Merge pull request #325 from image-rs/decode-values-into-buffer

Decode tag values into buffer

src/decoder/ifd.rs

@@ -6,7 +6,7 @@ use std::mem;
 use std::str;
 
 use super::stream::{ByteOrder, EndianReader};
-use crate::tags::{IfdPointer, Tag, Type};
+use crate::tags::{IfdPointer, Tag, Type, ValueBuffer};
 use crate::{TiffError, TiffFormatError, TiffResult};
 
 use self::Value::{
@@ -579,7 +579,7 @@ 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)?;
+        self.set_reader_offset_relative(bigtiff, reader, 0)?;
 
         match self.type_ {
             Type::BYTE | Type::UNDEFINED => {
@@ -737,6 +737,113 @@ impl Entry {
         Ok(List(v))
     }
 
+    pub(crate) fn buffered_value<R: Read + Seek>(
+        &self,
+        buf: &mut ValueBuffer,
+        limits: &super::Limits,
+        bigtiff: bool,
+        reader: &mut EndianReader<R>,
+    ) -> TiffResult<()> {
+        if self.count == 0 {
+            buf.assume_type(self.type_, 0, reader.byte_order);
+            return Ok(());
+        }
+
+        let value_bytes = self.buffer_with_capacity(buf, limits)?;
+
+        // Case 1: the value fits in the offset field.
+        if value_bytes <= 4 || bigtiff && value_bytes <= 8 {
+            let src = &self.offset[..value_bytes];
+            buf.raw_bytes_mut()[..value_bytes].copy_from_slice(src);
+            buf.assume_type(self.type_, self.count, reader.byte_order);
+
+            return Ok(());
+        }
+
+        // Case 2: the value is stored in the reader at an offset.
+        self.set_reader_offset_relative(bigtiff, reader, 0)?;
+
+        // In case of an error we set the type and endianess.
+        buf.assume_type(self.type_, 0, reader.byte_order);
+        let target = &mut buf.raw_bytes_mut()[..value_bytes];
+        // FIXME: if the read fails we have already grown to full size, which is not great.
+        reader.inner().read_exact(target)?;
+        buf.assume_type(self.type_, self.count, reader.byte_order);
+
+        Ok(())
+    }
+
+    pub(crate) fn raw_value_at<R: Read + Seek>(
+        &self,
+        buf: &mut [u8],
+        bigtiff: bool,
+        reader: &mut EndianReader<R>,
+        at: u64,
+    ) -> TiffResult<usize> {
+        if self.count == 0 {
+            return Ok(0);
+        }
+
+        // We have no limits to handle, we do not allocate.
+        let value_bytes = self.type_.value_bytes(self.count)?;
+
+        // No bytes to fill into the buffer.
+        if at >= value_bytes {
+            return Ok(0);
+        }
+
+        // Case 1: the value fits in the offset field.
+        if value_bytes <= 4 || bigtiff && value_bytes <= 8 {
+            // `at < value_bytes` and `value_bytes <= 8` so casting is mathematical
+            let src = &self.offset[..value_bytes as usize][at as usize..];
+            let len = src.len().min(buf.len());
+            buf[..len].copy_from_slice(&src[..len]);
+            return Ok(value_bytes as usize);
+        }
+
+        // Case 2: the value is stored in the reader at an offset. We will find the offset
+        // encoded in the entry, apply the relative start position and seek there.
+        self.set_reader_offset_relative(bigtiff, reader, at)?;
+
+        let remainder = value_bytes - at;
+        let len = usize::try_from(remainder)
+            .unwrap_or(usize::MAX)
+            .min(buf.len());
+
+        let target = &mut buf[..len];
+        reader.inner().read_exact(target)?;
+
+        // Design note: in a previous draft we would consume the rest of the bytes of this value
+        // here (into a stack buffer if need be) to verify the stream itself. But in the end we
+        // have `Seek` so we better verify this by seeking over the rest of the bytes, finding if
+        // the stream continues that far. Even that is maybe bad if we wanted to provide a
+        // async-adaptor that `WouldBlock` errors to fill back a read window then the seek is
+        // poison to that, too.
+
+        // So a really simple choice: The caller is responsible for handling the fact that this did
+        // not verify the whole value. Attempt a 1-byte read at the end of the value instead?
+        Ok(len)
+    }
+
+    // Returns `Ok(bytes)` if our value's bytes through type and count fit into `usize` and are
+    // within the limits. Extends the buffer to that many bytes.
+    fn buffer_with_capacity(
+        &self,
+        buf: &mut ValueBuffer,
+        limits: &super::Limits,
+    ) -> TiffResult<usize> {
+        let bytes = self.type_.value_bytes(self.count())?;
+
+        let allowed_length = usize::try_from(bytes)
+            .ok()
+            .filter(|&n| n <= limits.decoding_buffer_size)
+            .ok_or(TiffError::LimitsExceeded)?;
+
+        buf.prepare_length(allowed_length);
+
+        Ok(allowed_length)
+    }
+
     fn vec_with_capacity(
         value_count: u64,
         limits: &super::Limits,
@@ -750,21 +857,32 @@ impl Entry {
         Ok(Vec::with_capacity(value_count))
     }
 
