diff --git a/.bumpversion.toml b/.bumpversion.toml index de5f91973..a2c5fdd61 100644 --- a/.bumpversion.toml +++ b/.bumpversion.toml @@ -1,5 +1,5 @@ [tool.bumpversion] -current_version = "0.39.0-beta.6" +current_version = "0.39.0-beta.7" parse = """(?x) (?P0|[1-9]\\d*)\\. (?P0|[1-9]\\d*)\\. diff --git a/Cargo.lock b/Cargo.lock index 3afa04044..be5040d37 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -141,7 +141,7 @@ version = "1.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc" dependencies = [ - "windows-sys 0.61.2", + "windows-sys 0.60.2", ] [[package]] @@ -152,7 +152,7 @@ checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d" dependencies = [ "anstyle", "once_cell_polyfill", - "windows-sys 0.61.2", + "windows-sys 0.60.2", ] [[package]] @@ -581,6 +581,16 @@ dependencies = [ "loom", ] +[[package]] +name = "asyncband" +version = "0.6.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94a214ba60d6231afd0e805e3c27c45a1626d9debaa5a5061c45a1ea1b2f1ed0" +dependencies = [ + "hashbrown 0.17.1", + "slab", +] + [[package]] name = "atoi" version = "2.0.0" @@ -937,7 +947,7 @@ dependencies = [ "http 1.5.0", "http-body 1.1.0", "http-body-util", - "md-5 0.11.0", + "md-5", "pin-project-lite", "sha1 0.11.0", "sha2 0.11.0", @@ -1767,7 +1777,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1ddb117e43bbf7dacf0a4190fef4d345b9bad68dfc649cb349e7d17d28428e51" dependencies = [ "clap_builder", - "clap_derive", ] [[package]] @@ -1776,22 +1785,8 @@ version = "4.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "714a53001bf66416adb0e2ef5ac857140e7dc3a0c48fb28b2f10762fc4b5069f" dependencies = [ - "anstream", "anstyle", "clap_lex", - "strsim", -] - -[[package]] -name = "clap_derive" -version = "4.6.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f2ce8604710f6733aa641a2b3731eaa1e8b3d9973d5e3565da11800813f997a9" -dependencies = [ - "heck 0.5.0", - "proc-macro2", - "quote", - "syn 2.0.117", ] [[package]] @@ -1827,7 +1822,7 @@ version = "3.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "faf9468729b8cbcea668e36183cb69d317348c2e08e994829fb56ebfdfbaac34" dependencies = [ - "windows-sys 0.61.2", + "windows-sys 0.52.0", ] [[package]] @@ -2230,16 +2225,6 @@ dependencies = [ "memchr", ] -[[package]] -name = "ctor" -version = "0.6.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "424e0138278faeb2b401f174ad17e715c829512d74f3d1e81eb43365c2e0590e" -dependencies = [ - "ctor-proc-macro", - "dtor", -] - [[package]] name = "ctor" version = "1.0.12" @@ -2250,12 +2235,6 @@ dependencies = [ "linktime-proc-macro", ] -[[package]] -name = "ctor-proc-macro" -version = "0.0.7" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "52560adf09603e58c9a7ee1fe1dcb95a16927b17c127f0ac02d6e768a0e25bc1" - [[package]] name = "ctutils" version = "0.4.2" @@ -2392,7 +2371,7 @@ dependencies = [ "indexmap 2.14.0", "itertools 0.14.0", "log", - "object_store", + "object_store 0.13.2", "parking_lot", "sqlparser 0.62.0", "tempfile", @@ -2421,7 +2400,7 @@ dependencies = [ "futures", "itertools 0.14.0", "log", - "object_store", + "object_store 0.13.2", "parking_lot", "tokio", ] @@ -2446,7 +2425,7 @@ dependencies = [ "futures", "itertools 0.14.0", "log", - "object_store", + "object_store 0.13.2", ] [[package]] @@ -2466,7 +2445,7 @@ dependencies = [ "itertools 0.14.0", "libc", "log", - "object_store", + "object_store 0.13.2", "sqlparser 0.62.0", "tokio", "uuid", @@ -2507,7 +2486,7 @@ dependencies = [ "glob", "itertools 0.14.0", "log", - "object_store", + "object_store 0.13.2", "parking_lot", "rand 0.9.5", "tokio", @@ -2534,7 +2513,7 @@ dependencies = [ "datafusion-session", "futures", "itertools 0.14.0", - "object_store", + "object_store 0.13.2", "tokio", ] @@ -2556,7 +2535,7 @@ dependencies = [ "datafusion-physical-plan", "datafusion-session", "futures", - "object_store", + "object_store 0.13.2", "regex", "tokio", ] @@ -2579,7 +2558,7 @@ dependencies = [ "datafusion-physical-plan", "datafusion-session", "futures", - "object_store", + "object_store 0.13.2", "tokio", "tokio-stream", ] @@ -2605,7 +2584,7 @@ dependencies = [ "datafusion-physical-expr-common", "futures", "log", - "object_store", + "object_store 0.13.2", "parking_lot", "rand 0.9.5", "tempfile", @@ -2669,7 +2648,7 @@ dependencies = [ "hex", "itertools 0.14.0", "log", - "md-5 0.11.0", + "md-5", "memchr", "num-traits", "rand 0.9.5", @@ -3105,7 +3084,7 @@ dependencies = [ "libc", "option-ext", "redox_users", - "windows-sys 0.61.2", + "windows-sys 0.59.0", ] [[package]] @@ -3137,21 +3116,6 @@ dependencies = [ "litrs", ] -[[package]] -name = "dtor" -version = "0.1.1" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "404d02eeb088a82cfd873006cb713fe411306c7d182c344905e101fb1167d301" -dependencies = [ - "dtor-proc-macro", -] - -[[package]] -name = "dtor-proc-macro" -version = "0.0.6" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f678cf4a922c215c63e0de95eb1ff08a958a81d47e485cf9da1e27bf6305cfa5" - [[package]] name = "dunce" version = "1.0.5" @@ -3328,7 +3292,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb" dependencies = [ "libc", - "windows-sys 0.61.2", + "windows-sys 0.52.0", ] [[package]] @@ -3526,8 +3490,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c" [[package]] name = "fsst" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "rand 0.9.5", @@ -4085,18 +4049,21 @@ dependencies = [ [[package]] name = "hf-xet" -version = "1.5.2" +version = "1.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "430b33fa84f92796d4d263070b6c0d3ca219df7b9a0e1853ee431029b1612bcd" +checksum = "c237ef4fb0ce1962a5117f8bd8c74454b41629826a9df17d14a1840ca18f0754" dependencies = [ + "anyhow", "async-trait", "bytes", "http 1.5.0", "more-asserts", "serde", + "serde_json", "thiserror 2.0.18", "tokio", "tokio-util", + "tokio_with_wasm", "tracing", "uuid", "xet-client", @@ -4333,7 +4300,7 @@ dependencies = [ "libc", "percent-encoding", "pin-project-lite", - "socket2 0.6.3", + "socket2 0.5.10", "system-configuration", "tokio", "tower-service", @@ -4632,7 +4599,7 @@ checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46" dependencies = [ "hermit-abi", "libc", - "windows-sys 0.61.2", + "windows-sys 0.52.0", ] [[package]] @@ -4677,6 +4644,15 @@ dependencies = [ "either", ] +[[package]] +name = "itertools" +version = "0.15.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8b4baf93f58d4425749ca49a51c50ebab072c5df6994d08fed93541c331481dc" +dependencies = [ + "either", +] + [[package]] name = "itoa" version = "1.0.18" @@ -4886,8 +4862,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a" [[package]] name = "lance" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arc-swap", "arrow", @@ -4935,7 +4911,7 @@ dependencies = [ "lance-tokenizer", "log", "moka", - "object_store", + "object_store 0.14.1", "permutation", "pin-project", "prost", @@ -4959,8 +4935,8 @@ dependencies = [ [[package]] name = "lance-arrow" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-buffer", @@ -4982,7 +4958,7 @@ dependencies = [ [[package]] name = "lance-arrow-scalar" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-buffer", @@ -4996,7 +4972,7 @@ dependencies = [ [[package]] name = "lance-arrow-stats" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-schema", @@ -5005,8 +4981,8 @@ dependencies = [ [[package]] name = "lance-bitpacking" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrayref", "crunchy", @@ -5016,8 +4992,8 @@ dependencies = [ [[package]] name = "lance-core" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-buffer", @@ -5036,7 +5012,7 @@ dependencies = [ "log", "moka", "num_cpus", - "object_store", + "object_store 0.14.1", "pin-project", "prost", "quick_cache", @@ -5054,8 +5030,8 @@ dependencies = [ [[package]] name = "lance-datafusion" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow", "arrow-array", @@ -5085,8 +5061,8 @@ dependencies = [ [[package]] name = "lance-datagen" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow", "arrow-array", @@ -5103,8 +5079,8 @@ dependencies = [ [[package]] name = "lance-derive" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "proc-macro2", "quote", @@ -5113,8 +5089,8 @@ dependencies = [ [[package]] name = "lance-encoding" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-arith", "arrow-array", @@ -5147,8 +5123,8 @@ dependencies = [ [[package]] name = "lance-file" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-arith", "arrow-array", @@ -5169,7 +5145,7 @@ dependencies = [ "lance-io", "log", "num-traits", - "object_store", + "object_store 0.14.1", "prost", "prost-build", "prost-types", @@ -5179,8 +5155,8 @@ dependencies = [ [[package]] name = "lance-index" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arc-swap", "arrow", @@ -5224,7 +5200,7 @@ dependencies = [ "log", "ndarray", "num-traits", - "object_store", + "object_store 0.14.1", "prost", "prost-build", "prost-types", @@ -5244,8 +5220,8 @@ dependencies = [ [[package]] name = "lance-index-core" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-schema", @@ -5267,8 +5243,8 @@ dependencies = [ [[package]] name = "lance-io" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow", "arrow-array", @@ -5287,7 +5263,7 @@ dependencies = [ "log", "metrics", "moka", - "object_store", + "object_store 0.14.1", "object_store_opendal", "opendal", "path_abs", @@ -5308,8 +5284,8 @@ dependencies = [ [[package]] name = "lance-linalg" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-schema", @@ -5323,8 +5299,8 @@ dependencies = [ [[package]] name = "lance-namespace" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow", "async-trait", @@ -5338,8 +5314,8 @@ dependencies = [ [[package]] name = "lance-namespace-impls" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow", "arrow-ipc", @@ -5361,7 +5337,7 @@ dependencies = [ "lance-namespace", "lance-table", "log", - "object_store", + "object_store 0.14.1", "quick-xml 0.40.1", "rand 0.9.5", "reqwest 0.12.28", @@ -5392,8 +5368,8 @@ dependencies = [ [[package]] name = "lance-select" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-buffer", @@ -5407,8 +5383,8 @@ dependencies = [ [[package]] name = "lance-table" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow", "arrow-array", @@ -5429,7 +5405,7 @@ dependencies = [ "lance-io", "lance-select", "log", - "object_store", + "object_store 0.14.1", "prost", "prost-build", "prost-types", @@ -5448,8 +5424,8 @@ dependencies = [ [[package]] name = "lance-testing" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "arrow-array", "arrow-schema", @@ -5462,8 +5438,8 @@ dependencies = [ [[package]] name = "lance-tokenizer" -version = "12.0.0-beta.16" -source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.16#f7df098f5860cf9b3ac5339e7a641430cfbc6351" +version = "12.0.0-beta.18" +source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.18#1047c4bdbf36331cff2d9e21ab525c45ed741f93" dependencies = [ "frostem", "icu_segmenter", @@ -5476,7 +5452,7 @@ dependencies = [ [[package]] name = "lancedb" -version = "0.39.0-beta.6" +version = "0.39.0-beta.7" dependencies = [ "ahash", "anyhow", @@ -5536,7 +5512,7 @@ dependencies = [ "metrics-util", "moka", "num-traits", - "object_store", + "object_store 0.14.1", "pin-project", "polars", "polars-arrow", @@ -5567,7 +5543,7 @@ dependencies = [ [[package]] name = "lancedb-nodejs" -version = "0.39.0-beta.6" +version = "0.39.0-beta.7" dependencies = [ "arrow-array", "arrow-buffer", @@ -5592,7 +5568,7 @@ dependencies = [ [[package]] name = "lancedb-python" -version = "0.39.0-beta.6" +version = "0.39.0-beta.7" dependencies = [ "arrow", "async-trait", @@ -5956,16 +5932,6 @@ dependencies = [ "thread-tree", ] -[[package]] -name = "md-5" -version = "0.10.6" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf" -dependencies = [ - "cfg-if 1.0.4", - "digest 0.10.7", -] - [[package]] name = "md-5" version = "0.11.0" @@ -5978,10 +5944,11 @@ dependencies = [ [[package]] name = "mea" -version = "0.6.3" +version = "0.6.7" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6747f54621d156e1b47eb6b25f39a941b9fc347f98f67d25d8881ff99e8ed832" +checksum = "c709842c4ce65cb91e2666ad5319dfc1efc3af0d34f02075eddca9000d9f8afb" dependencies = [ + "hashbrown 0.17.1", "slab", ] @@ -6187,7 +6154,7 @@ checksum = "58c5f4d5375213fdb7be2655e152386e82f026f9a5ba36a75556e11359aafe09" dependencies = [ "bitflags 2.11.1", "chrono", - "ctor 1.0.12", + "ctor", "futures", "libc", "napi-build", @@ -6212,7 +6179,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0fa55ea69990c90b888e9e77044410e304ce7f35de599dc6d0b5c1923d2e59af" dependencies = [ "convert_case", - "ctor 1.0.12", + "ctor", "napi-derive-backend", "proc-macro2", "quote", @@ -6276,6 +6243,18 @@ dependencies = [ "libc", ] +[[package]] +name = "nix" +version = "0.31.