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 2013/04/01 18:30:05 UTC
svn commit: r1463191 [5/8] - in /lucene/dev/trunk: lucene/
lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/
lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/
lucene/analysis/common/src/java/org/apache/lucene/analysis/br/ luce...
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.fr;
import java.io.Reader;
import java.io.StringReader;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the French minimal stem factory is working.
*/
-public class TestFrenchMinimalStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestFrenchMinimalStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("chevaux");
- FrenchMinimalStemFilterFactory factory = new FrenchMinimalStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("FrenchMinimalStem").create(stream);
assertTokenStreamContents(stream, new String[] { "cheval" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("FrenchMinimalStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.ga;
import java.io.Reader;
import java.io.StringReader;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Irish lowercase filter factory is working.
*/
-public class TestIrishLowerCaseFilterFactory extends BaseTokenStreamTestCase {
+public class TestIrishLowerCaseFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testCasing() throws Exception {
Reader reader = new StringReader("nAthair tUISCE hARD");
- IrishLowerCaseFilterFactory factory = new IrishLowerCaseFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("IrishLowerCase").create(stream);
assertTokenStreamContents(stream, new String[] { "n-athair", "t-uisce", "hard" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("IrishLowerCase", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.gl;
import java.io.Reader;
import java.io.StringReader;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Galician plural stem factory is working.
*/
-public class TestGalicianMinimalStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestGalicianMinimalStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("elefantes");
- GalicianMinimalStemFilterFactory factory = new GalicianMinimalStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GalicianMinimalStem").create(stream);
assertTokenStreamContents(stream, new String[] { "elefante" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GalicianMinimalStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.gl;
import java.io.Reader;
import java.io.StringReader;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Galician stem factory is working.
*/
-public class TestGalicianStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestGalicianStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("cariñosa");
- GalicianStemFilterFactory factory = new GalicianStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GalicianStem").create(stream);
assertTokenStreamContents(stream, new String[] { "cariñ" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GalicianStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java Mon Apr 1 16:30:00 2013
@@ -19,33 +19,21 @@ package org.apache.lucene.analysis.hi;
import java.io.Reader;
import java.io.StringReader;
-import java.util.Collections;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.Tokenizer;
-import org.apache.lucene.analysis.in.IndicNormalizationFilterFactory;
-import org.apache.lucene.analysis.standard.StandardTokenizerFactory;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Hindi filter Factories are working.
*/
-public class TestHindiFilters extends BaseTokenStreamTestCase {
+public class TestHindiFilters extends BaseTokenStreamFactoryTestCase {
/**
* Test IndicNormalizationFilterFactory
*/
public void testIndicNormalizer() throws Exception {
Reader reader = new StringReader("তà§â à¤
ाà¥à¤°");
- StandardTokenizerFactory factory = new StandardTokenizerFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- IndicNormalizationFilterFactory filterFactory = new IndicNormalizationFilterFactory();
- filterFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- Map<String, String> args = Collections.emptyMap();
- factory.init(args);
- filterFactory.init(args);
- Tokenizer tokenizer = factory.create(reader);
- TokenStream stream = filterFactory.create(tokenizer);
+ TokenStream stream = tokenizerFactory("Standard").create(reader);
+ stream = tokenFilterFactory("IndicNormalization").create(stream);
assertTokenStreamContents(stream, new String[] { "à§", "à¤à¤°" });
}
@@ -54,17 +42,9 @@ public class TestHindiFilters extends Ba
*/
public void testHindiNormalizer() throws Exception {
Reader reader = new StringReader("à¥à¤¿à¤¤à¤¾à¤¬");
- StandardTokenizerFactory factory = new StandardTokenizerFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- IndicNormalizationFilterFactory indicFilterFactory = new IndicNormalizationFilterFactory();
- HindiNormalizationFilterFactory hindiFilterFactory = new HindiNormalizationFilterFactory();
- hindiFilterFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- Map<String, String> args = Collections.emptyMap();
- factory.init(args);
- hindiFilterFactory.init(args);
- Tokenizer tokenizer = factory.create(reader);
- TokenStream stream = indicFilterFactory.create(tokenizer);
- stream = hindiFilterFactory.create(stream);
+ TokenStream stream = tokenizerFactory("Standard").create(reader);
+ stream = tokenFilterFactory("IndicNormalization").create(stream);
+ stream = tokenFilterFactory("HindiNormalization").create(stream);
assertTokenStreamContents(stream, new String[] {"à¤à¤¿à¤¤à¤¾à¤¬"});
}
@@ -73,19 +53,34 @@ public class TestHindiFilters extends Ba
*/
public void testStemmer() throws Exception {
Reader reader = new StringReader("à¤à¤¿à¤¤à¤¾à¤¬à¥à¤");
- StandardTokenizerFactory factory = new StandardTokenizerFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- IndicNormalizationFilterFactory indicFilterFactory = new IndicNormalizationFilterFactory();
- HindiNormalizationFilterFactory hindiFilterFactory = new HindiNormalizationFilterFactory();
- HindiStemFilterFactory stemFactory = new HindiStemFilterFactory();
- stemFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- Map<String, String> args = Collections.emptyMap();
- factory.init(args);
- stemFactory.init(args);
- Tokenizer tokenizer = factory.create(reader);
- TokenStream stream = indicFilterFactory.create(tokenizer);
- stream = hindiFilterFactory.create(stream);
- stream = stemFactory.create(stream);
+ TokenStream stream = tokenizerFactory("Standard").create(reader);
+ stream = tokenFilterFactory("IndicNormalization").create(stream);
+ stream = tokenFilterFactory("HindiNormalization").create(stream);
+ stream = tokenFilterFactory("HindiStem").create(stream);
assertTokenStreamContents(stream, new String[] {"à¤à¤¿à¤¤à¤¾à¤¬"});
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("IndicNormalization", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+
+ try {
+ tokenFilterFactory("HindiNormalization", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+
+ try {
+ tokenFilterFactory("HindiStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.hu;
import java.io.Reader;
import java.io.StringReader;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Hungarian light stem factory is working.
