mirror of
https://github.com/lancedb/lancedb.git
synced 2026-09-11 15:52:17 +00:00
Compare commits
6
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Lance Release
|
243e6aea86 | ||
  LanceDB RobotandJack Ye
|
a487d4033e | ||
 dependabot[bot]
|
02ea0dda9f | ||
|
Lance Release
|
c7980dbc40 | ||
|
Jack Ye
|
1b0f9329ea | ||
|
Lance Release
|
e5cc7a4d66 |
+1
-1
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.39.0-beta.1"
|
||||
current_version = "0.39.0-beta.4"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
Generated
+49
-47
@@ -3526,8 +3526,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
|
||||
|
||||
[[package]]
|
||||
name = "fsst"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"rand 0.9.5",
|
||||
@@ -4886,8 +4886,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
|
||||
|
||||
[[package]]
|
||||
name = "lance"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arc-swap",
|
||||
"arrow",
|
||||
@@ -4959,8 +4959,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-arrow"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4982,7 +4982,7 @@ dependencies = [
|
||||
[[package]]
|
||||
name = "lance-arrow-scalar"
|
||||
version = "58.0.0"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4996,7 +4996,7 @@ dependencies = [
|
||||
[[package]]
|
||||
name = "lance-arrow-stats"
|
||||
version = "58.0.0"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-schema",
|
||||
@@ -5005,8 +5005,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-bitpacking"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrayref",
|
||||
"crunchy",
|
||||
@@ -5016,8 +5016,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-core"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -5054,8 +5054,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datafusion"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -5085,8 +5085,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datagen"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -5103,8 +5103,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-derive"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -5113,8 +5113,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-encoding"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -5147,8 +5147,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-file"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -5179,8 +5179,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-index"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arc-swap",
|
||||
"arrow",
|
||||
@@ -5244,8 +5244,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-index-core"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-schema",
|
||||
@@ -5267,8 +5267,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-io"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -5308,8 +5308,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-linalg"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-schema",
|
||||
@@ -5323,21 +5323,23 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"async-trait",
|
||||
"bytes",
|
||||
"lance-core",
|
||||
"lance-namespace-reqwest-client",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"snafu 0.9.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace-impls"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-ipc",
|
||||
@@ -5376,9 +5378,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace-reqwest-client"
|
||||
version = "0.11.1"
|
||||
version = "0.12.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1d06b1fbb5d41f93bc652b61e2872af92e8a6c5f6b4ce8839a8ecfa05365d359"
|
||||
checksum = "d8d23e54b1634d5bbb434f8dd33dc3c05f6e58d876a9a27b3b4aef58ddbe11af"
|
||||
dependencies = [
|
||||
"reqwest 0.12.28",
|
||||
"serde",
|
||||
