Function test_parquet_metadata_works_with_strings

datafusion-cli/src/main.rs:543–561

()

    #[tokio::test]
    async fn test_parquet_metadata_works_with_strings() -> Result<(), DataFusionError> {
        let ctx = SessionContext::new();
        ctx.register_udtf("parquet_metadata", Arc::new(ParquetMetadataFunc {}));

        // input with string columns
        let sql = "SELECT * FROM parquet_metadata('../parquet-testing/data/data_index_bloom_encoding_stats.parquet')";
        let df = ctx.sql(sql).await?;
        let rbs = df.collect().await?;

        assert_snapshot!(batches_to_string(&rbs),@r#"
        +-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
        | filename                                                        | row_group_id | row_group_num_rows | row_group_num_columns | row_group_bytes | column_id | file_offset | num_values | path_in_schema | type       | stats_min | stats_max | stats_null_count | stats_distinct_count | stats_min_value | stats_max_value | compression        | encodings                | index_page_offset | dictionary_page_offset | data_page_offset | total_compressed_size | total_uncompressed_size |
        +-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
        | ../parquet-testing/data/data_index_bloom_encoding_stats.parquet | 0            | 14                 | 1                     | 163             | 0         | 4           | 14         | "String"       | BYTE_ARRAY | Hello     | today     | 0                |                      | Hello           | today           | GZIP(GzipLevel(6)) | [PLAIN, RLE, BIT_PACKED] |                   |                        | 4                | 152                   | 163                     |
        +-----------------------------------------------------------------+--------------+--------------------+-----------------------+-----------------+-----------+-------------+------------+----------------+------------+-----------+-----------+------------------+----------------------+-----------------+-----------------+--------------------+--------------------------+-------------------+------------------------+------------------+-----------------------+-------------------------+
        "#);

        Ok(())
    }

    #[tokio::test]
    async fn test_metadata_cache() -> Result<(), DataFusionError> {