Compare commits

..

1 Commits

Author SHA1 Message Date
Yang Cen 81e7e71dde fix(storage): recover mirrored manifest creates 2026-08-11 02:18:01 +08:00
19 changed files with 360 additions and 2323 deletions
-10
View File
@@ -69,16 +69,6 @@ jobs:
uses: actions/setup-python@v6
with:
python-version: "3.10"
- name: Add swap for Arm fat LTO
if: matrix.config.platform == 'aarch64'
shell: bash
run: |
swap_file="$RUNNER_TEMP/lancedb-swap"
sudo fallocate --length 16G "$swap_file"
sudo chmod 600 "$swap_file"
sudo mkswap "$swap_file"
sudo swapon "$swap_file"
free -h
- uses: ./.github/workflows/build_linux_wheel
with:
python-minor-version: 10
Generated
+55 -43
View File
@@ -3455,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
[[package]]
name = "fsst"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"rand 0.9.5",
@@ -4815,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
[[package]]
name = "lance"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arc-swap",
"arrow",
@@ -4832,6 +4832,7 @@ dependencies = [
"async-recursion",
"async-trait",
"async_cell",
"aws-credential-types",
"aws-sdk-dynamodb",
"byteorder",
"bytes",
@@ -4847,6 +4848,7 @@ dependencies = [
"either",
"fst",
"futures",
"half",
"humantime",
"itertools 0.14.0",
"lance-arrow",
@@ -4888,8 +4890,8 @@ dependencies = [
[[package]]
name = "lance-arrow"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4911,7 +4913,7 @@ dependencies = [
[[package]]
name = "lance-arrow-scalar"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4925,7 +4927,7 @@ dependencies = [
[[package]]
name = "lance-arrow-stats"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -4934,8 +4936,8 @@ dependencies = [
[[package]]
name = "lance-bitpacking"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrayref",
"crunchy",
@@ -4945,8 +4947,8 @@ dependencies = [
[[package]]
name = "lance-core"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4954,10 +4956,12 @@ dependencies = [
"arrow-schema",
"async-trait",
"blake3",
"byteorder",
"bytes",
"datafusion-common",
"datafusion-sql",
"futures",
"itertools 0.14.0",
"lance-arrow",
"lance-derive",
"libc",
@@ -4975,6 +4979,7 @@ dependencies = [
"snafu 0.9.0",
"tempfile",
"tokio",
"tokio-stream",
"tokio-util",
"tracing",
"twox-hash",
@@ -4983,8 +4988,8 @@ dependencies = [
[[package]]
name = "lance-datafusion"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow",
"arrow-array",
@@ -5014,8 +5019,8 @@ dependencies = [
[[package]]
name = "lance-datagen"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow",
"arrow-array",
@@ -5032,8 +5037,8 @@ dependencies = [
[[package]]
name = "lance-derive"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"proc-macro2",
"quote",
@@ -5042,8 +5047,8 @@ dependencies = [
[[package]]
name = "lance-encoding"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5068,6 +5073,7 @@ dependencies = [
"num-traits",
"prost",
"prost-build",
"rand 0.9.5",
"tokio",
"tracing",
"xxhash-rust",
@@ -5076,8 +5082,8 @@ dependencies = [
[[package]]
name = "lance-file"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5108,8 +5114,8 @@ dependencies = [
[[package]]
name = "lance-index"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arc-swap",
"arrow",
@@ -5124,6 +5130,7 @@ dependencies = [
"async-trait",
"bitvec",
"bytes",
"chrono",
"crossbeam-queue",
"datafusion",
"datafusion-common",
@@ -5141,6 +5148,7 @@ dependencies = [
"lance-bitpacking",
"lance-core",
"lance-datafusion",
"lance-datagen",
"lance-encoding",
"lance-file",
"lance-index-core",
@@ -5169,12 +5177,13 @@ dependencies = [
"tempfile",
"tokio",
"tracing",
"uuid",
]
[[package]]
name = "lance-index-core"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5196,8 +5205,8 @@ dependencies = [
[[package]]
name = "lance-io"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow",
"arrow-array",
@@ -5211,6 +5220,7 @@ dependencies = [
"futures",
"http 1.5.0",
"io-uring",
"lance-arrow",
"lance-core",
"lance-namespace",
"log",
@@ -5228,28 +5238,29 @@ dependencies = [
"tokio",
"tracing",
"url",
"uuid",
]
[[package]]
name = "lance-linalg"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-buffer",
"arrow-schema",
"cc",
"half",
"lance-arrow",
"lance-core",
"num-traits",
"rand 0.9.5",
"rayon",
]
[[package]]
name = "lance-namespace"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow",
"async-trait",
@@ -5261,8 +5272,8 @@ dependencies = [
[[package]]
name = "lance-namespace-impls"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow",
"arrow-ipc",
@@ -5315,13 +5326,14 @@ dependencies = [
[[package]]
name = "lance-select"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-buffer",
"arrow-schema",
"byteorder",
"bytes",
"itertools 0.14.0",
"lance-core",
"roaring",
@@ -5330,8 +5342,8 @@ dependencies = [
[[package]]
name = "lance-table"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow",
"arrow-array",
@@ -5371,8 +5383,8 @@ dependencies = [
[[package]]
name = "lance-testing"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5385,8 +5397,8 @@ dependencies = [
[[package]]
name = "lance-tokenizer"
version = "11.0.0-beta.8"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.8#9acbac748e8a7d616146dac8b06da42d8e7c6b62"
version = "11.0.0-beta.3"
source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
dependencies = [
"frostem",
"icu_segmenter",
+14 -14
View File
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=11.0.0-beta.8", default-features = false, "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=11.0.0-beta.8", default-features = false, "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=11.0.0-beta.8", default-features = false, "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=11.0.0-beta.8", "tag" = "v11.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
lance = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
ahash = "0.8"
# Note that this one does not include pyarrow
arrow = { version = "58.0.0", optional = false }
-7
View File
@@ -101,13 +101,6 @@ ignore = [
# https://rustsec.org/advisories/RUSTSEC-2026-0195
{ id = "RUSTSEC-2026-0194", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
{ id = "RUSTSEC-2026-0195", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" },
# smartstring: unmaintained — the repository was archived by its author on
# 2026-05-03. Not a vulnerability. Reached only transitively through polars
# (polars-core/-io/-ops/-time/-utils); nothing in LanceDB depends on it directly.
# The advisory states no safe upgrade is available: upstream recommends
# compact_str/smol_str, so clearing this requires polars to migrate.
# https://rustsec.org/advisories/RUSTSEC-2026-0249
{ id = "RUSTSEC-2026-0249", reason = "smartstring unmaintained via polars; no fixed upstream release" },
]
# ---------------------------------------------------------------------------
+1 -1
View File
@@ -28,7 +28,7 @@
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<arrow.version>15.0.0</arrow.version>
<lance-core.version>11.0.0-beta.8</lance-core.version>
<lance-core.version>11.0.0-beta.3</lance-core.version>
<spotless.skip>false</spotless.skip>
<spotless.version>2.30.0</spotless.version>
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
+13 -2
View File
@@ -716,9 +716,20 @@ class LanceDBConnection(DBConnection):
if not isinstance(uri, Path):
scheme = get_uri_scheme(uri)
is_local = isinstance(uri, Path) or scheme == "file"
is_file_uri = isinstance(uri, str) and uri.lower().startswith("file:")
if is_local and not is_file_uri:
if is_local:
if isinstance(uri, str):
# Strip file:// or file:/ scheme if present
# file:///path becomes file:/path after URL normalization
if uri.startswith("file://"):
uri = uri[7:] # Remove "file://"
elif uri.startswith("file:/"):
uri = uri[5:] # Remove "file:"
if sys.platform == "win32":
# On Windows, a path like /C:/path should become C:/path
if len(uri) >= 3 and uri[0] == "/" and uri[2] == ":":
uri = uri[1:]
uri = Path(uri)
uri = uri.expanduser().absolute()
Path(uri).mkdir(parents=True, exist_ok=True)
+22 -2
View File
@@ -919,7 +919,17 @@ class LanceNamespaceDBConnection(DBConnection):
The namespace client for this connection.
"""
if self._namespace_client is None:
self._namespace_client = LOOP.run(self._inner.namespace_client())
if (
self._namespace_client_impl is None
or self._namespace_client_properties is None
):
raise ValueError(
"Cannot construct a Python namespace client without "
"namespace implementation properties"
)
self._namespace_client = namespace_connect(
self._namespace_client_impl, self._namespace_client_properties
)
return self._namespace_client
@@ -1360,7 +1370,17 @@ class AsyncLanceNamespaceDBConnection:
The namespace client for this connection.
