2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2009 Christian M. Zmasek
6 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // Contact: phylosoft @ gmail . com
24 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
26 package org.forester.util;
28 import java.awt.Color;
29 import java.io.BufferedReader;
30 import java.io.BufferedWriter;
32 import java.io.FileInputStream;
33 import java.io.FileNotFoundException;
34 import java.io.FileOutputStream;
35 import java.io.FileReader;
36 import java.io.FileWriter;
37 import java.io.FilenameFilter;
38 import java.io.IOException;
39 import java.io.InputStream;
40 import java.io.InputStreamReader;
41 import java.io.StringReader;
42 import java.io.Writer;
43 import java.math.BigDecimal;
45 import java.net.URLConnection;
46 import java.security.KeyManagementException;
47 import java.security.NoSuchAlgorithmException;
48 import java.text.DateFormat;
49 import java.text.DecimalFormat;
50 import java.text.DecimalFormatSymbols;
51 import java.text.NumberFormat;
52 import java.text.ParseException;
53 import java.text.SimpleDateFormat;
54 import java.util.ArrayList;
55 import java.util.Collection;
56 import java.util.Date;
57 import java.util.List;
59 import java.util.Map.Entry;
61 import java.util.SortedMap;
62 import java.util.SortedSet;
63 import java.util.TreeMap;
64 import java.util.TreeSet;
65 import java.util.regex.Matcher;
66 import java.util.regex.Pattern;
68 import org.forester.archaeopteryx.AptxConstants;
69 import org.forester.io.parsers.PhylogenyParser;
70 import org.forester.phylogeny.Phylogeny;
71 import org.forester.phylogeny.PhylogenyNode;
72 import org.forester.phylogeny.data.Distribution;
73 import org.forester.phylogeny.data.Sequence;
74 import org.forester.phylogeny.data.Taxonomy;
75 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
76 import org.forester.protein.BasicProtein;
77 import org.forester.protein.Domain;
78 import org.forester.protein.Protein;
79 import org.forester.sequence.MolecularSequence;
80 import org.forester.sequence.MolecularSequence.TYPE;
81 import org.forester.surfacing.SurfacingUtil;
83 public final class ForesterUtil {
85 public final static String FILE_SEPARATOR = System.getProperty( "file.separator" );
86 public static final NumberFormat FORMATTER_06;
87 public static final NumberFormat FORMATTER_3;
88 public static final NumberFormat FORMATTER_6;
89 public static final NumberFormat FORMATTER_9;
90 public final static String JAVA_VENDOR = System.getProperty( "java.vendor" );
91 public final static String JAVA_VERSION = System.getProperty( "java.version" );
92 public final static String LINE_SEPARATOR = System.getProperty( "line.separator" );
93 public static final String NCBI_GI = "http://www.ncbi.nlm.nih.gov/protein/gi:";
94 public static final String NCBI_NUCCORE = "http://www.ncbi.nlm.nih.gov/nuccore/";
95 public static final String NCBI_PROTEIN = "http://www.ncbi.nlm.nih.gov/protein/";
96 public static final BigDecimal NULL_BD = new BigDecimal( 0 );
97 public final static String OS_ARCH = System.getProperty( "os.arch" );
98 public final static String OS_NAME = System.getProperty( "os.name" );
99 public final static String OS_VERSION = System.getProperty( "os.version" );
100 public static final String PDB = "http://www.pdb.org/pdb/explore/explore.do?pdbId=";
101 public final static String UNIPROT_KB = "http://www.uniprot.org/uniprot/";
102 public final static double ZERO_DIFF = 1.0E-9;
103 private static final Pattern PARANTHESESABLE_NH_CHARS_PATTERN = Pattern.compile( "[(),;\\s:\\[\\]]" );
105 final DecimalFormatSymbols dfs = new DecimalFormatSymbols();
106 dfs.setDecimalSeparator( '.' );
107 // dfs.setGroupingSeparator( ( char ) 0 );
108 FORMATTER_9 = new DecimalFormat( "#.#########", dfs );
109 FORMATTER_6 = new DecimalFormat( "#.######", dfs );
110 FORMATTER_06 = new DecimalFormat( "0.######", dfs );
111 FORMATTER_3 = new DecimalFormat( "#.###", dfs );
114 final public static void appendSeparatorIfNotEmpty( final StringBuffer sb, final char separator ) {
115 if ( sb.length() > 0 ) {
116 sb.append( separator );
120 final public static String removeFileExtension( final String file_name ) {
121 if ( file_name.indexOf( "." ) > 0 ) {
122 return file_name.substring( 0, file_name.lastIndexOf( "." ) );
128 * This calculates a color. If value is equal to min the returned color is
129 * minColor, if value is equal to max the returned color is maxColor,
130 * otherwise a color 'proportional' to value is returned.
144 final public static Color calcColor( double value,
147 final Color minColor,
148 final Color maxColor ) {
155 final double x = ForesterUtil.calculateColorFactor( value, max, min );
156 final int red = ForesterUtil.calculateColorComponent( minColor.getRed(), maxColor.getRed(), x );
157 final int green = ForesterUtil.calculateColorComponent( minColor.getGreen(), maxColor.getGreen(), x );
158 final int blue = ForesterUtil.calculateColorComponent( minColor.getBlue(), maxColor.getBlue(), x );
159 return new Color( red, green, blue );
163 * This calculates a color. If value is equal to min the returned color is
164 * minColor, if value is equal to max the returned color is maxColor, if
165 * value is equal to mean the returned color is meanColor, otherwise a color
166 * 'proportional' to value is returned -- either between min-mean or
176 * the mean/median value
185 final public static Color calcColor( double value,
189 final Color minColor,
190 final Color maxColor,
191 final Color meanColor ) {
198 if ( value < mean ) {
199 final double x = ForesterUtil.calculateColorFactor( value, mean, min );
200 final int red = ForesterUtil.calculateColorComponent( minColor.getRed(), meanColor.getRed(), x );
201 final int green = ForesterUtil.calculateColorComponent( minColor.getGreen(), meanColor.getGreen(), x );
202 final int blue = ForesterUtil.calculateColorComponent( minColor.getBlue(), meanColor.getBlue(), x );
203 return new Color( red, green, blue );
205 else if ( value > mean ) {
206 final double x = ForesterUtil.calculateColorFactor( value, max, mean );
207 final int red = ForesterUtil.calculateColorComponent( meanColor.getRed(), maxColor.getRed(), x );
208 final int green = ForesterUtil.calculateColorComponent( meanColor.getGreen(), maxColor.getGreen(), x );
209 final int blue = ForesterUtil.calculateColorComponent( meanColor.getBlue(), maxColor.getBlue(), x );
210 return new Color( red, green, blue );
218 * Helper method for calcColor methods.
