*/
package jalview.io;
-import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentAnnotation;
+import jalview.datamodel.AlignmentI;
import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceGroup;
import jalview.datamodel.SequenceI;
import jalview.util.MessageManager;
import java.io.IOException;
+import java.util.ArrayList;
import java.util.Enumeration;
import java.util.Hashtable;
+import java.util.List;
import java.util.Vector;
/**
* @version $Revision$
*/
public abstract class AlignFile extends FileParse
+ implements AlignmentFileReaderI, AlignmentFileWriterI
{
int noSeqs = 0;
int maxLength = 0;
/**
- * Sequences to be added to form a new alignment.
+ * Sequences to be added to form a new alignment. TODO: remove vector in this
+ * class
*/
protected Vector<SequenceI> seqs;
protected Vector<AlignmentAnnotation> annotations;
/**
+ * SequenceGroups to be added to the alignment object
+ */
+ protected List<SequenceGroup> seqGroups;
+
+ /**
* Properties to be added to generated alignment object
*/
- protected Hashtable properties;
+ private Hashtable properties;
long start;
long end;
- boolean jvSuffix = true;
-
private boolean parseCalled;
/**
initData();
}
+ public AlignFile(SequenceI[] seqs)
+ {
+ this();
+ setSeqs(seqs);
+ }
+
/**
* Constructor which parses the data from a file of some specified type.
*
- * @param inFile
- * Filename to read from.
- * @param type
- * What type of file to read from (File, URL)
+ * @param dataObject
+ * Filename, URL or Pasted String to read from.
+ * @param sourceType
+ * What type of file to read from (File, URL, Pasted String)
*/
- public AlignFile(String inFile, String type) throws IOException
+ public AlignFile(String dataObject, DataSourceType sourceType)
+ throws IOException
{
- this(true, inFile, type);
+ this(true, dataObject, sourceType);
}
-
+
/**
- * Constructor which (optionally delays) parsing of data from a file of some specified type.
+ * Constructor which (optionally delays) parsing of data from a file of some
+ * specified type.
*
* @param parseImmediately
* if false, need to call 'doParse()' to begin parsing data
- * @param inFile
- * Filename to read from.
- * @param type
+ * @param dataObject
+ * Filename, URL or Pasted String to read from.
+ * @param sourceType
* What type of file to read from (File, URL)
* @throws IOException
*/
- public AlignFile(boolean parseImmediately, String inFile, String type) throws IOException
+ public AlignFile(boolean parseImmediately, String dataObject,
+ DataSourceType sourceType) throws IOException
{
- super(inFile, type);
+ super(dataObject, sourceType);
initData();
- if (parseImmediately) {
+ if (parseImmediately)
+ {
doParse();
}
}
+
/**
* Attempt to read from the position where some other parsing process left
* off.
*/
public AlignFile(FileParse source) throws IOException
{
- this(true,source);
+ this(true, source);
}
+
/**
- * Construct a new parser to read from the position where some other parsing process left
+ * Construct a new parser to read from the position where some other parsing
+ * process left
*
* @param parseImmediately
* if false, need to call 'doParse()' to begin parsing data
* @param source
*/
- public AlignFile(boolean parseImmediately, FileParse source) throws IOException
+ public AlignFile(boolean parseImmediately, FileParse source)
+ throws IOException
{
super(source);
initData();
- if (parseImmediately) {
+ if (parseImmediately)
+ {
doParse();
}
}
+
/**
* called if parsing was delayed till after parser was constructed
+ *
* @throws IOException
*/
public void doParse() throws IOException
"Implementation error: Parser called twice for same data.\n"
+ "Need to call initData() again before parsing can be reattempted.");
}
- parseCalled=true;
+ parseCalled = true;
parse();
// sets the index of each sequence in the alignment
for (int i = 0, c = seqs.size(); i < c; i++)
}
}
-
/**
* Return the seqs Vector
*/
return seqs;
}
+ public List<SequenceGroup> getSeqGroups()
+ {
+ return seqGroups;
+ }
+
/**
* Return the Sequences in the seqs Vector as an array of Sequences
*/
+ @Override
public SequenceI[] getSeqsAsArray()
{
SequenceI[] s = new SequenceI[seqs.size()];
for (int i = 0; i < seqs.size(); i++)
{
- s[i] = (SequenceI) seqs.elementAt(i);
+ s[i] = seqs.elementAt(i);
}
return s;
*
* @param al
*/
- public void addAnnotations(Alignment al)
+ @Override
+ public void addAnnotations(AlignmentI al)
{
addProperties(al);
for (int i = 0; i < annotations.size(); i++)
* Rna.GetBasePairsFromAlignmentAnnotation(annotations.elementAt(i));
* Rna.HelixMap(pairArray);
*/
- AlignmentAnnotation an = (AlignmentAnnotation) annotations
- .elementAt(i);
+ AlignmentAnnotation an = annotations.elementAt(i);
an.validateRangeAndDisplay();
al.addAnnotation(an);
}
}
/**
+ * register sequence groups on the alignment for **output**
+ *
+ * @param al
+ */
+ public void addSeqGroups(AlignmentI al)
+ {
+ this.seqGroups = al.getGroups();
+
+ }
+
+ /**
* Add any additional information extracted from the file to the alignment
* properties.
