airbyte-cdk 6.9.1.dev2__py3-none-any.whl → 6.9.1rc2__py3-none-any.whl

airbyte_cdk/sources/declarative/concurrent_declarative_source.py

@@ -86,23 +86,10 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
             component_factory=component_factory,
         )
 
+        # todo: We could remove state from initialization. Now that streams are grouped during the read(), a source
+        #  no longer needs to store the original incoming state. But maybe there's an edge case?
         self._state = state
 
-        self._concurrent_streams: Optional[List[AbstractStream]]
-        self._synchronous_streams: Optional[List[Stream]]
-
-        # If the connector command was SPEC, there is no incoming config, and we cannot instantiate streams because
-        # they might depend on it. Ideally we want to have a static method on this class to get the spec without
-        # any other arguments, but the existing entrypoint.py isn't designed to support this. Just noting this
-        # for our future improvements to the CDK.
-        if config:
-            self._concurrent_streams, self._synchronous_streams = self._group_streams(
-                config=config or {}
-            )
-        else:
-            self._concurrent_streams = None
-            self._synchronous_streams = None
-
         concurrency_level_from_manifest = self._source_config.get("concurrency_level")
         if concurrency_level_from_manifest:
             concurrency_level_component = self._constructor.create_component(
@@ -136,17 +123,20 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
         logger: logging.Logger,
         config: Mapping[str, Any],
         catalog: ConfiguredAirbyteCatalog,
-        state: Optional[Union[List[AirbyteStateMessage]]] = None,
+        state: Optional[List[AirbyteStateMessage]] = None,
     ) -> Iterator[AirbyteMessage]:
-        # ConcurrentReadProcessor pops streams that are finished being read so before syncing, the names of the concurrent
-        # streams must be saved so that they can be removed from the catalog before starting synchronous streams
-        if self._concurrent_streams:
+        concurrent_streams, _ = self._group_streams(config=config)
+
+        # ConcurrentReadProcessor pops streams that are finished being read so before syncing, the names of
+        # the concurrent streams must be saved so that they can be removed from the catalog before starting
+        # synchronous streams
+        if len(concurrent_streams) > 0:
             concurrent_stream_names = set(
-                [concurrent_stream.name for concurrent_stream in self._concurrent_streams]
+                [concurrent_stream.name for concurrent_stream in concurrent_streams]
             )
 
             selected_concurrent_streams = self._select_streams(
-                streams=self._concurrent_streams, configured_catalog=catalog
+                streams=concurrent_streams, configured_catalog=catalog
             )
             # It would appear that passing in an empty set of streams causes an infinite loop in ConcurrentReadProcessor.
             # This is also evident in concurrent_source_adapter.py so I'll leave this out of scope to fix for now
@@ -165,8 +155,7 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
         yield from super().read(logger, config, filtered_catalog, state)
 
     def discover(self, logger: logging.Logger, config: Mapping[str, Any]) -> AirbyteCatalog:
-        concurrent_streams = self._concurrent_streams or []
-        synchronous_streams = self._synchronous_streams or []
+        concurrent_streams, synchronous_streams = self._group_streams(config=config)
         return AirbyteCatalog(
             streams=[
                 stream.as_airbyte_stream() for stream in concurrent_streams + synchronous_streams
@@ -192,9 +181,13 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
 
         state_manager = ConnectorStateManager(state=self._state)  # type: ignore  # state is always in the form of List[AirbyteStateMessage]. The ConnectorStateManager should use generics, but this can be done later
 
