Funcionalidades e configurações

your_profile_name:
  target: dev
  outputs:
    dev:
      type: clickhouse

      # Optional
      schema: [default] # ClickHouse database for dbt models
      driver: [http] # http or native.  If not set this will be autodetermined based on port setting
      host: [localhost]
      port: [8123]  # If not set, defaults to 8123, 8443, 9000, 9440 depending on the secure and driver settings
      user: [default] # User for all database operations
      password: [<empty string>] # Password for the user
      cluster: [<empty string>] # If set, certain DDL/table operations will be executed with the `ON CLUSTER` clause using this cluster. Distributed materializations require this setting to work. See the following ClickHouse Cluster section for more details.
      verify: [True] # Validate TLS certificate if using TLS/SSL
      secure: [False] # Use TLS (native protocol) or HTTPS (http protocol)
      client_cert: [null] # Path to a TLS client certificate in .pem format
      client_cert_key: [null] # Path to the private key for the TLS client certificate
      server_host_name: [null] # Override the TLS SNI and hostname verification target. Useful when connecting via a DNS alias (e.g. an internal CNAME or AWS PrivateLink endpoint) where the TLS certificate is issued for a different hostname than the one used in `host`.
      retries: [1] # Number of times to retry a "retriable" database exception (such as a 503 'Service Unavailable' error)
      compression: [<empty string>] # Use gzip compression if truthy (http), or compression type for a native connection
      connect_timeout: [10] # Timeout in seconds to establish a connection to ClickHouse
      send_receive_timeout: [300] # Timeout in seconds to receive data from the ClickHouse server
      cluster_mode: [False] # Use specific settings designed to improve operation on Replicated databases (recommended for ClickHouse Cloud)
      use_lw_deletes: [False] # Use the strategy `delete+insert` as the default incremental strategy.
      check_exchange: [True] # Validate that clickhouse support the atomic EXCHANGE TABLES command.  (Not needed for most ClickHouse versions)
      local_suffix: [_local] # Table suffix of local tables on shards for distributed materializations.
      local_db_prefix: [<empty string>] # Database prefix of local tables on shards for distributed materializations. If empty, it uses the same database as the distributed table.
      allow_automatic_deduplication: [False] # Enable ClickHouse automatic deduplication for Replicated tables
      tcp_keepalive: [False] # Native client only, specify TCP keepalive configuration. Specify custom keepalive settings as [idle_time_sec, interval_sec, probes].
      reuse_connections: [True] # Re-use the same connection across models. Set to `False` to close the connection at the end of each model — useful on multi-replica ClickHouse Cloud services where the load balancer routes by TCP connection. Note: disabling connection reuse adds a new TCP/TLS handshake per model, which increases total `dbt run` wall time (typically ~200-500 ms per model). Combine with `threads > 1` for the best balance between distribution and throughput.
      custom_settings: [{}] # A dictionary/mapping of custom ClickHouse settings for the connection - default is empty.
      database_engine: '' # Database engine to use when creating new ClickHouse schemas (databases).  If not set (the default), new databases will use the default ClickHouse database engine (usually Atomic).
      threads: [1] # Number of threads to use when running queries. Before setting it to a number higher than 1, make sure to read the [consistência de leitura após gravação](#read-after-write-consistency) section.

      # Native (clickhouse-driver) connection settings
      sync_request_timeout: [5] # Timeout for server ping
      compress_block_size: [1048576] # Compression block size if compression is enabled

seeds:
  +quote_columns: false  #ou `true` se os cabeçalhos de coluna do CSV tiverem espaços

{{ config(
        engine='MergeTree',
        materialized='table',
        disable_on_cluster='true'
    )
}}

vars:
  taxi_s3:
    bucket: 'datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi'
    fmt: 'TabSeparatedWithNames'

select * from {{ clickhouse_s3source('taxi_s3', path='/trips_4.gz') }}

-- Example with REST Catalog
SET allow_experimental_database_iceberg = 1;

CREATE DATABASE iceberg_catalog
ENGINE = DataLakeCatalog('http://rest:8181/v1', 'admin', 'password')
SETTINGS
    catalog_type = 'rest',
    storage_endpoint = 'http://minio:9000/lakehouse',
    warehouse = 'demo'

version: 2

sources:
  - name: external_catalog
    database: iceberg_catalog
    tables:
      - name: orders
      - name: customers

SELECT
    o.order_id,
    c.customer_name,
    o.order_date
FROM {{ source('external_catalog', 'orders') }} o
INNER JOIN {{ source('external_catalog', 'customers') }} c
    ON o.customer_id = c.customer_id