Examples with SourceDocument de.catma.document.source.SourceDocument used on opensource projects

Example 1 with SourceDocument

use of de.catma.document.source.SourceDocument in project catma by forTEXT.

the class CorpusExporter method export.

public void export(String exportName, Corpus corpus, OutputStream os) throws IOException {
    OutputStream tarFileOs = new GZIPOutputStream(os);
    TarArchiveOutputStream taOut = new TarArchiveOutputStream(tarFileOs, "UTF-8");
    try {
        taOut.setLongFileMode(TarArchiveOutputStream.LONGFILE_GNU);
        taOut.setBigNumberMode(TarArchiveOutputStream.BIGNUMBER_POSIX);
        for (SourceDocument sd : corpus.getSourceDocuments()) {
            TarArchiveEntry sdEntry = new TarArchiveEntry(getSourceDocEntryName(exportName, sd));
            byte[] sdContent = sd.getContent().getBytes(Charset.forName("UTF8"));
            sdEntry.setSize(sdContent.length);
            taOut.putArchiveEntry(sdEntry);
            taOut.write(sdContent);
            taOut.closeArchiveEntry();
            for (AnnotationCollectionReference umcRef : corpus.getUserMarkupCollectionRefs(sd)) {
                AnnotationCollection umc = repo.getUserMarkupCollection(umcRef);
                TeiUserMarkupCollectionSerializationHandler handler = new TeiUserMarkupCollectionSerializationHandler(repo.getTagManager(), false);
                ByteArrayOutputStream teiDocOut = new ByteArrayOutputStream();
                handler.serialize(repo.getUserMarkupCollection(umcRef), sd, teiDocOut);
                byte[] umcContent = teiDocOut.toByteArray();
                String umcEntryName = getUmcEntryName(exportName, umc, sd);
                TarArchiveEntry umcEntry = new TarArchiveEntry(umcEntryName);
                umcEntry.setSize(umcContent.length);
                taOut.putArchiveEntry(umcEntry);
                taOut.write(umcContent);
                taOut.closeArchiveEntry();
            }
        }
    } finally {
        taOut.finish();
        taOut.close();
    }
}

Example 2 with SourceDocument

use of de.catma.document.source.SourceDocument in project catma by forTEXT.

the class ProjectResourceExportApiRequestHandler method serializeProjectResources.

private String serializeProjectResources() {
    try {
        Export export = new Export();
        for (SourceDocument sourceDocument : project.getSourceDocuments()) {
            ArrayList<AnnotationCollection> annotationCollections = new ArrayList<>();
            for (AnnotationCollectionReference annotationCollectionReference : sourceDocument.getUserMarkupCollectionRefs()) {
                annotationCollections.add(project.getUserMarkupCollection(annotationCollectionReference));
            }
            ArrayList<TagDefinition> tagDefinitions = new ArrayList<>();
            ArrayList<TagReference> tagReferences = new ArrayList<>();
            for (AnnotationCollection annotationCollection : annotationCollections) {
                for (TagsetDefinition tagsetDefinition : annotationCollection.getTagLibrary().getTagsetDefinitions()) {
                    tagDefinitions.addAll(tagsetDefinition.stream().collect(Collectors.toList()));
                }
                tagReferences.addAll(annotationCollection.getTagReferences());
            }
            ExportDocument exportDocument = new ExportDocument(new PreApiSourceDocument(sourceDocument, String.format("%s%s/doc/%s", BASE_URL, handlerPath.substring(1), sourceDocument.getUuid().toLowerCase())), tagDefinitions.stream().map(PreApiTagDefinition::new).collect(Collectors.toList()), tagReferences.stream().map((TagReference tagReference) -> {
                try {
                    return new PreApiAnnotation(tagReference, tagDefinitions.stream().filter(td -> td.getUuid().equals(tagReference.getTagDefinitionId())).findFirst().get(), sourceDocument);
                } catch (IOException e) {
                    logger.log(Level.WARNING, String.format("Error serializing TagReference: %s", tagReference), e);
                    return null;
                }
            }).collect(Collectors.toList()));
            export.addExportDocument(exportDocument);
        }
        return new SerializationHelper<Export>().serialize(export);
    } catch (Exception e) {
        logger.log(Level.SEVERE, "Failed to serialize project resources", e);
        return "{\"error\": \"Failed to serialize project resources, please contact CATMA support\"}";
    }
}

Example 3 with SourceDocument

use of de.catma.document.source.SourceDocument in project catma by forTEXT.

the class AnnotatedDocumentQueryResultRowItem method addChildRowItems.

