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 with
19 # Koha; if not, write to the Free Software Foundation, Inc., 59 Temple Place,
20 # Suite 330, Boston, MA 02111-1307 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 $query_desc - Human search description - what the user sees in search
113 This is a simple string that is human readable. It will contain '=', ',', etc.
117 =head3 2. Perform the Search
119 This section takes the query strings and performs searches on the named servers,
120 including the Koha Zebra server, stores the results in a deeply nested object,
121 builds 'faceted results', and returns these objects.
125 The final major section of this script takes the objects collected thusfar and
126 builds the HTML for output to the template and user.
128 =head3 Additional Notes
134 use strict; # always use
136 ## STEP 1. Load things that are used in both search page and
137 # results page and decide which template to load, operations
143 use C4::Auth qw(:DEFAULT get_session);
145 use C4::Languages qw(getAllLanguages);
147 use POSIX qw(ceil floor);
148 use C4::Branch; # GetBranches
150 # create a new CGI object
151 # FIXME: no_undef_params needs to be tested
152 use CGI qw('-no_undef_params');
155 my ($template,$borrowernumber,$cookie);
157 # decide which template to use
160 my @params = $cgi->param("limit");
161 if ((@params>=1) || ($cgi->param("q")) || ($cgi->param('multibranchlimit')) || ($cgi->param('limit-yr')) ) {
162 $template_name = 'catalogue/results.tmpl';
165 $template_name = 'catalogue/advsearch.tmpl';
166 $template_type = 'advsearch';
169 ($template, $borrowernumber, $cookie) = get_template_and_user({
170 template_name => $template_name,
173 authnotrequired => 0,
174 flagsrequired => { catalogue => 1 },
177 if (C4::Context->preference("marcflavour") eq "UNIMARC" ) {
178 $template->param('UNIMARC' => 1);
182 # Deprecated, but preserved because it's interesting :-)
183 # The same thing can be accomplished with mod_rewrite in
187 #my $uri = $cgi->url(-base => 1);
188 #my $relative_url = $cgi->url(-relative=>1);
189 #$uri.="/".$relative_url."?";
191 #my @cgi_params_list = $cgi->param();
192 #my $url_params = $cgi->Vars;
194 #for my $each_param_set (@cgi_params_list) {
195 # $uri.= join "", map "\&$each_param_set=".$_, split("\0",$url_params->{$each_param_set}) if $url_params->{$each_param_set};
197 #warn "New URI:$uri";
198 # Only re-write a URI if there are params or if it already hasn't been re-written
199 #unless (($cgi->param('r')) || (!$cgi->param()) ) {
200 # print $cgi->redirect( -uri=>$uri."&r=1",
201 # -cookie => $cookie);
206 my $branches = GetBranches();
209 # we need to know the borrower branch code to set a default branch
210 my $borrowerbranchcode = C4::Context->userenv->{'branch'};
212 for my $branch_hash (sort { $branches->{$a}->{branchname} cmp $branches->{$b}->{branchname} } keys %$branches) {
213 # if independantbranches is activated, set the default branch to the borrower branch
214 my $selected = (C4::Context->preference("independantbranches") and ($borrowerbranchcode eq $branch_hash)) ? 1 : undef;
215 push @branch_loop, {value => "$branch_hash" , branchname => $branches->{$branch_hash}->{'branchname'}, selected => $selected};
218 my $categories = GetBranchCategories(undef,'searchdomain');
220 $template->param(branchloop => \@branch_loop, searchdomainloop => $categories);
222 # load the Type stuff
223 # load the Type stuff
224 my $itemtypes = GetItemTypes;
225 # the index parameter is different for item-level itemtypes
226 my $itype_or_itemtype = (C4::Context->preference("item-level_itypes"))?'itype':'itemtype';
230 my $advanced_search_types = C4::Context->preference("AdvancedSearchTypes");
232 if (!$advanced_search_types or $advanced_search_types eq 'itemtypes') { foreach my $thisitemtype ( sort {$itemtypes->{$a}->{'description'} cmp $itemtypes->{$b}->{'description'} } keys %$itemtypes ) {
233 my %row =( number=>$cnt++,
234 ccl => $itype_or_itemtype,
235 code => $thisitemtype,
236 selected => $selected,
237 description => $itemtypes->{$thisitemtype}->{'description'},
239 imageurl=> getitemtypeimagelocation( 'intranet', $itemtypes->{$thisitemtype}->{'imageurl'} ),
241 $selected = 0 if ($selected) ;
242 push @itemtypesloop, \%row;
244 $template->param(itemtypeloop => \@itemtypesloop);
246 my $advsearchtypes = GetAuthorisedValues($advanced_search_types);
247 for my $thisitemtype (sort {$a->{'lib'} cmp $b->{'lib'}} @$advsearchtypes) {
250 ccl => $advanced_search_types,
251 code => $thisitemtype->{authorised_value},
252 selected => $selected,
253 description => $thisitemtype->{'lib'},
255 imageurl=> getitemtypeimagelocation( 'intranet', $thisitemtype->{'imageurl'} ),
257 push @itemtypesloop, \%row;
259 $template->param(itemtypeloop => \@itemtypesloop);
262 # The following should only be loaded if we're bringing up the advanced search template
263 if ( $template_type eq 'advsearch' ) {
265 # load the servers (used for searching -- to do federated searching, etc.)
