modules, so the first
  59 task is to load what they have in common and determine which template to use.
  60 Once determined, proceed to only load the variables and procedures necessary
  61 for that function.
  62
  63 =head2 THE ADVANCED SEARCH PAGE
  64
  65 If we're loading the advanced search page this script will call a number of
  66 display* routines which populate objects that are sent to the template for
  67 display of things like search indexes, languages, search limits, branches,
  68 etc. These are not stored in the template for two reasons:
  69
  70 =over
  71
  72 =item 1. Efficiency - we have more control over objects inside the script, and it's possible to not duplicate things like indexes (if the search indexes were stored in the template they would need to be repeated)
  73
  74 =item 2. Customization - if these elements were moved to the sql database it would allow a simple librarian to determine which fields to display on the page without editing any html (also how the fields should behave when being searched).
  75
  76 =back
  77
  78 However, they create one problem : the strings aren't translated. I have an idea
  79 for how to do this that I will purusue soon.
  80
  81 =head2 PERFORMING A SEARCH
  82
  83 If we're performing a search, this script  performs three primary
  84 operations:
  85
  86 =over
  87
  88 =item 1. builds query strings (yes, plural)
  89
  90 =item 2. perform the search and return the results array
  91
  92 =item 3. build the HTML for output to the template
  93
  94 =back
  95
  96 There are several additional secondary functions performed that I will
  97 not cover in detail.
  98
  99 =head3 1. Building Query Strings
 100
 101 There are several types of queries needed in the process of search and retrieve:
 102
 103 =over
 104
 105 =item 1 Koha query - the query that is passed to Zebra
 106
 107 This is the most complex query that needs to be built.The original design goal was to use a custom CCL2PQF query parser to translate an incoming CCL query into a multi-leaf query to pass to Zebra. It needs to be multi-leaf to allow field weighting, koha-specific relevance ranking, and stemming. When I have a chance I'll try to flesh out this section to better explain.
 108
 109 This query incorporates query profiles that aren't compatible with non-Zebra Z39.50 targets to acomplish the field weighting and relevance ranking.
 110
 111 =item 2 Federated query - the query that is passed to other Z39.50 targets
 112
 113 This query is just the user's query expressed in CCL CQL, or PQF for passing to a non-zebra Z39.50 target (one that doesn't support the extended profile that Zebra does).
 114
 115 =item 3 Search description - passed to the template / saved for future refinements of the query (by user)
 116
 117 This is a simple string that completely expresses the query in a way that can be parsed by Koha for future refinements of the query or as a part of a history feature. It differs from the human search description in several ways:
 118
 119 1. it does not contain commas or = signs
 120 2.
 121
 122 =item 4 Human search description - what the user sees in the search_desc area
 123
 124 This is a simple string nearly identical to the Search description, but more human readable. It will contain = signs or commas, etc.
 125
 126 =back
 127
 128 =head3 2. Perform the Search
 129
 130 This section takes the query strings and performs searches on the named servers, including the Koha Zebra server, stores the results in a deeply nested object, builds 'faceted results', and returns these objects.
 131
 132 =head3 3. Build HTML
 133
 134 The final major section of this script takes the objects collected thusfar and builds the HTML for output to the template and user.
 135
 136 =head3 Additional Notes
 137
 138 Not yet completed...
 139
 140 =cut
 141
 142 use strict;    # always use
 143
 144 #use warnings;        # use only for development
 145
 146 ## STEP 1. Load things that are used in both search page and
 147 # results page and decide which template to load, operations
 148 # to perform, etc.
 149 ## load Koha modules
 150 use C4::Context;
 151 use C4::Output;
 152 use C4::Auth;
 153 use C4::Search;
 154 use C4::Languages; # getAllLanguages
 155 use C4::Koha;
 156 use C4::Branch; # GetBranches
 157 use POSIX qw(ceil floor);
 158
 159 # create a new CGI object
 160 # not sure undef_params option is working, need to test
 161 use CGI qw('-no_undef_params');
 162 my $cgi = new CGI;
 163
 164 my ( $template, $borrowernumber, $cookie );
 165
 166 # decide which template to use
 167 my $template_name;
 168 my @params = $cgi->param("limit");
 169 if ( ( @params > 1 ) || ( $cgi->param("q") ) ) {
 170
 171     $template_name = 'opac-results.tmpl';
 172 }
 173 else {
 174
 175     $template_name = 'opac-advsearch.tmpl';
 176 }
 177
 178 # load the template
 179 ( $template, $borrowernumber, $cookie ) = get_template_and_user(
 180     {
 181         template_name   => $template_name,
 182         query           => $cgi,
 183         type            => "opac",
 184         authnotrequired => 1,
 185     }
 186 );
 187
 188 =head1 BUGS and FIXMEs
 189
 190 There are many, most are documented in the code. The one that
 191 isn't fully documented, but referred to is the need for a full
 192 query parser.
