2 # Script to perform searching
3 # For documentation try 'perldoc /path/to/search'
5 # Copyright 2006 LibLime
7 # This file is part of Koha
9 # Koha is free software; you can redistribute it and/or modify it under the
10 # terms of the GNU General Public License as published by the Free Software
11 # Foundation; either version 2 of the License, or (at your option) any later
14 # Koha is distributed in the hope that it will be useful, but WITHOUT ANY
15 # WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
16 # A PARTICULAR PURPOSE. See the GNU General Public License for more details.
18 # You should have received a copy of the GNU General Public License along
19 # with Koha; if not, write to the Free Software Foundation, Inc.,
20 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
24 search - a search script for finding records in a Koha system (Version 3)
28 This script utilizes a new search API for Koha 3. It is designed to be
29 simple to use and configure, yet capable of performing feats like stemming,
30 field weighting, relevance ranking, support for multiple query language
31 formats (CCL, CQL, PQF), full support for the bib1 attribute set, extended
32 attribute sets defined in Zebra profiles, access to the full range of Z39.50
33 and SRU query options, federated searches on Z39.50/SRU targets, etc.
35 The API as represented in this script is mostly sound, even if the individual
36 functions in Search.pm and Koha.pm need to be cleaned up. Of course, you are
39 I will attempt to describe what is happening at each part of this script.
40 -- Joshua Ferraro <jmf AT liblime DOT com>
44 This script performs two functions:
48 =item 1. interacts with Koha to retrieve and display the results of a search
50 =item 2. loads the advanced search page
54 These two functions share many of the same variables and modules, so the first
55 task is to load what they have in common and determine which template to use.
56 Once determined, proceed to only load the variables and procedures necessary
59 =head2 LOADING ADVANCED SEARCH PAGE
61 This is fairly straightforward, and I won't go into detail ;-)
63 =head2 PERFORMING A SEARCH
65 If we're performing a search, this script performs three primary
70 =item 1. builds query strings (yes, plural)
72 =item 2. perform the search and return the results array
74 =item 3. build the HTML for output to the template
78 There are several additional secondary functions performed that I will
81 =head3 1. Building Query Strings
83 There are several types of queries needed in the process of search and retrieve:
87 =item 1 $query - the fully-built query passed to zebra
89 This is the most complex query that needs to be built. The original design goal
90 was to use a custom CCL2PQF query parser to translate an incoming CCL query into
91 a multi-leaf query to pass to Zebra. It needs to be multi-leaf to allow field
92 weighting, koha-specific relevance ranking, and stemming. When I have a chance
93 I'll try to flesh out this section to better explain.
95 This query incorporates query profiles that aren't compatible with most non-Zebra
96 Z39.50 targets to acomplish the field weighting and relevance ranking.
98 =item 2 $simple_query - a simple query that doesn't contain the field weighting,
99 stemming, etc., suitable to pass off to other search targets
101 This query is just the user's query expressed in CCL CQL, or PQF for passing to a
102 non-zebra Z39.50 target (one that doesn't support the extended profile that Zebra does).
104 =item 3 $query_cgi - passed to the template / saved for future refinements of
107 This is a simple string that completely expresses the query as a CGI string that
108 can be used for future refinements of the query or as a part of a history feature.
110 =item 4 $query_desc - Human search description - what the user sees in search
113 This is a simple string that is human readable. It will contain '=', ',', etc.
117 =head3 2. Perform the Search
119 This section takes the query strings and performs searches on the named servers,
120 including the Koha Zebra server, stores the results in a deeply nested object,
121 builds 'faceted results', and returns these objects.
125 The final major section of this script takes the objects collected thusfar and
126 builds the HTML for output to the template and user.
