Github user deanchen commented on a diff in the pull request:
https://github.com/apache/spark/pull/13988#discussion_r71100480
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/UnivocityGenerator.scala
---
@@ -0,0 +1,83 @@
+/*
+ * 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.spark.sql.execution.datasources.csv
+
+import com.univocity.parsers.csv.{CsvWriter, CsvWriterSettings}
+
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.types.StructType
+
+/**
+ * Converts a sequence of string to CSV string
+ */
+private[csv] object UnivocityGenerator extends Logging {
+ /**
+ * Transforms a single InternalRow to CSV using Univocity
+ *
+ * @param rowSchema the schema object used for conversion
+ * @param writer a CsvWriter object
+ * @param headers headers to write
+ * @param writeHeader true if it needs to write header
+ * @param options CSVOptions object containing options
+ * @param row The row to convert
+ */
+ def apply(
+ rowSchema: StructType,
+ writer: CsvWriter,
+ headers: Array[String],
+ writeHeader: Boolean,
+ options: CSVOptions)(row: InternalRow): Unit = {
+ val tokens = {
+ row.toSeq(rowSchema).map { field =>
+ // TODO: It seems all the data types are not able to be
represented by `toString`.
+ // For example, `DateType` and `TimestampType` are being long
values as timestamps.
--- End diff --
ah thanks, commented on that PR. Glad to see someone showing some love to
Spark's csv datasource!
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
