public void FastQFormatter()
{
const string FilepathOriginal = @"TestUtils\FASTQ\SRR002012_5.fastq";
Assert.IsTrue(File.Exists(FilepathOriginal));
IList <IQualitativeSequence> seqsOriginal;
string filepathTmp = Path.GetTempFileName();
FastQParser parser = new FastQParser();
using (parser.Open(FilepathOriginal))
{
// Read the original file
seqsOriginal = parser.Parse().ToList();
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
new FastQFormatter()
.Format(seqsOriginal, filepathTmp);
}
// Read the new file, then compare the sequences
using (parser.Open(filepathTmp))
{
IList <IQualitativeSequence> seqsNew = parser.Parse().ToList();
Assert.IsNotNull(seqsNew);
// Now compare the sequences.
int countOriginal = seqsOriginal.Count();
int countNew = seqsNew.Count();
Assert.AreEqual(countOriginal, countNew);
int i;
for (i = 0; i < countOriginal; i++)
{
var orgSequence = seqsOriginal[i];
var sequence = seqsNew[i];
Assert.AreEqual(seqsOriginal[i].ID, sequence.ID);
string orgSeq = Encoding.ASCII.GetString(orgSequence.ToArray());
string newSeq = Encoding.ASCII.GetString(sequence.ToArray());
string orgscores = Encoding.ASCII.GetString(orgSequence.GetEncodedQualityScores());
string newscores = Encoding.ASCII.GetString(sequence.GetEncodedQualityScores());
Assert.AreEqual(orgSeq, newSeq);
Assert.AreEqual(orgscores, newscores);
}
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(filepathTmp);
}
public void FastQFormatter()
{
const string FilepathOriginal = @"TestUtils\FASTQ\SRR002012_5.fastq";
Assert.IsTrue(File.Exists(FilepathOriginal));
IList<IQualitativeSequence> seqsOriginal;
string filepathTmp = Path.GetTempFileName();
FastQParser parser = new FastQParser();
using (parser.Open(FilepathOriginal))
{
// Read the original file
seqsOriginal = parser.Parse().ToList();
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
new FastQFormatter()
.Format(seqsOriginal, filepathTmp);
}
// Read the new file, then compare the sequences
using (parser.Open(filepathTmp))
{
IList<IQualitativeSequence> seqsNew = parser.Parse().ToList();
Assert.IsNotNull(seqsNew);
// Now compare the sequences.
int countOriginal = seqsOriginal.Count();
int countNew = seqsNew.Count();
Assert.AreEqual(countOriginal, countNew);
int i;
for (i = 0; i < countOriginal; i++)
{
var orgSequence = seqsOriginal[i];
var sequence = seqsNew[i];
Assert.AreEqual(seqsOriginal[i].ID, sequence.ID);
string orgSeq = Encoding.ASCII.GetString(orgSequence.ToArray());
string newSeq = Encoding.ASCII.GetString(sequence.ToArray());
string orgscores = Encoding.ASCII.GetString(orgSequence.GetEncodedQualityScores());
string newscores = Encoding.ASCII.GetString(sequence.GetEncodedQualityScores());
Assert.AreEqual(orgSeq, newSeq);
Assert.AreEqual(orgscores, newscores);
}
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(filepathTmp);
}
public void TestFastQWhenParsingOneOfMany()
{
string filepath = @"TestUtils\FASTQ\SRR002012_5.fastq";
// parse
ISequenceParser parser = new FastQParser(filepath);
try
{
ISequence seq = parser.Parse().First();
Assert.IsNotNull(seq);
}
finally
{
parser.Dispose();
}
using (FastQParser fqParser = new FastQParser(filepath))
{
fqParser.AutoDetectFastQFormat = false;
fqParser.FormatType = FastQFormatType.Sanger;
fqParser.Alphabet = Alphabets.DNA;
QualitativeSequence qualSeq = fqParser.Parse().First();
Assert.IsNotNull(qualSeq);
}
}
/// <summary>
/// General method to validate FastQ Parser On Streams.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQParserOnAStream(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
IList <IQualitativeSequence> qualSequenceList;
using (var reader = File.OpenRead(filePath))
{
// Parse a FastQ file.
var fastQParserObj = new FastQParser();
qualSequenceList = fastQParserObj.Parse(reader).ToList();
}
string actualQualitativeSequence = qualSequenceList[0].ConvertToString();
string actualId = qualSequenceList[0].ID;
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, actualQualitativeSequence);
Assert.AreEqual(actualId, expectedSequenceId);
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence '{0}' validation after Parse(Stream) is found to be as expected.",
actualQualitativeSequence));
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence ID '{0}' validation after Parse(Stream) is found to be as expected.",
actualId));
}
/// <summary>
/// General method to validate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string expectedSeqCount = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SeqsCount);
// Parse a FastQ file.
using (var fastQParserObj = new FastQParser(filePath))
{
IEnumerable <QualitativeSequence> qualSequenceList = null;
qualSequenceList = fastQParserObj.Parse();
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(qualSequenceList.Count().ToString((IFormatProvider)null), expectedSeqCount);
Assert.AreEqual(new String(qualSequenceList.ElementAt(0).Select(a => (char)a).ToArray()),
expectedQualitativeSequence);
Assert.AreEqual(qualSequenceList.ElementAt(0).ID.ToString(null), expectedSequenceId);
ApplicationLog.WriteLine(string.Format(null,
"FastQ Parser BVT: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.",
qualSequenceList.ElementAt(0).Select(a => (char)a).ToArray()));
ApplicationLog.WriteLine(string.Format(null,
"FastQ Parser BVT: The FASTQ sequence ID '{0}' validation after Parse() is found to be as expected.",
qualSequenceList.ElementAt(0).ID.ToString(null)));
}
}
public void InvalidateFastQParseNoFileName()
{
using (var fqParserObj = new FastQParser(null))
{
fqParserObj.Parse();
}
}
void InValidateFastQParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string outputId = null;
// Create a FastQ Parser object.
FastQParser fastQParserObj = new FastQParser(filePath);
fastQParserObj.AutoDetectFastQFormat = true;
IEnumerable <QualitativeSequence> parse = null;
try
{
parse = fastQParserObj.Parse();
outputId = parse.ElementAt(0).ID;
Assert.Fail();
}
catch (FileFormatException)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
}
/// <summary>
/// General method to validate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
int expectedSeqCount = int.Parse(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SeqsCount));
// Parse a FastQ file.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
IList <IQualitativeSequence> qualSequenceList = fastQParserObj.Parse().ToList();
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedSeqCount, qualSequenceList.Count);
Assert.AreEqual(expectedQualitativeSequence, qualSequenceList[0].ConvertToString());
Assert.AreEqual(expectedSequenceId, qualSequenceList[0].ID);
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.",
qualSequenceList[0].ConvertToString()));
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence ID '{0}' validation after Parse() is found to be as expected.",
qualSequenceList[0].ID));
}
}
public IEnumerable <ISequence> Parse(Stream stream)
{
FastQParser fqp = new FastQParser();
foreach (var seq in fqp.Parse(stream))
{
var name = seq.ID;
var sp = name.Split('/');
var movie = sp [0];
var hole = sp [1];
SAMAlignedSequence sam = new SAMAlignedSequence();
sam.QuerySequence = seq;
sam.OptionalFields.Add(new SAMOptionalField()
{
Tag = "sn", Value = "f,0,0,0,0"
});
sam.OptionalFields.Add(new SAMOptionalField()
{
Tag = "rs", Value = "f,0,0,0,0,0,0"
});
sam.OptionalFields.Add(new SAMOptionalField()
{
Tag = "zs", Value = "f,0,0,0,0,0,0"
});
PacBioCCSRead read = new PacBioCCSRead(sam)
{
AvgZscore = Single.NaN,
HoleNumber = Convert.ToInt32(hole),
Movie = movie
};
yield return(read);
}
}
public void FastQFormatter()
{
string filepathOriginal = @"TestUtils\FASTQ\SRR002012_5.fastq";
Assert.IsTrue(File.Exists(filepathOriginal));
FastQParser parser = new FastQParser();
FastQFormatter formatter = new FastQFormatter();
// Read the original file
IList <IQualitativeSequence> seqsOriginal = null;
parser = new FastQParser();
seqsOriginal = parser.Parse(filepathOriginal);
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
string filepathTmp = Path.GetTempFileName();
using (TextWriter writer = new StreamWriter(filepathTmp))
{
foreach (IQualitativeSequence s in seqsOriginal)
{
formatter.Format(s, writer);
}
}
// Read the new file, then compare the sequences
IList <IQualitativeSequence> seqsNew = null;
parser = new FastQParser();
seqsNew = parser.Parse(filepathTmp);
Assert.IsNotNull(seqsNew);
// Now compare the sequences.
int countOriginal = seqsOriginal.Count();
int countNew = seqsNew.Count();
Assert.AreEqual(countOriginal, countNew);
int i;
for (i = 0; i < countOriginal; i++)
{
Assert.AreEqual(seqsOriginal[i].ID, seqsNew[i].ID);
string orgSeq = seqsOriginal[i].ToString();
string newSeq = seqsNew[i].ToString();
string orgscores = ASCIIEncoding.ASCII.GetString(seqsOriginal[i].Scores);
string newscores = ASCIIEncoding.ASCII.GetString(seqsNew[i].Scores);
Assert.AreEqual(orgSeq, newSeq);
Assert.AreEqual(orgscores, newscores);
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(filepathTmp);
((FastQParser)parser).Dispose();
}
/// <summary>
/// General method to validate FastQ Formatter on a Stream.
/// <param name="nodeName">xml node name.</param>
/// </summary>
void ValidateFastQFormatterOnAStream(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string tempFileName1 = System.IO.Path.GetTempFileName();
string parsedValue = string.Empty;
string parsedID = string.Empty;
IEnumerable <QualitativeSequence> qualSequence = null;
// Parse a FastQ file using parseOne method.
using (FastQParser fastQParserObj = new FastQParser(filePath))
{
fastQParserObj.AutoDetectFastQFormat = false;
qualSequence = fastQParserObj.Parse();
// New Sequence after formatting file.
