for( final UniProtTaxonomy up_taxonomy : up_taxonomies ) {
boolean match = true;
I: for( int i = 0; i < lineage.size(); ++i ) {
- if ( i == up_taxonomy.getLineage().size() || !lineage.get( i ).equalsIgnoreCase( up_taxonomy.getLineage().get( i ) ) ) {
+ if ( ( i == up_taxonomy.getLineage().size() )
+ || !lineage.get( i ).equalsIgnoreCase( up_taxonomy.getLineage().get( i ) ) ) {
match = false;
break I;
}
// Contact: phylosoft @ gmail . com
// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
-
-
package org.forester.archaeopteryx;
import java.awt.Color;
String default_config_filename = Constants.DEFAULT_CONFIGURATION_FILE_NAME;
final static String display_options[][] = {
{ "Phylogram", "display", "?" }, { "Node Name", "display", "yes" }, { "Taxonomy Code", "display", "yes" },
- { "Annotation", "nodisplay", "no" }, { "Confidence Values", "display", "?" }, { "Node Events", "display", "?" },
- { "Taxonomy Colorize", "display", "yes" }, { "Colorize Branches", "display", "no" },
- { "Use Branch-Widths", "display", "no" }, { "Show Custom Nodes", "display", "yes" },
- { "Domains", "nodisplay", "no" }, { "Binary Characters", "nodisplay", "no" },
- { "Binary Char Counts", "nodisplay", "no" }, { "Seq Name", "display", "yes" },
- { "Seq Acc", "display", "no" }, { "Show Internal Data", "display", "yes" },
- { "Dyna Hide", "display", "yes" }, { "Taxonomy Scientific", "display", "yes" },
- { "Taxonomy Common", "display", "no" }, { "Annotation Colorize", "nodisplay", "no" },
- { "Seq Symbol", "display", "yes" }, { "Rollover", "display", "yes" },
- { "Relation Confidence", "nodisplay", "no" }, { "Vector Data", "nodisplay", "no" },
- { "Taxonomy Images", "display", "no" }, { "Properties", "nodisplay", "no" } };
+ { "Annotation", "nodisplay", "no" }, { "Confidence Values", "display", "?" },
+ { "Node Events", "display", "?" }, { "Taxonomy Colorize", "display", "yes" },
+ { "Colorize Branches", "display", "no" }, { "Use Branch-Widths", "display", "no" },
+ { "Show Custom Nodes", "display", "yes" }, { "Domains", "nodisplay", "no" },
+ { "Binary Characters", "nodisplay", "no" }, { "Binary Char Counts", "nodisplay", "no" },
+ { "Seq Name", "display", "yes" }, { "Seq Acc", "display", "no" },
+ { "Show Internal Data", "display", "yes" }, { "Dyna Hide", "display", "yes" },
+ { "Taxonomy Scientific", "display", "yes" }, { "Taxonomy Common", "display", "no" },
+ { "Annotation Colorize", "nodisplay", "no" }, { "Seq Symbol", "display", "yes" },
+ { "Rollover", "display", "yes" }, { "Relation Confidence", "nodisplay", "no" },
+ { "Vector Data", "nodisplay", "no" }, { "Taxonomy Images", "display", "no" },
+ { "Properties", "nodisplay", "no" } };
final static String clickto_options[][] = {
{ "Display Node Data", "display" }, { "Collapse/Uncollapse", "display" }, { "Root/Reroot", "display" },
{ "Sub/Super Tree", "display" }, { "Swap Descendants", "display" }, { "Colorize Subtree", "display" },
public final class Constants {
final static boolean __ALLOW_PHYLOGENETIC_INFERENCE = true;
- public final static boolean __RELEASE = false; // TODO remove me
- public final static boolean __SNAPSHOT_RELEASE = false; // TODO remove me
- public final static boolean __SYNTH_LF = false; // TODO remove me
+ public final static boolean __RELEASE = false; // TODO remove me
+ public final static boolean __SNAPSHOT_RELEASE = false; // TODO remove me
+ public final static boolean __SYNTH_LF = false; // TODO remove me
public final static boolean ALLOW_DDBJ_BLAST = false;
public final static String PRG_NAME = "Archaeopteryx";
final static String VERSION = "0.979";
- final static String PRG_DATE = "121229";
+ final static String PRG_DATE = "130104";
final static String DEFAULT_CONFIGURATION_FILE_NAME = "_aptx_configuration_file";
final static String[] DEFAULT_FONT_CHOICES = { "Verdana", "Tahoma",
"Arial", "Helvetica", "Dialog", "Lucida Sans", "SansSerif", "Sans-serif", "Sans" };
final static float WHEEL_ZOOM_OUT_FACTOR = 1 / Constants.WHEEL_ZOOM_IN_FACTOR;
final static float WHEEL_ZOOM_IN_X_CORRECTION_FACTOR = 1.085f;
final static float WHEEL_ZOOM_OUT_X_CORRECTION_FACTOR = 1 / Constants.WHEEL_ZOOM_IN_X_CORRECTION_FACTOR;
- static final boolean SPECIAL_CUSTOM = false; //TODO remove me
+ static final boolean SPECIAL_CUSTOM = false; //TODO remove me
static final double EXT_NODE_INFO_LENGTH_MAX_RATIO = 0.95;
static final Dimension NODE_PANEL_SPLIT_MINIMUM_SIZE = new Dimension( 100, 50 );
static final Dimension NODE_PANEL_SIZE = new Dimension( 500, 600 );
final static String PHYLOXML_WEB_SITE = ForesterConstants.PHYLO_XML_LOCATION;
final static String PHYLOXML_REFERENCE_URL = "http://www.biomedcentral.com/1471-2105/10/356/";
final static String APTX_REFERENCE_URL = "http://www.biomedcentral.com/bmcbioinformatics/";
- final static String APTX_REFERENCE = "Zmasek..."; //TODO
+ final static String APTX_REFERENCE = "Zmasek..."; //TODO
final static String PHYLOXML_REFERENCE = ForesterConstants.PHYLO_XML_REFERENCE;
final static String PHYLOXML_REFERENCE_SHORT = "Han MV and Zmasek CM (2009), BMC Bioinformatics, 10:356";
final static short NUMBER_OF_DIGITS_AFTER_COMMA_FOR_BRANCH_LENGTH_VALUES_DEFAULT = 2;
public final class MainFrameApplet extends MainFrame {
- private static final long serialVersionUID = 1941019292746717053L;
- private final static int DEFAULT_FRAME_X_SIZE = 640;
+ private static final long serialVersionUID = 1941019292746717053L;
+ private final static int DEFAULT_FRAME_X_SIZE = 640;
private final static int DEFAULT_FRAME_Y_SIZE = 580;
private final ArchaeopteryxA _applet;
private ButtonGroup _radio_group_1;
// Contact: phylosoft @ gmail . com
// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
-
package org.forester.archaeopteryx;
import java.awt.BasicStroke;
// FORESTER -- software libraries and applications
// for evolutionary biology research and applications.
//
-// Copyright (C) 2008-2009 Christian M. Zmasek
-// Copyright (C) 2008-2009 Burnham Institute for Medical Research
-// All rights reserved
+// Copyright (C) 2013 Christian M. Zmasek
//
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
package org.forester.io.parsers.nhx;
-import java.awt.Color;
import java.io.BufferedReader;
import java.io.File;
+import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStream;
public final class NHXParser implements PhylogenyParser {
public static final TAXONOMY_EXTRACTION TAXONOMY_EXTRACTION_DEFAULT = TAXONOMY_EXTRACTION.NO;
+ public final static Pattern UC_LETTERS_NUMBERS_PATTERN = Pattern.compile( "^[A-Z0-9]+$" );
+ public final static Pattern NUMBERS_ONLY_PATTERN = Pattern.compile( "^[0-9\\.]+$" );
+ public final static Pattern MB_PROB_PATTERN = Pattern.compile( "prob=([^,]+)" );
+ public final static Pattern MB_PROB_SD_PATTERN = Pattern.compile( "prob_stddev=([^,]+)" );
+ public final static Pattern MB_BL_PATTERN = Pattern.compile( "length_median=([^,]+)" );
final static private boolean GUESS_ROOTEDNESS_DEFAULT = true;
final static private boolean GUESS_IF_SUPPORT_VALUES = true;
final static private boolean IGNORE_QUOTES_DEFAULT = false;
final static public boolean REPLACE_UNDERSCORES_DEFAULT = false;
- private boolean _saw_closing_paren;
final static private byte STRING = 0;
final static private byte STRING_BUFFER = 1;
final static private byte CHAR_ARRAY = 2;
private StringBuilder _current_anotation;
private Object _nhx_source;
private int _clade_level;
- private List<Phylogeny> _phylogenies;
private Phylogeny _current_phylogeny;
private TAXONOMY_EXTRACTION _taxonomy_extraction;
private boolean _replace_underscores;
- public final static Pattern UC_LETTERS_NUMBERS_PATTERN = Pattern.compile( "^[A-Z0-9]+$" );
- public final static Pattern NUMBERS_ONLY_PATTERN = Pattern.compile( "^[0-9\\.]+$" );
- public final static Pattern MB_PROB_PATTERN = Pattern.compile( "prob=([^,]+)" );
- public final static Pattern MB_PROB_SD_PATTERN = Pattern.compile( "prob_stddev=([^,]+)" );
- public final static Pattern MB_BL_PATTERN = Pattern.compile( "length_median=([^,]+)" );
+ private boolean _in_comment = false;
+ private boolean _saw_colon = false;
+ private boolean _saw_closing_paren;
+ private boolean _saw_open_bracket = false;
+ private boolean _in_open_bracket = false;
+ private boolean _in_double_quote = false;
+ private boolean _in_single_quote = false;
+ private String _my_source_str = null;
+ private StringBuffer _my_source_sbuff = null;
+ private StringBuilder _my_source_sbuil = null;
+ private char[] _my_source_charary = null;
+ private BufferedReader _my_source_br = null;
+ private int _i;
+ private Phylogeny _next;
+ private Object _source;
public NHXParser() {
init();
}
- public NHXParser.TAXONOMY_EXTRACTION getTaxonomyExtraction() {
+ public final TAXONOMY_EXTRACTION getTaxonomyExtraction() {
return _taxonomy_extraction;
}
- /**
- * Parses the source set with setSource( final Object nhx_source ). Returns
- * the Phylogenies found in the source as Phylogeny[].
