Browse Source
Removed NoZebra vestiges. This comprises several code blocks that depend on the NoZebra syspref and NZ related functions/methods. C4::Biblio-> GetNoZebraIndexes _DelBiblioNoZebra _AddBiblioNoZebra C4::Search-> NZgetRecords NZanalyse NZoperatorAND NZoperatorOR NZoperatorNOT NZorder C4::Installer-> set_indexing_engine Sponsored-by: Universidad Nacional de Córdoba Signed-off-by: Julian Maurice <julian.maurice@biblibre.com> Signed-off-by: Paul Poulain <paul.poulain@biblibre.com> Signed-off-by: Jared Camins-Esakov <jcamins@cpbibliography.com>3.12.x
Jared Camins-Esakov
30 changed files with 289 additions and 2175 deletions
@ -1,343 +0,0 @@ |
|||
#!/usr/bin/perl |
|||
|
|||
use C4::Context; |
|||
use Getopt::Long; |
|||
use C4::Biblio; |
|||
use C4::AuthoritiesMarc; |
|||
|
|||
use strict; |
|||
#use warnings; FIXME - Bug 2505 |
|||
# |
|||
# script that fills the nozebra table |
|||
# |
|||
# |
|||
|
|||
$|=1; # flushes output |
|||
|
|||
# limit for database dumping |
|||
my $limit;# = "LIMIT 100"; |
|||
my $directory; |
|||
#my $skip_export; |
|||
#my $keep_export; |
|||
#my $reset; |
|||
#my $biblios; |
|||
my $authorities; |
|||
my $sysprefs; |
|||
my $commit; |
|||
my $want_help; |
|||
|
|||
my $result = GetOptions( |
|||
'd:s' => \$directory, |
|||
# 'reset' => \$reset, |
|||
# 's' => \$skip_export, # Not used and conflicts with 's' option some lines below for sysprefs!!! |
|||
# 'k' => \$keep_export, |
|||
# 'b' => \$biblios, |
|||
# 'a' => \$authorities, |
|||
's' => \$sysprefs, # rebuild 'NoZebraIndexes' syspref |
|||
'h|help' => \$want_help, |
|||
'commit:f' => \$commit, |
|||
); |
|||
|
|||
if (not $result or $want_help) { |
|||
print_usage(); |
|||
exit 0; |
|||
} |
|||
|
|||
|
|||
sub print_usage { |
|||
print <<_USAGE_; |
|||
$0: reindex MARC bibs and authorities if NOT using Zebra ("NoZebra"). |
|||
|
|||
Use this batch job to reindex all biblio and authority |
|||
records in your Koha database. This job is useful |
|||
only if you are NOT using Zebra ('NoZebra'); if you are |
|||
using the 'Zebra'mode, this job should NOT be used. |
|||
|
|||
Parameters: |
|||
-d Temporary directory for indexing. |
|||
If not specified, one is automatically |
|||
created. The export directory |
|||
is automatically deleted unless |
|||
you supply the -k switch. |
|||
|
|||
-s Rebuild "NoZebraIndexes" System Preference |
|||
|
|||
--help or -h show this message. |
|||
_USAGE_ |
|||
} # END of print_usage sub |
|||
|
|||
|
|||
my $commitnum = 1000; |
|||
$commitnum = $commit if ($commit) ; |
|||
|
|||
$directory = "export" unless $directory; |
|||
my $dbh=C4::Context->dbh; |
|||
$dbh->do("update systempreferences set value=1 where variable='NoZebra'"); |
|||
|
|||
$dbh->do("truncate nozebra"); |
|||
|
|||
my %index = GetNoZebraIndexes(); |
|||
|
|||
if (!%index || $sysprefs ) { |
|||
if (C4::Context->preference('marcflavour') eq 'UNIMARC') { |
|||
$dbh->do("UPDATE systempreferences SET value=\"'title' => '200a,200c,200d,200e,225a,225d,225e,225f,225h,225i,225v,500*,501*,503*,510*,512*,513*,514*,515*,516*,517*,518*,519*,520*,530*,531*,532*,540*,541*,545*,604t,610t,605a', |
