Update project to use Poetry (#5)

.github/workflows/checks.yml

@@ -5,6 +5,9 @@ on:
   pull_request:
     branches:
       - main
+  push:
+    branches:
+      - main
 
 permissions:
   contents: read
@@ -29,8 +32,9 @@ jobs:
         with:
           python-version: 3.12
 
-      - name: install dev tools
-        run: pip install -v --no-cache -r requirements.dev.txt
+      - name: install ruff
+        run: |
+          pip install ruff
       
       - name: run ruff
         run: |
@@ -52,11 +56,14 @@ jobs:
 
       - name: install dependencies
         run: |
-          pip install -v --no-cache -r requirements.dev.txt
-          pip install -v --no-cache -r requirements.txt
+          pip install poetry
+          poetry config virtualenvs.in-project true
+          poetry install
 
       - name: run mypy
-        run: mypy .
+        run: |
+          source .venv/bin/activate
+          mypy .
   
   tests:
     runs-on: ubuntu-latest
@@ -71,10 +78,13 @@ jobs:
         with:
           python-version: 3.12
 
-      - name: install dev tools
+      - name: install dependencies
         run: |
-          pip install -v --no-cache -r requirements.dev.txt
-          pip install -v --no-cache -r requirements.txt
+          pip install poetry
+          poetry config virtualenvs.in-project true
+          poetry install
 
       - name: run pytest
-        run: pytest
+        run: |
+          source .venv/bin/activate
+          pytest

.github/workflows/release.yml

@@ -41,8 +41,8 @@ jobs:
 
       - name: build distributions
         run: |
-          python -m pip install build
-          python -m build
+          python -m pip install poetry
+          poetry build
 
       - name: upload distributions
         uses: actions/upload-artifact@v4

README.md

@@ -1,3 +1,16 @@
-# Post-it
+# :bookmark_tabs: Post-It
 
-A flexible Python data tagging framework for pre-training of AI models.
+[![checks](https://github.com/brennenho/post-it/actions/workflows/checks.yml/badge.svg)](https://github.com/brennenho/post-it/actions/workflows/checks.yml)
+
+A flexible data tagging framework for processing and filtering pretraining corpora for AI models.
+
+## Installation
+
+Install from PyPi with `pip install postit`.
+
+## Contributing
+
+- Clone this repo
+- Install [Poetry](https://python-poetry.org/docs/)
+- Activate Poetry: `poetry shell`
+- Install dependencies: `poetry install`

poetry.toml

@@ -0,0 +1,2 @@
+[virtualenvs]
+in-project = true

pyproject.toml

@@ -1,27 +1,32 @@
-[build-system]
-requires = ["setuptools"]
-build-backend = "setuptools.build_meta"
-
-
-[project]
+[tool.poetry]
 name = "postit"
-version = "0.0.1"
-description = "A flexible Python data tagging framework for pre-training of AI models."
+version = "0.0.2"
+description = "A flexible data tagging framework for processing and filtering pretraining corpora for AI models."
+authors = ["Brennen Ho <post-it@brennen.dev>"]
 readme = "README.md"
-authors = [
-  { name="Brennen Ho", email="post-it@brennen.dev" },
-]
 
-[project.urls]
-Homepage = "https://github.com/brennenho/post-it"
-Issues = "https://github.com/brennenho/post-it/issues"
+[tool.poetry.dependencies]
+python = "^3.12"
+gcsfs = "^2024.6.1"
+rich = "^13.7.1"
+mmh3 = "^4.1.0"
+bitarray = "^2.9.2"
 
-[tool.setuptools.dynamic]
-dependencies = { file = ["requirements.txt"] }
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.3.2"
+ruff = "^0.5.7"
+mypy = "^1.11.1"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
 
 [tool.ruff.lint]
 extend-select = ["I"]
 
 [tool.ruff.lint.isort]
 lines-between-types = 1
-no-sections = true
+no-sections = true
+
+[tool.mypy]
+disable_error_code = ["import-untyped"]