From 1853c92848de3cb4c1398c00a5871838d7fcef8b Mon Sep 17 00:00:00 2001 From: osipovartem Date: Sun, 11 Oct 2026 08:52:44 +0300 Subject: [PATCH 1/6] Align Arrow revision for CSV invalid UTF-8 recovery --- Cargo.lock | 38 +++++++++++++++++++------------------- Cargo.toml | 18 +++++++++--------- 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 35d74540b6cdc..78c24036d1d86 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -165,7 +165,7 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" [[package]] name = "arrow" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-arith", "arrow-array", @@ -187,7 +187,7 @@ dependencies = [ [[package]] name = "arrow-arith" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -200,7 +200,7 @@ dependencies = [ [[package]] name = "arrow-array" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "ahash", "arrow-buffer", @@ -219,7 +219,7 @@ dependencies = [ [[package]] name = "arrow-avro" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -242,7 +242,7 @@ dependencies = [ [[package]] name = "arrow-buffer" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "bytes", "half", @@ -253,7 +253,7 @@ dependencies = [ [[package]] name = "arrow-cast" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -274,7 +274,7 @@ dependencies = [ [[package]] name = "arrow-csv" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-cast", @@ -288,7 +288,7 @@ dependencies = [ [[package]] name = "arrow-data" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-buffer", "arrow-schema", @@ -300,7 +300,7 @@ dependencies = [ [[package]] name = "arrow-flight" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-arith", "arrow-array", @@ -326,7 +326,7 @@ dependencies = [ [[package]] name = "arrow-ipc" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -341,7 +341,7 @@ dependencies = [ [[package]] name = "arrow-json" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -365,7 +365,7 @@ dependencies = [ [[package]] name = "arrow-ord" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -377,7 +377,7 @@ dependencies = [ [[package]] name = "arrow-row" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -389,7 +389,7 @@ dependencies = [ [[package]] name = "arrow-schema" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "bitflags", "serde", @@ -400,7 +400,7 @@ dependencies = [ [[package]] name = "arrow-select" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "ahash", "arrow-array", @@ -413,7 +413,7 @@ dependencies = [ [[package]] name = "arrow-string" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "arrow-array", "arrow-buffer", @@ -4486,7 +4486,7 @@ dependencies = [ [[package]] name = "parquet" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=0e9c0b17db31ff260254d7dbfeecffe535675ed5#0e9c0b17db31ff260254d7dbfeecffe535675ed5" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" dependencies = [ "ahash", "arrow-array", @@ -4865,7 +4865,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "03da047801ff44bb6a4d407d4860c05fd70bb81714e6b2f3812603d5b145b042" dependencies = [ "heck", - "itertools 0.14.0", + "itertools 0.13.0", "log", "multimap", "petgraph", @@ -4884,7 +4884,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b570b25f7617e43d59005d0990ccb79e950a423952cea19671b7a876da390adf" dependencies = [ "anyhow", - "itertools 0.14.0", + "itertools 0.13.0", "proc-macro2", "quote", "syn 2.0.119", diff --git a/Cargo.toml b/Cargo.toml index bd20cf9b3b6a2..ea7bcce6788ce 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -89,30 +89,30 @@ version = "55.1.0" # # See for more details: https://github.com/rust-lang/cargo/issues/11329 apache-avro = { version = "0.21", default-features = false } -arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", features = [ +arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", features = [ "prettyprint", "chrono-tz", ] } -arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", default-features = false, features = [ +arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false, features = [ "deflate", "snappy", "zstd", "bzip2", "xz", ] } -arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", default-features = false } -arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", default-features = false } -arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", features = [ +arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } +arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } +arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", features = [ "flight-sql-experimental", ] } # Both codecs are required here to make sure that code paths like # file-spilling have access to all compression codecs. -arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", default-features = false, features = [ +arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false, features = [ "lz4", "zstd", ] } -arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", default-features = false } -arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", default-features = false } +arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } +arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } async-trait = "0.1.89" bigdecimal = "0.4.8" bytes = "1.11" @@ -178,7 +178,7 @@ memchr = "2.8.1" num-traits = { version = "0.2" } object_store = { version = "0.13.2", default-features = false } parking_lot = "0.12" -parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "0e9c0b17db31ff260254d7dbfeecffe535675ed5", default-features = false, features = [ +parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false, features = [ "arrow", "async", "object_store", From 44b05b1604e567fdf1b13481e1b459a928b51d56 Mon Sep 17 00:00:00 2001 From: osipovartem Date: Sun, 11 Oct 2026 09:00:32 +0300 Subject: [PATCH 2/6] Use Arrow CSV invalid UTF-8 public API --- Cargo.lock | 38 +++++++++++++++++++------------------- Cargo.toml | 18 +++++++++--------- 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 78c24036d1d86..94645f3604232 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -165,7 +165,7 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" [[package]] name = "arrow" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-arith", "arrow-array", @@ -187,7 +187,7 @@ dependencies = [ [[package]] name = "arrow-arith" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -200,7 +200,7 @@ dependencies = [ [[package]] name = "arrow-array" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "ahash", "arrow-buffer", @@ -219,7 +219,7 @@ dependencies = [ [[package]] name = "arrow-avro" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -242,7 +242,7 @@ dependencies = [ [[package]] name = "arrow-buffer" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "bytes", "half", @@ -253,7 +253,7 @@ dependencies = [ [[package]] name = "arrow-cast" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -274,7 +274,7 @@ dependencies = [ [[package]] name = "arrow-csv" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-cast", @@ -288,7 +288,7 @@ dependencies = [ [[package]] name = "arrow-data" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-buffer", "arrow-schema", @@ -300,7 +300,7 @@ dependencies = [ [[package]] name = "arrow-flight" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-arith", "arrow-array", @@ -326,7 +326,7 @@ dependencies = [ [[package]] name = "arrow-ipc" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -341,7 +341,7 @@ dependencies = [ [[package]] name = "arrow-json" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -365,7 +365,7 @@ dependencies = [ [[package]] name = "arrow-ord" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -377,7 +377,7 @@ dependencies = [ [[package]] name = "arrow-row" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -389,7 +389,7 @@ dependencies = [ [[package]] name = "arrow-schema" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "bitflags", "serde", @@ -400,7 +400,7 @@ dependencies = [ [[package]] name = "arrow-select" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "ahash", "arrow-array", @@ -413,7 +413,7 @@ dependencies = [ [[package]] name = "arrow-string" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "arrow-array", "arrow-buffer", @@ -4486,7 +4486,7 @@ dependencies = [ [[package]] name = "parquet" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=9a35f512a88bedf199d1f737025df75b11029fb7#9a35f512a88bedf199d1f737025df75b11029fb7" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" dependencies = [ "ahash", "arrow-array", @@ -4865,7 +4865,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "03da047801ff44bb6a4d407d4860c05fd70bb81714e6b2f3812603d5b145b042" dependencies = [ "heck", - "itertools 0.13.0", + "itertools 0.14.0", "log", "multimap", "petgraph", @@ -4884,7 +4884,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b570b25f7617e43d59005d0990ccb79e950a423952cea19671b7a876da390adf" dependencies = [ "anyhow", - "itertools 0.13.0", + "itertools 0.14.0", "proc-macro2", "quote", "syn 2.0.119", diff --git a/Cargo.toml b/Cargo.toml index ea7bcce6788ce..a4acdd9e8492b 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -89,30 +89,30 @@ version = "55.1.0" # # See for more details: https://github.com/rust-lang/cargo/issues/11329 apache-avro = { version = "0.21", default-features = false } -arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", features = [ +arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", features = [ "prettyprint", "chrono-tz", ] } -arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false, features = [ +arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false, features = [ "deflate", "snappy", "zstd", "bzip2", "xz", ] } -arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } -arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } -arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", features = [ +arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } +arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } +arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", features = [ "flight-sql-experimental", ] } # Both codecs are required here to make sure that code paths like # file-spilling have access to all compression codecs. -arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false, features = [ +arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false, features = [ "lz4", "zstd", ] } -arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } -arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false } +arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } +arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } async-trait = "0.1.89" bigdecimal = "0.4.8" bytes = "1.11" @@ -178,7 +178,7 @@ memchr = "2.8.1" num-traits = { version = "0.2" } object_store = { version = "0.13.2", default-features = false } parking_lot = "0.12" -parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "9a35f512a88bedf199d1f737025df75b11029fb7", default-features = false, features = [ +parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false, features = [ "arrow", "async", "object_store", From ca8ff6d85cea276aeaa6077a14605aeaa605baf9 Mon Sep 17 00:00:00 2001 