airbyte-cdk 6.38.5.dev0__tar.gz → 6.39.1__tar.gz

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: airbyte-cdk
-Version: 6.38.5.dev0
+Version: 6.39.1
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT
@@ -43,6 +43,7 @@ Requires-Dist: nltk (==3.9.1)
 Requires-Dist: numpy (<2)
 Requires-Dist: openai[embeddings] (==0.27.9) ; extra == "vector-db-based"
 Requires-Dist: orjson (>=3.10.7,<4.0.0)
+Requires-Dist: packaging
 Requires-Dist: pandas (==2.2.2)
 Requires-Dist: pdf2image (==1.16.3) ; extra == "file-based"
 Requires-Dist: pdfminer.six (==20221105) ; extra == "file-based"
@@ -63,6 +64,7 @@ Requires-Dist: requests_cache
 Requires-Dist: serpyco-rs (>=1.10.2,<2.0.0)
 Requires-Dist: sqlalchemy (>=2.0,<3.0,!=2.0.36) ; extra == "sql"
 Requires-Dist: tiktoken (==0.8.0) ; extra == "vector-db-based"
+Requires-Dist: typing-extensions
 Requires-Dist: unstructured.pytesseract (>=0.3.12) ; extra == "file-based"
 Requires-Dist: unstructured[docx,pptx] (==0.10.27) ; extra == "file-based"
 Requires-Dist: wcmatch (==10.0)

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/declarative/async_job/job_tracker.py

@@ -17,7 +17,11 @@ class ConcurrentJobLimitReached(Exception):
 class JobTracker:
     def __init__(self, limit: int):
         self._jobs: Set[str] = set()
-        self._limit = limit
+        if limit < 1:
+            LOGGER.warning(
+                f"The `max_concurrent_async_job_count` property is less than 1: {limit}. Setting to 1. Please update the source manifest to set a valid value."
+            )
+        self._limit = 1 if limit < 1 else limit
         self._lock = threading.Lock()
 
     def try_to_get_intent(self) -> str:

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -42,6 +42,10 @@ properties:
     "$ref": "#/definitions/ConcurrencyLevel"
   api_budget:
     "$ref": "#/definitions/HTTPAPIBudget"
+  max_concurrent_async_job_count:
+    title: Maximum Concurrent Asynchronous Jobs
+    description: Maximum number of concurrent asynchronous jobs to run. This property is only relevant for sources/streams that support asynchronous job execution through the AsyncRetriever (e.g. a report-based stream that initiates a job, polls the job status, and then fetches the job results). This is often set by the API's maximum number of concurrent jobs on the account level. Refer to the API's documentation for this information.
+    type: integer
   metadata:
     type: object
     description: For internal Airbyte use only - DO NOT modify manually. Used by consumers of declarative manifests for storing related metadata.
@@ -109,7 +113,7 @@ definitions:
         description: List of transformations (path and corresponding value) that will be added to the record.
         type: array
         items:
-          - "$ref": "#/definitions/AddedFieldDefinition"
+          "$ref": "#/definitions/AddedFieldDefinition"
       $parameters:
         type: object
         additionalProperties: true
@@ -1657,7 +1661,7 @@ definitions:
         description: List of potentially nested fields describing the full path of the field to extract. Use "*" to extract all values from an array. See more info in the [docs](https://docs.airbyte.com/connector-development/config-based/understanding-the-yaml-file/record-selector).
         type: array
         items:
-          - type: string
+          type: string
         interpolation_context:
           - config
         examples:
@@ -2073,7 +2077,7 @@ definitions:
         type: array
         default: []
         items:
-          - type: string
+          type: string
         interpolation_context:
           - config
       key_pointer:
@@ -2081,7 +2085,7 @@ definitions:
         description: List of potentially nested fields describing the full path of the field key to extract.
         type: array
         items:
-          - type: string
+          type: string
         interpolation_context:
           - config
       type_pointer:
@@ -2089,13 +2093,13 @@ definitions:
         description: List of potentially nested fields describing the full path of the field type to extract.
         type: array
         items:
-          - type: string
+          type: string
         interpolation_context:
           - config
       types_mapping:
         type: array
         items:
-          - "$ref": "#/definitions/TypesMap"
+          "$ref": "#/definitions/TypesMap"
       $parameters:
         type: object
         additionalProperties: true
@@ -2251,7 +2255,7 @@ definitions:
         description: A path to field that needs to be flattened.
         type: array
         items:
-          - type: string
+          type: string
         examples:
           - ["data"]
           - ["data", "*", "field"]
@@ -3526,7 +3530,7 @@ definitions:
         description: A list of potentially nested fields indicating the full path where value will be added or updated.
         type: array
         items:
-          - type: string
+          type: string
         interpolation_context:
           - config
           - components_values
@@ -3602,7 +3606,7 @@ definitions:
         description: A list of potentially nested fields indicating the full path in source config file where streams configs located.
         type: array
         items:
-          - type: string
+          type: string
         interpolation_context:
           - parameters
         examples:

