# ============================================================================
# texture.ludic — images for the GPU: PNG (8- and 16-bit, any colour type) and
# Radiance .hdr (RGBE) decoding straight into OpenGL textures.
#
# The engine's own PNG reader (image.ludic) expands to 8-bit 0xAARRGGBB for the
# 2D framebuffer; a renderer wants the file's real sample depth — normal and
# displacement maps ship as 16-bit — so this decoder keeps 16-bit samples and
# uploads them as GL_UNSIGNED_SHORT (big-endian, with GL_UNPACK_SWAP_BYTES) into
# RGB16 / R16 textures, and 8-bit ones into sRGB8 or RGB8 as the caller says.
# ============================================================================

const GL_TEXTURE_MAX_ANISOTROPY_EXT: int = 0x84FE

var tex_w: int = 0            # the last decoded image
var tex_h: int = 0
var tex_channels: int = 0
var tex_depth: int = 0        # bits per sample (8 or 16)
var tex_file_len: int = 0
var tex_anisotropy: fixed = 16.0

# The anisotropic filtering level for every mipmapped texture, loaded or not: 1 (off), 2, 4, 8
# or 16. Textures uploaded before a change are updated in place - on OpenGL by setting the
# parameter again, on Vulkan by rewriting the record the sampler cache reads - so a settings
# screen can offer it live instead of on the next start.
function r3d_set_anisotropy(level: int) -> void {
  var a: fixed = 1.0
  if level >= 2 { a = 2.0 }
  if level >= 4 { a = 4.0 }
  if level >= 8 { a = 8.0 }
  if level >= 16 { a = 16.0 }
  if a == tex_anisotropy { return }
  tex_anisotropy = a
  if gpu_tx == null { return }
  let keep = gpu_bound_2d
  for t in 1 .. gpu_tx_cap {
    let o = t * GPU_TX_W
    # a 2D texture with mipmaps that was given a level when it was uploaded
    if gpu_tx[o] != GPU_TEX2D or gpu_tx[o + 10] != 1 or gpu_tx[o + 11] == 0 { continue }
    gpu_tex_bind(GPU_TEX2D, t)
    gpu_tex_paramf(GPU_TEX2D, GL_TEXTURE_MAX_ANISOTROPY_EXT, a)
  }
  if keep > 0 { gpu_tex_bind(GPU_TEX2D, keep) }
}

function r3d_read_file(path: pointer) -> pointer {
  let f = file_open(path, "rb")
  if f == null { return null }
  file_seek(f, 0, 2)
  let n = file_tell(f)
  file_seek(f, 0, 0)
  if n <= 0 { file_close(f);  return null }
  let buf = bytes(n + 8)
  file_read(f, buf, n)
  file_close(f)
  tex_file_len = n
  return buf
}

function be32(b: pointer, at: int) -> int {
  return (b[at] << 24) | (b[at + 1] << 16) | (b[at + 2] << 8) | b[at + 3]
}
function tag4(b: pointer, at: int, a: int, c: int, d: int, e: int) -> bool {
  return b[at] == a and b[at + 1] == c and b[at + 2] == d and b[at + 3] == e
}

# Decode a PNG into tightly packed scanlines of raw samples (PNG byte order:
# 16-bit samples big-endian). Sets tex_w / tex_h / tex_channels / tex_depth.
# Indexed and sub-byte greyscale files are expanded to 8-bit RGB / grey.
# Reverse one scanline's PNG filter in place (spec 9.2). The filter type is
# loop-invariant, so it is resolved once here rather than per byte, and the
# leading `fbpp` bytes (where the left neighbour is zero by definition) run as
# their own prologue instead of costing a bounds test on every byte of the image.
# The caller keeps a zeroed scanline in front of row 0, so `prev` is always a real
# row and every filter has exactly one code path — no first-row special cases to
# get wrong or to leave untested.
function png_unfilter(raw: pointer, cur: int, prev: int, stride: int, fbpp: int, ft: int) -> void {
  if ft == 0 { return }
  var first = fbpp
  if first > stride { first = stride }
  var x = 0

