首页 文章

java.lang.NoClassDefFoundError:com中的com / amazonaws / services / s3 / AmazonS3Client

提问于
浏览
0

我有一个java spark进程,我调用它 - spark-submit --class MyClass target / MyJar.jar

这个过程的最后一部分是在本地编写,然后将其复制到s3,因为它需要具有特定的名称(也可以写入s3和mv'ed,为了问题,错误保持不变) .

代码编译并运行但是当它到达下面的代码片段时,我得到以下错误 -

java.lang.NoClassDefFoundError:com / amazonaws / services / s3 / AmazonS3 at java.lang.Class.forName0(Native Method),位于org.apache.spark的java.lang.Class.forName(Class.java:348) . util.Utils $ .classForName(Utils.scala:229)org.apache.spark.deploy.SparkSubmit $ .org $ apache $ spark $ deploy $ SparkSubmit $$ runMain(SparkSubmit.scala:700)at org.apache.spark orde.apache.spark.deploy.SparkSubmit $ .main(SparkSubmit . .scala:126)at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)由java.net.URLClassLoader.findClass(URLClassLoader)引起的:java.lang.ClassNotFoundException:com.amazonaws.services.s3.AmazonS3 .java:381)java.lang.ClassLoader.loadClass(ClassLoader.java:424)java.lang.ClassLoader.loadClass(ClassLoader.java:357)

public static void saveToS3(Dataset<Row> df, String outputBucket, String outputPath) throws IOException {
    String tmpFile = "temp" + Long.toString(System.nanoTime());
    df.coalesce(1).write().option("header", true).csv(tmpFile);
    File directory = new File(tmpFile);
    AmazonS3 s3client = new AmazonS3Client();
    for (File file : directory.listFiles()) {
        if (file.getName().startsWith("part_") || file.getName().endsWith("csv")) {
            s3client.putObject(new PutObjectRequest(outputBucket, getS3path(outputPath), file));
            }
        file.delete();
    }
    directory.delete();
}

我使用以下可能相关的依赖项

<dependency>
            <groupId>com.amazonaws</groupId>
            <artifactId>aws-java-sdk</artifactId>
            <version>1.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-aws</artifactId>
            <version>2.7.2</version>
            <exclusions>
                <exclusion>
                    <groupId>org.slf4j</groupId>
                    <artifactId>slf4j-log4j12</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>log4j</groupId>
                    <artifactId>log4j</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>javax.servlet</groupId>
                    <artifactId>servlet-api</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>org.mortbay.jetty</groupId>
                    <artifactId>servlet-api-2.5</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

任何的想法?

