fedor/Notes
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Vendor dependencies

Browse Source
This commit is contained in:
fedor
2026-08-01 16:11:49 +03:00
parent 7f139a0241
commit 6b5e7f0f8b
29706 changed files with 9575646 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notes-service/vendor/arrow-ord/.cargo-checksum.json
Vendored
+1
View File
@@ -0,0 +1 @@
{"$comment":"This file only protects against accidental modifications. It is not a security mechanism and does not protect against malicious changes.","files":{"Cargo.lock":"22bd75819cc4e7ab6389e1fd8e9f4f4e0491d76580c7ca6dd9597237001e1da0","Cargo.toml":"3518c96e49a94fde9d129705099a6be97f427d289ff0da424bffdf755978763b","Cargo.toml.orig":"33af4eb3815305fc82526dbc165c77e18973bacaa0f420cf4d01008945ec9c5c","LICENSE.txt":"cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30","NOTICE.txt":"f5b6a58f5d2082e403c49663d87566328d40cf03f16abb01f52632a09b97c55e","src/cmp.rs":"3bcad33f02f00db560d2a6153f652920d5155db78024b08098ec6306b8dcc448","src/comparison.rs":"e1b507d1fa102bbb0f65d4359fca0057aadb33f4a81d4606d399cdde3b7b54ac","src/lib.rs":"4e42fe12e00ea6aee1d3bc0944200fd3112c7dbef81cb06c173ceb5a23a35767","src/ord.rs":"c9adfd635fbc8dd4da74bcb018c1df03331c2ccf46b8a80933856b6b1d91eddf","src/partition.rs":"bf3ab4dd560a229c9b2b64c26d29302728213aede83949344e781d824c47c76d","src/rank.rs":"d3d949d22b71fdd3472bc980c37e072f070131acff7f25e59edd0662abb65588","src/sort.rs":"ddce3cebf43da96301bc55b406756e8921a319e9697d947ecf3dd4bb95913e13"},"package":"082342947d4e5a2bcccf029a0a0397e21cb3bb8421edd9571d34fb5dd2670256"}
notes-service/vendor/arrow-ord/Cargo.lock
Generated Vendored
+611
View File
@@ -0,0 +1,611 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 4
[[package]]
name = "ahash"
version = "0.8.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
dependencies = [
"cfg-if",
"const-random",
"getrandom 0.3.4",
"once_cell",
"version_check",
"zerocopy",
]
[[package]]
name = "android_system_properties"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
dependencies = [
"libc",
]
[[package]]
name = "arrow-array"
version = "57.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c8a4ab47b3f3eac60f7fd31b81e9028fda018607bcc63451aca4f2b755269862"
dependencies = [
"ahash",
"arrow-buffer",
"arrow-data",
"arrow-schema",
"chrono",
"half",
"hashbrown",
"num-complex",
"num-integer",
"num-traits",
]
[[package]]
name = "arrow-buffer"
version = "57.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0d18b89b4c4f4811d0858175e79541fe98e33e18db3b011708bc287b1240593f"
dependencies = [
"bytes",
"half",
"num-bigint",
"num-traits",
]
[[package]]
name = "arrow-data"
version = "57.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c1683705c63dcf0d18972759eda48489028cbbff67af7d6bef2c6b7b74ab778a"
dependencies = [
"arrow-buffer",
"arrow-schema",
"half",
"num-integer",
"num-traits",
]
[[package]]
name = "arrow-ord"
version = "57.3.1"
dependencies = [
"arrow-array",
"arrow-buffer",
"arrow-data",
"arrow-schema",
"arrow-select",
"half",
"rand",
]
[[package]]
name = "arrow-schema"
version = "57.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e4cf0d4a6609679e03002167a61074a21d7b1ad9ea65e462b2c0a97f8a3b2bc6"
[[package]]
name = "arrow-select"
version = "57.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b320d86a9806923663bb0fd9baa65ecaba81cb0cd77ff8c1768b9716b4ef891"
dependencies = [
"ahash",
"arrow-array",
"arrow-buffer",
"arrow-data",
"arrow-schema",
"num-traits",
]
[[package]]
name = "autocfg"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
[[package]]
name = "bumpalo"
version = "3.20.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d20789868f4b01b2f2caec9f5c4e0213b41e3e5702a50157d699ae31ced2fcb"
[[package]]
name = "bytes"
version = "1.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33"
[[package]]
name = "cc"
version = "1.2.62"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1dce859f0832a7d088c4f1119888ab94ef4b5d6795d1ce05afb7fe159d79f98"
dependencies = [
"find-msvc-tools",
"shlex",
]
[[package]]
name = "cfg-if"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
[[package]]
name = "chrono"
version = "0.4.44"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c673075a2e0e5f4a1dde27ce9dee1ea4558c7ffe648f576438a20ca1d2acc4b0"
dependencies = [
"iana-time-zone",
"num-traits",
"windows-link",
]
[[package]]
name = "const-random"
version = "0.1.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "87e00182fe74b066627d63b85fd550ac2998d4b0bd86bfed477a0ae4c7c71359"
dependencies = [
"const-random-macro",
]
[[package]]
name = "const-random-macro"
version = "0.1.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
dependencies = [
"getrandom 0.2.17",
"once_cell",
"tiny-keccak",
]
[[package]]
name = "core-foundation-sys"
version = "0.8.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
[[package]]
name = "crunchy"
version = "0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5"
[[package]]
name = "find-msvc-tools"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
[[package]]
name = "futures-core"
version = "0.3.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7e3450815272ef58cec6d564423f6e755e25379b217b0bc688e295ba24df6b1d"
[[package]]
name = "futures-task"
version = "0.3.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "037711b3d59c33004d3856fbdc83b99d4ff37a24768fa1be9ce3538a1cde4393"
[[package]]
name = "futures-util"
version = "0.3.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "389ca41296e6190b48053de0321d02a77f32f8a5d2461dd38762c0593805c6d6"
dependencies = [
"futures-core",
"futures-task",
"pin-project-lite",
"slab",
]
[[package]]
name = "getrandom"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ff2abc00be7fca6ebc474524697ae276ad847ad0a6b3faa4bcb027e9a4614ad0"
dependencies = [
"cfg-if",
"libc",
"wasi",
]
[[package]]
name = "getrandom"
version = "0.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
dependencies = [
"cfg-if",
"libc",
"r-efi",
"wasip2",
]
[[package]]
name = "half"
version = "2.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ea2d84b969582b4b1864a92dc5d27cd2b77b622a8d79306834f1be5ba20d84b"
dependencies = [
"cfg-if",
"crunchy",
"num-traits",
"zerocopy",
]
[[package]]
name = "hashbrown"
version = "0.16.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100"
[[package]]
name = "iana-time-zone"
version = "0.1.65"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e31bc9ad994ba00e440a8aa5c9ef0ec67d5cb5e5cb0cc7f8b744a35b389cc470"
dependencies = [
"android_system_properties",
"core-foundation-sys",
"iana-time-zone-haiku",
"js-sys",
"log",
"wasm-bindgen",
"windows-core",
]
[[package]]
name = "iana-time-zone-haiku"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
dependencies = [
"cc",
]
[[package]]
name = "js-sys"
version = "0.3.98"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "67df7112613f8bfd9150013a0314e196f4800d3201ae742489d999db2f979f08"
dependencies = [
"cfg-if",
"futures-util",
"once_cell",
"wasm-bindgen",
]
[[package]]
name = "libc"
version = "0.2.186"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
[[package]]
name = "libm"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6d2cec3eae94f9f509c767b45932f1ada8350c4bdb85af2fcab4a3c14807981"
[[package]]
name = "log"
version = "0.4.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
[[package]]
name = "num-bigint"
version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a5e44f723f1133c9deac646763579fdb3ac745e418f2a7af9cd0c431da1f20b9"
dependencies = [
"num-integer",
"num-traits",
]
[[package]]
name = "num-complex"
version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495"
dependencies = [
"num-traits",
]
[[package]]
name = "num-integer"
version = "0.1.46"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f"
dependencies = [
"num-traits",
]
[[package]]
name = "num-traits"
version = "0.2.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
dependencies = [
"autocfg",
"libm",
]
[[package]]
name = "once_cell"
version = "1.21.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
[[package]]
name = "pin-project-lite"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
[[package]]
name = "ppv-lite86"
version = "0.2.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
dependencies = [
"zerocopy",
]
[[package]]
name = "proc-macro2"
version = "1.0.106"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.45"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
dependencies = [
"proc-macro2",
]
[[package]]
name = "r-efi"
version = "5.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
[[package]]
name = "rand"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "44c5af06bb1b7d3216d91932aed5265164bf384dc89cd6ba05cf59a35f5f76ea"
dependencies = [
"rand_chacha",
"rand_core",
]
[[package]]
name = "rand_chacha"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
