Function test_header

arrow-avro/src/reader/header.rs:383–445

()

    #[test]
    fn test_header() {
        let header = decode_file(&arrow_test_data("avro/alltypes_plain.avro"));
        let schema_json = header.get(SCHEMA_METADATA_KEY).unwrap();
        let expected = br#"{"type":"record","name":"topLevelRecord","fields":[{"name":"id","type":["int","null"]},{"name":"bool_col","type":["boolean","null"]},{"name":"tinyint_col","type":["int","null"]},{"name":"smallint_col","type":["int","null"]},{"name":"int_col","type":["int","null"]},{"name":"bigint_col","type":["long","null"]},{"name":"float_col","type":["float","null"]},{"name":"double_col","type":["double","null"]},{"name":"date_string_col","type":["bytes","null"]},{"name":"string_col","type":["bytes","null"]},{"name":"timestamp_col","type":[{"type":"long","logicalType":"timestamp-micros"},"null"]}]}"#;
        assert_eq!(schema_json, expected);
        let schema: Schema<'_> = serde_json::from_slice(schema_json).unwrap();
        let field = AvroField::try_from(&schema).unwrap();

        assert_eq!(
            field.field(),
            Field::new(
                "topLevelRecord",
                DataType::Struct(Fields::from(vec![
                    Field::new("id", DataType::Int32, true),
                    Field::new("bool_col", DataType::Boolean, true),
                    Field::new("tinyint_col", DataType::Int32, true),
                    Field::new("smallint_col", DataType::Int32, true),
                    Field::new("int_col", DataType::Int32, true),
                    Field::new("bigint_col", DataType::Int64, true),
                    Field::new("float_col", DataType::Float32, true),
                    Field::new("double_col", DataType::Float64, true),
                    Field::new("date_string_col", DataType::Binary, true),
                    Field::new("string_col", DataType::Binary, true),
                    Field::new(
                        "timestamp_col",
                        DataType::Timestamp(TimeUnit::Microsecond, Some("+00:00".into())),
                        true
                    ),
                ])),
                false
            )
            .with_metadata(HashMap::from([(
                AVRO_NAME_METADATA_KEY.to_string(),
                AVRO_ROOT_RECORD_DEFAULT_NAME.to_string()
            )]))
        );

        assert_eq!(
            u128::from_le_bytes(header.sync()),
            226966037233754408753420635932530907102
        );

        let header = decode_file(&arrow_test_data("avro/fixed_length_decimal.avro"));

        let meta: Vec<_> = header
            .metadata()
            .map(|(k, _)| std::str::from_utf8(k).unwrap())
            .collect();

        assert_eq!(
            meta,
            &["avro.schema", "org.apache.spark.version", "avro.codec"]
        );

        let schema_json = header.get(SCHEMA_METADATA_KEY).unwrap();
        let expected = br#"{"type":"record","name":"topLevelRecord","fields":[{"name":"value","type":[{"type":"fixed","name":"fixed","namespace":"topLevelRecord.value","size":11,"logicalType":"decimal","precision":25,"scale":2},"null"]}]}"#;
        assert_eq!(schema_json, expected);
        let _schema: Schema<'_> = serde_json::from_slice(schema_json).unwrap();