Complex Types (CDH 5.5 or higher only)

Complex types let you associate arbitrary data structures with a particular row. If you are familiar with schema design for relational database management systems or data warehouses, a schema with complex types has the following differences:

• Logically, related values can now be grouped tightly together in the same table.

  In traditional data warehousing, related values were typically arranged in one of two ways:

  • Split across multiple normalized tables. Foreign key columns specified which rows from each table were associated with each other. This arrangement avoided duplicate data and therefore the data was compact, but join queries could be expensive because the related data had to be retrieved from separate locations. (In the case of distributed Hadoop queries, the joined tables might even be transmitted between different hosts in a cluster.)

  • Flattened into a single denormalized table. Although this layout eliminated some potential performance issues by removing the need for join queries, the table typically became larger because values were repeated. The extra data volume could cause performance issues in other parts of the workflow, such as longer ETL cycles or more expensive full-table scans during queries.

  Complex types represent a middle ground that addresses these performance and volume concerns. By physically locating related data within the same data files, complex types increase locality and reduce the expense of join queries. By associating an arbitrary amount of data with a single row, complex types avoid the need to repeat lengthy values such as strings. Because Impala knows which complex type values are associated with each row, you can save storage by avoiding artificial foreign key values that are only used for joins. The flexibility of the STRUCT, ARRAY, and MAP types lets you model familiar constructs such as fact and dimension tables from a data warehouse, and wide tables representing sparse matrixes.

Physically, the scalar and complex columns in each row are located adjacent to each other in the same Parquet data file, ensuring that they are processed on the same host rather than being broadcast across the network when cross-referenced within a query. This co-location simplifies the process of copying, converting, and backing all the columns up at once. Because of the column-oriented layout of Parquet files, you can still query only the scalar columns of a table without imposing the I/O penalty of reading the (possibly large) values of the composite columns.

Within each Parquet data file, the constituent parts of complex type columns are stored in column-oriented format:

• Each field of a STRUCT type is stored like a column, with all the scalar values adjacent to each other and encoded, compressed, and so on using the Parquet space-saving techniques.

• For an ARRAY containing scalar values, all those values (represented by the ITEM pseudocolumn) are stored adjacent to each other.

• For a MAP, the values of the KEY pseudocolumn are stored adjacent to each other. If the VALUE pseudocolumn is a scalar type, its values are also stored adjacent to each other.

• If an ARRAY element, STRUCT field, or MAP VALUE part is another complex type, the column-oriented storage applies to the next level down (or the next level after that, and so on for deeply nested types) where the final elements, fields, or values are of scalar types.

The numbers represented by the POS pseudocolumn of an ARRAY are not physically stored in the data files. They are synthesized at query time based on the order of the ARRAY elements associated with each row.

Currently, Impala queries support complex type data only in the Parquet file format. See Using the Parquet File Format with Impala Tables for details about the performance benefits and physical layout of this file format.

Because Impala does not parse the data structures containing nested types for unsupported formats such as text, Avro, SequenceFile, or RCFile, you cannot use data files in these formats with Impala, even if the query does not refer to the nested type columns. Also, if a table using an unsupported format originally contained nested type columns, and then those columns were dropped from the table using ALTER TABLE ... DROP COLUMN, any existing data files in the table still contain the nested type data and Impala queries on that table will generate errors.

The one exception to the preceding rule is COUNT(*) queries on RCFile tables that include complex types. Such queries are allowed in CDH 5.8 / Impala 2.6 and higher.

You can perform DDL operations for tables involving complex types in most file formats other than Parquet. You cannot create tables with complex types using text files.

You can have a partitioned table with complex type columns that uses a non-Parquet format, and use ALTER TABLE to change the file format to Parquet for individual partitions. When you put Parquet data files into those partitions, Impala can execute queries against that data as long as the query does not involve any of the non-Parquet partitions.

If you use the parquet-tools command to examine the structure of a Parquet data file that includes complex types, you see that both ARRAY and MAP are represented as a Bag in Parquet terminology, with all fields marked Optional because Impala allows any column to be nullable.

Impala supports either 2-level and 3-level encoding within each Parquet data file. When constructing Parquet data files outside Impala, use either encoding style but do not mix 2-level and 3-level encoding within the same data file.

Choosing between multiple normalized fact and dimension tables, or a single table containing complex types, is an important design decision.

• If you are coming from a traditional database or data warehousing background, you might be familiar with how to split up data between tables. Your business intelligence tools might already be optimized for dealing with this kind of multi-table scenario through join queries.

• If you are pulling data from Impala into an application written in a programming language that has data structures analogous to the complex types, such as Python or Java, complex types in Impala could simplify data interchange and improve understandability and reliability of your program logic.

• You might already be faced with existing infrastructure or receive high volumes of data that assume one layout or the other. For example, complex types are popular with web-oriented applications, for example to keep information about an online user all in one place for convenient lookup and analysis, or to deal with sparse or constantly evolving data fields.

• If some parts of the data change over time while related data remains constant, using multiple normalized tables lets you replace certain parts of the data without reloading the entire data set. Conversely, if you receive related data all bundled together, such as in JSON files, using complex types can save the overhead of splitting the related items across multiple tables.

• From a performance perspective:

  • In Parquet tables, Impala can skip columns that are not referenced in a query, avoiding the I/O penalty of reading the embedded data. When complex types are nested within a column, the data is physically divided at a very granular level; for example, a query referring to data nested multiple levels deep in a complex type column does not have to read all the data from that column, only the data for the relevant parts of the column type hierarchy.

  • Complex types avoid the possibility of expensive join queries when data from fact and dimension tables is processed in parallel across multiple hosts. All the information for a row containing complex types is typically to be in the same data block, and therefore does not need to be transmitted across the network when joining fields that are all part of the same row.

