Merge pull request #57: Configure pre-commit checks

.github/workflows/ingest-to-phylogenetic.yaml

@@ -66,7 +66,7 @@ jobs:
         ingest/benchmarks/
         ingest/logs/
         ingest/.snakemake/log/
-  
+
   # Check if ingest results include new data by checking for the cache
   # of the file with the results' Metadata.sh256sum (which should have been added within upload-to-s3)
   # GitHub will remove any cache entries that have not been accessed in over 7 days,
@@ -89,8 +89,8 @@ jobs:
 
           # Code below is modified from ingest/upload-to-s3
           # https://github.com/nextstrain/ingest/blob/c0b4c6bb5e6ccbba86374d2c09b42077768aac23/upload-to-s3#L23-L29
-          
-          
+
+
           no_hash=0000000000000000000000000000000000000000000000000000000000000000
 
           for s3_url in "${s3_urls[@]}"; do
@@ -109,7 +109,7 @@ jobs:
           path: ingest-output-sha256sum
           key: ingest-output-sha256sum-${{ hashFiles('ingest-output-sha256sum') }}
           lookup-only: true
-  
+
   phylogenetic:
     needs: [check-new-data]
     if: ${{ needs.check-new-data.outputs.cache-hit != 'true' }}

.github/workflows/pre-commit.yaml

@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  - push
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - uses: pre-commit/[email protected]

.pre-commit-config.yaml

@@ -0,0 +1,41 @@
+default_language_version:
+  python: python3
+exclude: '\.(tsv|fasta|gb)$|^ingest/vendored/'
+repos:
+  - repo: https://github.com/pre-commit/sync-pre-commit-deps
+    rev: v0.0.1
+    hooks:
+      - id: sync-pre-commit-deps
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+      - id: shellcheck
+  - repo: https://github.com/rhysd/actionlint
+    rev: v1.6.27
+    hooks:
+      - id: actionlint
+        entry: env SHELLCHECK_OPTS='--exclude=SC2027' actionlint
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: check-ast
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: check-json
+      - id: check-executables-have-shebangs
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-yaml
+      - id: destroyed-symlinks
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: fix-byte-order-marker
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.4.6
+    hooks:
+      # Run the linter.
+      - id: ruff

README.md

@@ -24,3 +24,24 @@ nextstrain view .
 ## Documentation
 
 - [Running a pathogen workflow](https://docs.nextstrain.org/en/latest/tutorials/running-a-workflow.html)
+
+## Working on this repo
+
+This repo is configured to use [pre-commit](https://pre-commit.com),
+to help automatically catch common coding errors and syntax issues
+with changes before they are committed to the repo.
+.
+If you will be writing new code or otherwise working within this repo,
+please do the following to get started:
+
+1. install `pre-commit` by running either `python -m pip install
+   pre-commit` or `brew install pre-commit`, depending on your
+   preferred package management solution
+2. install the local git hooks by running `pre-commit install` from
+   the root of the repo
+3. when problems are detected, correct them in your local working tree
+   before committing them.
+
+Note that these pre-commit checks are also run in a GitHub Action when
+changes are pushed to GitHub, so correcting issues locally will
+prevent extra cycles of correction.

ingest/bin/parse-measles-genotype-names.py

@@ -24,22 +24,22 @@ def parse_args():
 
