package edu.princeton.cs.algs4.ch55;
import edu.princeton.cs.introcs.*;
/***************************************************************
*
* Compilation: javac KMP.java
* Execution: java KMP pattern text
*
* Reads in two strings, the pattern and the input text, and
* searches for the pattern in the input text using the
* KMP algorithm.
*
* % java KMP abracadabra abacadabrabracabracadabrabrabracad
* text: abacadabrabracabracadabrabrabracad
* pattern: abracadabra
*
* % java KMP rab abacadabrabracabracadabrabrabracad
* text: abacadabrabracabracadabrabrabracad
* pattern: rab
*
* % java KMP bcara abacadabrabracabracadabrabrabracad
* text: abacadabrabracabracadabrabrabracad
* pattern: bcara
*
* % java KMP rabrabracad abacadabrabracabracadabrabrabracad
* text: abacadabrabracabracadabrabrabracad
* pattern: rabrabracad
*
* % java KMP abacad abacadabrabracabracadabrabrabracad
* text: abacadabrabracabracadabrabrabracad
* pattern: abacad
*
***************************************************************/
public class KMP {
private final int R; // the radix
private int[][] dfa; // the KMP automoton
private char[] pattern; // either the character array for the pattern
private String pat; // or the pattern string
// create the DFA from a String
public KMP(String pat) {
this.R = 256;
this.pat = pat;
// build DFA from pattern
int M = pat.length();
dfa = new int[R][M];
dfa[pat.charAt(0)][0] = 1;
for (int X = 0, j = 1; j < M; j++) {
for (int c = 0; c < R; c++)
dfa[c][j] = dfa[c][X]; // Copy mismatch cases.
dfa[pat.charAt(j)][j] = j+1; // Set match case.
X = dfa[pat.charAt(j)][X]; // Update restart state.
}
}
// create the DFA from a character array over R-character alphabet
public KMP(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];
// build DFA from pattern
int M = pattern.length;
dfa = new int[R][M];
dfa[pattern[0]][0] = 1;
for (int X = 0, j = 1; j < M; j++) {
for (int c = 0; c < R; c++)
dfa[c][j] = dfa[c][X]; // Copy mismatch cases.
dfa[pattern[j]][j] = j+1; // Set match case.
X = dfa[pattern[j]][X]; // Update restart state.
}
}
// return offset of first match; N if no match
public int search(String txt) {
// simulate operation of DFA on text
int M = pat.length();
int N = txt.length();
int i, j;
for (i = 0, j = 0; i < N && j < M; i++) {
j = dfa[txt.charAt(i)][j];
}
if (j == M) return i - M; // found
return N; // not found
}
// return offset of first match; N if no match
public int search(char[] text) {
// simulate operation of DFA on text
int M = pattern.length;
int N = text.length;
int i, j;
for (i = 0, j = 0; i < N && j < M; i++) {
j = dfa[text[i]][j];
}
if (j == M) return i - M; // found
return N; // not found
}
// test client
public static void main(String[] args) {
String pat = args[0];
String txt = args[1];
char[] pattern = pat.toCharArray();
char[] text = txt.toCharArray();
KMP kmp1 = new KMP(pat);
int offset1 = kmp1.search(txt);
KMP kmp2 = new KMP(pattern, 256);
int offset2 = kmp2.search(text);
// print results
StdOut.println("text: " + txt);
StdOut.print("pattern: ");
for (int i = 0; i < offset1; i++)
StdOut.print(" ");
StdOut.println(pat);
StdOut.print("pattern: ");
for (int i = 0; i < offset2; i++)
StdOut.print(" ");
StdOut.println(pat);
}
}
/*************************************************************************
* Copyright 2002-2012, Robert Sedgewick and Kevin Wayne.
*
* This file is part of algs4-package.jar, which accompanies the textbook
*
* Algorithms, 4th edition by Robert Sedgewick and Kevin Wayne,
* Addison-Wesley Professional, 2011, ISBN 0-321-57351-X.
* http://algs4.cs.princeton.edu
*
*
* algs4-package.jar is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* algs4-package.jar is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
* You should have received a copy of the GNU General Public License
* along with algs4-package.jar. If not, see http://www.gnu.org/licenses.
*************************************************************************/