220 * @param smallercolor_component_x
221 * color component the smaller color
222 * @param largercolor_component_x
223 * color component the larger color
226 * @return an int representing a color component
228 final private static int calculateColorComponent( final double smallercolor_component_x,
229 final double largercolor_component_x,
231 return ( int ) ( smallercolor_component_x
232 + ( ( x * ( largercolor_component_x - smallercolor_component_x ) ) / 255.0 ) );
236 * Helper method for calcColor methods.
245 * @return a normalized value between larger and smaller
247 final private static double calculateColorFactor( final double value, final double larger, final double smaller ) {
248 return ( 255.0 * ( value - smaller ) ) / ( larger - smaller );
251 public static int calculateOverlap( final Domain domain, final List<Boolean> covered_positions ) {
252 int overlap_count = 0;
253 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
254 if ( ( i < covered_positions.size() ) && ( covered_positions.get( i ) == true ) ) {
258 return overlap_count;
261 final public static String collapseWhiteSpace( final String s ) {
262 return s.replaceAll( "[\\s]+", " " );
265 final public static void collection2file( final File file, final Collection<?> data, final String separator )
267 final Writer writer = new BufferedWriter( new FileWriter( file ) );
268 collection2writer( writer, data, separator );
272 final public static void collection2writer( final Writer writer, final Collection<?> data, final String separator )
274 boolean first = true;
275 for( final Object object : data ) {
277 writer.write( separator );
282 writer.write( object.toString() );
286 final public static String colorToHex( final Color color ) {
287 final String rgb = Integer.toHexString( color.getRGB() );
288 return rgb.substring( 2, rgb.length() );
291 synchronized public static void copyFile( final File in, final File out ) throws IOException {
292 final FileInputStream in_s = new FileInputStream( in );
293 final FileOutputStream out_s = new FileOutputStream( out );
295 final byte[] buf = new byte[ 1024 ];
297 while ( ( i = in_s.read( buf ) ) != -1 ) {
298 out_s.write( buf, 0, i );
301 catch ( final IOException e ) {
305 if ( in_s != null ) {
308 if ( out_s != null ) {
314 final public static int countChars( final String str, final char c ) {
316 for( int i = 0; i < str.length(); ++i ) {
317 if ( str.charAt( i ) == c ) {
324 final public static BufferedWriter createBufferedWriter( final File file ) throws IOException {
325 if ( file.exists() ) {
326 throw new IOException( "[" + file + "] already exists" );
328 return new BufferedWriter( new FileWriter( file ) );
331 final public static BufferedWriter createBufferedWriter( final String name ) throws IOException {
332 return new BufferedWriter( new FileWriter( createFileForWriting( name ) ) );
335 final public static EasyWriter createEasyWriter( final File file ) throws IOException {
336 return new EasyWriter( createBufferedWriter( file ) );
339 final public static BufferedWriter createEasyWriter( final String name ) throws IOException {
340 return createEasyWriter( createFileForWriting( name ) );
343 final public static File createFileForWriting( final String name ) throws IOException {
344 final File file = new File( name );
345 if ( file.exists() ) {
346 throw new IOException( "[" + name + "] already exists" );
351 final public static void ensurePresenceOfDate( final PhylogenyNode node ) {
352 if ( !node.getNodeData().isHasDate() ) {
353 node.getNodeData().setDate( new org.forester.phylogeny.data.Date() );
357 final public static void ensurePresenceOfDistribution( final PhylogenyNode node ) {
358 if ( !node.getNodeData().isHasDistribution() ) {
359 node.getNodeData().setDistribution( new Distribution( "" ) );
363 public static void ensurePresenceOfSequence( final PhylogenyNode node ) {
364 if ( !node.getNodeData().isHasSequence() ) {
365 node.getNodeData().setSequence( new Sequence() );
369 public static void ensurePresenceOfTaxonomy( final PhylogenyNode node ) {
370 if ( !node.getNodeData().isHasTaxonomy() ) {
371 node.getNodeData().setTaxonomy( new Taxonomy() );
375 public static void fatalError( final String message ) {
376 System.err.println();
377 System.err.println( "error: " + message );
378 System.err.println();
382 public static void fatalError( final String prg_name, final String message ) {
383 System.err.println();
384 System.err.println( "[" + prg_name + "] > " + message );
385 System.err.println();
389 public static void fatalErrorIfFileNotReadable( final File file ) {
390 final String error = isReadableFile( file );
391 if ( !isEmpty( error ) ) {
392 System.err.println();
393 System.err.println( "error: " + error );
394 System.err.println();
399 public static void fatalErrorIfFileNotReadable( final String prg_name, final File file ) {
400 final String error = isReadableFile( file );
401 if ( !isEmpty( error ) ) {
402 System.err.println();
403 System.err.println( "[" + prg_name + "] > " + error );
404 System.err.println();
409 public static String[][] file22dArray( final File file ) throws IOException {
410 final List<String> list = new ArrayList<String>();
411 final BufferedReader in = new BufferedReader( new FileReader( file ) );
413 while ( ( str = in.readLine() ) != null ) {
415 if ( ( str.length() > 0 ) && !str.startsWith( "#" ) ) {
420 final String[][] ary = new String[ list.size() ][ 2 ];
421 final Pattern pa = Pattern.compile( "(\\S+)\\s+(\\S+)" );
423 for( final String s : list ) {
424 final Matcher m = pa.matcher( s );
426 ary[ i ][ 0 ] = m.group( 1 );
427 ary[ i ][ 1 ] = m.group( 2 );
431 throw new IOException( "unexpcted format: " + s );
437 public static String[] file2array( final File file ) throws IOException {
438 final List<String> list = file2list( file );
439 final String[] ary = new String[ list.size() ];
441 for( final String s : list ) {
447 final public static List<String> file2list( final File file ) throws IOException {
448 final List<String> list = new ArrayList<String>();
