You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2013/10/11 06:55:36 UTC
svn commit: r1531195 - in /lucene/dev/branches/branch_4x: ./ lucene/
lucene/analysis/
lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/
lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/
lucene/analysis/common/src...
Author: rmuir
Date: Fri Oct 11 04:55:35 2013
New Revision: 1531195
URL: http://svn.apache.org/r1531195
Log:
LUCENE-5269: Fix NGramTokenFilter length filtering
Added:
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/CodepointCountFilter.java
- copied unchanged from r1531186, lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/CodepointCountFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/CodepointCountFilterFactory.java
- copied unchanged from r1531186, lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/CodepointCountFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCodepointCountFilter.java
- copied unchanged from r1531186, lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCodepointCountFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCodepointCountFilterFactory.java
- copied unchanged from r1531186, lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCodepointCountFilterFactory.java
Modified:
lucene/dev/branches/branch_4x/ (props changed)
lucene/dev/branches/branch_4x/lucene/ (props changed)
lucene/dev/branches/branch_4x/lucene/CHANGES.txt (contents, props changed)
lucene/dev/branches/branch_4x/lucene/analysis/ (props changed)
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java
Modified: lucene/dev/branches/branch_4x/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/CHANGES.txt?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/CHANGES.txt (original)
+++ lucene/dev/branches/branch_4x/lucene/CHANGES.txt Fri Oct 11 04:55:35 2013
@@ -78,6 +78,10 @@ Bug Fixes
terms were present in the query and the high-frequent operator was set
to SHOULD. (Simon Willnauer)
+* LUCENE-5269: Fix bug in NGramTokenFilter where it would sometimes count
+ unicode characters incorrectly. Adds CodepointCountFilter.
+ (Mike McCandless, Robert Muir)
+
API Changes:
* LUCENE-5222: Add SortField.needsScores(). Previously it was not possible
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java Fri Oct 11 04:55:35 2013
@@ -21,7 +21,7 @@ import java.io.IOException;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.miscellaneous.LengthFilter;
+import org.apache.lucene.analysis.miscellaneous.CodepointCountFilter;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
@@ -81,7 +81,7 @@ public final class NGramTokenFilter exte
* @param maxGram the largest n-gram to generate
*/
public NGramTokenFilter(Version version, TokenStream input, int minGram, int maxGram) {
- super(new LengthFilter(version, input, minGram, Integer.MAX_VALUE));
+ super(new CodepointCountFilter(version, input, minGram, Integer.MAX_VALUE));
this.version = version;
this.charUtils = version.onOrAfter(Version.LUCENE_44)
? CharacterUtils.getInstance(version)
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory Fri Oct 11 04:55:35 2013
@@ -56,6 +56,7 @@ org.apache.lucene.analysis.it.ItalianLig
org.apache.lucene.analysis.lv.LatvianStemFilterFactory
org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory
org.apache.lucene.analysis.miscellaneous.CapitalizationFilterFactory
+org.apache.lucene.analysis.miscellaneous.CodepointCountFilterFactory
org.apache.lucene.analysis.miscellaneous.HyphenatedWordsFilterFactory
org.apache.lucene.analysis.miscellaneous.KeepWordFilterFactory
org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilterFactory
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java Fri Oct 11 04:55:35 2013
@@ -1,5 +1,6 @@
package org.apache.lucene.analysis.core;
+import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.nio.CharBuffer;
@@ -11,10 +12,14 @@ import org.apache.lucene.analysis.MockCh
import org.apache.lucene.analysis.MockTokenFilter;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.charfilter.MappingCharFilter;
import org.apache.lucene.analysis.charfilter.NormalizeCharMap;
import org.apache.lucene.analysis.commongrams.CommonGramsFilter;
+import org.apache.lucene.analysis.ngram.EdgeNGramTokenizer;
+import org.apache.lucene.analysis.ngram.NGramTokenFilter;
+import org.apache.lucene.analysis.shingle.ShingleFilter;
import org.apache.lucene.analysis.util.CharArraySet;
/*
@@ -195,4 +200,58 @@ public class TestBugInSomething extends
assertEquals("read(char[], int, int)", e.getMessage());
}
}
+
+ // todo: test framework?