  if ft == 1 {
    x = fbpp
    while x < stride { raw[cur + x] = ((raw[cur + x] + raw[cur + x - fbpp]) & 255);  x += 1 }
    return
  }

  if ft == 2 {
    x = 0
    while x < stride { raw[cur + x] = ((raw[cur + x] + raw[prev + x]) & 255);  x += 1 }
    return
  }

  if ft == 3 {
    x = 0
    while x < first { raw[cur + x] = ((raw[cur + x] + raw[prev + x] / 2) & 255);  x += 1 }
    while x < stride { raw[cur + x] = ((raw[cur + x] + (raw[cur + x - fbpp] + raw[prev + x]) / 2) & 255);  x += 1 }
    return
  }

  if ft == 4 {
    x = 0
    while x < first { raw[cur + x] = ((raw[cur + x] + raw[prev + x]) & 255);  x += 1 }
    while x < stride {
      let a = raw[cur + x - fbpp]
      let b = raw[prev + x]
      let c = raw[prev + x - fbpp]
      let p = a + b - c
      let pa = abs(p - a)
      let pb = abs(p - b)
      let pc = abs(p - c)
      var pick = c
      if pb <= pc { pick = b }
      if pa <= pb and pa <= pc { pick = a }
      raw[cur + x] = ((raw[cur + x] + pick) & 255)
      x += 1
    }
  }
}

function png_decode(path: pointer) -> pointer {
  let d = r3d_read_file(path)
  if d == null { print(`png: cannot read {path}`);  return null }
  let size = tex_file_len
  if size < 8 or d[0] != 137 or d[1] != 80 { free(d);  print(`png: not a png: {path}`);  return null }
  var w = 0;  var h = 0;  var bd = 0;  var ct = 0
  let plte = bytes(768)
  let idat = bytes(size)
  var idlen = 0
  var i = 8
  var done = false
  while not done {
    if i + 8 > size { done = true;  continue }
    let ln = be32(d, i)
    let typ = i + 4
    let body = i + 8
    if ln < 0 or body + ln > size { done = true;  continue }
    if tag4(d, typ, 73, 72, 68, 82) { w = be32(d, body);  h = be32(d, body + 4);  bd = d[body + 8];  ct = d[body + 9] }
    if tag4(d, typ, 80, 76, 84, 69) { let m = min(ln, 768);  for k in 0 .. m { plte[k] = d[body + k] } }
    if tag4(d, typ, 73, 68, 65, 84) { mem_copy(mem_off(idat, idlen), mem_off(d, body), ln);  idlen += ln }
    if tag4(d, typ, 73, 69, 78, 68) { done = true }
    i = i + 12 + ln
  }
  if w <= 0 or h <= 0 { free(d);  free(idat);  free(plte);  return null }
  var channels = 1
  if ct == 2 { channels = 3 }
  if ct == 4 { channels = 2 }
  if ct == 6 { channels = 4 }
  let bppbits = bd * channels
  var fbpp = (bppbits + 7) / 8
  if fbpp < 1 { fbpp = 1 }
  let stride = (w * bppbits + 7) / 8
  let rawlen = h * (stride + 1)
  # one zeroed scanline in front of the data, so row 0's "row above" is real
  let raw = bytes(stride + rawlen + 8)
  for z in 0 .. stride { raw[z] = 0 }
  if z_uncompress(idat, idlen, mem_off(raw, stride), rawlen) < 0 { free(d);  free(idat);  free(raw);  free(plte);  print(`png: inflate failed: {path}`);  return null }
  free(d);  free(idat)
  # reverse the per-scanline filters in place, then pack rows without the filter byte
  var y = 0
  while y < h {
    let line = stride + y * (stride + 1)
    png_unfilter(raw, line + 1, line + 1 - (stride + 1), stride, fbpp, raw[line])
    y += 1
  }
  var out: pointer = null
  if (ct == 3) or (bd < 8) {
    # expand palette / sub-byte grey to 8-bit RGB (palette) or 8-bit grey
    let maxv = (1 << bd) - 1
    var oc = 1
    if ct == 3 { oc = 3 }
    out = bytes(w * h * oc)
    for yy in 0 .. h {
      let row = stride + yy * (stride + 1) + 1
      for x in 0 .. w {
        let bp = x * bd
        let idx = ((raw[row + bp / 8] >> (8 - bd - bp % 8)) & maxv)
        if ct == 3 { out[(yy * w + x) * 3] = plte[idx * 3];  out[(yy * w + x) * 3 + 1] = plte[idx * 3 + 1];  out[(yy * w + x) * 3 + 2] = plte[idx * 3 + 2] }
        else { out[yy * w + x] = idx * 255 / maxv }
      }
    }
    channels = oc
    bd = 8
    free(raw)
  } else {
    out = bytes(h * stride + 8)
    for yy in 0 .. h { mem_copy(mem_off(out, yy * stride), mem_off(raw, stride + yy * (stride + 1) + 1), stride) }
    free(raw)
  }
  free(plte)
  tex_w = w;  tex_h = h;  tex_channels = channels;  tex_depth = bd
  return out
}