*/
-public class TestHungarianLightStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestHungarianLightStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("házakat");
- HungarianLightStemFilterFactory factory = new HungarianLightStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("HungarianLightStem").create(stream);
assertTokenStreamContents(stream, new String[] { "haz" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("HungarianLightStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -19,29 +19,33 @@ package org.apache.lucene.analysis.hunsp
import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.util.ClasspathResourceLoader;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Hunspell stemmer loads from factory
*/
-public class TestHunspellStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestHunspellStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
- HunspellStemFilterFactory factory = new HunspellStemFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- args.put("dictionary", "test.dic");
- args.put("affix", "test.aff");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(new ClasspathResourceLoader(getClass()));
-
Reader reader = new StringReader("abc");
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("HunspellStem",
+ "dictionary", "test.dic",
+ "affix", "test.aff").create(stream);
assertTokenStreamContents(stream, new String[] { "ab" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("HunspellStem",
+ "dictionary", "test.dic",
+ "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -19,28 +19,22 @@ package org.apache.lucene.analysis.id;
import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Indonesian stem filter factory is working.
*/
-public class TestIndonesianStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestIndonesianStemFilterFactory extends BaseTokenStreamFactoryTestCase {
/**
* Ensure the filter actually stems text.
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("dibukukannya");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- IndonesianStemFilterFactory factory = new IndonesianStemFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- factory.init(args);
- TokenStream stream = factory.create(tokenizer);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("IndonesianStem").create(stream);
assertTokenStreamContents(stream, new String[] { "buku" });
}
@@ -49,12 +43,18 @@ public class TestIndonesianStemFilterFac
*/
public void testStemmingInflectional() throws Exception {
Reader reader = new StringReader("dibukukannya");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- IndonesianStemFilterFactory factory = new IndonesianStemFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- args.put("stemDerivational", "false");
- factory.init(args);
- TokenStream stream = factory.create(tokenizer);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("IndonesianStem", "stemDerivational", "false").create(stream);
assertTokenStreamContents(stream, new String[] { "dibukukan" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("IndonesianStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.it;
import java.io.Reader;
import java.io.StringReader;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Italian light stem factory is working.
*/
-public class TestItalianLightStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestItalianLightStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("ragazzo ragazzi");
- ItalianLightStemFilterFactory factory = new ItalianLightStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("ItalianLightStem").create(stream);
assertTokenStreamContents(stream, new String[] { "ragazz", "ragazz" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("ItalianLightStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.lv;
import java.io.Reader;
import java.io.StringReader;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Latvian stem factory is working.
