Merge pull request #154 from fintelia/decoder-refactor

Decoder refactor
This commit is contained in:
Jonathan Behrens authored and GitHub committed 2022-01-15 17:04:11 -05:00
commit a780da0b34
6 files changed
+689 -519

No files matched your search

+82 -61
View File
@@ -341,14 +341,15 @@ impl Entry {
pub fn val<R: Read + Seek>(
&self,
limits: &super::Limits,
decoder: &mut super::Decoder<R>,
bigtiff: bool,
reader: &mut SmartReader<R>,
) -> TiffResult<Value> {
// Case 1: there are no values so we can return immediately.
if self.count == 0 {
return Ok(List(Vec::new()));
}
let bo = decoder.byte_order();
let bo = reader.byte_order();
let tag_size = match self.type_ {
Type::BYTE | Type::SBYTE | Type::ASCII | Type::UNDEFINED => 1,
@@ -373,7 +374,7 @@ impl Entry {
// Case 2: there is one value.
if self.count == 1 {
// 2a: the value is 5-8 bytes and we're in BigTiff mode.
if decoder.bigtiff && value_bytes > 4 && value_bytes <= 8 {
if bigtiff && value_bytes > 4 && value_bytes <= 8 {
return Ok(match self.type_ {
Type::LONG8 => UnsignedBig(self.r(bo).read_u64()?),
Type::SLONG8 => SignedBig(self.r(bo).read_i64()?),
@@ -419,36 +420,36 @@ impl Entry {
}
}
Type::LONG8 => {
decoder.goto_offset(self.r(bo).read_u32()?)?;
UnsignedBig(decoder.read_long8()?)
reader.goto_offset(self.r(bo).read_u32()?.into())?;
UnsignedBig(reader.read_u64()?)
}
Type::SLONG8 => {
decoder.goto_offset(self.r(bo).read_u32()?)?;
SignedBig(decoder.read_slong8()?)
reader.goto_offset(self.r(bo).read_u32()?.into())?;
SignedBig(reader.read_i64()?)
}
Type::DOUBLE => {
decoder.goto_offset(self.r(bo).read_u32()?)?;
Double(decoder.read_double()?)
reader.goto_offset(self.r(bo).read_u32()?.into())?;
Double(reader.read_f64()?)
}
Type::RATIONAL => {
decoder.goto_offset(self.r(bo).read_u32()?)?;
Rational(decoder.read_long()?, decoder.read_long()?)
reader.goto_offset(self.r(bo).read_u32()?.into())?;
Rational(reader.read_u32()?, reader.read_u32()?)
}
Type::SRATIONAL => {
decoder.goto_offset(self.r(bo).read_u32()?)?;
SRational(decoder.read_slong()?, decoder.read_slong()?)
reader.goto_offset(self.r(bo).read_u32()?.into())?;
SRational(reader.read_i32()?, reader.read_i32()?)
}
Type::IFD => Ifd(self.r(bo).read_u32()?),
Type::IFD8 => {
decoder.goto_offset(self.r(bo).read_u32()?)?;
IfdBig(decoder.read_long8()?)
reader.goto_offset(self.r(bo).read_u32()?.into())?;
IfdBig(reader.read_u64()?)
}
Type::__NonExhaustive => unreachable!(),
});
}
// Case 3: There is more than one value, but it fits in the offset field.
if value_bytes <= 4 || decoder.bigtiff && value_bytes <= 8 {
if value_bytes <= 4 || bigtiff && value_bytes <= 8 {
match self.type_ {
Type::BYTE => return Ok(offset_to_bytes(self.count as usize, self)?),
Type::SBYTE => return Ok(offset_to_sbytes(self.count as usize, self)?),
@@ -535,64 +536,80 @@ impl Entry {
match self.type_ {
// TODO check if this could give wrong results
// at a different endianess of file/computer.
Type::BYTE => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(UnsignedBig(u64::from(decoder.read_byte()?)))
