Description
Extract and normalize picture names, i.e.
License
Open Source License
Parameter
| Parameter | Description |
|---|
| xmlFile | The path to the XML file (merged XML files inside the ODF file). |
| odtFile | The path to the ODF file. |
| parentDir | The parent directory (of the new directory for the images (??)). |
| imgBaseDir | The new directory for the images. |
Exception
Return
LinkedHashMap where keys are old file names and values are new file names.
Declaration
public static LinkedHashMap<String, String> extractAndNormalizeEmbedPictures(String xmlFile, String odtFile,
String parentDir, String imgBaseDir) throws SAXException, IOException, ParserConfigurationException,
TransformerConfigurationException, TransformerException
Method Source Code
//package com.java2s;
/**/*from w w w . j a v a 2s . co m*/
* odt2daisy - OpenDocument to DAISY XML/Audio
*
* (c) Copyright 2008 - 2012 by Vincent Spiewak, All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Lesser Public License as published by
* the Free Software Foundation; either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.LinkedHashMap;
import java.util.logging.Level;
import java.util.logging.Logger;
import java.util.zip.ZipEntry;
import java.util.zip.ZipFile;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerException;
import org.w3c.dom.Element;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.EntityResolver;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
public class Main {
public static final String PICTURE_FOLDER = "Pictures/";
private static final Logger logger = Logger.getLogger("com.versusoft.packages.jodl.odtutils");
/**
* Extract and normalize picture names, i.e.
* converts <code>xlink:href</code> values like
* 'Pictures/100000000000034300000273CAF76237.png'
* into values like 'images/0.png'.
*
* @param xmlFile The path to the XML file (merged XML files inside the ODF file).
* @param odtFile The path to the ODF file.
* @param parentDir The parent directory (of the new directory for the images (??)).
* @param imgBaseDir The new directory for the images.
* @return LinkedHashMap where keys are old file names and values are new file names.
* @throws org.xml.sax.SAXException If an input source for the XML content cannot be created.
* @throws java.io.IOException If the String representing the image directory is actually a file instead of a directory, or if an input source for the XML content cannot be created.
* @throws javax.xml.parsers.ParserConfigurationException If a DocumentBuilder cannot be created which satisfies the configuration requested, i.e. a validating parser cannot be created.
* @throws javax.xml.transform.TransformerConfigurationException If a a serious configuration error occured.
* @throws javax.xml.transform.TransformerException If an exceptional condition occured during the transformation process.
*/
public static LinkedHashMap<String, String> extractAndNormalizeEmbedPictures(String xmlFile, String odtFile,
String parentDir, String imgBaseDir) throws SAXException, IOException, ParserConfigurationException,
TransformerConfigurationException, TransformerException {
logger.fine("entering");
ZipFile zip;
File imgDir;
ArrayList<String> pics;
DocumentBuilderFactory docFactory;
DocumentBuilder docBuilder;
Document contentDoc;
LinkedHashMap<String, String> oldAndNewImgNames = new LinkedHashMap<String, String>();
pics = getPictures(odtFile);
zip = new ZipFile(odtFile);
// @todo clean up / irrelevant after making method return oldAndNewImgNames:
if (pics.size() < 1) {
return oldAndNewImgNames;
}
imgDir = new File(parentDir + imgBaseDir);
logger.fine("imgBaseDir: " + imgBaseDir + "\n");
logger.fine("parentDir: " + parentDir + "\n");
if (imgDir.isFile()) {
throw new IOException("Wrong argument: parentDir is a file");
}
if (!imgDir.exists()) {
imgDir.mkdirs();
}
docFactory = DocumentBuilderFactory.newInstance();
docFactory.setValidating(false);
docBuilder = docFactory.newDocumentBuilder();
docBuilder.setEntityResolver(new EntityResolver() {
public InputSource resolveEntity(java.lang.String publicId, java.lang.String systemId)
throws SAXException, java.io.IOException {
return new InputSource(
new ByteArrayInputStream("<?xml version='1.0' encoding='UTF-8'?>".getBytes()));
}
});
contentDoc = docBuilder.parse(xmlFile);
Element root = contentDoc.getDocumentElement();
