Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/22379#discussion_r225033808
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csvExpressions.scala
---
@@ -0,0 +1,117 @@
+/*
+ * 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.catalyst.expressions
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.csv._
+import org.apache.spark.sql.catalyst.expressions.codegen.CodegenFallback
+import org.apache.spark.sql.catalyst.util._
+import org.apache.spark.sql.types._
+import org.apache.spark.unsafe.types.UTF8String
+
+/**
+ * Converts a CSV input string to a [[StructType]] with the specified
schema.
+ */
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+ usage = "_FUNC_(csvStr, schema[, options]) - Returns a struct value with
the given `csvStr` and `schema`.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_('1, 0.8', 'a INT, b DOUBLE');
+ {"a":1, "b":0.8}
+ > SELECT _FUNC_('26/08/2015', 'time Timestamp',
map('timestampFormat', 'dd/MM/yyyy'))
+ {"time":2015-08-26 00:00:00.0}
+ """,
+ since = "3.0.0")
+// scalastyle:on line.size.limit
+case class CsvToStructs(
+ schema: StructType,
+ options: Map[String, String],
+ child: Expression,
+ timeZoneId: Option[String] = None)
+ extends UnaryExpression
+ with TimeZoneAwareExpression
+ with CodegenFallback
+ with ExpectsInputTypes
+ with NullIntolerant {
+
+ override def nullable: Boolean = child.nullable
+
+ // The CSV input data might be missing certain fields. We force the
nullability
+ // of the user-provided schema to avoid data corruptions.
+ val nullableSchema: StructType = schema.asNullable
+
+ // Used in `FunctionRegistry`
+ def this(child: Expression, schema: Expression, options: Map[String,
String]) =
+ this(
+ schema = ExprUtils.evalSchemaExpr(schema),
+ options = options,
+ child = child,
+ timeZoneId = None)
+
+ def this(child: Expression, schema: Expression) = this(child, schema,
Map.empty[String, String])
+
+ def this(child: Expression, schema: Expression, options: Expression) =
+ this(
+ schema = ExprUtils.evalSchemaExpr(schema),
+ options = ExprUtils.convertToMapData(options),
+ child = child,
+ timeZoneId = None)
+
+ // This converts parsed rows to the desired output by the given schema.
+ @transient
+ lazy val converter = (rows: Iterator[InternalRow]) => {
+ if (rows.hasNext) {
+ rows.next()
--- End diff --
what if `rows` have more than one row? shall we fail or shall we return
null?
Up to my understanding it should fail. The parser should only return one
row for struct type. If it doesn't, there must be a bug.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
