You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2014/07/31 12:44:44 UTC
svn commit: r1614852 [4/9] - in /lucene/dev/trunk:
lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/
lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/
lucene/analysis/common/src/java/org/apache/lucene/analysis/br/
lucene/analy...
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArrayMap.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArrayMap.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArrayMap.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArrayMap.java Thu Jul 31 10:44:39 2014
@@ -25,6 +25,8 @@ import java.util.Map;
import java.util.Set;
import org.apache.lucene.analysis.util.CharacterUtils;
+import org.apache.lucene.util.Version;
+
/**
* A simple class that stores key Strings as char[]'s in a
@@ -34,6 +36,19 @@ import org.apache.lucene.analysis.util.C
* etc. It is designed to be quick to retrieve items
* by char[] keys without the necessity of converting
* to a String first.
+ *
+ * <a name="version"></a>
+ * <p>You must specify the required {@link Version}
+ * compatibility when creating {@link CharArrayMap}:
+ * <ul>
+ * <li> As of 3.1, supplementary characters are
+ * properly lowercased.</li>
+ * </ul>
+ * Before 3.1 supplementary characters could not be
+ * lowercased correctly due to the lack of Unicode 4
+ * support in JDK 1.4. To use instances of
+ * {@link CharArrayMap} with the behavior before Lucene
+ * 3.1 pass a {@link Version} < 3.1 to the constructors.
*/
public class CharArrayMap<V> extends AbstractMap<Object,V> {
// private only because missing generics
@@ -43,12 +58,16 @@ public class CharArrayMap<V> extends Abs
private final CharacterUtils charUtils;
private boolean ignoreCase;
private int count;
+ final Version matchVersion; // package private because used in CharArraySet
char[][] keys; // package private because used in CharArraySet's non Set-conform CharArraySetIterator
V[] values; // package private because used in CharArraySet's non Set-conform CharArraySetIterator
/**
* Create map with enough capacity to hold startSize terms
- *
+ *
+ * @param matchVersion
+ * compatibility match version see <a href="#version">Version
+ * note</a> above for details.
* @param startSize
* the initial capacity
* @param ignoreCase
@@ -56,27 +75,31 @@ public class CharArrayMap<V> extends Abs
* otherwise <code>true</code>.
*/
@SuppressWarnings("unchecked")
- public CharArrayMap(int startSize, boolean ignoreCase) {
+ public CharArrayMap(Version matchVersion, int startSize, boolean ignoreCase) {
this.ignoreCase = ignoreCase;
int size = INIT_SIZE;
while(startSize + (startSize>>2) > size)
size <<= 1;
keys = new char[size][];
values = (V[]) new Object[size];
- this.charUtils = CharacterUtils.getInstance();
+ this.charUtils = CharacterUtils.getInstance(matchVersion);
+ this.matchVersion = matchVersion;
}
/**
* Creates a map from the mappings in another map.
- *
+ *
+ * @param matchVersion
+ * compatibility match version see <a href="#version">Version
+ * note</a> above for details.
* @param c
* a map whose mappings to be copied
* @param ignoreCase
* <code>false</code> if and only if the set should be case sensitive
* otherwise <code>true</code>.
*/
- public CharArrayMap(Map<?,? extends V> c, boolean ignoreCase) {
- this(c.size(), ignoreCase);
+ public CharArrayMap(Version matchVersion, Map<?,? extends V> c, boolean ignoreCase) {
+ this(matchVersion, c.size(), ignoreCase);
putAll(c);
}
@@ -87,6 +110,7 @@ public class CharArrayMap<V> extends Abs
this.ignoreCase = toCopy.ignoreCase;
this.count = toCopy.count;
this.charUtils = toCopy.charUtils;
+ this.matchVersion = toCopy.matchVersion;
}
/** Clears all entries in this map. This method is supported for reusing, but not {@link Map#remove}. */
@@ -541,7 +565,18 @@ public class CharArrayMap<V> extends Abs
/**
* Returns a copy of the given map as a {@link CharArrayMap}. If the given map
* is a {@link CharArrayMap} the ignoreCase property will be preserved.
+ * <p>
+ * <b>Note:</b> If you intend to create a copy of another {@link CharArrayMap} where
+ * the {@link Version} of the source map differs from its copy
+ * {@link #CharArrayMap(Version, Map, boolean)} should be used instead.
+ * The {@link #copy(Version, Map)} will preserve the {@link Version} of the
+ * source map it is an instance of {@link CharArrayMap}.
+ * </p>
*
+ * @param matchVersion
+ * compatibility match version see <a href="#version">Version
+ * note</a> above for details. This argument will be ignored if the
+ * given map is a {@link CharArrayMap}.
* @param map
* a map to copy
* @return a copy of the given map as a {@link CharArrayMap}. If the given map
@@ -549,7 +584,7 @@ public class CharArrayMap<V> extends Abs
* matchVersion will be of the given map will be preserved.
*/
@SuppressWarnings("unchecked")
- public static <V> CharArrayMap<V> copy(final Map<?,? extends V> map) {
+ public static <V> CharArrayMap<V> copy(final Version matchVersion, final Map<?,? extends V> map) {
if(map == EMPTY_MAP)
return emptyMap();
if(map instanceof CharArrayMap) {
@@ -565,7 +600,7 @@ public class CharArrayMap<V> extends Abs
m.values = values;
return m;
}
- return new CharArrayMap<>(map, false);
+ return new CharArrayMap<>(matchVersion, map, false);
}
/** Returns an empty, unmodifiable map. */
@@ -624,7 +659,7 @@ public class CharArrayMap<V> extends Abs
*/
private static final class EmptyCharArrayMap<V> extends UnmodifiableCharArrayMap<V> {
EmptyCharArrayMap() {
- super(new CharArrayMap<V>(0, false));
+ super(new CharArrayMap<V>(Version.LUCENE_CURRENT, 0, false));
}
@Override
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArraySet.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArraySet.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArraySet.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArraySet.java Thu Jul 31 10:44:39 2014
@@ -22,6 +22,9 @@ import java.util.Collection;
import java.util.Iterator;
import java.util.Set;
+import org.apache.lucene.util.Version;
+
+
/**
* A simple class that stores Strings as char[]'s in a
* hash table. Note that this is not a general purpose
@@ -31,6 +34,18 @@ import java.util.Set;
* is in the set without the necessity of converting it
* to a String first.
