Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-3456: use MockTokenizer in analysis tests 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1175650 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2011-09-26 03:24:02 +00:00
parent 67fe9a6b81
commit e927a69698
54 changed files with 185 additions and 176 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
solr/core/src/test/org/apache/solr/analysis/CommonGramsFilterFactoryTest.java
View File

@ -17,9 +17,9 @@ package org.apache.solr.analysis;
* limitations under the License.
*/
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.common.ResourceLoader;
import org.apache.solr.core.SolrResourceLoader;
@ -77,7 +77,7 @@ public class CommonGramsFilterFactoryTest extends BaseTokenTestCase {
Set<?> words = factory.getCommonWords();
assertTrue("words is null and it shouldn't be", words != null);
assertTrue(words.contains("the"));
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("testing the factory"));
Tokenizer tokenizer = new MockTokenizer(new StringReader("testing the factory"), MockTokenizer.WHITESPACE, false);
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream,
new String[] { "testing", "testing_the", "the", "the_factory", "factory" });

4
solr/core/src/test/org/apache/solr/analysis/CommonGramsQueryFilterFactoryTest.java
View File

@ -16,9 +16,9 @@
*/
package org.apache.solr.analysis;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.common.ResourceLoader;
import org.apache.solr.core.SolrResourceLoader;
@ -76,7 +76,7 @@ public class CommonGramsQueryFilterFactoryTest extends BaseTokenTestCase {
Set<?> words = factory.getCommonWords();
assertTrue("words is null and it shouldn't be", words != null);
assertTrue(words.contains("the"));
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("testing the factory"));
Tokenizer tokenizer = new MockTokenizer(new StringReader("testing the factory"), MockTokenizer.WHITESPACE, false);
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream,
new String[] { "testing_the", "the_factory" });

9
solr/core/src/test/org/apache/solr/analysis/DoubleMetaphoneFilterFactoryTest.java
View File

@ -20,8 +20,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.phonetic.DoubleMetaphoneFilter;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
@ -30,7 +30,7 @@ public class DoubleMetaphoneFilterFactoryTest extends BaseTokenTestCase {
public void testDefaults() throws Exception {
DoubleMetaphoneFilterFactory factory = new DoubleMetaphoneFilterFactory();
factory.init(new HashMap<String, String>());
TokenStream inputStream = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("international"));
TokenStream inputStream = new MockTokenizer(new StringReader("international"), MockTokenizer.WHITESPACE, false);
TokenStream filteredStream = factory.create(inputStream);
assertEquals(DoubleMetaphoneFilter.class, filteredStream.getClass());
@ -44,7 +44,7 @@ public class DoubleMetaphoneFilterFactoryTest extends BaseTokenTestCase {
parameters.put("maxCodeLength", "8");
factory.init(parameters);
TokenStream inputStream = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("international"));
TokenStream inputStream = new MockTokenizer(new StringReader("international"), MockTokenizer.WHITESPACE, false);
TokenStream filteredStream = factory.create(inputStream);
assertEquals(DoubleMetaphoneFilter.class, filteredStream.getClass());
@ -57,12 +57,13 @@ public class DoubleMetaphoneFilterFactoryTest extends BaseTokenTestCase {
public void testReset() throws Exception {
DoubleMetaphoneFilterFactory factory = new DoubleMetaphoneFilterFactory();
factory.init(new HashMap<String, String>());
TokenStream inputStream = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("international"));
TokenStream inputStream = new MockTokenizer(new StringReader("international"), MockTokenizer.WHITESPACE, false);
TokenStream filteredStream = factory.create(inputStream);
CharTermAttribute termAtt = filteredStream.addAttribute(CharTermAttribute.class);
assertEquals(DoubleMetaphoneFilter.class, filteredStream.getClass());
filteredStream.reset();
assertTrue(filteredStream.incrementToken());
assertEquals(13, termAtt.length());
assertEquals("international", termAtt.toString());

6
solr/core/src/test/org/apache/solr/analysis/LengthFilterTest.java
View File

@ -21,8 +21,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
public class LengthFilterTest extends BaseTokenTestCase {
@ -34,7 +34,7 @@ public class LengthFilterTest extends BaseTokenTestCase {
// default: args.put("enablePositionIncrements", "false");
factory.init(args);
String test = "foo foobar super-duper-trooper";
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(test)));
TokenStream stream = factory.create(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "foobar" }, new int[] { 1 });
factory = new LengthFilterFactory();
@ -43,7 +43,7 @@ public class LengthFilterTest extends BaseTokenTestCase {
args.put(LengthFilterFactory.MAX_KEY, String.valueOf(10));
args.put("enablePositionIncrements", "true");
factory.init(args);
stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(test)));
stream = factory.create(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "foobar" }, new int[] { 2 });
}
}

8
solr/core/src/test/org/apache/solr/analysis/SnowballPorterFilterFactoryTest.java
View File

@ -16,9 +16,9 @@ package org.apache.solr.analysis;
* limitations under the License.
*/
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.common.ResourceLoader;
import org.apache.solr.common.util.StrUtils;
import org.apache.solr.core.SolrResourceLoader;
@ -52,8 +52,8 @@ public class SnowballPorterFilterFactoryTest extends BaseTokenTestCase {
factory.init(args);
factory.inform(new LinesMockSolrResourceLoader(new ArrayList<String>()));
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION,
new StringReader(StrUtils.join(Arrays.asList(test), ' ')));
Tokenizer tokenizer = new MockTokenizer(
new StringReader(StrUtils.join(Arrays.asList(test), ' ')), MockTokenizer.WHITESPACE, false);
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, gold);
}
@ -90,7 +90,7 @@ public class SnowballPorterFilterFactoryTest extends BaseTokenTestCase {
factory.init(args);
factory.inform(loader);
Reader reader = new StringReader("ridding of some stemming");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "ridding", "of", "some", "stem" });
}

