Examples with FormatSpecification co.cask.cdap.api.data.format.FormatSpecification used on opensource projects

Example 41 with FormatSpecification

use of co.cask.cdap.api.data.format.FormatSpecification in project cdap by caskdata.

the class RecordFormats method createInitializedFormat.

/**
   * Create an initialized record format for the given format specification. The name in the specification is
   * first checked against standard names like "CSV" or "TSV". If it is a standard name, the corresponding
   * format will be created, with specification settings applied on top of default settings.
   * For example, "CSV" will map to the {@link DelimitedStringsRecordFormat}, with a comma as the delimiter,
   * whereas "TSV" will map to the {@link DelimitedStringsRecordFormat}, with a tab as the delimiter.
   * If the name is not a standard name, it is interpreted as a class name.
   *
   * @param spec the specification for the format to create and initialize
   * @param <FROM> Type of underlying object the format reads
   * @param <TO> Type of object the format reads the underlying object into
   * @return Initialized {@link RecordFormat} based on the given name
   * @throws IllegalAccessException if there was an illegal access when instantiating the record format
   * @throws InstantiationException if there was an exception instantiating the record format
   * @throws ClassNotFoundException if the record format class could not be found
   * @throws UnsupportedTypeException if the specification is not supported by the format
   */
public static <FROM, TO> RecordFormat<FROM, TO> createInitializedFormat(FormatSpecification spec) throws IllegalAccessException, InstantiationException, ClassNotFoundException, UnsupportedTypeException {
    String name = spec.getName();
    // check if it's a standard class
    Class<? extends RecordFormat> formatClass = NAME_CLASS_MAP.get(name.toLowerCase());
    @SuppressWarnings("unchecked") RecordFormat<FROM, TO> format = (RecordFormat<FROM, TO>) (formatClass == null ? Class.forName(name).newInstance() : formatClass.newInstance());
    // compute actual settings: use default settings if present
    Map<String, String> settings;
    Map<String, String> defaultSettings = NAME_SETTINGS_MAP.get(name.toLowerCase());
    if (defaultSettings != null) {
        settings = Maps.newHashMap(defaultSettings);
        if (spec.getSettings() != null) {
            settings.putAll(spec.getSettings());
        }
    } else {
        settings = spec.getSettings();
    }
    // compute actual schema
    Schema schema;
    Schema defaultSchema = DEFAULT_SCHEMA_MAP.get(name.toLowerCase());
    if (defaultSchema != null && spec.getSchema() == null) {
        schema = defaultSchema;
    } else {
        schema = spec.getSchema();
    }
    FormatSpecification actualSpec = new FormatSpecification(name, schema, settings);
    format.initialize(actualSpec);
    return format;
}

Example 42 with FormatSpecification

use of co.cask.cdap.api.data.format.FormatSpecification in project cdap by caskdata.

the class AvroRecordFormatTest method testMultipleReads.

@Test
public void testMultipleReads() throws Exception {
    Schema schema = Schema.recordOf("record", Schema.Field.of("x", Schema.of(Schema.Type.INT)));
    FormatSpecification formatSpecification = new FormatSpecification(Formats.AVRO, schema, Collections.<String, String>emptyMap());
    org.apache.avro.Schema avroSchema = convertSchema(schema);
    RecordFormat<StreamEvent, StructuredRecord> format = RecordFormats.createInitializedFormat(formatSpecification);
    GenericRecord record = new GenericRecordBuilder(avroSchema).set("x", 5).build();
    StructuredRecord actual = format.read(toStreamEvent(record));
    Assert.assertEquals(5, actual.get("x"));
    record = new GenericRecordBuilder(avroSchema).set("x", 10).build();
    actual = format.read(toStreamEvent(record));
    Assert.assertEquals(10, actual.get("x"));
}

Example 43 with FormatSpecification

use of co.cask.cdap.api.data.format.FormatSpecification in project cdap by caskdata.

the class AvroRecordFormatTest method testSchemaProjection.

