Pipeline will not fail if version is the same.

Wrong package name given in 'setup.cfg' is now fixed.

.devcontainer/Dockerfile

@@ -0,0 +1,11 @@
+FROM mcr.microsoft.com/devcontainers/anaconda:1-3
+
+# Copy environment.yml (if found) to a temp location so we update the environment. Also
+# copy "noop.txt" so the COPY instruction does not fail if no environment.yml exists.
+COPY environment.yml* .devcontainer/noop.txt /tmp/conda-tmp/
+RUN if [ -f "/tmp/conda-tmp/environment.yml" ]; then umask 0002 && /opt/conda/bin/conda env update -n base -f /tmp/conda-tmp/environment.yml; fi \
+    && rm -rf /tmp/conda-tmp
+
+# [Optional] Uncomment this section to install additional OS packages.
+# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+#     && apt-get -y install --no-install-recommends <your-package-list-here>

.devcontainer/devcontainer.json

@@ -0,0 +1,35 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
+{
+	"name": "Anaconda (Python 3)",
+	"build": { 
+		"context": "..",
+		"dockerfile": "Dockerfile"
+	},
+	"customizations": {
+		"vscode": {
+			"extensions": [
+				"ms-python.debugpy",
+				"ms-python.python",
+				"ms-python.vscode-pylance",
+				"ms-python.black-formatter",
+				"ms-python.flake8"
+			]
+		}
+	}
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Use 'postCreateCommand' to run commands after the container is created.
+	// "postCreateCommand": "python --version",
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

.devcontainer/noop.txt

@@ -0,0 +1,3 @@
+This file copied into the container along with environment.yml* from the parent
+folder. This file is included to prevents the Dockerfile COPY instruction from 
+failing if no environment.yml is found.

.vscode/launch.json

@@ -8,15 +8,16 @@
             "name": "Splitter Single Gene with Translation",
             "type": "python",
             "request": "launch",
-            "program": "${workspaceFolder}/msa_splitter.py",
+            "program": "${workspaceFolder}/splitmsa/splitmsa.py",
             "args": [
                 "${workspaceFolder}/tests/resources/test_msa-shortened.fa",
-                "--gene-list", "${workspaceFolder}/tests/resources/gene_list.csv",
+                "--gene-list",
+                "${workspaceFolder}/tests/resources/gene_list.csv",
                 "-C",
-                "-E", "DEBUG",
+                "-E",
+                "DEBUG",
                 "--do-translate",
                 "--gen-cut-stop-codon"
-
             ],
             "console": "integratedTerminal",
             "justMyCode": true

Jenkinsfile

@@ -0,0 +1,42 @@
+pipeline {
+    agent {
+        kubernetes {
+            cloud 'Reslate Systems'
+            defaultContainer 'conda'
+        }
+    }
+    stages {
+        stage("install") {
+            steps {
+                sh 'conda update conda -y -q'
+                sh 'conda env update -n base --file environment.yml'
+            }
+        }
+        stage("build") {
+            steps {
+                sh "conda run -n base python -m build"
+            }
+        }
+        stage("test") {
+            steps {
+                sh "conda run -n base pip install dist/*.whl"
+                sh "conda run -n base splitmsa -h"
+            }
+        }
+        stage("archive") {
+            steps {
+                archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl'
+            }
+        }
+        stage("publish") {
+            when {
+                branch '**/master'
+            }
+            steps {
+                withCredentials([usernamePassword(credentialsId: 'rs-git-package-registry-ydeng', passwordVariable: 'PASS', usernameVariable: 'USER')]) {
+                    sh returnStatus: true, script: 'conda run -n base python -m twine upload --repository-url https://git.reslate.systems/api/packages/${USER}/pypi -u ${USER} -p ${PASS} --non-interactive --disable-progress-bar --verbose dist/*'
+                }
+            }
+        }
+    }
+}

README.md

@@ -1,4 +1,4 @@
-# MSA Splitter
+# SplitMSA
 
 Simple FASTA file splitter. Capable of batch trimming a large amount of sequences in the form of a MSA in a FASTA file.
 

