/*
 * Standalone bit-exact C reference for H.264 luma Intra_8x8
 * prediction modes (per H.264 spec §8.3.2.1).  High-profile-only
 * MB type — Baseline/Main/Extended profiles don't see Intra_8x8.
 *
 * Distinct from Intra_4x4 in two ways:
 *
 *   1. REFERENCE SAMPLE FILTERING (§8.3.2.1.1).  The 25 raw
 *      neighbour samples are pre-filtered with a 1-2-1 smoothing
 *      filter BEFORE prediction.  The filtering has spec-defined
 *      boundary handling at the corners and the right-edge of the
 *      top-row extension.
 *
 *   2. SCALE.  All 9 prediction modes operate at 8x8 with the
 *      filtered samples (Intra_4x4 operates at 4x4 with the raw
 *      samples).
 *
 * This PR implements the filter + the 3 simple modes (Vertical,
 * Horizontal, DC).  The 6 directional modes (DDL, DDR, VR, HD, VL,
 * HU at 8x8) follow in a separate PR — same template, different
 * formulas per spec sections §8.3.2.1.4..§8.3.2.1.9.
 *
 * Calling convention (FFmpeg-style):
 *   pred_8x8_<mode>_ref(uint8_t *dst, ptrdiff_t stride)
 *
 * `dst` points at row 0 col 0 of the 8x8 output block.  Reads from
 *   top[0..15]  = dst[-stride + 0..15]
 *   top-left    = dst[-stride - 1]
 *   left[0..7]  = dst[ 0*stride - 1 .. 7*stride - 1]
 *
 * AVAILABILITY: assumes all neighbours valid (interior-MB case).
 *
 * License: BSD-2-Clause.
 */
#include <stdint.h>
#include <stddef.h>
#include <string.h>

static inline int clip_u8(int v) { return v < 0 ? 0 : v > 255 ? 255 : v; }

/* H.264 §8.3.2.1.1 reference sample filtering.  Filters the 25 raw
 * samples around the 8x8 block into a `filt` array with the same
 * indices.  When called against an "all neighbours available" tile,
 * the filtered output uses these spec-defined formulas:
 *
 *   filt[top -1] (= filtered top-left) = (top[0] + 2*tl + left[0] + 2) >> 2
 *
 *   filt[top  0] = (tl + 2*top[0] + top[1] + 2) >> 2
 *   filt[top  i] for 1<=i<=14 = (top[i-1] + 2*top[i] + top[i+1] + 2) >> 2
 *   filt[top 15] = (top[14] + 3*top[15] + 2) >> 2    (boundary)
 *
 *   filt[left 0] = (tl + 2*left[0] + left[1] + 2) >> 2
 *   filt[left j] for 1<=j<=6 = (left[j-1] + 2*left[j] + left[j+1] + 2) >> 2
 *   filt[left 7] = (left[6] + 3*left[7] + 2) >> 2    (boundary)
 *
 * Reads neighbours from the dst buffer; writes filtered values to
 * a caller-provided 26-element array indexed as:
 *   filt[0]      = filtered top-left
 *   filt[1..16]  = filtered top[0..15]
 *   filt[17..24] = filtered left[0..7]
 */
static void filter_refs(const uint8_t *dst, ptrdiff_t stride,
                         uint8_t filt[25])
{
    int tl = dst[-stride - 1];
    int t[16];
    for (int i = 0; i < 16; i++) t[i] = dst[-stride + i];
    int l[8];
    for (int j = 0; j < 8; j++) l[j] = dst[j * stride - 1];

    /* Filtered top-left. */
    filt[0] = (uint8_t)((t[0] + 2*tl + l[0] + 2) >> 2);

    /* Filtered top. */
    filt[1] = (uint8_t)((tl + 2*t[0] + t[1] + 2) >> 2);
    for (int i = 1; i <= 14; i++)
        filt[1 + i] = (uint8_t)((t[i-1] + 2*t[i] + t[i+1] + 2) >> 2);
    filt[1 + 15] = (uint8_t)((t[14] + 3*t[15] + 2) >> 2);

    /* Filtered left. */
    filt[17 + 0] = (uint8_t)((tl + 2*l[0] + l[1] + 2) >> 2);
    for (int j = 1; j <= 6; j++)
        filt[17 + j] = (uint8_t)((l[j-1] + 2*l[j] + l[j+1] + 2) >> 2);
    filt[17 + 7] = (uint8_t)((l[6] + 3*l[7] + 2) >> 2);
}

/* Convenience macros for accessing the filt[] array by spec-style index. */
#define FT(i)  filt[1 + (i)]    /* filtered top[i],  i in 0..15  */
#define FL(j)  filt[17 + (j)]   /* filtered left[j], j in 0..7   */
#define FTL    filt[0]          /* filtered top-left              */

/* Mode 0 Vertical (§8.3.2.1.2): pred[r,c] = filt_top[c]. */
void daedalus_h264_pred_8x8l_vertical_ref(uint8_t *dst, ptrdiff_t stride)
{
    uint8_t filt[25];
    filter_refs(dst, stride, filt);
    for (int r = 0; r < 8; r++)
        for (int c = 0; c < 8; c++) dst[r * stride + c] = FT(c);
}

/* Mode 1 Horizontal (§8.3.2.1.3): pred[r,c] = filt_left[r]. */
void daedalus_h264_pred_8x8l_horizontal_ref(uint8_t *dst, ptrdiff_t stride)
{
    uint8_t filt[25];
    filter_refs(dst, stride, filt);
    for (int r = 0; r < 8; r++)
        for (int c = 0; c < 8; c++) dst[r * stride + c] = FL(r);
}

/* Mode 2 DC (§8.3.2.1.4): ((sum_filt_top[0..7] + sum_filt_left[0..7]
 * + 8) >> 4) broadcast.  Note the +8 (not +4 like 4x4): there are
 * 16 samples summed total, so >> 4 with half-step rounding +8. */
void daedalus_h264_pred_8x8l_dc_ref(uint8_t *dst, ptrdiff_t stride)
{
    uint8_t filt[25];
    filter_refs(dst, stride, filt);
    int sum = 8;
    for (int i = 0; i < 8; i++) sum += FT(i);
    for (int j = 0; j < 8; j++) sum += FL(j);
    uint8_t v = (uint8_t)(sum >> 4);
    for (int r = 0; r < 8; r++)
        for (int c = 0; c < 8; c++) dst[r * stride + c] = v;
}