Laboratoire ICAR » Plateforme TXM

}

if (symbol == null) {

import org.txm.rcpapplication.views.CorporaView

if (!(corpusViewSelection instanceof Corpus)) {

def corpus = corpusViewSelection

	partition = corpus.createPartition(NAME, QUERIES, PARTNAMES)

import org.txm.utils.logger.Log;

def corpus = corpusViewSelection

if (!(corpus instanceof Corpus)) {

 * 

	public Partition createPartition(Corpus corpus, boolean debug,

				return corpus.createPartition(PARTITION_NAME, queries, partNames);

	 * Recurse through structural units and structural units properties of corpus and create the queries and the part names. 

	protected void process(Corpus corpus, int index, String tmpQuery, String tmpPartName)	{

def corpus = corpusViewSelection

if (!(corpus instanceof Corpus)) {

def concordance = new Concordance(corpus, query, word, viewprops, referencePattern, referencePattern, leftcontextsize, rightcontextsize)

import org.txm.searchengine.cqp.corpus.*

if (!(corpusViewSelection instanceof Corpus)) {

def Corpus corpus = corpusViewSelection

println sprintf("** Warning: incoherent metadata content found for %s corpus - no 'id' metadata found", corpus)

println "** Aborting"

return

import org.txm.searchengine.cqp.corpus.query.Query

if (!(corpusViewSelection instanceof Corpus)) {

Corpus corpus = corpusViewSelection

def breaks_pos = Arrays.asList(corpus.query(new Query("[]</"+lineSeparatorStructureName+">"),"test", false).getEnds())

				corpus.getAttribute("lang"));

import org.txm.importer.DomUtils

package org.txm.macro.edition

import java.io.File;

import java.util.ArrayList;

import java.util.List;

import org.txm.scripts.importer.*

/**

 * Add a attribute value map in a XML file

 * Warning: if an attribute already exists its value won't be changed

 */

class AddAttributeValuesInXML extends StaxIdentityParser {

	File xmlFile;

	String tag, attribute;

	List<String> values;

	HashMap<String, String> attributesMap;

	boolean result;

	public AddAttributeValuesInXML(File xmlFile, String tag, String attribute, List<String> values)

	{

		super(xmlFile.toURI().toURL());

		this.xmlFile = xmlFile;

		this.tag = tag;

		this.attribute = attribute;

		this.values = values;

	}

	public boolean process(File outfile) {

		this.result = false;

		boolean ret = super.process(outfile)

		return this.result & ret;

	}

	/**

	 * Rewrite the processStartElement() to update/add attributes

	 */

	int n = 0;

	public void processStartElement()

	{

		if (localname != tag) {

			super.processStartElement()

		} else {

			String prefix = parser.getPrefix();

//TODO: uncomment for TXM 0.7.6

//			if (INCLUDE == localname && XI == prefix) {

//				processingXInclude();

//				return;

//			}

			if (prefix.length() > 0)

				writer.writeStartElement(Nscontext.getNamespaceURI(prefix), localname)

			else

				writer.writeStartElement(localname);

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

				writer.writeNamespace(parser.getNamespacePrefix(i), parser.getNamespaceURI(i));

			}

			// get attributes

			HashMap<String, String> attributes = new HashMap<String, String>();

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

				attributes[parser.getAttributeLocalName(i)] = parser.getAttributeValue(i);

			}

			// add/update the value

			if (n < values.size()) {

				attributes[attribute] = values[n]; 

			} else {

				println "ERROR: not enough values to insert for file $xmlFile, at XML parser location: l="+parser.getLocation().getLineNumber()+",c="+parser.getLocation().getColumnNumber()+")."

			}

			n++

			// write attributes

			for (def k : attributes.keySet()) {

				writer.writeAttribute(k, attributes[k])

			}

		}

	}

	@Override

	public void after() {

		super.after();

		if (n != values.size()) {

			println "ERROR: number of $tag ("+n+") missmatch the number of values to insert: "+values.size()