128 =head3 Additional Notes
134 use strict; # always use
135 #use warnings; FIXME - Bug 2505
137 ## STEP 1. Load things that are used in both search page and
138 # results page and decide which template to load, operations
144 use C4::Auth qw(:DEFAULT get_session);
146 use C4::Languages qw(getAllLanguages);
148 use C4::VirtualShelves qw(GetRecentShelves);
149 use POSIX qw(ceil floor);
150 use C4::Branch; # GetBranches
152 my $DisplayMultiPlaceHold = C4::Context->preference("DisplayMultiPlaceHold");
153 # create a new CGI object
154 # FIXME: no_undef_params needs to be tested
155 use CGI qw('-no_undef_params');
158 my ($template,$borrowernumber,$cookie);
160 # decide which template to use
163 my @params = $cgi->param("limit");
164 if ((@params>=1) || ($cgi->param("q")) || ($cgi->param('multibranchlimit')) || ($cgi->param('limit-yr')) ) {
165 $template_name = 'catalogue/results.tmpl';
168 $template_name = 'catalogue/advsearch.tmpl';
169 $template_type = 'advsearch';
172 ($template, $borrowernumber, $cookie) = get_template_and_user({
173 template_name => $template_name,
176 authnotrequired => 0,
177 flagsrequired => { catalogue => 1 },
180 if (C4::Context->preference("marcflavour") eq "UNIMARC" ) {
181 $template->param('UNIMARC' => 1);
185 # Deprecated, but preserved because it's interesting :-)
186 # The same thing can be accomplished with mod_rewrite in
190 #my $uri = $cgi->url(-base => 1);
191 #my $relative_url = $cgi->url(-relative=>1);
192 #$uri.="/".$relative_url."?";
194 #my @cgi_params_list = $cgi->param();
195 #my $url_params = $cgi->Vars;
197 #for my $each_param_set (@cgi_params_list) {
198 # $uri.= join "", map "\&$each_param_set=".$_, split("\0",$url_params->{$each_param_set}) if $url_params->{$each_param_set};
200 #warn "New URI:$uri";
201 # Only re-write a URI if there are params or if it already hasn't been re-written
202 #unless (($cgi->param('r')) || (!$cgi->param()) ) {
203 # print $cgi->redirect( -uri=>$uri."&r=1",
204 # -cookie => $cookie);
209 my $branches = GetBranches();
211 # Populate branch_loop with all branches sorted by their name. If
212 # independantbranches is activated, set the default branch to the borrower
213 # branch, except for superlibrarian who need to search all libraries.
214 my $user = C4::Context->userenv;
215 my @branch_loop = map {
218 branchname => $branches->{$_}->{branchname},
219 selected => $user->{branch} eq $_ && C4::Branch::onlymine(),
222 $branches->{$a}->{branchname} cmp $branches->{$b}->{branchname}
225 my $categories = GetBranchCategories(undef,'searchdomain');
227 $template->param(branchloop => \@branch_loop, searchdomainloop => $categories);
229 # load the Type stuff
230 # load the Type stuff
231 my $itemtypes = GetItemTypes;
232 # the index parameter is different for item-level itemtypes
233 my $itype_or_itemtype = (C4::Context->preference("item-level_itypes"))?'itype':'itemtype';
237 my $advanced_search_types = C4::Context->preference("AdvancedSearchTypes");
239 if (!$advanced_search_types or $advanced_search_types eq 'itemtypes') { foreach my $thisitemtype ( sort {$itemtypes->{$a}->{'description'} cmp $itemtypes->{$b}->{'description'} } keys %$itemtypes ) {
240 my %row =( number=>$cnt++,
241 ccl => $itype_or_itemtype,
242 code => $thisitemtype,
243 selected => $selected,
244 description => $itemtypes->{$thisitemtype}->{'description'},
246 imageurl=> getitemtypeimagelocation( 'intranet', $itemtypes->{$thisitemtype}->{'imageurl'} ),
248 $selected = 0 if ($selected) ;
249 push @itemtypesloop, \%row;
251 $template->param(itemtypeloop => \@itemtypesloop);
253 my $advsearchtypes = GetAuthorisedValues($advanced_search_types);
254 for my $thisitemtype (sort {$a->{'lib'} cmp $b->{'lib'}} @$advsearchtypes) {
257 ccl => $advanced_search_types,
258 code => $thisitemtype->{authorised_value},
259 selected => $selected,
260 description => $thisitemtype->{'lib'},
262 imageurl=> getitemtypeimagelocation( 'intranet', $thisitemtype->{'imageurl'} ),
264 push @itemtypesloop, \%row;
266 $template->param(itemtypeloop => \@itemtypesloop);
269 # The following should only be loaded if we're bringing up the advanced search template
270 if ( $template_type eq 'advsearch' ) {
272 # load the servers (used for searching -- to do federated searching, etc.)