- * Everything between [ and ] is considered comment and ignored,
- * unless:
- * "[&&NHX... ]"
- * or
- * ":digits and/or.[bootstrap]"
- *
- * @see #setSource( final Object nhx_source )
- * @see org.forester.io.parsers.PhylogenyParser#parse()
- * @return Phylogeny[]
- * @throws IOException
- * @throws NHXFormatException
- * @throws PhylogenyParserException
- */
+ public final boolean hasNext() {
+ return _next != null;
+ }
+
+ public final Phylogeny next() throws NHXFormatException, IOException {
+ final Phylogeny phy = _next;
+ getNext();
+ return phy;
+ }
+
@Override
- public Phylogeny[] parse() throws IOException, NHXFormatException {
- boolean in_comment = false;
- boolean saw_colon = false;
- boolean saw_open_bracket = false;
- boolean in_open_bracket = false;
- boolean in_double_quote = false;
- boolean in_single_quote = false;
- setPhylogenies( new ArrayList<Phylogeny>() );
- setCladeLevel( 0 );
- newCurrentAnotation();
- setCurrentPhylogeny( null );
- setCurrentNode( null );
- int i = 0;
- String my_source_str = null;
- StringBuffer my_source_sbuff = null;
- StringBuilder my_source_sbuil = null;
- char[] my_source_charary = null;
- BufferedReader my_source_br = null;
- switch ( getInputType() ) {
+ public final Phylogeny[] parse() throws IOException {
+ reset();
+ final List<Phylogeny> l = new ArrayList<Phylogeny>();
+ while ( hasNext() ) {
+ l.add( next() );
+ }
+ final Phylogeny[] p = new Phylogeny[ l.size() ];
+ for( int i = 0; i < l.size(); ++i ) {
+ p[ i ] = l.get( i );
+ }
+ return p;
+ }
+
+ public final void reset() throws NHXFormatException, IOException {
+ _i = 0;
+ _next = null;
+ _in_comment = false;
+ _saw_colon = false;
+ _saw_open_bracket = false;
+ _in_open_bracket = false;
+ _in_double_quote = false;
+ _in_single_quote = false;
+ _clade_level = 0;
+ _current_anotation = new StringBuilder();
+ _current_phylogeny = null;
+ _current_node = null;
+ _my_source_str = null;
+ _my_source_sbuff = null;
+ _my_source_sbuil = null;
+ _my_source_charary = null;
+ _my_source_br = null;
+ determineSourceType( _source );
+ switch ( _input_type ) {
case STRING:
- my_source_str = ( String ) getNhxSource();
+ _my_source_str = ( String ) _nhx_source;
break;
case STRING_BUFFER:
- my_source_sbuff = ( StringBuffer ) getNhxSource();
+ _my_source_sbuff = ( StringBuffer ) _nhx_source;
break;
case STRING_BUILDER:
- my_source_sbuil = ( StringBuilder ) getNhxSource();
+ _my_source_sbuil = ( StringBuilder ) _nhx_source;
break;
case CHAR_ARRAY:
- my_source_charary = ( char[] ) getNhxSource();
+ _my_source_charary = ( char[] ) _nhx_source;
break;
case BUFFERED_READER:
- my_source_br = ( BufferedReader ) getNhxSource();
+ if ( _my_source_br != null ) {
+ try {
+ _my_source_br.close();
+ }
+ catch ( final IOException e ) {
+ //do nothing
+ }
+ }
+ _my_source_br = ( BufferedReader ) _nhx_source;
break;
default:
throw new RuntimeException( "unknown input type" );
}
+ getNext();
+ }
+
+ public final void setGuessRootedness( final boolean guess_rootedness ) {
+ _guess_rootedness = guess_rootedness;
+ }
+
+ public final void setIgnoreQuotes( final boolean ignore_quotes ) {
+ _ignore_quotes = ignore_quotes;
+ }
+
+ public final void setReplaceUnderscores( final boolean replace_underscores ) {
+ _replace_underscores = replace_underscores;
+ }
+
+ @Override
+ public final void setSource( final Object nhx_source ) throws NHXFormatException, IOException {
+ _source = nhx_source;
+ reset();
+ }
+
+ public final void setTaxonomyExtraction( final TAXONOMY_EXTRACTION taxonomy_extraction ) {
+ _taxonomy_extraction = taxonomy_extraction;
+ }
+
+ private final void determineSourceType( final Object nhx_source ) throws PhylogenyParserException,
+ FileNotFoundException {
+ if ( nhx_source == null ) {
+ throw new PhylogenyParserException( getClass() + ": attempt to parse null object." );
+ }
+ else if ( nhx_source instanceof String ) {
+ _input_type = NHXParser.STRING;
+ _source_length = ( ( String ) nhx_source ).length();
+ _nhx_source = nhx_source;
+ }
+ else if ( nhx_source instanceof StringBuilder ) {
+ _input_type = NHXParser.STRING_BUILDER;
+ _source_length = ( ( StringBuilder ) nhx_source ).length();
+ _nhx_source = nhx_source;
+ }
+ else if ( nhx_source instanceof StringBuffer ) {
+ _input_type = NHXParser.STRING_BUFFER;
+ _source_length = ( ( StringBuffer ) nhx_source ).length();
+ _nhx_source = nhx_source;
+ }
+ else if ( nhx_source instanceof StringBuilder ) {
+ _input_type = NHXParser.STRING_BUILDER;
+ _source_length = ( ( StringBuilder ) nhx_source ).length();
+ _nhx_source = nhx_source;
+ }
+ else if ( nhx_source instanceof char[] ) {
+ _input_type = NHXParser.CHAR_ARRAY;
+ _source_length = ( ( char[] ) nhx_source ).length;
+ _nhx_source = nhx_source;
+ }
+ else if ( nhx_source instanceof File ) {
+ _input_type = NHXParser.BUFFERED_READER;
+ _source_length = 0;
+ final File f = ( File ) nhx_source;
+ final String error = ForesterUtil.isReadableFile( f );
+ if ( !ForesterUtil.isEmpty( error ) ) {
+ throw new PhylogenyParserException( error );
+ }
+ _nhx_source = new BufferedReader( new FileReader( f ) );
+ }
+ else if ( nhx_source instanceof InputStream ) {
+ _input_type = NHXParser.BUFFERED_READER;
+ _source_length = 0;
+ final InputStreamReader isr = new InputStreamReader( ( InputStream ) nhx_source );
+ _nhx_source = new BufferedReader( isr );
+ }
+ else {
+ throw new IllegalArgumentException( getClass() + " can only parse objects of type String,"
+ + " StringBuffer, StringBuilder, char[], File," + " or InputStream "
+ + " [attempt to parse object of " + nhx_source.getClass() + "]." );
+ }
+ }
+
+ private final Phylogeny finishPhylogeny() throws PhylogenyParserException, NHXFormatException,
+ PhyloXmlDataFormatException {
+ if ( _current_phylogeny != null ) {
+ parseNHX( _current_anotation != null ? _current_anotation.toString() : "",
+ _current_phylogeny.getRoot(),
+ getTaxonomyExtraction(),
+ isReplaceUnderscores() );
+ if ( GUESS_IF_SUPPORT_VALUES ) {
+ if ( isBranchLengthsLikeBootstrapValues( _current_phylogeny ) ) {
+ moveBranchLengthsToConfidenceValues( _current_phylogeny );
+ }
+ }
+ if ( isGuessRootedness() ) {
+ final PhylogenyNode root = _current_phylogeny.getRoot();
+ if ( ( root.getDistanceToParent() >= 0.0 ) || !ForesterUtil.isEmpty( root.getName() )
+ || !ForesterUtil.isEmpty( PhylogenyMethods.getSpecies( root ) ) || root.isHasAssignedEvent() ) {
+ _current_phylogeny.setRooted( true );
+ }
+ }
+ return _current_phylogeny;
+ }
+ return null;
+ }
+
+ private final Phylogeny finishSingleNodePhylogeny() throws PhylogenyParserException, NHXFormatException,
+ PhyloXmlDataFormatException {
+ final PhylogenyNode new_node = new PhylogenyNode();
+ parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
+ _current_phylogeny = new Phylogeny();
+ _current_phylogeny.setRoot( new_node );
+ return _current_phylogeny;
+ }
+
+ private final void getNext() throws IOException, NHXFormatException {
while ( true ) {
char c = '\b';
- if ( getInputType() == NHXParser.BUFFERED_READER ) {
- final int ci = my_source_br.read();
+ if ( _input_type == BUFFERED_READER ) {
+ final int ci = _my_source_br.read();
if ( ci >= 0 ) {
c = ( char ) ci;
}
}
}
else {
- if ( i >= getSourceLength() ) {
+ if ( _i >= _source_length ) {
break;
}
else {
- switch ( getInputType() ) {
+ switch ( _input_type ) {
case STRING:
- c = my_source_str.charAt( i );
+ c = _my_source_str.charAt( _i );
break;
case STRING_BUFFER:
- c = my_source_sbuff.charAt( i );
+ c = _my_source_sbuff.charAt( _i );
break;
case STRING_BUILDER:
- c = my_source_sbuil.charAt( i );
+ c = _my_source_sbuil.charAt( _i );
break;
case CHAR_ARRAY:
- c = my_source_charary[ i ];
+ c = _my_source_charary[ _i ];
break;
}
}
}
- if ( !in_single_quote && !in_double_quote ) {
+ if ( !_in_single_quote && !_in_double_quote ) {
if ( c == ':' ) {
- saw_colon = true;
+ _saw_colon = true;
}
- else if ( !( ( c < 33 ) || ( c > 126 ) ) && saw_colon
+ else if ( !( ( c < 33 ) || ( c > 126 ) ) && _saw_colon
&& ( ( c != '[' ) && ( c != '.' ) && ( ( c < 48 ) || ( c > 57 ) ) ) ) {
- saw_colon = false;
+ _saw_colon = false;
}
- if ( in_open_bracket && ( c == ']' ) ) {
- in_open_bracket = false;
+ if ( _in_open_bracket && ( c == ']' ) ) {
+ _in_open_bracket = false;
}
}
// \n\t is always ignored,
// as is " (34) and ' (39) (space is 32):
- if ( ( isIgnoreQuotes() && ( ( c < 33 ) || ( c > 126 ) || ( c == 34 ) || ( c == 39 ) || ( ( getCladeLevel() == 0 ) && ( c == ';' ) ) ) )
- || ( !isIgnoreQuotes() && ( ( c < 32 ) || ( c > 126 ) || ( ( getCladeLevel() == 0 ) && ( c == ';' ) ) ) ) ) {
- // Do nothing.
+ if ( ( isIgnoreQuotes() && ( ( c < 33 ) || ( c > 126 ) || ( c == 34 ) || ( c == 39 ) || ( ( _clade_level == 0 ) && ( c == ';' ) ) ) )
+ || ( !isIgnoreQuotes() && ( ( c < 32 ) || ( c > 126 ) || ( ( _clade_level == 0 ) && ( c == ';' ) ) ) ) ) {
+ //do nothing
}
- else if ( ( c == 32 ) && ( !in_single_quote && !in_double_quote ) ) {
- // Do nothing.
+ else if ( ( c == 32 ) && ( !_in_single_quote && !_in_double_quote ) ) {
+ //do nothing
}
- else if ( in_comment ) {
+ else if ( _in_comment ) {
if ( c == ']' ) {
- in_comment = false;
+ _in_comment = false;
}
}
- else if ( in_double_quote ) {
+ else if ( _in_double_quote ) {
if ( c == '"' ) {
- in_double_quote = false;
+ _in_double_quote = false;
}
else {
- getCurrentAnotation().append( c );
+ _current_anotation.append( c );
}
}
else if ( c == '"' ) {
- in_double_quote = true;
+ _in_double_quote = true;
}
- else if ( in_single_quote ) {
+ else if ( _in_single_quote ) {
if ( c == 39 ) {
- in_single_quote = false;
+ _in_single_quote = false;
}
else {
- getCurrentAnotation().append( c );
+ _current_anotation.append( c );
}
}
else if ( c == 39 ) {
- in_single_quote = true;
+ _in_single_quote = true;
}
else if ( c == '[' ) {
- saw_open_bracket = true;
- in_open_bracket = true;
+ _saw_open_bracket = true;
+ _in_open_bracket = true;
}
- else if ( saw_open_bracket ) {
+ else if ( _saw_open_bracket ) {
if ( c != ']' ) {
// everything not starting with "[&" is considered a comment
// unless ":digits and/or . [bootstrap]":
if ( c == '&' ) {
- getCurrentAnotation().append( "[&" );
+ _current_anotation.append( "[&" );
}
- else if ( saw_colon ) {
- getCurrentAnotation().append( "[" + c );
+ else if ( _saw_colon ) {
+ _current_anotation.append( "[" + c );
}
else {
- in_comment = true;
+ _in_comment = true;
}
}
// comment consisting just of "[]":
- saw_open_bracket = false;
- }
- else if ( ( c == '(' ) && !in_open_bracket ) {
- processOpenParen();
+ _saw_open_bracket = false;
+ }
+ else if ( ( c == '(' ) && !_in_open_bracket ) {
+ final Phylogeny phy = processOpenParen();
+ if ( phy != null ) {
+ ++_i;
+ // return phy;
+ _next = phy;
+ return;
+ }
}
- else if ( ( c == ')' ) && !in_open_bracket ) {
+ else if ( ( c == ')' ) && !_in_open_bracket ) {
processCloseParen();
}
- else if ( ( c == ',' ) && !in_open_bracket ) {
+ else if ( ( c == ',' ) && !_in_open_bracket ) {
processComma();
}
else {
- getCurrentAnotation().append( c );
+ _current_anotation.append( c );
}
- ++i;
- }
- if ( getCladeLevel() != 0 ) {
- setPhylogenies( null );
- throw new PhylogenyParserException( "error in NH (Newick)/NHX formatted data: most likely cause: number of open parens does not equal number of close parens" );
- }
- if ( getCurrentPhylogeny() != null ) {
- finishPhylogeny();
- }
- else if ( getCurrentAnotation().length() > 0 ) {
- finishSingleNodePhylogeny();
- }
- else if ( getPhylogenies().size() < 1 ) {
- getPhylogenies().add( new Phylogeny() );
- }
- return getPhylogeniesAsArray();
- } // parse()
-
- public void setGuessRootedness( final boolean guess_rootedness ) {
- _guess_rootedness = guess_rootedness;
- }
-
- public void setIgnoreQuotes( final boolean ignore_quotes ) {
- _ignore_quotes = ignore_quotes;
- }
-
- public void setReplaceUnderscores( final boolean replace_underscores ) {
- _replace_underscores = replace_underscores;
- }
-
- /**
- * This sets the source to be parsed. The source can be: String,
- * StringBuffer, char[], File, or InputStream. The source can contain more
- * than one phylogenies in either New Hamphshire (NH) or New Hamphshire
- * Extended (NHX) format. There is no need to separate phylogenies with any
- * special character. White space is always ignored, as are semicolons
- * inbetween phylogenies. Example of a source describing two phylogenies
- * (source is a String, in this example): "(A,(B,(C,(D,E)de)cde)bcde)abcde
- * ((((A,B)ab,C)abc,D)abcd,E)abcde". Everything between a '[' followed by any
- * character other than '&' and ']' is considered a comment and ignored
- * (example: "[this is a comment]"). NHX tags are surrounded by '[&&NHX' and
- * ']' (example: "[&&NHX:S=Varanus_storri]"). A sequence like "[& some
- * info]" is ignored, too (at the PhylogenyNode level, though).
- * Exception: numbers only between [ and ] (e.g. [90]) are interpreted as support values.
