Examples with Position org.dishevelled.bio.assembly.gfa2.Position used on opensource projects

Example 1 with Position

use of org.dishevelled.bio.assembly.gfa2.Position in project webanno by webanno.

the class AgreementUtils method configurationSetsWithItemsToCsv.

private static void configurationSetsWithItemsToCsv(CSVPrinter aOut, AgreementResult aAgreement, List<ConfigurationSet> aSets) throws IOException {
    List<String> headers = new ArrayList<>(asList("Type", "Collection", "Document", "Layer", "Feature", "Position"));
    headers.addAll(aAgreement.getCasGroupIds());
    aOut.printRecord(headers);
    int i = 0;
    for (ICodingAnnotationItem item : aAgreement.getStudy().getItems()) {
        Position pos = aSets.get(i).getPosition();
        List<String> values = new ArrayList<>();
        values.add(pos.getClass().getSimpleName());
        values.add(pos.getCollectionId());
        values.add(pos.getDocumentId());
        values.add(pos.getType());
        values.add(aAgreement.getFeature());
        values.add(aSets.get(i).getPosition().toMinimalString());
        for (IAnnotationUnit unit : item.getUnits()) {
            values.add(String.valueOf(unit.getCategory()));
        }
        aOut.printRecord(values);
        i++;
    }
}

Example 2 with Position

use of org.dishevelled.bio.assembly.gfa2.Position in project dishevelled-bio by heuermh.

the class Gfa1ToGfa2 method call.

@Override
public Integer call() throws Exception {
    PrintWriter writer = null;
    try {
        writer = writer(outputGfa2File);
        final PrintWriter w = writer;
        Gfa1Reader.stream(reader(inputGfa1File), new Gfa1Adapter() {

            @Override
            public boolean header(final Header header) {
                // convert VN:Z:1.0 to VN:Z:2.0 annotation if present
                if (header.getAnnotations().containsKey("VN")) {
                    if (!"1.0".equals(header.getAnnotations().get("VN").getValue())) {
                        throw new RuntimeException("cannot convert input as GFA 1.0, was " + header.getAnnotations().get("VN").getValue());
                    }
                    Map<String, Annotation> annotations = new HashMap<String, Annotation>();
                    annotations.put("VN", new Annotation("VN", "Z", "2.0"));
                    for (Annotation annotation : header.getAnnotations().values()) {
                        if (!"VN".equals(annotation.getName())) {
                            annotations.put(annotation.getName(), annotation);
                        }
                    }
                    Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Header(annotations), w);
                } else {
                    Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Header(header.getAnnotations()), w);
                }
                return true;
            }

            @Override
            public boolean segment(final Segment segment) {
                if (segment.getSequence() != null) {
                    Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Segment(segment.getId(), segment.getSequence().length(), segment.getSequence(), segment.getAnnotations()), w);
                } else if (segment.getAnnotations().containsKey("LN")) {
                    Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Segment(segment.getId(), Integer.parseInt(segment.getAnnotations().get("LN").getValue()), segment.getSequence(), segment.getAnnotations()), w);
                } else {
                    Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Segment(segment.getId(), 0, segment.getSequence(), segment.getAnnotations()), w);
                }
                return true;
            }

            @Override
            public boolean link(final Link link) {
                Position unknown = new Position(0, false);
                Alignment alignment = link.getOverlap() == null ? null : Alignment.valueOf(link.getOverlap());
                Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Edge(null, toGfa2Reference(link.getSource()), toGfa2Reference(link.getTarget()), unknown, unknown, unknown, unknown, alignment, link.getAnnotations()), w);
                return true;
            }

            @Override
            public boolean containment(final Containment containment) {
                Position unknown = new Position(0, false);
                Position targetStart = new Position(containment.getPosition(), false);
                Alignment alignment = containment.getOverlap() == null ? null : Alignment.valueOf(containment.getOverlap());
                Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Edge(null, toGfa2Reference(containment.getContainer()), toGfa2Reference(containment.getContained()), unknown, unknown, targetStart, unknown, alignment, containment.getAnnotations()), w);
                return true;
            }

            @Override
            public boolean path(final Path path) {
                Gfa2Writer.write(new org.dishevelled.bio.assembly.gfa2.Path(path.getName(), toGfa2References(path.getSegments()), path.getAnnotations()), w);
                return true;
            }
        });
        return 0;
    } finally {
        try {
            writer.close();
        } catch (Exception e) {
        // empty
        }
    }
}

Example 3 with Position

use of org.dishevelled.bio.assembly.gfa2.Position in project webanno by webanno.

the class MergeCas method reMergeCas.

