@Benchmark
@Warmup(iterations = 2, time = 2, timeUnit = TimeUnit.MILLISECONDS)
@Measurement(iterations = 2, time = 2, timeUnit = TimeUnit.MILLISECONDS)
public void bench() {
for (int i = 0; i < DEFAULT_ITER_TIME; i++) {
expression.evaluate(rowBatch);
}
}
@Override
public void process(Object row, int tag) throws HiveException {
try {
VectorizedRowBatch batch = (VectorizedRowBatch) row;
alias = (byte) tag;
if (needCommonSetup) {
// Our one time process method initialization.
commonSetup(batch);
/*
* Initialize Multi-Key members for this specialized class.
*/
keyVectorSerializeWrite =
new VectorSerializeRow(new BinarySortableSerializeWrite(bigTableKeyColumnMap.length));
keyVectorSerializeWrite.init(bigTableKeyTypeInfos, bigTableKeyColumnMap);
currentKeyOutput = new Output();
saveKeyOutput = new Output();
needCommonSetup = false;
}
if (needHashTableSetup) {
// Setup our hash table specialization. It will be the first time the process
// method is called, or after a Hybrid Grace reload.
/*
* Get our Multi-Key hash map information for this specialized class.
*/
hashMap = (VectorMapJoinBytesHashMap) vectorMapJoinHashTable;
needHashTableSetup = false;
}
batchCounter++;
final int inputLogicalSize = batch.size;
if (inputLogicalSize == 0) {
if (isLogDebugEnabled) {
LOG.debug(CLASS_NAME + " batch #" + batchCounter + " empty");
}
return;
}
// Do the per-batch setup for an outer join.
outerPerBatchSetup(batch);
// For outer join, remember our input rows before ON expression filtering or before
// hash table matching so we can generate results for all rows (matching and non matching)
// later.
boolean inputSelectedInUse = batch.selectedInUse;
if (inputSelectedInUse) {
// if (!verifyMonotonicallyIncreasing(batch.selected, batch.size)) {
// throw new HiveException("batch.selected is not in sort order and unique");
// }
System.arraycopy(batch.selected, 0, inputSelected, 0, inputLogicalSize);
}
// Filtering for outer join just removes rows available for hash table matching.
boolean someRowsFilteredOut = false;
if (bigTableFilterExpressions.length > 0) {
// Since the input
for (VectorExpression ve : bigTableFilterExpressions) {
ve.evaluate(batch);
}
someRowsFilteredOut = (batch.size != inputLogicalSize);
if (isLogDebugEnabled) {
if (batch.selectedInUse) {
if (inputSelectedInUse) {
LOG.debug(
CLASS_NAME
+ " inputSelected "
+ intArrayToRangesString(inputSelected, inputLogicalSize)
+ " filtered batch.selected "
+ intArrayToRangesString(batch.selected, batch.size));
} else {
LOG.debug(
CLASS_NAME
+ " inputLogicalSize "
+ inputLogicalSize
+ " filtered batch.selected "
+ intArrayToRangesString(batch.selected, batch.size));
}
}
}
}
// Perform any key expressions. Results will go into scratch columns.
if (bigTableKeyExpressions != null) {
for (VectorExpression ve : bigTableKeyExpressions) {
ve.evaluate(batch);
}
}
/*
* Multi-Key specific declarations.
*/
// None.
/*
* Multi-Key Long check for repeating.
*/
// If all BigTable input columns to key expressions are isRepeating, then
// calculate key once; lookup once.
// Also determine if any nulls are present since for a join that means no match.
boolean allKeyInputColumnsRepeating;
boolean someKeyInputColumnIsNull =
false; // Only valid if allKeyInputColumnsRepeating is true.
if (bigTableKeyColumnMap.length == 0) {
allKeyInputColumnsRepeating = false;
} else {
allKeyInputColumnsRepeating = true;
for (int i = 0; i < bigTableKeyColumnMap.length; i++) {
ColumnVector colVector = batch.cols[bigTableKeyColumnMap[i]];
if (!colVector.isRepeating) {
allKeyInputColumnsRepeating = false;
break;
}
if (!colVector.noNulls && colVector.isNull[0]) {
someKeyInputColumnIsNull = true;
}
}
}
if (allKeyInputColumnsRepeating) {
/*
* Repeating.
*/
// All key input columns are repeating. Generate key once. Lookup once.