 193
 194 =cut
 195
 196 ## URI Re-Writing
 197 # FIXME: URI re-writing should be tested more carefully and may better
 198 # handled by mod_rewrite or something else. The code below almost works,
 199 # but doesn't quite handle limits correctly when they are the only
 200 # param passed -- I'll work on this soon -- JF
 201 #my $rewrite_flag;
 202 #my $uri = $cgi->url(-base => 1);
 203 #my $relative_url = $cgi->url(-relative=>1);
 204 #$uri.="/".$relative_url."?";
 205 #warn "URI:$uri";
 206 #my @cgi_params_list = $cgi->param();
 207 #my $url_params = $cgi->Vars;
 208
 209 #for my $each_param_set (@cgi_params_list) {
 210 #    $uri.= join "",  map "\&$each_param_set=".$_, split("\0",$url_params->{$each_param_set}) if $url_params->{$each_param_set};
 211 #}
 212 #warn "New URI:$uri";
 213 # Only re-write a URI if there are params or if it already hasn't been re-written
 214 #unless (($cgi->param('r')) || (!$cgi->param()) ) {
 215 #    print $cgi->redirect(     -uri=>$uri."&r=1",
 216 #                            -cookie => $cookie);
 217 #    exit;
 218 #}
 219
 220 # load the branches
 221 my $branches = GetBranches();
 222 my @branch_loop;
 223 for my $branch_hash (sort keys %$branches ) {
 224     my $selected=(C4::Context->userenv && ($branch_hash eq C4::Context->userenv->{branch})) if (C4::Context->preference('SearchMyLibraryFirst'));
 225     push @branch_loop,
 226       {
 227         value      => "branch: $branch_hash",
 228         branchname => $branches->{$branch_hash}->{'branchname'},
 229         selected => $selected
 230       };
 231 }
 232 $template->param( branchloop => \@branch_loop, "mylibraryfirst"=>C4::Context->preference("SearchMyLibraryFirst"));
 233
 234 # load the itemtypes (Called Collection Codes in the template -- used for circ rules )
 235 my $itemtypes = GetItemTypes;
 236 my @itemtypesloop;
 237 my $selected = 1;
 238 my $cnt;
 239 my $imgdir = getitemtypeimagesrc();
 240 foreach my $thisitemtype ( sort {$itemtypes->{$a}->{'description'} cmp $itemtypes->{$b}->{'description'} } keys %$itemtypes ) {
 241     my %row = (
 242         number   => $cnt++,
 243         imageurl => $itemtypes->{$thisitemtype}->{'imageurl'}?$imgdir . "/" . $itemtypes->{$thisitemtype}->{'imageurl'}:'',
 244         code     => $thisitemtype,
 245         selected => $selected,
 246         description => $itemtypes->{$thisitemtype}->{'description'},
 247         count5      => $cnt % 4,
 248     );
 249     $selected = 0 if ($selected);
 250     push @itemtypesloop, \%row;
 251 }
 252 $template->param( itemtypeloop => \@itemtypesloop );
 253
 254 # # load the itypes (Called item types in the template -- just authorized values for searching)
 255 # my ($itypecount,@itype_loop) = GetCcodes();
 256 # $template->param(itypeloop=>\@itype_loop,);
 257
 258 # load the languages ( for switching from one template to another )
 259 # my @languages_options = displayLanguages($cgi);
 260 # my $languages_count = @languages_options;
 261 # if($languages_count > 1){
 262 #         $template->param(languages => \@languages_options);
 263 # }
 264
 265 # The following should only be loaded if we're bringing up the advanced search template
 266 if ( $template_name eq "opac-advsearch.tmpl" ) {
 267
 268     # load the servers (used for searching -- to do federated searching, etc.)
 269     my $primary_servers_loop;    # = displayPrimaryServers();
 270     $template->param( outer_servers_loop => $primary_servers_loop, );
 271
 272     my $secondary_servers_loop;    # = displaySecondaryServers();
 273     $template->param( outer_sup_servers_loop => $secondary_servers_loop, );
 274
 275     # determine what to display next to the search boxes (ie, boolean option
 276     # shouldn't appear on the first one, scan indexes should, adding a new
 277     # box should only appear on the last, etc.
 278     # FIXME: this stuff should be cleaned up a bit and the html should be turned
 279     # into flags for the template -- I'll work on that soon -- JF
 280     my @search_boxes_array;
 281     my $search_boxes_count = 1;    # should be a syspref
 282     for ( my $i = 0 ; $i <= $search_boxes_count ; $i++ ) {
 283         if ( $i == 0 ) {
 284             push @search_boxes_array,
 285               {
 286                 search_boxes_label => "<span class='labels'>Search for:</span>",
 287                 scan_index         => 1,
 288               };
 289
 290         }
 291         elsif ( $i == $search_boxes_count ) {
 292             push @search_boxes_array,
 293               {
 294                 left_content =>
 295 " <select name='op'><option value='and' selected='selected'>and</option><option value='or'>or</option><option value='not'>not</option></select>",
 296                 add_field => "1"
 297               };
 298         }
 299         else {
 300             push @search_boxes_array,
 301               {
 302                 left_content =>
 303 " <select name='op'><option value='and' selected='selected'>and</option><option value='or'>or</option><option value='not'>not</option></select>",
 304               };
 305         }
 306     }
 307     $template->param(
 308         uc( C4::Context->preference("marcflavour") ) => 1,
 309         search_boxes_loop                            => \@search_boxes_array
 310     );
 311
 312     # load the language limits (for search)
 313     my $languages_limit_loop = getAllLanguages();
 314     $template->param( search_languages_loop => $languages_limit_loop, );
 315
 316     my $expanded_options;
 317     if ( C4::Context->preference("expandedSearchOption") ) {
 318         $expanded_options = C4::Context->preference("expandedSearchOption");
 319     }
 320     else {
 321         $expanded_options = $cgi->param('expanded_options');
 322     }
 323
 324     $template->param( expanded_options => $expanded_options );
 325
 326     # load the sort_by options for the template
 327     my $sort_by      = $cgi->param('sort_by');
 328     $sort_by=$1.($2 eq "lt"?'d':'a') if ($sort_by=~/1=(\d+) \&([a-z]+)\;/);
 329     $template->param( sort_by => $sort_by);
 330
 331     output_html_with_http_headers $cgi, $cookie, $template->output;
 332     exit;
 333 }
 334
 335 ### OK, if we're this far, we're performing an actual search
 336
 337 # Fetch the paramater list as a hash in scalar context:
 338 #  * returns paramater list as tied hash ref
 339 #  * we can edit the values by changing the key
 340 #  * multivalued CGI paramaters are returned as a packaged string separated by "\0" (null)
 341 my $params = $cgi->Vars;
 342
 343 # Params that can have more than one value
 344 # sort by is used to sort the query
 345 my @sort_by;
 346 @sort_by = split( "\0", $params->{'sort_by'} ) if $params->{'sort_by'};
 347
 348 # load the sort_by options for the template
 349 my $sort_by      = $params->{'sort_by'};
 350 $sort_by=~$1.($2 eq "lt"?'d':'a') if ($sort_by=~/1=(\d+) \&([a-z]+)\;/);
 351 $template->param( sort_by => $sort_by);
 352
 353 #
 354 # Use the servers defined, or just search our local catalog(default)
 355 my @servers;
 356 @servers = split( "\0", $params->{'server'} ) if $params->{'server'};
 357 unless (@servers) {
 358
 359     #FIXME: this should be handled using Context.pm
 360     @servers = ("biblioserver");
 361
 362     # @servers = C4::Context->config("biblioserver");
 363 }
 364
 365 # operators include boolean and proximity operators and are used
 366 # to evaluate multiple operands
 367 my @operators;
 368 @operators = split( "\0", $params->{'op'} ) if $params->{'op'};
 369
 370 # indexes are query qualifiers, like 'title', 'author', etc. They
 371 # can be simple or complex
 372 my @indexes;
 373 @indexes = split( "\0", $params->{'idx'} ) if $params->{'idx'};
 374
 375 # an operand can be a single term, a phrase, or a complete ccl query
 376 my @operands;
 377 @operands = split( "\0", $params->{'q'} ) if $params->{'q'};
 378
 379 # limits are use to limit to results to a pre-defined category such as branch or language
 380 my @limits;
 381 @limits = split( "\0", $params->{'limit'} ) if $params->{'limit'};
 382
 383 my $available;
 384 foreach my $limit (@limits) {
 385     if ( $limit =~ /available/ ) {
 386         $available = 1;
 387     }
 388 }
 389 $template->param( available => $available );
 390 push @limits, map "yr:" . $_, split( "\0", $params->{'limit-yr'} )
