Files
guara/crates/guara-core/tests/vdisk.rs
T
Lucas RayanandClaude Sonnet 5.5 4bec3e971a Discos virtuais: arquivo de apoio do QCOW2, snapshots de VMDK e DMG com LZFSE
QCOW2 e VMDK filhos leem o pai no que não alocaram (o QCOW2 respeita o formato do apoio;
o VMDK acha o pai por nome ou, no VirtualBox, por UUID, e recusa o filho se o CID do pai
mudou). Chunks LZFSE do DMG usam lzfse_rust, conferidos com dados do compressor de
referência da Apple. Snapshot real do VirtualBox entra como fixture.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 07:55:58 -03:00

918 lines
31 KiB
Rust

//! Imagens de disco virtual: QCOW2, VMDK, VHD, VHDX e DMG.
//!
//! Os arquivos de `tests/fixtures/vdisk` foram feitos por ferramentas reais (VirtualBox para
//! VMDK/VHD, qemu para QCOW2, hdiutil para DMG) e conferidos contra o conteúdo bruto. VHDX, DMG
//! sintético e discos diferenciais são montados aqui, byte a byte, a partir da especificação.
//! As imagens do dfvfs em target/testdata (scripts/fetch-testdata.sh) são conferidas por hash,
//! calculado com um leitor independente (7-Zip), e pulam quando ausentes.
use guara_core::source::{open_path, read_vec, Source};
use sha2::{Digest, Sha256};
use std::io::Write;
use std::path::{Path, PathBuf};
fn fx(name: &str) -> PathBuf {
PathBuf::from(env!("CARGO_MANIFEST_DIR"))
.join("tests/fixtures/vdisk")
.join(name)
}
fn raw() -> Vec<u8> {
std::fs::read(fx("disk.raw")).unwrap()
}
fn dfvfs(name: &str) -> Option<PathBuf> {
let p = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
.join("../../target/testdata/dfvfs")
.join(name);
p.exists().then_some(p)
}
fn sha(src: &dyn Source) -> String {
let mut h = Sha256::new();
let mut off = 0;
while off < src.size() {
let n = (1 << 20).min((src.size() - off) as usize);
h.update(read_vec(src, off, n).unwrap());
off += n as u64;
}
h.finalize().iter().map(|b| format!("{b:02x}")).collect()
}
/// Lê o disco inteiro e também em pedaços que cruzam blocos, comparando com `want`.
fn check_content(path: &Path, want: &[u8]) {
let s = open_path(path).unwrap_or_else(|e| panic!("{}: {e}", path.display()));
assert_eq!(s.size(), want.len() as u64, "{}", path.display());
assert!(
read_vec(s.as_ref(), 0, want.len()).unwrap() == want,
"{}: conteúdo difere",
path.display()
);
let mut x = 88172645463325252u64;
for _ in 0..200 {
x ^= x << 13;
x ^= x >> 7;
x ^= x << 17;
let off = x % want.len() as u64;
let len = 1 + (x >> 20) as usize % 70_000;
let end = (off as usize + len).min(want.len());
let got = read_vec(s.as_ref(), off, end - off as usize).unwrap();
assert!(
got == want[off as usize..end],
"{}: @{off}+{len}",
path.display()
);
}
// leitura além do fim devolve só o que existe
let mut buf = [0u8; 64];
assert_eq!(s.read_at(want.len() as u64 - 10, &mut buf).unwrap(), 10);
assert_eq!(s.read_at(want.len() as u64, &mut buf).unwrap(), 0);
}
// ---------- imagens feitas por ferramentas reais ----------
#[test]
fn virtualbox_vmdk_sparse_and_stream_optimized() {
let want = raw();
check_content(&fx("disk.vmdk"), &want);
// streamOptimized: grãos comprimidos com zlib e cabeçalho no rodapé
check_content(&fx("disk-stream.vmdk"), &want);
}
#[test]
fn virtualbox_vhd_dynamic() {
check_content(&fx("disk.vhd"), &raw());
}
#[test]
fn qemu_qcow2_and_hdiutil_dmg_match_a_reference_reader() {
let s = open_path(&fx("ext2.qcow2")).unwrap();
assert_eq!(s.size(), 4 << 20);
assert_eq!(
sha(s.as_ref()),
"a6c2f0e39afe6c6ab432ca5465349fcefe8dc944398e97b2d957d3f89dbb5d80"
);
// UDIF com chunks zlib, zerados e ignorados
let d = open_path(&fx("hfsplus_zlib.dmg")).unwrap();
assert_eq!(d.size(), 1_954_304);
assert_eq!(
sha(d.as_ref()),
"c86d3616818e175caca2f6022f49e190e5b1cfe39b2e8f9373119e22aa7eaf58"
);
}
// ---------- montagem de imagens sintéticas ----------
fn be(v: &mut [u8], o: usize, x: u64, n: usize) {
v[o..o + n].copy_from_slice(&x.to_be_bytes()[8 - n..]);
}
fn le(v: &mut [u8], o: usize, x: u64, n: usize) {
v[o..o + n].copy_from_slice(&x.to_le_bytes()[..n]);
}
fn deflate(data: &[u8]) -> Vec<u8> {
let mut e = flate2::write::DeflateEncoder::new(vec![], flate2::Compression::default());
e.write_all(data).unwrap();
e.finish().unwrap()
}
fn zlib(data: &[u8]) -> Vec<u8> {
let mut e = flate2::write::ZlibEncoder::new(vec![], flate2::Compression::default());
e.write_all(data).unwrap();
e.finish().unwrap()
}
/// QCOW2 v3 com clusters de 64 KiB: zerados (sem entrada e com a flag), brutos e comprimidos.
