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 $query_desc - Human search description - what the user sees in search
115 This is a simple string that is human readable. It will contain '=', ',', etc.
119 =head3 2. Perform the Search
121 This section takes the query strings and performs searches on the named servers,
122 including the Koha Zebra server, stores the results in a deeply nested object,
123 builds 'faceted results', and returns these objects.
127 The final major section of this script takes the objects collected thusfar and
128 builds the HTML for output to the template and user.
130 =head3 Additional Notes
136 use strict; # always use
138 ## STEP 1. Load things that are used in both search page and
139 # results page and decide which template to load, operations
147 use C4::Languages; # getAllLanguages
149 use POSIX qw(ceil floor);
150 use C4::Branch; # GetBranches
152 # create a new CGI object
153 # FIXME: no_undef_params needs to be tested
154 use CGI qw('-no_undef_params');
157 my ($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 $branch_hash (sort keys %$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);
220 my $itemtypes = GetItemTypes;
224 my $imgdir = getitemtypeimagesrc();
225 foreach my $thisitemtype ( sort {$itemtypes->{$a}->{'description'} cmp $itemtypes->{$b}->{'description'} } keys %$itemtypes ) {
226 my %row =( number=>$cnt++,
227 imageurl=> $itemtypes->{$thisitemtype}->{'imageurl'}?($imgdir."/".$itemtypes->{$thisitemtype}->{'imageurl'}):"",
228 code => $thisitemtype,
229 selected => $selected,
230 description => $itemtypes->{$thisitemtype}->{'description'},
233 $selected = 0 if ($selected) ;
234 push @itemtypesloop, \%row;
236 $template->param(itemtypeloop => \@itemtypesloop);
239 # my ($ccodecount,@ccode_loop) = GetCcodes();
240 # $template->param(ccodeloop=>\@ccode_loop,);
242 # load the languages ( for switching from one template to another )
243 $template->param(languages_loop => getTranslatedLanguages('intranet','prog'));
245 # The following should only be loaded if we're bringing up the advanced search template
246 if ( $template_type eq 'advsearch' ) {
248 # load the servers (used for searching -- to do federated searching, etc.)
249 my $primary_servers_loop;# = displayPrimaryServers();
250 $template->param(outer_servers_loop => $primary_servers_loop,);
252 my $secondary_servers_loop;# = displaySecondaryServers();
253 $template->param(outer_sup_servers_loop => $secondary_servers_loop,);
255 # determine what to display next to the search boxes (ie, boolean option
256 # shouldn't appear on the first one, scan indexes should, adding a new
257 # box should only appear on the last, etc.
258 my @search_boxes_array;
259 my $search_boxes_count = C4::Context->preference("OPACAdvSearchInputCount") | 3; # FIXME: should be a syspref
260 for (my $i=1;$i<=$search_boxes_count;$i++) {
261 # if it's the first one, don't display boolean option, but show scan indexes
263 push @search_boxes_array,
269 # if it's the last one, show the 'add field' box
270 elsif ($i==$search_boxes_count) {
271 push @search_boxes_array,
278 push @search_boxes_array,
285 $template->param(uc(C4::Context->preference("marcflavour")) => 1,
286 search_boxes_loop => \@search_boxes_array);
288 # load the language limits (for search)
289 my $languages_limit_loop = getAllLanguages();
290 $template->param(search_languages_loop => $languages_limit_loop,);
292 # use the global setting by default
293 if ( C4::Context->preference("expandedSearchOption") == 1) {
294 $template->param( expanded_options => C4::Context->preference("expandedSearchOption") );
296 # but let the user override it
297 if ( ($cgi->param('expanded_options') == 0) || ($cgi->param('expanded_options') == 1 ) ) {
298 $template->param( expanded_options => $cgi->param('expanded_options'));
301 output_html_with_http_headers $cgi, $cookie, $template->output;
305 ### OK, if we're this far, we're performing a search, not just loading the advanced search page
307 # Fetch the paramater list as a hash in scalar context:
308 # * returns paramater list as tied hash ref
309 # * we can edit the values by changing the key
