/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9.0b2)
- * Copyright (C) 2015 The Jalview Authors
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
*
* This file is part of Jalview.
*
*/
package jalview.io;
+import jalview.api.FeatureColourI;
import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.DBRefSource;
+import jalview.datamodel.GeneLociI;
+import jalview.datamodel.MappedFeatures;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
-import jalview.io.gff.GffConstants;
-import jalview.util.DBRefUtils;
+import jalview.util.MessageManager;
+import jalview.util.StringUtils;
import jalview.util.UrlLink;
+import jalview.viewmodel.seqfeatures.FeatureRendererModel;
-import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collection;
+import java.util.Comparator;
+import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
*/
public class SequenceAnnotationReport
{
+ private static final String COMMA = ",";
+
+ private static final String ELLIPSIS = "...";
+
+ private static final int MAX_REFS_PER_SOURCE = 4;
+
+ private static final int MAX_SOURCES = 40;
+
+ private static final String[][] PRIMARY_SOURCES = new String[][] {
+ DBRefSource.CODINGDBS, DBRefSource.DNACODINGDBS,
+ DBRefSource.PROTEINDBS };
+
final String linkImageURL;
- public SequenceAnnotationReport(String linkImageURL)
+ /*
+ * Comparator to order DBRefEntry by Source + accession id (case-insensitive),
+ * with 'Primary' sources placed before others, and 'chromosome' first of all
+ */
+ private static Comparator<DBRefEntry> comparator = new Comparator<>()
{
- this.linkImageURL = linkImageURL;
+
+ @Override
+ public int compare(DBRefEntry ref1, DBRefEntry ref2)
+ {
+ if (ref1 instanceof GeneLociI)
+ {
+ return -1;
+ }
+ if (ref2 instanceof GeneLociI)
+ {
+ return 1;
+ }
+ String s1 = ref1.getSource();
+ String s2 = ref2.getSource();
+ boolean s1Primary = isPrimarySource(s1);
+ boolean s2Primary = isPrimarySource(s2);
+ if (s1Primary && !s2Primary)
+ {
+ return -1;
+ }
+ if (!s1Primary && s2Primary)
+ {
+ return 1;
+ }
+ int comp = s1 == null ? -1 : (s2 == null ? 1 : s1
+ .compareToIgnoreCase(s2));
+ if (comp == 0)
+ {
+ String a1 = ref1.getAccessionId();
+ String a2 = ref2.getAccessionId();
+ comp = a1 == null ? -1 : (a2 == null ? 1 : a1
+ .compareToIgnoreCase(a2));
+ }
+ return comp;
+ }
+
+ private boolean isPrimarySource(String source)
+ {
+ for (String[] primary : PRIMARY_SOURCES)
+ {
+ for (String s : primary)
+ {
+ if (source.equals(s))
+ {
+ return true;
+ }
+ }
+ }
+ return false;
+ }
+ };
+
+ public SequenceAnnotationReport(String linkURL)
+ {
+ this.linkImageURL = linkURL;
}
/**
* Append text for the list of features to the tooltip
*
- * @param tooltipText2
- * @param rpos
+ * @param sb
+ * @param residuePos
* @param features
* @param minmax
*/
- public void appendFeatures(final StringBuffer tooltipText2, int rpos,
- List<SequenceFeature> features, Map<String, float[][]> minmax)
+ public void appendFeatures(final StringBuilder sb, int residuePos,
+ List<SequenceFeature> features, FeatureRendererModel fr)
{
- if (features != null)
+ for (SequenceFeature feature : features)
{
- for (SequenceFeature feature : features)
- {
- appendFeature(tooltipText2, rpos, minmax, feature);
- }
+ appendFeature(sb, residuePos, fr, feature, null);
}
}
/**
- * Appends text for one sequence feature to the string buffer
+ * Appends text for mapped features (e.g. CDS feature for peptide or vice versa)
+ *
+ * @param sb
+ * @param residuePos
+ * @param mf
+ * @param fr
+ */
+ public void appendFeatures(StringBuilder sb, int residuePos,
+ MappedFeatures mf, FeatureRendererModel fr)
+ {
+ for (SequenceFeature feature : mf.features)
+ {
+ appendFeature(sb, residuePos, fr, feature, mf);
+ }
+ }
+
+ /**
+ * Appends the feature at rpos to the given buffer
*
* @param sb
* @param rpos