  • The tradeoff with complex types is that fewer rows fit in each data block. Whether it is better to have more data blocks with fewer rows, or fewer data blocks with many rows, depends on the distribution of your data and the characteristics of your query workload. If the complex columns are rarely referenced, using them might lower efficiency. If you are seeing low parallelism due to a small volume of data (relatively few data blocks) in each table partition, increasing the row size by including complex columns might produce more data blocks and thus spread the work more evenly across the cluster. See Scalability Considerations for Impala for more on this advanced topic.

Impala can query Parquet tables containing ARRAY, STRUCT, and MAP columns produced by Hive. There are some differences to be aware of between the Impala SQL and HiveQL syntax for complex types, primarily for queries.

Impala supports a subset of the syntax that Hive supports for specifying ARRAY, STRUCT, and MAP types in the CREATE TABLE statements.

Because Impala STRUCT columns include user-specified field names, you use the NAMED_STRUCT() constructor in Hive rather than the STRUCT() constructor when you populate an Impala STRUCT column using a Hive INSERT statement.

The Hive UNION type is not currently supported in Impala.

While Impala usually aims for a high degree of compatibility with HiveQL query syntax, Impala syntax differs from Hive for queries involving complex types. The differences are intended to provide extra flexibility for queries involving these kinds of tables.

• Impala uses dot notation for referring to element names or elements within complex types, and join notation for cross-referencing scalar columns with the elements of complex types within the same row, rather than the LATERAL VIEW clause and EXPLODE() function of HiveQL.
• Using join notation lets you use all the kinds of join queries with complex type columns. For example, you can use a LEFT OUTER JOIN, LEFT ANTI JOIN, or LEFT SEMI JOIN query to evaluate different scenarios where the complex columns do or do not contain any elements.
• You can include references to collection types inside subqueries and inline views. For example, you can construct a FROM clause where one of the "tables" is a subquery against a complex type column, or use a subquery against a complex type column as the argument to an IN or EXISTS clause.
• The Impala pseudocolumn POS lets you retrieve the position of elements in an array along with the elements themselves, equivalent to the POSEXPLODE() function of HiveQL. You do not use index notation to retrieve a single array element in a query; the join query loops through the array elements and you use WHERE clauses to specify which elements to return.

• Join clauses involving complex type columns do not require an ON or USING clause. Impala implicitly applies the join key so that the correct array entries or map elements are associated with the correct row from the table.

• Impala does not currently support the UNION complex type.

Complex type columns can only be used in tables or partitions with the Parquet file format.

Complex type columns cannot be used as partition key columns in a partitioned table.

When you use complex types with the ORDER BY, GROUP BY, HAVING, or WHERE clauses, you cannot refer to the column name by itself. Instead, you refer to the names of the scalar values within the complex type, such as the ITEM, POS, KEY, or VALUE pseudocolumns, or the field names from a STRUCT.

The maximum depth of nesting for complex types is 100 levels.

The maximum length of the column definition for any complex type, including declarations for any nested types, is 4000 characters.

For ideal performance and scalability, use small or medium-sized collections, where all the complex columns contain at most a few hundred megabytes per row. Remember, all the columns of a row are stored in the same HDFS data block, whose size in Parquet files typically ranges from 256 MB to 1 GB.

Including complex type columns in a table introduces some overhead that might make queries that do not reference those columns somewhat slower than Impala queries against tables without any complex type columns. Expect at most a 2x slowdown compared to tables that do not have any complex type columns.

Currently, the COMPUTE STATS statement does not collect any statistics for columns containing complex types. Impala uses heuristics to construct execution plans involving complex type columns.

Currently, Impala built-in functions and user-defined functions cannot accept complex types as parameters or produce them as function return values. (When the complex type values are materialized in an Impala result set, the result set contains the scalar components of the values, such as the POS or ITEM for an ARRAY, the KEY or VALUE for a MAP, or the fields of a STRUCT; these scalar data items can be used with built-in functions and UDFs as usual.)

Impala currently cannot write new data files containing complex type columns. Therefore, although the SELECT statement works for queries involving complex type columns, you cannot use a statement form that writes data to complex type columns, such as CREATE TABLE AS SELECT or INSERT ... SELECT. To create data files containing complex type data, use the Hive INSERT statement, or another ETL mechanism such as MapReduce jobs, Spark jobs, Pig, and so on.

Currently, Impala can query complex type columns only from Parquet tables or Parquet partitions within partitioned tables. Although you can use complex types in tables with Avro, text, and other file formats as part of your ETL pipeline, for example as intermediate tables populated through Hive, doing analytics through Impala requires that the data eventually ends up in a Parquet table. The requirement for Parquet data files means that you can use complex types with Impala tables hosted on other kinds of file storage systems such as Isilon and Amazon S3, but you cannot use Impala to query complex types from HBase tables. See File Format Support for Impala Complex Types for more details.

The definition of data_type, as seen in the CREATE TABLE and ALTER TABLE statements, now includes complex types in addition to primitive types:

  primitive_type
| array_type
| map_type
| struct_type

Unions are not currently supported.

Array, struct, and map column type declarations are specified in the CREATE TABLE statement. You can also add or change the type of complex columns through the ALTER TABLE statement.

Currently, Impala queries allow complex types only in tables that use the Parquet format. If an Impala query encounters complex types in a table or partition using another file format, the query returns a runtime error.

You can also use ALTER TABLE ... SET FILEFORMAT PARQUET to change the file format of an existing table containing complex types to Parquet, after which Impala can query it. Make sure to load Parquet files into the table after changing the file format, because the ALTER TABLE ... SET FILEFORMAT statement does not convert existing data to the new file format.

Partitioned tables can contain complex type columns. All the partition key columns must be scalar types.

