2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2013 Christian M. Zmasek
7 // This library is free software; you can redistribute it and/or
8 // modify it under the terms of the GNU Lesser General Public
9 // License as published by the Free Software Foundation; either
10 // version 2.1 of the License, or (at your option) any later version.
12 // This library is distributed in the hope that it will be useful,
13 // but WITHOUT ANY WARRANTY; without even the implied warranty of
14 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 // Lesser General Public License for more details.
17 // You should have received a copy of the GNU Lesser General Public
18 // License along with this library; if not, write to the Free Software
19 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
21 // Contact: phylosoft @ gmail . com
22 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
24 package org.forester.io.parsers.nhx;
26 import java.io.BufferedReader;
28 import java.io.FileNotFoundException;
29 import java.io.FileReader;
30 import java.io.IOException;
31 import java.io.InputStream;
32 import java.io.InputStreamReader;
33 import java.util.ArrayList;
34 import java.util.List;
35 import java.util.StringTokenizer;
36 import java.util.regex.Matcher;
37 import java.util.regex.Pattern;
39 import org.forester.io.parsers.IteratingPhylogenyParser;
40 import org.forester.io.parsers.PhylogenyParser;
41 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
42 import org.forester.io.parsers.util.ParserUtils;
43 import org.forester.io.parsers.util.PhylogenyParserException;
44 import org.forester.phylogeny.Phylogeny;
45 import org.forester.phylogeny.PhylogenyMethods;
46 import org.forester.phylogeny.PhylogenyNode;
47 import org.forester.phylogeny.data.Accession;
48 import org.forester.phylogeny.data.Confidence;
49 import org.forester.phylogeny.data.DomainArchitecture;
50 import org.forester.phylogeny.data.Event;
51 import org.forester.phylogeny.data.Identifier;
52 import org.forester.phylogeny.data.PhylogenyDataUtil;
53 import org.forester.phylogeny.data.Sequence;
54 import org.forester.phylogeny.data.Taxonomy;
55 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
56 import org.forester.util.ForesterUtil;
58 public final class NHXParser implements PhylogenyParser, IteratingPhylogenyParser {
60 public static final TAXONOMY_EXTRACTION TAXONOMY_EXTRACTION_DEFAULT = TAXONOMY_EXTRACTION.NO;
61 public final static Pattern UC_LETTERS_NUMBERS_PATTERN = Pattern.compile( "^[A-Z0-9]+$" );
62 public final static Pattern NUMBERS_ONLY_PATTERN = Pattern.compile( "^[0-9\\.]+$" );
63 public final static Pattern MB_PROB_PATTERN = Pattern.compile( "prob=([^,]+)" );
64 public final static Pattern MB_PROB_SD_PATTERN = Pattern.compile( "prob_stddev=([^,]+)" );
65 public final static Pattern MB_BL_PATTERN = Pattern.compile( "length_median=([^,]+)" );
66 final static private boolean GUESS_ROOTEDNESS_DEFAULT = true;
67 final static private boolean GUESS_IF_SUPPORT_VALUES = true;
68 final static private boolean IGNORE_QUOTES_DEFAULT = false;
69 final static public boolean REPLACE_UNDERSCORES_DEFAULT = false;
70 final static private byte STRING = 0;
71 final static private byte STRING_BUFFER = 1;
72 final static private byte CHAR_ARRAY = 2;
73 final static private byte BUFFERED_READER = 3;
74 final static private byte STRING_BUILDER = 4;
75 private boolean _guess_rootedness;
76 private boolean _ignore_quotes;
77 private byte _input_type;
78 private int _source_length;
79 private PhylogenyNode _current_node;
80 private StringBuilder _current_anotation;
81 private Object _nhx_source;
82 private int _clade_level;
83 private Phylogeny _current_phylogeny;
84 private TAXONOMY_EXTRACTION _taxonomy_extraction;
85 private boolean _replace_underscores;
86 private boolean _in_comment = false;
87 private boolean _saw_colon = false;
88 private boolean _saw_closing_paren;