4
solr/core/src/test/org/apache/solr/analysis/TestBrazilianStemFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Brazilian stem filter factory is working.
@ -33,7 +33,7 @@ public class TestBrazilianStemFilterFactory extends BaseTokenTestCase {
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("Brasília");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
BrazilianStemFilterFactory factory = new BrazilianStemFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "brasil" });

4
solr/core/src/test/org/apache/solr/analysis/TestBulgarianStemFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Bulgarian stem filter factory is working.
@ -33,7 +33,7 @@ public class TestBulgarianStemFilterFactory extends BaseTokenTestCase {
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("компютри");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
BulgarianStemFilterFactory factory = new BulgarianStemFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "компютр" });

53
solr/core/src/test/org/apache/solr/analysis/TestCapitalizationFilterFactory.java
View File

@ -21,10 +21,9 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
@ -41,56 +40,56 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
factory.init( args );
assertTokenStreamContents(factory.create(
new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("kiTTEN"))),
new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.WHITESPACE, false)),
new String[] { "Kitten" });
factory.forceFirstLetter = true;
assertTokenStreamContents(factory.create(
new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("and"))),
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 WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("AnD"))),
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 WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("AnD"))),
new MockTokenizer(new StringReader("AnD"), MockTokenizer.WHITESPACE, false)),
new String[] { "And" });
factory.forceFirstLetter = true;
assertTokenStreamContents(factory.create(
new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("big"))),
new MockTokenizer(new StringReader("big"), MockTokenizer.WHITESPACE, false)),
new String[] { "Big" });
assertTokenStreamContents(factory.create(
new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("BIG"))),
new MockTokenizer(new StringReader("BIG"), MockTokenizer.WHITESPACE, false)),
new String[] { "BIG" });
assertTokenStreamContents(factory.create(
new KeywordTokenizer(new StringReader("Hello thEre my Name is Ryan"))),
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 WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("Hello thEre my Name is Ryan"))),
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 WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("Hello thEre my Name is Ryan"))),
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 WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("McKinley"))),
new MockTokenizer(new StringReader("McKinley"), MockTokenizer.WHITESPACE, false)),
new String[] { "Mckinley" });
// Now try some prefixes
@ -98,19 +97,19 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
args.put( "okPrefix", "McK" ); // all words
factory.init( args );
assertTokenStreamContents(factory.create(
new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("McKinley"))),
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 WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("1st 2nd third"))),
new MockTokenizer(new StringReader("1st 2nd third"), MockTokenizer.WHITESPACE, false)),
new String[] { "1st", "2nd", "Third" });
factory.forceFirstLetter = true;
assertTokenStreamContents(factory.create(
new KeywordTokenizer(new StringReader("the The the"))),
new MockTokenizer(new StringReader("the The the"), MockTokenizer.KEYWORD, false)),
new String[] { "The The the" });
}
@ -124,17 +123,17 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
factory.init( args );
factory.forceFirstLetter = true;
assertTokenStreamContents(factory.create(
new KeywordTokenizer(new StringReader("kiTTEN"))),
new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.KEYWORD, false)),
new String[] { "KiTTEN" });
factory.forceFirstLetter = false;
assertTokenStreamContents(factory.create(
new KeywordTokenizer(new StringReader("kiTTEN"))),
new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.KEYWORD, false)),
new String[] { "kiTTEN" });
factory.keep = null;
assertTokenStreamContents(factory.create(
new KeywordTokenizer(new StringReader("kiTTEN"))),
new MockTokenizer(new StringReader("kiTTEN"), MockTokenizer.KEYWORD, false)),
new String[] { "Kitten" });
}
@ -149,8 +148,8 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
args.put(CapitalizationFilterFactory.MIN_WORD_LENGTH, "5");
CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
factory.init(args);
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(
"helo testing"));
Tokenizer tokenizer = new MockTokenizer(new StringReader(
"helo testing"), MockTokenizer.WHITESPACE, false);
TokenStream ts = factory.create(tokenizer);
assertTokenStreamContents(ts, new String[] {"helo", "Testing"});
}
@ -164,8 +163,8 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
args.put(CapitalizationFilterFactory.MAX_WORD_COUNT, "2");
CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
factory.init(args);
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(
"one two three four"));
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"});
}
@ -178,8 +177,8 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
args.put(CapitalizationFilterFactory.MAX_WORD_COUNT, "2");
CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
factory.init(args);
Tokenizer tokenizer = new KeywordTokenizer(new StringReader(
"one two three four"));
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"});
}
@ -194,8 +193,8 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
args.put(CapitalizationFilterFactory.MAX_TOKEN_LENGTH, "2");
CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
factory.init(args);
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(
"this is a test"));
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"});
}
@ -209,7 +208,7 @@ public class TestCapitalizationFilterFactory extends BaseTokenTestCase {
args.put(CapitalizationFilterFactory.FORCE_FIRST_LETTER, "true");
CapitalizationFilterFactory factory = new CapitalizationFilterFactory();
factory.init(args);
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("kitten"));
Tokenizer tokenizer = new MockTokenizer(new StringReader("kitten"), MockTokenizer.WHITESPACE, false);
TokenStream ts = factory.create(tokenizer);
assertTokenStreamContents(ts, new String[] {"Kitten"});
}