* @param minmax
- * {{min, max}, {min, max}} positional and non-positional feature
- * scores for this type
* @param feature
*/
- void appendFeature(final StringBuffer sb, int rpos,
- Map<String, float[][]> minmax, SequenceFeature feature)
+ void appendFeature(final StringBuilder sb, int rpos,
+ FeatureRendererModel fr, SequenceFeature feature,
+ MappedFeatures mf)
{
- if ("disulfide bond".equals(feature.getType()))
+ if (feature.isContactFeature())
{
if (feature.getBegin() == rpos || feature.getEnd() == rpos)
{
{
sb.append("<br>");
}
- sb.append("disulfide bond ").append(feature.getBegin()).append(":")
- .append(feature.getEnd());
+ sb.append(feature.getType()).append(" ").append(feature.getBegin())
+ .append(":").append(feature.getEnd());
}
+ return;
}
- else
+
+ if (sb.length() > 6)
{
- if (sb.length() > 6)
+ sb.append("<br>");
+ }
+ // TODO: remove this hack to display link only features
+ boolean linkOnly = feature.getValue("linkonly") != null;
+ if (!linkOnly)
+ {
+ sb.append(feature.getType()).append(" ");
+ if (rpos != 0)
{
- sb.append("<br>");
+ // we are marking a positional feature
+ sb.append(feature.begin);
}
- // TODO: remove this hack to display link only features
- boolean linkOnly = feature.getValue("linkonly") != null;
- if (!linkOnly)
+ if (feature.begin != feature.end)
{
- sb.append(feature.getType()).append(" ");
- if (rpos != 0)
- {
- // we are marking a positional feature
- sb.append(feature.begin);
- }
- if (feature.begin != feature.end)
- {
- sb.append(" " + feature.end);
- }
+ sb.append(" ").append(feature.end);
+ }
- if (feature.getDescription() != null
- && !feature.description.equals(feature.getType()))
- {
- String tmpString = feature.getDescription();
- String tmp2up = tmpString.toUpperCase();
- final int startTag = tmp2up.indexOf("<HTML>");
- if (startTag > -1)
- {
- tmpString = tmpString.substring(startTag + 6);
- tmp2up = tmp2up.substring(startTag + 6);
- }
- // TODO strips off </body> but not <body> - is that intended?
- int endTag = tmp2up.indexOf("</BODY>");
- if (endTag > -1)
- {
- tmpString = tmpString.substring(0, endTag);
- tmp2up = tmp2up.substring(0, endTag);
- }
- endTag = tmp2up.indexOf("</HTML>");
- if (endTag > -1)
- {
- tmpString = tmpString.substring(0, endTag);
- }
+ String description = feature.getDescription();
+ if (description != null && !description.equals(feature.getType()))
+ {
+ description = StringUtils.stripHtmlTags(description);
+ sb.append("; ").append(description);
+ }
- if (startTag > -1)
- {
- sb.append("; ").append(tmpString);
- }
- else
- {
- if (tmpString.indexOf("<") > -1 || tmpString.indexOf(">") > -1)
- {
- // The description does not specify html is to
- // be used, so we must remove < > symbols
- tmpString = tmpString.replaceAll("<", "<");
- tmpString = tmpString.replaceAll(">", ">");
- sb.append("; ").append(tmpString);
- }
- else
- {
- sb.append("; ").append(tmpString);
- }
- }
- }
+ if (showScore(feature, fr))
+ {
+ sb.append(" Score=").append(String.valueOf(feature.getScore()));
+ }
+ String status = (String) feature.getValue("status");
+ if (status != null && status.length() > 0)
+ {
+ sb.append("; (").append(status).append(")");
+ }
- /*
- * score should be shown if there is one, and min != max
- * for this feature type (e.g. not all 0)
- */
- if (!Float.isNaN(feature.getScore()))
+ /*
+ * add attribute value if coloured by attribute
+ */
+ if (fr != null)
+ {
+ FeatureColourI fc = fr.getFeatureColours().get(feature.getType());
+ if (fc != null && fc.isColourByAttribute())
{
- float[][] rng = (minmax == null) ? null : minmax.get(feature
- .getType());
- if (rng != null && rng[0] != null && rng[0][0] != rng[0][1])
+ String[] attName = fc.getAttributeName();
+ String attVal = feature.getValueAsString(attName);
+ if (attVal != null)
{
- sb.append(" Score=").append(String.valueOf(feature.getScore()));
