Laboratoire ICAR » Plateforme TXM

	@Override

	protected boolean __compute(TXMProgressMonitor monitor) throws Exception {

		if (!CQPSearchEngine.isInitialized()) {

			Log.warning("** TXM can't load MainCorpus when CQP search engine is not ready.");

			return false;

				PatchCwbRegistry.patch(this.registryFile, this.dataDirectory);

			}

			catch (IOException e) {

				Log.printStackTrace(e);

				return false;

			}

			CQPSearchEngine.getCqiClient().load_a_system_corpus(this.registryFile.getParent(), this.pID);

			corpora.put(this.pID, this); // register the corpus

		}

		catch (Exception e) {

	public void clean() {

		super.clean();

			CorpusManager.getCorpusManager().getCorpora().remove(this.pID);

		}

		}

		catch (Exception e) {

			Log.fine(e.getLocalizedMessage());

		}

		if (dataDirectory != null) {

	 */

	@Override

	public List<WordProperty> getProperties() throws CqiClientException {

			return this.lexicalUnitsProperties;

		String[] propertiesName;

		try {

		}

		catch (Exception e) {

			throw new CqiClientException(e);

		}

		}

		this.lexicalUnitsProperties = properties;

		return properties;

	}

 *

 * @author mdecorde

 */

	static Pattern pattern = Pattern.compile("\\p{Upper}(\\p{Upper}|\\p{Digit}|[_-])*"); //$NON-NLS-1$

	static Pattern pattern2 = Pattern.compile("\\p{Upper}(\\p{Lower}|\\p{Digit}|[_-])*"); //$NON-NLS-1$

	String lastError;

	/**

	 * Check wether <code>id</code> is a valid CQi for a corpus.

	 *

	 * @return true if <code>id</code> is in uppercase chararcters

	 */

	public static synchronized boolean checkCorpusId(String id) {

		return pattern.matcher(id).matches();

	}

	/**

	 * Check whether <code>id</code> is a valid CQi for a subcorpus.

	 *

	 * @param id the id

	 * @return true if <code>id</code> is an uppercase character followed by

	 */

	public static synchronized boolean checkSubcorpusId(String id) {

		return pattern2.matcher(id).matches();

	}

			return lastError;

		}

		return CQPSearchEngineCoreMessages.noError;

		if (!isWordProperty) {

			StructuralUnitProperty sprop = (StructuralUnitProperty) prop;

			int[] strucs = this.cpos2Struc(qname, qresult.getStarts());

			return Arrays.asList(cqiClient.struc2Str(qname, strucs));

		}

	}

	public List<String> getSingleData(Property prop, int[] positions) throws UnexpectedAnswerException, IOException, CqiServerError {

			int[] strucs = cqiClient.cpos2Struc(qname, positions);

			return Arrays.asList(cqiClient.struc2Str(qname, strucs));

		}

	}

	public List<List<String>> getData(Property prop, List<Integer> positions,

			List<Integer> nWords) throws CqiClientException, IOException, CqiServerError {

		// get all the positions needed, possible overlap

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

			int n = nWords.get(i);

			for (int j = 0; j < n; j++) {

		// conversion from List<Integer> to int[]

		int[] cpos = new int[allPositionsNeeded.size()];

		int c = 0;

		// get values for positions

		String[] values;

		boolean isWordProperty = !(prop instanceof StructuralUnitProperty);

		if (!isWordProperty) {

			int[] structs = this.cpos2Struc(qname, cpos);

			values = this.struc2Str(qname, structs);

			String qname = prop.getQualifiedName();

			values = this.cpos2Str(qname, cpos);

		}

		// sort results by position

			map.put(cpos[i], values[i]);

		}

		// fill results

		int start, end;

		SortedMap<Integer, String> smap;

			start = positions.get(i);

			end = positions.get(i) + nWords.get(i);

			if (start > end) {

				result.add(new ArrayList<String>());

				smap = map.subMap(start, end);

			}

		}

		return result;

	}

	/**

	 * Return lists of strings.

	 *

	 * @throws CqiClientException the cqi client exception

	 */

	public List<String> getData(StructuralUnitProperty property, CQPCorpus corpus) throws CqiClientException {

	}

	/**

	 */

	public List<String> getData(StructuralUnitProperty prop, int number) throws CqiClientException {

	}

	 * @return true, if successful

	 */

	@Override

	// None

	/**

	 * Disconnect.

