/*\r
-* Jalview - A Sequence Alignment Editor and Viewer\r
-* Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
-*\r
-* This program is free software; you can redistribute it and/or\r
-* modify it under the terms of the GNU General Public License\r
-* as published by the Free Software Foundation; either version 2\r
-* of the License, or (at your option) any later version.\r
-*\r
-* This program is distributed in the hope that it will be useful,\r
-* but WITHOUT ANY WARRANTY; without even the implied warranty of\r
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
-* GNU General Public License for more details.\r
-*\r
-* You should have received a copy of the GNU General Public License\r
-* along with this program; if not, write to the Free Software\r
-* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
-*/\r
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)\r
+ * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle\r
+ * \r
+ * This file is part of Jalview.\r
+ * \r
+ * Jalview is free software: you can redistribute it and/or\r
+ * modify it under the terms of the GNU General Public License \r
+ * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.\r
+ * \r
+ * Jalview is distributed in the hope that it will be useful, but \r
+ * WITHOUT ANY WARRANTY; without even the implied warranty \r
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR \r
+ * PURPOSE. See the GNU General Public License for more details.\r
+ * \r
+ * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.\r
+ */\r
package jalview.io;\r
\r
-import jalview.datamodel.*;\r
-\r
import java.io.*;\r
import java.util.*;\r
-import jalview.schemes.UserColourScheme;\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
+\r
+import jalview.analysis.SequenceIdMatcher;\r
+import jalview.datamodel.*;\r
+import jalview.schemes.*;\r
+import jalview.util.Format;\r
\r
/**\r
- * DOCUMENT ME!\r
- *\r
- * @author $author$\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
- * Creates a new FeaturesFile object.\r
- */\r
- public FeaturesFile()\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
+ */\r
+ public FeaturesFile(String inFile, String type) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed\r
+ {\r
+ super(inFile, type);\r
+ }\r
+\r
+ public FeaturesFile(FileParse source) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed\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
+ Hashtable 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, Hashtable colours,\r
+ Hashtable 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
+ Hashtable colours, Hashtable featureLink, boolean removeHTML, boolean relaxedIdmatching)\r
+ {\r
+\r
+ String line = null;\r
+ try\r
{\r
- }\r
-\r
- /**\r
- * Creates a new FeaturesFile object.\r
- *\r
- * @param inStr DOCUMENT ME!\r
- */\r
- public FeaturesFile(String inStr)\r
- {\r
- super(inStr);\r
- }\r
-\r
- /**\r
- * Creates a new FeaturesFile object.\r
- *\r
- * @param inFile DOCUMENT ME!\r
- * @param type DOCUMENT ME!\r
- *\r
- * @throws IOException DOCUMENT ME!\r
- */\r
- public FeaturesFile(String inFile, String type)\r
- throws IOException\r
- {\r
- super(inFile, type);\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @throws IOException DOCUMENT ME!\r
- */\r
- public boolean parse(AlignmentI align, Hashtable colours)\r
- throws IOException\r
- {\r
- String line = null;\r
- try\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
+ Hashtable 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
- 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;\r
-\r
- boolean GFFFile = true;\r
+ if (line.startsWith("#"))\r
+ {\r
+ continue;\r
+ }\r
\r
- while ( (line = nextLine()) != null)\r
+ st = new StringTokenizer(line, "\t");\r
+ if (st.countTokens() == 1)\r
{\r
- if(line.startsWith("#"))\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
- st = new StringTokenizer(line, "\t");\r
- if (st.countTokens()>1 && st.countTokens() < 4 )\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
- GFFFile = false;\r
- type = st.nextToken();\r
- if (type.equalsIgnoreCase("startgroup"))\r
+ featureGroup = st.nextToken();\r
+ if (st.hasMoreElements())\r
{\r
- featureGroup = st.nextToken();\r
+ groupLink = st.nextToken();\r
