Solr4.8.0源码分析(6)之非排序查询

1   /**
  2    * getDocList version that uses+populates query and filter caches.
  3    * In the event of a timeout, the cache is not populated.
  4    */
  5   private void getDocListC(QueryResult qr, QueryCommand cmd) throws IOException {
  6     DocListAndSet out = new DocListAndSet();
  7     qr.setDocListAndSet(out);
  8     QueryResultKey key=null;
  9     int maxDocRequested = cmd.getOffset() + cmd.getLen(); //当有偏移的查询产生，Solr首先会获取cmd.getOffset()+cmd.getLen()个的doc id然后　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　//再根据偏移量获取子集，所以maxDocRequested是实际的查询个数。
 10     // check for overflow, and check for # docs in index
 11     if (maxDocRequested < 0 || maxDocRequested > maxDoc()) maxDocRequested = maxDoc();// 最多的情况获取所有doc id
 12     int supersetMaxDoc= maxDocRequested;
 13     DocList superset = null;
 14 
 15     int flags = cmd.getFlags();
 16     Query q = cmd.getQuery();
 17     if (q instanceof ExtendedQuery) {
 18       ExtendedQuery eq = (ExtendedQuery)q;
 19       if (!eq.getCache()) {
 20         flags |= (NO_CHECK_QCACHE | NO_SET_QCACHE | NO_CHECK_FILTERCACHE);
 21       }
 22     }
 23 
 24 
 25     // we can try and look up the complete query in the cache.
 26     // we can‘t do that if filter!=null though (we don‘t want to
 27     // do hashCode() and equals() for a big DocSet).
        // 先从查询结果的缓存区查找是否出现过该条件的查询，若出现过则返回缓存的结果.关于缓存的内容将会独立写一篇文章
 28     if (queryResultCache != null && cmd.getFilter()==null
 29         && (flags & (NO_CHECK_QCACHE|NO_SET_QCACHE)) != ((NO_CHECK_QCACHE|NO_SET_QCACHE)))
 30     {
 31         // all of the current flags can be reused during warming,
 32         // so set all of them on the cache key.
 33         key = new QueryResultKey(q, cmd.getFilterList(), cmd.getSort(), flags);
 34         if ((flags & NO_CHECK_QCACHE)==0) {
 35           superset = queryResultCache.get(key);
 36 
 37           if (superset != null) {
 38             // check that the cache entry has scores recorded if we need them
 39             if ((flags & GET_SCORES)==0 || superset.hasScores()) {
 40               // NOTE: subset() returns null if the DocList has fewer docs than
 41               // requested
 42               out.docList = superset.subset(cmd.getOffset(),cmd.getLen()); //如果有缓存，就从中去除一部分子集
 43             }
 44           }
 45           if (out.docList != null) {   
 46             // found the docList in the cache... now check if we need the docset too.
 47             // OPT: possible future optimization - if the doclist contains all the matches,
 48             // use it to make the docset instead of rerunning the query.
                //获取缓存中的docSet，并传给result。
 49             if (out.docSet==null && ((flags & GET_DOCSET)!=0) ) {
 50               if (cmd.getFilterList()==null) {
 51                 out.docSet = getDocSet(cmd.getQuery());
 52               } else {  
 53                 List<Query> newList = new ArrayList<>(cmd.getFilterList().size()+1);
 54                 newList.add(cmd.getQuery());
 55                 newList.addAll(cmd.getFilterList());
 56                 out.docSet = getDocSet(newList);
 57               }
 58             }
 59             return;
 60           }
 61         }
 62 
 63       // If we are going to generate the result, bump up to the
 64       // next resultWindowSize for better caching.
 65       // 修改supersetMaxDoc为queryResultWindwSize的整数倍
 66       if ((flags & NO_SET_QCACHE) == 0) {
 67         // handle 0 special case as well as avoid idiv in the common case.
 68         if (maxDocRequested < queryResultWindowSize) {
 69           supersetMaxDoc=queryResultWindowSize;
 70         } else {
 71           supersetMaxDoc = ((maxDocRequested -1)/queryResultWindowSize + 1)*queryResultWindowSize;
 72           if (supersetMaxDoc < 0) supersetMaxDoc=maxDocRequested;
 73         }
 74       } else {
 75         key = null;  // we won‘t be caching the result
 76       }
 77     }
 78     cmd.setSupersetMaxDoc(supersetMaxDoc);
 79 
 80 
 81     // OK, so now we need to generate an answer.
 82     // One way to do that would be to check if we have an unordered list
 83     // of results for the base query.  If so, we can apply the filters and then
 84     // sort by the resulting set.  This can only be used if:
 85     // - the sort doesn‘t contain score
 86     // - we don‘t want score returned.
 87 
 88     // check if we should try and use the filter cache
 89     boolean useFilterCache=false;
 90     if ((flags & (GET_SCORES|NO_CHECK_FILTERCACHE))==0 && useFilterForSortedQuery && cmd.getSort() != null && filterCache != null) {
 91       useFilterCache=true;
 92       SortField[] sfields = cmd.getSort().getSort();
 93       for (SortField sf : sfields) {
 94         if (sf.getType() == SortField.Type.SCORE) {
 95           useFilterCache=false;
 96           break;
 97         }
 98       }
 99     }
100 
101     if (useFilterCache) {
102       // now actually use the filter cache.
103       // for large filters that match few documents, this may be
104       // slower than simply re-executing the query.
105       if (out.docSet == null) {
106         out.docSet = getDocSet(cmd.getQuery(),cmd.getFilter());
107         DocSet bigFilt = getDocSet(cmd.getFilterList());
108         if (bigFilt != null) out.docSet = out.docSet.intersection(bigFilt);
109       }
110       // todo: there could be a sortDocSet that could take a list of
111       // the filters instead of anding them first...
112       // perhaps there should be a multi-docset-iterator
113       sortDocSet(qr, cmd);  //排序查询
114     } else {
115       // do it the normal way...
116       if ((flags & GET_DOCSET)!=0) {
117         // this currently conflates returning the docset for the base query vs
118         // the base query and all filters.
119         DocSet qDocSet = getDocListAndSetNC(qr,cmd);
120         // cache the docSet matching the query w/o filtering
121         if (qDocSet!=null && filterCache!=null && !qr.isPartialResults()) filterCache.put(cmd.getQuery(),qDocSet);
122       } else {
123         getDocListNC(qr,cmd); //非排序查询，这也是本文的流程。
124       }
125       assert null != out.docList : "docList is null";
126     }
127 
128     if (null == cmd.getCursorMark()) {
129       // Kludge...
130       // we can‘t use DocSlice.subset, even though it should be an identity op
131       // because it gets confused by situations where there are lots of matches, but
132       // less docs in the slice then were requested, (due to the cursor)
133       // so we have to short circuit the call.
134       // None of which is really a problem since we can‘t use caching with
135       // cursors anyway, but it still looks weird to have to special case this
136       // behavior based on this condition - hence the long explanation.
137       superset = out.docList; //根据offset和len截取查询结果
138       out.docList = superset.subset(cmd.getOffset(),cmd.getLen()); 
139     } else {
140       // sanity check our cursor assumptions
141       assert null == superset : "cursor: superset isn‘t null";
142       assert 0 == cmd.getOffset() : "cursor: command offset mismatch";
143       assert 0 == out.docList.offset() : "cursor: docList offset mismatch";
144       assert cmd.getLen() >= supersetMaxDoc : "cursor: superset len mismatch: " +
145         cmd.getLen() + " vs " + supersetMaxDoc;
146     }
147 
148     // lastly, put the superset in the cache if the size is less than or equal
149     // to queryResultMaxDocsCached
150     if (key != null && superset.size() <= queryResultMaxDocsCached && !qr.isPartialResults()) {
151       queryResultCache.put(key, superset);    //如果结果的个数小于或者等于queryResultMaxDocsCached则将本次查询结果放入缓存
152     }
153   }

