diff options
Diffstat (limited to 'python/pyspark/sql/readwriter.py')
| -rw-r--r-- | python/pyspark/sql/readwriter.py | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/python/pyspark/sql/readwriter.py b/python/pyspark/sql/readwriter.py index b5e5b18bcb..ec47618e73 100644 --- a/python/pyspark/sql/readwriter.py +++ b/python/pyspark/sql/readwriter.py @@ -308,7 +308,7 @@ class DataFrameReader(OptionUtils): ignoreTrailingWhiteSpace=None, nullValue=None, nanValue=None, positiveInf=None, negativeInf=None, dateFormat=None, timestampFormat=None, maxColumns=None, maxCharsPerColumn=None, maxMalformedLogPerPartition=None, mode=None, timeZone=None, - columnNameOfCorruptRecord=None): + columnNameOfCorruptRecord=None, wholeFile=None): """Loads a CSV file and returns the result as a :class:`DataFrame`. This function will go through the input once to determine the input schema if @@ -385,6 +385,8 @@ class DataFrameReader(OptionUtils): ``spark.sql.columnNameOfCorruptRecord``. If None is set, it uses the value specified in ``spark.sql.columnNameOfCorruptRecord``. + :param wholeFile: parse records, which may span multiple lines. If None is + set, it uses the default value, ``false``. >>> df = spark.read.csv('python/test_support/sql/ages.csv') >>> df.dtypes @@ -398,7 +400,7 @@ class DataFrameReader(OptionUtils): dateFormat=dateFormat, timestampFormat=timestampFormat, maxColumns=maxColumns, maxCharsPerColumn=maxCharsPerColumn, maxMalformedLogPerPartition=maxMalformedLogPerPartition, mode=mode, timeZone=timeZone, - columnNameOfCorruptRecord=columnNameOfCorruptRecord) + columnNameOfCorruptRecord=columnNameOfCorruptRecord, wholeFile=wholeFile) if isinstance(path, basestring): path = [path] return self._df(self._jreader.csv(self._spark._sc._jvm.PythonUtils.toSeq(path))) |