*
* @note implicitly called by addAnnotations()
* @param al
*/
- public void addProperties(Alignment al)
+ public void addProperties(AlignmentI al)
{
if (properties != null && properties.size() > 0)
{
{
if (key == null)
{
- throw new Error(MessageManager.getString("error.implementation_error_cannot_have_null_alignment"));
+ throw new Error(MessageManager.getString(
+ "error.implementation_error_cannot_have_null_alignment"));
}
if (value == null)
{
*/
protected void initData()
{
- seqs = new Vector();
- annotations = new Vector();
- parseCalled=false;
+ seqs = new Vector<SequenceI>();
+ annotations = new Vector<AlignmentAnnotation>();
+ seqGroups = new ArrayList<SequenceGroup>();
+ parseCalled = false;
}
/**
* @param s
* DOCUMENT ME!
*/
- protected void setSeqs(SequenceI[] s)
+ @Override
+ public void setSeqs(SequenceI[] s)
{
- seqs = new Vector();
+ seqs = new Vector<SequenceI>();
for (int i = 0; i < s.length; i++)
{
public abstract void parse() throws IOException;
/**
- * Print out in alignment file format the Sequences in the seqs Vector.
- */
- public abstract String print();
-
- public void addJVSuffix(boolean b)
- {
- jvSuffix = b;
- }
-
- /**
* A general parser for ids.
*
* @String id Id to be parsed
if (space > -1)
{
seq = new Sequence(id.substring(0, space), "");
- seq.setDescription(id.substring(space + 1));
+ String desc = id.substring(space + 1);
+ seq.setDescription(desc);
+
+ /*
+ * it is tempting to parse Ensembl style gene description e.g.
+ * chromosome:GRCh38:7:140696688:140721955:1 and set the
+ * start position of the sequence, but this causes much confusion
+ * for reverse strand feature locations
+ */
}
else
{
}
/**
- * Creates the output id. Adds prefix Uniprot format source|id And suffix
- * Jalview /start-end
+ * Creates the output id. Adds prefix Uniprot format source|id and optionally
+ * suffix Jalview /start-end
+ *
+ * @param jvsuffix
*
* @String id Id to be parsed
*/
+ String printId(SequenceI seq, boolean jvsuffix)
+ {
+ return seq.getDisplayId(jvsuffix);
+ }
+
String printId(SequenceI seq)
{
- return seq.getDisplayId(jvSuffix);
+ return printId(seq, true);
}
/**
* vector of String[] treeName, newickString pairs
*/
- Vector newickStrings = null;
+ Vector<String[]> newickStrings = null;
protected void addNewickTree(String treeName, String newickString)
{
if (newickStrings == null)
{
- newickStrings = new Vector();
+ newickStrings = new Vector<String[]>();
}
- newickStrings.addElement(new String[]
- { treeName, newickString });
+ newickStrings.addElement(new String[] { treeName, newickString });
}
protected int getTreeCount()
{
- if (newickStrings == null)
+ return newickStrings == null ? 0 : newickStrings.size();
+ }
+
+ @Override
+ public void addGroups(AlignmentI al)
+ {
+
+ for (SequenceGroup sg : getSeqGroups())
{
- return 0;
+ al.addGroup(sg);
}
- return newickStrings.size();
}
+ protected void addSequence(SequenceI seq)
+ {
+ seqs.add(seq);
+ }
}