diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java index e7687be..10f16ca 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -297,6 +297,8 @@ public void analyzeInternal(ASTNode ast) throws SemanticException { public RelNode genLogicalPlan(ASTNode ast) throws SemanticException { LOG.info("Starting generating logical plan"); PreCboCtx cboCtx = new PreCboCtx(); + //change the location of position alias process here + processPositionAlias(ast); if (!genResolvedParseTree(ast, cboCtx)) { return null; } diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index 9c37af8..9eafb0b 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -10903,7 +10903,7 @@ boolean genResolvedParseTree(ASTNode ast, PlannerContext plannerCtx) throws Sema ctesExpanded = new ArrayList(); // 1. analyze and process the position alias - processPositionAlias(ast); + // step processPositionAlias out of genResolvedParseTree // 2. analyze create table command if (ast.getToken().getType() == HiveParser.TOK_CREATETABLE) { @@ -11019,6 +11019,8 @@ Operator genOPTree(ASTNode ast, PlannerContext plannerCtx) throws SemanticExcept void analyzeInternal(ASTNode ast, PlannerContext plannerCtx) throws SemanticException { // 1. Generate Resolved Parse tree from syntax tree LOG.info("Starting Semantic Analysis"); + //change the location of position alias process here + processPositionAlias(ast); if (!genResolvedParseTree(ast, plannerCtx)) { return; } @@ -11032,6 +11034,8 @@ void analyzeInternal(ASTNode ast, PlannerContext plannerCtx) throws SemanticExce if (tree != ast) { ctx.setSkipTableMasking(true); init(true); + //change the location of position alias process here + processPositionAlias(tree); genResolvedParseTree(tree, plannerCtx); if (this instanceof CalcitePlanner) { ((CalcitePlanner) this).resetCalciteConfiguration(); @@ -12258,7 +12262,7 @@ private void validateCreateView() } // Process the position alias in GROUPBY and ORDERBY - private void processPositionAlias(ASTNode ast) throws SemanticException { + public void processPositionAlias(ASTNode ast) throws SemanticException { boolean isBothByPos = HiveConf.getBoolVar(conf, ConfVars.HIVE_GROUPBY_ORDERBY_POSITION_ALIAS); boolean isGbyByPos = isBothByPos || HiveConf.getBoolVar(conf, ConfVars.HIVE_GROUPBY_POSITION_ALIAS); diff --git ql/src/test/queries/clientpositive/position_alias_test_1.q ql/src/test/queries/clientpositive/position_alias_test_1.q new file mode 100644 index 0000000..599bc08 --- /dev/null +++ ql/src/test/queries/clientpositive/position_alias_test_1.q @@ -0,0 +1,18 @@ +create table alias_test_01(a INT, b STRING) ; + create table alias_test_02(a INT, b STRING) ; + create table alias_test_03(a INT, b STRING) ; + set hive.groupby.position.alias = true; + set hive.cbo.enable=true; + + + explain + select * from + alias_test_01 alias01 + left join + ( + select 2017 as a, b from alias_test_02 group by 1, 2 + ) alias02 + on alias01.a = alias02.a + left join + alias_test_03 alias03 + on alias01.a = alias03.a; \ No newline at end of file diff --git ql/src/test/results/clientpositive/position_alias_test_1.q.out ql/src/test/results/clientpositive/position_alias_test_1.q.out new file mode 100644 index 0000000..9053bf1 --- /dev/null +++ ql/src/test/results/clientpositive/position_alias_test_1.q.out @@ -0,0 +1,148 @@ +PREHOOK: query: create table alias_test_01(a INT, b STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@alias_test_01 +POSTHOOK: query: create table alias_test_01(a INT, b STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@alias_test_01 +PREHOOK: query: create table alias_test_02(a INT, b STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@alias_test_02 +POSTHOOK: query: create table alias_test_02(a INT, b STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@alias_test_02 +PREHOOK: query: create table alias_test_03(a INT, b STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@alias_test_03 +POSTHOOK: query: create table alias_test_03(a INT, b STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@alias_test_03 +PREHOOK: query: explain + select * from + alias_test_01 alias01 + left join + ( + select 2017 as a, b from alias_test_02 group by 1, 2 + ) alias02 + on alias01.a = alias02.a + left join + alias_test_03 alias03 + on alias01.a = alias03.a +PREHOOK: type: QUERY +POSTHOOK: query: explain + select * from + alias_test_01 alias01 + left join + ( + select 2017 as a, b from alias_test_02 group by 1, 2 + ) alias02 + on alias01.a = alias02.a + left join + alias_test_03 alias03 + on alias01.a = alias03.a +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: alias_test_02 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: b (type: string) + outputColumnNames: b + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Group By Operator + keys: 2017 (type: int), b (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: 2017 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: 2017 (type: int), _col1 (type: string) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Operator Tree: + Group By Operator + keys: 2017 (type: int), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 2017 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: string) + TableScan + alias: alias01 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: a (type: int) + sort order: + + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: b (type: string) + TableScan + alias: alias03 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: a (type: int) + sort order: + + Map-reduce partition columns: a (type: int) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: b (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join0 to 1 + Left Outer Join0 to 2 + keys: + 0 a (type: int) + 1 _col0 (type: int) + 2 a (type: int) + outputColumnNames: _col0, _col1, _col5, _col6, _col7, _col8 + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: int), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +