Examples with SchemaNotFoundException org.apache.nifi.schema.access.SchemaNotFoundException used on opensource projects

Example 11 with SchemaNotFoundException

use of org.apache.nifi.schema.access.SchemaNotFoundException in project nifi by apache.

the class GetSolr method onTrigger.

@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) throws ProcessException {
    final ComponentLog logger = getLogger();
    final AtomicBoolean continuePaging = new AtomicBoolean(true);
    final SolrQuery solrQuery = new SolrQuery();
    try {
        if (id_field == null) {
            id_field = getFieldNameOfUniqueKey();
        }
        final String dateField = context.getProperty(DATE_FIELD).getValue();
        final Map<String, String> stateMap = new HashMap<String, String>();
        stateMap.putAll(context.getStateManager().getState(Scope.CLUSTER).toMap());
        solrQuery.setQuery("*:*");
        final String query = context.getProperty(SOLR_QUERY).getValue();
        if (!StringUtils.isBlank(query) && !query.equals("*:*")) {
            solrQuery.addFilterQuery(query);
        }
        final StringBuilder automatedFilterQuery = (new StringBuilder()).append(dateField).append(":[").append(stateMap.get(STATE_MANAGER_FILTER)).append(" TO *]");
        solrQuery.addFilterQuery(automatedFilterQuery.toString());
        final List<String> fieldList = new ArrayList<String>();
        final String returnFields = context.getProperty(RETURN_FIELDS).getValue();
        if (!StringUtils.isBlank(returnFields)) {
            fieldList.addAll(Arrays.asList(returnFields.trim().split("[,]")));
            if (!fieldList.contains(dateField)) {
                fieldList.add(dateField);
                dateFieldNotInSpecifiedFieldsList.set(true);
            }
            for (String returnField : fieldList) {
                solrQuery.addField(returnField.trim());
            }
        }
        solrQuery.setParam(CursorMarkParams.CURSOR_MARK_PARAM, stateMap.get(STATE_MANAGER_CURSOR_MARK));
        solrQuery.setRows(context.getProperty(BATCH_SIZE).asInteger());
        final StringBuilder sortClause = (new StringBuilder()).append(dateField).append(" asc,").append(id_field).append(" asc");
        solrQuery.setParam("sort", sortClause.toString());
        while (continuePaging.get()) {
            final QueryRequest req = new QueryRequest(solrQuery);
            if (isBasicAuthEnabled()) {
                req.setBasicAuthCredentials(getUsername(), getPassword());
            }
            logger.debug(solrQuery.toQueryString());
            final QueryResponse response = req.process(getSolrClient());
            final SolrDocumentList documentList = response.getResults();
            if (response.getResults().size() > 0) {
                final SolrDocument lastSolrDocument = documentList.get(response.getResults().size() - 1);
                final String latestDateValue = df.format(lastSolrDocument.get(dateField));
                final String newCursorMark = response.getNextCursorMark();
                solrQuery.setParam(CursorMarkParams.CURSOR_MARK_PARAM, newCursorMark);
                stateMap.put(STATE_MANAGER_CURSOR_MARK, newCursorMark);
                stateMap.put(STATE_MANAGER_FILTER, latestDateValue);
                FlowFile flowFile = session.create();
                flowFile = session.putAttribute(flowFile, "solrQuery", solrQuery.toString());
                if (context.getProperty(RETURN_TYPE).getValue().equals(MODE_XML.getValue())) {
                    if (dateFieldNotInSpecifiedFieldsList.get()) {
                        for (SolrDocument doc : response.getResults()) {
                            doc.removeFields(dateField);
                        }
                    }
                    flowFile = session.write(flowFile, SolrUtils.getOutputStreamCallbackToTransformSolrResponseToXml(response));
                    flowFile = session.putAttribute(flowFile, CoreAttributes.MIME_TYPE.key(), "application/xml");
                } else {
                    final RecordSetWriterFactory writerFactory = context.getProperty(RECORD_WRITER).asControllerService(RecordSetWriterFactory.class);
                    final RecordSchema schema = writerFactory.getSchema(null, null);
                    final RecordSet recordSet = SolrUtils.solrDocumentsToRecordSet(response.getResults(), schema);
                    final StringBuffer mimeType = new StringBuffer();
                    flowFile = session.write(flowFile, new OutputStreamCallback() {