273 my $primary_servers_loop;# = displayPrimaryServers();
274 $template->param(outer_servers_loop => $primary_servers_loop,);
276 my $secondary_servers_loop;
277 $template->param(outer_sup_servers_loop => $secondary_servers_loop,);
279 # set the default sorting
280 my $default_sort_by = C4::Context->preference('defaultSortField')."_".C4::Context->preference('defaultSortOrder')
281 if (C4::Context->preference('OPACdefaultSortField') && C4::Context->preference('OPACdefaultSortOrder'));
282 $template->param($default_sort_by => 1);
284 # determine what to display next to the search boxes (ie, boolean option
285 # shouldn't appear on the first one, scan indexes should, adding a new
286 # box should only appear on the last, etc.
287 my @search_boxes_array;
288 my $search_boxes_count = C4::Context->preference("OPACAdvSearchInputCount") || 3; # FIXME: using OPAC sysprefs?
289 # FIXME: all this junk can be done in TMPL using __first__ and __last__
290 for (my $i=1;$i<=$search_boxes_count;$i++) {
291 # if it's the first one, don't display boolean option, but show scan indexes
293 push @search_boxes_array, {scan_index => 1};
295 # if it's the last one, show the 'add field' box
296 elsif ($i==$search_boxes_count) {
297 push @search_boxes_array,
304 push @search_boxes_array,
311 $template->param(uc(C4::Context->preference("marcflavour")) => 1,
312 search_boxes_loop => \@search_boxes_array);
314 # load the language limits (for search)
315 my $languages_limit_loop = getAllLanguages();
316 $template->param(search_languages_loop => $languages_limit_loop,);
318 # use the global setting by default
319 if ( C4::Context->preference("expandedSearchOption") == 1) {
320 $template->param( expanded_options => C4::Context->preference("expandedSearchOption") );
322 # but let the user override it
323 if ( ($cgi->param('expanded_options') == 0) || ($cgi->param('expanded_options') == 1 ) ) {
324 $template->param( expanded_options => $cgi->param('expanded_options'));
327 $template->param(virtualshelves => C4::Context->preference("virtualshelves"));
329 output_html_with_http_headers $cgi, $cookie, $template->output;
333 ### OK, if we're this far, we're performing a search, not just loading the advanced search page
335 # Fetch the paramater list as a hash in scalar context:
336 # * returns paramater list as tied hash ref
337 # * we can edit the values by changing the key
338 # * multivalued CGI paramaters are returned as a packaged string separated by "\0" (null)
339 my $params = $cgi->Vars;
341 # Params that can have more than one value
342 # sort by is used to sort the query
343 # in theory can have more than one but generally there's just one
345 my $default_sort_by = C4::Context->preference('defaultSortField')."_".C4::Context->preference('defaultSortOrder')
346 if (C4::Context->preference('defaultSortField') && C4::Context->preference('defaultSortOrder'));
348 @sort_by = split("\0",$params->{'sort_by'}) if $params->{'sort_by'};
349 $sort_by[0] = $default_sort_by unless $sort_by[0];
350 foreach my $sort (@sort_by) {
351 $template->param($sort => 1);
353 $template->param('sort_by' => $sort_by[0]);
355 # Use the servers defined, or just search our local catalog(default)
357 @servers = split("\0",$params->{'server'}) if $params->{'server'};
359 #FIXME: this should be handled using Context.pm
360 @servers = ("biblioserver");
361 # @servers = C4::Context->config("biblioserver");
363 # operators include boolean and proximity operators and are used
364 # to evaluate multiple operands
366 @operators = split("\0",$params->{'op'}) if $params->{'op'};
368 # indexes are query qualifiers, like 'title', 'author', etc. They
