search for: set_stemmer

Displaying 20 results from an estimated 23 matches for "set_stemmer".

2015 Jul 26
1
Get term from document by position
...ar microbe"; int main(int argc, char **argv) { // indexing Xapian::WritableDatabase db_w(database_dir, Xapian::DB_CREATE_OR_OVERWRITE); MyText text_to_index; text_to_index.set_string(); Xapian::TermGenerator indexer; Xapian::Stem stemmer("english"); indexer.set_stemmer(stemmer); Xapian::Document doc; indexer.set_document(doc); indexer.set_stemming_strategy(Xapian::TermGenerator::STEM_ALL_Z); indexer.index_text(text_to_index.text_str); db_w.add_document(doc); db_w.commit(); db_w.close(); //searching Xapian::Database db(da...
2013 Sep 02
2
having trouble with prefixes
...:") + path); Problem is, I can't seem to run a query that returns the document using any of the terms. Here is the outline of the code that runs the queries I'm trying to run: Database db(db_path.string()); QueryParser queryparser; Stem stemmer("english"); //queryparser.set_stemmer(stemmer); queryparser.set_database(db); queryparser.add_prefix("type", "T"); queryparser.add_prefix("md5sum", "Q"); queryparser.add_prefix("path", "P"); queryparser.add_prefix("extension", "E"); //maybe set stemmi...
2018 Nov 30
1
Xapian Benchmark results
...---------- #define NUM_THREADS 4 void parallel_index(int tid, int num_threads,vector<string> documents,Xapian::WritableDatabase *db ) { int i =0; char line[2048]; string line_string; Xapian::TermGenerator indexer; Xapian::Stem stemmer("english"); indexer.set_stemmer(stemmer); // doc.set_data("content"); indexer.set_stemming_strategy(Xapian::TermGenerator::STEM_SOME); Xapian::WritableDatabase database = *db; try{ for(i=0;i<documents.size();++i) { ifstream file; file.open(documents[i]); line_string...
2008 Mar 12
1
how can i use stopwords?
...tion... I've set the termgenerator like this: $self->{'Stemmer'} = new Search::Xapian::Stem(german2); $self->{'Stopper'} = new Search::Xapian::SimpleStopper(); $self->{'TermGenerator'} = new Search::Xapian::TermGenerator; $self->{'TermGenerator'}->set_stemmer( $self->{'Stemmer'} ); $self->{'TermGenerator'}->set_stopper( $self->{'Stopper'} ); I've thought that xapian now exclude the stopwords automatic by the stemming-language. Could someone explain the stopword function? Thanks. Greetings Sascha
2012 Jun 04
1
Search not finding queries with stop words.
I have a search in perl that looks a bit like: my $qp = new Search::Xapian::QueryParser(); $qp->set_stemmer(new Search::Xapian::Stem("english")); $qp->set_stemming_strategy(STEM_SOME); $qp->set_default_op($defaultop); ... my $par = $qp->parse_query($query); my $enq = $xDatabase->enquire( $par ); and in the db create script: my $stopper = Search::Xapian::SimpleS...
2013 Sep 22
2
How to filter search result with query with has white space.
...std::string content; std::string url;}; void indexData(document d) { try { Xapian::WritableDatabase db("/Users/ramesh/Desktop/xapian", Xapian::DB_CREATE_OR_OPEN); Xapian::TermGenerator indexer; Xapian::Stem stemmer("english"); indexer.set_stemmer(stemmer); Xapian::Document doc; doc.set_data(d.title); indexer.set_document(doc); indexer.index_text(d.title,1,"title"); indexer.index_text(d.content,1,"content"); indexer.index_text(d.url,1,"url"); doc.add_boolea...
2013 Sep 22
2
How to filter search result with query with has white space.
...std::string content; std::string url;}; void indexData(document d) { try { Xapian::WritableDatabase db("/Users/ramesh/Desktop/xapian", Xapian::DB_CREATE_OR_OPEN); Xapian::TermGenerator indexer; Xapian::Stem stemmer("english"); indexer.set_stemmer(stemmer); Xapian::Document doc; doc.set_data(d.title); indexer.set_document(doc); indexer.index_text(d.title,1,"title"); indexer.index_text(d.content,1,"content"); indexer.index_text(d.url,1,"url"); doc.add_boolea...