+ sb.append("; ").append(String.join(":", attName)).append("=")
+ .append(attVal);
}
}
- String status = (String) feature.getValue("status");
- if (status != null && status.length() > 0)
- {
- sb.append("; (").append(status).append(")");
- }
- String clinSig = (String) feature
- .getValue(GffConstants.CLINICAL_SIGNIFICANCE);
- if (clinSig != null)
+ }
+
+ if (mf != null)
+ {
+ String variants = mf.findProteinVariants(feature);
+ if (!variants.isEmpty())
{
- sb.append("; ").append(clinSig);
+ sb.append(" ").append(variants);
}
}
}
- appendLinks(sb, feature);
+ }
+
+ /**
+ * Answers true if score should be shown, else false. Score is shown if it is
+ * not NaN, and the feature type has a non-trivial min-max score range
+ */
+ boolean showScore(SequenceFeature feature, FeatureRendererModel fr)
+ {
+ if (Float.isNaN(feature.getScore()))
+ {
+ return false;
+ }
+ if (fr == null)
+ {
+ return true;
+ }
+ float[][] minMax = fr.getMinMax().get(feature.getType());
+
+ /*
+ * minMax[0] is the [min, max] score range for positional features
+ */
+ if (minMax == null || minMax[0] == null || minMax[0][0] == minMax[0][1])
+ {
+ return false;
+ }
+ return true;
}
/**
{
try
{
- for (String[] urllink : createLinksFrom(null, urlstring))
+ for (List<String> urllink : createLinksFrom(null, urlstring))
{
sb.append("<br/> <a href=\""
- + urllink[3]
+ + urllink.get(3)
+ "\" target=\""
- + urllink[0]
+ + urllink.get(0)
+ "\">"
- + (urllink[0].toLowerCase().equals(
- urllink[1].toLowerCase()) ? urllink[0]
- : (urllink[0] + ":" + urllink[1]))
- + "</a></br>");
+ + (urllink.get(0).toLowerCase()
+ .equals(urllink.get(1).toLowerCase()) ? urllink
+ .get(0) : (urllink.get(0) + ":" + urllink
+ .get(1))) + "</a></br>");
}
} catch (Exception x)
{
*
* @param seq
* @param link
- * @return String[][] { String[] { link target, link label, dynamic component
- * inserted (if any), url }}
+ * @return Collection< List<String> > { List<String> { link target, link
+ * label, dynamic component inserted (if any), url }}
*/
- String[][] createLinksFrom(SequenceI seq, String link)
+ Collection<List<String>> createLinksFrom(SequenceI seq, String link)
{
- List<String[]> urlSets = new ArrayList<String[]>();
- List<String> uniques = new ArrayList<String>();
+ Map<String, List<String>> urlSets = new LinkedHashMap<>();
UrlLink urlLink = new UrlLink(link);
if (!urlLink.isValid())
{
System.err.println(urlLink.getInvalidMessage());
return null;
}
- if (seq != null && urlLink.isDynamic())
- {
- urlSets.addAll(createDynamicLinks(seq, urlLink, uniques));
- }
- else
- {
- String target = urlLink.getTarget();
- String label = urlLink.getLabel();
- String unq = label + "|" + urlLink.getUrl_prefix();
- if (!uniques.contains(unq))
- {
- uniques.add(unq);
- urlSets.add(new String[] { target, label, null,
- urlLink.getUrl_prefix() });
- }
- }
- return urlSets.toArray(new String[][] {});
- }
+ urlLink.createLinksFromSeq(seq, urlSets);
- /**
- * Formats and returns a list of dynamic href links
- *
- * @param seq
- * @param urlLink
- * @param uniques
- */
- List<String[]> createDynamicLinks(SequenceI seq, UrlLink urlLink,
- List<String> uniques)
- {
- List<String[]> result = new ArrayList<String[]>();
- final String target = urlLink.getTarget();
- final String label = urlLink.getLabel();
-
- // collect matching db-refs
- DBRefEntry[] dbr = DBRefUtils.selectRefs(seq.getDBRefs(),
- new String[] { target });
- // collect id string too
- String id = seq.getName();
- String descr = seq.getDescription();
- if (descr != null && descr.length() < 1)
- {
- descr = null;
- }
- if (dbr != null)
- {
- for (int r = 0; r < dbr.length; r++)
- {
- if (id != null && dbr[r].getAccessionId().equals(id))
- {
- // suppress duplicate link creation for the bare sequence ID
- // string with this link
- id = null;
