Knuth Morris Pratt Pattern Matching in Java

// Knuth Morris Pratt Pattern Matching in Java
//
// PURPOSE
// KMP avoids rechecking text tokens by remembering which matched pattern suffix is also a
// prefix. The prefix table tells where to resume after a mismatch.
//
// METHOD
// Build the longest proper prefix/suffix table for the pattern. During matching, fall back
// through that table without moving the text position backward. A full matched prefix gives
// the first occurrence.
//
// COMPLEXITY
// O(n+m) time and O(m) auxiliary space.
//
// CONTRACT
// Inputs are integer token sequences. Empty pattern matches at 0. Returns first matching
// index or -1. KMP does not define Unicode tokenization.
// Public APIs infer array lengths except in C, which accepts pointer/length pairs. Vertex
// counts and matrix dimensions remain explicit. Arrays must contain signed 32-bit integers.
// Sorted order, correct tree topology, and caller-owned data-structure invariants are
// preconditions; checking them on every query would change query complexity.
// Scalar and shape checks are included. Value-range checks are included where needed to
// prevent invalid indexing or nontermination. Allocation sizes are capped at 4,000,000
// workspace entries. Arithmetic outside Python raises an error on 32-bit overflow; Python
// uses arbitrary precision. Native allocation failures propagate. In-place outputs may be
// partly updated after arithmetic failure. These are single-threaded, in-memory
// implementations.
//
// LANGUAGE DETAILS
// Java 17+: primitive int arrays, Arrays.binarySearch for LIS, and Math exact arithmetic.
// Invalid input throws IllegalArgumentException; arithmetic overflow throws
// ArithmeticException.
//
// EXAMPLE
// Expected return: 2.
// Run: javac AlgorithmExample.java && java AlgorithmExample
// Tests for this exact source artifact run before publication. The accompanying source
// archive includes unit cases, runtime results, and source hashes.

class AlgorithmExample {
    static void alg_require(boolean valid) { if (!valid) throw new IllegalArgumentException("invalid algorithm input"); }
    static int alg_size(int n) { alg_require(n>=0 && n<=4000000); return n; }

    static int kmp_match(int[] text, int[] pattern) {
        java.util.Objects.requireNonNull(text, "text");
        java.util.Objects.requireNonNull(pattern, "pattern");
        int n = text.length;
        int m = pattern.length;
        alg_require(((n >= 0) && (n <= 1000000)));
        alg_require(((m >= 0) && (m <= 1000000)));
        alg_require((pattern.length == m));
        alg_require((text.length == n));
        if ((m == 0)) {
            return 0;
        }
        int[] prefix = new int[alg_size(Math.addExact(m, 1))];
        int i = 1;
        int j = 0;
        while ((i < m)) {
            while (((j > 0) && (pattern[i] != pattern[j]))) {
                j = prefix[Math.subtractExact(j, 1)];
            }
            if ((pattern[i] == pattern[j])) {
                j = Math.addExact(j, 1);
            }
            prefix[i] = j;
            i = Math.addExact(i, 1);
        }
        i = 0;
        j = 0;
        while ((i < n)) {
            while (((j > 0) && (text[i] != pattern[j]))) {
                j = prefix[Math.subtractExact(j, 1)];
            }
            if ((text[i] == pattern[j])) {
                j = Math.addExact(j, 1);
            }
            if ((j == m)) {
                return Math.addExact(Math.subtractExact(i, m), 1);
            }
            i = Math.addExact(i, 1);
        }
        return Math.negateExact(1);
    }

    public static void main(String[] args) {
        int[] text = new int[] {1, 2, 1, 2, 3};
        int[] pattern = new int[] {1, 2, 3};
        int result = kmp_match(text, pattern);
        System.out.println(result);
    }
}