		}

	}

}

package org.txm.macro.edition

import org.txm.scripts.importer.*

import org.xml.sax.Attributes

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

import java.util.ArrayList

import javax.xml.parsers.*

import javax.xml.stream.*

import java.net.URL

import org.xml.sax.InputSource

import org.xml.sax.helpers.DefaultHandler

class BuildXTZEditions {

	private def url

	private def inputData

	private def factory

	private XMLStreamReader parser

	OutputStreamWriter writer

	StaxStackWriter pagedWriter = null

	File editionDir

	File xmlFile

	File htmlFile

	def pages = []

	def txtname, corpusname

	int wordsPerPage = 500

	boolean firstWord

	boolean cutBefore = true;

	public BuildFacsEditions(File xmlFile, File editionDir, String corpusname, String txtname, int wordsPerPage) {

		inputData = xmlFile.toURI().toURL().openStream()

		factory = XMLInputFactory.newInstance()

		parser = factory.createXMLStreamReader(inputData)

		this.xmlFile = xmlFile

		this.editionDir = editionDir

		this.txtname = txtname

		this.wordsPerPage = wordsPerPage

	}

	int n = 0;

	private boolean createNextOutput()

	{

		try {

			def tags = closeMultiWriter();

			for (int i = 0 ; i < tags.size() ; i++) {

				String tag = tags[i]

				if ("body" != tag) {

					tags.remove(i--)

				} else {

					tags.remove(i--) // remove "body"

					break; // remove elements until "body tag

				}

			}

			n++

			htmlFile = new File(editionDir, "${txtname}_${n}.html")

			firstWord = true

			pagedWriter = new StaxStackWriter(htmlFile, "UTF-8");

			pagedWriter.writeStartDocument("UTF-8", "1.0")

			pagedWriter.writeStartElement("html");

			pagedWriter.writeEmptyElement("meta", ["http-equiv":"Content-Type", "content":"text/html","charset":"UTF-8"]);

			pagedWriter.writeEmptyElement("link", ["rel":"stylesheet", "type":"text/css","href":"txm.css"]);

			pagedWriter.writeEmptyElement("link", ["rel":"stylesheet", "type":"text/css","href":"${corpusname}.css"]);

			pagedWriter.writeStartElement("head");

			pagedWriter.writeStartElement("title")

			pagedWriter.writeCharacters(corpusname+" Edition - Page "+n)

			pagedWriter.writeEndElement(); // </title>

			pagedWriter.writeEndElement() // </head>

			pagedWriter.writeStartElement("body") //<body>

			pagedWriter.writeStartElements(tags);

			return true;

		} catch (Exception ee) {

			System.out.println(ee);

			return false;

		}

	}

	private def closeMultiWriter()

	{

		if (pagedWriter != null) {

			def tags = pagedWriter.getTagStack().clone();

			if (firstWord) { // there was no words

				pagedWriter.writeCharacters("");

				pagedWriter.write("<span id=\"w_0\"/>");

				pages << ["$n", "w_0"]

			}

			pagedWriter.writeEndElements();

			pagedWriter.close();

			return tags;

		} else {

			return [];

		}

	}

	private writeImg(String src) {

		pagedWriter.writeStartElement("div");

		pagedWriter.writeEmptyElement("img", ["src":src]);

		pagedWriter.writeEndElement(); // </div>

	}

	public def process() {

		String wordid = "w_0"

		boolean start = false

		String localname

		createNextOutput();

		for (int event = parser.next(); event != XMLStreamConstants.END_DOCUMENT; event = parser.next()) {

			switch (event) {

				case XMLStreamConstants.START_ELEMENT:

					localname = parser.getLocalName();

					switch (localname) {

						case "text":

							start = true

						break;

						case "w":

							if (firstWord) {

								wordid = parser.getAttributeValue(null, "id");

								firstWord = false;

							}

						break;

						case "pb":

							if (cutBefore) {

								pages << ["$n", wordid]

								// WRITE PB

								createNextOutput()

							} else {

								createNextOutput()

								pages << ["$n", wordid]

								// WRITE PB

							}

						break;

					}

				break;

			}

		}

		closeMultiWriter()

		if (parser != null) parser.close();

		if (inputData != null) inputData.close();

		return pages

	}

}

// 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.macro.edition;

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.metadatas.*

import org.txm.utils.*

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

	String xpath

	Document doc

	public RemoveTag(def root, def outfile, def xpath)

	{

		this.doc = root

		this.outfile = outfile

		this.xpath = xpath

		process()

	}

	/**

	 *

	 * @param xmlfile the xmlfile

	 * @param outfile the outfile

	 * @param xpath the XPath

	 */

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

	{

		this.outfile = outfile

		this.xpath = xpath

		def domFactory = DocumentBuilderFactory.newInstance();

