From 73cd1f8223a4799fd104fe48ba011315236cf4a8 Mon Sep 17 00:00:00 2001 From: Daoyuan Date: Mon, 9 Jun 2014 11:31:36 -0700 Subject: [SPARK-1495][SQL]add support for left semi join Just submit another solution for #395 Author: Daoyuan Author: Michael Armbrust Author: Daoyuan Wang Closes #837 from adrian-wang/left-semi-join-support and squashes the following commits: d39cd12 [Daoyuan Wang] Merge pull request #1 from marmbrus/pr/837 6713c09 [Michael Armbrust] Better debugging for failed query tests. 035b73e [Michael Armbrust] Add test for left semi that can't be done with a hash join. 5ec6fa4 [Michael Armbrust] Add left semi to SQL Parser. 4c726e5 [Daoyuan] improvement according to Michael 8d4a121 [Daoyuan] add golden files for leftsemijoin 83a3c8a [Daoyuan] scala style fix 14cff80 [Daoyuan] add support for left semi join (cherry picked from commit 0cf600280167a94faec75736223256e8f2e48085) Signed-off-by: Michael Armbrust --- .../org/apache/spark/sql/hive/HiveContext.scala | 1 + .../scala/org/apache/spark/sql/hive/HiveQl.scala | 1 + .../leftsemijoin-0-80b6466213face7fbcb0de044611e1f5 | 0 .../leftsemijoin-1-d1f6a3dea28a5f0fee08026bf33d9129 | 0 .../leftsemijoin-10-89737a8857b5b61cc909e0c797f86aea | 4 ++++ .../leftsemijoin-11-80b6466213face7fbcb0de044611e1f5 | 0 .../leftsemijoin-12-d1f6a3dea28a5f0fee08026bf33d9129 | 0 .../leftsemijoin-2-43d53504df013e6b35f81811138a167a | 1 + .../leftsemijoin-3-b07d292423312aafa5e5762a579decd2 | 0 .../leftsemijoin-4-3ac2226efe7cb5d999c1c5e4ac2114be | 0 .../leftsemijoin-5-9c307c0559d735960ce77efa95b2b17b | 0 .../leftsemijoin-6-82921fc96eef547ec0f71027ee88298c | 0 .../leftsemijoin-7-b30aa3b4a45db6b64bb46b4d9bd32ff0 | 0 .../leftsemijoin-8-73cad58a10a1483ccb15e94a857013 | 4 ++++ .../leftsemijoin-9-c5efa6b8771a51610d655be461670e1e | 2 ++ ...eftsemijoin_mr-0-7087fb6281a34d00f1812d2ff4ba8b75 | 0 ...eftsemijoin_mr-1-aa3f07f028027ffd13ab5535dc821593 | 0 ...ftsemijoin_mr-10-9914f44ecb6ae7587b62e5349ff60d04 | 1 + ...ftsemijoin_mr-11-2027ecb1495d5550c5d56abf6b95b0a7 | 2 ++ ...eftsemijoin_mr-2-3f65953ae60375156367c54533978782 | 0 ...eftsemijoin_mr-3-645cf8b871c9b27418d6fa1d1bda9a52 | 0 ...eftsemijoin_mr-4-333895fe6abca27c8edb5c91bfe10d2f | 2 ++ ...eftsemijoin_mr-5-896d0948c1df849df9764a6d8ad8fff9 | 20 ++++++++++++++++++++ ...eftsemijoin_mr-6-b1e2ade89ae898650f0be4f796d8947b | 1 + ...eftsemijoin_mr-7-8e9c2969b999557363e40f9ebb3f6d7c | 1 + ...eftsemijoin_mr-8-c61b972d4409babe41d8963e841af45b | 1 + ...eftsemijoin_mr-9-2027ecb1495d5550c5d56abf6b95b0a7 | 2 ++ .../sql/hive/execution/HiveCompatibilitySuite.scala | 2 ++ 28 files changed, 45 insertions(+) create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-0-80b6466213face7fbcb0de044611e1f5 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-1-d1f6a3dea28a5f0fee08026bf33d9129 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-10-89737a8857b5b61cc909e0c797f86aea create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-11-80b6466213face7fbcb0de044611e1f5 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-12-d1f6a3dea28a5f0fee08026bf33d9129 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-2-43d53504df013e6b35f81811138a167a create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-3-b07d292423312aafa5e5762a579decd2 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-4-3ac2226efe7cb5d999c1c5e4ac2114be create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-5-9c307c0559d735960ce77efa95b2b17b create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-6-82921fc96eef547ec0f71027ee88298c create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-7-b30aa3b4a45db6b64bb46b4d9bd32ff0 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-8-73cad58a10a1483ccb15e94a857013 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin-9-c5efa6b8771a51610d655be461670e1e create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-0-7087fb6281a34d00f1812d2ff4ba8b75 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-1-aa3f07f028027ffd13ab5535dc821593 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-10-9914f44ecb6ae7587b62e5349ff60d04 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-11-2027ecb1495d5550c5d56abf6b95b0a7 