use of org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc in project hive by apache.
the class ExprProcFactory method getExprString.
/**
* Get the expression string of an expression node.
*/
public static String getExprString(RowSchema rs, ExprNodeDesc expr, LineageCtx lctx, Operator<? extends OperatorDesc> inpOp, Predicate cond) {
if (expr instanceof ExprNodeColumnDesc) {
ExprNodeColumnDesc col = (ExprNodeColumnDesc) expr;
String internalName = col.getColumn();
String alias = internalName;
String tabAlias = col.getTabAlias();
ColumnInfo ci = rs.getColumnInfo(internalName);
if (ci != null) {
if (ci.getAlias() != null) {
alias = ci.getAlias();
}
if (ci.getTabAlias() != null) {
tabAlias = ci.getTabAlias();
}
}
Dependency dep = lctx.getIndex().getDependency(inpOp, internalName);
if ((tabAlias == null || tabAlias.startsWith("_") || tabAlias.startsWith("$")) && (dep != null && dep.getType() == DependencyType.SIMPLE)) {
Set<BaseColumnInfo> baseCols = dep.getBaseCols();
if (baseCols != null && !baseCols.isEmpty()) {
BaseColumnInfo baseCol = baseCols.iterator().next();
tabAlias = baseCol.getTabAlias().getAlias();
alias = baseCol.getColumn().getName();
}
}
if (tabAlias != null && tabAlias.length() > 0 && !tabAlias.startsWith("_") && !tabAlias.startsWith("$")) {
if (cond != null && !findSourceColumn(lctx, cond, tabAlias, alias) && dep != null) {
cond.getBaseCols().addAll(dep.getBaseCols());
}
return tabAlias + "." + alias;
}
if (dep != null) {
if (cond != null) {
cond.getBaseCols().addAll(dep.getBaseCols());
}
if (dep.getExpr() != null) {
return dep.getExpr();
}
}
if (alias.startsWith("_")) {
ci = inpOp.getSchema().getColumnInfo(internalName);
if (ci != null && ci.getAlias() != null) {
alias = ci.getAlias();
}
}
return alias;
} else if (expr instanceof ExprNodeGenericFuncDesc) {
ExprNodeGenericFuncDesc func = (ExprNodeGenericFuncDesc) expr;
List<ExprNodeDesc> children = func.getChildren();
String[] childrenExprStrings = new String[children.size()];
for (int i = 0; i < childrenExprStrings.length; i++) {
childrenExprStrings[i] = getExprString(rs, children.get(i), lctx, inpOp, cond);
}
return func.getGenericUDF().getDisplayString(childrenExprStrings);
}
return expr.getExprString();
}
use of org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc in project hive by apache.
the class BucketingSortingOpProcFactory method findBucketingSortingColumns.
/**
* For each expression, check if it represents a column known to be bucketed/sorted.
*
* The methods setBucketingColsIfComplete and setSortingColsIfComplete should be used to assign
* the values of newBucketCols and newSortCols as the bucketing/sorting columns of this operator
* because these arrays may contain nulls indicating that the output of this operator is not
* bucketed/sorted.
