HIVE-20102: Add a couple of additional tests for query parsing (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ParseDriver.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ParseDriver.java
index bda3c21..895c2f2 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ParseDriver.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ParseDriver.java
@@ -153,6 +153,17 @@
};
@Override
+ public Object dupTree(Object t, Object parent) {
+ // Overriden to copy start index / end index, that is needed through optimization,
+ // e.g., for masking/filtering
+ ASTNode astNode = (ASTNode) t;
+ ASTNode astNodeCopy = (ASTNode) super.dupTree(t, parent);
+ astNodeCopy.setTokenStartIndex(astNode.getTokenStartIndex());
+ astNodeCopy.setTokenStopIndex(astNode.getTokenStopIndex());
+ return astNodeCopy;
+ }
+
+ @Override
public Object errorNode(TokenStream input, Token start, Token stop, RecognitionException e) {
return new ASTErrorNode(input, start, stop, e);
};
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/QB.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/QB.java
index 64b3541..a2f6fbb 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/QB.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/QB.java
@@ -423,6 +423,10 @@
return viewDesc != null && !viewDesc.isMaterialized();
}
+ public boolean isMultiDestQuery() {
+ return qbp != null && qbp.getClauseNamesForDest() != null && qbp.getClauseNamesForDest().size() > 1;
+ }
+
public HashMap<String, Table> getViewToTabSchema() {
return viewAliasToViewSchema;
}
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
index 37e1a73..5044480 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
@@ -12117,8 +12117,9 @@
}
void analyzeInternal(ASTNode ast, PlannerContextFactory pcf) throws SemanticException {
- // 1. Generate Resolved Parse tree from syntax tree
LOG.info("Starting Semantic Analysis");
+ // 1. Generate Resolved Parse tree from syntax tree
+ boolean needsTransform = needsTransform();
//change the location of position alias process here
processPositionAlias(ast);
PlannerContext plannerCtx = pcf.create();
@@ -12138,7 +12139,6 @@
// Otherwise we have to wait until after the masking/filtering step.
boolean isCacheEnabled = isResultsCacheEnabled();
QueryResultsCache.LookupInfo lookupInfo = null;
- boolean needsTransform = needsTransform();
if (isCacheEnabled && !needsTransform && queryTypeCanUseCache()) {
lookupInfo = createLookupInfoForQuery(ast);
if (checkResultsCache(lookupInfo)) {
@@ -12146,32 +12146,45 @@
}
}
+ ASTNode astForMasking;
+ if (isCBOExecuted() && needsTransform &&
+ (qb.isCTAS() || qb.isView() || qb.isMaterializedView() || qb.isMultiDestQuery())) {
+ // If we use CBO and we may apply masking/filtering policies, we create a copy of the ast.
+ // The reason is that the generation of the operator tree may modify the initial ast,
+ // but if we need to parse for a second time, we would like to parse the unmodified ast.
+ astForMasking = (ASTNode) ParseDriver.adaptor.dupTree(ast);
+ } else {
+ astForMasking = ast;
+ }
+
// 2. Gen OP Tree from resolved Parse Tree
Operator sinkOp = genOPTree(ast, plannerCtx);
+ boolean usesMasking = false;
if (!unparseTranslator.isEnabled() &&
(tableMask.isEnabled() && analyzeRewrite == null)) {
// Here we rewrite the * and also the masking table
- ASTNode tree = rewriteASTWithMaskAndFilter(tableMask, ast, ctx.getTokenRewriteStream(),
+ ASTNode rewrittenAST = rewriteASTWithMaskAndFilter(tableMask, astForMasking, ctx.getTokenRewriteStream(),
ctx, db, tabNameToTabObject, ignoredTokens);
- if (tree != ast) {
+ if (astForMasking != rewrittenAST) {
+ usesMasking = true;
plannerCtx = pcf.create();
ctx.setSkipTableMasking(true);
init(true);
//change the location of position alias process here
- processPositionAlias(tree);
- genResolvedParseTree(tree, plannerCtx);
+ processPositionAlias(rewrittenAST);
+ genResolvedParseTree(rewrittenAST, plannerCtx);
if (this instanceof CalcitePlanner) {
((CalcitePlanner) this).resetCalciteConfiguration();
}
- sinkOp = genOPTree(tree, plannerCtx);
+ sinkOp = genOPTree(rewrittenAST, plannerCtx);
}
}
// Check query results cache
- // In the case that row or column masking/filtering was required, the cache must be checked
- // here, after applying the masking/filtering rewrite rules to the AST.