*
+ * <a name="version"></a>
+ * <p>You must specify the required {@link Version}
+ * compatibility when creating {@link CharArraySet}:
+ * <ul>
+ * <li> As of 3.1, supplementary characters are
+ * properly lowercased.</li>
+ * </ul>
+ * Before 3.1 supplementary characters could not be
+ * lowercased correctly due to the lack of Unicode 4
+ * support in JDK 1.4. To use instances of
+ * {@link CharArraySet} with the behavior before Lucene
+ * 3.1 pass a {@link Version} < 3.1 to the constructors.
* <P>
* <em>Please note:</em> This class implements {@link java.util.Set Set} but
* does not behave like it should in all cases. The generic type is
@@ -49,27 +64,33 @@ public class CharArraySet extends Abstra
/**
* Create set with enough capacity to hold startSize terms
*
+ * @param matchVersion
+ * compatibility match version see <a href="#version">Version
+ * note</a> above for details.
* @param startSize
* the initial capacity
* @param ignoreCase
* <code>false</code> if and only if the set should be case sensitive
* otherwise <code>true</code>.
*/
- public CharArraySet(int startSize, boolean ignoreCase) {
- this(new CharArrayMap<>(startSize, ignoreCase));
+ public CharArraySet(Version matchVersion, int startSize, boolean ignoreCase) {
+ this(new CharArrayMap<>(matchVersion, startSize, ignoreCase));
}
/**
* Creates a set from a Collection of objects.
*
+ * @param matchVersion
+ * compatibility match version see <a href="#version">Version
+ * note</a> above for details.
* @param c
* a collection whose elements to be placed into the set
* @param ignoreCase
* <code>false</code> if and only if the set should be case sensitive
* otherwise <code>true</code>.
*/
- public CharArraySet(Collection<?> c, boolean ignoreCase) {
- this(c.size(), ignoreCase);
+ public CharArraySet(Version matchVersion, Collection<?> c, boolean ignoreCase) {
+ this(matchVersion, c.size(), ignoreCase);
addAll(c);
}
@@ -151,21 +172,32 @@ public class CharArraySet extends Abstra
/**
* Returns a copy of the given set as a {@link CharArraySet}. If the given set
* is a {@link CharArraySet} the ignoreCase property will be preserved.
+ * <p>
+ * <b>Note:</b> If you intend to create a copy of another {@link CharArraySet} where
+ * the {@link Version} of the source set differs from its copy
+ * {@link #CharArraySet(Version, Collection, boolean)} should be used instead.
+ * The {@link #copy(Version, Set)} will preserve the {@link Version} of the
+ * source set it is an instance of {@link CharArraySet}.
+ * </p>
*
+ * @param matchVersion
+ * compatibility match version see <a href="#version">Version
+ * note</a> above for details. This argument will be ignored if the
+ * given set is a {@link CharArraySet}.
* @param set
* a set to copy
* @return a copy of the given set as a {@link CharArraySet}. If the given set
* is a {@link CharArraySet} the ignoreCase property as well as the
* matchVersion will be of the given set will be preserved.
*/
- public static CharArraySet copy(final Set<?> set) {
+ public static CharArraySet copy(final Version matchVersion, final Set<?> set) {
if(set == EMPTY_SET)
return EMPTY_SET;
if(set instanceof CharArraySet) {
final CharArraySet source = (CharArraySet) set;
- return new CharArraySet(CharArrayMap.copy(source.map));
+ return new CharArraySet(CharArrayMap.copy(source.map.matchVersion, source.map));
}
- return new CharArraySet(set, false);
+ return new CharArraySet(matchVersion, set, false);
}
/**
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharTokenizer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharTokenizer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharTokenizer.java Thu Jul 31 10:44:39 2014
@@ -18,12 +18,15 @@ package org.apache.lucene.analysis.util;
*/
import java.io.IOException;
+import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.AttributeFactory;
+import org.apache.lucene.util.AttributeSource;
import org.apache.lucene.analysis.util.CharacterUtils;
+import org.apache.lucene.util.Version;
import org.apache.lucene.analysis.util.CharacterUtils.CharacterBuffer;
/**
@@ -33,18 +36,25 @@ public abstract class CharTokenizer exte
/**
* Creates a new {@link CharTokenizer} instance
+ *
+ * @param matchVersion
+ * Lucene version to match
*/
- public CharTokenizer() {
+ public CharTokenizer(Version matchVersion) {
+ charUtils = CharacterUtils.getInstance(matchVersion);
}
/**
* Creates a new {@link CharTokenizer} instance
*
+ * @param matchVersion
+ * Lucene version to match
* @param factory
* the attribute factory to use for this {@link Tokenizer}
*/
- public CharTokenizer(AttributeFactory factory) {
+ public CharTokenizer(Version matchVersion, AttributeFactory factory) {
super(factory);
+ charUtils = CharacterUtils.getInstance(matchVersion);
}
private int offset = 0, bufferIndex = 0, dataLen = 0, finalOffset = 0;
@@ -54,7 +64,7 @@ public abstract class CharTokenizer exte
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
- private final CharacterUtils charUtils = CharacterUtils.getInstance();
+ private final CharacterUtils charUtils;
private final CharacterBuffer ioBuffer = CharacterUtils.newCharacterBuffer(IO_BUFFER_SIZE);
/**
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharacterUtils.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharacterUtils.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharacterUtils.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharacterUtils.java Thu Jul 31 10:44:39 2014
@@ -34,25 +34,29 @@ public abstract class CharacterUtils {
private static final Java5CharacterUtils JAVA_5 = new Java5CharacterUtils();
/**
- * Returns a {@link CharacterUtils} implementation.
+ * Returns a {@link CharacterUtils} implementation according to the given
+ * {@link Version} instance.
