edu.berkeley.cs.jqf.examples.algs4.BoyerMoore Maven / Gradle / Ivy
package edu.berkeley.cs.jqf.examples.algs4;
/**
* The {@code BoyerMoore} class finds the first occurrence of a pattern string
* in a text string.
*
* This implementation uses the Boyer-Moore algorithm (with the bad-character
* rule, but not the strong good suffix rule).
*
* For additional documentation,
* see Section 5.3 of
* Algorithms, 4th Edition by Robert Sedgewick and Kevin Wayne.
*
* Source: http://algs4.cs.princeton.edu/53substring/BoyerMoore.java
*/
public class BoyerMoore {
private final int R; // the radix
private int[] right; // the bad-character skip array
private char[] pattern; // store the pattern as a character array
private String pat; // or as a string
/**
* Preprocesses the pattern string.
*
* @param pat the pattern string
*/
public BoyerMoore(String pat) {
this.R = 256;
this.pat = pat;
// position of rightmost occurrence of c in the pattern
right = new int[R];
for (int c = 0; c < R; c++)
right[c] = -1;
for (int j = 0; j < pat.length(); j++)
right[pat.charAt(j)] = j;
}
/**
* Preprocesses the pattern string.
*
* @param pattern the pattern string
* @param R the alphabet size
*/
public BoyerMoore(char[] pattern, int R) {
this.R = R;
this.pattern = new char[pattern.length];
for (int j = 0; j < pattern.length; j++)
this.pattern[j] = pattern[j];
// position of rightmost occurrence of c in the pattern
right = new int[R];
for (int c = 0; c < R; c++)
right[c] = -1;
for (int j = 0; j < pattern.length; j++)
right[pattern[j]] = j;
}
/**
* Returns the index of the first occurrrence of the pattern string
* in the text string.
*
* @param txt the text string
* @return the index of the first occurrence of the pattern string
* in the text string; n if no such match
*/
public int search(String txt) {
int m = pat.length();
int n = txt.length();
int skip;
for (int i = 0; i <= n - m; i += skip) {
skip = 0;
for (int j = m-1; j >= 0; j--) {
if (pat.charAt(j) != txt.charAt(i+j)) {
skip = Math.max(1, j - right[txt.charAt(i+j)]);
break;
}
}
if (skip == 0) return i; // found
}
return n; // not found
}
/**
* Returns the index of the first occurrrence of the pattern string
* in the text string.
*
* @param text the text string
* @return the index of the first occurrence of the pattern string
* in the text string; n if no such match
*/
public int search(char[] text) {
int m = pattern.length;
int n = text.length;
int skip;
for (int i = 0; i <= n - m; i += skip) {
skip = 0;
for (int j = m-1; j >= 0; j--) {
if (pattern[j] != text[i+j]) {
skip = Math.max(1, j - right[text[i+j]]);
break;
}
}
if (skip == 0) return i; // found
}
return n; // not found
}
}