/// <summary>
/// Process and extract the given RAW file.
/// </summary>
/// <param name="parseInput">the parse input object</param>
private static void ProcessFile(ParseInput parseInput)
{
var rawFileWrapper = InitRawFile(parseInput);
ProcessFile(rawFileWrapper.RawFile, rawFileWrapper.FirstScanNumber, rawFileWrapper.LastScanNumber, parseInput);
rawFileWrapper.Dispose();
}
public RawFileWrapper(IRawDataPlus rawFile, int firstScanNumber, int lastScanNumber, ParseInput parseInput)
{
RawFile = rawFile;
FirstScanNumber = firstScanNumber;
LastScanNumber = lastScanNumber;
ParseInput = parseInput;
}
/// <summary>
/// Process and extract the RAW file(s).
/// </summary>
/// <param name="parseInput">the parse input object</param>
public static void Parse(ParseInput parseInput)
{
// Input raw folder mode
if (parseInput.RawDirectoryPath != null)
{
Log.Info("Started analyzing folder " + parseInput.RawDirectoryPath);
var rawFilesPath = Directory
.EnumerateFiles(parseInput.RawDirectoryPath, "*", SearchOption.TopDirectoryOnly)
.Where(s => s.ToLower().EndsWith("raw")).ToArray();
Log.Info(String.Format("The folder contains {0} RAW files", rawFilesPath.Length));
if (rawFilesPath.Length == 0)
{
Log.Debug("No raw files found in folder");
throw new RawFileParserException("No raw files found in folder!");
}
foreach (var filePath in rawFilesPath)
{
parseInput.RawFilePath = filePath;
Log.Info("Started parsing " + parseInput.RawFilePath);
try
{
ProcessFile(parseInput);
}
catch (UnauthorizedAccessException ex)
{
Log.Error(!ex.Message.IsNullOrEmpty()
? ex.Message
: "Attempting to write to an unauthorized location.");
}
catch (Exception ex)
{
if (ex is RawFileParserException)
{
Log.Error(ex.Message);
}
else
{
Log.Error("An unexpected error occured while parsing file:" + parseInput.RawFilePath);
Log.Error(ex.ToString());
}
}
}
}
// Input raw file mode
else
{
Log.Info("Started parsing " + parseInput.RawFilePath);
ProcessFile(parseInput);
}
}
/*private static readonly log4net.ILog Log =
* log4net.LogManager.GetLogger(System.Reflection.MethodBase.GetCurrentMethod().DeclaringType);*/
/// <summary>
/// Process and extract the RAW file(s).
/// </summary>
/// <param name="parseInput">the parse input object</param>
public static void Parse(ParseInput parseInput)
{
// Input raw folder mode
if (parseInput.RawDirectoryPath != null)
{
//Log.Info("Started analyzing folder " + parseInput.RawDirectoryPath);
Console.WriteLine("Started analyzing folder " + parseInput.RawDirectoryPath);
var rawFilesPath =
Directory.EnumerateFiles(parseInput.RawDirectoryPath);
if (Directory.GetFiles(parseInput.RawDirectoryPath, "*", SearchOption.TopDirectoryOnly).Length == 0)
{
//Log.Debug("No raw files found in folder");
throw new RawFileParserException("No raw files found in folder!");
}
foreach (var filePath in rawFilesPath)
{
parseInput.RawFilePath = filePath;
//Log.Info("Started parsing " + parseInput.RawFilePath);
try
{
ProcessFile(parseInput);
}
catch (UnauthorizedAccessException ex)
{
/*Log.Error(!ex.Message.IsNullOrEmpty()
* ? ex.Message
* : "Attempting to write to an unauthorized location.");*/
}
catch (Exception ex)
{
if (ex is RawFileParserException)
{
//Log.Error(ex.Message);
}
else
{
//Log.Error("An unexpected error occured while parsing file:" + parseInput.RawFilePath);
//Log.Error(ex.ToString());
}
}
}
}
// Input raw file mode
else
{
//Log.Info("Started parsing " + parseInput.RawFilePath);
ProcessFile(parseInput);
}
}
public static RawFileWrapper InitRawFile(ParseInput parseInput)
{
// Create the IRawDataPlus object for accessing the RAW file
IRawDataPlus rawFile;
rawFile = RawFileReaderFactory.ReadFile(parseInput.RawFilePath);
if (!rawFile.IsOpen)
{
throw new RawFileParserException("Unable to access the RAW file using the native Thermo library.");
}
// Check for any errors in the RAW file
if (rawFile.IsError)
{
throw new RawFileParserException($"Error opening ({rawFile.FileError}) - {parseInput.RawFilePath}");
}
// Check if the RAW file is being acquired
if (rawFile.InAcquisition)
{
throw new RawFileParserException("RAW file still being acquired - " + parseInput.RawFilePath);
}
// Get the number of instruments (controllers) present in the RAW file and set the
// selected instrument to the MS instrument, first instance of it
rawFile.SelectInstrument(Device.MS, 1);
// Get the first and last scan from the RAW file
var firstScanNumber = rawFile.RunHeaderEx.FirstSpectrum;
var lastScanNumber = rawFile.RunHeaderEx.LastSpectrum;
//Console.WriteLine("Last scan number is " + lastScanNumber);
return(new RawFileWrapper(rawFile, firstScanNumber, lastScanNumber, parseInput));
}
/// <summary>
/// Extract the RAW file metadata and spectra in MGF format.