@@ -5390,8 +5392,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-select"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -5405,8 +5407,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-table"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -5446,8 +5448,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-testing"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-schema",
|
||||
@@ -5460,8 +5462,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-tokenizer"
|
||||
version = "12.0.0-beta.11"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.11#4a0e26895729feb86d0cb9c09d551bfd619c6472"
|
||||
version = "12.0.0-beta.14"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
|
||||
dependencies = [
|
||||
"frostem",
|
||||
"icu_segmenter",
|
||||
@@ -5474,7 +5476,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb"
|
||||
version = "0.39.0-beta.1"
|
||||
version = "0.39.0-beta.3"
|
||||
dependencies = [
|
||||
"ahash",
|
||||
"anyhow",
|
||||
@@ -5565,7 +5567,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb-nodejs"
|
||||
version = "0.39.0-beta.1"
|
||||
version = "0.39.0-beta.3"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -5590,7 +5592,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb-python"
|
||||
version = "0.39.0-beta.1"
|
||||
version = "0.39.0-beta.3"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"async-trait",
|
||||
|
||||
+14
-14
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
|
||||
rust-version = "1.91.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=12.0.0-beta.11", default-features = false, "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=12.0.0-beta.11", default-features = false, "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=12.0.0-beta.11", default-features = false, "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=12.0.0-beta.11", "tag" = "v12.0.0-beta.11", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "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
|
||||
|
||||
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
|
||||
<dependency>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-core</artifactId>
|
||||
<version>0.39.0-beta.1</version>
|
||||
<version>0.39.0-beta.4</version>
|
||||
</dependency>
|
||||
```
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
<parent>
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.39.0-beta.1</version>
|
||||
<version>0.39.0-beta.4</version>
|
||||
<relativePath>../pom.xml</relativePath>
|
||||
</parent>
|
||||
|
||||
|
||||
+2
-2
@@ -6,7 +6,7 @@
|
||||
|
||||
<groupId>com.lancedb</groupId>
|
||||
<artifactId>lancedb-parent</artifactId>
|
||||
<version>0.39.0-beta.1</version>
|
||||
<version>0.39.0-beta.4</version>
|
||||
<packaging>pom</packaging>
|
||||
<name>${project.artifactId}</name>
|
||||
<description>LanceDB Java SDK Parent POM</description>
|
||||
@@ -28,7 +28,7 @@
|
||||
<properties>
|
||||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
|
||||
<arrow.version>15.0.0</arrow.version>
|
||||
<lance-core.version>12.0.0-beta.11</lance-core.version>
|
||||
<lance-core.version>12.0.0-beta.14</lance-core.version>
|
||||
<spotless.skip>false</spotless.skip>
|
||||
<spotless.version>2.30.0</spotless.version>
|
||||
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
|
||||
|
||||
+1
-1
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "lancedb-nodejs"
|
||||
edition.workspace = true
|
||||
version = "0.39.0-beta.1"
|
||||
version = "0.39.0-beta.4"
|
||||
publish = false
|
||||
license.workspace = true
|
||||
description.workspace = true
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-darwin-arm64",
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"os": ["darwin"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.darwin-arm64.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-gnu",
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-arm64-musl",
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"os": ["linux"],
|
||||
"cpu": ["arm64"],
|
||||
"main": "lancedb.linux-arm64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-gnu",
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-gnu.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-linux-x64-musl",
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"os": ["linux"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.linux-x64-musl.node",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-arm64-msvc",
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"os": [
|
||||
"win32"
|
||||
],
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb-win32-x64-msvc",
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"os": ["win32"],
|
||||
"cpu": ["x64"],
|
||||
"main": "lancedb.win32-x64-msvc.node",
|
||||
|
||||
+1
-1
@@ -11,7 +11,7 @@
|
||||
"ann"
|
||||
],
|
||||
"private": false,
|
||||
"version": "0.39.0-beta.1",
|
||||
"version": "0.39.0-beta.4",
|
||||
"main": "dist/index.js",
|
||||
"exports": {
|
||||
".": "./dist/index.js",
|
||||
|
||||
Generated
+24
-24
@@ -41,7 +41,7 @@ importers:
|
||||
version: 3.7.0(@emnapi/core@1.10.0)(@emnapi/runtime@1.11.3)(@types/node@22.7.4)
|
||||
'@opentelemetry/sdk-metrics':
|
||||
specifier: ^2.10.0
|
||||
version: 2.10.0(@opentelemetry/api@1.9.1)
|
||||
version: 2.11.0(@opentelemetry/api@1.9.1)
|
||||
'@types/axios':
|
||||
specifier: ^0.14.0
|
||||
version: 0.14.4
|
||||
@@ -80,7 +80,7 @@ importers:
|
||||
version: 0.2.7
|
||||
ts-jest:
|
||||
specifier: ^29.1.2
|
||||
version: 29.4.9(@babel/core@7.29.7)(@jest/transform@29.7.0)(@jest/types@29.6.3)(babel-jest@29.7.0(@babel/core@7.29.7))(jest-util@29.7.0)(jest@29.7.0(@types/node@22.7.4))(typescript@5.5.4)
|
||||
version: 29.4.12(@babel/core@7.29.7)(@jest/transform@29.7.0)(@jest/types@29.6.3)(babel-jest@29.7.0(@babel/core@7.29.7))(jest-util@29.7.0)(jest@29.7.0(@types/node@22.7.4))(typescript@5.5.4)
|
||||
typedoc:
|
||||
specifier: 0.26.4
|
||||
version: 0.26.4(typescript@5.5.4)
|
||||
@@ -1394,20 +1394,20 @@ packages:
|
||||
resolution: {integrity: sha512-gLyJlPHPZYdAk1JENA9LeHejZe1Ti77/pTeFm/nMXmQH/HFZlcS/O2XJB+L8fkbrNSqhdtlvjBVjxwUYanNH5Q==}
|
||||
engines: {node: '>=8.0.0'}
|
||||
|
||||
'@opentelemetry/core@2.10.0':
|
||||
resolution: {integrity: sha512-/wNZ8twnEQQA4HoHu22+vcsdru6pWPWxW+7w+FlxT6Id7PE/WIbZmVKkte+PF72e0F2dnImFeHD2syyE1Mw6MQ==}
|
||||
'@opentelemetry/core@2.11.0':
|
||||
resolution: {integrity: sha512-7YP44XH0tV6+Mb54x2YGf84i7yi+31MBZlE8JwvozkxyTvXbSp10X7cI7YE49ChJ3shMJoBmCJF3+1QFBJctGA==}
|
||||
engines: {node: ^18.19.0 || >=20.6.0}
|
||||
peerDependencies:
|
||||
'@opentelemetry/api': '>=1.0.0 <1.10.0'
|
||||
|
||||
'@opentelemetry/resources@2.10.0':
|
||||
resolution: {integrity: sha512-q6MMm2zhggzsHVNbabYwut+a6nbuQQe3URUoxaojM/8K1IBfwwPzvxIjNi2/lI1TFe+fMHMW9MWhrtDLEXEnkA==}
|
||||
'@opentelemetry/resources@2.11.0':
|
||||
resolution: {integrity: sha512-Ie7+8q8MDF4FAEQCKVMTx3ReUvxiIAgIiiW3c9JdmP8+HMcDy20puT+AHjexnExgnbvBxjQ9fjkFDWrikJ2jQA==}
|
||||
engines: {node: ^18.19.0 || >=20.6.0}
|
||||
peerDependencies:
|
||||
'@opentelemetry/api': '>=1.3.0 <1.10.0'
|
||||
|
||||
'@opentelemetry/sdk-metrics@2.10.0':
|
||||
resolution: {integrity: sha512-t6r1VSvXNtSDnPXU1FbZeetJb7yyovHmgu0wRSoftxtE0g2rSNhQZQUy69sRUCL+iioJpX8SN/S6wq6ZtvLySQ==}
|
||||
'@opentelemetry/sdk-metrics@2.11.0':
|
||||
resolution: {integrity: sha512-7GXXcObyHyDUUSG+L+kJoquty01bzm7ivE7+SSgXXJcHuPzGviptxwARmI2c+bnnxjexGQbJnyNlN8HxBP/Y7A==}
|
||||
engines: {node: ^18.19.0 || >=20.6.0}
|
||||
peerDependencies:
|
||||
'@opentelemetry/api': '>=1.9.0 <1.10.0'
|
||||
@@ -1480,6 +1480,7 @@ packages:
|
||||
'@smithy/core@3.24.1':
|
||||
resolution: {integrity: sha512-3mT7o4qQyUWttYnVK3A0Z/u3Xha3E81tXn32Tz6vjZiUXhBrkEivpw1hBYfh84iFF9CSzkBU9Y1DJ3Q6RQ231g==}
|
||||
engines: {node: '>=18.0.0'}
|
||||
deprecated: Deprecated due to bug in browser bundling instructions https://github.com/smithy-lang/smithy-typescript/issues/2025
|
||||
|
||||
'@smithy/credential-provider-imds@4.3.1':
|
||||
