/**
* Generate a mzTab data line parser. A couple of common method used to parse a data line into
* {@link MZTabRecord} structure.
*
* NOTICE: {@link MZTabColumnFactory} maintain a couple of {@link MZTabColumn} which have internal logical
* position and order. In physical mzTab file, we allow user not obey this logical position organized way,
* and provide their date with own order. In order to distinguish them, we use physical position (a positive
* integer) to record the column location in mzTab file. And use {@link PositionMapping} structure the maintain
* the mapping between them.
*
* @param factory SHOULD NOT set null
* @param positionMapping SHOULD NOT set null
* @param metadata SHOULD NOT set null
*/
protected MZTabDataLineParser(MZTabColumnFactory factory, PositionMapping positionMapping,
Metadata metadata, MZTabErrorList errorList)
{
if (factory == null){
throw new NullReferenceException("Column header factory should be create first.");
}
this.factory = factory;
this.positionMapping = positionMapping;
exchangeMapping = positionMapping.exchange();
mapping = factory.GetOffsetColumnsMap();
if (metadata == null){
throw new NullReferenceException("Metadata should be parser first.");
}
this.metadata = metadata;
_errorList = errorList ?? new MZTabErrorList();
}
public PSMLineParser(MZTabColumnFactory factory, PositionMapping positionMapping, Metadata metadata,
MZTabErrorList errorList)
: base(factory, positionMapping, metadata, errorList)
{
}
/**
* Query {@link uk.ac.ebi.pride.jmztab.utils.errors.MZTabErrorList} to check exist errors or not.
* @throws java.io.IOException
* @throws uk.ac.ebi.pride.jmztab.utils.errors.MZTabException during parse metadata, protein/peptide/small_molecule header line, exists error.
* @throws uk.ac.ebi.pride.jmztab.utils.errors.MZTabErrorOverflowException reference mztab.properties file mztab.max_error_count parameter.
*/
public void check(StreamReader reader)
{
COMLineParser comParser = new COMLineParser();
MTDLineParser mtdParser = new MTDLineParser();
PRHLineParser prhParser = null;
PRTLineParser prtParser = null;
PEHLineParser pehParser = null;
PEPLineParser pepParser = null;
PSHLineParser pshParser = null;
PSMLineParser psmParser = null;
SMHLineParser smhParser = null;
SMLLineParser smlParser = null;
SortedDictionary<int, Comment> commentMap = new SortedDictionary<int, Comment>();
SortedDictionary<int, Protein> proteinMap = new SortedDictionary<int, Protein>();
SortedDictionary<int, Peptide> peptideMap = new SortedDictionary<int, Peptide>();
SortedDictionary<int, PSM> psmMap = new SortedDictionary<int, PSM>();
SortedDictionary<int, SmallMolecule> smallMoleculeMap = new SortedDictionary<int, SmallMolecule>();
PositionMapping prtPositionMapping = null;
PositionMapping pepPositionMapping = null;
PositionMapping psmPositionMapping = null;
PositionMapping smlPositionMapping = null;
string line;
int highWaterMark = 1;
int lineNumber = 0;
while ((line = reader.ReadLine()) != null){
lineNumber++;
if (string.IsNullOrEmpty(line) || line.StartsWith("MTH") || line.StartsWith("#")){
continue;
}
if (line.StartsWith(Section.Comment.Prefix)){
comParser.Parse(lineNumber, line, errorList);
commentMap.Add(lineNumber, comParser.getComment());
continue;
}
Section section = getSection(line);
MZTabError error;
if (section == null){
error = new MZTabError(FormatErrorType.LinePrefix, lineNumber, subString(line));
throw new MZTabException(error);
}
if (section.Level < highWaterMark){
Section currentSection = Section.FindSection(highWaterMark);
error = new MZTabError(LogicalErrorType.LineOrder, lineNumber, currentSection.Name, section.Name);
throw new MZTabException(error);
}
highWaterMark = section.Level;
// There exists errors during checking metadata section.
if (highWaterMark == 1 && ! errorList.IsNullOrEmpty()){
break;
}
switch (highWaterMark){
case 1:
// metadata section.
mtdParser.Parse(lineNumber, line, errorList);
break;
case 2:
if (prhParser != null){
// header line only display once!
error = new MZTabError(LogicalErrorType.HeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
// protein header section
prhParser = new PRHLineParser(mtdParser.Metadata);
prhParser.Parse(lineNumber, line, errorList);
prtPositionMapping = new PositionMapping(prhParser.getFactory(), line);
// tell system to continue check protein data line.
highWaterMark = 3;
break;
case 3:
if (prhParser == null){
// header line should be check first.
