Github user xubo245 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/2181#discussion_r184578212
--- Diff:
examples/spark2/src/main/scala/org/apache/carbondata/examples/DirectSQLExample.scala
---
@@ -0,0 +1,114 @@
+/*
+ * 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.carbondata.examples
+
+import java.io.File
+
+import org.apache.commons.io.FileUtils
+
+import org.apache.carbondata.core.metadata.datatype.DataTypes
+import org.apache.carbondata.examples.util.ExampleUtils
+import org.apache.carbondata.sdk.file.{CarbonWriter, Field, Schema}
+
+/**
+ * Running SQL on carbondata files directly
+ */
+object DirectSQLExample {
+
+ // prepare SDK writer output
+ def buildTestData(
+ path: String,
+ num: Int = 3,
+ persistSchema: Boolean = false): Any = {
+
+ // getCanonicalPath gives path with \, so code expects /. Need to
handle in code ?
+ val writerPath = path.replace("\\", "/");
+
+ val fields: Array[Field] = new Array[Field](3)
+ fields(0) = new Field("name", DataTypes.STRING)
+ fields(1) = new Field("age", DataTypes.INT)
+ fields(2) = new Field("height", DataTypes.DOUBLE)
+
+ try {
+ val builder = CarbonWriter.builder()
+ val writer =
+ if (persistSchema) {
+ builder.persistSchemaFile(true)
+ builder.withSchema(new
Schema(fields)).outputPath(writerPath).isTransactionalTable(true)
+ .uniqueIdentifier(
+ System.currentTimeMillis)
+ .buildWriterForCSVInput()
+ } else {
+ builder.withSchema(new
Schema(fields)).outputPath(writerPath).isTransactionalTable(true)
+ .uniqueIdentifier(
+ System.currentTimeMillis).withBlockSize(2)
+ .buildWriterForCSVInput()
+ }
+ var i = 0
+ var row = num
+ while (i < row) {
+ writer.write(Array[String]("robot" + i, String.valueOf(i),
String.valueOf(i.toDouble / 2)))
+ i += 1
+ }
+ writer.close()
+ } catch {
+ case ex: Exception => None
+ case e => None
+ }
+ }
+
+ def cleanTestData(path: String): Unit = {
+ FileUtils.deleteDirectory(new File(path))
+ }
+
+ // scalastyle:off
+ def main(args: Array[String]) {
+ val cc = ExampleUtils.createCarbonSession("DirectSQLExample")
+ val rootPath = new File(this.getClass.getResource("/").getPath
+ + "../../../..").getCanonicalPath
+ System.setProperty("path.target", s"$rootPath/examples/spark2/target")
+ val path = s"$rootPath/examples/spark2/target/carbonFile/"
+
+ import cc._
+ // 1. generate data file
+ cleanTestData(path)
+ buildTestData(path, 100)
+ val readPath = path + "Fact/Part0/Segment_null"
+
+ println("Running SQL on carbon files directly")
+ try {
+ // 2. run queries
+ // 2.1 read data
+ sql("drop table if exists t1")
+ sql(s"""CREATE TABLE t1 USING carbonfile OPTIONS (PATH '$readPath')
""")
+ println("Reading data by SDK:")
+ sql("select count(*) from t1").show();
+
+ // 2.1 direct sql
+ //TODO: support more than one carbonfile
+ sql(s"""select * FROM carbonfile.`$readPath` limit
10""".stripMargin).show()
+ sql(s"""select count(*) FROM carbonfile.`$readPath`
""".stripMargin).show()
+ } catch {
+ case e: Exception => println(e.getMessage)
--- End diff --
ok, done
---