369 # can be single or multiple parameters separated by comma: kw,right-Truncation
371 @indexes = split("\0",$params->{'idx'});
373 # if a simple index (only one) display the index used in the top search box
374 if ($indexes[0] && !$indexes[1]) {
375 $template->param("ms_".$indexes[0] => 1);}
378 # an operand can be a single term, a phrase, or a complete ccl query
380 @operands = split("\0",$params->{'q'}) if $params->{'q'};
382 # limits are use to limit to results to a pre-defined category such as branch or language
384 @limits = split("\0",$params->{'limit'}) if $params->{'limit'};
386 if($params->{'multibranchlimit'}) {
387 push @limits, join(" or ", map { "branch: $_ "} @{GetBranchesInCategory($params->{'multibranchlimit'})}) ;
391 foreach my $limit(@limits) {
392 if ($limit =~/available/) {
396 $template->param(available => $available);
398 # append year limits if they exist
401 if ($params->{'limit-yr'}) {
402 if ($params->{'limit-yr'} =~ /\d{4}-\d{4}/) {
403 my ($yr1,$yr2) = split(/-/, $params->{'limit-yr'});
404 $limit_yr = "yr,st-numeric,ge=$yr1 and yr,st-numeric,le=$yr2";
405 $limit_yr_value = "$yr1-$yr2";
407 elsif ($params->{'limit-yr'} =~ /\d{4}/) {
408 $limit_yr = "yr,st-numeric=$params->{'limit-yr'}";
409 $limit_yr_value = $params->{'limit-yr'};
411 push @limits,$limit_yr;
412 #FIXME: Should return a error to the user, incorect date format specified
415 # convert indexes and operands to corresponding parameter names for the z3950 search
416 # $ %z3950p will be a hash ref if the indexes are present (advacned search), otherwise undef
418 my $indexes2z3950 = {
419 kw=>'title', au=>'author', 'au,phr'=>'author', nb=>'isbn', ns=>'issn',
420 'lcn,phr'=>'dewey', su=>'subject', 'su,phr'=>'subject',
421 ti=>'title', 'ti,phr'=>'title', se=>'title'
423 for (my $ii = 0; $ii < @operands; ++$ii)
425 my $name = $indexes2z3950->{$indexes[$ii]};
426 if (defined $name && defined $operands[$ii])
429 $z3950par->{$name} = $operands[$ii] if !exists $z3950par->{$name};
434 # Params that can only have one value
435 my $scan = $params->{'scan'};
436 my $count = C4::Context->preference('numSearchResults') || 20;
437 my $results_per_page = $params->{'count'} || $count;
438 my $offset = $params->{'offset'} || 0;
439 my $page = $cgi->param('page') || 1;
440 #my $offset = ($page-1)*$results_per_page;
442 my $expanded_facet = $params->{'expand'};
444 # Define some global variables
445 my ( $error,$query,$simple_query,$query_cgi,$query_desc,$limit,$limit_cgi,$limit_desc,$stopwords_removed,$query_type);
449 ## I. BUILD THE QUERY
450 my $lang = C4::Output::getlanguagecookie($cgi);
451 ( $error,$query,$simple_query,$query_cgi,$query_desc,$limit,$limit_cgi,$limit_desc,$stopwords_removed,$query_type) = buildQuery(\@operators,\@operands,\@indexes,\@limits,\@sort_by,$scan,$lang);
453 ## parse the query_cgi string and put it into a form suitable for <input>s
455 my $scan_index_to_use;
457 for my $this_cgi ( split('&',$query_cgi) ) {
458 next unless $this_cgi;
459 $this_cgi =~ m/(.*=)(.*)/;
461 my $input_value = $2;
462 $input_name =~ s/=$//;
463 push @query_inputs, { input_name => $input_name, input_value => $input_value };
464 if ($input_name eq 'idx') {
465 $scan_index_to_use = $input_value; # unless $scan_index_to_use;
468 $template->param ( QUERY_INPUTS => \@query_inputs,
469 scan_index_to_use => $scan_index_to_use );
471 ## parse the limit_cgi string and put it into a form suitable for <input>s
473 for my $this_cgi ( split('&',$limit_cgi) ) {
474 next unless $this_cgi;
475 # handle special case limit-yr
476 if ($this_cgi =~ /yr,st-numeric/) {
477 push @limit_inputs, { input_name => 'limit-yr', input_value => $limit_yr_value };
480 $this_cgi =~ m/(.*=)(.*)/;