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

		DocumentBuilder builder = domFactory.newDocumentBuilder();

		this.doc = builder.parse(xmlfile);

		process()

	}

	private void process() {

		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()

	{

		if (outfile == null) return true;

		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 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']"

			)

	}

}

package org.txm.macro.edition

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcp.swt.widget.parameters.*

try { println "ARGS=$args";} catch(Exception e) {args = [:]}

// BEGINNING OF PARAMETERS

@Field @Option(name="sourceDirectory", usage="Directory containig XML-TXM or XML SRC files", widget="Folder", required=true, def="src")

def sourceDirectory

@Field @Option(name="imageDirectory", usage="directory containing the ordered images files in subdirectories", widget="Folder", required=true, def="img")

def imageDirectory

@Field @Option(name="outputDirectory", usage="Output directory", widget="Folder", required=true, def="out")

def outputDirectory

@Field @Option(name="element", usage="The element to upgrade", widget="String", required=true, def="pb")

def element

@Field @Option(name="attribute", usage="The attribute to add", widget="String", required=true, def="facs")

def attribute

@Field @Option(name="prefix", usage="The image path prefix, if empty then the absolute file path is used", widget="String", required=true, def="../img/")

def prefix

// Open the parameters input dialog box

if (args.size() == 0) {

	if (!ParametersDialog.open(this)) return;

} else {

	monitor = args["monitor"];

	sourceDirectory = args["sourceDirectory"]

	imageDirectory = args["imageDirectory"]

	outputDirectory = args["outputDirectory"]

	element = args["element"]

	attribute = args["attribute"]

	prefix = args["prefix"]

}

// END OF PARAMETERS

println "Parameters: "

println " sourceDirectory: $sourceDirectory"

println " imageDirectory: $imageDirectory"

println " outputDirectory: $outputDirectory"

println " element: $element"

println " attribute: $attribute"

assert(sourceDirectory.exists())

assert(imageDirectory.exists())

outputDirectory.deleteDir()

outputDirectory.mkdir()

if (!outputDirectory.exists()) {

	println "Error: failed to create $outputDirectory"

	return;

}

def srcFiles = []

sourceDirectory.eachFile() { file ->

	if (!file.isDirectory() && !file.isHidden() && file.getName().endsWith(".xml") && file.getName() != "import.xml") srcFiles << file

}

println "srcFiles=$srcFiles"

for (def subdir : imageDirectory.listFiles()) {

	if (!subdir.isDirectory()) continue;

	String name = subdir.getName();

	File srcFile = new File(sourceDirectory, name+".xml")

	if (!srcFile.exists()) { println "Warning: missing source file: $srcFile"; continue }

	def imgFiles = subdir.listFiles().sort()

	if (imgFiles.size() == 0) { println "Warning: no image in $subdir"; continue }

	def imgPaths = []

	for (def img : imgFiles) {

		if (img.isFile() && !img.isHidden()) {

			if (prefix != null && prefix.length() > 0)

				imgPaths << prefix+name+"/"+img.getName()

			else

				imgPaths << img.getAbsolutePath()

		}

	}

	println "Processing '$name' directory with "+imgPaths.size()+" images."

	AddAttributeValuesInXML builder = new AddAttributeValuesInXML(srcFile, element, attribute, imgPaths);

	builder.process(new File(outputDirectory, srcFile.getName()));

}

package org.txm.macro.edition

import org.txm.scripts.importer.*

import org.xml.sax.Attributes

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

import java.util.ArrayList

import javax.xml.parsers.*

import javax.xml.stream.*

import java.net.URL

import org.xml.sax.InputSource

import org.xml.sax.helpers.DefaultHandler

class BuildFacsEditions {

	private def url

	private def inputData

	private def factory

	private XMLStreamReader parser

	OutputStreamWriter writer

	StaxStackWriter pagedWriter = null

	File editionDir

	File xmlFile

	File htmlFile

	def pages = []

	def tag, attribute, txtname, corpusname

	boolean firstWord

	boolean cutBefore = true;

	boolean debug = false;

	public BuildFacsEditions(File xmlFile, File editionDir, String corpusname, String txtname, String tag, String attribute, boolean debug) {

		inputData = xmlFile.toURI().toURL().openStream()

		factory = XMLInputFactory.newInstance()

		parser = factory.createXMLStreamReader(inputData)

		this.xmlFile = xmlFile

		this.editionDir = editionDir

		this.tag = tag

		this.attribute = attribute

		this.txtname = txtname

		this.debug = debug

	}

	int n = 1;

	private boolean createNextOutput()

