[
https://issues.apache.org/jira/browse/PDFBOX-2860?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14624345#comment-14624345
]
simon steiner commented on PDFBOX-2860:
---------------------------------------
{code}
import org.apache.pdfbox.pdmodel.PDDocument;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class TestPDFBoxParser {
private static void listFilesForFolder(File folder, List<String> out) {
for (File fileEntry : folder.listFiles()) {
if (fileEntry.isDirectory()) {
listFilesForFolder(fileEntry, out);
} else if (fileEntry.getName().toLowerCase().endsWith(".pdf")) {
out.add(fileEntry.getAbsolutePath());
}
}
}
public static void main(String[] args) throws IOException {
List<String> files = new ArrayList<String>();
listFilesForFolder(new File("/path/topdfs"), files);
for (String s : files) {
try {
long a = load(s);
long b = loadNonSeq(s);
if (a > 50 && b > (a * 2)) {
System.out.println(s + " " + a + " " + b);
}
} catch (Exception e) {
}
}
}
private static long load(String s) throws IOException {
long start = System.currentTimeMillis();
for (int i=0; i<100; i++) {
PDDocument.load(new FileInputStream(s)).close();
}
long finish = System.currentTimeMillis() - start;
return finish;
}
private static long loadNonSeq(String s) throws IOException {
long start = System.currentTimeMillis();
for (int i=0; i<100; i++) {
PDDocument.loadNonSeq(new FileInputStream(s)).close();
}
long finish = System.currentTimeMillis() - start;
return finish;
}
}
{code}
> NonSeq parser slower than Seq parser
> ------------------------------------
>
> Key: PDFBOX-2860
> URL: https://issues.apache.org/jira/browse/PDFBOX-2860
> Project: PDFBox
> Issue Type: Bug
> Components: Parsing
> Affects Versions: 2.0.0
> Reporter: simon steiner
>
> PDF from PDFBOX-797
> for (int i=0; i<1000; i++) {
> PDDocument.load(new FileInputStream(
> "4218.pdf")).close();
> }
> Nonseq:
> real 0m23.691s
> Seq:
> real 0m9.705s
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