environment.yaml

@@ -1,46 +0,0 @@
-name: /home/ydeng/msa-splitter/envs
-channels:
-  - conda-forge
-dependencies:
-  - _libgcc_mutex=0.1=conda_forge
-  - _openmp_mutex=4.5=2_gnu
-  - biopython=1.81=py311h2582759_0
-  - black=23.3.0=py311h38be061_0
-  - bzip2=1.0.8=h7f98852_4
-  - ca-certificates=2022.12.7=ha878542_0
-  - click=8.1.3=unix_pyhd8ed1ab_2
-  - ld_impl_linux-64=2.40=h41732ed_0
-  - libblas=3.9.0=16_linux64_openblas
-  - libcblas=3.9.0=16_linux64_openblas
-  - libexpat=2.5.0=hcb278e6_1
-  - libffi=3.4.2=h7f98852_5
-  - libgcc-ng=12.2.0=h65d4601_19
-  - libgfortran-ng=12.2.0=h69a702a_19
-  - libgfortran5=12.2.0=h337968e_19
-  - libgomp=12.2.0=h65d4601_19
-  - liblapack=3.9.0=16_linux64_openblas
-  - libnsl=2.0.0=h7f98852_0
-  - libopenblas=0.3.21=pthreads_h78a6416_3
-  - libsqlite=3.40.0=h753d276_0
-  - libstdcxx-ng=12.2.0=h46fd767_19
-  - libuuid=2.38.1=h0b41bf4_0
-  - libzlib=1.2.13=h166bdaf_4
-  - mypy_extensions=1.0.0=pyha770c72_0
-  - ncurses=6.3=h27087fc_1
-  - numpy=1.24.2=py311h8e6699e_0
-  - openssl=3.1.0=h0b41bf4_0
-  - packaging=23.0=pyhd8ed1ab_0
-  - pathspec=0.11.1=pyhd8ed1ab_0
-  - pip=23.0.1=pyhd8ed1ab_0
-  - platformdirs=3.2.0=pyhd8ed1ab_0
-  - python=3.11.1=h2755cc3_0_cpython
-  - python_abi=3.11=3_cp311
-  - readline=8.2=h8228510_1
-  - setuptools=67.6.1=pyhd8ed1ab_0
-  - tk=8.6.12=h27826a3_0
-  - typing-extensions=4.5.0=hd8ed1ab_0
-  - typing_extensions=4.5.0=pyha770c72_0
-  - tzdata=2023c=h71feb2d_0
-  - wheel=0.40.0=pyhd8ed1ab_0
-  - xz=5.2.6=h166bdaf_0
-prefix: /home/ydeng/msa-splitter/envs

environment.yml

@@ -0,0 +1,9 @@
+name: splitmsa
+channels:
+  - conda-forge
+dependencies:
+  - build=0.7.0
+  - pytest=7.2.2
+  - twine
+  - biopython=1.81
+  - python=3.9

pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+build-backend = "setuptools.build_meta"
+requires = ["setuptools", "wheel"]

requirements.txt

@@ -1 +0,0 @@
-Bio==1.5.6

setup.cfg

@@ -0,0 +1,12 @@
+[metadata]
+name = splitmsa
+version = 0.0.4
+
+[options]
+packages = splitmsa
+install_requires =
+    biopython ==1.81; python_version == "3.9"
+
+[options.entry_points]
+console_scripts =
+    splitmsa = splitmsa.splitmsa:main

setup.py

@@ -0,0 +1,3 @@
+from setuptools import setup
+
+setup()

splitmsa/splitmsa.py

@@ -203,7 +203,7 @@ def trim(
             )
 
         if perform_translation and not skip_translation:
-            if '-' in nt_sequence:
+            if "-" in nt_sequence:
                 sequence_with_ambiguity = []
                 for codon_in_sequence in range(0, len(nt_sequence), 3):
                     codon = nt_sequence[codon_in_sequence : codon_in_sequence + 3]
@@ -247,9 +247,7 @@ def output_as_csv(gene: str, problems: list[list[str]], output_path: str):
         writer.writerows(problems)
 
 
-def main(args):
-    logging.basicConfig(level=args.log_level.upper())
-
+def run(args):
     msa_records = list(read_msa_file(args.input))
     info(f"MSA records read complete. Found {len(msa_records)} records.")
     genes = []
@@ -310,9 +308,9 @@ def main(args):
         info(f"Completed gene {gene_name} ({start} - {end})")
 
 
-if __name__ == "__main__":
+def main():
     parser = argparse.ArgumentParser(
-        prog="msa_splitter",
+        prog="splitmsa",
         description="""
             The MSA splitter is a simple program that takes in two positions
             and a MSA file and produces two separate FASTA files
@@ -453,4 +451,10 @@ if __name__ == "__main__":
         action="store_true",
     )
 
-    main(parser.parse_args())
+    args = parser.parse_args()
+    logging.basicConfig(level=args.log_level.upper())
+    run(args)
+
+
+if __name__ == "__main__":
+    main()