fn build_qcow2(data: &[u8]) -> Vec<u8> {
const CS: usize = 1 << 16;
let clusters = data.len() / CS;
let mut img = vec![0u8; 3 * CS];
img[..4].copy_from_slice(b"QFI\xfb");
be(&mut img, 4, 3, 4);
be(&mut img, 20, 16, 4);
be(&mut img, 24, data.len() as u64, 8);
be(&mut img, 36, 1, 4);
be(&mut img, 40, CS as u64, 8);
be(&mut img, 100, 112, 4);
be(&mut img, CS, (2 * CS as u64) | (1 << 63), 8); // L1 -> L2 no cluster 2
for i in 0..clusters {
let c = &data[i * CS..(i + 1) * CS];
let entry: u64 = if c.iter().all(|&b| b == 0) {
if i % 2 == 0 {
0
} else {
1 // zerado explícito
}
} else if i % 3 == 0 {
let z = deflate(c);
let host = img.len() as u64;
let sectors = z.len().div_ceil(512);
img.extend_from_slice(&z);
img.resize(img.len().div_ceil(512) * 512, 0);
1 << 62 | ((sectors as u64 - 1) << (62 - 8)) | host
} else {
let host = img.len() as u64;
img.extend_from_slice(c);
host | 1 << 63
};
be(&mut img, 2 * CS + i * 8, entry, 8);
}
img
}
fn vhd_footer(size: u64, kind: u32, data_offset: u64) -> [u8; 512] {
let mut f = [0u8; 512];
f[..8].copy_from_slice(b"conectix");
be(&mut f, 8, 2, 4);
be(&mut f, 12, 0x0001_0000, 4);
be(&mut f, 16, data_offset, 8);
f[28..32].copy_from_slice(b"guar");
be(&mut f, 40, size, 8);
be(&mut f, 48, size, 8);
be(&mut f, 60, kind as u64, 4);
let sum = f.iter().fold(0u32, |a, &b| a.wrapping_add(b as u32));
be(&mut f, 64, !sum as u64, 4);
f
}
fn base64(d: &[u8]) -> String {
const T: &[u8] = b"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
let mut s = String::new();
for c in d.chunks(3) {
let n = (c[0] as u32) << 16
| (*c.get(1).unwrap_or(&0) as u32) << 8
| *c.get(2).unwrap_or(&0) as u32;
for i in 0..4 {
if i <= c.len() {
s.push(T[(n >> (18 - 6 * i) & 63) as usize] as char);
} else {
s.push('=');
}
}
if s.len() % 76 == 0 {
s.push('\n');
}
}
s
}
/// ADC só com literais e cópias de 3 bytes (deslocamento 8), como o `hdiutil` produz.