@Test
public void testSchemaProjection() throws Exception {
    Schema sourceSchema = Schema.recordOf("source", Schema.Field.of("id", Schema.of(Schema.Type.INT)), Schema.Field.of("name", Schema.nullableOf(Schema.of(Schema.Type.STRING))));
    Schema readSchema = Schema.recordOf("read", Schema.Field.of("name", Schema.of(Schema.Type.STRING)));
    GenericRecord record = new GenericRecordBuilder(convertSchema(sourceSchema)).set("id", 1).set("name", "value").build();
    FormatSpecification formatSpecification = new FormatSpecification(Formats.AVRO, readSchema, ImmutableMap.<String, String>of());
    RecordFormat<StreamEvent, StructuredRecord> format = RecordFormats.createInitializedFormat(formatSpecification);
    // Convert an event that has schema associated
    StructuredRecord projectedRecord = format.read(toStreamEvent(record, true));
    Assert.assertEquals(record.get("name").toString(), projectedRecord.get("name").toString());
    // Convert an event that has no schema associated. The record must be written with the read schema.
    record = new GenericRecordBuilder(convertSchema(readSchema)).set("name", "value2").build();
    projectedRecord = format.read(toStreamEvent(record));
    Assert.assertEquals(record.get("name").toString(), projectedRecord.get("name").toString());
}

Example 44 with FormatSpecification

use of co.cask.cdap.api.data.format.FormatSpecification in project cdap by caskdata.

the class CombinedLogRecordFormatTest method testCLFLog.

@Test
public void testCLFLog() throws UnsupportedTypeException, UnexpectedFormatException {
    CombinedLogRecordFormat format = new CombinedLogRecordFormat();
    FormatSpecification spec = new FormatSpecification(CombinedLogRecordFormat.class.getCanonicalName(), null, ImmutableMap.<String, String>of());
    format.initialize(spec);
    String data = "10.10.10.10 - - [01/Feb/2015:06:47:10 +0000] \"GET /browse/COOP-DBT-JOB1-238/artifact HTTP/1.1\"" + " 301 256 \"-\" \"Mozilla/5.0 (compatible; AhrefsBot/5.0; +http://ahrefs.com/robot/)\"";
    StructuredRecord output = format.read(new StreamEvent(ByteBuffer.wrap(Bytes.toBytes(data))));
    Assert.assertEquals("10.10.10.10", output.get("remote_host"));
    Assert.assertNull(output.get("remote_login"));
    Assert.assertNull(output.get("auth_user"));
    Assert.assertEquals("01/Feb/2015:06:47:10 +0000", output.get("request_time"));
    Assert.assertEquals("GET /browse/COOP-DBT-JOB1-238/artifact HTTP/1.1", output.get("request"));
    Assert.assertEquals(301, output.get("status"));
    Assert.assertEquals(256, output.get("content_length"));
    Assert.assertNull(output.get("referrer"));
    Assert.assertEquals("Mozilla/5.0 (compatible; AhrefsBot/5.0; +http://ahrefs.com/robot/)", output.get("user_agent"));
}

Example 45 with FormatSpecification

use of co.cask.cdap.api.data.format.FormatSpecification in project cdap by caskdata.

the class CombinedLogRecordFormatTest method testInvalid.

@Test(expected = UnexpectedFormatException.class)
public void testInvalid() throws UnsupportedTypeException, UnexpectedFormatException {
    CombinedLogRecordFormat format = new CombinedLogRecordFormat();
    FormatSpecification spec = new FormatSpecification(CombinedLogRecordFormat.class.getCanonicalName(), null, ImmutableMap.<String, String>of());
    format.initialize(spec);
    String data = "10.10.10.10[01/Feb/2015:06:47:10 +0000";
    StructuredRecord output = format.read(new StreamEvent(ByteBuffer.wrap(Bytes.toBytes(data))));
}