// Since the key is repeated, we must use entry 0 regardless of selectedInUse.
/*
* Multi-Key specific repeated lookup.
*/
JoinUtil.JoinResult joinResult;
if (batch.size == 0) {
// Whole repeated key batch was filtered out.
joinResult = JoinUtil.JoinResult.NOMATCH;
} else if (someKeyInputColumnIsNull) {
// Any (repeated) null key column is no match for whole batch.
joinResult = JoinUtil.JoinResult.NOMATCH;
} else {
// All key input columns are repeating. Generate key once. Lookup once.
keyVectorSerializeWrite.setOutput(currentKeyOutput);
keyVectorSerializeWrite.serializeWrite(batch, 0);
byte[] keyBytes = currentKeyOutput.getData();
int keyLength = currentKeyOutput.getLength();
joinResult = hashMap.lookup(keyBytes, 0, keyLength, hashMapResults[0]);
}
/*
* Common repeated join result processing.
*/
if (isLogDebugEnabled) {
LOG.debug(
CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name());
}
finishOuterRepeated(
batch,
joinResult,
hashMapResults[0],
someRowsFilteredOut,
inputSelectedInUse,
inputLogicalSize);
} else {
/*
* NOT Repeating.
*/
if (isLogDebugEnabled) {
LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated");
}
int selected[] = batch.selected;
boolean selectedInUse = batch.selectedInUse;
int hashMapResultCount = 0;
int allMatchCount = 0;
int equalKeySeriesCount = 0;
int spillCount = 0;
boolean atLeastOneNonMatch = someRowsFilteredOut;
/*
* Multi-Key specific variables.
*/
Output temp;
// We optimize performance by only looking up the first key in a series of equal keys.
boolean haveSaveKey = false;
JoinUtil.JoinResult saveJoinResult = JoinUtil.JoinResult.NOMATCH;
// Logical loop over the rows in the batch since the batch may have selected in use.
for (int logical = 0; logical < batch.size; logical++) {
int batchIndex = (selectedInUse ? selected[logical] : logical);
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, taskName + ", " +
// getOperatorId() + " candidate " + CLASS_NAME + " batch");
/*
* Multi-Key outer null detection.
*/
// Generate binary sortable key for current row in vectorized row batch.
keyVectorSerializeWrite.setOutput(currentKeyOutput);
keyVectorSerializeWrite.serializeWrite(batch, batchIndex);
if (keyVectorSerializeWrite.getHasAnyNulls()) {
// Have that the NULL does not interfere with the current equal key series, if there
// is one. We do not set saveJoinResult.
//
// Let a current MATCH equal key series keep going, or
// Let a current SPILL equal key series keep going, or
// Let a current NOMATCH keep not matching.
atLeastOneNonMatch = true;
// LOG.debug(CLASS_NAME + " logical " + logical + " batchIndex " + batchIndex + "
// NULL");
} else {
/*
* Multi-Key outer get key.
*/
// Generated earlier to get possible null(s).
/*
* Equal key series checking.
*/
if (!haveSaveKey || !saveKeyOutput.arraysEquals(currentKeyOutput)) {
// New key.
if (haveSaveKey) {
// Move on with our counts.
switch (saveJoinResult) {
case MATCH:
hashMapResultCount++;
equalKeySeriesCount++;
break;
case SPILL:
hashMapResultCount++;
break;
case NOMATCH:
break;
}
}
// Regardless of our matching result, we keep that information to make multiple use
// of it for a possible series of equal keys.
haveSaveKey = true;
/*
* Multi-Key specific save key.
*/
temp = saveKeyOutput;
saveKeyOutput = currentKeyOutput;
currentKeyOutput = temp;
/*
* Multi-Key specific lookup key.
*/
byte[] keyBytes = saveKeyOutput.getData();
int keyLength = saveKeyOutput.getLength();
saveJoinResult =
hashMap.lookup(keyBytes, 0, keyLength, hashMapResults[hashMapResultCount]);
/*
* Common outer join result processing.
