我正在尝试使用SPARQL查询本地版本的Linked Movie Database。该文件采用N-Triples格式，大小约为450mb。我正在使用servlet来实现。现在，当我传递查询时，servlet处理它需要大约五分钟以上，最后我得到以下异常：
type Exception report
message
description The server encountered an internal error () that prevented it from fulfilling this request.
exception
javax.servlet.ServletException: Servlet execution threw an exception
root cause
java.lang.OutOfMemoryError: Java heap space
java.util.Arrays.copyOfRange(Arrays.java:3209)
java.lang.String.<init>(String.java:215)
java.lang.StringBuilder.toString(StringBuilder.java:430)
org.openjena.riot.tokens.TokenizerText.allBetween(TokenizerText.java:732)
org.openjena.riot.tokens.TokenizerText.parseToken(TokenizerText.java:152)
org.openjena.riot.tokens.TokenizerText.hasNext(TokenizerText.java:69)
org.openjena.atlas.iterator.PeekIterator.fill(PeekIterator.java:37)
org.openjena.atlas.iterator.PeekIterator.next(PeekIterator.java:77)
org.openjena.riot.lang.LangBase.nextToken(LangBase.java:145)
org.openjena.riot.lang.LangNTriples.parseOne(LangNTriples.java:59)
org.openjena.riot.lang.LangNTriples.parseOne(LangNTriples.java:21)
org.openjena.riot.lang.LangNTuple.runParser(LangNTuple.java:58)
org.openjena.riot.lang.LangBase.parse(LangBase.java:75)
org.openjena.riot.system.JenaReaderNTriples2.readWorker(JenaReaderNTriples2.java:28)
org.openjena.riot.system.JenaReaderRIOT.readImpl(JenaReaderRIOT.java:124)
org.openjena.riot.system.JenaReaderRIOT.read(JenaReaderRIOT.java:79)
com.hp.hpl.jena.rdf.model.impl.ModelCom.read(ModelCom.java:226)
com.hp.hpl.jena.util.FileManager.readModelWorker(FileManager.java:395)
com.hp.hpl.jena.util.FileManager.loadModelWorker(FileManager.java:299)
com.hp.hpl.jena.util.FileManager.loadModel(FileManager.java:250)
ServletExample.runQuery(ServletExample.java:92)
ServletExample.doGet(ServletExample.java:62)
javax.servlet.http.HttpServlet.service(HttpServlet.java:627)
javax.servlet.http.HttpServlet.service(HttpServlet.java:729)
note The full stack trace of the root cause is available in the Apache Tomcat/5.5.31 logs.
我的代码是：
import java.io.IOException;
import java.io.PrintWriter;
import javax.servlet.ServletException;
import javax.servlet.http.*;
import com.hp.hpl.jena.query.*;
import com.hp.hpl.jena.rdf.model.*;
import com.hp.hpl.jena.util.FileManager;
public class ServletExample
extends HttpServlet
{
/***********************************/
/* Constants */
/***********************************/
private static final long serialVersionUID = 1L;
public static final String SPARQL_ENDPOINT = "http://data.linkedmdb.org/sparql";
public static final String QUERY ="PREFIX m: <http://data.linkedmdb.org/resource/movie/>"
+"SELECT DISTINCT ?actorName WHERE {"+
"?dir1 m:director_name \"Sofia Coppola\"."+
"?dir2 m:director_name \"Francis Ford Coppola\"."+
"?dir1film m:director ?dir1;"+
"m:actor ?actor."+
"?dir2film m:director ?dir2;"+
"m:actor ?actor."+
"?actor m:actor_name ?actorName."+
"}";
/*"PREFIX m: <http://data.linkedmdb.org/resource/movie/>\n" +
"SELECT DISTINCT ?actorName WHERE {\n" +
