Skip to content

refactor: redesign StringMatchFiniteAutomata #5222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -1,80 +1,118 @@
package com.thealgorithms.others;

/**
* @author Prateek Kumar Oraon (https://github.com/prateekKrOraon)
*/
import java.util.Scanner;
import java.util.Set;
import java.util.TreeSet;

// An implementation of string matching using finite automata
/**
* A class to perform string matching using <a href="https://en.wikipedia.org/wiki/Finite-state_machine">finite automata</a>.
*
* @author <a href="https://github.com/prateekKrOraon">Prateek Kumar Oraon</a>
*/
public final class StringMatchFiniteAutomata {

// Constants
private static final int CHARS = 256; // Total number of characters in the input alphabet

// Finite automata table
private static int[][] finiteAutomata;

// Private constructor to prevent instantiation
private StringMatchFiniteAutomata() {
}

public static final int CHARS = 256;
public static int[][] fa;
public static Scanner scanner = null;

public static void main(String[] args) {
scanner = new Scanner(System.in);
System.out.println("Enter String");
String text = scanner.nextLine();
System.out.println("Enter pattern");
String pat = scanner.nextLine();
// Scanner instance for user input
try (Scanner scanner = new Scanner(System.in);) {

System.out.println("Enter text:");
String text = scanner.nextLine();

searchPat(text, pat);
System.out.println("Enter pattern:");
String pattern = scanner.nextLine();

scanner.close();
Set<Integer> indexFound = searchPattern(text, pattern);
indexFound.forEach(System.out::println);
}
}

public static void searchPat(String text, String pat) {
int m = pat.length();
int n = text.length();
/**
* Searches for the pattern in the given text using finite automata.
*
* @param text The text to search within.
* @param pattern The pattern to search for.
*/
public static Set<Integer> searchPattern(String text, String pattern) {
Set<Integer> indexFound = new TreeSet<>();
int patternLength = pattern.length();
int textLength = text.length();

// Initialize finite automata table
finiteAutomata = new int[patternLength + 1][CHARS];

fa = new int[m + 1][CHARS];
// Preprocess the pattern to create the finite automata table
computeFiniteAutomata(pattern, patternLength);

computeFA(pat, m, fa);
int state = 0; // Initial state

int state = 0;
for (int i = 0; i < n; i++) {
state = fa[state][text.charAt(i)];
// Process the text over the finite automata
for (int i = 0; i < textLength; i++) {
state = finiteAutomata[state][text.charAt(i)];

if (state == m) {
System.out.println("Pattern found at index " + (i - m + 1));
if (state == patternLength) {
indexFound.add(i - patternLength + 1);
}
}
return indexFound;
}

// Computes finite automata for the pattern
public static void computeFA(String pat, int m, int[][] fa) {
for (int state = 0; state <= m; ++state) {
/**
* Computes the finite automata table for the given pattern.
*
* @param pattern The pattern to preprocess.
* @param patternLength The length of the pattern.
*/
private static void computeFiniteAutomata(String pattern, int patternLength) {
for (int state = 0; state <= patternLength; ++state) {
for (int x = 0; x < CHARS; ++x) {
fa[state][x] = getNextState(pat, m, state, x);
finiteAutomata[state][x] = getNextState(pattern, patternLength, state, x);
}
}
}

public static int getNextState(String pat, int m, int state, int x) {
// if current state is less than length of pattern
// and input character of pattern matches the character in the alphabet
// then automata goes to next state
if (state < m && x == pat.charAt(state)) {
/**
* Gets the next state for the finite automata.
*
* @param pattern The pattern being matched.
* @param patternLength The length of the pattern.
* @param state The current state.
* @param x The current character from the input alphabet.
* @return The next state.
*/
private static int getNextState(String pattern, int patternLength, int state, int x) {
// If the current state is less than the length of the pattern
// and the character matches the pattern character, go to the next state
if (state < patternLength && x == pattern.charAt(state)) {
return state + 1;
}

// Check for the highest prefix which is also a suffix
for (int ns = state; ns > 0; ns--) {
if (pat.charAt(ns - 1) == x) {
if (pattern.charAt(ns - 1) == x) {
boolean match = true;
for (int i = 0; i < ns - 1; i++) {
if (pat.charAt(i) != pat.charAt(state - ns + i + 1)) {
if (pattern.charAt(i) != pattern.charAt(state - ns + i + 1)) {
match = false;
break;
}

if (i == ns - 1) {
return ns;
}
}
if (match) {
return ns;
}
}
}

// If no prefix which is also a suffix is found, return 0
return 0;
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
package com.thealgorithms.others;

import static org.junit.jupiter.api.Assertions.assertEquals;

import java.util.Set;
import java.util.stream.Stream;
import org.junit.jupiter.params.ParameterizedTest;
import org.junit.jupiter.params.provider.Arguments;
import org.junit.jupiter.params.provider.MethodSource;

class StringMatchFiniteAutomataTest {

@ParameterizedTest
@MethodSource("provideTestCases")
void searchPattern(String text, String pattern, Set<Integer> expectedOutput) {
assertEquals(expectedOutput, StringMatchFiniteAutomata.searchPattern(text, pattern));
}

private static Stream<Arguments> provideTestCases() {
return Stream.of(Arguments.of("abcbcabc", "abc", Set.of(0, 5)), //
Arguments.of("", "abc", Set.of()), //
Arguments.of("abcdefg", "xyz", Set.of()), //
Arguments.of("abcde", "", Set.of(1, 2, 3, 4, 5)), //
Arguments.of("abcabcabc", "abc", Set.of(0, 3, 6)), //
Arguments.of("abcabcabc", "abcabcabc", Set.of(0)), //
Arguments.of("aaabbbaaa", "aaa", Set.of(0, 6)), //
Arguments.of("abcdefg", "efg", Set.of(4)) //
);
}
}