*
* @param exprs - list of expression
* @param colInfos - list of column infos
* @param bucketCols - list of bucketed columns from the input
* @param sortCols - list of sorted columns from the input
* @param newBucketCols - an array of bucket columns which should be the same length as
* bucketCols, updated such that the bucketed column(s) at index i in bucketCols became
* the bucketed column(s) at index i of newBucketCols in the output
* @param newSortCols - an array of sort columns which should be the same length as
* sortCols, updated such that the sorted column(s) at index i in sortCols became
* the sorted column(s) at index i of sortCols in the output
* @param colInfosOffset - the expressions are known to be represented by column infos
* beginning at this index
*/
private static void findBucketingSortingColumns(List<ExprNodeDesc> exprs, List<ColumnInfo> colInfos, List<BucketCol> bucketCols, List<SortCol> sortCols, BucketCol[] newBucketCols, SortCol[] newSortCols, int colInfosOffset) {
for (int cnt = 0; cnt < exprs.size(); cnt++) {
ExprNodeDesc expr = exprs.get(cnt);
// voids any assumptions
if (!(expr instanceof ExprNodeColumnDesc)) {
continue;
}
ExprNodeColumnDesc columnExpr = (ExprNodeColumnDesc) expr;
int colInfosIndex = cnt + colInfosOffset;
if (newBucketCols != null) {
int bucketIndex = indexOfColName(bucketCols, columnExpr.getColumn());
if (bucketIndex != -1) {
if (newBucketCols[bucketIndex] == null) {
newBucketCols[bucketIndex] = new BucketCol();
}
newBucketCols[bucketIndex].addAlias(colInfos.get(colInfosIndex).getInternalName(), colInfosIndex);
}
}
if (newSortCols != null) {
int sortIndex = indexOfColName(sortCols, columnExpr.getColumn());
if (sortIndex != -1) {
if (newSortCols[sortIndex] == null) {
newSortCols[sortIndex] = new SortCol(sortCols.get(sortIndex).getSortOrder());
}
newSortCols[sortIndex].addAlias(colInfos.get(colInfosIndex).getInternalName(), colInfosIndex);
}
}
}
}
use of org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc in project hive by apache.
the class GenMRSkewJoinProcessor method processSkewJoin.
/**
* Create tasks for processing skew joins. The idea is (HIVE-964) to use
* separated jobs and map-joins to handle skew joins.
* <p>
* <ul>
* <li>
* Number of mr jobs to handle skew keys is the number of table minus 1 (we
* can stream the last table, so big keys in the last table will not be a
* problem).
* <li>
* At runtime in Join, we output big keys in one table into one corresponding
* directories, and all same keys in other tables into different dirs(one for
* each table). The directories will look like:
* <ul>
* <li>
* dir-T1-bigkeys(containing big keys in T1), dir-T2-keys(containing keys
* which is big in T1),dir-T3-keys(containing keys which is big in T1), ...
* <li>
* dir-T1-keys(containing keys which is big in T2), dir-T2-bigkeys(containing
* big keys in T2),dir-T3-keys(containing keys which is big in T2), ...
* <li>
* dir-T1-keys(containing keys which is big in T3), dir-T2-keys(containing big
* keys in T3),dir-T3-bigkeys(containing keys which is big in T3), ... .....
* </ul>
* </ul>
* For each table, we launch one mapjoin job, taking the directory containing
* big keys in this table and corresponding dirs in other tables as input.
* (Actally one job for one row in the above.)
*
* <p>
* For more discussions, please check
* https://issues.apache.org/jira/browse/HIVE-964.