	 */

	@Override

	public abstract boolean disconnect() throws UnexpectedAnswerException, CqiServerError, IOException;

	// CQI_CTRL_LAST_GENERAL_ERROR

	/**

	 * return the last CQP error.

	 * @return the last error

	 */

	@Override

	// CQI_CTRL_LAST_CQP_ERROR

	/**

	 * return the last CQP error.

	 * @return the last error

	 */

	@Override

	// None

	/**

	 * Lists the corpora available on the server.

	 */

	@Override

	public abstract String[] listCorpora() throws UnexpectedAnswerException, IOException, CqiServerError;

	// None

	/**

	 * Gives the corpus charset.

	 */

	@Override

	public abstract String corpusCharset(String corpus) throws UnexpectedAnswerException, IOException, CqiServerError;

	// None (not really implemented anyway)

	/**

	 * Gives the corpus properties.

	 */

	@Override

	public abstract String[] corpusProperties(String corpus) throws UnexpectedAnswerException, IOException, CqiServerError;

	// CQI_CQP_ERROR_NO_SUCH_CORPUS

	/**

	 * Gives the corpus positional attributes.

	 */

	@Override

	public abstract String[] corpusPositionalAttributes(String corpusID) throws UnexpectedAnswerException, IOException, CqiServerError;

	// CQI_CQP_ERROR_NO_SUCH_CORPUS

	/**

	 * Gives the corpus structural attributes.

	 */

	@Override

	public abstract String[] corpusStructuralAttributes(String corpus) throws UnexpectedAnswerException, IOException, CqiServerError;

	// CQI_CQP_ERROR_NO_SUCH_CORPUS, CQI_CL_ERROR_NO_SUCH_ATTRIBUTE,

	// CQI_CL_ERROR_WRONG_ATTRIBUTE_TYPE

	/**

	 */

	@Override

	public abstract boolean corpusStructuralAttributeHasValues(String attribute) throws UnexpectedAnswerException, IOException,

	// CQI_CQP_ERROR_NO_SUCH_CORPUS

	/**

	 * Gives the corpus alignement attributes.

	 */

	@Override

	public abstract String[] corpusAlignementAttributes(String corpus) throws UnexpectedAnswerException, IOException, CqiServerError;

	// CQI_CQP_ERROR_NO_SUCH_CORPUS

	/**

	 * Gives the corpus full name.

	 */

	@Override

	public abstract String corpusFullName(String corpus) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Gives the corpus info listed in the .INFO file.

	 *

	 */

	@Override

	public abstract String[] corpusInfo(String corpus) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Drop a corpus.

	 * 

	 */

	@Override

	public abstract void dropCorpus(String corpus) throws Exception;

	// CQI_CQP_ERROR_NO_SUCH_CORPUS, CQI_CL_ERROR_NO_SUCH_ATTRIBUTE,

	// CQI_CL_ERROR_WRONG_ATTRIBUTE_TYPE, CQI_CL_ERROR_CORPUS_ACCESS

	/**

	 */

	@Override

	public abstract int attributeSize(String attribute) throws IOException, UnexpectedAnswerException, CqiServerError;

	// CQI_CQP_ERROR_NO_SUCH_CORPUS, CQI_CL_ERROR_NO_SUCH_ATTRIBUTE,

	// CQI_CL_ERROR_WRONG_ATTRIBUTE_TYPE, CQI_CL_ERROR_CORPUS_ACCESS

	/**

	 */

	@Override

	public abstract int lexiconSize(String attribute) throws IOException, UnexpectedAnswerException, CqiServerError;

	/**

	 * Drop attribute.

	 *

	 */

	@Override

	public abstract void dropAttribute(String attribute) throws IOException, UnexpectedAnswerException, CqiServerError;

	/**

	 * Converts an array of attribute values to their ID.

	 *

	 */

	@Override

	public abstract int[] str2Id(String attribute, String[] strings) throws IOException, UnexpectedAnswerException, CqiServerError;

	/**

	 * Converts an array of attribute ID to their values.

	 *

	 */

	@Override

	public abstract String[] id2Str(String attribute, int[] ids) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Converts an array of attribute IDs to their frequency.

	 *

	 */

	@Override

	public abstract int[] id2Freq(String attribute, int[] ids) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Converts an array of position to their ID given an attribute.

	 *

	 */

	@Override

	public abstract int[] cpos2Id(String attribute, int[] cpos) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Converts an array of position to their value given an attribute.