Type::BYTE => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
let mut buf = [0; 1];
reader.read_exact(&mut buf)?;
Ok(UnsignedBig(u64::from(buf[0])))
}),
Type::SBYTE => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(SignedBig(i64::from(decoder.read_byte()? as i8)))
Type::SBYTE => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(SignedBig(i64::from(reader.read_i8()? as i8)))
}),
Type::SHORT => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(UnsignedBig(u64::from(decoder.read_short()?)))
Type::SHORT => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(UnsignedBig(u64::from(reader.read_u16()?)))
}),
Type::SSHORT => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(SignedBig(i64::from(decoder.read_sshort()?)))
Type::SSHORT => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(SignedBig(i64::from(reader.read_i16()?)))
}),
Type::LONG => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(Unsigned(decoder.read_long()?))
Type::LONG => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(Unsigned(reader.read_u32()?))
}),
Type::SLONG => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(Signed(decoder.read_slong()?))
Type::SLONG => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(Signed(reader.read_i32()?))
}),
Type::FLOAT => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(Float(decoder.read_float()?))
Type::FLOAT => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(Float(reader.read_f32()?))
}),
Type::DOUBLE => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(Double(decoder.read_double()?))
Type::DOUBLE => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(Double(reader.read_f64()?))
}),
Type::RATIONAL => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(Rational(decoder.read_long()?, decoder.read_long()?))
Type::RATIONAL => {
self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(Rational(reader.read_u32()?, reader.read_u32()?))
})
}
Type::SRATIONAL => {
self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(SRational(reader.read_i32()?, reader.read_i32()?))
})
}
Type::LONG8 => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(UnsignedBig(reader.read_u64()?))
}),
Type::SRATIONAL => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(SRational(decoder.read_slong()?, decoder.read_slong()?))
Type::SLONG8 => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(SignedBig(reader.read_i64()?))
}),
Type::LONG8 => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(UnsignedBig(decoder.read_long8()?))
Type::IFD => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(Ifd(reader.read_u32()?))
}),
Type::SLONG8 => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(SignedBig(decoder.read_slong8()?))
}),
Type::IFD => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(Ifd(decoder.read_long()?))
}),
Type::IFD8 => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(IfdBig(decoder.read_long8()?))
}),
Type::UNDEFINED => self.decode_offset(self.count, bo, limits, decoder, |decoder| {
Ok(Byte(u8::from(decoder.read_byte()?)))
Type::IFD8 => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
Ok(IfdBig(reader.read_u64()?))
}),
Type::UNDEFINED => {
self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
let mut buf = [0; 1];
reader.read_exact(&mut buf)?;
Ok(Byte(buf[0]))
})
}
Type::ASCII => {
let n = usize::try_from(self.count)?;
if n > limits.decoding_buffer_size {
return Err(TiffError::LimitsExceeded);
}
if decoder.bigtiff {
decoder.goto_offset_u64(self.r(bo).read_u64()?)?
if bigtiff {
reader.goto_offset(self.r(bo).read_u64()?)?
} else {
decoder.goto_offset(self.r(bo).read_u32()?)?
reader.goto_offset(self.r(bo).read_u32()?.into())?
}
let string = decoder.read_string(n)?;
Ok(Ascii(string))
let mut out = vec![0; n];
reader.read_exact(&mut out)?;
// Strings may be null-terminated, so we trim anything downstream of the null byte
if let Some(first) = out.iter().position(|&b| b == 0) {
out.truncate(first);
}
Ok(Ascii(String::from_utf8(out)?))