dependencies = [
"ppv-lite86",
"rand_core",
]
[[package]]
name = "rand_core"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "76afc826de14238e6e8c374ddcc1fa19e374fd8dd986b0d2af0d02377261d83c"
dependencies = [
"getrandom 0.3.4",
]
[[package]]
name = "rustversion"
version = "1.0.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
[[package]]
name = "shlex"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
[[package]]
name = "slab"
version = "0.4.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0c790de23124f9ab44544d7ac05d60440adc586479ce501c1d6d7da3cd8c9cf5"
[[package]]
name = "syn"
version = "2.0.117"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "tiny-keccak"
version = "2.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2c9d3793400a45f954c52e73d068316d76b6f4e36977e3fcebb13a2721e80237"
dependencies = [
"crunchy",
]
[[package]]
name = "unicode-ident"
version = "1.0.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
[[package]]
name = "version_check"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
[[package]]
name = "wasi"
version = "0.11.1+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
[[package]]
name = "wasip2"
version = "1.0.3+wasi-0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "20064672db26d7cdc89c7798c48a0fdfac8213434a1186e5ef29fd560ae223d6"
dependencies = [
"wit-bindgen",
]
[[package]]
name = "wasm-bindgen"
version = "0.2.121"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49ace1d07c165b0864824eee619580c4689389afa9dc9ed3a4c75040d82e6790"
dependencies = [
"cfg-if",
"once_cell",
"rustversion",
"wasm-bindgen-macro",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.121"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e68e6f4afd367a562002c05637acb8578ff2dea1943df76afb9e83d177c8578"
dependencies = [
"quote",
"wasm-bindgen-macro-support",
]
[[package]]
name = "wasm-bindgen-macro-support"
version = "0.2.121"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d95a9ec35c64b2a7cb35d3fead40c4238d0940c86d107136999567a4703259f2"
dependencies = [
"bumpalo",
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-shared"
version = "0.2.121"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c4e0100b01e9f0d03189a92b96772a1fb998639d981193d7dbab487302513441"
dependencies = [
"unicode-ident",
]
[[package]]
name = "windows-core"
version = "0.62.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
dependencies = [
"windows-implement",
"windows-interface",
"windows-link",
"windows-result",
"windows-strings",
]
[[package]]
name = "windows-implement"
version = "0.60.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "windows-interface"
version = "0.59.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "windows-link"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
[[package]]
name = "windows-result"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
dependencies = [
"windows-link",
]
[[package]]
name = "windows-strings"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
dependencies = [
"windows-link",
]
[[package]]
name = "wit-bindgen"
version = "0.57.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1ebf944e87a7c253233ad6766e082e3cd714b5d03812acc24c318f549614536e"
[[package]]
name = "zerocopy"
version = "0.8.48"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eed437bf9d6692032087e337407a86f04cd8d6a16a37199ed57949d415bd68e9"
dependencies = [
"zerocopy-derive",
]
[[package]]
name = "zerocopy-derive"
version = "0.8.48"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "70e3cd084b1788766f53af483dd21f93881ff30d7320490ec3ef7526d203bad4"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
notes-service/vendor/arrow-ord/Cargo.toml
Vendored
+73
View File
@@ -0,0 +1,73 @@
# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.
[package]
edition = "2024"
rust-version = "1.85"
name = "arrow-ord"
version = "57.3.1"
authors = ["Apache Arrow <dev@arrow.apache.org>"]
build = false
include = [
"benches/*.rs",
"src/**/*.rs",
"Cargo.toml",
"LICENSE.txt",
"NOTICE.txt",
]
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Ordering kernels for arrow arrays"
homepage = "https://github.com/apache/arrow-rs"
readme = false
keywords = ["arrow"]
license = "Apache-2.0"
repository = "https://github.com/apache/arrow-rs"
resolver = "2"
[package.metadata.docs.rs]
all-features = true
[lib]
name = "arrow_ord"
path = "src/lib.rs"
bench = false
[dependencies.arrow-array]
version = "57.3.1"
[dependencies.arrow-buffer]
version = "57.3.1"
[dependencies.arrow-data]
version = "57.3.1"
[dependencies.arrow-schema]
version = "57.3.1"
[dependencies.arrow-select]
version = "57.3.1"
[dev-dependencies.half]
version = "2.1"
features = ["num-traits"]
default-features = false
[dev-dependencies.rand]
version = "0.9"
features = [
"std",
"std_rng",
]
default-features = false
notes-service/vendor/arrow-ord/Cargo.toml.orig
Generated Vendored
+47
View File
@@ -0,0 +1,47 @@
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
[package]
name = "arrow-ord"
version = { workspace = true }
description = "Ordering kernels for arrow arrays"
homepage = { workspace = true }
repository = { workspace = true }
authors = { workspace = true }
license = { workspace = true }
keywords = { workspace = true }
include = { workspace = true }
edition = { workspace = true }
rust-version = { workspace = true }
[lib]
name = "arrow_ord"
bench = false
[package.metadata.docs.rs]
all-features = true
[dependencies]
arrow-array = { workspace = true }
arrow-buffer = { workspace = true }
arrow-data = { workspace = true }
arrow-schema = { workspace = true }
arrow-select = { workspace = true }
[dev-dependencies]
half = { version = "2.1", default-features = false, features = ["num-traits"] }
rand = { version = "0.9", default-features = false, features = ["std", "std_rng"] }
notes-service/vendor/arrow-ord/LICENSE.txt
Vendored
+202
View File
@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
notes-service/vendor/arrow-ord/NOTICE.txt
Vendored
+84
View File
@@ -0,0 +1,84 @@
Apache Arrow
Copyright 2016-2019 The Apache Software Foundation
This product includes software developed at
The Apache Software Foundation (http://www.apache.org/).
This product includes software from the SFrame project (BSD, 3-clause).
* Copyright (C) 2015 Dato, Inc.
* Copyright (c) 2009 Carnegie Mellon University.
This product includes software from the Feather project (Apache 2.0)
https://github.com/wesm/feather
This product includes software from the DyND project (BSD 2-clause)
https://github.com/libdynd
This product includes software from the LLVM project
* distributed under the University of Illinois Open Source
This product includes software from the google-lint project
* Copyright (c) 2009 Google Inc. All rights reserved.
This product includes software from the mman-win32 project
* Copyright https://code.google.com/p/mman-win32/
* Licensed under the MIT License;
This product includes software from the LevelDB project
* Copyright (c) 2011 The LevelDB Authors. All rights reserved.
* Use of this source code is governed by a BSD-style license that can be
* Moved from Kudu http://github.com/cloudera/kudu
This product includes software from the CMake project
* Copyright 2001-2009 Kitware, Inc.
* Copyright 2012-2014 Continuum Analytics, Inc.
* All rights reserved.
This product includes software from https://github.com/matthew-brett/multibuild (BSD 2-clause)
* Copyright (c) 2013-2016, Matt Terry and Matthew Brett; all rights reserved.
This product includes software from the Ibis project (Apache 2.0)
* Copyright (c) 2015 Cloudera, Inc.
* https://github.com/cloudera/ibis
This product includes software from Dremio (Apache 2.0)
* Copyright (C) 2017-2018 Dremio Corporation
* https://github.com/dremio/dremio-oss
This product includes software from Google Guava (Apache 2.0)
* Copyright (C) 2007 The Guava Authors
* https://github.com/google/guava
This product include software from CMake (BSD 3-Clause)
* CMake - Cross Platform Makefile Generator
* Copyright 2000-2019 Kitware, Inc. and Contributors
The web site includes files generated by Jekyll.
--------------------------------------------------------------------------------
This product includes code from Apache Kudu, which includes the following in
its NOTICE file:
Apache Kudu
Copyright 2016 The Apache Software Foundation
This product includes software developed at
The Apache Software Foundation (http://www.apache.org/).
Portions of this software were developed at
Cloudera, Inc (http://www.cloudera.com/).
--------------------------------------------------------------------------------
This product includes code from Apache ORC, which includes the following in
its NOTICE file:
Apache ORC
Copyright 2013-2019 The Apache Software Foundation
This product includes software developed by The Apache Software
Foundation (http://www.apache.org/).