+
+ static final class SopTokenFilter extends TokenFilter {
+
+ SopTokenFilter(TokenStream input) {
+ super(input);
+ }
+
+ @Override
+ public boolean incrementToken() throws IOException {
+ if (input.incrementToken()) {
+ System.out.println(input.getClass().getSimpleName() + "->" + this.reflectAsString(false));
+ return true;
+ } else {
+ return false;
+ }
+ }
+
+ @Override
+ public void end() throws IOException {
+ super.end();
+ System.out.println(input.getClass().getSimpleName() + ".end()");
+ }
+
+ @Override
+ public void close() throws IOException {
+ super.close();
+ System.out.println(input.getClass().getSimpleName() + ".close()");
+ }
+
+ @Override
+ public void reset() throws IOException {
+ super.reset();
+ System.out.println(input.getClass().getSimpleName() + ".reset()");
+ }
+ }
+
+ // LUCENE-5269
+ public void testUnicodeShinglesAndNgrams() throws Exception {
+ Analyzer analyzer = new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, reader, 2, 94);
+ //TokenStream stream = new SopTokenFilter(tokenizer);
+ TokenStream stream = new ShingleFilter(tokenizer, 5);
+ //stream = new SopTokenFilter(stream);
+ stream = new NGramTokenFilter(TEST_VERSION_CURRENT, stream, 55, 83);
+ //stream = new SopTokenFilter(stream);
+ return new TokenStreamComponents(tokenizer, stream);
+ }
+ };
+ checkRandomData(random(), analyzer, 2000);
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java Fri Oct 11 04:55:35 2013
@@ -209,15 +209,20 @@ public class EdgeNGramTokenFilterTest ex
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- Analyzer a = new Analyzer() {
- @Override
- protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- return new TokenStreamComponents(tokenizer,
- new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, EdgeNGramTokenFilter.Side.FRONT, 2, 4));
- }
- };
- checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER);
+ for (int i = 0; i < 10; i++) {
+ final int min = _TestUtil.nextInt(random(), 2, 10);
+ final int max = _TestUtil.nextInt(random(), min, 20);
+
+ Analyzer a = new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ return new TokenStreamComponents(tokenizer,
+ new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, min, max));
+ }
+ };
+ checkRandomData(random(), a, 100*RANDOM_MULTIPLIER);
+ }
Analyzer b = new Analyzer() {
@Override
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java Fri Oct 11 04:55:35 2013
@@ -107,15 +107,20 @@ public class EdgeNGramTokenizerTest exte
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- Analyzer a = new Analyzer() {
- @Override
- protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, reader, 2, 4);
- return new TokenStreamComponents(tokenizer, tokenizer);
- }
- };
- checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER, 20, false, false);
- checkRandomData(random(), a, 100*RANDOM_MULTIPLIER, 8192, false, false);
+ for (int i = 0; i < 10; i++) {
+ final int min = _TestUtil.nextInt(random(), 2, 10);
+ final int max = _TestUtil.nextInt(random(), min, 20);
+
+ Analyzer a = new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, reader, min, max);
+ return new TokenStreamComponents(tokenizer, tokenizer);
+ }
+ };
+ checkRandomData(random(), a, 100*RANDOM_MULTIPLIER, 20);
+ checkRandomData(random(), a, 10*RANDOM_MULTIPLIER, 8192);
+ }
Analyzer b = new Analyzer() {
@Override
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java Fri Oct 11 04:55:35 2013
@@ -144,15 +144,19 @@ public class NGramTokenFilterTest extend
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- Analyzer a = new Analyzer() {
- @Override
- protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- return new TokenStreamComponents(tokenizer,
- new NGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, 2, 4));
- }
- };
- checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER, 20, false, false);
+ for (int i = 0; i < 10; i++) {
+ final int min = _TestUtil.nextInt(random(), 2, 10);
+ final int max = _TestUtil.nextInt(random(), min, 20);
+ Analyzer a = new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ return new TokenStreamComponents(tokenizer,
+ new NGramTokenFilter(TEST_VERSION_CURRENT, tokenizer, min, max));
+ }
+ };
+ checkRandomData(random(), a, 200*RANDOM_MULTIPLIER, 20);
+ }
}
public void testEmptyTerm() throws Exception {
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java?rev=1531195&r1=1531194&r2=1531195&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java Fri Oct 11 04:55:35 2013
@@ -107,15 +107,19 @@ public class NGramTokenizerTest extends
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- Analyzer a = new Analyzer() {
- @Override
- protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, reader, 2, 4);
- return new TokenStreamComponents(tokenizer, tokenizer);
- }
- };
- checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER, 20, false, false);
- checkRandomData(random(), a, 50*RANDOM_MULTIPLIER, 1027, false, false);
+ for (int i = 0; i < 10; i++) {
+ final int min = _TestUtil.nextInt(random(), 2, 10);
+ final int max = _TestUtil.nextInt(random(), min, 20);
+ Analyzer a = new Analyzer() {
+ @Override
+ protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
+ Tokenizer tokenizer = new NGramTokenizer(TEST_VERSION_CURRENT, reader, min, max);
+ return new TokenStreamComponents(tokenizer, tokenizer);
+ }
+ };
+ checkRandomData(random(), a, 200*RANDOM_MULTIPLIER, 20);
+ checkRandomData(random(), a, 10*RANDOM_MULTIPLIER, 1027);
+ }
}
private static void testNGrams(int minGram, int maxGram, int length, final String nonTokenChars) throws IOException {