*/
package jalview.io;
-import jalview.analysis.Rna;
-import jalview.datamodel.AlignmentAnnotation;
-import jalview.datamodel.AlignmentI;
-import jalview.datamodel.Annotation;
-import jalview.datamodel.DBRefEntry;
-import jalview.datamodel.DBRefSource;
-import jalview.datamodel.Mapping;
-import jalview.datamodel.Sequence;
-import jalview.datamodel.SequenceFeature;
-import jalview.datamodel.SequenceI;
-import jalview.schemes.ResidueProperties;
-import jalview.util.Comparison;
-import jalview.util.DBRefUtils;
-import jalview.util.Format;
-import jalview.util.MessageManager;
-
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.Hashtable;
import java.util.LinkedHashMap;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import java.util.Vector;
import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;
import fr.orsay.lri.varna.factories.RNAFactory;
import fr.orsay.lri.varna.models.rna.RNA;
-
-// import org.apache.log4j.*;
+import jalview.analysis.Rna;
+import jalview.datamodel.AlignmentAnnotation;
+import jalview.datamodel.AlignmentI;
+import jalview.datamodel.Annotation;
+import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.DBRefSource;
+import jalview.datamodel.Mapping;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
+import jalview.schemes.ResidueProperties;
+import jalview.util.Comparison;
+import jalview.util.DBRefUtils;
+import jalview.util.Format;
+import jalview.util.MessageManager;
/**
* This class is supposed to parse a Stockholm format file into Jalview There
{
private static final String ANNOTATION = "annotation";
- private static final Regex OPEN_PAREN = new Regex("(<|\\[)", "(");
-
- private static final Regex CLOSE_PAREN = new Regex("(>|\\])", ")");
+ // private static final Regex OPEN_PAREN = new Regex("(<|\\[)", "(");
+ //
+ // private static final Regex CLOSE_PAREN = new Regex("(>|\\])", ")");
public static final Regex DETECT_BRACKETS = new Regex(
"(<|>|\\[|\\]|\\(|\\)|\\{|\\})");
- // WUSS extended symbols. Avoid ambiguity with protein SS annotations by using NOT_RNASS first.
+ // WUSS extended symbols. Avoid ambiguity with protein SS annotations by using
+ // NOT_RNASS first.
public static final String RNASS_BRACKETS = "<>[](){}AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz";
// use the following regex to decide an annotations (whole) line is NOT an RNA
// SS (it contains only E,H,e,h and other non-brace/non-alpha chars)
private static final Regex NOT_RNASS = new Regex(
- "^[^<>[\\](){}A-DF-Za-df-z]*$");
+ "^[^<>[\\](){}ADFJ-RUVWYZadfj-ruvwyz]*$");
StringBuffer out; // output buffer
+ umcp.getMessage() + ")";
throw new IOException(umcp);
}
- // DEBUG System.out.println("this is the secondary scructure:"
+ // DEBUG jalview.bin.Console.outPrintln("this is the secondary scructure:"
// +result.size());
SequenceI[] seqs = new SequenceI[result.size()];
String id = null;
for (int i = 0; i < result.size(); i++)
{
- // DEBUG System.err.println("Processing i'th sequence in Stockholm file")
+ // DEBUG jalview.bin.Console.errPrintln("Processing i'th sequence in
+ // Stockholm file")
RNA current = result.get(i);
String seq = current.getSeq();
String rna = current.getStructDBN(true);
- // DEBUG System.out.println(seq);
- // DEBUG System.err.println(rna);
+ // DEBUG jalview.bin.Console.outPrintln(seq);
+ // DEBUG jalview.bin.Console.errPrintln(rna);
int begin = 0;
int end = seq.length() - 1;
id = safeName(getDataName());
r = new Regex("# STOCKHOLM ([\\d\\.]+)");
if (!r.search(nextLine()))
{
- throw new IOException(MessageManager
- .getString("exception.stockholm_invalid_format"));
+ throw new IOException(
+ MessageManager.getString("exception.stockholm_invalid_format")
+ + " (" + r + ")");