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf20d2fde8ff38632c426f1165ed7436270b44f199fc55284c38276f9db47c3d" +dependencies = [ + "bitflags 2.11.1", + "cfg-if 1.0.4", + "cfg_aliases", + "libc", +] + [[package]] name = "nohash-hasher" version = "0.2.0" @@ -6325,7 +6304,7 @@ version = "0.50.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5" dependencies = [ - "windows-sys 0.61.2", + "windows-sys 0.59.0", ] [[package]] @@ -6470,9 +6449,37 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "622acbc9100d3c10e2ee15804b0caa40e55c933d5aa53814cd520805b7958a49" dependencies = [ "async-trait", + "bytes", + "chrono", + "futures-channel", + "futures-core", + "futures-util", + "http 1.5.0", + "humantime", + "itertools 0.14.0", + "parking_lot", + "percent-encoding", + "thiserror 2.0.18", + "tokio", + "tracing", + "url", + "walkdir", + "wasm-bindgen-futures", + "web-time", +] + +[[package]] +name = "object_store" +version = "0.14.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d354792e39fa5f0009e47623cf8b15b099bf9a652fa55c6f817fe28ac84fea50" +dependencies = [ + "async-trait", + "aws-lc-rs", "base64 0.22.1", "bytes", "chrono", + "crc-fast", "form_urlencoded", "futures-channel", "futures-core", @@ -6482,14 +6489,14 @@ dependencies = [ "httparse", "humantime", "hyper 1.9.0", - "itertools 0.14.0", - "md-5 0.10.6", + "itertools 0.15.0", + "md-5", + "nix 0.31.3", "parking_lot", "percent-encoding", - "quick-xml 0.39.4", + "quick-xml 0.41.0", "rand 0.10.1", - "reqwest 0.12.28", - "ring", + "reqwest 0.13.4", "rustls-pki-types", "serde", "serde_json", @@ -6501,20 +6508,21 @@ dependencies = [ "walkdir", "wasm-bindgen-futures", "web-time", + "windows-sys 0.61.2", ] [[package]] name = "object_store_opendal" -version = "0.58.0" +version = "0.60.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "88f165780495c17aa3ce86846600504198c3fffd99073521552751c2430fa6ac" +checksum = "f0206382328a82a28b549e5b2d18b6b9384ac1d82fa1f3c63da06f5ee6f7f054" dependencies = [ "async-trait", + "asyncband", "bytes", "chrono", "futures", - "mea", - "object_store", + "object_store 0.14.1", "opendal", "pin-project", "tokio", @@ -6568,11 +6576,11 @@ checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e" [[package]] name = "opendal" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4f20562cc7447fcc915fc5c23df305a412ea80a733c9f2fd9e2d267e2815be6d" +checksum = "f950151f9587a51a7bed70a15fa0cff464eae96e41ae7499f97067bdafdf43eb" dependencies = [ - "ctor 1.0.12", + "ctor", "opendal-core", "opendal-http-transport-reqwest", "opendal-layer-concurrent-limit", @@ -6591,19 +6599,19 @@ dependencies = [ [[package]] name = "opendal-core" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ec75551ff4cf3e57da98979f6a937aaa9ddb3915bf68cc17d03df733be6646ed" +checksum = "a43405d217dfdfb543f58847336d3af672897dd1939bb7dcf314b63cf364f1c9" dependencies = [ "anyhow", + "asyncband", "base64 0.23.1", "bytes", "futures", "http 1.5.0", "jiff", "log", - "md-5 0.11.0", - "mea", + "md-5", "percent-encoding", "quick-xml 0.41.0", "reqsign-core", @@ -6617,9 +6625,9 @@ dependencies = [ [[package]] name = "opendal-http-transport-reqwest" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ad4d4f19c3ce01126a30611f8e544eaa217104a278c889ac17c9374fe4f9e4ef" +checksum = "401999057db611e592f883fcf2cbd6754ff37af587deaadd07b8c1398b2b6b06" dependencies = [ "bytes", "futures", @@ -6631,21 +6639,21 @@ dependencies = [ [[package]] name = "opendal-layer-concurrent-limit" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "249ac5b0aa5a7a6c3737342d10456067937f9c9a6f3f02544271f7908ab91081" +checksum = "fba1dd0742261925fc0eb910773ec39cbc1336c55d41e13b19f3af970ad5a126" dependencies = [ + "asyncband", "futures", "http 1.5.0", - "mea", "opendal-core", ] [[package]] name = "opendal-layer-logging" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5c75411ab00f77851ff086b686c1e9ca8175ac18c15afa2cb75b9036436cb06c" +checksum = "d0fd963f9d32dd276521479d7f1f3a265d669b03a75f2062a4570a26b1b17421" dependencies = [ "log", "opendal-core", @@ -6653,9 +6661,9 @@ dependencies = [ [[package]] name = "opendal-layer-retry" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "80b7738bd5f233ad8da39af9b9316b9b7a4eaddd91e8e32a1e19b7030688121d" +checksum = "06306202c97c54fb41bdbbdcb854c8798823f0022ae7aac7a40c8a1023aa83a6" dependencies = [ "backon", "log", @@ -6664,9 +6672,9 @@ dependencies = [ [[package]] name = "opendal-layer-timeout" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a704141924500f3803c05ed871b53305d2a2f11cb5ef20160c3ee688a1857f66" +checksum = "6bd334cbd0a0bc934146733e74a80a5faf8db8e014781a25f6d9d80d7b87c981" dependencies = [ "opendal-core", "tokio", @@ -6674,9 +6682,9 @@ dependencies = [ [[package]] name = "opendal-service-azblob" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b3310fbbb48f111c6f590473c2cd15e1b7f8e384444b0d4e328f0464c864d767" +checksum = "ba0d2662ddf0de1f838db5dc48fafb8212ed1a5c7980bc164aa67809696c309c" dependencies = [ "base64 0.23.1", "bytes", @@ -6695,15 +6703,15 @@ dependencies = [ [[package]] name = "opendal-service-azdls" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2e3c406729935fe214ce574d68681a1ff7e0b322548f14094912bdbfe50e5c53" +checksum = "9064ed464286bffbea5955d470082a1e72b9b89f1e8f7a61b9e303c55ec08e4f" dependencies = [ + "asyncband", "base64 0.23.1", "bytes", "http 1.5.0", "log", - "mea", "opendal-core", "opendal-service-azure-common", "quick-xml 0.41.0", @@ -6716,9 +6724,9 @@ dependencies = [ [[package]] name = "opendal-service-azure-common" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "7348c88edf15af435b7be930077746b569fac5e738c1bf6a363b675e7317c9df" +checksum = "6348e3c0d7ff77a9b05c5b7f3d744ed395c2b2511812d3b37a934218002248f8" dependencies = [ "http 1.5.0", "opendal-core", @@ -6726,9 +6734,9 @@ dependencies = [ [[package]] name = "opendal-service-cos" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d533d4582105d269c8aebeee5f0e8bcf960f41b8aab6197df7012254d9f39bf0" +checksum = "49a652eadc76b94f9cffa497b3de5250dff53cce394d2974c00dde62c4e4cd81" dependencies = [ "bytes", "http 1.5.0", @@ -6743,9 +6751,9 @@ dependencies = [ [[package]] name = "opendal-service-gcs" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "007f3fba63c21e516c956b891e96ff9892d8175662bfb781cdada9d3766a11e6" +checksum = "1ccbf8450652bfe7b3ae69b7decce090c95c120ad565048f9a5a77dac2917a19" dependencies = [ "async-trait", "bytes", @@ -6760,13 +6768,14 @@ dependencies = [ "serde", "serde_json", "tokio", + "uuid", ] [[package]] name = "opendal-service-goosefs" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "60871e6386f04d831e6a5bdbc032af4a91aeba49963252d0ef456a2cf36a9b78" +checksum = "4b53d8c3e1db3176add7aff9ad2637c907409bac19e025ee8e9c072c0061d9c5" dependencies = [ "bytes", "goosefs-sdk", @@ -6778,10 +6787,11 @@ dependencies = [ [[package]] name = "opendal-service-hf" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b41fd41eb7ed03c5e66cefda61e8e117808ffd2908f2916737cb020a6beb02c7" +checksum = "5c17b59cf22bd2da9f751b8e66db595d5fe546b4c6b6ff0fb84c7bfd27455d7a" dependencies = [ + "asyncband", "bytes", "hf-xet", "http 1.5.0", @@ -6794,9 +6804,9 @@ dependencies = [ [[package]] name = "opendal-service-oss" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cd528ec2d49c5ca69e674ffed7b3e0686fb9cfcfea0596870de381467fda4f1b" +checksum = "284373c4a1143d8efaa7d010c1db05856d33a7cad475aaee8405dbcb0660cd96" dependencies = [ "bytes", "http 1.5.0", @@ -6811,16 +6821,16 @@ dependencies = [ [[package]] name = "opendal-service-s3" -version = "0.58.1" +version = "0.59.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "58e80cdf192d7eff05feed747894d64f81905ac4eaf132edf7ea270abdd2d663" +checksum = "388b1d39b62535c62803754ebef89808859558697366dbedd0299345887ba461" dependencies = [ "base64 0.23.1", "bytes", "crc-fast", "http 1.5.0", "log", - "md-5 0.11.0", + "md-5", "opendal-core", "quick-xml 0.41.0", "reqsign-aws-v4", @@ -7633,7 +7643,7 @@ dependencies = [ "inferno", "libc", "log", - "nix", + "nix 0.26.4", "once_cell", "smallvec", "spin 0.10.1", @@ -7655,7 +7665,7 @@ dependencies = [ "inferno", "libc", "log", - "nix", + "nix 0.26.4", "once_cell", "smallvec", "spin 0.10.1", @@ -7915,16 +7925,6 @@ dependencies = [ "memchr", ] -[[package]] -name = "quick-xml" -version = "0.39.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cdcc8dd4e2f670d309a5f0e83fe36dfdc05af317008fea29144da1a2ac858e5e" -dependencies = [ - "memchr", - "serde", -] - [[package]] name = "quick-xml" version = "0.40.1" @@ -7969,7 +7969,7 @@ dependencies = [ "quinn-udp", "rustc-hash", "rustls 0.23.40", - "socket2 0.6.3", + "socket2 0.5.10", "thiserror 2.0.18", "tokio", "tracing", @@ -8007,7 +8007,7 @@ dependencies = [ "cfg_aliases", "libc", "once_cell", - "socket2 0.6.3", + "socket2 0.5.10", "tracing", "windows-sys 0.60.2", ] @@ -8382,9 +8382,9 @@ dependencies = [ [[package]] name = "reqsign-aws-core" -version = "3.0.3" +version = "3.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e4af084e1f3cbf3e67e0c972765399bce54ecec804cceba46b39a8331f3c1bff" +checksum = "bac4749b7dfa7bfaccd01eb03e9dc795ed37e3f20d6f0f38e2c67ee85ad6bc86" dependencies = [ "bytes", "form_urlencoded", @@ -8403,9 +8403,9 @@ dependencies = [ [[package]] name = "reqsign-aws-v4" -version = "3.1.0" +version = "3.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4ac5b3b7cefa28933792b439186459f77f19f9b6edbeab41b8b187150361a206" +checksum = "ff250f0fd0b913fbd565e405acc553da0f13bde30bfb5403178c9d0313cdc15f" dependencies = [ "bytes", "http 1.5.0", @@ -8439,9 +8439,9 @@ dependencies = [ [[package]] name = "reqsign-core" -version = "3.2.1" +version = "3.3.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c07dd510b1e1b9b241883e483358147fb2ed2d497a7b39b065ba61eb93deceb0" +checksum = "ff052daffb0599681c50f85c59e7236438976efe991ab864edd9f3b235501a0f" dependencies = [ "anyhow", "base64 0.23.1", @@ -8452,6 +8452,7 @@ dependencies = [ "http 1.5.0", "jiff", "log", + "mea", "percent-encoding", "rsa", "serde", @@ -8463,9 +8464,9 @@ dependencies = [ [[package]] name = "reqsign-file-read-tokio" -version = "3.0.4" +version = "3.0.6" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "663d9d55abd0df0830ef0ae43708297cc1371cf4e8ca91f3ac813c309cca8c98" +checksum = "b3235df90a6bca681aa47dd86f2393d122a6d77042aa8a7c81e218cd45c5bfc0" dependencies = [ "anyhow", "reqsign-core", @@ -8474,10 +8475,11 @@ dependencies = [ [[package]] name = "reqsign-google" -version = "3.0.4" +version = "3.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4080a227f82a09f68540ecd028622065d7ac4c0bcb8727a25bdcfc0526235792" +checksum = "272a5813571885c1455ffe106f0c768577e6ce69313446d4476e8d41dcf6ac5a" dependencies = [ + "bytes", "form_urlencoded", "http 1.5.0", "log", @@ -8561,6 +8563,7 @@ dependencies = [ "bytes", "futures-core", "futures-util", + "h2 0.4.16", "http 1.5.0", "http-body 1.1.0", "http-body-util", @@ -8787,7 +8790,7 @@ dependencies = [ "errno", "libc", "linux-raw-sys", - "windows-sys 0.61.2", + "windows-sys 0.52.0", ] [[package]] @@ -8858,7 +8861,7 @@ dependencies = [ "security-framework", "security-framework-sys", "webpki-root-certs", - "windows-sys 0.61.2", + "windows-sys 0.52.0", ] [[package]] @@ -9255,7 +9258,6 @@ dependencies = [ "cfg-if 1.0.4", "cpufeatures 0.2.17", "digest 0.10.7", - "sha2-asm", ] [[package]] @@ -9269,15 +9271,6 @@ dependencies = [ "digest 0.11.3", ] -[[package]] -name = "sha2-asm" -version = "0.6.4" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b845214d6175804686b2bd482bcffe96651bb2d1200742b712003504a2dac1ab" -dependencies = [ - "cc", -] - [[package]] name = "sharded-slab" version = "0.1.7" @@ -9450,7 +9443,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "3a766e1110788c36f4fa1c2b71b387a7815aa65f88ce0229841826633d93723e" dependencies = [ "libc", - "windows-sys 0.61.2", + "windows-sys 0.60.2", ] [[package]] @@ -9557,7 +9550,7 @@ dependencies = [ "cfg-if 1.0.4", "libc", "psm", - "windows-sys 0.61.2", + "windows-sys 0.60.2", ] [[package]] @@ -9849,7 +9842,7 @@ dependencies = [ "getrandom 0.4.2", "once_cell", "rustix", - "windows-sys 0.61.2", + "windows-sys 0.52.0", ] [[package]] @@ -10134,6 +10127,30 @@ dependencies = [ "tokio", ] +[[package]] +name = "tokio_with_wasm" +version = "0.8.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "34e40fbbbd95441133fe9483f522db15dbfd26dc636164ebd8f2dd28759a6aa6" +dependencies = [ + "js-sys", + "tokio", + "tokio_with_wasm_proc", + "wasm-bindgen", + "wasm-bindgen-futures", + "web-sys", +] + +[[package]] +name = "tokio_with_wasm_proc" +version = "0.8.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d01145a2c788d6aae4cd653afec1e8332534d7d783d01897cefcafe4428de992" +dependencies = [ + "quote", + "syn 2.0.117", +] + [[package]] name = "toml_datetime" version = "1.1.1+spec-1.1.0" @@ -10829,7 +10846,7 @@ version = "0.1.11" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22" dependencies = [ - "windows-sys 0.61.2", + "windows-sys 0.52.0", ] [[package]] @@ -11263,20 +11280,18 @@ dependencies = [ [[package]] name = "xet-client" -version = "1.5.2" +version = "1.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3e1e496dcbe6a09017acdfaf48e1a646735e7ff5b2a49e2c7e081cca77a59bc8" +checksum = "c3b8da8cc70aa2e3c500c0400e012df82c656ab9fca47f9f939fffc5afd89aca" dependencies = [ "anyhow", "async-trait", "base64 0.22.1", "bytes", - "clap", "crc32fast", "futures", "http 1.5.0", "hyper 1.9.0", - "lazy_static", "more-asserts", "rand 0.10.1", "redb", @@ -11290,8 +11305,8 @@ dependencies = [ "thiserror 2.0.18", "tokio", "tokio-retry", + "tokio_with_wasm", "tracing", - "tracing-subscriber", "url", "urlencoding", "web-time", @@ -11301,24 +11316,21 @@ dependencies = [ [[package]] name = "xet-core-structures" -version = "1.5.2" +version = "1.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "cb838aa8eb67d730af301584cf003caad407487606058292a6750711b603fbee" +checksum = "73503c223783dccc864abde22115e09d12f190448a0baf58ab2c54bc709e2f99" dependencies = [ "async-trait", "base64 0.22.1", "blake3", "bytemuck", "bytes", - "clap", "countio", - "csv", "futures", "futures-util", "getrandom 0.4.2", "heapify", "itertools 0.14.0", - "lazy_static", "lz4_flex", "more-asserts", "rand 0.10.1", @@ -11326,7 +11338,6 @@ dependencies = [ "safe-transmute", "serde", "static_assertions", - "tempfile", "thiserror 2.0.18", "tokio", "tokio-util", @@ -11338,32 +11349,31 @@ dependencies = [ [[package]] name = "xet-data" -version = "1.5.2" +version = "1.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "67fd409bef621411a9d9013798540bb8036cb2678f03ab39af89a5e88034ed8c" +checksum = "c89052ec5dec2187cad30b86af92cc24fd61c4a57a795f1ff7ff5f38d49184eb" dependencies = [ "anyhow", "async-trait", "bytes", "chrono", - "clap", "gearhash", "http 1.5.0", "itertools 0.14.0", - "lazy_static", "more-asserts", "rand 0.10.1", "serde", "serde_json", - "sha2 0.10.9", + "sha2 0.11.0", "tempfile", "thiserror 2.0.18", "tokio", "tokio-util", + "tokio_with_wasm", "tracing", "url", "uuid", - "walkdir", + "web-time", "xet-client", "xet-core-structures", "xet-runtime", @@ -11371,9 +11381,9 @@ dependencies = [ [[package]] name = "xet-runtime" -version = "1.5.2" +version = "1.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "15d8f121c33866f7648b737abe70d0e2dd9c0af4ffdd7219207531d0283aa63d" +checksum = "af5c60d5eed38ab4c576f4421bae835e7bd07631fb381705605529d2015c106b" dependencies = [ "anyhow", "async-trait", @@ -11381,13 +11391,12 @@ dependencies = [ "chrono", "colored", "const-str", - "ctor 0.6.3", + "ctor", "dirs", "futures", "git-version", "humantime", "konst", - "lazy_static", "libc", "more-asserts", "oneshot", @@ -11401,9 +11410,11 @@ dependencies = [ "thiserror 2.0.18", "tokio", "tokio-util", + "tokio_with_wasm", "tracing", "tracing-appender", "tracing-subscriber", + "web-time", "whoami", "winapi", ] diff --git a/Cargo.toml b/Cargo.toml index a0a908489..1068d48ee 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -13,20 +13,20 @@ categories = ["database-implementations"] rust-version = "1.91.0" [workspace.dependencies] -lance = { "version" = "=12.0.0-beta.16", default-features = false, "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-core = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-datagen = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-file = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-io = { "version" = "=12.0.0-beta.16", default-features = false, "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-index = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-linalg = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace-impls = { "version" = "=12.0.0-beta.16", default-features = false, "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-table = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-testing = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-datafusion = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-encoding = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } -lance-arrow = { "version" = "=12.0.0-beta.16", "tag" = "v12.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" } +lance = { "version" = "=12.0.0-beta.18", default-features = false, "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-core = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-datagen = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-file = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-io = { "version" = "=12.0.0-beta.18", default-features = false, "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-index = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-linalg = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace-impls = { "version" = "=12.0.0-beta.18", default-features = false, "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-table = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-testing = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-datafusion = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-encoding = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" } +lance-arrow = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "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 @@ -60,7 +60,7 @@ log = "0.4" metrics = "0.24" metrics-util = "0.19" moka = { version = "0.12", features = ["future"] } -object_store = "0.13.2" +object_store = "0.14.1" pin-project = "1.0.7" rand = "0.9" snafu = "0.8" diff --git a/docs/src/java/java.md b/docs/src/java/java.md index 17d14df15..59c995344 100644 --- a/docs/src/java/java.md +++ b/docs/src/java/java.md @@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`: com.lancedb lancedb-core - 0.39.0-beta.6 + 0.39.0-beta.7 ``` diff --git a/docs/src/js/classes/BlobFile.md b/docs/src/js/classes/BlobFile.md new file mode 100644 index 000000000..84a596d1a --- /dev/null +++ b/docs/src/js/classes/BlobFile.md @@ -0,0 +1,62 @@ +[**@lancedb/lancedb**](../README.md) • **Docs** + +*** + +[@lancedb/lancedb](../globals.md) / BlobFile + +# Class: BlobFile + +A lazy handle to blob bytes. Create one with [Table.fetchBlobFiles](Table.md#fetchblobfiles). + +## Methods + +### read() + +```ts +read(): Promise +``` + +Reads from the cursor to the end and advances the cursor. + +A second call returns an empty buffer. [BlobFile.readRange](BlobFile.md#readrange) does +not move the cursor. + +#### Returns + +`Promise`<`Buffer`> + +*** + +### readRange() + +```ts +readRange(start, end): Promise +``` + +Reads the half-open byte range `[start, end)`. + +Fails when `end` is past the blob size. Does not move the cursor. + +#### Parameters + +* **start**: `bigint` + +* **end**: `bigint` + +#### Returns + +`Promise`<`Buffer`> + +*** + +### size() + +```ts +size(): bigint +``` + +Returns the blob size in bytes. + +#### Returns + +`bigint` diff --git a/docs/src/js/classes/Table.md b/docs/src/js/classes/Table.md index 3847f3a39..ef6e9535a 100644 --- a/docs/src/js/classes/Table.md +++ b/docs/src/js/classes/Table.md @@ -137,6 +137,20 @@ containing the new version number of the table after altering the columns. *** +### blobColumns() + +```ts +abstract blobColumns(): Promise +``` + +Blob v2 columns, including nested dotted paths. + +#### Returns + +`Promise`<`string`[]> + +*** + ### branches() ```ts @@ -499,6 +513,54 @@ Drop an index from the table. *** +### fetchBlobFiles() + +```ts +abstract fetchBlobFiles(column, rowIds): Promise<(null | BlobFile)[]> +``` + +Opens lazy blob handles for `column` at the given row IDs using the +table's current checkout. + +Preserves input order, duplicates, and nulls. Use this for large payloads. +See [Table.fetchBlobs](Table.md#fetchblobs) for row-ID validity across versions. + +#### Parameters + +* **column**: `string` + +* **rowIds**: readonly (`number` \| `bigint`)[] + +#### Returns + +`Promise`<(`null` \| [`BlobFile`](BlobFile.md))[]> + +*** + +### fetchBlobs() + +```ts +abstract fetchBlobs(column, rowIds): Promise<(null | Buffer)[]> +``` + +Bytes for `column` at row IDs from [Query.withRowId](Query.md#withrowid). + +Reads the table's current checkout. IDs from another version can fail after +compaction unless stable row ids are enabled. Results keep input order and +duplicates. Null blobs are `null`. Empty blobs are empty buffers. + +#### Parameters + +* **column**: `string` + +* **rowIds**: readonly (`number` \| `bigint`)[] + +#### Returns + +`Promise`<(`null` \| `Buffer`)[]> + +*** + ### flushLsm() ```ts diff --git a/docs/src/js/functions/blob.md b/docs/src/js/functions/blob.md new file mode 100644 index 000000000..20a734cd4 --- /dev/null +++ b/docs/src/js/functions/blob.md @@ -0,0 +1,55 @@ +[**@lancedb/lancedb**](../README.md) • **Docs** + +*** + +[@lancedb/lancedb](../globals.md) / blob + +# Function: blob() + +```ts +function blob(name, options): Field +``` + +Declares a `lance.blob.v2` column. + +Query results are descriptors, not payload bytes. Use [Table.fetchBlobs](../classes/Table.md#fetchblobs) +or [Table.fetchBlobFiles](../classes/Table.md#fetchblobfiles) to read bytes. + +## Parameters + +* **name**: `string` + +* **options**: [`BlobOptions`](../type-aliases/BlobOptions.md) = `{}` + +## Returns + +`Field` + +## Example + +```ts +import { readFile } from "node:fs/promises"; +import { Field, Int64, Schema } from "apache-arrow"; +import { blob, connect } from "@lancedb/lancedb"; + +const