482 my $input_value = $2;
483 $input_name =~ s/=$//;
484 push @limit_inputs, { input_name => $input_name, input_value => $input_value };
486 $template->param ( LIMIT_INPUTS => \@limit_inputs );
488 ## II. DO THE SEARCH AND GET THE RESULTS
489 my $total; # the total results for the whole set
490 my $facets; # this object stores the faceted results that display on the left-hand of the results page
494 if (C4::Context->preference('NoZebra')) {
495 $query=~s/yr(:|=)\s*([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
496 $simple_query=~s/yr\s*(:|=)([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
499 ($error, $results_hashref, $facets) = NZgetRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
503 ($error, $results_hashref, $facets) = getRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
506 # This sorts the facets into alphabetical order
508 foreach my $f (@$facets) {
509 $f->{facets} = [ sort { uc($a->{facet_title_value}) cmp uc($b->{facet_title_value}) } @{ $f->{facets} } ];
513 $template->param(query_error => $error.$@);
514 output_html_with_http_headers $cgi, $cookie, $template->output;
518 # At this point, each server has given us a result set
519 # now we build that set for template display
520 my @sup_results_array;
521 for (my $i=0;$i<@servers;$i++) {
522 my $server = $servers[$i];
523 if ($server =~/biblioserver/) { # this is the local bibliographic server
524 $hits = $results_hashref->{$server}->{"hits"};
525 my $page = $cgi->param('page') || 0;
526 my @newresults = searchResults('intranet', $query_desc, $hits, $results_per_page, $offset, $scan,
527 @{$results_hashref->{$server}->{"RECORDS"}});
528 $total = $total + $results_hashref->{$server}->{"hits"};
529 ## If there's just one result, redirect to the detail page
531 my $biblionumber = $newresults[0]->{biblionumber};
532 my $defaultview = C4::Context->preference('IntranetBiblioDefaultView');
533 my $views = { C4::Search::enabled_staff_search_views };
534 if ($defaultview eq 'isbd' && $views->{can_view_ISBD}) {
535 print $cgi->redirect("/cgi-bin/koha/catalogue/ISBDdetail.pl?biblionumber=$biblionumber");
536 } elsif ($defaultview eq 'marc' && $views->{can_view_MARC}) {
537 print $cgi->redirect("/cgi-bin/koha/catalogue/MARCdetail.pl?biblionumber=$biblionumber");
538 } elsif ($defaultview eq 'labeled_marc' && $views->{can_view_labeledMARC}) {
539 print $cgi->redirect("/cgi-bin/koha/catalogue/labeledMARCdetail.pl?biblionumber=$biblionumber");
541 print $cgi->redirect("/cgi-bin/koha/catalogue/detail.pl?biblionumber=$biblionumber");
548 $template->param(total => $hits);
549 my $limit_cgi_not_availablity = $limit_cgi;
550 $limit_cgi_not_availablity =~ s/&limit=available//g;
551 $template->param(limit_cgi_not_availablity => $limit_cgi_not_availablity);
552 $template->param(limit_cgi => $limit_cgi);
553 $template->param(query_cgi => $query_cgi);
554 $template->param(query_desc => $query_desc);
555 $template->param(limit_desc => $limit_desc);
556 $template->param(offset => $offset);
557 $template->param(DisplayMultiPlaceHold => $DisplayMultiPlaceHold);
558 $template->param (z3950_search_params => C4::Search::z3950_search_args($query_desc));
559 if ($query_desc || $limit_desc) {
560 $template->param(searchdesc => 1);
562 $template->param(stopwords_removed => "@$stopwords_removed") if $stopwords_removed;
563 $template->param(results_per_page => $results_per_page);
564 $template->param(SEARCH_RESULTS => \@newresults);
566 ## FIXME: add a global function for this, it's better than the current global one
567 ## Build the page numbers on the bottom of the page
569 # total number of pages there will be
570 my $pages = ceil($hits / $results_per_page);
