pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / highlighter / src / java / org / apache / lucene / search / highlight / TokenStreamFromTermPositionVector.java

diff --git a/lucene-java-3.5.0/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenStreamFromTermPositionVector.java b/lucene-java-3.5.0/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenStreamFromTermPositionVector.java
new file mode 100644 (file)
index 0000000..64f46dd
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenStreamFromTermPositionVector.java
@@ -0,0 +1,111 @@
+package org.apache.lucene.search.highlight;
+
+/**
+ * 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.ArrayList;
+import java.util.Comparator;
+import java.util.Iterator;
+import java.util.List;
+
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.index.TermPositionVector;
+import org.apache.lucene.index.TermVectorOffsetInfo;
+import org.apache.lucene.util.CollectionUtil;
+
+public final class TokenStreamFromTermPositionVector extends TokenStream {
+
+  private final List<Token> positionedTokens = new ArrayList<Token>();
+
+  private Iterator<Token> tokensAtCurrentPosition;
+
+  private CharTermAttribute termAttribute;
+
+  private PositionIncrementAttribute positionIncrementAttribute;
+
+  private OffsetAttribute offsetAttribute;
+
+  /**
+   * Constructor.
+   * 
+   * @param termPositionVector TermPositionVector that contains the data for
+   *        creating the TokenStream. Must have positions and offsets.
+   */
+  public TokenStreamFromTermPositionVector(
+      final TermPositionVector termPositionVector) {
+    termAttribute = addAttribute(CharTermAttribute.class);
+    positionIncrementAttribute = addAttribute(PositionIncrementAttribute.class);
+    offsetAttribute = addAttribute(OffsetAttribute.class);
+    final String[] terms = termPositionVector.getTerms();
+    for (int i = 0; i < terms.length; i++) {
+      final TermVectorOffsetInfo[] offsets = termPositionVector.getOffsets(i);
+      final int[] termPositions = termPositionVector.getTermPositions(i);
+      for (int j = 0; j < termPositions.length; j++) {
+        Token token;
+        if (offsets != null) {
+          token = new Token(terms[i].toCharArray(), 0, terms[i].length(),
+              offsets[j].getStartOffset(), offsets[j].getEndOffset());
+        } else {
+          token = new Token();
+          token.setEmpty().append(terms[i]);
+        }
+        // Yes - this is the position, not the increment! This is for
+        // sorting. This value
+        // will be corrected before use.
+        token.setPositionIncrement(termPositions[j]);
+        this.positionedTokens.add(token);
+      }
+    }
+    CollectionUtil.mergeSort(this.positionedTokens, tokenComparator);
+    int lastPosition = -1;
+    for (final Token token : this.positionedTokens) {
+      int thisPosition = token.getPositionIncrement();
+      token.setPositionIncrement(thisPosition - lastPosition);
+      lastPosition = thisPosition;
+    }
+    this.tokensAtCurrentPosition = this.positionedTokens.iterator();
+  }
+
+  private static final Comparator<Token> tokenComparator = new Comparator<Token>() {
+    public int compare(final Token o1, final Token o2) {
+      return o1.getPositionIncrement() - o2.getPositionIncrement();
+    }
+  };
+  
+  @Override
+  public boolean incrementToken() throws IOException {
+    if (this.tokensAtCurrentPosition.hasNext()) {
+      final Token next = this.tokensAtCurrentPosition.next();
+      clearAttributes();
+      termAttribute.setEmpty().append(next);
+      positionIncrementAttribute.setPositionIncrement(next
+          .getPositionIncrement());
+      offsetAttribute.setOffset(next.startOffset(), next.endOffset());
+      return true;
+    }
+    return false;
+  }
+
+  @Override
+  public void reset() throws IOException {
+    this.tokensAtCurrentPosition = this.positionedTokens.iterator();
+  }
+}