Release notes for 0.11.2

Make `read_image_to_buffer` read out all planes

CHANGES.md

@@ -1,3 +1,20 @@
+# Version 0.11.2
+
+Changes:
+- Planar files can now be read with `Decoder::read_image_to_buffer` if the
+  limits allow for such a large buffer size. Previously only the first plane
+  was read and the decoder will attempt a fallback to this behavior if the
+  limits do not allow all planes to be allocated.
+
+Fixes:
+- An off-by-one error in a `debug_assert` of `ValueBuffer` caused its use in
+  `IfdDecoder::find_tag_buf` to panic outside release mode when the buffer
+  exactly matched the required size.
+
+Additions:
+- The methods `ColorType::{num_samples, bit_depth}` are now public. This
+  promises that we only have homogeneous color depths in this major version.
+
 # Version 0.11.1
 
 Fixes:

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tiff"
-version = "0.11.1"
+version = "0.11.2"
 edition = "2021"
 resolver = "2"
 

examples/decode.rs

@@ -37,6 +37,7 @@ fn debug_planes(
     (width, height): (u32, u32),
 ) {
     let (depth, mut tupltype) = match colortype {
+        // Note: we will expand, so this is in fact not BLACKANDWHITE
         tiff::ColorType::Gray(_) => (1, "GRAYSCALE"),
         tiff::ColorType::RGB(_) => (3, "RGB"),
         tiff::ColorType::RGBA(_) => (4, "RGB_ALPHA"),
@@ -49,8 +50,57 @@ fn debug_planes(
         }
     };
 
+    // Number of samples in a line and number of sample lines in the image, depending on whether
+    // they are planar or not. This determines the layout of the image buffer when expanding bit
+    // packed samples to a full byte (we support power-of-two sample sizes, positive and negative,
+    // but only those).
+    let (swidth, sheight) = if layout.planes > 1 {
+        (
+            u64::from(width) * u64::from(colortype.num_samples()),
+            u64::from(height),
+        )
+    } else {
+        (
+            u64::from(width),
+            u64::from(height) * u64::from(colortype.num_samples()),
+        )
+    };
+
+    let mut fallback_buffer;
     let maxval = match data.as_buffer(0) {
-        DecodingBuffer::U8(_) => u64::from(u8::MAX),
+        // `U8` is also our representation of bit-packed color. PAM uses the smallest number of
+        // *bytes* needed to represent a sample but we must also adhere to maxval. We could explode
+        // them here (e.g. represent 1-bit as `{0, 1}`) but we'd also set `maxval` accordingly and
+        // this requires tupltype to be `BLACKANDWHITE` so introducing a bunch of complexity. If
+        // you want to do that in your real code, go ahead.
+        DecodingBuffer::U8(buf) => match colortype.bit_depth() {
+            8 => u64::from(u8::MAX),
+            4 => {
+                fallback_buffer = vec![0; (swidth * sheight) as usize];
+                expand_4bit(buf, swidth, &mut fallback_buffer);
+                *data = DecodingResult::U8(fallback_buffer);
+                u64::from(u8::MAX)
+            }
+            2 => {
+                fallback_buffer = vec![0; (swidth * sheight) as usize];
+                expand_2bit(buf, swidth, &mut fallback_buffer);
+                *data = DecodingResult::U8(fallback_buffer);
+                u64::from(u8::MAX)
+            }
+            1 => {
+                fallback_buffer = vec![0; (swidth * sheight) as usize];
+                expand_1bit(buf, swidth, &mut fallback_buffer);
+                *data = DecodingResult::U8(fallback_buffer);
+                u64::from(u8::MAX)
+            }
+            _ => {
+                eprintln!(
+                    "Unsupported bit depth for U8 buffer: {}",
+                    colortype.bit_depth()
+                );
+                return;
+            }
+        },
         DecodingBuffer::U16(_) => u64::from(u16::MAX),
         DecodingBuffer::U32(_) => u64::from(u32::MAX),
         DecodingBuffer::U64(_) => u64::MAX,
@@ -101,3 +151,56 @@ fn debug_planes(
             .expect("Failed to write PAM data");
     }
 }
+
+/// Put exactly the ith `SCALE`-bit chunk of `val` into the least significant bits.
+#[inline(always)]
+fn bits_extract<const SCALE: u8>(val: u8, i: u8) -> u8 {
+    // Shift left to discard high bits, then right to bring desired bits down. This way also
+    // conveniently avoids all cases of overflow.
+    (val << (i * SCALE)) >> (8 - SCALE)
+}
+
+fn expand_1bit(from: &[u8], samples_per_padded: u64, into: &mut [u8]) {
+    let stride = samples_per_padded.div_ceil(8);
+
+    let from_row = from.chunks_exact(stride as usize);
+    let into_row = into.chunks_exact_mut(samples_per_padded as usize);
+
+    for (from_row, into_row) in from_row.zip(into_row) {
+        for (into, &from) in into_row.chunks_mut(8).zip(from_row) {
+            let data =
+                core::array::from_fn::<u8, 8, _>(|i| 0xff * bits_extract::<1>(from, i as u8));
+            into.copy_from_slice(&data[..into.len()]);
+        }
+    }
+}
+
+fn expand_2bit(from: &[u8], samples_per_padded: u64, into: &mut [u8]) {
+    let stride = samples_per_padded.div_ceil(4);
+
+    let from_row = from.chunks_exact(stride as usize);
+    let into_row = into.chunks_exact_mut(samples_per_padded as usize);
+
+    for (from_row, into_row) in from_row.zip(into_row) {
+        for (into, &from) in into_row.chunks_mut(4).zip(from_row) {
+            let data =
+                core::array::from_fn::<u8, 4, _>(|i| 0xaa * bits_extract::<2>(from, i as u8));
+            into.copy_from_slice(&data[..into.len()]);
+        }
+    }
+}
+
+fn expand_4bit(from: &[u8], samples_per_padded: u64, into: &mut [u8]) {
+    let stride = samples_per_padded.div_ceil(2);
+
+    let from_row = from.chunks_exact(stride as usize);
+    let into_row = into.chunks_exact_mut(samples_per_padded as usize);
+
+    for (from_row, into_row) in from_row.zip(into_row) {
+        for (into, &from) in into_row.chunks_mut(2).zip(from_row) {
+            let data =
+                core::array::from_fn::<u8, 2, _>(|i| 0x88 * bits_extract::<4>(from, i as u8));
+            into.copy_from_slice(&data[..into.len()]);
+        }
+    }
+}

