🎉 New Destination: DuckDB

airbyte-config/init/src/main/resources/seed/destination_definitions.yaml

@@ -329,3 +329,10 @@
   documentationUrl: https://docs.airbyte.io/integrations/destinations/tidb
   icon: tidb.svg
   releaseStage: alpha
+- name: DuckDB
+  destinationDefinitionId: 94bd199c-2ff0-4aa2-b98e-17f0acb72610
+  dockerRepository: airbyte/destination-duckdb
+  dockerImageTag: 0.1.0
+  documentationUrl: https://docs.airbyte.io/integrations/destinations/duckdb
+  icon: duckdb.svg
+  releaseStage: alpha

airbyte-config/init/src/main/resources/seed/destination_specs.yaml

@@ -5800,3 +5800,19 @@
     supported_destination_sync_modes:
     - "overwrite"
     - "append"
+- dockerImage: "airbyte/destination-duckdb:0.1.0"
+  spec:
+    documentationUrl: "https://docs.airbyte.io/integrations/destinations/duckdb"
+    connectionSpecification:
+      $schema: "http://json-schema.org/draft-07/schema#"
+      title: "DuckDB Destination Spec"
+      type: "object"
+      required:
+      - "destination_path"
+      additionalProperties: false
+    supportsIncremental: true
+    supportsNormalization: true
+    supportsDBT: true
+    supported_destination_sync_modes:
+    - "overwrite"
+    - "append"

airbyte-integrations/bases/base-normalization/Dockerfile

@@ -28,5 +28,5 @@ WORKDIR /airbyte
 ENV AIRBYTE_ENTRYPOINT "/airbyte/entrypoint.sh"
 ENTRYPOINT ["/airbyte/entrypoint.sh"]
 
-LABEL io.airbyte.version=0.2.22
+LABEL io.airbyte.version=0.2.23
 LABEL io.airbyte.name=airbyte/normalization

airbyte-integrations/bases/base-normalization/build.gradle

@@ -83,6 +83,10 @@ task airbyteDockerTiDB(type: Exec, dependsOn: checkSshScriptCopy) {
     configure buildAirbyteDocker('tidb')
     dependsOn assemble
 }
+task airbyteDockerDuckDB(type: Exec, dependsOn: checkSshScriptCopy) {
+    configure buildAirbyteDocker('duckdb')
+    dependsOn assemble
+}
 
 airbyteDocker.dependsOn(airbyteDockerMSSql)
 airbyteDocker.dependsOn(airbyteDockerMySql)
@@ -91,6 +95,7 @@ airbyteDocker.dependsOn(airbyteDockerClickhouse)
 airbyteDocker.dependsOn(airbyteDockerSnowflake)
 airbyteDocker.dependsOn(airbyteDockerRedshift)
 airbyteDocker.dependsOn(airbyteDockerTiDB)
+airbyteDocker.dependsOn(airbyteDockerDuckDB)
 
 task("customIntegrationTestPython", type: PythonTask, dependsOn: installTestReqs) {
     module = "pytest"
@@ -106,6 +111,7 @@ task("customIntegrationTestPython", type: PythonTask, dependsOn: installTestReqs
     dependsOn ':airbyte-integrations:connectors:destination-mssql:airbyteDocker'
     dependsOn ':airbyte-integrations:connectors:destination-clickhouse:airbyteDocker'
     dependsOn ':airbyte-integrations:connectors:destination-tidb:airbyteDocker'
+    dependsOn ':airbyte-integrations:connectors:destination-duckdb:airbyteDocker'
 }
 
 // not really sure what this task does differently from customIntegrationTestPython, but it seems to also run integration tests
@@ -120,6 +126,7 @@ project.tasks.findByName('_customIntegrationTestsCoverage').dependsOn ':airbyte-
 project.tasks.findByName('_customIntegrationTestsCoverage').dependsOn ':airbyte-integrations:connectors:destination-mssql:airbyteDocker'
 project.tasks.findByName('_customIntegrationTestsCoverage').dependsOn ':airbyte-integrations:connectors:destination-clickhouse:airbyteDocker'
 project.tasks.findByName('_customIntegrationTestsCoverage').dependsOn ':airbyte-integrations:connectors:destination-tidb:airbyteDocker'
+project.tasks.findByName('_customIntegrationTestsCoverage').dependsOn ':airbyte-integrations:connectors:destination-duckdb:airbyteDocker'
 
