我有一个rpt文件，使用它我将以pdf格式生成多个报告。使用inet清除报告中的Engine类。这个过程需要很长时间，因为我要生成近10000个报告。我可以使用Mutli线程或其他方法来加速这个过程吗？
任何有关如何做到这一点的帮助都会有所帮助
我的部分代码。
//Loops
Engine eng = new Engine(Engine.EXPORT_PDF);
eng.setReportFile(rpt); //rpt is the report name
if (cn.isClosed() || cn == null ) {
cn = ds.getConnection();
}
eng.setConnection(cn);
System.out.println(" After set connection");
eng.setPrompt(data[i], 0);
ReportProperties repprop = eng.getReportProperties();
repprop.setPaperOrient(ReportProperties.DEFAULT_PAPER_ORIENTATION, ReportProperties.PAPER_FANFOLD_US);
eng.execute();
System.out.println(" After excecute");
try {
PDFExportThread pdfExporter = new PDFExportThread(eng, sFileName, sFilePath);
pdfExporter.execute();
} catch (Exception e) {
e.printStackTrace();
}
PDFExportThread执行
public void execute() throws IOException {
FileOutputStream fos = null;
try {
String FileName = sFileName + "_" + (eng.getPageCount() - 1);
File file = new File(sFilePath + FileName + ".pdf");
if (!file.getParentFile().exists()) {
file.getParentFile().mkdirs();
}
if (!file.exists()) {
file.createNewFile();
}
fos = new FileOutputStream(file);
for (int k = 1; k <= eng.getPageCount(); k++) {
fos.write(eng.getPageData(k));
}
fos.flush();
fos.close();
} catch (Exception e) {
e.printStackTrace();
} finally {
if (fos != null) {
fos.close();
fos = null;
}
}
}
答案 0 :(得分：2)
这是一个非常基本的代码。在池中具有固定大小线程的ThreadPoolExecutor是主干。
一些注意事项：
希望这有帮助。
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.sql.Connection;
import java.util.concurrent.Executors;
import java.util.concurrent.ThreadPoolExecutor;
import java.util.concurrent.TimeUnit;
public class RunEngine {
public static void main(String[] args) throws Exception {
final String rpt = "/tmp/rpt/input/rpt-1.rpt";
final String sFilePath = "/tmp/rpt/output/";
final String sFileName = "pdfreport";
final Object[] data = new Object[10];
ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(10);
for (int i = 0; i < data.length; i++) {
PDFExporterRunnable runnable = new PDFExporterRunnable(rpt, data[i], sFilePath, sFileName, i);
executor.execute(runnable);
}
executor.shutdown();
executor.awaitTermination(1L, TimeUnit.HOURS);
Engine.stopAll();
Engine.shutdown();
}
private static class PDFExporterRunnable implements Runnable {
private final String rpt;
private final Object data;
private final String sFilePath;
private final String sFileName;
private final int runIndex;
public PDFExporterRunnable(String rpt, Object data, String sFilePath,
String sFileName, int runIndex) {
this.rpt = rpt;
this.data = data;
this.sFilePath = sFilePath;
this.sFileName = sFileName;
this.runIndex = runIndex;
}
@Override
public void run() {
// Loops
Engine eng = new Engine(Engine.EXPORT_PDF);
eng.setReportFile(rpt); // rpt is the report name
Connection cn = null;
/*
* DB connection related code. Check and use.
