Laboratoire ICAR » Plateforme TXM

String userDir = System.getProperty("user.home");

def MONITOR;

String model = lang

File srcDir = new File(rootDir);

binDir.mkdirs();

if (!binDir.exists()) {

	println "Could not create binDir "+binDir

println "-- IMPORTER - Reading source files"

def imp = new importer();

imp.doValidation(true) // change this to not validate xml

imp.doTokenize(!skipDoTokenizeStep) // change this, to not tokenize xml

imp.setStopIfMalformed(stopIfMalformed);

if (!imp.run( srcDir, binDir, txmDir, basename, ignoredElements, lang)) {

c.setOptions(textSortAttribute, normalizeMetadata);

c.setAnnotationSuccess(annotationSuccess)

c.setLang(lang);

	println "import process stopped";

	return;

}

		List<String> NoSpaceBefore = LangFormater.getNoSpaceBefore(lang);

		List<String> NoSpaceAfter = LangFormater.getNoSpaceAfter(lang);

		def ed = new pager(txmFile, outdir, txtname, NoSpaceBefore, NoSpaceAfter, wordsPerPage, basename, page_element);

		for (i = 0 ; i < ed.getPageFiles().size();) {

			File f = ed.getPageFiles().get(i);

			String wordid = ed.getIdx().get(i);

		}

	}

}

if (MONITOR != null && MONITOR.isCanceled()) { return MONITOR.done(); }

if (MONITOR != null) MONITOR.worked(20, "FINALIZING")

import org.txm.scripts.*

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

import org.txm.utils.treetagger.TreeTagger

import javax.xml.stream.*

import java.net.URL

import java.util.HashSet

import org.txm.metadatas.*

import org.txm.utils.io.FileCopy

/**

 * The "compiler" Class of the XML/w import module.

	/** The base. */

	String base="";

	/** The text attributes. */

	String[] textAttributes = null;

	 * @param base the base

	 * @param project the project

	 */

	{

		this.text = text

		this.base = base;

		this.textAttributes = textAttributes;

		try {

			this.url = url;

	 * @param fileName the file name

	 * @return true, if successful

	 */

	{

		if (!createOutput(cqpFile))

			return false;

							case "text":

								sattrsListener.startElement(localname);

								foundtext = true;

							//							for (String name : textmetadata.keySet())

							//								output.write(" "+name+"=\""+textmetadata.get(name)+"\"")

								for (int i = 0 ; i < parser.getAttributeCount() ; i++) {

	 * @param srcfiles the srcfiles

	 * @return true, if successful

	 */

	{

		sattrsListener = null; // reset SAttribute Listener for each new import

		String rootDir = binDir.getAbsolutePath();

		anavalues = [:] // reset

		if (!(CwbEncode.isExecutableAvailable() && CwbMakeAll.isExecutableAvailable())) {

			return false;

		}

		}

		String textid = ""

		int counttext = 0

		//1- Transform into CQP file

		def builder = null

				String txtname = f.getName().substring(0,f.getName().length()-4)

				builder = new compiler(f.toURI().toURL(), txtname, corpusname, "default")

				builder.setLang(lang);

					println("Failed to compile "+f)

				}

			}

			cwbMa.run(corpusname, outDir + "/registry");

		} catch (Exception ex) {System.out.println(ex); return false;}

		return true;

	}

String userDir = System.getProperty("user.home");

def MONITOR;

String model = lang

File srcDir = new File(rootDir);

binDir.mkdirs();

if (!binDir.exists()) {

	println "Could not create binDir "+binDir

if (MONITOR != null && MONITOR.isCanceled()) { return MONITOR.done(); }

if (MONITOR != null) MONITOR.worked(20, "CREATING TEI FILES")

println "-- CONVERTER - Converting source files"

if (!DocumentToTei.processFiles(srcfiles, txmDir, xsldir)) {

	println "Abord import"

	return;

// filtering

println "Filtering XML files with xpaths: [//tei:term]"

if (xpaths != null) {

	println "Filtering XML files with xpaths: $xpaths"

c.setOptions(textSortAttribute, normalizeMetadata);

c.setAnnotationSuccess(annotationSuccess)

c.setLang(lang);

	println "import process stopped";

	return;

}

		List<String> NoSpaceBefore = LangFormater.getNoSpaceBefore(lang);

		List<String> NoSpaceAfter = LangFormater.getNoSpaceAfter(lang);

		def ed = new pager(txmFile, outdir, txtname, NoSpaceBefore, NoSpaceAfter, wordsPerPage, basename, "pb");

		for (i = 0 ; i < ed.getPageFiles().size();) {

			File f = ed.getPageFiles().get(i);

			String wordid = ed.getIdx().get(i);

		}

	}

if (MONITOR != null && MONITOR.isCanceled()) { return MONITOR.done(); }

if (MONITOR != null) MONITOR.worked(20, "FINALIZING")

// 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.

	/** The multiwriter. */

	OutputStreamWriter multiwriter = null;

	/** The pagedWriter. */

	StaxStackWriter pagedWriter = null;

	 */

	void process() {

		try {

						}

								pagedWriter.writeStartElement("tr")

								pagedWriter.writeStartElement("td")

								NoSpaceAfter.contains(lastword) ||

								wordvalue.startsWith("-") ||

								NoSpaceAfter.contains(endOfLastWord))

			}

	}

}

import org.txm.importer.*

String userDir = System.getProperty("user.home");

def MONITOR;

Project project;

try {project=projectBinding;MONITOR=monitor} catch (Exception)

{	}

c.setLang(lang);

c.setAnnotationSuccess(annotationSuccess)

if (debug) c.setDebug();

	println "Import process stopped";

	return;

}

	Collections.sort(filelist);

	def second = 0

	for (File srcfile : filelist) {

		print "."

		String txtname = srcfile.getName();

		}

	}

}

if (MONITOR != null && MONITOR.isCanceled()) { return MONITOR.done(); }

if (MONITOR != null) MONITOR.worked(20, "FINALIZING")

import org.txm.scripts.importer.*;

import org.txm.scripts.*;

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

import org.txm.utils.treetagger.TreeTagger;

import javax.xml.stream.*;

import java.net.URL;

		File txmDir = new File(binDir, "txm/"+corpusname)

		if (!(CwbEncode.isExecutableAvailable() && CwbMakeAll.isExecutableAvailable())) {

			return false;

		}

		CorpusBuild corpus = project.getCorpusBuild(project.getName());

		if (corpus != null) {

			corpus.delete(); // remove old files

		}

		corpus = new MainCorpus(project);

		corpus.setID(project.getName());

		corpus.setName(project.getName());

		File cqpFile = new File(binDir,"cqp/"+corpusname+".cqp");

		new File(binDir,"cqp").mkdirs()

			print "."

			cqpbuilder = new XMLTXM2CQP(txmfile.toURI().toURL());

			String txtname = txmfile.getName().substring(0,txmfile.getName().length()-4);

			cqpbuilder.setBalisesToKeep(["text","s"]);

			cqpbuilder.setSendToPAttributes(["lb":["n"]]);

new File(binDir,"HTML/$corpusname").mkdirs();

if (build_edition) {

	println "-- EDITION - Building edition"

	File outdir = new File(binDir,"/HTML/$corpusname/default/");

	outdir.mkdirs();

	List<File> filelist = txmDir.listFiles();

		print "."

		String txtname = srcfile.getName();

		int i = txtname.lastIndexOf(".");

		List<String> NoSpaceBefore = LangFormater.getNoSpaceBefore(lang);

		List<String> NoSpaceAfter = LangFormater.getNoSpaceAfter(lang);

		Text t = new Text(project);

		t.setName(txtname);

		t.setSourceFile(srcfile)

		t.setTXMFile(srcfile)

		def ed = new pager_old(srcfile, outdir, txtname, NoSpaceBefore, NoSpaceAfter, wordsPerPage, basename, "pb");

		Edition edition = new Edition(t);

		edition.setName("default");

		edition.setIndex(outdir.getAbsolutePath());

if (MONITOR != null && MONITOR.isCanceled()) { return MONITOR.done(); }

if (MONITOR != null) MONITOR.worked(20, "FINALIZING")

readyToLoad = project.save();

		if (selection.getFirstElement() instanceof CQPCorpus) {

			try {

				CQPCorpus c = (CQPCorpus) selection.getFirstElement();

				//EditionSelectorDialog d = new EditionSelectorDialog(shell, c, null);

				SynopticEditionEditor editor = null;

				editor = openEdition(c, editionsToOpen);

			} catch (Exception e) {

				System.out.println(EditionUIMessages.OpenEdition_4+e);

				org.txm.rcp.utils.Logger.printStackTrace(e);

		}

		return null;

	}

	public static String[] getDefaultEditions(Project p) {

		return p.getDefaultEdition().split(","); //$NON-NLS-1$ //$NON-NLS-2$

	}

	public static String[] getDefaultEditions(CQPCorpus c) {

		return getDefaultEditions(c.getProject());

	}

			//String[] editions = {maincorpus.getDefaultEdition()};

			IWorkbenchWindow window = PlatformUI.getWorkbench().getActiveWorkbenchWindow();

			IWorkbenchPage page = window.getActivePage();

			SynopticEditorInput editorInput = new SynopticEditorInput(corpus, text.getName(), editions);

			SynopticEditionEditor editor = (SynopticEditionEditor) page.openEditor(editorInput,

					SynopticEditionEditor.ID, true);

			return editor;

		} catch (Exception e) {

		}

	}

	//FIXME: this code is dedicated to dynamically retrieve the static field PREFERENCES_NODE of the runtime subclass and use it super class to avoid to pass it to all methods.

	// eg. to use ProgressionPreferences.getBoolean("test") instead of TXMPreferences.getBoolean(ProgressionPreferences.PREFERENCES_NODE, "test")

	// but it doesn"t work, need to continue the tests...

		String names = this.getStringParameterValue(TBXPreferences.NAMES);

		if (names != null && names.length() > 0) {

			pPageNames = new ArrayList<>(Arrays.asList(names.split("\t")));

		}

		String wordids = this.getStringParameterValue("pages_wordids");

		if (wordids != null && wordids.length() > 0) {

			pPageFirstWordIds = new ArrayList<>(Arrays.asList(wordids.split("\t")));

		}

		if (pages == null) {

		} else {

			pages.clear();

		}

		for (int i = 0 ; i < pPageNames.size() && i < pPageFirstWordIds.size() ; i++) {

			pages.add(new Page(this, pPageNames.get(i), pPageFirstWordIds.get(i)));

		}

		}

		if (!rcpProject.exists()) {

		}

		if (!rcpProject.isOpen()) {

		}

		this.preferenceScope = new ProjectScope(rcpProject);

	}

	public Project(String uuid) throws CoreException {

		super(uuid);

		initRCPStuffs();

		IEclipsePreferences params = this.getPreferences().getNode("Tokenizer");

		params.put(name, value);

	}

	public EditionDefinition getEditionDefinition(String name) {

		return new EditionDefinition(this, name);

	@Override

	public void clean() {

			pTXMFile.delete();

		}

	}

	 * @return the left context size

	 */

	public int getLeftContextSize() {

		return leftCtxViewPropertiesValues.values().iterator().next().size();

	}

	 * @return the keywords size

	 */

	public int getKeywordsSize() {

		return keywordsViewValues.values().iterator().next().size();

	}

	 * @return the right context size

	 */

	public int getRightContextSize() {

		return rightCtxViewValues.values().iterator().next().size();

	}

		int start = this.getLeftContextSize() - max;

		for (int i = start; i < this.getLeftContextSize(); i++) {

			List<String> word = new ArrayList<String>();

//				if(propertiesToProcess.contains(property.getName()))

//					word.add(TxmRenderer.jseshrenderer.render(values.get(property).get(i)));

//				else

package org.txm.rcp.editors.imports.sections;

import java.io.File;

import java.util.LinkedHashMap;

import org.eclipse.jface.viewers.ISelection;

import org.eclipse.ui.forms.widgets.TableWrapData;

import org.eclipse.ui.forms.widgets.TableWrapLayout;

import org.txm.Toolbox;

import org.txm.objects.Project;

import org.txm.rcp.editors.TableKeyListener;

import org.txm.rcp.handlers.files.EditFile;

import org.txm.rcp.messages.TXMUIMessages;

import org.txm.rcp.swt.dialog.LastOpened;

import org.txm.rcp.swt.dialog.MultipleValueDialog;

import org.txm.rcp.swt.provider.HashMapLabelProvider;

public class FrontXSLSection extends ImportEditorSection {

		gd.colspan = 4;

		gd.heightHint = 100;

		xsltParamsViewer.getTable().setLayoutData(gd);

		xsltParamsViewer.getTable().setHeaderVisible(true);

		xsltParamsViewer.getTable().setLinesVisible(true);

import org.txm.objects.Project;

import org.txm.rcp.editors.imports.ImportModuleCustomization;

import org.txm.rcp.messages.TXMUIMessages;

import org.txm.tokenizer.TokenizerClasses;

import org.w3c.dom.Element;

import org.w3c.dom.NodeList;

		slayout.numColumns = 3;

		sectionClient.setLayout(slayout);

		this.section.setClient(sectionClient);

		Label tmpLabel3 = toolkit.createLabel(sectionClient, "Word tag");

		TableWrapData gdata = new TableWrapData(TableWrapData.LEFT, TableWrapData.FILL);

		gdata.colspan = 2;

		tmpLabel3.setLayoutData(gdata);

		tmpLabel3.setToolTipText("XML tag name that encodes words");

		tmpLabel3.setVisible(moduleParams.get(ImportModuleCustomization.ADVANCEDTOKENIZER));

		wordElementText = toolkit.createText(sectionClient, "w", SWT.BORDER); //$NON-NLS-1$

		gdata = getTextGridData();

		wordElementText.setLayoutData(gdata);

			public void widgetSelected(SelectionEvent e) {

				updateFieldsEnableState();

			}

			@Override

			public void widgetDefaultSelected(SelectionEvent e) { }

		});

		Label l0 = toolkit.createLabel(sectionClient, TXMUIMessages.CorpusPage_16a, SWT.WRAP);

		gdata = new TableWrapData(TableWrapData.LEFT, TableWrapData.FILL);

		gdata.colspan = 3;

		gdata.indent = 10;

		l0.setLayoutData(gdata);

		Label l1 = toolkit.createLabel(sectionClient, TXMUIMessages.CorpusPage_5, SWT.WRAP);

		gdata = new TableWrapData(TableWrapData.LEFT, TableWrapData.FILL);

		gdata.colspan = 2;

		textWhiteSpaces = toolkit.createText(sectionClient, TokenizerClasses.whitespaces, SWT.BORDER);

		gdata = getLongTextGridData();

		textWhiteSpaces.setLayoutData(gdata);

		Label l2 = toolkit.createLabel(sectionClient, TXMUIMessages.CorpusPage_16, SWT.WRAP);

		gdata = new TableWrapData(TableWrapData.LEFT, TableWrapData.FILL);

		gdata.colspan = 2;

	@Override

	public void update(Project project) {

	}

	@Override

	public boolean save(Project project) {

		if (textWhiteSpaces.getText().length() == 0 && textPuncts.getText().length() == 0) {

			System.out.println("Error while saving tokenizer parameters: whitespace and punctuation regular expressions are both empty.");

			return false;

		project.addTokenizerParameter("wordelement", wordElementText.getText()); //$NON-NLS-1$

		project.addTokenizerParameter("doTokenizeStep", ""+!doTokenizeStepButton.getSelection()); //$NON-NLS-1$

		project.addTokenizerParameter("onlyThoseTests", "false"); //$NON-NLS-1$

		return true;

	}

		wdialog.open();

		project = wiz.getProject();

		if (project == null) {

			return;

		}

		try {

			loadParams();

import org.eclipse.swt.SWT;

import org.eclipse.swt.events.KeyEvent;

import org.eclipse.swt.events.KeyListener;

import org.eclipse.swt.events.SelectionEvent;

import org.eclipse.swt.events.SelectionListener;

import org.eclipse.swt.layout.GridData;

import org.eclipse.swt.widgets.DirectoryDialog;

import org.eclipse.swt.widgets.Label;

import org.eclipse.swt.widgets.Text;

public class GeneralWizardPage extends WizardPage {

//    private Text corpusName;

        label2.setText("Source directory");

        sourceDirectory = new Text(container, SWT.BORDER | SWT.SINGLE);

        sourceDirectory.setToolTipText("The corpus source directory");

        sourceDirectory.setLayoutData(gd);

        Button button = new Button(container, SWT.PUSH);

        button.setText("...");

			@Override

			public void widgetSelected(SelectionEvent e) {

				DirectoryDialog dialog = new DirectoryDialog(e.display.getActiveShell());

				dialog.setText("Source directory");

				if (getSourcePath().length() > 0) {

					dialog.setFilterPath(getSourcePath());

				String path = dialog.open();

				if (path != null) {

					sourceDirectory.setText(path);

					setPageComplete(isCompleted());

				}

			}

        // required to avoid an error in the system

        setControl(container);

        setPageComplete(false);

    }

    protected boolean isCompleted() {

//    }

    public String getSourcePath() {

    }

}