IEnumerable <QualitativeSequence> newQualSeq = null;
using (StreamWriter writer = new StreamWriter(tempFileName1))
{
using (FastQFormatter fastQFormatter = new FastQFormatter())
{
fastQFormatter.Open(writer);
fastQFormatter.Write(qualSequence.ElementAt(0));
}
}
using (FastQParser fastQParserObjTemp = new FastQParser(tempFileName1))
{
newQualSeq = fastQParserObjTemp.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString((IFormatProvider)null);
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(parsedValue, expectedQualitativeSequence);
Assert.AreEqual(parsedID, expectedSequenceId);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
// Logs to the VSTest GUI (Console.Out) window
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedID));
qualSequence = null;
File.Delete(tempFileName1);
}
}
/// <summary>
/// General method to Invalidate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void InValidateFastQParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
// Create a FastQ Parser object.
var fastQParserObj = new FastQParser();
{
fastQParserObj.Parse(filePath).ToList();
}
}
void InValidateFastQFormatter(FastQFormatParameters param)
{
// Gets the expected sequence from the Xml
string filepath = utilityObj.xmlUtil.GetTextValue(
Constants.MultiSeqSangerRnaProNode, Constants.FilePathNode);
// Parse a FastQ file.
using (FastQParser fastQParser = new FastQParser(filepath))
{
fastQParser.AutoDetectFastQFormat = true;
IEnumerable <QualitativeSequence> sequence = null;
FastQFormatter fastQFormatter = null;
switch (param)
{
case FastQFormatParameters.Sequence:
try
{
fastQFormatter = new FastQFormatter(filepath);
fastQFormatter.Write(null as ISequence);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
default:
try
{
sequence = fastQParser.Parse();
fastQFormatter = new FastQFormatter(Constants.FastQTempFileName);
fastQFormatter.Write(sequence as QualitativeSequence);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
}
}
}
GetVirtualQualitativeSequenceList(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = Utility._xmlUtil.GetTextValue(
nodeName,
Constants.FilePathNode);
FastQParser parserObj = new FastQParser();
parserObj.EnforceDataVirtualization = true;
VirtualQualitativeSequenceList seqList =
(VirtualQualitativeSequenceList)parserObj.Parse(filePath);
return(seqList);
}
/// <summary>
/// Gets the VirtualSequenceProvider
/// </summary>
/// <returns>Virtual Sequence Provider</returns>
static FileVirtualQualitativeSequenceProvider GetVirtualSequenceProvider()
{
string filePath = Utility._xmlUtil.GetTextValue(
Constants.SingleSequenceSangerFastQNode, Constants.FilePathNode);
FastQParser parserObj = new FastQParser();
parserObj.Parse(filePath);
FileVirtualQualitativeSequenceProvider provObj =
new FileVirtualQualitativeSequenceProvider(parserObj,
GetSequencePointer());
return(provObj);
}
private void InValidateFastQFormatter(FastQFormatParameters param)
{
// Gets the expected sequence from the Xml
string filepath = utilityObj.xmlUtil.GetTextValue(
Constants.MultiSeqSangerRnaProNode, Constants.FilePathNode);
// Parse a FastQ file.
var fastQParser = new FastQParser();
using (fastQParser.Open(filepath))
{
FastQFormatter fastQFormatter = null;
switch (param)
{
case FastQFormatParameters.Sequence:
try
{
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(null as ISequence, filepath);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
default:
try
{
IEnumerable <IQualitativeSequence> sequence = fastQParser.Parse();
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(sequence, null);
Assert.Fail();
}
catch (ArgumentNullException)
{
ApplicationLog.WriteLine("FastQ Parser P2 : Successfully validated the exception");
}
break;
}
}
}
/// <summary>
/// General method to Invalidate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// <param name="IsParseOne">True for FastQParseOne validations, else false</param>
/// </summary>
void InValidateFastQParser(string nodeName, bool IsParseOne)
{
// Gets the expected sequence from the Xml
string filePath = _utilityObj._xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
FastQFormatType expectedFormatType = Utility.GetFastQFormatType(
_utilityObj._xmlUtil.GetTextValue(nodeName, Constants.FastQFormatType));
// Create a FastQ Parser object.
using (FastQParser fastQParserObj = new FastQParser())
{
fastQParserObj.AutoDetectFastQFormat = true;
fastQParserObj.FastqType = expectedFormatType;
if (IsParseOne)
{
try
{
fastQParserObj.ParseOne(filePath);
Assert.Fail();
}
catch (Exception)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
}
else
{
try
{
fastQParserObj.Parse(filePath);
Assert.Fail();
}
catch (Exception)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
}
}
}
public static async void AssemblySequences(string fastqFileName)
{
var parser = new FastQParser();
List <IQualitativeSequence> sequences = new List <IQualitativeSequence>();
using (var fileStream = new FileStream(fastqFileName, FileMode.Open))
{
sequences = parser.Parse(fileStream).ToList();
}
OverlapDeNovoAssembler assembler = new OverlapDeNovoAssembler();
IDeNovoAssembly assembly = assembler.Assemble(sequences);
FastAFormatter outputFormatter = new FastAFormatter();
outputFormatter.Open("assembled_sequences.fasta");
outputFormatter.Format(assembly.AssembledSequences);
outputFormatter.Close();
}
public void InvalidateFastQParseNoFileName()
{
try
{
using (FastQParser fqParserObj = new FastQParser())
{
fqParserObj.Parse(null as string, true);
}
Assert.Fail();
}
catch (ArgumentNullException)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
}
/// <summary>
/// General method to validate FastQ Formatter.