	{

		try {

			def tags = closeMultiWriter();

			for (int i = 0 ; i < tags.size() ; i++) {

				String tag = tags[i]

				if ("body" != tag) {

					tags.remove(i--)

				} else {

					tags.remove(i--) // remove "body"

					break; // remove elements until "body tag

				}

			}

			if (wordid != null) {//wordid = "w_0";

				//println " add page $n $wordid, page=$pages"

				pages << ["$n", wordid]

				n++

			}

			// Page suivante

			htmlFile = new File(editionDir, "${txtname}_${n}.html")

			firstWord = true

	//println "SET FIRST WORD=true"

			pagedWriter = new StaxStackWriter(htmlFile, "UTF-8");

			if (debug) println "Create file $htmlFile"

			pagedWriter.writeStartDocument("UTF-8", "1.0")

			pagedWriter.writeStartElement("html");

			pagedWriter.writeEmptyElement("meta", ["http-equiv":"Content-Type", "content":"text/html","charset":"UTF-8"]);

			pagedWriter.writeEmptyElement("link", ["rel":"stylesheet", "type":"text/css","href":"txm.css"]);

			pagedWriter.writeEmptyElement("link", ["rel":"stylesheet", "type":"text/css","href":"${corpusname}.css"]);

			pagedWriter.writeStartElement("head");

			pagedWriter.writeStartElement("title")

			pagedWriter.writeCharacters(corpusname+" Edition - Page "+n)

			pagedWriter.writeEndElement(); // </title>

			pagedWriter.writeEndElement() // </head>

			pagedWriter.writeStartElement("body") //<body>

			pagedWriter.writeStartElements(tags);

			wordid = "w_0"; // default value if no word is found

			return true;

		} catch (Exception e) {

			System.out.println(e.getLocalizedMessage());

			return false;

		}

	}

	private def closeMultiWriter()

	{

		if (pagedWriter != null) {

			def tags = pagedWriter.getTagStack().clone();

			if (firstWord) { // there was no words

				pagedWriter.writeCharacters("");

				pagedWriter.write("<span id=\"w_0\"/>");

			}

			pagedWriter.writeEndElements();

			pagedWriter.close();

			return tags;

		} else {

			return [];

		}

	}

	private writeImg(String src) {

		pagedWriter.writeStartElement("div");

		pagedWriter.writeEmptyElement("img", ["src":src, "width":"100%"]);

		pagedWriter.writeEndElement(); // </div>

	}

	String wordid = null;

	public def process() {

		boolean start = false

		String localname

		createNextOutput();

		for (int event = parser.next(); event != XMLStreamConstants.END_DOCUMENT; event = parser.next()) {

			switch (event) {

				case XMLStreamConstants.START_ELEMENT:

					localname = parser.getLocalName();

					switch (localname) {

						case "text":

							start = true

						break;

						case "w":

							if (firstWord) {

								wordid = parser.getAttributeValue(null, "id");

								//println "found word: $wordid"

								firstWord = false;

							}

						break;

						case tag:

							if (debug) println "** TAG $tag $attribute : "+parser.getAttributeValue(null, "id");

							String imgPath = parser.getAttributeValue(null, attribute);

							if (imgPath == null) {

								println "ERROR in $xmlFile no value found for $tag@$attribute at location "+parser.getLocation().getLineNumber()

							} else {

								if (cutBefore) {

									if (debug) println " cut before"

									createNextOutput()

									if (debug) println " write img $imgPath"

									writeImg(imgPath)

								} else {

									if (debug) println " write img $imgPath"

									writeImg(imgPath)

									if (debug) println " cut after"

									createNextOutput()

								}

							}

							//firstWord = true;

						break;

					}

				break;

			}

		}

		if (parser != null) parser.close();

		if (inputData != null) inputData.close();

		closeMultiWriter()

		pages << ["$n", wordid] // add the last page (no pb encountered

		return pages

	}

}

package org.txm.macro.edition

// STANDARD DECLARATIONS

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcp.swt.widget.parameters.*

import org.txm.objects.*

import org.txm.searchengine.cqp.corpus.*;

import org.w3c.dom.*

import org.txm.utils.xml.DomUtils

import org.txm.Toolbox

import org.w3c.dom.Document;

import org.xml.sax.SAXException;

import org.txm.rcp.commands.*

import javax.xml.parsers.*;

import javax.xml.transform.*;

import javax.xml.transform.dom.DOMSource;

import javax.xml.transform.stream.StreamResult;

try { println "ARGS=$args";} catch(Exception e) {args = [:]}

def corpus = null

if (args.size() == 0) {

	if (!(corpusViewSelection instanceof MainCorpus)) {

		println "This marcro works with a MainCorpus selection. Aborting"

		return;

	}

	println "Working on $corpusViewSelection corpus"

	corpus = corpusViewSelection

} else {

	monitor = args["monitor"];

}

// BEGINNING OF PARAMETERS

@Field @Option(name="editionName", usage="the edition name to create", widget="String", required=true, def="facs")

def editionName

@Field @Option(name="tag", usage="The tag to upgrade", widget="String", required=true, def="pb")

def tag

@Field @Option(name="attribute", usage="The attribute to add", widget="String", required=true, def="facs")

def attribute

@Field @Option(name="debug", usage="Debug mode", widget="Boolean", required=false, def="true")

def debug = false

// END OF params

if (args.size() == 0) {

	if (!ParametersDialog.open(this)) return;

} else {

	monitor = args["monitor"];

	attribute = args["attribute"]

	tag = args["tag"]

	editionName = args["editionName"]

}

if (args.size() == 0) { // the "corpus" variable exists

	binDirectory = corpus.getProject().getProjectDirectory()

	txmDirectory = new File(binDirectory, "txm/"+corpus.getID().toUpperCase())

	tokenizedDirectory = new File(binDirectory, "tokenized")

	HTMLDirectory = new File(binDirectory, "HTML")

	newEditionDirectory = new File(HTMLDirectory, corpus.getID().toUpperCase()+"/"+editionName)

	params = corpus.getProject().params

} else { // the "corpus" variable does not exist, get informations from the "args" map

	binDirectory = args["binDirectory"]

	txmDirectory = args["txmDirectory"]

	params = args["params"]

	tokenizedDirectory = new File(binDirectory, "tokenized")

	HTMLDirectory = new File(binDirectory, "HTML")

	corpusName = params.getCorpusName()

	newEditionDirectory = new File(HTMLDirectory, corpusName.toUpperCase()+"/"+editionName)

}

println "Parameters:"

println "	attribute = $attribute"

println "	tag =  $tag"

println "	editionName =  $editionName"

if (!HTMLDirectory.exists()) {

	println "ERROR: can't find this corpus 'HTML' directory: $HTMLDirectory. Aborting"

	return false;

}

File workDirectory = txmDirectory

if (!workDirectory.exists()) {

	println "XML-TXM directory ($txmDirectory) not found. Using XML tokenized directory instead: "+tokenizedDirectory

	workDirectory = tokenizedDirectory

}

if (!workDirectory.exists()) {

	println "XML tokenized directory not found: "+tokenizedDirectory

	println "Aborting."

	return false

}

println "Working directory=$workDirectory"

//0- clean previous edition if any : html files, import.xml

if (newEditionDirectory.exists()) {

	println "** Old version of $editionName edition found."

	println " removing the 'edition' reference from the corpus configuration."

	File tempParam = new File(binDirectory, "import.xml.cpy")

	RemoveTag rt = new RemoveTag(

			params.root.getOwnerDocument(), // will be updated

			null, // don't create a new import.xml

			"//edition[@name='$editionName']"

			)

	println " delete $newEditionDirectory"

	newEditionDirectory.deleteDir()

	//printDOM(params.root.getOwnerDocument())

}

//2- fix import.xml

println "** Updating corpus configuration..."

// for edition list

def corpusElem = params.getCorpusElement()

params.addEditionDefinition(corpusElem, editionName, "groovy", "FacsEditionBuilderMacro");

//1- create HTML files

println "** Building new edition HTML files..."

println " Creating edition '$editionName' directory: '$newEditionDirectory'"

newEditionDirectory.mkdir()

for (def xmlFile : workDirectory.listFiles()) {

	if (xmlFile.isHidden() || xmlFile.isDirectory()) continue // ignore

	String txtname = xmlFile.getName()

	int idx = txtname.lastIndexOf(".")

	if (idx > 0) txtname = txtname.substring(0,idx)

	// create a page per "pb" element found in the xml-txm file

	println " Building HTML pages of text=$txtname"

	BuildFacsEditions builder = new BuildFacsEditions(xmlFile, newEditionDirectory, params.name, txtname, tag, attribute, debug);

	def newPages = builder.process()

	if (newPages == null || newPages.size() == 0) {

		println "WARNING: no edition files created with $xmlFile"

	}

	println " Building edition references in corpus configuration"

	Element corpusElement = params.getCorpusElement();

	//println "corpusElement $corpusElement"

	Element textsElem = params.getTextsElement(corpusElement);

	//println "textsElem $textsElem"

	Element textElem = params.getTextElement(textsElem, txtname);

	if (textElem == null) { // just in case

		textElem = params.addText(textsElem, txtname, xmlFile)

	}

	//println "textElem $textElem with txtname=$txtname"

	Element editionElem = params.addEdition(textElem, editionName, newEditionDirectory.getAbsolutePath(), "html"); // add a new edition to the "text" node

	for (def pagedef : newPages) {

		params.addPage(editionElem, pagedef[0], pagedef[1]);

	}

}

//printDOM(params.root.getOwnerDocument())

//3- Save and reload the corpus

println " Saving corpus configuration..."

File paramFile = new File(binDirectory, "import.xml");

DomUtils.save(params.root.getOwnerDocument(), paramFile);

//4- Reload Corpora

if (args.size() == 0) {

	Toolbox.restart();

	monitor.syncExec(new Runnable() {

				public void run() {

					RestartTXM.reloadViews();

				}

			});

}

//5- Done

println "New edition created."

//printDOM(params.root.getOwnerDocument())

def printDOM(def doc) {

	if (!debug) return;

	try {

		// Création de la source DOM

		Source source = new DOMSource(doc);

		// Création du fichier de sortie

		StreamResult resultat = new StreamResult(new PrintWriter(System.out));

		// Configuration du transformer

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

		Transformer transformer = fabrique.newTransformer();

		transformer.setOutputProperty(OutputKeys.METHOD, "xml"); //$NON-NLS-1$

		transformer.setOutputProperty(OutputKeys.INDENT, "yes");  //$NON-NLS-1$

		transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");  //$NON-NLS-1$

		// Transformation

		transformer.transform(source, resultat);

		// writer.close();

		return true;

	} catch (Exception e) {

		e.printStackTrace();

		return false;

	}

}

package org.txm.macro.edition

// STANDARD DECLARATIONS

import org.kohsuke.args4j.*

import groovy.transform.Field

import org.txm.rcp.swt.widget.parameters.*

import org.txm.objects.*

import org.txm.searchengine.cqp.corpus.*;

import org.w3c.dom.*

import org.txm.scripts.importer.*

import org.txm.Toolbox

import java.io.*

import org.w3c.dom.Document;

import org.xml.sax.SAXException;

import org.txm.rcp.commands.*

import javax.xml.parsers.*;

import javax.xml.transform.*;

import javax.xml.transform.dom.DOMSource;

import javax.xml.transform.stream.StreamResult;

import org.txm.utils.io.FileCopy

try { println "ARGS=$args";} catch(Exception e) {args = [:]}

def corpus = null

if (args.size() == 0) {

	if (!(corpusViewSelection instanceof MainCorpus)) {

		println "This marcro works with a MainCorpus selection. Aborting"

		return;

	}

	println "Working on $corpusViewSelection corpus"

	corpus = corpusViewSelection

} else {

	monitor = args["monitor"];

}

// BEGINNING OF params

@Field @Option(name="xslEdition", usage="XSL to build the HTML edition - if empty uses 'txm-edition-xtz.xsl'", widget="File", required=false, def="txm-edition-xtz.xsl")

def xslEdition

@Field @Option(name="xslPages", usage="XSL to build the edition pages - if empty uses 'txm-edition-page-split.xsl'", widget="File", required=false, def="txm-edition-page-split.xsl")

def xslPages

@Field @Option(name="editionName", usage="The edition name to produce", widget="String", required=false, def="default")