449 final BufferedReader in = new BufferedReader( new FileReader( file ) );
451 while ( ( str = in.readLine() ) != null ) {
453 if ( ( str.length() > 0 ) && !str.startsWith( "#" ) ) {
454 for( final String s : splitString( str ) ) {
463 final public static SortedSet<String> file2set( final File file ) throws IOException {
464 final SortedSet<String> set = new TreeSet<String>();
465 final BufferedReader in = new BufferedReader( new FileReader( file ) );
467 while ( ( str = in.readLine() ) != null ) {
469 if ( ( str.length() > 0 ) && !str.startsWith( "#" ) ) {
470 for( final String s : splitString( str ) ) {
479 final public static String getCurrentDateTime() {
480 final DateFormat format = new SimpleDateFormat( "yyyy/MM/dd HH:mm:ss" );
481 return format.format( new Date() );
484 final public static String getFileSeparator() {
485 return ForesterUtil.FILE_SEPARATOR;
488 final public static String getFirstLine( final Object source ) throws FileNotFoundException, IOException {
489 BufferedReader reader = null;
490 if ( source instanceof File ) {
491 final File f = ( File ) source;
493 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
495 else if ( !f.isFile() ) {
496 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
498 else if ( !f.canRead() ) {
499 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
501 reader = new BufferedReader( new FileReader( f ) );
503 else if ( source instanceof InputStream ) {
504 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
506 else if ( source instanceof String ) {
507 reader = new BufferedReader( new StringReader( ( String ) source ) );
509 else if ( source instanceof StringBuffer ) {
510 reader = new BufferedReader( new StringReader( source.toString() ) );
512 else if ( source instanceof URL ) {
513 final URLConnection url_connection = ( ( URL ) source ).openConnection();
514 url_connection.setDefaultUseCaches( false );
515 reader = new BufferedReader( new InputStreamReader( url_connection.getInputStream() ) );
518 throw new IllegalArgumentException( "dont know how to read [" + source.getClass() + "]" );
521 while ( ( line = reader.readLine() ) != null ) {
523 if ( !ForesterUtil.isEmpty( line ) ) {
524 if ( reader != null ) {
530 if ( reader != null ) {
536 final public static String getForesterLibraryInformation() {
537 return "forester " + ForesterConstants.FORESTER_VERSION + " (" + ForesterConstants.FORESTER_DATE + ")";
540 final public static String getLineSeparator() {
541 return ForesterUtil.LINE_SEPARATOR;
544 final public static MolecularSequence.TYPE guessMolecularSequenceType( final String mol_seq ) {
545 if ( mol_seq.contains( "L" ) || mol_seq.contains( "I" ) || mol_seq.contains( "E" ) || mol_seq.contains( "H" )
546 || mol_seq.contains( "D" ) || mol_seq.contains( "Q" ) ) {
550 if ( mol_seq.contains( "T" ) ) {
553 else if ( mol_seq.contains( "U" ) ) {
560 final public static void increaseCountingMap( final Map<String, Integer> counting_map, final String item_name ) {
561 if ( !counting_map.containsKey( item_name ) ) {
562 counting_map.put( item_name, 1 );
565 counting_map.put( item_name, counting_map.get( item_name ) + 1 );
569 final public static boolean isEmpty( final List<?> l ) {
570 if ( ( l == null ) || l.isEmpty() ) {
573 for( final Object o : l ) {
581 final public static boolean isEmpty( final Set<?> s ) {
582 if ( ( s == null ) || s.isEmpty() ) {
585 for( final Object o : s ) {
593 final public static boolean isEmpty( final String s ) {
594 return ( ( s == null ) || ( s.length() < 1 ) );
598 * Returns true is Domain domain falls in an uninterrupted stretch of
602 * @param covered_positions
605 public static boolean isEngulfed( final Domain domain, final List<Boolean> covered_positions ) {
606 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
607 if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) {
614 final public static boolean isEqual( final double a, final double b ) {
615 return ( ( Math.abs( a - b ) ) < ZERO_DIFF );
618 final public static boolean isEven( final int n ) {
619 return ( n % 2 ) == 0;
623 * This determines whether String[] a and String[] b have at least one
624 * String in common (intersect). Returns false if at least one String[] is
628 * a String[] b a String[]
629 * @return true if both a and b or not empty or null and contain at least
630 * one element in common false otherwise
632 final public static boolean isIntersecting( final String[] a, final String[] b ) {
633 if ( ( a == null ) || ( b == null ) ) {
636 if ( ( a.length < 1 ) || ( b.length < 1 ) ) {
639 for( final String ai : a ) {
640 for( final String element : b ) {
641 if ( ( ai != null ) && ( element != null ) && ai.equals( element ) ) {
649 final public static double isLargerOrEqualToZero( final double d ) {
658 public final static boolean isMac() {
660 return OS_NAME.toLowerCase().startsWith( "mac" );
662 catch ( final Exception e ) {
663 ForesterUtil.printWarningMessage( AptxConstants.PRG_NAME, "minor error: " + e );
668 final public static boolean isNull( final BigDecimal s ) {
669 return ( ( s == null ) || ( s.compareTo( NULL_BD ) == 0 ) );
672 final public static String isReadableFile( final File f ) {
674 return "file [" + f + "] does not exist";
676 if ( f.isDirectory() ) {
677 return "[" + f + "] is a directory";
680 return "[" + f + "] is not a file";
682 if ( !f.canRead() ) {
683 return "file [" + f + "] is not readable";
685 if ( f.length() < 1 ) {
686 return "file [" + f + "] is empty";
691 final public static String isReadableFile( final String s ) {
692 return isReadableFile( new File( s ) );
695 public final static boolean isWindows() {
697 return OS_NAME.toLowerCase().indexOf( "win" ) > -1;
699 catch ( final Exception e ) {
700 ForesterUtil.printWarningMessage( AptxConstants.PRG_NAME, "minor error: " + e );
705 final public static String isWritableFile( final File f ) {
706 if ( f.isDirectory() ) {
707 return "[" + f + "] is a directory";
710 return "[" + f + "] already exists";
716 * Helper for method "stringToColor".
718 * (Last modified: 12/20/03)
720 final public static int limitRangeForColor( int i ) {
730 final public static SortedMap<Object, Integer> listToSortedCountsMap( final List<?> list ) {
731 final SortedMap<Object, Integer> map = new TreeMap<Object, Integer>();
732 for( final Object key : list ) {
733 if ( !map.containsKey( key ) ) {
737 map.put( key, map.get( key ) + 1 );
743 final public static void map2file( final File file,
744 final Map<?, ?> data,
745 final String entry_separator,
746 final String data_separator )
748 final Writer writer = new BufferedWriter( new FileWriter( file ) );
749 map2writer( writer, data, entry_separator, data_separator );
753 final public static void map2writer( final Writer writer,
754 final Map<?, ?> data,
755 final String entry_separator,
756 final String data_separator )
758 boolean first = true;
759 for( final Entry<?, ?> entry : data.entrySet() ) {
761 writer.write( data_separator );
766 writer.write( entry.getKey().toString() );
767 writer.write( entry_separator );
768 writer.write( entry.getValue().toString() );
772 final public static StringBuffer mapToStringBuffer( final Map<Object, Object> map,
773 final String key_value_separator ) {
774 final StringBuffer sb = new StringBuffer();
775 for( final Object key : map.keySet() ) {
776 sb.append( key.toString() );
777 sb.append( key_value_separator );
778 sb.append( map.get( key ).toString() );
779 sb.append( ForesterUtil.getLineSeparator() );
784 final public static String normalizeString( final String s,
786 final boolean left_pad,
787 final char pad_char ) {
788 if ( s.length() > length ) {
789 return s.substring( 0, length );
792 final StringBuffer pad = new StringBuffer( length - s.length() );
793 for( int i = 0; i < ( length - s.length() ); ++i ) {
794 pad.append( pad_char );
805 public final static Color obtainColorDependingOnTaxonomyGroup( final String tax_group ) {
806 if ( !ForesterUtil.isEmpty( tax_group ) ) {
807 if ( tax_group.equals( TaxonomyGroups.DEUTEROSTOMIA ) ) {
808 return TaxonomyColors.DEUTEROSTOMIA_COLOR;
810 else if ( tax_group.equals( TaxonomyGroups.PROTOSTOMIA ) ) {
811 return TaxonomyColors.PROTOSTOMIA_COLOR;
813 else if ( tax_group.equals( TaxonomyGroups.CNIDARIA ) ) {
814 return TaxonomyColors.CNIDARIA_COLOR;
816 else if ( tax_group.equals( TaxonomyGroups.PLACOZOA ) ) {
817 return TaxonomyColors.PLACOZOA_COLOR;
819 else if ( tax_group.equals( TaxonomyGroups.CTENOPHORA ) ) {
820 return TaxonomyColors.CTENOPHORA_COLOR;
822 else if ( tax_group.equals( TaxonomyGroups.PORIFERA ) ) {
823 return TaxonomyColors.PORIFERA_COLOR;
825 else if ( tax_group.equals( TaxonomyGroups.CHOANOFLAGELLIDA ) ) {
826 return TaxonomyColors.CHOANOFLAGELLIDA;
828 else if ( tax_group.equals( TaxonomyGroups.ICHTHYOPHONIDA_FILASTEREA ) ) {
829 return TaxonomyColors.ICHTHYOSPOREA_AND_FILASTEREA;
831 else if ( tax_group.equals( TaxonomyGroups.DIKARYA ) ) {
832 return TaxonomyColors.DIKARYA_COLOR;
834 else if ( tax_group.equalsIgnoreCase( TaxonomyGroups.FUNGI )
835 || tax_group.equalsIgnoreCase( TaxonomyGroups.OTHER_FUNGI ) ) {
836 return TaxonomyColors.OTHER_FUNGI_COLOR;
838 else if ( tax_group.equals( TaxonomyGroups.NUCLEARIIDAE_AND_FONTICULA_GROUP ) ) {
839 return TaxonomyColors.NUCLEARIIDAE_AND_FONTICULA_GROUP_COLOR;
841 else if ( tax_group.equals( TaxonomyGroups.AMOEBOZOA ) ) {
842 return TaxonomyColors.AMOEBOZOA_COLOR;
844 else if ( tax_group.equals( TaxonomyGroups.EMBRYOPHYTA ) ) {
845 return TaxonomyColors.EMBRYOPHYTA_COLOR;
847 else if ( tax_group.equals( TaxonomyGroups.CHLOROPHYTA ) ) {
848 return TaxonomyColors.CHLOROPHYTA_COLOR;
850 else if ( tax_group.equals( TaxonomyGroups.RHODOPHYTA ) ) {
851 return TaxonomyColors.RHODOPHYTA_COLOR;
853 else if ( tax_group.equals( TaxonomyGroups.HACROBIA ) ) {
854 return TaxonomyColors.HACROBIA_COLOR;
856 else if ( tax_group.equals( TaxonomyGroups.GLAUCOCYSTOPHYCEAE ) ) {
857 return TaxonomyColors.GLAUCOPHYTA_COLOR;
859 else if ( tax_group.equals( TaxonomyGroups.STRAMENOPILES ) ) {
860 return TaxonomyColors.STRAMENOPILES_COLOR;
862 else if ( tax_group.equals( TaxonomyGroups.ALVEOLATA ) ) {
863 return TaxonomyColors.ALVEOLATA_COLOR;
865 else if ( tax_group.equals( TaxonomyGroups.RHIZARIA ) ) {
866 return TaxonomyColors.RHIZARIA_COLOR;
868 else if ( tax_group.equals( TaxonomyGroups.EXCAVATA ) ) {
869 return TaxonomyColors.EXCAVATA_COLOR;
871 else if ( tax_group.equals( TaxonomyGroups.APUSOZOA ) ) {
872 return TaxonomyColors.APUSOZOA_COLOR;
874 else if ( tax_group.equals( TaxonomyGroups.ARCHAEA ) ) {
875 return TaxonomyColors.ARCHAEA_COLOR;
877 else if ( tax_group.equals( TaxonomyGroups.BACTERIA ) ) {
878 return TaxonomyColors.BACTERIA_COLOR;
880 else if ( tax_group.equals( TaxonomyGroups.VIRUSES ) ) {
881 return TaxonomyColors.VIRUSES_COLOR;
883 else if ( tax_group.equals( TaxonomyGroups.ALPHAHERPESVIRINAE ) ) {
884 return TaxonomyColors.ALPHAHERPESVIRINAE_COLOR;
886 else if ( tax_group.equals( TaxonomyGroups.BETAHERPESVIRINAE ) ) {
887 return TaxonomyColors.BETAHERPESVIRINAE_COLOR;
889 else if ( tax_group.equals( TaxonomyGroups.GAMMAHERPESVIRINAE ) ) {
890 return TaxonomyColors.GAMMAHERPESVIRINAE_COLOR;
892 else if ( tax_group.equals( TaxonomyGroups.OTHER ) ) {
893 return TaxonomyColors.OTHER_COLOR;
899 public final static String obtainNormalizedTaxonomyGroup( final String tax ) {
900 if ( tax.equalsIgnoreCase( TaxonomyGroups.DEUTEROSTOMIA ) ) {
901 return TaxonomyGroups.DEUTEROSTOMIA;
903 else if ( tax.equalsIgnoreCase( TaxonomyGroups.PROTOSTOMIA ) ) {
904 return TaxonomyGroups.PROTOSTOMIA;
906 else if ( tax.equalsIgnoreCase( TaxonomyGroups.CNIDARIA ) ) {
907 return TaxonomyGroups.CNIDARIA;
909 else if ( tax.toLowerCase().startsWith( "trichoplax" ) || tax.equalsIgnoreCase( TaxonomyGroups.PLACOZOA ) ) {
910 return TaxonomyGroups.PLACOZOA;
912 else if ( tax.toLowerCase().startsWith( "mnemiopsis" ) || tax.equalsIgnoreCase( TaxonomyGroups.CTENOPHORA ) ) {
913 return TaxonomyGroups.CTENOPHORA;
915 else if ( tax.toLowerCase().startsWith( "amphimedon" ) || tax.equalsIgnoreCase( TaxonomyGroups.PORIFERA ) ) {
916 return TaxonomyGroups.PORIFERA;
918 else if ( tax.equalsIgnoreCase( "codonosigidae" ) || tax.equalsIgnoreCase( TaxonomyGroups.CHOANOFLAGELLIDA ) ) {
919 return TaxonomyGroups.CHOANOFLAGELLIDA;
921 else if ( tax.toLowerCase().startsWith( TaxonomyGroups.ICHTHYOPHONIDA_FILASTEREA )
922 || tax.toLowerCase().startsWith( "ichthyophonida and filasterea" )
923 || tax.toLowerCase().startsWith( "ichthyosporea & filasterea" )
924 || tax.toLowerCase().startsWith( "ichthyosporea and filasterea" ) ) {
925 return TaxonomyGroups.ICHTHYOPHONIDA_FILASTEREA;
927 else if ( tax.equalsIgnoreCase( TaxonomyGroups.DIKARYA ) ) {
928 return TaxonomyGroups.DIKARYA;
930 else if ( tax.equalsIgnoreCase( TaxonomyGroups.FUNGI ) || tax.equalsIgnoreCase( TaxonomyGroups.OTHER_FUNGI ) ) {
931 return TaxonomyGroups.OTHER_FUNGI;
933 else if ( tax.toLowerCase().startsWith( "nucleariidae and fonticula" ) ) {
934 return TaxonomyGroups.NUCLEARIIDAE_AND_FONTICULA_GROUP;
936 else if ( tax.equalsIgnoreCase( TaxonomyGroups.AMOEBOZOA ) ) {
937 return TaxonomyGroups.AMOEBOZOA;
939 else if ( tax.equalsIgnoreCase( TaxonomyGroups.EMBRYOPHYTA ) ) {
940 return TaxonomyGroups.EMBRYOPHYTA;
942 else if ( tax.equalsIgnoreCase( TaxonomyGroups.CHLOROPHYTA ) ) {
943 return TaxonomyGroups.CHLOROPHYTA;
945 else if ( tax.equalsIgnoreCase( TaxonomyGroups.RHODOPHYTA ) ) {
946 return TaxonomyGroups.RHODOPHYTA;
948 else if ( tax.toLowerCase().startsWith( TaxonomyGroups.HACROBIA ) ) {
949 return TaxonomyGroups.HACROBIA;
951 else if ( tax.equalsIgnoreCase( TaxonomyGroups.GLAUCOCYSTOPHYCEAE ) || tax.equalsIgnoreCase( "glaucophyta" ) ) {
952 return TaxonomyGroups.GLAUCOCYSTOPHYCEAE;
954 else if ( tax.equalsIgnoreCase( TaxonomyGroups.STRAMENOPILES ) ) {
955 return TaxonomyGroups.STRAMENOPILES;
957 else if ( tax.equalsIgnoreCase( TaxonomyGroups.ALVEOLATA ) ) {
958 return TaxonomyGroups.ALVEOLATA;
960 else if ( tax.equalsIgnoreCase( TaxonomyGroups.RHIZARIA ) ) {
961 return TaxonomyGroups.RHIZARIA;
963 else if ( tax.equalsIgnoreCase( TaxonomyGroups.EXCAVATA ) ) {
964 return TaxonomyGroups.EXCAVATA;
966 else if ( tax.equalsIgnoreCase( TaxonomyGroups.APUSOZOA ) ) {
967 return TaxonomyGroups.APUSOZOA;
969 else if ( tax.equalsIgnoreCase( TaxonomyGroups.ARCHAEA ) ) {
970 return TaxonomyGroups.ARCHAEA;
972 else if ( tax.equalsIgnoreCase( TaxonomyGroups.BACTERIA ) ) {
973 return TaxonomyGroups.BACTERIA;
975 else if ( tax.equalsIgnoreCase( TaxonomyGroups.BACTERIA ) ) {
976 return TaxonomyGroups.BACTERIA;
978 else if ( tax.equalsIgnoreCase( TaxonomyGroups.VIRUSES ) ) {
979 return TaxonomyGroups.VIRUSES;
981 else if ( tax.equalsIgnoreCase( TaxonomyGroups.ALPHAHERPESVIRINAE ) ) {
982 return TaxonomyGroups.ALPHAHERPESVIRINAE;
984 else if ( tax.equalsIgnoreCase( TaxonomyGroups.BETAHERPESVIRINAE ) ) {
985 return TaxonomyGroups.BETAHERPESVIRINAE;
987 else if ( tax.equalsIgnoreCase( TaxonomyGroups.GAMMAHERPESVIRINAE ) ) {
988 return TaxonomyGroups.GAMMAHERPESVIRINAE;
993 final public static BufferedReader obtainReader( final Object source ) throws IOException, FileNotFoundException {
994 BufferedReader reader = null;
995 if ( source instanceof File ) {
996 final File f = ( File ) source;
998 throw new IOException( "\"" + f.getAbsolutePath() + "\" does not exist" );
1000 else if ( !f.isFile() ) {
1001 throw new IOException( "\"" + f.getAbsolutePath() + "\" is not a file" );
1003 else if ( !f.canRead() ) {
1004 throw new IOException( "\"" + f.getAbsolutePath() + "\" is not a readable" );
1006 reader = new BufferedReader( new FileReader( f ) );
1008 else if ( source instanceof InputStream ) {
1009 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
1011 else if ( source instanceof String ) {
1012 reader = new BufferedReader( new StringReader( ( String ) source ) );
1014 else if ( source instanceof StringBuffer ) {
1015 reader = new BufferedReader( new StringReader( source.toString() ) );
1018 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
1019 + "] (can only parse objects of type File, InputStream, String, or StringBuffer)" );
1024 public final static void outOfMemoryError( final OutOfMemoryError e ) {
