Compare commits

..

1 Commits

Author SHA1 Message Date
Lance Release e600f000b3 Bump version: 0.38.0-beta.14 → 0.38.0-beta.15 2026-08-31 07:33:01 +00:00
22 changed files with 148 additions and 221 deletions
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.38.0"
current_version = "0.38.0-beta.15"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
Generated
+45 -68
View File
@@ -3455,9 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
[[package]]
name = "fsst"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f727719438dfdb74f358a347c91ff81b6e7084a6421f34de3e473ce271f10caa"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"rand 0.9.5",
@@ -4816,9 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
[[package]]
name = "lance"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "be781f40c7a75f9eae2188a2f71174acb7a360dca97163db40b041d0828dea48"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arc-swap",
"arrow",
@@ -4890,9 +4888,8 @@ dependencies = [
[[package]]
name = "lance-arrow"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fb97fd9875f3036d7c2561aa5b16eb87b80ccabaa4eeb5e6099b19cc662f1cd8"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4914,8 +4911,7 @@ dependencies = [
[[package]]
name = "lance-arrow-scalar"
version = "58.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "771f68b04b47f3addf781116f65061808de94b05e1e9411c23c18f32d14ebe79"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4929,20 +4925,17 @@ dependencies = [
[[package]]
name = "lance-arrow-stats"
version = "58.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dd47ec33c90bf29f688fd02118e37d3a5ad5c339caa3163f89e417dc0867001f"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-schema",
"half",
"lance-arrow-scalar",
]
[[package]]
name = "lance-bitpacking"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6f45658c5b2dc9aada41b66ee44b83af3fa888b7385ae414bae951b12a9f1cd3"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrayref",
"crunchy",
@@ -4952,9 +4945,8 @@ dependencies = [
[[package]]
name = "lance-core"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "27af3df3a7d08897efccd04461df31cedf0880c4b86a055ddce48e423d27f967"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -4991,9 +4983,8 @@ dependencies = [
[[package]]
name = "lance-datafusion"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c377f837df5296e92f9fad724c83c1bef4e74d5af6e5a9312e9307e1dead8614"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow",
"arrow-array",
@@ -5022,9 +5013,8 @@ dependencies = [
[[package]]
name = "lance-datagen"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "778e1a5065fa4bc184e36e32681f10f8f4680ad8cedc9377b4c088dce8c5b8da"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow",
"arrow-array",
@@ -5041,9 +5031,8 @@ dependencies = [
[[package]]
name = "lance-derive"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13e5e95e0fd3d74f7938f4bee623041421b323b5c61f242c8622a1f48a202527"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"proc-macro2",
"quote",
@@ -5052,9 +5041,8 @@ dependencies = [
[[package]]
name = "lance-encoding"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1625653c55c65f3426e281f6e29b54c603f38a40bd4cebd707bd4f3ea48be6c5"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5087,9 +5075,8 @@ dependencies = [
[[package]]
name = "lance-file"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b7e13c9266b478fc98f36ee19347c4658f7a6613fed77778b1a455fe1b88552e"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5120,9 +5107,8 @@ dependencies = [
[[package]]
name = "lance-index"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b0e0cb95f2c4f341c4dd04ac60f6a89ea26a6f75e09570225cbda4854c8b088e"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arc-swap",
"arrow",
@@ -5186,9 +5172,8 @@ dependencies = [
[[package]]
name = "lance-index-core"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "79ccd371977c1f7168da259d66ad37154f23146f093d46136bc7f79559f00f2c"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5210,9 +5195,8 @@ dependencies = [
[[package]]
name = "lance-io"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "414d50997391b1ac83dc183c1612fdff88f58b959806078dc4c5e465154566de"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow",
"arrow-array",
@@ -5252,9 +5236,8 @@ dependencies = [
[[package]]
