You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rj...@apache.org on 2014/08/21 05:12:58 UTC
svn commit: r1619283 [5/11] - 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/o...
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java Thu Aug 21 03:12:52 2014
@@ -36,7 +36,7 @@ import org.apache.lucene.util.Version;
public abstract class FilteringTokenFilter extends TokenFilter {
private static void checkPositionIncrement(Version version, boolean enablePositionIncrements) {
- if (!enablePositionIncrements && version.onOrAfter(Version.LUCENE_4_4)) {
+ if (!enablePositionIncrements && version.onOrAfter(Version.LUCENE_4_4_0)) {
throw new IllegalArgumentException("enablePositionIncrements=false is not supported anymore as of Lucene 4.4 as it can create broken token streams");
}
}
@@ -49,7 +49,7 @@ public abstract class FilteringTokenFilt
/**
* Create a new {@link FilteringTokenFilter}.
- * @param version the <a href="#lucene_match_version">Lucene match version</a>
+ *
* @param enablePositionIncrements whether to increment position increments when filtering out terms
* @param input the input to consume
* @deprecated enablePositionIncrements=false is not supported anymore as of Lucene 4.4
@@ -63,9 +63,17 @@ public abstract class FilteringTokenFilt
/**
* Create a new {@link FilteringTokenFilter}.
- * @param version the Lucene match version
+ *
* @param in the {@link TokenStream} to consume
*/
+ public FilteringTokenFilter(TokenStream in) {
+ this(Version.LATEST, in);
+ }
+
+ /**
+ * @deprecated Use {@link #FilteringTokenFilter(TokenStream)}
+ */
+ @Deprecated
public FilteringTokenFilter(Version version, TokenStream in) {
super(in);
this.version = version;
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java Thu Aug 21 03:12:52 2014
@@ -37,8 +37,6 @@ public abstract class StopwordAnalyzerBa
*/
protected final CharArraySet stopwords;
- protected final Version matchVersion;
-
/**
* Returns the analyzer's stopword set or an empty set if the analyzer has no
* stopwords
@@ -53,24 +51,37 @@ public abstract class StopwordAnalyzerBa
/**
* Creates a new instance initialized with the given stopword set
*
- * @param version
- * the Lucene version for cross version compatibility
* @param stopwords
* the analyzer's stopword set
*/
+ protected StopwordAnalyzerBase(final CharArraySet stopwords) {
+ // analyzers should use char array set for stopwords!
+ this.stopwords = stopwords == null ? CharArraySet.EMPTY_SET : CharArraySet
+ .unmodifiableSet(CharArraySet.copy(stopwords));
+ }
+
+ /**
+ * @deprecated Use {@link #StopwordAnalyzerBase(CharArraySet)}
+ */
+ @Deprecated
protected StopwordAnalyzerBase(final Version version, final CharArraySet stopwords) {
- matchVersion = version;
// analyzers should use char array set for stopwords!
this.stopwords = stopwords == null ? CharArraySet.EMPTY_SET : CharArraySet
.unmodifiableSet(CharArraySet.copy(version, stopwords));
+ setVersion(version);
}
/**
* Creates a new Analyzer with an empty stopword set
- *
- * @param version
- * the Lucene version for cross version compatibility
*/
+ protected StopwordAnalyzerBase() {
+ this((CharArraySet)null);
+ }
+
+ /**
+ * @deprecated Use {@link #StopwordAnalyzerBase()}
+ */
+ @Deprecated
protected StopwordAnalyzerBase(final Version version) {
this(version, null);
}
@@ -99,7 +110,7 @@ public abstract class StopwordAnalyzerBa
Reader reader = null;
try {
reader = IOUtils.getDecodingReader(aClass.getResourceAsStream(resource), StandardCharsets.UTF_8);
- return WordlistLoader.getWordSet(reader, comment, new CharArraySet(Version.LUCENE_CURRENT, 16, ignoreCase));
+ return WordlistLoader.getWordSet(reader, comment, new CharArraySet(16, ignoreCase));
} finally {
IOUtils.close(reader);
}
@@ -111,14 +122,19 @@ public abstract class StopwordAnalyzerBa
*
* @param stopwords
* the stopwords file to load
- *
- * @param matchVersion
- * the Lucene version for cross version compatibility
* @return a CharArraySet containing the distinct stopwords from the given
* file
* @throws IOException
* if loading the stopwords throws an {@link IOException}
*/
+ protected static CharArraySet loadStopwordSet(File stopwords) throws IOException {
+ return loadStopwordSet(stopwords, Version.LATEST);
+ }
+
+ /**
+ * @deprecated Use {@link #loadStopwordSet(File)}
+ */
+ @Deprecated
protected static CharArraySet loadStopwordSet(File stopwords,
Version matchVersion) throws IOException {
Reader reader = null;
@@ -136,13 +152,19 @@ public abstract class StopwordAnalyzerBa
* @param stopwords
* the stopwords reader to load
*
- * @param matchVersion
- * the Lucene version for cross version compatibility
* @return a CharArraySet containing the distinct stopwords from the given
* reader
* @throws IOException
* if loading the stopwords throws an {@link IOException}
*/
+ protected static CharArraySet loadStopwordSet(Reader stopwords) throws IOException {
+ return loadStopwordSet(stopwords, Version.LATEST);
+ }
+
+ /**
+ * @deprecated Use {@link #loadStopwordSet(Reader)}
+ */
+ @Deprecated
protected static CharArraySet loadStopwordSet(Reader stopwords,
Version matchVersion) throws IOException {
try {
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java Thu Aug 21 03:12:52 2014
@@ -73,9 +73,16 @@ public class WordlistLoader {
* Analyzer which uses LowerCaseFilter (like StandardAnalyzer).
*
* @param reader Reader containing the wordlist
- * @param matchVersion the Lucene {@link Version}
* @return A {@link CharArraySet} with the reader's words
*/
+ public static CharArraySet getWordSet(Reader reader) throws IOException {
+ return getWordSet(reader, new CharArraySet(INITIAL_CAPACITY, false));
+ }
+
+ /**
+ * @deprecated Use {@link #getWordSet(Reader)}
+ */
+ @Deprecated
public static CharArraySet getWordSet(Reader reader, Version matchVersion) throws IOException {
return getWordSet(reader, new CharArraySet(matchVersion, INITIAL_CAPACITY, false));
}
@@ -88,9 +95,16 @@ public class WordlistLoader {
*
* @param reader Reader containing the wordlist
* @param comment The string representing a comment.
