[SPARK-23522][PYTHON] always use sys.exit over builtin exit

The exit() builtin is only for interactive use. applications should use sys.exit().

## What changes were proposed in this pull request?

All usage of the builtin `exit()` function is replaced by `sys.exit()`.

## How was this patch tested?

I ran `python/run-tests`.

Please review http://spark.apache.org/contributing.html before opening a pull request.

Author: Benjamin Peterson <[email protected]>

Closes #20682 from benjaminp/sys-exit.

Author: benjaminp

dev/merge_spark_pr.py

@@ -510,7 +510,7 @@ def main():
     import doctest
     (failure_count, test_count) = doctest.testmod()
     if failure_count:
-        exit(-1)
+        sys.exit(-1)
     try:
         main()
     except:

dev/run-tests.py

@@ -621,7 +621,7 @@ def _test():
     import doctest
     failure_count = doctest.testmod()[0]
     if failure_count:
-        exit(-1)
+        sys.exit(-1)
 
 if __name__ == "__main__":
     _test()

examples/src/main/python/avro_inputformat.py

@@ -61,7 +61,7 @@
         Assumes you have Avro data stored in <data_file>. Reader schema can be optionally specified
         in [reader_schema_file].
         """, file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
 
     path = sys.argv[1]
 

examples/src/main/python/kmeans.py

@@ -49,7 +49,7 @@ def closestPoint(p, centers):
 
     if len(sys.argv) != 4:
         print("Usage: kmeans <file> <k> <convergeDist>", file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
 
     print("""WARN: This is a naive implementation of KMeans Clustering and is given
        as an example! Please refer to examples/src/main/python/ml/kmeans_example.py for an

examples/src/main/python/logistic_regression.py

@@ -48,7 +48,7 @@ def readPointBatch(iterator):
 
     if len(sys.argv) != 3:
         print("Usage: logistic_regression <file> <iterations>", file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
 
     print("""WARN: This is a naive implementation of Logistic Regression and is
       given as an example!

examples/src/main/python/ml/dataframe_example.py

@@ -33,7 +33,7 @@
 if __name__ == "__main__":
     if len(sys.argv) > 2:
         print("Usage: dataframe_example.py <libsvm file>", file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
     elif len(sys.argv) == 2:
         input = sys.argv[1]
     else:

examples/src/main/python/mllib/correlations.py

@@ -31,7 +31,7 @@
 if __name__ == "__main__":
     if len(sys.argv) not in [1, 2]:
         print("Usage: correlations (<file>)", file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
     sc = SparkContext(appName="PythonCorrelations")
     if len(sys.argv) == 2:
         filepath = sys.argv[1]

examples/src/main/python/mllib/kmeans.py

@@ -36,7 +36,7 @@ def parseVector(line):
 if __name__ == "__main__":
     if len(sys.argv) != 3:
         print("Usage: kmeans <file> <k>", file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
     sc = SparkContext(appName="KMeans")
     lines = sc.textFile(sys.argv[1])
     data = lines.map(parseVector)

examples/src/main/python/mllib/logistic_regression.py

@@ -42,7 +42,7 @@ def parsePoint(line):
 if __name__ == "__main__":
     if len(sys.argv) != 3:
         print("Usage: logistic_regression <file> <iterations>", file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
     sc = SparkContext(appName="PythonLR")
     points = sc.textFile(sys.argv[1]).map(parsePoint)
     iterations = int(sys.argv[2])

examples/src/main/python/mllib/random_rdd_generation.py

@@ -29,7 +29,7 @@
 if __name__ == "__main__":
     if len(sys.argv) not in [1, 2]:
         print("Usage: random_rdd_generation", file=sys.stderr)
-        exit(-1)
+        sys.exit(-1)
 
     sc = SparkContext(appName="PythonRandomRDDGeneration")