-    fn set_reader_offset<R>(
+    /// Seek to an offset within a value stored in the offset defined by this entry.
+    fn set_reader_offset_relative<R>(
         &self,
-        bo: ByteOrder,
         bigtiff: bool,
         reader: &mut EndianReader<R>,
+        at: u64,
     ) -> TiffResult<()>
     where
         R: Read + Seek,
     {
+        let bo = reader.byte_order;
+
         let offset = if bigtiff {
             self.offset_field_reader(bo).read_u64()?
         } else {
             self.offset_field_reader(bo).read_u32()?.into()
         };
 
+        // FIXME: `at` should be within `self.type_.value_bytes(self.count)` and that itself should
+        // be within the bounds of the stream. But we do not check this eagerly so this below will
+        // fail sometimes differently for exotic streams, depending on the method by which we read
+        // (at once or through multiple raw into-byte-slice reads).
+        let offset = offset.checked_add(at).ok_or(TiffError::FormatError(
+            TiffFormatError::InconsistentSizesEncountered,
+        ))?;
+
         reader.goto_offset(offset)?;
 
         Ok(())

src/decoder/mod.rs

@@ -5,7 +5,7 @@ use std::num::NonZeroUsize;
 
 use crate::tags::{
     CompressionMethod, IfdPointer, PhotometricInterpretation, PlanarConfiguration, Predictor,
-    SampleFormat, Tag, Type,
+    SampleFormat, Tag, Type, ValueBuffer,
 };
 use crate::{
     bytecast, ColorType, Directory, TiffError, TiffFormatError, TiffResult, TiffUnsupportedError,
@@ -1717,12 +1717,41 @@ impl<R: Seek + Read> ValueReader<R> {
 }
 
 impl IfdDecoder<'_> {
+    /// Retrieve the IFD entry for a given tag, if it exists.
+    ///
+    /// The entry contains the metadata of the value, that is its type and count from which we can
+    /// calculate a total byte size.
+    pub fn find_entry(&self, tag: Tag) -> Option<ifd::Entry> {
+        self.inner.ifd.get(tag).cloned()
+    }
+
     /// Tries to retrieve a tag.
     /// Return `Ok(None)` if the tag is not present.
     pub fn find_tag(&mut self, tag: Tag) -> TiffResult<Option<ifd::Value>> {
         self.inner.find_tag(tag)
     }
 
+    /// Retrieve a tag and reproduce its bytes into the provided buffer.
+    ///
+    /// The buffer is unmodified if the tag is not present.
+    pub fn find_tag_buf(
+        &mut self,
+        tag: Tag,
+        buf: &mut ValueBuffer,
+    ) -> TiffResult<Option<ifd::Entry>> {
+        self.inner.find_tag_buf(tag, buf)
+    }
+
+    /// Read bytes of a tag's value into a byte buffer.
+    pub fn find_tag_bytes(
+        &mut self,
+        tag: Tag,
+        buf: &mut [u8],
+        offset: u64,
+    ) -> TiffResult<Option<usize>> {
+        self.inner.find_tag_raw(tag, buf, offset)
+    }
+
     /// Tries to retrieve a tag and convert it to the desired unsigned type.
     pub fn find_tag_unsigned<T: TryFrom<u64>>(&mut self, tag: Tag) -> TiffResult<Option<T>> {
         self.find_tag(tag)?
@@ -1836,3 +1865,70 @@ impl<'l> IfdDecoder<'l> {
             })
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::Decoder;
+    use crate::{
+        bytecast,
+        tags::{ByteOrder, Tag, ValueBuffer},
+    };
+
+    #[test]
+    fn equivalence_of_tag_readers() {
+        let file = std::fs::File::open(concat!(
+            env!("CARGO_MANIFEST_DIR"),
+            "/tests/images/int8_rgb.tif"
+        ))
+        .unwrap();
+
+        let mut decoder = Decoder::new(file).unwrap();
+        let file_bo = decoder.byte_order();
+        let mut ifd = decoder.image_ifd();
+
+        {
+            let value = ifd
+                .find_tag(Tag::BitsPerSample)
+                .unwrap()
+                .expect("must have BitsPerSample");
+
+            let samples = value.into_u16_vec().unwrap();
+            assert_eq!(samples.as_slice(), [8, 8, 8]);
+        }
+
+        {
+            let mut value = ValueBuffer::from_value(&[0u16; 4]);
+            let _entry = ifd
+                .find_tag_buf(Tag::BitsPerSample, &mut value)
+                .unwrap()
+                .expect("must have BitsPerSample");
+
+            value.set_byte_order(ByteOrder::native());
+            assert_eq!(value.as_bytes(), bytecast::u16_as_ne_bytes(&[8, 8, 8]));
+        }
+
+        {
+            let mut by_bytes = [0u16; 4];
+            let entry = ifd
+                .find_entry(Tag::BitsPerSample)
+                .expect("must have BitsPerSample");
+
+            let byte_len = ifd
+                .find_tag_bytes(
+                    Tag::BitsPerSample,
+                    bytecast::u16_as_ne_mut_bytes(&mut by_bytes),
+                    0,
+                )
+                .unwrap()
+                .expect("must have BitsPerSample");
+            assert_eq!(byte_len, 3 * std::mem::size_of::<u16>());
+
+            file_bo.convert(
+                entry.field_type(),
+                bytecast::u16_as_ne_mut_bytes(&mut by_bytes[..3]),
+                ByteOrder::native(),
+            );
+            assert_eq!(&by_bytes[..3], &[8, 8, 8]);
+        }
+    }
+}

src/decoder/tag_reader.rs

@@ -1,7 +1,9 @@
 use std::io::{Read, Seek};
 
-use crate::{tags::Tag, Directory};
+use crate::{
-use crate::{TiffError, TiffFormatError, TiffResult};
+    tags::{Tag, ValueBuffer},
+    Directory, TiffError, TiffFormatError, TiffResult,
+};
 
 use super::ifd::{Entry, Value};
 use super::ValueReader;
@@ -14,12 +16,25 @@ pub(crate) struct TagReader<'lt, R: EntryDecoder + ?Sized> {
 pub(crate) trait EntryDecoder {
     /// Turn an entry into a value by fetching the required bytes in the stream.
     fn entry_val(&mut self, entry: &Entry) -> TiffResult<Value>;
+    /// Fill a  `ValueBuffer` by fetching the required bytes.
+    fn entry_buf(&mut self, entry: &Entry, _: &mut ValueBuffer) -> TiffResult<()>;
+    /// Fill the prefix of the buffer and return the actual bytes. Start interpreting the inner
+    /// value at `offset`.
+    fn entry_raw(&mut self, entry: &Entry, _: &mut [u8], offset: u64) -> TiffResult<usize>;
 }
 
 impl<R: Seek + Read> EntryDecoder for ValueReader<R> {
     fn entry_val(&mut self, entry: &Entry) -> TiffResult<Value> {
         entry.val(&self.limits, self.bigtiff, &mut self.reader)
     }
+
+    fn entry_buf(&mut self, entry: &Entry, buf: &mut ValueBuffer) -> TiffResult<()> {
+        entry.buffered_value(buf, &self.limits, self.bigtiff, &mut self.reader)
+    }
+
+    fn entry_raw(&mut self, entry: &Entry, buf: &mut [u8], offset: u64) -> TiffResult<usize> {
+        entry.raw_value_at(buf, self.bigtiff, &mut self.reader, offset)
+    }
 }
 
 impl<'a, R: EntryDecoder + ?Sized> TagReader<'a, R> {
@@ -32,6 +47,39 @@ impl<'a, R: EntryDecoder + ?Sized> TagReader<'a, R> {
         self.decoder.entry_val(&entry).map(Some)
     }
 
