wip: real coeffs extraction

CMakeLists.txt

@@ -195,6 +195,23 @@ if(DAEDALUS_BUILD_TOOLS)
             ${DAEDALUS_FFMPEG_PREFIX}/lib/libswresample.a
             m z pthread)
         set(FFMPEG_CFLAGS_OTHER "-DDAEDALUS_HAVE_H264_MB_INSPECT_CB=1")
+
+        # PR-A3+ optional: also point at the patched FFmpeg SOURCE TREE
+        # so the CLI can include libavcodec/h264dec.h directly and
+        # dereference H264Context fields (the side-buffer mb_inspect_coeffs
+        # added in marfrit-packages patch 0017, the cur_pic.f for
+        # pre-deblock pixel access, etc.).  When set, the internal-header
+        # include codepath is compiled in.
+        set(DAEDALUS_FFMPEG_SRC "" CACHE PATH
+            "Path to patched FFmpeg source tree (= path to FFmpeg/ checkout where build was run; contains config.h + libavcodec/h264dec.h). Empty = h264dec.h includes are disabled.")
+        if(DAEDALUS_FFMPEG_SRC)
+            message(STATUS "daedalus_decode_h264: FFmpeg source at ${DAEDALUS_FFMPEG_SRC}")
+            list(APPEND FFMPEG_INCLUDE_DIRS ${DAEDALUS_FFMPEG_SRC})
+            set(FFMPEG_CFLAGS_OTHER
+                "${FFMPEG_CFLAGS_OTHER} -DDAEDALUS_HAVE_H264_MB_INSPECT_COEFFS=1 -DHAVE_AV_CONFIG_H")
+            # Convert space-separated string to list (CMake idiom for compile flags).
+            separate_arguments(FFMPEG_CFLAGS_OTHER UNIX_COMMAND "${FFMPEG_CFLAGS_OTHER}")
+        endif()
     else()
         pkg_check_modules(FFMPEG REQUIRED libavcodec libavformat libavutil)
         message(STATUS "daedalus_decode_h264: system FFmpeg (no inspection callback)")

tools/daedalus_decode_h264.c

@@ -51,14 +51,32 @@
 #include <libavutil/imgutils.h>
 
 /* Per-MB inspection callback API — provided by the patched FFmpeg
- * fork via marfrit-packages 0016.  The H264Context struct itself
+ * fork via marfrit-packages patches 0016 + 0017.
- * remains internal (declared in libavcodec/h264dec.h which isn't
+ *
- * installed), so we only forward-declare it here and use it
+ * When DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS is defined (CMake sets it
- * opaquely through the callback signature.  Real per-MB state
+ * alongside DAEDALUS_FFMPEG_SRC), we include libavcodec's INTERNAL
- * extraction (sl->mb coefficients, mb_type, etc.) will land in
+ * h264dec.h header to dereference H264Context fields — specifically
- * PR-A3 alongside an internal-header include path. */
+ * h->mb_inspect_coeffs (the 0017 side buffer holding pre-IDCT-
-#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_CB
+ * destruction sl->mb), h->cur_pic.f (pre-deblock reconstructed pixels),
+ * and h->cur_pic.mb_type[mb_xy] for the mb-type gate.  The same
+ * configure-time config.h that built the static libavcodec.a is
+ * picked up via -DHAVE_AV_CONFIG_H + -I path; ABI match is automatic.
+ *
+ * When only DAEDALUS_HAVE_H264_MB_INSPECT_CB is defined (no source
+ * tree available — e.g. building against a distro-shipped patched
+ * libavcodec), the H264Context stays opaque and we fall back to
+ * identity-passthrough across all MBs.
+ *
+ * When neither is defined: stock libavcodec, no callback, identity-
+ * passthrough only (PR-A1b behaviour). */
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+#  include "libavcodec/h264dec.h"
+#  include "libavcodec/h264.h"   /* IS_INTRA4x4 / IS_8x8DCT / IS_INTRA_PCM */
+#elif defined(DAEDALUS_HAVE_H264_MB_INSPECT_CB)
 struct H264Context;
+#endif
+
+#if defined(DAEDALUS_HAVE_H264_MB_INSPECT_CB) || defined(DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS)
 typedef void (*ff_h264_mb_inspect_cb)(void *opaque,
                                        const struct H264Context *h,
                                        int mb_x, int mb_y);
@@ -76,35 +94,170 @@ static const char *substrate_str = "auto";
 static int   max_frames = -1;
 
