Data commit

This commit is contained in:
Ingy döt Net 2023-07-01 11:58:00 -04:00
parent 7387c8f97b
commit cb5bb5e222
199093 changed files with 3378972 additions and 0 deletions

View file

@ -0,0 +1,28 @@
public class Levenshtein {
public static int distance(String a, String b) {
a = a.toLowerCase();
b = b.toLowerCase();
// i == 0
int [] costs = new int [b.length() + 1];
for (int j = 0; j < costs.length; j++)
costs[j] = j;
for (int i = 1; i <= a.length(); i++) {
// j == 0; nw = lev(i - 1, j)
costs[0] = i;
int nw = i - 1;
for (int j = 1; j <= b.length(); j++) {
int cj = Math.min(1 + Math.min(costs[j], costs[j - 1]), a.charAt(i - 1) == b.charAt(j - 1) ? nw : nw + 1);
nw = costs[j];
costs[j] = cj;
}
}
return costs[b.length()];
}
public static void main(String [] args) {
String [] data = { "kitten", "sitting", "saturday", "sunday", "rosettacode", "raisethysword" };
for (int i = 0; i < data.length; i += 2)
System.out.println("distance(" + data[i] + ", " + data[i+1] + ") = " + distance(data[i], data[i+1]));
}
}

View file

@ -0,0 +1,46 @@
public class Levenshtein{
public static int levenshtein(String s, String t){
/* if either string is empty, difference is inserting all chars
* from the other
*/
if(s.length() == 0) return t.length();
if(t.length() == 0) return s.length();
/* if first letters are the same, the difference is whatever is
* required to edit the rest of the strings
*/
if(s.charAt(0) == t.charAt(0))
return levenshtein(s.substring(1), t.substring(1));
/* else try:
* changing first letter of s to that of t,
* remove first letter of s, or
* remove first letter of t
*/
int a = levenshtein(s.substring(1), t.substring(1));
int b = levenshtein(s, t.substring(1));
int c = levenshtein(s.substring(1), t);
if(a > b) a = b;
if(a > c) a = c;
//any of which is 1 edit plus editing the rest of the strings
return a + 1;
}
public static void main(String[] args) {
String s1 = "kitten";
String s2 = "sitting";
System.out.println("distance between '" + s1 + "' and '"
+ s2 + "': " + levenshtein(s1, s2));
s1 = "rosettacode";
s2 = "raisethysword";
System.out.println("distance between '" + s1 + "' and '"
+ s2 + "': " + levenshtein(s1, s2));
StringBuilder sb1 = new StringBuilder(s1);
StringBuilder sb2 = new StringBuilder(s2);
System.out.println("distance between '" + sb1.reverse() + "' and '"
+ sb2.reverse() + "': "
+ levenshtein(sb1.reverse().toString(), sb2.reverse().toString()));
}
}

View file

@ -0,0 +1,73 @@
import static java.lang.Math.abs;
import static java.lang.Math.max;
public class Levenshtein {
public static int ld(String a, String b) {
return distance(a, b, -1);
}
public static boolean ld(String a, String b, int max) {
return distance(a, b, max) <= max;
}
private static int distance(String a, String b, int max) {
if (a == b) return 0;
int la = a.length();
int lb = b.length();
if (max >= 0 && abs(la - lb) > max) return max+1;
if (la == 0) return lb;
if (lb == 0) return la;
if (la < lb) {
int tl = la; la = lb; lb = tl;
String ts = a; a = b; b = ts;
}
int[] cost = new int[lb+1];
for (int i=0; i<=lb; i+=1) {
cost[i] = i;
}
for (int i=1; i<=la; i+=1) {
cost[0] = i;
int prv = i-1;
int min = prv;
for (int j=1; j<=lb; j+=1) {
int act = prv + (a.charAt(i-1) == b.charAt(j-1) ? 0 : 1);
cost[j] = min(1+(prv=cost[j]), 1+cost[j-1], act);
if (prv < min) min = prv;
}
if (max >= 0 && min > max) return max+1;
}
if (max >= 0 && cost[lb] > max) return max+1;
return cost[lb];
}
private static int min(int ... a) {
int min = Integer.MAX_VALUE;
for (int i: a) if (i<min) min = i;
return min;
}
public static void main(String[] args) {
System.out.println(
ld("kitten","kitten") + " " + // 0
ld("kitten","sitten") + " " + // 1
ld("kitten","sittes") + " " + // 2
ld("kitten","sityteng") + " " + // 3
ld("kitten","sittYing") + " " + // 4
ld("rosettacode","raisethysword") + " " + // 8
ld("kitten","kittenaaaaaaaaaaaaaaaaa") + " " + // 17
ld("kittenaaaaaaaaaaaaaaaaa","kitten") // 17
);
System.out.println(
ld("kitten","kitten", 3) + " " + // true
ld("kitten","sitten", 3) + " " + // true
ld("kitten","sittes", 3) + " " + // true
ld("kitten","sityteng", 3) + " " + // true
ld("kitten","sittYing", 3) + " " + // false
ld("rosettacode","raisethysword", 3) + " " + // false
ld("kitten","kittenaaaaaaaaaaaaaaaaa", 3) + " " + // false
ld("kittenaaaaaaaaaaaaaaaaa","kitten", 3) // false
);
}
}