Because use cases for Impala complex types require that you already have Parquet data files produced outside of Impala, you can use the Impala CREATE TABLE LIKE PARQUET syntax to produce a table with columns that match the structure of an existing Parquet file, including complex type columns for nested data structures. Remember to include the STORED AS PARQUET clause in this case, because even with CREATE TABLE LIKE PARQUET, the default file format of the resulting table is still text.

Because the complex columns are omitted from the result set of an Impala SELECT * or SELECT col_name query, and because Impala currently does not support writing Parquet files with complex type columns, you cannot use the CREATE TABLE AS SELECT syntax to create a table with nested type columns.

For example, when defining a table that holds contact information, you might represent phone numbers differently depending on the expected layout and relationships of the data, and how well you can predict those properties in advance.

Here are different ways that you might represent phone numbers in a traditional relational schema, with equivalent representations using complex types.

CREATE TABLE contacts_fixed_phones
(
    id BIGINT
  , name STRING
  , address STRING
  , home_phone STRING
  , work_phone STRING
  , mobile_phone STRING
) STORED AS PARQUET;

CREATE TABLE contacts_array_of_phones
(
    id BIGINT
  , name STRING
  , address STRING
  , phone_number ARRAY < STRING >
) STORED AS PARQUET;

CREATE TABLE contacts_unlimited_phones
(
  id BIGINT, name STRING, address STRING, phone_number MAP < STRING,STRING >
) STORED AS PARQUET;

CREATE TABLE fact_contacts (id BIGINT, name STRING, address STRING) STORED AS PARQUET;
CREATE TABLE dim_phones
(
    contact_id BIGINT
  , category STRING
  , international_code STRING
  , area_code STRING
  , exchange STRING
  , extension STRING
  , mobile BOOLEAN
  , carrier STRING
  , current BOOLEAN
  , service_start_date TIMESTAMP
  , service_end_date TIMESTAMP
)
STORED AS PARQUET;

CREATE TABLE contacts_detailed_phones
(
  id BIGINT, name STRING, address STRING
    , phone ARRAY < STRUCT <
        category: STRING
      , international_code: STRING
      , area_code: STRING
      , exchange: STRING
      , extension: STRING
      , mobile: BOOLEAN
      , carrier: STRING
      , current: BOOLEAN
      , service_start_date: TIMESTAMP
      , service_end_date: TIMESTAMP
    >>
) STORED AS PARQUET;

The Impala SQL statements that support complex types are currently CREATE TABLE, ALTER TABLE, DESCRIBE, LOAD DATA, and SELECT. That is, currently Impala can create or alter tables containing complex type columns, examine the structure of a table containing complex type columns, import existing data files containing complex type columns into a table, and query Parquet tables containing complex types.

Impala currently cannot write new data files containing complex type columns. Therefore, although the SELECT statement works for queries involving complex type columns, you cannot use a statement form that writes data to complex type columns, such as CREATE TABLE AS SELECT or INSERT ... SELECT. To create data files containing complex type data, use the Hive INSERT statement, or another ETL mechanism such as MapReduce jobs, Spark jobs, Pig, and so on.

Each element in an ARRAY type has a position, indexed starting from zero, and a value. Each element in a MAP type represents a key-value pair. Impala provides pseudocolumns that let you retrieve this metadata as part of a query, or filter query results by including such things in a WHERE clause. You refer to the pseudocolumns as part of qualified column names in queries:

• ITEM: The value of an array element. If the ARRAY contains STRUCT elements, you can refer to either array_name.ITEM.field_name or use the shorthand array_name.field_name.
• POS: The position of an element within an array.
• KEY: The value forming the first part of a key-value pair in a map. It is not necessarily unique.
• VALUE: The data item forming the second part of a key-value pair in a map. If the VALUE part of the MAP element is a STRUCT, you can refer to either map_name.VALUE.field_name or use the shorthand map_name.field_name.

Because the Impala INSERT statement does not currently support creating new data with complex type columns, or copying existing complex type values from one table to another, you primarily use Impala to query Parquet tables with complex types where the data was inserted through Hive, or create tables with complex types where you already have existing Parquet data files.

If you have created a Hive table with the Parquet file format and containing complex types, use the same table for Impala queries with no changes. If you have such a Hive table in some other format, use a Hive CREATE TABLE AS SELECT ... STORED AS PARQUET or INSERT ... SELECT statement to produce an equivalent Parquet table that Impala can query.

If you have existing Parquet data files containing complex types, located outside of any Impala or Hive table, such as data files created by Spark jobs, you can use an Impala CREATE TABLE ... STORED AS PARQUET statement, followed by an Impala LOAD DATA statement to move the data files into the table. As an alternative, you can use an Impala CREATE EXTERNAL TABLE statement to create a table pointing to the HDFS directory that already contains the data files.

Perhaps the simplest way to get started with complex type data is to take a denormalized table containing duplicated values, and use an INSERT ... SELECT statement to copy the data into a Parquet table and condense the repeated values into complex types. With the Hive INSERT statement, you use the COLLECT_LIST(), NAMED_STRUCT(), and MAP() constructor functions within a GROUP BY query to produce the complex type values. COLLECT_LIST() turns a sequence of values into an ARRAY. NAMED_STRUCT() uses the first, third, and so on arguments as the field names for a STRUCT, to match the field names from the CREATE TABLE statement.

The ARRAY, STRUCT, and MAP types can be the top-level types for "nested type" columns. That is, each of these types can contain other complex or scalar types, with multiple levels of nesting to a maximum depth of 100. For example, you can have an array of structures, a map containing other maps, a structure containing an array of other structures, and so on. At the lowest level, there are always scalar types making up the fields of a STRUCT, elements of an ARRAY, and keys and values of a MAP.

Schemas involving complex types typically use some level of nesting for the complex type columns.

