Basic filtering system and tests completed

.vscode/settings.json

@@ -0,0 +1,17 @@
+{
+    "python.testing.pytestArgs": [],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "python.linting.pylintArgs": [
+        "--rcfile=setup.cfg"
+    ],
+    "python.analysis.autoSearchPaths": true,
+    "python.analysis.extraPaths": [
+        "src"
+    ],
+    "cSpell.words": [
+        "pytest",
+        "pyvcf",
+        "vcfs"
+    ],
+}

Jenkinsfile

@@ -9,7 +9,6 @@ pipeline {
         }
         stage("unit tests") {
             steps {
-                // TODO Update the 
                 sh returnStatus: true, script: "python -m pytest --junitxml=unit_tests.xml --cov-report xml:test_coverage.xml --cov=program"
                 xunit checksName: '', tools: [JUnit(excludesPattern: '', pattern: 'test_results.xml', stopProcessingIfError: true)]
                 cobertura autoUpdateHealth: false, autoUpdateStability: false, coberturaReportFile: 'test_coverage.xml', failUnhealthy: false, failUnstable: false, maxNumberOfBuilds: 64, lineCoverageTargets: '50, 0, 0', methodCoverageTargets: '50, 0, 0', onlyStable: false, sourceEncoding: 'ASCII', zoomCoverageChart: false
@@ -18,7 +17,7 @@ pipeline {
         stage("build") {
             steps {
                 sh "python -m build"
-                // Additional build steps go here
+                // TODO Additional build steps go here
             }
         }
         stage("test installation") {
@@ -30,7 +29,7 @@ pipeline {
         stage("archive") {
             steps {
                 archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl'
-                // Additional archival or documentation steps go here
+                // TODO Additional archival or documentation steps go here
             }
         }
         stage("publish") {

environment.yml

@@ -8,3 +8,4 @@ dependencies:
   - pytest
   - twine
   - sphinx
+  - pyvcf

setup.cfg

@@ -1,17 +1,17 @@
 [metadata]
-name = sample
+name = modvcfsamples
 version = 0.0.1
 
 [options]
 package_dir =
-    = src
+    = ./src
-# install_requires =
+install_requires =
-#    cachier   ==2.1
+   pyvcf     ==0.6.8
 
 
-# [options.entry_points]
+[options.entry_points]
-# console_scripts =
+console_scripts =
-#     avariantas = program.program:entry_function
+    modvcfsamples = modvcfsamples.cli:main
 
 [tool:pytest]
 pythonpath = src

setup.py

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

src/modvcfsamples/cli.py

@@ -0,0 +1,39 @@
+import argparse
+import os
+from modvcfsamples import sample
+
+def run(vcfs: list[str], only: list[str], output_dir: str):
+    for vcf in vcfs:
+        vcf_records = sample.get_records_from_vcf(vcf)
+        sample.filter_all_sample_datatypes(vcf_records, *only)
+        sample.write_records_to_vcf(vcf_records, os.path.join(output_dir, os.path.basename(vcf)))
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "vcfs",
+        help="The VCFs to run filtering on",
+        nargs="+",
+        metavar="I",
+        type=str
+    )
+    parser.add_argument(
+        "output_dir",
+        help="The output directory",
+        metavar="O",
+        type=str
+    )
+    parser.add_argument(
+        "--only",
+        "-n",
+        help="Remove everything but the sample datatype",
+        action="append",
+        type=str
+    )
+
+    args = parser.parse_args()
+    run(args.vcfs, args.only, args.output_dir)
+
+
+if __name__ == "__main__":
+    main()

src/modvcfsamples/sample.py

@@ -0,0 +1,34 @@
+import vcf
+from collections import namedtuple
+from copy import deepcopy
+
+def get_records_from_vcf(path: str):
+    vcf_records = []
+    with open(path, "r") as vcf_stream:
+        reader = vcf.Reader(vcf_stream)
+        for record in reader:
+            vcf_records.append(record)
+
+    return vcf_records
+
+def filter_sample_datatype(record, *datatypes: str):
+    call_data = namedtuple("Data", *datatypes)
+    filtered_calls = []
+    modified_record = deepcopy(record)
+    for call in record.samples:
+        kept_data = {}
+        for datatype in datatypes:
+            kept_data[datatype] = call[datatype]
+        filtered_calls.append(call_data(**kept_data))
+    modified_record.samples = filtered_calls
+    return modified_record
+
+def filter_all_sample_datatypes(records: list, *datatypes: str):
+    for record in records:
+        yield filter_sample_datatype(record, *datatypes)
+
+def write_records_to_vcf(records: list, path: str):
+    with open(path, "w") as vcf_stream:
+        writer = vcf.Writer(vcf_stream, records[0])
+        for record in records:
+            writer.write_record(record)

src/program/program.py

@@ -1 +0,0 @@
-# TODO Do stuff!