*/
-public class TestLatvianStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestLatvianStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("tirgiem tirgus");
- LatvianStemFilterFactory factory = new LatvianStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("LatvianStem").create(stream);
assertTokenStreamContents(stream, new String[] { "tirg", "tirg" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("LatvianStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -17,127 +17,188 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
+import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
-/**
- *
- */
-public class TestCapitalizationFilterFactory extends BaseTokenStreamTestCase {
+public class TestCapitalizationFilterFactory extends BaseTokenStreamFactoryTestCase {
+
+ public void testCapitalization() throws Exception {
+ Reader reader = new StringReader("kiTTEN");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "Kitten" });
+ }
+
+ public void testCapitalization2() throws Exception {
+ Reader reader = new StringReader("and");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "And" });
+ }
+
+ /** first is forced, but it's not a keep word, either */
+ public void testCapitalization3() throws Exception {
+ Reader reader = new StringReader("AnD");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "And" });
+ }
+
+ public void testCapitalization4() throws Exception {
+ Reader reader = new StringReader("AnD");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "false").create(stream);
+ assertTokenStreamContents(stream, new String[] { "And" });
+ }
+
+ public void testCapitalization5() throws Exception {
+ Reader reader = new StringReader("big");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "Big" });
+ }
+
+ public void testCapitalization6() throws Exception {
+ Reader reader = new StringReader("BIG");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "BIG" });
+ }
+
+ public void testCapitalization7() throws Exception {
+ Reader reader = new StringReader("Hello thEre my Name is Ryan");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "Hello there my name is ryan" });
+ }
+
+ public void testCapitalization8() throws Exception {
+ Reader reader = new StringReader("Hello thEre my Name is Ryan");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "false",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "Hello", "There", "My", "Name", "Is", "Ryan" });
+ }
- public void testCapitalization() throws Exception
- {
- Map<String,String> args = new HashMap<String, String>();
- args.put( CapitalizationFilterFactory.KEEP, "and the it BIG" );
- args.put( CapitalizationFilterFactory.ONLY_FIRST_WORD, "true" );
-
- CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init( args );
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.WHITESPACE, false)),
- new String[] { "Kitten" });
-
- factory.forceFirstLetter = true;
-
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("and"), MockTokenizer.WHITESPACE, false)),
- new String[] { "And" });
-
- //first is forced, but it's not a keep word, either
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("AnD"), MockTokenizer.WHITESPACE, false)),
- new String[] { "And" });
-
- factory.forceFirstLetter = false;
-
- //first is not forced, but it's not a keep word, either
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("AnD"), MockTokenizer.WHITESPACE, false)),
- new String[] { "And" });
-
- factory.forceFirstLetter = true;
-
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("big"), MockTokenizer.WHITESPACE, false)),
- new String[] { "Big" });
-
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("BIG"), MockTokenizer.WHITESPACE, false)),
- new String[] { "BIG" });
-
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("Hello thEre my Name is Ryan"), MockTokenizer.KEYWORD, false)),
- new String[] { "Hello there my name is ryan" });
-
- // now each token
- factory.onlyFirstWord = false;
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("Hello thEre my Name is Ryan"), MockTokenizer.WHITESPACE, false)),
- new String[] { "Hello", "There", "My", "Name", "Is", "Ryan" });
-
- // now only the long words
- factory.minWordLength = 3;
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("Hello thEre my Name is Ryan"), MockTokenizer.WHITESPACE, false)),
- new String[] { "Hello", "There", "my", "Name", "is", "Ryan" });
-
- // without prefix
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("McKinley"), MockTokenizer.WHITESPACE, false)),
- new String[] { "Mckinley" });
-
- // Now try some prefixes
- factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- args.put( "okPrefix", "McK" ); // all words
- factory.init( args );
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("McKinley"), MockTokenizer.WHITESPACE, false)),
- new String[] { "McKinley" });
-
- // now try some stuff with numbers
- factory.forceFirstLetter = false;
- factory.onlyFirstWord = false;
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("1st 2nd third"), MockTokenizer.WHITESPACE, false)),
- new String[] { "1st", "2nd", "Third" });
-
- factory.forceFirstLetter = true;
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("the The the"), MockTokenizer.KEYWORD, false)),
- new String[] { "The The the" });
+ public void testCapitalization9() throws Exception {
+ Reader reader = new StringReader("Hello thEre my Name is Ryan");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "false",
+ "minWordLength", "3",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "Hello", "There", "my", "Name", "is", "Ryan" });
+ }
+
+ public void testCapitalization10() throws Exception {
+ Reader reader = new StringReader("McKinley");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "false",
+ "minWordLength", "3",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "Mckinley" });
+ }
+
+ /** using "McK" as okPrefix */
+ public void testCapitalization11() throws Exception {
+ Reader reader = new StringReader("McKinley");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "false",
+ "minWordLength", "3",
+ "okPrefix", "McK",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "McKinley" });
+ }
+
+ /** test with numbers */
+ public void testCapitalization12() throws Exception {
+ Reader reader = new StringReader("1st 2nd third");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "false",
+ "minWordLength", "3",
+ "okPrefix", "McK",
+ "forceFirstLetter", "false").create(stream);
+ assertTokenStreamContents(stream, new String[] { "1st", "2nd", "Third" });
+ }
+
+ public void testCapitalization13() throws Exception {
+ Reader reader = new StringReader("the The the");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "and the it BIG",
+ "onlyFirstWord", "false",
+ "minWordLength", "3",
+ "okPrefix", "McK",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "The The the" });
}
public void testKeepIgnoreCase() throws Exception {
- Map<String,String> args = new HashMap<String, String>();
- args.put( CapitalizationFilterFactory.KEEP, "kitten" );
- args.put( CapitalizationFilterFactory.KEEP_IGNORE_CASE, "true" );
- args.put( CapitalizationFilterFactory.ONLY_FIRST_WORD, "true" );
-
- CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init( args );
- factory.forceFirstLetter = true;
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.KEYWORD, false)),
- new String[] { "KiTTEN" });
-
- factory.forceFirstLetter = false;
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.KEYWORD, false)),
- new String[] { "kiTTEN" });
-
- factory.keep = null;
- assertTokenStreamContents(factory.create(
- new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.KEYWORD, false)),
- new String[] { "Kitten" });
+ Reader reader = new StringReader("kiTTEN");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "kitten",
+ "keepIgnoreCase", "true",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "true").create(stream);
+
+ assertTokenStreamContents(stream, new String[] { "KiTTEN" });
+ }
+
+ public void testKeepIgnoreCase2() throws Exception {
+ Reader reader = new StringReader("kiTTEN");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "kitten",
+ "keepIgnoreCase", "true",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "false").create(stream);
+
+ assertTokenStreamContents(stream, new String[] { "kiTTEN" });
+ }
+
+ public void testKeepIgnoreCase3() throws Exception {
+ Reader reader = new StringReader("kiTTEN");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keepIgnoreCase", "true",
+ "onlyFirstWord", "true",
+ "forceFirstLetter", "false").create(stream);
+
+ assertTokenStreamContents(stream, new String[] { "Kitten" });
}
/**
@@ -146,16 +207,12 @@ public class TestCapitalizationFilterFac
* This is very weird when combined with ONLY_FIRST_WORD!!!