- *
- * @see #parse()
- * @see org.forester.io.parsers.PhylogenyParser#setSource(java.lang.Object)
- * @param nhx_source
- * the source to be parsed (String, StringBuffer, char[], File,
- * or InputStream)
- * @throws IOException
- * @throws PhylogenyParserException
- */
- @Override
- public void setSource( final Object nhx_source ) throws PhylogenyParserException, IOException {
- if ( nhx_source == null ) {
- throw new PhylogenyParserException( getClass() + ": attempt to parse null object." );
- }
- else if ( nhx_source instanceof String ) {
- setInputType( NHXParser.STRING );
- setSourceLength( ( ( String ) nhx_source ).length() );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof StringBuilder ) {
- setInputType( NHXParser.STRING_BUILDER );
- setSourceLength( ( ( StringBuilder ) nhx_source ).length() );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof StringBuffer ) {
- setInputType( NHXParser.STRING_BUFFER );
- setSourceLength( ( ( StringBuffer ) nhx_source ).length() );
- setNhxSource( nhx_source );
+ ++_i;
+ } // while ( true )
+ if ( _clade_level != 0 ) {
+ throw new PhylogenyParserException( "error in NH (Newick) formatted data: most likely cause: number of open parens does not equal number of close parens" );
}
- else if ( nhx_source instanceof StringBuilder ) {
- setInputType( NHXParser.STRING_BUILDER );
- setSourceLength( ( ( StringBuilder ) nhx_source ).length() );
- setNhxSource( nhx_source );
+ if ( _current_phylogeny != null ) {
+ _next = finishPhylogeny();
+ _current_phylogeny = null;
+ _current_anotation = null;
}
- else if ( nhx_source instanceof char[] ) {
- setInputType( NHXParser.CHAR_ARRAY );
- setSourceLength( ( ( char[] ) nhx_source ).length );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof File ) {
- setInputType( NHXParser.BUFFERED_READER );
- setSourceLength( 0 );
- final File f = ( File ) nhx_source;
- final String error = ForesterUtil.isReadableFile( f );
- if ( !ForesterUtil.isEmpty( error ) ) {
- throw new PhylogenyParserException( error );
- }
- setNhxSource( new BufferedReader( new FileReader( f ) ) );
- }
- else if ( nhx_source instanceof InputStream ) {
- setInputType( NHXParser.BUFFERED_READER );
- setSourceLength( 0 );
- final InputStreamReader isr = new InputStreamReader( ( InputStream ) nhx_source );
- setNhxSource( new BufferedReader( isr ) );
+ else if ( ( _current_anotation != null ) && ( _current_anotation.length() > 0 ) ) {
+ _next = finishSingleNodePhylogeny();
+ _current_anotation = null;
}
else {
- throw new IllegalArgumentException( getClass() + " can only parse objects of type String,"
- + " StringBuffer, char[], File," + " or InputStream " + " [attempt to parse object of "
- + nhx_source.getClass() + "]." );
- }
- }
-
- public void setTaxonomyExtraction( final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction ) {
- _taxonomy_extraction = taxonomy_extraction;
- }
-
- /**
- * Decreases the clade level by one.
- *
- * @throws PhylogenyParserException
- * if level goes below zero.
- */
- private void decreaseCladeLevel() throws PhylogenyParserException {
- if ( getCladeLevel() < 0 ) {
- throw new PhylogenyParserException( "error in NH (Newick)/NHX formatted data: most likely cause: number of close parens is larger than number of open parens" );
- }
- --_clade_level;
- }
-
- /**
- * Finishes the current Phylogeny and adds it to the list of Phylogenies
- * created.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- * @throws PhyloXmlDataFormatException
- */
- private void finishPhylogeny() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
- setCladeLevel( 0 );
- if ( getCurrentPhylogeny() != null ) {
- parseNHX( getCurrentAnotation().toString(),
- getCurrentPhylogeny().getRoot(),
- getTaxonomyExtraction(),
- isReplaceUnderscores() );
- if ( NHXParser.GUESS_IF_SUPPORT_VALUES ) {
- if ( NHXParser.isBranchLengthsLikeBootstrapValues( getCurrentPhylogeny() ) ) {
- NHXParser.moveBranchLengthsToConfidenceValues( getCurrentPhylogeny() );
- }
- }
- if ( isGuessRootedness() ) {
- final PhylogenyNode root = getCurrentPhylogeny().getRoot();
- if ( ( root.getDistanceToParent() >= 0.0 ) || !ForesterUtil.isEmpty( root.getName() )
- || !ForesterUtil.isEmpty( PhylogenyMethods.getSpecies( root ) ) || root.isHasAssignedEvent() ) {
- getCurrentPhylogeny().setRooted( true );
- }
- }
- getPhylogenies().add( getCurrentPhylogeny() );
- }
- }
-
- private void finishSingleNodePhylogeny() throws PhylogenyParserException, NHXFormatException,
- PhyloXmlDataFormatException {
- setCladeLevel( 0 );
- final PhylogenyNode new_node = new PhylogenyNode();
- parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
- setCurrentPhylogeny( new Phylogeny() );
- getCurrentPhylogeny().setRoot( new_node );
- getPhylogenies().add( getCurrentPhylogeny() );
- }
-
- private int getCladeLevel() {
- return _clade_level;
- }
-
- private StringBuilder getCurrentAnotation() {
- return _current_anotation;
- }
-
- private PhylogenyNode getCurrentNode() {
- return _current_node;
- }
-
- private Phylogeny getCurrentPhylogeny() {
- return _current_phylogeny;
- }
-
- private byte getInputType() {
- return _input_type;
- }
-
- private Object getNhxSource() {
- return _nhx_source;
- }
-
- private List<Phylogeny> getPhylogenies() {
- return _phylogenies;
- }
-
- /**
- * Returns the Phylogenies created as Array.
- *
- * @return the Phylogenies created as Array
- */
- private Phylogeny[] getPhylogeniesAsArray() {
- final Phylogeny[] p = new Phylogeny[ getPhylogenies().size() ];
- for( int i = 0; i < getPhylogenies().size(); ++i ) {
- p[ i ] = getPhylogenies().get( i );
+ _next = null;
}
- return p;
- }
-
- private int getSourceLength() {
- return _source_length;
- }
-
- /**
- * Increases the clade level by one.
- */
- private void increaseCladeLevel() {
- ++_clade_level;
}
- private void init() {
+ private final void init() {
setTaxonomyExtraction( TAXONOMY_EXTRACTION_DEFAULT );
setReplaceUnderscores( REPLACE_UNDERSCORES_DEFAULT );
setGuessRootedness( GUESS_ROOTEDNESS_DEFAULT );
setIgnoreQuotes( IGNORE_QUOTES_DEFAULT );
}
- private boolean isGuessRootedness() {
+ private final boolean isGuessRootedness() {
return _guess_rootedness;
}
- private boolean isIgnoreQuotes() {
+ private final boolean isIgnoreQuotes() {
return _ignore_quotes;
}
- private boolean isReplaceUnderscores() {
+ private final boolean isReplaceUnderscores() {
return _replace_underscores;
}
- private boolean isSawClosingParen() {
- return _saw_closing_paren;
- }
-
- /**
- * Replaces the current annotation with a new StringBuffer.
- */
- private void newCurrentAnotation() {
- setCurrentAnotation( new StringBuilder() );
- }
-
- /**
- * Called if a closing paren is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- * @throws PhyloXmlDataFormatException
- */
- private void processCloseParen() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
- decreaseCladeLevel();
- if ( !isSawClosingParen() ) {
+ private final void processCloseParen() throws PhylogenyParserException, NHXFormatException,
+ PhyloXmlDataFormatException {
+ if ( _clade_level < 0 ) {
+ throw new PhylogenyParserException( "error in NH (Newick)/NHX formatted data: most likely cause: number of close parens is larger than number of open parens" );
+ }
+ --_clade_level;
+ if ( !_saw_closing_paren ) {
final PhylogenyNode new_node = new PhylogenyNode();
- parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
- newCurrentAnotation();
- getCurrentNode().addAsChild( new_node );
+ parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
+ _current_anotation = new StringBuilder();
+ _current_node.addAsChild( new_node );
}
else {
- parseNHX( getCurrentAnotation().toString(),
- getCurrentNode().getLastChildNode(),
+ parseNHX( _current_anotation.toString(),
+ _current_node.getLastChildNode(),
getTaxonomyExtraction(),
isReplaceUnderscores() );
- newCurrentAnotation();
- }
- if ( !getCurrentNode().isRoot() ) {
- setCurrentNode( getCurrentNode().getParent() );
- }
- setSawClosingParen( true );
- } // processCloseParen()
-
- /**
- * Called if a comma is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- * @throws PhyloXmlDataFormatException
- */
- private void processComma() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
- if ( !isSawClosingParen() ) {
+ _current_anotation = new StringBuilder();
+ }
+ if ( !_current_node.isRoot() ) {
+ _current_node = _current_node.getParent();
+ }
+ _saw_closing_paren = true;
+ }
+
+ private final void processComma() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
+ if ( !_saw_closing_paren ) {
final PhylogenyNode new_node = new PhylogenyNode();
- parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
- if ( getCurrentNode() == null ) {
+ parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
+ if ( _current_node == null ) {
throw new NHXFormatException( "format might not be NH or NHX" );
}
- getCurrentNode().addAsChild( new_node );
+ _current_node.addAsChild( new_node );
}
else {
- parseNHX( getCurrentAnotation().toString(),
- getCurrentNode().getLastChildNode(),
+ parseNHX( _current_anotation.toString(),
+ _current_node.getLastChildNode(),
getTaxonomyExtraction(),
isReplaceUnderscores() );
}
- newCurrentAnotation();
- setSawClosingParen( false );
- } // processComma()
-
- /**
- * Called if a opening paren is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- * @throws PhyloXmlDataFormatException
- */
- private void processOpenParen() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
+ _current_anotation = new StringBuilder();
+ _saw_closing_paren = false;
+ }
+
+ private final Phylogeny processOpenParen() throws PhylogenyParserException, NHXFormatException,
+ PhyloXmlDataFormatException {
+ Phylogeny phy = null;
final PhylogenyNode new_node = new PhylogenyNode();
- if ( getCladeLevel() == 0 ) {
- if ( getCurrentPhylogeny() != null ) {
- finishPhylogeny();
+ if ( _clade_level == 0 ) {
+ if ( _current_phylogeny != null ) {
+ phy = finishPhylogeny();
}
- setCladeLevel( 1 );
- newCurrentAnotation();
- setCurrentPhylogeny( new Phylogeny() );
- getCurrentPhylogeny().setRoot( new_node );
+ _clade_level = 1;
+ _current_anotation = new StringBuilder();
+ _current_phylogeny = new Phylogeny();
+ _current_phylogeny.setRoot( new_node );
}
else {
- increaseCladeLevel();
- getCurrentNode().addAsChild( new_node );
+ ++_clade_level;
+ _current_node.addAsChild( new_node );
}
- setCurrentNode( new_node );
- setSawClosingParen( false );
- }
-
- private void setCladeLevel( final int clade_level ) {
- if ( clade_level < 0 ) {
- throw new IllegalArgumentException( "Attempt to set clade level to a number smaller than zero." );
- }
- _clade_level = clade_level;
- }
-
- private void setCurrentAnotation( final StringBuilder current_anotation ) {
- _current_anotation = current_anotation;
- }
-
- private void setCurrentNode( final PhylogenyNode current_node ) {
- _current_node = current_node;
- }
-
- private void setCurrentPhylogeny( final Phylogeny current_phylogeny ) {
- _current_phylogeny = current_phylogeny;
- }
-
- private void setInputType( final byte input_type ) {
- _input_type = input_type;
+ _current_node = new_node;
+ _saw_closing_paren = false;
+ return phy;
}
- private void setNhxSource( final Object nhx_source ) {
- _nhx_source = nhx_source;
- }
-
- private void setPhylogenies( final ArrayList<Phylogeny> phylogenies ) {
- _phylogenies = phylogenies;
- }
-
- private void setSawClosingParen( final boolean saw_closing_paren ) {
- _saw_closing_paren = saw_closing_paren;
- }
-
- private void setSourceLength( final int source_length ) {
- _source_length = source_length;
- }
-
- public static void parseNHX( String s,
- final PhylogenyNode node_to_annotate,
- final TAXONOMY_EXTRACTION taxonomy_extraction,
- final boolean replace_underscores ) throws NHXFormatException,
+ public final static void parseNHX( String s,
+ final PhylogenyNode node_to_annotate,
+ final TAXONOMY_EXTRACTION taxonomy_extraction,
+ final boolean replace_underscores ) throws NHXFormatException,
PhyloXmlDataFormatException {
if ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) && replace_underscores ) {
throw new IllegalArgumentException( "cannot extract taxonomies and replace under scores at the same time" );
}
while ( t.hasMoreTokens() ) {
s = t.nextToken();
- if ( s.startsWith( org.forester.io.parsers.nhx.NHXtags.SPECIES_NAME ) ) {
+ if ( s.startsWith( NHXtags.SPECIES_NAME ) ) {
if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
}
node_to_annotate.getNodeData().getTaxonomy().setScientificName( s.substring( 2 ) );
}
- else if ( s.startsWith( org.forester.io.parsers.nhx.NHXtags.IS_DUPLICATION ) ) {
+ else if ( s.startsWith( NHXtags.IS_DUPLICATION ) ) {
if ( ( s.charAt( 2 ) == 'Y' ) || ( s.charAt( 2 ) == 'T' ) ) {
node_to_annotate.getNodeData().setEvent( Event.createSingleDuplicationEvent() );
}
}
node_to_annotate.getNodeData().getTaxonomy().setIdentifier( new Identifier( s.substring( 2 ) ) );
}
- else if ( s.startsWith( NHXtags.PARENT_BRANCH_WIDTH ) ) {
- PhylogenyMethods.setBranchWidthValue( node_to_annotate, Integer.parseInt( s.substring( 2 ) ) );
- }
- else if ( s.startsWith( NHXtags.COLOR ) ) {
- final Color c = NHXParser.stringToColor( s.substring( 2 ) );
- if ( c != null ) {
- PhylogenyMethods.setBranchColorValue( node_to_annotate, c );
- }
- }
else if ( s.startsWith( NHXtags.DOMAIN_STRUCTURE ) ) {
if ( !node_to_annotate.getNodeData().isHasSequence() ) {
node_to_annotate.getNodeData().setSequence( new Sequence() );
}
}
- private static double doubleValue( final String str ) throws NHXFormatException {
+ private final static double doubleValue( final String str ) throws NHXFormatException {
try {
return Double.valueOf( str ).doubleValue();
}
}
}
- private static boolean isBranchLengthsLikeBootstrapValues( final Phylogeny p ) {
+ private final static boolean isBranchLengthsLikeBootstrapValues( final Phylogeny p ) {
final PhylogenyNodeIterator it = p.iteratorExternalForward();
final double d0 = it.next().getDistanceToParent();
if ( ( d0 < 10 ) || !it.hasNext() ) {
return true;
}
- private static void moveBranchLengthsToConfidenceValues( final Phylogeny p ) {
+ private final static void moveBranchLengthsToConfidenceValues( final Phylogeny p ) {
final PhylogenyNodeIterator it = p.iteratorPostorder();
while ( it.hasNext() ) {
final PhylogenyNode n = it.next();
}
}
- private static void processMrBayes3Data( final String s, final PhylogenyNode node_to_annotate )
+ private final static void processMrBayes3Data( final String s, final PhylogenyNode node_to_annotate )
throws NHXFormatException {
double sd = -1;
final Matcher mb_prob_sd_matcher = MB_PROB_SD_PATTERN.matcher( s );
}
}
- /**
- * Parses String s in the format r.g.b (e.g. "12.34.234" ) into red, green,
- * and blue and returns the corresponding Color.