/// <param name="nodeName">xml node name.</param>
/// <param name="fileExtension">Different temporary file extensions</param>
/// </summary>
private void ValidateFastQFormatter(string nodeName, FastQFileParameters fileExtension)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
string tempFileName = Path.GetTempFileName();
// Parse a FastQ file using parseOne method.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
IQualitativeSequence oneSequence = fastQParserObj.ParseOne();
// Format Parsed Sequence to temp file with different extension.
var fastQFormatter = new FastQFormatter();
using (fastQFormatter.Open(tempFileName))
{
fastQFormatter.Format(oneSequence);
}
string parsedValue;
string parsedId;
var fastQParserObjTemp = new FastQParser();
using (fastQParserObjTemp.Open(tempFileName))
{
oneSequence = fastQParserObjTemp.Parse().First();
parsedValue = oneSequence.ConvertToString();
parsedId = oneSequence.ID;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(expectedQualitativeSequence, parsedValue);
Assert.AreEqual(expectedSequenceId, parsedId);
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedId));
File.Delete(tempFileName);
}
}
/// <summary>
/// General method to validate FastQ Parser On Streams.
/// <param name="nodeName">xml node name.</param>
/// </summary>
void ValidateFastQParserOnAStream(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string actualQualitativeSequence = String.Empty;
string actualId = String.Empty;
IEnumerable <QualitativeSequence> qualSequence = null;
IList <QualitativeSequence> qualSequenceList = null;
using (StreamReader reader = new StreamReader(filePath))
{
// Parse a FastQ file.
using (FastQParser fastQParserObj = new FastQParser())
{
fastQParserObj.AutoDetectFastQFormat = false;
qualSequence = fastQParserObj.Parse(reader);
qualSequenceList = qualSequence.ToList();
}
}
actualQualitativeSequence = new string(qualSequenceList[0].Select(a => (char)a).ToArray());
actualId = qualSequenceList[0].ID.ToString((IFormatProvider)null);
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, actualQualitativeSequence);
Assert.AreEqual(actualId, expectedSequenceId);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastQ Parser BVT: The FASTQ sequence '{0}' validation after Parse(Stream) is found to be as expected.",
actualQualitativeSequence));
// Logs to the VSTest GUI (Console.Out) window
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Parser BVT: The FASTQ sequence ID '{0}' validation after Parse(Stream) is found to be as expected.",
actualQualitativeSequence));
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Parser BVT: The FASTQ sequence ID '{0}' validation after Parse(Stream) is found to be as expected.",
actualId));
}
public void TestFastQWhenParsingOneOfMany()
{
string filepath = @"TestUtils\FASTQ\SRR002012_5.fastq";
// Parse
ISequence seq = new FastQParser().ParseOne(filepath);
Assert.IsNotNull(seq);
FastQParser fqParser = new FastQParser
{
FormatType = FastQFormatType.Sanger,
Alphabet = Alphabets.DNA
};
using (fqParser.Open(filepath))
{
var qualSeq = fqParser.Parse().First() as QualitativeSequence;
Assert.IsNotNull(qualSeq);
}
}
public void TestFastQWhenParsingOneOfMany()
{
string filepath = @"TestUtils\FASTQ\SRR002012_5.fastq";
// Parse
ISequence seq = new FastQParser().ParseOne(filepath);
Assert.IsNotNull(seq);
FastQParser fqParser = new FastQParser
{
FormatType = FastQFormatType.Sanger,
Alphabet = Alphabets.DNA
};
using (fqParser.Open(filepath))
{
var qualSeq = fqParser.Parse().First() as QualitativeSequence;
Assert.IsNotNull(qualSeq);
}
}
public IEnumerable<ISequence> Parse(Stream stream)
{
FastQParser fqp = new FastQParser ();
foreach (var seq in fqp.Parse (stream)) {
var name = seq.ID;
var sp = name.Split ('/');
var movie = sp [0];
var hole = sp [1];
SAMAlignedSequence sam = new SAMAlignedSequence ();
sam.QuerySequence = seq;
sam.OptionalFields.Add (new SAMOptionalField () { Tag = "sn", Value = "f,0,0,0,0" });
sam.OptionalFields.Add (new SAMOptionalField () { Tag = "rs", Value = "f,0,0,0,0,0,0" });
sam.OptionalFields.Add (new SAMOptionalField () { Tag = "zs", Value = "f,0,0,0,0,0,0" });
PacBioCCSRead read = new PacBioCCSRead (sam) {
AvgZscore = Single.NaN,
HoleNumber = Convert.ToInt32 (hole),
Movie = movie
};
yield return read;
}
}
public void FastQParserForManyFiles()
{
