airbyte-cdk 6.13.0.dev0__py3-none-any.whl → 6.13.1.dev4101__py3-none-any.whl

airbyte_cdk/sources/declarative/concurrent_declarative_source.py

@@ -194,11 +194,10 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
             # Some low-code sources use a combination of DeclarativeStream and regular Python streams. We can't inspect
             # these legacy Python streams the way we do low-code streams to determine if they are concurrent compatible,
             # so we need to treat them as synchronous
-            if isinstance(declarative_stream, DeclarativeStream) and (
-                name_to_stream_mapping[declarative_stream.name]["retriever"]["type"]
+            if (
+                isinstance(declarative_stream, DeclarativeStream)
+                and name_to_stream_mapping[declarative_stream.name]["retriever"]["type"]
                 == "SimpleRetriever"
-                or name_to_stream_mapping[declarative_stream.name]["retriever"]["type"]
-                == "AsyncRetriever"
             ):
                 incremental_sync_component_definition = name_to_stream_mapping[
                     declarative_stream.name
@@ -218,11 +217,6 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
                     and not incremental_sync_component_definition
                 )
 
-                is_async_job_stream = (
-                    name_to_stream_mapping[declarative_stream.name].get("retriever", {}).get("type")
-                    == "AsyncRetriever"
-                )
-
                 if self._is_datetime_incremental_without_partition_routing(
                     declarative_stream, incremental_sync_component_definition
                 ):
@@ -274,26 +268,15 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
                 elif (
                     is_substream_without_incremental or is_without_partition_router_or_cursor
                 ) and hasattr(declarative_stream.retriever, "stream_slicer"):
-                    if is_async_job_stream:
-                        # A stream's AsyncRetriever must be shared across all partitions because it uses a
-                        # shared JobRepository to manage the state of jobs requests and when they are ready
-                        async_retriever = declarative_stream.retriever
-
-                        def async_retriever_factory_method() -> Retriever:
-                            return async_retriever
-
-                        retriever_factory = async_retriever_factory_method
-                    else:
-                        retriever_factory = self._retriever_factory(
-                            name_to_stream_mapping[declarative_stream.name],
-                            config,
-                            {},
-                        )
                     partition_generator = StreamSlicerPartitionGenerator(
                         DeclarativePartitionFactory(
                             declarative_stream.name,
                             declarative_stream.get_json_schema(),
-                            retriever_factory,
+                            self._retriever_factory(
+                                name_to_stream_mapping[declarative_stream.name],
+                                config,
+                                {},
+                            ),
                             self.message_repository,
                         ),
                         declarative_stream.retriever.stream_slicer,

airbyte_cdk/sources/declarative/requesters/paginators/default_paginator.py

@@ -112,39 +112,27 @@ class DefaultPaginator(Paginator):
             )
         if isinstance(self.url_base, str):
             self.url_base = InterpolatedString(string=self.url_base, parameters=parameters)
-
-    def get_initial_token(self) -> Optional[Any]:
-        """
-        Return the page token that should be used for the first request of a stream
-
-        WARNING: get_initial_token() should not be used by streams that use RFR that perform checkpointing
-        of state using page numbers. Because paginators are stateless
-        """
-        return self.pagination_strategy.initial_token
+        self._token: Optional[Any] = self.pagination_strategy.initial_token
 
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any] = None,
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Mapping[str, Any]]:
-        next_page_token = self.pagination_strategy.next_page_token(
-            response=response,
-            last_page_size=last_page_size,
-            last_record=last_record,
-            last_page_token_value=last_page_token_value,
+        self._token = self.pagination_strategy.next_page_token(
+            response, last_page_size, last_record
         )
-        if next_page_token:
-            return {"next_page_token": next_page_token}
+        if self._token:
+            return {"next_page_token": self._token}
         else:
             return None
 
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
-        token = next_page_token.get("next_page_token") if next_page_token else None
-        if token and self.page_token_option and isinstance(self.page_token_option, RequestPath):
+    def path(self) -> Optional[str]:
+        if (
+            self._token
+            and self.page_token_option
+            and isinstance(self.page_token_option, RequestPath)
+        ):
             # Replace url base to only return the path
-            return str(token).replace(self.url_base.eval(self.config), "")  # type: ignore # url_base is casted to a InterpolatedString in __post_init__
+            return str(self._token).replace(self.url_base.eval(self.config), "")  # type: ignore # url_base is casted to a InterpolatedString in __post_init__
         else:
             return None
 
@@ -155,7 +143,7 @@ class DefaultPaginator(Paginator):
         stream_slice: Optional[StreamSlice] = None,
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> MutableMapping[str, Any]:
-        return self._get_request_options(RequestOptionType.request_parameter, next_page_token)
+        return self._get_request_options(RequestOptionType.request_parameter)
 
     def get_request_headers(
         self,
@@ -164,7 +152,7 @@ class DefaultPaginator(Paginator):
         stream_slice: Optional[StreamSlice] = None,
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> Mapping[str, str]:
-        return self._get_request_options(RequestOptionType.header, next_page_token)
+        return self._get_request_options(RequestOptionType.header)
 
     def get_request_body_data(
         self,
@@ -173,7 +161,7 @@ class DefaultPaginator(Paginator):
         stream_slice: Optional[StreamSlice] = None,
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> Mapping[str, Any]:
-        return self._get_request_options(RequestOptionType.body_data, next_page_token)
+        return self._get_request_options(RequestOptionType.body_data)
 
     def get_request_body_json(
         self,
@@ -182,21 +170,25 @@ class DefaultPaginator(Paginator):
         stream_slice: Optional[StreamSlice] = None,
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> Mapping[str, Any]:
-        return self._get_request_options(RequestOptionType.body_json, next_page_token)
+        return self._get_request_options(RequestOptionType.body_json)
 
-    def _get_request_options(
-        self, option_type: RequestOptionType, next_page_token: Optional[Mapping[str, Any]]
-    ) -> MutableMapping[str, Any]:
+    def reset(self, reset_value: Optional[Any] = None) -> None:
+        if reset_value:
+            self.pagination_strategy.reset(reset_value=reset_value)
+        else:
+            self.pagination_strategy.reset()
+        self._token = self.pagination_strategy.initial_token
+
+    def _get_request_options(self, option_type: RequestOptionType) -> MutableMapping[str, Any]:
         options = {}
 
-        token = next_page_token.get("next_page_token") if next_page_token else None
         if (
             self.page_token_option
-            and token is not None
+            and self._token is not None
             and isinstance(self.page_token_option, RequestOption)
             and self.page_token_option.inject_into == option_type
         ):
-            options[self.page_token_option.field_name.eval(config=self.config)] = token  # type: ignore # field_name is always cast to an interpolated string
+            options[self.page_token_option.field_name.eval(config=self.config)] = self._token  # type: ignore # field_name is always cast to an interpolated string
         if (
             self.page_size_option
             and self.pagination_strategy.get_page_size()
@@ -212,9 +204,6 @@ class PaginatorTestReadDecorator(Paginator):
     """
     In some cases, we want to limit the number of requests that are made to the backend source. This class allows for limiting the number of
     pages that are queried throughout a read command.
-
-    WARNING: This decorator is not currently thread-safe like the rest of the low-code framework because it has
-    an internal state to track the current number of pages counted so that it can exit early during a test read
     """
 