- */
- private static Color stringToColor( final String s ) {
- final StringTokenizer st = new StringTokenizer( s, "." );
- if ( st.countTokens() != 3 ) {
- throw new IllegalArgumentException( "illegal format for color: " + s );
- }
- final int red = ForesterUtil.limitRangeForColor( Integer.parseInt( st.nextToken() ) );
- final int green = ForesterUtil.limitRangeForColor( Integer.parseInt( st.nextToken() ) );
- final int blu = ForesterUtil.limitRangeForColor( Integer.parseInt( st.nextToken() ) );
- return new Color( red, green, blu );
- }
-
public static enum TAXONOMY_EXTRACTION {
NO, YES, PFAM_STYLE_ONLY;
}
+++ /dev/null
-// $Id:
-// FORESTER -- software libraries and applications
-// for evolutionary biology research and applications.
-//
-// Copyright (C) 2008-2009 Christian M. Zmasek
-// Copyright (C) 2008-2009 Burnham Institute for Medical Research
-// All rights reserved
-//
-// This library is free software; you can redistribute it and/or
-// modify it under the terms of the GNU Lesser General Public
-// License as published by the Free Software Foundation; either
-// version 2.1 of the License, or (at your option) any later version.
-//
-// This library is distributed in the hope that it will be useful,
-// but WITHOUT ANY WARRANTY; without even the implied warranty of
-// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
-// Lesser General Public License for more details.
-//
-// You should have received a copy of the GNU Lesser General Public
-// License along with this library; if not, write to the Free Software
-// Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
-//
-// Contact: phylosoft @ gmail . com
-// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
-
-package org.forester.io.parsers.nhx;
-
-import java.awt.Color;
-import java.io.BufferedReader;
-import java.io.File;
-import java.io.FileNotFoundException;
-import java.io.FileReader;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.InputStreamReader;
-import java.util.ArrayList;
-import java.util.List;
-import java.util.StringTokenizer;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-
-import org.forester.io.parsers.PhylogenyParser;
-import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
-import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
-import org.forester.io.parsers.util.ParserUtils;
-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.Accession;
-import org.forester.phylogeny.data.Confidence;
-import org.forester.phylogeny.data.DomainArchitecture;
-import org.forester.phylogeny.data.Event;
-import org.forester.phylogeny.data.Identifier;
-import org.forester.phylogeny.data.PhylogenyDataUtil;
-import org.forester.phylogeny.data.Sequence;
-import org.forester.phylogeny.data.Taxonomy;
-import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
-import org.forester.util.ForesterUtil;
-
-public final class NHXParser2 implements PhylogenyParser {
-
- public static final TAXONOMY_EXTRACTION TAXONOMY_EXTRACTION_DEFAULT = TAXONOMY_EXTRACTION.NO;
- final static private boolean GUESS_ROOTEDNESS_DEFAULT = true;
- final static private boolean GUESS_IF_SUPPORT_VALUES = true;
- final static private boolean IGNORE_QUOTES_DEFAULT = false;
- final static public boolean REPLACE_UNDERSCORES_DEFAULT = false;
- private boolean _saw_closing_paren;
- final static private byte STRING = 0;
- final static private byte STRING_BUFFER = 1;
- final static private byte CHAR_ARRAY = 2;
- final static private byte BUFFERED_READER = 3;
- final static private byte STRING_BUILDER = 4;
- private boolean _guess_rootedness;
- private boolean _ignore_quotes;
- private byte _input_type;
- private int _source_length;
- private PhylogenyNode _current_node;
- private StringBuilder _current_anotation;
- private Object _nhx_source;
- private int _clade_level;
- private Phylogeny _current_phylogeny;
- private TAXONOMY_EXTRACTION _taxonomy_extraction;
- private boolean _replace_underscores;
- public final static Pattern UC_LETTERS_NUMBERS_PATTERN = Pattern.compile( "^[A-Z0-9]+$" );
- public final static Pattern NUMBERS_ONLY_PATTERN = Pattern.compile( "^[0-9\\.]+$" );
- public final static Pattern MB_PROB_PATTERN = Pattern.compile( "prob=([^,]+)" );
- public final static Pattern MB_PROB_SD_PATTERN = Pattern.compile( "prob_stddev=([^,]+)" );
- public final static Pattern MB_BL_PATTERN = Pattern.compile( "length_median=([^,]+)" );
- boolean _in_comment = false;
- boolean _saw_colon = false;
- boolean _saw_open_bracket = false;
- boolean _in_open_bracket = false;
- boolean _in_double_quote = false;
- boolean _in_single_quote = false;
- String _my_source_str = null;
- StringBuffer _my_source_sbuff = null;
- StringBuilder _my_source_sbuil = null;
- char[] _my_source_charary = null;
- BufferedReader _my_source_br = null;
- int _i;
- private Phylogeny _next;
- private Object _source;
-
- public NHXParser2() {
- init();
- }
-
- public TAXONOMY_EXTRACTION getTaxonomyExtraction() {
- return _taxonomy_extraction;
- }
-
- public boolean hasNext() {
- return _next != null;
- }
-
- public Phylogeny next() throws NHXFormatException, IOException {
- final Phylogeny phy = _next;
- getNext();
- return phy;
- }
-
- @Override
- public Phylogeny[] parse() throws IOException {
- reset();
- List<Phylogeny> l = new ArrayList<Phylogeny>();
- System.out.println( ">> _next=" + _next );
- while ( hasNext() ) {
- Phylogeny n = next();
- System.out.println( ">> going to add " + n );
- l.add( n );
- }
- final Phylogeny[] p = new Phylogeny[ l.size() ];
- for( int i = 0; i < l.size(); ++i ) {
- p[ i ] = l.get( i );
- }
- return p;
- }
-
- public void reset() throws NHXFormatException, IOException {
- _i = 0;
- _next = null;
- _in_comment = false;
- _saw_colon = false;
- _saw_open_bracket = false;
- _in_open_bracket = false;
- _in_double_quote = false;
- _in_single_quote = false;
- setCladeLevel( 0 );
- newCurrentAnotation();
- setCurrentPhylogeny( null );
- setCurrentNode( null );
- _my_source_str = null;
- _my_source_sbuff = null;
- _my_source_sbuil = null;
- _my_source_charary = null;
- _my_source_br = null;
- determineSourceType( _source );
- switch ( getInputType() ) {
- case STRING:
- _my_source_str = ( String ) getNhxSource();
- break;
- case STRING_BUFFER:
- _my_source_sbuff = ( StringBuffer ) getNhxSource();
- break;
- case STRING_BUILDER:
- _my_source_sbuil = ( StringBuilder ) getNhxSource();
- break;
- case CHAR_ARRAY:
- _my_source_charary = ( char[] ) getNhxSource();
- break;
- case BUFFERED_READER:
- if ( _my_source_br != null ) {
- try {
- _my_source_br.close();
- }
- catch ( IOException e ) {
- //do nothing
- }
- }
- _my_source_br = ( BufferedReader ) getNhxSource();
- break;
- default:
- throw new RuntimeException( "unknown input type" );
- }
- getNext();
- }
-
- public void setGuessRootedness( final boolean guess_rootedness ) {
- _guess_rootedness = guess_rootedness;
- }
-
- public void setIgnoreQuotes( final boolean ignore_quotes ) {
- _ignore_quotes = ignore_quotes;
- }
-
- public void setReplaceUnderscores( final boolean replace_underscores ) {
- _replace_underscores = replace_underscores;
- }
-
- /**
- * This sets the source to be parsed. The source can be: String,
- * StringBuffer, char[], File, or InputStream. The source can contain more
- * than one phylogenies in either New Hamphshire (NH) or New Hamphshire
- * Extended (NHX) format. There is no need to separate phylogenies with any
- * special character. White space is always ignored, as are semicolons
- * inbetween phylogenies. Example of a source describing two phylogenies
- * (source is a String, in this example): "(A,(B,(C,(D,E)de)cde)bcde)abcde
- * ((((A,B)ab,C)abc,D)abcd,E)abcde". Everything between a '[' followed by any
- * character other than '&' and ']' is considered a comment and ignored
- * (example: "[this is a comment]"). NHX tags are surrounded by '[&&NHX' and
- * ']' (example: "[&&NHX:S=Varanus_storri]"). A sequence like "[& some
- * info]" is ignored, too (at the PhylogenyNode level, though).
- * Exception: numbers only between [ and ] (e.g. [90]) are interpreted as support values.
- *
- * @see #parse()
- * @see org.forester.io.parsers.PhylogenyParser#setSource(java.lang.Object)
- * @param nhx_source
- * the source to be parsed (String, StringBuffer, char[], File,
- * or InputStream)
- * @throws NHXFormatException
- * @throws IOException
- * @throws PhylogenyParserException
- */
- @Override
- public void setSource( final Object nhx_source ) throws NHXFormatException, IOException {
- _source = nhx_source;
- reset();
- }
-
- private void determineSourceType( final Object nhx_source ) throws PhylogenyParserException, FileNotFoundException {
- if ( nhx_source == null ) {
- throw new PhylogenyParserException( getClass() + ": attempt to parse null object." );
- }
- else if ( nhx_source instanceof String ) {
- setInputType( NHXParser2.STRING );
- setSourceLength( ( ( String ) nhx_source ).length() );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof StringBuilder ) {
- setInputType( NHXParser2.STRING_BUILDER );
- setSourceLength( ( ( StringBuilder ) nhx_source ).length() );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof StringBuffer ) {
- setInputType( NHXParser2.STRING_BUFFER );
- setSourceLength( ( ( StringBuffer ) nhx_source ).length() );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof StringBuilder ) {
- setInputType( NHXParser2.STRING_BUILDER );
- setSourceLength( ( ( StringBuilder ) nhx_source ).length() );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof char[] ) {
- setInputType( NHXParser2.CHAR_ARRAY );
- setSourceLength( ( ( char[] ) nhx_source ).length );
- setNhxSource( nhx_source );
- }
- else if ( nhx_source instanceof File ) {
- setInputType( NHXParser2.BUFFERED_READER );
- setSourceLength( 0 );
- final File f = ( File ) nhx_source;
- final String error = ForesterUtil.isReadableFile( f );
- if ( !ForesterUtil.isEmpty( error ) ) {
- throw new PhylogenyParserException( error );
- }
- setNhxSource( new BufferedReader( new FileReader( f ) ) );
- }
- else if ( nhx_source instanceof InputStream ) {
- setInputType( NHXParser2.BUFFERED_READER );
- setSourceLength( 0 );
- final InputStreamReader isr = new InputStreamReader( ( InputStream ) nhx_source );
- setNhxSource( new BufferedReader( isr ) );
- }
- else {
- throw new IllegalArgumentException( getClass() + " can only parse objects of type String,"
- + " StringBuffer, StringBuilder, char[], File," + " or InputStream "
- + " [attempt to parse object of " + nhx_source.getClass() + "]." );
- }
- }
-
- public void setTaxonomyExtraction( final TAXONOMY_EXTRACTION taxonomy_extraction ) {
- _taxonomy_extraction = taxonomy_extraction;
- }
-
- /**
- * Decreases the clade level by one.
- *
- * @throws PhylogenyParserException
- * if level goes below zero.
