Switch from pyvcf to cyvcf2 for VCF parsing

.gitignore

@@ -119,3 +119,4 @@ test-probes.txt
 z.test.pncA_T2ATAC.txt
 
 .idea
+.mongodb

CHANGELOG.md

@@ -21,6 +21,7 @@ this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 - Default kmer size (21) made consistent across all subcommands [[#141][141]]
 - Nanopore preset `--ont` defaults to an expected error rate of 0.08 and ploidy
   'haploid' [[#134][134]]
+- VCF interface from pyvcf to cyvcf2 [[#142][142]]
 
 ### Fixed
 - Improved error messaging when an X amino acid resolves to a mutation already present
@@ -68,6 +69,7 @@ this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 [134]: https://github.com/Mykrobe-tools/mykrobe/issues/134
 [140]: https://github.com/Mykrobe-tools/mykrobe/issues/140
 [141]: https://github.com/Mykrobe-tools/mykrobe/issues/141
+[142]: https://github.com/Mykrobe-tools/mykrobe/issues/142
 [Unreleased]: https://github.com/Mykrobe-tools/mykrobe/compare/v0.10.0...HEAD
 [mkdtemp]: https://docs.python.org/3.6/library/tempfile.html#tempfile.mkdtemp
 

requirements.txt

@@ -1,6 +1,6 @@
 anytree
 Biopython
-pyvcf
+cyvcf2
 requests
 mongoengine
 cython

setup.py

@@ -2,27 +2,25 @@
 # -*- encoding: utf-8 -*-
 from __future__ import absolute_import
 from __future__ import print_function
-import logging
+
+import io
 import os
-import requests
 import shutil
 import subprocess
 import tarfile
-import io
-import re
 from glob import glob
 from os.path import basename
 from os.path import dirname
 from os.path import join
 from os.path import splitext
 
+import requests
 from setuptools import find_packages
 from setuptools import setup
 from setuptools.command.install import install as DistutilsInstall
 
 
 class MyInstall(DistutilsInstall):
-
     def run(self):
         self._install_mccortex()
 
@@ -37,7 +35,7 @@ def _get_mykrobe_data(self):
         extracted_name = "mykrobe-data"
         tarball_filename = "mykrobe_data.tar.gz"
         request = requests.get(data_tarball_url, allow_redirects=True)
-        with open(tarball_filename, 'wb') as t:
+        with open(tarball_filename, "wb") as t:
             t.write(request.content)
         if os.path.exists(extracted_name):
             shutil.rmtree(extracted_name)
@@ -63,16 +61,26 @@ def _install_mccortex(self):
 
         if not os.path.exists(mccortex_git_dir):
             subprocess.call(
-                ["git", "clone", "--recursive", "-b", "geno_kmer_count", "https://github.com/Mykrobe-tools/mccortex", mccortex_git_dir], cwd=dir_of_this_file)
+                [
+                    "git",
+                    "clone",
+                    "--recursive",
+                    "-b",
+                    "geno_kmer_count",
+                    "https://github.com/Mykrobe-tools/mccortex",
+                    mccortex_git_dir,
+                ],
+                cwd=dir_of_this_file,
+            )
 
         mccortex_build_binary = os.path.join(mccortex_git_dir, "bin", "mccortex31")
         if not os.path.exists(mccortex_build_binary):
-            subprocess.call(
-                ["make", "clean"], cwd=mccortex_git_dir)
-            subprocess.call(
-                ["make"], cwd=mccortex_git_dir)
+            subprocess.call(["make", "clean"], cwd=mccortex_git_dir)
+            subprocess.call(["make"], cwd=mccortex_git_dir)
 
