From fe1cedc87e2f5e7df82e072a5908f687d9bf584f Mon Sep 17 00:00:00 2001 From: Andrew Lamb Date: Mon, 20 Jul 2026 14:47:09 -0400 Subject: [PATCH] chore: test with sparse page mask --- Cargo.lock | 84 +++++++++++++++++++++++------------------------------- Cargo.toml | 17 +++++++++++ 2 files changed, 52 insertions(+), 49 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index f00c931f15032..21d3063cebe95 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -165,8 +165,7 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50" [[package]] name = "arrow" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b952ca5a8046ad741b60f142d6eca4aeebcad615694202bc64c5341f23e32c5b" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-arith", "arrow-array", @@ -188,8 +187,7 @@ dependencies = [ [[package]] name = "arrow-arith" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "64a13b8d3008c4e9063c597a08f46446fe3fd5789277127672d6c0bdbb43b1ff" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -202,8 +200,7 @@ dependencies = [ [[package]] name = "arrow-array" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "9486151b2f0785bafc6fa04fc5c99fcb4495455662e58787ea32eaaed33c4192" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "ahash", "arrow-buffer", @@ -213,6 +210,7 @@ dependencies = [ "chrono-tz", "half", "hashbrown 0.17.1", + "libc", "num-complex", "num-integer", "num-traits", @@ -221,8 +219,7 @@ dependencies = [ [[package]] name = "arrow-avro" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "2e4f9b23a0d7b613acb59fa20bdbe0f80ffdae6411498378340b3915e45f5b84" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -245,20 +242,18 @@ dependencies = [ [[package]] name = "arrow-buffer" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c4776577a87794bfdf0b4e90e2ea12454fa7738ea2823c4be5b9d1851da7b434" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "bytes", "half", - "num-bigint", + "num-bigint 0.5.1", "num-traits", ] [[package]] name = "arrow-cast" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a9ad451ce4f98710828a455b96991b8f031deb2e67f5fcad6773f017e4a69c3a" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -279,8 +274,7 @@ dependencies = [ [[package]] name = "arrow-csv" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "8aa7bf96d6141a7bcca2eed57c7c9767d2a2175281857b8a7b68308992864784" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-cast", @@ -294,8 +288,7 @@ dependencies = [ [[package]] name = "arrow-data" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "b38fe43e2e8704360f1464e6e8cc4fc381ef02cc4fb0192afa8df1aaa0115c66" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-buffer", "arrow-schema", @@ -307,8 +300,7 @@ dependencies = [ [[package]] name = "arrow-flight" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "42115e09dbb694b5955da998912121451c6910b338228cb80a5701370dba43ff" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-arith", "arrow-array", @@ -325,7 +317,6 @@ dependencies = [ "bytes", "futures", "once_cell", - "paste", "prost", "prost-types", "tonic", @@ -335,8 +326,7 @@ dependencies = [ [[package]] name = "arrow-ipc" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "29dac499fcbc6ba74ee0324057821d381929a48526a3966bd9dffb44aa06d98c" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -351,8 +341,7 @@ dependencies = [ [[package]] name = "arrow-json" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0fe05e916ddc50f4c7a363cd69c0ef5894fcee063517e9a0b8582f0c56746af6" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -376,8 +365,7 @@ dependencies = [ [[package]] name = "arrow-ord" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0e13dbdc2a9c053c10c7baa6e30faee04a180aa7ce88e471835850ce37abd20b" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -389,8 +377,7 @@ dependencies = [ [[package]] name = "arrow-row" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "4d5a1f8c733d15260b305683472ee8ad89c62cbd706703ca873b90d051b41592" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -402,8 +389,7 @@ dependencies = [ [[package]] name = "arrow-schema" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "d9e4969dc350d571766247143ab36a5187d095d3d3690970408bc630d47c69e5" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "bitflags", "serde", @@ -414,8 +400,7 @@ dependencies = [ [[package]] name = "arrow-select" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "402770dba90865359d98d1ef92ef16e23d75c0cca9c2c880c8a05468b7743bf9" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "ahash", "arrow-array", @@ -428,8 +413,7 @@ dependencies = [ [[package]] name = "arrow-string" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "a2b0afbb8b9016700938291123df30838b89decc3213dba00852021988b170d3" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "arrow-array", "arrow-buffer", @@ -1007,7 +991,7 @@ checksum = "4d6867f1565b3aad85681f1015055b087fcfd840d6aeee6eee7f2da317603695" dependencies = [ "autocfg", "libm", - "num-bigint", + "num-bigint 0.4.6", "num-integer", "num-traits", ] @@ -4053,9 +4037,9 @@ checksum = "112b39cec0b298b6c1999fee3e31427f74f676e4cb9879ed1a121b43661a4154" [[package]] name = "lz4_flex" -version = "0.13.0" +version = "0.14.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "db9a0d582c2874f68138a16ce1867e0ffde6c0bb0a0df85e1f36d04146db488a" +checksum = "ecbdfe44b1bd960b68170b417450a628c43f7cf56bb3c5317e61cb230ee7f226" dependencies = [ "twox-hash", ] @@ -4198,7 +4182,7 @@ version = "0.4.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "35bd024e8b2ff75562e5f34e7f4905839deb4b22955ef5e73d2fea1b9813cb23" dependencies = [ - "num-bigint", + "num-bigint 0.4.6", "num-complex", "num-integer", "num-iter", @@ -4216,6 +4200,16 @@ dependencies = [ "num-traits", ] +[[package]] +name = "num-bigint" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "93e7820bc0a80a0238e650327316f929ba18d5be054b647490a3a6a339f3e7c0" +dependencies = [ + "num-integer", + "num-traits", +] + [[package]] name = "num-complex" version = "0.4.6" @@ -4257,7 +4251,7 @@ version = "0.4.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f83d14da390562dca69fc84082e73e548e1ad308d24accdedd2720017cb37824" dependencies = [ - "num-bigint", + "num-bigint 0.4.6", "num-integer", "num-traits", ] @@ -4464,8 +4458,7 @@ dependencies = [ [[package]] name = "parquet" version = "59.1.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "5302d4da74d6596a1f11f9928767995b53bca657cbeea1e4e8c5074f8a1157dd" +source = "git+https://github.com/hhhizzz/arrow-rs.git?branch=fix%2Fparquet-mask-sparse-pages#f1a32c5e96521dccae46ff386c371cd0cb127df8" dependencies = [ "ahash", "arrow-array", @@ -4483,11 +4476,10 @@ dependencies = [ "half", "hashbrown 0.17.1", "lz4_flex", - "num-bigint", + "num-bigint 0.5.1", "num-integer", "num-traits", "object_store", - "paste", "ring", "seq-macro", "simdutf8", @@ -4522,12 +4514,6 @@ dependencies = [ "syn", ] -[[package]] -name = "paste" -version = "1.0.15" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a" - [[package]] name = "pbjson" version = "0.8.0" diff --git a/Cargo.toml b/Cargo.toml index fef23162ffac4..84fa1fa9a16c9 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -294,3 +294,20 @@ debug = false debug-assertions = false strip = "debuginfo" incremental = false + +## Temporary arrow-rs patch to test https://github.com/apache/arrow-rs/pull/10288 + +[patch.crates-io] +arrow = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-array = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-avro = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-buffer = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-cast = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-data = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-ipc = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-schema = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-select = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-string = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-ord = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +arrow-flight = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" } +parquet = { git = "https://github.com/hhhizzz/arrow-rs.git", branch = "fix/parquet-mask-sparse-pages" }