Build Directory FromIterator

This enables a test for the encoder's DirectoryOffset but it seems to
fit nicely with the current design, too.

CHANGES.md

@@ -1,3 +1,7 @@
+# Version 0.10.4 (unreleased)
+
+- `Directory` now implements `FromIterator<(Tag, Value)>`.
+
 # Version 0.10.3
 
 New features:

Cargo.toml

@@ -25,7 +25,7 @@ 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"

src/decoder/ifd.rs

@@ -332,6 +332,12 @@ 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 +355,14 @@ 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 +384,10 @@ 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 +403,25 @@ 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 +440,11 @@ 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 +453,28 @@ 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 +505,7 @@ 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 +513,7 @@ 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 +521,7 @@ 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 +529,7 @@ 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 +537,7 @@ 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 +545,7 @@ 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 +564,149 @@ 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(Byte(buf[0]))
-            }),
-            Type::SBYTE => self.decode_offset(self.count, bo, bigtiff, limits, reader, |reader| {
-                Ok(SignedByte(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 +715,81 @@ 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(())
     }
-        Ok(List(v))
+
+    #[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(())
     }
 }
 

src/decoder/image.rs

@@ -145,12 +145,15 @@ 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,
         };
@@ -442,13 +445,14 @@ 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);
                 }
 

src/decoder/mod.rs

@@ -368,27 +368,82 @@ pub struct IfdDecoder<'lt> {
 }
 
 fn rev_hpredict_nsamp(buf: &mut [u8], bit_depth: u8, samples: usize) {
-    match bit_depth {
-        0..=8 => {
+    fn one_byte_predict<const N: usize>(buf: &mut [u8]) {
+        for i in N..buf.len() {
+            buf[i] = buf[i].wrapping_add(buf[i - N]);
+        }
+    }
+
+    fn two_bytes_predict<const N: usize>(buf: &mut [u8]) {
+        for i in (2 * N..buf.len()).step_by(2) {
+            let v = u16::from_ne_bytes(buf[i..][..2].try_into().unwrap());
+            let p = u16::from_ne_bytes(buf[i - 2 * N..][..2].try_into().unwrap());
+            buf[i..][..2].copy_from_slice(&(v.wrapping_add(p)).to_ne_bytes());
+        }
+    }
+
+    fn four_bytes_predict<const N: usize>(buf: &mut [u8]) {
+        for i in (N * 4..buf.len()).step_by(4) {
+            let v = u32::from_ne_bytes(buf[i..][..4].try_into().unwrap());
+            let p = u32::from_ne_bytes(buf[i - 4 * N..][..4].try_into().unwrap());
+            buf[i..][..4].copy_from_slice(&(v.wrapping_add(p)).to_ne_bytes());
+        }
+    }
+
+    match (bit_depth, samples) {
+        // Note we can't use `windows` or so due to the overlap between each iteration. We split
+        // the cases by the samples / lookback constant so that each is optimized individually.
+        // This is more code generated but each loop can then have a different vectorization
+        // strategy.
+        (0..=8, 1) => one_byte_predict::<1>(buf),
+        (0..=8, 2) => one_byte_predict::<2>(buf),
+        (0..=8, 3) => one_byte_predict::<3>(buf),
+        (0..=8, 4) => one_byte_predict::<4>(buf),
+        // The generic, sub-optimal case for the above.
+        (0..=8, _) => {
             for i in samples..buf.len() {
                 buf[i] = buf[i].wrapping_add(buf[i - samples]);
             }
         }
-        9..=16 => {
+        (9..=16, 1) => {
+            two_bytes_predict::<1>(buf);
+        }
+        (9..=16, 2) => {
+            two_bytes_predict::<2>(buf);
+        }
+        (9..=16, 3) => {
+            two_bytes_predict::<3>(buf);
+        }
+        (9..=16, 4) => {
+            two_bytes_predict::<4>(buf);
+        }
+        (9..=16, _) => {
             for i in (samples * 2..buf.len()).step_by(2) {
                 let v = u16::from_ne_bytes(buf[i..][..2].try_into().unwrap());
                 let p = u16::from_ne_bytes(buf[i - 2 * samples..][..2].try_into().unwrap());
                 buf[i..][..2].copy_from_slice(&(v.wrapping_add(p)).to_ne_bytes());
             }
         }
-        17..=32 => {
+        (17..=32, 1) => {
+            four_bytes_predict::<1>(buf);
+        }
+        (17..=32, 2) => {
+            four_bytes_predict::<2>(buf);
+        }
+        (17..=32, 3) => {
+            four_bytes_predict::<3>(buf);
+        }
+        (17..=32, 4) => {
+            four_bytes_predict::<4>(buf);
+        }
+        (17..=32, _) => {
             for i in (samples * 4..buf.len()).step_by(4) {
                 let v = u32::from_ne_bytes(buf[i..][..4].try_into().unwrap());
                 let p = u32::from_ne_bytes(buf[i - 4 * samples..][..4].try_into().unwrap());
                 buf[i..][..4].copy_from_slice(&(v.wrapping_add(p)).to_ne_bytes());
             }
         }
-        33..=64 => {
+        (33..=64, _) => {
             for i in (samples * 8..buf.len()).step_by(8) {
                 let v = u64::from_ne_bytes(buf[i..][..8].try_into().unwrap());
                 let p = u64::from_ne_bytes(buf[i - 8 * samples..][..8].try_into().unwrap());
@@ -535,32 +590,16 @@ fn invert_colors(
 