tests/modvcfsamples/test_sample.py

@@ -0,0 +1,38 @@
+from modvcfsamples.sample import filter_sample_datatype, filter_all_sample_datatypes, get_records_from_vcf
+import os
+
+def test_get_records_from_vcf_not_none():
+    records = get_records_from_vcf(os.path.abspath("tests/resources/test_files_shortened.vcf"))
+    assert len(records) > 0
+
+def test_filter_sample_datatype_not_none():
+    records = get_records_from_vcf(os.path.abspath("tests/resources/test_files_shortened.vcf"))
+    filter_for = ["GT"]
+    modified_record = filter_sample_datatype(records[0], *filter_for)
+    assert modified_record is not None
+
+def test_filter_sample_datatype_only_filtered():
+    records = get_records_from_vcf(os.path.abspath("tests/resources/test_files_shortened.vcf"))
+    filter_for = ["GT"]
+    modified_record = filter_sample_datatype(records[0], *filter_for)
+    for sample in modified_record.samples:
+        assert len(sample) <= len(filter_for)
+        for key, _ in sample._asdict().items():
+            assert key in filter_for
+
+def test_filter_all_sample_datatypes_not_empty():
+    records = get_records_from_vcf(os.path.abspath("tests/resources/test_files_shortened.vcf"))
+    filter_for = ["GT"]
+    modified_records = list(filter_all_sample_datatypes(records, *filter_for))
+    assert len(modified_records) == 11
+
+def test_filter_all_sample_datatypes_filtered():
+    records = get_records_from_vcf(os.path.abspath("tests/resources/test_files_shortened.vcf"))
+    filter_for = ["GT"]
+    modified_records = list(filter_all_sample_datatypes(records, *filter_for))
+    for modified_record in modified_records:
+        for sample in modified_record.samples:
+            assert len(sample) <= len(filter_for)
+            for key, _ in sample._asdict().items():
+                assert key in filter_for
+

tests/program/test_program.py

@@ -1,2 +0,0 @@
-# TODO Test program!
-

tests/resources/test_files_shortened.vcf

@@ -0,0 +1,17 @@
+##fileformat=VCFv4.1
+##fileDate=10122015_22h01m13s
+##source=SHAPEIT2.v837
+##log_file=shapeit_10122015_22h01m13s_3f764d75-2fbb-42df-ab75-8c2dfd5731ce.log
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Phased Genotype">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	Gambian	Chinese	French	Brazilian	Nigerian	Pakistani	English	Colombian	Indian	Japanese
+1	846808	rs4475691	C	T	100	.	AC=1276;AN=5008;DP=20368	GT:GQ:DP	1|1:70:60	0|0:30:10	0|0:20:40	./.:0:0	0|0:70:60	0|0:90:30	0|0:80:70	0|0:50:80	./.:0:0	0|0:100:80	
+1	846854	rs111957712	G	A	100	.	AC=114;AN=5008;DP=20538	GT:GQ:DP	./.:0:0	0|0:40:30	0|0:80:30	0|0:0:20	0|0:40:80	0|0:10:30	./.:0:0	./.:0:0	0|0:70:0	0|0:90:30	
+1	846864	rs950122	G	C	100	.	AC=1116;AN=5008;DP=20582	GT:GQ:DP	1|1:60:0	0|0:20:0	0|0:90:70	0|0:80:50	0|0:80:30	0|0:10:80	0|0:100:20	0|0:30:40	./.:0:0	0|0:30:90	
+1	847228	rs3905286	C	T	100	.	AC=1215;AN=5008;DP=20731	GT:GQ:DP	1|1:70:80	0|0:90:80	0|0:60:50	0|0:60:90	0|0:30:40	0|0:70:10	0|0:100:80	0|0:100:50	0|1:70:100	0|0:40:40	
+1	847297	rs11507768	G	A	100	.	AC=359;AN=5008;DP=20809	GT:GQ:DP	1|0:0:60	0|0:10:30	0|0:80:60	./.:0:0	0|0:10:100	0|0:10:100	./.:0:0	0|0:100:40	0|0:20:20	0|0:10:0	
+1	847491	rs28407778	G	A	100	.	AC=1262;AN=5008;DP=16939	GT:GQ:DP	1|1:0:100	0|0:70:40	0|0:0:60	0|0:90:90	0|0:90:90	./.:0:0	0|0:70:60	0|0:70:0	0|1:90:100	0|0:60:60	
+1	848023	rs144407116	C	A	100	.	AC=52;AN=5008;DP=22562	GT:GQ:DP	0|1:10:60	0|0:20:80	0|0:20:50	0|0:20:90	0|0:90:10	0|0:70:60	0|0:40:30	0|0:60:0	0|0:40:40	0|0:10:10	
+1	848090	rs4246505	G	A	100	.	AC=857;AN=5008;DP=19301	GT:GQ:DP	0|0:70:70	0|0:90:30	0|0:40:10	0|0:80:20	0|0:50:50	0|0:10:30	./.:0:0	0|0:20:60	./.:0:0	0|0:90:0	
+1	848445	rs4626817	G	A	100	.	AC=1255;AN=5008;DP=18444	GT:GQ:DP	1|1:100:40	0|0:80:90	0|0:30:100	0|0:100:60	0|0:40:90	0|0:20:30	0|0:70:100	./.:0:0	./.:0:0	0|0:80:30	
+1	848456	rs11507767	A	G	100	.	AC=1266;AN=5008;DP=18137	GT:GQ:DP	1|1:40:30	./.:0:0	0|0:60:90	0|0:60:40	0|0:100:80	0|0:50:50	0|0:0:10	0|0:60:0	0|1:100:100	./.:0:0 
+1	848738	rs3829741	C	T	100	.	AC=855;AN=5008;DP=16663	GT:GQ:DP	0|0:50:90	0|0:50:50	0|0:50:30	0|0:60:60	0|0:80:40	0|0:50:80	0|0:0:80	0|0:0:30	0|1:10:0	0|0:70:30