*/
@SuppressWarnings("unchecked")
public static void processSkewJoin(JoinOperator joinOp, Task<? extends Serializable> currTask, ParseContext parseCtx) throws SemanticException {
// now does not work with outer joins
if (!GenMRSkewJoinProcessor.skewJoinEnabled(parseCtx.getConf(), joinOp)) {
return;
}
List<Task<? extends Serializable>> children = currTask.getChildTasks();
Path baseTmpDir = parseCtx.getContext().getMRTmpPath();
JoinDesc joinDescriptor = joinOp.getConf();
Map<Byte, List<ExprNodeDesc>> joinValues = joinDescriptor.getExprs();
int numAliases = joinValues.size();
Map<Byte, Path> bigKeysDirMap = new HashMap<Byte, Path>();
Map<Byte, Map<Byte, Path>> smallKeysDirMap = new HashMap<Byte, Map<Byte, Path>>();
Map<Byte, Path> skewJoinJobResultsDir = new HashMap<Byte, Path>();
Byte[] tags = joinDescriptor.getTagOrder();
for (int i = 0; i < numAliases; i++) {
Byte alias = tags[i];
bigKeysDirMap.put(alias, getBigKeysDir(baseTmpDir, alias));
Map<Byte, Path> smallKeysMap = new HashMap<Byte, Path>();
smallKeysDirMap.put(alias, smallKeysMap);
for (Byte src2 : tags) {
if (!src2.equals(alias)) {
smallKeysMap.put(src2, getSmallKeysDir(baseTmpDir, alias, src2));
}
}
skewJoinJobResultsDir.put(alias, getBigKeysSkewJoinResultDir(baseTmpDir, alias));
}
joinDescriptor.setHandleSkewJoin(true);
joinDescriptor.setBigKeysDirMap(bigKeysDirMap);
joinDescriptor.setSmallKeysDirMap(smallKeysDirMap);
joinDescriptor.setSkewKeyDefinition(HiveConf.getIntVar(parseCtx.getConf(), HiveConf.ConfVars.HIVESKEWJOINKEY));
HashMap<Path, Task<? extends Serializable>> bigKeysDirToTaskMap = new HashMap<Path, Task<? extends Serializable>>();
List<Serializable> listWorks = new ArrayList<Serializable>();
List<Task<? extends Serializable>> listTasks = new ArrayList<Task<? extends Serializable>>();
MapredWork currPlan = (MapredWork) currTask.getWork();
TableDesc keyTblDesc = (TableDesc) currPlan.getReduceWork().getKeyDesc().clone();
List<String> joinKeys = Utilities.getColumnNames(keyTblDesc.getProperties());
List<String> joinKeyTypes = Utilities.getColumnTypes(keyTblDesc.getProperties());
Map<Byte, TableDesc> tableDescList = new HashMap<Byte, TableDesc>();
Map<Byte, RowSchema> rowSchemaList = new HashMap<Byte, RowSchema>();
Map<Byte, List<ExprNodeDesc>> newJoinValues = new HashMap<Byte, List<ExprNodeDesc>>();
Map<Byte, List<ExprNodeDesc>> newJoinKeys = new HashMap<Byte, List<ExprNodeDesc>>();
// used for create mapJoinDesc, should be in order
List<TableDesc> newJoinValueTblDesc = new ArrayList<TableDesc>();
for (Byte tag : tags) {
newJoinValueTblDesc.add(null);
}
for (int i = 0; i < numAliases; i++) {
Byte alias = tags[i];
List<ExprNodeDesc> valueCols = joinValues.get(alias);
String colNames = "";
String colTypes = "";
int columnSize = valueCols.size();
List<ExprNodeDesc> newValueExpr = new ArrayList<ExprNodeDesc>();
List<ExprNodeDesc> newKeyExpr = new ArrayList<ExprNodeDesc>();
ArrayList<ColumnInfo> columnInfos = new ArrayList<ColumnInfo>();
boolean first = true;
for (int k = 0; k < columnSize; k++) {
TypeInfo type = valueCols.get(k).getTypeInfo();
// any name, it does not matter.
String newColName = i + "_VALUE_" + k;
ColumnInfo columnInfo = new ColumnInfo(newColName, type, alias.toString(), false);
columnInfos.add(columnInfo);
newValueExpr.add(new ExprNodeColumnDesc(columnInfo));
if (!first) {
colNames = colNames + ",";
colTypes = colTypes + ",";
}
first = false;
colNames = colNames + newColName;
colTypes = colTypes + valueCols.get(k).getTypeString();
}
// we are putting join keys at last part of the spilled table
for (int k = 0; k < joinKeys.size(); k++) {
if (!first) {
colNames = colNames + ",";
colTypes = colTypes + ",";
}
first = false;
colNames = colNames + joinKeys.get(k);
colTypes = colTypes + joinKeyTypes.get(k);
ColumnInfo columnInfo = new ColumnInfo(joinKeys.get(k), TypeInfoFactory.getPrimitiveTypeInfo(joinKeyTypes.get(k)), alias.toString(), false);
columnInfos.add(columnInfo);
newKeyExpr.add(new ExprNodeColumnDesc(columnInfo));
}
newJoinValues.put(alias, newValueExpr);
newJoinKeys.put(alias, newKeyExpr);
tableDescList.put(alias, Utilities.getTableDesc(colNames, colTypes));
rowSchemaList.put(alias, new RowSchema(columnInfos));
// construct value table Desc
String valueColNames = "";
String valueColTypes = "";
first = true;
for (int k = 0; k < columnSize; k++) {
// any name, it does not matter.