	 *

	 */

	@Override

	public abstract String[] cpos2Str(String attribute, int[] cpos) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Computes for each position of an array the Id of the enclosing structural

	 * attribute.

	 */

	@Override

	public abstract int[] cpos2Struc(String attribute, int[] cpos) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Computes for each position of an array the position of the left boundary

	 * of the enclosing structural attribute.

	 */

	@Override

	public abstract int[] cpos2LBound(String attribute, int[] cpos) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Computes for each position of an array the position of the right boundary

	 * of the enclosing structural attribute.

	 */

	@Override

	public abstract int[] cpos2RBound(String attribute, int[] cpos) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Computes for each position of an array the Id of the enclosing alignment

	 * attribute.

	 */

	@Override

	public abstract int[] cpos2Alg(String attribute, int[] cpos) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Retrieves annotated string values of structure regions in <strucs>; "" if

	 * out of range.

	 */

	@Override

	public abstract String[] struc2Str(String attribute, int[] strucs) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Retrieves all corpus positions where the given token occurs.

	 *

	 */

	@Override

	public abstract int[] id2Cpos(String attribute, int id) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Retrieves all corpus positions where one of the tokens in <id_list>

	 * occurs; the returned list is sorted as a whole, not per token id.

	 */

	@Override

	public abstract int[] idList2Cpos(String attribute, int[] ids) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Retrieves the lexicon IDs of all tokens that match <regex>; the returned

	 * list may be empty (size 0).

	 */

	@Override

	public abstract int[] regex2Id(String attribute, String regex) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Retrieves the start and end corpus positions of structure region <struc>.

	 *

	 */

	@Override

	public abstract int[] struc2Cpos(String attribute, int struc) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Retrieves start and end corpus positions of an alignement region in the

	 * source and target corpora<struc>.

	 * @param attribute the attribute

	 * @param struc the struc

	 * @return an array of size 4 containing (src_start, src_end, target_start,

	 * @throws UnexpectedAnswerException Signals that the data read on the socket is unexpected

	 * @throws IOException Signals that an I/O exception has occurred.

	 * @throws CqiServerError the cqi server error

	 */

	@Override

	public abstract int[] alg2Cpos(String attribute, int struc) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Runs a CQL query.

	 *

	 */

	@Override

	public abstract void cqpQuery(String motherCorpus, String subcorpus, String query) throws IOException, UnexpectedAnswerException, CqiServerError;

	/**

	 * Runs a CQP query line.

	 *

	 */

	@Override

	public abstract void query(String query) throws IOException, UnexpectedAnswerException, CqiServerError;

	/**

	 *

	 * @param motherCorpus the mother corpus

	 * @param query the query

	 * @throws IOException Signals that an I/O exception has occurred.

	 * @throws UnexpectedAnswerException Signals that the data read on the socket is unexpected

	 * @throws CqiServerError the cqi server error

	 */

	@Override

	public abstract boolean load_a_system_corpus(String regfilepath, String entry) throws IOException, UnexpectedAnswerException, CqiServerError;

	/**

	 * Lists all the subcorpora of a corpus.

	 *

	 */

	@Override

	public abstract String[] listSubcorpora(String corpus) throws UnexpectedAnswerException, IOException, CqiServerError;

	/**

	 * Gives the size of a subcorpus .

	 * 

	 */

	@Override

	public abstract int subCorpusSize(String subcorpus) throws IOException,

	/**

	 * Checks wether a subcorpus has a field.

	 * 

	 */

	@Override

	public abstract boolean subCorpusHasField(String subcorpus, byte field) throws IOException, UnexpectedAnswerException, CqiServerError;

	/**

	 * Dumps the values of <field> for match ranges <first> .. <last> in

	 * <subcorpus>. <field> is one of the CQI_CONST_FIELD_* constants.

	 */

	@Override

	public abstract int[] dumpSubCorpus(String subcorpus, byte field, int first, int last) throws IOException, UnexpectedAnswerException,

	/**

	 * Drops a subcorpus.

	 * 

	 */

	@Override

	public abstract void dropSubCorpus(String subcorpus) throws IOException,

	/**

	 * Returns <n> (id, frequency) pairs flattened into a list of size 2*<n> NB:

	 * pairs are sorted by frequency desc.

	public abstract int[][] fdist1(String subcorpus, int cutoff,

			byte field, String attribute) throws IOException,

			UnexpectedAnswerException, CqiServerError;

	/**

	 * Returns <n> (id1, id2, frequency) pairs flattened into a list of size

	 * 3*<n> NB: triples are sorted by frequency desc. .

