writer: v2 B-trees with internal nodes (no 65 535-record limit)

Dense link and attribute indexes and the chunk index for several
unlimited dimensions were single leaves, capping them at 65 535
records. btree_v2_write builds trees of any depth, with node capacities
and pointer widths from libhdf5's H5B2__hdr_init arithmetic (now shared
with the reader as btree_v2::node_info) and libhdf5's node sizes (512
dense, 2048 chunks). Indexes that fit the old one-leaf layout are
written byte for byte as before (compared for 10..65 535 links, attrs
and chunks, tracked and filtered).

Tests: 100 000 links (short names; long names with creation order),
70 000 attributes, 200 000 chunks (and 80 000 deflated), read by h5py,
h5dump and clawhdf5 and edited by h5py r+; h5rs check on the same
shapes, asserting depths 2-3.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/clawhdf5-format/src/btree_v2.rs

@@ -71,7 +71,7 @@ fn ensure_len(data: &[u8], pos: usize, needed: usize) -> Result<(), FormatError>
 
 /// Compute the number of bytes needed to represent a count, using variable-width encoding.
 /// B-tree v2 uses this for the number of records fields in internal nodes.
-fn bytes_for_max_records(max_nrec: u64) -> usize {
+pub(crate) fn bytes_for_max_records(max_nrec: u64) -> usize {
     if max_nrec == 0 {
         return 1;
     }
@@ -163,7 +163,7 @@ impl BTreeV2Header {
 /// Compute maximum records per node for a given depth level.
 /// leaf: (node_size - overhead) / record_size
 /// internal: depends on pointers
-fn max_records_leaf(node_size: u32, record_size: u16) -> u64 {
+pub(crate) fn max_records_leaf(node_size: u32, record_size: u16) -> u64 {
     // Leaf overhead: signature(4) + version(1) + type(1) + checksum(4) = 10
     let overhead = 10u32;
     if node_size <= overhead || record_size == 0 {
@@ -418,10 +418,7 @@ fn collect_internal_records(
 }
 
 /// Most records a subtree whose root is at `depth` can hold (libhdf5's
-/// `cum_max_nrec`): a leaf holds `max_leaf_nrec`; an internal node at depth
-/// `d` holds `max_nrec(d)` records and `max_nrec(d) + 1` subtrees of depth
-/// `d - 1`, where `max_nrec(d)` is what fits in a node once each record is
-/// paired with a child pointer of the width depth `d` needs.
+/// `cum_max_nrec`). See [`node_info`].
 fn cum_max_records(
     node_size: u32,
     record_size: u16,
@@ -429,24 +426,82 @@ fn cum_max_records(
     max_leaf_nrec: u64,
     depth: u16,
 ) -> u64 {
+    node_info_from_leaf(node_size, record_size, offset_size, max_leaf_nrec, depth)
+        .last()
+        .map_or(max_leaf_nrec, |n| n.cum_max_nrec)
+}
+
+/// Capacity of a B-tree v2 node at one depth, as libhdf5 computes it
+/// (`H5B2__hdr_init`'s `node_info`).
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) struct NodeInfo {
+    /// Most records one node at this depth holds.
+    pub(crate) max_nrec: u64,
+    /// Most records a subtree rooted at this depth holds.
+    pub(crate) cum_max_nrec: u64,
+    /// Bytes a subtree's total record count takes in a pointer to a node
+    /// at this depth (0 for a leaf, whose count is its own).
+    pub(crate) cum_max_nrec_size: usize,
+}
+
+/// Node capacities for depths `0..=depth` (entry `d` for depth `d`): a leaf
+/// holds `max_nrec(0)` records; an internal node at depth `d` holds
+/// `max_nrec(d)` records and `max_nrec(d) + 1` subtrees of depth `d - 1`,
+/// where `max_nrec(d)` is what fits in a node once each record is paired
+/// with a child pointer of the width depth `d` needs (address, the child's
+/// record count in the width a *leaf's* maximum needs, and below the first
+/// internal level the child subtree's total in the width its maximum
+/// needs), with one pointer more than records.
+pub(crate) fn node_info(
+    node_size: u32,
+    record_size: u16,
+    offset_size: u8,
+    depth: u16,
+) -> Vec<NodeInfo> {
+    let max_leaf = max_records_leaf(node_size, record_size);
+    node_info_from_leaf(node_size, record_size, offset_size, max_leaf, depth)
+}
+
+fn node_info_from_leaf(
+    node_size: u32,
+    record_size: u16,
+    offset_size: u8,
+    max_leaf_nrec: u64,
+    depth: u16,
+) -> Vec<NodeInfo> {
     // Internal node overhead: signature(4) + version(1) + type(1) + checksum(4).
     const PREFIX: u64 = 10;
     let nrec_width = bytes_for_max_records(max_leaf_nrec) as u64;
-    let mut cum = max_leaf_nrec;
-    let mut cum_width = 0u64;
+    let mut info = Vec::with_capacity(usize::from(depth) + 1);
+    info.push(NodeInfo {
+        max_nrec: max_leaf_nrec,
+        cum_max_nrec: max_leaf_nrec,
+        cum_max_nrec_size: 0,
+    });
     for d in 1..=depth {
-        let ptr = u64::from(offset_size) + nrec_width + if d > 1 { cum_width } else { 0 };
+        let below = info[usize::from(d) - 1];
+        let ptr = u64::from(offset_size)
+            + nrec_width
+            + if d > 1 {
+                below.cum_max_nrec_size as u64
+            } else {
+                0
+            };
         let max_nrec = u64::from(node_size)
             .saturating_sub(PREFIX)
             .saturating_sub(ptr)
             / (u64::from(record_size) + ptr).max(1);
-        cum = max_nrec
+        let cum = max_nrec
             .saturating_add(1)
-            .saturating_mul(cum)
+            .saturating_mul(below.cum_max_nrec)
             .saturating_add(max_nrec);
-        cum_width = bytes_for_max_records(cum) as u64;
+        info.push(NodeInfo {
+            max_nrec,
+            cum_max_nrec: cum,
+            cum_max_nrec_size: bytes_for_max_records(cum),
+        });
     }
-    cum
+    info
 }
 
 #[cfg(test)]