/// </summary>
/// <param name="parseInput">the parse input object</param>
public static void Parse(ParseInput parseInput)
{
// Check to see if the RAW file name was supplied as an argument to the program
if (string.IsNullOrEmpty(parseInput.RawFilePath))
{
throw new Exception("No RAW file specified!");
}
// Check to see if the specified RAW file exists
if (!File.Exists(parseInput.RawFilePath))
{
throw new Exception(@"The file doesn't exist in the specified location - " + parseInput.RawFilePath);
}
Log.Info("Started parsing " + parseInput.RawFilePath);
// Create the IRawDataPlus object for accessing the RAW file
//var rawFile = RawFileReaderAdapter.FileFactory(rawFilePath);
IRawDataPlus rawFile;
using (rawFile = RawFileReaderFactory.ReadFile(parseInput.RawFilePath))
{
if (!rawFile.IsOpen)
{
throw new Exception("Unable to access the RAW file using the RawFileReader class!");
}
// Check for any errors in the RAW file
if (rawFile.IsError)
{
throw new Exception($"Error opening ({rawFile.FileError}) - {parseInput.RawFilePath}");
}
// Check if the RAW file is being acquired
if (rawFile.InAcquisition)
{
throw new Exception("RAW file still being acquired - " + parseInput.RawFilePath);
}
// Get the number of instruments (controllers) present in the RAW file and set the
// selected instrument to the MS instrument, first instance of it
rawFile.SelectInstrument(Device.MS, 1);
// Get the first and last scan from the RAW file
var firstScanNumber = rawFile.RunHeaderEx.FirstSpectrum;
var lastScanNumber = rawFile.RunHeaderEx.LastSpectrum;
if (parseInput.OutputMetadata != MetadataFormat.NON)
{
var metadataWriter = new MetadataWriter(parseInput.OutputDirectory, parseInput.RawFileNameWithoutExtension);
if (parseInput.OutputMetadata == MetadataFormat.JSON)
{
metadataWriter.WriteJsonMetada(rawFile, firstScanNumber, lastScanNumber);
}
if (parseInput.OutputMetadata == MetadataFormat.TXT)
{
metadataWriter.WriteMetada(rawFile, firstScanNumber, lastScanNumber);
}
}
if (parseInput.OutputFormat != OutputFormat.NON)
{
SpectrumWriter spectrumWriter;
switch (parseInput.OutputFormat)
{
case OutputFormat.Mgf:
spectrumWriter = new MgfSpectrumWriter(parseInput);
spectrumWriter.Write(rawFile, firstScanNumber, lastScanNumber);
break;
case OutputFormat.Mzml:
spectrumWriter = new MzMlSpectrumWriter(parseInput);
spectrumWriter.Write(rawFile, firstScanNumber, lastScanNumber);
break;
case OutputFormat.Parquet:
spectrumWriter = new ParquetSpectrumWriter(parseInput);
spectrumWriter.Write(rawFile, firstScanNumber, lastScanNumber);
break;
}
}
Log.Info("Finished parsing " + parseInput.RawFilePath);
}
}
private static void RegularParametersParsing(string[] args)
{
var help = false;
var version = false;
string outputFormatString = null;
string metadataFormatString = null;
string logFormatString = null;
var parseInput = new ParseInput();
var optionSet = new OptionSet
{
{
"h|help", "Prints out the options.",
h => help = h != null
},
{
"version", "Prints out the library version.",
v => version = v != null
},
{
"i=|input=", "The raw file input (Required). Specify this or an input directory -d.",
v => parseInput.RawFilePath = v
},
{
"d=|input_directory=",
"The directory containing the raw files (Required). Specify this or an input raw file -i.",
v => parseInput.RawDirectoryPath = v
},
{
"o=|output=",
"The output directory. Specify this or an output file -b. Specifying neither writes to the input directory.",
v => parseInput.OutputDirectory = v
},
{
"b=|output_file",