1025 System.err.println();
1026 System.err.println( "Java memory allocation might be too small, try \"-Xmx2048m\" java command line option" );
1027 System.err.println();
1028 e.printStackTrace( System.err );
1029 System.err.println();
1033 final public static StringBuffer pad( final double number,
1036 final boolean left_pad ) {
1037 return pad( new StringBuffer( number + "" ), size, pad, left_pad );
1040 final public static StringBuffer pad( final String string,
1043 final boolean left_pad ) {
1044 return pad( new StringBuffer( string ), size, pad, left_pad );
1047 final public static StringBuffer pad( final StringBuffer string,
1050 final boolean left_pad ) {
1051 final StringBuffer padding = new StringBuffer();
1052 final int s = size - string.length();
1054 return new StringBuffer( string.substring( 0, size ) );
1056 for( int i = 0; i < s; ++i ) {
1057 padding.append( pad );
1060 return padding.append( string );
1063 return string.append( padding );
1067 final public static double parseDouble( final String str ) throws ParseException {
1068 if ( ForesterUtil.isEmpty( str ) ) {
1071 return Double.parseDouble( str );
1074 final public static int parseInt( final String str ) throws ParseException {
1075 if ( ForesterUtil.isEmpty( str ) ) {
1078 return Integer.parseInt( str );
1081 final public static void printArray( final Object[] a ) {
1082 for( int i = 0; i < a.length; ++i ) {
1083 System.out.println( "[" + i + "]=" + a[ i ] );
1087 final public static void printCountingMap( final Map<String, Integer> counting_map ) {
1088 for( final String key : counting_map.keySet() ) {
1089 System.out.println( key + ": " + counting_map.get( key ) );
1093 final public static void printErrorMessage( final String prg_name, final String message ) {
1094 System.err.println( "[" + prg_name + "] > error: " + message );
1097 final public static void printProgramInformation( final String prg_name,
1098 final String prg_version,
1099 final String date ) {
1100 final int l = prg_name.length() + prg_version.length() + date.length() + 4;
1101 System.out.println();
1102 System.out.println( prg_name + " " + prg_version + " (" + date + ")" );
1103 for( int i = 0; i < l; ++i ) {
1104 System.out.print( "_" );
1106 System.out.println();
1109 final public static void printProgramInformation( final String prg_name,
1110 final String prg_version,
1113 final String www ) {
1114 printProgramInformation( prg_name, null, prg_version, date, email, www, null );
1117 final public static void printProgramInformation( final String prg_name,
1119 final String prg_version,
1123 final String based_on ) {
1124 String my_prg_name = new String( prg_name );
1125 if ( !ForesterUtil.isEmpty( desc ) ) {
1126 my_prg_name += ( " - " + desc );
1128 final int l = my_prg_name.length() + prg_version.length() + date.length() + 4;
1129 System.out.println();
1130 System.out.println( my_prg_name + " " + prg_version + " (" + date + ")" );
1131 for( int i = 0; i < l; ++i ) {
1132 System.out.print( "_" );
1134 System.out.println();
1135 System.out.println();
1136 System.out.println( "WWW : " + www );
1137 System.out.println( "Contact : " + email );
1138 if ( !ForesterUtil.isEmpty( based_on ) ) {
1139 System.out.println( "Based on: " + based_on );
1141 if ( !ForesterUtil.isEmpty( ForesterUtil.JAVA_VERSION ) && !ForesterUtil.isEmpty( ForesterUtil.JAVA_VENDOR ) ) {
1142 System.out.println();
1144 .println( "[running on Java " + ForesterUtil.JAVA_VERSION + " " + ForesterUtil.JAVA_VENDOR + "]" );
1146 System.out.println();
1149 final public static void printWarningMessage( final String prg_name, final String message ) {
1150 System.out.println( "[" + prg_name + "] > warning: " + message );
1153 final public static void programMessage( final String prg_name, final String message ) {
1154 System.out.println( "[" + prg_name + "] > " + message );
1157 public static List<String> readUrl( final String url_str ) throws IOException {
1158 final URL url = new URL( url_str );
1159 final URLConnection urlc = url.openConnection();
1160 //urlc.setRequestProperty( "User-Agent", "" );
1161 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
1163 final List<String> result = new ArrayList<String>();
1164 while ( ( line = in.readLine() ) != null ) {
1173 * Example regarding engulfment: ------------0.1 ----------0.2 --0.3 =>
1174 * domain with 0.3 is ignored
1176 * -----------0.1 ----------0.2 --0.3 => domain with 0.3 is ignored
1179 * ------------0.1 ----------0.3 --0.2 => domains with 0.3 and 0.2 are _not_
1182 * @param max_allowed_overlap
1183 * maximal allowed overlap (inclusive) to be still considered not
1184 * overlapping (zero or negative value to allow any overlap)
1185 * @param remove_engulfed_domains
1186 * to remove domains which are completely engulfed by coverage of
1187 * domains with better support
1191 public static Protein removeOverlappingDomains( final int max_allowed_overlap,
1192 final boolean remove_engulfed_domains,
1193 final Protein protein ) {
1194 final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(),
