Skip to content

Apache Lucene open-source search software

removing constructor with deprecated attribute 'onlyLongestMatch (#14356)

Renato Haeberliebc63504bd62
diff --git a/lucene/analysis/common/src/java/module-info.java b/lucene/analysis/common/src/java/module-info.java
index 7b36613b2e2..857663f8f0c 100644
--- a/lucene/analysis/common/src/java/module-info.java
+++ b/lucene/analysis/common/src/java/module-info.java
@@ -19,6 +19,7 @@
module org.apache.lucene.analysis.common {
requires java.xml;
requires org.apache.lucene.core;
+ requires java.logging;
exports org.apache.lucene.analysis.ar;
exports org.apache.lucene.analysis.bg;
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
index f3afe51c62f..c6acbb147f3 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
@@ -43,36 +43,6 @@ public class DictionaryCompoundWordTokenFilter extends CompoundWordTokenFilterBa
}
}
- /**
- * Creates a new {@link DictionaryCompoundWordTokenFilter}
- *
- * @param input the {@link org.apache.lucene.analysis.TokenStream} to process
- * @param dictionary the word dictionary to match against.
- * @param minWordSize only words longer than this get processed
- * @param minSubwordSize only subwords longer than this get to the output stream
- * @param maxSubwordSize only subwords shorter than this get to the output stream
- * @param onlyLongestMatch deprecated, use parameter onlyLongestMatchIgnoreSubwords instead
- * @param onlyLongestMatchIgnoreSubwords Subwords are igored, e.g. if a word contains 'schwein',
- * only the longer word 'schwein' will be extracted, the subword 'wein' will be ignored.
- * Supersede parameter onlyLongestMatch
- */
- @Deprecated
- public DictionaryCompoundWordTokenFilter(
- TokenStream input,
- CharArraySet dictionary,
- int minWordSize,
- int minSubwordSize,
- int maxSubwordSize,
- boolean onlyLongestMatch,
- boolean onlyLongestMatchIgnoreSubwords) {
- super(input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
- this.onlyLongestMatchNoSubwords = onlyLongestMatchIgnoreSubwords;
-
- if (dictionary == null) {
- throw new IllegalArgumentException("dictionary must not be null");
- }
- }
-
/**
* Creates a new {@link DictionaryCompoundWordTokenFilter}
*
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java
index b72a9fa9009..13071aec38d 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java
@@ -18,6 +18,7 @@ package org.apache.lucene.analysis.compound;
import java.io.IOException;
import java.util.Map;
+import java.util.logging.Logger;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.TokenFilterFactory;
import org.apache.lucene.analysis.TokenStream;
@@ -42,6 +43,9 @@ import org.apache.lucene.util.ResourceLoaderAware;
public class DictionaryCompoundWordTokenFilterFactory extends TokenFilterFactory
implements ResourceLoaderAware {
+ private static final Logger LOG =
+ Logger.getLogger(DictionaryCompoundWordTokenFilterFactory.class.getName());
+
/** SPI name */
public static final String NAME = "dictionaryCompoundWord";
@@ -50,7 +54,6 @@ public class DictionaryCompoundWordTokenFilterFactory extends TokenFilterFactory
private final int minWordSize;
private final int minSubwordSize;
private final int maxSubwordSize;
- private final boolean onlyLongestMatch;
private final boolean onlyLongestMatchIgnoreSubwords;
/** Creates a new DictionaryCompoundWordTokenFilterFactory */
@@ -62,7 +65,12 @@ public class DictionaryCompoundWordTokenFilterFactory extends TokenFilterFactory
getInt(args, "minSubwordSize", CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE);
maxSubwordSize =
getInt(args, "maxSubwordSize", CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE);
- onlyLongestMatch = getBoolean(args, "onlyLongestMatch", true);
+
+ boolean onlyLongestMatch = getBoolean(args, "onlyLongestMatch", true);
+ if (onlyLongestMatch)
+ LOG.warning(
+ "onlyLongestMatch has been removed and replaced by onlyLongestMatchIgnoreSubwords");
+
onlyLongestMatchIgnoreSubwords = getBoolean(args, "onlyLongestMatchIgnoreSubwords", true);
if (!args.isEmpty()) {
@@ -92,7 +100,6 @@ public class DictionaryCompoundWordTokenFilterFactory extends TokenFilterFactory
minWordSize,
minSubwordSize,
maxSubwordSize,
- onlyLongestMatch,
onlyLongestMatchIgnoreSubwords);
}
}
diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java
index fbf811b29b0..d25d77d350c 100644
--- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java
+++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java
@@ -251,14 +251,11 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE,
- true,
- false);
+ true);
assertTokenStreamContents(
tf,
- new String[] {
- "Basfiolsfodralmakaregesäll", "Bas", "fiolsfodral", "fodral", "makare", "gesäll"
- },
+ new String[] {"Basfiolsfodralmakaregesäll", "Bas", "fiolsfodral", "makare", "gesäll"},
new int[] {0, 0, 0, 0, 0, 0},
new int[] {26, 26, 26, 26, 26, 26},
new int[] {1, 0, 0, 0, 0, 0});
@@ -276,7 +273,6 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE,
- false,
false);
assertTokenStreamContents(
@@ -299,7 +295,6 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE,
- false,
false);
// since "d" is shorter than the minimum subword size, it should not be added to the token
@@ -326,7 +321,6 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE,
- false,
false);
CharTermAttribute termAtt = tf.getAttribute(CharTermAttribute.class);
@@ -355,7 +349,6 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE,
- false,
false);
MockRetainAttribute retAtt = stream.addAttribute(MockRetainAttribute.class);
stream.reset();
@@ -695,7 +688,7 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
String searchTerm = "schweinefleisch";
DictionaryCompoundWordTokenFilter tf =
- getDictionaryCompoundWordTokenFilter(tokenizer, searchTerm, dict, true);
+ getDictionaryCompoundWordTokenFilter(tokenizer, searchTerm, dict);
assertTokenStreamContents(tf, new String[] {searchTerm, "schwein", "fleisch"});
}
@@ -707,13 +700,13 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
String searchTerm = "nahkampfwaffen";
DictionaryCompoundWordTokenFilter tf =
- getDictionaryCompoundWordTokenFilter(tokenizer, searchTerm, dict, true);
+ getDictionaryCompoundWordTokenFilter(tokenizer, searchTerm, dict);
assertTokenStreamContents(tf, new String[] {searchTerm, "kampf", "waffe"});
}
private DictionaryCompoundWordTokenFilter getDictionaryCompoundWordTokenFilter(
- Tokenizer tokenizer, String searchTerm, CharArraySet dict, boolean onlyLongestMatch) {
+ Tokenizer tokenizer, String searchTerm, CharArraySet dict) {
tokenizer.setReader(new StringReader(searchTerm));
return new DictionaryCompoundWordTokenFilter(
tokenizer,
@@ -721,7 +714,6 @@ public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE,
- onlyLongestMatch,
true);
}
}