Deprecate unofficial value types

Seems they were introduced with BigTiff but since the enumeration of the
decoder had no obligation of introducing discriminant values the list
was not cross-referenced to libtiff. Hence, some rational types exist
with no basis in decoding.

.github/workflows/rust.yml

@@ -9,14 +9,14 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        rust: ["1.74.0", stable, beta, nightly]
+        rust: ["1.85.0", stable, beta, nightly]
     steps:
     - uses: actions/checkout@v2
 
     - uses: dtolnay/rust-toolchain@nightly
-      if: ${{ matrix.rust == '1.74.0' }}
+      if: ${{ matrix.rust == '1.85.0' }}
     - name: Generate Cargo.lock with minimal-version dependencies
-      if: ${{ matrix.rust == '1.74.0' }}
+      if: ${{ matrix.rust == '1.85.0' }}
       run: cargo -Zminimal-versions generate-lockfile
 
     - uses: dtolnay/rust-toolchain@v1
@@ -29,7 +29,7 @@ jobs:
     - name: build
       run: cargo build -v
     - name: test
-      if: ${{ matrix.rust != '1.74.0' }}
+      if: ${{ matrix.rust != '1.85.0' }}
       run: cargo test -v && cargo doc -v
 
   features:

CHANGES.md

@@ -1,3 +1,75 @@
+# Version 0.11.0
+
+- `Directory` now implements `FromIterator<(Tag, Value)>`.
+
+Changes:
+- The decoder now interprets the `ExtraSamples` tag. The sample count must now
+  more strict match the expected value with alpha channels only allowing for
+  explicitly denoted unassociated or associated alpha. This effects the
+  indicated color type when decoding images with additional samples indicated
+  as unspecified relation.  Previously, these may have been interpreted as
+  alpha by the total sample count (e.g. RgbA if 4 samples under a photometric
+  interpretation of RGB).
+- The decoder handles planar data, current limited to non-subsampled channels.
+  The `Decoder::read_image` method return planes one-after-another depending on
+  the size of the buffer that was passed.
+- `Decoder::read_image_to_buffer` now takes `&mut DecodingResult` and resizes
+  it according to the required layout. Previously, a borrowed `DecodingBuffer`
+  was passed which can be replaced by calling `as_bytes_mut` and
+  `read_image_bytes`.
+- Several methods of tags are now `const`. Note that does not guarantee any
+  particular value when calling these methods.
+
+Fixes:
+- Fix a bug in the uncompressed encoder that could lead to short writes, i.e.
+  data silently dropped when the underlying writer did not accept all data in a
+  single write call.
+- Encoding YCbCr data now writes the `ChromaSubsampling` tag as `(1, 1)` to
+  indicate no subsampling, instead of leaving it at its default of `(2, 2)`.
+- The decoder will reject subsampled YCbCr data as there is no upsampling
+  routine, except for JPEG compressed images where the JPEG decoders handles
+  this. Since the buffer in that case indicates a full-sized plane for all
+  color samples any future support for the tag will upsample all planes (at
+  least within this major version).
+
+Additions:
+- Added support for the `CieLab` color type.
+- Added `DecodingResult::resize_to` to create a buffer with a matching sample
+  type and dimensions.
+- Added `ByteOrder::native` to access the platform's native endianness.
+- Added `ByteOrder::convert` to change the byte-order of values in a byte
+  buffer, depending on their `Type` as described at runtime.
+- Added `DirectoryOffset::new` to encode a directory whose offset is known to
+  the caller but that has not been written through the encoder itself.
+- Added `Encoder::extra_samples` to encode images with more samples than their
+  color's trait implementation would otherwise suggest.
+- Added `DirectoryEncoder::extend_from` to encode multiple tag entries from a
+  directory whose values were written to the file by means outside the
+  encoder's control.
+- Added `Decoder::read_coding_unit_bytes` to retrieve data of corresponding
+  coordinates from potentially planar data, which is encoded in multiple chunks
+  of the file.
+
+# Version 0.10.3
+
+New features:
+- Group 4 `fax` is now recognized as a compression type and decoded.
+- A crate feature `fax` controls related dependencies, on by default.
+
+Changes:
+- The presence of PhotometricInterpretation::WhiteIsZero now returns an error
+  if the color type can not be inverted by the library where they were
+  previously silently ignored. Please report any missing color types.
+
+Fixes:
+- The PhotometricInterpretation::WhiteIsZero is now also applied to 1-bit
+  images, as well as 2-bit and 4-bit sample types where previously the presence
+  of this tag was ignored.
+
+# Version 0.10.2
+
+Republished 0.10.1, fixing an accidentally removed method (`Decoder::find_tag_unsigned_vec`).
+
 # Version 0.10.1
 
 New features:

Cargo.toml

@@ -1,11 +1,11 @@
 [package]
 name = "tiff"
-version = "0.10.1"
+version = "0.11.0"
 edition = "2021"
 resolver = "2"
 
 # note: when changed, also update test runner in `.github/workflows/rust.yml`
-rust-version = "1.74.0"
+rust-version = "1.85.0"
 
 license = "MIT"
 description = "TIFF decoding and encoding library in pure Rust"
@@ -20,10 +20,12 @@ exclude = ["tests/images/*", "tests/fuzz_images/*"]
 half = { version = "2.4.1" }
 quick-error = "2.0.1"
 
+# Rename to avoid confusion with the feature name.
+fax34 = { package = "fax", version = "0.2.6", optional = true }
 flate2 = { version = "1.0.20", optional = true }
 weezl = { version = "0.1.10", optional = true }
 zstd = { version = "0.13", optional = true }
-zune-jpeg = { version = "0.4.17", optional = true }
+zune-jpeg = { version = "0.5.1", optional = true }
 
 [dev-dependencies]
 criterion = "0.3.1"
@@ -31,10 +33,11 @@ criterion = "0.3.1"
 crc32fast = "1.5"
 
 [features]
-default = ["deflate", "jpeg", "lzw"]
+default = ["deflate", "fax", "jpeg", "lzw"]
 
 # Compression algorithms
 deflate = ["dep:flate2"]
+fax = ["dep:fax34"]
 jpeg = ["dep:zune-jpeg"]
 lzw = ["dep:weezl"]
 zstd = ["dep:zstd"]

README.md

@@ -36,6 +36,7 @@ This table lists photometric interpretations and sample formats which are suppor
 | LZW      | ✓        | ✓        |
 | Deflate  | ✓        | ✓        |
 | PackBits | ✓        | ✓        |
+| Fax4     | ✓        | not yet  |
 | JPEG     | ✓        | not yet  |
 | ZSTD     | ✓        | not yet  |
 

examples/decode.rs

@@ -0,0 +1,103 @@
+use tiff::decoder::{BufferLayoutPreference, Decoder, DecodingBuffer, DecodingResult};
+
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let Some(image) = std::env::args_os().nth(1) else {
+        eprintln!("Usage: decode FILE");
+        return Ok(());
+    };
+
+    let file = std::fs::File::open(image)?;
+    let io = std::io::BufReader::new(file);
+    let mut reader = Decoder::new(io)?;
+
+    let mut data = DecodingResult::I8(vec![]);
+
+    for i in 0u32.. {
+        let colortype = reader.colortype()?;
+        let dimensions = reader.dimensions()?;
+        let layout = reader.read_image_to_buffer(&mut data)?;
+
+        debug_planes(i, &mut data, &layout, &colortype, dimensions);
+
+        if !reader.more_images() {
+            break;
+        }
+
+        reader.next_image()?
+    }
+
+    Ok(())
+}
+
+fn debug_planes(
+    index: u32,
+    data: &mut DecodingResult,
+    layout: &BufferLayoutPreference,
+    colortype: &tiff::ColorType,
+    (width, height): (u32, u32),
+) {
+    let (depth, mut tupltype) = match colortype {
+        tiff::ColorType::Gray(_) => (1, "GRAYSCALE"),
+        tiff::ColorType::RGB(_) => (3, "RGB"),
+        tiff::ColorType::RGBA(_) => (4, "RGB_ALPHA"),
+        tiff::ColorType::Palette(_) => (1, "PALETTE"),
+        tiff::ColorType::CMYK(_) => (4, "CMYK"),
+        tiff::ColorType::Multiband { num_samples: 2, .. } => (2, "GRAYSCALE_ALPHA"),
+        _ => {
+            eprintln!("Unsupported color type for PAM output: {:?}", colortype);
+            return;
+        }
+    };
+
+    let maxval = match data.as_buffer(0) {
+        DecodingBuffer::U8(_) => u64::from(u8::MAX),
+        DecodingBuffer::U16(_) => u64::from(u16::MAX),
+        DecodingBuffer::U32(_) => u64::from(u32::MAX),
+        DecodingBuffer::U64(_) => u64::MAX,
+        // Eh, this is a good effort I guess.
+        DecodingBuffer::I8(items) => {
+            items.iter_mut().for_each(|v| *v = 0.max(*v));
+            u64::from(i8::MAX as u8)
+        }
+        DecodingBuffer::I16(items) => {
+            items.iter_mut().for_each(|v| *v = 0.max(*v));
+            u64::from(i16::MAX as u16)
+        }
+        DecodingBuffer::I32(items) => {
+            items.iter_mut().for_each(|v| *v = 0.max(*v));
+            u64::from(i32::MAX as u32)
+        }
+        DecodingBuffer::I64(items) => {
+            items.iter_mut().for_each(|v| *v = 0.max(*v));
+            i64::MAX as u64
+        }
+        // Not supported by PAM.
+        DecodingBuffer::F16(_) | DecodingBuffer::F32(_) | DecodingBuffer::F64(_) => return,
+    };
+
+    let byte_len = if layout.planes > 1 {
+        tupltype = "GRAYSCALE";
+        layout.plane_stride.unwrap().get()
+    } else {
+        data.as_buffer(0).byte_len()
+    };
+
+    // Write out this image's planes to PAM files.
+    let header = format!("P7\nWIDTH {width}\nHEIGHT {height}\nDEPTH {depth}\nMAXVAL {maxval}\nTUPLTYPE {tupltype}\nENDHDR\n");
+
+    for (plane, plane_data) in data
+        .as_buffer(0)
+        .as_bytes_mut()
+        .chunks_exact(byte_len)
+        .enumerate()
+    {
+        let filename = format!("image_{index:03}_plane_{plane:03}.pam");
+        let mut file = std::fs::File::create(filename).expect("Failed to create output file");
+
+        use std::io::Write;
+        file.write_all(header.as_bytes())
+            .expect("Failed to write PAM header");
+        file.write_all(plane_data)
+            .expect("Failed to write PAM data");
+    }
+}

src/decoder/ifd.rs

@@ -10,8 +10,8 @@ use crate::tags::{IfdPointer, Tag, Type};
 use crate::{TiffError, TiffFormatError, TiffResult};
 
 use self::Value::{
-    Ascii, Byte, Double, Float, Ifd, IfdBig, List, Rational, RationalBig, SRational, SRationalBig,
-    Short, Signed, SignedBig, SignedByte, SignedShort, Unsigned, UnsignedBig,
+    Ascii, Byte, Double, Float, Ifd, IfdBig, List, Rational, SRational, Short, Signed, SignedBig,
+    SignedByte, SignedShort, Unsigned, UnsignedBig,
 };
 
 #[allow(unused_qualifications)]
@@ -30,8 +30,16 @@ pub enum Value {
     Double(f64),
     List(Vec<Value>),
     Rational(u32, u32),
+    #[deprecated(
+        note = "Not implemented in BigTIFF with a standard tag value",
+        since = "0.11.1"
+    )]
     RationalBig(u64, u64),
     SRational(i32, i32),
+    #[deprecated(
+        note = "Not implemented in BigTIFF with a standard tag value",
+        since = "0.11.1"
+    )]
     SRationalBig(i64, i64),
     Ascii(String),
     Ifd(u32),
@@ -170,7 +178,8 @@ impl Value {
             Unsigned(val) => Ok(vec![val]),
             UnsignedBig(val) => Ok(vec![u32::try_from(val)?]),
             Rational(numerator, denominator) => Ok(vec![numerator, denominator]),
-            RationalBig(numerator, denominator) => {
+            #[expect(deprecated)]
+            Value::RationalBig(numerator, denominator) => {
                 Ok(vec![u32::try_from(numerator)?, u32::try_from(denominator)?])
             }
             Ifd(val) => Ok(vec![val]),
@@ -220,7 +229,8 @@ impl Value {
                             new_vec.push(numerator);
                             new_vec.push(denominator);
                         }
-                        SRationalBig(numerator, denominator) => {
+                        #[expect(deprecated)]
+                        Value::SRationalBig(numerator, denominator) => {
                             new_vec.push(i32::try_from(numerator)?);
                             new_vec.push(i32::try_from(denominator)?);
                         }
@@ -234,7 +244,8 @@ impl Value {
             Signed(val) => Ok(vec![val]),
             SignedBig(val) => Ok(vec![i32::try_from(val)?]),
             SRational(numerator, denominator) => Ok(vec![numerator, denominator]),
-            SRationalBig(numerator, denominator) => {
+            #[expect(deprecated)]
+            Value::SRationalBig(numerator, denominator) => {
                 Ok(vec![i32::try_from(numerator)?, i32::try_from(denominator)?])
             }
             _ => Err(TiffError::FormatError(TiffFormatError::InvalidTypeForTag)),
@@ -283,7 +294,8 @@ impl Value {
             Unsigned(val) => Ok(vec![val.into()]),
             UnsignedBig(val) => Ok(vec![val]),
             Rational(numerator, denominator) => Ok(vec![numerator.into(), denominator.into()]),
-            RationalBig(numerator, denominator) => Ok(vec![numerator, denominator]),
+            #[expect(deprecated)]
+            Value::RationalBig(numerator, denominator) => Ok(vec![numerator, denominator]),
             Ifd(val) => Ok(vec![val.into()]),
             IfdBig(val) => Ok(vec![val]),
             Ascii(val) => Ok(val.chars().map(u32::from).map(u64::from).collect()),
@@ -301,7 +313,8 @@ impl Value {
                             new_vec.push(numerator.into());
                             new_vec.push(denominator.into());
                         }
-                        SRationalBig(numerator, denominator) => {
+                        #[expect(deprecated)]
+                        Value::SRationalBig(numerator, denominator) => {
                             new_vec.push(numerator);
                             new_vec.push(denominator);
                         }
@@ -315,7 +328,8 @@ impl Value {
             Signed(val) => Ok(vec![val.into()]),
             SignedBig(val) => Ok(vec![val]),
             SRational(numerator, denominator) => Ok(vec![numerator.into(), denominator.into()]),
-            SRationalBig(numerator, denominator) => Ok(vec![numerator, denominator]),
+            #[expect(deprecated)]
+            Value::SRationalBig(numerator, denominator) => Ok(vec![numerator, denominator]),
             _ => Err(TiffError::FormatError(TiffFormatError::InvalidTypeForTag)),
         }
     }
@@ -332,6 +346,12 @@ impl Value {
     }
 }
 