2010 Jun 09
1
TermGenerator incorrectly tokenizes German text which contains special characters
...?dlich is indexed as gesundheitssch? and Zgesundheitssch? (stemmed). All character encodings are set to UTF-8, the MySql database is also in UTF-8 encoding. * #1 $lIndexer = new XapianTermGenerator(); #2 $lStemmer = new XapianStem(XapianHelper::GetStemmer($pLanguage)); // ?german? #3 $lIndexer->set_stemmer($lStemmer); #4 $lDoc = new XapianDocument(); #5 $lDoc->add_term($lObj->Id); #6 $lIndexer->set_document($lDoc); #7 $lIndexer->index_text("Nahrungserg?nzungsmittel Ausrei?er"); #8 $lIndexer->index_text($lSomeStringFromDb);* In the code example just above here the problem onl...
2014 Jan 27
4
Perl Search::Xapian
...; my $csvfile = $ARGV[0]; my $dbpath = $ARGV[1]; my $db = Search::Xapian::WritableDatabase->new( path => $dbpath, mode => "DB_CREATE_OR_OPEN", ); # setup TermGenerator that'll be used in indexing. my $tg = Search::Xapian::TermGenerator->new(); $tg->set_stemmer(Search::Xapian::Stem->new('en')); # here is a for to loop thru all the csv? file. my $fh = Tie::Handle::CSV->new($csvfile, header => 1); while (my $csvline = <$fh>) { my $description = $csvline->{DESCRIPTION}; my $title = $csvline->{TITLE}; my $identifier =...
2005 Jun 09
1
Query parser and stemming of norwegian letters
Hello, can I get an explanation of the following. Running the following code: .... pqp=new QueryParser(); Stem stem("norwegian"); cout << "DEBUG " << stem.stem_word(_sXapian)<< endl; pqp->set_stemmer(stem); pqp->set_database(*_pdatabase); pqp->set_default_op(Query::OP_AND); //Set the enquire Query p=pqp->parse_query(_sXapian); cout << " Query " << string(bufSL) << p.get_description() << endl; --- gives the foll...
2007 Dec 29
3
Term-Flags
Hi, Is it necessary to set the down below flag to the TermGenerator, if I want the "Did you mean ..." spelling corrections? Xapian::TermGenerator::flags::FLAG_SPELLING Thank you very much Markus
2009 Mar 02
0
Xapian, PHP bindings and
...shell // level. $query_string = xapianEncode( $_GET['q'] ); $rset = new XapianRSet(); $qp = new XapianQueryParser(); $stemmer = new XapianStem( 'french' ); $qp->set_stemmer($stemmer); $qp->set_database($database); $qp->set_stemming_strategy(XapianQueryParser::STEM_SOME); $query = $qp->parse_query( $query_string ); //, XapianQueryParser::FLAG_SPELLING_CORRECTION); print 'Parsed query is: &...
2009 Aug 17
1
Xapian DatabaseError
...f search function.inc <?php require_once 'xapian.php'; function simpleSearch($query,$path){ try { $database = new XapianDatabase($path); $enquire = new XapianEnquire($database); $qp = new XapianQueryParser(); $stemmer = new XapianStem("italian"); $qp->set_stemmer($stemmer); $qp->set_database($database); $qp->set_stemming_strategy(XapianQueryParser::STEM_SOME); $query = $qp->parse_query($query); echo "<br>Parsed query is: {$query->get_description()}\n"; $enquire->set_query($que...
2010 Mar 31
1
Hyphen search with parse_query()
...from "peter" & "bengtsson" and is different from "peterbengtsson") and find it. To start with I'm trying to use a basic python script to get to grips with it. When I do this:: qp = xapian.QueryParser() stemmer = xapian.Stem("english") qp.set_stemmer(stemmer) qp.set_database(database) qp.set_stemming_strategy(xapian.QueryParser.STEM_SOME) print "Query string is:", repr(query_string) query = qp.parse_query(query_string) print "Parsed query is: %s" % str(query) I get the following output:: Query string...