|||
'author' =>'200f,600a,601a,604a,700a,700b,700c,700d,700a,701b,701c,701d,702a,702b,702c,702d,710a,710b,710c,710d,711a,711b,711c,711d,712a,712b,712c,712d', |
|||
'isbn' => '010a', |
|||
'issn' => '011a', |
|||
'biblionumber' =>'0909', |
|||
'itemtype' => '200b', |
|||
'language' => '101a', |
|||
'publisher' => '210c', |
|||
'date' => '210d', |
|||
'note' => '300a,301a,302a,303a,304a,305a,306az,307a,308a,309a,310a,311a,312a,313a,314a,315a,316a,317a,318a,319a,320a,321a,322a,323a,324a,325a,326a,327a,328a,330a,332a,333a,336a,337a,345a', |
|||
'Koha-Auth-Number' => '6009,6019,6029,6039,6049,6059,6069,6109,7009,7019,7029,7109,7119,7129', |
|||
'subject' => '600*,601*,606*,610*', |
|||
'dewey' => '676a', |
|||
'host-item' => '995a,995c',\" where variable='NoZebraIndexes'"); |
|||
%index = GetNoZebraIndexes(); |
|||
} elsif (C4::Context->preference('marcflavour') eq 'MARC21') { |
|||
$dbh->do("UPDATE systempreferences SET value=\" |
|||
'title' => '130a,210a,222a,240a,243a,245a,245b,246a,246b,247a,247b,250a,250b,440a,830a', |
|||
'author' => '100a,100b,100c,100d,110a,111a,111b,111c,111d,245c,700a,710a,711a,800a,810a,811a', |
|||
'isbn' => '020a', |
|||
'issn' => '022a', |
|||
'lccn' => '010a', |
|||
'biblionumber => '999c', |
|||
'itemtype' => '942c', |
|||
'publisher' => '260b', |
|||
'date' => '260c', |
|||
'note' => '500a, 501a,504a,505a,508a,511a,518a,520a,521a,522a,524a,526a,530a,533a,538a,541a,546a,555a,556a,562a,563a,583a,585a,582a', |
|||
'subject' => '600*,610*,611*,630*,650*,651*,653*,654*,655*,662*,690*', |
|||
'dewey' => '082', |
|||
'bc' => '952p', |
|||
'callnum' => '952o', |
|||
'an' => '6009,6109,6119', |
|||
'series' => 440*,490*, |
|||
'host-item' => '9529 |
|||
'shelf' => '952c', |
|||
'collection' => '9528', |
|||
\"WHERE variable='NoZebraIndexes'"); |
|||
|
|||
%index = GetNoZebraIndexes(); |
|||
} |
|||
} |
|||
$|=1; |
|||
|
|||
$dbh->{AutoCommit} = 0; |
|||
|
|||
print "***********************************\n"; |
|||
print "***** building BIBLIO indexes *****\n"; |
|||
print "***********************************\n"; |
|||
|
|||
my $sth; |
|||
$sth=$dbh->prepare("select biblionumber from biblioitems order by biblionumber $limit"); |
|||
$sth->execute(); |
|||
my $i=0; |
|||
my %result; |
|||
while (my ($biblionumber) = $sth->fetchrow) { |
|||
$i++; |
|||
print "\r$i"; |
|||
my $record; |
|||
eval{ |
|||
$record = GetMarcBiblio($biblionumber); |
|||
}; |
|||
if($@){ |
|||
print " There was some pb getting biblionumber : ".$biblionumber."\n"; |
|||
next; |
|||
} |
|||
next unless $record; |
|||
# get title of the record (to store the 10 first letters with the index) |
|||
my ($titletag,$titlesubfield) = GetMarcFromKohaField('biblio.title', ''); |
|||
my $title = lc($record->subfield($titletag,$titlesubfield)); |
|||
|
|||
# remove blancks comma (that could cause problem when decoding the string for CQL retrieval) and regexp specific values |
|||
$title =~ s/ |\.|,|;|\[|\]|\(|\)|\*|-|'|=|://g; |
|||
# limit to 10 char, should be enough, and limit the DB size |
|||
$title = substr($title,0,10); |
|||
#parse each field |
|||
foreach my $field ($record->fields()) { |
|||
#parse each subfield |
|||
next if $field->tag <10; |
|||
foreach my $subfield ($field->subfields()) { |
|||
my $tag = $field->tag(); |
|||
my $subfieldcode = $subfield->[0]; |
|||
my $indexed=0; |
|||
# check each index to see if the subfield is stored somewhere |
|||
# otherwise, store it in __RAW__ index |
|||
foreach my $key (keys %index) { |
|||
if ($index{$key} =~ /\Q$tag\E\*/ or $index{$key} =~ /\Q$tag$subfieldcode\E/) { |
|||
$indexed=1; |
|||
my $line= lc $subfield->[1]; |
|||
# remove meaningless value in the field... |
|||
$line =~ s/-|\.|\?|,|;|!|'|\(|\)|\[|\]|{|}|"|<|>|&|\+|\*|\/|=|:/ /g; |
|||
# ... and split in words |
|||
foreach (split / /,$line) { |
|||
next unless $_; # skip empty values (multiple spaces) |
|||
# remove any accented char |
|||
# if the entry is already here, improve weight |
|||
if ($result{$key}->{"$_"} =~ /$biblionumber,\Q$title\E\-(\d);/) { |
|||
my $weight=$1+1; |
|||
$result{$key}->{"$_"} =~ s/$biblionumber,\Q$title\E\-(\d);//; |
|||
$result{$key}->{"$_"} .= "$biblionumber,$title-$weight;"; |
|||
# otherwise, create it, with weight=1 |
|||
} else { |
|||
$result{$key}->{"$_"}.="$biblionumber,$title-1;"; |
|||
} |
|||
} |
|||
} |
|||
} |
|||
# the subfield is not indexed, store it in __RAW__ index anyway |
|||
unless ($indexed) { |
|||
my $line= lc $subfield->[1]; |
|||
$line =~ s/-|\.|\?|,|;|!|'|\(|\)|\[|\]|{|}|"|<|>|&|\+|\*|\/|=/ /g; |
|||
foreach (split / /,$line) { |
|||
next unless $_; |
|||
# warn $record->as_formatted."$_ =>".$title; |
|||
if ($result{__RAW__}->{"$_"} =~ /$biblionumber,\Q$title\E\-(\d);/) { |
|||
my $weight=$1+1; |
|||
# $weight++; |
|||
$result{__RAW__}->{"$_"} =~ s/$biblionumber,\Q$title\E\-(\d);//; |
|||
$result{__RAW__}->{"$_"} .= "$biblionumber,$title-$weight;"; |
|||
} else { |
|||
$result{__RAW__}->{"$_"}.="$biblionumber,$title-1;"; |
|||
} |
|||
} |
|||
} |
|||
} |
|||
} |
|||
} |
|||
|
|||
|
|||
print "\nInserting records...\n"; |
|||
$i=0; |
|||
|
|||
my $commitnum = 100; |
|||
$dbh->{AutoCommit} = 0; |
|||
|
|||
$sth = $dbh->prepare("INSERT INTO nozebra (server,indexname,value,biblionumbers) VALUES ('biblioserver',?,?,?)"); |
|||
foreach my $key (keys %result) { |
|||
foreach my $index (keys %{$result{$key}}) { |
|||
if (length($result{$key}->{$index}) > 1000000) { |
|||
print "very long index (".length($result{$key}->{$index}).")for $key / $index. update mySQL config file if you have an error just after this warning (max_paquet_size parameter)\n"; |
|||
} |
|||
print "\r$i"; |
|||
$i++; |
|||
$sth->execute($key,$index,$result{$key}->{$index}); |
|||
$dbh->commit() if (0 == $i % $commitnum); |
|||
} |
|||
$dbh->commit() if (0 == $i % $commitnum); |
|||
} |
|||
$dbh->commit; |
|||
|
|||
|
|||
print "\nbiblios done\n"; |
|||
|
|||
print "\n***********************************\n"; |
|||
print "***** building AUTHORITIES indexes *****\n"; |
|||