name = "lance-linalg"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ff55b152ef23a56d7ba7e4d1b2c9cf0cc79aef6ee607c115597557ea4059f41"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5268,9 +5251,8 @@ dependencies = [
[[package]]
name = "lance-namespace"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09991c13ab282b731e323619613914e08da9cc82b312f904e58c128b23f2f0e3"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow",
"async-trait",
@@ -5282,9 +5264,8 @@ dependencies = [
[[package]]
name = "lance-namespace-impls"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0ec0bc005f6bb8f120774eb4a9ba02e10463d8338167a46cbb1391d46680a174"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow",
"arrow-ipc",
@@ -5337,9 +5318,8 @@ dependencies = [
[[package]]
name = "lance-select"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e8f676a2a1837cc85b77feb5326d3296827da964e40d67144f646563302a6ce9"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5353,9 +5333,8 @@ dependencies = [
[[package]]
name = "lance-table"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bd33054347395048b1d842dfb85a13f7801392c2da5f39425db62f00a481744b"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow",
"arrow-array",
@@ -5395,9 +5374,8 @@ dependencies = [
[[package]]
name = "lance-testing"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ecc9ad9ae24f045dfddd538a39e55a28fa7e1ca6ad9f23e20d4087eaf2bb66f7"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5410,9 +5388,8 @@ dependencies = [
[[package]]
name = "lance-tokenizer"
version = "11.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3bfa6f0164c8b7056150f5682ce4d415a335b59b04c479873fda04b200117d27"
version = "12.0.0-beta.5"
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.5#556637791d0048c2b4f1342dd84b67c8bbd65259"
dependencies = [
"frostem",
"icu_segmenter",
@@ -5425,7 +5402,7 @@ dependencies = [
[[package]]
name = "lancedb"
version = "0.38.0-beta.15"
version = "0.38.0-beta.14"
dependencies = [
"ahash",
"anyhow",
@@ -5513,7 +5490,7 @@ dependencies = [
[[package]]
name = "lancedb-nodejs"
version = "0.38.0-beta.15"
version = "0.38.0-beta.14"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5538,7 +5515,7 @@ dependencies = [
[[package]]
name = "lancedb-python"
version = "0.38.0-beta.15"
version = "0.38.0-beta.14"
dependencies = [
"arrow",
"async-trait",
+14 -14
View File
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=11.0.0", default-features = false }
lance-core = "=11.0.0"
lance-datagen = "=11.0.0"
lance-file = "=11.0.0"
lance-io = { "version" = "=11.0.0", default-features = false }
lance-index = "=11.0.0"
lance-linalg = "=11.0.0"
lance-namespace = "=11.0.0"
lance-namespace-impls = { "version" = "=11.0.0", default-features = false }
lance-table = "=11.0.0"
lance-testing = "=11.0.0"
lance-datafusion = "=11.0.0"
lance-encoding = "=11.0.0"
lance-arrow = "=11.0.0"
lance = { "version" = "=12.0.0-beta.5", default-features = false, "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=12.0.0-beta.5", default-features = false, "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=12.0.0-beta.5", default-features = false, "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { "version" = "=12.0.0-beta.5", "tag" = "v12.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
lancedb = { path = "rust/lancedb", default-features = false }
ahash = "0.8"
# Note that this one does not include pyarrow
+1 -1
View File
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
<dependency>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-core</artifactId>
<version>0.38.0</version>
<version>0.38.0-beta.15</version>
</dependency>
```
+1 -1
View File
@@ -8,7 +8,7 @@
<parent>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.38.0-final.0</version>
<version>0.38.0-beta.15</version>
<relativePath>../pom.xml</relativePath>
</parent>
+2 -2
View File
@@ -6,7 +6,7 @@
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.38.0-final.0</version>
<version>0.38.0-beta.15</version>
<packaging>pom</packaging>
<name>${project.artifactId}</name>
<description>LanceDB Java SDK Parent POM</description>
@@ -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</lance-core.version>
<lance-core.version>12.0.0-beta.5</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>
+1 -1
View File
@@ -1,7 +1,7 @@
