2 # Script to perform searching
3 # For documentation try 'perldoc /path/to/search'
7 # Copyright 2006 LibLime
9 # This file is part of Koha
11 # Koha is free software; you can redistribute it and/or modify it under the
12 # terms of the GNU General Public License as published by the Free Software
13 # Foundation; either version 2 of the License, or (at your option) any later
16 # Koha is distributed in the hope that it will be useful, but WITHOUT ANY
17 # WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
18 # A PARTICULAR PURPOSE. See the GNU General Public License for more details.
20 # You should have received a copy of the GNU General Public License along with
21 # Koha; if not, write to the Free Software Foundation, Inc., 59 Temple Place,
22 # Suite 330, Boston, MA 02111-1307 USA
26 search - a search script for finding records in a Koha system (Version 3)
30 This script utilizes a new search API for Koha 3. It is designed to be
31 simple to use and configure, yet capable of performing feats like stemming,
32 field weighting, relevance ranking, support for multiple query language
33 formats (CCL, CQL, PQF), full support for the bib1 attribute set, extended
34 attribute sets defined in Zebra profiles, access to the full range of Z39.50
35 and SRU query options, federated searches on Z39.50/SRU targets, etc.
37 The API as represented in this script is mostly sound, even if the individual
38 functions in Search.pm and Koha.pm need to be cleaned up. Of course, you are
41 I will attempt to describe what is happening at each part of this script.
42 -- Joshua Ferraro <jmf AT liblime DOT com>
46 This script performs two functions:
50 =item 1. interacts with Koha to retrieve and display the results of a search
52 =item 2. loads the advanced search page
56 These two functions share many of the same variables and modules, so the first
57 task is to load what they have in common and determine which template to use.
58 Once determined, proceed to only load the variables and procedures necessary
61 =head2 LOADING ADVANCED SEARCH PAGE
63 This is fairly straightforward, and I won't go into detail ;-)
65 =head2 PERFORMING A SEARCH
67 If we're performing a search, this script performs three primary
72 =item 1. builds query strings (yes, plural)
74 =item 2. perform the search and return the results array
76 =item 3. build the HTML for output to the template
80 There are several additional secondary functions performed that I will
83 =head3 1. Building Query Strings
85 There are several types of queries needed in the process of search and retrieve:
89 =item 1 $query - the fully-built query passed to zebra
91 This is the most complex query that needs to be built. The original design goal
92 was to use a custom CCL2PQF query parser to translate an incoming CCL query into
93 a multi-leaf query to pass to Zebra. It needs to be multi-leaf to allow field
94 weighting, koha-specific relevance ranking, and stemming. When I have a chance
95 I'll try to flesh out this section to better explain.
97 This query incorporates query profiles that aren't compatible with most non-Zebra
98 Z39.50 targets to acomplish the field weighting and relevance ranking.
100 =item 2 $simple_query - a simple query that doesn't contain the field weighting,
101 stemming, etc., suitable to pass off to other search targets
103 This query is just the user's query expressed in CCL CQL, or PQF for passing to a
104 non-zebra Z39.50 target (one that doesn't support the extended profile that Zebra does).
106 =item 3 $query_cgi - passed to the template / saved for future refinements of
109 This is a simple string that completely expresses the query as a CGI string that
110 can be used for future refinements of the query or as a part of a history feature.
112 =item 4 $query_desc - Human search description - what the user sees in search
115 This is a simple string that is human readable. It will contain '=', ',', etc.
119 =head3 2. Perform the Search
121 This section takes the query strings and performs searches on the named servers,
122 including the Koha Zebra server, stores the results in a deeply nested object,
123 builds 'faceted results', and returns these objects.
127 The final major section of this script takes the objects collected thusfar and
128 builds the HTML for output to the template and user.