1195 protein.getSpecies().getSpeciesId(),
1196 protein.getLength() );
1197 final List<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
1198 final List<Boolean> covered_positions = new ArrayList<Boolean>();
1199 for( final Domain domain : sorted ) {
1200 if ( ( ( max_allowed_overlap < 0 )
1201 || ( ForesterUtil.calculateOverlap( domain, covered_positions ) <= max_allowed_overlap ) )
1202 && ( !remove_engulfed_domains || !isEngulfed( domain, covered_positions ) ) ) {
1203 final int covered_positions_size = covered_positions.size();
1204 for( int i = covered_positions_size; i < domain.getFrom(); ++i ) {
1205 covered_positions.add( false );
1207 final int new_covered_positions_size = covered_positions.size();
1208 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
1209 if ( i < new_covered_positions_size ) {
1210 covered_positions.set( i, true );
1213 covered_positions.add( true );
1216 pruned_protein.addProteinDomain( domain );
1219 return pruned_protein;
1222 final public static String removeSuffix( final String file_name ) {
1223 final int i = file_name.lastIndexOf( '.' );
1225 return file_name.substring( 0, i );
1231 * Removes all white space from String s.
1233 * @return String s with white space removed
1235 final public static String removeWhiteSpace( String s ) {
1237 for( i = 0; i <= ( s.length() - 1 ); i++ ) {
1238 if ( ( s.charAt( i ) == ' ' ) || ( s.charAt( i ) == '\t' ) || ( s.charAt( i ) == '\n' )
1239 || ( s.charAt( i ) == '\r' ) ) {
1240 s = s.substring( 0, i ) + s.substring( i + 1 );
1247 final public static String replaceIllegalNhxCharacters( final String nhx ) {
1248 if ( nhx == null ) {
1251 return nhx.trim().replaceAll( "[\\[\\]']+", "_" );
1254 final public static double round( final double value, final int decimal_place ) {
1255 BigDecimal bd = new BigDecimal( value );
1256 bd = bd.setScale( decimal_place, BigDecimal.ROUND_HALF_UP );
1257 return bd.doubleValue();
1261 * Rounds d to an int.
1263 final public static int roundToInt( final double d ) {
1264 return ( int ) ( d + 0.5 );
1267 final public static int roundToInt( final float f ) {
1268 return ( int ) ( f + 0.5f );
1271 final public static short roundToShort( final double d ) {
1272 return ( short ) ( d + 0.5 );
1275 final public static String sanitizeString( final String s ) {
1284 public final static StringBuilder santitizeStringForNH( String data ) {
1285 data = data.replaceAll( "\\s+", " " ).trim();
1286 final StringBuilder sb = new StringBuilder();
1287 if ( data.length() > 0 ) {
1288 final boolean single_pars = data.indexOf( '\'' ) > -1;
1289 final boolean double_pars = data.indexOf( '"' ) > -1;
1290 if ( single_pars && double_pars ) {
1291 data = data.replace( '\'', '`' );
1296 else if ( single_pars ) {
1301 else if ( PARANTHESESABLE_NH_CHARS_PATTERN.matcher( data ).find() ) {
1313 public static boolean seqIsLikelyToBeAa( final String s ) {
1314 final String seq = s.toLowerCase();
1315 if ( ( seq.indexOf( 'r' ) > -1 ) || ( seq.indexOf( 'd' ) > -1 ) || ( seq.indexOf( 'e' ) > -1 )
1316 || ( seq.indexOf( 'q' ) > -1 ) || ( seq.indexOf( 'h' ) > -1 ) || ( seq.indexOf( 'k' ) > -1 )
1317 || ( seq.indexOf( 'w' ) > -1 ) || ( seq.indexOf( 's' ) > -1 ) || ( seq.indexOf( 'm' ) > -1 )
1318 || ( seq.indexOf( 'p' ) > -1 ) || ( seq.indexOf( 'v' ) > -1 ) ) {
1324 final private static String[] splitString( final String str ) {
1325 final String regex = "[\\s;,]+";
1326 return str.split( regex );
1329 final public static String stringArrayToString( final String[] a ) {
1330 return stringArrayToString( a, ", " );
1333 final public static String stringArrayToString( final String[] a, final String separator ) {
1334 final StringBuilder sb = new StringBuilder();
1335 if ( ( a != null ) && ( a.length > 0 ) ) {
1336 for( int i = 0; i < ( a.length - 1 ); ++i ) {
1337 sb.append( a[ i ] + separator );
1339 sb.append( a[ a.length - 1 ] );
1341 return sb.toString();
1344 final public static String[] stringListToArray( final List<String> list ) {
1345 if ( list != null ) {
1346 final String[] str = new String[ list.size() ];
1348 for( final String l : list ) {
1356 final public static String stringListToString( final List<String> l, final String separator ) {
1357 final StringBuilder sb = new StringBuilder();
1358 if ( ( l != null ) && ( l.size() > 0 ) ) {
1359 for( int i = 0; i < ( l.size() - 1 ); ++i ) {
1360 sb.append( l.get( i ) + separator );
1362 sb.append( l.get( l.size() - 1 ) );
1364 return sb.toString();
1367 final public static String[] stringSetToArray( final Set<String> strings ) {
1368 final String[] str_array = new String[ strings.size() ];
1370 for( final String e : strings ) {
1371 str_array[ i++ ] = e;
1376 final public static void unexpectedFatalError( final Error e ) {
1377 System.err.println();
1378 System.err.println( "unexpected error: should not have occured! Please contact program author(s)." );
1379 e.printStackTrace( System.err );
1380 System.err.println();
1384 final public static void unexpectedFatalError( final Exception e ) {
1385 System.err.println();
