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 2013/04/06 13:08:21 UTC
svn commit: r1465224 [5/9] - in /lucene/dev/branches/branch_4x: ./ lucene/
lucene/analysis/
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/or...
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -17,51 +17,36 @@ package org.apache.lucene.analysis.core;
* 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 TestStopFilterFactory extends BaseTokenStreamTestCase {
+public class TestStopFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testInform() throws Exception {
ResourceLoader loader = new ClasspathResourceLoader(getClass());
assertTrue("loader is null and it shouldn't be", loader != null);
- StopFilterFactory factory = new StopFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put("words", "stop-1.txt");
- args.put("ignoreCase", "true");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
+ StopFilterFactory factory = (StopFilterFactory) tokenFilterFactory("Stop",
+ "words", "stop-1.txt",
+ "ignoreCase", "true");
CharArraySet words = factory.getStopWords();
assertTrue("words is null and it shouldn't be", words != null);
assertTrue("words Size: " + words.size() + " is not: " + 2, words.size() == 2);
assertTrue(factory.isIgnoreCase() + " does not equal: " + true, factory.isIgnoreCase() == true);
- factory = new StopFilterFactory();
- args.put("words", "stop-1.txt, stop-2.txt");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
+ factory = (StopFilterFactory) tokenFilterFactory("Stop",
+ "words", "stop-1.txt, stop-2.txt",
+ "ignoreCase", "true");
words = factory.getStopWords();
assertTrue("words is null and it shouldn't be", words != null);
assertTrue("words Size: " + words.size() + " is not: " + 4, words.size() == 4);
assertTrue(factory.isIgnoreCase() + " does not equal: " + true, factory.isIgnoreCase() == true);
- factory = new StopFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- args.put("words", "stop-snowball.txt");
- args.put("format", "snowball");
- factory.init(args);
- factory.inform(loader);
+ factory = (StopFilterFactory) tokenFilterFactory("Stop",
+ "words", "stop-snowball.txt",
+ "format", "snowball",
+ "ignoreCase", "true");
words = factory.getStopWords();
assertEquals(8, words.size());
assertTrue(words.contains("he"));
@@ -73,4 +58,14 @@ public class TestStopFilterFactory exten
assertTrue(words.contains("hers"));
assertTrue(words.contains("herself"));
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("Stop", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestTypeTokenFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestTypeTokenFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestTypeTokenFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestTypeTokenFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -17,88 +17,73 @@ package org.apache.lucene.analysis.core;
* limitations under the License.
*/
-import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.NumericTokenStream;
-import org.apache.lucene.analysis.util.ClasspathResourceLoader;
-import org.apache.lucene.analysis.util.ResourceLoader;
-import org.junit.Test;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
+import org.apache.lucene.analysis.util.TokenFilterFactory;
-import java.util.HashMap;
-import java.util.Map;
import java.util.Set;
/**
* Testcase for {@link TypeTokenFilterFactory}
*/
-public class TestTypeTokenFilterFactory extends BaseTokenStreamTestCase {
+public class TestTypeTokenFilterFactory extends BaseTokenStreamFactoryTestCase {
- @Test
public void testInform() throws Exception {
- ResourceLoader loader = new ClasspathResourceLoader(getClass());
- TypeTokenFilterFactory factory = new TypeTokenFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put("types", "stoptypes-1.txt");
- args.put("enablePositionIncrements", "true");
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- factory.init(args);
- factory.inform(loader);
+ TypeTokenFilterFactory factory = (TypeTokenFilterFactory) tokenFilterFactory("Type",
+ "types", "stoptypes-1.txt",
+ "enablePositionIncrements", "true");
Set<String> types = factory.getStopTypes();
assertTrue("types is null and it shouldn't be", types != null);
assertTrue("types Size: " + types.size() + " is not: " + 2, types.size() == 2);
assertTrue("enablePositionIncrements was set to true but not correctly parsed", factory.isEnablePositionIncrements());
- factory = new TypeTokenFilterFactory();
- args.put("types", "stoptypes-1.txt, stoptypes-2.txt");
