public void FastqTrimNullTest()
{
ISequence seqObj = new QualitativeSequence(Alphabets.DNA, FastQFormatType.Sanger,
"GGCGCACTTACACCCTACATCCATTG", "IIIIG1?II;IIIII1IIII1%.I7I");
double trimLength = seqObj.Count + 1;
bool trimFromStart = false;
TrimByLength target = new TrimByLength(new FastQParser(), new FastQFormatter(), null, trimLength, trimFromStart);
ISequence actual;
actual = target.Trim(seqObj);
Assert.IsNull(actual);
}
public void FastqTrimFromLeftTest2()
{
ISequence seqObj = new QualitativeSequence(Alphabets.DNA, FastQFormatType.Sanger,
"GGCGCACTTACACCCTACATCCATTG", "IIIIG1?II;IIIII1IIII1%.I7I");
ISequence expected = new QualitativeSequence(Alphabets.DNA, FastQFormatType.Sanger,
"G", "I");
double trimLength = 1;
bool trimFromStart = true;
TrimByLength target = new TrimByLength(new FastQParser(), new FastQFormatter(), null, trimLength, trimFromStart);
ISequence actual;
actual = target.Trim(seqObj);
Assert.AreEqual(BioHelper.GetStringSequence(expected), BioHelper.GetStringSequence(actual));
Assert.AreEqual((expected as QualitativeSequence).QualityScores.ToString(), (actual as QualitativeSequence).QualityScores.ToString());
}
/// <summary>
/// Constructor for holding Trim by length event arguments
/// </summary>
/// <param name="trimFromStart"></param>
/// <param name="input"></param>
/// <param name="filtered"></param>
/// <param name="discarded"></param>
public TrimByLengthArgs(double newLength, bool trimFromStart, InputSubmission input, ISequenceFormatter filtered, ISequenceFormatter discarded, string outFile)
: base(input, outFile)
{
trimmer = new TrimByLength(input.Parser, filtered, discarded, newLength, trimFromStart);
}
/// <summary>
/// usage: SeqcosTrimmerUtil.exe [options] <input> <output>
/// </summary>
/// <param name="args">Command line arguments</param>
static void Main(string[] args)
{
Console.Error.WriteLine(SplashString());
CommandLineOptions myArgs = ProcessCommandLine(args);
#region Trimming
// Determine parser
InputSubmission input = new InputSubmission(myArgs.InputFile);
input.DetermineParserUtil();
// Create a sequence filteredFormatter object
ISequenceFormatter filteredFormatter;
ISequenceFormatter discardedFormatter = null;
// If the format is FASTA, then output will be FASTA.
// Everything else (assuming quality scores are available)
// will be outputted to FASTQ.
if (input.Parser is FastAParser)
{
if (myArgs.TrimByQuality > 0)
{
Console.Error.WriteLine("Cannot trim by quality using a FASTA file.");
Environment.Exit(-1);
}
if (myArgs.DiscardedFile != null)
{
discardedFormatter = new FastAFormatter(myArgs.DiscardedFile);
}
filteredFormatter = new FastAFormatter(myArgs.OutputFile);
}
else
{
if (myArgs.DiscardedFile != null)
{
discardedFormatter = new FastQFormatter(myArgs.DiscardedFile);
}
filteredFormatter = new FastQFormatter(myArgs.OutputFile);
}
// Initialize a Trimmer object
Trimmer myTrimmer = null;
// By now, we should have sanity checked the command line arguments. So we should be able to
// figure out what mode is being used simply by checking the properties.
if (myArgs.TrimByLength > 0)
{
Console.Error.WriteLine("Trimming reads to length {0}", myArgs.TrimByLength);
myTrimmer = new TrimByLength(input.Parser, filteredFormatter, discardedFormatter, myArgs.TrimByLength, myArgs.Left);
}
else if (myArgs.TrimByQuality > 0)
{
if (!(input.Parser is FastQParser))
{
throw new ArgumentException("Input file must be in FASTQ format.");
}
Console.Error.WriteLine("Trimming reads based on quality score {0}", myArgs.TrimByQuality);
myTrimmer = new TrimByQuality(input.Parser, filteredFormatter, discardedFormatter, (byte)myArgs.TrimByQuality, myArgs.Left, (int)Math.Round(myArgs.TrimByLength));
}
else if (myArgs.TrimByRegex != null)
{
Console.Error.WriteLine("Trimming reads based on the regular expression pattern {0}", myArgs.TrimByRegex);
myTrimmer = new TrimByRegex(input.Parser, filteredFormatter, discardedFormatter, myArgs.TrimByRegex);
}
else
{
// Should never reach this line.
Console.Error.WriteLine("Invalid trim mode. Use '-l' or '-q'.");
Environment.Exit(-1);
}
myTrimmer.TrimAll();
#endregion
if (myArgs.Verbose)
{
Console.Error.WriteLine("Trimmed {0}/{1} sequences.", myTrimmer.TrimCount, myTrimmer.Counted);
Console.Error.WriteLine("Discarded {0}/{1} sequences.", myTrimmer.DiscardCount, myTrimmer.Counted);
Console.Error.WriteLine("Output saved in {0}.", Path.GetFullPath(myArgs.OutputFile));
Console.Error.WriteLine("Warning: Output may not be in the same order as the original input.");
}
input.Parser.Close();
filteredFormatter.Close();
if (discardedFormatter != null)
{
discardedFormatter.Close();
}
}
