X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Farchaeopteryx%2FAptxUtil.java;h=8ceb398a2e08ffaf1bde034aeb7a025662f6ad2b;hb=5c4e24e304f57058fa1c3a3f1256a573b37d89f6;hp=2ca3b8732c77fb99accc5ad77029dc96e6616da7;hpb=0e23c7a534e22c1b4238bf59e676a7a500395bd3;p=jalview.git diff --git a/forester/java/src/org/forester/archaeopteryx/AptxUtil.java b/forester/java/src/org/forester/archaeopteryx/AptxUtil.java index 2ca3b87..8ceb398 100644 --- a/forester/java/src/org/forester/archaeopteryx/AptxUtil.java +++ b/forester/java/src/org/forester/archaeopteryx/AptxUtil.java @@ -36,11 +36,14 @@ import java.io.ByteArrayOutputStream; import java.io.File; import java.io.FileNotFoundException; import java.io.IOException; +import java.io.UnsupportedEncodingException; import java.lang.reflect.InvocationTargetException; import java.lang.reflect.Method; import java.net.URI; import java.net.URL; +import java.net.URLEncoder; import java.text.ParseException; +import java.util.ArrayList; import java.util.Arrays; import java.util.HashMap; import java.util.HashSet; @@ -48,8 +51,11 @@ import java.util.Iterator; import java.util.List; import java.util.Locale; import java.util.Map; +import java.util.Map.Entry; import java.util.Set; +import java.util.SortedMap; import java.util.SortedSet; +import java.util.TreeMap; import java.util.TreeSet; import java.util.regex.Matcher; import java.util.regex.Pattern; @@ -73,8 +79,10 @@ import org.forester.io.parsers.tol.TolParser; import org.forester.io.parsers.util.ParserUtils; import org.forester.phylogeny.Phylogeny; import org.forester.phylogeny.PhylogenyMethods; +import org.forester.phylogeny.PhylogenyMethods.DESCENDANT_SORT_PRIORITY; import org.forester.phylogeny.PhylogenyNode; import org.forester.phylogeny.data.Accession; +import org.forester.phylogeny.data.Annotation; import org.forester.phylogeny.data.BranchColor; import org.forester.phylogeny.data.Taxonomy; import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory; @@ -83,20 +91,19 @@ import org.forester.phylogeny.iterators.PhylogenyNodeIterator; import org.forester.phylogeny.iterators.PreorderTreeIterator; import org.forester.util.AsciiHistogram; import org.forester.util.DescriptiveStatistics; +import org.forester.util.ForesterConstants; import org.forester.util.ForesterUtil; +import org.forester.util.SequenceIdParser; import org.forester.ws.seqdb.UniProtTaxonomy; public final class AptxUtil { - final static String UNIPROT_KB = "http://www.uniprot.org/uniprot/"; - final static Pattern UNIPROT_KB_PATTERN = Pattern - .compile( "\\b[A-Z0-9]{5,6}_[A-Z9][A-Z]{2}[A-Z0-9]{2}|RAT|PIG|PEA\\b" ); + private final static String[] AVAILABLE_FONT_FAMILIES_SORTED = GraphicsEnvironment.getLocalGraphicsEnvironment() + .getAvailableFontFamilyNames(); private final static Pattern seq_identifier_pattern_1 = Pattern .compile( "^([A-Za-z]{2,5})[|=:]([0-9A-Za-z_\\.]{5,40})\\s*$" ); private final static Pattern seq_identifier_pattern_2 = Pattern .compile( "^([A-Za-z]{2,5})[|=:]([0-9A-Za-z_\\.]{5,40})[|,; ].