// 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
// Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
//
// Contact: phylosoft @ gmail . com
-// WWW: www.phylosoft.org/forester
+// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
package org.forester.io.parsers.nhx;
import java.awt.Color;
import java.io.BufferedReader;
+import java.io.ByteArrayInputStream;
import java.io.File;
-import java.io.FileReader;
+import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
+import java.net.URL;
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.IteratingPhylogenyParser;
import org.forester.io.parsers.PhylogenyParser;
+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.Annotation;
-import org.forester.phylogeny.data.DomainArchitecture;
+import org.forester.phylogeny.data.BranchColor;
+import org.forester.phylogeny.data.Confidence;
import org.forester.phylogeny.data.Event;
import org.forester.phylogeny.data.Identifier;
-import org.forester.phylogeny.data.PropertiesMap;
-import org.forester.phylogeny.data.Property;
+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.ForesterConstants;
import org.forester.util.ForesterUtil;
-public final class NHXParser implements PhylogenyParser {
-
- public static final boolean LIMIT_SPECIES_NAMES_TO_FIVE_CHARS = true;
- public static final PhylogenyMethods.TAXONOMY_EXTRACTION TAXONOMY_EXTRACTION_DEFAULT = PhylogenyMethods.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;
- private boolean _guess_rootedness;
- private boolean _has_next;
- 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 List<Phylogeny> _phylogenies;
- private Phylogeny _current_phylogeny;
- private PhylogenyMethods.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 class NHXParser implements PhylogenyParser, IteratingPhylogenyParser {
+
+ private final static Pattern MB_BL_PATTERN = Pattern.compile( "length.median=([-+eE0-9\\.]+)" );
+ private final static Pattern MB_PROB_PATTERN = Pattern.compile( "prob=([-+eE0-9\\.]+)" );
+ private final static Pattern MB_PROB_SD_PATTERN = Pattern.compile( "prob.stddev=([-+eE0-9\\.]+)" );
+ private final static Pattern NUMBERS_ONLY_PATTERN = Pattern.compile( "^[0-9\\.]+$" );
+
+ private final static Pattern BEAST_STYLE_EXTENDED_BOOTSTRAP_PATTERN = Pattern.compile( "boot?strap=([\\d\\.]+)" );
+ private final static Pattern BEAST_STYLE_EXTENDED_COLOR_PATTERN = Pattern.compile( "colou?r=(#[\\da-fA-F]{6})" );
+ private final static Pattern ENDS_WITH_NUMBER_PATTERN = Pattern.compile( "(:[-+eE0-9\\.]+$)" );
+
+
+ public final static boolean REPLACE_UNDERSCORES_DEFAULT = false;
+ private final static boolean ALLOW_ERRORS_IN_DISTANCE_TO_PARENT_DEFAULT = false;
+ private final static byte BUFFERED_READER = 3;
+ private final static byte CHAR_ARRAY = 2;
+ private final static boolean GUESS_IF_SUPPORT_VALUES = true;
+ private final static boolean GUESS_ROOTEDNESS_DEFAULT = true;
+ private final static boolean IGNORE_QUOTES_DEFAULT = false;
+
+ private final static char BELL = 7;
+ private final static String ENCODING_DEFAULT = ForesterConstants.UTF_8;
+ private boolean _allow_errors_in_distance_to_parent;
+ private int _clade_level;
+ private StringBuilder _current_anotation;
+ private PhylogenyNode _current_node;
+ private Phylogeny _current_phylogeny;
+ private boolean _guess_rootedness;
+ private int _i;
+ private boolean _ignore_quotes;
+ private boolean _in_comment = false;
+ private boolean _in_double_quote = false;
+ private boolean _in_open_bracket = false;
+ private boolean _in_single_quote = false;
+ private byte _input_type;
+ private BufferedReader _my_source_br = null;
+ private char[] _my_source_charary = null;
+ private Phylogeny _next;
+ private Object _nhx_source;
+ private boolean _replace_underscores;
+ private boolean _saw_closing_paren;
+ private boolean _saw_colon = false;
+ private boolean _saw_open_bracket = false;
+ private Object _source;
+ private int _source_length;
+ private TAXONOMY_EXTRACTION _taxonomy_extraction;
+ private boolean _parse_beast_style_extended_tags = false;
+ private final String _encoding;
public NHXParser() {
+ _encoding = ENCODING_DEFAULT;
+ init();
+ }
+
+ public NHXParser( final String encoding ) {