fn adc_pattern(len: usize) -> (Vec<u8>, Vec<u8>) {
let pat = *b"ADC-test";
let mut enc = vec![0x80 | 7];
enc.extend_from_slice(&pat);
let mut made = 8;
while made < len {
let rem = len - made;
let mut n = rem.min(67);
if rem - n > 0 && rem - n < 3 {
n = rem - 3;
}
if n >= 4 {
enc.extend_from_slice(&[0x40 | (n as u8 - 4), 0, 7]);
} else {
enc.extend_from_slice(&[((n as u8 - 3) << 2), 7]); // 2 bytes, comprimento 3
}
made += n;
}
let want: Vec<u8> = (0..len).map(|i| pat[i % 8]).collect();
(enc, want)
}
struct DmgChunk {
ty: u32,
sectors: u64,
payload: Vec<u8>,
}
fn build_dmg(chunks: &[DmgChunk], total_sectors: u64) -> Vec<u8> {
let mut fork = vec![];
let mut table = vec![0u8; 204];
table[..4].copy_from_slice(b"mish");
be(&mut table, 4, 1, 4);
be(&mut table, 16, total_sectors, 8);
be(&mut table, 200, chunks.len() as u64 + 1, 4);
let mut sector = 0;
for c in chunks {
let mut e = [0u8; 40];
be(&mut e, 0, c.ty as u64, 4);
be(&mut e, 8, sector, 8);
be(&mut e, 16, c.sectors, 8);
be(&mut e, 24, fork.len() as u64, 8);
be(&mut e, 32, c.payload.len() as u64, 8);
table.extend_from_slice(&e);
fork.extend_from_slice(&c.payload);
sector += c.sectors;
}
let mut end = [0u8; 40];
be(&mut end, 0, 0xFFFF_FFFF, 4);
be(&mut end, 8, sector, 8);
table.extend_from_slice(&end);
let xml = format!(
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<plist version=\"1.0\"><dict><key>resource-fork</key><dict>\
<key>blkx</key><array><dict><key>Data</key><data>\n{}\n</data><key>Name</key><string>teste</string></dict></array>\
<key>plst</key><array><dict><key>Data</key><data>AAAA</data></dict></array></dict></dict></plist>",
base64(&table)
);
let mut img = fork;
let xml_off = img.len() as u64;
img.extend_from_slice(xml.as_bytes());
let mut k = vec![0u8; 512];
k[..4].copy_from_slice(b"koly");
be(&mut k, 4, 4, 4);
be(&mut k, 8, 512, 4);
be(&mut k, 32, xml_off, 8);
be(&mut k, 216, xml_off, 8);
be(&mut k, 224, xml.len() as u64, 8);
be(&mut k, 492, total_sectors, 8);
img.extend_from_slice(&k);
img
}
// ---------- QCOW2 ----------
#[test]
fn qcow2_with_zero_raw_and_compressed_clusters() {
let want = raw();
let dir = tempfile::tempdir().unwrap();
let p = dir.path().join("t.qcow2");
std::fs::write(&p, build_qcow2(&want)).unwrap();
check_content(&p, &want);
}
#[test]
fn qcow2_with_encryption_or_a_remote_backing_file_is_refused() {
let dir = tempfile::tempdir().unwrap();
let mut img = build_qcow2(&raw());
be(&mut img, 32, 2, 4);
let p = dir.path().join("e.qcow2");
std::fs::write(&p, &img).unwrap();
let e = open_path(&p).err().expect("deveria recusar").to_string();
assert!(e.contains("LUKS"), "{e}");
let mut img = build_qcow2(&raw());
let name = b"nbd://servidor/disco";
img[512..512 + name.len()].copy_from_slice(name);
be(&mut img, 8, 512, 8);
be(&mut img, 16, name.len() as u64, 4);
let p = dir.path().join("r.qcow2");
std::fs::write(&p, &img).unwrap();
let e = open_path(&p).err().expect("deveria recusar").to_string();
assert!(e.contains("não é um arquivo local"), "{e}");
}
/// Filho QCOW2 que só aloca o cluster 1 (dados), marca o 2 como zerado e deixa o resto para o pai.
fn build_qcow2_child(backing: &str, fmt: Option<&str>, own: &[u8]) -> Vec<u8> {
const CS: usize = 1 << 16;
let mut img = vec![0u8; 3 * CS];
img[..4].copy_from_slice(b"QFI\xfb");
be(&mut img, 4, 3, 4);
be(&mut img, 16, backing.len() as u64, 4);
be(&mut img, 8, 1024, 8);
img[1024..1024 + backing.len()].copy_from_slice(backing.as_bytes());
be(&mut img, 20, 16, 4);
be(&mut img, 24, 16 * CS as u64, 8);
be(&mut img, 36, 1, 4);
be(&mut img, 40, CS as u64, 8);
be(&mut img, 100, 112, 4);
if let Some(f) = fmt {
// extensão 0xE2792ACA com o nome do formato do apoio, depois o fim das extensões
be(&mut img, 112, 0xE279_2ACA, 4);
be(&mut img, 116, f.len() as u64, 4);
img[120..120 + f.len()].copy_from_slice(f.as_bytes());
}
be(&mut img, CS, (2 * CS as u64) | (1 << 63), 8);
let host = img.len() as u64;
img.extend_from_slice(own);
img.resize(img.len().div_ceil(CS) * CS, 0);
be(&mut img, 2 * CS + 8, host | (1 << 63), 8); // cluster 1