[package]
name = "lancedb-nodejs"
edition.workspace = true
version = "0.38.0"
version = "0.38.0-beta.15"
publish = false
license.workspace = true
description.workspace = true
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-arm64",
"version": "0.38.0",
"version": "0.38.0-beta.15",
"os": ["darwin"],
"cpu": ["arm64"],
"main": "lancedb.darwin-arm64.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-gnu",
"version": "0.38.0",
"version": "0.38.0-beta.15",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-musl",
"version": "0.38.0",
"version": "0.38.0-beta.15",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-gnu",
"version": "0.38.0",
"version": "0.38.0-beta.15",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-gnu.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-musl",
"version": "0.38.0",
"version": "0.38.0-beta.15",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-musl.node",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-arm64-msvc",
"version": "0.38.0",
"version": "0.38.0-beta.15",
"os": [
"win32"
],
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-x64-msvc",
"version": "0.38.0",
"version": "0.38.0-beta.15",
"os": ["win32"],
"cpu": ["x64"],
"main": "lancedb.win32-x64-msvc.node",
+1 -1
View File
@@ -11,7 +11,7 @@
"ann"
],
"private": false,
"version": "0.38.0",
"version": "0.38.0-beta.15",
"main": "dist/index.js",
"exports": {
".": "./dist/index.js",
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb-python"
version = "0.38.0"
version = "0.38.0-beta.15"
publish = false
edition.workspace = true
description = "Python bindings for LanceDB"
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb"
version = "0.38.0"
version = "0.38.0-beta.15"
edition.workspace = true
description = "LanceDB: A serverless, low-latency vector database for AI applications"
license.workspace = true
+38 -120
View File
@@ -13,7 +13,7 @@ use lance::dataset::{ReadParams, WriteMode, builder::DatasetBuilder};
use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
use lance_datafusion::utils::StreamingWriteSource;
use lance_file::version::LanceFileVersion;
use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
use lance_io::object_store::{ReadDirOptions, StorageOptionsAccessor, StorageOptionsProvider};
use lance_table::io::commit::commit_handler_from_url;
use object_store::local::LocalFileSystem;
use snafu::ResultExt;
@@ -282,11 +282,14 @@ impl std::fmt::Display for ListingDatabase {
const LANCE_EXTENSION: &str = "lance";
/// The table a listed child directory holds, or `None` if it is not a table at all.
/// The table a listed child of the database names, or `None` if the child is not a table.
///
/// A table is the directory `<name>.lance`; a loose file or any other directory under the
/// database prefix belongs to something else. `dir_suffix` is `.lance`, built once by the
/// caller rather than per child.
/// The table a listed child directory holds, or `None` if it is not a table at all.
///
/// Only directories are considered, so a loose object named like a table is not one.
fn table_name(location: &object_store::path::Path, dir_suffix: &str) -> Option<String> {
location
.filename()?
@@ -294,75 +297,6 @@ fn table_name(location: &object_store::path::Path, dir_suffix: &str) -> Option<S
.map(String::from)
.filter(|name| !name.is_empty())
}
/// One page of the table directories under the database directory, in key order.
struct DirPage {
/// The table directories the page holds, as the store lists them.
common_prefixes: Vec<object_store::path::Path>,
/// Resumes after this page, or `None` when the page reached the end of the level.
page_token: Option<String>,
}
/// Where a listed location sits inside the database directory — the space page tokens live
/// in — or `None` if it is not a child of that directory at all. Matching both halves of the
/// prefix drops a location that merely starts with the directory's name (`dbx/y` against
/// `db/`) as well as the marker object some stores keep for the directory itself.
fn relative_key<'a>(prefix: Option<&str>, location: &'a str) -> Option<&'a str> {
let relative = match prefix {
Some(prefix) => location.strip_prefix(prefix)?,
None => location,
};
(!relative.is_empty()).then_some(relative)
}
/// One page of the table directories under `base_path`, one directory level deep.
