rustytree-xarray 0.4.0__tar.gz → 0.5.0__tar.gz

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/.github/workflows/ci.yml

@@ -39,7 +39,7 @@ jobs:
       - uses: dtolnay/rust-toolchain@stable
         with:
           components: clippy, rustfmt
-      - uses: actions/setup-python@v6
+      - uses: actions/setup-python@v7
         with:
           python-version: "3.12"
       - uses: Swatinem/rust-cache@v2
@@ -73,7 +73,7 @@ jobs:
         with:
           # Keyed by Python version so each matrix cell gets its own cache.
           key: py-${{ matrix.python-version }}
-      - uses: actions/setup-python@v6
+      - uses: actions/setup-python@v7
         with:
           python-version: ${{ matrix.python-version }}
       - uses: astral-sh/setup-uv@v7

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/.github/workflows/release.yml

@@ -48,7 +48,7 @@ jobs:
     runs-on: ${{ matrix.platform.os }}
     steps:
       - uses: actions/checkout@v7
-      - uses: actions/setup-python@v6
+      - uses: actions/setup-python@v7
         with:
           python-version: ${{ matrix.python-version }}
       - uses: dtolnay/rust-toolchain@stable

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/CHANGELOG.md

@@ -11,6 +11,35 @@ release, that section is renamed to `[x.y.z] - YYYY-MM-DD` and a fresh
 
 ## [Unreleased]
 
+## [0.5.0] - 2026-07-26
+
+### Added
+
+- Eager-fetch small `object`-dtype (vlen `string`) scalars and self-named
+  1-D coords during the walk's Phase C ([#77]). `xr.open_datatree(engine=
+  "rustytree")` was paying one serial lazy read per `object`-dtype variable
+  at open time — xarray's `_contains_datetime_like_objects` samples every
+  such variable to rule out `cftime.datetime`, independent of the existing
+  CF-time-like/dim-coord triggers Phase C already covers. Extends the walk's
+  parallel pre-fetch to cover this case (bounded by a 4096-element count cap
+  and an 8 MiB total-byte-size cap, since per-element size is unbounded for
+  strings unlike the existing fixed-width numeric cap), and adds the
+  matching `object` → declared-read-dtype cast on the eager path in
+  `backend.py` (mirroring the lazy path's existing cast from #71). Scoped to
+  scalars and self-named 1-D coords only, so an ordinary small string data
+  variable doesn't lose its dask laziness just because it's small. Verified
+  on the live `s3://nexrad-arco/KLOT` store: ~48% faster `open_datatree`
+  (8.223s → 4.241s mean over 4 trials), 42 serial lazy reads eliminated.
+
+### Changed
+
+- Routine dependency and CI-action bumps via Dependabot ([#72], [#74],
+  [#75], [#76]). Cargo: `quinn-proto` 0.11.14 → 0.11.16 ([#72]); cargo-minor
+  group — `tokio` 1.53.0 → 1.53.1, `thiserror` 2.0.18 → 2.0.19, `async-trait`
+  0.1.89 → 0.1.91, `serde` 1.0.228 → 1.0.229, `zarrs_storage` 0.4.4 → 0.4.5,
+  `serde_json` 1.0.150 → 1.0.151 ([#75]); `zarrs_object_store` 0.6.2 → 0.7.0
+  ([#76]). CI: `actions/setup-python` 6 → 7 ([#74]).
+
 ## [0.4.0] - 2026-07-24
 
 ### Added
@@ -835,7 +864,8 @@ below.
   intentionally not normalized — relative-vs-absolute glob
   semantics differ in `PurePosixPath.match`.
 