571 # default page number
572 my $current_page_number = 1;
573 $current_page_number = ($offset / $results_per_page + 1) if $offset;
574 my $previous_page_offset = $offset - $results_per_page unless ($offset - $results_per_page <0);
575 my $next_page_offset = $offset + $results_per_page;
576 # If we're within the first 10 pages, keep it simple
577 #warn "current page:".$current_page_number;
578 if ($current_page_number < 10) {
579 # just show the first 10 pages
580 # Loop through the pages
581 my $pages_to_show = 10;
582 $pages_to_show = $pages if $pages<10;
583 for (my $i=1; $i<=$pages_to_show;$i++) {
584 # the offset for this page
585 my $this_offset = (($i*$results_per_page)-$results_per_page);
586 # the page number for this page
587 my $this_page_number = $i;
588 # it should only be highlighted if it's the current page
589 my $highlight = 1 if ($this_page_number == $current_page_number);
590 # put it in the array
591 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
597 # now, show twenty pages, with the current one smack in the middle
599 for (my $i=$current_page_number; $i<=($current_page_number + 20 );$i++) {
600 my $this_offset = ((($i-9)*$results_per_page)-$results_per_page);
601 my $this_page_number = $i-9;
602 my $highlight = 1 if ($this_page_number == $current_page_number);
603 if ($this_page_number <= $pages) {
604 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
608 # FIXME: no previous_page_offset when pages < 2
609 $template->param( PAGE_NUMBERS => \@page_numbers,
610 previous_page_offset => $previous_page_offset) unless $pages < 2;
611 $template->param( next_page_offset => $next_page_offset) unless $pages eq $current_page_number;
617 $template->param(searchdesc => 1,query_desc => $query_desc,limit_desc => $limit_desc);
618 $template->param (z3950_search_params => C4::Search::z3950_search_args($z3950par || $query_desc));
621 } # end of the if local
623 # asynchronously search the authority server
624 elsif ($server =~/authorityserver/) { # this is the local authority server
625 my @inner_sup_results_array;
626 for my $sup_record ( @{$results_hashref->{$server}->{"RECORDS"}} ) {
627 my $marc_record_object = MARC::Record->new_from_usmarc($sup_record);
628 # warn "Authority Found: ".$marc_record_object->as_formatted();
629 push @inner_sup_results_array, {
630 'title' => $marc_record_object->field(100)->subfield('a'),
631 'link' => "&idx=an&q=".$marc_record_object->field('001')->as_string(),
634 push @sup_results_array, { servername => $server,
635 inner_sup_results_loop => \@inner_sup_results_array} if @inner_sup_results_array;
637 # FIXME: can add support for other targets as needed here
638 $template->param( outer_sup_results_loop => \@sup_results_array);
639 } #/end of the for loop
640 #$template->param(FEDERATED_RESULTS => \@results_array);
644 #classlist => $classlist,
647 facets_loop => $facets,
649 search_error => $error,
652 if ($query_desc || $limit_desc) {
653 $template->param(searchdesc => 1);
656 # VI. BUILD THE TEMPLATE
658 # Build drop-down list for 'Add To:' menu...
660 my $row_count = 10; # FIXME:This probably should be a syspref
661 my ($pubshelves, $total) = GetRecentShelves(2, $row_count, undef);
662 my ($barshelves, $total) = GetRecentShelves(1, $row_count, $borrowernumber);
664 my @pubshelves = @{$pubshelves};
665 my @barshelves = @{$barshelves};
668 $template->param( addpubshelves => scalar (@pubshelves));
669 $template->param( addpubshelvesloop => @pubshelves);
673 $template->param( addbarshelves => scalar (@barshelves));
674 $template->param( addbarshelvesloop => @barshelves);
679 output_html_with_http_headers $cgi, $cookie, $template->output;