@Override
public void addChildRowItems(TreeData<QueryResultRowItem> treeData, LoadingCache<String, KwicProvider> kwicProviderCache) {
    try {
        HashMap<String, QueryResultRowArray> rowsByCollectionId = new HashMap<String, QueryResultRowArray>();
        for (QueryResultRow row : groupedQueryResult) {
            if (row instanceof TagQueryResultRow) {
                TagQueryResultRow tRow = (TagQueryResultRow) row;
                String collectionId = tRow.getMarkupCollectionId();
                QueryResultRowArray rows = null;
                if (!rowsByCollectionId.containsKey(collectionId)) {
                    rows = new QueryResultRowArray();
                    rowsByCollectionId.put(collectionId, rows);
                } else {
                    rows = rowsByCollectionId.get(collectionId);
                }
                rows.add(row);
            }
        }
        for (String collectionId : rowsByCollectionId.keySet()) {
            SourceDocument document = kwicProviderCache.get(getDocumentId()).getSourceDocument();
            String collectionName = document.getUserMarkupCollectionReference(collectionId).getName();
            QueryResultRowArray rows = rowsByCollectionId.get(collectionId);
            CollectionQueryResultRowItem item = new CollectionQueryResultRowItem(identity, collectionName, getDocumentId(), collectionId, rows, project);
            if (!treeData.contains(item)) {
                treeData.addItem(this, item);
                treeData.addItem(item, new DummyQueryResultRowItem());
            }
        }
    } catch (Exception e) {
        ((ErrorHandler) UI.getCurrent()).showAndLogError("error displaying annotated query results", e);
    }
}

Example 4 with SourceDocument

use of de.catma.document.source.SourceDocument in project catma by forTEXT.

the class ProjectView method buildResourceDataProvider.

private TreeDataProvider<Resource> buildResourceDataProvider() throws Exception {
    if (project != null) {
        TreeData<Resource> treeData = new TreeData<>();
        Collection<SourceDocument> srcDocs = project.getSourceDocuments();
        Locale locale = Locale.getDefault();
        for (SourceDocument srcDoc : srcDocs) {
            locale = srcDoc.getSourceContentHandler().getSourceDocumentInfo().getIndexInfoSet().getLocale();
            DocumentResource docResource = new DocumentResource(srcDoc, project.getProjectId(), project.hasPermission(project.getRoleForDocument(srcDoc.getUuid()), RBACPermission.DOCUMENT_WRITE));
            if (project.hasPermission(project.getRoleForDocument(srcDoc.getUuid()), RBACPermission.DOCUMENT_READ)) {
                treeData.addItem(null, docResource);
                List<AnnotationCollectionReference> collections = srcDoc.getUserMarkupCollectionRefs();
                List<Resource> readableCollectionResources = collections.stream().filter(collectionRef -> project.hasPermission(project.getRoleForCollection(collectionRef.getId()), RBACPermission.COLLECTION_READ)).map(collectionRef -> new CollectionResource(collectionRef, project.getProjectId(), project.hasPermission(project.getRoleForCollection(collectionRef.getId()), RBACPermission.COLLECTION_WRITE))).collect(Collectors.toList());
                if (!collections.isEmpty()) {
                    treeData.addItems(docResource, readableCollectionResources);
                }
            }
        }
        Collator collator = Collator.getInstance(locale);
        collator.setStrength(Collator.PRIMARY);
        documentGrid.getColumn(DocumentGridColumn.NAME.name()).setComparator((r1, r2) -> collator.compare(r1.getName(), r2.getName()));
        tagsetGrid.getColumn(TagsetGridColumn.NAME.name()).setComparator((t1, t2) -> collator.compare(t1.getName(), t2.getName()));
        return new TreeDataProvider<>(treeData);
    }
    return new TreeDataProvider<>(new TreeData<>());
}

Example 5 with SourceDocument

use of de.catma.document.source.SourceDocument in project catma by forTEXT.

the class ProjectView method handleResourceItemClick.

private void handleResourceItemClick(ItemClick<Resource> itemClickEvent) {
    if (itemClickEvent.getMouseEventDetails().isDoubleClick()) {
        Resource resource = itemClickEvent.getItem();
        @SuppressWarnings("unchecked") TreeDataProvider<Resource> resourceDataProvider = (TreeDataProvider<Resource>) documentGrid.getDataProvider();
        Resource root = resourceDataProvider.getTreeData().getParent(resource);
        Resource child = null;
        if (root == null) {
            root = resource;
        } else {
            child = resource;
        }
        if (root != null) {
            SourceDocument document = ((DocumentResource) root).getDocument();
            AnnotationCollectionReference collectionReference = (child == null ? null : ((CollectionResource) child).getCollectionReference());
            eventBus.post(new RouteToAnnotateEvent(project, document, collectionReference));
        }
    }
}