Examples with PegasusSchemaParser com.linkedin.data.schema.PegasusSchemaParser used on opensource projects

Example 16 with PegasusSchemaParser

use of com.linkedin.data.schema.PegasusSchemaParser in project rest.li by linkedin.

the class SchemaTranslator method avroToDataSchema.

/**
 * Translate an Avro {@link Schema} to a {@link DataSchema}.
 * <p>
 * If the translation mode is {@link AvroToDataSchemaTranslationMode#RETURN_EMBEDDED_SCHEMA}
 * and a {@link DataSchema} is embedded in the Avro schema, then return the embedded schema.
 * An embedded schema is present if the Avro {@link Schema} has a "com.linkedin.data" property and the
 * "com.linkedin.data" property contains both "schema" and "optionalDefaultMode" properties.
 * The "schema" property provides the embedded {@link DataSchema}.
 * The "optionalDefaultMode" property provides how optional default values were translated.
 * <p>
 * If the translation mode is {@link AvroToDataSchemaTranslationMode#VERIFY_EMBEDDED_SCHEMA}
 * and a {@link DataSchema} is embedded in the Avro schema, then verify that the embedded schema
 * translates to the input Avro schema. If the translated and embedded schema is the same,
 * then return the embedded schema, else throw {@link IllegalArgumentException}.
 * <p>
 * If the translation mode is {@link com.linkedin.data.avro.AvroToDataSchemaTranslationMode#TRANSLATE}
 * or no embedded {@link DataSchema} is present, then this method
 * translates the provided Avro {@link Schema} to a {@link DataSchema}
 * as described follows:
 * <p>
 * This method translates union with null record fields in Avro {@link Schema}
 * to optional fields in {@link DataSchema}. Record fields
 * whose type is a union with null will be translated to a new type, and the field becomes optional.
 * If the Avro union has two types (one of them is the null type), then the new type of the
 * field is the non-null member type of the union. If the Avro union does not have two types
 * (one of them is the null type) then the new type of the field is a union type with the null type
 * removed from the original union.
 * <p>
 * This method also translates default values. If the field's type is a union with null
 * and has a default value, then this method also translates the default value of the field
 * to comply with the new type of the field. If the default value is null,
 * then remove the default value. If new type is not a union and the default value
 * is of the non-null member type, then assign the default value to the
 * non-null value within the union value (i.e. the value of the only entry within the
 * JSON object.) If the new type is a union and the default value is of the
 * non-null member type, then assign the default value to a JSON object
 * containing a single entry with the key being the member type discriminator of
 * the first union member and the value being the actual member value.
 * <p>
 * Both the schema and default value translation takes into account that default value
 * representation for Avro unions does not include the member type discriminator and
 * the type of the default value is always the 1st member of the union.
 *
 * @param avroSchemaInJson provides the JSON representation of the Avro {@link Schema}.
 * @param options specifies the {@link AvroToDataSchemaTranslationOptions}.
 * @return the translated {@link DataSchema}.
 * @throws IllegalArgumentException if the Avro {@link Schema} cannot be translated.
 */
public static DataSchema avroToDataSchema(String avroSchemaInJson, AvroToDataSchemaTranslationOptions options) throws IllegalArgumentException {
    ValidationOptions validationOptions = SchemaParser.getDefaultSchemaParserValidationOptions();
    validationOptions.setAvroUnionMode(true);
    SchemaParserFactory parserFactory = SchemaParserFactory.instance(validationOptions);
    DataSchemaResolver resolver = getResolver(parserFactory, options);
    PegasusSchemaParser parser = parserFactory.create(resolver);
    parser.parse(avroSchemaInJson);
    if (parser.hasError()) {
        throw new IllegalArgumentException(parser.errorMessage());
    }
    assert (parser.topLevelDataSchemas().size() == 1);
    DataSchema dataSchema = parser.topLevelDataSchemas().get(0);
    DataSchema resultDataSchema = null;
    AvroToDataSchemaTranslationMode translationMode = options.getTranslationMode();
    if (translationMode == AvroToDataSchemaTranslationMode.RETURN_EMBEDDED_SCHEMA || translationMode == AvroToDataSchemaTranslationMode.VERIFY_EMBEDDED_SCHEMA) {
        // check for embedded schema
        Object dataProperty = dataSchema.getProperties().get(SchemaTranslator.DATA_PROPERTY);
        if (dataProperty != null && dataProperty.getClass() == DataMap.class) {
            Object schemaProperty = ((DataMap) dataProperty).get(SchemaTranslator.SCHEMA_PROPERTY);
            if (schemaProperty.getClass() == DataMap.class) {
                SchemaParser embeddedSchemaParser = SchemaParserFactory.instance().create(null);
                embeddedSchemaParser.parse(Arrays.asList(schemaProperty));
                if (embeddedSchemaParser.hasError()) {
                    throw new IllegalArgumentException("Embedded schema is invalid\n" + embeddedSchemaParser.errorMessage());
                }
                assert (embeddedSchemaParser.topLevelDataSchemas().size() == 1);
                resultDataSchema = embeddedSchemaParser.topLevelDataSchemas().get(0);
                if (translationMode == AvroToDataSchemaTranslationMode.VERIFY_EMBEDDED_SCHEMA) {
                    // additional verification to make sure that embedded schema translates to Avro schema
                    DataToAvroSchemaTranslationOptions dataToAvroSchemaOptions = new DataToAvroSchemaTranslationOptions();
                    Object optionalDefaultModeProperty = ((DataMap) dataProperty).get(SchemaTranslator.OPTIONAL_DEFAULT_MODE_PROPERTY);
                    dataToAvroSchemaOptions.setOptionalDefaultMode(OptionalDefaultMode.valueOf(optionalDefaultModeProperty.toString()));
                    Schema avroSchemaFromEmbedded = dataToAvroSchema(resultDataSchema, dataToAvroSchemaOptions);
                    Schema avroSchemaFromJson = Schema.parse(avroSchemaInJson);
                    if (!avroSchemaFromEmbedded.equals(avroSchemaFromJson)) {
                        throw new IllegalArgumentException("Embedded schema does not translate to input Avro schema: " + avroSchemaInJson);
                    }
                }
            }
        }
    }
    if (resultDataSchema == null) {
        // translationMode == TRANSLATE or no embedded schema
        DataSchemaTraverse traverse = new DataSchemaTraverse();
        traverse.traverse(dataSchema, AvroToDataSchemaConvertCallback.INSTANCE);
        // convert default values
        traverse.traverse(dataSchema, DefaultAvroToDataConvertCallback.INSTANCE);
        // make sure it can round-trip
        String dataSchemaJson = dataSchema.toString();
        resultDataSchema = DataTemplateUtil.parseSchema(dataSchemaJson);
    }
    return resultDataSchema;
}

