Laboratoire ICAR » Plateforme TXM

// Copyright © 2010-2013 ENS de Lyon.

// Copyright © 2007-2010 ENS de Lyon, CNRS, INRP, University of

// Lyon 2, University of Franche-Comté, University of Nice

// Sophia Antipolis, University of Paris 3.

// 

// The TXM platform is free software: you can redistribute it

// and/or modify it under the terms of the GNU General Public

// License as published by the Free Software Foundation,

// either version 2 of the License, or (at your option) any

// later version.

// 

// The TXM platform 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 General Public License for more

// details.

// 

// You should have received a copy of the GNU General

// Public License along with the TXM platform. If not, see

// http://www.gnu.org/licenses.

// 

// 

// 

// $LastChangedDate:$

// $LastChangedRevision:$

// $LastChangedBy:$ 

//

package org.txm.scripts.importer;

import javax.xml.parsers.*

import javax.xml.transform.*

import javax.xml.transform.dom.DOMSource

import javax.xml.transform.stream.StreamResult

import javax.xml.xpath.*

import org.txm.importer.PersonalNamespaceContext

import org.txm.metadatas.*

import org.txm.utils.*

import org.txm.utils.xml.*

import org.w3c.dom.Document

import org.w3c.dom.Element

/**

 * Removes tags of XML file given a XPath. 

 * @author mdecorde

 *

 */

public class RemoveTag {

        File outfile;

        /** The doc. */

        Document doc;

        /**

         *

         * @param xmlfile the xmlfile

         * @param outfile the outfile

         * @param xpath the XPath

         */

        public RemoveTag(File xmlfile, File outfile, String xpath)

        {

                this.outfile = outfile;

                DocumentBuilderFactory domFactory = DocumentBuilderFactory.newInstance();

                domFactory.setNamespaceAware(true); // never forget this!

                domFactory.setXIncludeAware(true);

                DocumentBuilder builder = domFactory.newDocumentBuilder();

                doc = builder.parse(xmlfile);

                def expr = XPathFactory.newInstance().newXPath().compile(xpath);

                def nodes = expr.evaluate(doc, XPathConstants.NODESET);

                if (nodes != null)

                for(def node : nodes)

                {

                        //println "Remove node "+node

                        Element elem = (Element)node;

                        elem.getParentNode().removeChild(node);

                }

                save()

                doc = null

        }

        /**

         * Save.

         *

         * @return true, if successful

         */

        private boolean save()

        {

                try {

                        // Création de la source DOM

                        Source source = new DOMSource(doc);

                        // Création du fichier de sortie

                                Writer writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(outfile), "UTF-8")); 

                        Result resultat = new StreamResult(writer);

                        // Configuration du transformer

                        TransformerFactory fabrique = new net.sf.saxon.TransformerFactoryImpl();

                        Transformer transformer = fabrique.newTransformer();

                        transformer.setOutputProperty(OutputKeys.METHOD, "xml");

                        transformer.setOutputProperty(OutputKeys.INDENT, "yes"); 

                        transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8"); 

                        // Transformation

                        transformer.transform(source, resultat);

                        writer.close();

                        return true;

                } catch (Exception e) {

                        org.txm.utils.logger.Log.printStackTrace(e);

                        return false;

                }

        }

        public static boolean xpath(File xmlfile, String xpath)

        {

                if (!xmlfile.exists()) {

                        println "Error: $xmlfile does not exists"

                }

                if (!(xmlfile.canRead() && xmlfile.canWrite())) {

                        println "Error: $xmlfile is not readable or writable"

                }

                DocumentBuilderFactory domFactory = DocumentBuilderFactory.newInstance();

                domFactory.setNamespaceAware(true); // never forget this!

                domFactory.setXIncludeAware(true);

                DocumentBuilder builder = domFactory.newDocumentBuilder();

                Document doc = builder.parse(xmlfile);

                XPathFactory xpathfactory = XPathFactory.newInstance();

                def _xpath = xpathfactory.newXPath();

                _xpath.setNamespaceContext(new PersonalNamespaceContext());

                def expr = _xpath.compile(xpath);

                def nodes = expr.evaluate(doc, XPathConstants.NODESET);

                for(Element node : nodes) {

                        def parent = node.getParentNode();

                        if (parent != null)

                                parent.removeChild(node)

                }

                return DomUtils.save(doc, xmlfile)

        }

        public static boolean xpath(File xmlfile, List<String> xpaths)

        {

                if (!xmlfile.exists()) {

                        println "Error: $xmlfile does not exists"

                }

                if (!(xmlfile.canRead() && xmlfile.canWrite())) {

                        println "Error: $xmlfile is not readable or writable"

                }

                DocumentBuilderFactory domFactory = DocumentBuilderFactory.newInstance();

                domFactory.setNamespaceAware(true); // never forget this!

                domFactory.setXIncludeAware(true);

                DocumentBuilder builder = domFactory.newDocumentBuilder();

                Document doc = builder.parse(xmlfile);

                XPathFactory xpathfactory = XPathFactory.newInstance();

                for (String xpath : xpaths) {

                        def _xpath = xpathfactory.newXPath();

                        _xpath.setNamespaceContext(new PersonalNamespaceContext());

                        def expr = _xpath.compile(xpath);

                        def nodes = expr.evaluate(doc, XPathConstants.NODESET);

                        for (Element node : nodes) {

                                def parent = node.getParentNode();

                                if (parent != null)

                                        parent.removeChild(node)

                        }

                }

                return DomUtils.save(doc, xmlfile)

        }

        public static void main(String[] args) {

                RemoveTag rt = new RemoveTag(

                        new File("/home/mdecorde/TXM/corpora/graal/import.xml"),

                        new File("/home/mdecorde/TXM/corpora/graal/import-o.xml"),

                        "//edition[@name='courante']"

                        )

        }

}