130 =head3 Additional Notes
136 use strict; # always use
138 ## STEP 1. Load things that are used in both search page and
139 # results page and decide which template to load, operations
147 use C4::Languages qw(getAllLanguages);
149 use POSIX qw(ceil floor);
150 use C4::Branch; # GetBranches
152 # create a new CGI object
153 # FIXME: no_undef_params needs to be tested
154 use CGI qw('-no_undef_params');
157 my ($template,$borrowernumber,$cookie);
159 # decide which template to use
162 my @params = $cgi->param("limit");
163 if ((@params>=1) || ($cgi->param("q")) || ($cgi->param('multibranchlimit')) || ($cgi->param('limit-yr')) ) {
164 $template_name = 'catalogue/results.tmpl';
167 $template_name = 'catalogue/advsearch.tmpl';
168 $template_type = 'advsearch';
171 ($template, $borrowernumber, $cookie) = get_template_and_user({
172 template_name => $template_name,
175 authnotrequired => 0,
176 flagsrequired => { catalogue => 1 },
179 if (C4::Context->preference("marcflavour") eq "UNIMARC" ) {
180 $template->param('UNIMARC' => 1);
184 # Deprecated, but preserved because it's interesting :-)
185 # The same thing can be accomplished with mod_rewrite in
189 #my $uri = $cgi->url(-base => 1);
190 #my $relative_url = $cgi->url(-relative=>1);
191 #$uri.="/".$relative_url."?";
193 #my @cgi_params_list = $cgi->param();
194 #my $url_params = $cgi->Vars;
196 #for my $each_param_set (@cgi_params_list) {
197 # $uri.= join "", map "\&$each_param_set=".$_, split("\0",$url_params->{$each_param_set}) if $url_params->{$each_param_set};
199 #warn "New URI:$uri";
200 # Only re-write a URI if there are params or if it already hasn't been re-written
201 #unless (($cgi->param('r')) || (!$cgi->param()) ) {
202 # print $cgi->redirect( -uri=>$uri."&r=1",
203 # -cookie => $cookie);
208 my $branches = GetBranches();
211 for my $branch_hash (sort { $branches->{$a}->{branchname} cmp $branches->{$b}->{branchname} } keys %$branches) {
212 push @branch_loop, {value => "$branch_hash" , branchname => $branches->{$branch_hash}->{'branchname'}, };
215 my $categories = GetBranchCategories(undef,'searchdomain');
217 $template->param(branchloop => \@branch_loop, searchdomainloop => $categories);
219 # load the Type stuff
220 # load the Type stuff
221 my $itemtypes = GetItemTypes;
225 my $imgdir = getitemtypeimagesrc('intranet');
226 my $advanced_search_types = C4::Context->preference("AdvancedSearchTypes");
228 if (!$advanced_search_types or $advanced_search_types eq 'itemtypes') { foreach my $thisitemtype ( sort {$itemtypes->{$a}->{'description'} cmp $itemtypes->{$b}->{'description'} } keys %$itemtypes ) {
229 my %row =( number=>$cnt++,
230 imageurl=> $itemtypes->{$thisitemtype}->{'imageurl'}?($imgdir."/".$itemtypes->{$thisitemtype}->{'imageurl'}):"",
232 code => $thisitemtype,
233 selected => $selected,
234 description => $itemtypes->{$thisitemtype}->{'description'},
237 $selected = 0 if ($selected) ;
238 push @itemtypesloop, \%row;
240 $template->param(itemtypeloop => \@itemtypesloop);
242 my $advsearchtypes = GetAuthorisedValues($advanced_search_types);
243 for my $thisitemtype (@$advsearchtypes) {
246 imageurl=> $imgdir."/".$thisitemtype->{'imageurl'},
247 ccl => $advanced_search_types,
248 code => $thisitemtype->{authorised_value},
249 selected => $selected,
250 description => $thisitemtype->{'lib'},
253 push @itemtypesloop, \%row;
255 $template->param(itemtypeloop => \@itemtypesloop);
258 # The following should only be loaded if we're bringing up the advanced search template
259 if ( $template_type eq 'advsearch' ) {
261 # load the servers (used for searching -- to do federated searching, etc.)