 // DATs have some additional tests that exercise normalization code paths,
 // so we want to run these in addition to the base-normalization integration tests.

airbyte-integrations/bases/base-normalization/dbt-project-template-duckdb/dbt_project.yml

@@ -0,0 +1,63 @@
+# This file is necessary to install dbt-utils with dbt deps
+# the content will be overwritten by the transform function
+
+# Name your package! Package names should contain only lowercase characters
+# and underscores. A good package name should reflect your organization's
+# name or the intended use of these models
+name: "airbyte_utils"
+version: "1.0"
+config-version: 2
+
+# This setting configures which "profile" dbt uses for this project. Profiles contain
+# database connection information, and should be configured in the  ~/.dbt/profiles.yml file
+profile: "normalize"
+
+# These configurations specify where dbt should look for different types of files.
+# The `model-paths` config, for example, states that source models can be found
+# in the "models/" directory. You probably won't need to change these!
+model-paths: ["models"]
+docs-paths: ["docs"]
+analysis-paths: ["analysis"]
+test-paths: ["tests"]
+seed-paths: ["data"]
+macro-paths: ["macros"]
+
+target-path: "../build" # directory which will store compiled SQL files
+log-path: "../logs" # directory which will store DBT logs
+packages-install-path: "/dbt" # directory which will store external DBT dependencies
+
+clean-targets: # directories to be removed by `dbt clean`
+  - "build"
+  - "dbt_modules"
+
+quoting:
+  database: true
+  # Temporarily disabling the behavior of the ExtendedNameTransformer on table/schema names, see (issue #1785)
+  # all schemas should be unquoted
+  schema: false
+  identifier: true
+
+# You can define configurations for models in the `model-paths` directory here.
+# Using these configurations, you can enable or disable models, change how they
+# are materialized, and more!
+models:
+  airbyte_utils:
+    +materialized: table
+    generated:
+      airbyte_ctes:
+        +tags: airbyte_internal_cte
+        +materialized: ephemeral
+      airbyte_incremental:
+        +tags: incremental_tables
+        +materialized: incremental
+        +on_schema_change: sync_all_columns
+      airbyte_tables:
+        +tags: normalized_tables
+        +materialized: table
+      airbyte_views:
+        +tags: airbyte_internal_views
+        +materialized: view
+
+dispatch:
+  - macro_namespace: dbt_utils
+    search_order: ["airbyte_utils", "dbt_utils"]

airbyte-integrations/bases/base-normalization/dbt-project-template-duckdb/packages.yml

@@ -0,0 +1,5 @@
+# add dependencies. these will get pulled during the `dbt deps` process.
+
+packages:
+  - git: "https://github.com/fishtown-analytics/dbt-utils.git"
+    revision: 0.8.2

airbyte-integrations/bases/base-normalization/dbt-project-template/macros/cross_db_utils/array.sql

@@ -46,6 +46,10 @@
     left join joined on _airbyte_{{ stream_name }}_hashid = joined._airbyte_hashid
 {%- endmacro %}
 
+{% macro duckdb__cross_join_unnest(stream_name, array_col) -%}
+    left join joined on _airbyte_{{ stream_name }}_hashid = joined._airbyte_hashid
+{%- endmacro %}
+
 {% macro redshift__cross_join_unnest(stream_name, array_col) -%}
     left join joined on _airbyte_{{ stream_name }}_hashid = joined._airbyte_hashid
 {%- endmacro %}
@@ -95,6 +99,10 @@
     _airbyte_nested_data
 {%- endmacro %}
 
