afedulov commented on a change in pull request #17598:
URL: https://github.com/apache/flink/pull/17598#discussion_r770679363
##########
File path:
flink-formats/flink-csv/src/main/java/org/apache/flink/formats/csv/CsvFormatFactory.java
##########
@@ -19,103 +19,48 @@
package org.apache.flink.formats.csv;
import org.apache.flink.annotation.Internal;
-import org.apache.flink.api.common.serialization.DeserializationSchema;
-import org.apache.flink.api.common.serialization.SerializationSchema;
-import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.configuration.ConfigOption;
import org.apache.flink.configuration.ReadableConfig;
-import org.apache.flink.table.api.ValidationException;
+import org.apache.flink.connector.file.src.FileSourceSplit;
+import org.apache.flink.connector.file.src.impl.StreamFormatAdapter;
+import org.apache.flink.connector.file.src.reader.BulkFormat;
+import org.apache.flink.formats.common.Converter;
import org.apache.flink.table.connector.ChangelogMode;
-import org.apache.flink.table.connector.format.DecodingFormat;
-import org.apache.flink.table.connector.format.EncodingFormat;
-import org.apache.flink.table.connector.sink.DynamicTableSink;
-import org.apache.flink.table.connector.source.DynamicTableSource;
+import org.apache.flink.table.connector.Projection;
+import org.apache.flink.table.connector.format.BulkDecodingFormat;
+import org.apache.flink.table.connector.format.ProjectableDecodingFormat;
+import org.apache.flink.table.connector.source.DynamicTableSource.Context;
import org.apache.flink.table.data.RowData;
-import org.apache.flink.table.factories.DeserializationFormatFactory;
+import org.apache.flink.table.factories.BulkReaderFormatFactory;
import org.apache.flink.table.factories.DynamicTableFactory;
-import org.apache.flink.table.factories.FactoryUtil;
-import org.apache.flink.table.factories.SerializationFormatFactory;
import org.apache.flink.table.types.DataType;
import org.apache.flink.table.types.logical.RowType;
+import
org.apache.flink.shaded.jackson2.com.fasterxml.jackson.databind.JsonNode;
+import
org.apache.flink.shaded.jackson2.com.fasterxml.jackson.dataformat.csv.CsvMapper;
+import
org.apache.flink.shaded.jackson2.com.fasterxml.jackson.dataformat.csv.CsvSchema;
+
import org.apache.commons.lang3.StringEscapeUtils;
import java.util.Collections;
-import java.util.HashSet;
import java.util.Set;
import static org.apache.flink.formats.csv.CsvFormatOptions.ALLOW_COMMENTS;
import static
org.apache.flink.formats.csv.CsvFormatOptions.ARRAY_ELEMENT_DELIMITER;
import static
org.apache.flink.formats.csv.CsvFormatOptions.DISABLE_QUOTE_CHARACTER;
import static org.apache.flink.formats.csv.CsvFormatOptions.ESCAPE_CHARACTER;
import static org.apache.flink.formats.csv.CsvFormatOptions.FIELD_DELIMITER;
-import static
org.apache.flink.formats.csv.CsvFormatOptions.IGNORE_PARSE_ERRORS;
import static org.apache.flink.formats.csv.CsvFormatOptions.NULL_LITERAL;
import static org.apache.flink.formats.csv.CsvFormatOptions.QUOTE_CHARACTER;
-/**
- * Format factory for providing configured instances of CSV to RowData {@link
SerializationSchema}
- * and {@link DeserializationSchema}.
- */
+/** CSV format factory for file system. */
+//TODO: Rename back to CsvFileSystemFormatFactory? @Arvid
Review comment:
I had this thought because `BulkReader` is a `flink-connector-file`
interface, and `CsvBulkWriter` writer into `FSDataOutputStream`. Both the
encoder and the decoder exposed by the factory are for files.
I like the `TableCsvFormatFactory`, renamed.
##########
File path:
flink-formats/flink-csv/src/main/java/org/apache/flink/formats/csv/CsvFormatFactory.java
##########
@@ -19,103 +19,48 @@
package org.apache.flink.formats.csv;
import org.apache.flink.annotation.Internal;
-import org.apache.flink.api.common.serialization.DeserializationSchema;
-import org.apache.flink.api.common.serialization.SerializationSchema;
-import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.configuration.ConfigOption;
import org.apache.flink.configuration.ReadableConfig;
-import org.apache.flink.table.api.ValidationException;
+import org.apache.flink.connector.file.src.FileSourceSplit;
+import org.apache.flink.connector.file.src.impl.StreamFormatAdapter;
+import org.apache.flink.connector.file.src.reader.BulkFormat;
+import org.apache.flink.formats.common.Converter;
import org.apache.flink.table.connector.ChangelogMode;
-import org.apache.flink.table.connector.format.DecodingFormat;
-import org.apache.flink.table.connector.format.EncodingFormat;
-import org.apache.flink.table.connector.sink.DynamicTableSink;
-import org.apache.flink.table.connector.source.DynamicTableSource;
+import org.apache.flink.table.connector.Projection;
+import org.apache.flink.table.connector.format.BulkDecodingFormat;
+import org.apache.flink.table.connector.format.ProjectableDecodingFormat;
+import org.apache.flink.table.connector.source.DynamicTableSource.Context;
import org.apache.flink.table.data.RowData;
-import org.apache.flink.table.factories.DeserializationFormatFactory;
+import org.apache.flink.table.factories.BulkReaderFormatFactory;
import org.apache.flink.table.factories.DynamicTableFactory;
-import org.apache.flink.table.factories.FactoryUtil;
-import org.apache.flink.table.factories.SerializationFormatFactory;
import org.apache.flink.table.types.DataType;
import org.apache.flink.table.types.logical.RowType;
+import
org.apache.flink.shaded.jackson2.com.fasterxml.jackson.databind.JsonNode;
+import
org.apache.flink.shaded.jackson2.com.fasterxml.jackson.dataformat.csv.CsvMapper;
+import
org.apache.flink.shaded.jackson2.com.fasterxml.jackson.dataformat.csv.CsvSchema;
+
import org.apache.commons.lang3.StringEscapeUtils;
import java.util.Collections;
-import java.util.HashSet;
import java.util.Set;
import static org.apache.flink.formats.csv.CsvFormatOptions.ALLOW_COMMENTS;
import static
org.apache.flink.formats.csv.CsvFormatOptions.ARRAY_ELEMENT_DELIMITER;
import static
org.apache.flink.formats.csv.CsvFormatOptions.DISABLE_QUOTE_CHARACTER;
import static org.apache.flink.formats.csv.CsvFormatOptions.ESCAPE_CHARACTER;
import static org.apache.flink.formats.csv.CsvFormatOptions.FIELD_DELIMITER;
-import static
org.apache.flink.formats.csv.CsvFormatOptions.IGNORE_PARSE_ERRORS;
import static org.apache.flink.formats.csv.CsvFormatOptions.NULL_LITERAL;
import static org.apache.flink.formats.csv.CsvFormatOptions.QUOTE_CHARACTER;
-/**
- * Format factory for providing configured instances of CSV to RowData {@link
SerializationSchema}
- * and {@link DeserializationSchema}.
- */
+/** CSV format factory for file system. */
+//TODO: Rename back to CsvFileSystemFormatFactory? @Arvid
Review comment:
I had this thought because `BulkReader` is a `flink-connector-file`
interface, and `CsvBulkWriter` writes into `FSDataOutputStream`. Both the
encoder and the decoder exposed by the factory are for files.
I like the `TableCsvFormatFactory`, renamed.
--
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]
