/*\r
- * Jalview - A Sequence Alignment Editor and Viewer\r
- * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
- *\r
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.4)\r
+ * Copyright (C) 2008 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
+ * \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
+ * \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
import jalview.datamodel.*;\r
import jalview.schemes.*;\r
+import jalview.util.Format;\r
\r
/**\r
- * Parse and create Jalview Features files\r
- * Detects GFF format features files and parses.\r
- * Does not implement standard print() - call specific printFeatures or printGFF.\r
- * Uses AlignmentI.findSequence(String id) to find the sequence object for the features annotation - this normally works on an exact match.\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\r
- extends AlignFile\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
* Creates a new FeaturesFile object.\r
- *\r
- * @param inFile DOCUMENT ME!\r
- * @param type DOCUMENT ME!\r
- *\r
- * @throws IOException DOCUMENT ME!\r
+ * \r
+ * @param inFile\r
+ * DOCUMENT ME!\r
+ * @param type\r
+ * DOCUMENT ME!\r
+ * \r
+ * @throws IOException\r
+ * DOCUMENT ME!\r
*/\r
- public FeaturesFile(String inFile, String type)\r
- throws IOException\r
+ public FeaturesFile(String inFile, String type) throws IOException\r
{\r
super(inFile, type);\r
}\r
\r
+ public FeaturesFile(FileParse source) throws IOException\r
+ {\r
+ super(source);\r
+ }\r
+\r
/**\r
- * The Application can render HTML, but the applet will\r
- * remove HTML tags and replace links with %LINK%\r
- * Both need to read links in HTML however\r
- *\r
- * @throws IOException DOCUMENT ME!\r
+ * The Application can render HTML, but the applet will remove HTML tags and\r
+ * replace links with %LINK% Both need to read links in HTML however\r
+ * \r
+ * @throws IOException\r
+ * DOCUMENT ME!\r
*/\r
- public boolean parse(AlignmentI align,\r
- Hashtable colours,\r
- boolean removeHTML)\r
+ public boolean parse(AlignmentI align, Hashtable colours,\r
+ boolean removeHTML)\r
{\r
return parse(align, colours, null, removeHTML);\r
}\r
\r
/**\r
- * The Application can render HTML, but the applet will\r
- * remove HTML tags and replace links with %LINK%\r
- * Both need to read links in HTML however\r
- *\r
- * @throws IOException DOCUMENT ME!\r
+ * The Application can render HTML, but the applet will remove HTML tags and\r
+ * replace links with %LINK% Both need to read links in HTML however\r
+ * \r
+ * @throws IOException\r
+ * DOCUMENT ME!\r
*/\r
- public boolean parse(AlignmentI align,\r
- Hashtable colours,\r
- Hashtable featureLink,\r
- boolean removeHTML)\r
+ public boolean parse(AlignmentI align, Hashtable colours,\r
+ Hashtable featureLink, boolean removeHTML)\r
{\r
String line = null;\r
try\r
\r
boolean GFFFile = true;\r
\r
- while ( (line = nextLine()) != null)\r
+ while ((line = nextLine()) != null)\r
{\r
if (line.startsWith("#"))\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
+ // 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
- UserColourScheme ucs = new UserColourScheme(st.nextToken());\r
- colours.put(type, ucs.findColour('A'));\r
+ Object colour = null;\r
+ String colscheme = st.nextToken();\r
+ if (colscheme.indexOf("|") > -1)\r
+ {\r
+ // Parse '|' separated graduated colourscheme fields:\r
+ // mincolour|maxcolour|[absolute|]minvalue|maxvalue|thresholdtype|thresholdvalue\r
+ // first four are required.\r
+ // first two are hexadecimal or word equivalent colours.\r
+ // second 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
+ String mincol = gcol.nextToken(), maxcol = gcol.nextToken();\r
+ String abso = gcol\r
+ .nextToken(), minval, maxval;\r
+ if (abso.toLowerCase().indexOf("abso")!=0) {\r
+ minval = abso;\r
+ abso = null;\r
+ } else {\r
+ minval = gcol.nextToken();\r
+ }\r
+ maxval = gcol.nextToken();\r
+ // set defaults\r