" ?dir1 m:director_name %dir_name_1%.\n" +
" ?dir2 m:director_name %dir_name_2%.\n" +
" ?dir1film m:director ?dir1;\n" +
" m:actor ?actor.\n" +
" ?dir2film m:director ?dir2;\n" +
" m:actor ?actor.\n" +
" ?actor m:actor_name ?actorName.\n" +
"}\n" +
"";*/
private static final String HEADER = "<html>\n" +
" <head>\n" +
" <title>results</title>\n" +
" <link href=\"simple.css\" type=\"text/css\" rel=\"stylesheet\" />\n" +
" </head>\n" +
" <body>\n" +
"";
private static final String FOOTER = "</body></html>";
/**
* Respond to HTTP GET request. Will need to be mounted against some URL
* pattern in web.xml
*/
@Override
protected void doGet( HttpServletRequest req, HttpServletResponse resp )
throws ServletException, IOException
{
String dir1 = req.getParameter( "dir1" );//"Sofia";
String dir2 = req.getParameter( "dir2" );//"Francis Ford Coppola";
//String dir1 = "Sofia";
//String dir2 = "Francis Ford Coppola";
if (dir1 == null || dir2 == null || dir1.isEmpty() || dir2.isEmpty()) {
noInput( resp );
}
else {
runQuery( resp, dir1, dir2 );
}
}
protected void noInput( HttpServletResponse resp )
throws IOException
{
header( resp );
resp.getWriter().println( "<p>Please select director names as query params <code>dir1</code> and <code>dir2</code></p>" );
footer( resp );
}
protected void footer( HttpServletResponse resp ) throws IOException {
resp.getWriter().println( FOOTER );
}
protected void header( HttpServletResponse resp ) throws IOException {
resp.getWriter().println( HEADER );
}
protected void runQuery( HttpServletResponse resp, String dir1, String dir2 )
throws IOException
{
PrintWriter out = resp.getWriter();
// Set up the query
// String q = QUERY.replace( "%dir_name_1%", "\"" + dir1 + "\"" )
// .replace( "%dir_name_2%", "\"" + dir2 + "\"" );
String q=QUERY;
Query query = QueryFactory.create( q ) ;
Model model = FileManager.get().loadModel( "e:\\applications\\linkedmdb-18-05-2009-dump\\dump.nt" );
// QueryExecution qexec = QueryExecutionFactory.sparqlService( SPARQL_ENDPOINT, query );
//com.hp.hpl.jena.query.Query query = QueryFactory.create(QUERY);
QueryExecution qexec = QueryExecutionFactory.create(query, model);
// perform the query
ResultSet results = qexec.execSelect();
// generate the output
header( resp );
if (!results.hasNext()) {
out.println( "<p>No results, sorry.</p>" );
}
else {
out.println( "<h1>Results</h1>" );
while (results.hasNext()) {
QuerySolution qs = results.next();
String actorName = qs.getLiteral( "actorName" ).getLexicalForm();
out.println( String.format( "<div>Actor named: %s</div>", actorName ) );
}
}
footer( resp );
}
}
有没有办法解决这个异常？
答案 0 :(得分：1)
您似乎正在使用Jena / RIOT将所有数据加载到内存中。据我所知，LinkedIMDB足够大，可以解决这种方法的问题。你正在做的是将你的所有数据库带到内存中。
增加JVM的堆可能是一种可能的解决方案，但如果您的数据不断增长，它将无法扩展。
正确的解决方案是针对为此大小的数据集设计的Jena的其他配置。这些是：
答案 1 :(得分：0)
Java虚拟机（JVM）中的堆内存不足。增加JVM可用的堆内存量或设计软件以减少内存使用量，例如以较小的块处理内容。
要增加堆内存，请将这些参数添加到servlet容器或应用程序服务器的启动脚本中，执行java二进制文件。这告诉JVM它可能使用多达512兆字节的内存，如果这还不够，请尝试使用更大的值：
-Xmx512m
很难说如何在不看实际代码的情况下改进软件以减少内存使用。