}
Type::__NonExhaustive => unreachable!(),
}
@@ -603,13 +620,14 @@ impl Entry {
&self,
value_count: u64,
bo: ByteOrder,
bigtiff: bool,
limits: &super::Limits,
decoder: &mut super::Decoder<R>,
reader: &mut SmartReader<R>,
decode_fn: F,
) -> TiffResult<Value>
where
R: Read + Seek,
F: Fn(&mut super::Decoder<R>) -> TiffResult<Value>,
F: Fn(&mut SmartReader<R>) -> TiffResult<Value>,
{
let value_count = usize::try_from(value_count)?;
if value_count > limits.decoding_buffer_size / mem::size_of::<Value>() {
@@ -617,13 +635,16 @@ impl Entry {
}
let mut v = Vec::with_capacity(value_count);
if decoder.bigtiff {
decoder.goto_offset_u64(self.r(bo).read_u64()?)?
let offset = if bigtiff {
self.r(bo).read_u64()?
} else {
decoder.goto_offset(self.r(bo).read_u32()?)?
}
self.r(bo).read_u32()?.into()
};
reader.goto_offset(offset)?;
for _ in 0..value_count {
v.push(decode_fn(decoder)?)
v.push(decode_fn(reader)?)
}
Ok(List(v))
}
+290
View File
@@ -0,0 +1,290 @@
use super::ifd::{Directory, Value};
use super::tag_reader::TagReader;
use super::Limits;
use super::{stream::SmartReader, ChunkType};
use crate::tags::{CompressionMethod, PhotometricInterpretation, Predictor, SampleFormat, Tag};
use crate::{TiffError, TiffFormatError, TiffResult, TiffUnsupportedError};
use std::convert::{TryFrom, TryInto};
use std::io::{Read, Seek};
#[derive(Debug)]
pub(crate) struct StripDecodeState {
pub rows_per_strip: u32,
}
#[derive(Debug)]
/// Computed values useful for tile decoding
pub(crate) struct TileAttributes {
pub image_width: usize,
pub image_height: usize,
pub samples_per_pixel: usize,
pub tile_width: usize,
pub tile_length: usize,
}
impl TileAttributes {
pub fn tiles_across(&self) -> usize {
(self.image_width + self.tile_width - 1) / self.tile_width
}
pub fn tiles_down(&self) -> usize {
(self.image_height + self.tile_length - 1) / self.tile_length
}
fn padding_right(&self) -> usize {
self.tile_width - self.image_width % self.tile_width
}
fn padding_down(&self) -> usize {
self.tile_length - self.image_height % self.tile_length
}
pub fn row_samples(&self) -> usize {
self.tile_width * self.samples_per_pixel
}
pub fn tile_samples(&self) -> usize {
self.tile_length * self.tile_width * self.samples_per_pixel
}
fn tile_strip_samples(&self) -> usize {
(self.tile_samples() * self.tiles_across())
- (self.padding_right() * self.tile_length * self.samples_per_pixel)
}
/// Returns the tile offset in the result buffer, counted in samples
pub fn get_offset(&self, tile: usize) -> usize {
let row = tile / self.tiles_across();
let column = tile % self.tiles_across();
(row * self.tile_strip_samples()) + (column * self.row_samples())
}
pub fn get_padding(&self, tile: usize) -> (usize, usize) {
let row = tile / self.tiles_across();
let column = tile % self.tiles_across();
let padding_right = if column == self.tiles_across() - 1 {
self.padding_right()
} else {
0
};
let padding_down = if row == self.tiles_down() - 1 {
self.padding_down()
} else {
0
};
(padding_right, padding_down)
}
}
#[derive(Debug)]
pub(crate) struct Image {
pub ifd: Option<Directory>,
pub width: u32,
pub height: u32,
pub bits_per_sample: Vec<u8>,
#[allow(unused)]
pub samples: u8,
pub sample_format: Vec<SampleFormat>,
pub photometric_interpretation: PhotometricInterpretation,
pub compression_method: CompressionMethod,
pub predictor: Predictor,
pub jpeg_tables: Option<Vec<u8>>,
pub chunk_type: ChunkType,
pub strip_decoder: Option<StripDecodeState>,
pub tile_attributes: Option<TileAttributes>,
pub chunk_offsets: Vec<u64>,
pub chunk_bytes: Vec<u64>,
}
impl Image {
pub fn from_reader<R: Read + Seek>(
reader: &mut SmartReader<R>,
ifd: Directory,
limits: &Limits,
bigtiff: bool,
) -> TiffResult<Image> {
let mut tag_reader = TagReader {
reader,
limits,
ifd: &ifd,
bigtiff,
};
let width = tag_reader.require_tag(Tag::ImageWidth)?.into_u32()?;
let height = tag_reader.require_tag(Tag::ImageLength)?.into_u32()?;
let photometric_interpretation = tag_reader
.find_tag(Tag::PhotometricInterpretation)?
