public void CreateAndQuery_multiple_chromosomes()
{
using (var stream = new MemoryStream())
using (var writer = new ExtendedBinaryWriter(stream))
{
var index = new RefMinorIndex(writer, GenomeAssembly.GRCh37, new DataSourceVersion("name", "1", DateTime.Now.Ticks), SaCommon.SchemaVersion);
index.Add(0, 100);
index.Add(0, 105);
index.Add(0, 110);
index.Add(0, 115);
index.Add(1, 200);
index.Add(1, 205);
index.Add(1, 210);
index.Add(2, 315);
index.Write(320);
(long location, int byteCount, int count) = index.GetFileRange(0);
Assert.Equal(100, location);
Assert.Equal(100, byteCount);
Assert.Equal(4, count);
(location, byteCount, count) = index.GetFileRange(1);
Assert.Equal(200, location);
Assert.Equal(115, byteCount);
Assert.Equal(3, count);
(location, byteCount, count) = index.GetFileRange(2);
Assert.Equal(315, location);
Assert.Equal(5, byteCount);
Assert.Equal(1, count);
}
}
public void ReadBack()
{
var stream = new MemoryStream();
using (var writer = new ExtendedBinaryWriter(stream))
{
var index = new RefMinorIndex(writer, GenomeAssembly.GRCh37, new DataSourceVersion("name", "1", DateTime.Now.Ticks), SaCommon.SchemaVersion);
index.Add(0, 100);
index.Add(0, 105);
index.Add(0, 110);
index.Add(0, 115);
index.Add(1, 200);
index.Add(1, 205);
index.Add(1, 210);
index.Add(2, 315);
index.Write(320);
}
var readStream = new MemoryStream(stream.ToArray())
{
Position = 0
};
using (var reader = new ExtendedBinaryReader(readStream))
{
var index = new RefMinorIndex(reader);
(long location, int byteCount, int count) = index.GetFileRange(0);
Assert.Equal(100, location);
Assert.Equal(100, byteCount);
Assert.Equal(4, count);
(location, byteCount, count) = index.GetFileRange(1);
Assert.Equal(200, location);
Assert.Equal(115, byteCount);
Assert.Equal(3, count);
(location, byteCount, count) = index.GetFileRange(2);
Assert.Equal(315, location);
Assert.Equal(5, byteCount);
Assert.Equal(1, count);
}
}
public void Write(IEnumerable <ISupplementaryDataItem> saItems)
{
var itemsMinHeap = new MinHeap <ISupplementaryDataItem>(SuppDataUtilities.CompareTo);
var chromIndex = ushort.MaxValue;
var currentEnsemblName = "";
var benchmark = new Benchmark();
foreach (var saItem in saItems)
{
if (chromIndex != saItem.Chromosome.Index)
{
if (chromIndex != ushort.MaxValue)
{
//flushing out the remaining items in buffer
WriteUptoPosition(itemsMinHeap, int.MaxValue);
Console.WriteLine($"Chromosome {currentEnsemblName} completed in {Benchmark.ToHumanReadable(benchmark.GetElapsedTime())}");
benchmark.Reset();
}
chromIndex = saItem.Chromosome.Index;
currentEnsemblName = saItem.Chromosome.EnsemblName;
_refProvider.LoadChromosome(saItem.Chromosome);
}
if (saItem.RefAllele != _refProvider.Sequence.Substring(saItem.Position - 1, saItem.RefAllele.Length))
{
continue;
}
//the items come in sorted order of the pre-trimmed position.
//So when writing out, we have to make sure that we do not write past this position.
//Once a position has been seen in the stream, we can safely write all positions before that.
var writeToPos = saItem.Position;
saItem.Trim();
itemsMinHeap.Add(saItem);
WriteUptoPosition(itemsMinHeap, writeToPos);
}
//flushing out the remaining items in buffer
WriteUptoPosition(itemsMinHeap, int.MaxValue);
Console.WriteLine($"Chromosome {currentEnsemblName} completed in {Benchmark.ToHumanReadable(benchmark.GetElapsedTime())}");
_refMinorIndex.Write(_stream.Position);
}