pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / analyzers / common / src / java / org / apache / lucene / analysis / hi / HindiNormalizationFilter.java

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/hi/HindiNormalizationFilter.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/hi/HindiNormalizationFilter.java
new file mode 100644 (file)
index 0000000..1a751a9
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/hi/HindiNormalizationFilter.java
@@ -0,0 +1,59 @@
+package org.apache.lucene.analysis.hi;
+
+/**
+ * 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.KeywordMarkerFilter;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+
+/**
+ * A {@link TokenFilter} that applies {@link HindiNormalizer} to normalize the
+ * orthography.
+ * <p>
+ * In some cases the normalization may cause unrelated terms to conflate, so
+ * to prevent terms from being normalized use an instance of
+ * {@link KeywordMarkerFilter} or a custom {@link TokenFilter} that sets
+ * the {@link KeywordAttribute} before this {@link TokenStream}.
+ * </p>
+ * @see HindiNormalizer
+ */
+public final class HindiNormalizationFilter extends TokenFilter {
+
+  private final HindiNormalizer normalizer = new HindiNormalizer();
+  private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+  private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
+  
+  public HindiNormalizationFilter(TokenStream input) {
+    super(input);
+  }
+
+  @Override
+  public boolean incrementToken() throws IOException {
+    if (input.incrementToken()) {
+      if (!keywordAtt.isKeyword())
+        termAtt.setLength(normalizer.normalize(termAtt.buffer(), 
+            termAtt.length()));
+      return true;
+    } 
+    return false;
+  }
+}