*/
public void testMinWordLength() throws Exception {
- Map<String,String> args = new HashMap<String,String>();
- args.put(CapitalizationFilterFactory.ONLY_FIRST_WORD, "true");
- args.put(CapitalizationFilterFactory.MIN_WORD_LENGTH, "5");
- CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- Tokenizer tokenizer = new MockTokenizer(new StringReader(
- "helo testing"), MockTokenizer.WHITESPACE, false);
- TokenStream ts = factory.create(tokenizer);
- assertTokenStreamContents(ts, new String[] {"helo", "Testing"});
+ Reader reader = new StringReader("helo testing");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "onlyFirstWord", "true",
+ "minWordLength", "5").create(stream);
+ assertTokenStreamContents(stream, new String[] { "helo", "Testing" });
}
/**
@@ -163,30 +220,22 @@ public class TestCapitalizationFilterFac
* in each token (it should do nothing)
*/
public void testMaxWordCount() throws Exception {
- Map<String,String> args = new HashMap<String,String>();
- args.put(CapitalizationFilterFactory.MAX_WORD_COUNT, "2");
- CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- Tokenizer tokenizer = new MockTokenizer(new StringReader(
- "one two three four"), MockTokenizer.WHITESPACE, false);
- TokenStream ts = factory.create(tokenizer);
- assertTokenStreamContents(ts, new String[] {"One", "Two", "Three", "Four"});
+ Reader reader = new StringReader("one two three four");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "maxWordCount", "2").create(stream);
+ assertTokenStreamContents(stream, new String[] { "One", "Two", "Three", "Four" });
}
/**
* Test CapitalizationFilterFactory's maxWordCount option when exceeded
*/
public void testMaxWordCount2() throws Exception {
- Map<String,String> args = new HashMap<String,String>();
- args.put(CapitalizationFilterFactory.MAX_WORD_COUNT, "2");
- CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- Tokenizer tokenizer = new MockTokenizer(new StringReader(
- "one two three four"), MockTokenizer.KEYWORD, false);
- TokenStream ts = factory.create(tokenizer);
- assertTokenStreamContents(ts, new String[] {"one two three four"});
+ Reader reader = new StringReader("one two three four");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+ stream = tokenFilterFactory("Capitalization",
+ "maxWordCount", "2").create(stream);
+ assertTokenStreamContents(stream, new String[] { "one two three four" });
}
/**
@@ -195,29 +244,32 @@ public class TestCapitalizationFilterFac
* This is weird, it is not really a max, but inclusive (look at 'is')
*/
public void testMaxTokenLength() throws Exception {
- Map<String,String> args = new HashMap<String,String>();
- args.put(CapitalizationFilterFactory.MAX_TOKEN_LENGTH, "2");
- CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- Tokenizer tokenizer = new MockTokenizer(new StringReader(
- "this is a test"), MockTokenizer.WHITESPACE, false);
- TokenStream ts = factory.create(tokenizer);
- assertTokenStreamContents(ts, new String[] {"this", "is", "A", "test"});
+ Reader reader = new StringReader("this is a test");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "maxTokenLength", "2").create(stream);
+ assertTokenStreamContents(stream, new String[] { "this", "is", "A", "test" });
}
/**
* Test CapitalizationFilterFactory's forceFirstLetter option
*/
- public void testForceFirstLetter() throws Exception {
- Map<String,String> args = new HashMap<String,String>();
- args.put(CapitalizationFilterFactory.KEEP, "kitten");
- args.put(CapitalizationFilterFactory.FORCE_FIRST_LETTER, "true");
- CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- Tokenizer tokenizer = new MockTokenizer(new StringReader("kitten"), MockTokenizer.WHITESPACE, false);
- TokenStream ts = factory.create(tokenizer);
- assertTokenStreamContents(ts, new String[] {"Kitten"});
+ public void testForceFirstLetterWithKeep() throws Exception {
+ Reader reader = new StringReader("kitten");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Capitalization",
+ "keep", "kitten",
+ "forceFirstLetter", "true").create(stream);
+ assertTokenStreamContents(stream, new String[] { "Kitten" });
+ }
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("Capitalization", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeepFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeepFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeepFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeepFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -17,45 +17,38 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.ClasspathResourceLoader;
import org.apache.lucene.analysis.util.ResourceLoader;
-import java.util.Map;
-import java.util.HashMap;
-
-/**
- *
- *
- **/
-public class TestKeepFilterFactory extends BaseTokenStreamTestCase {
+public class TestKeepFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testInform() throws Exception {
ResourceLoader loader = new ClasspathResourceLoader(getClass());
assertTrue("loader is null and it shouldn't be", loader != null);
- KeepWordFilterFactory factory = new KeepWordFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put("words", "keep-1.txt");
- args.put("ignoreCase", "true");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
+ KeepWordFilterFactory factory = (KeepWordFilterFactory) tokenFilterFactory("KeepWord",
+ "words", "keep-1.txt",
+ "ignoreCase", "true");
CharArraySet words = factory.getWords();
assertTrue("words is null and it shouldn't be", words != null);
assertTrue("words Size: " + words.size() + " is not: " + 2, words.size() == 2);
-
