We are trying to read a teradata table from spark2.0 using jdbc using the following code :
import sys
spark_home = os.environ.get('SPARK_HOME', None)
sys.path.insert(0, os.path.join(spark_home, 'python/lib/py4j-0.10.1-src.zip'))
sys.path.insert(0, os.path.join(spark_home, 'python/lib/pyspark.zip'))
filename = os.path.join(spark_home, 'python/pyspark/shell.py')
print(os.environ.get('SPARK_HOME', None))
exec(compile(open(filename, "rb").read(), filename, 'exec'))
spark_release_file = spark_home + "/RELEASE"
if os.path.exists(spark_release_file) and "Spark 2" in open(spark_release_file).read():
print("Spark is there.")
argsstr= "--master yarn-client --deploy-mode cluster pyspark-shell --driver-class-path /path/to/teradata/terajdbc4.jar,/path/to/teradata/tdgssconfig.jar --driver-library-path /path/to/teradata/terajdbc4.jar,/path/to/teradata/tdgssconfig.jar --jars /path/to/teradata/terajdbc4.jar,/path/to/teradata/tdgssconfig.jar"
pyspark_submit_args = os.environ.get("PYSPARK_SUBMIT_ARGS", argsstr)
if not "pyspark-shell" in pyspark_submit_args:
pyspark_submit_args += " pyspark-shell"
print(pyspark_submit_args)
os.environ["PYSPARK_SUBMIT_ARGS"] = pyspark_submit_args
os.environ["SPARK_SUBMIT_ARGS"] = pyspark_submit_args
from pyspark.sql import SQLContext
from pyspark import SparkConf, SparkContext
url = 'jdbc:teradata://teradata.server.com'
user='username'
password=''
driver = 'com.teradata.jdbc.TeraDriver'
dbtable_read = 'mi_temp.bd_test_spark_read'
sqlContext = SQLContext(sc)
df = sqlContext.read.format("jdbc").options(url=url, user=user, password=password, driver=driver, dbtable=dbtable_read).load()We get the follwoing error :
Py4JJavaError: An error occurred while calling o48.load.
: java.lang.ClassNotFoundException: com.teradata.jdbc.TeraDriver
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at org.apache.spark.sql.execution.datasources.jdbc.DriverRegistry$.register(DriverRegistry.scala:38)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:49)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$anonfun$createConnectionFactory$1.apply(JdbcUtils.scala:49)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.createConnectionFactory(JdbcUtils.scala:49)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:123)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:117)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:53)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:315)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:149)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:122)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
However the if we run the same code, via command line it works.
Can you please give us some pointers?