-        name_to_stream_mapping = {
-            stream["name"]: stream for stream in self.resolved_manifest["streams"]
-        }
+        # Combine streams and dynamic_streams. Note: both cannot be empty at the same time,
+        # and this is validated during the initialization of the source.
+        streams = self._stream_configs(self._source_config) + self._dynamic_stream_configs(
+            self._source_config, config
+        )
+
+        name_to_stream_mapping = {stream["name"]: stream for stream in streams}
 
         for declarative_stream in self.streams(config=config):
             # Some low-code sources use a combination of DeclarativeStream and regular Python streams. We can't inspect
@@ -202,7 +195,7 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
             # so we need to treat them as synchronous
             if (
                 isinstance(declarative_stream, DeclarativeStream)
-                and name_to_stream_mapping[declarative_stream.name].get("retriever")["type"]
+                and name_to_stream_mapping[declarative_stream.name]["retriever"]["type"]
                 == "SimpleRetriever"
             ):
                 incremental_sync_component_definition = name_to_stream_mapping[
@@ -211,7 +204,7 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
 
                 partition_router_component_definition = (
                     name_to_stream_mapping[declarative_stream.name]
-                    .get("retriever")
+                    .get("retriever", {})
                     .get("partition_router")
                 )
                 is_without_partition_router_or_cursor = not bool(
@@ -233,7 +226,7 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
                     cursor = self._constructor.create_concurrent_cursor_from_datetime_based_cursor(
                         state_manager=state_manager,
                         model_type=DatetimeBasedCursorModel,
-                        component_definition=incremental_sync_component_definition,
+                        component_definition=incremental_sync_component_definition,  # type: ignore  # Not None because of the if condition above
                         stream_name=declarative_stream.name,
                         stream_namespace=declarative_stream.namespace,
                         config=config or {},
@@ -316,10 +309,11 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
     def _is_datetime_incremental_without_partition_routing(
         self,
         declarative_stream: DeclarativeStream,
-        incremental_sync_component_definition: Mapping[str, Any],
+        incremental_sync_component_definition: Mapping[str, Any] | None,
     ) -> bool:
         return (
-            bool(incremental_sync_component_definition)
+            incremental_sync_component_definition is not None
+            and bool(incremental_sync_component_definition)
             and incremental_sync_component_definition.get("type", "")
             == DatetimeBasedCursorModel.__name__
             and self._stream_supports_concurrent_partition_processing(

airbyte_cdk/sources/declarative/datetime/datetime_parser.py

@@ -37,17 +37,17 @@ class DatetimeParser:
             return parsed_datetime.replace(tzinfo=datetime.timezone.utc)
         return parsed_datetime
 
-    def format(self, dt: datetime.datetime, format: str) -> str:
+    def format(self, dt: datetime.datetime, format: str) -> Union[str, int]:
         # strftime("%s") is unreliable because it ignores the time zone information and assumes the time zone of the system it's running on
         # It's safer to use the timestamp() method than the %s directive
         # See https://stackoverflow.com/a/4974930
         if format == "%s":
-            return str(int(dt.timestamp()))
+            return int(dt.timestamp())
         if format == "%s_as_float":
-            return str(float(dt.timestamp()))
+            return float(dt.timestamp())
         if format == "%ms":
             # timstamp() returns a float representing the number of seconds since the unix epoch
-            return str(int(dt.timestamp() * 1000))
+            return int(dt.timestamp() * 1000)
         else:
             return dt.strftime(format)
 

airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -7,8 +7,12 @@ version: 1.0.0
 required:
   - type
   - check
-  - streams
   - version
+anyOf:
+  - required:
+      - streams
+  - required:
+      - dynamic_streams
 properties:
   type:
     type: string
@@ -19,6 +23,10 @@ properties:
     type: array
     items:
       "$ref": "#/definitions/DeclarativeStream"
+  dynamic_streams:
+    type: array
+    items:
+      "$ref": "#/definitions/DynamicDeclarativeStream"
   version:
     type: string
     description: The version of the Airbyte CDK used to build and test the source.
@@ -1321,7 +1329,7 @@ definitions:
         type: array
         items:
           - type: string
-        interpolation_content:
+        interpolation_context:
           - config
         examples:
           - ["data"]
@@ -2895,6 +2903,96 @@ definitions:
       $parameters:
         type: object
         additionalProperties: true
+  ComponentMappingDefinition:
+    title: Component Mapping Definition
+    description: (This component is experimental. Use at your own risk.) Specifies a mapping definition to update or add fields in a record or configuration. This allows dynamic mapping of data by interpolating values into the template based on provided contexts.
+    type: object
+    required:
+      - type
+      - field_path
+      - value
+    properties:
+      type:
+        type: string
+        enum: [ComponentMappingDefinition]
+      field_path:
+        title: Field Path
+        description: A list of potentially nested fields indicating the full path where value will be added or updated.
+        type: array
+        items:
+          - type: string
+        interpolation_context:
+          - config
+          - components_values
+          - stream_template_config
+        examples:
+          - ["data"]
+          - ["data", "records"]
+          - ["data", "{{ parameters.name }}"]
+          - ["data", "*", "record"]
+      value:
+        title: Value
+        description: The dynamic or static value to assign to the key. Interpolated values can be used to dynamically determine the value during runtime.
+        type: string
+        interpolation_context:
+          - config
+          - stream_template_config
+          - components_values
+        examples:
+          - "{{ components_values['updates'] }}"
+          - "{{ components_values['MetaData']['LastUpdatedTime'] }}"
+          - "{{ config['segment_id'] }}"
+      value_type:
+        title: Value Type
+        description: The expected data type of the value. If omitted, the type will be inferred from the value provided.
+        "$ref": "#/definitions/ValueType"
+      $parameters:
+        type: object
+        additionalProperties: true
+  HttpComponentsResolver:
+    type: object
+    description: (This component is experimental. Use at your own risk.) Component resolve and populates stream templates with components fetched via an HTTP retriever.
+    properties:
+      type:
+        type: string
+        enum: [HttpComponentsResolver]
+      retriever:
+        title: Retriever
+        description: Component used to coordinate how records are extracted across stream slices and request pages.
+        anyOf:
+          - "$ref": "#/definitions/AsyncRetriever"
+          - "$ref": "#/definitions/CustomRetriever"
+          - "$ref": "#/definitions/SimpleRetriever"
+      components_mapping:
+        type: array
+        items:
+          "$ref": "#/definitions/ComponentMappingDefinition"
+      $parameters:
+        type: object
+        additionalProperties: true
+    required:
+      - type
+      - retriever
+      - components_mapping
+  DynamicDeclarativeStream:
+    type: object
+    description: (This component is experimental. Use at your own risk.) A component that described how will be created declarative streams based on stream template.
+    properties:
+      type:
+        type: string
+        enum: [DynamicDeclarativeStream]
+      stream_template:
+        title: Stream Template
+        description: Reference to the stream template.
+        "$ref": "#/definitions/DeclarativeStream"
+      components_resolver:
+        title: Components Resolver
+        description: Component resolve and populates stream templates with components values.
+        "$ref": "#/definitions/HttpComponentsResolver"
+    required:
+      - type
+      - stream_template
+      - components_resolver
 interpolation:
   variables:
     - title: config

airbyte_cdk/sources/declarative/incremental/datetime_based_cursor.py

@@ -248,7 +248,7 @@ class DatetimeBasedCursor(DeclarativeCursor):
         return datetime.datetime.min.replace(tzinfo=datetime.timezone.utc)
 
     def _format_datetime(self, dt: datetime.datetime) -> str:
-        return self._parser.format(dt, self.datetime_format)
+        return str(self._parser.format(dt, self.datetime_format))
 
     def _partition_daterange(
         self,

airbyte_cdk/sources/declarative/manifest_declarative_source.py

@@ -39,6 +39,7 @@ from airbyte_cdk.sources.declarative.parsers.manifest_reference_resolver import
 from airbyte_cdk.sources.declarative.parsers.model_to_component_factory import (
     ModelToComponentFactory,
 )
+from airbyte_cdk.sources.declarative.resolvers import COMPONENTS_RESOLVER_TYPE_MAPPING
 from airbyte_cdk.sources.message import MessageRepository
 from airbyte_cdk.sources.streams.core import Stream
 from airbyte_cdk.sources.types import ConnectionDefinition
@@ -120,7 +121,10 @@ class ManifestDeclarativeSource(DeclarativeSource):
         self._emit_manifest_debug_message(
             extra_args={"source_name": self.name, "parsed_config": json.dumps(self._source_config)}
         )
-        stream_configs = self._stream_configs(self._source_config)
+
+        stream_configs = self._stream_configs(self._source_config) + self._dynamic_stream_configs(
+            self._source_config, config
+        )
 