依赖树 -

[INFO] +- org.apache.spark:spark-core_2.11:jar:2.1.0:compile
[INFO] |  +- org.apache.avro:avro-mapred:jar:hadoop2:1.7.7:compile
[INFO] |  |  +- org.apache.avro:avro-ipc:jar:1.7.7:compile
[INFO] |  |  +- org.apache.avro:avro-ipc:jar:tests:1.7.7:compile
[INFO] |  |  +- org.codehaus.jackson:jackson-core-asl:jar:1.9.13:compile
[INFO] |  |  \- org.codehaus.jackson:jackson-mapper-asl:jar:1.9.13:compile
[INFO] |  +- com.twitter:chill_2.11:jar:0.8.0:compile
[INFO] |  |  \- com.esotericsoftware:kryo-shaded:jar:3.0.3:compile
[INFO] |  |     +- com.esotericsoftware:minlog:jar:1.3.0:compile
[INFO] |  |     \- org.objenesis:objenesis:jar:2.1:compile
[INFO] |  +- com.twitter:chill-java:jar:0.8.0:compile
[INFO] |  +- org.apache.xbean:xbean-asm5-shaded:jar:4.4:compile
[INFO] |  +- org.apache.hadoop:hadoop-client:jar:2.2.0:compile
[INFO] |  |  +- org.apache.hadoop:hadoop-hdfs:jar:2.2.0:compile
[INFO] |  |  +- org.apache.hadoop:hadoop-mapreduce-client-app:jar:2.2.0:compile
[INFO] |  |  |  +- org.apache.hadoop:hadoop-mapreduce-client-common:jar:2.2.0:compile
[INFO] |  |  |  |  +- org.apache.hadoop:hadoop-yarn-client:jar:2.2.0:compile
[INFO] |  |  |  |  |  \- com.google.inject:guice:jar:3.0:compile
[INFO] |  |  |  |  |     +- javax.inject:javax.inject:jar:1:compile
[INFO] |  |  |  |  |     \- aopalliance:aopalliance:jar:1.0:compile
[INFO] |  |  |  |  \- org.apache.hadoop:hadoop-yarn-server-common:jar:2.2.0:compile
[INFO] |  |  |  \- org.apache.hadoop:hadoop-mapreduce-client-shuffle:jar:2.2.0:compile
[INFO] |  |  +- org.apache.hadoop:hadoop-yarn-api:jar:2.2.0:compile
[INFO] |  |  +- org.apache.hadoop:hadoop-mapreduce-client-core:jar:2.2.0:compile
[INFO] |  |  |  \- org.apache.hadoop:hadoop-yarn-common:jar:2.2.0:compile
[INFO] |  |  +- org.apache.hadoop:hadoop-mapreduce-client-jobclient:jar:2.2.0:compile
[INFO] |  |  \- org.apache.hadoop:hadoop-annotations:jar:2.2.0:compile
[INFO] |  +- org.apache.spark:spark-launcher_2.11:jar:2.1.0:compile
[INFO] |  +- org.apache.spark:spark-network-common_2.11:jar:2.1.0:compile
[INFO] |  |  \- org.fusesource.leveldbjni:leveldbjni-all:jar:1.8:compile
[INFO] |  +- org.apache.spark:spark-network-shuffle_2.11:jar:2.1.0:compile
[INFO] |  +- org.apache.spark:spark-unsafe_2.11:jar:2.1.0:compile
[INFO] |  +- net.java.dev.jets3t:jets3t:jar:0.7.1:compile
[INFO] |  |  \- commons-httpclient:commons-httpclient:jar:3.1:compile
[INFO] |  +- org.apache.curator:curator-recipes:jar:2.4.0:compile
[INFO] |  |  +- org.apache.curator:curator-framework:jar:2.4.0:compile
[INFO] |  |  +- org.apache.zookeeper:zookeeper:jar:3.4.5:compile
[INFO] |  |  \- com.google.guava:guava:jar:14.0.1:compile
[INFO] |  +- javax.servlet:javax.servlet-api:jar:3.1.0:compile
[INFO] |  +- org.apache.commons:commons-lang3:jar:3.5:compile
[INFO] |  +- org.apache.commons:commons-math3:jar:3.4.1:compile
[INFO] |  +- com.google.code.findbugs:jsr305:jar:1.3.9:compile
[INFO] |  +- org.slf4j:slf4j-api:jar:1.7.16:compile
[INFO] |  +- org.slf4j:jul-to-slf4j:jar:1.7.16:compile
[INFO] |  +- org.slf4j:jcl-over-slf4j:jar:1.7.16:compile
[INFO] |  +- com.ning:compress-lzf:jar:1.0.3:compile
[INFO] |  +- org.xerial.snappy:snappy-java:jar:1.1.2.6:compile
[INFO] |  +- net.jpountz.lz4:lz4:jar:1.3.0:compile
[INFO] |  +- org.roaringbitmap:RoaringBitmap:jar:0.5.11:compile
[INFO] |  +- commons-net:commons-net:jar:2.2:compile
[INFO] |  +- org.scala-lang:scala-library:jar:2.11.8:compile
[INFO] |  +- org.json4s:json4s-jackson_2.11:jar:3.2.11:compile
[INFO] |  |  \- org.json4s:json4s-core_2.11:jar:3.2.11:compile
[INFO] |  |     +- org.json4s:json4s-ast_2.11:jar:3.2.11:compile
[INFO] |  |     +- com.thoughtworks.paranamer:paranamer:jar:2.6:compile
[INFO] |  |     \- org.scala-lang:scalap:jar:2.11.0:compile