*/
//if (cn.isClosed() || cn == null) {
//cn = ds.getConnection();
//}
eng.setConnection(cn);
System.out.println(" After set connection");
eng.setPrompt(data, 0);
ReportProperties repprop = eng.getReportProperties();
repprop.setPaperOrient(ReportProperties.DEFAULT_PAPER_ORIENTATION,
ReportProperties.PAPER_FANFOLD_US);
eng.execute();
System.out.println(" After excecute");
FileOutputStream fos = null;
try {
String FileName = sFileName + "_" + runIndex;
File file = new File(sFilePath + FileName + ".pdf");
if (!file.getParentFile().exists()) {
file.getParentFile().mkdirs();
}
if (!file.exists()) {
file.createNewFile();
}
fos = new FileOutputStream(file);
for (int k = 1; k <= eng.getPageCount(); k++) {
fos.write(eng.getPageData(k));
}
fos.flush();
fos.close();
} catch (Exception e) {
e.printStackTrace();
} finally {
if (fos != null) {
try {
fos.close();
} catch (IOException e) {
e.printStackTrace();
}
fos = null;
}
}
}
}
/*
* Dummy classes to avoid compilation errors.
*/
private static class ReportProperties {
public static final String PAPER_FANFOLD_US = null;
public static final String DEFAULT_PAPER_ORIENTATION = null;
public void setPaperOrient(String defaultPaperOrientation, String paperFanfoldUs) {
}
}
private static class Engine {
public static final int EXPORT_PDF = 1;
public Engine(int exportType) {
}
public static void shutdown() {
}
public static void stopAll() {
}
public void setPrompt(Object singleData, int i) {
}
public byte[] getPageData(int k) {
return null;
}
public int getPageCount() {
return 0;
}
public void execute() {
}
public ReportProperties getReportProperties() {
return null;
}
public void setConnection(Connection cn) {
}
public void setReportFile(String reportFile) {
}
}
}
答案 1 :(得分：1)
我会提供这个“答案”作为一个可能的快速＆amp;肮脏的解决方案，让您开始并行化工作。
您将构建一个渲染农场。 我不认为在java中有一个简单的方法可以做到这一点;我希望有人发布一个答案，展示如何在几行代码中并行化您的示例。但在此之前，这有望帮助您取得一些进展。
您将在同一个JVM实例中进行有限的扩展。 但是......让我们看看你能走多远，看看它是否足够。
您可能想要一个地方来保存每个报告的状态，例如“工作单位”。
如果您需要重新启动所有内容（可能是您的服务器崩溃）并且您不想重新运行到目前为止的所有报告，您需要这样做。
你有很多方法可以做到这一点;数据库，检查报告文件夹中是否存在“已完成”文件（不足以存在* .pdf，因为这可能是不完整的...对于xyz_200.pdf，您可以将空xyz_200.done或xyz_200 .err文件，以帮助重新运行任何问题子... ...当您编写该文件操作/检查/初始化逻辑时，似乎可能更容易向您的数据库添加列，其中包含列表工作待完成。）
您不希望使系统饱和并且并行运行一千个报告。
也许10。
也许100。
可能不是5,000。
您需要进行一些规模研究，看看是什么让您接近80％到90％的系统利用率。
过于复杂，超出了Stack Exchange答案的范围。 您必须在运行类似下面的工作程序的多个系统上启动JVM，并且可以从共享的“队列”结构中提取工作项的报表管理器，再次数据库表可能比执行某些文件更容易基于（或网络馈送）。
警告：这些代码都没有经过充分测试，它几乎肯定会有大量的拼写错误，逻辑错误和糟糕的设计。使用风险自负。
所以无论如何......我确实想给你一个基本的任务跑步者的基本想法。 用以下代码替换问题中的“//循环”示例：
这或多或少做了你的示例代码所做的事情，修改后将大部分工作推送到ReportWorker（新类，见下文）。很多东西似乎都包含在原始问题的“// Loop”示例中，所以我不打算对其进行逆向工程。
fwiw，我不清楚“rpt”和“data [i]”来自哪里，所以我修改了一些测试数据。
public class Main {
public static boolean complete( String data ) {
return false; // for testing nothing is complete.
}
public static void main(String args[] ) {
String data[] = new String[] {
"A",
"B",
"C",
"D",
"E" };
String rpt = "xyz";
// Loop
ReportManager reportMgr = new ReportManager(); // a new helper class (see below), it assigns/monitors work.
long startTime = System.currentTimeMillis();
for( int i = 0; i < data.length; ++i ) {
// complete is something you should write that knows if a report "unit of work"
// finished successfully.
if( !complete( data[i] ) ) {
reportMgr.assignWork( rpt, data[i] ); // so... where did values for your "rpt" variable come from?
