import java.io.Writer;
import java.math.BigDecimal;
import java.net.URL;
+import java.net.URLConnection;
+import java.security.KeyManagementException;
+import java.security.NoSuchAlgorithmException;
import java.text.DateFormat;
import java.text.DecimalFormat;
import java.text.DecimalFormatSymbols;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
-import org.forester.archaeopteryx.Constants;
+import org.forester.archaeopteryx.AptxConstants;
+import org.forester.io.parsers.PhylogenyParser;
+import org.forester.phylogeny.Phylogeny;
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.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.protein.BasicProtein;
import org.forester.protein.Domain;
import org.forester.protein.Protein;
+import org.forester.sequence.MolecularSequence;
+import org.forester.sequence.MolecularSequence.TYPE;
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 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;
- 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 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 static final String NCBI_GI = "http://www.ncbi.nlm.nih.gov/protein/gi:";
+ public final static double ZERO_DIFF = 1.0E-9;
+ private static final Pattern PARANTHESESABLE_NH_CHARS_PATTERN = Pattern.compile( "[(),;\\s:\\[\\]]" );
static {
final DecimalFormatSymbols dfs = new DecimalFormatSymbols();
dfs.setDecimalSeparator( '.' );
FORMATTER_3 = new DecimalFormat( "#.###", dfs );
}
- private ForesterUtil() {
- }
-
- public static int calculateOverlap( final Domain domain, final List<Boolean> 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 void appendSeparatorIfNotEmpty( final StringBuffer sb, final char separator ) {
if ( sb.length() > 0 ) {
sb.append( separator );
}
}
- /**
- *
- * 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<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
- final List<Boolean> covered_positions = new ArrayList<Boolean>();
- 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;
- }
-
- /**
- * 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<Boolean> covered_positions ) {
- for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
- if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) {
- return false;
- }
+ final public static String removeFileExtension( final String file_name ) {
+ if ( file_name.indexOf( "." ) > 0 ) {
+ return file_name.substring( 0, file_name.lastIndexOf( "." ) );
}
- return true;
+ return file_name;
}
/**
* This calculates a color. If value is equal to min the returned color is
* minColor, if value is equal to max the returned color is maxColor,
* otherwise a color 'proportional' to value is returned.
- *
+ *
* @param value
- * the value
+ * the value
* @param min
- * the smallest value
+ * the smallest value
* @param max
- * the largest value
+ * the largest value
* @param minColor
* the color for min
* @param maxColor
* value is equal to mean the returned color is meanColor, otherwise a color
* 'proportional' to value is returned -- either between min-mean or
* mean-max
- *
+ *
* @param value
* the value
* @param min
* the smallest value
* @param max
- * the largest value
+ * the largest value
* @param mean
- * the mean/median value
+ * the mean/median value
* @param minColor
* the color for min
* @param maxColor
}
}
+ /**
+ * 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 );
+ }
+
+ public static int calculateOverlap( final Domain domain, final List<Boolean> 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]+", " " );
}
}
}
- public static String[] file2array( final File file ) throws IOException {
- final List<String> list = file2list( file );
- final String[] ary = new String[ list.size() ];
- int i = 0;
- for( final String s : list ) {