89 private boolean _saw_open_bracket = false;
90 private boolean _in_open_bracket = false;
91 private boolean _in_double_quote = false;
92 private boolean _in_single_quote = false;
93 private String _my_source_str = null;
94 private StringBuffer _my_source_sbuff = null;
95 private StringBuilder _my_source_sbuil = null;
96 private char[] _my_source_charary = null;
97 private BufferedReader _my_source_br = null;
99 private Phylogeny _next;
100 private Object _source;
106 public final TAXONOMY_EXTRACTION getTaxonomyExtraction() {
107 return _taxonomy_extraction;
111 public final boolean hasNext() {
112 return _next != null;
116 public final Phylogeny next() throws NHXFormatException, IOException {
117 final Phylogeny phy = _next;
123 public final Phylogeny[] parse() throws IOException {
125 final List<Phylogeny> l = new ArrayList<Phylogeny>();
126 while ( hasNext() ) {
129 final Phylogeny[] p = new Phylogeny[ l.size() ];
130 for( int i = 0; i < l.size(); ++i ) {
137 public final void reset() throws NHXFormatException, IOException {
142 _saw_open_bracket = false;
143 _in_open_bracket = false;
144 _in_double_quote = false;
145 _in_single_quote = false;
147 _current_anotation = new StringBuilder();
148 _current_phylogeny = null;
149 _current_node = null;
150 _my_source_str = null;
151 _my_source_sbuff = null;
152 _my_source_sbuil = null;
153 _my_source_charary = null;
154 _my_source_br = null;
155 determineSourceType( _source );
156 switch ( _input_type ) {
158 _my_source_str = ( String ) _nhx_source;
161 _my_source_sbuff = ( StringBuffer ) _nhx_source;
164 _my_source_sbuil = ( StringBuilder ) _nhx_source;
167 _my_source_charary = ( char[] ) _nhx_source;
169 case BUFFERED_READER:
170 if ( _my_source_br != null ) {
172 _my_source_br.close();
174 catch ( final IOException e ) {
178 _my_source_br = ( BufferedReader ) _nhx_source;
181 throw new RuntimeException( "unknown input type" );
186 public final void setGuessRootedness( final boolean guess_rootedness ) {
187 _guess_rootedness = guess_rootedness;
190 public final void setIgnoreQuotes( final boolean ignore_quotes ) {
191 _ignore_quotes = ignore_quotes;
194 public final void setReplaceUnderscores( final boolean replace_underscores ) {
195 _replace_underscores = replace_underscores;
199 public final void setSource( final Object nhx_source ) throws NHXFormatException, IOException {
200 _source = nhx_source;
204 public final void setTaxonomyExtraction( final TAXONOMY_EXTRACTION taxonomy_extraction ) {
205 _taxonomy_extraction = taxonomy_extraction;
208 private final void determineSourceType( final Object nhx_source ) throws PhylogenyParserException,
209 FileNotFoundException {
210 if ( nhx_source == null ) {
211 throw new PhylogenyParserException( getClass() + ": attempt to parse null object." );
213 else if ( nhx_source instanceof String ) {
214 _input_type = NHXParser.STRING;
215 _source_length = ( ( String ) nhx_source ).length();
216 _nhx_source = nhx_source;
218 else if ( nhx_source instanceof StringBuilder ) {
219 _input_type = NHXParser.STRING_BUILDER;
220 _source_length = ( ( StringBuilder ) nhx_source ).length();
221 _nhx_source = nhx_source;
223 else if ( nhx_source instanceof StringBuffer ) {
224 _input_type = NHXParser.STRING_BUFFER;
225 _source_length = ( ( StringBuffer ) nhx_source ).length();
226 _nhx_source = nhx_source;
228 else if ( nhx_source instanceof StringBuilder ) {
229 _input_type = NHXParser.STRING_BUILDER;
230 _source_length = ( ( StringBuilder ) nhx_source ).length();
231 _nhx_source = nhx_source;
233 else if ( nhx_source instanceof char[] ) {
234 _input_type = NHXParser.CHAR_ARRAY;
235 _source_length = ( ( char[] ) nhx_source ).length;
236 _nhx_source = nhx_source;
238 else if ( nhx_source instanceof File ) {
239 _input_type = NHXParser.BUFFERED_READER;
241 final File f = ( File ) nhx_source;
242 final String error = ForesterUtil.isReadableFile( f );