*/
switch (saveJoinResult) {
case MATCH:
equalKeySeriesHashMapResultIndices[equalKeySeriesCount] = hashMapResultCount;
equalKeySeriesAllMatchIndices[equalKeySeriesCount] = allMatchCount;
equalKeySeriesIsSingleValue[equalKeySeriesCount] =
hashMapResults[hashMapResultCount].isSingleRow();
equalKeySeriesDuplicateCounts[equalKeySeriesCount] = 1;
allMatchs[allMatchCount++] = batchIndex;
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH
// isSingleValue " + equalKeySeriesIsSingleValue[equalKeySeriesCount] + "
// currentKey " + currentKey);
break;
case SPILL:
spills[spillCount] = batchIndex;
spillHashMapResultIndices[spillCount] = hashMapResultCount;
spillCount++;
break;
case NOMATCH:
atLeastOneNonMatch = true;
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + "
// NOMATCH" + " currentKey " + currentKey);
break;
}
} else {
// LOG.debug(CLASS_NAME + " logical " + logical + " batchIndex " + batchIndex + " Key
// Continues " + saveKey + " " + saveJoinResult.name());
// Series of equal keys.
switch (saveJoinResult) {
case MATCH:
equalKeySeriesDuplicateCounts[equalKeySeriesCount]++;
allMatchs[allMatchCount++] = batchIndex;
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH
// duplicate");
break;
case SPILL:
spills[spillCount] = batchIndex;
spillHashMapResultIndices[spillCount] = hashMapResultCount;
spillCount++;
break;
case NOMATCH:
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + "
// NOMATCH duplicate");
break;
}
}
// if (!verifyMonotonicallyIncreasing(allMatchs, allMatchCount)) {
// throw new HiveException("allMatchs is not in sort order and unique");
// }
}
}
if (haveSaveKey) {
// Update our counts for the last key.
switch (saveJoinResult) {
case MATCH:
hashMapResultCount++;
equalKeySeriesCount++;
break;
case SPILL:
hashMapResultCount++;
break;
case NOMATCH:
break;
}
}
if (isLogDebugEnabled) {
LOG.debug(
CLASS_NAME
+ " batch #"
+ batchCounter
+ " allMatchs "
+ intArrayToRangesString(allMatchs, allMatchCount)
+ " equalKeySeriesHashMapResultIndices "
+ intArrayToRangesString(equalKeySeriesHashMapResultIndices, equalKeySeriesCount)
+ " equalKeySeriesAllMatchIndices "
+ intArrayToRangesString(equalKeySeriesAllMatchIndices, equalKeySeriesCount)
+ " equalKeySeriesIsSingleValue "
+ Arrays.toString(
Arrays.copyOfRange(equalKeySeriesIsSingleValue, 0, equalKeySeriesCount))
+ " equalKeySeriesDuplicateCounts "
+ Arrays.toString(
Arrays.copyOfRange(equalKeySeriesDuplicateCounts, 0, equalKeySeriesCount))
+ " atLeastOneNonMatch "
+ atLeastOneNonMatch
+ " inputSelectedInUse "
+ inputSelectedInUse
+ " inputLogicalSize "
+ inputLogicalSize
+ " spills "
+ intArrayToRangesString(spills, spillCount)
+ " spillHashMapResultIndices "
+ intArrayToRangesString(spillHashMapResultIndices, spillCount)
+ " hashMapResults "
+ Arrays.toString(Arrays.copyOfRange(hashMapResults, 0, hashMapResultCount)));
}
// We will generate results for all matching and non-matching rows.
finishOuter(
batch,
allMatchCount,
equalKeySeriesCount,
atLeastOneNonMatch,
inputSelectedInUse,
inputLogicalSize,
spillCount,
hashMapResultCount);
}
if (batch.size > 0) {
// Forward any remaining selected rows.
forwardBigTableBatch(batch);
}
} catch (IOException e) {
throw new HiveException(e);
} catch (Exception e) {
throw new HiveException(e);
}
}
@Override
public void process(Object row, int tag) throws HiveException {
try {
VectorizedRowBatch batch = (VectorizedRowBatch) row;
alias = (byte) tag;
if (needCommonSetup) {
// Our one time process method initialization.
commonSetup(batch);
/*
* Initialize Single-Column String members for this specialized class.
*/
singleJoinColumn = bigTableKeyColumnMap[0];
needCommonSetup = false;
}
if (needHashTableSetup) {
// Setup our hash table specialization. It will be the first time the process
// method is called, or after a Hybrid Grace reload.
/*
* Get our Single-Column String hash set information for this specialized class.
*/
hashSet = (VectorMapJoinBytesHashSet) vectorMapJoinHashTable;
needHashTableSetup = false;
}
batchCounter++;
// Do the per-batch setup for an left semi join.