print "***********************************\n"; |
|||
|
|||
$sth=$dbh->prepare("select authid from auth_header order by authid $limit"); |
|||
$sth->execute(); |
|||
$i=0; |
|||
%result = (); |
|||
while (my ($authid) = $sth->fetchrow) { |
|||
$i++; |
|||
print "\r$i"; |
|||
my $record; |
|||
eval{ |
|||
$record = GetAuthority($authid); |
|||
}; |
|||
if($@){ |
|||
print " There was some pb getting authnumber : ".$authid."\n"; |
|||
next; |
|||
} |
|||
|
|||
my %index; |
|||
# for authorities, the "title" is the $a mainentry |
|||
my $authref = C4::AuthoritiesMarc::GetAuthType(C4::AuthoritiesMarc::GetAuthTypeCode($authid)); |
|||
|
|||
warn "ERROR : authtype undefined for ".$record->as_formatted unless $authref; |
|||
my $title = $record->subfield($authref->{auth_tag_to_report},'a'); |
|||
$index{'mainmainentry'}= $authref->{'auth_tag_to_report'}.'a'; |
|||
$index{'mainentry'} = $authref->{'auth_tag_to_report'}.'*'; |
|||
$index{'auth_type'} = '152b'; |
|||
|
|||
# remove blancks comma (that could cause problem when decoding the string for CQL retrieval) and regexp specific values |
|||
$title =~ s/ |\.|,|;|\[|\]|\(|\)|\*|-|'|:|=//g; |
|||
$title = quotemeta $title; |
|||
# limit to 10 char, should be enough, and limit the DB size |
|||
$title = substr($title,0,10); |
|||
#parse each field |
|||
foreach my $field ($record->fields()) { |
|||
#parse each subfield |
|||
next if $field->tag <10; |
|||
foreach my $subfield ($field->subfields()) { |
|||
my $tag = $field->tag(); |
|||
my $subfieldcode = $subfield->[0]; |
|||
my $indexed=0; |
|||
# check each index to see if the subfield is stored somewhere |
|||
# otherwise, store it in __RAW__ index |
|||
foreach my $key (keys %index) { |
|||
if ($index{$key} =~ /$tag\*/ or $index{$key} =~ /$tag$subfieldcode/) { |
|||
$indexed=1; |
|||
my $line= lc $subfield->[1]; |
|||
# remove meaningless value in the field... |
|||
$line =~ s/-|\.|\?|,|;|!|'|\(|\)|\[|\]|{|}|"|<|>|&|\+|\*|\/|=|:/ /g; |
|||
# ... and split in words |
|||
foreach (split / /,$line) { |
|||
next unless $_; # skip empty values (multiple spaces) |
|||
# if the entry is already here, improve weight |
|||
if ($result{$key}->{"$_"} =~ /$authid,$title\-(\d);/) { |
|||
my $weight=$1+1; |
|||
$result{$key}->{"$_"} =~ s/$authid,$title\-(\d);//; |
|||
$result{$key}->{"$_"} .= "$authid,$title-$weight;"; |
|||
# otherwise, create it, with weight=1 |
|||
} else { |
|||
$result{$key}->{"$_"}.="$authid,$title-1;"; |
|||
} |
|||
} |
|||
} |
|||
} |
|||
# the subfield is not indexed, store it in __RAW__ index anyway |
|||
unless ($indexed) { |
|||
my $line= lc $subfield->[1]; |
|||
$line =~ s/-|\.|\?|,|;|!|'|\(|\)|\[|\]|{|}|"|<|>|&|\+|\*|\/|=/ /g; |
|||
foreach (split / /,$line) { |
|||
next unless $_; |
|||
# warn $record->as_formatted."$_ =>".$title; |
|||
if ($result{__RAW__}->{"$_"} =~ /$authid,$title\-(\d);/) { |
|||
my $weight=$1+1; |
|||
# $weight++; |
|||
$result{__RAW__}->{"$_"} =~ s/$authid,$title\-(\d);//; |
|||
$result{__RAW__}->{"$_"} .= "$authid,$title-$weight;"; |
|||
} else { |
|||
$result{__RAW__}->{"$_"}.="$authid,$title-1;"; |
