public void RemoveConflictingAlleles_does_not_remove_duplicates()
{
var seqProvider = ParserTestUtils.GetSequenceProvider(70220313, "TGCC", 'A', _chromDict);
var topMedReader = new TopMedReader(new StreamReader(GetDupItemsStream()), seqProvider);
var items = topMedReader.GetItems().ToList();
var saItems = new List <ISupplementaryDataItem>(items);
saItems = SuppDataUtilities.RemoveConflictingAlleles(saItems, false);
Assert.Single(saItems);
}
public void GetItems_test()
{
var sequence = new SimpleSequence(new string('T', VariantUtils.MaxUpstreamLength) + "A" + new string('T', 10146 - 10128) + "AC" + new string('T', 10177 - 10146 - 1) + "A", 10128 - 1 - VariantUtils.MaxUpstreamLength);
var seqProvider = new SimpleSequenceProvider(GenomeAssembly.GRCh37, sequence, _chromDict);
var gnomadReader = new TopMedReader(new StreamReader(GetStream()), seqProvider);
var items = gnomadReader.GetItems().ToList();
Assert.Equal(3, items.Count);
Assert.Equal("\"allAf\":0.00266,\"allAn\":125568,\"allAc\":334,\"allHc\":0,\"failedFilter\":true", items[0].GetJsonString());
}
private static ExitCodes ProgramExecution()
{
var referenceProvider = new ReferenceSequenceProvider(FileUtilities.GetReadStream(_compressedReference));
var version = DataSourceVersionReader.GetSourceVersion(_inputFile + ".version");
string outFileName = $"{version.Name}_{version.Version}";
using (var topMedReader = new TopMedReader(GZipUtilities.GetAppropriateStreamReader(_inputFile), referenceProvider))
using (var nsaStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix)))
using (var indexStream = FileUtilities.GetCreateStream(Path.Combine(_outputDirectory, outFileName + SaCommon.SaFileSuffix + SaCommon.IndexSufix)))
using (var nsaWriter = new NsaWriter(nsaStream, indexStream, version, referenceProvider, SaCommon.TopMedTag, true, false, SaCommon.SchemaVersion, false))
{
nsaWriter.Write(topMedReader.GetItems());
}
return(ExitCodes.Success);
}