src/decoder/mod.rs

@@ -1396,14 +1396,16 @@ impl<R: Read + Seek> Decoder<R> {
     /// # Bugs
     ///
     /// When the image is stored as a planar configuration, this method will currently only read
-    /// the first sample's plane. This will be fixed in a future major version of `tiff`.
+    /// the first sample's plane. This will be fixed in a future major version of `tiff`. To read
+    /// multiple planes, [`Self::read_image_to_buffer`] can be used instead.
     ///
     /// # Intent to deprecate
     ///
-    /// Use `DecodingResult::resize_to` and `read_image_bytes` instead where possible, preserving
-    /// the buffer across multiple calls. This old method will likely keep its bugged planar
-    /// behavior until it is fully replaced, to ensure that existing code will not run into
-    /// unexpectedly large allocations that will error on limits instead.
+    /// Use [`Self::read_image_to_buffer`] or a combination of [`DecodingResult::resize_to`] and
+    /// [`Self::read_image_bytes`] instead where possible, preserving the buffer across multiple
+    /// calls. This old method will likely keep its bugged planar behavior until it is fully
+    /// replaced, to ensure that existing code will not run into unexpectedly large allocations
+    /// that will error on limits instead.
     pub fn read_image(&mut self) -> TiffResult<DecodingResult> {
         let readout = self.image().readout_for_image()?;
 
