dnaber 2004/08/13 11:35:02
Modified: src/java/org/apache/lucene/search FuzzyTermEnum.java
FuzzyQuery.java
src/test/org/apache/lucene/search TestFuzzyQuery.java
Log:
You can now set the required fuzziness of FuzzyQuery. Note that QueryParser does not
support this (yet?).
Revision Changes Path
1.7 +11 -6
jakarta-lucene/src/java/org/apache/lucene/search/FuzzyTermEnum.java
Index: FuzzyTermEnum.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/search/FuzzyTermEnum.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -u -r1.6 -r1.7
--- FuzzyTermEnum.java 11 May 2004 17:23:21 -0000 1.6
+++ FuzzyTermEnum.java 13 Aug 2004 18:35:01 -0000 1.7
@@ -26,16 +26,24 @@
the enumeration is greater than all that precede it. */
public final class FuzzyTermEnum extends FilteredTermEnum {
double distance;
- boolean fieldMatch = false;
boolean endEnum = false;
Term searchTerm = null;
String field = "";
String text = "";
int textlen;
+ float minimumSimilarity;
+ double scale_factor;
+
public FuzzyTermEnum(IndexReader reader, Term term) throws IOException {
+ this(reader, term, 0.5f);
+ }
+
+ public FuzzyTermEnum(IndexReader reader, Term term, float minSimilarity) throws
IOException {
super();
+ minimumSimilarity = minSimilarity;
+ scale_factor = 1.0f / (1.0f - minimumSimilarity);
searchTerm = term;
field = searchTerm.field();
text = searchTerm.text();
@@ -53,14 +61,14 @@
int targetlen = target.length();
int dist = editDistance(text, target, textlen, targetlen);
distance = 1 - ((double)dist / (double)Math.min(textlen, targetlen));
- return (distance > FUZZY_THRESHOLD);
+ return (distance > minimumSimilarity);
}
endEnum = true;
return false;
}
protected final float difference() {
- return (float)((distance - FUZZY_THRESHOLD) * SCALE_FACTOR);
+ return (float)((distance - minimumSimilarity) * scale_factor);
}
public final boolean endEnum() {
@@ -70,9 +78,6 @@
/******************************
* Compute Levenshtein distance
******************************/
-
- public static final double FUZZY_THRESHOLD = 0.5;
- public static final double SCALE_FACTOR = 1.0f / (1.0f - FUZZY_THRESHOLD);
/**
Finds and returns the smallest of three integers
1.5 +32 -3 jakarta-lucene/src/java/org/apache/lucene/search/FuzzyQuery.java
Index: FuzzyQuery.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/search/FuzzyQuery.java,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- FuzzyQuery.java 29 Mar 2004 22:48:03 -0000 1.4
+++ FuzzyQuery.java 13 Aug 2004 18:35:01 -0000 1.5
@@ -20,14 +20,43 @@
import org.apache.lucene.index.Term;
import java.io.IOException;
-/** Implements the fuzzy search query */
+/** Implements the fuzzy search query. The similiarity measurement
+ * is based on the Levenshtein (edit distance) algorithm.
+ */
public final class FuzzyQuery extends MultiTermQuery {
- public FuzzyQuery(Term term) {
+
+ private float minimumSimilarity;
+
+ /**
+ * Create a new FuzzyQuery that will match terms with a similarity
+ * of at least <code>minimumSimilarity</code> to <code>term</code>.
+ *
+ * @param term the term to search for
+ * @param minimumSimilarity a value between 0 and 1 to set the required similarity
+ * between the query term and the matching terms. For example, for a
+ * <code>minimumSimilarity</code> of <code>0.5</code> a term of the same length
+ * as the query term is considered similar to the query term if the edit distance
+ * between both terms is less than <code>length(term)*0.5</code>.
+ * @throws IllegalArgumentException if minimumSimilarity is > 1 or < 0
+ */
+ public FuzzyQuery(Term term, float minimumSimilarity) throws
IllegalArgumentException {
super(term);
+ if (minimumSimilarity > 1.0f)
+ throw new IllegalArgumentException("minimumSimilarity > 1");
+ else if (minimumSimilarity < 0.0f)
+ throw new IllegalArgumentException("minimumSimilarity < 0");
+ this.minimumSimilarity = minimumSimilarity;
+ }
+
+ /**
+ * Calls [EMAIL PROTECTED] #FuzzyQuery(Term, float) FuzzyQuery(term, 0.5f)}.
+ */
+ public FuzzyQuery(Term term) {
+ this(term, 0.5f);
}
protected FilteredTermEnum getEnum(IndexReader reader) throws IOException {
- return new FuzzyTermEnum(reader, getTerm());
+ return new FuzzyTermEnum(reader, getTerm(), minimumSimilarity);
}
public String toString(String field) {
1.2 +20 -2
jakarta-lucene/src/test/org/apache/lucene/search/TestFuzzyQuery.java
Index: TestFuzzyQuery.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/test/org/apache/lucene/search/TestFuzzyQuery.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- TestFuzzyQuery.java 1 Aug 2004 22:19:59 -0000 1.1
+++ TestFuzzyQuery.java 13 Aug 2004 18:35:02 -0000 1.2
@@ -33,7 +33,7 @@
*/
public class TestFuzzyQuery extends TestCase {
- public void testDefaultFuzziness() throws Exception {
+ public void testFuzziness() throws Exception {
RAMDirectory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
addDoc("aaaaa", writer);
@@ -90,7 +90,7 @@
directory.close();
}
- public void testDefaultFuzzinessLong() throws Exception {
+ public void testFuzzinessLong() throws Exception {
RAMDirectory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
addDoc("aaaaaaa", writer);
@@ -123,6 +123,24 @@
query = new FuzzyQuery(new Term("field", "stellent"));
hits = searcher.search(query);
assertEquals(1, hits.length());
+
+ // "student" doesn't match anymore thanks to increased minimum similarity:
+ query = new FuzzyQuery(new Term("field", "student"), 0.6f);
+ hits = searcher.search(query);
+ assertEquals(0, hits.length());
+
+ try {
+ query = new FuzzyQuery(new Term("field", "student"), 1.1f);
+ fail("Expected IllegalArgumentException");
+ } catch (IllegalArgumentException e) {
+ // expecting exception
+ }
+ try {
+ query = new FuzzyQuery(new Term("field", "student"), -0.1f);
+ fail("Expected IllegalArgumentException");
+ } catch (IllegalArgumentException e) {
+ // expecting exception
+ }
searcher.close();
directory.close();
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