- factory = new KeepWordFilterFactory();
- args.put("words", "keep-1.txt, keep-2.txt");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
+ factory = (KeepWordFilterFactory) tokenFilterFactory("KeepWord",
+ "words", "keep-1.txt, keep-2.txt",
+ "ignoreCase", "true");
words = factory.getWords();
assertTrue("words is null and it shouldn't be", words != null);
assertTrue("words Size: " + words.size() + " is not: " + 4, words.size() == 4);
-
-
-
+ }
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("KeepWord", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
}
}
\ No newline at end of file
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeywordMarkerFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeywordMarkerFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeywordMarkerFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeywordMarkerFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -17,114 +17,89 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
-import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
-import org.apache.lucene.analysis.en.PorterStemFilter;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.Tokenizer;
-import org.apache.lucene.analysis.util.ResourceLoader;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
import org.apache.lucene.analysis.util.StringMockResourceLoader;
/**
* Simple tests to ensure the keyword marker filter factory is working.
*/
-public class TestKeywordMarkerFilterFactory extends BaseTokenStreamTestCase {
+public class TestKeywordMarkerFilterFactory extends BaseTokenStreamFactoryTestCase {
- public void testKeywords() throws IOException {
+ public void testKeywords() throws Exception {
Reader reader = new StringReader("dogs cats");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- KeywordMarkerFilterFactory factory = new KeywordMarkerFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- ResourceLoader loader = new StringMockResourceLoader("cats");
- args.put("protected", "protwords.txt");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
-
- TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "dog", "cats" });
-
-
- reader = new StringReader("dogs cats");
- tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- factory = new KeywordMarkerFilterFactory();
- args = new HashMap<String,String>();
-
- args.put("pattern", "cats|Dogs");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(null);
-
- ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "dog", "cats" });
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("KeywordMarker", TEST_VERSION_CURRENT,
+ new StringMockResourceLoader("cats"),
+ "protected", "protwords.txt").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);
+ assertTokenStreamContents(stream, new String[] { "dog", "cats" });
}
- public void testKeywordsMixed() throws IOException {
+ public void testKeywords2() throws Exception {
+ Reader reader = new StringReader("dogs cats");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("KeywordMarker",
+ "pattern", "cats|Dogs").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);
+ assertTokenStreamContents(stream, new String[] { "dog", "cats" });
+ }
+
+ public void testKeywordsMixed() throws Exception {
Reader reader = new StringReader("dogs cats birds");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- KeywordMarkerFilterFactory factory = new KeywordMarkerFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- ResourceLoader loader = new StringMockResourceLoader("cats");
- args.put("protected", "protwords.txt");
- args.put("pattern", "birds|Dogs");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
-
- TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "dog", "cats", "birds" });
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("KeywordMarker", TEST_VERSION_CURRENT,
+ new StringMockResourceLoader("cats"),
+ "protected", "protwords.txt",
+ "pattern", "birds|Dogs").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);
+ assertTokenStreamContents(stream, new String[] { "dog", "cats", "birds" });
+ }
+
+ public void testKeywordsCaseInsensitive() throws Exception {
+ Reader reader = new StringReader("dogs cats Cats");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("KeywordMarker", TEST_VERSION_CURRENT,
+ new StringMockResourceLoader("cats"),
+ "protected", "protwords.txt",
+ "ignoreCase", "true").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);
+ assertTokenStreamContents(stream, new String[] { "dog", "cats", "Cats" });
}
- public void testKeywordsCaseInsensitive() throws IOException {
+ public void testKeywordsCaseInsensitive2() throws Exception {
Reader reader = new StringReader("dogs cats Cats");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- KeywordMarkerFilterFactory factory = new KeywordMarkerFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- ResourceLoader loader = new StringMockResourceLoader("cats");
- args.put("protected", "protwords.txt");
- args.put("ignoreCase", "true");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
-
- TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "dog", "cats", "Cats" });
-
- reader = new StringReader("dogs cats Cats");
- tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- factory = new KeywordMarkerFilterFactory();
- args = new HashMap<String,String>();
-
- args.put("pattern", "Cats");
- args.put("ignoreCase", "true");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(null);
-
- ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "dog", "cats", "Cats" });