|||
} |
|||
} |
|||
} |
|||
} |
|||
} |
|||
} |
|||
|
|||
|
|||
|
|||
print "\nInserting...\n"; |
|||
$i=0; |
|||
|
|||
my $commitnum = 100; |
|||
$dbh->{AutoCommit} = 0; |
|||
$sth = $dbh->prepare("INSERT INTO nozebra (server,indexname,value,biblionumbers) VALUES ('authorityserver',?,?,?)"); |
|||
foreach my $key (keys %result) { |
|||
foreach my $index (keys %{$result{$key}}) { |
|||
if (length($result{$key}->{$index}) > 1000000) { |
|||
print "very long index (".length($result{$key}->{$index}).")for $key / $index. update mySQL config file if you have an error just after this warning (max_paquet_size parameter)\n"; |
|||
} |
|||
print "\r$i"; |
|||
$i++; |
|||
$sth->execute($key,$index,$result{$key}->{$index}); |
|||
$dbh->commit() if (0 == $i % $commitnum); |
|||
} |
|||
$dbh->commit() if (0 == $i % $commitnum); |
|||
} |
|||
$dbh->commit; |
|||
print "\nauthorities done\n"; |
|||
@ -1,72 +0,0 @@ |
|||
package KohaTest::Biblio::GetNoZebraIndexes; |
|||
use base qw( KohaTest::Biblio ); |
|||
|
|||
use strict; |
|||
use warnings; |
|||
|
|||
use Test::More; |
|||
|
|||
use C4::Biblio; |
|||
|
|||
=head2 STARTUP METHODS |
|||
|
|||
These get run once, before the main test methods in this module |
|||
|
|||
=cut |
|||
|
|||
|
|||
=head2 TEST METHODS |
|||
|
|||
standard test methods |
|||
|
|||
=head3 |
|||
|
|||
=cut |
|||
|
|||
sub returns_expected_hashref : Test(2) { |
|||
my $self = shift; |
|||
|
|||
my %nzi = C4::Biblio::GetNoZebraIndexes(); |
|||
ok( scalar keys %nzi, 'got some keys from GetNoZebraIndexes' ); |
|||
|
|||
my %expected = ( |
|||
'title' => '130a,210a,222a,240a,243a,245a,245b,246a,246b,247a,247b,250a,250b,440a,830a', |
|||
'author' => '100a,100b,100c,100d,110a,111a,111b,111c,111d,245c,700a,710a,711a,800a,810a,811a', |
|||
'isbn' => '020a', |
|||
'issn' => '022a', |
|||
'lccn' => '010a', |
|||
'biblionumber' => '999c', |
|||
'itemtype' => '942c', |
|||
'publisher' => '260b', |
|||
'date' => '260c', |
|||
'note' => '500a,501a,504a,505a,508a,511a,518a,520a,521a,522a,524a,526a,530a,533a,538a,541a,546a,555a,556a,562a,563a,583a,585a,582a', |
|||
'subject' => '600*,610*,611*,630*,650*,651*,653*,654*,655*,662*,690*', |
|||
'dewey' => '082', |
|||
'bc' => '952p', |
|||
'callnum' => '952o', |
|||
'an' => '6009,6109,6119', |
|||
'homebranch' => '952a,952c' |
|||
); |
|||
is_deeply( \%nzi, \%expected, 'GetNoZebraIndexes returns the expected hashref' ); |
|||
} |
|||
|
|||
=head2 HELPER METHODS |
|||
|
|||
These methods are used by other test methods, but |
|||
are not meant to be called directly. |
|||
|
|||
=cut |
|||
|
|||
=cut |
|||
|
|||
|
|||
=head2 SHUTDOWN METHODS |
|||
|
|||
These get run once, after the main test methods in this module |
|||
|
|||
=head3 |
|||
|
|||
=cut |
|||
|
|||
|
|||
1; |
|||
@ -1,235 +0,0 @@ |
|||
package KohaTest::Search::NoZebra; |
|||
use base qw( KohaTest::Search ); |
|||
|
|||
use strict; |
|||
use warnings; |
|||
|
|||
use Test::More; |
|||
|
|||
use MARC::Record; |
|||
|
|||
use C4::Search; |
|||
use C4::Biblio; |
|||
use C4::Context; |