310 # * multivalued CGI paramaters are returned as a packaged string separated by "\0" (null)
311 my $params = $cgi->Vars;
313 # Params that can have more than one value
314 # sort by is used to sort the query
315 # in theory can have more than one but generally there's just one
317 my $default_sort_by = C4::Context->preference('defaultSortField')."_".C4::Context->preference('defaultSortOrder')
318 if (C4::Context->preference('defaultSortField') && C4::Context->preference('defaultSortOrder'));
320 @sort_by = split("\0",$params->{'sort_by'}) if $params->{'sort_by'};
321 $sort_by[0] = $default_sort_by unless $sort_by[0];
322 foreach my $sort (@sort_by) {
323 $template->param($sort => 1);
325 $template->param('sort_by' => $sort_by[0]);
327 # Use the servers defined, or just search our local catalog(default)
329 @servers = split("\0",$params->{'server'}) if $params->{'server'};
331 #FIXME: this should be handled using Context.pm
332 @servers = ("biblioserver");
333 # @servers = C4::Context->config("biblioserver");
335 # operators include boolean and proximity operators and are used
336 # to evaluate multiple operands
338 @operators = split("\0",$params->{'op'}) if $params->{'op'};
340 # indexes are query qualifiers, like 'title', 'author', etc. They
341 # can be single or multiple parameters separated by comma: kw,right-Truncation
343 @indexes = split("\0",$params->{'idx'});
345 # an operand can be a single term, a phrase, or a complete ccl query
347 @operands = split("\0",$params->{'q'}) if $params->{'q'};
349 # limits are use to limit to results to a pre-defined category such as branch or language
351 @limits = split("\0",$params->{'limit'}) if $params->{'limit'};
353 if($params->{'multibranchlimit'}) {
354 push @limits, join(" or ", map { "branch: $_ "} @{GetBranchesInCategory($params->{'multibranchlimit'})}) ;
358 foreach my $limit(@limits) {
359 if ($limit =~/available/) {
363 $template->param(available => $available);
365 # append year limits if they exist
368 if ($params->{'limit-yr'}) {
369 if ($params->{'limit-yr'} =~ /\d{4}-\d{4}/) {
370 my ($yr1,$yr2) = split(/-/, $params->{'limit-yr'});
371 $limit_yr = "yr,st-numeric,ge=$yr1 and yr,st-numeric,le=$yr2";
372 $limit_yr_value = "$yr1-$yr2";
374 elsif ($params->{'limit-yr'} =~ /\d{4}/) {
375 $limit_yr = "yr,st-numeric=$params->{'limit-yr'}";
376 $limit_yr_value = $params->{'limit-yr'};
378 push @limits,$limit_yr;
379 #FIXME: Should return a error to the user, incorect date format specified
382 # Params that can only have one value
383 my $scan = $params->{'scan'};
384 my $count = C4::Context->preference('numSearchResults') || 20;
385 my $results_per_page = $params->{'count'} || $count;
386 my $offset = $params->{'offset'} || 0;
387 my $page = $cgi->param('page') || 1;
388 #my $offset = ($page-1)*$results_per_page;
390 my $expanded_facet = $params->{'expand'};
392 # Define some global variables
393 my ( $error,$query,$simple_query,$query_cgi,$query_desc,$limit,$limit_cgi,$limit_desc,$stopwords_removed,$query_type);
397 ## I. BUILD THE QUERY
398 ( $error,$query,$simple_query,$query_cgi,$query_desc,$limit,$limit_cgi,$limit_desc,$stopwords_removed,$query_type) = buildQuery(\@operators,\@operands,\@indexes,\@limits,\@sort_by,$scan);
400 ## parse the query_cgi string and put it into a form suitable for <input>s
402 for my $this_cgi ( split('&',$query_cgi) ) {
403 next unless $this_cgi;
404 $this_cgi =~ m/(.*=)(.*)/;
406 my $input_value = $2;
407 $input_name =~ s/=$//;
408 push @query_inputs, { input_name => $input_name, input_value => $input_value };
410 $template->param ( QUERY_INPUTS => \@query_inputs );
412 ## parse the limit_cgi string and put it into a form suitable for <input>s
414 for my $this_cgi ( split('&',$limit_cgi) ) {
415 next unless $this_cgi;
416 # handle special case limit-yr
417 if ($this_cgi =~ /yr,st-numeric/) {
418 push @limit_inputs, { input_name => 'limit-yr', input_value => $limit_yr_value };
421 $this_cgi =~ m/(.*=)(.*)/;
423 my $input_value = $2;
424 $input_name =~ s/=$//;
425 push @limit_inputs, { input_name => $input_name, input_value => $input_value };