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/declarative/manifest_declarative_source.py

@@ -93,7 +93,10 @@ class ManifestDeclarativeSource(DeclarativeSource):
         self._constructor = (
             component_factory
             if component_factory
-            else ModelToComponentFactory(emit_connector_builder_messages)
+            else ModelToComponentFactory(
+                emit_connector_builder_messages,
+                max_concurrent_async_job_count=source_config.get("max_concurrent_async_job_count"),
+            )
         )
         self._message_repository = self._constructor.get_message_repository()
         self._slice_logger: SliceLogger = (

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -1871,6 +1871,11 @@ class DeclarativeSource1(BaseModel):
     spec: Optional[Spec] = None
     concurrency_level: Optional[ConcurrencyLevel] = None
     api_budget: Optional[HTTPAPIBudget] = None
+    max_concurrent_async_job_count: Optional[int] = Field(
+        None,
+        description="Maximum number of concurrent asynchronous jobs to run. This property is only relevant for sources/streams that support asynchronous job execution through the AsyncRetriever (e.g. a report-based stream that initiates a job, polls the job status, and then fetches the job results). This is often set by the API's maximum number of concurrent jobs on the account level. Refer to the API's documentation for this information.",
+        title="Maximum Concurrent Asynchronous Jobs",
+    )
     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.",
@@ -1898,6 +1903,11 @@ class DeclarativeSource2(BaseModel):
     spec: Optional[Spec] = None
     concurrency_level: Optional[ConcurrencyLevel] = None
     api_budget: Optional[HTTPAPIBudget] = None
+    max_concurrent_async_job_count: Optional[int] = Field(
+        None,
+        description="Maximum number of concurrent asynchronous jobs to run. This property is only relevant for sources/streams that support asynchronous job execution through the AsyncRetriever (e.g. a report-based stream that initiates a job, polls the job status, and then fetches the job results). This is often set by the API's maximum number of concurrent jobs on the account level. Refer to the API's documentation for this information.",
+        title="Maximum Concurrent Asynchronous Jobs",
+    )
     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.",

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py

@@ -503,7 +503,7 @@ from airbyte_cdk.sources.streams.concurrent.state_converters.incrementing_count_
     IncrementingCountStreamStateConverter,
 )
 from airbyte_cdk.sources.streams.http.error_handlers.response_models import ResponseAction
-from airbyte_cdk.sources.types import Config
+from airbyte_cdk.sources.types import Config, ConnectionDefinition
 from airbyte_cdk.sources.utils.transform import TransformConfig, TypeTransformer
 
