chore(deps): Update arrow and datafusion to 49.0.0

This commit copies in our dependency code from influxdb_iox in order for
us to be able to upgrade from a forked version of 46.0.0 to 49.0.0 of
both arrow and datafusion. Most of the important changes were around how
we consumed the crates in influxdb3(_server/_write). Those diffs are
particularly worth looking at as the rest was a straight copy and we
don't touch those crates in our development currently for influxdb3
edge.

Cargo.toml

@@ -98,18 +98,41 @@ edition = "2021"
 license = "MIT OR Apache-2.0"
 
 [workspace.dependencies]
-arrow = { version = "46.0.0" }
-arrow-flight = { version = "46.0.0" }
-datafusion = { git = "https://github.com/apache/arrow-datafusion.git", rev = "81f33b0e27f5694348cd953a937203d835b57178", default-features = false }
-datafusion-proto = { git = "https://github.com/apache/arrow-datafusion.git", rev = "81f33b0e27f5694348cd953a937203d835b57178" }
+arrow = { version = "49.0.0", features = ["prettyprint", "chrono-tz"] }
+arrow-buffer = { version = "49.0.0" }
+arrow-flight = { version = "49.0.0", features = ["flight-sql-experimental"] }
+datafusion = { git = "https://github.com/apache/arrow-datafusion.git", rev = "0e53c6d816f3a9d3d27c6ebb6d25b1699e5553e7" }
+datafusion-proto = { git = "https://github.com/apache/arrow-datafusion.git", rev = "0e53c6d816f3a9d3d27c6ebb6d25b1699e5553e7" }
+hashbrown = { version = "0.14.3" }
+object_store = { version = "0.8.0" }
+parquet = { version = "49.0.0", features = ["object_store"] }
+pbjson = { version = "0.6.0" }
+pbjson-build = { version = "0.6.2" }
+pbjson-types = { version = "0.6.0" }
+prost = { version = "0.12.3" }
+prost-build = { version = "0.12.2" }
+prost-types = { version = "0.12.3" }
+sqlparser = { version = "0.41.0" }
+tonic = { version = "0.10.2", features = ["tls", "tls-roots"] }
+tonic-build = { version = "0.10.2" }
+tonic-health = { version = "0.10.2" }
+tonic-reflection = { version = "0.10.2" }
 
-hashbrown = { version = "0.14.0" }
-object_store = { version = "0.7.0" }
-parquet = { version = "46.0.0" }
-tonic = { version = "0.9.2", features = ["tls", "tls-webpki-roots"] }
-tonic-build = { version = "0.9.2" }
-tonic-health = { version = "0.9.2" }
-tonic-reflection = { version = "0.9.2" }
+[workspace.lints.rust]
+rust_2018_idioms = "deny"
+unreachable_pub = "deny"
+missing_debug_implementations = "deny"
+missing_copy_implementations = "deny"
+
+[workspace.lints.clippy]
+dbg_macro = "deny"
+todo = "deny"
+clone_on_ref_ptr = "deny"
+future_not_send = "deny"
+
+[workspace.lints.rustdoc]
+broken_intra_doc_links = "deny"
+bare_urls = "deny"
 
 # This profile optimizes for runtime performance and small binary size at the expense of longer
 # build times. It's most suitable for final release builds.
@@ -135,19 +158,3 @@ opt-level = 3
 
 [profile.dev.package.similar]
 opt-level = 3
-
-[patch.crates-io]
-# Can remove after arrow 47 is released
-# Pin to https://github.com/apache/arrow-rs/pull/4790
-# To get fixes for
-# - https://github.com/apache/arrow-rs/issues/4788,
-# - https://github.com/apache/arrow-rs/pull/4799
-arrow = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-arrow-array = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-arrow-buffer = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-arrow-schema = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-arrow-select = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-arrow-string = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-arrow-ord = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-arrow-flight = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }
-parquet = { git = "https://github.com/alamb/arrow-rs.git", rev = "7c236c06bfb78c0c877055c1617d9373971511a5" }

arrow_util/Cargo.toml

@@ -6,22 +6,24 @@ authors.workspace = true
 edition.workspace = true
 license.workspace = true
 
+[lints]
+workspace = true
+
 [dependencies]
 ahash = { version = "0.8", default-features = false, features = ["runtime-rng"] }
-# need dyn_cmp_dict feature for comparing dictionary arrays
-arrow = { workspace = true, features = ["prettyprint", "dyn_cmp_dict"] }
+arrow = { workspace = true }
 # used by arrow anyway (needed for printing workaround)
 chrono = { version = "0.4", default-features = false }
-comfy-table = { version = "7.0", default-features = false }
+comfy-table = { version = "7.1", default-features = false }
 hashbrown = { workspace = true }
 num-traits = "0.2"
-once_cell = { version = "1.18", features = ["parking_lot"] }
-regex = "1.9.5"
-snafu = "0.7"
+once_cell = { version = "1.19", features = ["parking_lot"] }
+regex = "1.10.2"
+snafu = "0.8"
 uuid = "1"
 workspace-hack = { version = "0.1", path = "../workspace-hack" }
 
-
 [dev-dependencies]
 datafusion = { workspace = true }
+proptest = { version = "1.4.0", default-features = false, features = ["std"] }
 rand = "0.8.3"