db = await connect("./data"); +const video = await readFile("clip.mp4"); +const table = await db.createTable( + "videos", + [{ id: 1n, video }], + { + schema: new Schema([ + new Field("id", new Int64()), + blob("video"), + ]), + }, +); + +const rows = await table.query().select(["id"]).withRowId().toArray(); +const rowIds = rows.map((row) => row._rowid as bigint); +const bytes = await table.fetchBlobs("video", rowIds); + +const [handle] = await table.fetchBlobFiles("video", rowIds); +const size = handle!.size(); +const header = await handle!.readRange(0n, size < 65536n ? size : 65536n); +``` diff --git a/docs/src/js/functions/isBlobField.md b/docs/src/js/functions/isBlobField.md new file mode 100644 index 000000000..944309f90 --- /dev/null +++ b/docs/src/js/functions/isBlobField.md @@ -0,0 +1,22 @@ +[**@lancedb/lancedb**](../README.md) • **Docs** + +*** + +[@lancedb/lancedb](../globals.md) / isBlobField + +# Function: isBlobField() + +```ts +function isBlobField(field): boolean +``` + +Checks for the `lance.blob.v2` extension marker. Does not validate the +field's storage type. + +## Parameters + +* **field**: `Field`<`any`> + +## Returns + +`boolean` diff --git a/docs/src/js/globals.md b/docs/src/js/globals.md index eb0fc7d5a..4a5effaae 100644 --- a/docs/src/js/globals.md +++ b/docs/src/js/globals.md @@ -19,6 +19,7 @@ ## Classes - [AutoQuery](classes/AutoQuery.md) +- [BlobFile](classes/BlobFile.md) - [BooleanQuery](classes/BooleanQuery.md) - [BoostQuery](classes/BoostQuery.md) - [BranchContents](classes/BranchContents.md) @@ -143,6 +144,7 @@ - [AnalyzePlanDistributedMetrics](type-aliases/AnalyzePlanDistributedMetrics.md) - [BaseTokenizer](type-aliases/BaseTokenizer.md) +- [BlobOptions](type-aliases/BlobOptions.md) - [Data](type-aliases/Data.md) - [DataLike](type-aliases/DataLike.md) - [FieldLike](type-aliases/FieldLike.md) @@ -158,9 +160,11 @@ ## Functions - [RecordBatchIterator](functions/RecordBatchIterator.md) +- [blob](functions/blob.md) - [connect](functions/connect.md) - [connectNamespace](functions/connectNamespace.md) - [instrumentLanceDbMetrics](functions/instrumentLanceDbMetrics.md) +- [isBlobField](functions/isBlobField.md) - [makeArrowTable](functions/makeArrowTable.md) - [packBits](functions/packBits.md) - [permutationBuilder](functions/permutationBuilder.md) diff --git a/docs/src/js/type-aliases/BlobOptions.md b/docs/src/js/type-aliases/BlobOptions.md new file mode 100644 index 000000000..41dbe92c2 --- /dev/null +++ b/docs/src/js/type-aliases/BlobOptions.md @@ -0,0 +1,48 @@ +[**@lancedb/lancedb**](../README.md) • **Docs** + +*** + +[@lancedb/lancedb](../globals.md) / BlobOptions + +# Type Alias: BlobOptions + +```ts +type BlobOptions: object; +``` + +## Type declaration + +### dedicatedSizeThreshold? + +```ts +optional dedicatedSizeThreshold: number; +``` + +Max payload bytes stored in a packed sidecar before a dedicated file. Must +be a positive safe integer. + +### inlineSizeThreshold? + +```ts +optional inlineSizeThreshold: number; +``` + +Max payload bytes kept inline in the data file. Zero is allowed. Must be a +safe integer. + +### nullable? + +```ts +optional nullable: boolean; +``` + +Defaults to true. + +### packFileSizeThreshold? + +```ts +optional packFileSizeThreshold: number; +``` + +Max bytes in one packed sidecar before starting another. Must be a positive +safe integer. diff --git a/java/lancedb-core/pom.xml b/java/lancedb-core/pom.xml index c5c928219..afe9b8c5c 100644 --- a/java/lancedb-core/pom.xml +++ b/java/lancedb-core/pom.xml @@ -8,7 +8,7 @@ com.lancedb lancedb-parent - 0.39.0-beta.6 + 0.39.0-beta.7 ../pom.xml diff --git a/java/pom.xml b/java/pom.xml index b3dbe413c..e66e1bbd4 100644 --- a/java/pom.xml +++ b/java/pom.xml @@ -6,7 +6,7 @@ com.lancedb lancedb-parent - 0.39.0-beta.6 + 0.39.0-beta.7 pom ${project.artifactId} LanceDB Java SDK Parent POM @@ -28,7 +28,7 @@ UTF-8 15.0.0 - 12.0.0-beta.16 + 12.0.0-beta.18 false 2.30.0 1.7 diff --git a/nodejs/Cargo.toml b/nodejs/Cargo.toml index c4ef09cda..340d8e500 100644 --- a/nodejs/Cargo.toml +++ b/nodejs/Cargo.toml @@ -1,7 +1,7 @@ [package] name = "lancedb-nodejs" edition.workspace = true -version = "0.39.0-beta.6" +version = "0.39.0-beta.7" publish = false license.workspace = true description.workspace = true diff --git a/nodejs/__test__/blob.test.ts b/nodejs/__test__/blob.test.ts new file mode 100644 index 000000000..e8e9357e3 --- /dev/null +++ b/nodejs/__test__/blob.test.ts @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +import { Field, Int64, List, Schema, Struct, Utf8 } from "apache-arrow"; +import { makeArrowTable } from "../lancedb/arrow"; +import { BlobFile, blob, coerceBlobValue, isBlobField } from "../lancedb/blob"; + +describe("blob()", () => { + it("marks the field as lance.blob.v2", () => { + const field = blob("image", { nullable: false }); + expect(field.nullable).toBe(false); + expect(isBlobField(field)).toBe(true); + expect(field.metadata.get("ARROW:extension:name")).toBe("lance.blob.v2"); + }); + + it("writes encoding thresholds as field metadata", () => { + const field = blob("video", { + inlineSizeThreshold: 1024, + dedicatedSizeThreshold: 2 * 1024 * 1024, + packFileSizeThreshold: 64 * 1024 * 1024, + }); + expect( + field.metadata.get("lance-encoding:blob-inline-size-threshold"), + ).toBe("1024"); + expect( + field.metadata.get("lance-encoding:blob-dedicated-size-threshold"), + ).toBe(String(2 * 1024 * 1024)); + expect( + field.metadata.get("lance-encoding:blob-pack-file-size-threshold"), + ).toBe(String(64 * 1024 * 1024)); + }); + + it("rejects invalid thresholds", () => { + expect(() => blob("image", { inlineSizeThreshold: -1 })).toThrow( + /inlineSizeThreshold must be non-negative/, + ); + expect(() => blob("image", { dedicatedSizeThreshold: 0 })).toThrow( + /dedicatedSizeThreshold must be positive/, + ); + expect(() => blob("image", { packFileSizeThreshold: 1.5 })).toThrow( + /packFileSizeThreshold must be a safe integer/, + ); + expect(() => + blob("image", { dedicatedSizeThreshold: Number.MAX_SAFE_INTEGER + 1 }), + ).toThrow(/dedicatedSizeThreshold must be a safe integer/); + }); +}); + +describe("coerceBlobValue", () => { + it.each([ + ["Buffer", Buffer.from("x"), { data: Buffer.from("x"), uri: null }], + [ + "Uint8Array", + new Uint8Array([120]), + { data: new Uint8Array([120]), uri: null }, + ], + ["URI string", "s3://bucket/key", { data: null, uri: "s3://bucket/key" }], + [ + "data struct", + { data: Buffer.from("y") }, + { data: Buffer.from("y"), uri: null }, + ], + [ + "uri struct", + { uri: "s3://bucket/key" }, + { data: null, uri: "s3://bucket/key" }, + ], + ["null", null, null], + ])("accepts %s", (_name, input, expected) => { + expect(coerceBlobValue(input)).toEqual(expected); + }); + + it.each([ + ["empty URI", "", /uri cannot be empty/], + ["object without data or uri", { position: 0 }, /data' or 'uri/], + [ + "Int16Array", + new Int16Array([1]), + /Blob data must be Buffer or Uint8Array/, + ], + [ + "both data and uri", + { data: Buffer.from("y"), uri: "s3://bucket/key" }, + /exactly one of 'data' or 'uri'/, + ], + [ + "neither data nor uri", + { data: null, uri: null }, + /exactly one of 'data' or 'uri'/, + ], + ])("rejects %s", (_name, input, message) => { + expect(() => coerceBlobValue(input)).toThrow(message); + }); +}); + +describe("BlobFile", () => { + it("rejects constructing BlobFile without a native handle", () => { + expect(() => new (BlobFile as unknown as { new (): BlobFile })()).toThrow( + /fetchBlobFiles/, + ); + }); +}); + +describe("makeArrowTable blob columns", () => { + it("coerces Buffer input onto a blob field", () => { + const schema = new Schema([ + new Field("id", new Int64(), true), + blob("image"), + ]); + const table = makeArrowTable([{ id: 1n, image: Buffer.from("hello") }], { + schema, + }); + expect(isBlobField(table.schema.fields[1])).toBe(true); + const image = table.getChild("image")!; + expect(image.nullCount).toBe(0); + expect(image.getChild("uri")!.get(0)).toBeNull(); + expect(image.getChild("data")!.nullCount).toBe(0); + expect(Buffer.from(image.getChild("data")!.get(0)!).toString()).toBe( + "hello", + ); + }); + + it("coerces Buffer elements inside a list and keeps null slots", () => { + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field("images", new List(blob("image")), true), + ]); + const table = makeArrowTable( + [ + { id: 1n, images: [Buffer.from("a"), Buffer.from("bb")] }, + { id: 2n, images: null }, + { id: 3n, images: [Buffer.from("c"), null] }, + { id: 4n, images: [] }, + ], + { schema }, + ); + const images = table.getChild("images")!; + expect(images.nullCount).toBe(1); + const rows = images.toArray(); + expect(rows[1]).toBeNull(); + expect(Array.from(rows[3] as Iterable)).toHaveLength(0); + const first = Array.from(rows[0] as Iterable<{ data: Uint8Array | null }>); + expect(Buffer.from(first[0].data!).toString()).toBe("a"); + expect(Buffer.from(first[1].data!).toString()).toBe("bb"); + const third = Array.from( + rows[2] as Iterable<{ data: Uint8Array | null } | null>, + ); + expect(Buffer.from(third[0]!.data!).toString()).toBe("c"); + expect(third[1]).toBeNull(); + }); + + it("coerces Buffer fields inside list structs", () => { + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field( + "items", + new List( + new Field( + "item", + new Struct([new Field("name", new Utf8(), true), blob("image")]), + true, + ), + ), + true, + ), + ]); + const table = makeArrowTable( + [ + { + id: 1n, + items: [{ name: "one", image: Buffer.from("alpha") }], + }, + ], + { schema }, + ); + const items = Array.from( + table.getChild("items")!.toArray()[0] as Iterable<{ + name: string; + image: { data: Uint8Array | null }; + }>, + ); + expect(items[0].name).toBe("one"); + expect(Buffer.from(items[0].image.data!).toString()).toBe("alpha"); + }); +}); diff --git a/nodejs/__test__/table.test.ts b/nodejs/__test__/table.test.ts index 43a027642..ac74c65ef 100644 --- a/nodejs/__test__/table.test.ts +++ b/nodejs/__test__/table.test.ts @@ -18,6 +18,7 @@ import { Query, Table, VectorQuery, + blob, connect, tokenize, } from "../lancedb"; @@ -2402,6 +2403,276 @@ describe("when dealing with versioning", () => { }); }); +describe("when dealing with blob columns", () => { + let tmpDir: tmp.DirResult; + beforeEach(() => { + tmpDir = tmp.dirSync({ unsafeCleanup: true }); + }); + afterEach(() => { + tmpDir.removeCallback(); + }); + + it("discovers blob columns", async () => { + const { table } = await openBlobTable(); + expect(await table.blobColumns()).toEqual(["image"]); + }); + + it("preserves order, duplicates, and nulls", async () => { + const { table, rowIds } = await openBlobTable(); + const [alphaId, betaId, nullId] = rowIds; + const bytes = await table.fetchBlobs("image", [ + betaId, + alphaId, + betaId, + nullId, + ]); + expect(bytes.map((b) => (b == null ? null : b.toString()))).toEqual([ + "beta", + "alpha", + "beta", + null, + ]); + const files = await table.fetchBlobFiles("image", [ + betaId, + nullId, + alphaId, + ]); + expect(files.map((f) => f == null)).toEqual([false, true, false]); + }); + + it("reads full blob contents", async () => { + const { table, rowIds, alpha, beta } = await openBlobTable(); + const bytes = await table.fetchBlobs("image", rowIds); + expect(bytes[0]!.equals(alpha)).toBe(true); + expect(bytes[1]!.equals(beta)).toBe(true); + const files = await table.fetchBlobFiles("image", rowIds); + expect(files[0]!.size()).toBe(BigInt(alpha.length)); + expect(Buffer.from(await files[0]!.read()).toString()).toBe("alpha"); + expect(Buffer.from(await files[1]!.read()).toString()).toBe("beta"); + }); + + it("reads a half-open