import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.FileWriter;
+import java.io.FilenameFilter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
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;
public final static String OS_VERSION = System.getProperty( "os.version" );
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 final static double ZERO_DIFF = 1.0E-12;
private static final Pattern PARANTHESESABLE_NH_CHARS_PATTERN = Pattern.compile( "[(),;\\s:\\[\\]]" );
static {
final DecimalFormatSymbols dfs = new DecimalFormatSymbols();
FORMATTER_3 = new DecimalFormat( "#.###", dfs );
}
- private ForesterUtil() {
- }
-
final public static void appendSeparatorIfNotEmpty( final StringBuffer sb, final char separator ) {
if ( sb.length() > 0 ) {
sb.append( separator );
}
}
+ final public static String removeFileExtension( final String file_name ) {
+ if ( file_name.indexOf( "." ) > 0 ) {
+ return file_name.substring( 0, file_name.lastIndexOf( "." ) );
+ }
+ 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 ) {
return ForesterUtil.LINE_SEPARATOR;
}
+ final public static MolecularSequence.TYPE guessMolecularSequenceType( final String mol_seq ) {
+ final String s = mol_seq.toUpperCase();
+ if ( s.contains( "L" ) || s.contains( "I" ) || s.contains( "E" ) || s.contains( "H" )
+ || s.contains( "D" ) || s.contains( "Q" ) ) {
+ return TYPE.AA;
+ }
+ else {
+ if ( s.contains( "T" ) ) {
+ return TYPE.DNA;
+ }
+ else if ( s.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 );
return ( ( s == null ) || ( s.length() < 1 ) );
}
+ final public static boolean isEmptyTrimmed( final String s ) {
+ if ( s == null ) {
+ return true;
+ }
+ return ( ( s.trim().length() < 1 ) );
+ }
+
/**
* Returns true is Domain domain falls in an uninterrupted stretch of
* covered positions.
- *
+ *
* @param domain
* @param covered_positions
* @return
return ( ( Math.abs( a - b ) ) < ZERO_DIFF );
}
+ final public static boolean isEqual( final double a, final double b, final double tolerance ) {
+ return ( ( Math.abs( a - b ) ) < tolerance );
+ }
+
final public static boolean isEven( final int n ) {
return ( n % 2 ) == 0;
}
* 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
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;
}
}
return OS_NAME.toLowerCase().indexOf( "win" ) > -1;
}
catch ( final Exception e ) {
- ForesterUtil.printWarningMessage( Constants.PRG_NAME, "minor error: " + e );
+ ForesterUtil.printWarningMessage( AptxConstants.PRG_NAME, "minor error: " + e );
return false;
}
}
}
return null;
}
+
+ final public static String isWritableFile( final String s ) {
+ return isWritableFile( new File( s ) );
+ }
/**
* Helper for method "stringToColor".
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() );
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;
}
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;
}
System.exit( -1 );
}
- final public static StringBuffer pad( final double number, final int size, final char pad, final boolean left_pad ) {
+ 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)
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 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 ) )
+ 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 ) {
/**
* Removes all white space from String s.
- *
+ *
* @return String s with white space removed
*/
final public static String removeWhiteSpace( String s ) {
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 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 ) );
+ 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 ( parser == null ) {
+ throw new IllegalArgumentException( "parser to use to read from URL must not be null" );
+ }
+ final URLConnection con;
+ if ( url.toString().startsWith( "https:" ) ) {
+ con = TrustManager.makeHttpsURLConnection( url );
+ }
+ else if ( url.toString().startsWith( "http:" ) ) {
+ con = url.openConnection();
+ }
+ else {
+ throw new IllegalArgumentException( "Cannot deal with URL: " + url );
+ }
+ if ( con == null ) {
+ throw new IOException( "could not create connection from " + url );
+ }
+ con.setDefaultUseCaches( false );
+ final InputStream is = con.getInputStream();
+ if ( is == null ) {
+ throw new IOException( "could not create input stream from " + url );
+ }
+ final Phylogeny[] trees = ParserBasedPhylogenyFactory.getInstance().create( is, parser );
+ try {
+ is.close();
+ }
+ catch ( final Exception e ) {
+ // ignore
+ }
+ return trees;
}
- 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;
+ public final static File getMatchingFile( final File dir, final String prefix, final String suffix )
+ throws IOException {
+ if ( !dir.exists() ) {
+ throw new IOException( "[" + dir + "] does not exist" );
+ }
+ if ( !dir.isDirectory() ) {
+ throw new IOException( "[" + dir + "] is not a directory" );
+ }
+ if ( dir.listFiles().length == 0 ) {
+ throw new IOException( "[" + dir + "] is empty" );
