*
* You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
*/
-package jalview.io;\r
-\r
-import java.io.*;\r
-import java.util.*;\r
-\r
-import javax.xml.parsers.ParserConfigurationException;\r
-\r
-import org.xml.sax.SAXException;\r
-\r
-import fr.orsay.lri.varna.exceptions.ExceptionFileFormatOrSyntax;\r
-import fr.orsay.lri.varna.exceptions.ExceptionLoadingFailed;\r
-import fr.orsay.lri.varna.exceptions.ExceptionPermissionDenied;\r
-import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;\r
-\r
-import jalview.analysis.SequenceIdMatcher;\r
-import jalview.datamodel.*;\r
-import jalview.schemes.*;\r
-import jalview.util.Format;\r
-\r
-/**\r
- * Parse and create Jalview Features files Detects GFF format features files and\r
- * parses. Does not implement standard print() - call specific printFeatures or\r
- * printGFF. Uses AlignmentI.findSequence(String id) to find the sequence object\r
- * for the features annotation - this normally works on an exact match.\r
- * \r
- * @author AMW\r
- * @version $Revision$\r
- */\r
-public class FeaturesFile extends AlignFile\r
-{\r
- /**\r
- * work around for GFF interpretation bug where source string becomes\r
- * description rather than a group\r
- */\r
- private boolean doGffSource = true;\r
-\r
- /**\r
- * Creates a new FeaturesFile object.\r
- */\r
- public FeaturesFile()\r
- {\r
- }\r
-\r
- /**\r
- * Creates a new FeaturesFile object.\r
- * \r
- * @param inFile\r
- * DOCUMENT ME!\r
- * @param type\r
- * DOCUMENT ME!\r
- * \r
- * @throws IOException\r
- * DOCUMENT ME!\r
- * @throws SAXException \r
- * @throws ParserConfigurationException \r
- * @throws ExceptionFileFormatOrSyntax \r
- * @throws ExceptionLoadingFailed \r
- * @throws ExceptionPermissionDenied \r
- * @throws InterruptedException \r
- * @throws ExceptionUnmatchedClosingParentheses \r
- */\r
- public FeaturesFile(String inFile, String type) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses\r
- {\r
- super(inFile, type);\r
- }\r
-\r
- public FeaturesFile(FileParse source) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses\r
- {\r
- super(source);\r
- }\r
-\r
- /**\r
- * Parse GFF or sequence features file using case-independent matching, discarding URLs\r
- * @param align - alignment/dataset containing sequences that are to be annotated\r
- * @param colours - hashtable to store feature colour definitions\r
- * @param removeHTML - process html strings into plain text\r
- * @return true if features were added\r
- */\r
- public boolean parse(AlignmentI align, Hashtable colours,\r
- boolean removeHTML)\r
- {\r
- return parse(align, colours, null, removeHTML, false);\r
- }\r
-\r
- /**\r
- * Parse GFF or sequence features file optionally using case-independent matching, discarding URLs\r
- * @param align - alignment/dataset containing sequences that are to be annotated\r
- * @param colours - hashtable to store feature colour definitions\r
- * @param removeHTML - process html strings into plain text\r
- * @param relaxedIdmatching - when true, ID matches to compound sequence IDs are allowed\r
- * @return true if features were added\r
- */\r
- public boolean parse(AlignmentI align, \r
- Map colours, boolean removeHTML, boolean relaxedIdMatching)\r
- {\r
- return parse(align, colours, null, removeHTML, relaxedIdMatching);\r
- }\r
-\r
- /**\r
- * Parse GFF or sequence features file optionally using case-independent matching\r
- * @param align - alignment/dataset containing sequences that are to be annotated\r
- * @param colours - hashtable to store feature colour definitions\r
- * @param featureLink - hashtable to store associated URLs \r
- * @param removeHTML - process html strings into plain text\r
- * @return true if features were added\r
- */\r
- public boolean parse(AlignmentI align, Map colours,\r
- Map featureLink, boolean removeHTML)\r
- {\r
- return parse(align, colours, featureLink, removeHTML, false);\r
- }\r
-\r
- /**\r
- /**\r
- * Parse GFF or sequence features file \r
- * @param align - alignment/dataset containing sequences that are to be annotated\r
- * @param colours - hashtable to store feature colour definitions\r
- * @param featureLink - hashtable to store associated URLs \r
- * @param removeHTML - process html strings into plain text\r
- * @param relaxedIdmatching - when true, ID matches to compound sequence IDs are allowed\r
- * @return true if features were added\r
