#define WIN32_LEAN_AND_MEAN
#define COBJMACROS
#include <windows.h>
#include <d3d11.h>
#include <dxgi1_2.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "capture_dda.h"
#include "capture-win32.h"   /* capture_thread_arg (win32-private) */
#include "present.h"
#include "cursor.h"          /* cursor_resolve_id + ctx->cursor compose state */
#include "geometry.h"        /* reactive geometry resample on recreate */
#include "stream.h"          /* vgpu_publish_cursor / vgpu_publish_cursor_shape */

typedef struct {
    ID3D11Device*           dev;
    ID3D11DeviceContext*    dctx;
    IDXGIOutput1*           out1;
    IDXGIOutputDuplication* dup;
    ID3D11Texture2D*        staging;
    UINT                    W, H;
    int32_t                 cap_x, cap_y;       /* captured output origin (virt coords) */
    UINT64                  last_mouse_update;  /* shape-gate by fi.LastMouseUpdateTime */
    int                     seeded;             /* cold-start position seed done */
} dda_state;

/* Source the cursor from the already-fetched frame info (0 syscalls for position) and publish
 * it under the cursor_seq gate. Position/visibility come from fi.PointerPosition; the shape is
 * re-extracted only when fi.LastMouseUpdateTime changed (shape-gate). Cold start: fi is invalid
 * until the mouse first moves (LastMouseUpdateTime==0) — seed the position once via one
 * GetCursorInfo, then rely on fi. ctx->cursor compose fields are written under ctx->lock; the
 * producer-block publish uses release/seq, no lock. */
static void dda_source_cursor(vgpu_ctx* ctx, dda_state* st,
                              const DXGI_OUTDUPL_FRAME_INFO* fi) {
    int vis = fi->PointerPosition.Visible ? 1 : 0;
    int x, y;
    UINT64 upd = (UINT64)fi->LastMouseUpdateTime.QuadPart;

    if (!st->seeded && upd == 0) {
        CURSORINFO ci; ci.cbSize = sizeof ci;
        if (GetCursorInfo(&ci)) {
            vis = (ci.flags & CURSOR_SHOWING) != 0;
            x = ci.ptScreenPos.x; y = ci.ptScreenPos.y;
        } else {
            x = ctx->cursor.x; y = ctx->cursor.y;
        }
        st->seeded = 1;
    } else {
        x = fi->PointerPosition.Position.x;
        y = fi->PointerPosition.Position.y;
        if (upd != 0) st->seeded = 1;
    }

    /* shape-gate: re-extract only when the mouse-update stamp advanced */
    if (upd != 0 && upd != st->last_mouse_update) {
        CURSORINFO ci; ci.cbSize = sizeof ci;
        if (GetCursorInfo(&ci) && ci.hCursor && ci.hCursor != ctx->cursor.handle) {
            EnterCriticalSection(&ctx->lock);
            cursor_apply_shape(ctx, ci.hCursor);
            LeaveCriticalSection(&ctx->lock);
        }
        st->last_mouse_update = upd;
    }

    EnterCriticalSection(&ctx->lock);
    ctx->cursor.visible = vis;
    ctx->cursor.x = x; ctx->cursor.y = y;
    uint32_t hx = (uint32_t)ctx->cursor.hot_x, hy = (uint32_t)ctx->cursor.hot_y;
    uint32_t gw = (uint32_t)ctx->cursor.gw,    gh = (uint32_t)ctx->cursor.gh;
    uint32_t cid = (uint32_t)ctx->cursor.cursor_id;
    LeaveCriticalSection(&ctx->lock);

    vgpu_publish_cursor_shape(&ctx->view, hx, hy, gw, gh, cid);
    vgpu_publish_cursor(&ctx->view, (int32_t)x, (int32_t)y, (uint32_t)vis);
}

static DWORD WINAPI dda_thread(LPVOID param) {
    capture_thread_arg* arg = (capture_thread_arg*)param;
    vgpu_ctx*  ctx = arg->ctx;
    dda_state* st  = (dda_state*)arg->backend_state;
    free(arg);

    for (;;) {
        DXGI_OUTDUPL_FRAME_INFO fi;
        IDXGIResource* res = NULL;
        HRESULT hr = st->dup->lpVtbl->AcquireNextFrame(st->dup, 1000, &fi, &res);
        if (hr == DXGI_ERROR_WAIT_TIMEOUT) continue;
        if (hr == DXGI_ERROR_ACCESS_LOST) {
            if (st->dup) { st->dup->lpVtbl->Release(st->dup); st->dup = NULL; }
            if (FAILED(st->out1->lpVtbl->DuplicateOutput(st->out1,
                       (IUnknown*)st->dev, &st->dup))) {
                Sleep(200);
            } else {
                /* display config may have changed across the access loss → resample geometry */
                geometry_sample_and_publish(ctx, st->cap_x, st->cap_y);
            }
            continue;
        }
        if (FAILED(hr)) { Sleep(50); continue; }

        dda_source_cursor(ctx, st, &fi);