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-2-3f65953ae60375156367c54533978782 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-3-645cf8b871c9b27418d6fa1d1bda9a52 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-4-333895fe6abca27c8edb5c91bfe10d2f create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-5-896d0948c1df849df9764a6d8ad8fff9 create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-6-b1e2ade89ae898650f0be4f796d8947b create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-7-8e9c2969b999557363e40f9ebb3f6d7c create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-8-c61b972d4409babe41d8963e841af45b create mode 100644 sql/hive/src/test/resources/golden/leftsemijoin_mr-9-2027ecb1495d5550c5d56abf6b95b0a7 (limited to 'sql/hive') diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala index b21f24dad7..fbab2ac16b 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala @@ -224,6 +224,7 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { DataSinks, Scripts, PartialAggregation, + LeftSemiJoin, HashJoin, BasicOperators, CartesianProduct, diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index 7e91c16c6b..cc9e24a057 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -685,6 +685,7 @@ private[hive] object HiveQl { case "TOK_RIGHTOUTERJOIN" => RightOuter case "TOK_LEFTOUTERJOIN" => LeftOuter case "TOK_FULLOUTERJOIN" => FullOuter + case "TOK_LEFTSEMIJOIN" => LeftSemi } assert(other.size <= 1, "Unhandled join clauses.") Join(nodeToRelation(relation1), diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-0-80b6466213face7fbcb0de044611e1f5 b/sql/hive/src/test/resources/golden/leftsemijoin-0-80b6466213face7fbcb0de044611e1f5 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-1-d1f6a3dea28a5f0fee08026bf33d9129 b/sql/hive/src/test/resources/golden/leftsemijoin-1-d1f6a3dea28a5f0fee08026bf33d9129 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-10-89737a8857b5b61cc909e0c797f86aea b/sql/hive/src/test/resources/golden/leftsemijoin-10-89737a8857b5b61cc909e0c797f86aea new file mode 100644 index 0000000000..25ce912507 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin-10-89737a8857b5b61cc909e0c797f86aea @@ -0,0 +1,4 @@ +Hank 2 +Hank 2 +Joe 2 +Joe 2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-11-80b6466213face7fbcb0de044611e1f5 b/sql/hive/src/test/resources/golden/leftsemijoin-11-80b6466213face7fbcb0de044611e1f5 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-12-d1f6a3dea28a5f0fee08026bf33d9129 b/sql/hive/src/test/resources/golden/leftsemijoin-12-d1f6a3dea28a5f0fee08026bf33d9129 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-2-43d53504df013e6b35f81811138a167a b/sql/hive/src/test/resources/golden/leftsemijoin-2-43d53504df013e6b35f81811138a167a new file mode 100644 index 0000000000..573541ac97 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin-2-43d53504df013e6b35f81811138a167a @@ -0,0 +1 @@ +0 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-3-b07d292423312aafa5e5762a579decd2 b/sql/hive/src/test/resources/golden/leftsemijoin-3-b07d292423312aafa5e5762a579decd2 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-4-3ac2226efe7cb5d999c1c5e4ac2114be b/sql/hive/src/test/resources/golden/leftsemijoin-4-3ac2226efe7cb5d999c1c5e4ac2114be new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-5-9c307c0559d735960ce77efa95b2b17b b/sql/hive/src/test/resources/golden/leftsemijoin-5-9c307c0559d735960ce77efa95b2b17b new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-6-82921fc96eef547ec0f71027ee88298c b/sql/hive/src/test/resources/golden/leftsemijoin-6-82921fc96eef547ec0f71027ee88298c new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-7-b30aa3b4a45db6b64bb46b4d9bd32ff0 b/sql/hive/src/test/resources/golden/leftsemijoin-7-b30aa3b4a45db6b64bb46b4d9bd32ff0 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-8-73cad58a10a1483ccb15e94a857013 b/sql/hive/src/test/resources/golden/leftsemijoin-8-73cad58a10a1483ccb15e94a857013 new file mode 100644 index 0000000000..25ce912507 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin-8-73cad58a10a1483ccb15e94a857013 @@ -0,0 +1,4 @@ +Hank 2 +Hank 2 +Joe 2 +Joe 2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin-9-c5efa6b8771a51610d655be461670e1e