use Business::ISBN;
use MARC::Record;
use MARC::Field;
-
+use utf8;
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS $DEBUG);
# set the version for version checking
&AddSearchHistory
&GetDistinctValues
&enabled_staff_search_views
- &SimpleSearch
+ &PurgeSearchHistory
);
# make all your functions, whether exported or not;
$titleindex = 'title|exact';
$authorindex = 'author|exact';
$op = '&&';
+ $QParser->custom_data->{'QueryAutoTruncate'} = C4::Context->preference('QueryAutoTruncate');
} else {
$titleindex = 'ti,ext';
$authorindex = 'au,ext';
my @results;
if (!defined $error) {
foreach my $possible_duplicate_record (@{$searchresults}) {
- my $marcrecord =
- MARC::Record->new_from_usmarc($possible_duplicate_record);
+ my $marcrecord = new_record_from_zebra(
+ 'biblioserver',
+ $possible_duplicate_record
+ );
+
my $result = TransformMarcToKoha( $dbh, $marcrecord, '' );
# FIXME :: why 2 $biblionumber ?
my $QParser;
$QParser = C4::Context->queryparser if (C4::Context->preference('UseQueryParser') && ! ($query =~ m/\w,\w|\w=\w/));
+ if ($QParser) {
+ $QParser->custom_data->{'QueryAutoTruncate'} = C4::Context->preference('QueryAutoTruncate');
+ }
# Initialize & Search Zebra
for ( my $i = 0 ; $i < @servers ; $i++ ) {
}
for my $j ( $first_record .. $last_record ) {
- my $record =
+ my $record = eval {
$tmpresults[ $i - 1 ]->record( $j - 1 )->raw()
; # 0 indexed
- push @{$results}, $record;
+ };
+ push @{$results}, $record if defined $record;
}
}
);
else {
$times = $size;
}
+
for ( my $j = $offset ; $j < $times ; $j++ ) {
my $records_hash;
my $record;
# not an index scan
else {
$record = $results[ $i - 1 ]->record($j)->raw();
- utf8::decode( $record );
-
# warn "RECORD $j:".$record;
$results_hash->{'RECORDS'}[$j] = $record;
}
$size > $facets_maxrecs ? $facets_maxrecs : $size;
for my $facet (@$facets) {
for ( my $j = 0 ; $j < $jmax ; $j++ ) {
- my $render_record =
- $results[ $i - 1 ]->record($j)->render();
- utf8::decode($render_record);
+
+ my $marc_record = new_record_from_zebra (
+ 'biblioserver',
+ $results[ $i - 1 ]->record($j)->raw()
+ );
+
+ if ( ! defined $marc_record ) {
+ warn "ERROR DECODING RECORD - $@: " .
+ $results[ $i - 1 ]->record($j)->raw();
+ next;
+ }
+
my @used_datas = ();
+
foreach my $tag ( @{ $facet->{tags} } ) {
# avoid first line
my $tag_num = substr( $tag, 0, 3 );
- my $letters = substr( $tag, 3 );
- my $field_pattern =
- '\n' . $tag_num . ' ([^z][^\n]+)';
- $field_pattern = '\n' . $tag_num . ' ([^\n]+)'
- if ( int($tag_num) < 10 );
- my @field_tokens =
- ( $render_record =~ /$field_pattern/g );
- foreach my $field_token (@field_tokens) {
- my @subf = ( $field_token =~
- /\$([a-zA-Z0-9]) ([^\$]+)/g );
- my @values;
- for ( my $i = 0 ; $i < @subf ; $i += 2 ) {
- if ( $letters =~ $subf[$i] ) {
- my $value = $subf[ $i + 1 ];
- $value =~ s/^ *//;
- $value =~ s/ *$//;
- push @values, $value;
- }
- }
- my $data = join( $facet->{sep}, @values );
+ my $subfield_letters = substr( $tag, 3 );
+ # Removed when as_string fixed
+ my @subfields = $subfield_letters =~ /./sg;
+
+ my @fields = $marc_record->field($tag_num);
+ foreach my $field (@fields) {
+ my $data = $field->as_string( $subfield_letters, $facet->{sep} );
+
unless ( $data ~~ @used_datas ) {
- $facets_counter->{ $facet->{idx} }
- ->{$data}++;
push @used_datas, $data;
+ $facets_counter->{ $facet->{idx} }->{$data}++;
}
- } # fields
+ } # fields
} # field codes
} # records
$facets_info->{ $facet->{idx} }->{label_value} =
)
{
$number_of_facets++;
- if ( ( $number_of_facets < 6 )
+ if ( ( $number_of_facets <= 5 )
|| ( $expanded_facet eq $link_value )
|| ( $facets_info->{$link_value}->{'expanded'} )
)
# handle expanded option
unless ( $facets_info->{$link_value}->{'expanded'} ) {
$expandable = 1
- if ( ( $number_of_facets > 6 )
+ if ( ( $number_of_facets > 5 )
&& ( $expanded_facet ne $link_value ) );
}
push @facets_loop,
for (my $i = 0; $i < $count; $i++) {
# FIXME -- may need to worry about diacritics here
my $rec = $paz->record($recid, $i);
- utf8::decode( $rec );
push @{ $result_group->{'RECORDS'} }, $rec;
}
my @stopwords_removed;
# phrase and exact-qualified indexes shouldn't have stopwords removed
- if ( $index !~ m/phr|ext/ ) {
+ 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.
my $stemming = C4::Context->preference("QueryStemming") || 0;
my $weight_fields = C4::Context->preference("QueryWeightFields") || 0;
my $fuzzy_enabled = C4::Context->preference("QueryFuzzy") || 0;
+ $operand =~ s/"/ /g; # Bug 7518: searches with quotation marks don't work
my $weighted_query .= "(rk=("; # Specifies that we're applying rank
$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 .= " or $index,wrdl,r6=\"$operand\""; # word list index
+ $weighted_query .= " or $index,wrdl,fuzzy,r8=\"$operand\""
+ if $fuzzy_enabled; # add fuzzy, word list
+ $weighted_query .= " or $index,wrdl,rt,r9=\"$stemmed_operand\""
+ if ( $stemming and $stemmed_operand ); # add stemming, right truncation
}
$weighted_query .= "))"; # close rank specification
'Corporate-name-heading',
'Corporate-name-see',
'Corporate-name-seealso',
+ 'Country-publication',
'ctype',
'date-entered-on-file',
'Date-of-acquisition',
'Date-of-publication',
'Dewey-classification',
+ 'Dissertation-information',
'EAN',
'extent',
'fic',
'Koha-Auth-Number',
'l-format',
'language',
+ 'language-original',
'lc-card',
'LC-card-number',
'lcn',
'su-to',
'su-ut',
'ut',
- 'UPC',
'Term-genre-form',
'Term-genre-form-heading',
'Term-genre-form-see',
'Title',
'Title-cover',
'Title-series',
- 'Title-host',
'Title-uniform',
'Title-uniform-heading',
'Title-uniform-see',
'mc-itype',
'mc-loc',
'notforloan',
+ 'Number-local-acquisition',
'onloan',
'price',
'renewals',
if ($QParser)
{
+ $QParser->custom_data->{'QueryAutoTruncate'} = C4::Context->preference('QueryAutoTruncate');
$query = '';
for ( my $ii = 0 ; $ii <= @operands ; $ii++ ) {
next unless $operands[$ii];
$query .= $operators[ $ii - 1 ] eq 'or' ? ' || ' : ' && '
if ($query);
- if ( $indexes[$ii] =~ m/su-/ ) {
+ if ( $operands[$ii] =~ /^[^"]\W*[-|_\w]*:\w.*[^"]$/ ) {
+ $query .= $operands[$ii];
+ }
+ elsif ( $indexes[$ii] =~ m/su-/ ) {
$query .= $indexes[$ii] . '(' . $operands[$ii] . ')';
}
else {
my $cclq = 0;
my $cclindexes = getIndexes();
- if ( $query !~ /\s*ccl=/ ) {
+ if ( $query !~ /\s*(ccl=|pqf=|cql=)/ ) {
while ( !$cclq && $query =~ /(?:^|\W)([\w-]+)(,[\w-]+)*[:=]/g ) {
my $dx = lc($1);
$cclq = grep { lc($_) eq $dx } @$cclindexes;
if ( @limits ) {
$q .= ' and '.join(' and ', @limits);
}
- return ( undef, $q, $q, "q=ccl=".uri_escape_utf8($q), $q, '', '', '', '', 'ccl' );
+ return ( undef, $q, $q, "q=ccl=".uri_escape($q), $q, '', '', '', '', 'ccl' );
}
if ( $query =~ /^cql=/ ) {
- return ( undef, $', $', "q=cql=".uri_escape_utf8($'), $', '', '', '', '', 'cql' );
+ return ( undef, $', $', "q=cql=".uri_escape($'), $', '', '', '', '', 'cql' );
}
if ( $query =~ /^pqf=/ ) {
if ($query_desc) {
- $query_cgi = "q=".uri_escape_utf8($query_desc);
+ $query_cgi = "q=".uri_escape($query_desc);
} else {
$query_desc = $';
- $query_cgi = "q=pqf=".uri_escape_utf8($');
+ $query_cgi = "q=pqf=".uri_escape($');
}
return ( undef, $', $', $query_cgi, $query_desc, '', '', '', '', 'pqf' );
}