         source_streams = [
             self._constructor.create_component(
@@ -234,7 +238,8 @@ class ManifestDeclarativeSource(DeclarativeSource):
             )
 
         streams = self._source_config.get("streams")
-        if not streams:
+        dynamic_streams = self._source_config.get("dynamic_streams")
+        if not (streams or dynamic_streams):
             raise ValidationError(
                 f"A valid manifest should have at least one stream defined. Got {streams}"
             )
@@ -303,5 +308,51 @@ class ManifestDeclarativeSource(DeclarativeSource):
                 s["type"] = "DeclarativeStream"
         return stream_configs
 
+    def _dynamic_stream_configs(
+        self, manifest: Mapping[str, Any], config: Mapping[str, Any]
+    ) -> List[Dict[str, Any]]:
+        dynamic_stream_definitions: List[Dict[str, Any]] = manifest.get("dynamic_streams", [])
+        dynamic_stream_configs: List[Dict[str, Any]] = []
+
+        for dynamic_definition in dynamic_stream_definitions:
+            components_resolver_config = dynamic_definition["components_resolver"]
+
+            if not components_resolver_config:
+                raise ValueError(
+                    f"Missing 'components_resolver' in dynamic definition: {dynamic_definition}"
+                )
+
+            resolver_type = components_resolver_config.get("type")
+            if not resolver_type:
+                raise ValueError(
+                    f"Missing 'type' in components resolver configuration: {components_resolver_config}"
+                )
+
+            if resolver_type not in COMPONENTS_RESOLVER_TYPE_MAPPING:
+                raise ValueError(
+                    f"Invalid components resolver type '{resolver_type}'. "
+                    f"Expected one of {list(COMPONENTS_RESOLVER_TYPE_MAPPING.keys())}."
+                )
+
+            if "retriever" in components_resolver_config:
+                components_resolver_config["retriever"]["requester"]["use_cache"] = True
+
+            # Create a resolver for dynamic components based on type
+            components_resolver = self._constructor.create_component(
+                COMPONENTS_RESOLVER_TYPE_MAPPING[resolver_type], components_resolver_config, config
+            )
+
+            stream_template_config = dynamic_definition["stream_template"]
+
+            for dynamic_stream in components_resolver.resolve_components(
+                stream_template_config=stream_template_config
+            ):
+                if "type" not in dynamic_stream:
+                    dynamic_stream["type"] = "DeclarativeStream"
+
+                dynamic_stream_configs.append(dynamic_stream)
+
+        return dynamic_stream_configs
+
     def _emit_manifest_debug_message(self, extra_args: dict[str, Any]) -> None:
         self.logger.debug("declarative source created from manifest", extra=extra_args)

airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -1158,6 +1158,37 @@ class WaitUntilTimeFromHeader(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class ComponentMappingDefinition(BaseModel):
+    type: Literal["ComponentMappingDefinition"]
+    field_path: List[str] = Field(
+        ...,
+        description="A list of potentially nested fields indicating the full path where value will be added or updated.",
+        examples=[
+            ["data"],
+            ["data", "records"],
+            ["data", "{{ parameters.name }}"],
+            ["data", "*", "record"],
+        ],
+        title="Field Path",
+    )
+    value: str = Field(
+        ...,
+        description="The dynamic or static value to assign to the key. Interpolated values can be used to dynamically determine the value during runtime.",
+        examples=[
+            "{{ components_values['updates'] }}",
+            "{{ components_values['MetaData']['LastUpdatedTime'] }}",
+            "{{ config['segment_id'] }}",
+        ],
+        title="Value",
+    )
+    value_type: Optional[ValueType] = Field(
+        None,
+        description="The expected data type of the value. If omitted, the type will be inferred from the value provided.",
+        title="Value Type",
+    )
+    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
+
+
 class AddedFieldDefinition(BaseModel):
     type: Literal["AddedFieldDefinition"]
     path: List[str] = Field(
@@ -1455,13 +1486,40 @@ class CompositeErrorHandler(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
-class DeclarativeSource(BaseModel):
+class DeclarativeSource1(BaseModel):
     class Config:
         extra = Extra.forbid
 
