airbyte-cdk 6.45.0__py3-none-any.whl → 6.45.0.dev4101__py3-none-any.whl

airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -47,12 +47,7 @@ properties:
   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
-      - string
-    examples:
-      - 3
-      - "{{ config['max_concurrent_async_job_count'] }}"
+    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.
@@ -316,6 +311,7 @@ definitions:
     type: object
     required:
       - type
+      - stream_names
     properties:
       type:
         type: string
@@ -329,28 +325,6 @@ definitions:
         examples:
           - ["users"]
           - ["users", "contacts"]
-      dynamic_streams_check_configs:
-        type: array
-        items:
-          "$ref": "#/definitions/DynamicStreamCheckConfig"
-  DynamicStreamCheckConfig:
-    type: object
-    required:
-      - type
-      - dynamic_stream_name
-    properties:
-      type:
-        type: string
-        enum: [DynamicStreamCheckConfig]
-      dynamic_stream_name:
-        title: Dynamic Stream Name
-        description: The dynamic stream name.
-        type: string
-      stream_count:
-        title: Stream Count
-        description: The number of streams to attempt reading from during a check operation. If `stream_count` exceeds the total number of available streams, the minimum of the two values will be used.
-        type: integer
-        default: 0
   CheckDynamicStream:
     title: Dynamic Streams to Check
     description: (This component is experimental. Use at your own risk.) Defines the dynamic streams to try reading when running a check operation.
@@ -1448,6 +1422,42 @@ definitions:
             - "$ref": "#/definitions/LegacyToPerPartitionStateMigration"
             - "$ref": "#/definitions/CustomStateMigration"
         default: []
+      file_uploader:
+        title: File Uploader
+        description: (experimental) Describes how to fetch a file
+        type: object
+        required:
+          - type
+          - requester
+          - download_target_extractor
+        properties:
+          type:
+            type: string
+            enum: [ FileUploader ]
+          requester:
+            description: Requester component that describes how to prepare HTTP requests to send to the source API.
+            anyOf:
+              - "$ref": "#/definitions/CustomRequester"
+              - "$ref": "#/definitions/HttpRequester"
+          download_target_extractor:
+            description: Responsible for fetching the url where the file is located. This is applied on each records and not on the HTTP response
+            anyOf:
+              - "$ref": "#/definitions/CustomRecordExtractor"
+              - "$ref": "#/definitions/DpathExtractor"
+          file_extractor:
+            description: Responsible for fetching the content of the file. If not defined, the assumption is that the whole response body is the file content
+            anyOf:
+              - "$ref": "#/definitions/CustomRecordExtractor"
+              - "$ref": "#/definitions/DpathExtractor"
+          filename_extractor:
+            description: Defines the name to store the file. Stream name is automatically added to the file path. File unique ID can be used to avoid overwriting files. Random UUID will be used if the extractor is not provided.
+            type: string
+            interpolation_context:
+              - config
+              - record
+            examples:
+              - "{{ record.id }}/{{ record.file_name }}/"
+              - "{{ record.id }}_{{ record.file_name }}/"
       $parameters:
         type: object
         additional_properties: true
@@ -1752,30 +1762,6 @@ definitions:
       $parameters:
         type: object
         additionalProperties: true
-  GroupByKeyMergeStrategy:
-    title: Group by Key
-    description: Record merge strategy that combines records according to fields on the record.
-    required:
-      - type
-      - key
-    properties:
-      type:
-        type: string
-        enum: [GroupByKeyMergeStrategy]
-      key:
-        title: Key
-        description: The name of the field on the record whose value will be used to group properties that were retrieved through multiple API requests.
-        anyOf:
-          - type: string
-          - type: array
-            items:
-              type: string
-        examples:
-          - "id"
-          - ["parent_id", "end_date"]
-      $parameters:
-        type: object
-        additionalProperties: true
   SessionTokenAuthenticator:
     type: object
     required:
@@ -1995,9 +1981,7 @@ definitions:
           - type: string
           - type: object
             additionalProperties:
-              anyOf:
-                - type: string
-                - $ref": "#/definitions/QueryProperties"
+              type: string
         interpolation_context:
           - next_page_token
           - stream_interval
@@ -2244,8 +2228,7 @@ definitions:
         type: object
         additionalProperties: true
   JsonDecoder:
-    title: JSON
-    description: Select 'JSON' if the response is formatted as a JSON object.
+    title: Json Decoder
     type: object
     required:
       - type
@@ -2254,8 +2237,8 @@ definitions:
         type: string
