X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Futil%2FForesterUtil.java;h=899e7751fa62053ba5be2eb32d01e9c0bfef4370;hb=d0bb37d418d945966304afe70431185c3873635a;hp=cb04e6521e93833a056a9756c4cad769ed6647ac;hpb=cc75486aa58b98ab6fa53d8de4cb9b984a86bf83;p=jalview.git diff --git a/forester/java/src/org/forester/util/ForesterUtil.java b/forester/java/src/org/forester/util/ForesterUtil.java index cb04e65..899e775 100644 --- a/forester/java/src/org/forester/util/ForesterUtil.java +++ b/forester/java/src/org/forester/util/ForesterUtil.java @@ -21,7 +21,7 @@ // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA // // Contact: phylosoft @ gmail . com -// WWW: www.phylosoft.org/forester +// WWW: https://sites.google.com/site/cmzmasek/home/software/forester package org.forester.util; @@ -50,7 +50,6 @@ import java.text.SimpleDateFormat; import java.util.ArrayList; import java.util.Collection; import java.util.Date; -import java.util.Iterator; import java.util.List; import java.util.Map; import java.util.Map.Entry; @@ -59,29 +58,40 @@ import java.util.SortedMap; import java.util.SortedSet; import java.util.TreeMap; import java.util.TreeSet; +import java.util.regex.Matcher; import java.util.regex.Pattern; +import org.forester.archaeopteryx.Constants; import org.forester.phylogeny.PhylogenyNode; import org.forester.phylogeny.data.Distribution; import org.forester.phylogeny.data.Sequence; import org.forester.phylogeny.data.Taxonomy; +import org.forester.protein.BasicProtein; +import org.forester.protein.Domain; +import org.forester.protein.Protein; +import org.forester.surfacing.SurfacingUtil; public final class ForesterUtil { public final static String FILE_SEPARATOR = System.getProperty( "file.separator" ); - public final static String LINE_SEPARATOR = System.getProperty( "line.separator" ); + public static final NumberFormat FORMATTER_06; + public static final NumberFormat FORMATTER_3; + public static final NumberFormat FORMATTER_6; + public static final NumberFormat FORMATTER_9; public final static String JAVA_VENDOR = System.getProperty( "java.vendor" ); public final static String JAVA_VERSION = System.getProperty( "java.version" ); + public final static String LINE_SEPARATOR = System.getProperty( "line.separator" ); + public static final String NCBI_GI = "http://www.ncbi.nlm.nih.gov/protein/gi:"; + public static final String NCBI_NUCCORE = "http://www.ncbi.nlm.nih.gov/nuccore/"; + public static final String NCBI_PROTEIN = "http://www.ncbi.nlm.nih.gov/protein/"; + public static final BigDecimal NULL_BD = new BigDecimal( 0 ); public final static String OS_ARCH = System.getProperty( "os.arch" ); public final static String OS_NAME = System.getProperty( "os.name" ); public final static String OS_VERSION = System.getProperty( "os.version" ); - public final static Pattern PARANTHESESABLE_NH_CHARS_PATTERN = Pattern.compile( "[(),;\\s]" ); + public static final String PDB = "http://www.pdb.org/pdb/explore/explore.do?pdbId="; + public final static String UNIPROT_KB = "http://www.uniprot.org/uniprot/"; public final static double ZERO_DIFF = 1.0E-9; - public static final BigDecimal NULL_BD = new BigDecimal( 0 ); - public static final NumberFormat FORMATTER_9; - public static final NumberFormat FORMATTER_6; - public static final NumberFormat FORMATTER_06; - public static final NumberFormat FORMATTER_3; + private static final Pattern PARANTHESESABLE_NH_CHARS_PATTERN = Pattern.compile( "[(),;\\s:\\[\\]]" ); static { final DecimalFormatSymbols dfs = new DecimalFormatSymbols(); dfs.setDecimalSeparator( '.' ); @@ -191,6 +201,16 @@ public final class ForesterUtil { } } + public static int calculateOverlap( final Domain domain, final List covered_positions ) { + int overlap_count = 0; + for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) { + if ( ( i < covered_positions.size() ) && ( covered_positions.get( i ) == true ) ) { + ++overlap_count; + } + } + return overlap_count; + } + final public static String collapseWhiteSpace( final String