"""
if self._namespace_client is None:
self._namespace_client = await self._inner.namespace_client()
if (
self._namespace_client_impl is None
or self._namespace_client_properties is None
):
raise ValueError(
"Cannot construct a Python namespace client without "
"namespace implementation properties"
)
self._namespace_client = namespace_connect(
self._namespace_client_impl, self._namespace_client_properties
)
return self._namespace_client
-89
View File
@@ -89,32 +89,6 @@ def test_sync_debugger_inspection_does_not_use_background_loop(tmp_path, monkeyp
assert repr(table) == f"LanceTable(name='test', _conn={db!r})"
def test_connect_preserves_file_uri_authority(monkeypatch):
uri = "file://server/share/database"
received = []
async def fake_connect(passed_uri, *_args):
received.append(passed_uri)
return SimpleNamespace(uri=passed_uri)
monkeypatch.setattr("lancedb.db.lancedb_connect", fake_connect)
db = lancedb.connect(uri)
assert received == [uri]
assert db.uri == uri
def test_connect_file_uri_lifecycle(tmp_path):
uri = (tmp_path / "sync").as_uri()
db = lancedb.connect(uri)
db.create_table("test", data=[{"id": 1}])
assert db.table_names() == ["test"]
assert db.open_table("test").count_rows() == 1
db.drop_table("test")
assert db.table_names() == []
def test_read_consistency_interval_does_not_use_background_loop(tmp_path, monkeypatch):
from lancedb.background_loop import LOOP
from lancedb.db import LanceDBConnection
@@ -431,35 +405,6 @@ async def test_connect(tmp_path):
assert str(db) == f"ListingDatabase(uri={tmp_path}, read_consistency_interval=5s)"
@pytest.mark.asyncio
async def test_connect_async_preserves_file_uri_authority(monkeypatch):
uri = "file://server/share/database"
received = []
async def fake_connect(passed_uri, *_args):
received.append(passed_uri)
return SimpleNamespace(uri=passed_uri)
monkeypatch.setattr(lancedb, "lancedb_connect", fake_connect)
db = await lancedb.connect_async(uri)
assert received == [uri]
assert db.uri == uri
@pytest.mark.asyncio
async def test_connect_async_file_uri_lifecycle(tmp_path):
uri = (tmp_path / "async").as_uri()
db = await lancedb.connect_async(uri)
await db.create_table("test", data=[{"id": 1}])
assert await db.table_names() == ["test"]
table = await db.open_table("test")
assert await table.count_rows() == 1
await db.drop_table("test")
assert await db.table_names() == []
@pytest.mark.asyncio
async def test_close(mem_db_async: lancedb.AsyncConnection):
assert mem_db_async.is_open()
@@ -1235,40 +1180,6 @@ def test_clone_table_deep_clone_fails(tmp_path):
db.clone_table("cloned", source_uri, is_shallow=False)
class _UnsupportedNamespaceConfig:
async def namespace_client_config(self):
raise RuntimeError("UNC namespace client export is not supported")
def test_sync_namespace_client_propagates_export_guard(monkeypatch):
from lancedb.db import AsyncConnection, LanceDBConnection
monkeypatch.setattr(
"lancedb.db.namespace_connect",
lambda *_args, **_kwargs: pytest.fail("guarded config was reconstructed"),
)
db = LanceDBConnection.__new__(LanceDBConnection)
db._conn = AsyncConnection(_UnsupportedNamespaceConfig())
db._cached_namespace_client = None
with pytest.raises(RuntimeError, match="UNC namespace client export"):
db.namespace_client()
@pytest.mark.asyncio
async def test_async_namespace_client_propagates_export_guard(monkeypatch):
from lancedb.db import AsyncConnection
monkeypatch.setattr(
"lancedb.db.namespace_connect",
lambda *_args, **_kwargs: pytest.fail("guarded config was reconstructed"),
)
db = AsyncConnection(_UnsupportedNamespaceConfig())
with pytest.raises(RuntimeError, match="UNC namespace client export"):
await db.namespace_client()
@pytest.mark.skipif(sys.platform == "win32", reason="Namespace client issues")
def test_namespace_client_native_storage(tmp_path):
"""Test namespace_client() returns DirectoryNamespace for native storage."""
-41
View File
@@ -60,11 +60,6 @@ class _NamespaceClient:
return _ipc_file()
class _UnsupportedNamespaceConfig:
async def namespace_client_config(self):
raise RuntimeError("UNC namespace client export is not supported")
def _namespace_lance_table(namespace_client: _NamespaceClient) -> LanceTable:
table = LanceTable.__new__(LanceTable)
table._table = _FailingSyncInner()
@@ -143,24 +138,6 @@ class TestNamespaceConnection:
db.drop_namespace(["test_ns"])
assert "test_ns" not in db.list_namespaces().namespaces
def test_sync_namespace_client_propagates_export_guard(self, monkeypatch):
from lancedb.db import AsyncConnection
monkeypatch.setattr(
"lancedb.namespace.namespace_connect",
lambda *_args, **_kwargs: pytest.fail("guarded config was reconstructed"),
)
db = lancedb.LanceNamespaceDBConnection.__new__(
lancedb.LanceNamespaceDBConnection
)
db._namespace_client = None
db._namespace_client_impl = "dir"
db._namespace_client_properties = {"root": "file://server/share/database"}
db._inner = AsyncConnection(_UnsupportedNamespaceConfig())
with pytest.raises(RuntimeError, match="UNC namespace client export"):
db.namespace_client()
def test_create_table_through_namespace(self):
"""Test creating a table through namespace."""
db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
@@ -662,24 +639,6 @@ class TestAsyncNamespaceConnection:
await db.drop_namespace(["test_ns"])
assert "test_ns" not in (await db.list_namespaces()).namespaces
async def test_async_namespace_client_propagates_export_guard(self, monkeypatch):
from lancedb.db import AsyncConnection
monkeypatch.setattr(
"lancedb.namespace.namespace_connect",
lambda *_args, **_kwargs: pytest.fail("guarded config was reconstructed"),
)
db = lancedb.AsyncLanceNamespaceDBConnection.__new__(
lancedb.AsyncLanceNamespaceDBConnection
)
db._namespace_client = None
db._namespace_client_impl = "dir"
db._namespace_client_properties = {"root": "file://server/share/database"}
db._inner = AsyncConnection(_UnsupportedNamespaceConfig())
with pytest.raises(RuntimeError, match="UNC namespace client export"):
await db.namespace_client()
async def test_async_namespace_client_is_lazy(self):
"""namespace_client() should still return the backing client on demand."""
pytest.importorskip("lance")
-3
View File
@@ -188,9 +188,6 @@ required-features = ["bedrock"]
[[example]]
name = "bench_streaming_dataloader"
[[example]]
name = "bench_open_missing_table"
[[example]]
name = "simple"
@@ -1,150 +0,0 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
// Release benchmark for opening a missing table as sibling-table cardinality grows.
//
// The fixture uses real `.lance` directories and marker files. Fixture creation is
// outside the timed section. Defaults intentionally cover 1k, 10k, and 100k siblings
// with 10 warmups and 100 distinct missing-table opens per scale:
//
// ```text
// cargo run --release -p lancedb --example bench_open_missing_table
// ```
//
// `BENCH_SIBLINGS`, `BENCH_WARMUPS`, and `BENCH_TRIALS` override those defaults.
// Reduced settings are useful only as a smoke test. Performance comparisons require
// the same machine, filesystem, fixture sizes, settings, lockfile, and alternating
// baseline/candidate execution order.
use std::time::{Duration, Instant};
use anyhow::{Context, Result, bail};
use lancedb::connection::Connection;
use lancedb::{Error, connect};
use object_store::ObjectStoreExt as _;
use object_store::path::Path;
const MAX_SIBLINGS: usize = 1_000_000;
const MAX_WARMUPS: usize = 10_000;
const MAX_TRIALS: usize = 100_000;
fn env_usize(key: &str, default: usize, max: usize) -> Result<usize> {
let value = match std::env::var(key) {
Ok(value) => value
.parse()
.with_context(|| format!("invalid {key} value: {value}"))?,
Err(std::env::VarError::NotPresent) => default,
Err(error) => return Err(error).with_context(|| format!("reading {key}")),
};
if value == 0 || value > max {
bail!("{key} must be between 1 and {max}");
}
Ok(value)
}
fn sibling_counts() -> Result<Vec<usize>> {
let raw = std::env::var("BENCH_SIBLINGS").unwrap_or_else(|_| "1000,10000,100000".into());
let mut counts = raw
.split(',')
.map(|value| {
value
.trim()
.parse::<usize>()
.with_context(|| format!("invalid BENCH_SIBLINGS value: {value}"))
})
.collect::<Result<Vec<_>>>()?;
counts.sort_unstable();
counts.dedup();
if counts.is_empty() || counts[0] == 0 || counts[counts.len() - 1] > MAX_SIBLINGS {
bail!("BENCH_SIBLINGS values must be between 1 and {MAX_SIBLINGS}");
}
Ok(counts)
}
async fn add_siblings(
store: &object_store::local::LocalFileSystem,
start: usize,
end: usize,
) -> Result<()> {
for index in start..end {
let marker = Path::from(format!("sibling_{index:06}.lance/_marker"));
store
.put(&marker, bytes::Bytes::new().into())
.await
.with_context(|| format!("creating benchmark marker {marker}"))?;
}
Ok(())
}
async fn time_missing_open(db: &Connection, name: &str) -> Result<Duration> {
let started = Instant::now();
let result = db.open_table(name).execute().await;
let elapsed = started.elapsed();
match result {
Err(Error::TableNotFound { .. }) => Ok(elapsed),
Err(error) => bail!("expected TableNotFound for {name}, got {error:?}"),
Ok(_) => bail!("benchmark missing-table name unexpectedly exists: {name}"),
}
}
fn percentile(sorted: &[Duration], percentile: usize) -> Duration {
let rank = (sorted.len() * percentile).div_ceil(100).saturating_sub(1);
sorted[rank]
}
#[tokio::main]
async fn main() -> Result<()> {
let counts = sibling_counts()?;
let warmups = env_usize("BENCH_WARMUPS", 10, MAX_WARMUPS)?;
let trials = env_usize("BENCH_TRIALS", 100, MAX_TRIALS)?;
let fixture = tempfile::tempdir().context("creating benchmark fixture")?;
let database_path = fixture.path();
let fixture_store = object_store::local::LocalFileSystem::new_with_prefix(database_path)
.context("creating benchmark object store")?;
let db = connect(database_path.to_str().context("non-UTF-8 fixture path")?)