         enum: [JsonDecoder]
   JsonlDecoder:
-    title: JSON Lines
-    description: Select 'JSON Lines' if the response consists of JSON objects separated by new lines ('\n') in JSONL format.
+    title: JSONL Decoder
+    description: Use this if the response consists of JSON objects separated by new lines (`\n`) in JSONL format.
     type: object
     required:
       - type
@@ -2380,8 +2363,8 @@ definitions:
         type: object
         additionalProperties: true
   IterableDecoder:
-    title: Iterable
-    description: Select 'Iterable' if the response consists of strings separated by new lines (`\n`). The string will then be wrapped into a JSON object with the `record` key.
+    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.
     type: object
     required:
       - type
@@ -2390,8 +2373,8 @@ definitions:
         type: string
         enum: [IterableDecoder]
   XmlDecoder:
-    title: XML
-    description: Select 'XML' if the response consists of XML-formatted data.
+    title: XML Decoder
+    description: Use this if the response is XML.
     type: object
     required:
       - type
@@ -2422,8 +2405,8 @@ definitions:
         type: object
         additionalProperties: true
   ZipfileDecoder:
-    title: ZIP File
-    description: Select 'ZIP file' for response data that is returned as a zipfile. Requires specifying an inner data type/decoder to parse the unzipped data.
+    title: Zipfile Decoder
+    description: Decoder for response data that is returned as zipfile(s).
     type: object
     additionalProperties: true
     required:
@@ -2947,7 +2930,7 @@ definitions:
         title: Lazy Read Pointer
         description: If set, this will enable lazy reading, using the initial read of parent records to extract child records.
         type: array
-        default: []
+        default: [ ]
         items:
           - type: string
         interpolation_context:
@@ -3015,96 +2998,6 @@ definitions:
     examples:
       - id
       - ["code", "type"]
-  PropertiesFromEndpoint:
-    title: Properties from Endpoint
-    description: Defines the behavior for fetching the list of properties from an API that will be loaded into the requests to extract records.
-    type: object
-    required:
-      - type
-      - property_field_path
-      - retriever
-    properties:
-      type:
-        type: string
-        enum: [PropertiesFromEndpoint]
-      property_field_path:
-        description: Describes the path to the field that should be extracted
-        type: array
-        items:
-          type: string
-        examples:
-          - ["name"]
-        interpolation_context:
-          - config
-          - parameters
-      retriever:
-        description: Requester component that describes how to fetch the properties to query from a remote API endpoint.
-        anyOf:
-          - "$ref": "#/definitions/CustomRetriever"
-          - "$ref": "#/definitions/SimpleRetriever"
-      $parameters:
-        type: object
-        additionalProperties: true
-  PropertyChunking:
-    title: Property Chunking
-    description: For APIs with restrictions on the amount of properties that can be requester per request, property chunking can be applied to make multiple requests with a subset of the properties.
-    type: object
-    required:
-      - type
-      - property_limit_type
-    properties:
-      type:
-        type: string
-        enum: [PropertyChunking]
-      property_limit_type:
-        title: Property Limit Type
-        description: The type used to determine the maximum number of properties per chunk
-        enum:
-          - characters
-          - property_count
-      property_limit:
-        title: Property Limit
-        description: The maximum amount of properties that can be retrieved per request according to the limit type.
-        type: integer
-      record_merge_strategy:
-        title: Record Merge Strategy
-        description: Dictates how to records that require multiple requests to get all properties should be emitted to the destination
-        "$ref": "#/definitions/GroupByKeyMergeStrategy"
-      $parameters:
-        type: object
-        additionalProperties: true
-  QueryProperties:
-    title: Query Properties
-    description: For APIs that require explicit specification of the properties to query for, this component specifies which property fields and how they are supplied to outbound requests.
-    type: object
-    required:
-      - type
-      - property_list
-    properties:
-      type:
-        type: string
-        enum: [QueryProperties]
-      property_list:
-        title: Property List
-        description: The set of properties that will be queried for in the outbound request. This can either be statically defined or dynamic based on an API endpoint
-        anyOf:
-          - type: array
-            items:
-              type: string
-          - "$ref": "#/definitions/PropertiesFromEndpoint"
-      always_include_properties:
-        title: Always Include Properties
-        description: The list of properties that should be included in every set of properties when multiple chunks of properties are being requested.
-        type: array
-        items:
-          type: string