     _PAGE_COUNT_BEFORE_FIRST_NEXT_CALL = 1
@@ -228,27 +217,17 @@ class PaginatorTestReadDecorator(Paginator):
         self._decorated = decorated
         self._page_count = self._PAGE_COUNT_BEFORE_FIRST_NEXT_CALL
 
-    def get_initial_token(self) -> Optional[Any]:
-        self._page_count = self._PAGE_COUNT_BEFORE_FIRST_NEXT_CALL
-        return self._decorated.get_initial_token()
-
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any] = None,
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Mapping[str, Any]]:
         if self._page_count >= self._maximum_number_of_pages:
             return None
 
         self._page_count += 1
-        return self._decorated.next_page_token(
-            response, last_page_size, last_record, last_page_token_value
-        )
+        return self._decorated.next_page_token(response, last_page_size, last_record)
 
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
-        return self._decorated.path(next_page_token)
+    def path(self) -> Optional[str]:
+        return self._decorated.path()
 
     def get_request_params(
         self,
@@ -293,3 +272,7 @@ class PaginatorTestReadDecorator(Paginator):
         return self._decorated.get_request_body_json(
             stream_state=stream_state, stream_slice=stream_slice, next_page_token=next_page_token
         )
+
+    def reset(self, reset_value: Optional[Any] = None) -> None:
+        self._decorated.reset()
+        self._page_count = self._PAGE_COUNT_BEFORE_FIRST_NEXT_CALL

airbyte_cdk/sources/declarative/requesters/paginators/no_pagination.py

@@ -19,7 +19,7 @@ class NoPagination(Paginator):
 
     parameters: InitVar[Mapping[str, Any]]
 
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
+    def path(self) -> Optional[str]:
         return None
 
     def get_request_params(
@@ -58,14 +58,11 @@ class NoPagination(Paginator):
     ) -> Mapping[str, Any]:
         return {}
 
-    def get_initial_token(self) -> Optional[Any]:
-        return None
-
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any],
-    ) -> Optional[Mapping[str, Any]]:
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
+    ) -> Mapping[str, Any]:
         return {}
+
+    def reset(self, reset_value: Optional[Any] = None) -> None:
+        # No state to reset
+        pass

airbyte_cdk/sources/declarative/requesters/paginators/paginator.py

@@ -24,18 +24,14 @@ class Paginator(ABC, RequestOptionsProvider):
     """
 
     @abstractmethod
-    def get_initial_token(self) -> Optional[Any]:
+    def reset(self, reset_value: Optional[Any] = None) -> None:
         """
-        Get the page token that should be included in the request to get the first page of records
+        Reset the pagination's inner state
         """
 
     @abstractmethod
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any],
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Mapping[str, Any]]:
         """
         Returns the next_page_token to use to fetch the next page of records.
@@ -43,13 +39,12 @@ class Paginator(ABC, RequestOptionsProvider):
         :param response: the response to process
         :param last_page_size: the number of records read from the response
         :param last_record: the last record extracted from the response
-        :param last_page_token_value: The current value of the page token made on the last request
         :return: A mapping {"next_page_token": <token>} for the next page from the input response object. Returning None means there are no more pages to read in this response.
         """
         pass
 
     @abstractmethod
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
+    def path(self) -> Optional[str]:
         """
         Returns the URL path to hit to fetch the next page of records
 

airbyte_cdk/sources/declarative/requesters/paginators/strategies/cursor_pagination_strategy.py

@@ -43,6 +43,7 @@ class CursorPaginationStrategy(PaginationStrategy):
     )
 
     def __post_init__(self, parameters: Mapping[str, Any]) -> None:
+        self._initial_cursor = None
         if isinstance(self.cursor_value, str):
             self._cursor_value = InterpolatedString.create(self.cursor_value, parameters=parameters)
         else:
@@ -56,19 +57,10 @@ class CursorPaginationStrategy(PaginationStrategy):
 
     @property
     def initial_token(self) -> Optional[Any]:
-        """
-        CursorPaginationStrategy does not have an initial value because the next cursor is typically included
-        in the response of the first request. For Resumable Full Refresh streams that checkpoint the page
-        cursor, the next cursor should be read from the state or stream slice object.
-        """
-        return None
+        return self._initial_cursor
 
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any] = None,
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Any]:
         decoded_response = next(self.decoder.decode(response))
 
@@ -95,5 +87,8 @@ class CursorPaginationStrategy(PaginationStrategy):
         )
         return token if token else None
 
+    def reset(self, reset_value: Optional[Any] = None) -> None:
+        self._initial_cursor = reset_value
+
     def get_page_size(self) -> Optional[int]:
         return self.page_size

airbyte_cdk/sources/declarative/requesters/paginators/strategies/offset_increment.py

@@ -52,6 +52,7 @@ class OffsetIncrement(PaginationStrategy):
     inject_on_first_request: bool = False
 
     def __post_init__(self, parameters: Mapping[str, Any]) -> None:
+        self._offset = 0
         page_size = str(self.page_size) if isinstance(self.page_size, int) else self.page_size
         if page_size:
             self._page_size: Optional[InterpolatedString] = InterpolatedString(
@@ -63,15 +64,11 @@ class OffsetIncrement(PaginationStrategy):
     @property
     def initial_token(self) -> Optional[Any]:
         if self.inject_on_first_request:
-            return 0
+            return self._offset
         return None
 
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any] = None,
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Any]:
         decoded_response = next(self.decoder.decode(response))
 
@@ -81,17 +78,9 @@ class OffsetIncrement(PaginationStrategy):
             and last_page_size < self._page_size.eval(self.config, response=decoded_response)
         ) or last_page_size == 0:
             return None
-        elif last_page_token_value is None:
-            # If the OffsetIncrement strategy does not inject on the first request, the incoming last_page_token_value
-            # will be None. For this case, we assume that None was the first page and progress to the next offset
-            return 0 + last_page_size
-        elif not isinstance(last_page_token_value, int):
-            raise ValueError(
-                "The page token for a OffsetIncrement pagination strategy must be an integer"
-            )
         else:
-            next_page_token_value = last_page_token_value + last_page_size
-            return next_page_token_value
+            self._offset += last_page_size
+            return self._offset
 
     def reset(self, reset_value: Optional[Any] = 0) -> None:
         if not isinstance(reset_value, int):

airbyte_cdk/sources/declarative/requesters/paginators/strategies/page_increment.py