-[Unreleased]: https://github.com/aladinor/rustytree/compare/v0.4.0...HEAD
+[Unreleased]: https://github.com/aladinor/rustytree/compare/v0.5.0...HEAD
+[0.5.0]: https://github.com/aladinor/rustytree/compare/v0.4.0...v0.5.0
 [0.4.0]: https://github.com/aladinor/rustytree/compare/v0.3.0...v0.4.0
 [0.3.0]: https://github.com/aladinor/rustytree/compare/v0.2.1...v0.3.0
 [0.2.1]: https://github.com/aladinor/rustytree/compare/v0.2.0...v0.2.1
@@ -884,3 +914,8 @@ below.
 [#64]: https://github.com/aladinor/rustytree/pull/64
 [#68]: https://github.com/aladinor/rustytree/pull/68
 [#71]: https://github.com/aladinor/rustytree/pull/71
+[#72]: https://github.com/aladinor/rustytree/pull/72
+[#74]: https://github.com/aladinor/rustytree/pull/74
+[#75]: https://github.com/aladinor/rustytree/pull/75
+[#76]: https://github.com/aladinor/rustytree/pull/76
+[#77]: https://github.com/aladinor/rustytree/pull/77

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/Cargo.lock

@@ -120,13 +120,13 @@ dependencies = [
 
 [[package]]
 name = "async-trait"
-version = "0.1.89"
+version = "0.1.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9035ad2d096bed7955a320ee7e2230574d28fd3c3a0f186cbea1ff3c7eed5dbb"
+checksum = "ae36dc4177970ef04fde5178d3e2429882def40e57a451f919c098f72baa6cec"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 3.0.2",
 ]
 
 [[package]]
@@ -1529,11 +1529,13 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0de51e6874e94e7bf76d726fc5d13ba782deca734ff60d5bb2fb2607c7406555"
 dependencies = [
  "cfg-if",
+ "js-sys",
  "libc",
  "r-efi 6.0.0",
  "rand_core 0.10.1",
  "wasip2",
  "wasip3",
+ "wasm-bindgen",
 ]
 
 [[package]]
@@ -1900,7 +1902,7 @@ dependencies = [
  "icechunk-types",
  "itertools 0.15.0",
  "quick_cache",
- "rand 0.10.1",
+ "rand",
  "regex",
  "reqwest 0.13.3",
  "rmp-serde",
@@ -1932,8 +1934,8 @@ dependencies = [
  "http 1.4.0",
  "icechunk-storage",
  "icechunk-types",
- "object_store",
- "rand 0.10.1",
+ "object_store 0.13.2",
+ "rand",
  "serde",
  "tokio",
  "tokio-util",
@@ -1957,7 +1959,7 @@ dependencies = [
  "icechunk-types",
  "itertools 0.15.0",
  "quick_cache",
- "rand 0.10.1",
+ "rand",
  "rmp-serde",
  "serde",
  "serde_bytes",
@@ -2486,9 +2488,9 @@ dependencies = [
 
 [[package]]
 name = "ndarray"
-version = "0.16.1"
+version = "0.17.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "882ed72dce9365842bf196bdeedf5055305f11fc8c03dee7bb0194a6cad34841"
+checksum = "520080814a7a6b4a6e9070823bb24b4531daac8c4627e08ba5de8c5ef2f2752d"
 dependencies = [
  "matrixmultiply",
  "num-complex",
@@ -2500,18 +2502,15 @@ dependencies = [
 ]
 
 [[package]]
-name = "ndarray"
-version = "0.17.2"
+name = "nix"
+version = "0.31.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "520080814a7a6b4a6e9070823bb24b4531daac8c4627e08ba5de8c5ef2f2752d"
+checksum = "cf20d2fde8ff38632c426f1165ed7436270b44f199fc55284c38276f9db47c3d"
 dependencies = [
- "matrixmultiply",
- "num-complex",
- "num-integer",
- "num-traits",
- "portable-atomic",
- "portable-atomic-util",
- "rawpointer",
+ "bitflags 2.11.1",
+ "cfg-if",
+ "cfg_aliases",
+ "libc",
 ]
 