[INFO] |  |        \- org.scala-lang:scala-compiler:jar:2.11.0:compile
[INFO] |  |           \- org.scala-lang.modules:scala-parser-combinators_2.11:jar:1.0.1:compile
[INFO] |  +- org.glassfish.jersey.core:jersey-client:jar:2.22.2:compile
[INFO] |  |  +- javax.ws.rs:javax.ws.rs-api:jar:2.0.1:compile
[INFO] |  |  +- org.glassfish.hk2:hk2-api:jar:2.4.0-b34:compile
[INFO] |  |  |  +- org.glassfish.hk2:hk2-utils:jar:2.4.0-b34:compile
[INFO] |  |  |  \- org.glassfish.hk2.external:aopalliance-repackaged:jar:2.4.0-b34:compile
[INFO] |  |  +- org.glassfish.hk2.external:javax.inject:jar:2.4.0-b34:compile
[INFO] |  |  \- org.glassfish.hk2:hk2-locator:jar:2.4.0-b34:compile
[INFO] |  |     \- org.javassist:javassist:jar:3.18.1-GA:compile
[INFO] |  +- org.glassfish.jersey.core:jersey-common:jar:2.22.2:compile
[INFO] |  |  +- javax.annotation:javax.annotation-api:jar:1.2:compile
[INFO] |  |  +- org.glassfish.jersey.bundles.repackaged:jersey-guava:jar:2.22.2:compile
[INFO] |  |  \- org.glassfish.hk2:osgi-resource-locator:jar:1.0.1:compile
[INFO] |  +- org.glassfish.jersey.core:jersey-server:jar:2.22.2:compile
[INFO] |  |  +- org.glassfish.jersey.media:jersey-media-jaxb:jar:2.22.2:compile
[INFO] |  |  \- javax.validation:validation-api:jar:1.1.0.Final:compile
[INFO] |  +- org.glassfish.jersey.containers:jersey-container-servlet:jar:2.22.2:compile
[INFO] |  +- org.glassfish.jersey.containers:jersey-container-servlet-core:jar:2.22.2:compile
[INFO] |  +- io.netty:netty-all:jar:4.0.42.Final:compile
[INFO] |  +- io.netty:netty:jar:3.8.0.Final:compile
[INFO] |  +- com.clearspring.analytics:stream:jar:2.7.0:compile
[INFO] |  +- io.dropwizard.metrics:metrics-core:jar:3.1.2:compile
[INFO] |  +- io.dropwizard.metrics:metrics-jvm:jar:3.1.2:compile
[INFO] |  +- io.dropwizard.metrics:metrics-json:jar:3.1.2:compile
[INFO] |  +- io.dropwizard.metrics:metrics-graphite:jar:3.1.2:compile
[INFO] |  +- com.fasterxml.jackson.module:jackson-module-scala_2.11:jar:2.6.5:compile
[INFO] |  |  +- org.scala-lang:scala-reflect:jar:2.11.7:compile
[INFO] |  |  \- com.fasterxml.jackson.module:jackson-module-paranamer:jar:2.6.5:compile
[INFO] |  +- org.apache.ivy:ivy:jar:2.4.0:compile
[INFO] |  +- oro:oro:jar:2.0.8:compile
[INFO] |  +- net.razorvine:pyrolite:jar:4.13:compile
[INFO] |  +- net.sf.py4j:py4j:jar:0.10.4:compile
[INFO] |  +- org.apache.spark:spark-tags_2.11:jar:2.1.0:compile
[INFO] |  |  \- org.scalatest:scalatest_2.11:jar:2.2.6:compile
[INFO] |  |     \- org.scala-lang.modules:scala-xml_2.11:jar:1.0.2:compile
[INFO] |  +- org.apache.commons:commons-crypto:jar:1.0.0:compile
[INFO] |  \- org.spark-project.spark:unused:jar:1.0.0:compile
[INFO] +- org.apache.hadoop:hadoop-aws:jar:2.7.2:compile
[INFO] |  \- org.apache.hadoop:hadoop-common:jar:2.7.2:compile
[INFO] |     +- commons-cli:commons-cli:jar:1.2:compile
[INFO] |     +- xmlenc:xmlenc:jar:0.52:compile
[INFO] |     +- commons-io:commons-io:jar:2.4:compile
[INFO] |     +- commons-collections:commons-collections:jar:3.2.2:compile
[INFO] |     +- org.mortbay.jetty:jetty:jar:6.1.26:compile
[INFO] |     +- org.mortbay.jetty:jetty-util:jar:6.1.26:compile
[INFO] |     +- javax.servlet.jsp:jsp-api:jar:2.1:runtime
[INFO] |     +- com.sun.jersey:jersey-core:jar:1.9:compile
[INFO] |     +- com.sun.jersey:jersey-json:jar:1.9:compile
[INFO] |     |  +- org.codehaus.jettison:jettison:jar:1.1:compile
[INFO] |     |  +- com.sun.xml.bind:jaxb-impl:jar:2.2.3-1:compile
[INFO] |     |  |  \- javax.xml.bind:jaxb-api:jar:2.2.2:compile
[INFO] |     |  |     +- javax.xml.stream:stax-api:jar:1.0-2:compile
[INFO] |     |  |     \- javax.activation:activation:jar:1.1:compile
[INFO] |     |  +- org.codehaus.jackson:jackson-jaxrs:jar:1.8.3:compile