262 my $primary_servers_loop;# = displayPrimaryServers();
263 $template->param(outer_servers_loop => $primary_servers_loop,);
265 my $secondary_servers_loop;# = displaySecondaryServers();
266 $template->param(outer_sup_servers_loop => $secondary_servers_loop,);
268 # determine what to display next to the search boxes (ie, boolean option
269 # shouldn't appear on the first one, scan indexes should, adding a new
270 # box should only appear on the last, etc.
271 my @search_boxes_array;
272 my $search_boxes_count = C4::Context->preference("OPACAdvSearchInputCount") | 3; # FIXME: should be a syspref
273 for (my $i=1;$i<=$search_boxes_count;$i++) {
274 # if it's the first one, don't display boolean option, but show scan indexes
276 push @search_boxes_array,
282 # if it's the last one, show the 'add field' box
283 elsif ($i==$search_boxes_count) {
284 push @search_boxes_array,
291 push @search_boxes_array,
298 $template->param(uc(C4::Context->preference("marcflavour")) => 1,
299 search_boxes_loop => \@search_boxes_array);
301 # load the language limits (for search)
302 my $languages_limit_loop = getAllLanguages();
303 $template->param(search_languages_loop => $languages_limit_loop,);
305 # use the global setting by default
306 if ( C4::Context->preference("expandedSearchOption") == 1) {
307 $template->param( expanded_options => C4::Context->preference("expandedSearchOption") );
309 # but let the user override it
310 if ( ($cgi->param('expanded_options') == 0) || ($cgi->param('expanded_options') == 1 ) ) {
311 $template->param( expanded_options => $cgi->param('expanded_options'));
314 output_html_with_http_headers $cgi, $cookie, $template->output;
318 ### OK, if we're this far, we're performing a search, not just loading the advanced search page
320 # Fetch the paramater list as a hash in scalar context:
321 # * returns paramater list as tied hash ref
322 # * we can edit the values by changing the key
323 # * multivalued CGI paramaters are returned as a packaged string separated by "\0" (null)
324 my $params = $cgi->Vars;
326 # Params that can have more than one value
327 # sort by is used to sort the query
328 # in theory can have more than one but generally there's just one
330 my $default_sort_by = C4::Context->preference('defaultSortField')."_".C4::Context->preference('defaultSortOrder')
331 if (C4::Context->preference('defaultSortField') && C4::Context->preference('defaultSortOrder'));
333 @sort_by = split("\0",$params->{'sort_by'}) if $params->{'sort_by'};
334 $sort_by[0] = $default_sort_by unless $sort_by[0];
335 foreach my $sort (@sort_by) {
336 $template->param($sort => 1);
338 $template->param('sort_by' => $sort_by[0]);
340 # Use the servers defined, or just search our local catalog(default)
342 @servers = split("\0",$params->{'server'}) if $params->{'server'};
344 #FIXME: this should be handled using Context.pm
345 @servers = ("biblioserver");
346 # @servers = C4::Context->config("biblioserver");
348 # operators include boolean and proximity operators and are used
349 # to evaluate multiple operands
351 @operators = split("\0",$params->{'op'}) if $params->{'op'};
353 # indexes are query qualifiers, like 'title', 'author', etc. They
354 # can be single or multiple parameters separated by comma: kw,right-Truncation
356 @indexes = split("\0",$params->{'idx'});
358 # an operand can be a single term, a phrase, or a complete ccl query
360 @operands = split("\0",$params->{'q'}) if $params->{'q'};
362 # limits are use to limit to results to a pre-defined category such as branch or language
364 @limits = split("\0",$params->{'limit'}) if $params->{'limit'};
366 if($params->{'multibranchlimit'}) {
