Files
ImHex-Patterns/patterns/tiff.hexpat
Benjamin Gilbert 7ecd6d87dd patterns/tiff: Support BigTIFF and tiled TIFF; bugfixes and cleanups (#159)
* patterns/tiff: show TIFF tag name/number in DirectoryEntry array

Don't require unfolding the array entry to see what tag it contains.

* patterns/tiff: show IFD number in IFD list

* patterns/tiff: add JPEGTables tag; correct name of ICC Profile tag

* patterns/tiff: add TIFFRational type

Rationals, uniquely, are primitives with two fields.  Add a struct to
represent this, rather than inlining them.

* patterns/tiff: use correct types for fields smaller than 4 bytes

Small fields are always left-aligned in the 4-byte Value Offset.  On
little-endian TIFFs we currently cheat this by declaring a 32-bit value
and letting little-endianness handle the semantics.  However, this adds
some extra conditionals, and misrepresents the resulting field as 32 bits.
Drop the cheat.

* patterns/tiff: add ValueOffset abstraction

We were using the field type to make assumptions about whether the Value
Offset is a Value or an Offset, which is incorrect.  If the Count
multiplied by the field size is larger than 4, the field is an Offset;
otherwise it's a Value.

Add display sugar for single-element arrays to avoid extra nesting.

* patterns/tiff: drop dead code

get_ifds_offsets() and BIG/LITTLE aren't used at all.  get_total_IFDs()
is only used for declaring the length of TIFFFile.IFDs, and isn't needed
because IFDs are structured as a linked list.

* patterns/tiff: drop set_endian()

The call in TIFFFile is redundant.  Drop both calls and open-code the
check at the top level, before executing any code.  The BigTIFF check
will eventually be added alongside this one.

Fail if we don't recognize the magic number.

* patterns/tiff: minor cleanups

* patterns/tiff: drop strip offset/byte count arrays from struct IFD

They're redundant with the fields in the DirectoryEntry array.  Also
they're buggy: they assume the field Value Offsets are always offsets,
which isn't true for single-strip IFDs, and they ignore a partial last
strip in multiple-strip IFDs.

* patterns/tiff: rewrite strip array generation

We're making extra work for ourselves by avoiding the type system.  Also,
by calculating the number of strips we expect rather than the number of
strips we actually have, we're miscounting and omitting any partial last
strip.

Instead, read the strip offsets and byte counts directly from the
IFDEntry array.

* patterns/tiff: add ImageData array for tiled IFDs

* patterns/tiff: increase variable widths for BigTIFF

Use 64-bit temporary variables for values that can be 64 bits in BigTIFF.

