WweiL commented on code in PR #40586: URL: https://github.com/apache/spark/pull/40586#discussion_r1157836737
########## python/pyspark/sql/connect/streaming/readwriter.py: ########## @@ -0,0 +1,484 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from pyspark.sql.connect.utils import check_dependencies + +check_dependencies(__name__) + +import sys +from typing import cast, overload, Callable, Dict, List, Optional, TYPE_CHECKING, Union + +from pyspark.sql.connect.plan import DataSource, LogicalPlan, WriteStreamOperation +import pyspark.sql.connect.proto as pb2 +from pyspark.sql.connect.readwriter import OptionUtils, to_str +from pyspark.sql.connect.streaming.query import StreamingQuery +from pyspark.sql.streaming.readwriter import ( + DataStreamReader as PySparkDataStreamReader, + DataStreamWriter as PySparkDataStreamWriter, +) +from pyspark.sql.types import Row, StructType + +if TYPE_CHECKING: + from pyspark.sql.connect.session import SparkSession + from pyspark.sql.connect._typing import OptionalPrimitiveType + from pyspark.sql.connect.dataframe import DataFrame + +__all__ = ["DataStreamReader", "DataStreamWriter"] + + +class DataStreamReader(OptionUtils): + def __init__(self, client: "SparkSession") -> None: + self._format: Optional[str] = None + self._schema = "" + self._client = client + self._options: Dict[str, str] = {} + + def _df(self, plan: LogicalPlan) -> "DataFrame": + from pyspark.sql.connect.dataframe import DataFrame + + return DataFrame.withPlan(plan, self._client) + + def format(self, source: str) -> "DataStreamReader": + self._format = source + return self + + format.__doc__ = PySparkDataStreamReader.format.__doc__ + + def schema(self, schema: Union[StructType, str]) -> "DataStreamReader": + if isinstance(schema, StructType): + self._schema = schema.json() + elif isinstance(schema, str): + self._schema = schema + else: + raise TypeError("schema should be StructType or string") + return self + + schema.__doc__ = PySparkDataStreamReader.schema.__doc__ + + def option(self, key: str, value: "OptionalPrimitiveType") -> "DataStreamReader": + self._options[key] = str(value) + return self + + option.__doc__ = PySparkDataStreamReader.option.__doc__ + + def options(self, **options: "OptionalPrimitiveType") -> "DataStreamReader": + for k in options: + self.option(k, to_str(options[k])) + return self + + options.__doc__ = PySparkDataStreamReader.options.__doc__ + + def load( + self, + path: Optional[str] = None, + format: Optional[str] = None, + schema: Optional[Union[StructType, str]] = None, + **options: "OptionalPrimitiveType", + ) -> "DataFrame": + if format is not None: + self.format(format) + if schema is not None: + self.schema(schema) + self.options(**options) + if path is not None: + if type(path) != str or len(path.strip()) == 0: + raise ValueError( + "If the path is provided for stream, it needs to be a " + + "non-empty string. List of paths are not supported." + ) + + plan = DataSource( + format=self._format, + schema=self._schema, + options=self._options, + paths=[path] if path else None, + is_streaming=True, + ) + + return self._df(plan) + + load.__doc__ = PySparkDataStreamReader.load.__doc__ + + def json( + self, + path: str, + schema: Optional[Union[StructType, str]] = None, + primitivesAsString: Optional[Union[bool, str]] = None, + prefersDecimal: Optional[Union[bool, str]] = None, + allowComments: Optional[Union[bool, str]] = None, + allowUnquotedFieldNames: Optional[Union[bool, str]] = None, + allowSingleQuotes: Optional[Union[bool, str]] = None, + allowNumericLeadingZero: Optional[Union[bool, str]] = None, + allowBackslashEscapingAnyCharacter: Optional[Union[bool, str]] = None, + mode: Optional[str] = None, + columnNameOfCorruptRecord: Optional[str] = None, + dateFormat: Optional[str] = None, + timestampFormat: Optional[str] = None, + multiLine: Optional[Union[bool, str]] = None, + allowUnquotedControlChars: Optional[Union[bool, str]] = None, + lineSep: Optional[str] = None, + locale: Optional[str] = None, + dropFieldIfAllNull: Optional[Union[bool, str]] = None, + encoding: Optional[str] = None, + pathGlobFilter: Optional[Union[bool, str]] = None, + recursiveFileLookup: Optional[Union[bool, str]] = None, + allowNonNumericNumbers: Optional[Union[bool, str]] = None, + ) -> "DataFrame": + self._set_opts( + schema=schema, + primitivesAsString=primitivesAsString, + prefersDecimal=prefersDecimal, + allowComments=allowComments, + allowUnquotedFieldNames=allowUnquotedFieldNames, + allowSingleQuotes=allowSingleQuotes, + allowNumericLeadingZero=allowNumericLeadingZero, + allowBackslashEscapingAnyCharacter=allowBackslashEscapingAnyCharacter, + mode=mode, + columnNameOfCorruptRecord=columnNameOfCorruptRecord, + dateFormat=dateFormat, + timestampFormat=timestampFormat, + multiLine=multiLine, + allowUnquotedControlChars=allowUnquotedControlChars, + lineSep=lineSep, + locale=locale, + dropFieldIfAllNull=dropFieldIfAllNull, + encoding=encoding, + pathGlobFilter=pathGlobFilter, + recursiveFileLookup=recursiveFileLookup, + allowNonNumericNumbers=allowNonNumericNumbers, + ) + if isinstance(path, str): + return self.load(path=path, format="json") + else: + raise TypeError("path can be only a single string") + + json.__doc__ = PySparkDataStreamReader.json.__doc__ + + # def orc() TODO Review Comment: Yes we've filed a JIRA, https://issues.apache.org/jira/projects/SPARK/issues/SPARK-42951 -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