- ary[ i++ ] = s;
- }
- return ary;
- }
-
public static String[][] file22dArray( final File file ) throws IOException {
final List<String> list = new ArrayList<String>();
final BufferedReader in = new BufferedReader( new FileReader( file ) );
return ary;
}
+ public static String[] file2array( final File file ) throws IOException {
+ final List<String> list = file2list( file );
+ final String[] ary = new String[ list.size() ];
+ int i = 0;
+ for( final String s : list ) {
+ ary[ i++ ] = s;
+ }
+ return ary;
+ }
+
final public static List<String> file2list( final File file ) throws IOException {
final List<String> list = new ArrayList<String>();
final BufferedReader in = new BufferedReader( new FileReader( file ) );
reader = new BufferedReader( new StringReader( source.toString() ) );
}
else if ( source instanceof URL ) {
- reader = new BufferedReader( new InputStreamReader( ( ( URL ) source ).openStream() ) );
+ final URLConnection url_connection = ( ( URL ) source ).openConnection();
+ url_connection.setDefaultUseCaches( false );
+ reader = new BufferedReader( new InputStreamReader( url_connection.getInputStream() ) );
}
else {
throw new IllegalArgumentException( "dont know how to read [" + source.getClass() + "]" );
return ForesterUtil.LINE_SEPARATOR;
}
+ final public static MolecularSequence.TYPE guessMolecularSequenceType( final String mol_seq ) {
+ if ( mol_seq.contains( "L" ) || mol_seq.contains( "I" ) || mol_seq.contains( "E" ) || mol_seq.contains( "H" )
+ || mol_seq.contains( "D" ) || mol_seq.contains( "Q" ) ) {
+ return TYPE.AA;
+ }
+ else {
+ if ( mol_seq.contains( "T" ) ) {
+ return TYPE.DNA;
+ }
+ else if ( mol_seq.contains( "U" ) ) {
+ return TYPE.RNA;
+ }
+ }
+ return null;
+ }
+
final public static void increaseCountingMap( final Map<String, Integer> counting_map, final String item_name ) {
if ( !counting_map.containsKey( item_name ) ) {
counting_map.put( item_name, 1 );
}
}
- 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;
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<Boolean> 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 );
}
* This determines whether String[] a and String[] b have at least one
* String in common (intersect). Returns false if at least one String[] is
* null or empty.
- *
+ *
* @param a
* a String[] b a String[]
* @return true if both a and b or not empty or null and contain at least
}
}
+ public final static boolean isMac() {
+ try {
+ return OS_NAME.toLowerCase().startsWith( "mac" );
+ }
+ catch ( final Exception e ) {
+ ForesterUtil.printWarningMessage( AptxConstants.PRG_NAME, "minor error: " + e );
+ return false;
+ }
+ }
+
final public static boolean isNull( final BigDecimal s ) {
return ( ( s == null ) || ( s.compareTo( NULL_BD ) == 0 ) );
}
return OS_NAME.toLowerCase().indexOf( "win" ) > -1;
}
catch ( final Exception e ) {
- ForesterUtil.printWarningMessage( Constants.PRG_NAME, "minor error: " + e );
- return false;
- }
- }
-
- public final static boolean isMac() {
- try {
- return OS_NAME.toLowerCase().startsWith( "mac" );
- }
- catch ( final Exception e ) {
- ForesterUtil.printWarningMessage( Constants.PRG_NAME, "minor error: " + e );
+ ForesterUtil.printWarningMessage( AptxConstants.PRG_NAME, "minor error: " + e );
return false;
}
}
final public static void map2file( final File file,
final Map<?, ?> data,
final String entry_separator,
- final String data_separator ) throws IOException {
+ 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 {
+ final String data_separator )
+ throws IOException {
boolean first = true;
for( final Entry<?, ?> entry : data.entrySet() ) {
if ( !first ) {
}
}
- final public static StringBuffer mapToStringBuffer( final Map<Object, Object> map, final String key_value_separator ) {