4
solr/core/src/test/org/apache/solr/analysis/TestChineseFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Chinese filter factory is working.
@ -33,7 +33,7 @@ public class TestChineseFilterFactory extends BaseTokenTestCase {
*/
public void testFiltering() throws Exception {
Reader reader = new StringReader("this 1234 Is such a silly filter");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
ChineseFilterFactory factory = new ChineseFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "Is", "silly", "filter" });

28
solr/core/src/test/org/apache/solr/analysis/TestCollationKeyFilterFactory.java
View File

@ -28,8 +28,8 @@ import java.util.List;
import java.util.Locale;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.solr.common.ResourceLoader;
@ -51,9 +51,9 @@ public class TestCollationKeyFilterFactory extends BaseTokenTestCase {
factory.init(args);
factory.inform(new StringMockSolrResourceLoader(""));
TokenStream tsUpper = factory.create(
new KeywordTokenizer(new StringReader(turkishUpperCase)));
new MockTokenizer(new StringReader(turkishUpperCase), MockTokenizer.KEYWORD, false));
TokenStream tsLower = factory.create(
new KeywordTokenizer(new StringReader(turkishLowerCase)));
new MockTokenizer(new StringReader(turkishLowerCase), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsUpper, tsLower);
}
@ -71,9 +71,9 @@ public class TestCollationKeyFilterFactory extends BaseTokenTestCase {
factory.init(args);
factory.inform(new StringMockSolrResourceLoader(""));
TokenStream tsUpper = factory.create(
new KeywordTokenizer(new StringReader(turkishUpperCase)));
new MockTokenizer(new StringReader(turkishUpperCase), MockTokenizer.KEYWORD, false));
TokenStream tsLower = factory.create(
new KeywordTokenizer(new StringReader(turkishLowerCase)));
new MockTokenizer(new StringReader(turkishLowerCase), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsUpper, tsLower);
}
@ -92,9 +92,9 @@ public class TestCollationKeyFilterFactory extends BaseTokenTestCase {
factory.init(args);
factory.inform(new StringMockSolrResourceLoader(""));
TokenStream tsFull = factory.create(
new KeywordTokenizer(new StringReader(fullWidth)));
new MockTokenizer(new StringReader(fullWidth), MockTokenizer.KEYWORD, false));
TokenStream tsHalf = factory.create(
new KeywordTokenizer(new StringReader(halfWidth)));
new MockTokenizer(new StringReader(halfWidth), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsFull, tsHalf);
}
@ -112,9 +112,9 @@ public class TestCollationKeyFilterFactory extends BaseTokenTestCase {
factory.init(args);
factory.inform(new StringMockSolrResourceLoader(""));
TokenStream tsUpper = factory.create(
new KeywordTokenizer(new StringReader(upperCase)));
new MockTokenizer(new StringReader(upperCase), MockTokenizer.KEYWORD, false));
TokenStream tsLower = factory.create(
new KeywordTokenizer(new StringReader(lowerCase)));
new MockTokenizer(new StringReader(lowerCase), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsUpper, tsLower);
}
@ -148,9 +148,9 @@ public class TestCollationKeyFilterFactory extends BaseTokenTestCase {
factory.init(args);
factory.inform(new StringMockSolrResourceLoader(tailoredRules));
TokenStream tsUmlaut = factory.create(
new KeywordTokenizer(new StringReader(germanUmlaut)));
new MockTokenizer(new StringReader(germanUmlaut), MockTokenizer.KEYWORD, false));
TokenStream tsOE = factory.create(
new KeywordTokenizer(new StringReader(germanOE)));
new MockTokenizer(new StringReader(germanOE), MockTokenizer.KEYWORD, false));
assertCollatesToSame(tsUmlaut, tsOE);
}
@ -177,6 +177,8 @@ public class TestCollationKeyFilterFactory extends BaseTokenTestCase {
private void assertCollatesToSame(TokenStream stream1, TokenStream stream2)
throws IOException {
stream1.reset();
stream2.reset();
CharTermAttribute term1 = stream1
.addAttribute(CharTermAttribute.class);
CharTermAttribute term2 = stream2
@ -186,5 +188,9 @@ public class TestCollationKeyFilterFactory extends BaseTokenTestCase {
assertEquals(term1.toString(), term2.toString());
assertFalse(stream1.incrementToken());
assertFalse(stream2.incrementToken());
stream1.end();
stream2.end();
stream1.close();
stream2.close();
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestCzechStemFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Czech stem filter factory is working.
@ -33,7 +33,7 @@ public class TestCzechStemFilterFactory extends BaseTokenTestCase {
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("angličtí");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
CzechStemFilterFactory factory = new CzechStemFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "anglick" });

8
solr/core/src/test/org/apache/solr/analysis/TestDelimitedPayloadTokenFilterFactory.java
View File