resolution: {integrity: sha512-0S/acwHnqX4WrjXzhdiDRxsG2s9SC0cpPIK9nZ1R6UOHd+j7uL28+4bHu22urbLk2TVw3fkp6na/+fkUt/pLNQ==}
|
||||
@@ -3238,8 +3239,8 @@ packages:
|
||||
peerDependencies:
|
||||
typescript: '>=4.2.0'
|
||||
|
||||
ts-jest@29.4.9:
|
||||
resolution: {integrity: sha512-LTb9496gYPMCqjeDLdPrKuXtncudeV1yRZnF4Wo5l3SFi0RYEnYRNgMrFIdg+FHvfzjCyQk1cLncWVqiSX+EvQ==}
|
||||
ts-jest@29.4.12:
|
||||
resolution: {integrity: sha512-Ov6ClY53Fflh6BGAnY2DlTq1hYDrTycz2PVTXBWFW2CU+9zrEqAp9fWdGXl42EXO5RLSFAcAZ2JFKbP+zBTFfw==}
|
||||
engines: {node: ^14.15.0 || ^16.10.0 || ^18.0.0 || >=20.0.0}
|
||||
hasBin: true
|
||||
peerDependencies:
|
||||
@@ -5110,22 +5111,22 @@ snapshots:
|
||||
|
||||
'@opentelemetry/api@1.9.1': {}
|
||||
|
||||
'@opentelemetry/core@2.10.0(@opentelemetry/api@1.9.1)':
|
||||
'@opentelemetry/core@2.11.0(@opentelemetry/api@1.9.1)':
|
||||
dependencies:
|
||||
'@opentelemetry/api': 1.9.1
|
||||
'@opentelemetry/semantic-conventions': 1.43.0
|
||||
|
||||
'@opentelemetry/resources@2.10.0(@opentelemetry/api@1.9.1)':
|
||||
'@opentelemetry/resources@2.11.0(@opentelemetry/api@1.9.1)':
|
||||
dependencies:
|
||||
'@opentelemetry/api': 1.9.1
|
||||
'@opentelemetry/core': 2.10.0(@opentelemetry/api@1.9.1)
|
||||
'@opentelemetry/core': 2.11.0(@opentelemetry/api@1.9.1)
|
||||
'@opentelemetry/semantic-conventions': 1.43.0
|
||||
|
||||
'@opentelemetry/sdk-metrics@2.10.0(@opentelemetry/api@1.9.1)':
|
||||
'@opentelemetry/sdk-metrics@2.11.0(@opentelemetry/api@1.9.1)':
|
||||
dependencies:
|
||||
'@opentelemetry/api': 1.9.1
|
||||
'@opentelemetry/core': 2.10.0(@opentelemetry/api@1.9.1)
|
||||
'@opentelemetry/resources': 2.10.0(@opentelemetry/api@1.9.1)
|
||||
'@opentelemetry/core': 2.11.0(@opentelemetry/api@1.9.1)
|
||||
'@opentelemetry/resources': 2.11.0(@opentelemetry/api@1.9.1)
|
||||
|
||||
'@opentelemetry/semantic-conventions@1.43.0': {}
|
||||
|
||||
@@ -5574,7 +5575,7 @@ snapshots:
|
||||
globby: 11.1.0
|
||||
is-glob: 4.0.3
|
||||
minimatch: 9.0.9
|
||||
semver: 7.8.0
|
||||
semver: 7.8.5
|
||||
ts-api-utils: 1.4.3(typescript@5.5.4)
|
||||
optionalDependencies:
|
||||
typescript: 5.5.4
|
||||
@@ -6426,7 +6427,7 @@ snapshots:
|
||||
'@babel/parser': 7.29.3
|
||||
'@istanbuljs/schema': 0.1.6
|
||||
istanbul-lib-coverage: 3.2.2
|
||||
semver: 7.8.0
|
||||
semver: 7.8.5
|
||||
transitivePeerDependencies:
|
||||
- supports-color
|
||||
|
||||
@@ -6705,7 +6706,7 @@ snapshots:
|
||||
jest-util: 29.7.0
|
||||
natural-compare: 1.4.0
|
||||
pretty-format: 29.7.0
|
||||
semver: 7.8.0
|
||||
semver: 7.8.5
|
||||
transitivePeerDependencies:
|
||||
- supports-color
|
||||
|
||||
@@ -6828,7 +6829,7 @@ snapshots:
|
||||
|
||||
make-dir@4.0.0:
|
||||
dependencies:
|
||||
semver: 7.8.0
|
||||
semver: 7.8.5
|
||||
|
||||
make-error@1.3.6: {}
|
||||
|
||||
@@ -7162,8 +7163,7 @@ snapshots:
|
||||
|
||||
semver@7.8.0: {}
|
||||
|
||||
semver@7.8.5:
|
||||
optional: true
|
||||
semver@7.8.5: {}
|
||||
|
||||
sharp@0.35.4(@types/node@22.7.4):
|
||||
dependencies:
|
||||
@@ -7327,7 +7327,7 @@ snapshots:
|
||||
dependencies:
|
||||
typescript: 5.5.4
|
||||
|
||||
ts-jest@29.4.9(@babel/core@7.29.7)(@jest/transform@29.7.0)(@jest/types@29.6.3)(babel-jest@29.7.0(@babel/core@7.29.7))(jest-util@29.7.0)(jest@29.7.0(@types/node@22.7.4))(typescript@5.5.4):
|
||||
ts-jest@29.4.12(@babel/core@7.29.7)(@jest/transform@29.7.0)(@jest/types@29.6.3)(babel-jest@29.7.0(@babel/core@7.29.7))(jest-util@29.7.0)(jest@29.7.0(@types/node@22.7.4))(typescript@5.5.4):
|
||||
dependencies:
|
||||
bs-logger: 0.2.6
|
||||
fast-json-stable-stringify: 2.1.0
|
||||
@@ -7336,7 +7336,7 @@ snapshots:
|
||||
json5: 2.2.3
|
||||
lodash.memoize: 4.1.2
|
||||
make-error: 1.3.6
|
||||
semver: 7.8.0
|
||||
semver: 7.8.5
|
||||
type-fest: 4.41.0
|
||||
typescript: 5.5.4
|
||||
yargs-parser: 21.1.1
|
||||
|
||||
+1
-1
@@ -127,7 +127,7 @@ impl Job {
|
||||
}
|
||||
|
||||
/// Serialise Arrow batches as a single IPC stream for the TypeScript layer.
