diff options
| author | Reynold Xin <rxin@databricks.com> | 2015-08-12 15:27:52 -0700 |
|---|---|---|
| committer | Reynold Xin <rxin@databricks.com> | 2015-08-12 15:27:58 -0700 |
| commit | b28295fe0c91405ade86e215083de25ec5bb52d9 (patch) | |
| tree | 4145cab355c33fd02c37078a522d95ea0078017d | |
| parent | 6a7582ea2d232982c3480e7d4ee357ea45d0b303 (diff) | |
| download | spark-b28295fe0c91405ade86e215083de25ec5bb52d9.tar.gz spark-b28295fe0c91405ade86e215083de25ec5bb52d9.tar.bz2 spark-b28295fe0c91405ade86e215083de25ec5bb52d9.zip | |
[SPARK-9907] [SQL] Python crc32 is mistakenly calling md5
Author: Reynold Xin <rxin@databricks.com>
Closes #8138 from rxin/SPARK-9907.
(cherry picked from commit a17384fa343628cec44437da5b80b9403ecd5838)
Signed-off-by: Reynold Xin <rxin@databricks.com>
| -rw-r--r-- | python/pyspark/sql/functions.py | 4 |
1 files 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 |