This product includes software developed by Hewlett-Packard:
(c) Copyright [2014-2015] Hewlett-Packard Development Company, L.P
notes-service/vendor/arrow-ord/src/cmp.rs
Vendored
+818
View File
@@ -0,0 +1,818 @@
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
//! Comparison kernels for `Array`s.
//!
//! These kernels can leverage SIMD if available on your system. Currently no runtime
//! detection is provided, you should enable the specific SIMD intrinsics using
//! `RUSTFLAGS="-C target-feature=+avx2"` for example. See the documentation
//! [here](https://doc.rust-lang.org/stable/core/arch/) for more information.
//!
use arrow_array::cast::AsArray;
use arrow_array::types::{ByteArrayType, ByteViewType};
use arrow_array::{
AnyDictionaryArray, Array, ArrowNativeTypeOp, BooleanArray, Datum, FixedSizeBinaryArray,
GenericByteArray, GenericByteViewArray, downcast_primitive_array,
};
use arrow_buffer::bit_util::ceil;
use arrow_buffer::{BooleanBuffer, NullBuffer};
use arrow_schema::ArrowError;
use arrow_select::take::take;
use std::cmp::Ordering;
use std::ops::Not;
#[derive(Debug, Copy, Clone)]
enum Op {
Equal,
NotEqual,
Less,
LessEqual,
Greater,
GreaterEqual,
Distinct,
NotDistinct,
}
impl std::fmt::Display for Op {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Op::Equal => write!(f, "=="),
Op::NotEqual => write!(f, "!="),
Op::Less => write!(f, "<"),
Op::LessEqual => write!(f, "<="),
Op::Greater => write!(f, ">"),
Op::GreaterEqual => write!(f, ">="),
Op::Distinct => write!(f, "IS DISTINCT FROM"),
Op::NotDistinct => write!(f, "IS NOT DISTINCT FROM"),
}
}
}
/// Perform `left == right` operation on two [`Datum`].
///
/// Comparing null values on either side will yield a null in the corresponding
/// slot of the resulting [`BooleanArray`].
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn eq(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::Equal, lhs, rhs)
}
/// Perform `left != right` operation on two [`Datum`].
///
/// Comparing null values on either side will yield a null in the corresponding
/// slot of the resulting [`BooleanArray`].
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn neq(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::NotEqual, lhs, rhs)
}
/// Perform `left < right` operation on two [`Datum`].
///
/// Comparing null values on either side will yield a null in the corresponding
/// slot of the resulting [`BooleanArray`].
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn lt(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::Less, lhs, rhs)
}
/// Perform `left <= right` operation on two [`Datum`].
///
/// Comparing null values on either side will yield a null in the corresponding
/// slot of the resulting [`BooleanArray`].
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn lt_eq(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::LessEqual, lhs, rhs)
}
/// Perform `left > right` operation on two [`Datum`].
///
/// Comparing null values on either side will yield a null in the corresponding
/// slot of the resulting [`BooleanArray`].
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn gt(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::Greater, lhs, rhs)
}
/// Perform `left >= right` operation on two [`Datum`].
///
/// Comparing null values on either side will yield a null in the corresponding
/// slot of the resulting [`BooleanArray`].
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn gt_eq(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::GreaterEqual, lhs, rhs)
}
/// Perform `left IS DISTINCT FROM right` operation on two [`Datum`]
///
/// [`distinct`] is similar to [`neq`], only differing in null handling. In particular, two
/// operands are considered DISTINCT if they have a different value or if one of them is NULL
/// and the other isn't. The result of [`distinct`] is never NULL.
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn distinct(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::Distinct, lhs, rhs)
}
/// Perform `left IS NOT DISTINCT FROM right` operation on two [`Datum`]
///
/// [`not_distinct`] is similar to [`eq`], only differing in null handling. In particular, two
/// operands are considered `NOT DISTINCT` if they have the same value or if both of them
/// is NULL. The result of [`not_distinct`] is never NULL.
///
/// For floating values like f32 and f64, this comparison produces an ordering in accordance to
/// the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard.
/// Note that totalOrder treats positive and negative zeros as different. If it is necessary
/// to treat them as equal, please normalize zeros before calling this kernel. See
/// [`f32::total_cmp`] and [`f64::total_cmp`].
///
/// Nested types, such as lists, are not supported as the null semantics are not well-defined.
/// For comparisons involving nested types see [`crate::ord::make_comparator`]
pub fn not_distinct(lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
compare_op(Op::NotDistinct, lhs, rhs)
}
/// Perform `op` on the provided `Datum`
#[inline(never)]
fn compare_op(op: Op, lhs: &dyn Datum, rhs: &dyn Datum) -> Result<BooleanArray, ArrowError> {
use arrow_schema::DataType::*;
let (l, l_s) = lhs.get();
let (r, r_s) = rhs.get();
let l_len = l.len();
let r_len = r.len();
if l_len != r_len && !l_s && !r_s {
return Err(ArrowError::InvalidArgumentError(format!(
"Cannot compare arrays of different lengths, got {l_len} vs {r_len}"
)));
}
let len = match l_s {
true => r_len,
false => l_len,
};
let l_nulls = l.logical_nulls();
let r_nulls = r.logical_nulls();
let l_v = l.as_any_dictionary_opt();
let l = l_v.map(|x| x.values().as_ref()).unwrap_or(l);
let l_t = l.data_type();
let r_v = r.as_any_dictionary_opt();
let r = r_v.map(|x| x.values().as_ref()).unwrap_or(r);
let r_t = r.data_type();
if r_t.is_nested() || l_t.is_nested() {
return Err(ArrowError::InvalidArgumentError(format!(
"Nested comparison: {l_t} {op} {r_t} (hint: use make_comparator instead)"
)));
} else if l_t != r_t {
return Err(ArrowError::InvalidArgumentError(format!(
"Invalid comparison operation: {l_t} {op} {r_t}"
)));
}
// Defer computation as may not be necessary
let values = || -> BooleanBuffer {
let d = downcast_primitive_array! {
(l, r) => apply(op, l.values().as_ref(), l_s, l_v, r.values().as_ref(), r_s, r_v),
(Boolean, Boolean) => apply(op, l.as_boolean(), l_s, l_v, r.as_boolean(), r_s, r_v),
(Utf8, Utf8) => apply(op, l.as_string::<i32>(), l_s, l_v, r.as_string::<i32>(), r_s, r_v),
(Utf8View, Utf8View) => apply(op, l.as_string_view(), l_s, l_v, r.as_string_view(), r_s, r_v),
(LargeUtf8, LargeUtf8) => apply(op, l.as_string::<i64>(), l_s, l_v, r.as_string::<i64>(), r_s, r_v),
(Binary, Binary) => apply(op, l.as_binary::<i32>(), l_s, l_v, r.as_binary::<i32>(), r_s, r_v),
(BinaryView, BinaryView) => apply(op, l.as_binary_view(), l_s, l_v, r.as_binary_view(), r_s, r_v),
(LargeBinary, LargeBinary) => apply(op, l.as_binary::<i64>(), l_s, l_v, r.as_binary::<i64>(), r_s, r_v),
(FixedSizeBinary(_), FixedSizeBinary(_)) => apply(op, l.as_fixed_size_binary(), l_s, l_v, r.as_fixed_size_binary(), r_s, r_v),
(Null, Null) => None,
_ => unreachable!(),
};
d.unwrap_or_else(|| BooleanBuffer::new_unset(len))
};
let l_nulls = l_nulls.filter(|n| n.null_count() > 0);
let r_nulls = r_nulls.filter(|n| n.null_count() > 0);
Ok(match (l_nulls, l_s, r_nulls, r_s) {
(Some(l), true, Some(r), true) | (Some(l), false, Some(r), false) => {
// Either both sides are scalar or neither side is scalar
match op {
Op::Distinct => {
let values = values();
let l = l.inner().bit_chunks().iter_padded();
let r = r.inner().bit_chunks().iter_padded();
let ne = values.bit_chunks().iter_padded();
let c = |((l, r), n)| (l ^ r) | (l & r & n);
let buffer = l.zip(r).zip(ne).map(c).collect();
BooleanBuffer::new(buffer, 0, len).into()
}
Op::NotDistinct => {
let values = values();
let l = l.inner().bit_chunks().iter_padded();
let r = r.inner().bit_chunks().iter_padded();
let e = values.bit_chunks().iter_padded();
let c = |((l, r), e)| u64::not(l | r) | (l & r & e);
let buffer = l.zip(r).zip(e).map(c).collect();
BooleanBuffer::new(buffer, 0, len).into()
}
_ => BooleanArray::new(values(), NullBuffer::union(Some(&l), Some(&r))),
}
}
(Some(_), true, Some(a), false) | (Some(a), false, Some(_), true) => {
// Scalar is null, other side is non-scalar and nullable
match op {
Op::Distinct => a.into_inner().into(),
Op::NotDistinct => a.into_inner().not().into(),
_ => BooleanArray::new_null(len),
}
}
(Some(nulls), is_scalar, None, _) | (None, _, Some(nulls), is_scalar) => {
// Only one side is nullable
match is_scalar {
true => match op {
// Scalar is null, other side is not nullable
Op::Distinct => BooleanBuffer::new_set(len).into(),
Op::NotDistinct => BooleanBuffer::new_unset(len).into(),
_ => BooleanArray::new_null(len),
},
false => match op {
Op::Distinct => {
let values = values();
let l = nulls.inner().bit_chunks().iter_padded();
let ne = values.bit_chunks().iter_padded();
let c = |(l, n)| u64::not(l) | n;
let buffer = l.zip(ne).map(c).collect();
BooleanBuffer::new(buffer, 0, len).into()
}
Op::NotDistinct => (nulls.inner() & &values()).into(),
_ => BooleanArray::new(values(), Some(nulls)),
},
}
}
// Neither side is nullable
(None, _, None, _) => BooleanArray::new(values(), None),
})
}
/// Perform a potentially vectored `op` on the provided `ArrayOrd`
fn apply<T: ArrayOrd>(
op: Op,
l: T,
l_s: bool,
l_v: Option<&dyn AnyDictionaryArray>,
r: T,
r_s: bool,
r_v: Option<&dyn AnyDictionaryArray>,
) -> Option<BooleanBuffer> {
if l.len() == 0 || r.len() == 0 {
return None; // Handle empty dictionaries
}
if !l_s && !r_s && (l_v.is_some() || r_v.is_some()) {
// Not scalar and at least one side has a dictionary, need to perform vectored comparison
let l_v = l_v
.map(|x| x.normalized_keys())
.unwrap_or_else(|| (0..l.len()).collect());
let r_v = r_v
.map(|x| x.normalized_keys())
.unwrap_or_else(|| (0..r.len()).collect());
assert_eq!(l_v.len(), r_v.len()); // Sanity check
Some(match op {
Op::Equal | Op::NotDistinct => apply_op_vectored(l, &l_v, r, &r_v, false, T::is_eq),
Op::NotEqual | Op::Distinct => apply_op_vectored(l, &l_v, r, &r_v, true, T::is_eq),
Op::Less => apply_op_vectored(l, &l_v, r, &r_v, false, T::is_lt),
Op::LessEqual => apply_op_vectored(r, &r_v, l, &l_v, true, T::is_lt),
Op::Greater => apply_op_vectored(r, &r_v, l, &l_v, false, T::is_lt),
Op::GreaterEqual => apply_op_vectored(l, &l_v, r, &r_v, true, T::is_lt),
})
} else {
let l_s = l_s.then(|| l_v.map(|x| x.normalized_keys()[0]).unwrap_or_default());
let r_s = r_s.then(|| r_v.map(|x| x.normalized_keys()[0]).unwrap_or_default());
let buffer = match op {
Op::Equal | Op::NotDistinct => apply_op(l, l_s, r, r_s, false, T::is_eq),
Op::NotEqual | Op::Distinct => apply_op(l, l_s, r, r_s, true, T::is_eq),
Op::Less => apply_op(l, l_s, r, r_s, false, T::is_lt),
Op::LessEqual => apply_op(r, r_s, l, l_s, true, T::is_lt),
Op::Greater => apply_op(r, r_s, l, l_s, false, T::is_lt),
Op::GreaterEqual => apply_op(l, l_s, r, r_s, true, T::is_lt),
};
// If a side had a dictionary, and was not scalar, we need to materialize this
Some(match (l_v, r_v) {
(Some(l_v), _) if l_s.is_none() => take_bits(l_v, buffer),
(_, Some(r_v)) if r_s.is_none() => take_bits(r_v, buffer),
_ => buffer,
})
}
}
/// Perform a take operation on `buffer` with the given dictionary
fn take_bits(v: &dyn AnyDictionaryArray, buffer: BooleanBuffer) -> BooleanBuffer {
let array = take(&BooleanArray::new(buffer, None), v.keys(), None).unwrap();
array.as_boolean().values().clone()
}
/// Invokes `f` with values `0..len` collecting the boolean results into a new `BooleanBuffer`
///
/// This is similar to [`arrow_buffer::MutableBuffer::collect_bool`] but with
/// the option to efficiently negate the result
fn collect_bool(len: usize, neg: bool, f: impl Fn(usize) -> bool) -> BooleanBuffer {
let mut buffer = Vec::with_capacity(ceil(len, 64));
let chunks = len / 64;
let remainder = len % 64;
buffer.extend((0..chunks).map(|chunk| {
let mut packed = 0;
for bit_idx in 0..64 {
let i = bit_idx + chunk * 64;
packed |= (f(i) as u64) << bit_idx;
}
if neg {
packed = !packed
}
packed
}));
if remainder != 0 {
let mut packed = 0;
for bit_idx in 0..remainder {
let i = bit_idx + chunks * 64;
packed |= (f(i) as u64) << bit_idx;
}
if neg {
packed = !packed
}
buffer.push(packed);
}
BooleanBuffer::new(buffer.into(), 0, len)
}
/// Applies `op` to possibly scalar `ArrayOrd`
///
/// If l is scalar `l_s` will be `Some(idx)` where `idx` is the index of the scalar value in `l`
/// If r is scalar `r_s` will be `Some(idx)` where `idx` is the index of the scalar value in `r`
///
/// If `neg` is true the result of `op` will be negated
fn apply_op<T: ArrayOrd>(
l: T,
l_s: Option<usize>,
r: T,
r_s: Option<usize>,
neg: bool,
op: impl Fn(T::Item, T::Item) -> bool,
) -> BooleanBuffer {
match (l_s, r_s) {
(None, None) => {
assert_eq!(l.len(), r.len());
collect_bool(l.len(), neg, |idx| unsafe {
op(l.value_unchecked(idx), r.value_unchecked(idx))
})
}
(Some(l_s), Some(r_s)) => {
let a = l.value(l_s);
let b = r.value(r_s);
std::iter::once(op(a, b) ^ neg).collect()
}
(Some(l_s), None) => {
let v = l.value(l_s);
collect_bool(r.len(), neg, |idx| op(v, unsafe { r.value_unchecked(idx) }))
}
(None, Some(r_s)) => {
let v = r.value(r_s);
collect_bool(l.len(), neg, |idx| op(unsafe { l.value_unchecked(idx) }, v))
}
}
}
/// Applies `op` to possibly scalar `ArrayOrd` with the given indices
fn apply_op_vectored<T: ArrayOrd>(
l: T,
l_v: &[usize],
r: T,
r_v: &[usize],
neg: bool,
op: impl Fn(T::Item, T::Item) -> bool,
) -> BooleanBuffer {
assert_eq!(l_v.len(), r_v.len());
collect_bool(l_v.len(), neg, |idx| unsafe {
let l_idx = *l_v.get_unchecked(idx);
let r_idx = *r_v.get_unchecked(idx);
op(l.value_unchecked(l_idx), r.value_unchecked(r_idx))
})
}
trait ArrayOrd {
type Item: Copy;
fn len(&self) -> usize;
fn value(&self, idx: usize) -> Self::Item {
assert!(idx < self.len());
unsafe { self.value_unchecked(idx) }
}
/// # Safety
///
/// Safe if `idx < self.len()`
unsafe fn value_unchecked(&self, idx: usize) -> Self::Item;
fn is_eq(l: Self::Item, r: Self::Item) -> bool;
fn is_lt(l: Self::Item, r: Self::Item) -> bool;
}
impl ArrayOrd for &BooleanArray {
type Item = bool;
fn len(&self) -> usize {
Array::len(self)
}
unsafe fn value_unchecked(&self, idx: usize) -> Self::Item {
unsafe { BooleanArray::value_unchecked(self, idx) }
}
fn is_eq(l: Self::Item, r: Self::Item) -> bool {
l == r
}
fn is_lt(l: Self::Item, r: Self::Item) -> bool {
!l & r
}
}
impl<T: ArrowNativeTypeOp> ArrayOrd for &[T] {
type Item = T;
fn len(&self) -> usize {
(*self).len()
}
unsafe fn value_unchecked(&self, idx: usize) -> Self::Item {
unsafe { *self.get_unchecked(idx) }
}
fn is_eq(l: Self::Item, r: Self::Item) -> bool {
l.is_eq(r)
}
fn is_lt(l: Self::Item, r: Self::Item) -> bool {
l.is_lt(r)
}
}
impl<'a, T: ByteArrayType> ArrayOrd for &'a GenericByteArray<T> {
type Item = &'a [u8];
fn len(&self) -> usize {
Array::len(self)
}
unsafe fn value_unchecked(&self, idx: usize) -> Self::Item {
unsafe { GenericByteArray::value_unchecked(self, idx).as_ref() }
}
fn is_eq(l: Self::Item, r: Self::Item) -> bool {
l == r
}
fn is_lt(l: Self::Item, r: Self::Item) -> bool {
l < r
}
}
impl<'a, T: ByteViewType> ArrayOrd for &'a GenericByteViewArray<T> {
/// This is the item type for the GenericByteViewArray::compare
/// Item.0 is the array, Item.1 is the index
type Item = (&'a GenericByteViewArray<T>, usize);
#[inline(always)]
fn is_eq(l: Self::Item, r: Self::Item) -> bool {
let l_view = unsafe { l.0.views().get_unchecked(l.1) };
let r_view = unsafe { r.0.views().get_unchecked(r.1) };
if l.0.data_buffers().is_empty() && r.0.data_buffers().is_empty() {
// For eq case, we can directly compare the inlined bytes
return l_view == r_view;
}
let l_len = *l_view as u32;
let r_len = *r_view as u32;
// This is a fast path for equality check.