From: osipovartem Date: Sun, 11 Oct 2026 09:50:27 +0300 Subject: [PATCH 3/6] Pin final Arrow CSV invalid UTF-8 recovery revision --- Cargo.lock | 38 +++++++++++++++++++------------------- Cargo.toml | 18 +++++++++--------- 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 94645f3604232..5ab0837823e01 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -165,7 +165,7 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" [[package]] name = "arrow" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-arith", "arrow-array", @@ -187,7 +187,7 @@ dependencies = [ [[package]] name = "arrow-arith" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -200,7 +200,7 @@ dependencies = [ [[package]] name = "arrow-array" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "ahash", "arrow-buffer", @@ -219,7 +219,7 @@ dependencies = [ [[package]] name = "arrow-avro" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -242,7 +242,7 @@ dependencies = [ [[package]] name = "arrow-buffer" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "bytes", "half", @@ -253,7 +253,7 @@ dependencies = [ [[package]] name = "arrow-cast" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -274,7 +274,7 @@ dependencies = [ [[package]] name = "arrow-csv" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-cast", @@ -288,7 +288,7 @@ dependencies = [ [[package]] name = "arrow-data" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-buffer", "arrow-schema", @@ -300,7 +300,7 @@ dependencies = [ [[package]] name = "arrow-flight" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-arith", "arrow-array", @@ -326,7 +326,7 @@ dependencies = [ [[package]] name = "arrow-ipc" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -341,7 +341,7 @@ dependencies = [ [[package]] name = "arrow-json" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -365,7 +365,7 @@ dependencies = [ [[package]] name = "arrow-ord" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -377,7 +377,7 @@ dependencies = [ [[package]] name = "arrow-row" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -389,7 +389,7 @@ dependencies = [ [[package]] name = "arrow-schema" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "bitflags", "serde", @@ -400,7 +400,7 @@ dependencies = [ [[package]] name = "arrow-select" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "ahash", "arrow-array", @@ -413,7 +413,7 @@ dependencies = [ [[package]] name = "arrow-string" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "arrow-array", "arrow-buffer", @@ -4486,7 +4486,7 @@ dependencies = [ [[package]] name = "parquet" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=071137e276b7d86dd2e495c4479ba600182936b9#071137e276b7d86dd2e495c4479ba600182936b9" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" dependencies = [ "ahash", "arrow-array", @@ -4865,7 +4865,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "03da047801ff44bb6a4d407d4860c05fd70bb81714e6b2f3812603d5b145b042" dependencies = [ "heck", - "itertools 0.14.0", + "itertools 0.13.0", "log", "multimap", "petgraph", @@ -4884,7 +4884,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b570b25f7617e43d59005d0990ccb79e950a423952cea19671b7a876da390adf" dependencies = [ "anyhow", - "itertools 0.14.0", + "itertools 0.13.0", "proc-macro2", "quote", "syn 2.0.119", diff --git a/Cargo.toml b/Cargo.toml index a4acdd9e8492b..8bc153467583e 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -89,30 +89,30 @@ version = "55.1.0" # # See for more details: https://github.com/rust-lang/cargo/issues/11329 apache-avro = { version = "0.21", default-features = false } -arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", features = [ +arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", features = [ "prettyprint", "chrono-tz", ] } -arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false, features = [ +arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false, features = [ "deflate", "snappy", "zstd", "bzip2", "xz", ] } -arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } -arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } -arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", features = [ +arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } +arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } +arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", features = [ "flight-sql-experimental", ] } # Both codecs are required here to make sure that code paths like # file-spilling have access to all compression codecs. -arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false, features = [ +arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false, features = [ "lz4", "zstd", ] } -arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } -arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false } +arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } +arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } async-trait = "0.1.89" bigdecimal = "0.4.8" bytes = "1.11" @@ -178,7 +178,7 @@ memchr = "2.8.1" num-traits = { version = "0.2" } object_store = { version = "0.13.2", default-features = false } parking_lot = "0.12" -parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "071137e276b7d86dd2e495c4479ba600182936b9", default-features = false, features = [ +parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false, features = [ "arrow", "async", "object_store", From e2e067e78636b8375597050c1aec7ba57570a944 Mon Sep 17 00:00:00 2001 From: osipovartem Date: Sun, 11 Oct 2026 10:05:45 +0300 Subject: [PATCH 4/6] Pin Arrow CSV source-line recovery revision --- Cargo.lock | 39 ++++++++++++++++++++------------------- Cargo.toml | 18 +++++++++--------- 2 files changed, 29 insertions(+), 28 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 5ab0837823e01..ca913b20cadbe 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -165,7 +165,7 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" [[package]] name = "arrow" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-arith", "arrow-array", @@ -187,7 +187,7 @@ dependencies = [ [[package]] name = "arrow-arith" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -200,7 +200,7 @@ dependencies = [ [[package]] name = "arrow-array" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "ahash", "arrow-buffer", @@ -219,7 +219,7 @@ dependencies = [ [[package]] name = "arrow-avro" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -242,7 +242,7 @@ dependencies = [ [[package]] name = "arrow-buffer" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "bytes", "half", @@ -253,7 +253,7 @@ dependencies = [ [[package]] name = "arrow-cast" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -274,7 +274,7 @@ dependencies = [ [[package]] name = "arrow-csv" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-cast", @@ -282,13 +282,14 @@ dependencies = [ "chrono", "csv", "csv-core", + "memchr", "regex", ] [[package]] name = "arrow-data" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-buffer", "arrow-schema", @@ -300,7 +301,7 @@ dependencies = [ [[package]] name = "arrow-flight" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-arith", "arrow-array", @@ -326,7 +327,7 @@ dependencies = [ [[package]] name = "arrow-ipc" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -341,7 +342,7 @@ dependencies = [ [[package]] name = "arrow-json" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -365,7 +366,7 @@ dependencies = [ [[package]] name = "arrow-ord" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -377,7 +378,7 @@ dependencies = [ [[package]] name = "arrow-row" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -389,7 +390,7 @@ dependencies = [ [[package]] name = "arrow-schema" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "bitflags", "serde", @@ -400,7 +401,7 @@ dependencies = [ [[package]] name = "arrow-select" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "ahash", "arrow-array", @@ -413,7 +414,7 @@ dependencies = [ [[package]] name = "arrow-string" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "arrow-array", "arrow-buffer", @@ -4486,7 +4487,7 @@ dependencies = [ [[package]] name = "parquet" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=ef1cd05e3f47cfd153183efff5dd122ea69e5d09#ef1cd05e3f47cfd153183efff5dd122ea69e5d09" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" dependencies = [ "ahash", "arrow-array", @@ -4865,7 +4866,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "03da047801ff44bb6a4d407d4860c05fd70bb81714e6b2f3812603d5b145b042" dependencies = [ "heck", - "itertools 0.13.0", + "itertools 0.14.0", "log", "multimap", "petgraph", @@ -4884,7 +4885,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b570b25f7617e43d59005d0990ccb79e950a423952cea19671b7a876da390adf" dependencies = [ "anyhow", - "itertools 0.13.0", + "itertools 0.14.0", "proc-macro2", "quote", "syn 2.0.119", diff --git a/Cargo.toml b/Cargo.toml index 8bc153467583e..cbc2cd806e8ad 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -89,30 +89,30 @@ version = "55.1.0" # # See for more details: https://github.com/rust-lang/cargo/issues/11329 apache-avro = { version = "0.21", default-features = false } -arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", features = [ +arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", features = [ "prettyprint", "chrono-tz", ] } -arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false, features = [ +arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false, features = [ "deflate", "snappy", "zstd", "bzip2", "xz", ] } -arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } -arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } -arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", features = [ +arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } +arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } +arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", features = [ "flight-sql-experimental", ] } # Both codecs are required here to make sure that code paths like # file-spilling have access to all compression codecs. -arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false, features = [ +arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false, features = [ "lz4", "zstd", ] } -arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } -arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false } +arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } +arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } async-trait = "0.1.89" bigdecimal = "0.4.8" bytes = "1.11" @@ -178,7 +178,7 @@ memchr = "2.8.1" num-traits = { version = "0.2" } object_store = { version = "0.13.2", default-features = false } parking_lot = "0.12" -parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "ef1cd05e3f47cfd153183efff5dd122ea69e5d09", default-features = false, features = [ +parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false, features = [ "arrow", "async", "object_store", From ec3df8907ae9d3561913687544d656507cfd316b Mon Sep 17 00:00:00 2001 From: osipovartem Date: Sun, 11 Oct 2026 10:36:38 +0300 Subject: [PATCH 5/6] Pin bounded Arrow CSV UTF-8 recovery --- Cargo.lock | 38 +++++++++++++++++++------------------- Cargo.toml | 18 +++++++++--------- 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index ca913b20cadbe..61b117682a25a 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -165,7 +165,7 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" [[package]] name = "arrow" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-arith", "arrow-array", @@ -187,7 +187,7 @@ dependencies = [ [[package]] name = "arrow-arith" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -200,7 +200,7 @@ dependencies = [ [[package]] name = "arrow-array" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "ahash", "arrow-buffer", @@ -219,7 +219,7 @@ dependencies = [ [[package]] name = "arrow-avro" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -242,7 +242,7 @@ dependencies = [ [[package]] name = "arrow-buffer" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "bytes", "half", @@ -253,7 +253,7 @@ dependencies = [ [[package]] name = "arrow-cast" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -274,7 +274,7 @@ dependencies = [ [[package]] name = "arrow-csv" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-cast", @@ -289,7 +289,7 @@ dependencies = [ [[package]] name = "arrow-data" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-buffer", "arrow-schema", @@ -301,7 +301,7 @@ dependencies = [ [[package]] name = "arrow-flight" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-arith", "arrow-array", @@ -327,7 +327,7 @@ dependencies = [ [[package]] name = "arrow-ipc" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -342,7 +342,7 @@ dependencies = [ [[package]] name = "arrow-json" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -366,7 +366,7 @@ dependencies = [ [[package]] name = "arrow-ord" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -378,7 +378,7 @@ dependencies = [ [[package]] name = "arrow-row" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -390,7 +390,7 @@ dependencies = [ [[package]] name = "arrow-schema" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "bitflags", "serde", @@ -401,7 +401,7 @@ dependencies = [ [[package]] name = "arrow-select" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "ahash", "arrow-array", @@ -414,7 +414,7 @@ dependencies = [ [[package]] name = "arrow-string" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "arrow-array", "arrow-buffer", @@ -4487,7 +4487,7 @@ dependencies = [ [[package]] name = "parquet" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=6b8ce8d4407ffa79794235545df3fb0e2bb6d57c#6b8ce8d4407ffa79794235545df3fb0e2bb6d57c" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" dependencies = [ "ahash", "arrow-array", @@ -4866,7 +4866,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "03da047801ff44bb6a4d407d4860c05fd70bb81714e6b2f3812603d5b145b042" dependencies = [ "heck", - "itertools 0.14.0", + "itertools 0.13.0", "log", "multimap", "petgraph", @@ -4885,7 +4885,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b570b25f7617e43d59005d0990ccb79e950a423952cea19671b7a876da390adf" dependencies = [ "anyhow", - "itertools 0.14.0", + "itertools 0.13.0", "proc-macro2", "quote", "syn 2.0.119", diff --git a/Cargo.toml b/Cargo.toml index cbc2cd806e8ad..f61af14410f24 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -89,30 +89,30 @@ version = "55.1.0" # # See for more details: https://github.com/rust-lang/cargo/issues/11329 apache-avro = { version = "0.21", default-features = false } -arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", features = [ +arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", features = [ "prettyprint", "chrono-tz", ] } -arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false, features = [ +arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false, features = [ "deflate", "snappy", "zstd", "bzip2", "xz", ] } -arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } -arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } -arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", features = [ +arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } +arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } +arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", features = [ "flight-sql-experimental", ] } # Both codecs are required here to make sure that code paths like # file-spilling have access to all compression codecs. -arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false, features = [ +arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false, features = [ "lz4", "zstd", ] } -arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } -arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false } +arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } +arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } async-trait = "0.1.89" bigdecimal = "0.4.8" bytes = "1.11" @@ -178,7 +178,7 @@ memchr = "2.8.1" num-traits = { version = "0.2" } object_store = { version = "0.13.2", default-features = false } parking_lot = "0.12" -parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "6b8ce8d4407ffa79794235545df3fb0e2bb6d57c", default-features = false, features = [ +parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false, features = [ "arrow", "async", "object_store", From 0da0acd46f6d40244f0c8ad7efc18146e4afa396 Mon Sep 17 00:00:00 2001 From: osipovartem Date: Sun, 11 Oct 2026 10:45:55 +0300 Subject: [PATCH 6/6] Pin final Arrow CSV recovery revision --- Cargo.lock | 38 +++++++++++++++++++------------------- Cargo.toml | 18 +++++++++--------- 