String newColName = i + "_VALUE_" + k;
if (!first) {
valueColNames = valueColNames + ",";
valueColTypes = valueColTypes + ",";
}
valueColNames = valueColNames + newColName;
valueColTypes = valueColTypes + valueCols.get(k).getTypeString();
first = false;
}
newJoinValueTblDesc.set(Byte.valueOf((byte) i), Utilities.getTableDesc(valueColNames, valueColTypes));
}
joinDescriptor.setSkewKeysValuesTables(tableDescList);
joinDescriptor.setKeyTableDesc(keyTblDesc);
for (int i = 0; i < numAliases - 1; i++) {
Byte src = tags[i];
MapWork newPlan = PlanUtils.getMapRedWork().getMapWork();
// This code has been only added for testing
boolean mapperCannotSpanPartns = parseCtx.getConf().getBoolVar(HiveConf.ConfVars.HIVE_MAPPER_CANNOT_SPAN_MULTIPLE_PARTITIONS);
newPlan.setMapperCannotSpanPartns(mapperCannotSpanPartns);
MapredWork clonePlan = SerializationUtilities.clonePlan(currPlan);
Operator<? extends OperatorDesc>[] parentOps = new TableScanOperator[tags.length];
for (int k = 0; k < tags.length; k++) {
Operator<? extends OperatorDesc> ts = GenMapRedUtils.createTemporaryTableScanOperator(joinOp.getCompilationOpContext(), rowSchemaList.get((byte) k));
((TableScanOperator) ts).setTableDescSkewJoin(tableDescList.get((byte) k));
parentOps[k] = ts;
}
Operator<? extends OperatorDesc> tblScan_op = parentOps[i];
ArrayList<String> aliases = new ArrayList<String>();
String alias = src.toString().intern();
aliases.add(alias);
Path bigKeyDirPath = bigKeysDirMap.get(src);
newPlan.addPathToAlias(bigKeyDirPath, aliases);
newPlan.getAliasToWork().put(alias, tblScan_op);
PartitionDesc part = new PartitionDesc(tableDescList.get(src), null);
newPlan.addPathToPartitionInfo(bigKeyDirPath, part);
newPlan.getAliasToPartnInfo().put(alias, part);
Operator<? extends OperatorDesc> reducer = clonePlan.getReduceWork().getReducer();
assert reducer instanceof JoinOperator;
JoinOperator cloneJoinOp = (JoinOperator) reducer;
String dumpFilePrefix = "mapfile" + PlanUtils.getCountForMapJoinDumpFilePrefix();
MapJoinDesc mapJoinDescriptor = new MapJoinDesc(newJoinKeys, keyTblDesc, newJoinValues, newJoinValueTblDesc, newJoinValueTblDesc, joinDescriptor.getOutputColumnNames(), i, joinDescriptor.getConds(), joinDescriptor.getFilters(), joinDescriptor.getNoOuterJoin(), dumpFilePrefix, joinDescriptor.getMemoryMonitorInfo(), joinDescriptor.getInMemoryDataSize());
mapJoinDescriptor.setTagOrder(tags);
mapJoinDescriptor.setHandleSkewJoin(false);
mapJoinDescriptor.setNullSafes(joinDescriptor.getNullSafes());
mapJoinDescriptor.setColumnExprMap(joinDescriptor.getColumnExprMap());
MapredLocalWork localPlan = new MapredLocalWork(new LinkedHashMap<String, Operator<? extends OperatorDesc>>(), new LinkedHashMap<String, FetchWork>());