+ *
+ * @param matchVersion
+ * a version instance
* @return a {@link CharacterUtils} implementation according to the given
* {@link Version} instance.
*/
- public static CharacterUtils getInstance() {
+ public static CharacterUtils getInstance(final Version matchVersion) {
return JAVA_5;
}
- /**
- * explicitly returns a version matching java 4 semantics
- * @deprecated Only for n-gram backwards compat
- */
- @Deprecated
+ /** explicitly returns a version matching java 4 semantics */
public static CharacterUtils getJava4Instance() {
return JAVA_4;
}
/**
* Returns the code point at the given index of the {@link CharSequence}.
+ * Depending on the {@link Version} passed to
+ * {@link CharacterUtils#getInstance(Version)} this method mimics the behavior
+ * of {@link Character#codePointAt(char[], int)} as it would have been
+ * available on a Java 1.4 JVM or on a later virtual machine version.
*
* @param seq
* a character sequence
@@ -71,6 +75,10 @@ public abstract class CharacterUtils {
/**
* Returns the code point at the given index of the char array where only elements
* with index less than the limit are used.
+ * Depending on the {@link Version} passed to
+ * {@link CharacterUtils#getInstance(Version)} this method mimics the behavior
+ * of {@link Character#codePointAt(char[], int)} as it would have been
+ * available on a Java 1.4 JVM or on a later virtual machine version.
*
* @param chars
* a character array
@@ -180,7 +188,10 @@ public abstract class CharacterUtils {
* the middle of a surrogate pair, even if there are remaining characters in
* the {@link Reader}.
* <p>
- * This method guarantees
+ * Depending on the {@link Version} passed to
+ * {@link CharacterUtils#getInstance(Version)} this method implements
+ * supplementary character awareness when filling the given buffer. For all
+ * {@link Version} > 3.0 {@link #fill(CharacterBuffer, Reader, int)} guarantees
* that the given {@link CharacterBuffer} will never contain a high surrogate
* character as the last element in the buffer unless it is the last available
* character in the reader. In other words, high and low surrogate pairs will
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java Thu Jul 31 10:44:39 2014
@@ -32,15 +32,18 @@ import org.apache.lucene.util.Version;
*/
public abstract class FilteringTokenFilter extends TokenFilter {
+ protected final Version version;
private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
private int skippedPositions;
/**
* Create a new {@link FilteringTokenFilter}.
+ * @param version the Lucene match version
* @param in the {@link TokenStream} to consume
*/
- public FilteringTokenFilter(TokenStream in) {
+ public FilteringTokenFilter(Version version, TokenStream in) {
super(in);
+ this.version = version;
}
/** Override this method and return if the current input token should be returned by {@link #incrementToken}. */
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java Thu Jul 31 10:44:39 2014
@@ -24,6 +24,7 @@ import java.nio.charset.StandardCharsets
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.util.IOUtils;
+import org.apache.lucene.util.Version;
/**
* Base class for Analyzers that need to make use of stopword sets.
@@ -36,6 +37,8 @@ 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
@@ -50,20 +53,26 @@ 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) {
+ 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(stopwords));
+ .unmodifiableSet(CharArraySet.copy(version, stopwords));
}
/**
* Creates a new Analyzer with an empty stopword set
+ *
+ * @param version
+ * the Lucene version for cross version compatibility
*/
- protected StopwordAnalyzerBase() {
- this(null);
+ protected StopwordAnalyzerBase(final Version version) {
+ this(version, null);
}
/**
@@ -90,7 +99,7 @@ public abstract class StopwordAnalyzerBa
Reader reader = null;
try {
reader = IOUtils.getDecodingReader(aClass.getResourceAsStream(resource), StandardCharsets.UTF_8);
- return WordlistLoader.getWordSet(reader, comment, new CharArraySet(16, ignoreCase));
+ return WordlistLoader.getWordSet(reader, comment, new CharArraySet(Version.LUCENE_CURRENT, 16, ignoreCase));
} finally {
IOUtils.close(reader);
}
@@ -102,16 +111,20 @@ 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 {
+ protected static CharArraySet loadStopwordSet(File stopwords,
+ Version matchVersion) throws IOException {
Reader reader = null;
try {
reader = IOUtils.getDecodingReader(stopwords, StandardCharsets.UTF_8);
- return WordlistLoader.getWordSet(reader);
+ return WordlistLoader.getWordSet(reader, matchVersion);
} finally {
IOUtils.close(reader);
}
@@ -123,14 +136,17 @@ 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 {
+ protected static CharArraySet loadStopwordSet(Reader stopwords,
+ Version matchVersion) throws IOException {
try {
- return WordlistLoader.getWordSet(stopwords);
+ return WordlistLoader.getWordSet(stopwords, matchVersion);
} finally {
IOUtils.close(stopwords);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java Thu Jul 31 10:44:39 2014
@@ -26,6 +26,7 @@ import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.util.IOUtils;
+import org.apache.lucene.util.Version;
/**
* Loader for text files that represent a list of stopwords.