Example 17 with PegasusSchemaParser

use of com.linkedin.data.schema.PegasusSchemaParser in project rest.li by linkedin.

the class TestCustomAvroSchema method translate.

private void translate(String dataSchemaFieldsJson, String avroSchemaFieldsJson, String dataJson, String avroDataJson) throws IOException {
    boolean debug = false;
    String fullSchemaJson = DATA_SCHEMA_JSON_TEMPLATE.replace("##FIELDS", dataSchemaFieldsJson);
    String avroSchemaFieldsJsonAfterVariableExpansion = avroSchemaFieldsJson.replace("##ANYRECORD_FULL_JSON", ANYRECORD_AVRO_SCHEMA_JSON).replace("##ANYRECORD_NAME", ANYRECORD_AVRO_FULL_NAME);
    String fullAvroSchemaJson = AVRO_SCHEMA_JSON_TEMPLATE.replace("##FIELDS", avroSchemaFieldsJsonAfterVariableExpansion);
    PegasusSchemaParser parser = TestUtil.schemaParserFromString(fullSchemaJson);
    assertFalse(parser.hasError(), parser.errorMessage());
    RecordDataSchema schema = (RecordDataSchema) parser.topLevelDataSchemas().get(2);
    String avroJsonOutput = SchemaTranslator.dataToAvroSchemaJson(schema);
    assertEquals(TestUtil.dataMapFromString(avroJsonOutput), TestUtil.dataMapFromString(fullAvroSchemaJson));
    Schema avroSchema = Schema.parse(avroJsonOutput);
    Schema avroSchema2 = SchemaTranslator.dataToAvroSchema(schema);
    assertEquals(avroSchema, avroSchema2);
    String avroSchemaToString = avroSchema.toString();
    assertEquals(Schema.parse(avroSchemaToString), Schema.parse(fullAvroSchemaJson));
    if (debug) {
        TestUtil.out.println(schema);
        TestUtil.out.println(avroSchema);
    }
    // translate from Data to Avro generic
    DataMap inputDataMap = TestUtil.dataMapFromString(dataJson);
    GenericRecord genericRecord = DataTranslator.dataMapToGenericRecord(inputDataMap, schema);
    GenericRecord expectedGenericRecord = AvroUtil.genericRecordFromJson(avroDataJson, avroSchema);
    assertEquals(genericRecord.toString(), expectedGenericRecord.toString());
    // translate form Avro generic back to Data
    Object data = DataTranslator.genericRecordToDataMap(genericRecord, schema, avroSchema);
    assertEquals(data, inputDataMap);
}