be(&mut img, 2 * CS + 16, 1, 8); // cluster 2: zerado de propósito
img
}
#[test]
fn qcow2_backing_file_supplies_what_the_child_did_not_allocate() {
const CS: usize = 1 << 16;
let base = raw();
let dir = tempfile::tempdir().unwrap();
std::fs::write(dir.path().join("base.raw"), &base).unwrap();
let own = vec![0x42u8; CS];
let mut expect = base.clone();
expect[CS..2 * CS].copy_from_slice(&own);
expect[2 * CS..3 * CS].fill(0);
for (name, fmt) in [("a.qcow2", Some("raw")), ("b.qcow2", None)] {
let p = dir.path().join(name);
std::fs::write(&p, build_qcow2_child("base.raw", fmt, &own)).unwrap();
check_content(&p, &expect);
}
// com o pai em outro formato: o filho aponta para um QCOW2
std::fs::write(dir.path().join("base.qcow2"), build_qcow2(&base)).unwrap();
let p = dir.path().join("c.qcow2");
std::fs::write(&p, build_qcow2_child("base.qcow2", Some("qcow2"), &own)).unwrap();
check_content(&p, &expect);
// sem o pai, a abertura diz o que falta
std::fs::remove_file(dir.path().join("base.raw")).unwrap();
let e = open_path(&dir.path().join("a.qcow2"))
.err()
.unwrap()
.to_string();
assert!(e.contains("disco pai não encontrado"), "{e}");
}
// ---------- VMDK ----------
#[test]
fn vmdk_descriptor_with_flat_and_zero_extents() {
let want = raw();
let dir = tempfile::tempdir().unwrap();
let half = want.len() / 2;
std::fs::write(dir.path().join("a-f001.vmdk"), &want[..half]).unwrap();
std::fs::write(
dir.path().join("a-f002.vmdk"),
&want[half..want.len() - 4096],
)
.unwrap();
let desc = format!(
"# Disk DescriptorFile\nversion=1\nCID=fffffffe\nparentCID=ffffffff\ncreateType=\"twoGbMaxExtentFlat\"\n\n# Extent description\nRW {} FLAT \"a-f001.vmdk\" 0\nRW {} FLAT \"a-f002.vmdk\" 0\nRW 8 ZERO\n",
half / 512,
(want.len() - 4096 - half) / 512
);
let p = dir.path().join("a.vmdk");
std::fs::write(&p, desc).unwrap();
let mut expect = want.clone();
expect[want.len() - 4096..].fill(0);
check_content(&p, &expect);
}
/// VMDK esparso feito à mão: 16 grãos de 64 KiB; `grains[i]` = `None` (não alocado, vem do pai),
/// `Some(None)` (zerado de propósito) ou `Some(Some(dados))`.
fn build_vmdk_sparse(descriptor: &str, grains: &[Option<Option<Vec<u8>>>]) -> Vec<u8> {
const GRAIN: usize = 128; // setores
let mut img = vec![0u8; 26 * 512];
img[..4].copy_from_slice(b"KDMV");
le(&mut img, 4, 1, 4);
le(&mut img, 8, 3, 4);
le(&mut img, 12, (grains.len() * GRAIN) as u64, 8);
le(&mut img, 20, GRAIN as u64, 8);
le(&mut img, 28, 1, 8);
le(&mut img, 36, 20, 8);
le(&mut img, 44, 512, 4);
le(&mut img, 56, 21, 8);
le(&mut img, 64, 26, 8);
img[512..512 + descriptor.len()].copy_from_slice(descriptor.as_bytes());
le(&mut img, 21 * 512, 22, 4); // diretório de grãos -> tabela no setor 22
for (i, g) in grains.iter().enumerate() {
let entry = match g {
None => 0,
Some(None) => 1,
Some(Some(d)) => {
let sector = (img.len() / 512) as u64;
let mut d = d.clone();
d.resize(GRAIN * 512, 0);
img.extend_from_slice(&d);
sector
}
};
le(&mut img, 22 * 512 + i * 4, entry, 4);
}
img
}
#[test]
fn vmdk_child_reads_the_parent_for_unallocated_grains() {
let base = raw();
let dir = tempfile::tempdir().unwrap();
std::fs::write(dir.path().join("base.vmdk"), build_vmdk_sparse(
"# Disk DescriptorFile\nversion=1\nCID=11111111\nparentCID=ffffffff\ncreateType=\"monolithicSparse\"\n",
&(0..16)
.map(|i| Some(Some(base[i * 65536..(i + 1) * 65536].to_vec())))
.collect::<Vec<_>>(),
))
.unwrap();
let own = vec![0x37u8; 65536];
let mut grains: Vec<Option<Option<Vec<u8>>>> = vec![None; 16];
grains[3] = Some(Some(own.clone()));
grains[5] = Some(None); // zerado de propósito: não consulta o pai
let child = build_vmdk_sparse(
"# Disk DescriptorFile\nversion=1\nCID=22222222\nparentCID=11111111\ncreateType=\"monolithicSparse\"\nparentFileNameHint=\"base.vmdk\"\n",
&grains,
);
let p = dir.path().join("child.vmdk");
std::fs::write(&p, child).unwrap();
let mut expect = base.clone();
expect[3 * 65536..4 * 65536].copy_from_slice(&own);
expect[5 * 65536..6 * 65536].fill(0);
check_content(&p, &expect);
}
/// Snapshot real do VirtualBox: o filho só diz o UUID do pai (`ddb.uuid.parent`), sem nome.