+{% macro duckdb__unnested_column_value(column_col) -%}
+    _airbyte_nested_data
+{%- endmacro %}
+
 {% macro oracle__unnested_column_value(column_col) -%}
     {{ column_col }}
 {%- endmacro %}
@@ -193,3 +201,7 @@ joined as (
 {% macro tidb__unnest_cte(from_table, stream_name, column_col) -%}
     {{ mysql__unnest_cte(from_table, stream_name, column_col) }}
 {%- endmacro %}
+
+{% macro duckdb__unnest_cte(from_table, stream_name, column_col) -%}
+    {{ mysql__unnest_cte(from_table, stream_name, column_col) }}
+{%- endmacro %}

airbyte-integrations/bases/base-normalization/dbt-project-template/macros/cross_db_utils/concat.sql

@@ -30,3 +30,7 @@
 {% macro tidb__concat(fields) -%}
     concat({{ fields|join(', ') }})
 {%- endmacro %}
+
+{% macro duckdb__concat(fields) -%}
+    concat({{ fields|join(', ') }})
+{%- endmacro %}

airbyte-integrations/bases/base-normalization/dbt-project-template/macros/cross_db_utils/datatypes.sql

@@ -44,6 +44,9 @@
     json
 {%- endmacro -%}
 
+{%- macro duckdb__type_json() -%}
+    json
+{%- endmacro -%}
 
 {# string ------------------------------------------------- #}
 
@@ -72,6 +75,10 @@
     char(1000)
 {%- endmacro -%}
 
+{%- macro duckdb__type_string() -%}
+    VARCHAR
+{%- endmacro -%}
+
 {# float ------------------------------------------------- #}
 {% macro mysql__type_float() %}
     float
@@ -89,6 +96,10 @@
     float
 {% endmacro %}
 
+{% macro duckdb__type_float() %}
+    DOUBLE
+{% endmacro %}
+
 {# int  ------------------------------------------------- #}
 {% macro default__type_int() %}
     int
@@ -110,6 +121,10 @@
     signed
 {% endmacro %}
 
+{% macro duckdb__type_int() %}
+    INTEGER
+{% endmacro %}
+
 {# bigint ------------------------------------------------- #}
 {% macro mysql__type_bigint() %}
     signed
@@ -127,6 +142,10 @@
     signed
 {% endmacro %}
 
+{% macro duckdb__type_bigint() %}
+    BIGINT
+{% endmacro %}
+
 {# numeric ------------------------------------------------- --#}
 {% macro mysql__type_numeric() %}
     float
@@ -140,6 +159,10 @@
     float
 {% endmacro %}
 
+{% macro duckdb__type_numeric() %}
+    DOUBLE
+{% endmacro %}
+
 {# very_large_integer --------------------------------------- --#}
 {#
 Most databases don't have a true unbounded numeric datatype, so we use a really big numeric field.
@@ -170,6 +193,10 @@ so this macro needs to be called very_large_integer.
     decimal(38, 0)
 {% endmacro %}
 
+{% macro duckdb__type_very_large_integer() %}
+    DECIMAL(38, 0)
+{% endmacro %}
+
 {# timestamp ------------------------------------------------- --#}
 {% macro mysql__type_timestamp() %}
     time
@@ -189,6 +216,10 @@ so this macro needs to be called very_large_integer.
     time
 {% endmacro %}
 
+{% macro duckdb__type_timestamp() %}
+    TIMESTAMP
+{% endmacro %}
+
 {# timestamp with time zone  -------------------------------------------------     #}
 
 {%- macro type_timestamp_with_timezone() -%}
@@ -229,6 +260,10 @@ so this macro needs to be called very_large_integer.
     char(1000)
 {%- endmacro -%}
 
+{%- macro duckdb__type_timestamp_with_timezone() -%}
+    TIMESTAMPTZ
+{%- endmacro -%}
+
 {# timestamp without time zone  -------------------------------------------------     #}
 
 {%- macro type_timestamp_without_timezone() -%}
@@ -261,6 +296,10 @@ so this macro needs to be called very_large_integer.
     datetime
 {% endmacro %}
 
+{% macro duckdb__type_timestamp_without_timezone() %}
+    TIMESTAMP
+{% endmacro %}
+
 {# time without time zone  -------------------------------------------------     #}
 
 {%- macro type_time_without_timezone() -%}
@@ -287,6 +326,9 @@ so this macro needs to be called very_large_integer.
     time
 {% endmacro %}
 
+{% macro duckdb__type_time_without_timezone() %}
+    TIMESTAMP 
+{% endmacro %}
 
 {# time with time zone  -------------------------------------------------     #}
 
@@ -330,6 +372,9 @@ so this macro needs to be called very_large_integer.
     char(1000)
 {%- endmacro -%}
 
+{%- macro duckdb__type_time_with_timezone() -%}
+    TIMESTAMPTZ
+{%- endmacro -%}
 {# date  -------------------------------------------------     #}
 
 {%- macro type_date() -%}

airbyte-integrations/bases/base-normalization/dbt-project-template/macros/cross_db_utils/json_operations.sql

@@ -7,6 +7,7 @@
     - MySQL: JSON_EXTRACT(json_doc, 'path' [, 'path'] ...) -> https://dev.mysql.com/doc/refman/8.0/en/json-search-functions.html
     - ClickHouse: JSONExtractString(json_doc, 'path' [, 'path'] ...) -> https://clickhouse.com/docs/en/sql-reference/functions/json-functions/
     - TiDB: JSON_EXTRACT(json_doc, 'path' [, 'path'] ...) -> https://docs.pingcap.com/tidb/stable/json-functions
+    - DuckDB: json_extract(json, 'path') note: If path is a LIST, the result will be a LIST of JSON -> https://duckdb.org/docs/extensions/json
 #}
 
 {# format_json_path --------------------------------------------------     #}
@@ -103,6 +104,11 @@
     {{ "'$.\"" ~ json_path_list|join(".") ~ "\"'" }}
 {%- endmacro %}
 
+{% macro duckdb__format_json_path(json_path_list) -%}
+    {# -- '$."x"."y"."z"' #}
+    {{ "'$.\"" ~ json_path_list|join(".") ~ "\"'" }}
+{%- endmacro %}
+
 {# json_extract -------------------------------------------------     #}
 
 {% macro json_extract(from_table, json_column, json_path_list, normalized_json_path) -%}
@@ -180,6 +186,14 @@
     {% endif -%}
 {%- endmacro %}
 
+{% macro duckdb__json_extract(from_table, json_column, json_path_list, normalized_json_path) -%}
+    {%- if from_table|string() == '' %}
+        json_extract({{ json_column }}, {{ format_json_path(normalized_json_path) }})
+    {% else %}
+        json_extract({{ from_table }}.{{ json_column }}, {{ format_json_path(normalized_json_path) }})
+    {% endif -%}
+{%- endmacro %}
+
 {# json_extract_scalar -------------------------------------------------     #}
 
 {% macro json_extract_scalar(json_column, json_path_list, normalized_json_path) -%}
@@ -234,6 +248,14 @@
     )
 {%- endmacro %}
 
+{% macro duckdb__json_extract_scalar(json_column, json_path_list, normalized_json_path) -%}
+    IF(
+        JSON_UNQUOTE(JSON_EXTRACT({{ json_column }}, {{ format_json_path(normalized_json_path) }})) = 'null',
+        NULL,
+        JSON_UNQUOTE(JSON_EXTRACT({{ json_column }}, {{ format_json_path(normalized_json_path) }}))
+    )
+{%- endmacro %}
+
 {# json_extract_array -------------------------------------------------     #}
 
 {% macro json_extract_array(json_column, json_path_list, normalized_json_path) -%}
@@ -284,6 +306,10 @@
     json_extract({{ json_column }}, {{ format_json_path(normalized_json_path) }})
 {%- endmacro %}
 
+{% macro duckdb__json_extract_array(json_column, json_path_list, normalized_json_path) -%}
+    json_extract({{ json_column }}, {{ format_json_path(normalized_json_path) }})
+{%- endmacro %}
+
 {# json_extract_string_array -------------------------------------------------     #}
 
 {% macro json_extract_string_array(json_column, json_path_list, normalized_json_path) -%}