From 31c6a5701649241d2f8a493b09d2871acd146d43 Mon Sep 17 00:00:00 2001 From: cmzmasek Date: Tue, 22 Aug 2017 18:33:26 -0700 Subject: [PATCH] in progress... --- .../src/org/forester/application/cladinator.java | 6 +- .../{Analysis2.java => AnalysisMulti.java} | 166 ++------ .../{Analysis.java => AnalysisSingle.java} | 6 +- .../forester/clade_analysis/CladeAnalysisTest.java | 260 +++++------- .../{Result2.java => ResultMulti.java} | 422 +++++++++----------- .../{Result.java => ResultSingle.java} | 100 +++-- 6 files changed, 381 insertions(+), 579 deletions(-) rename forester/java/src/org/forester/clade_analysis/{Analysis2.java => AnalysisMulti.java} (51%) rename forester/java/src/org/forester/clade_analysis/{Analysis.java => AnalysisSingle.java} (97%) rename forester/java/src/org/forester/clade_analysis/{Result2.java => ResultMulti.java} (69%) rename forester/java/src/org/forester/clade_analysis/{Result.java => ResultSingle.java} (85%) diff --git a/forester/java/src/org/forester/application/cladinator.java b/forester/java/src/org/forester/application/cladinator.java index ddc1aef..daf0224 100644 --- a/forester/java/src/org/forester/application/cladinator.java +++ b/forester/java/src/org/forester/application/cladinator.java @@ -31,8 +31,8 @@ import java.text.DecimalFormat; import java.util.ArrayList; import java.util.List; -import org.forester.clade_analysis.Analysis; -import org.forester.clade_analysis.Result; +import org.forester.clade_analysis.AnalysisSingle; +import org.forester.clade_analysis.ResultSingle; import org.forester.io.parsers.PhylogenyParser; import org.forester.io.parsers.util.ParserUtils; import org.forester.phylogeny.Phylogeny; @@ -115,7 +115,7 @@ public final class cladinator { System.out.println( "\nCould not read \"" + intreefile + "\" [" + e.getMessage() + "]\n" ); System.exit( -1 ); } - final Result res = Analysis.execute( p, query, separator ); + final ResultSingle res = AnalysisSingle.execute( p, query, separator ); System.out.println(); System.out.println( "Result:" ); System.out.println( "Query : " + query ); diff --git a/forester/java/src/org/forester/clade_analysis/Analysis2.java b/forester/java/src/org/forester/clade_analysis/AnalysisMulti.java similarity index 51% rename from forester/java/src/org/forester/clade_analysis/Analysis2.java rename to forester/java/src/org/forester/clade_analysis/AnalysisMulti.java index f565b55..219588c 100644 --- a/forester/java/src/org/forester/clade_analysis/Analysis2.java +++ b/forester/java/src/org/forester/clade_analysis/AnalysisMulti.java @@ -41,11 +41,36 @@ import org.forester.phylogeny.PhylogenyNode; import org.forester.phylogeny.data.Confidence; import org.forester.util.ForesterUtil; -public final class Analysis2 { +public final class AnalysisMulti { - public static Result2 execute( final Phylogeny p, final Pattern query, final String separator ) { + private final static String UNKNOWN = "?"; + public final static double DEFAULT_CUTOFF_FOR_SPECIFICS = 0.5; + public final static String DEFAULT_SEPARATOR = "."; + public final static Pattern DEFAULT_QUERY_PATTERN_FOR_PPLACER_TYPE = Pattern.compile( ".+#\\d+_M=(.+)" ); + + + public static ResultMulti execute( final Phylogeny p ) { + return execute( p, DEFAULT_QUERY_PATTERN_FOR_PPLACER_TYPE, DEFAULT_SEPARATOR, DEFAULT_CUTOFF_FOR_SPECIFICS ); + } + + public static ResultMulti execute( final Phylogeny p, final String separator ) { + return execute( p, DEFAULT_QUERY_PATTERN_FOR_PPLACER_TYPE, separator , DEFAULT_CUTOFF_FOR_SPECIFICS ); + } + + public static ResultMulti execute( final Phylogeny p, final String separator, final double cutoff_for_specifics ) { + return execute( p, DEFAULT_QUERY_PATTERN_FOR_PPLACER_TYPE, separator , cutoff_for_specifics ); + } + + public static ResultMulti execute( final Phylogeny p, final double cutoff_for_specifics ) { + return execute( p, DEFAULT_QUERY_PATTERN_FOR_PPLACER_TYPE, DEFAULT_SEPARATOR , cutoff_for_specifics ); + } + + public static ResultMulti execute( final Phylogeny p, + final Pattern query, + final String separator, + final double cutoff_for_specifics ) { final List qnodes = p.getNodes( query ); - final Result2 res = new Result2(); + final ResultMulti res = new ResultMulti(); for( int i = 0; i < qnodes.size(); ++i ) { final PhylogenyNode qnode = qnodes.get( i ); System.out.println( ">>" + qnode.getName() ); @@ -64,7 +89,6 @@ public final class Analysis2 { while ( qnode_pp.getNumberOfDescendants() == 1 ) { qnode_pp = qnode_pp.getParent(); } - // final List qnode_ext_nodes = new ArrayList(); final List qnode_ext_nodes_names = new ArrayList<>(); for( final PhylogenyNode qnode_ext_node : qnode_pp.getAllExternalDescendants() ) { final String name = qnode_ext_node.getName(); @@ -76,8 +100,6 @@ public final class Analysis2 { qnode_ext_nodes_names.add( name ); } } - //final int lec_ext_nodes = qnode_ext_nodes_names.size(); - //final int p_ext_nodes = p.getNumberOfExternalNodes() - 1; final String greatest_common_prefix = ForesterUtil.greatestCommonPrefix( qnode_ext_nodes_names, separator ); // System.out.println( greatest_common_prefix ); Matcher matcher = query.matcher( qnode.getName() ); @@ -93,125 +115,34 @@ public final class Analysis2 { res.addGreatestCommonPrefix( greatest_common_prefix, conf ); } else { - res.addGreatestCommonPrefix( "?", conf ); + res.addGreatestCommonPrefix( UNKNOWN, conf ); } //final String greatest_common_prefix_up[] = analyzeSiblings( qnode_p, qnode_pp, separator, query, res ); final String greatest_common_prefix_up = analyzeSiblings( qnode_p, qnode_pp, separator, query ); - System.out.println( "greatest_common_prefix_up=" + greatest_common_prefix_up + " " + conf); - if ( !ForesterUtil.isEmpty( greatest_common_prefix_up) ) { + System.out.println( "greatest_common_prefix_up=" + greatest_common_prefix_up + " " + conf ); + if ( !ForesterUtil.isEmpty( greatest_common_prefix_up ) ) { res.addGreatestCommonPrefixUp( greatest_common_prefix_up, conf ); } else { - res.addGreatestCommonPrefixUp( "?", conf ); + res.addGreatestCommonPrefixUp( UNKNOWN, conf ); } - // res.addGreatestCommonPrefixUp( greatest_common_prefix_up, conf ); - //res.addGreatestCommonPrefixUp( greatest_common_prefix_up[ 0 ], 0.1 ); - // res.setGreatestCommonPrefixUp( greatest_common_prefix_up[ 0 ] ); - //if ( greatest_common_prefix_up[ 1 ] != null ) { - // res.setGreatestCommonCladeUpSubtreeConfidence( greatest_common_prefix_up[ 