airbyte-cdk 6.11.2.dev1__tar.gz → 6.12.0__tar.gz

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: airbyte-cdk
-Version: 6.11.2.dev1
+Version: 6.12.0
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT
@@ -22,6 +22,7 @@ Provides-Extra: sql
 Provides-Extra: vector-db-based
 Requires-Dist: Jinja2 (>=3.1.2,<3.2.0)
 Requires-Dist: PyYAML (>=6.0.1,<7.0.0)
+Requires-Dist: Unidecode (>=1.3,<2.0)
 Requires-Dist: airbyte-protocol-models-dataclasses (>=0.14,<0.15)
 Requires-Dist: avro (>=1.11.2,<1.12.0) ; extra == "file-based"
 Requires-Dist: backoff

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -1234,6 +1234,8 @@ definitions:
             - "$ref": "#/definitions/CustomTransformation"
             - "$ref": "#/definitions/RemoveFields"
             - "$ref": "#/definitions/KeysToLower"
+            - "$ref": "#/definitions/KeysToSnakeCase"
+            - "$ref": "#/definitions/FlattenFields"
       state_migrations:
         title: State Migrations
         description: Array of state migrations to be applied on the input state
@@ -1766,6 +1768,18 @@ definitions:
           - "$ref": "#/definitions/AsyncRetriever"
           - "$ref": "#/definitions/CustomRetriever"
           - "$ref": "#/definitions/SimpleRetriever"
+      schema_transformations:
+        title: Schema Transformations
+        description: A list of transformations to be applied to the schema.
+        type: array
+        items:
+          anyOf:
+            - "$ref": "#/definitions/AddFields"
+            - "$ref": "#/definitions/CustomTransformation"
+            - "$ref": "#/definitions/RemoveFields"
+            - "$ref": "#/definitions/KeysToLower"
+            - "$ref": "#/definitions/KeysToSnakeCase"
+            - "$ref": "#/definitions/FlattenFields"
       schema_type_identifier:
         "$ref": "#/definitions/SchemaTypeIdentifier"
       $parameters:
@@ -1838,6 +1852,32 @@ definitions:
       $parameters:
         type: object
         additionalProperties: true
+  KeysToSnakeCase:
+    title: Key to Snake Case
+    description: A transformation that renames all keys to snake case.
+    type: object
+    required:
+      - type
+    properties:
+      type:
+        type: string
+        enum: [KeysToSnakeCase]
+      $parameters:
+        type: object
+        additionalProperties: true
+  FlattenFields:
+    title: Flatten Fields
+    description: A transformation that flatten record to single level format.
+    type: object
+    required:
+      - type
+    properties:
+      type:
+        type: string
+        enum: [FlattenFields]
+      $parameters:
+        type: object
+        additionalProperties: true
   IterableDecoder:
     title: Iterable Decoder
     description: Use this if the response consists of strings separated by new lines (`\n`). The Decoder will wrap each row into a JSON object with the `record` key.
@@ -2160,7 +2200,9 @@ definitions:
             description: |-
               The DeclarativeOAuth Specific optional headers to inject while exchanging the `auth_code` to `access_token` during `completeOAuthFlow` step.
             examples:
-              - {"Authorization": "Basic {base64Encoder:{client_id}:{client_secret}}"}
+              - {
+                  "Authorization": "Basic {base64Encoder:{client_id}:{client_secret}}",
+                }
           access_token_params:
             title: Access Token Query Params (Json Encoded)
             type: object

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -710,6 +710,16 @@ class KeysToLower(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class KeysToSnakeCase(BaseModel):
+    type: Literal["KeysToSnakeCase"]
+    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
+
+
+class FlattenFields(BaseModel):
+    type: Literal["FlattenFields"]
+    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
+
+
 class IterableDecoder(BaseModel):
     type: Literal["IterableDecoder"]
 
@@ -1654,7 +1664,16 @@ class DeclarativeStream(BaseModel):
         title="Schema Loader",
     )
     transformations: Optional[
-        List[Union[AddFields, CustomTransformation, RemoveFields, KeysToLower]]
+        List[
+            Union[
+                AddFields,
+                CustomTransformation,
+                RemoveFields,
+                KeysToLower,
+                KeysToSnakeCase,
+                FlattenFields,
+            ]
+        ]
     ] = Field(
         None,
         description="A list of transformations to be applied to each output record.",
@@ -1818,6 +1837,22 @@ class DynamicSchemaLoader(BaseModel):
         description="Component used to coordinate how records are extracted across stream slices and request pages.",
         title="Retriever",
     )
+    schema_transformations: Optional[
+        List[
+            Union[
+                AddFields,
+                CustomTransformation,
+                RemoveFields,
+                KeysToLower,
+                KeysToSnakeCase,
+                FlattenFields,
+            ]
+        ]
+    ] = Field(
+        None,
+        description="A list of transformations to be applied to the schema.",
+        title="Schema Transformations",
+    )
     schema_type_identifier: SchemaTypeIdentifier
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py

