/* redos_atomic - demonstrates atomic groups (?>...) as a defense against
 * catastrophic backtracking (ReDoS), on the textbook (a+)+b shape, and
 * shows precisely when that defense is still needed versus when it no
 * longer is.
 *
 * (a+)+b by itself is no longer a useful demonstration of the problem:
 * it has no backreference, lookahead, lookbehind, or atomic group, so it
 * is eligible for and automatically matched by the Pike VM (concept.md
 * 7.2/7.7), which runs it in genuinely linear time, not merely improved
 * time, with no atomic group needed at all (README.md "The Pike VM").
 * The backtracking engine's own remaining ceiling for this exact shape
 * (empirically quadratic, not exponential, because the inner a+'s
 * OP_REPEAT1 is followed by the group's closing save rather than a
 * simple atom, so the skip-ahead table that makes a*b linear does not
 * apply to it) is real and still documented in README.md "Implementation
 * status", but only actually applies to a pattern that keeps a
 * construct forcing it onto that engine. This program shows both halves
 * directly: first, that the plain (a+)+b form is now fast on its own,
 * with no atomic group; second, a variant with a trailing backreference
 * added specifically to keep it on the backtracking engine, where the
 * same nested-quantifier ambiguity is still exponential (memoization is
 * unsound in the presence of a backreference and is disabled whenever
 * one is present anywhere in the pattern, README.md "Implementation
 * status"), and where the atomic group fix from this file's original
 * version still matters exactly as much as it always did.
 */
#define _POSIX_C_SOURCE 199309L
#include "regexx.h"
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <time.h>

static double now_seconds(void) {
    struct timespec ts;
    clock_gettime(CLOCK_MONOTONIC, &ts);
    return (double)ts.tv_sec + (double)ts.tv_nsec / 1e9;
}

static void run_case(const char *label, const char *pattern, const char *subject, size_t subjlen) {
    PatternError err; memset(&err, 0, sizeof err);
    Pattern *pat = re_compile(pattern, strlen(pattern), ASCII, &err);
    if (!pat) {
        fprintf(stderr, "compile error for %s: %s\n", pattern, err.msg);
        PatternError_free(&err);
        return;
    }
    Input *in = Input_from_buffer((const uint8_t *)subject, subjlen);
    Match m; memset(&m, 0, sizeof m);
    double t0 = now_seconds();
    int rc = Pattern_search(pat, in, 0, -1, &m);
    double t1 = now_seconds();
    printf("%-28s pattern=%-18s n=%-8zu rc=%-2d time=%.4fs\n",
           label, pattern, subjlen, rc, t1 - t0);
    if (rc == 1) Match_free(&m);
    Input_free(in);
    Pattern_free(pat);
}

int main(void) {
    printf("=== Part 1: (a+)+b, backreference-free, now Pike VM eligible ===\n\n");
    {
        size_t n = 20000;
        char *subject = malloc(n + 1);
        memset(subject, 'a', n);
        subject[n] = '\0';
        printf("Searching %zu characters of 'a' with no trailing 'b' (never matches):\n\n", n);
        run_case("plain nested quantifier", "(a+)+b", subject, n);
        run_case("atomic inner group",      "(?>a+)+b", subject, n);
        run_case("possessive inner quant.", "(a++)+b", subject, n);
        printf("\nAll three finish in comparable, close-to-instant time: the plain form\n"
               "is no longer the slow one. It has no backreference, lookahead,\n"
               "lookbehind, or atomic group, so it runs on the Pike VM (README.md\n"
               "\"The Pike VM\"), which holds a bounded set of live parse states\n"
               "instead of backtracking, and is linear in n regardless of this\n"
               "pattern's nested-quantifier shape. The atomic and possessive forms\n"
               "were not what fixed this; the engine dispatch did.\n\n");
        free(subject);
    }

    printf("=== Part 2: the same shape, forced onto the backtracking engine ===\n\n");
    {
        /* \2 (a backreference to the literal "b") is enough to make this
         * pattern ineligible for the Pike VM (no backreference can ever
         * be, README.md "Implementation status"), which is the only
         * change from Part 1 that matters here: it puts the same
         * (a+)+-shaped ambiguity back onto the engine that still pays
         * for it. n is deliberately tiny (not the 20000 above): a
         * backreference disables memoization entirely (it is unsound
         * whenever one is present anywhere in the pattern, not only
         * where it appears), so this shape is exponential here, not
         * merely quadratic, and n = 24 already takes most of a second. */
        size_t n = 24;
        char *subject = malloc(n + 1);
        memset(subject, 'a', n);
        subject[n] = '\0';
        printf("Searching %zu characters of 'a' with no trailing \"bb\" (never matches):\n\n", n);
        run_case("plain, backreference",  "(a+)+(b)\\2", subject, n);
        run_case("atomic, backreference", "(?>(a+))+(b)\\2", subject, n);
        printf("\nThe plain form is slow again (exponential, not merely quadratic,\n"
               "since the backreference disables memoization outright), and the\n"
               "atomic group fixes it again, exactly as it always did: wrapping the\n"
               "capturing group itself, (?>(a+))+, keeps group 1 capturing (unlike\n"
               "(?>a+)+, which would make the inner run non-capturing) while still\n"
               "forbidding the atomic sub-program from ever giving back characters\n"
               "it already consumed to try a shorter run instead. This is the\n"
               "pattern author's own tool for the minority of patterns that still\n"
               "need it, not something the engine can fix automatically the way it\n"
               "now does for Part 1's plain, backreference-free shape.\n");
        free(subject);
    }

    return 0;
}