Files
Going-Commando/crates/gc-extract/tests/disc.rs
T
ReaperOfVeriod 4c4a78d402 Identify the container the class tables point into: core_data itself
assets_compressed_size and assets_decompressed_size at index offsets
0x88 and 0x8c are 9,738,678 and 16,969,296 on level 0 -- exactly the
sizes of core_data before and after decompression. There is no separate
asset container. The "asset WAD" is core_data, and offset_in_asset_wad
indexes the decompressed form directly.

Checked rather than assumed, on all 27 levels: the decompressed size
equals core_data's exact length, every class offset is either 0 or inside
it, and the moby, tie and shrub spans do not overlap each other.

An offset of 0 means the slot has no geometry, not the start of the
lump; level 0's ninth moby class is 4909 at offset 0. Two assumptions
worth discarding while here -- the tables are not sorted by class number
(level 0's run 0, 1, 2, 14 ... 4909) and the offsets within a table are
not monotonic. Neither is needed, but both look true from the first few
entries.

The chunk descriptors after the named extents are not it: they exist on
only 3 of 27 levels, because level 0's four named extents tile the
container exactly. An asset blob there would be missing almost
everywhere.

What sits at the offsets is raw GS/VIF packet data rather than a further
container -- moby[0] begins 00 00 00 00 3f 16 02 55 6f 6f and tie[0]
00 01 00 00 70 50 00 00, which read as packet headers rather than a
magic number.

None of the three is decoded yet and this does not start that. Moby is
skeletal and is the largest single piece left before the rest of a level
can draw.

Also: the pipeline now writes each level's chunk descriptors where they
exist, and LevelCoreHeader decodes the asset lump's two sizes.
2026-10-11 02:03:31 +02:00

1202 lines
45 KiB
Rust

//! Integration tests against a real disc image.
//!
//! These are skipped unless `GC_DISC` points at a legally obtained disc, since
//! the repository must not contain game data. When it is set they check the
//! identification and unpack results against the committed hash table.
//!
//! ```sh
//! GC_DISC="path/to/disc.iso" cargo test -p gc-extract --test disc
//! ```
use std::path::{Path, PathBuf};
/// The disc under test, if the environment names one.
fn disc() -> Option<PathBuf> {
let p = std::env::var_os("GC_DISC")?;
let p = PathBuf::from(p);
p.is_file().then_some(p)
}
/// Skip a test with a clear reason rather than failing.
macro_rules! require_disc {
() => {
match disc() {
Some(p) => p,
None => {
eprintln!("skipped: set GC_DISC to a Going Commando disc image to run this");
return;
}
}
};
}
#[test]
fn identifies_the_supported_build() {
let path = require_disc!();
let info = gc_extract::identify::identify(&path).expect("disc should identify");
assert_eq!(info.serial, "SCUS_972.68");
assert_eq!(info.volume_id, "RATCHETANDCLANK2");
assert!(
info.is_target(),
"expected the supported build, got: {}",
info.verdict()
);
assert_eq!(
info.boot_elf_sha1,
gc_extract::identify::TARGET_BOOT_ELF_SHA1,
"boot ELF SHA-1 differs from the recorded retail value"
);
assert_eq!(info.boot_elf_size, 2_618_684);
// This disc is NTSC; the movement constants assume 60 Hz.
assert!(!info.is_pal(), "test disc should be NTSC");
}
#[test]
fn agrees_with_the_python_reference_identifier() {
let path = require_disc!();
let info = gc_extract::identify::identify(&path).expect("disc should identify");
// tools/identify-disc.py is the reference implementation and prints these
// two values. If they ever disagree, one of them has a bug.
// Run from the workspace root so the relative path to the tool resolves.
let root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
.parent()
.and_then(|p| p.parent())
.expect("the crate should live two levels below the workspace root")
.to_path_buf();
let py = std::process::Command::new("python3")
.arg(root.join("tools/identify-disc.py"))
.arg(&path)
.current_dir(&root)
.output()
.expect("python3 should be available to run the reference identifier");
assert!(
py.status.success(),
"the reference identifier failed:\n{}",
String::from_utf8_lossy(&py.stderr)
);
let text = String::from_utf8_lossy(&py.stdout);
assert!(
text.contains(&format!("serial {}", info.serial)),
"serial disagrees with the reference identifier:\n{text}"
);
assert!(
text.contains(&format!("SHA-1 {}", info.boot_elf_sha1)),
"boot ELF SHA-1 disagrees with the reference identifier:\n{text}"
);
}
#[test]
fn unpacks_and_matches_the_committed_table() {
let path = require_disc!();
let table_path = Path::new(env!("CARGO_MANIFEST_DIR")).join("data/gc-files.tsv");
let table_text =
std::fs::read_to_string(&table_path).expect("the hash table should be committed");
let expected = gc_extract::verify::parse_table(&table_text);
assert!(
expected.len() > 5000,
"expected a full table, got {} rows",
expected.len()
);
// Unpack into a temporary directory so the test leaves nothing behind.
let tmp = std::env::temp_dir().join(format!("gc-unpack-{}", std::process::id()));
let _ = std::fs::remove_dir_all(&tmp);
std::fs::create_dir_all(&tmp).expect("should create a temp directory");
let files = gc_extract::unpack::unpack(&path, &tmp).expect("unpack should succeed");
// Every unpacked file must match the recorded size and hash.