                        @Override
                        public void process(final OutputStream out) throws IOException {
                            try {
                                final RecordSetWriter writer = writerFactory.createWriter(getLogger(), schema, out);
                                writer.write(recordSet);
                                writer.flush();
                                mimeType.append(writer.getMimeType());
                            } catch (SchemaNotFoundException e) {
                                throw new ProcessException("Could not parse Solr response", e);
                            }
                        }
                    });
                    flowFile = session.putAttribute(flowFile, CoreAttributes.MIME_TYPE.key(), mimeType.toString());
                }
                session.transfer(flowFile, REL_SUCCESS);
            }
            continuePaging.set(response.getResults().size() == Integer.parseInt(context.getProperty(BATCH_SIZE).getValue()));
        }
        context.getStateManager().setState(stateMap, Scope.CLUSTER);
    } catch (SolrServerException | SchemaNotFoundException | IOException e) {
        context.yield();
        session.rollback();
        logger.error("Failed to execute query {} due to {}", new Object[] { solrQuery.toString(), e }, e);
        throw new ProcessException(e);
    } catch (final Throwable t) {
        context.yield();
        session.rollback();
        logger.error("Failed to execute query {} due to {}", new Object[] { solrQuery.toString(), t }, t);
        throw t;
    }
}

Example 12 with SchemaNotFoundException

use of org.apache.nifi.schema.access.SchemaNotFoundException in project nifi by apache.

the class AvroReader method createRecordReader.

@Override
public RecordReader createRecordReader(final Map<String, String> variables, final InputStream in, final ComponentLog logger) throws MalformedRecordException, IOException, SchemaNotFoundException {
    final String schemaAccessStrategy = getConfigurationContext().getProperty(getSchemaAcessStrategyDescriptor()).getValue();
    if (EMBEDDED_AVRO_SCHEMA.getValue().equals(schemaAccessStrategy)) {
        return new AvroReaderWithEmbeddedSchema(in);
    } else {
        final RecordSchema recordSchema = getSchema(variables, in, null);
        final Schema avroSchema;
        try {
            if (recordSchema.getSchemaFormat().isPresent() & recordSchema.getSchemaFormat().get().equals(AvroTypeUtil.AVRO_SCHEMA_FORMAT)) {
                final Optional<String> textOption = recordSchema.getSchemaText();
                if (textOption.isPresent()) {
                    avroSchema = compileAvroSchema(textOption.get());
                } else {
                    avroSchema = AvroTypeUtil.extractAvroSchema(recordSchema);
                }
            } else {
                avroSchema = AvroTypeUtil.extractAvroSchema(recordSchema);
            }
        } catch (final Exception e) {
            throw new SchemaNotFoundException("Failed to compile Avro Schema", e);
        }
        return new AvroReaderWithExplicitSchema(in, recordSchema, avroSchema);
    }
}

Example 13 with SchemaNotFoundException

use of org.apache.nifi.schema.access.SchemaNotFoundException in project nifi by apache.

the class AvroRecordSetWriter method createWriter.

@Override
public RecordSetWriter createWriter(final ComponentLog logger, final RecordSchema recordSchema, final OutputStream out) throws IOException {
    final String strategyValue = getConfigurationContext().getProperty(getSchemaWriteStrategyDescriptor()).getValue();
    final String compressionFormat = getConfigurationContext().getProperty(COMPRESSION_FORMAT).getValue();
    try {
        final Schema avroSchema;
        try {
            if (recordSchema.getSchemaFormat().isPresent() && recordSchema.getSchemaFormat().get().equals(AvroTypeUtil.AVRO_SCHEMA_FORMAT)) {
                final Optional<String> textOption = recordSchema.getSchemaText();
                if (textOption.isPresent()) {
                    avroSchema = compileAvroSchema(textOption.get());
                } else {
                    avroSchema = AvroTypeUtil.extractAvroSchema(recordSchema);
                }
            } else {
                avroSchema = AvroTypeUtil.extractAvroSchema(recordSchema);
            }
        } catch (final Exception e) {
            throw new SchemaNotFoundException("Failed to compile Avro Schema", e);
        }
        if (AVRO_EMBEDDED.getValue().equals(strategyValue)) {
            return new WriteAvroResultWithSchema(avroSchema, out, getCodecFactory(compressionFormat));
        } else {
            return new WriteAvroResultWithExternalSchema(avroSchema, recordSchema, getSchemaAccessWriter(recordSchema), out);
        }
    } catch (final SchemaNotFoundException e) {
        throw new ProcessException("Could not determine the Avro Schema to use for writing the content", e);
    }
}

Example 14 with SchemaNotFoundException

use of org.apache.nifi.schema.access.SchemaNotFoundException in project nifi by apache.

the class PublishKafkaRecord_0_10 method onTrigger.