#[test]
fn virtualbox_snapshot_vmdk_finds_its_parent_by_uuid() {
let dir = tempfile::tempdir().unwrap();
let sub = dir.path().join("Snapshots");
std::fs::create_dir(&sub).unwrap();
// o pai fica na pasta de cima, como o VirtualBox organiza a máquina
std::fs::copy(fx("disk.vmdk"), dir.path().join("disco-base.vmdk")).unwrap();
std::fs::copy(fx("vbox-snapshot.vmdk"), sub.join("filho.vmdk")).unwrap();
check_content(&sub.join("filho.vmdk"), &raw());
// sem o pai por perto, a abertura explica
std::fs::remove_file(dir.path().join("disco-base.vmdk")).unwrap();
let e = open_path(&sub.join("filho.vmdk"))
.err()
.unwrap()
.to_string();
assert!(e.contains("identificado só por UUID"), "{e}");
}
#[test]
fn vmdk_child_is_refused_when_the_parent_changed() {
let dir = tempfile::tempdir().unwrap();
std::fs::write(
dir.path().join("base.vmdk"),
build_vmdk_sparse(
"# Disk DescriptorFile\nversion=1\nCID=aaaaaaaa\nparentCID=ffffffff\ncreateType=\"monolithicSparse\"\n",
&vec![None; 16],
),
)
.unwrap();
std::fs::write(
dir.path().join("filho.vmdk"),
build_vmdk_sparse(
"# Disk DescriptorFile\nversion=1\nCID=bbbbbbbb\nparentCID=11111111\ncreateType=\"monolithicSparse\"\nparentFileNameHint=\"base.vmdk\"\n",
&vec![None; 16],
),
)
.unwrap();
let e = open_path(&dir.path().join("filho.vmdk"))
.err()
.unwrap()
.to_string();
assert!(e.contains("foi alterado depois do filho"), "{e}");
}
#[test]
fn vmdk_with_a_parent_but_no_name_is_refused() {
let dir = tempfile::tempdir().unwrap();
let p = dir.path().join("c.vmdk");
std::fs::write(
&p,
"# Disk DescriptorFile\nversion=1\nparentCID=12345678\ncreateType=\"monolithicFlat\"\nRW 8 ZERO\n",
)
.unwrap();
let e = open_path(&p).err().expect("deveria recusar").to_string();
assert!(e.contains("não diz qual"), "{e}");
}
// ---------- VHD ----------
#[test]
fn vhd_fixed_hides_the_footer() {
let want = raw();
let mut img = want.clone();
img.extend_from_slice(&vhd_footer(want.len() as u64, 2, u64::MAX));
let dir = tempfile::tempdir().unwrap();
let p = dir.path().join("f.vhd");
std::fs::write(&p, img).unwrap();
check_content(&p, &want);
}
/// VHD diferencial: a filha só traz o setor 100 e o bloco inteiro do fim; o resto vem do pai.
#[test]
fn vhd_differencing_reads_the_parent_for_missing_sectors() {
let want = raw();
let dir = tempfile::tempdir().unwrap();
let mut parent = want.clone();
parent.extend_from_slice(&vhd_footer(want.len() as u64, 2, u64::MAX));
std::fs::write(dir.path().join("pai.vhd"), &parent).unwrap();
const BLOCK: usize = 1 << 20; // um bloco só
let mut f = vec![0u8; 512 + 1024 + 512];
let hdr = vhd_footer(want.len() as u64, 4, 512);
f[..512].copy_from_slice(&hdr);
let mut dh = [0u8; 1024];
dh[..8].copy_from_slice(b"cxsparse");
be(&mut dh, 8, u64::MAX, 8);
be(&mut dh, 16, 1536, 8); // BAT
be(&mut dh, 28, 1, 4);
be(&mut dh, 32, BLOCK as u64, 4);
let name = "pai.vhd"
.encode_utf16()
.flat_map(|u| u.to_be_bytes())
.collect::<Vec<u8>>();
dh[64..64 + name.len()].copy_from_slice(&name);
f[512..1536].copy_from_slice(&dh);
be(&mut f, 1536, 4, 4); // bloco 0 no setor 4
f.resize(4 * 512, 0);
// bitmap (4096 setores = 512 bytes) com o setor 100 presente, depois os dados
let mut bitmap = vec![0u8; 512];
bitmap[100 / 8] |= 0x80 >> (100 % 8);
f.extend_from_slice(&bitmap);
let mut block = vec![0u8; BLOCK];
let marker = [0xA5u8; 512];
block[100 * 512..101 * 512].copy_from_slice(&marker);
f.extend_from_slice(&block);
f.extend_from_slice(&hdr);
let p = dir.path().join("filho.vhd");
std::fs::write(&p, f).unwrap();
let mut expect = want.clone();
expect[100 * 512..101 * 512].copy_from_slice(&marker);
check_content(&p, &expect);
// sem o pai a abertura falha com o motivo
std::fs::remove_file(dir.path().join("pai.vhd")).unwrap();
let e = open_path(&p).err().expect("deveria recusar").to_string();
assert!(e.contains("disco pai não encontrado"), "{e}");
}
// ---------- VHDX ----------
fn guid(s: &str) -> [u8; 16] {
let h: Vec<u8> = s
.replace('-', "")
.as_bytes()
.chunks(2)
.map(|p| u8::from_str_radix(std::str::from_utf8(p).unwrap(), 16).unwrap())
.collect();
let mut g = [0u8; 16];
g[..4].copy_from_slice(&[h[3], h[2], h[1], h[0]]);
g[4..6].copy_from_slice(&[h[5], h[4]]);
g[6..8].copy_from_slice(&[h[7], h[6]]);
g[8..].copy_from_slice(&h[8..]);
g
}
const MB: usize = 1 << 20;
/// VHDX com blocos de 1 MiB. `blocks[i]`: `None` = não presente, `Some((estado, dados))`.