243 if ( !ForesterUtil.isEmpty( error ) ) {
244 throw new PhylogenyParserException( error );
246 _nhx_source = new BufferedReader( new FileReader( f ) );
248 else if ( nhx_source instanceof InputStream ) {
249 _input_type = NHXParser.BUFFERED_READER;
251 final InputStreamReader isr = new InputStreamReader( ( InputStream ) nhx_source );
252 _nhx_source = new BufferedReader( isr );
255 throw new IllegalArgumentException( getClass() + " can only parse objects of type String,"
256 + " StringBuffer, StringBuilder, char[], File," + " or InputStream "
257 + " [attempt to parse object of " + nhx_source.getClass() + "]." );
261 private final Phylogeny finishPhylogeny() throws PhylogenyParserException, NHXFormatException,
262 PhyloXmlDataFormatException {
263 if ( _current_phylogeny != null ) {
264 parseNHX( _current_anotation != null ? _current_anotation.toString() : "",
265 _current_phylogeny.getRoot(),
266 getTaxonomyExtraction(),
267 isReplaceUnderscores() );
268 if ( GUESS_IF_SUPPORT_VALUES ) {
269 if ( isBranchLengthsLikeBootstrapValues( _current_phylogeny ) ) {
270 moveBranchLengthsToConfidenceValues( _current_phylogeny );
273 if ( isGuessRootedness() ) {
274 final PhylogenyNode root = _current_phylogeny.getRoot();
275 if ( ( root.getDistanceToParent() >= 0.0 ) || !ForesterUtil.isEmpty( root.getName() )
276 || !ForesterUtil.isEmpty( PhylogenyMethods.getSpecies( root ) ) || root.isHasAssignedEvent() ) {
277 _current_phylogeny.setRooted( true );
280 return _current_phylogeny;
285 private final Phylogeny finishSingleNodePhylogeny() throws PhylogenyParserException, NHXFormatException,
286 PhyloXmlDataFormatException {
287 final PhylogenyNode new_node = new PhylogenyNode();
288 parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
289 _current_phylogeny = new Phylogeny();
290 _current_phylogeny.setRoot( new_node );
291 return _current_phylogeny;
294 private final void getNext() throws IOException, NHXFormatException {
297 if ( _input_type == BUFFERED_READER ) {
298 final int ci = _my_source_br.read();
307 if ( _i >= _source_length ) {
311 switch ( _input_type ) {
313 c = _my_source_str.charAt( _i );
316 c = _my_source_sbuff.charAt( _i );
319 c = _my_source_sbuil.charAt( _i );
322 c = _my_source_charary[ _i ];
327 if ( !_in_single_quote && !_in_double_quote ) {
331 else if ( !( ( c < 33 ) || ( c > 126 ) ) && _saw_colon
332 && ( ( c != '[' ) && ( c != '.' ) && ( ( c < 48 ) || ( c > 57 ) ) ) ) {
335 if ( _in_open_bracket && ( c == ']' ) ) {
336 _in_open_bracket = false;
339 // \n\t is always ignored,
340 // as is " (34) and ' (39) (space is 32):
341 if ( ( isIgnoreQuotes() && ( ( c < 33 ) || ( c > 126 ) || ( c == 34 ) || ( c == 39 ) || ( ( _clade_level == 0 ) && ( c == ';' ) ) ) )
342 || ( !isIgnoreQuotes() && ( ( c < 32 ) || ( c > 126 ) || ( ( _clade_level == 0 ) && ( c == ';' ) ) ) ) ) {
345 else if ( ( c == 32 ) && ( !_in_single_quote && !_in_double_quote ) ) {
348 else if ( _in_comment ) {
353 else if ( _in_double_quote ) {
355 _in_double_quote = false;
358 _current_anotation.append( c );
361 else if ( c == '"' ) {
362 _in_double_quote = true;
364 else if ( _in_single_quote ) {
366 _in_single_quote = false;
369 _current_anotation.append( c );
372 else if ( c == 39 ) {
373 _in_single_quote = true;
375 else if ( c == '[' ) {
376 _saw_open_bracket = true;
377 _in_open_bracket = true;
379 else if ( _saw_open_bracket ) {
381 // everything not starting with "[&" is considered a comment
382 // unless ":digits and/or . [bootstrap]":
384 _current_anotation.append( "[&" );
386 else if ( _saw_colon ) {
387 _current_anotation.append( "[" + c );
393 // comment consisting just of "[]":
394 _saw_open_bracket = false;
396 else if ( ( c == '(' ) && !_in_open_bracket ) {
397 final Phylogeny phy = processOpenParen();
405 else if ( ( c == ')' ) && !_in_open_bracket ) {
408 else if ( ( c == ',' ) && !_in_open_bracket ) {
412 _current_anotation.append( c );
416 if ( _clade_level != 0 ) {
417 throw new PhylogenyParserException( "error in NH (Newick) formatted data: most likely cause: number of open parens does not equal number of close parens" );
419 if ( _current_phylogeny != null ) {
420 _next = finishPhylogeny();
421 _current_phylogeny = null;
422 _current_anotation = null;
424 else if ( ( _current_anotation != null ) && ( _current_anotation.length() > 0 ) ) {
425 _next = finishSingleNodePhylogeny();
426 _current_anotation = null;
433 private final void init() {
434 setTaxonomyExtraction( TAXONOMY_EXTRACTION_DEFAULT );
435 setReplaceUnderscores( REPLACE_UNDERSCORES_DEFAULT );
436 setGuessRootedness( GUESS_ROOTEDNESS_DEFAULT );
437 setIgnoreQuotes( IGNORE_QUOTES_DEFAULT );
440 private final boolean isGuessRootedness() {
441 return _guess_rootedness;
444 private final boolean isIgnoreQuotes() {
445 return _ignore_quotes;
448 private final boolean isReplaceUnderscores() {
449 return _replace_underscores;
452 private final void processCloseParen() throws PhylogenyParserException, NHXFormatException,
453 PhyloXmlDataFormatException {
454 if ( _clade_level < 0 ) {
455 throw new PhylogenyParserException( "error in NH (Newick)/NHX formatted data: most likely cause: number of close parens is larger than number of open parens" );
458 if ( !_saw_closing_paren ) {
459 final PhylogenyNode new_node = new PhylogenyNode();
460 parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
461 _current_anotation = new StringBuilder();
462 _current_node.addAsChild( new_node );
465 parseNHX( _current_anotation.toString(),
466 _current_node.getLastChildNode(),
467 getTaxonomyExtraction(),
468 isReplaceUnderscores() );
469 _current_anotation = new StringBuilder();
471 if ( !_current_node.isRoot() ) {
472 _current_node = _current_node.getParent();
474 _saw_closing_paren = true;
477 private final void processComma() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
478 if ( !_saw_closing_paren ) {
479 final PhylogenyNode new_node = new PhylogenyNode();
480 parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
481 if ( _current_node == null ) {
482 throw new NHXFormatException( "format might not be NH or NHX" );
484 _current_node.addAsChild( new_node );
487 parseNHX( _current_anotation.toString(),
488 _current_node.getLastChildNode(),
489 getTaxonomyExtraction(),
490 isReplaceUnderscores() );
492 _current_anotation = new StringBuilder();
493 _saw_closing_paren = false;
496 private final Phylogeny processOpenParen() throws PhylogenyParserException, NHXFormatException,
497 PhyloXmlDataFormatException {
498 Phylogeny phy = null;
499 final PhylogenyNode new_node = new PhylogenyNode();
500 if ( _clade_level == 0 ) {
501 if ( _current_phylogeny != null ) {
502 phy = finishPhylogeny();
505 _current_anotation = new StringBuilder();
506 _current_phylogeny = new Phylogeny();
507 _current_phylogeny.setRoot( new_node );
511 _current_node.addAsChild( new_node );
513 _current_node = new_node;
514 _saw_closing_paren = false;
518 public final static void parseNHX( String s,
519 final PhylogenyNode node_to_annotate,
520 final TAXONOMY_EXTRACTION taxonomy_extraction,
521 final boolean replace_underscores ) throws NHXFormatException,
522 PhyloXmlDataFormatException {
523 if ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) && replace_underscores ) {
524 throw new IllegalArgumentException( "cannot extract taxonomies and replace under scores at the same time" );
526 if ( ( s != null ) && ( s.length() > 0 ) ) {
527 if ( replace_underscores ) {
528 s = s.replaceAll( "_+", " " );
530 boolean is_nhx = false;
531 final int ob = s.indexOf( "[" );
535 final int cb = s.indexOf( "]" );
537 throw new NHXFormatException( "error in NHX formatted data: no closing \"]\" in \"" + s + "\"" );
539 if ( s.indexOf( "&&NHX" ) == ( ob + 1 ) ) {
540 b = s.substring( ob + 6, cb );
543 // No &&NHX and digits only: is likely to be a support value.