- }
- // create Bare ID link for this URL
- String[] urls = urlLink.makeUrls(dbr[r].getAccessionId(), true);
- if (urls != null)
- {
- for (int u = 0; u < urls.length; u += 2)
- {
- String unq = urls[u] + "|" + urls[u + 1];
- if (!uniques.contains(unq))
- {
- result.add(new String[] { target, label, urls[u], urls[u + 1] });
- uniques.add(unq);
- }
- }
- }
- }
- }
- if (id != null)
- {
- // create Bare ID link for this URL
- String[] urls = urlLink.makeUrls(id, true);
- if (urls != null)
- {
- for (int u = 0; u < urls.length; u += 2)
- {
- String unq = urls[u] + "|" + urls[u + 1];
- if (!uniques.contains(unq))
- {
- result.add(new String[] { target, label, urls[u], urls[u + 1] });
- uniques.add(unq);
- }
- }
- }
- }
- if (descr != null && urlLink.getRegexReplace() != null)
- {
- // create link for this URL from description only if regex matches
- String[] urls = urlLink.makeUrls(descr, true);
- if (urls != null)
- {
- for (int u = 0; u < urls.length; u += 2)
- {
- String unq = urls[u] + "|" + urls[u + 1];
- if (!uniques.contains(unq))
- {
- result.add(new String[] { target, label, urls[u], urls[u + 1] });
- uniques.add(unq);
- }
- }
- }
- }
- return result;
+ return urlSets.values();
}
- public void createSequenceAnnotationReport(final StringBuffer tip,
+ public void createSequenceAnnotationReport(final StringBuilder tip,
SequenceI sequence, boolean showDbRefs, boolean showNpFeats,
- Map<String, float[][]> minmax)
+ FeatureRendererModel fr)
{
createSequenceAnnotationReport(tip, sequence, showDbRefs, showNpFeats,
- true, minmax);
+ fr, false);
}
- public void createSequenceAnnotationReport(final StringBuffer tip,
+ /**
+ * Builds an html formatted report of sequence details and appends it to the
+ * provided buffer.
+ *
+ * @param sb
+ * buffer to append report to
+ * @param sequence
+ * the sequence the report is for
+ * @param showDbRefs
+ * whether to include database references for the sequence
+ * @param showNpFeats
+ * whether to include non-positional sequence features
+ * @param fr
+ * @param summary
+ * @return
+ */
+ int createSequenceAnnotationReport(final StringBuilder sb,
SequenceI sequence, boolean showDbRefs, boolean showNpFeats,
- boolean tableWrap, Map<String, float[][]> minmax)
+ FeatureRendererModel fr, boolean summary)
{
String tmp;
- tip.append("<i>");
+ sb.append("<i>");
int maxWidth = 0;
if (sequence.getDescription() != null)
{
tmp = sequence.getDescription();
- tip.append("<br>" + tmp);
+ sb.append("<br>").append(tmp);
maxWidth = Math.max(maxWidth, tmp.length());
}
SequenceI ds = sequence;
{
ds = ds.getDatasetSequence();
}
- DBRefEntry[] dbrefs = ds.getDBRefs();
- if (showDbRefs && dbrefs != null)
+
+ if (showDbRefs)
{
- for (int i = 0; i < dbrefs.length; i++)
+ maxWidth = Math.max(maxWidth, appendDbRefs(sb, ds, summary));
+ }
+
+ /*
+ * add non-positional features if wanted
+ */
+ if (showNpFeats)
+ {
+ for (SequenceFeature sf : sequence.getFeatures()
+ .getNonPositionalFeatures())
{
- tip.append("<br>");
- tmp = dbrefs[i].getSource() + " " + dbrefs[i].getAccessionId();
- tip.append(tmp);
- maxWidth = Math.max(maxWidth, tmp.length());
+ int sz = -sb.length();
+ appendFeature(sb, 0, fr, sf, null);
+ sz += sb.length();
+ maxWidth = Math.max(maxWidth, sz);
}
}
+ sb.append("</i>");
+ return maxWidth;
+ }
+
+ /**
+ * A helper method that appends any DBRefs, returning the maximum line length
+ * added
+ *
+ * @param sb
+ * @param ds
+ * @param summary
+ * @return
+ */
+ protected int appendDbRefs(final StringBuilder sb, SequenceI ds,
+ boolean summary)
+ {
+ DBRefEntry[] dbrefs = ds.getDBRefs();
+ if (dbrefs == null)
+ {
+ return 0;
+ }
- // ADD NON POSITIONAL SEQUENCE INFO
- SequenceFeature[] features = sequence.getSequenceFeatures();
- if (showNpFeats && features != null)
+ // note this sorts the refs held on the sequence!