- args.put("enablePositionIncrements", "false");
- args.put("useWhitelist","true");
- factory.init(args);
- factory.inform(loader);
+ factory = (TypeTokenFilterFactory) tokenFilterFactory("Type",
+ "types", "stoptypes-1.txt, stoptypes-2.txt",
+ "enablePositionIncrements", "false",
+ "useWhitelist", "true");
types = factory.getStopTypes();
assertTrue("types is null and it shouldn't be", types != null);
assertTrue("types Size: " + types.size() + " is not: " + 4, types.size() == 4);
assertTrue("enablePositionIncrements was set to false but not correctly parsed", !factory.isEnablePositionIncrements());
}
- @Test
public void testCreationWithBlackList() throws Exception {
- TypeTokenFilterFactory typeTokenFilterFactory = new TypeTokenFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put("types", "stoptypes-1.txt, stoptypes-2.txt");
- args.put("enablePositionIncrements", "false");
- typeTokenFilterFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- typeTokenFilterFactory.init(args);
+ TokenFilterFactory factory = tokenFilterFactory("Type",
+ "types", "stoptypes-1.txt, stoptypes-2.txt",
+ "enablePositionIncrements", "false");
NumericTokenStream input = new NumericTokenStream();
input.setIntValue(123);
- typeTokenFilterFactory.create(input);
+ factory.create(input);
}
- @Test
- public void testCreationWithWhiteList() throws Exception {
- TypeTokenFilterFactory typeTokenFilterFactory = new TypeTokenFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put("types", "stoptypes-1.txt, stoptypes-2.txt");
- args.put("enablePositionIncrements", "false");
- args.put("useWhitelist","true");
- typeTokenFilterFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- typeTokenFilterFactory.init(args);
- NumericTokenStream input = new NumericTokenStream();
- input.setIntValue(123);
- typeTokenFilterFactory.create(input);
- }
+ public void testCreationWithWhiteList() throws Exception {
+ TokenFilterFactory factory = tokenFilterFactory("Type",
+ "types", "stoptypes-1.txt, stoptypes-2.txt",
+ "enablePositionIncrements", "false",
+ "useWhitelist", "true");
+ NumericTokenStream input = new NumericTokenStream();
+ input.setIntValue(123);
+ factory.create(input);
+ }
- @Test
public void testMissingTypesParameter() throws Exception {
try {
- TypeTokenFilterFactory typeTokenFilterFactory = new TypeTokenFilterFactory();
- Map<String, String> args = new HashMap<String, String>();
- args.put("enablePositionIncrements", "false");
- typeTokenFilterFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- typeTokenFilterFactory.init(args);
- typeTokenFilterFactory.inform(new ClasspathResourceLoader(getClass()));
+ tokenFilterFactory("Type", "enablePositionIncrements", "false");
fail("not supplying 'types' parameter should cause an IllegalArgumentException");
} catch (IllegalArgumentException e) {
// everything ok
}
}
-
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("Type",
+ "types", "stoptypes-1.txt",
+ "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cz/TestCzechStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cz/TestCzechStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cz/TestCzechStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cz/TestCzechStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,23 +20,31 @@ package org.apache.lucene.analysis.cz;
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.Tokenizer;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Czech stem filter factory is working.
*/
-public class TestCzechStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestCzechStemFilterFactory extends BaseTokenStreamFactoryTestCase {
/**
* Ensure the filter actually stems text.
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("angliÄtÃ");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- CzechStemFilterFactory factory = new CzechStemFilterFactory();
- TokenStream stream = factory.create(tokenizer);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("CzechStem").create(stream);
assertTokenStreamContents(stream, new String[] { "anglick" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("CzechStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanLightStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanLightStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanLightStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.de;
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 German light stem factory is working.
