Merge pull request #82 from PMCC-BioinformaticsCore/v0.11.x

V0.11.x

Author: illusional

.github/workflows/publish.yml

@@ -0,0 +1,33 @@
+name: Upload Python Package
+
+on:
+  push:
+    tags:
+      - v*
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .
+        pip install -e .[tests]
+        pip install -e .[ci]
+
+    - name: Test with nosetests
+      run: |
+        nosetests -s -w tests -a ci --ignore-files="local_*"
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*

.github/workflows/unit_tests.yml

@@ -0,0 +1,26 @@
+name: Unit Tests
+
+on: [push]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.6, 3.7, 3.8]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .
+        pip install -e .[tests]
+    - name: Test with nosetests
+      run: |
+        nosetests -s -w tests -a ci --ignore-files="local_*"

.gitignore

@@ -10,3 +10,5 @@ janis_pipelines.bioinformatics.egg-info/
 pip-wheel-metadata/
 cromwell-executions/
 cromwell-workflow-logs/
+venv/
+.python-version

.pre-commit-config.yaml

@@ -3,7 +3,6 @@ repos:
     rev: stable
     hooks:
     - id: black
-      language_version: python3.7
 - repo: local
   hooks:
     - id: nosetests

.travis.yml

@@ -1,2 +1,2 @@
-__version__ = "v0.10.12"
+__version__ = "v0.11.0"
 description = "Bioinformatics tools for Janis; the Pipeline creation helper"

janis_bioinformatics/__meta__.py

@@ -1,3 +1,4 @@
+import subprocess
 from janis_core import File
 
 
@@ -12,6 +13,28 @@ def name():
     def doc(self):
         return "A binary version of a SAM file, http://software.broadinstitute.org/software/igv/bam"
 
+    @classmethod
+    def flagstat(cls, file_path: str):
+        command = ["samtools", "flagstat", file_path]
+        result = subprocess.run(
+            command,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            universal_newlines=True,
+        )
+
+        if result.stderr:
+            raise Exception(result.stderr)
+
+        return result.stdout
+
+    @classmethod
+    def equal(cls, file_path_1: str, file_path_2: str):
+        flagstat1 = cls.flagstat(file_path_1)
+        flagstat2 = cls.flagstat(file_path_2)
+
+        return flagstat1 == flagstat2
+
 
 class BamBai(Bam):
     @staticmethod

janis_bioinformatics/data_types/bam.py

@@ -1,4 +1,7 @@
 from janis_core import File
+from janis_unix.data_types import Gunzipped
+
+from janis_bioinformatics.data_types.tabix import FileTabix
 
 
 class Bed(File):
@@ -10,14 +13,16 @@ def name():
         return "bed"
 
 
-class BedTabix(File):
+class BedGz(Gunzipped):
     def __init__(self, optional=False):
-        super().__init__(optional=optional, extension=".bed.gz")
+        super().__init__(inner_type=Bed, optional=optional, extension=".bed.gz")
 
     @staticmethod
     def name():
-        return "BedTABIX"
+        return "BedGz"
+
 
+class BedTabix(FileTabix, BedGz):
     @staticmethod
-    def secondary_files():
-        return [".tbi"]
+    def name():
+        return "BedTABIX"

janis_bioinformatics/data_types/bed.py

@@ -4,7 +4,9 @@
 
 class Fasta(File):
     def __init__(self, optional=False):
-        super().__init__(optional, extension=".fasta")
+        super().__init__(
+            optional, extension=".fasta", alternate_extensions={".fa", ".fna"}
+        )
 
     @staticmethod
     def name():

janis_bioinformatics/data_types/fasta.py

@@ -5,7 +5,9 @@
 
 class Fastq(File):
     def __init__(self, optional=False):
-        super().__init__(optional=optional, extension=".fastq")
+        super().__init__(
+            optional=optional, extension=".fastq", alternate_extensions={".fq"}
+        )
 
     @staticmethod
     def name():
@@ -20,7 +22,9 @@ def doc(self):
 
 class FastqGz(File):
     def __init__(self, optional=False):
-        super().__init__(optional=optional, extension=".fastq.gz")
+        super().__init__(
+            optional=optional, extension=".fastq.gz", alternate_extensions={".fq.gz"}
+        )
 
     @staticmethod
     def name():
@@ -69,7 +73,7 @@ def invalid_value_hint(self, meta):
 
 class FastqPairedEnd(Array):
     def __init__(self, optional=False):
-        super().__init__(File(optional=False, extension=".fastq"), optional=optional)
+        super().__init__(Fastq(optional=False), optional=optional)
 
     def id(self):
         if self.optional: