From 5638907fa5d2be1081fb62a3a482fe0afde8afdf Mon Sep 17 00:00:00 2001 From: Xuanwo Date: Sat, 30 May 2026 00:18:22 +0800 Subject: [PATCH] chore: update Lance to v7.2.0-beta.1 (#3461) Update the Rust workspace Lance git dependencies and Java lance-core dependency to v7.2.0-beta.1. This keeps LanceDB aligned with the latest Lance beta release and refreshes the Cargo lockfile for the new Lance dependency graph. --- Cargo.lock | 167 +++++++++++++----- Cargo.toml | 28 +-- java/pom.xml | 2 +- rust/lancedb/src/table/datafusion/udtf/fts.rs | 6 +- 4 files changed, 144 insertions(+), 59 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 1777d9591..c558506ca 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -1399,6 +1399,12 @@ dependencies = [ "syn 2.0.117", ] +[[package]] +name = "bytecount" +version = "0.6.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "175812e0be2bccb6abe50bb8d566126198344f707e304f45c648fd8f2cc0365e" + [[package]] name = "bytemuck" version = "1.25.0" @@ -1522,9 +1528,9 @@ dependencies = [ [[package]] name = "cedarwood" -version = "0.4.6" +version = "0.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6d910bedd62c24733263d0bed247460853c9d22e8956bd4cd964302095e04e90" +checksum = "c0524a528a6a0288df1863c3c20fe92c301875b4941e7b6c4b394ab08c5a4c55" dependencies = [ "smallvec", ] @@ -3284,8 +3290,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c" [[package]] name = "fsst" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-array", "rand 0.9.4", @@ -4077,6 +4083,21 @@ dependencies = [ "zerovec", ] +[[package]] +name = "icu_locale" +version = "2.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d5a396343c7208121dc86e35623d3dfe19814a7613cfd14964994cdc9c9a2e26" +dependencies = [ + "icu_collections", + "icu_locale_core", + "icu_locale_data", + "icu_provider", + "potential_utf", + "tinystr", + "zerovec", +] + [[package]] name = "icu_locale_core" version = "2.2.0" @@ -4085,11 +4106,18 @@ checksum = "92219b62b3e2b4d88ac5119f8904c10f8f61bf7e95b640d25ba3075e6cac2c29" dependencies = [ "displaydoc", "litemap", + "serde", "tinystr", "writeable", "zerovec", ] +[[package]] +name = "icu_locale_data" +version = "2.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d5fdcc9ac77c6d74ff5cf6e65ef3181d6af32003b16fce3a77fb451d2f695993" + [[package]] name = "icu_normalizer" version = "2.2.0" @@ -4138,6 +4166,8 @@ checksum = "139c4cf31c8b5f33d7e199446eff9c1e02decfc2f0eec2c8d71f65befa45b421" dependencies = [ "displaydoc", "icu_locale_core", + "serde", + "stable_deref_trait", "writeable", "yoke", "zerofrom", @@ -4145,6 +4175,27 @@ dependencies = [ "zerovec", ] +[[package]] +name = "icu_segmenter" +version = "2.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5c0794db0b1a86193ac9c48768d0e6c52c54448e0870ad87907d456ee0dac964" +dependencies = [ + "icu_collections", + "icu_locale", + "icu_provider", + "icu_segmenter_data", + "potential_utf", + "utf8_iter", + "zerovec", +] + +[[package]] +name = "icu_segmenter_data" +version = "2.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e4a2c462a4d927d512f5f882a033ddd62f33a05bb9f230d98f736ac3dc85938f" + [[package]] name = "id-arena" version = "2.3.0" @@ -4306,19 +4357,20 @@ checksum = "9028f49264629065d057f340a86acb84867925865f73bbf8d47b4d149a7e88b8" [[package]] name = "jieba-macros" -version = "0.9.0" +version = "0.10.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a29cfc5dcd898604c6f80363411fa6b6b08e27d1d253d6225b9cb6702ea02fc0" +checksum = "46adade69b634535a8f495cf87710ed893cff53e1dbc9dd750c2ab81c5defb82" dependencies = [ "phf_codegen 0.13.1", ] [[package]] name = "jieba-rs" -version = "0.9.0" +version = "0.10.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3245d6e9d1d5facbd6a23848d6b67e3439738ccbb4fa5a3d65da315ba1a910a2" +checksum = "11b53580aaa8ec8b713da271da434f8947409242c537a9ab3f7b76bdbb19e8a9" dependencies = [ + "bytecount", "cedarwood", "jieba-macros", "phf 0.13.1", @@ -4506,8 +4558,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a" [[package]] name = "lance" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arc-swap", "arrow", @@ -4580,8 +4632,8 @@ dependencies = [ [[package]] name = "lance-arrow" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-array", "arrow-buffer", @@ -4599,10 +4651,34 @@ dependencies = [ "rand 0.9.4", ] +[[package]] +name = "lance-arrow-scalar" +version = "58.0.0" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-cast", + "arrow-data", + "arrow-row", + "arrow-schema", + "half", +] + +[[package]] +name = "lance-arrow-stats" +version = "58.0.0" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" +dependencies = [ + "arrow-array", + "arrow-schema", + "lance-arrow-scalar", +] + [[package]] name = "lance-bitpacking" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrayref", "paste", @@ -4611,8 +4687,8 @@ dependencies = [ [[package]] name = "lance-core" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-array", "arrow-buffer", @@ -4647,8 +4723,8 @@ dependencies = [ [[package]] name = "lance-datafusion" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow", "arrow-array", @@ -4678,8 +4754,8 @@ dependencies = [ [[package]] name = "lance-datagen" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow", "arrow-array", @@ -4697,8 +4773,8 @@ dependencies = [ [[package]] name = "lance-encoding" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-arith", "arrow-array", @@ -4733,8 +4809,8 @@ dependencies = [ [[package]] name = "lance-file" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-arith", "arrow-array", @@ -4765,8 +4841,8 @@ dependencies = [ [[package]] name = "lance-index" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arc-swap", "arrow", @@ -4796,6 +4872,7 @@ dependencies = [ "jieba-rs", "jsonb", "lance-arrow", + "lance-arrow-stats", "lance-core", "lance-datafusion", "lance-datagen", @@ -4831,8 +4908,8 @@ dependencies = [ [[package]] name = "lance-io" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow", "arrow-arith", @@ -4874,8 +4951,8 @@ dependencies = [ [[package]] name = "lance-linalg" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-array", "arrow-buffer", @@ -4891,8 +4968,8 @@ dependencies = [ [[package]] name = "lance-namespace" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow", "async-trait", @@ -4904,8 +4981,8 @@ dependencies = [ [[package]] name = "lance-namespace-impls" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow", "arrow-ipc", @@ -4954,8 +5031,8 @@ dependencies = [ [[package]] name = "lance-select" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-array", "arrow-buffer", @@ -4969,8 +5046,8 @@ dependencies = [ [[package]] name = "lance-table" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow", "arrow-array", @@ -5010,8 +5087,8 @@ dependencies = [ [[package]] name = "lance-testing" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ "arrow-array", "arrow-schema", @@ -5022,9 +5099,10 @@ dependencies = [ [[package]] name = "lance-tokenizer" -version = "7.1.0-beta.4" -source = "git+https://github.com/lance-format/lance.git?tag=v7.1.0-beta.4#0c0b3e18c0a4c75bda1dd6ec9d6247ef75bd29d9" +version = "7.2.0-beta.1" +source = "git+https://github.com/lance-format/lance.git?tag=v7.2.0-beta.1#b9995aba6115e8e4bc43179a45cbd0f9a170f305" dependencies = [ + "icu_segmenter", "jieba-rs", "lindera", "rust-stemmers", @@ -6955,6 +7033,8 @@ version = "0.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0103b1cef7ec0cf76490e969665504990193874ea05c85ff9bab8b911d0a0564" dependencies = [ + "serde_core", + "writeable", "zerovec", ] @@ -9193,6 +9273,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c8323304221c2a851516f22236c5722a72eaa19749016521d6dff0824447d96d" dependencies = [ "displaydoc", + "serde_core", "zerovec", ] @@ -10661,6 +10742,7 @@ dependencies = [ "displaydoc", "yoke", "zerofrom", + "zerovec", ] [[package]] @@ -10669,6 +10751,7 @@ version = "0.11.6" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "90f911cbc359ab6af17377d242225f4d75119aec87ea711a880987b18cd7b239" dependencies = [ + "serde", "yoke", "zerofrom", "zerovec-derive", diff --git a/Cargo.toml b/Cargo.toml index 4cf9f2001..7ff946895 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -13,20 +13,20 @@ categories = ["database-implementations"] rust-version = "1.91.0" [workspace.dependencies] -lance = { "version" = "=7.1.0-beta.4", default-features = false, "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-core = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-datagen = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-file = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-io = { "version" = "=7.1.0-beta.4", default-features = false, "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-index = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-linalg = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace-impls = { "version" = "=7.1.0-beta.4", default-features = false, "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-table = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-testing = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-datafusion = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-encoding = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } -lance-arrow = { "version" = "=7.1.0-beta.4", "tag" = "v7.1.0-beta.4", "git" = "https://github.com/lance-format/lance.git" } +lance = { "version" = "=7.2.0-beta.1", default-features = false, "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-core = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-datagen = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-file = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-io = { "version" = "=7.2.0-beta.1", default-features = false, "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-index = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-linalg = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace-impls = { "version" = "=7.2.0-beta.1", default-features = false, "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-table = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-testing = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-datafusion = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-encoding = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "git" = "https://github.com/lance-format/lance.git" } +lance-arrow = { "version" = "=7.2.0-beta.1", "tag" = "v7.2.0-beta.1", "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 } diff --git a/java/pom.xml b/java/pom.xml index 317c48b3f..7b23cd52a 100644 --- a/java/pom.xml +++ b/java/pom.xml @@ -28,7 +28,7 @@ UTF-8 15.0.0 - 7.1.0-beta.4 + 7.2.0-beta.1 false 2.30.0 1.7 diff --git a/rust/lancedb/src/table/datafusion/udtf/fts.rs b/rust/lancedb/src/table/datafusion/udtf/fts.rs index 5b50ddfa3..8b79ca676 100644 --- a/rust/lancedb/src/table/datafusion/udtf/fts.rs +++ b/rust/lancedb/src/table/datafusion/udtf/fts.rs @@ -870,8 +870,10 @@ mod tests { .await .unwrap(); - // Should return empty or nearly empty result - assert!(result[0].num_rows() <= 1); + assert_eq!( + result.iter().map(|batch| batch.num_rows()).sum::(), + 0 + ); } #[tokio::test]