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("KeywordMarker",
+ "pattern", "Cats",
+ "ignoreCase", "true").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);;
+ assertTokenStreamContents(stream, new String[] { "dog", "cats", "Cats" });
}
- public void testKeywordsCaseInsensitiveMixed() throws IOException {
+ public void testKeywordsCaseInsensitiveMixed() throws Exception {
Reader reader = new StringReader("dogs cats Cats Birds birds");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- KeywordMarkerFilterFactory factory = new KeywordMarkerFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- ResourceLoader loader = new StringMockResourceLoader("cats");
- args.put("protected", "protwords.txt");
- args.put("pattern", "birds");
- args.put("ignoreCase", "true");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
-
- TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "dog", "cats", "Cats", "Birds", "birds" });
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("KeywordMarker", TEST_VERSION_CURRENT,
+ new StringMockResourceLoader("cats"),
+ "protected", "protwords.txt",
+ "pattern", "birds",
+ "ignoreCase", "true").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);
+ assertTokenStreamContents(stream, new String[] { "dog", "cats", "Cats", "Birds", "birds" });
+ }
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("KeywordMarker", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLengthFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLengthFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLengthFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLengthFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -16,35 +16,44 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
-import java.io.IOException;
+import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
-public class TestLengthFilterFactory extends BaseTokenStreamTestCase {
+public class TestLengthFilterFactory extends BaseTokenStreamFactoryTestCase {
- public void test() throws IOException {
- LengthFilterFactory factory = new LengthFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put(LengthFilterFactory.MIN_KEY, String.valueOf(4));
- args.put(LengthFilterFactory.MAX_KEY, String.valueOf(10));
- // default: args.put("enablePositionIncrements", "false");
- factory.init(args);
- String test = "foo foobar super-duper-trooper";
- TokenStream stream = factory.create(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
+ public void test() throws Exception {
+ Reader reader = new StringReader("foo foobar super-duper-trooper");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Length",
+ "min", "4",
+ "max", "10").create(stream);
assertTokenStreamContents(stream, new String[] { "foobar" }, new int[] { 1 });
+ }
- factory = new LengthFilterFactory();
- args = new HashMap<String, String>();
- args.put(LengthFilterFactory.MIN_KEY, String.valueOf(4));
- args.put(LengthFilterFactory.MAX_KEY, String.valueOf(10));
- args.put("enablePositionIncrements", "true");
- factory.init(args);
- stream = factory.create(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
+ public void testPositionIncrements() throws Exception {
+ Reader reader = new StringReader("foo foobar super-duper-trooper");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("Length",
+ "min", "4",
+ "max", "10",
+ "enablePositionIncrements", "true").create(stream);
assertTokenStreamContents(stream, new String[] { "foobar" }, new int[] { 2 });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("Length",
+ "min", "4",
+ "max", "5",
+ "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
\ No newline at end of file
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenCountFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenCountFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenCountFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenCountFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -16,40 +16,46 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
-import java.io.IOException;
+import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
-public class TestLimitTokenCountFilterFactory extends BaseTokenStreamTestCase {
+public class TestLimitTokenCountFilterFactory extends BaseTokenStreamFactoryTestCase {
- public void test() throws IOException {
- LimitTokenCountFilterFactory factory = new LimitTokenCountFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put(LimitTokenCountFilterFactory.MAX_TOKEN_COUNT_KEY, "3");
- factory.init(args);
- String test = "A1 B2 C3 D4 E5 F6";
- MockTokenizer tok = new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false);
+ public void test() throws Exception {
+ Reader reader = new StringReader("A1 B2 C3 D4 E5 F6");
+ MockTokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
// LimitTokenCountFilter doesn't consume the entire stream that it wraps
- tok.setEnableChecks(false);
- TokenStream stream = factory.create(tok);
+ tokenizer.setEnableChecks(false);
+ TokenStream stream = tokenizer;
+ stream = tokenFilterFactory("LimitTokenCount",
+ "maxTokenCount", "3").create(stream);
assertTokenStreamContents(stream, new String[] { "A1", "B2", "C3" });
+ }
+ public void testRequired() throws Exception {
// param is required
- factory = new LimitTokenCountFilterFactory();
- args = new HashMap<String, String>();
- IllegalArgumentException iae = null;
try {
- factory.init(args);
+ tokenFilterFactory("LimitTokenCount");
+ fail();
} catch (IllegalArgumentException e) {
assertTrue("exception doesn't mention param: " + e.getMessage(),
