public static string GetText(DocumentType helpType, Section section)
{
IList<ParameterDescription> list = Read();
if (list == null){
return null;
}
list = list.Where(x => x.Section.Name == section.Name).ToList();
StringBuilder builder = new StringBuilder();
if (helpType == DocumentType.Rtf){
builder.Append("{\rtf1\ansi");
}
foreach (ParameterDescription descripition in list){
switch (helpType){
case DocumentType.Html:
descripition.ToHtml(builder);
break;
case DocumentType.PlainText:
descripition.ToPlainText(builder);
break;
case DocumentType.Rtf:
descripition.ToRichText(builder);
break;
}
}
if (helpType == DocumentType.Rtf){
builder.Append("}");
}
return builder.ToString();
}
private ParameterDescription(string name, Section section, string definition, string multiplicity,
IList<string> example, FieldType fieldType)
{
Name = name;
Section = section;
Definition = definition;
Multiplicity = multiplicity;
Example = example;
_fieldType = fieldType;
}
/**
* {position}{Parameter}-{Type:accession}|{neutral loss}
*/
public Modification(Section section, ModificationType type, string accession)
{
if (! section.isData()){
throw new ArgumentException("Section should use Protein, Peptide, PSM or SmallMolecule.");
}
_section = section;
_type = type;
if (accession == null){
throw new NullReferenceException("Modification accession can not null!");
}
_accession = accession;
}
public static SortedDictionary<string, MZTabColumn> createOptionalColumns(Section section,
StudyVariable studyVariable,
int offset)
{
SortedDictionary<string, MZTabColumn> columns = new SortedDictionary<string, MZTabColumn>();
Section dataSection = Section.toDataSection(section);
AbundanceColumn column = new AbundanceColumn(dataSection, Field.ABUNDANCE, studyVariable, offset);
columns.Add(column.LogicPosition, column);
column = new AbundanceColumn(dataSection, Field.ABUNDANCE_STDEV, studyVariable, offset);
columns.Add(column.LogicPosition, column);
column = new AbundanceColumn(dataSection, Field.ABUNDANCE_STD_ERROR, studyVariable, offset);
columns.Add(column.LogicPosition, column);
return columns;
}
/**
* We assume that user before call this method, have parse the raw line
* is not empty line and start with section prefix.
*/
protected void Parse(int lineNumber, string line, MZTabErrorList errorList)
{
_lineNumber = lineNumber;
_line = line;
_errorList = errorList ?? new MZTabErrorList();
_items = line.Split(MZTabConstants.TAB);
_items[0] = _items[0].Trim();
_items[_items.Length - 1] = _items[_items.Length - 1].Trim();
_section = Section.findSection(_items[0]);
if (_section == null){
MZTabError error = new MZTabError(FormatErrorType.LinePrefix, lineNumber, _items[0]);
_errorList.Add(error);
}
}
/**
* Translate the data line to a {@link MZTabRecord}.
*
* NOTICE: Normally, we suggest user do convert operation after validate successfully.
*
* @see #parse(int, string, uk.ac.ebi.pride.jmztab.utils.errors.MZTabErrorList)
*/
protected MZTabRecord getRecord(Section section, string line)
{
MZTabRecord record = null;
if (section.Equals(Section.Protein)){
record = new Protein(factory);
}
else if (section.Equals(Section.Peptide)){
record = new Peptide(factory, metadata);
}
else if (section.Equals(Section.PSM)){
record = new PSM(factory, metadata);
}
else if (section.Equals(Section.Small_Molecule)){
record = new SmallMolecule(factory, metadata);
}
int offset = loadStableData(record, line);
if (offset == _items.Length - 1){
return record;
}
loadOptionalData(record, offset);
return record;
}
/**
* Check and translate target string into {@link Modification} list which split by ',' character..
* If parse incorrect, raise {@link FormatErrorType#ModificationList} error.
* Normally, ambiguityMembers can set "null", but in "Complete" file, in general "null" values SHOULD not be given.
*
* If software cannot determine protein-level modifications, "null" MUST be used.
* If the software has determined that there are no modifications to a given protein "0" MUST be used.
*
* @param section SHOULD NOT set null
* @param column SHOULD NOT set null
* @param modificationsLabel SHOULD NOT be empty.