|||
|
|||
=head2 STARTUP METHODS |
|||
|
|||
These get run once, before the main test methods in this module |
|||
|
|||
=cut |
|||
|
|||
=head3 startup_50_init_nozebra |
|||
|
|||
Turn on NoZebra mode, for now, assumes and requires |
|||
that the test database has started out using Zebra. |
|||
|
|||
=cut |
|||
|
|||
sub startup_50_init_nozebra : Test( startup => 3 ) { |
|||
my $using_nozebra = C4::Context->preference('NoZebra'); |
|||
ok(!$using_nozebra, "starting out using Zebra"); |
|||
my $dbh = C4::Context->dbh; |
|||
$dbh->do("UPDATE systempreferences SET value=1 WHERE variable='NoZebra'"); |
|||
$dbh->do("UPDATE systempreferences SET value=0 WHERE variable in ('QueryFuzzy','QueryWeightFields','QueryStemming')"); |
|||
C4::Context->clear_syspref_cache(); |
|||
$using_nozebra = C4::Context->preference('NoZebra'); |
|||
ok($using_nozebra, "switched to NoZebra"); |
|||
|
|||
my $sth = $dbh->prepare("SELECT COUNT(*) FROM nozebra"); |
|||
$sth->execute; |
|||
my ($count) = $sth->fetchrow_array; |
|||
$sth->finish; |
|||
cmp_ok($count, '==', 0, "NoZebra index starts off empty"); |
|||
} |
|||
|
|||
sub startup_51_add_bibs : Test( startup => 2 ) { |
|||
my $self = shift; |
|||
|
|||
my $bib1 = MARC::Record->new(); |
|||
$bib1->leader(' nam a22 7a 4500'); |
|||
$bib1->append_fields( |
|||
MARC::Field->new('010', ' ', ' ', a => 'lccn001'), |
|||
MARC::Field->new('020', ' ', ' ', a => 'isbn001'), |
|||
MARC::Field->new('022', ' ', ' ', a => 'issn001'), |
|||
MARC::Field->new('100', ' ', ' ', a => 'Cat, Felix T.'), |
|||
MARC::Field->new('245', ' ', ' ', a => 'Of mice and men :', b=> 'a history'), |
|||
); |
|||
my $bib2 = MARC::Record->new(); |
|||
$bib2->leader(' nam a22 7a 4500'); |
|||
$bib2->append_fields( |
|||
MARC::Field->new('010', ' ', ' ', a => 'lccn002'), |
|||
MARC::Field->new('020', ' ', ' ', a => 'isbn002'), |
|||
MARC::Field->new('022', ' ', ' ', a => 'issn002'), |
|||
MARC::Field->new('100', ' ', ' ', a => 'Dog, Rover T.'), |
|||
MARC::Field->new('245', ' ', ' ', a => 'Of mice and men :', b=> 'a digression'), |
|||
); |
|||
|
|||
my $dbh = C4::Context->dbh; |
|||
my $count_sth = $dbh->prepare("SELECT COUNT(*) FROM nozebra"); |
|||
my $count; |
|||
my ($bib1_bibnum, $bib1_bibitemnum) = AddBiblio($bib1, ''); |
|||
$count_sth->execute; |
|||
($count) = $count_sth->fetchrow_array; |
|||
cmp_ok($count, '==', 14, "correct number of new words indexed"); # tokens + biblionumber + __RAW__ |
|||
|
|||
my ($bib2_bibnum, $bib2_bibitemnum) = AddBiblio($bib2, ''); |
|||
$count_sth->execute; |
|||
($count) = $count_sth->fetchrow_array; |
|||
cmp_ok($count, '==', 22, "correct number of new words indexed"); # tokens + biblionumber + __RAW__ |
|||
|
|||
push @{ $self->{nozebra_test_bibs} }, $bib1_bibnum, $bib2_bibnum; |
|||
} |
|||
|
|||
=head2 TEST METHODS |
|||
|
|||
Standard test methods |
|||
|
|||
=cut |
|||
|
|||
sub basic_searches_via_nzanalyze : Test( 28 ) { |
|||
my $self = shift; |
|||
my ($bib1_bibnum, $bib2_bibnum) = @{ $self->{nozebra_test_bibs} }; |
|||
|
|||