 def _set_genotype_name(record):
     genotype_name = record["genotype_ncbi"]
-    
+
     genotype_name = genotype_name.replace('Measles virus genotype ', '')
-    genotype_name = re.sub(r'Measles morbillivirus.*$', r'', genotype_name)   
+    genotype_name = re.sub(r'Measles morbillivirus.*$', r'', genotype_name)
     genotype_name = re.sub(r'.*?\[(.*)\]$', r'\1', genotype_name) # If square brackets present at end of string, keep only the text inside the brackets
     genotype_name = re.sub(r'Measles virus MVs.*$', r'', genotype_name)
     genotype_name = re.sub(r'Measles virus MVi.*$', r'', genotype_name)
     genotype_name = re.sub(r'Measles virus strain MVi.*$', r'', genotype_name)
     genotype_name = genotype_name.replace('Measles virus strain ', '')
     genotype_name = re.sub(r'Measles virus.*$', r'', genotype_name)
     genotype_name = re.sub(r'A-vaccine.*$', r'A', genotype_name)
-    genotype_name = re.sub(r'B3.1', r'B3', genotype_name) 
-    genotype_name = re.sub(r'B3.2', r'B3', genotype_name) 
-    genotype_name = re.sub(r'D4a', r'D4', genotype_name) 
-    genotype_name = re.sub(r'D4b', r'D4', genotype_name) 
-    genotype_name = re.sub(r'H1a', r'H1', genotype_name) 
-    genotype_name = re.sub(r'H1b', r'H1', genotype_name) 
+    genotype_name = re.sub(r'B3.1', r'B3', genotype_name)
+    genotype_name = re.sub(r'B3.2', r'B3', genotype_name)
+    genotype_name = re.sub(r'D4a', r'D4', genotype_name)
+    genotype_name = re.sub(r'D4b', r'D4', genotype_name)
+    genotype_name = re.sub(r'H1a', r'H1', genotype_name)
+    genotype_name = re.sub(r'H1b', r'H1', genotype_name)
 
     return (
         genotype_name)

nextclade/README.md

@@ -1,11 +1,11 @@
 
 # Measles Nextclade Dataset Tree
 
-This workflow creates a phylogenetic tree that can be used as part of a Nextclade dataset to assign genotypes to measles samples based on [criteria outlined by the WHO](https://www.who.int/publications/i/item/WER8709). 
+This workflow creates a phylogenetic tree that can be used as part of a Nextclade dataset to assign genotypes to measles samples based on [criteria outlined by the WHO](https://www.who.int/publications/i/item/WER8709).
 
-The WHO has defined 24 measles genotypes based on N gene and H gene sequences from 28 reference strains. For new measles samples, genotypes can be assigned based on genetic similarity to the reference strains at the "N450" region (a 450 bp region of the N gene). 
+The WHO has defined 24 measles genotypes based on N gene and H gene sequences from 28 reference strains. For new measles samples, genotypes can be assigned based on genetic similarity to the reference strains at the "N450" region (a 450 bp region of the N gene).
 
-The tree created here includes N450 sequences for the 28 reference strains, along with other representative strains for each genotype. 
+The tree created here includes N450 sequences for the 28 reference strains, along with other representative strains for each genotype.
 
 The workflow includes the following steps:
 * Build a tree using samples from the `ingest` output, with the following sampling criteria:

nextclade/Snakefile

@@ -1,4 +1,4 @@
-configfile: "defaults/config.yaml" 
+configfile: "defaults/config.yaml"
 
 rule all:
     input:

nextclade/rules/annotate_phylogeny.smk

@@ -65,7 +65,7 @@ rule timeout:
     run:
         import json
         with open(input[0], 'r') as fh:
-            data = json.load(fh)        
+            data = json.load(fh)
         new_nodes = {}
         for name, attrs in data['nodes'].items():
             new_nodes[name] = {'mutation_length': attrs.get('mutation_length')}

phylogenetic/defaults/auspice_config.json

@@ -10,7 +10,7 @@
       "url": "https://www.ncbi.nlm.nih.gov/genbank/"
     }
   ],
-  "build_url": "https://github.com/nextstrain/measles",  
+  "build_url": "https://github.com/nextstrain/measles",
   "colorings": [
     {
       "key": "gt",

phylogenetic/defaults/auspice_config_N450.json

@@ -67,7 +67,7 @@
     "map",
     "entropy",
     "frequencies"
-  ],  
+  ],
   "metadata_columns": [
     "author"
   ]

phylogenetic/rules/prepare_sequences.smk

@@ -64,7 +64,7 @@ rule filter:
             --group-by {params.group_by} \
             --sequences-per-group {params.sequences_per_group} \
             --min-date {params.min_date} \
-            --min-length {params.min_length} 
+            --min-length {params.min_length}
         """
 
 rule align:
@@ -86,4 +86,3 @@ rule align:
             --fill-gaps \
             --remove-reference
         """
-