Bump Rust Deps, Standards compliant pyproject.toml and start a Changlog

.github/workflows/CI.yaml

@@ -1,12 +1,9 @@
 name: CI
-
 on:
   push:
   pull_request:
-
 env:
   CARGO_TERM_COLOR: always
-
 jobs:
   check:
     name: Check
@@ -15,7 +12,6 @@ jobs:
       - uses: actions/checkout@v4
       - uses: dtolnay/rust-toolchain@stable
       - run: cargo check
-
   test:
     name: Test Suite
     runs-on: ubuntu-latest
@@ -24,23 +20,20 @@ jobs:
       - uses: dtolnay/rust-toolchain@stable
       - uses: Swatinem/rust-cache@v2
       - run: cargo test --benches --verbose --all
-
   test_python:
     name: Test Python
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
         with:
-          python-version: '3.10'
-          cache: 'pip'
+          python-version: "3.10"
+          enable-cache: true
+          cache-dependency-glob: pyproject.toml
       - uses: dtolnay/rust-toolchain@stable
       - uses: Swatinem/rust-cache@v2
+      - name: install project
+        run: uv sync --all-extras --dev
       - name: pytest
-        shell: bash
-        run: |
-          set -e
-          python -m venv .venv
-          source .venv/bin/activate
-          pip install '.[test]'
-          pytest
+        run: uv run pytest

.github/workflows/pre-commit.yml

@@ -1,14 +1,17 @@
 name: pre-commit
-
 on:
   pull_request:
   push:
-    branches: [main]
-
+    branches:
+      - main
 jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
-    - uses: actions/setup-python@v3
-    - uses: pre-commit/action@v3.0.1
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v3
+      - uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+          cache-dependency-glob: pyproject.toml
+      - run: uv run --only-group dev pre-commit run --all

CHANGELOG.md

@@ -0,0 +1,49 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+### Added
+
+- Started a changelog ([#2](https://github.com/BattModels/smirk/pull/2))
+
+### Changed
+
+- Bumped PyO3, tokenizers and dict_derive dependencies ([#2](https://github.com/BattModels/smirk/pull/2))
+- Switched to uv for CI/pre-commit workflows ([#2](https://github.com/BattModels/smirk/pull/2))
+
+### Breaking
+
+- Increased minimum python version to 3.9 ([#2](https://github.com/BattModels/smirk/pull/2))
+
+### Fixed
+
+- Mark version as dynamic in pyproject ([#2](https://github.com/BattModels/smirk/pull/2))
+
+### Removed
+
+## [0.1.1] - 2024-12-09
+
+Preprint v2 posted: [arXiv:2409.15370v2](https://arxiv.org/abs/2409.15370v2)
+
+## Added
+
+- Added support for post-processing templates to `SmirkTokenizerFast` ([#1](https://github.com/BattModels/smirk/pull/1))
+- Registered smirk with transformer's AutoTokenizer ([#1](https://github.com/BattModels/smirk/pull/1))
+- Added `vocab`, `convert_ids_to_tokens` and `convert_tokens_to_ids` methods ([#1](https://github.com/BattModels/smirk/pull/1))
+- Added support for truncating and padding during tokenization ([#1](https://github.com/BattModels/smirk/pull/1))
+
+## Fixed
+
+- Fixed CI to install test dependencies ([#1](https://github.com/BattModels/smirk/pull/1))
+
+## [0.1.0] - 2024-09-11
+
+Preprint posted: [arXiv:2409.15370v1](https://arxiv.org/abs/2409.15370v1)
+
+### Added
+
+- Initial tagged version of smirk

Cargo.toml

@@ -1,29 +1,35 @@
 [package]
 name = "smirk"
-version = "0.1.1"
+version = "0.2.0"
 edition = "2021"
+license = "Apache-2.0"
+description = "A chemically complete tokenizer for OpenSMILES"
+authors = [
+    "Alexius Wadell <awadell@umich.edu>",
+    "Anoushka Bhutani",
+]
+readme = "README.md"
+repository = "https://github.com/BattModels/smirk"
 
 [lib]
 name = "smirk"
-
-# "cdylib" is necessary to produce a shared library for Python to import from.
 crate-type = ["cdylib"]
 
 [dependencies]
 clap = "4.5.1"
 const_format = "0.2.32"
 derive_builder = "0.20.0"
-dict_derive = "0.5.0"
+dict_derive = "0.6.0"
 either = "1.13.0"
 macro_rules_attribute = "0.2.0"
 once_cell = "1.19.0"
 paste = "1.0.14"
-pyo3 = { version = "^0.20", features = ["extension-module"] }
+pyo3 = { version = "^0.23", features = ["extension-module"] }
 regex = "1.10.3"
 serde = "1.0.197"
 serde_json = "1.0.114"
 serde_with = "3.8.0"
-tokenizers = { version = "^0.19"}
+tokenizers = { version = "^0.21"}
 
 [dev-dependencies]
 tempfile = "3.10.1"

dependabot.yaml

@@ -0,0 +1,11 @@
+version: 2
+updates:
+  - package-ecosystem: cargo
+    directory: /
+    schedule:
+      interval: monthly
+    versioning-strategy: increase
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: monthly

pyproject.toml

@@ -1,22 +1,25 @@
 [project]
 name = "smirk"
-requires-python = ">=3.7"
+requires-python = ">=3.9"
 license = {file = "LICENSE"}
+dynamic = ["version"]
 classifiers = [
     "Programming Language :: Rust",
     "Programming Language :: Python :: Implementation :: CPython",
     "Programming Language :: Python :: Implementation :: PyPy",
 ]
 dependencies = [
-    "transformers ~= 4.40",
+    "transformers >=4.40,<5",
 ]
 
-[project.optional-dependencies]
-test = [
+[dependency-groups]
+dev = [
     "pytest~=8.3",
     "parameterized==0.9.0",
-    "torch",
-    "numpy",
+    "ruff~=0.9.4",
+    "torch~=2.0",
+    "numpy~=2.0",
+    "pre-commit~=4.1.0",
 ]
 
 [build-system]