.map(Value::into_u16)
.transpose()?
.and_then(PhotometricInterpretation::from_u16)
.ok_or(TiffUnsupportedError::UnknownInterpretation)?;
// Try to parse both the compression method and the number, format, and bits of the included samples.
// If they are not explicitly specified, those tags are reset to their default values and not carried from previous images.
let compression_method = match tag_reader.find_tag(Tag::Compression)? {
Some(val) => CompressionMethod::from_u16(val.into_u16()?)
.ok_or(TiffUnsupportedError::UnknownCompressionMethod)?,
None => CompressionMethod::None,
};
let jpeg_tables = if compression_method == CompressionMethod::ModernJPEG
&& ifd.contains_key(&Tag::JPEGTables)
{
let vec = tag_reader
.find_tag(Tag::JPEGTables)?
.unwrap()
.into_u8_vec()?;
if vec.len() < 2 {
return Err(TiffError::FormatError(
TiffFormatError::InvalidTagValueType(Tag::JPEGTables),
));
}
Some(vec)
} else {
None
};
let samples = tag_reader
.find_tag(Tag::SamplesPerPixel)?
.map(Value::into_u16)
.transpose()?
.unwrap_or(1)
.try_into()?;
let sample_format = match tag_reader.find_tag_uint_vec(Tag::SampleFormat)? {
Some(vals) => {
let sample_format: Vec<_> = vals
.into_iter()
.map(SampleFormat::from_u16_exhaustive)
.collect();
// TODO: for now, only homogenous formats across samples are supported.
if !sample_format.windows(2).all(|s| s[0] == s[1]) {
return Err(TiffUnsupportedError::UnsupportedSampleFormat(sample_format).into());
}
sample_format
}
None => vec![SampleFormat::Uint],
};
let bits_per_sample = match samples {
1 | 3 | 4 => tag_reader
.find_tag_uint_vec(Tag::BitsPerSample)?
.unwrap_or_else(|| vec![1]),
_ => return Err(TiffUnsupportedError::UnsupportedSampleDepth(samples).into()),
};
let predictor = tag_reader
.find_tag(Tag::Predictor)?
.map(Value::into_u16)
.transpose()?
.map(|p| {
Predictor::from_u16(p)
.ok_or(TiffError::FormatError(TiffFormatError::UnknownPredictor(p)))
})
.transpose()?
.unwrap_or(Predictor::None);
let chunk_type;
let chunk_offsets;
let chunk_bytes;
let strip_decoder;
let tile_attributes;
match (
ifd.contains_key(&Tag::StripByteCounts),
ifd.contains_key(&Tag::StripOffsets),
ifd.contains_key(&Tag::TileByteCounts),
ifd.contains_key(&Tag::TileOffsets),
) {
(true, true, false, false) => {
chunk_type = ChunkType::Strip;
chunk_offsets = tag_reader
.find_tag(Tag::StripOffsets)?
.unwrap()
.into_u64_vec()?;
chunk_bytes = tag_reader
.find_tag(Tag::StripByteCounts)?
.unwrap()
.into_u64_vec()?;
let rows_per_strip = tag_reader
.find_tag(Tag::RowsPerStrip)?
.map(Value::into_u32)
.transpose()?