1 ] ); - // } - // final String greatest_common_prefix_down[] = analyzeSiblings( qnode, qnode_p, separator,query, res ); - final String greatest_common_prefix_down = analyzeSiblings( qnode, qnode_p, separator, query ); - System.out.println( "greatest_common_prefix_down=" + greatest_common_prefix_down+ " " + conf); - if ( !ForesterUtil.isEmpty( greatest_common_prefix_down) ) { + final String greatest_common_prefix_down = analyzeSiblings( qnode, qnode_p, separator, query ); + System.out.println( "greatest_common_prefix_down=" + greatest_common_prefix_down + " " + conf ); + if ( !ForesterUtil.isEmpty( greatest_common_prefix_down ) ) { res.addGreatestCommonPrefixDown( greatest_common_prefix_down, conf ); } else { - res.addGreatestCommonPrefixDown( "?", conf ); - } - //res.addGreatestCommonPrefixDown( greatest_common_prefix_down, conf ); - // res.setGreatestCommonPrefixDown( greatest_common_prefix_down[ 0 ] ); - // if ( greatest_common_prefix_down[ 1 ] != null ) { - // res.setGreatestCommonCladeDownSubtreeConfidence( greatest_common_prefix_down[ 1 ] ); - // } - } - /* for( final PhylogenyNode qnode_ext_node : qnode_ext_nodes ) { - String name = qnode_ext_node.getName(); - if ( ForesterUtil.isEmptyTrimmed( name ) ) { - throw new IllegalArgumentException( "external node(s) with empty names found" ); - } - name = name.trim(); - if ( !name.equals( query ) ) { - qnode_ext_nodes_names.add( name ); + res.addGreatestCommonPrefixDown( UNKNOWN, conf ); } - }*/ - // if ( greatest_common_prefix.length() < 1 ) { - // res.addWarning( "No greatest common prefix" ); - //res.setGreatestCommonPrefix( "" ); - // } - // else { - // // res.setGreatestCommonPrefix( greatest_common_prefix ); - // res.addGreatestCommonPrefix( prefix, confidence, separator ); //TODO - // } - // if ( qnode_pp.isRoot() ) { - // res.addWarning( "Least Encompassing Clade is entire tree" ); - // } - /* final String conf = obtainConfidence( qnode_pp ); - if ( conf != null ) { - res.setGreatestCommonCladeSubtreeConfidence(conf); - }*/ - /* final String greatest_common_prefix_up[] = analyzeSiblings( qnode_p, qnode_pp, separator ); - res.setGreatestCommonPrefixUp( greatest_common_prefix_up[ 0 ] ); - if ( greatest_common_prefix_up[ 1 ] != null ) { - res.setGreatestCommonCladeUpSubtreeConfidence( greatest_common_prefix_up[ 1 ] ); } - final String greatest_common_prefix_down[] = analyzeSiblings( qnode, qnode_p, separator ); - res.setGreatestCommonPrefixDown( greatest_common_prefix_down[ 0 ] ); - if ( greatest_common_prefix_down[ 1 ] != null ) { - res.setGreatestCommonCladeDownSubtreeConfidence( greatest_common_prefix_down[ 1 ] ); - }*/ + res.analyze( cutoff_for_specifics ); return res; } - private final static void analyzeSiblingsOLD( final PhylogenyNode child, - final PhylogenyNode parent, - final String separator, - final Pattern query, - Result2 res, - double conf2 ) { - final int child_index = child.getChildNodeIndex(); - final List ext_nodes_names = new ArrayList<>(); - final List descs = parent.getDescendants(); - // String conf = null; - for( int i = 0; i < descs.size(); ++i ) { - if ( i != child_index ) { - final PhylogenyNode d = descs.get( i ); - for( final PhylogenyNode n : d.getAllExternalDescendants() ) { - final String name = n.getName(); - if ( ForesterUtil.isEmptyTrimmed( name ) ) { - throw new IllegalArgumentException( "external node(s) with empty names found" ); - } - ext_nodes_names.add( name.trim() ); - } - // if ( descs.size() == 2 ) { - // conf = obtainConfidence( d ); - // } - } - } - //////////////////////////////////////////////////////////// - /* Matcher matcher = query.matcher( child.getName() ); - String conf_str = null; - if ( matcher.find() ) { - conf_str = matcher.group( 1 ); - } - else { - throw new IllegalStateException( "pattern did not match for \"" + child.getName() + "\" -- this should have never happened!" ); - }*/ - //////////////////////////////////////////////////////////// - final String greatest_common_prefix = ForesterUtil.greatestCommonPrefix( ext_nodes_names, separator ); - //final double conf = Double.parseDouble( conf_str ); - if ( !ForesterUtil.isEmpty( greatest_common_prefix ) ) { - res.addGreatestCommonPrefix( greatest_common_prefix, conf2 ); - } - else { - res.addGreatestCommonPrefix( "?", conf2 ); - } - } - private final static String analyzeSiblings( final PhylogenyNode child, - final PhylogenyNode parent, - final String separator, - final Pattern query) { + final PhylogenyNode parent, + final String separator, + final Pattern query ) { final int child_index = child.getChildNodeIndex(); final List ext_nodes_names = new ArrayList<>(); final List descs = parent.getDescendants(); @@ -224,34 +155,17 @@ public final class Analysis2 { if ( ForesterUtil.isEmptyTrimmed( name ) ) { throw new IllegalArgumentException( "external node(s) with empty names found" ); } - - //// - final Matcher m = query.matcher( name ); if ( !m.find() ) { ext_nodes_names.add( name ); } - - //// - } // if ( descs.size() == 2 ) { // conf = obtainConfidence( d ); // } } } - //////////////////////////////////////////////////////////// - /* Matcher matcher = query.matcher( child.getName() ); - String conf_str = null; - if ( matcher.find() ) { - conf_str = matcher.group( 1 ); - } - else { - throw new IllegalStateException( "pattern did not match for \"" + child.getName() + "\" -- this should have never happened!" ); - }*/ - //////////////////////////////////////////////////////////// final String greatest_common_prefix = ForesterUtil.greatestCommonPrefix( ext_nodes_names, separator ); - //final double conf = Double.parseDouble( conf_str ); return greatest_common_prefix; } diff --git a/forester/java/src/org/forester/clade_analysis/Analysis.java b/forester/java/src/org/forester/clade_analysis/AnalysisSingle.java similarity index 97% rename from forester/java/src/org/forester/clade_analysis/Analysis.java rename to forester/java/src/org/forester/clade_analysis/AnalysisSingle.java index 4803f54..5c725b6 100644 --- a/forester/java/src/org/forester/clade_analysis/Analysis.java +++ b/forester/java/src/org/forester/clade_analysis/AnalysisSingle.java @@ -39,9 +39,9 @@ import org.forester.phylogeny.PhylogenyNode; import org.forester.phylogeny.data.Confidence; import org.forester.util.ForesterUtil; -public final class Analysis { +public final class AnalysisSingle { - public