-      property_chunking:
-        title: Property Chunking
-        description: Defines how query properties will be grouped into smaller sets for APIs with limitations on the number of properties fetched per API request.
-        "$ref": "#/definitions/PropertyChunking"
-      $parameters:
-        type: object
-        additionalProperties: true
   RecordFilter:
     title: Record Filter
     description: Filter applied on a list of records.
@@ -3342,7 +3235,7 @@ definitions:
     properties:
       type:
         type: string
-        enum: [StateDelegatingStream]
+        enum: [ StateDelegatingStream ]
       name:
         title: Name
         description: The stream name.
@@ -3397,14 +3290,12 @@ definitions:
           - "$ref": "#/definitions/CustomPartitionRouter"
           - "$ref": "#/definitions/ListPartitionRouter"
           - "$ref": "#/definitions/SubstreamPartitionRouter"
-          - "$ref": "#/definitions/GroupingPartitionRouter"
           - type: array
             items:
               anyOf:
                 - "$ref": "#/definitions/CustomPartitionRouter"
                 - "$ref": "#/definitions/ListPartitionRouter"
                 - "$ref": "#/definitions/SubstreamPartitionRouter"
-                - "$ref": "#/definitions/GroupingPartitionRouter"
       decoder:
         title: Decoder
         description: Component decoding the response so records can be extracted.
@@ -3421,8 +3312,6 @@ definitions:
         type: object
         additionalProperties: true
   GzipDecoder:
-    title: gzip
-    description: Select 'gzip' for response data that is compressed with gzip. Requires specifying an inner data type/decoder to parse the decompressed data.
     type: object
     required:
       - type
@@ -3438,8 +3327,6 @@ definitions:
           - "$ref": "#/definitions/JsonDecoder"
           - "$ref": "#/definitions/JsonlDecoder"
   CsvDecoder:
-    title: CSV
-    description: "Select 'CSV' for response data that is formatted as CSV (comma-separated values). Can specify an encoding (default: 'utf-8') and a delimiter (default: ',')."
     type: object
     required:
       - type
@@ -3570,14 +3457,12 @@ definitions:
           - "$ref": "#/definitions/CustomPartitionRouter"
           - "$ref": "#/definitions/ListPartitionRouter"
           - "$ref": "#/definitions/SubstreamPartitionRouter"
-          - "$ref": "#/definitions/GroupingPartitionRouter"
           - type: array
             items:
               anyOf:
                 - "$ref": "#/definitions/CustomPartitionRouter"
                 - "$ref": "#/definitions/ListPartitionRouter"
                 - "$ref": "#/definitions/SubstreamPartitionRouter"
-                - "$ref": "#/definitions/GroupingPartitionRouter"
       decoder:
         title: Decoder
         description: Component decoding the response so records can be extracted.
@@ -3694,44 +3579,6 @@ definitions:
       $parameters:
         type: object
         additionalProperties: true
-  GroupingPartitionRouter:
-    title: Grouping Partition Router
-    description: >
-      A decorator on top of a partition router that groups partitions into batches of a specified size.
-      This is useful for APIs that support filtering by multiple partition keys in a single request.
-      Note that per-partition incremental syncs may not work as expected because the grouping
-      of partitions might change between syncs, potentially leading to inconsistent state tracking.
-    type: object
-    required:
-      - type
-      - group_size
-      - underlying_partition_router
-    properties:
-      type:
-        type: string
-        enum: [GroupingPartitionRouter]
-      group_size:
-        title: Group Size
-        description: The number of partitions to include in each group. This determines how many partition values are batched together in a single slice.
-        type: integer
-        examples:
-          - 10
-          - 50
-      underlying_partition_router:
-        title: Underlying Partition Router
-        description: The partition router whose output will be grouped. This can be any valid partition router component.
-        anyOf:
-          - "$ref": "#/definitions/CustomPartitionRouter"
-          - "$ref": "#/definitions/ListPartitionRouter"
-          - "$ref": "#/definitions/SubstreamPartitionRouter"
-      deduplicate:
-        title: Deduplicate Partitions
-        description: If true, ensures that partitions are unique within each group by removing duplicates based on the partition key.
-        type: boolean
-        default: true
-      $parameters:
-        type: object
-        additionalProperties: true
   WaitUntilTimeFromHeader:
     title: Wait Until Time Defined In Response Header
     description: Extract time at which we can retry the request from response header and wait for the difference between now and that time.
@@ -3903,13 +3750,6 @@ definitions:
       type:
         type: string
         enum: [DynamicDeclarativeStream]
-      name:
-        title: Name
-        description: The dynamic stream name.
-        type: string
-        default: ""
-        example:
-          - "Tables"
       stream_template:
         title: Stream Template
         description: Reference to the stream template.