+ _encoding = encoding;
init();
}
- /**
- * 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;
+ @Override
+ public String getName() {
+ return "NH/NHX Parser";
}
- /**
- * Finishes the current Phylogeny and adds it to the list of Phylogenies
- * created.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- */
- private void finishPhylogeny() throws PhylogenyParserException, NHXFormatException {
- setCladeLevel( 0 );
- if ( getCurrentPhylogeny() != null ) {
- parseNHX( getCurrentAnotation().toString(),
- getCurrentPhylogeny().getRoot(),
- getTaxonomyExtraction(),
- isReplaceUnderscores() );
- if ( NHXParser.GUESS_IF_SUPPORT_VALUES ) {
- if ( NHXParser.isBranchLengthsLikeBootstrapValues( getCurrentPhylogeny() ) ) {
- NHXParser.moveBranchLengthsToBootstrapValues( 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() );
- }
+ public final TAXONOMY_EXTRACTION getTaxonomyExtraction() {
+ return _taxonomy_extraction;
}
- private void finishSingleNodePhylogeny() throws PhylogenyParserException, NHXFormatException {
- 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() );
+ @Override
+ public final boolean hasNext() {
+ return _next != null;
}
- private int getCladeLevel() {
- return _clade_level;
+ @Override
+ public final Phylogeny next() throws NHXFormatException, IOException {
+ final Phylogeny phy = _next;
+ parseNext();
+ return phy;
}
- private StringBuilder getCurrentAnotation() {
- return _current_anotation;
+ @Override
+ public final Phylogeny[] parse() throws IOException {
+ 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 );
+ }
+ reset();
+ return p;
}
- private PhylogenyNode getCurrentNode() {
- return _current_node;
+ @Override
+ 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_charary = null;
+ determineAndProcessSourceType( _source );
+ switch ( _input_type ) {
+ case CHAR_ARRAY:
+ _my_source_br = null;
+ _my_source_charary = ( char[] ) _nhx_source;
+ break;
+ case BUFFERED_READER:
+ _my_source_br = ( BufferedReader ) _nhx_source;
+ break;
+ default:
+ throw new RuntimeException( "unknown input type" );
+ }
+ parseNext();
}
- private Phylogeny getCurrentPhylogeny() {
- return _current_phylogeny;
+ public final void setGuessRootedness( final boolean guess_rootedness ) {
+ _guess_rootedness = guess_rootedness;
}
- private byte getInputType() {
- return _input_type;
+ public final void setIgnoreQuotes( final boolean ignore_quotes ) {
+ _ignore_quotes = ignore_quotes;
}
- private Object getNhxSource() {
- return _nhx_source;
+ public final void setReplaceUnderscores( final boolean replace_underscores ) {
+ _replace_underscores = replace_underscores;
}
- private List<Phylogeny> getPhylogenies() {
- return _phylogenies;
+ @Override
+ public final void setSource( final Object nhx_source ) throws NHXFormatException, IOException {
+ _source = nhx_source;
+ reset();
}
- /**
- * 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 );
- }
- return p;
+ public final void setTaxonomyExtraction( final TAXONOMY_EXTRACTION taxonomy_extraction ) {
+ _taxonomy_extraction = taxonomy_extraction;
}
- private int getSourceLength() {
- return _source_length;
+ public final void setAllowErrorsInDistanceToParent( final boolean allow_errors_in_distance_to_parent ) {
+ _allow_errors_in_distance_to_parent = allow_errors_in_distance_to_parent;
}
- public PhylogenyMethods.TAXONOMY_EXTRACTION getTaxonomyExtraction() {
- return _taxonomy_extraction;
+ private final void determineAndProcessSourceType( final Object nhx_source ) throws IOException {
+ if ( nhx_source == null ) {
+ throw new PhylogenyParserException( getClass() + ": attempt to parse null object." );
+ }
+ else if ( nhx_source instanceof String ) {
+ _nhx_source = nhx_source;
+ _input_type = NHXParser.BUFFERED_READER;
+ _source_length = 0;
+ InputStream is = new ByteArrayInputStream( (( String ) nhx_source ).getBytes(getEncoding()));
+ final InputStreamReader isr = new InputStreamReader( is, getEncoding() );
+ _nhx_source = new BufferedReader( isr );
+ }
+ 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;
+ if ( _my_source_br != null ) {
+ //I am REALLY not sure if it is a "good" idea NOT to close the stream...