}
else
{
Regex openparen = new Regex("(<|\\[)", "(");
Regex closeparen = new Regex("(>|\\])", ")");
- // Detect if file is RNA by looking for bracket types
- Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
+ // // Detect if file is RNA by looking for bracket types
+ // Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
rend.optimize();
p.optimize();
// End of the alignment, pass stuff back
this.noSeqs = seqs.size();
- String seqdb, dbsource = null;
+ String dbsource = null;
Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
if (getAlignmentProperty("AC") != null)
if (dbr != null)
{
// we could get very clever here - but for now - just try to
- // guess accession type from type of sequence, source of alignment plus
+ // guess accession type from type of sequence, source of alignment
+ // plus
// structure
// of accession
guessDatabaseFor(seqO, dbr, dbsource);
}
else if (!r.search(line))
{
- // System.err.println("Found sequence line: " + line);
+ // jalview.bin.Console.errPrintln("Found sequence line: " + line);
// Split sequence in sequence and accession parts
if (!x.search(line))
String annType = r.stringMatched(1);
String annContent = r.stringMatched(2);
- // System.err.println("type:" + annType + " content: " + annContent);
+ // jalview.bin.Console.errPrintln("type:" + annType + " content: " +
+ // annContent);
if (annType.equals("GF"))
{
treeName = an.stringMatched(2);
treeString = new StringBuffer();
}
- // TODO: JAL-3532 - this is where GF comments and database references are lost
- // suggest overriding this method for Stockholm files to catch and properly
+ // TODO: JAL-3532 - this is where GF comments and database
+ // references are lost
+ // suggest overriding this method for Stockholm files to catch and
+ // properly
// process CC, DR etc into multivalued properties
setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));
}
else
{
// throw new IOException("Error parsing " + line);
- System.err.println(">> missing annotation: " + line);
+ jalview.bin.Console
+ .errPrintln(">> missing annotation: " + line);
}
}
else if (annType.equals("GC"))
// }
else
{
- System.err.println(
+ jalview.bin.Console.errPrintln(
"Warning - couldn't parse sequence annotation row line:\n"
+ line);
// throw new IOException("Error parsing " + line);
}
if (dbsource == null)
{
- // make up an origin based on whether the sequence looks like it is nucleotide
+ // make up an origin based on whether the sequence looks like it is
+ // nucleotide
// or protein
dbsource = (seqO.isProtein()) ? "PFAM" : "RFAM";
}
annot.annotations.length);
System.arraycopy(els, 0, anns, annot.annotations.length, els.length);
annot.annotations = anns;
- // System.out.println("else: ");
+ // jalview.bin.Console.outPrintln("else: ");
}
return annot;
}
return ref.getSource().toString() + " ; "
+ ref.getAccessionId().toString();
}
+
@Override
public String print(SequenceI[] s, boolean jvSuffix)
{
int max = 0;
int maxid = 0;
int in = 0;
- Hashtable dataRef = null;
+ int slen = s.length;
+ SequenceI seq;
+ Hashtable<String, String> dataRef = null;
boolean isAA = s[in].isProtein();
- while ((in < s.length) && (s[in] != null))
+ while ((in < slen) && ((seq = s[in]) != null))
{
-
- String tmp = printId(s[in], jvSuffix);
- max = Math.max(max, s[in].getLength());
+ String tmp = printId(seq, jvSuffix);
+ max = Math.max(max, seq.getLength());
if (tmp.length() > maxid)
{
maxid = tmp.length();
}
- if (s[in].getDBRefs() != null)
+ List<DBRefEntry> seqrefs = seq.getDBRefs();
+ int ndb;
+ if (seqrefs != null && (ndb = seqrefs.size()) > 0)
{
if (dataRef == null)
{
- dataRef = new Hashtable();
+ dataRef = new Hashtable<>();
}
- List<DBRefEntry> primrefs = s[in].getPrimaryDBRefs();
