Switch from simd-json back to serde_json

If I remember correctly, there wasn't any significant performance
improvement, but I might be misremembering.
This commit is contained in:
Joscha 2024-06-27 21:51:29 +02:00
parent 7a52c818fb
commit 32ce86682c
4 changed files with 2 additions and 328 deletions

325
brood/Cargo.lock generated
View file

@ -2,24 +2,6 @@
# It is not intended for manual editing. # It is not intended for manual editing.
version = 3 version = 3
[[package]]
name = "ahash"
version = "0.8.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011"
dependencies = [
"cfg-if",
"once_cell",
"version_check",
"zerocopy",
]
[[package]]
name = "allocator-api2"
version = "0.2.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c6cb57a04249c6480766f7f7cef5467412af1490f8d1e243141daddada3264f"
[[package]] [[package]]
name = "anstream" name = "anstream"
version = "0.6.14" version = "0.6.14"
@ -69,12 +51,6 @@ dependencies = [
"windows-sys", "windows-sys",
] ]
[[package]]
name = "autocfg"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0c4b4d0bd25bd0b74681c0ad21497610ce1b7c91b1022cd21c80c6fbdd9476b0"
[[package]] [[package]]
name = "brood" name = "brood"
version = "0.0.0" version = "0.0.0"
@ -84,21 +60,8 @@ dependencies = [
"rustc-hash", "rustc-hash",
"serde", "serde",
"serde_json", "serde_json",
"simd-json",
] ]
[[package]]
name = "bumpalo"
version = "3.16.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]] [[package]]
name = "clap" name = "clap"
version = "4.5.7" version = "4.5.7"
@ -166,48 +129,6 @@ dependencies = [
"memchr", "memchr",
] ]
[[package]]
name = "float-cmp"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "98de4bbd547a563b716d8dfa9aad1cb19bfab00f4fa09a6a4ed21dbcf44ce9c4"
dependencies = [
"num-traits",
]
[[package]]
name = "getrandom"
version = "0.2.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
dependencies = [
"cfg-if",
"js-sys",
"libc",
"wasi",
"wasm-bindgen",
]
[[package]]
name = "halfbrown"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8588661a8607108a5ca69cab034063441a0413a0b041c13618a7dd348021ef6f"
dependencies = [
"hashbrown",
"serde",
]
[[package]]
name = "hashbrown"
version = "0.14.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
dependencies = [
"ahash",
"allocator-api2",
]
[[package]] [[package]]
name = "heck" name = "heck"
version = "0.5.0" version = "0.5.0"
@ -226,112 +147,12 @@ version = "1.0.11"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b" checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
[[package]]
name = "js-sys"
version = "0.3.69"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "29c15563dc2726973df627357ce0c9ddddbea194836909d655df6a75d2cf296d"
dependencies = [
"wasm-bindgen",
]
[[package]]
name = "lexical-core"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2cde5de06e8d4c2faabc400238f9ae1c74d5412d03a7bd067645ccbc47070e46"
dependencies = [
"lexical-parse-float",
"lexical-parse-integer",
"lexical-util",
"lexical-write-float",
"lexical-write-integer",
]
[[package]]
name = "lexical-parse-float"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "683b3a5ebd0130b8fb52ba0bdc718cc56815b6a097e28ae5a6997d0ad17dc05f"
dependencies = [
"lexical-parse-integer",
"lexical-util",
"static_assertions",
]
[[package]]
name = "lexical-parse-integer"
version = "0.8.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6d0994485ed0c312f6d965766754ea177d07f9c00c9b82a5ee62ed5b47945ee9"
dependencies = [
"lexical-util",
"static_assertions",
]
[[package]]
name = "lexical-util"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5255b9ff16ff898710eb9eb63cb39248ea8a5bb036bea8085b1a767ff6c4e3fc"
dependencies = [
"static_assertions",
]
[[package]]
name = "lexical-write-float"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "accabaa1c4581f05a3923d1b4cfd124c329352288b7b9da09e766b0668116862"
dependencies = [
"lexical-util",
"lexical-write-integer",
"static_assertions",
]
[[package]]
name = "lexical-write-integer"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e1b6f3d1f4422866b68192d62f77bc5c700bee84f3069f2469d7bc8c77852446"
dependencies = [
"lexical-util",
"static_assertions",
]
[[package]]
name = "libc"
version = "0.2.155"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
[[package]]
name = "log"
version = "0.4.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
[[package]] [[package]]
name = "memchr" name = "memchr"
version = "2.7.4" version = "2.7.4"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3" checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
[[package]]
name = "num-traits"
version = "0.2.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
dependencies = [
"autocfg",
]
[[package]]
name = "once_cell"
version = "1.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
[[package]] [[package]]
name = "proc-macro2" name = "proc-macro2"
version = "1.0.86" version = "1.0.86"
@ -350,26 +171,6 @@ dependencies = [
"proc-macro2", "proc-macro2",
] ]
[[package]]
name = "ref-cast"
version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ccf0a6f84d5f1d581da8b41b47ec8600871962f2a528115b542b362d4b744931"
dependencies = [
"ref-cast-impl",
]
[[package]]
name = "ref-cast-impl"
version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bcc303e793d3734489387d205e9b186fac9c6cfacedd98cbb2e8a5943595f3e6"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]] [[package]]
name = "rustc-hash" name = "rustc-hash"
version = "2.0.0" version = "2.0.0"
@ -413,34 +214,6 @@ dependencies = [
"serde", "serde",
] ]
[[package]]
name = "simd-json"
version = "0.13.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "570c430b3d902ea083097e853263ae782dfe40857d93db019a12356c8e8143fa"
dependencies = [
"getrandom",
"halfbrown",
"lexical-core",
"ref-cast",
"serde",
"serde_json",
"simdutf8",
"value-trait",
]
[[package]]
name = "simdutf8"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f27f6278552951f1f2b8cf9da965d10969b2efdea95a6ec47987ab46edfe263a"
[[package]]
name = "static_assertions"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
[[package]] [[package]]
name = "strsim" name = "strsim"
version = "0.11.1" version = "0.11.1"
@ -470,84 +243,6 @@ version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
[[package]]
name = "value-trait"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dad8db98c1e677797df21ba03fca7d3bf9bec3ca38db930954e4fe6e1ea27eb4"
dependencies = [
"float-cmp",
"halfbrown",
"itoa",
"ryu",
]
[[package]]
name = "version_check"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
[[package]]
name = "wasi"
version = "0.11.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
[[package]]
name = "wasm-bindgen"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4be2531df63900aeb2bca0daaaddec08491ee64ceecbee5076636a3b026795a8"
dependencies = [
"cfg-if",
"wasm-bindgen-macro",
]
[[package]]
name = "wasm-bindgen-backend"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "614d787b966d3989fa7bb98a654e369c762374fd3213d212cfc0251257e747da"
dependencies = [
"bumpalo",
"log",
"once_cell",
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1f8823de937b71b9460c0c34e25f3da88250760bec0ebac694b49997550d726"
dependencies = [
"quote",
"wasm-bindgen-macro-support",
]
[[package]]
name = "wasm-bindgen-macro-support"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
dependencies = [
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-backend",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-shared"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "af190c94f2773fdb3729c55b007a722abb5384da03bc0986df4c289bf5567e96"
[[package]] [[package]]
name = "windows-sys" name = "windows-sys"
version = "0.52.0" version = "0.52.0"
@ -620,23 +315,3 @@ name = "windows_x86_64_msvc"
version = "0.52.5" version = "0.52.5"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0" checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0"
[[package]]
name = "zerocopy"
version = "0.7.34"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae87e3fcd617500e5d106f0380cf7b77f3c6092aae37191433159dda23cfb087"
dependencies = [
"zerocopy-derive",
]
[[package]]
name = "zerocopy-derive"
version = "0.7.34"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "15e934569e47891f7d9411f1a451d947a60e000ab3bd24fbb970f000387d1b3b"
dependencies = [
"proc-macro2",
"quote",
"syn",
]

