cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/CdmUtilsBelen.java

   1 package eu.etaxonomy.cdm.common;
   2
   3 import java.util.ArrayList;
   4 import java.util.Arrays;
   5 import java.util.List;
   6
   7 public class CdmUtilsBelen {
   8
   9 //      Trim white spaces
  10
  11         public static String deleteEmptySpaces(String inputName) {
  12                 String outputName = inputName.replaceAll("\\s+", " ").trim();
  13                 return outputName;
  14         }
  15
  16 //      Replace characters with ASCII characters
  17
  18         public static String replaceSpecialCharacters(String str) {
  19                 String output;
  20                 output = str.replaceAll("[áåâãàä]", "a");
  21                 output = output.replaceAll("[éêèë]", "e");
  22                 output = output.replaceAll("[ôõøòóö]", "o");
  23                 output = output.replaceAll("[ìíîï]", "i");
  24                 output = output.replaceAll("[üûúù]", "u");
  25                 output = output.replaceAll("ñ", "n");
  26                 output = output.replaceAll("ç", "c");
  27                 return output;
  28         }
  29
  30 //      Change lists to lowercase
  31
  32         public static List <String> listToLowerCase(List<String> List) {
  33                 List <String> lowerCaseList = new ArrayList<>();
  34                 for (String x : List) {
  35                         lowerCaseList.add(x.toLowerCase());
  36                 }
  37                 return lowerCaseList ;
  38         }
  39
  40 // Replace characters combinations that sound similar
  41
  42         public static String soundalike(String inputName) {
  43                 String[][] soundalike = {
  44                                 {"ae","e"},
  45                                 {"ia","a"},
  46                                 {"oe", "i"},
  47                                 {"oi", "a"},
  48                                 {"sc", "s"}
  49                                 };
  50                 for (int i = 0 ; i<soundalike.length;i++) {
  51                         if (inputName.contains(soundalike[i][0])) {
  52                         inputName = inputName.replace(soundalike[i][0],soundalike[i][1]);
  53                         }
  54                 }
  55                 return inputName;
  56         }
  57
  58 //      Remove duplicated letters
  59
  60         public static String removeDuplicate(String input) {
  61                 char [] temp= input.toCharArray();
  62                 int lenght=temp.length;
  63
  64                 int index = 0;
  65                 int p;
  66                 for (int i = 0; i < lenght- 1; i++) {
  67                         p = i + 1;
  68                         if (!(temp[i] == temp[p])) {
  69                                 temp[index++] = temp[i];
  70                         }
  71                 }
  72                 String output = String.valueOf(Arrays.copyOf(temp, index));
  73                 output= output+ temp[lenght- 1];
  74                 return output;
  75         }
  76
  77 //      normalize ending ignoring gender issues
  78
  79         public static String replacerGenderEnding(String input) {
  80
  81                 String firstPart= input.substring(0, input.length() - 2);
  82                 String lastTwoChar = input.substring((input.length() - 2), input.length());
  83                 String[] endingChar = new String[] { "is", "us", "ys", "es", "im", "as", "um", "os" };
  84                 for (String i : endingChar) {
  85                         if (lastTwoChar.contains(i)) {
  86                                 lastTwoChar = lastTwoChar.replace(i, "a");
  87                         }
  88                 }
  89                 String output = firstPart + lastTwoChar;
  90                 return output;
  91         }
  92 }