@@ -72,10 +73,11 @@ 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));
+ public static CharArraySet getWordSet(Reader reader, Version matchVersion) throws IOException {
+ return getWordSet(reader, new CharArraySet(matchVersion, INITIAL_CAPACITY, false));
}
/**
@@ -86,10 +88,11 @@ 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));
+ public static CharArraySet getWordSet(Reader reader, String comment, Version matchVersion) throws IOException {
+ return getWordSet(reader, comment, new CharArraySet(matchVersion, INITIAL_CAPACITY, false));
}
/**
@@ -167,10 +170,11 @@ 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));
+ public static CharArraySet getSnowballWordSet(Reader reader, Version matchVersion) throws IOException {
+ return getSnowballWordSet(reader, new CharArraySet(matchVersion, INITIAL_CAPACITY, false));
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java Thu Jul 31 10:44:39 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();
+ new ArabicAnalyzer(TEST_VERSION_CURRENT);
}
/**
* Some simple tests showing some features of the analyzer, how some regular forms will conflate
*/
public void testBasicFeatures() throws Exception {
- ArabicAnalyzer a = new ArabicAnalyzer();
+ ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT);
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();
+ ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT);
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(), "English text.", new String[] {
+ assertAnalyzesTo(new ArabicAnalyzer(TEST_VERSION_CURRENT), "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(asSet("the", "and", "a"), false);
- ArabicAnalyzer a = new ArabicAnalyzer(set);
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, asSet("the", "and", "a"), false);
+ ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT, set);
assertAnalyzesTo(a, "The quick brown fox.", new String[] { "quick",
"brown", "fox" });
}
public void testWithStemExclusionSet() throws IOException {
- CharArraySet set = new CharArraySet(asSet("ساÙدÙات"), false);
- ArabicAnalyzer a = new ArabicAnalyzer(CharArraySet.EMPTY_SET, set);
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, asSet("ساÙدÙات"), false);
+ ArabicAnalyzer a = new ArabicAnalyzer(TEST_VERSION_CURRENT, 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(CharArraySet.EMPTY_SET, CharArraySet.EMPTY_SET);
+ a = new ArabicAnalyzer(TEST_VERSION_CURRENT, 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(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new ArabicAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java Thu Jul 31 10:44:39 2014
@@ -118,7 +118,7 @@ public class TestArabicStemFilter extend
}
public void testWithKeywordAttribute() throws IOException {
- CharArraySet set = new CharArraySet(1, true);
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("ساÙدÙات");
MockTokenizer tokenStream = whitespaceMockTokenizer("ساÙدÙات");
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java Thu Jul 31 10:44:39 2014
@@ -33,22 +33,22 @@ public class TestBulgarianAnalyzer exten
* This test fails with NPE when the stopwords file is missing in classpath
*/
public void testResourcesAvailable() {
- new BulgarianAnalyzer();
+ new BulgarianAnalyzer(TEST_VERSION_CURRENT);
}
public void testStopwords() throws IOException {
- Analyzer a = new BulgarianAnalyzer();
+ Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "Ðак Ñе казваÑ?", new String[] {"казваÑ"});
}
public void testCustomStopwords() throws IOException {
- Analyzer a = new BulgarianAnalyzer(CharArraySet.EMPTY_SET);
+ Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET);
assertAnalyzesTo(a, "Ðак Ñе казваÑ?",
new String[] {"как", "Ñе", "казваÑ"});
}
public void testReusableTokenStream() throws IOException {
- Analyzer a = new BulgarianAnalyzer();
+ Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "докÑменÑи", new String[] {"докÑменÑ"});
assertAnalyzesTo(a, "докÑменÑ", new String[] {"докÑменÑ"});
}
@@ -57,7 +57,7 @@ public class TestBulgarianAnalyzer exten
* Test some examples from the paper
*/
public void testBasicExamples() throws IOException {
- Analyzer a = new BulgarianAnalyzer();
+ Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "енеÑгийни кÑизи", new String[] {"енеÑгийн", "кÑиз"});
assertAnalyzesTo(a, "ÐÑомнаÑа енеÑгиÑ", new String[] {"аÑомн", "енеÑг"});
@@ -68,14 +68,14 @@ public class TestBulgarianAnalyzer exten
}
public void testWithStemExclusionSet() throws IOException {
- CharArraySet set = new CharArraySet(1, true);
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("ÑÑÑоеве");
- Analyzer a = new BulgarianAnalyzer(CharArraySet.EMPTY_SET, set);
+ Analyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT, 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(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new BulgarianAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java Thu Jul 31 10:44:39 2014
@@ -39,7 +39,7 @@ public class TestBulgarianStemmer extend
* common (and some rare) plural pattern is listed.
*/
public void testMasculineNouns() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer();
+ BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
// -и pattern
assertAnalyzesTo(a, "гÑад", new String[] {"гÑад"});
@@ -105,7 +105,7 @@ public class TestBulgarianStemmer extend
* Test showing how feminine noun forms conflate
*/
public void testFeminineNouns() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer();
+ BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "веÑÑ", new String[] {"веÑÑ"});
assertAnalyzesTo(a, "веÑÑÑа", new String[] {"веÑÑ"});
@@ -118,7 +118,7 @@ public class TestBulgarianStemmer extend
* plural pattern is listed
*/
public void testNeuterNouns() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer();
+ BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
// -а pattern
assertAnalyzesTo(a, "дÑÑво", new String[] {"дÑÑв"});
@@ -146,7 +146,7 @@ public class TestBulgarianStemmer extend
* Test showing how adjectival forms conflate
*/
public void testAdjectives() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer();
+ BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "кÑаÑив", new String[] {"кÑаÑив"});
assertAnalyzesTo(a, "кÑаÑивиÑ", new String[] {"кÑаÑив"});
assertAnalyzesTo(a, "кÑаÑивиÑÑ", new String[] {"кÑаÑив"});
@@ -162,7 +162,7 @@ public class TestBulgarianStemmer extend
* Test some exceptional rules, implemented as rewrites.
*/
public void testExceptions() throws IOException {
- BulgarianAnalyzer a = new BulgarianAnalyzer();
+ BulgarianAnalyzer a = new BulgarianAnalyzer(TEST_VERSION_CURRENT);
// Ñи -> к
assertAnalyzesTo(a, "ÑобÑÑвеник", new String[] {"ÑобÑÑвеник"});
@@ -217,7 +217,7 @@ public class TestBulgarianStemmer extend
}
public void testWithKeywordAttribute() throws IOException {
- CharArraySet set = new CharArraySet(1, true);
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("ÑÑÑоеве");
MockTokenizer tokenStream = new MockTokenizer(MockTokenizer.WHITESPACE, false);
tokenStream.setReader(new StringReader("ÑÑÑоевеÑе ÑÑÑоеве"));
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java Thu Jul 31 10:44:39 2014
@@ -130,7 +130,7 @@ public class TestBrazilianStemmer extend
}
public void testReusableTokenStream() throws Exception {
- Analyzer a = new BrazilianAnalyzer();
+ Analyzer a = new BrazilianAnalyzer(TEST_VERSION_CURRENT);
checkReuse(a, "boa", "boa");
checkReuse(a, "boainain", "boainain");
checkReuse(a, "boas", "boas");
@@ -138,15 +138,15 @@ public class TestBrazilianStemmer extend
}
public void testStemExclusionTable() throws Exception {
- BrazilianAnalyzer a = new BrazilianAnalyzer(
- CharArraySet.EMPTY_SET, new CharArraySet(asSet("quintessência"), false));
+ BrazilianAnalyzer a = new BrazilianAnalyzer(TEST_VERSION_CURRENT,
+ CharArraySet.EMPTY_SET, new CharArraySet(TEST_VERSION_CURRENT, asSet("quintessência"), false));
checkReuse(a, "quintessência", "quintessência"); // excluded words will be completely unchanged.