544 final String bracketed = s.substring( ob + 1, cb );
545 final Matcher numbers_only = NUMBERS_ONLY_PATTERN.matcher( bracketed );
546 if ( numbers_only.matches() ) {
547 b = ":" + NHXtags.SUPPORT + bracketed;
549 else if ( s.indexOf( "prob=" ) > -1 ) {
550 processMrBayes3Data( s, node_to_annotate );
553 s = s.substring( 0, ob ) + b;
554 if ( ( s.indexOf( "[" ) > -1 ) || ( s.indexOf( "]" ) > -1 ) ) {
555 throw new NHXFormatException( "error in NHX formatted data: more than one \"]\" or \"[\"" );
558 final StringTokenizer t = new StringTokenizer( s, ":" );
559 if ( t.countTokens() > 0 ) {
560 if ( !s.startsWith( ":" ) ) {
561 node_to_annotate.setName( t.nextToken() );
562 if ( !replace_underscores && ( !is_nhx && ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) ) ) {
563 ParserUtils.extractTaxonomyDataFromNodeName( node_to_annotate, taxonomy_extraction );
566 while ( t.hasMoreTokens() ) {
568 if ( s.startsWith( NHXtags.SPECIES_NAME ) ) {
569 if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
570 node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
572 node_to_annotate.getNodeData().getTaxonomy().setScientificName( s.substring( 2 ) );
574 else if ( s.startsWith( NHXtags.IS_DUPLICATION ) ) {
575 if ( ( s.charAt( 2 ) == 'Y' ) || ( s.charAt( 2 ) == 'T' ) ) {
576 node_to_annotate.getNodeData().setEvent( Event.createSingleDuplicationEvent() );
578 else if ( ( s.charAt( 2 ) == 'N' ) || ( s.charAt( 2 ) == 'F' ) ) {
579 node_to_annotate.getNodeData().setEvent( Event.createSingleSpeciationEvent() );
581 else if ( s.charAt( 2 ) == '?' ) {
582 node_to_annotate.getNodeData().setEvent( Event.createSingleSpeciationOrDuplicationEvent() );
585 throw new NHXFormatException( "error in NHX formatted data: :D=Y or :D=N or :D=?" );
588 else if ( s.startsWith( NHXtags.SUPPORT ) ) {
589 PhylogenyMethods.setConfidence( node_to_annotate, doubleValue( s.substring( 2 ) ) );
591 else if ( s.startsWith( NHXtags.TAXONOMY_ID ) ) {
592 if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
593 node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
595 node_to_annotate.getNodeData().getTaxonomy().setIdentifier( new Identifier( s.substring( 2 ) ) );
597 else if ( s.startsWith( NHXtags.DOMAIN_STRUCTURE ) ) {
598 if ( !node_to_annotate.getNodeData().isHasSequence() ) {
599 node_to_annotate.getNodeData().setSequence( new Sequence() );
601 node_to_annotate.getNodeData().getSequence()
602 .setDomainArchitecture( new DomainArchitecture( s.substring( 3 ) ) );
604 else if ( s.startsWith( NHXtags.SEQUENCE_ACCESSION ) ) {
605 if ( !node_to_annotate.getNodeData().isHasSequence() ) {
606 node_to_annotate.getNodeData().setSequence( new Sequence() );
608 node_to_annotate.getNodeData().getSequence()
609 .setAccession( new Accession( s.substring( 3 ), "?" ) );
611 else if ( s.startsWith( NHXtags.GENE_NAME ) ) {
612 if ( !node_to_annotate.getNodeData().isHasSequence() ) {
613 node_to_annotate.getNodeData().setSequence( new Sequence() );