+ int threshtype = AnnotationColourGradient.NO_THRESHOLD;\r
+ float min=Float.MIN_VALUE,max=Float.MAX_VALUE,threshval=Float.NaN;\r
+ try\r
+ {\r
+ if (minval.length()>0) { \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 + ") - did you misspell 'auto' for the optional automatic colour switch ?");\r
+ e.printStackTrace();\r
+ }\r
+ try\r
+ {\r
+ if (maxval.length()>0) { \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
+ try\r
+ {\r
+ colour = new jalview.schemes.GraduatedColor(\r
+ new UserColourScheme(mincol).findColour('A'),\r
+ new UserColourScheme(maxcol).findColour('A'),\r
+ min, 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).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
+ tval = gcol.nextToken();\r
+ try\r
+ {\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);\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
}\r
featureLink.put(type, link);\r
}\r
-\r
}\r
continue;\r
}\r
-\r
+ String seqId = "";\r
while (st.hasMoreElements())\r
{\r
\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
+ seqId = token = st.nextToken();\r
+ seq = align.findName(seqId, true);\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
- start = Integer.parseInt(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
+ start = 0;\r
}\r
- try {\r
- end = Integer.parseInt(st.nextToken());\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
- catch (NumberFormatException ex)\r
+ // TODO: decide if non positional feature assertion for input data\r
+ // where end==0 is generally valid\r
+ if (end == 0)\r
{\r
- end=-1;\r
- } \r
+ // treat as non-positional feature, regardless.\r
+ start = 0;\r
+ }\r
try\r
{\r
score = new Float(st.nextToken()).floatValue();\r
- }\r
- catch (NumberFormatException ex)\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
{\r
sf.setValue("STRAND", st.nextToken());\r
sf.setValue("FRAME", st.nextToken());\r
+ } catch (Exception ex)\r
+ {\r
}\r
- catch (Exception ex)\r
- {}\r
\r
if (st.hasMoreTokens())\r
{\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
-\r
+ while ((seq = align.findName(seq, seqId, true)) != null)\r
+ {\r
+ seq.addSequenceFeature(new SequenceFeature(sf));\r
+ }\r
break;\r
}\r
}\r
}\r
if (!st.hasMoreTokens())\r
{\r
- System.err.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 quietly.\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
+\r
token = st.nextToken();\r
- \r
+\r
if (!token.equals("ID_NOT_SPECIFIED"))\r
{\r
- seq = align.findName(token);\r
+ seq = align.findName(seqId = token, true);\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
- }\r
- catch (NumberFormatException ex)\r
+ } catch (NumberFormatException ex)\r
{\r
seq = null;\r
}\r
UserColourScheme ucs = new UserColourScheme(type);\r
colours.put(type, ucs.findColour('A'));\r
}\r
-\r
sf = new SequenceFeature(type, desc, "", start, end, featureGroup);\r
-\r
- seq.addSequenceFeature(sf);\r
-\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
\r
parseDescriptionHTML(sf, removeHTML);\r
\r
- //If we got here, its not a GFFFile\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
- }\r
- catch (Exception ex)\r
+ } catch (Exception ex)\r
{\r
System.out.println(line);\r
System.out.println("Error parsing feature file: " + ex + "\n" + line);\r
return;\r
}\r
\r
- if (removeHTML && sf.getDescription().toUpperCase().indexOf("<HTML>") == -1)\r
+ if (removeHTML\r
+ && sf.getDescription().toUpperCase().indexOf("<HTML>") == -1)\r
{\r
removeHTML = false;\r
}\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
+ * generate a features file for seqs\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,\r
- Hashtable visible)\r
+ public String printJalviewFormat(SequenceI[] seqs, Hashtable visible)\r
+ {\r
+ return printJalviewFormat(seqs, visible, 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
+ * @return features file contents\r
+ */\r
+ public String printJalviewFormat(SequenceI[] seqs, Hashtable visible,\r
+ boolean visOnly)\r
{\r
StringBuffer out = new StringBuffer();\r
