Newer
Older
/* GFFStreamFeature.java
*
* created: Tue Sep 14 1999
*
* This file is part of Artemis
*
* Copyright (C) 1999,2000,2001 Genome Research Limited
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* $Header: //tmp/pathsoft/artemis/uk/ac/sanger/artemis/io/GFFStreamFeature.java,v 1.42 2006-08-04 11:00:30 tjc Exp $
*/
package uk.ac.sanger.artemis.io;
import uk.ac.sanger.artemis.util.*;
import java.io.*;
import java.util.Hashtable;
import java.util.StringTokenizer;
import java.sql.Timestamp;
import java.text.SimpleDateFormat;
/**
* A StreamFeature that thinks it is a GFF feature.
*
* @author Kim Rutherford
* @version $Id: GFFStreamFeature.java,v 1.42 2006-08-04 11:00:30 tjc Exp $
public class GFFStreamFeature extends SimpleDocumentFeature
implements DocumentFeature, StreamFeature, ComparableFeature
{
/**
* This is the line of GFF input that was read to get this
* GFFStreamFeature. A GFFStreamFeature that was created from multiple GFF
* lines will have a gff_lines variable that contains multiple line.
**/
StringVector gff_lines = null;
/** store for spliced features containing id and range of each segment */
private Hashtable id_range_store;
private Timestamp timelastmodified;
/** combined rank store for exons */
private Hashtable feature_relationship_rank_store;
/**
* Create a new GFFStreamFeature object. The feature should be added
* @param key The new feature key
* @param location The Location object for the new feature
* @param qualifiers The qualifiers for the new feature
**/
public GFFStreamFeature(final Key key, final Location location,
final QualifierVector qualifiers)
{
super(null);
try
{
setKey(key);
setLocation(location);
setQualifiers(qualifiers);
if(getQualifierByName("score") == null)
setQualifier(new Qualifier("score", "."));
if(getQualifierByName("gff_source") == null)
setQualifier(new Qualifier("gff_source", "artemis"));
if(getQualifierByName("gff_seqname") == null)
setQualifier(new Qualifier("gff_seqname", "."));
if(getQualifierByName("ID") == null)
setQualifier(new Qualifier("ID", "to_be_set"));
}
catch(EntryInformationException e)
{
// this should never happen because the feature will not be in an Entry
throw new Error("internal error - unexpected exception: " + e);
}
catch(ReadOnlyException e)
{
// this should never happen because the feature will not be in an Entry
throw new Error("internal error - unexpected exception: " + e);
}
catch(OutOfRangeException e)
{
// this should never happen because the feature will not be in an Entry
throw new Error("internal error - unexpected exception: " + e);
}
}
/**
* Create a new GFFStreamFeature with the same key, location and
* qualifiers as the given feature. The feature should be added to an
public GFFStreamFeature(final Feature feature)
{
this(feature.getKey(), feature.getLocation(), feature.getQualifiers());
// if(feature instanceof GFFStreamFeature)
// {
// this.id_range_store = ((GFFStreamFeature)feature).id_range_store;
// }
}
/**
* Create a new GFFStreamFeature from the given line. The String should be
* in gene finder format.