For example, to model a relationship like a dimension table and a fact table, you typically use an ARRAY where each array element is a STRUCT. The STRUCT fields represent what would traditionally be columns in a separate joined table. It makes little sense to use a STRUCT as the top-level type for a column, because you could just make the fields of the STRUCT into regular table columns.

Perhaps the only use case for a top-level STRUCT would be to to allow STRUCT fields with the same name as columns to coexist in the same table. The following example shows how a table could have a column named ID, and two separate STRUCT fields also named ID. Because the STRUCT fields are always referenced using qualified names, the identical ID names do not cause a conflict.

CREATE TABLE struct_namespaces
(
  id BIGINT
  , s1 STRUCT < id: BIGINT, field1: STRING >
  , s2 STRUCT < id: BIGINT, when_happened: TIMESTAMP >
)
STORED AS PARQUET;

select id, s1.id, s2.id from struct_namespaces;

It is common to make the value portion of each key-value pair in a MAP a STRUCT, ARRAY of STRUCT, or other complex type variation. That way, each key in the MAP can be associated with a flexible and extensible data structure. The key values are not predefined ahead of time (other than by specifying their data type). Therefore, the MAP can accommodate a rapidly evolving schema, or sparse data structures where each row contains only a few data values drawn from a large set of possible choices.

Although you can use an ARRAY of scalar values as the top-level column in a table, such a simple array is typically of limited use for analytic queries. The only property of the array elements, aside from the element value, is the ordering sequence available through the POS pseudocolumn. To record any additional item about each array element, such as a TIMESTAMP or a symbolic name, you use an ARRAY of STRUCT rather than of scalar values.

If you are considering having multiple ARRAY or MAP columns, with related items under the same position in each ARRAY or the same key in each MAP, prefer to use a STRUCT to group all the related items into a single ARRAY or MAP. Doing so avoids the additional storage overhead and potential duplication of key values from having an extra complex type column. Also, because each ARRAY or MAP that you reference in the query SELECT list requires an additional join clause, minimizing the number of complex type columns also makes the query easier to read and maintain, relying more on dot notation to refer to the relevant fields rather than a sequence of join clauses.

For example, here is a table with several complex type columns all at the top level and containing only scalar types. To retrieve every data item for the row requires a separate join for each ARRAY or MAP column. The fields of the STRUCT can be referenced using dot notation, but there is no real advantage to using the STRUCT at the top level rather than just making separate columns FIELD1 and FIELD2.

CREATE TABLE complex_types_top_level
(
  id BIGINT,
  a1 ARRAY<INT>,
  a2 ARRAY<STRING>,
  s STRUCT<field1: INT, field2: STRING>,
-- Numeric lookup key for a string value.
  m1 MAP<INT,STRING>,
-- String lookup key for a numeric value.
  m2 MAP<STRING,INT>
)
STORED AS PARQUET;

describe complex_types_top_level;
+------+-----------------+
| name | type            |
+------+-----------------+
| id   | bigint          |
| a1   | array<int>      |
| a2   | array<string>   |
| s    | struct<         |
|      |   field1:int,   |
|      |   field2:string |
|      | >               |
| m1   | map<int,string> |
| m2   | map<string,int> |
+------+-----------------+

select
  id,
  a1.item,
  a2.item,
  s.field1,
  s.field2,
  m1.key,
  m1.value,
  m2.key,
  m2.value
from
  complex_types_top_level,
  complex_types_top_level.a1,
  complex_types_top_level.a2,
  complex_types_top_level.m1,
  complex_types_top_level.m2;

For example, here is a table with columns containing an ARRAY of STRUCT, a MAP where each key value is a STRUCT, and a MAP where each key value is an ARRAY of STRUCT.

CREATE TABLE nesting_demo
(
  user_id BIGINT,
  family_members ARRAY < STRUCT < name: STRING, email: STRING, date_joined: TIMESTAMP >>,
  foo map < STRING, STRUCT < f1: INT, f2: INT, f3: TIMESTAMP, f4: BOOLEAN >>,
  gameplay MAP < STRING , ARRAY < STRUCT <
    name: STRING, highest: BIGINT, lives_used: INT, total_spent: DECIMAL(16,2)
  >>>
)
STORED AS PARQUET;

The DESCRIBE statement rearranges the < and > separators and the field names within each STRUCT for easy readability:

DESCRIBE nesting_demo;
+----------------+-----------------------------+
| name           | type                        |
+----------------+-----------------------------+
| user_id        | bigint                      |
| family_members | array<struct<               |
|                |   name:string,              |
|                |   email:string,             |
|                |   date_joined:timestamp     |
|                | >>                          |
| foo            | map<string,struct<          |
|                |   f1:int,                   |
|                |   f2:int,                   |
|                |   f3:timestamp,             |
|                |   f4:boolean                |
|                | >>                          |
| gameplay       | map<string,array<struct<    |
|                |   name:string,              |
|                |   highest:bigint,           |
|                |   lives_used:int,           |
|                |   total_spent:decimal(16,2) |
|                | >>>                         |
+----------------+-----------------------------+

To query the complex type columns, you use join notation to refer to the lowest-level scalar values. If the value is an ARRAY element, the fully qualified name includes the ITEM pseudocolumn. If the value is inside a MAP, the fully qualified name includes the KEY or VALUE pseudocolumn. Each reference to a different ARRAY or MAP (even if nested inside another complex type) requires an additional join clause.