+ }
+ final File files[] = dir.listFiles( new FilenameFilter() {
+
+ @Override
+ public boolean accept( final File dir, final String name ) {
+ return ( name.endsWith( suffix ) );
+ }
+ } );
+ if ( files.length == 0 ) {
+ throw new IOException( "no files ending with \"" + suffix + "\" found in [" + dir + "]" );
+ }
+ String my_prefix = prefix;
+ boolean done = false;
+ boolean more_than_one = false;
+ File the_one = null;
+ do {
+ int matches = 0;
+ for( File file : files ) {
+ if ( file.getName().startsWith( my_prefix ) ) {
+ matches++;
+ if ( matches > 1 ) {
+ the_one = null;
+ break;
+ }
+ the_one = file;
+ }
+ }
+ if ( matches > 1 ) {
+ more_than_one = true;
+ done = true;
+ }
+ if ( matches == 1 ) {
+ done = true;
+ }
+ else {
+ if ( my_prefix.length() <= 1 ) {
+ throw new IOException( "no file matching \"" + removeFileExtension( prefix )
+ + "\" and ending with \"" + suffix + "\" found in [" + dir + "]" );
+ }
+ my_prefix = my_prefix.substring( 0, my_prefix.length() - 1 );
+ }
+ } while ( !done );
+ if ( more_than_one ) {
+ throw new IOException( "multiple files matching \"" + removeFileExtension( prefix )
+ + "\" and ending with \"" + suffix + "\" found in [" + dir + "]" );
+ }
+ else if ( the_one != null ) {
}
else {
- if ( mol_seq.contains( "T" ) ) {
- return TYPE.DNA;
+ throw new IOException( "no file matching \"" + removeFileExtension( prefix ) + "\" and ending with \""
+ + suffix + "\" found in [" + dir + "]" );
+ }
+ return the_one;
+ }
+
+ public final static String greatestCommonPrefix( final String a, final String b ) {
+ final int min_length = Math.min( a.length(), b.length() );
+ for( int i = 0; i < min_length; ++i ) {
+ if ( a.charAt( i ) != b.charAt( i ) ) {
+ return a.substring( 0, i );
}
- else if ( mol_seq.contains( "U" ) ) {
- return TYPE.RNA;
+ }
+ return a.substring( 0, min_length );
+ }
+
+ public final static String greatestCommonPrefix( final String a, final String b, final String separator ) {
+ if ( ForesterUtil.isEmpty( separator ) ) {
+ throw new IllegalArgumentException( "separator must not be null or empty" );
+ }
+ final String[] as = a.split( Pattern.quote( separator ) );
+ final String[] bs = b.split( Pattern.quote( separator ) );
+ final int min_length = Math.min( as.length, bs.length );
+ for( int i = 0; i < min_length; ++i ) {
+ if ( !( as[ i ].equals( bs[ i ] ) ) ) {
+ StringBuilder sb = new StringBuilder();
+ boolean first = true;
+ for( int j = 0; j < i; ++j ) {
+ if ( first ) {
+ first = false;
+ }
+ else {
+ sb.append( separator );
+ }
+ sb.append( as[ j ] );
+ }
+ return sb.toString();
}
}
- return null;
+ StringBuilder sb = new StringBuilder();
+ boolean first = true;
+ for( int j = 0; j < min_length; ++j ) {
+ if ( first ) {
+ first = false;
+ }
+ else {
+ sb.append( separator );
+ }
+ sb.append( as[ j ] );
+ }
+ return sb.toString();
}
- /**
- * 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 final static String greatestCommonPrefix( final List<String> strings ) {
+ if ( strings == null ) {
+ throw new IllegalArgumentException( "list of strings is null" );
+ }
+ if ( strings.isEmpty() ) {
+ throw new IllegalArgumentException( "list of strings is empty" );
+ }
+ String common = strings.get( 0 );
+ for( int i = 1; i < strings.size(); ++i ) {
+ common = greatestCommonPrefix( common, strings.get( i ) );
+ }
+ return common;
}
- final private static String[] splitString( final String str ) {
- final String regex = "[\\s;,]+";
- return str.split( regex );
+ public final static String greatestCommonPrefix( final List<String> strings, final String separator ) {
+ if ( ForesterUtil.isEmpty( separator ) ) {
+ return greatestCommonPrefix( strings );
+ }
+ if ( strings == null ) {
+ throw new IllegalArgumentException( "list of strings is null" );
+ }
+ if ( strings.isEmpty() ) {
+ throw new IllegalArgumentException( "list of strings is empty" );
+ }
+ String common = strings.get( 0 );
+ for( int i = 1; i < strings.size(); ++i ) {
+ common = greatestCommonPrefix( common, strings.get( i ), separator );
+ }
+ return common;
+ }
+
+ private ForesterUtil() {
+ }
+
+ public static List<String> spliIntoPrefixes( final String prefix, final String separator ) {
+ final String[] a = prefix.split( Pattern.quote( separator ) );
+ final List<String> l = new ArrayList<String>();
+ for( int i = 0; i < a.length; ++i ) {
+ final StringBuilder sb = new StringBuilder();
+ for( int j = 0; j <= i; ++j ) {
+ sb.append( a[ j ] );
+ if ( j < i ) {
+ sb.append( separator );
+ }
+ }
+ // System.out.println( sb.toString() );
+ l.add( sb.toString() );
+ }
+ return l;
+ }
+
+ //
+ public static boolean isLooksLikeFasta( final File file ) throws IOException {
+ final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
+ return ( ( !isEmptyTrimmed( first_line ) && first_line.trim().startsWith( ">" ) ) );
}
}
git://source.jalview.org / jalview.git / blobdiff