airbyte-cdk 6.9.2__tar.gz → 6.9.2.dev4100__tar.gz

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: airbyte-cdk
-Version: 6.9.2
+Version: 6.9.2.dev4100
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/airbyte_cdk/sources/declarative/concurrent_declarative_source.py

@@ -56,9 +56,8 @@ from airbyte_cdk.sources.types import Config, StreamState
 
 
 class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
-    # By default, we defer to a value of 2. A value lower than than could cause a PartitionEnqueuer to be stuck in a state of deadlock
-    # because it has hit the limit of futures but not partition reader is consuming them.
-    _LOWEST_SAFE_CONCURRENCY_LEVEL = 2
+    # By default, we defer to a value of 1 which represents running a connector using the Concurrent CDK engine on only one thread.
+    SINGLE_THREADED_CONCURRENCY_LEVEL = 1
 
     def __init__(
         self,
@@ -108,8 +107,8 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
                 concurrency_level // 2, 1
             )  # Partition_generation iterates using range based on this value. If this is floored to zero we end up in a dead lock during start up
         else:
-            concurrency_level = self._LOWEST_SAFE_CONCURRENCY_LEVEL
-            initial_number_of_partitions_to_generate = self._LOWEST_SAFE_CONCURRENCY_LEVEL // 2
+            concurrency_level = self.SINGLE_THREADED_CONCURRENCY_LEVEL
+            initial_number_of_partitions_to_generate = self.SINGLE_THREADED_CONCURRENCY_LEVEL
 
         self._concurrent_source = ConcurrentSource.create(
             num_workers=concurrency_level,

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -327,7 +327,7 @@ definitions:
         additionalProperties: true
   ConcurrencyLevel:
     title: Concurrency Level
-    description: Defines the amount of parallelization for the streams that are being synced. The factor of parallelization is how many partitions or streams are synced at the same time. For example, with a concurrency_level of 10, ten streams or partitions of data will processed at the same time. Note that a value of 1 could create deadlock if a stream has a very high number of partitions.
+    description: Defines the amount of parallelization for the streams that are being synced. The factor of parallelization is how many partitions or streams are synced at the same time. For example, with a concurrency_level of 10, ten streams or partitions of data will processed at the same time.
     type: object
     required:
       - default_concurrency
@@ -1221,6 +1221,7 @@ definitions:
           - "$ref": "#/definitions/InlineSchemaLoader"
           - "$ref": "#/definitions/JsonFileSchemaLoader"
           - "$ref": "#/definitions/CustomSchemaLoader"
+          - "$ref": "#/definitions/DynamicSchemaLoader"
       # TODO we have move the transformation to the RecordSelector level in the code but kept this here for
       # compatibility reason. We should eventually move this to align with the code.
       transformations:
@@ -1684,6 +1685,92 @@ definitions:
       $parameters:
         type: object
         additionalProperties: true
+  TypesMap:
+    title: Types Map
+    description: (This component is experimental. Use at your own risk.) Represents a mapping between a current type and its corresponding target type.
+    type: object
+    required:
+      - target_type
+      - current_type
+    properties:
+      target_type:
+        anyOf:
+          - type: string
+          - type: array
+            items:
+              type: string
+      current_type:
+        anyOf:
+          - type: string
+          - type: array
+            items:
+              type: string
+  SchemaTypeIdentifier:
+    title: Schema Type Identifier
+    description: (This component is experimental. Use at your own risk.) Identifies schema details for dynamic schema extraction and processing.
+    type: object
+    required:
+      - key_pointer
+    properties:
+      type:
+        type: string
+        enum: [SchemaTypeIdentifier]
+      schema_pointer:
+        title: Schema Path
+        description: List of nested fields defining the schema field path to extract. Defaults to [].
+        type: array
+        default: []
+        items:
+          - type: string
+        interpolation_context:
+          - config
+      key_pointer:
+        title: Key Path
+        description: List of potentially nested fields describing the full path of the field key to extract.
+        type: array
+        items:
+          - type: string
+        interpolation_context:
+          - config
+      type_pointer:
+        title: Type Path
+        description: List of potentially nested fields describing the full path of the field type to extract.
+        type: array
+        items:
+          - type: string
+        interpolation_context:
+          - config
+      types_mapping:
+        type: array
+        items:
+          - "$ref": "#/definitions/TypesMap"
+      $parameters:
+        type: object
+        additionalProperties: true
+  DynamicSchemaLoader:
+    title: Dynamic Schema Loader
+    description: (This component is experimental. Use at your own risk.) Loads a schema by extracting data from retrieved records.
+    type: object
+    required:
+      - type
+      - retriever
+      - schema_type_identifier
+    properties:
+      type:
+        type: string
+        enum: [DynamicSchemaLoader]
+      retriever:
+        title: Retriever
+        description: Component used to coordinate how records are extracted across stream slices and request pages.
+        anyOf:
+          - "$ref": "#/definitions/AsyncRetriever"
+          - "$ref": "#/definitions/CustomRetriever"
+          - "$ref": "#/definitions/SimpleRetriever"
+      schema_type_identifier:
+        "$ref": "#/definitions/SchemaTypeIdentifier"
+      $parameters:
+        type: object
+        additionalProperties: true
   InlineSchemaLoader:
     title: Inline Schema Loader
     description: Loads a schema that is defined directly in the manifest file.