266 my $primary_servers_loop;# = displayPrimaryServers();
267 $template->param(outer_servers_loop => $primary_servers_loop,);
269 my $secondary_servers_loop;
270 $template->param(outer_sup_servers_loop => $secondary_servers_loop,);
272 # set the default sorting
273 my $default_sort_by = C4::Context->preference('defaultSortField')."_".C4::Context->preference('defaultSortOrder')
274 if (C4::Context->preference('OPACdefaultSortField') && C4::Context->preference('OPACdefaultSortOrder'));
275 $template->param($default_sort_by => 1);
277 # determine what to display next to the search boxes (ie, boolean option
278 # shouldn't appear on the first one, scan indexes should, adding a new
279 # box should only appear on the last, etc.
280 my @search_boxes_array;
281 my $search_boxes_count = C4::Context->preference("OPACAdvSearchInputCount") || 3; # FIXME: using OPAC sysprefs?
282 # FIXME: all this junk can be done in TMPL using __first__ and __last__
283 for (my $i=1;$i<=$search_boxes_count;$i++) {
284 # if it's the first one, don't display boolean option, but show scan indexes
286 push @search_boxes_array, {scan_index => 1};
288 # if it's the last one, show the 'add field' box
289 elsif ($i==$search_boxes_count) {
290 push @search_boxes_array,
297 push @search_boxes_array,
304 $template->param(uc(C4::Context->preference("marcflavour")) => 1,
305 search_boxes_loop => \@search_boxes_array);
307 # load the language limits (for search)
308 my $languages_limit_loop = getAllLanguages();
309 $template->param(search_languages_loop => $languages_limit_loop,);
311 # use the global setting by default
312 if ( C4::Context->preference("expandedSearchOption") == 1) {
313 $template->param( expanded_options => C4::Context->preference("expandedSearchOption") );
315 # but let the user override it
316 if ( ($cgi->param('expanded_options') == 0) || ($cgi->param('expanded_options') == 1 ) ) {
317 $template->param( expanded_options => $cgi->param('expanded_options'));
320 $template->param(virtualshelves => C4::Context->preference("virtualshelves"));
322 output_html_with_http_headers $cgi, $cookie, $template->output;
326 ### OK, if we're this far, we're performing a search, not just loading the advanced search page
328 # Fetch the paramater list as a hash in scalar context:
329 # * returns paramater list as tied hash ref
330 # * we can edit the values by changing the key
331 # * multivalued CGI paramaters are returned as a packaged string separated by "\0" (null)
332 my $params = $cgi->Vars;
334 # Params that can have more than one value
335 # sort by is used to sort the query
336 # in theory can have more than one but generally there's just one
338 my $default_sort_by = C4::Context->preference('defaultSortField')."_".C4::Context->preference('defaultSortOrder')
339 if (C4::Context->preference('defaultSortField') && C4::Context->preference('defaultSortOrder'));
341 @sort_by = split("\0",$params->{'sort_by'}) if $params->{'sort_by'};
342 $sort_by[0] = $default_sort_by unless $sort_by[0];
343 foreach my $sort (@sort_by) {
344 $template->param($sort => 1);
346 $template->param('sort_by' => $sort_by[0]);
348 # Use the servers defined, or just search our local catalog(default)
350 @servers = split("\0",$params->{'server'}) if $params->{'server'};
352 #FIXME: this should be handled using Context.pm
353 @servers = ("biblioserver");
354 # @servers = C4::Context->config("biblioserver");
356 # operators include boolean and proximity operators and are used
357 # to evaluate multiple operands
359 @operators = split("\0",$params->{'op'}) if $params->{'op'};
