public abstract class Collector {//指定打分器public abstract void setScorer(Scorer scorer) throws IOException;//对目标结果进行收集，很重要！public abstract void collect(int doc) throws IOException;//一个索引可能会有多个子索引，这里相当于是对子索引的遍历操作public abstract void setNextReader(IndexReader reader, int docBase) throws IOException;//public abstract boolean acceptsDocsOutOfOrder();}

public void search(Weight weight, Filter filter, Collector collector)throws IOException {// TODO: should we make this// threaded...? the Collector could be sync'd?// always use single thread:for (int i = 0; i < subReaders.length; i++) { // 检索每个子索引collector.setNextReader(subReaders[i], docBase + docStarts[i]);final Scorer scorer = (filter == null) ? weight.scorer(subReaders[i], !collector.acceptsDocsOutOfOrder(), true): FilteredQuery.getFilteredScorer(subReaders[i],getSimilarity(), weight, weight, filter);//构建打分器if (scorer != null) {scorer.score(collector);//打分}}}

public void score(Collector collector) throws IOException {collector.setScorer(this);int doc;while ((doc = nextDoc()) != NO_MORE_DOCS) {collector.collect(doc);//搜集结果}}

    @Overridepublic void collect(int doc) throws IOException {float score = scorer.score();// This collector cannot handle these scores:assert score != Float.NEGATIVE_INFINITY;assert !Float.isNaN(score);totalHits++;if (score <= pqTop.score) {// 以下的实现使用了优先级队列，如果当前分值小于队列中pqTop.score则直接pass！return;}pqTop.doc = doc + docBase;pqTop.score = score;pqTop = pq.updateTop();}

package com.fox.group;import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.List;
import java.util.Map;import org.apache.lucene.index.IndexReader;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.FieldCache;
import org.apache.lucene.search.Scorer;/*** @author huangfox* @data 2012-7-10* @email huangfox009@126.com* @desc */
public class GroupCollectorDemo extends Collector {private GF gf = new GF();// 保存分组统计结果private String[] fc;// fieldCacheprivate String f;// 统计字段String spliter;int length;public void setFc(String[] fc) {this.fc = fc;}@Overridepublic void setScorer(Scorer scorer) throws IOException {}@Overridepublic void setNextReader(IndexReader reader, int docBase)throws IOException {fc = FieldCache.DEFAULT.getStrings(reader, f);}@Overridepublic void collect(int doc) throws IOException {// 添加的GroupField中，由GroupField负责统计每个不同值的数目gf.addValue(fc[doc]);}@Overridepublic boolean acceptsDocsOutOfOrder() {return true;}public GF getGroupField() {return gf;}public void setSpliter(String spliter) {this.spliter = spliter;}public void setLength(int length) {this.length = length;}public void setF(String f) {this.f = f;}
}class GF {// 所有可能的分组字段值，排序按每个字段值的文档个数大小排序private List<String> values = new ArrayList<String>();// 保存字段值和文档个数的对应关系private Map<String, Integer> countMap = new HashMap<String, Integer>();public Map<String, Integer> getCountMap() {return countMap;}public void setCountMap(Map<String, Integer> countMap) {this.countMap = countMap;}public List<String> getValues() {Collections.sort(values, new ValueComparator());return values;}public void setValues(List<String> values) {this.values = values;}public void addValue(String value) {if (value == null || "".equals(value))return;if (countMap.get(value) == null) {countMap.put(value, 1);values.add(value);} else {countMap.put(value, countMap.get(value) + 1);}}class ValueComparator implements Comparator<String> {public int compare(String value0, String value1) {if (countMap.get(value0) > countMap.get(value1)) {return -1;} else if (countMap.get(value0) < countMap.get(value1)) {return 1;}return 0;}}
}

package com.fox.group;import java.io.File;
import java.io.IOException;
import java.util.List;import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;/*** @author huangfox* @data 2012-7-10* @email huangfox009@126.com* @desc */
public class GroupTest {public static void main(String[] f) throws IOException, ParseException {FSDirectory dir = SimpleFSDirectory.open(new File("d:/nrttest"));IndexReader reader = IndexReader.open(dir);IndexSearcher searcher = new IndexSearcher(reader);// GroupCollector是自定义文档收集器，用于实现分组统计String str = "";QueryParser parser = new QueryParser(Version.LUCENE_36, "f",new IKAnalyzer());while (true) {str = "an:cn*";long bt = System.currentTimeMillis();Query query = parser.parse(str);System.out.println(query);GroupCollectorDemo myCollector = new GroupCollectorDemo();// myCollector.setFc(ad);myCollector.setF("in");searcher.search(query, myCollector);// GroupField用来保存分组统计的结果GF gf = myCollector.getGroupField();List<String> values = gf.getValues();long et = System.currentTimeMillis();System.out.println((et - bt) + "ms");for (int i = 0; i < 10; i++) {String value = values.get(i);System.out.println(value + "=" + gf.getCountMap().get(value));}}}
}

an:cn*
6616ms
毛裕民;谢毅=13728
邱则有=10126
杨孟君=3771
王尔中=1712
王信锁=1658
张逶=1314
朱炜=1200
赵蕴岚;何唯平=1039
杨贻方=872
黄金富=871

ad:2006*
213ms
邱则有=1244
张云波=628
赵蕴岚;何唯平=398
余内逊;余谦梁=376
杨贻方=298
王尔中=258
汪铁良=224
赵发=222
黄振华=212
陆舟;于华章=196