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/airbyte_cdk/sources/declarative/interpolation/jinja.py

@@ -4,7 +4,7 @@
 
 import ast
 from functools import cache
-from typing import Any, Mapping, Optional, Set, Tuple, Type
+from typing import Any, Mapping, Optional, Tuple, Type
 
 from jinja2 import meta
 from jinja2.environment import Template
@@ -27,35 +27,7 @@ class StreamPartitionAccessEnvironment(SandboxedEnvironment):
     def is_safe_attribute(self, obj: Any, attr: str, value: Any) -> bool:
         if attr in ["_partition"]:
             return True
-        return super().is_safe_attribute(obj, attr, value)  # type: ignore  # for some reason, mypy says 'Returning Any from function declared to return "bool"'
-
-
-# These aliases are used to deprecate existing keywords without breaking all existing connectors.
-_ALIASES = {
-    "stream_interval": "stream_slice",  # Use stream_interval to access incremental_sync values
-    "stream_partition": "stream_slice",  # Use stream_partition to access partition router's values
-}
-
-# These extensions are not installed so they're not currently a problem,
-# but we're still explicitly removing them from the jinja context.
-# At worst, this is documentation that we do NOT want to include these extensions because of the potential security risks
-_RESTRICTED_EXTENSIONS = ["jinja2.ext.loopcontrols"]  # Adds support for break continue in loops
-
-# By default, these Python builtin functions are available in the Jinja context.
-# We explicitly remove them because of the potential security risk.
-# Please add a unit test to test_jinja.py when adding a restriction.
-_RESTRICTED_BUILTIN_FUNCTIONS = [
-    "range"
-]  # The range function can cause very expensive computations
-
-_ENVIRONMENT = StreamPartitionAccessEnvironment()
-_ENVIRONMENT.filters.update(**filters)
-_ENVIRONMENT.globals.update(**macros)
-
-for extension in _RESTRICTED_EXTENSIONS:
-    _ENVIRONMENT.extensions.pop(extension, None)
-for builtin in _RESTRICTED_BUILTIN_FUNCTIONS:
-    _ENVIRONMENT.globals.pop(builtin, None)
+        return super().is_safe_attribute(obj, attr, value)
 
 
 class JinjaInterpolation(Interpolation):
@@ -76,6 +48,34 @@ class JinjaInterpolation(Interpolation):
     Additional information on jinja templating can be found at https://jinja.palletsprojects.com/en/3.1.x/templates/#
     """
 
+    # These aliases are used to deprecate existing keywords without breaking all existing connectors.
+    ALIASES = {
+        "stream_interval": "stream_slice",  # Use stream_interval to access incremental_sync values
+        "stream_partition": "stream_slice",  # Use stream_partition to access partition router's values
+    }
+
+    # These extensions are not installed so they're not currently a problem,
+    # but we're still explicitely removing them from the jinja context.
+    # At worst, this is documentation that we do NOT want to include these extensions because of the potential security risks
+    RESTRICTED_EXTENSIONS = ["jinja2.ext.loopcontrols"]  # Adds support for break continue in loops
+
+    # By default, these Python builtin functions are available in the Jinja context.
+    # We explicitely remove them because of the potential security risk.
+    # Please add a unit test to test_jinja.py when adding a restriction.
+    RESTRICTED_BUILTIN_FUNCTIONS = [
+        "range"
+    ]  # The range function can cause very expensive computations
+
+    def __init__(self) -> None:
+        self._environment = StreamPartitionAccessEnvironment()
+        self._environment.filters.update(**filters)
+        self._environment.globals.update(**macros)
+
+        for extension in self.RESTRICTED_EXTENSIONS:
+            self._environment.extensions.pop(extension, None)
+        for builtin in self.RESTRICTED_BUILTIN_FUNCTIONS:
+            self._environment.globals.pop(builtin, None)
+
     def eval(
         self,
         input_str: str,
@@ -86,7 +86,7 @@ class JinjaInterpolation(Interpolation):
     ) -> Any:
         context = {"config": config, **additional_parameters}
 