// We don't need to look at the actual bytes to determine if they are equal.
if l_len != r_len {
return false;
}
if l_len == 0 && r_len == 0 {
return true;
}
// # Safety
// The index is within bounds as it is checked in value()
unsafe { GenericByteViewArray::compare_unchecked(l.0, l.1, r.0, r.1).is_eq() }
}
#[inline(always)]
fn is_lt(l: Self::Item, r: Self::Item) -> bool {
// If both arrays use only the inline buffer
if l.0.data_buffers().is_empty() && r.0.data_buffers().is_empty() {
let l_view = unsafe { l.0.views().get_unchecked(l.1) };
let r_view = unsafe { r.0.views().get_unchecked(r.1) };
return GenericByteViewArray::<T>::inline_key_fast(*l_view)
< GenericByteViewArray::<T>::inline_key_fast(*r_view);
}
// Fallback to the generic, unchecked comparison for non-inline cases
// # Safety
// The index is within bounds as it is checked in value()
unsafe { GenericByteViewArray::compare_unchecked(l.0, l.1, r.0, r.1).is_lt() }
}
fn len(&self) -> usize {
Array::len(self)
}
unsafe fn value_unchecked(&self, idx: usize) -> Self::Item {
(self, idx)
}
}
impl<'a> ArrayOrd for &'a FixedSizeBinaryArray {
type Item = &'a [u8];
fn len(&self) -> usize {
Array::len(self)
}
unsafe fn value_unchecked(&self, idx: usize) -> Self::Item {
unsafe { FixedSizeBinaryArray::value_unchecked(self, idx) }
}
fn is_eq(l: Self::Item, r: Self::Item) -> bool {
l == r
}
fn is_lt(l: Self::Item, r: Self::Item) -> bool {
l < r
}
}
/// Compares two [`GenericByteViewArray`] at index `left_idx` and `right_idx`
#[inline(always)]
pub fn compare_byte_view<T: ByteViewType>(
left: &GenericByteViewArray<T>,
left_idx: usize,
right: &GenericByteViewArray<T>,
right_idx: usize,
) -> Ordering {
assert!(left_idx < left.len());
assert!(right_idx < right.len());
if left.data_buffers().is_empty() && right.data_buffers().is_empty() {
let l_view = unsafe { left.views().get_unchecked(left_idx) };
let r_view = unsafe { right.views().get_unchecked(right_idx) };
return GenericByteViewArray::<T>::inline_key_fast(*l_view)
.cmp(&GenericByteViewArray::<T>::inline_key_fast(*r_view));
}
unsafe { GenericByteViewArray::compare_unchecked(left, left_idx, right, right_idx) }
}
#[cfg(test)]
mod tests {
use std::sync::Arc;
use arrow_array::{DictionaryArray, Int32Array, Scalar, StringArray};
use super::*;
#[test]
fn test_null_dict() {
let a = DictionaryArray::new(Int32Array::new_null(10), Arc::new(Int32Array::new_null(0)));
let r = eq(&a, &a).unwrap();
assert_eq!(r.null_count(), 10);
let a = DictionaryArray::new(
Int32Array::from(vec![1, 2, 3, 4, 5, 6]),
Arc::new(Int32Array::new_null(10)),
);
let r = eq(&a, &a).unwrap();
assert_eq!(r.null_count(), 6);
let scalar =
DictionaryArray::new(Int32Array::new_null(1), Arc::new(Int32Array::new_null(0)));
let r = eq(&a, &Scalar::new(&scalar)).unwrap();
assert_eq!(r.null_count(), 6);
let scalar =
DictionaryArray::new(Int32Array::new_null(1), Arc::new(Int32Array::new_null(0)));
let r = eq(&Scalar::new(&scalar), &Scalar::new(&scalar)).unwrap();
assert_eq!(r.null_count(), 1);
let a = DictionaryArray::new(
Int32Array::from(vec![0, 1, 2]),
Arc::new(Int32Array::from(vec![3, 2, 1])),
);
let r = eq(&a, &Scalar::new(&scalar)).unwrap();
assert_eq!(r.null_count(), 3);
}
#[test]
fn is_distinct_from_non_nulls() {
let left_int_array = Int32Array::from(vec![0, 1, 2, 3, 4]);
let right_int_array = Int32Array::from(vec![4, 3, 2, 1, 0]);
assert_eq!(
BooleanArray::from(vec![true, true, false, true, true,]),
distinct(&left_int_array, &right_int_array).unwrap()
);
assert_eq!(
BooleanArray::from(vec![false, false, true, false, false,]),
not_distinct(&left_int_array, &right_int_array).unwrap()
);
}
#[test]
fn is_distinct_from_nulls() {
// [0, 0, NULL, 0, 0, 0]
let left_int_array = Int32Array::new(
vec![0, 0, 1, 3, 0, 0].into(),
Some(NullBuffer::from(vec![true, true, false, true, true, true])),
);
// [0, NULL, NULL, NULL, 0, NULL]
let right_int_array = Int32Array::new(
vec![0; 6].into(),
Some(NullBuffer::from(vec![
true, false, false, false, true, false,
])),
);
assert_eq!(
BooleanArray::from(vec![false, true, false, true, false, true,]),
distinct(&left_int_array, &right_int_array).unwrap()
);
assert_eq!(
BooleanArray::from(vec![true, false, true, false, true, false,]),
not_distinct(&left_int_array, &right_int_array).unwrap()
);
}
#[test]
fn test_distinct_scalar() {
let a = Int32Array::new_scalar(12);
let b = Int32Array::new_scalar(12);
assert!(!distinct(&a, &b).unwrap().value(0));
assert!(not_distinct(&a, &b).unwrap().value(0));
let a = Int32Array::new_scalar(12);
let b = Int32Array::new_null(1);
assert!(distinct(&a, &b).unwrap().value(0));
assert!(!not_distinct(&a, &b).unwrap().value(0));
assert!(distinct(&b, &a).unwrap().value(0));
assert!(!not_distinct(&b, &a).unwrap().value(0));
let b = Scalar::new(b);
assert!(distinct(&a, &b).unwrap().value(0));
assert!(!not_distinct(&a, &b).unwrap().value(0));
assert!(!distinct(&b, &b).unwrap().value(0));
assert!(not_distinct(&b, &b).unwrap().value(0));
let a = Int32Array::new(
vec![0, 1, 2, 3].into(),
Some(vec![false, false, true, true].into()),
);
let expected = BooleanArray::from(vec![false, false, true, true]);
assert_eq!(distinct(&a, &b).unwrap(), expected);
assert_eq!(distinct(&b, &a).unwrap(), expected);
let expected = BooleanArray::from(vec![true, true, false, false]);
assert_eq!(not_distinct(&a, &b).unwrap(), expected);
assert_eq!(not_distinct(&b, &a).unwrap(), expected);
let b = Int32Array::new_scalar(1);
let expected = BooleanArray::from(vec![true; 4]);
assert_eq!(distinct(&a, &b).unwrap(), expected);
assert_eq!(distinct(&b, &a).unwrap(), expected);
let expected = BooleanArray::from(vec![false; 4]);
assert_eq!(not_distinct(&a, &b).unwrap(), expected);
assert_eq!(not_distinct(&b, &a).unwrap(), expected);
let b = Int32Array::new_scalar(3);
let expected = BooleanArray::from(vec![true, true, true, false]);
assert_eq!(distinct(&a, &b).unwrap(), expected);
assert_eq!(distinct(&b, &a).unwrap(), expected);
let expected = BooleanArray::from(vec![false, false, false, true]);
assert_eq!(not_distinct(&a, &b).unwrap(), expected);
assert_eq!(not_distinct(&b, &a).unwrap(), expected);
}
#[test]
fn test_scalar_negation() {
let a = Int32Array::new_scalar(54);
let b = Int32Array::new_scalar(54);
let r = eq(&a, &b).unwrap();
assert!(r.value(0));
let r = neq(&a, &b).unwrap();
assert!(!r.value(0))
}
#[test]
fn test_scalar_empty() {
let a = Int32Array::new_null(0);
let b = Int32Array::new_scalar(23);
let r = eq(&a, &b).unwrap();
assert_eq!(r.len(), 0);
let r = eq(&b, &a).unwrap();
assert_eq!(r.len(), 0);
}
#[test]
fn test_dictionary_nulls() {
let values = StringArray::from(vec![Some("us-west"), Some("us-east")]);
let nulls = NullBuffer::from(vec![false, true, true]);
let key_values = vec![100i32, 1i32, 0i32].into();
let keys = Int32Array::new(key_values, Some(nulls));
let col = DictionaryArray::try_new(keys, Arc::new(values)).unwrap();
neq(&col.slice(0, col.len() - 1), &col.slice(1, col.len() - 1)).unwrap();
}
}
notes-service/vendor/arrow-ord/src/comparison.rs
Vendored
+3576
View File
File diff suppressed because it is too large Load Diff
notes-service/vendor/arrow-ord/src/lib.rs
Vendored
+58
View File
@@ -0,0 +1,58 @@
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
//! Arrow ordering kernels
//!
