crates/clawhdf5-format/src/filters.rs

@@ -28,7 +28,20 @@ pub fn decompress_chunk(
 ) -> Result<Vec<u8>, FormatError> {
     let mut data = compressed.to_vec();
 
-    for filter in pipeline.filters.iter().rev() {
+    for (i, filter) in pipeline.filters.iter().enumerate().rev() {
+        // Fletcher32 appends a 4-byte checksum on write, so a filter that
+        // follows it in the (forward) pipeline decodes to the chunk plus one
+        // checksum per earlier Fletcher32 — e.g. libhdf5's
+        // shuffle + fletcher32 + deflate (h5repack_filters.h5 `/dset_all`).
+        let chunk_size = if chunk_size == 0 {
+            0
+        } else {
+            let checksums = pipeline.filters[..i]
+                .iter()
+                .filter(|f| f.filter_id == FILTER_FLETCHER32)
+                .count();
+            chunk_size.saturating_add(4 * checksums)
+        };
         data = match filter.filter_id {
             FILTER_SHUFFLE => shuffle_decompress(&data, element_size as usize)?,
             // `chunk_size` is the expected decompressed size (shuffle/fletcher32
@@ -1642,6 +1655,40 @@ mod tests {
         }
     }
 
+    /// Fletcher32 before a compressor (libhdf5 applies filters in pipeline
+    /// order, so the compressor sees chunk + checksum): deflate's output is 4
+    /// bytes over the chunk size, which we rejected as "deflate: output
+    /// exceeds size limit". Chunks from h5py/libhdf5, values from h5py.
+    #[test]
+    #[cfg(feature = "deflate")]
+    fn fletcher32_before_deflate_decodes() {
+        // h5py: set_fletcher32(); set_deflate(4); i32 0..100, chunks of 10.
+        let pipeline = FilterPipeline {
+            version: 2,
+            filters: vec![
+                one_filter(FILTER_FLETCHER32, vec![]),
+                one_filter(FILTER_DEFLATE, vec![4]),
+            ],
+        };
+        let raw =
+            unhex("785e936360609007620520560462252056066215205605623520560762c6483e3d00234501f0");
+        let want: Vec<u8> = (30..40i32).flat_map(i32::to_le_bytes).collect();
+        assert_eq!(decompress_chunk(&raw, &pipeline, 40, 4).unwrap(), want);
+
+        // And our own writer's round trip through the same pipeline order.
+        let data: Vec<u8> = (0..400u32).map(|i| (i % 13) as u8).collect();
+        let pipeline = FilterPipeline {
+            version: 2,
+            filters: vec![
+                one_filter(FILTER_SHUFFLE, vec![4]),
+                one_filter(FILTER_FLETCHER32, vec![]),
+                one_filter(FILTER_DEFLATE, vec![9]),
+            ],
+        };
+        let c = compress_chunk(&data, &pipeline, 4).unwrap();
+        assert_eq!(decompress_chunk(&c, &pipeline, 400, 4).unwrap(), data);
+    }
+
     /// `le_data.h5` scale-offset (D-scale, D = 3, fill -2.2) chunks, decoded
     /// bit for bit as libhdf5 does: single-precision arithmetic for `float`
     /// (we computed in f64 and rounded once, which was 1 ULP off for e.g.