// (Currently none)
// leftSemiPerBatchSetup(batch);
// For left semi joins, we may apply the filter(s) now.
for (VectorExpression ve : bigTableFilterExpressions) {
ve.evaluate(batch);
}
final int inputLogicalSize = batch.size;
if (inputLogicalSize == 0) {
if (LOG.isDebugEnabled()) {
LOG.debug(CLASS_NAME + " batch #" + batchCounter + " empty");
}
return;
}
// Perform any key expressions. Results will go into scratch columns.
if (bigTableKeyExpressions != null) {
for (VectorExpression ve : bigTableKeyExpressions) {
ve.evaluate(batch);
}
}
/*
* Single-Column String specific declarations.
*/
// The one join column for this specialized class.
BytesColumnVector joinColVector = (BytesColumnVector) batch.cols[singleJoinColumn];
byte[][] vector = joinColVector.vector;
int[] start = joinColVector.start;
int[] length = joinColVector.length;
/*
* Single-Column Long check for repeating.
*/
// Check single column for repeating.
boolean allKeyInputColumnsRepeating = joinColVector.isRepeating;
if (allKeyInputColumnsRepeating) {
/*
* Repeating.
*/
// All key input columns are repeating. Generate key once. Lookup once.
// Since the key is repeated, we must use entry 0 regardless of selectedInUse.
/*
* Single-Column String specific repeated lookup.
*/
byte[] keyBytes = vector[0];
int keyStart = start[0];
int keyLength = length[0];
JoinUtil.JoinResult joinResult =
hashSet.contains(keyBytes, keyStart, keyLength, hashSetResults[0]);
/*
* Common repeated join result processing.
*/
if (LOG.isDebugEnabled()) {
LOG.debug(
CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name());
}
finishLeftSemiRepeated(batch, joinResult, hashSetResults[0]);
} else {
/*
* NOT Repeating.
*/
if (LOG.isDebugEnabled()) {
LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated");
}
// We remember any matching rows in matchs / matchSize. At the end of the loop,
// selected / batch.size will represent both matching and non-matching rows for outer join.
// Only deferred rows will have been removed from selected.
int selected[] = batch.selected;
boolean selectedInUse = batch.selectedInUse;
int hashSetResultCount = 0;
int allMatchCount = 0;
int spillCount = 0;
/*
* Single-Column String specific variables.
*/
int saveKeyBatchIndex = -1;
// We optimize performance by only looking up the first key in a series of equal keys.
boolean haveSaveKey = false;
JoinUtil.JoinResult saveJoinResult = JoinUtil.JoinResult.NOMATCH;
// Logical loop over the rows in the batch since the batch may have selected in use.
for (int logical = 0; logical < inputLogicalSize; logical++) {
int batchIndex = (selectedInUse ? selected[logical] : logical);
/*
* Single-Column String get key.
*/
// Implicit -- use batchIndex.
/*
* Equal key series checking.
*/
if (!haveSaveKey
|| StringExpr.compare(
vector[saveKeyBatchIndex],
start[saveKeyBatchIndex],
length[saveKeyBatchIndex],
vector[batchIndex],
start[batchIndex],
length[batchIndex])
!= 0) {
// New key.
if (haveSaveKey) {
// Move on with our counts.
switch (saveJoinResult) {
case MATCH:
// We have extracted the existence from the hash set result, so we don't keep it.
break;
case SPILL:
// We keep the hash set result for its spill information.
hashSetResultCount++;
break;
case NOMATCH:
break;
}
}
// Regardless of our matching result, we keep that information to make multiple use
// of it for a possible series of equal keys.
haveSaveKey = true;
/*
* Single-Column String specific save key and lookup.
*/
saveKeyBatchIndex = batchIndex;
/*
* Single-Column String specific lookup key.
*/
byte[] keyBytes = vector[batchIndex];
int keyStart = start[batchIndex];
int keyLength = length[batchIndex];
saveJoinResult =
hashSet.contains(keyBytes, keyStart, keyLength, hashSetResults[hashSetResultCount]);
/*
* Common left-semi join result processing.