@ -21,8 +21,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.payloads.DelimitedPayloadTokenFilter;
import org.apache.lucene.analysis.payloads.FloatEncoder;
import org.apache.lucene.analysis.payloads.PayloadHelper;
@ -40,8 +40,9 @@ public class TestDelimitedPayloadTokenFilterFactory extends BaseTokenTestCase {
ResourceLoader loader = new SolrResourceLoader(null, null);
factory.inform(loader);
TokenStream input = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("the|0.1 quick|0.1 red|0.1"));
TokenStream input = new MockTokenizer(new StringReader("the|0.1 quick|0.1 red|0.1"), MockTokenizer.WHITESPACE, false);
DelimitedPayloadTokenFilter tf = factory.create(input);
tf.reset();
while (tf.incrementToken()){
PayloadAttribute payAttr = tf.getAttribute(PayloadAttribute.class);
assertTrue("payAttr is null and it shouldn't be", payAttr != null);
@ -62,8 +63,9 @@ public class TestDelimitedPayloadTokenFilterFactory extends BaseTokenTestCase {
ResourceLoader loader = new SolrResourceLoader(null, null);
factory.inform(loader);
TokenStream input = new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("the*0.1 quick*0.1 red*0.1"));
TokenStream input = new MockTokenizer(new StringReader("the*0.1 quick*0.1 red*0.1"), MockTokenizer.WHITESPACE, false);
DelimitedPayloadTokenFilter tf = factory.create(input);
tf.reset();
while (tf.incrementToken()){
PayloadAttribute payAttr = tf.getAttribute(PayloadAttribute.class);
assertTrue("payAttr is null and it shouldn't be", payAttr != null);

4
solr/core/src/test/org/apache/solr/analysis/TestDictionaryCompoundWordTokenFilterFactory.java
View File

@ -22,9 +22,9 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.common.ResourceLoader;
import org.apache.solr.core.SolrResourceLoader;
@ -37,7 +37,7 @@ public class TestDictionaryCompoundWordTokenFilterFactory extends BaseTokenTestC
*/
public void testDecompounding() throws Exception {
Reader reader = new StringReader("I like to play softball");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
DictionaryCompoundWordTokenFilterFactory factory = new DictionaryCompoundWordTokenFilterFactory();
ResourceLoader loader = new SolrResourceLoader(null, null);
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);

6
solr/core/src/test/org/apache/solr/analysis/TestElisionFilterFactory.java
View File

@ -22,9 +22,9 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.common.ResourceLoader;
import org.apache.solr.core.SolrResourceLoader;
@ -37,7 +37,7 @@ public class TestElisionFilterFactory extends BaseTokenTestCase {
*/
public void testElision() throws Exception {
Reader reader = new StringReader("l'avion");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
ElisionFilterFactory factory = new ElisionFilterFactory();
factory.init(DEFAULT_VERSION_PARAM);
ResourceLoader loader = new SolrResourceLoader(null, null);
@ -54,7 +54,7 @@ public class TestElisionFilterFactory extends BaseTokenTestCase {
*/
public void testDefaultArticles() throws Exception {
Reader reader = new StringReader("l'avion");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
ElisionFilterFactory factory = new ElisionFilterFactory();
factory.init(DEFAULT_VERSION_PARAM);
ResourceLoader loader = new SolrResourceLoader(null, null);

4
solr/core/src/test/org/apache/solr/analysis/TestEnglishMinimalStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the English minimal stem factory is working.
@ -30,7 +30,7 @@ public class TestEnglishMinimalStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("bricks");
EnglishMinimalStemFilterFactory factory = new EnglishMinimalStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "brick" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestFinnishLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Finnish light stem factory is working.
@ -30,7 +30,7 @@ public class TestFinnishLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("aseistettujen");
FinnishLightStemFilterFactory factory = new FinnishLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "aseistet" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestFrenchLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the French light stem factory is working.
@ -30,7 +30,7 @@ public class TestFrenchLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("administrativement");
FrenchLightStemFilterFactory factory = new FrenchLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "administratif" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestFrenchMinimalStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the French minimal stem factory is working.
@ -30,7 +30,7 @@ public class TestFrenchMinimalStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("chevaux");
FrenchMinimalStemFilterFactory factory = new FrenchMinimalStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "cheval" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestGalicianStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Galician stem factory is working.
@ -30,7 +30,7 @@ public class TestGalicianStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("cariñosa");
GalicianStemFilterFactory factory = new GalicianStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "cariñ" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestGermanLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the German light stem factory is working.
@ -30,7 +30,7 @@ public class TestGermanLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("häuser");
GermanLightStemFilterFactory factory = new GermanLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "haus" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestGermanMinimalStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the German minimal stem factory is working.
@ -30,7 +30,7 @@ public class TestGermanMinimalStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("bilder");
GermanMinimalStemFilterFactory factory = new GermanMinimalStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "bild" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestGermanStemFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the German stem filter factory is working.
@ -33,7 +33,7 @@ public class TestGermanStemFilterFactory extends BaseTokenTestCase {
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("Tischen");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
GermanStemFilterFactory factory = new GermanStemFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "tisch" });

4
solr/core/src/test/org/apache/solr/analysis/TestGreekLowerCaseFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Greek lowercase filter factory is working.
@ -33,7 +33,7 @@ public class TestGreekLowerCaseFilterFactory extends BaseTokenTestCase {
*/
public void testNormalization() throws Exception {
Reader reader = new StringReader("Μάϊος ΜΆΪΟΣ");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
GreekLowerCaseFilterFactory factory = new GreekLowerCaseFilterFactory();
factory.init(DEFAULT_VERSION_PARAM);
TokenStream stream = factory.create(tokenizer);

4
solr/core/src/test/org/apache/solr/analysis/TestGreekStemFilterFactory.java
View File