|
||||
pub(crate) fn batches_to_ipc_buffer(batches: &[RecordBatch]) -> napi::Result<Buffer> {
|
||||
fn batches_to_ipc_buffer(batches: &[RecordBatch]) -> napi::Result<Buffer> {
|
||||
let Some(first) = batches.first() else {
|
||||
return Ok(Buffer::from(Vec::<u8>::new()));
|
||||
};
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb-python"
|
||||
version = "0.39.0-beta.1"
|
||||
version = "0.39.0-beta.4"
|
||||
publish = false
|
||||
edition.workspace = true
|
||||
description = "Python bindings for LanceDB"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "lancedb"
|
||||
version = "0.39.0-beta.1"
|
||||
version = "0.39.0-beta.4"
|
||||
edition.workspace = true
|
||||
description = "LanceDB: A serverless, low-latency vector database for AI applications"
|
||||
license.workspace = true
|
||||
|
||||
@@ -8021,7 +8021,7 @@ mod tests {
|
||||
match request.url().path() {
|
||||
"/v1/table/my_table/backfill_column" => http::Response::builder()
|
||||
.status(202)
|
||||
.body(r#"{"job_id": "j-42"}"#.as_bytes().to_vec())
|
||||
.body(br#"{"job_id": "j-42"}"#.to_vec())
|
||||
.unwrap(),
|
||||
"/v1/jobs/describe" => http::Response::builder()
|
||||
.status(200)
|
||||
|
||||
@@ -759,14 +759,33 @@ fn function_output_field(name: &str, nullable: bool, raw: &str) -> Result<JsonAr
|
||||
Ok(field)
|
||||
}
|
||||
|
||||
fn function_output_field_matches(expected: &ArrowField, actual: &ArrowField) -> bool {
|
||||
expected.name() == actual.name()
|
||||
&& expected.is_nullable() == actual.is_nullable()
|
||||
&& if expected.is_blob_v2() {
|
||||
/// Whether two fields describe the same Function output.
|
||||
///
|
||||
/// `compare_identity` covers the field's own name and nullability. Struct
|
||||
/// children carry both as part of the declaration and compare with it on. List
|
||||
/// children do not: Lance rewrites a list item's name and nullability when it
|
||||
/// writes, so a stored `fixed_size_list<item: float not null>` comes back as
|
||||
/// `fixed_size_list<item: float>` and never matches the declaration again.
|
||||
/// Comparing those by type alone keeps this agreeing with the server, which
|
||||
/// draws the same distinction and is what accepted the column when it was
|
||||
/// declared.
|
||||
fn function_output_field_matches(
|
||||
expected: &ArrowField,
|
||||
actual: &ArrowField,
|
||||
compare_identity: bool,
|
||||
) -> bool {
|
||||
if compare_identity
|
||||
&& (expected.name() != actual.name() || expected.is_nullable() != actual.is_nullable())
|
||||
{
|
||||
return false;
|
||||
}
|
||||
match (expected.is_blob_v2(), actual.is_blob_v2()) {
|
||||
(false, false) => function_output_type_matches(expected.data_type(), actual.data_type()),
|
||||
(true, true) => {
|
||||
has_supported_blob_v2_layout(expected) && has_supported_blob_v2_layout(actual)
|
||||
} else {
|
||||
function_output_type_matches(expected.data_type(), actual.data_type())
|
||||
}
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
fn function_output_type_matches(expected: &DataType, actual: &DataType) -> bool {
|
||||
@@ -779,33 +798,19 @@ fn function_output_type_matches(expected: &DataType, actual: &DataType) -> bool
|
||||
&& expected
|
||||
.iter()
|
||||
.zip(actual)
|
||||
.all(|(expected, actual)| function_output_field_matches(expected, actual))
|
||||
.all(|(expected, actual)| function_output_field_matches(expected, actual, true))
|
||||
}
|
||||
(DataType::List(expected), DataType::List(actual))
|
||||
| (DataType::LargeList(expected), DataType::LargeList(actual)) => {
|
||||
function_output_field_matches(expected, actual)
|
||||
function_output_field_matches(expected, actual, false)
|
||||
}
|
||||
(
|
||||
DataType::FixedSizeList(expected, expected_size),
|
||||
DataType::FixedSizeList(actual, actual_size),
|
||||
) => expected_size == actual_size && function_output_field_matches(expected, actual),
|
||||
) => expected_size == actual_size && function_output_field_matches(expected, actual, false),
|
||||
(DataType::Map(expected, expected_sorted), DataType::Map(actual, actual_sorted)) => {
|
||||
expected_sorted == actual_sorted && function_output_field_matches(expected, actual)
|
||||
}
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
fn function_output_type_has_blob(data_type: &DataType) -> bool {
|
||||
match data_type {
|
||||
DataType::Struct(fields) => fields
|
||||
.iter()
|
||||
.any(|field| field.is_blob_v2() || function_output_type_has_blob(field.data_type())),
|
||||
DataType::List(field)
|
||||
| DataType::LargeList(field)
|
||||