let report = gc_extract::verify::verify(&tmp, &expected);
let _ = std::fs::remove_dir_all(&tmp);
assert!(
report.ok(),
"unpacked data does not match the committed table:\n{}",
report.summary()
);
assert_eq!(
files.len(),
expected.len(),
"unpack produced a different file count"
);
}
#[test]
fn every_container_parses() {
let path = require_disc!();
let iso = gc_formats::iso9660::IsoImage::open(&path).expect("ISO should open");
let containers: Vec<_> = iso
.files
.iter()
.filter(|e| e.name.starts_with("G/") && e.name.ends_with(".WAD"))
.collect();
// 92 `G/*.WAD` containers: 27 LEVEL, 27 AUDIO, 27 SCENE, 11 globals.
assert_eq!(containers.len(), 92, "expected 92 asset containers");
// MPEG1 and MPEG2 are raw video streams with no table; the other 90 must
// all parse as indexed containers.
let raw_video: Vec<&str> = containers
.iter()
.map(|c| c.name.as_str())
.filter(|n| *n == "G/MPEG1.WAD" || *n == "G/MPEG2.WAD")
.collect();
assert_eq!(
raw_video.len(),
2,
"expected MPEG1 and MPEG2 to be the raw streams"
);
// The per-level families must all be present, at 27 each.
for family in ["LEVEL", "AUDIO", "SCENE"] {
let n = containers
.iter()
.filter(|c| {
let stem = c.name.trim_start_matches("G/").trim_end_matches(".WAD");
stem.strip_prefix(family)
.map(|rest| !rest.is_empty() && rest.chars().all(|ch| ch.is_ascii_digit()))
.unwrap_or(false)
})
.count();
assert_eq!(n, 27, "expected 27 {family}<n>.WAD containers, found {n}");
}
for entry in &containers {
if raw_video.contains(&entry.name.as_str()) {
continue;
}
let data = gc_formats::iso9660::read_at(&path, entry.lba, entry.size)
.expect("read should succeed");
let kind = gc_formats::global_wad::RangeKind::for_container(&entry.name);
let container = gc_formats::global_wad::GlobalWad::parse_with(&data, kind)
.unwrap_or_else(|e| panic!("{} failed to parse: {e}", entry.name));
assert!(
!container.entries.is_empty(),
"{} parsed but had no entries",
entry.name
);
}
}
/// The level container header is the first typed structure we parse from real
/// data, and the tiling invariant is the check that holds on every level rather
/// than one hand-picked sample.
#[test]
fn level_headers_tile_their_containers() {
let path = require_disc!();
let iso = gc_formats::iso9660::IsoImage::open(&path).expect("ISO should open");
let mut checked = 0;
for entry in iso.files.iter().filter(|e| e.name.starts_with("G/LEVEL")) {
let data = gc_formats::iso9660::read_at(&path, entry.lba, 0x60).expect("read header");
let h = gc_formats::level_wad::LevelHeader::parse(&data)
.unwrap_or_else(|e| panic!("{}: {e}", entry.name));
assert_eq!(h.header_size, 0x60, "{}", entry.name);
assert_eq!(
h.runtime_sector, 0,
"{}: runtime sector field should be 0 on disc",
entry.name
);
// Every present extent must start where the previous one ended.
let extents = h.ordered_extents();
for w in extents.windows(2) {
let (pn, p) = w[0];
let (nn, n) = w[1];
assert_eq!(
p.offset + p.size,
n.offset,
"{}: gap or overlap between {} and {}",
entry.name,
pn.name(),
nn.name()
);
}
// Nothing may fall outside the container. The last extent may end one
// sector past the file end through sector rounding, hence `+ 1`.
let container_sectors = (entry.size / 2048) as i32;
for (name, r) in &extents {
assert!(
r.offset >= 0 && r.offset + r.size <= container_sectors + 1,
"{}: {} extent {:?} is outside the container ({container_sectors} sectors)",
entry.name,
name.name(),
r
);
}
checked += 1;
}
assert_eq!(checked, 27, "expected 27 level containers");
}
/// Level ids are not file order: `LEVEL21.WAD` reports 30. Anything that keys
/// off the container index would silently mislabel that planet.
#[test]
fn level_ids_are_not_container_indices() {
let path = require_disc!();
let iso = gc_formats::iso9660::IsoImage::open(&path).expect("ISO should open");
// The ISO filesystem lists names alphabetically, so LEVEL10 sorts before
// LEVEL2. Order by the numeric suffix, which is what the container names
// mean.
let mut levels: Vec<(usize, &gc_formats::iso9660::DirEntry)> = iso
.files
.iter()
.filter(|e| e.name.starts_with("G/LEVEL"))
.map(|e| {
let n: usize = e
.name
.trim_start_matches("G/LEVEL")
.trim_end_matches(".WAD")
.parse()
.expect("level container names end in a number");
(n, e)
})
.collect();
levels.sort_by_key(|(n, _)| *n);
let mut mismatches = Vec::new();
for (index, (_, entry)) in levels.iter().enumerate() {
let data = gc_formats::iso9660::read_at(&path, entry.lba, 0x60).expect("read header");
let h = gc_formats::level_wad::LevelHeader::parse(&data).expect("parse");
if h.id as usize != index {
mismatches.push(format!(
"{}: id {} but is container {index}",
entry.name, h.id
));
}
}
// Exactly one level is out of step: the gap left by a removed level.
assert_eq!(
mismatches.len(),
1,
"expected exactly one level whose id differs from its container index, got {mismatches:?}"
);
assert!(
mismatches[0].contains("LEVEL21"),
"unexpected mismatch: {mismatches:?}"
);
}
/// Sizes in the level header are sector counts. If they were byte counts, the
/// extents could not tile a container this size, so this also guards against
/// "fixing" the parser to read them as bytes.