-        for alias, equivalent in _ALIASES.items():
+        for alias, equivalent in self.ALIASES.items():
             if alias in context:
                 # This is unexpected. We could ignore or log a warning, but failing loudly should result in fewer surprises
                 raise ValueError(
@@ -105,7 +105,6 @@ class JinjaInterpolation(Interpolation):
                 raise Exception(f"Expected a string, got {input_str}")
         except UndefinedError:
             pass
-
         # If result is empty or resulted in an undefined error, evaluate and return the default string
         return self._literal_eval(self._eval(default, context), valid_types)
 
@@ -133,16 +132,16 @@ class JinjaInterpolation(Interpolation):
             return s
 
     @cache
-    def _find_undeclared_variables(self, s: Optional[str]) -> Set[str]:
+    def _find_undeclared_variables(self, s: Optional[str]) -> set[str]:
         """
         Find undeclared variables and cache them
         """
-        ast = _ENVIRONMENT.parse(s)  # type: ignore # parse is able to handle None
+        ast = self._environment.parse(s)  # type: ignore # parse is able to handle None
         return meta.find_undeclared_variables(ast)
 
     @cache
-    def _compile(self, s: str) -> Template:
+    def _compile(self, s: Optional[str]) -> Template:
         """
         We must cache the Jinja Template ourselves because we're using `from_string` instead of a template loader
         """
-        return _ENVIRONMENT.from_string(s)
+        return self._environment.from_string(s)  # type: ignore [arg-type]  # Expected `str | Template` but passed `str | None`

