X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Futil%2FForesterUtil.java;h=a8c81b0dd23ae214f2280b324a659ae3f3f544f2;hb=aec065f948a075773794133f102ea19eb1d59f64;hp=64f3f81ccc0467b431025aebc718a06402cd44a0;hpb=93ef19e783e50f00e4e4d1467613d74142b40654;p=jalview.git diff --git a/forester/java/src/org/forester/util/ForesterUtil.java b/forester/java/src/org/forester/util/ForesterUtil.java index 64f3f81..a8c81b0 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; @@ -38,6 +38,7 @@ import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.io.StringReader; +import java.io.Writer; import java.math.BigDecimal; import java.net.URL; import java.text.DateFormat; @@ -47,11 +48,12 @@ import java.text.NumberFormat; import java.text.ParseException; import java.text.SimpleDateFormat; import java.util.ArrayList; +import java.util.Collection; import java.util.Date; -import java.util.Hashtable; import java.util.Iterator; import java.util.List; import java.util.Map; +import java.util.Map.Entry; import java.util.Set; import java.util.SortedMap; import java.util.SortedSet; @@ -60,24 +62,10 @@ import java.util.TreeSet; import java.util.regex.Matcher; import java.util.regex.Pattern; -import org.forester.io.parsers.PhylogenyParser; -import org.forester.io.parsers.nexus.NexusPhylogeniesParser; -import org.forester.io.parsers.nhx.NHXParser; -import org.forester.io.parsers.phyloxml.PhyloXmlParser; -import org.forester.io.parsers.phyloxml.PhyloXmlUtil; -import org.forester.io.parsers.tol.TolParser; -import org.forester.io.parsers.util.PhylogenyParserException; -import org.forester.phylogeny.Phylogeny; -import org.forester.phylogeny.PhylogenyMethods; import org.forester.phylogeny.PhylogenyNode; -import org.forester.phylogeny.data.Confidence; import org.forester.phylogeny.data.Distribution; -import org.forester.phylogeny.data.Identifier; import org.forester.phylogeny.data.Sequence; import org.forester.phylogeny.data.Taxonomy; -import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory; -import org.forester.phylogeny.factories.PhylogenyFactory; -import org.forester.phylogeny.iterators.PhylogenyNodeIterator; public final class ForesterUtil { @@ -95,6 +83,14 @@ public final class ForesterUtil { public static final NumberFormat FORMATTER_6; public static final NumberFormat FORMATTER_06; public static final NumberFormat FORMATTER_3; + public static final String NCBI_PROTEIN = "http://www.ncbi.nlm.nih.gov/protein/"; + public static final String NCBI_NUCCORE = "http://www.ncbi.nlm.nih.gov/nuccore/"; + public final static String UNIPROT_KB = "http://www.uniprot.org/uniprot/"; + public final static Pattern UNIPROT_KB_PATTERN_1 = Pattern + .compile( "(?:\\b|_)(?:sp|tr)[\\.|\\-_=/\\\\]([A-Z][0-9][A-Z0-9]{3}[0-9])(?:\\b|_)" ); + public final static Pattern UNIPROT_KB_PATTERN_2 = Pattern + .compile( "\\b(?:[A-Z0-9]{2,5}|(?:[A-Z][0-9][A-Z0-9]{3}[0-9]))_(([A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA)\\b" ); + public static final String NCBI_GI = "http://www.ncbi.nlm.nih.gov/protein/gi:"; static { final DecimalFormatSymbols dfs = new DecimalFormatSymbols(); dfs.setDecimalSeparator( '.' ); @@ -108,6 +104,124 @@ public final class ForesterUtil { private ForesterUtil() { } + public static String extractRefSeqAccessorAccessor( final PhylogenyNode node ) { + String v = null; + if ( node.getNodeData().isHasSequence() ) { + final Sequence seq = node.getNodeData().getSequence(); + if ( !isEmpty( seq.getSymbol() ) ) { + v = SequenceIdParser.parseRefSeqAccessor( seq.getSymbol() ); + } + if ( isEmpty( v ) && !isEmpty( seq.getName() ) ) { + v = SequenceIdParser.parseRefSeqAccessor( seq.getName() ); + } + if ( isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null ) + && !isEmpty( seq.getAccession().getValue() ) ) { + v = SequenceIdParser.parseRefSeqAccessor( seq.getAccession().getValue() ); + } + } + if ( isEmpty( v ) && !isEmpty( node.getName() ) ) { + v = SequenceIdParser.parseRefSeqAccessor( node.getName() ); + } + return v; + } + + public static String extractGenbankAccessor( final PhylogenyNode node ) { + String v = null; + if ( node.getNodeData().isHasSequence() ) { + final Sequence seq = node.getNodeData().getSequence(); + if ( !isEmpty( seq.getSymbol() ) ) { + v = SequenceIdParser.parseGenbankAccessor( seq.getSymbol() ); + } + if ( isEmpty( v ) && !isEmpty( seq.getName() ) ) { + v = SequenceIdParser.parseGenbankAccessor( seq.getName() ); + } + if ( isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null ) + && !isEmpty( seq.getAccession().getValue() ) ) { + v = SequenceIdParser.parseGenbankAccessor( seq.getAccession().getValue() ); + } + } + if ( isEmpty( v ) && !isEmpty( node.getName() ) ) { + v = SequenceIdParser.parseGenbankAccessor( node.getName() ); + } + return v; + } + + public static String extractGInumber( final PhylogenyNode node ) { + String v = null; + if ( node.getNodeData().isHasSequence() ) { + final Sequence seq = node.getNodeData().getSequence(); + if ( isEmpty( v ) && !isEmpty( seq.getName() ) ) { + v = SequenceIdParser.parseGInumber( seq.getName() ); + } + if ( isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null ) + && !isEmpty( seq.getAccession().getValue() ) ) { + v = SequenceIdParser.parseGInumber( seq.getAccession().getValue() ); + } + } + if ( isEmpty( v ) && !isEmpty( node.getName() ) ) { + v = SequenceIdParser.parseGInumber( node.getName() ); + } + return v; + } + + public static String extractUniProtKbProteinSeqIdentifier( final PhylogenyNode node ) { + String upkb = null; + if ( node.getNodeData().isHasSequence() ) { + final Sequence seq = node.getNodeData().getSequence(); + Matcher m; + if ( !isEmpty( seq.getSymbol() ) ) { + m = UNIPROT_KB_PATTERN_1.matcher( seq.getSymbol() ); + if ( m.find() ) { + upkb = m.group( 1 ); + } + else { + m = UNIPROT_KB_PATTERN_2.matcher( seq.getSymbol() ); + if ( m.find() ) { + upkb = m.group(); + } + } + } + if ( isEmpty( upkb ) && !isEmpty( seq.getName() ) ) { + m = UNIPROT_KB_PATTERN_1.matcher( seq.getName() ); + if ( m.find() ) { + upkb = m.group( 1 ); + } + else { + m = UNIPROT_KB_PATTERN_2.matcher( seq.getName() ); + if ( m.find() ) { + upkb = m.group(); + } + } + } + if ( isEmpty( upkb ) && ( node.getNodeData().getSequence().getAccession() != null ) + && !isEmpty( seq.getAccession().getValue() ) ) { + m = UNIPROT_KB_PATTERN_1.matcher( seq.getAccession().getValue() ); + if ( m.find() ) { + upkb = m.group( 1 ); + } + else { + m = UNIPROT_KB_PATTERN_2.matcher( seq.getAccession().getValue() ); + if ( m.find() ) { + upkb = m.group(); + } + } + } + } + if ( isEmpty( upkb ) && !isEmpty( node.getName() ) ) { + final Matcher m1 = UNIPROT_KB_PATTERN_1.matcher( node.getName() ); + if ( m1.find() ) { + upkb = m1.group( 1 ); + } + else { + final Matcher m2 = UNIPROT_KB_PATTERN_2.matcher( node.getName() ); + if ( m2.find() ) { + upkb = m2.group(); + } + } + } + return upkb; + } + final public static void appendSeparatorIfNotEmpty( final StringBuffer sb, final char separator ) { if ( sb.length() > 0 ) { sb.append( separator ); @@ -204,41 +318,29 @@ public final class ForesterUtil { } } - /** - * Helper method for calcColor methods. - * - * @param smallercolor_component_x - * color component the smaller color - * @param largercolor_component_x - * color component the larger color - * @param x - * factor - * @return an int representing a color component - */ - final private static int calculateColorComponent( final double smallercolor_component_x, - final double largercolor_component_x, - final double x ) { - return ( int ) ( smallercolor_component_x + ( ( x * ( largercolor_component_x - smallercolor_component_x ) ) / 255.0 ) ); + final public static String collapseWhiteSpace( final String s ) { + return s.replaceAll( "[\\s]+", " " ); } - /** - * Helper method for calcColor methods. - * - * - * @param value - * the value - * @param larger - * the largest value - * @param smaller - * the smallest value - * @return a normalized value between larger and smaller - */ - final private static double calculateColorFactor( final double value, final double larger, final double smaller ) { - return ( 255.0 * ( value - smaller ) ) / ( larger - smaller ); + final public static void collection2file( final File file, final Collection data, final String separator ) + throws IOException { + final Writer writer = new BufferedWriter( new FileWriter( file ) ); + collection2writer( writer, data, separator ); + writer.close(); } - final public static String collapseWhiteSpace( final String s ) { - return s.replaceAll( "[\\s]+", " " ); + final public static void collection2writer( final Writer writer, final Collection data, final String separator ) + throws IOException { + boolean first = true; + for( final Object object : data ) { + if ( !first ) { + writer.write( separator ); + } + else { + first = false; + } + writer.write( object.toString() ); + } } final public static String colorToHex( final Color color ) { @@ -290,6 +392,14 @@ public final class ForesterUtil { return new BufferedWriter( new FileWriter( createFileForWriting( name ) ) ); } + final public static EasyWriter createEasyWriter( final File file ) throws IOException { + return new EasyWriter( createBufferedWriter( file ) ); + } + + final public static BufferedWriter createEasyWriter( final String name ) throws IOException { + return createEasyWriter( createFileForWriting( name ) ); + } + final public static File createFileForWriting( final String name ) throws IOException { final File file = new File( name ); if ( file.exists() ) { @@ -298,127 +408,6 @@ public final class ForesterUtil { return file; } - final public static PhylogenyParser createParserDependingFileContents( final File file, - final boolean phyloxml_validate_against_xsd ) - throws FileNotFoundException, IOException { - PhylogenyParser parser = null; - final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase(); - if ( first_line.startsWith( "<" ) ) { - parser = new PhyloXmlParser(); - if ( phyloxml_validate_against_xsd ) { - final ClassLoader cl = PhyloXmlParser.class.getClassLoader(); - final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE ); - if ( xsd_url != null ) { - ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() ); - } - else { - if ( ForesterConstants.RELEASE ) { - throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from [" - + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" ); - } - } - } - } - else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) ) - || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) { - parser = new NexusPhylogeniesParser(); - } - else { - parser = new NHXParser(); - } - return parser; - } - - final public static PhylogenyParser createParserDependingOnFileType( final File file, - final boolean phyloxml_validate_against_xsd ) - throws FileNotFoundException, IOException { - PhylogenyParser parser = null; - parser = createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd ); - if ( parser == null ) { - parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd ); - } - return parser; - } - - /** - * Return null if it can not guess the parser to use based on name suffix. - * - * @param filename - * @return - */ - final public static PhylogenyParser createParserDependingOnSuffix( final String filename, - final boolean phyloxml_validate_against_xsd ) { - PhylogenyParser parser = null; - final String filename_lc = filename.toLowerCase(); - if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) { - parser = new TolParser(); - } - else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( ".px" ) || filename_lc.endsWith( "phyloxml" ) - || filename_lc.endsWith( ".zip" ) ) { - parser = new PhyloXmlParser(); - if ( phyloxml_validate_against_xsd ) { - final ClassLoader cl = PhyloXmlParser.class.getClassLoader(); - final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE ); - if ( xsd_url != null ) { - ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() ); - } - else { - if ( ForesterConstants.RELEASE ) { - throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from [" - + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" ); - } - } - } - } - else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) { - parser = new NexusPhylogeniesParser(); - } - else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" ) ) { - parser = new NHXParser(); - } - return parser; - } - - final public static PhylogenyParser createParserDependingOnUrlContents( final URL url, - final boolean phyloxml_validate_against_xsd ) - throws FileNotFoundException, IOException { - final String lc_filename = url.getFile().toString().toLowerCase(); - PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd ); - if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) { - if ( parser instanceof PhyloXmlParser ) { - ( ( PhyloXmlParser ) parser ).setZippedInputstream( true ); - } - else if ( parser instanceof TolParser ) { - ( ( TolParser ) parser ).setZippedInputstream( true ); - } - } - if ( parser == null ) { - final String first_line = getFirstLine( url ).trim().toLowerCase(); - if ( first_line.startsWith( "<" ) ) { - parser = new PhyloXmlParser(); - if ( phyloxml_validate_against_xsd ) { - final ClassLoader cl = PhyloXmlParser.class.getClassLoader(); - final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE ); - if ( xsd_url != null ) { - ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() ); - } - else { - throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from [" - + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" ); - } - } - } - else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) ) - || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) { - parser = new NexusPhylogeniesParser(); - } - else { - parser = new NHXParser(); - } - } - return parser; - } - final public static void ensurePresenceOfDate( final PhylogenyNode node ) { if ( !node.getNodeData().isHasDate() ) { node.getNodeData().setDate( new org.forester.phylogeny.data.Date() ); @@ -443,56 +432,11 @@ public final class ForesterUtil { } } - /** - * Extracts a code if and only if: - * one and only one _, - * shorter than 25, - * no |, - * no ., - * if / present it has to be after the _, - * if PFAM_STYLE_ONLY: / must be present, - * tax code can only contain uppercase letters and numbers, - * and must contain at least one uppercase letter. - * Return null if no code extractable. - * - * @param name - * @param limit_to_five - * @return - */ - public static String extractTaxonomyCodeFromNodeName( final String name, - final boolean limit_to_five, - final ForesterUtil.TAXONOMY_EXTRACTION taxonomy_extraction ) { - if ( ( name.indexOf( "_" ) > 0 ) - && ( name.length() < 25 ) - && ( name.lastIndexOf( "_" ) == name.indexOf( "_" ) ) - && ( name.indexOf( "|" ) < 0 ) - && ( name.indexOf( "." ) < 0 ) - && ( ( taxonomy_extraction != ForesterUtil.TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) || ( name - .indexOf( "/" ) >= 0 ) ) - && ( ( ( name.indexOf( "/" ) ) < 0 ) || ( name.indexOf( "/" ) > name.indexOf( "_" ) ) ) ) { - final String[] s = name.split( "[_/]" ); - if ( s.length > 1 ) { - String str = s[ 1 ]; - if ( limit_to_five ) { - if ( str.length() > 5 ) { - str = str.substring( 0, 5 ); - } - else if ( ( str.length() < 5 ) && ( str.startsWith( "RAT" ) || str.startsWith( "PIG" ) ) ) { - str = str.substring( 0, 3 ); - } - } - final Matcher letters_and_numbers = NHXParser.UC_LETTERS_NUMBERS_PATTERN.matcher( str ); - if ( !letters_and_numbers.matches() ) { - return null; - } - final Matcher numbers_only = NHXParser.NUMBERS_ONLY_PATTERN.matcher( str ); - if ( numbers_only.matches() ) { - return null; - } - return str; - } - } - return null; + public static void fatalError( final String message ) { + System.err.println(); + System.err.println( "error: " + message ); + System.err.println(); + System.exit( -1 ); } public static void fatalError( final String prg_name, final String message ) { @@ -502,6 +446,26 @@ public final class ForesterUtil { System.exit( -1 ); } + public static void fatalErrorIfFileNotReadable( final File file ) { + final String error = isReadableFile( file ); + if ( !isEmpty( error ) ) { + System.err.println(); + System.err.println( "error: " + error ); + System.err.println(); + System.exit( -1 ); + } + } + + public static void fatalErrorIfFileNotReadable( final String prg_name, final File file ) { + final String error = isReadableFile( file ); + if ( !isEmpty( error ) ) { + System.err.println(); + System.err.println( "[" + prg_name + "] > " + error ); + System.err.println(); + System.exit( -1 ); + } + } + public static String[] file2array( final File file ) throws IOException { final List list = file2list( file ); final String[] ary = new String[ list.size() ]; @@ -599,29 +563,12 @@ public final class ForesterUtil { return line; } - final public static String getLineSeparator() { - return ForesterUtil.LINE_SEPARATOR; + final public static String getForesterLibraryInformation() { + return "forester " + ForesterConstants.FORESTER_VERSION + " (" + ForesterConstants.FORESTER_DATE + ")"; } - /** - * Returns all custom data tag names of this Phylogeny as Hashtable. Tag - * names are keys, values are Boolean set to false. - */ - final public static Hashtable getPropertyRefs( final Phylogeny phylogeny ) { - final Hashtable ht = new Hashtable(); - if ( phylogeny.isEmpty() ) { - return ht; - } - for( final PhylogenyNodeIterator iter = phylogeny.iteratorPreorder(); iter.hasNext(); ) { - final PhylogenyNode current_node = iter.next(); - if ( current_node.getNodeData().isHasProperties() ) { - final String[] tags = current_node.getNodeData().getProperties().getPropertyRefs(); - for( int i = 0; i < tags.length; ++i ) { - ht.put( tags[ i ], new Boolean( false ) ); - } - } - } - return ht; + final public static String getLineSeparator() { + return ForesterUtil.LINE_SEPARATOR; } final public static void increaseCountingMap( final Map counting_map, final String item_name ) { @@ -633,28 +580,6 @@ public final class ForesterUtil { } } - final static public boolean isAllNonEmptyInternalLabelsArePositiveNumbers( final Phylogeny phy ) { - final PhylogenyNodeIterator it = phy.iteratorPostorder(); - while ( it.hasNext() ) { - final PhylogenyNode n = it.next(); - if ( !n.isRoot() && !n.isExternal() ) { - if ( !ForesterUtil.isEmpty( n.getName() ) ) { - double d = -1.0; - try { - d = Double.parseDouble( n.getName() ); - } - catch ( final Exception e ) { - d = -1.0; - } - if ( d < 0.0 ) { - return false; - } - } - } - } - return true; - } - final public static boolean isContainsParanthesesableNhCharacter( final String nh ) { return PARANTHESESABLE_NH_CHARS_PATTERN.matcher( nh ).find(); } @@ -692,43 +617,7 @@ public final class ForesterUtil { } final public static boolean isEven( final int n ) { - return n % 2 == 0; - } - - final static public boolean isHasAtLeastNodeWithEvent( final Phylogeny phy ) { - final PhylogenyNodeIterator it = phy.iteratorPostorder(); - while ( it.hasNext() ) { - if ( it.next().getNodeData().isHasEvent() ) { - return true; - } - } - return false; - } - - /** - * Returns true if at least one branch has a length larger than zero. - * - * - * @param phy - */ - final static public boolean isHasAtLeastOneBranchLengthLargerThanZero( final Phylogeny phy ) { - final PhylogenyNodeIterator it = phy.iteratorPostorder(); - while ( it.hasNext() ) { - if ( it.next().getDistanceToParent() > 0.0 ) { - return true; - } - } - return false; - } - - final static public boolean isHasAtLeastOneBranchWithSupportValues( final Phylogeny phy ) { - final PhylogenyNodeIterator it = phy.iteratorPostorder(); - while ( it.hasNext() ) { - if ( it.next().getBranchData().isHasConfidences() ) { - return true; - } - } - return false; + return ( n % 2 ) == 0; } /** @@ -748,10 +637,9 @@ public final class ForesterUtil { if ( ( a.length < 1 ) || ( b.length < 1 ) ) { return false; } - for( int i = 0; i < a.length; ++i ) { - final String ai = a[ i ]; - for( int j = 0; j < b.length; ++j ) { - if ( ( ai != null ) && ( b[ j ] != null ) && ai.equals( b[ j ] ) ) { + for( final String ai : a ) { + for( final String element : b ) { + if ( ( ai != null ) && ( element != null ) && ai.equals( element ) ) { return true; } } @@ -795,6 +683,10 @@ public final class ForesterUtil { return isReadableFile( new File( s ) ); } + public static boolean isWindowns() { + return ForesterUtil.OS_NAME.toLowerCase().indexOf( "win" ) > -1; + } + final public static String isWritableFile( final File f ) { if ( f.isDirectory() ) { return "[" + f + "] is a directory"; @@ -833,6 +725,33 @@ public final class ForesterUtil { return map; } + final public static void map2file( final File file, + final Map data, + final String entry_separator, + final String data_separator ) throws IOException { + final Writer writer = new BufferedWriter( new FileWriter( file ) ); + map2writer( writer, data, entry_separator, data_separator ); + writer.close(); + } + + final public static void map2writer( final Writer writer, + final Map data, + final String entry_separator, + final String data_separator ) throws IOException { + boolean first = true; + for( final Entry entry : data.entrySet() ) { + if ( !first ) { + writer.write( data_separator ); + } + else { + first = false; + } + writer.write( entry.getKey().toString() ); + writer.write( entry_separator ); + writer.write( entry.getValue().toString() ); + } + } + 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(); ) { @@ -939,16 +858,6 @@ public final class ForesterUtil { return Integer.parseInt( str ); } - final public static void postOrderRelabelInternalNodes( final Phylogeny phylogeny, final int starting_number ) { - int i = starting_number; - for( final PhylogenyNodeIterator it = phylogeny.iteratorPostorder(); it.hasNext(); ) { - final PhylogenyNode node = it.next(); - if ( !node.isExternal() ) { - node.setName( String.valueOf( i++ ) ); - } - } - } - final public static void