# Edge padding for cut-out atlases: pixels darker than `thresh` (the unused
# background) take the mean of their lit neighbours, repeated `passes` times, so
# mipmaps and bilinear taps never pull black into the blades. 8-bit RGB/RGBA only.
function tex_dilate(px: pointer, thresh: int, passes: int) -> void {
  if tex_depth != 8 or tex_channels < 3 { return }
  let w = tex_w;  let h = tex_h;  let c = tex_channels
  let mask = bytes(w * h)
  var i = 0
  while i < w * h { let o = i * c;  if px[o] + px[o + 1] + px[o + 2] < thresh { mask[i] = 1 } else { mask[i] = 0 };  i += 1 }
  let next = bytes(w * h)
  for pass in 0 .. passes {
    mem_copy(next, mask, w * h)
    var y = 0
    while y < h {
      var x = 0
      while x < w {
        let k = y * w + x
        if mask[k] == 1 {
          var r = 0;  var g = 0;  var b = 0;  var n = 0
          if x > 0 and mask[k - 1] == 0 { let o = (k - 1) * c;  r += px[o];  g += px[o + 1];  b += px[o + 2];  n += 1 }
          if x < w - 1 and mask[k + 1] == 0 { let o = (k + 1) * c;  r += px[o];  g += px[o + 1];  b += px[o + 2];  n += 1 }
          if y > 0 and mask[k - w] == 0 { let o = (k - w) * c;  r += px[o];  g += px[o + 1];  b += px[o + 2];  n += 1 }
          if y < h - 1 and mask[k + w] == 0 { let o = (k + w) * c;  r += px[o];  g += px[o + 1];  b += px[o + 2];  n += 1 }
          if n > 0 { let o = k * c;  px[o] = r / n;  px[o + 1] = g / n;  px[o + 2] = b / n;  next[k] = 0 }
        }
        x += 1
      }
      y += 1
    }
    mem_copy(mask, next, w * h)
  }
  free(mask);  free(next)
}

# Upload the last-decoded samples as a 2D texture. srgb: colour data (8-bit only).
function tex_upload(px: pointer, srgb: bool, mips: bool) -> int {
  let id = gpu_tex_new()
  gpu_tex_bind(GPU_TEX2D, id)
  var fmt = GL_RED
  if tex_channels == 2 { fmt = GL_RG }
  if tex_channels == 3 { fmt = GL_RGB }
  if tex_channels == 4 { fmt = GL_RGBA }
  var ifmt = GL_R8
  var ty = GL_UNSIGNED_BYTE
  if tex_depth == 16 {
    ty = GL_UNSIGNED_SHORT
    ifmt = GL_R16
    if tex_channels == 2 { ifmt = GL_RG16 }
    if tex_channels == 3 { ifmt = GL_RGB16 }
    if tex_channels == 4 { ifmt = GL_RGBA16 }
    gpu_pixel_store(GL_UNPACK_SWAP_BYTES, 1)
  } else {
    if tex_channels == 2 { ifmt = GL_RG8 }
    if tex_channels == 3 { ifmt = GL_RGB8;  if srgb { ifmt = GL_SRGB8 } }
    if tex_channels == 4 { ifmt = GL_RGBA8;  if srgb { ifmt = GL_SRGB8_ALPHA8 } }
    gpu_pixel_store(GL_UNPACK_SWAP_BYTES, 0)
  }
  gpu_pixel_store(GL_UNPACK_ALIGNMENT, 1)
  gpu_tex_image2d(ifmt, tex_w, tex_h, fmt, ty, px)
  gpu_pixel_store(GL_UNPACK_SWAP_BYTES, 0)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_WRAP_S, GL_REPEAT)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_WRAP_T, GL_REPEAT)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR)
  if mips {
    gpu_tex_param(GPU_TEX2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR_MIPMAP_LINEAR)
    gpu_tex_mips(GPU_TEX2D)
    gpu_tex_paramf(GPU_TEX2D, GL_TEXTURE_MAX_ANISOTROPY_EXT, tex_anisotropy)
  } else {
    gpu_tex_param(GPU_TEX2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR)
  }
  return id
}