+/// A combination of type, count, and offset.
+///
+/// In a TIFF the data offset portion of an entry is used for inline data in case the length of the
+/// encoded value does not exceed the size of the offset field. Since the size of the offset field
+/// depends on the file kind (4 bytes for standard TIFF, 8 bytes for BigTIFF) the interpretation of
+/// this struct is only complete in combination with file metadata.
 #[derive(Clone)]
 pub struct Entry {
     type_: Type,
@@ -349,12 +369,14 @@ impl ::std::fmt::Debug for Entry {
 }
 
 impl Entry {
+    /// Create a new entry fit to be added to a standard TIFF IFD.
     pub fn new(type_: Type, count: u32, offset: [u8; 4]) -> Entry {
         let mut entry_off = [0u8; 8];
         entry_off[..4].copy_from_slice(&offset);
         Entry::new_u64(type_, count.into(), entry_off)
     }
 
+    /// Create a new entry with data for a Big TIFF IFD.
     pub fn new_u64(type_: Type, count: u64, offset: [u8; 8]) -> Entry {
         Entry {
             type_,
@@ -376,7 +398,10 @@ impl Entry {
     }
 
     /// Returns a mem_reader for the offset/value field
-    fn r(&self, byte_order: ByteOrder) -> EndianReader<io::Cursor<Vec<u8>>> {
+    pub(crate) fn offset_field_reader(
+        &self,
+        byte_order: ByteOrder,
+    ) -> EndianReader<io::Cursor<Vec<u8>>> {
         EndianReader::new(io::Cursor::new(self.offset.to_vec()), byte_order)
     }
 
@@ -392,43 +417,25 @@ impl Entry {
         }
 
         let bo = reader.byte_order;
-
-        let tag_size = match self.type_ {
-            Type::BYTE | Type::SBYTE | Type::ASCII | Type::UNDEFINED => 1,
-            Type::SHORT | Type::SSHORT => 2,
-            Type::LONG | Type::SLONG | Type::FLOAT | Type::IFD => 4,
-            Type::LONG8
-            | Type::SLONG8
-            | Type::DOUBLE
-            | Type::RATIONAL
-            | Type::SRATIONAL
-            | Type::IFD8 => 8,
-        };
-
-        let value_bytes = match self.count.checked_mul(tag_size) {
-            Some(n) => n,
-            None => {
-                return Err(TiffError::LimitsExceeded);
-            }
-        };
+        let value_bytes = self.type_.value_bytes(self.count)?;
 
         // Case 2: there is one value.
         if self.count == 1 {
             // 2a: the value is 5-8 bytes and we're in BigTiff mode.
             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()?),
-                    Type::DOUBLE => Double(self.r(bo).read_f64()?),
+                    Type::LONG8 => UnsignedBig(self.offset_field_reader(bo).read_u64()?),
+                    Type::SLONG8 => SignedBig(self.offset_field_reader(bo).read_i64()?),
+                    Type::DOUBLE => Double(self.offset_field_reader(bo).read_f64()?),
                     Type::RATIONAL => {
-                        let mut r = self.r(bo);
+                        let mut r = self.offset_field_reader(bo);
                         Rational(r.read_u32()?, r.read_u32()?)
                     }
                     Type::SRATIONAL => {
-                        let mut r = self.r(bo);
+                        let mut r = self.offset_field_reader(bo);
                         SRational(r.read_i32()?, r.read_i32()?)
                     }
-                    Type::IFD8 => IfdBig(self.r(bo).read_u64()?),
+                    Type::IFD8 => IfdBig(self.offset_field_reader(bo).read_u64()?),
                     Type::BYTE
                     | Type::SBYTE
                     | Type::ASCII
@@ -447,11 +454,11 @@ impl Entry {
                 Type::BYTE => Byte(self.offset[0]),
                 Type::SBYTE => SignedByte(self.offset[0] as i8),
                 Type::UNDEFINED => Byte(self.offset[0]),
-                Type::SHORT => Short(self.r(bo).read_u16()?),
-                Type::SSHORT => SignedShort(self.r(bo).read_i16()?),
-                Type::LONG => Unsigned(self.r(bo).read_u32()?),
-                Type::SLONG => Signed(self.r(bo).read_i32()?),
-                Type::FLOAT => Float(self.r(bo).read_f32()?),
+                Type::SHORT => Short(self.offset_field_reader(bo).read_u16()?),
+                Type::SSHORT => SignedShort(self.offset_field_reader(bo).read_i16()?),
+                Type::LONG => Unsigned(self.offset_field_reader(bo).read_u32()?),
+                Type::SLONG => Signed(self.offset_field_reader(bo).read_i32()?),
+                Type::FLOAT => Float(self.offset_field_reader(bo).read_f32()?),
                 Type::ASCII => {
                     if self.offset[0] == 0 {
                         Ascii("".to_string())
@@ -460,28 +467,28 @@ impl Entry {
                     }
                 }
                 Type::LONG8 => {
-                    reader.goto_offset(self.r(bo).read_u32()?.into())?;
+                    reader.goto_offset(self.offset_field_reader(bo).read_u32()?.into())?;
                     UnsignedBig(reader.read_u64()?)
                 }
                 Type::SLONG8 => {
-                    reader.goto_offset(self.r(bo).read_u32()?.into())?;
+                    reader.goto_offset(self.offset_field_reader(bo).read_u32()?.into())?;
                     SignedBig(reader.read_i64()?)
                 }
                 Type::DOUBLE => {
-                    reader.goto_offset(self.r(bo).read_u32()?.into())?;
+                    reader.goto_offset(self.offset_field_reader(bo).read_u32()?.into())?;
                     Double(reader.read_f64()?)
                 }
                 Type::RATIONAL => {
-                    reader.goto_offset(self.r(bo).read_u32()?.into())?;
+                    reader.goto_offset(self.offset_field_reader(bo).read_u32()?.into())?;
                     Rational(reader.read_u32()?, reader.read_u32()?)
                 }
                 Type::SRATIONAL => {
-                    reader.goto_offset(self.r(bo).read_u32()?.into())?;
+                    reader.goto_offset(self.offset_field_reader(bo).read_u32()?.into())?;
                     SRational(reader.read_i32()?, reader.read_i32()?)
                 }
-                Type::IFD => Ifd(self.r(bo).read_u32()?),
+                Type::IFD => Ifd(self.offset_field_reader(bo).read_u32()?),
                 Type::IFD8 => {
-                    reader.goto_offset(self.r(bo).read_u32()?.into())?;
+                    reader.goto_offset(self.offset_field_reader(bo).read_u32()?.into())?;
                     IfdBig(reader.read_u64()?)
                 }
             });
@@ -512,7 +519,7 @@ impl Entry {
                     ));
                 }
                 Type::SHORT => {
-                    let mut r = self.r(bo);
+                    let mut r = self.offset_field_reader(bo);
                     let mut v = Vec::new();
                     for _ in 0..self.count {
                         v.push(Short(r.read_u16()?));
@@ -520,7 +527,7 @@ impl Entry {
                     return Ok(List(v));
                 }
                 Type::SSHORT => {
-                    let mut r = self.r(bo);
+                    let mut r = self.offset_field_reader(bo);
                     let mut v = Vec::new();
                     for _ in 0..self.count {
                         v.push(SignedShort(r.read_i16()?));
@@ -528,7 +535,7 @@ impl Entry {
                     return Ok(List(v));
                 }
                 Type::LONG => {
-                    let mut r = self.r(bo);
+                    let mut r = self.offset_field_reader(bo);
                     let mut v = Vec::new();
                     for _ in 0..self.count {
                         v.push(Unsigned(r.read_u32()?));
@@ -536,7 +543,7 @@ impl Entry {
                     return Ok(List(v));
                 }
                 Type::SLONG => {
-                    let mut r = self.r(bo);
+                    let mut r = self.offset_field_reader(bo);
                     let mut v = Vec::new();
                     for _ in 0..self.count {
                         v.push(Signed(r.read_i32()?));
@@ -544,7 +551,7 @@ impl Entry {
                     return Ok(List(v));
                 }
                 Type::FLOAT => {
-                    let mut r = self.r(bo);
+                    let mut r = self.offset_field_reader(bo);
                     let mut v = Vec::new();
                     for _ in 0..self.count {
                         v.push(Float(r.read_f32()?));
@@ -552,7 +559,7 @@ impl Entry {
                     return Ok(List(v));
                 }
                 Type::IFD => {
-                    let mut r = self.r(bo);
+                    let mut r = self.offset_field_reader(bo);
                     let mut v = Vec::new();
                     for _ in 0..self.count {
                         v.push(Ifd(r.read_u32()?));
@@ -571,74 +578,149 @@ impl Entry {
         }
 
         // Case 4: there is more than one value, and it doesn't fit in the offset field.
+        let mut v;
+        self.set_reader_offset(bo, bigtiff, reader)?;
+
         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, bigtiff, limits, reader, |reader| {
-                let mut buf = [0; 1];
-                reader.inner().read_exact(&mut buf)?;
-                Ok(UnsignedBig(u64::from(buf[0])))
-            }),
-            Type::SBYTE => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                Ok(SignedBig(i64::from(reader.read_i8()?)))
-            }),
-            Type::SHORT => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                Ok(Short(reader.read_u16()?))
-            }),
-            Type::SSHORT => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                Ok(SignedShort(reader.read_i16()?))
-            }),
-            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, bigtiff, limits, reader, |reader| {
-                Ok(Signed(reader.read_i32()?))
-            }),
-            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, bigtiff, limits, reader, |reader| {
-                Ok(Double(reader.read_f64()?))
-            }),
+            Type::BYTE | Type::UNDEFINED => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(bytes.iter().copied().map(Byte))
+                })
+            }
+            Type::SBYTE => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(bytes.iter().copied().map(|v| SignedByte(v as i8)))
+                })
+            }
+            Type::SHORT => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(2)
+                            .map(|ch| Short(u16::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::SSHORT => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(2)
+                            .map(|ch| SignedShort(i16::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::LONG => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(4)
+                            .map(|ch| Unsigned(u32::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::SLONG => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(4)
+                            .map(|ch| Signed(i32::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::FLOAT => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(4)
+                            .map(|ch| Float(f32::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::DOUBLE => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(8)
+                            .map(|ch| Double(f64::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
             Type::RATIONAL => {
-                self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                    Ok(Rational(reader.read_u32()?, reader.read_u32()?))
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(bytes.chunks_exact(8).map(|ch| {
+                        Rational(
+                            u32::from_ne_bytes(ch[..4].try_into().unwrap()),
+                            u32::from_ne_bytes(ch[4..].try_into().unwrap()),
+                        )
+                    }))
                 })
             }
             Type::SRATIONAL => {
-                self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                    Ok(SRational(reader.read_i32()?, reader.read_i32()?))
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(bytes.chunks_exact(8).map(|ch| {
+                        SRational(
+                            i32::from_ne_bytes(ch[..4].try_into().unwrap()),
+                            i32::from_ne_bytes(ch[4..].try_into().unwrap()),
+                        )
+                    }))
                 })
             }
-            Type::LONG8 => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                Ok(UnsignedBig(reader.read_u64()?))
-            }),
-            Type::SLONG8 => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                Ok(SignedBig(reader.read_i64()?))
-            }),
-            Type::IFD => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                Ok(Ifd(reader.read_u32()?))
-            }),
-            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.inner().read_exact(&mut buf)?;
-                    Ok(Byte(buf[0]))
+            Type::LONG8 => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(8)
+                            .map(|ch| UnsignedBig(u64::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::SLONG8 => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(8)
+                            .map(|ch| SignedBig(i64::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::IFD => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(4)
+                            .map(|ch| Ifd(u32::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
+                })
+            }
+            Type::IFD8 => {
+                v = Self::vec_with_capacity(self.count, limits)?;
+                self.decode_values(self.count, self.type_, reader, |bytes| {
+                    v.extend(
+                        bytes
+                            .chunks_exact(8)
+                            .map(|ch| IfdBig(u64::from_ne_bytes(ch.try_into().unwrap()))),
+                    )
                 })
             }
             Type::ASCII => {
                 let n = usize::try_from(self.count)?;
-                if n > limits.decoding_buffer_size {
-                    return Err(TiffError::LimitsExceeded);
-                }
 
-                if bigtiff {
-                    reader.goto_offset(self.r(bo).read_u64()?)?
-                } else {
-                    reader.goto_offset(self.r(bo).read_u32()?.into())?
+                if n > limits.decoding_buffer_size {
+                    return Err(dbg!(TiffError::LimitsExceeded));
                 }
 
                 let mut out = vec![0; n];
@@ -647,43 +729,81 @@ impl Entry {
                 if let Some(first) = out.iter().position(|&b| b == 0) {
                     out.truncate(first);
                 }
-                Ok(Ascii(String::from_utf8(out)?))
+
+                return Ok(Ascii(String::from_utf8(out)?));
             }
-        }
+        }?;
+
+        Ok(List(v))
     }
 
