From a17384fa343628cec44437da5b80b9403ecd5838 Mon Sep 17 00:00:00 2001
From: Reynold Xin <rxin@databricks.com>
Date: Wed, 12 Aug 2015 15:27:52 -0700
Subject: [PATCH] [SPARK-9907] [SQL] Python crc32 is mistakenly calling md5
Author: Reynold Xin <rxin@databricks.com>
Closes #8138 from rxin/SPARK-9907.
---
python/pyspark/sql/functions.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py
index 95f46044d3..e98979533f 100644
--- a/python/pyspark/sql/functions.py
+++ b/python/pyspark/sql/functions.py
@@ -885,10 +885,10 @@ def crc32(col):
returns the value as a bigint.
>>> sqlContext.createDataFrame([('ABC',)], ['a']).select(crc32('a').alias('crc32')).collect()
- [Row(crc32=u'902fbdd2b1df0c4f70b4a5d23525e932')]
+ [Row(crc32=2743272264)]
"""
sc = SparkContext._active_spark_context
- return Column(sc._jvm.functions.md5(_to_java_column(col)))
+ return Column(sc._jvm.functions.crc32(_to_java_column(col)))
@ignore_unicode_prefix
--
GitLab