0 < e.getMessage().indexOf(LimitTokenCountFilterFactory.MAX_TOKEN_COUNT_KEY));
- iae = e;
}
- assertNotNull("no exception thrown", iae);
+ }
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("LimitTokenCount",
+ "maxTokenCount", "3",
+ "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenPositionFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenPositionFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenPositionFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLimitTokenPositionFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -16,69 +16,69 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
-import java.io.IOException;
+import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.shingle.ShingleFilter;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
-public class TestLimitTokenPositionFilterFactory extends BaseTokenStreamTestCase {
+public class TestLimitTokenPositionFilterFactory extends BaseTokenStreamFactoryTestCase {
- public void testMaxPosition1() throws IOException {
- LimitTokenPositionFilterFactory factory = new LimitTokenPositionFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put(LimitTokenPositionFilterFactory.MAX_TOKEN_POSITION_KEY, "1");
- factory.init(args);
- String test = "A1 B2 C3 D4 E5 F6";
- MockTokenizer tok = new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false);
+ public void testMaxPosition1() throws Exception {
+ Reader reader = new StringReader("A1 B2 C3 D4 E5 F6");
+ MockTokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
// LimitTokenPositionFilter doesn't consume the entire stream that it wraps
- tok.setEnableChecks(false);
- TokenStream stream = factory.create(tok);
+ tokenizer.setEnableChecks(false);
+ TokenStream stream = tokenizer;
+ stream = tokenFilterFactory("LimitTokenPosition",
+ "maxTokenPosition", "1").create(stream);
assertTokenStreamContents(stream, new String[] { "A1" });
}
- public void testMissingParam() {
- LimitTokenPositionFilterFactory factory = new LimitTokenPositionFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- IllegalArgumentException iae = null;
+ public void testMissingParam() throws Exception {
try {
- factory.init(args);
+ tokenFilterFactory("LimitTokenPosition");
+ fail();
} catch (IllegalArgumentException e) {
assertTrue("exception doesn't mention param: " + e.getMessage(),
0 < e.getMessage().indexOf(LimitTokenPositionFilterFactory.MAX_TOKEN_POSITION_KEY));
- iae = e;
}
- assertNotNull("no exception thrown", iae);
}
- public void testMaxPosition1WithShingles() throws IOException {
- LimitTokenPositionFilterFactory factory = new LimitTokenPositionFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put(LimitTokenPositionFilterFactory.MAX_TOKEN_POSITION_KEY, "1");
- factory.init(args);
- String input = "one two three four five";
- MockTokenizer tok = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
+ public void testMaxPosition1WithShingles() throws Exception {
+ Reader reader = new StringReader("one two three four five");
+ MockTokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
// LimitTokenPositionFilter doesn't consume the entire stream that it wraps
- tok.setEnableChecks(false);
- ShingleFilter shingleFilter = new ShingleFilter(tok, 2, 3);
- shingleFilter.setOutputUnigrams(true);
- TokenStream stream = factory.create(shingleFilter);
+ tokenizer.setEnableChecks(false);
+ TokenStream stream = tokenizer;
+ stream = tokenFilterFactory("Shingle",
+ "minShingleSize", "2",
+ "maxShingleSize", "3",
+ "outputUnigrams", "true").create(stream);
+ stream = tokenFilterFactory("LimitTokenPosition",
+ "maxTokenPosition", "1").create(stream);
assertTokenStreamContents(stream, new String[] { "one", "one two", "one two three" });
}
- public void testConsumeAllTokens() throws IOException {
- LimitTokenPositionFilterFactory factory = new LimitTokenPositionFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put(LimitTokenPositionFilterFactory.MAX_TOKEN_POSITION_KEY, "3");
- args.put(LimitTokenPositionFilterFactory.CONSUME_ALL_TOKENS_KEY, "true");
- factory.init(args);
- String test = "A1 B2 C3 D4 E5 F6";
- MockTokenizer tok = new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false);
- TokenStream stream = factory.create(tok);
+ public void testConsumeAllTokens() throws Exception {
+ Reader reader = new StringReader("A1 B2 C3 D4 E5 F6");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("LimitTokenPosition",
+ "maxTokenPosition", "3",
+ "consumeAllTokens", "true").create(stream);
assertTokenStreamContents(stream, new String[] { "A1", "B2", "C3" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("LimitTokenPosition",
+ "maxTokenPosition", "3",
+ "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -17,54 +17,24 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.CannedTokenStream;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
-
-import java.util.Iterator;
-import java.util.Arrays;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/** Simple tests to ensure this factory is working */
-public class TestRemoveDuplicatesTokenFilterFactory extends BaseTokenStreamTestCase {
+public class TestRemoveDuplicatesTokenFilterFactory extends BaseTokenStreamFactoryTestCase {
public static Token tok(int pos, String t, int start, int end) {
Token tok = new Token(t,start,end);
tok.setPositionIncrement(pos);
return tok;
}
- public static Token tok(int pos, String t) {
- return tok(pos, t, 0,0);
- }
- public void testDups(final String expected, final Token... tokens)
- throws Exception {
-
- final Iterator<Token> toks = Arrays.asList(tokens).iterator();