-    #[inline]
-    fn decode_offset<R, F>(
-        &self,
+    fn vec_with_capacity(
         value_count: u64,
-        bo: ByteOrder,
-        bigtiff: bool,
         limits: &super::Limits,
-        reader: &mut EndianReader<R>,
-        decode_fn: F,
-    ) -> TiffResult<Value>
-    where
-        R: Read + Seek,
-        F: Fn(&mut EndianReader<R>) -> TiffResult<Value>,
-    {
+    ) -> Result<Vec<Value>, TiffError> {
         let value_count = usize::try_from(value_count)?;
+
         if value_count > limits.decoding_buffer_size / mem::size_of::<Value>() {
             return Err(TiffError::LimitsExceeded);
         }
 
-        let mut v = Vec::with_capacity(value_count);
+        Ok(Vec::with_capacity(value_count))
+    }
 
+    fn set_reader_offset<R>(
+        &self,
+        bo: ByteOrder,
+        bigtiff: bool,
+        reader: &mut EndianReader<R>,
+    ) -> TiffResult<()>
+    where
+        R: Read + Seek,
+    {
         let offset = if bigtiff {
-            self.r(bo).read_u64()?
+            self.offset_field_reader(bo).read_u64()?
         } else {
-            self.r(bo).read_u32()?.into()
+            self.offset_field_reader(bo).read_u32()?.into()
         };
+
         reader.goto_offset(offset)?;
 
-        for _ in 0..value_count {
-            v.push(decode_fn(reader)?)
+        Ok(())
+    }
+
+    #[inline]
+    fn decode_values<R, F>(
+        &self,
+        value_count: u64,
+        type_: Type,
+        reader: &mut EndianReader<R>,
+        mut collect: F,
+    ) -> TiffResult<()>
+    where
+        R: Read + Seek,
+        F: FnMut(&[u8]),
+    {
+        let mut total_bytes = type_.value_bytes(value_count)?;
+        let mut buffer = [0u8; 512];
+
+        let buf_unit = usize::from(type_.byte_len());
+        let mul_of_ty = buffer.len() / buf_unit * buf_unit;
+
+        let cls = type_.endian_bytes();
+        let native = ByteOrder::native();
+
+        while total_bytes > 0 {
+            // `now <= mul_of_ty < 512` so casting is mathematical
+            let now = total_bytes.min(mul_of_ty as u64);
+            total_bytes -= now;
+
+            let buffer = &mut buffer[..now as usize];
+            reader.inner().read_exact(buffer)?;
+
+            reader.byte_order.convert_endian_bytes(cls, buffer, native);
+            collect(buffer);
         }
-        Ok(List(v))
+
+        Ok(())
     }
 }
 

src/decoder/image.rs

@@ -4,13 +4,14 @@ use super::tag_reader::TagReader;
 use super::ChunkType;
 use super::{predict_f16, predict_f32, predict_f64, ValueReader};
 use crate::tags::{
-    CompressionMethod, PhotometricInterpretation, PlanarConfiguration, Predictor, SampleFormat, Tag,
+    CompressionMethod, ExtraSamples, PhotometricInterpretation, PlanarConfiguration, Predictor,
+    SampleFormat, Tag,
 };
 use crate::{
     ColorType, Directory, TiffError, TiffFormatError, TiffResult, TiffUnsupportedError, UsageError,
 };
+
 use std::io::{self, Cursor, Read, Seek};
-use std::num::NonZeroUsize;
 use std::sync::Arc;
 
 #[derive(Debug)]
@@ -68,6 +69,11 @@ pub(crate) struct Image {
     pub height: u32,
     pub bits_per_sample: u8,
     pub samples: u16,
+    /// The `ExtraSamples`, defaulting to empty if not given.
+    pub extra_samples: Vec<ExtraSamples>,
+    /// Number of samples that belong to the photometric interpretation, samples except
+    /// `ExtraSamples` (338, 0x0152) tag.
+    pub photometric_samples: u16,
     pub sample_format: SampleFormat,
     pub photometric_interpretation: PhotometricInterpretation,
     pub compression_method: CompressionMethod,
@@ -79,6 +85,58 @@ pub(crate) struct Image {
     pub tile_attributes: Option<TileAttributes>,
     pub chunk_offsets: Vec<u64>,
     pub chunk_bytes: Vec<u64>,
+    pub chroma_subsampling: (u16, u16),
+}
+
+/// Describes how to read a tile-aligned portion of the image.
+#[derive(Clone)]
+pub(crate) struct ReadoutLayout {
+    /// The planar configuration, which applies to both the underlying image and the output buffer.
+    /// This may be relaxed if we find a clean enough way to provide it.
+    pub planar_config: PlanarConfiguration,
+
+    /// The sample interpretation (interpret with planar_config).
+    ///
+    /// FIXME: we should not require this here. The ability to turn out the raw bytes from the
+    /// sample arrays is very different from turning out interpretable color. Firstly we can always
+    /// readout `Multiband` but currently only use that ColorType in special circumstances (it must
+    /// not overlap cases where actually want to use a ColorType).
+    ///
+    /// And then we have CIE Lab, which uses a tuple of `(u8, i8, i8)`, that is still filterable
+    /// but still not represented by any of our `DecoderResult` variants. Other color variants
+    /// depend on extra tags (YCbCrCoefficients/0x0211) and we don't have a good side channel to
+    /// tag the output with all that TIFF specific information, so arguably we should process and
+    /// apply those to the data so it becomes a self-contained representation.
+    ///
+    /// This should be computed at a higher level, in `Decoder`, instead.
+    pub color: ColorType,
+    /// The number of bytes from one row to another.
+    pub minimum_row_stride: usize,
+    /// The format of samples (assumed uniform for now, same with depth of `ColorType`).
+    pub sample_format: SampleFormat,
+
+    /// Number of bytes to advance in output per row.
+    pub row_stride: usize,
+    /// Number of bytes to advance in output per chunk in width.
+    pub chunk_row_stride: usize,
+    /// Number of bytes to advance in output per chunk in height.
+    pub chunk_col_stride: usize,
+    /// Number of bytes in output from one plane to another.
+    pub plane_stride: usize,
+
+    /// Bits per sample in the encoded data.
+    pub tiff_bits_per_sample: u8,
+    /// Number of samples in the encoded data.
+    pub tiff_samples: u16,
+    /// Dimensions of the underlying rectangular chunks (tile or strips).
+    pub tiff_chunk_dimensions: (u32, u32),
+    /// Number of bytes in the underlying data with all samples per row of chunks.
+    pub tiff_row_bytes: usize,
+
+    /// Chunks until wrapping to the next row of chunks.
+    pub chunks_across: u32,
+    /// Chunks to advance to get to the next plane of chunks.
+    pub chunks_per_plane: u32,
 }
 
 impl Image {
@@ -133,10 +191,30 @@ impl Image {
             .map(Value::into_u16)
             .transpose()?
             .unwrap_or(1);
+
         if samples == 0 {
             return Err(TiffFormatError::SamplesPerPixelIsZero.into());
         }
 
+        let extra_samples = match tag_reader.find_tag(Tag::ExtraSamples)? {
+            Some(n) => n.into_u16_vec()?,
+            None => vec![],
+        };
+
+        let extra_samples = extra_samples
+            .into_iter()
+            .map(|x| ExtraSamples::from_u16(x).unwrap_or(ExtraSamples::Unspecified))
+            .collect::<Vec<_>>();
+
+        let photometric_samples = match usize::from(samples).checked_sub(extra_samples.len()) {
+            None => {
+                return Err(TiffError::FormatError(
+                    TiffFormatError::InconsistentSizesEncountered,
+                ));
+            }
+            Some(n) => n as u16,
+        };
+
         let sample_format = match tag_reader.find_tag_uint_vec(Tag::SampleFormat)? {
             Some(vals) => {
                 let sample_format: Vec<_> = vals
@@ -144,12 +222,15 @@ impl Image {
                     .map(SampleFormat::from_u16_exhaustive)
                     .collect();
 
+                let Some(format) = sample_format.first().copied() else {
+                    // Reject empty sample formats
+                    return Err(TiffFormatError::InvalidTagValueType(Tag::SampleFormat).into());
+                };
                 // TODO: for now, only homogenous formats across samples are supported.
-                if !sample_format.windows(2).all(|s| s[0] == s[1]) {
+                if !sample_format.iter().all(|&s| s == format) {
                     return Err(TiffUnsupportedError::UnsupportedSampleFormat(sample_format).into());
                 }
-
-                sample_format[0]
+                format
             }
             None => SampleFormat::Uint,
         };
@@ -160,7 +241,7 @@ impl Image {
 
         // Technically bits_per_sample.len() should be *equal* to samples, but libtiff also allows
         // it to be a single value that applies to all samples.
-        if bits_per_sample.len() != samples.into() && bits_per_sample.len() != 1 {
+        if bits_per_sample.len() != usize::from(samples) && bits_per_sample.len() != 1 {
             return Err(TiffError::FormatError(
                 TiffFormatError::InconsistentSizesEncountered,
             ));
@@ -195,6 +276,25 @@ impl Image {
             .transpose()?
             .unwrap_or(PlanarConfiguration::Chunky);
 
+        let ycbcr_subsampling = tag_reader.find_tag_uint_vec::<u16>(Tag::ChromaSubsampling)?;
+
+        let chroma_subsampling = if let Some(subsamples) = &ycbcr_subsampling {
+            let [a, b] = subsamples.as_slice() else {
+                return Err(TiffError::FormatError(TiffFormatError::InvalidCountForTag(
+                    Tag::ChromaSubsampling,
+                    subsamples.len(),
+                )));
+            };
+
+            // ImageWidth and ImageLength are constrained to be integer multiples of
+            // YCbCrSubsampleHoriz and YCbCrSubsampleVert respectively. TileWidth and TileLength
+            // have the same constraints. RowsPerStrip must be an integer multiple of
+            // YCbCrSubsampleVert.
+            (*a, *b)
+        } else {
+            (2, 2)
+        };
+
         let planes = match planar_config {
             PlanarConfiguration::Chunky => 1,
             PlanarConfiguration::Planar => samples,
@@ -293,6 +393,8 @@ impl Image {
             height,
             bits_per_sample: bits_per_sample[0],
             samples,
+            extra_samples,
+            photometric_samples,
             sample_format,
             photometric_interpretation,
             compression_method,
@@ -304,19 +406,24 @@ impl Image {
             tile_attributes,
             chunk_offsets,
             chunk_bytes,
+            chroma_subsampling,
         })
     }
 
     pub(crate) fn colortype(&self) -> TiffResult<ColorType> {
+        let is_alpha_extra_samples = matches!(
+            self.extra_samples.as_slice(),
+            [ExtraSamples::AssociatedAlpha, ..] | [ExtraSamples::UnassociatedAlpha, ..]
+        );
+
         match self.photometric_interpretation {
-            PhotometricInterpretation::RGB => match self.samples {
-                3 => Ok(ColorType::RGB(self.bits_per_sample)),
+            PhotometricInterpretation::RGB => match self.photometric_samples {
+                3 => Ok(if is_alpha_extra_samples {
+                    ColorType::RGBA(self.bits_per_sample)
+                } else {
+                    ColorType::RGB(self.bits_per_sample)
+                }),
                 4 => Ok(ColorType::RGBA(self.bits_per_sample)),
-                // FIXME: We should _ignore_ other components. In particular:
-                // > Beware of extra components. Some TIFF files may have more components per pixel
-                // than you think. A Baseline TIFF reader must skip over them gracefully,using the
-                // values of the SamplesPerPixel and BitsPerSample fields.
-                // > -- TIFF 6.0 Specification, Section 7, Additional Baseline requirements.
                 _ => Err(TiffError::UnsupportedError(
                     TiffUnsupportedError::InterpretationWithBits(
                         self.photometric_interpretation,
@@ -324,8 +431,12 @@ impl Image {
                     ),
                 )),
             },
-            PhotometricInterpretation::CMYK => match self.samples {
-                4 => Ok(ColorType::CMYK(self.bits_per_sample)),
+            PhotometricInterpretation::CMYK => match self.photometric_samples {
+                4 => Ok(if is_alpha_extra_samples {
+                    ColorType::CMYKA(self.bits_per_sample)
+                } else {
+                    ColorType::CMYK(self.bits_per_sample)
+                }),
                 5 => Ok(ColorType::CMYKA(self.bits_per_sample)),
                 _ => Err(TiffError::UnsupportedError(
                     TiffUnsupportedError::InterpretationWithBits(
@@ -334,7 +445,7 @@ impl Image {
                     ),
                 )),
             },
-            PhotometricInterpretation::YCbCr => match self.samples {
+            PhotometricInterpretation::YCbCr => match self.photometric_samples {
                 3 => Ok(ColorType::YCbCr(self.bits_per_sample)),
                 _ => Err(TiffError::UnsupportedError(
                     TiffUnsupportedError::InterpretationWithBits(
@@ -343,7 +454,13 @@ impl Image {
                     ),
                 )),
             },
+            // TODO: treatment of WhiteIsZero is not quite consistent with `invert_colors` that is
+            // later called when that interpretation is read. That function does not support
+            // Multiband as a color type and will error. It's unclear how to resolve that exactly.
             PhotometricInterpretation::BlackIsZero | PhotometricInterpretation::WhiteIsZero => {
+                // Note: compatibility with previous implementation requires us to return extra
+                // samples as `Multiband`. For gray images however the better choice would be
+                // returning a `Gray` color, i.e. matching on `photometric_samples` instead.
                 match self.samples {
                     1 => Ok(ColorType::Gray(self.bits_per_sample)),
                     _ => Ok(ColorType::Multiband {
@@ -352,39 +469,70 @@ impl Image {
                     }),
                 }
             }
-            // TODO: this is bad we should not fail at this point
-            PhotometricInterpretation::RGBPalette
-            | PhotometricInterpretation::TransparencyMask
-            | PhotometricInterpretation::CIELab => Err(TiffError::UnsupportedError(
+            // ```
+            // struct IccLab /* Interpretation 9* {
+            //     pub L: u8, // SampleFormat::Uint
+            //     pub a: u8, // SampleFormat::Uint, defined as TiffLab::a + 128
+            //     pub b: u8, // SampleFormat::Uint, defined as TiffLab::b + 128
+            // }
+            // ```
+            PhotometricInterpretation::IccLab => match self.photometric_samples {
+                3 if matches!(self.sample_format, SampleFormat::Uint) => {
+                    Ok(ColorType::Lab(self.bits_per_sample))
+                }
+                _ => Err(TiffError::UnsupportedError(
+                    TiffUnsupportedError::InterpretationWithBits(
+                        self.photometric_interpretation,
+                        vec![self.bits_per_sample; self.samples as usize],
+                    ),
+                )),
+            },
+            // Unsupported due to inherently heterogeneous sample types. This is represented as:
+            // ```
+            // struct TiffLab /* Interpretation 8* {
+            //     pub L: u8, // SampleFormat::Uint
+            //     pub a: i8, // SampleFormat::Int
+            //     pub b: i8, // SampleFormat::Int
+            // }
+            // ```
+            PhotometricInterpretation::CIELab => Err(TiffError::UnsupportedError(
                 TiffUnsupportedError::InterpretationWithBits(
-                    self.photometric_interpretation,
+                    PhotometricInterpretation::CIELab,
                     vec![self.bits_per_sample; self.samples as usize],
                 ),
             )),
+            // Unsupported due to extra unfiltering and conversion steps. We need to find the
+            // Decode tag (SRATIONAL; 2 * SamplesPerPixel) and apply the following conversion:
+            //
+            // L* = Decode[0] + Lsample x (Decode[1] - Decode[0]) / (2^n -1)
+            // …
+            //
+            // So we'll have a larger depth in the output and either worry about reducing fractions
+            // or turn everything into floats. That's a lot of decisions.
+            PhotometricInterpretation::ItuLab => Err(TiffError::UnsupportedError(
+                TiffUnsupportedError::InterpretationWithBits(
+                    PhotometricInterpretation::CIELab,
+                    vec![self.bits_per_sample; self.samples as usize],
+                ),
+            )),
+            PhotometricInterpretation::RGBPalette | PhotometricInterpretation::TransparencyMask => {
+                Err(TiffError::UnsupportedError(
+                    TiffUnsupportedError::InterpretationWithBits(
+                        self.photometric_interpretation,
+                        vec![self.bits_per_sample; self.samples as usize],
+                    ),
+                ))
+            }
         }
     }
 
