X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java?ds=sidebyside

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java
new file mode 100644
index 0000000..f89b07a
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/in/IndicTokenizer.java
@@ -0,0 +1,50 @@
+package org.apache.lucene.analysis.in;
+
+/**
+ * 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.Reader;
+
+import org.apache.lucene.analysis.CharTokenizer;
+import org.apache.lucene.util.AttributeSource;
+import org.apache.lucene.util.Version;
+
+/**
+ * Simple Tokenizer for text in Indian Languages.
+ */
+public final class IndicTokenizer extends CharTokenizer {
+ 
+  public IndicTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
+    super(matchVersion, factory, input);
+  }
+
+  public IndicTokenizer(Version matchVersion, AttributeSource source, Reader input) {
+    super(matchVersion, source, input);
+  }
+
+  public IndicTokenizer(Version matchVersion, Reader input) {
+    super(matchVersion, input);
+  }
+
+  @Override
+  protected boolean isTokenChar(int c) {
+    return Character.isLetter(c)
+    || Character.getType(c) == Character.NON_SPACING_MARK
+    || Character.getType(c) == Character.FORMAT
+    || Character.getType(c) == Character.COMBINING_SPACING_MARK;
+  }
+}