+ // try {
+ // _my_source_br.close();
+ // }
+ // catch ( final IOException e ) {
+ // }
+ }
+ final File f = ( File ) nhx_source;
+ final String error = ForesterUtil.isReadableFile( f );
+ if ( !ForesterUtil.isEmpty( error ) ) {
+ throw new PhylogenyParserException( error );
+ }
+ final InputStream is = new FileInputStream( f );
+ final InputStreamReader isr = new InputStreamReader( is, getEncoding() );
+ _nhx_source = new BufferedReader( isr );
+ }
+ else if ( nhx_source instanceof URL ) {
+ _input_type = NHXParser.BUFFERED_READER;
+ _source_length = 0;
+ if ( _my_source_br != null ) {
+ //I am REALLY not sure if it is a "good" idea NOT to close the stream...
+ // try {
+ // _my_source_br.close();
+ // }
+ // catch ( final IOException e ) {
+ // }
+ }
+ final InputStream is = ( ( URL ) nhx_source ).openStream();
+ final InputStreamReader isr = new InputStreamReader( is, getEncoding() );
+ _nhx_source = new BufferedReader( isr );
+ }
+ else if ( nhx_source instanceof InputStream ) {
+ _input_type = NHXParser.BUFFERED_READER;
+ _source_length = 0;
+ if ( _my_source_br != null ) {
+ //I am REALLY not sure if it is a "good" idea NOT to close the stream...
+ // try {
+ // _my_source_br.close();
+ // }
+ // catch ( final IOException e ) {
+ // }
+ }
+ final InputStream is = ( InputStream ) nhx_source;
+ final InputStreamReader isr = new InputStreamReader( is, getEncoding() );
+ _nhx_source = new BufferedReader( isr );
+ }
+ else {
+ throw new IllegalArgumentException( getClass() + " can only parse objects of type String,"
+ + " char[], File, InputStream, or URL "
+ + " [attempt to parse object of " + nhx_source.getClass() + "]." );
+ }
}
- public boolean hasNext() {
- return _has_next;
+ private final Phylogeny finishPhylogeny() throws PhylogenyParserException, NHXFormatException,
+ PhyloXmlDataFormatException {
+ if ( _current_phylogeny != null ) {
+ parseNHX( _current_anotation != null ? _current_anotation.toString() : "",
+ _current_phylogeny.getRoot(),
+ getTaxonomyExtraction(),
+ isReplaceUnderscores(),
+ isAllowErrorsInDistanceToParent(),
+ true,
+ isParseBeastStyleExtendedTags());
+ 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;
}
- /**
- * Increases the clade level by one.