 [[package]]
@@ -2622,7 +2621,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6a5b15d63a5ff39e378daed0e1340d3a5964703ea9712eb09a0dc66fade996f4"
 dependencies = [
  "libc",
- "ndarray 0.16.1",
+ "ndarray",
  "num-complex",
  "num-integer",
  "num-traits",
@@ -2654,8 +2653,8 @@ dependencies = [
  "md-5 0.10.6",
  "parking_lot",
  "percent-encoding",
- "quick-xml",
- "rand 0.10.1",
+ "quick-xml 0.39.3",
+ "rand",
  "reqwest 0.12.28",
  "ring",
  "rustls-pki-types",
@@ -2671,6 +2670,48 @@ dependencies = [
  "web-time",
 ]
 
+[[package]]
+name = "object_store"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d354792e39fa5f0009e47623cf8b15b099bf9a652fa55c6f817fe28ac84fea50"
+dependencies = [
+ "async-trait",
+ "aws-lc-rs",
+ "base64",
+ "bytes",
+ "chrono",
+ "crc-fast",
+ "form_urlencoded",
+ "futures-channel",
+ "futures-core",
+ "futures-util",
+ "http 1.4.0",
+ "http-body-util",
+ "humantime",
+ "hyper 1.9.0",
+ "itertools 0.15.0",
+ "md-5 0.11.0",
+ "nix",
+ "parking_lot",
+ "percent-encoding",
+ "quick-xml 0.41.0",
+ "rand",
+ "reqwest 0.13.3",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "serde_urlencoded",
+ "thiserror",
+ "tokio",
+ "tracing",
+ "url",
+ "walkdir",
+ "wasm-bindgen-futures",
+ "web-time",
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "once_cell"
 version = "1.21.4"
@@ -2826,15 +2867,6 @@ version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
 
-[[package]]
-name = "ppv-lite86"
-version = "0.2.21"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
-dependencies = [
- "zerocopy",
-]
-
 [[package]]
 name = "prettyplease"
 version = "0.2.37"
@@ -2932,6 +2964,16 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "quick-xml"
+version = "0.41.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e660451e55124f798a69a5af3f49ccfbefbd41910eefd25caf2393e1f3473ec1"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
 [[package]]
 name = "quick_cache"
 version = "0.6.24"
@@ -2966,15 +3008,16 @@ dependencies = [
 
 [[package]]
 name = "quinn-proto"
-version = "0.11.14"
+version = "0.11.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "434b42fec591c96ef50e21e886936e66d3cc3f737104fdb9b737c40ffb94c098"
+checksum = "2f4bfc015262b9df63c8845072ce59068853ff5872180c2ce2f13038b970e560"
 dependencies = [
  "aws-lc-rs",
  "bytes",
- "getrandom 0.3.4",
+ "getrandom 0.4.2",
  "lru-slab",
- "rand 0.9.4",
+ "rand",
+ "rand_pcg",
  "ring",
  "rustc-hash",
  "rustls 0.23.40",
@@ -3021,16 +3064,6 @@ version = "6.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
 
-[[package]]
-name = "rand"
-version = "0.9.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44c5af06bb1b7d3216d91932aed5265164bf384dc89cd6ba05cf59a35f5f76ea"
-dependencies = [
- "rand_chacha",
- "rand_core 0.9.5",
-]
-
 [[package]]
 name = "rand"
 version = "0.10.1"
@@ -3042,16 +3075,6 @@ dependencies = [
  "rand_core 0.10.1",
 ]
 
-[[package]]
-name = "rand_chacha"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
-dependencies = [
- "ppv-lite86",
- "rand_core 0.9.5",
-]
-
 [[package]]
 name = "rand_core"
 version = "0.6.4"
@@ -3063,18 +3086,18 @@ dependencies = [
 
 [[package]]
 name = "rand_core"
-version = "0.9.5"
+version = "0.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "76afc826de14238e6e8c374ddcc1fa19e374fd8dd986b0d2af0d02377261d83c"
-dependencies = [
- "getrandom 0.3.4",
-]
+checksum = "63b8176103e19a2643978565ca18b50549f6101881c443590420e4dc998a3c69"
 