}
public void testWithKeywordAttribute() throws IOException {
- CharArraySet set = new CharArraySet(1, true);
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("BrasÃlia");
- Tokenizer tokenizer = new LowerCaseTokenizer();
+ Tokenizer tokenizer = new LowerCaseTokenizer(TEST_VERSION_CURRENT);
tokenizer.setReader(new StringReader("BrasÃlia Brasilia"));
BrazilianStemFilter filter = new BrazilianStemFilter(new SetKeywordMarkerFilter(tokenizer, set));
@@ -154,7 +154,7 @@ public class TestBrazilianStemmer extend
}
private void check(final String input, final String expected) throws Exception {
- checkOneTerm(new BrazilianAnalyzer(), input, expected);
+ checkOneTerm(new BrazilianAnalyzer(TEST_VERSION_CURRENT), input, expected);
}
private void checkReuse(Analyzer a, String input, String expected) throws Exception {
@@ -163,7 +163,7 @@ public class TestBrazilianStemmer extend
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new BrazilianAnalyzer(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new BrazilianAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
public void testEmptyTerm() throws IOException {
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java Thu Jul 31 10:44:39 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();
+ new CatalanAnalyzer(TEST_VERSION_CURRENT);
}
/** test stopwords and stemming */
public void testBasics() throws IOException {
- Analyzer a = new CatalanAnalyzer();
+ Analyzer a = new CatalanAnalyzer(TEST_VERSION_CURRENT);
// stemming
checkOneTerm(a, "llengües", "llengu");
checkOneTerm(a, "llengua", "llengu");
@@ -42,21 +42,22 @@ public class TestCatalanAnalyzer extends
/** test use of elisionfilter */
public void testContractions() throws IOException {
- Analyzer a = new CatalanAnalyzer();
+ Analyzer a = new CatalanAnalyzer(TEST_VERSION_CURRENT);
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(asSet("llengües"), false);
- Analyzer a = new CatalanAnalyzer(CatalanAnalyzer.getDefaultStopSet(), exclusionSet);
+ CharArraySet exclusionSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("llengües"), false);
+ Analyzer a = new CatalanAnalyzer(TEST_VERSION_CURRENT,
+ 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(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new CatalanAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java Thu Jul 31 10:44:39 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();
+ private Analyzer analyzer = new CJKAnalyzer(TEST_VERSION_CURRENT);
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) {
- Tokenizer tokenizer = new StandardTokenizer();
+ Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT);
return new TokenStreamComponents(tokenizer, new CJKBigramFilter(tokenizer));
}
@@ -255,7 +255,7 @@ public class TestCJKAnalyzer extends Bas
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
TokenFilter filter = new FakeStandardTokenizer(tokenizer);
- filter = new StopFilter(filter, CharArraySet.EMPTY_SET);
+ filter = new StopFilter(TEST_VERSION_CURRENT, 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(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new CJKAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
/** blast some random strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new CJKAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new CJKAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
}
public void testEmptyTerm() throws IOException {
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java Thu Jul 31 10:44:39 2014
@@ -29,7 +29,7 @@ public class TestCJKBigramFilter extends
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer t = new StandardTokenizer();
+ Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT);
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) {
- Tokenizer t = new StandardTokenizer();
+ Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT);
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) {
- Tokenizer t = new StandardTokenizer();
+ Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT);
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) {
- Tokenizer t = new StandardTokenizer();
+ Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT);
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) {
- Tokenizer t = new StandardTokenizer();
+ Tokenizer t = new StandardTokenizer(TEST_VERSION_CURRENT);
return new TokenStreamComponents(t, new CJKBigramFilter(t, CJKBigramFilter.HAN, true));
}
};
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java Thu Jul 31 10:44:39 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();
+ new SoraniAnalyzer(TEST_VERSION_CURRENT);
}
public void testStopwords() throws IOException {
- Analyzer a = new SoraniAnalyzer();
+ Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "ئÛÙ
Ù¾ÛاÙÛ", new String[] {"Ù¾ÛاÙ"});
}
public void testCustomStopwords() throws IOException {
- Analyzer a = new SoraniAnalyzer(CharArraySet.EMPTY_SET);
+ Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET);
assertAnalyzesTo(a, "ئÛÙ
Ù¾ÛاÙÛ",
new String[] {"ئÛÙ
", "Ù¾ÛاÙ"});
}
public void testReusableTokenStream() throws IOException {
- Analyzer a = new SoraniAnalyzer();
+ Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "Ù¾ÛاÙÛ", new String[] {"Ù¾ÛاÙ"});
assertAnalyzesTo(a, "Ù¾ÛاÙ", new String[] {"Ù¾ÛاÙ"});
}
public void testWithStemExclusionSet() throws IOException {
- CharArraySet set = new CharArraySet(1, true);
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
set.add("Ù¾ÛاÙÛ");
- Analyzer a = new SoraniAnalyzer(CharArraySet.EMPTY_SET, set);
+ Analyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT, 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(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new SoraniAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java Thu Jul 31 10:44:39 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();
+ SoraniAnalyzer a = new SoraniAnalyzer(TEST_VERSION_CURRENT);
public void testIndefiniteSingular() throws Exception {
checkOneTerm(a, "Ù¾ÛاÙÛÚ©", "Ù¾ÛاÙ"); // -ek
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java Thu Jul 31 10:44:39 2014
@@ -29,15 +29,15 @@ import org.apache.lucene.analysis.util.C
* Tests CommonGrams(Query)Filter
*/
public class CommonGramsFilterTest extends BaseTokenStreamTestCase {
- private static final CharArraySet commonWords = new CharArraySet(Arrays.asList(