@@ -197,6 +197,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     ExponentialBackoffStrategy as ExponentialBackoffStrategyModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    FlattenFields as FlattenFieldsModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     GzipJsonDecoder as GzipJsonDecoderModel,
 )
@@ -236,6 +239,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     KeysToLower as KeysToLowerModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    KeysToSnakeCase as KeysToSnakeCaseModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     LegacySessionTokenAuthenticator as LegacySessionTokenAuthenticatorModel,
 )
@@ -323,9 +329,6 @@ from airbyte_cdk.sources.declarative.partition_routers import (
     SinglePartitionRouter,
     SubstreamPartitionRouter,
 )
-from airbyte_cdk.sources.declarative.partition_routers.async_job_partition_router import (
-    AsyncJobPartitionRouter,
-)
 from airbyte_cdk.sources.declarative.partition_routers.substream_partition_router import (
     ParentStreamConfig,
 )
@@ -390,9 +393,15 @@ from airbyte_cdk.sources.declarative.transformations import (
     RemoveFields,
 )
 from airbyte_cdk.sources.declarative.transformations.add_fields import AddedFieldDefinition
+from airbyte_cdk.sources.declarative.transformations.flatten_fields import (
+    FlattenFields,
+)
 from airbyte_cdk.sources.declarative.transformations.keys_to_lower_transformation import (
     KeysToLowerTransformation,
 )
+from airbyte_cdk.sources.declarative.transformations.keys_to_snake_transformation import (
+    KeysToSnakeCaseTransformation,
+)
 from airbyte_cdk.sources.message import (
     InMemoryMessageRepository,
     LogAppenderMessageRepositoryDecorator,
@@ -475,6 +484,8 @@ class ModelToComponentFactory:
             JsonlDecoderModel: self.create_jsonl_decoder,
             GzipJsonDecoderModel: self.create_gzipjson_decoder,
             KeysToLowerModel: self.create_keys_to_lower_transformation,
+            KeysToSnakeCaseModel: self.create_keys_to_snake_transformation,
+            FlattenFieldsModel: self.create_flatten_fields,
             IterableDecoderModel: self.create_iterable_decoder,
             XmlDecoderModel: self.create_xml_decoder,
             JsonFileSchemaLoaderModel: self.create_json_file_schema_loader,
@@ -590,6 +601,16 @@ class ModelToComponentFactory:
     ) -> KeysToLowerTransformation:
         return KeysToLowerTransformation()
 
+    def create_keys_to_snake_transformation(
+        self, model: KeysToSnakeCaseModel, config: Config, **kwargs: Any
+    ) -> KeysToSnakeCaseTransformation:
+        return KeysToSnakeCaseTransformation()
+
+    def create_flatten_fields(
+        self, model: FlattenFieldsModel, config: Config, **kwargs: Any
+    ) -> FlattenFields:
+        return FlattenFields()
+
     @staticmethod
     def _json_schema_type_name_to_type(value_type: Optional[ValueType]) -> Optional[Type[Any]]:
         if not value_type:
@@ -1641,6 +1662,13 @@ class ModelToComponentFactory:
             model.retriever, stream_slicer
         )
 
+        schema_transformations = []
+        if model.schema_transformations:
+            for transformation_model in model.schema_transformations:
+                schema_transformations.append(
+                    self._create_component_from_model(model=transformation_model, config=config)
+                )
+
         retriever = self._create_component_from_model(
             model=model.retriever,
             config=config,
@@ -1655,6 +1683,7 @@ class ModelToComponentFactory:
         return DynamicSchemaLoader(
             retriever=retriever,
             config=config,
+            schema_transformations=schema_transformations,
             schema_type_identifier=schema_type_identifier,
             parameters=model.parameters or {},
         )
@@ -2231,24 +2260,18 @@ class ModelToComponentFactory:
             urls_extractor=urls_extractor,
         )
 
