diff options
Diffstat (limited to 'python/pyspark/sql/readwriter.py')
-rw-r--r-- | python/pyspark/sql/readwriter.py | 13 |
1 files changed, 8 insertions, 5 deletions
diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py index 1678334889..6bed390e60 100644 --- a/python/pyspark/sql/readwriter.py +++ b/python/pyspark/sql/readwriter.py @@ -159,11 +159,12 @@ class DataFrameReader(OptionUtils): allowComments=None, allowUnquotedFieldNames=None, allowSingleQuotes=None, allowNumericLeadingZero=None, allowBackslashEscapingAnyCharacter=None, mode=None, columnNameOfCorruptRecord=None, dateFormat=None, timestampFormat=None, - timeZone=None): + timeZone=None, wholeFile=None): """ - 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`. + Loads a JSON file and returns the results as a :class:`DataFrame`. + + Both JSON (one record per file) and `JSON Lines <http://jsonlines.org/>`_ + (newline-delimited JSON) are supported and can be selected with the `wholeFile` parameter. If the ``schema`` parameter is not specified, this function goes through the input once to determine the input schema. @@ -212,6 +213,8 @@ class DataFrameReader(OptionUtils): default value, ``yyyy-MM-dd'T'HH:mm:ss.SSSZZ``. :param timeZone: sets the string that indicates a timezone to be used to parse timestamps. If None is set, it uses the default value, session local timezone. + :param wholeFile: parse one record, which may span multiple lines, per file. If None is + set, it uses the default value, ``false``. >>> df1 = spark.read.json('python/test_support/sql/people.json') >>> df1.dtypes @@ -228,7 +231,7 @@ class DataFrameReader(OptionUtils): allowSingleQuotes=allowSingleQuotes, allowNumericLeadingZero=allowNumericLeadingZero, allowBackslashEscapingAnyCharacter=allowBackslashEscapingAnyCharacter, mode=mode, columnNameOfCorruptRecord=columnNameOfCorruptRecord, dateFormat=dateFormat, - timestampFormat=timestampFormat, timeZone=timeZone) + timestampFormat=timestampFormat, timeZone=timeZone, wholeFile=wholeFile) if isinstance(path, basestring): path = [path] if type(path) == list: |