+ private static final CharArraySet commonWords = new CharArraySet(TEST_VERSION_CURRENT, 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();
+ WhitespaceTokenizer wt = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
wt.setReader(new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
CharTermAttribute term = cgf.addAttribute(CharTermAttribute.class);
cgf.reset();
@@ -59,9 +59,9 @@ 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();
+ WhitespaceTokenizer wt = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
wt.setReader(new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
CommonGramsQueryFilter nsf = new CommonGramsQueryFilter(cgf);
CharTermAttribute term = wt.addAttribute(CharTermAttribute.class);
@@ -93,7 +93,7 @@ public class CommonGramsFilterTest exten
@Override
public TokenStreamComponents createComponents(String field) {
Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
- return new TokenStreamComponents(tokenizer, new CommonGramsQueryFilter(new CommonGramsFilter(
+ return new TokenStreamComponents(tokenizer, new CommonGramsQueryFilter(new CommonGramsFilter(TEST_VERSION_CURRENT,
tokenizer, commonWords)));
}
};
@@ -163,7 +163,8 @@ public class CommonGramsFilterTest exten
@Override
public TokenStreamComponents createComponents(String field) {
Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
- return new TokenStreamComponents(tokenizer, new CommonGramsFilter(tokenizer, commonWords));
+ return new TokenStreamComponents(tokenizer, new CommonGramsFilter(TEST_VERSION_CURRENT,
+ tokenizer, commonWords));
}
};
@@ -251,7 +252,7 @@ public class CommonGramsFilterTest exten
final String input = "How The s a brown s cow d like A B thing?";
MockTokenizer wt = new MockTokenizer(MockTokenizer.WHITESPACE, false);
wt.setReader(new StringReader(input));
- TokenFilter cgf = new CommonGramsFilter(wt, commonWords);
+ TokenFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, 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?"});
@@ -264,7 +265,7 @@ public class CommonGramsFilterTest exten
final String input = "dog the";
MockTokenizer wt = new MockTokenizer(MockTokenizer.WHITESPACE, false);
wt.setReader(new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "dog_the" });
}
@@ -276,7 +277,7 @@ public class CommonGramsFilterTest exten
final String input = "the dog";
MockTokenizer wt = new MockTokenizer(MockTokenizer.WHITESPACE, false);
wt.setReader(new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "the_dog" });
}
@@ -288,7 +289,7 @@ public class CommonGramsFilterTest exten
final String input = "the";
MockTokenizer wt = new MockTokenizer(MockTokenizer.WHITESPACE, false);
wt.setReader(new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "the" });
}
@@ -300,7 +301,7 @@ public class CommonGramsFilterTest exten
final String input = "monster";
MockTokenizer wt = new MockTokenizer(MockTokenizer.WHITESPACE, false);
wt.setReader(new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "monster" });
}
@@ -312,7 +313,7 @@ public class CommonGramsFilterTest exten
final String input = "the of";
MockTokenizer wt = new MockTokenizer(MockTokenizer.WHITESPACE, false);
wt.setReader(new StringReader(input));
- CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, wt, commonWords);
TokenFilter nsf = new CommonGramsQueryFilter(cgf);
assertTokenStreamContents(nsf, new String[] { "the_of" });
}
@@ -324,7 +325,7 @@ public class CommonGramsFilterTest exten
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer t = new MockTokenizer(MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(t, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, t, commonWords);
return new TokenStreamComponents(t, cgf);
}
};
@@ -336,7 +337,7 @@ public class CommonGramsFilterTest exten
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer t = new MockTokenizer(MockTokenizer.WHITESPACE, false);
- CommonGramsFilter cgf = new CommonGramsFilter(t, commonWords);
+ CommonGramsFilter cgf = new CommonGramsFilter(TEST_VERSION_CURRENT, t, commonWords);
return new TokenStreamComponents(t, new CommonGramsQueryFilter(cgf));
}
};
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java Thu Jul 31 10:44:39 2014
@@ -42,7 +42,7 @@ import org.xml.sax.InputSource;
public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
private static CharArraySet makeDictionary(String... dictionary) {
- return new CharArraySet(Arrays.asList(dictionary), true);
+ return new CharArraySet(TEST_VERSION_CURRENT, Arrays.asList(dictionary), true);
}
public void testHyphenationCompoundWordsDA() throws Exception {
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java Thu Jul 31 10:44:39 2014
@@ -31,7 +31,7 @@ import org.apache.lucene.util.BytesRef;
public class TestAnalyzers extends BaseTokenStreamTestCase {
public void testSimple() throws Exception {
- Analyzer a = new SimpleAnalyzer();
+ Analyzer a = new SimpleAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "foo bar FOO BAR",
new String[] { "foo", "bar", "foo", "bar" });
assertAnalyzesTo(a, "foo bar . FOO <> BAR",
@@ -51,7 +51,7 @@ public class TestAnalyzers extends BaseT
}
public void testNull() throws Exception {
- Analyzer a = new WhitespaceAnalyzer();
+ Analyzer a = new WhitespaceAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "foo bar FOO BAR",
new String[] { "foo", "bar", "FOO", "BAR" });
assertAnalyzesTo(a, "foo bar . FOO <> BAR",
@@ -71,7 +71,7 @@ public class TestAnalyzers extends BaseT
}
public void testStop() throws Exception {
- Analyzer a = new StopAnalyzer();
+ Analyzer a = new StopAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a, "foo bar FOO BAR",
new String[] { "foo", "bar", "foo", "bar" });
assertAnalyzesTo(a, "foo a bar such FOO THESE BAR",
@@ -94,12 +94,12 @@ public class TestAnalyzers extends BaseT
public void testPayloadCopy() throws IOException {
String s = "how now brown cow";
TokenStream ts;
- ts = new WhitespaceTokenizer();
+ ts = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
((Tokenizer)ts).setReader(new StringReader(s));
ts = new PayloadSetter(ts);
verifyPayload(ts);
- ts = new WhitespaceTokenizer();
+ ts = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
((Tokenizer)ts).setReader(new StringReader(s));
ts = new PayloadSetter(ts);
verifyPayload(ts);
@@ -124,8 +124,8 @@ public class TestAnalyzers extends BaseT
@Override
public TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new WhitespaceTokenizer();
