/ - Diff - Plateforme TXM - Forge du Centre Blaise Pascal

Révision 2930

     import org.odftoolkit.odfdom.dom.element.table.TableTableRowElement;
     import org.odftoolkit.simple.SpreadsheetDocument;
     import org.odftoolkit.simple.table.Cell;
     import org.odftoolkit.simple.table.Row;
     import org.odftoolkit.simple.table.Table;
     import org.w3c.dom.NodeList;
-...
     	String[] headers;
     	HashMap<String, String> record = null;
     	int iRow = 0;
     	int nRows, nCols;
     	public ReadODS(File tableFile, String sheetname) throws Exception {
     		spreadsheet = SpreadsheetDocument.loadDocument(tableFile);
-...
     		if (table == null) {
     			table = spreadsheet.getSheetByIndex(0);
+    		}
     		nRows = table.getRowCount();
     		nCols = table.getColumnCount();
     		// table.getRowByIndex(0);
+    	}
-...
+    			}
+    		}
     		if (iRow == 0) iRow = 1; // skip first line
     		return headers.length > 0;
+    	}
-...
+    	}
     	public boolean readRecord() {
     		return false;
     		if (iRow < nRows) {
     			_getRecord();
     			iRow++; // for next
     			return true;
+    		}
     		else { // end of file
     			record = null;
     			return false;
+    		}
+    	}
     	protected void _getRecord() {
     		record = new HashMap<>();
     		Row row = table.getRowByIndex(iRow);
     		for (int colIndex = 0; colIndex < headers.length; colIndex++) {
     			String col = headers[colIndex];
     			Cell cell = row.getCellByIndex(colIndex);
     			if (cell != null) {
     				String value = cell.getStringValue();
     				if (value == null) {
     					record.put(col, "");
+    				}
     				else {
     					record.put(col, value);
+    				}
+    			}
     			else {
     				record.put(col, "");
+    			}
+    		}
     		for (String k : record.keySet())
     			if (record.get(k) == null) System.out.println("ERROR null value with " + k);
+    	}
     	public HashMap<String, String> getRecord() {
     		return null;
     		return record;
+    	}
     	public static ArrayList<HashMap<String, String>> toHashMap(File inputFile, String sheetname) throws Exception {
-...
+    	}
     	public static void main(String[] args) throws Exception {
     		File file = new File("/home/mdecorde/xml/ruscorpora1m-test/metadata.ods");
     		ArrayList<ArrayList<String>> table = toTable(file, "metadata");
     		File file = new File("/home/mdecorde/Téléchargements/Requêtes_SVO-SOV.ods");
     		ArrayList<ArrayList<String>> table = toTable(file, null);
     		for (ArrayList<String> line : table) {
     			System.out.print(line.get(0) + ", ");
     			System.out.println(line);
+    		}
     		// Metadatas m = new Metadatas(file, )
+    	}