#[test]
fn level_extent_sizes_are_sector_counts() {
let path = require_disc!();
let iso = gc_formats::iso9660::IsoImage::open(&path).expect("ISO should open");
let entry = iso.find("G/LEVEL0.WAD").expect("level 0");
let data = gc_formats::iso9660::read_at(&path, entry.lba, 0x60).expect("read header");
let h = gc_formats::level_wad::LevelHeader::parse(&data).expect("parse");
// Sound bank occupies sectors 1..735 and data 735..7219.
assert_eq!(h.sound_bank.offset, 1);
assert_eq!(h.sound_bank.size, 734);
assert_eq!(h.data.offset, 735);
// Read as bytes, 734 would be under four sectors and the tiling would break.
assert_eq!(h.sound_bank.byte_len(), 734 * 2048);
}
/// The level data extent is a container of byte ranges. Its header locates the
/// geometry index and the compressed geometry, and every range must lie inside
/// the extent on all 27 levels.
#[test]
fn level_data_extents_are_in_range() {
let path = require_disc!();
let iso = gc_formats::iso9660::IsoImage::open(&path).expect("ISO should open");
let mut checked = 0;
for entry in iso.files.iter().filter(|e| e.name.starts_with("G/LEVEL")) {
let raw =
gc_formats::iso9660::read_at(&path, entry.lba, entry.size).expect("read container");
let lh = gc_formats::level_wad::LevelHeader::parse(&raw).expect("level header");
let data = lh.data;
let Some(offset) = data.byte_offset() else {
continue;
};
let len = data.byte_len() as usize;
let extent = &raw[offset as usize..offset as usize + len];
let dh = gc_formats::level_data::LevelDataHeader::parse(extent)
.unwrap_or_else(|e| panic!("{}: data extent header: {e}", entry.name));
for (part, r) in dh.present_parts() {
assert!(
r.end() <= extent.len() as u64,
"{}: {part:?} ends at {} but the extent is {} bytes",
entry.name,
r.end(),
extent.len()
);
}
// The geometry is the big one and must be substantial.
assert!(
dh.core_data.size > 1_000_000,
"{}: core_data is only {} bytes",
entry.name,
dh.core_data.size
);
checked += 1;
}
assert_eq!(checked, 27, "expected 27 level containers");
}
/// The geometry must decompress. This is the first test that touches real level
/// content rather than headers.
#[test]
fn level_geometry_decompresses() {
let path = require_disc!();
let iso = gc_formats::iso9660::IsoImage::open(&path).expect("ISO should open");
let entry = iso.find("G/LEVEL0.WAD").expect("level 0");
let raw = gc_formats::iso9660::read_at(&path, entry.lba, entry.size).expect("read container");
let lh = gc_formats::level_wad::LevelHeader::parse(&raw).expect("level header");
let data = lh.data;
let extent = &raw[data.byte_offset().unwrap() as usize
..(data.byte_offset().unwrap() + data.byte_len()) as usize];
let dh = gc_formats::level_data::LevelDataHeader::parse(extent).expect("data header");
let core = dh
.core_data
.slice(extent, extent.len())
.expect("core_data slice");
assert!(
gc_formats::wad::is_wad(core),
"core_data should start with the WAD magic"
);
let decoded = gc_formats::wad::decompress(core).expect("core_data should decompress");
assert!(
decoded.len() > core.len(),
"decompressed geometry ({}) should exceed the compressed size ({})",
decoded.len(),
core.len()
);
}
/// The terrain itself. This is the first test to touch real level content: it
/// parses the tfrags directory and decodes vertex positions from every patch.
///
/// The gate is deliberately about *coverage*, not correctness of a sample: a
/// parser that works on one tfrag and silently returns `None` on the rest would
/// otherwise pass.
#[test]
fn tfrag_vertices_decode_for_every_level() {
require_disc!();
// Opening the image also confirms the disc is readable, not merely present.
gc_formats::iso9660::IsoImage::open(std::path::Path::new(
&std::env::var("GC_DISC").expect("GC_DISC is set by require_disc!"),
))
.expect("ISO should open");
// Where the unpacked data lives. GC_EXTRACTED overrides; otherwise the
// default location used during development.
let data = std::env::var_os("GC_EXTRACTED")
.map(PathBuf::from)
.unwrap_or_else(|| {
let home = std::env::var("HOME").unwrap_or_else(|_| ".".to_string());
PathBuf::from(home).join("Documents/gc-extracted")
});
if !data.exists() {
eprintln!(
"skipped: unpack the disc first, e.g.\
gc-extract unpack <disc.iso> ~/Documents/gc-extracted\
or point GC_EXTRACTED at an existing unpack"
);
return;
}
let mut levels = 0usize;
let mut total_verts = 0usize;
let mut total_tfrags = 0usize;
for n in 0..27 {
let dir = data.join(format!("level{n}"));
let core_path = dir.join("core_data.bin");
let index_path = dir.join("core_index.bin");
if !core_path.exists() || !index_path.exists() {
continue;
}
let core = std::fs::read(&core_path).expect("core_data");
let index = std::fs::read(&index_path).expect("core_index");
// The tfrags block starts at the core header's 0x08 field and runs to
// the next region that exists.
let region_start =
|off: usize| -> i32 { i32::from_le_bytes(index[off..off + 4].try_into().unwrap()) };
let start = region_start(0x08) as usize;
let end = [0x0c_usize, 0x10, 0x14]
.iter()
.map(|&o| region_start(o))
.filter(|&v| v > 0)
.min()
.unwrap_or(core.len() as i32) as usize;
let block = &core[start..end];
let header = gc_formats::tfrag::TfragsBlock::parse(block).expect("tfrags block header");
assert_eq!(header.table_offset, 0x40, "level{n}: table offset");
let table_offset = header.table_offset as usize;
let mut decoded = 0usize;
let mut verts = 0usize;
for i in 0..header.tfrag_count as usize {
let th = header.header(block, i).expect("tfrag header");
let data_base = table_offset.wrapping_add(th.data as usize);
if data_base >= block.len() {
continue;
}
let slice = &block[data_base..];
if let Some(p) = gc_formats::tfrag::tfrag_positions(slice, &th) {
decoded += 1;
verts += p.len();
assert_eq!(p.len(), th.vert_count as usize);
}
}
assert!(header.tfrag_count > 0, "level{n}: no tfrags");
assert_eq!(
decoded, header.tfrag_count as usize,
"level{n}: only {decoded} of {} tfrags decoded",
header.tfrag_count
);
levels += 1;
total_tfrags += header.tfrag_count as usize;
total_verts += verts;
}
assert!(levels > 0, "no unpacked levels were found");
assert!(
total_tfrags > 5000,
"expected thousands of tfrags, got {total_tfrags}"
);
assert!(
total_verts > 100_000,
"expected 100k+ vertices, got {total_verts}"
);
eprintln!("decoded {total_verts} vertices from {total_tfrags} tfrags across {levels} levels");
}
/// Terrain topology: strips and index arrays must expand to exactly the
/// triangle count each patch's header claims.
///
/// `tri_count` is stored in the patch header but is not derivable from the
/// lists directly, so reproducing it on all 18,102 patches is a strong check
/// that the strip walk, the index bank and the LOD assignment are all right.
/// Triangle indices must also stay inside the vertex-info range for the LOD.
#[test]
fn tfrag_topology_reproduces_the_header_triangle_count() {
require_disc!();
gc_formats::iso9660::IsoImage::open(std::path::Path::new(
&std::env::var("GC_DISC").expect("GC_DISC is set by require_disc!"),
))
.expect("ISO should open");
let data = std::env::var_os("GC_EXTRACTED")
.map(PathBuf::from)
.unwrap_or_else(|| {
let home = std::env::var("HOME").unwrap_or_else(|_| ".".to_string());
PathBuf::from(home).join("Documents/gc-extracted")
});
if !data.exists() {
eprintln!("skipped: unpack the disc first");
return;
}
let mut patches = 0usize;
let mut triangles = 0usize;
let mut levels = 0usize;
for n in 0..27 {
let dir = data.join(format!("level{n}"));
let core = match std::fs::read(dir.join("core_data.bin")) {
Ok(c) => c,
Err(_) => continue,
};
let index = match std::fs::read(dir.join("core_index.bin")) {
Ok(i) => i,
Err(_) => continue,
};
let region =
|off: usize| i32::from_le_bytes(index[off..off + 4].try_into().unwrap()) as usize;
let start = region(0x08);
let end = [0x0c_usize, 0x10, 0x14]
.iter()
.map(|&o| region(o))
.filter(|&v| v > 0)
.min()
.unwrap_or(core.len());
let block = &core[start..end];
let header = gc_formats::tfrag::TfragsBlock::parse(block).expect("tfrags block header");
let table = header.table_offset as usize;
for i in 0..header.tfrag_count as usize {
let th = header.header(block, i).expect("tfrag header");
let data_base = table.wrapping_add(th.data as usize);
if data_base >= block.len() {
continue;
}
let g = gc_formats::tfrag::parse_tfrag(&block[data_base..], &th)
.unwrap_or_else(|e| panic!("level{n} patch {i}: {e}"));
let tris = gc_formats::tfrag::tfrag_triangles(&g, 0)
.unwrap_or_else(|e| panic!("level{n} patch {i}: {e}"));
assert_eq!(
tris.len(),
th.tri_count as usize,
"level{n} patch {i}: {} triangles, header says {}",
tris.len(),
th.tri_count
);
let vinfo = g.lod_vinfo_count(0);
for t in &tris {
let idx = [t.a as usize, t.b as usize, t.c as usize];
assert!(
idx.iter().all(|&v| v < vinfo),
"level{n} patch {i}: triangle index outside {vinfo} vertex-info entries"
);
assert!((t.ad_gif as usize) < g.ad_gifs.len());
}
patches += 1;
triangles += tris.len();
}
levels += 1;
}
assert!(levels > 0, "no unpacked levels were found");
assert!(patches > 18_000, "expected 18k+ patches, got {patches}");
assert!(
triangles > 700_000,
"expected 700k+ triangles, got {triangles}"
);
eprintln!("reproduced {triangles} triangles across {patches} patches in {levels} levels");
}
/// Texture bindings: every ad-gif a patch uses must index an entry that
/// actually exists in the level's texture table, and the light array must be
/// one record per vertex.
///
/// The texture table is the join between tfrags and the texel data, so an
/// out-of-range index here means the level's geometry and its textures have
/// been misread independently of each other.
#[test]
fn tfrag_ad_gifs_index_the_level_texture_table() {
require_disc!();
gc_formats::iso9660::IsoImage::open(std::path::Path::new(
&std::env::var("GC_DISC").expect("GC_DISC is set by require_disc!"),
))
.expect("ISO should open");
let data = std::env::var_os("GC_EXTRACTED")
.map(PathBuf::from)
.unwrap_or_else(|| {
let home = std::env::var("HOME").unwrap_or_else(|_| ".".to_string());
PathBuf::from(home).join("Documents/gc-extracted")
});
if !data.exists() {
eprintln!("skipped: unpack the disc first");
return;
}
let mut patches = 0usize;
let mut ad_gifs = 0usize;
let mut textures_seen = 0usize;
let mut textures_total = 0usize;
let mut levels = 0usize;
for n in 0..27 {
let dir = data.join(format!("level{n}"));
let core = match std::fs::read(dir.join("core_data.bin")) {
Ok(c) => c,
Err(_) => continue,
};
let index = match std::fs::read(dir.join("core_index.bin")) {
Ok(i) => i,
Err(_) => continue,
};
let ch = gc_formats::level_core::LevelCoreHeader::parse(&index).expect("core header");
let textures = gc_formats::level_core::texture_table(&index, ch.tfrag_textures)
.expect("texture table");
assert!(!textures.is_empty(), "level{n}: no tfrag textures");
// Indices are per-level, so the pair is what identifies a texture.
let mut level_seen = std::collections::BTreeSet::new();
let region =
|off: usize| i32::from_le_bytes(index[off..off + 4].try_into().unwrap()) as usize;
let start = region(0x08);
let end = [0x0c_usize, 0x10, 0x14]
.iter()
.map(|&o| region(o))
.filter(|&v| v > 0)
.min()
.unwrap_or(core.len());
let block = &core[start..end];
let header = gc_formats::tfrag::TfragsBlock::parse(block).expect("tfrags block header");
let table = header.table_offset as usize;
for i in 0..header.tfrag_count as usize {
let th = header.header(block, i).expect("tfrag header");
let data_base = table.wrapping_add(th.data as usize);
if data_base >= block.len() {
continue;
}
let g = gc_formats::tfrag::parse_tfrag(&block[data_base..], &th)
.unwrap_or_else(|e| panic!("level{n} patch {i}: {e}"));
assert_eq!(
g.lights.len(),
th.vert_count as usize,
"level{n} patch {i}: {} light records for {} vertices",
g.lights.len(),
th.vert_count
);
assert_eq!(
g.rgba.len(),
th.rgba_size as usize * 4,
"level{n} patch {i}: rgba"
);
for a in &g.ad_gifs {
let t = a.texture_index();
assert!(
t < textures.len(),
"level{n} patch {i}: texture {} outside the {} entry table",
t,
textures.len()
);
let tex = &textures[t];
assert!(
tex.width > 0 && tex.height > 0 && tex.width <= 256 && tex.height <= 256,
"level{n} patch {i}: texture {t} is {}x{}",
tex.width,
tex.height
);
level_seen.insert(t);
ad_gifs += 1;
}
patches += 1;
}
textures_seen += level_seen.len();
textures_total += textures.len();
levels += 1;
}
assert!(levels > 0, "no unpacked levels were found");
assert!(patches > 18_000, "expected 18k+ patches, got {patches}");
// Most of each level's texture table should be referenced by some tfrag. A
// handful genuinely go unused; if that share grows, the ad-gif walk has
// started missing primitives rather than the data having spare entries.
let covered = textures_seen as f64 / textures_total as f64;
assert!(
covered > 0.85,
"only {textures_seen} of {textures_total} level textures referenced ({:.1}%)",
covered * 100.0
);
eprintln!(
"{ad_gifs} ad-gifs over {patches} patches reference {textures_seen}/{textures_total} level textures"
);
}
/// Level textures decode: every tfrag texture's base level must resolve to a
/// plausible RGBA image.
///
/// This is the join between the texture table, the texel block and GS RAM, so
/// it is where a wrong CLUT remap, a wrong alpha scale or a wrong pixel base
/// would show up. The check is deliberately about *shape*, not specific
/// colours: a decoded image is plausible when it is fully opaque, is not
/// uniformly one colour, and uses more than a handful of distinct entries.