# Set default structure attribute (word list)
my $struct_attr = q{};
- unless ( $indexes_set || !$index || $index =~ /(st-|phr|ext|wrdl|nb|ns)/ ) {
+ unless ( $indexes_set || !$index || $index =~ /,(st-|phr|ext|wrdl)/ || $index =~ /^(nb|ns)$/ ) {
$struct_attr = ",wrdl";
}
}
if ($auto_truncation){
- unless ( $index =~ /(st-|phr|ext)/ ) {
+ unless ( $index =~ /,(st-|phr|ext)/ ) {
#FIXME only valid with LTR scripts
$operand=join(" ",map{
(index($_,"*")>0?"$_":"$_*")
$query .= " $operators[$i-1] ";
$query .= " $index_plus " unless $indexes_set;
$query .= " $operand";
- $query_cgi .= "&op=".uri_escape_utf8($operators[$i-1]);
- $query_cgi .= "&idx=".uri_escape_utf8($index) if $index;
- $query_cgi .= "&q=".uri_escape_utf8($operands[$i]) if $operands[$i];
+ $query_cgi .= "&op=".uri_escape($operators[$i-1]);
+ $query_cgi .= "&idx=".uri_escape($index) if $index;
+ $query_cgi .= "&q=".uri_escape($operands[$i]) if $operands[$i];
$query_desc .=
" $operators[$i-1] $index_plus $operands[$i]";
}
$query .= " and ";
$query .= "$index_plus " unless $indexes_set;
$query .= "$operand";
- $query_cgi .= "&op=and&idx=".uri_escape_utf8($index) if $index;
- $query_cgi .= "&q=".uri_escape_utf8($operands[$i]) if $operands[$i];
+ $query_cgi .= "&op=and&idx=".uri_escape($index) if $index;
+ $query_cgi .= "&q=".uri_escape($operands[$i]) if $operands[$i];
$query_desc .= " and $index_plus $operands[$i]";
}
}
$query .= " $index_plus " unless $indexes_set;
$query .= $operand;
$query_desc .= " $index_plus $operands[$i]";
- $query_cgi .= "&idx=".uri_escape_utf8($index) if $index;
- $query_cgi .= "&q=".uri_escape_utf8($operands[$i]) if $operands[$i];
+ $query_cgi .= "&idx=".uri_escape($index) if $index;
+ $query_cgi .= "&q=".uri_escape($operands[$i]) if $operands[$i];
$previous_operand = 1;
}
} #/if $operands
while ( ( my $column ) = $sth2->fetchrow ) {
my ( $tagfield, $tagsubfield ) =
&GetMarcFromKohaField( "items." . $column, "" );
- $subfieldstosearch{$column} = $tagsubfield;
+ if ( defined $tagsubfield ) {
+ $subfieldstosearch{$column} = $tagsubfield;
+ }
}
# handle which records to actually retrieve
$times = $hits; # FIXME: if $hits is undefined, why do we want to equal it?
}
- my $marcflavour = C4::Context->preference("marcflavour");
+ 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 $marcrecord;
+ if ($scan) {
+ # For Scan searches we built USMARC data
+ $marcrecord = MARC::Record->new_from_usmarc( $marcresults->[$i]);
+ } else {
+ # Normal search, render from Zebra's output
+ $marcrecord = new_record_from_zebra(
+ 'biblioserver',
+ $marcresults->[$i]
+ );
+
+ if ( ! defined $marcrecord ) {
+ warn "ERROR DECODING RECORD - $@: " . $marcresults->[$i];
+ next;
+ }
+ }
+
my $fw = $scan
? undef
: $bibliotag < 10
my $onloan_count = 0;
my $longoverdue_count = 0;
my $other_count = 0;
- my $wthdrawn_count = 0;
+ my $withdrawn_count = 0;
my $itemlost_count = 0;
my $hideatopac_count = 0;
my $itembinding_count = 0;