-        async_job_partition_router = AsyncJobPartitionRouter(
+        return AsyncRetriever(
             job_orchestrator_factory=lambda stream_slices: AsyncJobOrchestrator(
                 job_repository,
                 stream_slices,
-                JobTracker(1),
-                # FIXME eventually make the number of concurrent jobs in the API configurable. Until then, we limit to 1
+                JobTracker(
+                    1
+                ),  # FIXME eventually make the number of concurrent jobs in the API configurable. Until then, we limit to 1
                 self._message_repository,
-                has_bulk_parent=False,
-                # FIXME work would need to be done here in order to detect if a stream as a parent stream that is bulk
+                has_bulk_parent=False,  # FIXME work would need to be done here in order to detect if a stream as a parent stream that is bulk
             ),
-            stream_slicer=stream_slicer,
-            config=config,
-            parameters=model.parameters or {},
-        )
-
-        return AsyncRetriever(
             record_selector=record_selector,
-            stream_slicer=async_job_partition_router,
+            stream_slicer=stream_slicer,
             config=config,
             parameters=model.parameters or {},
         )

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/airbyte_cdk/sources/declarative/partition_routers/__init__.py

@@ -2,18 +2,10 @@
 # Copyright (c) 2022 Airbyte, Inc., all rights reserved.
 #
 
-from airbyte_cdk.sources.declarative.partition_routers.async_job_partition_router import AsyncJobPartitionRouter
 from airbyte_cdk.sources.declarative.partition_routers.cartesian_product_stream_slicer import CartesianProductStreamSlicer
 from airbyte_cdk.sources.declarative.partition_routers.list_partition_router import ListPartitionRouter
 from airbyte_cdk.sources.declarative.partition_routers.single_partition_router import SinglePartitionRouter
 from airbyte_cdk.sources.declarative.partition_routers.substream_partition_router import SubstreamPartitionRouter
 from airbyte_cdk.sources.declarative.partition_routers.partition_router import PartitionRouter
 
-__all__ = [
-    "AsyncJobPartitionRouter",
-    "CartesianProductStreamSlicer",
-    "ListPartitionRouter",
-    "SinglePartitionRouter",
-    "SubstreamPartitionRouter",
-    "PartitionRouter"
-]
+__all__ = ["CartesianProductStreamSlicer", "ListPartitionRouter", "SinglePartitionRouter", "SubstreamPartitionRouter", "PartitionRouter"]

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/airbyte_cdk/sources/declarative/retrievers/async_retriever.py

@@ -1,8 +1,8 @@
 # Copyright (c) 2024 Airbyte, Inc., all rights reserved.
 
 
-from dataclasses import InitVar, dataclass
-from typing import Any, Iterable, Mapping, Optional
+from dataclasses import InitVar, dataclass, field
+from typing import Any, Callable, Iterable, Mapping, Optional
 
 from typing_extensions import deprecated
 
@@ -12,10 +12,9 @@ from airbyte_cdk.sources.declarative.async_job.job_orchestrator import (
     AsyncPartition,
 )
 from airbyte_cdk.sources.declarative.extractors.record_selector import RecordSelector
-from airbyte_cdk.sources.declarative.partition_routers.async_job_partition_router import (
-    AsyncJobPartitionRouter,
-)
+from airbyte_cdk.sources.declarative.partition_routers import SinglePartitionRouter
 from airbyte_cdk.sources.declarative.retrievers import Retriever
+from airbyte_cdk.sources.declarative.stream_slicers import StreamSlicer
 from airbyte_cdk.sources.source import ExperimentalClassWarning
 from airbyte_cdk.sources.streams.core import StreamData
 from airbyte_cdk.sources.types import Config, StreamSlice, StreamState
@@ -30,10 +29,15 @@ from airbyte_cdk.utils.traced_exception import AirbyteTracedException
 class AsyncRetriever(Retriever):
     config: Config
     parameters: InitVar[Mapping[str, Any]]
+    job_orchestrator_factory: Callable[[Iterable[StreamSlice]], AsyncJobOrchestrator]
     record_selector: RecordSelector
-    stream_slicer: AsyncJobPartitionRouter
+    stream_slicer: StreamSlicer = field(
+        default_factory=lambda: SinglePartitionRouter(parameters={})
+    )
 
     def __post_init__(self, parameters: Mapping[str, Any]) -> None:
+        self._job_orchestrator_factory = self.job_orchestrator_factory
+        self.__job_orchestrator: Optional[AsyncJobOrchestrator] = None
         self._parameters = parameters
 
     @property
@@ -50,6 +54,17 @@ class AsyncRetriever(Retriever):
         """
         pass
 
