Return-Path: X-Original-To: apmail-hive-commits-archive@www.apache.org Delivered-To: apmail-hive-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 131A018985 for ; Mon, 7 Dec 2015 09:52:48 +0000 (UTC) Received: (qmail 95409 invoked by uid 500); 7 Dec 2015 09:52:48 -0000 Delivered-To: apmail-hive-commits-archive@hive.apache.org Received: (qmail 95357 invoked by uid 500); 7 Dec 2015 09:52:47 -0000 Mailing-List: contact commits-help@hive.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: hive-dev@hive.apache.org Delivered-To: mailing list commits@hive.apache.org Received: (qmail 95346 invoked by uid 99); 7 Dec 2015 09:52:47 -0000 Received: from git1-us-west.apache.org (HELO git1-us-west.apache.org) (140.211.11.23) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 07 Dec 2015 09:52:47 +0000 Received: by git1-us-west.apache.org (ASF Mail Server at git1-us-west.apache.org, from userid 33) id B692FDFDC5; Mon, 7 Dec 2015 09:52:47 +0000 (UTC) Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: jcamacho@apache.org To: commits@hive.apache.org Message-Id: <7910f4fa5c6a4fe4a6630da92d751392@git.apache.org> X-Mailer: ASF-Git Admin Mailer Subject: hive git commit: HIVE-12477: Left Semijoins are incompatible with a cross-product (Jesus Camacho Rodriguez, reviewed by Sergey Shelukhin) Date: Mon, 7 Dec 2015 09:52:47 +0000 (UTC) Repository: hive Updated Branches: refs/heads/master 7a1f14c4d -> 84d747a2e HIVE-12477: Left Semijoins are incompatible with a cross-product (Jesus Camacho Rodriguez, reviewed by Sergey Shelukhin) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/84d747a2 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/84d747a2 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/84d747a2 Branch: refs/heads/master Commit: 84d747a2ec79923ba357c69bc3ef9f6d4fcc6634 Parents: 7a1f14c Author: Jesus Camacho Rodriguez Authored: Sat Dec 5 13:01:17 2015 +0100 Committer: Jesus Camacho Rodriguez Committed: Mon Dec 7 10:42:21 2015 +0100 ---------------------------------------------------------------------- .../hadoop/hive/ql/parse/SemanticAnalyzer.java | 7 +- ql/src/test/queries/clientpositive/semijoin3.q | 28 ++++ .../test/results/clientpositive/semijoin3.q.out | 156 +++++++++++++++++++ 3 files changed, 190 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/84d747a2/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java ---------------------------------------------------------------------- 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 e1a0c4a..dca3081 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 @@ -55,7 +55,6 @@ import org.apache.hadoop.fs.Path; import org.apache.hadoop.fs.permission.FsAction; import org.apache.hadoop.hive.common.FileUtils; import org.apache.hadoop.hive.common.ObjectPair; -import org.apache.hadoop.hive.common.StatsSetupConst; import org.apache.hadoop.hive.common.StatsSetupConst.StatDB; import org.apache.hadoop.hive.conf.HiveConf; import org.apache.hadoop.hive.conf.HiveConf.ConfVars; @@ -2367,6 +2366,12 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { LOG.warn(ErrorMsg.OUTERJOIN_USES_FILTERS.getErrorCodedMsg()); joinTree.getFiltersForPushing().get(1).add(joinCond); } + } else if (type.equals(JoinType.LEFTSEMI)) { + joinTree.getExpressions().get(0).add(leftCondn); + joinTree.getExpressions().get(1).add(rightCondn); + boolean nullsafe = joinCond.getToken().getType() == HiveParser.EQUAL_NS; + joinTree.getNullSafes().add(nullsafe); + joinTree.getFiltersForPushing().get(1).add(joinCond); } else { joinTree.getFiltersForPushing().get(1).add(joinCond); } http://git-wip-us.apache.org/repos/asf/hive/blob/84d747a2/ql/src/test/queries/clientpositive/semijoin3.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/semijoin3.q b/ql/src/test/queries/clientpositive/semijoin3.q new file mode 100644 index 0000000..a502b9b --- /dev/null +++ b/ql/src/test/queries/clientpositive/semijoin3.q @@ -0,0 +1,28 @@ +create table t1 as select cast(key as int) key, value from src; + +create table t2 as select cast(key as int) key, value from src; + +set hive.cbo.enable=false; + +explain +select count(1) +from + (select key + from t1 + where key = 0) t1 +left semi join + (select key + from t2 + where key = 0) t2 +on 1 = 1; + +select count(1) +from + (select key + from t1 + where key = 0) t1 +left semi join + (select key + from t2 + where key = 0) t2 +on 1 = 1; http://git-wip-us.apache.org/repos/asf/hive/blob/84d747a2/ql/src/test/results/clientpositive/semijoin3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/semijoin3.q.out b/ql/src/test/results/clientpositive/semijoin3.q.out new file mode 100644 index 0000000..d7aad9e --- /dev/null +++ b/ql/src/test/results/clientpositive/semijoin3.q.out @@ -0,0 +1,156 @@ +PREHOOK: query: create table t1 as select cast(key as int) key, value from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@t1 +POSTHOOK: query: create table t1 as select cast(key as int) key, value from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1 +PREHOOK: query: create table t2 as select cast(key as int) key, value from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@t2 +POSTHOOK: query: create table t2 as select cast(key as int) key, value from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t2 +PREHOOK: query: explain +select count(1) +from + (select key + from t1 + where key = 0) t1 +left semi join + (select key + from t2 + where key = 0) t2 +on 1 = 1 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) +from + (select key + from t1 + where key = 0) t1 +left semi join + (select key + from t2 + where key = 0) t2 +on 1 = 1 +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: t1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: 1 (type: int) + sort order: + + Map-reduce partition columns: 1 (type: int) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + TableScan + alias: t2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: 1 (type: int) + sort order: + + Map-reduce partition columns: 1 (type: int) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 1 (type: int) + 1 1 (type: int) + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE 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 + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1) +from + (select key + from t1 + where key = 0) t1 +left semi join + (select key + from t2 + where key = 0) t2 +on 1 = 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select count(1) +from + (select key + from t1 + where key = 0) t1 +left semi join + (select key + from t2 + where key = 0) t2 +on 1 = 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +3