inteligr8/alfresco-community-repo
1
0
Fork 0
mirror of https://github.com/Alfresco/alfresco-community-repo.git synced 2025-10-08 14:51:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

MNT-16709 : Metadata extraction on 200MB PDF file causes large heap utilization

Browse Source 
- added concurrent extraction limit
   - added max document size limit

git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/BRANCHES/DEV/5.2.N/root@131709 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
This commit is contained in:
Andreea Dragoi
2016-10-24 12:13:50 +00:00
parent 2b4db66fbe
commit c95cbaccd9
8 changed files with 282 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
source/test-java/org/alfresco/repo/content/metadata/PdfBoxMetadataExtracterTest.java
View File

@@ -25,12 +25,18 @@
*/
package org.alfresco.repo.content.metadata;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.Serializable;
import java.util.Calendar;
import java.util.HashMap;
import java.util.Map;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.TimeUnit;
import org.alfresco.model.ContentModel;
import org.alfresco.repo.content.MimetypeMap;
import org.alfresco.repo.content.transform.AbstractContentTransformerTest;
import org.alfresco.service.cmr.repository.datatype.DefaultTypeConverter;
import org.alfresco.service.namespace.QName;
import org.apache.pdfbox.util.DateConverter;
@@ -42,14 +48,25 @@ import org.apache.pdfbox.util.DateConverter;
*/
public class PdfBoxMetadataExtracterTest extends AbstractMetadataExtracterTest
{
private PdfBoxMetadataExtracter extracter;
private PdfBoxMetadataExtracter extracter;
private static final int MAX_CONCURENT_EXTRACTIONS = 5;
private static final double MAX_DOC_SIZE_MB = 0.03;
@Override
public void setUp() throws Exception
{
super.setUp();
extracter = new PdfBoxMetadataExtracter();
extracter.setDictionaryService(dictionaryService);
extracter.setDictionaryService(dictionaryService);
MetadataExtracterLimits pdfLimit = new MetadataExtracterLimits();
pdfLimit.setMaxConcurrentExtractionsCount(MAX_CONCURENT_EXTRACTIONS);
pdfLimit.setMaxDocumentSizeMB(MAX_DOC_SIZE_MB);
Map<String,MetadataExtracterLimits> limits = new HashMap<>();
limits.put(MimetypeMap.MIMETYPE_PDF,pdfLimit);
extracter.setMimetypeLimits(limits);
extracter.register();
}
@@ -107,5 +124,49 @@ public class PdfBoxMetadataExtracterTest extends AbstractMetadataExtracterTest
assertEquals(52, c.get(Calendar.MINUTE));
assertEquals(58, c.get(Calendar.SECOND));
//assertEquals(0, c.get(Calendar.MILLISECOND));
}
public void testConcurrentExtractions() throws InterruptedException
{
int threadNum = 10;
final CountDownLatch extractionsCountDown = new CountDownLatch(threadNum);
for (int i = 0; i < threadNum; i++)
{
Thread t = new Thread(new Runnable()
{
@Override
public void run()
{
try
{
Map<QName, Serializable> properties = extractFromMimetype(MimetypeMap.MIMETYPE_PDF);
if (!properties.isEmpty())
{
extractionsCountDown.countDown();
}
}
catch (Exception e)
{
e.printStackTrace();
}
}
});
t.start();
}
extractionsCountDown.await(1000, TimeUnit.MILLISECONDS);
long rejectedExtractions = extractionsCountDown.getCount();
assertTrue("Wrong number of rejected extractions", rejectedExtractions == (threadNum - MAX_CONCURENT_EXTRACTIONS));
}
public void testMaxDocumentSizeLimit() throws Exception
{
File sourceFile = AbstractContentTransformerTest.loadNamedQuickTestFile("quick-size-limit.pdf");
if (sourceFile == null)
{
throw new FileNotFoundException("No quick-size-limit.pdf file found for test");
}
Map<QName, Serializable> properties = extractFromFile(sourceFile, MimetypeMap.MIMETYPE_PDF);
assertTrue(properties.isEmpty());
}
}