.execute()
.await?;
println!(
"config: siblings={counts:?} warmups={warmups} trials={trials} profile={} os={} arch={}",
if cfg!(debug_assertions) {
"debug"
} else {
"release"
},
std::env::consts::OS,
std::env::consts::ARCH,
);
println!("lower is better; fixture setup and teardown are excluded");
println!("| siblings | samples | p50 | p95 | max |");
println!("| ---: | ---: | ---: | ---: | ---: |");
let mut created = 0;
for sibling_count in counts {
add_siblings(&fixture_store, created, sibling_count).await?;
created = sibling_count;
for index in 0..warmups {
let name = format!("__missing_warmup_{sibling_count}_{index}");
let _ = time_missing_open(&db, &name).await?;
}
let mut samples = Vec::with_capacity(trials);
for index in 0..trials {
let name = format!("__missing_trial_{sibling_count}_{index}");
samples.push(time_missing_open(&db, &name).await?);
}
samples.sort_unstable();
println!(
"| {sibling_count} | {} | {:?} | {:?} | {:?} |",
samples.len(),
percentile(&samples, 50),
percentile(&samples, 95),
samples[samples.len() - 1],
);
}
Ok(())
}
+4 -7
View File
@@ -17,7 +17,7 @@ use arrow_array::builder::LargeBinaryBuilder;
use arrow_schema::{DataType, Field, Schema};
use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams};
use lance_arrow::FieldExt;
use lance_file::version::{ConcreteFileVersion, LanceFileVersion};
use lance_file::version::LanceFileVersion;
use lance_io::object_store::ObjectStore;
use object_store::path::Path;
@@ -333,10 +333,7 @@ pub(crate) fn ensure_blob_storage_version(schema: &Schema, params: &mut WritePar
.data_storage_version
.unwrap_or(LanceFileVersion::Stable)
.resolve();
if matches!(
resolved,
ConcreteFileVersion::V1 | ConcreteFileVersion::V2_0 | ConcreteFileVersion::V2_1
) {
if resolved < LanceFileVersion::V2_2 {
params.data_storage_version = Some(LanceFileVersion::V2_2);
}
}
@@ -502,7 +499,7 @@ mod tests {
ensure_blob_storage_version(&blob_schema(), &mut params);
assert_eq!(
params.data_storage_version.unwrap().resolve(),
ConcreteFileVersion::V2_2
LanceFileVersion::V2_2
);
}
@@ -515,7 +512,7 @@ mod tests {
ensure_blob_storage_version(&blob_schema(), &mut params);
assert_eq!(
params.data_storage_version.unwrap().resolve(),
ConcreteFileVersion::V2_2
LanceFileVersion::V2_2
);
}
+4 -8
View File
@@ -409,11 +409,6 @@ impl Connection {
///
/// The names will be returned in lexicographical order (ascending)
///
/// Listing databases discover physical `*.lance` entries without opening every
/// dataset. The result is a point-in-time discovery snapshot: an entry may still be
/// under creation, may contain only uncommitted storage, or may be concurrently
/// dropped before it is opened.
///
/// The parameters `page_token` and `limit` can be used to paginate the results
pub fn table_names(&self) -> TableNamesBuilder {
TableNamesBuilder::new(self.internal.clone())
@@ -461,9 +456,10 @@ impl Connection {
///
/// # Returns
/// Created [`TableRef`], or [`Error::TableNotFound`] if the table does not exist.
/// On listing databases, a committed Lance manifest is authoritative for table
/// existence. Uncommitted files or a physical `<name>.lance` directory alone do not
/// make a table openable.
/// If the table's storage is present but holds no readable dataset (for example a
/// `<name>.lance` directory left behind by an interrupted drop and re-create, which
/// [`Self::table_names`] still lists) this returns [`Error::TableCorrupted`]
/// instead.
pub fn open_table(&self, name: impl Into<String>) -> OpenTableBuilder {
OpenTableBuilder::new(
self.internal.clone(),
+3 -2
View File
@@ -438,9 +438,10 @@ mod tests {
.await
.unwrap()
.data_storage_format
.lance_file_format();
.lance_file_version()
.unwrap();
// Compare resolved versions since Stable/Next are aliases that resolve at storage time
assert_eq!(storage_format, data_storage_version.resolve());
assert_eq!(storage_format.resolve(), data_storage_version.resolve());
}
#[tokio::test]
File diff suppressed because it is too large Load Diff
-132
View File
@@ -59,46 +59,6 @@ fn is_table_already_exists_namespace_error(err: &lance::Error) -> bool {
/// via the `delimiter` property.
const DEFAULT_NAMESPACE_DELIMITER: &str = "$";
#[cfg(any(windows, test))]
fn is_unc_root(root: &str) -> bool {
let normalized = root.replace('\\', "/");
let lowercase = normalized.to_ascii_lowercase();
if lowercase.starts_with("//?/unc/") {
return true;
}
if lowercase.starts_with("//?/") || lowercase.starts_with("//./") {
return false;
}
if let Some(authority) = normalized.strip_prefix("//") {
return !authority.is_empty() && !authority.starts_with('/');
}
normalized.split_once("://").is_some_and(|(scheme, path)| {
scheme.eq_ignore_ascii_case("file") && !path.is_empty() && !path.starts_with('/')
})
}
#[cfg(any(windows, test))]
fn is_directory_unc_root(ns_impl: &str, ns_properties: &HashMap<String, String>) -> bool {
ns_impl.eq_ignore_ascii_case("dir")
&& ns_properties
.get("root")
.is_some_and(|root| is_unc_root(root))
}
#[cfg(any(windows, test))]
#[derive(Debug)]
struct UnavailableUncDirectoryNamespace;
#[cfg(any(windows, test))]
#[async_trait]
impl LanceNamespace for UnavailableUncDirectoryNamespace {
fn namespace_id(&self) -> String {
"unavailable-unc-directory".to_string()
}
}
/// A database implementation that uses lance-namespace for table management
pub struct LanceNamespaceDatabase {
namespace: Arc<dyn LanceNamespace>,
@@ -132,17 +92,6 @@ fn resolve_delimiter(ns_properties: &HashMap<String, String>) -> String {
}
impl LanceNamespaceDatabase {
fn ensure_storage_supported(&self) -> Result<()> {
#[cfg(any(windows, test))]
if is_directory_unc_root(&self.ns_impl, &self.ns_properties) {
return Err(Error::NotSupported {
message: "Directory namespace operations are not supported for UNC roots because the namespace manifest resolver does not preserve file URI authorities; use flat root tables or a non-UNC namespace root"
.to_string(),
});
}
Ok(())
}
pub fn from_namespace_client(
namespace_client: Arc<dyn LanceNamespace>,
namespace_client_impl: String,
@@ -204,25 +153,6 @@ impl LanceNamespaceDatabase {
pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
new_table_config: NewTableConfig,
) -> Result<Self> {
#[cfg(any(windows, test))]
if is_directory_unc_root(ns_impl, &ns_properties) {
let freshness_baselines: FreshnessBaselines = Arc::new(Mutex::new(HashMap::new()));
let delimiter = resolve_delimiter(&ns_properties);
return Ok(Self {
namespace: Arc::new(UnavailableUncDirectoryNamespace),
storage_options,
read_consistency_interval,
session,
uri: format!("namespace://{}", ns_impl),
pushdown_operations,
ns_impl: ns_impl.to_string(),
ns_properties,
new_table_config,
freshness_baselines,
delimiter,
});
}
let mut builder = ConnectBuilder::new(ns_impl);
for (key, value) in ns_properties.clone() {
builder = builder.property(key, value);
@@ -380,7 +310,6 @@ impl Database for LanceNamespaceDatabase {
&self,
request: ListNamespacesRequest,
) -> Result<ListNamespacesResponse> {
self.ensure_storage_supported()?;
Ok(self.namespace.list_namespaces(request).await?)
}
@@ -388,12 +317,10 @@ impl Database for LanceNamespaceDatabase {
&self,
request: CreateNamespaceRequest,
) -> Result<CreateNamespaceResponse> {
self.ensure_storage_supported()?;
Ok(self.namespace.create_namespace(request).await?)
}
async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<DropNamespaceResponse> {
self.ensure_storage_supported()?;
Ok(self.namespace.drop_namespace(request).await?)
}
@@ -401,12 +328,10 @@ impl Database for LanceNamespaceDatabase {
&self,
request: DescribeNamespaceRequest,
) -> Result<DescribeNamespaceResponse> {
self.ensure_storage_supported()?;
Ok(self.namespace.describe_namespace(request).await?)
}
async fn table_names(&self, request: TableNamesRequest) -> Result<Vec<String>> {
self.ensure_storage_supported()?;
let ns_request = ListTablesRequest {
id: Some(request.namespace_path),
page_token: request.start_after,
@@ -420,12 +345,10 @@ impl Database for LanceNamespaceDatabase {
}
async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
self.ensure_storage_supported()?;
Ok(self.namespace.list_tables(request).await?)