my $results = C4::Search::NZanalyse('foobar'); |
|||
ok(!defined($results), "no hits on 'foobar'"); |
|||
|
|||
$results = C4::Search::NZanalyse('dog'); |
|||
my ($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 1, "one hit on 'dog'"); |
|||
is($bib2_bibnum, $bibnumbers[0], "correct hit on 'dog'"); |
|||
|
|||
$results = C4::Search::NZanalyse('au=dog'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 1, "one hit on 'au=dog'"); |
|||
is($bib2_bibnum, $bibnumbers[0], "correct hit on 'au=dog'"); |
|||
|
|||
$results = C4::Search::NZanalyse('isbn=dog'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 0, "zero hits on 'isbn=dog'"); |
|||
|
|||
$results = C4::Search::NZanalyse('cat'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 1, "one hit on 'cat'"); |
|||
is($bib1_bibnum, $bibnumbers[0], "correct hit on 'cat'"); |
|||
|
|||
$results = C4::Search::NZanalyse('cat and dog'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 0, "zero hits on 'cat and dog'"); |
|||
|
|||
$results = C4::Search::NZanalyse('cat or dog'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 2, "two hits on 'cat or dog'"); |
|||
is_deeply([ sort @bibnumbers ], [ sort($bib1_bibnum, $bib2_bibnum) ], "correct hits on 'cat or dog'"); |
|||
|
|||
$results = C4::Search::NZanalyse('mice and men'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 2, "two hits on 'mice and men'"); |
|||
is_deeply([ sort @bibnumbers ], [ sort($bib1_bibnum, $bib2_bibnum) ], "correct hits on 'mice and men'"); |
|||
|
|||
$results = C4::Search::NZanalyse('title=digression or issn=issn001'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 2, "two hits on 'title=digression or issn=issn001'"); |
|||
is_deeply([ sort @bibnumbers ], [ sort($bib1_bibnum, $bib2_bibnum) ], "correct hits on 'title=digression or issn=issn001'"); |
|||
|
|||
$results = C4::Search::NZanalyse('title=digression and issn=issn002'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 1, "two hits on 'title=digression and issn=issn002'"); |
|||
is($bib2_bibnum, $bibnumbers[0], "correct hit on 'title=digression and issn=issn002'"); |
|||
|
|||
$results = C4::Search::NZanalyse('mice not men'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 0, "zero hits on 'mice not men'"); |
|||
|
|||
$results = C4::Search::NZanalyse('mice not dog'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 1, "one hit on 'mice not dog'"); |
|||
is($bib1_bibnum, $bibnumbers[0], "correct hit on 'mice not dog'"); |
|||
|
|||
$results = C4::Search::NZanalyse('isbn > a'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 2, "two hits on 'isbn > a'"); |
|||
is_deeply([ sort @bibnumbers ], [ sort($bib1_bibnum, $bib2_bibnum) ], "correct hits on 'isbn > a'"); |
|||
|
|||
$results = C4::Search::NZanalyse('isbn < z'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 2, "two hits on 'isbn < z'"); |
|||
is_deeply([ sort @bibnumbers ], [ sort($bib1_bibnum, $bib2_bibnum) ], "correct hits on 'isbn < z'"); |
|||
|
|||
$results = C4::Search::NZanalyse('isbn > isbn001'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 1, "one hit on 'isbn > isbn001'"); |
