aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/sql/readwriter.py
diff options
context:
space:
mode:
authorFelix Cheung <felixcheung_m@hotmail.com>2016-10-26 23:06:11 -0700
committerFelix Cheung <felixcheung@apache.org>2016-10-26 23:06:11 -0700
commit44c8bfda793b7655e2bd1da5e9915a09ed9d42ce (patch)
tree4f42de29a093fe5f845307dca278a80d51bae96c /python/pyspark/sql/readwriter.py
parent1dbe9896b7f30538a5fad2f5d718d035c7906936 (diff)
downloadspark-44c8bfda793b7655e2bd1da5e9915a09ed9d42ce.tar.gz
spark-44c8bfda793b7655e2bd1da5e9915a09ed9d42ce.tar.bz2
spark-44c8bfda793b7655e2bd1da5e9915a09ed9d42ce.zip
[SQL][DOC] updating doc for JSON source to link to jsonlines.org
## What changes were proposed in this pull request? API and programming guide doc changes for Scala, Python and R. ## How was this patch tested? manual test Author: Felix Cheung <felixcheung_m@hotmail.com> Closes #15629 from felixcheung/jsondoc.
Diffstat (limited to 'python/pyspark/sql/readwriter.py')
-rw-r--r--python/pyspark/sql/readwriter.py5
1 files changed, 3 insertions, 2 deletions
diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py
index 91c2b17049..bc786ef95e 100644
--- a/python/pyspark/sql/readwriter.py
+++ b/python/pyspark/sql/readwriter.py
@@ -160,8 +160,9 @@ class DataFrameReader(OptionUtils):
allowNumericLeadingZero=None, allowBackslashEscapingAnyCharacter=None,
mode=None, columnNameOfCorruptRecord=None, dateFormat=None, timestampFormat=None):
"""
- Loads a JSON file (one object per line) or an RDD of Strings storing JSON objects
- (one object per record) and returns the result as a :class`DataFrame`.
+ Loads a JSON file (`JSON Lines text format or newline-delimited JSON
+ <[http://jsonlines.org/>`_) or an RDD of Strings storing JSON objects (one object per
+ record) and returns the result as a :class`DataFrame`.
If the ``schema`` parameter is not specified, this function goes
through the input once to determine the input schema.