361 # indexes are query qualifiers, like 'title', 'author', etc. They
362 # can be single or multiple parameters separated by comma: kw,right-Truncation
364 @indexes = split("\0",$params->{'idx'});
366 # if a simple index (only one) display the index used in the top search box
367 if ($indexes[0] && !$indexes[1]) {
368 $template->param("ms_".$indexes[0] => 1);}
371 # an operand can be a single term, a phrase, or a complete ccl query
373 @operands = split("\0",$params->{'q'}) if $params->{'q'};
375 # limits are use to limit to results to a pre-defined category such as branch or language
377 @limits = split("\0",$params->{'limit'}) if $params->{'limit'};
379 if($params->{'multibranchlimit'}) {
380 push @limits, join(" or ", map { "branch: $_ "} @{GetBranchesInCategory($params->{'multibranchlimit'})}) ;
384 foreach my $limit(@limits) {
385 if ($limit =~/available/) {
389 $template->param(available => $available);
391 # append year limits if they exist
394 if ($params->{'limit-yr'}) {
395 if ($params->{'limit-yr'} =~ /\d{4}-\d{4}/) {
396 my ($yr1,$yr2) = split(/-/, $params->{'limit-yr'});
397 $limit_yr = "yr,st-numeric,ge=$yr1 and yr,st-numeric,le=$yr2";
398 $limit_yr_value = "$yr1-$yr2";
400 elsif ($params->{'limit-yr'} =~ /\d{4}/) {
401 $limit_yr = "yr,st-numeric=$params->{'limit-yr'}";
402 $limit_yr_value = $params->{'limit-yr'};
404 push @limits,$limit_yr;
405 #FIXME: Should return a error to the user, incorect date format specified
408 # convert indexes and operands to corresponding parameter names for the z3950 search
409 # $ %z3950p will be a hash ref if the indexes are present (advacned search), otherwise undef
411 my $indexes2z3950 = {
412 kw=>'title', au=>'author', 'au,phr'=>'author', nb=>'isbn', ns=>'issn',
413 'lcn,phr'=>'dewey', su=>'subject', 'su,phr'=>'subject',
414 ti=>'title', 'ti,phr'=>'title', se=>'title'
416 for (my $ii = 0; $ii < @operands; ++$ii)
418 my $name = $indexes2z3950->{$indexes[$ii]};
419 if (defined $name && defined $operands[$ii])
422 $z3950par->{$name} = $operands[$ii] if !exists $z3950par->{$name};
427 # Params that can only have one value
428 my $scan = $params->{'scan'};
429 my $count = C4::Context->preference('numSearchResults') || 20;
430 my $results_per_page = $params->{'count'} || $count;
431 my $offset = $params->{'offset'} || 0;
432 my $page = $cgi->param('page') || 1;
433 #my $offset = ($page-1)*$results_per_page;
435 my $expanded_facet = $params->{'expand'};
437 # Define some global variables
438 my ( $error,$query,$simple_query,$query_cgi,$query_desc,$limit,$limit_cgi,$limit_desc,$stopwords_removed,$query_type);
442 ## I. BUILD THE QUERY
443 my $lang = C4::Output::getlanguagecookie($cgi);
444 ( $error,$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);
446 ## parse the query_cgi string and put it into a form suitable for <input>s
448 my $scan_index_to_use;
450 for my $this_cgi ( split('&',$query_cgi) ) {
451 next unless $this_cgi;
452 $this_cgi =~ m/(.*=)(.*)/;
454 my $input_value = $2;
455 $input_name =~ s/=$//;
456 push @query_inputs, { input_name => $input_name, input_value => $input_value };
457 if ($input_name eq 'idx') {
458 $scan_index_to_use = $input_value; # unless $scan_index_to_use;
461 $template->param ( QUERY_INPUTS => \@query_inputs,
462 scan_index_to_use => $scan_index_to_use );
464 ## parse the limit_cgi string and put it into a form suitable for <input>s
466 for my $this_cgi ( split('&',$limit_cgi) ) {
467 next unless $this_cgi;
468 # handle special case limit-yr
469 if ($this_cgi =~ /yr,st-numeric/) {
470 push @limit_inputs, { input_name => 'limit-yr', input_value => $limit_yr_value };
