sedona(Geospark)读取csv
package com.grady.sedona
import org.apache.sedona.sql.utils.SedonaSQLRegistrator
import org.apache.sedona.viz.core.Serde.SedonaVizKryoRegistrator
import org.apache.spark.serializer.KryoSerializer
import org.apache.spark.sql.SparkSession
object SedonaReadCsv {
// hdfs 文件位置
val csvPointInputLocation = "/tmp/jiang/" + "testpoint.csv"
def main(args: Array[String]): Unit = {
val ss:SparkSession = SparkSession.builder()
.config("spark.serializer",classOf[KryoSerializer].getName)
.config("spark.kryo.registrator", classOf[SedonaVizKryoRegistrator].getName)
.appName("SedonaAnalysisScv").getOrCreate()
SedonaSQLRegistrator.registerAll(ss)
readCsv(ss)
ss.stop()
}
def readCsv(ss: SparkSession): Unit = {
val pointCsvDF = ss.read
.format("csv")
.option("delimiter",",")
.option("header","false")
.load(csvPointInputLocation)
pointCsvDF.createOrReplaceTempView("test_point_csv")
pointCsvDF.show(10)
val pointDF = ss.sql("select ST_Point(cast(test_point_csv._c0 as Decimal(24,20)),cast(test_point_csv._c1 as Decimal(24,20))) as pointshape from test_point_csv")
pointCsvDF.createOrReplaceTempView("test_point")
pointDF.show()
}
}
pom.xml
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<artifactId>spark-practise</artifactId>
<groupId>org.example</groupId>
<version>1.0-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>sedona</artifactId>
<properties>
<maven.compiler.source>8</maven.compiler.source>
<maven.compiler.target>8</maven.compiler.target>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-yarn_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<!-- sedona -->
<dependency>
<groupId>org.apache.sedona</groupId>
<artifactId>sedona-core-3.0_2.12</artifactId>
<version>1.1.1-incubating</version>
</dependency>
<dependency>
<groupId>org.apache.sedona</groupId>
<artifactId>sedona-sql-3.0_2.12</artifactId>
<version>1.1.1-incubating</version>
</dependency>
<dependency>
<groupId>org.apache.sedona</groupId>
<artifactId>sedona-viz-3.0_2.12</artifactId>
<version>1.1.1-incubating</version>
</dependency>
<dependency>
<groupId>org.locationtech.jts</groupId>
<artifactId>jts-core</artifactId>
<version>1.18.0</version>
</dependency>
</dependencies>
<build>
<resources>
<resource>
<directory>src/main/resources</directory>
<filtering>true</filtering>
</resource>
</resources>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
<scalaVersion>${scala.version}</scalaVersion>
</configuration>
<executions>
<execution>
<id>scala-compile-first</id>
<phase>process-resources</phase>
<goals>
<goal>add-source</goal>
<goal>compile</goal>
</goals>
</execution>
<execution>
<id>scala-test-compile</id>
<phase>process-test-resources</phase>
<goals>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.2.1</version>
<configuration>
<artifactSet>
<excludes>
<exclude>org.slf4j:*</exclude>
</excludes>
</artifactSet>
</configuration>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<createDependencyReducedPom>false</createDependencyReducedPom>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
<transformers>
<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
执行spark-submit --master yarn --driver-memory=2G --class com.grady.sedona.SedonaReadCsv /app/data/appdeploy/sedona-1.0-SNAPSHOT.jar
日志:
+----+-----+
| _c0| _c1|
+----+-----+
| 1.1|101.1|
| 2.1|102.1|
| 3.1|103.1|
| 4.1|104.1|
| 5.1|105.1|
| 6.1|106.1|
| 7.1|107.1|
| 8.1|108.1|
| 9.1|109.1|
|10.1|110.1|
+----+-----+
+------------------+
| pointshape|
+------------------+
| POINT (1.1 101.1)|
| POINT (2.1 102.1)|
| POINT (3.1 103.1)|
| POINT (4.1 104.1)|
| POINT (5.1 105.1)|
| POINT (6.1 106.1)|
| POINT (7.1 107.1)|
| POINT (8.1 108.1)|
| POINT (9.1 109.1)|
|POINT (10.1 110.1)|
|POINT (11.1 111.1)|
|POINT (12.1 112.1)|
|POINT (13.1 113.1)|
|POINT (14.1 114.1)|
|POINT (15.1 115.1)|
|POINT (16.1 116.1)|
|POINT (17.1 117.1)|
|POINT (18.1 118.1)|
|POINT (19.1 119.1)|
|POINT (20.1 120.1)|
+------------------+
only showing top 20 rows