- * @param matchVersion the Lucene {@link Version}
* @return A CharArraySet with the reader's words
*/
+ public static CharArraySet getWordSet(Reader reader, String comment) throws IOException {
+ return getWordSet(reader, comment, new CharArraySet(INITIAL_CAPACITY, false));
+ }
+
+ /**
+ * @deprecated Use {@link #getWordSet(Reader,String)}
+ */
+ @Deprecated
public static CharArraySet getWordSet(Reader reader, String comment, Version matchVersion) throws IOException {
return getWordSet(reader, comment, new CharArraySet(matchVersion, INITIAL_CAPACITY, false));
}
@@ -170,9 +184,16 @@ public class WordlistLoader {
* </p>
*
* @param reader Reader containing a Snowball stopword list
- * @param matchVersion the Lucene {@link Version}
* @return A {@link CharArraySet} with the reader's words
*/
+ public static CharArraySet getSnowballWordSet(Reader reader) throws IOException {
+ return getSnowballWordSet(reader, new CharArraySet(INITIAL_CAPACITY, false));
+ }
+
+ /**
+ * @deprecated Use {@link #getSnowballWordSet(Reader)}
+ */
+ @Deprecated
public static CharArraySet getSnowballWordSet(Reader reader, Version matchVersion) throws IOException {
return getSnowballWordSet(reader, new CharArraySet(matchVersion, INITIAL_CAPACITY, false));
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/collation/CollationKeyAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/collation/CollationKeyAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/collation/CollationKeyAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/collation/CollationKeyAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -89,7 +89,7 @@ public final class CollationKeyAnalyzer
/**
* Create a new CollationKeyAnalyzer, using the specified collator.
- *
+ *
* @param matchVersion See <a href="#version">above</a>
* @param collator CollationKey generator
*/
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -31,14 +31,14 @@ public class TestArabicAnalyzer extends
/** This test fails with NPE when the
* stopwords file is missing in classpath */
public void testResourcesAvailable() {
- new ArabicAnalyzer(TEST_VERSION_CURRENT);
+ new ArabicAnalyzer();
}
/**
* Some simple tests showing some features of the analyzer, how some regular forms will conflate
*/
public void testBasicFeatures() throws Exception {
- ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT);
+ ArabicAnalyzer a = new ArabicAnalyzer();
assertAnalyzesTo(a, "ÙبÙر", new String[] { "ÙبÙر" });
assertAnalyzesTo(a, "ÙبÙرة", new String[] { "ÙبÙر" }); // feminine marker
@@ -59,7 +59,7 @@ public class TestArabicAnalyzer extends
* Simple tests to show things are getting reset correctly, etc.
*/
public void testReusableTokenStream() throws Exception {
- ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT);
+ ArabicAnalyzer a = new ArabicAnalyzer();
assertAnalyzesTo(a, "ÙبÙر", new String[] { "ÙبÙر" });
assertAnalyzesTo(a, "ÙبÙرة", new String[] { "ÙبÙر" }); // feminine marker
}
@@ -68,7 +68,7 @@ public class TestArabicAnalyzer extends
* Non-arabic text gets treated in a similar way as SimpleAnalyzer.
*/
public void testEnglishInput() throws Exception {
- assertAnalyzesTo(new ArabicAnalyzer(TEST_VERSION_CURRENT), "English text.", new String[] {
+ assertAnalyzesTo(new ArabicAnalyzer(), "English text.", new String[] {
"english", "text" });
}
@@ -76,26 +76,26 @@ public class TestArabicAnalyzer extends
* Test that custom stopwords work, and are not case-sensitive.
*/
public void testCustomStopwords() throws Exception {
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, asSet("the", "and", "a"), false);
- ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT, set);
+ CharArraySet set = new CharArraySet(asSet("the", "and", "a"), false);
+ ArabicAnalyzer a = new ArabicAnalyzer(set);
assertAnalyzesTo(a, "The quick brown fox.", new String[] { "quick",
"brown", "fox" });
}
public void testWithStemExclusionSet() throws IOException {
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, asSet("ساÙدÙات"), false);
- ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
+ CharArraySet set = new CharArraySet(asSet("ساÙدÙات"), false);
+ ArabicAnalyzer a = new ArabicAnalyzer(CharArraySet.EMPTY_SET, set);
assertAnalyzesTo(a, "ÙبÙرة the quick ساÙدÙات", new String[] { "ÙبÙر","the", "quick", "ساÙدÙات" });
assertAnalyzesTo(a, "ÙبÙرة the quick ساÙدÙات", new String[] { "ÙبÙر","the", "quick", "ساÙدÙات" });
- a = new ArabicAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, CharArraySet.EMPTY_SET);
+ a = new ArabicAnalyzer(CharArraySet.EMPTY_SET, CharArraySet.EMPTY_SET);
assertAnalyzesTo(a, "ÙبÙرة the quick ساÙدÙات", new String[] { "ÙبÙر","the", "quick", "ساÙد" });
assertAnalyzesTo(a, "ÙبÙرة the quick ساÙدÙات", new String[] { "ÙبÙر","the", "quick", "ساÙد" });
}
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new ArabicAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new ArabicAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java Thu Aug 21 03:12:52 2014
@@ -119,7 +119,7 @@ public class TestArabicStemFilter extend
}
public void testWithKeywordAttribute() throws IOException {
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
+ CharArraySet set = new CharArraySet(1, true);
set.add("ساÙدÙات");
ArabicLetterTokenizer tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader("ساÙدÙات"));
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -22,7 +22,6 @@ import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.util.CharArraySet;
-import org.apache.lucene.util.Version;
/**
* Test the Bulgarian analyzer
@@ -33,22 +32,22 @@ public class TestBulgarianAnalyzer exten
* This test fails with NPE when the stopwords file is missing in classpath
*/
public void testResourcesAvailable() {
- new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ new BulgarianAnalyzer();
}
public void testStopwords() throws IOException {
- Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new BulgarianAnalyzer();
assertAnalyzesTo(a, "Ðак Ñе казваÑ?", new String[] {"казваÑ"});
}
public void testCustomStopwords() throws IOException {
- Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET);
+ Analyzer a = new BulgarianAnalyzer(CharArraySet.EMPTY_SET);
assertAnalyzesTo(a, "Ðак Ñе казваÑ?",
new String[] {"как", "Ñе", "казваÑ"});
}
public void testReusableTokenStream() throws IOException {
- Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new BulgarianAnalyzer();
assertAnalyzesTo(a, "докÑменÑи", new String[] {"докÑменÑ"});
assertAnalyzesTo(a, "докÑменÑ", new String[] {"докÑменÑ"});
}
@@ -57,7 +56,7 @@ public class TestBulgarianAnalyzer exten
* Test some examples from the paper
*/
public void testBasicExamples() throws IOException {
- Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new BulgarianAnalyzer();
assertAnalyzesTo(a, "енеÑгийни кÑизи", new String[] {"енеÑгийн", "кÑиз"});
assertAnalyzesTo(a, "ÐÑомнаÑа енеÑгиÑ", new String[] {"аÑомн", "енеÑг"});
@@ -68,14 +67,14 @@ public class TestBulgarianAnalyzer exten
}
public void testWithStemExclusionSet() throws IOException {
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
+ CharArraySet set = new CharArraySet(1, true);
set.add("ÑÑÑоеве");
- Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
+ Analyzer a = new BulgarianAnalyzer(CharArraySet.EMPTY_SET, set);
assertAnalyzesTo(a, "ÑÑÑоевеÑе ÑÑÑоеве", new String[] { "ÑÑÑой", "ÑÑÑоеве" });
}
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new BulgarianAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new BulgarianAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java Thu Aug 21 03:12:52 2014
@@ -28,7 +28,6 @@ import org.apache.lucene.analysis.Tokeni
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
import org.apache.lucene.analysis.util.CharArraySet;
-import org.apache.lucene.util.Version;
/**
* Test the Bulgarian Stemmer
@@ -39,7 +38,7 @@ public class TestBulgarianStemmer extend
* common (and some rare) plural pattern is listed.