}
async fn create_table(&self, request: DbCreateTableRequest) -> Result<Arc<dyn BaseTable>> {
self.ensure_storage_supported()?;
let mut table_id = request.namespace_path.clone();
table_id.push(request.name.clone());
let mut existing_table = None;
@@ -595,7 +518,6 @@ impl Database for LanceNamespaceDatabase {
}
async fn open_table(&self, request: OpenTableRequest) -> Result<Arc<dyn BaseTable>> {
self.ensure_storage_supported()?;
let native_table = NativeTable::open_from_namespace(
self.namespace.clone(),
&request.name,
@@ -625,7 +547,6 @@ impl Database for LanceNamespaceDatabase {
cur_namespace_path: &[String],
new_namespace_path: &[String],
) -> Result<()> {
self.ensure_storage_supported()?;
let mut cur_table_id = cur_namespace_path.to_vec();
cur_table_id.push(cur_name.to_string());
@@ -652,7 +573,6 @@ impl Database for LanceNamespaceDatabase {
}
async fn drop_table(&self, name: &str, namespace_path: &[String]) -> Result<()> {
self.ensure_storage_supported()?;
let mut table_id = namespace_path.to_vec();
table_id.push(name.to_string());
@@ -692,12 +612,10 @@ impl Database for LanceNamespaceDatabase {
}
async fn namespace_client(&self) -> Result<Arc<dyn LanceNamespace>> {
self.ensure_storage_supported()?;
Ok(self.namespace.clone())
}
async fn namespace_client_config(&self) -> Result<(String, HashMap<String, String>)> {
self.ensure_storage_supported()?;
Ok((self.ns_impl.clone(), self.ns_properties.clone()))
}
}
@@ -726,56 +644,6 @@ mod tests {
RecordBatch::try_new(schema, vec![Arc::new(id_array), Arc::new(name_array)]).unwrap()
}
#[test]
fn detects_unc_namespace_roots_without_misclassifying_drives() {
for root in [
"file://server/share/database",
"FILE://server/share/database",
r"\\server\share\database",
r"\\?\UNC\server\share\database",
] {
assert!(is_unc_root(root), "expected an UNC root: {root}");
}
for root in [
"file:///C:/database",
r"C:\database",
r"\\?\C:\database",
"/var/lib/database",
] {
assert!(!is_unc_root(root), "expected a non-UNC root: {root}");
}
}
#[tokio::test]
async fn directory_namespace_fails_closed_before_accessing_an_unc_root() {
let mut properties = HashMap::new();
properties.insert(
"root".to_string(),
"file://server/share/database".to_string(),
);
let db = LanceNamespaceDatabase::connect(
"dir",
properties,
HashMap::new(),
None,
None,
HashSet::new(),
)
.await
.unwrap();
let error = db
.list_tables(ListTablesRequest::default())
.await
.unwrap_err();
assert!(matches!(error, Error::NotSupported { .. }));
assert!(error.to_string().contains("UNC roots"));
let error = db.namespace_client_config().await.unwrap_err();
assert!(matches!(error, Error::NotSupported { .. }));
assert!(error.to_string().contains("UNC roots"));
}
#[tokio::test]
async fn test_namespace_connection_simple() {
// Test that namespace connections work with simple connect_namespace(impl_type, properties)
+71 -801
View File
@@ -1,821 +1,23 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
//! Object-store providers and adapters used by LanceDB.
//! A mirroring object store that mirror writes to a secondary object store
use std::{fmt::Formatter, sync::Arc};
#[cfg(any(windows, test))]
use futures::TryStreamExt;
use futures::{StreamExt, TryFutureExt, stream::BoxStream};
use lance::io::WrappingObjectStore;
#[cfg(any(windows, test))]
use lance_table::{
format::{IndexMetadata, Manifest, Transaction},
io::commit::{
CommitError, CommitHandler, ManifestLocation, ManifestNamingScheme, ManifestWriter,
RenameCommitHandler,
},
};
use object_store::{
CopyOptions, Error, GetOptions, GetResult, ListResult, MultipartUpload, ObjectMeta,
CopyMode, CopyOptions, Error, GetOptions, GetResult, ListResult, MultipartUpload, ObjectMeta,
ObjectStore, ObjectStoreExt, PutMultipartOptions, PutOptions, PutPayload, PutResult, Result,
UploadPart, path::Path,
};
use async_trait::async_trait;
#[cfg(any(windows, test))]
use lance_core::{Error as LanceError, Result as LanceResult};
#[cfg(test)]
use lance_io::object_store::ObjectStoreRegistry;
#[cfg(any(windows, test))]
use lance_io::object_store::{
DEFAULT_LOCAL_IO_PARALLELISM, ObjectStoreParams, ObjectStoreProvider, StorageOptions,
};
#[cfg(any(windows, test))]
use object_store::local::LocalFileSystem;
#[cfg(any(windows, test))]
use url::Url;
#[cfg(test)]
pub mod io_tracking;
/// A local commit handler that resolves the latest manifest through the object store.
///
/// Lance's native local shortcut reconstructs the selected manifest from a
/// filesystem path. On Windows that conversion drops the authority from a UNC
/// path. Listing through the already-rooted object store preserves the structural
/// server/share prefix while retaining the normal atomic-rename commit behavior.
#[derive(Debug)]
#[cfg(any(windows, test))]
struct RootedFileCommitHandler;
#[cfg(any(windows, test))]
#[async_trait]
impl CommitHandler for RootedFileCommitHandler {
fn is_version_not_found_definitive(&self) -> bool {
RenameCommitHandler.is_version_not_found_definitive()
}
fn propagate_commit_error_after_success(&self) -> bool {
RenameCommitHandler.propagate_commit_error_after_success()
}
async fn resolve_latest_location(
&self,
base_path: &Path,
object_store: &lance::io::ObjectStore,
) -> LanceResult<ManifestLocation> {
self.list_manifest_locations(base_path, object_store, true)
.try_next()
.await?
.ok_or_else(|| LanceError::not_found(base_path.to_string()))
}
async fn commit(
&self,
manifest: &mut Manifest,
indices: Option<Vec<IndexMetadata>>,
base_path: &Path,
object_store: &lance::io::ObjectStore,
manifest_writer: ManifestWriter,
naming_scheme: ManifestNamingScheme,
transaction: Option<Transaction>,
) -> std::result::Result<ManifestLocation, CommitError> {
RenameCommitHandler
.commit(
manifest,
indices,
base_path,
object_store,
manifest_writer,
naming_scheme,
transaction,
)
.await
}
}
#[cfg(any(windows, test))]
pub(crate) fn rooted_file_commit_handler() -> Arc<dyn CommitHandler> {
Arc::new(RootedFileCommitHandler)
}
/// A file-store provider that anchors each request at its filesystem root.
///
/// On Windows, an unprefixed [`LocalFileSystem`] cannot service UNC paths. Its
/// conversion to an object-store [`Path`] drops the UNC host, so subsequent I/O
/// is directed at a different local path. Anchoring the store at the drive or
/// UNC-share root keeps the UNC authority in the filesystem prefix and exposes
/// only paths relative to that prefix to `object_store`.
///
/// Extracted paths retain the native drive or UNC-share root as a structural
/// first component. This keeps Lance's local classification and optimized I/O
/// safe without recovering absolute path provenance from ambiguous path text.
#[cfg(any(windows, test))]
#[derive(Debug)]
struct PrefixedFileStoreProvider;
#[cfg(any(windows, test))]
impl PrefixedFileStoreProvider {
fn root_and_relative_path(url: &Url) -> LanceResult<(std::path::PathBuf, Path)> {
let filesystem_path = url.to_file_path().map_err(|_| {
LanceError::invalid_input(format!("Unable to convert URL '{url}' to a local path"))
})?;
let mut root = std::path::PathBuf::new();
for component in filesystem_path.components() {
match component {
std::path::Component::Prefix(_) | std::path::Component::RootDir => {
root.push(component.as_os_str());
}
_ => break,
}
}
if root.as_os_str().is_empty() {
return Err(LanceError::invalid_input(format!(
"Local path '{}' has no filesystem root",
filesystem_path.display()
)));
}
let relative = filesystem_path.strip_prefix(&root).map_err(|_| {
LanceError::invalid_input(format!(
"Local path '{}' is not beneath store root '{}'",
filesystem_path.display(),
root.display()
))
})?;
let relative = relative
.components()
.filter_map(|component| match component {
std::path::Component::Normal(part) => Some(part),
_ => None,
})
.map(|part| {
part.to_str().ok_or_else(|| {
LanceError::invalid_input(format!(
"Local path '{}' is not valid UTF-8",
filesystem_path.display()
))
})
})
.collect::<LanceResult<Vec<_>>>()?
.join("/");
Ok((root, Path::parse(relative)?))
}
/// Preserve the native filesystem root as a structural path component.
///
/// `object_store::Path::from_absolute_path` converts a UNC path to its URL
/// path and loses the server. Keeping `C:` or `\\server\share` as the first
/// component distinguishes an absolute path from every relative path while
/// remaining directly usable by Windows filesystem APIs.
fn rooted_path(root: &std::path::Path, relative: &Path) -> LanceResult<Path> {
let root = root.to_string_lossy();
let root = root.trim_end_matches(['/', '\\']);
if root.is_empty() {
return Ok(relative.clone());
}
Ok(relative
.parts()
.fold(Path::parse(root)?, |path, part| path.join(part)))
}
}
/// A local store rooted at a Windows drive or UNC share.
///
/// Most calls use paths returned by [`PrefixedFileStoreProvider`], which are
/// relative to `root`. Some Lance operations retain an existing object store
/// while independently re-extracting a Windows file URI with the default file
/// provider. Those paths include the drive (`C:/...`) or UNC share
/// (`share/...`) again. Normalize that absolute alias before delegating so the
/// filesystem prefix is never applied twice.