615 node_to_annotate.getNodeData().getSequence().setName( s.substring( 3 ) );
617 else if ( s.indexOf( '=' ) < 0 ) {
618 if ( node_to_annotate.getDistanceToParent() != PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT ) {
619 throw new NHXFormatException( "error in NHX formatted data: more than one distance to parent:"
622 node_to_annotate.setDistanceToParent( doubleValue( s ) );
624 } // while ( t.hasMoreTokens() )
629 private final static double doubleValue( final String str ) throws NHXFormatException {
631 return Double.valueOf( str ).doubleValue();
633 catch ( final NumberFormatException ex ) {
634 throw new NHXFormatException( "error in NH/NHX formatted data: failed to parse number from " + "\"" + str
639 private final static boolean isBranchLengthsLikeBootstrapValues( final Phylogeny p ) {
640 final PhylogenyNodeIterator it = p.iteratorExternalForward();
641 final double d0 = it.next().getDistanceToParent();
642 if ( ( d0 < 10 ) || !it.hasNext() ) {
645 while ( it.hasNext() ) {
646 final double d = it.next().getDistanceToParent();
647 if ( ( d != d0 ) || ( d < 10 ) ) {
654 private final static void moveBranchLengthsToConfidenceValues( final Phylogeny p ) {
655 final PhylogenyNodeIterator it = p.iteratorPostorder();
656 while ( it.hasNext() ) {
657 final PhylogenyNode n = it.next();
658 PhylogenyMethods.setBootstrapConfidence( n, n.getDistanceToParent() );
659 n.setDistanceToParent( PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT );
663 private final static void processMrBayes3Data( final String s, final PhylogenyNode node_to_annotate )
664 throws NHXFormatException {
666 final Matcher mb_prob_sd_matcher = MB_PROB_SD_PATTERN.matcher( s );
667 if ( mb_prob_sd_matcher.find() ) {
669 sd = Double.parseDouble( mb_prob_sd_matcher.group( 1 ) );
671 catch ( final NumberFormatException e ) {
672 throw new NHXFormatException( "failed to parse probability standard deviation (Mr Bayes output) from \""
676 final Matcher mb_prob_matcher = MB_PROB_PATTERN.matcher( s );
677 if ( mb_prob_matcher.find() ) {
680 prob = Double.parseDouble( mb_prob_matcher.group( 1 ) );
682 catch ( final NumberFormatException e ) {
683 throw new NHXFormatException( "failed to parse probability (Mr Bayes output) from \"" + s + "\"" );
687 node_to_annotate.getBranchData()
688 .addConfidence( new Confidence( prob, "posterior probability", sd ) );
691 node_to_annotate.getBranchData().addConfidence( new Confidence( prob, "posterior probability" ) );
695 final Matcher mb_bl_matcher = MB_BL_PATTERN.matcher( s );
696 if ( mb_bl_matcher.find() ) {
699 bl = Double.parseDouble( mb_bl_matcher.group( 1 ) );
701 catch ( final NumberFormatException e ) {
702 throw new NHXFormatException( "failed to parse median branch length (Mr Bayes output) from \"" + s
706 node_to_annotate.setDistanceToParent( bl );
711 public static enum TAXONOMY_EXTRACTION {
712 NO, YES, PFAM_STYLE_ONLY;