seqpro 0.15.2__tar.gz → 0.16.0__tar.gz

seqpro-0.16.0/.github/workflows/bench.yaml

@@ -0,0 +1,60 @@
+name: Benchmarks
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  id-token: write # for OpenID Connect authentication with CodSpeed
+
+jobs:
+  python-benchmarks:
+    runs-on: ubuntu-latest
+    name: "Run Python CodSpeed benchmarks"
+    steps:
+      - name: Check out
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Setup pixi
+        uses: prefix-dev/setup-pixi@v0.9.5
+        with:
+          pixi-version: v0.67.2
+          cache: true
+          environments: bench
+          locked: false
+      - name: Build extension
+        run: pixi run -e bench maturin develop
+      - name: Run benchmarks
+        uses: CodSpeedHQ/action@v4
+        with:
+          mode: simulation
+          run: pixi run -e bench bench
+
+  rust-benchmarks:
+    runs-on: ubuntu-latest
+    name: "Run Rust CodSpeed benchmarks"
+    steps:
+      - name: Check out
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Setup rust toolchain, cache and cargo-codspeed binary
+        uses: moonrepo/setup-rust@v0
+        with:
+          channel: stable
+          cache-target: release
+          bins: cargo-codspeed
+      - name: Build the benchmark target(s)
+        run: cargo codspeed build
+      - name: Run benchmarks
+        uses: CodSpeedHQ/action@v4
+        with:
+          mode: simulation
+          run: cargo codspeed run

{seqpro-0.15.2 → seqpro-0.16.0}/CHANGELOG.md

@@ -1,3 +1,9 @@
+## 0.16.0 (2026-06-14)
+
+### Feat
+
+- **tokenize**: add parallel escape hatch overriding the size heuristic
+
 ## 0.15.2 (2026-06-13)
 
 ### Fix

{seqpro-0.15.2 → seqpro-0.16.0}/Cargo.lock

@@ -29,6 +29,15 @@ version = "1.0.99"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b0674a1ddeecb70197781e945de4b3b8ffb61fa939a5597bcf48503737663100"
 
+[[package]]
+name = "approx"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cab112f0a86d568ea0e627cc1d6be74a1e9cd55214684db5561995f6dad897c6"
+dependencies = [
+ "num-traits",
+]
+
 [[package]]
 name = "autocfg"
 version = "1.5.0"
@@ -64,9 +73,9 @@ checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
 
 [[package]]
 name = "bumpalo"
-version = "3.20.2"
+version = "3.20.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5d20789868f4b01b2f2caec9f5c4e0213b41e3e5702a50157d699ae31ced2fcb"
+checksum = "72f5acc6cb2ba439de613abc23857ec3d78374d8ed5ac84e9d11336e87da8649"
 
 [[package]]
 name = "cast"
@@ -74,12 +83,28 @@ version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
 
+[[package]]
+name = "cc"
+version = "1.2.64"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dad887fd958be91b5098c0248def011f4523ab786cd411be668777e55063501f"
+dependencies = [
+ "find-msvc-tools",
+ "shlex",
+]
+
 [[package]]
 name = "cfg-if"
 version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2fd1289c04a9ea8cb22300a459a72a385d7c73d3259e2ed7dcb2af674838cfa9"
 
+[[package]]
+name = "cfg_aliases"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
+
 [[package]]
 name = "ciborium"
 version = "0.2.2"
@@ -133,15 +158,47 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
 
 [[package]]
-name = "criterion"
-version = "0.5.1"
+name = "codspeed"
+version = "4.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57af92d1db7f6871b7e82c79cd87f2501db66f36b0eab924be6ea83dd6b2f3f3"
+dependencies = [
+ "anyhow",
+ "cc",
+ "colored",
+ "getrandom 0.2.11",
+ "glob",
+ "libc",
+ "nix",
+ "serde",
+ "serde_json",
+ "statrs",
+]
+
+[[package]]
+name = "codspeed-criterion-compat"
+version = "4.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f"
+checksum = "1d31ae2e9ab23c29fa13bdfa06d012524176f5c0f4e25ec262cd829d947ebc5e"
+dependencies = [
+ "clap",
+ "codspeed",
+ "codspeed-criterion-compat-walltime",
+ "colored",
+ "regex",
+]
+
+[[package]]
+name = "codspeed-criterion-compat-walltime"
+version = "4.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc8605e40bab5114dcb0f76268e18880082b5798dec10757b5b58d2c3bbc7a1c"
 dependencies = [
  "anes",
  "cast",
  "ciborium",
  "clap",
+ "codspeed",
  "criterion-plot",
  "is-terminal",
  "itertools",
@@ -158,6 +215,16 @@ dependencies = [
  "walkdir",
 ]
 