473 $this_cgi =~ m/(.*=)(.*)/;
475 my $input_value = $2;
476 $input_name =~ s/=$//;
477 push @limit_inputs, { input_name => $input_name, input_value => $input_value };
479 $template->param ( LIMIT_INPUTS => \@limit_inputs );
481 ## II. DO THE SEARCH AND GET THE RESULTS
482 my $total; # the total results for the whole set
483 my $facets; # this object stores the faceted results that display on the left-hand of the results page
487 if (C4::Context->preference('NoZebra')) {
488 $query=~s/yr(:|=)\s*([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
489 $simple_query=~s/yr\s*(:|=)([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
492 ($error, $results_hashref, $facets) = NZgetRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
496 ($error, $results_hashref, $facets) = getRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
500 $template->param(query_error => $error.$@);
501 output_html_with_http_headers $cgi, $cookie, $template->output;
505 # At this point, each server has given us a result set
506 # now we build that set for template display
507 my @sup_results_array;
508 for (my $i=0;$i<@servers;$i++) {
509 my $server = $servers[$i];
510 if ($server =~/biblioserver/) { # this is the local bibliographic server
511 $hits = $results_hashref->{$server}->{"hits"};
512 my $page = $cgi->param('page') || 0;
513 my @newresults = searchResults( $query_desc,$hits,$results_per_page,$offset,$scan,@{$results_hashref->{$server}->{"RECORDS"}});
514 $total = $total + $results_hashref->{$server}->{"hits"};
515 ## If there's just one result, redirect to the detail page
517 my $biblionumber = $newresults[0]->{biblionumber};
518 my $defaultview = C4::Context->preference('IntranetBiblioDefaultView');
519 my $views = { C4::Search::enabled_staff_search_views };
520 if ($defaultview eq 'isbd' && $views->{can_view_ISBD}) {
521 print $cgi->redirect("/cgi-bin/koha/catalogue/ISBDdetail.pl?biblionumber=$biblionumber");
522 } elsif ($defaultview eq 'marc' && $views->{can_view_MARC}) {
523 print $cgi->redirect("/cgi-bin/koha/catalogue/MARCdetail.pl?biblionumber=$biblionumber");
524 } elsif ($defaultview eq 'labeled_marc' && $views->{can_view_labeledMARC}) {
525 print $cgi->redirect("/cgi-bin/koha/catalogue/labeledMARCdetail.pl?biblionumber=$biblionumber");
527 print $cgi->redirect("/cgi-bin/koha/catalogue/detail.pl?biblionumber=$biblionumber");
534 $template->param(total => $hits);
535 my $limit_cgi_not_availablity = $limit_cgi;
536 $limit_cgi_not_availablity =~ s/&limit=available//g;
537 $template->param(limit_cgi_not_availablity => $limit_cgi_not_availablity);
538 $template->param(limit_cgi => $limit_cgi);
539 $template->param(query_cgi => $query_cgi);
540 $template->param(query_desc => $query_desc);
541 $template->param(limit_desc => $limit_desc);
542 $template->param (z3950_search_params => C4::Search::z3950_search_args($query_desc));
543 if ($query_desc || $limit_desc) {
544 $template->param(searchdesc => 1);
546 $template->param(stopwords_removed => "@$stopwords_removed") if $stopwords_removed;
547 $template->param(results_per_page => $results_per_page);
548 $template->param(SEARCH_RESULTS => \@newresults);
550 ## FIXME: add a global function for this, it's better than the current global one
551 ## Build the page numbers on the bottom of the page
553 # total number of pages there will be
554 my $pages = ceil($hits / $results_per_page);
555 # default page number
556 my $current_page_number = 1;
557 $current_page_number = ($offset / $results_per_page + 1) if $offset;
558 my $previous_page_offset = $offset - $results_per_page unless ($offset - $results_per_page <0);