- if (isCacheEnabled && needsTransform && queryTypeCanUseCache()) {
+ // In the case that row or column masking/filtering was required, we do not support caching.
+ // TODO: Enable caching for queries with masking/filtering
+ if (isCacheEnabled && needsTransform && !usesMasking && queryTypeCanUseCache()) {
lookupInfo = createLookupInfoForQuery(ast);
if (checkResultsCache(lookupInfo)) {
return;
diff --git a/ql/src/test/queries/clientpositive/masking_13.q b/ql/src/test/queries/clientpositive/masking_13.q
new file mode 100644
index 0000000..bb050b5
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/masking_13.q
@@ -0,0 +1,28 @@
+--! qt:dataset:srcpart
+--! qt:dataset:src
+set hive.mapred.mode=nonstrict;
+set hive.security.authorization.manager=org.apache.hadoop.hive.ql.security.authorization.plugin.sqlstd.SQLStdHiveAuthorizerFactoryForTest;
+
+create table masking_test as select cast(key as int) as key, value from src;
+
+explain select * from masking_test;
+select * from masking_test;
+
+create table new_masking_test_nx as
+select * from masking_test;
+select * from new_masking_test_nx;
+
+create view `masking_test_view` as select key from `masking_test`;
+
+explain
+select key from `masking_test_view`;
+select key from `masking_test_view`;
+
+create table `my_table_masked` (key int);
+insert into `my_table_masked` select key from `masking_test_view`;
+select * from `my_table_masked`;
+
+create table new_masking_test_nx_2 as
+select * from masking_test_view;
+
+select * from new_masking_test_nx_2;
diff --git a/ql/src/test/queries/clientpositive/results_cache_with_masking.q b/ql/src/test/queries/clientpositive/results_cache_with_masking.q
index 1bb9c9a..688ea24 100644
--- a/ql/src/test/queries/clientpositive/results_cache_with_masking.q
+++ b/ql/src/test/queries/clientpositive/results_cache_with_masking.q
@@ -11,7 +11,8 @@
select key, count(*) from masking_test_n7 group by key;
select key, count(*) from masking_test_n7 group by key;
--- This time we should use the cache
+-- It will not use the cache as it is masked
+-- TODO: We should use the cache
explain
select key, count(*) from masking_test_n7 group by key;
select key, count(*) from masking_test_n7 group by key;
diff --git a/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out b/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out
index 20a2e8d..e0e48b0 100644
--- a/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out
+++ b/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out
@@ -92,15 +92,62 @@
select key, count(*) from masking_test_n7 group by key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-0 is a root stage
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: masking_test_n7
+ filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean)
+ Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((key % 2) = 0) and (key < 10)) (type: boolean)
+ Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 125 Data size: 476 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 125 Data size: 476 Basic stats: COMPLETE 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
- Cached Query Result: true
PREHOOK: query: select key, count(*) from masking_test_n7 group by key
PREHOOK: type: QUERY
diff --git a/ql/src/test/results/clientpositive/masking_13.q.out b/ql/src/test/results/clientpositive/masking_13.q.out
new file mode 100644
index 0000000..8fa3a41
--- /dev/null
+++ b/ql/src/test/results/clientpositive/masking_13.q.out
@@ -0,0 +1,206 @@
+PREHOOK: query: create table masking_test as select cast(key as int) as key, value from src
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+PREHOOK: Output: database:default
+PREHOOK: Output: default@masking_test
+POSTHOOK: query: create table masking_test as select cast(key as int) as key, value from src
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@masking_test
+POSTHOOK: Lineage: masking_test.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: masking_test.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: explain select * from masking_test
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select * from masking_test
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: masking_test
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((key % 2) = 0) and (key < 10)) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), reverse(value) (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE 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
+ Execution mode: vectorized
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select * from masking_test
+PREHOOK: type: QUERY
+PREHOOK: Input: default@masking_test
+#### A masked pattern was here ####
+POSTHOOK: query: select * from masking_test
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@masking_test
+#### A masked pattern was here ####