 [[package]]
-name = "rand_core"
-version = "0.10.1"
+name = "rand_pcg"
+version = "0.10.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "63b8176103e19a2643978565ca18b50549f6101881c443590420e4dc998a3c69"
+checksum = "caa0f4137e1c0a72f4c651489402276c8e8e1cf081f3b0ba156d2cbeef09e86a"
+dependencies = [
+ "rand_core 0.10.1",
+]
 
 [[package]]
 name = "rawpointer"
@@ -3213,7 +3236,7 @@ dependencies = [
  "url",
  "wasm-bindgen",
  "wasm-bindgen-futures",
- "wasm-streams",
+ "wasm-streams 0.4.2",
  "web-sys",
 ]
 
@@ -3227,6 +3250,7 @@ dependencies = [
  "bytes",
  "encoding_rs",
  "futures-core",
+ "futures-util",
  "h2 0.4.14",
  "http 1.4.0",
  "http-body 1.0.1",
@@ -3246,12 +3270,14 @@ dependencies = [
  "sync_wrapper",
  "tokio",
  "tokio-rustls 0.26.4",
+ "tokio-util",
  "tower",
  "tower-http",
  "tower-service",
  "url",
  "wasm-bindgen",
  "wasm-bindgen-futures",
+ "wasm-streams 0.5.0",
  "web-sys",
 ]
 
@@ -3420,7 +3446,7 @@ checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
 
 [[package]]
 name = "rustytree"
-version = "0.4.0"
+version = "0.5.0"
 dependencies = [
  "async-trait",
  "chrono",
@@ -3549,9 +3575,9 @@ checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
 
 [[package]]
 name = "serde"
-version = "1.0.228"
+version = "1.0.229"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
+checksum = "4148590afebada386688f18773da617792bf2ef03ffc1e4cbd2b1d45b023e0ba"
 dependencies = [
  "serde_core",
  "serde_derive",
@@ -3569,29 +3595,29 @@ dependencies = [
 
 [[package]]
 name = "serde_core"
-version = "1.0.228"
+version = "1.0.229"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
+checksum = "67dca2c9c51e58a4791a4b1ed58308b39c64224d349a935ab5039aa360942a48"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.228"
+version = "1.0.229"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
+checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 3.0.2",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.150"
+version = "1.0.151"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e8014e44b4736ed0538adeecded0fce2a272f22dc9578a7eb6b2d9993c74cfb9"
+checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14"
 dependencies = [
  "indexmap 2.14.0",
  "itoa",
@@ -3940,22 +3966,22 @@ checksum = "adb6935a6f5c20170eeceb1a3835a49e12e19d792f6dd344ccc76a985ca5a6ca"
 
 [[package]]
 name = "thiserror"
-version = "2.0.18"
+version = "2.0.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
+checksum = "09a43598840e33d5b0331f38c5e30d13bb11c11210a4b58f0d9b18a5a5eefcd9"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "2.0.18"
+version = "2.0.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
+checksum = "43cbfe0cf76104d42a574802844187e84a305e531ed54455f11fbde0f10541cd"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.117",
+ "syn 3.0.2",
 ]
 
 [[package]]
@@ -4025,9 +4051,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
 
 [[package]]
 name = "tokio"
-version = "1.53.0"
+version = "1.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d988bcd52dbe076d3d46903332f58c912b87a2c49b1428419a5845154762ffee"
+checksum = "202caea871b69668250d242070849eb495be178ed697a3e98aebce5bc81a0bed"
 dependencies = [
  "bytes",
  "libc",
@@ -4474,6 +4500,19 @@ dependencies = [
  "web-sys",
 ]
 