- */\r
- public boolean parse(AlignmentI align,\r
- Map colours, Map featureLink, boolean removeHTML, boolean relaxedIdmatching)\r
- {\r
-\r
- String line = null;\r
- try\r
- {\r
- SequenceI seq = null;\r
- String type, desc, token = null;\r
-\r
- int index, start, end;\r
- float score;\r
- StringTokenizer st;\r
- SequenceFeature sf;\r
- String featureGroup = null, groupLink = null;\r
- Map typeLink = new Hashtable();\r
- /**\r
- * when true, assume GFF style features rather than Jalview style.\r
- */\r
- boolean GFFFile = true;\r
- while ((line = nextLine()) != null)\r
- {\r
- if (line.startsWith("#"))\r
- {\r
- continue;\r
- }\r
-\r
- st = new StringTokenizer(line, "\t");\r
- if (st.countTokens() == 1)\r
- {\r
- if (line.trim().equalsIgnoreCase("GFF"))\r
- {\r
- // Start parsing file as if it might be GFF again.\r
- GFFFile = true;\r
- continue;\r
- }\r
- }\r
- if (st.countTokens() > 1 && st.countTokens() < 4)\r
- {\r
- GFFFile = false;\r
- type = st.nextToken();\r
- if (type.equalsIgnoreCase("startgroup"))\r
- {\r
- featureGroup = st.nextToken();\r
- if (st.hasMoreElements())\r
- {\r
- groupLink = st.nextToken();\r
- featureLink.put(featureGroup, groupLink);\r
- }\r
- }\r
- else if (type.equalsIgnoreCase("endgroup"))\r
- {\r
- // We should check whether this is the current group,\r
- // but at present theres no way of showing more than 1 group\r
- st.nextToken();\r
- featureGroup = null;\r
- groupLink = null;\r
- }\r
- else\r
- {\r
- Object colour = null;\r
- String colscheme = st.nextToken();\r
- if (colscheme.indexOf("|") > -1\r
- || colscheme.trim().equalsIgnoreCase("label"))\r
- {\r
- // Parse '|' separated graduated colourscheme fields:\r
- // [label|][mincolour|maxcolour|[absolute|]minvalue|maxvalue|thresholdtype|thresholdvalue]\r
- // can either provide 'label' only, first is optional, next two\r
- // colors are required (but may be\r
- // left blank), next is optional, nxt two min/max are required.\r
- // first is either 'label'\r
- // first/second and third are both hexadecimal or word equivalent\r
- // colour.\r
- // next two are values parsed as floats.\r
- // fifth is either 'above','below', or 'none'.\r
- // sixth is a float value and only required when fifth is either\r
- // 'above' or 'below'.\r
- StringTokenizer gcol = new StringTokenizer(colscheme, "|",\r
- true);\r
- // set defaults\r
- int threshtype = AnnotationColourGradient.NO_THRESHOLD;\r
- float min = Float.MIN_VALUE, max = Float.MAX_VALUE, threshval = Float.NaN;\r
- boolean labelCol = false;\r
- // Parse spec line\r
- String mincol = gcol.nextToken();\r
- if (mincol == "|")\r
- {\r
- System.err\r
- .println("Expected either 'label' or a colour specification in the line: "\r
- + line);\r
- continue;\r
- }\r
- String maxcol = null;\r
- if (mincol.toLowerCase().indexOf("label") == 0)\r
- {\r
- labelCol = true;\r
- mincol = (gcol.hasMoreTokens() ? gcol.nextToken() : null); // skip\r
- // '|'\r
- mincol = (gcol.hasMoreTokens() ? gcol.nextToken() : null);\r
- }\r
- String abso = null, minval, maxval;\r
- if (mincol != null)\r
- {\r
- // at least four more tokens\r
- if (mincol.equals("|"))\r
- {\r
- mincol = "";\r
- }\r
- else\r
- {\r
- gcol.nextToken(); // skip next '|'\r
- }\r
- // continue parsing rest of line\r
- maxcol = gcol.nextToken();\r
- if (maxcol.equals("|"))\r
- {\r
- maxcol = "";\r
- }\r
- else\r
- {\r
- gcol.nextToken(); // skip next '|'\r
- }\r
- abso = gcol.nextToken();\r
- gcol.nextToken(); // skip next '|'\r
- if (abso.toLowerCase().indexOf("abso") != 0)\r
- {\r
- minval = abso;\r
- abso = null;\r
- }\r
- else\r
- {\r
- minval = gcol.nextToken();\r
- gcol.nextToken(); // skip next '|'\r
- }\r
- maxval = gcol.nextToken();\r
- if (gcol.hasMoreTokens())\r
- {\r
- gcol.nextToken(); // skip next '|'\r
- }\r
- try\r
- {\r
- if (minval.length() > 0)\r
- {\r
- min = new Float(minval).floatValue();\r
- }\r
- } catch (Exception e)\r
- {\r
- System.err\r
- .println("Couldn't parse the minimum value for graduated colour for type ("\r
- + colscheme\r
- + ") - did you misspell 'auto' for the optional automatic colour switch ?");\r
- e.printStackTrace();\r
- }\r
- try\r
- {\r
- if (maxval.length() > 0)\r
- {\r
- max = new Float(maxval).floatValue();\r
- }\r
- } catch (Exception e)\r
- {\r
- System.err\r
- .println("Couldn't parse the maximum value for graduated colour for type ("\r
- + colscheme + ")");\r
- e.printStackTrace();\r