/// Com `parent`, acrescenta o localizador de pai e o bitmap de setores (`bitmap`).
fn build_vhdx(
size: u64,
blocks: &[Option<(u64, Vec<u8>)>],
parent: Option<&str>,
bitmap: Option<Vec<u8>>,
) -> Vec<u8> {
let mut img = vec![0u8; 4 * MB];
img[..8].copy_from_slice(b"vhdxfile");
img[64 * 1024..64 * 1024 + 4].copy_from_slice(b"head");
img[128 * 1024..128 * 1024 + 4].copy_from_slice(b"head");
// tabela de regiões: BAT em 2 MiB, metadados em 1 MiB
let rt = 192 * 1024;
img[rt..rt + 4].copy_from_slice(b"regi");
le(&mut img, rt + 8, 2, 4);
img[rt + 16..rt + 32].copy_from_slice(&guid("2DC27766-F623-4200-9D64-115E9BFD4A08"));
le(&mut img, rt + 32, 2 * MB as u64, 8);
le(&mut img, rt + 40, MB as u64, 4);
img[rt + 48..rt + 64].copy_from_slice(&guid("8B7CA206-4790-4B9A-B8FE-575F050F886E"));
le(&mut img, rt + 64, MB as u64, 8);
le(&mut img, rt + 72, MB as u64, 4);
// metadados
let m = MB;
img[m..m + 8].copy_from_slice(b"metadata");
let mut items: Vec<([u8; 16], Vec<u8>)> = vec![];
let mut params = vec![0u8; 8];
le(&mut params, 0, MB as u64, 4);
le(&mut params, 4, if parent.is_some() { 2 } else { 0 }, 4);
items.push((guid("CAA16737-FA36-4D43-B3B6-33F0AA44E76B"), params));
items.push((
guid("2FA54224-CD1B-4876-B211-5DBED83BF4B8"),
size.to_le_bytes().to_vec(),
));
items.push((
guid("8141BF1D-A96F-4709-BA47-F233A8FAAB5F"),
512u32.to_le_bytes().to_vec(),
));
if let Some(p) = parent {
let key: Vec<u8> = "relative_path"
.encode_utf16()
.flat_map(|u| u.to_le_bytes())
.collect();
let val: Vec<u8> = p.encode_utf16().flat_map(|u| u.to_le_bytes()).collect();
let mut loc = vec![0u8; 20 + 12];
loc[..16].copy_from_slice(&guid("B04AEFB7-D19E-4A81-B789-25B8E9445913"));
le(&mut loc, 18, 1, 2);
let (ko, vo) = (32, 32 + key.len());
le(&mut loc, 20, ko as u64, 4);
le(&mut loc, 24, vo as u64, 4);
le(&mut loc, 28, key.len() as u64, 2);
le(&mut loc, 30, val.len() as u64, 2);
loc.extend_from_slice(&key);
loc.extend_from_slice(&val);
items.push((guid("A8D35F2D-B30B-454D-ABF7-D3D84834AB0C"), loc));
}
le(&mut img, m + 10, items.len() as u64, 2);
let mut at = 64 * 1024;
for (i, (id, data)) in items.iter().enumerate() {
let e = m + 32 + i * 32;
img[e..e + 16].copy_from_slice(id);
le(&mut img, e + 16, at as u64, 4);
le(&mut img, e + 20, data.len() as u64, 4);
img[m + at..m + at + data.len()].copy_from_slice(data);
at += data.len().div_ceil(8) * 8;
}
// blocos de dados a partir de 4 MiB; o BAT guarda estado e deslocamento (em MiB)
let ratio = (1usize << 23) * 512 / MB;
let bat = 2 * MB;
for (i, b) in blocks.iter().enumerate() {
let Some((state, data)) = b else { continue };
let mut off = 0;
if !data.is_empty() {
off = img.len();
let mut d = data.clone();
d.resize(MB, 0);
img.extend_from_slice(&d);
}
le(
&mut img,
bat + (i + i / ratio) * 8,
state | (off as u64 >> 20) << 20,
8,
);
}
if let Some(bm) = bitmap {