}
}
reportMgr.waitForWorkToFinish(); // out of new work to assign, let's wait until everything in-flight complete.
long endTime = System.currentTimeMillis();
System.out.println("Done. Elapsed time = " + (endTime - startTime)/1000 +" seconds.");
}
}
这个类不是线程安全的，只是让你的原始循环继续调用assignWork（）直到你没有报告来分配然后继续调用它直到完成所有工作，例如waitForWorkToFinish（），如上所示。 （fwiw，我认为你不能说这里的任何类都特别是线程安全的。）
public class ReportManager {
public int polling_delay = 500; // wait 0.5 seconds for testing.
//public int polling_delay = 60 * 1000; // wait 1 minute.
// not high throughput millions of reports / second, we'll run at a slower tempo.
public int nWorkers = 3; // just 3 for testing.
public int assignedCnt = 0;
public ReportWorker workers[];
public ReportManager() {
// initialize our manager.
workers = new ReportWorker[ nWorkers ];
for( int i = 0; i < nWorkers; ++i ) {
workers[i] = new ReportWorker( i );
System.out.println("Created worker #"+i);
}
}
private ReportWorker handleWorkerError( int i ) {
// something went wrong, update our "report" status as one of the reports failed.
System.out.println("handlerWokerError(): failure in "+workers[i]+", resetting worker.");
workers[i].teardown();
workers[i] = new ReportWorker( i ); // just replace everything.
return workers[i]; // the new worker will, incidentally, be avaialble.
}
private ReportWorker handleWorkerComplete( int i ) {
// this unit of work was completed, update our "report" status tracker as success.
System.out.println("handleWorkerComplete(): success in "+workers[i]+", resetting worker.");
workers[i].teardown();
workers[i] = new ReportWorker( i ); // just replace everything.
return workers[i]; // the new worker will, incidentally, be avaialble.
}
private int activeWorkerCount() {
int activeCnt = 0;
for( int i = 0; i < nWorkers; ++i ) {
ReportWorker worker = workers[i];
System.out.println("activeWorkerCount() i="+i+", checking worker="+worker);
if( worker.hasError() ) {
worker = handleWorkerError( i );
}
if( worker.isComplete() ) {
worker = handleWorkerComplete( i );
}
if( worker.isInitialized() || worker.isRunning() ) {
++activeCnt;
}
}
System.out.println("activeWorkerCount() activeCnt="+activeCnt);
return activeCnt;
}
private ReportWorker getAvailableWorker() {
// check each worker to see if anybody recently completed...
// This (rather lazily) creates completely new ReportWorker instances.
// You might want to try pooling (salvaging and reinitializing them)
// to see if that helps your performance.
System.out.println("\n-----");
ReportWorker firstAvailable = null;
for( int i = 0; i < nWorkers; ++i ) {
ReportWorker worker = workers[i];
System.out.println("getAvailableWorker(): i="+i+" worker="+worker);
if( worker.hasError() ) {
worker = handleWorkerError( i );
}
if( worker.isComplete() ) {
worker = handleWorkerComplete( i );
}
if( worker.isAvailable() && firstAvailable==null ) {
System.out.println("Apparently worker "+worker+" is 'available'");
firstAvailable = worker;
System.out.println("getAvailableWorker(): i="+i+" now firstAvailable = "+firstAvailable);
}
}
return firstAvailable; // May (or may not) be null.
}
public void assignWork( String rpt, String data ) {
ReportWorker worker = getAvailableWorker();
while( worker == null ) {
System.out.println("assignWork: No workers available, sleeping for "+polling_delay);
try { Thread.sleep( polling_delay ); }
catch( InterruptedException e ) { System.out.println("assignWork: sleep interrupted, ignoring exception "+e); }
// any workers avaialble now?
worker = getAvailableWorker();
}
++assignedCnt;
worker.initialize( rpt, data ); // or whatever else you need.