367 push @limits, join(" or ", map { "branch: $_ "} @{GetBranchesInCategory($params->{'multibranchlimit'})}) ;
371 foreach my $limit(@limits) {
372 if ($limit =~/available/) {
376 $template->param(available => $available);
378 # append year limits if they exist
381 if ($params->{'limit-yr'}) {
382 if ($params->{'limit-yr'} =~ /\d{4}-\d{4}/) {
383 my ($yr1,$yr2) = split(/-/, $params->{'limit-yr'});
384 $limit_yr = "yr,st-numeric,ge=$yr1 and yr,st-numeric,le=$yr2";
385 $limit_yr_value = "$yr1-$yr2";
387 elsif ($params->{'limit-yr'} =~ /\d{4}/) {
388 $limit_yr = "yr,st-numeric=$params->{'limit-yr'}";
389 $limit_yr_value = $params->{'limit-yr'};
391 push @limits,$limit_yr;
392 #FIXME: Should return a error to the user, incorect date format specified
395 # Params that can only have one value
396 my $scan = $params->{'scan'};
397 my $count = C4::Context->preference('numSearchResults') || 20;
398 my $results_per_page = $params->{'count'} || $count;
399 my $offset = $params->{'offset'} || 0;
400 my $page = $cgi->param('page') || 1;
401 #my $offset = ($page-1)*$results_per_page;
403 my $expanded_facet = $params->{'expand'};
405 # Define some global variables
406 my ( $error,$query,$simple_query,$query_cgi,$query_desc,$limit,$limit_cgi,$limit_desc,$stopwords_removed,$query_type);
410 ## I. BUILD THE QUERY
411 ( $error,$query,$simple_query,$query_cgi,$query_desc,$limit,$limit_cgi,$limit_desc,$stopwords_removed,$query_type) = buildQuery(\@operators,\@operands,\@indexes,\@limits,\@sort_by,$scan);
413 ## parse the query_cgi string and put it into a form suitable for <input>s
415 for my $this_cgi ( split('&',$query_cgi) ) {
416 next unless $this_cgi;
417 $this_cgi =~ m/(.*=)(.*)/;
419 my $input_value = $2;
420 $input_name =~ s/=$//;
421 push @query_inputs, { input_name => $input_name, input_value => $input_value };
423 $template->param ( QUERY_INPUTS => \@query_inputs );
425 ## parse the limit_cgi string and put it into a form suitable for <input>s
427 for my $this_cgi ( split('&',$limit_cgi) ) {
428 next unless $this_cgi;
429 # handle special case limit-yr
430 if ($this_cgi =~ /yr,st-numeric/) {
431 push @limit_inputs, { input_name => 'limit-yr', input_value => $limit_yr_value };
434 $this_cgi =~ m/(.*=)(.*)/;
436 my $input_value = $2;
437 $input_name =~ s/=$//;
438 push @limit_inputs, { input_name => $input_name, input_value => $input_value };
440 $template->param ( LIMIT_INPUTS => \@limit_inputs );
442 ## II. DO THE SEARCH AND GET THE RESULTS
443 my $total; # the total results for the whole set
444 my $facets; # this object stores the faceted results that display on the left-hand of the results page
448 if (C4::Context->preference('NoZebra')) {
449 $query=~s/yr(:|=)\s*([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
450 $simple_query=~s/yr\s*(:|=)([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
453 ($error, $results_hashref, $facets) = NZgetRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
457 ($error, $results_hashref, $facets) = getRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
461 $template->param(query_error => $error.$@);
463 output_html_with_http_headers $cgi, $cookie, $template->output;
467 # FIXME: This belongs in tools/ not in the primary search results page
468 my $op=$cgi->param("operation");
469 if ($op eq "bulkedit"){
470 my ($countchanged,$listunchanged)=
471 ModBiblios($results_hashref->{'biblioserver'}->{"RECORDS"},
472 $params->{"tagsubfield"},
473 $params->{"inputvalue"},
474 $params->{"targetvalue"},
477 $template->param(bulkeditresults=>1,
478 tagsubfield=>$params->{"tagsubfield"},
479 inputvalue=>$params->{"inputvalue"},
480 targetvalue=>$params->{"targetvalue"},
481 countchanged=>$countchanged,
