vdm/core/tests/meta/veloxpart_test.cpp

#include "vdm/meta/veloxpart.hpp"

#include <unistd.h>

#include <cstdint>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>

#include "vdm/util/crc32.hpp"
#include "vtest.hpp"

using namespace vdm;
using namespace vdm::meta;

namespace {

VeloxPart sample_full() {
    VeloxPart vp;
    vp.version = kVersion;
    vp.total_size = 5'000'000'000ull;
    vp.downloaded = 1'234'567;
    vp.urls = {"https://origin.example/big.iso", "https://cdn.example/big.iso?sig=abc",
               "https://mirror1.example/big.iso"};
    vp.etag = "\"deadbeef-1234\"";
    vp.last_modified = "Wed, 01 Jan 2025 00:00:00 GMT";
    vp.content_type = "application/octet-stream";
    for (int i = 0; i < 8; ++i) {
        SegmentRecord s;
        s.start = static_cast<std::uint64_t>(i) * 625'000'000ull;
        s.end = s.start + 625'000'000ull - 1;  // inclusive
        s.completed = (i < 2) ? s.end - s.start + 1 : 100'000ull * (i + 1);
        vp.segments.push_back(s);
    }
    vp.flags = kFlagHasShaState;
    vp.sha256_state = {std::byte{1}, std::byte{2}, std::byte{3}, std::byte{0xAA}, std::byte{0xFF}};
    return vp;
}

VeloxPart sample_minimal() {
    VeloxPart vp;
    vp.total_size = 0;  // chunked / unknown
    vp.urls = {"http://x/y"};
    SegmentRecord s;
    s.start = 0;
    s.end = 0;  // 1-byte resource
    s.completed = 0;
    vp.segments.push_back(s);
    return vp;
}

// Re-CRC a mutated body (everything except the final u32).
std::vector<std::byte> refresh_crc(std::vector<std::byte> image) {
    std::uint32_t c = crc32(ConstByteSpan(image.data(), image.size() - 4));
    for (int i = 0; i < 4; ++i)
        image[image.size() - 4 + i] = static_cast<std::byte>((c >> (8 * i)) & 0xFF);
    return image;
}

struct TempPath {
    std::string path;
    TempPath() {
        const char *d = std::getenv("TMPDIR");
        path = (d ? d : "/tmp");
        path += "/vdm_vp_test_XXXXXX";
        int fd = ::mkstemp(path.data());
        if (fd >= 0) {
            ::close(fd);
            ::unlink(path.c_str());
        }
    }
    ~TempPath() {
        ::unlink(path.c_str());
        ::unlink((path + ".tmp").c_str());
    }
};

}  // namespace

VT_TEST(crc32_known_vector) {
    const char *s = "123456789";
    VT_CHECK_EQ(crc32(ConstByteSpan(reinterpret_cast<const std::byte *>(s), 9)), 0xCBF43926u);
    VT_CHECK_EQ(crc32(ConstByteSpan{}), 0u);
}

VT_TEST(vp_roundtrip_full) {
    VeloxPart in = sample_full();
    auto image = serialize_veloxpart(in);
    auto out = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(out.has_value());
    VT_CHECK(out.value() == in);
    VT_CHECK_EQ(out.value().effective_url(),
                std::string_view("https://cdn.example/big.iso?sig=abc"));
    VT_CHECK_EQ(out.value().segments.size(), 8u);
}

VT_TEST(vp_roundtrip_minimal) {
    VeloxPart in = sample_minimal();
    auto image = serialize_veloxpart(in);
    auto out = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(out.has_value());
    VT_CHECK(out.value() == in);
    VT_CHECK(out.value().sha256_state.empty());
}

VT_TEST(vp_serialize_is_deterministic) {
    VeloxPart in = sample_full();
    auto a = serialize_veloxpart(in);
    auto b = serialize_veloxpart(in);
    VT_CHECK(a == b);
}

VT_TEST(vp_file_roundtrip) {
    TempPath tp;
    VeloxPart in = sample_full();
    VT_REQUIRE(write_veloxpart_file(tp.path, in, /*fsync=*/true).has_value());
    auto out = read_veloxpart_file(tp.path);
    VT_REQUIRE(out.has_value());
    VT_CHECK(out.value() == in);
    // the temp file must be gone after the atomic rename
    VT_CHECK_EQ(::access((tp.path + ".tmp").c_str(), F_OK), -1);
}

VT_TEST(vp_read_missing_file_errors) {
    auto out = read_veloxpart_file("/vdm_no_such_dir_zz/x.veloxpart.meta");
    VT_REQUIRE(!out.has_value());
    VT_CHECK_EQ(out.error().code, Error::path_rejected);
}