*/
switch (saveJoinResult) {
case MATCH:
allMatchs[allMatchCount++] = batchIndex;
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH
// isSingleValue " + equalKeySeriesIsSingleValue[equalKeySeriesCount] + " currentKey
// " + currentKey);
break;
case SPILL:
spills[spillCount] = batchIndex;
spillHashMapResultIndices[spillCount] = hashSetResultCount;
spillCount++;
break;
case NOMATCH:
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH"
// + " currentKey " + currentKey);
break;
}
} else {
// Series of equal keys.
switch (saveJoinResult) {
case MATCH:
allMatchs[allMatchCount++] = batchIndex;
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH
// duplicate");
break;
case SPILL:
spills[spillCount] = batchIndex;
spillHashMapResultIndices[spillCount] = hashSetResultCount;
spillCount++;
break;
case NOMATCH:
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH
// duplicate");
break;
}
}
}
if (haveSaveKey) {
// Update our counts for the last key.
switch (saveJoinResult) {
case MATCH:
// We have extracted the existence from the hash set result, so we don't keep it.
break;
case SPILL:
// We keep the hash set result for its spill information.
hashSetResultCount++;
break;
case NOMATCH:
break;
}
}
if (LOG.isDebugEnabled()) {
LOG.debug(
CLASS_NAME
+ " allMatchs "
+ intArrayToRangesString(allMatchs, allMatchCount)
+ " spills "
+ intArrayToRangesString(spills, spillCount)
+ " spillHashMapResultIndices "
+ intArrayToRangesString(spillHashMapResultIndices, spillCount)
+ " hashMapResults "
+ Arrays.toString(Arrays.copyOfRange(hashSetResults, 0, hashSetResultCount)));
}
finishLeftSemi(
batch, allMatchCount, spillCount, (VectorMapJoinHashTableResult[]) hashSetResults);
}
if (batch.size > 0) {
// Forward any remaining selected rows.
forwardBigTableBatch(batch);
}
} catch (IOException e) {
throw new HiveException(e);
} catch (Exception e) {
throw new HiveException(e);
}
}
@Override
/**
* Method to evaluate scalar-column operation in vectorized fashion.
*
* @batch a package of rows with each column stored in a vector
*/
public void evaluate(VectorizedRowBatch batch) {
if (childExpressions != null) {
super.evaluateChildren(batch);
}
// Input #2 is type date (epochDays).
LongColumnVector inputColVector2 = (LongColumnVector) batch.cols[colNum];
// Output is type HiveIntervalDayTime.
IntervalDayTimeColumnVector outputColVector =
(IntervalDayTimeColumnVector) batch.cols[outputColumn];
int[] sel = batch.selected;
boolean[] inputIsNull = inputColVector2.isNull;
boolean[] outputIsNull = outputColVector.isNull;
outputColVector.noNulls = inputColVector2.noNulls;
outputColVector.isRepeating = inputColVector2.isRepeating;
int n = batch.size;
long[] vector2 = inputColVector2.vector;
// return immediately if batch is empty
if (n == 0) {
return;
}
if (inputColVector2.isRepeating) {
scratchTimestamp2.setTime(DateWritable.daysToMillis((int) vector2[0]));
dtm.subtract(value, scratchTimestamp2, outputColVector.getScratchIntervalDayTime());
outputColVector.setFromScratchIntervalDayTime(0);
// Even if there are no nulls, we always copy over entry 0. Simplifies code.
outputIsNull[0] = inputIsNull[0];
} else if (inputColVector2.noNulls) {
if (batch.selectedInUse) {
for (int j = 0; j != n; j++) {
int i = sel[j];
scratchTimestamp2.setTime(DateWritable.daysToMillis((int) vector2[i]));
dtm.subtract(value, scratchTimestamp2, outputColVector.getScratchIntervalDayTime());
outputColVector.setFromScratchIntervalDayTime(i);
}
} else {
for (int i = 0; i != n; i++) {
scratchTimestamp2.setTime(DateWritable.daysToMillis((int) vector2[i]));
dtm.subtract(value, scratchTimestamp2, outputColVector.getScratchIntervalDayTime());
outputColVector.setFromScratchIntervalDayTime(i);
}
}
} else {
/* there are nulls */
if (batch.selectedInUse) {
for (int j = 0; j != n; j++) {
int i = sel[j];
scratchTimestamp2.setTime(DateWritable.daysToMillis((int) vector2[i]));
dtm.subtract(value, scratchTimestamp2, outputColVector.getScratchIntervalDayTime());
outputColVector.setFromScratchIntervalDayTime(i);
outputIsNull[i] = inputIsNull[i];
}
} else {
for (int i = 0; i != n; i++) {
scratchTimestamp2.setTime(DateWritable.daysToMillis((int) vector2[i]));
dtm.subtract(value, scratchTimestamp2, outputColVector.getScratchIntervalDayTime());
outputColVector.setFromScratchIntervalDayTime(i);
}
System.arraycopy(inputIsNull, 0, outputIsNull, 0, n);
}
}
NullUtil.setNullOutputEntriesColScalar(outputColVector, batch.selectedInUse, sel, n);
}
@Override
public void process(Object row, int tag) throws HiveException {
try {
VectorizedRowBatch batch = (VectorizedRowBatch) row;
alias = (byte) tag;
if (needCommonSetup) {
// Our one time process method initialization.