*/
public void testMasculineNouns() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ BulgarianAnalyzer a = new BulgarianAnalyzer();
// -и pattern
assertAnalyzesTo(a, "гÑад", new String[] {"гÑад"});
@@ -105,7 +104,7 @@ public class TestBulgarianStemmer extend
* Test showing how feminine noun forms conflate
*/
public void testFeminineNouns() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ BulgarianAnalyzer a = new BulgarianAnalyzer();
assertAnalyzesTo(a, "веÑÑ", new String[] {"веÑÑ"});
assertAnalyzesTo(a, "веÑÑÑа", new String[] {"веÑÑ"});
@@ -118,7 +117,7 @@ public class TestBulgarianStemmer extend
* plural pattern is listed
*/
public void testNeuterNouns() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ BulgarianAnalyzer a = new BulgarianAnalyzer();
// -а pattern
assertAnalyzesTo(a, "дÑÑво", new String[] {"дÑÑв"});
@@ -146,7 +145,7 @@ public class TestBulgarianStemmer extend
* Test showing how adjectival forms conflate
*/
public void testAdjectives() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ BulgarianAnalyzer a = new BulgarianAnalyzer();
assertAnalyzesTo(a, "кÑаÑив", new String[] {"кÑаÑив"});
assertAnalyzesTo(a, "кÑаÑивиÑ", new String[] {"кÑаÑив"});
assertAnalyzesTo(a, "кÑаÑивиÑÑ", new String[] {"кÑаÑив"});
@@ -162,7 +161,7 @@ public class TestBulgarianStemmer extend
* Test some exceptional rules, implemented as rewrites.
*/
public void testExceptions() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
+ BulgarianAnalyzer a = new BulgarianAnalyzer();
// Ñи -> к
assertAnalyzesTo(a, "ÑобÑÑвеник", new String[] {"ÑобÑÑвеник"});
@@ -217,7 +216,7 @@ public class TestBulgarianStemmer extend
}
public void testWithKeywordAttribute() throws IOException {
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
+ CharArraySet set = new CharArraySet(1, true);
set.add("ÑÑÑоеве");
MockTokenizer tokenStream = new MockTokenizer(new StringReader("ÑÑÑоевеÑе ÑÑÑоеве"), MockTokenizer.WHITESPACE, false);
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java Thu Aug 21 03:12:52 2014
@@ -130,7 +130,7 @@ public class TestBrazilianStemmer extend
}
public void testReusableTokenStream() throws Exception {
- Analyzer a = new BrazilianAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new BrazilianAnalyzer();
checkReuse(a, "boa", "boa");
checkReuse(a, "boainain", "boainain");
checkReuse(a, "boas", "boas");
@@ -138,22 +138,22 @@ public class TestBrazilianStemmer extend
}
public void testStemExclusionTable() throws Exception {
- BrazilianAnalyzer a = new BrazilianAnalyzer(TEST_VERSION_CURRENT,
- CharArraySet.EMPTY_SET, new CharArraySet(TEST_VERSION_CURRENT, asSet("quintessência"), false));
+ BrazilianAnalyzer a = new BrazilianAnalyzer(
+ CharArraySet.EMPTY_SET, new CharArraySet(asSet("quintessência"), false));
checkReuse(a, "quintessência", "quintessência"); // excluded words will be completely unchanged.
}
public void testWithKeywordAttribute() throws IOException {
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
+ CharArraySet set = new CharArraySet(1, true);
set.add("BrasÃlia");
BrazilianStemFilter filter = new BrazilianStemFilter(
- new SetKeywordMarkerFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader(
+ new SetKeywordMarkerFilter(new LowerCaseTokenizer(new StringReader(
"BrasÃlia Brasilia")), set));
assertTokenStreamContents(filter, new String[] { "brasÃlia", "brasil" });
}
private void check(final String input, final String expected) throws Exception {
- checkOneTerm(new BrazilianAnalyzer(TEST_VERSION_CURRENT), input, expected);
+ checkOneTerm(new BrazilianAnalyzer(), input, expected);
}
private void checkReuse(Analyzer a, String input, String expected) throws Exception {
@@ -162,7 +162,7 @@ public class TestBrazilianStemmer extend
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new BrazilianAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new BrazilianAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
public void testEmptyTerm() throws IOException {
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -27,12 +27,12 @@ public class TestCatalanAnalyzer extends
/** This test fails with NPE when the
* stopwords file is missing in classpath */
public void testResourcesAvailable() {
- new CatalanAnalyzer(TEST_VERSION_CURRENT);
+ new CatalanAnalyzer();
}
/** test stopwords and stemming */
public void testBasics() throws IOException {
- Analyzer a = new CatalanAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new CatalanAnalyzer();
// stemming
checkOneTerm(a, "llengües", "llengu");
checkOneTerm(a, "llengua", "llengu");
@@ -42,22 +42,21 @@ public class TestCatalanAnalyzer extends
/** test use of elisionfilter */
public void testContractions() throws IOException {
- Analyzer a = new CatalanAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new CatalanAnalyzer();
assertAnalyzesTo(a, "Diccionari de l'Institut d'Estudis Catalans",
new String[] { "diccion", "inst", "estud", "catalan" });
}
/** test use of exclusion set */
public void testExclude() throws IOException {
- CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("llengües"), false);
- Analyzer a = new CatalanAnalyzer(TEST_VERSION_CURRENT,
- CatalanAnalyzer.getDefaultStopSet(), exclusionSet);
+ CharArraySet exclusionSet = new CharArraySet(asSet("llengües"), false);
+ Analyzer a = new CatalanAnalyzer(CatalanAnalyzer.getDefaultStopSet(), exclusionSet);
checkOneTerm(a, "llengües", "llengües");
checkOneTerm(a, "llengua", "llengu");
}
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new CatalanAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new CatalanAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -39,7 +39,7 @@ import org.apache.lucene.analysis.util.C
* Most tests adopted from TestCJKTokenizer
*/
public class TestCJKAnalyzer extends BaseTokenStreamTestCase {
- private Analyzer analyzer = new CJKAnalyzer(TEST_VERSION_CURRENT);
+ private Analyzer analyzer = new CJKAnalyzer();
public void testJa1() throws IOException {
assertAnalyzesTo(analyzer, "ä¸äºä¸åäºå
ä¸å
«ä¹å",
@@ -209,7 +209,7 @@ public class TestCJKAnalyzer extends Bas
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
+ Tokenizer tokenizer = new StandardTokenizer(reader);
return new TokenStreamComponents(tokenizer, new CJKBigramFilter(tokenizer));
}
@@ -255,7 +255,7 @@ public class TestCJKAnalyzer extends Bas
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
TokenFilter filter = new FakeStandardTokenizer(tokenizer);
- filter = new StopFilter(TEST_VERSION_CURRENT, filter, CharArraySet.EMPTY_SET);
+ filter = new StopFilter(filter, CharArraySet.EMPTY_SET);
filter = new CJKBigramFilter(filter);
return new TokenStreamComponents(tokenizer, filter);
}
@@ -271,13 +271,13 @@ public class TestCJKAnalyzer extends Bas
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new CJKAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new CJKAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
/** blast some random strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new CJKAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new CJKAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
}
public void testEmptyTerm() throws IOException {