*/
protected SplitList<Modification> checkModifications(Section section, MZTabColumn column,
string modificationsLabel)
{
string result_modifications = checkData(column, modificationsLabel, true);
if (result_modifications == null ||
result_modifications.Equals("NULL", StringComparison.CurrentCultureIgnoreCase) ||
result_modifications.Equals("0")){
return new SplitList<Modification>(MZTabConstants.COMMA);
}
SplitList<Modification> modificationList = MZTabUtils.ParseModificationList(section, modificationsLabel);
if (modificationList.Count == 0){
_errorList.Add(new MZTabError(FormatErrorType.ModificationList, _lineNumber, column.Header,
result_modifications));
}
return modificationList;
}
internal static MZTabColumn CreateOptionalColumn(Section section, MZTabColumn column, Integer id, IndexedElement element)
{
if (! column.isOptional()){
throw new ArgumentException(column + " is not optional column!");
}
MZTabColumn optionColumn = null;
if (section.Equals(Section.Protein_Header)){
optionColumn = new ProteinColumn(column.Name, column.Type, column.isOptional(), column.Order, id);
}
else if (section.Equals(Section.Peptide_Header)){
optionColumn = new PeptideColumn(column.Name, column.Type, column.isOptional(), column.Order, id);
}
else if (section.Equals(Section.PSM_Header)){
optionColumn = new PSMColumn(column.Name, column.Type, column.isOptional(), column.Order, id);
}
else if (section.Equals(Section.Small_Molecule_Header)){
optionColumn = new SmallMoleculeColumn(column.Name, column.Type, column.isOptional(), column.Order, id);
}
if (optionColumn != null && element != null){
optionColumn.Element = element;
}
return optionColumn;
}
private AbundanceColumn(Section section, Field field, IndexedElement element, int offset)
: base(translate(section.Name) + "_" + field.name, field.columnType, true, offset + field.position + "")
{
Element = element;
}
public static MZTabColumn createOptionalColumn(Section section, Assay assay, int offset)
{
return new AbundanceColumn(Section.toDataSection(section), Field.ABUNDANCE, assay, offset);
}
private static Modification ParseModification(Section section, string target)
{
target = ParseString(target);
// no modification
if (target.Equals("0")){
return Modification.CreateNoModification(section);
}
target = translateMinusToUnicode(target);
if (target == null){
return null;
}
target = translateTabToComma(target);
string[] items = target.Split("\\-".ToCharArray());
string modLabel;
string positionLabel;
if (items.Length > 2){
// error
return null;
}
if (items.Length == 2){
positionLabel = items[0];
modLabel = items[1];
}
else{
positionLabel = null;
modLabel = items[0];
}
Modification modification = null;
modLabel = translateUnicodeToMinus(modLabel);
Regex regex = new Regex("(MOD|UNIMOD|CHEMMOD|SUBST):([^\\|]+)(\\|\\[([^,]+)?,([^,]+)?,([^,]+),([^,]*)\\])?");
if (regex.IsMatch(modLabel)){
Modification.ModificationType type = Modification.FindType(regex.Match(target).Groups[1].Value);
string accession = regex.Match(target).Groups[2].Value;
modification = new Modification(section, type, accession);
if (positionLabel != null){
parsePosition(positionLabel, modification);
}
CVParam neutralLoss = string.IsNullOrEmpty(regex.Match(target).Groups[6].Value)
? null
: new CVParam(regex.Match(target).Groups[4].Value,
regex.Match(target).Groups[5].Value,
regex.Match(target).Groups[6].Value,
regex.Match(target).Groups[7].Value);
modification.NeutralLoss = neutralLoss;
}
return modification;
}
public static SplitList<Modification> ParseModificationList(Section section, string target)
{
target = ParseString(target);
if (target == null){
return null;
}
SplitList<Modification> modList = new SplitList<Modification>(MZTabConstants.COMMA);
if (target.Equals("0")){
modList.Add(Modification.CreateNoModification(section));
return modList;
}
target = translateCommaToTab(target);
SplitList<string> list = ParseStringList(MZTabConstants.COMMA, target);
foreach (string item in list){
Modification mod = ParseModification(section, item.Trim());
if (mod == null){
modList.Clear();
break;
}
modList.Add(mod);
}
return modList;
}
public Modification(Section section, ModificationType type, int accession)
: this(section, type, accession.ToString(CultureInfo.InvariantCulture))
{
}
/**
*. If the software has determined that there are no modifications to a given protein “0” MUST be used.
*/
public static Modification CreateNoModification(Section section)
{
return new Modification(section, ModificationType.UNKNOWN, "0");
}
/**
* Based on {@link #section} to generate stable columns, and store them into {@link #stableColumnMapping} and
* {@link #columnMapping} which maintain all columns in the factory.
*
* @param section SHOULD be {@link Section#Protein_Header}, {@link Section#Peptide_Header} {@link Section#PSM_Header}
* or {@link Section#Small_Molecule_Header}.
