5207699f98
Squashed patch incorporating all previous patches (there is no functional
change compared to the previous version of this patch, this patch merely
squashes the original patch and follow-up, and rebases on latest master).
=== TL;DR VERSION ===
*** Installation ***
1. Run installer/data/mysql/atomicupdate/bug_7284_authority_linking_pt1
and installer/data/mysql/atomicupdate/bug_7284_authority_linking_pt2
2. Make sure you copy the following files from kohaclone to koha-dev:
etc/zeradb/authorities/etc/bib1.att,
etc/zebradb/marc_defs/marc21/authorities/authority-koha-indexdefs.xml,
etc/zebradb/marc_defs/marc21/authorities/authority-zebra-indexdefs.xsl,
etc/zebradb/marc_defs/marc21/authorities/koha-indexdefs-to-zebra.xsl, and
etc/zebradb/marc_defs/unimarc/authorities/record.abs
3. Run misc/migration_tools/rebuild_zebra.pl -a -r
*** New sysprefs ***
* AutoCreateAuthorities
* CatalogModuleRelink
* LinkerModule
* LinkerOptions
* LinkerRelink
* LinkerKeepStale
*** Important notes ***
You must have rebuild_zebra processing the zebraqueue for bibs when testing this
patch.
=== DESCRIPTION ===
*** Cataloging module ***
* Added an additional box to the authority finder plugin for "Heading match,"
which consults not just the main entry but also See-from and See-also-from
headings.
* With this patch, the automatic authority linking will actually work properly
in the cataloging module. As Owen pointed out while testing the patch,
though, longtime users of Koha will not be expecting that. In keeping with
the principles of least surprise and maximum configurability, a new syspref,
CatalogModuleRelink makes it possible to disable authority relinking in the
cataloging module only (i.e. leaving it enabled for future runs of
link_bibs_to_authorities.pl). Note that though the default behavior matches
the current behavior of Koha, it does not match the intended behavior.
Libraries that want the intended behavior rather than the current behavior
will need to adjust the CatalogModuleRelink syspref.
*** misc/link_bibs_to_authorities.pl ***
Added the following options to the misc/link_bibs_to_authorities.pl script:
--auth-limit Only process those headings that match the authorities
matching the user-specified WHERE clause.
--bib-limit Only process those bib records that match the
user-specified WHERE clause.
--commit Commit the results to the database after every N records
are processed.
--link-report Display a report of all the headings that were processed.
Converted misc/link_bibs_to_authorities.pl to use POD.
Added a detailed report of headings that linked, did not link, and linked
in a "fuzzy" fashion (the exact semantics of fuzzy are up to the individual
linker modules) during the run.
*** C4::Linker ***
Implemented new C4::Linker functionality to make it possible to easily add
custom authority linker algorithms. Currently available linker options are:
* Default: retains the current behavior of only creating links when there is
an exact match to one and only one authority record; if the 'broader_headings'
option is enabled, it will try to link to headings to authority records for
broader headings by removing subfields from the end of the heading (NOTE:
test the results before enabling broader_headings in a production system
because its usefulness is very much dependent on individual sites' authority
files)
* First Match: based on Default, creates a link to the *first* authority
record that matches a given heading, even if there is more than one
authority record that matches
* Last Match: based on Default, creates a link to the *last* authority
record that matches a given heading, even if there is more than one record
that matches
The API for linker modules is very simple. All modules should implement the
following two functions:
<get_link ($field)> - return the authid for the authority that should be
linked to the provided MARC::Field object, and a boolean to indicate whether
the match is "fuzzy" (the semantics of "fuzzy" are up to the individual plugin).
In order to handle authority limits, get_link should always end with:
return $self->SUPER::_handle_auth_limit($authid), $fuzzy;
<flip_heading ($field)> - return a MARC::Field object with the heading flipped
to the preferred form. At present this routine is not used, and can be a stub.
Made the linking functionality use the SearchAuthorities in C4::AuthoritiesMarc
rather than SimpleSearch in C4::Search. Once C4::Search has been refactored,
SearchAuthorities should be rewritten to simply call into C4::Search. However,
at this time C4::Search cannot handle authority searching. Also fixed numerous
performance issues in SearchAuthorities and the Linker script:
* Correctly destroy ZOOM recordsets in SearchAuthorities when finished. If left
undestroyed, efficiency appears to approach O(log n^n)
* Add an optional $skipmetadata flag to SearchAuthorities that can be used to
avoid additional calls into Zebra when all that is wanted are authority
records and not statistics about their use
*** New sysprefs ***
* AutoCreateAuthorities - When this and BiblioAddsAuthorities are both turned
on, automatically create authority records for headings that don't have
any authority link when cataloging. When BiblioAddsAuthorities is on and
AutoCreateAuthorities is turned off, do not automatically generate authority
records, but allow the user to enter headings that don't match an existing
authority. When BiblioAddsAuthorities is off, this has no effect.
* CatalogModuleRelink - when turned on, the automatic linker will relink
headings when a record is saved in the cataloging module when LinkerRelink
is turned on, even if the headings were manually linked to a different
authority by the cataloger. When turned off (the default), the automatic
linker will not relink any headings that have already been linked when a
record is saved.
* LinkerModule - Chooses which linker module to use for matching headings
(current options are as described above in the section on linker options:
"Default," "FirstMatch," and "LastMatch")
* LinkerOptions - A pipe-separated list of options to set for the authority
linker (at the moment, the only option available is "broader_headings," which
is described below)
* LinkerRelink - When turned on, the linker will confirm the links for headings
that have previously been linked to an authority record when it runs. When
turned off, any heading with an existing link will be ignored.
* LinkerKeepStale - When turned on, the linker will never *delete* a link to an
authority record, though, depending on the value of LinkerRelink, it may
change the link.
*** Other changes ***
* Cleaned up authorities code by removing unused functions and adding
unimplemented functions and added some unit tests.
* This patch also modifies the authority indexing to remove trailing punctuation
from Match indexes.
* Replace the old BiblioAddAuthorities subroutines with calls into the new
C4::Linker routines.
* Add a simple implementation for C4::Heading::UNIMARC. (With thanks to F.
Demians, 2011.01.09) Correct C4::Heading::UNIMARC class loading. Create
biblio tag to authority types data structure at initialization rather than
querying DB.
* Ran perltidy on all changed code.
*** Linker Options ***
Enter "broader_headings" in LinkerOptions. With this option, the linker will
try to match the following heading as follows:
=600 10$aCamins-Esakov, Jared$xCoin collections$vCatalogs$vEarly works to
1800.
First: Camins-Esakov, Jared--Coin collections--Catalogs--Early works to 1800
Next: Camins-Esakov, Jared--Coin collections--Catalogs
Next: Camins-Esakov, Jared--Coin collections
Next: Camins-Esakov, Jared (matches! if a previous attempt had matched, it
would not have tried this)
This is probably relevant only to MARC21 and LCSH, but could potentially be of
great use to libraries that make heavy use of floating subdivisions.
=== TESTING PLAN ===
Note: all of these tests require that you have some authority records,
preferably for headings that actually appear in your bibliographic data. At
least one authority record must contain a "see from" reference (remember which
one contains this, as you'll need it for some of the tests). The number shown
in the "Used in" column in the authority module is populated using Zebra
searches of the bibliographic database, so you *must* have
rebuild_zebra.pl -b -z [-x] running in cron, or manually run it after running
the linker.
*** Testing the Heading match in the cataloging plugin ***
1. Create a new record, and open the cataloging plugin for an
authority-controlled field.
2. Search for an authority by entering the "see from" term in the Heading Match
box
3. Confirm that the appropriate heading shows up
4. Search for an authority by entering the preferred heading into the Main
entry or Main entry ($a only) box (i.e., repeat the procedure you usually
use for cataloging, whatever that may be)
5. Confirm that the appropriate heading shows up
*** Testing the cataloging interface ***
6. Turn off BiblioAddsAuthorities
7. Confirm that you cannot enter text directly in an authority-controlled field
8. Confirm that if you search for a heading using the authority control plugin
the heading is inserted (note, however, that this patch does not AND IS NOT
INTENDED TO fix the bugs in the authority plugin with duplicate subfields;
those are wholly out of scope- this check is for regressions)
9. Turn on BiblioAddsAuthorities and AutoCreateAuthorities
10. Confirm that you can enter text directly into an authority-controlled field,
and if you enter a heading that doesn't currently have an authority record,
an authority record stub is automatically created, and the heading you
entered linked
11. Confirm that if you enter a heading with only a subfield $a that fully
*matches* an existing heading (i.e. the existing heading has only
subfield $a populated), the authid for that heading is inserted into
subfield $9
12. Confirm that if you enter a heading with multiple subfields that *matches*
an existing heading, the authid for that heading is inserted into
subfield $9
13. Turn on BiblioAddsAuthorities and turn off AutoCreateAuthorities
14. Confirm that you can enter text directly into an authority-controlled field,
and if you enter a heading that doesn't currently have an authority record,
an authority record stub is *not* created
15. Confirm that if you enter a heading with only a subfield $a that *matches*
an existing heading, the authid for that heading is inserted into
subfield $9
16. Confirm that if you enter a heading with multiple subfields that *matches*
an existing heading, the authid for that heading is inserted into
subfield $9
17. Create a record and link an authority record to an authorized field using
the authority plugin.
18. Save the record. Ensure that the heading is linked to the appropriate
authority.
19. Open the record. Change the heading manually to something else, leaving
the link. Save the record.
20. Ensure that the heading remains linked to that same authority.
21. Change CatalogModuleRelink to "on."
22. Open the record. Use the authority plugin to link that heading to the
same authority record you did earlier.
23. Save the record. Ensure that the heading is linked to the appropriate
authority.
24. Open the record. Change the heading manually to something else, leaving
the link. Save the record.
25. Ensure that the heading is no longer linked to the old authority record.
*** Testing link_bibs_to_authorities.pl ***
26. Set LinkerModule to "Default," turn on LinkerRelink and
BiblioAddsAuthorities, and turn AutoCreateAuthorities and
LinkerKeepStale off
27. Edit one bib record so that an authority controlled field that has already
been linked (i.e. has data in $9) has a heading that does not match any
authority record in your database
28. Run misc/link_bibs_to_authorities.pl --link-report --verbose --test (you may
want to pipe the output into less or a file, as the result is quite a lot of
information)
29. Look over the report to see if the headings that you have authority records
for report being matched, that the heading you modified in step 2 is
reported as "unlinked," and confirm that no changes were actually made to
the database (to check this, look at the bib record you edited earlier, and
check that the authid in the field you edited hasn't changed)
30. Run misc/link_bibs_to_authorities.pl --link-report --verbose (you may want
to pipe the output into less or a file, as the result is quite a lot of
information)
31. Check that the heading you modified has been unlinked
32. Change the modified heading back to whatever it was, but don't use the
authority control plugin to populate $9
33. Run misc/link_bibs_to_authorities.pl --link-report --verbose
--bib-limit="biblionumber=${BIB}" (replacing ${BIB} with the biblionumber
of the record you've been editing)
34. Confirm that the heading has been linked to the correct authority record
35. Turn LinkerKeepStale on
36. Change that heading to something else
37. Run misc/link_bibs_to_authorities.pl --link-report --verbose
--bib-limit="biblionumber=${BIB}" (replacing ${BIB} with the biblionumber
of the record you've been editing)
38. Confirm that the $9 has not changed
39. Turn LinkerKeepStale off
40. Create two authorities with the same heading
41. Run misc/migration_tools/rebuild_zebra.pl -a -z
42. Enter that heading into the bibliographic record you are working with
43. Run misc/link_bibs_to_authorities.pl --link-report --verbose
--bib-limit="biblionumber=${BIB}" (replacing ${BIB} with the biblionumber
of the record you've been editing)
44. Confirm that the heading has not been linked
45. Change LinkerModule to "FirstMatch"
46. Run misc/link_bibs_to_authorities.pl --link-report --verbose
--bib-limit="biblionumber=${BIB}" (replacing ${BIB} with the biblionumber
of the record you've been editing)
47. Confirm that the heading has been linked to the first authority record it
matches
48. Change LinkerModule to "LastMatch"
49. Run misc/link_bibs_to_authorities.pl --link-report --verbose
--bib-limit="biblionumber=${BIB}" (replacing ${BIB} with the biblionumber
of the record you've been editing)
50. Confirm that the heading has been linked to the second authority record it
matches
51. Run misc/link_bibs_to_authorities.pl --link-report --verbose
--auth-limit="authid=${AUTH}" (replacing ${AUTH} with an authid)
52. Confirm that only that heading is displayed in the report, and only those
bibs with that heading have been changed
If all those things worked, good news! You're ready to sign off on the patch
for bug 7284.
Signed-off-by: Jared Camins-Esakov <jcamins@cpbibliography.com>
Rebased on latest master and squashed follow-up, 16 February 2012
Signed-off-by: Jared Camins-Esakov <jcamins@cpbibliography.com>
Rebased on latest master, 21 February 2012
Signed-off-by: schuster <dschust1@gmail.com>
2711 lines
101 KiB
Perl
2711 lines
101 KiB
Perl
package C4::Search;
|
|
|
|
# This file is part of Koha.
|
|
#
|
|
# Koha is free software; you can redistribute it and/or modify it under the
|
|
# terms of the GNU General Public License as published by the Free Software
|
|
# Foundation; either version 2 of the License, or (at your option) any later
|
|
# version.
|
|
#
|
|
# Koha is distributed in the hope that it will be useful, but WITHOUT ANY
|
|
# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
|
|
# A PARTICULAR PURPOSE. See the GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU General Public License along with
|
|
# Koha; if not, write to the Free Software Foundation, Inc., 59 Temple Place,
|
|
# Suite 330, Boston, MA 02111-1307 USA
|
|
|
|
use strict;
|
|
#use warnings; FIXME - Bug 2505
|
|
require Exporter;
|
|
use C4::Context;
|
|
use C4::Biblio; # GetMarcFromKohaField, GetBiblioData
|
|
use C4::Koha; # getFacets
|
|
use Lingua::Stem;
|
|
use C4::Search::PazPar2;
|
|
use XML::Simple;
|
|
use C4::Dates qw(format_date);
|
|
use C4::Members qw(GetHideLostItemsPreference);
|
|
use C4::XSLT;
|
|
use C4::Branch;
|
|
use C4::Reserves; # CheckReserves
|
|
use C4::Debug;
|
|
use C4::Items;
|
|
use C4::Charset;
|
|
use YAML;
|
|
use URI::Escape;
|
|
use Business::ISBN;
|
|
|
|
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS $DEBUG);
|
|
|
|
# set the version for version checking
|
|
BEGIN {
|
|
$VERSION = 3.01;
|
|
$DEBUG = ($ENV{DEBUG}) ? 1 : 0;
|
|
}
|
|
|
|
=head1 NAME
|
|
|
|
C4::Search - Functions for searching the Koha catalog.