+    @property
+    def _job_orchestrator(self) -> AsyncJobOrchestrator:
+        if not self.__job_orchestrator:
+            raise AirbyteTracedException(
+                message="Invalid state within AsyncJobRetriever. Please contact Airbyte Support",
+                internal_message="AsyncPartitionRepository is expected to be accessed only after `stream_slices`",
+                failure_type=FailureType.system_error,
+            )
+
+        return self.__job_orchestrator
+
     def _get_stream_state(self) -> StreamState:
         """
         Gets the current state of the stream.
@@ -84,7 +99,15 @@ class AsyncRetriever(Retriever):
         return stream_slice["partition"]  # type: ignore  # stream_slice["partition"] has been added as an AsyncPartition as part of stream_slices
 
     def stream_slices(self) -> Iterable[Optional[StreamSlice]]:
-        return self.stream_slicer.stream_slices()
+        slices = self.stream_slicer.stream_slices()
+        self.__job_orchestrator = self._job_orchestrator_factory(slices)
+
+        for completed_partition in self._job_orchestrator.create_and_get_completed_partitions():
+            yield StreamSlice(
+                partition=dict(completed_partition.stream_slice.partition)
+                | {"partition": completed_partition},
+                cursor_slice=completed_partition.stream_slice.cursor_slice,
+            )
 
     def read_records(
         self,
@@ -93,7 +116,7 @@ class AsyncRetriever(Retriever):
     ) -> Iterable[StreamData]:
         stream_state: StreamState = self._get_stream_state()
         partition: AsyncPartition = self._validate_and_get_stream_slice_partition(stream_slice)
-        records: Iterable[Mapping[str, Any]] = self.stream_slicer.fetch_records(partition)
+        records: Iterable[Mapping[str, Any]] = self._job_orchestrator.fetch_records(partition)
 
         yield from self.record_selector.filter_and_transform(
             all_data=records,

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/airbyte_cdk/sources/declarative/schema/dynamic_schema_loader.py

@@ -4,7 +4,7 @@
 
 
 from copy import deepcopy
-from dataclasses import InitVar, dataclass
+from dataclasses import InitVar, dataclass, field
 from typing import Any, List, Mapping, MutableMapping, Optional, Union
 
 import dpath
@@ -13,8 +13,9 @@ from typing_extensions import deprecated
 from airbyte_cdk.sources.declarative.interpolation.interpolated_string import InterpolatedString
 from airbyte_cdk.sources.declarative.retrievers.retriever import Retriever
 from airbyte_cdk.sources.declarative.schema.schema_loader import SchemaLoader
+from airbyte_cdk.sources.declarative.transformations import RecordTransformation
 from airbyte_cdk.sources.source import ExperimentalClassWarning
-from airbyte_cdk.sources.types import Config
+from airbyte_cdk.sources.types import Config, StreamSlice, StreamState
 
 AIRBYTE_DATA_TYPES: Mapping[str, Mapping[str, Any]] = {
     "string": {"type": ["null", "string"]},
@@ -103,6 +104,7 @@ class DynamicSchemaLoader(SchemaLoader):
     config: Config
     parameters: InitVar[Mapping[str, Any]]
     schema_type_identifier: SchemaTypeIdentifier
+    schema_transformations: List[RecordTransformation] = field(default_factory=lambda: [])
 
     def get_json_schema(self) -> Mapping[str, Any]:
         """
@@ -128,12 +130,27 @@ class DynamicSchemaLoader(SchemaLoader):
             )
             properties[key] = value
 
+        transformed_properties = self._transform(properties, {})
+
         return {
             "$schema": "http://json-schema.org/draft-07/schema#",
             "type": "object",
-            "properties": properties,
+            "properties": transformed_properties,
         }
 
+    def _transform(
+        self,
+        properties: Mapping[str, Any],
+        stream_state: StreamState,
+        stream_slice: Optional[StreamSlice] = None,
+    ) -> Mapping[str, Any]:
+        for transformation in self.schema_transformations:
+            transformation.transform(
+                properties,  # type: ignore  # properties has type Mapping[str, Any], but Dict[str, Any] expected
+                config=self.config,
+            )
+        return properties
+
     def _get_key(
         self,
         raw_schema: MutableMapping[str, Any],

airbyte_cdk-6.12.0/airbyte_cdk/sources/declarative/transformations/flatten_fields.py

