/*
* Copyright (c) 1997-2019 IDRsolutions (https://www.idrsolutions.com)
*/
package org.jpedal.examples.text;
import org.jpedal.exception.PdfException;
import org.jpedal.utils.LogWriter;
import org.jpedal.utils.SecureTransformerFactory;
import org.w3c.dom.Document;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import javax.xml.transform.stream.StreamSource;
import java.io.File;
import java.io.InputStream;
/**
* <h2>Extract Structured Content (if present) from PDF files</h2>
* <br>
* This class provides a simple Java API to extract Structured Content (if present) from a PDF file and also a static convenience method if you just want to dump any structured outlines from a PDF file or directory containing PDF files<br>
* If no Structure is present a blank file is returned<br>
* <h3>Example 1 - access API methods</h3>
* <pre><code>ExtractStructuredText extract=new ExtractStructuredText("C:/pdfs/mypdf.pdf");
* //extract.setPassword("password");
* if (extract.openPDFFile()) {
* Document anyStructuredText=extract.getStructuredTextContent();
* }
*
* extract.closePDFfile();</code></pre>
* <br>
* <h3>Example 2 - convenience static method</h3>
* Extract any Structured test for a file or set of files and write out results as XML in a txt file (separate directory for each PDF file)<br>
* <br>
* <pre><code>ExtractStructuredText.writeAllStructuredTextOutlinesToDir("pdfs", "output");</code></pre>
*
* <h3>Example 3 - Access directly from the Jar</h3>
* ExtractStructuredText can run directly from the jar using the command line and will extract any data from a PDF file or directory
* to a defined output directory
* <br>
* <code>java -cp libraries_needed org/jpedal/examples/text/ExtractStructuredText input_pdf output_dir</code>
* <br>
* <ul>
* <li>input_pdf: The PDF filename (including the path if needed) or a directory containing PDF files. If it contains spaces it must be enclosed by double quotes (ie "C:/Path with spaces/").</li>
* <li>output_dir: The directory to write out outline data extracted from the PDF file or files. If it contains spaces it must be enclosed by double quotes (ie "C:/Path with spaces/").</li>
* </ul>
*
* <br>For non-structured files, consider:
* <ul>
* <li>http://files.idrsolutions.com/samplecode/org/jpedal/examples/text/ExtractTextAsWordlist.java.html</li>
* <li>http://files.idrsolutions.com/samplecode/org/jpedal/examples/text/ExtractTextInRectangle.java.html</li>
* </ul>
*
* <br><a href="https://support.idrsolutions.com/hc/en-us/articles/115001889651-Extract-text-from-PDF-files">See our Support Pages for more information on Text Extraction</a><br>
*/
public class ExtractStructuredText extends BaseTextExtraction {
/**
* Sets up an ExtractStructuredText instance to open a PDF File
*
* @param fileName full path to a single PDF file
*/
public ExtractStructuredText(final String fileName) {
super(fileName);
init();
}
/**
* Sets up an ExtractStructuredText instance to open a PDF file contained as a BLOB within a byte[] stream
*
* @param byteArray Array which will hold BLOB
*/
public ExtractStructuredText(final byte[] byteArray) {
super(byteArray);
init();
}
/**
* routine to decode a file
*/
@Override
void decodeFile(final String file_name) throws PdfException {
this.fileName = file_name;
if (openPDFFile()) {
//read pages -if you already have code this is probably
//all you need!
final Document tree = getStructuredTextContent();
if (tree != null) {
InputStream stylesheet = null;
final TransformerFactory transformerFactory = SecureTransformerFactory.newInstance();
try {
stylesheet = this.getClass().getResourceAsStream("/org/jpedal/examples/text/xmlstyle.xslt");
final Transformer transformer = transformerFactory.newTransformer(new StreamSource(stylesheet));
//useful for debugging
//transformer.transform(new DOMSource(tree), new StreamResult(System.out));
if (!tree.hasChildNodes()) {
return;
}
//warn user if no content present
if (!tree.getDocumentElement().hasChildNodes()) {
tree.appendChild(tree.createComment("There is NO Structured text in the file to extract!!"));
tree.appendChild(tree.createComment("JPedal can only extract it if it has been added when PDF created"));
tree.appendChild(tree.createComment("Please read our blog post at https://blog.idrsolutions.com/2010/09/the-easy-way-to-discover-if-a-pdf-file-contains-structured-content/ "));
}
//get just the name of the file without the path to use as a sub-directory or .pdf
String name = "demo"; //set a default just in case
final int pointer = file_name.lastIndexOf(separator);
if (pointer != -1) {
name = file_name.substring(pointer + 1, file_name.length() - 4);
}
final String outputFile = output_dir + separator + name + ".xml";
final File output = new File(output_dir);
if (!output.exists()) {
final File createDir = new File(output_dir);
createDir.mkdirs();
output.createNewFile();
}
transformer.transform(new DOMSource(tree), new StreamResult(outputFile));
} catch (final Exception | Error e) {
throw new PdfException(e.getMessage());
} finally {
if (stylesheet != null) {
try {
stylesheet.close();
} catch (Exception e) {
LogWriter.writeLog(e);
}
}
}
}
}
}
/**
* This class will allow you to extract any Structured Text data via command line from a single PDF file or a directory of PDF files.
* <br>
* The example expects two or three parameters:
* <ul>
* <li>Value 1 is the file name or directory of PDF files to process</li>
* <li>Value 2 is directory to write out the outline data</li>
* </ul>
*
* @param args The expected arguments are described above.
*/
@SuppressWarnings("unused")
public static void main(final String[] args) {
final int len = args.length;
switch (len) {
case 0:
case 1:
System.out.println("Example takes 2 parameters");
System.out.println("Value 1 is the file name or directory of PDF files to process");
System.out.println("Value 2 is Directory for writing the data as text files");
System.exit(0);
case 2:
try {
ExtractStructuredText.writeAllStructuredTextOutlinesToDir(args[0], args[1]);
} catch (final PdfException e) {
e.printStackTrace();
}
break;
default:
System.out.println("too many arguments entered - run with no values to see defaults");
final StringBuilder arguments = new StringBuilder();
for (final String arg : args) {
arguments.append(arg).append('\n');
}
System.out.println("you entered:\n" + arguments + "as the arguments");
System.exit(0);
}
}
@Override
void init() {
type = BaseTextExtraction.ExtractTypes.STRUCTURED_TEXT;
super.init();
}
/**
* Convenience method to write any Structured text in a directory of PDF files
*
* @param inputDir directory containing PDF files
* @param outputDir directory for writing out images
* @throws org.jpedal.exception.PdfException a PDF exception
*/
public static void writeAllStructuredTextOutlinesToDir(final String inputDir, final String outputDir) throws PdfException {
final ExtractStructuredText extract = new ExtractStructuredText(inputDir);
extract.setup(outputDir);
extract.processFiles(inputDir);
extract.closePDFfile();
}
private void setup(String outputDir) {
//check output dir has separator
if (!outputDir.endsWith(separator)) {
outputDir += separator;
}
this.output_dir = outputDir;
}
/**
* gets the Document containing any Structured text (if present) as a Document structure
* <br>
* If the Document does not contain the meta data for Structured Content, an empty Document is returned
*
* @return Document
*/
public Document getStructuredTextContent() {
return decode_pdf.getMarkedContent();
}
}
|