Google cloud dataflow 如何使用其他命令行参数显式设置直接运行程序?
我编写了这个管道,但当我将其作为jar运行时,当我在build.gradle中指定了直接运行程序时,以及当我尝试传递参数--runner=direct或 --runner=Directrunner。下面是我的代码和build.gradle文件。我正在运行gradle任务fatJar来创建jar,导航到build/libs文件夹来运行jar,并看到这个错误。这是我正在使用的命令Google cloud dataflow 如何使用其他命令行参数显式设置直接运行程序?,google-cloud-dataflow,apache-beam,apache-beam-io,Google Cloud Dataflow,Apache Beam,Apache Beam Io,我编写了这个管道,但当我将其作为jar运行时,当我在build.gradle中指定了直接运行程序时,以及当我尝试传递参数--runner=direct或 --runner=Directrunner。下面是我的代码和build.gradle文件。我正在运行gradle任务fatJar来创建jar,导航到build/libs文件夹来运行jar,并看到这个错误。这是我正在使用的命令java-jar filepipeline-all-1.0-SNAPSHOT.jar--input=“../testdat
java-jar filepipeline-all-1.0-SNAPSHOT.jar--input=“../testdata”--output=“./manifest.json”--runner=DirectRunner
在此问题上的任何帮助都将不胜感激
我的文件夹结构如下所示:
--src
--主要
--爪哇
--com.pipeline
--BeamPipeline.java
格雷德尔先生
plugins {
id 'java'
}
group 'com.dustin'
version '1.0-SNAPSHOT'
sourceCompatibility = 1.8
repositories {
mavenCentral()
}
task fatJar(type: Jar) {
manifest {
attributes 'Implementation-Title': 'Gradle Jar File',
'Implementation-Version': version,
'Main-Class': 'com.pipeline.BeamPipeline'
}
baseName = project.name + '-all'
from { configurations.compile.collect { it.isDirectory() ? it : zipTree(it) } }
with jar
}
apply plugin: 'application'
mainClassName = 'src.main.java.com.pipeline.BeamPipeline'
dependencies {
runtime group: 'org.apache.beam', name: 'beam-runners-direct-java', version:'2.8.0'
compile group: 'org.apache.beam', name: 'beam-sdks-java-core', version:'2.8.0'
runtime group: 'org.slf4j', name: 'slf4j-jdk14', version:'1.7.25'
testCompile group: 'junit', name: 'junit', version: '4.12'
compile group: 'org.apache.commons', name: 'commons-lang3', version: '3.0'
compile group: 'commons-io', name: 'commons-io', version: '2.6'
compile group: 'commons-codec', name:'commons-codec', version:'1.12'
compileOnly 'org.projectlombok:lombok:1.18.6'
compile group: 'com.google.code.gson', name: 'gson', version: '2.7'
compile group: 'org.json', name: 'json', version: '20180813'
annotationProcessor 'org.projectlombok:lombok:1.18.6'
}
管道:
package com.pipeline;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.PipelineRunner;
import org.apache.beam.sdk.io.FileIO;
import org.apache.beam.sdk.options.*;
import org.apache.beam.sdk.transforms.*;
import org.apache.beam.sdk.values.KV;
import org.json.JSONObject;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
public class BeamPipeline {
private static final Logger log = LoggerFactory.getLogger(BeamPipeline.class);
public static interface MyOptions extends PipelineOptions {
@Validation.Required
@Description("Input Path(with gs:// prefix)")
String getInput();
void setInput(String value);
@Validation.Required
@Description("Output Path (with gs:// prefix)")
String getOutput();
void setOutput(String value);
}
public static void main(String[] args) {
MyOptions options = PipelineOptionsFactory.fromArgs(args).withValidation().as(MyOptions.class);
Pipeline p = Pipeline.create(options);
File dir = new File(options.getInput());
String output = options.getOutput();
for (File file : dir.listFiles()) {
String inputString = file.toString();
p
.apply("Match Files", FileIO.match().filepattern(inputString))
.apply("Read Files", FileIO.readMatches())
.apply(MapElements.via(new SimpleFunction<FileIO.ReadableFile, KV<String, String>>() {
public KV<String, String> apply(FileIO.ReadableFile file) {
String temp = null;
try {
temp = file.readFullyAsUTF8String();
} catch (IOException e) {
}
String sha256hex = org.apache.commons.codec.digest.DigestUtils.sha256Hex(temp);
return KV.of(file.getMetadata().resourceId().toString(), sha256hex);
}
}))
.apply("Print", ParDo.of(new DoFn<KV<String, String>, Void>() {
@ProcessElement
public void processElement(ProcessContext c) throws IOException {
FileWriter fileWriter = new FileWriter(output,true);
JSONObject obj = new JSONObject();
obj.put(c.element().getKey(), c.element().getValue());
fileWriter.write(obj.toString());
fileWriter.close();
log.info(String.format("File: %s, SHA-256 %s", c.element().getKey(), c.element().getValue()));
}
}));
}
p.run().waitUntilFinish();
}
}
package.com.pipeline;
导入org.apache.beam.sdk.Pipeline;
导入org.apache.beam.sdk.PipelineRunner;
导入org.apache.beam.sdk.io.FileIO;
导入org.apache.beam.sdk.options.*;
导入org.apache.beam.sdk.transforms.*;
导入org.apache.beam.sdk.values.KV;
导入org.json.JSONObject;
导入org.slf4j.Logger;
导入org.slf4j.LoggerFactory;
导入java.io.File;
导入java.io.FileWriter;
