From 7c41d135709c148d4fa3a1b06b5905715c970519 Mon Sep 17 00:00:00 2001 From: wangfei Date: Fri, 31 Oct 2014 11:27:59 -0700 Subject: [SPARK-3826][SQL]enable hive-thriftserver to support hive-0.13.1 In #2241 hive-thriftserver is not enabled. This patch enable hive-thriftserver to support hive-0.13.1 by using a shim layer refer to #2241. 1 A light shim layer(code in sql/hive-thriftserver/hive-version) for each different hive version to handle api compatibility 2 New pom profiles "hive-default" and "hive-versions"(copy from #2241) to activate different hive version 3 SBT cmd for different version as follows: hive-0.12.0 --- sbt/sbt -Phive,hadoop-2.3 -Phive-0.12.0 assembly hive-0.13.1 --- sbt/sbt -Phive,hadoop-2.3 -Phive-0.13.1 assembly 4 Since hive-thriftserver depend on hive subproject, this patch should be merged with #2241 to enable hive-0.13.1 for hive-thriftserver Author: wangfei Author: scwf Closes #2685 from scwf/shim-thriftserver1 and squashes the following commits: f26f3be [wangfei] remove clean to save time f5cac74 [wangfei] remove local hivecontext test 578234d [wangfei] use new shaded hive 18fb1ff [wangfei] exclude kryo in hive pom fa21d09 [wangfei] clean package assembly/assembly 8a4daf2 [wangfei] minor fix 0d7f6cf [wangfei] address comments f7c93ae [wangfei] adding build with hive 0.13 before running tests bcf943f [wangfei] Merge branch 'master' of https://github.com/apache/spark into shim-thriftserver1 c359822 [wangfei] reuse getCommandProcessor in hiveshim 52674a4 [scwf] sql/hive included since examples depend on it 3529e98 [scwf] move hive module to hive profile f51ff4e [wangfei] update and fix conflicts f48d3a5 [scwf] Merge branch 'master' of https://github.com/apache/spark into shim-thriftserver1 41f727b [scwf] revert pom changes 13afde0 [scwf] fix small bug 4b681f4 [scwf] enable thriftserver in profile hive-0.13.1 0bc53aa [scwf] fixed when result filed is null dfd1c63 [scwf] update run-tests to run hive-0.12.0 default now c6da3ce [scwf] Merge branch 'master' of https://github.com/apache/spark into shim-thriftserver 7c66b8e [scwf] update pom according spark-2706 ae47489 [scwf] update and fix conflicts --- python/pyspark/sql.py | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'python') diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index 93fd9d4909..f0bd3cbd98 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -1400,33 +1400,6 @@ class HiveContext(SQLContext): class LocalHiveContext(HiveContext): - """Starts up an instance of hive where metadata is stored locally. - - An in-process metadata data is created with data stored in ./metadata. - Warehouse data is stored in in ./warehouse. - - >>> import os - >>> hiveCtx = LocalHiveContext(sc) - >>> try: - ... supress = hiveCtx.sql("DROP TABLE src") - ... except Exception: - ... pass - >>> kv1 = os.path.join(os.environ["SPARK_HOME"], - ... 'examples/src/main/resources/kv1.txt') - >>> supress = hiveCtx.sql( - ... "CREATE TABLE IF NOT EXISTS src (key INT, value STRING)") - >>> supress = hiveCtx.sql("LOAD DATA LOCAL INPATH '%s' INTO TABLE src" - ... % kv1) - >>> results = hiveCtx.sql("FROM src SELECT value" - ... ).map(lambda r: int(r.value.split('_')[1])) - >>> num = results.count() - >>> reduce_sum = results.reduce(lambda x, y: x + y) - >>> num - 500 - >>> reduce_sum - 130091 - """ - def __init__(self, sparkContext, sqlContext=None): HiveContext.__init__(self, sparkContext, sqlContext) warnings.warn("LocalHiveContext is deprecated. " -- cgit v1.2.3