 ComponentDefinition = Mapping[str, Any]
@@ -527,6 +527,7 @@ class ModelToComponentFactory:
         disable_resumable_full_refresh: bool = False,
         message_repository: Optional[MessageRepository] = None,
         connector_state_manager: Optional[ConnectorStateManager] = None,
+        max_concurrent_async_job_count: Optional[int] = None,
     ):
         self._init_mappings()
         self._limit_pages_fetched_per_slice = limit_pages_fetched_per_slice
@@ -540,6 +541,7 @@ class ModelToComponentFactory:
         )
         self._connector_state_manager = connector_state_manager or ConnectorStateManager()
         self._api_budget: Optional[Union[APIBudget, HttpAPIBudget]] = None
+        self._job_tracker: JobTracker = JobTracker(max_concurrent_async_job_count or 1)
 
     def _init_mappings(self) -> None:
         self.PYDANTIC_MODEL_TO_CONSTRUCTOR: Mapping[Type[BaseModel], Callable[..., Any]] = {
@@ -2928,8 +2930,7 @@ class ModelToComponentFactory:
             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
+                self._job_tracker,
                 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

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/declarative/requesters/http_requester.py

@@ -132,7 +132,7 @@ class HttpRequester(Requester):
             stream_slice=stream_slice,
             next_page_token=next_page_token,
         )
-        return os.path.join(self._url_base.eval(self.config, **interpolation_context), EmptyString)
+        return str(self._url_base.eval(self.config, **interpolation_context))
 
     def get_path(
         self,
@@ -370,13 +370,18 @@ class HttpRequester(Requester):
         Example:
             1) _join_url("https://example.com/api/", "endpoint") >> 'https://example.com/api/endpoint'
             2) _join_url("https://example.com/api", "/endpoint") >> 'https://example.com/api/endpoint'
-            3) _join_url("https://example.com/api/", "") >> 'https://example.com/api'
+            3) _join_url("https://example.com/api/", "") >> 'https://example.com/api/'
             4) _join_url("https://example.com/api", None) >> 'https://example.com/api'
         """
 
         # return a full-url if provided directly from interpolation context
         if path == EmptyString or path is None:
-            return url_base.rstrip("/")
+            return url_base
+        else:
+            # since we didn't provide a full-url, the url_base might not have a trailing slash
+            # so we join the url_base and path correctly
+            if not url_base.endswith("/"):
+                url_base += "/"
 
         return urljoin(url_base, path)
 

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/file_based/file_based_source.py

@@ -48,6 +48,9 @@ from airbyte_cdk.sources.file_based.exceptions import (
     FileBasedErrorsCollector,
     FileBasedSourceError,
 )
+from airbyte_cdk.sources.file_based.file_based_stream_permissions_reader import (
+    AbstractFileBasedStreamPermissionsReader,
+)
 from airbyte_cdk.sources.file_based.file_based_stream_reader import AbstractFileBasedStreamReader
 from airbyte_cdk.sources.file_based.file_types import default_parsers
 from airbyte_cdk.sources.file_based.file_types.file_type_parser import FileTypeParser
@@ -100,8 +103,10 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
         cursor_cls: Type[
             Union[AbstractConcurrentFileBasedCursor, AbstractFileBasedCursor]
         ] = FileBasedConcurrentCursor,
+        stream_permissions_reader: Optional[AbstractFileBasedStreamPermissionsReader] = None,
     ):
         self.stream_reader = stream_reader
+        self.stream_permissions_reader = stream_permissions_reader
         self.spec_class = spec_class
         self.config = config
         self.catalog = catalog
@@ -234,6 +239,8 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
         try:
             parsed_config = self._get_parsed_config(config)
             self.stream_reader.config = parsed_config
+            if self.stream_permissions_reader:
+                self.stream_permissions_reader.config = parsed_config
             streams: List[Stream] = []
             for stream_config in parsed_config.streams:
                 # Like state_manager, `catalog_stream` may be None during `check`
@@ -337,9 +344,23 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
             preserve_directory_structure=preserve_directory_structure(parsed_config),
         )
 