- */
- private void decreaseCladeLevel() throws PhylogenyParserException {
- if ( getCladeLevel() < 0 ) {
- throw new PhylogenyParserException( "error in NH (Newick)/NHX formatted data: most likely cause: number of close parens is larger than number of open parens" );
- }
- --_clade_level;
- }
-
- private Phylogeny finishPhylogeny2() throws PhylogenyParserException, NHXFormatException,
- PhyloXmlDataFormatException {
- //setCladeLevel( 0 );
- if ( getCurrentPhylogeny() != null ) {
- System.out.println( "fp: cp=" + getCurrentPhylogeny() );
- if ( getCurrentAnotation() != null ) {
- System.out.println( "fp: ca=" + getCurrentAnotation().toString() );
- }
- else {
- System.out.println( "fp: ca=null" );
- }
- parseNHX( getCurrentAnotation() != null ? getCurrentAnotation().toString() : "", getCurrentPhylogeny()
- .getRoot(), getTaxonomyExtraction(), isReplaceUnderscores() );
- if ( GUESS_IF_SUPPORT_VALUES ) {
- if ( isBranchLengthsLikeBootstrapValues( getCurrentPhylogeny() ) ) {
- moveBranchLengthsToConfidenceValues( getCurrentPhylogeny() );
- }
- }
- if ( isGuessRootedness() ) {
- final PhylogenyNode root = getCurrentPhylogeny().getRoot();
- if ( ( root.getDistanceToParent() >= 0.0 ) || !ForesterUtil.isEmpty( root.getName() )
- || !ForesterUtil.isEmpty( PhylogenyMethods.getSpecies( root ) ) || root.isHasAssignedEvent() ) {
- getCurrentPhylogeny().setRooted( true );
- }
- }
- return getCurrentPhylogeny();
- }
- return null;
- }
-
- private Phylogeny finishSingleNodePhylogeny2() throws PhylogenyParserException, NHXFormatException,
- PhyloXmlDataFormatException {
- // setCladeLevel( 0 );
- final PhylogenyNode new_node = new PhylogenyNode();
- parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
- setCurrentPhylogeny( new Phylogeny() );
- getCurrentPhylogeny().setRoot( new_node );
- return getCurrentPhylogeny();
- }
-
- private int getCladeLevel() {
- return _clade_level;
- }
-
- private StringBuilder getCurrentAnotation() {
- return _current_anotation;
- }
-
- private PhylogenyNode getCurrentNode() {
- return _current_node;
- }
-
- private Phylogeny getCurrentPhylogeny() {
- return _current_phylogeny;
- }
-
- private byte getInputType() {
- return _input_type;
- }
-
- private void getNext() throws IOException, NHXFormatException {
- while ( true ) {
- char c = '\b';
- if ( getInputType() == BUFFERED_READER ) {
- final int ci = _my_source_br.read();
- if ( ci >= 0 ) {
- c = ( char ) ci;
- }
- else {
- break;
- }
- }
- else {
- if ( _i >= getSourceLength() ) {
- break;
- }
- else {
- switch ( getInputType() ) {
- case STRING:
- c = _my_source_str.charAt( _i );
- break;
- case STRING_BUFFER:
- c = _my_source_sbuff.charAt( _i );
- break;
- case STRING_BUILDER:
- c = _my_source_sbuil.charAt( _i );
- break;
- case CHAR_ARRAY:
- c = _my_source_charary[ _i ];
- break;
- }
- }
- }
- if ( !_in_single_quote && !_in_double_quote ) {
- if ( c == ':' ) {
- _saw_colon = true;
- }
- else if ( !( ( c < 33 ) || ( c > 126 ) ) && _saw_colon
- && ( ( c != '[' ) && ( c != '.' ) && ( ( c < 48 ) || ( c > 57 ) ) ) ) {
- _saw_colon = false;
- }
- if ( _in_open_bracket && ( c == ']' ) ) {
- _in_open_bracket = false;
- }
- }
- // \n\t is always ignored,
- // as is " (34) and ' (39) (space is 32):
- if ( ( isIgnoreQuotes() && ( ( c < 33 ) || ( c > 126 ) || ( c == 34 ) || ( c == 39 ) || ( ( getCladeLevel() == 0 ) && ( c == ';' ) ) ) )
- || ( !isIgnoreQuotes() && ( ( c < 32 ) || ( c > 126 ) || ( ( getCladeLevel() == 0 ) && ( c == ';' ) ) ) ) ) {
- // Do nothing.
- }
- else if ( ( c == 32 ) && ( !_in_single_quote && !_in_double_quote ) ) {
- // Do nothing.
- }
- else if ( _in_comment ) {
- if ( c == ']' ) {
- _in_comment = false;
- }
- }
- else if ( _in_double_quote ) {
- if ( c == '"' ) {
- _in_double_quote = false;
- }
- else {
- getCurrentAnotation().append( c );
- }
- }
- else if ( c == '"' ) {
- _in_double_quote = true;
- }
- else if ( _in_single_quote ) {
- if ( c == 39 ) {
- _in_single_quote = false;
- }
- else {
- getCurrentAnotation().append( c );
- }
- }
- else if ( c == 39 ) {
- _in_single_quote = true;
- }
- else if ( c == '[' ) {
- _saw_open_bracket = true;
- _in_open_bracket = true;
- }
- else if ( _saw_open_bracket ) {
- if ( c != ']' ) {
- // everything not starting with "[&" is considered a comment
- // unless ":digits and/or . [bootstrap]":
- if ( c == '&' ) {
- getCurrentAnotation().append( "[&" );
- }
- else if ( _saw_colon ) {
- getCurrentAnotation().append( "[" + c );
- }
- else {
- _in_comment = true;
- }
- }
- // comment consisting just of "[]":
- _saw_open_bracket = false;
- }
- else if ( ( c == '(' ) && !_in_open_bracket ) {
- final Phylogeny phy = processOpenParen2();
- if ( phy != null ) {
- ++_i;
- // return phy;
- _next = phy;
- return;
- }
- }
- else if ( ( c == ')' ) && !_in_open_bracket ) {
- processCloseParen();
- }
- else if ( ( c == ',' ) && !_in_open_bracket ) {
- processComma();
- }
- else {
- getCurrentAnotation().append( c );
- }
- ++_i;
- } // while ( true )
- System.out.println( "done with loop" );
- if ( getCurrentPhylogeny() == null ) {
- System.out.println( "... but is null" );
- }
- if ( getCladeLevel() != 0 ) {
- throw new PhylogenyParserException( "error in NH (Newick) formatted data: most likely cause: number of open parens does not equal number of close parens" );
- }
- if ( getCurrentPhylogeny() != null ) {
- System.out.println( "... and current=" + getCurrentPhylogeny() );
- _next = finishPhylogeny2();
- System.out.println( "... _next=" + _next );
- setCurrentPhylogeny( null );
- setCurrentAnotation( null );
- //return finishPhylogeny2();
- }
- else if ( ( getCurrentAnotation() != null ) && ( getCurrentAnotation().length() > 0 ) ) {
- System.out.println( "1node=" + getCurrentAnotation() );
- _next = finishSingleNodePhylogeny2();
- setCurrentAnotation( null );
- //return finishSingleNodePhylogeny2();
- }
- else {
- _next = null;
- //return null;
- }
- }
-
- private Object getNhxSource() {
- return _nhx_source;
- }
-
- private int getSourceLength() {
- return _source_length;
- }
-
- private void increaseCladeLevel() {
- ++_clade_level;
- }
-
- private void init() {
- setTaxonomyExtraction( TAXONOMY_EXTRACTION_DEFAULT );
- setReplaceUnderscores( REPLACE_UNDERSCORES_DEFAULT );
- setGuessRootedness( GUESS_ROOTEDNESS_DEFAULT );
- setIgnoreQuotes( IGNORE_QUOTES_DEFAULT );
- }
-
- private boolean isGuessRootedness() {
- return _guess_rootedness;
- }
-
- private boolean isIgnoreQuotes() {
- return _ignore_quotes;
- }
-
- private boolean isReplaceUnderscores() {
- return _replace_underscores;
- }
-
- private boolean isSawClosingParen() {
- return _saw_closing_paren;
- }
-
- /**
- * Replaces the current annotation with a new StringBuffer.
- */
- private void newCurrentAnotation() {
- setCurrentAnotation( new StringBuilder() );
- }
-
- /**
- * Called if a closing paren is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- * @throws PhyloXmlDataFormatException
- */
- private void processCloseParen() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
- decreaseCladeLevel();
- if ( !isSawClosingParen() ) {
- final PhylogenyNode new_node = new PhylogenyNode();
- parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
- newCurrentAnotation();
- getCurrentNode().addAsChild( new_node );
- }
- else {
- parseNHX( getCurrentAnotation().toString(),
- getCurrentNode().getLastChildNode(),
- getTaxonomyExtraction(),
- isReplaceUnderscores() );
- newCurrentAnotation();
- }
- if ( !getCurrentNode().isRoot() ) {
- setCurrentNode( getCurrentNode().getParent() );
- }
- setSawClosingParen( true );
- }
-
- /**
- * Called if a comma is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- * @throws PhyloXmlDataFormatException
- */
- private void processComma() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
- if ( !isSawClosingParen() ) {
- final PhylogenyNode new_node = new PhylogenyNode();
- parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
- if ( getCurrentNode() == null ) {
- throw new NHXFormatException( "format might not be NH or NHX" );
- }
- getCurrentNode().addAsChild( new_node );
- }
- else {
- parseNHX( getCurrentAnotation().toString(),
- getCurrentNode().getLastChildNode(),
- getTaxonomyExtraction(),
- isReplaceUnderscores() );
- }
- newCurrentAnotation();
- setSawClosingParen( false );
- }
-
- private Phylogeny processOpenParen2() throws PhylogenyParserException, NHXFormatException,
- PhyloXmlDataFormatException {
- Phylogeny phy = null;
- final PhylogenyNode new_node = new PhylogenyNode();
- System.out.println( "level=" + getCladeLevel() );
- if ( getCladeLevel() == 0 ) {
- if ( getCurrentPhylogeny() != null ) {
- phy = finishPhylogeny2();
- }
- setCladeLevel( 1 );
- newCurrentAnotation();
- setCurrentPhylogeny( new Phylogeny() );
- getCurrentPhylogeny().setRoot( new_node );
- }
- else {
- increaseCladeLevel();
- getCurrentNode().addAsChild( new_node );
- }
- setCurrentNode( new_node );
- setSawClosingParen( false );
- if ( phy != null ) {
- System.out.println( "processOpenParen2 returns " + phy.toString() );
- }
- else {
- System.out.println( "processOpenParen2 returns null" );
- }
- return phy;
- }
-
- private void setCladeLevel( final int clade_level ) {
- if ( clade_level < 0 ) {
- throw new IllegalArgumentException( "attempt to set clade level to a number smaller than zero" );
- }
- _clade_level = clade_level;
- }
-
- private void setCurrentAnotation( final StringBuilder current_anotation ) {
- _current_anotation = current_anotation;
- }
-
- private void setCurrentNode( final PhylogenyNode current_node ) {
- _current_node = current_node;
- }
-
- private void setCurrentPhylogeny( final Phylogeny current_phylogeny ) {
- _current_phylogeny = current_phylogeny;
- }
-
- private void setInputType( final byte input_type ) {
- _input_type = input_type;
- }
-
- private void setNhxSource( final Object nhx_source ) {
- _nhx_source = nhx_source;
- }
-
- private void setSawClosingParen( final boolean saw_closing_paren ) {
- _saw_closing_paren = saw_closing_paren;
- }
-
- private void setSourceLength( final int source_length ) {
- _source_length = source_length;
- }
-
- public static void parseNHX( String s,
- final PhylogenyNode node_to_annotate,
- final TAXONOMY_EXTRACTION taxonomy_extraction,
- final boolean replace_underscores ) throws NHXFormatException,
- PhyloXmlDataFormatException {
- if ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) && replace_underscores ) {
- throw new IllegalArgumentException( "cannot extract taxonomies and replace under scores at the same time" );
- }
- if ( ( s != null ) && ( s.length() > 0 ) ) {
- if ( replace_underscores ) {
- s = s.replaceAll( "_+", " " );
- }
- boolean is_nhx = false;
- final int ob = s.indexOf( "[" );
- if ( ob > -1 ) {
- String b = "";
- is_nhx = true;
- final int cb = s.indexOf( "]" );
- if ( cb < 0 ) {
- throw new NHXFormatException( "error in NHX formatted data: no closing \"]\" in \"" + s + "\"" );
- }
- if ( s.indexOf( "&&NHX" ) == ( ob + 1 ) ) {
- b = s.substring( ob + 6, cb );
- }
- else {
- // No &&NHX and digits only: is likely to be a support value.