# is item on the reserve shelf?
my $reservestatus = '';
- unless ($item->{wthdrawn}
+ unless ($item->{withdrawn}
|| $item->{itemlost}
|| $item->{damaged}
|| $item->{notforloan}
}
# item is withdrawn, lost, damaged, not for loan, reserved or in transit
- if ( $item->{wthdrawn}
+ if ( $item->{withdrawn}
|| $item->{itemlost}
|| $item->{damaged}
|| $item->{notforloan}
|| $reservestatus eq 'Waiting'
|| ($transfertwhen ne ''))
{
- $wthdrawn_count++ if $item->{wthdrawn};
+ $withdrawn_count++ if $item->{withdrawn};
$itemlost_count++ if $item->{itemlost};
$itemdamaged_count++ if $item->{damaged};
$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->{itemlost} ) {
- if ( !$item->{wthdrawn} ){
- if ( $item->{damaged} ){
- if ( C4::Context->preference('AllowHoldsOnDamagedItems') ){
- # can place a hold on a damaged item if AllowHoldsOnDamagedItems is true
- if ( ( !$item->{notforloan} || $item->{notforloan} < 0 ) ){
- # item is either for loan or has notforloan < 0
- $can_place_holds = 1;
- }
- }
- } elsif ( $item->{notforloan} < 0 ) {
- # item is not damaged and notforloan is < 0
- $can_place_holds = 1;
- }
- }
- }
+ $item->{status} = $item->{withdrawn} . "-" . $item->{itemlost} . "-" . $item->{damaged} . "-" . $item->{notforloan};
+
+ # can place a hold on a item if
+ # not lost nor withdrawn
+ # not damaged unless AllowHoldsOnDamagedItems is true
+ # item is either for loan or on order (notforloan < 0)
+ $can_place_holds = 1
+ if (
+ !$item->{itemlost}
+ && !$item->{withdrawn}
+ && ( !$item->{damaged} || C4::Context->preference('AllowHoldsOnDamagedItems') )
+ && ( !$item->{notforloan} || $item->{notforloan} < 0 )
+ );
$other_count++;
my $key = $prefix . $item->{status};
- foreach (qw(wthdrawn itemlost damaged branchname itemcallnumber)) {
+ foreach (qw(withdrawn itemlost damaged branchname itemcallnumber)) {
$other_items->{$key}->{$_} = $item->{$_};
}
$other_items->{$key}->{intransit} = ( $transfertwhen ne '' ) ? 1 : 0;
$oldbiblio->{onloanplural} = 1 if $onloan_count > 1;
$oldbiblio->{othercount} = $other_count;
$oldbiblio->{otherplural} = 1 if $other_count > 1;
- $oldbiblio->{wthdrawncount} = $wthdrawn_count;
+ $oldbiblio->{withdrawncount} = $withdrawn_count;
$oldbiblio->{itemlostcount} = $itemlost_count;
$oldbiblio->{damagedcount} = $itemdamaged_count;
$oldbiblio->{intransitcount} = $item_in_transit_count;
return $sth->fetchall_hashref({});
}
+sub PurgeSearchHistory{
+ my ($pSearchhistory)=@_;
+ my $dbh = C4::Context->dbh;
+ my $sth = $dbh->prepare("DELETE FROM search_history WHERE time < DATE_SUB( NOW(), INTERVAL ? DAY )");
+ $sth->execute($pSearchhistory) or die $dbh->errstr;
+}
+
=head2 z3950_search_args
$arrayref = z3950_search_args($matchpoints)
sub z3950_search_args {
my $bibrec = shift;
- my $isbn = Business::ISBN->new($bibrec);
+
+ my $isbn_string = ref( $bibrec ) ? $bibrec->{title} : $bibrec;
+ my $isbn = Business::ISBN->new( $isbn_string );
if (defined $isbn && $isbn->is_valid)
{
- $bibrec = { isbn => $bibrec } if !ref $bibrec;
+ if ( ref($bibrec) ) {
+ $bibrec->{isbn} = $isbn_string;
+ $bibrec->{title} = undef;
+ } else {
+ $bibrec = { isbn => $isbn_string };
+ }
}
else {
$bibrec = { title => $bibrec } if !ref $bibrec;
}
}
+=head2 new_record_from_zebra
+
+Given raw data from a Zebra result set, return a MARC::Record object
+
+This helper function is needed to take into account all the involved
+system preferences and configuration variables to properly create the
+MARC::Record object.
+
+If we are using GRS-1, then the raw data we get from Zebra should be USMARC
+data. If we are using DOM, then it has to be MARCXML.
+
+=cut
+
+sub new_record_from_zebra {
+
+ my $server = shift;
+ my $raw_data = shift;
+ # Set the default indexing modes
+ my $index_mode = ( $server eq 'biblioserver' )
+ ? C4::Context->config('zebra_bib_index_mode') // 'grs1'
+ : C4::Context->config('zebra_auth_index_mode') // 'dom';
+
+ my $marc_record = eval {
+ if ( $index_mode eq 'dom' ) {
+ MARC::Record->new_from_xml( $raw_data, 'UTF-8' );
+ } else {
+ MARC::Record->new_from_usmarc( $raw_data );
+ }
+ };
+
+ if ($@) {
+ return;
+ } else {
+ return $marc_record;
+ }
+
+}
END { } # module clean-up code here (global destructor)