| DataType::FixedSizeList(field, _)
|
||||
| DataType::Map(field, _) => {
|
||||
field.is_blob_v2() || function_output_type_has_blob(field.data_type())
|
||||
expected_sorted == actual_sorted
|
||||
&& function_output_field_matches(expected, actual, true)
|
||||
}
|
||||
_ => false,
|
||||
}
|
||||
@@ -891,16 +896,13 @@ fn ensure_binding_matches_schema(schema: &ArrowSchema, binding: &FunctionBinding
|
||||
binding.binding_id()
|
||||
)));
|
||||
}
|
||||
let (type_matches, has_semantic_blob) = if output.arrow_type == FUNCTION_BLOB_V2_TYPE {
|
||||
(has_supported_blob_v2_layout(field), true)
|
||||
let type_matches = if output.arrow_type == FUNCTION_BLOB_V2_TYPE {
|
||||
has_supported_blob_v2_layout(field)
|
||||
} else {
|
||||
let expected_type = parse_output_arrow_type(&output.arrow_type)?;
|
||||
let expected_type = lance_namespace::schema::convert_json_arrow_type(&expected_type)
|
||||
.map_err(|e| invalid_function(format!("invalid Function output type: {e}")))?;
|
||||
(
|
||||
function_output_type_matches(&expected_type, field.data_type()),
|
||||
function_output_type_has_blob(&expected_type),
|
||||
)
|
||||
function_output_type_matches(&expected_type, field.data_type())
|
||||
};
|
||||
if !type_matches {
|
||||
return Err(invalid_function(format!(
|
||||
@@ -931,19 +933,16 @@ fn ensure_binding_matches_schema(schema: &ArrowSchema, binding: &FunctionBinding
|
||||
binding.binding_id()
|
||||
)));
|
||||
}
|
||||
if has_semantic_blob {
|
||||
output_fields.push(function_output_field(
|
||||
field.name(),
|
||||
true,
|
||||
&output.arrow_type,
|
||||
)?);
|
||||
} else {
|
||||
let json = lance_namespace::schema::arrow_schema_to_json(&ArrowSchema::new(vec![
|
||||
ArrowField::new(field.name().clone(), field.data_type().clone(), true),
|
||||
]))
|
||||
.map_err(|e| invalid_function(format!("invalid Function output schema: {e}")))?;
|
||||
output_fields.push(json.fields.into_iter().next().unwrap());
|
||||
}
|
||||
// Rebuild from the declaration rather than from the stored field. The
|
||||
// stored field carries Lance's write-time normalization, which would
|
||||
// never round-trip back to the schema the binding recorded -- the same
|
||||
// reason list children compare by type above. Whether the column on
|
||||
// disk still matches is settled by that comparison, not here.
|
||||
output_fields.push(function_output_field(
|
||||
field.name(),
|
||||
true,
|
||||
&output.arrow_type,
|
||||
)?);
|
||||
}
|
||||
if let Some(assignment) = binding.assignment() {
|
||||
if binding
|
||||
@@ -1815,6 +1814,69 @@ mod tests {
|
||||
assert!(super::validate_declarations(schema, &declarations).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn list_children_match_by_type_but_struct_children_by_identity() {
|
||||
use arrow_schema::Field as F;
|
||||
|
||||
// Lance rewrites a list item's name and nullability on write, so the
|
||||
// stored field is no longer identical to what was declared. Comparing
|
||||
// those by type keeps a table with a vector output usable.
|
||||
let declared =
|
||||
DataType::FixedSizeList(Arc::new(F::new("item", DataType::Float32, false)), 4);
|
||||
let stored = DataType::FixedSizeList(Arc::new(F::new("item", DataType::Float32, true)), 4);
|
||||
assert!(super::function_output_type_matches(&declared, &stored));
|
||||
|
||||
let renamed =
|
||||
DataType::FixedSizeList(Arc::new(F::new("element", DataType::Float32, true)), 4);
|
||||
assert!(super::function_output_type_matches(&declared, &renamed));
|
||||
|
||||
// The dimension is still part of the declaration.
|
||||
let resized = DataType::FixedSizeList(Arc::new(F::new("item", DataType::Float32, true)), 8);
|
||||
assert!(!super::function_output_type_matches(&declared, &resized));
|
||||
|
||||
// Struct children keep comparing by name and nullability.
|
||||
let struct_declared =
|
||||
DataType::Struct(vec![F::new("changed", DataType::Boolean, false)].into());
|
||||
let struct_nullable =
|
||||
DataType::Struct(vec![F::new("changed", DataType::Boolean, true)].into());
|
||||
let struct_renamed =
|
||||
DataType::Struct(vec![F::new("altered", DataType::Boolean, false)].into());
|
||||
assert!(super::function_output_type_matches(
|
||||
&struct_declared,
|
||||
&struct_declared
|
||||
));
|
||||
assert!(!super::function_output_type_matches(
|
||||
&struct_declared,
|
||||
&struct_nullable
|
||||
));
|
||||
assert!(!super::function_output_type_matches(
|
||||
&struct_declared,
|
||||
&struct_renamed
|
||||
));
|
||||
|
||||
// A list nested inside a struct gets the list rule.