@@ -0,0 +1,50 @@
+#
+# Copyright (c) 2024 Airbyte, Inc., all rights reserved.
+#
+
+from dataclasses import dataclass
+from typing import Any, Dict, Optional
+
+from airbyte_cdk.sources.declarative.transformations import RecordTransformation
+from airbyte_cdk.sources.types import Config, StreamSlice, StreamState
+
+
+@dataclass
+class FlattenFields(RecordTransformation):
+    def transform(
+        self,
+        record: Dict[str, Any],
+        config: Optional[Config] = None,
+        stream_state: Optional[StreamState] = None,
+        stream_slice: Optional[StreamSlice] = None,
+    ) -> None:
+        transformed_record = self.flatten_record(record)
+        record.clear()
+        record.update(transformed_record)
+
+    def flatten_record(self, record: Dict[str, Any]) -> Dict[str, Any]:
+        stack = [(record, "_")]
+        transformed_record: Dict[str, Any] = {}
+        force_with_parent_name = False
+
+        while stack:
+            current_record, parent_key = stack.pop()
+
+            if isinstance(current_record, dict):
+                for current_key, value in current_record.items():
+                    new_key = (
+                        f"{parent_key}.{current_key}"
+                        if (current_key in transformed_record or force_with_parent_name)
+                        else current_key
+                    )
+                    stack.append((value, new_key))
+
+            elif isinstance(current_record, list):
+                for i, item in enumerate(current_record):
+                    force_with_parent_name = True
+                    stack.append((item, f"{parent_key}.{i}"))
+
+            else:
+                transformed_record[parent_key] = current_record
+
+        return transformed_record

airbyte_cdk-6.12.0/airbyte_cdk/sources/declarative/transformations/keys_to_snake_transformation.py

@@ -0,0 +1,68 @@
+#
+# Copyright (c) 2024 Airbyte, Inc., all rights reserved.
+#
+
+import re
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional
+
+import unidecode
+
+from airbyte_cdk.sources.declarative.transformations import RecordTransformation
+from airbyte_cdk.sources.types import Config, StreamSlice, StreamState
+
+
+@dataclass
+class KeysToSnakeCaseTransformation(RecordTransformation):
+    token_pattern: re.Pattern[str] = re.compile(
+        r"[A-Z]+[a-z]*|[a-z]+|\d+|(?P<NoToken>[^a-zA-Z\d]+)"
+    )
+
+    def transform(
+        self,
+        record: Dict[str, Any],
+        config: Optional[Config] = None,
+        stream_state: Optional[StreamState] = None,
+        stream_slice: Optional[StreamSlice] = None,
+    ) -> None:
+        transformed_record = self._transform_record(record)
+        record.clear()
+        record.update(transformed_record)
+
+    def _transform_record(self, record: Dict[str, Any]) -> Dict[str, Any]:
+        transformed_record = {}
+        for key, value in record.items():
+            transformed_key = self.process_key(key)
+            transformed_value = value
+
+            if isinstance(value, dict):
+                transformed_value = self._transform_record(value)
+
+            transformed_record[transformed_key] = transformed_value
+        return transformed_record
+
+    def process_key(self, key: str) -> str:
+        key = self.normalize_key(key)
+        tokens = self.tokenize_key(key)
+        tokens = self.filter_tokens(tokens)
+        return self.tokens_to_snake_case(tokens)
+
+    def normalize_key(self, key: str) -> str:
+        return unidecode.unidecode(key)
+
+    def tokenize_key(self, key: str) -> List[str]:
+        tokens = []
+        for match in self.token_pattern.finditer(key):
+            token = match.group(0) if match.group("NoToken") is None else ""
+            tokens.append(token)
+        return tokens
+
+    def filter_tokens(self, tokens: List[str]) -> List[str]:
+        if len(tokens) >= 3:
+            tokens = tokens[:1] + [t for t in tokens[1:-1] if t] + tokens[-1:]
+        if tokens and tokens[0].isdigit():
+            tokens.insert(0, "")
+        return tokens
+
+    def tokens_to_snake_case(self, tokens: List[str]) -> str:
+        return "_".join(token.lower() for token in tokens)

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/airbyte_cdk/sources/streams/http/http_client.py

