警告：使用--illegal-access=warn来启用进一步非法反射访问操作的警告
警告：所有非法访问操作将在将来的版本中被拒绝
20/08/07 11:56:33 WARN NativeCodeLoader: 无法加载适用于您的平台的本地Hadoop库...在适用的情况下使用内置的Java类
错误：无法加载com.deeq.CompareDataFrames：com/amazon/deequ/checks/Check
log4j:警告：找不到附加程序，用于记录器（org.apache.spark.util.ShutdownHookManager）。
log4j:警告：请

./spark-submit --class com.deeq.CompareDataFrames--master 
spark://saif-VirtualBox:7077 ~/Downloads/deeq-trial-1.0-SNAPSHOT.jar

import com.amazon.deequ.VerificationResult;
import com.amazon.deequ.VerificationSuite;
import com.amazon.deequ.checks.Check;
import com.amazon.deequ.checks.CheckLevel;
import com.amazon.deequ.checks.CheckStatus;
import com.amazon.deequ.constraints.Constraint;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import scala.Option;
import scala.Tuple2;
import scala.collection.mutable.ArraySeq;
import scala.collection.mutable.Seq;
public class CompareDataFrames {
    public static void main(String[] args) {
        SparkSession session = SparkSession.builder().appName("CompareDataFrames").getOrCreate();
        session.sparkContext().setLogLevel("ALL");
        StructType schema = DataTypes.createStructType(new StructField[]{
                DataTypes.createStructField("CUST_ID", DataTypes.StringType, true),
                DataTypes.createStructField("RECORD_LOCATOR_ID", DataTypes.StringType, true),
                DataTypes.createStructField("EVNT_ID", DataTypes.StringType, true)
        });
        Dataset<Row> first = session.read().option("multiline", "true").schema(schema).json("/home/saif/Downloads/FILE_DEV1.json");
        System.out.println("======= DataSet 1 =======");
        first.printSchema();
        first.show(false);
        Dataset<Row> second = session.read().option("multiline", "true").schema(schema).json("/home/saif/Downloads/FILE_DEV2.json");
        System.out.println("======= DataSet 2 =======");
        second.printSchema();
        second.show(false);
        // This will show all the rows which are present in the first dataset
        // but not present in the second dataset. But the comparison is at row
        // level and not at column level.
        System.out.println("======= Expect =======");
        first.except(second).show();
        StructType one = first.schema();
        JavaPairRDD<String, Row> pair1 = first.toJavaRDD().mapToPair((PairFunction<Row, String, Row>)
                row -> new Tuple2<>(row.getString(1), row));
        JavaPairRDD<String, Row> pair2 = second.toJavaRDD().mapToPair((PairFunction<Row, String, Row>)
                row -> new Tuple2<>(row.getString(1), row));
        System.out.println("======= Pair1 & Pair2 were created =======");
        JavaPairRDD<String, Row> subs = pair1.subtractByKey(pair2);
        JavaRDD<Row> rdd = subs.values();
        Dataset<Row> diff = session.createDataFrame(rdd, one);
        System.out.println("======= Diff Show =======");
        diff.show();
        Seq<Constraint> cons = new ArraySeq<>(0);
        VerificationResult vr = new VerificationSuite().onData(first)
                .addCheck(new Check(CheckLevel.Error(), "unit test", cons)
                        .isComplete("EVNT_ID", Option.empty())
                )
                .run();
        Seq<Check> checkSeq = new ArraySeq<>(0);
        if (vr.status() != CheckStatus.Success()) {
            Dataset<Row> vrr = vr.checkResultsAsDataFrame(session, vr, checkSeq);
            vrr.show(false);
        }
    }
}

<dependencies>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.12</artifactId>
        <version>3.0.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming_2.12</artifactId>
        <version>3.0.0</version>
        <scope>provided</scope>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.12</artifactId>
        <version>3.0.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-catalyst_2.12</artifactId>
        <version>3.0.0</version>
    </dependency>
    <dependency>
        <groupId>com.amazon.deequ</groupId>
        <artifactId>deequ</artifactId>
        <version>1.0.4</version>
    </dependency>
    <dependency>
        <groupId>org.apache.logging.log4j</groupId>
        <artifactId>log4j-core</artifactId>
        <version>2.13.3</version>
    </dependency>
    <dependency>
        <groupId>org.scala-lang.modules</groupId>
        <artifactId>scala-java8-compat_2.13</artifactId>
        <version>0.9.1</version>
    </dependency>
</dependencies>