SequenceFeature[] next;\r
\r
- if (visible == null || visible.size() < 1)\r
+ if (visOnly && (visible == null || visible.size() < 1))\r
{\r
return "No Features Visible";\r
}\r
-\r
- Enumeration en = visible.keys();\r
- String type;\r
- int color;\r
- while (en.hasMoreElements())\r
+ if (visible != null && visOnly)\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
- }\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
- //Work out which groups are both present and visible\r
+ if (visible.get(type) instanceof GraduatedColor)\r
+ {\r
+ GraduatedColor gc = (GraduatedColor) visible.get(type);\r
+ color = Format.getHexString(gc.getMinColor()) + "|"\r
+ + Format.getHexString(gc.getMaxColor()) +\r
+ (gc.isAutoScale() ? "|" : "|abso|")+ gc.getMin() + "|" + 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\r
+ if (visible.get(type) instanceof java.awt.Color) {\r
+ color = Format.getHexString((java.awt.Color)visible.get(type));\r
+ } else {\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 + "\t" + color + "\n");\r
+ }\r
+ }\r
+ // Work out which groups are both present and visible\r
Vector groups = new Vector();\r
int groupIndex = 0;\r
\r
{\r
for (int j = 0; j < next.length; j++)\r
{\r
- if (!visible.containsKey(next[j].type))\r
+ if (visOnly && !visible.containsKey(next[j].type))\r
{\r
continue;\r
}\r
\r
if (next[j].featureGroup != null\r
- && !groups.contains(next[j].featureGroup))\r
+ && !groups.contains(next[j].featureGroup))\r
{\r
groups.addElement(next[j].featureGroup);\r
}\r
{\r
for (int j = 0; j < next.length; j++)\r
{\r
- if (!visible.containsKey(next[j].type))\r
+ if (visOnly && !visible.containsKey(next[j].type))\r
{\r
continue;\r
}\r
\r
if (group != null\r
- && (next[j].featureGroup == null\r
- || !next[j].featureGroup.equals(group))\r
- )\r
+ && (next[j].featureGroup == null || !next[j].featureGroup\r
+ .equals(group)))\r
{\r
continue;\r
}\r
continue;\r
}\r
\r
- if (next[j].description == null || next[j].description.equals(""))\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
+ && next[j].getDescription().indexOf("<html>") == -1)\r
{\r
out.append("<html>");\r
}\r
\r
if (next[j].description.indexOf(href) == -1)\r
{\r
- out.append("<a href=\""\r
- + href\r
- + "\">"\r
- + label\r
- + "</a>");\r
+ out\r
+ .append("<a href=\"" + href + "\">" + label\r
+ + "</a>");\r
}\r
}\r
\r
out.append("\t");\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
+ out.append(seqs[i].getName() + "\t-1\t" + next[j].begin + "\t"\r
+ + next[j].end + "\t" + next[j].type + ((visible.get(next[j].type) instanceof GraduatedColor) ? "\t"+next[j].score+"\n" : "\n"));\r
}\r
}\r
}\r
break;\r
}\r
\r
- }\r
- while (groupIndex < groups.size() + 1);\r
+ } while (groupIndex < groups.size() + 1);\r
\r
return out.toString();\r
}\r
\r
public String printGFFFormat(SequenceI[] seqs, Hashtable visible)\r
{\r
+ return printGFFFormat(seqs, visible, true);\r
+ }\r
+\r
+ public String printGFFFormat(SequenceI[] seqs, Hashtable visible,\r
+ boolean visOnly)\r
+ {\r
StringBuffer out = new StringBuffer();\r
SequenceFeature[] next;\r
String source;\r
next = seqs[i].getSequenceFeatures();\r
for (int j = 0; j < next.length; j++)\r
{\r
- if (!visible.containsKey(next[j].type))\r
+ if (visOnly && visible != null\r
+ && !visible.containsKey(next[j].type))\r
{\r
continue;\r
}\r
source = next[j].getDescription();\r
}\r
\r
- out.append(seqs[i].getName() + "\t"\r
- + source + "\t"\r
- + next[j].type + "\t"\r
- + next[j].begin + "\t"\r
- + next[j].end + "\t"\r
- + next[j].score + "\t"\r
- );\r
+ out.append(seqs[i].getName() + "\t" + source + "\t"\r
+ + next[j].type + "\t" + next[j].begin + "\t"\r
+ + next[j].end + "\t" + next[j].score + "\t");\r
\r
if (next[j].getValue("STRAND") != null)\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
+ // IGNORED\r
}\r
\r
/**\r
- * DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\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