+ List<DBRefEntry> primrefs = seq.getPrimaryDBRefs();
if (primrefs.size() >= 1)
{
dataRef.put(tmp, dbref_to_ac_record(primrefs.get(0)));
}
else
{
- for (int idb = 0; idb < s[in].getDBRefs().length; idb++)
+ for (int idb = 0; idb < seq.getDBRefs().size(); idb++)
{
- DBRefEntry dbref = s[in].getDBRefs()[idb];
+ DBRefEntry dbref = seq.getDBRefs().get(idb);
dataRef.put(tmp, dbref_to_ac_record(dbref));
// if we put in a uniprot or EMBL record then we're done:
if (isAA && DBRefSource.UNIPROT
// output database accessions
if (dataRef != null)
{
- Enumeration en = dataRef.keys();
+ Enumeration<String> en = dataRef.keys();
while (en.hasMoreElements())
{
Object idd = en.nextElement();
- String type = (String) dataRef.remove(idd);
+ String type = dataRef.remove(idd);
out.append(new Format("%-" + (maxid - 2) + "s")
.form("#=GS " + idd.toString() + " "));
if (isAA && type.contains("UNIPROT")
}
}
- // output annotations
- while (i < s.length && s[i] != null)
+ // output description and annotations
+
+ while (i < slen && (seq = s[i]) != null)
{
- AlignmentAnnotation[] alAnot = s[i].getAnnotation();
+ if (seq.getDescription() != null)
+ {
+ // out.append("#=GR ");
+ out.append(new Format("%-" + maxid + "s").form("#=GS "
+ + printId(seq, jvSuffix) + " DE " + seq.getDescription()));
+ out.append(newline);
+ }
+
+ AlignmentAnnotation[] alAnot = seq.getAnnotation();
if (alAnot != null)
{
Annotation[] ann;
- for (int j = 0; j < alAnot.length; j++)
+ for (int j = 0, nj = alAnot.length; j < nj; j++)
{
String key = type2id(alAnot[j].label);
// out.append("#=GR ");
out.append(new Format("%-" + maxid + "s").form(
- "#=GR " + printId(s[i], jvSuffix) + " " + key + " "));
+ "#=GR " + printId(seq, jvSuffix) + " " + key + " "));
ann = alAnot[j].annotations;
- String seq = "";
- for (int k = 0; k < ann.length; k++)
+ String sseq = "";
+ for (int k = 0, nk = ann.length; k < nk; k++)
{
- seq += outputCharacter(key, k, isrna, ann, s[i]);
+ sseq += outputCharacter(key, k, isrna, ann, seq);
}
- out.append(seq);
+ out.append(sseq);
out.append(newline);
}
}
out.append(new Format("%-" + maxid + "s")
- .form(printId(s[i], jvSuffix) + " "));
- out.append(s[i].getSequenceAsString());
+ .form(printId(seq, jvSuffix) + " "));
+ out.append(seq.getSequenceAsString());
out.append(newline);
i++;
}
// alignment annotation
AlignmentAnnotation aa;
- if (al.getAlignmentAnnotation() != null)
+ AlignmentAnnotation[] an = al.getAlignmentAnnotation();
+ if (an != null)
{
- for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++)
+ for (int ia = 0, na = an.length; ia < na; ia++)
{
- aa = al.getAlignmentAnnotation()[ia];
+ aa = an[ia];
if (aa.autoCalculated || !aa.visible || aa.sequenceRef != null)
{
continue;
}
- String seq = "";
+ String sseq = "";
String label;
String key = "";
if (aa.label.equals("seq"))
}
else
{
- key = type2id(aa.label.toLowerCase());
+ key = type2id(aa.label.toLowerCase(Locale.ROOT));
if (key == null)
{
label = aa.label;
out.append(
new Format("%-" + maxid + "s").form("#=GC " + label + " "));
boolean isrna = aa.isValidStruc();
- for (int j = 0; j < aa.annotations.length; j++)
+ for (int j = 0, nj = aa.annotations.length; j < nj; j++)
{
- seq += outputCharacter(key, j, isrna, aa.annotations, null);
+ sseq += outputCharacter(key, j, isrna, aa.annotations, null);
}
- out.append(seq);
+ out.append(sseq);
out.append(newline);
}
}
{
return (String) typeIds.get(id);
}
- System.err.println(
+ jalview.bin.Console.errPrintln(
"Warning : Unknown Stockholm annotation type code " + id);
return id;
}
{
return key;
}
- System.err.println(
+ jalview.bin.Console.errPrintln(
"Warning : Unknown Stockholm annotation type: " + type);
return key;
}