- */
- private void increaseCladeLevel() {
- ++_clade_level;
+ private final Phylogeny finishSingleNodePhylogeny() throws PhylogenyParserException, NHXFormatException,
+ PhyloXmlDataFormatException {
+ final PhylogenyNode new_node = new PhylogenyNode();
+ parseNHX( _current_anotation.toString(),
+ new_node,
+ getTaxonomyExtraction(),
+ isReplaceUnderscores(),
+ isAllowErrorsInDistanceToParent(),
+ true,
+ isParseBeastStyleExtendedTags());
+ _current_phylogeny = new Phylogeny();
+ _current_phylogeny.setRoot( new_node );
+ return _current_phylogeny;
}
- private void init() {
- setTaxonomyExtraction( TAXONOMY_EXTRACTION_DEFAULT );
+ private final void init() {
+ setTaxonomyExtraction( TAXONOMY_EXTRACTION.NO );
setReplaceUnderscores( REPLACE_UNDERSCORES_DEFAULT );
setGuessRootedness( GUESS_ROOTEDNESS_DEFAULT );
setIgnoreQuotes( IGNORE_QUOTES_DEFAULT );
- setHasNext( false );
+ setAllowErrorsInDistanceToParent( ALLOW_ERRORS_IN_DISTANCE_TO_PARENT_DEFAULT );
+ setParseBeastStyleExtendedTags( false );
+ }
+
+ private final boolean isAllowErrorsInDistanceToParent() {
+ return _allow_errors_in_distance_to_parent;
}
- 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() );
- }
-
- /**
- * 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
- */
- @Override
- public Phylogeny[] parse() throws IOException, NHXFormatException {
- setHasNext( false );
- 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();
- int i = 0;
+ private final void parseNext() throws IOException, NHXFormatException {
+ if ( _source == null ) {
+ throw new IOException( "source is not set" );
+ }
while ( true ) {
char c = '\b';
- if ( getInputType() == NHXParser.BUFFERED_READER ) {
- final int ci = ( ( BufferedReader ) getNhxSource() ).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() ) {
- case STRING:
- c = ( ( String ) getNhxSource() ).charAt( i );
- break;
- case STRING_BUFFER:
- c = ( ( StringBuffer ) getNhxSource() ).charAt( i );
- break;
- case CHAR_ARRAY:
- c = ( ( char[] ) getNhxSource() )[ i ];
- break;
- }
- }
+ c = _my_source_charary[ _i ];
}
- 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 == 127 ) ) && _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.
- }
- else if ( ( c == 32 ) && ( !in_single_quote && !in_double_quote ) ) {
- // Do nothing.
+ // "=34 '=39 space=32
+ if ( ( c < 32 ) || ( c == 127 ) || ( isIgnoreQuotes() && ( ( c == 32 ) || ( c == 34 ) || ( c == 39 ) ) )
+ || ( ( c == 32 ) && ( !_in_single_quote && !_in_double_quote ) )
+ || ( ( _clade_level == 0 ) && ( c == ';' ) && ( !_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( changeCharInParens( c ) );
}
}
- else if ( c == '"' ) {
- in_double_quote = true;
+ else if ( ( c == '"' ) && !_in_single_quote ) {
+ _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( changeCharInParens( 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;
+ _saw_open_bracket = false;
}
- else if ( c == '(' && !in_open_bracket ) {
- processOpenParen();
+ else if ( ( c == '(' ) && !_in_open_bracket ) {
+ final Phylogeny phy = processOpenParen();
+ if ( phy != null ) {
+ ++_i;
+ _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" );
+ ++_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" );
}
- if ( getCurrentPhylogeny() != null ) {
- finishPhylogeny();
+ if ( _current_phylogeny != null ) {
+ _next = finishPhylogeny();
+ _current_phylogeny = null;
+ _current_anotation = null;
}
- else if ( getCurrentAnotation().length() > 0 ) {
- finishSingleNodePhylogeny();
+ else if ( ( _current_anotation != null ) && ( _current_anotation.length() > 0 ) ) {
+ _next = finishSingleNodePhylogeny();
+ _current_anotation = null;
}
- else if ( getPhylogenies().size() < 1 ) {