*/
public static MZTabColumnFactory GetInstance(Section section)
{
section = Section.toHeaderSection(section);
if (section == null){
throw new ArgumentException(
"Section should use Protein_Header, Peptide_Header, PSM_Header or Small_Molecule_Header.");
}
MZTabColumnFactory factory = new MZTabColumnFactory();
if (section.Equals(Section.Protein_Header)){
AddStableColumn(factory, ProteinColumn.ACCESSION);
AddStableColumn(factory, ProteinColumn.DESCRIPTION);
AddStableColumn(factory, ProteinColumn.TAXID);
AddStableColumn(factory, ProteinColumn.SPECIES);
AddStableColumn(factory, ProteinColumn.DATABASE);
AddStableColumn(factory, ProteinColumn.DATABASE_VERSION);
AddStableColumn(factory, ProteinColumn.SEARCH_ENGINE);
AddStableColumn(factory, ProteinColumn.AMBIGUITY_MEMBERS);
AddStableColumn(factory, ProteinColumn.MODIFICATIONS);
AddStableColumn(factory, ProteinColumn.PROTEIN_COVERAGE);
}
else if (section.Equals(Section.Peptide_Header)){
AddStableColumn(factory, PeptideColumn.SEQUENCE);
AddStableColumn(factory, PeptideColumn.ACCESSION);
AddStableColumn(factory, PeptideColumn.UNIQUE);
AddStableColumn(factory, PeptideColumn.DATABASE);
AddStableColumn(factory, PeptideColumn.DATABASE_VERSION);
AddStableColumn(factory, PeptideColumn.SEARCH_ENGINE);
AddStableColumn(factory, PeptideColumn.MODIFICATIONS);
AddStableColumn(factory, PeptideColumn.RETENTION_TIME);
AddStableColumn(factory, PeptideColumn.RETENTION_TIME_WINDOW);
AddStableColumn(factory, PeptideColumn.CHARGE);
AddStableColumn(factory, PeptideColumn.MASS_TO_CHARGE);
AddStableColumn(factory, PeptideColumn.SPECTRA_REF);
}
else if (section.Equals(Section.PSM_Header)){
AddStableColumn(factory, PSMColumn.SEQUENCE);
AddStableColumn(factory, PSMColumn.PSM_ID);
AddStableColumn(factory, PSMColumn.ACCESSION);
AddStableColumn(factory, PSMColumn.UNIQUE);
AddStableColumn(factory, PSMColumn.DATABASE);
AddStableColumn(factory, PSMColumn.DATABASE_VERSION);
AddStableColumn(factory, PSMColumn.SEARCH_ENGINE);
AddStableColumn(factory, PSMColumn.MODIFICATIONS);
AddStableColumn(factory, PSMColumn.RETENTION_TIME);
AddStableColumn(factory, PSMColumn.CHARGE);
AddStableColumn(factory, PSMColumn.EXP_MASS_TO_CHARGE);
AddStableColumn(factory, PSMColumn.CALC_MASS_TO_CHARGE);
AddStableColumn(factory, PSMColumn.SPECTRA_REF);
AddStableColumn(factory, PSMColumn.PRE);
AddStableColumn(factory, PSMColumn.POST);
AddStableColumn(factory, PSMColumn.START);
AddStableColumn(factory, PSMColumn.END);
}
else if (section.Equals(Section.Small_Molecule_Header)){
AddStableColumn(factory, SmallMoleculeColumn.IDENTIFIER);
AddStableColumn(factory, SmallMoleculeColumn.CHEMICAL_FORMULA);
AddStableColumn(factory, SmallMoleculeColumn.SMILES);
AddStableColumn(factory, SmallMoleculeColumn.INCHI_KEY);
AddStableColumn(factory, SmallMoleculeColumn.DESCRIPTION);
AddStableColumn(factory, SmallMoleculeColumn.EXP_MASS_TO_CHARGE);
AddStableColumn(factory, SmallMoleculeColumn.CALC_MASS_TO_CHARGE);
AddStableColumn(factory, SmallMoleculeColumn.CHARGE);
AddStableColumn(factory, SmallMoleculeColumn.RETENTION_TIME);
AddStableColumn(factory, SmallMoleculeColumn.TAXID);
AddStableColumn(factory, SmallMoleculeColumn.SPECIES);
AddStableColumn(factory, SmallMoleculeColumn.DATABASE);
AddStableColumn(factory, SmallMoleculeColumn.DATABASE_VERSION);
AddStableColumn(factory, SmallMoleculeColumn.SPECTRA_REF);
AddStableColumn(factory, SmallMoleculeColumn.SEARCH_ENGINE);
AddStableColumn(factory, SmallMoleculeColumn.BEST_SEARCH_ENGINE_SCORE);
AddStableColumn(factory, SmallMoleculeColumn.MODIFICATIONS);
}
else{
throw new NotImplementedException("Section should be Protein, Peptide or " +
"Small_Molecule. Others can not setting. ");
}
foreach (var column in factory.StableColumnMapping){
factory.ColumnMapping.Add(column.Key, column.Value);
}
factory.section = section;
return factory;
}