/**
 * Using {@code DiffResult}, determine the annotations to be deleted from the randomly generated
 * MergeCase. The initial Merge CAs is stored under a name {@code CurationPanel#CURATION_USER}.
 * <p>
 * Any similar annotations stacked in a {@code CasDiff2.Position} will be assumed a difference
 * <p>
 * Any two annotation with different value will be assumed a difference
 * <p>
 * Any non stacked empty/null annotations are assumed agreement
 * <p>
 * Any non stacked annotations with similar values for each of the features are assumed
 * agreement
 * <p>
 * Any two link mode / slotable annotations which agree on the base features are assumed
 * agreement
 *
 * @param aDiff
 *            the {@code CasDiff2.DiffResult}
 * @param aJCases
 *            a map of{@code JCas}s for each users and the random merge
 * @return the actual merge {@code JCas}
 */
public static JCas reMergeCas(DiffResult aDiff, Map<String, JCas> aJCases) {
    Set<FeatureStructure> slotFeaturesToReset = new HashSet<>();
    Set<FeatureStructure> annotationsToDelete = new HashSet<>();
    Set<String> users = aJCases.keySet();
    for (Position position : aDiff.getPositions()) {
        Map<String, List<FeatureStructure>> annosPerUser = new HashMap<>();
        ConfigurationSet cfgs = aDiff.getConfigurtionSet(position);
        if (cfgs.getConfigurations(WebAnnoConst.CURATION_USER).isEmpty()) {
            // annotations
            continue;
        }
        AnnotationFS mergeAnno = (AnnotationFS) cfgs.getConfigurations(WebAnnoConst.CURATION_USER).get(0).getFs(WebAnnoConst.CURATION_USER, aJCases);
        // Get Annotations per user in this position
        getAllAnnosOnPosition(aJCases, annosPerUser, users, mergeAnno);
        for (FeatureStructure mergeFs : annosPerUser.get(WebAnnoConst.CURATION_USER)) {
            // incomplete annotations
            if (aJCases.size() != annosPerUser.size()) {
                annotationsToDelete.add(mergeFs);
            } else // agreed and not stacked
            if (isAgree(mergeFs, annosPerUser)) {
                Type t = mergeFs.getType();
                Feature sourceFeat = t.getFeatureByBaseName(WebAnnoConst.FEAT_REL_SOURCE);
                Feature targetFeat = t.getFeatureByBaseName(WebAnnoConst.FEAT_REL_TARGET);
                // Is this a relation?
                if (sourceFeat != null && targetFeat != null) {
                    AnnotationFS source = (AnnotationFS) mergeFs.getFeatureValue(sourceFeat);
                    AnnotationFS target = (AnnotationFS) mergeFs.getFeatureValue(targetFeat);
                    // all span anno on this source positions
                    Map<String, List<FeatureStructure>> sourceAnnosPerUser = new HashMap<>();
                    // all span anno on this target positions
                    Map<String, List<FeatureStructure>> targetAnnosPerUser = new HashMap<>();
                    getAllAnnosOnPosition(aJCases, sourceAnnosPerUser, users, source);
                    getAllAnnosOnPosition(aJCases, targetAnnosPerUser, users, target);
                    if (isAgree(source, sourceAnnosPerUser) && isAgree(target, targetAnnosPerUser)) {
                        slotFeaturesToReset.add(mergeFs);
                    } else {
                        annotationsToDelete.add(mergeFs);
                    }
                } else {
                    slotFeaturesToReset.add(mergeFs);
                }
            } else // disagree or stacked annotations
            {
                annotationsToDelete.add(mergeFs);
            }
        // remove dangling rels
        // setDanglingRelToDel(aJCases.get(CurationPanel.CURATION_USER),
        // mergeFs, annotationsToDelete);
        }
    }
    // remove annotations that do not agree or are a stacked ones
