crates/clawhdf5-format/src/object_header.rs

@@ -7,6 +7,7 @@ use byteorder::{ByteOrder, LittleEndian};
 
 use crate::error::FormatError;
 use crate::message_type::MessageType;
+use crate::storage::{Storage, len_usize, read_exact_at, read_upto};
 
 /// OHDR signature for v2 object headers.
 const OHDR_SIGNATURE: [u8; 4] = *b"OHDR";
@@ -118,32 +119,45 @@ impl ObjectHeader {
         offset_size: u8,
         length_size: u8,
     ) -> Result<ObjectHeader, FormatError> {
-        ensure_len(data, offset, 4)?;
-        if data[offset..offset + 4] == OHDR_SIGNATURE {
-            Self::parse_v2(data, offset, offset_size, length_size)
+        Self::parse_in(&data, offset as u64, offset_size, length_size)
+    }
+
+    /// [`Self::parse`] over any [`Storage`].
+    ///
+    /// Reads the signature, the prefix (at most [`V2_PREFIX_MAX`] bytes),
+    /// then each chunk as one bounded read, continuation chunks included.
+    pub fn parse_in(
+        file: &dyn Storage,
+        offset: u64,
+        offset_size: u8,
+        length_size: u8,
+    ) -> Result<ObjectHeader, FormatError> {
+        let sig = read_exact_at(file, offset, 4)?;
+        if *sig == OHDR_SIGNATURE {
+            Self::parse_v2(file, offset, offset_size, length_size)
         } else {
-            Self::parse_v1(data, offset, offset_size, length_size)
+            Self::parse_v1(file, offset, offset_size, length_size)
         }
     }
 
     fn parse_v1(
-        data: &[u8],
-        offset: usize,
+        file: &dyn Storage,
+        offset: u64,
         offset_size: u8,
         length_size: u8,
     ) -> Result<ObjectHeader, FormatError> {
         // version(1) + reserved(1) + num_messages(2) + ref_count(4) + header_size(4) = 12
         // then pad to 8-byte alignment from start of header
-        ensure_len(data, offset, 12)?;
+        let prefix = read_exact_at(file, offset, 12)?;
 
-        let version = data[offset];
+        let version = prefix[0];
         if version != 1 {
             return Err(FormatError::InvalidObjectHeaderVersion(version));
         }
 
-        let num_messages = LittleEndian::read_u16(&data[offset + 2..offset + 4]) as usize;
-        let reference_count = LittleEndian::read_u32(&data[offset + 4..offset + 8]);
-        let header_data_size = LittleEndian::read_u32(&data[offset + 8..offset + 12]) as usize;
+        let num_messages = LittleEndian::read_u16(&prefix[2..4]) as usize;
+        let reference_count = LittleEndian::read_u32(&prefix[4..8]);
+        let header_data_size = LittleEndian::read_u32(&prefix[8..12]) as usize;
 
         // libhdf5 (H5O__prefix_deserialize): a header with messages needs room
         // for at least one message header, and one without has an empty chunk.
@@ -161,14 +175,13 @@ impl ObjectHeader {
             .checked_add(12 + padding)
             .ok_or(FormatError::UnexpectedEof {
                 expected: usize::MAX,
-                available: data.len(),
+                available: len_usize(file),
             })?;
 
-        ensure_len(data, msg_start, header_data_size)?;
-
+        // parse_v1_chunk reads the chunk, with the bounds check that was here.
         let mut messages = Vec::new();
         let chunk0_count = Self::parse_v1_chunk(
-            data,
+            file,
             msg_start,
             header_data_size,
             offset_size,
@@ -209,8 +222,8 @@ impl ObjectHeader {
     /// "gap", which only version 2 allows).
     #[allow(clippy::too_many_arguments)]
     fn parse_v1_chunk(
-        data: &[u8],
-        offset: usize,
+        file: &dyn Storage,
+        offset: u64,
         length: usize,
         offset_size: u8,
         length_size: u8,
@@ -220,9 +233,10 @@ impl ObjectHeader {
         if depth_remaining == 0 {
             return Err(FormatError::NestingDepthExceeded);
         }
-        ensure_len(data, offset, length)?;
-        let end = offset + length;
-        let mut pos = offset;
+        let chunk = read_exact_at(file, offset, length)?;
+        let data: &[u8] = &chunk;
+        let end = length;
+        let mut pos = 0usize;
         let mut count = 0usize;
 
         while pos < end {
@@ -267,8 +281,8 @@ impl ObjectHeader {
                 let cont_offset = read_offset(body, 0, offset_size)? as usize;
                 let cont_length = read_offset(body, offset_size as usize, length_size)? as usize;
                 Self::parse_v1_chunk(
-                    data,
-                    cont_offset,
+                    file,
+                    cont_offset as u64,
                     cont_length,
                     offset_size,
                     length_size,
@@ -282,11 +296,31 @@ impl ObjectHeader {
     }
 
     fn parse_v2(
-        data: &[u8],
-        offset: usize,
+        file: &dyn Storage,
+        offset: u64,
         offset_size: u8,
         length_size: u8,
     ) -> Result<ObjectHeader, FormatError> {
+        // The prefix, read as one window. The window holds the whole prefix
+        // or ends at the end of the file, so a position past the window is
+        // past the end of the file: `ensure_len` checks positions relative
+        // to the header against it and reports them as the whole-file check
+        // did, with absolute positions and the file's length.
+        let window = read_upto(file, offset, V2_PREFIX_MAX)?;
+        let data: &[u8] = &window;
+        let file_len = len_usize(file);
+        let base = usize::try_from(offset).unwrap_or(usize::MAX);
+        let abs = |rel: usize| base.saturating_add(rel);
+        let ensure_len = |_: &[u8], rel: usize, needed: usize| -> Result<(), FormatError> {
+            match rel.checked_add(needed) {
+                Some(end) if end <= data.len() => Ok(()),
+                _ => Err(FormatError::UnexpectedEof {
+                    expected: abs(rel).saturating_add(needed),
+                    available: file_len,
+                }),
+            }
+        };
+        let offset = 0usize;
         // signature(4) + version(1) + flags(1) = 6
         ensure_len(data, offset, 6)?;
 
@@ -351,15 +385,20 @@ impl ObjectHeader {
         }
 
         let chunk0_msg_start = pos;
-        let chunk0_msg_end = pos
+        let chunk0_msg_end = abs(pos)
             .checked_add(chunk0_size)
             .ok_or(FormatError::UnexpectedEof {
                 expected: usize::MAX,
-                available: data.len(),
-            })?;
+                available: file_len,
+            })?
+            - base;
+
+        // The whole first chunk, prefix to checksum, in one read (its
+        // bounds check is the one on the checksum's 4 bytes).
+        let chunk0 = read_exact_at(file, base as u64, chunk0_msg_end.saturating_add(4))?;
+        let data: &[u8] = &chunk0;
 
         // Validate checksum: from OHDR signature through all messages (before checksum)
-        ensure_len(data, chunk0_msg_end, 4)?;
         #[cfg(feature = "checksum")]
         {
             let stored = LittleEndian::read_u32(&data[chunk0_msg_end..chunk0_msg_end + 4]);
@@ -394,8 +433,8 @@ impl ObjectHeader {
             }
             cont_remaining -= 1;
             Self::parse_v2_continuation(
-                data,
-                cont_offset,
+                file,
+                cont_offset as u64,
                 cont_length,
                 has_creation_order,
                 offset_size,
@@ -495,8 +534,8 @@ impl ObjectHeader {
 
     #[allow(clippy::too_many_arguments)]
     fn parse_v2_continuation(
-        data: &[u8],
-        offset: usize,
+        file: &dyn Storage,
+        offset: u64,
         length: usize,
         has_creation_order: bool,
         offset_size: u8,
@@ -505,7 +544,9 @@ impl ObjectHeader {
         continuations: &mut Vec<(usize, usize)>,
     ) -> Result<(), FormatError> {
         // OCHK signature(4) + messages + checksum(4)
-        ensure_len(data, offset, length)?;
+        let chunk = read_exact_at(file, offset, length)?;
+        let data: &[u8] = &chunk;
+        let offset = 0usize;
         if length < 8 {
             return Err(FormatError::UnexpectedEof {
                 expected: 8,
@@ -546,6 +587,10 @@ impl ObjectHeader {
     }
 }
 
