diff --git a/examples/src/main/python/sql.py b/examples/src/main/python/sql.py index 87d7b088f077bd2b1c1baa26715ca0dffa66e19c..2c188759328f26d5f7a1b3180f34b672b5efed63 100644 --- a/examples/src/main/python/sql.py +++ b/examples/src/main/python/sql.py @@ -18,6 +18,7 @@ from __future__ import print_function import os +import sys from pyspark import SparkContext from pyspark.sql import SQLContext @@ -50,7 +51,11 @@ if __name__ == "__main__": # A JSON dataset is pointed to by path. # The path can be either a single text file or a directory storing text files. - path = os.path.join(os.environ['SPARK_HOME'], "examples/src/main/resources/people.json") + if len(sys.argv) < 2: + path = "file://" + \ + os.path.join(os.environ['SPARK_HOME'], "examples/src/main/resources/people.json") + else: + path = sys.argv[1] # Create a DataFrame from the file(s) pointed to by path people = sqlContext.jsonFile(path) # root