    for (FeatureStructure fs : annotationsToDelete) {
        if (!slotFeaturesToReset.contains(fs)) {
            JCas mergeCas = aJCases.get(WebAnnoConst.CURATION_USER);
            // Check if this difference is on POS, STEM and LEMMA (so remove from the token too)
            Type type = fs.getType();
            int fsBegin = ((AnnotationFS) fs).getBegin();
            int fsEnd = ((AnnotationFS) fs).getEnd();
            if (type.getName().equals(POS.class.getName())) {
                Token t = JCasUtil.selectCovered(mergeCas, Token.class, fsBegin, fsEnd).get(0);
                t.setPos(null);
            }
            if (type.getName().equals(Stem.class.getName())) {
                Token t = JCasUtil.selectCovered(mergeCas, Token.class, fsBegin, fsEnd).get(0);
                t.setStem(null);
            }
            if (type.getName().equals(Lemma.class.getName())) {
                Token t = JCasUtil.selectCovered(mergeCas, Token.class, fsBegin, fsEnd).get(0);
                t.setLemma(null);
            }
            if (type.getName().equals(MorphologicalFeatures.class.getName())) {
                Token t = JCasUtil.selectCovered(mergeCas, Token.class, fsBegin, fsEnd).get(0);
                t.setMorph(null);
            }
            mergeCas.removeFsFromIndexes(fs);
        }
    }
    // if slot bearing annotation, clean
    for (FeatureStructure baseFs : slotFeaturesToReset) {
        for (Feature roleFeature : baseFs.getType().getFeatures()) {
            if (isLinkMode(baseFs, roleFeature)) {
                // FeatureStructure roleFs = baseFs.getFeatureValue(f);
                ArrayFS roleFss = (ArrayFS) WebAnnoCasUtil.getFeatureFS(baseFs, roleFeature.getShortName());
                if (roleFss == null) {
                    continue;
                }
                Map<String, ArrayFS> roleAnnosPerUser = new HashMap<>();
                setAllRoleAnnosOnPosition(aJCases, roleAnnosPerUser, users, baseFs, roleFeature);
                List<FeatureStructure> linkFSes = new LinkedList<>(Arrays.asList(roleFss.toArray()));
                for (FeatureStructure roleFs : roleFss.toArray()) {
                    if (isRoleAgree(roleFs, roleAnnosPerUser)) {
                        for (Feature targetFeature : roleFs.getType().getFeatures()) {
                            if (isBasicFeature(targetFeature)) {
                                continue;
                            }
                            if (!targetFeature.getShortName().equals("target")) {
                                continue;
                            }
                            AnnotationFS targetFs = (AnnotationFS) roleFs.getFeatureValue(targetFeature);
                            if (targetFs == null) {
                                continue;
                            }
                            Map<String, List<FeatureStructure>> targetAnnosPerUser = new HashMap<>();
                            getAllAnnosOnPosition(aJCases, targetAnnosPerUser, users, targetFs);
                            // do not agree on targets
                            if (!isAgree(targetFs, targetAnnosPerUser)) {
                                linkFSes.remove(roleFs);
                            }
                        }
                    } else // do not agree on some role features
                    {
                        linkFSes.remove(roleFs);
                    }
                }
                ArrayFS array = baseFs.getCAS().createArrayFS(linkFSes.size());
                array.copyFromArray(linkFSes.toArray(new FeatureStructure[linkFSes.size()]), 0, 0, linkFSes.size());
                baseFs.setFeatureValue(roleFeature, array);
            }
        }
    }
    return aJCases.get(WebAnnoConst.CURATION_USER);
}