String editionName

@Field @Option(name="useTokenizedDirectory", usage="Use the 'XML/w' of the 'tokenized' directory instead of the 'XML-TXM' files", widget="Boolean", required=false, def="false")

def useTokenizedDirectory = false

@Field @Option(name="debug", usage="Enable debug mode: temporary files are not deleted", widget="Boolean", required=false, def="false")

def debug = false

// END OF params

if (args.size() == 0) {

	if (!ParametersDialog.open(this)) return;

} else {

	monitor = args["monitor"];

	xslEdition = new File(args["xslEdition"])

	xslPages = new File(args["xslPages"])

	editionName = args["editionName"]

	useTokenizedDirectory = args["useTokenizedDirectory"]

}

if (args.size() == 0) { // corpus informations

	defaultEditionName = corpus.getDefaultEdition()

	corpusName = corpus.getID()

	binDirectory = corpus.getProject().getProjectDirectory()

	txmDirectory = new File(binDirectory, "txm/"+corpusName.toUpperCase())

	params = corpus.getProject().params

} else { // the "corpus" variable does not exists

	defaultEditionName = "default"

	binDirectory = args["binDirectory"]

	txmDirectory = args["txmDirectory"]

	params = args["params"]

	corpusName = params.getCorpusName()

}

if (editionName == null || editionName.length() == 0) {

	editionName = defaultEditionName

}

println "Parameters:"

println "	xslEdition = $xslEdition"

println "	xslPages = $xslPages"

println "	editionName = $editionName"

println "	useTokenizedDirectory = $useTokenizedDirectory"

File TXMHOME = new File(Toolbox.getTxmHomePath())

File xslDirectory = new File(TXMHOME, "xsl")

if (xslEdition == null || xslEdition.getName() == "txm-edition-xtz.xsl")

	xslEdition = new File(xslDirectory, "txm-edition-xtz.xsl")

if (xslPages == null || xslPages.getName() == "txm-edition-page-split.xsl")

	xslPages = new File(xslDirectory, "txm-edition-page-split.xsl")

println "XSLs: "+xslEdition.getName()+" & "+ xslPages.getName()

println ""

if (useTokenizedDirectory) {

	println "Using the 'tokenized' directory instead of the 'txm' directory to get XML files"

	txmDirectory = new File(binDirectory, "tokenized")

}

File HTMLDirectory = new File(binDirectory, "HTML")

File HTMLCorpusDirectory = new File(HTMLDirectory, corpusName.toUpperCase())

File defaultEditionDirectory = new File(HTMLCorpusDirectory, editionName)

File cssDirectory = new File(TXMHOME, "css")

File cssDefaultEditionDirectory = new File(defaultEditionDirectory, "css")

File cssTXM = new File(cssDirectory, "txm.css")

File cssTEI = new File(cssDirectory, "tei.css")

boolean newEdition = false;

if (!txmDirectory.exists()) {

	println "ERROR: can't find this corpus 'txm' directory: $txmDirectory. Aborting"

	return false;

}

if (!defaultEditionDirectory.exists()) {

	println "This is a new edition"

	newEdition = true;

	defaultEditionDirectory.mkdir()

	if (!defaultEditionDirectory.exists()) {

		println "HTML directory could be created: $defaultEditionDirectory. Aborting"

		return false

	}

}

if (!cssTXM.exists()) {

	println "WARNING: can't find the $cssTXM CSS file. Aborting"

	return false;

}

if (!cssTEI.exists()) {

	println "WARNING: can't find the $cssTEI CSS file. Aborting"

	return false;

}

if (!xslEdition.exists()) {

	println "Error: can't find $xslEdition XSL file"

	return false;

}

if (!xslPages.exists()) {

	println "Error: can't find $xslPages XSL file"

	return false;

}

defaultEditionDirectory.mkdir()

cssDefaultEditionDirectory.mkdir()

FileCopy.copy(cssTXM, new File(cssDefaultEditionDirectory, cssTXM.getName()))

FileCopy.copy(cssTEI, new File(cssDefaultEditionDirectory, cssTEI.getName()))

//1- Back up current "HTML" directory

if (!newEdition) {

	File backupDirectory = new File(binDirectory, "HTML-"+defaultEditionDirectory.getName()+"-back")

	backupDirectory.mkdir()

	println "Backup of $defaultEditionDirectory directory to $backupDirectory..."