-    pub(crate) fn minimum_row_stride(&self, dims: (u32, u32)) -> Option<NonZeroUsize> {
-        let (width, height) = dims;
-
-        let row_stride = u64::from(width)
-            .saturating_mul(self.samples_per_pixel() as u64)
-            .saturating_mul(self.bits_per_sample as u64)
-            .div_ceil(8);
-
-        // Note: row stride should be smaller than the len if we have an actual buffer. If there
-        // are no pixels in the buffer (height _or_ width is 0) then the stride is not well defined
-        // and we return `None`.
-        (height > 0)
-            .then_some(row_stride as usize)
-            .and_then(NonZeroUsize::new)
-    }
-
     fn create_reader<'r, R: 'r + Read>(
         reader: R,
         compression_method: CompressionMethod,
         compressed_length: u64,
-        #[allow(unused_variables)] jpeg_tables: Option<&[u8]>,
+        // FIXME: these should be `expect` attributes or we choose another way of passing them.
+        #[cfg_attr(not(feature = "jpeg"), allow(unused_variables))] jpeg_tables: Option<&[u8]>,
+        #[cfg_attr(not(feature = "fax"), allow(unused_variables))] dimensions: (u32, u32),
     ) -> TiffResult<Box<dyn Read + 'r>> {
         Ok(match compression_method {
             CompressionMethod::None => Box::new(reader),
@@ -436,13 +584,14 @@ impl Image {
                 let mut jpeg_data = Vec::new();
                 jpeg_reader.read_to_end(&mut jpeg_data)?;
 
-                let mut decoder = zune_jpeg::JpegDecoder::new(jpeg_data);
+                let mut decoder =
+                    zune_jpeg::JpegDecoder::new(zune_core::bytestream::ZCursor::new(jpeg_data));
                 let mut options: zune_core::options::DecoderOptions = Default::default();
 
                 // Disable color conversion by setting the output colorspace to the input
                 // colorspace.
                 decoder.decode_headers()?;
-                if let Some(colorspace) = decoder.get_input_colorspace() {
+                if let Some(colorspace) = decoder.input_colorspace() {
                     options = options.jpeg_set_out_colorspace(colorspace);
                 }
 
@@ -452,6 +601,12 @@ impl Image {
 
                 Box::new(Cursor::new(data))
             }
+            #[cfg(feature = "fax")]
+            CompressionMethod::Fax4 => Box::new(super::stream::Group4Reader::new(
+                dimensions,
+                reader,
+                compressed_length,
+            )?),
             method => {
                 return Err(TiffError::UnsupportedError(
                     TiffUnsupportedError::UnsupportedCompressionMethod(method),
@@ -467,18 +622,25 @@ impl Image {
     /// Example with `bits_per_sample = [8, 8, 8]` and `PhotometricInterpretation::RGB`:
     /// * `PlanarConfiguration::Chunky` -> 3 (RGBRGBRGB...)
     /// * `PlanarConfiguration::Planar` -> 1 (RRR...) (GGG...) (BBB...)
-    pub(crate) fn samples_per_pixel(&self) -> usize {
+    pub(crate) fn samples_per_pixel(&self) -> u16 {
         match self.planar_config {
-            PlanarConfiguration::Chunky => self.samples.into(),
+            PlanarConfiguration::Chunky => self.samples,
+            PlanarConfiguration::Planar => 1,
+        }
+    }
+
+    pub(crate) fn samples_per_out_texel(&self, color: ColorType) -> u16 {
+        match self.planar_config {
+            PlanarConfiguration::Chunky => color.num_samples(),
             PlanarConfiguration::Planar => 1,
         }
     }
 
     /// Number of strips per pixel.
-    pub(crate) fn strips_per_pixel(&self) -> usize {
+    pub(crate) fn strips_per_pixel(&self) -> u16 {
         match self.planar_config {
             PlanarConfiguration::Chunky => 1,
-            PlanarConfiguration::Planar => self.samples.into(),
+            PlanarConfiguration::Planar => self.samples,
         }
     }
 
@@ -516,14 +678,107 @@ impl Image {
         }
     }
 
+    pub(crate) fn readout_for_image(&self) -> TiffResult<ReadoutLayout> {
+        let Image { width, height, .. } = *self;
+        self.readout_for_size(width, height)
+    }
+
+    /// Get the layout for reading out a tile-aligned portion of the image.
+    ///
+    /// The provided width and height should be less than or equal to the image dimensions.
+    pub(crate) fn readout_for_size(&self, width: u32, height: u32) -> TiffResult<ReadoutLayout> {
+        let color = self.colortype()?;
+
+        let tiff_samples = self.samples_per_pixel();
+        let tiff_bits_per_sample = self.bits_per_sample;
+        let data_samples = self.samples_per_out_texel(color);
+        let tiff_chunk_dimensions = self.chunk_dimensions()?;
+        let strips_per_pixel = self.strips_per_pixel();
+
+        let data_dimensions = (width, height);
+
+        let tiff_row_bits = (u64::from(tiff_chunk_dimensions.0) * u64::from(tiff_bits_per_sample))
+            .checked_mul(u64::from(tiff_samples))
+            .ok_or(TiffError::LimitsExceeded)?;
+        let tiff_row_bytes: usize = tiff_row_bits.div_ceil(8).try_into()?;
+
+        let chunk_row_bits = (u64::from(tiff_chunk_dimensions.0) * u64::from(tiff_bits_per_sample))
+            .checked_mul(u64::from(data_samples))
+            .ok_or(TiffError::LimitsExceeded)?;
+        let chunk_row_bytes: usize = chunk_row_bits.div_ceil(8).try_into()?;
+
+        let data_row_bits = (u64::from(data_dimensions.0) * u64::from(tiff_bits_per_sample))
+            .checked_mul(u64::from(data_samples))
+            .ok_or(TiffError::LimitsExceeded)?;
+        let data_row_bytes: usize = data_row_bits.div_ceil(8).try_into()?;
+
+        let chunk_col_stride: usize = data_row_bits
+            .div_ceil(8)
+            .checked_mul(u64::from(tiff_chunk_dimensions.1))
+            .ok_or(TiffError::LimitsExceeded)?
+            .try_into()?;
+
+        let plane_stride: usize = data_row_bits
+            .div_ceil(8)
+            .checked_mul(u64::from(data_dimensions.1))
+            .ok_or(TiffError::LimitsExceeded)?
+            .try_into()?;
+
+        let minimum_row_stride = data_row_bytes;
+
+        let chunks_across: u32 = data_dimensions.0.div_ceil(tiff_chunk_dimensions.0);
+        let chunks_per_plane = (self.chunk_offsets.len() as u32) / u32::from(strips_per_pixel);
+
+        // We would not get an offset in byte units, sorry, no bit interleaving in the output.
+        if chunks_across > 1 && chunk_row_bits % 8 != 0 {
+            return Err(TiffError::UnsupportedError(
+                TiffUnsupportedError::MisalignedTileBoundaries,
+            ));
+        }
+
+        // Only this color type interprets the tag, which is defined with a default of (2, 2)
+        if matches!(color, ColorType::YCbCr(_)) && self.chroma_subsampling != (1, 1) {
+            // The JPEG library does upsampling for us and defines its buffers correctly
+            // (presumably). All other compression schemes are not supported..
+            //
+            // NOTE: as explained in <fa225e820b96bef35f01bf4685654beeb4a8df0c> we may be better
+            // off supporting this tag by consistently upsampling, not by adjusting the buffer
+            // size. At least as a default this makes more sense and is much more permissive in
+            // case the compression stream disagrees with the tags (we would not have enough / or
+            // the wrong buffer layout if we only asked for subsampled planes in a planar layout).
+            if !matches!(self.compression_method, CompressionMethod::ModernJPEG) {
+                return Err(TiffError::UnsupportedError(
+                    TiffUnsupportedError::ChromaSubsampling,
+                ));
+            }
+        }
+
+        Ok(ReadoutLayout {
+            planar_config: self.planar_config,
+            color,
+            minimum_row_stride,
+            sample_format: self.sample_format,
+            row_stride: data_row_bytes,
+            chunk_row_stride: chunk_row_bytes,
+            chunk_col_stride,
+            plane_stride,
+            tiff_bits_per_sample,
+            tiff_samples,
+            tiff_chunk_dimensions,
+            tiff_row_bytes,
+            chunks_across,
+            chunks_per_plane,
+        })
+    }
+
     pub(crate) fn chunk_data_dimensions(&self, chunk_index: u32) -> TiffResult<(u32, u32)> {
         let dims = self.chunk_dimensions()?;
 
         match self.chunk_type {
             ChunkType::Strip => {
-                let strip_attrs = self.strip_decoder.as_ref().unwrap();
-                let strips_per_band =
-                    self.height.saturating_sub(1) / strip_attrs.rows_per_strip + 1;
+                let rows_per_strip = dims.1;
+                let strips_per_band = self.height.div_ceil(rows_per_strip);
+
                 let strip_height_without_padding = (chunk_index % strips_per_band)
                     .checked_mul(dims.1)
                     .and_then(|x| self.height.checked_sub(x))
@@ -552,7 +807,7 @@ impl Image {
         &self,
         reader: &mut ValueReader<impl Read>,
         buf: &mut [u8],
-        output_row_stride: usize,
+        layout: &ReadoutLayout,
         chunk_index: u32,
     ) -> TiffResult<()> {
         let ValueReader {
@@ -562,10 +817,10 @@ impl Image {
         } = reader;
 
         let byte_order = reader.byte_order;
-        let reader = reader.inner();
 
         // Validate that the color type is supported.
-        let color_type = self.colortype()?;
+        let color_type = layout.color;
+
         match color_type {
             ColorType::RGB(n)
             | ColorType::RGBA(n)
@@ -627,6 +882,7 @@ impl Image {
                 .ok_or(TiffError::FormatError(
                     TiffFormatError::InconsistentSizesEncountered,
                 ))?;
+
         if *compressed_bytes > limits.intermediate_buffer_size as u64 {
             return Err(TiffError::LimitsExceeded);
         }
@@ -634,33 +890,39 @@ impl Image {
         let compression_method = self.compression_method;
         let photometric_interpretation = self.photometric_interpretation;
         let predictor = self.predictor;
-        let samples = self.samples_per_pixel();
 
+        let samples = layout.tiff_samples;
+        let data_samples = layout.samples_per_out_texel();
+
+        // We have two dimensions: the 2d rectangle of encoded data and the 2d rectangle this
+        // takes up in the output. Each has an associated count of bits per pixel. The first
+        // dimension, i.e. a ''row'', is the number of pixels that are encoded with bit packing
+        // while the second is the byte-padded array of each so encoded slices.
+        //
+        // During decoding we map the relevant bits from one to the other.
         let chunk_dims = self.chunk_dimensions()?;
         let data_dims = self.chunk_data_dimensions(chunk_index)?;
 
-        let chunk_row_bits = (u64::from(chunk_dims.0) * u64::from(self.bits_per_sample))
-            .checked_mul(samples as u64)
-            .ok_or(TiffError::LimitsExceeded)?;
-        let chunk_row_bytes: usize = chunk_row_bits.div_ceil(8).try_into()?;
-
-        let data_row_bits = (u64::from(data_dims.0) * u64::from(self.bits_per_sample))
-            .checked_mul(samples as u64)
-            .ok_or(TiffError::LimitsExceeded)?;
-        let data_row_bytes: usize = data_row_bits.div_ceil(8).try_into()?;
+        let chunk_row_bytes: usize = layout.tiff_row_bytes;
+        let data_row_bytes: usize = layout.chunk_row_bytes(data_dims.0)?;
 