+[[package]]
+name = "wasm-streams"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9d1ec4f6517c9e11ae630e200b2b65d193279042e28edd4a2cda233e46670bbb"
+dependencies = [
+ "futures-util",
+ "js-sys",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
 [[package]]
 name = "wasmparser"
 version = "0.244.0"
@@ -4937,7 +4976,7 @@ dependencies = [
  "log",
  "lru",
  "moka",
- "ndarray 0.17.2",
+ "ndarray",
  "num",
  "num-complex",
  "paste",
@@ -5094,13 +5133,13 @@ dependencies = [
 
 [[package]]
 name = "zarrs_object_store"
-version = "0.6.2"
+version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ba1662bcdc585be1923a8b98ee5d6314d19af8c5775d6516a69ca33fd88b46af"
+checksum = "f39632e2ce9e862f81e45ae3526ae70cb2ceb4ae0e24e9580d85441e75f16a43"
 dependencies = [
  "async-trait",
  "futures",
- "object_store",
+ "object_store 0.14.1",
  "zarrs_storage",
 ]
 
@@ -5118,9 +5157,9 @@ dependencies = [
 
 [[package]]
 name = "zarrs_storage"
-version = "0.4.4"
+version = "0.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf372205f5ab996c7e48ead8c68188c0bc3aaf205f3aa3afe8d7eb8db178a592"
+checksum = "e13f043c9bd3de69637574f7a2c4b3450f8e310d650fe5c2a78a08d13095cbf9"
 dependencies = [
  "async-trait",
  "auto_impl",

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "rustytree"
-version = "0.4.0"
+version = "0.5.0"
 edition = "2024"
 rust-version = "1.91.1"
 license = "Apache-2.0"
@@ -61,7 +61,7 @@ serde = { version = "1", features = ["derive"] }
 # crc32c) come from zarrs's default features, which we keep enabled.
 zarrs = { version = "0.23", features = ["async", "zlib"] }
 zarrs_storage = { version = "0.4", features = ["async"] }
-zarrs_object_store = { version = "0.6", features = ["fs", "aws"] }
+zarrs_object_store = { version = "0.7", features = ["fs", "aws"] }
 serde_json = "1"
 
 # icechunk = transactional Zarr v3 storage layer. `zarrs_icechunk` wraps an

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rustytree-xarray
-Version: 0.4.0
+Version: 0.5.0
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: Apache Software License

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/pyproject.toml

@@ -10,7 +10,7 @@ build-backend = "maturin"
 # `-`/`_`/case so they collapse). Users `pip install rustytree-xarray`,
 # then `import rustytree`.
 name = "rustytree-xarray"
-version = "0.4.0"
+version = "0.5.0"
 description = "Rust-backed xarray DataTree backend for fast Zarr access from object storage"
 readme = "README.md"
 requires-python = ">=3.12"

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/python/rustytree/__init__.py

@@ -8,4 +8,4 @@ plugin discovery) doesn't pay the cdylib load cost upfront.
 from rustytree.backend import RustytreeBackendEntrypoint
 
 __all__ = ["RustytreeBackendEntrypoint"]
-__version__ = "0.4.0"
+__version__ = "0.5.0"

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/python/rustytree/_array.py

@@ -17,6 +17,17 @@ from xarray.backends.common import BackendArray
 from xarray.core import indexing
 
 
+def cast_to_read_dtype(arr: np.ndarray, read_dtype: np.dtype) -> np.ndarray:
+    """Cast `arr` to the dtype its read actually materialises, if it doesn't
+    already match. A no-op (`astype(..., copy=False)` skips the copy when the
+    dtype already matches) for every dtype except vlen `string` (declared
+    `object`, read as `StringDType`) — see `RustyBackendArray.__init__`.
+    Shared by the lazy read path below and the eager path in `backend.py`,
+    which both need the same declared-dtype/read-dtype reconciliation.
+    """
+    return arr.astype(read_dtype, copy=False)
+
+
 class RustyBackendArray(BackendArray):
     """Lazy view over a Rust-side `ZarrsArrayHandle`.
 