@@ -31,6 +31,7 @@ class PageIncrement(PaginationStrategy):
     inject_on_first_request: bool = False
 
     def __post_init__(self, parameters: Mapping[str, Any]) -> None:
+        self._page = self.start_from_page
         if isinstance(self.page_size, int) or (self.page_size is None):
             self._page_size = self.page_size
         else:
@@ -42,30 +43,28 @@ class PageIncrement(PaginationStrategy):
     @property
     def initial_token(self) -> Optional[Any]:
         if self.inject_on_first_request:
-            return self.start_from_page
+            return self._page
         return None
 
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any],
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Any]:
         # Stop paginating when there are fewer records than the page size or the current page has no records
         if (self._page_size and last_page_size < self._page_size) or last_page_size == 0:
             return None
-        elif last_page_token_value is None:
-            # If the PageIncrement strategy does not inject on the first request, the incoming last_page_token_value
-            # may be None. When this is the case, we assume we've already requested the first page specified by
-            # start_from_page and must now get the next page
-            return self.start_from_page + 1
-        elif not isinstance(last_page_token_value, int):
+        else:
+            self._page += 1
+            return self._page
+
+    def reset(self, reset_value: Optional[Any] = None) -> None:
+        if reset_value is None:
+            self._page = self.start_from_page
+        elif not isinstance(reset_value, int):
             raise ValueError(
-                "The page token for a PageIncrement pagination strategy must be an integer"
+                f"Reset value {reset_value} for PageIncrement pagination strategy was not an integer"
             )
         else:
-            return last_page_token_value + 1
+            self._page = reset_value
 
     def get_page_size(self) -> Optional[int]:
         return self._page_size

airbyte_cdk/sources/declarative/requesters/paginators/strategies/pagination_strategy.py

@@ -4,7 +4,7 @@
 
 from abc import abstractmethod
 from dataclasses import dataclass
-from typing import Any, Mapping, Optional
+from typing import Any, Optional
 
 import requests
 
@@ -26,21 +26,22 @@ class PaginationStrategy:
 
     @abstractmethod
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any],
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Any]:
         """
         :param response: response to process
         :param last_page_size: the number of records read from the response
         :param last_record: the last record extracted from the response
-        :param last_page_token_value: The current value of the page token made on the last request
         :return: next page token. Returns None if there are no more pages to fetch
         """
         pass
 
+    @abstractmethod
+    def reset(self, reset_value: Optional[Any] = None) -> None:
+        """
+        Reset the pagination's inner state
+        """
+
     @abstractmethod
     def get_page_size(self) -> Optional[int]:
         """

airbyte_cdk/sources/declarative/requesters/paginators/strategies/stop_condition.py

@@ -44,19 +44,16 @@ class StopConditionPaginationStrategyDecorator(PaginationStrategy):
         self._stop_condition = stop_condition
 
     def next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any] = None,
+        self, response: requests.Response, last_page_size: int, last_record: Optional[Record]
     ) -> Optional[Any]:
-        # We evaluate in reverse order because the assumption is that most of the APIs using data feed structure
-        # will return records in descending order. In terms of performance/memory, we return the records lazily
+        # We evaluate in reverse order because the assumption is that most of the APIs using data feed structure will return records in
+        # descending order. In terms of performance/memory, we return the records lazily
         if last_record and self._stop_condition.is_met(last_record):
             return None
-        return self._delegate.next_page_token(
-            response, last_page_size, last_record, last_page_token_value
-        )
+        return self._delegate.next_page_token(response, last_page_size, last_record)
+
+    def reset(self, reset_value: Optional[Any] = None) -> None:
+        self._delegate.reset(reset_value)
 
     def get_page_size(self) -> Optional[int]:
         return self._delegate.get_page_size()

airbyte_cdk/sources/declarative/retrievers/simple_retriever.py

@@ -6,7 +6,18 @@ import json
 from dataclasses import InitVar, dataclass, field
 from functools import partial
 from itertools import islice
-from typing import Any, Callable, Iterable, List, Mapping, Optional, Set, Tuple, Union
+from typing import (
+    Any,
+    Callable,
+    Iterable,
+    List,
+    Mapping,
+    MutableMapping,
+    Optional,
+    Set,
+    Tuple,
+    Union,
+)
 
 import requests
 
@@ -79,6 +90,9 @@ class SimpleRetriever(Retriever):
 
     def __post_init__(self, parameters: Mapping[str, Any]) -> None:
         self._paginator = self.paginator or NoPagination(parameters=parameters)
+        self._last_response: Optional[requests.Response] = None
+        self._last_page_size: int = 0
+        self._last_record: Optional[Record] = None
         self._parameters = parameters
         self._name = (
             InterpolatedString(self._name, parameters=parameters)
@@ -86,6 +100,10 @@ class SimpleRetriever(Retriever):
             else self._name
         )
 
+        # This mapping is used during a resumable full refresh syncs to indicate whether a partition has started syncing
+        # records. Partitions serve as the key and map to True if they already began processing records
+        self._partition_started: MutableMapping[Any, bool] = dict()
+
     @property  # type: ignore
     def name(self) -> str:
         """
@@ -233,13 +251,17 @@ class SimpleRetriever(Retriever):
             raise ValueError("Request body json cannot be a string")
         return body_json
 
-    def _paginator_path(self, next_page_token: Optional[Mapping[str, Any]] = None) -> Optional[str]:
+    def _paginator_path(
+        self,
+    ) -> Optional[str]:
         """
         If the paginator points to a path, follow it, else return nothing so the requester is used.
+        :param stream_state:
+        :param stream_slice:
         :param next_page_token:
         :return:
         """
-        return self._paginator.path(next_page_token=next_page_token)
+        return self._paginator.path()
 
     def _parse_response(
         self,
@@ -250,15 +272,22 @@ class SimpleRetriever(Retriever):
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> Iterable[Record]:
         if not response:
+            self._last_response = None
             yield from []
         else:
-            yield from self.record_selector.select_records(
+            self._last_response = response
+            record_generator = self.record_selector.select_records(
                 response=response,
                 stream_state=stream_state,
                 records_schema=records_schema,
                 stream_slice=stream_slice,
                 next_page_token=next_page_token,
             )
+            self._last_page_size = 0
+            for record in record_generator:
+                self._last_page_size += 1
+                self._last_record = record
+                yield record
 
     @property  # type: ignore
     def primary_key(self) -> Optional[Union[str, List[str], List[List[str]]]]:
@@ -270,13 +299,7 @@ class SimpleRetriever(Retriever):
         if not isinstance(value, property):
             self._primary_key = value
 
-    def _next_page_token(
-        self,
-        response: requests.Response,
-        last_page_size: int,
-        last_record: Optional[Record],
-        last_page_token_value: Optional[Any],
-    ) -> Optional[Mapping[str, Any]]:
+    def _next_page_token(self, response: requests.Response) -> Optional[Mapping[str, Any]]:
         """
         Specifies a pagination strategy.
 
@@ -284,12 +307,7 @@ class SimpleRetriever(Retriever):
 
         :return: The token for the next page from the input response object. Returning None means there are no more pages to read in this response.
         """
-        return self._paginator.next_page_token(
-            response=response,
-            last_page_size=last_page_size,
-            last_record=last_record,
-            last_page_token_value=last_page_token_value,
-        )
+        return self._paginator.next_page_token(response, self._last_page_size, self._last_record)
 
     def _fetch_next_page(
         self,
@@ -298,7 +316,7 @@ class SimpleRetriever(Retriever):
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> Optional[requests.Response]:
         return self.requester.send_request(
-            path=self._paginator_path(next_page_token=next_page_token),
+            path=self._paginator_path(),
             stream_state=stream_state,
             stream_slice=stream_slice,
             next_page_token=next_page_token,
@@ -327,37 +345,20 @@ class SimpleRetriever(Retriever):
     # This logic is similar to _read_pages in the HttpStream class. When making changes here, consider making changes there as well.
     def _read_pages(
         self,
-        records_generator_fn: Callable[[Optional[requests.Response]], Iterable[Record]],
+        records_generator_fn: Callable[[Optional[requests.Response]], Iterable[StreamData]],
         stream_state: Mapping[str, Any],
         stream_slice: StreamSlice,
-    ) -> Iterable[Record]:
+    ) -> Iterable[StreamData]:
         pagination_complete = False
-        initial_token = self._paginator.get_initial_token()
-        next_page_token: Optional[Mapping[str, Any]] = (
-            {"next_page_token": initial_token} if initial_token else None
-        )
+        next_page_token = None
         while not pagination_complete:
             response = self._fetch_next_page(stream_state, stream_slice, next_page_token)
-
-            last_page_size = 0
-            last_record: Optional[Record] = None
-            for record in records_generator_fn(response):
-                last_page_size += 1
-                last_record = record
-                yield record
+            yield from records_generator_fn(response)
 
             if not response:
                 pagination_complete = True
             else:
-                last_page_token_value = (
-                    next_page_token.get("next_page_token") if next_page_token else None
-                )
-                next_page_token = self._next_page_token(
-                    response=response,
-                    last_page_size=last_page_size,
-                    last_record=last_record,
-                    last_page_token_value=last_page_token_value,
-                )
+                next_page_token = self._next_page_token(response)
                 if not next_page_token:
                     pagination_complete = True
 
@@ -366,38 +367,19 @@ class SimpleRetriever(Retriever):
 
     def _read_single_page(
         self,
-        records_generator_fn: Callable[[Optional[requests.Response]], Iterable[Record]],
+        records_generator_fn: Callable[[Optional[requests.Response]], Iterable[StreamData]],
         stream_state: Mapping[str, Any],
         stream_slice: StreamSlice,
     ) -> Iterable[StreamData]:
-        initial_token = stream_state.get("next_page_token")
-        if initial_token is None:
-            initial_token = self._paginator.get_initial_token()
-        next_page_token: Optional[Mapping[str, Any]] = (
-            {"next_page_token": initial_token} if initial_token else None
-        )
-
-        response = self._fetch_next_page(stream_state, stream_slice, next_page_token)
-
-        last_page_size = 0
-        last_record: Optional[Record] = None
-        for record in records_generator_fn(response):
-            last_page_size += 1
-            last_record = record
-            yield record
+        response = self._fetch_next_page(stream_state, stream_slice)
+        yield from records_generator_fn(response)
 
         if not response:
-            next_page_token = {FULL_REFRESH_SYNC_COMPLETE_KEY: True}
+            next_page_token: Mapping[str, Any] = {FULL_REFRESH_SYNC_COMPLETE_KEY: True}
         else:
-            last_page_token_value = (
-                next_page_token.get("next_page_token") if next_page_token else None
-            )
-            next_page_token = self._next_page_token(
-                response=response,
-                last_page_size=last_page_size,
-                last_record=last_record,
-                last_page_token_value=last_page_token_value,
-            ) or {FULL_REFRESH_SYNC_COMPLETE_KEY: True}
+            next_page_token = self._next_page_token(response) or {
+                FULL_REFRESH_SYNC_COMPLETE_KEY: True
+            }
 
         if self.cursor:
             self.cursor.close_slice(
@@ -432,14 +414,25 @@ class SimpleRetriever(Retriever):
         if self.cursor and isinstance(self.cursor, ResumableFullRefreshCursor):
             stream_state = self.state
 
-            # Before syncing the RFR stream, we check if the job's prior attempt was successful and don't need to
-            # fetch more records. The platform deletes stream state for full refresh streams before starting a
-            # new job, so we don't need to worry about this value existing for the initial attempt
+            # Before syncing the RFR stream, we check if the job's prior attempt was successful and don't need to fetch more records
+            # The platform deletes stream state for full refresh streams before starting a new job, so we don't need to worry about
+            # this value existing for the initial attempt
             if stream_state.get(FULL_REFRESH_SYNC_COMPLETE_KEY):
                 return
+            cursor_value = stream_state.get("next_page_token")
+
+            # The first attempt to read a page for the current partition should reset the paginator to the current
+            # cursor state which is initially assigned to the incoming state from the platform
+            partition_key = self._to_partition_key(_slice.partition)
+            if partition_key not in self._partition_started:
+                self._partition_started[partition_key] = True
+                self._paginator.reset(reset_value=cursor_value)
 
             yield from self._read_single_page(record_generator, stream_state, _slice)
         else:
+            # Fixing paginator types has a long tail of dependencies
+            self._paginator.reset()
+
             for stream_data in self._read_pages(record_generator, self.state, _slice):
                 current_record = self._extract_record(stream_data, _slice)
                 if self.cursor and current_record:
@@ -525,7 +518,7 @@ class SimpleRetriever(Retriever):
         stream_state: Mapping[str, Any],
         records_schema: Mapping[str, Any],
         stream_slice: Optional[StreamSlice],
-    ) -> Iterable[Record]:
+    ) -> Iterable[StreamData]:
         yield from self._parse_response(
             response,
             stream_slice=stream_slice,
@@ -569,7 +562,7 @@ class SimpleRetrieverTestReadDecorator(SimpleRetriever):
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> Optional[requests.Response]:
         return self.requester.send_request(
-            path=self._paginator_path(next_page_token=next_page_token),
+            path=self._paginator_path(),
             stream_state=stream_state,
             stream_slice=stream_slice,
             next_page_token=next_page_token,

airbyte_cdk/sources/file_based/config/abstract_file_based_spec.py

@@ -31,6 +31,12 @@ class DeliverRawFiles(BaseModel):
 
     delivery_type: Literal["use_file_transfer"] = Field("use_file_transfer", const=True)
 