+ Arrays.sort(dbrefs, comparator);
+ boolean ellipsis = false;
+ String source = null;
+ String lastSource = null;
+ int countForSource = 0;
+ int sourceCount = 0;
+ boolean moreSources = false;
+ int maxLineLength = 0;
+ int lineLength = 0;
+
+ for (DBRefEntry ref : dbrefs)
{
- for (int i = 0; i < features.length; i++)
+ source = ref.getSource();
+ if (source == null)
+ {
+ // shouldn't happen
+ continue;
+ }
+ boolean sourceChanged = !source.equals(lastSource);
+ if (sourceChanged)
+ {
+ lineLength = 0;
+ countForSource = 0;
+ sourceCount++;
+ }
+ if (sourceCount > MAX_SOURCES && summary)
{
- if (features[i].begin == 0 && features[i].end == 0)
+ ellipsis = true;
+ moreSources = true;
+ break;
+ }
+ lastSource = source;
+ countForSource++;
+ if (countForSource == 1 || !summary)
+ {
+ sb.append("<br>");
+ }
+ if (countForSource <= MAX_REFS_PER_SOURCE || !summary)
+ {
+ String accessionId = ref.getAccessionId();
+ lineLength += accessionId.length() + 1;
+ if (countForSource > 1 && summary)
{
- int sz = -tip.length();
- List<SequenceFeature> tfeat = new ArrayList<SequenceFeature>();
- tfeat.add(features[i]);
- appendFeatures(tip, 0, tfeat, minmax);
- sz += tip.length();
- maxWidth = Math.max(maxWidth, sz);
+ sb.append(", ").append(accessionId);
+ lineLength++;
}
+ else
+ {
+ sb.append(source).append(" ").append(accessionId);
+ lineLength += source.length();
+ }
+ maxLineLength = Math.max(maxLineLength, lineLength);
+ }
+ if (countForSource == MAX_REFS_PER_SOURCE && summary)
+ {
+ sb.append(COMMA).append(ELLIPSIS);
+ ellipsis = true;
}
}
-
- if (tableWrap && maxWidth > 60)
+ if (moreSources)
+ {
+ sb.append("<br>").append(source).append(COMMA).append(ELLIPSIS);
+ }
+ if (ellipsis)
{
- tip.insert(0, "<table width=350 border=0><tr><td><i>");
- tip.append("</i></td></tr></table>");
+ sb.append("<br>(");
+ sb.append(MessageManager.getString("label.output_seq_details"));
+ sb.append(")");
}
+ return maxLineLength;
+ }
+
+ public void createTooltipAnnotationReport(final StringBuilder tip,
+ SequenceI sequence, boolean showDbRefs, boolean showNpFeats,
+ FeatureRendererModel fr)
+ {
+ int maxWidth = createSequenceAnnotationReport(tip, sequence,
+ showDbRefs, showNpFeats, fr, true);
+
+ if (maxWidth > 60)
+ {
+ // ? not sure this serves any useful purpose
+ // tip.insert(0, "<table width=350 border=0><tr><td>");
+ // tip.append("</td></tr></table>");
+ }
}
}