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 MolecularSequence {
33 private final char[] _mol_sequence;
34 private String _identifier;
35 private final TYPE _type;
38 * Only use if you know what you are doing!
41 public BasicSequence( final String identifier, final String mol_sequence, final TYPE type ) {
42 check( identifier, mol_sequence );
43 _mol_sequence = mol_sequence.toCharArray();
44 _identifier = identifier;
48 private static final void check( final String identifier, final String mol_sequence ) {
49 if ( ForesterUtil.isEmpty( identifier ) ) {
50 throw new IllegalArgumentException( "identifier of sequence cannot be empty" );
52 if ( ForesterUtil.isEmpty( mol_sequence ) ) {
53 throw new IllegalArgumentException( "molecular sequence cannot be empty" );
58 * Only use if you know what you are doing!
61 public BasicSequence( final String identifier, final char[] mol_sequence, final TYPE type ) {
62 if ( ForesterUtil.isEmpty( identifier ) ) {
63 throw new IllegalArgumentException( "identifier of sequence cannot be empty" );
65 if ( ( mol_sequence == null ) || ( mol_sequence.length < 1 ) ) {
66 throw new IllegalArgumentException( "molecular sequence cannot be empty" );
68 _mol_sequence = mol_sequence;
69 _identifier = identifier;
73 public void setIdentifier( final String id ) {
78 public String getIdentifier() {
83 public int getLength() {
84 return _mol_sequence.length;
88 public char[] getMolecularSequence() {
93 public char getResidueAt( final int position ) {
94 return _mol_sequence[ position ];
98 public TYPE getType() {
103 public int getNumberOfGapResidues() {
105 for( final char element : _mol_sequence ) {
106 if ( element == GAP ) {
114 public boolean equals( final Object obj ) {
118 if ( obj.getClass() != getClass() ) {
121 final MolecularSequence other = ( MolecularSequence ) obj;
122 if ( getMolecularSequenceAsString().equals( other.getMolecularSequenceAsString() ) ) {
129 public int hashCode() {
130 return getMolecularSequenceAsString().hashCode();
134 public String toString() {
135 final StringBuffer sb = new StringBuffer();
136 sb.append( _identifier.toString() );
138 sb.append( getMolecularSequenceAsString() );
139 return sb.toString();
142 public static MolecularSequence copySequence( final MolecularSequence seq ) {
143 final char[] s = new char[ seq.getMolecularSequence().length ];
144 for( int i = 0; i < seq.getMolecularSequence().length; i++ ) {
145 s[ i ] = seq.getMolecularSequence()[ i ];
147 return new BasicSequence( new String( seq.getIdentifier() ), s, seq.getType() );
150 public static MolecularSequence createAaSequence( final String identifier, final String mol_sequence ) {
151 check( identifier, mol_sequence );
152 return new BasicSequence( identifier, mol_sequence.toUpperCase().replaceAll( "\\.", GAP_STR )
153 .replaceAll( AA_REGEXP, Character.toString( UNSPECIFIED_AA ) ), TYPE.AA );
156 public static MolecularSequence createDnaSequence( final String identifier, final String mol_sequence ) {
157 check( identifier, mol_sequence );
158 return new BasicSequence( identifier, mol_sequence.toUpperCase().replaceAll( "\\.", GAP_STR )
159 .replaceAll( DNA_REGEXP, Character.toString( UNSPECIFIED_NUC ) ), TYPE.DNA );
162 public static MolecularSequence createRnaSequence( final String identifier, final String mol_sequence ) {
163 check( identifier, mol_sequence );
164 return new BasicSequence( identifier, mol_sequence.toUpperCase().replaceAll( "\\.", GAP_STR )
165 .replaceAll( RNA_REGEXP, Character.toString( UNSPECIFIED_NUC ) ), TYPE.RNA );
169 public String getMolecularSequenceAsString() {
170 return new String( getMolecularSequence() );
174 public boolean isGapAt( final int position ) {
175 return getResidueAt( position ) == GAP;