|
|
|
|
=head1 SYNOPSIS
|
|
|
|
See opac/opac-search.pl or catalogue/search.pl for example of usage
|
|
|
|
=head1 DESCRIPTION
|
|
|
|
This module provides searching functions for Koha's bibliographic databases
|
|
|
|
=head1 FUNCTIONS
|
|
|
|
=cut
|
|
|
|
@ISA = qw(Exporter);
|
|
@EXPORT = qw(
|
|
&FindDuplicate
|
|
&SimpleSearch
|
|
&searchResults
|
|
&getRecords
|
|
&buildQuery
|
|
&NZgetRecords
|
|
&AddSearchHistory
|
|
&GetDistinctValues
|
|
&enabled_staff_search_views
|
|
);
|
|
|
|
# make all your functions, whether exported or not;
|
|
|
|
=head2 FindDuplicate
|
|
|
|
($biblionumber,$biblionumber,$title) = FindDuplicate($record);
|
|
|
|
This function attempts to find duplicate records using a hard-coded, fairly simplistic algorithm
|
|
|
|
=cut
|
|
|
|
sub FindDuplicate {
|
|
my ($record) = @_;
|
|
my $dbh = C4::Context->dbh;
|
|
my $result = TransformMarcToKoha( $dbh, $record, '' );
|
|
my $sth;
|
|
my $query;
|
|
my $search;
|
|
my $type;
|
|
my ( $biblionumber, $title );
|
|
|
|
# search duplicate on ISBN, easy and fast..
|
|
# ... normalize first
|
|
if ( $result->{isbn} ) {
|
|
$result->{isbn} =~ s/\(.*$//;
|
|
$result->{isbn} =~ s/\s+$//;
|
|
$query = "isbn=$result->{isbn}";
|
|
}
|
|
else {
|
|
$result->{title} =~ s /\\//g;
|
|
$result->{title} =~ s /\"//g;
|
|
$result->{title} =~ s /\(//g;
|
|
$result->{title} =~ s /\)//g;
|
|
|
|
# FIXME: instead of removing operators, could just do
|
|
# quotes around the value
|
|
$result->{title} =~ s/(and|or|not)//g;
|
|
$query = "ti,ext=$result->{title}";
|
|
$query .= " and itemtype=$result->{itemtype}"
|
|
if ( $result->{itemtype} );
|
|
if ( $result->{author} ) {
|
|
$result->{author} =~ s /\\//g;
|
|
$result->{author} =~ s /\"//g;
|
|
$result->{author} =~ s /\(//g;
|
|
$result->{author} =~ s /\)//g;
|
|
|
|
# remove valid operators
|
|
$result->{author} =~ s/(and|or|not)//g;
|
|
$query .= " and au,ext=$result->{author}";
|
|
}
|
|
}
|
|
|
|
my ( $error, $searchresults, undef ) = SimpleSearch($query); # FIXME :: hardcoded !
|
|
my @results;
|
|
if (!defined $error) {
|
|
foreach my $possible_duplicate_record (@{$searchresults}) {
|
|
my $marcrecord =
|
|
MARC::Record->new_from_usmarc($possible_duplicate_record);
|
|
my $result = TransformMarcToKoha( $dbh, $marcrecord, '' );
|
|
|
|
# FIXME :: why 2 $biblionumber ?
|
|
if ($result) {
|
|
push @results, $result->{'biblionumber'};
|
|
push @results, $result->{'title'};
|
|
}
|
|
}
|
|
}
|
|
return @results;
|
|
}
|
|
|
|
=head2 SimpleSearch
|
|
|
|
( $error, $results, $total_hits ) = SimpleSearch( $query, $offset, $max_results, [@servers] );
|
|
|
|
This function provides a simple search API on the bibliographic catalog
|
|
|
|
=over 2
|
|
|
|
=item C<input arg:>
|
|
|
|
* $query can be a simple keyword or a complete CCL query
|
|
* @servers is optional. Defaults to biblioserver as found in koha-conf.xml
|
|
* $offset - If present, represents the number of records at the beggining to omit. Defaults to 0
|
|
* $max_results - if present, determines the maximum number of records to fetch. undef is All. defaults to undef.
|
|
|
|
|
|
=item C<Return:>
|
|
|
|
Returns an array consisting of three elements
|
|
* $error is undefined unless an error is detected
|
|
* $results is a reference to an array of records.
|
|
* $total_hits is the number of hits that would have been returned with no limit
|
|
|
|
If an error is returned the two other return elements are undefined. If error itself is undefined
|
|
the other two elements are always defined
|
|
|
|
=item C<usage in the script:>
|
|
|
|
=back
|
|
|
|
my ( $error, $marcresults, $total_hits ) = SimpleSearch($query);
|
|
|
|
if (defined $error) {
|
|
$template->param(query_error => $error);
|
|
warn "error: ".$error;
|
|
output_html_with_http_headers $input, $cookie, $template->output;
|
|
exit;
|
|
}
|
|
|
|
my $hits = @{$marcresults};
|
|
my @results;
|
|
|
|
for my $r ( @{$marcresults} ) {
|
|
my $marcrecord = MARC::File::USMARC::decode($r);
|
|
my $biblio = TransformMarcToKoha(C4::Context->dbh,$marcrecord,q{});
|
|
|
|
#build the iarray of hashs for the template.
|
|
push @results, {
|
|
title => $biblio->{'title'},
|
|
subtitle => $biblio->{'subtitle'},
|
|
biblionumber => $biblio->{'biblionumber'},
|
|
author => $biblio->{'author'},
|
|
publishercode => $biblio->{'publishercode'},
|
|
publicationyear => $biblio->{'publicationyear'},
|
|
};
|
|
|
|
}
|
|
|
|
$template->param(result=>\@results);
|
|
|
|
=cut
|
|
|
|
sub SimpleSearch {
|
|
my ( $query, $offset, $max_results, $servers ) = @_;
|
|
|
|
if ( C4::Context->preference('NoZebra') ) {
|
|
my $result = NZorder( NZanalyse($query) )->{'biblioserver'};
|
|
my $search_result =
|
|
( $result->{hits}
|
|
&& $result->{hits} > 0 ? $result->{'RECORDS'} : [] );
|
|
return ( undef, $search_result, scalar($result->{hits}) );
|
|
}
|
|
else {
|
|
return ( 'No query entered', undef, undef ) unless $query;
|
|
# FIXME hardcoded value. See catalog/search.pl & opac-search.pl too.
|
|
my @servers = defined ( $servers ) ? @$servers : ( 'biblioserver' );
|
|
my @zoom_queries;
|
|
my @tmpresults;
|
|
my @zconns;
|
|
my $results = [];
|
|
my $total_hits = 0;
|
|
|
|
# Initialize & Search Zebra
|
|
for ( my $i = 0 ; $i < @servers ; $i++ ) {
|
|
eval {
|
|
$zconns[$i] = C4::Context->Zconn( $servers[$i], 1 );
|
|
$zoom_queries[$i] = new ZOOM::Query::CCL2RPN( $query, $zconns[$i]);
|
|
$tmpresults[$i] = $zconns[$i]->search( $zoom_queries[$i] );
|
|
|
|
# error handling
|
|
my $error =
|
|
$zconns[$i]->errmsg() . " ("
|
|
. $zconns[$i]->errcode() . ") "
|
|
. $zconns[$i]->addinfo() . " "
|
|
. $zconns[$i]->diagset();
|
|
|
|
return ( $error, undef, undef ) if $zconns[$i]->errcode();
|
|
};
|
|
if ($@) {
|
|
|
|
# caught a ZOOM::Exception
|
|
my $error =
|
|
$@->message() . " ("
|
|
. $@->code() . ") "
|
|
. $@->addinfo() . " "
|
|
. $@->diagset();
|
|
warn $error;
|
|
return ( $error, undef, undef );
|
|
}
|
|
}
|
|
while ( ( my $i = ZOOM::event( \@zconns ) ) != 0 ) {
|
|
my $event = $zconns[ $i - 1 ]->last_event();
|
|
if ( $event == ZOOM::Event::ZEND ) {
|
|
|
|
my $first_record = defined( $offset ) ? $offset+1 : 1;
|
|
my $hits = $tmpresults[ $i - 1 ]->size();
|
|
$total_hits += $hits;
|
|
my $last_record = $hits;
|
|
if ( defined $max_results && $offset + $max_results < $hits ) {
|
|
$last_record = $offset + $max_results;
|
|
}
|
|
|
|
for my $j ( $first_record..$last_record ) {
|
|
my $record = $tmpresults[ $i - 1 ]->record( $j-1 )->raw(); # 0 indexed
|
|
push @{$results}, $record;
|
|
}
|
|
}
|
|
}
|
|
|
|
foreach my $result (@tmpresults) {
|
|
$result->destroy();
|
|
}
|
|
foreach my $zoom_query (@zoom_queries) {
|
|
$zoom_query->destroy();
|
|
}
|
|
|
|
return ( undef, $results, $total_hits );
|
|
}
|
|
}
|
|
|
|
=head2 getRecords
|
|
|
|
( undef, $results_hashref, \@facets_loop ) = getRecords (
|
|
|
|
$koha_query, $simple_query, $sort_by_ref, $servers_ref,
|
|
$results_per_page, $offset, $expanded_facet, $branches,
|
|
$query_type, $scan
|
|
);
|
|
|
|
The all singing, all dancing, multi-server, asynchronous, scanning,
|
|
searching, record nabbing, facet-building
|
|
|
|
See verbse embedded documentation.
|
|
|
|
=cut
|
|
|
|
sub getRecords {
|
|
my (
|
|
$koha_query, $simple_query, $sort_by_ref, $servers_ref,
|
|
$results_per_page, $offset, $expanded_facet, $branches,
|
|
$query_type, $scan
|
|
) = @_;
|
|
|
|
my @servers = @$servers_ref;
|
|
my @sort_by = @$sort_by_ref;
|
|
|
|
# Initialize variables for the ZOOM connection and results object
|
|
my $zconn;
|
|
my @zconns;
|
|
my @results;
|
|
my $results_hashref = ();
|
|
|
|
# Initialize variables for the faceted results objects
|
|
my $facets_counter = ();
|
|
my $facets_info = ();
|
|
my $facets = getFacets();
|
|
my $facets_maxrecs = C4::Context->preference('maxRecordsForFacets')||20;
|
|
|
|
my @facets_loop; # stores the ref to array of hashes for template facets loop
|
|
|
|
### LOOP THROUGH THE SERVERS
|
|
for ( my $i = 0 ; $i < @servers ; $i++ ) {
|
|
$zconns[$i] = C4::Context->Zconn( $servers[$i], 1 );
|
|
|
|
# perform the search, create the results objects
|
|
# if this is a local search, use the $koha-query, if it's a federated one, use the federated-query
|
|
my $query_to_use = ($servers[$i] =~ /biblioserver/) ? $koha_query : $simple_query;
|
|
|
|
#$query_to_use = $simple_query if $scan;
|
|
warn $simple_query if ( $scan and $DEBUG );
|
|
|
|
# Check if we've got a query_type defined, if so, use it
|
|
eval {
|
|
if ($query_type) {
|
|
if ($query_type =~ /^ccl/) {
|
|
$query_to_use =~ s/\:/\=/g; # change : to = last minute (FIXME)
|
|
$results[$i] = $zconns[$i]->search(new ZOOM::Query::CCL2RPN($query_to_use, $zconns[$i]));
|
|
} elsif ($query_type =~ /^cql/) {
|
|
$results[$i] = $zconns[$i]->search(new ZOOM::Query::CQL($query_to_use, $zconns[$i]));
|
|
} elsif ($query_type =~ /^pqf/) {
|
|
$results[$i] = $zconns[$i]->search(new ZOOM::Query::PQF($query_to_use, $zconns[$i]));
|
|
} else {
|
|
warn "Unknown query_type '$query_type'. Results undetermined.";
|
|
}
|
|
} elsif ($scan) {
|
|
$results[$i] = $zconns[$i]->scan( new ZOOM::Query::CCL2RPN($query_to_use, $zconns[$i]));
|
|
} else {
|
|
$results[$i] = $zconns[$i]->search(new ZOOM::Query::CCL2RPN($query_to_use, $zconns[$i]));
|
|
}
|
|
};
|
|
if ($@) {
|
|
warn "WARNING: query problem with $query_to_use " . $@;
|
|
}
|
|
|
|
# Concatenate the sort_by limits and pass them to the results object
|
|
# Note: sort will override rank
|
|
my $sort_by;
|
|
foreach my $sort (@sort_by) {
|
|
if ( $sort eq "author_az" || $sort eq "author_asc" ) {
|
|
$sort_by .= "1=1003 <i ";
|
|
}
|
|
elsif ( $sort eq "author_za" || $sort eq "author_dsc" ) {
|
|
$sort_by .= "1=1003 >i ";
|
|
}
|
|
elsif ( $sort eq "popularity_asc" ) {
|
|
$sort_by .= "1=9003 <i ";
|
|
}
|
|
elsif ( $sort eq "popularity_dsc" ) {
|
|
$sort_by .= "1=9003 >i ";
|
|
}
|
|
elsif ( $sort eq "call_number_asc" ) {
|
|
$sort_by .= "1=8007 <i ";
|
|
}
|
|
elsif ( $sort eq "call_number_dsc" ) {
|
|
$sort_by .= "1=8007 >i ";
|
|
}
|
|
elsif ( $sort eq "pubdate_asc" ) {
|
|
$sort_by .= "1=31 <i ";
|
|
}
|
|
elsif ( $sort eq "pubdate_dsc" ) {
|
|
$sort_by .= "1=31 >i ";
|
|
}
|
|
elsif ( $sort eq "acqdate_asc" ) {
|
|
$sort_by .= "1=32 <i ";
|
|
}
|
|
elsif ( $sort eq "acqdate_dsc" ) {
|
|
$sort_by .= "1=32 >i ";
|
|
}
|
|
elsif ( $sort eq "title_az" || $sort eq "title_asc" ) {
|
|
$sort_by .= "1=4 <i ";
|
|
}
|
|
elsif ( $sort eq "title_za" || $sort eq "title_dsc" ) {
|
|
$sort_by .= "1=4 >i ";
|
|
}
|
|
else {
|
|
warn "Ignoring unrecognized sort '$sort' requested" if $sort_by;
|
|
}
|
|
}
|
|
if ($sort_by && !$scan) {
|
|
if ( $results[$i]->sort( "yaz", $sort_by ) < 0 ) {
|
|
warn "WARNING sort $sort_by failed";
|
|
}
|
|
}
|
|
} # finished looping through servers
|
|
|
|
# The big moment: asynchronously retrieve results from all servers
|
|
while ( ( my $i = ZOOM::event( \@zconns ) ) != 0 ) {
|
|
my $ev = $zconns[ $i - 1 ]->last_event();
|
|
if ( $ev == ZOOM::Event::ZEND ) {
|
|
next unless $results[ $i - 1 ];
|
|
my $size = $results[ $i - 1 ]->size();
|
|
if ( $size > 0 ) {
|
|
my $results_hash;
|
|
|
|
# loop through the results
|
|
$results_hash->{'hits'} = $size;
|
|
my $times;
|
|
if ( $offset + $results_per_page <= $size ) {
|
|
$times = $offset + $results_per_page;
|
|
}
|
|
else {
|
|
$times = $size;
|
|
}
|
|
for ( my $j = $offset ; $j < $times ; $j++ ) {
|
|
my $records_hash;
|
|
my $record;
|
|
|
|
## Check if it's an index scan
|
|
if ($scan) {
|
|
my ( $term, $occ ) = $results[ $i - 1 ]->term($j);
|
|
|
|
# here we create a minimal MARC record and hand it off to the
|
|
# template just like a normal result ... perhaps not ideal, but
|
|
# it works for now
|
|
my $tmprecord = MARC::Record->new();
|
|
$tmprecord->encoding('UTF-8');
|
|
my $tmptitle;
|
|
my $tmpauthor;
|
|
|
|
# the minimal record in author/title (depending on MARC flavour)
|
|
if (C4::Context->preference("marcflavour") eq "UNIMARC") {
|
|
$tmptitle = MARC::Field->new('200',' ',' ', a => $term, f => $occ);
|
|
$tmprecord->append_fields($tmptitle);
|
|
} else {
|
|
$tmptitle = MARC::Field->new('245',' ',' ', a => $term,);
|
|
$tmpauthor = MARC::Field->new('100',' ',' ', a => $occ,);
|
|
$tmprecord->append_fields($tmptitle);
|
|
$tmprecord->append_fields($tmpauthor);
|
|
}
|
|
$results_hash->{'RECORDS'}[$j] = $tmprecord->as_usmarc();
|
|
}
|
|
|
|
# not an index scan
|
|
else {
|
|
$record = $results[ $i - 1 ]->record($j)->raw();
|
|
|
|
# warn "RECORD $j:".$record;
|
|
$results_hash->{'RECORDS'}[$j] = $record;
|
|
}
|
|
|
|
}
|
|
$results_hashref->{ $servers[ $i - 1 ] } = $results_hash;
|
|
|
|
# Fill the facets while we're looping, but only for the biblioserver and not for a scan
|
|
if ( !$scan && $servers[ $i - 1 ] =~ /biblioserver/ ) {
|
|
|
|
my $jmax = $size>$facets_maxrecs? $facets_maxrecs: $size;
|
|
|
|
for ( my $k = 0 ; $k <= @$facets ; $k++ ) {
|
|
($facets->[$k]) or next;
|
|
my @fcodes = @{$facets->[$k]->{'tags'}};
|
|
my $sfcode = $facets->[$k]->{'subfield'};
|
|
|
|
for ( my $j = 0 ; $j < $jmax ; $j++ ) {
|
|
my $render_record = $results[ $i - 1 ]->record($j)->render();
|
|
my @used_datas = ();
|
|
|
|
foreach my $fcode (@fcodes) {
|
|
|
|
# avoid first line
|
|
my $field_pattern = '\n'.$fcode.' ([^\n]+)';
|
|
my @field_tokens = ( $render_record =~ /$field_pattern/g ) ;
|
|
|
|
foreach my $field_token (@field_tokens) {
|
|
my $subfield_pattern = '\$'.$sfcode.' ([^\$]+)';
|
|
my @subfield_values = ( $field_token =~ /$subfield_pattern/g );
|
|
|
|
foreach my $subfield_value (@subfield_values) {
|
|
|
|
my $data = $subfield_value;
|
|
$data =~ s/^\s+//; # trim left
|
|
$data =~ s/\s+$//; # trim right
|
|
|
|
unless ( $data ~~ @used_datas ) {
|
|
$facets_counter->{ $facets->[$k]->{'link_value'} }->{$data}++;
|
|
push @used_datas, $data;
|
|
}
|
|
} # subfields
|
|
} # fields
|
|
} # field codes
|
|
} # records
|
|
|
|
$facets_info->{ $facets->[$k]->{'link_value'} }->{'label_value'} = $facets->[$k]->{'label_value'};
|
|
$facets_info->{ $facets->[$k]->{'link_value'} }->{'expanded'} = $facets->[$k]->{'expanded'};
|
|
} # facets
|
|
}
|
|
# End PROGILONE
|
|
}
|
|
|
|
# warn "connection ", $i-1, ": $size hits";
|
|
# warn $results[$i-1]->record(0)->render() if $size > 0;
|
|
|
|
# BUILD FACETS
|
|
if ( $servers[ $i - 1 ] =~ /biblioserver/ ) {
|
|
for my $link_value (
|
|
sort { $facets_counter->{$b} <=> $facets_counter->{$a} }
|
|
keys %$facets_counter )
|
|
{
|
|
my $expandable;
|
|
my $number_of_facets;
|
|
my @this_facets_array;
|
|
for my $one_facet (
|
|
sort {
|
|
$facets_counter->{$link_value}->{$b}
|
|
<=> $facets_counter->{$link_value}->{$a}
|
|
} keys %{ $facets_counter->{$link_value} }
|
|
)
|
|
{
|
|
$number_of_facets++;
|
|
if ( ( $number_of_facets < 6 )
|
|
|| ( $expanded_facet eq $link_value )
|
|
|| ( $facets_info->{$link_value}->{'expanded'} ) )
|
|
{
|
|
|
|
# Sanitize the link value ), ( will cause errors with CCL,
|
|
my $facet_link_value = $one_facet;
|
|
$facet_link_value =~ s/(\(|\))/ /g;
|
|
|
|
# fix the length that will display in the label,
|
|
my $facet_label_value = $one_facet;
|
|
my $facet_max_length =
|
|
C4::Context->preference('FacetLabelTruncationLength') || 20;
|
|
$facet_label_value =
|
|
substr( $one_facet, 0, $facet_max_length ) . "..."