     		if (headers == null) return false;
     		int colMax = headers.getLastCellNum();
     		ArrayList<Integer> columnIdxToTest = new ArrayList<Integer>();
     		ArrayList<String> columnsTest = new ArrayList<String>();
     		ArrayList<Integer> columnIdxToTest = new ArrayList<>();
     		ArrayList<String> columnsTest = new ArrayList<>();
     		for (int colIndex = 0; colIndex < colMax; colIndex++) {
     			Cell cell = headers.getCell(colIndex);
     			if (cell != null) {
-...
     			return false;
+    		}
     		ArrayList<Integer> removed = new ArrayList<Integer>();
     		ArrayList<Integer> removed = new ArrayList<>();
     		for (int rowIndex = 0; rowIndex < nRows; rowIndex++) {
     			Row row = ws.getRow(rowIndex);
     			if (row == null) continue;
-...
     		int colMax = headers.getLastCellNum();
     		ArrayList<Integer> columnIdxToTest = new ArrayList<Integer>();
     		ArrayList<Integer> columnIdxToWrite = new ArrayList<Integer>();
     		ArrayList<String> columns = new ArrayList<String>();
     		ArrayList<String> columnsTest = new ArrayList<String>();
     		ArrayList<Integer> columnIdxToTest = new ArrayList<>();
     		ArrayList<Integer> columnIdxToWrite = new ArrayList<>();
     		ArrayList<String> columns = new ArrayList<>();
     		ArrayList<String> columnsTest = new ArrayList<>();
     		for (int colIndex = 0; colIndex < colMax; colIndex++) {
     			Cell cell = headers.getCell(colIndex);
     			if (cell != null) {
-...
     		if (columnIdxToWrite.size() != columnsSelection.size()) {
     			System.out.println("Error: not all columns found=" + columnIdxToWrite + " of " + columnsSelection);
     			ArrayList<String> notFound = new ArrayList<String>(columnsSelection);
     			ArrayList<String> notFound = new ArrayList<>(columnsSelection);
     			notFound.removeAll(columns);
     			System.out.println("NOT FOUND: " + notFound);
     			return false;
-...
+    	}
     	protected void _getRecord() {
     		record = new HashMap<String, String>();
     		record = new HashMap<>();
     		Row row = ws.getRow(iRow);
     		for (int colIndex = 0; colIndex < header.length; colIndex++) {
-...
     			if (cell != null) {
     				String value = cellToString(cell).trim();
     				if (value == null) {
     					record.put(header[colIndex], "");
     					record.put(col, "");
+    				}
     				else {
     					record.put(header[colIndex], value);
     					record.put(col, value);
+    				}
+    			}
     			else {
     				record.put(header[colIndex], "");
     				record.put(col, "");
+    			}
+    		}
-...
     	 */
     	public static ArrayList<ArrayList<String>> toTable(File inputFile, String sheetName) {
     		ArrayList<ArrayList<String>> data = new ArrayList<ArrayList<String>>();
     		ArrayList<ArrayList<String>> data = new ArrayList<>();
     		if (!inputFile.canRead()) {
     			System.out.println("** Excel2XML: '" + inputFile.getName() + "' file not readable. Aborting.");
-...
     			Row firstRow = ws.getRow(0);
     			int colMax = firstRow.getLastCellNum();
     			ArrayList<String> headers = new ArrayList<String>();
     			ArrayList<String> headers = new ArrayList<>();
     			for (int it = 0; it < colMax; it++) {
     				headers.add(firstRow.getCell(it).getStringCellValue());
+    			}
     			for (int rowIndex = 0; rowIndex < nRows; rowIndex++) {
     				Row row = ws.getRow(rowIndex);
     				ArrayList<String> dataLine = new ArrayList<String>();
     				ArrayList<String> dataLine = new ArrayList<>();
     				data.add(dataLine);
     				for (int colIndex = 0; colIndex < colMax; colIndex++) {
     					Cell cell = row.getCell(colIndex);
-...
+    		}
+    	}
     	public static void main(String[] args) throws Exception {
     		File tableFile = new File("/home/mdecorde/Téléchargements/Requêtes_SVO-SOV.xlsx");
     		// ReadExcel excel = new ReadExcel(tableFile, null);
     		ArrayList<ArrayList<String>> table = ReadExcel.toTable(tableFile, null);
     		for (ArrayList<String> line : table) {
     			System.out.println(line);
+    		}
+    	}
     	public static void mainAF(String[] args) throws Exception {
     		// ArrayList<ArrayList<String>> data = toTable(new File("/home/mdecorde/xml/ruscorpora1m-test/metadata.xlsx"), null);
     		// if (data.size() == 0) {
     		// System.out.println("no data.");
-...
     		System.out.println("open...");
     		ReadExcel excel = new ReadExcel(tableFile, null);
     		HashMap<String, String> lineRules = new HashMap<String, String>(); // line tests to select line to keep
     		HashMap<String, String> lineRules = new HashMap<>(); // line tests to select line to keep
     		List<String> columnsSelection; // list of columns to keep
     		HashMap<String, String> columnsToCopy = new HashMap<String, String>();
     		HashMap<String, String> columnsToRenameRules = new HashMap<String, String>();
     		HashMap<String, String[]> searchAndReplaceRules = new HashMap<String, String[]>();
     		HashMap<String, String> columnsToCopy = new HashMap<>();
     		HashMap<String, String> columnsToRenameRules = new HashMap<>();
     		HashMap<String, String[]> searchAndReplaceRules = new HashMap<>();
     		// //emissions
     //		 table2File = new File("/home/mdecorde/TEMP/ANTRACT/AF/emissions.xlsx");
     //		 columnsSelection = Arrays.asList(
     //		 "Identifiant de la notice", "Titre propre", "Notes du titre", "Date de diffusion", "Durée", "Nom fichier segmenté (info)", "antract_video",
     //		 "antract_debut","antract_fin","antract_duree","antract_tc_type","antract_tc_date");
     //		 lineRules.put("Type de notice", "Notice sommaire");
     //		 columnsToRenameRules.put("Identifiant de la notice", "id");
     //
     //		 columnsToCopy.put("Notes du titre", "subtitle"); // not working yet
     //		 columnsToCopy.put("Titre propre", "title"); // not working yet
     //		 columnsToCopy.put("Date de diffusion", "textorder"); // not working yet
     //		 searchAndReplaceRules.put("textorder", new String[] {"../../....", "$3$2$1"}); // not working yet
     		// table2File = new File("/home/mdecorde/TEMP/ANTRACT/AF/emissions.xlsx");
     		// columnsSelection = Arrays.asList(
     		// "Identifiant de la notice", "Titre propre", "Notes du titre", "Date de diffusion", "Durée", "Nom fichier segmenté (info)", "antract_video",
     		// "antract_debut","antract_fin","antract_duree","antract_tc_type","antract_tc_date");
     		// lineRules.put("Type de notice", "Notice sommaire");
     		// columnsToRenameRules.put("Identifiant de la notice", "id");
     		//
     		// columnsToCopy.put("Notes du titre", "subtitle"); // not working yet
     		// columnsToCopy.put("Titre propre", "title"); // not working yet
     		// columnsToCopy.put("Date de diffusion", "textorder"); // not working yet
     		// searchAndReplaceRules.put("textorder", new String[] {"../../....", "$3$2$1"}); // not working yet
     		// sujets
     		table2File = new File("/home/mdecorde/TEMP/ANTRACT/AF/sujets.xlsx");
-...
+    		}
     		System.out.println("copying column: " + columnsToCopy.size());
     		//excel2.copyColumns(columnsToCopy);
     		// excel2.copyColumns(columnsToCopy);
     		System.out.println("search&replace column: " + searchAndReplaceRules.size());
     		//excel2.searchAndReplaceInLines(searchAndReplaceRules);
     		// excel2.searchAndReplaceInLines(searchAndReplaceRules);
     		System.out.println("renaming column: " + columnsToRenameRules.size());
     		excel2.renameColumns(columnsToRenameRules);