- return new TokenStreamComponents(tokenizer, new LowerCaseFilter(tokenizer));
+ Tokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
+ return new TokenStreamComponents(tokenizer, new LowerCaseFilter(TEST_VERSION_CURRENT, tokenizer));
}
}
@@ -134,8 +134,8 @@ public class TestAnalyzers extends BaseT
@Override
public TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new WhitespaceTokenizer();
- return new TokenStreamComponents(tokenizer, new UpperCaseFilter(tokenizer));
+ Tokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
+ return new TokenStreamComponents(tokenizer, new UpperCaseFilter(TEST_VERSION_CURRENT, tokenizer));
}
}
@@ -190,9 +190,10 @@ 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();
+ WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
tokenizer.setReader(new StringReader("BogustermBogusterm\udc16"));
- LowerCaseFilter filter = new LowerCaseFilter(tokenizer);
+ LowerCaseFilter filter = new LowerCaseFilter(TEST_VERSION_CURRENT,
+ tokenizer);
assertTokenStreamContents(filter, new String[] {"bogustermbogusterm\udc16"});
filter.reset();
String highSurEndingUpper = "BogustermBoguster\ud801";
@@ -207,7 +208,7 @@ public class TestAnalyzers extends BaseT
public void testLowerCaseTokenizer() throws IOException {
StringReader reader = new StringReader("Tokenizer \ud801\udc1ctest");
- LowerCaseTokenizer tokenizer = new LowerCaseTokenizer();
+ LowerCaseTokenizer tokenizer = new LowerCaseTokenizer(TEST_VERSION_CURRENT);
tokenizer.setReader(reader);
assertTokenStreamContents(tokenizer, new String[] { "tokenizer",
"\ud801\udc44test" });
@@ -215,7 +216,7 @@ public class TestAnalyzers extends BaseT
public void testWhitespaceTokenizer() throws IOException {
StringReader reader = new StringReader("Tokenizer \ud801\udc1ctest");
- WhitespaceTokenizer tokenizer = new WhitespaceTokenizer();
+ WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT);
tokenizer.setReader(reader);
assertTokenStreamContents(tokenizer, new String[] { "Tokenizer",
"\ud801\udc1ctest" });
@@ -223,17 +224,17 @@ public class TestAnalyzers extends BaseT
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new WhitespaceAnalyzer(), 1000*RANDOM_MULTIPLIER);
- checkRandomData(random(), new SimpleAnalyzer(), 1000*RANDOM_MULTIPLIER);
- checkRandomData(random(), new StopAnalyzer(), 1000*RANDOM_MULTIPLIER);
+ 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);
}
/** blast some random large strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new WhitespaceAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
- checkRandomData(random, new SimpleAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
- checkRandomData(random, new StopAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
+ 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);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java Thu Jul 31 10:44:39 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(3, false);
+ final CharArraySet cas = new CharArraySet(TEST_VERSION_CURRENT, 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) {
Tokenizer t = new MockTokenizer(MockTokenFilter.ENGLISH_STOPSET, false, -65);
- TokenFilter f = new CommonGramsFilter(t, cas);
+ TokenFilter f = new CommonGramsFilter(TEST_VERSION_CURRENT, t, cas);
return new TokenStreamComponents(t, f);
}
@@ -263,7 +263,7 @@ public class TestBugInSomething extends
}
public void testCuriousWikipediaString() throws Exception {
- final CharArraySet protWords = new CharArraySet(new HashSet<>(
+ final CharArraySet protWords = new CharArraySet(TEST_VERSION_CURRENT, 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,
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java Thu Jul 31 10:44:39 2014
@@ -40,16 +40,16 @@ import java.util.Random;
public class TestClassicAnalyzer extends BaseTokenStreamTestCase {
- private Analyzer a = new ClassicAnalyzer();
+ private Analyzer a = new ClassicAnalyzer(TEST_VERSION_CURRENT);
public void testMaxTermLength() throws Exception {
- ClassicAnalyzer sa = new ClassicAnalyzer();
+ ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
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();
+ ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(sa, "ab cd toolong xy z", new String[]{"ab", "cd", "toolong", "xy", "z"});
sa.setMaxTokenLength(5);
@@ -113,7 +113,7 @@ public class TestClassicAnalyzer extends
public void testLucene1140() throws Exception {
try {
- ClassicAnalyzer analyzer = new ClassicAnalyzer();
+ ClassicAnalyzer analyzer = new ClassicAnalyzer(TEST_VERSION_CURRENT);
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");
@@ -123,7 +123,7 @@ public class TestClassicAnalyzer extends
public void testDomainNames() throws Exception {
// Current lucene should not show the bug
- ClassicAnalyzer a2 = new ClassicAnalyzer();
+ ClassicAnalyzer a2 = new ClassicAnalyzer(TEST_VERSION_CURRENT);
// domain names
assertAnalyzesTo(a2, "www.nutch.org", new String[]{"www.nutch.org"});
@@ -137,7 +137,7 @@ public class TestClassicAnalyzer extends
// 2.4 should not show the bug. But, alas, it's also obsolete,
// so we check latest released (Robert's gonna break this on 4.0 soon :) )
- a2 = new ClassicAnalyzer();
+ a2 = new ClassicAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(a2, "www.nutch.org.", new String[]{ "www.nutch.org" }, new String[] { "<HOST>" });
}
@@ -244,7 +244,7 @@ public class TestClassicAnalyzer extends
}
public void testJava14BWCompatibility() throws Exception {
- ClassicAnalyzer sa = new ClassicAnalyzer();
+ ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
assertAnalyzesTo(sa, "test\u02C6test", new String[] { "test", "test" });
}
@@ -253,7 +253,8 @@ 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()));
+ IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(
+ TEST_VERSION_CURRENT, new ClassicAnalyzer(TEST_VERSION_CURRENT)));
char[] chars = new char[IndexWriter.MAX_TERM_LENGTH];
Arrays.fill(chars, 'x');
@@ -299,7 +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();
+ ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
sa.setMaxTokenLength(100000);
writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, sa));
writer.addDocument(doc);
@@ -313,12 +314,12 @@ public class TestClassicAnalyzer extends
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new ClassicAnalyzer(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new ClassicAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
