document mergeSchema directly in API

python/pyspark/sql/readwriter.py

@@ -300,18 +300,20 @@ def table(self, tableName):
         return self._df(self._jreader.table(tableName))
 
     @since(1.4)
-    def parquet(self, *paths):
-        """Loads Parquet files, returning the result as a :class:`DataFrame`.
+    def parquet(self, *paths, **options):
+        """
+        Loads Parquet files, returning the result as a :class:`DataFrame`.
 
-        You can set the following Parquet-specific option(s) for reading Parquet files:
-            * ``mergeSchema``: sets whether we should merge schemas collected from all \
-                Parquet part-files. This will override ``spark.sql.parquet.mergeSchema``. \
-                The default value is specified in ``spark.sql.parquet.mergeSchema``.
+        :param mergeSchema: sets whether we should merge schemas collected from all
+            Parquet part-files. This will override ``spark.sql.parquet.mergeSchema``.
+            The default value is specified in ``spark.sql.parquet.mergeSchema``.
 
         >>> df = spark.read.parquet('python/test_support/sql/parquet_partitioned')
         >>> df.dtypes
         [('name', 'string'), ('year', 'int'), ('month', 'int'), ('day', 'int')]
         """
+        mergeSchema = options.get('mergeSchema', None)
+        self._set_opts(mergeSchema=mergeSchema)
         return self._df(self._jreader.parquet(_to_seq(self._spark._sc, paths)))
 
     @ignore_unicode_prefix

python/pyspark/sql/streaming.py

@@ -526,22 +526,23 @@ def orc(self, path):
             raise TypeError("path can be only a single string")
 
     @since(2.0)
-    def parquet(self, path):
-        """Loads a Parquet file stream, returning the result as a :class:`DataFrame`.
-
-        You can set the following Parquet-specific option(s) for reading Parquet files:
-            * ``mergeSchema``: sets whether we should merge schemas collected from all \
-                Parquet part-files. This will override ``spark.sql.parquet.mergeSchema``. \
-                The default value is specified in ``spark.sql.parquet.mergeSchema``.
+    def parquet(self, path, mergeSchema=None):
+        """
+        Loads a Parquet file stream, returning the result as a :class:`DataFrame`.
 
         .. note:: Evolving.
 
+        :param mergeSchema: sets whether we should merge schemas collected from all
+            Parquet part-files. This will override ``spark.sql.parquet.mergeSchema``.
+            The default value is specified in ``spark.sql.parquet.mergeSchema``.
+
         >>> parquet_sdf = spark.readStream.schema(sdf_schema).parquet(tempfile.mkdtemp())
         >>> parquet_sdf.isStreaming
         True
         >>> parquet_sdf.schema == sdf_schema
         True
         """
+        self._set_opts(mergeSchema=mergeSchema)
         if isinstance(path, basestring):
             return self._df(self._jreader.parquet(path))
         else: