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.io.parsers;
29 import java.io.BufferedReader;
30 import java.io.ByteArrayInputStream;
32 import java.io.FileInputStream;
33 import java.io.IOException;
34 import java.io.InputStream;
35 import java.io.InputStreamReader;
36 import java.util.ArrayList;
37 import java.util.List;
38 import java.util.regex.Matcher;
39 import java.util.regex.Pattern;
41 import org.forester.msa.BasicMsa;
42 import org.forester.msa.Msa;
43 import org.forester.msa.MsaFormatException;
44 import org.forester.sequence.BasicSequence;
45 import org.forester.sequence.Sequence;
47 public class FastaParser {
49 private static final Pattern NAME_REGEX = Pattern.compile( "^\\s*>\\s*(.+)" );
50 private static final Pattern SEQ_REGEX = Pattern.compile( "^\\s*(.+)" );
51 private static final Pattern ANYTHING_REGEX = Pattern.compile( "[\\d\\s]+" );
52 //>gi|71834668|ref|NP_001025424.1| Bcl2 [Danio rerio]
53 public static final Pattern FASTA_DESC_LINE = Pattern
54 .compile( ">?\\s*([^|]+)\\|([^|]+)\\S*\\s+(.+)\\s+\\[(.+)\\]" );
56 public static void main( final String[] args ) {
57 final String a = ">gi|71834668|ref|NP_001025424.1| Bcl2 [Danio rerio]";
58 final Matcher name_m = FASTA_DESC_LINE.matcher( a );
59 if ( name_m.lookingAt() ) {
61 System.out.println( name_m.group( 1 ) );
62 System.out.println( name_m.group( 2 ) );
63 System.out.println( name_m.group( 3 ) );
64 System.out.println( name_m.group( 4 ) );
67 System.out.println( "Does not match." );
71 static public boolean isLikelyFasta( final File f ) throws IOException {
72 return isLikelyFasta( new FileInputStream( f ) );
75 static public boolean isLikelyFasta( final InputStream is ) throws IOException {
76 final BufferedReader reader = new BufferedReader( new InputStreamReader( is, "UTF-8" ) );
78 while ( ( line = reader.readLine() ) != null ) {
79 final boolean is_name_line = NAME_REGEX.matcher( line ).lookingAt();
80 if ( canIgnore( line, true, false ) ) {
83 else if ( is_name_line ) {
87 else if ( SEQ_REGEX.matcher( line ).lookingAt() ) {
96 static public Msa parseMsa( final File f ) throws IOException {
97 return parseMsa( new FileInputStream( f ) );
100 static public Msa parseMsa( final InputStream is ) throws IOException {
101 return BasicMsa.createInstance( parse( is ) );
104 static public Msa parseMsa( final String s ) throws IOException {
105 return parseMsa( s.getBytes() );
108 static public Msa parseMsa( final byte[] bytes ) throws IOException {
109 return parseMsa( new ByteArrayInputStream( bytes ) );
112 static public List<Sequence> parse( final File f ) throws IOException {
113 return parse( new FileInputStream( f ) );
116 static public List<Sequence> parse( final InputStream is ) throws IOException {
117 final BufferedReader reader = new BufferedReader( new InputStreamReader( is, "UTF-8" ) );
119 int line_counter = 0;
120 boolean saw_first_seq = false;
121 StringBuilder current_seq = null;
122 StringBuilder name = null;
123 final List<StringBuilder[]> temp_msa = new ArrayList<StringBuilder[]>();
124 while ( ( line = reader.readLine() ) != null ) {
126 final Matcher name_m = NAME_REGEX.matcher( line );
127 final boolean is_name_line = name_m.lookingAt();
128 if ( canIgnore( line, saw_first_seq, is_name_line ) ) {
131 final Matcher seq_m = SEQ_REGEX.matcher( line );
132 if ( is_name_line ) {
133 saw_first_seq = true;
134 addSeq( name, current_seq, temp_msa );
135 name = new StringBuilder( name_m.group( 1 ).trim() );
136 current_seq = new StringBuilder();
138 else if ( seq_m.lookingAt() ) {
139 if ( name.length() < 1 ) {
141 throw new MsaFormatException( "illegally formatted fasta msa (line: " + line_counter + "):\n\""
142 + trim( line ) + "\"" );
144 current_seq.append( seq_m.group( 1 ).replaceAll( "\\s+", "" ) );
148 throw new MsaFormatException( "illegally formatted fasta msa (line: " + line_counter + "):\n\""
149 + trim( line ) + "\"" );
152 addSeq( name, current_seq, temp_msa );
154 final List<Sequence> seqs = new ArrayList<Sequence>();
155 for( int i = 0; i < temp_msa.size(); ++i ) {
156 seqs.add( BasicSequence.createAaSequence( temp_msa.get( i )[ 0 ].toString(),
157 temp_msa.get( i )[ 1 ].toString() ) );
162 static private boolean canIgnore( final String line, final boolean saw_first_seq, final boolean is_name_line ) {
163 if ( ( line.length() < 1 ) || ANYTHING_REGEX.matcher( line ).matches() ) {
166 if ( !saw_first_seq && !is_name_line ) {
172 private static void addSeq( final StringBuilder name, final StringBuilder seq, final List<StringBuilder[]> temp_msa ) {
173 if ( ( name != null ) && ( seq != null ) && ( name.length() > 0 ) && ( seq.length() > 0 ) ) {
174 final StringBuilder[] ary = new StringBuilder[ 2 ];
181 private static String trim( final String line ) {
182 if ( line.length() > 100 ) {
183 return line.substring( 0, 100 ) + " ...";