SELECT
-- The lone scalar field doesn't require any dot notation or join clauses.
    user_id
-- Retrieve the fields of a STRUCT inside an ARRAY.
-- The FAMILY_MEMBERS name refers to the FAMILY_MEMBERS table alias defined later in the FROM clause.
  , family_members.item.name
  , family_members.item.email
  , family_members.item.date_joined
-- Retrieve the KEY and VALUE fields of a MAP, with the value being a STRUCT consisting of more fields.
-- The FOO name refers to the FOO table alias defined later in the FROM clause.
  , foo.key
  , foo.value.f1
  , foo.value.f2
  , foo.value.f3
  , foo.value.f4
-- Retrieve the KEY fields of a MAP, and expand the VALUE part into ARRAY items consisting of STRUCT fields.
-- The GAMEPLAY name refers to the GAMEPLAY table alias defined later in the FROM clause (referring to the MAP item).
-- The GAME_N name refers to the GAME_N table alias defined later in the FROM clause (referring to the ARRAY
-- inside the MAP item's VALUE part.)
  , gameplay.key
  , game_n.name
  , game_n.highest
  , game_n.lives_used
  , game_n.total_spent
FROM
    nesting_demo
  , nesting_demo.family_members AS family_members
  , nesting_demo.foo AS foo
  , nesting_demo.gameplay AS gameplay
  , nesting_demo.gameplay.value AS game_n;

Once you understand the notation to refer to a particular data item in the SELECT list, you can use the same qualified name to refer to that data item in other parts of the query, such as the WHERE clause, ORDER BY or GROUP BY clauses, or calls to built-in functions. For example, you might frequently retrieve the VALUE part of each MAP item in the SELECT list, while choosing the specific MAP items by running comparisons against the KEY part in the WHERE clause.

The layout of complex and nested types is largely a physical consideration. The complex type columns reside in the same data files rather than in separate normalized tables, for your convenience in managing related data sets and performance in querying related data sets. You can use views to treat tables with complex types as if they were flattened. By putting the join logic and references to the complex type columns in the view definition, you can query the same tables using existing queries intended for tables containing only scalar columns. This technique also lets you use tables with complex types with BI tools that are not aware of the data types and query notation for accessing complex type columns.

For example, the variation of the TPC-H schema containing complex types has a table REGION. This table has 5 rows, corresponding to 5 regions such as NORTH AMERICA and AFRICA. Each row has an ARRAY column, where each array item is a STRUCT containing details about a country in that region.

DESCRIBE region;
+-------------+-------------------------+
| name        | type                    |
+-------------+-------------------------+
| r_regionkey | smallint                |
| r_name      | string                  |
| r_comment   | string                  |
| r_nations   | array<struct<           |
|             |   n_nationkey:smallint, |
|             |   n_name:string,        |
|             |   n_comment:string      |
|             | >>                      |
+-------------+-------------------------+

The same data could be represented in traditional denormalized form, as a single table where the information about each region is repeated over and over, alongside the information about each country. The nested complex types let us avoid the repetition, while still keeping the data in a single table rather than normalizing across multiple tables.

To use this table with a JDBC or ODBC application that expected scalar columns, we could create a view that represented the result set as a set of scalar columns (three columns from the original table, plus three more from the STRUCT fields of the array elements). In the following examples, any column with an R_* prefix is taken unchanged from the original table, while any column with an N_* prefix is extracted from the STRUCT inside the ARRAY.

CREATE VIEW region_view AS
  SELECT
    r_regionkey,
    r_name,
    r_comment,
    array_field.item.n_nationkey AS n_nationkey,
    array_field.item.n_name AS n_name,
    array_field.n_comment AS n_comment
FROM
  region, region.r_nations AS array_field;

Then we point the application queries at the view rather than the original table. From the perspective of the view, there are 25 rows in the result set, one for each nation in each region, and queries can refer freely to fields related to the region or the nation.

-- Retrieve info such as the nation name from the original R_NATIONS array elements.
select n_name from region_view where r_name in ('EUROPE', 'ASIA');
+----------------+
| n_name         |
+----------------+
| UNITED KINGDOM |
| RUSSIA         |
| ROMANIA        |
| GERMANY        |
| FRANCE         |
| VIETNAM        |
| CHINA          |
| JAPAN          |
| INDONESIA      |
| INDIA          |
+----------------+

-- UNITED STATES in AMERICA and UNITED KINGDOM in EUROPE.
SELECT DISTINCT r_name FROM region_view WHERE n_name LIKE 'UNITED%';
+---------+
| r_name  |
+---------+
| AMERICA |
| EUROPE  |
+---------+

-- For conciseness, we only list some view columns in the SELECT list.
-- SELECT * would bring back all the data, unlike SELECT *
-- queries on the original table with complex type columns.
SELECT r_regionkey, r_name, n_nationkey, n_name FROM region_view LIMIT 7;
+-------------+--------+-------------+----------------+
| r_regionkey | r_name | n_nationkey | n_name         |
+-------------+--------+-------------+----------------+
| 3           | EUROPE | 23          | UNITED KINGDOM |
| 3           | EUROPE | 22          | RUSSIA         |
| 3           | EUROPE | 19          | ROMANIA        |
| 3           | EUROPE | 7           | GERMANY        |
| 3           | EUROPE | 6           | FRANCE         |
| 2           | ASIA   | 21          | VIETNAM        |
| 2           | ASIA   | 18          | CHINA          |
+-------------+--------+-------------+----------------+

The tables used for earlier examples of complex type syntax are trivial ones with no actual data. The more substantial examples of the complex type feature use these tables, adapted from the schema used for TPC-H testing:

SHOW TABLES;
+----------+
| name     |
+----------+
| customer |
| part     |
| region   |
| supplier |
+----------+