string path = @"testdata\FASTQ";
Assert.IsTrue(Directory.Exists(path));
int count = 0;
FastQParser parser = new FastQParser();
FastQFormatter formatter = new FastQFormatter();
DirectoryInfo di = new DirectoryInfo(path);
foreach (FileInfo fi in di.GetFiles("*.fastq"))
{
using (StreamReader reader = File.OpenText(fi.FullName))
{
foreach (IQualitativeSequence seq in parser.Parse(reader))
{
count++;
}
}
}
Assert.IsTrue(count >= 3);
}
public void FastQParserForManyFiles()
{
string path = @"TestUtils\FASTQ";
Assert.IsTrue(Directory.Exists(path));
int count = 0;
DirectoryInfo di = new DirectoryInfo(path);
foreach (FileInfo fi in di.GetFiles("*.fastq"))
{
using (FastQParser parser = new FastQParser(fi.FullName))
{
foreach (QualitativeSequence seq in parser.Parse())
{
Assert.IsNotNull(seq);
count++;
}
}
}
Assert.IsTrue(count >= 3);
}
public void AllEditableScenarios()
{
string filepathOriginal = @"TestData\FastQ\SRR002012_5.fastq";
FastQParser fastqParser = new FastQParser();
IList <IQualitativeSequence> qualitativeSequences;
string[] expectedSequences = new string[] {
"GGCGCACTTACACCCTACATCCATTG",
"GTCTGCATTATCTACCAGCACTTCCC",
"GCTGTCTTCCCGCTGTTTTATCCCCC",
"GTAGTTTACCTGTTCATATGTTTCTG",
"GGAAGGAAGAGGCTAGCCCAGCCTTT"
};
fastqParser.EnforceDataVirtualization = true;
fastqParser.AutoDetectFastQFormat = false;
fastqParser.FastqType = FastQFormatType.Sanger;
qualitativeSequences = fastqParser.Parse(filepathOriginal, true);
int sequenceCount = qualitativeSequences.Count;
for (int i = 0; i < sequenceCount; i++)
{
QualitativeSequence actualSequence = qualitativeSequences[i] as QualitativeSequence;
actualSequence.IsReadOnly = false;
ISequenceItem item = actualSequence[1];
actualSequence.Add(item);
expectedSequences[i] += item.Symbol;
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
actualSequence.Remove(item);
int indexOfItem = expectedSequences[i].IndexOf(item.Symbol);
expectedSequences[i] = expectedSequences[i].Remove(indexOfItem, 1);
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
actualSequence.RemoveAt(0);
expectedSequences[i] = expectedSequences[i].Remove(0, 1);
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
actualSequence.RemoveRange(2, 5);
expectedSequences[i] = expectedSequences[i].Remove(2, 5);
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
actualSequence.Replace(0, 'C');
expectedSequences[i] = expectedSequences[i].Remove(0, 1);
expectedSequences[i] = expectedSequences[i].Insert(0, "C");
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
actualSequence.ReplaceRange(5, "GG");
expectedSequences[i] = expectedSequences[i].Remove(5, 2);
expectedSequences[i] = expectedSequences[i].Insert(5, "GG");
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
actualSequence.Insert(10, item);
expectedSequences[i] = expectedSequences[i].Insert(10, item.Symbol.ToString());
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
actualSequence.InsertRange(2, "CC");
expectedSequences[i] = expectedSequences[i].Insert(2, "CC");
Assert.AreEqual(expectedSequences[i], actualSequence.ToString());
bool actualContainsValue = actualSequence.Contains(actualSequence[3]);
bool expectedContainsValue = expectedSequences[i].Contains(actualSequence[3].Symbol.ToString());
Assert.AreEqual(actualContainsValue, expectedContainsValue);
}
}
private void InValidateFastQFormatter(FastQFormatParameters param)
{
// Gets the expected sequence from the Xml
string filepath = utilityObj.xmlUtil.GetTextValue(
Constants.MultiSeqSangerRnaProNode, Constants.FilePathNode);
// Parse a FastQ file.
var fastQParser = new FastQParser();
using (fastQParser.Open(filepath))
{
FastQFormatter fastQFormatter = null;
switch (param)
{
case FastQFormatParameters.Sequence:
try
{
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(null as ISequence, filepath);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
default:
try
{
IEnumerable<IQualitativeSequence> sequence = fastQParser.Parse();
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(sequence, null);
Assert.Fail();
}
catch (ArgumentNullException)
{
ApplicationLog.WriteLine("FastQ Parser P2 : Successfully validated the exception");
}
break;
}
}
}
/// <summary>
/// General method to Invalidate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void InValidateFastQParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
// Create a FastQ Parser object.