./spark-submit --class com.deeq.CompareDataFrames --master 
spark://saif-VirtualBox:7077 --jars ~/Downloads/deequ-1.0.4.jar ~/Downloads/deeq-trial-1.0-SNAPSHOT.jar 

./spark-submit --class com.deeq.CompareDataFrames --master 
spark://saif-VirtualBox:7077 --packages com.amazon.deequ:deequ:1.0.4 ~/Downloads/deeq-trial-1.0-SNAPSHOT.jar

spark-submit --class com.deeq.CompareDataFrames --master 
spark://saif-VirtualBox:7077 ~/Downloads/deeq-trial-1.0-SNAPSHOT.jar

<?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">
	<modelVersion>4.0.0</modelVersion>
	<groupId>com.deeq</groupId>
	<artifactId>deeq-trial-1.0-SNAPSHOT</artifactId>
	<version>1.0</version>
	<name>Spark-3.0  Spark  Application</name>
	<url>https://maven.apache.org</url>
	<repositories>
		<repository>
			<id>codelds</id>
			<url>https://code.lds.org/nexus/content/groups/main-repo</url>
		</repository>
		<repository>
			<id>central</id>
			<name>Maven Repository Switchboard</name>
			<layout>default</layout>
			<url>https://repo1.maven.org/maven2</url>
			<snapshots>
				<enabled>false</enabled>
			</snapshots>
		</repository>
	</repositories>
	<properties>
		<maven.compiler.source>1.8</maven.compiler.source>
		<maven.compiler.target>1.8</maven.compiler.target>
		<encoding>UTF-8</encoding>
		<scala.version>2.12.8</scala.version>
		<java.version>1.8</java.version>
		<CodeCacheSize>512m</CodeCacheSize>
		<es.version>2.4.6</es.version>
	</properties>
	<dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.12</artifactId>
            <version>3.0.0</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-catalyst_2.12</artifactId>
            <version>3.0.0</version>
        </dependency>
        <dependency>
            <groupId>com.amazon.deequ</groupId>
            <artifactId>deequ</artifactId>
            <version>1.0.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.13.3</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang.modules</groupId>
            <artifactId>scala-java8-compat_2.13</artifactId>
            <version>0.9.1</version>
        </dependency>
	</dependencies>
	<build>
		<resources>
			<resource>
				<directory>src/main/resources</directory>
			</resource>
		</resources>
		<plugins>
			<plugin>
				<groupId>net.alchim31.maven</groupId>
				<artifactId>scala-maven-plugin</artifactId>
				<version>3.2.2</version>
				<executions>
					<execution>
						<id>eclipse-add-source</id>
						<goals>
							<goal>add-source</goal>
						</goals>
					</execution>
					<execution>
						<id>scala-compile-first</id>
						<phase>process-resources</phase>
						<goals>
							<goal>compile</goal>
						</goals>
					</execution>
					<execution>
						<id>scala-test-compile-first</id>
						<phase>process-test-resources</phase>
						<goals>
							<goal>testCompile</goal>
						</goals>
					</execution>
					<execution>
						<id>attach-scaladocs</id>
						<phase
<details>
<summary>英文:</summary>
Please follow the below approaches to resolve your problem.
**Approach 1.** 
spark submit with `--jars` option,
Download the jar from the following Maven Repo to your machine, https://mvnrepository.com/artifact/com.amazon.deequ/deequ/1.0.4 to `~/Downloads/deequ-1.0.4.jar`

**Approach 2.** 
spark submit with `--packages` option,

**Notes:**
1. The `--repositories` option is required only if some custom repository has to be referenced
By default the maven central repository is used if the `--repositories` option is not provided
When `--packages` option is specified, the submit operation tries to look for the packages and their dependencies in the `~/.ivy2/cache`, `~/.ivy2/jars`, `~/.m2/repository` directories.
If they are not found, then they are downloaded from maven central using ivy and stored under the `~/.ivy2` directory.
**Edit 1:** 
**Approach 3:** 
If the above solutions 1 & 2 is not working then use `maven-shade-plugin` to build the `uber jar` and proceed with the `spark-submit`.
use the below `pom.xml` file for building uber jar using `maven-shade-plugin`. adding the below pom and rebuild your jar and deploy it with `spark-submit`.

</details>