1386 System.err.println( "unexpected exception: should not have occured! Please contact program author(s)." );
1387 e.printStackTrace( System.err );
1388 System.err.println();
1392 final public static void unexpectedFatalError( final String message ) {
1393 System.err.println();
1394 System.err.println( "unexpected error: should not have occured! Please contact program author(s)." );
1395 System.err.println( message );
1396 System.err.println();
1400 final public static void unexpectedFatalError( final String prg_name, final Exception e ) {
1401 System.err.println();
1402 System.err.println( "[" + prg_name
1403 + "] > unexpected error; should not have occured! Please contact program author(s)." );
1404 e.printStackTrace( System.err );
1405 System.err.println();
1409 final public static void unexpectedFatalError( final String prg_name, final String message ) {
1410 System.err.println();
1411 System.err.println( "[" + prg_name
1412 + "] > unexpected error: should not have occured! Please contact program author(s)." );
1413 System.err.println( message );
1414 System.err.println();
1418 final public static void unexpectedFatalError( final String prg_name, final String message, final Exception e ) {
1419 System.err.println();
1420 System.err.println( "[" + prg_name
1421 + "] > unexpected error: should not have occured! Please contact program author(s)." );
1422 System.err.println( message );
1423 e.printStackTrace( System.err );
1424 System.err.println();
1428 public final static void updateProgress( final double progress_percentage ) {
1429 final int width = 50;
1430 System.out.print( "\r[" );
1432 for( ; i <= ForesterUtil.roundToInt( progress_percentage * width ); i++ ) {
1433 System.out.print( "." );
1435 for( ; i < width; i++ ) {
1436 System.out.print( " " );
1438 System.out.print( "]" );
1441 public final static void updateProgress( final int i, final DecimalFormat f ) {
1442 System.out.print( "\r[" + f.format( i ) + "]" );
1445 public final static String wordWrap( final String str, final int width ) {
1446 final StringBuilder sb = new StringBuilder( str );
1450 while ( i < sb.length() ) {
1451 if ( sb.charAt( i ) == ' ' ) {
1454 if ( sb.charAt( i ) == '\n' ) {
1458 if ( i > ( ( start + width ) - 1 ) ) {
1460 sb.setCharAt( ls, '\n' );
1465 sb.insert( i, '\n' );
1471 return sb.toString();
1474 public final static Phylogeny[] readPhylogeniesFromUrl( final URL url, final PhylogenyParser parser )
1475 throws NoSuchAlgorithmException, IOException, KeyManagementException {
1476 if ( url == null ) {
1477 throw new IllegalArgumentException( "URL to read from must not be null" );
1479 else if ( parser == null ) {
1480 throw new IllegalArgumentException( "parser to use to read from URL must not be null" );
1482 final URLConnection con;
1483 if ( url.toString().startsWith( "https:" ) ) {
1484 con = TrustManager.makeHttpsURLConnection( url );
1486 else if ( url.toString().startsWith( "http:" ) ) {
1487 con = url.openConnection();
1490 throw new IllegalArgumentException( "Cannot deal with URL: " + url );
1492 if ( con == null ) {
1493 throw new IOException( "could not create connection from " + url );
1495 con.setDefaultUseCaches( false );
1496 final InputStream is = con.getInputStream();
1498 throw new IOException( "could not create input stream from " + url );
1500 final Phylogeny[] trees = ParserBasedPhylogenyFactory.getInstance().create( is, parser );
1504 catch ( final Exception e ) {
1510 private ForesterUtil() {
1513 public final static File getMatchingFile( final File dir, final String prefix, final String suffix )
1514 throws IOException {
1515 if ( !dir.exists() ) {
1516 throw new IOException( "[" + dir + "] does not exist" );
1518 if ( !dir.isDirectory() ) {
1519 throw new IOException( "[" + dir + "] is not a directory" );
1521 final File mapping_files[] = dir.listFiles( new FilenameFilter() {
1524 public boolean accept( final File dir, final String name ) {
1525 return ( name.endsWith( suffix ) );
1528 if ( mapping_files.length == 1 ) {
1529 throw new IOException( "no files ending with \"" + suffix + "\" found in [" + dir + "]" );
1531 String my_prefix = removeFileExtension( prefix );
1532 boolean done = false;
1533 boolean more_than_one = false;
1534 File the_one = null;
1537 for( File file : mapping_files ) {
1538 if ( file.getName().startsWith( my_prefix ) ) {
1540 if ( matches > 1 ) {
1547 if ( matches > 1 ) {
1548 more_than_one = true;
1551 if ( matches == 1 ) {
1555 if ( my_prefix.length() <= 1 ) {
1556 throw new IOException( "no file matching \"" + removeFileExtension( prefix )
1557 + "\" and ending with \"" + suffix + "\" found in [" + dir + "]" );
1559 my_prefix = my_prefix.substring( 0, my_prefix.length() - 1 );
1562 if ( more_than_one ) {
1563 throw new IOException( "multiple files matching \"" + removeFileExtension( prefix )
1564 + "\" and ending with \"" + suffix + "\" found in [" + dir + "]" );
1566 else if ( the_one != null ) {
1569 throw new IOException( "no file matching \"" + removeFileExtension( prefix ) + "\" and ending with \""
1570 + suffix + "\" found in [" + dir + "]" );