+/// Longest version-2 object header prefix: signature(4) + version(1) +
+/// flags(1) + times(16) + attribute phase change(4) + chunk-0 size(8).
+const V2_PREFIX_MAX: usize = 34;
+
 /// Size of a version-1 message header: type(2) + size(2) + flags(1) + reserved(3).
 const V1_MSG_HEADER_SIZE: usize = 8;
 
@@ -754,13 +799,13 @@ mod tests {
         let mut msg_bytes = Vec::new();
         for (mtype, mdata, mflags) in messages {
             // v1 message sizes are multiples of 8 (the data is zero-padded).
-            let padded = mdata.len().div_ceil(8) * 8;
+            let padded = <[u8]>::len(mdata).div_ceil(8) * 8;
             msg_bytes.extend_from_slice(&mtype.to_le_bytes()); // type(2)
             msg_bytes.extend_from_slice(&(padded as u16).to_le_bytes()); // size(2)
             msg_bytes.push(*mflags); // flags(1)
             msg_bytes.extend_from_slice(&[0u8; 3]); // reserved(3)
             msg_bytes.extend_from_slice(mdata); // data
-            msg_bytes.resize(msg_bytes.len() + padded - mdata.len(), 0);
+            msg_bytes.resize(msg_bytes.len() + padded - <[u8]>::len(mdata), 0);
         }
 
         let mut buf = Vec::new();
@@ -1280,4 +1325,52 @@ mod tests {
         let err = ObjectHeader::parse(&data, 0, 8, 8).unwrap_err();
         assert!(matches!(err, FormatError::UnexpectedEof { .. }));
     }
+
+    /// Every header, and every truncation of it, parses to the same result
+    /// (or the same error) through a `read_at`-only storage as from a slice;
+    /// a header in one chunk takes three reads (signature, prefix, chunk).
+    #[test]
+    fn parse_in_matches_slice_parse() {
+        use crate::storage::CountingStorage;
+        let mut headers = vec![
+            build_v1_header(&[], 8, 8),
+            build_v1_header(&[(0x0001, &[1, 2, 3], 0), (0x0003, &[9; 8], 0)], 8, 8),
+            build_v2_header(0x00, &[(0x01, &[42], 0)], None),
+            build_v2_header(0x03, &[(0x01, &[1, 2], 0), (0x03, &[3], 0)], None),
+            build_v2_header(0x24, &[(0x01, &[1], 0)], Some((1, 2, 3, 4))),
+            build_v2_header(0x35, &[(0x01, &[1], 0)], Some((5, 6, 7, 8))),
+        ];
+        // A v2 header with a continuation chunk at 256.
+        let mut ochk = OCHK_SIGNATURE.to_vec();
+        ochk.extend_from_slice(&[0x03, 2, 0, 0, 0xDE, 0xAD]);
+        let sum = crate::checksum::jenkins_lookup3(&ochk);
+        ochk.extend_from_slice(&sum.to_le_bytes());
+        let mut cont = 256u64.to_le_bytes().to_vec();
+        cont.extend_from_slice(&(ochk.len() as u64).to_le_bytes());
+        let main = build_v2_header(0x00, &[(0x01, &[42], 0), (0x10, &cont, 0)], None);
+        let mut with_cont = vec![0u8; 256 + ochk.len()];
+        with_cont[..main.len()].copy_from_slice(&main);
+        with_cont[256..].copy_from_slice(&ochk);
+        headers.push(with_cont);
+
+        for h in headers {
+            for at in [0usize, 3] {
+                for cut in 0..=h.len() {
+                    let mut f = vec![0u8; at];
+                    f.extend_from_slice(&h[..cut]);
+                    if at == 0 && cut == h.len() {
+                        f.resize(f.len() + 64, 0);
+                    }
+                    let want = ObjectHeader::parse(&f, at, 8, 8);
+                    let storage = CountingStorage::new(f.clone());
+                    let got = ObjectHeader::parse_in(&storage, at as u64, 8, 8);
+                    assert_eq!(format!("{got:?}"), format!("{want:?}"), "at {at}, cut {cut}");
+                }
+            }
+        }
+        let one_chunk = build_v2_header(0x00, &[(0x01, &[42], 0)], None);
+        let storage = CountingStorage::new(one_chunk);
+        ObjectHeader::parse_in(&storage, 0, 8, 8).unwrap();
+        assert_eq!(storage.reads(), 3);
+    }
 }