+    preserve_subdirectories_directories: bool = Field(
+        title="Preserve Subdirectories Directories",
+        description="Flag indicating we should preserve subdirectories directories",
+        default=True,
+    )
+
 
 class AbstractFileBasedSpec(BaseModel):
     """
@@ -65,6 +71,12 @@ class AbstractFileBasedSpec(BaseModel):
         airbyte_hidden=True,
     )
 
+    preserve_subdirectories_directories: bool = Field(
+        title="Preserve Subdirectories Directories",
+        description="Flag indicating we should preserve subdirectories directories",
+        default=True,
+    )
+
     @classmethod
     @abstractmethod
     def documentation_url(cls) -> AnyUrl:

airbyte_cdk/sources/file_based/exceptions.py

@@ -111,6 +111,10 @@ class ErrorListingFiles(BaseFileBasedSourceError):
     pass
 
 
+class DuplicatedFilesError(BaseFileBasedSourceError):
+    pass
+
+
 class CustomFileBasedException(AirbyteTracedException):
     """
     A specialized exception for file-based connectors.
@@ -123,3 +127,25 @@ class CustomFileBasedException(AirbyteTracedException):
 
 class FileSizeLimitError(CustomFileBasedException):
     pass
+
+
+def format_duplicate_files_error_message(
+    stream_name: str, duplicated_files_names: List[dict[str, List[str]]]
+) -> str:
+    duplicated_files_messages = []
+    for duplicated_file in duplicated_files_names:
+        for duplicated_file_name, file_paths in duplicated_file.items():
+            file_duplicated_message = (
+                f"{len(file_paths)} duplicates found for file name {duplicated_file_name}:\n\n"
+                + "".join(f"\n - {file_paths}")
+            )
+            duplicated_files_messages.append(file_duplicated_message)
+
+    error_message = (
+        f"ERROR: Duplicate filenames found for stream {stream_name}. "
+        "Duplicate file names are not allowed if the Preserve Subdirectories in File Paths option is disabled. "
+        "Please remove or rename the duplicate files before attempting to re-run the sync.\n\n"
+        + "\n".join(duplicated_files_messages)
+    )
+
+    return error_message

airbyte_cdk/sources/file_based/file_based_source.py

@@ -242,7 +242,7 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
                         stream=self._make_default_stream(
                             stream_config=stream_config,
                             cursor=cursor,
-                            use_file_transfer=self._use_file_transfer(parsed_config),
+                            parsed_config=parsed_config,
                         ),
                         source=self,
                         logger=self.logger,
@@ -273,7 +273,7 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
                         stream=self._make_default_stream(
                             stream_config=stream_config,
                             cursor=cursor,
-                            use_file_transfer=self._use_file_transfer(parsed_config),
+                            parsed_config=parsed_config,
                         ),
                         source=self,
                         logger=self.logger,
@@ -285,7 +285,7 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
                     stream = self._make_default_stream(
                         stream_config=stream_config,
                         cursor=cursor,
-                        use_file_transfer=self._use_file_transfer(parsed_config),
+                        parsed_config=parsed_config,
                     )
 
                 streams.append(stream)
@@ -298,7 +298,7 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
         self,
         stream_config: FileBasedStreamConfig,
         cursor: Optional[AbstractFileBasedCursor],
-        use_file_transfer: bool = False,
+        parsed_config: AbstractFileBasedSpec,
     ) -> AbstractFileBasedStream:
         return DefaultFileBasedStream(
             config=stream_config,
@@ -310,7 +310,10 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
             validation_policy=self._validate_and_get_validation_policy(stream_config),
             errors_collector=self.errors_collector,
             cursor=cursor,
-            use_file_transfer=use_file_transfer,
+            use_file_transfer=self._use_file_transfer(parsed_config),
+            preserve_subdirectories_directories=self._preserve_subdirectories_directories(
+                parsed_config
+            ),
         )
 
     def _get_stream_from_catalog(
@@ -385,3 +388,13 @@ class FileBasedSource(ConcurrentSourceAdapter, ABC):
             and parsed_config.delivery_method.delivery_type == "use_file_transfer"
         )
         return use_file_transfer
+
+    @staticmethod
+    def _preserve_subdirectories_directories(parsed_config: AbstractFileBasedSpec) -> bool:
+        # fall back to preserve subdirectories if config is not present or incomplete
+        if (
+            hasattr(parsed_config, "preserve_subdirectories_directories")
+            and parsed_config.preserve_subdirectories_directories is not None
+        ):
+            return parsed_config.preserve_subdirectories_directories
+        return True

airbyte_cdk/sources/file_based/file_based_stream_reader.py

@@ -135,6 +135,16 @@ class AbstractFileBasedStreamReader(ABC):
             return use_file_transfer
         return False
 
+    def preserve_subdirectories_directories(self) -> bool:
+        # fall back to preserve subdirectories if config is not present or incomplete
+        if (
+            self.config
+            and hasattr(self.config, "preserve_subdirectories_directories")
+            and self.config.preserve_subdirectories_directories is not None
+        ):
+            return self.config.preserve_subdirectories_directories
+        return True
+
     @abstractmethod
     def get_file(
         self, file: RemoteFile, local_directory: str, logger: logging.Logger
@@ -159,10 +169,13 @@ class AbstractFileBasedStreamReader(ABC):
         """
         ...
 
-    @staticmethod
-    def _get_file_transfer_paths(file: RemoteFile, local_directory: str) -> List[str]:
-        # Remove left slashes from source path format to make relative path for writing locally
-        file_relative_path = file.uri.lstrip("/")
+    def _get_file_transfer_paths(self, file: RemoteFile, local_directory: str) -> List[str]:
+        preserve_subdirectories_directories = self.preserve_subdirectories_directories()
+        if preserve_subdirectories_directories:
+            # Remove left slashes from source path format to make relative path for writing locally
+            file_relative_path = file.uri.lstrip("/")
+        else:
+            file_relative_path = path.basename(file.uri)
         local_file_path = path.join(local_directory, file_relative_path)
 
         # Ensure the local directory exists

airbyte_cdk/sources/file_based/stream/default_file_based_stream.py

@@ -5,20 +5,24 @@
 import asyncio
 import itertools
 import traceback
+from collections import defaultdict
 from copy import deepcopy
 from functools import cache
-from typing import Any, Dict, Iterable, List, Mapping, MutableMapping, Optional, Set, Union
+from os import path
+from typing import Any, Dict, Iterable, List, Mapping, MutableMapping, Optional, Set, Tuple, Union
 
 from airbyte_cdk.models import AirbyteLogMessage, AirbyteMessage, FailureType, Level
 from airbyte_cdk.models import Type as MessageType
 from airbyte_cdk.sources.file_based.config.file_based_stream_config import PrimaryKeyType
 from airbyte_cdk.sources.file_based.exceptions import (
+    DuplicatedFilesError,
     FileBasedSourceError,
     InvalidSchemaError,
     MissingSchemaError,
     RecordParseError,
     SchemaInferenceError,
     StopSyncPerValidationPolicy,
+    format_duplicate_files_error_message,
 )
 from airbyte_cdk.sources.file_based.file_types import FileTransfer
 from airbyte_cdk.sources.file_based.remote_file import RemoteFile
@@ -43,6 +47,8 @@ class DefaultFileBasedStream(AbstractFileBasedStream, IncrementalMixin):
     """
 