static Result execute( final Phylogeny p, final String query, final String separator ) { + public static ResultSingle execute( final Phylogeny p, final String query, final String separator ) { final PhylogenyNode qnode = p.getNode( query ); if ( qnode.isRoot() ) { throw new IllegalStateException( "Unexpected error: Query " + query @@ -74,7 +74,7 @@ public final class Analysis { } } final String greatest_common_prefix = ForesterUtil.greatestCommonPrefix( qnode_ext_nodes_names, separator ); - final Result res = new Result(); + final ResultSingle res = new ResultSingle(); if ( greatest_common_prefix.length() < 1 ) { res.addWarning( "No greatest common prefix" ); res.setGreatestCommonPrefix( "" ); diff --git a/forester/java/src/org/forester/clade_analysis/CladeAnalysisTest.java b/forester/java/src/org/forester/clade_analysis/CladeAnalysisTest.java index f5a9d92..35c08b5 100644 --- a/forester/java/src/org/forester/clade_analysis/CladeAnalysisTest.java +++ b/forester/java/src/org/forester/clade_analysis/CladeAnalysisTest.java @@ -2,8 +2,6 @@ package org.forester.clade_analysis; import java.io.File; -import java.util.List; -import java.util.regex.Pattern; import org.forester.io.parsers.PhylogenyParser; import org.forester.io.parsers.util.ParserUtils; @@ -19,7 +17,7 @@ public class CladeAnalysisTest { public static void main( final String[] args ) { boolean failed = false; - /* if ( !testCladeAnalysis1() ) { + if ( !testCladeAnalysis1() ) { System.out.println( "Clade analysis 1 failed" ); failed = true; } @@ -34,18 +32,21 @@ public class CladeAnalysisTest { if ( !testCladeAnalysis4() ) { System.out.println( "Clade analysis 4 failed" ); failed = true; - */ + } if ( !testCladeAnalysis5() ) { System.out.println( "Clade analysis 5 failed" ); failed = true; } - /* if ( !testCladeAnalysis6() ) { + if ( !testCladeAnalysis6() ) { System.out.println( "Clade analysis 6 failed" ); failed = true; - }*/ + } if ( !failed ) { System.out.println( "OK" ); } + else { + System.out.println( "NOT OK" ); + } } public static boolean test() { @@ -76,7 +77,7 @@ public class CladeAnalysisTest { final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( intreefile1, true ); final Phylogeny p1 = factory.create( intreefile1, pp )[ 0 ]; - Result res = Analysis.execute( p1, "A.1.1.1", "." ); + ResultSingle res = AnalysisSingle.execute( p1, "A.1.1.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.1" ) ) { return false; } @@ -95,7 +96,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.1.1.2", "." ); + res = AnalysisSingle.execute( p1, "A.1.1.2", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.1" ) ) { return false; } @@ -114,7 +115,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.1.1.3", "." ); + res = AnalysisSingle.execute( p1, "A.1.1.3", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.1" ) ) { return false; } @@ -133,7 +134,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.1.1.4", "." ); + res = AnalysisSingle.execute( p1, "A.1.1.4", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.1.1" ) ) { return false; } @@ -152,7 +153,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.1.2.1", "." ); + res = AnalysisSingle.execute( p1, "A.1.2.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A" ) ) { return false; } @@ -171,7 +172,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.2.1.1", "." ); + res = AnalysisSingle.execute( p1, "A.2.1.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A" ) ) { return false; } @@ -190,7 +191,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.2.1.2", "." ); + res = AnalysisSingle.execute( p1, "A.2.1.2", "." ); if ( !res.getGreatestCommonPrefix().equals( "A" ) ) { return false; } @@ -209,7 +210,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.3.1.1", "." ); + res = AnalysisSingle.execute( p1, "A.3.1.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.3" ) ) { return false; } @@ -228,7 +229,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.3.1.2", "." ); + res = AnalysisSingle.execute( p1, "A.3.1.2", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.3" ) ) { return false; } @@ -247,7 +248,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.3.2.1", "." ); + res = AnalysisSingle.execute( p1, "A.3.2.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.3" ) ) { return false; } @@ -266,7 +267,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.3.3.1", "." ); + res = AnalysisSingle.execute( p1, "A.3.3.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A" ) ) { return false; } @@ -285,7 +286,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.4.1.1", "." ); + res = AnalysisSingle.execute( p1, "A.4.1.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.4.1" ) ) { return false; } @@ -304,7 +305,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.4.1.1.a", "." ); + res = AnalysisSingle.execute( p1, "A.4.1.1.a", "." ); if ( !res.getGreatestCommonPrefix().equals( "A.4.1" ) ) { return false; } @@ -323,9 +324,9 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.4.1.2", "." ); - res = Analysis.execute( p1, "A.4.1.2.a", "." ); - res = Analysis.execute( p1, "A.5.1.1", "." ); + res = AnalysisSingle.execute( p1, "A.4.1.2", "." ); + res = AnalysisSingle.execute( p1, "A.4.1.2.a", "." ); + res = AnalysisSingle.execute( p1, "A.5.1.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "A" ) ) { return false; } @@ -344,7 +345,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.5.1.2", "." ); + res = AnalysisSingle.execute( p1, "A.5.1.2", "." ); if ( !res.getGreatestCommonPrefix().equals( "A" ) ) { return false; } @@ -363,7 +364,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "A.6.3.12", "." ); + res = AnalysisSingle.execute( p1, "A.6.3.12", "." ); if ( !res.getGreatestCommonPrefix().equals( "A" ) ) { return false; } @@ -382,7 +383,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "B.1.1.1", "." ); + res = AnalysisSingle.execute( p1, "B.1.1.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "" ) ) { return false; } @@ -401,7 +402,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 2 ) { return false; } - res = Analysis.execute( p1, "B.1.234.3", "." ); + res = AnalysisSingle.execute( p1, "B.1.234.3", "." ); if ( !res.getGreatestCommonPrefix().equals( "" ) ) { return false; } @@ -420,7 +421,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 2 ) { return false; } - res = Analysis.execute( p1, "C.1.1.1", "." ); + res = AnalysisSingle.execute( p1, "C.1.1.