zhengruifeng commented on code in PR #38086:
URL: https://github.com/apache/spark/pull/38086#discussion_r989876847
##########
python/pyspark/sql/connect/readwriter.py:
##########
@@ -31,6 +39,104 @@ class DataFrameReader:
def __init__(self, client: "RemoteSparkSession") -> None:
self._client = client
+ self._path = []
+ self._format = None
+ self._schema = None
+ self._options = {}
+
+ def format(self, source: str) -> "DataFrameReader":
+ """
+ Specifies the input data source format.
+
+ .. versionadded:: 3.4.0
+
+ Parameters
+ ----------
+ source : str
+ string, name of the data source, e.g. 'json', 'parquet'.
+
+ """
+ self._format = source
+ return self
+
+ # TODO(SPARK-40539): support StructType in python client and support
schema as StructType.
+ def schema(self, schema: str) -> "DataFrameReader":
+ """
+ Specifies the input schema.
+
+ Some data sources (e.g. JSON) can infer the input schema automatically
from data.
+ By specifying the schema here, the underlying data source can skip the
schema
+ inference step, and thus speed up data loading.
+
+ .. versionadded:: 3.4.0
+
+ Parameters
+ ----------
+ schema : str
+ a DDL-formatted string
+ (For example ``col0 INT, col1 DOUBLE``).
+
+ """
+ self._schema = schema
+ return self
+
+ def option(self, key: str, value: "OptionalPrimitiveType") ->
"DataFrameReader":
+ """
+ Adds an input option for the underlying data source.
+
+ .. versionadded:: 3.4.0
+
+ Parameters
+ ----------
+ key : str
+ The key for the option to set. key string is case-insensitive.
+ value
+ The value for the option to set.
+
+ """
+ self._options[key] = str(value)
+ return self
+
+ def load(
+ self,
+ path: Optional[PathOrPaths] = None,
+ format: Optional[str] = None,
+ schema: Optional[str] = None,
+ **options: "OptionalPrimitiveType",
+ ) -> "DataFrame":
+ """
+ Loads data from a data source and returns it as a :class:`DataFrame`.
+
+ .. versionadded:: 3.4.0
+
+ Parameters
+ ----------
+ path : str or list, optional
+ optional string or a list of string for file-system backed data
sources.
+ format : str, optional
+ optional string for format of the data source.
+ schema : str, optional
+ optional DDL-formatted string (For example ``col0 INT, col1
DOUBLE``).
+ **options : dict
+ all other string options
+ """
+ if format is not None:
+ self.format(format)
+ if schema is not None:
+ self.schema(schema)
+ for k in options.keys():
+ self.option(k, options.get(k))
+ if isinstance(path, str):
+ self._path.append(path)
+ elif path is not None:
+ if type(path) != list:
Review Comment:
```suggestion
if not isinstance(path, list):
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