//! # Sort RecordBatch
//!
//! ```
//! # use std::sync::Arc;
//! # use arrow_array::*;
//! # use arrow_array::cast::AsArray;
//! # use arrow_array::types::Int32Type;
//! # use arrow_ord::sort::sort_to_indices;
//! # use arrow_select::take::take;
//! #
//! let a: ArrayRef = Arc::new(Int32Array::from(vec![1, 2, 3, 4]));
//! let b: ArrayRef = Arc::new(StringArray::from(vec!["b", "a", "e", "d"]));
//! let batch = RecordBatch::try_from_iter(vec![("a", a), ("b", b)]).unwrap();
//!
//! // Sort by column 1
//! let indices = sort_to_indices(batch.column(1), None, None).unwrap();
//!
//! // Apply indices to batch columns
//! let columns = batch.columns().iter().map(|c| take(&*c, &indices, None).unwrap()).collect();
//! let sorted = RecordBatch::try_new(batch.schema(), columns).unwrap();
//!
//! let col1 = sorted.column(0).as_primitive::<Int32Type>();
//! assert_eq!(col1.values(), &[2, 1, 4, 3]);
//! ```
//!
#![doc(
html_logo_url = "https://arrow.apache.org/img/arrow-logo_chevrons_black-txt_white-bg.svg",
html_favicon_url = "https://arrow.apache.org/img/arrow-logo_chevrons_black-txt_transparent-bg.svg"
)]
#![cfg_attr(docsrs, feature(doc_cfg))]
#![warn(missing_docs)]
pub mod cmp;
#[doc(hidden)]
pub mod comparison;
pub mod ord;
pub mod partition;
pub mod rank;
pub mod sort;
notes-service/vendor/arrow-ord/src/ord.rs
Vendored
+1504
View File
File diff suppressed because it is too large Load Diff
notes-service/vendor/arrow-ord/src/partition.rs
Vendored
+335
View File
@@ -0,0 +1,335 @@
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
//! Defines partition kernel for `ArrayRef`
use std::ops::Range;
use arrow_array::{Array, ArrayRef};
use arrow_buffer::BooleanBuffer;
use arrow_schema::{ArrowError, SortOptions};
use crate::cmp::distinct;
use crate::ord::make_comparator;
/// A computed set of partitions, see [`partition`]
#[derive(Debug, Clone)]
pub struct Partitions(Option<BooleanBuffer>);
impl Partitions {
/// Returns the range of each partition
///
/// Consecutive ranges will be contiguous: i.e [`(a, b)` and `(b, c)`], and
/// `start = 0` and `end = self.len()` for the first and last range respectively
pub fn ranges(&self) -> Vec<Range<usize>> {
let boundaries = match &self.0 {
Some(boundaries) => boundaries,
None => return vec![],
};
let mut out = vec![];
let mut current = 0;
for idx in boundaries.set_indices() {
let t = current;
current = idx + 1;
out.push(t..current)
}
let last = boundaries.len() + 1;
if current != last {
out.push(current..last)
}
out
}
/// Returns the number of partitions
pub fn len(&self) -> usize {
match &self.0 {
Some(b) => b.count_set_bits() + 1,
None => 0,
}
}
/// Returns true if this contains no partitions
pub fn is_empty(&self) -> bool {
self.0.is_none()
}
}
/// Given a list of lexicographically sorted columns, computes the [`Partitions`],
/// where a partition consists of the set of consecutive rows with equal values
///
/// Returns an error if no columns are specified or all columns do not
/// have the same number of rows.
///
/// # Example:
///
/// For example, given columns `x`, `y` and `z`, calling
/// [`partition`]`(values, (x, y))` will divide the
/// rows into ranges where the values of `(x, y)` are equal:
///
/// ```text
/// ┌ ─ ┬───┬ ─ ─┌───┐─ ─ ┬───┬ ─ ─ ┐
/// │ 1 │ │ 1 │ │ A │ Range: 0..1 (x=1, y=1)
/// ├ ─ ┼───┼ ─ ─├───┤─ ─ ┼───┼ ─ ─ ┤
/// │ 1 │ │ 2 │ │ B │
/// │ ├───┤ ├───┤ ├───┤ │
/// │ 1 │ │ 2 │ │ C │ Range: 1..4 (x=1, y=2)
/// │ ├───┤ ├───┤ ├───┤ │
/// │ 1 │ │ 2 │ │ D │
/// ├ ─ ┼───┼ ─ ─├───┤─ ─ ┼───┼ ─ ─ ┤
/// │ 2 │ │ 1 │ │ E │ Range: 4..5 (x=2, y=1)
/// ├ ─ ┼───┼ ─ ─├───┤─ ─ ┼───┼ ─ ─ ┤
/// │ 3 │ │ 1 │ │ F │ Range: 5..6 (x=3, y=1)
/// └ ─ ┴───┴ ─ ─└───┘─ ─ ┴───┴ ─ ─ ┘
///
/// x y z partition(&[x, y])
/// ```
///
/// # Example Code
///
/// ```
/// # use std::{sync::Arc, ops::Range};
/// # use arrow_array::{RecordBatch, Int64Array, StringArray, ArrayRef};
/// # use arrow_ord::sort::{SortColumn, SortOptions};
/// # use arrow_ord::partition::partition;
/// let batch = RecordBatch::try_from_iter(vec![
/// ("x", Arc::new(Int64Array::from(vec![1, 1, 1, 1, 2, 3])) as ArrayRef),
/// ("y", Arc::new(Int64Array::from(vec![1, 2, 2, 2, 1, 1])) as ArrayRef),
/// ("z", Arc::new(StringArray::from(vec!["A", "B", "C", "D", "E", "F"])) as ArrayRef),
/// ]).unwrap();
///
/// // Partition on first two columns
/// let ranges = partition(&batch.columns()[..2]).unwrap().ranges();
///
/// let expected = vec![
/// (0..1),
/// (1..4),
/// (4..5),
/// (5..6),
/// ];
///
/// assert_eq!(ranges, expected);
/// ```
pub fn partition(columns: &[ArrayRef]) -> Result<Partitions, ArrowError> {
if columns.is_empty() {
return Err(ArrowError::InvalidArgumentError(
"Partition requires at least one column".to_string(),
));
}
let num_rows = columns[0].len();
if columns.iter().any(|item| item.len() != num_rows) {
return Err(ArrowError::InvalidArgumentError(
"Partition columns have different row counts".to_string(),
));
};
match num_rows {
0 => return Ok(Partitions(None)),
1 => return Ok(Partitions(Some(BooleanBuffer::new_unset(0)))),
_ => {}
}
let acc = find_boundaries(&columns[0])?;
let acc = columns
.iter()
.skip(1)
.try_fold(acc, |acc, c| find_boundaries(c.as_ref()).map(|b| &acc | &b))?;
Ok(Partitions(Some(acc)))
}
/// Returns a mask with bits set whenever the value or nullability changes
fn find_boundaries(v: &dyn Array) -> Result<BooleanBuffer, ArrowError> {
let slice_len = v.len() - 1;
let v1 = v.slice(0, slice_len);
let v2 = v.slice(1, slice_len);
if !v.data_type().is_nested() {
return Ok(distinct(&v1, &v2)?.values().clone());
}
// Given that we're only comparing values, null ordering in the input or
// sort options do not matter.