+ final public static StringBuffer mapToStringBuffer( final Map<Object, Object> map,
+ final String key_value_separator ) {
final StringBuffer sb = new StringBuffer();
for( final Object key : map.keySet() ) {
sb.append( key.toString() );
}
}
+ 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;
+ }
+ else if ( tax_group.equals( TaxonomyGroups.VIRUSES ) ) {
+ return TaxonomyColors.VIRUSES_COLOR;
+ }
+ else if ( tax_group.equals( TaxonomyGroups.ALPHAHERPESVIRINAE ) ) {
+ return TaxonomyColors.ALPHAHERPESVIRINAE_COLOR;
+ }
+ else if ( tax_group.equals( TaxonomyGroups.BETAHERPESVIRINAE ) ) {
+ return TaxonomyColors.BETAHERPESVIRINAE_COLOR;
+ }
+ else if ( tax_group.equals( TaxonomyGroups.GAMMAHERPESVIRINAE ) ) {
+ return TaxonomyColors.GAMMAHERPESVIRINAE_COLOR;
+ }
+ else if ( tax_group.equals( TaxonomyGroups.OTHER ) ) {
+ return TaxonomyColors.OTHER_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;
+ }
+ else if ( tax.equalsIgnoreCase( TaxonomyGroups.BACTERIA ) ) {
+ return TaxonomyGroups.BACTERIA;
+ }
+ else if ( tax.equalsIgnoreCase( TaxonomyGroups.VIRUSES ) ) {
+ return TaxonomyGroups.VIRUSES;
+ }
+ else if ( tax.equalsIgnoreCase( TaxonomyGroups.ALPHAHERPESVIRINAE ) ) {
+ return TaxonomyGroups.ALPHAHERPESVIRINAE;
+ }
+ else if ( tax.equalsIgnoreCase( TaxonomyGroups.BETAHERPESVIRINAE ) ) {
+ return TaxonomyGroups.BETAHERPESVIRINAE;
+ }
+ else if ( tax.equalsIgnoreCase( TaxonomyGroups.GAMMAHERPESVIRINAE ) ) {
+ return TaxonomyGroups.GAMMAHERPESVIRINAE;
+ }
+ return null;
+ }
+
final public static BufferedReader obtainReader( final Object source ) throws IOException, FileNotFoundException {
BufferedReader reader = null;
if ( source instanceof File ) {
return reader;
}
- final public static StringBuffer pad( final double number, final int size, final char pad, final boolean left_pad ) {
+ 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 );
}
- final public static StringBuffer pad( final String string, final int size, final char pad, final boolean left_pad ) {
+ final public static StringBuffer pad( final String string,
+ final int size,
+ final char pad,
+ final boolean left_pad ) {
return pad( new StringBuffer( string ), size, pad, left_pad );
}
System.err.println( "[" + prg_name + "] > error: " + message );
}
- final public static void printProgramInformation( final String prg_name, final String prg_version, final String date ) {
+ final public static void printProgramInformation( final String prg_name,
+ final String prg_version,
+ final String date ) {
final int l = prg_name.length() + prg_version.length() + date.length() + 4;
System.out.println();
System.out.println( prg_name + " " + prg_version + " (" + date + ")" );
}
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 + "]" );
+ System.out
+ .println( "[running on Java " + ForesterUtil.JAVA_VERSION + " " + ForesterUtil.JAVA_VENDOR + "]" );
}
System.out.println();
}
System.out.println( "[" + prg_name + "] > " + message );
}
+ public static List<String> readUrl( final String url_str ) throws IOException {
+ final URL url = new URL( url_str );
+ final URLConnection urlc = url.openConnection();
+ //urlc.setRequestProperty( "User-Agent", "" );
+ final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
+ String line;
+ final List<String> result = new ArrayList<String>();
+ while ( ( line = in.readLine() ) != null ) {
+ result.add( line );
+ }
+ in.close();
+ return result;
+ }
+
+ /**
+ *
+ * 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<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
+ final List<Boolean> covered_positions = new ArrayList<Boolean>();
+ 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 ) {
/**
* Removes all white space from String s.