Example 4 with Position

use of org.dishevelled.bio.assembly.gfa2.Position in project webanno by webanno.

the class AgreementUtils method makeStudy.

private static AgreementResult makeStudy(DiffResult aDiff, Collection<String> aUsers, String aType, String aFeature, boolean aExcludeIncomplete, boolean aNullLabelsAsEmpty, Map<String, List<JCas>> aCasMap) {
    List<String> users = new ArrayList<>(aUsers);
    Collections.sort(users);
    List<ConfigurationSet> completeSets = new ArrayList<>();
    List<ConfigurationSet> setsWithDifferences = new ArrayList<>();
    List<ConfigurationSet> incompleteSetsByPosition = new ArrayList<>();
    List<ConfigurationSet> incompleteSetsByLabel = new ArrayList<>();
    List<ConfigurationSet> pluralitySets = new ArrayList<>();
    List<ConfigurationSet> irrelevantSets = new ArrayList<>();
    CodingAnnotationStudy study = new CodingAnnotationStudy(users.size());
    // Check if the feature we are looking at is a primitive feature or a link feature
    // We do this by looking it up in the first available CAS. Mind that at this point all
    // CASes should have exactly the same typesystem.
    JCas someCas = findSomeCas(aCasMap);
    if (someCas == null) {
        // Well... there is NOTHING here!
        // All positions are irrelevant
        aDiff.getPositions().forEach(p -> irrelevantSets.add(aDiff.getConfigurtionSet(p)));
        return new AgreementResult(aType, aFeature, aDiff, study, users, completeSets, irrelevantSets, setsWithDifferences, incompleteSetsByPosition, incompleteSetsByLabel, pluralitySets, aExcludeIncomplete);
    }
    TypeSystem ts = someCas.getTypeSystem();
    // We should just do the right thing here which is: do nothing
    if (ts.getType(aType) == null) {
        // All positions are irrelevant
        aDiff.getPositions().forEach(p -> irrelevantSets.add(aDiff.getConfigurtionSet(p)));
        return new AgreementResult(aType, aFeature, aDiff, study, users, completeSets, irrelevantSets, setsWithDifferences, incompleteSetsByPosition, incompleteSetsByLabel, pluralitySets, aExcludeIncomplete);
    }
    // Check that the feature really exists instead of just getting a NPE later
    if (ts.getType(aType).getFeatureByBaseName(aFeature) == null) {
        throw new IllegalArgumentException("Type [" + aType + "] has no feature called [" + aFeature + "]");
    }
    boolean isPrimitiveFeature = ts.getType(aType).getFeatureByBaseName(aFeature).getRange().isPrimitive();
    nextPosition: for (Position p : aDiff.getPositions()) {
        ConfigurationSet cfgSet = aDiff.getConfigurtionSet(p);
        // Only calculate agreement for the given layer
        if (!cfgSet.getPosition().getType().equals(aType)) {
            // We don't even consider these as irrelevant, they are just filtered out
            continue;
        }
        // If the feature on a position is set, then it is a subposition
        boolean isSubPosition = p.getFeature() != null;
        // this is an inverted XOR!
        if (!(isPrimitiveFeature ^ isSubPosition)) {
            irrelevantSets.add(cfgSet);
            continue;
        }
        // feature
        if (isSubPosition && !aFeature.equals(cfgSet.getPosition().getFeature())) {
            irrelevantSets.add(cfgSet);
            continue nextPosition;
        }
        // If non of the current users has made any annotation at this position, then skip it
        if (users.stream().filter(u -> cfgSet.getCasGroupIds().contains(u)).count() == 0) {
            irrelevantSets.add(cfgSet);
            continue nextPosition;
        }
        Object[] values = new Object[users.size()];
        int i = 0;
        for (String user : users) {
            // this configuration set.
            if (!cfgSet.getCasGroupIds().contains(user)) {
                incompleteSetsByPosition.add(cfgSet);
                if (aExcludeIncomplete) {
                    // Record as incomplete
                    continue nextPosition;
                } else {
                    // Record as missing value
                    values[i] = null;
                    i++;
                    continue;
                }
            }
            // Make sure a single user didn't do multiple alternative annotations at a single
            // position. So there is currently no support for calculating agreement on stacking
            // annotations.
            List<Configuration> cfgs = cfgSet.getConfigurations(user);
            if (cfgs.size() > 1) {
                pluralitySets.add(cfgSet);
                continue nextPosition;
            }