* patterns/tiff: support BigTIFF

* tests/patterns/test_data: add more TIFF tests
2023-09-24 20:04:20 +02:00

257 lines
7.2 KiB
Rust

#pragma description Tag Image File Format
#pragma MIME image/tiff
#pragma eval_depth 100
#include <std/io.pat>
#include <std/mem.pat>
#include <std/string.pat>
#include <std/core.pat>
char Magic[2] @ 0 [[hidden]];
match (Magic) {
("II"): std::core::set_endian(std::mem::Endian::Little);
("MM"): std::core::set_endian(std::mem::Endian::Big);
(_): std::error(std::format("Unrecognized magic number: {}", Magic));
}
u16 Version @ 2 [[hidden]];
u32 ValueOffsetSize;
match (Version) {
(42): ValueOffsetSize = 4;
(43): ValueOffsetSize = 8;
(_): std::error(std::format("Unrecognized version: {}", Version));
}
struct Big<T> {
match (Version) {
(42): T V;
(43): u64 V;
(_): std::error(std::format("Unrecognized version: {}", Version));
}
} [[sealed, format_read("format_read_big"), format_write("format_write_big"), transform("transform_big")]];
fn format_read_big(Big<u32> v) {
return std::format("{} (0x{:X})", v, v);
};
fn format_write_big(str v) {
return std::string::parse_int(v, 0);
};
fn transform_big(Big<u32> v) {
return v.V;
};
struct TIFFHeader {
char Magic[2];
u16 Version;
if (Version > 42) {
u16 OffsetSize;
padding[2];
}
Big<u32> Offset;
};
enum TIFFFieldType : u16 {
BYTE = 1,
ASCII = 2,
SHORT = 3,
LONG = 4,
RATIONAL = 5,
SBYTE = 6,
UNDEFINED = 7,
SSHORT = 8,
SLONG = 9,
SRATIONAL = 10,
FLOAT = 11,
DOUBLE = 12,
LONG8 = 16,
SLONG8 = 17,
};
struct TIFFRational<T> {
T Numerator;
T Denominator;
} [[format_read("format_read_rational")]];
fn format_read_rational(auto r) {
return std::format("{}/{}", r.Numerator, r.Denominator);
};
enum TIFFTag : u16 {
NewSubfileType = 0x00FE,
SubfileType = 0x00FF,
ImageWidth = 0x0100,
ImageLength = 0x0101,
BitsPerSample = 0x0102,
Compression = 0x0103,
PhotometricInterpretation = 0x0106,
Threshholding = 0x0107,
CellWidth = 0x0108,
CellLength = 0x0109,
FillOrder = 0x010A,
DocumentName = 0x010D,
ImageDescription = 0x010E,
Make = 0x010F,
Model = 0x0110,
StripOffsets = 0x0111,
Orientation = 0x0112,
SamplesPerPixel = 0x0115,
RowsPerStrip = 0x0116,
StripByteCounts = 0x0117,
MinSampleValue = 0x0118,
MaxSampleValue = 0x0119,
XResolution = 0x011A,
YResolution = 0x011B,
PlanarConfiguration = 0x011C,
PageName = 0x011D,
XPosition = 0x011E,
YPosition = 0x011F,
FreeOffsets = 0x0120,
FreeByteCounts = 0x0121,
GrayResponseUnit = 0x0122,
GrayResponseCurve = 0x0123,
T4Options = 0x0124,
T6Options = 0x0125,
ResolutionUnit = 0x0128,
PageNumber = 0x0129,
TransferFunction = 0x012D,
Software = 0x0131,
DateTime = 0x0132,
Artist = 0x013B,
HostComputer = 0x013C,
Predictor = 0x013D,
WhitePoint = 0x013E,
PrimaryChromaticities = 0x013F,
ColorMap = 0x0140,
HalftoneHints = 0x0141,
TileWidth = 0x0142,
TileLength = 0x0143,
TileOffsets = 0x0144,
TileByteCounts = 0x0145,
InkSet = 0x014C,
InkNames = 0x014D,
NumberOfInks = 0x014E,
DotRange = 0x0150,
TargetPrinter = 0x0151,
ExtraSamples = 0x0152,
SampleFormat = 0x0153,
SMinSampleValue = 0x0154,
SMaxSampleValue = 0x0155,
TransferRange = 0x0156,
JPEGTables = 0x015B,
JPEGProc = 0x0200,
JPEGInterchangeFormat = 0x0201,
JPEGInterchangeFormatLngth = 0x0202,
JPEGRestartInterval = 0x0203,
JPEGLosslessPredictors = 0x0205,
JPEGPointTransforms = 0x0206,
JPEGQTables = 0x0207,
JPEGDCTables = 0x0208,