|
|
if length($facet_label_value) > $facet_max_length;
|
|
|
|
# if it's a branch, label by the name, not the code,
|
|
if ( $link_value =~ /branch/ ) {
|
|
if (defined $branches
|
|
&& ref($branches) eq "HASH"
|
|
&& defined $branches->{$one_facet}
|
|
&& ref ($branches->{$one_facet}) eq "HASH")
|
|
{
|
|
$facet_label_value =
|
|
$branches->{$one_facet}->{'branchname'};
|
|
}
|
|
else {
|
|
$facet_label_value = "*";
|
|
}
|
|
}
|
|
|
|
# but we're down with the whole label being in the link's title.
|
|
push @this_facets_array, {
|
|
facet_count => $facets_counter->{$link_value}->{$one_facet},
|
|
facet_label_value => $facet_label_value,
|
|
facet_title_value => $one_facet,
|
|
facet_link_value => $facet_link_value,
|
|
type_link_value => $link_value,
|
|
};
|
|
}
|
|
}
|
|
|
|
# handle expanded option
|
|
unless ( $facets_info->{$link_value}->{'expanded'} ) {
|
|
$expandable = 1
|
|
if ( ( $number_of_facets > 6 )
|
|
&& ( $expanded_facet ne $link_value ) );
|
|
}
|
|
push @facets_loop, {
|
|
type_link_value => $link_value,
|
|
type_id => $link_value . "_id",
|
|
"type_label_" . $facets_info->{$link_value}->{'label_value'} => 1,
|
|
facets => \@this_facets_array,
|
|
expandable => $expandable,
|
|
expand => $link_value,
|
|
} unless ( ($facets_info->{$link_value}->{'label_value'} =~ /Libraries/) and (C4::Context->preference('singleBranchMode')) );
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return ( undef, $results_hashref, \@facets_loop );
|
|
}
|
|
|
|
sub pazGetRecords {
|
|
my (
|
|
$koha_query, $simple_query, $sort_by_ref, $servers_ref,
|
|
$results_per_page, $offset, $expanded_facet, $branches,
|
|
$query_type, $scan
|
|
) = @_;
|
|
|
|
my $paz = C4::Search::PazPar2->new(C4::Context->config('pazpar2url'));
|
|
$paz->init();
|
|
$paz->search($simple_query);
|
|
sleep 1; # FIXME: WHY?
|
|
|
|
# do results
|
|
my $results_hashref = {};
|
|
my $stats = XMLin($paz->stat);
|
|
my $results = XMLin($paz->show($offset, $results_per_page, 'work-title:1'), forcearray => 1);
|
|
|
|
# for a grouped search result, the number of hits
|
|
# is the number of groups returned; 'bib_hits' will have
|
|
# the total number of bibs.
|
|
$results_hashref->{'biblioserver'}->{'hits'} = $results->{'merged'}->[0];
|
|
$results_hashref->{'biblioserver'}->{'bib_hits'} = $stats->{'hits'};
|
|
|
|
HIT: foreach my $hit (@{ $results->{'hit'} }) {
|
|
my $recid = $hit->{recid}->[0];
|
|
|
|
my $work_title = $hit->{'md-work-title'}->[0];
|
|
my $work_author;
|
|
if (exists $hit->{'md-work-author'}) {
|
|
$work_author = $hit->{'md-work-author'}->[0];
|
|
}
|
|
my $group_label = (defined $work_author) ? "$work_title / $work_author" : $work_title;
|
|
|
|
my $result_group = {};
|
|
$result_group->{'group_label'} = $group_label;
|
|
$result_group->{'group_merge_key'} = $recid;
|
|
|
|
my $count = 1;
|
|
if (exists $hit->{count}) {
|
|
$count = $hit->{count}->[0];
|
|
}
|
|
$result_group->{'group_count'} = $count;
|
|
|
|
for (my $i = 0; $i < $count; $i++) {
|
|
# FIXME -- may need to worry about diacritics here
|
|
my $rec = $paz->record($recid, $i);
|
|
push @{ $result_group->{'RECORDS'} }, $rec;
|
|
}
|
|
|
|
push @{ $results_hashref->{'biblioserver'}->{'GROUPS'} }, $result_group;
|
|
}
|
|
|
|
# pass through facets
|
|
my $termlist_xml = $paz->termlist('author,subject');
|
|
my $terms = XMLin($termlist_xml, forcearray => 1);
|
|
my @facets_loop = ();
|
|
#die Dumper($results);
|
|
# foreach my $list (sort keys %{ $terms->{'list'} }) {
|
|
# my @facets = ();
|
|
# foreach my $facet (sort @{ $terms->{'list'}->{$list}->{'term'} } ) {
|
|
# push @facets, {
|
|
# facet_label_value => $facet->{'name'}->[0],
|
|
# };
|
|
# }
|
|
# push @facets_loop, ( {
|
|
# type_label => $list,
|
|
# facets => \@facets,
|
|
# } );
|
|
# }
|
|
|
|
return ( undef, $results_hashref, \@facets_loop );
|
|
}
|
|
|
|
# STOPWORDS
|
|
sub _remove_stopwords {
|
|
my ( $operand, $index ) = @_;
|
|
my @stopwords_removed;
|
|
|
|
# phrase and exact-qualified indexes shouldn't have stopwords removed
|
|
if ( $index !~ m/phr|ext/ ) {
|
|
|
|
# remove stopwords from operand : parse all stopwords & remove them (case insensitive)
|
|
# we use IsAlpha unicode definition, to deal correctly with diacritics.
|
|
# otherwise, a French word like "leçon" woudl be split into "le" "çon", "le"
|
|
# is a stopword, we'd get "çon" and wouldn't find anything...
|
|
#
|
|
foreach ( keys %{ C4::Context->stopwords } ) {
|
|
next if ( $_ =~ /(and|or|not)/ ); # don't remove operators
|
|
if ( my ($matched) = ($operand =~
|
|
/([^\X\p{isAlnum}]\Q$_\E[^\X\p{isAlnum}]|[^\X\p{isAlnum}]\Q$_\E$|^\Q$_\E[^\X\p{isAlnum}])/gi))
|
|
{
|
|
$operand =~ s/\Q$matched\E/ /gi;
|
|
push @stopwords_removed, $_;
|
|
}
|
|
}
|
|
}
|
|
return ( $operand, \@stopwords_removed );
|
|
}
|
|
|
|
# TRUNCATION
|
|
sub _detect_truncation {
|
|
my ( $operand, $index ) = @_;
|
|
my ( @nontruncated, @righttruncated, @lefttruncated, @rightlefttruncated,
|
|
@regexpr );
|
|
$operand =~ s/^ //g;
|
|
my @wordlist = split( /\s/, $operand );
|
|
foreach my $word (@wordlist) {
|
|
if ( $word =~ s/^\*([^\*]+)\*$/$1/ ) {
|
|
push @rightlefttruncated, $word;
|
|
}
|
|
elsif ( $word =~ s/^\*([^\*]+)$/$1/ ) {
|
|
push @lefttruncated, $word;
|
|
}
|
|
elsif ( $word =~ s/^([^\*]+)\*$/$1/ ) {
|
|
push @righttruncated, $word;
|
|
}
|
|
elsif ( index( $word, "*" ) < 0 ) {
|
|
push @nontruncated, $word;
|
|
}
|
|
else {
|
|
push @regexpr, $word;
|
|
}
|
|
}
|
|
return (
|
|
\@nontruncated, \@righttruncated, \@lefttruncated,
|
|
\@rightlefttruncated, \@regexpr
|
|
);
|
|
}
|
|
|
|
# STEMMING
|
|
sub _build_stemmed_operand {
|
|
my ($operand,$lang) = @_;
|
|
require Lingua::Stem::Snowball ;
|
|
my $stemmed_operand;
|
|
|
|
# If operand contains a digit, it is almost certainly an identifier, and should
|
|
# not be stemmed. This is particularly relevant for ISBNs and ISSNs, which
|
|
# can contain the letter "X" - for example, _build_stemmend_operand would reduce
|
|
# "014100018X" to "x ", which for a MARC21 database would bring up irrelevant
|
|
# results (e.g., "23 x 29 cm." from the 300$c). Bug 2098.
|
|
return $operand if $operand =~ /\d/;
|
|
|
|
# FIXME: the locale should be set based on the user's language and/or search choice
|
|
#warn "$lang";
|
|
my $stemmer = Lingua::Stem::Snowball->new( lang => $lang,
|
|
encoding => "UTF-8" );
|
|
|
|
my @words = split( / /, $operand );
|
|
my @stems = $stemmer->stem(\@words);
|
|
for my $stem (@stems) {
|
|
$stemmed_operand .= "$stem";
|
|
$stemmed_operand .= "?"
|
|
unless ( $stem =~ /(and$|or$|not$)/ ) || ( length($stem) < 3 );
|
|
$stemmed_operand .= " ";
|
|
}
|
|
warn "STEMMED OPERAND: $stemmed_operand" if $DEBUG;
|
|
return $stemmed_operand;
|
|
}
|
|
|
|
# FIELD WEIGHTING
|
|
sub _build_weighted_query {
|
|
|
|
# FIELD WEIGHTING - This is largely experimental stuff. What I'm committing works
|
|
# pretty well but could work much better if we had a smarter query parser
|
|
my ( $operand, $stemmed_operand, $index ) = @_;
|
|
my $stemming = C4::Context->preference("QueryStemming") || 0;
|
|
my $weight_fields = C4::Context->preference("QueryWeightFields") || 0;
|
|
my $fuzzy_enabled = C4::Context->preference("QueryFuzzy") || 0;
|
|
|
|
my $weighted_query .= "(rk=("; # Specifies that we're applying rank
|
|
|
|
# Keyword, or, no index specified
|
|
if ( ( $index eq 'kw' ) || ( !$index ) ) {
|
|
$weighted_query .=
|
|
"Title-cover,ext,r1=\"$operand\""; # exact title-cover
|
|
$weighted_query .= " or ti,ext,r2=\"$operand\""; # exact title
|
|
$weighted_query .= " or ti,phr,r3=\"$operand\""; # phrase title
|
|
#$weighted_query .= " or any,ext,r4=$operand"; # exact any
|
|
#$weighted_query .=" or kw,wrdl,r5=\"$operand\""; # word list any
|
|
$weighted_query .= " or wrdl,fuzzy,r8=\"$operand\""
|
|
if $fuzzy_enabled; # add fuzzy, word list
|
|
$weighted_query .= " or wrdl,right-Truncation,r9=\"$stemmed_operand\""
|
|
if ( $stemming and $stemmed_operand )
|
|
; # add stemming, right truncation
|
|
$weighted_query .= " or wrdl,r9=\"$operand\"";
|
|
|
|
# embedded sorting: 0 a-z; 1 z-a
|
|
# $weighted_query .= ") or (sort1,aut=1";
|
|
}
|
|
|
|
# Barcode searches should skip this process
|
|
elsif ( $index eq 'bc' ) {
|
|
$weighted_query .= "bc=\"$operand\"";
|
|
}
|
|
|
|
# Authority-number searches should skip this process
|
|
elsif ( $index eq 'an' ) {
|
|
$weighted_query .= "an=\"$operand\"";
|
|
}
|
|
|
|
# If the index already has more than one qualifier, wrap the operand
|
|
# in quotes and pass it back (assumption is that the user knows what they
|
|
# are doing and won't appreciate us mucking up their query
|
|
elsif ( $index =~ ',' ) {
|
|
$weighted_query .= " $index=\"$operand\"";
|
|
}
|
|
|
|
#TODO: build better cases based on specific search indexes
|
|
else {
|
|
$weighted_query .= " $index,ext,r1=\"$operand\""; # exact index
|
|
#$weighted_query .= " or (title-sort-az=0 or $index,startswithnt,st-word,r3=$operand #)";
|
|
$weighted_query .= " or $index,phr,r3=\"$operand\""; # phrase index
|
|
$weighted_query .=
|
|
" or $index,rt,wrdl,r3=\"$operand\""; # word list index
|
|
}
|
|
|
|
$weighted_query .= "))"; # close rank specification
|
|
return $weighted_query;
|
|
}
|
|
|
|
=head2 getIndexes
|
|
|
|
Return an array with available indexes.