|||
is($bib2_bibnum, $bibnumbers[0], "correct hit on 'isbn > isbn001'"); |
|||
|
|||
$results = C4::Search::NZanalyse('isbn>=isbn001'); |
|||
($hits, @bibnumbers) = parse_nzanalyse($results); |
|||
cmp_ok($hits, '==', 2, "two hits on 'isbn>=isbn001'"); |
|||
is_deeply([ sort @bibnumbers ], [ sort($bib1_bibnum, $bib2_bibnum) ], "correct hits on 'isbn>=isbn001'"); |
|||
} |
|||
|
|||
sub parse_nzanalyse { |
|||
my $results = shift; |
|||
my @bibnumbers = (); |
|||
if (defined $results) { |
|||
# NZanalyze currently has a funky way of returning results - |
|||
# it does not guarantee that a biblionumber occurs only |
|||
# once in the results string. Hence we must remove |
|||
# duplicates, like NZorder (inefficently) does |
|||
my %hash; |
|||
@bibnumbers = grep { ++$hash{$_} == 1 } map { my @f = split /,/, $_; $f[0]; } split /;/, $results; |
|||
} |
|||
return scalar(@bibnumbers), @bibnumbers; |
|||
} |
|||
|
|||
=head2 SHUTDOWN METHODS |
|||
|
|||
These get run once, after all of the main tests methods in this module |
|||
|
|||
=cut |
|||
|
|||
sub shutdown_49_remove_bibs : Test( shutdown => 4 ) { |
|||
my $self = shift; |
|||
my ($bib1_bibnum, $bib2_bibnum) = @{ $self->{nozebra_test_bibs} }; |
|||
|
|||
my $dbh = C4::Context->dbh; |
|||
my $count_sth = $dbh->prepare("SELECT COUNT(*) FROM nozebra"); |
|||
my $count; |
|||
|
|||
my $error = DelBiblio($bib2_bibnum); |
|||
ok(!defined($error), "deleted bib $bib2_bibnum"); |
|||
$count_sth->execute; |
|||
($count) = $count_sth->fetchrow_array; |
|||
TODO: { local $TODO = 'nothing actually gets deleted from nozebra currently'; |
|||
cmp_ok($count, '==', 14, "correct number of words indexed after bib $bib2_bibnum deleted"); |
|||
} |
|||
|
|||
$error = DelBiblio($bib1_bibnum); |
|||
ok(!defined($error), "deleted bib $bib1_bibnum"); |
|||
$count_sth->execute; |
|||
($count) = $count_sth->fetchrow_array; |
|||
TODO: { local $TODO = 'nothing actually gets deleted from nozebra currently'; |
|||
cmp_ok($count, '==', 0, "no entries left in nozebra after bib $bib1_bibnum deleted"); |
|||
} |
|||
|
|||
delete $self->{nozebra_test_bibs}; |
|||
} |
|||
|
|||
sub shutdown_50_init_nozebra : Test( shutdown => 3 ) { |
|||
my $using_nozebra = C4::Context->preference('NoZebra'); |
|||
ok($using_nozebra, "still in NoZebra mode"); |
|||
my $dbh = C4::Context->dbh; |
|||
$dbh->do("UPDATE systempreferences SET value=0 WHERE variable='NoZebra'"); |
|||
$dbh->do("UPDATE systempreferences SET value=1 WHERE variable in ('QueryFuzzy','QueryWeightFields','QueryStemming')"); |
|||
C4::Context->clear_syspref_cache(); |
|||
$using_nozebra = C4::Context->preference('NoZebra'); |
|||
ok(!$using_nozebra, "switched to Zebra"); |
|||
|
|||
# FIXME |
|||
$dbh->do("DELETE FROM nozebra"); |
|||
my $sth = $dbh->prepare("SELECT COUNT(*) FROM nozebra"); |
|||
$sth->execute; |
|||
my ($count) = $sth->fetchrow_array; |
|||
$sth->finish; |
|||
cmp_ok($count, '==', 0, "NoZebra index finishes up empty"); |
|||
} |
|||
|
|||
1; |
|||
Loading…
Reference in new issue