"The output file. Specify this or an output directory -o. Specifying neither writes to the input directory.",
v => parseInput.OutputFile = v
},
{
"f=|format=",
"The spectra output format: 0 for MGF, 1 for mzML, 2 for indexed mzML, 3 for Parquet. Defaults to mzML if no format is specified.",
v => outputFormatString = v
},
{
"m=|metadata=", "The metadata output format: 0 for JSON, 1 for TXT.",
v => metadataFormatString = v
},
{
"c=|metadata_output_file",
"The metadata output file. By default the metadata file is written to the output directory.",
v => parseInput.MetadataOutputFile = v
},
{
"g|gzip", "GZip the output file.",
v => parseInput.Gzip = v != null
},
{
"p|noPeakPicking",
"Don't use the peak picking provided by the native Thermo library. By default peak picking is enabled.",
v => parseInput.NoPeakPicking = v != null
},
{
"z|noZlibCompression",
"Don't use zlib compression for the m/z ratios and intensities. By default zlib compression is enabled.",
v => parseInput.NoZlibCompression = v != null
},
{
"a|allDetectors",
"Extract additional detector data: UV/PDA etc",
v => parseInput.AllDetectors = v != null
},
{
"l=|logging=", "Optional logging level: 0 for silent, 1 for verbose.",
v => logFormatString = v
},
{
"e|ignoreInstrumentErrors", "Ignore missing properties by the instrument.",
v => parseInput.IgnoreInstrumentErrors = v != null
},
{
"L=|msLevel=",
"Select MS levels (MS1, MS2, etc) included in the output, should be a comma-separated list of integers ( 1,2,3 ) and/or intervals ( 1-3 ), open-end intervals ( 1- ) are allowed",
v => parseInput.MsLevel = ParseMsLevel(v)
},
{
"P|mgfPrecursor",
"Include precursor scan number in MGF file TITLE",
v => parseInput.MGFPrecursor = v != null
},
{
"u:|s3_url:",
"Optional property to write directly the data into S3 Storage.",
v => parseInput.S3Url = v
},
{
"k:|s3_accesskeyid:",
"Optional key for the S3 bucket to write the file output.",
v => parseInput.S3AccessKeyId = v
},
{
"t:|s3_secretaccesskey:",
"Optional key for the S3 bucket to write the file output.",
v => parseInput.S3SecretAccessKey = v
},
{
"n:|s3_bucketName:",
"S3 bucket name",
v => parseInput.BucketName = v
}
};
try
{
// parse the command line
var extra = optionSet.Parse(args);
if (!extra.IsNullOrEmpty())
{
throw new OptionException("unexpected extra arguments", null);
}
if (help)
{
var helpMessage =
$"usage is {Assembly.GetExecutingAssembly().GetName().Name}.exe [subcommand] [options]\noptional subcommands are xic|query (use [subcommand] -h for more info]):";
ShowHelp(helpMessage, null,
optionSet);
return;
}
if (version)
{
Console.WriteLine(Version);
return;
}
if (parseInput.RawFilePath == null && parseInput.RawDirectoryPath == null)
{
throw new OptionException(
"specify an input file or an input directory",
"-i, --input or -d, --input_directory");
}
if (parseInput.RawFilePath != null)
{
if (parseInput.RawDirectoryPath != null)
{
throw new OptionException(
"specify an input file or an input directory, not both",
"-i, --input or -d, --input_directory");
}
if (!File.Exists(parseInput.RawFilePath))
{
throw new OptionException(
"specify a valid RAW file location",
"-i, --input");
}
}
if (parseInput.RawDirectoryPath != null && !Directory.Exists(parseInput.RawDirectoryPath))
{
throw new OptionException(
"specify a valid input directory",
"-d, --input_directory");
}
if (parseInput.OutputFile == null && parseInput.OutputDirectory == null)
{
if (parseInput.RawFilePath != null)
{
parseInput.OutputDirectory = Path.GetDirectoryName(Path.GetFullPath(parseInput.RawFilePath));
