[
https://issues.apache.org/jira/browse/FLINK-5571?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15853765#comment-15853765
]
ASF GitHub Bot commented on FLINK-5571:
---------------------------------------
Github user godfreyhe commented on a diff in the pull request:
https://github.com/apache/flink/pull/3176#discussion_r99548048
--- Diff:
flink-libraries/flink-table/src/test/scala/org/apache/flink/table/api/scala/batch/sql/UserDefinedTableFunctionITCase.scala
---
@@ -0,0 +1,106 @@
+/*
+ * 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.table.api.scala.batch.sql
+
+import org.apache.flink.api.scala.util.CollectionDataSets
+import org.apache.flink.api.scala.{ExecutionEnvironment, _}
+import org.apache.flink.table.api.TableEnvironment
+import org.apache.flink.table.api.scala._
+import org.apache.flink.table.api.scala.batch.utils.UDFTestUtils
+import org.apache.flink.table.utils.{RichTableFunc0, RichTableFunc1}
+import org.apache.flink.test.util.TestBaseUtils
+import org.apache.flink.types.Row
+import org.junit.Test
+
+import scala.collection.JavaConverters._
+
+class UserDefinedTableFunctionITCase {
+
+ @Test
+ def testOpenClose(): Unit = {
+ val env = ExecutionEnvironment.getExecutionEnvironment
+ val tEnv = TableEnvironment.getTableEnvironment(env)
+ tEnv.registerFunction("RichTableFunc0", new RichTableFunc0)
+
+ val sqlQuery = "SELECT a, s FROM t1, LATERAL TABLE(RichTableFunc0(c))
as T(s)"
+
+ val ds = CollectionDataSets.get3TupleDataSet(env)
+ tEnv.registerDataSet("t1", ds, 'a, 'b, 'c)
+
+ val result = tEnv.sql(sqlQuery)
+
+ val expected =
+ "1,Hi\n2,Hello\n3,Hello world\n4,Hello world, how are you?\n5,I am
fine.\n6,Luke Skywalker"
+ val results = result.toDataSet[Row].collect()
+ TestBaseUtils.compareResultAsText(results.asJava, expected)
+ }
+
+ @Test
+ def testSingleUDTFWithParameter(): Unit = {
+ val env = ExecutionEnvironment.getExecutionEnvironment
+ val tEnv = TableEnvironment.getTableEnvironment(env)
+ tEnv.registerFunction("RichTableFunc1", new RichTableFunc1)
+ UDFTestUtils.setJobParameters(env, Map("word_separator" -> " "))
+
+ val sqlQuery = "SELECT a, s FROM t1, LATERAL TABLE(RichTableFunc1(c))
as T(s)"
+
+ val ds = CollectionDataSets.getSmall3TupleDataSet(env)
+ tEnv.registerDataSet("t1", ds, 'a, 'b, 'c)
+
+ val result = tEnv.sql(sqlQuery)
+
+ val expected = "3,Hello\n3,world"
+ val results = result.toDataSet[Row].collect()
+ TestBaseUtils.compareResultAsText(results.asJava, expected)
+ }
+
+ @Test
+ def testMultiUDTFs(): Unit = {
--- End diff --
yes, each `RichTableFunction` will generate independent FlatMap function.
And I think this test is also meaningful. I will add cases to test UDTF with
UDF later.
> add open and close methods for UserDefinedFunction in TableAPI & SQL
> --------------------------------------------------------------------
>
> Key: FLINK-5571
> URL: https://issues.apache.org/jira/browse/FLINK-5571
> Project: Flink
> Issue Type: New Feature
> Components: Table API & SQL
> Reporter: godfrey he
> Assignee: godfrey he
>
> Currently, a User Defined Function (UDF) in table API & SQL works on zero,
> one, or multiple values in custom evaluation method. Many UDFs need more
> complex features, e.g. report metrics, get parameters from job configuration,
> or get extra data from distribute cache file, etc. Adding open and close
> methods in UserDefinedFunction class can solve this problem. The code cloud
> look like:
> {code}
> trait UserDefinedFunction {
> def open(context: UDFContext): Unit = {}
> def close(): Unit = {}
> }
> {code}
> UDFContext contains the information about metric reporters, job parameters,
> distribute cache, etc. The code cloud look like:
> {code}
> class UDFContext(context: RuntimeContext) {
> def getMetricGroup: MetricGroup = ???
> def getDistributedCacheFile(name: String): File = ???
> def getJobParameter(key: String, default: String): String = ???
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
