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/pt/PortugueseMinimalStemFilter.java

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/pt/PortugueseMinimalStemFilter.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/pt/PortugueseMinimalStemFilter.java
new file mode 100644
index 0000000..8d4f32b
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/pt/PortugueseMinimalStemFilter.java
@@ -0,0 +1,58 @@
+package org.apache.lucene.analysis.pt;
+
+/**
+ * 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.KeywordMarkerFilter;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
+
+/**
+ * A {@link TokenFilter} that applies {@link PortugueseMinimalStemmer} to stem 
+ * Portuguese words.
+ * <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>
+ */
+public final class PortugueseMinimalStemFilter extends TokenFilter {
+  private final PortugueseMinimalStemmer stemmer = new PortugueseMinimalStemmer();
+  private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+  private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
+
+  public PortugueseMinimalStemFilter(TokenStream input) {
+    super(input);
+  }
+  
+  @Override
+  public boolean incrementToken() throws IOException {
+    if (input.incrementToken()) {
+      if (!keywordAttr.isKeyword()) {
+        final int newlen = stemmer.stem(termAtt.buffer(), termAtt.length());
+        termAtt.setLength(newlen);
+      }
+      return true;
+    } else {
+      return false;
+    }
+  }
+}