range", async () => { + const { table, rowIds } = await openBlobTable(); + const files = await table.fetchBlobFiles("image", rowIds); + expect(Buffer.from(await files[0]!.readRange(0n, 2n)).toString()).toBe( + "al", + ); + }); + + it("readRange does not move the cursor", async () => { + const { table, rowIds, alpha } = await openBlobTable(); + const [handle] = await table.fetchBlobFiles("image", rowIds); + expect((await handle!.readRange(1n, 3n)).toString()).toBe("lp"); + expect(await handle!.read()).toEqual(alpha); + expect(await handle!.read()).toEqual(Buffer.alloc(0)); + }); + + it("fails when readRange end is past the blob size", async () => { + const { table, rowIds, alpha } = await openBlobTable(); + const files = await table.fetchBlobFiles("image", rowIds); + await expect( + files[0]!.readRange(0n, BigInt(alpha.length + 1)), + ).rejects.toThrow(/exceeds blob size/); + }); + + it("rejects fetchBlobs on a non-blob column", async () => { + const { table, rowIds } = await openBlobTable(); + await expect(table.fetchBlobs("id", rowIds)).rejects.toThrow(/blob/i); + }); + + it("discovers and fetches nested blob columns", async () => { + const db = await connect(tmpDir.name); + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field("info", new Struct([blob("image")]), true), + ]); + const payload = Buffer.from("nested"); + const table = await db.createTable( + "nested_blobs", + [{ id: 1n, info: { image: payload } }], + { schema }, + ); + expect(await table.blobColumns()).toEqual(["info.image"]); + const rows = await table.query().withRowId().toArray(); + const bytes = await table.fetchBlobs("info.image", [ + rows[0]._rowid as bigint, + ]); + expect(bytes[0]!.equals(payload)).toBe(true); + }); + + it("creates and adds list blob columns", async () => { + const db = await connect(tmpDir.name); + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field("images", new List(blob("image")), true), + ]); + const alpha = Buffer.from("alpha"); + const beta = Buffer.from("beta"); + const gamma = Buffer.from("gamma"); + const table = await db.createTable( + "list_blobs", + [{ id: 1n, images: [alpha, beta] }], + { schema }, + ); + await table.add([ + { id: 2n, images: null }, + { id: 3n, images: [gamma, null] }, + { id: 4n, images: [] }, + ]); + expect(await table.blobColumns()).toEqual(["images.image"]); + const rows = await table.query().toArray(); + const byId = new Map(rows.map((row) => [Number(row.id), row])); + expect(descriptorSizes(byId.get(1)!.images)).toEqual([ + alpha.length, + beta.length, + ]); + expect(byId.get(2)!.images).toBeNull(); + expect(descriptorSizes(byId.get(3)!.images)).toEqual([gamma.length, null]); + expect(Array.from(byId.get(4)!.images as Iterable)).toHaveLength( + 0, + ); + }); + + it("creates and adds list struct blob columns", async () => { + const db = await connect(tmpDir.name); + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field( + "items", + new List( + new Field( + "item", + new Struct([new Field("name", new Utf8(), true), blob("image")]), + true, + ), + ), + true, + ), + ]); + const alpha = Buffer.from("nested-alpha"); + const beta = Buffer.from("nested-beta"); + const table = await db.createTable( + "list_struct_blobs", + [{ id: 1n, items: [{ name: "one", image: alpha }] }], + { schema }, + ); + await table.add([ + { + id: 2n, + items: [ + { name: "two", image: beta }, + { name: "three", image: null }, + ], + }, + ]); + const rows = await table.query().toArray(); + const byId = new Map(rows.map((row) => [Number(row.id), row])); + expect( + descriptorSizes( + Array.from(byId.get(1)!.items as Iterable<{ image: unknown }>).map( + (item) => item.image, + ), + ), + ).toEqual([alpha.length]); + expect( + descriptorSizes( + Array.from(byId.get(2)!.items as Iterable<{ image: unknown }>).map( + (item) => item.image, + ), + ), + ).toEqual([beta.length, null]); + }); + + it("rejects blob fields inside a fixed-size list", async () => { + const db = await connect(tmpDir.name); + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field("frames", new FixedSizeList(2, blob("frame")), true), + ]); + await expect( + db.createTable( + "fsl_blobs", + [{ id: 1n, frames: [Buffer.from("a"), Buffer.from("b")] }], + { schema }, + ), + ).rejects.toThrow( + "Blob fields inside FixedSizeList are not supported. Use List instead.", + ); + }); + + it("rejects blob fields inside a nested fixed-size list", async () => { + const db = await connect(tmpDir.name); + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field( + "clip", + new Struct([ + new Field("frames", new FixedSizeList(2, blob("frame")), true), + ]), + true, + ), + ]); + await expect( + db.createTable( + "nested_fsl_blobs", + [ + { + id: 1n, + clip: { frames: [Buffer.from("a"), Buffer.from("b")] }, + }, + ], + { schema }, + ), + ).rejects.toThrow( + "Blob fields inside FixedSizeList are not supported. Use List instead.", + ); + }); + + it("rejects an Arrow table with blob fields inside a fixed-size list", async () => { + const db = await connect(tmpDir.name); + const schema = new Schema([ + new Field("id", new Int64(), true), + new Field("frames", new FixedSizeList(2, blob("frame")), true), + ]); + await expect( + db.createTable("fsl_blobs_ipc", new ArrowTable(schema)), + ).rejects.toThrow( + "Blob fields inside FixedSizeList are not supported. Use List instead.", + ); + }); + + function descriptorSizes(values: unknown): (number | null)[] { + return Array.from( + values as Iterable<{ size?: bigint | number } | null>, + ).map((value) => (value == null ? null : Number(value.size))); + } + + async function openBlobTable() { + const db = await connect(tmpDir.name); + const schema = new Schema([ + new Field("id", new Int64(), true), + blob("image"), + ]); + const alpha = Buffer.from("alpha"); + const beta = Buffer.from("beta"); + const table = await db.createTable( + "blobs", + [ + { id: 1n, image: alpha }, + { id: 2n, image: beta }, + { id: 3n, image: null }, + ], + { schema }, + ); + const rows = await table.query().withRowId().toArray(); + const rowIdById = new Map( + rows.map((r) => [Number(r.id), r._rowid as bigint]), + ); + const rowIds = [1, 2, 3].map((id) => rowIdById.get(id)!); + return { table, rowIds, alpha, beta }; + } +}); + describe("when dealing with tags", () => { let tmpDir: tmp.DirResult; beforeEach(() => { diff --git a/nodejs/lancedb/arrow.ts b/nodejs/lancedb/arrow.ts index 119887704..81b140da7 100644 --- a/nodejs/lancedb/arrow.ts +++ b/nodejs/lancedb/arrow.ts @@ -40,6 +40,7 @@ import { } from "apache-arrow"; import { Buffers } from "apache-arrow/data"; import { typedArrayToArrowType } from "./arrow_type"; +import { coerceBlobValue, isBlobField } from "./blob"; import { type EmbeddingFunction } from "./embedding/embedding_function"; import { EmbeddingFunctionConfig, @@ -430,12 +431,14 @@ export function makeArrowTable( throw new Error("A schema must be provided if data is empty"); } else { schema = new Schema(schema.fields, schemaMetadata); + validateBlobSchema(schema); return new ArrowTable(schema); } } let inferredSchema = inferSchema(data, schema, opt); inferredSchema = new Schema(inferredSchema.fields, schemaMetadata); + validateBlobSchema(inferredSchema); const finalColumns: Record = {}; for (const field of inferredSchema.fields) { @@ -445,6 +448,35 @@ export function makeArrowTable( return new ArrowTable(inferredSchema, finalColumns); } +function validateBlobSchema(schema: Schema): void { + for (const field of schema.fields) { + validateBlobField(field); + } +} + +function validateBlobField(field: Field): void { + if ( + isFixedSizeList(field.type) && + containsBlobField(field.type.children[0]) + ) { + throw new Error( + "Blob fields inside FixedSizeList are not supported. Use List instead.", + ); + } + for (const child of field.type.children ?? []) { + validateBlobField(child); + } +} + +function containsBlobField(field: Field): boolean { + if (isBlobField(field)) { + return true; + } + return (field.type.children ?? []).some((child: Field) => + containsBlobField(child), + ); +} + function isObject(value: unknown): value is Record { return ( typeof value === "object" && @@ -480,6 +512,32 @@ function transposeData( path: string[] = [], ): Vector { const valuesPath = [...path, field.name]; + if (isBlobField(field) && field.type instanceof Struct) { + const blobRows = data.map((datum) => + coerceBlobValue(valueAtPath(datum, valuesPath)), + ); + const childVectors = field.type.children.map((child) => { + const values = blobRows.map((row) => + row == null ? null : (row[child.name as "data" | "uri"] ?? null), + ); + return makeVector(values, child.type, undefined, child.nullable); + }); + const nullCount = blobRows.filter((row) => row === null).length; + const structData = makeData({ + type: field.type, + length: blobRows.length, + nullCount, + nullBitmap: + nullCount > 0 + ? arrowUtil.packBools(blobRows.map((row) => row !== null)) + : undefined, + children: childVectors.map((v) => v.data[0]), + }); + return arrowMakeVector(structData); + } + if (isList(field.type) && containsBlobField(field.type.children[0])) { + return transposeListData(data, field, valuesPath); + } const values = data.map((datum) => valueAtPath(datum, valuesPath)); if (field.type instanceof Struct) { const childFields = field.type.children; @@ -495,7 +553,7 @@ function transposeData( nullCount > 0 ? arrowUtil.packBools(values.map((value) => value !== null)) : undefined, - children: childVectors as unknown as ArrowData[], + children: childVectors.map((v) => v.data[0]), }); return arrowMakeVector(structData); } else { @@ -503,6 +561,48 @@ function transposeData( } } +function transposeListData( + data: Record[], + field: Field, + valuesPath: string[], +): Vector { + const listType = field.type as List; + const childField = listType.children[0]; + const lists = data.map((datum) => valueAtPath(datum, valuesPath)); + const flattened: Record[] = []; + const validity: boolean[] = []; + const offsets: number[] = [0]; + + for (const list of lists) { + if (list == null) { + validity.push(false); + offsets.push(flattened.length); + continue; + } + if (!Array.isArray(list)) { + throw new Error(`expected an array for list field '${field.name}'`); + } + validity.push(true); + for (const element of list) { + flattened.push({ [childField.name]: element }); + } + offsets.push(flattened.length); + } + + const childVector = transposeData(flattened, childField, []); + const nullCount = validity.filter((valid) => !valid).length; + return arrowMakeVector( + makeData({ + type: listType, + length: lists.length, + nullCount, + nullBitmap: nullCount > 0 ? arrowUtil.packBools(validity) : undefined, + valueOffsets: Int32Array.from(offsets), + child: childVector.data[0], + }), + ); +} + /** * Create an empty Arrow table with the provided schema */ @@ -952,6 +1052,7 @@ export async function fromTableToBuffer( schema = sanitizeSchema(schema); } const tableWithEmbeddings = await applyEmbeddings(table, embeddings, schema); + validateBlobSchema(tableWithEmbeddings.schema); const writer = RecordBatchFileWriter.writeAll(tableWithEmbeddings); return Buffer.from(await writer.toUint8Array()); } diff --git a/nodejs/lancedb/blob.ts b/nodejs/lancedb/blob.ts new file mode 100644 index 000000000..244faac09 --- /dev/null +++ b/nodejs/lancedb/blob.ts @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +import { Field, LargeBinary, Struct, Utf8 } from "apache-arrow"; +import { BlobFile as NativeBlobFile } from "./native"; + +const BLOB_V2_EXTENSION_NAME = "lance.blob.v2"; + +const INLINE_SIZE_THRESHOLD_KEY = "lance-encoding:blob-inline-size-threshold"; +const DEDICATED_SIZE_THRESHOLD_KEY = + "lance-encoding:blob-dedicated-size-threshold"; +const PACK_FILE_SIZE_THRESHOLD_KEY = + "lance-encoding:blob-pack-file-size-threshold"; + +export type BlobInput = { + data: Buffer | Uint8Array | null; + uri: string | null; +}; + +export type BlobOptions = { + /** Defaults to true. */ + nullable?: boolean; + /** + * Max payload bytes kept inline in the data file. Zero is allowed. Must be a + * safe integer. + */ + inlineSizeThreshold?: number; + /** + * Max payload bytes stored in a packed sidecar before a dedicated file. Must + * be a positive safe integer. + */ + dedicatedSizeThreshold?: number; + /** + * Max bytes in one packed sidecar before starting another. Must be a positive + * safe integer. + */ + packFileSizeThreshold?: number; +}; + +/** + * Declares a `lance.blob.v2` column. + * + * Query results are descriptors, not payload bytes. Use {@link Table.fetchBlobs} + * or {@link Table.fetchBlobFiles} to read bytes. + * + * @example + * ```ts + * import { readFile } from "node:fs/promises"; + * import { Field, Int64, Schema } from "apache-arrow"; + * import { blob, connect } from "@lancedb/lancedb"; + * + * const db = await connect("./data"); + * const video = await readFile("clip.mp4"); + * const table = await db.createTable( + * "videos", + * [{ id: 1n, video }], + * { + * schema: new Schema([ + * new Field("id", new Int64()), + * blob("video"), + * ]), + * }, + * ); + * + * const rows = await table.query().select(["id"]).withRowId().toArray(); + * const rowIds = rows.map((row) => row._rowid as bigint); + * const bytes = await table.fetchBlobs("video", rowIds); + * + * const [handle] = await table.fetchBlobFiles("video", rowIds); + * const size = handle!.size(); + * const header = await handle!.readRange(0n, size < 65536n ? size : 65536n); + * ``` + */ +export function blob(name: string, options: BlobOptions = {}): Field { + const metadata = new Map([ + ["ARROW:extension:name", BLOB_V2_EXTENSION_NAME], + ]); + setThreshold( + metadata, + INLINE_SIZE_THRESHOLD_KEY, + "inlineSizeThreshold", + options.inlineSizeThreshold, + 0, + ); + setThreshold( + metadata, + DEDICATED_SIZE_THRESHOLD_KEY, + "dedicatedSizeThreshold", + options.dedicatedSizeThreshold, + 1, + ); + setThreshold( + metadata, + PACK_FILE_SIZE_THRESHOLD_KEY, + "packFileSizeThreshold", + options.packFileSizeThreshold, + 1, + ); + return new Field( + name, + new Struct([ + new Field("data", new LargeBinary(), true), + new Field("uri", new Utf8(), true), + ]), + options.nullable ?? true, + metadata, + ); +} + +/** + * Checks for the `lance.blob.v2` extension marker. Does not validate the + * field's storage type. + */ +export function isBlobField(field: Field): boolean { + return field.metadata?.get("ARROW:extension:name") === BLOB_V2_EXTENSION_NAME; +} + +/** + * A lazy handle to blob bytes. Create one with {@link Table.fetchBlobFiles}. + * + * @hideconstructor + */ +export class BlobFile { + private readonly inner: NativeBlobFile; + + private constructor(inner: NativeBlobFile) { + if (!(inner instanceof NativeBlobFile)) { + throw new Error("BlobFile handles come from Table.fetchBlobFiles"); + } + this.inner = inner; + } + + /** @ignore */ + static fromNative(inner: NativeBlobFile): BlobFile { + return new BlobFile(inner); + } + + /** Returns the blob size in bytes. */ + size(): bigint { + return this.inner.size(); + } + + /** + * Reads from the cursor to the end and advances the cursor. + * + * A second call returns an empty buffer. {@link BlobFile.readRange} does + * not move the cursor. + */ + read(): Promise { + return this.inner.read(); + } + + /** + * Reads the half-open byte range `[start, end)`. + * + * Fails when `end` is past the blob size. Does not move the cursor. + */ + readRange(start: bigint, end: bigint): Promise { + return this.inner.readRange(start, end); + } +} + +export function coerceBlobValue(value: unknown): BlobInput | null { + if (value == null) { + return null; + } + if (isBlobBytes(value)) { + return { data: value, uri: null }; + } + if (ArrayBuffer.isView(value)) { + throw new Error("Blob data must be Buffer or Uint8Array"); + } + if (typeof value === "string") { + if (value === "") { + throw new Error("Blob uri cannot be empty"); + } + return { data: null, uri: value }; + } + if (typeof value === "object") { + const record = value as Record; + if (!("data" in record) && !("uri" in record)) { + throw new Error( + "Blob struct values must include a 'data' or 'uri' field", + ); + } + const uri = record.uri; + if (uri === "") { + throw new Error("Blob uri cannot be empty"); + } + if (uri != null && typeof uri !== "string") { + throw new Error(`Blob uri must be a string or null, got ${typeof uri}`); + } + const data = record.data; + if (data != null && !isBlobBytes(data)) { + throw new Error("Blob data must be Buffer, Uint8Array, or null"); + } + const bytes = (data as Buffer | Uint8Array | null | undefined) ?? null; + const uriValue = uri ?? null; + if ((bytes == null) === (uriValue == null)) { + throw new Error( + "Blob struct values must set exactly one of 'data' or 'uri'", + ); + } + return { data: bytes, uri: uriValue }; + } + throw new Error( + "Blob column values must be Buffer, Uint8Array, a URI string, null, or { data?, uri? }", + ); +} + +function isBlobBytes(value: unknown): value is Buffer | Uint8Array { + return Buffer.isBuffer(value) || value instanceof Uint8Array; +} + +function setThreshold( + metadata: Map, + key: string, + optionName: string, + value: number | undefined, + minimum: number, +): void { + if (value === undefined) { + return; + } + if (!Number.isSafeInteger(value)) { + throw new Error(`${optionName} must be a safe integer`); + } + if (value < minimum) { + throw new Error( + minimum <= 0 + ? `${optionName} must be non-negative` + : `${optionName} must be positive`, + ); + } + metadata.set(key, String(value)); +} diff --git a/nodejs/lancedb/index.ts b/nodejs/lancedb/index.ts index 4f8ff77e5..d94007a11 100644 --- a/nodejs/lancedb/index.ts +++ b/nodejs/lancedb/index.ts @@ -77,6 +77,9 @@ export { VectorColumnOptions, } from "./arrow"; +export { blob, isBlobField, BlobFile } from "./blob"; +export type { BlobOptions } from "./blob"; + export { Connection, CreateTableOptions, diff --git a/nodejs/lancedb/table.ts b/nodejs/lancedb/table.ts index 02d4fee83..91886e869 100644 --- a/nodejs/lancedb/table.ts +++ b/nodejs/lancedb/table.ts @@ -17,6 +17,7 @@ import { tableFromIPC, } from "./arrow"; +import { BlobFile } from "./blob"; import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry"; import { IndexOptions } from "./indices"; import { Job } from "./job"; @@ -511,6 +512,35 @@ export abstract class Table { */ abstract takeRowIds(rowIds: readonly (bigint | number)[]): TakeQuery; + /** + * Blob v2 columns, including nested dotted paths. + */ + abstract blobColumns(): Promise; + + /** + * Bytes for `column` at row IDs from {@link Query.withRowId}. + * + * Reads the table's current checkout. IDs from another version can fail after + * compaction unless stable row ids are enabled. Results keep input order and + * duplicates. Null blobs are `null`. Empty blobs are empty buffers. + */ + abstract fetchBlobs( + column: string, + rowIds: readonly (bigint | number)[], + ): Promise<(Buffer | null)[]>; + + /** + * Opens lazy blob handles for `column` at the given row IDs using the + * table's current checkout. + * + * Preserves input order, duplicates, and nulls. Use this for large payloads. + * See {@link Table.fetchBlobs} for row-ID validity across versions. + */ + abstract fetchBlobFiles( + column: string, + rowIds: readonly (bigint | number)[], + ): Promise<(BlobFile | null)[]>; + /** * Create a search query to find the nearest neighbors * of the given query @@ -1161,23 +1191,34 @@ export class LocalTable extends Table { } takeRowIds(rowIds: readonly (bigint | number)[]): TakeQuery { - const ids = rowIds.map((id) => { - if (typeof id === "bigint") { - return id; - } - if (!Number.isInteger(id)) { - throw new Error("Row id must be an integer (or bigint)"); - } - if (id < 0) { - throw new Error("Row id cannot be negative"); - } - if (!Number.isSafeInteger(id)) { - throw new Error("Row id is too large for number; use bigint instead"); - } - return BigInt(id); - }); + return new TakeQuery(this.inner.takeRowIds(rowIdsToBigInts(rowIds))); + } - return new TakeQuery(this.inner.takeRowIds(ids)); + blobColumns(): Promise { + return this.inner.blobColumns(); + } + + async fetchBlobs( + column: string, + rowIds: readonly (bigint | number)[], + ): Promise<(Buffer | null)[]> { + const values = await this.inner.fetchBlobs(column, rowIdsToBigInts(rowIds)); + // N-API Option maps missing values to undefined. Collapse those to null. + return values.map((value) => value ?? null); + } + + async fetchBlobFiles( + column: string, + rowIds: readonly (bigint | number)[], + ): Promise<(BlobFile | null)[]> { + const files = await this.inner.fetchBlobFiles( + column, + rowIdsToBigInts(rowIds), + ); + // N-API Option maps missing values to undefined. Collapse those to null. + return files.map((file) => + file == null ? null : BlobFile.fromNative(file), + ); } query(): Query { @@ -1726,3 +1767,21 @@ export class Branches { )) as unknown as CherryPickResult; } } + +function rowIdsToBigInts(rowIds: readonly (bigint | number)[]): bigint[] { + return rowIds.map((id) => { + if (typeof id === "bigint") { + return id; + } + if (!Number.isInteger(id)) { + throw new Error("Row id must be an integer (or bigint)"); + } + if (id < 0) { + throw new Error("Row id cannot be negative"); + } + if (!Number.isSafeInteger(id)) { + throw new Error("Row id is too large for number; use bigint instead"); + } + return BigInt(id); + }); +} diff --git a/nodejs/npm/darwin-arm64/package.json b/nodejs/npm/darwin-arm64/package.json index 7ebfcaacb..e1ea88e62 100644 --- a/nodejs/npm/darwin-arm64/package.json +++ b/nodejs/npm/darwin-arm64/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-darwin-arm64", - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "os": ["darwin"], "cpu": ["arm64"], "main": "lancedb.darwin-arm64.node", diff --git a/nodejs/npm/linux-arm64-gnu/package.json b/nodejs/npm/linux-arm64-gnu/package.json index 1e2ad10b3..7bbbd3221 100644 --- a/nodejs/npm/linux-arm64-gnu/package.json +++ b/nodejs/npm/linux-arm64-gnu/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-arm64-gnu", - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "os": ["linux"], "cpu": ["arm64"], "main": "lancedb.linux-arm64-gnu.node", diff --git a/nodejs/npm/linux-arm64-musl/package.json b/nodejs/npm/linux-arm64-musl/package.json index d4843f743..58c488e47 100644 --- a/nodejs/npm/linux-arm64-musl/package.json +++ b/nodejs/npm/linux-arm64-musl/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-arm64-musl", - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "os": ["linux"], "cpu": ["arm64"], "main": "lancedb.linux-arm64-musl.node", diff --git a/nodejs/npm/linux-x64-gnu/package.json b/nodejs/npm/linux-x64-gnu/package.json index d4107659a..ca364168e 100644 --- a/nodejs/npm/linux-x64-gnu/package.json +++ b/nodejs/npm/linux-x64-gnu/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-x64-gnu", - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "os": ["linux"], "cpu": ["x64"], "main": "lancedb.linux-x64-gnu.node", diff --git a/nodejs/npm/linux-x64-musl/package.json b/nodejs/npm/linux-x64-musl/package.json index d14af6c09..c088a4d7d 100644 --- a/nodejs/npm/linux-x64-musl/package.json +++ b/nodejs/npm/linux-x64-musl/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-x64-musl", - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "os": ["linux"], "cpu": ["x64"], "main": "lancedb.linux-x64-musl.node", diff --git a/nodejs/npm/win32-arm64-msvc/package.json b/nodejs/npm/win32-arm64-msvc/package.json index 823db7c7c..af28f68d3 100644 --- a/nodejs/npm/win32-arm64-msvc/package.json +++ b/nodejs/npm/win32-arm64-msvc/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-win32-arm64-msvc", - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "os": [ "win32" ], diff --git a/nodejs/npm/win32-x64-msvc/package.json b/nodejs/npm/win32-x64-msvc/package.json index c2f0b0a80..ff612c4df 100644 --- a/nodejs/npm/win32-x64-msvc/package.json +++ b/nodejs/npm/win32-x64-msvc/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-win32-x64-msvc", - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "os": ["win32"], "cpu": ["x64"], "main": "lancedb.win32-x64-msvc.node", diff --git a/nodejs/package.json b/nodejs/package.json index dae336765..e9621ba60 100644 --- a/nodejs/package.json +++ b/nodejs/package.json @@ -11,7 +11,7 @@ "ann" ], "private": false, - "version": "0.39.0-beta.6", + "version": "0.39.0-beta.7", "main": "dist/index.js", "exports": { ".": "./dist/index.js", diff --git a/nodejs/src/blob.rs b/nodejs/src/blob.rs new file mode 100644 index 000000000..230a11bae --- /dev/null +++ b/nodejs/src/blob.rs @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +use std::ops::Range; +use std::sync::Arc; + +use arrow_array::{Array, LargeBinaryArray}; +use lancedb::blob::BlobFile as LanceBlobFile; +use napi::bindgen_prelude::*; +use napi_derive::napi; + +use crate::error::convert_error; + +#[napi] +pub struct BlobFile { + inner: Arc, +} + +impl BlobFile { + pub(crate) fn new(inner: LanceBlobFile) -> Self { + Self { + inner: Arc::new(inner), + } + } +} + +#[napi] +impl BlobFile { + #[napi] + pub fn size(&self) -> BigInt { + BigInt::from(self.inner.size()) + } + + #[napi] + pub async fn read(&self) -> napi::Result { + let bytes = self.inner.read().await.map_err(|err| convert_error(&err))?; + Ok(Buffer::from(bytes.as_ref())) + } + + #[napi] + pub async fn read_range(&self, start: BigInt, end: BigInt) -> napi::Result { + let range = bigint_range(start, end)?; + let bytes = self + .inner + .read_range(range) + .await + .map_err(|err| convert_error(&err))?; + Ok(Buffer::from(bytes.as_ref())) + } +} + +fn bigint_range(start: BigInt, end: BigInt) -> napi::Result> { + let start = parse_u64(start, "start")?; + let end = parse_u64(end, "end")?; + if start > end { + return Err(napi::Error::from_reason(format!( + "invalid blob range: start ({start}) > end ({end})" + ))); + } + Ok(start..end) +} + +fn parse_u64(value: BigInt, name: &str) -> napi::Result { + let (negative, value, lossless) = value.get_u64(); + if negative { + return Err(napi::Error::from_reason(format!( + "{name} cannot be negative" + ))); + } + if !lossless { + return Err(napi::Error::from_reason(format!( + "{name} is too large to fit in u64" + ))); + } + Ok(value) +} + +pub fn parse_row_ids(row_ids: Vec) -> napi::Result> { + row_ids + .into_iter() + .map(|id| parse_u64(id, "row id")) + .collect() +} + +pub fn copy_blob_buffers(array: LargeBinaryArray) -> Vec> { + (0..array.len()) + .map(|i| { + if array.is_null(i) { + None + } else { + Some(Buffer::from(array.value(i).to_vec())) + } + }) + .collect() +} diff --git a/nodejs/src/lib.rs b/nodejs/src/lib.rs index 1110f6203..288a2b925 100644 --- a/nodejs/src/lib.rs +++ b/nodejs/src/lib.rs @@ -10,6 +10,7 @@ use std::collections::HashMap; use env_logger::Env; use napi_derive::*; +mod blob; mod connection; mod error; mod header; diff --git a/nodejs/src/table.rs b/nodejs/src/table.rs index 12ade78e0..cf7ec4020 100644 --- a/nodejs/src/table.rs +++ b/nodejs/src/table.rs @@ -15,6 +15,7 @@ use napi::bindgen_prelude::*; use napi::threadsafe_function::{ThreadsafeFunction, ThreadsafeFunctionCallMode}; use napi_derive::napi; +use crate::blob::{BlobFile, copy_blob_buffers, parse_row_ids}; use crate::error::NapiErrorExt; use crate::index::Index; use crate::merge::NativeMergeInsertBuilder; @@ -329,6 +330,44 @@ impl Table { )) } + #[napi(catch_unwind)] + pub async fn blob_columns(&self) -> napi::Result> { + self.inner_ref()?.blob_columns().await.default_error() + } + + #[napi(catch_unwind)] + pub async fn fetch_blobs( + &self, + column: String, + row_ids: Vec, + ) -> napi::Result>> { + let row_ids = parse_row_ids(row_ids)?; + let array = self + .inner_ref()? + .fetch_blobs(column.as_str(), &row_ids) + .await + .default_error()?; + Ok(copy_blob_buffers(array)) + } + + #[napi(catch_unwind)] + pub async fn fetch_blob_files( + &self, + column: String, + row_ids: Vec, + ) -> napi::Result>> { + let row_ids = parse_row_ids(row_ids)?; + let files = self + .inner_ref()? + .fetch_blob_files(column.as_str(), &row_ids) + .await + .default_error()?; + Ok(files + .into_iter() + .map(|file| file.map(BlobFile::new)) + .collect()) + } + #[napi(catch_unwind)] pub fn vector_search(&self, vector: Float32Array) -> napi::Result { self.query()?.nearest_to(vector) diff --git a/python/Cargo.toml b/python/Cargo.toml index e0c72df48..ff7a98234 100644 --- a/python/Cargo.toml +++ b/python/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "lancedb-python" -version = "0.39.0-beta.6" +version = "0.39.0-beta.7" publish = false edition.workspace = true description = "Python bindings for LanceDB" diff --git a/python/python/lancedb/embeddings/utils.py b/python/python/lancedb/embeddings/utils.py index 189bbe53c..98806fa52 100644 --- a/python/python/lancedb/embeddings/utils.py +++ b/python/python/lancedb/embeddings/utils.py @@ -249,7 +249,7 @@ def retry_with_exponential_backoff( initial_delay (float): Initial delay in seconds (default is 1). exponential_base (float): The base for exponential backoff (default is 2). jitter (bool): Whether to add jitter to the delay (default is True). - max_retries (int): Maximum number of retries (default is 10). + max_retries (int): Maximum number of retries (default is 7). Returns: function: The decorated function. diff --git a/python/python/tests/test_first_class_function_slice2.py b/python/python/tests/test_first_class_function_slice2.py index 4816019d6..900f69f8d 100644 --- a/python/python/tests/test_first_class_function_slice2.py +++ b/python/python/tests/test_first_class_function_slice2.py @@ -15,6 +15,7 @@ from pathlib import Path import subprocess import sys import threading +import urllib.parse from typing import Optional import pyarrow as pa @@ -1213,14 +1214,22 @@ def _mock_remote_function_catalog(): def log_message(self, *args): pass + def _write_response(self, status, response): + encoded = json.dumps(response).encode() + self.send_response(status) + self.send_header("Content-Type", "application/json") + self.send_header("Content-Length", str(len(encoded))) + self.end_headers() + self.wfile.write(encoded) + def do_POST(self): length = int(self.headers.get("Content-Length", "0")) body = json.loads(self.rfile.read(length) or b"{}") state["requests"].append((self.path, body)) status = 200 - if self.path == "/v1/functions/create": + if self.path == "/v1/function/normalize_score/create": state["version"] = { - "name": body["name"], + "name": "normalize_score", "version": "fv_exact", "artifact": { key: body["artifact"][key] @@ -1242,43 +1251,43 @@ def _mock_remote_function_catalog(): "job_state": "DONE", "result": state["version"], } - elif self.path == "/v1/functions/describe": - assert body == { - "name": "normalize_score", - "version": "fv_exact", - } + elif self.path == "/v1/function/normalize_score/describe": + assert body == {"version": "fv_exact"} response = state["version"] - elif self.path == "/v1/functions/list": - assert body["include_definition"] is True - if "page_token" not in body: - response = { - "functions": [ - { - "name": "normalize_score", - "version": "fv_exact", - "definition": state["version"], - } - ], - "page_token": "next", - } - else: - assert body["page_token"] == "next" - response = {"functions": []} - elif self.path == "/v1/functions/drop": - assert body == { - "name": "normalize_score", - "version": "fv_exact", - } + elif self.path == "/v1/function/normalize_score/drop": + assert body == {"version": "fv_exact"} response = {"dropped": True} else: status = 404 response = {"error": "not found"} - encoded = json.dumps(response).encode() - self.send_response(status) - self.send_header("Content-Type", "application/json") - self.send_header("Content-Length", str(len(encoded))) - self.end_headers() - self.wfile.write(encoded) + self._write_response(status, response) + + def do_GET(self): + url = urllib.parse.urlsplit(self.path) + query = { + key: values[-1] + for key, values in urllib.parse.parse_qs(url.query).items() + } + state["requests"].append((url.path, query)) + if url.path != "/v1/namespace/$/function/list": + self._write_response(404, {"error": "not found"}) + return + assert query["include_definition"] == "true" + if "page_token" not in query: + response = { + "functions": [ + { + "name": "normalize_score", + "version": "fv_exact", + "definition": state["version"], + } + ], + "page_token": "next", + } + else: + assert query["page_token"] == "next" + response = {"functions": []} + self._write_response(200, response) with http.server.HTTPServer(("localhost", 0), Handler) as server: thread = threading.Thread(target=server.serve_forever) @@ -1307,9 +1316,11 @@ def test_remote_registration_job_and_exact_version_reopen_round_trip(): assert reopened.name == "normalize_score" assert reopened.version == "fv_exact" create_request = state["requests"][0][1] - assert create_request == json.loads( + expected_request = json.loads( normalize_score.registration_request.to_canonical_json() ) + expected_request.pop("name") + assert create_request == expected_request def test_blocking_remote_registration_returns_function_version(): @@ -1325,7 +1336,7 @@ def test_blocking_remote_registration_returns_function_version(): assert created.name == "normalize_score" assert created.version == "fv_exact" assert [path for path, _ in state["requests"]] == [ - "/v1/functions/create", + "/v1/function/normalize_score/create", "/v1/jobs/describe", ] @@ -1344,10 +1355,10 @@ def test_remote_list_functions_paginates_and_returns_typed_versions(): assert functions == [created] assert state["requests"] == [ - ("/v1/functions/list", {"include_definition": True}), + ("/v1/namespace/$/function/list", {"include_definition": "true"}), ( - "/v1/functions/list", - {"include_definition": True, "page_token": "next"}, + "/v1/namespace/$/function/list", + {"include_definition": "true", "page_token": "next"}, ), ] @@ -1368,8 +1379,8 @@ async def test_async_remote_list_functions_returns_typed_versions(): assert functions == [created] assert [path for path, _ in state["requests"]] == [ - "/v1/functions/list", - "/v1/functions/list", + "/v1/namespace/$/function/list", + "/v1/namespace/$/function/list", ] @@ -1385,8 +1396,8 @@ def test_remote_drop_function_sends_exact_version(): assert state["requests"] == [ ( - "/v1/functions/drop", - {"name": "normalize_score", "version": "fv_exact"}, + "/v1/function/normalize_score/drop", + {"version": "fv_exact"}, ) ] @@ -1404,7 +1415,7 @@ async def test_async_remote_drop_function_sends_exact_version(): assert state["requests"] == [ ( - "/v1/functions/drop", - {"name": "normalize_score", "version": "fv_exact"}, + "/v1/function/normalize_score/drop", + {"version": "fv_exact"}, ) ] diff --git a/python/python/tests/test_package_metadata.py b/python/python/tests/test_package_metadata.py index 5792f457b..27def814f 100644 --- a/python/python/tests/test_package_metadata.py +++ b/python/python/tests/test_package_metadata.py @@ -9,6 +9,15 @@ from pathlib import Path import pytest +@pytest.mark.parametrize("name", ["JobInfo", "JobDescription", "JobFailureInfo"]) +def test_job_metadata_types_have_resolvable_modules(name): + """Documentation tools resolve re-exports through each type's module.""" + public_type = getattr(importlib.import_module("lancedb.job"), name) + defining_module = importlib.import_module(public_type.