DESCRIBE customer;
+--------------+------------------------------------+
| name         | type                               |
+--------------+------------------------------------+
| c_custkey    | bigint                             |
| c_name       | string                             |
| c_address    | string                             |
| c_nationkey  | smallint                           |
| c_phone      | string                             |
| c_acctbal    | decimal(12,2)                      |
| c_mktsegment | string                             |
| c_comment    | string                             |
| c_orders     | array<struct<                      |
|              |   o_orderkey:bigint,               |
|              |   o_orderstatus:string,            |
|              |   o_totalprice:decimal(12,2),      |
|              |   o_orderdate:string,              |
|              |   o_orderpriority:string,          |
|              |   o_clerk:string,                  |
|              |   o_shippriority:int,              |
|              |   o_comment:string,                |
|              |   o_lineitems:array<struct<        |
|              |     l_partkey:bigint,              |
|              |     l_suppkey:bigint,              |
|              |     l_linenumber:int,              |
|              |     l_quantity:decimal(12,2),      |
|              |     l_extendedprice:decimal(12,2), |
|              |     l_discount:decimal(12,2),      |
|              |     l_tax:decimal(12,2),           |
|              |     l_returnflag:string,           |
|              |     l_linestatus:string,           |
|              |     l_shipdate:string,             |
|              |     l_commitdate:string,           |
|              |     l_receiptdate:string,          |
|              |     l_shipinstruct:string,         |
|              |     l_shipmode:string,             |
|              |     l_comment:string               |
|              |   >>                               |
|              | >>                                 |
+--------------+------------------------------------+

DESCRIBE part;
+---------------+---------------+
| name          | type          |
+---------------+---------------+
| p_partkey     | bigint        |
| p_name        | string        |
| p_mfgr        | string        |
| p_brand       | string        |
| p_type        | string        |
| p_size        | int           |
| p_container   | string        |
| p_retailprice | decimal(12,2) |
| p_comment     | string        |
+---------------+---------------+

DESCRIBE region;
+-------------+--------------------------------------------------------------------+
| name        | type                                                               |
+-------------+--------------------------------------------------------------------+
| r_regionkey | smallint                                                           |
| r_name      | string                                                             |
| r_comment   | string                                                             |
| r_nations   | array<struct<n_nationkey:smallint,n_name:string,n_comment:string>> |
+-------------+--------------------------------------------------------------------+

DESCRIBE supplier;
+-------------+----------------------------------------------+
| name        | type                                         |
+-------------+----------------------------------------------+
| s_suppkey   | bigint                                       |
| s_name      | string                                       |
| s_address   | string                                       |
| s_nationkey | smallint                                     |
| s_phone     | string                                       |
| s_acctbal   | decimal(12,2)                                |
| s_comment   | string                                       |
| s_partsupps | array<struct<ps_partkey:bigint,              |
|             | ps_availqty:int,ps_supplycost:decimal(12,2), |
|             | ps_comment:string>>                          |
+-------------+----------------------------------------------+

The volume of data used in the following examples is:

SELECT count(*) FROM customer;
+----------+
| count(*) |
+----------+
| 150000   |
+----------+

SELECT count(*) FROM part;
+----------+
| count(*) |
+----------+
| 200000   |
+----------+

SELECT count(*) FROM region;
+----------+
| count(*) |
+----------+
| 5        |
+----------+

SELECT count(*) FROM supplier;
+----------+
| count(*) |
+----------+
| 10000    |
+----------+

The following examples demonstrate the Hive syntax to transform flat data (tables with all scalar columns) into Parquet tables where Impala can query the complex type columns. Each example shows the full sequence of steps, including switching back and forth between Impala and Hive. Although the source table can use any file format, the destination table must use the Parquet file format.

Create table with ARRAY in Impala, load data in Hive, query in Impala:

This example shows the cycle of creating the tables and querying the complex data in Impala, and using Hive (either the hive shell or beeline) for the data loading step. The data starts in flattened, denormalized form in a text table. Hive writes the corresponding Parquet data, including an ARRAY column. Then Impala can run analytic queries on the Parquet table, using join notation to unpack the ARRAY column.

/* Initial DDL and loading of flat, denormalized data happens in impala-shell */CREATE TABLE flat_array (country STRING, city STRING);INSERT INTO flat_array VALUES
    ('Canada', 'Toronto') , ('Canada', 'Vancouver') , ('Canada', "St. John\'s")
  , ('Canada', 'Saint John') , ('Canada', 'Montreal') , ('Canada', 'Halifax')
  , ('Canada', 'Winnipeg') , ('Canada', 'Calgary') , ('Canada', 'Saskatoon')
  , ('Canada', 'Ottawa') , ('Canada', 'Yellowknife') , ('France', 'Paris')
  , ('France', 'Nice') , ('France', 'Marseilles') , ('France', 'Cannes')
  , ('Greece', 'Athens') , ('Greece', 'Piraeus') , ('Greece', 'Hania')
  , ('Greece', 'Heraklion') , ('Greece', 'Rethymnon') , ('Greece', 'Fira');

CREATE TABLE complex_array (country STRING, city ARRAY <STRING>) STORED AS PARQUET;

/* Conversion to Parquet and complex and/or nested columns happens in Hive */

INSERT INTO complex_array SELECT country, collect_list(city) FROM flat_array GROUP BY country;
Query ID = dev_20151108160808_84477ff2-82bd-4ba4-9a77-554fa7b8c0cb
Total jobs = 1
Launching Job 1 out of 1
...

/* Back to impala-shell again for analytic queries */

REFRESH complex_array;
SELECT country, city.item FROM complex_array, complex_array.city
+---------+-------------+
| country | item        |
+---------+-------------+
| Canada  | Toronto     |
| Canada  | Vancouver   |
| Canada  | St. John's  |
| Canada  | Saint John  |
| Canada  | Montreal    |
| Canada  | Halifax     |
| Canada  | Winnipeg    |
| Canada  | Calgary     |
| Canada  | Saskatoon   |
| Canada  | Ottawa      |
| Canada  | Yellowknife |
| France  | Paris       |
| France  | Nice        |
| France  | Marseilles  |
| France  | Cannes      |
| Greece  | Athens      |
| Greece  | Piraeus     |
| Greece  | Hania       |
| Greece  | Heraklion   |
| Greece  | Rethymnon   |
| Greece  | Fira        |
+---------+-------------+

Create table with STRUCT and ARRAY in Impala, load data in Hive, query in Impala:

This example shows the cycle of creating the tables and querying the complex data in Impala, and using Hive (either the hive shell or beeline) for the data loading step. The data starts in flattened, denormalized form in a text table. Hive writes the corresponding Parquet data, including a STRUCT column with an ARRAY field. Then Impala can run analytic queries on the Parquet table, using join notation to unpack the ARRAY field from the STRUCT column.