|
|
|
|
=cut
|
|
|
|
sub getIndexes{
|
|
my @indexes = (
|
|
# biblio indexes
|
|
'ab',
|
|
'Abstract',
|
|
'acqdate',
|
|
'allrecords',
|
|
'an',
|
|
'Any',
|
|
'at',
|
|
'au',
|
|
'aub',
|
|
'aud',
|
|
'audience',
|
|
'auo',
|
|
'aut',
|
|
'Author',
|
|
'Author-in-order ',
|
|
'Author-personal-bibliography',
|
|
'Authority-Number',
|
|
'authtype',
|
|
'bc',
|
|
'Bib-level',
|
|
'biblionumber',
|
|
'bio',
|
|
'biography',
|
|
'callnum',
|
|
'cfn',
|
|
'Chronological-subdivision',
|
|
'cn-bib-source',
|
|
'cn-bib-sort',
|
|
'cn-class',
|
|
'cn-item',
|
|
'cn-prefix',
|
|
'cn-suffix',
|
|
'cpn',
|
|
'Code-institution',
|
|
'Conference-name',
|
|
'Conference-name-heading',
|
|
'Conference-name-see',
|
|
'Conference-name-seealso',
|
|
'Content-type',
|
|
'Control-number',
|
|
'copydate',
|
|
'Corporate-name',
|
|
'Corporate-name-heading',
|
|
'Corporate-name-see',
|
|
'Corporate-name-seealso',
|
|
'ctype',
|
|
'date-entered-on-file',
|
|
'Date-of-acquisition',
|
|
'Date-of-publication',
|
|
'Dewey-classification',
|
|
'EAN',
|
|
'extent',
|
|
'fic',
|
|
'fiction',
|
|
'Form-subdivision',
|
|
'format',
|
|
'Geographic-subdivision',
|
|
'he',
|
|
'Heading',
|
|
'Heading-use-main-or-added-entry',
|
|
'Heading-use-series-added-entry ',
|
|
'Heading-use-subject-added-entry',
|
|
'Host-item',
|
|
'id-other',
|
|
'Illustration-code',
|
|
'ISBN',
|
|
'isbn',
|
|
'ISSN',
|
|
'issn',
|
|
'itemtype',
|
|
'kw',
|
|
'Koha-Auth-Number',
|
|
'l-format',
|
|
'language',
|
|
'lc-card',
|
|
'LC-card-number',
|
|
'lcn',
|
|
'llength',
|
|
'ln',
|
|
'Local-classification',
|
|
'Local-number',
|
|
'Match-heading',
|
|
'Match-heading-see-from',
|
|
'Material-type',
|
|
'mc-itemtype',
|
|
'mc-rtype',
|
|
'mus',
|
|
'name',
|
|
'Music-number',
|
|
'Name-geographic',
|
|
'Name-geographic-heading',
|
|
'Name-geographic-see',
|
|
'Name-geographic-seealso',
|
|
'nb',
|
|
'Note',
|
|
'notes',
|
|
'ns',
|
|
'nt',
|
|
'pb',
|
|
'Personal-name',
|
|
'Personal-name-heading',
|
|
'Personal-name-see',
|
|
'Personal-name-seealso',
|
|
'pl',
|
|
'Place-publication',
|
|
'pn',
|
|
'popularity',
|
|
'pubdate',
|
|
'Publisher',
|
|
'Record-control-number',
|
|
'rcn',
|
|
'Record-type',
|
|
'rtype',
|
|
'se',
|
|
'See',
|
|
'See-also',
|
|
'sn',
|
|
'Stock-number',
|
|
'su',
|
|
'Subject',
|
|
'Subject-heading-thesaurus',
|
|
'Subject-name-personal',
|
|
'Subject-subdivision',
|
|
'Summary',
|
|
'Suppress',
|
|
'su-geo',
|
|
'su-na',
|
|
'su-to',
|
|
'su-ut',
|
|
'ut',
|
|
'UPC',
|
|
'Term-genre-form',
|
|
'Term-genre-form-heading',
|
|
'Term-genre-form-see',
|
|
'Term-genre-form-seealso',
|
|
'ti',
|
|
'Title',
|
|
'Title-cover',
|
|
'Title-series',
|
|
'Title-host',
|
|
'Title-uniform',
|
|
'Title-uniform-heading',
|
|
'Title-uniform-see',
|
|
'Title-uniform-seealso',
|
|
'totalissues',
|
|
'yr',
|
|
|
|
# items indexes
|
|
'acqsource',
|
|
'barcode',
|
|
'bc',
|
|
'branch',
|
|
'ccode',
|
|
'classification-source',
|
|
'cn-sort',
|
|
'coded-location-qualifier',
|
|
'copynumber',
|
|
'damaged',
|
|
'datelastborrowed',
|
|
'datelastseen',
|
|
'holdingbranch',
|
|
'homebranch',
|
|
'issues',
|
|
'item',
|
|
'itemnumber',
|
|
'itype',
|
|
'Local-classification',
|
|
'location',
|
|
'lost',
|
|
'materials-specified',
|
|
'mc-ccode',
|
|
'mc-itype',
|
|
'mc-loc',
|
|
'notforloan',
|
|
'onloan',
|
|
'price',
|
|
'renewals',
|
|
'replacementprice',
|
|
'replacementpricedate',
|
|
'reserves',
|
|
'restricted',
|
|
'stack',
|
|
'stocknumber',
|
|
'inv',
|
|
'uri',
|
|
'withdrawn',
|
|
|
|
# subject related
|
|
);
|
|
|
|
return \@indexes;
|
|
}
|
|
|
|
=head2 buildQuery
|
|
|
|
( $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);
|
|
|
|
Build queries and limits in CCL, CGI, Human,
|
|
handle truncation, stemming, field weighting, stopwords, fuzziness, etc.
|
|
|
|
See verbose embedded documentation.
|
|
|
|
|
|
=cut
|
|
|
|
sub buildQuery {
|
|
my ( $operators, $operands, $indexes, $limits, $sort_by, $scan, $lang) = @_;
|
|
|
|
warn "---------\nEnter buildQuery\n---------" if $DEBUG;
|
|
|
|
# dereference
|
|
my @operators = $operators ? @$operators : ();
|
|
my @indexes = $indexes ? @$indexes : ();
|
|
my @operands = $operands ? @$operands : ();
|
|
my @limits = $limits ? @$limits : ();
|
|
my @sort_by = $sort_by ? @$sort_by : ();
|
|
|
|
my $stemming = C4::Context->preference("QueryStemming") || 0;
|
|
my $auto_truncation = C4::Context->preference("QueryAutoTruncate") || 0;
|
|
my $weight_fields = C4::Context->preference("QueryWeightFields") || 0;
|
|
my $fuzzy_enabled = C4::Context->preference("QueryFuzzy") || 0;
|
|
my $remove_stopwords = C4::Context->preference("QueryRemoveStopwords") || 0;
|
|
|
|
# no stemming/weight/fuzzy in NoZebra
|
|
if ( C4::Context->preference("NoZebra") ) {
|
|
$stemming = 0;
|
|
$weight_fields = 0;
|
|
$fuzzy_enabled = 0;
|
|
$auto_truncation = 0;
|
|
}
|
|
|
|
my $query = $operands[0];
|
|
my $simple_query = $operands[0];
|
|
|
|
# initialize the variables we're passing back
|
|
my $query_cgi;
|
|
my $query_desc;
|
|
my $query_type;
|
|
|
|
my $limit;
|
|
my $limit_cgi;
|
|
my $limit_desc;
|
|
|
|
my $stopwords_removed; # flag to determine if stopwords have been removed
|
|
|
|
my $cclq = 0;
|
|
my $cclindexes = getIndexes();
|
|
if ( $query !~ /\s*ccl=/ ) {
|
|
while ( !$cclq && $query =~ /(?:^|\W)([\w-]+)(,[\w-]+)*[:=]/g ) {
|
|
my $dx = lc($1);
|
|
$cclq = grep { lc($_) eq $dx } @$cclindexes;
|
|
}
|
|
$query = "ccl=$query" if $cclq;
|
|
}
|
|
|
|
# for handling ccl, cql, pqf queries in diagnostic mode, skip the rest of the steps
|
|
# DIAGNOSTIC ONLY!!
|
|
if ( $query =~ /^ccl=/ ) {
|
|
my $q=$';
|
|
# This is needed otherwise ccl= and &limit won't work together, and
|
|
# this happens when selecting a subject on the opac-detail page
|
|
if (@limits) {
|
|
$q .= ' and '.join(' and ', @limits);
|
|
}
|
|
return ( undef, $q, $q, "q=ccl=$q", $q, '', '', '', '', 'ccl' );
|
|
}
|
|
if ( $query =~ /^cql=/ ) {
|
|
return ( undef, $', $', "q=cql=$'", $', '', '', '', '', 'cql' );
|
|
}
|
|
if ( $query =~ /^pqf=/ ) {
|
|
return ( undef, $', $', "q=pqf=$'", $', '', '', '', '', 'pqf' );
|
|
}
|
|
|
|
# pass nested queries directly
|
|
# FIXME: need better handling of some of these variables in this case
|
|
# Nested queries aren't handled well and this implementation is flawed and causes users to be
|
|
# unable to search for anything containing () commenting out, will be rewritten for 3.4.0
|
|
# if ( $query =~ /(\(|\))/ ) {
|
|
# return (
|
|
# undef, $query, $simple_query, $query_cgi,
|
|
# $query, $limit, $limit_cgi, $limit_desc,
|
|
# $stopwords_removed, 'ccl'
|
|
# );
|
|
# }
|
|
|
|
# Form-based queries are non-nested and fixed depth, so we can easily modify the incoming
|
|
# query operands and indexes and add stemming, truncation, field weighting, etc.
|
|
# Once we do so, we'll end up with a value in $query, just like if we had an
|
|
# incoming $query from the user
|
|
else {
|
|
$query = ""
|
|
; # clear it out so we can populate properly with field-weighted, stemmed, etc. query
|
|
my $previous_operand
|
|
; # a flag used to keep track if there was a previous query
|
|
# if there was, we can apply the current operator
|
|
# for every operand
|
|
for ( my $i = 0 ; $i <= @operands ; $i++ ) {
|
|
|
|
# COMBINE OPERANDS, INDEXES AND OPERATORS
|
|
if ( $operands[$i] ) {
|
|
$operands[$i]=~s/^\s+//;
|
|
|
|
# A flag to determine whether or not to add the index to the query
|
|
my $indexes_set;
|
|
|
|
# If the user is sophisticated enough to specify an index, turn off field weighting, stemming, and stopword handling
|
|
if ( $operands[$i] =~ /\w(:|=)/ || $scan ) {
|
|
$weight_fields = 0;
|
|
$stemming = 0;
|
|
$remove_stopwords = 0;
|
|
} else {
|
|
$operands[$i] =~ s/\?/{?}/g; # need to escape question marks
|
|
}
|
|
my $operand = $operands[$i];
|
|
my $index = $indexes[$i];
|
|
|
|
# Add index-specific attributes
|
|
# Date of Publication
|
|
if ( $index eq 'yr' ) {
|
|
$index .= ",st-numeric";
|
|
$indexes_set++;
|
|
$stemming = $auto_truncation = $weight_fields = $fuzzy_enabled = $remove_stopwords = 0;
|
|
}
|
|
|
|
# Date of Acquisition
|
|
elsif ( $index eq 'acqdate' ) {
|
|
$index .= ",st-date-normalized";
|
|
$indexes_set++;
|
|
$stemming = $auto_truncation = $weight_fields = $fuzzy_enabled = $remove_stopwords = 0;
|
|
}
|
|
# ISBN,ISSN,Standard Number, don't need special treatment
|
|
elsif ( $index eq 'nb' || $index eq 'ns' ) {
|
|
(
|
|
$stemming, $auto_truncation,
|
|
$weight_fields, $fuzzy_enabled,
|
|
$remove_stopwords
|
|
) = ( 0, 0, 0, 0, 0 );
|
|
|
|
}
|
|
|
|
if(not $index){
|
|
$index = 'kw';
|
|
}
|
|
|
|
# Set default structure attribute (word list)
|
|
my $struct_attr = q{};
|
|
unless ( $indexes_set || !$index || $index =~ /(st-|phr|ext|wrdl|nb|ns)/ ) {
|
|
$struct_attr = ",wrdl";
|
|
}
|
|
|
|
# Some helpful index variants
|
|
my $index_plus = $index . $struct_attr . ':';
|
|
my $index_plus_comma = $index . $struct_attr . ',';
|
|
|
|
# Remove Stopwords
|
|
if ($remove_stopwords) {
|
|
( $operand, $stopwords_removed ) =
|
|
_remove_stopwords( $operand, $index );
|
|
warn "OPERAND w/out STOPWORDS: >$operand<" if $DEBUG;
|
|
warn "REMOVED STOPWORDS: @$stopwords_removed"
|
|
if ( $stopwords_removed && $DEBUG );
|
|
}
|
|
|
|
if ($auto_truncation){
|
|
unless ( $index =~ /(st-|phr|ext)/ ) {
|
|
#FIXME only valid with LTR scripts
|
|
$operand=join(" ",map{
|
|
(index($_,"*")>0?"$_":"$_*")
|
|
}split (/\s+/,$operand));
|
|
warn $operand if $DEBUG;
|
|
}
|
|
}
|
|
|
|
# Detect Truncation
|
|
my $truncated_operand;
|
|
my( $nontruncated, $righttruncated, $lefttruncated,
|
|
$rightlefttruncated, $regexpr
|
|
) = _detect_truncation( $operand, $index );
|
|
warn
|
|
"TRUNCATION: NON:>@$nontruncated< RIGHT:>@$righttruncated< LEFT:>@$lefttruncated< RIGHTLEFT:>@$rightlefttruncated< REGEX:>@$regexpr<"
|
|
if $DEBUG;
|
|
|
|
# Apply Truncation
|
|
if (
|
|
scalar(@$righttruncated) + scalar(@$lefttruncated) +
|
|
scalar(@$rightlefttruncated) > 0 )
|
|
{
|
|
|
|
# Don't field weight or add the index to the query, we do it here
|
|
$indexes_set = 1;
|
|
undef $weight_fields;
|
|
my $previous_truncation_operand;
|
|
if (scalar @$nontruncated) {
|
|
$truncated_operand .= "$index_plus @$nontruncated ";
|
|
$previous_truncation_operand = 1;
|
|
}
|
|
if (scalar @$righttruncated) {
|
|
$truncated_operand .= "and " if $previous_truncation_operand;
|
|
$truncated_operand .= $index_plus_comma . "rtrn:@$righttruncated ";
|
|
$previous_truncation_operand = 1;
|
|
}
|
|
if (scalar @$lefttruncated) {
|
|
$truncated_operand .= "and " if $previous_truncation_operand;
|
|
$truncated_operand .= $index_plus_comma . "ltrn:@$lefttruncated ";
|
|
$previous_truncation_operand = 1;
|
|
}
|
|
if (scalar @$rightlefttruncated) {
|
|
$truncated_operand .= "and " if $previous_truncation_operand;
|
|
$truncated_operand .= $index_plus_comma . "rltrn:@$rightlefttruncated ";
|
|
$previous_truncation_operand = 1;
|
|
}
|
|
}
|
|
$operand = $truncated_operand if $truncated_operand;
|
|
warn "TRUNCATED OPERAND: >$truncated_operand<" if $DEBUG;
|
|
|
|
# Handle Stemming
|
|
my $stemmed_operand;
|
|
$stemmed_operand = _build_stemmed_operand($operand, $lang)
|
|
if $stemming;
|
|
|
|
warn "STEMMED OPERAND: >$stemmed_operand<" if $DEBUG;
|
|
|
|
# Handle Field Weighting
|
|
my $weighted_operand;
|
|
if ($weight_fields) {
|
|
$weighted_operand = _build_weighted_query( $operand, $stemmed_operand, $index );
|
|
$operand = $weighted_operand;
|
|
$indexes_set = 1;
|
|
}
|
|
|
|
warn "FIELD WEIGHTED OPERAND: >$weighted_operand<" if $DEBUG;
|
|
|
|
# If there's a previous operand, we need to add an operator
|
|
if ($previous_operand) {
|
|
|
|
# User-specified operator
|
|
if ( $operators[ $i - 1 ] ) {
|
|
$query .= " $operators[$i-1] ";
|
|
$query .= " $index_plus " unless $indexes_set;
|
|
$query .= " $operand";
|
|
$query_cgi .= "&op=$operators[$i-1]";
|
|
$query_cgi .= "&idx=$index" if $index;
|
|
$query_cgi .= "&q=$operands[$i]" if $operands[$i];
|
|
$query_desc .=
|
|
" $operators[$i-1] $index_plus $operands[$i]";
|
|
}
|
|
|
|
# Default operator is and
|
|
else {
|
|
$query .= " and ";
|
|
$query .= "$index_plus " unless $indexes_set;
|
|
$query .= "$operand";
|
|
$query_cgi .= "&op=and&idx=$index" if $index;
|
|
$query_cgi .= "&q=$operands[$i]" if $operands[$i];
|
|
$query_desc .= " and $index_plus $operands[$i]";
|
|
}
|
|
}
|
|
|
|
# There isn't a pervious operand, don't need an operator
|
|
else {
|
|
|
|
# Field-weighted queries already have indexes set
|
|
$query .= " $index_plus " unless $indexes_set;
|
|
$query .= $operand;
|
|
$query_desc .= " $index_plus $operands[$i]";
|
|
$query_cgi .= "&idx=$index" if $index;
|
|
$query_cgi .= "&q=$operands[$i]" if $operands[$i];
|
|
$previous_operand = 1;
|
|
}
|
|
} #/if $operands
|
|
} # /for
|
|
}
|
|
warn "QUERY BEFORE LIMITS: >$query<" if $DEBUG;
|
|
|
|
# add limits
|
|
my $group_OR_limits;
|
|
my $availability_limit;
|
|
foreach my $this_limit (@limits) {
|
|
if ( $this_limit =~ /available/ ) {
|
|
#
|
|
## 'available' is defined as (items.onloan is NULL) and (items.itemlost = 0)
|
|
## In English:
|
|
## all records not indexed in the onloan register (zebra) and all records with a value of lost equal to 0
|
|
$availability_limit .=
|
|