@ -3,9 +3,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.el.GreekLowerCaseFilter;
/**
@ -31,7 +31,7 @@ import org.apache.lucene.analysis.el.GreekLowerCaseFilter;
public class TestGreekStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("άνθρωπος");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
TokenStream normalized = new GreekLowerCaseFilter(DEFAULT_VERSION, tokenizer);
GreekStemFilterFactory factory = new GreekStemFilterFactory();
TokenStream stream = factory.create(normalized);

4
solr/core/src/test/org/apache/solr/analysis/TestHungarianLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Hungarian light stem factory is working.
@ -30,7 +30,7 @@ public class TestHungarianLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("házakat");
HungarianLightStemFilterFactory factory = new HungarianLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "haz" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestHunspellStemFilterFactory.java
View File

@ -22,8 +22,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.core.SolrResourceLoader;
import org.apache.solr.schema.IndexSchema;
@ -41,7 +41,7 @@ public class TestHunspellStemFilterFactory extends BaseTokenTestCase {
factory.inform(new SolrResourceLoader("solr"));
Reader reader = new StringReader("abc");
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "ab" });
}
}

6
solr/core/src/test/org/apache/solr/analysis/TestHyphenationCompoundWordTokenFilterFactory.java
View File

@ -22,9 +22,9 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.common.ResourceLoader;
import org.apache.solr.core.SolrResourceLoader;
@ -37,7 +37,7 @@ public class TestHyphenationCompoundWordTokenFilterFactory extends BaseTokenTest
*/
public void testHyphenationWithDictionary() throws Exception {
Reader reader = new StringReader("min veninde som er lidt af en læsehest");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
HyphenationCompoundWordTokenFilterFactory factory = new HyphenationCompoundWordTokenFilterFactory();
ResourceLoader loader = new SolrResourceLoader(null, null);
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
@ -60,7 +60,7 @@ public class TestHyphenationCompoundWordTokenFilterFactory extends BaseTokenTest
*/
public void testHyphenationOnly() throws Exception {
Reader reader = new StringReader("basketballkurv");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
HyphenationCompoundWordTokenFilterFactory factory = new HyphenationCompoundWordTokenFilterFactory();
ResourceLoader loader = new SolrResourceLoader(null, null);
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);

6
solr/core/src/test/org/apache/solr/analysis/TestIndonesianStemFilterFactory.java
View File

@ -22,9 +22,9 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Indonesian stem filter factory is working.
@ -35,7 +35,7 @@ public class TestIndonesianStemFilterFactory extends BaseTokenTestCase {
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("dibukukannya");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
IndonesianStemFilterFactory factory = new IndonesianStemFilterFactory();
Map<String,String> args = new HashMap<String,String>();
factory.init(args);
@ -48,7 +48,7 @@ public class TestIndonesianStemFilterFactory extends BaseTokenTestCase {
*/
public void testStemmingInflectional() throws Exception {
Reader reader = new StringReader("dibukukannya");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
IndonesianStemFilterFactory factory = new IndonesianStemFilterFactory();
Map<String,String> args = new HashMap<String,String>();
args.put("stemDerivational", "false");

4
solr/core/src/test/org/apache/solr/analysis/TestItalianLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Italian light stem factory is working.
@ -30,7 +30,7 @@ public class TestItalianLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("ragazzo ragazzi");
ItalianLightStemFilterFactory factory = new ItalianLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "ragazz", "ragazz" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestKStemFilterFactory.java
View File

@ -3,8 +3,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
@ -30,7 +30,7 @@ public class TestKStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("bricks");
KStemFilterFactory factory = new KStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "brick" });
}
}

6
solr/core/src/test/org/apache/solr/analysis/TestKeywordMarkerFilterFactory.java
View File

@ -23,8 +23,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
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.solr.common.ResourceLoader;
@ -36,7 +36,7 @@ import org.apache.solr.core.SolrResourceLoader;
public class TestKeywordMarkerFilterFactory extends BaseTokenTestCase {
public void testKeywords() throws IOException {
Reader reader = new StringReader("dogs cats");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
KeywordMarkerFilterFactory factory = new KeywordMarkerFilterFactory();
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
ResourceLoader loader = new SolrResourceLoader(null, null);
@ -50,7 +50,7 @@ public class TestKeywordMarkerFilterFactory extends BaseTokenTestCase {
public void testKeywordsCaseInsensitive() throws IOException {
Reader reader = new StringReader("dogs cats Cats");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
KeywordMarkerFilterFactory factory = new KeywordMarkerFilterFactory();
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
ResourceLoader loader = new SolrResourceLoader(null, null);

4
solr/core/src/test/org/apache/solr/analysis/TestLatvianStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Latvian stem factory is working.
@ -30,7 +30,7 @@ public class TestLatvianStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("tirgiem tirgus");
LatvianStemFilterFactory factory = new LatvianStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "tirg", "tirg" });
}
}

3
solr/core/src/test/org/apache/solr/analysis/TestMultiWordSynonyms.java
View File

@ -19,7 +19,6 @@ package org.apache.solr.analysis;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.common.ResourceLoader;
import java.io.ByteArrayInputStream;
@ -46,7 +45,7 @@ public class TestMultiWordSynonyms extends BaseTokenTestCase {
SlowSynonymMap synMap = new SlowSynonymMap(true);
SlowSynonymFilterFactory.parseRules(rules, synMap, "=>", ",", true, null);
SlowSynonymFilter ts = new SlowSynonymFilter(new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader("a e")), synMap);
SlowSynonymFilter ts = new SlowSynonymFilter(new MockTokenizer(new StringReader("a e"), MockTokenizer.WHITESPACE, false), synMap);
// This fails because ["e","e"] is the value of the token stream
assertTokenStreamContents(ts, new String[] { "a", "e" });
}