let cmp = make_comparator(&v1, &v2, SortOptions::default())?;
Ok((0..slice_len).map(|i| !cmp(i, i).is_eq()).collect())
}
#[cfg(test)]
mod tests {
use std::sync::Arc;
use super::*;
use arrow_array::*;
use arrow_schema::DataType;
#[test]
fn test_partition_empty() {
let err = partition(&[]).unwrap_err();
assert_eq!(
err.to_string(),
"Invalid argument error: Partition requires at least one column"
);
}
#[test]
fn test_partition_unaligned_rows() {
let input = vec![
Arc::new(Int64Array::from(vec![None, Some(-1)])) as _,
Arc::new(StringArray::from(vec![Some("foo")])) as _,
];
let err = partition(&input).unwrap_err();
assert_eq!(
err.to_string(),
"Invalid argument error: Partition columns have different row counts"
)
}
#[test]
fn test_partition_small() {
let results = partition(&[
Arc::new(Int32Array::new(vec![].into(), None)) as _,
Arc::new(Int32Array::new(vec![].into(), None)) as _,
Arc::new(Int32Array::new(vec![].into(), None)) as _,
])
.unwrap();
assert_eq!(results.len(), 0);
assert!(results.is_empty());
let results = partition(&[
Arc::new(Int32Array::from(vec![1])) as _,
Arc::new(Int32Array::from(vec![1])) as _,
])
.unwrap()
.ranges();
assert_eq!(results.len(), 1);
assert_eq!(results[0], 0..1);
}
#[test]
fn test_partition_single_column() {
let a = Int64Array::from(vec![1, 2, 2, 2, 2, 2, 2, 2, 9]);
let input = vec![Arc::new(a) as _];
assert_eq!(
partition(&input).unwrap().ranges(),
vec![(0..1), (1..8), (8..9)],
);
}
#[test]
fn test_partition_all_equal_values() {
let a = Int64Array::from_value(1, 1000);
let input = vec![Arc::new(a) as _];
assert_eq!(partition(&input).unwrap().ranges(), vec![(0..1000)]);
}
#[test]
fn test_partition_all_null_values() {
let input = vec![
new_null_array(&DataType::Int8, 1000),
new_null_array(&DataType::UInt16, 1000),
];
assert_eq!(partition(&input).unwrap().ranges(), vec![(0..1000)]);
}
#[test]
fn test_partition_unique_column_1() {
let input = vec![
Arc::new(Int64Array::from(vec![None, Some(-1)])) as _,
Arc::new(StringArray::from(vec![Some("foo"), Some("bar")])) as _,
];
assert_eq!(partition(&input).unwrap().ranges(), vec![(0..1), (1..2)],);
}
#[test]
fn test_partition_unique_column_2() {
let input = vec![
Arc::new(Int64Array::from(vec![None, Some(-1), Some(-1)])) as _,
Arc::new(StringArray::from(vec![
Some("foo"),
Some("bar"),
Some("apple"),
])) as _,
];
assert_eq!(
partition(&input).unwrap().ranges(),
vec![(0..1), (1..2), (2..3),],
);
}
#[test]
fn test_partition_non_unique_column_1() {
let input = vec![
Arc::new(Int64Array::from(vec![None, Some(-1), Some(-1), Some(1)])) as _,
Arc::new(StringArray::from(vec![
Some("foo"),
Some("bar"),
Some("bar"),
Some("bar"),
])) as _,
];
assert_eq!(
partition(&input).unwrap().ranges(),
vec![(0..1), (1..3), (3..4),],
);
}
#[test]
fn test_partition_masked_nulls() {
let input = vec![
Arc::new(Int64Array::new(vec![1; 9].into(), None)) as _,
Arc::new(Int64Array::new(
vec![1, 1, 2, 2, 2, 3, 3, 3, 3].into(),
Some(vec![false, true, true, true, true, false, false, true, false].into()),
)) as _,
Arc::new(Int64Array::new(
vec![1, 1, 2, 2, 2, 2, 2, 3, 7].into(),
Some(vec![true, true, true, true, false, true, true, true, false].into()),
)) as _,
];
assert_eq!(
partition(&input).unwrap().ranges(),
vec![(0..1), (1..2), (2..4), (4..5), (5..7), (7..8), (8..9)],
);
}
#[test]
fn test_partition_nested() {
let input = vec![
Arc::new(
StructArray::try_from(vec![(
"f1",
Arc::new(Int64Array::from(vec![
None,
None,
Some(1),
Some(2),
Some(2),
Some(2),
Some(3),
Some(4),
])) as _,
)])
.unwrap(),
) as _,
Arc::new(Int64Array::from(vec![1, 1, 1, 2, 3, 3, 3, 4])) as _,
];
assert_eq!(
partition(&input).unwrap().ranges(),
vec![0..2, 2..3, 3..4, 4..6, 6..7, 7..8]
)
}
}
notes-service/vendor/arrow-ord/src/rank.rs
Vendored
+361
View File
@@ -0,0 +1,361 @@
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
//! Provides `rank` function to assign a rank to each value in an array
use arrow_array::cast::AsArray;
use arrow_array::types::*;
use arrow_array::{
Array, ArrowNativeTypeOp, BooleanArray, GenericByteArray, downcast_primitive_array,
};
use arrow_buffer::NullBuffer;
use arrow_schema::{ArrowError, DataType, SortOptions};
use std::cmp::Ordering;
/// Whether `arrow_ord::rank` can rank an array of given data type.