#[cfg(any(windows, test))]
#[derive(Debug, Clone)]
struct RootedLocalFileSystem {
inner: Arc<LocalFileSystem>,
root: std::path::PathBuf,
absolute_alias: Path,
}
#[cfg(any(windows, test))]
impl RootedLocalFileSystem {
fn new(root: std::path::PathBuf) -> LanceResult<Self> {
let absolute_alias = PrefixedFileStoreProvider::rooted_path(&root, &Path::default())?;
Ok(Self {
inner: Arc::new(LocalFileSystem::new_with_prefix(&root)?),
root,
absolute_alias,
})
}
fn path_from_parts<'a>(parts: impl Iterator<Item = object_store::path::PathPart<'a>>) -> Path {
parts.fold(Path::default(), |path, part| path.join(part))
}
fn normalize(&self, path: &Path) -> Path {
if self.absolute_alias.as_ref().is_empty() {
return path.clone();
}
let Some(suffix) = path.prefix_match(&self.absolute_alias) else {
return path.clone();
};
Self::path_from_parts(suffix)
}
fn restore_prefix(&self, path: Path, requested: &Path, normalized: &Path) -> Path {
if requested == normalized {
return path;
}
path.prefix_match(normalized)
.map(|suffix| suffix.fold(requested.clone(), |path, part| path.join(part)))
.unwrap_or(path)
}
}
#[cfg(any(windows, test))]
impl std::fmt::Display for RootedLocalFileSystem {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
write!(f, "RootedLocalFileSystem({})", self.root.display())
}
}
#[cfg(any(windows, test))]
#[async_trait]
impl ObjectStore for RootedLocalFileSystem {
async fn put_opts(
&self,
location: &Path,
payload: PutPayload,
options: PutOptions,
) -> Result<PutResult> {
self.inner
.put_opts(&self.normalize(location), payload, options)
.await
}
async fn put_multipart_opts(
&self,
location: &Path,
options: PutMultipartOptions,
) -> Result<Box<dyn MultipartUpload>> {
self.inner
.put_multipart_opts(&self.normalize(location), options)
.await
}
async fn get_opts(&self, location: &Path, options: GetOptions) -> Result<GetResult> {
let normalized = self.normalize(location);
let mut result = self.inner.get_opts(&normalized, options).await?;
result.meta.location = location.clone();
Ok(result)
}
fn delete_stream(
&self,
locations: BoxStream<'static, Result<Path>>,
) -> BoxStream<'static, Result<Path>> {
let store = self.clone();
locations
.map(move |location| {
let store = store.clone();
async move {
let location = location?;
let normalized = store.normalize(&location);
store.inner.delete(&normalized).await?;
Ok(location)
}
})
.buffered(10)
.boxed()
}
fn list(&self, prefix: Option<&Path>) -> BoxStream<'static, Result<ObjectMeta>> {
let requested = prefix.cloned().unwrap_or_default();
let normalized = self.normalize(&requested);
let store = self.clone();
self.inner
.list(prefix.map(|_| &normalized))
.map(move |result| {
result.map(|mut meta| {
meta.location = store.restore_prefix(meta.location, &requested, &normalized);
meta
})
})
.boxed()
}
async fn list_with_delimiter(&self, prefix: Option<&Path>) -> Result<ListResult> {
let requested = prefix.cloned().unwrap_or_default();
let normalized = self.normalize(&requested);
let mut result = self
.inner
.list_with_delimiter(prefix.map(|_| &normalized))
.await?;
for meta in &mut result.objects {
meta.location = self.restore_prefix(meta.location.clone(), &requested, &normalized);
}
for path in &mut result.common_prefixes {
*path = self.restore_prefix(path.clone(), &requested, &normalized);
}
Ok(result)
}
async fn copy_opts(&self, from: &Path, to: &Path, options: CopyOptions) -> Result<()> {
self.inner
.copy_opts(&self.normalize(from), &self.normalize(to), options)
.await
}
}
#[cfg(any(windows, test))]
#[async_trait]
impl ObjectStoreProvider for PrefixedFileStoreProvider {
async fn new_store(
&self,
base_path: Url,
params: &ObjectStoreParams,
) -> LanceResult<lance::io::ObjectStore> {
let (root, _) = Self::root_and_relative_path(&base_path)?;
let raw_store: Arc<dyn ObjectStore> = Arc::new(RootedLocalFileSystem::new(root)?);
// Native local shortcuts are safe only when the rooted filesystem is
// the final store. An arbitrary wrapper can redirect I/O, so use
// Lance's non-cloud object-store route in that case. This keeps local
// scan planning without enabling native copy/delete or the io_uring
// scheduler, all of which would bypass the wrapper.
let location = if params.object_store_wrapper.is_some() {
Url::parse("memory:///").expect("static URL must be valid")
} else {
Url::parse("file:///").expect("static URL must be valid")
};
let storage_options =
StorageOptions::new(params.storage_options().cloned().unwrap_or_default());
// ObjectStore::new initializes the private local-store fields. The
// registry owns tracing, custom wrapper, and I/O tracker installation,
// so restore the raw store before returning to avoid applying them twice.
let mut store = lance::io::ObjectStore::new(
raw_store.clone(),
location,
Some(params.block_size.unwrap_or(4 * 1024)),
None,
false,
false,
DEFAULT_LOCAL_IO_PARALLELISM,
storage_options.download_retry_count(),
params.storage_options(),
);
store.inner = raw_store;
store.store_prefix =
self.calculate_object_store_prefix(&base_path, params.storage_options())?;
Ok(store)
}
fn extract_path(&self, url: &Url) -> LanceResult<Path> {
let (root, relative) = Self::root_and_relative_path(url)?;
Self::rooted_path(&root, &relative)
}
fn calculate_object_store_prefix(
&self,
url: &Url,
_storage_options: Option<&std::collections::HashMap<String, String>>,
) -> LanceResult<String> {
let (root, _) = Self::root_and_relative_path(url)?;
let root = root.canonicalize()?;
// One store per drive or UNC share keeps registry and metrics
// cardinality bounded. Absolute-vs-relative provenance is carried by
// the extracted path instead of the cache key.
Ok(format!("file${}", root.display()))
}
}
/// Build LanceDB's default session with the Windows file fallback installed.
///
/// Callers that provide a Session retain its registry unchanged.
pub(crate) fn new_default_session() -> Arc<lance::session::Session> {
let session = Arc::new(lance::session::Session::default());
#[cfg(windows)]
session
.store_registry()
.insert("file", Arc::new(PrefixedFileStoreProvider));
session
}
#[cfg(test)]
pub(crate) fn new_prefixed_file_session() -> Arc<lance::session::Session> {
let session = Arc::new(lance::session::Session::default());
session
.store_registry()
.insert("file", Arc::new(PrefixedFileStoreProvider));
session
}
#[cfg(test)]
mod prefixed_file_store_test {
use super::*;
use object_store::memory::InMemory;
use std::sync::atomic::{AtomicUsize, Ordering};
#[derive(Debug, Default)]
struct CountingWrapper {
calls: AtomicUsize,
}
impl WrappingObjectStore for CountingWrapper {
fn wrap(
&self,
_store_prefix: &str,
original: Arc<dyn ObjectStore>,
) -> Arc<dyn ObjectStore> {
self.calls.fetch_add(1, Ordering::Relaxed);
original
}
}
#[derive(Debug, Default)]
struct MemoryRedirectWrapper {
store: Arc<InMemory>,
}
impl WrappingObjectStore for MemoryRedirectWrapper {
fn wrap(
&self,
_store_prefix: &str,
_original: Arc<dyn ObjectStore>,
) -> Arc<dyn ObjectStore> {
self.store.clone()
}
}
#[test]
fn commit_handler_forwards_commit_outcome_capabilities() {
let handler = RootedFileCommitHandler;
assert!(handler.is_version_not_found_definitive());
assert!(!handler.propagate_commit_error_after_success());
}
#[tokio::test]
async fn anchors_new_and_existing_directories_at_a_filesystem_prefix() {
let tempdir = tempfile::tempdir().unwrap();
let database_path = tempdir.path().join("database");
std::fs::create_dir(&database_path).unwrap();
let table_path = database_path.join("test.lance");
let table_url = Url::from_directory_path(&table_path).unwrap();
let registry = Arc::new(ObjectStoreRegistry::default());
registry.insert("file", Arc::new(PrefixedFileStoreProvider));
// The extracted path remains absolute for Lance's local fast paths,
// while the inner store strips the structural root before delegation.
let (store, base_path) = lance::io::ObjectStore::from_uri_and_params(
registry.clone(),
table_url.as_str(),
&ObjectStoreParams::default(),
)
.await
.unwrap();
assert_eq!(store.scheme(), "file");
assert!(store.is_local());
assert!(!store.is_cloud());
assert_eq!(store.block_size(), 4 * 1024);
assert_eq!(store.io_parallelism(), DEFAULT_LOCAL_IO_PARALLELISM);
assert_eq!(base_path.filename(), Some("test.lance"));
let initial_base_path = base_path.clone();
let marker = base_path.join("marker");
store
.inner
.put(&marker, bytes::Bytes::from_static(b"new").into())
.await
.unwrap();
assert_eq!(std::fs::read(table_path.join("marker")).unwrap(), b"new");
// Once the table directory exists, a fresh store uses the same stable
// root and object-store path.