/* Initial DDL and loading of flat, denormalized data happens in impala-shell */

CREATE TABLE flat_struct_array (continent STRING, country STRING, city STRING);
INSERT INTO flat_struct_array VALUES
    ('North America', 'Canada', 'Toronto') , ('North America', 'Canada', 'Vancouver')
  , ('North America', 'Canada', "St. John\'s") , ('North America', 'Canada', 'Saint John')
  , ('North America', 'Canada', 'Montreal') , ('North America', 'Canada', 'Halifax')
  , ('North America', 'Canada', 'Winnipeg') , ('North America', 'Canada', 'Calgary')
  , ('North America', 'Canada', 'Saskatoon') , ('North America', 'Canada', 'Ottawa')
  , ('North America', 'Canada', 'Yellowknife') , ('Europe', 'France', 'Paris')
  , ('Europe', 'France', 'Nice') , ('Europe', 'France', 'Marseilles')
  , ('Europe', 'France', 'Cannes') , ('Europe', 'Greece', 'Athens')
  , ('Europe', 'Greece', 'Piraeus') , ('Europe', 'Greece', 'Hania')
  , ('Europe', 'Greece', 'Heraklion') , ('Europe', 'Greece', 'Rethymnon')
  , ('Europe', 'Greece', 'Fira');

CREATE TABLE complex_struct_array (continent STRING, country STRUCT <name: STRING, city: ARRAY <STRING> >) STORED AS PARQUET;

/* Conversion to Parquet and complex and/or nested columns happens in Hive */

INSERT INTO complex_struct_array SELECT continent, named_struct('name', country, 'city', collect_list(city)) FROM flat_array_array GROUP BY continent, country;
Query ID = dev_20151108163535_11a4fa53-0003-4638-97e6-ef13cdb8e09e
Total jobs = 1
Launching Job 1 out of 1
...

/* Back to impala-shell again for analytic queries */

REFRESH complex_struct_array;
SELECT t1.continent, t1.country.name, t2.item
  FROM complex_struct_array t1, t1.country.city t2
+---------------+--------------+-------------+
| continent     | country.name | item        |
+---------------+--------------+-------------+
| Europe        | France       | Paris       |
| Europe        | France       | Nice        |
| Europe        | France       | Marseilles  |
| Europe        | France       | Cannes      |
| Europe        | Greece       | Athens      |
| Europe        | Greece       | Piraeus     |
| Europe        | Greece       | Hania       |
| Europe        | Greece       | Heraklion   |
| Europe        | Greece       | Rethymnon   |
| Europe        | Greece       | Fira        |
| North America | Canada       | Toronto     |
| North America | Canada       | Vancouver   |
| North America | Canada       | St. John's  |
| North America | Canada       | Saint John  |
| North America | Canada       | Montreal    |
| North America | Canada       | Halifax     |
| North America | Canada       | Winnipeg    |
| North America | Canada       | Calgary     |
| North America | Canada       | Saskatoon   |
| North America | Canada       | Ottawa      |
| North America | Canada       | Yellowknife |
+---------------+--------------+-------------+

One common use for complex types is to embed the contents of one table into another. The traditional technique of denormalizing results in a huge number of rows with some column values repeated over and over. With complex types, you can keep the same number of rows as in the original normalized table, and put all the associated data from the other table in a single new column.

In this flattening scenario, you might frequently use a column that is an ARRAY consisting of STRUCT elements, where each field within the STRUCT corresponds to a column name from the table that you are combining.

The following example shows a traditional normalized layout using two tables, and then an equivalent layout using complex types in a single table.

/* Traditional relational design */

-- This table just stores numbers, allowing us to look up details about the employee
-- and details about their vacation time using a three-table join query.
CREATE table employee_vacations
(
  employee_id BIGINT,
  vacation_id BIGINT
)
STORED AS PARQUET;

-- Each kind of information to track gets its own "fact table".
CREATE table vacation_details
(
  vacation_id BIGINT,
  vacation_start TIMESTAMP,
  duration INT
)
STORED AS PARQUET;

-- Any time we print a human-readable report, we join with this table to
-- display info about employee #1234.
CREATE TABLE employee_contact
(
  employee_id BIGINT,
  name STRING,
  address STRING,
  phone STRING,
  email STRING,
  address_type STRING /* 'home', 'work', 'remote', etc. */
)
STORED AS PARQUET;

/* Equivalent flattened schema using complex types */

-- For analytic queries using complex types, we can bundle the dimension table
-- and multiple fact tables into a single table.
CREATE TABLE employee_vacations_nested_types
(
-- We might still use the employee_id for other join queries.
-- The table needs at least one scalar column to serve as an identifier
-- for the complex type columns.
  employee_id BIGINT,

-- Columns of the VACATION_DETAILS table are folded into a STRUCT.
-- We drop the VACATION_ID column because Impala doesn't need
-- synthetic IDs to join a complex type column.
-- Each row from the VACATION_DETAILS table becomes an array element.
  vacation ARRAY < STRUCT <
    vacation_start: TIMESTAMP,
    duration: INT
  >>,

-- The ADDRESS_TYPE column, with a small number of predefined values that are distinct
-- for each employee, makes the EMPLOYEE_CONTACT table a good candidate to turn into a MAP,
-- with each row represented as a STRUCT. The string value from ADDRESS_TYPE becomes the
-- "key" (the anonymous first field) of the MAP.
  contact MAP < STRING, STRUCT <
    address: STRING,
    phone: STRING,
    email: STRING
  >>
)
STORED AS PARQUET;

You can produce Parquet data files through several Hadoop components and APIs, as explained in Using Apache Parquet Data Files with CDH.