let off = img.len();
let mut d = bm;
d.resize(MB, 0);
img.extend_from_slice(&d);
le(&mut img, bat + ratio * 8, 6 | (off as u64 >> 20) << 20, 8);
}
img
}
#[test]
fn vhdx_dynamic_with_zero_and_missing_blocks() {
let want = raw(); // 1 MiB = um bloco
let mut expect = want.clone();
expect.extend_from_slice(&vec![0u8; 3 * MB]);
let tail = vec![0x5Au8; 100_000];
expect[3 * MB..3 * MB + tail.len()].copy_from_slice(&tail);
let img = build_vhdx(
4 * MB as u64,
&[
Some((6, want.clone())),
Some((2, vec![])), // zerado
None, // não presente
Some((6, tail)),
],
None,
None,
);
let dir = tempfile::tempdir().unwrap();
let p = dir.path().join("t.vhdx");
std::fs::write(&p, img).unwrap();
check_content(&p, &expect);
}
#[test]
fn vhdx_differencing_uses_the_sector_bitmap() {
let want = raw();
let dir = tempfile::tempdir().unwrap();
std::fs::write(dir.path().join("pai.raw"), &want).unwrap();
// filho: bloco 0 parcialmente presente, só com os setores 3 e 2000..2010 no filho
let mut data = vec![0u8; MB];
let mut bm = vec![0u8; 512];
let mut expect = want.clone();
for s in std::iter::once(3usize).chain(2000..2010) {
data[s * 512..(s + 1) * 512].fill(0x77);
expect[s * 512..(s + 1) * 512].fill(0x77);
bm[s / 8] |= 1 << (s % 8);
}
let img = build_vhdx(MB as u64, &[Some((7, data))], Some("pai.raw"), Some(bm));
let p = dir.path().join("filho.vhdx");
std::fs::write(&p, img).unwrap();
check_content(&p, &expect);
}
// ---------- DMG ----------
#[test]
fn dmg_with_every_chunk_type() {
let want = raw();
let sec = 512usize;
// 8 chunks de 128 setores (64 KiB)
let part = |i: usize| want[i * 128 * sec..(i + 1) * 128 * sec].to_vec();
let (adc_enc, adc_want) = adc_pattern(128 * sec);
let mut bz = bzip2::write::BzEncoder::new(vec![], bzip2::Compression::default());
bz.write_all(&part(3)).unwrap();
let chunks = vec![
DmgChunk {
ty: 1,
sectors: 128,
payload: part(0),
}, // bruto
DmgChunk {
ty: 0,
sectors: 128,
payload: vec![],
}, // zerado
DmgChunk {
ty: 0x8000_0005,
sectors: 128,
payload: zlib(&part(2)),
},
DmgChunk {
ty: 0x8000_0006,
sectors: 128,
payload: bz.finish().unwrap(),
},
DmgChunk {
ty: 0x8000_0004,
sectors: 128,
payload: adc_enc,
},
DmgChunk {
ty: 2,
sectors: 128,
payload: vec![],
}, // ignorado
DmgChunk {
ty: 0x8000_0005,
sectors: 128,
payload: zlib(&part(6)),
},
];
let mut expect = vec![];
expect.extend(part(0));
expect.extend(vec![0u8; 128 * sec]);
expect.extend(part(2));
expect.extend(part(3));
expect.extend(adc_want);
expect.extend(vec![0u8; 128 * sec]);
expect.extend(part(6));
let dir = tempfile::tempdir().unwrap();
let p = dir.path().join("t.dmg");
std::fs::write(&p, build_dmg(&chunks, expect.len() as u64 / 512)).unwrap();
check_content(&p, &expect);
}
/// Chunks `ULFO` com dados compactados pelo compressor de referência da Apple (`lzfse`):
/// um bloco `bvx2` (FSE, 64 KiB) e um pequeno (`bvxn`/LZVN).