}
else if (parseInput.RawDirectoryPath != null)
{
parseInput.OutputDirectory = parseInput.RawDirectoryPath;
}
}
if (parseInput.OutputFile != null)
{
if (parseInput.OutputDirectory == null)
{
parseInput.OutputDirectory = Path.GetDirectoryName(parseInput.OutputFile);
}
else
{
throw new OptionException(
"specify an output directory or an output file, not both",
"-o, --output or -b, --output_file");
}
if (Directory.Exists(parseInput.OutputFile))
{
throw new OptionException(
"specify a valid output file, not a directory",
"-b, --output_file");
}
if (parseInput.RawDirectoryPath != null)
{
throw new OptionException(
"when using an input directory, specify an output directory instead of an output file",
"-o, --output instead of -b, --output_file");
}
}
if (!parseInput.OutputDirectory.IsNullOrEmpty() && !Directory.Exists(parseInput.OutputDirectory))
{
throw new OptionException(
"specify a valid output directory",
"-o, --output");
}
if (metadataFormatString == null && outputFormatString == null)
{
parseInput.OutputFormat = OutputFormat.MzML;
}
if (outputFormatString != null)
{
int outPutFormatInt;
try
{
outPutFormatInt = int.Parse(outputFormatString);
}
catch (FormatException)
{
throw new OptionException(
"unknown output format value (0 for MGF, 1 for mzML, 2 for indexed mzML, 3 for Parquet)",
"-f, --format");
}
if (Enum.IsDefined(typeof(OutputFormat), outPutFormatInt) &&
((OutputFormat)outPutFormatInt) != OutputFormat.NONE)
{
parseInput.OutputFormat = (OutputFormat)outPutFormatInt;
}
else
{
throw new OptionException(
"unknown output format value (0 for MGF, 1 for mzML, 2 for indexed mzML, 3 for Parquet)",
"-f, --format");
}
}
if (metadataFormatString != null)
{
int metadataInt;
try
{
metadataInt = int.Parse(metadataFormatString);
}
catch (FormatException)
{
throw new OptionException("unknown metadata format value (0 for JSON, 1 for TXT)",
"-m, --metadata");
}
if (Enum.IsDefined(typeof(MetadataFormat), metadataInt) &&
((MetadataFormat)metadataInt) != MetadataFormat.NONE)
{
parseInput.MetadataFormat = (MetadataFormat)metadataInt;
}
else
{
throw new OptionException("unknown metadata format value (0 for JSON, 1 for TXT)",
"-m, --metadata");
}
}
if (parseInput.MetadataOutputFile != null && Directory.Exists(parseInput.MetadataOutputFile))
{
throw new OptionException(
"specify a valid metadata output file, not a directory",
"-c, --metadata_output_file");
}
if (parseInput.MetadataOutputFile != null && parseInput.MetadataFormat == MetadataFormat.NONE)
{
throw new OptionException("specify a metadata format (0 for JSON, 1 for TXT)",
"-m, --metadata");
}
if (parseInput.MetadataOutputFile != null && parseInput.RawDirectoryPath != null)
{
throw new OptionException(
"when using an input directory, specify an output directory instead of a metadata output file",
"-o, --output instead of -c, --metadata_output_file");
}
if (logFormatString != null)
{
int logFormatInt;
try
{
logFormatInt = int.Parse(logFormatString);
}
catch (FormatException)
{
throw new OptionException("unknown log format value (0 for silent, 1 for verbose)",
"-l, --logging");
}
if (Enum.IsDefined(typeof(LogFormat), logFormatInt))
{
if ((LogFormat)logFormatInt != LogFormat.NONE)
{
parseInput.LogFormat = (LogFormat)logFormatInt;
}
}
else
{
throw new OptionException("unknown log format value (0 for silent, 1 for verbose)",
"-l, --logging");
}
}
if (parseInput.S3Url != null && parseInput.S3AccessKeyId != null &&
parseInput.S3SecretAccessKey != null && parseInput.BucketName != null)
{
