Date a DNG whose IFDs follow its pixels: read the head and the tail

The scan reads the first 256 KB of a file for its metadata. A camera
writes its IFDs at the front, so that is the whole structure; the linear
DNG a merge writes puts its first IFD after the pixels, and rawler,
given the head alone, finds no decoder in it. The composite was
catalogued without a date and sorted to the very end of the grid, after
every dated photograph — which is where a panorama merged on the tablet
went unfound.

dr-decode's own TIFF reader now reads through a head and a tail at a
known offset; trailing_ifd says where the tail starts and
metadata_split reads the two together. The scan, when the head fails
and points beyond itself, fetches from the IFD to the end — kilobytes —
and dates the file from both. Tested against the writer's own output.

core/dr-decode/src/locate.rs

@@ -183,22 +183,65 @@ struct Entry {
     value: u32,
 }
 
+/// The bytes a [`TiffReader`] reads: the head of a file, and optionally a
+/// second range from further in, at a known offset.
+///
+/// A camera writes its IFDs at the front, so the first 256 KB of a file
+/// is the whole structure. A file written strip by strip — the linear
+/// DNG a merge produces — has its first IFD at the *end*, after the
+/// pixels, and a reader that only has the head sees a pointer into
+/// nothing. Rather than fetch 800 MB to read a date, the caller fetches
+/// the head, asks [`crate::trailing_ifd`] where the IFD is, fetches that
+/// tail, and reads through both. Offsets are the file's own throughout;
+/// a read that falls in neither range is simply absent.
+#[derive(Clone, Copy)]
+struct Src<'a> {
+    head: &'a [u8],
+    tail: &'a [u8],
+    /// Where `tail` starts in the file.
+    tail_at: usize,
+}
+
+impl<'a> Src<'a> {
+    fn whole(data: &'a [u8]) -> Self {
+        Src {
+            head: data,
+            tail: &[],
+            tail_at: 0,
+        }
+    }
+
+    fn get(&self, start: usize, len: usize) -> Option<&'a [u8]> {
+        let end = start.checked_add(len)?;
+        if let Some(b) = self.head.get(start..end) {
+            return Some(b);
+        }
+        let s = start.checked_sub(self.tail_at)?;
+        self.tail.get(s..s.checked_add(len)?)
+    }
+}
+
 /// A minimal TIFF structure reader.
 ///
 /// Deliberately not a general TIFF parser: it reads the IFD chain and entry
 /// values and nothing else, because that is all locating a preview needs.
 struct TiffReader<'a> {
-    data: &'a [u8],
+    data: Src<'a>,
     little_endian: bool,
     first_ifd: u32,
 }
 
 impl<'a> TiffReader<'a> {
     fn new(data: &'a [u8]) -> Option<Self> {
-        if data.len() < 8 {
+        Self::over(Src::whole(data))
+    }
+
+    fn over(data: Src<'a>) -> Option<Self> {
+        let head = data.head;
+        if head.len() < 8 {
             return None;
         }
-        let little_endian = match &data[0..2] {
+        let little_endian = match &head[0..2] {
             b"II" => true,
             b"MM" => false,
             _ => return None,
@@ -362,9 +405,7 @@ impl<'a> TiffReader<'a> {
             };
             raw[..len.min(4)].to_vec()
         } else {
-            self.data
-                .get(e.value as usize..e.value as usize + len)?
-                .to_vec()
+            self.data.get(e.value as usize, len)?.to_vec()
         };
 
         let s = String::from_utf8_lossy(&bytes);
@@ -396,8 +437,7 @@ impl<'a> TiffReader<'a> {
             // same way to recover the original byte order.
             return None;
         }
-        let start = e.value as usize;
-        self.data.get(start..start.checked_add(len)?)
+        self.data.get(e.value as usize, len)
     }
 
     fn offsets(&self, e: &Entry) -> Vec<u32> {
@@ -420,8 +460,8 @@ impl<'a> TiffReader<'a> {
     }
 }
 
-fn read_u16(data: &[u8], at: usize, le: bool) -> Option<u16> {
-    let b = data.get(at..at + 2)?;
+fn read_u16(data: Src<'_>, at: usize, le: bool) -> Option<u16> {
+    let b = data.get(at, 2)?;
     Some(if le {
         u16::from_le_bytes([b[0], b[1]])
     } else {
@@ -429,8 +469,8 @@ fn read_u16(data: &[u8], at: usize, le: bool) -> Option<u16> {
     })
 }
 
-fn read_u32(data: &[u8], at: usize, le: bool) -> Option<u32> {
-    let b = data.get(at..at + 4)?;
+fn read_u32(data: Src<'_>, at: usize, le: bool) -> Option<u32> {
+    let b = data.get(at, 4)?;
     Some(if le {
         u32::from_le_bytes([b[0], b[1], b[2], b[3]])
     } else {
@@ -460,7 +500,36 @@ pub fn jpeg_metadata(bytes: &[u8]) -> Result<crate::Metadata, crate::DecodeError
 /// no `DateTimeOriginal` for some DNGs whose tag sits plainly at byte 826 —
 /// and without this fallback those images are silently undated.
 pub fn tiff_metadata(tiff_data: &[u8]) -> Result<crate::Metadata, crate::DecodeError> {
-    let reader = TiffReader::new(tiff_data)
+    tiff_metadata_over(Src::whole(tiff_data))
+}
+
+/// Where a TIFF-shaped file's first IFD is, when the head does not reach
+/// it: the offset to fetch from, so [`tiff_metadata_split`] can read it.
+/// `None` for a file that is not TIFF, or whose IFD the head already holds.
+pub fn trailing_ifd(head: &[u8]) -> Option<u64> {
+    let r = TiffReader::new(head)?;
+    let at = r.first_ifd as u64;
+    (at >= head.len() as u64).then_some(at)
+}
+
+/// [`tiff_metadata`] over a head and a tail fetched separately: the head
+/// from offset 0, the tail from `tail_at`. For the file whose IFDs follow
+/// its pixels.
+pub fn tiff_metadata_split(
+    head: &[u8],
+    tail: &[u8],
+    tail_at: u64,
+) -> Result<crate::Metadata, crate::DecodeError> {
+    tiff_metadata_over(Src {
+        head,
+        tail,
+        tail_at: usize::try_from(tail_at)
+            .map_err(|_| crate::DecodeError::Metadata("tail offset out of range".into()))?,
+    })
+}
+
+fn tiff_metadata_over(src: Src<'_>) -> Result<crate::Metadata, crate::DecodeError> {
+    let reader = TiffReader::over(src)
         .ok_or_else(|| crate::DecodeError::Metadata("malformed EXIF header".into()))?;
 
     let mut md = crate::Metadata::default();