2013 Aug 21
2
Perl interface isn't working in 1.2.x
At least it isn't working the way it used to. Code: $db = Search::Xapian::Database->new( $dx ); my $qp = Search::Xapian::QueryParser->new(); my $dbSize=$db->get_doccount(); # $qp->set_stemmer(new Search::Xapian::Stem("english")); # $qp->set_stemming_strategy(STEM_SOME); # $qp->set_default_op($defaultop); my $par = $qp->parse_query($query); my $enq = $db->enquire( $par ); my @matches = $enq->matches($nstart,$nrecords); my $mset = $enq-&...
2007 May 30
1
QueryParser prefixing terms when stemming?
...wever, something seems to have changed during the upgrade and I need help figuring out how my code should be written. In version 0.9.9.1 of Search::Xapian, the following code results in this output "Xapian::Query(pet:(pos=1))". my $qp = new Search::Xapian::QueryParser; $qp->set_stemmer(new Search::Xapian::Stem('english')); $qp->set_default_op(OP_AND); $qp->set_stemming_strategy(STEM_SOME); warn $qp->parse_query($search_term); In version 1.0.0.0, the same code results in "Xapian::Query(Zpet: (pos=1))". The result is no matches, even though t...
2010 Oct 28
1
hypens in words + NEAR + 3 terms + AND_MAYBE => crash
...AR test NEAR x-y" will. Stemming language was "english", strategy STEM_SOME. Default op was OP_AND_MAYBE. This is the offending Perl code: [...] my $qp = Search::Xapian::QueryParser->new(); my $stemmer = Search::Xapian::Stem->new("english"); $qp->set_stemmer($stemmer); $qp->set_database($database); $qp->set_stemming_strategy(STEM_SOME); $qp->set_default_op(OP_AND_MAYBE); $query_string = " x-y NEAR test NEAR test "; my $query = $qp->parse_query($query_string, Search::Xapian::FLAG_DEFAULT); [...] Here'...
2018 Jul 19
1
choosing between probabilistic and boolean prefixes for terms
...= 'english'; sub stemmer { Search::Xapian::Stem->new($LANG) } sub qp { my ($self) = @_; my $qp = $self->{query_parser}; return $qp if $qp; # new parser $qp = Search::Xapian::QueryParser->new; $qp->set_default_op(OP_AND); $qp->set_database($self->{xdb}); $qp->set_stemmer($self->stemmer); $qp->set_stemming_strategy(STEM_SOME); $qp->set_max_wildcard_expansion(100); $qp->add_valuerangeprocessor( Search::Xapian::NumberValueRangeProcessor->new(YYYYMMDD, 'd:')); $qp->add_valuerangeprocessor( Search::Xapian::NumberValueRangeProcessor->...
2014 Jan 21
2
seg fault on search
...base db; db.add_database(Database(fullDB)); Enquire enquire(db); try { Xapian::QueryParser qp; Xapian::Stem stemmer("english"); qp.set_database(db); qp.set_default_op(Query::OP_OR); qp.set_stemmer(stemmer); qp.set_stemming_strategy(QueryParser::STEM_SOME); Xapian::Query q=qp.parse_query(queryString); ... As soon as it hits the q=qp.parse_query line it gets the seg fault. The function is called like so: int main (int argc, char* const argv[]) { int...
2006 Nov 30
1
PHP / XapianQueryParser
...d I'm not sure if it is actually my mistake (although I'm pretty sure it is :)) I'm trying to use the XapianQueryParser (in PHP5), but I get an error everytime. $odb = new XapianDatabase($db); $ostem = new XapianStem("en"); $oqparser = new XapianQueryParser();$oqparser->set_stemmer($ostem);$oqparser->set_database($odb);$oqparser->set_stemming_strategy(1);$oqparser->add_boolean_prefix("Q",1);$oquery = $oqparser->parse_query($query, 1); I found some perl examples and 'ported' it over to the PHP version. Varying the flags (like XapianQueryParser::...