X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FNewickFile.java;h=f3eaa45e2882fd08445dbbc85fbb8848bc46de6d;hb=4f77328104498504339216829abf5ea87e2791ec;hp=7596db4b5d145ccbd200596cea5567a37fb7fa6b;hpb=2b8c0785318a3528e1876e8e2dd48b7d831eae69;p=jalview.git diff --git a/src/jalview/io/NewickFile.java b/src/jalview/io/NewickFile.java index 7596db4..f3eaa45 100755 --- a/src/jalview/io/NewickFile.java +++ b/src/jalview/io/NewickFile.java @@ -28,7 +28,6 @@ package jalview.io; import jalview.datamodel.SequenceNode; import jalview.util.MessageManager; -import jalview.util.Platform; import java.io.BufferedReader; import java.io.File; @@ -38,8 +37,6 @@ import java.util.StringTokenizer; import com.stevesoft.pat.Regex; -// TODO This class does not conform to Java standards for field name capitalization. - /** * 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 @@ -79,7 +76,7 @@ import com.stevesoft.pat.Regex; */ public class NewickFile extends FileParse { - private SequenceNode root; + SequenceNode root; private boolean HasBootstrap = false; @@ -88,90 +85,21 @@ public class NewickFile extends FileParse private boolean RootHasDistance = false; // File IO Flags - private boolean ReplaceUnderscores = false; - - private boolean printRootInfo = true; - - private static final int REGEX_PERL_NODE_REQUIRE_QUOTE = 0; - - private static final int REGEX_PERL_NODE_ESCAPE_QUOTE = 1; - - private static final int REGEX_PERL_NODE_UNQUOTED_WHITESPACE = 2; - - private static final int REGEX_MAJOR_SYMS = 3; - - private static final int REGEX_QNODE_NAME = 4; - - private static final int REGEX_COMMENT = 5; - - private static final int REGEX_UQNODE_NAME = 6; + boolean ReplaceUnderscores = false; - private static final int REGEX_NBOOTSTRAP = 7; - - private static final int REGEX_NDIST = 8; - - private static final int REGEX_NO_LINES = 9; - - private static final int REGEX_PERL_EXPAND_QUOTES = 10; - - private static final int REGEX_MAX = 11; - - private static final Regex[] REGEX = new Regex[REGEX_MAX]; - - private static Regex getRegex(int id) - { - if (REGEX[id] == null) - { - String code = null; - String code2 = null; - String codePerl = null; - switch (id) - { - case REGEX_PERL_NODE_REQUIRE_QUOTE: - codePerl = "m/[\\[,:'()]/"; - break; - case REGEX_PERL_NODE_ESCAPE_QUOTE: - codePerl = "s/'/''/"; - break; - case REGEX_PERL_NODE_UNQUOTED_WHITESPACE: - codePerl = "s/\\/w/_/"; - break; - case REGEX_PERL_EXPAND_QUOTES: - codePerl = "s/''/'/"; - break; - case REGEX_MAJOR_SYMS: - code = "[(\\['),;]"; - break; - case REGEX_QNODE_NAME: - code = "'([^']|'')+'"; - break; - case REGEX_COMMENT: - code = "]"; - break; - case REGEX_UQNODE_NAME: - code = "\\b([^' :;\\](),]+)"; - break; - case REGEX_NBOOTSTRAP: - code = "\\s*([0-9+]+)\\s*:"; - break; - case REGEX_NDIST: - code = ":([-0-9Ee.+]+)"; - break; - case REGEX_NO_LINES: - code = "\n+"; - code2 = ""; - break; - default: - return null; - } - return codePerl == null ? Platform.newRegex(code, code2) - : Platform.newRegexPerl(codePerl); - } - return REGEX[id]; - } + boolean printRootInfo = true; + private Regex[] NodeSafeName = new Regex[] { + new Regex().perlCode("m/[\\[,:'()]/"), // test for + // requiring + // quotes + new Regex().perlCode("s/'/''/"), // escaping quote + // characters + new Regex().perlCode("s/\\/w/_/") // unqoted whitespace + // transformation + }; - private char quoteChar = '\''; + char QuoteChar = '\''; /** * Creates a new NewickFile object. @@ -329,7 +257,6 @@ public class NewickFile extends FileParse */ public void parse() throws IOException { - Platform.ensureRegex(); String nf; { // fill nf with complete tree file @@ -367,7 +294,8 @@ public class