Project

General

Profile

« Previous | Next » 

Revision e082affd

Added by Andreas Kohlbecker over 7 years ago

fix #6035 character replacement rules

View differences:

app-import/src/main/java/eu/etaxonomy/cdm/app/iapt/IAPTActivator.java
37 37 

  		




  38
  38
  
    
    public static final String DATA_FILE_0_100 = "fileURI-100.xls";


  		




  39
  39
  
    
    public static final String DATA_FILE_FULL = "Registration_DB_from_BGBM17.xls";


  		




  40
  
  
    
    public static final String DATA_FILE = DATA_FILE_0_100;


  		




  
  40
  
    
    public static final String DATA_ENCODING_PROBLEMS = "encoding-problems.xls";


  		




  
  41
  
    
    public static final String DATA_FILE = DATA_ENCODING_PROBLEMS;


  		




  41
  42
  
    

  		




  42
  43
  
    
    //database validation status (create, update, validate ...)


  		




  43
  44
  
    
    static DbSchemaValidation hbm2dll = DbSchemaValidation.CREATE;


  		












  

    
      app-import/src/main/java/eu/etaxonomy/cdm/io/iapt/IAPTExcelImport.java
    
  





  388
  388
  
    
     */


  		




  389
  389
  
    
    private String getValue(HashMap<String, String> record, String originalKey, boolean doUnescapeHtmlEntities) {


  		




  390
  390
  
    
        String value = record.get(originalKey);


  		




  
  391
  
    

  		




  
  392
  
    
        value = fixCharacters(value);


  		




  
  393
  
    

  		




  391
  394
  
    
        if (! StringUtils.isBlank(value)) {


  		




  392
  395
  
    
        	if (logger.isDebugEnabled()) {


  		




  393
  396
  
    
        	    logger.debug(originalKey + ": " + value);


  		




  ......




  402
  405
  
    
        }


  		




  403
  406
  
    
    }


  		




  404
  407
  
    

  		




  
  408
  
    
    /**


  		




  
  409
  
    
     * Fixes broken characters.


  		




  
  410
  
    
     * For details see


  		




  
  411
  
    
     * http://dev.e-taxonomy.eu/redmine/issues/6035


  		




  
  412
  
    
     *


  		




  
  413
  
    
     * @param value


  		




  
  414
  
    
     * @return


  		




  
  415
  
    
     */


  		




  
  416
  
    
    private String fixCharacters(String value) {


  		




  
  417
  
    

  		




  
  418
  
    
        value = StringUtils.replace(value, "s$K", "š");


  		




  
  419
  
    
        value = StringUtils.replace(value, "n$K", "ň");


  		




  
  420
  
    
        value = StringUtils.replace(value, "e$K", "ě");


  		




  
  421
  
    
        value = StringUtils.replace(value, "r$K", "ř");


  		




  
  422
  
    
        value = StringUtils.replace(value, "c$K", "č");


  		




  
  423
  
    
        value = StringUtils.replace(value, "z$K", "ž");


  		




  
  424
  
    
        value = StringUtils.replace(value, "S>U$K", "Š");


  		




  
  425
  
    
        value = StringUtils.replace(value, "C>U$K", "Č");


  		




  
  426
  
    
        value = StringUtils.replace(value, "R>U$K", "Ř");


  		




  
  427
  
    
        value = StringUtils.replace(value, "Z>U$K", "Ž");


  		




  
  428
  
    
        value = StringUtils.replace(value, "g$K", "ǧ");


  		




  
  429
  
    
        value = StringUtils.replace(value, "s$A", "ś");


  		




  
  430
  
    
        value = StringUtils.replace(value, "n$A", "ń");


  		




  
  431
  
    
        value = StringUtils.replace(value, "c$A", "ć");


  		




  
  432
  
    
        value = StringUtils.replace(value, "e$E", "ę");


  		




  
  433
  
    
        value = StringUtils.replace(value, "o$H", "õ");


  		




  
  434
  
    
        value = StringUtils.replace(value, "s$C", "ş");


  		




  
  435
  
    
        value = StringUtils.replace(value, "t$C", "ț");


  		




  
  436
  
    
        value = StringUtils.replace(value, "S>U$C", "Ş");


  		




  
  437
  
    
        value = StringUtils.replace(value, "a$O", "å");


  		




  
  438
  
    
        value = StringUtils.replace(value, "A>U$O", "Å");


  		




  
  439
  
    
        value = StringUtils.replace(value, "u$O", "ů");


  		




  
  440
  
    
        value = StringUtils.replace(value, "g$B", "ğ");


  		




  
  441
  
    
        value = StringUtils.replace(value, "g$B", "ĕ");


  		




  
  442
  
    
        value = StringUtils.replace(value, "a$B", "ă");


  		




  
  443
  
    
        value = StringUtils.replace(value, "l$/", "ł");


  		




  
  444
  
    
        value = StringUtils.replace(value, ">i", "ı");


  		




  
  445
  
    
        value = StringUtils.replace(value, "i$U", "ï");


  		




  
  446
  
    
        // Special-cases


  		




  
  447
  
    
        value = StringUtils.replace(value, "&yacute", "ý");


  		




  
  448
  
    
        value = StringUtils.replace(value, "<L", "Ł");


  		




  
  449
  
    
        value = StringUtils.replace(value, "E>U$D", "З");


  		




  
  450
  
    
        value = StringUtils.replace(value, "S>U$E", "Ş");


  		




  
  451
  
    
        value = StringUtils.replace(value, "s$E", "ş");


  		




  
  452
  
    

  		




  
  453
  
    
        return value;


  		




  
  454
  
    
    }


  		




  405
  455
  
    

  		




  406
  456
  
    

  		




  407
  
  
    
	/**


  		




  
  457
  
    
    /**


  		




  408
  458
  
    
	 *  Stores taxa records in DB


  		




  409
  459
  
    
	 */


  		




  410
  460
  
    
	@Override


  		












Also available in:  Unified diff