X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=src%2Fjalview%2Fio%2FFeaturesFile.java;h=2ac0e13458f32eb1076948cc6a5332bee5191504;hb=3f72d101fbeb83a7526a3c4f8f62cfe8e8a0189d;hp=64bb539bfafe961aefe5c50deaf77e78ef58a8fe;hpb=e601d78bc7762386f570e346a803684c43a66ff1;p=jalview.git diff --git a/src/jalview/io/FeaturesFile.java b/src/jalview/io/FeaturesFile.java index 64bb539..2ac0e13 100755 --- a/src/jalview/io/FeaturesFile.java +++ b/src/jalview/io/FeaturesFile.java @@ -1,6 +1,6 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.6) - * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7) + * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle * * This file is part of Jalview. * @@ -20,6 +20,7 @@ package jalview.io; import java.io.*; import java.util.*; +import jalview.analysis.SequenceIdMatcher; import jalview.datamodel.*; import jalview.schemes.*; import jalview.util.Format; @@ -70,28 +71,60 @@ public class FeaturesFile extends AlignFile } /** - * The Application can render HTML, but the applet will remove HTML tags and - * replace links with %LINK% Both need to read links in HTML however - * - * @throws IOException - * DOCUMENT ME! + * Parse GFF or sequence features file using case-independent matching, discarding URLs + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param removeHTML - process html strings into plain text + * @return true if features were added */ public boolean parse(AlignmentI align, Hashtable colours, boolean removeHTML) { - return parse(align, colours, null, removeHTML); + return parse(align, colours, null, removeHTML, false); } /** - * The Application can render HTML, but the applet will remove HTML tags and - * replace links with %LINK% Both need to read links in HTML however - * - * @throws IOException - * DOCUMENT ME! + * Parse GFF or sequence features file optionally using case-independent matching, discarding URLs + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param removeHTML - process html strings into plain text + * @param relaxedIdmatching - when true, ID matches to compound sequence IDs are allowed + * @return true if features were added + */ + public boolean parse(AlignmentI align, + Hashtable colours, boolean removeHTML, boolean relaxedIdMatching) + { + return parse(align, colours, null, removeHTML, relaxedIdMatching); + } + + /** + * Parse GFF or sequence features file optionally using case-independent matching + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param featureLink - hashtable to store associated URLs + * @param removeHTML - process html strings into plain text + * @return true if features were added */ public boolean parse(AlignmentI align, Hashtable colours, Hashtable featureLink, boolean removeHTML) { + return parse(align, colours, featureLink, removeHTML, false); + } + + /** + /** + * Parse GFF or sequence features file + * @param align - alignment/dataset containing sequences that are to be annotated + * @param colours - hashtable to store feature colour definitions + * @param featureLink - hashtable to store associated URLs + * @param removeHTML - process html strings into plain text + * @param relaxedIdmatching - when true, ID matches to compound sequence IDs are allowed + * @return true if features were added + */ + public boolean parse(AlignmentI align, + Hashtable colours, Hashtable featureLink, boolean removeHTML, boolean relaxedIdmatching) + { + String line = null; try { @@ -369,7 +402,7 @@ public class FeaturesFile extends AlignFile // Still possible this is an old Jalview file, // which does not have type colours at the beginning seqId = token = st.nextToken(); - seq = align.findName(seqId, true); + seq = findName(align, seqId, relaxedIdmatching); if (seq != null) { desc = st.nextToken(); @@ -478,7 +511,7 @@ public class FeaturesFile extends AlignFile if (!token.equals("ID_NOT_SPECIFIED")) { - seq = align.findName(seqId = token, true); + seq = findName(align, seqId = token, relaxedIdmatching); st.nextToken(); } else @@ -548,88 +581,64 @@ public class FeaturesFile extends AlignFile GFFFile = false; } } + resetMatcher(); } catch (Exception ex) { System.out.println(line); System.out.println("Error parsing feature file: " + ex + "\n" + line); ex.printStackTrace(System.err); + resetMatcher(); return false; } return true; } - public void parseDescriptionHTML(SequenceFeature sf, boolean removeHTML) + private AlignmentI lastmatchedAl = null; + + private SequenceIdMatcher matcher = null; + + /** + * clear any temporary handles used to speed up ID matching + */ + private void resetMatcher() { - if (sf.getDescription() == null) + lastmatchedAl = null; + matcher = null; + } + + private SequenceI findName(AlignmentI align, String seqId, + boolean relaxedIdMatching) + { + SequenceI match = null; + if (relaxedIdMatching) { - return; + if (lastmatchedAl != align) + { + matcher = new SequenceIdMatcher( + (lastmatchedAl = align).getSequencesArray()); + } + match = matcher.findIdMatch(seqId); } - - if (removeHTML - && sf.getDescription().toUpperCase().indexOf("") == -1) + else { - removeHTML = false; + match = align.findName(seqId, true); } + return match; + } - StringBuffer sb = new StringBuffer(); - StringTokenizer st = new StringTokenizer(sf.getDescription(), "<"); - String token, link; - int startTag; - String tag = null; - while (st.hasMoreElements()) + public void parseDescriptionHTML(SequenceFeature sf, boolean removeHTML) + { + if (sf.getDescription() == null) { - token = st.nextToken("&>"); - if (token.equalsIgnoreCase("html") || token.startsWith("/")) - { - continue; - } - - tag = null; - startTag = token.indexOf("<"); - - if (startTag > -1) - { - tag = token.substring(startTag + 1); - token = token.substring(0, startTag); - } - - if (tag != null && tag.toUpperCase().startsWith("A HREF=")) - { - if (token.length() > 0) - { - sb.append(token); - } - link = tag.substring(tag.indexOf("\"") + 1, tag.length() - 1); - String label = st.nextToken("<>"); - sf.addLink(label + "|" + link); - sb.append(label + "%LINK%"); - } - else if (tag != null && tag.equalsIgnoreCase("br")) - { - sb.append(newline); - } - else if (token.startsWith("lt;")) - { - sb.append("<" + token.substring(3)); - } - else if (token.startsWith("gt;")) - { - sb.append(">" + token.substring(3)); - } - else if (token.startsWith("amp;")) - { - sb.append("&" + token.substring(4)); - } - else - { - sb.append(token); - } + return; } + jalview.util.ParseHtmlBodyAndLinks parsed = new jalview.util.ParseHtmlBodyAndLinks(sf.getDescription(), removeHTML, newline); - if (removeHTML) + sf.description = (removeHTML) ? parsed.getNonHtmlContent() : sf.description; + for (String link:parsed.getLinks()) { - sf.description = sb.toString(); + sf.addLink(link); } } @@ -929,19 +938,18 @@ public class FeaturesFile extends AlignFile out.append(source); out.append("\t"); out.append(next[j].type); - out.append( "\t"); - out.append( next[j].begin ); out.append("\t"); - out.append( - next[j].end); - out.append( "\t"); - out.append( next[j].score); - out.append( "\t"); + out.append(next[j].begin); + out.append("\t"); + out.append(next[j].end); + out.append("\t"); + out.append(next[j].score); + out.append("\t"); if (next[j].getValue("STRAND") != null) { out.append(next[j].getValue("STRAND")); - out.append( "\t"); + out.append("\t"); } else { @@ -956,7 +964,8 @@ public class FeaturesFile extends AlignFile { out.append("."); } - // TODO: verify/check GFF - should there be a /t here before attribute output ? + // TODO: verify/check GFF - should there be a /t here before attribute + // output ? if (next[j].getValue("ATTRIBUTES") != null) { @@ -989,4 +998,5 @@ public class FeaturesFile extends AlignFile { return "USE printGFFFormat() or printJalviewFormat()"; } + }