 391   if $params->{'limit-yr'};
 392
 393 # Params that can only have one value
 394 my $query            = $params->{'q'};
 395 my $scan             = $params->{'scan'};
 396 my $results_per_page = $params->{'count'} || 20;
 397 my $offset           = $params->{'offset'} || 0;
 398 my $hits;
 399 my $expanded_facet = $params->{'expand'};
 400
 401 # Define some global variables
 402 my $error;          # used for error handling
 403 my $search_desc;    # the query expressed in terms that humans understand
 404 my $koha_query; # the query expressed in terms that zoom understands with field weighting and stemming
 405 my $federated_query;
 406 my $query_type; # usually not needed, but can be used to trigger ccl, cql, or pqf queries if set
 407 my @results;
 408
 409 ## I. BUILD THE QUERY
 410 ( $error, $search_desc, $koha_query, $federated_query, $query_type ) =
 411   buildQuery( $query, \@operators, \@operands, \@indexes, \@limits );
 412
 413 # warn "query : $koha_query";
 414 ## II. DO THE SEARCH AND GET THE RESULTS
 415 my $total;    # the total results for the whole set
 416 my $facets; # this object stores the faceted results that display on the left-hand of the results page
 417 my @results_array;
 418 my $results_hashref;
 419
 420 if (C4::Context->preference('NoZebra')) {
 421     eval {
 422         ($error, $results_hashref, $facets) = NZgetRecords($koha_query,$federated_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
 423     };
 424 } else {
 425     eval {
 426         ($error, $results_hashref, $facets) = getRecords($koha_query,$federated_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
 427     };
 428 }
 429 if ( $@ || $error ) {
 430     $template->param( query_error => $error . $@ );
 431
 432     #     warn "error: ".$error.$@;
 433     output_html_with_http_headers $cgi, $cookie, $template->output;
 434     exit;
 435 }
 436
 437 # At this point, each server has given us a result set
 438 # now we build that set for template display
 439 my @sup_results_array;
 440 for ( my $i = 0 ; $i <= @servers ; $i++ ) {
 441     my $server = $servers[$i];
 442     if ( $server =~ /biblioserver/ ) {  # this is the local bibliographic server
 443         $hits = $results_hashref->{$server}->{"hits"};
 444         my @newresults =
 445           searchResults( $search_desc, $hits, $results_per_page, $offset,
 446             @{ $results_hashref->{$server}->{"RECORDS"} } );
 447         $total = $total + $results_hashref->{$server}->{"hits"};
 448         if ($hits) {
 449             $template->param( total            => $hits );
 450             $template->param( searchdesc       => $search_desc );
 451             $template->param( results_per_page => $results_per_page );
 452             $template->param( SEARCH_RESULTS   => \@newresults );
 453
 454             my @page_numbers;
 455             my $pages               = ceil( $hits / $results_per_page );
 456             my $current_page_number = 1;
 457             $current_page_number = ( $offset / $results_per_page + 1 )
 458               if $offset;
 459             my $previous_page_offset = $offset - $results_per_page
 460               unless ( $offset - $results_per_page < 0 );
 461             my $next_page_offset = $offset + $results_per_page;
 462             for ( $i = 1 ; $i <= $pages ; $i++ ) {
 463                 my $this_offset =
 464                   ( ( $i * $results_per_page ) - $results_per_page );
 465                 my $this_page_number = $i;
 466                 my $highlight        = 1
 467                   if ( $this_page_number == $current_page_number );
 468                 if ($this_page_number <= $pages) {
 469                 push @page_numbers,
 470                   {
 471                     offset    => $this_offset,
 472                     pg        => $this_page_number,
 473                     highlight => $highlight,
 474                     sort_by   => join " ",
 475                     @sort_by
 476                   };
 477                 }
 478             }
 479             $template->param(
 480                 PAGE_NUMBERS         => \@page_numbers,
 481                 previous_page_offset => $previous_page_offset,
 482                 next_page_offset     => $next_page_offset
 483             ) unless $pages < 2;
 484         }
 485     }    # end of the if local
 486     else {
 487
 488         # check if it's a z3950 or opensearch source
 489         my $zed3950 = 0;    # FIXME :: Hardcoded value.