- getPhylogenies().add( new Phylogeny() );
+ else {
+ _next = null;
}
- return getPhylogeniesAsArray();
- } // parse()
+ }
- public Phylogeny parseNext() throws IOException, NHXFormatException {
- return null;
+ private final static char changeCharInParens( char c ) {
+ if ( c == ':' ) {
+ c = BELL;
+ }
+ else if ( c == '[' ) {
+ c = '{';
+ }
+ else if ( c == ']' ) {
+ c = '}';
+ }
+ return c;
}
- /**
- * Called if a closing paren is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- */
- private void processCloseParen() throws PhylogenyParserException, NHXFormatException {
- decreaseCladeLevel();
- if ( !isSawClosingParen() ) {
- final PhylogenyNode new_node = new PhylogenyNode();
- parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
- newCurrentAnotation();
- getCurrentNode().addAsChild( new_node );
+ 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" );
}
- else {
- parseNHX( getCurrentAnotation().toString(),
- getCurrentNode().getLastChildNode(),
- getTaxonomyExtraction(),
- isReplaceUnderscores() );
- newCurrentAnotation();
- }
- if ( !getCurrentNode().isRoot() ) {
- setCurrentNode( getCurrentNode().getParent() );
- }
- setSawClosingParen( true );
- } // processCloseParen()
-
- /**
- * Called if a comma is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- */
- private void processComma() throws PhylogenyParserException, NHXFormatException {
- if ( !isSawClosingParen() ) {
+ --_clade_level;
+ if ( !_saw_closing_paren ) {
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(),
+ parseNHX( _current_anotation.toString(),
+ new_node,
getTaxonomyExtraction(),
- isReplaceUnderscores() );
- }
- newCurrentAnotation();
- setSawClosingParen( false );
- } // processComma()
-
- /**
- * Called if a opening paren is encountered.
- *
- * @throws PhylogenyParserException
- * @throws NHXFormatException
- */
- private void processOpenParen() throws PhylogenyParserException, NHXFormatException {
- final PhylogenyNode new_node = new PhylogenyNode();
- if ( getCladeLevel() == 0 ) {
- if ( getCurrentPhylogeny() != null ) {
- finishPhylogeny();
- }
- setCladeLevel( 1 );
- newCurrentAnotation();
- setCurrentPhylogeny( new Phylogeny() );
- getCurrentPhylogeny().setRoot( new_node );
+ isReplaceUnderscores(),
+ isAllowErrorsInDistanceToParent(),
+ true,
+ isParseBeastStyleExtendedTags());
+ _current_anotation = new StringBuilder();
+ _current_node.addAsChild( new_node );
}
else {
- increaseCladeLevel();
- getCurrentNode().addAsChild( new_node );
+ parseNHX( _current_anotation.toString(),
+ _current_node.getLastChildNode(),
+ getTaxonomyExtraction(),
+ isReplaceUnderscores(),
+ isAllowErrorsInDistanceToParent(),
+ true,
+ isParseBeastStyleExtendedTags());
+ _current_anotation = new StringBuilder();
}
- 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." );
+ if ( !_current_node.isRoot() ) {
+ _current_node = _current_node.getParent();
}
- _clade_level = clade_level;
+ _saw_closing_paren = true;
}
- 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;
- }
-
- public void setGuessRootedness( final boolean guess_rootedness ) {
- _guess_rootedness = guess_rootedness;
- }
-
- private void setHasNext( final boolean has_next ) {
- _has_next = has_next;
- }
-
- public void setIgnoreQuotes( final boolean ignore_quotes ) {
- _ignore_quotes = ignore_quotes;
- }
-
- private void setInputType( final byte input_type ) {
- _input_type = input_type;
- }
-
- private void setNhxSource( final Object nhx_source ) {
- _nhx_source = nhx_source;
- }
-
- private void setPhylogenies( final ArrayList<Phylogeny> phylogenies ) {
- _phylogenies = phylogenies;
- }
-
- public void setReplaceUnderscores( final boolean replace_underscores ) {