- final String bracketed = s.substring( ob + 1, cb );
- final Matcher numbers_only = NUMBERS_ONLY_PATTERN.matcher( bracketed );
- if ( numbers_only.matches() ) {
- b = ":" + NHXtags.SUPPORT + bracketed;
- }
- else if ( s.indexOf( "prob=" ) > -1 ) {
- processMrBayes3Data( s, node_to_annotate );
- }
- }
- s = s.substring( 0, ob ) + b;
- if ( ( s.indexOf( "[" ) > -1 ) || ( s.indexOf( "]" ) > -1 ) ) {
- throw new NHXFormatException( "error in NHX formatted data: more than one \"]\" or \"[\"" );
- }
- }
- final StringTokenizer t = new StringTokenizer( s, ":" );
- if ( t.countTokens() > 0 ) {
- if ( !s.startsWith( ":" ) ) {
- node_to_annotate.setName( t.nextToken() );
- if ( !replace_underscores && ( !is_nhx && ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) ) ) {
- ParserUtils.extractTaxonomyDataFromNodeName( node_to_annotate, taxonomy_extraction );
- }
- }
- while ( t.hasMoreTokens() ) {
- s = t.nextToken();
- if ( s.startsWith( org.forester.io.parsers.nhx.NHXtags.SPECIES_NAME ) ) {
- if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
- node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
- }
- node_to_annotate.getNodeData().getTaxonomy().setScientificName( s.substring( 2 ) );
- }
- else if ( s.startsWith( org.forester.io.parsers.nhx.NHXtags.IS_DUPLICATION ) ) {
- if ( ( s.charAt( 2 ) == 'Y' ) || ( s.charAt( 2 ) == 'T' ) ) {
- node_to_annotate.getNodeData().setEvent( Event.createSingleDuplicationEvent() );
- }
- else if ( ( s.charAt( 2 ) == 'N' ) || ( s.charAt( 2 ) == 'F' ) ) {
- node_to_annotate.getNodeData().setEvent( Event.createSingleSpeciationEvent() );
- }
- else if ( s.charAt( 2 ) == '?' ) {
- node_to_annotate.getNodeData().setEvent( Event.createSingleSpeciationOrDuplicationEvent() );
- }
- else {
- throw new NHXFormatException( "error in NHX formatted data: :D=Y or :D=N or :D=?" );
- }
- }
- else if ( s.startsWith( NHXtags.SUPPORT ) ) {
- PhylogenyMethods.setConfidence( node_to_annotate, doubleValue( s.substring( 2 ) ) );
- }
- else if ( s.startsWith( NHXtags.TAXONOMY_ID ) ) {
- if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
- node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
- }
- node_to_annotate.getNodeData().getTaxonomy().setIdentifier( new Identifier( s.substring( 2 ) ) );
- }
- else if ( s.startsWith( NHXtags.PARENT_BRANCH_WIDTH ) ) {
- PhylogenyMethods.setBranchWidthValue( node_to_annotate, Integer.parseInt( s.substring( 2 ) ) );
- }
- else if ( s.startsWith( NHXtags.COLOR ) ) {
- final Color c = NHXParser2.stringToColor( s.substring( 2 ) );
- if ( c != null ) {
- PhylogenyMethods.setBranchColorValue( node_to_annotate, c );
- }
- }
- else if ( s.startsWith( NHXtags.DOMAIN_STRUCTURE ) ) {
- if ( !node_to_annotate.getNodeData().isHasSequence() ) {
- node_to_annotate.getNodeData().setSequence( new Sequence() );
- }
- node_to_annotate.getNodeData().getSequence()
- .setDomainArchitecture( new DomainArchitecture( s.substring( 3 ) ) );
- }
- else if ( s.startsWith( NHXtags.SEQUENCE_ACCESSION ) ) {
- if ( !node_to_annotate.getNodeData().isHasSequence() ) {
- node_to_annotate.getNodeData().setSequence( new Sequence() );
- }
- node_to_annotate.getNodeData().getSequence()
- .setAccession( new Accession( s.substring( 3 ), "?" ) );
- }
- else if ( s.startsWith( NHXtags.GENE_NAME ) ) {
- if ( !node_to_annotate.getNodeData().isHasSequence() ) {
- node_to_annotate.getNodeData().setSequence( new Sequence() );
- }
- node_to_annotate.getNodeData().getSequence().setName( s.substring( 3 ) );
- }
- else if ( s.indexOf( '=' ) < 0 ) {
- if ( node_to_annotate.getDistanceToParent() != PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT ) {
- throw new NHXFormatException( "error in NHX formatted data: more than one distance to parent:"
- + "\"" + s + "\"" );
- }
- node_to_annotate.setDistanceToParent( doubleValue( s ) );
- }
- } // while ( t.hasMoreTokens() )
- }
- }
- }
-
- private static double doubleValue( final String str ) throws NHXFormatException {
- try {
- return Double.valueOf( str ).doubleValue();
- }
- catch ( final NumberFormatException ex ) {
- throw new NHXFormatException( "error in NH/NHX formatted data: failed to parse number from " + "\"" + str
- + "\"" );
- }
- }
-
- private static boolean isBranchLengthsLikeBootstrapValues( final Phylogeny p ) {
- final PhylogenyNodeIterator it = p.iteratorExternalForward();
- final double d0 = it.next().getDistanceToParent();
- if ( ( d0 < 10 ) || !it.hasNext() ) {
- return false;
- }
- while ( it.hasNext() ) {
- final double d = it.next().getDistanceToParent();
- if ( ( d != d0 ) || ( d < 10 ) ) {
- return false;
- }
- }
- return true;
- }
-
- private static void moveBranchLengthsToConfidenceValues( final Phylogeny p ) {
- final PhylogenyNodeIterator it = p.iteratorPostorder();
- while ( it.hasNext() ) {
- final PhylogenyNode n = it.next();
- PhylogenyMethods.setBootstrapConfidence( n, n.getDistanceToParent() );
- n.setDistanceToParent( PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT );
- }
- }
-
- private static void processMrBayes3Data( final String s, final PhylogenyNode node_to_annotate )
- throws NHXFormatException {
- double sd = -1;
- final Matcher mb_prob_sd_matcher = MB_PROB_SD_PATTERN.matcher( s );
- if ( mb_prob_sd_matcher.find() ) {
- try {
- sd = Double.parseDouble( mb_prob_sd_matcher.group( 1 ) );
- }
- catch ( final NumberFormatException e ) {
- throw new NHXFormatException( "failed to parse probability standard deviation (Mr Bayes output) from \""
- + s + "\"" );
- }
- }
- final Matcher mb_prob_matcher = MB_PROB_PATTERN.matcher( s );
- if ( mb_prob_matcher.find() ) {
- double prob = -1;
- try {
- prob = Double.parseDouble( mb_prob_matcher.group( 1 ) );
- }
- catch ( final NumberFormatException e ) {
- throw new NHXFormatException( "failed to parse probability (Mr Bayes output) from \"" + s + "\"" );
- }
- if ( prob >= 0.0 ) {
- if ( sd >= 0.0 ) {
- node_to_annotate.getBranchData()
- .addConfidence( new Confidence( prob, "posterior probability", sd ) );
- }
- else {
- node_to_annotate.getBranchData().addConfidence( new Confidence( prob, "posterior probability" ) );
- }
- }
- }
- final Matcher mb_bl_matcher = MB_BL_PATTERN.matcher( s );
- if ( mb_bl_matcher.find() ) {
- double bl = -1;
- try {
- bl = Double.parseDouble( mb_bl_matcher.group( 1 ) );
- }
- catch ( final NumberFormatException e ) {
- throw new NHXFormatException( "failed to parse median branch length (Mr Bayes output) from \"" + s
- + "\"" );
- }
- if ( bl >= 0.0 ) {
- node_to_annotate.setDistanceToParent( bl );
- }
- }
- }
-
- /**
- * Parses String s in the format r.g.b (e.g. "12.34.234" ) into red, green,
- * and blue and returns the corresponding Color.
- */
- private static Color stringToColor( final String s ) {
- final StringTokenizer st = new StringTokenizer( s, "." );
- if ( st.countTokens() != 3 ) {
- throw new IllegalArgumentException( "illegal format for color: " + s );
- }
- final int red = ForesterUtil.limitRangeForColor( Integer.parseInt( st.nextToken() ) );
- final int green = ForesterUtil.limitRangeForColor( Integer.parseInt( st.nextToken() ) );
- final int blu = ForesterUtil.limitRangeForColor( Integer.parseInt( st.nextToken() ) );
- return new Color( red, green, blu );
- }
-}
public final class NHXtags {
- public static final String COLOR = "C=";
- public static final String PARENT_BRANCH_WIDTH = "W=";
- public static final String TAXONOMY_ID = "T=";
- public static final String SUPPORT = "B=";
- public static final String IS_DUPLICATION = "D=";
- public static final String SPECIES_NAME = "S=";
- public static final String DOMAIN_STRUCTURE = "DS=";
- public static final String GENE_NAME = "GN=";
- public static final String SEQUENCE_ACCESSION = "AC=";
- public static final Object BRANCH_WIDTH = "W=";
+ public static final String TAXONOMY_ID = "T=";
+ public static final String SUPPORT = "B=";
+ public static final String IS_DUPLICATION = "D=";
+ public static final String SPECIES_NAME = "S=";
+ public static final String DOMAIN_STRUCTURE = "DS=";
+ public static final String GENE_NAME = "GN=";
+ public static final String SEQUENCE_ACCESSION = "AC=";
}
import java.io.IOException;
import java.io.Writer;
-import org.forester.io.parsers.nhx.NHXtags;
import org.forester.io.parsers.phyloxml.PhyloXmlMapping;
import org.forester.util.ForesterUtil;
@Override
public StringBuffer toNHX() {
- final StringBuffer sb = new StringBuffer();
- sb.append( NHXtags.COLOR );
- sb.append( getValue().getRed() );
- sb.append( "." );
- sb.append( getValue().getGreen() );
- sb.append( "." );
- sb.append( getValue().getBlue() );
- return sb;
+ throw new UnsupportedOperationException();
}
@Override
sb.append( ":" );
sb.append( getConfidence( 0 ).toNHX() );
}
- if ( isHasBranchWidth() && ( getBranchWidth().getValue() != BranchWidth.BRANCH_WIDTH_DEFAULT_VALUE ) ) {
- sb.append( ":" );
- sb.append( getBranchWidth().toNHX() );
- }
- if ( isHasBranchColor() && ( getBranchColor().getValue() != null ) ) {
- sb.append( ":" );
- sb.append( getBranchColor().toNHX() );
- }
return sb;
}
import java.io.IOException;
import java.io.Writer;
-import org.forester.io.parsers.nhx.NHXtags;
import org.forester.io.parsers.phyloxml.PhyloXmlMapping;
import org.forester.util.ForesterUtil;
@Override
public StringBuffer toNHX() {
- final StringBuffer sb = new StringBuffer();
- sb.append( NHXtags.PARENT_BRANCH_WIDTH );
- sb.append( getValue() );
- return sb;
+ throw new UnsupportedOperationException();
}
@Override
if ( isHasEvent() ) {
sb.append( getEvent().toNHX() );
}
- if ( isHasProperties() ) {
- sb.append( getProperties().toNHX() );
- }
return sb;
}
@Override
public StringBuffer toNHX() {
- final StringBuffer sb = new StringBuffer();
- if ( getProperties() != null ) {
- for( final String ref : getProperties().keySet() ) {
- sb.append( getProperties().get( ref ).toNHX() );
- }
- }
- return sb;
+ throw new UnsupportedOperationException();
}
@Override
@Override
public StringBuffer toNHX() {
- final StringBuffer nhx = new StringBuffer();
- nhx.append( ":X" );
- switch ( getAppliesTo() ) {
- case CLADE:
- nhx.append( "C=" );
- break;
- case NODE:
- nhx.append( "N=" );
- break;
- case PARENT_BRANCH:
- nhx.append( "B=" );
- break;
- case PHYLOGENY:
- nhx.append( "P=" );
- break;
- case ANNOTATION:
- nhx.append( "S=" );
- break;
- default:
- nhx.append( "O=" );
- break;
- }
- if ( !getDataType().equals( "" ) ) {
- if ( getDataType().equals( "xsd:string" ) ) {
- nhx.append( "S=" );
- }
- else if ( getDataType().equals( "xsd:long" ) ) {
- nhx.append( "L=" );
- }
- else if ( getDataType().equals( "xsd:decimal" ) ) {
- nhx.append( "D=" );
- }
- else if ( getDataType().equals( "xsd:boolean" ) ) {
- nhx.append( "B=" );
- }
- else if ( getDataType().equals( "xsd:anyUR" ) ) {
- nhx.append( "U=" );
- }
- }
- nhx.append( getRef() );
- nhx.append( "=" );
- nhx.append( getValue() );
- if ( !getUnit().equals( "" ) ) {
- nhx.append( "=" );
- nhx.append( getUnit() );
- }
- return nhx;