+0 0_lav
+4 4_lav
+8 8_lav
+0 0_lav
+0 0_lav
+2 2_lav
+PREHOOK: query: create table new_masking_test_nx as
+select * from masking_test
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@masking_test
+PREHOOK: Output: database:default
+PREHOOK: Output: default@new_masking_test_nx
+POSTHOOK: query: create table new_masking_test_nx as
+select * from masking_test
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@masking_test
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@new_masking_test_nx
+POSTHOOK: Lineage: new_masking_test_nx.key SIMPLE [(masking_test)masking_test.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: new_masking_test_nx.value EXPRESSION [(masking_test)masking_test.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from new_masking_test_nx
+PREHOOK: type: QUERY
+PREHOOK: Input: default@new_masking_test_nx
+#### A masked pattern was here ####
+POSTHOOK: query: select * from new_masking_test_nx
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@new_masking_test_nx
+#### A masked pattern was here ####
+0 0_lav
+4 4_lav
+8 8_lav
+0 0_lav
+0 0_lav
+2 2_lav
+PREHOOK: query: create view `masking_test_view` as select key from `masking_test`
+PREHOOK: type: CREATEVIEW
+PREHOOK: Input: default@masking_test
+PREHOOK: Output: database:default
+PREHOOK: Output: default@masking_test_view
+POSTHOOK: query: create view `masking_test_view` as select key from `masking_test`
+POSTHOOK: type: CREATEVIEW
+POSTHOOK: Input: default@masking_test
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@masking_test_view
+POSTHOOK: Lineage: masking_test_view.key SIMPLE [(masking_test)masking_test.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: explain
+select key from `masking_test_view`
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key from `masking_test_view`
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: masking_test
+ properties:
+ insideView TRUE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((key % 2) = 0) and (key < 10) and (key > 6)) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger((UDFToDouble(key) / 2.0D)) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE 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
+ Execution mode: vectorized
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key from `masking_test_view`
+PREHOOK: type: QUERY
+PREHOOK: Input: default@masking_test
+PREHOOK: Input: default@masking_test_view
+#### A masked pattern was here ####
+POSTHOOK: query: select key from `masking_test_view`
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@masking_test
+POSTHOOK: Input: default@masking_test_view
+#### A masked pattern was here ####
+4
+PREHOOK: query: create table `my_table_masked` (key int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@my_table_masked
+POSTHOOK: query: create table `my_table_masked` (key int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@my_table_masked
+PREHOOK: query: insert into `my_table_masked` select key from `masking_test_view`
+PREHOOK: type: QUERY
+PREHOOK: Input: default@masking_test
+PREHOOK: Input: default@masking_test_view
+PREHOOK: Output: default@my_table_masked
+POSTHOOK: query: insert into `my_table_masked` select key from `masking_test_view`
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@masking_test
+POSTHOOK: Input: default@masking_test_view
+POSTHOOK: Output: default@my_table_masked
+POSTHOOK: Lineage: my_table_masked.key EXPRESSION [(masking_test)masking_test.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: select * from `my_table_masked`
+PREHOOK: type: QUERY
+PREHOOK: Input: default@my_table_masked
+#### A masked pattern was here ####
+POSTHOOK: query: select * from `my_table_masked`
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@my_table_masked
+#### A masked pattern was here ####
+4
+PREHOOK: query: create table new_masking_test_nx_2 as
+select * from masking_test_view
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@masking_test
+PREHOOK: Input: default@masking_test_view
+PREHOOK: Output: database:default
+PREHOOK: Output: default@new_masking_test_nx_2
+POSTHOOK: query: create table new_masking_test_nx_2 as
+select * from masking_test_view
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@masking_test
+POSTHOOK: Input: default@masking_test_view
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@new_masking_test_nx_2
+POSTHOOK: Lineage: new_masking_test_nx_2.key EXPRESSION [(masking_test)masking_test.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: select * from new_masking_test_nx_2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@new_masking_test_nx_2
+#### A masked pattern was here ####
+POSTHOOK: query: select * from new_masking_test_nx_2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@new_masking_test_nx_2
+#### A masked pattern was here ####
+4