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

		String name = f.getName()

		if (f.isDirectory() || f.isHidden()) continue

		File rez = new File(backupDirectory, f.getName())

		if (debug) println " file $f >> $rez"

		else print "."

		if (!FileCopy.copy(f, rez)) {

			println "Error: failed to backup $f"

			return false;

		}

	}

	println ""

}

//2- Apply edition XSL

println "Applying XSL 1: $xslEdition..."

ApplyXsl2 applier = new ApplyXsl2(xslEdition);

def htmlFiles = []

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

	String name = f.getName()

	String txtname = name.substring(0, name.lastIndexOf("."));

	File rez = new File(HTMLCorpusDirectory, txtname+".html")

	if (!f.isDirectory() && !f.isHidden() && name.endsWith(".xml") && !name.equals("import.xml")) {

		if (debug) println " file $f >> $rez"

		else print "."

		if (!applier.process(f, rez)) {

			println "Error: failed to process $f"

			return false

		} else {

			htmlFiles << rez

		}

	}

}

println ""

//3- Apply pages XSL

println "Applying XSL 2: $xslPages..."

ApplyXsl2 applier2 = new ApplyXsl2(xslPages);

applier2.setParam("editionname", editionName)

applier2.setParam("cssname", corpusName)

for (File f : htmlFiles) {

	String name = f.getName()

	String txtname = name.substring(0, name.lastIndexOf("."));

	File rez = new File(defaultEditionDirectory, txtname+"-pages.html")

	if (debug) println " file $f >> $rez"

	else print "."

	if (!applier2.process(f, rez)) {

		println "Error: failed to process $f"

		return false

	} else {

		if (!debug) rez.delete()

	}

}

println ""

// clean temp files

if (!debug) {

	for (File f : htmlFiles) {

		f.delete()

	}

}

//4- register new edition if any (copy edition)

if (editionName != defaultEditionName) {

	println "Update corpus configuration"

	// remove edition declaration if any

	RemoveTag rt = new RemoveTag(

			params.root.getOwnerDocument(), // will be updated

			null, // don't create a new import.xml

			"//edition[@name='$editionName']"

			)

	def corpusElem = params.getCorpusElement()

	params.addEditionDefinition(corpusElem, editionName, "xsl", "XSLEditionBuilder"); // declare the new edition

	for (def text : corpus.getTexts()) {

		Element textElem = text.getSelfElement()

		def defaultEdition = text.getEdition(defaultEditionName)

		if (defaultEdition == null) { println "Error: no default edition with name="+defaultEditionName; return false} 

		Element editionElem = params.addEdition(textElem, editionName, defaultEditionDirectory.getAbsolutePath(), "html");

		def pages = defaultEdition.getPages()

		for (int i = 1 ; i <= pages.size() ; i++) {

			def page = pages[i-1]

			params.addPage(editionElem, "$i", page.getWordId());

		}

	}

	File paramFile = new File(binDirectory, "import.xml");

	DomUtils.save(params.root.getOwnerDocument(), paramFile);

}

//5- Reload Corpora

if (args.size() == 0) { // the user run the macro

	Toolbox.restart();

	monitor.syncExec(new Runnable() {

			public void run() {

				RestartTXM.reloadViews();

			}

		});

}

println "New edition created."

package org.txm.macro.misc

@Field @Option(name="inputDirectory",usage="TXT directory", widget="Folder", required=false, def="txt")

File inputDirectory;

// **change this parameter**

@Field @Option(name="extension",usage="Regexp de l'extension des fichiers à modifier", widget="String", required=true, def='\\.txt')

def extension = "\\.trs"

// **change this parameter**

@Field @Option(name="find",usage="Expression régulière", widget="String", required=true, def='’')

def find = "Bobine"

// **change this parameter**

@Field @Option(name="replaceWith",usage="Chaîne de remplacement", widget="String", required=false, def='\'')

def replaceWith = ""

println "In $inputDirectory..."

inputDirectory.eachFileMatch(~/.*$extension/) { file ->               // for each file matching extension

		println " renaming: "+file.getName()

		String name = file.getName()

		name = name.replaceAll(find, replaceWith)

		file.renameTo(new File(file.getParentFile(), name))

	}