"( ( allrecords,AlwaysMatches='' not onloan,AlwaysMatches='') and (lost,st-numeric=0) )"; #or ( allrecords,AlwaysMatches='' not lost,AlwaysMatches='')) )";
|
|
$limit_cgi .= "&limit=available";
|
|
$limit_desc .= "";
|
|
}
|
|
|
|
# group_OR_limits, prefixed by mc-
|
|
# OR every member of the group
|
|
elsif ( $this_limit =~ /mc/ ) {
|
|
|
|
if ( $this_limit =~ /mc-ccode:/ ) {
|
|
# in case the mc-ccode value has complicating chars like ()'s inside it we wrap in quotes
|
|
$this_limit =~ tr/"//d;
|
|
my ($k,$v) = split(/:/, $this_limit,2);
|
|
$this_limit = $k.":\"".$v."\"";
|
|
}
|
|
|
|
$group_OR_limits .= " or " if $group_OR_limits;
|
|
$limit_desc .= " or " if $group_OR_limits;
|
|
$group_OR_limits .= "$this_limit";
|
|
$limit_cgi .= "&limit=$this_limit";
|
|
$limit_desc .= " $this_limit";
|
|
}
|
|
|
|
# Regular old limits
|
|
else {
|
|
$limit .= " and " if $limit || $query;
|
|
$limit .= "$this_limit";
|
|
$limit_cgi .= "&limit=$this_limit";
|
|
if ($this_limit =~ /^branch:(.+)/) {
|
|
my $branchcode = $1;
|
|
my $branchname = GetBranchName($branchcode);
|
|
if (defined $branchname) {
|
|
$limit_desc .= " branch:$branchname";
|
|
} else {
|
|
$limit_desc .= " $this_limit";
|
|
}
|
|
} else {
|
|
$limit_desc .= " $this_limit";
|
|
}
|
|
}
|
|
}
|
|
if ($group_OR_limits) {
|
|
$limit .= " and " if ( $query || $limit );
|
|
$limit .= "($group_OR_limits)";
|
|
}
|
|
if ($availability_limit) {
|
|
$limit .= " and " if ( $query || $limit );
|
|
$limit .= "($availability_limit)";
|
|
}
|
|
|
|
# Normalize the query and limit strings
|
|
# This is flawed , means we can't search anything with : in it
|
|
# if user wants to do ccl or cql, start the query with that
|
|
# $query =~ s/:/=/g;
|
|
$query =~ s/(?<=(ti|au|pb|su|an|kw|mc|nb|ns)):/=/g;
|
|
$query =~ s/(?<=(wrdl)):/=/g;
|
|
$query =~ s/(?<=(trn|phr)):/=/g;
|
|
$limit =~ s/:/=/g;
|
|
for ( $query, $query_desc, $limit, $limit_desc ) {
|
|
s/ +/ /g; # remove extra spaces
|
|
s/^ //g; # remove any beginning spaces
|
|
s/ $//g; # remove any ending spaces
|
|
s/==/=/g; # remove double == from query
|
|
}
|
|
$query_cgi =~ s/^&//; # remove unnecessary & from beginning of the query cgi
|
|
|
|
for ($query_cgi,$simple_query) {
|
|
s/"//g;
|
|
}
|
|
# append the limit to the query
|
|
$query .= " " . $limit;
|
|
|
|
# Warnings if DEBUG
|
|
if ($DEBUG) {
|
|
warn "QUERY:" . $query;
|
|
warn "QUERY CGI:" . $query_cgi;
|
|
warn "QUERY DESC:" . $query_desc;
|
|
warn "LIMIT:" . $limit;
|
|
warn "LIMIT CGI:" . $limit_cgi;
|
|
warn "LIMIT DESC:" . $limit_desc;
|
|
warn "---------\nLeave buildQuery\n---------";
|
|
}
|
|
return (
|
|
undef, $query, $simple_query, $query_cgi,
|
|
$query_desc, $limit, $limit_cgi, $limit_desc,
|
|
$stopwords_removed, $query_type
|
|
);
|
|
}
|
|
|
|
=head2 searchResults
|
|
|
|
my @search_results = searchResults($search_context, $searchdesc, $hits,
|
|
$results_per_page, $offset, $scan,
|
|
@marcresults, $hidelostitems);
|
|
|
|
Format results in a form suitable for passing to the template
|
|
|
|
=cut
|
|
|
|
# IMO this subroutine is pretty messy still -- it's responsible for
|
|
# building the HTML output for the template
|
|
sub searchResults {
|
|
my ( $search_context, $searchdesc, $hits, $results_per_page, $offset, $scan, $marcresults ) = @_;
|
|
my $dbh = C4::Context->dbh;
|
|
my @newresults;
|
|
|
|
$search_context = 'opac' if !$search_context || $search_context ne 'intranet';
|
|
my ($is_opac, $hidelostitems);
|
|
if ($search_context eq 'opac') {
|
|
$hidelostitems = C4::Context->preference('hidelostitems');
|
|
$is_opac = 1;
|
|
}
|
|
|
|
#Build branchnames hash
|
|
#find branchname
|
|
#get branch information.....
|
|
my %branches;
|
|
my $bsth =$dbh->prepare("SELECT branchcode,branchname FROM branches"); # FIXME : use C4::Branch::GetBranches
|
|
$bsth->execute();
|
|
while ( my $bdata = $bsth->fetchrow_hashref ) {
|
|
$branches{ $bdata->{'branchcode'} } = $bdata->{'branchname'};
|
|
}
|
|
# FIXME - We build an authorised values hash here, using the default framework
|
|
# though it is possible to have different authvals for different fws.
|
|
|
|
my $shelflocations =GetKohaAuthorisedValues('items.location','');
|
|
|
|
# get notforloan authorised value list (see $shelflocations FIXME)
|
|
my $notforloan_authorised_value = GetAuthValCode('items.notforloan','');
|
|
|
|
#Build itemtype hash
|
|
#find itemtype & itemtype image
|
|
my %itemtypes;
|
|
$bsth =
|
|
$dbh->prepare(
|
|
"SELECT itemtype,description,imageurl,summary,notforloan FROM itemtypes"
|
|
);
|
|
$bsth->execute();
|
|
while ( my $bdata = $bsth->fetchrow_hashref ) {
|
|
foreach (qw(description imageurl summary notforloan)) {
|
|
$itemtypes{ $bdata->{'itemtype'} }->{$_} = $bdata->{$_};
|
|
}
|
|
}
|
|
|
|
#search item field code
|
|
my $sth =
|
|
$dbh->prepare(
|
|
"SELECT tagfield FROM marc_subfield_structure WHERE kohafield LIKE 'items.itemnumber'"
|
|
);
|
|
$sth->execute;
|
|
my ($itemtag) = $sth->fetchrow;
|
|
|
|
## find column names of items related to MARC
|
|
my $sth2 = $dbh->prepare("SHOW COLUMNS FROM items");
|
|
$sth2->execute;
|
|
my %subfieldstosearch;
|
|
while ( ( my $column ) = $sth2->fetchrow ) {
|
|
my ( $tagfield, $tagsubfield ) =
|
|
&GetMarcFromKohaField( "items." . $column, "" );
|
|
$subfieldstosearch{$column} = $tagsubfield;
|
|
}
|
|
|
|
# handle which records to actually retrieve
|
|
my $times;
|
|
if ( $hits && $offset + $results_per_page <= $hits ) {
|
|
$times = $offset + $results_per_page;
|
|
}
|
|
else {
|
|
$times = $hits; # FIXME: if $hits is undefined, why do we want to equal it?
|
|
}
|
|
|
|
my $marcflavour = C4::Context->preference("marcflavour");
|
|
# We get the biblionumber position in MARC
|
|
my ($bibliotag,$bibliosubf)=GetMarcFromKohaField('biblio.biblionumber','');
|
|
|
|
# loop through all of the records we've retrieved
|
|
for ( my $i = $offset ; $i <= $times - 1 ; $i++ ) {
|
|
my $marcrecord = MARC::File::USMARC::decode( $marcresults->[$i] );
|
|
my $fw = $scan
|
|
? undef
|
|
: $bibliotag < 10
|
|
? GetFrameworkCode($marcrecord->field($bibliotag)->data)
|
|
: GetFrameworkCode($marcrecord->subfield($bibliotag,$bibliosubf));
|
|
my $oldbiblio = TransformMarcToKoha( $dbh, $marcrecord, $fw );
|
|
$oldbiblio->{subtitle} = GetRecordValue('subtitle', $marcrecord, $fw);
|
|
$oldbiblio->{result_number} = $i + 1;
|
|
|
|
# add imageurl to itemtype if there is one
|
|
$oldbiblio->{imageurl} = getitemtypeimagelocation( $search_context, $itemtypes{ $oldbiblio->{itemtype} }->{imageurl} );
|
|
|
|
$oldbiblio->{'authorised_value_images'} = ($search_context eq 'opac' && C4::Context->preference('AuthorisedValueImages')) || ($search_context eq 'intranet' && C4::Context->preference('StaffAuthorisedValueImages')) ? C4::Items::get_authorised_value_images( C4::Biblio::get_biblio_authorised_values( $oldbiblio->{'biblionumber'}, $marcrecord ) ) : [];
|
|
$oldbiblio->{normalized_upc} = GetNormalizedUPC( $marcrecord,$marcflavour);
|
|
$oldbiblio->{normalized_ean} = GetNormalizedEAN( $marcrecord,$marcflavour);
|
|
$oldbiblio->{normalized_oclc} = GetNormalizedOCLCNumber($marcrecord,$marcflavour);
|
|
$oldbiblio->{normalized_isbn} = GetNormalizedISBN(undef,$marcrecord,$marcflavour);
|
|
$oldbiblio->{content_identifier_exists} = 1 if ($oldbiblio->{normalized_isbn} or $oldbiblio->{normalized_oclc} or $oldbiblio->{normalized_ean} or $oldbiblio->{normalized_upc});
|
|
|
|
# edition information, if any
|
|
$oldbiblio->{edition} = $oldbiblio->{editionstatement};
|
|
$oldbiblio->{description} = $itemtypes{ $oldbiblio->{itemtype} }->{description};
|
|
# Build summary if there is one (the summary is defined in the itemtypes table)
|
|
# FIXME: is this used anywhere, I think it can be commented out? -- JF
|
|
if ( $itemtypes{ $oldbiblio->{itemtype} }->{summary} ) {
|
|
my $summary = $itemtypes{ $oldbiblio->{itemtype} }->{summary};
|
|
my @fields = $marcrecord->fields();
|
|
|
|
my $newsummary;
|
|
foreach my $line ( "$summary\n" =~ /(.*)\n/g ){
|
|
my $tags = {};
|
|
foreach my $tag ( $line =~ /\[(\d{3}[\w|\d])\]/ ) {
|
|
$tag =~ /(.{3})(.)/;
|
|
if($marcrecord->field($1)){
|
|
my @abc = $marcrecord->field($1)->subfield($2);
|
|
$tags->{$tag} = $#abc + 1 ;
|
|
}
|
|
}
|
|
|
|
# We catch how many times to repeat this line
|
|
my $max = 0;
|
|
foreach my $tag (keys(%$tags)){
|
|
$max = $tags->{$tag} if($tags->{$tag} > $max);
|
|
}
|
|
|
|
# we replace, and repeat each line
|
|
for (my $i = 0 ; $i < $max ; $i++){
|
|
my $newline = $line;
|
|
|
|
foreach my $tag ( $newline =~ /\[(\d{3}[\w|\d])\]/g ) {
|
|
$tag =~ /(.{3})(.)/;
|
|
|
|
if($marcrecord->field($1)){
|
|
my @repl = $marcrecord->field($1)->subfield($2);
|
|
my $subfieldvalue = $repl[$i];
|
|
|
|
if (! utf8::is_utf8($subfieldvalue)) {
|
|
utf8::decode($subfieldvalue);
|
|
}
|
|
|
|
$newline =~ s/\[$tag\]/$subfieldvalue/g;
|
|
}
|
|
}
|
|
$newsummary .= "$newline\n";
|
|
}
|
|
}
|
|
|
|
$newsummary =~ s/\[(.*?)]//g;
|
|
$newsummary =~ s/\n/<br\/>/g;
|
|
$oldbiblio->{summary} = $newsummary;
|
|
}
|
|
|
|
# Pull out the items fields
|
|
my @fields = $marcrecord->field($itemtag);
|
|
my $marcflavor = C4::Context->preference("marcflavour");
|
|
# adding linked items that belong to host records
|
|
my $analyticsfield = '773';
|
|
if ($marcflavor eq 'MARC21' || $marcflavor eq 'NORMARC') {
|
|
$analyticsfield = '773';
|
|
} elsif ($marcflavor eq 'UNIMARC') {
|
|
$analyticsfield = '461';
|
|
}
|
|
foreach my $hostfield ( $marcrecord->field($analyticsfield)) {
|
|
my $hostbiblionumber = $hostfield->subfield("0");
|
|
my $linkeditemnumber = $hostfield->subfield("9");
|
|
if(!$hostbiblionumber eq undef){
|
|
my $hostbiblio = GetMarcBiblio($hostbiblionumber, 1);
|
|
my ($itemfield, undef) = GetMarcFromKohaField( 'items.itemnumber', GetFrameworkCode($hostbiblionumber) );
|
|
if(!$hostbiblio eq undef){
|
|
my @hostitems = $hostbiblio->field($itemfield);
|
|
foreach my $hostitem (@hostitems){
|
|
if ($hostitem->subfield("9") eq $linkeditemnumber){
|
|
my $linkeditem =$hostitem;
|
|
# append linked items if they exist
|
|
if (!$linkeditem eq undef){
|
|
push (@fields, $linkeditem);}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
# Setting item statuses for display
|
|
my @available_items_loop;
|
|
my @onloan_items_loop;
|
|
my @other_items_loop;
|
|
|
|
my $available_items;
|
|
my $onloan_items;
|
|
my $other_items;
|
|
|
|
my $ordered_count = 0;
|
|
my $available_count = 0;
|
|
my $onloan_count = 0;
|
|
my $longoverdue_count = 0;
|
|
my $other_count = 0;
|
|
my $wthdrawn_count = 0;
|
|
my $itemlost_count = 0;
|
|
my $hideatopac_count = 0;
|
|
my $itembinding_count = 0;
|
|
my $itemdamaged_count = 0;
|
|
my $item_in_transit_count = 0;
|
|
my $can_place_holds = 0;
|
|
my $item_onhold_count = 0;
|
|
my $items_count = scalar(@fields);
|
|
my $maxitems_pref = C4::Context->preference('maxItemsinSearchResults');
|
|
my $maxitems = $maxitems_pref ? $maxitems_pref - 1 : 1;
|
|
|
|
# loop through every item
|
|
my @hiddenitems;
|
|
foreach my $field (@fields) {
|
|
my $item;
|
|
|
|
# populate the items hash
|
|
foreach my $code ( keys %subfieldstosearch ) {
|
|
$item->{$code} = $field->subfield( $subfieldstosearch{$code} );
|
|
}
|
|
|
|
# Hidden items
|
|
if ($is_opac) {
|
|
my @hi = GetHiddenItemnumbers($item);
|
|
$item->{'hideatopac'} = @hi;
|
|
push @hiddenitems, @hi;
|
|
}
|
|
|
|
my $hbranch = C4::Context->preference('HomeOrHoldingBranch') eq 'homebranch' ? 'homebranch' : 'holdingbranch';
|
|
my $otherbranch = C4::Context->preference('HomeOrHoldingBranch') eq 'homebranch' ? 'holdingbranch' : 'homebranch';
|
|
|
|
# set item's branch name, use HomeOrHoldingBranch syspref first, fall back to the other one
|
|
if ($item->{$hbranch}) {
|
|
$item->{'branchname'} = $branches{$item->{$hbranch}};
|
|
}
|
|
elsif ($item->{$otherbranch}) { # Last resort
|
|
$item->{'branchname'} = $branches{$item->{$otherbranch}};
|
|
}
|
|
|
|
my $prefix = $item->{$hbranch} . '--' . $item->{location} . $item->{itype} . $item->{itemcallnumber};
|
|
# For each grouping of items (onloan, available, unavailable), we build a key to store relevant info about that item
|
|
my $userenv = C4::Context->userenv;
|
|
if ( $item->{onloan} && !(C4::Members::GetHideLostItemsPreference($userenv->{'number'}) && $item->{itemlost}) ) {
|
|
$onloan_count++;
|
|
my $key = $prefix . $item->{onloan} . $item->{barcode};
|
|
$onloan_items->{$key}->{due_date} = format_date($item->{onloan});
|
|
$onloan_items->{$key}->{count}++ if $item->{$hbranch};
|
|
$onloan_items->{$key}->{branchname} = $item->{branchname};
|
|
$onloan_items->{$key}->{location} = $shelflocations->{ $item->{location} };
|
|
$onloan_items->{$key}->{itemcallnumber} = $item->{itemcallnumber};
|
|
$onloan_items->{$key}->{imageurl} = getitemtypeimagelocation( $search_context, $itemtypes{ $item->{itype} }->{imageurl} );
|
|
# if something's checked out and lost, mark it as 'long overdue'
|
|
if ( $item->{itemlost} ) {
|
|
$onloan_items->{$prefix}->{longoverdue}++;
|
|
$longoverdue_count++;
|
|
} else { # can place holds as long as item isn't lost
|
|
$can_place_holds = 1;
|
|
}
|
|
}
|
|
|
|
# items not on loan, but still unavailable ( lost, withdrawn, damaged )
|
|
else {
|
|
|
|
# item is on order
|
|
if ( $item->{notforloan} == -1 ) {
|
|
$ordered_count++;