- }\r
- }\r
- else\r
- {\r
- // add in some dummy min/max colours for the label-only\r
- // colourscheme.\r
- mincol = "FFFFFF";\r
- maxcol = "000000";\r
- }\r
- try\r
- {\r
- colour = new jalview.schemes.GraduatedColor(\r
- new UserColourScheme(mincol).findColour('A'),\r
- new UserColourScheme(maxcol).findColour('A'), min,\r
- max);\r
- } catch (Exception e)\r
- {\r
- System.err\r
- .println("Couldn't parse the graduated colour scheme ("\r
- + colscheme + ")");\r
- e.printStackTrace();\r
- }\r
- if (colour != null)\r
- {\r
- ((jalview.schemes.GraduatedColor) colour)\r
- .setColourByLabel(labelCol);\r
- ((jalview.schemes.GraduatedColor) colour)\r
- .setAutoScaled(abso == null);\r
- // add in any additional parameters\r
- String ttype = null, tval = null;\r
- if (gcol.hasMoreTokens())\r
- {\r
- // threshold type and possibly a threshold value\r
- ttype = gcol.nextToken();\r
- if (ttype.toLowerCase().startsWith("below"))\r
- {\r
- ((jalview.schemes.GraduatedColor) colour)\r
- .setThreshType(AnnotationColourGradient.BELOW_THRESHOLD);\r
- }\r
- else if (ttype.toLowerCase().startsWith("above"))\r
- {\r
- ((jalview.schemes.GraduatedColor) colour)\r
- .setThreshType(AnnotationColourGradient.ABOVE_THRESHOLD);\r
- }\r
- else\r
- {\r
- ((jalview.schemes.GraduatedColor) colour)\r
- .setThreshType(AnnotationColourGradient.NO_THRESHOLD);\r
- if (!ttype.toLowerCase().startsWith("no"))\r
- {\r
- System.err\r
- .println("Ignoring unrecognised threshold type : "\r
- + ttype);\r
- }\r
- }\r
- }\r
- if (((GraduatedColor) colour).getThreshType() != AnnotationColourGradient.NO_THRESHOLD)\r
- {\r
- try\r
- {\r
- gcol.nextToken();\r
- tval = gcol.nextToken();\r
- ((jalview.schemes.GraduatedColor) colour)\r
- .setThresh(new Float(tval).floatValue());\r
- } catch (Exception e)\r
- {\r
- System.err\r
- .println("Couldn't parse threshold value as a float: ("\r
- + tval + ")");\r
- e.printStackTrace();\r
- }\r
- }\r
- // parse the thresh-is-min token ?\r
- if (gcol.hasMoreTokens())\r
- {\r
- System.err\r
- .println("Ignoring additional tokens in parameters in graduated colour specification\n");\r
- while (gcol.hasMoreTokens())\r
- {\r
- System.err.println("|" + gcol.nextToken());\r
- }\r
- System.err.println("\n");\r
- }\r
- }\r
- }\r
- else\r
- {\r
- UserColourScheme ucs = new UserColourScheme(colscheme);\r
- colour = ucs.findColour('A');\r
- }\r
- if (colour != null)\r
- {\r
- colours.put(type, colour);\r
- }\r
- if (st.hasMoreElements())\r
- {\r
- String link = st.nextToken();\r
- typeLink.put(type, link);\r
- if (featureLink == null)\r
- {\r
- featureLink = new Hashtable();\r
- }\r
- featureLink.put(type, link);\r
- }\r
- }\r
- continue;\r
- }\r
- String seqId = "";\r
- while (st.hasMoreElements())\r
- {\r
-\r
- if (GFFFile)\r
- {\r
- // Still possible this is an old Jalview file,\r
- // which does not have type colours at the beginning\r
- seqId = token = st.nextToken();\r
- seq = findName(align, seqId, relaxedIdmatching);\r
- if (seq != null)\r
- {\r
- desc = st.nextToken();\r
- String group = null;\r
- if (doGffSource && desc.indexOf(' ') == -1)\r
- {\r
- // could also be a source term rather than description line\r
- group = new String(desc);\r
- }\r
- type = st.nextToken();\r
- try\r
- {\r
- String stt = st.nextToken();\r
- if (stt.length() == 0 || stt.equals("-"))\r
- {\r
- start = 0;\r
- }\r
- else\r
- {\r
- start = Integer.parseInt(stt);\r
- }\r
- } catch (NumberFormatException ex)\r
- {\r
- start = 0;\r
- }\r
- try\r
- {\r
- String stt = st.nextToken();\r
- if (stt.length() == 0 || stt.equals("-"))\r
- {\r
- end = 0;\r
- }\r
- else\r
- {\r
- end = Integer.parseInt(stt);\r
- }\r
- } catch (NumberFormatException ex)\r
- {\r
- end = 0;\r
- }\r
- // TODO: decide if non positional feature assertion for input data\r
- // where end==0 is generally valid\r
- if (end == 0)\r
- {\r
- // treat as non-positional feature, regardless.\r
- start = 0;\r
- }\r
- try\r
- {\r
- score = new Float(st.nextToken()).floatValue();\r
- } catch (NumberFormatException ex)\r
- {\r
- score = 0;\r
- }\r
-\r
- sf = new SequenceFeature(type, desc, start, end, score, group);\r
-\r
- try\r
- {\r
- sf.setValue("STRAND", st.nextToken());\r
- sf.setValue("FRAME", st.nextToken());\r
- } catch (Exception ex)\r
- {\r
- }\r
-\r
- if (st.hasMoreTokens())\r
- {\r
- StringBuffer attributes = new StringBuffer();\r
- while (st.hasMoreTokens())\r
- {\r
- attributes.append("\t" + st.nextElement());\r
- }\r
- // TODO validate and split GFF2 attributes field ? parse out\r
- // ([A-Za-z][A-Za-z0-9_]*) <value> ; and add as\r
- // sf.setValue(attrib, val);\r
- sf.setValue("ATTRIBUTES", attributes.toString());\r
- }\r
-\r
- seq.addSequenceFeature(sf);\r
- while ((seq = align.findName(seq, seqId, true)) != null)\r
- {\r
- seq.addSequenceFeature(new SequenceFeature(sf));\r
- }\r
- break;\r
- }\r
- }\r
-\r
- if (GFFFile && seq == null)\r
- {\r
- desc = token;\r
- }\r
- else\r
- {\r
- desc = st.nextToken();\r
- }\r
- if (!st.hasMoreTokens())\r
- {\r
- System.err\r
- .println("DEBUG: Run out of tokens when trying to identify the destination for the feature.. giving up.");\r
- // in all probability, this isn't a file we understand, so bail\r
- // quietly.\r
- return false;\r
- }\r
-\r
- token = st.nextToken();\r
-\r
- if (!token.equals("ID_NOT_SPECIFIED"))\r
- {\r
- seq = findName(align, seqId = token, relaxedIdmatching);\r
- st.nextToken();\r
- }\r
- else\r
- {\r
- seqId = null;\r
- try\r
- {\r
- index = Integer.parseInt(st.nextToken());\r
- seq = align.getSequenceAt(index);\r
- } catch (NumberFormatException ex)\r
- {\r
- seq = null;\r
- }\r
- }\r
-\r
- if (seq == null)\r
- {\r
- System.out.println("Sequence not found: " + line);\r
- break;\r
- }\r
-\r
- start = Integer.parseInt(st.nextToken());\r
- end = Integer.parseInt(st.nextToken());\r
-\r
- type = st.nextToken();\r
-\r
- if (!colours.containsKey(type))\r
- {\r
- // Probably the old style groups file\r
- UserColourScheme ucs = new UserColourScheme(type);\r
- colours.put(type, ucs.findColour('A'));\r
- }\r
- sf = new SequenceFeature(type, desc, "", start, end, featureGroup);\r
- if (st.hasMoreTokens())\r
- {\r
- try\r
- {\r
- score = new Float(st.nextToken()).floatValue();\r
- // update colourgradient bounds if allowed to\r
- } catch (NumberFormatException ex)\r
- {\r
- score = 0;\r
- }\r
- sf.setScore(score);\r
- }\r
- if (groupLink != null && removeHTML)\r
- {\r
- sf.addLink(groupLink);\r
- sf.description += "%LINK%";\r
- }\r
- if (typeLink.containsKey(type) && removeHTML)\r
- {\r
- sf.addLink(typeLink.get(type).toString());\r
- sf.description += "%LINK%";\r
- }\r
-\r
- parseDescriptionHTML(sf, removeHTML);\r
-\r
- seq.addSequenceFeature(sf);\r
-\r
- while (seqId != null\r
- && (seq = align.findName(seq, seqId, false)) != null)\r
- {\r
- seq.addSequenceFeature(new SequenceFeature(sf));\r
- }\r
- // If we got here, its not a GFFFile\r
- GFFFile = false;\r
- }\r
- }\r
- resetMatcher();\r
- } catch (Exception ex)\r
- {\r
- System.out.println(line);\r
- System.out.println("Error parsing feature file: " + ex + "\n" + line);\r
- ex.printStackTrace(System.err);\r
- resetMatcher();\r
- return false;\r
- }\r
-\r
- return true;\r
- }\r
-\r
- private AlignmentI lastmatchedAl = null;\r
-\r
- private SequenceIdMatcher matcher = null;\r
-\r
- /**\r
- * clear any temporary handles used to speed up ID matching\r
- */\r
- private void resetMatcher()\r
- {\r
- lastmatchedAl = null;\r
- matcher = null;\r
- }\r
-\r
- private SequenceI findName(AlignmentI align, String seqId,\r
- boolean relaxedIdMatching)\r
- {\r
- SequenceI match = null;\r
- if (relaxedIdMatching)\r
- {\r
- if (lastmatchedAl != align)\r
- {\r
- matcher = new SequenceIdMatcher(\r
- (lastmatchedAl = align).getSequencesArray());\r
- }\r
- match = matcher.findIdMatch(seqId);\r
- }\r
- else\r
- {\r
- match = align.findName(seqId, true);\r
- }\r
- return match;\r
- }\r
-\r
- public void parseDescriptionHTML(SequenceFeature sf, boolean removeHTML)\r
- {\r
- if (sf.getDescription() == null)\r
- {\r
- return;\r
- }\r
- jalview.util.ParseHtmlBodyAndLinks parsed = new jalview.util.ParseHtmlBodyAndLinks(sf.getDescription(), removeHTML, newline);\r
-\r
- sf.description = (removeHTML) ? parsed.getNonHtmlContent() : sf.description;\r
- for (String link:parsed.getLinks())\r
- {\r
- sf.addLink(link);\r
- }\r
-\r
- }\r
-\r
- /**\r
- * generate a features file for seqs includes non-pos features by default.\r
- * \r
- * @param seqs\r
- * source of sequence features\r
- * @param visible\r
- * hash of feature types and colours\r
- * @return features file contents\r
- */\r
- public String printJalviewFormat(SequenceI[] seqs, Hashtable visible)\r
- {\r
- return printJalviewFormat(seqs, visible, true, true);\r
- }\r
-\r
- /**\r
- * generate a features file for seqs with colours from visible (if any)\r
- * \r
- * @param seqs\r
- * source of features\r
- * @param visible\r
- * hash of Colours for each feature type\r
- * @param visOnly\r
- * when true only feature types in 'visible' will be output\r
- * @param nonpos\r
- * indicates if non-positional features should be output (regardless\r
- * of group or type)\r
- * @return features file contents\r
- */\r
- public String printJalviewFormat(SequenceI[] seqs, Hashtable visible,\r
- boolean visOnly, boolean nonpos)\r
- {\r
- StringBuffer out = new StringBuffer();\r
- SequenceFeature[] next;\r
- boolean featuresGen = false;\r
- if (visOnly && !nonpos && (visible == null || visible.size() < 1))\r
- {\r
- // no point continuing.\r
- return "No Features Visible";\r
- }\r
-\r
- if (visible != null && visOnly)\r
- {\r
- // write feature colours only if we're given them and we are generating\r
- // viewed features\r
- // TODO: decide if feature links should also be written here ?\r
- Enumeration en = visible.keys();\r
- String type, color;\r
- while (en.hasMoreElements())\r
- {\r
- type = en.nextElement().toString();\r
-\r
- if (visible.get(type) instanceof GraduatedColor)\r
- {\r
- GraduatedColor gc = (GraduatedColor) visible.get(type);\r
- color = (gc.isColourByLabel() ? "label|" : "")\r
- + Format.getHexString(gc.getMinColor()) + "|"\r
- + Format.getHexString(gc.getMaxColor())\r
- + (gc.isAutoScale() ? "|" : "|abso|") + gc.getMin() + "|"\r
- + gc.getMax() + "|";\r
- if (gc.getThreshType() != AnnotationColourGradient.NO_THRESHOLD)\r
- {\r
- if (gc.getThreshType() == AnnotationColourGradient.BELOW_THRESHOLD)\r
- {\r
- color += "below";\r
- }\r
- else\r
- {\r
- if (gc.getThreshType() != AnnotationColourGradient.ABOVE_THRESHOLD)\r
- {\r
- System.err.println("WARNING: Unsupported threshold type ("\r
- + gc.getThreshType() + ") : Assuming 'above'");\r
- }\r
- color += "above";\r
- }\r
- // add the value\r
- color += "|" + gc.getThresh();\r
- }\r
- else\r
- {\r
- color += "none";\r
- }\r
- }\r
- else if (visible.get(type) instanceof java.awt.Color)\r
- {\r
- color = Format.getHexString((java.awt.Color) visible.get(type));\r
- }\r
- else\r
- {\r
- // legacy support for integer objects containing colour triplet values\r
- color = Format.getHexString(new java.awt.Color(Integer\r
- .parseInt(visible.get(type).toString())));\r
- }\r
- out.append(type);\r
- out.append("\t");\r
- out.append(color);\r
- out.append(newline);\r
- }\r
- }\r
- // Work out which groups are both present and visible\r
- Vector groups = new Vector();\r
- int groupIndex = 0;\r
- boolean isnonpos = false;\r
-\r
- for (int i = 0; i < seqs.length; i++)\r
- {\r
- next = seqs[i].getSequenceFeatures();\r
- if (next != null)\r
- {\r
- for (int j = 0; j < next.length; j++)\r
- {\r
- isnonpos = next[j].begin == 0 && next[j].end == 0;\r
- if ((!nonpos && isnonpos)\r
- || (!isnonpos && visOnly && !visible\r
- .containsKey(next[j].type)))\r
- {\r
- continue;\r
- }\r
-\r
- if (next[j].featureGroup != null\r
- && !groups.contains(next[j].featureGroup))\r
- {\r
- groups.addElement(next[j].featureGroup);\r
- }\r
- }\r
- }\r
- }\r
-\r
- String group = null;\r
- do\r
- {\r
-\r
- if (groups.size() > 0 && groupIndex < groups.size())\r
- {\r
- group = groups.elementAt(groupIndex).toString();\r
- out.append(newline);\r
- out.append("STARTGROUP\t");\r
- out.append(group);\r
- out.append(newline);\r
- }\r
- else\r
- {\r
- group = null;\r
- }\r
-\r
- for (int i = 0; i < seqs.length; i++)\r
- {\r
- next = seqs[i].getSequenceFeatures();\r
- if (next != null)\r
- {\r
- for (int j = 0; j < next.length; j++)\r
- {\r
- isnonpos = next[j].begin == 0 && next[j].end == 0;\r
- if ((!nonpos && isnonpos)\r
- || (!isnonpos && visOnly && !visible\r
- .containsKey(next[j].type)))\r
- {\r
- // skip if feature is nonpos and we ignore them or if we only\r
- // output visible and it isn't non-pos and it's not visible\r
- continue;\r
- }\r
-\r
- if (group != null\r
- && (next[j].featureGroup == null || !next[j].featureGroup\r
- .equals(group)))\r
- {\r
- continue;\r
- }\r
-\r
- if (group == null && next[j].featureGroup != null)\r
- {\r
- continue;\r
- }\r
- // we have features to output\r
- featuresGen = true;\r
- if (next[j].description == null\r
- || next[j].description.equals(""))\r
- {\r
- out.append(next[j].type + "\t");\r
- }\r
- else\r
- {\r
- if (next[j].links != null\r
- && next[j].getDescription().indexOf("<html>") == -1)\r
- {\r
- out.append("<html>");\r
- }\r
-\r
- out.append(next[j].description + " ");\r
- if (next[j].links != null)\r
- {\r
- for (int l = 0; l < next[j].links.size(); l++)\r
- {\r
- String label = next[j].links.elementAt(l).toString();\r
- String href = label.substring(label.indexOf("|") + 1);\r
- label = label.substring(0, label.indexOf("|"));\r
-\r
- if (next[j].description.indexOf(href) == -1)\r
- {\r
- out.append("<a href=\"" + href + "\">" + label + "</a>");\r
- }\r
- }\r
-\r
- if (next[j].getDescription().indexOf("</html>") == -1)\r
- {\r
- out.append("</html>");\r
- }\r
- }\r
-\r
- out.append("\t");\r
- }\r
- out.append(seqs[i].getName());\r
- out.append("\t-1\t");\r
- out.append(next[j].begin);\r
- out.append("\t");\r
- out.append(next[j].end);\r
- out.append("\t");\r
- out.append(next[j].type);\r
- if (next[j].score != Float.NaN)\r
- {\r
- out.append("\t");\r
- out.append(next[j].score);\r
- }\r
- out.append(newline);\r
- }\r
- }\r
- }\r
-\r
- if (group != null)\r
- {\r
- out.append("ENDGROUP\t");\r
- out.append(group);\r
- out.append(newline);\r
- groupIndex++;\r
- }\r
- else\r
- {\r
- break;\r
- }\r
-\r
- } while (groupIndex < groups.size() + 1);\r
-\r
- if (!featuresGen)\r
- {\r
- return "No Features Visible";\r
- }\r
-\r
- return out.toString();\r
- }\r
-\r
- /**\r
- * generate a gff file for sequence features includes non-pos features by\r
- * default.\r
- * \r
- * @param seqs\r
- * @param visible\r
- * @return\r
- */\r
- public String printGFFFormat(SequenceI[] seqs, Hashtable visible)\r
- {\r
- return printGFFFormat(seqs, visible, true, true);\r
- }\r
-\r
- public String printGFFFormat(SequenceI[] seqs, Hashtable visible,\r
- boolean visOnly, boolean nonpos)\r
- {\r
- StringBuffer out = new StringBuffer();\r
- SequenceFeature[] next;\r
- String source;\r
- boolean isnonpos;\r
- for (int i = 0; i < seqs.length; i++)\r
- {\r
- if (seqs[i].getSequenceFeatures() != null)\r
- {\r
- next = seqs[i].getSequenceFeatures();\r
- for (int j = 0; j < next.length; j++)\r
- {\r
- isnonpos = next[j].begin == 0 && next[j].end == 0;\r
- if ((!nonpos && isnonpos)\r
- || (!isnonpos && visOnly && !visible\r
- .containsKey(next[j].type)))\r
- {\r
- continue;\r
- }\r
-\r
- source = next[j].featureGroup;\r
- if (source == null)\r
- {\r
- source = next[j].getDescription();\r
- }\r
-\r
- out.append(seqs[i].getName());\r
- out.append("\t");\r
- out.append(source);\r
- out.append("\t");\r
- out.append(next[j].type);\r
- out.append("\t");\r
- out.append(next[j].begin);\r
- out.append("\t");\r
- out.append(next[j].end);\r
- out.append("\t");\r
- out.append(next[j].score);\r
- out.append("\t");\r
-\r
- if (next[j].getValue("STRAND") != null)\r
- {\r
- out.append(next[j].getValue("STRAND"));\r
- out.append("\t");\r
- }\r
- else\r
- {\r
- out.append(".\t");\r
- }\r
-\r
- if (next[j].getValue("FRAME") != null)\r
- {\r
- out.append(next[j].getValue("FRAME"));\r
- }\r
- else\r
- {\r
- out.append(".");\r
- }\r
- // TODO: verify/check GFF - should there be a /t here before attribute\r
- // output ?\r
-\r
- if (next[j].getValue("ATTRIBUTES") != null)\r
- {\r
- out.append(next[j].getValue("ATTRIBUTES"));\r
- }\r
-\r
- out.append(newline);\r
-\r
- }\r
- }\r
- }\r
-\r
- return out.toString();\r
- }\r
-\r
- /**\r
- * this is only for the benefit of object polymorphism - method does nothing.\r
- */\r
- public void parse()\r
- {\r
- // IGNORED\r
- }\r
-\r
- /**\r
- * this is only for the benefit of object polymorphism - method does nothing.\r
- * \r
- * @return error message\r
- */\r
- public String print()\r
- {\r
- return "USE printGFFFormat() or printJalviewFormat()";\r
- }\r
-\r
-}\r
+package jalview.io;
+
+import java.io.*;
+import java.util.*;
+
+import javax.xml.parsers.ParserConfigurationException;
+
+import org.xml.sax.SAXException;
+
+import fr.orsay.lri.varna.exceptions.ExceptionFileFormatOrSyntax;
+import fr.orsay.lri.varna.exceptions.ExceptionLoadingFailed;
+import fr.orsay.lri.varna.exceptions.ExceptionPermissionDenied;
+import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;
+
+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.
+ *
+ * @author AMW
+ * @version $Revision$
+ */
+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()
+ {
+ }
+
+ /**
+ * Creates a new FeaturesFile object.
+ *
+ * @param inFile
+ * DOCUMENT ME!
+ * @param type
+ * DOCUMENT ME!
+ *
+ * @throws IOException
+ * DOCUMENT ME!
+ * @throws SAXException
+ * @throws ParserConfigurationException
+ * @throws ExceptionFileFormatOrSyntax
+ * @throws ExceptionLoadingFailed
+ * @throws ExceptionPermissionDenied
+ * @throws InterruptedException
+ * @throws ExceptionUnmatchedClosingParentheses
+ */
+ public FeaturesFile(String inFile, String type) throws IOException,
+ ExceptionFileFormatOrSyntax, ParserConfigurationException,
+ SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed,
+ InterruptedException, ExceptionUnmatchedClosingParentheses
+ {
+ super(inFile, type);
+ }
+
+ public FeaturesFile(FileParse source) throws IOException,
+ ExceptionFileFormatOrSyntax, ParserConfigurationException,
+ SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed,
+ InterruptedException, ExceptionUnmatchedClosingParentheses
+ {
+ super(source);
+ }
+
+ /**
+ * 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, 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, Map 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, Map colours, Map 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, Map colours, Map featureLink,
+ boolean removeHTML, boolean relaxedIdmatching)
+ {
+
+ String line = null;
+ try
+ {
+ SequenceI seq = null;
+ String type, desc, token = null;
+
+ int index, start, end;
+ float score;
+ StringTokenizer st;
+ SequenceFeature sf;
+ String featureGroup = null, groupLink = null;
+ Map typeLink = new Hashtable();
+ /**
+ * when true, assume GFF style features rather than Jalview style.
+ */
+ boolean GFFFile = true;
+ while ((line = nextLine()) != null)
+ {
+ if (line.startsWith("#"))
+ {
+ continue;
+ }
+
+ 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;
+ type = st.nextToken();
+ if (type.equalsIgnoreCase("startgroup"))
+ {
+ featureGroup = st.nextToken();
+ if (st.hasMoreElements())
+ {
+ groupLink = st.nextToken();
+ featureLink.put(featureGroup, groupLink);
+ }
+ }
+ 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
+ st.nextToken();
+ featureGroup = null;
+ groupLink = null;
+ }
+ else
+ {
+ 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();
+ typeLink.put(type, link);
+ if (featureLink == null)
+ {
+ featureLink = new Hashtable();
+ }
+ featureLink.put(type, link);
+ }
+ }
+ continue;
+ }
+ String seqId = "";
+ while (st.hasMoreElements())
+ {
+
+ if (GFFFile)
+ {
+ // Still possible this is an old Jalview file,
+ // which does not have type colours at the beginning
+ 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
+ {
+ String stt = st.nextToken();
+ if (stt.length() == 0 || stt.equals("-"))
+ {
+ start = 0;
+ }
+ else
+ {
+ start = Integer.parseInt(stt);
+ }
+ } catch (NumberFormatException ex)
+ {
+ start = 0;
+ }
+ try
+ {
+ String stt = st.nextToken();
+ if (stt.length() == 0 || stt.equals("-"))
+ {
+ end = 0;
+ }
+ else
+ {
+ end = Integer.parseInt(stt);
+ }
+ } catch (NumberFormatException ex)
+ {
+ end = 0;
+ }
+ // TODO: decide if non positional feature assertion for input data
+ // where end==0 is generally valid
+ if (end == 0)
+ {
+ // treat as non-positional feature, regardless.
+ start = 0;
+ }
+ try
+ {
+ score = new Float(st.nextToken()).floatValue();
+ } catch (NumberFormatException ex)
+ {
+ score = 0;
+ }
+
+ sf = new SequenceFeature(type, desc, start, end, score, group);
+
+ try
+ {
+ sf.setValue("STRAND", st.nextToken());
+ sf.setValue("FRAME", st.nextToken());
+ } catch (Exception ex)
+ {
+ }
+
+ if (st.hasMoreTokens())
+ {
+ StringBuffer attributes = new StringBuffer();
+ while (st.hasMoreTokens())
+ {
+ attributes.append("\t" + st.nextElement());
+ }
+ // TODO validate and split GFF2 attributes field ? parse out
+ // ([A-Za-z][A-Za-z0-9_]*) <value> ; 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;
+ }
+ }
+
+ if (GFFFile && seq == null)
+ {
+ desc = token;
+ }
+ else
+ {
+ desc = st.nextToken();
+ }
+ 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.
+ return false;
+ }
+
+ token = st.nextToken();
+
+ if (!token.equals("ID_NOT_SPECIFIED"))
+ {
+ seq = findName(align, seqId = token, relaxedIdmatching);
+ st.nextToken();
+ }
+ else
+ {
+ seqId = null;
+ try
+ {
+ index = Integer.parseInt(st.nextToken());
+ seq = align.getSequenceAt(index);
+ } catch (NumberFormatException ex)
+ {
+ seq = null;
+ }
+ }
+
+ if (seq == null)
+ {
+ System.out.println("Sequence not found: " + line);
+ break;
+ }
+
+ start = Integer.parseInt(st.nextToken());
+ end = Integer.parseInt(st.nextToken());
+
+ type = st.nextToken();
+
+ if (!colours.containsKey(type))
+ {
+ // Probably the old style groups file
+ UserColourScheme ucs = new UserColourScheme(type);
+ colours.put(type, ucs.findColour('A'));
+ }
+ sf = new SequenceFeature(type, desc, "", start, end, featureGroup);
+ 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);
+ sf.description += "%LINK%";
+ }
+ if (typeLink.containsKey(type) && removeHTML)
+ {
+ sf.addLink(typeLink.get(type).toString());
+ sf.description += "%LINK%";
+ }
+
+ parseDescriptionHTML(sf, removeHTML);
+
+ 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;
+ }
+ }
+ 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;
+ }
+
+ private AlignmentI lastmatchedAl = null;
+
+ private SequenceIdMatcher matcher = null;
+
+ /**
+ * clear any temporary handles used to speed up ID matching
+ */
+ private void resetMatcher()
+ {
+ lastmatchedAl = null;
+ matcher = null;
+ }
+
+ private SequenceI findName(AlignmentI align, String seqId,
+ boolean relaxedIdMatching)
+ {
+ SequenceI match = null;
+ if (relaxedIdMatching)
+ {
+ if (lastmatchedAl != align)
+ {
+ matcher = new SequenceIdMatcher(
+ (lastmatchedAl = align).getSequencesArray());
+ }
+ match = matcher.findIdMatch(seqId);
+ }
+ else
+ {
+ match = align.findName(seqId, true);
+ }
+ return match;
+ }
+
+ public void parseDescriptionHTML(SequenceFeature sf, boolean removeHTML)
+ {
+ if (sf.getDescription() == null)
+ {
+ return;
+ }
+ jalview.util.ParseHtmlBodyAndLinks parsed = new jalview.util.ParseHtmlBodyAndLinks(
+ sf.getDescription(), removeHTML, newline);
+
+ sf.description = (removeHTML) ? parsed.getNonHtmlContent()
+ : sf.description;
+ for (String link : parsed.getLinks())
+ {
+ sf.addLink(link);
+ }
+
+ }
+
+ /**
+ * 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)
+ {
+ 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;
+ boolean featuresGen = false;
+ if (visOnly && !nonpos && (visible == null || visible.size() < 1))
+ {
+ // no point continuing.
+ return "No Features Visible";
+ }
+
+ if (visible != null && visOnly)
+ {
+ // 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();
+
+ 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++)
+ {
+ next = seqs[i].getSequenceFeatures();
+ if (next != null)
+ {
+ for (int j = 0; j < next.length; j++)
+ {
+ 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.addElement(next[j].featureGroup);
+ }
+ }
+ }
+ }
+
+ String group = null;
+ do
+ {
+
+ if (groups.size() > 0 && groupIndex < groups.size())
+ {
+ group = groups.elementAt(groupIndex).toString();
+ out.append(newline);
+ out.append("STARTGROUP\t");
+ out.append(group);
+ out.append(newline);
+ }
+ else
+ {
+ group = null;
+ }
+
+ for (int i = 0; i < seqs.length; i++)
+ {
+ next = seqs[i].getSequenceFeatures();
+ if (next != null)
+ {
+ for (int j = 0; j < next.length; j++)
+ {
+ 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)))
+ {
+ continue;
+ }
+
+ if (group == null && next[j].featureGroup != null)
+ {
+ continue;
+ }
+ // 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("<html>") == -1)
+ {
+ out.append("<html>");
+ }
+
+ out.append(next[j].description + " ");
+ if (next[j].links != null)
+ {
+ for (int l = 0; l < next[j].links.size(); l++)
+ {
+ String label = next[j].links.elementAt(l).toString();
+ String href = label.substring(label.indexOf("|") + 1);
+ label = label.substring(0, label.indexOf("|"));
+
+ if (next[j].description.indexOf(href) == -1)
+ {
+ out.append("<a href=\"" + href + "\">" + label + "</a>");
+ }
+ }
+
+ if (next[j].getDescription().indexOf("</html>") == -1)
+ {
+ out.append("</html>");
+ }
+ }
+
+ out.append("\t");
+ }
+ 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");
+ out.append(group);
+ out.append(newline);
+ groupIndex++;
+ }
+ else
+ {
+ break;
+ }
+
+ } while (groupIndex < groups.size() + 1);
+
+ if (!featuresGen)
+ {
+ return "No Features Visible";
+ }
+
+ 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)
+ {
+ next = seqs[i].getSequenceFeatures();
+ for (int j = 0; j < next.length; j++)
+ {
+ isnonpos = next[j].begin == 0 && next[j].end == 0;
+ if ((!nonpos && isnonpos)
+ || (!isnonpos && visOnly && !visible
+ .containsKey(next[j].type)))
+ {
+ continue;
+ }
+
+ source = next[j].featureGroup;
+ if (source == null)
+ {
+ source = next[j].getDescription();
+ }
+
+ 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"));
+ out.append("\t");
+ }
+ else
+ {
+ out.append(".\t");
+ }
+
+ if (next[j].getValue("FRAME") != null)
+ {
+ out.append(next[j].getValue("FRAME"));
+ }
+ else
+ {
+ 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(newline);
+
+ }
+ }
+ }
+
+ return out.toString();
+ }
+
+ /**
+ * this is only for the benefit of object polymorphism - method does nothing.
+ */
+ public void parse()
+ {
+ // IGNORED
+ }
+
+ /**
+ * this is only for the benefit of object polymorphism - method does nothing.
+ *
+ * @return error message
+ */
+ public String print()
+ {
+ return "USE printGFFFormat() or printJalviewFormat()";
+ }
+
+}
git://source.jalview.org / jalview.git / commitdiff