|
||||
let nested_declared = DataType::Struct(
|
||||
vec![F::new(
|
||||
"tokens",
|
||||
DataType::List(Arc::new(F::new("item", DataType::Utf8, false))),
|
||||
true,
|
||||
)]
|
||||
.into(),
|
||||
);
|
||||
let nested_stored = DataType::Struct(
|
||||
vec![F::new(
|
||||
"tokens",
|
||||
DataType::List(Arc::new(F::new("item", DataType::Utf8, true))),
|
||||
true,
|
||||
)]
|
||||
.into(),
|
||||
);
|
||||
assert!(super::function_output_type_matches(
|
||||
&nested_declared,
|
||||
&nested_stored
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn output_arrow_type_grammar_matches_the_shared_golden() {
|
||||
let golden: serde_json::Value = serde_json::from_str(include_str!(
|
||||
@@ -3289,6 +3351,70 @@ mod tests {
|
||||
assert!(output_schema.field(0).is_blob_v2());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn binding_accepts_a_lance_normalized_list_child() {
|
||||
// The whole guard, not just the type helper: this also reaches the
|
||||
// output-schema comparison at the end of ensure_binding_matches_schema,
|
||||
// which used to rebuild the schema from the stored field and so failed
|
||||
// on exactly the same normalization.
|
||||
let input = ArrowField::new("value", DataType::Int64, false);
|
||||
let application = FunctionApplication::from_json(
|
||||
&serde_json::json!({
|
||||
"function": {"name": "embed", "version": "fv_embed"},
|
||||
"inputs": [{
|
||||
"parameter": "value",
|
||||
"kind": "column",
|
||||
"value": {"path": "value"}
|
||||
}],
|
||||
"output": {
|
||||
"kind": "scalar",
|
||||
"arrow_type": "fixed_size_list<float32, 4>",
|
||||
"nullable": false
|
||||
}
|
||||
})
|
||||
.to_string(),
|
||||
)
|
||||
.unwrap();
|
||||
let plan = plan_function_application(
|
||||
&ArrowSchema::new(vec![input.clone()]),
|
||||
&application,
|
||||
Some("embedding"),
|
||||
)
|
||||
.unwrap();
|
||||
let binding = binding_from_plan(&plan);
|
||||
|
||||
// The declaration says the item is non-nullable; Lance rewrites it to
|
||||
// nullable on write, so this is what the column looks like on disk.
|
||||
let stored = DataType::FixedSizeList(
|
||||
Arc::new(ArrowField::new("item", DataType::Float32, true)),
|
||||
4,
|
||||
);
|
||||
let output = ArrowField::new("embedding", stored, true).with_metadata(
|
||||
function_computed_column_metadata(binding.binding_id(), 0, &["value".into()]),
|
||||
);
|
||||
|
||||
ensure_binding_matches_schema(&ArrowSchema::new(vec![input.clone(), output]), &binding)
|
||||
.unwrap();
|
||||
|
||||
// A different element type is still a mismatch.
|
||||
let wrong = ArrowField::new(
|
||||
"embedding",
|
||||
DataType::FixedSizeList(
|
||||
Arc::new(ArrowField::new("item", DataType::Float64, true)),
|
||||
4,
|
||||
),
|
||||
true,
|
||||
)
|
||||
.with_metadata(function_computed_column_metadata(
|
||||
binding.binding_id(),
|
||||
0,
|
||||
&["value".into()],
|
||||
));
|
||||
assert!(
|
||||
ensure_binding_matches_schema(&ArrowSchema::new(vec![input, wrong]), &binding).is_err()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_blob_scalar_binding_accepts_full_logical_layout() {
|
||||
let input = crate::blob("image", false);
|
||||
|
||||
@@ -5,12 +5,17 @@
|
||||
//!
|
||||
//! [`super::cast::cast_to_table_schema`] calls [`coerce_blob_expr`].
|
||||
|
||||
use std::fmt;
|
||||
use std::hash::{Hash, Hasher};
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow_schema::{DataType, Field, FieldRef, Fields};
|
||||
use arrow_array::{Array, BooleanArray, RecordBatch};
|
||||
use arrow_schema::{DataType, Field, FieldRef, Fields, Schema};
|
||||
use arrow_select::nullif::nullif;
|
||||
use datafusion::functions::core::{get_field, named_struct};
|
||||
use datafusion_common::ScalarValue;
|
||||
use datafusion_common::config::ConfigOptions;
|
||||
use datafusion_expr::ColumnarValue;
|
||||
use datafusion_physical_expr::ScalarFunctionExpr;
|
||||
use datafusion_physical_expr::expressions::{CastExpr, Literal};
|
||||
use datafusion_physical_plan::PhysicalExpr;
|
||||
@@ -133,16 +138,102 @@ pub(super) fn coerce_blob_expr(
|
||||
ns_args.push(value);
|
||||
}
|
||||
|
||||
let expr: Arc<dyn PhysicalExpr> = Arc::new(ScalarFunctionExpr::new(
|
||||
let built: Arc<dyn PhysicalExpr> = Arc::new(ScalarFunctionExpr::new(
|
||||
&format!("named_struct({})", table_field.name()),
|
||||
named_struct(),
|
||||
ns_args,
|
||||
table_field.clone(),
|
||||
config.clone(),
|
||||
));
|
||||
|
||||
// `named_struct` always yields a valid struct, so a null input would land
|
||||
// as a row that set neither `data` nor `uri` -- not an absent blob but a
|
||||
// malformed one, which Lance rejects on write.