482 countunchanged=>scalar(@$listunchanged),
483 listunchanged=>$listunchanged);
485 if (C4::Context->userenv->{'flags'}==1 ||(C4::Context->userenv->{'flags'} & ( 2**9 ) )){
486 #Edit Catalogue Permissions
487 my $editable_subfields = GetManagedTagSubfields();
488 # change '--' to '—' to avoid escaping issues
489 for (my $i = 0; $i <= $#{$editable_subfields}; $i++) {
490 $editable_subfields->[$i]->{subfielddesc} =~ s/--/—/g;
491 $editable_subfields->[$i]->{tagdesc} =~ s/--/—/g;
493 $template->param(bulkedit => 1);
494 $template->param(tagsubfields=>$editable_subfields);
498 # At this point, each server has given us a result set
499 # now we build that set for template display
500 my @sup_results_array;
501 for (my $i=0;$i<@servers;$i++) {
502 my $server = $servers[$i];
503 if ($server =~/biblioserver/) { # this is the local bibliographic server
504 $hits = $results_hashref->{$server}->{"hits"};
505 my $page = $cgi->param('page') || 0;
506 my @newresults = searchResults( $query_desc,$hits,$results_per_page,$offset,@{$results_hashref->{$server}->{"RECORDS"}});
507 $total = $total + $results_hashref->{$server}->{"hits"};
508 ## If there's just one result, redirect to the detail page
510 my $biblionumber=@newresults[0]->{biblionumber};
511 if (C4::Context->preference('IntranetBiblioDefaultView') eq 'isbd') {
512 print $cgi->redirect("/cgi-bin/koha/catalogue/ISBDdetail.pl?biblionumber=$biblionumber");
513 } elsif (C4::Context->preference('IntranetBiblioDefaultView') eq 'marc') {
514 print $cgi->redirect("/cgi-bin/koha/catalogue/MARCdetail.pl?biblionumber=$biblionumber");
516 print $cgi->redirect("/cgi-bin/koha/catalogue/detail.pl?biblionumber=$biblionumber");
521 $template->param(total => $hits);
522 my $limit_cgi_not_availablity = $limit_cgi;
523 $limit_cgi_not_availablity =~ s/&limit=available//g;
524 $template->param(limit_cgi_not_availablity => $limit_cgi_not_availablity);
525 $template->param(limit_cgi => $limit_cgi);
526 $template->param(query_cgi => $query_cgi);
527 $template->param(query_desc => $query_desc);
528 $template->param(limit_desc => $limit_desc);
529 if ($query_desc || $limit_desc) {
530 $template->param(searchdesc => 1);
532 $template->param(stopwords_removed => "@$stopwords_removed") if $stopwords_removed;
533 $template->param(results_per_page => $results_per_page);
534 $template->param(SEARCH_RESULTS => \@newresults);
536 ## FIXME: add a global function for this, it's better than the current global one
537 ## Build the page numbers on the bottom of the page
539 # total number of pages there will be
540 my $pages = ceil($hits / $results_per_page);
541 # default page number
542 my $current_page_number = 1;
543 $current_page_number = ($offset / $results_per_page + 1) if $offset;
544 my $previous_page_offset = $offset - $results_per_page unless ($offset - $results_per_page <0);
545 my $next_page_offset = $offset + $results_per_page;
546 # If we're within the first 10 pages, keep it simple
547 #warn "current page:".$current_page_number;
548 if ($current_page_number < 10) {
549 # just show the first 10 pages
550 # Loop through the pages
551 my $pages_to_show = 10;
552 $pages_to_show = $pages if $pages<10;
553 for (my $i=1; $i<=$pages_to_show;$i++) {
554 # the offset for this page
555 my $this_offset = (($i*$results_per_page)-$results_per_page);
556 # the page number for this page
557 my $this_page_number = $i;
558 # it should only be highlighted if it's the current page
559 my $highlight = 1 if ($this_page_number == $current_page_number);
560 # put it in the array
561 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
566 # now, show twenty pages, with the current one smack in the middle
