yihua commented on a change in pull request #1165: [HUDI-76] Add CSV Source support for Hudi Delta Streamer URL: https://github.com/apache/incubator-hudi/pull/1165#discussion_r390760597
########## File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/CsvDFSSource.java ########## @@ -0,0 +1,125 @@ +/* + * 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. + */ + +package org.apache.hudi.utilities.sources; + +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.TypedProperties; +import org.apache.hudi.common.util.collection.Pair; +import org.apache.hudi.utilities.schema.SchemaProvider; +import org.apache.hudi.utilities.sources.helpers.DFSPathSelector; + +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.DataFrameReader; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.avro.SchemaConverters; +import org.apache.spark.sql.types.StructType; + +import java.util.Arrays; +import java.util.List; + +/** + * Reads data from CSV files on DFS as the data source. + * + * Internally, we use Spark to read CSV files thus any limitation of Spark CSV also applies here + * (e.g., limited support for nested schema). + * + * You can set the CSV-specific configs in the format of hoodie.deltastreamer.csv.* + * that are Spark compatible to deal with CSV files in Hudi. The supported options are: + * + * "sep", "encoding", "quote", "escape", "charToEscapeQuoteEscaping", "comment", + * "header", "enforceSchema", "inferSchema", "samplingRatio", "ignoreLeadingWhiteSpace", + * "ignoreTrailingWhiteSpace", "nullValue", "emptyValue", "nanValue", "positiveInf", + * "negativeInf", "dateFormat", "timestampFormat", "maxColumns", "maxCharsPerColumn", + * "mode", "columnNameOfCorruptRecord", "multiLine" + * + * Detailed information of these CSV options can be found at: + * https://spark.apache.org/docs/latest/api/java/org/apache/spark/sql/DataFrameReader.html#csv-scala.collection.Seq- + * + * If the source Avro schema is provided through the {@link org.apache.hudi.utilities.schema.FilebasedSchemaProvider} + * using "hoodie.deltastreamer.schemaprovider.source.schema.file" config, the schema is + * passed to the CSV reader without inferring the schema from the CSV file. + */ +public class CsvDFSSource extends RowSource { + // CsvSource config prefix + public static final String CSV_SRC_CONFIG_PREFIX = "hoodie.deltastreamer.csv."; + // CSV-specific configurations to pass in from Hudi to Spark + public static final List<String> CSV_CONFIG_KEYS = Arrays.asList( + "sep", "encoding", "quote", "escape", "charToEscapeQuoteEscaping", "comment", + "header", "enforceSchema", "inferSchema", "samplingRatio", "ignoreLeadingWhiteSpace", + "ignoreTrailingWhiteSpace", "nullValue", "emptyValue", "nanValue", "positiveInf", + "negativeInf", "dateFormat", "timestampFormat", "maxColumns", "maxCharsPerColumn", + "mode", "columnNameOfCorruptRecord", "multiLine" + ); + + private final DFSPathSelector pathSelector; + private final StructType sourceSchema; + + public CsvDFSSource(TypedProperties props, + JavaSparkContext sparkContext, + SparkSession sparkSession, + SchemaProvider schemaProvider) { + super(props, sparkContext, sparkSession, schemaProvider); + this.pathSelector = new DFSPathSelector(props, sparkContext.hadoopConfiguration()); + if (overriddenSchemaProvider != null) { + sourceSchema = (StructType) SchemaConverters.toSqlType(overriddenSchemaProvider.getSourceSchema()).dataType(); Review comment: Good point. Done. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