s ) { return s.replaceAll( "[\\s]+", " " ); } @@ -339,6 +359,34 @@ public final class ForesterUtil { } } + public static String[][] file22dArray( final File file ) throws IOException { + final List list = new ArrayList(); + final BufferedReader in = new BufferedReader( new FileReader( file ) ); + String str; + while ( ( str = in.readLine() ) != null ) { + str = str.trim(); + if ( ( str.length() > 0 ) && !str.startsWith( "#" ) ) { + list.add( str ); + } + } + in.close(); + final String[][] ary = new String[ list.size() ][ 2 ]; + final Pattern pa = Pattern.compile( "(\\S+)\\s+(\\S+)" ); + int i = 0; + for( final String s : list ) { + final Matcher m = pa.matcher( s ); + if ( m.matches() ) { + ary[ i ][ 0 ] = m.group( 1 ); + ary[ i ][ 1 ] = m.group( 2 ); + ++i; + } + else { + throw new IOException( "unexpcted format: " + s ); + } + } + return ary; + } + public static String[] file2array( final File file ) throws IOException { final List list = file2list( file ); final String[] ary = new String[ list.size() ]; @@ -453,10 +501,6 @@ public final class ForesterUtil { } } - final public static boolean isContainsParanthesesableNhCharacter( final String nh ) { - return PARANTHESESABLE_NH_CHARS_PATTERN.matcher( nh ).find(); - } - final public static boolean isEmpty( final List l ) { if ( ( l == null ) || l.isEmpty() ) { return true; @@ -485,6 +529,23 @@ public final class ForesterUtil { return ( ( s == null ) || ( s.length() < 1 ) ); } + /** + * Returns true is Domain domain falls in an uninterrupted stretch of + * covered positions. + * + * @param domain + * @param covered_positions + * @return + */ + public static boolean isEngulfed( final Domain domain, final List covered_positions ) { + for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) { + if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) { + return false; + } + } + return true; + } + final public static boolean isEqual( final double a, final double b ) { return ( ( Math.abs( a - b ) ) < ZERO_DIFF ); } @@ -529,6 +590,16 @@ public final class ForesterUtil { } } + public final static boolean isMac() { + try { + return OS_NAME.toLowerCase().startsWith( "mac" ); + } + catch ( final Exception e ) { + ForesterUtil.printWarningMessage( Constants.PRG_NAME, "minor error: " + e ); + return false; + } + } + final public static boolean isNull( final BigDecimal s ) { return ( ( s == null ) || ( s.compareTo( NULL_BD ) == 0 ) ); } @@ -556,8 +627,14 @@ public final class ForesterUtil { return isReadableFile( new File( s ) ); } - public static boolean isWindowns() { - return ForesterUtil.OS_NAME.toLowerCase().indexOf( "win" ) > -1; + public final static boolean isWindows() { + try { + return OS_NAME.toLowerCase().indexOf( "win" ) > -1; + } + catch ( final Exception e ) { + ForesterUtil.printWarningMessage( Constants.PRG_NAME, "minor error: " + e ); + return false; + } } final public static String isWritableFile( final File f ) { @@ -585,7 +662,7 @@ public final class ForesterUtil { return i; } - final public static SortedMap listToSortedCountsMap( final List list ) { + final public static SortedMap listToSortedCountsMap( final List list ) { final SortedMap map = new TreeMap(); for( final Object key : list ) { if ( !map.containsKey( key ) ) { @@ -625,10 +702,9 @@ public final class ForesterUtil { } } - final public static StringBuffer mapToStringBuffer( final Map map, final String key_value_separator ) { + final public static StringBuffer mapToStringBuffer( final Map map, final String key_value_separator ) { final StringBuffer sb = new StringBuffer(); - for( final Iterator iter = map.keySet().iterator(); iter.hasNext(); ) { - final Object key = iter.next(); + for( final Object key : map.keySet() ) { sb.append( key.toString() ); sb.append( key_value_separator ); sb.append( map.get( key ).toString() ); @@ -658,6 +734,164 @@ public final class ForesterUtil { } } + public final static Color obtainColorDependingOnTaxonomyGroup( final String tax_group ) { + if ( !ForesterUtil.isEmpty( tax_group ) ) { + if ( tax_group.equals( TaxonomyGroups.DEUTEROSTOMIA ) ) { + return TaxonomyColors.DEUTEROSTOMIA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.PROTOSTOMIA ) ) { + return TaxonomyColors.PROTOSTOMIA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.CNIDARIA ) ) { + return TaxonomyColors.CNIDARIA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.PLACOZOA ) ) { + return TaxonomyColors.PLACOZOA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.CTENOPHORA ) ) { + return TaxonomyColors.CTENOPHORA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.PORIFERA ) ) { + return TaxonomyColors.PORIFERA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.CHOANOFLAGELLIDA ) ) { + return TaxonomyColors.CHOANOFLAGELLIDA; + } + else if ( tax_group.equals( TaxonomyGroups.ICHTHYOPHONIDA_FILASTEREA ) ) { + return TaxonomyColors.ICHTHYOSPOREA_AND_FILASTEREA; + } + else if ( tax_group.equals( TaxonomyGroups.DIKARYA ) ) { + return TaxonomyColors.DIKARYA_COLOR; + } + else if ( tax_group.equalsIgnoreCase( TaxonomyGroups.FUNGI ) + || tax_group.equalsIgnoreCase( TaxonomyGroups.OTHER_FUNGI ) ) { + return TaxonomyColors.OTHER_FUNGI_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.NUCLEARIIDAE_AND_FONTICULA_GROUP ) ) { + return TaxonomyColors.NUCLEARIIDAE_AND_FONTICULA_GROUP_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.AMOEBOZOA ) ) { + return TaxonomyColors.AMOEBOZOA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.EMBRYOPHYTA ) ) { + return TaxonomyColors.EMBRYOPHYTA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.CHLOROPHYTA ) ) { + return TaxonomyColors.CHLOROPHYTA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.RHODOPHYTA ) ) { + return TaxonomyColors.RHODOPHYTA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.HACROBIA ) ) { + return TaxonomyColors.HACROBIA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.GLAUCOCYSTOPHYCEAE ) ) { + return TaxonomyColors.GLAUCOPHYTA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.STRAMENOPILES ) ) { + return TaxonomyColors.STRAMENOPILES_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.ALVEOLATA ) ) { + return TaxonomyColors.ALVEOLATA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.RHIZARIA ) ) { + return TaxonomyColors.RHIZARIA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.EXCAVATA ) ) { + return TaxonomyColors.EXCAVATA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.APUSOZOA ) ) { + return TaxonomyColors.APUSOZOA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.ARCHAEA ) ) { + return TaxonomyColors.ARCHAEA_COLOR; + } + else if ( tax_group.equals( TaxonomyGroups.BACTERIA ) ) { + return TaxonomyColors.BACTERIA_COLOR; + } + } + return null; + } + + public final static String obtainNormalizedTaxonomyGroup( final String tax ) { + if ( tax.equalsIgnoreCase( TaxonomyGroups.DEUTEROSTOMIA ) ) { + return TaxonomyGroups.DEUTEROSTOMIA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.PROTOSTOMIA ) ) { + return TaxonomyGroups.PROTOSTOMIA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.CNIDARIA ) ) { + return TaxonomyGroups.CNIDARIA; + } + else if ( tax.toLowerCase().startsWith( "trichoplax" ) || tax.equalsIgnoreCase( TaxonomyGroups.PLACOZOA ) ) { + return TaxonomyGroups.PLACOZOA; + } + else if ( tax.toLowerCase().startsWith( "mnemiopsis" ) || tax.equalsIgnoreCase( TaxonomyGroups.CTENOPHORA ) ) { + return TaxonomyGroups.CTENOPHORA; + } + else if ( tax.toLowerCase().startsWith( "amphimedon" ) || tax.equalsIgnoreCase( TaxonomyGroups.PORIFERA ) ) { + return TaxonomyGroups.PORIFERA; + } + else if ( tax.equalsIgnoreCase( "codonosigidae" ) || tax.equalsIgnoreCase( TaxonomyGroups.CHOANOFLAGELLIDA ) ) { + return TaxonomyGroups.CHOANOFLAGELLIDA; + } + else if ( tax.toLowerCase().startsWith( TaxonomyGroups.ICHTHYOPHONIDA_FILASTEREA ) + || tax.toLowerCase().startsWith( "ichthyophonida and filasterea" ) + || tax.toLowerCase().startsWith( "ichthyosporea & filasterea" ) + || tax.toLowerCase().startsWith( "ichthyosporea and filasterea" ) ) { + return