pylucene 3.5.0-3

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

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/de/GermanStemFilter.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/de/GermanStemFilter.java
new file mode 100644 (file)
index 0000000..8348119
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/de/GermanStemFilter.java
@@ -0,0 +1,114 @@
+package org.apache.lucene.analysis.de;
+
+/**
+ * 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.util.Set;
+
+import org.apache.lucene.analysis.KeywordMarkerFilter;// for javadoc
+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 stems German words. 
+ * <p>
+ * It supports a table of words that should
+ * not be stemmed at all. The stemmer used can be changed at runtime after the
+ * filter object is created (as long as it is a {@link GermanStemmer}).
+ * </p>
+ * <p>
+ * To prevent terms from being stemmed use an instance of
+ * {@link KeywordMarkerFilter} or a custom {@link TokenFilter} that sets
+ * the {@link KeywordAttribute} before this {@link TokenStream}.
+ * </p>
+ * @see KeywordMarkerFilter
+ */
+public final class GermanStemFilter extends TokenFilter
+{
+    /**
+     * The actual token in the input stream.
+     */
+    private GermanStemmer stemmer = new GermanStemmer();
+    private Set<?> exclusionSet = null;
+
+    private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+    private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
+
+    /**
+     * Creates a {@link GermanStemFilter} instance
+     * @param in the source {@link TokenStream} 
+     */
+    public GermanStemFilter( TokenStream in )
+    {
+      super(in);
+    }
+
+    /**
+     * Builds a GermanStemFilter that uses an exclusion table.
+     * @deprecated use {@link KeywordAttribute} with {@link KeywordMarkerFilter} instead.
+     */
+    @Deprecated
+    public GermanStemFilter( TokenStream in, Set<?> exclusionSet )
+    {
+      this( in );
+      this.exclusionSet = exclusionSet;
+    }
+
+    /**
+     * @return  Returns true for next token in the stream, or false at EOS
+     */
+    @Override
+    public boolean incrementToken() throws IOException {
+      if (input.incrementToken()) {
+        String term = termAtt.toString();
+        // Check the exclusion table.
+        if (!keywordAttr.isKeyword() && (exclusionSet == null || !exclusionSet.contains(term))) {
+          String s = stemmer.stem(term);
+          // If not stemmed, don't waste the time adjusting the token.
+          if ((s != null) && !s.equals(term))
+            termAtt.setEmpty().append(s);
+        }
+        return true;
+      } else {
+        return false;
+      }
+    }
+
+    /**
+     * Set a alternative/custom {@link GermanStemmer} for this filter.
+     */
+    public void setStemmer( GermanStemmer stemmer )
+    {
+      if ( stemmer != null ) {
+        this.stemmer = stemmer;
+      }
+    }
+
+
+    /**
+     * Set an alternative exclusion list for this filter.
+     * @deprecated use {@link KeywordAttribute} with {@link KeywordMarkerFilter} instead.
+     */
+    @Deprecated
+    public void setExclusionSet( Set<?> exclusionSet )
+    {
+      this.exclusionSet = exclusionSet;
+    }
+}