|
I developed a
Filter that restricts search results to documents that has terms in specific
fields
(because currently we can't search with
lucene documents with this kind of feature (a document with present/absent of
values in specific fields)
nicolas
|
package org.apache.lucene.search;
import java.io.IOException;
import org.apache.lucene.index.IndexReader;
import java.util.BitSet;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermEnum;
import org.apache.lucene.index.TermDocs;
import java.util.*;
/**
* A Filter that restricts search results to documents that has terms in specific fields
* (OR operator: the documents that has terms in field1 or in field2)
* @author Nicolas Maisonneuve
*/
public class HasFieldFilter
extends Filter {
private Set fieldnames;
/**
* a array of the field's names
* @param fieldname String[] a array of field's names
*/
public HasFieldFilter (String[] fieldnames) {
this.fieldnames=new HashSet();
for (int i=0; i<fieldnames.length; i++) {
this.fieldnames.add(fieldnames[i].intern());
}
}
public BitSet bits (IndexReader reader) throws IOException {
final BitSet bits=new BitSet(reader.maxDoc());
TermEnum enumerator=reader.terms();
TermDocs termDocs=reader.termDocs();
Iterator iter=reader.getFieldNames().iterator();
try {
// for each field
while (iter.hasNext()) {
String field=(String) iter.next();
//if is not in the list of specific fields
if (!fieldnames.contains(field)) {
continue;
}
enumerator.skipTo(new Term(field, ""));
if (enumerator.term()==null) {
continue;
}
// restrict doc to the field
while (enumerator.term().field()==field) {
termDocs.seek(enumerator.term());
while (termDocs.next()) {
bits.set(termDocs.doc());
}
if (!enumerator.next()) {
break;
}
}
}
}
finally {
enumerator.close();
termDocs.close();
}
return bits;
}
}
--------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
