学步园

Lucene的Collector是一项高级功能，涉及到搜索过程的详细步骤，通过定制Collector可以改变默认搜索，也可以在此阶段收集命中的文档的信息。

下面用一个例子演示如何自定义Collector以及如何在自定义的Collector中实现数据收集功能。

package test;<br /> import java.io.IOException;<br /> import java.util.Map;<br /> import java.util.Set;<br /> import java.util.TreeMap;<br /> import org.apache.lucene.document.Document;<br /> import org.apache.lucene.document.Field;<br /> import org.apache.lucene.document.Field.Index;<br /> import org.apache.lucene.document.Field.Store;<br /> import org.apache.lucene.index.CorruptIndexException;<br /> import org.apache.lucene.index.IndexReader;<br /> import org.apache.lucene.index.IndexWriter;<br /> import org.apache.lucene.search.Collector;<br /> import org.apache.lucene.search.HitCollector;<br /> import org.apache.lucene.search.IndexSearcher;<br /> import org.apache.lucene.search.MatchAllDocsQuery;<br /> import org.apache.lucene.search.ParallelMultiSearcher;<br /> import org.apache.lucene.search.RangeFilter;<br /> import org.apache.lucene.search.Scorer;<br /> import org.apache.lucene.search.Searcher;<br /> import org.apache.lucene.store.LockObtainFailedException;<br /> import org.apache.lucene.store.RAMDirectory;<br /> import casia.isiteam.plgroup.indexer.commons.AnalyzerFactory;<br /> /**<br /> * 自定义收集器<br /> * @author cn.mingyuan@foxmail.com<br /> *<br /> */<br /> class MyCollector extends Collector {<br /> IndexReader reader = null;//reader用于读取获取文档<br /> //收集信息的map<br /> public Map<Integer, Integer> map = new TreeMap<Integer, Integer>();<br /> @Override<br /> public boolean acceptsDocsOutOfOrder() {<br /> // TODO Auto-generated method stub<br /> return true;<br /> }<br /> /**<br /> * 收集<br /> */<br /> @Override<br /> public void collect(int doc) throws IOException {<br /> System.out.println("doc:" + doc);<br /> Document document = reader.document(doc);<br /> int id = Integer.parseInt(document.get("id"));<br /> int count = Integer.parseInt(document.get("count"));<br /> map.put(id, count);<br /> System.out.println("put:" + id + " " + count);<br /> }<br /> @Override<br /> public void setNextReader(IndexReader reader, int docBase) throws IOException {<br /> this.reader = reader;//假设reader由多个subReader构成，那么本方法将被调用与subReader个数相同的次数<br /> System.out.println("set reader");<br /> }<br /> @Override<br /> public void setScorer(Scorer scorer) throws IOException {<br /> // do nothing<br /> }<br /> }<br /> public class HitCollectorTest {<br /> @SuppressWarnings("deprecation")<br /> public static void test() throws CorruptIndexException, LockObtainFailedException, IOException {<br /> // 构建内存索引<br /> RAMDirectory directory = new RAMDirectory();<br /> RAMDirectory directory2 = new RAMDirectory();<br /> IndexWriter writer = new IndexWriter(directory, AnalyzerFactory.getMMInstance());<br /> IndexWriter writer2 = new IndexWriter(directory2, AnalyzerFactory.getMMInstance());<br /> Document document = new Document();<br /> Field idField = new Field("id", "1", Store.YES, Index.ANALYZED);<br /> Field countFiled = new Field("count", "33", Store.YES, Index.ANALYZED);<br /> Field range = new Field("range", "1", Store.YES, Index.ANALYZED);// 用于过滤数据<br /> document.add(idField);<br /> document.add(countFiled);<br /> document.add(range);<br /> writer.addDocument(document);<br /> writer.close();<br /> document = new Document();<br /> idField = new Field("id", "2", Store.YES, Index.ANALYZED);<br /> countFiled = new Field("count", "211", Store.YES, Index.ANALYZED);<br /> range = new Field("range", "2", Store.YES, Index.ANALYZED);<br /> document.add(idField);<br /> document.add(countFiled);<br /> document.add(range);<br /> writer2.addDocument(document);<br /> writer2.close();<br /> // 使用MatchAllDocsQuery结合filter进行搜索，使用自定义Collector对数据进行收集<br /> Searcher searcher = new IndexSearcher(directory);<br /> Searcher searcher2 = new IndexSearcher(directory2);<br /> Searcher searcher3=new ParallelMultiSearcher(new Searcher[]{searcher,searcher2});<br /> MyCollector collector = new MyCollector();<br /> RangeFilter filter = new RangeFilter("range", "0", "4", true, true);<br /> searcher3.search(new MatchAllDocsQuery(), filter, collector);<br /> searcher3.close();<br /> directory.close();<br /> // 取出数据<br /> Map<Integer, Integer> map = collector.map;<br /> Set<Integer> keySet = map.keySet();<br /> for (int i : keySet) {<br /> System.out.println("<" + i + "," + map.get(i) + ">");<br /> }<br /> }<br /> public static void main(String[] args) throws CorruptIndexException, LockObtainFailedException, IOException {<br /> test();<br /> }<br /> }<br />