# Load a PNG as a mipmapped, anisotropic texture (0 on failure). srgb for albedo.
function tex_load(path: pointer, srgb: bool) -> int { return tex_load_ex(path, srgb, 0) }
# ... with `dilate` passes of edge padding for a cut-out atlas (0 = none)
function tex_load_ex(path: pointer, srgb: bool, dilate: int) -> int {
  let px = png_decode(path)
  if px == null { return 0 }
  if dilate > 0 { tex_dilate(px, 60, dilate) }
  let id = tex_upload(px, srgb, true)
  free(px)
  return id
}

# A small solid-colour fallback texture (linear rgb 0..255), for missing maps.
function tex_solid(r: int, g: int, b: int, a: int) -> int {
  let px = bytes(16)
  for i in 0 .. 4 { px[i * 4] = r;  px[i * 4 + 1] = g;  px[i * 4 + 2] = b;  px[i * 4 + 3] = a }
  tex_w = 2;  tex_h = 2;  tex_channels = 4;  tex_depth = 8
  let id = tex_upload(px, false, false)
  free(px)
  return id
}

# ---- Radiance .hdr (RGBE, new-style RLE) -> RGB float bits -------------------------
var hdr_max_lum: float = 0.0      # float bits of the brightest texel (sun finding)
var hdr_max_x: int = 0
var hdr_max_y: int = 0
var hdr_sun_r: float = 0.0        # irradiance (float bits) of everything above the IBL clip: the sun
var hdr_sun_g: float = 0.0
var hdr_sun_b: float = 0.0
var hdr_clip: float = 0.0         # float bits; texels above this (per channel) feed the sun, not the IBL