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java Thu Aug 21 03:12:52 2014
@@ -29,7 +29,7 @@ public class TestCJKBigramFilter extends
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
+ Tokenizer t = new StandardTokenizer(reader);
return new TokenStreamComponents(t, new CJKBigramFilter(t));
}
};
@@ -37,7 +37,7 @@ public class TestCJKBigramFilter extends
Analyzer unibiAnalyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
+ Tokenizer t = new StandardTokenizer(reader);
return new TokenStreamComponents(t,
new CJKBigramFilter(t, 0xff, true));
}
@@ -67,7 +67,7 @@ public class TestCJKBigramFilter extends
Analyzer a = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
+ Tokenizer t = new StandardTokenizer(reader);
return new TokenStreamComponents(t, new CJKBigramFilter(t, CJKBigramFilter.HAN));
}
};
@@ -85,7 +85,7 @@ public class TestCJKBigramFilter extends
Analyzer a = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
+ Tokenizer t = new StandardTokenizer(reader);
return new TokenStreamComponents(t,
new CJKBigramFilter(t, 0xff, false));
}
@@ -119,7 +119,7 @@ public class TestCJKBigramFilter extends
Analyzer a = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
+ Tokenizer t = new StandardTokenizer(reader);
return new TokenStreamComponents(t, new CJKBigramFilter(t, CJKBigramFilter.HAN, true));
}
};
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -32,35 +32,35 @@ public class TestSoraniAnalyzer extends
* This test fails with NPE when the stopwords file is missing in classpath
*/
public void testResourcesAvailable() {
- new SoraniAnalyzer(TEST_VERSION_CURRENT);
+ new SoraniAnalyzer();
}
public void testStopwords() throws IOException {
- Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new SoraniAnalyzer();
assertAnalyzesTo(a, "ئÛÙ
Ù¾ÛاÙÛ", new String[] {"Ù¾ÛاÙ"});
}
public void testCustomStopwords() throws IOException {
- Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET);
+ Analyzer a = new SoraniAnalyzer(CharArraySet.EMPTY_SET);
assertAnalyzesTo(a, "ئÛÙ
Ù¾ÛاÙÛ",
new String[] {"ئÛÙ
", "Ù¾ÛاÙ"});
}
public void testReusableTokenStream() throws IOException {
- Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new SoraniAnalyzer();
assertAnalyzesTo(a, "Ù¾ÛاÙÛ", new String[] {"Ù¾ÛاÙ"});
assertAnalyzesTo(a, "Ù¾ÛاÙ", new String[] {"Ù¾ÛاÙ"});
}
public void testWithStemExclusionSet() throws IOException {
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
+ CharArraySet set = new CharArraySet(1, true);
set.add("Ù¾ÛاÙÛ");
- Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, set);
+ Analyzer a = new SoraniAnalyzer(CharArraySet.EMPTY_SET, set);
assertAnalyzesTo(a, "Ù¾ÛاÙÛ", new String[] { "Ù¾ÛاÙÛ" });
}
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new SoraniAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new SoraniAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java Thu Aug 21 03:12:52 2014
@@ -31,7 +31,7 @@ import org.apache.lucene.analysis.core.K
* Test the Sorani Stemmer.
*/
public class TestSoraniStemFilter extends BaseTokenStreamTestCase {
- SoraniAnalyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT);
+ SoraniAnalyzer a = new SoraniAnalyzer();
public void testIndefiniteSingular() throws Exception {
checkOneTerm(a, "Ù¾ÛاÙÛÚ©", "Ù¾ÛاÙ"); // -ek
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java Thu Aug 21 03:12:52 2014
@@ -29,14 +29,14 @@ import org.apache.lucene.analysis.util.C
* Tests CommonGrams(Query)Filter
*/
public class CommonGramsFilterTest extends BaseTokenStreamTestCase {
- private static final CharArraySet commonWords = new CharArraySet(TEST_VERSION_CURRENT, Arrays.asList(
+ private static final CharArraySet commonWords = new CharArraySet(Arrays.asList(
"s", "a", "b", "c", "d", "the", "of"
), false);
public void testReset() throws Exception {
final String input = "How the s a brown s cow d like A B thing?";
- WhitespaceTokenizer wt = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ WhitespaceTokenizer wt = new WhitespaceTokenizer(new StringReader(input));
+ CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
CharTermAttribute term = cgf.addAttribute(CharTermAttribute.class);
cgf.reset();
@@ -58,8 +58,8 @@ public class CommonGramsFilterTest exten
public void testQueryReset() throws Exception {
final String input = "How the s a brown s cow d like A B thing?";
- WhitespaceTokenizer wt = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ WhitespaceTokenizer wt = new WhitespaceTokenizer(new StringReader(input));
+ CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
CommonGramsQueryFilter nsf = new CommonGramsQueryFilter(cgf);
CharTermAttribute term = wt.addAttribute(CharTermAttribute.class);
@@ -91,7 +91,7 @@ public class CommonGramsFilterTest exten
@Override
public TokenStreamComponents createComponents(String field, Reader in) {
Tokenizer tokenizer = new MockTokenizer(in, MockTokenizer.WHITESPACE, false);
- return new TokenStreamComponents(tokenizer, new CommonGramsQueryFilter(new CommonGramsFilter(TEST_VERSION_CURRENT,
+ return new TokenStreamComponents(tokenizer, new CommonGramsQueryFilter(new CommonGramsFilter(
tokenizer, commonWords)));
}
};
@@ -161,8 +161,7 @@ public class CommonGramsFilterTest exten
@Override
public TokenStreamComponents createComponents(String field, Reader in) {
Tokenizer tokenizer = new MockTokenizer(in, MockTokenizer.WHITESPACE, false);
- return new TokenStreamComponents(tokenizer, new CommonGramsFilter(TEST_VERSION_CURRENT,
- tokenizer, commonWords));
+ return new TokenStreamComponents(tokenizer, new CommonGramsFilter(tokenizer, commonWords));
}
};
@@ -249,7 +248,7 @@ public class CommonGramsFilterTest exten
public void testCaseSensitive() throws Exception {
final String input = "How The s a brown s cow d like A B thing?";
MockTokenizer wt = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
- TokenFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ TokenFilter cgf = new CommonGramsFilter(wt, commonWords);
assertTokenStreamContents(cgf, new String[] {"How", "The", "The_s", "s",
"s_a", "a", "a_brown", "brown", "brown_s", "s", "s_cow", "cow",
"cow_d", "d", "d_like", "like", "A", "B", "thing?"});
@@ -261,7 +260,7 @@ public class CommonGramsFilterTest exten
public void testLastWordisStopWord() throws Exception {
final String input = "dog the";
MockTokenizer wt = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "dog_the" });
}
@@ -272,7 +271,7 @@ public class CommonGramsFilterTest exten
public void testFirstWordisStopWord() throws Exception {
final String input = "the dog";
MockTokenizer wt = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "the_dog" });
}
@@ -283,7 +282,7 @@ public class CommonGramsFilterTest exten
public void testOneWordQueryStopWord() throws Exception {
final String input = "the";
MockTokenizer wt = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "the" });
}
@@ -294,7 +293,7 @@ public class CommonGramsFilterTest exten
public void testOneWordQuery() throws Exception {
final String input = "monster";
MockTokenizer wt = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "monster" });
}
@@ -305,7 +304,7 @@ public class CommonGramsFilterTest exten