- RemoveDuplicatesTokenFilterFactory factory = new RemoveDuplicatesTokenFilterFactory();
- final TokenStream ts = factory.create
- (new TokenStream() {
- CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
- OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
- PositionIncrementAttribute posIncAtt = addAttribute(PositionIncrementAttribute.class);
- @Override
- public boolean incrementToken() {
- if (toks.hasNext()) {
- clearAttributes();
- Token tok = toks.next();
- termAtt.setEmpty().append(tok);
- offsetAtt.setOffset(tok.startOffset(), tok.endOffset());
- posIncAtt.setPositionIncrement(tok.getPositionIncrement());
- return true;
- } else {
- return false;
- }
- }
- });
-
- assertTokenStreamContents(ts, expected.split("\\s"));
+ public void testDups(final String expected, final Token... tokens) throws Exception {
+ TokenStream stream = new CannedTokenStream(tokens);
+ stream = tokenFilterFactory("RemoveDuplicates").create(stream);
+ assertTokenStreamContents(stream, expected.split("\\s"));
}
public void testSimpleDups() throws Exception {
@@ -77,4 +47,14 @@ public class TestRemoveDuplicatesTokenFi
,tok(1,"E",21, 25)
);
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("RemoveDuplicates", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestStemmerOverrideFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestStemmerOverrideFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestStemmerOverrideFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestStemmerOverrideFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -17,53 +17,49 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
-import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
-import org.apache.lucene.analysis.en.PorterStemFilter;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.Tokenizer;
-import org.apache.lucene.analysis.util.ResourceLoader;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
import org.apache.lucene.analysis.util.StringMockResourceLoader;
/**
* Simple tests to ensure the stemmer override filter factory is working.
*/
-public class TestStemmerOverrideFilterFactory extends BaseTokenStreamTestCase {
- public void testKeywords() throws IOException {
+public class TestStemmerOverrideFilterFactory extends BaseTokenStreamFactoryTestCase {
+ public void testKeywords() throws Exception {
// our stemdict stems dogs to 'cat'
Reader reader = new StringReader("testing dogs");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- StemmerOverrideFilterFactory factory = new StemmerOverrideFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- ResourceLoader loader = new StringMockResourceLoader("dogs\tcat");
- args.put("dictionary", "stemdict.txt");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
-
- TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "test", "cat" });
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("StemmerOverride", TEST_VERSION_CURRENT,
+ new StringMockResourceLoader("dogs\tcat"),
+ "dictionary", "stemdict.txt").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);
+
+ assertTokenStreamContents(stream, new String[] { "test", "cat" });
}
- public void testKeywordsCaseInsensitive() throws IOException {
+ public void testKeywordsCaseInsensitive() throws Exception {
Reader reader = new StringReader("testing DoGs");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- StemmerOverrideFilterFactory factory = new StemmerOverrideFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- ResourceLoader loader = new StringMockResourceLoader("dogs\tcat");
- args.put("dictionary", "stemdict.txt");
- args.put("ignoreCase", "true");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("StemmerOverride", TEST_VERSION_CURRENT,
+ new StringMockResourceLoader("dogs\tcat"),
+ "dictionary", "stemdict.txt",
+ "ignoreCase", "true").create(stream);
+ stream = tokenFilterFactory("PorterStem").create(stream);
- TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
- assertTokenStreamContents(ts, new String[] { "test", "cat" });
+ assertTokenStreamContents(stream, new String[] { "test", "cat" });
+ }
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("StemmerOverride", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilterFactory.java?rev=1463191&r1=1463190&r2=1463191&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilterFactory.java Mon Apr 1 16:30:00 2013
@@ -17,24 +17,31 @@ package org.apache.lucene.analysis.misce
* limitations under the License.
*/
+import java.io.Reader;
import java.io.StringReader;
-import java.util.HashMap;
-import java.util.Map;
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure this factory is working
*/
-public class TestTrimFilterFactory extends BaseTokenStreamTestCase {
+public class TestTrimFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testTrimming() throws Exception {
- TrimFilterFactory factory = new TrimFilterFactory();
- Map<String,String> args = new HashMap<String,String>();
- args.put("updateOffsets", "false");
- factory.init(args);
- TokenStream ts = factory.create(new MockTokenizer(new StringReader("trim me "), MockTokenizer.KEYWORD, false));
- assertTokenStreamContents(ts, new String[] { "trim me" });
+ Reader reader = new StringReader("trim me ");
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+ stream = tokenFilterFactory("Trim").create(stream);
+ assertTokenStreamContents(stream, new String[] { "trim me" });
+ }
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("Trim", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
}
}