拆解Cluene系列(11)——索引的合併（二）

    合併詞典和倒排表的源代碼和註釋

  

void SegmentMerger::mergeTermInfos(SegmentMergeQueue* queue)
{
	
	//base is the id of the first document in a segment
	int32_t base = 0;

	IndexReader* reader = NULL;
	SegmentMergeInfo* smi = NULL;
    //0.準備工作，初始化每個seg的枚舉器，使之指向seg的第一個term,構建SegmentMergeInfo信息（這時，修改了doc Id編號）,壓入隊列.

	for (uint32_t i = 0; i < readers.size(); i++) {

		reader = readers[i];

		TermEnum* termEnum = reader->terms();
		smi = _CLNEW SegmentMergeInfo(base, termEnum, reader);
		base += reader->numDocs();
		if (smi->next()){
			queue->put(smi);
		}else{
			smi->close();
			_CLDELETE(smi);
		}
	}

	
	SegmentMergeInfo** match = _CL_NEWARRAY(SegmentMergeInfo*,readers.size()+1);
	SegmentMergeInfo* top = NULL;

	//As long as there are SegmentMergeInfo instances stored in the queue
	while (queue->size() > 0) {
		int32_t matchSize = 0;			  

		
		//1.從優先級隊列中彈出第一個Term放到match數組中。
		match[matchSize++] = queue->pop();
		
		Term* term = match[0]->term;
		top = queue->top();
		//2.尋找含有相同Term的其他seg也放到match數組中
		while (top != NULL && term->equals(top->term) ){ 
			match[matchSize++] = queue->pop();
			top = queue->top();
		}
		match[matchSize]=NULL;

		//3.合併這些相同Term的倒排表，並把新的倒排表加入新生成的seg中。
		mergeTermInfo(match); //matchSize 處理這個Term

		//4.將match數組中還有Term的seg重新放入優先級隊列中.
		while (matchSize > 0){
			smi = match[--matchSize];
			if (smi->next()){
				queue->put(smi);
			}else{
				_CLDELETE( smi );
			}
		}
	   //5.繼續檢測隊列，重複上述過程，直到隊列元素爲空。
	}

	_CLDELETE_ARRAY(match);
}


void SegmentMerger::mergeTermInfo( SegmentMergeInfo** smis)
{
	....
}