airbyte_cdk/sources/declarative/extractors/record_selector.py

@@ -15,6 +15,7 @@ from airbyte_cdk.sources.declarative.extractors.type_transformer import (
 )
 from airbyte_cdk.sources.declarative.interpolation import InterpolatedString
 from airbyte_cdk.sources.declarative.models import SchemaNormalization
+from airbyte_cdk.sources.declarative.retrievers.file_uploader import FileUploader
 from airbyte_cdk.sources.declarative.transformations import RecordTransformation
 from airbyte_cdk.sources.types import Config, Record, StreamSlice, StreamState
 from airbyte_cdk.sources.utils.transform import TypeTransformer
@@ -42,6 +43,7 @@ class RecordSelector(HttpSelector):
     record_filter: Optional[RecordFilter] = None
     transformations: List[RecordTransformation] = field(default_factory=lambda: [])
     transform_before_filtering: bool = False
+    file_uploader: Optional[FileUploader] = None
 
     def __post_init__(self, parameters: Mapping[str, Any]) -> None:
         self._parameters = parameters
@@ -117,7 +119,10 @@ class RecordSelector(HttpSelector):
             transformed_filtered_data, schema=records_schema
         )
         for data in normalized_data:
-            yield Record(data=data, stream_name=self.name, associated_slice=stream_slice)
+            record = Record(data=data, stream_name=self.name, associated_slice=stream_slice)
+            if self.file_uploader:
+                self.file_uploader.upload(record)
+            yield record
 
     def _normalize_by_schema(
         self, records: Iterable[Mapping[str, Any]], schema: Optional[Mapping[str, Any]]

airbyte_cdk/sources/declarative/incremental/concurrent_partition_cursor.py

@@ -79,7 +79,6 @@ class ConcurrentPerPartitionCursor(Cursor):
         connector_state_manager: ConnectorStateManager,
         connector_state_converter: AbstractStreamStateConverter,
         cursor_field: CursorField,
-        use_global_cursor: bool = False,
     ) -> None:
         self._global_cursor: Optional[StreamState] = {}
         self._stream_name = stream_name
@@ -107,7 +106,7 @@ class ConcurrentPerPartitionCursor(Cursor):
         self._lookback_window: int = 0
         self._parent_state: Optional[StreamState] = None
         self._number_of_partitions: int = 0
-        self._use_global_cursor: bool = use_global_cursor
+        self._use_global_cursor: bool = False
         self._partition_serializer = PerPartitionKeySerializer()
         # Track the last time a state message was emitted
         self._last_emission_time: float = 0.0