导入java.io.IOException;
公共类波束管道{
私有静态最终记录器log=LoggerFactory.getLogger(BeamPipeline.class);
公共静态接口MyOptions扩展了PipelineOptions{
@验证。必需
@说明(“输入路径(带gs://前缀)”)
字符串getInput();
void setInput(字符串值);
@验证。必需
@说明(“输出路径(带gs://前缀)”)
字符串getOutput();
void setOutput(字符串值);
}
公共静态void main(字符串[]args){
MyOptions options=PipelineOptionsFactory.fromArgs(args).withValidation().as(MyOptions.class);
Pipeline p=Pipeline.create(选项);
File dir=新文件(options.getInput());
字符串输出=options.getOutput();
对于(文件:dir.listFiles()){
String inputString=file.toString();
P
.apply(“匹配文件”,FileIO.Match().filepattern(inputString))
.apply(“读取文件”,FileIO.readMatches())
.apply(MapElements.via)(新的SimpleFunction(){
公共KV应用(FileIO.ReadableFile文件){
字符串temp=null;
试一试{
temp=file.readFullyAsUTF8String();
}捕获(IOE异常){
}
字符串sha256hex=org.apache.commons.codec.digest.DigestUtils.sha256hex(temp);
返回KV.of(file.getMetadata().resourceId().toString(),sha256hex);
}
}))
.应用(“打印”,第页,共页(新DoFn)(){
@过程元素
public void processElement(ProcessContext c)引发IOException{
FileWriter FileWriter=新的FileWriter(输出,true);
JSONObject obj=新的JSONObject();
对象put(c.element().getKey(),c.element().getValue());
write(obj.toString());
fileWriter.close();
log.info(String.format(“文件:%s,SHA-256%s”,c.element().getKey(),c.element().getValue());
}
}));
}
p、 run().waitUntilFinish();
}
}
beam runners direct java
作为运行时依赖项添加,因此不会添加到fat jar中。
您可以添加beam runners directjava
作为编译时依赖项来使用它
plugins {
id 'java'
}
group 'com.dustin'
version '1.0-SNAPSHOT'
sourceCompatibility = 1.8
repositories {
mavenCentral()
}
task fatJar(type: Jar) {
manifest {
attributes 'Implementation-Title': 'Gradle Jar File',
'Implementation-Version': version,
'Main-Class': 'com.pipeline.BeamPipeline'
}
baseName = project.name + '-all'
from { configurations.compile.collect { it.isDirectory() ? it : zipTree(it) } }
with jar
}
apply plugin: 'application'
mainClassName = 'src.main.java.com.pipeline.BeamPipeline'
dependencies {
compile group: 'org.apache.beam', name: 'beam-runners-direct-java', version:'2.8.0'
compile group: 'org.apache.beam', name: 'beam-sdks-java-core', version:'2.8.0'
runtime group: 'org.slf4j', name: 'slf4j-jdk14', version:'1.7.25'
testCompile group: 'junit', name: 'junit', version: '4.12'
compile group: 'org.apache.commons', name: 'commons-lang3', version: '3.0'
compile group: 'commons-io', name: 'commons-io', version: '2.6'
compile group: 'commons-codec', name:'commons-codec', version:'1.12'
compileOnly 'org.projectlombok:lombok:1.18.6'
compile group: 'com.google.code.gson', name: 'gson', version: '2.7'
compile group: 'org.json', name: 'json', version: '20180813'
annotationProcessor 'org.projectlombok:lombok:1.18.6'
}
或者,如果您不想用fatjar打包DirectRunner
,而只想将其用于测试,则可以创建单独的DirectRunner
jar,并在运行管道时将其添加到类部分
plugins {
id 'java'
}
group 'com.dustin'
version '1.0-SNAPSHOT'
sourceCompatibility = 1.8
repositories {
mavenCentral()
}
task fatJar(type: Jar) {
manifest {
attributes 'Implementation-Title': 'Gradle Jar File',
'Implementation-Version': version,
'Main-Class': 'com.pipeline.BeamPipeline'
}
baseName = project.name + '-all'
from { configurations.compile.collect { it.isDirectory() ? it : zipTree(it) } }
with jar
}
task directrunnerjar(type: Jar) {
manifest {
attributes 'Implementation-Title': 'Gradle Jar File',
'Implementation-Version': version,
'Main-Class': 'com.pipeline.BeamPipeline'
}
baseName = project.name + '-runtime'
from { configurations.runtime.collect { it.isDirectory() ? it : zipTree(it) } }
with jar
}
apply plugin: 'application'
mainClassName = 'src.main.java.com.pipeline.BeamPipeline'
dependencies {
runtime group: 'org.apache.beam', name: 'beam-runners-direct-java', version:'2.8.0'
compile group: 'org.apache.beam', name: 'beam-sdks-java-core', version:'2.8.0'
runtime group: 'org.slf4j', name: 'slf4j-jdk14', version:'1.7.25'
testCompile group: 'junit', name: 'junit', version: '4.12'
compile group: 'org.apache.commons', name: 'commons-lang3', version: '3.0'
compile group: 'commons-io', name: 'commons-io', version: '2.6'
compile group: 'commons-codec', name:'commons-codec', version:'1.12'
compileOnly 'org.projectlombok:lombok:1.18.6'
compile group: 'com.google.code.gson', name: 'gson', version: '2.7'
compile group: 'org.json', name: 'json', version: '20180813'
annotationProcessor 'org.projectlombok:lombok:1.18.6'
}
java-cp“libs/myartifact-runtime-1.0-SNAPSHOT.jar:libs/filepipeline-all-1.0-SNAPSHOT”com.pipeline.BeamPipeline--input=“../testdata”--output=“/manifest.json”--runner=DirectRunner