__module__) + + assert getattr(defining_module, public_type.__name__, None) is public_type + + def test_pyo3_abi_matches_minimum_supported_python(): project_dir = Path(__file__).parents[2] pyproject = (project_dir / "pyproject.toml").read_text() diff --git a/python/src/job.rs b/python/src/job.rs index 4922c701a..e22b2f897 100644 --- a/python/src/job.rs +++ b/python/src/job.rs @@ -151,7 +151,7 @@ impl Job { } /// A row from `Connection.list_jobs`: one server-side job. -#[pyclass(get_all, skip_from_py_object)] +#[pyclass(module = "lancedb._lancedb", get_all, skip_from_py_object)] #[derive(Clone)] pub struct JobInfo { job_id: String, @@ -184,7 +184,7 @@ impl From for JobInfo { } /// The server's account of why a job failed. -#[pyclass(get_all, skip_from_py_object)] +#[pyclass(module = "lancedb._lancedb", get_all, skip_from_py_object)] #[derive(Clone)] pub struct JobFailureInfo { phase: Option, @@ -203,7 +203,7 @@ impl JobFailureInfo { } /// The server-side record behind a `Job` handle. -#[pyclass(get_all, skip_from_py_object)] +#[pyclass(module = "lancedb._lancedb", get_all, skip_from_py_object)] #[derive(Clone)] pub struct JobDescription { job_id: String, diff --git a/rust/lancedb/Cargo.toml b/rust/lancedb/Cargo.toml index c8f17d50c..404753d7a 100644 --- a/rust/lancedb/Cargo.toml +++ b/rust/lancedb/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "lancedb" -version = "0.39.0-beta.6" +version = "0.39.0-beta.7" edition.workspace = true description = "LanceDB: A serverless, low-latency vector database for AI applications" license.workspace = true diff --git a/rust/lancedb/src/remote/db.rs b/rust/lancedb/src/remote/db.rs index 32ace368e..1d6f9abe8 100644 --- a/rust/lancedb/src/remote/db.rs +++ b/rust/lancedb/src/remote/db.rs @@ -591,7 +591,15 @@ impl Database for RemoteDatabase { &self, request: FunctionRegistrationRequest, ) -> Result> { - let req = self.client.post("/v1/functions/create").json(&request); + let function_id = urlencoding::encode(&request.name); + let req = self + .client + .post(&format!("/v1/function/{function_id}/create")) + .json(&serde_json::json!({ + "artifact": request.artifact, + "signature": request.signature, + "runtime": request.runtime, + })); let (request_id, response) = self.client.send(req).await?; let response = self.client.check_response(&request_id, response).await?; let status = response.status(); @@ -608,11 +616,11 @@ impl Database for RemoteDatabase { } async fn get_function(&self, name: &str, version: &str) -> Result { + let function_id = urlencoding::encode(name); let req = self .client - .post("/v1/functions/describe") + .post(&format!("/v1/function/{function_id}/describe")) .json(&serde_json::json!({ - "name": name, "version": version, })); let (request_id, response) = self.client.send(req).await?; @@ -621,15 +629,19 @@ impl Database for RemoteDatabase { } async fn list_functions(&self) -> Result> { + let namespace_id = build_namespace_identifier(&[], &self.client.id_delimiter); + let path = format!("/v1/namespace/{namespace_id}/function/list"); let mut functions = Vec::new(); let mut page_token: Option = None; let mut seen_page_tokens = HashSet::new(); loop { - let mut body = serde_json::json!({ "include_definition": true }); + let mut req = self + .client + .get(&path) + .query(&[("include_definition", true)]); if let Some(token) = &page_token { - body["page_token"] = serde_json::Value::String(token.clone()); + req = req.query(&[("page_token", token)]); } - let req = self.client.post("/v1/functions/list").json(&body); let (request_id, response) = self.client.send(req).await?; let response = self.client.check_response(&request_id, response).await?; let status = response.status(); @@ -658,11 +670,11 @@ impl Database for RemoteDatabase { } async fn drop_function(&self, name: &str, version: &str) -> Result { + let function_id = urlencoding::encode(name); let req = self .client - .post("/v1/functions/drop") + .post(&format!("/v1/function/{function_id}/drop")) .json(&serde_json::json!({ - "name": name, "version": version, })); let (request_id, response) = self.client.send(req).await?; @@ -688,6 +700,7 @@ impl Database for RemoteDatabase { async fn list_jobs(&self) -> Result> { let mut out = Vec::new(); let mut page_token: Option = None; + let mut seen_page_tokens = HashSet::new(); for page in 0..MAX_LIST_JOBS_PAGES { let mut body = serde_json::json!({}); if let Some(token) = &page_token { @@ -696,7 +709,8 @@ impl Database for RemoteDatabase { let req = self.client.post("/v1/jobs/list").json(&body); let (request_id, rsp) = self.client.send(req).await?; let rsp = self.client.check_response(&request_id, rsp).await?; - let body: RemoteListJobsResponse = rsp.json().await.err_to_http(request_id)?; + let status = rsp.status(); + let body: RemoteListJobsResponse = rsp.json().await.err_to_http(request_id.clone())?; out.extend(body.jobs.into_iter().map(|row| JobInfo { job_id: row.job_id, table: row.table, @@ -704,10 +718,17 @@ impl Database for RemoteDatabase { state: job_state_to_client(&row.state), created_at_millis: row.created_at_millis, })); - page_token = body.page_token; - if page_token.is_none() { + let Some(next_page_token) = body.page_token.filter(|token| !token.is_empty()) else { break; + }; + if !seen_page_tokens.insert(next_page_token.clone()) { + return Err(Error::Http { + source: "Job listing response repeated a page_token".into(), + request_id, + status_code: Some(status), + }); } + page_token = Some(next_page_token); if page + 1 == MAX_LIST_JOBS_PAGES { log::warn!( "list_jobs truncated after {} pages ({} jobs)", @@ -2622,6 +2643,37 @@ mod tests { assert_eq!(jobs[2].state, "failed"); } + #[tokio::test] + async fn test_list_jobs_rejects_a_page_token_cycle() { + let requests = Arc::new(AtomicUsize::new(0)); + let seen = requests.clone(); + let conn = Connection::new_with_handler(move |request| { + let body: serde_json::Value = + serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); + match seen.fetch_add(1, Ordering::SeqCst) { + 0 => assert!(body.get("page_token").is_none()), + _ => assert_eq!(body["page_token"], "loop"), + } + http::Response::builder() + .status(200) + .body(r#"{"jobs": [], "page_token": "loop"}"#) + .unwrap() + }); + + let error = conn.list_jobs().await.unwrap_err(); + assert!( + matches!( + &error, + Error::Http { + status_code: Some(http::StatusCode::OK), + .. + } + ), + "got {error:?}" + ); + assert_eq!(requests.load(Ordering::SeqCst), 2); + } + #[tokio::test] async fn test_open_job() { let conn = Connection::new_with_handler(|request| { @@ -2788,9 +2840,10 @@ mod tests { ); const FUNCTION_JOB: &str = include_str!("../../tests/fixtures/first_class_functions/v1/remote_function_job.json"); - let expected: serde_json::Value = serde_json::from_str(REQUEST).unwrap(); + let mut expected: serde_json::Value = serde_json::from_str(REQUEST).unwrap(); + expected.as_object_mut().unwrap().remove("name"); let conn = Connection::new_with_handler(move |request| match request.url().path() { - "/v1/functions/create" => { + "/v1/function/normalize_score/create" => { assert_eq!(request.method(), &reqwest::Method::POST); let body: serde_json::Value = serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); @@ -2821,13 +2874,10 @@ mod tests { ); let conn = Connection::new_with_handler(|request| { assert_eq!(request.method(), &reqwest::Method::POST); - assert_eq!(request.url().path(), "/v1/functions/describe"); + assert_eq!(request.url().path(), "/v1/function/embed/describe"); let body: serde_json::Value = serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); - assert_eq!( - body, - serde_json::json!({"name": "embed", "version": "fv_01K3EXACT"}) - ); + assert_eq!(body, serde_json::json!({"version": "fv_01K3EXACT"})); http::Response::builder().status(200).body(VERSION).unwrap() }); let version = conn.get_function("embed", "fv_01K3EXACT").await.unwrap(); @@ -2843,21 +2893,20 @@ mod tests { let version: serde_json::Value = serde_json::from_str(VERSION).unwrap(); let page = Arc::new(AtomicUsize::new(0)); let conn = Connection::new_with_handler(move |request| { - assert_eq!(request.method(), &reqwest::Method::POST); - assert_eq!(request.url().path(), "/v1/functions/list"); - let body: serde_json::Value = - serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); - assert_eq!(body["include_definition"], true); + assert_eq!(request.method(), &reqwest::Method::GET); + assert_eq!(request.url().path(), "/v1/namespace/$/function/list"); + let query = request.url().query_pairs().collect::>(); + assert_eq!(query.get("include_definition").unwrap(), "true"); match page.fetch_add(1, Ordering::SeqCst) { 0 => { - assert!(body.get("page_token").is_none()); + assert!(!query.contains_key("page_token")); http::Response::builder() .status(200) .body(r#"{"functions": [], "page_token": "next"}"#.to_string()) .unwrap() } _ => { - assert_eq!(body["page_token"], "next"); + assert_eq!(query.get("page_token").unwrap(), "next"); http::Response::builder() .status(200) .body( @@ -2886,9 +2935,11 @@ mod tests { let seen = requests.clone(); let conn = Connection::new_with_handler(move |request| { seen.fetch_add(1, Ordering::SeqCst); - let body: serde_json::Value = - serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); - assert!(body.get("page_token").is_none()); + assert_eq!(request.method(), &reqwest::Method::GET); + assert_eq!(request.url().path(), "/v1/namespace/$/function/list"); + let query = request.url().query_pairs().collect::>(); + assert_eq!(query.get("include_definition").unwrap(), "true"); + assert!(!query.contains_key("page_token")); http::Response::builder() .status(200) .body(r#"{"functions": [], "page_token": ""}"#) @@ -2905,19 +2956,21 @@ mod tests { let page = Arc::new(AtomicUsize::new(0)); let requests = page.clone(); let conn = Connection::new_with_handler(move |request| { - let body: serde_json::Value = - serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); + assert_eq!(request.method(), &reqwest::Method::GET); + assert_eq!(request.url().path(), "/v1/namespace/$/function/list"); + let query = request.url().query_pairs().collect::>(); + assert_eq!(query.get("include_definition").unwrap(), "true"); let next_page_token = match page.fetch_add(1, Ordering::SeqCst) { 0 => { - assert!(body.get("page_token").is_none()); + assert!(!query.contains_key("page_token")); "one" } 1 => { - assert_eq!(body["page_token"], "one"); + assert_eq!(query.get("page_token").unwrap(), "one"); "two" } 2 => { - assert_eq!(body["page_token"], "two"); + assert_eq!(query.get("page_token").unwrap(), "two"); "one" } page => panic!("unexpected page: {page}"), @@ -2952,13 +3005,10 @@ mod tests { async fn test_drop_function_sends_exact_version_and_decodes_replay() { let conn = Connection::new_with_handler(|request| { assert_eq!(request.method(), &reqwest::Method::POST); - assert_eq!(request.url().path(), "/v1/functions/drop"); + assert_eq!(request.url().path(), "/v1/function/embed/drop"); let body: serde_json::Value = serde_json::from_slice(request.body().unwrap().as_bytes().unwrap()).unwrap(); - assert_eq!( - body, - serde_json::json!({"name": "embed", "version": "fv_01K3EXACT"}) - ); + assert_eq!(body, serde_json::json!({"version": "fv_01K3EXACT"})); http::Response::builder() .status(200) .body(r#"{"dropped":false}"#)