+    def _ensure_permissions_reader_available(self) -> None:
+        """
+        Validates that a stream permissions reader is available.
+        Raises a ValueError if the reader is not provided.
+        """
+        if not self.stream_permissions_reader:
+            raise ValueError(
+                "Stream permissions reader is required for streams that use permissions transfer mode."
+            )
+
     def _make_permissions_stream(
         self, stream_config: FileBasedStreamConfig, cursor: Optional[AbstractFileBasedCursor]
     ) -> AbstractFileBasedStream:
+        """
+        Creates a stream that reads permissions from files.
+        """
+        self._ensure_permissions_reader_available()
         return PermissionsFileBasedStream(
             config=stream_config,
             catalog_schema=self.stream_schemas.get(stream_config.name),
@@ -350,6 +371,7 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
             validation_policy=self._validate_and_get_validation_policy(stream_config),
             errors_collector=self.errors_collector,
             cursor=cursor,
+            stream_permissions_reader=self.stream_permissions_reader,  # type: ignore
         )
 
     def _make_file_based_stream(
@@ -370,9 +392,10 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
     def _make_identities_stream(
         self,
     ) -> Stream:
+        self._ensure_permissions_reader_available()
         return FileIdentitiesStream(
             catalog_schema=self.stream_schemas.get(FileIdentitiesStream.IDENTITIES_STREAM_NAME),
-            stream_reader=self.stream_reader,
+            stream_permissions_reader=self.stream_permissions_reader,  # type: ignore
             discovery_policy=self.discovery_policy,
             errors_collector=self.errors_collector,
         )

airbyte_cdk-6.39.1/airbyte_cdk/sources/file_based/file_based_stream_permissions_reader.py

