X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FNewickFile.java;h=517701bc1ecaaca880a925cccf8c6be2e926fbd7;hb=8fa69554edf6aeb278b4a4afd8e2b60264fdccd8;hp=800d51adf9d213bc4d6e929a18dd5313cadbfa19;hpb=17e77c3f2949a0729322b4a8d907f3f34b6a9914;p=jalview.git diff --git a/src/jalview/io/NewickFile.java b/src/jalview/io/NewickFile.java index 800d51a..517701b 100755 --- a/src/jalview/io/NewickFile.java +++ b/src/jalview/io/NewickFile.java @@ -1,6 +1,6 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9) - * Copyright (C) 2015 The Jalview Authors + * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) + * Copyright (C) $$Year-Rel$$ The Jalview Authors * * This file is part of Jalview. * @@ -35,6 +35,8 @@ import java.io.FileReader; import java.io.IOException; import java.util.StringTokenizer; +import com.stevesoft.pat.Regex; + /** * Parse a new hanpshire style tree Caveats: NHX files are NOT supported and the * tree distances and topology are unreliable when they are parsed. TODO: on @@ -87,14 +89,14 @@ public class NewickFile extends FileParse boolean printRootInfo = true; - private com.stevesoft.pat.Regex[] NodeSafeName = new com.stevesoft.pat.Regex[] - { new com.stevesoft.pat.Regex().perlCode("m/[\\[,:'()]/"), // test for + private Regex[] NodeSafeName = new Regex[] { + new Regex().perlCode("m/[\\[,:'()]/"), // test for // requiring // quotes - new com.stevesoft.pat.Regex().perlCode("s/'/''/"), // escaping quote + new Regex().perlCode("s/'/''/"), // escaping quote // characters - new com.stevesoft.pat.Regex().perlCode("s/\\/w/_/") // unqoted whitespace - // transformation + new Regex().perlCode("s/\\/w/_/") // unqoted whitespace + // transformation }; char QuoteChar = '\''; @@ -110,7 +112,7 @@ public class NewickFile extends FileParse */ public NewickFile(String inStr) throws IOException { - super(inStr, "Paste"); + super(inStr, DataSourceType.PASTE); } /** @@ -118,15 +120,16 @@ public class NewickFile extends FileParse * * @param inFile * DOCUMENT ME! - * @param type + * @param protocol * DOCUMENT ME! * * @throws IOException * DOCUMENT ME! */ - public NewickFile(String inFile, String type) throws IOException + public NewickFile(String inFile, DataSourceType protocol) + throws IOException { - super(inFile, type); + super(inFile, protocol); } public NewickFile(FileParse source) throws IOException @@ -217,13 +220,10 @@ public class NewickFile extends FileParse private String ErrorStringrange(String Error, String Er, int r, int p, String s) { - return ((Error == null) ? "" : Error) - + Er - + " at position " - + p - + " ( " + return ((Error == null) ? "" : Error) + Er + " at position " + p + " ( " + s.substring(((p - r) < 0) ? 0 : (p - r), - ((p + r) > s.length()) ? s.length() : (p + r)) + " )\n"; + ((p + r) > s.length()) ? s.length() : (p + r)) + + " )\n"; } // @tree annotations @@ -294,7 +294,7 @@ public class NewickFile extends FileParse boolean ascending = false; // flag indicating that we are leaving the // current node - com.stevesoft.pat.Regex majorsyms = new com.stevesoft.pat.Regex( + Regex majorsyms = new Regex( "[(\\['),;]"); int nextcp = 0; @@ -356,16 +356,16 @@ public class NewickFile extends FileParse // Deal with quoted fields case '\'': - com.stevesoft.pat.Regex qnodename = new com.stevesoft.pat.Regex( + Regex qnodename = new Regex( "'([^']|'')+'"); if (qnodename.searchFrom(nf, fcp)) { int nl = qnodename.stringMatched().length(); - nodename = new String(qnodename.stringMatched().substring(1, - nl - 1)); + nodename = new String( + qnodename.stringMatched().substring(1, nl - 1)); // unpack any escaped colons - com.stevesoft.pat.Regex xpandquotes = com.stevesoft.pat.Regex + Regex xpandquotes = Regex .perlCode("s/''/'/"); String widernodename = xpandquotes.replaceAll(nodename); nodename = widernodename; @@ -386,8 +386,8 @@ public class NewickFile extends FileParse { if (d != -1) { - Error = ErrorStringrange(Error, "Wayward semicolon (depth=" + d - + ")", 7, fcp, nf); + Error = ErrorStringrange(Error, + "Wayward semicolon (depth=" + d + ")", 7, fcp, nf); } // cp advanced at the end of default } @@ -400,7 +400,8 @@ public class NewickFile extends FileParse * '"+nf.substring(cp,fcp)+"'"); } */ // verify termination. - com.stevesoft.pat.Regex comment = new com.stevesoft.pat.Regex("]"); + Regex comment = new Regex( + "]"); if (comment.searchFrom(nf, fcp)) { // Skip the comment field @@ -433,15 +434,14 @@ public class NewickFile extends FileParse + fstring.substring(cend + 1); } - com.stevesoft.pat.Regex uqnodename = new com.stevesoft.pat.Regex( + Regex uqnodename = new Regex( "\\b([^' :;\\](),]+)"); - com.stevesoft.pat.Regex nbootstrap = new com.stevesoft.pat.Regex( + Regex nbootstrap = new Regex( "\\s*([0-9+]+)\\s*:"); - com.stevesoft.pat.Regex ndist = new com.stevesoft.pat.Regex( + Regex ndist = new Regex( ":([-0-9Ee.