- _replace_underscores = replace_underscores;
- }
-
- private void setSawClosingParen( final boolean saw_closing_paren ) {
- _saw_closing_paren = saw_closing_paren;
- }
-
- /**
- * 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 StringBuffer ) {
- setInputType( NHXParser.STRING_BUFFER );
- setSourceLength( ( ( StringBuffer ) nhx_source ).length() );
- setNhxSource( nhx_source );
- }
- 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 );
+ private final void processComma() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
+ if ( !_saw_closing_paren ) {
+ final PhylogenyNode new_node = new PhylogenyNode();
+ parseNHX( _current_anotation.toString(),
+ new_node,
+ getTaxonomyExtraction(),
+ isReplaceUnderscores(),
+ isAllowErrorsInDistanceToParent(),
+ true,
+ isParseBeastStyleExtendedTags());
+ if ( _current_node == null ) {
+ throw new NHXFormatException( "format might not be NH or NHX" );
}
- 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 ) );
+ _current_node.addAsChild( new_node );
}
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() + "]." );
+ parseNHX( _current_anotation.toString(),
+ _current_node.getLastChildNode(),
+ getTaxonomyExtraction(),
+ isReplaceUnderscores(),
+ isAllowErrorsInDistanceToParent(),
+ true,
+ isParseBeastStyleExtendedTags());
}
- setHasNext( true );
- }
-
- private void setSourceLength( final int source_length ) {
- _source_length = source_length;
+ _current_anotation = new StringBuilder();
+ _saw_closing_paren = false;
}
- public void setTaxonomyExtraction( final PhylogenyMethods.TAXONOMY_EXTRACTION taxonomy_extraction ) {
- _taxonomy_extraction = taxonomy_extraction;
- }
-
- private static double doubleValue( final String str ) throws NHXFormatException {
- try {
- return Double.valueOf( str ).doubleValue();
+ private final Phylogeny processOpenParen() throws PhylogenyParserException, NHXFormatException,
+ PhyloXmlDataFormatException {
+ Phylogeny phy = null;
+ final PhylogenyNode new_node = new PhylogenyNode();
+ if ( _clade_level == 0 ) {
+ if ( _current_phylogeny != null ) {
+ phy = finishPhylogeny();
+ }
+ _clade_level = 1;
+ _current_anotation = new StringBuilder();
+ _current_phylogeny = new Phylogeny();
+ _current_phylogeny.setRoot( new_node );
}
- catch ( final NumberFormatException ex ) {
- throw new NHXFormatException( "error in NH/NHX formatted data: failed to parse number from :" + "\"" + str
- + "\"" );
+ else {
+ ++_clade_level;
+ _current_node.addAsChild( new_node );
}
+ _current_node = new_node;
+ _saw_closing_paren = false;
+ return phy;
}
- 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 final static NHXParser createInstance( final Object nhx_source ) throws NHXFormatException, IOException {
+ final NHXParser parser = new NHXParser();
+ parser.setSource( nhx_source );
+ return parser;
}
- private static void moveBranchLengthsToBootstrapValues( final Phylogeny p ) {
- final PhylogenyNodeIterator it = p.iteratorPostorder();
- while ( it.hasNext() ) {
- final PhylogenyNode n = it.next();
- PhylogenyMethods.setBootstrapConfidence( n, n.getDistanceToParent() );
- n.setDistanceToParent( PhylogenyNode.DISTANCE_DEFAULT );
- }
+ public final static Phylogeny[] parse( final Object nhx_source ) throws NHXFormatException, IOException {
+ return NHXParser.createInstance( nhx_source ).parse();
}
- public static void parseNHX( String s,
- final PhylogenyNode node_to_annotate,
- final PhylogenyMethods.TAXONOMY_EXTRACTION taxonomy_extraction,
- final boolean replace_underscores ) throws NHXFormatException {
- System.out.println( s );
- System.out.println();