	@Override

	public abstract int[][] fdist2(String subcorpus, int cutoff,

			byte field1, String attribute1, byte field2, String attribute2) throws IOException, UnexpectedAnswerException, CqiServerError;

	@Override

// STANDARD DECLARATIONS

package org.txm.macro.export

import groovy.transform.Field

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

if (!(corpusViewSelection instanceof CQPCorpus)) {

	println "Please select a corpus"

}

// PARAMETERS

File exportDirectory

def lineSeparatorStructureName

if (!ParametersDialog.open(this)) return

if (!exportDirectory.exists()) exportDirectory.mkdirs()

def lineSeparatorStructure = corpus.getStructuralUnit(lineSeparatorStructureName)

if (lineSeparatorStructure == null) {

}

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

def wordProperty = corpus.getWordProperty()

def textidProperty = corpus.getStructuralUnit("text").getProperty("id")

int[] struct_pos = CQI.cpos2Struc(textidProperty.getQualifiedName(), textStartBoundaries)

String[] textids =  CQI.struc2Str(textidProperty.getQualifiedName(), struct_pos)

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

	int end = textEndBoundaries[i]

	File txtFile = new File(exportDirectory, textids[i]+".txt")

	def writer = txtFile.newWriter("UTF-8")

	int[] positions = new int[end - start + 1]

	for (int p : start..end) {

		positions[c++] = p

	}

	int[] idx = CQI.cpos2Id(wordProperty.getQualifiedName(), positions)

	def words = CQI.id2Str(wordProperty.getQualifiedName(), idx)

	for (int j = 0 ; j < positions.length ; j++) {

		int p = positions[j]

	}

}  

println "\nDone, result saved in "+exportDirectory.getAbsolutePath()

import org.txm.importer.xtz.*

public class XTZDefaultPagerStep {

	List<String> NoSpaceBefore;

	/** The No space after. */

	List<String> NoSpaceAfter;

	/** The wordcount. */

	int wordcount = 0;

	/** The pagecount. */

	int pagecount = 0;

	/** The wordmax. */

	int wordmax = 0;

	/** The basename. */

	String basename = "";

	String txtname = "";

	File outdir;

	/** The wordid. */

	String wordid;

	/** The first word. */

	boolean firstWord = true;

	/** The wordvalue. */

	String wordvalue = "";

	/** The interpvalue. */

	String interpvalue = "";

	/** The lastword. */

	String lastword = " ";

	/** The wordtype. */

	String wordtype;

	/** The flagform. */

	boolean flagform = false;

	/** The flaginterp. */

	boolean flaginterp = false;

	/** The url. */

	private def url;

	/** The input data. */

	private def inputData;

	/** The factory. */

	private def factory;

	/** The parser. */

	private XMLStreamReader parser;

	/** The writer. */

	OutputStreamWriter writer;

	/** The pagedWriter. */

	StaxStackWriter pagedWriter = null;

	/** The infile. */

	File infile;

	/** The outfile. */

	File outfile;

	/** The pages. */

	//TODO enhance this to store the page name/id as well

	ArrayList<File> pages = new ArrayList<File>();

	/** The idxstart. */

	ArrayList<String> idxstart = new ArrayList<String>();

	String paginationElement;

	def noteElements = new HashSet<String>();

	def outOfTextElements = new HashSet<String>();

	XTZPager pager;

	/**

	 * Instantiates a new pager.

	 *

		this.infile = infile;

		this.wordTag= pager.wordTag;

		outdir.mkdirs()

		inputData = new BufferedInputStream(url.openStream());

		factory = XMLInputFactory.newInstance();

		parser = factory.createXMLStreamReader(inputData);

		String notesListString = pager.getImportModule().getProject().getTextualPlan("Note")

		if (notesListString != null) for (def s : notesListString.split(",")) noteElements << s;

		String elems = pager.getImportModule().getProject().getTextualPlan("OutSideTextTagsAndKeepContent")

		if (elems != null) for (def s : elems.split(",")) outOfTextElements << s;

		//process();

	}

	public String getAttributeValue(def parser, String ns, String name) {

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

			if (name == parser.getAttributeLocalName(i)) {

		}

		return "";

	}

	private def closeMultiWriter() {

		if (pagedWriter != null) {

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

			if (firstWord) { // there was no words

				pagedWriter.writeCharacters("");

				this.idxstart.add("${wordTag}_0")

				}

				notes.clear()

			}

			pagedWriter.close();

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

				String tag = tags.remove(0)

				i--

				if (tag == "div") {

					break; // remove elements until first "div" tag

				}

			}

			return tags;

		} else {

			return [];

		}

	}

	/**

	 * Creates the next output.