*$" ); - private final static String[] AVAILABLE_FONT_FAMILIES_SORTED = GraphicsEnvironment.getLocalGraphicsEnvironment() - .getAvailableFontFamilyNames(); static { Arrays.sort( AVAILABLE_FONT_FAMILIES_SORTED ); } @@ -112,6 +119,69 @@ public final class AptxUtil { return formatter; } + public final static String createUriForSeqWeb( final PhylogenyNode node, + final Configuration conf, + final TreePanel tp ) { + String uri_str = null; + final String upkb = ForesterUtil.extractUniProtKbProteinSeqIdentifier( node ); + if ( !ForesterUtil.isEmpty( upkb ) ) { + try { + uri_str = ForesterUtil.UNIPROT_KB + URLEncoder.encode( upkb, ForesterConstants.UTF8 ); + } + catch ( final UnsupportedEncodingException e ) { + showErrorMessage( tp, e.toString() ); + e.printStackTrace(); + } + } + if ( ForesterUtil.isEmpty( uri_str ) ) { + final String v = ForesterUtil.extractGenbankAccessor( node ); + if ( !ForesterUtil.isEmpty( v ) ) { + try { + if ( SequenceIdParser.isProtein( v ) ) { + uri_str = ForesterUtil.NCBI_PROTEIN + URLEncoder.encode( v, ForesterConstants.UTF8 ); + } + else { + uri_str = ForesterUtil.NCBI_NUCCORE + URLEncoder.encode( v, ForesterConstants.UTF8 ); + } + } + catch ( final UnsupportedEncodingException e ) { + showErrorMessage( tp, e.toString() ); + e.printStackTrace(); + } + } + } + if ( ForesterUtil.isEmpty( uri_str ) ) { + final String v = ForesterUtil.extractRefSeqAccessorAccessor( node ); + if ( !ForesterUtil.isEmpty( v ) ) { + try { + if ( SequenceIdParser.isProtein( v ) ) { + uri_str = ForesterUtil.NCBI_PROTEIN + URLEncoder.encode( v, ForesterConstants.UTF8 ); + } + else { + uri_str = ForesterUtil.NCBI_NUCCORE + URLEncoder.encode( v, ForesterConstants.UTF8 ); + } + } + catch ( final UnsupportedEncodingException e ) { + showErrorMessage( tp, e.toString() ); + e.printStackTrace(); + } + } + } + if ( ForesterUtil.isEmpty( uri_str ) ) { + final String v = ForesterUtil.extractGInumber( node ); + if ( !ForesterUtil.isEmpty( v ) ) { + try { + uri_str = ForesterUtil.NCBI_GI + URLEncoder.encode( v, ForesterConstants.UTF8 ); + } + catch ( final UnsupportedEncodingException e ) { + showErrorMessage( tp, e.toString() ); + e.printStackTrace(); + } + } + } + return uri_str; + } + final static public boolean isHasAtLeastNodeWithEvent( final Phylogeny phy ) { final PhylogenyNodeIterator it = phy.iteratorPostorder(); while ( it.hasNext() ) { @@ -279,6 +349,10 @@ public final class AptxUtil { && !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getScientificName() ) ) { showExtDescNodeDataUserSelectedHelperHelper( node.getNodeData().getTaxonomy().getScientificName(), sb ); } + if ( cp.isShowTaxonomyCommonNames() && node.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getCommonName() ) ) { + showExtDescNodeDataUserSelectedHelperHelper( node.getNodeData().getTaxonomy().getCommonName(), sb ); + } if ( ( cp.isShowGeneNames() || cp.isShowGeneSymbols() || cp.isShowSequenceAcc() ) && node.getNodeData().isHasSequence() && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getMolecularSequence() ) ) { @@ -469,25 +543,41 @@ public final class AptxUtil { lookAtSomeTreePropertiesForAptxControlSettings( phy, main_panel.getControlPanel(), configuration ); } - final static Color calculateColorFromString( final String str ) { - final String species_uc = str.toUpperCase(); - char first = species_uc.charAt( 0 ); + final static Color calculateColorFromString( final String str, final boolean is_taxonomy ) { + final String my_str = str.toUpperCase(); + char first = my_str.charAt( 0 ); char second = ' '; char third = ' '; - if ( species_uc.length() > 1 ) { - second = species_uc.charAt( 1 ); - if ( species_uc.length() > 2 ) { - if ( species_uc.indexOf( " " ) > 0 ) { - third = species_uc.charAt( species_uc.indexOf( " " ) + 1 ); - } - else { - third = species_uc.charAt( 2 ); + if ( my_str.length() > 1 ) { + if ( is_taxonomy ) { + second = my_str.charAt( 1 ); + } + else { + second = my_str.charAt( my_str.length() - 1 ); + } + if ( is_taxonomy ) { + if ( my_str.length() > 2 ) { + if ( my_str.indexOf( " " ) > 0 ) { + third = my_str.charAt( my_str.indexOf( " " ) + 1 ); + } + else { + third = my_str.charAt( 2 ); + } } } + else if ( my_str.length() > 2 ) { + third = ( char ) ( Math.abs( str.hashCode() / 16909320 ) ); + System.out.println( str.hashCode() ); + } } first = AptxUtil.normalizeCharForRGB( first ); second = AptxUtil.normalizeCharForRGB( second ); - third = AptxUtil.normalizeCharForRGB( third ); + if ( is_taxonomy ) { + third = AptxUtil.normalizeCharForRGB( third ); + } + else { + third = third > 255 ? 255 : third; + } if ( ( first > 235 ) && ( second > 235 ) && ( third > 235 ) ) { first = 0; } @@ -660,6 +750,49 @@ public final class AptxUtil { return colorizations; } + final static String createAnnotationString( final SortedSet annotations ) { + final SortedMap> m = new TreeMap>(); + for( final Annotation an : annotations ) { + final String ref_source = ForesterUtil.isEmpty( an.getRefSource() ) ? "?" : an.getRefSource(); + if ( !m.containsKey( ref_source ) ) { + m.put( ref_source, new ArrayList() ); + } + m.get( ref_source ).add( an ); + } + final StringBuilder sb = new StringBuilder(); + for( final Entry> e : m.entrySet() ) { + final String ref_source = e.getKey(); + final List ans = e.getValue(); + if ( m.size() > 1 ) { + sb.append( "[" ); + } + if ( !ref_source.equals( "?" ) ) { + sb.append( ref_source ); + sb.append( ": " ); + } + for( int i = 0; i < ans.size(); ++i ) { + final Annotation an = ans.get( i ); + if ( !ForesterUtil.isEmpty( an.getRefValue() ) ) { + sb.append( an.getRefValue() ); + sb.append( " " ); + } + if ( !ForesterUtil.isEmpty( an.getDesc() ) ) { + sb.append( an.getDesc() ); + } + if ( sb.charAt( sb.length() - 1 ) == ' ' ) { + sb.deleteCharAt( sb.length() - 1 ); + } + if ( i < ans.size() - 1 ) { + sb.append( ", " ); + } + } + if ( m.size() > 1 ) { + sb.append( "] " ); + } + } + return sb.toString(); + } + final static String createBasicInformation( final Phylogeny phy ) { final StringBuilder desc = new StringBuilder(); if ( ( phy != null ) && !phy.isEmpty() ) { @@ -720,6 +853,9 @@ public final class AptxUtil { desc.append( "Distinct external taxonomies: " ); desc.append( taxs.size() ); } + for( final Taxonomy t : taxs ) { + System.out.println( t.toString() ); + } desc.append( "\n" ); final DescriptiveStatistics bs = PhylogenyMethods.calculatBranchLengthStatistics( phy ); if ( bs.getN() > 3 ) { @@ -730,9 +866,8 @@ public final class AptxUtil { desc.append( "\n" ); desc.append( " Median: " + ForesterUtil.round( bs.median(), 6 ) ); desc.append( "\n" ); - desc.append( " Mean: " + ForesterUtil.round( bs.arithmeticMean(), 6 ) ); - desc.append( "\n" ); - desc.append( " SD: " + ForesterUtil.round( bs.sampleStandardDeviation(), 6 ) ); + desc.append( " Mean: " + ForesterUtil.round( bs.arithmeticMean(), 6 ) + " (stdev: " + + ForesterUtil.round( bs.sampleStandardDeviation(), 6 ) + ")" ); desc.append( "\n" ); desc.append( " Minimum: " + ForesterUtil.round( bs.getMin(), 6 ) ); desc.append( "\n" ); @@ -751,9 +886,8 @@ public final class AptxUtil { desc.append( "\n" ); desc.append( " Median: " + ForesterUtil.round( ds.median(), 2 ) ); desc.append( "\n" ); - desc.append( " Mean: " + ForesterUtil.round( ds.arithmeticMean(), 2 ) ); - desc.append( "\n" ); - desc.append( " SD: " + ForesterUtil.round( ds.sampleStandardDeviation(), 2 ) ); + desc.append( " Mean: " + ForesterUtil.round( ds.arithmeticMean(), 