[
https://issues.apache.org/jira/browse/LUCENE-5396?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Piotr Pęzik updated LUCENE-5396:
--------------------------------
Description:
Let's assume we have an index with two documents:
1. contents: "test bunga bunga test"
2. contents: "test bunga test"
We run two SpanNearQueries against this index:
1. spanNear([contents:bunga, contents:bunga], 0, true)
2. spanNear([contents:bunga, contents:bunga], 0, false)
For the first query we get 1 hit. The first document in the example above gets
matched and the second one doesn't. This make sense, because we want the term
"bunga" followed by another "bunga" here.
However, both documents get matched by the second query. This is also
problematic in cases where we have duplicate terms in longer (unordered)
spannear queries, e. g.: unordered 'A B A' will match spans such as 'A B' or 'B
A'.
A complete example follows.
---------
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import java.io.StringReader;
import static org.junit.Assert.assertEquals;
class SpansBug {
public static void main(String [] args) throws Exception {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_45,
analyzer);
IndexWriter writer = new IndexWriter(dir, iwc);
String contents = "contents";
Document doc1 = new Document();
doc1.add(new TextField(contents, new StringReader("test bunga bunga
test")));
Document doc2 = new Document();
doc2.add(new TextField(contents, new StringReader("test bunga test")));
writer.addDocument(doc1);
writer.addDocument(doc2);
writer.commit();
IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
SpanQuery stq1 = new SpanTermQuery(new Term(contents,"bunga"));
SpanQuery stq2 = new SpanTermQuery(new Term(contents,"bunga"));
SpanQuery [] spqa = new SpanQuery[]{stq1,stq2};
SpanNearQuery spanQ1 = new SpanNearQuery(spqa,0, true);
SpanNearQuery spanQ2 = new SpanNearQuery(spqa,0, false);
System.out.println(spanQ1);
TopDocs tdocs1 = searcher.search(spanQ1,10);
assertEquals(tdocs1.totalHits ,1);
System.out.println(spanQ2);
TopDocs tdocs2 = searcher.search(spanQ2,10);
//I'd expect one hit here:
assertEquals(tdocs2.totalHits ,1); // Assertion fails
}
}
was:
Let's assume we have an index with two documents:
1. contents: "test bunga bunga test"
2. contents: "test bunga test"
We run two SpanNearQueries against this index:
1. spanNear([contents:bunga, contents:bunga], 0, true)
2. spanNear([contents:bunga, contents:bunga], 0, false)
For the first query we get 1 hit. The first document in the example above gets
matched and the second one doesn't. This make sense, because we want the term
"bunga" followed by another "bunga" here.
However, both documents get matched by the second query, although two term
occurrences are required (?). This is also problematic in cases where we have
duplicate terms in longer (unordered) phrases, e. g.: unordered 'A B A' will
match spans such as 'A B' or 'B A'.
A complete example follows.
---------
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import java.io.StringReader;
import static org.junit.Assert.assertEquals;
class SpansBug {
public static void main(String [] args) throws Exception {
Directory dir = new RAMDirectory();
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_45,
analyzer);
IndexWriter writer = new IndexWriter(dir, iwc);
String contents = "contents";
Document doc1 = new Document();
doc1.add(new TextField(contents, new StringReader("test bunga bunga
test")));
Document doc2 = new Document();
doc2.add(new TextField(contents, new StringReader("test bunga test")));
writer.addDocument(doc1);
writer.addDocument(doc2);
writer.commit();
IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
SpanQuery stq1 = new SpanTermQuery(new Term(contents,"bunga"));
SpanQuery stq2 = new SpanTermQuery(new Term(contents,"bunga"));
SpanQuery [] spqa = new SpanQuery[]{stq1,stq2};
SpanNearQuery spanQ1 = new SpanNearQuery(spqa,0, true);
SpanNearQuery spanQ2 = new SpanNearQuery(spqa,0, false);
System.out.println(spanQ1);
TopDocs tdocs1 = searcher.search(spanQ1,10);
assertEquals(tdocs1.totalHits ,1);
System.out.println(spanQ2);
TopDocs tdocs2 = searcher.search(spanQ2,10);
//I'd expect one hit here:
assertEquals(tdocs2.totalHits ,1); // Assertion fails
}
}
> SpanNearQuery returns single term spans
> ---------------------------------------
>
> Key: LUCENE-5396
> URL: https://issues.apache.org/jira/browse/LUCENE-5396
> Project: Lucene - Core
> Issue Type: Bug
> Components: core/search
> Reporter: Piotr Pęzik
>
> Let's assume we have an index with two documents:
> 1. contents: "test bunga bunga test"
> 2. contents: "test bunga test"
> We run two SpanNearQueries against this index:
> 1. spanNear([contents:bunga, contents:bunga], 0, true)
> 2. spanNear([contents:bunga, contents:bunga], 0, false)
> For the first query we get 1 hit. The first document in the example above
> gets matched and the second one doesn't. This make sense, because we want the
> term "bunga" followed by another "bunga" here.
> However, both documents get matched by the second query. This is also
> problematic in cases where we have duplicate terms in longer (unordered)
> spannear queries, e. g.: unordered 'A B A' will match spans such as 'A B' or
> 'B A'.
> A complete example follows.
> ---------
> import org.apache.lucene.analysis.Analyzer;
> import org.apache.lucene.analysis.standard.StandardAnalyzer;
> import org.apache.lucene.document.Document;
> import org.apache.lucene.document.TextField;
> import org.apache.lucene.index.DirectoryReader;
> import org.apache.lucene.index.IndexWriter;
> import org.apache.lucene.index.IndexWriterConfig;
> import org.apache.lucene.index.Term;
> import org.apache.lucene.search.IndexSearcher;
> import org.apache.lucene.search.TopDocs;
> import org.apache.lucene.search.spans.SpanNearQuery;
> import org.apache.lucene.search.spans.SpanQuery;
> import org.apache.lucene.search.spans.SpanTermQuery;
> import org.apache.lucene.store.Directory;
> import org.apache.lucene.store.FSDirectory;
> import org.apache.lucene.store.RAMDirectory;
> import org.apache.lucene.util.Version;
> import java.io.StringReader;
> import static org.junit.Assert.assertEquals;
> class SpansBug {
> public static void main(String [] args) throws Exception {
> Directory dir = new RAMDirectory();
> Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);
> IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_45,
> analyzer);
> IndexWriter writer = new IndexWriter(dir, iwc);
> String contents = "contents";
> Document doc1 = new Document();
> doc1.add(new TextField(contents, new StringReader("test bunga bunga
> test")));
> Document doc2 = new Document();
> doc2.add(new TextField(contents, new StringReader("test bunga
> test")));
> writer.addDocument(doc1);
> writer.addDocument(doc2);
> writer.commit();
> IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
> SpanQuery stq1 = new SpanTermQuery(new Term(contents,"bunga"));
> SpanQuery stq2 = new SpanTermQuery(new Term(contents,"bunga"));
> SpanQuery [] spqa = new SpanQuery[]{stq1,stq2};
> SpanNearQuery spanQ1 = new SpanNearQuery(spqa,0, true);
> SpanNearQuery spanQ2 = new SpanNearQuery(spqa,0, false);
> System.out.println(spanQ1);
> TopDocs tdocs1 = searcher.search(spanQ1,10);
> assertEquals(tdocs1.totalHits ,1);
> System.out.println(spanQ2);
> TopDocs tdocs2 = searcher.search(spanQ2,10);
> //I'd expect one hit here:
> assertEquals(tdocs2.totalHits ,1); // Assertion fails
> }
> }
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