	 *

			outfile = new File(outdir, txtname+"_"+(++pagecount)+".html")

			pages.add(outfile)

			firstWord = true; // waiting for next word

			pagedWriter = new StaxStackWriter(outfile, "UTF-8")

			//pagedWriter.writeStartDocument()

			pagedWriter.writeDTD("<!DOCTYPE html>")

			pagedWriter.writeCharacters("\n")

			pagedWriter.writeCharacters("\n")

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

			pagedWriter.writeStartElement("div", ["class": "txmeditionpage"]) //<div>

			pagedWriter.writeStartElements(tags)

			return true;

		} catch (Exception e) {

			return false;

		}

	}

	/**

	 * Creates the output.

	 *

			return false;

		}

	}

	/**

	 * Gets the page files.

	 *

	public ArrayList<File> getPageFiles() {

		return pages;

	}

	/**

	 * Gets the idx.

	 *

	public ArrayList<String> getIdx() {

		return idxstart;

	}

	/**

	 * Go to text.

	 */

					return;

		}

	}

	def notes = []

	def currentOutOfTextElements = [] // stack of element with out of text to edit opened element

	def writeOutOfTextToEditText = false

	 * Process.

	 */

	public boolean process() {

		try {

			boolean flagNote = false;

			String noteContent = "";

			String rend = ""

			goToText();

			String localname = "";

			if (!createNextOutput()) {

				return false;

			}

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

				rend = "";

				switch (event) {

						} else if (currentOutOfTextElements.size() > 0) {

							currentOutOfTextElements << localname

						}

						if (localname == paginationElement) {

							createNextOutput()

							wordcount=0;

								pagedWriter.writeElement("p", ["class":"txmeditionpb", "align":"center"], getAttributeValue(parser, null,"n"))

							}

						}

						rend = getAttributeValue(parser, null, "rend")

						if (rend == null) rend = "";

						switch (localname) {

							case "text":

								LinkedHashMap attributes = new LinkedHashMap();

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

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

								}

								pagedWriter.write("\n")

								pagedWriter.writeStartElement("p")

								pagedWriter.writeAttribute("class", rend)

								if (attributes.containsKey("id")) {

									pagedWriter.writeElement("h3", attributes["id"])

								}

								pagedWriter.writeStartElement("table")

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

									if (k == "id") continue;

									if (k == "rend") continue;

									pagedWriter.writeStartElement("tr")

									pagedWriter.writeElement("td", k)

									pagedWriter.writeElement("td", attributes[k])

								break;

							case "sp":

								pagedWriter.writeStartElement("p", ["class":"turn"])

								break;

							case "u":

								break;

							case "div":

							case "div1":

								break;

							case wordTag:

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

								wordcount++;

								if (wordcount >= wordmax) {

									createNextOutput();

								}

								if (firstWord) {

									firstWord = false;

									this.idxstart.add(wordid);

								}

								break;

							case "ana":

								flaginterp=true;

						localname = parser.getLocalName();

						if (currentOutOfTextElements.size() > 0) currentOutOfTextElements.pop()

						writeOutOfTextToEditText = currentOutOfTextElements.size() > 0

						switch (localname) {

							case "text":

								break;

								if (l > 0) {

									endOfLastWord = lastword.subSequence(l-1, l)

								}

								if (interpvalue != null) {

									interpvalue = interpvalue

								}

									pagedWriter.writeCharacters("\n")

									pagedWriter.writeStartElement("span", ["title":interpvalue, "id":wordid])

								}

								pagedWriter.writeCharacters(wordvalue)

								pagedWriter.writeEndElement()

								lastword=wordvalue;

								break;

							default:

	File xmlfile;

	/** The metadatas. */

	/** The headers list. */

	/** The isinialize. */

	boolean isInitialize = false;

	public HashMap<String, String> getTextMetadata(File f) {

		String txtname = f.getName();

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

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

	 */

	public static boolean convertCsvToXml(File csvfile, File xmlFile, String encoding, String separator, String txtseparator, int nbheaderline) throws Exception {

			}

			}

			}

			}

			}

			}

				}

				}

				}

			writer.writeCharacters("\n");