if (Uri.IsWellFormedUriString(parseInput.S3Url, UriKind.Absolute))
{
parseInput.InitializeS3Bucket();
}
else
{
throw new RawFileParserException("Invalid S3 url: " + parseInput.S3Url);
}
}
}
catch (OptionException optionException)
{
ShowHelp("Error - usage is:", optionException,
optionSet);
}
catch (ArgumentNullException)
{
if (help)
{
ShowHelp("usage is:", null,
optionSet);
}
else
{
ShowHelp("Error - usage is:", null,
optionSet);
}
}
var exitCode = 1;
try
{
switch (parseInput.LogFormat)
{
case LogFormat.VERBOSE:
((log4net.Repository.Hierarchy.Hierarchy)LogManager.GetRepository()).Root.Level =
Level.Debug;
((log4net.Repository.Hierarchy.Hierarchy)LogManager.GetRepository())
.RaiseConfigurationChanged(EventArgs.Empty);
break;
case LogFormat.SILENT:
((log4net.Repository.Hierarchy.Hierarchy)LogManager.GetRepository()).Root.Level =
Level.Off;
((log4net.Repository.Hierarchy.Hierarchy)LogManager.GetRepository())
.RaiseConfigurationChanged(EventArgs.Empty);
break;
}
RawFileParser.Parse(parseInput);
exitCode = 0;
}
catch (UnauthorizedAccessException ex)
{
Log.Error(!ex.Message.IsNullOrEmpty()
? ex.Message
: "Attempting to write to an unauthorized location.");
}
catch (Amazon.S3.AmazonS3Exception ex)
{
Log.Error(!ex.Message.IsNullOrEmpty()
? "An Amazon S3 exception occured: " + ex.Message
: "An Amazon S3 exception occured: " + ex);
}
catch (Exception ex)
{
if (ex is RawFileParserException)
{
Log.Error(ex.Message);
}
else
{
Log.Error("An unexpected error occured:");
Log.Error(ex.ToString());
}
}
finally
{
Environment.Exit(exitCode);
}
}
public static void Main(string[] args)
{
string rawFilePath = null;
string outputDirectory = null;
string outputFile = null;
string outputFormatString = null;
var outputFormat = OutputFormat.NONE;
var gzip = false;
string outputMetadataString = null;
var outputMetadataFormat = MetadataFormat.NONE;
string s3url = null;
string s3AccessKeyId = null;
string s3SecretAccessKey = null;
var verbose = false;
string bucketName = null;
var ignoreInstrumentErrors = false;
var noPeakPicking = false;
var help = false;
var version = false;
var optionSet = new OptionSet
{
{
"h|help", "Prints out the options.",
h => help = h != null
},
{
"version", "Prints out the library version.",
v => version = v != null
},
{
"i=|input=", "The raw file input.",
v => rawFilePath = v
},
{
"o=|output=", "The output directory. Specify this or an output file.",
v => outputDirectory = v
},
{
"b=|output_file", "The output file. Specify this or an output directory",
v => outputFile = v
},
{
"f=|format=",
"The output format for the spectra (0 for MGF, 1 for mzMl, 2 for indexed mzML, 3 for Parquet)",
v => outputFormatString = v
},
{
"m=|metadata=", "The metadata output format (0 for JSON, 1 for TXT).",
v => outputMetadataString = v
},
{
"g|gzip", "GZip the output file if this flag is specified (without value).",
v => gzip = v != null
},
{
"p|noPeakPicking",
"Don't use the peak picking provided by the native thermo library (by default peak picking is enabled)",
v => noPeakPicking = v != null
},
{
"v|verbose", "Enable verbose logging.",
v => verbose = v != null
},
{
"e|ignoreInstrumentErrors", "Ignore missing properties by the instrument.",
v => ignoreInstrumentErrors = v != null
},
{
"u:|s3_url:",
"Optional property to write directly the data into S3 Storage.",
v => s3url = v
},
{
"k:|s3_accesskeyid:",
"Optional key for the S3 bucket to write the file output.",
v => s3AccessKeyId = v
},
{
"t:|s3_secretaccesskey:",
"Optional key for the S3 bucket to write the file output.",