function hdr_decode(path: pointer) -> floats {
  let d = r3d_read_file(path)
  if d == null { print(`hdr: cannot read {path}`);  return null }
  let size = tex_file_len
  # header: lines until an empty line, then "-Y h +X w"
  var i = 0
  var blank = false
  while i < size and not blank {
    if d[i] == 10 and d[i + 1] == 10 { blank = true;  i += 2 }
    else { i += 1 }
  }
  # parse "-Y <h> +X <w>"
  var h = 0;  var w = 0
  i += 3
  while d[i] >= '0' and d[i] <= '9' { h = h * 10 + (d[i] - 48);  i += 1 }
  i += 4
  while d[i] >= '0' and d[i] <= '9' { w = w * 10 + (d[i] - 48);  i += 1 }
  i += 1
  if w <= 0 or h <= 0 { free(d);  print(`hdr: bad header {path}`);  return null }
  let out = floats(w * h * 3)
  let line = bytes(w * 4)
  var maxl = 0.0
  if hdr_clip == 0.0 { hdr_clip = 20.0 }
  var sr = 0.0;  var sg = 0.0;  var sb = 0.0
  var skye = 0.0      # sky irradiance on an upward face (clipped part only)
  let dphi = 2.0 * PI / float(w)
  let dth = PI / float(h)
  var y = 0
  while y < h {
    if d[i] == 2 and d[i + 1] == 2 and (d[i + 2] & 128) == 0 {
      i += 4
      for c in 0 .. 4 {
        var x = 0
        while x < w {
          var n = d[i];  i += 1
          if n > 128 {
            n -= 128
            let v = d[i];  i += 1
            for k in 0 .. n { line[(x + k) * 4 + c] = v }
            x += n
          } else {
            for k in 0 .. n { line[(x + k) * 4 + c] = d[i + k] }
            i += n
            x += n
          }
        }
      }
    } else {
      for x in 0 .. w { for c in 0 .. 4 { line[x * 4 + c] = d[i + x * 4 + c] } }
      i += w * 4
    }
    let sinth = Math.sin((float(y) + 0.5) * dth)
    let domega = dphi * dth * sinth
    for x in 0 .. w {
      let e = line[x * 4 + 3]
      let o = (y * w + x) * 3
      if e == 0 { out[o] = 0.0;  out[o + 1] = 0.0;  out[o + 2] = 0.0 }
      else {
        let sh = e - 136
        let vr = float_from_bits(f_ldexp(float_bits(float(line[x * 4])), sh))
        let vg = float_from_bits(f_ldexp(float_bits(float(line[x * 4 + 1])), sh))
        let vb = float_from_bits(f_ldexp(float_bits(float(line[x * 4 + 2])), sh))
        # the texture is capped at what a half-float holds; the sun is integrated uncapped
        out[o] = Math.min(vr, 60000.0)
        out[o + 1] = Math.min(vg, 60000.0)
        out[o + 2] = Math.min(vb, 60000.0)
        let lum = vr + vg + vb
        if maxl < lum { maxl = lum;  hdr_max_x = x;  hdr_max_y = y }
        if y < h / 2 { skye = skye + Math.min(vg, hdr_clip) * Math.cos((float(y) + 0.5) * dth) * domega }
        if hdr_clip < vg or hdr_clip < vr {
          sr = sr + Math.max(vr - hdr_clip, 0.0) * domega
          sg = sg + Math.max(vg - hdr_clip, 0.0) * domega
          sb = sb + Math.max(vb - hdr_clip, 0.0) * domega
        }
      }
    }
    y += 1
  }
  free(line);  free(d)
  tex_w = w;  tex_h = h;  tex_channels = 3;  tex_depth = 32
  hdr_max_lum = maxl
  hdr_sun_r = sr;  hdr_sun_g = sg;  hdr_sun_b = sb
  print(`hdr: peak/1000 {fixed(maxl / 1000.0)} sky irradiance(up) {fixed(skye)} sun irradiance {fixed(sg)} (Q16.16 = /65536)`)
  return out
}

# Load an equirectangular .hdr as an RGB16F texture with mips (clamped in v).
function tex_load_hdr(path: pointer) -> int {
  let px = hdr_decode(path)
  if px == null { return 0 }
  let id = gpu_tex_new()
  gpu_tex_bind(GPU_TEX2D, id)
  gpu_pixel_store(GL_UNPACK_ALIGNMENT, 4)
  gpu_tex_image2d(GL_RGB16F, tex_w, tex_h, GL_RGB, GL_FLOAT, px)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_WRAP_S, GL_REPEAT)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR_MIPMAP_LINEAR)
  gpu_tex_mips(GPU_TEX2D)
  free(px)
  return id
}

# An empty render-target texture of the given internal format (no mips, clamped).
function tex_target(w: int, h: int, ifmt: int, fmt: int, ty: int, filter: int) -> int {
  let id = gpu_tex_new()
  gpu_tex_bind(GPU_TEX2D, id)
  gpu_tex_image2d(ifmt, w, h, fmt, ty, null)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_MAG_FILTER, filter)
  gpu_tex_param(GPU_TEX2D, GL_TEXTURE_MIN_FILTER, filter)
  return id
}