[INFO] |     |  \- org.codehaus.jackson:jackson-xc:jar:1.8.3:compile
[INFO] |     +- com.sun.jersey:jersey-server:jar:1.9:compile
[INFO] |     |  \- asm:asm:jar:3.1:compile
[INFO] |     +- commons-lang:commons-lang:jar:2.6:compile
[INFO] |     +- commons-configuration:commons-configuration:jar:1.6:compile
[INFO] |     |  +- commons-digester:commons-digester:jar:1.8:compile
[INFO] |     |  |  \- commons-beanutils:commons-beanutils:jar:1.7.0:compile
[INFO] |     |  \- commons-beanutils:commons-beanutils-core:jar:1.8.0:compile
[INFO] |     +- org.apache.avro:avro:jar:1.7.4:compile
[INFO] |     +- com.google.protobuf:protobuf-java:jar:2.5.0:compile
[INFO] |     +- com.google.code.gson:gson:jar:2.2.4:compile
[INFO] |     +- org.apache.hadoop:hadoop-auth:jar:2.7.2:compile
[INFO] |     |  \- org.apache.directory.server:apacheds-kerberos-codec:jar:2.0.0-M15:compile
[INFO] |     |     +- org.apache.directory.server:apacheds-i18n:jar:2.0.0-M15:compile
[INFO] |     |     +- org.apache.directory.api:api-asn1-api:jar:1.0.0-M20:compile
[INFO] |     |     \- org.apache.directory.api:api-util:jar:1.0.0-M20:compile
[INFO] |     +- com.jcraft:jsch:jar:0.1.42:compile
[INFO] |     +- org.apache.curator:curator-client:jar:2.7.1:compile
[INFO] |     +- org.apache.htrace:htrace-core:jar:3.1.0-incubating:compile
[INFO] |     \- org.apache.commons:commons-compress:jar:1.4.1:compile
[INFO] |        \- org.tukaani:xz:jar:1.0:compile
[INFO] +- org.apache.spark:spark-sql_2.10:jar:2.1.0:compile
[INFO] |  +- com.univocity:univocity-parsers:jar:2.2.1:compile
[INFO] |  +- org.apache.spark:spark-sketch_2.10:jar:2.1.0:compile
[INFO] |  +- org.apache.spark:spark-core_2.10:jar:2.1.0:compile
[INFO] |  |  +- com.twitter:chill_2.10:jar:0.8.0:compile
[INFO] |  |  +- org.apache.spark:spark-launcher_2.10:jar:2.1.0:compile
[INFO] |  |  +- org.apache.spark:spark-network-common_2.10:jar:2.1.0:compile
[INFO] |  |  +- org.apache.spark:spark-network-shuffle_2.10:jar:2.1.0:compile
[INFO] |  |  +- org.apache.spark:spark-unsafe_2.10:jar:2.1.0:compile
[INFO] |  |  +- org.json4s:json4s-jackson_2.10:jar:3.2.11:compile
[INFO] |  |  |  \- org.json4s:json4s-core_2.10:jar:3.2.11:compile
[INFO] |  |  |     \- org.json4s:json4s-ast_2.10:jar:3.2.11:compile
[INFO] |  |  \- com.fasterxml.jackson.module:jackson-module-scala_2.10:jar:2.6.5:compile
[INFO] |  +- org.apache.spark:spark-catalyst_2.10:jar:2.1.0:compile
[INFO] |  |  +- org.codehaus.janino:janino:jar:3.0.0:compile
[INFO] |  |  +- org.codehaus.janino:commons-compiler:jar:3.0.0:compile
[INFO] |  |  \- org.antlr:antlr4-runtime:jar:4.5.3:compile
[INFO] |  +- org.apache.spark:spark-tags_2.10:jar:2.1.0:compile
[INFO] |  |  \- org.scalatest:scalatest_2.10:jar:2.2.6:compile
[INFO] |  +- org.apache.parquet:parquet-column:jar:1.8.1:compile
[INFO] |  |  +- org.apache.parquet:parquet-common:jar:1.8.1:compile
[INFO] |  |  \- org.apache.parquet:parquet-encoding:jar:1.8.1:compile
[INFO] |  \- org.apache.parquet:parquet-hadoop:jar:1.8.1:compile
[INFO] |     +- org.apache.parquet:parquet-format:jar:2.3.0-incubating:compile
[INFO] |     \- org.apache.parquet:parquet-jackson:jar:1.8.1:compile
[INFO] +- com.amazonaws:aws-java-sdk:jar:1.7.4:compile
[INFO] |  +- commons-logging:commons-logging:jar:1.1.1:compile
[INFO] |  +- org.apache.httpcomponents:httpclient:jar:4.2:compile
[INFO] |  |  \- org.apache.httpcomponents:httpcore:jar:4.2:compile
[INFO] |  +- commons-codec:commons-codec:jar:1.3:compile
[INFO] |  \- joda-time:joda-time:jar:2.9.9:compile (version selected from constraint [2.2,))
[INFO] +- com.fasterxml.jackson.core:jackson-core:jar:2.7.3:compile
[INFO] +- com.fasterxml.jackson.core:jackson-databind:jar:2.7.3:compile
[INFO] \- com.fasterxml.jackson.core:jackson-annotations:jar:2.7.3:compile

2 回答

  • 0

    您似乎从2014年开始使用really old version of AWS SDK (1.7.4) . Your apache spark is 2.1, which is from 2016.

    Commit history for the AmazonS3Client only goes back to 1.9,因此您的AWS开发工具包可能不存在 .

    您的代码编译的原因是您的代码本身不是问题,但您的一个依赖项是尝试使用旧版SDK没有的更新版本的S3客户端 . 换句话说,这不是代码问题,而是依赖管理问题 . 如果您根本没有直接使用SDK,那么使用更合适的AWS SDK 1.11.X是安全的,如果您使用,则必须将代码哄到这一点 .

    通常情况下,spark-core模块会指出它对aws版本的依赖性,但我认为它是专门排除在自己之外的,所以你可以提供自己的SDK版本供你使用而不会产生任何冲突 . 如果你使用太旧的依赖,它只是打破 .

  • 0

    在按摩我的pom文件后,我能够使用以下pom文件进入稳定版并打包 -

    mvn clean compile assembly:single;

    <?xml version="1.0" encoding="UTF-8"?>
    <project xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
             xmlns="http://maven.apache.org/POM/4.0.0"
             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.group</groupId>
        <artifactId>arifact</artifactId>
        <packaging>jar</packaging>
        <version>1.0-SNAPSHOT</version>
    
        <properties>
            <java.version>1.8</java.version>
            <jdk.version>1.8</jdk.version>
            <maven.compiler.source>1.8</maven.compiler.source>
            <maven.compiler.target>1.8</maven.compiler.target>
        </properties>
    
        <dependencies>
            <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-aws -->
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-aws</artifactId>
                <version>2.8.2</version>
            </dependency>
            <dependency> <!-- Spark dependency -->
                <groupId>org.apache.spark</groupId>
                <artifactId>spark-core_2.11</artifactId>
                <version>2.1.1</version>
            </dependency>
            <dependency>
                <groupId>org.apache.spark</groupId>
                <artifactId>spark-sql_2.11</artifactId>
                <version>2.1.1</version>
            </dependency>
            <dependency>
                <groupId>com.amazonaws</groupId>
                <artifactId>aws-java-sdk-s3</artifactId>
                <version>1.11.229</version>
            </dependency>
        </dependencies>
        <build>
          <plugins>
                  <plugin>
                      <groupId>org.apache.maven.plugins</groupId>
                      <artifactId>maven-compiler-plugin</artifactId>
                      <version>2.3.2</version>
                      <configuration>
                          <source>${jdk.version}</source>
                          <target>${jdk.version}</target>
                      </configuration>
                  </plugin>
              <plugin>
                  <artifactId>maven-assembly-plugin</artifactId>
                  <configuration>
                      <archive>
                          <manifest>
                              <mainClass>com.group.artifact.MainClass</mainClass>
                          </manifest>
                      </archive>
                      <descriptorRefs>
                          <descriptorRef>jar-with-dependencies</descriptorRef>
                      </descriptorRefs>
                  </configuration>
              </plugin>
          </plugins>
        </build>
    </project>
    

相关问题