pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / src / java / org / apache / lucene / analysis / standard / StandardFilter.java

diff --git a/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/analysis/standard/StandardFilter.java b/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/analysis/standard/StandardFilter.java
new file mode 100644 (file)
index 0000000..7eeb87c
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/analysis/standard/StandardFilter.java
@@ -0,0 +1,87 @@
+package org.apache.lucene.analysis.standard;
+
+/**
+ * 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.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
+import org.apache.lucene.util.Version;
+
+/**
+ * Normalizes tokens extracted with {@link StandardTokenizer}.
+ */
+public class StandardFilter extends TokenFilter {
+  private final Version matchVersion;
+  
+  /** @deprecated Use {@link #StandardFilter(Version, TokenStream)} instead. */
+  @Deprecated
+  public StandardFilter(TokenStream in) {
+    this(Version.LUCENE_30, in);
+  }
+  
+  public StandardFilter(Version matchVersion, TokenStream in) {
+    super(in);
+    this.matchVersion = matchVersion;
+  }
+  
+  private static final String APOSTROPHE_TYPE = ClassicTokenizer.TOKEN_TYPES[ClassicTokenizer.APOSTROPHE];
+  private static final String ACRONYM_TYPE = ClassicTokenizer.TOKEN_TYPES[ClassicTokenizer.ACRONYM];
+
+  // this filters uses attribute type
+  private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
+  private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+  
+  @Override
+  public final boolean incrementToken() throws IOException {
+    if (matchVersion.onOrAfter(Version.LUCENE_31))
+      return input.incrementToken(); // TODO: add some niceties for the new grammar
+    else
+      return incrementTokenClassic();
+  }
+  
+  public final boolean incrementTokenClassic() throws IOException {
+    if (!input.incrementToken()) {
+      return false;
+    }
+
+    final char[] buffer = termAtt.buffer();
+    final int bufferLength = termAtt.length();
+    final String type = typeAtt.type();
+
+    if (type == APOSTROPHE_TYPE &&      // remove 's
+        bufferLength >= 2 &&
+        buffer[bufferLength-2] == '\'' &&
+        (buffer[bufferLength-1] == 's' || buffer[bufferLength-1] == 'S')) {
+      // Strip last 2 characters off
+      termAtt.setLength(bufferLength - 2);
+    } else if (type == ACRONYM_TYPE) {      // remove dots
+      int upto = 0;
+      for(int i=0;i<bufferLength;i++) {
+        char c = buffer[i];
+        if (c != '.')
+          buffer[upto++] = c;
+      }
+      termAtt.setLength(upto);
+    }
+
+    return true;
+  }
+}