     FILE_TRANSFER_KW = "use_file_transfer"
+    PRESERVE_SUBDIRECTORIES_KW = "preserve_subdirectories_directories"
+    FILES_KEY = "files"
     DATE_TIME_FORMAT = "%Y-%m-%dT%H:%M:%S.%fZ"
     ab_last_mod_col = "_ab_source_file_last_modified"
     ab_file_name_col = "_ab_source_file_url"
@@ -50,10 +56,14 @@ class DefaultFileBasedStream(AbstractFileBasedStream, IncrementalMixin):
     source_file_url = "source_file_url"
     airbyte_columns = [ab_last_mod_col, ab_file_name_col]
     use_file_transfer = False
+    preserve_subdirectories_directories = True
 
     def __init__(self, **kwargs: Any):
         if self.FILE_TRANSFER_KW in kwargs:
             self.use_file_transfer = kwargs.pop(self.FILE_TRANSFER_KW, False)
+            self.preserve_subdirectories_directories = kwargs.pop(
+                self.PRESERVE_SUBDIRECTORIES_KW, True
+            )
         super().__init__(**kwargs)
 
     @property
@@ -98,15 +108,43 @@ class DefaultFileBasedStream(AbstractFileBasedStream, IncrementalMixin):
         else:
             return super()._filter_schema_invalid_properties(configured_catalog_json_schema)
 
+    def _duplicated_files_names(
+        self, slices: List[dict[str, List[RemoteFile]]]
+    ) -> List[dict[str, List[str]]]:
+        seen_file_names = set()
+        duplicates_file_names = set()
+        file_paths = defaultdict(list)
+        for file_slice in slices:
+            for file_found in file_slice[self.FILES_KEY]:
+                file_name = path.basename(file_found.uri)
+                if file_name not in seen_file_names:
+                    seen_file_names.add(file_name)
+                else:
+                    duplicates_file_names.add(file_name)
+                file_paths[file_name].append(file_found.uri)
+        return [
+            {duplicated_file: file_paths[duplicated_file]}
+            for duplicated_file in duplicates_file_names
+        ]
+
     def compute_slices(self) -> Iterable[Optional[Mapping[str, Any]]]:
         # Sort files by last_modified, uri and return them grouped by last_modified
         all_files = self.list_files()
         files_to_read = self._cursor.get_files_to_sync(all_files, self.logger)
         sorted_files_to_read = sorted(files_to_read, key=lambda f: (f.last_modified, f.uri))
         slices = [
-            {"files": list(group[1])}
+            {self.FILES_KEY: list(group[1])}
             for group in itertools.groupby(sorted_files_to_read, lambda f: f.last_modified)
         ]
+        if slices and not self.preserve_subdirectories_directories:
+            duplicated_files_names = self._duplicated_files_names(slices)
+            if duplicated_files_names:
+                raise DuplicatedFilesError(
+                    format_duplicate_files_error_message(
+                        stream_name=self.name, duplicated_files_names=duplicated_files_names
+                    ),
+                    stream=self.name,
+                )
         return slices
 
     def transform_record(

{airbyte_cdk-6.13.0.dev0.dist-info → airbyte_cdk-6.13.1.dev4101.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: airbyte-cdk
-Version: 6.13.0.dev0
+Version: 6.13.1.dev4101
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT

{airbyte_cdk-6.13.0.dev0.dist-info → airbyte_cdk-6.13.1.dev4101.dist-info}/RECORD