         // TODO: Should these return errors instead?
-        assert!(output_row_stride >= data_row_bytes);
-        assert!(buf.len() >= output_row_stride * (data_dims.1 as usize - 1) + data_row_bytes);
+        assert!(layout.minimum_row_stride >= data_row_bytes);
+        assert!(buf.len() >= layout.row_stride * (data_dims.1 as usize - 1) + data_row_bytes);
+
+        let is_all_bits = samples == data_samples;
+        let is_output_chunk_rows = layout.row_stride == chunk_row_bytes;
 
         let mut reader = Self::create_reader(
-            reader,
+            reader.inner(),
             compression_method,
             *compressed_bytes,
             self.jpeg_tables.as_deref().map(|a| &**a),
+            chunk_dims,
         )?;
 
-        if output_row_stride == chunk_row_bytes {
+        if is_output_chunk_rows && is_all_bits {
+            // Here we can read directly into the output buffer itself.
             let tile = &mut buf[..chunk_row_bytes * data_dims.1 as usize];
             reader.read_exact(tile)?;
 
@@ -673,14 +935,15 @@ impl Image {
                     predictor,
                 );
             }
+
             if photometric_interpretation == PhotometricInterpretation::WhiteIsZero {
-                super::invert_colors(tile, color_type, self.sample_format);
+                super::invert_colors(tile, color_type, self.sample_format)?;
             }
         } else if chunk_row_bytes > data_row_bytes && self.predictor == Predictor::FloatingPoint {
             // The floating point predictor shuffles the padding bytes into the encoded output, so
             // this case is handled specially when needed.
             let mut encoded = vec![0u8; chunk_row_bytes];
-            for row in buf.chunks_mut(output_row_stride).take(data_dims.1 as usize) {
+            for row in buf.chunks_mut(layout.row_stride).take(data_dims.1 as usize) {
                 reader.read_exact(&mut encoded)?;
 
                 let row = &mut row[..data_row_bytes];
@@ -691,14 +954,19 @@ impl Image {
                     _ => unreachable!(),
                 }
                 if photometric_interpretation == PhotometricInterpretation::WhiteIsZero {
-                    super::invert_colors(row, color_type, self.sample_format);
+                    super::invert_colors(row, color_type, self.sample_format)?;
                 }
             }
-        } else {
-            for row in buf.chunks_mut(output_row_stride).take(data_dims.1 as usize) {
+        } else if is_all_bits {
+            // We read row-by-row but each row fits in its output buffer.
+            for row in buf.chunks_mut(layout.row_stride).take(data_dims.1 as usize) {
                 let row = &mut row[..data_row_bytes];
-                reader.read_exact(row)?;
+                let used = data_row_bytes.min(chunk_row_bytes);
 
+                // Two ways how we get here: we have more bytes in our chunk data than in the image
+                // we are to read. Then we need to skip the rest of the data. Or we have a bigger
+                // row stride than the chunk contains data, then we  need to fill only the front.
+                reader.read_exact(&mut row[..used])?;
                 // Skip horizontal padding
                 if chunk_row_bytes > data_row_bytes {
                     let len = u64::try_from(chunk_row_bytes - data_row_bytes)?;
@@ -712,12 +980,183 @@ impl Image {
                     byte_order,
                     predictor,
                 );
+
                 if photometric_interpretation == PhotometricInterpretation::WhiteIsZero {
-                    super::invert_colors(row, color_type, self.sample_format);
+                    super::invert_colors(row, color_type, self.sample_format)?;
+                }
+            }
+        } else {
+            // The encoded data potentially takes up more space than the output data so we must be
+            // prepared to discard some of it. That decision is bit-by-bit.
+            let bits_per_pixel = u32::from(self.bits_per_sample) * u32::from(self.samples);
+            // Assumes the photometric samples are always the start.. This is slightly problematic.
+            // To expand spport we should instead have different methods of transforming the read
+            // buffer data, not only the `compact_photometric_bytes` method below and then choose
+            // from the right one with supplied parameters. Then we can also bit-for-bit copy with
+            // a selection for better performance.
+            let photometric_bit_end = u32::from(self.bits_per_sample) * data_samples as u32;
+
+            debug_assert!(bits_per_pixel >= photometric_bit_end);
+
+            if bits_per_pixel % 8 != 0 || photometric_bit_end % 8 != 0 {
+                return Err(TiffError::UnsupportedError(
+                    TiffUnsupportedError::InterpretationWithBits(
+                        self.photometric_interpretation,
+                        vec![self.bits_per_sample; self.samples as usize],
+                    ),
+                ));
+            }
+
+            let photo_range = photometric_bit_end / 8..bits_per_pixel / 8;
+            let mut encoded = vec![0u8; chunk_row_bytes];
+            for row in buf.chunks_mut(layout.row_stride).take(data_dims.1 as usize) {
+                reader.read_exact(&mut encoded)?;
+
+                Self::compact_photometric_bytes(&mut encoded, row, &photo_range);
+
+                super::fix_endianness_and_predict(
+                    row,
+                    color_type.bit_depth(),
+                    samples,
+                    byte_order,
+                    predictor,
+                );
+
+                if photometric_interpretation == PhotometricInterpretation::WhiteIsZero {
+                    super::invert_colors(row, color_type, self.sample_format)?;
                 }
             }
         }
 
         Ok(())
     }
+
+    /// Turn a contiguous buffer of a whole number of raw sample arrays into a whole number of
+    /// photometric sample arrays by removing the extra samples in-between.
+    fn compact_photometric_bytes(
+        raw: &mut [u8],
+        row: &mut [u8],
+        photo_range: &std::ops::Range<u32>,
+    ) {
+        raw.chunks_exact_mut(photo_range.end as usize)
+            .zip(row.chunks_exact_mut(photo_range.start as usize))
+            .for_each(|(src, dst)| {
+                dst.copy_from_slice(&src[..photo_range.start as usize]);
+            });
+    }
+}
+
+impl ReadoutLayout {
+    pub(crate) fn samples_per_out_texel(&self) -> u16 {
+        match self.planar_config {
+            PlanarConfiguration::Chunky => self.color.num_samples(),
+            PlanarConfiguration::Planar => 1,
+        }
+    }
+
+    // For a concrete chunk, which may be a partial border chunk, the byte length of one row of its
+    // pixel data.
+    pub(crate) fn chunk_row_bytes(&self, width: u32) -> TiffResult<usize> {
+        let data_samples = self.samples_per_out_texel();
+        let data_row_bits = (u64::from(width) * u64::from(self.tiff_bits_per_sample))
+            .checked_mul(u64::from(data_samples))
+            .ok_or(TiffError::LimitsExceeded)?;
+        Ok(data_row_bits.div_ceil(8).try_into()?)
+    }
+
+    pub(crate) fn set_row_stride(&mut self, row_stride: usize) -> Result<(), TiffError> {
+        if row_stride < self.minimum_row_stride {
+            return Err(TiffError::UsageError(
+                UsageError::InsufficientOutputRowStride {
+                    needed: self.minimum_row_stride,
+                    requested: row_stride,
+                },
+            ));
+        }
+
+        let data_row_bytes = u64::try_from(row_stride)?;
+
+        let chunk_col_stride = data_row_bytes
+            .checked_mul(u64::from(self.tiff_chunk_dimensions.1))
+            .ok_or(TiffError::LimitsExceeded)?
+            .try_into()?;
+
+        let height = self.plane_stride.checked_div(self.row_stride);
+
+        let plane_stride = height
+            .and_then(|h| data_row_bytes.checked_mul(h as u64))
+            // If height was zero, or the previous stride was zero, there are no bytes in a plane
+            .unwrap_or(0)
+            .try_into()?;
+
+        self.row_stride = row_stride;
+        self.chunk_col_stride = chunk_col_stride;
+        self.plane_stride = plane_stride;
+
+        Ok(())
+    }
+
+    /// Reduce this down to the layout of the output planes.
+    pub(crate) fn to_plane_layout(&self) -> Result<PlaneLayout, TiffError> {
+        let num_planes = self.color.num_samples() / self.samples_per_out_texel();
+
+        // Using the standard range iterator as checked_add on steroids.
+        //
+        // Note: for supporting subsampling, adjust as required.
+        let mut offset = (0..=usize::MAX).step_by(self.plane_stride);
+
+        let plane_offsets = offset.by_ref().take(usize::from(num_planes)).collect();
+
+        // Get the past-the-end of the last plane.
+        //
+        // This also verifies the `take` above was not short.
+        let Some(total_bytes) = offset.next() else {
+            return Err(TiffError::LimitsExceeded);
+        };
+
+        Ok(PlaneLayout {
+            plane_offsets,
+            total_bytes,
+            readout: self.clone(),
+        })
+    }
+}
+
+/// A `ReadoutLayout` with pre-calculated plane information.
+pub(crate) struct PlaneLayout {
+    /// The underlying readout layout.
+    pub readout: ReadoutLayout,
+    /// Buffer offset from one plane of output to the next.
+    pub plane_offsets: Vec<usize>,
+    /// Total number of bytes for all planes in given order.
+    pub total_bytes: usize,
+}
+
+impl PlaneLayout {
+    /// Return the number of planes to extract into the provided buffer.
+    pub(crate) fn used_planes(&self, buffer: &[impl Sized]) -> TiffResult<u16> {
+        self.readout.assert_min_layout(buffer)?;
+        let buffer_len = core::mem::size_of_val(buffer);
+
+        // Note: with differently sized planes this is dependent on the plane.
+        let last_plane_start = buffer_len.checked_sub(self.readout.plane_stride);
+
+        // Find how many planes fit into the output buffer.
+        let used_plane_offsets = self
+            .plane_offsets
+            .iter()
+            .enumerate()
+            // Find the first plane that would not fit completely at its offset.
+            .skip_while(|(_, &offset)| last_plane_start >= Some(offset))
+            .nth(0)
+            // If all planes fit, use all of them.
+            .map_or(self.plane_offsets.len(), |(idx, _)| idx);
+
+        debug_assert!(
+            used_plane_offsets <= usize::from(u16::MAX),
+            "Planes limited by number of samples, which is encoded as u16"
+        );
+
+        Ok(used_plane_offsets as u16)
+    }
 }

src/decoder/stream.rs

@@ -1,15 +1,7 @@
 //! All IO functionality needed for TIFF decoding
-
 use std::io::{self, BufRead, BufReader, Read, Seek, Take};
 
-/// Byte order of the TIFF file.
-#[derive(Clone, Copy, Debug)]
-pub enum ByteOrder {
-    /// little endian byte order
-    LittleEndian,
-    /// big endian byte order
-    BigEndian,
-}
+pub use crate::tags::ByteOrder;
 
 /// Reader that is aware of the byte order.
 #[derive(Debug)]
@@ -46,17 +38,6 @@ impl<R: Read> EndianReader<R> {
         })
     }
 
-    /// Reads an i8
-    #[inline(always)]
-    pub fn read_i8(&mut self) -> Result<i8, io::Error> {
-        let mut n = [0u8; 1];
-        self.reader.read_exact(&mut n)?;
-        Ok(match self.byte_order {
-            ByteOrder::LittleEndian => i8::from_le_bytes(n),
-            ByteOrder::BigEndian => i8::from_be_bytes(n),
-        })
-    }
-
     /// Reads an i16
     #[inline(always)]
     pub fn read_i16(&mut self) -> Result<i16, io::Error> {
@@ -187,9 +168,6 @@ impl<R: Read> Read for LZWReader<R> {
                     }
                 }
                 Ok(weezl::LzwStatus::NoProgress) => {
-                    assert_eq!(result.consumed_in, 0);
-                    assert_eq!(result.consumed_out, 0);
-                    assert!(self.reader.buffer().is_empty());
                     return Err(io::Error::new(
                         io::ErrorKind::UnexpectedEof,
                         "no lzw end code found",
@@ -276,6 +254,106 @@ impl<R: Read> Read for PackBitsReader<R> {
     }
 }
 