 /* Inspection-callback state: per-frame counter + "each MB seen exactly
- * once" check.  We use a bitmap rather than a raster-order assertion
+ * once" check.  Bitmap, not raster-order — libavcodec's MB threading +
- * because libavcodec's MB-level threading + multi-slice frames mean
+ * multi-slice frames mean MBs reach the callback out of strict order;
- * MBs reach the callback in non-strictly-raster order; the contract
+ * contract is "every MB fires the callback exactly once per frame".
- * is "every MB fires the callback exactly once per frame", not "in
+ *
- * raster order".  Reset at end of each frame. */
+ * When real-coeff extraction is compiled in (PR-A3+), we ALSO maintain
+ * a per-MB capture buffer (real-coeffs path) so the main loop can
+ * drive daedalus_decoder_append_mb with REAL pre-residual P + real
+ * coefficients for MBs that satisfy the gate (Intra_4x4, no 8x8 DCT,
+ * no PCM).  Other MBs stay on identity-passthrough. */
 #ifdef DAEDALUS_HAVE_H264_MB_INSPECT_CB
+struct mb_capture {
+    int     valid;              /* 1 = real-coeffs path, 0 = identity passthrough */
+    int16_t coeffs[256];        /* luma, column-major within 4x4, raster block order */
+    uint8_t predicted[256];     /* luma P recovered = pre_deblock - clipped IDCT(C) */
+};
+
 struct inspect_state {
     int       n_cbs_this_frame;
     int       mb_w, mb_h;
     uint8_t  *seen;             /* mb_w * mb_h bitmap */
-    int       duplicate_mbs;    /* same (mb_x, mb_y) seen twice this frame */
+    int       duplicate_mbs;
-    int       out_of_bounds;    /* (mb_x, mb_y) outside the coded grid */
+    int       out_of_bounds;
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+    struct mb_capture *captures;        /* mb_w * mb_h entries */
+    int       real_coeffs_mbs;          /* count of MBs in real-coeffs path this frame */
+    int       skipped_intra16x16;
+    int       skipped_8x8dct;
+    int       skipped_other;
+#endif
 };
 
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+/* Zig-zag scan position → column-major-within-4x4 idx.
+ * daedalus convention: block[c*4 + r] = coeff at (row=r, col=c).
+ * H.264 §6.4.3 / fig 6-12 4x4 luma zig-zag scan order. */
+static const uint8_t zigzag_to_colmajor[16] = {
+    0, 4, 1, 2, 5, 8, 12, 9, 6, 3, 7, 10, 13, 14, 11, 15
+};
+
+/* H.264 §6.4.3 4x4 luma block scan within MB (z-scan).
+ * Maps raster-block-idx (sb_y*4+sb_x) → libavcodec sl->mb's z-scan idx.
+ * Z-scan happens to be its own inverse (symmetric mapping). */
+static const uint8_t raster_to_zscan[16] = {
+    0, 1, 4, 5, 2, 3, 6, 7, 8, 9, 12, 13, 10, 11, 14, 15
+};
+
+/* H.264 4x4 IDCT — transcribed from daedalus-fourier
+ * tests/test_idct_bitexact.c (which itself mirrors h264_idct4_ref.c).
+ * Outputs row-major 16-element residual; clip + shift happens in
+ * the consumer. */
+static void h264_idct4_butterfly(const int d[4], int out[4]) {
+    int e = d[0] + d[2];
+    int f = d[0] - d[2];
+    int g = (d[1] >> 1) - d[3];
+    int h = d[1] + (d[3] >> 1);
+    out[0] = e + h;
+    out[1] = f + g;
+    out[2] = f - g;
+    out[3] = e - h;
+}
+static void ref_idct4_compute(const int16_t block[16], int out[16]) {
+    /* block COLUMN-MAJOR: block[c*4+r] = coef at (row=r, col=c). */
+    int tmp[4][4];
+    for (int r = 0; r < 4; r++) {
+        int d[4] = { block[0*4+r], block[1*4+r], block[2*4+r], block[3*4+r] };
+        int o[4];
+        h264_idct4_butterfly(d, o);
+        for (int c = 0; c < 4; c++) tmp[r][c] = o[c];
+    }
+    for (int c = 0; c < 4; c++) {
+        int d[4] = { tmp[0][c], tmp[1][c], tmp[2][c], tmp[3][c] };
+        int o[4];
+        h264_idct4_butterfly(d, o);
+        for (int r = 0; r < 4; r++) out[r*4+c] = o[r];
+    }
+}
+#endif  /* DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS */
+
 static void inspect_cb(void *opaque,
                         const struct H264Context *h,
                         int mb_x, int mb_y)
 {
-    (void) h;
     struct inspect_state *st = opaque;
+#ifndef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+    (void) h;
+#endif
 