+[[package]]
+name = "colored"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "117725a109d387c937a1533ce01b450cbde6b88abceea8473c4d7a85853cda3c"
+dependencies = [
+ "lazy_static",
+ "windows-sys 0.59.0",
+]
+
 [[package]]
 name = "criterion-plot"
 version = "0.5.0"
@@ -284,7 +351,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
 dependencies = [
  "libc",
- "windows-sys",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -293,6 +360,12 @@ version = "2.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
 
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
+
 [[package]]
 name = "fnv"
 version = "1.0.7"
@@ -365,6 +438,12 @@ dependencies = [
  "wasip3",
 ]
 
+[[package]]
+name = "glob"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
+
 [[package]]
 name = "half"
 version = "2.7.1"
@@ -447,7 +526,7 @@ checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46"
 dependencies = [
  "hermit-abi",
  "libc",
- "windows-sys",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -467,16 +546,21 @@ checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
 [[package]]
 name = "js-sys"
-version = "0.3.98"
+version = "0.3.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67df7112613f8bfd9150013a0314e196f4800d3201ae742489d999db2f979f08"
+checksum = "03d04c30968dffe80775bd4d7fb676131cd04a1fb46d2686dbffbaec2d9dfd31"
 dependencies = [
  "cfg-if",
  "futures-util",
- "once_cell",
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
 [[package]]
 name = "leb128fmt"
 version = "0.1.0"
@@ -550,6 +634,18 @@ dependencies = [
  "rayon",
 ]
 
+[[package]]
+name = "nix"
+version = "0.31.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf20d2fde8ff38632c426f1165ed7436270b44f199fc55284c38276f9db47c3d"
+dependencies = [
+ "bitflags 2.11.1",
+ "cfg-if",
+ "cfg_aliases",
+ "libc",
+]
+
 [[package]]
 name = "num-complex"
 version = "0.4.4"
@@ -625,7 +721,7 @@ dependencies = [
  "libc",
  "redox_syscall",
  "smallvec",
- "windows-targets",
+ "windows-targets 0.48.5",
 ]
 
 [[package]]
@@ -942,7 +1038,7 @@ dependencies = [
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -989,7 +1085,7 @@ name = "seqpro"
 version = "0.1.0"
 dependencies = [
  "anyhow",
- "criterion",
+ "codspeed-criterion-compat",
  "derive_builder",
  "ndarray",
  "numpy",
@@ -1044,6 +1140,12 @@ dependencies = [
  "zmij",
 ]
 
+[[package]]
+name = "shlex"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba"
+
 [[package]]
 name = "slab"
 version = "0.4.12"
@@ -1056,6 +1158,16 @@ version = "1.11.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4dccd0940a2dcdf68d092b8cbab7dc0ad8fa938bf95787e1b916b0e3d0e8e970"
 
+[[package]]
+name = "statrs"
+version = "0.18.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2a3fe7c28c6512e766b0874335db33c94ad7b8f9054228ae1c2abd47ce7d335e"
+dependencies = [
+ "approx",
+ "num-traits",
+]
+
 [[package]]
 name = "strsim"
 version = "0.10.0"
@@ -1100,7 +1212,7 @@ dependencies = [
  "getrandom 0.4.2",
  "once_cell",
  "rustix",
- "windows-sys",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -1202,9 +1314,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.121"
+version = "0.2.125"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49ace1d07c165b0864824eee619580c4689389afa9dc9ed3a4c75040d82e6790"
+checksum = "8ddb3f79143bced6de84270411622a2699cee572fc0875aeaf1e7867cf9fca1a"
 dependencies = [
  "cfg-if",
  "once_cell",
@@ -1215,9 +1327,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.121"
+version = "0.2.125"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e68e6f4afd367a562002c05637acb8578ff2dea1943df76afb9e83d177c8578"
+checksum = "4e21a184b13fb19e157296e2c46056aec9092264fab83e4ba59e68c61b323c3d"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -1225,9 +1337,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.121"
+version = "0.2.125"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d95a9ec35c64b2a7cb35d3fead40c4238d0940c86d107136999567a4703259f2"
+checksum = "fecefd9c35bd935a20fc3fc344b5f29138961e4f47fb03297d88f2587afb5ebd"
 dependencies = [
  "bumpalo",
  "proc-macro2",
@@ -1238,9 +1350,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.121"
+version = "0.2.125"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4e0100b01e9f0d03189a92b96772a1fb998639d981193d7dbab487302513441"
+checksum = "23939e44bb9a5d7576fa2b563dc2e136628f1224e88a8deed09e04858b77871f"
 dependencies = [
  "unicode-ident",
 ]
@@ -1281,9 +1393,9 @@ dependencies = [
 
