Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/17315#discussion_r107020700
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/FailureSafeParser.scala
---
@@ -0,0 +1,80 @@
+/*
+ * 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.util
+
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.GenericInternalRow
+import org.apache.spark.sql.types.StructType
+import org.apache.spark.unsafe.types.UTF8String
+
+class FailureSafeParser[IN](
+ rawParser: IN => Seq[InternalRow],
+ mode: String,
+ schema: StructType,
+ columnNameOfCorruptRecord: String) {
+
+ private val corruptFieldIndex =
schema.getFieldIndex(columnNameOfCorruptRecord)
+ private val actualSchema = StructType(schema.filterNot(_.name ==
columnNameOfCorruptRecord))
+ private val resultRow = new GenericInternalRow(schema.length)
+ private val nullResult = new GenericInternalRow(schema.length)
+
+ // This function takes 2 parameters: an optional partial result, and the
bad record. If the given
+ // schema doesn't contain a field for corrupted record, we just return
the partial result or a
+ // row with all fields null. If the given schema contains a field for
corrupted record, we will
+ // set the bad record to this field, and set other fields according to
the partial result or null.
+ private val toResultRow: (Option[InternalRow], () => UTF8String) =>
InternalRow = {
+ if (corruptFieldIndex.isDefined) {
+ (row, badRecord) => {
+ var i = 0
+ while (i < actualSchema.length) {
+ val f = actualSchema(i)
+ resultRow(schema.fieldIndex(f.name)) = row.map(_.get(i,
f.dataType)).orNull
+ i += 1
+ }
+ resultRow(corruptFieldIndex.get) = badRecord()
+ resultRow
+ }
+ } else {
+ (row, _) => row.getOrElse(nullResult)
+ }
+ }
+
+ def parse(input: IN): Iterator[InternalRow] = {
+ try {
+ rawParser.apply(input).toIterator.map(row => toResultRow(Some(row),
() => null))
+ } catch {
+ case e: BadRecordException if ParseModes.isPermissiveMode(mode) =>
+ Iterator(toResultRow(e.partialResult(), e.record))
+ case _: BadRecordException if ParseModes.isDropMalformedMode(mode) =>
+ Iterator.empty
+ case e: BadRecordException => throw e.cause
--- End diff --
I just did a re-check. This part in CSV is kind of messy. The codes are
random without any rule. At the very beginning, we should have test cases.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