            Configuration cfg = cfgs.get(0);
            // Check if source and/or targets of a relation are stacked
            if (cfg.getPosition() instanceof ArcPosition) {
                ArcPosition pos = (ArcPosition) cfg.getPosition();
                FeatureStructure arc = cfg.getFs(user, pos.getCasId(), aCasMap);
                ArcDiffAdapter adapter = (ArcDiffAdapter) aDiff.getDiffAdapter(pos.getType());
                // Check if the source of the relation is stacked
                AnnotationFS source = FSUtil.getFeature(arc, adapter.getSourceFeature(), AnnotationFS.class);
                List<AnnotationFS> sourceCandidates = CasUtil.selectAt(arc.getCAS(), source.getType(), source.getBegin(), source.getEnd());
                if (sourceCandidates.size() > 1) {
                    pluralitySets.add(cfgSet);
                    continue nextPosition;
                }
                // Check if the target of the relation is stacked
                AnnotationFS target = FSUtil.getFeature(arc, adapter.getTargetFeature(), AnnotationFS.class);
                List<AnnotationFS> targetCandidates = CasUtil.selectAt(arc.getCAS(), target.getType(), target.getBegin(), target.getEnd());
                if (targetCandidates.size() > 1) {
                    pluralitySets.add(cfgSet);
                    continue nextPosition;
                }
            }
            // Only calculate agreement for the given feature
            FeatureStructure fs = cfg.getFs(user, cfg.getPosition().getCasId(), aCasMap);
            // BEGIN PARANOIA
            assert fs.getType().getFeatureByBaseName(aFeature).getRange().isPrimitive() == isPrimitiveFeature;
            // should never have gotten here in the first place.
            assert !isPrimitiveFeature || !isSubPosition;
            if (isPrimitiveFeature && !isSubPosition) {
                // Primitive feature / primary position
                values[i] = getFeature(fs, aFeature);
            } else if (!isPrimitiveFeature && isSubPosition) {
                // Link feature / sub-position
                ArrayFS links = (ArrayFS) fs.getFeatureValue(fs.getType().getFeatureByBaseName(aFeature));
                FeatureStructure link = links.get(cfg.getAID(user).index);
                switch(cfg.getPosition().getLinkCompareBehavior()) {
                    case LINK_TARGET_AS_LABEL:
                        // FIXME The target feature name should be obtained from the feature
                        // definition!
                        AnnotationFS target = (AnnotationFS) link.getFeatureValue(link.getType().getFeatureByBaseName("target"));
                        values[i] = target.getBegin() + "-" + target.getEnd() + " [" + target.getCoveredText() + "]";
                        break;
                    case LINK_ROLE_AS_LABEL:
                        // FIXME The role feature name should be obtained from the feature
                        // definition!
                        String role = link.getStringValue(link.getType().getFeatureByBaseName("role"));
                        values[i] = role;
                        break;
                    default:
                        throw new IllegalStateException("Unknown link target comparison mode [" + cfg.getPosition().getLinkCompareBehavior() + "]");
                }
            } else {
                throw new IllegalStateException("Should never get here: primitive: " + fs.getType().getFeatureByBaseName(aFeature).getRange().isPrimitive() + "; subpos: " + isSubPosition);
            }
            // agreement calculation. The empty label is still a valid label.
            if (aNullLabelsAsEmpty && values[i] == null) {
                values[i] = "";
            }
            // "null" cannot be used in agreement calculations. We treat these as incomplete
            if (values[i] == null) {
                incompleteSetsByLabel.add(cfgSet);
                if (aExcludeIncomplete) {
                    continue nextPosition;
                }
            }
            i++;
        }
        if (ObjectUtils.notEqual(values[0], values[1])) {
            setsWithDifferences.add(cfgSet);
        }
        // are calculating agreement over
        assert cfgSet.getPosition().getFeature() == null || cfgSet.getPosition().getFeature().equals(aFeature);
        completeSets.add(cfgSet);
        study.addItemAsArray(values);
    }
    return new AgreementResult(aType, aFeature, aDiff, study, users, completeSets, irrelevantSets, setsWithDifferences, incompleteSetsByPosition, incompleteSetsByLabel, pluralitySets, aExcludeIncomplete);
}