 [[package]]
 name = "web-sys"
-version = "0.3.98"
+version = "0.3.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4b572dff8bcf38bad0fa19729c89bb5748b2b9b1d8be70cf90df697e3a8f32aa"
+checksum = "a6430a72df5eb332242960fe84b3002a241163998241eb596d4f739b9757061d"
 dependencies = [
  "js-sys",
  "wasm-bindgen",
@@ -1295,7 +1407,7 @@ version = "0.1.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
 dependencies = [
- "windows-sys",
+ "windows-sys 0.61.2",
 ]
 
 [[package]]
@@ -1304,6 +1416,15 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
 
+[[package]]
+name = "windows-sys"
+version = "0.59.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
+dependencies = [
+ "windows-targets 0.52.6",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.61.2"
@@ -1319,13 +1440,29 @@ version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
 dependencies = [
- "windows_aarch64_gnullvm",
- "windows_aarch64_msvc",
- "windows_i686_gnu",
- "windows_i686_msvc",
- "windows_x86_64_gnu",
- "windows_x86_64_gnullvm",
- "windows_x86_64_msvc",
+ "windows_aarch64_gnullvm 0.48.5",
+ "windows_aarch64_msvc 0.48.5",
+ "windows_i686_gnu 0.48.5",
+ "windows_i686_msvc 0.48.5",
+ "windows_x86_64_gnu 0.48.5",
+ "windows_x86_64_gnullvm 0.48.5",
+ "windows_x86_64_msvc 0.48.5",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
 ]
 
 [[package]]
@@ -1334,42 +1471,90 @@ version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
 
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
 
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
 [[package]]
 name = "windows_i686_gnu"
 version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
 
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
 [[package]]
 name = "windows_i686_msvc"
 version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
 
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
 
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
 
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
 
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
+
 [[package]]
 name = "wit-bindgen"
 version = "0.51.0"
@@ -1472,18 +1657,18 @@ checksum = "fdd20c5420375476fbd4394763288da7eb0cc0b8c11deed431a91562af7335d3"
 
 [[package]]
 name = "zerocopy"
-version = "0.8.48"
+version = "0.8.52"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eed437bf9d6692032087e337407a86f04cd8d6a16a37199ed57949d415bd68e9"
+checksum = "ce1022995ff5ff5d841ad7d994facc23098cd40152f2c1d11cd607c6f530653f"
 dependencies = [
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.8.48"
+version = "0.8.52"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "70e3cd084b1788766f53af483dd21f93881ff30d7320490ec3ef7526d203bad4"
+checksum = "1ae7f38b72ec2a254e2b87ef277cf2cd4fb97cbebf944faa6f33354da0867930"
 dependencies = [
  "proc-macro2",
  "quote",

{seqpro-0.15.2 → seqpro-0.16.0}/Cargo.toml

@@ -24,7 +24,7 @@ version = "0.20"
 features = ["abi3-py39"]
 
 [dev-dependencies]
-criterion = { version = "0.5", features = ["html_reports"] }
+criterion = { version = "4.7.0", package = "codspeed-criterion-compat" }
 derive_builder = "0.13.1"
 proptest = "1.4"
 

{seqpro-0.15.2 → seqpro-0.16.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: seqpro
-Version: 0.15.2
+Version: 0.16.0
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy

{seqpro-0.15.2 → seqpro-0.16.0}/README.md

@@ -1,5 +1,6 @@
 ![PyPI - Downloads](https://img.shields.io/pypi/dm/seqpro)
 ![GitHub stars](https://img.shields.io/github/stars/ML4GLand/SeqPro)
+[![CodSpeed](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://app.codspeed.io/ML4GLand/SeqPro?utm_source=badge)
 