v => s3SecretAccessKey = v
},
{
"n:|s3_bucketName:",
"S3 bucket name",
v => bucketName = v
}
};
try
{
// parse the command line
var extra = optionSet.Parse(args);
if (!extra.IsNullOrEmpty())
{
throw new OptionException("unexpected extra arguments", null);
}
if (help)
{
ShowHelp(" usage is (use -option=value for the optional arguments):", null,
optionSet);
return;
}
if (version)
{
Console.WriteLine(Version);
return;
}
if (outputMetadataString == null && outputFormatString == null)
{
throw new OptionException("The parameter -f or -m should be provided",
"-f|--format , -m|--format");
}
if (outputFormatString != null)
{
int outPutFormatInt;
try
{
outPutFormatInt = int.Parse(outputFormatString);
}
catch (FormatException e)
{
throw new OptionException(
"unknown output format value (0 for MGF, 1 for mzMl, 2 for indexed mzML, 3 for Parquet)",
"-f, --format");
}
if (Enum.IsDefined(typeof(OutputFormat), outPutFormatInt) &&
((OutputFormat)outPutFormatInt) != OutputFormat.NONE)
{
outputFormat = (OutputFormat)outPutFormatInt;
}
else
{
throw new OptionException(
"unknown output format value (0 for MGF, 1 for mzMl, 2 for indexed mzML, 3 for Parquet)",
"-f, --format");
}
}
if (outputMetadataString != null)
{
int metadataInt;
try
{
metadataInt = int.Parse(outputMetadataString);
}
catch (FormatException e)
{
throw new OptionException("unknown metadata format value (0 for JSON, 1 for TXT)",
"-m, --metadata");
}
if (Enum.IsDefined(typeof(MetadataFormat), metadataInt) &&
((MetadataFormat)metadataInt) != MetadataFormat.NONE)
{
outputMetadataFormat = (MetadataFormat)metadataInt;
}
else
{
throw new OptionException("unknown metadata format value (0 for JSON, 1 for TXT)",
"-m, --metadata");
}
}
if (outputFile == null && outputDirectory == null)
{
throw new OptionException(
"specify an output directory or output file",
"-o, --output or -b, --output_file");
}
if (outputFile != null && Directory.Exists(outputFile))
{
throw new OptionException(
"specify a valid output file, not a directory",
"-b, --output_file");
}
if (outputDirectory != null && !Directory.Exists(outputDirectory))
{
throw new OptionException(
"specify a valid output directory",
"-o, --output");
}
}
catch (OptionException optionException)
{
ShowHelp("Error - usage is (use -option=value for the optional arguments):", optionException,
optionSet);
}
catch (ArgumentNullException argumentNullException)
{
if (help)
{
ShowHelp(" usage is (use -option=value for the optional arguments):", null,
optionSet);
}
else
{
ShowHelp("Error - usage is (use -option=value for the optional arguments):", null,
optionSet);
}
}
try
{
if (verbose)
{
((log4net.Repository.Hierarchy.Hierarchy)LogManager.GetRepository()).Root.Level =
Level.Debug;
((log4net.Repository.Hierarchy.Hierarchy)LogManager.GetRepository())
.RaiseConfigurationChanged(EventArgs.Empty);
}
var parseInput = new ParseInput(rawFilePath, outputDirectory, outputFile, outputFormat, gzip,
outputMetadataFormat,
s3url, s3AccessKeyId, s3SecretAccessKey, bucketName, ignoreInstrumentErrors, noPeakPicking,
verbose);
RawFileParser.Parse(parseInput);
}
catch (Exception ex)
{
Log.Error("An unexpected error occured:");
Log.Error(ex.ToString());
Environment.Exit(1);
}
}
public static void Main(string[] args)
{
string rawFilePath = null;
string outputDirectory = null;
string outputFormatString = null;
var outputFormat = OutputFormat.NON;
var gzip = false;
string outputMetadataString = null;
var outputMetadataFormat = MetadataFormat.NON;
var includeProfileData = false;