     type: Literal["DeclarativeSource"]
     check: CheckStream
     streams: List[DeclarativeStream]
+    dynamic_streams: Optional[List[DynamicDeclarativeStream]] = None
+    version: str = Field(
+        ...,
+        description="The version of the Airbyte CDK used to build and test the source.",
+    )
+    schemas: Optional[Schemas] = None
+    definitions: Optional[Dict[str, Any]] = None
+    spec: Optional[Spec] = None
+    concurrency_level: Optional[ConcurrencyLevel] = None
+    metadata: Optional[Dict[str, Any]] = Field(
+        None,
+        description="For internal Airbyte use only - DO NOT modify manually. Used by consumers of declarative manifests for storing related metadata.",
+    )
+    description: Optional[str] = Field(
+        None,
+        description="A description of the connector. It will be presented on the Source documentation page.",
+    )
+
+
+class DeclarativeSource2(BaseModel):
+    class Config:
+        extra = Extra.forbid
+
+    type: Literal["DeclarativeSource"]
+    check: CheckStream
+    streams: Optional[List[DeclarativeStream]] = None
+    dynamic_streams: List[DynamicDeclarativeStream]
     version: str = Field(
         ...,
         description="The version of the Airbyte CDK used to build and test the source.",
@@ -1480,6 +1538,17 @@ class DeclarativeSource(BaseModel):
     )
 
 
+class DeclarativeSource(BaseModel):
+    class Config:
+        extra = Extra.forbid
+
+    __root__: Union[DeclarativeSource1, DeclarativeSource2] = Field(
+        ...,
+        description="An API source that extracts data according to its declarative components.",
+        title="DeclarativeSource",
+    )
+
+
 class SelectiveAuthenticator(BaseModel):
     class Config:
         extra = Extra.allow
@@ -1883,8 +1952,32 @@ class SubstreamPartitionRouter(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class HttpComponentsResolver(BaseModel):
+    type: Literal["HttpComponentsResolver"]
+    retriever: Union[AsyncRetriever, CustomRetriever, SimpleRetriever] = Field(
+        ...,
+        description="Component used to coordinate how records are extracted across stream slices and request pages.",
+        title="Retriever",
+    )
+    components_mapping: List[ComponentMappingDefinition]
+    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
+
+
+class DynamicDeclarativeStream(BaseModel):
+    type: Literal["DynamicDeclarativeStream"]
+    stream_template: DeclarativeStream = Field(
+        ..., description="Reference to the stream template.", title="Stream Template"
+    )
+    components_resolver: HttpComponentsResolver = Field(
+        ...,
+        description="Component resolve and populates stream templates with components values.",
+        title="Components Resolver",
+    )
+
+
 CompositeErrorHandler.update_forward_refs()
-DeclarativeSource.update_forward_refs()
+DeclarativeSource1.update_forward_refs()
+DeclarativeSource2.update_forward_refs()
 SelectiveAuthenticator.update_forward_refs()
 DeclarativeStream.update_forward_refs()
 SessionTokenAuthenticator.update_forward_refs()

airbyte_cdk/sources/declarative/parsers/manifest_component_transformer.py

@@ -31,6 +31,12 @@ DEFAULT_MODEL_TYPES: Mapping[str, str] = {
     # DeclarativeStream
     "DeclarativeStream.retriever": "SimpleRetriever",
     "DeclarativeStream.schema_loader": "JsonFileSchemaLoader",
+    # DynamicDeclarativeStream
+    "DynamicDeclarativeStream.stream_template": "DeclarativeStream",
+    "DynamicDeclarativeStream.components_resolver": "HttpComponentsResolver",
+    # HttpComponentsResolver
+    "HttpComponentsResolver.retriever": "SimpleRetriever",
+    "HttpComponentsResolver.components_mapping": "ComponentMappingDefinition",
     # DefaultErrorHandler
     "DefaultErrorHandler.response_filters": "HttpResponseFilter",
     # DefaultPaginator