+]+)"); - if (!parsednodename - && uqnodename.search(fstring) + if (!parsednodename && uqnodename.search(fstring) && ((uqnodename.matchedFrom(1) == 0) || (fstring .charAt(uqnodename.matchedFrom(1) - 1) != ':'))) // JBPNote // HACK! @@ -468,15 +468,14 @@ public class NewickFile extends FileParse if (nbootstrap.search(fstring)) { - if (nbootstrap.stringMatched(1).equals( - uqnodename.stringMatched(1))) + if (nbootstrap.stringMatched(1) + .equals(uqnodename.stringMatched(1))) { nodename = null; // no nodename here. } - if (nodename == null - || nodename.length() == 0 - || nbootstrap.matchedFrom(1) > (uqnodename.matchedFrom(1) + uqnodename - .stringMatched().length())) + if (nodename == null || nodename.length() == 0 + || nbootstrap.matchedFrom(1) > (uqnodename.matchedFrom(1) + + uqnodename.stringMatched().length())) { try { @@ -485,9 +484,8 @@ public class NewickFile extends FileParse HasBootstrap = true; } catch (Exception e) { - Error = ErrorStringrange(Error, - "Can't parse bootstrap value", 4, - ncp + nbootstrap.matchedFrom(), nf); + Error = ErrorStringrange(Error, "Can't parse bootstrap value", + 4, ncp + nbootstrap.matchedFrom(), nf); } } } @@ -564,8 +562,7 @@ public class NewickFile extends FileParse if ((d > -1) && (c == null)) { - Error = ErrorStringrange( - Error, + Error = ErrorStringrange(Error, "File broke algorithm: Lost place in tree (is there an extra ')' ?)", 7, fcp, nf); } @@ -615,14 +612,15 @@ public class NewickFile extends FileParse if (Error != null) { - throw (new IOException(MessageManager.formatMessage( - "exception.newfile", new String[] { Error.toString() }))); + throw (new IOException( + MessageManager.formatMessage("exception.newfile", new String[] + { Error.toString() }))); } if (root == null) { - throw (new IOException(MessageManager.formatMessage( - "exception.newfile", new String[] { MessageManager - .getString("label.no_tree_read_in") }))); + throw (new IOException( + MessageManager.formatMessage("exception.newfile", new String[] + { MessageManager.getString("label.no_tree_read_in") }))); } // THe next line is failing for topali trees - not sure why yet. if // (root.right()!=null && root.isDummy()) @@ -674,8 +672,8 @@ public class NewickFile extends FileParse // more codes here. } catch (Exception e) { - System.err.println("Couldn't parse code '" + code + "' = '" - + value + "'"); + System.err.println( + "Couldn't parse code '" + code + "' = '" + value + "'"); e.printStackTrace(System.err); } } @@ -846,10 +844,10 @@ public class NewickFile extends FileParse private String printNodeField(SequenceNode c) { return ((c.getName() == null) ? "" : nodeName(c.getName())) - + ((HasBootstrap) ? ((c.getBootstrap() > -1) ? ((c.getName() != null ? " " - : "") + c.getBootstrap()) - : "") - : "") + ((HasDistances) ? (":" + c.dist) : ""); + + ((HasBootstrap) ? ((c.getBootstrap() > -1) + ? ((c.getName() != null ? " " : "") + c.getBootstrap()) + : "") : "") + + ((HasDistances) ? (":" + c.dist) : ""); } /** @@ -862,12 +860,16 @@ public class NewickFile extends FileParse */ private String printRootField(SequenceNode root) { - return (printRootInfo) ? (((root.getName() == null) ? "" - : nodeName(root.getName())) - + ((HasBootstrap) ? ((root.getBootstrap() > -1) ? ((root - .getName() != null ? " " : "") + +root.getBootstrap()) - : "") : "") + ((RootHasDistance) ? (":" + root.dist) - : "")) : ""; + return (printRootInfo) + ? (((root.getName() == null) ? "" : nodeName(root.getName())) + + ((HasBootstrap) + ? ((root.getBootstrap() > -1) + ? ((root.getName() != null ? " " : "") + + +root.getBootstrap()) + : "") + : "") + + ((RootHasDistance) ? (":" + root.dist) : "")) + : ""; } // Non recursive call deals with root node properties @@ -947,8 +949,8 @@ public class NewickFile extends FileParse { if (args == null || args.length != 1) { - System.err - .println("Takes one argument - file name of a newick tree file."); + System.err.println( + "Takes one argument - file name of a newick tree file."); System.exit(0); } @@ -966,11 +968,11 @@ public class NewickFile extends FileParse treefile.close(); System.out.println("Read file :\n"); - NewickFile trf = new NewickFile(args[0], "File"); + NewickFile trf = new NewickFile(args[0], DataSourceType.FILE); trf.parse(); System.out.println("Original file :\n"); - com.stevesoft.pat.Regex nonl = new com.stevesoft.pat.Regex("\n+", ""); + Regex nonl = new Regex("\n+", ""); System.out.println(nonl.replaceAll(newickfile.toString()) + "\n"); System.out.println("Parsed file.\n");