     if (mb_x < 0 || mb_x >= st->mb_w || mb_y < 0 || mb_y >= st->mb_h) {
         st->out_of_bounds++;
-    } else {
+        st->n_cbs_this_frame++;
-        const size_t idx = (size_t) mb_y * st->mb_w + (size_t) mb_x;
+        return;
-        if (st->seen[idx]) st->duplicate_mbs++;
-        st->seen[idx] = 1;
     }
+
+    const size_t idx = (size_t) mb_y * st->mb_w + (size_t) mb_x;
+    if (st->seen[idx]) st->duplicate_mbs++;
+    st->seen[idx] = 1;
     st->n_cbs_this_frame++;
+
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+    /* Real-coeffs path: extract per-MB state for daedalus-decoder
+     * IDCT validation on this MB.  Gate: only Intra_4x4 + 4x4 transform
+     * + non-PCM is supported in PR-A3b — other MB flavours fall back
+     * to identity-passthrough in the main loop. */
+    struct mb_capture *cap = &st->captures[idx];
+    cap->valid = 0;  /* default to passthrough */
+
+    const int mb_xy = mb_y * h->mb_stride + mb_x;
+    const uint32_t mb_type = h->cur_pic.mb_type[mb_xy];
+
+    if (!IS_INTRA4x4(mb_type)) {
+        if (IS_INTRA16x16(mb_type))  st->skipped_intra16x16++;
+        else                          st->skipped_other++;
+        return;
+    }
+    if (IS_8x8DCT(mb_type)) { st->skipped_8x8dct++; return; }
+    if (IS_INTRA_PCM(mb_type)) { st->skipped_other++; return; }
+
+    /* Snapshot luma pre-deblock pixels from cur_pic. */
+    const uint8_t *luma_plane = h->cur_pic.f->data[0];
+    const int luma_stride = h->cur_pic.f->linesize[0];
+    const uint8_t *mb_pixels = luma_plane + (ptrdiff_t) mb_y * 16 * luma_stride
+                                          + mb_x * 16;
+
+    /* Coefficients are in sl->mb at end of entropy decode but zeroed by
+     * the time the callback fires (IDCT-add consumed them).  Patch 0017
+     * preserves them in h->mb_inspect_coeffs[16 * 48] BEFORE IDCT runs,
+     * so we read from there. */
+    const int16_t *zz_mb = h->mb_inspect_coeffs;  /* layout matches sl->mb 8-bit half */
+
+    for (int r_block = 0; r_block < 16; r_block++) {
+        const int z_block = raster_to_zscan[r_block];
+        const int16_t *zz_block = &zz_mb[z_block * 16];
+
+        /* Inverse zig-zag scan → column-major-within-block. */
+        int16_t col[16] = {0};
+        for (int p = 0; p < 16; p++)
+            col[zigzag_to_colmajor[p]] = zz_block[p];
+
+        memcpy(&cap->coeffs[r_block * 16], col, 16 * sizeof(int16_t));
+
+        /* IDCT → row-major 16-int residual. */
+        int idct_row[16];
+        ref_idct4_compute(col, idct_row);
+
+        /* P = clip(pre_deblock - ((IDCT + 32) >> 6)) for each pixel.
+         * Symmetric: daedalus IDCT-add will undo the subtract, including
+         * for saturating cases (where the same shift puts the value back
+         * at the same clip boundary). */
+        const int sb_y = r_block >> 2;
+        const int sb_x = r_block & 3;
+        for (int r = 0; r < 4; r++) {
+            for (int c = 0; c < 4; c++) {
+                const int pre_db = mb_pixels[(sb_y * 4 + r) * luma_stride + sb_x * 4 + c];
+                const int shift  = (idct_row[r * 4 + c] + 32) >> 6;
+                int p = pre_db - shift;
+                if (p < 0)   p = 0;
+                if (p > 255) p = 255;
+                cap->predicted[(sb_y * 4 + r) * 16 + (sb_x * 4 + c)] = (uint8_t) p;
+            }
+        }
+    }
+    cap->valid = 1;
+    st->real_coeffs_mbs++;
+#endif
 }
 #endif
 