+#[cfg(feature = "fax")]
+pub struct Group4Reader<R: Read> {
+    decoder: fax34::decoder::Group4Decoder<io::Bytes<io::BufReader<io::Take<R>>>>,
+    line_buf: io::Cursor<Vec<u8>>,
+    height: u16,
+    width: u16,
+    y: u16,
+}
+
+#[cfg(feature = "fax")]
+impl<R: Read> Group4Reader<R> {
+    pub fn new(
+        dimensions: (u32, u32),
+        reader: R,
+        compressed_length: u64,
+    ) -> crate::TiffResult<Self> {
+        let width = u16::try_from(dimensions.0)?;
+        let height = u16::try_from(dimensions.1)?;
+
+        Ok(Self {
+            decoder: fax34::decoder::Group4Decoder::new(
+                io::BufReader::new(reader.take(compressed_length)).bytes(),
+                width,
+            )?,
+            line_buf: io::Cursor::new(Vec::with_capacity(width.into())),
+            width,
+            height,
+            y: 0,
+        })
+    }
+}
+
+#[cfg(feature = "fax")]
+impl<R: Read> Read for Group4Reader<R> {
+    fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
+        // Either we have not read any line or we are at the end of a line.
+        if self.line_buf.position() as usize == self.line_buf.get_ref().len()
+            && self.y < self.height
+        {
+            let next = self.decoder.advance().map_err(std::io::Error::other)?;
+
+            match next {
+                fax34::decoder::DecodeStatus::End => (),
+                fax34::decoder::DecodeStatus::Incomplete => {
+                    self.y += 1;
+
+                    // We known `transitions` yields exactly `self.width` items (per doc).
+                    // FIXME: performance. We do not need an individual pixel iterator, filling
+                    // memory especially for long runs can be much quicker. The `transitions` are
+                    // the positions at which each run-length ends, i.e. the prefix sum of run
+                    // lengths. Runs in fax4 start with white.
+                    let transitions = fax34::decoder::pels(self.decoder.transition(), self.width);
+
+                    let buffer = self.line_buf.get_mut();
+                    buffer.resize(usize::from(self.width).div_ceil(8), 0u8);
+
+                    let target = &mut buffer[..];
+
+                    // Note: it may seem strange to treat black as 0b1 and white as 0b0 despite all
+                    // our streams by default decoding as-if PhotometricInterpretation::BlackIsMin.
+                    // This is however consistent with libtiff. It seems that fax4's "White"
+                    // differs from what libtiff thinks of as "White". For content, a line of data
+                    // is in runlength encoding of white-black-white-black always starting with
+                    // white. In libtiff, the loop always does both colors in one go and the
+                    // structure is:
+                    //
+                    // ```
+                    // for (; runs < erun; runs += 2)
+                    //   // white run
+                    //       do { *lp++ = 0L; } while (…)
+                    //   // black run
+                    //       do { *lp++ = -1L; } while (…)
+                    // ```
+                    //
+                    // So indeed the Fax4::White run is implemented by filling with zeros.
+                    let mut bits = transitions.map(|c| match c {
+                        fax34::Color::Black => true,
+                        fax34::Color::White => false,
+                    });
+
+                    // Assemble bits in MSB as per our library representation for buffer.
+                    for byte in target {
+                        let mut val = 0;
+
+                        for (idx, bit) in bits.by_ref().take(8).enumerate() {
+                            val |= u8::from(bit) << (7 - idx % 8);
+                        }
+
+                        *byte = val;
+                    }
+
+                    self.line_buf.set_position(0);
+                }
+            }
+        }
+
+        self.line_buf.read(buf)
+    }
+}
+
 #[cfg(test)]
 mod test {
     use super::*;

src/directory.rs

@@ -104,6 +104,28 @@ impl Directory {
             }
         }
     }
+
+    pub(crate) fn encoded_len<K: crate::encoder::TiffKind>(&self) -> u64 {
+        let (len_count, len_offset);
+
+        match std::mem::size_of::<K::OffsetType>() {
+            offset @ 4 => {
+                // non-BigTiff uses a `u16` here.
+                len_count = 2;
+                len_offset = offset as u64;
+            }
+            offset => {
+                let offset = offset as u64;
+                // assuming BigTIFF
+                len_count = offset;
+                len_offset = offset;
+            }
+        }
+
+        // Each entry is 12 bytes in classic TIFF, 20 bytes in BigTIFF.
+        let entry_bytes = 4 + 2 * len_offset;
+        len_count + entry_bytes * self.entries.len() as u64 + len_offset
+    }
 }
 
 impl fmt::Debug for Directory {
@@ -118,6 +140,14 @@ impl fmt::Debug for Directory {
     }
 }
 
+impl core::iter::FromIterator<(Tag, Entry)> for Directory {
+    fn from_iter<T: IntoIterator<Item = (Tag, Entry)>>(iter: T) -> Self {
+        let mut dir = Directory::empty();
+        dir.extend(iter);
+        dir
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::Directory;

src/encoder/compression/uncompressed.rs

@@ -14,7 +14,7 @@ impl Compression for Uncompressed {
 
 impl CompressionAlgorithm for Uncompressed {
     fn write_to<W: Write>(&mut self, writer: &mut W, bytes: &[u8]) -> Result<u64, io::Error> {
-        writer.write(bytes).map(|byte_count| byte_count as u64)
+        writer.write_all(bytes).map(|()| bytes.len() as u64)
     }
 }
 

src/encoder/mod.rs

@@ -11,7 +11,10 @@ use std::{
 use crate::{
     decoder::ifd::Entry,
     error::{TiffResult, UsageError},
-    tags::{CompressionMethod, IfdPointer, ResolutionUnit, SampleFormat, Tag, Type},
+    tags::{
+        CompressionMethod, ExtraSamples, IfdPointer, PhotometricInterpretation, ResolutionUnit,
+        SampleFormat, Tag, Type,
+    },
     Directory, TiffError, TiffFormatError,
 };
 
@@ -37,8 +40,9 @@ pub type Predictor = crate::tags::Predictor;
 #[cfg(feature = "deflate")]
 pub type DeflateLevel = compression::DeflateLevel;
 
-#[derive(Clone, Copy, PartialEq)]
+#[derive(Clone, Copy, PartialEq, Default)]
 pub enum Compression {
+    #[default]
     Uncompressed,
     #[cfg(feature = "lzw")]
     Lzw,
@@ -47,12 +51,6 @@ pub enum Compression {
     Packbits,
 }
 
-impl Default for Compression {
-    fn default() -> Self {
-        Self::Uncompressed
-    }
-}
-
 impl Compression {
     fn tag(&self) -> CompressionMethod {
         match self {
@@ -79,10 +77,10 @@ impl Compression {
 
 /// Encoder for Tiff and BigTiff files.
 ///
-/// With this type you can get a `DirectoryEncoder` or a `ImageEncoder`
+/// With this type you can get a [`DirectoryEncoder`] or a [`ImageEncoder`]
 /// to encode Tiff/BigTiff ifd directories with images.
 ///
-/// See `DirectoryEncoder` and `ImageEncoder`.
+/// See [`DirectoryEncoder`] and [`ImageEncoder`].
 ///
 /// # Examples
 /// ```
@@ -176,7 +174,7 @@ impl<W: Write + Seek, K: TiffKind> TiffEncoder<W, K> {
         Self::chain_directory(&mut self.writer, &mut self.last_ifd_chain)
     }
 
-    /// Create a [`DirectoryEncoder`] to encode an ifd directory.
+    /// Create a [`DirectoryEncoder`] to encode an ifd (directory).
     ///
     /// The caller is responsible for ensuring that the directory is a valid image in the main TIFF
     /// IFD sequence. To encode additional directories that are not linked into the sequence, use
@@ -185,7 +183,7 @@ impl<W: Write + Seek, K: TiffKind> TiffEncoder<W, K> {
         Self::chain_directory(&mut self.writer, &mut self.last_ifd_chain)
     }
 
-    /// Create a [`DirectoryEncoder`] to encode an ifd directory.
+    /// Create a [`DirectoryEncoder`] to encode a non-image directory.
     ///
     /// The directory is not linked into the sequence of directories. For instance, encode Exif
     /// directories or SubIfd directories with this method.
@@ -249,6 +247,12 @@ pub struct DirectoryEncoder<'a, W: 'a + Write + Seek, K: TiffKind> {
 }
 
 /// The offset of an encoded directory in the file.
+///
+/// Both the `offset` and `pointer` field are a complete description of the start offset of the
+/// dictionary which is used to point to it. The struct also describes the extent covered by the
+/// encoding of the directory. The constructors [`new`][DirectoryOffset::new] allow the checked
+/// conversion. Note that even though the offsets are public do not expect their information to
+/// propagate when modified.
 #[derive(Clone, Copy, Debug, PartialEq, Eq, Hash)]
 pub struct DirectoryOffset<K: TiffKind> {
     /// The start of the directory as a Tiff value.
@@ -260,7 +264,9 @@ pub struct DirectoryOffset<K: TiffKind> {
     pub offset: K::OffsetType,
     /// The start of the directory as a pure offset.
     pub pointer: IfdPointer,
-    /// The offset of its sequence link field, in our private representation.
+    /// The offset of its sequence link field, in our private representation. Before exposing this
+    /// make sure that we don't want any invariants (e.g. pointer being smaller than this). The
+    /// type should be fine.
     ifd_chain: NonZeroU64,
     /// The kind of Tiff file the offset is for.
     kind: PhantomData<K>,
@@ -318,6 +324,17 @@ impl<'a, W: 'a + Write + Seek, K: TiffKind> DirectoryEncoder<'a, W, K> {
         Ok(offset)
     }
 
+    /// Insert previously written key-value entries.
+    ///
+    /// It is the caller's responsibility to ensure that the data referred to by the entries is
+    /// actually (or will be) written to the file. Note that small values are necessarily inline in
+    /// the entry, the size limit depends on the Tiff kind. So do not confuse a directory from a
+    /// BigTiff in a standard tiff or the other way around.
+    pub fn extend_from(&mut self, dir: &Directory) {
+        let entries = dir.iter().map(|(tag, val)| (tag, val.clone()));
+        self.directory.extend(entries);
+    }
+
     /// Define the parent directory.
     ///
     /// Each directory has an offset based link to its successor, forming a linked list in the
@@ -334,6 +351,11 @@ impl<'a, W: 'a + Write + Seek, K: TiffKind> DirectoryEncoder<'a, W, K> {
         Ok(())
     }
 
+    /// Write the IFD to the file and return the offset it is written to.
+    ///
+    /// The offset can be used as the value, or as part of a list of values, in the entry of
+    /// another directory. If you're constructing the entry directly you'll want to use an
+    /// appropriate type variant for this such as [`Type::IFD`].
     pub fn finish_with_offsets(mut self) -> TiffResult<DirectoryOffset<K>> {
         self.finish_internal()
     }
@@ -487,6 +509,7 @@ pub struct ImageEncoder<'a, W: 'a + Write + Seek, C: ColorType, K: TiffKind> {
     row_samples: u64,
     width: u32,
     height: u32,
+    extra_samples: Vec<u16>,
     rows_per_strip: u64,
     strip_offsets: Vec<K::OffsetType>,
     strip_byte_count: Vec<K::OffsetType>,
@@ -543,11 +566,14 @@ impl<'a, W: 'a + Write + Seek, T: ColorType, K: TiffKind> ImageEncoder<'a, W, T,
         encoder.write_tag(Tag::Compression, compression.tag().to_u16())?;
         encoder.write_tag(Tag::Predictor, predictor.to_u16())?;
 
-        encoder.write_tag(Tag::BitsPerSample, <T>::BITS_PER_SAMPLE)?;
-        let sample_format: Vec<_> = <T>::SAMPLE_FORMAT.iter().map(|s| s.to_u16()).collect();
-        encoder.write_tag(Tag::SampleFormat, &sample_format[..])?;
         encoder.write_tag(Tag::PhotometricInterpretation, <T>::TIFF_VALUE.to_u16())?;
 
+        if matches!(<T>::TIFF_VALUE, PhotometricInterpretation::YCbCr) {
+            // The default for this tag is 2,2 for subsampling but we do not support such a
+            // transformation. Instead all samples must be provided.
+            encoder.write_tag(Tag::ChromaSubsampling, &[1u16, 1u16][..])?;
+        }
+
         encoder.write_tag(Tag::RowsPerStrip, u32::try_from(rows_per_strip)?)?;
 
         encoder.write_tag(
@@ -564,6 +590,7 @@ impl<'a, W: 'a + Write + Seek, T: ColorType, K: TiffKind> ImageEncoder<'a, W, T,
             strip_idx: 0,
             row_samples,
             rows_per_strip,
+            extra_samples: vec![],
             width,
             height,
             strip_offsets: Vec::new(),
@@ -575,6 +602,27 @@ impl<'a, W: 'a + Write + Seek, T: ColorType, K: TiffKind> ImageEncoder<'a, W, T,
         })
     }
 
+    pub fn extra_samples(&mut self, extra: &[ExtraSamples]) -> Result<(), TiffError> {
+        if self.strip_idx != 0 {
+            return Err(TiffError::UsageError(
+                UsageError::ReconfiguredAfterImageWrite,
+            ));
+        }
+
+        let samples = self.extra_samples.len() + extra.len() + <T>::BITS_PER_SAMPLE.len();
+        let row_samples = u64::from(self.width) * u64::try_from(samples)?;
+
+        self.extra_samples
+            .extend(extra.iter().map(ExtraSamples::to_u16));
+
+        self.encoder
+            .write_tag(Tag::ExtraSamples, &self.extra_samples[..])?;
+
+        self.row_samples = row_samples;
+
+        Ok(())
+    }
+
     /// Number of samples the next strip should have.
     pub fn next_strip_sample_count(&self) -> u64 {
         if self.strip_idx >= self.strip_count {
@@ -712,6 +760,39 @@ impl<'a, W: 'a + Write + Seek, T: ColorType, K: TiffKind> ImageEncoder<'a, W, T,
     }
 
     fn finish_internal(&mut self) -> TiffResult<DirectoryOffset<K>> {
+        if self.extra_samples.is_empty() {
+            self.encoder
+                .write_tag(Tag::BitsPerSample, <T>::BITS_PER_SAMPLE)?;
+        } else {
+            let mut sample_format: Vec<_> = <T>::BITS_PER_SAMPLE.to_vec();
+            let replicated =
+                core::iter::repeat_n(<T>::BITS_PER_SAMPLE[0], self.extra_samples.len());
+            sample_format.extend(replicated);
+
+            self.encoder
+                .write_tag(Tag::BitsPerSample, &sample_format[..])?;
+
+            self.encoder.write_tag(
+                Tag::SamplesPerPixel,
+                u16::try_from(<T>::BITS_PER_SAMPLE.len() + self.extra_samples.len())?,
+            )?;
+        }
+
+        let mut sample_format: Vec<_> = <T>::SAMPLE_FORMAT.iter().map(|s| s.to_u16()).collect();
+        let extra_format = sample_format
+            .first()
+            .copied()
+            // Frankly should not occur, we have no sample format without at least one entry. We
+            // would need an interface upgrade to handle this however. Either decide to support
+            // heterogeneous sample formats or a way to provide fallback that is used for purely
+            // extra samples and not provided via a slice used for samples themselves.
+            .unwrap_or(SampleFormat::Void.to_u16());
+
+        sample_format.extend(core::iter::repeat_n(extra_format, self.extra_samples.len()));
+
+        self.encoder
+            .write_tag(Tag::SampleFormat, &sample_format[..])?;
+
         self.encoder
             .write_tag(Tag::StripOffsets, K::convert_slice(&self.strip_offsets))?;
         self.encoder.write_tag(
@@ -791,6 +872,71 @@ pub trait TiffKind {
     fn convert_slice(slice: &[Self::OffsetType]) -> &Self::OffsetArrayType;
 }
 