If you have a Hive-created Parquet table that includes ARRAY, STRUCT, or MAP columns, Impala can query that same table in CDH 5.5 / Impala 2.3 and higher, subject to the usual restriction that all other columns are of data types supported by Impala, and also that the file type of the table must be Parquet.

If you have a Parquet data file produced outside of Impala, Impala can automatically deduce the appropriate table structure using the syntax CREATE TABLE ... LIKE PARQUET 'hdfs_path_of_parquet_file'. In CDH 5.5 / Impala 2.3 and higher, this feature works for Parquet files that include ARRAY, STRUCT, or MAP types.

/* In impala-shell, find the HDFS data directory of the original table.
DESCRIBE FORMATTED tpch_nested_parquet.customer;
...
| Location: | hdfs://localhost:20500/test-warehouse/tpch_nested_parquet.db/customer   | NULL |
...

# In the Unix shell, find the path of any Parquet data file in that HDFS directory.
$ hdfs dfs -ls hdfs://localhost:20500/test-warehouse/tpch_nested_parquet.db/customer
Found 4 items
-rwxr-xr-x   3 dev supergroup  171298918 2015-09-22 23:30 hdfs://localhost:20500/blah/tpch_nested_parquet.db/customer/000000_0
...

/* Back in impala-shell, use the HDFS path in a CREATE TABLE LIKE PARQUET statement. */
CREATE TABLE customer_ctlp
  LIKE PARQUET 'hdfs://localhost:20500/blah/tpch_nested_parquet.db/customer/000000_0'
  STORED AS PARQUET;

/* Confirm that old and new tables have the same column layout, including complex types. */
DESCRIBE tpch_nested_parquet.customer
+--------------+------------------------------------+---------+
| name         | type                               | comment |
+--------------+------------------------------------+---------+
| c_custkey    | bigint                             |         |
| c_name       | string                             |         |
| c_address    | string                             |         |
| c_nationkey  | smallint                           |         |
| c_phone      | string                             |         |
| c_acctbal    | decimal(12,2)                      |         |
| c_mktsegment | string                             |         |
| c_comment    | string                             |         |
| c_orders     | array<struct<                      |         |
|              |   o_orderkey:bigint,               |         |
|              |   o_orderstatus:string,            |         |
|              |   o_totalprice:decimal(12,2),      |         |
|              |   o_orderdate:string,              |         |
|              |   o_orderpriority:string,          |         |
|              |   o_clerk:string,                  |         |
|              |   o_shippriority:int,              |         |
|              |   o_comment:string,                |         |
|              |   o_lineitems:array<struct<        |         |
|              |     l_partkey:bigint,              |         |
|              |     l_suppkey:bigint,              |         |
|              |     l_linenumber:int,              |         |
|              |     l_quantity:decimal(12,2),      |         |
|              |     l_extendedprice:decimal(12,2), |         |
|              |     l_discount:decimal(12,2),      |         |
|              |     l_tax:decimal(12,2),           |         |
|              |     l_returnflag:string,           |         |
|              |     l_linestatus:string,           |         |
|              |     l_shipdate:string,             |         |
|              |     l_commitdate:string,           |         |
|              |     l_receiptdate:string,          |         |
|              |     l_shipinstruct:string,         |         |
|              |     l_shipmode:string,             |         |
|              |     l_comment:string               |         |
|              |   >>                               |         |
|              | >>                                 |         |
+--------------+------------------------------------+---------+

describe customer_ctlp;
+--------------+------------------------------------+-----------------------------+
| name         | type                               | comment                     |
+--------------+------------------------------------+-----------------------------+
| c_custkey    | bigint                             | Inferred from Parquet file. |
| c_name       | string                             | Inferred from Parquet file. |
| c_address    | string                             | Inferred from Parquet file. |
| c_nationkey  | int                                | Inferred from Parquet file. |
| c_phone      | string                             | Inferred from Parquet file. |
| c_acctbal    | decimal(12,2)                      | Inferred from Parquet file. |
| c_mktsegment | string                             | Inferred from Parquet file. |
| c_comment    | string                             | Inferred from Parquet file. |
| c_orders     | array<struct<                      | Inferred from Parquet file. |
|              |   o_orderkey:bigint,               |                             |
|              |   o_orderstatus:string,            |                             |
|              |   o_totalprice:decimal(12,2),      |                             |
|              |   o_orderdate:string,              |                             |
|              |   o_orderpriority:string,          |                             |
|              |   o_clerk:string,                  |                             |
|              |   o_shippriority:int,              |                             |
|              |   o_comment:string,                |                             |
|              |   o_lineitems:array<struct<        |                             |
|              |     l_partkey:bigint,              |                             |
|              |     l_suppkey:bigint,              |                             |
|              |     l_linenumber:int,              |                             |
|              |     l_quantity:decimal(12,2),      |                             |
|              |     l_extendedprice:decimal(12,2), |                             |
|              |     l_discount:decimal(12,2),      |                             |
|              |     l_tax:decimal(12,2),           |                             |
|              |     l_returnflag:string,           |                             |
|              |     l_linestatus:string,           |                             |
|              |     l_shipdate:string,             |                             |
|              |     l_commitdate:string,           |                             |
|              |     l_receiptdate:string,          |                             |
|              |     l_shipinstruct:string,         |                             |
|              |     l_shipmode:string,             |                             |
|              |     l_comment:string               |                             |
|              |   >>                               |                             |
|              | >>                                 |                             |
+--------------+------------------------------------+-----------------------------+