LUCENE-2399: Add support for ICU's Normalizer2

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@935186 13f79535-47bb-0310-9956-ffa450edef68

lucene/contrib/CHANGES.txt

@@ -119,6 +119,11 @@ New features
    the ability to override any stemmer with a custom dictionary map.
    (Robert Muir, Uwe Schindler, Simon Willnauer)
 
+ * LUCENE-2399: Add ICUNormalizer2Filter, which normalizes tokens with ICU's
+   Normalizer2. This allows for efficient combinations of normalization and custom 
+   mappings in addition to standard normalization, and normalization combined
+   with unicode case folding.  (Robert Muir)
+
 Build
 
  * LUCENE-2124: Moved the JDK-based collation support from contrib/collation 
@@ -135,6 +140,8 @@ Build
    core were changed without ant clean. This fix also optimizes the
    dependency management between contribs by a new ANT macro.
    (Uwe Schindler, Shai Erera)
+
+ * LUCENE-2399: Upgrade contrib/icu's ICU jar file to ICU 4.4.  (Robert Muir)
    
 Optimizations
 

lucene/contrib/icu/lib/icu4j-4_4.jar

@@ -0,0 +1,2 @@
+AnyObjectId[bd1ef881718dca394dd563279eb015e154b01f90] was removed in git history.
+Apache SVN contains full history.

lucene/contrib/icu/lib/icu4j-collation-4.0.jar

@@ -1,2 +0,0 @@
-AnyObjectId[1159f04caacfda235b66d73dc65198fa40153812] was removed in git history.
-Apache SVN contains full history.

lucene/contrib/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2Filter.java

@@ -0,0 +1,92 @@
+package org.apache.lucene.analysis.icu;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+
+import com.ibm.icu.text.Normalizer;
+import com.ibm.icu.text.Normalizer2;
+
+/**
+ * Normalize token text with ICU's {@link com.ibm.icu.text.Normalizer2}
+ * <p>
+ * With this filter, you can normalize text in the following ways:
+ * <ul>
+ *  <li> NFKC Normalization, Case Folding, and removing Ignorables (the default)
+ *  <li> Using a standard Normalization mode (NFC, NFD, NFKC, NFKD)
+ *  <li> Based on rules from a custom normalization mapping.
+ * </ul>
+ * <p>
+ * If you use the defaults, this filter is a simple way to standardize Unicode text
+ * in a language-independent way for search:
+ * <ul>
+ *  <li> The case folding that it does can be seen as a replacement for
+ *  LowerCaseFilter: For example, it handles cases such as the Greek sigma, so that
+ * "Μάϊος" and "ΜΆΪΟΣ" will match correctly.
+ *  <li> The normalization will standardizes different forms of the same 
+ *  character in Unicode. For example, CJK full-width numbers will be standardized
+ *  to their ASCII forms.
+ *  <li> Ignorables such as Zero-Width Joiner and Variation Selectors are removed.
+ *  These are typically modifier characters that affect display.
+ * </ul>
+ * 
+ * @see com.ibm.icu.text.Normalizer2
+ * @see com.ibm.icu.text.FilteredNormalizer2
+ */
+public class ICUNormalizer2Filter extends TokenFilter {
+  private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+  private final Normalizer2 normalizer;
+  private final StringBuilder buffer = new StringBuilder();
+
+  /**
+   * Create a new Normalizer2Filter that combines NFKC normalization, Case
+   * Folding, and removes Default Ignorables (NFKC_Casefold)
+   */
+  public ICUNormalizer2Filter(TokenStream input) {
+    this(input, Normalizer2.getInstance(null, "nfkc_cf", Normalizer2.Mode.COMPOSE));
+  }
+
+  /**
+   * Create a new Normalizer2Filter with the specified Normalizer2
+   * @param input stream
+   * @param normalizer normalizer to use
+   */
+  public ICUNormalizer2Filter(TokenStream input, Normalizer2 normalizer) {
+    super(input);
+    this.normalizer = normalizer;
+  }
+
+  @Override
+  public final boolean incrementToken() throws IOException {
+    if (input.incrementToken()) {
+      if (normalizer.quickCheck(termAtt) != Normalizer.YES) {
+        buffer.setLength(0);
+        buffer.append(termAtt.buffer(), 0, termAtt.length());
+        termAtt.setEmpty();
+        normalizer.normalize(buffer, termAtt);
+      }
+      return true;
+    } else {
+      return false;
+    }
+  }
+}

lucene/contrib/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2Filter.java

@@ -0,0 +1,78 @@
+package org.apache.lucene.analysis.icu;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+import java.io.Reader;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.WhitespaceTokenizer;
+
+import com.ibm.icu.text.Normalizer2;
+
+/**
+ * Tests the ICUNormalizer2Filter
+ */
+public class TestICUNormalizer2Filter extends BaseTokenStreamTestCase {
+
+  public void testDefaults() throws IOException {
+    Analyzer a = new Analyzer() {
+      @Override
+      public TokenStream tokenStream(String fieldName, Reader reader) {
+        return new ICUNormalizer2Filter(
+            new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader));
+      }
+    };
+
+    // case folding
+    assertAnalyzesTo(a, "This is a test", new String[] { "this", "is", "a", "test" });
+
+    // case folding
+    assertAnalyzesTo(a, "Ruß", new String[] { "russ" });
+    
+    // case folding
+    assertAnalyzesTo(a, "ΜΆΪΟΣ", new String[] { "μάϊοσ" });
+    assertAnalyzesTo(a, "Μάϊος", new String[] { "μάϊοσ" });
+
+    // supplementary case folding
+    assertAnalyzesTo(a, "𐐖", new String[] { "𐐾" });
+    
+    // normalization
+    assertAnalyzesTo(a, "ﴳﴺﰧ", new String[] { "طمطمطم" });
+
+    // removal of default ignorables
+    assertAnalyzesTo(a, "क्‍ष", new String[] { "क्ष" });
+  }
+  
+  public void testAlternate() throws IOException {
+    Analyzer a = new Analyzer() {
+      @Override
+      public TokenStream tokenStream(String fieldName, Reader reader) {
+        return new ICUNormalizer2Filter(
+            new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader),
+            /* specify nfc with decompose to get nfd */
+            Normalizer2.getInstance(null, "nfc", Normalizer2.Mode.DECOMPOSE));
+      }
+    };
+    
+    // decompose EAcute into E + combining Acute
+    assertAnalyzesTo(a, "\u00E9", new String[] { "\u0065\u0301" });
+  }
+}