X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FFeaturesFile.java;h=2ac0e13458f32eb1076948cc6a5332bee5191504;hb=797df64fa2a0a30773d0f48f5494d4155e5a8be3;hp=3c8ad21b2978de6d84dd414bfc3375bc520771ad;hpb=336b270e68fe281a9a881f751fe850e8a92e05c9;p=jalview.git diff --git a/src/jalview/io/FeaturesFile.java b/src/jalview/io/FeaturesFile.java index 3c8ad21..2ac0e13 100755 --- a/src/jalview/io/FeaturesFile.java +++ b/src/jalview/io/FeaturesFile.java @@ -1,41 +1,48 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer - * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA + * 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. + * + * Jalview is free software: you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. + * + * Jalview is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR + * PURPOSE. See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along with Jalview. If not, see . */ package jalview.io; import java.io.*; import java.util.*; +import jalview.analysis.SequenceIdMatcher; import jalview.datamodel.*; import jalview.schemes.*; +import jalview.util.Format; /** - * Parse and create Jalview Features files - * Detects GFF format features files and parses. - * Does not implement standard print() - call specific printFeatures or printGFF. - * Uses AlignmentI.findSequence(String id) to find the sequence object for the features annotation - this normally works on an exact match. + * Parse and create Jalview Features files Detects GFF format features files and + * parses. Does not implement standard print() - call specific printFeatures or + * printGFF. Uses AlignmentI.findSequence(String id) to find the sequence object + * for the features annotation - this normally works on an exact match. + * * @author AMW * @version $Revision$ */ -public class FeaturesFile - extends AlignFile +public class FeaturesFile extends AlignFile { /** + * work around for GFF interpretation bug where source string becomes + * description rather than a group + */ + private boolean doGffSource = true; + + /** * Creates a new FeaturesFile object. */ public FeaturesFile() @@ -44,44 +51,80 @@ public class FeaturesFile /** * Creates a new FeaturesFile object. - * - * @param inFile DOCUMENT ME! - * @param type DOCUMENT ME! - * - * @throws IOException DOCUMENT ME! + * + * @param inFile + * DOCUMENT ME! + * @param type + * DOCUMENT ME! + * + * @throws IOException + * DOCUMENT ME! */ - public FeaturesFile(String inFile, String type) - throws IOException + public FeaturesFile(String inFile, String type) throws IOException { super(inFile, type); } + public FeaturesFile(FileParse source) throws IOException + { + super(source); + } + /** - * 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) + public boolean parse(AlignmentI align, Hashtable colours, + boolean removeHTML) + { + return parse(align, colours, null, removeHTML, false); + } + + /** + * 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, null, removeHTML); + return parse(align, colours, featureLink, 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 + * @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) + Hashtable colours, Hashtable featureLink, boolean removeHTML, boolean relaxedIdmatching) { + String line = null; try { @@ -94,10 +137,11 @@ public class FeaturesFile SequenceFeature sf; String featureGroup = null, groupLink = null; Hashtable typeLink = new Hashtable(); - + /** + * when true, assume GFF style features rather than Jalview style. + */ boolean GFFFile = true; - - while ( (line = nextLine()) != null) + while ((line = nextLine()) != null) { if (line.startsWith("#")) { @@ -105,6 +149,15 @@ public class FeaturesFile } st = new StringTokenizer(line, "\t"); + if (st.countTokens() == 1) + { + if (line.trim().equalsIgnoreCase("GFF")) + { + // Start parsing file as if it might be GFF again. + GFFFile = true; + continue; + } + } if (st.countTokens() > 1 && st.countTokens() < 4) { GFFFile = false; @@ -120,16 +173,213 @@ public class FeaturesFile } else if (type.equalsIgnoreCase("endgroup")) { - //We should check whether this is the current group, - //but at present theres no way of showing more than 1 group + // We should check whether this is the current group, + // but at present theres no way of showing more than 1 group st.nextToken(); featureGroup = null; groupLink = null; } else { - UserColourScheme ucs = new UserColourScheme(st.nextToken()); - colours.put(type, ucs.findColour('A')); + Object colour = null; + String colscheme = st.nextToken(); + if (colscheme.indexOf("|") > -1 + || colscheme.trim().equalsIgnoreCase("label")) + { + // Parse '|' separated graduated colourscheme fields: + // [label|][mincolour|maxcolour|[absolute|]minvalue|maxvalue|thresholdtype|thresholdvalue] + // can either provide 'label' only, first is optional, next two + // colors are required (but may be + // left blank), next is optional, nxt two min/max are required. + // first is either 'label' + // first/second and third are both hexadecimal or word equivalent + // colour. + // next two are values parsed as floats. + // fifth is either 'above','below', or 'none'. + // sixth is a float value and only required when fifth is either + // 'above' or 'below'. + StringTokenizer gcol = new StringTokenizer(colscheme, "|", + true); + // set defaults + int threshtype = AnnotationColourGradient.NO_THRESHOLD; + float min = Float.MIN_VALUE, max = Float.MAX_VALUE, threshval = Float.NaN; + boolean labelCol = false; + // Parse spec line + String mincol = gcol.nextToken(); + if (mincol == "|") + { + System.err + .println("Expected either 'label' or a colour specification in the line: " + + line); + continue; + } + String maxcol = null; + if (mincol.toLowerCase().indexOf("label") == 0) + { + labelCol = true; + mincol = (gcol.hasMoreTokens() ? gcol.nextToken() : null); // skip + // '|' + mincol = (gcol.hasMoreTokens() ? gcol.nextToken() : null); + } + String abso = null, minval, maxval; + if (mincol != null) + { + // at least four more tokens + if (mincol.equals("|")) + { + mincol = ""; + } + else + { + gcol.nextToken(); // skip next '|' + } + // continue parsing rest of line + maxcol = gcol.nextToken(); + if (maxcol.equals("|")) + { + maxcol = ""; + } + else + { + gcol.nextToken(); // skip next '|' + } + abso = gcol.nextToken(); + gcol.nextToken(); // skip next '|' + if (abso.toLowerCase().indexOf("abso") != 0) + { + minval = abso; + abso = null; + } + else + { + minval = gcol.nextToken(); + gcol.nextToken(); // skip next '|' + } + maxval = gcol.nextToken(); + if (gcol.hasMoreTokens()) + { + gcol.nextToken(); // skip next '|' + } + try + { + if (minval.length() > 0) + { + min = new Float(minval).floatValue(); + } + } catch (Exception e) + { + System.err + .println("Couldn't parse the minimum value for graduated colour for type (" + + colscheme + + ") - did you misspell 'auto' for the optional automatic colour switch ?"); + e.printStackTrace(); + } + try + { + if (maxval.length() > 0) + { + max = new Float(maxval).floatValue(); + } + } catch (Exception e) + { + System.err + .println("Couldn't parse the maximum value for graduated colour for type (" + + colscheme + ")"); + e.printStackTrace(); + } + } + else + { + // add in some dummy min/max colours for the label-only + // colourscheme. + mincol = "FFFFFF"; + maxcol = "000000"; + } + try + { + colour = new jalview.schemes.GraduatedColor( + new UserColourScheme(mincol).findColour('A'), + new UserColourScheme(maxcol).findColour('A'), min, + max); + } catch (Exception e) + { + System.err + .println("Couldn't parse the graduated colour scheme (" + + colscheme + ")"); + e.printStackTrace(); + } + if (colour != null) + { + ((jalview.schemes.GraduatedColor) colour) + .setColourByLabel(labelCol); + ((jalview.schemes.GraduatedColor) colour) + .setAutoScaled(abso == null); + // add in any additional parameters + String ttype = null, tval = null; + if (gcol.hasMoreTokens()) + { + // threshold type and possibly a threshold value + ttype = gcol.nextToken(); + if (ttype.toLowerCase().startsWith("below")) + { + ((jalview.schemes.GraduatedColor) colour) + .setThreshType(AnnotationColourGradient.BELOW_THRESHOLD); + } + else if (ttype.toLowerCase().startsWith("above")) + { + ((jalview.schemes.GraduatedColor) colour) + .setThreshType(AnnotationColourGradient.ABOVE_THRESHOLD); + } + else + { + ((jalview.schemes.GraduatedColor) colour) + .setThreshType(AnnotationColourGradient.NO_THRESHOLD); + if (!ttype.toLowerCase().startsWith("no")) + { + System.err + .println("Ignoring unrecognised threshold type : " + + ttype); + } + } + } + if (((GraduatedColor) colour).getThreshType() != AnnotationColourGradient.NO_THRESHOLD) + { + try + { + gcol.nextToken(); + tval = gcol.nextToken(); + ((jalview.schemes.GraduatedColor) colour) + .setThresh(new Float(tval).floatValue()); + } catch (Exception e) + { + System.err + .println("Couldn't parse threshold value as a float: (" + + tval + ")"); + e.printStackTrace(); + } + } + // parse the thresh-is-min token ? + if (gcol.hasMoreTokens()) + { + System.err + .println("Ignoring additional tokens in parameters in graduated colour specification\n"); + while (gcol.hasMoreTokens()) + { + System.err.println("|" + gcol.nextToken()); + } + System.err.println("\n"); + } + } + } + else + { + UserColourScheme ucs = new UserColourScheme(colscheme); + colour = ucs.findColour('A'); + } + if (colour != null) + { + colours.put(type, colour); + } if (st.hasMoreElements()) { String link = st.nextToken(); @@ -140,11 +390,10 @@ public class FeaturesFile } featureLink.put(type, link); } - } continue; } - + String seqId = ""; while (st.hasMoreElements()) { @@ -152,43 +401,72 @@ public class FeaturesFile { // Still possible this is an old Jalview file, // which does not have type colours at the beginning - token = st.nextToken(); - seq = align.findName(token); + seqId = token = st.nextToken(); + seq = findName(align, seqId, relaxedIdmatching); if (seq != null) { desc = st.nextToken(); + String group = null; + if (doGffSource && desc.indexOf(' ') == -1) + { + // could also be a source term rather than description line + group = new String(desc); + } type = st.nextToken(); - try { - start = Integer.parseInt(st.nextToken()); + try + { + String stt = st.nextToken(); + if (stt.length() == 0 || stt.equals("-")) + { + start = 0; + } + else + { + start = Integer.parseInt(stt); + } } catch (NumberFormatException ex) { - start=0; + start = 0; } - try { - end = Integer.parseInt(st.nextToken()); + try + { + String stt = st.nextToken(); + if (stt.length() == 0 || stt.equals("-")) + { + end = 0; + } + else + { + end = Integer.parseInt(stt); + } + } catch (NumberFormatException ex) + { + end = 0; } - catch (NumberFormatException ex) + // TODO: decide if non positional feature assertion for input data + // where end==0 is generally valid + if (end == 0) { - end=-1; - } + // treat as non-positional feature, regardless. + start = 0; + } try { score = new Float(st.nextToken()).floatValue(); - } - catch (NumberFormatException ex) + } catch (NumberFormatException ex) { score = 0; } - sf = new SequenceFeature(type, desc, start, end, score, null); + sf = new SequenceFeature(type, desc, start, end, score, group); try { sf.setValue("STRAND", st.nextToken()); sf.setValue("FRAME", st.nextToken()); + } catch (Exception ex) + { } - catch (Exception ex) - {} if (st.hasMoreTokens()) { @@ -197,11 +475,17 @@ public class FeaturesFile { attributes.append("\t" + st.nextElement()); } + // TODO validate and split GFF2 attributes field ? parse out + // ([A-Za-z][A-Za-z0-9_]*) ; and add as + // sf.setValue(attrib, val); sf.setValue("ATTRIBUTES", attributes.toString()); } seq.addSequenceFeature(sf); - + while ((seq = align.findName(seq, seqId, true)) != null) + { + seq.addSequenceFeature(new SequenceFeature(sf)); + } break; } } @@ -216,26 +500,28 @@ public class FeaturesFile } if (!st.hasMoreTokens()) { - System.err.println("DEBUG: Run out of tokens when trying to identify the destination for the feature.. giving up."); - // in all probability, this isn't a file we understand, so bail quietly. + System.err + .println("DEBUG: Run out of tokens when trying to identify the destination for the feature.. giving up."); + // in all probability, this isn't a file we understand, so bail + // quietly. return false; } - + token = st.nextToken(); - + if (!token.equals("ID_NOT_SPECIFIED")) { - seq = align.findName(token); + seq = findName(align, seqId = token, relaxedIdmatching); st.nextToken(); } else { + seqId = null; try { index = Integer.parseInt(st.nextToken()); seq = align.getSequenceAt(index); - } - catch (NumberFormatException ex) + } catch (NumberFormatException ex) { seq = null; } @@ -258,11 +544,19 @@ public class FeaturesFile UserColourScheme ucs = new UserColourScheme(type); colours.put(type, ucs.findColour('A')); } - sf = new SequenceFeature(type, desc, "", start, end, featureGroup); - - seq.addSequenceFeature(sf); - + if (st.hasMoreTokens()) + { + try + { + score = new Float(st.nextToken()).floatValue(); + // update colourgradient bounds if allowed to + } catch (NumberFormatException ex) + { + score = 0; + } + sf.setScore(score); + } if (groupLink != null && removeHTML) { sf.addLink(groupLink); @@ -276,133 +570,181 @@ public class FeaturesFile parseDescriptionHTML(sf, removeHTML); - //If we got here, its not a GFFFile + seq.addSequenceFeature(sf); + + while (seqId != null + && (seq = align.findName(seq, seqId, false)) != null) + { + seq.addSequenceFeature(new SequenceFeature(sf)); + } + // If we got here, its not a GFFFile GFFFile = false; } } - } - catch (Exception ex) + 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("\n"); - } - 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); } } /** - * DOCUMENT ME! - * - * @param s DOCUMENT ME! - * @param len DOCUMENT ME! - * @param gaps DOCUMENT ME! - * @param displayId DOCUMENT ME! - * - * @return DOCUMENT ME! + * generate a features file for seqs includes non-pos features by default. + * + * @param seqs + * source of sequence features + * @param visible + * hash of feature types and colours + * @return features file contents */ - public String printJalviewFormat(SequenceI[] seqs, - Hashtable visible) + public String printJalviewFormat(SequenceI[] seqs, Hashtable visible) + { + return printJalviewFormat(seqs, visible, true, true); + } + + /** + * generate a features file for seqs with colours from visible (if any) + * + * @param seqs + * source of features + * @param visible + * hash of Colours for each feature type + * @param visOnly + * when true only feature types in 'visible' will be output + * @param nonpos + * indicates if non-positional features should be output (regardless + * of group or type) + * @return features file contents + */ + public String printJalviewFormat(SequenceI[] seqs, Hashtable visible, + boolean visOnly, boolean nonpos) { StringBuffer out = new StringBuffer(); SequenceFeature[] next; - - if (visible == null || visible.size() < 1) + boolean featuresGen = false; + if (visOnly && !nonpos && (visible == null || visible.size() < 1)) { + // no point continuing. return "No Features Visible"; } - Enumeration en = visible.keys(); - String type; - int color; - while (en.hasMoreElements()) + if (visible != null && visOnly) { - type = en.nextElement().toString(); - color = Integer.parseInt(visible.get(type).toString()); - out.append(type + "\t" - + jalview.util.Format.getHexString( - new java.awt.Color(color)) - + "\n"); - } + // write feature colours only if we're given them and we are generating + // viewed features + // TODO: decide if feature links should also be written here ? + Enumeration en = visible.keys(); + String type, color; + while (en.hasMoreElements()) + { + type = en.nextElement().toString(); - //Work out which groups are both present and visible + if (visible.get(type) instanceof GraduatedColor) + { + GraduatedColor gc = (GraduatedColor) visible.get(type); + color = (gc.isColourByLabel() ? "label|" : "") + + Format.getHexString(gc.getMinColor()) + "|" + + Format.getHexString(gc.getMaxColor()) + + (gc.isAutoScale() ? "|" : "|abso|") + gc.getMin() + "|" + + gc.getMax() + "|"; + if (gc.getThreshType() != AnnotationColourGradient.NO_THRESHOLD) + { + if (gc.getThreshType() == AnnotationColourGradient.BELOW_THRESHOLD) + { + color += "below"; + } + else + { + if (gc.getThreshType() != AnnotationColourGradient.ABOVE_THRESHOLD) + { + System.err.println("WARNING: Unsupported threshold type (" + + gc.getThreshType() + ") : Assuming 'above'"); + } + color += "above"; + } + // add the value + color += "|" + gc.getThresh(); + } + else + { + color += "none"; + } + } + else if (visible.get(type) instanceof java.awt.Color) + { + color = Format.getHexString((java.awt.Color) visible.get(type)); + } + else + { + // legacy support for integer objects containing colour triplet values + color = Format.getHexString(new java.awt.Color(Integer + .parseInt(visible.get(type).toString()))); + } + out.append(type); + out.append("\t"); + out.append(color); + out.append(newline); + } + } + // Work out which groups are both present and visible Vector groups = new Vector(); int groupIndex = 0; + boolean isnonpos = false; for (int i = 0; i < seqs.length; i++) { @@ -411,13 +753,16 @@ public class FeaturesFile { for (int j = 0; j < next.length; j++) { - if (!visible.containsKey(next[j].type)) + isnonpos = next[j].begin == 0 && next[j].end == 0; + if ((!nonpos && isnonpos) + || (!isnonpos && visOnly && !visible + .containsKey(next[j].type))) { continue; } if (next[j].featureGroup != null - && !groups.contains(next[j].featureGroup)) + && !groups.contains(next[j].featureGroup)) { groups.addElement(next[j].featureGroup); } @@ -426,14 +771,16 @@ public class FeaturesFile } String group = null; - do { if (groups.size() > 0 && groupIndex < groups.size()) { group = groups.elementAt(groupIndex).toString(); - out.append("\nSTARTGROUP\t" + group + "\n"); + out.append(newline); + out.append("STARTGROUP\t"); + out.append(group); + out.append(newline); } else { @@ -447,15 +794,19 @@ public class FeaturesFile { for (int j = 0; j < next.length; j++) { - if (!visible.containsKey(next[j].type)) + isnonpos = next[j].begin == 0 && next[j].end == 0; + if ((!nonpos && isnonpos) + || (!isnonpos && visOnly && !visible + .containsKey(next[j].type))) { + // skip if feature is nonpos and we ignore them or if we only + // output visible and it isn't non-pos and it's not visible continue; } if (group != null - && (next[j].featureGroup == null - || !next[j].featureGroup.equals(group)) - ) + && (next[j].featureGroup == null || !next[j].featureGroup + .equals(group))) { continue; } @@ -464,15 +815,17 @@ public class FeaturesFile { continue; } - - if (next[j].description == null || next[j].description.equals("")) + // we have features to output + featuresGen = true; + if (next[j].description == null + || next[j].description.equals("")) { out.append(next[j].type + "\t"); } else { if (next[j].links != null - && next[j].getDescription().indexOf("") == -1) + && next[j].getDescription().indexOf("") == -1) { out.append(""); } @@ -488,11 +841,7 @@ public class FeaturesFile if (next[j].description.indexOf(href) == -1) { - out.append("" - + label - + ""); + out.append("" + label + ""); } } @@ -504,19 +853,28 @@ public class FeaturesFile out.append("\t"); } - - out.append(seqs[i].getName() + "\t-1\t" - + next[j].begin + "\t" - + next[j].end + "\t" - + next[j].type + "\n" - ); + out.append(seqs[i].getName()); + out.append("\t-1\t"); + out.append(next[j].begin); + out.append("\t"); + out.append(next[j].end); + out.append("\t"); + out.append(next[j].type); + if (next[j].score != Float.NaN) + { + out.append("\t"); + out.append(next[j].score); + } + out.append(newline); } } } if (group != null) { - out.append("ENDGROUP\t" + group + "\n"); + out.append("ENDGROUP\t"); + out.append(group); + out.append(newline); groupIndex++; } else @@ -524,18 +882,36 @@ public class FeaturesFile break; } + } while (groupIndex < groups.size() + 1); + + if (!featuresGen) + { + return "No Features Visible"; } - while (groupIndex < groups.size() + 1); return out.toString(); } + /** + * generate a gff file for sequence features includes non-pos features by + * default. + * + * @param seqs + * @param visible + * @return + */ public String printGFFFormat(SequenceI[] seqs, Hashtable visible) { + return printGFFFormat(seqs, visible, true, true); + } + + public String printGFFFormat(SequenceI[] seqs, Hashtable visible, + boolean visOnly, boolean nonpos) + { StringBuffer out = new StringBuffer(); SequenceFeature[] next; String source; - + boolean isnonpos; for (int i = 0; i < seqs.length; i++) { if (seqs[i].getSequenceFeatures() != null) @@ -543,7 +919,10 @@ public class FeaturesFile next = seqs[i].getSequenceFeatures(); for (int j = 0; j < next.length; j++) { - if (!visible.containsKey(next[j].type)) + isnonpos = next[j].begin == 0 && next[j].end == 0; + if ((!nonpos && isnonpos) + || (!isnonpos && visOnly && !visible + .containsKey(next[j].type))) { continue; } @@ -554,17 +933,23 @@ public class FeaturesFile source = next[j].getDescription(); } - out.append(seqs[i].getName() + "\t" - + source + "\t" - + next[j].type + "\t" - + next[j].begin + "\t" - + next[j].end + "\t" - + next[j].score + "\t" - ); + out.append(seqs[i].getName()); + out.append("\t"); + 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"); if (next[j].getValue("STRAND") != null) { - out.append(next[j].getValue("STRAND") + "\t"); + out.append(next[j].getValue("STRAND")); + out.append("\t"); } else { @@ -579,13 +964,15 @@ public class FeaturesFile { out.append("."); } + // TODO: verify/check GFF - should there be a /t here before attribute + // output ? if (next[j].getValue("ATTRIBUTES") != null) { out.append(next[j].getValue("ATTRIBUTES")); } - out.append("\n"); + out.append(newline); } } @@ -594,18 +981,22 @@ public class FeaturesFile return out.toString(); } + /** + * this is only for the benefit of object polymorphism - method does nothing. + */ public void parse() { - //IGNORED + // IGNORED } /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! + * this is only for the benefit of object polymorphism - method does nothing. + * + * @return error message */ public String print() { return "USE printGFFFormat() or printJalviewFormat()"; } + }