/* v0.4 smoke test publisher — NV12 1920x1080 ring 4, fill каждый slot
 * с pattern (i % 256), publish, infinite loop. */
#include <cuframes/cuframes.h>
#include <cuda_runtime.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <unistd.h>

int main(int argc, char **argv) {
    const char *key = argc > 1 ? argv[1] : "smoke";

    cuframes_publisher_config_t cfg = {0};
    cfg.key = key;
    cfg.width = 1920;
    cfg.height = 1080;
    cfg.format = CUFRAMES_FORMAT_NV12;
    cfg.ownership = CUFRAMES_OWNERSHIP_LIBRARY;
    cfg.ring_size = 4;
    cfg.policy = CUFRAMES_POLICY_DROP_OLDEST;
    cfg.cuda_device = 0;

    cuframes_publisher_t *pub = NULL;
    int r = cuframes_publisher_create(&cfg, &pub);
    if (r != CUFRAMES_OK) {
        fprintf(stderr, "publisher create failed: %d (%s)\n", r, cuframes_strerror(r));
        return 1;
    }
    fprintf(stderr, "publisher 'cuframes-%s' ready (v0.4 VMM)\n", key);

    cudaStream_t stream;
    cudaStreamCreate(&stream);

    int i = 0;
    while (1) {
        void *ptr = NULL;
        r = cuframes_publisher_acquire(pub, &ptr);
        if (r != CUFRAMES_OK) { fprintf(stderr, "acquire: %d\n", r); break; }

        uint8_t pattern = (uint8_t)(i & 0xFF);
        cudaMemsetAsync(ptr, pattern, 1920 * 1080 * 3 / 2, stream);

        r = cuframes_publisher_publish(pub, stream,
                                        (int64_t)cuframes_now_ns());
        if (r != CUFRAMES_OK) { fprintf(stderr, "publish: %d\n", r); break; }
        i++;
        if (i % 50 == 0) fprintf(stderr, "published %d frames\n", i);
        struct timespec ts = {.tv_sec = 0, .tv_nsec = 40000000};  /* 25 fps */
        nanosleep(&ts, NULL);
    }

    cudaStreamDestroy(stream);
    cuframes_publisher_destroy(pub);
    return 0;
}