568 for (my $i=$current_page_number; $i<=($current_page_number + 20 );$i++) {
569 my $this_offset = ((($i-9)*$results_per_page)-$results_per_page);
570 my $this_page_number = $i-9;
571 my $highlight = 1 if ($this_page_number == $current_page_number);
572 if ($this_page_number <= $pages) {
573 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
578 # FIXME: no previous_page_offset when pages < 2
579 $template->param( PAGE_NUMBERS => \@page_numbers,
580 previous_page_offset => $previous_page_offset) unless $pages < 2;
581 $template->param( next_page_offset => $next_page_offset) unless $pages eq $current_page_number;
585 $template->param(searchdesc => 1,query_desc => $query_desc,limit_desc => $limit_desc);
587 } # end of the if local
589 # asynchronously search the authority server
590 elsif ($server =~/authorityserver/) { # this is the local authority server
591 my @inner_sup_results_array;
592 for my $sup_record ( @{$results_hashref->{$server}->{"RECORDS"}} ) {
593 my $marc_record_object = MARC::Record->new_from_usmarc($sup_record);
594 # warn "Authority Found: ".$marc_record_object->as_formatted();
595 push @inner_sup_results_array, {
596 'title' => $marc_record_object->field(100)->subfield('a'),
597 'link' => "&idx=an&q=".$marc_record_object->field('001')->as_string(),
600 my $servername = $server;
601 push @sup_results_array, { servername => $servername,
602 inner_sup_results_loop => \@inner_sup_results_array} if @inner_sup_results_array;
604 # FIXME: can add support for other targets as needed here
605 $template->param( outer_sup_results_loop => \@sup_results_array);
606 } #/end of the for loop
607 #$template->param(FEDERATED_RESULTS => \@results_array);
611 #classlist => $classlist,
614 facets_loop => $facets,
616 search_error => $error,
619 if ($query_desc || $limit_desc) {
620 $template->param(searchdesc => 1);
623 ## Now let's find out if we have any supplemental data to show the user
624 # and in the meantime, save the current query for statistical purposes, etc.
625 my $koha_spsuggest; # a flag to tell if we've got suggestions coming from Koha
626 my @koha_spsuggest; # place we store the suggestions to be returned to the template as LOOP
627 my $phrases = $query_desc;
630 if ( C4::Context->preference("kohaspsuggest") ) {
631 my ($suggest_host, $suggest_dbname, $suggest_user, $suggest_pwd) = split(':', C4::Context->preference("kohaspsuggest"));
633 my $koha_spsuggest_dbh;
634 # FIXME: this needs to be moved to Context.pm
636 $koha_spsuggest_dbh=DBI->connect("DBI:mysql:$suggest_dbname:$suggest_host","$suggest_user","$suggest_pwd");
639 warn "can't connect to spsuggest db";
642 my $koha_spsuggest_insert = "INSERT INTO phrase_log(phr_phrase,phr_resultcount,phr_ip) VALUES(?,?,?)";
643 my $koha_spsuggest_query = "SELECT display FROM distincts WHERE strcmp(soundex(suggestion), soundex(?)) = 0 order by soundex(suggestion) limit 0,5";
644 my $koha_spsuggest_sth = $koha_spsuggest_dbh->prepare($koha_spsuggest_query);
645 $koha_spsuggest_sth->execute($phrases);
646 while (my $spsuggestion = $koha_spsuggest_sth->fetchrow_array) {
647 $spsuggestion =~ s/(:|\/)//g;
649 $line{spsuggestion} = $spsuggestion;
650 push @koha_spsuggest,\%line;
654 # Now save the current query
655 $koha_spsuggest_sth=$koha_spsuggest_dbh->prepare($koha_spsuggest_insert);
656 #$koha_spsuggest_sth->execute($phrases,$results_per_page,$ipaddress);
657 $koha_spsuggest_sth->finish;
659 $template->param( koha_spsuggest => $koha_spsuggest ) unless $hits;
660 $template->param( SPELL_SUGGEST => \@koha_spsuggest,
665 warn "Kohaspsuggest failure:".$@;
669 # VI. BUILD THE TEMPLATE
670 output_html_with_http_headers $cgi, $cookie, $template->output;