        ID3D11Texture2D* tex = NULL;
        res->lpVtbl->QueryInterface(res, &IID_ID3D11Texture2D, (void**)&tex);
        if (tex) {
            st->dctx->lpVtbl->CopyResource(st->dctx,
                (ID3D11Resource*)st->staging, (ID3D11Resource*)tex);
            D3D11_MAPPED_SUBRESOURCE m;
            if (SUCCEEDED(st->dctx->lpVtbl->Map(st->dctx,
                    (ID3D11Resource*)st->staging, 0, D3D11_MAP_READ, 0, &m))) {
                vgpu_present_submit(ctx, (const uint8_t*)m.pData, st->W, st->H, m.RowPitch);
                st->dctx->lpVtbl->Unmap(st->dctx, (ID3D11Resource*)st->staging, 0);
            }
            tex->lpVtbl->Release(tex);
        }
        if (res) res->lpVtbl->Release(res);
        st->dup->lpVtbl->ReleaseFrame(st->dup);
    }
    return 0;  /* unreachable; satisfies -Wreturn-type */
}

int dda_start(vgpu_ctx* ctx, int fps) {
    (void)fps;
    dda_state* st = (dda_state*)calloc(1, sizeof *st);
    if (!st) return 0;

    D3D_FEATURE_LEVEL fl;
    if (FAILED(D3D11CreateDevice(NULL, D3D_DRIVER_TYPE_HARDWARE, NULL, 0, NULL, 0,
              D3D11_SDK_VERSION, &st->dev, &fl, &st->dctx))) {
        fprintf(stderr, "eyes(dda): D3D11CreateDevice failed\n");
        goto fail;
    }

    IDXGIDevice*  dxgiDev = NULL;
    IDXGIAdapter* adapter = NULL;
    IDXGIOutput*  output  = NULL;
    st->dev->lpVtbl->QueryInterface(st->dev, &IID_IDXGIDevice, (void**)&dxgiDev);
    if (dxgiDev) dxgiDev->lpVtbl->GetAdapter(dxgiDev, &adapter);
    if (adapter) adapter->lpVtbl->EnumOutputs(adapter, 0, &output);
    if (output) {
        DXGI_OUTPUT_DESC od;
        if (SUCCEEDED(output->lpVtbl->GetDesc(output, &od))) {
            st->cap_x = (int32_t)od.DesktopCoordinates.left;
            st->cap_y = (int32_t)od.DesktopCoordinates.top;
        }
        output->lpVtbl->QueryInterface(output, &IID_IDXGIOutput1, (void**)&st->out1);
    }

    if (output)  output->lpVtbl->Release(output);
    if (adapter) adapter->lpVtbl->Release(adapter);
    if (dxgiDev) dxgiDev->lpVtbl->Release(dxgiDev);

    if (!st->out1 || FAILED(st->out1->lpVtbl->DuplicateOutput(st->out1,
                            (IUnknown*)st->dev, &st->dup))) {
        fprintf(stderr, "eyes(dda): DuplicateOutput failed\n");
        goto fail;
    }

    DXGI_OUTDUPL_DESC dd;
    st->dup->lpVtbl->GetDesc(st->dup, &dd);
    st->W = dd.ModeDesc.Width;
    st->H = dd.ModeDesc.Height;

    D3D11_TEXTURE2D_DESC td; memset(&td, 0, sizeof td);
    td.Width = st->W; td.Height = st->H; td.MipLevels = 1; td.ArraySize = 1;
    td.Format = DXGI_FORMAT_B8G8R8A8_UNORM; td.SampleDesc.Count = 1;
    td.Usage = D3D11_USAGE_STAGING; td.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
    if (FAILED(st->dev->lpVtbl->CreateTexture2D(st->dev, &td, NULL, &st->staging))) {
        fprintf(stderr, "eyes(dda): CreateTexture2D failed\n");
        goto fail;
    }

    capture_thread_arg* arg = (capture_thread_arg*)malloc(sizeof *arg);
    if (!arg) goto fail;
    arg->ctx = ctx; arg->fps = fps; arg->backend_state = st;

    ctx->backend = VGPU_BK_DDA;
    ctx->draw_cursor_cap = 1;   /* DDA frames are content-only → presenter draws cursor */

    HANDLE t = CreateThread(NULL, 0, dda_thread, arg, 0, NULL);
    if (!t) { free(arg); goto fail; }
    CloseHandle(t);

    fprintf(stderr, "eyes(dda): desktop %ux%u (content-only; cursor by presenter)\n",
            st->W, st->H);
    return 1;

fail:
    /* release any COM objects created before the failure (no ref leaks) */
    if (st->staging) st->staging->lpVtbl->Release(st->staging);
    if (st->dup)     st->dup->lpVtbl->Release(st->dup);
    if (st->out1)    st->out1->lpVtbl->Release(st->out1);
    if (st->dctx)    st->dctx->lpVtbl->Release(st->dctx);
    if (st->dev)     st->dev->lpVtbl->Release(st->dev);
    free(st);
    return 0;
}