@@ -262,7 +262,7 @@ class HttpClient:
         user_backoff_handler = user_defined_backoff_handler(max_tries=max_tries, max_time=max_time)(
             self._send
         )
-        rate_limit_backoff_handler = rate_limit_default_backoff_handler()
+        rate_limit_backoff_handler = rate_limit_default_backoff_handler(max_tries=max_tries)
         backoff_handler = http_client_default_backoff_handler(
             max_tries=max_tries, max_time=max_time
         )
@@ -472,7 +472,9 @@ class HttpClient:
 
             elif retry_endlessly:
                 raise RateLimitBackoffException(
-                    request=request, response=response or exc, error_message=error_message
+                    request=request,
+                    response=(response if response is not None else exc),
+                    error_message=error_message,
                 )
 
             raise DefaultBackoffException(

{airbyte_cdk-6.11.2.dev1 → airbyte_cdk-6.12.0}/pyproject.toml

@@ -23,7 +23,7 @@ classifiers = [
 keywords = ["airbyte", "connector-development-kit", "cdk"]
 
 # Python CDK uses dynamic versioning: https://github.com/mtkennerly/poetry-dynamic-versioning
-version = "6.11.2dev1"  # Version will be calculated dynamically.
+version = "6.12.0"  # Version will be calculated dynamically.
 
 [tool.poetry-dynamic-versioning]
 enable = false
@@ -80,6 +80,7 @@ orjson = "^3.10.7"
 serpyco-rs = "^1.10.2"
 sqlalchemy = {version = "^2.0,!=2.0.36", optional = true }
 xmltodict = "^0.13.0"
+Unidecode = "^1.3"
 
 [tool.poetry.group.dev.dependencies]
 freezegun = "*"

airbyte_cdk-6.11.2.dev1/airbyte_cdk/sources/declarative/partition_routers/async_job_partition_router.py

@@ -1,65 +0,0 @@
-# Copyright (c) 2024 Airbyte, Inc., all rights reserved.
-
-from dataclasses import InitVar, dataclass, field
-from typing import Any, Callable, Iterable, Mapping, Optional
-
-from airbyte_cdk.models import FailureType
-from airbyte_cdk.sources.declarative.async_job.job_orchestrator import (
-    AsyncJobOrchestrator,
-    AsyncPartition,
-)
-from airbyte_cdk.sources.declarative.partition_routers.single_partition_router import (
-    SinglePartitionRouter,
-)
-from airbyte_cdk.sources.streams.concurrent.partitions.stream_slicer import StreamSlicer
-from airbyte_cdk.sources.types import Config, StreamSlice
-from airbyte_cdk.utils.traced_exception import AirbyteTracedException
-
-
-@dataclass
-class AsyncJobPartitionRouter(StreamSlicer):
-    """
-    Partition router that creates async jobs in a source API, periodically polls for job
-    completion, and supplies the completed job URL locations as stream slices so that
-    records can be extracted.
-    """
-
-    config: Config
-    parameters: InitVar[Mapping[str, Any]]
-    job_orchestrator_factory: Callable[[Iterable[StreamSlice]], AsyncJobOrchestrator]
-    stream_slicer: StreamSlicer = field(
-        default_factory=lambda: SinglePartitionRouter(parameters={})
-    )
-
-    def __post_init__(self, parameters: Mapping[str, Any]) -> None:
-        self._job_orchestrator_factory = self.job_orchestrator_factory
-        self._job_orchestrator: Optional[AsyncJobOrchestrator] = None
-        self._parameters = parameters
-
-    def stream_slices(self) -> Iterable[StreamSlice]:
-        slices = self.stream_slicer.stream_slices()
-        self._job_orchestrator = self._job_orchestrator_factory(slices)
-
-        for completed_partition in self._job_orchestrator.create_and_get_completed_partitions():
-            yield StreamSlice(
-                partition=dict(completed_partition.stream_slice.partition)
-                | {"partition": completed_partition},
-                cursor_slice=completed_partition.stream_slice.cursor_slice,
-            )
-
-    def fetch_records(self, partition: AsyncPartition) -> Iterable[Mapping[str, Any]]:
-        """
-        This method of fetching records extends beyond what a PartitionRouter/StreamSlicer should
-        be responsible for. However, this was added in because the JobOrchestrator is required to
-        retrieve records. And without defining fetch_records() on this class, we're stuck with either
-        passing the JobOrchestrator to the AsyncRetriever or storing it on multiple classes.
-        """
-
-        if not self._job_orchestrator:
-            raise AirbyteTracedException(
-                message="Invalid state within AsyncJobRetriever. Please contact Airbyte Support",
-                internal_message="AsyncPartitionRepository is expected to be accessed only after `stream_slices`",
-                failure_type=FailureType.system_error,
-            )
-
-        return self._job_orchestrator.fetch_records(partition=partition)