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 61b117682a25a..fefdba8bd5d44 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -165,7 +165,7 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" [[package]] name = "arrow" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-arith", "arrow-array", @@ -187,7 +187,7 @@ dependencies = [ [[package]] name = "arrow-arith" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -200,7 +200,7 @@ dependencies = [ [[package]] name = "arrow-array" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "ahash", "arrow-buffer", @@ -219,7 +219,7 @@ dependencies = [ [[package]] name = "arrow-avro" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -242,7 +242,7 @@ dependencies = [ [[package]] name = "arrow-buffer" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "bytes", "half", @@ -253,7 +253,7 @@ dependencies = [ [[package]] name = "arrow-cast" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -274,7 +274,7 @@ dependencies = [ [[package]] name = "arrow-csv" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-cast", @@ -289,7 +289,7 @@ dependencies = [ [[package]] name = "arrow-data" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-buffer", "arrow-schema", @@ -301,7 +301,7 @@ dependencies = [ [[package]] name = "arrow-flight" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-arith", "arrow-array", @@ -327,7 +327,7 @@ dependencies = [ [[package]] name = "arrow-ipc" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -342,7 +342,7 @@ dependencies = [ [[package]] name = "arrow-json" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -366,7 +366,7 @@ dependencies = [ [[package]] name = "arrow-ord" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -378,7 +378,7 @@ dependencies = [ [[package]] name = "arrow-row" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -390,7 +390,7 @@ dependencies = [ [[package]] name = "arrow-schema" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "bitflags", "serde", @@ -401,7 +401,7 @@ dependencies = [ [[package]] name = "arrow-select" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "ahash", "arrow-array", @@ -414,7 +414,7 @@ dependencies = [ [[package]] name = "arrow-string" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "arrow-array", "arrow-buffer", @@ -4487,7 +4487,7 @@ dependencies = [ [[package]] name = "parquet" version = "59.2.0" -source = "git+https://github.com/Embucket/arrow-rs.git?rev=3a5aecdf7ee7bafee9a37575aeda065a70be703a#3a5aecdf7ee7bafee9a37575aeda065a70be703a" +source = "git+https://github.com/Embucket/arrow-rs.git?rev=bacbe37ba111653fa1ab0e534e8570ca7321ac94#bacbe37ba111653fa1ab0e534e8570ca7321ac94" dependencies = [ "ahash", "arrow-array", @@ -4866,7 +4866,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "03da047801ff44bb6a4d407d4860c05fd70bb81714e6b2f3812603d5b145b042" dependencies = [ "heck", - "itertools 0.13.0", + "itertools 0.14.0", "log", "multimap", "petgraph", @@ -4885,7 +4885,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b570b25f7617e43d59005d0990ccb79e950a423952cea19671b7a876da390adf" dependencies = [ "anyhow", - "itertools 0.13.0", + "itertools 0.14.0", "proc-macro2", "quote", "syn 2.0.119", diff --git a/Cargo.toml b/Cargo.toml index f61af14410f24..69cf6bee34343 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -89,30 +89,30 @@ version = "55.1.0" # # See for more details: https://github.com/rust-lang/cargo/issues/11329 apache-avro = { version = "0.21", default-features = false } -arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", features = [ +arrow = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", features = [ "prettyprint", "chrono-tz", ] } -arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false, features = [ +arrow-avro = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", default-features = false, features = [ "deflate", "snappy", "zstd", "bzip2", "xz", ] } -arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } -arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } -arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", features = [ +arrow-buffer = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", default-features = false } +arrow-data = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", default-features = false } +arrow-flight = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", features = [ "flight-sql-experimental", ] } # Both codecs are required here to make sure that code paths like # file-spilling have access to all compression codecs. -arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false, features = [ +arrow-ipc = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", default-features = false, features = [ "lz4", "zstd", ] } -arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } -arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false } +arrow-ord = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", default-features = false } +arrow-schema = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", default-features = false } async-trait = "0.1.89" bigdecimal = "0.4.8" bytes = "1.11" @@ -178,7 +178,7 @@ memchr = "2.8.1" num-traits = { version = "0.2" } object_store = { version = "0.13.2", default-features = false } parking_lot = "0.12" -parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "3a5aecdf7ee7bafee9a37575aeda065a70be703a", default-features = false, features = [ +parquet = { git = "https://github.com/Embucket/arrow-rs.git", rev = "bacbe37ba111653fa1ab0e534e8570ca7321ac94", default-features = false, features = [ "arrow", "async", "object_store",