+impl<K: TiffKind> DirectoryOffset<K> {
+    /// Construct the directory pointer information from its raw offset.
+    ///
+    /// Fails in these cases:
+    ///
+    /// - if start offset is too large to be represented with the chosen TIFF format, i.e. a value
+    ///   larger than [`u32::MAX`] with a standard tiff which is only valid in a BigTiff. This
+    ///   returns [`TiffError::IntSizeError`].
+    /// - the extent of the directory would overflow the file length. This returns a
+    ///   [`TiffError::UsageError`].
+    ///
+    /// The library does *not* validate the contents or offset in any way, it just performs the
+    /// necessary math assuming the data is an accurate representation of existing content.
+    ///
+    /// # Examples
+    ///
+    /// If you have any custom way of writing a directory to a file that can not go through the
+    /// usual [`TiffEncoder::extra_directory`] then you can reconstruct the offset information as
+    /// long as you provide all the necessary data to the library. You can then use it as a parent
+    /// directory, i.e. have the library overwrite its `next` field.
+    ///
+    /// ```
+    /// use tiff::{
+    ///     encoder::{TiffEncoder, DirectoryOffset},
+    ///     Directory,
+    ///     tags::IfdPointer,
+    /// };
+    ///
+    /// # let mut file = std::io::Cursor::new(Vec::new());
+    /// let mut tiff = TiffEncoder::new(&mut file)?;
+    ///
+    /// // … some custom data writes, assume we know where a directory was written
+    /// # fn reconstruction_of_your_directory() -> Directory { Directory::from_iter([]) }
+    /// let known_offset = IfdPointer(1024);
+    /// let known_contents: Directory = reconstruction_of_your_directory();
+    ///
+    /// let reconstructed = DirectoryOffset::new(known_offset, &known_contents)?;
+    ///
+    /// // Now we can use it as if the directory was written by the `TiffEncoder` itself.
+    /// let mut chain = tiff.extra_directory()?;
+    /// chain.set_parent(&reconstructed);
+    /// chain.finish_with_offsets()?;
+    ///
+    /// # Ok::<_, tiff::TiffError>(())
+    /// ```
+    pub fn new(pointer: IfdPointer, dir: &Directory) -> TiffResult<Self> {
+        let offset = K::convert_offset(pointer.0)?;
+        let encoded = dir.encoded_len::<K>();
+        let offset_field_offset = encoded - mem::size_of_val(&offset) as u64;
+
+        let ifd_chain = pointer
+            .0
+            .checked_add(offset_field_offset)
+            .and_then(NonZeroU64::new)
+            .ok_or(TiffError::UsageError(UsageError::ZeroIfdPointer))?;
+
+        Ok(DirectoryOffset {
+            pointer,
+            offset,
+            ifd_chain,
+            kind: PhantomData,
+        })
+    }
+}
+
 /// Create a standard Tiff file.
 pub struct TiffKindStandard;
 
@@ -859,3 +1005,33 @@ impl TiffKind for TiffKindBig {
         slice
     }
 }
+
+#[test]
+fn directory_offset_new_equivalent_to_writing() {
+    type K = TiffKindStandard;
+
+    let dir = Directory::from_iter(vec![
+        (
+            Tag::ImageWidth,
+            Entry::new(Type::LONG, 1, 100u32.to_ne_bytes()),
+        ),
+        (
+            Tag::ImageLength,
+            Entry::new(Type::LONG, 1, 200u32.to_ne_bytes()),
+        ),
+    ]);
+
+    let data = std::io::Cursor::new(vec![]);
+    let mut file = TiffEncoder::new(data).unwrap();
+
+    let mut as_dir_encoder = file.extra_directory().unwrap();
+    as_dir_encoder.extend_from(&dir);
+    let dir_extent = as_dir_encoder.finish_with_offsets().unwrap();
+
+    // Check we can recreate the extent had we written ourselves.
+    let synth = DirectoryOffset::<K>::new(dir_extent.pointer, &dir).unwrap();
+
+    assert_eq!(synth.pointer, dir_extent.pointer);
+    assert_eq!(synth.offset, dir_extent.offset);
+    assert_eq!(synth.ifd_chain, dir_extent.ifd_chain);
+}

src/encoder/tiff_value.rs

@@ -5,6 +5,14 @@ use crate::{bytecast, tags::Type, TiffError, TiffFormatError, TiffResult};
 use super::writer::TiffWriter;
 
 /// Trait for types that can be encoded in a tiff file
+#[diagnostic::on_unimplemented(
+    message = "the type `{Self}` does not implement `TiffValue`",
+    note = "the trait is implemented for primitive types (`u8`, `i16`, `f32`, etc.)",
+    note = "the trait is implemented for shared references to values",
+    note = "the trait is implemented for slices, pass them by reference (e.g. `&[u8]`)",
+    note = "the trait is implemented for arrays if it is implemented for a slice",
+    note = "values in a `Vec` or `Box` should be dereferenced, e.g. `&vec[..]`"
+)]
 pub trait TiffValue {
     const BYTE_LEN: u8;
     const FIELD_TYPE: Type;
@@ -450,6 +458,14 @@ impl TiffValue for str {
     }
 }
 
+// If you pass `&Vec<_>` then you'd get at first sight the  complaint:
+//
+//  `Vec<T>` does not implement `TiffValue`
+//
+// and a list of implementations of `TiffValue` that are quite unrelated. That is not very helpful.
+// We do not *want* `Vec` to implement the trait as an owning type, instead you should pass a
+// reference to a slice. The error message is further customized in the diagnostics of the trait.
+#[diagnostic::do_not_recommend]
 impl<T: TiffValue + ?Sized> TiffValue for &'_ T {
     const BYTE_LEN: u8 = T::BYTE_LEN;
     const FIELD_TYPE: Type = T::FIELD_TYPE;
@@ -467,6 +483,27 @@ impl<T: TiffValue + ?Sized> TiffValue for &'_ T {
     }
 }
 
+/// An array is treated like a slice of the same length.
+impl<T, const N: usize> TiffValue for [T; N]
+where
+    [T]: TiffValue,
+{
+    const BYTE_LEN: u8 = <[T]>::BYTE_LEN;
+    const FIELD_TYPE: Type = <[T]>::FIELD_TYPE;
+
+    fn count(&self) -> usize {
+        self.as_slice().count()
+    }
+
+    fn write<W: Write>(&self, writer: &mut TiffWriter<W>) -> TiffResult<()> {
+        self.as_slice().write(writer)
+    }
+
+    fn data(&self) -> Cow<'_, [u8]> {
+        self.as_slice().data()
+    }
+}
+
 macro_rules! impl_tiff_value_for_contiguous_sequence {
     ($inner_type:ty; $bytes:expr; $field_type:expr) => {
         impl $crate::encoder::TiffValue for [$inner_type] {

src/encoder/writer.rs

@@ -190,3 +190,64 @@ impl<W: Seek> TiffWriter<W> {
         Ok(())
     }
 }
+
+#[test]
+fn encoder_on_short_writes() {
+    struct ShortWriter<T> {
+        inner: T,
+    }
+
+    impl<T: std::io::Write> std::io::Write for ShortWriter<T> {
+        fn write(&mut self, buf: &[u8]) -> std::io::Result<usize> {
+            let lower_bound = buf.len().min(1);
+            let lower = buf.len().saturating_sub(1).max(lower_bound);
+
+            self.inner.write(&buf[..lower])
+        }
+
+        fn flush(&mut self) -> std::io::Result<()> {
+            self.inner.flush()
+        }
+    }
+
+    impl<T: std::io::Seek> std::io::Seek for ShortWriter<T> {
+        fn seek(&mut self, pos: std::io::SeekFrom) -> std::io::Result<u64> {
+            self.inner.seek(pos)
+        }
+    }
+
+    let mut write = ShortWriter {
+        inner: std::io::Cursor::new(vec![0u8; 0]),
+    };
+
+    let imgdata = vec![42u8; 100 * 100];
+    let mut data = crate::decoder::DecodingResult::U8(vec![]);
+
+    for comp in [
+        super::Compression::Uncompressed,
+        super::Compression::Packbits,
+    ] {
+        write.inner.set_position(0);
+        write.inner.get_mut().clear();
+
+        {
+            let mut tiff_writer = super::TiffEncoder::new(&mut write)
+                .unwrap()
+                .with_compression(comp);
+
+            tiff_writer
+                .write_image::<super::Gray8>(100, 100, &imgdata)
+                .unwrap();
+        }
+
+        write.inner.set_position(0);
+        let mut tiff_reader = crate::decoder::Decoder::new(&mut write.inner).unwrap();
+        let _layout = tiff_reader.read_image_to_buffer(&mut data).unwrap();
+
+        assert!(
+            matches!(&data, crate::decoder::DecodingResult::U8(v) if *v == imgdata),
+            "{data:?} @ {}",
+            data.as_buffer(0).byte_len()
+        );
+    }
+}

src/error.rs

@@ -90,6 +90,9 @@ quick_error! {
         InvalidTypeForTag {
             display("tag has invalid type")
         }
+        InvalidCountForTag(tag: Tag, len: usize) {
+            display("tag `{tag:?}` with incorrect number of elements ({len}) encountered")
+        }
         StripTileTagConflict {
             display("file should contain either (StripByteCounts and StripOffsets) or (TileByteCounts and TileOffsets), other combination was found")
         }
@@ -156,6 +159,9 @@ quick_error! {
         UnsupportedInterpretation(interpretation: PhotometricInterpretation) {
             display("unsupported photometric interpretation \"{interpretation:?}\"")
         }
+        ChromaSubsampling {
+            display("chroma subsampling of YCbCr color is unsupported")
+        }
         MisalignedTileBoundaries {
             display("tile rows are not aligned to byte boundaries")
         }
@@ -175,6 +181,12 @@ quick_error! {
         InvalidChunkIndex(index: u32) {
             display("invalid chunk index ({index}) requested")
         }
+        InvalidPlaneIndex(index: u16) {
+            display("invalid plane index ({index}) requested")
+        }
+        InvalidCodingUnit(index: u32, have: u32) {
+            display("out of bounds coding unit ({index}) requested, only {have} available")
+        }
         PredictorCompressionMismatch {
             display("requested predictor is not compatible with the requested compression")
         }
@@ -187,6 +199,15 @@ quick_error! {
         InsufficientOutputBufferSize { needed: usize, provided: usize } {
             display("the borrowed output buffer is not large enough for the decoded data, needed {needed} but have {provided}")
         }
+        InsufficientOutputRowStride { needed: usize, requested: usize } {
+            display("the provided output row stride would alias rows of decoded data, needed {needed} but have {requested}")
+        }
+        ZeroIfdPointer {
+            display("the offset 0 can not point to a valid IFD")
+        }
+        ReconfiguredAfterImageWrite {
+            display("attempted to reconfigure the encoder after image writing has started")
+        }
     }
 }
 

src/lib.rs

@@ -44,6 +44,9 @@ pub enum ColorType {
     /// Pixel is YCbCr
     YCbCr(u8),
 
+    /// Pixel is CIE L*a*b* (ICC LAb)
+    Lab(u8),
+
     /// Pixel has multiple bands/channels
     Multiband { bit_depth: u8, num_samples: u16 },
 }
@@ -58,7 +61,23 @@ impl ColorType {
             | ColorType::CMYK(b)
             | ColorType::CMYKA(b)
             | ColorType::YCbCr(b)
+            | ColorType::Lab(b)
             | ColorType::Multiband { bit_depth: b, .. } => b,
         }
     }
+
+    fn num_samples(&self) -> u16 {
+        match *self {
+            ColorType::Gray(_) => 1,
+            ColorType::RGB(_) => 3,
+            ColorType::Palette(_) => 1,
+            ColorType::GrayA(_) => 2,
+            ColorType::RGBA(_) => 4,
+            ColorType::CMYK(_) => 4,
+            ColorType::CMYKA(_) => 5,
+            ColorType::YCbCr(_) => 3,
+            ColorType::Lab(_) => 3,
+            ColorType::Multiband { num_samples, .. } => num_samples,
+        }
+    }
 }

src/tags.rs

@@ -20,7 +20,7 @@ macro_rules! tags {
 
         impl $name {
             #[inline(always)]
-            fn __from_inner_type(n: $ty) -> Result<Self, $ty> {
+            const fn __from_inner_type(n: $ty) -> Result<Self, $ty> {
                 match n {
                     $( $val => Ok($name::$tag), )*
                     n => Err(n),
@@ -28,7 +28,7 @@ macro_rules! tags {
             }
 
             #[inline(always)]
-            fn __to_inner_type(&self) -> $ty {
+            const fn __to_inner_type(&self) -> $ty {
                 match *self {
                     $( $name::$tag => $val, )*
                     $( $name::Unknown($unknown_doc) => { $unknown_doc }, )*
@@ -42,19 +42,25 @@ macro_rules! tags {
     ($name:tt, u16, $($unknown_doc:ident)*) => {
         impl $name {
             #[inline(always)]
-            pub fn from_u16(val: u16) -> Option<Self> {
-                Self::__from_inner_type(val).ok()
+            pub const fn from_u16(val: u16) -> Option<Self> {
+                match Self::__from_inner_type(val) {
+                    Ok(v) => Some(v),
+                    Err(_) => None,
+                }
             }
 
             $(
             #[inline(always)]
-            pub fn from_u16_exhaustive($unknown_doc: u16) -> Self {
-                Self::__from_inner_type($unknown_doc).unwrap_or_else(|_| $name::Unknown($unknown_doc))
+            pub const fn from_u16_exhaustive($unknown_doc: u16) -> Self {
+                match Self::__from_inner_type($unknown_doc) {
+                    Ok(v) => v,
+                    Err(_) => $name::Unknown($unknown_doc),
+                }
             }
             )*
 
             #[inline(always)]
-            pub fn to_u16(&self) -> u16 {
+            pub const fn to_u16(&self) -> u16 {
                 Self::__to_inner_type(self)
             }
         }
@@ -122,6 +128,11 @@ pub enum Tag(u16) unknown(
     SMaxSampleValue = 341, // TODO add support
     // JPEG
     JPEGTables = 347,
+    // Subsampling
+    #[doc(alias = "YCbCrSubsampling")]
+    ChromaSubsampling = 530, // TODO add support
+    #[doc(alias = "YCbCrPositioning")]
+    ChromaPositioning = 531, // TODO add support
     // GeoTIFF
     ModelPixelScaleTag = 33550, // (SoftDesk)
     ModelTransformationTag = 34264, // (JPL Carto Group)
@@ -193,6 +204,45 @@ pub enum Type(u16) {
 }
 }
 
