twalthr commented on a change in pull request #6541: [FLINK-9964] [table] Add a CSV table format factory URL: https://github.com/apache/flink/pull/6541#discussion_r209625213
########## File path: flink-formats/flink-csv/src/main/java/org/apache/flink/formats/csv/CsvRowDeserializationSchema.java ########## @@ -0,0 +1,228 @@ +/* + * 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.flink.formats.csv; + +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.api.common.serialization.DeserializationSchema; +import org.apache.flink.api.common.typeinfo.BasicArrayTypeInfo; +import org.apache.flink.api.common.typeinfo.PrimitiveArrayTypeInfo; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.common.typeinfo.Types; +import org.apache.flink.api.java.typeutils.RowTypeInfo; +import org.apache.flink.types.Row; +import org.apache.flink.util.Preconditions; + +import com.fasterxml.jackson.databind.JsonNode; +import com.fasterxml.jackson.databind.node.ArrayNode; +import com.fasterxml.jackson.databind.node.TextNode; +import com.fasterxml.jackson.dataformat.csv.CsvMapper; +import com.fasterxml.jackson.dataformat.csv.CsvSchema; + +import java.io.IOException; +import java.io.UnsupportedEncodingException; +import java.lang.reflect.Array; +import java.math.BigDecimal; +import java.math.BigInteger; +import java.sql.Date; +import java.sql.Time; +import java.sql.Timestamp; + +/** + * Deserialization schema from CSV to Flink types. + * + * <p>Deserializes a <code>byte[]</code> message as a {@link JsonNode} and + * convert it to {@link Row}. + * + * <p>Failure during deserialization are forwarded as wrapped IOExceptions. + */ +@PublicEvolving +public class CsvRowDeserializationSchema implements DeserializationSchema<Row> { + + /** Schema describing the input csv data. */ + private CsvSchema csvSchema; + + /** Type information describing the input csv data. */ + private TypeInformation<Row> rowTypeInfo; + + /** CsvMapper used to write {@link JsonNode} into bytes. */ + private CsvMapper csvMapper = new CsvMapper(); + + /** Charset for byte[]. */ + private String charset = "UTF-8"; + + + /** + * Create a csv row DeserializationSchema with given {@link TypeInformation}. + */ + CsvRowDeserializationSchema(TypeInformation<Row> rowTypeInfo) { + Preconditions.checkNotNull(rowTypeInfo, "rowTypeInfo must not be null !"); + this.rowTypeInfo = rowTypeInfo; + this.csvSchema = CsvRowSchemaConverter.rowTypeToCsvSchema((RowTypeInfo) rowTypeInfo); + } + + @Override + public Row deserialize(byte[] message) throws IOException { + JsonNode root = csvMapper.readerFor(JsonNode.class) Review comment: The method calls here are expensive for every record. Can we initialize the mapper before and only call `readValue` here? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on 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