System.out.println("assignment #"+assignedCnt+" given to "+worker);
Thread t = new Thread( worker );
t.start( ); // that is pretty much it, let it go.
}
public void waitForWorkToFinish() {
int active = activeWorkerCount();
while( active >= 1 ) {
System.out.println("waitForWorkToFinish(): #active workers="+active+", waiting...");
// wait a minute....
try { Thread.sleep( polling_delay ); }
catch( InterruptedException e ) { System.out.println("assignWork: sleep interrupted, ignoring exception "+e); }
active = activeWorkerCount();
}
}
}
public class ReportWorker implements Runnable {
int test_delay = 10*1000; //sleep for 10 seconds.
// (actual code would be generating PDF output)
public enum StatusCodes { UNINITIALIZED,
INITIALIZED,
RUNNING,
COMPLETE,
ERROR };
int id = -1;
StatusCodes status = StatusCodes.UNINITIALIZED;
boolean initialized = false;
public String rpt = "";
public String data = "";
//Engine eng;
//PDFExportThread pdfExporter;
//DataSource_type cn;
public boolean isInitialized() { return initialized; }
public boolean isAvailable() { return status == StatusCodes.UNINITIALIZED; }
public boolean isRunning() { return status == StatusCodes.RUNNING; }
public boolean isComplete() { return status == StatusCodes.COMPLETE; }
public boolean hasError() { return status == StatusCodes.ERROR; }
public ReportWorker( int id ) {
this.id = id;
}
public String toString( ) {
return "ReportWorker."+id+"("+status+")/"+rpt+"/"+data;
}
// the example code doesn't make clear if there is a relationship between rpt & data[i].
public void initialize( String rpt, String data /* data[i] in original code */ ) {
try {
this.rpt = rpt;
this.data = data;
/* uncomment this part where you have the various classes availble.
* I have it commented out for testing.
cn = ds.getConnection();
Engine eng = new Engine(Engine.EXPORT_PDF);
eng.setReportFile(rpt); //rpt is the report name
eng.setConnection(cn);
eng.setPrompt(data, 0);
ReportProperties repprop = eng.getReportProperties();
repprop.setPaperOrient(ReportProperties.DEFAULT_PAPER_ORIENTATION, ReportProperties.PAPER_FANFOLD_US);
*/
status = StatusCodes.INITIALIZED;
initialized = true; // want this true even if we're running.
} catch( Exception e ) {
status = StatusCodes.ERROR;
throw new RuntimeException("initialze(rpt="+rpt+", data="+data+")", e);
}
}
public void run() {
status = StatusCodes.RUNNING;
System.out.println("run().BEGIN: "+this);
try {
// delay for testing.
try { Thread.sleep( test_delay ); }
catch( InterruptedException e ) { System.out.println(this+".run(): test interrupted, ignoring "+e); }
/* uncomment this part where you have the various classes availble.
* I have it commented out for testing.
eng.execute();
PDFExportThread pdfExporter = new PDFExportThread(eng, sFileName, sFilePath);
pdfExporter.execute();
*/
status = StatusCodes.COMPLETE;
System.out.println("run().END: "+this);
} catch( Exception e ) {
System.out.println("run().ERROR: "+this);
status = StatusCodes.ERROR;
throw new RuntimeException("run(rpt="+rpt+", data="+data+")", e);
}
}
public void teardown() {
if( ! isInitialized() || isRunning() ) {
System.out.println("Warning: ReportWorker.teardown() called but I am uninitailzied or running.");
// should never happen, fatal enough to throw an exception?
}
/* commented out for testing.
try { cn.close(); }
catch( Exception e ) { System.out.println("Warning: ReportWorker.teardown() ignoring error on connection close: "+e); }
cn = null;
*/
// any need to close things on eng?
// any need to close things on pdfExporter?
}
}