JPEGACTables = 0x0209,
YCbCrCoefficients = 0x0211,
YCbCrSubSampling = 0x0212,
YCbCrPositioning = 0x0213,
ReferenceBlackWhite = 0x0214,
Copyright = 0x8298,
ICCProfile = 0x8773
};
struct ValueArray<T, auto Count> {
if (Count > 1) {
T Values[Count];
} else {
T Values[Count] [[hidden, no_unique_address]];
T Value;
}
} [[inline]];
struct ValueOffset<T, auto Count> {
u64 Size = sizeof(T) * Count;
if (Size <= ValueOffsetSize) {
ValueArray<T, Count> ValueArray;
padding[ValueOffsetSize - Size];
} else {
Big<u32> Offset;
ValueArray<T, Count> ValueArray @ Offset;
}
} [[inline]];
struct IFDEntry {
TIFFTag Tag;
TIFFFieldType Type;
Big<u32> Count;
match (Type) {
(TIFFFieldType::BYTE): ValueOffset<u8, Count> ValueOffset;
(TIFFFieldType::ASCII): ValueOffset<char, Count> ValueOffset;
(TIFFFieldType::SHORT): ValueOffset<u16, Count> ValueOffset;
(TIFFFieldType::LONG): ValueOffset<u32, Count> ValueOffset;
(TIFFFieldType::RATIONAL): ValueOffset<TIFFRational<u32>, Count> ValueOffset;
(TIFFFieldType::SBYTE): ValueOffset<s8, Count> ValueOffset;
(TIFFFieldType::UNDEFINED): ValueOffset<u8, Count> ValueOffset;
(TIFFFieldType::SSHORT): ValueOffset<s16, Count> ValueOffset;
(TIFFFieldType::SLONG): ValueOffset<s32, Count> ValueOffset;
(TIFFFieldType::SRATIONAL): ValueOffset<TIFFRational<s32>, Count> ValueOffset;
(TIFFFieldType::FLOAT): ValueOffset<float, Count> ValueOffset;
(TIFFFieldType::DOUBLE): ValueOffset<double, Count> ValueOffset;
(TIFFFieldType::LONG8): ValueOffset<u64, Count> ValueOffset;
(TIFFFieldType::SLONG8): ValueOffset<s64, Count> ValueOffset;
(_): {
padding[ValueOffsetSize];
std::print(std::format("TIFFFieldType {} not supported", u16(Type)));
}
}
} [[name(std::string::replace(std::core::formatted_value(Tag), "TIFFTag::", ""))]];
fn get_field(ref auto entries, TIFFTag tag) {
for (u64 i = 0, i < std::core::member_count(entries), i = i + 1) {
if (entries[i].Tag == tag) {
return i;
}
}
std::error(std::format("Tag {} not found in directory", tag));
};
struct ImageData<auto Desc> {
u64 Index = std::core::array_index();
u64 Offset = parent.DirectoryEntry[parent.OffsetField].ValueOffset.ValueArray.Values[Index];
u64 ByteCount = parent.DirectoryEntry[parent.ByteCountField].ValueOffset.ValueArray.Values[Index];
std::mem::Bytes<ByteCount> ImageData @ Offset [[name(std::format("{} {}", Desc, Index))]];
} [[inline]];
u64 currentIFD = 0;
struct IFD {
u64 Number = currentIFD;
Big<u16> NumberDirectoryEntries;
IFDEntry DirectoryEntry[NumberDirectoryEntries];
Big<u32> NextIFD;
try {
u64 OffsetField = get_field(DirectoryEntry, TIFFTag::StripOffsets);
u64 ByteCountField = get_field(DirectoryEntry, TIFFTag::StripByteCounts);
u64 Count = std::core::member_count(DirectoryEntry[OffsetField].ValueOffset.ValueArray.Values);
ImageData<"Strip"> Strips[Count];
} catch {}
try {
u64 OffsetField = get_field(DirectoryEntry, TIFFTag::TileOffsets);
u64 ByteCountField = get_field(DirectoryEntry, TIFFTag::TileByteCounts);
u64 Count = std::core::member_count(DirectoryEntry[OffsetField].ValueOffset.ValueArray.Values);
ImageData<"Tile"> Tiles[Count];
} catch {}
} [[name(std::format("IFD {}", Number))]];
struct IFDS {
IFD IFD;
if (IFD.NextIFD > 0) {
currentIFD += 1;
IFDS IFD_tmp @ IFD.NextIFD;
}
} [[inline]];
struct TIFFFile {
TIFFHeader Header;
IFDS @ Header.Offset;
};
TIFFFile File @ 0x00;