 490         if ($zed3950) {
 491             my @inner_sup_results_array;
 492             for my $sup_record ( @{ $results_hashref->{$server}->{"RECORDS"} } )
 493             {
 494                 my $marc_record_object =
 495                   MARC::Record->new_from_usmarc($sup_record);
 496                 my $control_number =
 497                   $marc_record_object->field('010')->subfield('a')
 498                   if $marc_record_object->field('010');
 499                 $control_number =~ s/^ //g;
 500                 my $link =
 501                     "http://catalog.loc.gov/cgi-bin/Pwebrecon.cgi?SAB1="
 502                   . $control_number
 503                   . "&BOOL1=all+of+these&FLD1=LC+Control+Number+LCCN+%28K010%29+%28K010%29&GRP1=AND+with+next+set&SAB2=&BOOL2=all+of+these&FLD2=Keyword+Anywhere+%28GKEY%29+%28GKEY%29&PID=6211&SEQ=20060816121838&CNT=25&HIST=1";
 504                 my $title = $marc_record_object->title();
 505                 push @inner_sup_results_array,
 506                   {
 507                     'title' => $title,
 508                     'link'  => $link,
 509                   };
 510             }
 511             my $servername = $server;
 512             push @sup_results_array,
 513               {
 514                 servername             => $servername,
 515                 inner_sup_results_loop => \@inner_sup_results_array
 516               };
 517             $template->param( outer_sup_results_loop => \@sup_results_array );
 518         }
 519     }
 520
 521 }    #/end of the for loop
 522
 523 #$template->param(FEDERATED_RESULTS => \@results_array);
 524 # adding the $RequestOnOpac param
 525 my $RequestOnOpac;
 526 if (C4::Context->preference("RequestOnOpac")) {
 527         $RequestOnOpac = 1;
 528 }
 529 # get site URL (for RSS link)
 530 $cgi->url() =~ /(.*)\/(.*)/;
 531 my $site_url = $1;
 532
 533 $template->param(
 534
 535     #classlist => $classlist,
 536     total                => $total,
 537     searchdesc           => $search_desc,
 538     opacfacets           => 1,
 539     facets_loop          => $facets,
 540     "BiblioDefaultView" . C4::Context->preference("BiblioDefaultView") => 1,
 541     scan_use     => $scan,
 542     search_error => $error,
 543     RequestOnOpac        => $RequestOnOpac,
 544     RSS=> 1,
 545     site_url => $site_url,
 546 );
 547 ## Now let's find out if we have any supplemental data to show the user
 548 #  and in the meantime, save the current query for statistical purposes, etc.
 549 my $koha_spsuggest;   # a flag to tell if we've got suggestions coming from Koha
 550 my @koha_spsuggest
 551   ;    # place we store the suggestions to be returned to the template as LOOP
 552 my $phrases = $search_desc;
 553 my $ipaddress;
 554
 555 if ( C4::Context->preference("kohaspsuggest") ) {
 556         my ($suggest_host, $suggest_dbname, $suggest_user, $suggest_pwd) = split(':', C4::Context->preference("kohaspsuggest"));
 557     eval {
 558         my $koha_spsuggest_dbh;
 559
 560         # FIXME: this needs to be moved to Context.pm
 561         eval {
 562                         $koha_spsuggest_dbh=DBI->connect("DBI:mysql:$suggest_dbname:$suggest_host","$suggest_user","$suggest_pwd");
 563         };
 564         if ($@) {
 565             warn "can't connect to spsuggest db";
 566         }
 567         else {
 568             my $koha_spsuggest_insert =
 569 "INSERT INTO phrase_log(phr_phrase,phr_resultcount,phr_ip) VALUES(?,?,?)";
 570             my $koha_spsuggest_query =
 571 "SELECT display FROM distincts WHERE strcmp(soundex(suggestion), soundex(?)) = 0 order by soundex(suggestion) limit 0,5";
 572             my $koha_spsuggest_sth =
 573               $koha_spsuggest_dbh->prepare($koha_spsuggest_query);
 574             $koha_spsuggest_sth->execute($phrases);
 575             while ( my $spsuggestion = $koha_spsuggest_sth->fetchrow_array ) {
 576                 $spsuggestion =~ s/(:|\/)//g;
 577                 my %line;
 578                 $line{spsuggestion} = $spsuggestion;
 579                 push @koha_spsuggest, \%line;
 580                 $koha_spsuggest = 1;
 581             }
 582
 583             # Now save the current query
 584             $koha_spsuggest_sth =
 585               $koha_spsuggest_dbh->prepare($koha_spsuggest_insert);
 586
 587            #$koha_spsuggest_sth->execute($phrases,$results_per_page,$ipaddress);
 588             $koha_spsuggest_sth->finish;
 589             $template->param( koha_spsuggest => $koha_spsuggest ) unless $hits;
 590             $template->param( SPELL_SUGGEST => \@koha_spsuggest, );
 591         }
 592     };
 593     if ($@) {
 594         warn "Kohaspsuggest failure:" . $@;
 595     }
 596 }
 597
 598 # VI. BUILD THE TEMPLATE
 599 output_html_with_http_headers $cgi, $cookie, $template->output;