@@ -62,7 +62,7 @@ airbyte_cdk/sources/declarative/checks/check_stream.py,sha256=dAA-UhmMj0WLXCkRQr
 airbyte_cdk/sources/declarative/checks/connection_checker.py,sha256=MBRJo6WJlZQHpIfOGaNOkkHUmgUl_4wDM6VPo41z5Ss,1383
 airbyte_cdk/sources/declarative/concurrency_level/__init__.py,sha256=5XUqrmlstYlMM0j6crktlKQwALek0uiz2D3WdM46MyA,191
 airbyte_cdk/sources/declarative/concurrency_level/concurrency_level.py,sha256=YIwCTCpOr_QSNW4ltQK0yUGWInI8PKNY216HOOegYLk,2101
-airbyte_cdk/sources/declarative/concurrent_declarative_source.py,sha256=G5bqKcYZTPhY9-CGwbmJDOdgThZOnIx75W3p0H1VlmM,24325
+airbyte_cdk/sources/declarative/concurrent_declarative_source.py,sha256=PxP4p2686wsf1gjsumGKnh2o2Jjnrqg8QLGijEIrp-A,23412
 airbyte_cdk/sources/declarative/datetime/__init__.py,sha256=l9LG7Qm6e5r_qgqfVKnx3mXYtg1I9MmMjomVIPfU4XA,177
 airbyte_cdk/sources/declarative/datetime/datetime_parser.py,sha256=SX9JjdesN1edN2WVUVMzU_ptqp2QB1OnsnjZ4mwcX7w,2579
 airbyte_cdk/sources/declarative/datetime/min_max_datetime.py,sha256=0BHBtDNQZfvwM45-tY5pNlTcKAFSGGNxemoi0Jic-0E,5785
@@ -135,15 +135,15 @@ airbyte_cdk/sources/declarative/requesters/error_handlers/http_response_filter.p
 airbyte_cdk/sources/declarative/requesters/http_job_repository.py,sha256=o0520AmHMb7SAoeokVNwoOzuZzIAT6ryx9uFYGSOrs0,8664
 airbyte_cdk/sources/declarative/requesters/http_requester.py,sha256=RqYPkgJFAWfcZBTc-JBcGHPm4JL1ZQOhs9GKU4MP2eE,14723
 airbyte_cdk/sources/declarative/requesters/paginators/__init__.py,sha256=uArbKs9JKNCt7t9tZoeWwjDpyI1HoPp29FNW0JzvaEM,644
-airbyte_cdk/sources/declarative/requesters/paginators/default_paginator.py,sha256=FnSl3qPvv5wD6ieAI2Ic5c4dqBk-3fRe4tCaWzq3YwM,11840
-airbyte_cdk/sources/declarative/requesters/paginators/no_pagination.py,sha256=j6j9QRPaTbKQ2N661RFVKthhkWiodEp6ut0tKeEd0Ng,2019
-airbyte_cdk/sources/declarative/requesters/paginators/paginator.py,sha256=OlN-y0PEOMzlUNUh3pzonoTpIJpGwkP4ibFengvpLVU,2230
+airbyte_cdk/sources/declarative/requesters/paginators/default_paginator.py,sha256=LxTq1hieznRWlYlfODdZbMDUml-g6NyBkdwVI2mCNMM,10910
+airbyte_cdk/sources/declarative/requesters/paginators/no_pagination.py,sha256=-P-QOlefFhEe99bsB2y3yTvA8c8kCCbfBaTS6qPvF6I,1927
+airbyte_cdk/sources/declarative/requesters/paginators/paginator.py,sha256=ZgyvH7DOrASQ5K__J5SRAXH3REUW2n3yPHnFW9xq4NU,1972
 airbyte_cdk/sources/declarative/requesters/paginators/strategies/__init__.py,sha256=2gly8fuZpDNwtu1Qg6oE2jBLGqQRdzSLJdnpk_iDV6I,767
-airbyte_cdk/sources/declarative/requesters/paginators/strategies/cursor_pagination_strategy.py,sha256=yLzzK5YIRTkXd2Z-BS__AZXuTd6HXjJIxq05K-lQoxI,3898
-airbyte_cdk/sources/declarative/requesters/paginators/strategies/offset_increment.py,sha256=8qOyydbRrZqL6XbbHksNetteumZ8AEAUNoOo4L6zZr0,3960
-airbyte_cdk/sources/declarative/requesters/paginators/strategies/page_increment.py,sha256=a202Je_hxst_RwobRGRQT59nWoDI1tr8b-q3sMEcL4w,2701
-airbyte_cdk/sources/declarative/requesters/paginators/strategies/pagination_strategy.py,sha256=UiHQI2lsRDPqM4nMvKMnmsXA3gFg5BFE4lCPEBhuCTs,1317
-airbyte_cdk/sources/declarative/requesters/paginators/strategies/stop_condition.py,sha256=LoKXdUbSgHEtSwtA8DFrnX6SpQbRVVwreY8NguTKTcI,2229
+airbyte_cdk/sources/declarative/requesters/paginators/strategies/cursor_pagination_strategy.py,sha256=vFzpNv8BdgXrYO5qhi2_Un4x4y-EAQWxinZtEPWz5KI,3654
+airbyte_cdk/sources/declarative/requesters/paginators/strategies/offset_increment.py,sha256=pMPi6iQrhtrI9VRPj218QNM_OqD8lX8P3Tr9yloKoE8,3367
+airbyte_cdk/sources/declarative/requesters/paginators/strategies/page_increment.py,sha256=kQGpfr-dOwarxTIf2S4sHVulBzm8zSwQXBM7rOhkafA,2491
+airbyte_cdk/sources/declarative/requesters/paginators/strategies/pagination_strategy.py,sha256=ABpO4t0UUziBZnyml8UT_NhlF6loekhQji57TpKnaiY,1290
+airbyte_cdk/sources/declarative/requesters/paginators/strategies/stop_condition.py,sha256=-8NwokW-aKwv8DdeHh1ssODTobBYSOmIhH2-IjSjlNA,2213
 airbyte_cdk/sources/declarative/requesters/request_option.py,sha256=_qmv8CLQQ3fERt6BuMZeRu6tZXscPoeARx1VJdWMQ_M,1055
 airbyte_cdk/sources/declarative/requesters/request_options/__init__.py,sha256=WCwpKqM4wKqy-DHJaCHbKAlFqRVOqMi9K5qonxIfi_Y,809
 airbyte_cdk/sources/declarative/requesters/request_options/datetime_based_request_options_provider.py,sha256=FLkg0uzC9bc-zFnALWr0FLYpKsz8iK2xQsd4UOyeW08,3706
@@ -161,7 +161,7 @@ airbyte_cdk/sources/declarative/resolvers/http_components_resolver.py,sha256=Aio
 airbyte_cdk/sources/declarative/retrievers/__init__.py,sha256=ix9m1dkR69DcXCXUKC5RK_ZZM7ojTLBQ4IkWQTfmfCk,456
 airbyte_cdk/sources/declarative/retrievers/async_retriever.py,sha256=_-d3MvHh-4r46i4wjQikD4ZygKA7TvuDu2i04qqULEg,3731
 airbyte_cdk/sources/declarative/retrievers/retriever.py,sha256=XPLs593Xv8c5cKMc37XzUAYmzlXd1a7eSsspM-CMuWA,1696
-airbyte_cdk/sources/declarative/retrievers/simple_retriever.py,sha256=jxQ_9xcVD07r9PKhofitAqMkdX1k8ZNyy50qz5NwkFs,24540
+airbyte_cdk/sources/declarative/retrievers/simple_retriever.py,sha256=N4swGw5mfuTXJ2R7AKX18CHzizsr69pXwt5uSHLPi48,24172
 airbyte_cdk/sources/declarative/schema/__init__.py,sha256=HztgVVaZdil5UfgUZcv_Hyy84r89_EKRwyO2hoewNVg,749
 airbyte_cdk/sources/declarative/schema/default_schema_loader.py,sha256=KTACrIE23a83wsm3Rd9Eb4K6-20lrGqYxTHNp9yxsso,1820