View file

@ -9,4 +9,3 @@ csv = "1.3.0"
rustc-hash = "2.0.0" rustc-hash = "2.0.0"
serde = { version = "1.0.203", features = ["derive"] } serde = { version = "1.0.203", features = ["derive"] }
serde_json = "1.0.118" serde_json = "1.0.118"
simd-json = "0.13.10"

View file

@ -67,7 +67,7 @@ fn first_stage() -> io::Result<(AdjacencyList<PageInfo, LinkInfo>, Titles)> {
let stdin = BufReader::new(io::stdin()); let stdin = BufReader::new(io::stdin());
for (i, line) in stdin.lines().enumerate() { for (i, line) in stdin.lines().enumerate() {
let json_page = simd_json::serde::from_slice::<JsonPage>(&mut line?.into_bytes()).unwrap(); let json_page = serde_json::from_str::<JsonPage>(&line?).unwrap();
result.pages.push(Page { result.pages.push(Page {
link_idx: result.links.len() as u32, link_idx: result.links.len() as u32,

View file

@ -32,7 +32,7 @@ pub fn run(datafile: &Path, articlesfile: &Path, language: &str) -> io::Result<(
let articlesbuf = BufReader::new(File::open(articlesfile)?); let articlesbuf = BufReader::new(File::open(articlesfile)?);
let articles: Vec<Article> = let articles: Vec<Article> =
simd_json::from_reader(articlesbuf).expect("failed to parse articles file"); serde_json::from_reader(articlesbuf).expect("failed to parse articles file");
let titles = articles let titles = articles
.into_iter() .into_iter()