TaxonomyGroups.ICHTHYOPHONIDA_FILASTEREA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.DIKARYA ) ) { + return TaxonomyGroups.DIKARYA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.FUNGI ) || tax.equalsIgnoreCase( TaxonomyGroups.OTHER_FUNGI ) ) { + return TaxonomyGroups.OTHER_FUNGI; + } + else if ( tax.toLowerCase().startsWith( "nucleariidae and fonticula" ) ) { + return TaxonomyGroups.NUCLEARIIDAE_AND_FONTICULA_GROUP; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.AMOEBOZOA ) ) { + return TaxonomyGroups.AMOEBOZOA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.EMBRYOPHYTA ) ) { + return TaxonomyGroups.EMBRYOPHYTA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.CHLOROPHYTA ) ) { + return TaxonomyGroups.CHLOROPHYTA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.RHODOPHYTA ) ) { + return TaxonomyGroups.RHODOPHYTA; + } + else if ( tax.toLowerCase().startsWith( TaxonomyGroups.HACROBIA ) ) { + return TaxonomyGroups.HACROBIA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.GLAUCOCYSTOPHYCEAE ) || tax.equalsIgnoreCase( "glaucophyta" ) ) { + return TaxonomyGroups.GLAUCOCYSTOPHYCEAE; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.STRAMENOPILES ) ) { + return TaxonomyGroups.STRAMENOPILES; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.ALVEOLATA ) ) { + return TaxonomyGroups.ALVEOLATA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.RHIZARIA ) ) { + return TaxonomyGroups.RHIZARIA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.EXCAVATA ) ) { + return TaxonomyGroups.EXCAVATA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.APUSOZOA ) ) { + return TaxonomyGroups.APUSOZOA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.ARCHAEA ) ) { + return TaxonomyGroups.ARCHAEA; + } + else if ( tax.equalsIgnoreCase( TaxonomyGroups.BACTERIA ) ) { + return TaxonomyGroups.BACTERIA; + } + return null; + } + final public static BufferedReader obtainReader( final Object source ) throws IOException, FileNotFoundException { BufferedReader reader = null; if ( source instanceof File ) { @@ -689,6 +923,15 @@ public final class ForesterUtil { return reader; } + public final static void outOfMemoryError( final OutOfMemoryError e ) { + System.err.println(); + System.err.println( "Java memory allocation might be too small, try \"-Xmx2048m\" java command line option" ); + System.err.println(); + e.printStackTrace( System.err ); + System.err.println(); + System.exit( -1 ); + } + final public static StringBuffer pad( final double number, final int size, final char pad, final boolean left_pad ) { return pad( new StringBuffer( number + "" ), size, pad, left_pad ); } @@ -804,6 +1047,55 @@ public final class ForesterUtil { System.out.println( "[" + prg_name + "] > " + message ); } + /** + * + * Example regarding engulfment: ------------0.1 ----------0.2 --0.3 => + * domain with 0.3 is ignored + * + * -----------0.1 ----------0.2 --0.3 => domain with 0.3 is ignored + * + * + * ------------0.1 ----------0.3 --0.2 => domains with 0.3 and 0.2 are _not_ + * ignored + * + * @param max_allowed_overlap + * maximal allowed overlap (inclusive) to be still considered not + * overlapping (zero or negative value to allow any overlap) + * @param remove_engulfed_domains + * to remove domains which are completely engulfed by coverage of + * domains with better support + * @param protein + * @return + */ + public static Protein removeOverlappingDomains( final int max_allowed_overlap, + final boolean remove_engulfed_domains, + final Protein protein ) { + final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(), protein.getSpecies() + .getSpeciesId(), protein.getLength() ); + final List sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein ); + final List covered_positions = new ArrayList(); + for( final Domain domain : sorted ) { + if ( ( ( max_allowed_overlap < 0 ) || ( ForesterUtil.calculateOverlap( domain, covered_positions ) <= max_allowed_overlap ) ) + && ( !remove_engulfed_domains || !isEngulfed( domain, covered_positions ) ) ) { + final int covered_positions_size = covered_positions.size(); + for( int i = covered_positions_size; i < domain.getFrom(); ++i ) { + covered_positions.add( false ); + } + final int new_covered_positions_size = covered_positions.size(); + for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) { + if ( i < new_covered_positions_size ) { + covered_positions.set( i, true ); + } + else { + covered_positions.add( true ); + } + } + pruned_protein.addProteinDomain( domain ); + } + } + return pruned_protein; + } + final public static String removeSuffix( final String file_name ) { final int i = file_name.lastIndexOf( '.' ); if ( i > 1 ) { @@ -829,18 +1121,11 @@ public final class ForesterUtil { return s; } - final public static String replaceIllegalNhCharacters( final String nh ) { - if ( nh == null ) { - return ""; - } - return nh.trim().replaceAll( "[\\[\\]:]+", "_" ); - } - final public static String replaceIllegalNhxCharacters( final String nhx ) { if ( nhx == null ) { return ""; } - return nhx.trim().replaceAll( "[\\[\\](),:;\\s]+", "_" ); + return nhx.trim().replaceAll( "[\\[\\]']+", "_" ); } final public static double round( final double value, final int decimal_place ) { @@ -873,6 +1158,35 @@ public final class ForesterUtil { } } + public final static StringBuilder santitizeStringForNH( String data ) { + data = data.replaceAll( "\\s+", " " ).trim(); + final StringBuilder sb = new StringBuilder(); + if ( data.length() > 0 ) { + final boolean single_pars = data.indexOf( '\'' ) > -1; + final boolean double_pars = data.indexOf( '"' ) > -1; + if ( single_pars && double_pars ) { + data = data.replace( '\'', '`' ); + sb.append( '\'' ); + sb.append( data ); + sb.append( '\'' ); + } + else if ( single_pars ) { + sb.append( '"' ); + sb.append( data ); + sb.append( '"' ); + } + else if ( PARANTHESESABLE_NH_CHARS_PATTERN.matcher( data ).find() ) { + sb.append( '\'' ); + sb.append( data ); + sb.append( '\'' ); + } + else { + sb.append( data ); + } + } + return sb; + } + public static boolean seqIsLikelyToBeAa( final String s ) { final String seq = s.toLowerCase(); if ( ( seq.indexOf( 'r' ) > -1 ) || ( seq.indexOf( 'd' ) > -1 ) || ( seq.indexOf( 'e' ) > -1 ) @@ -931,17 +1245,17 @@ public final class ForesterUtil { return str_array; } - final public static void unexpectedFatalError( final Exception e ) { + final public static void unexpectedFatalError( final Error e ) { System.err.println(); - System.err.println( "unexpected exception: should not have occured! Please contact program author(s)." ); + System.err.println( "unexpected error: should not have occured! Please contact program author(s)." ); e.printStackTrace( System.err ); System.err.println(); System.exit( -1 ); } - final public static void unexpectedFatalError( final Error e ) { + final public static void unexpectedFatalError( final Exception e ) { System.err.println(); - System.err.println( "unexpected error: should not have occured! Please contact program author(s)." ); + System.err.println( "unexpected exception: should not have occured! Please contact program author(s)." ); e.printStackTrace( System.err ); System.err.println(); System.exit( -1 ); @@ -996,6 +1310,10 @@ public final class ForesterUtil { System.out.print( "]" ); } + public final static void updateProgress( final int i, final DecimalFormat f ) { + System.out.print( "\r[" + f.format( i ) + "]" ); + } + public final static String wordWrap( final String str, final int width ) { final StringBuilder sb = new StringBuilder( str ); int start = 0; @@ -1062,13 +1380,4 @@ public final class ForesterUtil { final String regex = "[\\s;,]+"; return str.split( regex ); } - - public final static void outOfMemoryError( final OutOfMemoryError e ) { - System.err.println(); - System.err.println( "Java memory allocation might be too small, try \"-Xmx2048m\" java command line option" ); - System.err.println(); - e.printStackTrace( System.err ); - System.err.println(); - System.exit( -1 ); - } }