Обычный способ вычисления сходства между двумя строками в режиме 0% -100% , используемый во многих библиотеках, состоит в измерении того, сколько (в%) вам потребуется изменить длинная строка, чтобы превратить ее в более короткую:
/**
* Calculates the similarity (a number within 0 and 1) between two strings.
*/
public static double similarity(String s1, String s2) {
String longer = s1, shorter = s2;
if (s1.length() < s2.length()) { // longer should always have greater length
longer = s2; shorter = s1;
}
int longerLength = longer.length();
if (longerLength == 0) { return 1.0; /* both strings are zero length */ }
return (longerLength - editDistance(longer, shorter)) / (double) longerLength;
}
// you can use StringUtils.getLevenshteinDistance() as the editDistance() function
// full copy-paste working code is below
Вычисление editDistance():
Приведенная выше функция editDistance() рассчитывает расстояние редактирования между двумя строками. Для этого шага существует несколько реализаций , каждая из которых может лучше соответствовать определенному сценарию. Наиболее распространенным является алгоритм расстояния Левенштейна , и мы будем использовать его в нашем примере ниже (для очень больших строк другие алгоритмы, вероятно, будут работать лучше) .
Вот два варианта вычисления расстояния редактирования:
Рабочий пример:
См. Демо-версию здесь.
public class StringSimilarity {
/**
* Calculates the similarity (a number within 0 and 1) between two strings.
*/
public static double similarity(String s1, String s2) {
String longer = s1, shorter = s2;
if (s1.length() < s2.length()) { // longer should always have greater length
longer = s2; shorter = s1;
}
int longerLength = longer.length();
if (longerLength == 0) { return 1.0; /* both strings are zero length */ }
/* // If you have Apache Commons Text, you can use it to calculate the edit distance:
LevenshteinDistance levenshteinDistance = new LevenshteinDistance();
return (longerLength - levenshteinDistance.apply(longer, shorter)) / (double) longerLength; */
return (longerLength - editDistance(longer, shorter)) / (double) longerLength;
}
// Example implementation of the Levenshtein Edit Distance
// See http://rosettacode.org/wiki/Levenshtein_distance#Java
public static int editDistance(String s1, String s2) {
s1 = s1.toLowerCase();
s2 = s2.toLowerCase();
int[] costs = new int[s2.length() + 1];
for (int i = 0; i <= s1.length(); i++) {
int lastValue = i;
for (int j = 0; j <= s2.length(); j++) {
if (i == 0)
costs[j] = j;
else {
if (j > 0) {
int newValue = costs[j - 1];
if (s1.charAt(i - 1) != s2.charAt(j - 1))
newValue = Math.min(Math.min(newValue, lastValue),
costs[j]) + 1;
costs[j - 1] = lastValue;
lastValue = newValue;
}
}
}
if (i > 0)
costs[s2.length()] = lastValue;
}
return costs[s2.length()];
}
public static void printSimilarity(String s, String t) {
System.out.println(String.format(
"%.3f is the similarity between \"%s\" and \"%s\"", similarity(s, t), s, t));
}
public static void main(String[] args) {
printSimilarity("", "");
printSimilarity("1234567890", "1");
printSimilarity("1234567890", "123");
printSimilarity("1234567890", "1234567");
printSimilarity("1234567890", "1234567890");
printSimilarity("1234567890", "1234567980");
printSimilarity("47/2010", "472010");
printSimilarity("47/2010", "472011");
printSimilarity("47/2010", "AB.CDEF");
printSimilarity("47/2010", "4B.CDEFG");
printSimilarity("47/2010", "AB.CDEFG");
printSimilarity("The quick fox jumped", "The fox jumped");
printSimilarity("The quick fox jumped", "The fox");
printSimilarity("kitten", "sitting");
}
}
Выход:
1.000 is the similarity between "" and ""
0.100 is the similarity between "1234567890" and "1"
0.300 is the similarity between "1234567890" and "123"
0.700 is the similarity between "1234567890" and "1234567"
1.000 is the similarity between "1234567890" and "1234567890"
0.800 is the similarity between "1234567890" and "1234567980"
0.857 is the similarity between "47/2010" and "472010"
0.714 is the similarity between "47/2010" and "472011"
0.000 is the similarity between "47/2010" and "AB.CDEF"
0.125 is the similarity between "47/2010" and "4B.CDEFG"
0.000 is the similarity between "47/2010" and "AB.CDEFG"
0.700 is the similarity between "The quick fox jumped" and "The fox jumped"
0.350 is the similarity between "The quick fox jumped" and "The fox"
0.571 is the similarity between "kitten" and "sitting"