var tex_dump_alpha: bool = false
# Debug: the brightest texel of an RGBA float texture and where it is.
function tex_max(tex: int, w: int, h: int, tag: pointer) -> void {
  let buf = floats(w * h * 4)
  gpu_tex_bind(GPU_TEX2D, tex)
  gpu_pixel_store(GL_PACK_ALIGNMENT, 4)
  gpu_tex_read(GPU_TEX2D, GL_RGBA, GL_FLOAT, buf)
  var best = 0.0;  var bx = 0;  var by = 0
  var i = 0
  while i < w * h {
    let v = Math.max(buf[i * 4], Math.max(buf[i * 4 + 1], buf[i * 4 + 2]))
    if v > best { best = v;  bx = i % w;  by = i / w }
    i += 1
  }
  print(`{tag}: max {fixed(best / 100.0)}/100 at {bx} {h - 1 - by} (top-down)`)
  let o = (by * w + bx) * 4
  let big = 65000.0
  let finite = best < big
  print(`  rgba (clamped/100): {fixed(Math.min(buf[o], big) / 100.0)} {fixed(Math.min(buf[o + 1], big) / 100.0)} {fixed(Math.min(buf[o + 2], big) / 100.0)} {fixed(Math.min(buf[o + 3], big))}  finite {finite}  bits {buf[o]}`)
  free(buf)
}
# Debug: write a 2D texture's level 0 (RGBA8, alpha dropped) as a binary PPM.
function tex_dump(tex: int, w: int, h: int, path: pointer) -> void {
  let f = file_open(path, "wb")
  if f == null { return }
  let buf = bytes(w * h * 4)
  gpu_tex_bind(GPU_TEX2D, tex)
  gpu_pixel_store(GL_PACK_ALIGNMENT, 1)
  gpu_tex_read(GPU_TEX2D, GL_RGBA, GL_UNSIGNED_BYTE, buf)
  let hdr = `P6\n{w} {h}\n255\n`
  file_write(f, hdr, len(hdr))
  let row = bytes(w * 3)
  for y in 0 .. h {
    for x in 0 .. w {
      row[x * 3] = buf[(y * w + x) * 4];  row[x * 3 + 1] = buf[(y * w + x) * 4 + 1];  row[x * 3 + 2] = buf[(y * w + x) * 4 + 2]
      if tex_dump_alpha { let a = buf[(y * w + x) * 4 + 3];  row[x * 3] = a;  row[x * 3 + 1] = a;  row[x * 3 + 2] = a }
    }
    file_write(f, row, w * 3)
  }
  file_close(f)
  free(buf);  free(row)
}

# A binary PPM (P6, what Gl.screenshot writes) as an RGB8 texture, box-filtered down by
# `shrink` (a photo thumbnail); 0 when the file is missing.
function tex_load_ppm(path: pointer, shrink: int) -> int {
  let d = r3d_read_file(path)
  if d == null { return 0 }
  let size = tex_file_len
  var i = 2
  var w = 0;  var h = 0;  var mx = 0
  var field = 0
  while i < size and field < 3 {
    while i < size and (d[i] == 32 or d[i] == 10 or d[i] == 13 or d[i] == 9) { i += 1 }
    var v = 0
    while i < size and d[i] >= '0' and d[i] <= '9' { v = v * 10 + (d[i] - 48);  i += 1 }
    if field == 0 { w = v } else if field == 1 { h = v } else { mx = v }
    field += 1
  }
  i += 1
  if w <= 0 or h <= 0 or i + w * h * 3 > size { free(d);  return 0 }
  var k = shrink
  if k < 1 { k = 1 }
  let ow = w / k;  let oh = h / k
  let px = bytes(ow * oh * 3)
  for y in 0 .. oh {
    for x in 0 .. ow {
      var r = 0;  var g = 0;  var b = 0
      for yy in 0 .. k { for xx in 0 .. k {
        let o = i + ((y * k + yy) * w + x * k + xx) * 3
        r += d[o];  g += d[o + 1];  b += d[o + 2]
      } }
      let n = k * k
      let q = (y * ow + x) * 3
      px[q] = r / n;  px[q + 1] = g / n;  px[q + 2] = b / n
    }
  }
  free(d)
  tex_w = ow;  tex_h = oh;  tex_channels = 3;  tex_depth = 8
  let id = tex_upload(px, true, false)
  free(px)
  return id
}