|
|
}
|
|
|
|
# is item in transit?
|
|
my $transfertwhen = '';
|
|
my ($transfertfrom, $transfertto);
|
|
|
|
# is item on the reserve shelf?
|
|
my $reservestatus = '';
|
|
my $reserveitem;
|
|
|
|
unless ($item->{wthdrawn}
|
|
|| $item->{itemlost}
|
|
|| $item->{damaged}
|
|
|| $item->{notforloan}
|
|
|| $items_count > 20) {
|
|
|
|
# A couple heuristics to limit how many times
|
|
# we query the database for item transfer information, sacrificing
|
|
# accuracy in some cases for speed;
|
|
#
|
|
# 1. don't query if item has one of the other statuses
|
|
# 2. don't check transit status if the bib has
|
|
# more than 20 items
|
|
#
|
|
# FIXME: to avoid having the query the database like this, and to make
|
|
# the in transit status count as unavailable for search limiting,
|
|
# should map transit status to record indexed in Zebra.
|
|
#
|
|
($transfertwhen, $transfertfrom, $transfertto) = C4::Circulation::GetTransfers($item->{itemnumber});
|
|
($reservestatus, $reserveitem, undef) = C4::Reserves::CheckReserves($item->{itemnumber});
|
|
}
|
|
|
|
# item is withdrawn, lost, damaged, not for loan, reserved or in transit
|
|
if ( $item->{wthdrawn}
|
|
|| $item->{itemlost}
|
|
|| $item->{damaged}
|
|
|| $item->{notforloan} > 0
|
|
|| $item->{hideatopac}
|
|
|| $reservestatus eq 'Waiting'
|
|
|| ($transfertwhen ne ''))
|
|
{
|
|
$wthdrawn_count++ if $item->{wthdrawn};
|
|
$itemlost_count++ if $item->{itemlost};
|
|
$itemdamaged_count++ if $item->{damaged};
|
|
$hideatopac_count++ if $item->{hideatopac};
|
|
$item_in_transit_count++ if $transfertwhen ne '';
|
|
$item_onhold_count++ if $reservestatus eq 'Waiting';
|
|
$item->{status} = $item->{wthdrawn} . "-" . $item->{itemlost} . "-" . $item->{damaged} . "-" . $item->{notforloan};
|
|
|
|
# can place hold on item ?
|
|
if ((!$item->{damaged} || C4::Context->preference('AllowHoldsOnDamagedItems'))
|
|
&& !$item->{itemlost}
|
|
&& !$item->{withdrawn}
|
|
) {
|
|
$can_place_holds = 1;
|
|
}
|
|
|
|
$other_count++;
|
|
|
|
my $key = $prefix . $item->{status};
|
|
foreach (qw(wthdrawn itemlost damaged branchname itemcallnumber hideatopac)) {
|
|
$other_items->{$key}->{$_} = $item->{$_};
|
|
}
|
|
$other_items->{$key}->{intransit} = ( $transfertwhen ne '' ) ? 1 : 0;
|
|
$other_items->{$key}->{onhold} = ($reservestatus) ? 1 : 0;
|
|
$other_items->{$key}->{notforloan} = GetAuthorisedValueDesc('','',$item->{notforloan},'','',$notforloan_authorised_value) if $notforloan_authorised_value;
|
|
$other_items->{$key}->{count}++ if $item->{$hbranch};
|
|
$other_items->{$key}->{location} = $shelflocations->{ $item->{location} };
|
|
$other_items->{$key}->{imageurl} = getitemtypeimagelocation( $search_context, $itemtypes{ $item->{itype} }->{imageurl} );
|
|
}
|
|
# item is available
|
|
else {
|
|
$can_place_holds = 1;
|
|
$available_count++;
|
|
$available_items->{$prefix}->{count}++ if $item->{$hbranch};
|
|
foreach (qw(branchname itemcallnumber hideatopac)) {
|
|
$available_items->{$prefix}->{$_} = $item->{$_};
|
|
}
|
|
$available_items->{$prefix}->{location} = $shelflocations->{ $item->{location} };
|
|
$available_items->{$prefix}->{imageurl} = getitemtypeimagelocation( $search_context, $itemtypes{ $item->{itype} }->{imageurl} );
|
|
}
|
|
}
|
|
} # notforloan, item level and biblioitem level
|
|
if ($items_count > 0) {
|
|
next if $is_opac && $hideatopac_count >= $items_count;
|
|
next if $hidelostitems && $itemlost_count >= $items_count;
|
|
}
|
|
my ( $availableitemscount, $onloanitemscount, $otheritemscount );
|
|
for my $key ( sort keys %$onloan_items ) {
|
|
(++$onloanitemscount > $maxitems) and last;
|
|
push @onloan_items_loop, $onloan_items->{$key};
|
|
}
|
|
for my $key ( sort keys %$other_items ) {
|
|
(++$otheritemscount > $maxitems) and last;
|
|
push @other_items_loop, $other_items->{$key};
|
|
}
|
|
for my $key ( sort keys %$available_items ) {
|
|
(++$availableitemscount > $maxitems) and last;
|
|
push @available_items_loop, $available_items->{$key}
|
|
}
|
|
|
|
# XSLT processing of some stuff
|
|
use C4::Charset;
|
|
SetUTF8Flag($marcrecord);
|
|
$debug && warn $marcrecord->as_formatted;
|
|
my $interface = $search_context eq 'opac' ? 'OPAC' : '';
|
|
if (!$scan && C4::Context->preference($interface . "XSLTResultsDisplay")) {
|
|
$oldbiblio->{XSLTResultsRecord} = XSLTParse4Display($oldbiblio->{biblionumber}, $marcrecord, 'Results',
|
|
$search_context, 1, \@hiddenitems);
|
|
# the last parameter tells Koha to clean up the problematic ampersand entities that Zebra outputs
|
|
}
|
|
|
|
# if biblio level itypes are used and itemtype is notforloan, it can't be reserved either
|
|
if (!C4::Context->preference("item-level_itypes")) {
|
|
if ($itemtypes{ $oldbiblio->{itemtype} }->{notforloan}) {
|
|
$can_place_holds = 0;
|
|
}
|
|
}
|
|
$oldbiblio->{norequests} = 1 unless $can_place_holds;
|
|
$oldbiblio->{itemsplural} = 1 if $items_count > 1;
|
|
$oldbiblio->{items_count} = $items_count;
|
|
$oldbiblio->{available_items_loop} = \@available_items_loop;
|
|
$oldbiblio->{onloan_items_loop} = \@onloan_items_loop;
|
|
$oldbiblio->{other_items_loop} = \@other_items_loop;
|
|
$oldbiblio->{availablecount} = $available_count;
|
|
$oldbiblio->{availableplural} = 1 if $available_count > 1;
|
|
$oldbiblio->{onloancount} = $onloan_count;
|
|
$oldbiblio->{onloanplural} = 1 if $onloan_count > 1;
|
|
$oldbiblio->{othercount} = $other_count;
|
|
$oldbiblio->{otherplural} = 1 if $other_count > 1;
|
|
$oldbiblio->{wthdrawncount} = $wthdrawn_count;
|
|
$oldbiblio->{itemlostcount} = $itemlost_count;
|
|
$oldbiblio->{damagedcount} = $itemdamaged_count;
|
|
$oldbiblio->{intransitcount} = $item_in_transit_count;
|
|
$oldbiblio->{onholdcount} = $item_onhold_count;
|
|
$oldbiblio->{orderedcount} = $ordered_count;
|
|
# deleting - in isbn to enable amazon content
|
|
$oldbiblio->{isbn} =~ s/-//g;
|
|
|
|
if (C4::Context->preference("AlternateHoldingsField") && $items_count == 0) {
|
|
my $fieldspec = C4::Context->preference("AlternateHoldingsField");
|
|
my $subfields = substr $fieldspec, 3;
|
|
my $holdingsep = C4::Context->preference("AlternateHoldingsSeparator") || ' ';
|
|
my @alternateholdingsinfo = ();
|
|
my @holdingsfields = $marcrecord->field(substr $fieldspec, 0, 3);
|
|
my $alternateholdingscount = 0;
|
|
|
|
for my $field (@holdingsfields) {
|
|
my %holding = ( holding => '' );
|
|
my $havesubfield = 0;
|
|
for my $subfield ($field->subfields()) {
|
|
if ((index $subfields, $$subfield[0]) >= 0) {
|
|
$holding{'holding'} .= $holdingsep if (length $holding{'holding'} > 0);
|
|
$holding{'holding'} .= $$subfield[1];
|
|
$havesubfield++;
|
|
}
|
|
}
|
|
if ($havesubfield) {
|
|
push(@alternateholdingsinfo, \%holding);
|
|
$alternateholdingscount++;
|
|
}
|
|
}
|
|
|
|
$oldbiblio->{'ALTERNATEHOLDINGS'} = \@alternateholdingsinfo;
|
|
$oldbiblio->{'alternateholdings_count'} = $alternateholdingscount;
|
|
}
|
|
|
|
push( @newresults, $oldbiblio );
|
|
}
|
|
|
|
return @newresults;
|
|
}
|
|
|
|
=head2 SearchAcquisitions
|
|
Search for acquisitions
|
|
=cut
|
|
|
|
sub SearchAcquisitions{
|
|
my ($datebegin, $dateend, $itemtypes,$criteria, $orderby) = @_;
|
|
|
|
my $dbh=C4::Context->dbh;
|
|
# Variable initialization
|
|
my $str=qq|
|
|
SELECT marcxml
|
|
FROM biblio
|
|
LEFT JOIN biblioitems ON biblioitems.biblionumber=biblio.biblionumber
|
|
LEFT JOIN items ON items.biblionumber=biblio.biblionumber
|
|
WHERE dateaccessioned BETWEEN ? AND ?
|
|
|;
|
|
|
|
my (@params,@loopcriteria);
|
|
|
|
push @params, $datebegin->output("iso");
|
|
push @params, $dateend->output("iso");
|
|
|
|
if (scalar(@$itemtypes)>0 and $criteria ne "itemtype" ){
|
|
if(C4::Context->preference("item-level_itypes")){
|
|
$str .= "AND items.itype IN (?".( ',?' x scalar @$itemtypes - 1 ).") ";
|
|
}else{
|
|
$str .= "AND biblioitems.itemtype IN (?".( ',?' x scalar @$itemtypes - 1 ).") ";
|
|
}
|
|
push @params, @$itemtypes;
|
|
}
|
|
|
|
if ($criteria =~/itemtype/){
|
|
if(C4::Context->preference("item-level_itypes")){
|
|
$str .= "AND items.itype=? ";
|
|
}else{
|
|
$str .= "AND biblioitems.itemtype=? ";
|
|
}
|
|
|
|
if(scalar(@$itemtypes) == 0){
|
|
my $itypes = GetItemTypes();
|
|
for my $key (keys %$itypes){
|
|
push @$itemtypes, $key;
|
|
}
|
|
}
|
|
|
|
@loopcriteria= @$itemtypes;
|
|
}elsif ($criteria=~/itemcallnumber/){
|
|
$str .= "AND (items.itemcallnumber LIKE CONCAT(?,'%')
|
|
OR items.itemcallnumber is NULL
|
|
OR items.itemcallnumber = '')";
|
|
|
|
@loopcriteria = ("AA".."ZZ", "") unless (scalar(@loopcriteria)>0);
|
|
}else {
|
|
$str .= "AND biblio.title LIKE CONCAT(?,'%') ";
|
|
@loopcriteria = ("A".."z") unless (scalar(@loopcriteria)>0);
|
|
}
|
|
|
|
if ($orderby =~ /date_desc/){
|
|
$str.=" ORDER BY dateaccessioned DESC";
|
|
} else {
|
|
$str.=" ORDER BY title";
|
|
}
|
|
|
|
my $qdataacquisitions=$dbh->prepare($str);
|
|
|
|
my @loopacquisitions;
|
|
foreach my $value(@loopcriteria){
|
|
push @params,$value;
|
|
my %cell;
|
|
$cell{"title"}=$value;
|
|
$cell{"titlecode"}=$value;
|
|
|
|
eval{$qdataacquisitions->execute(@params);};
|
|
|
|
if ($@){ warn "recentacquisitions Error :$@";}
|
|
else {
|
|
my @loopdata;
|
|
while (my $data=$qdataacquisitions->fetchrow_hashref){
|
|
push @loopdata, {"summary"=>GetBiblioSummary( $data->{'marcxml'} ) };
|
|
}
|
|
$cell{"loopdata"}=\@loopdata;
|
|
}
|
|
push @loopacquisitions,\%cell if (scalar(@{$cell{loopdata}})>0);
|
|
pop @params;
|
|
}
|
|
$qdataacquisitions->finish;
|
|
return \@loopacquisitions;
|
|
}
|
|
#----------------------------------------------------------------------
|
|
#
|
|
# Non-Zebra GetRecords#
|
|
#----------------------------------------------------------------------
|
|
|
|
=head2 NZgetRecords
|
|
|
|
NZgetRecords has the same API as zera getRecords, even if some parameters are not managed
|
|
|
|
=cut
|
|
|
|
sub NZgetRecords {
|
|
my (
|
|
$query, $simple_query, $sort_by_ref, $servers_ref,
|
|
$results_per_page, $offset, $expanded_facet, $branches,
|
|
$query_type, $scan
|
|
) = @_;
|
|
warn "query =$query" if $DEBUG;
|
|
my $result = NZanalyse($query);
|
|
warn "results =$result" if $DEBUG;
|
|
return ( undef,
|
|
NZorder( $result, @$sort_by_ref[0], $results_per_page, $offset ),
|
|
undef );
|
|
}
|
|
|
|
=head2 NZanalyse
|
|
|
|
NZanalyse : get a CQL string as parameter, and returns a list of biblionumber;title,biblionumber;title,...
