[
https://issues.apache.org/jira/browse/PDFBOX-3581?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Dmitri Russu updated PDFBOX-3581:
---------------------------------
Description:
Hi, I try to use pdfbox to extract text from a list of files, the problem is
PDFTextStripper does not work on thread mode, when I try to use it in
multythread nothing happens. it is a bug or limitation?
could you help me ?
thanks
I have added the full class
{code}
private void scanFolderFiles(File scanDirectory) {
File[] filesScan = scanDirectory.listFiles();
if ( filesScan.length > 0 ) {
int iterator=0;
for (final File fileEntry : filesScan) {
if (fileEntry.isDirectory()) {
scanFolderFiles(fileEntry);
} else {
try {
new PDFExtractThread(fileEntry).start();
}
catch (Exception e) {
e.printStackTrace();
}
}
iterator++;
}
}
}
////////////////////////////////////////////////////////////////////////////////////////////
package org.pdfextractor;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import java.io.*;
/**
* Created by dru on 21.11.2016.
*/
class PDFExtractThread extends Thread {
private String fileName;
private File readFile;
private PDDocument document;
public PDFExtractThread(File readFile) {
try {
this.readFile = readFile;
} catch (Exception e) {
e.printStackTrace();
System.exit(1);
}
}
public void run() {
try {
//get FileName
this.readFile.setWritable(true);
this.document = PDDocument.load(this.readFile);
this.fileName = (new
String(this.readFile.getName()).toLowerCase().replace(".pdf", ""));
pdfBoxExtractText();
//Closing the document
this.document.close();
} catch (IOException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
}
public void pdfBoxExtractText() throws Exception {
//Retrieving text from PDF document
PDFTextStripper pdfStripper = new PDFTextStripper();
System.out.println(this.fileName);
FileWriter fileWriter = new FileWriter(this.fileName+".txt");
BufferedWriter writer = new BufferedWriter(fileWriter);
String text = pdfStripper.getText(this.document);
writer.write(text);
writer.close();
}
}
{code}
was:
Hi, I try to use pdfbox to extract text from a list of files, the problem is
PDFTextStripper does not work on thread mode, when I try to use it in
multythread nothing happens. it is a bug or limitation?
could you help me ?
thanks
I have added the full class
{code}
package org.pdfextractor;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import java.io.*;
/**
* Created by dru on 21.11.2016.
*/
class PDFExtractThread extends Thread {
private String fileName;
private File readFile;
private PDDocument document;
public PDFExtractThread(File readFile) {
try {
this.readFile = readFile;
} catch (Exception e) {
e.printStackTrace();
System.exit(1);
}
}
public void run() {
try {
//get FileName
this.readFile.setWritable(true);
this.document = PDDocument.load(this.readFile);
this.fileName = (new
String(this.readFile.getName()).toLowerCase().replace(".pdf", ""));
pdfBoxExtractText();
//Closing the document
this.document.close();
} catch (IOException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
}
public void pdfBoxExtractText() throws Exception {
//Retrieving text from PDF document
PDFTextStripper pdfStripper = new PDFTextStripper();
System.out.println(this.fileName);
FileWriter fileWriter = new FileWriter(this.fileName+".txt");
BufferedWriter writer = new BufferedWriter(fileWriter);
String text = pdfStripper.getText(this.document);
writer.write(text);
writer.close();
}
}
{code}
> PDFTextStripper not working with multiple threads
> -------------------------------------------------
>
> Key: PDFBOX-3581
> URL: https://issues.apache.org/jira/browse/PDFBOX-3581
> Project: PDFBox
> Issue Type: Bug
> Components: Text extraction
> Affects Versions: 2.0.3
> Environment: Ubuntu 15.1
> Reporter: Dmitri Russu
> Labels: multithreading
>
> Hi, I try to use pdfbox to extract text from a list of files, the problem is
> PDFTextStripper does not work on thread mode, when I try to use it in
> multythread nothing happens. it is a bug or limitation?
> could you help me ?
> thanks
> I have added the full class
> {code}
> private void scanFolderFiles(File scanDirectory) {
> File[] filesScan = scanDirectory.listFiles();
> if ( filesScan.length > 0 ) {
> int iterator=0;
> for (final File fileEntry : filesScan) {
>
> if (fileEntry.isDirectory()) {
> scanFolderFiles(fileEntry);
> } else {
> try {
> new PDFExtractThread(fileEntry).start();
> }
> catch (Exception e) {
> e.printStackTrace();
> }
> }
> iterator++;
> }
> }
> }
> ////////////////////////////////////////////////////////////////////////////////////////////
> package org.pdfextractor;
> import org.apache.pdfbox.pdmodel.PDDocument;
> import org.apache.pdfbox.text.PDFTextStripper;
> import java.io.*;
> /**
> * Created by dru on 21.11.2016.
> */
> class PDFExtractThread extends Thread {
> private String fileName;
> private File readFile;
> private PDDocument document;
> public PDFExtractThread(File readFile) {
> try {
> this.readFile = readFile;
> } catch (Exception e) {
> e.printStackTrace();
> System.exit(1);
> }
> }
> public void run() {
> try {
> //get FileName
> this.readFile.setWritable(true);
> this.document = PDDocument.load(this.readFile);
> this.fileName = (new
> String(this.readFile.getName()).toLowerCase().replace(".pdf", ""));
> pdfBoxExtractText();
> //Closing the document
> this.document.close();
> } catch (IOException e) {
> e.printStackTrace();
> } catch (Exception e) {
> e.printStackTrace();
> }
> }
> public void pdfBoxExtractText() throws Exception {
> //Retrieving text from PDF document
> PDFTextStripper pdfStripper = new PDFTextStripper();
> System.out.println(this.fileName);
> FileWriter fileWriter = new FileWriter(this.fileName+".txt");
> BufferedWriter writer = new BufferedWriter(fileWriter);
> String text = pdfStripper.getText(this.document);
> writer.write(text);
> writer.close();
> }
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@pdfbox.apache.org
For additional commands, e-mail: dev-h...@pdfbox.apache.org
