Merged with upstream

.git-blame-ignore-revs

@@ -0,0 +1,5 @@
+# 240110, non-invasive, repo-wide formatting with ruff and prettier
+7634a3bd7b150f552f064e7089b4ab160b6f4564
+
+# 240110, safe ruff-fixes
+1d308fb21d4c4d07f1d6a97d0e85d9495db80557

.github/workflows/anglerfish.yml

@@ -14,11 +14,11 @@ jobs:
       - uses: actions/checkout@v4
       - uses: mamba-org/setup-micromamba@v1
         with:
-           init-shell: bash
-           create-args: >-
+          init-shell: bash
+          create-args: >-
             python=${{ matrix.python-version }}
             pip
-           environment-file: environment.yml
+          environment-file: environment.yml
 
       # Install Anglerfish
       - shell: bash -l {0}
@@ -29,7 +29,7 @@ jobs:
       # Run anglerfish --help
       - shell: bash -l {0}
         name: Test anglerfish
-        run: | 
+        run: |
           anglerfish --help
 
       # Run anglerfish using test data

.github/workflows/lint-code.yml

@@ -0,0 +1,99 @@
+name: lint-code
+on: [push, pull_request]
+
+# Cancel if a newer run is started
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  # Use ruff to check for code style violations
+  ruff-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff
+      - name: ruff --> Check for style violations
+        # Configured in pyproject.toml
+        run: ruff check .
+
+  # Use ruff to check code formatting
+  ruff-format:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff
+      - name: ruff --> Check code formatting
+        run: ruff format --check .
+
+  # Use mypy for static type checking
+  mypy-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install mypy
+      # Start by installing type stubs
+      - name: mypy --> Install stubs
+        run: echo -e "y" | mypy --install-types **/*.py || exit 0
+      - name: mypy --> Static type checking
+        # Configured in pyprojet.toml
+        run: mypy **/*.py
+
+    # Use Prettier to check various file formats
+  prettier:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Setup node
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+
+      - name: Install Prettier
+        run: npm install -g prettier
+
+      - name: Run Prettier --check
+        run: prettier --check .
+
+  # Use editorconfig to check all remaining file formats
+  editorconfig:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+
+      - name: Setup node
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+
+      - name: Install editorconfig-checker
+        run: npm install -g editorconfig-checker
+
+      - name: editorconfig --> Lint files
+        run: editorconfig-checker $(git ls-files | grep -v '.py\|.md\|.json\|.yml\|.yaml\|.html')

.github/workflows/pypi.yml

@@ -28,4 +28,4 @@ jobs:
         uses: pypa/gh-action-pypi-publish@master
         with:
           user: __token__
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          password: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -2,3 +2,7 @@
 *~
 *.egg-info
 .DS_Store
+.benchmarks
+.*_cache
+node_modules
+.vscode

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+# .pre-commit-config.yaml
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.6
+    hooks:
+      - id: ruff
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: "v1.7.1"
+    hooks:
+      - id: mypy
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v4.0.0-alpha.8"
+    hooks:
+      - id: prettier
+  - repo: https://github.com/editorconfig-checker/editorconfig-checker.python
+    rev: "2.7.2"
+    hooks:
+      - id: editorconfig-checker

Dockerfile

@@ -1,7 +1,7 @@
 FROM mambaorg/micromamba
 
 LABEL author="Remi-Andre Olsen" \
-      description="Anglerfish" \
+      description="Anglerfish development version" \
       maintainer="[email protected]"
 
 USER root
@@ -43,7 +43,9 @@ RUN if [ "$TARGETARCH" = "arm64" ]; then \
 ADD . /usr/src/anglerfish
 WORKDIR /usr/src/anglerfish
 
-RUN micromamba install -y -n base -f /environment.tmp.yml && micromamba clean --all --yes
+# Activate the environment
+ARG MAMBA_DOCKERFILE_ACTIVATE=1
+RUN micromamba install -y -f /environment.tmp.yml && micromamba clean --all --yes
 
-RUN eval "$(micromamba shell hook --shell bash)" && micromamba activate base && python -m pip install . 
-USER $MAMBA_USER
+RUN eval "$(micromamba shell hook --shell bash)" && python -m pip install .[dev]
+USER $MAMBA_USER