var fastQParserObj = new FastQParser();
{
fastQParserObj.Parse(filePath).ToList();
}
}
public void InvalidateFastQParseNoFileName()
{
var fqParserObj = new FastQParser();
Assert.Throws<ArgumentNullException>( () => fqParserObj.Parse(null).ToList());
}
/// <summary>
/// General method to validate BasicSequence Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateBasicSequenceParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filepathOriginal = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
IAlphabet alphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.AlphabetNameNode));
Assert.IsTrue(File.Exists(filepathOriginal));
string tempPath = Path.GetTempFileName();
try
{
ISequenceParser fastQParserObj = SequenceParsers.FindParserByFileName("temp.fq");
// Read the original file
IEnumerable<ISequence> seqsOriginal = fastQParserObj.Parse(filepathOriginal);
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
var formatter = new FastQFormatter();
formatter.Format(seqsOriginal.ElementAt(0), tempPath);
// Read the new file, then compare the sequences
var fastQParserObjNew = new FastQParser();
IEnumerable<IQualitativeSequence> seqsNew = fastQParserObjNew.Parse(tempPath);
Assert.IsNotNull(seqsNew);
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence,
new string(seqsOriginal.ElementAt(0).Select(a => (char) a).ToArray()));
Assert.AreEqual(
seqsOriginal.ElementAt(0).ID.ToString(null),
expectedSequenceId);
Assert.AreEqual(
seqsOriginal.ElementAt(0).Alphabet.Name,
alphabet.Name);
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.",
seqsOriginal.ElementAt(0)));
}
finally
{
File.Delete(tempPath);
}
}
/// <summary>
/// General method to validate FastQ Formatter on a Stream.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQFormatterOnAStream(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
string tempFileName1 = Path.GetTempFileName();
// Parse a FastQ file using parseOne method.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
var oneSequence = fastQParserObj.ParseOne();
// New Sequence after formatting file.
var fastQFormatter = new FastQFormatter();
using (fastQFormatter.Open(tempFileName1))
fastQFormatter.Format(oneSequence);
var fastQParserObjTemp = new FastQParser();
string parsedValue, parsedId;
using (fastQParserObjTemp.Open(tempFileName1))
{
oneSequence = fastQParserObjTemp.Parse().First();
parsedValue = oneSequence.ConvertToString();
parsedId = oneSequence.ID;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(expectedQualitativeSequence, parsedValue);
Assert.AreEqual(expectedSequenceId, parsedId);
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.", parsedValue));
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.", parsedId));
File.Delete(tempFileName1);
}
}
/// <summary>
/// General method to validate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
string expectedSeqCount = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SeqsCount);
IAlphabet alphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.AlphabetNameNodeV2));
var fastQParserObj = new FastQParser();
{
// Validate qualitative Sequence upon parsing FastQ file.
IList<IQualitativeSequence> qualSequenceList = fastQParserObj.Parse<IQualitativeSequence>(filePath).ToList();
Assert.AreEqual(expectedSeqCount, qualSequenceList.Count.ToString((IFormatProvider) null));
Assert.AreEqual(expectedQualitativeSequence, qualSequenceList[0].ConvertToString());
Assert.AreEqual(expectedSequenceId, qualSequenceList[0].ID.ToString(null));
Assert.AreEqual(alphabet, qualSequenceList[0].Alphabet);
}
}
/// <summary>
/// General method to validate FastQ Parser for Multiple sequence with
/// different alphabets.
/// <param name="nodeName">xml node name.</param>
/// <param name="triSeq">Tri Sequence</param>
/// </summary>
private void ValidateMulitpleSequenceFastQParser(string nodeName, string triSeq)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedFirstQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequence1Node);
string expectedSecondQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequence2Node);
string expectedthirdQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequence3Node);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
int expectedSeqCount = int.Parse(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SeqsCount));
// Parse a multiple sequence FastQ file.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
IList<IQualitativeSequence> qualSequenceList = fastQParserObj.Parse().ToList();
// Validate first qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedSeqCount, qualSequenceList.Count);
Assert.AreEqual(expectedFirstQualitativeSequence, qualSequenceList[0].ConvertToString());
Assert.AreEqual(expectedSequenceId, qualSequenceList[0].ID);
// Validate second qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedSecondQualitativeSequence, qualSequenceList[1].ConvertToString());
Assert.AreEqual(expectedSequenceId, qualSequenceList[1].ID);
// Validate third sequence in FastQ file if it is tri sequence FastQ file.
if (0 == string.Compare(triSeq, "MultiSequenceFastQ", CultureInfo.CurrentCulture, CompareOptions.IgnoreCase))
{
// Validate second qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedthirdQualitativeSequence, qualSequenceList[2].ConvertToString());
Assert.AreEqual(expectedSequenceId, qualSequenceList[2].ID);
}
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.",
qualSequenceList[0]));
}
}
/// <summary>
/// General method to validate FastQ formatting
/// Qualitative Sequence by passing TextWriter as a parameter
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQFormatByFormattingQualSeqeunce(string nodeName)
{
// Gets the actual sequence and the alphabet from the Xml
IAlphabet alphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.AlphabetNameNodeV2));
FastQFormatType expectedFormatType = Utility.GetFastQFormatType(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FastQFormatType));
string qualSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string qualityScores = "";
int i;
for (i = 0; i < qualSequence.Length; i++)
qualityScores = qualityScores + "}";
byte[] seq = Encoding.UTF8.GetBytes(qualSequence);
byte[] qScore = Encoding.UTF8.GetBytes(qualityScores);
string tempFileName = Path.GetTempFileName();
// Create a Qualitative Sequence.