#[test]
fn tfrag_textures_decode_to_plausible_images() {
require_disc!();
gc_formats::iso9660::IsoImage::open(std::path::Path::new(
&std::env::var("GC_DISC").expect("GC_DISC is set by require_disc!"),
))
.expect("ISO should open");
let data = std::env::var_os("GC_EXTRACTED")
.map(PathBuf::from)
.unwrap_or_else(|| {
let home = std::env::var("HOME").unwrap_or_else(|_| ".".to_string());
PathBuf::from(home).join("Documents/gc-extracted")
});
if !data.exists() {
eprintln!("skipped: unpack the disc first");
return;
}
let mut decoded = 0usize;
let mut opaque = 0usize;
let mut multi_colour = 0usize;
let mut flat = 0usize;
for n in 0..27 {
let dir = data.join(format!("level{n}"));
let core = match std::fs::read(dir.join("core_data.bin")) {
Ok(c) => c,
Err(_) => continue,
};
let index = match std::fs::read(dir.join("core_index.bin")) {
Ok(i) => i,
Err(_) => continue,
};
let gs = match std::fs::read(dir.join("gs_ram.bin")) {
Ok(g) => g,
Err(_) => {
eprintln!("level{n}: no gs_ram.bin, skipping");
continue;
}
};
let ch = gc_formats::level_core::LevelCoreHeader::parse(&index).expect("core header");
let textures_at = ch.textures_base.max(0) as usize;
let texture_block = &core[textures_at..];
let table =
gc_formats::level_core::texture_table(&index, ch.tfrag_textures).expect("table");
for (i, e) in table.iter().enumerate() {
let img = gc_formats::texture::base_image(texture_block, &gs, e)
.unwrap_or_else(|err| panic!("level{n} texture {i}: {err}"));
let t = img.decode().unwrap();
let texels = (e.width as i32) * (e.height as i32);
assert_eq!(t.rgba.len(), (texels * 4) as usize);
assert_eq!(t.width, e.width as u32);
decoded += 1;
// Count distinct colours and how many texels are fully opaque.
let mut seen = std::collections::HashSet::new();
let mut op = 0usize;
for px in t.rgba.chunks_exact(4) {
seen.insert([px[0], px[1], px[2], px[3]]);
if px[3] == 0xff {
op += 1;
}
}
if seen.len() > 8 {
multi_colour += 1;
} else {
flat += 1;
}
if op == texels as usize {
opaque += 1;
}
}
}
assert!(decoded > 1_500, "only {decoded} textures decoded");
// Level art is mostly opaque and has real detail. A flat, transparent or
// single-colour result almost always means a CLUT or offset mistake.
let opaque_pct = opaque as f64 / decoded as f64;
let detail_pct = multi_colour as f64 / decoded as f64;
assert!(
opaque_pct > 0.9,
"only {opaque:.1}% of textures are fully opaque"
);
assert!(
detail_pct > 0.9,
"only {detail_pct:.1} of textures have >8 colours"
);
eprintln!(
"{decoded} textures decoded: {:.1}% fully opaque, {:.1}% with >8 colours ({flat} flat)",
opaque_pct * 100.0,
detail_pct * 100.0
);
}
/// LOD linkage: every LOD-01 and LOD-0 vertex-info entry must resolve to a
/// first parent that exists and to positions inside the patch.
///
/// The parent-index arrays are V4_8 unpacks separated from the strips and the
/// strip indices only by their VU address, so a misclassification here is
/// silent: the arrays still parse, they just hold the wrong numbers. Resolving
/// every entry is what catches it.
#[test]
fn tfrag_lod_parents_resolve_for_every_entry() {
require_disc!();
gc_formats::iso9660::IsoImage::open(std::path::Path::new(
&std::env::var("GC_DISC").expect("GC_DISC is set by require_disc!"),
))
.expect("ISO should open");
let data = std::env::var_os("GC_EXTRACTED")
.map(PathBuf::from)
.unwrap_or_else(|| {
let home = std::env::var("HOME").unwrap_or_else(|_| ".".to_string());
PathBuf::from(home).join("Documents/gc-extracted")
});
if !data.exists() {
eprintln!("skipped: unpack the disc first");
return;
}
let mut patches = 0usize;
let mut entries = 0usize;
let mut lod01 = 0usize;
let mut lod0 = 0usize;
let mut resolved_common = 0usize;
let mut common_total = 0usize;
let mut primary_failed = 0usize;
let mut extras_unresolved = 0usize;
for n in 0..27 {
let dir = data.join(format!("level{n}"));
let core = match std::fs::read(dir.join("core_data.bin")) {
Ok(c) => c,
Err(_) => continue,
};
let index = match std::fs::read(dir.join("core_index.bin")) {
Ok(i) => i,
Err(_) => continue,
};
let region =
|off: usize| i32::from_le_bytes(index[off..off + 4].try_into().unwrap()) as usize;
let start = region(0x08);
let end = [0x0c_usize, 0x10, 0x14]
.iter()
.map(|&o| region(o))
.filter(|&v| v > 0)
.min()
.unwrap_or(core.len());
let block = &core[start..end];
let header = gc_formats::tfrag::TfragsBlock::parse(block).expect("tfrags block");
let table = header.table_offset as usize;
for i in 0..header.tfrag_count as usize {
let th = header.header(block, i).expect("tfrag header");
let data_base = table.wrapping_add(th.data as usize);
if data_base >= block.len() {
continue;
}
let g = gc_formats::tfrag::parse_tfrag(&block[data_base..], &th)
.unwrap_or_else(|e| panic!("level{n} patch {i}: {e}"));
common_total += g.vinfo_tier[0];
if n == 0 && patches < 5 {
eprintln!(
"p{i}: tier={:?} n01={} n0={} p01={}b x01={}b p0={}b x0={}b",
g.vinfo_tier,
g.vu_positions_lod_01_count,
g.vu_positions_lod_0_count,
g.parent_indices_lod01.len(),
g.unk_indices_2_lod01.len(),
g.parent_indices_lod0.len(),
g.unk_indices_2_lod0.len()
);
}
for v in 0..g.vertex_info.len() {
entries += 1;
match gc_formats::tfrag::tfrag_lod_link(&g, v) {
Some(link) => {
if v < g.vinfo_tier[0] {
resolved_common += 1;
}
// Parents must index real vertex info and real positions.
assert!(
link.parent1_vinfo < g.vertex_info.len(),
"level{n} patch {i}: entry {v} parent {} outside {} entries",
link.parent1_vinfo,
g.vertex_info.len()
);
assert!(link.own_position < g.positions.len());
assert!(link.parent1_position < g.positions.len());
assert!(link.parent2_position < g.positions.len());
// The first parent of a LOD-01 entry is always a common one.
if link.tier == gc_formats::tfrag::TfragMorphTier::Lod01 {
assert!(
link.parent1_vinfo < g.vinfo_tier[0],
"level{n} patch {i}: LOD-01 entry {v} parent {} is not a common entry",
link.parent1_vinfo
);
lod01 += 1;
} else {
lod0 += 1;
}
}
None => {
// Distinguish the two kinds of LOD entry. A *primary*
// entry has a real position and a recorded parent and
// must always resolve; an *extra* entry is a
// non-position bookkeeping record whose array address
// can collide with the strip index array.
let c = g.vinfo_tier[0];
let kind = if v < c {
None
} else if v < c + g.vinfo_tier[1] {
Some((g.vu_positions_lod_01_count, v - c, true))
} else {
Some((g.vu_positions_lod_0_count, v - c - g.vinfo_tier[1], false))
};
match kind {
None => {}
Some((prim, k, _)) if k < prim => primary_failed += 1,
Some(_) => extras_unresolved += 1,
}
}
}
}
patches += 1;
}
}
assert!(patches > 18_000, "expected 18k+ patches, got {patches}");
// A common entry never has a link: they are the full-detail positions and
// have no parent. Anything else means the tier boundaries are wrong.
assert!(
resolved_common == 0,
"{resolved_common} common entries claimed an LOD parent"
);
assert!(
lod01 > 0 && lod0 > 0,
"both LOD tiers should occur in the data"
);
assert_eq!(
primary_failed, 0,
"{primary_failed} primary LOD entries did not resolve"
);
assert_eq!(
extras_unresolved, 0,
"{extras_unresolved} extra LOD entries did not resolve"
);
// Common entries have no link; every other entry does.
assert_eq!(entries, common_total + lod01 + lod0);
eprintln!(
"{entries} vertex-info entries over {patches} patches: {common_total} common, \
{lod01} LOD-01 and {lod0} LOD-0, all resolved"
);
}
/// The level core index's class tables.
///
/// These are what put the environment on top of the terrain: tie instances,
/// moby actors and shrub foliage. They were ruled out earlier for want of an
/// entry size, which turned out to be knowable exactly.
///
/// The check is the chain: each table must end precisely where the next one
/// begins, moby (32 bytes/entry) into tie (32) into shrub (48) into the tfrag
/// texture table. That closes on all 27 levels and would not close if any
/// entry size were wrong, so it is the evidence rather than a coincidence.
#[test]
fn level_core_class_tables_tile_the_index() {
require_disc!();
gc_formats::iso9660::IsoImage::open(std::path::Path::new(
&std::env::var("GC_DISC").expect("GC_DISC is set by require_disc!"),
))
.expect("ISO should open");
let data = std::env::var_os("GC_EXTRACTED")
.map(PathBuf::from)
.unwrap_or_else(|| {
let home = std::env::var("HOME").unwrap_or_else(|_| ".".to_string());
PathBuf::from(home).join("Documents/gc-extracted")
});
if !data.exists() {
eprintln!("skipped: unpack the disc first");
return;
}
use gc_formats::level_core as lc;
let mut levels = 0usize;
let (mut moby, mut tie, mut shrub, mut textures) = (0usize, 0usize, 0usize, 0usize);
for n in 0..27 {
let dir = data.join(format!("level{n}"));
let Ok(index) = std::fs::read(dir.join("core_index.bin")) else {
continue;
};
let h = lc::LevelCoreHeader::parse(&index).expect("core header");
let end = |r: lc::ArrayRange, size: usize| r.offset as usize + r.count as usize * size;
assert_eq!(
end(h.moby_classes, lc::MOBY_CLASS_SIZE),
h.tie_classes.offset as usize,
"level{n}: moby -> tie"
);
assert_eq!(
end(h.tie_classes, lc::TIE_CLASS_SIZE),
h.shrub_classes.offset as usize,
"level{n}: tie -> shrub"
);
assert_eq!(
end(h.shrub_classes, lc::SHRUB_CLASS_SIZE),
h.tfrag_textures.offset as usize,
"level{n}: shrub -> textures"
);
// Every entry parses, and its asset offset lands inside the level.