@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) throws ProcessException {
    final List<FlowFile> flowFiles = session.get(FlowFileFilters.newSizeBasedFilter(1, DataUnit.MB, 500));
    if (flowFiles.isEmpty()) {
        return;
    }
    final PublisherPool pool = getPublisherPool(context);
    if (pool == null) {
        context.yield();
        return;
    }
    final String securityProtocol = context.getProperty(KafkaProcessorUtils.SECURITY_PROTOCOL).getValue();
    final String bootstrapServers = context.getProperty(KafkaProcessorUtils.BOOTSTRAP_SERVERS).evaluateAttributeExpressions().getValue();
    final RecordSetWriterFactory writerFactory = context.getProperty(RECORD_WRITER).asControllerService(RecordSetWriterFactory.class);
    final RecordReaderFactory readerFactory = context.getProperty(RECORD_READER).asControllerService(RecordReaderFactory.class);
    final long startTime = System.nanoTime();
    try (final PublisherLease lease = pool.obtainPublisher()) {
        // Send each FlowFile to Kafka asynchronously.
        for (final FlowFile flowFile : flowFiles) {
            if (!isScheduled()) {
                // If stopped, re-queue FlowFile instead of sending it
                session.transfer(flowFile);
                continue;
            }
            final String topic = context.getProperty(TOPIC).evaluateAttributeExpressions(flowFile).getValue();
            final String messageKeyField = context.getProperty(MESSAGE_KEY_FIELD).evaluateAttributeExpressions(flowFile).getValue();
            final Map<String, String> attributes = flowFile.getAttributes();
            try {
                session.read(flowFile, new InputStreamCallback() {

                    @Override
                    public void process(final InputStream rawIn) throws IOException {
                        try (final InputStream in = new BufferedInputStream(rawIn)) {
                            final RecordReader reader = readerFactory.createRecordReader(attributes, in, getLogger());
                            final RecordSet recordSet = reader.createRecordSet();
                            final RecordSchema schema = writerFactory.getSchema(attributes, recordSet.getSchema());
                            lease.publish(flowFile, recordSet, writerFactory, schema, messageKeyField, topic);
                        } catch (final SchemaNotFoundException | MalformedRecordException e) {
                            throw new ProcessException(e);
                        }
                    }
                });
            } catch (final Exception e) {
                // The FlowFile will be obtained and the error logged below, when calling publishResult.getFailedFlowFiles()
                lease.getTracker().fail(flowFile, e);
                continue;
            }
        }
        // Complete the send
        final PublishResult publishResult = lease.complete();
        // Transfer any successful FlowFiles.
        final long transmissionMillis = TimeUnit.NANOSECONDS.toMillis(System.nanoTime() - startTime);
        for (FlowFile success : publishResult.getSuccessfulFlowFiles()) {
            final String topic = context.getProperty(TOPIC).evaluateAttributeExpressions(success).getValue();
            final int msgCount = publishResult.getSuccessfulMessageCount(success);
            success = session.putAttribute(success, MSG_COUNT, String.valueOf(msgCount));
            session.adjustCounter("Messages Sent", msgCount, true);
            final String transitUri = KafkaProcessorUtils.buildTransitURI(securityProtocol, bootstrapServers, topic);
            session.getProvenanceReporter().send(success, transitUri, "Sent " + msgCount + " messages", transmissionMillis);
            session.transfer(success, REL_SUCCESS);
        }
        // Transfer any failures.
        for (final FlowFile failure : publishResult.getFailedFlowFiles()) {
            final int successCount = publishResult.getSuccessfulMessageCount(failure);
            if (successCount > 0) {
                getLogger().error("Failed to send some messages for {} to Kafka, but {} messages were acknowledged by Kafka. Routing to failure due to {}", new Object[] { failure, successCount, publishResult.getReasonForFailure(failure) });
            } else {
                getLogger().error("Failed to send all message for {} to Kafka; routing to failure due to {}", new Object[] { failure, publishResult.getReasonForFailure(failure) });
            }
            session.transfer(failure, REL_FAILURE);
        }
    }
}

Example 15 with SchemaNotFoundException

use of org.apache.nifi.schema.access.SchemaNotFoundException in project nifi by apache.

the class MockSchemaRegistry method retrieveSchemaByIdAndVersion.

private RecordSchema retrieveSchemaByIdAndVersion(final SchemaIdentifier schemaIdentifier) throws IOException, SchemaNotFoundException {
    final OptionalLong schemaId = schemaIdentifier.getIdentifier();
    if (!schemaId.isPresent()) {
        throw new org.apache.nifi.schema.access.SchemaNotFoundException("Cannot retrieve schema because Schema Id is not present");
    }
    final OptionalInt version = schemaIdentifier.getVersion();
    if (!version.isPresent()) {
        throw new org.apache.nifi.schema.access.SchemaNotFoundException("Cannot retrieve schema because Schema Version is not present");
    }
    final Tuple<Long, Integer> tuple = new Tuple<>(schemaId.getAsLong(), version.getAsInt());
    final RecordSchema schema = schemaIdVersionMap.get(tuple);
    return schema;
}