Map<Byte, Path> smallTblDirs = smallKeysDirMap.get(src);
for (int j = 0; j < numAliases; j++) {
if (j == i) {
continue;
}
Byte small_alias = tags[j];
Operator<? extends OperatorDesc> tblScan_op2 = parentOps[j];
localPlan.getAliasToWork().put(small_alias.toString(), tblScan_op2);
Path tblDir = smallTblDirs.get(small_alias);
localPlan.getAliasToFetchWork().put(small_alias.toString(), new FetchWork(tblDir, tableDescList.get(small_alias)));
}
newPlan.setMapRedLocalWork(localPlan);
// construct a map join and set it as the child operator of tblScan_op
MapJoinOperator mapJoinOp = (MapJoinOperator) OperatorFactory.getAndMakeChild(joinOp.getCompilationOpContext(), mapJoinDescriptor, (RowSchema) null, parentOps);
// change the children of the original join operator to point to the map
// join operator
List<Operator<? extends OperatorDesc>> childOps = cloneJoinOp.getChildOperators();
for (Operator<? extends OperatorDesc> childOp : childOps) {
childOp.replaceParent(cloneJoinOp, mapJoinOp);
}
mapJoinOp.setChildOperators(childOps);
HiveConf jc = new HiveConf(parseCtx.getConf(), GenMRSkewJoinProcessor.class);
newPlan.setNumMapTasks(HiveConf.getIntVar(jc, HiveConf.ConfVars.HIVESKEWJOINMAPJOINNUMMAPTASK));
newPlan.setMinSplitSize(HiveConf.getLongVar(jc, HiveConf.ConfVars.HIVESKEWJOINMAPJOINMINSPLIT));
newPlan.setInputformat(HiveInputFormat.class.getName());
MapredWork w = new MapredWork();
w.setMapWork(newPlan);
Task<? extends Serializable> skewJoinMapJoinTask = TaskFactory.get(w);
skewJoinMapJoinTask.setFetchSource(currTask.isFetchSource());
bigKeysDirToTaskMap.put(bigKeyDirPath, skewJoinMapJoinTask);
listWorks.add(skewJoinMapJoinTask.getWork());
listTasks.add(skewJoinMapJoinTask);
}
if (children != null) {
for (Task<? extends Serializable> tsk : listTasks) {
for (Task<? extends Serializable> oldChild : children) {
tsk.addDependentTask(oldChild);
}
}
currTask.setChildTasks(new ArrayList<Task<? extends Serializable>>());
for (Task<? extends Serializable> oldChild : children) {
oldChild.getParentTasks().remove(currTask);
}
listTasks.addAll(children);
}
ConditionalResolverSkewJoinCtx context = new ConditionalResolverSkewJoinCtx(bigKeysDirToTaskMap, children);
ConditionalWork cndWork = new ConditionalWork(listWorks);
ConditionalTask cndTsk = (ConditionalTask) TaskFactory.get(cndWork);
cndTsk.setListTasks(listTasks);
cndTsk.setResolver(new ConditionalResolverSkewJoin());
cndTsk.setResolverCtx(context);
currTask.setChildTasks(new ArrayList<Task<? extends Serializable>>());
currTask.addDependentTask(cndTsk);
return;
}
use of org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc in project hive by apache.
the class VectorGroupByOperatorBench method buildAggregationDesc.