var qualSeq = new QualitativeSequence(alphabet, expectedFormatType, seq, qScore);
var formatter = new FastQFormatter();
using (formatter.Open(tempFileName))
{
formatter.Format(qualSeq);
formatter.Close();
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(tempFileName))
{
// Read the new file and validate Sequences.
var seqsNew = fastQParserObj.Parse();
var firstSequence = seqsNew.First();
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, firstSequence.ConvertToString());
Assert.IsTrue(string.IsNullOrEmpty(firstSequence.ID));
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.", firstSequence));
}
File.Delete(tempFileName);
}
}
private void ValidateFastQFormatter(string nodeName, bool writeMultipleSequences)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
string tempFileName = Path.GetTempFileName();
// Parse a FastQ file.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
IEnumerable<IQualitativeSequence> qualSequenceList = fastQParserObj.Parse();
var fastQFormatter = new FastQFormatter();
using (fastQFormatter.Open(tempFileName))
{
if (writeMultipleSequences)
{
foreach (IQualitativeSequence newQualSeq in qualSequenceList)
{
fastQFormatter.Format(newQualSeq);
}
}
else
{
fastQFormatter.Format(qualSequenceList.First());
}
} // temp file is closed.
// Read the new file and validate the first Sequence.
FastQParser fastQParserObjNew = new FastQParser();
IQualitativeSequence firstSequence = fastQParserObjNew.ParseOne(tempFileName);
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, firstSequence.ConvertToString());
Assert.AreEqual(expectedSequenceId, firstSequence.ID);
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.", firstSequence));
File.Delete(tempFileName);
}
}
public void InvalidateFastQParseNoFileName()
{
var fqParserObj = new FastQParser();
Assert.Throws <ArgumentNullException>(() => fqParserObj.Parse(null).ToList());
}
/// <summary>
/// General method to validate multi sequence FastQ Format.
/// </summary>
/// <param name="nodeName">xml node name.</param>
private void ValidateMultiSeqFastQFormatter(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
string expectedSecondQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequence2Node);
string expectedSecondSeqID = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceId1Node);
// Parse a FastQ file.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
var qualSequenceList = fastQParserObj.Parse().ToList();
// Format a first Qualitative sequence
new FastQFormatter().Format(qualSequenceList[0], Constants.FastQTempFileName);
// Read it back
var seqsNew = new FastQParser().Parse(Constants.FastQTempFileName).ToList();
// Format a Second Qualitative sequence
new FastQFormatter().Format(qualSequenceList[1], Constants.StreamWriterFastQTempFileName);
var secondSeqsNew = new FastQParser().Parse(Constants.StreamWriterFastQTempFileName).ToList();
// Validate Second qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedSecondQualitativeSequence, secondSeqsNew[0].ConvertToString());
Assert.AreEqual(expectedSecondSeqID, secondSeqsNew[0].ID);
// Validate first qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, seqsNew[0].ConvertToString());
Assert.AreEqual(expectedSequenceId, seqsNew[0].ID);
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.", seqsNew[0]));
File.Delete(Constants.FastQTempFileName);
File.Delete(Constants.StreamWriterFastQTempFileName);
}
}
private void ValidateFastQFormatter(string nodeName,
FastQFileParameters fileExtension)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string tempFileName = Path.GetTempFileName();
// Parse a FastQ file using parseOne method.
using (var fastQParserObj = new FastQParser(filePath))
{
IEnumerable <QualitativeSequence> qualSequence = null;
qualSequence = fastQParserObj.Parse();
// New Sequence after formatting file.
IEnumerable <QualitativeSequence> newQualSeq = null;
string parsedValue = null;
string parsedID = null;
// Format Parsed Sequence to temp file with different extension.
switch (fileExtension)
{
case FastQFileParameters.FastQ:
using (var fastQFormatter = new FastQFormatter(tempFileName))
{
fastQFormatter.Write(qualSequence.ElementAt(0));
}
using (var fastQParserObjTemp = new FastQParser(tempFileName))
{
newQualSeq = fastQParserObjTemp.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString(null);
}
break;
case FastQFileParameters.Fq:
using (var fastQFormatterFq = new FastQFormatter(tempFileName))
{
fastQFormatterFq.Write(qualSequence.ElementAt(0));
}
using (var fastQParserObjTemp1 = new FastQParser(tempFileName))
{
newQualSeq = fastQParserObjTemp1.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString(null);
}
break;
default:
break;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(parsedValue, expectedQualitativeSequence);
Assert.AreEqual(parsedID, expectedSequenceId);
ApplicationLog.WriteLine(string.Format(null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
ApplicationLog.WriteLine(string.Format(null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedID));
qualSequence = null;
File.Delete(tempFileName);
}
}
void ValidateFastQFormatter(string nodeName,
FastQFileParameters fileExtension)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string tempFileName1 = System.IO.Path.GetTempFileName();
string tempFileName2 = System.IO.Path.GetTempFileName();
// Parse a FastQ file using parseOne method.
using (FastQParser fastQParserObj = new FastQParser(filePath))
{
fastQParserObj.AutoDetectFastQFormat = false;
IEnumerable <ISequence> qualSequence = null;
qualSequence = fastQParserObj.Parse();
// New Sequence after formatting file.