+ featureLink.put(featureGroup, groupLink);\r
}\r
- else if (type.equalsIgnoreCase("endgroup"))\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
- //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
+ // 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(st.nextToken());\r
- colours.put(type, ucs.findColour("A"));\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
- continue;\r
}\r
+ continue;\r
+ }\r
+ String seqId = "";\r
+ while (st.hasMoreElements())\r
+ {\r
\r
- while (st.hasMoreElements())\r
+ if (GFFFile)\r
{\r
-\r
- if(GFFFile)\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
- // Still possible this is an old Jalview file,\r
- // which does not have type colours at the beginning\r
- token = st.nextToken();\r
- seq = align.findName(token);\r
- if(seq != null)\r
+ desc = st.nextToken();\r
+ String group = null;\r
+ if (doGffSource && desc.indexOf(' ') == -1)\r
{\r
- desc = st.nextToken();\r
- type = st.nextToken();\r
- start = Integer.parseInt(st.nextToken());\r
- end = Integer.parseInt(st.nextToken());\r
- try\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
- score = Float.parseFloat(st.nextToken());\r
+ start = Integer.parseInt(stt);\r
}\r
- catch (NumberFormatException ex)\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
- score = 0;\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, null);\r
+ sf = new SequenceFeature(type, desc, start, end, score, group);\r
\r
- try\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
- sf.setValue("STRAND", st.nextToken());\r
- sf.setValue("FRAME", st.nextToken());\r
+ attributes.append("\t" + st.nextElement());\r
}\r
- catch (Exception ex)\r
- {}\r
-\r
- seq.getDatasetSequence().addSequenceFeature(sf);\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
- break;\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
- desc = st.nextToken();\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
- token = st.nextToken();\r
- if (!token.equals("ID_NOT_SPECIFIED"))\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
- seq = align.findName(token);\r
- st.nextToken();\r
- }\r
- else\r
+ index = Integer.parseInt(st.nextToken());\r
+ seq = align.getSequenceAt(index);\r
+ } catch (NumberFormatException ex)\r
{\r
- try{\r
- index = Integer.parseInt(st.nextToken());\r
- seq = align.getSequenceAt(index);\r
- }\r
- catch(NumberFormatException ex)\r
- {\r
- seq = null;\r
- }\r
+ seq = null;\r
}\r
+ }\r
\r
- if(seq==null)\r
- {\r
- System.out.println("Sequence not found: "+line);\r
- break;\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
+ start = Integer.parseInt(st.nextToken());\r
+ end = Integer.parseInt(st.nextToken());\r
\r
- type = st.nextToken();\r
+ type = st.nextToken();\r
\r
- if (!colours.containsKey(type))\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
- // Probably the old style groups file\r
- UserColourScheme ucs = new UserColourScheme(type);\r
- colours.put(type, ucs.findColour("A"));\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
- sf = new SequenceFeature(type, desc, "", start, end, featureGroup);\r
+ parseDescriptionHTML(sf, removeHTML);\r
\r
- seq.getDatasetSequence().addSequenceFeature(sf);\r
+ seq.addSequenceFeature(sf);\r
\r
- //If we got here, its not a GFFFile\r
- GFFFile = false;\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
- catch (Exception ex)\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
- System.out.println(line);\r
- ex.printStackTrace();\r
- System.out.println("Error parsing groups file: " + ex +"\n"+line);\r
- return false;\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
- return true;\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
- * DOCUMENT ME!\r
- *\r
- * @param s DOCUMENT ME!\r
- * @param len DOCUMENT ME!\r
- * @param gaps DOCUMENT ME!\r
- * @param displayId DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public String printJalviewFormat(SequenceI [] seqs,\r
- Hashtable visible)\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
- StringBuffer out = new StringBuffer();\r
- SequenceFeature [] next;\r
+ // no point continuing.\r
+ return "No Features Visible";\r
+ }\r
\r
- if(visible==null || visible.size()<1)\r
- return "No Features Visible";\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