- *
+ *
* @return String s with white space removed
*/
final public static String removeWhiteSpace( String s ) {
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 ) {
}
}
+ 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 )
return false;
}
+ final private static String[] splitString( final String str ) {
+ final String regex = "[\\s;,]+";
+ return str.split( regex );
+ }
+
final public static String stringArrayToString( final String[] a ) {
return stringArrayToString( a, ", " );
}
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 );
return sb.toString();
}
- /**
- * 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 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 );
- }
-
- public final static Color obtainColorDependingOnTaxonomyGroup( final String tax_group ) {
- if ( !ForesterUtil.isEmpty( tax_group ) ) {
- if ( tax_group.equals( "deuterostomia" ) ) {
- return TaxonomyColors.DEUTEROSTOMIA_COLOR;
- }
- else if ( tax_group.equals( "protostomia" ) ) {
- return TaxonomyColors.PROTOSTOMIA_COLOR;
- }
- else if ( tax_group.equals( "cnidaria" ) ) {
- return TaxonomyColors.CNIDARIA_COLOR;
- }
- else if ( tax_group.equals( "placozoa" ) ) {
- return TaxonomyColors.PLACOZOA_COLOR;
- }
- else if ( tax_group.equals( "ctenophora" ) ) {
- return TaxonomyColors.CTENOPHORA_COLOR;
- }
- else if ( tax_group.equals( "porifera" ) ) {
- return TaxonomyColors.PORIFERA_COLOR;
- }
- else if ( tax_group.equals( "choanoflagellida" ) ) {
- return TaxonomyColors.CHOANOFLAGELLIDA;
- }
- else if ( tax_group.equals( "ichthyophonida & filasterea" ) ) {
- return TaxonomyColors.ICHTHYOSPOREA_AND_FILASTEREA;
- }
- else if ( tax_group.equals( "dikarya" ) ) {
- return TaxonomyColors.DIKARYA_COLOR;
- }
- else if ( tax_group.equalsIgnoreCase( "fungi" ) || tax_group.equalsIgnoreCase( "other fungi" ) ) {
- return TaxonomyColors.OTHER_FUNGI_COLOR;
- }
- else if ( tax_group.equals( "nucleariidae and fonticula" ) ) {
- return TaxonomyColors.NUCLEARIIDAE_AND_FONTICULA_GROUP_COLOR;
- }
- else if ( tax_group.equals( "amoebozoa" ) ) {
- return TaxonomyColors.AMOEBOZOA_COLOR;
- }
- else if ( tax_group.equals( "embryophyta" ) ) {
- return TaxonomyColors.EMBRYOPHYTA_COLOR;
- }
- else if ( tax_group.equals( "chlorophyta" ) ) {
- return TaxonomyColors.CHLOROPHYTA_COLOR;
- }
- else if ( tax_group.equals( "rhodophyta" ) ) {
- return TaxonomyColors.RHODOPHYTA_COLOR;
- }
- else if ( tax_group.equals( "hacrobia" ) ) {
- return TaxonomyColors.HACROBIA_COLOR;
- }
- else if ( tax_group.equals( "glaucocystophyceae" ) ) {
- return TaxonomyColors.GLAUCOPHYTA_COLOR;
- }
- else if ( tax_group.equals( "stramenopiles" ) ) {
- return TaxonomyColors.STRAMENOPILES_COLOR;
- }
- else if ( tax_group.equals( "alveolata" ) ) {
- return TaxonomyColors.ALVEOLATA_COLOR;
- }
- else if ( tax_group.equals( "rhizaria" ) ) {
- return TaxonomyColors.RHIZARIA_COLOR;
- }
- else if ( tax_group.equals( "excavata" ) ) {
- return TaxonomyColors.EXCAVATA_COLOR;
- }
- else if ( tax_group.equals( "apusozoa" ) ) {
- return TaxonomyColors.APUSOZOA_COLOR;
- }
- else if ( tax_group.equals( "archaea" ) ) {
- return TaxonomyColors.ARCHAEA_COLOR;
- }
- else if ( tax_group.equals( "bacteria" ) ) {
- return TaxonomyColors.BACTERIA_COLOR;
- }
- }
- return null;
- }
-
- public final static String obtainNormalizedTaxonomyGroup( final String tax ) {
- if ( tax.equalsIgnoreCase( "deuterostomia" ) ) {
- return "deuterostomia";
- }
- else if ( tax.equalsIgnoreCase( "protostomia" ) ) {
- return "protostomia";
- }
- else if ( tax.equalsIgnoreCase( "cnidaria" ) ) {
- return "cnidaria";
- }
- else if ( tax.toLowerCase().startsWith( "trichoplax" ) || tax.equalsIgnoreCase( "placozoa" ) ) {
- return "placozoa";
+ public final static Phylogeny[] readPhylogeniesFromUrl( final URL url, final PhylogenyParser parser )
+ throws NoSuchAlgorithmException, IOException, KeyManagementException {
+ if ( url == null ) {
+ throw new IllegalArgumentException( "URL to read from must not be null" );
}
- else if ( tax.toLowerCase().startsWith( "mnemiopsis" ) || tax.equalsIgnoreCase( "ctenophora" ) ) {
- return "ctenophora";
+ else if ( parser == null ) {
+ throw new IllegalArgumentException( "parser to use to read from URL must not be null" );
}
- else if ( tax.toLowerCase().startsWith( "amphimedon" ) || tax.equalsIgnoreCase( "porifera" ) ) {
- return "porifera";
+ final URLConnection con;
+ if ( url.toString().startsWith( "https:" ) ) {
+ con = TrustManager.makeHttpsURLConnection( url );
}
- else if ( tax.equalsIgnoreCase( "codonosigidae" ) || tax.equalsIgnoreCase( "choanoflagellida" ) ) {
- return "choanoflagellida";
- }
- else if ( tax.toLowerCase().startsWith( "ichthyophonida & filasterea" )
- || tax.toLowerCase().startsWith( "ichthyophonida and filasterea" )
- || tax.toLowerCase().startsWith( "ichthyosporea & filasterea" )
- || tax.toLowerCase().startsWith( "ichthyosporea and filasterea" ) ) {
- return "ichthyophonida & filasterea";
- }
- else if ( tax.equalsIgnoreCase( "dikarya" ) ) {
- return "dikarya";
- }
- else if ( tax.equalsIgnoreCase( "other fungi" ) ) {
- return "other fungi";
- }
- else if ( tax.toLowerCase().startsWith( "nucleariidae and fonticula" ) ) {
- return "nucleariidae and fonticula group";
+ else if ( url.toString().startsWith( "http:" ) ) {
+ con = url.openConnection();
}
- else if ( tax.equalsIgnoreCase( "amoebozoa" ) ) {
- return "amoebozoa";
- }
- else if ( tax.equalsIgnoreCase( "embryophyta" ) ) {
- return "embryophyta";
- }
- else if ( tax.equalsIgnoreCase( "chlorophyta" ) ) {
- return "chlorophyta";
- }
- else if ( tax.equalsIgnoreCase( "rhodophyta" ) ) {
- return "rhodophyta";
- }
- else if ( tax.toLowerCase().startsWith( "hacrobia" ) ) {
- return "hacrobia";
- }
- else if ( tax.equalsIgnoreCase( "glaucocystophyceae" ) || tax.equalsIgnoreCase( "glaucophyta" ) ) {
- return "glaucocystophyceae";
- }
- else if ( tax.equalsIgnoreCase( "stramenopiles" ) ) {
- return "stramenopiles";
- }
- else if ( tax.equalsIgnoreCase( "alveolata" ) ) {
- return "alveolata";
- }
- else if ( tax.equalsIgnoreCase( "rhizaria" ) ) {
- return "rhizaria";
+ else {
+ throw new IllegalArgumentException( "Cannot deal with URL: " + url );
}
- else if ( tax.equalsIgnoreCase( "excavata" ) ) {
- return "excavata";
+ if ( con == null ) {
+ throw new IOException( "could not create connection from " + url );
}
- else if ( tax.equalsIgnoreCase( "apusozoa" ) ) {
- return "apusozoa";
+ con.setDefaultUseCaches( false );
+ final InputStream is = con.getInputStream();
+ if ( is == null ) {
+ throw new IOException( "could not create input stream from " + url );
}
- else if ( tax.equalsIgnoreCase( "archaea" ) ) {
- return "archaea";
+ final Phylogeny[] trees = ParserBasedPhylogenyFactory.getInstance().create( is, parser );
+ try {
+ is.close();
}
- else if ( tax.equalsIgnoreCase( "bacteria" ) ) {
- return "bacteria";
+ catch ( final Exception e ) {
+ // ignore
}
- return null;
+ return trees;
+ }
+
+ private ForesterUtil() {
}
}
git://source.jalview.org / jalview.git / blobdiff