b/sql/hive/src/test/resources/golden/leftsemijoin-9-c5efa6b8771a51610d655be461670e1e new file mode 100644 index 0000000000..f1470bad57 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin-9-c5efa6b8771a51610d655be461670e1e @@ -0,0 +1,2 @@ +2 Tie +2 Tie diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-0-7087fb6281a34d00f1812d2ff4ba8b75 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-0-7087fb6281a34d00f1812d2ff4ba8b75 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-1-aa3f07f028027ffd13ab5535dc821593 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-1-aa3f07f028027ffd13ab5535dc821593 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-10-9914f44ecb6ae7587b62e5349ff60d04 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-10-9914f44ecb6ae7587b62e5349ff60d04 new file mode 100644 index 0000000000..573541ac97 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-10-9914f44ecb6ae7587b62e5349ff60d04 @@ -0,0 +1 @@ +0 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-11-2027ecb1495d5550c5d56abf6b95b0a7 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-11-2027ecb1495d5550c5d56abf6b95b0a7 new file mode 100644 index 0000000000..6ed281c757 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-11-2027ecb1495d5550c5d56abf6b95b0a7 @@ -0,0 +1,2 @@ +1 +1 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-2-3f65953ae60375156367c54533978782 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-2-3f65953ae60375156367c54533978782 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-3-645cf8b871c9b27418d6fa1d1bda9a52 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-3-645cf8b871c9b27418d6fa1d1bda9a52 new file mode 100644 index 0000000000..e69de29bb2 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-4-333895fe6abca27c8edb5c91bfe10d2f b/sql/hive/src/test/resources/golden/leftsemijoin_mr-4-333895fe6abca27c8edb5c91bfe10d2f new file mode 100644 index 0000000000..6ed281c757 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-4-333895fe6abca27c8edb5c91bfe10d2f @@ -0,0 +1,2 @@ +1 +1 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-5-896d0948c1df849df9764a6d8ad8fff9 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-5-896d0948c1df849df9764a6d8ad8fff9 new file mode 100644 index 0000000000..179ef0e020 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-5-896d0948c1df849df9764a6d8ad8fff9 @@ -0,0 +1,20 @@ +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 +1 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-6-b1e2ade89ae898650f0be4f796d8947b b/sql/hive/src/test/resources/golden/leftsemijoin_mr-6-b1e2ade89ae898650f0be4f796d8947b new file mode 100644 index 0000000000..573541ac97 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-6-b1e2ade89ae898650f0be4f796d8947b @@ -0,0 +1 @@ +0 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-7-8e9c2969b999557363e40f9ebb3f6d7c b/sql/hive/src/test/resources/golden/leftsemijoin_mr-7-8e9c2969b999557363e40f9ebb3f6d7c new file mode 100644 index 0000000000..573541ac97 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-7-8e9c2969b999557363e40f9ebb3f6d7c @@ -0,0 +1 @@ +0 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-8-c61b972d4409babe41d8963e841af45b b/sql/hive/src/test/resources/golden/leftsemijoin_mr-8-c61b972d4409babe41d8963e841af45b new file mode 100644 index 0000000000..573541ac97 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-8-c61b972d4409babe41d8963e841af45b @@ -0,0 +1 @@ +0 diff --git a/sql/hive/src/test/resources/golden/leftsemijoin_mr-9-2027ecb1495d5550c5d56abf6b95b0a7 b/sql/hive/src/test/resources/golden/leftsemijoin_mr-9-2027ecb1495d5550c5d56abf6b95b0a7 new file mode 100644 index 0000000000..6ed281c757 --- /dev/null +++ b/sql/hive/src/test/resources/golden/leftsemijoin_mr-9-2027ecb1495d5550c5d56abf6b95b0a7 @@ -0,0 +1,2 @@ +1 +1 diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala index 9031abf733..fb8f272d5a 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala @@ -480,6 +480,8 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter { "lateral_view", "lateral_view_cp", "lateral_view_ppd", + "leftsemijoin", + "leftsemijoin_mr", "lineage1", "literal_double", "literal_ints", -- cgit v1.2.3