- Enumeration en = visible.keys();\r
- String type;\r
- int color;\r
- while( en.hasMoreElements() )\r
+ if (visible.get(type) instanceof GraduatedColor)\r
{\r
- type = en.nextElement().toString();\r
- color = Integer.parseInt( visible.get(type).toString() );\r
- out.append(type + "\t"\r
- + jalview.util.Format.getHexString(\r
- new java.awt.Color(color) )\r
- +"\n");\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
- //Work out which groups are both present and visible\r
- Vector groups = new Vector();\r
- int groupIndex = 0;\r
-\r
- for(int i=0; i<seqs.length; i++)\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
- next = seqs[i].getSequenceFeatures();\r
- if(next!=null)\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
- for(int j=0; j<next.length; j++)\r
- {\r
- if (!visible.containsKey(next[j].type))\r
- continue;\r
+ continue;\r
+ }\r
\r
- if ( next[j].featureGroup != null\r
+ if (next[j].featureGroup != null\r
&& !groups.contains(next[j].featureGroup))\r
- groups.addElement(next[j].featureGroup);\r
- }\r
+ {\r
+ groups.addElement(next[j].featureGroup);\r
}\r
}\r
+ }\r
+ }\r
\r
- String group = null;\r
+ String group = null;\r
+ do\r
+ {\r
\r
- do\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
- if (groups.size() > 0)\r
+ for (int j = 0; j < next.length; j++)\r
{\r
- group = groups.elementAt(groupIndex).toString();\r
- out.append("\nSTARTGROUP\t" + group + "\n");\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
- for (int i = 0; i < seqs.length; i++)\r
- {\r
- next = seqs[i].getSequenceFeatures();\r
- if (next != null)\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
- for (int j = 0; j < next.length; j++)\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
- if (!visible.containsKey(next[j].type))\r
- continue;\r
-\r
- if (group != null && !next[j].featureGroup.equals(group))\r
- continue;\r
+ out.append("<html>");\r
+ }\r
\r
- if(next[j].description==null || next[j].description.equals(""))\r
- out.append(next[j].type+"\t");\r
- else\r
- out.append(next[j].description + "\t");\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
- out.append( seqs[i].getName() + "\t-1\t"\r
- + next[j].begin + "\t"\r
- + next[j].end + "\t"\r
- + next[j].type + "\n"\r
- );\r
+ if (next[j].getDescription().indexOf("</html>") == -1)\r
+ {\r
+ out.append("</html>");\r
+ }\r
}\r
- }\r
- }\r
\r
- if(groups.size()>0)\r
- {\r
- out.append("ENDGROUP\t"+group+"\n");\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
- groupIndex++;\r
}\r
- while(groupIndex < groups.size());\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
- return out.toString();\r
+ if (!featuresGen)\r
+ {\r
+ return "No Features Visible";\r
}\r
\r
- public String printGFFFormat(SequenceI [] seqs, Hashtable visible)\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
- StringBuffer out = new StringBuffer();\r
- SequenceFeature [] next;\r
-\r
- for(int i=0; i<seqs.length; i++)\r
+ if (seqs[i].getSequenceFeatures() != null)\r
{\r
- if(seqs[i].getSequenceFeatures()!=null)\r
+ next = seqs[i].getSequenceFeatures();\r
+ for (int j = 0; j < next.length; j++)\r
{\r
- next = seqs[i].getSequenceFeatures();\r
- for(int j=0; j<next.length; j++)\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
- if(!visible.containsKey(next[j].type))\r
- continue;\r
+ continue;\r
+ }\r
\r
- out.append(seqs[i].getName() + "\t"\r
- + next[j].description + "\t"\r
- + next[j].type + "\t"\r
- + next[j].begin + "\t"\r
- + next[j].end + "\t"\r
- + next[j].score + "\t"\r
- );\r
+ source = next[j].featureGroup;\r
+ if (source == null)\r
+ {\r
+ source = next[j].getDescription();\r
+ }\r
\r
- if(next[j].getValue("STRAND")!=null)\r
- out.append(next[j].getValue("STRAND")+"\t");\r
- else\r
- out.append(".\t");\r
- if(next[j].getValue("FRAME")!=null)\r
- out.append(next[j].getValue("FRAME")+"\n");\r
- else\r
- out.append(".\n");\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
- return out.toString();\r
}\r
\r
- public void parse()\r
- {\r
- //IGNORED\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
- * DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public String print()\r
- {\r
- return "USE printGFFFormat() or printJalviewFormat()";\r
- }\r
}\r