3 // forester -- software libraries and applications
4 // for genomics and evolutionary biology research.
6 // Copyright (C) 2010 Christian M Zmasek
7 // Copyright (C) 2010 Sanford-Burnham Medical Research Institute
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.sequence;
29 import org.forester.util.ForesterUtil;
31 public class BasicSequence implements Sequence {
33 private final char[] _mol_sequence;
34 private String _identifier;
35 private final TYPE _type;
37 private BasicSequence( final String identifier, final String mol_sequence, final TYPE type ) {
38 if ( ForesterUtil.isEmpty( identifier ) ) {
39 throw new IllegalArgumentException( "identifier of sequence cannot be empty" );
41 if ( ForesterUtil.isEmpty( mol_sequence ) ) {
42 throw new IllegalArgumentException( "molecular sequence cannot be empty" );
44 _mol_sequence = mol_sequence.toCharArray();
45 _identifier = identifier;
49 // Only use if you know what you are doing!
50 public BasicSequence( final String identifier, final char[] mol_sequence, final TYPE type ) {
51 if ( ForesterUtil.isEmpty( identifier ) ) {
52 throw new IllegalArgumentException( "identifier of sequence cannot be empty" );
54 if ( ( mol_sequence == null ) || ( mol_sequence.length < 1 ) ) {
55 throw new IllegalArgumentException( "molecular sequence cannot be empty" );
57 _mol_sequence = mol_sequence;
58 _identifier = identifier;
62 public void setIdentifier( final String id ) {
67 public String getIdentifier() {
72 public int getLength() {
73 return _mol_sequence.length;
77 public char[] getMolecularSequence() {
82 public char getResidueAt( final int position ) {
83 return _mol_sequence[ position ];
87 public TYPE getType() {
92 public int getNumberOfGapResidues() {
94 for( final char element : _mol_sequence ) {
95 if ( element == GAP ) {
103 public boolean equals( final Object obj ) {
107 if ( obj.getClass() != getClass() ) {
110 final Sequence other = ( Sequence ) obj;
111 if ( getMolecularSequenceAsString().equals( other.getMolecularSequenceAsString() ) ) {
118 public int hashCode() {
119 return getMolecularSequenceAsString().hashCode();
123 public String toString() {
124 final StringBuffer sb = new StringBuffer();
125 sb.append( _identifier.toString() );
127 sb.append( getMolecularSequenceAsString() );
128 return sb.toString();
131 public static Sequence copySequence( final Sequence seq ) {
132 final char[] s = new char[ seq.getMolecularSequence().length ];
133 for( int i = 0; i < seq.getMolecularSequence().length; i++ ) {
134 s[ i ] = seq.getMolecularSequence()[ i ];
136 return new BasicSequence( new String( seq.getIdentifier() ), s, seq.getType() );
139 public static Sequence createAaSequence( final String identifier, final String mol_sequence ) {
140 return new BasicSequence( identifier, mol_sequence.toUpperCase().replaceAll( "\\.", GAP_STR )
141 .replaceAll( AA_REGEXP, Character.toString( UNSPECIFIED_AA ) ), TYPE.AA );
144 public static Sequence createDnaSequence( final String identifier, final String mol_sequence ) {
145 return new BasicSequence( identifier, mol_sequence.toUpperCase().replaceAll( "\\.", GAP_STR )
146 .replaceAll( DNA_REGEXP, Character.toString( UNSPECIFIED_NUC ) ), TYPE.DNA );
149 public static Sequence createRnaSequence( final String identifier, final String mol_sequence ) {
150 return new BasicSequence( identifier, mol_sequence.toUpperCase().replaceAll( "\\.", GAP_STR )
151 .replaceAll( RNA_REGEXP, Character.toString( UNSPECIFIED_NUC ) ), TYPE.RNA );
155 public String getMolecularSequenceAsString() {
156 return new String( getMolecularSequence() );