 1       final TopDocsCollector topCollector = buildTopDocsCollector(len, cmd); //新建TopDocsCollector对象，里面会新建(offset + len(查询条          //件的len))的HitQueue，每当获取到一个符合查询条件的doc，就会将该doc id放入HitQueue,并totalhit计数加一，这个totalhit变量也就是查询结果的数量
 2       Collector collector = topCollector;
 3       if (terminateEarly) {
 4         collector = new EarlyTerminatingCollector(collector, cmd.len);
 5       }
 6       if( timeAllowed > 0 ) {
 7         collector = new TimeLimitingCollector(collector, TimeLimitingCollector.getGlobalCounter(), timeAllowed); 
           //TimeLimitingCollector的实现原理很简单，从第一个找到符合查询条件的doc id开始计时，在达到timeAllowed之前，会想查询得到的doc id放入HitQue           //ue,一旦timeAllowed到了，就会立即扔出错误，中断后续的查询。这对于我们优化查询是个重要的提示
 8       }
 9       if (pf.postFilter != null) {
10         pf.postFilter.setLastDelegate(collector);
11         collector = pf.postFilter;
12       }
13       try {
           // 进入Lucene的IndexSearch.Search()
14         super.search(query, luceneFilter, collector);
15         if(collector instanceof DelegatingCollector) {
16           ((DelegatingCollector)collector).finish();
17         }
18       }
19       catch( TimeLimitingCollector.TimeExceededException x ) {
20         log.warn( "Query: " + query + "; " + x.getMessage() );
21         qr.setPartialResults(true);
22       }
23 
24       totalHits = topCollector.getTotalHits();           //返回totalhit的结果
25       TopDocs topDocs = topCollector.topDocs(0, len);    //返回优先级队列hitqueue的doc id
26       populateNextCursorMarkFromTopDocs(qr, cmd, topDocs);
27 
28       maxScore = totalHits>0 ? topDocs.getMaxScore() : 0.0f;
29       nDocsReturned = topDocs.scoreDocs.length;
30       ids = new int[nDocsReturned];
31       scores = (cmd.getFlags()&GET_SCORES)!=0 ? new float[nDocsReturned] : null;
32       for (int i=0; i<nDocsReturned; i++) {
33         ScoreDoc scoreDoc = topDocs.scoreDocs[i];
34         ids[i] = scoreDoc.doc;
35         if (scores != null) scores[i] = scoreDoc.score;
36       }