427 $template->param ( LIMIT_INPUTS => \@limit_inputs );
429 ## II. DO THE SEARCH AND GET THE RESULTS
430 my $total; # the total results for the whole set
431 my $facets; # this object stores the faceted results that display on the left-hand of the results page
435 if (C4::Context->preference('NoZebra')) {
436 $query=~s/yr(:|=)\s*([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
437 $simple_query=~s/yr\s*(:|=)([\d]{1,4})-([\d]{1,4})/(yr>=$2 and yr<=$3)/g;
440 ($error, $results_hashref, $facets) = NZgetRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
444 ($error, $results_hashref, $facets) = getRecords($query,$simple_query,\@sort_by,\@servers,$results_per_page,$offset,$expanded_facet,$branches,$query_type,$scan);
448 $template->param(query_error => $error.$@);
450 output_html_with_http_headers $cgi, $cookie, $template->output;
454 # FIXME: This belongs in tools/ not in the primary search results page
455 my $op=$cgi->param("operation");
456 if ($op eq "bulkedit"){
457 my ($countchanged,$listunchanged)=
458 ModBiblios($results_hashref->{'biblioserver'}->{"RECORDS"},
459 $params->{"tagsubfield"},
460 $params->{"inputvalue"},
461 $params->{"targetvalue"},
464 $template->param(bulkeditresults=>1,
465 tagsubfield=>$params->{"tagsubfield"},
466 inputvalue=>$params->{"inputvalue"},
467 targetvalue=>$params->{"targetvalue"},
468 countchanged=>$countchanged,
469 countunchanged=>scalar(@$listunchanged),
470 listunchanged=>$listunchanged);
472 if (C4::Context->userenv->{'flags'}==1 ||(C4::Context->userenv->{'flags'} & ( 2**9 ) )){
473 #Edit Catalogue Permissions
474 my $editable_subfields = GetManagedTagSubfields();
475 # change '--' to '—' to avoid escaping issues
476 for (my $i = 0; $i <= $#{$editable_subfields}; $i++) {
477 $editable_subfields->[$i]->{subfielddesc} =~ s/--/—/g;
478 $editable_subfields->[$i]->{tagdesc} =~ s/--/—/g;
480 $template->param(bulkedit => 1);
481 $template->param(tagsubfields=>$editable_subfields);
485 # At this point, each server has given us a result set
486 # now we build that set for template display
487 my @sup_results_array;
488 for (my $i=0;$i<@servers;$i++) {
489 my $server = $servers[$i];
490 if ($server =~/biblioserver/) { # this is the local bibliographic server
491 $hits = $results_hashref->{$server}->{"hits"};
492 my $page = $cgi->param('page') || 0;
493 my @newresults = searchResults( $query_desc,$hits,$results_per_page,$offset,@{$results_hashref->{$server}->{"RECORDS"}});
494 $total = $total + $results_hashref->{$server}->{"hits"};
496 $template->param(total => $hits);
497 my $limit_cgi_not_availablity = $limit_cgi;
498 $limit_cgi_not_availablity =~ s/&limit=available//g;
499 $template->param(limit_cgi_not_availablity => $limit_cgi_not_availablity);
500 $template->param(limit_cgi => $limit_cgi);
501 $template->param(query_cgi => $query_cgi);
502 $template->param(query_desc => $query_desc);
503 $template->param(limit_desc => $limit_desc);
504 if ($query_desc || $limit_desc) {
505 $template->param(searchdesc => 1);
507 $template->param(stopwords_removed => "@$stopwords_removed") if $stopwords_removed;
508 $template->param(results_per_page => $results_per_page);
509 $template->param(SEARCH_RESULTS => \@newresults);
511 ## FIXME: add a global function for this, it's better than the current global one
512 ## Build the page numbers on the bottom of the page
514 # total number of pages there will be
515 my $pages = ceil($hits / $results_per_page);
516 # default page number
517 my $current_page_number = 1;
518 $current_page_number = ($offset / $results_per_page + 1) if $offset;
519 my $previous_page_offset = $offset - $results_per_page unless ($offset - $results_per_page <0);
520 my $next_page_offset = $offset + $results_per_page;
521 # If we're within the first 10 pages, keep it simple
522 #warn "current page:".$current_page_number;
523 if ($current_page_number < 10) {
524 # just show the first 10 pages
525 # Loop through the pages
526 my $pages_to_show = 10;
527 $pages_to_show = $pages if $pages<10;
528 for (my $i=1; $i<=$pages_to_show;$i++) {
529 # the offset for this page
530 my $this_offset = (($i*$results_per_page)-$results_per_page);