README.md

@@ -1,10 +1,10 @@
 # Anglerfish
+
 [![Anglerfish CI Status](https://github.com/remiolsen/anglerfish/workflows/Anglerfish/badge.svg)](https://github.com/remiolsen/anglerfish/actions)
 [![PyPI](https://img.shields.io/pypi/v/bio-anglerfish)](https://pypi.python.org/pypi/bio-anglerfish/)
 [![Conda (channel only)](https://img.shields.io/conda/vn/bioconda/anglerfish)](https://anaconda.org/bioconda/anglerfish)
 [![Docker Container available](https://img.shields.io/docker/automated/remiolsen/anglerfish.svg)](https://hub.docker.com/r/remiolsen/anglerfish/)
 
-
 ## Introduction
 
 Anglerfish is a tool designed to demultiplex Illumina libraries sequenced on Oxford Nanopore
@@ -15,21 +15,6 @@ For more information on how this can be used, please see this [poster](docs/AGBT
 
 ## Installation
 
-### Requirements
-
-* Python3 (3.7)
-
-Python modules:
-
-* biopython v. 1.70
-* python-levenshtein v. 0.12.0
-* numpy v. 1.19.2
-* pyyaml v. 6.0
-
-Software:
-
-* minimap2 v. 2.20
-
 ### From PyPi
 
 ```
@@ -42,31 +27,53 @@ pip install bio-anglerfish
 conda install -c bioconda anglerfish
 ```
 
-### Manually with Conda
+### Install development version
+
+```
+pip install --upgrade --force-reinstall git+https://github.com/remiolsen/anglerfish.git
+```
+
+## Source development
 
-First [install miniconda](https://docs.conda.io/en/latest/miniconda.html), then:
+1. [Install miniconda](https://docs.conda.io/en/latest/miniconda.html).
+
+2. Set up repo clone with editable install
 
 ```
 git clone https://github.com/remiolsen/anglerfish.git
 cd anglerfish
 # Create a the anglerfish conda environment
 conda env create -f environment.yml
 # Install anglerfish
-pip install -e .
+conda activate anglerfish-dev
+pip install -e ".[dev]"
 ```
 
-### Development version
+3. (Optional) Install pre-commit to prevent committing code that will fail linting
 
 ```
-pip install --upgrade --force-reinstall git+https://github.com/remiolsen/anglerfish.git
+pre-commit install
+```
+
+4. (Optional) Enable automatic formatting in VS Code by creating `.vscode/settings.json` with:
+
+```
+{
+  "editor.formatOnSave": true,
+  "editor.defaultFormatter": "esbenp.prettier-vscode",
+  "[python]": {
+    "editor.defaultFormatter": "charliermarsh.ruff"
+  },
+  "prettier.configPath": "./pyproject.toml"
+}
 ```
 
 ## Usage
 
 Anglerfish requires two files to run.
 
-  * A basecalled FASTQ file from for instance Guppy (`/path/to/ONTreads.fastq.gz`)
-  * A samplesheet containing the sample names and indices expected to be found in the sequencing run. (`/path/to/samples.csv`)
+- A basecalled FASTQ file from for instance Guppy (`/path/to/ONTreads.fastq.gz`)
+- A samplesheet containing the sample names and indices expected to be found in the sequencing run. (`/path/to/samples.csv`)
 
 Example of a samplesheet file:
 
@@ -135,10 +142,9 @@ P54321_101,truseq,ATTACTCG,/path/to/barcode02/*.fastq.gz
 
 In folder `anglerfish_????_??_??_?????/`
 
-* `*.fastq.gz` Demultiplexed reads (if any)
-* `anglerfish_stats.txt` Barcode statistics from anglerfish run
-* `anglerfish_stats.json` Machine readable anglerfish statistics
-
+- `*.fastq.gz` Demultiplexed reads (if any)
+- `anglerfish_stats.txt` Barcode statistics from anglerfish run
+- `anglerfish_stats.json` Machine readable anglerfish statistics
 
 ## Credits
 

anglerfish/__main__.py

@@ -1,4 +1,4 @@
-from . import anglerfish
+from .anglerfish import anglerfish
 
-if __name__ == '__main__':
-    anglerfish()
+if __name__ == "__main__":
+    anglerfish()