error = new MZTabError(LogicalErrorType.NoHeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
if (prtParser == null){
prtParser = new PRTLineParser(prhParser.getFactory(), prtPositionMapping, mtdParser.Metadata,
errorList);
}
prtParser.Parse(lineNumber, line, errorList);
proteinMap.Add(lineNumber, prtParser.getRecord(line));
break;
case 4:
if (pehParser != null){
// header line only display once!
error = new MZTabError(LogicalErrorType.HeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
if (mtdParser.Metadata.MzTabType == MzTabType.Identification){
errorList.Add(new MZTabError(LogicalErrorType.PeptideSection, lineNumber, subString(line)));
}
// peptide header section
pehParser = new PEHLineParser(mtdParser.Metadata);
pehParser.Parse(lineNumber, line, errorList);
pepPositionMapping = new PositionMapping(pehParser.getFactory(), line);
// tell system to continue check peptide data line.
highWaterMark = 5;
break;
case 5:
if (pehParser == null){
// header line should be check first.
error = new MZTabError(LogicalErrorType.NoHeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
if (pepParser == null){
pepParser = new PEPLineParser(pehParser.getFactory(), pepPositionMapping, mtdParser.Metadata,
errorList);
}
pepParser.Parse(lineNumber, line, errorList);
peptideMap.Add(lineNumber, pepParser.getRecord(line));
break;
case 6:
if (pshParser != null){
// header line only display once!
error = new MZTabError(LogicalErrorType.HeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
// psm header section
pshParser = new PSHLineParser(mtdParser.Metadata);
pshParser.Parse(lineNumber, line, errorList);
psmPositionMapping = new PositionMapping(pshParser.getFactory(), line);
// tell system to continue check peptide data line.
highWaterMark = 7;
break;
case 7:
if (pshParser == null){
// header line should be check first.
error = new MZTabError(LogicalErrorType.NoHeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
if (psmParser == null){
psmParser = new PSMLineParser(pshParser.getFactory(), psmPositionMapping, mtdParser.Metadata,
errorList);
}
psmParser.Parse(lineNumber, line, errorList);
psmMap.Add(lineNumber, psmParser.getRecord(line));
break;
case 8:
if (smhParser != null){
// header line only display once!
error = new MZTabError(LogicalErrorType.HeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
// small molecule header section
smhParser = new SMHLineParser(mtdParser.Metadata);
smhParser.Parse(lineNumber, line, errorList);
smlPositionMapping = new PositionMapping(smhParser.getFactory(), line);
// tell system to continue check small molecule data line.
highWaterMark = 9;
break;
case 9:
if (smhParser == null){
// header line should be check first.
error = new MZTabError(LogicalErrorType.NoHeaderLine, lineNumber, subString(line));
throw new MZTabException(error);
}
if (smlParser == null){
smlParser = new SMLLineParser(smhParser.getFactory(), smlPositionMapping, mtdParser.Metadata,
errorList);
}
smlParser.Parse(lineNumber, line, errorList);
smallMoleculeMap.Add(lineNumber, smlParser.getRecord(line));
break;
}
}
if (reader != null){
reader.Close();
}
if (errorList.IsNullOrEmpty()){
_mzTabFile = new MZTabFile(mtdParser.Metadata);
foreach (int id in commentMap.Keys){
_mzTabFile.addComment(id, commentMap[id]);
}
if (prhParser != null){
MZTabColumnFactory proteinColumnFactory = prhParser.getFactory();
_mzTabFile.setProteinColumnFactory(proteinColumnFactory);
foreach (int id in proteinMap.Keys){
_mzTabFile.addProtein(id, proteinMap[id]);
}
}
if (pehParser != null){
MZTabColumnFactory peptideColumnFactory = pehParser.getFactory();
_mzTabFile.setPeptideColumnFactory(peptideColumnFactory);
foreach (int id in peptideMap.Keys){
_mzTabFile.addPeptide(id, peptideMap[id]);
}
}
if (pshParser != null){
MZTabColumnFactory psmColumnFactory = pshParser.getFactory();
_mzTabFile.setPSMColumnFactory(psmColumnFactory);
foreach (int id in psmMap.Keys){
_mzTabFile.addPSM(id, psmMap[id]);
}
}
if (smhParser != null){
MZTabColumnFactory smallMoleculeColumnFactory = smhParser.getFactory();
_mzTabFile.setSmallMoleculeColumnFactory(smallMoleculeColumnFactory);
foreach (int id in smallMoleculeMap.Keys){
_mzTabFile.addSmallMolecule(id, smallMoleculeMap[id]);
}
}
}
}