string collection = null;
string msRun = null;
string subFolder = null;
var help = false;
var optionSet = new OptionSet
{
{
"h|help", "Prints out the options.",
h => help = h != null
},
{
"i=|input=", "The raw file input.",
v => rawFilePath = v
},
{
"o=|output=", "The output directory.",
v => outputDirectory = v
},
{
"f=|format=", "The output format for the spectra (0 for MGF, 1 for MzMl, 2 for Parquet)",
v => outputFormatString = v
},
{
"m=|metadata=", "The metadata output format (0 for JSON, 1 for TXT).",
v => outputMetadataString = v
},
{
"g|gzip", "GZip the output file if this flag is specified (without value).",
v => gzip = v != null
},
{
"p|profiledata",
"Exclude MS2 profile data if this flag is specified (without value). Only for MGF format!",
v => includeProfileData = v != null
},
{
"c:|collection", "The optional collection identifier (PXD identifier for example).",
v => collection = v
},
{
"r:|run:",
"The optional mass spectrometry run name used in the spectrum title. The RAW file name will be used if not specified.",
v => msRun = v
},
{
"s:|subfolder:",
"Optional, to disambiguate instances where the same collection has 2 or more MS runs with the same name.",
v => subFolder = v
}
};
try
{
//parse the command line
var extra = optionSet.Parse(args);
if (!extra.IsNullOrEmpty())
{
throw new OptionException("unexpected extra arguments", null);
}
if (help)
{
ShowHelp(" usage is (use -option=value for the optional arguments):", null,
optionSet);
return;
}
if (outputMetadataString == null && outputFormatString == null)
{
throw new OptionException("The parameter -f or -m should be provided",
"-f|--format , -m|--format");
}
if (outputFormatString != null)
{
int outPutFormatInt;
try
{
outPutFormatInt = int.Parse(outputFormatString);
}
catch (FormatException e)
{
throw new OptionException("unknown output format value (0 for MGF, 1 for MzMl, 2 for Parquet)",
"-f, --format");
}
if (Enum.IsDefined(typeof(OutputFormat), outPutFormatInt) &&
((OutputFormat)outPutFormatInt) != OutputFormat.NON)
{
outputFormat = (OutputFormat)outPutFormatInt;
}
else
{
throw new OptionException("unknown output format value (0 for MGF, 1 for MzMl, 2 for Parquet)",
"-f, --format");
}
}
if (outputMetadataString != null)
{
int metadataInt;
try
{
metadataInt = int.Parse(outputMetadataString);
}
catch (FormatException e)
{
throw new OptionException("unknown metadata format value (0 for JSON, 1 for TXT)",
"-m, --metadata");
}
if (Enum.IsDefined(typeof(MetadataFormat), metadataInt) &&
((MetadataFormat)metadataInt) != MetadataFormat.NON)
{
outputMetadataFormat = (MetadataFormat)metadataInt;
}
else
{
throw new OptionException("unknown metadata format value (0 for JSON, 1 for TXT)",
"-m, --metadata");
}
}
}
catch (OptionException optionException)
{
ShowHelp("Error - usage is (use -option=value for the optional arguments):", optionException,
optionSet);
}
catch (ArgumentNullException argumentNullException)
{
if (help)
{
ShowHelp(" usage is (use -option=value for the optional arguments):", null,
optionSet);
}
else
{
ShowHelp("Error - usage is (use -option=value for the optional arguments):", null,
optionSet);
}
}
try
{
var parseInput = new ParseInput(rawFilePath, outputDirectory, outputFormat, gzip,
outputMetadataFormat,
includeProfileData, collection, msRun, subFolder);
RawFileParser.Parse(parseInput);
}
catch (Exception ex)
{
Log.Error("An unexpected error occured:");
Log.Error(ex.ToString());
Environment.Exit(1);
}
}
/// <summary>
/// Process and extract the given RAW file.