pub(crate) fn can_rank(data_type: &DataType) -> bool {
data_type.is_primitive()
|| matches!(
data_type,
DataType::Boolean
| DataType::Utf8
| DataType::LargeUtf8
| DataType::Binary
| DataType::LargeBinary
)
}
/// Assigns a rank to each value in `array` based on its position in the sorted order
///
/// Where values are equal, they will be assigned the highest of their ranks,
/// leaving gaps in the overall rank assignment
///
/// ```
/// # use arrow_array::StringArray;
/// # use arrow_ord::rank::rank;
/// let array = StringArray::from(vec![Some("foo"), None, Some("foo"), None, Some("bar")]);
/// let ranks = rank(&array, None).unwrap();
/// assert_eq!(ranks, &[5, 2, 5, 2, 3]);
/// ```
pub fn rank(array: &dyn Array, options: Option<SortOptions>) -> Result<Vec<u32>, ArrowError> {
let options = options.unwrap_or_default();
let ranks = downcast_primitive_array! {
array => primitive_rank(array.values(), array.nulls(), options),
DataType::Boolean => boolean_rank(array.as_boolean(), options),
DataType::Utf8 => bytes_rank(array.as_bytes::<Utf8Type>(), options),
DataType::LargeUtf8 => bytes_rank(array.as_bytes::<LargeUtf8Type>(), options),
DataType::Binary => bytes_rank(array.as_bytes::<BinaryType>(), options),
DataType::LargeBinary => bytes_rank(array.as_bytes::<LargeBinaryType>(), options),
d => return Err(ArrowError::ComputeError(format!("{d:?} not supported in rank")))
};
Ok(ranks)
}
#[inline(never)]
fn primitive_rank<T: ArrowNativeTypeOp>(
values: &[T],
nulls: Option<&NullBuffer>,
options: SortOptions,
) -> Vec<u32> {
let len: u32 = values.len().try_into().unwrap();
let to_sort = match nulls.filter(|n| n.null_count() > 0) {
Some(n) => n
.valid_indices()
.map(|idx| (values[idx], idx as u32))
.collect(),
None => values.iter().copied().zip(0..len).collect(),
};
rank_impl(values.len(), to_sort, options, T::compare, T::is_eq)
}
#[inline(never)]
fn bytes_rank<T: ByteArrayType>(array: &GenericByteArray<T>, options: SortOptions) -> Vec<u32> {
let to_sort: Vec<(&[u8], u32)> = match array.nulls().filter(|n| n.null_count() > 0) {
Some(n) => n
.valid_indices()
.map(|idx| (array.value(idx).as_ref(), idx as u32))
.collect(),
None => (0..array.len())
.map(|idx| (array.value(idx).as_ref(), idx as u32))
.collect(),
};
rank_impl(array.len(), to_sort, options, Ord::cmp, PartialEq::eq)
}
fn rank_impl<T, C, E>(
len: usize,
mut valid: Vec<(T, u32)>,
options: SortOptions,
compare: C,
eq: E,
) -> Vec<u32>
where
T: Copy,
C: Fn(T, T) -> Ordering,
E: Fn(T, T) -> bool,
{
// We can use an unstable sort as we combine equal values later
valid.sort_unstable_by(|a, b| compare(a.0, b.0));
if options.descending {
valid.reverse();
}
let (mut valid_rank, null_rank) = match options.nulls_first {
true => (len as u32, (len - valid.len()) as u32),
false => (valid.len() as u32, len as u32),
};
let mut out: Vec<_> = vec![null_rank; len];
if let Some(v) = valid.last() {
out[v.1 as usize] = valid_rank;
}
let mut count = 1; // Number of values in rank
for w in valid.windows(2).rev() {
match eq(w[0].0, w[1].0) {
true => {
count += 1;
out[w[0].1 as usize] = valid_rank;
}
false => {
valid_rank -= count;
count = 1;
out[w[0].1 as usize] = valid_rank
}
}
}
out
}
/// Return the index for the rank when ranking boolean array
///
/// The index is calculated as follows:
/// if is_null is true, the index is 2
/// if is_null is false and the value is true, the index is 1
/// otherwise, the index is 0
///
/// false is 0 and true is 1 because these are the value when cast to number
#[inline]
fn get_boolean_rank_index(value: bool, is_null: bool) -> usize {
let is_null_num = is_null as usize;
(is_null_num << 1) | (value as usize & !is_null_num)
}
#[inline(never)]
fn boolean_rank(array: &BooleanArray, options: SortOptions) -> Vec<u32> {
let null_count = array.null_count() as u32;
let true_count = array.true_count() as u32;
let false_count = array.len() as u32 - null_count - true_count;
// Rank values for [false, true, null] in that order
//
// The value for a rank is last value rank + own value count
// this means that if we have the following order: `false`, `true` and then `null`
// the ranks will be:
// - false: false_count
// - true: false_count + true_count
// - null: false_count + true_count + null_count
//
// If we have the following order: `null`, `false` and then `true`
// the ranks will be:
// - false: null_count + false_count
// - true: null_count + false_count + true_count
// - null: null_count
//
// You will notice that the last rank is always the total length of the array but we don't use it for readability on how the rank is calculated
let ranks_index: [u32; 3] = match (options.descending, options.nulls_first) {
// The order is null, true, false
(true, true) => [
null_count + true_count + false_count,
null_count + true_count,
null_count,
],
// The order is true, false, null
(true, false) => [
true_count + false_count,
true_count,
true_count + false_count + null_count,
],
// The order is null, false, true
(false, true) => [
null_count + false_count,
null_count + false_count + true_count,
null_count,
],
// The order is false, true, null
(false, false) => [
false_count,
false_count + true_count,
false_count + true_count + null_count,
],
};
match array.nulls().filter(|n| n.null_count() > 0) {
Some(n) => array
.values()
.iter()
.zip(n.iter())
.map(|(value, is_valid)| ranks_index[get_boolean_rank_index(value, !is_valid)])
.collect::<Vec<u32>>(),
None => array
.values()
.iter()
.map(|value| ranks_index[value as usize])
.collect::<Vec<u32>>(),
}
}
#[cfg(test)]
mod tests {
use super::*;
use arrow_array::*;
#[test]
fn test_primitive() {
let descending = SortOptions {
descending: true,
nulls_first: true,
};
let nulls_last = SortOptions {
descending: false,
nulls_first: false,
};
let nulls_last_descending = SortOptions {
descending: true,
nulls_first: false,
};
let a = Int32Array::from(vec![Some(1), Some(1), None, Some(3), Some(3), Some(4)]);
let res = rank(&a, None).unwrap();
assert_eq!(res, &[3, 3, 1, 5, 5, 6]);
let res = rank(&a, Some(descending)).unwrap();
assert_eq!(res, &[6, 6, 1, 4, 4, 2]);
let res = rank(&a, Some(nulls_last)).unwrap();
assert_eq!(res, &[2, 2, 6, 4, 4, 5]);
let res = rank(&a, Some(nulls_last_descending)).unwrap();
assert_eq!(res, &[5, 5, 6, 3, 3, 1]);
// Test with non-zero null values
let nulls = NullBuffer::from(vec![true, true, false, true, false, false]);
let a = Int32Array::new(vec![1, 4, 3, 4, 5, 5].into(), Some(nulls));
let res = rank(&a, None).unwrap();
assert_eq!(res, &[4, 6, 3, 6, 3, 3]);
}
#[test]
fn test_get_boolean_rank_index() {
assert_eq!(get_boolean_rank_index(true, true), 2);
assert_eq!(get_boolean_rank_index(false, true), 2);
assert_eq!(get_boolean_rank_index(true, false), 1);
assert_eq!(get_boolean_rank_index(false, false), 0);
}
#[test]
fn test_nullable_booleans() {
let descending = SortOptions {
descending: true,
nulls_first: true,
};
let nulls_last = SortOptions {
descending: false,
nulls_first: false,
};
let nulls_last_descending = SortOptions {
descending: true,
nulls_first: false,
};
let a = BooleanArray::from(vec![Some(true), Some(true), None, Some(false), Some(false)]);
let res = rank(&a, None).unwrap();
assert_eq!(res, &[5, 5, 1, 3, 3]);
let res = rank(&a, Some(descending)).unwrap();
assert_eq!(res, &[3, 3, 1, 5, 5]);
let res = rank(&a, Some(nulls_last)).unwrap();
assert_eq!(res, &[4, 4, 5, 2, 2]);
let res = rank(&a, Some(nulls_last_descending)).unwrap();
assert_eq!(res, &[2, 2, 5, 4, 4]);
// Test with non-zero null values
let nulls = NullBuffer::from(vec![true, true, false, true, true]);
let a = BooleanArray::new(vec![true, true, true, false, false].into(), Some(nulls));
let res = rank(&a, None).unwrap();
assert_eq!(res, &[5, 5, 1, 3, 3]);
}
#[test]
fn test_booleans() {
let descending = SortOptions {
descending: true,
nulls_first: true,
};
let nulls_last = SortOptions {
descending: false,
nulls_first: false,
};
let nulls_last_descending = SortOptions {
descending: true,
nulls_first: false,
};
let a = BooleanArray::from(vec![true, false, false, false, true]);
let res = rank(&a, None).unwrap();
assert_eq!(res, &[5, 3, 3, 3, 5]);
let res = rank(&a, Some(descending)).unwrap();
assert_eq!(res, &[2, 5, 5, 5, 2]);
let res = rank(&a, Some(nulls_last)).unwrap();
assert_eq!(res, &[5, 3, 3, 3, 5]);
let res = rank(&a, Some(nulls_last_descending)).unwrap();
assert_eq!(res, &[2, 5, 5, 5, 2]);
}
#[test]
fn test_bytes() {
let v = vec!["foo", "fo", "bar", "bar"];
let values = StringArray::from(v.clone());
let res = rank(&values, None).unwrap();
assert_eq!(res, &[4, 3, 2, 2]);
let values = LargeStringArray::from(v.clone());
let res = rank(&values, None).unwrap();
assert_eq!(res, &[4, 3, 2, 2]);
let v: Vec<&[u8]> = vec![&[1, 2], &[0], &[1, 2, 3], &[1, 2]];
let values = LargeBinaryArray::from(v.clone());
let res = rank(&values, None).unwrap();
assert_eq!(res, &[3, 1, 4, 3]);
let values = BinaryArray::from(v);
let res = rank(&values, None).unwrap();
assert_eq!(res, &[3, 1, 4, 3]);
}
}
notes-service/vendor/arrow-ord/src/sort.rs
Vendored
+5238
View File
File diff suppressed because it is too large Load Diff