NodeList nodelist = root.getElementsByTagName("draw:image");
// for every draw:image element in the merged XML:
for (int i = 0; i < nodelist.getLength(); i++) {
Node objectNode = nodelist.item(i);
Node hrefNode = objectNode.getAttributes().getNamedItem("xlink:href");
String imagePath = hrefNode.getTextContent();
logger.fine("Image path: " + imagePath);
// if the xlink:href value can be found in the list of images from the ODF file:
if (pics.contains(imagePath)) {
int id = pics.indexOf(imagePath);
// create file extension based on original extension turned to lower case:
String ext = imagePath.substring(imagePath.lastIndexOf(".")).toLowerCase();
//String newImageName = id + ext;
//String newImagePath = parentDir + imgBaseDir + newImageName;
//if (ext.endsWith("gif") || ext.endsWith("bmp") || ext.endsWith("wbmp")) {
// hrefNode.setTextContent(imgBaseDir + id + ".png");
// logger.fine("extract image\n");
// copyInputStream(zip.getInputStream(zip.getEntry(imagePath)), new FileOutputStream(parentDir + imgBaseDir + id + ext));
// logger.fine("convert to png\n");
// toPNG(parentDir + imgBaseDir + id + ext, parentDir + imgBaseDir + id + ".png");
// logger.fine("delete old image\n");
// new File(parentDir + imgBaseDir + id + ext).delete();
//} else {
// Set xlink:href value to new image directory + image index + image extension (lower case):
String newXlinkHref = imgBaseDir + id + ext;
hrefNode.setTextContent(newXlinkHref);
logger.fine("extracted image: " + newXlinkHref + "\n");
// Store mapping between new and old image names:
oldAndNewImgNames.put(imagePath, newXlinkHref);
copyInputStream(zip.getInputStream(zip.getEntry(imagePath)),
new FileOutputStream(parentDir + imgBaseDir + id + ext));
//}
//@todo Remove logger output after testing
logger.fine("Image mapping = " + oldAndNewImgNames.toString());
logger.fine("done\n");
}
}
saveDOM(contentDoc, xmlFile);
logger.fine("done");
return oldAndNewImgNames;
}
/**
* Return an ArrayList of image(s) path(s) included in the ODF file,
* i.e. a ArrayList of Strings like 'Pictures/100000000000034300000273CAF76237.png'.
*
* @param odtFile The path to the ODF file.
* @return ArrayList of image(s) path(s)
* @throws java.io.IOException If an exceptional condition occurred while creating a ZipFile based on the path to the ODF file.
*/
public static ArrayList<String> getPictures(String odtFile) throws IOException {
ArrayList<String> ret = new ArrayList<String>();
ZipFile zf = null;
Enumeration<? extends ZipEntry> entries = null;
zf = new ZipFile(odtFile);
entries = zf.entries();
while (entries.hasMoreElements()) {
ZipEntry entry = (ZipEntry) entries.nextElement();
if (entry.getName().startsWith(PICTURE_FOLDER)) {
if (!entry.isDirectory()) {
ret.add(entry.getName());
}
}
}
return ret;
}
private static final void copyInputStream(InputStream in, OutputStream out) throws IOException {
byte[] buffer = new byte[1024];
int len;
while ((len = in.read(buffer)) >= 0) {
out.write(buffer, 0, len);
}
in.close();
out.close();
}
/**
* Saves a document object model (DOM) as a file with the chosen file name.
*
* @param doc DOM representation of XML instance.
* @param filename The file to which the DOM should be saved. The String must conform to the URI syntax.
* @return true if the file could be saved; false if the file could not be saved.
*/
public static boolean saveDOM(Document doc, String filename) {
boolean save = false;
try {
Transformer transformer = TransformerFactory.newInstance().newTransformer();
transformer.setOutputProperty(OutputKeys.METHOD, "xml");
transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
transformer.setOutputProperty(OutputKeys.INDENT, "yes");
transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "3");
StreamResult result = new StreamResult(filename);
DOMSource source = new DOMSource(doc);
transformer.transform(source, result);
save = true;
} catch (TransformerConfigurationException ex) {
logger.log(Level.SEVERE, null, ex);
} catch (TransformerException ex) {
logger.log(Level.SEVERE, null, ex);
} finally {
return save;
}
}
}
Related
- decodeHex(String hex)
- elementToXMLString(Object aElement)
- encode(final String value)
- encodeStringIntoMemento(String str)
- escapeBackslashes(String value)
- extractElement(String xml, String tagName)
- extractText(Node n, StringBuffer buf)
- fileToXMLString(String filename)
- getAsXMLString(final Node node)