- if ( ( taxonomy_extraction != PhylogenyMethods.TAXONOMY_EXTRACTION.NO ) && replace_underscores ) {
+ public final static void parseNHX( String s,
+ final PhylogenyNode node_to_annotate,
+ final TAXONOMY_EXTRACTION taxonomy_extraction,
+ final boolean replace_underscores,
+ final boolean allow_errors_in_distance_to_parent,
+ final boolean replace_bell,
+ final boolean parse_beast_style_extended_tags ) 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( "_+", " " );
}
- int ob = 0;
- int cb = 0;
- String a = "";
- String b = "";
- StringTokenizer t = null;
+ s = s.replaceAll( "\\s+", " " ).trim();
boolean is_nhx = false;
- ob = s.indexOf( "[" );
- cb = s.indexOf( "]" );
+ final int ob = s.indexOf( "[" );
if ( ob > -1 ) {
- a = "";
- b = "";
+ 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 ( numbers_only.matches() ) {
b = ":" + NHXtags.SUPPORT + bracketed;
}
+ else if ( s.indexOf( "prob=" ) > -1 ) {
+ processMrBayes3Data( s, node_to_annotate );
+ }
+ if ( parse_beast_style_extended_tags ) {
+ processBeastStyleExtendedData( s, node_to_annotate );
+ }
+ final Matcher ewn_matcher = ENDS_WITH_NUMBER_PATTERN.matcher( s );
+ if ( ewn_matcher.find() ) {
+ b = ewn_matcher.group(1);
+ }
}
- a = s.substring( 0, ob );
- s = a + b;
+ 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 \"[\"" );
}
}
- t = new StringTokenizer( s, ":" );
+ 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 != PhylogenyMethods.TAXONOMY_EXTRACTION.NO ) ) ) {
- final String tax = ParserUtils
- .extractTaxonomyCodeFromNodeName( node_to_annotate.getName(),
- LIMIT_SPECIES_NAMES_TO_FIVE_CHARS,
- taxonomy_extraction );
- if ( !ForesterUtil.isEmpty( tax ) ) {
- if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
- node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
- }
- node_to_annotate.getNodeData().getTaxonomy().setTaxonomyCode( tax );
- }
+ if ( ( s.indexOf( BELL ) <= -1 ) || !replace_bell ) {
+ node_to_annotate.setName( t.nextToken() );
+ }
+ else {
+ node_to_annotate.setName( t.nextToken().replace( BELL, ':' ) );
+ }
+ if ( !replace_underscores && ( !is_nhx && ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) ) ) {
+ ParserUtils.extractTaxonomyDataFromNodeName( node_to_annotate, taxonomy_extraction );
}
}
while ( t.hasMoreTokens() ) {
s = t.nextToken();
- System.out.println( "=>" + s );
- System.out.println();
- if ( s.startsWith( org.forester.io.parsers.nhx.NHXtags.SPECIES_NAME ) ) {
+ if ( ( s.indexOf( BELL ) > -1 ) && replace_bell ) {
+ s = s.replace( BELL, ':' );
+ }
+ if ( s.indexOf( '=' ) < 0 ) {
+ if ( ( node_to_annotate.getDistanceToParent() != PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT )
+ && !allow_errors_in_distance_to_parent ) {
+ throw new NHXFormatException( "error in NHX formatted data: more than one distance to parent:"
+ + "\"" + s + "\"" );
+ }
+ node_to_annotate.setDistanceToParent( doubleValue( s, allow_errors_in_distance_to_parent ) );
+ }
+ else 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.ANNOTATION ) ) {
- if ( !node_to_annotate.getNodeData().isHasSequence() ) {
- node_to_annotate.getNodeData().setSequence( new Sequence() );
- }
- final Annotation annotation = new Annotation( "_:_" );
- annotation.setDesc( s.substring( 3 ) );
- node_to_annotate.getNodeData().getSequence().addAnnotation( annotation );
- }
- 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() );
}
}
}
else if ( s.startsWith( NHXtags.SUPPORT ) ) {
- PhylogenyMethods.setConfidence( node_to_annotate, doubleValue( s.substring( 2 ) ) );
+ PhylogenyMethods.setConfidence( node_to_annotate, doubleValue( s.substring( 2 ), false ) );
}
else if ( s.startsWith( NHXtags.TAXONOMY_ID ) ) {
if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
}