if n == 0 {
eprintln!(
"hdr moby={:?} tie={:?} shrub={:?} tex={:?} base={}",
h.moby_classes, h.tie_classes, h.shrub_classes, h.tfrag_textures, h.textures_base
);
eprintln!("index[192..200] = {:?}", &index[192..200]);
}
let moby_v = lc::class_table(
&index,
h.moby_classes,
lc::MOBY_CLASS_SIZE,
lc::ClassEntry::parse,
)
.expect("moby classes");
let tie_v = lc::class_table(
&index,
h.tie_classes,
lc::TIE_CLASS_SIZE,
lc::ClassEntry::parse,
)
.expect("tie classes");
let shrub_v = lc::class_table(
&index,
h.shrub_classes,
lc::SHRUB_CLASS_SIZE,
lc::ShrubClassEntry::parse,
)
.expect("shrub classes");
let tex_v = lc::texture_table(&index, h.tfrag_textures).expect("tfrag textures");
assert_eq!(moby_v.len(), h.moby_classes.count as usize);
for (i, c) in moby_v.iter().chain(tie_v.iter()).enumerate() {
assert!(
c.offset_in_asset_wad >= 0,
"level{n} entry {i}: asset offset {}",
c.offset_in_asset_wad
);
}
// Billboard slots are optional: every shrub class on level 0 carries
// them all zero, so only their sign is meaningful here.
for s in &shrub_v {
assert!(s.base.offset_in_asset_wad >= 0);
assert!(
s.palette_offset >= -1 && s.texture_offset >= -1,
"level{n}: shrub billboard offsets below the -1 sentinel"
);
}
moby += moby_v.len();
tie += tie_v.len();
shrub += shrub_v.len();
textures += tex_v.len();
levels += 1;
}
assert_eq!(levels, 27, "expected all 27 levels, got {levels}");
assert!(
moby + tie + shrub > 1000,
"only {moby}+{tie}+{shrub} class entries"
);
eprintln!(
"level core index: {moby} moby, {tie} tie, {shrub} shrub classes, \
{textures} tfrag textures across {levels} levels"
);
}
/// The moby, tie and shrub class tables point into `core_data`, and they do so
/// without overlapping.
///
/// `assets_decompressed_size` is the size of `core_data` itself, so there is
/// no separate asset container: the class entries index the decompressed asset
/// lump directly. If that is right, every offset must land inside the lump, the
/// three tables must occupy disjoint spans, and each must be internally sorted
/// so the geometry is laid out in class order.
#[test]
fn class_geometry_offsets_tile_core_data_without_overlap() {
require_disc!();
gc_formats::iso9660::IsoImage::open(std::path::Path::new(
&std::env::var("GC_DISC").expect("GC_DISC is set by require_disc!"),
))
.expect("ISO should open");
let data = std::env::var_os("GC_EXTRACTED")
.map(PathBuf::from)
.unwrap_or_else(|| {
let home = std::env::var("HOME").unwrap_or_else(|_| ".".to_string());
PathBuf::from(home).join("Documents/gc-extracted")
});
if !data.exists() {
eprintln!("skipped: unpack the disc first");
return;
}
use gc_formats::level_core as lc;
let mut levels = 0usize;
for n in 0..27 {
let dir = data.join(format!("level{n}"));
let (Ok(index), Ok(core)) = (
std::fs::read(dir.join("core_index.bin")),
std::fs::read(dir.join("core_data.bin")),
) else {
continue;
};
let h = lc::LevelCoreHeader::parse(&index).expect("core header");
// The claim under test: the "asset lump" is core_data itself.
assert_eq!(
h.assets_decompressed_size as usize,
core.len(),
"level{n}: assets_decompressed_size is not core_data's length"
);
let span = |r: lc::ArrayRange, size: usize| -> Vec<usize> {
lc::class_table(&index, r, size, lc::ClassEntry::parse)
.unwrap_or_default()
.iter()
.map(|c| c.offset_in_asset_wad as usize)
.collect()
};
// Shrub entries are read as ShrubClassEntry so the offsets line up.
let shrub: Vec<usize> = lc::class_table(
&index,
h.shrub_classes,
lc::SHRUB_CLASS_SIZE,
lc::ShrubClassEntry::parse,
)
.unwrap_or_default()
.iter()
.map(|s| s.base.offset_in_asset_wad as usize)
.collect();
let moby = span(h.moby_classes, lc::MOBY_CLASS_SIZE);
let tie = span(h.tie_classes, lc::TIE_CLASS_SIZE);
// An offset of 0 marks a slot with no geometry rather than the start of
// the lump, so those are excluded from the span checks. Entries are not
// sorted by class number and the offsets are not monotonic, so nothing
// here assumes an order.
let moby_l: Vec<usize> = moby.iter().copied().filter(|&o| o != 0).collect();
let tie_l: Vec<usize> = tie.iter().copied().filter(|&o| o != 0).collect();
let shrub_l: Vec<usize> = shrub.iter().copied().filter(|&o| o != 0).collect();
for (name, v) in [("moby", &moby), ("tie", &tie), ("shrub", &shrub)] {
for &o in v {
assert!(
o < core.len(),
"level{n}: {name} offset {o} past core data ({})",
core.len()
);
}
}
// The three spans must not overlap each other.
for (an, a) in [("moby", &moby_l), ("tie", &tie_l), ("shrub", &shrub_l)] {
for (bn, b) in [("moby", &moby_l), ("tie", &tie_l), ("shrub", &shrub_l)] {
// A level may have no geometry of one kind at all.
if an >= bn || a.is_empty() || b.is_empty() {
continue;
}
let (lo, hi) = (a[0], *a.last().unwrap());
for &o in b {
assert!(
o >= hi || o < lo,
"level{n}: {an} [{lo},{hi}] overlaps {bn} at {o}"
);
}
}
}
levels += 1;
}
assert_eq!(levels, 27, "expected all 27 levels, got {levels}");
eprintln!("class geometry offsets verified inside core_data on {levels} levels");
}