drop(store);
let (store, base_path) = lance::io::ObjectStore::from_uri_and_params(
registry,
table_url.as_str(),
&ObjectStoreParams::default(),
)
.await
.unwrap();
assert_eq!(base_path, initial_base_path);
let contents = store
.inner
.get(&base_path.join("marker"))
.await
.unwrap()
.bytes()
.await
.unwrap();
assert_eq!(contents.as_ref(), b"new");
}
#[tokio::test]
async fn applies_wrapper_and_io_tracking_once() {
let tempdir = tempfile::tempdir().unwrap();
let table_url = Url::from_directory_path(tempdir.path().join("test.lance")).unwrap();
let registry = Arc::new(ObjectStoreRegistry::default());
registry.insert("file", Arc::new(PrefixedFileStoreProvider));
let wrapper = Arc::new(CountingWrapper::default());
let params = ObjectStoreParams {
object_store_wrapper: Some(wrapper.clone()),
..Default::default()
};
let (store, base_path) =
lance::io::ObjectStore::from_uri_and_params(registry, table_url.as_str(), &params)
.await
.unwrap();
assert_eq!(wrapper.calls.load(Ordering::Relaxed), 1);
assert_eq!(store.scheme(), "memory");
assert!(!store.is_local());
assert!(!store.is_cloud());
assert!(!store.prefers_lite_scheduler());
store
.inner
.put(
&base_path.join("marker"),
bytes::Bytes::from_static(b"tracked").into(),
)
.await
.unwrap();
let stats = store.io_tracker().stats();
assert_eq!(stats.write_iops, 1);
assert_eq!(stats.written_bytes, 7);
}
#[tokio::test]
async fn wrapped_store_cleanup_does_not_bypass_the_wrapper() {
let tempdir = tempfile::tempdir().unwrap();
let table_path = tempdir.path().join("test.lance");
std::fs::create_dir(&table_path).unwrap();
std::fs::write(table_path.join("native-marker"), b"native").unwrap();
let table_url = Url::from_directory_path(&table_path).unwrap();
let registry = Arc::new(ObjectStoreRegistry::default());
registry.insert("file", Arc::new(PrefixedFileStoreProvider));
let wrapper = Arc::new(MemoryRedirectWrapper::default());
let params = ObjectStoreParams {
object_store_wrapper: Some(wrapper.clone()),
..Default::default()
};
let (store, base_path) =
lance::io::ObjectStore::from_uri_and_params(registry, table_url.as_str(), &params)
.await
.unwrap();
let wrapped_marker = base_path.clone().join("wrapped-marker");
store
.inner
.put(
&wrapped_marker,
bytes::Bytes::from_static(b"wrapped").into(),
)
.await
.unwrap();
store.remove_dir_all(base_path).await.unwrap();
assert!(table_path.join("native-marker").exists());
assert!(matches!(
wrapper.store.head(&wrapped_marker).await,
Err(object_store::Error::NotFound { .. })
));
}
#[tokio::test]
async fn rooted_commit_handler_uses_store_paths_for_latest_manifest() {
let tempdir = tempfile::tempdir().unwrap();
let versions = tempdir.path().join("_versions");
std::fs::create_dir(&versions).unwrap();
std::fs::write(versions.join("2.manifest"), b"native").unwrap();
let base_path = Path::from_absolute_path(tempdir.path()).unwrap();
let raw_store: Arc<dyn ObjectStore> = Arc::new(InMemory::new());
raw_store
.put(
&base_path.clone().join("_versions").join("1.manifest"),
bytes::Bytes::from_static(b"wrapped").into(),
)
.await
.unwrap();
let mut store = lance::io::ObjectStore::new(
raw_store.clone(),
Url::parse("file:///").unwrap(),
Some(4 * 1024),
None,
false,
false,
DEFAULT_LOCAL_IO_PARALLELISM,
0,
None,
);
store.inner = raw_store;
let native = RenameCommitHandler
.resolve_latest_location(&base_path, &store)
.await
.unwrap();
assert_eq!(native.version, 2);
let rooted = rooted_file_commit_handler()
.resolve_latest_location(&base_path, &store)
.await
.unwrap();
assert_eq!(rooted.version, 1);
assert_eq!(
rooted.path,
base_path.clone().join("_versions").join("1.manifest")
);
}
#[tokio::test]
async fn reuses_store_cache_across_database_paths() {
let tempdir = tempfile::tempdir().unwrap();
let first_url = Url::from_directory_path(tempdir.path().join("database")).unwrap();
let second_url = Url::from_directory_path(tempdir.path().join("share/database")).unwrap();
let registry = Arc::new(ObjectStoreRegistry::default());
registry.insert("file", Arc::new(PrefixedFileStoreProvider));
let (first, _) = lance::io::ObjectStore::from_uri_and_params(
registry.clone(),
first_url.as_str(),
&ObjectStoreParams::default(),
)
.await
.unwrap();
let (second, _) = lance::io::ObjectStore::from_uri_and_params(
registry.clone(),
second_url.as_str(),
&ObjectStoreParams::default(),
)
.await
.unwrap();
assert!(Arc::ptr_eq(&first, &second));
assert_eq!(registry.stats().misses, 1);
assert_eq!(registry.stats().hits, 1);
}
#[tokio::test]
async fn reuses_database_store_for_table_and_clone_targets() {
let tempdir = tempfile::tempdir().unwrap();
let database_url = Url::from_directory_path(tempdir.path().join("database")).unwrap();
let source_url =
Url::from_directory_path(tempdir.path().join("database/source.lance")).unwrap();
let target_url =
Url::from_directory_path(tempdir.path().join("database/target.lance")).unwrap();
let registry = Arc::new(ObjectStoreRegistry::default());
registry.insert("file", Arc::new(PrefixedFileStoreProvider));
let (database, _) = lance::io::ObjectStore::from_uri_and_params(
registry.clone(),
database_url.as_str(),
&ObjectStoreParams::default(),
)
.await
.unwrap();
let (source, _) = lance::io::ObjectStore::from_uri_and_params(
registry.clone(),
source_url.as_str(),
&ObjectStoreParams::default(),
)
.await
.unwrap();
let (target, _) = lance::io::ObjectStore::from_uri_and_params(
registry.clone(),
target_url.as_str(),
&ObjectStoreParams::default(),
)
.await
.unwrap();
assert!(Arc::ptr_eq(&database, &source));
assert!(Arc::ptr_eq(&database, &target));
assert_eq!(registry.stats().misses, 1);
assert_eq!(registry.stats().hits, 2);
}
#[test]
fn normalizes_absolute_drive_and_unc_aliases() {
let tempdir = tempfile::tempdir().unwrap();
let mut drive_store = RootedLocalFileSystem::new(tempdir.path().to_path_buf()).unwrap();
drive_store.absolute_alias = Path::from("C:");
assert_eq!(
drive_store.normalize(&Path::from("C:/Users/db/table.lance")),
Path::from("Users/db/table.lance")
);
let mut unc_store = RootedLocalFileSystem::new(tempdir.path().to_path_buf()).unwrap();
unc_store.absolute_alias = Path::parse(r"\\server\share").unwrap();
assert_eq!(
unc_store.normalize(&Path::parse(r"\\server\share/share/db/table.lance").unwrap()),
Path::from("share/db/table.lance")
);
assert_eq!(
unc_store.normalize(&Path::from("share/db/table.lance")),
Path::from("share/db/table.lance")
);
}
#[test]
fn relative_unc_alias_does_not_cross_database_roots() {
let tempdir = tempfile::tempdir().unwrap();
let mut store = RootedLocalFileSystem::new(tempdir.path().to_path_buf()).unwrap();
store.absolute_alias = Path::parse(r"\\server\share").unwrap();
let relative = Path::from("share/database/table.lance/marker");
assert_eq!(store.normalize(&relative), relative);
assert_eq!(
store.normalize(
&Path::parse(r"\\server\share/share/database/table.lance/marker").unwrap()
),
relative
);
}
#[tokio::test]
async fn routes_unc_alias_lifecycle_through_the_prefix() {
let tempdir = tempfile::tempdir().unwrap();
let mut store = RootedLocalFileSystem::new(tempdir.path().to_path_buf()).unwrap();
store.absolute_alias = Path::parse(r"\\server\share").unwrap();
let table = Path::parse(r"\\server\share/share/db/test.lance").unwrap();
let marker = table.clone().join("marker");
store
.put(&marker, bytes::Bytes::from_static(b"unc").into())
.await
.unwrap();
assert_eq!(
std::fs::read(tempdir.path().join("share/db/test.lance/marker")).unwrap(),
b"unc"
);
let listed = store.list(Some(&table)).collect::<Vec<_>>().await;
assert_eq!(listed.len(), 1);
assert_eq!(listed[0].as_ref().unwrap().location, marker);
assert_eq!(
store
.get(&marker)
.await
.unwrap()
.bytes()
.await
.unwrap()
.as_ref(),
b"unc"
);
store.delete(&marker).await.unwrap();
assert!(!tempdir.path().join("share/db/test.lance/marker").exists());
}
#[cfg(windows)]
#[test]
fn extracts_drive_and_unc_share_roots() {
let (root, path) = PrefixedFileStoreProvider::root_and_relative_path(
&Url::parse("file:///C:/database").unwrap(),
)
.unwrap();
assert_eq!(root, std::path::PathBuf::from(r"C:\"));
assert_eq!(path, Path::from("database"));
let (root, path) = PrefixedFileStoreProvider::root_and_relative_path(
&Url::parse("file://server/share/database").unwrap(),
)
.unwrap();
assert_eq!(root, std::path::PathBuf::from(r"\\server\share\"));
assert_eq!(path, Path::from("database"));
}
#[test]
fn preserves_drive_and_unc_roots_in_extracted_paths() {
assert_eq!(
PrefixedFileStoreProvider::rooted_path(
std::path::Path::new(r"C:\"),
&Path::from("database/table.lance")
)
.unwrap(),
Path::from("C:/database/table.lance")
);
assert_eq!(
PrefixedFileStoreProvider::rooted_path(
std::path::Path::new(r"\\server\share\"),
&Path::from("database/table.lance")
)
.unwrap(),
Path::parse(r"\\server\share/database/table.lance").unwrap()
);
}
}
#[derive(Debug)]
struct MirroringObjectStore {
primary: Arc<dyn ObjectStore>,
@@ -850,7 +52,7 @@ impl PrimaryOnly for Path {
/// store. We have primary store that is durable but slow, and a secondary
/// store that is fast but not asdurable
///
/// Note: this object store does not mirror writes to *.manifest files
/// Note: this object store does not mirror writes to `_latest.manifest`.
#[async_trait]
impl ObjectStore for MirroringObjectStore {
async fn put_opts(
@@ -935,6 +137,16 @@ impl ObjectStore for MirroringObjectStore {
// or may be evicted before the copy begins.
match self.secondary.copy_opts(from, to, options.clone()).await {
Ok(()) | Err(Error::NotFound { .. }) => {}
// The secondary is a non-authoritative cache. A process can
// leave an orphaned manifest there if it exits before creating
// the durable primary object, so let the primary decide the
// outcome of create-only manifest copies.