+    /// Find a tag and fill the provided buffer with its raw data.
+    ///
+    /// Returns the entry of the tag if found. This signals that the buffer was overwritten.
+    /// Otherwise the buffer is preserved as-is.
+    pub(crate) fn find_tag_buf(
+        &mut self,
+        tag: Tag,
+        buf: &mut ValueBuffer,
+    ) -> TiffResult<Option<Entry>> {
+        let entry = match self.ifd.get(tag) {
+            None => return Ok(None),
+            Some(entry) => entry.clone(),
+        };
+
+        self.decoder.entry_buf(&entry, buf)?;
+        Ok(Some(entry))
+    }
+
+    pub(crate) fn find_tag_raw(
+        &mut self,
+        tag: Tag,
+        buf: &mut [u8],
+        at: u64,
+    ) -> TiffResult<Option<usize>> {
+        let entry = match self.ifd.get(tag) {
+            None => return Ok(None),
+            Some(entry) => entry.clone(),
+        };
+
+        let len = self.decoder.entry_raw(&entry, buf, at)?;
+        Ok(Some(len))
+    }
+
     pub(crate) fn require_tag(&mut self, tag: Tag) -> TiffResult<Value> {
         match self.find_tag(tag)? {
             Some(val) => Ok(val),

src/tags.rs

@@ -346,6 +346,10 @@ pub struct ValueBuffer {
     /// The type of the value.
     ty: Type,
 
+    /// The number of items, as `bytes` may be oversized while holding bytes that are initialized
+    /// but not used by any value.
+    count: u64,
+
     /// The byte order of the value.
     byte_order: ByteOrder,
 }
@@ -358,6 +362,7 @@ impl ValueBuffer {
         ValueBuffer {
             bytes: vec![],
             ty,
+            count: 0,
             byte_order: ByteOrder::native(),
         }
     }
@@ -367,6 +372,7 @@ impl ValueBuffer {
         ValueBuffer {
             bytes: value.data().into_owned(),
             ty: <T as TiffValue>::FIELD_TYPE,
+            count: value.count() as u64,
             byte_order: ByteOrder::native(),
         }
     }
@@ -381,26 +387,73 @@ impl ValueBuffer {
 
     /// The count of items in the value.
     pub fn count(&self) -> u64 {
-        (self.bytes.len() / usize::from(self.ty.byte_len())) as u64
+        debug_assert!({
+            self.ty
+                .value_bytes(self.count)
+                .is_ok_and(|n| n < self.bytes.len() as u64)
+        });
+
+        self.count
     }
 
     /// View the underlying raw bytes of this value.
     pub fn as_bytes(&self) -> &[u8] {
-        &self.bytes
+        &self.bytes[..self.assumed_len_from_count()]
     }
 
     /// View the underlying mutable raw bytes of this value.
     pub fn as_bytes_mut(&mut self) -> &mut [u8] {
-        &mut self.bytes
+        let len = self.assumed_len_from_count();
+        &mut self.bytes[..len]
     }
 
     /// Change the byte order of the value representation.
     pub fn set_byte_order(&mut self, byte_order: ByteOrder) {
+        let len = self.assumed_len_from_count();
+
         self.byte_order
-            .convert(self.ty, self.bytes.as_mut_slice(), byte_order);
+            .convert(self.ty, &mut self.bytes[..len], byte_order);
 
         self.byte_order = byte_order;
     }
+
+    /// Prepare the internal for a value `to_len` bytes long.
+    ///
+    /// Shrinks the allocation if it is far too large or extends it if it is too small. In either
+    /// case ensures that at least `to_len` bytes are initialized for [`Self::raw_bytes_mut`].
+    pub(crate) fn prepare_length(&mut self, to_len: usize) {
+        if to_len > self.bytes.len() {
+            self.bytes.resize(to_len, 0);
+        }
+
+        if self.bytes.len() < to_len / 2 {
+            self.bytes.truncate(to_len);
+            self.bytes.shrink_to_fit();
+        }
+    }
+
+    /// Internal method to change the type and count while re-interpreting the byte buffer.
+    ///
+    /// Should only be called after writing bytes to the internal buffer prepared with
+    /// `Self::prepare_length`.
+    pub(crate) fn assume_type(&mut self, ty: Type, count: u64, bo: ByteOrder) {
+        debug_assert!({
+            ty.value_bytes(count)
+                .is_ok_and(|n| n < self.bytes.len() as u64)
+        });
+
+        self.byte_order = bo;
+        self.ty = ty;
+        self.count = count;
+    }
+
+    pub(crate) fn raw_bytes_mut(&mut self) -> &mut [u8] {
+        &mut self.bytes
+    }
+
+    fn assumed_len_from_count(&self) -> usize {
+        usize::from(self.ty.byte_len()) * self.count as usize
+    }
 }
 
 /// Byte order of the TIFF file.