12
solr/core/src/test/org/apache/solr/analysis/TestNGramFilters.java
View File

@ -22,9 +22,9 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the NGram filter factories are working.
@ -64,7 +64,7 @@ public class TestNGramFilters extends BaseTokenTestCase {
Map<String,String> args = new HashMap<String,String>();
NGramFilterFactory factory = new NGramFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "t", "e", "s", "t", "te", "es", "st" });
}
@ -78,7 +78,7 @@ public class TestNGramFilters extends BaseTokenTestCase {
args.put("maxGramSize", "3");
NGramFilterFactory factory = new NGramFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "te", "es", "st", "tes", "est" });
}
@ -129,7 +129,7 @@ public class TestNGramFilters extends BaseTokenTestCase {
Map<String,String> args = new HashMap<String,String>();
EdgeNGramFilterFactory factory = new EdgeNGramFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "t" });
}
@ -143,7 +143,7 @@ public class TestNGramFilters extends BaseTokenTestCase {
args.put("maxGramSize", "2");
EdgeNGramFilterFactory factory = new EdgeNGramFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "t", "te" });
}
@ -156,7 +156,7 @@ public class TestNGramFilters extends BaseTokenTestCase {
args.put("side", "back");
EdgeNGramFilterFactory factory = new EdgeNGramFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "y" });
}

11
solr/core/src/test/org/apache/solr/analysis/TestPatternReplaceCharFilterFactory.java
View File

@ -24,8 +24,8 @@ import java.util.Map;
import org.apache.lucene.analysis.CharReader;
import org.apache.lucene.analysis.CharStream;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure this factory is working
@ -44,7 +44,7 @@ public class TestPatternReplaceCharFilterFactory extends BaseTokenTestCase {
factory.init(args);
CharStream cs = factory.create(
CharReader.get( new StringReader( BLOCK ) ) );
TokenStream ts = new WhitespaceTokenizer(DEFAULT_VERSION, cs );
TokenStream ts = new MockTokenizer(cs, MockTokenizer.WHITESPACE, false);
assertTokenStreamContents(ts,
new String[] { "this", "is", "test." },
new int[] { 0, 5, 8 },
@ -61,8 +61,11 @@ public class TestPatternReplaceCharFilterFactory extends BaseTokenTestCase {
factory.init(args);
CharStream cs = factory.create(
CharReader.get( new StringReader( BLOCK ) ) );
TokenStream ts = new WhitespaceTokenizer(DEFAULT_VERSION, cs );
TokenStream ts = new MockTokenizer(cs, MockTokenizer.WHITESPACE, false);
ts.reset();
assertFalse(ts.incrementToken());
ts.end();
ts.close();
}
// 012345678
@ -77,7 +80,7 @@ public class TestPatternReplaceCharFilterFactory extends BaseTokenTestCase {
factory.init(args);
CharStream cs = factory.create(
CharReader.get( new StringReader( BLOCK ) ) );
TokenStream ts = new WhitespaceTokenizer(DEFAULT_VERSION, cs );
TokenStream ts = new MockTokenizer(cs, MockTokenizer.WHITESPACE, false);
assertTokenStreamContents(ts,
new String[] { "aa#bb#cc" },
new int[] { 0 },

4
solr/core/src/test/org/apache/solr/analysis/TestPatternReplaceFilterFactory.java
View File

@ -17,8 +17,8 @@
package org.apache.solr.analysis;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import java.io.StringReader;
import java.util.HashMap;
@ -37,7 +37,7 @@ public class TestPatternReplaceFilterFactory extends BaseTokenTestCase {
args.put("replacement", "-");
factory.init(args);
TokenStream ts = factory.create
(new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(input)));
(new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(ts,
new String[] { "-foo-foo-foo-", "-", "c-" });

4
solr/core/src/test/org/apache/solr/analysis/TestPersianNormalizationFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Persian normalization factory is working.
@ -33,7 +33,7 @@ public class TestPersianNormalizationFilterFactory extends BaseTokenTestCase {
*/
public void testNormalization() throws Exception {
Reader reader = new StringReader("های");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
PersianNormalizationFilterFactory factory = new PersianNormalizationFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "هاي" });

5
solr/core/src/test/org/apache/solr/analysis/TestPhoneticFilterFactory.java
View File

@ -22,9 +22,9 @@ import java.util.HashMap;
import java.util.Map;
import org.apache.commons.codec.language.Metaphone;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
@ -89,8 +89,7 @@ public class TestPhoneticFilterFactory extends BaseTokenTestCase {
static void assertAlgorithm(String algName, String inject, String input,
String[] expected) throws Exception {
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION,
new StringReader(input));
Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
Map<String,String> args = new HashMap<String,String>();
args.put("encoder", algName);
args.put("inject", inject);

4
solr/core/src/test/org/apache/solr/analysis/TestPorterStemFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Porter stem filter factory is working.
@ -33,7 +33,7 @@ public class TestPorterStemFilterFactory extends BaseTokenTestCase {
*/
public void testStemming() throws Exception {
Reader reader = new StringReader("dogs");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
PorterStemFilterFactory factory = new PorterStemFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "dog" });