+ throw new UnsupportedOperationException();
}
@Override
import org.forester.io.parsers.nexus.NexusPhylogeniesParser;
import org.forester.io.parsers.nhx.NHXParser;
import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
-import org.forester.io.parsers.nhx.NHXParser2;
import org.forester.io.parsers.phyloxml.PhyloXmlParser;
import org.forester.io.parsers.tol.TolParser;
import org.forester.io.parsers.util.ParserUtils;
System.out.println( "failed." );
failed++;
}
- System.exit( 0 );
System.out.print( "Conversion to NHX (node level): " );
if ( Test.testNHXconversion() ) {
System.out.println( "OK." );
if ( t8.getHeight() != 15 ) {
return false;
}
- final char[] a9 = new char[] {};
+ final char[] a9 = new char[] { 'a' };
final Phylogeny t9 = factory.create( a9, new NHXParser() )[ 0 ];
if ( t9.getHeight() != 0 ) {
return false;
private static boolean testNHParsing() {
try {
final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- final Phylogeny p1 = factory.create( "(A,B1)", new NHXParser2() )[ 0 ];
+ final Phylogeny p1 = factory.create( "(A,B1)", new NHXParser() )[ 0 ];
if ( !p1.toNewHampshireX().equals( "(A,B1)" ) ) {
return false;
}
if ( !p1b.toNewHampshire().equals( "(';A;',';B;1;');" ) ) {
return false;
}
- final Phylogeny p2 = factory.create( new StringBuffer( "(A,B2)" ), new NHXParser2() )[ 0 ];
- final Phylogeny p3 = factory.create( new char[] { '(', 'A', ',', 'B', '3', ')' }, new NHXParser2() )[ 0 ];
- final Phylogeny p4 = factory.create( "(A,B4);", new NHXParser2() )[ 0 ];
- final Phylogeny p5 = factory.create( new StringBuffer( "(A,B5);" ), new NHXParser2() )[ 0 ];
- final Phylogeny[] p7 = factory.create( "(A,B7);(C,D7)", new NHXParser2() );
- final Phylogeny[] p8 = factory.create( "(A,B8) (C,D8)", new NHXParser2() );
- final Phylogeny[] p9 = factory.create( "(A,B9)\n(C,D9)", new NHXParser2() );
- final Phylogeny[] p10 = factory.create( "(A,B10);(C,D10);", new NHXParser2() );
- final Phylogeny[] p11 = factory.create( "(A,B11);(C,D11) (E,F11)\t(G,H11)", new NHXParser2() );
- final Phylogeny[] p12 = factory.create( "(A,B12) (C,D12) (E,F12) (G,H12)", new NHXParser2() );
+ final Phylogeny p2 = factory.create( new StringBuffer( "(A,B2)" ), new NHXParser() )[ 0 ];
+ final Phylogeny p3 = factory.create( new char[] { '(', 'A', ',', 'B', '3', ')' }, new NHXParser() )[ 0 ];
+ final Phylogeny p4 = factory.create( "(A,B4);", new NHXParser() )[ 0 ];
+ final Phylogeny p5 = factory.create( new StringBuffer( "(A,B5);" ), new NHXParser() )[ 0 ];
+ final Phylogeny[] p7 = factory.create( "(A,B7);(C,D7)", new NHXParser() );
+ final Phylogeny[] p8 = factory.create( "(A,B8) (C,D8)", new NHXParser() );
+ final Phylogeny[] p9 = factory.create( "(A,B9)\n(C,D9)", new NHXParser() );
+ final Phylogeny[] p10 = factory.create( "(A,B10);(C,D10);", new NHXParser() );
+ final Phylogeny[] p11 = factory.create( "(A,B11);(C,D11) (E,F11)\t(G,H11)", new NHXParser() );
+ final Phylogeny[] p12 = factory.create( "(A,B12) (C,D12) (E,F12) (G,H12)", new NHXParser() );
final Phylogeny[] p13 = factory.create( " ; (;A; , ; B ; 1 3 ; \n)\t ( \n ;"
+ " C ; ,; D;13;);;;;;;(;E;,;F;13 ;) ; "
+ "; ; ( \t\n\r\b; G ;, ;H ;1 3; ) ; ; ;",
- new NHXParser2() );
+ new NHXParser() );
if ( !p13[ 0 ].toNewHampshireX().equals( "(';A;',';B;13;')" ) ) {
return false;
}
if ( !p13[ 3 ].toNewHampshireX().equals( "(';G;',';H;13;')" ) ) {
return false;
}
- final Phylogeny[] p14 = factory.create( "(A,B14)ab", new NHXParser2() );
- final Phylogeny[] p15 = factory.create( "(A,B15)ab;", new NHXParser2() );
+ final Phylogeny[] p14 = factory.create( "(A,B14)ab", new NHXParser() );
+ final Phylogeny[] p15 = factory.create( "(A,B15)ab;", new NHXParser() );
final String p16_S = "((A,B),C)";
- final Phylogeny[] p16 = factory.create( p16_S, new NHXParser2() );
+ final Phylogeny[] p16 = factory.create( p16_S, new NHXParser() );
if ( p16.length != 1 ) {
return false;
}
return false;
}
final String p17_S = "(C,(A,B))";
- final Phylogeny[] p17 = factory.create( p17_S, new NHXParser2() );
+ final Phylogeny[] p17 = factory.create( p17_S, new NHXParser() );
if ( p17.length != 1 ) {
return false;
}
return false;
}
final String p18_S = "((A,B),(C,D))";
- final Phylogeny[] p18 = factory.create( p18_S, new NHXParser2() );
+ final Phylogeny[] p18 = factory.create( p18_S, new NHXParser() );
if ( p18.length != 1 ) {
return false;
}
return false;
}
final String p19_S = "(((A,B),C),D)";
- final Phylogeny[] p19 = factory.create( p19_S, new NHXParser2() );
+ final Phylogeny[] p19 = factory.create( p19_S, new NHXParser() );
if ( p19.length != 1 ) {
return false;
}
return false;
}
final String p20_S = "(A,(B,(C,D)))";
- final Phylogeny[] p20 = factory.create( p20_S, new NHXParser2() );
+ final Phylogeny[] p20 = factory.create( p20_S, new NHXParser() );
if ( p20.length != 1 ) {
return false;
}
return false;
}
final String p21_S = "(A,(B,(C,(D,E))))";
- final Phylogeny[] p21 = factory.create( p21_S, new NHXParser2() );
+ final Phylogeny[] p21 = factory.create( p21_S, new NHXParser() );
if ( p21.length != 1 ) {
return false;
}
return false;
}
final String p22_S = "((((A,B),C),D),E)";
- final Phylogeny[] p22 = factory.create( p22_S, new NHXParser2() );
+ final Phylogeny[] p22 = factory.create( p22_S, new NHXParser() );
if ( p22.length != 1 ) {
return false;
}
return false;
}
final String p23_S = "(A,(B,(C,(D,E)de)cde)bcde)abcde";
- final Phylogeny[] p23 = factory.create( p23_S, new NHXParser2() );
+ final Phylogeny[] p23 = factory.create( p23_S, new NHXParser() );
if ( p23.length != 1 ) {
System.out.println( "xl=" + p23.length );
System.exit( -1 );
return false;
}
final String p24_S = "((((A,B)ab,C)abc,D)abcd,E)abcde";
- final Phylogeny[] p24 = factory.create( p24_S, new NHXParser2() );
+ final Phylogeny[] p24 = factory.create( p24_S, new NHXParser() );
if ( p24.length != 1 ) {
return false;
}
}
final String p241_S1 = "(A,(B,(C,(D,E)de)cde)bcde)abcde";
final String p241_S2 = "((((A,B)ab,C)abc,D)abcd,E)abcde";
- final Phylogeny[] p241 = factory.create( p241_S1 + p241_S2, new NHXParser2() );
+ final Phylogeny[] p241 = factory.create( p241_S1 + p241_S2, new NHXParser() );
if ( p241.length != 2 ) {
return false;
}
+ "E)abcde)abcd,E)abcde,((((A,B)ab,C)abc,D)abcd,E)abcde)"
+ "ab,C)abc,((((A,B)ab,C)abc,D)abcd,E)abcde)abcd,E)abcde"
+ ")ab,C)abc,D)abcd,E)abcde)ab,C)abc,((((A,B)ab,C)abc,D)" + "abcd,E)abcde)abcd,E)abcde";
- final Phylogeny[] p25 = factory.create( p25_S, new NHXParser2() );
+ final Phylogeny[] p25 = factory.create( p25_S, new NHXParser() );
if ( !p25[ 0 ].toNewHampshireX().equals( p25_S ) ) {
return false;
}
final String p26_S = "(A,B)ab";
- final Phylogeny[] p26 = factory.create( p26_S, new NHXParser2() );
+ final Phylogeny[] p26 = factory.create( p26_S, new NHXParser() );
if ( !p26[ 0 ].toNewHampshireX().equals( p26_S ) ) {
return false;
}
final String p27_S = "((((A,B)ab,C)abc,D)abcd,E)abcde";
- final Phylogeny[] p27s = factory.create( p27_S, new NHXParser2() );
+ final Phylogeny[] p27s = factory.create( p27_S, new NHXParser() );
if ( p27s.length != 1 ) {
System.out.println( "xxl=" + p27s.length );
System.exit( -1 );
return false;
}
final Phylogeny[] p27 = factory.create( new File( Test.PATH_TO_TEST_DATA + "phylogeny27.nhx" ),
- new NHXParser2() );
+ new NHXParser() );
if ( p27.length != 1 ) {
System.out.println( "yl=" + p27.length );
System.exit( -1 );
final String p28_S3 = "(A,B)ab";
final String p28_S4 = "((((A,B),C),D),;E;)";
final Phylogeny[] p28 = factory.create( new File( Test.PATH_TO_TEST_DATA + "phylogeny28.nhx" ),
- new NHXParser2() );
+ new NHXParser() );
if ( !p28[ 0 ].toNewHampshireX().equals( p28_S1 ) ) {
return false;
}
return false;
}
final String p29_S = "((((A:0.01,B:0.684)ab:0.345,C:0.3451)abc:0.3451,D:1.5)abcd:0.134,E:0.32)abcde:0.1345";
- final Phylogeny[] p29 = factory.create( p29_S, new NHXParser2() );
+ final Phylogeny[] p29 = factory.create( p29_S, new NHXParser() );
if ( !p29[ 0 ].toNewHampshireX().equals( p29_S ) ) {
return false;
}
final String p30_S = "((((A:0.01,B:0.02):0.93,C:0.04):0.05,D:1.4):0.06,E):0.72";
- final Phylogeny[] p30 = factory.create( p30_S, new NHXParser2() );
+ final Phylogeny[] p30 = factory.create( p30_S, new NHXParser() );
if ( !p30[ 0 ].toNewHampshireX().equals( p30_S ) ) {
return false;
}
final String p32_S = " ; ; \n \t \b \f \r ;;;;;; ";
- final Phylogeny[] p32 = factory.create( p32_S, new NHXParser2() );
+ final Phylogeny[] p32 = factory.create( p32_S, new NHXParser() );
if ( ( p32.length != 0 ) ) {
return false;
}
final String p33_S = "A";
- final Phylogeny[] p33 = factory.create( p33_S, new NHXParser2() );
+ final Phylogeny[] p33 = factory.create( p33_S, new NHXParser() );
if ( !p33[ 0 ].toNewHampshireX().equals( p33_S ) ) {
return false;
}
final String p34_S = "B;";
- final Phylogeny[] p34 = factory.create( p34_S, new NHXParser2() );
+ final Phylogeny[] p34 = factory.create( p34_S, new NHXParser() );
if ( !p34[ 0 ].toNewHampshireX().equals( "B" ) ) {
return false;
}
final String p35_S = "B:0.2";
- final Phylogeny[] p35 = factory.create( p35_S, new NHXParser2() );
+ final Phylogeny[] p35 = factory.create( p35_S, new NHXParser() );
if ( !p35[ 0 ].toNewHampshireX().equals( p35_S ) ) {
return false;
}
final String p36_S = "(A)";
- final Phylogeny[] p36 = factory.create( p36_S, new NHXParser2() );
+ final Phylogeny[] p36 = factory.create( p36_S, new NHXParser() );
if ( !p36[ 0 ].toNewHampshireX().equals( p36_S ) ) {
return false;
}
final String p37_S = "((A))";
- final Phylogeny[] p37 = factory.create( p37_S, new NHXParser2() );
+ final Phylogeny[] p37 = factory.create( p37_S, new NHXParser() );
if ( !p37[ 0 ].toNewHampshireX().equals( p37_S ) ) {
return false;
}
final String p38_S = "(((((((A:0.2):0.2):0.3):0.4):0.5):0.6):0.7):0.8";
- final Phylogeny[] p38 = factory.create( p38_S, new NHXParser2() );
+ final Phylogeny[] p38 = factory.create( p38_S, new NHXParser() );
if ( !p38[ 0 ].toNewHampshireX().equals( p38_S ) ) {
return false;
}
final String p39_S = "(((B,((((A:0.2):0.2):0.3):0.4):0.5):0.6):0.7):0.8";
- final Phylogeny[] p39 = factory.create( p39_S, new NHXParser2() );
+ final Phylogeny[] p39 = factory.create( p39_S, new NHXParser() );
if ( !p39[ 0 ].toNewHampshireX().equals( p39_S ) ) {
return false;
}
final String p40_S = "(A,B,C)";
- final Phylogeny[] p40 = factory.create( p40_S, new NHXParser2() );
+ final Phylogeny[] p40 = factory.create( p40_S, new NHXParser() );
if ( !p40[ 0 ].toNewHampshireX().equals( p40_S ) ) {
return false;
}
final String p41_S = "(A,B,C,D,E,F,G,H,I,J,K)";
- final Phylogeny[] p41 = factory.create( p41_S, new NHXParser2() );
+ final Phylogeny[] p41 = factory.create( p41_S, new NHXParser() );
if ( !p41[ 0 ].toNewHampshireX().equals( p41_S ) ) {
return false;
}
final String p42_S = "(A,B,(X,Y,Z),D,E,F,G,H,I,J,K)";
- final Phylogeny[] p42 = factory.create( p42_S, new NHXParser2() );
+ final Phylogeny[] p42 = factory.create( p42_S, new NHXParser() );
if ( !p42[ 0 ].toNewHampshireX().equals( p42_S ) ) {