airbyte_cdk/sources/declarative/interpolation/macros.py

@@ -156,7 +156,7 @@ def duration(datestring: str) -> Union[datetime.timedelta, isodate.Duration]:
 
 
 def format_datetime(
-    dt: Union[str, datetime.datetime, int], format: str, input_format: Optional[str] = None
+    dt: Union[str, datetime.datetime], format: str, input_format: Optional[str] = None
 ) -> str:
     """
     Converts datetime to another format
@@ -170,13 +170,9 @@ def format_datetime(
     """
     if isinstance(dt, datetime.datetime):
         return dt.strftime(format)
-
-    if isinstance(dt, int):
-        dt_datetime = DatetimeParser().parse(dt, input_format if input_format else "%s")
-    else:
-        dt_datetime = (
-            datetime.datetime.strptime(dt, input_format) if input_format else str_to_datetime(dt)
-        )
+    dt_datetime = (
+        datetime.datetime.strptime(dt, input_format) if input_format else str_to_datetime(dt)
+    )
     return DatetimeParser().format(dt=dt_datetime, format=format)
 
 

airbyte_cdk/sources/declarative/manifest_declarative_source.py

@@ -106,7 +106,6 @@ class ManifestDeclarativeSource(DeclarativeSource):
             AlwaysLogSliceLogger() if emit_connector_builder_messages else DebugSliceLogger()
         )
 
-        self._config = config or {}
         self._validate_source()
 
     @property
@@ -117,12 +116,6 @@ class ManifestDeclarativeSource(DeclarativeSource):
     def message_repository(self) -> MessageRepository:
         return self._message_repository
 
-    @property
-    def dynamic_streams(self) -> List[Dict[str, Any]]:
-        return self._dynamic_stream_configs(
-            manifest=self._source_config, config=self._config, with_dynamic_stream_name=True
-        )
-
     @property
     def connection_checker(self) -> ConnectionChecker:
         check = self._source_config["check"]
@@ -355,16 +348,13 @@ class ManifestDeclarativeSource(DeclarativeSource):
         return stream_configs
 
     def _dynamic_stream_configs(
-        self,
-        manifest: Mapping[str, Any],
-        config: Mapping[str, Any],
-        with_dynamic_stream_name: Optional[bool] = None,
+        self, manifest: Mapping[str, Any], config: Mapping[str, Any]
     ) -> List[Dict[str, Any]]:
         dynamic_stream_definitions: List[Dict[str, Any]] = manifest.get("dynamic_streams", [])
         dynamic_stream_configs: List[Dict[str, Any]] = []
         seen_dynamic_streams: Set[str] = set()
 
-        for dynamic_definition_index, dynamic_definition in enumerate(dynamic_stream_definitions):
+        for dynamic_definition in dynamic_stream_definitions:
             components_resolver_config = dynamic_definition["components_resolver"]
 
             if not components_resolver_config:
@@ -397,23 +387,12 @@ class ManifestDeclarativeSource(DeclarativeSource):
             for dynamic_stream in components_resolver.resolve_components(
                 stream_template_config=stream_template_config
             ):
-                dynamic_stream = {
-                    **ManifestComponentTransformer().propagate_types_and_parameters(
-                        "", dynamic_stream, {}, use_parent_parameters=True
-                    )
-                }
-
                 if "type" not in dynamic_stream:
                     dynamic_stream["type"] = "DeclarativeStream"
 
                 # Ensure that each stream is created with a unique name
                 name = dynamic_stream.get("name")
 
-                if with_dynamic_stream_name:
-                    dynamic_stream["dynamic_stream_name"] = dynamic_definition.get(
-                        "name", f"dynamic_stream_{dynamic_definition_index}"
-                    )
-
                 if not isinstance(name, str):
                     raise ValueError(
                         f"Expected stream name {name} to be a string, got {type(name)}."