@@ -0,0 +1,123 @@
+#
+# Copyright (c) 2025 Airbyte, Inc., all rights reserved.
+#
+
+import logging
+from abc import ABC, abstractmethod
+from typing import Any, Dict, Iterable, Optional
+
+from airbyte_cdk.sources.file_based import AbstractFileBasedSpec
+from airbyte_cdk.sources.file_based.remote_file import RemoteFile
+
+
+class AbstractFileBasedStreamPermissionsReader(ABC):
+    """
+    This class is responsible for reading file permissions and Identities from a source.
+    """
+
+    def __init__(self) -> None:
+        self._config = None
+
+    @property
+    def config(self) -> Optional[AbstractFileBasedSpec]:
+        return self._config
+
+    @config.setter
+    @abstractmethod
+    def config(self, value: AbstractFileBasedSpec) -> None:
+        """
+        FileBasedSource reads the config from disk and parses it, and once parsed, the source sets the config on its StreamReader.
+
+        Note: FileBasedSource only requires the keys defined in the abstract config, whereas concrete implementations of StreamReader
+        will require keys that (for example) allow it to authenticate with the 3rd party.
+
+        Therefore, concrete implementations of AbstractFileBasedStreamPermissionsReader's's config setter should assert that `value` is of the correct
+        config type for that type of StreamReader.
+        """
+        ...
+
+    @abstractmethod
+    def get_file_acl_permissions(self, file: RemoteFile, logger: logging.Logger) -> Dict[str, Any]:
+        """
+        This function should return the allow list for a given file, i.e. the list of all identities and their permission levels associated with it
+
+        e.g.
+        def get_file_acl_permissions(self, file: RemoteFile, logger: logging.Logger):
+            api_conn = some_api.conn(credentials=SOME_CREDENTIALS)
+            result = api_conn.get_file_permissions_info(file.id)
+            return MyPermissionsModel(
+                id=result["id"],
+                access_control_list = result["access_control_list"],
+                is_public = result["is_public"],
+                ).dict()
+        """
+        ...
+
+    @abstractmethod
+    def load_identity_groups(self, logger: logging.Logger) -> Iterable[Dict[str, Any]]:
+        """
+        This function should return the Identities in a determined "space" or "domain" where the file metadata (ACLs) are fetched and ACLs items (Identities) exists.
+
+        e.g.
+        def load_identity_groups(self, logger: logging.Logger) -> Iterable[Dict[str, Any]]:
+            api_conn = some_api.conn(credentials=SOME_CREDENTIALS)
+            users_api = api_conn.users()
+            groups_api = api_conn.groups()
+            members_api = self.google_directory_service.members()
+            for user in users_api.list():
+                yield my_identity_model(id=user.id, name=user.name, email_address=user.email, type="user").dict()
+            for group in groups_api.list():
+                group_obj = my_identity_model(id=group.id, name=groups.name, email_address=user.email, type="group").dict()
+                for member in members_api.list(group=group):
+                    group_obj.member_email_addresses = group_obj.member_email_addresses or []
+                    group_obj.member_email_addresses.append(member.email)
+                yield group_obj.dict()
+        """
+        ...
+
+    @property
+    @abstractmethod
+    def file_permissions_schema(self) -> Dict[str, Any]:
+        """
+        This function should return the permissions schema for file permissions stream.
+
+        e.g.
+        def file_permissions_schema(self) -> Dict[str, Any]:
+            # you can also follow the pattern we have for python connectors and have a json file and read from there e.g. schemas/identities.json
+            return {
+                  "type": "object",
+                  "properties": {
+                    "id": { "type": "string" },
+                    "file_path": { "type": "string" },
+                    "access_control_list": {
+                      "type": "array",
+                      "items": { "type": "string" }
+                    },
+                    "publicly_accessible": { "type": "boolean" }
+                  }
+                }
+        """
+        ...
+
+    @property
+    @abstractmethod
+    def identities_schema(self) -> Dict[str, Any]:
+        """
+        This function should return the identities schema for file identity stream.
+
+        e.g.
+        def identities_schema(self) -> Dict[str, Any]:
+            # you can also follow the pattern we have for python connectors and have a json file and read from there e.g. schemas/identities.json
+            return {
+              "type": "object",
+              "properties": {
+                "id": { "type": "string" },
+                "remote_id": { "type": "string" },
+                "name": { "type": ["null", "string"] },
+                "email_address": { "type": ["null", "string"] },
+                "member_email_addresses": { "type": ["null", "array"] },
+                "type": { "type": "string" },
+              }
+            }
+        """
+        ...

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/file_based/file_based_stream_reader.py