@@ -1422,6 +1424,30 @@ impl<R: Read + Seek> Decoder<R> {
     /// configured limits, and then pass it to the underlying method. This is essentially a
     /// type-safe wrapper around the raw [`Self::read_image_bytes`] method.
     ///
+    /// ## Planar behavior
+    ///
+    /// If the image is stored as a planar configuration, an attempt is made to resize the buffer
+    /// to hold all planes. If that does not fit then only the first plane is read. Check the
+    /// buffer size against [`BufferLayoutPreference::complete_len`] to ensure that all planes were
+    /// read:
+    ///
+    /// ```
+    /// use tiff::decoder::{Decoder, DecodingResult};
+    /// let mut result = DecodingResult::U8(vec![]);
+    ///
+    /// let mut reader = /* */
+    /// # Decoder::new(std::io::Cursor::new(include_bytes!(concat!(
+    /// #   env!("CARGO_MANIFEST_DIR"), "/tests/images/tiled-gray-i1.tif"
+    /// # )))).unwrap();
+    /// let layout = reader.read_image_to_buffer(&mut result)?;
+    ///
+    /// if result.as_buffer(0).as_bytes().len() < layout.complete_len {
+    ///    println!("Only the first plane was read");
+    /// }
+    ///
+    /// # Ok::<_, tiff::TiffError>(())
+    /// ```
+    ///
     /// # Examples
     ///
     /// ```
@@ -1443,12 +1469,20 @@ impl<R: Read + Seek> Decoder<R> {
         result: &mut DecodingResult,
     ) -> TiffResult<BufferLayoutPreference> {
         let readout = self.image().readout_for_image()?;
-
         let planes = readout.to_plane_layout()?;
-        let layout = BufferLayoutPreference::from_planes(&planes);
 
-        let extent = readout.result_extent_for_planes(0..1)?;
+        let num_planes = if planes.total_bytes <= self.value_reader.limits.decoding_buffer_size {
+            planes.plane_offsets.len() as u16
+        } else {
+            1
+        };
+
+        let layout = BufferLayoutPreference::from_planes(&planes);
+        let extent = readout.result_extent_for_planes(0..num_planes)?;
+        // Compatibility: if this extent is too large our configured limits we will fall back to
+        // reading only the first plane.
         result.resize_to_extent(extent, &self.value_reader.limits)?;
+
         self.read_image_bytes(result.as_buffer(0).as_bytes_mut())?;
 
         Ok(layout)

src/lib.rs

@@ -51,7 +51,8 @@ pub enum ColorType {
     Multiband { bit_depth: u8, num_samples: u16 },
 }
 impl ColorType {
-    fn bit_depth(&self) -> u8 {
+    /// The number of bits used to store each sample.
+    pub fn bit_depth(&self) -> u8 {
         match *self {
             ColorType::Gray(b)
             | ColorType::RGB(b)
@@ -66,7 +67,8 @@ impl ColorType {
         }
     }
 
-    fn num_samples(&self) -> u16 {
+    /// The number of samples in each representation of a single color.
+    pub fn num_samples(&self) -> u16 {
         match *self {
             ColorType::Gray(_) => 1,
             ColorType::RGB(_) => 3,

tests/decode_planes.rs

@@ -1,4 +1,4 @@
-use tiff::decoder::{Decoder, TiffCodingUnit};
+use tiff::decoder::{Decoder, DecodingResult, Limits, TiffCodingUnit};
 
 use std::fs::File;
 use std::path::PathBuf;
@@ -74,3 +74,50 @@ fn read_first_coding_unit() {
         }
     }
 }
+
+#[test]
+fn read_planes_by_limits() {
+    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 limits = Limits::default();
+    let mut buffer = DecodingResult::U8(vec![]);
+
+    // Make room for 1 plane.
+    let mut tif = Decoder::new(io).unwrap();
+    tif = tif.with_limits({
+        limits.decoding_buffer_size = 374 * 499;
+        limits.clone()
+    });
+
+    tif.read_image_to_buffer(&mut buffer).unwrap();
+    assert_eq!(buffer.as_buffer(0).byte_len(), 374 * 499);
+
+    // Make room for 2 planes.
+    tif = tif.with_limits({
+        limits.decoding_buffer_size = 374 * 499 * 2;
+        limits.clone()
+    });
+
+    tif.read_image_to_buffer(&mut buffer).unwrap();
+    assert_eq!(buffer.as_buffer(0).byte_len(), 374 * 499);
+
+    // Make room for 3 planes.
+    tif = tif.with_limits({
+        limits.decoding_buffer_size = 374 * 499 * 3;
+        limits.clone()
+    });
+
+    tif.read_image_to_buffer(&mut buffer).unwrap();
+    assert_eq!(buffer.as_buffer(0).byte_len(), 374 * 499 * 3);
+
+    // Make room for 4 planes?
+    tif = tif.with_limits({
+        limits.decoding_buffer_size = 374 * 499 * 4;
+        limits.clone()
+    });
+
+    tif.read_image_to_buffer(&mut buffer).unwrap();
+    assert_eq!(buffer.as_buffer(0).byte_len(), 374 * 499 * 3);
+}