Err(Error::AlreadyExists { .. } | Error::Precondition { .. })
if options.mode == CopyMode::Create
&& to
.filename()
.map(|name| name.ends_with(".manifest"))
.unwrap_or(false) => {}
Err(err) => return Err(err),
}
self.primary.copy_opts(from, to, options).await
@@ -1138,6 +350,64 @@ mod test {
));
}
#[tokio::test]
async fn test_create_manifest_recovers_from_orphaned_secondary() {
let primary: Arc<dyn ObjectStore> = Arc::new(InMemory::new());
let secondary: Arc<dyn ObjectStore> = Arc::new(InMemory::new());
let store = MirroringObjectStore {
primary: primary.clone(),
secondary: secondary.clone(),
};
let staging = Path::from("_versions/1.manifest-staging");
let finalized = Path::from("_versions/1.manifest");
primary
.put(&staging, "manifest contents".into())
.await
.unwrap();
secondary
.put(&staging, "manifest contents".into())
.await
.unwrap();
secondary
.copy_if_not_exists(&staging, &finalized)
.await
.expect("simulate a crash after secondary create and before primary create");
store
.copy_if_not_exists(&staging, &finalized)
.await
.expect("an orphaned secondary manifest must not block primary creation");
let copied = primary
.get(&finalized)
.await
.unwrap()
.bytes()
.await
.unwrap();
assert_eq!(copied, "manifest contents");
assert!(matches!(
store.copy_if_not_exists(&staging, &finalized).await,
Err(Error::AlreadyExists { .. } | Error::Precondition { .. })
));
let non_manifest = Path::from("data/existing.lance");
secondary
.copy_if_not_exists(&staging, &non_manifest)
.await
.unwrap();
assert!(matches!(
store.copy_if_not_exists(&staging, &non_manifest).await,
Err(Error::AlreadyExists { .. } | Error::Precondition { .. })
));
assert!(matches!(
primary.head(&non_manifest).await,
Err(Error::NotFound { .. })
));
}
// This test is ignored because lance 3.0 introduced LocalWriter optimization
// that bypasses the object store wrapper for local writes. The mirroring feature
// still works for remote/cloud storage, but can't be tested with local storage.
+106 -201
View File
@@ -50,6 +50,7 @@ use crate::DistanceType;
use crate::blob::BlobRangeRequest;
use crate::data::scannable::{PeekedScannable, Scannable, estimate_write_partitions};
use crate::database::Database;
use crate::database::listing::LANCE_FILE_EXTENSION;
use crate::database::read_freshness::TableFreshness;
use crate::embeddings::{EmbeddingDefinition, EmbeddingRegistry, MemoryRegistry};
use crate::error::{Error, Result};
@@ -151,6 +152,55 @@ pub(crate) fn map_namespace_lance_error(err: lance::Error, table_name: &str) ->
}
}
/// Map a `lance::Error::DatasetNotFound` for the table at `uri` into a `lancedb::Error`.
///
/// Lance reports "there is nothing at this location" and "there is a table directory
/// here but nothing loadable inside it" with the same error. Only the first is a
/// `TableNotFound`: a `<name>.lance` directory left behind by an interrupted drop and
/// re-create is still reported by `Connection::table_names`, so callers need to be able
/// to tell "never existed" from "exists but is broken".
///
/// See <https://github.com/lancedb/lancedb/issues/3127>.
async fn map_dataset_not_found(
uri: &str,
name: &str,
params: ReadParams,
err: lance::Error,
) -> Error {
let name = name.to_string();
let source = Box::new(err);
if table_dir_exists(uri, params).await.unwrap_or(false) {
Error::TableCorrupted { name, source }
} else {
Error::TableNotFound { name, source }
}
}
/// Whether a table directory is present at `uri`, even though no dataset could be
/// loaded from it.
///
/// This looks for a `<name>.lance` entry in the parent directory, which is exactly what
/// `ListingDatabase::table_names` lists, so the two APIs agree on whether a table is
/// present. Probing `uri` itself would not work: object stores have no empty
/// directories to probe, and on a local filesystem the interesting case is precisely an
/// empty directory.
async fn table_dir_exists(uri: &str, params: ReadParams) -> Result<bool> {
let (object_store, path, _) = DatasetBuilder::from_uri(uri)
.with_read_params(params)
.build_object_store()
.await?;
// Only `*.lance` entries are ever reported as tables, so nothing else can produce
// the list-then-open mismatch this guards against.
if path.extension() != Some(LANCE_FILE_EXTENSION) {
return Ok(false);
}
let (Some(parent), Some(dir_name)) = (path.parent(), path.filename()) else {
return Ok(false);
};
let entries = object_store.read_dir(parent).await?;
Ok(entries.iter().any(|entry| entry.as_str() == dir_name))
}
/// Defines the type of column
#[derive(Debug, Clone, Serialize, Deserialize)]
pub enum ColumnKind {
@@ -2370,6 +2420,8 @@ impl NativeTable {
None => false,
};
// Kept so that a `DatasetNotFound` can be re-checked against storage below.
let recovery_params = params.clone();
let mut builder = DatasetBuilder::from_uri(uri).with_read_params(params);
// Set up commit handler when managed_versioning is enabled
@@ -2388,12 +2440,7 @@ impl NativeTable {
let dataset = match builder.load().await {
Ok(dataset) => dataset,
Err(e @ lance::Error::DatasetNotFound { .. }) => {
// The manifest load is the existence check. A physical prefix may be
// from a concurrent or abandoned create, so it cannot refine this error.
return Err(Error::TableNotFound {
name: name.to_string(),
source: Box::new(e),
});
return Err(map_dataset_not_found(uri, name, recovery_params, e).await);
}
Err(e) => return Err(e.into()),
};
@@ -3661,7 +3708,7 @@ pub struct FragmentSummaryStats {
#[allow(deprecated)]
mod tests {
use std::sync::Arc;
use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
use std::sync::atomic::{AtomicBool, Ordering};
use std::time::Duration;
use arrow_array::{
@@ -3743,50 +3790,73 @@ mod tests {
);
}
#[tokio::test]
async fn test_open_not_found_when_empty_directory_exists() {
let tmp_dir = tempdir().unwrap();
let dataset_path = tmp_dir.path().join("test.lance");
std::fs::create_dir(&dataset_path).unwrap();
/// Write a table and then break it, leaving the `<name>.lance` directory in place.
///
/// `remove_all` reproduces an interrupted drop + re-create (the directory is left
/// empty); otherwise only the manifests are removed, leaving the data files behind.
async fn write_then_corrupt_table(dir: &std::path::Path, remove_all: bool) -> String {
let dataset_path = dir.join("test.lance");
let uri = dataset_path.to_str().unwrap().to_string();
let err = NativeTable::open(dataset_path.to_str().unwrap())
.await
.unwrap_err();
let batch = make_test_batches();
let reader = RecordBatchIterator::new(vec![Ok(batch.clone())], batch.schema());
Dataset::write(reader, &uri, None).await.unwrap();
if remove_all {
for entry in std::fs::read_dir(&dataset_path).unwrap() {
let entry = entry.unwrap();
if entry.file_type().unwrap().is_dir() {
std::fs::remove_dir_all(entry.path()).unwrap();
} else {
std::fs::remove_file(entry.path()).unwrap();
}
}
assert_eq!(std::fs::read_dir(&dataset_path).unwrap().count(), 0);
} else {
let versions = dataset_path.join("_versions");
assert!(versions.is_dir(), "expected manifests under {versions:?}");
std::fs::remove_dir_all(&versions).unwrap();
assert!(std::fs::read_dir(&dataset_path).unwrap().count() > 0);
}
uri
}
#[tokio::test]
async fn test_open_corrupt_empty_dir() {
let tmp_dir = tempdir().unwrap();
let uri = write_then_corrupt_table(tmp_dir.path(), true).await;
let err = NativeTable::open(&uri).await.unwrap_err();
assert!(
matches!(&err, Error::TableNotFound { name, .. } if name == "test"),
matches!(&err, Error::TableCorrupted { name, .. } if name == "test"),
"got {err:?}"
);
}
#[tokio::test]
async fn test_open_not_found_when_only_uncommitted_storage_exists() {
async fn test_open_corrupt_missing_manifest() {
let tmp_dir = tempdir().unwrap();
let dataset_path = tmp_dir.path().join("test.lance");
let data_dir = dataset_path.join("data");
std::fs::create_dir_all(&data_dir).unwrap();
std::fs::write(data_dir.join("orphan.lance"), b"uncommitted").unwrap();
let uri = write_then_corrupt_table(tmp_dir.path(), false).await;
let err = NativeTable::open(dataset_path.to_str().unwrap())
.await
.unwrap_err();
let err = NativeTable::open(&uri).await.unwrap_err();
assert!(
matches!(&err, Error::TableNotFound { name, .. } if name == "test"),
matches!(&err, Error::TableCorrupted { name, .. } if name == "test"),
"got {err:?}"
);
}
/// Listing databases discover physical `*.lance` entries. That snapshot is not an
/// authoritative table-existence check: only a committed manifest makes a table
/// openable, and the entry could also be concurrently created or dropped.
/// A table listed by `table_names()` must not be reported as missing by
/// `open_table()`. See <https://github.com/lancedb/lancedb/issues/3127>.