 /// Fix endianness. If `byte_order` matches the host, then conversion is a no-op.
 fn fix_endianness(buf: &mut [u8], byte_order: ByteOrder, bit_depth: u8) {
-    match byte_order {
-        ByteOrder::LittleEndian => match bit_depth {
-            0..=8 => {}
-            9..=16 => buf.chunks_exact_mut(2).for_each(|v| {
-                v.copy_from_slice(&u16::from_le_bytes((*v).try_into().unwrap()).to_ne_bytes())
-            }),
-            17..=32 => buf.chunks_exact_mut(4).for_each(|v| {
-                v.copy_from_slice(&u32::from_le_bytes((*v).try_into().unwrap()).to_ne_bytes())
-            }),
-            _ => buf.chunks_exact_mut(8).for_each(|v| {
-                v.copy_from_slice(&u64::from_le_bytes((*v).try_into().unwrap()).to_ne_bytes())
-            }),
-        },
-        ByteOrder::BigEndian => match bit_depth {
-            0..=8 => {}
-            9..=16 => buf.chunks_exact_mut(2).for_each(|v| {
-                v.copy_from_slice(&u16::from_be_bytes((*v).try_into().unwrap()).to_ne_bytes())
-            }),
-            17..=32 => buf.chunks_exact_mut(4).for_each(|v| {
-                v.copy_from_slice(&u32::from_be_bytes((*v).try_into().unwrap()).to_ne_bytes())
-            }),
-            _ => buf.chunks_exact_mut(8).for_each(|v| {
-                v.copy_from_slice(&u64::from_be_bytes((*v).try_into().unwrap()).to_ne_bytes())
-            }),
-        },
+    let host = ByteOrder::native();
+
+    let class = match bit_depth {
+        0..=8 => crate::tags::EndianBytes::One,
+        9..=16 => crate::tags::EndianBytes::Two,
+        17..=32 => crate::tags::EndianBytes::Four,
+        _ => crate::tags::EndianBytes::Eight,
     };
+
+    host.convert_endian_bytes(class, buf, byte_order);
 }
 
 impl<R: Read + Seek> Decoder<R> {
@@ -747,6 +786,11 @@ impl<R: Read + Seek> Decoder<R> {
     }
 
     /// Returns the byte_order of the file.
+    ///
+    /// # Usage
+    ///
+    /// This is only relevant to interpreting raw bytes read from tags. The image decoding methods
+    /// will correct to the host byte order automatically.
     pub fn byte_order(&self) -> ByteOrder {
         self.value_reader.reader.byte_order
     }

src/decoder/stream.rs

@@ -1,14 +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)]
@@ -45,17 +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> {
@@ -186,9 +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",

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

@@ -37,8 +37,9 @@ 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 +48,6 @@ pub enum Compression {
     Packbits,
 }
 
-impl Default for Compression {
-    fn default() -> Self {
-        Self::Uncompressed
-    }
-}
-
 impl Compression {
     fn tag(&self) -> CompressionMethod {
         match self {
@@ -79,10 +74,10 @@ 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 +171,7 @@ 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 +180,7 @@ 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 +244,12 @@ 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 +261,9 @@ 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 +321,17 @@ 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 +348,11 @@ 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()
     }
@@ -791,6 +810,71 @@ 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 +943,33 @@ 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/writer.rs

@@ -190,3 +190,58 @@ 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];
+    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 data = tiff_reader.read_image().unwrap();
+
+        assert!(matches!(data, crate::decoder::DecodingResult::U8(v) if v == imgdata));
+    }
+}

src/error.rs

@@ -187,6 +187,9 @@ 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}")
         }
+        ZeroIfdPointer {
+            display("the offset 0 can not point to a valid IFD")
+        }
     }
 }
 

src/tags.rs

@@ -193,6 +193,45 @@ 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.
@@ -271,3 +310,79 @@ pub enum SampleFormat(u16) unknown(
     Void = 4,
 }
 }
+
+/// 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,
+}