///
/// Lance 11 exposes no paginated directory listing, so the level is listed in full and paged
/// locally: table directories go into key order (a directory's key keeps its trailing `/`,
/// so a token is never a table name), the page is the smallest `limit` of them past
/// `page_token`, and the token handed back is the key of the last directory the page took —
/// so a page that took nothing ends the listing rather than resuming from a position no page
/// ever reached. Only `<name>.lance/` directories enter the page: loose objects, other
/// directories, and a bare `.lance/` never take a page slot or name a token, which keeps a
/// page to exactly one listing of the level. Correct on every store, at the cost of that one
/// full-level listing per page.
async fn read_dir_page(
object_store: &ObjectStore,
base_path: &object_store::path::Path,
page_token: Option<String>,
limit: Option<usize>,
) -> Result<DirPage> {
let listed = object_store.list_with_delimiter(Some(base_path)).await?;
let prefix = {
let base = base_path.as_ref();
(!base.is_empty()).then(|| format!("{base}/"))
};
let table_dir_suffix = format!(".{LANCE_EXTENSION}/");
let mut children: Vec<(String, object_store::path::Path)> = listed
.common_prefixes
.into_iter()
.filter_map(|location| {
let key = format!("{}/", relative_key(prefix.as_deref(), location.as_ref())?);
(key.len() > table_dir_suffix.len() && key.ends_with(&table_dir_suffix))
.then_some((key, location))
})
.collect();
children.sort_unstable_by(|(left, _), (right, _)| left.cmp(right));
if let Some(resume) = &page_token {
children.retain(|(key, _)| key > resume);
}
let total = children.len();
children.truncate(limit.unwrap_or(total).min(total));
let page_token = match children.last() {
Some((last, _)) if children.len() < total => Some(last.clone()),
_ => None,
};
Ok(DirPage {
common_prefixes: children.into_iter().map(|(_, location)| location).collect(),
page_token,
})
}
const ENGINE: &str = "engine";
const MIRRORED_STORE: &str = "mirroredStore";
@@ -1048,7 +982,8 @@ impl Database for ListingDatabase {
let mut tables = Vec::new();
let mut page_token = request.page_token.filter(|token| !token.is_empty());
// A page of nothing: no table was handed over for a token to resume after.
// A page of nothing: the store rejects a limit of zero, and no table was handed over
// for a token to resume after.
if limit == Some(0) {
return Ok(ListTablesResponse {
context: None,
@@ -1057,21 +992,35 @@ impl Database for ListingDatabase {
});
}
// The page holds only table directories, so one call — and the one full-level
// listing behind it — fills it.
let page = read_dir_page(
&self.object_store,
&self.base_path,
page_token.take(),
limit,
)
.await?;
page_token = page.page_token;
tables.extend(
page.common_prefixes
.iter()
.filter_map(|location| table_name(location, &dir_suffix)),
);
loop {
// Ask only for what the page still has room for, so a database holding more
// than one page costs one request per page rather than one per table.
let listing = self
.object_store
.read_dir_page(
self.base_path.clone(),
ReadDirOptions {
page_token: page_token.take(),
limit: limit.map(|limit| limit - tables.len()),
},
)
.await?;
page_token = listing.page_token;
// Only child directories can be tables, and the store already separates them
// out, so the objects in the page are not looked at.
tables.extend(
listing
.result
.common_prefixes
.iter()
.filter_map(|location| table_name(location, &dir_suffix)),
);
// Children that are not tables leave the page short of the limit, so keep
// going until the page is full or the database runs out.
if page_token.is_none() || limit.is_none_or(|limit| tables.len() >= limit) {
break;
}
}
Ok(ListTablesResponse {
context: None,
@@ -1717,8 +1666,8 @@ mod tests {
}
/// Only directories named `<name>.lance` are tables; loose files and other directories
/// under the database prefix are not. They never take a page slot, so even a `limit`
/// smaller than the clutter ahead of the first table returns that table.
/// under the database prefix are not. A page spent on them is filled from the next one,
/// so a page holding only non-tables does not read as an empty database.
#[tokio::test]
async fn test_listing_ignores_non_table_children() {
let (tempdir, db) = setup_database().await;
@@ -1737,37 +1686,6 @@ mod tests {
assert_eq!(page.tables, vec!["real"]);
}
/// The Lance 11 fallback pages locally over one full-level listing, so a bounded page
/// costs exactly one listing call — clutter ahead of the first table must not buy extra
/// round trips.