2 ) + " (stdev: " + + ForesterUtil.round( ds.sampleStandardDeviation(), 2 ) + ")" ); desc.append( "\n" ); desc.append( " Minimum: " + ForesterUtil.roundToInt( ds.getMin() ) ); desc.append( "\n" ); @@ -788,11 +922,10 @@ public final class AptxUtil { desc.append( " Median: " + ForesterUtil.round( cs.median(), 6 ) ); desc.append( "\n" ); desc.append( " Mean: " + ForesterUtil.round( cs.arithmeticMean(), 6 ) ); - desc.append( "\n" ); if ( cs.getN() > 2 ) { - desc.append( " SD: " + ForesterUtil.round( cs.sampleStandardDeviation(), 6 ) ); - desc.append( "\n" ); + desc.append( " (stdev: " + ForesterUtil.round( cs.sampleStandardDeviation(), 6 ) + ")" ); } + desc.append( "\n" ); desc.append( " Minimum: " + ForesterUtil.roundToInt( cs.getMin() ) ); desc.append( "\n" ); desc.append( " Maximum: " + ForesterUtil.roundToInt( cs.getMax() ) ); @@ -856,17 +989,6 @@ public final class AptxUtil { return true; } - final static boolean isMac() { - try { - final String s = ForesterUtil.OS_NAME.toLowerCase(); - return s.startsWith( "mac" ); - } - catch ( final Exception e ) { - ForesterUtil.printWarningMessage( Constants.PRG_NAME, "minor error: " + e ); - return false; - } - } - final static boolean isUsOrCanada() { try { if ( ( Locale.getDefault().equals( Locale.CANADA ) ) || ( Locale.getDefault().equals( Locale.US ) ) ) { @@ -879,17 +1001,6 @@ public final class AptxUtil { return false; } - final static boolean isWindows() { - try { - final String s = ForesterUtil.OS_NAME.toLowerCase(); - return s.indexOf( "win" ) > -1; - } - catch ( final Exception e ) { - ForesterUtil.printWarningMessage( Constants.PRG_NAME, "minor error: " + e ); - return false; - } - } - final static void lookAtSomeTreePropertiesForAptxControlSettings( final Phylogeny t, final ControlPanel atv_control, final Configuration configuration ) { @@ -963,8 +1074,9 @@ public final class AptxUtil { final boolean phyloxml_validate_against_xsd, final boolean replace_underscores, final boolean internal_numbers_are_confidences, - final TAXONOMY_EXTRACTION taxonomy_extraction ) - throws FileNotFoundException, IOException { + final TAXONOMY_EXTRACTION taxonomy_extraction, + final boolean midpoint_reroot ) throws FileNotFoundException, + IOException { final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); final PhylogenyParser parser; boolean nhx_or_nexus = false; @@ -993,6 +1105,12 @@ public final class AptxUtil { PhylogenyMethods.transferInternalNodeNamesToConfidence( phy ); } } + if ( midpoint_reroot ) { + for( final Phylogeny phy : phys ) { + PhylogenyMethods.midpointRoot( phy ); + PhylogenyMethods.orderAppearance( phy.getRoot(), true, true, DESCENDANT_SORT_PRIORITY.NODE_NAME ); + } + } return phys; } @@ -1228,7 +1346,7 @@ public final class AptxUtil { if ( os.toLowerCase().startsWith( "win" ) ) { Runtime.getRuntime().exec( "rundll32 url.dll,FileProtocolHandler " + url ); } - else if ( isMac() ) { + else if ( ForesterUtil.isMac() ) { final Class file_mgr = Class.forName( "com.apple.eio.FileManager" ); final Method open_url = file_mgr.getDeclaredMethod( "openURL", new Class[] { String.class } ); open_url.invoke( null, new Object[] { url } ); @@ -1275,7 +1393,7 @@ public final class AptxUtil { // br.close(); // } public static enum GraphicsExportType { - GIF( "gif" ), JPG( "jpg" ), PDF( "pdf" ), PNG( "png" ), TIFF( "tif" ), BMP( "bmp" ); + BMP( "bmp" ), GIF( "gif" ), JPG( "jpg" ), PDF( "pdf" ), PNG( "png" ), TIFF( "tif" ); private final String _suffix;