/** blast some random large strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new ClassicAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new ClassicAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java Thu Jul 31 10:44:39 2014
@@ -69,7 +69,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -89,7 +89,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -107,7 +107,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -126,7 +126,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -144,7 +144,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
@@ -163,7 +163,7 @@ public class TestDuelingAnalyzers extend
Analyzer right = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new LetterTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new LetterTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
return new TokenStreamComponents(tokenizer, tokenizer);
}
};
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java Thu Jul 31 10:44:39 2014
@@ -49,7 +49,8 @@ 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()));
+ IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(
+ TEST_VERSION_CURRENT, new SimpleAnalyzer(TEST_VERSION_CURRENT)));
Document doc = new Document();
doc.add(new StringField("partnum", "Q36", Field.Store.YES));
@@ -71,10 +72,10 @@ public class TestKeywordAnalyzer extends
/*
public void testPerFieldAnalyzer() throws Exception {
- PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SimpleAnalyzer());
+ PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SimpleAnalyzer(TEST_VERSION_CURRENT));
analyzer.addAnalyzer("partnum", new KeywordAnalyzer());
- QueryParser queryParser = new QueryParser(, "description", analyzer);
+ QueryParser queryParser = new QueryParser(TEST_VERSION_CURRENT, "description", analyzer);
Query query = queryParser.parse("partnum:Q36 AND SPACE");
ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java Thu Jul 31 10:44:39 2014
@@ -385,7 +385,7 @@ 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(num, random.nextBoolean());
+ CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, num, random.nextBoolean());
for (int i = 0; i < num; i++) {
// TODO: make nastier
set.add(TestUtil.randomSimpleString(random));
@@ -494,7 +494,7 @@ 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<>(num, random.nextBoolean());
+ CharArrayMap<String> map = new CharArrayMap<>(TEST_VERSION_CURRENT, num, random.nextBoolean());
for (int i = 0; i < num; i++) {
// TODO: make nastier
map.put(TestUtil.randomSimpleString(random), TestUtil.randomSimpleString(random));
@@ -619,7 +619,7 @@ 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(stream, newRandomArg(random, CharArraySet.class));
+ args[i] = new CommonGramsFilter(TEST_VERSION_CURRENT, stream, newRandomArg(random, CharArraySet.class));
} else {
args[i] = newRandomArg(random, paramType);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java Thu Jul 31 10:44:39 2014
@@ -41,7 +41,7 @@ public class TestStandardAnalyzer extend
sb.append(whitespace);
sb.append("testing 1234");
String input = sb.toString();
- StandardTokenizer tokenizer = new StandardTokenizer();
+ StandardTokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT);
tokenizer.setReader(new StringReader(input));
BaseTokenStreamTestCase.assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" });
}
@@ -50,7 +50,7 @@ public class TestStandardAnalyzer extend
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new StandardTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
return new TokenStreamComponents(tokenizer);
}
};
@@ -282,13 +282,13 @@ public class TestStandardAnalyzer extend
/** blast some random strings through the analyzer */
public void testRandomStrings() throws Exception {
- checkRandomData(random(), new StandardAnalyzer(), 1000*RANDOM_MULTIPLIER);
+ checkRandomData(random(), new StandardAnalyzer(TEST_VERSION_CURRENT), 1000*RANDOM_MULTIPLIER);
}
/** blast some random large strings through the analyzer */
public void testRandomHugeStrings() throws Exception {
Random random = random();
- checkRandomData(random, new StandardAnalyzer(), 100*RANDOM_MULTIPLIER, 8192);
+ checkRandomData(random, new StandardAnalyzer(TEST_VERSION_CURRENT), 100*RANDOM_MULTIPLIER, 8192);
}
// Adds random graph after:
@@ -298,7 +298,7 @@ public class TestStandardAnalyzer extend
new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = new StandardTokenizer(newAttributeFactory());
+ Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, newAttributeFactory());
TokenStream tokenStream = new MockGraphTokenFilter(random(), tokenizer);
return new TokenStreamComponents(tokenizer, tokenStream);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java?rev=1614852&r1=1614851&r2=1614852&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java Thu Jul 31 10:44:39 2014
@@ -31,7 +31,7 @@ import java.util.HashSet;
public class TestStopAnalyzer extends BaseTokenStreamTestCase {
- private StopAnalyzer stop = new StopAnalyzer();
+ private StopAnalyzer stop = new StopAnalyzer(TEST_VERSION_CURRENT);
private Set<Object> inValidTokens = new HashSet<>();
@Override
@@ -59,8 +59,8 @@ public class TestStopAnalyzer extends Ba
}
public void testStopList() throws IOException {
- CharArraySet stopWordsSet = new CharArraySet(asSet("good", "test", "analyzer"), false);
- StopAnalyzer newStop = new StopAnalyzer(stopWordsSet);
+ CharArraySet stopWordsSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("good", "test", "analyzer"), false);
+ StopAnalyzer newStop = new StopAnalyzer(TEST_VERSION_CURRENT, stopWordsSet);
try (TokenStream stream = newStop.tokenStream("test", "This is a good test of the english stop analyzer")) {
assertNotNull(stream);
CharTermAttribute termAtt = stream.getAttribute(CharTermAttribute.class);
@@ -75,8 +75,8 @@ public class TestStopAnalyzer extends Ba
}
public void testStopListPositions() throws IOException {
- CharArraySet stopWordsSet = new CharArraySet(asSet("good", "test", "analyzer"), false);
- StopAnalyzer newStop = new StopAnalyzer(stopWordsSet);
+ CharArraySet stopWordsSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("good", "test", "analyzer"), false);
+ StopAnalyzer newStop = new StopAnalyzer(TEST_VERSION_CURRENT, 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};
try (TokenStream stream = newStop.tokenStream("test", s)) {