printArray( final Object[] a ) { for( int i = 0; i < a.length; ++i ) { System.out.println( "[" + i + "]=" + a[ i ] ); @@ -962,7 +871,7 @@ public final class ForesterUtil { } final public static void printErrorMessage( final String prg_name, final String message ) { - System.out.println( "[" + prg_name + "] > error: " + message ); + System.err.println( "[" + prg_name + "] > error: " + message ); } final public static void printProgramInformation( final String prg_name, final String prg_version, final String date ) { @@ -980,16 +889,33 @@ public final class ForesterUtil { final String date, final String email, final String www ) { - final int l = prg_name.length() + prg_version.length() + date.length() + 4; + printProgramInformation( prg_name, null, prg_version, date, email, www, null ); + } + + final public static void printProgramInformation( final String prg_name, + final String desc, + final String prg_version, + final String date, + final String email, + final String www, + final String based_on ) { + String my_prg_name = new String( prg_name ); + if ( !ForesterUtil.isEmpty( desc ) ) { + my_prg_name += ( " - " + desc ); + } + final int l = my_prg_name.length() + prg_version.length() + date.length() + 4; System.out.println(); - System.out.println( prg_name + " " + prg_version + " (" + date + ")" ); + System.out.println( my_prg_name + " " + prg_version + " (" + date + ")" ); for( int i = 0; i < l; ++i ) { System.out.print( "_" ); } System.out.println(); System.out.println(); - System.out.println( "WWW : " + www ); - System.out.println( "Contact: " + email ); + System.out.println( "WWW : " + www ); + System.out.println( "Contact : " + email ); + if ( !ForesterUtil.isEmpty( based_on ) ) { + System.out.println( "Based on: " + based_on ); + } if ( !ForesterUtil.isEmpty( ForesterUtil.JAVA_VERSION ) && !ForesterUtil.isEmpty( ForesterUtil.JAVA_VENDOR ) ) { System.out.println(); System.out.println( "[running on Java " + ForesterUtil.JAVA_VERSION + " " + ForesterUtil.JAVA_VENDOR + "]" ); @@ -1005,15 +931,6 @@ public final class ForesterUtil { System.out.println( "[" + prg_name + "] > " + message ); } - public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final File file ) throws IOException { - final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); - final Phylogeny[] trees = factory.create( file, parser ); - if ( ( trees == null ) || ( trees.length == 0 ) ) { - throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file ); - } - return trees; - } - final public static String removeSuffix( final String file_name ) { final int i = file_name.lastIndexOf( '.' ); if ( i > 1 ) { @@ -1029,7 +946,7 @@ public final class ForesterUtil { */ final public static String removeWhiteSpace( String s ) { int i; - for( i = 0; i <= s.length() - 1; i++ ) { + for( i = 0; i <= ( s.length() - 1 ); i++ ) { if ( ( s.charAt( i ) == ' ' ) || ( s.charAt( i ) == '\t' ) || ( s.charAt( i ) == '\n' ) || ( s.charAt( i ) == '\r' ) ) { s = s.substring( 0, i ) + s.substring( i + 1 ); @@ -1083,15 +1000,25 @@ public final class ForesterUtil { } } - final private static String[] splitString( final String str ) { - final String regex = "[\\s;,]+"; - return str.split( regex ); + 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 ) + || ( seq.indexOf( 'q' ) > -1 ) || ( seq.indexOf( 'h' ) > -1 ) || ( seq.indexOf( 'k' ) > -1 ) + || ( seq.indexOf( 'w' ) > -1 ) || ( seq.indexOf( 's' ) > -1 ) || ( seq.indexOf( 'm' ) > -1 ) + || ( seq.indexOf( 'p' ) > -1 ) || ( seq.indexOf( 'v' ) > -1 ) ) { + return true; + } + return false; + } + + final public static String stringArrayToString( final String[] a ) { + return stringArrayToString( a, ", " ); } final public static String stringArrayToString( final String[] a, final String separator ) { final StringBuilder sb = new StringBuilder(); if ( ( a != null ) && ( a.length > 0 ) ) { - for( int i = 0; i < a.length - 1; ++i ) { + for( int i = 0; i < ( a.length - 1 ); ++i ) { sb.append( a[ i ] + separator ); } sb.append( a[ a.length - 1 ] ); @@ -1099,10 +1026,22 @@ public final class ForesterUtil { return sb.toString(); } + final public static String[] stringListToArray( final List list ) { + if ( list != null ) { + final String[] str = new String[ list.size() ]; + int i = 0; + for( final String l : list ) { + str[ i++ ] = l; + } + return str; + } + return null; + } + final public static String stringListToString( final List l, final String separator ) { final StringBuilder sb = new StringBuilder(); if ( ( l != null ) && ( l.size() > 0 ) ) { - for( int i = 0; i < l.size() - 1; ++i ) { + for( int i = 0; i < ( l.size() - 1 ); ++i ) { sb.append( l.get( i ) + separator ); } sb.append( l.get( l.size() - 1 ) ); @@ -1110,10 +1049,6 @@ public final class ForesterUtil { return sb.toString(); } - final public static String stringArrayToString( final String[] a ) { - return stringArrayToString( a, ", " ); - } - final public static String[] stringSetToArray( final Set strings ) { final String[] str_array = new String[ strings.size() ]; int i = 0; @@ -1123,151 +1058,34 @@ public final class ForesterUtil { return str_array; } - final public static String[] stringListToArray( final List list ) { - if ( list != null ) { - final String[] str = new String[ list.size() ]; - int i = 0; - for( final String l : list ) { - str[ i++ ] = l; - } - return str; - } - return null; - } - - final static public void transferInternalNamesToBootstrapSupport( final Phylogeny phy ) { - final PhylogenyNodeIterator it = phy.iteratorPostorder(); - while ( it.hasNext() ) { - final PhylogenyNode n = it.next(); - if ( !n.isExternal() && !ForesterUtil.isEmpty( n.getName() ) ) { - double value = -1; - try { - value = Double.parseDouble( n.getName() ); - } - catch ( final NumberFormatException e ) { - throw new IllegalArgumentException( "failed to parse number from [" + n.getName() + "]: " - + e.getLocalizedMessage() ); - } - if ( value >= 0.0 ) { - n.getBranchData().addConfidence( new Confidence( value, "bootstrap" ) ); - n.setName( "" ); - } - } - } + final public static void unexpectedFatalError( final Exception e ) { + System.err.println(); + System.err.println( "unexpected exception: should not have occured! Please contact program author(s)." ); + e.printStackTrace( System.err ); + System.err.println(); + System.exit( -1 ); } - final static public void transferInternalNodeNamesToConfidence( final Phylogeny phy ) { - final PhylogenyNodeIterator it = phy.iteratorPostorder(); - while ( it.hasNext() ) { - final PhylogenyNode n = it.next(); - if ( !n.isRoot() && !n.isExternal() && !n.getBranchData().isHasConfidences() ) { - if ( !ForesterUtil.isEmpty( n.getName() ) ) { - double d = -1.0; - try { - d = Double.parseDouble( n.getName() ); - } - catch ( final Exception e ) { - d = -1.0; - } - if ( d >= 0.0 ) { - n.getBranchData().addConfidence( new Confidence( d, "" ) ); - n.setName( "" ); - } - } - } - } + final public static void unexpectedFatalError( final Error e ) { + System.err.println(); + 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 static public void transferNodeNameToField( final Phylogeny phy, final PhylogenyNodeField field ) { - final PhylogenyNodeIterator it = phy.iteratorPostorder(); - while ( it.hasNext() ) { - final PhylogenyNode n = it.next(); - final String name = n.getName().trim(); - if ( !ForesterUtil.isEmpty( name ) ) { - switch ( field ) { - case TAXONOMY_CODE: - //temp hack - // if ( name.length() > 5 ) { - // n.setName( "" ); - // if ( !n.getNodeData().isHasTaxonomy() ) { - // n.getNodeData().setTaxonomy( new Taxonomy() ); - // } - // n.getNodeData().getTaxonomy().setScientificName( name ); - // break; - // } - // - n.setName( "" ); - PhylogenyMethods.setTaxonomyCode( n, name ); - break; - case TAXONOMY_SCIENTIFIC_NAME: - n.setName( "" ); - if ( !n.getNodeData().isHasTaxonomy() ) { - n.getNodeData().setTaxonomy( new Taxonomy() ); - } - n.getNodeData().getTaxonomy().setScientificName( name ); - break; - case TAXONOMY_COMMON_NAME: - n.setName( "" ); - if ( !n.getNodeData().isHasTaxonomy() ) { - n.getNodeData().setTaxonomy( new Taxonomy() ); - } - n.getNodeData().getTaxonomy().setCommonName( name ); - break; - case SEQUENCE_SYMBOL: - n.setName( "" ); - if ( !n.getNodeData().isHasSequence() ) { - n.getNodeData().setSequence( new Sequence() ); - } - n.getNodeData().getSequence().setSymbol( name ); - break; - case SEQUENCE_NAME: - n.setName( "" ); - if ( !n.getNodeData().isHasSequence() ) { - n.getNodeData().setSequence( new Sequence() ); - } - n.getNodeData().getSequence().setName( name ); - break; - case TAXONOMY_ID_UNIPROT_1: { - if ( !n.getNodeData().isHasTaxonomy() ) { - n.getNodeData().setTaxonomy( new Taxonomy() ); - } - String id = name; - final int i = name.indexOf( '_' ); - if ( i > 0 ) { - id = name.substring( 0, i ); - } - else { - n.setName( "" ); - } - n.getNodeData().getTaxonomy() - .