refactor(chunk-grids): remove VaryingDimension.cumulative

The per-chunk prefix sums were no longer used by any lookup and cost
time and memory in the number of chunks on every access.
`chunk_offset` gives the start of a chunk from the runs.

Assisted-by: ClaudeCode:claude-fable-5.1

Author: d-v-b

changes/4479.bugfix.md

@@ -1 +1 @@
-Opening an array with a rectilinear chunk grid, and indexing it, now costs time and memory proportional to the size of the grid's run-length encoded metadata rather than to its number of chunks: a stored grid such as `[[1, 1000000000000]]`, a few hundred bytes of JSON, previously took seconds per ten million chunks to open and could exhaust memory. The explicit edges in `RectilinearChunkGridMetadata.chunk_shapes` and `VaryingDimension.edges` are now held as `zarr.core.common.RunLengthEdges`, an immutable run-length encoded value that is not a sequence: it has no `len`, indexing or iteration and does not compare equal to a `tuple`. Its `expand()` method yields one entry per chunk. `VaryingDimension.cumulative` is now computed on access. The repr of a chunk grid shows a dimension of more than 100 chunks in its run-length encoded form.
+Opening an array with a rectilinear chunk grid, and indexing it, now costs time and memory proportional to the size of the grid's run-length encoded metadata rather than to its number of chunks: a stored grid such as `[[1, 1000000000000]]`, a few hundred bytes of JSON, previously took seconds per ten million chunks to open and could exhaust memory. The explicit edges in `RectilinearChunkGridMetadata.chunk_shapes` and `VaryingDimension.edges` are now held as `zarr.core.common.RunLengthEdges`, an immutable run-length encoded value that is not a sequence: it has no `len`, indexing or iteration and does not compare equal to a `tuple`. Its `expand()` method yields one entry per chunk. `VaryingDimension.cumulative` is removed; `VaryingDimension.chunk_offset` gives the start of a chunk. The repr of a chunk grid shows a dimension of more than 100 chunks in its run-length encoded form.

src/zarr/core/chunk_grids.py

@@ -178,15 +178,6 @@ def __init__(self, edges: Sequence[int] | RunLengthEdges, extent: int) -> None:
         object.__setattr__(self, "nchunks", n)
         object.__setattr__(self, "ngridcells", rle.num_edges)
 
-    @property
-    def cumulative(self) -> tuple[int, ...]:
-        """Prefix sums of the edges, one entry per chunk.
-
-        Lookups do not use this: it is computed on each access, in time and
-        memory proportional to the number of chunks.
-        """
-        return tuple(itertools.accumulate(self.edges.expand()))
-
     def index_to_chunk(self, idx: int) -> int:
         if idx < 0 or idx >= self.extent:
             raise IndexError(f"Index {idx} out of bounds for dimension with extent {self.extent}")

tests/test_unified_chunk_grid.py

@@ -248,10 +248,9 @@ def test_fixed_dimension_rejects_invalid(size: int, extent: int, match: str) ->
 
 
 def test_varying_dimension_construction() -> None:
-    """VaryingDimension stores edges, cumulative sums, nchunks, and extent correctly"""
+    """VaryingDimension stores edges, nchunks, and extent correctly"""
     d = VaryingDimension([10, 20, 30], extent=60)
     assert tuple(d.edges.expand()) == (10, 20, 30)
-    assert d.cumulative == (10, 30, 60)
     assert d.nchunks == 3
     assert d.extent == 60