public void TestFirstAndLastStopWord() throws Exception {
final String input = "the of";
MockTokenizer wt = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "the_of" });
}
@@ -317,7 +316,7 @@ public class CommonGramsFilterTest exten
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer t = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, t, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(t, commonWords);
return new TokenStreamComponents(t, cgf);
}
};
@@ -329,7 +328,7 @@ public class CommonGramsFilterTest exten
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer t = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, t, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(t, commonWords);
return new TokenStreamComponents(t, new CommonGramsQueryFilter(cgf));
}
};
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java Thu Aug 21 03:12:52 2014
@@ -42,7 +42,7 @@ import org.xml.sax.InputSource;
public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
private static CharArraySet makeDictionary(String... dictionary) {
- return new CharArraySet(TEST_VERSION_CURRENT, Arrays.asList(dictionary), true);
+ return new CharArraySet(Arrays.asList(dictionary), true);
}
public void testHyphenationCompoundWordsDA() throws Exception {
@@ -52,7 +52,7 @@ public class TestCompoundWordTokenFilter
HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter
.getHyphenationTree(is);
- HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT,
+ HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
new MockTokenizer(new StringReader("min veninde som er lidt af en læsehest"), MockTokenizer.WHITESPACE, false),
hyphenator,
dict, CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
@@ -72,7 +72,7 @@ public class TestCompoundWordTokenFilter
.getHyphenationTree(is);
// the word basket will not be added due to the longest match option
- HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT,
+ HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
hyphenator, dict,
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
@@ -94,7 +94,7 @@ public class TestCompoundWordTokenFilter
.getHyphenationTree(is);
HyphenationCompoundWordTokenFilter tf = new HyphenationCompoundWordTokenFilter(
- TEST_VERSION_CURRENT,
+
new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
hyphenator,
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
@@ -106,7 +106,7 @@ public class TestCompoundWordTokenFilter
);
tf = new HyphenationCompoundWordTokenFilter(
- TEST_VERSION_CURRENT,
+
new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
hyphenator,
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
@@ -118,7 +118,7 @@ public class TestCompoundWordTokenFilter
);
tf = new HyphenationCompoundWordTokenFilter(
- TEST_VERSION_CURRENT,
+
new MockTokenizer(new StringReader("basketballkurv"), MockTokenizer.WHITESPACE, false),
hyphenator,
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
@@ -137,8 +137,8 @@ public class TestCompoundWordTokenFilter
"Pelar", "Glas", "Ãgon", "Fodral", "Bas", "Fiol", "Makare", "Gesäll",
"Sko", "Vind", "Rute", "Torkare", "Blad");
- DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT,
- new MockTokenizer(
+ DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(
+ new MockTokenizer(
new StringReader(
"Bildörr Bilmotor Biltak Slagborr Hammarborr Pelarborr Glasögonfodral Basfiolsfodral Basfiolsfodralmakaregesäll Skomakare Vindrutetorkare Vindrutetorkarblad abba"),
MockTokenizer.WHITESPACE, false),
@@ -167,7 +167,7 @@ public class TestCompoundWordTokenFilter
"Pelar", "Glas", "Ãgon", "Fodral", "Bas", "Fiols", "Makare", "Gesäll",
"Sko", "Vind", "Rute", "Torkare", "Blad", "Fiolsfodral");
- DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT,
+ DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(
new MockTokenizer(new StringReader("Basfiolsfodralmakaregesäll"), MockTokenizer.WHITESPACE, false),
dict, CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
@@ -183,8 +183,8 @@ public class TestCompoundWordTokenFilter
CharArraySet dict = makeDictionary("ab", "cd", "ef");
Tokenizer tokenizer = new MockTokenizer(new StringReader("abcdef"), MockTokenizer.WHITESPACE, false);
- DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT,
- new WhitespaceTokenizer(TEST_VERSION_CURRENT,
+ DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(
+ new WhitespaceTokenizer(
new StringReader(
"abcdef")
),
@@ -205,8 +205,8 @@ public class TestCompoundWordTokenFilter
CharArraySet dict = makeDictionary("abc", "d", "efg");
Tokenizer tokenizer = new MockTokenizer(new StringReader("abcdefg"), MockTokenizer.WHITESPACE, false);
- DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT,
- new WhitespaceTokenizer(TEST_VERSION_CURRENT,
+ DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(
+ new WhitespaceTokenizer(
new StringReader(
"abcdefg")
),
@@ -231,7 +231,7 @@ public class TestCompoundWordTokenFilter
MockTokenizer wsTokenizer = new MockTokenizer(new StringReader("Rindfleischüberwachungsgesetz"), MockTokenizer.WHITESPACE, false);
wsTokenizer.setEnableChecks(false); // we will reset in a strange place
wsTokenizer.setReader(new StringReader("Rindfleischüberwachungsgesetz"));
- DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT,
+ DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(
wsTokenizer, dict,
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
@@ -256,7 +256,7 @@ public class TestCompoundWordTokenFilter
Tokenizer tokenizer = new MockTokenizer(new StringReader("abcdefg"), MockTokenizer.WHITESPACE, false);
TokenStream stream = new MockRetainAttributeFilter(tokenizer);
stream = new DictionaryCompoundWordTokenFilter(
- TEST_VERSION_CURRENT, stream, dict,
+ stream, dict,
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE, false);
@@ -328,7 +328,7 @@ public class TestCompoundWordTokenFilter
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- TokenFilter filter = new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT, tokenizer, dict);
+ TokenFilter filter = new DictionaryCompoundWordTokenFilter(tokenizer, dict);
return new TokenStreamComponents(tokenizer, filter);
}
@@ -352,7 +352,7 @@ public class TestCompoundWordTokenFilter
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- return new TokenStreamComponents(tokenizer, new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT, tokenizer, dict));
+ return new TokenStreamComponents(tokenizer, new DictionaryCompoundWordTokenFilter(tokenizer, dict));
}
};
checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER);
@@ -364,7 +364,7 @@ public class TestCompoundWordTokenFilter
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
- TokenFilter filter = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT, tokenizer, hyphenator);
+ TokenFilter filter = new HyphenationCompoundWordTokenFilter(tokenizer, hyphenator);
return new TokenStreamComponents(tokenizer, filter);
}
};
@@ -378,7 +378,7 @@ public class TestCompoundWordTokenFilter
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new KeywordTokenizer(reader);
- return new TokenStreamComponents(tokenizer, new DictionaryCompoundWordTokenFilter(TEST_VERSION_CURRENT, tokenizer, dict));