 # SeqPro (Sequence processing toolkit)
 ```python

{seqpro-0.15.2 → seqpro-0.16.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "seqpro"
-version = "0.15.2"
+version = "0.16.0"
 authors = [
     { name = "David Laub", email = "dlaub@ucsd.edu" },
     { name = "Adam Klie", email = "aklie@ucsd.edu" },

{seqpro-0.15.2 → seqpro-0.16.0}/python/seqpro/_encoders.py

@@ -234,6 +234,8 @@ def tokenize(
     token_map: dict[str, int],
     unknown_token: int,
     out: NDArray[np.int32] | None = None,
+    *,
+    parallel: bool | None = None,
 ) -> NDArray[np.int32]: ...
 @overload
 def tokenize(
@@ -241,12 +243,16 @@ def tokenize(
     token_map: dict[str, int],
     unknown_token: int,
     out: None = None,
+    *,
+    parallel: bool | None = None,
 ) -> Ragged[np.int32]: ...
 def tokenize(
     seqs: StrSeqType | Ragged[np.bytes_],
     token_map: dict[str, int],
     unknown_token: int,
     out: NDArray[np.int32] | None = None,
+    *,
+    parallel: bool | None = None,
 ) -> NDArray[np.int32] | Ragged[np.int32]:
     """Tokenize sequences. Maps each character to its integer token.
     Characters absent from token_map are replaced with unknown_token.
@@ -262,6 +268,13 @@ def tokenize(
     out
         Output array to store the result in. Only valid for non-Ragged input.
         Must have dtype ``np.int32``; any other dtype raises ``TypeError``.
+    parallel
+        Escape hatch overriding the size-based heuristic for choosing between the
+        single-threaded ``np.take`` and the parallel Numba LUT gather. ``None``
+        (default) uses the heuristic (parallel past
+        ``_TOKENIZE_PARALLEL_THRESHOLD`` elements); ``True`` forces the parallel
+        kernel; ``False`` forces single-threaded. ``parallel=True`` is
+        incompatible with a non-C-contiguous ``out`` and raises ``ValueError``.
 
     Returns
     -------
@@ -283,20 +296,32 @@ def tokenize(
         n = len(seqs.lengths.ravel())
         trailing = seqs.data.shape[1:]
         u8 = seqs.data.view(np.uint8)
-        if u8.size < _TOKENIZE_PARALLEL_THRESHOLD:
-            flat = np.take(lut, u8)
-        else:
+        use_parallel = (
+            u8.size >= _TOKENIZE_PARALLEL_THRESHOLD if parallel is None else parallel
+        )
+        if use_parallel:
             flat = np.empty(u8.shape, dtype=np.int32)
             lut_gather(np.ascontiguousarray(u8).reshape(-1), lut, flat.reshape(-1))
+        else:
+            flat = np.take(lut, u8)
         return Ragged.from_offsets(flat, (n, None, *trailing), seqs.offsets)
 
     _seqs = cast_seqs(seqs)
     u8 = _seqs.view(np.uint8)
-    # A strided out= can't be flattened to a writable view, so it takes the
-    # np.take path (which handles arbitrary strides) regardless of size.
-    if u8.size < _TOKENIZE_PARALLEL_THRESHOLD or (
-        out is not None and not out.flags.c_contiguous
-    ):
+    # A strided out= can't be flattened to a writable view, so the parallel
+    # kernel can't write through it; such out= always takes the np.take path
+    # (which handles arbitrary strides). parallel=True can't honor it -> error.
+    out_blocks_parallel = out is not None and not out.flags.c_contiguous
+    if parallel is True and out_blocks_parallel:
+        raise ValueError(
+            "parallel=True requires a C-contiguous out array, got a "
+            "non-contiguous out. Use parallel=None/False or a contiguous out."
+        )
+    if parallel is None:
+        use_parallel = u8.size >= _TOKENIZE_PARALLEL_THRESHOLD
+    else:
+        use_parallel = parallel
+    if not use_parallel or out_blocks_parallel:
         return np.take(lut, u8, out=out)
     result = out if out is not None else np.empty(u8.shape, dtype=np.int32)
     lut_gather(np.ascontiguousarray(u8).reshape(-1), lut, result.reshape(-1))

{seqpro-0.15.2 → seqpro-0.16.0}/skills/seqpro/SKILL.md

@@ -33,7 +33,7 @@ Python/Rust package for fast biological-sequence processing. Python+NumPy+Numba
 | Normalize input | `sp.cast_seqs(x)` | → `|S1` bytes, or passthrough for OHE |
 | One-hot encode | `sp.ohe(x, alphabet, length_axis=-1)` | last axis added for OHE dim |
 | Decode OHE | `sp.decode_ohe(x, alphabet, ohe_axis=-1)` | |
-| Tokenize / detokenize | `sp.tokenize` / `sp.decode_tokens` | integer ids |
+| Tokenize / detokenize | `sp.tokenize` / `sp.decode_tokens` | integer ids; `parallel=True/False` forces/disables the parallel kernel (default `None` = size heuristic) |
 | Pad | `sp.pad_seqs(x, pad_val, length=...)` | |
 | Reverse complement | `sp.reverse_complement(x, alphabet, length_axis=-1)` | works on str/bytes/OHE |
 | K-mer shuffle | `sp.k_shuffle(x, k, length_axis=-1, seed=...)` | calls Rust `_k_shuffle` |

{seqpro-0.15.2 → seqpro-0.16.0}/tests/test_tokenize.py

@@ -260,3 +260,53 @@ def test_tokenize_parallel_branch_matches_reference():
     rag = Ragged.from_lengths(data, lengths)
     rag_got = sp.tokenize(rag, token_map, unknown_token=4)
     np.testing.assert_array_equal(rag_got.data, ref(data.view(np.uint8)))
+
+
+def test_tokenize_parallel_override_forces_path(monkeypatch):
+    """parallel= overrides the size heuristic in both directions, while staying
+    correct. Spying on the parallel kernel reveals which branch ran."""
+    import seqpro._encoders as enc
+    from seqpro._encoders import _TOKENIZE_PARALLEL_THRESHOLD as THRESH
+
+    token_map = {"A": 0, "C": 1, "G": 2, "T": 3}
+    bases = np.frombuffer(b"ACGT", dtype="S1")
+
+    calls = {"n": 0}
+    real_lut = enc.lut_gather
+
+    def spy(*args, **kwargs):
+        calls["n"] += 1
+        return real_lut(*args, **kwargs)
+
+    monkeypatch.setattr(enc, "lut_gather", spy)
+
+    # small input, parallel=True -> parallel kernel used despite being below thresh
+    small = bases[np.zeros(8, dtype=int)]
+    assert small.size < THRESH
+    res = sp.tokenize(small, token_map, unknown_token=-1, parallel=True)
+    assert calls["n"] == 1
+    np.testing.assert_array_equal(res, np.zeros(8, dtype=np.int32))
+
+    # large input, parallel=False -> single-threaded np.take, kernel not used
+    calls["n"] = 0
+    large = bases[np.zeros(THRESH + 1000, dtype=int)]
+    res = sp.tokenize(large, token_map, unknown_token=-1, parallel=False)
+    assert calls["n"] == 0
+    np.testing.assert_array_equal(res, np.zeros(THRESH + 1000, dtype=np.int32))
+
+    # ragged honors the override too: small ragged forced parallel
+    calls["n"] = 0
+    data = bases[np.zeros(8, dtype=int)]
+    rag = Ragged.from_lengths(data, np.array([4, 4]))
+    sp.tokenize(rag, token_map, unknown_token=-1, parallel=True)
+    assert calls["n"] == 1
+
+
+def test_tokenize_parallel_true_rejects_noncontiguous_out():
+    """parallel=True cannot honor a non-C-contiguous out= buffer, so it raises."""
+    token_map = {"A": 0, "C": 1, "G": 2, "T": 3}
+    flat = np.frombuffer(b"ACGT" * 4, dtype="S1")
+    strided = np.empty((flat.size, 2), dtype=np.int32)[:, 0]
+    assert not strided.flags.c_contiguous
+    with pytest.raises(ValueError):
+        sp.tokenize(flat, token_map, unknown_token=-1, out=strided, parallel=True)

seqpro-0.15.2/.github/workflows/bench.yaml

@@ -1,31 +0,0 @@
-name: Benchmarks
-
-on:
-  pull_request:
-    branches:
-      - main
-  workflow_dispatch:
-
-jobs:
-  benchmarks:
-    runs-on: ubuntu-latest
-    name: "Run CodSpeed microbenchmarks"
-    steps:
-      - name: Check out
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-      - name: Setup pixi
-        uses: prefix-dev/setup-pixi@v0.9.5
-        with:
-          pixi-version: v0.67.2
-          cache: true
-          environments: bench
-          locked: false
-      - name: Build extension
-        run: pixi run -e bench maturin develop
-      - name: Run benchmarks
-        uses: CodSpeedHQ/action@v3
-        with:
-          token: ${{ secrets.CODSPEED_TOKEN }}
-          run: pixi run -e bench bench