return false;
}
final String p43_S = "(A,B,C,(AA,BB,CC,(CCC,DDD,EEE,(FFFF,GGGG)x)y,DD,EE,FF,GG,HH),D,E,(EE,FF),F,G,H,(((((5)4)3)2)1),I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,(XX,(YY)),Y,Z)";
- final Phylogeny[] p43 = factory.create( p43_S, new NHXParser2() );
+ final Phylogeny[] p43 = factory.create( p43_S, new NHXParser() );
if ( !p43[ 0 ].toNewHampshireX().equals( p43_S ) ) {
return false;
}
final String p44_S = "(((A,B,C,D),(A,B,C,D),(A,B,C,D),(A,B,C,D)),((A,B,C,D),(A,B,C,D),(A,B,C,D),(A,B,C,D)),((A,B,C,D),(A,B,C,D),(A,B,C,D),(A,B,C,D)),((A,B,C,D),(A,B,C,D),(A,B,C,D),(A,B,C,D)))";
- final Phylogeny[] p44 = factory.create( p44_S, new NHXParser2() );
+ final Phylogeny[] p44 = factory.create( p44_S, new NHXParser() );
if ( !p44[ 0 ].toNewHampshireX().equals( p44_S ) ) {
return false;
}
final String p45_S = "((((((((((A))))))))),(((((((((B))))))))),(((((((((C))))))))))";
- final Phylogeny[] p45 = factory.create( p45_S, new NHXParser2() );
+ final Phylogeny[] p45 = factory.create( p45_S, new NHXParser() );
if ( !p45[ 0 ].toNewHampshireX().equals( p45_S ) ) {
return false;
}
final String p46_S = "";
- final Phylogeny[] p46 = factory.create( p46_S, new NHXParser2() );
+ final Phylogeny[] p46 = factory.create( p46_S, new NHXParser() );
if ( p46.length != 0 ) {
return false;
}
- final Phylogeny p47 = factory.create( new StringBuffer( "((A,B)ab:2[0.44],C)" ), new NHXParser2() )[ 0 ];
+ final Phylogeny p47 = factory.create( new StringBuffer( "((A,B)ab:2[0.44],C)" ), new NHXParser() )[ 0 ];
if ( !isEqual( 0.44, p47.getNode( "ab" ).getBranchData().getConfidence( 0 ).getValue() ) ) {
return false;
}
- final Phylogeny p48 = factory.create( new StringBuffer( "((A,B)ab:2[88],C)" ), new NHXParser2() )[ 0 ];
+ final Phylogeny p48 = factory.create( new StringBuffer( "((A,B)ab:2[88],C)" ), new NHXParser() )[ 0 ];
if ( !isEqual( 88, p48.getNode( "ab" ).getBranchData().getConfidence( 0 ).getValue() ) ) {
return false;
}
final Phylogeny p49 = factory
.create( new StringBuffer( "((A,B)a[comment:a,b;(a)]b:2[0.44][comment(a,b,b);],C)" ),
- new NHXParser2() )[ 0 ];
+ new NHXParser() )[ 0 ];
if ( !isEqual( 0.44, p49.getNode( "ab" ).getBranchData().getConfidence( 0 ).getValue() ) ) {
return false;
}
- final Phylogeny p50 = factory.create( new StringBuffer( "((\"A\",B)ab:2[88],C)" ), new NHXParser2() )[ 0 ];
+ final Phylogeny p50 = factory.create( new StringBuffer( "((\"A\",B)ab:2[88],C)" ), new NHXParser() )[ 0 ];
if ( p50.getNode( "A" ) == null ) {
return false;
}
.equals( "((A,B)88:2.0,C);" ) ) {
return false;
}
- final Phylogeny p51 = factory.create( new StringBuffer( "((\"A(A\",B)ab:2[88],C)" ), new NHXParser2() )[ 0 ];
+ final Phylogeny p51 = factory.create( new StringBuffer( "((\"A(A\",B)ab:2[88],C)" ), new NHXParser() )[ 0 ];
if ( p51.getNode( "A(A" ) == null ) {
return false;
}
- final Phylogeny p52 = factory.create( new StringBuffer( "(('A(A',B)ab:2[88],C)" ), new NHXParser2() )[ 0 ];
+ final Phylogeny p52 = factory.create( new StringBuffer( "(('A(A',B)ab:2[88],C)" ), new NHXParser() )[ 0 ];
if ( p52.getNode( "A(A" ) == null ) {
return false;
}
final Phylogeny p53 = factory
.create( new StringBuffer( "(('A(A',\"B (x (a' ,b) f(x);\"[com])[ment]ab:2[88],C)" ),
- new NHXParser2() )[ 0 ];
+ new NHXParser() )[ 0 ];
if ( p53.getNode( "B (x (a' ,b) f(x);" ) == null ) {
return false;
}
//
- final Phylogeny p54 = factory.create( new StringBuffer( "((A,B):[88],C)" ), new NHXParser2() )[ 0 ];
+ final Phylogeny p54 = factory.create( new StringBuffer( "((A,B):[88],C)" ), new NHXParser() )[ 0 ];
if ( p54.getNode( "A" ) == null ) {
return false;
}
private static boolean testNHParsingIter() {
try {
- String p0_str = "(A,B);";
- NHXParser2 p = new NHXParser2();
+ final String p0_str = "(A,B);";
+ final NHXParser p = new NHXParser();
p.setSource( p0_str );
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p0 = p.next();
+ final Phylogeny p0 = p.next();
if ( !p0.toNewHampshire().equals( p0_str ) ) {
System.out.println( p0.toNewHampshire() );
return false;
return false;
}
//
- String p00_str = "(A,B)root;";
+ final String p00_str = "(A,B)root;";
p.setSource( p00_str );
- Phylogeny p00 = p.next();
+ final Phylogeny p00 = p.next();
if ( !p00.toNewHampshire().equals( p00_str ) ) {
System.out.println( p00.toNewHampshire() );
return false;
}
//
- String p000_str = "A;";
+ final String p000_str = "A;";
p.setSource( p000_str );
- Phylogeny p000 = p.next();
+ final Phylogeny p000 = p.next();
if ( !p000.toNewHampshire().equals( p000_str ) ) {
System.out.println( p000.toNewHampshire() );
return false;
}
//
- String p0000_str = "A";
+ final String p0000_str = "A";
p.setSource( p0000_str );
- Phylogeny p0000 = p.next();
+ final Phylogeny p0000 = p.next();
if ( !p0000.toNewHampshire().equals( "A;" ) ) {
System.out.println( p0000.toNewHampshire() );
return false;
}
//
p.setSource( "(A)" );
- Phylogeny p00000 = p.next();
+ final Phylogeny p00000 = p.next();
if ( !p00000.toNewHampshire().equals( "(A);" ) ) {
System.out.println( p00000.toNewHampshire() );
return false;
}
//
- String p1_str = "(A,B)(C,D)(E,F)(G,H)";
+ final String p1_str = "(A,B)(C,D)(E,F)(G,H)";
p.setSource( p1_str );
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p1_0 = p.next();
+ final Phylogeny p1_0 = p.next();
if ( !p1_0.toNewHampshire().equals( "(A,B);" ) ) {
System.out.println( p1_0.toNewHampshire() );
return false;
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p1_1 = p.next();
+ final Phylogeny p1_1 = p.next();
if ( !p1_1.toNewHampshire().equals( "(C,D);" ) ) {
System.out.println( "(C,D) != " + p1_1.toNewHampshire() );
return false;
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p1_2 = p.next();
+ final Phylogeny p1_2 = p.next();
if ( !p1_2.toNewHampshire().equals( "(E,F);" ) ) {
System.out.println( "(E,F) != " + p1_2.toNewHampshire() );
return false;
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p1_3 = p.next();
+ final Phylogeny p1_3 = p.next();
if ( !p1_3.toNewHampshire().equals( "(G,H);" ) ) {
System.out.println( "(G,H) != " + p1_3.toNewHampshire() );
return false;
return false;
}
//
- String p2_str = "((1,2,3),B);(C,D) (E,F)root;(G,H); ;(X)";
+ final String p2_str = "((1,2,3),B);(C,D) (E,F)root;(G,H); ;(X)";
p.setSource( p2_str );
if ( !p.hasNext() ) {
return false;
return false;
}
//
- String p3_str = "((A,B),C)abc";
+ final String p3_str = "((A,B),C)abc";
p.setSource( p3_str );
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p3_0 = p.next();
+ final Phylogeny p3_0 = p.next();
if ( !p3_0.toNewHampshire().equals( "((A,B),C)abc;" ) ) {
return false;
}
return false;
}
//
- String p4_str = "((A,B)ab,C)abc";
+ final String p4_str = "((A,B)ab,C)abc";
p.setSource( p4_str );
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p4_0 = p.next();
+ final Phylogeny p4_0 = p.next();
if ( !p4_0.toNewHampshire().equals( "((A,B)ab,C)abc;" ) ) {
return false;
}
return false;
}
//
- String p5_str = "(((A,B)ab,C)abc,D)abcd";
+ final String p5_str = "(((A,B)ab,C)abc,D)abcd";
p.setSource( p5_str );
if ( !p.hasNext() ) {
return false;
}
- Phylogeny p5_0 = p.next();
+ final Phylogeny p5_0 = p.next();
if ( !p5_0.toNewHampshire().equals( "(((A,B)ab,C)abc,D)abcd;" ) ) {
return false;
}
return false;
}
//
- String p6_str = "(A,(B,(C,(D,E)de)cde)bcde)abcde";
+ final String p6_str = "(A,(B,(C,(D,E)de)cde)bcde)abcde";
p.setSource( p6_str );
if ( !p.hasNext() ) {
return false;
return false;
}
//
- String p7_str = "((((A,B)ab,C)abc,D)abcd,E)abcde";
+ final String p7_str = "((((A,B)ab,C)abc,D)abcd,E)abcde";
p.setSource( p7_str );
if ( !p.hasNext() ) {
return false;
return false;
}
//
- String p8_str = "((((A,B)ab,C)abc,D)abcd,E)abcde ((((a,b)ab,c)abc,d)abcd,e)abcde";
+ final String p8_str = "((((A,B)ab,C)abc,D)abcd,E)abcde ((((a,b)ab,c)abc,d)abcd,e)abcde";
p.setSource( p8_str );
if ( !p.hasNext() ) {
return false;
final PhylogenyNode n3 = PhylogenyNode.createInstanceFromNhxString( "n3" );
final PhylogenyNode n4 = PhylogenyNode.createInstanceFromNhxString( "n4:0.01" );
final PhylogenyNode n5 = PhylogenyNode
- .createInstanceFromNhxString( "n5:0.1[&&NHX:S=Ecoli:E=1.1.1.1:D=Y:Co=Y:B=56:T=1:W=2:C=10.20.30]" );
+ .createInstanceFromNhxString( "n5:0.1[&&NHX:S=Ecoli:E=1.1.1.1:D=Y:Co=Y:B=56:T=1]" );
final PhylogenyNode n6 = PhylogenyNode
- .createInstanceFromNhxString( "n6:0.000001[&&NHX:S=Ecoli:E=1.1.1.1:D=N:Co=N:B=100:T=1:W=2:C=0.0.0]" );
+ .createInstanceFromNhxString( "n6:0.000001[&&NHX:S=Ecoli:E=1.1.1.1:D=N:Co=N:B=100:T=1]" );
if ( !n1.toNewHampshireX().equals( "" ) ) {
return false;
}
if ( !n4.toNewHampshireX().equals( "n4:0.01" ) ) {
return false;
}
- if ( !n5.toNewHampshireX().equals( "n5:0.1[&&NHX:T=1:S=Ecoli:D=Y:B=56:W=2.0:C=10.20.30]" ) ) {
+ if ( !n5.toNewHampshireX().equals( "n5:0.1[&&NHX:T=1:S=Ecoli:D=Y:B=56]" ) ) {
return false;
}
- if ( !n6.toNewHampshireX().equals( "n6:1.0E-6[&&NHX:T=1:S=Ecoli:D=N:B=100:W=2.0:C=0.0.0]" ) ) {
+ if ( !n6.toNewHampshireX().equals( "n6:1.0E-6[&&NHX:T=1:S=Ecoli:D=N:B=100]" ) ) {
return false;
}
}
if ( !n5.isHasAssignedEvent() ) {
return false;
}
- if ( PhylogenyMethods.getBranchWidthValue( n5 ) != 2 ) {
- return false;
- }
final PhylogenyNode n8 = PhylogenyNode
.createInstanceFromNhxString( "n8_ECOLI/12:0.01", NHXParser.TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY );
if ( !n8.getName().equals( "n8_ECOLI/12" ) ) {
return false;
}
final PhylogenyNode n00 = PhylogenyNode
- .createInstanceFromNhxString( "n7:0.000001[&&NHX:GN=gene_name:AC=accession123:S=Ecoli:D=N:Co=N:B=100:T=1:W=2:C=0.0.0]" );
+ .createInstanceFromNhxString( "n7:0.000001[&&NHX:GN=gene_name:AC=accession123:S=Ecoli:D=N:Co=N:B=100:T=1]" );
if ( !n00.getNodeData().getSequence().getName().equals( "gene_name" ) ) {
return false;
}
+ "prob_range={1.000000000000000e+00,1.000000000000000e+00},prob(percent)=\"100\","
+ "prob+-sd=\"100+-0\"]:6.375699999999999e-02[&length_mean=6.395210411945065e-02,"
+ "length_median=6.375699999999999e-02,length_95%HPD={5.388600000000000e-02,"
- + "7.369400000000000e-02}])", new NHXParser2() )[ 0 ];
+ + "7.369400000000000e-02}])", new NHXParser() )[ 0 ];
if ( !isEqual( p1.getNode( "1" ).getDistanceToParent(), 4.129e-02 ) ) {
return false;
}
+ "prob+-sd=\"100+-0\"]:6.375699999999999e-02[&length_mean=6.395210411945065e-02,"
+ "length_median=6.375699999999999e-02,length_95%HPD={5.388600000000000e-02,"
+ "7.369400000000000e-02}])",
- new NHXParser2() )[ 0 ];
+ new NHXParser() )[ 0 ];
if ( p2.getNode( "1" ) == null ) {
return false;
}
public final class ForesterConstants {
- public final static String FORESTER_VERSION = "1.014";
- public final static String FORESTER_DATE = "121229";
+ public final static String FORESTER_VERSION = "1.015";
+ public final static String FORESTER_DATE = "130104";
public final static String PHYLO_XML_VERSION = "1.10";
public final static String PHYLO_XML_LOCATION = "http://www.phyloxml.org";
public final static String PHYLO_XML_XSD = "phyloxml.xsd";
git://source.jalview.org / jalview.git / commitdiff