.unwrap_or(height);
strip_decoder = Some(StripDecodeState { rows_per_strip });
tile_attributes = None;
if chunk_offsets.len() != chunk_bytes.len() {
return Err(TiffError::FormatError(
TiffFormatError::InconsistentSizesEncountered,
));
}
}
(false, false, true, true) => {
chunk_type = ChunkType::Tile;
let tile_width =
usize::try_from(tag_reader.require_tag(Tag::TileWidth)?.into_u32()?)?;
let tile_length =
usize::try_from(tag_reader.require_tag(Tag::TileLength)?.into_u32()?)?;
if tile_width == 0 {
return Err(TiffFormatError::InvalidTagValueType(Tag::TileWidth).into());
} else if tile_length == 0 {
return Err(TiffFormatError::InvalidTagValueType(Tag::TileLength).into());
}
strip_decoder = None;
tile_attributes = Some(TileAttributes {
image_width: usize::try_from(width)?,
image_height: usize::try_from(height)?,
samples_per_pixel: bits_per_sample.len(),
tile_width,
tile_length,
});
chunk_offsets = tag_reader
.find_tag(Tag::TileOffsets)?
.unwrap()
.into_u64_vec()?;
chunk_bytes = tag_reader
.find_tag(Tag::TileByteCounts)?
.unwrap()
.into_u64_vec()?;
let tile = tile_attributes.as_ref().unwrap();
if chunk_offsets.len() != chunk_bytes.len()
|| chunk_offsets.len() != tile.tiles_down() * tile.tiles_across()
{
return Err(TiffError::FormatError(
TiffFormatError::InconsistentSizesEncountered,
));
}
}
(_, _, _, _) => {
return Err(TiffError::FormatError(
TiffFormatError::StripTileTagConflict,
))
}
};
Ok(Image {
ifd: Some(ifd),
width,
height,
bits_per_sample,
samples,
sample_format,
photometric_interpretation,
compression_method,
jpeg_tables,
predictor,
chunk_type,
strip_decoder,
tile_attributes,
chunk_offsets,
chunk_bytes,
})
}
}
+258 -425
View File
File diff suppressed because it is too large. Load diff
+8
View File
@@ -339,6 +339,14 @@ where
pub fn wrap(reader: R, byte_order: ByteOrder) -> SmartReader<R> {
SmartReader { reader, byte_order }
}
pub fn into_inner(self) -> R {
self.reader
}
}
impl<R: Read + Seek> SmartReader<R> {
pub fn goto_offset(&mut self, offset: u64) -> io::Result<()> {
self.seek(io::SeekFrom::Start(offset)).map(|_| ())
}
}
impl<R> EndianReader for SmartReader<R>
+45
View File
@@ -0,0 +1,45 @@
use std::convert::TryFrom;
use std::io::{Read, Seek};
use crate::tags::Tag;
use crate::{TiffError, TiffFormatError, TiffResult};
use super::ifd::{Directory, Value};
use super::stream::SmartReader;
use super::Limits;
pub(crate) struct TagReader<'a, R: Read + Seek> {
pub reader: &'a mut SmartReader<R>,
pub ifd: &'a Directory,
pub limits: &'a Limits,
pub bigtiff: bool,
}
impl<'a, R: Read + Seek> TagReader<'a, R> {
pub(crate) fn find_tag(&mut self, tag: Tag) -> TiffResult<Option<Value>> {
Ok(match self.ifd.get(&tag) {
Some(entry) => Some(entry.clone().val(self.limits, self.bigtiff, self.reader)?),
None => None,
})
}
pub(crate) fn require_tag(&mut self, tag: Tag) -> TiffResult<Value> {
match self.find_tag(tag)? {
Some(val) => Ok(val),
None => Err(TiffError::FormatError(
TiffFormatError::RequiredTagNotFound(tag),
)),
}
}
pub fn find_tag_uint_vec<T: TryFrom<u64>>(&mut self, tag: Tag) -> TiffResult<Option<Vec<T>>> {
self.find_tag(tag)?