NewickFile extends FileParse boolean ascending = false; // flag indicating that we are leaving the // current node - Regex majorsyms = getRegex(REGEX_MAJOR_SYMS); // "[(\\['),;]" + Regex majorsyms = new Regex( + "[(\\['),;]"); int nextcp = 0; int ncp = cp; @@ -426,7 +354,8 @@ public class NewickFile extends FileParse // Deal with quoted fields case '\'': - Regex qnodename = getRegex(REGEX_QNODE_NAME);// "'([^']|'')+'"); + Regex qnodename = new Regex( + "'([^']|'')+'"); if (qnodename.searchFrom(nf, fcp)) { @@ -434,7 +363,8 @@ public class NewickFile extends FileParse nodename = new String( qnodename.stringMatched().substring(1, nl - 1)); // unpack any escaped colons - Regex xpandquotes = getRegex(REGEX_PERL_EXPAND_QUOTES); + Regex xpandquotes = Regex + .perlCode("s/''/'/"); String widernodename = xpandquotes.replaceAll(nodename); nodename = widernodename; // jump to after end of quoted nodename @@ -468,7 +398,8 @@ public class NewickFile extends FileParse * '"+nf.substring(cp,fcp)+"'"); } */ // verify termination. - Regex comment = getRegex(REGEX_COMMENT); // "]" + Regex comment = new Regex( + "]"); if (comment.searchFrom(nf, fcp)) { // Skip the comment field @@ -499,9 +430,12 @@ public class NewickFile extends FileParse + fstring.substring(cend + 1); } - Regex uqnodename = getRegex(REGEX_UQNODE_NAME);// "\\b([^' :;\\](),]+)" - Regex nbootstrap = getRegex(REGEX_NBOOTSTRAP);// "\\s*([0-9+]+)\\s*:"); - Regex ndist = getRegex(REGEX_NDIST);// ":([-0-9Ee.+]+)"); + Regex uqnodename = new Regex( + "\\b([^' :;\\](),]+)"); + Regex nbootstrap = new Regex( + "\\s*([0-9+]+)\\s*:"); + Regex ndist = new Regex( + ":([-0-9Ee.+]+)"); if (!parsednodename && uqnodename.search(fstring) && ((uqnodename.matchedFrom(1) == 0) || (fstring @@ -541,7 +475,7 @@ public class NewickFile extends FileParse { try { - bootstrap = (new Integer(nbootstrap.stringMatched(1))) + bootstrap = (Integer.valueOf(nbootstrap.stringMatched(1))) .intValue(); HasBootstrap = true; } catch (Exception e) @@ -558,7 +492,7 @@ public class NewickFile extends FileParse { try { - distance = (new Float(ndist.stringMatched(1))).floatValue(); + distance = (Float.valueOf(ndist.stringMatched(1))).floatValue(); HasDistances = true; nodehasdistance = true; } catch (Exception e) @@ -725,7 +659,7 @@ public class NewickFile extends FileParse if (code.toLowerCase().equals("b")) { int v = -1; - Float iv = new Float(value); + Float iv = Float.valueOf(value); v = iv.intValue(); // jalview only does integer bootstraps // currently c.setBootstrap(v); @@ -856,7 +790,7 @@ public class NewickFile extends FileParse */ char getQuoteChar() { - return quoteChar; + return QuoteChar; } /** @@ -869,8 +803,8 @@ public class NewickFile extends FileParse */ char setQuoteChar(char c) { - char old = quoteChar; - quoteChar = c; + char old = QuoteChar; + QuoteChar = c; return old; } @@ -885,15 +819,13 @@ public class NewickFile extends FileParse */ private String nodeName(String name) { - if (getRegex(REGEX_PERL_NODE_REQUIRE_QUOTE).search(name)) + if (NodeSafeName[0].search(name)) { - return quoteChar - + getRegex(REGEX_PERL_NODE_ESCAPE_QUOTE).replaceAll(name) - + quoteChar; + return QuoteChar + NodeSafeName[1].replaceAll(name) + QuoteChar; } else { - return getRegex(REGEX_PERL_NODE_UNQUOTED_WHITESPACE).replaceAll(name); + return NodeSafeName[2].replaceAll(name); } } @@ -1040,7 +972,7 @@ public class NewickFile extends FileParse trf.parse(); System.out.println("Original file :\n"); - Regex nonl = getRegex(REGEX_NO_LINES);// "\n+", ""); + Regex nonl = new Regex("\n+", ""); System.out.println(nonl.replaceAll(newickfile.toString()) + "\n"); System.out.println("Parsed file.\n");