*/
-public class TestGermanLightStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestGermanLightStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("häuser");
- GermanLightStemFilterFactory factory = new GermanLightStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GermanLightStem").create(stream);
assertTokenStreamContents(stream, new String[] { "haus" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GermanLightStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanMinimalStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanMinimalStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanMinimalStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanMinimalStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.de;
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 German minimal stem factory is working.
*/
-public class TestGermanMinimalStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestGermanMinimalStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("bilder");
- GermanMinimalStemFilterFactory factory = new GermanMinimalStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GermanMinimalStem").create(stream);
assertTokenStreamContents(stream, new String[] { "bild" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GermanMinimalStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanNormalizationFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanNormalizationFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanNormalizationFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanNormalizationFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.de;
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 German normalization factory is working.
*/
-public class TestGermanNormalizationFilterFactory extends BaseTokenStreamTestCase {
+public class TestGermanNormalizationFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("weiÃbier");
- GermanNormalizationFilterFactory factory = new GermanNormalizationFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GermanNormalization").create(stream);
assertTokenStreamContents(stream, new String[] { "weissbier" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GermanNormalization", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,23 +20,31 @@ package org.apache.lucene.analysis.de;
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.Tokenizer;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the German stem filter factory is working.
*/
-public class TestGermanStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestGermanStemFilterFactory extends BaseTokenStreamFactoryTestCase {
/**
* Ensure the filter actually stems text.
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("Tischen");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- GermanStemFilterFactory factory = new GermanStemFilterFactory();
- TokenStream stream = factory.create(tokenizer);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GermanStem").create(stream);
assertTokenStreamContents(stream, new String[] { "tisch" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GermanStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekLowerCaseFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekLowerCaseFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekLowerCaseFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekLowerCaseFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -19,29 +19,32 @@ package org.apache.lucene.analysis.el;
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.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 Greek lowercase filter factory is working.
*/
-public class TestGreekLowerCaseFilterFactory extends BaseTokenStreamTestCase {
+public class TestGreekLowerCaseFilterFactory extends BaseTokenStreamFactoryTestCase {
/**
* Ensure the filter actually lowercases (and a bit more) greek text.
*/
public void testNormalization() throws Exception {
Reader reader = new StringReader("ÎάÏÎ¿Ï ÎÎΪÎΣ");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- GreekLowerCaseFilterFactory factory = new GreekLowerCaseFilterFactory();
- factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
- Map<String, String> args = Collections.emptyMap();
- factory.init(args);
- TokenStream stream = factory.create(tokenizer);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GreekLowerCase").create(stream);
assertTokenStreamContents(stream, new String[] { "μαιοÏ", "μαιοÏ" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GreekLowerCase", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,22 +20,29 @@ package org.apache.lucene.analysis.el;
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.Tokenizer;
-import org.apache.lucene.analysis.el.GreekLowerCaseFilter;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Greek stem filter factory is working.
*/
-public class TestGreekStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestGreekStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("άνθÏÏÏοÏ");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- TokenStream normalized = new GreekLowerCaseFilter(TEST_VERSION_CURRENT, tokenizer);
- GreekStemFilterFactory factory = new GreekStemFilterFactory();
- TokenStream stream = factory.create(normalized);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("GreekLowerCase").create(stream);
+ stream = tokenFilterFactory("GreekStem").create(stream);
assertTokenStreamContents(stream, new String[] { "ανθÏÏÏ" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("GreekStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishMinimalStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishMinimalStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishMinimalStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishMinimalStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.en;
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 English minimal stem factory is working.
*/
-public class TestEnglishMinimalStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestEnglishMinimalStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("bricks");
- EnglishMinimalStemFilterFactory factory = new EnglishMinimalStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("EnglishMinimalStem").create(stream);
assertTokenStreamContents(stream, new String[] { "brick" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("EnglishMinimalStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestKStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestKStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestKStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestKStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.en;
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 kstem filter factory is working.