4
solr/core/src/test/org/apache/solr/analysis/TestPortugueseLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Portuguese Light stem factory is working.
@ -30,7 +30,7 @@ public class TestPortugueseLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("evidentemente");
PortugueseLightStemFilterFactory factory = new PortugueseLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "evident" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestPortugueseMinimalStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Portuguese Minimal stem factory is working.
@ -30,7 +30,7 @@ public class TestPortugueseMinimalStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("questões");
PortugueseMinimalStemFilterFactory factory = new PortugueseMinimalStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "questão" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestPortugueseStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Portuguese stem factory is working.
@ -30,7 +30,7 @@ public class TestPortugueseStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("maluquice");
PortugueseStemFilterFactory factory = new PortugueseStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "maluc" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestReverseStringFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Reverse string filter factory is working.
@ -33,7 +33,7 @@ public class TestReverseStringFilterFactory extends BaseTokenTestCase {
*/
public void testReversing() throws Exception {
Reader reader = new StringReader("simple test");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
ReverseStringFilterFactory factory = new ReverseStringFilterFactory();
factory.init(DEFAULT_VERSION_PARAM);
TokenStream stream = factory.create(tokenizer);

6
solr/core/src/test/org/apache/solr/analysis/TestReversedWildcardFilterFactory.java
View File

@ -25,8 +25,8 @@ import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.search.AutomatonQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.util.automaton.Automaton;
@ -66,7 +66,7 @@ public class TestReversedWildcardFilterFactory extends SolrTestCaseJ4 {
String text = "simple text";
args.put("withOriginal", "true");
factory.init(args);
TokenStream input = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(text)));
TokenStream input = factory.create(new MockTokenizer(new StringReader(text), MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(input,
new String[] { "\u0001elpmis", "simple", "\u0001txet", "text" },
new int[] { 1, 0, 1, 0 });
@ -74,7 +74,7 @@ public class TestReversedWildcardFilterFactory extends SolrTestCaseJ4 {
// now without original tokens
args.put("withOriginal", "false");
factory.init(args);
input = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, new StringReader(text)));
input = factory.create(new MockTokenizer(new StringReader(text), MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(input,
new String[] { "\u0001elpmis", "\u0001txet" },
new int[] { 1, 1 });

4
solr/core/src/test/org/apache/solr/analysis/TestRussianLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Russian light stem factory is working.
@ -30,7 +30,7 @@ public class TestRussianLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("журналы");
RussianLightStemFilterFactory factory = new RussianLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "журнал" });
}
}

28
solr/core/src/test/org/apache/solr/analysis/TestShingleFilterFactory.java
View File

@ -22,8 +22,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Shingle filter factory works.
@ -37,7 +37,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
Map<String,String> args = new HashMap<String,String>();
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] {"this", "this is", "is",
"is a", "a", "a test", "test"});
}
@ -51,7 +51,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("outputUnigrams", "false");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] {"this is", "is a", "a test"});
}
@ -65,7 +65,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("maxShingleSize", "3");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] {"this", "this is", "this is a", "is",
"is a", "is a test", "a", "a test", "test"});
@ -81,7 +81,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("maxShingleSize", "4");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this", "this is a", "this is a test",
"is", "is a test", "a", "test" });
@ -98,7 +98,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("outputUnigrams", "false");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this is a", "this is a test", "is a test" });
}
@ -113,7 +113,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("maxShingleSize", "3");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this", "this is a", "is", "is a test", "a", "test" });
}
@ -129,7 +129,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("outputUnigrams", "false");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this is a", "is a test" });
}
@ -143,7 +143,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("tokenSeparator", "=BLAH=");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this", "this=BLAH=is", "is", "is=BLAH=a",
"a", "a=BLAH=test", "test" });
@ -159,7 +159,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("outputUnigrams", "false");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this=BLAH=is", "is=BLAH=a", "a=BLAH=test" });
}
@ -173,7 +173,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("tokenSeparator", "");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this", "thisis", "is", "isa", "a", "atest", "test" });
}
@ -190,7 +190,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("tokenSeparator", "=BLAH=");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this", "this=BLAH=is=BLAH=a",
"this=BLAH=is=BLAH=a=BLAH=test", "is",
@ -211,7 +211,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("outputUnigrams", "false");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream,
new String[] { "this=BLAH=is=BLAH=a", "this=BLAH=is=BLAH=a=BLAH=test",
"is=BLAH=a=BLAH=test", });
@ -232,7 +232,7 @@ public class TestShingleFilterFactory extends BaseTokenTestCase {
args.put("outputUnigramsIfNoShingles", "true");
ShingleFilterFactory factory = new ShingleFilterFactory();
factory.init(args);
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "test" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestSpanishLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Spanish Light stem factory is working.
@ -30,7 +30,7 @@ public class TestSpanishLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("sociedades");
SpanishLightStemFilterFactory factory = new SpanishLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "sociedad" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestStandardFactories.java
View File

@ -22,9 +22,9 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the standard lucene factories are working.
@ -158,7 +158,7 @@ public class TestStandardFactories extends BaseTokenTestCase {
*/
public void testASCIIFolding() throws Exception {
Reader reader = new StringReader("Česká");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
ASCIIFoldingFilterFactory factory = new ASCIIFoldingFilterFactory();
factory.init(DEFAULT_VERSION_PARAM);
TokenStream stream = factory.create(tokenizer);

6
solr/core/src/test/org/apache/solr/analysis/TestStemmerOverrideFilterFactory.java
View File

