highlighter.java

lucene2.2.0版本

					newText.append(encoder.encodeText(text.substring(lastEndOffset, startOffset)));
				newText.append(markedUpText);
				lastEndOffset=Math.max(lastEndOffset,endOffset);
			}

			//Test what remains of the original text beyond the point where we stopped analyzing 
			if (
//					if there is text beyond the last token considered..
					(lastEndOffset < text.length()) 
					&&
//					and that text is not too large...
					(text.length()<maxDocBytesToAnalyze)
				)				
			{
				//append it to the last fragment
				newText.append(encoder.encodeText(text.substring(lastEndOffset)));
			}

			currentFrag.textEndPos = newText.length();

			//sort the most relevant sections of the text
			for (Iterator i = docFrags.iterator(); i.hasNext();)
			{
				currentFrag = (TextFragment) i.next();

				//If you are running with a version of Lucene before 11th Sept 03
				// you do not have PriorityQueue.insert() - so uncomment the code below
				/*
									if (currentFrag.getScore() >= minScore)
									{
										fragQueue.put(currentFrag);
										if (fragQueue.size() > maxNumFragments)
										{ // if hit queue overfull
											fragQueue.pop(); // remove lowest in hit queue
											minScore = ((TextFragment) fragQueue.top()).getScore(); // reset minScore
										}


									}
				*/
				//The above code caused a problem as a result of Christoph Goller's 11th Sept 03
				//fix to PriorityQueue. The correct method to use here is the new "insert" method
				// USE ABOVE CODE IF THIS DOES NOT COMPILE!
				fragQueue.insert(currentFrag);
			}

			//return the most relevant fragments
			TextFragment frag[] = new TextFragment[fragQueue.size()];
			for (int i = frag.length - 1; i >= 0; i--)
			{
				frag[i] = (TextFragment) fragQueue.pop();
			}

			//merge any contiguous fragments to improve readability
			if(mergeContiguousFragments)
			{
				mergeContiguousFragments(frag);
				ArrayList fragTexts = new ArrayList();
				for (int i = 0; i < frag.length; i++)
				{
					if ((frag[i] != null) && (frag[i].getScore() > 0))
					{
						fragTexts.add(frag[i]);
					}
				}
				frag= (TextFragment[]) fragTexts.toArray(new TextFragment[0]);
			}

			return frag;

		}
		finally
		{
			if (tokenStream != null)
			{
				try
				{
					tokenStream.close();
				}
				catch (Exception e)
				{
				}
			}
		}
	}


	/** Improves readability of a score-sorted list of TextFragments by merging any fragments
	 * that were contiguous in the original text into one larger fragment with the correct order.
	 * This will leave a "null" in the array entry for the lesser scored fragment. 
	 * 
	 * @param frag An array of document fragments in descending score
	 */
	private void mergeContiguousFragments(TextFragment[] frag)
	{
		boolean mergingStillBeingDone;
		if (frag.length > 1)
			do
			{
				mergingStillBeingDone = false; //initialise loop control flag
				//for each fragment, scan other frags looking for contiguous blocks
				for (int i = 0; i < frag.length; i++)
				{
					if (frag[i] == null)
					{
						continue;
					}
					//merge any contiguous blocks 
					for (int x = 0; x < frag.length; x++)
					{
						if (frag[x] == null)
						{
							continue;
						}
						if (frag[i] == null)
						{
							break;
						}
						TextFragment frag1 = null;
						TextFragment frag2 = null;
						int frag1Num = 0;
						int frag2Num = 0;
						int bestScoringFragNum;
						int worstScoringFragNum;
						//if blocks are contiguous....
						if (frag[i].follows(frag[x]))
						{
							frag1 = frag[x];
							frag1Num = x;
							frag2 = frag[i];
							frag2Num = i;
						}
						else
							if (frag[x].follows(frag[i]))
							{
								frag1 = frag[i];
								frag1Num = i;
								frag2 = frag[x];
								frag2Num = x;
							}
						//merging required..
						if (frag1 != null)
						{
							if (frag1.getScore() > frag2.getScore())
							{
								bestScoringFragNum = frag1Num;
								worstScoringFragNum = frag2Num;
							}
							else
							{
								bestScoringFragNum = frag2Num;
								worstScoringFragNum = frag1Num;
							}
							frag1.merge(frag2);
							frag[worstScoringFragNum] = null;
							mergingStillBeingDone = true;
							frag[bestScoringFragNum] = frag1;
						}
					}
				}
			}
			while (mergingStillBeingDone);
	}
	
	
	/**
	 * Highlights terms in the  text , extracting the most relevant sections
	 * and concatenating the chosen fragments with a separator (typically "...").
	 * The document text is analysed in chunks to record hit statistics
	 * across the document. After accumulating stats, the fragments with the highest scores
	 * are returned in order as "separator" delimited strings.
	 *
	 * @param text        text to highlight terms in
	 * @param maxNumFragments  the maximum number of fragments.
	 * @param separator  the separator used to intersperse the document fragments (typically "...")
	 *
	 * @return highlighted text
	 */
	public final String getBestFragments(
		TokenStream tokenStream,	
		String text,
		int maxNumFragments,
		String separator)
		throws IOException
	{
		String sections[] =	getBestFragments(tokenStream,text, maxNumFragments);
		StringBuffer result = new StringBuffer();
		for (int i = 0; i < sections.length; i++)
		{
			if (i > 0)
			{
				result.append(separator);
			}
			result.append(sections[i]);
		}
		return result.toString();
	}

	/**
	 * @return the maximum number of bytes to be tokenized per doc 
	 */
	public int getMaxDocBytesToAnalyze()
	{
		return maxDocBytesToAnalyze;
	}

	/**
	 * @param byteCount the maximum number of bytes to be tokenized per doc
	 * (This can improve performance with large documents)
	 */
	public void setMaxDocBytesToAnalyze(int byteCount)
	{
		maxDocBytesToAnalyze = byteCount;
	}

	/**
	 */
	public Fragmenter getTextFragmenter()
	{
		return textFragmenter;
	}

	/**
	 * @param fragmenter
	 */
	public void setTextFragmenter(Fragmenter fragmenter)
	{
		textFragmenter = fragmenter;
	}

	/**
	 * @return Object used to score each text fragment 
	 */
	public Scorer getFragmentScorer()
	{
		return fragmentScorer;
	}


	/**
	 * @param scorer
	 */
	public void setFragmentScorer(Scorer scorer)
	{
		fragmentScorer = scorer;
	}

    public Encoder getEncoder()
    {
        return encoder;
    }
    public void setEncoder(Encoder encoder)
    {
        this.encoder = encoder;
    }
}
class FragmentQueue extends PriorityQueue
{
	public FragmentQueue(int size)
	{
		initialize(size);
	}

	public final boolean lessThan(Object a, Object b)
	{
		TextFragment fragA = (TextFragment) a;
		TextFragment fragB = (TextFragment) b;
		if (fragA.getScore() == fragB.getScore())
			return fragA.fragNum > fragB.fragNum;
		else
			return fragA.getScore() < fragB.getScore();
	}
}