@@ -184,97 +184,3 @@ class AbstractFileBasedStreamReader(ABC):
         makedirs(path.dirname(local_file_path), exist_ok=True)
         absolute_file_path = path.abspath(local_file_path)
         return [file_relative_path, local_file_path, absolute_file_path]
-
-    @abstractmethod
-    def get_file_acl_permissions(self, file: RemoteFile, logger: logging.Logger) -> Dict[str, Any]:
-        """
-        This function should return the allow list for a given file, i.e. the list of all identities and their permission levels associated with it
-
-        e.g.
-        def get_file_acl_permissions(self, file: RemoteFile, logger: logging.Logger):
-            api_conn = some_api.conn(credentials=SOME_CREDENTIALS)
-            result = api_conn.get_file_permissions_info(file.id)
-            return MyPermissionsModel(
-                id=result["id"],
-                access_control_list = result["access_control_list"],
-                is_public = result["is_public"],
-                ).dict()
-        """
-        raise NotImplementedError(
-            f"{self.__class__.__name__} does not implement get_file_acl_permissions(). To support ACL permissions, implement this method and update file_permissions_schema."
-        )
-
-    @abstractmethod
-    def load_identity_groups(self, logger: logging.Logger) -> Iterable[Dict[str, Any]]:
-        """
-        This function should return the Identities in a determined "space" or "domain" where the file metadata (ACLs) are fetched and ACLs items (Identities) exists.
-
-        e.g.
-        def load_identity_groups(self, logger: logging.Logger) -> Dict[str, Any]:
-            api_conn = some_api.conn(credentials=SOME_CREDENTIALS)
-            users_api = api_conn.users()
-            groups_api = api_conn.groups()
-            members_api = self.google_directory_service.members()
-            for user in users_api.list():
-                yield my_identity_model(id=user.id, name=user.name, email_address=user.email, type="user").dict()
-            for group in groups_api.list():
-                group_obj = my_identity_model(id=group.id, name=groups.name, email_address=user.email, type="group").dict()
-                for member in members_api.list(group=group):
-                    group_obj.member_email_addresses = group_obj.member_email_addresses or []
-                    group_obj.member_email_addresses.append(member.email)
-                yield group_obj.dict()
-        """
-        raise NotImplementedError(
-            f"{self.__class__.__name__} does not implement load_identity_groups(). To support identities, implement this method and update identities_schema."
-        )
-
-    @property
-    @abstractmethod
-    def file_permissions_schema(self) -> Dict[str, Any]:
-        """
-        This function should return the permissions schema for file permissions stream.
-
-        e.g.
-        def file_permissions_schema(self) -> Dict[str, Any]:
-            # you can also follow the patter we have for python connectors and have a json file and read from there e.g. schemas/identities.json
-            return {
-                  "type": "object",
-                  "properties": {
-                    "id": { "type": "string" },
-                    "file_path": { "type": "string" },
-                    "access_control_list": {
-                      "type": "array",
-                      "items": { "type": "string" }
-                    },
-                    "publicly_accessible": { "type": "boolean" }
-                  }
-                }
-        """
-        raise NotImplementedError(
-            f"{self.__class__.__name__} does not implement file_permissions_schema, please return json schema for your permissions streams."
-        )
-
-    @property
-    @abstractmethod
-    def identities_schema(self) -> Dict[str, Any]:
-        """
-        This function should return the identities schema for file identity stream.
-
-        e.g.
-        def identities_schema(self) -> Dict[str, Any]:
-            # you can also follow the patter we have for python connectors and have a json file and read from there e.g. schemas/identities.json
-            return {
-              "type": "object",
-              "properties": {
-                "id": { "type": "string" },
-                "remote_id": { "type": "string" },
-                "name": { "type": ["null", "string"] },
-                "email_address": { "type": ["null", "string"] },
-                "member_email_addresses": { "type": ["null", "array"] },
-                "type": { "type": "string" },
-              }
-            }
-        """
-        raise NotImplementedError(
-            f"{self.__class__.__name__} does not implement identities_schema, please return json schema for your identities stream."
-        )

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/file_based/stream/default_file_based_stream.py

@@ -356,10 +356,7 @@ class DefaultFileBasedStream(AbstractFileBasedStream, IncrementalMixin):
                         if "null" not in v:
                             schema[k] = ["null"] + v
                     elif v != "null":
-                        if isinstance(v, (str, list)):
-                            schema[k] = ["null", v]
-                        else:
-                            DefaultFileBasedStream._fill_nulls(v)
+                        schema[k] = ["null", v]
                 else:
                     DefaultFileBasedStream._fill_nulls(v)
         elif isinstance(schema, list):

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/file_based/stream/identities_stream.py

@@ -8,7 +8,9 @@ from typing import Any, Dict, Iterable, Mapping, MutableMapping, Optional
 from airbyte_cdk.sources.file_based.config.file_based_stream_config import PrimaryKeyType
 from airbyte_cdk.sources.file_based.discovery_policy import AbstractDiscoveryPolicy
 from airbyte_cdk.sources.file_based.exceptions import FileBasedErrorsCollector
-from airbyte_cdk.sources.file_based.file_based_stream_reader import AbstractFileBasedStreamReader
+from airbyte_cdk.sources.file_based.file_based_stream_permissions_reader import (
+    AbstractFileBasedStreamPermissionsReader,
+)
 from airbyte_cdk.sources.streams.core import JsonSchema
 from airbyte_cdk.sources.streams.permissions.identities_stream import IdentitiesStream
 