commonSetup(batch);
/*
* Initialize Single-Column String members for this specialized class.
*/
singleJoinColumn = bigTableKeyColumnMap[0];
needCommonSetup = false;
}
if (needHashTableSetup) {
// Setup our hash table specialization. It will be the first time the process
// method is called, or after a Hybrid Grace reload.
/*
* Get our Single-Column String hash map information for this specialized class.
*/
hashMap = (VectorMapJoinBytesHashMap) vectorMapJoinHashTable;
needHashTableSetup = false;
}
batchCounter++;
// Do the per-batch setup for an outer join.
outerPerBatchSetup(batch);
// For outer join, DO NOT apply filters yet. It is incorrect for outer join to
// apply the filter before hash table matching.
final int inputLogicalSize = batch.size;
if (inputLogicalSize == 0) {
if (LOG.isDebugEnabled()) {
LOG.debug(CLASS_NAME + " batch #" + batchCounter + " empty");
}
return;
}
// Perform any key expressions. Results will go into scratch columns.
if (bigTableKeyExpressions != null) {
for (VectorExpression ve : bigTableKeyExpressions) {
ve.evaluate(batch);
}
}
// We rebuild in-place the selected array with rows destine to be forwarded.
int numSel = 0;
/*
* Single-Column String specific declarations.
*/
// The one join column for this specialized class.
BytesColumnVector joinColVector = (BytesColumnVector) batch.cols[singleJoinColumn];
byte[][] vector = joinColVector.vector;
int[] start = joinColVector.start;
int[] length = joinColVector.length;
/*
* Single-Column String check for repeating.
*/
// Check single column for repeating.
boolean allKeyInputColumnsRepeating = joinColVector.isRepeating;
if (allKeyInputColumnsRepeating) {
/*
* Repeating.
*/
// All key input columns are repeating. Generate key once. Lookup once.
// Since the key is repeated, we must use entry 0 regardless of selectedInUse.
/*
* Single-Column String specific repeated lookup.
*/
JoinUtil.JoinResult joinResult;
if (!joinColVector.noNulls && joinColVector.isNull[0]) {
// Null key is no match for whole batch.
joinResult = JoinUtil.JoinResult.NOMATCH;
} else {
// Handle *repeated* join key, if found.
byte[] keyBytes = vector[0];
int keyStart = start[0];
int keyLength = length[0];
joinResult = hashMap.lookup(keyBytes, keyStart, keyLength, hashMapResults[0]);
}
/*
* Common repeated join result processing.
*/
if (LOG.isDebugEnabled()) {
LOG.debug(
CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name());
}
numSel = finishOuterRepeated(batch, joinResult, hashMapResults[0], scratch1);
} else {
/*
* NOT Repeating.
*/
if (LOG.isDebugEnabled()) {
LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated");
}
int selected[] = batch.selected;
boolean selectedInUse = batch.selectedInUse;
// For outer join we must apply the filter after match and cause some matches to become
// non-matches, we do not track non-matches here. Instead we remember all non spilled rows
// and compute non matches later in finishOuter.
int hashMapResultCount = 0;
int matchCount = 0;
int nonSpillCount = 0;
int spillCount = 0;
/*
* Single-Column String specific variables.
*/
int saveKeyBatchIndex = -1;
// We optimize performance by only looking up the first key in a series of equal keys.
boolean haveSaveKey = false;
JoinUtil.JoinResult saveJoinResult = JoinUtil.JoinResult.NOMATCH;
// Logical loop over the rows in the batch since the batch may have selected in use.
for (int logical = 0; logical < inputLogicalSize; logical++) {
int batchIndex = (selectedInUse ? selected[logical] : logical);
/*
* Single-Column String outer null detection.