@ -23,8 +23,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
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.solr.common.ResourceLoader;
@ -37,7 +37,7 @@ public class TestStemmerOverrideFilterFactory extends BaseTokenTestCase {
public void testKeywords() throws IOException {
// our stemdict stems dogs to 'cat'
Reader reader = new StringReader("testing dogs");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
StemmerOverrideFilterFactory factory = new StemmerOverrideFilterFactory();
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
ResourceLoader loader = new SolrResourceLoader(null, null);
@ -51,7 +51,7 @@ public class TestStemmerOverrideFilterFactory extends BaseTokenTestCase {
public void testKeywordsCaseInsensitive() throws IOException {
Reader reader = new StringReader("testing DoGs");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
StemmerOverrideFilterFactory factory = new StemmerOverrideFilterFactory();
Map<String,String> args = new HashMap<String,String>(DEFAULT_VERSION_PARAM);
ResourceLoader loader = new SolrResourceLoader(null, null);

4
solr/core/src/test/org/apache/solr/analysis/TestSwedishLightStemFilterFactory.java
View File

@ -20,8 +20,8 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Swedish Light stem factory is working.
@ -30,7 +30,7 @@ public class TestSwedishLightStemFilterFactory extends BaseTokenTestCase {
public void testStemming() throws Exception {
Reader reader = new StringReader("äpplen äpple");
SwedishLightStemFilterFactory factory = new SwedishLightStemFilterFactory();
TokenStream stream = factory.create(new WhitespaceTokenizer(DEFAULT_VERSION, reader));
TokenStream stream = factory.create(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false));
assertTokenStreamContents(stream, new String[] { "äppl", "äppl" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestThaiWordFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.th.ThaiWordFilter;
/**
@ -35,7 +35,7 @@ public class TestThaiWordFilterFactory extends BaseTokenTestCase {
public void testWordBreak() throws Exception {
assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
Reader reader = new StringReader("การที่ได้ต้องแสดงว่างานดี");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
ThaiWordFilterFactory factory = new ThaiWordFilterFactory();
factory.init(DEFAULT_VERSION_PARAM);
TokenStream stream = factory.create(tokenizer);

4
solr/core/src/test/org/apache/solr/analysis/TestTrimFilterFactory.java
View File

@ -21,8 +21,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordTokenizer;
/**
* Simple tests to ensure this factory is working
@ -33,7 +33,7 @@ public class TestTrimFilterFactory extends BaseTokenTestCase {
Map<String,String> args = new HashMap<String,String>();
args.put("updateOffsets", "false");
factory.init(args);
TokenStream ts = factory.create(new KeywordTokenizer(new StringReader("trim me ")));
TokenStream ts = factory.create(new MockTokenizer(new StringReader("trim me "), MockTokenizer.KEYWORD, false));
assertTokenStreamContents(ts, new String[] { "trim me" });
}
}

4
solr/core/src/test/org/apache/solr/analysis/TestTurkishLowerCaseFilterFactory.java
View File

@ -20,9 +20,9 @@ package org.apache.solr.analysis;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
/**
* Simple tests to ensure the Turkish lowercase filter factory is working.
@ -33,7 +33,7 @@ public class TestTurkishLowerCaseFilterFactory extends BaseTokenTestCase {
*/
public void testCasing() throws Exception {
Reader reader = new StringReader("AĞACI");
Tokenizer tokenizer = new WhitespaceTokenizer(DEFAULT_VERSION, reader);
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
TurkishLowerCaseFilterFactory factory = new TurkishLowerCaseFilterFactory();
TokenStream stream = factory.create(tokenizer);
assertTokenStreamContents(stream, new String[] { "ağacı" });

10
solr/core/src/test/org/apache/solr/analysis/TestWordDelimiterFilterFactory.java
View File

@ -21,8 +21,8 @@ import java.io.StringReader;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.solr.SolrTestCaseJ4;
import org.apache.solr.common.ResourceLoader;
import org.apache.solr.core.SolrResourceLoader;
@ -210,12 +210,12 @@ public class TestWordDelimiterFilterFactory extends SolrTestCaseJ4 {
factoryDefault.inform(loader);
TokenStream ts = factoryDefault.create(
new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader(testText)));
new MockTokenizer(new StringReader(testText), MockTokenizer.WHITESPACE, false));
BaseTokenTestCase.assertTokenStreamContents(ts,
new String[] { "I", "borrowed", "5", "400", "00", "540000", "at", "25", "interest", "rate", "interestrate" });
ts = factoryDefault.create(
new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader("foo\u200Dbar")));
new MockTokenizer(new StringReader("foo\u200Dbar"), MockTokenizer.WHITESPACE, false));
BaseTokenTestCase.assertTokenStreamContents(ts,
new String[] { "foo", "bar", "foobar" });
@ -228,13 +228,13 @@ public class TestWordDelimiterFilterFactory extends SolrTestCaseJ4 {
factoryCustom.inform(loader);
ts = factoryCustom.create(
new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader(testText)));
new MockTokenizer(new StringReader(testText), MockTokenizer.WHITESPACE, false));
BaseTokenTestCase.assertTokenStreamContents(ts,
new String[] { "I", "borrowed", "$5,400.00", "at", "25%", "interest", "rate", "interestrate" });
/* test custom behavior with a char > 0x7F, because we had to make a larger byte[] */
ts = factoryCustom.create(
new WhitespaceTokenizer(BaseTokenTestCase.DEFAULT_VERSION, new StringReader("foo\u200Dbar")));
new MockTokenizer(new StringReader("foo\u200Dbar"), MockTokenizer.WHITESPACE, false));
BaseTokenTestCase.assertTokenStreamContents(ts,
new String[] { "foo\u200Dbar" });
}