#[test]
fn dmg_lzfse_chunks_from_the_reference_compressor() {
let big = std::fs::read(fx("lzfse-64k.bin")).unwrap();
let small = std::fs::read(fx("lzfse-small.bin")).unwrap();
let mut small_padded = small.clone();
small_padded.resize(small.len().div_ceil(512) * 512, 0);
let chunks = [
DmgChunk {
ty: 0x8000_0007,
sectors: (big.len() / 512) as u64,
payload: std::fs::read(fx("lzfse-64k.bin.lzfse")).unwrap(),
},
DmgChunk {
ty: 0x8000_0007,
sectors: (small_padded.len() / 512) as u64,
payload: std::fs::read(fx("lzfse-small.bin.lzfse")).unwrap(),
},
];
let mut expect = big.clone();
expect.extend_from_slice(&small_padded);
let dir = tempfile::tempdir().unwrap();
let p = dir.path().join("l.dmg");
std::fs::write(&p, build_dmg(&chunks, expect.len() as u64 / 512)).unwrap();
check_content(&p, &expect);
}
#[test]
fn dmg_with_a_corrupt_lzfse_chunk_and_encrypted_are_refused_with_a_reason() {
let dir = tempfile::tempdir().unwrap();
let p = dir.path().join("l.dmg");
let chunks = [DmgChunk {
ty: 0x8000_0007,
sectors: 8,
payload: vec![1, 2, 3],
}];
std::fs::write(&p, build_dmg(&chunks, 8)).unwrap();
let s = open_path(&p).unwrap();
let e = read_vec(s.as_ref(), 0, 512).unwrap_err().to_string();
assert!(e.contains("LZFSE"), "{e}");
let p = dir.path().join("e.dmg");
let mut img = b"encrcdsa".to_vec();
img.resize(8192, 0);
std::fs::write(&p, img).unwrap();
let e = open_path(&p).err().expect("deveria recusar").to_string();
assert!(e.contains("cifrado"), "{e}");
}
// ---------- imagens reais do dfvfs (target/testdata) ----------
#[test]
fn dfvfs_images_match_a_reference_reader() {
// hashes do disco virtual inteiro, conferidos com o 7-Zip (árvore de arquivos e partições)
let table: &[(&str, &str)] = &[
(
"ext2.vhdx",
"a6c2f0e39afe6c6ab432ca5465349fcefe8dc944398e97b2d957d3f89dbb5d80",
),
(
"ext2.vmdk",
"a6c2f0e39afe6c6ab432ca5465349fcefe8dc944398e97b2d957d3f89dbb5d80",
),
(
"ext2.vhd",
"870be7ae16c1fa8faab05c6eb9205dc9a7ae35c5f552c5cf8a267c0bc6a5cb99",
),
(
"fvdetest.qcow2",
"732091e57632b7a2332f218d2d3a9ce1355a836ebacce91615a2c30a178e4ec3",
),
(
"windows_volume.qcow2",
"44abe9deca9658f331a2bdba2deb53192d04f35d157a1fb3ba0597b03f0524f2",
),
(
"apm.dmg",
"897f487f4971e72c762e00460935e3b25176cda35620b508b490f65a7e0118ff",
),
(
"ntfs-dynamic.vhd",
"8b10b52e3d1e76075d05a5101a6536b9fa8376a5b8f7c22f502d0987d165c876",
),
(
"ntfs-fixed.vhd",
"cd81fade3878f1b2957f1ece168201876bdf4e90c9b30f60c2f232eba5fea76c",
),
(
"ntfs-dynamic.vhdx",
"b92731f8e4bf3532418444d22a9086823a8122569500acd09cd8d2ce20eb98e9",
),
(
"ntfs-fixed.vhdx",
"5237dd895f38052344e2ef35a207fe9df08cd18d17b6ea857a1b93cc475e1f2e",
),
(
"fat-differential.vhd",
"f4b61a33ee2f7e8c19f737792a4107e46340026a9a829e4169b751901cc3ef02",
),
(
"ntfs-differential.vhd",
"b7922a46a6b08fa4f4fc0c51a25d5587d1d49f15cfade45ca740dd07110ae144",
),
(
"fat-differential.vhdx",
"a538161f34bc44c12bf9a542ce9218741c62728723ea18d0e4f6ea92e9f32e93",
),
(
"ntfs-differential.vhdx",
"1ef1fb5360247aa7d36a38415bc7bf6e1e52f62af5e6bd1283815e82584c7efc",
),
];
for (name, hash) in table {
let Some(p) = dfvfs(name) else { continue };
let s = open_path(&p).unwrap_or_else(|e| panic!("{name}: {e}"));
assert_eq!(&sha(s.as_ref()), hash, "{name}");
}
}
#[test]
fn partition_table_is_found_inside_a_qcow2() {
let Some(p) = dfvfs("fvdetest.qcow2") else {
return;
};
let s = open_path(&p).unwrap();
let layout = guara_core::partition::analyze(s.as_ref(), false);
assert_eq!(layout.table, "gpt");
assert_eq!(layout.partitions.len(), 1);
}