@@ -92,8 +103,6 @@ class RustyBackendArray(BackendArray):
         # String-like dtypes come back from Rust as an `object` array of Python
         # `str` (the `numpy` crate can only build `object` arrays); cast to the
         # dtype the read materialises — `StringDType` for `string`, `<U…` for
-        # `fixed_length_utf32`. Numeric reads already match `_read_dtype`, so the
-        # guard skips the (copying) `astype` for them.
-        if out.dtype != self._read_dtype:
-            out = out.astype(self._read_dtype)
-        return out
+        # `fixed_length_utf32`. Numeric reads already match `_read_dtype`, so
+        # this is a no-op copy-wise for them.
+        return cast_to_read_dtype(out, self._read_dtype)

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/python/rustytree/backend.py

@@ -43,7 +43,7 @@ from xarray.core.dataset import Dataset
 from xarray.core.datatree import DataTree
 from xarray.core.variable import Variable
 
-from rustytree._array import RustyBackendArray
+from rustytree._array import RustyBackendArray, cast_to_read_dtype
 
 ROOT = "/"
 
@@ -360,12 +360,15 @@ class _RustyDataStore(AbstractDataStore):
             # Phase C may have pre-fetched the variable's full contents
             # (1-D self-named dim coords + CF time-likes); other vars
             # stay lazy through `RustyBackendArray`.
-            data: Any = (
-                var["data"]
-                if "data" in var
-                else indexing.LazilyIndexedArray(RustyBackendArray(var["handle"]))
-            )
             handle = var["handle"]
+            if "data" in var:
+                # Eager path (Phase C): eager vars bypass `RustyBackendArray`
+                # entirely, so the declared-dtype/read-dtype reconciliation
+                # (`object`-declared/`StringDType`-materialized vlen strings,
+                # added for #71) has to be applied here explicitly instead.
+                data: Any = cast_to_read_dtype(var["data"], np.dtype(handle.read_dtype))
+            else:
+                data = indexing.LazilyIndexedArray(RustyBackendArray(handle))
             chunks = tuple(handle.chunks)
             attrs = dict(var["attrs"])
             # Mirror xarray's zarr backend: decode a base64 str/bytes `_FillValue`

{rustytree_xarray-0.4.0 → rustytree_xarray-0.5.0}/src/array.rs

@@ -449,13 +449,25 @@ fn strings_to_object_pyarray<'py>(
     request_shape: &[u64],
 ) -> PyResult<Bound<'py, PyAny>> {
     let sliced = slice_nd(strings, aligned_shape, offsets, request_shape);
+    strings_to_pyobject_array(py, &sliced)
+}
+
+/// Build a flat 1-D numpy `object` array of `PyString`s from a string slice.
+/// Shared tail of [`strings_to_object_pyarray`] (the lazy, possibly-sliced
+/// read path) and Phase C's eager-fetch path (`lib.rs::eager_to_pyarray`,
+/// which reads the whole array and reshapes separately, so needs no slicing
+/// here).
+pub(crate) fn strings_to_pyobject_array<'py>(
+    py: Python<'py>,
+    strings: &[String],
+) -> PyResult<Bound<'py, PyAny>> {
     // `from_slice` (not `from_vec`): for object dtype it clones each ref into a
     // numpy-owned buffer, so numpy and the local `objs` Vec own their
     // references independently — no double-decref hazard if the array is later
     // mutated. One incref/element, negligible at coord/scalar sizes.
-    let objs: Vec<Py<PyAny>> = sliced
-        .into_iter()
-        .map(|s| PyString::new(py, &s).into_any().unbind())
+    let objs: Vec<Py<PyAny>> = strings
+        .iter()
+        .map(|s| PyString::new(py, s).into_any().unbind())
         .collect();
     PyArray1::from_slice(py, &objs).into_bound_py_any(py)
 }