spark 写入数据到Geomesa(Hbase)

package com.grady.geomesa

import org.apache.spark.sql.jts.PointUDT
import org.apache.spark.sql.types.{IntegerType, StringType, StructField, StructType}
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.{SparkConf, sql}
import org.geotools.data.DataStoreFinder
import org.geotools.geometry.jts.JTSFactoryFinder
import org.locationtech.geomesa.utils.geotools.SchemaBuilder
import org.locationtech.jts.geom.Coordinate
import org.locationtech.geomesa.spark.jts._

import scala.collection.JavaConversions._

object SparkWriteGeomesa {

  val ToGeomesaCatalog = "gradytest"
  val ToGeomesaCatalogFeature = "student"

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("SparkWriteGeomesa")
    val ss = SparkSession.builder().config(conf).getOrCreate().withJTS

    // 组装要写入的数据
    val inDataFrame = gainData(ss)
    inDataFrame.show()
    // 写入数据
    saveData(inDataFrame, ToGeomesaCatalog, ToGeomesaCatalogFeature)

    ss.stop()
  }

  def gainData(ss: SparkSession): sql.DataFrame = {
    val inDataRDD = ss.sparkContext.makeRDD(Array("1,jack,15,11.10,12.10", "2,Lily,16,12.10,13.10", "3,mike,16,14.10,15.10"))
    val rowRDD = inDataRDD.map(_.split(','))
      .map(row => {
        val id = row(0)
        val name = row(1)
        val age = row(2)
        val lon = row(3).toDouble
        val lat = row(4).toDouble
        val factory = JTSFactoryFinder.getGeometryFactory()
        val coordinate = new Coordinate(lon, lat)
        val geom = factory.createPoint(coordinate)
        Row(geom, id, name, age)
      })

    val structType = StructType(
      Seq(
        StructField("geom", PointUDT, nullable = true),
        StructField("studentId", StringType, nullable = true),
        StructField("name", StringType, nullable = true),
        StructField("age", StringType, nullable = true)
      )
    )
    ss.createDataFrame(rowRDD, structType)
  }

  def saveData(inDataFrame: sql.DataFrame, toGeomesaCatalog: String, toGeomesaCatalogFeature: String) = {
    val sft = SchemaBuilder.builder()
      .addPoint("geom", true)
      // 不可用id, id为保留字段
      .addString("studentId")
      .addString("name")
      .addString("age")
      .build(toGeomesaCatalogFeature)
    //geomesa.mix.geometries指定同时支持point 和non-point混合几何特性
    sft.getUserData.put("geomesa.mixed.geometries",Boolean.box(true))

    val params = Map(
      "hbase.zookeepers" -> "10.82.232.64:2181",
      "hbase.catalog"  -> toGeomesaCatalog)

    //创建feature
    DataStoreFinder.getDataStore(params).createSchema(sft)

    inDataFrame.write.format("geomesa")
      .options(params)
      .option("geomesa.feature", toGeomesaCatalogFeature)
      .save()
  }

}

hbase 查看表是否生成:

hbase(main):001:0> list
TABLE
gradytest
gradytest_student_id_v4
gradytest_student_z2_geom_v5


## geomesa 数据会序列化,这里是序列化后的数据
hbase(main):003:0> scan 'gradytest_student_z2_geom_v5'
ROW                               COLUMN+CELL
 \x000\x85\xD7\x8C\x9B\xE0\xE7\xF column=d:, timestamp=2022-02-09T19:21:38.287, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 F000017ed-e37a-4e60-b90f-93fc81e x00\x00\x00\x00\x01\x01@&333333@(333333\x821jac\xEB1\xB5
 0ab0e
 \x000\x922Q\xB1\xD4\x1E\xFF00001 column=d:, timestamp=2022-02-09T19:19:35.603, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 7ed-e35c-4d77-99e7-c6918a06c008  x00\x00\x00\x00\x01\x01@(333333@*333333\x822Lil\xF91\xB6
 \x000\x99\x8A\xA5\xB6\xEBQ\x0200 column=d:, timestamp=2022-02-09T19:21:38.332, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 0017ed-e37a-4ebd-b3a5-a9c7399a63 x00\x00\x00\x00\x01\x01@,333333@.333333\x823mik\xE51\xB6
 5b
 \x000\x99\x8A\xA5\xB6\xEBQ\x0200 column=d:, timestamp=2022-02-09T20:02:28.707, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 0017ed-e5d1-4257-a75d-b0e2372954 x00\x00\x00\x00\x01\x01@,333333@.333333\x823mik\xE51\xB6
 2e
 \x020\x85\xD7\x8C\x9B\xE0\xE7\xF column=d:, timestamp=2022-02-09T19:19:35.334, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 F000017ed-e35c-4d77-a841-b3bcf6f x00\x00\x00\x00\x01\x01@&333333@(333333\x821jac\xEB1\xB5
 aa8ac
 \x020\x922Q\xB1\xD4\x1E\xFF00001 column=d:, timestamp=2022-02-09T19:21:38.285, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 7ed-e37a-4e60-9d7f-66988be48234  x00\x00\x00\x00\x01\x01@(333333@*333333\x822Lil\xF91\xB6
 \x020\x99\x8A\xA5\xB6\xEBQ\x0200 column=d:, timestamp=2022-02-09T19:19:35.335, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 0017ed-e35c-4e9a-8600-97ed8d92c4 x00\x00\x00\x00\x01\x01@,333333@.333333\x823mik\xE51\xB6
 8b
 \x030\x85\xD7\x8C\x9B\xE0\xE7\xF column=d:, timestamp=2022-02-09T20:02:28.622, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 F000017ed-e5d1-41f8-ae71-84db58b x00\x00\x00\x00\x01\x01@&333333@(333333\x821jac\xEB1\xB5
 9478f
 \x030\x922Q\xB1\xD4\x1E\xFF00001 column=d:, timestamp=2022-02-09T20:02:28.662, value=\x03\x00\x04\x02\x00\x0E\x00 \x00"\x00&\x00(\
 7ed-e5d1-41f8-a308-efcee8b70bf9  x00\x00\x00\x00\x01\x01@(333333@*333333\x822Lil\xF91\xB6
9 row(s)

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>geomesa</artifactId>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <geomesa.version>3.1.0</geomesa.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
                <groupId>org.locationtech.geomesa</groupId>
                <artifactId>geomesa-hbase-spark-runtime-hbase2_2.12</artifactId>
                <version>3.3.0</version>
            <exclusions>
                <exclusion>
                    <groupId>org.apache.hadoop</groupId>
                    <artifactId>hadoop-hdfs</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>org.locationtech.geomesa</groupId>
            <artifactId>geomesa-spark-core_2.12</artifactId>
            <version>3.3.0</version>
        </dependency>

        <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>
    </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>
PS: 一定要使用maven-shade-plugin 插件 或其他插件将相关依赖(比如:geomesa-hbase-spark-runtime-hbase2_2.12)打入,否则会报错
posted @ 2022-02-10 15:31  明月照江江  阅读(407)  评论(0编辑  收藏  举报