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: 2017-06-26 16:53:47 +0200 (lun. 26 juin 2017) $

// $LastChangedRevision: 3451 $

// $LastChangedBy: mdecorde $

//

package org.txm.scripts.importer.alceste

//import org.txm.scripts.filters.TabulatedToXml.*;

import org.txm.scripts.importer.*;

import org.txm.importer.scripts.filters.*;

import org.txm.scripts.*;

import org.txm.importer.cwb.CwbEncode

import org.txm.importer.cwb.CwbMakeAll

import org.txm.utils.io.FileCopy;

import org.txm.importer.scripts.xmltxm.*;

import javax.xml.stream.*;

import java.io.BufferedWriter;

import java.io.File;

import java.io.FileOutputStream;

import java.io.OutputStreamWriter;

import java.io.PrintStream;

import java.net.URL;

import org.txm.scripts.filters.CutHeader.*;

import org.txm.scripts.filters.Tokeniser.*;

import org.txm.scripts.filters.FusionHeader.*;

import org.txm.scripts.filters.TagSentences.*;

import org.txm.Toolbox;

// TODO: Auto-generated Javadoc

/**

 * The Class importer.

 */

class importer {

        /**

         * Run.

         *

         * @param rootDirFile the root dir file

         * @param encoding the encoding

         * @param basename the basename

         * @return true, if successful

         */

        public static boolean run(File rootDirFile, File binDir, File txmDir, String encoding, String basename, String lang)

        {

                if (rootDirFile.listFiles() == null || rootDirFile.listFiles().size() == 0) {

                        println "Error: no file to process in "+rootDirFile;

                        return false;

                }

                File srcfile;

                for (File f : rootDirFile.listFiles()) {

                        if (!f.isHidden() && f.canRead() && f.isFile() && f.getName() != "import.xml" && !f.getName().endsWith("~")) {

                                srcfile = f

                                break;

                        }

                }

                File splitDir = new File(binDir, "split");

                File tokenizeDir = new File(binDir, "tokenized");

                File stokenizeDir = new File(binDir,"stokenized")

                stokenizeDir.deleteDir();

                stokenizeDir.mkdir();

                tokenizeDir.deleteDir();

                tokenizeDir.mkdir();

                splitDir.deleteDir();

                splitDir.mkdir();

                // Build xml files from the alceste file

                Alceste2Xml transformer = new Alceste2Xml()

                if (!transformer.run(srcfile, splitDir, encoding)) {

                        return false;

                }

                // Tokenize xml files

                List<File> srcfiles = splitDir.listFiles();

                println (srcfiles.size()+ " texts found in "+srcfile)

                println("Tokenizing files ("+srcfiles.size()+")")

                for (File f : srcfiles) {

                        print "."

                        File resultfile = new File(tokenizeDir, f.getName());

                        try {

                                def builder = new SimpleTokenizerXml(f, resultfile, lang);

                                builder.setStartTag("text")

                                if (!builder.process()) {

                                        println "Failed to tokenize: "+f;

                                        resultfile.delete();

                                }

                        }

                        catch(Exception e){org.txm.utils.logger.Log.printStackTrace(e); println "Failed to tokenize: "+f; return false;}

                }

                println ""

                List<File> stokenfiles = tokenizeDir.listFiles();

                println("Tagging sentences of "+stokenfiles.size()+" files")

                for (File f : stokenfiles) {

                        print "."

                        Sequence S = new Sequence();

                        Filter F1 = new CutHeader();

                        Filter F7 = new TagSentences();

                        Filter F11 = new FusionHeader();

                        S.add(F1);

                        S.add(F7);

                        S.add(F11);

                        File infile = f;

                        File xmlfile = new File(stokenizeDir, f.getName());

                        File headerfile = new File(f.getParentFile(), f.getName()+"header.xml");

                        S.SetInFileAndOutFile(infile.getPath(), xmlfile.getPath());

                        S.setEncodages("UTF-8","UTF-8");

                        Object[] arguments1 = [headerfile.getAbsolutePath()];

                        F1.SetUsedParam(arguments1);

                        Object[] arguments2 = [headerfile.getAbsolutePath(),F1];

                        F11.SetUsedParam(arguments2);

                        if (!S.proceed()) {

                                println "Failed to tag file: "+f

                        }

                        S.clean();

                        headerfile.delete();//remove the prepared file to clean

                }

                println ""

                //TRANSFORM INTO XML-TEI-TXM

                List<File> tokenfiles = stokenizeDir.listFiles()

                println("Building xml-tei-txm ("+tokenfiles.size()+" files)")

                for (File f : tokenfiles) {

                        print "."

                        File file = f;

                        File txmfile = new File(txmDir, f.getName());

                        def correspType = new HashMap<String, String>()

                        def correspRef = new HashMap<String, String>()

                        //il faut lister les id de tous les respStmt

                        def respId = [];

                        //fait la correspondance entre le respId et le rapport d'execution de l'outil

                        def applications = new HashMap<String,HashMap<String,String>>();

                        //fait la correspondance entre le respId et les attributs type de la propriété ana du w txm

                        //pour construire les ref vers les taxonomies

                        def taxonomiesUtilisees = new HashMap<String,String[]>();

                        //associe un id d'item avec sa description et son URI

                        def itemsURI = new HashMap<String,HashMap<String,String>>();

                        //informations de respStmt

                        //resps (respId <voir ci-dessus>, [description, person, date])

                        def resps = new HashMap<String,String[]>();

                        //lance le traitement

                        def builder = new Xml2Ana(file);

                        builder.setConvertAllAtrtibutes true;

                        builder.setCorrespondances(correspRef, correspType);

                        builder.setHeaderInfos(respId,resps, applications, taxonomiesUtilisees, itemsURI)

                        if(!builder.process(txmfile))

                        {

                                println "Failed to build xml-txm of file: "+file;

                                txmfile.delete();

                        }

                }

                println ""

                return true;

        }

}