+impl Type {
+    pub(crate) fn byte_len(&self) -> u8 {
+        match *self {
+            Type::BYTE | Type::SBYTE | Type::ASCII | Type::UNDEFINED => 1,
+            Type::SHORT | Type::SSHORT => 2,
+            Type::LONG | Type::SLONG | Type::FLOAT | Type::IFD => 4,
+            Type::LONG8
+            | Type::SLONG8
+            | Type::DOUBLE
+            | Type::RATIONAL
+            | Type::SRATIONAL
+            | Type::IFD8 => 8,
+        }
+    }
+
+    pub(crate) fn value_bytes(&self, count: u64) -> Result<u64, crate::error::TiffError> {
+        let tag_size = u64::from(self.byte_len());
+
+        match count.checked_mul(tag_size) {
+            Some(n) => Ok(n),
+            None => Err(crate::error::TiffError::LimitsExceeded),
+        }
+    }
+
+    pub(crate) fn endian_bytes(self) -> EndianBytes {
+        match self {
+            Type::BYTE | Type::SBYTE | Type::ASCII | Type::UNDEFINED => EndianBytes::One,
+            Type::SHORT | Type::SSHORT => EndianBytes::Two,
+            Type::LONG
+            | Type::SLONG
+            | Type::FLOAT
+            | Type::IFD
+            | Type::RATIONAL
+            | Type::SRATIONAL => EndianBytes::Four,
+            Type::LONG8 | Type::SLONG8 | Type::DOUBLE | Type::IFD8 => EndianBytes::Eight,
+        }
+    }
+}
+
 tags! {
 /// See [TIFF compression tags](https://www.awaresystems.be/imaging/tiff/tifftags/compression.html)
 /// for reference.
@@ -227,6 +277,8 @@ pub enum PhotometricInterpretation(u16) {
     CMYK = 5,
     YCbCr = 6,
     CIELab = 8,
+    IccLab = 9,
+    ItuLab = 10,
 }
 }
 
@@ -271,3 +323,90 @@ pub enum SampleFormat(u16) unknown(
     Void = 4,
 }
 }
+
+tags! {
+pub enum ExtraSamples(u16) {
+    /// There is no specified association between the sample and the image.
+    Unspecified = 0,
+    /// The sample is associated alpha, i.e. pre-multiplied color.
+    AssociatedAlpha = 1,
+    /// The sample is unassociated alpha such as a mask. There might be more than one such sample.
+    UnassociatedAlpha = 2,
+}
+}
+
+/// Byte order of the TIFF file.
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum ByteOrder {
+    /// little endian byte order
+    LittleEndian,
+    /// big endian byte order
+    BigEndian,
+}
+
+impl ByteOrder {
+    /// Get the byte order representing the running target.
+    ///
+    /// The infallibility of this method represents the fact that only little and big endian
+    /// systems are supported by the library. No mixed endian and no other weird stuff. (Note: as
+    /// of Rust 1.90 this is a tautology as Rust itself only has those two kinds).
+    pub const fn native() -> Self {
+        match () {
+            #[cfg(target_endian = "little")]
+            () => ByteOrder::LittleEndian,
+            #[cfg(target_endian = "big")]
+            () => ByteOrder::BigEndian,
+            #[cfg(not(any(target_endian = "big", target_endian = "little")))]
+            () => compile_error!("Unsupported target"),
+        }
+    }
+
+    /// Given a typed buffer, convert its contents to the specified byte order in-place.
+    ///
+    /// The buffer is assumed to represent an array of the given type. If the length of the buffer
+    /// is not divisible into an integer number of values, the behavior for the remaining bytes it
+    /// not specified.
+    pub fn convert(self, ty: Type, buffer: &mut [u8], to: ByteOrder) {
+        self.convert_endian_bytes(ty.endian_bytes(), buffer, to)
+    }
+
+    pub(crate) fn convert_endian_bytes(self, cls: EndianBytes, buffer: &mut [u8], to: ByteOrder) {
+        if self == to {
+            return;
+        }
+
+        // FIXME: at MSRV 1.89 or higher use `slice::as_chunks_mut`.
+        match cls {
+            EndianBytes::One => {
+                // No change needed
+            }
+            EndianBytes::Two => {
+                for chunk in buffer.chunks_exact_mut(2) {
+                    let chunk: &mut [u8; 2] = chunk.try_into().unwrap();
+                    *chunk = u16::from_be_bytes(*chunk).to_le_bytes();
+                }
+            }
+            EndianBytes::Four => {
+                for chunk in buffer.chunks_exact_mut(4) {
+                    let chunk: &mut [u8; 4] = chunk.try_into().unwrap();
+                    *chunk = u32::from_be_bytes(*chunk).to_le_bytes();
+                }
+            }
+            EndianBytes::Eight => {
+                for chunk in buffer.chunks_exact_mut(8) {
+                    let chunk: &mut [u8; 8] = chunk.try_into().unwrap();
+                    *chunk = u64::from_be_bytes(*chunk).to_le_bytes();
+                }
+            }
+        }
+    }
+}
+
+/// The size of individual byte-order corrected elements.
+#[derive(Clone, Copy)]
+pub(crate) enum EndianBytes {
+    One,
+    Two,
+    Four,
+    Eight,
+}

tests/decode_images.rs

@@ -672,3 +672,51 @@ fn bytes_gray_f32() {
         byte_order_u32,
     );
 }
+
+#[test]
+#[cfg(feature = "fax")]
+fn test_fax4() {
+    test_image_sum_u8("fax4.tiff", ColorType::Gray(1), 7802706);
+}
+
+#[test]
+#[cfg(feature = "fax")]
+fn test_fax4_white_is_min() {
+    test_image_sum_u8("imagemagick_group4.tiff", ColorType::Gray(1), 3742820);
+}
+
+#[test]
+fn write_extra_bits_image() {
+    use tiff::{encoder, tags::ExtraSamples};
+
+    let path = PathBuf::from(TEST_IMAGE_DIR).join("extra_bits_rgb_8b.tiff");
+    let img_file = File::create(path).expect("Cannot find test image!");
+
+    let mut encoder = encoder::TiffEncoder::new(img_file).expect("Cannot create encoder");
+    let mut img = encoder.new_image::<encoder::colortype::RGB8>(8, 8).unwrap();
+
+    img.extra_samples(&[ExtraSamples::Unspecified]).unwrap();
+
+    // all pixels are supposed to be 0, the extra is 1
+    let data: [u8; 256] = core::array::from_fn(|i| (i as u8 % 4).saturating_sub(2));
+
+    img.write_data(&data)
+        .expect("correct amount of data to write");
+}
+
+#[test]
+fn extra_bits_gray() {
+    test_image_sum_u8(
+        "extra_bits_gray_8b.tiff",
+        ColorType::Multiband {
+            bit_depth: 8,
+            num_samples: 2,
+        },
+        64,
+    );
+}
+
+#[test]
+fn extra_bits_rgb() {
+    test_image_sum_u8("extra_bits_rgb_8b.tiff", ColorType::RGB(8), 0);
+}

tests/decode_planes.rs

@@ -0,0 +1,76 @@
+use tiff::decoder::{Decoder, TiffCodingUnit};
+
+use std::fs::File;
+use std::path::PathBuf;
+
+const TEST_IMAGE_DIR: &str = "./tests/images/";
+
+#[test]
+fn read_all_planes() {
+    let path = PathBuf::from(TEST_IMAGE_DIR).join("planar-rgb-u8.tif");
+    let file = File::open(path).unwrap();
+    let io = std::io::BufReader::new(file);
+
+    let mut tif = Decoder::new(io).unwrap();
+    let layout = tif.image_buffer_layout().unwrap();
+    assert_eq!(layout.planes, 3);
+    let plane_stride = layout.plane_stride.map_or(0, |x| x.get());
+
+    eprintln!("{:?}", layout);
+    let mut buffer = vec![0u8; layout.complete_len];
+    tif.read_image_bytes(&mut buffer).unwrap();
+
+    // Mainly you can see: these are different and non-zero. Otherwise these magic constants just
+    // depend on the file itself that is being used.
+    const PLANE_EXCPECTED_SUMS: [u32; 3] = [15417630, 13007788, 11103530];
+
+    for (plane, expected) in (0..layout.planes).zip(PLANE_EXCPECTED_SUMS) {
+        let plane_data = &buffer[plane_stride * plane..][..layout.len];
+        let sum: u32 = plane_data.iter().copied().map(u32::from).sum();
+        assert_eq!(sum, expected);
+    }
+}
+
+#[test]
+fn read_first_coding_unit() {
+    let path = PathBuf::from(TEST_IMAGE_DIR).join("planar-rgb-u8.tif");
+    let file = File::open(path).unwrap();
+    let io = std::io::BufReader::new(file);
+
+    let mut tif = Decoder::new(io).unwrap();
+    let layout = tif.image_coding_unit_layout(TiffCodingUnit(0)).unwrap();
+
+    assert_eq!(layout.planes, 3);
+    let plane_stride = layout.plane_stride.map_or(0, |x| x.get());
+    eprintln!("{:?}", layout);
+    let mut buffer = vec![0u8; layout.complete_len];
+
+    struct Expected {
+        plane_sums: [u32; 3],
+        unit: TiffCodingUnit,
+    }
+
+    // Mainly you can see: these are different and non-zero. Otherwise these magic constants just
+    // depend on the file itself that is being used. Also this varies by what unit we are reading.
+    const PLANE_EXCPECTED_SUMS: [Expected; 2] = [
+        Expected {
+            plane_sums: [856853, 767686, 688532],
+            unit: TiffCodingUnit(0),
+        },
+        Expected {
+            plane_sums: [883679, 797329, 711086],
+            unit: TiffCodingUnit(1),
+        },
+    ];
+
+    for expected in PLANE_EXCPECTED_SUMS {
+        tif.read_coding_unit_bytes(expected.unit, &mut buffer)
+            .unwrap();
+
+        for (plane, expected) in (0..layout.planes).zip(expected.plane_sums) {
+            let plane_data = &buffer[plane_stride * plane..][..layout.len];
+            let sum: u32 = plane_data.iter().copied().map(u32::from).sum();
+            assert_eq!(sum, expected);
+        }
+    }
+}

tests/encode_images.rs

@@ -57,7 +57,7 @@ fn encode_decode() {
                 ),
                 (Tag::Compression, ifd::Value::Short(1)),
                 (Tag::PhotometricInterpretation, ifd::Value::Short(2)),
-                (Tag::StripOffsets, ifd::Value::Unsigned(47)),
+                (Tag::StripOffsets, ifd::Value::Unsigned(35)),
                 (Tag::SamplesPerPixel, ifd::Value::Short(3)),
                 (Tag::RowsPerStrip, ifd::Value::Unsigned(3334)),
                 (Tag::StripByteCounts, ifd::Value::Unsigned(30000)),
@@ -81,7 +81,10 @@ fn encode_decode() {
             decoder.get_tag(Tag::Artist).unwrap(),
             ifd::Value::Ascii("Image-tiff".into())
         );
-        if let DecodingResult::U8(img_res) = decoder.read_image().unwrap() {
+
+        let mut buffer = tiff::decoder::DecodingResult::U8(vec![]);
+        let _layout = decoder.read_image_to_buffer(&mut buffer).unwrap();
+        if let tiff::decoder::DecodingResult::U8(img_res) = buffer {
             assert_eq!(image_data, img_res);
         } else {
             panic!("Wrong data type");
@@ -161,7 +164,9 @@ fn encode_decode_big() {
             decoder.get_tag(Tag::Artist).unwrap(),
             ifd::Value::Ascii("Image-tiff".into())
         );
-        if let DecodingResult::U8(img_res) = decoder.read_image().unwrap() {
+        let mut buffer = tiff::decoder::DecodingResult::U8(vec![]);
+        let _layout = decoder.read_image_to_buffer(&mut buffer).unwrap();
+        if let DecodingResult::U8(img_res) = buffer {
             assert_eq!(image_data, img_res);
         } else {
             panic!("Wrong data type");
@@ -235,6 +240,7 @@ const TEST_IMAGE_DIR: &str = "./tests/images/";
 
 macro_rules! test_roundtrip {
     ($name:ident, $buffer:ident, $buffer_ty:ty) => {
+        #[track_caller]
         fn $name<C: colortype::ColorType<Inner = $buffer_ty>>(
             file: &str,
             expected_type: ColorType,
@@ -244,7 +250,10 @@ macro_rules! test_roundtrip {
             let mut decoder = Decoder::new(img_file).expect("Cannot create decoder");
             assert_eq!(decoder.colortype().unwrap(), expected_type);
 
-            let image_data = match decoder.read_image().unwrap() {
+            let mut buffer = tiff::decoder::DecodingResult::U8(vec![]);
+            decoder.read_image_to_buffer(&mut buffer).unwrap();
+
+            let image_data = match buffer {
                 DecodingResult::$buffer(res) => res,
                 _ => panic!("Wrong data type"),
             };
@@ -258,9 +267,11 @@ macro_rules! test_roundtrip {
             }
             file.seek(SeekFrom::Start(0)).unwrap();
             {
+                let mut buffer = tiff::decoder::DecodingResult::U8(vec![]);
                 let mut decoder = Decoder::new(&mut file).unwrap();
-                if let DecodingResult::$buffer(img_res) = decoder.read_image().unwrap() {
-                    assert_eq!(image_data, img_res);
+                decoder.read_image_to_buffer(&mut buffer).unwrap();
+                if let DecodingResult::$buffer(img_res) = buffer {
+                    assert_eq!(*image_data, img_res);
                 } else {
                     panic!("Wrong data type");
                 }