559 my $next_page_offset = $offset + $results_per_page;
560 # If we're within the first 10 pages, keep it simple
561 #warn "current page:".$current_page_number;
562 if ($current_page_number < 10) {
563 # just show the first 10 pages
564 # Loop through the pages
565 my $pages_to_show = 10;
566 $pages_to_show = $pages if $pages<10;
567 for (my $i=1; $i<=$pages_to_show;$i++) {
568 # the offset for this page
569 my $this_offset = (($i*$results_per_page)-$results_per_page);
570 # the page number for this page
571 my $this_page_number = $i;
572 # it should only be highlighted if it's the current page
573 my $highlight = 1 if ($this_page_number == $current_page_number);
574 # put it in the array
575 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
581 # now, show twenty pages, with the current one smack in the middle
583 for (my $i=$current_page_number; $i<=($current_page_number + 20 );$i++) {
584 my $this_offset = ((($i-9)*$results_per_page)-$results_per_page);
585 my $this_page_number = $i-9;
586 my $highlight = 1 if ($this_page_number == $current_page_number);
587 if ($this_page_number <= $pages) {
588 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
592 # FIXME: no previous_page_offset when pages < 2
593 $template->param( PAGE_NUMBERS => \@page_numbers,
594 previous_page_offset => $previous_page_offset) unless $pages < 2;
595 $template->param( next_page_offset => $next_page_offset) unless $pages eq $current_page_number;
601 $template->param(searchdesc => 1,query_desc => $query_desc,limit_desc => $limit_desc);
602 $template->param (z3950_search_params => C4::Search::z3950_search_args($z3950par || $query_desc));
605 } # end of the if local
607 # asynchronously search the authority server
608 elsif ($server =~/authorityserver/) { # this is the local authority server
609 my @inner_sup_results_array;
610 for my $sup_record ( @{$results_hashref->{$server}->{"RECORDS"}} ) {
611 my $marc_record_object = MARC::Record->new_from_usmarc($sup_record);
612 # warn "Authority Found: ".$marc_record_object->as_formatted();
613 push @inner_sup_results_array, {
614 'title' => $marc_record_object->field(100)->subfield('a'),
615 'link' => "&idx=an&q=".$marc_record_object->field('001')->as_string(),
618 push @sup_results_array, { servername => $server,
619 inner_sup_results_loop => \@inner_sup_results_array} if @inner_sup_results_array;
621 # FIXME: can add support for other targets as needed here
622 $template->param( outer_sup_results_loop => \@sup_results_array);
623 } #/end of the for loop
624 #$template->param(FEDERATED_RESULTS => \@results_array);
628 #classlist => $classlist,
631 facets_loop => $facets,
633 search_error => $error,
636 if ($query_desc || $limit_desc) {
637 $template->param(searchdesc => 1);
640 # VI. BUILD THE TEMPLATE
642 # Build drop-down list for 'Add To:' menu...
643 my $session = get_session($cgi->cookie("CGISESSID"));
645 my $pubshelves = $session->param('pubshelves');
646 my $barshelves = $session->param('barshelves');
647 foreach my $shelf (@$pubshelves) {
648 next if ( ($shelf->{'owner'} != ($borrowernumber ? $borrowernumber : -1)) && ($shelf->{'category'} < 3) );
649 push (@addpubshelves, $shelf);
652 if (@addpubshelves) {
653 $template->param( addpubshelves => scalar (@addpubshelves));
654 $template->param( addpubshelvesloop => \@addpubshelves);
657 if (defined $barshelves) {
658 $template->param( addbarshelves => scalar (@$barshelves));
659 $template->param( addbarshelvesloop => $barshelves);
664 output_html_with_http_headers $cgi, $cookie, $template->output;