// --- truncation / corruption table -------------------------------------------------

VT_TEST(vp_reject_empty_and_tiny) {
    VT_CHECK_EQ(parse_veloxpart(ConstByteSpan{}).error().code, Error::meta_corrupt);
    std::array<std::byte, 3> three{};
    VT_CHECK_EQ(parse_veloxpart(ConstByteSpan(three.data(), 3)).error().code, Error::meta_corrupt);
    std::array<std::byte, 51> almost{};
    VT_CHECK_EQ(parse_veloxpart(ConstByteSpan(almost.data(), almost.size())).error().code,
                Error::meta_corrupt);
}

VT_TEST(vp_reject_bad_magic) {
    auto image = serialize_veloxpart(sample_minimal());
    image[1] = std::byte{'X'};              // "VDMP" -> "VXMP"
    image = refresh_crc(std::move(image));  // fix CRC so we're testing the magic check
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_corrupt);
}

VT_TEST(vp_reject_crc_mismatch) {
    auto image = serialize_veloxpart(sample_minimal());
    image[20] ^= std::byte{0x40};  // flip a payload bit, do NOT refresh the CRC
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_corrupt);

    // flipping the CRC field itself is also a mismatch
    auto image2 = serialize_veloxpart(sample_minimal());
    image2.back() ^= std::byte{0xFF};
    VT_CHECK_EQ(parse_veloxpart(ConstByteSpan(image2.data(), image2.size())).error().code,
                Error::meta_corrupt);
}

VT_TEST(vp_future_version_is_unsupported) {
    auto image = serialize_veloxpart(sample_minimal());
    image[4] = std::byte{99};  // version u16 low byte
    image[5] = std::byte{0};
    image = refresh_crc(std::move(image));
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_version_unsupported);
}

VT_TEST(vp_reject_truncation_at_every_stage) {
    auto full = serialize_veloxpart(sample_full());
    // Chop the image at many lengths; each must be meta_corrupt, never a crash.
    for (std::size_t len = full.size() - 1; len >= 1; len = (len > 8 ? len - 7 : len - 1)) {
        auto r = parse_veloxpart(ConstByteSpan(full.data(), len));
        VT_CHECK(!r.has_value());
        if (r.has_value())
            break;
        VT_CHECK_EQ(r.error().code, Error::meta_corrupt);
        if (len == 1)
            break;
    }
}

VT_TEST(vp_reject_hostile_url_count) {
    auto image = serialize_veloxpart(sample_minimal());
    // url_count u32 sits right after magic(4)+ver(2)+flags(2)+total(8)+downloaded(8) = 24
    for (int i = 0; i < 4; ++i)
        image[24 + i] = std::byte{0xFF};
    image = refresh_crc(std::move(image));
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_corrupt);
}

VT_TEST(vp_reject_hostile_lp_string_length) {
    // The case AGENT-CORE singles out: a length prefix that reaches past the buffer.
    // Build a minimal image, then overwrite url[0]'s length prefix with a huge value.
    auto image = serialize_veloxpart(sample_minimal());
    // layout up to url[0] length: magic4 ver2 flags2 total8 downloaded8 url_count4 = 28
    for (int i = 0; i < 4; ++i)
        image[28 + i] = std::byte{0xFF};  // url[0] len = 4 GiB - 1
    image = refresh_crc(std::move(image));
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_corrupt);
}

VT_TEST(vp_reject_hostile_segment_count) {
    auto image = serialize_veloxpart(sample_minimal());
    // find the segment_count: it's u32 right before the (24-byte) segment records and the
    // trailing crc. minimal sample has 1 segment and no sha state, so:
    //   segment_count is at  size - 4(crc) - 24(one segment) - 4 = size - 32
    std::size_t sc = image.size() - 32;
    for (int i = 0; i < 4; ++i)
        image[sc + i] = std::byte{0xFF};
    image = refresh_crc(std::move(image));
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_corrupt);
}

VT_TEST(vp_reject_trailing_bytes) {
    auto image = serialize_veloxpart(sample_minimal());
    image.push_back(std::byte{0});
    image.push_back(std::byte{0});
    image = refresh_crc(std::move(image));  // CRC now covers the padding too
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_corrupt);
}

VT_TEST(vp_reject_segment_completed_over_length) {
    VeloxPart in = sample_minimal();
    in.segments[0].start = 0;
    in.segments[0].end = 99;         // length 100
    in.segments[0].completed = 500;  // impossible
    auto image = serialize_veloxpart(in);
    auto r = parse_veloxpart(ConstByteSpan(image.data(), image.size()));
    VT_REQUIRE(!r.has_value());
    VT_CHECK_EQ(r.error().code, Error::meta_corrupt);
}