private AggregationDesc buildAggregationDesc(String aggregate, GenericUDAFEvaluator.Mode mode, String column, TypeInfo typeInfo) throws SemanticException {
ExprNodeDesc inputColumn = new ExprNodeColumnDesc(typeInfo, column, "table", false);
ArrayList<ExprNodeDesc> params = new ArrayList<ExprNodeDesc>();
params.add(inputColumn);
AggregationDesc agg = new AggregationDesc();
ObjectInspector oi = TypeInfoUtils.getStandardJavaObjectInspectorFromTypeInfo(typeInfo);
GenericUDAFEvaluator genericUDAFEvaluator = FunctionRegistry.getGenericUDAFEvaluator(aggregate, ImmutableList.of(oi).asList(), false, false);
agg.setGenericUDAFEvaluator(genericUDAFEvaluator);
if (aggregate.equals("bloom_filter")) {
GenericUDAFBloomFilter.GenericUDAFBloomFilterEvaluator udafBloomFilterEvaluator = (GenericUDAFBloomFilter.GenericUDAFBloomFilterEvaluator) agg.getGenericUDAFEvaluator();
udafBloomFilterEvaluator.setHintEntries(10000);
}
agg.setGenericUDAFName(aggregate);
agg.setMode(mode);
agg.setParameters(params);
return agg;
}
use of org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc in project hive by apache.
the class VectorSelectOperatorBench method setup.
@Setup
public void setup(Blackhole bh) throws HiveException {
HiveConf hconf = new HiveConf();
List<String> columns = new ArrayList<String>();
columns.add("a");
columns.add("b");
columns.add("c");
VectorizationContext vc = new VectorizationContext("name", columns);
selDesc = new SelectDesc(false);
List<ExprNodeDesc> colList = new ArrayList<ExprNodeDesc>();
ExprNodeColumnDesc colDesc1 = new ExprNodeColumnDesc(Long.class, "a", "table", false);
ExprNodeColumnDesc colDesc2 = new ExprNodeColumnDesc(Long.class, "b", "table", false);
ExprNodeColumnDesc colDesc3 = new ExprNodeColumnDesc(Long.class, "c", "table", false);
ExprNodeGenericFuncDesc plusDesc = new ExprNodeGenericFuncDesc();
GenericUDF gudf = new GenericUDFOPPlus();
plusDesc.setGenericUDF(gudf);
List<ExprNodeDesc> children = new ArrayList<ExprNodeDesc>();
children.add(colDesc1);
children.add(colDesc2);
plusDesc.setChildren(children);
plusDesc.setTypeInfo(TypeInfoFactory.longTypeInfo);
colList.add(plusDesc);
colList.add(colDesc3);
selDesc.setColList(colList);
List<String> outputColNames = new ArrayList<String>();
outputColNames.add("_col0");
outputColNames.add("_col1");
selDesc.setOutputColumnNames(outputColNames);
VectorSelectDesc vectorSelectDesc = new VectorSelectDesc();
selDesc.setVectorDesc(vectorSelectDesc);
List<ExprNodeDesc> selectColList = selDesc.getColList();
VectorExpression[] vectorSelectExprs = new VectorExpression[selectColList.size()];
for (int i = 0; i < selectColList.size(); i++) {
ExprNodeDesc expr = selectColList.get(i);
VectorExpression ve = vc.getVectorExpression(expr);
vectorSelectExprs[i] = ve;
}
vectorSelectDesc.setSelectExpressions(vectorSelectExprs);
vectorSelectDesc.setProjectedOutputColumns(new int[] { 3, 2 });
CompilationOpContext opContext = new CompilationOpContext();
vso = new VectorSelectOperator(opContext, selDesc, vc, vectorSelectDesc);
// to trigger vectorForward
child = new ArrayList<>();
child.add(new BlackholeOperator(opContext, bh));
child.add(new BlackholeOperator(opContext, bh));
vso.initialize(hconf, null);
vrg = VectorizedRowGroupGenUtil.getVectorizedRowBatch(VectorizedRowBatch.DEFAULT_SIZE, 4, 17);
}
Aggregations