@@ -24,13 +26,13 @@ class FileIdentitiesStream(IdentitiesStream):
     def __init__(
         self,
         catalog_schema: Optional[Mapping[str, Any]],
-        stream_reader: AbstractFileBasedStreamReader,
+        stream_permissions_reader: AbstractFileBasedStreamPermissionsReader,
         discovery_policy: AbstractDiscoveryPolicy,
         errors_collector: FileBasedErrorsCollector,
     ) -> None:
         super().__init__()
         self.catalog_schema = catalog_schema
-        self.stream_reader = stream_reader
+        self.stream_permissions_reader = stream_permissions_reader
         self._discovery_policy = discovery_policy
         self.errors_collector = errors_collector
         self._cursor: MutableMapping[str, Any] = {}
@@ -40,8 +42,8 @@ class FileIdentitiesStream(IdentitiesStream):
         return None
 
     def load_identity_groups(self) -> Iterable[Dict[str, Any]]:
-        return self.stream_reader.load_identity_groups(logger=self.logger)
+        return self.stream_permissions_reader.load_identity_groups(logger=self.logger)
 
     @cache
     def get_json_schema(self) -> JsonSchema:
-        return self.stream_reader.identities_schema
+        return self.stream_permissions_reader.identities_schema

{airbyte_cdk-6.38.5.dev0 → airbyte_cdk-6.39.1}/airbyte_cdk/sources/file_based/stream/permissions_file_based_stream.py

@@ -7,6 +7,9 @@ from typing import Any, Dict, Iterable
 
 from airbyte_cdk.models import AirbyteLogMessage, AirbyteMessage, Level
 from airbyte_cdk.models import Type as MessageType
+from airbyte_cdk.sources.file_based.file_based_stream_permissions_reader import (
+    AbstractFileBasedStreamPermissionsReader,
+)
 from airbyte_cdk.sources.file_based.stream import DefaultFileBasedStream
 from airbyte_cdk.sources.file_based.types import StreamSlice
 from airbyte_cdk.sources.streams.core import JsonSchema
@@ -26,10 +29,16 @@ class PermissionsFileBasedStream(DefaultFileBasedStream):
     and schema definition, while this class handles the streaming interface.
     """
 
+    def __init__(
+        self, stream_permissions_reader: AbstractFileBasedStreamPermissionsReader, **kwargs: Any
+    ):
+        super().__init__(**kwargs)
+        self.stream_permissions_reader = stream_permissions_reader
+
     def _filter_schema_invalid_properties(
         self, configured_catalog_json_schema: Dict[str, Any]
     ) -> Dict[str, Any]:
-        return self.stream_reader.file_permissions_schema
+        return self.stream_permissions_reader.file_permissions_schema
 
     def read_records_from_slice(self, stream_slice: StreamSlice) -> Iterable[AirbyteMessage]:
         """
@@ -40,7 +49,7 @@ class PermissionsFileBasedStream(DefaultFileBasedStream):
             no_permissions = False
             file_datetime_string = file.last_modified.strftime(self.DATE_TIME_FORMAT)
             try:
-                permissions_record = self.stream_reader.get_file_acl_permissions(
+                permissions_record = self.stream_permissions_reader.get_file_acl_permissions(
                     file, logger=self.logger
                 )
                 if not permissions_record:
@@ -82,4 +91,4 @@ class PermissionsFileBasedStream(DefaultFileBasedStream):
         Returns:
            The file permissions schema that defines the structure of permission records
         """
-        return self.stream_reader.file_permissions_schema
+        return self.stream_permissions_reader.file_permissions_schema