+ return new TokenStreamComponents(tokenizer, new DictionaryCompoundWordTokenFilter(tokenizer, dict));
}
};
checkOneTerm(a, "", "");
@@ -390,7 +390,7 @@ public class TestCompoundWordTokenFilter
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new KeywordTokenizer(reader);
- TokenFilter filter = new HyphenationCompoundWordTokenFilter(TEST_VERSION_CURRENT, tokenizer, hyphenator);
+ TokenFilter filter = new HyphenationCompoundWordTokenFilter(tokenizer, hyphenator);
return new TokenStreamComponents(tokenizer, filter);
}
};
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java Thu Aug 21 03:12:52 2014
@@ -32,7 +32,7 @@ import org.apache.lucene.util.Version;
public class TestAnalyzers extends BaseTokenStreamTestCase {
public void testSimple() throws Exception {
- Analyzer a = new SimpleAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new SimpleAnalyzer();
assertAnalyzesTo(a, "foo bar FOO BAR",
new String[] { "foo", "bar", "foo", "bar" });
assertAnalyzesTo(a, "foo bar . FOO <> BAR",
@@ -52,7 +52,7 @@ public class TestAnalyzers extends BaseT
}
public void testNull() throws Exception {
- Analyzer a = new WhitespaceAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new WhitespaceAnalyzer();
assertAnalyzesTo(a, "foo bar FOO BAR",
new String[] { "foo", "bar", "FOO", "BAR" });
assertAnalyzesTo(a, "foo bar . FOO <> BAR",
@@ -72,7 +72,7 @@ public class TestAnalyzers extends BaseT
}
public void testStop() throws Exception {
- Analyzer a = new StopAnalyzer(TEST_VERSION_CURRENT);
+ Analyzer a = new StopAnalyzer();
assertAnalyzesTo(a, "foo bar FOO BAR",
new String[] { "foo", "bar", "foo", "bar" });
assertAnalyzesTo(a, "foo a bar such FOO THESE BAR",
@@ -95,11 +95,11 @@ public class TestAnalyzers extends BaseT
public void testPayloadCopy() throws IOException {
String s = "how now brown cow";
TokenStream ts;
- ts = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(s));
+ ts = new WhitespaceTokenizer(new StringReader(s));
ts = new PayloadSetter(ts);
verifyPayload(ts);
- ts = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(s));
+ ts = new WhitespaceTokenizer(new StringReader(s));
ts = new PayloadSetter(ts);
verifyPayload(ts);
}
@@ -123,8 +123,8 @@ public class TestAnalyzers extends BaseT
@Override
public TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader);
- return new TokenStreamComponents(tokenizer, new LowerCaseFilter(TEST_VERSION_CURRENT, tokenizer));
+ Tokenizer tokenizer = new WhitespaceTokenizer(reader);
+ return new TokenStreamComponents(tokenizer, new LowerCaseFilter(tokenizer));
}
}
@@ -133,8 +133,8 @@ public class TestAnalyzers extends BaseT
@Override
public TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader);
- return new TokenStreamComponents(tokenizer, new UpperCaseFilter(TEST_VERSION_CURRENT, tokenizer));
+ Tokenizer tokenizer = new WhitespaceTokenizer(reader);
+ return new TokenStreamComponents(tokenizer, new UpperCaseFilter(tokenizer));
}
}
@@ -189,10 +189,9 @@ public class TestAnalyzers extends BaseT
public void testLowerCaseFilterLowSurrogateLeftover() throws IOException {
// test if the limit of the termbuffer is correctly used with supplementary
// chars
- WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT,
+ WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(
new StringReader("BogustermBogusterm\udc16"));
- LowerCaseFilter filter = new LowerCaseFilter(TEST_VERSION_CURRENT,
- tokenizer);
+ LowerCaseFilter filter = new LowerCaseFilter(tokenizer);
assertTokenStreamContents(filter, new String[] {"bogustermbogusterm\udc16"});
filter.reset();
String highSurEndingUpper = "BogustermBoguster\ud801";
@@ -207,8 +206,7 @@ public class TestAnalyzers extends BaseT
public void testLowerCaseTokenizer() throws IOException {
StringReader reader = new StringReader("Tokenizer \ud801\udc1ctest");
- LowerCaseTokenizer tokenizer = new LowerCaseTokenizer(TEST_VERSION_CURRENT,
- reader);
+ LowerCaseTokenizer tokenizer = new LowerCaseTokenizer(reader);
assertTokenStreamContents(tokenizer, new String[] { "tokenizer",
"\ud801\udc44test" });
}
@@ -224,7 +222,7 @@ public class TestAnalyzers extends BaseT
public void testWhitespaceTokenizer() throws IOException {
StringReader reader = new StringReader("Tokenizer \ud801\udc1ctest");
- WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT,
+ WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(
reader);
assertTokenStreamContents(tokenizer, new String[] { "Tokenizer",
"\ud801\udc1ctest" });
@@ -242,17 +240,17 @@ public class TestAnalyzers extends BaseT
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new WhitespaceAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
- checkRandomData(random(), new SimpleAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
- checkRandomData(random(), new StopAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new WhitespaceAnalyzer(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new SimpleAnalyzer(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new StopAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
/** blast some random large strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new WhitespaceAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
- checkRandomData(random, new SimpleAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
- checkRandomData(random, new StopAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new WhitespaceAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new SimpleAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new StopAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java Thu Aug 21 03:12:52 2014
@@ -47,7 +47,7 @@ import org.apache.lucene.util.LuceneTest
@SuppressCodecs("Direct")
public class TestBugInSomething extends BaseTokenStreamTestCase {
public void test() throws Exception {
- final CharArraySet cas = new CharArraySet(TEST_VERSION_CURRENT, 3, false);
+ final CharArraySet cas = new CharArraySet(3, false);
cas.add("jjp");
cas.add("wlmwoknt");
cas.add("tcgyreo");
@@ -62,7 +62,7 @@ public class TestBugInSomething extends
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer t = new MockTokenizer(new TestRandomChains.CheckThatYouDidntReadAnythingReaderWrapper(reader), MockTokenFilter.ENGLISH_STOPSET, false, -65);
- TokenFilter f = new CommonGramsFilter(TEST_VERSION_CURRENT, t, cas);
+ TokenFilter f = new CommonGramsFilter(t, cas);
return new TokenStreamComponents(t, f);
}
@@ -249,11 +249,11 @@ public class TestBugInSomething extends
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new EdgeNGramTokenizer(TEST_VERSION_CURRENT, reader, 2, 94);
+ Tokenizer tokenizer = new EdgeNGramTokenizer(reader, 2, 94);
//TokenStream stream = new SopTokenFilter(tokenizer);
TokenStream stream = new ShingleFilter(tokenizer, 5);
//stream = new SopTokenFilter(stream);
- stream = new NGramTokenFilter(TEST_VERSION_CURRENT, stream, 55, 83);
+ stream = new NGramTokenFilter(stream, 55, 83);
//stream = new SopTokenFilter(stream);
return new TokenStreamComponents(tokenizer, stream);
}
@@ -262,7 +262,7 @@ public class TestBugInSomething extends
}
public void testCuriousWikipediaString() throws Exception {
