int32_t SegmentMerger::mergeFields()
{
//Func - Merge the fields of all segments
//Pre - true
//Post - The field infos and field values of all segments have been merged.
//Create a new FieldInfos
fieldInfos = _CLNEW FieldInfos(); // merge field names
//Condition check to see if fieldInfos points to a valid instance
CND_CONDITION(fieldInfos != NULL, "Memory allocation for fieldInfos failed");
IndexReader* reader = NULL;
int32_t docCount = 0;
//Iterate through all readers
for (uint32_t i = 0; i < readers.size(); i++) {
//get the i-th reader
reader = readers[i];
//Condition check to see if reader points to a valid instance
CND_CONDITION(reader != NULL,"No IndexReader found");
StringArrayWithDeletor tmp;
tmp.clear();
reader->getFieldNames(IndexReader::TERMVECTOR_WITH_POSITION_OFFSET, tmp);
addIndexed(reader, fieldInfos, tmp, true, true, true);
tmp.clear();
reader->getFieldNames(IndexReader::TERMVECTOR_WITH_POSITION, tmp);
addIndexed(reader, fieldInfos, tmp, true, true, false);
tmp.clear();
reader->getFieldNames(IndexReader::TERMVECTOR_WITH_OFFSET, tmp);
addIndexed(reader, fieldInfos, tmp, true, false, true);
tmp.clear();
reader->getFieldNames(IndexReader::TERMVECTOR, tmp);
addIndexed(reader, fieldInfos, tmp, true, false, false);
tmp.clear();
reader->getFieldNames(IndexReader::INDEXED, tmp);
addIndexed(reader, fieldInfos, tmp, false, false, false);
tmp.clear();
reader->getFieldNames(IndexReader::UNINDEXED, tmp);
if (tmp.size() > 0) {
TCHAR** arr = _CL_NEWARRAY(TCHAR*,tmp.size()+1);
tmp.toArray(arr);
fieldInfos->add((const TCHAR**)arr, false);
_CLDELETE_ARRAY(arr);
//no need to delete the contents, since tmp is responsible for it
}
}
int32_t SegmentMerger::mergeFields() {
//Func - Merge the fields of all segments
//Pre - true
//Post - The field infos and field values of all segments have been merged.
if (!mergeDocStores) {
// When we are not merging by doc stores, that means
// all segments were written as part of a single
// autoCommit=false IndexWriter session, so their field
// name -> number mapping are the same. So, we start
// with the fieldInfos of the last segment in this
// case, to keep that numbering.
assert(readers[readers.size()-1]->instanceOf(SegmentReader::getClassName()));
assert(false);//check last...and remove if correct...
SegmentReader* sr = (SegmentReader*)readers[readers.size()-1];
fieldInfos = sr->fieldInfos()->clone();
} else {
//Create a new FieldInfos
fieldInfos = _CLNEW FieldInfos(); // merge field names
}
//Condition check to see if fieldInfos points to a valid instance
CND_CONDITION(fieldInfos != NULL,"Memory allocation for fieldInfos failed");
IndexReader* reader = NULL;
//Iterate through all readers
for (uint32_t i = 0; i < readers.size(); i++){
//get the i-th reader
reader = readers[i];
//Condition check to see if reader points to a valid instance
CND_CONDITION(reader != NULL,"No IndexReader found");
if (reader->instanceOf(SegmentReader::getClassName())) {
SegmentReader* segmentReader = (SegmentReader*) reader;
for (size_t j = 0; j < segmentReader->getFieldInfos()->size(); j++) {
FieldInfo* fi = segmentReader->getFieldInfos()->fieldInfo(j);
fieldInfos->add(fi->name, fi->isIndexed, fi->storeTermVector,
fi->storePositionWithTermVector, fi->storeOffsetWithTermVector,
!reader->hasNorms(fi->name), fi->storePayloads);
}
} else {
StringArrayWithDeletor tmp;
tmp.clear(); reader->getFieldNames(IndexReader::TERMVECTOR_WITH_POSITION_OFFSET, tmp);
addIndexed(reader, fieldInfos, tmp, true, true, true, false);
tmp.clear(); reader->getFieldNames(IndexReader::TERMVECTOR_WITH_POSITION, tmp);
addIndexed(reader, fieldInfos, tmp, true, true, false, false);
tmp.clear(); reader->getFieldNames(IndexReader::TERMVECTOR_WITH_OFFSET, tmp);
addIndexed(reader, fieldInfos, tmp, true, false, true, false);
tmp.clear(); reader->getFieldNames(IndexReader::TERMVECTOR, tmp);
addIndexed(reader, fieldInfos, tmp, true, false, false, false);
tmp.clear(); reader->getFieldNames(IndexReader::STORES_PAYLOADS, tmp);
addIndexed(reader, fieldInfos, tmp, false, false, false, true);
tmp.clear(); reader->getFieldNames(IndexReader::INDEXED, tmp);
addIndexed(reader, fieldInfos, tmp, false, false, false, false);
tmp.clear(); reader->getFieldNames(IndexReader::UNINDEXED, tmp);
if ( tmp.size() > 0 ){
TCHAR** arr = _CL_NEWARRAY(TCHAR*,tmp.size()+1);
tmp.toArray_nullTerminated(arr);
fieldInfos->add((const TCHAR**)arr, false);
_CLDELETE_ARRAY(arr); //no need to delete the contents, since tmp is responsible for it
}
}
}
int main()
{
Node * head = NULL;
FILE * fin = NULL;
fin = openFile();
createWordNodes(fin,&head);
printf("\n\n-----------Printing Original List-----------\n\n");
printList(head);
printf("\n\n\nBREAK\n\n\n");
char temp[6] = "frank";
Word * tempWord = createWordStruct(temp);
addOrdered(tempWord, &head);
printf("\n\n-----------Printing List Adding Ordered the name \"frank\"-----------\n\n");
printList(head);
printf("\n\n\nBREAK\n\n\n");
char temp1[6] = "AAAAA";
tempWord = createWordStruct(temp1);
addFirst(tempWord, &head);
printf("\n\n-----------Printing List Adding First the word \"AAAAA\"-----------\n\n");
printList(head);
printf("\n\n\nBREAK\n\n\n");
char temp2[6] = "ZZZZZ";
tempWord = createWordStruct(temp2);
addLast(tempWord, &head);
printf("\n\n-----------Printing List Adding Last the word \"ZZZZZ\"-----------\n\n");
printList(head);
printf("\n\n\nBREAK\n\n\n");
char temp3[6] = "XXXXX";
tempWord = createWordStruct(temp3);
addIndexed(tempWord, &head, 2);
char prevWord[MAX], postWord[MAX];
strcpy(prevWord,((Word*)(head->next->data))->wrd);
strcpy(postWord,((Word*)(head->next->next->next->data))->wrd);
printf("\n\n-----------Printing List Adding at Index #2 the word \"XXXXX\"-----------\n\n");
printf("\n\n-----------It should be between the words \"%s\" and \"%s\"-----------\n\n", prevWord, postWord);
printList(head);
printf("\n\n\nBREAK\n\n\n");
removeFirst(&head);
printf("\n\n-----------Printing List Removing First which will be the word \"AAAAA\"-----------\n\n");
printList(head);
printf("\n\n\nBREAK\n\n\n");
removeLast(&head);
printf("\n\n-----------Printing List Removing Last which will be the word \"ZZZZZ\"-----------\n\n");
printList(head);
printf("\n\n\nBREAK\n\n\n");
printf("\n\n-----------Attempting to remove at index out of bounds-----------\n\n");
removeIndex(&head,-30);
char word2Remove[MAX];
strcpy(word2Remove,((Word*)(head->next->next->data))->wrd);
printf("\n\n-----------Attempting to remove at index 2 which will be: \"%s\"-----------\n\n", word2Remove);
removeIndex(&head, 2);
printf("\n\n-----------Printing list having removed %s-----------\n\n", word2Remove);
printList(head);
printf("\n\n\nBREAK\n\n\n");
printf("\n\n-----------Clearing (freeing) the entire list-----------\n\n");
clearList(&head);
printf("\n\n-----------Attempting to print empty list-----------\n\n");
printList(head);
printf("\n\n\nBREAK\n\n\n");
printf("\n\n-----------GOODBYE-----------\n\n");
fclose(fin);
return 0;
}// end main