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -650,6 +650,32 @@ class HttpResponseFilter(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class TypesMap(BaseModel):
+    target_type: Union[str, List[str]]
+    current_type: Union[str, List[str]]
+
+
+class SchemaTypeIdentifier(BaseModel):
+    type: Optional[Literal["SchemaTypeIdentifier"]] = None
+    schema_pointer: Optional[List[str]] = Field(
+        [],
+        description="List of nested fields defining the schema field path to extract. Defaults to [].",
+        title="Schema Path",
+    )
+    key_pointer: List[str] = Field(
+        ...,
+        description="List of potentially nested fields describing the full path of the field key to extract.",
+        title="Key Path",
+    )
+    type_pointer: Optional[List[str]] = Field(
+        None,
+        description="List of potentially nested fields describing the full path of the field type to extract.",
+        title="Type Path",
+    )
+    types_mapping: Optional[List[TypesMap]] = None
+    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
+
+
 class InlineSchemaLoader(BaseModel):
     type: Literal["InlineSchemaLoader"]
     schema_: Optional[Dict[str, Any]] = Field(
@@ -822,13 +848,13 @@ class OauthConnectorInputSpecification(BaseModel):
     )
     extract_output: List[str] = Field(
         ...,
-        description="The DeclarativeOAuth Specific list of strings to indicate which keys should be extracted and returned back to the input config.                ",
+        description="The DeclarativeOAuth Specific list of strings to indicate which keys should be extracted and returned back to the input config.",
         examples=[{"extract_output": ["access_token", "refresh_token", "other_field"]}],
         title="DeclarativeOAuth Extract Output",
     )
     state: Optional[State] = Field(
         None,
-        description="The DeclarativeOAuth Specific object to provide the criteria of how the `state` query param should be constructed,\nincluding length and complexity.                ",
+        description="The DeclarativeOAuth Specific object to provide the criteria of how the `state` query param should be constructed,\nincluding length and complexity.",
         examples=[{"state": {"min": 7, "max": 128}}],
         title="(Optional) DeclarativeOAuth Configurable State Query Param",
     )
@@ -852,13 +878,13 @@ class OauthConnectorInputSpecification(BaseModel):
     )
     state_key: Optional[str] = Field(
         None,
-        description="The DeclarativeOAuth Specific optional override to provide the custom `state` key name, if required by data-provider.                ",
+        description="The DeclarativeOAuth Specific optional override to provide the custom `state` key name, if required by data-provider.",
         examples=[{"state_key": "my_custom_state_key_key_name"}],
         title="(Optional) DeclarativeOAuth State Key Override",
     )
     auth_code_key: Optional[str] = Field(
         None,
-        description="The DeclarativeOAuth Specific optional override to provide the custom `code` key name to something like `auth_code` or `custom_auth_code`, if required by data-provider.                ",
+        description="The DeclarativeOAuth Specific optional override to provide the custom `code` key name to something like `auth_code` or `custom_auth_code`, if required by data-provider.",
         examples=[{"auth_code_key": "my_custom_auth_code_key_name"}],
         title="(Optional) DeclarativeOAuth Auth Code Key Override",
     )
@@ -1609,7 +1635,7 @@ class DeclarativeStream(BaseModel):
     primary_key: Optional[PrimaryKey] = Field(
         "", description="The primary key of the stream.", title="Primary Key"
     )
-    schema_loader: Optional[Union[InlineSchemaLoader, JsonFileSchemaLoader, CustomSchemaLoader]] = (
+    schema_loader: Optional[Union[InlineSchemaLoader, JsonFileSchemaLoader, CustomSchemaLoader, DynamicSchemaLoader]] = (
         Field(
             None,
             description="Component used to retrieve the schema for the current stream.",
@@ -1774,6 +1800,17 @@ class HttpRequester(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class DynamicSchemaLoader(BaseModel):
+    type: Literal["DynamicSchemaLoader"]
+    retriever: Union[AsyncRetriever, CustomRetriever, SimpleRetriever] = Field(
+        ...,
+        description="Component used to coordinate how records are extracted across stream slices and request pages.",
+        title="Retriever",
+    )
+    schema_type_identifier: SchemaTypeIdentifier
+    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
+
+
 class ParentStreamConfig(BaseModel):
     type: Literal["ParentStreamConfig"]
     parent_key: str = Field(
@@ -1981,5 +2018,6 @@ DeclarativeSource2.update_forward_refs()
 SelectiveAuthenticator.update_forward_refs()
 DeclarativeStream.update_forward_refs()
 SessionTokenAuthenticator.update_forward_refs()
+DynamicSchemaLoader.update_forward_refs()
 SimpleRetriever.update_forward_refs()
 AsyncRetriever.update_forward_refs()

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/airbyte_cdk/sources/declarative/parsers/manifest_component_transformer.py

@@ -64,6 +64,10 @@ DEFAULT_MODEL_TYPES: Mapping[str, str] = {
     "AddFields.fields": "AddedFieldDefinition",
     # CustomPartitionRouter
     "CustomPartitionRouter.parent_stream_configs": "ParentStreamConfig",
+    # DynamicSchemaLoader
+    "DynamicSchemaLoader.retriever": "SimpleRetriever",
+    # SchemaTypeIdentifier
+    "SchemaTypeIdentifier.types_map": "TypesMap",
 }
 
 # We retain a separate registry for custom components to automatically insert the type if it is missing. This is intended to

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py

@@ -188,6 +188,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     DpathExtractor as DpathExtractorModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    DynamicSchemaLoader as DynamicSchemaLoaderModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     ExponentialBackoffStrategy as ExponentialBackoffStrategyModel,
 )
@@ -278,6 +281,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     ResponseToFileExtractor as ResponseToFileExtractorModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    SchemaTypeIdentifier as SchemaTypeIdentifierModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     SelectiveAuthenticator as SelectiveAuthenticatorModel,
 )
@@ -291,6 +297,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     SubstreamPartitionRouter as SubstreamPartitionRouterModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    TypesMap as TypesMapModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import ValueType
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     WaitTimeFromHeader as WaitTimeFromHeaderModel,
@@ -356,8 +365,11 @@ from airbyte_cdk.sources.declarative.retrievers import (
 )
 from airbyte_cdk.sources.declarative.schema import (
     DefaultSchemaLoader,
+    DynamicSchemaLoader,
     InlineSchemaLoader,
     JsonFileSchemaLoader,
+    SchemaTypeIdentifier,
+    TypesMap,
 )
 from airbyte_cdk.sources.declarative.spec import Spec
 from airbyte_cdk.sources.declarative.stream_slicers import StreamSlicer
@@ -455,6 +467,9 @@ class ModelToComponentFactory:
             IterableDecoderModel: self.create_iterable_decoder,
             XmlDecoderModel: self.create_xml_decoder,
             JsonFileSchemaLoaderModel: self.create_json_file_schema_loader,
+            DynamicSchemaLoaderModel: self.create_dynamic_schema_loader,
+            SchemaTypeIdentifierModel: self.create_schema_type_identifier,
+            TypesMapModel: self.create_types_map,
             JwtAuthenticatorModel: self.create_jwt_authenticator,
             LegacyToPerPartitionStateMigrationModel: self.create_legacy_to_per_partition_state_migration,
             ListPartitionRouterModel: self.create_list_partition_router,
@@ -1574,6 +1589,63 @@ class ModelToComponentFactory:
     ) -> InlineSchemaLoader:
         return InlineSchemaLoader(schema=model.schema_ or {}, parameters={})
 