IEnumerable <ISequence> newQualSeq = null;
FastQFormatter fastQFormatter = new FastQFormatter(tempFileName1);
FastQFormatter fastQFormatterFq = new FastQFormatter(tempFileName2);
string parsedValue = null;
string parsedID = null;
// Format Parsed Sequence to temp file with different extension.
switch (fileExtension)
{
case FastQFileParameters.FastQ:
fastQFormatter.Write(qualSequence.ElementAt(0));
fastQFormatter.Close();
FastQParser fastQParserObjTemp = new FastQParser(tempFileName1);
newQualSeq = fastQParserObjTemp.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString((IFormatProvider)null);
fastQParserObjTemp.Dispose();
break;
case FastQFileParameters.Fq:
fastQFormatterFq.Write(qualSequence.ElementAt(0));
fastQFormatterFq.Close();
FastQParser fastQParserObjTemp1 = new FastQParser(tempFileName2);
newQualSeq = fastQParserObjTemp1.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString((IFormatProvider)null);
break;
default:
break;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(parsedValue, expectedQualitativeSequence);
Assert.AreEqual(parsedID, expectedSequenceId);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
// Logs to the NUnit GUI (Console.Out) window
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedID));
qualSequence = null;
fastQFormatter = null;
fastQFormatterFq = null;
GC.Collect();
GC.WaitForPendingFinalizers();
File.Delete(tempFileName1);
File.Delete(tempFileName2);
}
}
public void FastQFormatterUsingInterface()
{
string filepathOriginal = @"TestUtils\FASTQ\SRR002012_5.fastq";
Assert.IsTrue(File.Exists(filepathOriginal));
IList <QualitativeSequence> seqsOriginal = null;
string filepathTmp = Path.GetTempFileName();
using (FastQParser parser = new FastQParser())
{
parser.Open(filepathOriginal);
// Read the original file
seqsOriginal = parser.Parse().ToList();
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
ISequenceFormatter formatter = null;
try
{
formatter = new FastQFormatter();
formatter.Open(filepathTmp);
foreach (ISequence s in seqsOriginal)
{
formatter.Write(s);
}
formatter.Close();
}
finally
{
if (formatter != null)
{
((FastQFormatter)formatter).Dispose();
}
}
}
// Read the new file, then compare the sequences
IList <QualitativeSequence> seqsNew = null;
using (FastQParser parser = new FastQParser(filepathTmp))
{
seqsNew = parser.Parse().ToList();
Assert.IsNotNull(seqsNew);
// Now compare the sequences.
int countOriginal = seqsOriginal.Count();
int countNew = seqsNew.Count();
Assert.AreEqual(countOriginal, countNew);
int i;
for (i = 0; i < countOriginal; i++)
{
Assert.AreEqual(seqsOriginal[i].ID, seqsNew[i].ID);
string orgSeq = ASCIIEncoding.ASCII.GetString(seqsOriginal[i].ToArray());
string newSeq = ASCIIEncoding.ASCII.GetString(seqsNew[i].ToArray());
string orgscores = ASCIIEncoding.ASCII.GetString(seqsOriginal[i].GetEncodedQualityScores());
string newscores = ASCIIEncoding.ASCII.GetString(seqsNew[i].GetEncodedQualityScores());
Assert.AreEqual(orgSeq, newSeq);
Assert.AreEqual(orgscores, newscores);
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(filepathTmp);
}
}
/// <summary>
/// General method to validate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
int expectedSeqCount = int.Parse(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SeqsCount));
// Parse a FastQ file.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
IList<IQualitativeSequence> qualSequenceList = fastQParserObj.Parse().ToList();
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedSeqCount, qualSequenceList.Count);
Assert.AreEqual(expectedQualitativeSequence, qualSequenceList[0].ConvertToString());
Assert.AreEqual(expectedSequenceId, qualSequenceList[0].ID);
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.",
qualSequenceList[0].ConvertToString()));
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence ID '{0}' validation after Parse() is found to be as expected.",
qualSequenceList[0].ID));
}
}
/// <summary>
/// General method to validate FastQ Parser On Streams.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQParserOnAStream(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
IList<IQualitativeSequence> qualSequenceList;
using (var reader = File.OpenRead(filePath))
{
// Parse a FastQ file.
var fastQParserObj = new FastQParser();
qualSequenceList = fastQParserObj.Parse(reader).ToList();
}
string actualQualitativeSequence = qualSequenceList[0].ConvertToString();
string actualId = qualSequenceList[0].ID;
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, actualQualitativeSequence);
Assert.AreEqual(actualId, expectedSequenceId);
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence '{0}' validation after Parse(Stream) is found to be as expected.",
actualQualitativeSequence));
ApplicationLog.WriteLine(string.Format("FastQ Parser BVT: The FASTQ sequence ID '{0}' validation after Parse(Stream) is found to be as expected.",
actualId));
}