-        mccortex_install_dir = os.path.join(dir_of_this_file, "src", "mykrobe", "cortex")
+        mccortex_install_dir = os.path.join(
+            dir_of_this_file, "src", "mykrobe", "cortex"
+        )
         mccortex_install_binary = os.path.join(mccortex_install_dir, "mccortex31")
         assert os.path.exists(mccortex_install_dir)
         shutil.copy(mccortex_build_binary, mccortex_install_binary)
@@ -82,65 +90,52 @@ def _install_mccortex(self):
 
 def read(*names, **kwargs):
     return io.open(
-        join(dirname(__file__), *names),
-        encoding=kwargs.get('encoding', 'utf8')
+        join(dirname(__file__), *names), encoding=kwargs.get("encoding", "utf8")
     ).read()
 
 
 setup(
-    name='mykrobe',
-    version='0.10.0',
-    license='MIT',
-    description='Antibiotic resistance prediction in minutes',
-    # long_description='%s\n%s' % (
-    #     re.compile('^.. start-badges.*^.. end-badges',
-    #                re.M | re.S).sub('', read('README.md')),
-    #     re.sub(':[a-z]+:`~?(.*?)`', r'``\1``', read('CHANGELOG.rst'))
-    # ),
-    author='Phelim Bradley',
-    author_email='wave@phel.im',
-    url='https://github.com/Mykrobe-tools/mykrobe',
-    packages=find_packages('src'),
-    package_dir={'': 'src'},
-    py_modules=[splitext(basename(path))[0] for path in glob(
-        'src/*.py')]+[splitext(basename(path))[0] for path in glob('src/*/*.py')]+[splitext(basename(path))[0] for path in glob('src/*/*/*.py')],
+    name="mykrobe",
+    version="0.10.0",
+    license="MIT",
+    description="Antibiotic resistance prediction in minutes",
+    author="Phelim Bradley",
+    author_email="wave@phel.im",
+    url="https://github.com/Mykrobe-tools/mykrobe",
+    packages=find_packages("src"),
+    package_dir={"": "src"},
+    py_modules=[splitext(basename(path))[0] for path in glob("src/*.py")]
+    + [splitext(basename(path))[0] for path in glob("src/*/*.py")]
+    + [splitext(basename(path))[0] for path in glob("src/*/*/*.py")],
     include_package_data=True,
     package_data={"mykrobe": ["cortex/mccortex31"]},
     zip_safe=False,
     classifiers=[
-        'Intended Audience :: Developers',
-        'Operating System :: Unix',
-        'Operating System :: POSIX',
-        'Programming Language :: Python',
-        'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.3',
-        'Programming Language :: Python :: 3.4',
-        'Programming Language :: Python :: 3.5',
-        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: Implementation :: CPython',
-        'Programming Language :: Python :: Implementation :: PyPy',
-        'Topic :: Utilities',
-    ],
-    keywords=[
-        # eg: 'keyword1', 'keyword2', 'keyword3',
+        "Intended Audience :: Developers",
+        "Operating System :: Unix",
+        "Operating System :: POSIX",
+        "Programming Language :: Python",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.3",
+        "Programming Language :: Python :: 3.4",
+        "Programming Language :: Python :: 3.5",
+        "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: Implementation :: CPython",
+        "Programming Language :: Python :: Implementation :: PyPy",
+        "Topic :: Utilities",
     ],
     install_requires=[
-        'anytree',
-        'Biopython',
-        "pyvcf",
-        'mongoengine',
-        'requests',
-        # eg: 'aspectlib==1.1.1', 'six>=1.7',
+        "anytree",
+        "Biopython",
+        "cyvcf2",
+        "mongoengine",
+        "requests",
+        "numpy",
     ],
-    extras_require={
-        # eg:
-        #   'rst': ['docutils>=0.11'],
-        #   ':python_version=="2.6"': ['argparse'],
-    },
     entry_points={
-        'console_scripts': [
-            'mykrobe = mykrobe.cli:main',
+        "console_scripts": [
+            "mykrobe = mykrobe.cli:main",
         ]
     },
-    cmdclass={'install': MyInstall}
+    cmdclass={"install": MyInstall},
 )

src/mykrobe/_vcf/__init__.py

@@ -1 +1 @@
-from mykrobe._vcf.models import VCF
+from mykrobe._vcf.models import VCF, Genotype