**/
throws ReadFormatException
{
super(null);
final StringVector line_bits = StringVector.getStrings(line, "\t", true);
if(line_bits.size() < 8)
throw new ReadFormatException("invalid GFF line: 8 fields needed " +
"(got " + line_bits.size () +
" fields) from: " + line);
final String start_base_string = ((String)line_bits.elementAt(3)).trim();
final String end_base_string = ((String)line_bits.elementAt(4)).trim();
try
{
start_base = Integer.parseInt(start_base_string);
throw new ReadFormatException("Could not understand the start or end base " +
"of a GFF feature: " + start_base_string +
" " + end_base_string);
//final String note_string = "this feature is unstranded";
//setQualifier(new Qualifier("note", note_string));
final Hashtable attributes = parseAttributes(rest_of_line);
for(final java.util.Enumeration attribute_enum = attributes.keys();
attribute_enum.hasMoreElements();)
{
String name = (String)attribute_enum.nextElement();
final StringVector values = (StringVector)attributes.get(name);
if(values.size() == 0)
setQualifier(new Qualifier(name));
else
setQualifier(new Qualifier(name, values));
new Qualifier("gff_seqname", decode((String)line_bits.elementAt(0)));
else if(frame.equals("1"))
frame = "2";
else if(frame.equals("2"))
frame = "3";
else
frame = ".";
if(start_base > end_base)
throw new ReadFormatException("start position is greater than end " +
"position: " + start_base + " > " +
if(start_base < 0)
throw new ReadFormatException("start position must be positive: " +
start_base);
final Range location_range = new Range(start_base, end_base);
final RangeVector location_ranges = new RangeVector(location_range);
setLocation(new Location(location_ranges, complement_flag));
}
catch(ReadOnlyException e)
{
throw new Error("internal error - unexpected exception: " + e);
}
catch(EntryInformationException e)
{
throw new Error("internal error - unexpected exception: " + e);
}
catch(OutOfRangeException e)
{
throw new Error("internal error - unexpected exception: " + e);
this.gff_lines = new StringVector(line);
}
/**
*
* Store for spliced regions of segments ID's and ranges.
*
*/
public void setSegmentRangeStore(Hashtable id_range_store)
{
this.id_range_store = id_range_store;
}
public Hashtable getSegmentRangeStore()
{
return id_range_store;
}
/**
* Store for ID's and CHADO feature_relationship.rank
* @param feature_relationship_rank_store
public void setFeature_relationship_rank_store(
Hashtable feature_relationship_rank_store)
{
this.feature_relationship_rank_store = feature_relationship_rank_store;
}
/**
* Store for ID's and CHADO feature_relationship.rank
* @return
*/
public Hashtable getFeature_relationship_rank_store()
{
return feature_relationship_rank_store;
}
/**
* Get the chado uniquename
* @param r
* @return
*/
public String getSegmentID(Range r)
{
if(id_range_store != null)
{
//Iterator it = id_range_store.values().iterator();
String key = (String)enum_ranges.nextElement();
Range range = (Range)id_range_store.get(key);
if(range.getStart() == r.getStart() ||
range.getEnd() == r.getEnd())
else if (getQualifierByName("ID") != null)
{
return (String)getQualifierByName("ID").getValues().get(0);
}
/**
* Get the feature ID based on the segments chado
* uniquename's.
* @param rv
* @return
*/
public String getSegmentID(RangeVector rv)
{
String id = "";
if(id_range_store != null)
{
String id_new;
Range range;
for(int i=0; i<rv.size(); i++)
{
range = (Range)rv.get(i);
id_new = getSegmentID(range);
String prefix[] = getPrefix(id_new, ':');
if(prefix[0] != null)
{
index = id.indexOf(prefix[0]);
if(id.equals("") || index < 0)
{
if(!id.equals(""))
id = id +",";
id = id+prefix[0] + "{" + prefix[1] + "}";
continue;
}
index = id.indexOf('}', index);
id = id.substring(0,index) + "," +
prefix[1] + id.substring(index);
}
else if(id_new != null)
{
if(!id.equals(""))
id = id +",";
id = id+id_new;
}
}
}
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
/**
* Get the ID prefix, e.g. for SPAC1556.06.1:exon:2
* returns SPAC1556.06.1:exon as the prefix and 2 as the
* index.
