chore: upgrade datafusion to 51, arrow to 57, pyo3 to 0.26

Cargo.toml

@@ -69,17 +69,17 @@ lance-test-macros = { version = "=2.0.0-beta.4", path = "./rust/lance-test-macro
 lance-testing = { version = "=2.0.0-beta.4", path = "./rust/lance-testing" }
 approx = "0.5.1"
 # Note that this one does not include pyarrow
-arrow = { version = "56.1", optional = false, features = ["prettyprint"] }
-arrow-arith = "56.1"
-arrow-array = "56.1"
-arrow-buffer = "56.1"
-arrow-cast = "56.1"
-arrow-data = "56.1"
-arrow-ipc = { version = "56.1", features = ["zstd"] }
-arrow-ord = "56.1"
-arrow-row = "56.1"
-arrow-schema = "56.1"
-arrow-select = "56.1"
+arrow = { version = "57.0.0", optional = false, features = ["prettyprint"] }
+arrow-arith = "57.0.0"
+arrow-array = "57.0.0"
+arrow-buffer = "57.0.0"
+arrow-cast = "57.0.0"
+arrow-data = "57.0.0"
+arrow-ipc = { version = "57.0.0", features = ["zstd"] }
+arrow-ord = "57.0.0"
+arrow-row = "57.0.0"
+arrow-schema = "57.0.0"
+arrow-select = "57.0.0"
 async-recursion = "1.0"
 async-trait = "0.1"
 axum = "0.7"
@@ -107,34 +107,35 @@ criterion = { version = "0.5", features = [
     "html_reports",
 ] }
 crossbeam-queue = "0.3"
-datafusion = { version = "50.0.0", default-features = false, features = [
+datafusion = { version = "51.0.0", default-features = false, features = [
     "nested_expressions",
     "regex_expressions",
     "unicode_expressions",
     "crypto_expressions",
     "encoding_expressions",
     "datetime_expressions",
+    "sql",
     "string_expressions",
 ] }
-datafusion-common = "50.0.0"
-datafusion-functions = { version = "50.0.0", features = ["regex_expressions"] }
-datafusion-sql = "50.0.0"
-datafusion-expr = "50.0.0"
-datafusion-ffi = "50.0.0"
-datafusion-execution = "50.0.0"
-datafusion-optimizer = "50.0.0"
-datafusion-physical-expr = "50.0.0"
-datafusion-physical-plan = "50.0.0"
-datafusion-substrait = "50.0.0"
+datafusion-common = "51.0.0"
+datafusion-functions = { version = "51.0.0", features = ["regex_expressions"] }
+datafusion-sql = "51.0.0"
+datafusion-expr = "51.0.0"
+datafusion-ffi = "51.0.0"
+datafusion-execution = "51.0.0"
+datafusion-optimizer = "51.0.0"
+datafusion-physical-expr = "51.0.0"
+datafusion-physical-plan = "51.0.0"
+datafusion-substrait = "51.0.0"
 deepsize = "0.2.0"
 dirs = "6.0.0"
 either = "1.0"
 fst = { version = "0.4.7", features = ["levenshtein"] }
 fsst = { version = "=2.0.0-beta.4", path = "./rust/compression/fsst" }
 futures = "0.3"
-geoarrow-array = "0.6"
-geoarrow-schema = "0.6"
-geodatafusion = "0.1.1"
+geoarrow-array = "0.7"
+geoarrow-schema = "0.7"
+geodatafusion = "0.2.0"
 geo-traits = "0.3.0"
 geo-types = "0.7.16"
 http = "1.1.0"
@@ -157,9 +158,9 @@ pin-project = "1.0"
 path_abs = "0.5"
 pprof = { version = "0.14.0", features = ["flamegraph", "criterion"] }
 proptest = "1.3.1"
-prost = "0.13.2"
-prost-build = "0.13.2"
-prost-types = "0.13.2"
+prost = "0.14.1"
+prost-build = "0.14.1"
+prost-types = "0.14.1"
 rand = { version = "0.9.1", features = ["small_rng"] }
 rand_distr = { version = "0.5.1" }
 rand_xoshiro = "0.7.0"

deny.toml

@@ -85,7 +85,9 @@ ignore = [
     { id = "RUSTSEC-2024-0436", reason = "`paste` is used by datafusion" },
     { id = "RUSTSEC-2023-0071", reason = "`rsa` is used by opendal via reqsign" },
     { id = "RUSTSEC-2025-0119", reason = "`number_prefix` used by hf-hub in examples" },
-    { id = "RUSTSEC-2025-0134", reason = "`rustls-pemfile` unmaintained; awaiting upstream object_store/hyper-rustls migration to rustls-pki-types" }
+    { id = "RUSTSEC-2025-0134", reason = "`rustls-pemfile` unmaintained; awaiting upstream object_store/hyper-rustls migration to rustls-pki-types" },
+    { id = "RUSTSEC-2025-0141", reason = "`bincode` is unmaintained and used by tantivy"},
+    { id = "RUSTSEC-2026-0002", reason = "`lru` is used by tantivy and aws-sdk-s3"},
 ]
 # If this is true, then cargo deny will use the git executable to fetch advisory database.
 # If this is false, then it uses a built-in git library.