+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.io.gff;
import jalview.analysis.SequenceIdMatcher;
import jalview.datamodel.SequenceDummy;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
+import jalview.io.FeaturesFile;
import jalview.util.MapList;
import jalview.util.StringUtils;
* restrict from range to make them match up
* it's kind of arbitrary which end we truncate - here it is the end
*/
- System.err.print("Truncating mapping from " + Arrays.toString(from)
- + " to ");
+ System.err.print(
+ "Truncating mapping from " + Arrays.toString(from) + " to ");
if (from[1] > from[0])
{
from[1] -= fromOverlap / toRatio;
/*
* restrict to range to make them match up
*/
- System.err.print("Truncating mapping to " + Arrays.toString(to)
- + " to ");
+ System.err.print(
+ "Truncating mapping to " + Arrays.toString(to) + " to ");
if (to[1] > to[0])
{
to[1] -= fromOverlap / fromRatio;
/**
* Parses the input line to a map of name / value(s) pairs. For example the
* line <br>
- * Notes=Fe-S;Method=manual curation, prediction; source = Pfam; Notes = Metal <br>
+ * Notes=Fe-S;Method=manual curation, prediction; source = Pfam; Notes = Metal
+ * <br>
* if parsed with delimiter=";" and separators {' ', '='} <br>
* would return a map with { Notes={Fe=S, Metal}, Method={manual curation,
* prediction}, source={Pfam}} <br>
String namesDelimiter, char nameValueSeparator,
String valuesDelimiter)
{
- Map<String, List<String>> map = new HashMap<String, List<String>>();
+ Map<String, List<String>> map = new HashMap<>();
if (text == null || text.trim().length() == 0)
{
return map;
List<String> vals = map.get(key);
if (vals == null)
{
- vals = new ArrayList<String>();
+ vals = new ArrayList<>();
map.put(key, vals);
}
for (String val : values.split(valuesDelimiter))
protected SequenceFeature buildSequenceFeature(String[] gff,
Map<String, List<String>> attributes)
{
+ return buildSequenceFeature(gff, TYPE_COL, gff[SOURCE_COL], attributes);
+ }
+
+ /**
+ * @param gff
+ * @param typeColumn
+ * @param group
+ * @param attributes
+ * @return
+ */
+ protected SequenceFeature buildSequenceFeature(String[] gff,
+ int typeColumn, String group, Map<String, List<String>> attributes)
+ {
try
{
int start = Integer.parseInt(gff[START_COL]);
int end = Integer.parseInt(gff[END_COL]);
- float score = Float.NaN;
+
+ /*
+ * default 'score' is 0 rather than Float.NaN - see JAL-2554
+ */
+ float score = 0f;
try
{
score = Float.parseFloat(gff[SCORE_COL]);
} catch (NumberFormatException nfe)
{
- // e.g. '.' - leave as NaN to indicate no score
+ // e.g. '.' - leave as zero
}
- SequenceFeature sf = new SequenceFeature(gff[TYPE_COL],
- gff[SOURCE_COL], start, end, score, gff[SOURCE_COL]);
+ SequenceFeature sf = new SequenceFeature(gff[typeColumn],
+ gff[SOURCE_COL], start, end, score, group);
sf.setStrand(gff[STRAND_COL]);
if (attributes != null)
{
/*
- * save 'raw' column 9 to allow roundtrip output as input
- */
- sf.setAttributes(gff[ATTRIBUTES_COL]);
-
- /*
* Add attributes in column 9 to the sequence feature's
- * 'otherData' table; use Note as a best proxy for description
+ * 'otherData' table; use Note as a best proxy for description;
+ * decode any encoded comma, equals, semi-colon as per GFF3 spec
*/
for (Entry<String, List<String>> attr : attributes.entrySet())
{
- String values = StringUtils.listToDelimitedString(
- attr.getValue(), ",");
- sf.setValue(attr.getKey(), values);
- if (NOTE.equals(attr.getKey()))
+ String key = attr.getKey();
+ List<String> value = attr.getValue();
+ if (key.startsWith(FeaturesFile.MAP_ATTRIBUTE_PREFIX))
+ {
+ /*
+ * e.g. jvmap_CSQ={ALLELE_NUM=1,CDS_position=249,Codons=caG/caT}
+ */
+ String trueKey = key
+ .substring(FeaturesFile.MAP_ATTRIBUTE_PREFIX.length());
+ if (trueKey.isEmpty() || value.isEmpty()
+ || !value.get(0).startsWith("{")
+ || !value.get(value.size() - 1).endsWith("}"))
+ {
+ System.err.println("Malformed GFF data '" + value.toString()
+ + "' for " + key);
+ continue;
+ }
+ Map<String, String> values = new HashMap<>();
+ for (String entry : value)
+ {
+ if (entry.startsWith("{"))
+ {
+ entry = entry.substring(1);
+ }
+ if (entry.endsWith("}"))
+ {
+ entry = entry.substring(0, entry.length() - 1);
+ }
+ String[] fields = entry.split(",");
+ for (String field : fields)
+ {
+ String[] keyValue = field.split("=");
+ if (keyValue.length == 2)
+ {
+ String theKey = StringUtils.urlDecode(keyValue[0],
+ GFF_ENCODABLE);
+ String theValue = StringUtils.urlDecode(keyValue[1],
+ GFF_ENCODABLE);
+ values.put(theKey, theValue);
+ }
+ }
+ }
+ sf.setValue(trueKey, values);
+ }
+ else
{
- sf.setDescription(values);
+ String values = StringUtils
+ .listToDelimitedString(value, ",");
+ values = StringUtils.urlDecode(values, GFF_ENCODABLE);
+ sf.setValue(key, values);
+ if (NOTE.equals(key))
+ {
+ sf.setDescription(values);
+ }
}
}
}
* @param toSeq
* @return
*/
- protected AlignedCodonFrame getMapping(AlignmentI align, SequenceI fromSeq, SequenceI toSeq)
+ protected AlignedCodonFrame getMapping(AlignmentI align,
+ SequenceI fromSeq, SequenceI toSeq)
{
AlignedCodonFrame acf = align.getMapping(fromSeq, toSeq);
if (acf == null)
git://source.jalview.org / jalview.git / blobdiff