|
|
the list is built from an inverted index in the nozebra SQL table
|
|
note that title is here only for convenience : the sorting will be very fast when requested on title
|
|
if the sorting is requested on something else, we will have to reread all results, and that may be longer.
|
|
|
|
=cut
|
|
|
|
sub NZanalyse {
|
|
my ( $string, $server ) = @_;
|
|
# warn "---------" if $DEBUG;
|
|
warn " NZanalyse" if $DEBUG;
|
|
# warn "---------" if $DEBUG;
|
|
|
|
# $server contains biblioserver or authorities, depending on what we search on.
|
|
#warn "querying : $string on $server";
|
|
$server = 'biblioserver' unless $server;
|
|
|
|
# if we have a ", replace the content to discard temporarily any and/or/not inside
|
|
my $commacontent;
|
|
if ( $string =~ /"/ ) {
|
|
$string =~ s/"(.*?)"/__X__/;
|
|
$commacontent = $1;
|
|
warn "commacontent : $commacontent" if $DEBUG;
|
|
}
|
|
|
|
# split the query string in 3 parts : X AND Y means : $left="X", $operand="AND" and $right="Y"
|
|
# then, call again NZanalyse with $left and $right
|
|
# (recursive until we find a leaf (=> something without and/or/not)
|
|
# delete repeated operator... Would then go in infinite loop
|
|
while ( $string =~ s/( and| or| not| AND| OR| NOT)\1/$1/g ) {
|
|
}
|
|
|
|
#process parenthesis before.
|
|
if ( $string =~ /^\s*\((.*)\)(( and | or | not | AND | OR | NOT )(.*))?/ ) {
|
|
my $left = $1;
|
|
my $right = $4;
|
|
my $operator = lc($3); # FIXME: and/or/not are operators, not operands
|
|
warn
|
|
"dealing w/parenthesis before recursive sub call. left :$left operator:$operator right:$right"
|
|
if $DEBUG;
|
|
my $leftresult = NZanalyse( $left, $server );
|
|
if ($operator) {
|
|
my $rightresult = NZanalyse( $right, $server );
|
|
|
|
# OK, we have the results for right and left part of the query
|
|
# depending of operand, intersect, union or exclude both lists
|
|
# to get a result list
|
|
if ( $operator eq ' and ' ) {
|
|
return NZoperatorAND($leftresult,$rightresult);
|
|
}
|
|
elsif ( $operator eq ' or ' ) {
|
|
|
|
# just merge the 2 strings
|
|
return $leftresult . $rightresult;
|
|
}
|
|
elsif ( $operator eq ' not ' ) {
|
|
return NZoperatorNOT($leftresult,$rightresult);
|
|
}
|
|
}
|
|
else {
|
|
# this error is impossible, because of the regexp that isolate the operand, but just in case...
|
|
return $leftresult;
|
|
}
|
|
}
|
|
warn "string :" . $string if $DEBUG;
|
|
my $left = "";
|
|
my $right = "";
|
|
my $operator = "";
|
|
if ($string =~ /(.*?)( and | or | not | AND | OR | NOT )(.*)/) {
|
|
$left = $1;
|
|
$right = $3;
|
|
$operator = lc($2); # FIXME: and/or/not are operators, not operands
|
|
}
|
|
warn "no parenthesis. left : $left operator: $operator right: $right"
|
|
if $DEBUG;
|
|
|
|
# it's not a leaf, we have a and/or/not
|
|
if ($operator) {
|
|
|
|
# reintroduce comma content if needed
|
|
$right =~ s/__X__/"$commacontent"/ if $commacontent;
|
|
$left =~ s/__X__/"$commacontent"/ if $commacontent;
|
|
warn "node : $left / $operator / $right\n" if $DEBUG;
|
|
my $leftresult = NZanalyse( $left, $server );
|
|
my $rightresult = NZanalyse( $right, $server );
|
|
warn " leftresult : $leftresult" if $DEBUG;
|
|
warn " rightresult : $rightresult" if $DEBUG;
|
|
# OK, we have the results for right and left part of the query
|
|
# depending of operand, intersect, union or exclude both lists
|
|
# to get a result list
|
|
if ( $operator eq ' and ' ) {
|
|
return NZoperatorAND($leftresult,$rightresult);
|
|
}
|
|
elsif ( $operator eq ' or ' ) {
|
|
|
|
# just merge the 2 strings
|
|
return $leftresult . $rightresult;
|
|
}
|
|
elsif ( $operator eq ' not ' ) {
|
|
return NZoperatorNOT($leftresult,$rightresult);
|
|
}
|
|
else {
|
|
|
|
# this error is impossible, because of the regexp that isolate the operand, but just in case...
|
|
die "error : operand unknown : $operator for $string";
|
|
}
|
|
|
|
# it's a leaf, do the real SQL query and return the result
|
|
}
|
|
else {
|
|
$string =~ s/__X__/"$commacontent"/ if $commacontent;
|
|
$string =~ s/-|\.|\?|,|;|!|'|\(|\)|\[|\]|{|}|"|&|\+|\*|\// /g;
|
|
#remove trailing blank at the beginning
|
|
$string =~ s/^ //g;
|
|
warn "leaf:$string" if $DEBUG;
|
|
|
|
# parse the string in in operator/operand/value again
|
|
my $left = "";
|
|
my $operator = "";
|
|
my $right = "";
|
|
if ($string =~ /(.*)(>=|<=)(.*)/) {
|
|
$left = $1;
|
|
$operator = $2;
|
|
$right = $3;
|
|
} else {
|
|
$left = $string;
|
|
}
|
|
# warn "handling leaf... left:$left operator:$operator right:$right"
|
|
# if $DEBUG;
|
|
unless ($operator) {
|
|
if ($string =~ /(.*)(>|<|=)(.*)/) {
|
|
$left = $1;
|
|
$operator = $2;
|
|
$right = $3;
|
|
warn
|
|
"handling unless (operator)... left:$left operator:$operator right:$right"
|
|
if $DEBUG;
|
|
} else {
|
|
$left = $string;
|
|
}
|
|
}
|
|
my $results;
|
|
|
|
# strip adv, zebra keywords, currently not handled in nozebra: wrdl, ext, phr...
|
|
$left =~ s/ .*$//;
|
|
|
|
# automatic replace for short operators
|
|
$left = 'title' if $left =~ '^ti$';
|
|
$left = 'author' if $left =~ '^au$';
|
|
$left = 'publisher' if $left =~ '^pb$';
|
|
$left = 'subject' if $left =~ '^su$';
|
|
$left = 'koha-Auth-Number' if $left =~ '^an$';
|
|
$left = 'keyword' if $left =~ '^kw$';
|
|
$left = 'itemtype' if $left =~ '^mc$'; # Fix for Bug 2599 - Search limits not working for NoZebra
|
|
warn "handling leaf... left:$left operator:$operator right:$right" if $DEBUG;
|
|
my $dbh = C4::Context->dbh;
|
|
if ( $operator && $left ne 'keyword' ) {
|
|
#do a specific search
|
|
$operator = 'LIKE' if $operator eq '=' and $right =~ /%/;
|
|
my $sth = $dbh->prepare(
|
|
"SELECT biblionumbers,value FROM nozebra WHERE server=? AND indexname=? AND value $operator ?"
|
|
);
|
|
warn "$left / $operator / $right\n" if $DEBUG;
|
|
|
|
# split each word, query the DB and build the biblionumbers result
|
|
#sanitizing leftpart
|
|
$left =~ s/^\s+|\s+$//;
|
|
foreach ( split / /, $right ) {
|
|
my $biblionumbers;
|
|
$_ =~ s/^\s+|\s+$//;
|
|
next unless $_;
|
|
warn "EXECUTE : $server, $left, $_" if $DEBUG;
|
|
$sth->execute( $server, $left, $_ )
|
|
or warn "execute failed: $!";
|
|
while ( my ( $line, $value ) = $sth->fetchrow ) {
|
|
|
|
# if we are dealing with a numeric value, use only numeric results (in case of >=, <=, > or <)
|
|
# otherwise, fill the result
|
|
$biblionumbers .= $line
|
|
unless ( $right =~ /^\d+$/ && $value =~ /\D/ );
|
|
warn "result : $value "
|
|
. ( $right =~ /\d/ ) . "=="
|
|
. ( $value =~ /\D/?$line:"" ) if $DEBUG; #= $line";
|
|
}
|
|
|
|
# do a AND with existing list if there is one, otherwise, use the biblionumbers list as 1st result list
|
|
if ($results) {
|
|
warn "NZAND" if $DEBUG;
|
|
$results = NZoperatorAND($biblionumbers,$results);
|
|
} else {
|
|
$results = $biblionumbers;
|
|
}
|
|
}
|
|
}
|
|
else {
|
|
#do a complete search (all indexes), if index='kw' do complete search too.
|
|
my $sth = $dbh->prepare(
|
|
"SELECT biblionumbers FROM nozebra WHERE server=? AND value LIKE ?"
|
|
);
|
|
|
|
# split each word, query the DB and build the biblionumbers result
|
|
foreach ( split / /, $string ) {
|
|
next if C4::Context->stopwords->{ uc($_) }; # skip if stopword
|
|
warn "search on all indexes on $_" if $DEBUG;
|
|
my $biblionumbers;
|
|
next unless $_;
|
|
$sth->execute( $server, $_ );
|
|
while ( my $line = $sth->fetchrow ) {
|
|
$biblionumbers .= $line;
|
|
}
|
|
|
|
# do a AND with existing list if there is one, otherwise, use the biblionumbers list as 1st result list
|
|
if ($results) {
|
|
$results = NZoperatorAND($biblionumbers,$results);
|
|
}
|
|
else {
|
|
warn "NEW RES for $_ = $biblionumbers" if $DEBUG;
|
|
$results = $biblionumbers;
|
|
}
|
|
}
|
|
}
|
|
warn "return : $results for LEAF : $string" if $DEBUG;
|
|
return $results;
|
|
}
|
|
warn "---------\nLeave NZanalyse\n---------" if $DEBUG;
|
|
}
|
|
|
|
sub NZoperatorAND{
|
|
my ($rightresult, $leftresult)=@_;
|
|
|
|
my @leftresult = split /;/, $leftresult;
|
|
warn " @leftresult / $rightresult \n" if $DEBUG;
|
|
|
|
# my @rightresult = split /;/,$leftresult;
|
|
my $finalresult;
|
|
|
|
# parse the left results, and if the biblionumber exist in the right result, save it in finalresult
|
|
# the result is stored twice, to have the same weight for AND than OR.
|
|
# example : TWO : 61,61,64,121 (two is twice in the biblio #61) / TOWER : 61,64,130
|
|
# result : 61,61,61,61,64,64 for two AND tower : 61 has more weight than 64
|
|
foreach (@leftresult) {
|
|
my $value = $_;
|
|
my $countvalue;
|
|
( $value, $countvalue ) = ( $1, $2 ) if ($value=~/(.*)-(\d+)$/);
|
|
if ( $rightresult =~ /\Q$value\E-(\d+);/ ) {
|
|
$countvalue = ( $1 > $countvalue ? $countvalue : $1 );
|
|
$finalresult .=
|
|
"$value-$countvalue;$value-$countvalue;";
|
|
}
|
|
}
|
|
warn "NZAND DONE : $finalresult \n" if $DEBUG;
|
|
return $finalresult;
|
|
}
|
|
|
|
sub NZoperatorOR{
|
|
my ($rightresult, $leftresult)=@_;
|
|
return $rightresult.$leftresult;
|
|
}
|
|
|
|
sub NZoperatorNOT{
|
|
my ($leftresult, $rightresult)=@_;
|
|
|
|
my @leftresult = split /;/, $leftresult;
|
|
|
|
# my @rightresult = split /;/,$leftresult;
|
|
my $finalresult;
|
|
foreach (@leftresult) {
|
|
my $value=$_;
|
|
$value=$1 if $value=~m/(.*)-\d+$/;
|
|
unless ($rightresult =~ "$value-") {
|
|
$finalresult .= "$_;";
|
|
}
|
|
}
|
|
return $finalresult;
|
|
}
|
|
|
|
=head2 NZorder
|
|
|
|
$finalresult = NZorder($biblionumbers, $ordering,$results_per_page,$offset);
|
|
|
|
TODO :: Description
|
|
|
|
=cut
|
|
|
|
sub NZorder {
|
|
my ( $biblionumbers, $ordering, $results_per_page, $offset ) = @_;
|
|
warn "biblionumbers = $biblionumbers and ordering = $ordering\n" if $DEBUG;
|
|
|
|
# order title asc by default
|
|
# $ordering = '1=36 <i' unless $ordering;
|
|
$results_per_page = 20 unless $results_per_page;
|
|
$offset = 0 unless $offset;
|
|
my $dbh = C4::Context->dbh;
|
|
|
|
#
|
|
# order by POPULARITY
|
|
#
|
|
if ( $ordering =~ /popularity/ ) {
|
|
my %result;
|
|
my %popularity;
|
|
|
|
# popularity is not in MARC record, it's builded from a specific query
|
|
my $sth =
|
|
$dbh->prepare("select sum(issues) from items where biblionumber=?");
|
|
foreach ( split /;/, $biblionumbers ) {
|
|
my ( $biblionumber, $title ) = split /,/, $_;
|
|
$result{$biblionumber} = GetMarcBiblio($biblionumber);
|
|
$sth->execute($biblionumber);
|
|
my $popularity = $sth->fetchrow || 0;
|
|
|
|
# hint : the key is popularity.title because we can have
|
|
# many results with the same popularity. In this case, sub-ordering is done by title
|
|
# we also have biblionumber to avoid bug for 2 biblios with the same title & popularity
|
|
# (un-frequent, I agree, but we won't forget anything that way ;-)
|
|
$popularity{ sprintf( "%10d", $popularity ) . $title
|
|
. $biblionumber } = $biblionumber;
|
|
}
|
|
|
|
# sort the hash and return the same structure as GetRecords (Zebra querying)
|
|
my $result_hash;
|
|
my $numbers = 0;
|
|
if ( $ordering eq 'popularity_dsc' ) { # sort popularity DESC
|
|
foreach my $key ( sort { $b cmp $a } ( keys %popularity ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{ $popularity{$key} }->as_usmarc();
|
|
}
|
|
}
|
|
else { # sort popularity ASC
|
|
foreach my $key ( sort ( keys %popularity ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{ $popularity{$key} }->as_usmarc();
|
|
}
|
|
}
|
|
my $finalresult = ();
|
|
$result_hash->{'hits'} = $numbers;
|
|
$finalresult->{'biblioserver'} = $result_hash;
|
|
return $finalresult;
|
|
|
|
#
|
|
# ORDER BY author
|
|
#
|
|
}
|
|
elsif ( $ordering =~ /author/ ) {
|
|
my %result;
|
|
foreach ( split /;/, $biblionumbers ) {
|
|
my ( $biblionumber, $title ) = split /,/, $_;
|
|
my $record = GetMarcBiblio($biblionumber);
|
|
my $author;
|
|
if ( C4::Context->preference('marcflavour') eq 'UNIMARC' ) {
|
|
$author = $record->subfield( '200', 'f' );
|
|
$author = $record->subfield( '700', 'a' ) unless $author;
|
|
}
|
|
else {
|
|
$author = $record->subfield( '100', 'a' );