|
||||
let expr: Arc<dyn PhysicalExpr> = Arc::new(AbsentBlobIsNull {
|
||||
source: input_expr,
|
||||
built,
|
||||
field: table_field.clone(),
|
||||
});
|
||||
Ok((expr, table_field.clone()))
|
||||
}
|
||||
|
||||
/// Carries the source column's nullity onto the struct built for it.
|
||||
///
|
||||
/// This is its own expression rather than a `CASE` because the projection
|
||||
/// takes its output field from `return_field`, and the generic implementation
|
||||
/// rebuilds a bare field -- which would drop the `lance.blob.v2` extension
|
||||
/// metadata and stop the column being recognised as a blob at all.
|
||||
#[derive(Debug, Clone)]
|
||||
struct AbsentBlobIsNull {
|
||||
source: Arc<dyn PhysicalExpr>,
|
||||
built: Arc<dyn PhysicalExpr>,
|
||||
field: FieldRef,
|
||||
}
|
||||
|
||||
impl fmt::Display for AbsentBlobIsNull {
|
||||
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
write!(f, "absent_blob_is_null({}, {})", self.source, self.built)
|
||||
}
|
||||
}
|
||||
|
||||
impl PartialEq for AbsentBlobIsNull {
|
||||
fn eq(&self, other: &Self) -> bool {
|
||||
self.source.eq(&other.source) && self.built.eq(&other.built) && self.field == other.field
|
||||
}
|
||||
}
|
||||
|
||||
impl Eq for AbsentBlobIsNull {}
|
||||
|
||||
impl Hash for AbsentBlobIsNull {
|
||||
fn hash<H: Hasher>(&self, state: &mut H) {
|
||||
self.source.hash(state);
|
||||
self.built.hash(state);
|
||||
self.field.hash(state);
|
||||
}
|
||||
}
|
||||
|
||||
impl PhysicalExpr for AbsentBlobIsNull {
|
||||
fn return_field(&self, _input_schema: &Schema) -> datafusion_common::Result<FieldRef> {
|
||||
Ok(self.field.clone())
|
||||
}
|
||||
|
||||
fn nullable(&self, _input_schema: &Schema) -> datafusion_common::Result<bool> {
|
||||
Ok(true)
|
||||
}
|
||||
|
||||
fn evaluate(&self, batch: &RecordBatch) -> datafusion_common::Result<ColumnarValue> {
|
||||
let rows = batch.num_rows();
|
||||
let built = self.built.evaluate(batch)?.into_array(rows)?;
|
||||
let source = self.source.evaluate(batch)?.into_array(rows)?;
|
||||
let Some(nulls) = source.logical_nulls() else {
|
||||
return Ok(ColumnarValue::Array(built));
|
||||
};
|
||||
// `nullif` nulls the rows the mask marks true, which is where the
|
||||
// source had no value.
|
||||
let absent = BooleanArray::new(!nulls.inner(), None);
|
||||
Ok(ColumnarValue::Array(nullif(built.as_ref(), &absent)?))
|
||||
}
|
||||
|
||||
fn children(&self) -> Vec<&Arc<dyn PhysicalExpr>> {
|
||||
vec![&self.source, &self.built]
|
||||
}
|
||||
|
||||
fn with_new_children(
|
||||
self: Arc<Self>,
|
||||
children: Vec<Arc<dyn PhysicalExpr>>,
|
||||
) -> datafusion_common::Result<Arc<dyn PhysicalExpr>> {
|
||||
Ok(Arc::new(Self {
|
||||
source: children[0].clone(),
|
||||
built: children[1].clone(),
|
||||
field: self.field.clone(),
|
||||
}))
|
||||
}
|
||||
|
||||
fn fmt_sql(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
write!(f, "{self}")
|
||||
}
|
||||
}
|
||||
|
||||
enum BlobInputShape<'a> {
|
||||
Bytes,
|
||||
String,
|
||||
@@ -313,6 +404,11 @@ mod tests {
|
||||
let data = image.column_by_name("data").unwrap();
|
||||
assert!(!data.is_null(0));
|
||||
assert!(data.is_null(1));
|
||||
// The row itself has to be null, not merely a struct whose children
|
||||
// are. A present-but-empty struct set neither `data` nor `uri`, which
|
||||
// Lance rejects as malformed rather than reading as an absent blob.
|
||||
assert!(!image.is_null(0));
|
||||
assert!(image.is_null(1));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
|
||||
Reference in New Issue
Block a user