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/ar/ArabicLetterTokenizer.java?ds=inline

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicLetterTokenizer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicLetterTokenizer.java
new file mode 100644
index 0000000..c2f7c9e
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/ar/ArabicLetterTokenizer.java
@@ -0,0 +1,133 @@
+package org.apache.lucene.analysis.ar;
+/**
+ * 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.analysis.LetterTokenizer;
+import org.apache.lucene.analysis.standard.StandardTokenizer; // javadoc @link
+import org.apache.lucene.util.AttributeSource;
+import org.apache.lucene.util.Version;
+
+/**
+ * Tokenizer that breaks text into runs of letters and diacritics.
+ * <p>
+ * The problem with the standard Letter tokenizer is that it fails on diacritics.
+ * Handling similar to this is necessary for Indic Scripts, Hebrew, Thaana, etc.
+ * </p>
+ * <p>
+ * <a name="version"/>
+ * You must specify the required {@link Version} compatibility when creating
+ * {@link ArabicLetterTokenizer}:
+ * <ul>
+ * <li>As of 3.1, {@link CharTokenizer} uses an int based API to normalize and
+ * detect token characters. See {@link #isTokenChar(int)} and
+ * {@link #normalize(int)} for details.</li>
+ * </ul>
+ * @deprecated (3.1) Use {@link StandardTokenizer} instead.
+ */
+@Deprecated
+public class ArabicLetterTokenizer extends LetterTokenizer {
+
+  
+  /**
+   * Construct a new ArabicLetterTokenizer.
+   * @param matchVersion Lucene version
+   * to match See {@link <a href="#version">above</a>}
+   * 
+   * @param in
+   *          the input to split up into tokens
+   */
+  public ArabicLetterTokenizer(Version matchVersion, Reader in) {
+    super(matchVersion, in);
+  }
+
+  /**
+   * Construct a new ArabicLetterTokenizer using a given {@link AttributeSource}.
+   * 
+   * @param matchVersion
+   *          Lucene version to match See {@link <a href="#version">above</a>}
+   * @param source
+   *          the attribute source to use for this Tokenizer
+   * @param in
+   *          the input to split up into tokens
+   */
+  public ArabicLetterTokenizer(Version matchVersion, AttributeSource source, Reader in) {
+    super(matchVersion, source, in);
+  }
+
+  /**
+   * Construct a new ArabicLetterTokenizer using a given
+   * {@link org.apache.lucene.util.AttributeSource.AttributeFactory}. * @param
+   * matchVersion Lucene version to match See
+   * {@link <a href="#version">above</a>}
+   * 
+   * @param factory
+   *          the attribute factory to use for this Tokenizer
+   * @param in
+   *          the input to split up into tokens
+   */
+  public ArabicLetterTokenizer(Version matchVersion, AttributeFactory factory, Reader in) {
+    super(matchVersion, factory, in);
+  }
+  
+  /**
+   * Construct a new ArabicLetterTokenizer.
+   * 
+   * @deprecated use {@link #ArabicLetterTokenizer(Version, Reader)} instead. This will
+   *             be removed in Lucene 4.0.
+   */
+  @Deprecated
+  public ArabicLetterTokenizer(Reader in) {
+    super(in);
+  }
+
+  /**
+   * Construct a new ArabicLetterTokenizer using a given {@link AttributeSource}.
+   * 
+   * @deprecated use {@link #ArabicLetterTokenizer(Version, AttributeSource, Reader)}
+   *             instead. This will be removed in Lucene 4.0.
+   */
+  @Deprecated
+  public ArabicLetterTokenizer(AttributeSource source, Reader in) {
+    super(source, in);
+  }
+
+  /**
+   * Construct a new ArabicLetterTokenizer using a given
+   * {@link org.apache.lucene.util.AttributeSource.AttributeFactory}.
+   * 
+   * @deprecated use {@link #ArabicLetterTokenizer(Version, AttributeSource.AttributeFactory, Reader)}
+   *             instead. This will be removed in Lucene 4.0.
+   */
+  @Deprecated
+  public ArabicLetterTokenizer(AttributeFactory factory, Reader in) {
+    super(factory, in);
+  }
+  
+  
+  /** 
+   * Allows for Letter category or NonspacingMark category
+   * @see org.apache.lucene.analysis.LetterTokenizer#isTokenChar(int)
+   */
+  @Override
+  protected boolean isTokenChar(int c) {
+    return super.isTokenChar(c) || Character.getType(c) == Character.NON_SPACING_MARK;
+  }
+
+}