|
|
}
|
|
|
|
# hint : the result is sorted by title.biblionumber because we can have X biblios with the same title
|
|
# and we don't want to get only 1 result for each of them !!!
|
|
$result{ $author . $biblionumber } = $record;
|
|
}
|
|
|
|
# sort the hash and return the same structure as GetRecords (Zebra querying)
|
|
my $result_hash;
|
|
my $numbers = 0;
|
|
if ( $ordering eq 'author_za' || $ordering eq 'author_dsc' ) { # sort by author desc
|
|
foreach my $key ( sort { $b cmp $a } ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{$key}->as_usmarc();
|
|
}
|
|
}
|
|
else { # sort by author ASC
|
|
foreach my $key ( sort ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{$key}->as_usmarc();
|
|
}
|
|
}
|
|
my $finalresult = ();
|
|
$result_hash->{'hits'} = $numbers;
|
|
$finalresult->{'biblioserver'} = $result_hash;
|
|
return $finalresult;
|
|
|
|
#
|
|
# ORDER BY callnumber
|
|
#
|
|
}
|
|
elsif ( $ordering =~ /callnumber/ ) {
|
|
my %result;
|
|
foreach ( split /;/, $biblionumbers ) {
|
|
my ( $biblionumber, $title ) = split /,/, $_;
|
|
my $record = GetMarcBiblio($biblionumber);
|
|
my $callnumber;
|
|
my $frameworkcode = GetFrameworkCode($biblionumber);
|
|
my ( $callnumber_tag, $callnumber_subfield ) = GetMarcFromKohaField( 'items.itemcallnumber', $frameworkcode);
|
|
( $callnumber_tag, $callnumber_subfield ) = GetMarcFromKohaField('biblioitems.callnumber', $frameworkcode)
|
|
unless $callnumber_tag;
|
|
if ( C4::Context->preference('marcflavour') eq 'UNIMARC' ) {
|
|
$callnumber = $record->subfield( '200', 'f' );
|
|
} else {
|
|
$callnumber = $record->subfield( '100', 'a' );
|
|
}
|
|
|
|
# hint : the result is sorted by title.biblionumber because we can have X biblios with the same title
|
|
# and we don't want to get only 1 result for each of them !!!
|
|
$result{ $callnumber . $biblionumber } = $record;
|
|
}
|
|
|
|
# sort the hash and return the same structure as GetRecords (Zebra querying)
|
|
my $result_hash;
|
|
my $numbers = 0;
|
|
if ( $ordering eq 'call_number_dsc' ) { # sort by title desc
|
|
foreach my $key ( sort { $b cmp $a } ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{$key}->as_usmarc();
|
|
}
|
|
}
|
|
else { # sort by title ASC
|
|
foreach my $key ( sort { $a cmp $b } ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{$key}->as_usmarc();
|
|
}
|
|
}
|
|
my $finalresult = ();
|
|
$result_hash->{'hits'} = $numbers;
|
|
$finalresult->{'biblioserver'} = $result_hash;
|
|
return $finalresult;
|
|
}
|
|
elsif ( $ordering =~ /pubdate/ ) { #pub year
|
|
my %result;
|
|
foreach ( split /;/, $biblionumbers ) {
|
|
my ( $biblionumber, $title ) = split /,/, $_;
|
|
my $record = GetMarcBiblio($biblionumber);
|
|
my ( $publicationyear_tag, $publicationyear_subfield ) =
|
|
GetMarcFromKohaField( 'biblioitems.publicationyear', '' );
|
|
my $publicationyear =
|
|
$record->subfield( $publicationyear_tag,
|
|
$publicationyear_subfield );
|
|
|
|
# hint : the result is sorted by title.biblionumber because we can have X biblios with the same title
|
|
# and we don't want to get only 1 result for each of them !!!
|
|
$result{ $publicationyear . $biblionumber } = $record;
|
|
}
|
|
|
|
# sort the hash and return the same structure as GetRecords (Zebra querying)
|
|
my $result_hash;
|
|
my $numbers = 0;
|
|
if ( $ordering eq 'pubdate_dsc' ) { # sort by pubyear desc
|
|
foreach my $key ( sort { $b cmp $a } ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{$key}->as_usmarc();
|
|
}
|
|
}
|
|
else { # sort by pub year ASC
|
|
foreach my $key ( sort ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] =
|
|
$result{$key}->as_usmarc();
|
|
}
|
|
}
|
|
my $finalresult = ();
|
|
$result_hash->{'hits'} = $numbers;
|
|
$finalresult->{'biblioserver'} = $result_hash;
|
|
return $finalresult;
|
|
|
|
#
|
|
# ORDER BY title
|
|
#
|
|
}
|
|
elsif ( $ordering =~ /title/ ) {
|
|
|
|
# the title is in the biblionumbers string, so we just need to build a hash, sort it and return
|
|
my %result;
|
|
foreach ( split /;/, $biblionumbers ) {
|
|
my ( $biblionumber, $title ) = split /,/, $_;
|
|
|
|
# hint : the result is sorted by title.biblionumber because we can have X biblios with the same title
|
|
# and we don't want to get only 1 result for each of them !!!
|
|
# hint & speed improvement : we can order without reading the record
|
|
# so order, and read records only for the requested page !
|
|
$result{ $title . $biblionumber } = $biblionumber;
|
|
}
|
|
|
|
# sort the hash and return the same structure as GetRecords (Zebra querying)
|
|
my $result_hash;
|
|
my $numbers = 0;
|
|
if ( $ordering eq 'title_az' ) { # sort by title desc
|
|
foreach my $key ( sort ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] = $result{$key};
|
|
}
|
|
}
|
|
else { # sort by title ASC
|
|
foreach my $key ( sort { $b cmp $a } ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] = $result{$key};
|
|
}
|
|
}
|
|
|
|
# limit the $results_per_page to result size if it's more
|
|
$results_per_page = $numbers - 1 if $numbers < $results_per_page;
|
|
|
|
# for the requested page, replace biblionumber by the complete record
|
|
# speed improvement : avoid reading too much things
|
|
for (
|
|
my $counter = $offset ;
|
|
$counter <= $offset + $results_per_page ;
|
|
$counter++
|
|
)
|
|
{
|
|
$result_hash->{'RECORDS'}[$counter] =
|
|
GetMarcBiblio( $result_hash->{'RECORDS'}[$counter] )->as_usmarc;
|
|
}
|
|
my $finalresult = ();
|
|
$result_hash->{'hits'} = $numbers;
|
|
$finalresult->{'biblioserver'} = $result_hash;
|
|
return $finalresult;
|
|
}
|
|
else {
|
|
|
|
#
|
|
# order by ranking
|
|
#
|
|
# we need 2 hashes to order by ranking : the 1st one to count the ranking, the 2nd to order by ranking
|
|
my %result;
|
|
my %count_ranking;
|
|
foreach ( split /;/, $biblionumbers ) {
|
|
my ( $biblionumber, $title ) = split /,/, $_;
|
|
$title =~ /(.*)-(\d)/;
|
|
|
|
# get weight
|
|
my $ranking = $2;
|
|
|
|
# note that we + the ranking because ranking is calculated on weight of EACH term requested.
|
|
# if we ask for "two towers", and "two" has weight 2 in biblio N, and "towers" has weight 4 in biblio N
|
|
# biblio N has ranking = 6
|
|
$count_ranking{$biblionumber} += $ranking;
|
|
}
|
|
|
|
# build the result by "inverting" the count_ranking hash
|
|
# hing : as usual, we don't order by ranking only, to avoid having only 1 result for each rank. We build an hash on concat(ranking,biblionumber) instead
|
|
# warn "counting";
|
|
foreach ( keys %count_ranking ) {
|
|
$result{ sprintf( "%10d", $count_ranking{$_} ) . '-' . $_ } = $_;
|
|
}
|
|
|
|
# sort the hash and return the same structure as GetRecords (Zebra querying)
|
|
my $result_hash;
|
|
my $numbers = 0;
|
|
foreach my $key ( sort { $b cmp $a } ( keys %result ) ) {
|
|
$result_hash->{'RECORDS'}[ $numbers++ ] = $result{$key};
|
|
}
|
|
|
|
# limit the $results_per_page to result size if it's more
|
|
$results_per_page = $numbers - 1 if $numbers < $results_per_page;
|
|
|
|
# for the requested page, replace biblionumber by the complete record
|
|
# speed improvement : avoid reading too much things
|
|
for (
|
|
my $counter = $offset ;
|
|
$counter <= $offset + $results_per_page ;
|
|
$counter++
|
|
)
|
|
{
|
|
$result_hash->{'RECORDS'}[$counter] =
|
|
GetMarcBiblio( $result_hash->{'RECORDS'}[$counter] )->as_usmarc
|
|
if $result_hash->{'RECORDS'}[$counter];
|
|
}
|
|
my $finalresult = ();
|
|
$result_hash->{'hits'} = $numbers;
|
|
$finalresult->{'biblioserver'} = $result_hash;
|
|
return $finalresult;
|
|
}
|
|
}
|
|
|
|
=head2 enabled_staff_search_views
|
|
|
|
%hash = enabled_staff_search_views()
|
|
|
|
This function returns a hash that contains three flags obtained from the system
|
|
preferences, used to determine whether a particular staff search results view
|
|
is enabled.
|
|
|
|
=over 2
|
|
|
|
=item C<Output arg:>
|
|
|
|
* $hash{can_view_MARC} is true only if the MARC view is enabled
|
|
* $hash{can_view_ISBD} is true only if the ISBD view is enabled
|
|
* $hash{can_view_labeledMARC} is true only if the Labeled MARC view is enabled
|
|
|
|
=item C<usage in the script:>
|
|
|
|
=back
|
|
|
|
$template->param ( C4::Search::enabled_staff_search_views );
|
|
|
|
=cut
|
|
|
|
sub enabled_staff_search_views
|
|
{
|
|
return (
|
|
can_view_MARC => C4::Context->preference('viewMARC'), # 1 if the staff search allows the MARC view
|
|
can_view_ISBD => C4::Context->preference('viewISBD'), # 1 if the staff search allows the ISBD view
|
|
can_view_labeledMARC => C4::Context->preference('viewLabeledMARC'), # 1 if the staff search allows the Labeled MARC view
|
|
);
|
|
}
|
|
|
|
sub AddSearchHistory{
|
|
my ($borrowernumber,$session,$query_desc,$query_cgi, $total)=@_;
|
|
my $dbh = C4::Context->dbh;
|
|
|
|
# Add the request the user just made
|
|
my $sql = "INSERT INTO search_history(userid, sessionid, query_desc, query_cgi, total, time) VALUES(?, ?, ?, ?, ?, NOW())";
|
|
my $sth = $dbh->prepare($sql);
|
|
$sth->execute($borrowernumber, $session, $query_desc, $query_cgi, $total);
|
|
return $dbh->last_insert_id(undef, 'search_history', undef,undef,undef);
|
|
}
|
|
|
|
sub GetSearchHistory{
|
|
my ($borrowernumber,$session)=@_;
|
|
my $dbh = C4::Context->dbh;
|
|
|
|
# Add the request the user just made
|
|
my $query = "SELECT FROM search_history WHERE (userid=? OR sessionid=?)";
|
|
my $sth = $dbh->prepare($query);
|
|
$sth->execute($borrowernumber, $session);
|
|
return $sth->fetchall_hashref({});
|
|
}
|
|
|
|
=head2 z3950_search_args
|
|
|
|
$arrayref = z3950_search_args($matchpoints)
|
|
|
|
This function returns an array reference that contains the search parameters to be
|
|
passed to the Z39.50 search script (z3950_search.pl). The array elements
|
|
are hash refs whose keys are name, value and encvalue, and whose values are the
|
|
name of a search parameter, the value of that search parameter and the URL encoded
|
|
value of that parameter.
|
|
|
|
The search parameter names are lccn, isbn, issn, title, author, dewey and subject.
|
|
|
|
The search parameter values are obtained from the bibliographic record whose
|
|
data is in a hash reference in $matchpoints, as returned by Biblio::GetBiblioData().
|
|
|
|
If $matchpoints is a scalar, it is assumed to be an unnamed query descriptor, e.g.
|
|
a general purpose search argument. In this case, the returned array contains only
|
|
entry: the key is 'title' and the value and encvalue are derived from $matchpoints.
|
|
|
|
If a search parameter value is undefined or empty, it is not included in the returned
|
|
array.
|
|
|
|
The returned array reference may be passed directly to the template parameters.
|
|
|
|
=over 2
|
|
|
|
=item C<Output arg:>
|
|
|
|
* $array containing hash refs as described above
|
|
|
|
=item C<usage in the script:>
|
|
|
|
=back
|
|
|
|
$data = Biblio::GetBiblioData($bibno);
|
|
$template->param ( MYLOOP => C4::Search::z3950_search_args($data) )
|
|
|
|
*OR*
|
|
|
|
$template->param ( MYLOOP => C4::Search::z3950_search_args($searchscalar) )
|
|
|
|
=cut
|
|
|
|
sub z3950_search_args {
|
|
my $bibrec = shift;
|
|
my $isbn = Business::ISBN->new($bibrec);
|
|
|
|
if (defined $isbn && $isbn->is_valid)
|
|
{
|
|
$bibrec = { isbn => $bibrec } if !ref $bibrec;
|
|
}
|
|
else {
|
|
$bibrec = { title => $bibrec } if !ref $bibrec;
|
|
}
|
|
my $array = [];
|
|
for my $field (qw/ lccn isbn issn title author dewey subject /)
|
|
{
|
|
my $encvalue = URI::Escape::uri_escape_utf8($bibrec->{$field});
|
|
push @$array, { name=>$field, value=>$bibrec->{$field}, encvalue=>$encvalue } if defined $bibrec->{$field};
|
|
}
|
|
return $array;
|
|
}
|
|
|
|
=head2 GetDistinctValues($field);
|
|
|
|
C<$field> is a reference to the fields array
|
|
|
|
=cut
|
|
|
|
sub GetDistinctValues {
|
|
my ($fieldname,$string)=@_;
|
|
# returns a reference to a hash of references to branches...
|
|
if ($fieldname=~/\./){
|
|
my ($table,$column)=split /\./, $fieldname;
|
|
my $dbh = C4::Context->dbh;
|
|
warn "select DISTINCT($column) as value, count(*) as cnt from $table group by lib order by $column " if $DEBUG;
|
|
my $sth = $dbh->prepare("select DISTINCT($column) as value, count(*) as cnt from $table ".($string?" where $column like \"$string%\"":"")."group by value order by $column ");
|
|
$sth->execute;
|
|
my $elements=$sth->fetchall_arrayref({});
|
|
return $elements;
|
|
}
|
|
else {
|
|
$string||= qq("");
|
|
my @servers=qw<biblioserver authorityserver>;
|
|
my (@zconns,@results);
|
|
for ( my $i = 0 ; $i < @servers ; $i++ ) {
|
|
$zconns[$i] = C4::Context->Zconn( $servers[$i], 1 );
|
|
$results[$i] =
|
|
$zconns[$i]->scan(
|
|
ZOOM::Query::CCL2RPN->new( qq"$fieldname $string", $zconns[$i])
|
|
);
|
|
}
|
|
# The big moment: asynchronously retrieve results from all servers
|
|
my @elements;
|
|
while ( ( my $i = ZOOM::event( \@zconns ) ) != 0 ) {
|
|
my $ev = $zconns[ $i - 1 ]->last_event();
|
|
if ( $ev == ZOOM::Event::ZEND ) {
|
|
next unless $results[ $i - 1 ];
|
|
my $size = $results[ $i - 1 ]->size();
|
|
if ( $size > 0 ) {
|
|
for (my $j=0;$j<$size;$j++){
|
|
my %hashscan;
|
|
@hashscan{qw(value cnt)}=$results[ $i - 1 ]->display_term($j);
|
|
push @elements, \%hashscan;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return \@elements;
|
|
}
|
|
}
|
|
|
|
|
|
END { } # module clean-up code here (global destructor)
|
|
|
|
1;
|
|
__END__
|
|
|
|
=head1 AUTHOR
|
|
|
|
Koha Development Team <http://koha-community.org/>
|
|
|
|
=cut
|