- final CharArraySet protWords = new CharArraySet(TEST_VERSION_CURRENT, new HashSet<>(
+ final CharArraySet protWords = new CharArraySet(new HashSet<>(
Arrays.asList("rrdpafa", "pupmmlu", "xlq", "dyy", "zqrxrrck", "o", "hsrlfvcha")), false);
final byte table[] = new byte[] {
-57, 26, 1, 48, 63, -23, 55, -84, 18, 120, -97, 103, 58, 13, 84, 89, 57, -13, -63,
@@ -277,7 +277,7 @@ public class TestBugInSomething extends
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = new WikipediaTokenizer(reader);
TokenStream stream = new SopTokenFilter(tokenizer);
- stream = new WordDelimiterFilter(TEST_VERSION_CURRENT, stream, table, -50, protWords);
+ stream = new WordDelimiterFilter(stream, table, -50, protWords);
stream = new SopTokenFilter(stream);
return new TokenStreamComponents(tokenizer, stream);
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -41,16 +41,16 @@ import java.util.Random;
public class TestClassicAnalyzer extends BaseTokenStreamTestCase {
- private Analyzer a = new ClassicAnalyzer(TEST_VERSION_CURRENT);
+ private Analyzer a = new ClassicAnalyzer();
public void testMaxTermLength() throws Exception {
- ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
+ ClassicAnalyzer sa = new ClassicAnalyzer();
sa.setMaxTokenLength(5);
assertAnalyzesTo(sa, "ab cd toolong xy z", new String[]{"ab", "cd", "xy", "z"});
}
public void testMaxTermLength2() throws Exception {
- ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
+ ClassicAnalyzer sa = new ClassicAnalyzer();
assertAnalyzesTo(sa, "ab cd toolong xy z", new String[]{"ab", "cd", "toolong", "xy", "z"});
sa.setMaxTokenLength(5);
@@ -114,7 +114,7 @@ public class TestClassicAnalyzer extends
public void testLucene1140() throws Exception {
try {
- ClassicAnalyzer analyzer = new ClassicAnalyzer(TEST_VERSION_CURRENT);
+ ClassicAnalyzer analyzer = new ClassicAnalyzer();
assertAnalyzesTo(analyzer, "www.nutch.org.", new String[]{ "www.nutch.org" }, new String[] { "<HOST>" });
} catch (NullPointerException e) {
fail("Should not throw an NPE and it did");
@@ -124,7 +124,7 @@ public class TestClassicAnalyzer extends
public void testDomainNames() throws Exception {
// Current lucene should not show the bug
- ClassicAnalyzer a2 = new ClassicAnalyzer(TEST_VERSION_CURRENT);
+ ClassicAnalyzer a2 = new ClassicAnalyzer();
// domain names
assertAnalyzesTo(a2, "www.nutch.org", new String[]{"www.nutch.org"});
@@ -254,8 +254,7 @@ public class TestClassicAnalyzer extends
*/
public void testWickedLongTerm() throws IOException {
RAMDirectory dir = new RAMDirectory();
- IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(
- TEST_VERSION_CURRENT, new ClassicAnalyzer(TEST_VERSION_CURRENT)));
+ IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, new ClassicAnalyzer()));
char[] chars = new char[IndexWriter.MAX_TERM_LENGTH];
Arrays.fill(chars, 'x');
@@ -301,7 +300,7 @@ public class TestClassicAnalyzer extends
// maximum length term, and search on that term:
doc = new Document();
doc.add(new TextField("content", bigTerm, Field.Store.NO));
- ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
+ ClassicAnalyzer sa = new ClassicAnalyzer();
sa.setMaxTokenLength(100000);
writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, sa));
writer.addDocument(doc);
@@ -315,12 +314,12 @@ public class TestClassicAnalyzer extends
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new ClassicAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new ClassicAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
/** blast some random large strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new ClassicAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new ClassicAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java Thu Aug 21 03:12:52 2014
@@ -69,7 +69,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -89,7 +89,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -107,7 +107,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -126,7 +126,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -144,7 +144,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -163,7 +163,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory(), reader);
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -50,8 +50,7 @@ public class TestKeywordAnalyzer extends
public void setUp() throws Exception {
super.setUp();
directory = newDirectory();
- IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(
- TEST_VERSION_CURRENT, new SimpleAnalyzer(TEST_VERSION_CURRENT)));
+ IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(TEST_VERSION_CURRENT, new SimpleAnalyzer()));
Document doc = new Document();
doc.add(new StringField("partnum", "Q36", Field.Store.YES));
@@ -73,7 +72,7 @@ public class TestKeywordAnalyzer extends
/*
public void testPerFieldAnalyzer() throws Exception {
- PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SimpleAnalyzer(TEST_VERSION_CURRENT));
+ PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SimpleAnalyzer());
analyzer.addAnalyzer("partnum", new KeywordAnalyzer());
QueryParser queryParser = new QueryParser(TEST_VERSION_CURRENT, "description", analyzer);
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java Thu Aug 21 03:12:52 2014
@@ -60,7 +60,7 @@ import org.apache.lucene.analysis.charfi
import org.apache.lucene.analysis.cjk.CJKBigramFilter;
import org.apache.lucene.analysis.commongrams.CommonGramsFilter;
import org.apache.lucene.analysis.commongrams.CommonGramsQueryFilter;
-import org.apache.lucene.analysis.compound.HyphenationCompoundWordTokenFilter;
+import org.apache.lucene.analysis.compound.Lucene43HyphenationCompoundWordTokenFilter;
import org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
import org.apache.lucene.analysis.hunspell.Dictionary;
@@ -387,7 +387,7 @@ public class TestRandomChains extends Ba
put(CharArraySet.class, new ArgProducer() {
@Override public Object create(Random random) {
int num = random.nextInt(10);
- CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, num, random.nextBoolean());
+ CharArraySet set = new CharArraySet(num, random.nextBoolean());
for (int i = 0; i < num; i++) {
// TODO: make nastier
set.add(TestUtil.randomSimpleString(random));
@@ -445,7 +445,7 @@ public class TestRandomChains extends Ba
// TODO: make nastier
try {
InputSource is = new InputSource(TestCompoundWordTokenFilter.class.getResource("da_UTF8.xml").toExternalForm());
- HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
+ HyphenationTree hyphenator = Lucene43HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
return hyphenator;
} catch (Exception ex) {
Rethrow.rethrow(ex);
@@ -510,7 +510,7 @@ public class TestRandomChains extends Ba
put(CharArrayMap.class, new ArgProducer() {
@Override public Object create(Random random) {
int num = random.nextInt(10);
- CharArrayMap<String> map = new CharArrayMap<>(TEST_VERSION_CURRENT, num, random.nextBoolean());
+ CharArrayMap<String> map = new CharArrayMap<>(num, random.nextBoolean());
for (int i = 0; i < num; i++) {
// TODO: make nastier
map.put(TestUtil.randomSimpleString(random), TestUtil.randomSimpleString(random));
@@ -637,7 +637,7 @@ public class TestRandomChains extends Ba
args[i] = stream;