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "C.1" ) ) { return false; } @@ -439,7 +440,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "C.1.1.2", "." ); + res = AnalysisSingle.execute( p1, "C.1.1.2", "." ); if ( !res.getGreatestCommonPrefix().equals( "C.1" ) ) { return false; } @@ -458,7 +459,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "C.1.2.1", "." ); + res = AnalysisSingle.execute( p1, "C.1.2.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "C" ) ) { return false; } @@ -477,7 +478,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "C.2.1", "." ); + res = AnalysisSingle.execute( p1, "C.2.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "C" ) ) { return false; } @@ -496,7 +497,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "C.3", "." ); + res = AnalysisSingle.execute( p1, "C.3", "." ); if ( !res.getGreatestCommonPrefix().equals( "" ) ) { return false; } @@ -515,7 +516,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 1 ) { return false; } - res = Analysis.execute( p1, "QE.1.1.1.2.1", "." ); + res = AnalysisSingle.execute( p1, "QE.1.1.1.2.1", "." ); if ( !res.getGreatestCommonPrefix().equals( "" ) ) { return false; } @@ -548,7 +549,7 @@ public class CladeAnalysisTest { final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( intreefile1, true ); final Phylogeny p1 = factory.create( intreefile1, pp )[ 0 ]; - Result res = Analysis.execute( p1, "6_DQ278891", null ); + ResultSingle res = AnalysisSingle.execute( p1, "6_DQ278891", null ); if ( !res.getGreatestCommonPrefix().equals( "6_" ) ) { return false; } @@ -567,7 +568,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "6xa_EU408330", null ); + res = AnalysisSingle.execute( p1, "6xa_EU408330", null ); if ( !res.getGreatestCommonPrefix().equals( "6xa_EU40833" ) ) { return false; } @@ -586,7 +587,7 @@ public class CladeAnalysisTest { if ( res.getWarnings().size() != 0 ) { return false; } - res = Analysis.execute( p1, "7a_EF108306", null ); + res = AnalysisSingle.execute( p1, "7a_EF108306", null ); if ( !res.getGreatestCommonPrefix().equals( "" ) ) { return false; } @@ -615,63 +616,56 @@ public class CladeAnalysisTest { private static boolean testCladeAnalysis3() { try { - final Result2 res1 = new Result2(); + final ResultMulti res1 = new ResultMulti(); res1.addGreatestCommonPrefix( "A.1.1", 0.3 ); res1.addGreatestCommonPrefix( "A.1.2", 0.3 ); res1.addGreatestCommonPrefix( "A.1.3", 0.3 ); res1.addGreatestCommonPrefix( "B.1", 0.1 ); - res1.analyzeGreatestCommonPrefixes( 0.5 ); - //res1.analyzeGreatestCommonPrefixesDown(0.5); - //res1.analyzeGreatestCommonPrefixesUp(0.5); - System.out.print( res1.toString()); - System.out.println( "------------------------- "); + res1.analyze( 0.5 ); + System.out.print( res1.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res2 = new Result2( "." ); + final ResultMulti res2 = new ResultMulti( "." ); res2.addGreatestCommonPrefix( "A.1.1.1", 0.1 ); res2.addGreatestCommonPrefix( "A.1", 0.7 ); res2.addGreatestCommonPrefix( "A.1.2", 0.1 ); res2.addGreatestCommonPrefix( "B.1", 0.1 ); - res2.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res2.toString()); - System.out.println( "------------------------- "); + res2.analyze( 0.3 ); + System.out.print( res2.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res3 = new Result2( "." ); + final ResultMulti res3 = new ResultMulti( "." ); res3.addGreatestCommonPrefix( "A.1.1.1", 0.1 ); res3.addGreatestCommonPrefix( "A.1.1.1.1", 0.6 ); res3.addGreatestCommonPrefix( "A.1", 0.1 ); res3.addGreatestCommonPrefix( "A.1.2", 0.1 ); res3.addGreatestCommonPrefix( "B.1", 0.1 ); - res3.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res3.toString()); - System.out.println( "------------------------- "); + res3.analyze( 0.3 ); + System.out.print( res3.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res33 = new Result2( "." ); + final ResultMulti res33 = new ResultMulti( "." ); res33.addGreatestCommonPrefix( "A.1.1.1", 0.1 ); res33.addGreatestCommonPrefix( "A.1.1.1.1", 0.3 ); res33.addGreatestCommonPrefix( "A.1", 0.1 ); res33.addGreatestCommonPrefix( "A.1.2", 0.1 ); res33.addGreatestCommonPrefix( "B.1", 0.1 ); res33.addGreatestCommonPrefix( "B.1.1.1", 0.3 ); - res33.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res33.toString()); - System.out.println( "------------------------- "); + res33.analyze( 0.3 ); + System.out.print( res33.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res4 = new Result2(); + final ResultMulti res4 = new ResultMulti(); res4.addGreatestCommonPrefix( "A.1.1.1.1", 0.35 ); res4.addGreatestCommonPrefix( "A.1.1.1.2", 0.35 ); res4.addGreatestCommonPrefix( "A.1", 0.1 ); res4.addGreatestCommonPrefix( "A.1.2", 0.1 ); res4.addGreatestCommonPrefix( "B.1", 0.1 ); - res4.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res4.toString()); - System.out.println( "------------------------- "); + res4.analyze( 0.3 ); + System.out.print( res4.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res5 = new Result2(); + final ResultMulti res5 = new ResultMulti(); res5.addGreatestCommonPrefix( "A.1.1.1.1", 0.2 ); res5.addGreatestCommonPrefix( "C.2.3", 0.2 ); res5.addGreatestCommonPrefix( "A.1.5", 0.1 ); @@ -679,54 +673,50 @@ public class CladeAnalysisTest { res5.addGreatestCommonPrefix( "B.1.1", 0.2 ); res5.addGreatestCommonPrefix( "B.1.2", 0.09 ); res5.addGreatestCommonPrefix( "D.1.1.1.1", 0.01 ); - res5.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res5.toString()); - System.out.println( "------------------------- "); + res5.analyze( 0.3 ); + System.out.print( res5.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res6 = new Result2(); + final ResultMulti res6 = new ResultMulti(); res6.addGreatestCommonPrefix( "A.1.1.1", 0.05 ); res6.addGreatestCommonPrefix( "A.1.1.1.1", 0.65 ); res6.addGreatestCommonPrefix( "A.1", 0.1 ); res6.addGreatestCommonPrefix( "A.1.2", 0.1 ); res6.addGreatestCommonPrefix( "B.1", 0.1 ); - res6.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res6.toString()); - System.out.println( "------------------------- "); + res6.analyze( 0.3 ); + System.out.print( res6.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res7 = new Result2(); + final ResultMulti res7 = new ResultMulti(); res7.addGreatestCommonPrefix( "A.1.1.1", 0.07 ); res7.addGreatestCommonPrefix( "A.1.1.1.1", 0.9 ); res7.addGreatestCommonPrefix( "A.1", 0.01 ); res7.addGreatestCommonPrefix( "A.1.2", 0.01 ); res7.addGreatestCommonPrefix( "B.1", 0.01 ); - res7.