*/
boolean isNull = !joinColVector.noNulls && joinColVector.isNull[batchIndex];
if (isNull) {
// Have that the NULL does not interfere with the current equal key series, if there
// is one. We do not set saveJoinResult.
//
// Let a current MATCH equal key series keep going, or
// Let a current SPILL equal key series keep going, or
// Let a current NOMATCH keep not matching.
// Remember non-matches for Outer Join.
nonSpills[nonSpillCount++] = batchIndex;
// LOG.debug(CLASS_NAME + " logical " + logical + " batchIndex " + batchIndex + "
// NULL");
} else {
/*
* Single-Column String outer get key.
*/
// Implicit -- use batchIndex.
/*
* Equal key series checking.
*/
if (!haveSaveKey
|| StringExpr.compare(
vector[saveKeyBatchIndex],
start[saveKeyBatchIndex],
length[saveKeyBatchIndex],
vector[batchIndex],
start[batchIndex],
length[batchIndex])
!= 0) {
// New key.
if (haveSaveKey) {
// Move on with our count(s).
switch (saveJoinResult) {
case MATCH:
case SPILL:
hashMapResultCount++;
break;
case NOMATCH:
break;
}
}
// Regardless of our matching result, we keep that information to make multiple use
// of it for a possible series of equal keys.
haveSaveKey = true;
/*
* Single-Column String specific save key.
*/
saveKeyBatchIndex = batchIndex;
/*
* Single-Column Long specific lookup key.
*/
byte[] keyBytes = vector[batchIndex];
int keyStart = start[batchIndex];
int keyLength = length[batchIndex];
saveJoinResult =
hashMap.lookup(keyBytes, keyStart, keyLength, hashMapResults[hashMapResultCount]);
// LOG.debug(CLASS_NAME + " logical " + logical + " batchIndex " + batchIndex + " New
// Key " + saveJoinResult.name());
} else {
// LOG.debug(CLASS_NAME + " logical " + logical + " batchIndex " + batchIndex + " Key
// Continues " + saveJoinResult.name());
}
/*
* Common outer join result processing.
*/
switch (saveJoinResult) {
case MATCH:
matchs[matchCount] = batchIndex;
matchHashMapResultIndices[matchCount] = hashMapResultCount;
matchCount++;
nonSpills[nonSpillCount++] = batchIndex;
break;
case SPILL:
spills[spillCount] = batchIndex;
spillHashMapResultIndices[spillCount] = hashMapResultCount;
spillCount++;
break;
case NOMATCH:
nonSpills[nonSpillCount++] = batchIndex;
// VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH
// duplicate");
break;
}
}
}
if (haveSaveKey) {
// Account for last equal key sequence.
switch (saveJoinResult) {
case MATCH:
case SPILL:
hashMapResultCount++;
break;
case NOMATCH:
break;
}
}
if (LOG.isDebugEnabled()) {
LOG.debug(
CLASS_NAME
+ " batch #"
+ batchCounter
+ " matchs "
+ intArrayToRangesString(matchs, matchCount)
+ " matchHashMapResultIndices "
+ intArrayToRangesString(matchHashMapResultIndices, matchCount)
+ " nonSpills "
+ intArrayToRangesString(nonSpills, nonSpillCount)
+ " spills "
+ intArrayToRangesString(spills, spillCount)
+ " spillHashMapResultIndices "
+ intArrayToRangesString(spillHashMapResultIndices, spillCount)
+ " hashMapResults "
+ Arrays.toString(Arrays.copyOfRange(hashMapResults, 0, hashMapResultCount)));
}
// We will generate results for all matching and non-matching rows.
// Note that scratch1 is undefined at this point -- it's preallocated storage.
numSel =
finishOuter(
batch,
matchs,
matchHashMapResultIndices,
matchCount,
nonSpills,
nonSpillCount,
spills,
spillHashMapResultIndices,
spillCount,
hashMapResults,
hashMapResultCount,
scratch1);
}
batch.selectedInUse = true;
batch.size = numSel;
if (batch.size > 0) {
// Forward any remaining selected rows.
forwardBigTableBatch(batch);
}
} catch (IOException e) {
throw new HiveException(e);
} catch (Exception e) {
throw new HiveException(e);
}
}