} else if (paramType == CommonGramsFilter.class) {
// TODO: fix this one, thats broken: CommonGramsQueryFilter takes this one explicitly
- args[i] = new CommonGramsFilter(TEST_VERSION_CURRENT, stream, newRandomArg(random, CharArraySet.class));
+ args[i] = new CommonGramsFilter(stream, newRandomArg(random, CharArraySet.class));
} else {
args[i] = newRandomArg(random, paramType);
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -41,7 +41,7 @@ public class TestStandardAnalyzer extend
sb.append(whitespace);
sb.append("testing 1234");
String input = sb.toString();
- StandardTokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
+ StandardTokenizer tokenizer = new StandardTokenizer(new StringReader(input));
BaseTokenStreamTestCase.assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" });
}
@@ -50,7 +50,7 @@ public class TestStandardAnalyzer extend
protected TokenStreamComponents createComponents
(String fieldName, Reader reader) {
- Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new StandardTokenizer(newAttributeFactory(), reader);
return new TokenStreamComponents(tokenizer);
}
};
@@ -321,13 +321,13 @@ public class TestStandardAnalyzer extend
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new StandardAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new StandardAnalyzer(), 1000*RANDOM_MULTIPLIER);
}
/** blast some random large strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new StandardAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new StandardAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
}
// Adds random graph after:
@@ -337,7 +337,7 @@ public class TestStandardAnalyzer extend
new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, newAttributeFactory(), reader);
+ Tokenizer tokenizer = new StandardTokenizer(newAttributeFactory(), reader);
TokenStream tokenStream = new MockGraphTokenFilter(random(), tokenizer);
return new TokenStreamComponents(tokenizer, tokenStream);
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -23,7 +23,7 @@ import org.apache.lucene.analysis.tokena
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.IOUtils;
-import org.apache.lucene.util.Version;
+
import java.io.IOException;
import java.util.Iterator;
@@ -32,7 +32,7 @@ import java.util.HashSet;
public class TestStopAnalyzer extends BaseTokenStreamTestCase {
- private StopAnalyzer stop = new StopAnalyzer(TEST_VERSION_CURRENT);
+ private StopAnalyzer stop = new StopAnalyzer();
private Set<Object> inValidTokens = new HashSet<>();
@Override
@@ -63,8 +63,8 @@ public class TestStopAnalyzer extends Ba
}
public void testStopList() throws IOException {
- CharArraySet stopWordsSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("good", "test", "analyzer"), false);
- StopAnalyzer newStop = new StopAnalyzer(TEST_VERSION_CURRENT, stopWordsSet);
+ CharArraySet stopWordsSet = new CharArraySet(asSet("good", "test", "analyzer"), false);
+ StopAnalyzer newStop = new StopAnalyzer(stopWordsSet);
TokenStream stream = newStop.tokenStream("test", "This is a good test of the english stop analyzer");
try {
assertNotNull(stream);
@@ -82,8 +82,8 @@ public class TestStopAnalyzer extends Ba
}
public void testStopListPositions() throws IOException {
- CharArraySet stopWordsSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("good", "test", "analyzer"), false);
- StopAnalyzer newStop = new StopAnalyzer(TEST_VERSION_CURRENT, stopWordsSet);
+ CharArraySet stopWordsSet = new CharArraySet(asSet("good", "test", "analyzer"), false);
+ StopAnalyzer newStop = new StopAnalyzer(stopWordsSet);
String s = "This is a good test of the english stop analyzer with positions";
int expectedIncr[] = { 1, 1, 1, 3, 1, 1, 1, 2, 1};
TokenStream stream = newStop.tokenStream("test", s);
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java Thu Aug 21 03:12:52 2014
@@ -41,16 +41,16 @@ public class TestStopFilter extends Base
public void testExactCase() throws IOException {
StringReader reader = new StringReader("Now is The Time");
- CharArraySet stopWords = new CharArraySet(TEST_VERSION_CURRENT, asSet("is", "the", "Time"), false);
- TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopWords);
+ CharArraySet stopWords = new CharArraySet(asSet("is", "the", "Time"), false);
+ TokenStream stream = new StopFilter(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopWords);
assertTokenStreamContents(stream, new String[] { "Now", "The" });
}
public void testStopFilt() throws IOException {
StringReader reader = new StringReader("Now is The Time");
String[] stopWords = new String[] { "is", "the", "Time" };
- CharArraySet stopSet = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords);
- TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet);
+ CharArraySet stopSet = StopFilter.makeStopSet(stopWords);
+ TokenStream stream = new StopFilter(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet);
assertTokenStreamContents(stream, new String[] { "Now", "The" });
}
@@ -68,7 +68,7 @@ public class TestStopFilter extends Base
log(sb.toString());
String stopWords[] = a.toArray(new String[0]);
for (int i=0; i<a.size(); i++) log("Stop: "+stopWords[i]);
- CharArraySet stopSet = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords);
+ CharArraySet stopSet = StopFilter.makeStopSet(stopWords);
// with increments
StringReader reader = new StringReader(sb.toString());
StopFilter stpf = new StopFilter(Version.LUCENE_4_0, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet);
@@ -91,19 +91,19 @@ public class TestStopFilter extends Base
for (int i=0; i<a0.size(); i++) log("Stop0: "+stopWords0[i]);
String stopWords1[] = a1.toArray(new String[0]);
for (int i=0; i<a1.size(); i++) log("Stop1: "+stopWords1[i]);
- CharArraySet stopSet0 = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords0);
- CharArraySet stopSet1 = StopFilter.makeStopSet(TEST_VERSION_CURRENT, stopWords1);
+ CharArraySet stopSet0 = StopFilter.makeStopSet(stopWords0);
+ CharArraySet stopSet1 = StopFilter.makeStopSet(stopWords1);
reader = new StringReader(sb.toString());
- StopFilter stpf0 = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet0); // first part of the set
+ StopFilter stpf0 = new StopFilter(new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopSet0); // first part of the set
stpf0.setEnablePositionIncrements(true);
- StopFilter stpf01 = new StopFilter(TEST_VERSION_CURRENT, stpf0, stopSet1); // two stop filters concatenated!
+ StopFilter stpf01 = new StopFilter(stpf0, stopSet1); // two stop filters concatenated!
doTestStopPositons(stpf01,true);
}
// LUCENE-3849: make sure after .end() we see the "ending" posInc
public void testEndStopword() throws Exception {
- CharArraySet stopSet = StopFilter.makeStopSet(TEST_VERSION_CURRENT, "of");
- StopFilter stpf = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(new StringReader("test of"), MockTokenizer.WHITESPACE, false), stopSet);
+ CharArraySet stopSet = StopFilter.makeStopSet("of");
+ StopFilter stpf = new StopFilter(new MockTokenizer(new StringReader("test of"), MockTokenizer.WHITESPACE, false), stopSet);
assertTokenStreamContents(stpf, new String[] { "test" },
new int[] {0},
new int[] {4},