.map(|v| v.into_u64_vec())
.transpose()?
.map(|v| {
v.into_iter()
.map(|u| {
T::try_from(u).map_err(|_| TiffFormatError::InvalidTagValueType(tag).into())
})
.collect()
})
.transpose()
}
}
+6 -33
View File
@@ -344,7 +344,7 @@ fn test_bad_strip_count() {
}
#[test]
fn test_too_big_buffer_size() {
fn fuzzer_testcase1() {
let image = [
73, 73, 42, 0, 8, 0, 0, 0, 8, 0, 0, 1, 4, 0, 1, 0, 0, 0, 99, 255, 255, 254, 1, 1, 4, 0, 1,
0, 0, 0, 158, 0, 0, 251, 3, 1, 3, 255, 254, 255, 255, 0, 1, 0, 0, 0, 6, 1, 3, 0, 1, 0, 0,
@@ -353,14 +353,7 @@ fn test_too_big_buffer_size() {
178,
];
let mut decoder = tiff::decoder::Decoder::new(std::io::Cursor::new(&image)).unwrap();
let err = decoder.read_image().unwrap_err();
match err {
tiff::TiffError::LimitsExceeded => {}
unexpected => panic!("Unexpected error {}", unexpected),
}
let _ = tiff::decoder::Decoder::new(std::io::Cursor::new(&image)).unwrap_err();
}
#[test]
@@ -422,10 +415,7 @@ fn oom_2() {
}
#[test]
fn invalid_jpeg_tag() {
use tiff::tags;
use tiff::{TiffError, TiffFormatError};
fn fuzzer_testcase2() {
let image = [
73, 73, 42, 0, 8, 0, 0, 0, 15, 0, 0, 254, 44, 1, 0, 0, 0, 0, 0, 32, 0, 0, 0, 1, 4, 0, 1, 0,
0, 0, 0, 1, 0, 0, 91, 1, 1, 0, 0, 0, 0, 0, 242, 4, 0, 0, 0, 22, 0, 56, 77, 0, 77, 1, 0, 0,
@@ -437,14 +427,7 @@ fn invalid_jpeg_tag() {
73,
];
let mut decoder = tiff::decoder::Decoder::new(std::io::Cursor::new(&image)).unwrap();
let err = decoder.read_image().unwrap_err();
match err {
TiffError::FormatError(TiffFormatError::InvalidTagValueType(tags::Tag::JPEGTables)) => {}
unexpected => panic!("Unexpected error {}", unexpected),
}
let _ = tiff::decoder::Decoder::new(std::io::Cursor::new(&image)).unwrap_err();
}
#[test]
@@ -474,9 +457,7 @@ fn invalid_jpeg_tag_2() {
}
#[test]
fn multiple_images_strip_height() {
use tiff::TiffError;
fn fuzzer_testcase3() {
let image = [
73, 73, 42, 0, 8, 0, 0, 0, 8, 0, 0, 1, 4, 0, 1, 0, 0, 0, 2, 0, 0, 0, 61, 1, 9, 0, 46, 22,
128, 0, 0, 0, 0, 1, 6, 1, 3, 0, 1, 0, 0, 0, 0, 0, 0, 0, 17, 1, 4, 0, 27, 0, 0, 0, 0, 0, 0,
@@ -485,15 +466,7 @@ fn multiple_images_strip_height() {
255, 255,
];
let mut decoder = tiff::decoder::Decoder::new(std::io::Cursor::new(&image)).unwrap();
let _ = decoder.read_image().unwrap();
let err = decoder.read_image().unwrap_err();
match err {
TiffError::IntSizeError => {}
unexpected => panic!("Unexpected error {}", unexpected),
}
let _ = tiff::decoder::Decoder::new(std::io::Cursor::new(&image)).unwrap_err();
}
#[test]