#[tokio::test]
async fn test_table_names_may_include_uncommitted_storage() {
async fn test_open_table_corrupt_is_still_listed() {
let tmp_dir = tempdir().unwrap();
let db = connect(tmp_dir.path().to_str().unwrap())
.execute()
.await
.unwrap();
std::fs::create_dir(tmp_dir.path().join("test.lance")).unwrap();
write_then_corrupt_table(tmp_dir.path(), true).await;
assert_eq!(
db.table_names().execute().await.unwrap(),
@@ -3794,177 +3864,12 @@ mod tests {
);
let err = db.open_table("test").execute().await.unwrap_err();
assert!(
matches!(&err, Error::TableNotFound { name, .. } if name == "test"),
"physical storage without a committed manifest is not a table: {err:?}"
);
}
#[derive(Debug)]
struct ParentListGuardStore {
inner: Arc<dyn object_store::ObjectStore>,
parent: object_store::path::Path,
parent_list_calls: Arc<AtomicUsize>,
}
impl std::fmt::Display for ParentListGuardStore {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_str("ParentListGuardStore")
}
}
#[async_trait::async_trait]
#[deny(clippy::missing_trait_methods)]
impl object_store::ObjectStore for ParentListGuardStore {
async fn put_opts(
&self,
location: &object_store::path::Path,
payload: object_store::PutPayload,
opts: object_store::PutOptions,
) -> object_store::Result<object_store::PutResult> {
self.inner.put_opts(location, payload, opts).await
}
async fn put_multipart_opts(
&self,
location: &object_store::path::Path,
opts: object_store::PutMultipartOptions,
) -> object_store::Result<Box<dyn object_store::MultipartUpload>> {
self.inner.put_multipart_opts(location, opts).await
}
async fn get_opts(
&self,
location: &object_store::path::Path,
options: object_store::GetOptions,
) -> object_store::Result<object_store::GetResult> {
self.inner.get_opts(location, options).await
}
async fn get_ranges(
&self,
location: &object_store::path::Path,
ranges: &[std::ops::Range<u64>],
) -> object_store::Result<Vec<bytes::Bytes>> {
self.inner.get_ranges(location, ranges).await
}
fn delete_stream(
&self,
locations: futures::stream::BoxStream<
'static,
object_store::Result<object_store::path::Path>,
>,
) -> futures::stream::BoxStream<'static, object_store::Result<object_store::path::Path>>
{
self.inner.delete_stream(locations)
}
fn list(
&self,
prefix: Option<&object_store::path::Path>,
) -> futures::stream::BoxStream<'static, object_store::Result<object_store::ObjectMeta>>
{
if prefix == Some(&self.parent) {
self.parent_list_calls.fetch_add(1, Ordering::Relaxed);
}
self.inner.list(prefix)
}
fn list_with_offset(
&self,
prefix: Option<&object_store::path::Path>,
offset: &object_store::path::Path,
) -> futures::stream::BoxStream<'static, object_store::Result<object_store::ObjectMeta>>
{
if prefix == Some(&self.parent) {
self.parent_list_calls.fetch_add(1, Ordering::Relaxed);
}
self.inner.list_with_offset(prefix, offset)
}
async fn list_with_delimiter(
&self,
prefix: Option<&object_store::path::Path>,
) -> object_store::Result<object_store::ListResult> {
if prefix == Some(&self.parent) {
self.parent_list_calls.fetch_add(1, Ordering::Relaxed);
}
self.inner.list_with_delimiter(prefix).await
}
async fn copy_opts(
&self,
from: &object_store::path::Path,
to: &object_store::path::Path,
options: object_store::CopyOptions,
) -> object_store::Result<()> {
self.inner.copy_opts(from, to, options).await
}
async fn rename_opts(
&self,
from: &object_store::path::Path,
to: &object_store::path::Path,
options: object_store::RenameOptions,
) -> object_store::Result<()> {
self.inner.rename_opts(from, to, options).await
}
}
#[derive(Debug)]
struct ParentListGuardWrapper {
parent_list_calls: Arc<AtomicUsize>,
}
impl WrappingObjectStore for ParentListGuardWrapper {
fn wrap(
&self,
_store_prefix: &str,
inner: Arc<dyn object_store::ObjectStore>,
) -> Arc<dyn object_store::ObjectStore> {
Arc::new(ParentListGuardStore {
inner,
parent: object_store::path::Path::from("database"),
parent_list_calls: self.parent_list_calls.clone(),
})
}
}
#[tokio::test]
async fn test_open_missing_never_lists_database_parent() {
let parent_list_calls = Arc::new(AtomicUsize::new(0));
let params = ReadParams {
store_options: Some(ObjectStoreParams {
object_store_wrapper: Some(Arc::new(ParentListGuardWrapper {
parent_list_calls: parent_list_calls.clone(),
})),
..Default::default()
}),
..Default::default()
};
let err = NativeTable::open_with_params(
"memory:///database/missing.lance",
"missing",
Vec::new(),
None,
Some(params),
None,
None,
HashSet::new(),
None,
)
.await
.unwrap_err();
assert!(
matches!(&err, Error::TableNotFound { name, .. } if name == "missing"),
matches!(&err, Error::TableCorrupted { name, .. } if name == "test"),
"got {err:?}"
);
assert_eq!(
parent_list_calls.load(Ordering::Relaxed),
0,
"opening one missing table must not enumerate sibling tables"
assert!(
err.to_string().contains("exists but could not be loaded"),
"got {err}"
);
}
@@ -5434,7 +5339,7 @@ mod tests {
pub async fn test_stats_includes_index_and_overlay_files() {
use lance::dataset::WriteDestination;
use lance::dataset::transaction::{DataOverlayGroup, Operation};
use lance_file::version::stable_file_version;
use lance_file::version::{ConcreteFileVersion, LanceFileVersion};
use lance_file::writer::FileWriterOptions;
use lance_io::utils::CachedFileSize;
use lance_table::format::DataFile;
@@ -5500,7 +5405,7 @@ mod tests {
let fragment_id = dataset.get_fragments()[0].id() as u64;
let foo_field_id = dataset.schema().field("foo").unwrap().id;
let overlay_schema = dataset.schema().project_by_ids(&[foo_field_id], true);
let file_version = stable_file_version();
let file_version = ConcreteFileVersion::from(LanceFileVersion::Stable);
let filename = "overlay.lance".to_string();
let store = dataset.object_store(None).await.unwrap();
+13 -18
View File
@@ -10,7 +10,7 @@ use arrow_array::{
use arrow_schema::{DataType, Field, Fields, Schema};
use futures::TryStreamExt;
use lance::Dataset;
use lance_file::version::{ConcreteFileVersion, LanceFileVersion};
use lance_file::version::LanceFileVersion;
use lancedb::{
Connection, Error, Result, Table,
blob::{BlobRangeRequest, blob},
@@ -61,7 +61,7 @@ async fn create_inline_blob_table(
Ok(table)
}
async fn storage_format_version(table: &Table) -> ConcreteFileVersion {
async fn storage_format_version(table: &Table) -> LanceFileVersion {
table
.as_native()
.unwrap()
@@ -69,14 +69,9 @@ async fn storage_format_version(table: &Table) -> ConcreteFileVersion {
.await
.unwrap()
.data_storage_format
.lance_file_format()
}
fn supports_blob_v2(version: ConcreteFileVersion) -> bool {
matches!(
version,
ConcreteFileVersion::V2_2 | ConcreteFileVersion::V2_3
)
.lance_file_version()
.unwrap()
.resolve()
}
async fn uses_stable_row_ids(table: &Table) -> bool {
@@ -117,7 +112,7 @@ async fn declaring_blob_column_bumps_format_and_enables_stable_row_ids() -> Resu
.execute()
.await?;
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(uses_stable_row_ids(&table).await);
Ok(())
}
@@ -132,7 +127,7 @@ async fn explicit_stable_row_id_setting_wins_over_blob_default() -> Result<()> {
.execute()
.await?;
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(!uses_stable_row_ids(&table).await);
Ok(())
}
@@ -144,7 +139,7 @@ async fn non_blob_table_keeps_default_format_and_row_id_setting() -> Result<()>
let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int64, false)]));
let table = db.create_empty_table("t", schema).execute().await?;
assert!(!supports_blob_v2(storage_format_version(&table).await));
assert!(storage_format_version(&table).await < LanceFileVersion::V2_2);
assert!(!uses_stable_row_ids(&table).await);
Ok(())
}
@@ -176,7 +171,7 @@ async fn creating_with_blob_data_bumps_format() -> Result<()> {
.unwrap();
let table = db.create_table("t", batch).execute().await?;
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(uses_stable_row_ids(&table).await);
assert_eq!(table.count_rows(None).await?, 1);
Ok(())
@@ -286,7 +281,7 @@ async fn connection_level_stable_row_id_setting_wins_over_blob_default() -> Resu
.execute()
.await?;
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(!uses_stable_row_ids(&table).await);
Ok(())
}
@@ -302,7 +297,7 @@ async fn namespace_create_applies_blob_defaults() -> Result<()> {
.execute()
.await?;
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(uses_stable_row_ids(&table).await);
Ok(())
}
@@ -479,7 +474,7 @@ async fn fetch_blobs_round_trips_nested_blob_column() -> Result<()> {
let batch = RecordBatch::try_new(schema, vec![Arc::new(info_array) as ArrayRef]).unwrap();
let table = db.create_table("t", batch).execute().await?;
assert!(supports_blob_v2(storage_format_version(&table).await));
assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2);
assert!(uses_stable_row_ids(&table).await);
let ids = collect_row_ids(&table).await?;
@@ -1310,7 +1305,7 @@ async fn optimize_preserves_blob_v2_null_and_empty_distinction() -> Result<()> {
.await?;
table.add(null_empty_input_batch()).execute().await?;
assert!(
supports_blob_v2(storage_format_version(&table).await),
storage_format_version(&table).await >= LanceFileVersion::V2_2,
"blob v2 columns require storage >= 2.2"
);