* @param id
* @return
*/
public String[] getPrefix(final String id,
final char separator)
{
String prefix[] = new String[2];
int index = id.lastIndexOf(separator);
if(index > -1)
{
prefix[0] = id.substring(0,index);
prefix[1] = id.substring(index+1);
}
return prefix;
}
/**
* Used to automatically generate
* @param prefix
* @return
*/
public int getAutoNumber(final String prefix,
final char separator)
{
int auto = 1;
String val = prefix + separator + auto;
while(id_range_store.containsKey(val))
{
auto++;
val = prefix + separator + auto;
}
return auto;
}
/**
*
* For gff-version 3:
* http://song.sourceforge.net/gff3-jan04.shtml
*
* Remove URL escaping rule (e.g. space="%20" or "+")
*
*/
final String map[][] = {
{ " ", "%20" }, // white space
{ ",", "%2C" }, // comma
{ ";", "%3B" }, // semi-colon
{ "=", "%3D" }, // equals
{ "\t", "%09" }, // tab
{ " ", "+" }, // white space
{ "(", "%28" }, // left bracket
{ ")", "%29" } // right bracket )
};
for(int i=0; i<map.length; i++)
{
enc = map[i][1];
dec = map[i][0];
while( (ind = s.indexOf(enc)) > -1)
s = s.substring(0,ind) + dec + s.substring(ind+enc.length());
}
/**
*
* For gff-version 3:
* http://song.sourceforge.net/gff3-jan04.shtml
*
* Add URL escaping rule (e.g. space="%20" or "+")
*
*/
final String map[][] = {
// { " ", "%20" }, // white space
{ ",", "%2C" }, // comma
{ ";", "%3B" }, // semi-colon
{ "=", "%3D" }, // equals
{ "\t", "%09" }, // tab
{ " ", "+" }, // white space
{ "(", "%28" }, // left bracket
{ ")", "%29" } // right bracket )
};
for(int i=0; i<map.length; i++)
{
enc = map[i][1];
dec = map[i][0];
while( (ind = s.indexOf(dec)) > -1 )
s = s.substring(0,ind) + enc + s.substring(ind+1);
}
/**
* Return the reference of a new copy of this Feature.
**/
public Feature copy()
{
final Feature return_value = new GFFStreamFeature(this);
return return_value;
}
/**
* Read and return a GFFStreamFeature from a stream. A feature must be the
* next thing in the stream.
* @param stream the Feature is read from this stream
* @exception IOException thrown if there is a problem reading the Feature -
* most likely ReadFormatException.
* @exception InvalidRelationException Thrown if this Feature cannot contain
* the given Qualifier.
* @return null if in_stream is at the end of file when the method is
* called
*/
protected static GFFStreamFeature readFromStream(LinePushBackReader stream)
throws IOException, InvalidRelationException
{
String line = stream.readLine();
if(line == null)
try
{
final GFFStreamFeature new_feature = new GFFStreamFeature(line);
}
catch(ReadFormatException exception)
{
final String new_error_string = exception.getMessage();
throw new ReadFormatException(new_error_string,
stream.getLineNumber());
}
}
/**
* Read the details of a feature from an EMBL stream into the current
* object.
* @param entry_information The EntryInformation object of the Entry that
* will contain the Feature.
* @param in_stream the Feature is read from this stream
* @exception IOException thrown if there is a problem reading the Feature -
* most likely ReadFormatException if the stream does not contain GFF
* feature.
**/
public void setFromStream(final EntryInformation entry_information,
final LinePushBackReader in_stream)
throws IOException, InvalidRelationException, ReadOnlyException
{
throw new ReadOnlyException();
/**
* Write this Feature to the given stream.
* @param writer The stream to write to.
* @exception IOException thrown if there is an io problem while writing
* the Feature.
**/
public void writeToStream(final Writer writer)
throws IOException
{
final RangeVector ranges = getLocation().getRanges();
final int ranges_size = ranges.size();
// final Hashtable contig_ranges = SimpleDocumentEntry.getContigRanges();
Qualifier seqname = getQualifierByName("gff_seqname");
Qualifier source = getQualifierByName("gff_source");
Qualifier score = getQualifierByName("score");
Qualifier group = getQualifierByName("group");
// String source_str = null;
// if(getQualifierByName("Dbxref") != null)
// source_str = getDbxrefGFFSource(getQualifierByName("Dbxref"));
int start = this_range.getStart();
int end = this_range.getEnd();
if(seqname != null && contig_ranges != null &&
contig_ranges.containsKey(seqname.getValues().elementAt(0)))
{
Range offset_range = (Range)contig_ranges.get(seqname.getValues().elementAt(0));
start = start-offset_range.getStart()+1;
end = end-offset_range.getStart()+1;
}
if(group == null || group.getValues() == null ||
group.getValues().elementAt(0).equals(""))
{
final Qualifier gene = getQualifierByName("gene");
if(gene == null)
group = new Qualifier("group", "");
else
group = gene;
}
if(frame.equals ("1"))
frame = "0";
else if(frame.equals("2"))
frame = "1";
else if(frame.equals("3"))
frame = "2";
else
frame = ".";
//if(source_str == null)
String source_str = (String)source.getValues().elementAt(0);
score.getValues() .elementAt(0)+ "\t" +
(getLocation().isComplement() ? "-\t" : "+\t") +
frame + "\t" +
attribute_string + "\n");
}
// for(int i = 0 ; i < gff_lines.size() ; ++i)
// writer.write(gff_lines.elementAt(i) + "\n");
/**
* Get the GFF_source value of a Dbxref qualifier.
* @param qualifier
* @return the gff_source value or NULL
*/
private String getDbxrefGFFSource(final Qualifier qualifier)
{
StringVector qualifier_strings =
StreamQualifier.toStringVector(null, qualifier);
for(int i=0; i<qualifier_strings.size(); i++)
{
String qualifier_string = (String)qualifier_strings.elementAt(i);
if(qualifier_string.indexOf("GFF_source:") >-1)
{
int index = qualifier_string.indexOf(":")+1;
int len = qualifier_string.length();
if(qualifier_string.endsWith("\""))
len--;
return qualifier_string.substring(index, len);
}
}
return null;
}
/**
* Return a String containing the qualifiers of this feature in a form
* suitable for using as the last field of a GFF line. The codon_start
* attribute is not included since GFF has a frame field. gff_seqname,
* gff_source and score aren't included since they have corresponding
* fields.
**/
private String unParseAttributes()
{
final StringBuffer buffer = new StringBuffer();
final QualifierVector qualifiers = getQualifiers();
final String names[] = { "ID", "Name", "Alias", "Parent",
"Target", "Gap", "Note",
"Dbxref", "Ontology_term" };
int count = 0;
final String this_qualifier_str = getQualifierString(this_qualifier);
if(this_qualifier_str == null)
continue;
if(count != 0)
buffer.append(";");
buffer.append(this_qualifier_str);
count++;
}
if(this_qualifier.getName().equals(names[j]))
String this_qualifier_str = getQualifierString(this_qualifier);
if(this_qualifier_str == null)
continue;
buffer.append(this_qualifier_str);
}
return buffer.toString();
}
/**
* Used to write out the GFF attributes.
* @param q the qualifier to represent as a <code>String</code>
* @return the <code>String</code> representation
*/
private String getQualifierString(Qualifier q)
{
StringBuffer buffer = new StringBuffer();
final String name = q.getName();
if(name.equals("codon_start") || name.equals("gff_source") ||
name.equals("gff_seqname") || name.equals("score"))
return null;
final StringVector values = q.getValues();
buffer.append(encode(name));
for(int value_index = 0; value_index < values.size();
++value_index)
final String this_value = encode((String)values.elementAt(value_index));
if(value_index>0)
buffer.append("%2C");
try
{
buffer.append(Integer.valueOf(this_value));
}
catch(NumberFormatException _)
buffer.append(Double.valueOf(this_value));
}
catch (NumberFormatException __)
}
/**
* Parse the given String as ACeDB format attributes.
* Adapted from code by Matthew Pocock for the BioJava project.
* @return Return a Hashtable. Each key is an attribute name and each value
* of the Hashtable is a StringVector containing the attribute values.
* If the attribute has no value then the Hashtable value will be a zero
* length vector.
**/
private Hashtable parseAttributes(final String att_val_list)
{
Hashtable attributes = new Hashtable();
// StringTokenizer tokeniser = new StringTokenizer(att_val_list, ";", false);
// while(tokeniser.hasMoreTokens())
// {
// final String this_token = tokeniser.nextToken().trim();
int ind_start = 0;
int ind_end;
while( (ind_end = att_val_list.indexOf(";",ind_start)) > -1 ||
ind_start < att_val_list.length() )
final String this_token = decode(att_val_list.substring(ind_start, ind_end).trim());
if(this_token.startsWith("feature_relationship_rank="))
{
setFeature_relationship_rank(
Integer.parseInt(this_token.substring(26)) );
continue;
}
int index_of_first_space = this_token.indexOf(" ");
StringVector att_values = new StringVector();
if( this_token.indexOf("=") > -1 &&
(this_token.indexOf("=") < index_of_first_space ||
index_of_first_space == -1) )
{
index_of_first_space = this_token.indexOf("=");
att_name = this_token.substring(0, index_of_first_space);
att_values.add(this_token.substring(index_of_first_space+1).trim());
}
else if(index_of_first_space == -1)
else
{
att_name = this_token.substring(0, index_of_first_space);
this_token.substring(index_of_first_space+1).trim();
while(rest_of_token.length() > 0)
{
if(rest_of_token.startsWith("\""))
{
quote_index = rest_of_token.indexOf("\"", quote_index);
} while(quote_index > -1 &&
rest_of_token.charAt(quote_index - 1) == '\\');
final Hashtable panic_attributes = new Hashtable();
final StringVector notes = new StringVector();
notes.add(att_val_list);
panic_attributes.put("note", notes);
final String next_bit = rest_of_token.substring(1, quote_index);
att_values.add(next_bit);
rest_of_token = rest_of_token.substring(quote_index + 1).trim();
}
else
{
final int index_of_next_space = rest_of_token.indexOf(" ");
if(index_of_next_space == -1)
{
att_values.add(rest_of_token);
rest_of_token.substring(0, index_of_next_space);
rest_of_token.substring(index_of_next_space).trim();
if(!rest_of_token.equals(""))
att_values.add(rest_of_token);
if(att_name.equals("Dbxref") || att_name.equals("Alias")) // convert to multi-line
{
StringTokenizer stok =
new StringTokenizer((String)att_values.get(0), ",");
StringVector str_values = new StringVector();
while(stok.hasMoreTokens())
str_values.add(stok.nextElement());
att_values = str_values;
}
if(att_name.equals("timelastmodified"))
{
this.timelastmodified =
new Timestamp( Long.parseLong((String)att_values.get(0)) );
SimpleDateFormat date_format =
new SimpleDateFormat("dd.MM.yyyy hh:mm:ss z");
att_values.set(0,date_format.format(timelastmodified));
}
if(attributes.get(att_name) != null)
((StringVector)attributes.get(att_name)).add(att_values);
else
attributes.put(att_name, att_values);
/**
* Get the feature time last modified timestamp.
* @return
*/
public Timestamp getLastModified()
{
return timelastmodified;
}
/**
* Set the feature time last modified timestamp.
* @param timelastmodified
*/
public void setLastModified(final Timestamp timelastmodified)
{
this.timelastmodified = timelastmodified;
// now update the qualifier value itself
QualifierVector qualifiers = getQualifiers();
Qualifier qualifier = qualifiers.getQualifierByName("timelastmodified");
SimpleDateFormat date_format =
new SimpleDateFormat("dd.MM.yyyy hh:mm:ss z");
if(qualifier != null)
qualifier.removeValue((String)qualifier.getValues().get(0));
else
{
try
{
qualifier = new Qualifier("timelastmodified",
date_format.format(timelastmodified));
setQualifier(qualifier);
return;
}
catch(EntryInformationException eie)
{}
catch(ReadOnlyException roe)
{}
}
qualifier.addValue(date_format.format(timelastmodified));
}
public ChadoCanonicalGene getChadoGene()
{
return chadoGene;
}
public void setChadoGene(ChadoCanonicalGene chadoGene)
{
this.chadoGene = chadoGene;
}
public boolean isVisible()
{
return visible;
}
public void setVisible(boolean visible)
{
this.visible = visible;
}
public int getFeature_relationship_rank()
{