  /**
   * Calls {@link Collector#collect(int)} on the decorated {@link Collector}
   * unless the allowed time has passed, in which case it throws an exception.
   * 
   * @throws TimeExceededException
   *           if the time allowed has exceeded.
   */
  @Override
  public void collect(final int doc) throws IOException {
    final long time = clock.get();
    if (timeout < time) {
      if (greedy) {
        //System.out.println(this+"  greedy: before failing, collecting doc: "+(docBase + doc)+"  "+(time-t0));
        collector.collect(doc);
      }
      //System.out.println(this+"  failing on:  "+(docBase + doc)+"  "+(time-t0));
      throw new TimeExceededException( timeout-t0, time-t0, docBase + doc );   
    }
    //System.out.println(this+"  collecting: "+(docBase + doc)+"  "+(time-t0));
    collector.collect(doc);
  }

 1     public BooleanWeight(IndexSearcher searcher, boolean disableCoord)
 2       throws IOException {
 3       this.similarity = searcher.getSimilarity();
 4       this.disableCoord = disableCoord;
 5       weights = new ArrayList<>(clauses.size());
 6       for (int i = 0 ; i < clauses.size(); i++) {
 7         BooleanClause c = clauses.get(i);
 8         Weight w = c.getQuery().createWeight(searcher);
 9         weights.add(w);
10         if (!c.isProhibited()) {
11           maxCoord++;
12         }
13       }
14     }

 1 /**
 2    * Lower-level search API.
 3    * 
 4    * <p>
 5    * {@link Collector#collect(int)} is called for every document. <br>
 6    * 
 7    * <p>
 8    * NOTE: this method executes the searches on all given leaves exclusively.
 9    * To search across all the searchers leaves use {@link #leafContexts}.
10    * 
11    * @param leaves 
12    *          the searchers leaves to execute the searches on
13    * @param weight
14    *          to match documents
15    * @param collector
16    *          to receive hits
17    * @throws BooleanQuery.TooManyClauses If a query would exceed 
18    *         {@link BooleanQuery#getMaxClauseCount()} clauses.
19    */
20   protected void search(List<AtomicReaderContext> leaves, Weight weight, Collector collector)
21       throws IOException {
22 
23     // TODO: should we make this
24     // threaded...?  the Collector could be sync‘d?
25     // always use single thread:
26     for (AtomicReaderContext ctx : leaves) { // search each subreader
27       try {
28         collector.setNextReader(ctx);
29       } catch (CollectionTerminatedException e) {
30         // there is no doc of interest in this reader context
31         // continue with the following leaf
32         continue;
33       }
34       BulkScorer scorer = weight.bulkScorer(ctx, !collector.acceptsDocsOutOfOrder(), ctx.reader().getLiveDocs());
35       if (scorer != null) {
36         try {
37           scorer.score(collector);
38         } catch (CollectionTerminatedException e) {
39           // collection was terminated prematurely
40           // continue with the following leaf
41         }
42       }
43     }
44   }

 1  @Override
 2     public boolean score(Collector collector, int max) throws IOException {
 3       // TODO: this may be sort of weird, when we are
 4       // embedded in a BooleanScorer, because we are
 5       // called for every chunk of 2048 documents.  But,
 6       // then, scorer is a FakeScorer in that case, so any
 7       // Collector doing something "interesting" in
 8       // setScorer will be forced to use BS2 anyways:
 9       collector.setScorer(scorer);
10       if (max == DocIdSetIterator.NO_MORE_DOCS) {
11         scoreAll(collector, scorer);
12         return false;
13       } else {
14         int doc = scorer.docID();
15         if (doc < 0) {
16           doc = scorer.nextDoc();
17         }
18         return scoreRange(collector, scorer, doc, max);
19       }
20     }

1     static void scoreAll(Collector collector, Scorer scorer) throws IOException {
2       int doc;
3       while ((doc = scorer.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
4         collector.collect(doc);
5       }
6     }

 1     @Override
 2     public void collect(int doc) throws IOException {
 3       float score = scorer.score();
 4 
 5       // This collector cannot handle these scores:
 6       assert score != Float.NEGATIVE_INFINITY;
 7       assert !Float.isNaN(score);
 8 
 9       totalHits++;
10       if (score <= pqTop.score) {
11         // Since docs are returned in-order (i.e., increasing doc Id), a document
12         // with equal score to pqTop.score cannot compete since HitQueue favors
13         // documents with lower doc Ids. Therefore reject those docs too.
14         return;
15       }
16       pqTop.doc = doc + docBase;
17       pqTop.score = score;
18       pqTop = pq.updateTop();
19     }