 airbyte_cdk/sources/declarative/schema/dynamic_schema_loader.py,sha256=H6A3NQ6kPPM-cUNPmdvDPc9xNzR1rQNrK95GbgCW334,8822
@@ -193,7 +193,7 @@ airbyte_cdk/sources/file_based/availability_strategy/__init__.py,sha256=ddKQfUmk
 airbyte_cdk/sources/file_based/availability_strategy/abstract_file_based_availability_strategy.py,sha256=01Nd4b7ERAbp-OZo_8rrAzFXWPTMwr02SnWiN17nx8Q,2363
 airbyte_cdk/sources/file_based/availability_strategy/default_file_based_availability_strategy.py,sha256=j9T5TimfWFUz7nqsaj-83G3xWmDpsmeSbDnaUNmz0UM,5849
 airbyte_cdk/sources/file_based/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-airbyte_cdk/sources/file_based/config/abstract_file_based_spec.py,sha256=tj-M1L5BTa5yIQ3jHo09CtCTSq_eR-68zgyOPqwsurw,6455
+airbyte_cdk/sources/file_based/config/abstract_file_based_spec.py,sha256=zjFFoLMb9TL3zJkTmm-YtmqQ0Y4EwIGFljM8s8h7hxU,6899
 airbyte_cdk/sources/file_based/config/avro_format.py,sha256=NxTF96ewzn6HuhgodsY7Rpb-ybr1ZEWW5d4Vid64g5A,716
 airbyte_cdk/sources/file_based/config/csv_format.py,sha256=NWekkyT8dTwiVK0mwa_krQD4FJPHSDfILo8kPAg3-Vs,8006
 airbyte_cdk/sources/file_based/config/excel_format.py,sha256=9qAmTsT6SoVzNfNv0oBVkVCmiyqQuVAbfRKajjoa7Js,378
@@ -204,9 +204,9 @@ airbyte_cdk/sources/file_based/config/unstructured_format.py,sha256=tIbB9Pn1HqU6
 airbyte_cdk/sources/file_based/discovery_policy/__init__.py,sha256=gl3ey6mZbyfraB9P3pFhf9UJp2JeTZ1SUFAopy2iBvY,301
 airbyte_cdk/sources/file_based/discovery_policy/abstract_discovery_policy.py,sha256=dCfXX529Rd5rtopg4VeEgTPJjFtqjtjzPq6LCw18Wt0,605
 airbyte_cdk/sources/file_based/discovery_policy/default_discovery_policy.py,sha256=-xujTidtrq6HC00WKbjQh1CZdT5LMuzkp5BLjqDmfTY,1007
-airbyte_cdk/sources/file_based/exceptions.py,sha256=AEELNIRzKPX6eopKd_2jhE7WiNeR0Aw7nQWVOL8fvkc,5760
-airbyte_cdk/sources/file_based/file_based_source.py,sha256=RfpctRNLJ_EHKKEc2E1EZGYRfhG0Z9o6TgsKS4XrSNY,16652
-airbyte_cdk/sources/file_based/file_based_stream_reader.py,sha256=ohxKlqPuV7TGwjyRy_gaWUol8QN5lBSoCYoaqBtRh1c,6179
+airbyte_cdk/sources/file_based/exceptions.py,sha256=KfOgQgssBKgsv3h5po2IG1DhZcH664Zf_fx96mBlPSg,6761
+airbyte_cdk/sources/file_based/file_based_source.py,sha256=cnAncQfuXMAKK_u8W2GFlPXTaPUs_FAP-H6tXuNcgGg,17189
+airbyte_cdk/sources/file_based/file_based_stream_reader.py,sha256=MwH4kHELXvNvE_CBxedxgfZtyOS71N1OBY-x03kgLeo,6816
 airbyte_cdk/sources/file_based/file_types/__init__.py,sha256=blCLn0-2LC-ZdgcNyDEhqM2RiUvEjEBh-G4-t32ZtuM,1268
 airbyte_cdk/sources/file_based/file_types/avro_parser.py,sha256=XNx-JC-sgzH9u3nOJ2M59FxBXvtig8LN6BIkeDOavZA,10858
 airbyte_cdk/sources/file_based/file_types/csv_parser.py,sha256=QlCXB-ry3np67Q_VerQEPoWDOTcPTB6Go4ydZxY9ae4,20445
@@ -232,7 +232,7 @@ airbyte_cdk/sources/file_based/stream/concurrent/cursor/file_based_final_state_c
 airbyte_cdk/sources/file_based/stream/cursor/__init__.py,sha256=MhFB5hOo8sjwvCh8gangaymdg3EJWYt_72brFOZt068,191
 airbyte_cdk/sources/file_based/stream/cursor/abstract_file_based_cursor.py,sha256=om-x3gZFPgWDpi15S9RxZmR36VHnk8sytgN6LlBQhAw,1934
 airbyte_cdk/sources/file_based/stream/cursor/default_file_based_cursor.py,sha256=VGV7xLyBribuBMVrXtO1xqkWJD86bl7yhXtjnwLMohM,7051
-airbyte_cdk/sources/file_based/stream/default_file_based_stream.py,sha256=rpwU6AOyhFLuXtcFKkcOHFWbRQ4kLCOKzAjcID_M87k,16770
+airbyte_cdk/sources/file_based/stream/default_file_based_stream.py,sha256=HRjR0rQGc8cYK2PxpLgAvZQ--jvtV8QgS1QIxkemnko,18413
 airbyte_cdk/sources/file_based/types.py,sha256=INxG7OPnkdUP69oYNKMAbwhvV1AGvLRHs1J6pIia2FI,218
 airbyte_cdk/sources/http_config.py,sha256=OBZeuyFilm6NlDlBhFQvHhTWabEvZww6OHDIlZujIS0,730
 airbyte_cdk/sources/http_logger.py,sha256=TyBmtRA6D9g0XDkKGvdM415b36RXDjgfkwRewDsH8-0,1576
@@ -340,8 +340,8 @@ airbyte_cdk/utils/slice_hasher.py,sha256=-pHexlNYoWYPnXNH-M7HEbjmeJe9Zk7SJijdQ7d
 airbyte_cdk/utils/spec_schema_transformations.py,sha256=-5HTuNsnDBAhj-oLeQXwpTGA0HdcjFOf2zTEMUTTg_Y,816
 airbyte_cdk/utils/stream_status_utils.py,sha256=ZmBoiy5HVbUEHAMrUONxZvxnvfV9CesmQJLDTAIWnWw,1171
 airbyte_cdk/utils/traced_exception.py,sha256=C8uIBuCL_E4WnBAOPSxBicD06JAldoN9fGsQDp463OY,6292
-airbyte_cdk-6.13.0.dev0.dist-info/LICENSE.txt,sha256=Wfe61S4BaGPj404v8lrAbvhjYR68SHlkzeYrg3_bbuM,1051
-airbyte_cdk-6.13.0.dev0.dist-info/METADATA,sha256=DsnhBukVBErZ-7zXBww8Gtdw1nMQ0cGg7QpIzj_2Fvk,5993
-airbyte_cdk-6.13.0.dev0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-airbyte_cdk-6.13.0.dev0.dist-info/entry_points.txt,sha256=fj-e3PAQvsxsQzyyq8UkG1k8spunWnD4BAH2AwlR6NM,95
-airbyte_cdk-6.13.0.dev0.dist-info/RECORD,,
+airbyte_cdk-6.13.1.dev4101.dist-info/LICENSE.txt,sha256=Wfe61S4BaGPj404v8lrAbvhjYR68SHlkzeYrg3_bbuM,1051
+airbyte_cdk-6.13.1.dev4101.dist-info/METADATA,sha256=qzqdg5215pSnyafRjwL5bK2Qw4Wvr7FpOuxWJUFZc6M,5996
+airbyte_cdk-6.13.1.dev4101.dist-info/WHEEL,sha256=RaoafKOydTQ7I_I3JTrPCg6kUmTgtm4BornzOqyEfJ8,88
+airbyte_cdk-6.13.1.dev4101.dist-info/entry_points.txt,sha256=fj-e3PAQvsxsQzyyq8UkG1k8spunWnD4BAH2AwlR6NM,95
+airbyte_cdk-6.13.1.dev4101.dist-info/RECORD,,

{airbyte_cdk-6.13.0.dev0.dist-info → airbyte_cdk-6.13.1.dev4101.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: poetry-core 2.0.0
 Root-Is-Purelib: true
 Tag: py3-none-any