@@ -247,6 +400,17 @@ int main(int argc, char **argv)
     const AVCodec *codec = avcodec_find_decoder(AV_CODEC_ID_H264);
     AVCodecContext *avctx = avcodec_alloc_context3(codec);
     avcodec_parameters_to_context(avctx, fmt->streams[vstream]->codecpar);
+
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+    /* Patch 0017's coefficient side buffer lives in H264Context (single
+     * per-stream); multi-threaded slice decode would race on it.  Force
+     * single-thread.  Also disable libavcodec's deblock so AVFrame is
+     * pre-deblock and the P-recovery math is exact. */
+    avctx->thread_count     = 1;
+    avctx->thread_type      = 0;
+    avctx->skip_loop_filter = AVDISCARD_ALL;
+#endif
+
     if (avcodec_open2(avctx, codec, NULL) < 0) {
         fprintf(stderr, "avcodec_open2 failed\n");
         avformat_close_input(&fmt); return 2;
@@ -280,6 +444,11 @@ int main(int argc, char **argv)
         inspect_st.mb_h = H_round / 16;
         inspect_st.seen = calloc(1, (size_t) inspect_st.mb_w * inspect_st.mb_h);
         if (!inspect_st.seen) { rc = 1; goto cleanup; }
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+        inspect_st.captures = calloc((size_t) inspect_st.mb_w * inspect_st.mb_h,
+                                      sizeof(*inspect_st.captures));
+        if (!inspect_st.captures) { rc = 1; goto cleanup; }
+#endif
     }
     ff_h264_set_mb_inspect_cb(avctx, inspect_cb, &inspect_st);
     int inspect_total_cbs       = 0;
@@ -363,7 +532,26 @@ int main(int argc, char **argv)
             struct daedalus_decoder_mb_input mb = {0};
             for (int my = 0; my < mb_h; my++) {
                 for (int mx = 0; mx < mb_w; mx++) {
+                    /* Default: identity-passthrough — luma from AVFrame,
+                     * chroma from AVFrame, coeffs all zero. */
                     pack_mb_predicted(fr, mx, my, mb_pred);
+                    memset(mb_coeffs, 0, sizeof(mb_coeffs));
+
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+                    /* Real-coeffs path: if the callback captured this MB
+                     * as Intra_4x4 / 4x4-DCT, override luma predicted
+                     * with the recovered P and use the real luma coeffs.
+                     * Chroma stays identity-passthrough (PR-A3b scope —
+                     * chroma DC Hadamard + 8x8 transform follow-ups). */
+                    const int mb_idx = my * mb_w + mx;
+                    const struct mb_capture *cap = &inspect_st.captures[mb_idx];
+                    if (cap->valid) {
+                        memcpy(mb_pred, cap->predicted, 256);
+                        for (int i = 0; i < 256; i++)
+                            mb_coeffs[i] = cap->coeffs[i];
+                    }
+#endif
+
                     mb.mb_x        = (uint16_t) mx;
                     mb.mb_y        = (uint16_t) my;
                     mb.transform_8x8 = 0;
@@ -424,6 +612,21 @@ int main(int argc, char **argv)
                 inspect_st.duplicate_mbs    = 0;
                 inspect_st.out_of_bounds    = 0;
                 memset(inspect_st.seen, 0, (size_t) expected);
+
+#ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+                printf("  frame %d: real-coeffs path %d MBs, "
+                       "skipped intra16x16=%d 8x8dct=%d other=%d\n",
+                       n_frames, inspect_st.real_coeffs_mbs,
+                       inspect_st.skipped_intra16x16,
+                       inspect_st.skipped_8x8dct,
+                       inspect_st.skipped_other);
+                inspect_st.real_coeffs_mbs      = 0;
+                inspect_st.skipped_intra16x16   = 0;
+                inspect_st.skipped_8x8dct       = 0;
+                inspect_st.skipped_other        = 0;
+                memset(inspect_st.captures, 0,
+                       (size_t) expected * sizeof(*inspect_st.captures));
+#endif
             }
 #endif
             printf("  frame %d: Y diff %zu/%zu  UV diff %zu/%zu%s\n",
@@ -478,6 +681,9 @@ cleanup:
     free(out_uv_dadec);free(out_y_dadec);
 #ifdef DAEDALUS_HAVE_H264_MB_INSPECT_CB
     free(inspect_st.seen);
+#  ifdef DAEDALUS_HAVE_H264_MB_INSPECT_COEFFS
+    free(inspect_st.captures);
+#  endif
 #endif
     if (dec)   daedalus_decoder_destroy(dec);
     av_frame_free(&fr);