/// </summary>
/// <param name="parseInput">the parse input object</param>
private static void ProcessFile(ParseInput parseInput)
{
// Create the IRawDataPlus object for accessing the RAW file
IRawDataPlus rawFile;
using (rawFile = RawFileReaderFactory.ReadFile(parseInput.RawFilePath))
{
if (!rawFile.IsOpen)
{
throw new RawFileParserException("Unable to access the RAW file using the native Thermo library.");
}
// Check for any errors in the RAW file
if (rawFile.IsError)
{
throw new RawFileParserException($"Error opening ({rawFile.FileError}) - {parseInput.RawFilePath}");
}
// Check if the RAW file is being acquired
if (rawFile.InAcquisition)
{
throw new RawFileParserException("RAW file still being acquired - " + parseInput.RawFilePath);
}
// Get the number of instruments (controllers) present in the RAW file and set the
// selected instrument to the MS instrument, first instance of it
rawFile.SelectInstrument(Device.MS, 1);
rawFile.IncludeReferenceAndExceptionData = parseInput.ExData;
// Get the first and last scan from the RAW file
var firstScanNumber = rawFile.RunHeaderEx.FirstSpectrum;
var lastScanNumber = rawFile.RunHeaderEx.LastSpectrum;
if (parseInput.MetadataFormat != MetadataFormat.NONE)
{
MetadataWriter metadataWriter;
if (parseInput.MetadataOutputFile != null)
{
metadataWriter = new MetadataWriter(null, parseInput.MetadataOutputFile);
}
else
{
metadataWriter = new MetadataWriter(parseInput.OutputDirectory,
parseInput.RawFileNameWithoutExtension);
}
switch (parseInput.MetadataFormat)
{
case MetadataFormat.JSON:
metadataWriter.WriteJsonMetada(rawFile, firstScanNumber, lastScanNumber);
break;
case MetadataFormat.TXT:
metadataWriter.WriteMetadata(rawFile, firstScanNumber, lastScanNumber);
break;
}
}
if (parseInput.OutputFormat != OutputFormat.NONE)
{
SpectrumWriter spectrumWriter;
switch (parseInput.OutputFormat)
{
case OutputFormat.MGF:
spectrumWriter = new MgfSpectrumWriter(parseInput);
spectrumWriter.Write(rawFile, firstScanNumber, lastScanNumber);
break;
case OutputFormat.MzML:
case OutputFormat.IndexMzML:
spectrumWriter = new MzMlSpectrumWriter(parseInput);
spectrumWriter.Write(rawFile, firstScanNumber, lastScanNumber);
break;
case OutputFormat.Parquet:
spectrumWriter = new ParquetSpectrumWriter(parseInput);
spectrumWriter.Write(rawFile, firstScanNumber, lastScanNumber);
break;
}
}
Log.Info("Finished parsing " + parseInput.RawFilePath);
}
}
private static void ProcessFile(IRawDataPlus rawFile, int firstScanNumber, int lastScanNumber, ParseInput parseInput)
{
if (parseInput.MetadataFormat != MetadataFormat.NONE)
{
MetadataWriter metadataWriter;
if (parseInput.MetadataOutputFile != null)
{
metadataWriter = new MetadataWriter(null, parseInput.MetadataOutputFile);
}
else
{
metadataWriter = new MetadataWriter(parseInput.OutputDirectory,
parseInput.RawFileNameWithoutExtension);
}
switch (parseInput.MetadataFormat)
{
case MetadataFormat.JSON:
metadataWriter.WriteJsonMetada(rawFile, firstScanNumber, lastScanNumber);
break;
case MetadataFormat.TXT:
metadataWriter.WriteMetadata(rawFile, firstScanNumber, lastScanNumber);
break;
}
}
if (parseInput.OutputFormat != OutputFormat.NONE)
{
SpectrumWriter spectrumWriter;
switch (parseInput.OutputFormat)
{
case OutputFormat.MGF:
spectrumWriter = new MgfSpectrumWriter(rawFile, parseInput);
spectrumWriter.Write(firstScanNumber, lastScanNumber);
break;
case OutputFormat.MzML:
case OutputFormat.IndexMzML:
spectrumWriter = new MzMlSpectrumWriter(rawFile, parseInput);
spectrumWriter.Write(firstScanNumber, lastScanNumber);
break;
case OutputFormat.Parquet:
spectrumWriter = new ParquetSpectrumWriter(rawFile, parseInput);
spectrumWriter.Write(firstScanNumber, lastScanNumber);
break;
}
}
//Log.Info("Finished parsing " + parseInput.RawFilePath);
Console.WriteLine("Finished parsing " + parseInput.RawFilePath);
}