*/
-public class TestKStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestKStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("bricks");
- KStemFilterFactory factory = new KStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("KStem").create(stream);
assertTokenStreamContents(stream, new String[] { "brick" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("KStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestPorterStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestPorterStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestPorterStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestPorterStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,23 +20,31 @@ package org.apache.lucene.analysis.en;
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.Tokenizer;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Porter stem filter factory is working.
*/
-public class TestPorterStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestPorterStemFilterFactory extends BaseTokenStreamFactoryTestCase {
/**
* Ensure the filter actually stems text.
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("dogs");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- PorterStemFilterFactory factory = new PorterStemFilterFactory();
- TokenStream stream = factory.create(tokenizer);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("PorterStem").create(stream);
assertTokenStreamContents(stream, new String[] { "dog" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("PorterStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishLightStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishLightStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishLightStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.es;
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 Spanish Light stem factory is working.
*/
-public class TestSpanishLightStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestSpanishLightStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("sociedades");
- SpanishLightStemFilterFactory factory = new SpanishLightStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("SpanishLightStem").create(stream);
assertTokenStreamContents(stream, new String[] { "sociedad" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("SpanishLightStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianNormalizationFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianNormalizationFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianNormalizationFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianNormalizationFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,23 +20,31 @@ package org.apache.lucene.analysis.fa;
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.Tokenizer;
+import org.apache.lucene.analysis.util.BaseTokenStreamFactoryTestCase;
/**
* Simple tests to ensure the Persian normalization factory is working.
*/
-public class TestPersianNormalizationFilterFactory extends BaseTokenStreamTestCase {
+public class TestPersianNormalizationFilterFactory extends BaseTokenStreamFactoryTestCase {
/**
* Ensure the filter actually normalizes persian text.
*/
public void testNormalization() throws Exception {
Reader reader = new StringReader("ÙاÛ");
- Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- PersianNormalizationFilterFactory factory = new PersianNormalizationFilterFactory();
- TokenStream stream = factory.create(tokenizer);
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("PersianNormalization").create(stream);
assertTokenStreamContents(stream, new String[] { "ÙاÙ" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("PersianNormalization", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishLightStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishLightStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishLightStemFilterFactory.java Sat Apr 6 11:08:17 2013
@@ -20,18 +20,28 @@ package org.apache.lucene.analysis.fi;
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 Finnish light stem factory is working.
*/
-public class TestFinnishLightStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestFinnishLightStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("aseistettujen");
- FinnishLightStemFilterFactory factory = new FinnishLightStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("FinnishLightStem").create(stream);
assertTokenStreamContents(stream, new String[] { "aseistet" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("FinnishLightStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchLightStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchLightStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchLightStemFilterFactory.java Sat Apr 6 11:08:17 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 light stem factory is working.
*/
-public class TestFrenchLightStemFilterFactory extends BaseTokenStreamTestCase {
+public class TestFrenchLightStemFilterFactory extends BaseTokenStreamFactoryTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("administrativement");
- FrenchLightStemFilterFactory factory = new FrenchLightStemFilterFactory();
- TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
+ TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
+ stream = tokenFilterFactory("FrenchLightStem").create(stream);
assertTokenStreamContents(stream, new String[] { "administratif" });
}
+
+ /** Test that bogus arguments result in exception */
+ public void testBogusArguments() throws Exception {
+ try {
+ tokenFilterFactory("FrenchLightStem", "bogusArg", "bogusValue");
+ fail();
+ } catch (IllegalArgumentException expected) {
+ assertTrue(expected.getMessage().contains("Unknown parameters"));
+ }
+ }
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishLowerCaseFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiFilters.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianLightStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianStemFilterFactory.java Sat Apr 6 11:08:17 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/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java?rev=1465224&r1=1465223&r2=1465224&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilterFactory.java Sat Apr 6 11:08:17 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"));
+ }
}
}