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.CUSTOM_DATA_ON_NODE ) ) {
- if ( !node_to_annotate.getNodeData().isHasProperties() ) {
- node_to_annotate.getNodeData().setProperties( new PropertiesMap() );
- }
- node_to_annotate.getNodeData().getProperties().addProperty( Property.createFromNhxString( s ) );
- }
- 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.NODE_IDENTIFIER ) ) {
- node_to_annotate.getNodeData().setNodeIdentifier( new Identifier( 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 ), "?" ) );
+ .setAccession( new Accession( s.substring( 3 ), "?" ) );
}
else if ( s.startsWith( NHXtags.GENE_NAME ) ) {
if ( !node_to_annotate.getNodeData().isHasSequence() ) {
}
node_to_annotate.getNodeData().getSequence().setName( s.substring( 3 ) );
}
- else if ( s.startsWith( NHXtags.GENE_NAME_SYNONYM ) ) {
- if ( !node_to_annotate.getNodeData().isHasSequence() ) {
- node_to_annotate.getNodeData().setSequence( new Sequence() );
- }
- node_to_annotate.getNodeData().getSequence().setName( s.substring( 2 ) );
- }
- else if ( s.indexOf( '=' ) < 0 ) {
- if ( node_to_annotate.getDistanceToParent() != PhylogenyNode.DISTANCE_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() )
+ } // while ( t.hasMoreTokens() )
}
}
}
- /**
- * 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 );
+ private final static double doubleValue( final String str, final boolean allow_errors ) throws NHXFormatException {
+ try {
+ return Double.valueOf( str ).doubleValue();
+ }
+ catch ( final NumberFormatException ex ) {
+ if ( !allow_errors ) {
+ throw new NHXFormatException( "error in NH/NHX formatted data: failed to parse number from " + "\""
+ + str + "\"" );
+ }
+ }
+ return 0.0;
+ }
+
+ 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 false;
+ }
+ while ( it.hasNext() ) {
+ final double d = it.next().getDistanceToParent();
+ if ( ( d != d0 ) || ( d < 10 ) ) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ private final 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 final static void processBeastStyleExtendedData( final String s,
+ final PhylogenyNode node_to_annotate )
+ throws NHXFormatException {
+ final Matcher ft_bs_matcher = BEAST_STYLE_EXTENDED_BOOTSTRAP_PATTERN.matcher( s );
+
+ double bs = -1;
+ if ( ft_bs_matcher.find() ) {
+ try {
+ bs = Double.parseDouble( ft_bs_matcher.group( 1 ) );
+ }
+ catch ( final NumberFormatException e ) {
+ throw new NHXFormatException( "failed to parse bootstrap support from \""
+ + s + "\"" );
+ }
+ if ( bs >= 0.0 ) {
+ node_to_annotate.getBranchData()
+ .addConfidence( new Confidence( bs, "bootstrap" ) );
+ }
+ }
+ final Matcher ft_color_matcher = BEAST_STYLE_EXTENDED_COLOR_PATTERN.matcher( s );
+ Color c = null;
+ if ( ft_color_matcher.find() ) {
+ try {
+ c = Color.decode(ft_color_matcher.group( 1 ) );
+ }
+ catch ( final NumberFormatException e ) {
+ throw new NHXFormatException( "failed to parse color from \""
+ + 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 );
+ if ( c != null ) {
+ node_to_annotate.getBranchData().setBranchColor( new BranchColor( c ) );
+ }
+ }
+
+ 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 );
+ 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 );
+ }
+ }
+ }
+
+ public String getEncoding() {
+ return _encoding;
+ }
+
+ private final boolean isParseBeastStyleExtendedTags() {
+ return _parse_beast_style_extended_tags;
+ }
+
+ public final void setParseBeastStyleExtendedTags( final boolean parse_beast_style_extended_tags ) {
+ _parse_beast_style_extended_tags = parse_beast_style_extended_tags;
+ }
+
+ public static enum TAXONOMY_EXTRACTION {
+ AGGRESSIVE, NO, PFAM_STYLE_RELAXED, PFAM_STYLE_STRICT;
}
}