531 # the page number for this page
532 my $this_page_number = $i;
533 # it should only be highlighted if it's the current page
534 my $highlight = 1 if ($this_page_number == $current_page_number);
535 # put it in the array
536 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
541 # now, show twenty pages, with the current one smack in the middle
543 for (my $i=$current_page_number; $i<=($current_page_number + 20 );$i++) {
544 my $this_offset = ((($i-9)*$results_per_page)-$results_per_page);
545 my $this_page_number = $i-9;
546 my $highlight = 1 if ($this_page_number == $current_page_number);
547 if ($this_page_number <= $pages) {
548 push @page_numbers, { offset => $this_offset, pg => $this_page_number, highlight => $highlight, sort_by => join " ",@sort_by };
553 # FIXME: no previous_page_offset when pages < 2
554 $template->param( PAGE_NUMBERS => \@page_numbers,
555 previous_page_offset => $previous_page_offset) unless $pages < 2;
556 $template->param( next_page_offset => $next_page_offset) unless $pages eq $current_page_number;
560 $template->param(searchdesc => 1,query_desc => $query_desc,limit_desc => $limit_desc);
562 } # end of the if local
564 # asynchronously search the authority server
565 elsif ($server =~/authorityserver/) { # this is the local authority server
566 my @inner_sup_results_array;
567 for my $sup_record ( @{$results_hashref->{$server}->{"RECORDS"}} ) {
568 my $marc_record_object = MARC::Record->new_from_usmarc($sup_record);
569 # warn "Authority Found: ".$marc_record_object->as_formatted();
570 push @inner_sup_results_array, {
571 'title' => $marc_record_object->field(100)->subfield('a'),
572 'link' => "&idx=an&q=".$marc_record_object->field('001')->as_string(),
575 my $servername = $server;
576 push @sup_results_array, { servername => $servername,
577 inner_sup_results_loop => \@inner_sup_results_array} if @inner_sup_results_array;
579 # FIXME: can add support for other targets as needed here
580 $template->param( outer_sup_results_loop => \@sup_results_array);
581 } #/end of the for loop
582 #$template->param(FEDERATED_RESULTS => \@results_array);
586 #classlist => $classlist,
589 facets_loop => $facets,
591 search_error => $error,
594 if ($query_desc || $limit_desc) {
595 $template->param(searchdesc => 1);
598 ## Now let's find out if we have any supplemental data to show the user
599 # and in the meantime, save the current query for statistical purposes, etc.
600 my $koha_spsuggest; # a flag to tell if we've got suggestions coming from Koha
601 my @koha_spsuggest; # place we store the suggestions to be returned to the template as LOOP
602 my $phrases = $query_desc;
605 if ( C4::Context->preference("kohaspsuggest") ) {
606 my ($suggest_host, $suggest_dbname, $suggest_user, $suggest_pwd) = split(':', C4::Context->preference("kohaspsuggest"));
608 my $koha_spsuggest_dbh;
609 # FIXME: this needs to be moved to Context.pm
611 $koha_spsuggest_dbh=DBI->connect("DBI:mysql:$suggest_dbname:$suggest_host","$suggest_user","$suggest_pwd");
614 warn "can't connect to spsuggest db";
617 my $koha_spsuggest_insert = "INSERT INTO phrase_log(phr_phrase,phr_resultcount,phr_ip) VALUES(?,?,?)";
618 my $koha_spsuggest_query = "SELECT display FROM distincts WHERE strcmp(soundex(suggestion), soundex(?)) = 0 order by soundex(suggestion) limit 0,5";
619 my $koha_spsuggest_sth = $koha_spsuggest_dbh->prepare($koha_spsuggest_query);
620 $koha_spsuggest_sth->execute($phrases);
621 while (my $spsuggestion = $koha_spsuggest_sth->fetchrow_array) {
622 $spsuggestion =~ s/(:|\/)//g;
624 $line{spsuggestion} = $spsuggestion;
625 push @koha_spsuggest,\%line;
629 # Now save the current query
630 $koha_spsuggest_sth=$koha_spsuggest_dbh->prepare($koha_spsuggest_insert);
631 #$koha_spsuggest_sth->execute($phrases,$results_per_page,$ipaddress);
632 $koha_spsuggest_sth->finish;
634 $template->param( koha_spsuggest => $koha_spsuggest ) unless $hits;
635 $template->param( SPELL_SUGGEST => \@koha_spsuggest,
640 warn "Kohaspsuggest failure:".$@;
644 # VI. BUILD THE TEMPLATE
645 output_html_with_http_headers $cgi, $cookie, $template->output;