// 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.util.regex.Pattern;
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.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.PropertiesMap;
-import org.forester.phylogeny.data.Property;
import org.forester.phylogeny.data.Sequence;
import org.forester.phylogeny.data.Taxonomy;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
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 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=([^,]+)" );
+ 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 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=([^,]+)" );
public NHXParser() {
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;
- }
-
- /**
- * 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() );
- }
- }
-
- 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() );
- }
-
- 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 );
- }
- return p;
- }
-
- private int getSourceLength() {
- return _source_length;
- }
-
- public PhylogenyMethods.TAXONOMY_EXTRACTION getTaxonomyExtraction() {
+ public NHXParser.TAXONOMY_EXTRACTION getTaxonomyExtraction() {
return _taxonomy_extraction;
}
- public boolean hasNext() {
- return _has_next;
- }
-
- /**
- * Increases the clade level by one.
- */
- private void increaseCladeLevel() {
- ++_clade_level;
- }
-
- private void init() {
- setTaxonomyExtraction( TAXONOMY_EXTRACTION_DEFAULT );
- setReplaceUnderscores( REPLACE_UNDERSCORES_DEFAULT );
- setGuessRootedness( GUESS_ROOTEDNESS_DEFAULT );
- setIgnoreQuotes( IGNORE_QUOTES_DEFAULT );
- setHasNext( false );
- }
-
- 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() );
- }
-
/**
* Parses the source set with setSource( final Object nhx_source ). Returns
* the Phylogenies found in the source as Phylogeny[].
*/
@Override
public Phylogeny[] parse() throws IOException, NHXFormatException {
- setHasNext( false );
boolean in_comment = false;
boolean saw_colon = false;
boolean saw_open_bracket = 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() ) {
+ 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:
+ my_source_br = ( BufferedReader ) getNhxSource();
+ break;
+ default:
+ throw new RuntimeException( "unknown input type" );
+ }
while ( true ) {
char c = '\b';
if ( getInputType() == NHXParser.BUFFERED_READER ) {
- final int ci = ( ( BufferedReader ) getNhxSource() ).read();
+ final int ci = my_source_br.read();
if ( ci >= 0 ) {
c = ( char ) ci;
}
else {
switch ( getInputType() ) {
case STRING:
- c = ( ( String ) getNhxSource() ).charAt( i );
+ c = my_source_str.charAt( i );
break;
case STRING_BUFFER:
- c = ( ( StringBuffer ) getNhxSource() ).charAt( i );
+ c = my_source_sbuff.charAt( i );
+ break;
+ case STRING_BUILDER:
+ c = my_source_sbuil.charAt( i );
break;
case CHAR_ARRAY:
- c = ( ( char[] ) getNhxSource() )[ i ];
+ c = my_source_charary[ i ];
break;
}
}
&& ( ( c != '[' ) && ( c != '.' ) && ( ( c < 48 ) || ( c > 57 ) ) ) ) {
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):
return getPhylogeniesAsArray();
} // parse()
- public Phylogeny parseNext() throws IOException, NHXFormatException {
- return null;
+ 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 );
+ }
+ else if ( nhx_source instanceof StringBuilder ) {
+ setInputType( NHXParser.STRING_BUILDER );
+ setSourceLength( ( ( StringBuilder ) 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 );
+ }
+ 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 {
+ 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 );
+ }
+ return p;
+ }
+
+ private int getSourceLength() {
+ return _source_length;
+ }
+
+ /**
+ * Increases the clade level by one.
+ */
+ 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() );
}
/**
*
* @throws PhylogenyParserException
* @throws NHXFormatException
+ * @throws PhyloXmlDataFormatException
*/
- private void processCloseParen() throws PhylogenyParserException, NHXFormatException {
+ private void processCloseParen() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
decreaseCladeLevel();
if ( !isSawClosingParen() ) {
final PhylogenyNode new_node = new PhylogenyNode();
*
* @throws PhylogenyParserException
* @throws NHXFormatException
+ * @throws PhyloXmlDataFormatException
*/
- private void processComma() throws PhylogenyParserException, NHXFormatException {
+ private void processComma() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
if ( !isSawClosingParen() ) {
final PhylogenyNode new_node = new PhylogenyNode();
parseNHX( getCurrentAnotation().toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
*
* @throws PhylogenyParserException
* @throws NHXFormatException
+ * @throws PhyloXmlDataFormatException
*/
- private void processOpenParen() throws PhylogenyParserException, NHXFormatException {
+ private void processOpenParen() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
final PhylogenyNode new_node = new PhylogenyNode();
if ( getCladeLevel() == 0 ) {
if ( getCurrentPhylogeny() != null ) {
_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;
}
_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 );
- }
- 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 {
- throw new IllegalArgumentException( getClass() + " can only parse objects of type String,"
- + " StringBuffer, char[], File," + " or InputStream " + " [attempt to parse object of "
- + nhx_source.getClass() + "]." );
- }
- setHasNext( true );
- }
-
private void setSourceLength( final int source_length ) {
_source_length = source_length;
}
- 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();
- }
- 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 moveBranchLengthsToBootstrapValues( 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 );
- }
- }
-
public static void parseNHX( String s,
final PhylogenyNode node_to_annotate,
- final PhylogenyMethods.TAXONOMY_EXTRACTION taxonomy_extraction,
- final boolean replace_underscores ) throws NHXFormatException {
- if ( ( taxonomy_extraction != PhylogenyMethods.TAXONOMY_EXTRACTION.NO ) && replace_underscores ) {
+ 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 ( 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 ( !replace_underscores && ( !is_nhx && ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) ) ) {
+ ParserUtils.extractTaxonomyDataFromNodeName( node_to_annotate, taxonomy_extraction );
}
}
while ( t.hasMoreTokens() ) {
}
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 ) ) {
if ( ( s.charAt( 2 ) == 'Y' ) || ( s.charAt( 2 ) == 'T' ) ) {
node_to_annotate.getNodeData().setEvent( Event.createSingleDuplicationEvent() );
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().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() != PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT ) {
throw new NHXFormatException( "error in NHX formatted data: more than one distance to parent:"
}
}
+ 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 int blu = ForesterUtil.limitRangeForColor( Integer.parseInt( st.nextToken() ) );
return new Color( red, green, blu );
}
+
+ public static enum TAXONOMY_EXTRACTION {
+ NO, YES, PFAM_STYLE_ONLY;
+ }
}
git://source.jalview.org / jalview.git / blobdiff