[SPARK-8271][SQL]string function: soundex

This PR brings SQL function soundex(), see https://issues.apache.org/jira/browse/HIVE-9738

It's based on #7115 , thanks to HuJiayin

Author: HuJiayin <jiayin.hu@intel.com>
Author: Davies Liu <davies@databricks.com>

Closes #7812 from davies/soundex and squashes the following commits:

fa75941 [Davies Liu] Merge branch 'master' of github.com:apache/spark into soundex
a4bd6d8 [Davies Liu] fix soundex
2538908 [HuJiayin] add codegen soundex
d15d329 [HuJiayin] add back ut
ded1a14 [HuJiayin] Merge branch 'master' of https://github.com/apache/spark
e2dec2c [HuJiayin] support soundex rebase code

1 files changed, 17 insertions, 0 deletions

diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py
index 8024a8de07..bb9926ce8c 100644
--- a/python/pyspark/sql/functions.py
+++ b/python/pyspark/sql/functions.py
@@ -63,6 +63,8 @@ __all__ += [
     'year', 'quarter', 'month', 'hour', 'minute', 'second',
     'dayofmonth', 'dayofyear', 'weekofyear']
 
+__all__ += ['soundex']
+
 
 def _create_function(name, doc=""):
     """ Create a function for aggregator by name"""
@@ -922,6 +924,7 @@ def trunc(date, format):
 def size(col):
     """
     Collection function: returns the length of the array or map stored in the column.
+
     :param col: name of column or expression
 
     >>> df = sqlContext.createDataFrame([([1, 2, 3],),([1],),([],)], ['data'])
@@ -932,6 +935,20 @@ def size(col):
     return Column(sc._jvm.functions.size(_to_java_column(col)))
 
 
+@since
+@ignore_unicode_prefix
+def soundex(col):
+    """
+    Returns the SoundEx encoding for a string
+
+    >>> df = sqlContext.createDataFrame([("Peters",),("Uhrbach",)], ['name'])
+    >>> df.select(soundex(df.name).alias("soundex")).collect()
+    [Row(soundex=u'P362'), Row(soundex=u'U612')]
+    """
+    sc = SparkContext._active_spark_context
+    return Column(sc._jvm.functions.size(_to_java_column(col)))
+
+
 class UserDefinedFunction(object):
     """
     User defined function in Python