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res7.toString()); - System.out.println( "------------------------- "); + res7.analyze( 0.3 ); + System.out.print( res7.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res8 = new Result2( "_/_" ); + final ResultMulti res8 = new ResultMulti( "_/_" ); res8.addGreatestCommonPrefix( "AA_/_abc_/_def", 0.07 ); res8.addGreatestCommonPrefix( "AA_/_abc_/_sfc", 0.9 ); res8.addGreatestCommonPrefix( "AA_/_abc_/_xcd", 0.01 ); res8.addGreatestCommonPrefix( "AA_/_abc_/_memr", 0.01 ); res8.addGreatestCommonPrefix( "AA_/_abc_/_fkem_/_odem", 0.01 ); - res8.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res8.toString()); - System.out.println( "------------------------- "); + res8.analyze( 0.3 ); + System.out.print( res8.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - final Result2 res9 = new Result2( "_/_" ); + final ResultMulti res9 = new ResultMulti( "_/_" ); res9.addGreatestCommonPrefix( "AA_/_abc_/_def", 0.07 ); res9.addGreatestCommonPrefix( "AA_/_abc_/_sfc", 0.6 ); res9.addGreatestCommonPrefix( "AA_/_abc_/_xcd", 0.01 ); res9.addGreatestCommonPrefix( "AA_/_abc_/_memr", 0.01 ); res9.addGreatestCommonPrefix( "AA_/_abc_/_fkem_/_odem", 0.01 ); res9.addGreatestCommonPrefix( "BB_/_fke_/_dme_/_nx2", 0.3 ); - res9.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res9.toString()); - System.out.println( "------------------------- "); + res9.analyze( 0.3 ); + System.out.print( res9.toString() ); + System.out.println( "------------------------- " ); System.out.println(); } catch ( final Exception e ) { @@ -735,41 +725,18 @@ public class CladeAnalysisTest { } return true; } - + private static boolean testCladeAnalysis4() { try { final File intreefile1 = new File( PATH_TO_TEST_DATA + "pplacer_2.tre" ); final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( intreefile1, true ); final Phylogeny p1 = factory.create( intreefile1, pp )[ 0 ]; - Pattern query = Pattern.compile(".+#\\d+_M=(.+)"); - Result2 res = Analysis2.execute( p1, query, "." ); - - res.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res.toString()); - System.out.println( "------------------------- "); + ResultMulti res2 = AnalysisMulti.execute( p1 ); + res2.analyze( 0.3 ); + System.out.print( res2.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - // Result res = Analysis.execute( p1, "A.1.1.1", "." ); - /* if ( !res.getGreatestCommonPrefix().equals( "A.1" ) ) { - return false; - } - if ( !res.getGreatestCommonPrefixDown().equals( "A.1.1" ) ) { - return false; - } - if ( !res.getGreatestCommonPrefixUp().equals( "A.1.2.1" ) ) { - return false; - } - if ( res.getLeastEncompassingCladeSize() != 4 ) { - return false; - } - if ( res.getTreeSize() != 25 ) { - return false; - } - if ( res.getWarnings().size() != 0 ) { - return false; - }*/ - } catch ( final Exception e ) { e.printStackTrace( System.out ); @@ -777,41 +744,18 @@ public class CladeAnalysisTest { } return true; } - + private static boolean testCladeAnalysis5() { try { final File intreefile1 = new File( PATH_TO_TEST_DATA + "clade_analysis_test_3.xml" ); final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( intreefile1, true ); final Phylogeny p1 = factory.create( intreefile1, pp )[ 0 ]; - Pattern query = Pattern.compile(".+#\\d+_M=(.+)"); - Result2 res = Analysis2.execute( p1, query, "." ); - - res.analyzeGreatestCommonPrefixes( 0.3 ); - System.out.print( res.toString()); - System.out.println( "------------------------- "); + ResultMulti res = AnalysisMulti.execute( p1 ); + res.analyze( 0.3 ); + System.out.print( res.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - // Result res = Analysis.execute( p1, "A.1.1.1", "." ); - /* if ( !res.getGreatestCommonPrefix().equals( "A.1" ) ) { - return false; - } - if ( !res.getGreatestCommonPrefixDown().equals( "A.1.1" ) ) { - return false; - } - if ( !res.getGreatestCommonPrefixUp().equals( "A.1.2.1" ) ) { - return false; - } - if ( res.getLeastEncompassingCladeSize() != 4 ) { - return false; - } - if ( res.getTreeSize() != 25 ) { - return false; - } - if ( res.getWarnings().size() != 0 ) { - return false; - }*/ - } catch ( final Exception e ) { e.printStackTrace( System.out ); @@ -819,41 +763,17 @@ public class CladeAnalysisTest { } return true; } - + private static boolean testCladeAnalysis6() { try { final File intreefile1 = new File( PATH_TO_TEST_DATA + "clade_analysis_test_4.xml" ); final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( intreefile1, true ); final Phylogeny p1 = factory.create( intreefile1, pp )[ 0 ]; - Pattern query = Pattern.compile(".+#\\d+_M=(.+)"); - Result2 res = Analysis2.execute( p1, query, "." ); - - res.analyzeGreatestCommonPrefixes( 0.45 ); - System.out.print( res.toString()); - System.out.println( "------------------------- "); + ResultMulti res = AnalysisMulti.execute( p1, 0.45 ); + System.out.print( res.toString() ); + System.out.println( "------------------------- " ); System.out.println(); - - // Result res = Analysis.execute( p1, "A.1.1.1", "." ); - /* if ( !res.getGreatestCommonPrefix().equals( "A.1" ) ) { - return false; - } - if ( !res.getGreatestCommonPrefixDown().equals( "A.1.1" ) ) { - return false; - } - if ( !res.getGreatestCommonPrefixUp().equals( "A.1.2.1" ) ) { - return false; - } - if ( res.getLeastEncompassingCladeSize() != 4 ) { - return false; - } - if ( res.getTreeSize() != 25 ) { - return false; - } - if ( res.getWarnings().size() != 0 ) { - return false; - }*/ - } catch ( final Exception e ) { e.printStackTrace( System.out ); diff --git a/forester/java/src/org/forester/clade_analysis/Result2.java b/forester/java/src/org/forester/clade_analysis/ResultMulti.java similarity index 69% rename from forester/java/src/org/forester/clade_analysis/Result2.java rename to forester/java/src/org/forester/clade_analysis/ResultMulti.java index 0135bec..d3bfba3 100644 --- a/forester/java/src/org/forester/clade_analysis/Result2.java +++ b/forester/java/src/org/forester/clade_analysis/ResultMulti.java @@ -37,35 +37,33 @@ import java.util.TreeMap; import org.forester.util.ForesterUtil; -public final class Result2 { +public final class ResultMulti { private final String _separator; - private final List _greatest_common_prefixes = new ArrayList(); - private List _greatest_common_prefixes_up = new ArrayList(); - private List _greatest_common_prefixes_down = new ArrayList(); - private final List _warnings = new ArrayList<>(); - private String _greatest_common_clade_subtree_confidence = ""; - private String _greatest_common_clade_subtree_confidence_up = ""; - private String _greatest_common_clade_subtree_confidence_down = ""; - private List _all = null; - private List _collapsed = null; - private List _cleaned_spec = null; - private boolean _has_specifics = false; - private List _all_up = null; - private List _collapsed_up = null; - private List _cleaned_spec_up = null; - private boolean _has_specifics_up = false; - private List _all_down = null; - private List _collapsed_down = null; - private List _cleaned_spec_down = null; - private boolean _has_specifics_down = false; - - public Result2( final String separator ) { + private final List _greatest_common_prefixes = new ArrayList(); + private final List _greatest_common_prefixes_up = new ArrayList(); + private final List _greatest_common_prefixes_down = new ArrayList(); + private List _all = null; + private List _collapsed = null; + private List _cleaned_spec = null; + private boolean _has_specifics = false; + private List _all_up = null; + private List _collapsed_up = null; + private List _cleaned_spec_up = null; + private boolean _has_specifics_up = false; + private List _all_down = null; + private List _collapsed_down = null; + private List _cleaned_spec_down = null; + private boolean _has_specifics_down = false; + + ResultMulti( final String separator ) { _separator = separator; + reset(); } - public Result2() { - _separator = ".";//TODO make const somewhere + ResultMulti() { + _separator = AnalysisMulti.DEFAULT_SEPARATOR; + reset(); } public List getAllMultiHitPrefixesUp() { @@ -116,8 +114,121 @@ public final class Result2 { return _has_specifics; } - void addWarning( final String warning ) { - _warnings.add( warning ); + @Override + public final String toString() { + final StringBuilder sb = new StringBuilder(); + sb.append( "Cleaned:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _all ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Collapsed:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _collapsed ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + if ( _has_specifics ) { + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Specifics:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _cleaned_spec ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Collapsed With Specifics:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _collapsed ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix spec : _cleaned_spec ) { + if ( spec.getPrefix().startsWith( prefix.getPrefix() ) ) { + sb.append( " " + spec ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + } + } + } + if ( !ForesterUtil.isEmpty( _all_down ) ) { + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Cleaned Down:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _all_down ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Collapsed Down:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _collapsed_down ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + if ( _has_specifics_down ) { + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Specifics Down:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _cleaned_spec_down ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Collapsed With Specifics Down:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _collapsed_down ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix spec : _cleaned_spec_down ) { + if ( spec.getPrefix().startsWith( prefix.getPrefix() ) ) { + sb.append( " " + spec ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + } + } + } + } + if ( !ForesterUtil.isEmpty( _all_up ) ) { + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Cleaned Up:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _all_up ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Collapsed Up:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _collapsed_up ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + if ( _has_specifics ) { + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Specifics Up:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _cleaned_spec_up ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Collapsed With Specifics Up:" ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix prefix : _collapsed_up ) { + sb.append( prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + for( final Prefix spec : _cleaned_spec_up ) { + if ( spec.getPrefix().startsWith( prefix.getPrefix() ) ) { + sb.append( " " + spec ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + } + } + } + } + } + return sb.toString(); } void addGreatestCommonPrefix( final String prefix, final double confidence ) { @@ -132,120 +243,85 @@ public final class Result2 { _greatest_common_prefixes_down.add( new Prefix( prefix_down, confidence, _separator ) ); } - void setGreatestCommonCladeSubtreeConfidence( final String greatest_common_clade_confidence ) { - _greatest_common_clade_subtree_confidence = greatest_common_clade_confidence; - } - - void setGreatestCommonCladeUpSubtreeConfidence( final String greatest_common_clade_confidence_up ) { - _greatest_common_clade_subtree_confidence_up = greatest_common_clade_confidence_up; - } - - void setGreatestCommonCladeDownSubtreeConfidence( final String greatest_common_clade_confidence_down ) { - _greatest_common_clade_subtree_confidence_down = greatest_common_clade_confidence_down; - } - - public String getGreatestCommonCladeSubtreeConfidence() { - return _greatest_common_clade_subtree_confidence; - } - - public String getGreatestCommonCladeUpSubtreeConfidence() { - return _greatest_common_clade_subtree_confidence_up; - } - - public String getGreatestCommonCladeDownSubtreeConfidence() { - return _greatest_common_clade_subtree_confidence_down; - } - - public List getWarnings() { - return _warnings; - } - - public void analyzeGreatestCommonPrefixes( final double cutoff_for_specifics ) { + final void analyze( final double cutoff_for_specifics ) { + reset(); analyzeGreatestCommonPrefixes( _greatest_common_prefixes, _separator, cutoff_for_specifics ); analyzeGreatestCommonPrefixesUp( _greatest_common_prefixes_up, _separator, cutoff_for_specifics ); analyzeGreatestCommonPrefixesDown( _greatest_common_prefixes_down, _separator, cutoff_for_specifics ); } - public void analyzeGreatestCommonPrefixes() { - analyzeGreatestCommonPrefixes( _greatest_common_prefixes, _separator, -1 ); - } - - private void analyzeGreatestCommonPrefixesUp( final double cutoff_for_specifics ) { - analyzeGreatestCommonPrefixesUp( _greatest_common_prefixes_up, _separator, cutoff_for_specifics ); - } - - private void analyzeGreatestCommonPrefixesUp() { - analyzeGreatestCommonPrefixesUp( _greatest_common_prefixes_up, _separator, -1 ); - } - - private void analyzeGreatestCommonPrefixesDown( final double cutoff_for_specifics ) { - analyzeGreatestCommonPrefixesDown( _greatest_common_prefixes_down, _separator, cutoff_for_specifics ); - } - - private void analyzeGreatestCommonPrefixesDown() { - analyzeGreatestCommonPrefixesDown( _greatest_common_prefixes_down, _separator, -1 ); + private final void reset() { + _all = new ArrayList(); + _collapsed = new ArrayList(); + _cleaned_spec = new ArrayList(); + _has_specifics = false; + _all_up = new ArrayList(); + _collapsed_up = new ArrayList(); + _cleaned_spec_up = new ArrayList(); + _has_specifics_up = false; + _all_down = new ArrayList(); + _collapsed_down = new ArrayList(); + _cleaned_spec_down = new ArrayList(); + _has_specifics_down = false; } private final void analyzeGreatestCommonPrefixes( final List greatest_common_prefixes, final String separator, final double cutoff ) { final List l = obtainAllPrefixes( greatest_common_prefixes, separator ); - sortPrefixesAccordingToConfidence( l ); - _all = removeLessSpecificPrefixes( l ); - _collapsed = collapse( _all ); - _has_specifics = false; - if ( cutoff >= 0 ) { - _cleaned_spec = obtainSpecifics( cutoff, _all, _collapsed ); - if ( _cleaned_spec != null && _cleaned_spec.size() > 0 ) { - _has_specifics = true; + if ( !ForesterUtil.isEmpty( l ) ) { + sortPrefixesAccordingToConfidence( l ); + _all = removeLessSpecificPrefixes( l ); + _collapsed = collapse( _all ); + _has_specifics = false; + if ( cutoff >= 0 ) { + _cleaned_spec = obtainSpecifics( cutoff, _all, _collapsed ); + if ( !ForesterUtil.isEmpty( _cleaned_spec ) ) { + _has_specifics = true; + } } } - else { - _cleaned_spec = null; - } } private final void analyzeGreatestCommonPrefixesUp( final List greatest_common_prefixes_up, final String separator, final double cutoff ) { final List l = obtainAllPrefixes( greatest_common_prefixes_up, separator ); - sortPrefixesAccordingToConfidence( l ); - _all_up = removeLessSpecificPrefixes( l ); - _collapsed_up = collapse( _all_up ); - _has_specifics_up = false; - if ( cutoff >= 0 ) { - _cleaned_spec_up = obtainSpecifics( cutoff, _all_up, _collapsed_up ); - if ( _cleaned_spec_up != null && _cleaned_spec_up.size() > 0 ) { - _has_specifics_up = true; + if ( !ForesterUtil.isEmpty( l ) ) { + sortPrefixesAccordingToConfidence( l ); + _all_up = removeLessSpecificPrefixes( l ); + _collapsed_up = collapse( _all_up ); + _has_specifics_up = false; + if ( cutoff >= 0 ) { + _cleaned_spec_up = obtainSpecifics( cutoff, _all_up, _collapsed_up ); + if ( !ForesterUtil.isEmpty( _cleaned_spec_up ) ) { + _has_specifics_up = true; + } } } - else { - _cleaned_spec_up = null; - } } - private final void analyzeGreatestCommonPrefixesDown( final List greatest_common_prefixes_down, - final String separator, - final double cutoff ) { + final void analyzeGreatestCommonPrefixesDown( final List greatest_common_prefixes_down, + final String separator, + final double cutoff ) { final List l = obtainAllPrefixes( greatest_common_prefixes_down, separator ); - sortPrefixesAccordingToConfidence( l ); - _all_down = removeLessSpecificPrefixes( l ); - _collapsed_down = collapse( _all_down ); - _has_specifics_down = false; - if ( cutoff >= 0 ) { - _cleaned_spec_down = obtainSpecifics( cutoff, _all_down, _collapsed_down ); - if ( _cleaned_spec_down != null && _cleaned_spec_down.size() > 0 ) { - _has_specifics_down = true; + if ( !ForesterUtil.isEmpty( l ) ) { + sortPrefixesAccordingToConfidence( l ); + _all_down = removeLessSpecificPrefixes( l ); + _collapsed_down = collapse( _all_down ); + _has_specifics_down = false; + if ( cutoff >= 0 ) { + _cleaned_spec_down = obtainSpecifics( cutoff, _all_down, _collapsed_down ); + if ( !ForesterUtil.isEmpty( _cleaned_spec_down ) ) { + _has_specifics_down = true; + } } } - else { - _cleaned_spec_down = null; - } } - private final static List obtainSpecifics( final double cutoff, - final List cleaned, - final List collapsed ) { + final static List obtainSpecifics( final double cutoff, + final List cleaned, + final List collapsed ) { final List cleaned_spec = new ArrayList<>(); final Set collapsed_set = new HashSet<>(); for( final Prefix prefix : collapsed ) { @@ -285,7 +361,7 @@ public final class Result2 { } } if ( !ForesterUtil.isEqual( confidence_sum, 1.0, 1E-5 ) ) { - // throw new IllegalArgumentException( "Confidences add up to " + confidence_sum + " instead of 1.0" ); + throw new IllegalArgumentException( "Confidences add up to " + confidence_sum + " instead of 1.0" ); } return collapsed; } @@ -355,124 +431,4 @@ public final class Result2 { } return l; } - - public final String toString() { - final StringBuilder sb = new StringBuilder(); - //TODO add all other stuff - sb.append( "Cleaned:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _all ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Collapsed:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _collapsed ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - if ( _has_specifics ) { - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Specifics:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _cleaned_spec ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Collapsed With Specifics:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _collapsed ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix spec : _cleaned_spec ) { - if ( spec.getPrefix().startsWith( prefix.getPrefix() ) ) { - sb.append( " " + spec ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - } - } - } - ////// - if ( _all_down != null ) { - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Cleaned Down:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _all_down ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Collapsed Down:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _collapsed_down ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - if ( _has_specifics_down ) { - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Specifics Down:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _cleaned_spec_down ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Collapsed With Specifics Down:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _collapsed_down ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix spec : _cleaned_spec_down ) { - if ( spec.getPrefix().startsWith( prefix.getPrefix() ) ) { - sb.append( " " + spec ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - } - } - } - } - ////// - if ( _all_up != null ) { - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Cleaned Up:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _all_up ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Collapsed Up:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _collapsed_up ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - if ( _has_specifics ) { - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Specifics Up:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _cleaned_spec_up ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - sb.append( ForesterUtil.LINE_SEPARATOR ); - sb.append( "Collapsed With Specifics Up:" ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix prefix : _collapsed_up ) { - sb.append( prefix ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - for( final Prefix spec : _cleaned_spec_up ) { - if ( spec.getPrefix().startsWith( prefix.getPrefix() ) ) { - sb.append( " " + spec ); - sb.append( ForesterUtil.LINE_SEPARATOR ); - } - } - } - } - } - ///// - return sb.toString(); - } } diff --git a/forester/java/src/org/forester/clade_analysis/Result.java b/forester/java/src/org/forester/clade_analysis/ResultSingle.java similarity index 85% rename from forester/java/src/org/forester/clade_analysis/Result.java rename to forester/java/src/org/forester/clade_analysis/ResultSingle.java index e11fcd5..a122d7e 100644 --- a/forester/java/src/org/forester/clade_analysis/Result.java +++ b/forester/java/src/org/forester/clade_analysis/ResultSingle.java @@ -28,46 +28,20 @@ package org.forester.clade_analysis; import java.util.ArrayList; import java.util.List; -public final class Result { - - private String _greatest_common_prefix = ""; - private String _greatest_common_prefix_up = ""; - private String _greatest_common_prefix_down = ""; - private final List _warnings = new ArrayList<>(); - private int _lec_ext_nodes = 0; - private int _p_ext_nodes = 0; +import org.forester.util.ForesterUtil; + +public final class ResultSingle { + + private String _greatest_common_prefix = ""; + private String _greatest_common_prefix_up = ""; + private String _greatest_common_prefix_down = ""; + private final List _warnings = new ArrayList<>(); + private int _lec_ext_nodes = 0; + private int _p_ext_nodes = 0; private String _greatest_common_clade_subtree_confidence = ""; private String _greatest_common_clade_subtree_confidence_up = ""; private String _greatest_common_clade_subtree_confidence_down = ""; - void addWarning( final String warning ) { - _warnings.add( warning ); - } - - void setGreatestCommonPrefix( final String greatest_common_prefix ) { - _greatest_common_prefix = greatest_common_prefix; - } - - void setGreatestCommonPrefixUp( final String greatest_common_prefix_up ) { - _greatest_common_prefix_up = greatest_common_prefix_up; - } - - void setGreatestCommonPrefixDown( final String greatest_common_prefix_down ) { - _greatest_common_prefix_down = greatest_common_prefix_down; - } - - void setGreatestCommonCladeSubtreeConfidence( final String greatest_common_clade_confidence ) { - _greatest_common_clade_subtree_confidence = greatest_common_clade_confidence; - } - - void setGreatestCommonCladeUpSubtreeConfidence( final String greatest_common_clade_confidence_up ) { - _greatest_common_clade_subtree_confidence_up = greatest_common_clade_confidence_up; - } - - void setGreatestCommonCladeDownSubtreeConfidence( final String greatest_common_clade_confidence_down ) { - _greatest_common_clade_subtree_confidence_down = greatest_common_clade_confidence_down; - } - public String getGreatestCommonPrefix() { return _greatest_common_prefix; } @@ -96,14 +70,6 @@ public final class Result { return _warnings; } - void setLeastEncompassingCladeSize( final int lec_ext_nodes ) { - _lec_ext_nodes = lec_ext_nodes; - } - - void setTreeSize( final int p_ext_nodes ) { - _p_ext_nodes = p_ext_nodes; - } - public int getLeastEncompassingCladeSize() { return _lec_ext_nodes; } @@ -111,4 +77,50 @@ public final class Result { public int getTreeSize() { return _p_ext_nodes; } + + public final String toString() { + final StringBuilder sb = new StringBuilder(); + sb.append( "Greatest common prefix : " + _greatest_common_prefix ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Greatest common prefix down: " + _greatest_common_prefix_down ); + sb.append( ForesterUtil.LINE_SEPARATOR ); + sb.append( "Greatest common prefix up : " + _greatest_common_prefix_up ); + return sb.toString(); + } + + void addWarning( final String warning ) { + _warnings.add( warning ); + } + + void setGreatestCommonPrefix( final String greatest_common_prefix ) { + _greatest_common_prefix = greatest_common_prefix; + } + + void setGreatestCommonPrefixUp( final String greatest_common_prefix_up ) { + _greatest_common_prefix_up = greatest_common_prefix_up; + } + + void setGreatestCommonPrefixDown( final String greatest_common_prefix_down ) { + _greatest_common_prefix_down = greatest_common_prefix_down; + } + + void setGreatestCommonCladeSubtreeConfidence( final String greatest_common_clade_confidence ) { + _greatest_common_clade_subtree_confidence = greatest_common_clade_confidence; + } + + void setGreatestCommonCladeUpSubtreeConfidence( final String greatest_common_clade_confidence_up ) { + _greatest_common_clade_subtree_confidence_up = greatest_common_clade_confidence_up; + } + + void setGreatestCommonCladeDownSubtreeConfidence( final String greatest_common_clade_confidence_down ) { + _greatest_common_clade_subtree_confidence_down = greatest_common_clade_confidence_down; + } + + void setLeastEncompassingCladeSize( final int lec_ext_nodes ) { + _lec_ext_nodes = lec_ext_nodes; + } + + void setTreeSize( final int p_ext_nodes ) { + _p_ext_nodes = p_ext_nodes; + } } -- 1.7.10.2