     	return
+    }
     while (reader.readRecord()) {
     	if (reader.get("mesure").length() > 0 && reader.get("valeur").length() > 0 && reader.get("requête").length() > 0) {
     	test_queries << [
     		reader.get("mesure"),
     		reader.get("valeur"),
     		reader.get("requête")
+    	]
+    	}
+    }
     if (test_queries.size() == 0) {
-...
     	return null;
+    }
     ConsoleProgressBar cpb = new ConsoleProgressBar(selection.size())
     ConsoleProgressBar cpb = new ConsoleProgressBar(selection.size()*SVO_queries.size()*test_queries.size())
     println "Resolving ${test_queries.size()*SVO_queries.size()} queries for ${selection.size()} corpus."
     println "selection=$selection"
     println "test_queries=$test_queries"
     println "SVO_queries=$SVO_queries"
     TIGERSearchEngine tse = SearchEnginesManager.getTIGERSearchEngine()
     def results = new LinkedHashMap()
     for (def corpus : selection) {
     	cpb.tick()
     	writer.newTable(corpus.getName())
-...
     			if (debug > 0) println svo_query
     			cpb.tick()
     			def test_result = tcorpus.manager.processQuery(svo_query, based_sentences_min_max[0], based_sentences_min_max[1], 9999999);
     			if (print_queries) lineToWrite << svo_query
     			if (count_sub_matches) {

Formats disponibles : Unified diff

Laboratoire ICAR » Plateforme TXM

Révision 2930