+    @staticmethod
+    def create_types_map(model: TypesMapModel, **kwargs: Any) -> TypesMap:
+        return TypesMap(target_type=model.target_type, current_type=model.current_type)
+
+    def create_schema_type_identifier(
+        self, model: SchemaTypeIdentifierModel, config: Config, **kwargs: Any
+    ) -> SchemaTypeIdentifier:
+        types_mapping = []
+        if model.types_mapping:
+            types_mapping.extend(
+                [
+                    self._create_component_from_model(types_map, config=config)
+                    for types_map in model.types_mapping
+                ]
+            )
+        model_schema_pointer: List[Union[InterpolatedString, str]] = (
+            [x for x in model.schema_pointer] if model.schema_pointer else []
+        )
+        model_key_pointer: List[Union[InterpolatedString, str]] = [x for x in model.key_pointer]
+        model_type_pointer: Optional[List[Union[InterpolatedString, str]]] = (
+            [x for x in model.type_pointer] if model.type_pointer else None
+        )
+
+        return SchemaTypeIdentifier(
+            schema_pointer=model_schema_pointer,
+            key_pointer=model_key_pointer,
+            type_pointer=model_type_pointer,
+            types_mapping=types_mapping,
+            parameters=model.parameters or {},
+        )
+
+    def create_dynamic_schema_loader(
+        self, model: DynamicSchemaLoaderModel, config: Config, **kwargs: Any
+    ) -> DynamicSchemaLoader:
+        stream_slicer = self._build_stream_slicer_from_partition_router(model.retriever, config)
+        combined_slicers = self._build_resumable_cursor_from_paginator(
+            model.retriever, stream_slicer
+        )
+
+        retriever = self._create_component_from_model(
+            model=model.retriever,
+            config=config,
+            name="",
+            primary_key=None,
+            stream_slicer=combined_slicers,
+            transformations=[],
+        )
+        schema_type_identifier = self._create_component_from_model(
+            model.schema_type_identifier, config=config, parameters=model.parameters or {}
+        )
+        return DynamicSchemaLoader(
+            retriever=retriever,
+            config=config,
+            schema_type_identifier=schema_type_identifier,
+            parameters=model.parameters or {},
+        )
+
     @staticmethod
     def create_json_decoder(model: JsonDecoderModel, config: Config, **kwargs: Any) -> JsonDecoder:
         return JsonDecoder(parameters={})

{airbyte_cdk-6.9.2 → airbyte_cdk-6.9.2.dev4100}/airbyte_cdk/sources/declarative/schema/__init__.py

@@ -6,5 +6,6 @@ from airbyte_cdk.sources.declarative.schema.default_schema_loader import Default
 from airbyte_cdk.sources.declarative.schema.inline_schema_loader import InlineSchemaLoader
 from airbyte_cdk.sources.declarative.schema.json_file_schema_loader import JsonFileSchemaLoader
 from airbyte_cdk.sources.declarative.schema.schema_loader import SchemaLoader
+from airbyte_cdk.sources.declarative.schema.dynamic_schema_loader import DynamicSchemaLoader, TypesMap, SchemaTypeIdentifier
 
-__all__ = ["JsonFileSchemaLoader", "DefaultSchemaLoader", "SchemaLoader", "InlineSchemaLoader"]
+__all__ = ["JsonFileSchemaLoader", "DefaultSchemaLoader", "SchemaLoader", "InlineSchemaLoader", "DynamicSchemaLoader", "TypesMap", "SchemaTypeIdentifier"]