use C4::Dates qw(format_date);
use C4::XSLT;
use C4::Branch;
+use C4::Debug;
+use YAML;
use URI::Escape;
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS $DEBUG);
# 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
+ $debug && warn "$_ Dump($operand)";
if ( my ($matched) = ($operand =~
- /(\P{IsAlnum}\Q$_\E\P{IsAlnum}|^\Q$_\E\P{IsAlnum}|\P{IsAlnum}\Q$_\E$|^\Q$_\E$)/gi) )
+ /([^\X\p{isAlnum}]\Q$_\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 $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',
+ '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',
+ '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',
+ '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-geographic',
+ 'Name-geographic-heading',
+ 'Name-geographic-see',
+ 'Name-geographic-seealso',
+ 'nb',
+ 'Note',
+ 'ns',
+ 'nt',
+ 'pb',
+ 'Personal-name',
+ 'Personal-name-heading',
+ 'Personal-name-see',
+ 'Personal-name-seealso',
+ 'pl',
+ 'Place-publication',
+ 'pn',
+ 'popularity',
+ 'pubdate',
+ 'Publisher',
+ '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',
+ 'Term-genre-form',
+ 'Term-genre-form-heading',
+ 'Term-genre-form-see',
+ 'Term-genre-form-seealso',
+ 'ti',
+ 'Title',
+ 'Title-cover',
+ 'Title-series',
+ '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',
+ 'itemnumber',
+ 'itype',
+ 'Local-classification',
+ 'location',
+ 'lost',
+ 'materials-specified',
+ 'mc-ccode',
+ 'mc-itype',
+ 'mc-loc',
+ 'notforloan',
+ 'onloan',
+ 'price',
+ 'renewals',
+ 'replacementprice',
+ 'replacementpricedate',
+ 'reserves',
+ 'restricted',
+ 'stack',
+ 'uri',
+ 'withdrawn',
+
+ # subject related
+ );
+
+ return \@indexes;
+}
+
=head2 buildQuery
( $error, $query,
# no stemming/weight/fuzzy in NoZebra
if ( C4::Context->preference("NoZebra") ) {
- $stemming = 0;
- $weight_fields = 0;
- $fuzzy_enabled = 0;
+ $stemming = 0;
+ $weight_fields = 0;
+ $fuzzy_enabled = 0;
+ $auto_truncation = 0;
}
my $query = $operands[0];
my $stopwords_removed; # flag to determine if stopwords have been removed
+ my $cclq;
+ my $cclindexes = getIndexes();
+ if( $query !~ /\s*ccl=/ ){
+ for my $index (@$cclindexes){
+ if($query =~ /($index)(,?\w)*[:=]/){
+ $cclq = 1;
+ }
+ }
+ $query = "ccl=$query" if($cclq);
+ }
+
# for handling ccl, cql, pqf queries in diagnostic mode, skip the rest of the steps
# DIAGNOSTIC ONLY!!
if ( $query =~ /^ccl=/ ) {
) = ( 0, 0, 0, 0, 0 );
}
+
+ if(not $index){
+ $index = 'kw';
+ }
+
# Set default structure attribute (word list)
my $struct_attr;
unless ( $indexes_set || !$index || $index =~ /(st-|phr|ext|wrdl)/ ) {
}
if ($auto_truncation){
- #FIXME only valid with LTR scripts
- $operand=join(" ",map{
- "$_*"
- }split (/\s+/,$operand));
- warn $operand if $DEBUG;
+ unless ( $index =~ /(st-|phr|ext)/ ) {
+ #FIXME only valid with LTR scripts
+ $operand=join(" ",map{
+ (index($_,"*")>0?"$_":"$_*")
+ }split (/\s+/,$operand));
+ warn $operand if $DEBUG;
+ }
}
# Detect Truncation
# We get the biblionumber position in MARC
my ($bibliotag,$bibliosubf)=GetMarcFromKohaField('biblio.biblionumber','');
- my $fw;
+ my $fw = '';
# 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 $biblionumber;
- if ($bibliotag<10){
- $fw = GetFrameworkCode($marcrecord->field($bibliotag)->data);
- }else{
- $fw = GetFrameworkCode($marcrecord->subfield($bibliotag,$bibliosubf));
+ if(not $scan){
+ if ($bibliotag<10){
+ $biblionumber = $marcrecord->field($bibliotag)->data;
+ }else{
+ $biblionumber = $marcrecord->subfield($bibliotag,$bibliosubf);
+ }
+ $fw = GetFrameworkCode($biblionumber);
}
my $oldbiblio = TransformMarcToKoha( $dbh, $marcrecord, $fw );