#[tokio::test]
async fn test_one_full_listing_per_public_page() {
use crate::io::object_store::io_tracking::IoStatsHolder;
use lance_io::object_store::WrappingObjectStore;
let (tempdir, mut db) = setup_database().await;
create_tables(&db, &["real"]).await;
std::fs::write(tempdir.path().join("aaa-loose.lance"), b"not a table").unwrap();
create_dir_all(tempdir.path().join("aaa-scratch")).unwrap();
let io_stats = IoStatsHolder::default();
let mut tracked_store = (*db.object_store).clone();
tracked_store.inner =
io_stats.wrap(&tracked_store.store_prefix, tracked_store.inner.clone());
db.object_store = Arc::new(tracked_store);
let page = db
.list_tables(ListTablesRequest {
limit: Some(1),
..Default::default()
})
.await
.unwrap();
assert_eq!(page.tables, vec!["real"]);
assert_eq!(io_stats.incremental_stats().read_iops, 1);
}
#[tokio::test]
async fn listing_ignores_empty_table_name() {
let (tempdir, db) = setup_database().await;
+9 -1
View File
@@ -10,7 +10,7 @@ use lance::io::WrappingObjectStore;
use object_store::{
CopyOptions, Error, GetOptions, GetResult, ListResult, MultipartUpload, ObjectMeta,
ObjectStore, ObjectStoreExt, PutMultipartOptions, PutOptions, PutPayload, PutResult, Result,
UploadPart, path::Path,
UploadPart, list::PaginatedListStore, path::Path,
};
use async_trait::async_trait;
@@ -187,6 +187,14 @@ impl WrappingObjectStore for MirroringObjectStoreWrapper {
secondary: self.secondary.clone(),
})
}
fn wrap_paginated(
&self,
_store_prefix: &str,
original: Arc<dyn PaginatedListStore>,
) -> Option<Arc<dyn PaginatedListStore>> {
Some(original)
}
}
// windows pathing can't be simply concatenated
@@ -12,7 +12,7 @@ use lance::io::WrappingObjectStore;
use object_store::{
CopyOptions, GetOptions, GetResult, ListResult, MultipartUpload, ObjectMeta, ObjectStore,
PutMultipartOptions, PutOptions, PutPayload, PutResult, RenameOptions, Result as OSResult,
UploadPart, path::Path,
UploadPart, list::PaginatedListStore, path::Path,
};
#[derive(Debug, Default)]
@@ -57,6 +57,14 @@ impl WrappingObjectStore for IoStatsHolder {
stats: self.0.clone(),
})
}
fn wrap_paginated(
&self,
_store_prefix: &str,
original: Arc<dyn PaginatedListStore>,
) -> Option<Arc<dyn PaginatedListStore>> {
Some(original)
}
}
impl IoTrackingStore {
+16
View File
@@ -4183,6 +4183,14 @@ mod tests {
parent_list_calls: self.parent_list_calls.clone(),
})
}
fn wrap_paginated(
&self,
_store_prefix: &str,
_original: Arc<dyn object_store::list::PaginatedListStore>,
) -> Option<Arc<dyn object_store::list::PaginatedListStore>> {
None
}
}
#[tokio::test]
@@ -4286,6 +4294,14 @@ mod tests {
self.called.store(true, Ordering::Relaxed);
original
}
fn wrap_paginated(
&self,
_store_prefix: &str,
original: Arc<dyn object_store::list::PaginatedListStore>,
) -> Option<Arc<dyn object_store::list::PaginatedListStore>> {
Some(original)
}
}
#[tokio::test]
+1 -1
View File
@@ -300,7 +300,7 @@ async fn build_read_context(
for shard_id in shard_ids {
let manifest_store =
ShardManifestStore::new(store.clone(), &base_path, shard_id, scan_batch_size);
if let Some(manifest) = manifest_store.read_latest().await? {
if let Some(manifest) = manifest_store.latest().await? {
snapshots.push(snapshot_from_manifest(shard_id, &manifest, &exclude));
}
}