8.2 查询过程
完整过程如下：IndexSearcher调用search方法
protectedvoidsearch(List
throws IOException {
// TODO: should we make this
// threaded...? the Collector could be sync'd?
// always use single thread:for(LeafReaderContext ctx : leaves) {// search each subreaderfinal LeafCollector leafCollector;
try{ leafCollector = collector.getLeafCollector(ctx);//1}catch (CollectionTerminatedException e) {
// there is no doc of interest in this reader context
// continue with the following leafcontinue; } BulkScorer scorer = weight.bulkScorer(ctx);//2
if(scorer !=null) {
try{scorer.score(leafCollector, ctx.reader().getLiveDocs());//3}catch (CollectionTerminatedException e) {
// collection was terminated prematurely
// continue with the following leaf }
}
}
}
8.2.1 获取Collector
TopScoreDocCollector.java#SimpleTopScoreDocCollector
@Override
public LeafCollector getLeafCollector(LeafReaderContext context)
throws IOException {
finalintdocBase = context.docBase;
returnnew ScorerLeafCollector() {
@Override
publicvoidcollect(intdoc)throws IOException {
float score = scorer.score();/* Document document=context.reader().document(doc);*/// This collector cannot handle these scores:assertscore != Float.NEGATIVE_INFINITY;
assert!Float.isNaN(score);
totalHits++;
if(score <= pqTop.score) {
// Since docs are returned in-order (i.e., increasing doc Id), a document
// with equal score to pqTop.score cannot compete since HitQueue favors
// documents with lower doc Ids. Therefore reject those docs too.return;
}
pqTop.doc = doc + docBase;
pqTop.score = score;
pqTop = pq.updateTop();
}
};
}
8.2.2 调用打分socore
/** * Optional method, to return a {@link BulkScorer} to
* score the query and send hits to a {@link Collector}.
* Only queries that have a different top-level approach
* need to override this; the default implementation
* pulls a normal {@link Scorer} and iterates and
* collects the resulting hits which are not marked as deleted.
*
* @param context
* the {@link org.apache.lucene.index.LeafReaderContext} for which to return the {@link Scorer}.
*
* @return a {@link BulkScorer} which scores documents and
* passes them to a collector.
* @throws IOException if there is a low-level I/O error
*/publicBulkScorer bulkScorer(LeafReaderContext context)throwsIOException {Scorer scorer = scorer(context);
if(scorer ==null) {
// No docs matchreturnnull;
}
// This impl always scores docs in order, so we can
// ignore scoreDocsInOrder:returnnew DefaultBulkScorer(scorer);
}
/** Just wraps a Scorer and performs top scoring using it.
* @lucene.internal */protectedstaticclassDefaultBulkScorerextends BulkScorer {
privatefinal Scorer scorer;
privatefinal DocIdSetIterator iterator;
privatefinal TwoPhaseIterator twoPhase;
/** Sole constructor. */public DefaultBulkScorer(Scorer scorer) {
if(scorer ==null) {
thrownew NullPointerException();
}
this.scorer = scorer;
this.iterator = scorer.iterator();
this.twoPhase = scorer.twoPhaseIterator();
}
@Override
publiclong cost() {
return iterator.cost();
}
@Override
publicintscore(LeafCollector collector, Bits acceptDocs,intmin,intmax)throws IOException {
collector.setScorer(scorer);
if(scorer.docID() == -1 && min == 0 && max ==DocIdSetIterator.NO_MORE_DOCS) {scoreAll(collector, iterator, twoPhase, acceptDocs);
return DocIdSetIterator.NO_MORE_DOCS;
} else {
intdoc = scorer.docID();
if(doc < min) {
if(twoPhase ==null) {
doc = iterator.advance(min);
} else {
doc = twoPhase.approximation().advance(min);
}
}
return scoreRange(collector, iterator, twoPhase, acceptDocs, doc, max);
}
}
调用scoreAll方法，遍历Document，执行SimpleTopScoreDocCollector的collect方法，包含打分逻辑<见SimpleTopScoreDocCollector代码>。
/** Specialized method to bulk-score all hits; we
* separate this from {@link #scoreRange} to help out
* hotspot.
* See <a href="https://issues.apache.org/jira/browse/LUCENE-5487">LUCENE-5487</a> */staticvoidscoreAll(LeafCollector collector, DocIdSetIterator iterator, TwoPhaseIterator twoPhase, Bits acceptDocs)throws IOException {
if(twoPhase ==null) {
for(intdoc = iterator.nextDoc(); doc != DocIdSetIterator.NO_MORE_DOCS; doc = iterator.nextDoc()) {
if(acceptDocs ==null||acceptDocs.get(doc)) {collector.collect(doc);} } }else {
// The scorer has an approximation, so run the approximation first, then check acceptDocs, then confirmfinalDocIdSetIterator approximation = twoPhase.approximation();
for(intdoc = approximation.nextDoc(); doc != DocIdSetIterator.NO_MORE_DOCS; doc = approximation.nextDoc()) {
if((acceptDocs ==null|| acceptDocs.get(doc)) &&twoPhase.matches()) {collector.collect(doc);} } } }
总结：
梳理整理整个流程太累了。