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) ); - break; - } - case TAXONOMY_ID_UNIPROT_2: { - if ( !n.getNodeData().isHasTaxonomy() ) { - n.getNodeData().setTaxonomy( new Taxonomy() ); - } - String id = name; - final int i = name.indexOf( '_' ); - if ( i > 0 ) { - id = name.substring( i + 1, name.length() ); - } - else { - n.setName( "" ); - } - n.getNodeData().getTaxonomy() - .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) ); - break; - } - } - } - } + final public static void unexpectedFatalError( final String message ) { + System.err.println(); + System.err.println( "unexpected error: should not have occured! Please contact program author(s)." ); + System.err.println( message ); + System.err.println(); + System.exit( -1 ); } final public static void unexpectedFatalError( final String prg_name, final Exception e ) { System.err.println(); System.err.println( "[" + prg_name - + "] > unexpected error (Should not have occured! Please contact program author(s).)" ); + + "] > unexpected error; should not have occured! Please contact program author(s)." ); e.printStackTrace( System.err ); System.err.println(); System.exit( -1 ); @@ -1276,7 +1094,7 @@ public final class ForesterUtil { final public static void unexpectedFatalError( final String prg_name, final String message ) { System.err.println(); System.err.println( "[" + prg_name - + "] > unexpected error. Should not have occured! Please contact program author(s)." ); + + "] > unexpected error: should not have occured! Please contact program author(s)." ); System.err.println( message ); System.err.println(); System.exit( -1 ); @@ -1285,13 +1103,30 @@ public final class ForesterUtil { final public static void unexpectedFatalError( final String prg_name, final String message, final Exception e ) { System.err.println(); System.err.println( "[" + prg_name - + "] > unexpected error. Should not have occured! Please contact program author(s)." ); + + "] > unexpected error: should not have occured! Please contact program author(s)." ); System.err.println( message ); e.printStackTrace( System.err ); System.err.println(); System.exit( -1 ); } + public final static void updateProgress( final double progress_percentage ) { + final int width = 50; + System.out.print( "\r[" ); + int i = 0; + for( ; i <= ForesterUtil.roundToInt( progress_percentage * width ); i++ ) { + System.out.print( "." ); + } + for( ; i < width; i++ ) { + System.out.print( " " ); + } + 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; @@ -1305,7 +1140,7 @@ public final class ForesterUtil { ls = -1; start = i + 1; } - if ( i > start + width - 1 ) { + if ( i > ( ( start + width ) - 1 ) ) { if ( ls != -1 ) { sb.setCharAt( ls, '\n' ); start = ls + 1; @@ -1321,18 +1156,50 @@ public final class ForesterUtil { return sb.toString(); } - public static enum PhylogenyNodeField { - CLADE_NAME, - TAXONOMY_CODE, - TAXONOMY_SCIENTIFIC_NAME, - TAXONOMY_COMMON_NAME, - SEQUENCE_SYMBOL, - SEQUENCE_NAME, - TAXONOMY_ID_UNIPROT_1, - TAXONOMY_ID_UNIPROT_2; + /** + * Helper method for calcColor methods. + * + * @param smallercolor_component_x + * color component the smaller color + * @param largercolor_component_x + * color component the larger color + * @param x + * factor + * @return an int representing a color component + */ + final private static int calculateColorComponent( final double smallercolor_component_x, + final double largercolor_component_x, + final double x ) { + return ( int ) ( smallercolor_component_x + ( ( x * ( largercolor_component_x - smallercolor_component_x ) ) / 255.0 ) ); + } + + /** + * Helper method for calcColor methods. + * + * + * @param value + * the value + * @param larger + * the largest value + * @param smaller + * the smallest value + * @return a normalized value between larger and smaller + */ + final private static double calculateColorFactor( final double value, final double larger, final double smaller ) { + return ( 255.0 * ( value - smaller ) ) / ( larger - smaller ); + } + + final private static String[] splitString( final String str ) { + final String regex = "[\\s;,]+"; + return str.split( regex ); } - public static enum TAXONOMY_EXTRACTION { - NO, YES, PFAM_STYLE_ONLY; + 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 ); } }