airbyte-cdk 6.12.4__tar.gz → 6.13.0__tar.gz

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: airbyte-cdk
-Version: 6.12.4
+Version: 6.13.0
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/__init__.py

@@ -48,27 +48,46 @@ API Reference
 # Once those issues are resolved, the below can be sorted with isort.
 import dunamai as _dunamai
 
-from .destinations import Destination
-from .models import AirbyteConnectionStatus, AirbyteMessage, ConfiguredAirbyteCatalog, Status, Type, FailureType, AirbyteStream, AdvancedAuth, DestinationSyncMode, ConnectorSpecification, OAuthConfigSpecification, OrchestratorType, ConfiguredAirbyteStream, SyncMode, AirbyteLogMessage, Level, AirbyteRecordMessage
-
-from .sources import Source
-from .config_observation import create_connector_config_control_message, emit_configuration_as_airbyte_control_message
+from .config_observation import (
+    create_connector_config_control_message,
+    emit_configuration_as_airbyte_control_message,
+)
 from .connector import BaseConnector, Connector
-
-from .entrypoint import launch, AirbyteEntrypoint
-
+from .destinations import Destination
+from .entrypoint import AirbyteEntrypoint, launch
 from .logger import AirbyteLogFormatter, init_logger
-from .sources import AbstractSource
+from .models import (
+    AdvancedAuth,
+    AirbyteConnectionStatus,
+    AirbyteLogMessage,
+    AirbyteMessage,
+    AirbyteRecordMessage,
+    AirbyteStream,
+    ConfiguredAirbyteCatalog,
+    ConfiguredAirbyteStream,
+    ConnectorSpecification,
+    DestinationSyncMode,
+    FailureType,
+    Level,
+    OAuthConfigSpecification,
+    OrchestratorType,
+    Status,
+    SyncMode,
+    Type,
+)
+from .sources import AbstractSource, Source
 from .sources.concurrent_source.concurrent_source import ConcurrentSource
 from .sources.concurrent_source.concurrent_source_adapter import ConcurrentSourceAdapter
 from .sources.config import BaseConfig
-from .sources.types import Config, Record, StreamSlice
 from .sources.connector_state_manager import ConnectorStateManager
 from .sources.declarative.auth import DeclarativeOauth2Authenticator
-from .sources.declarative.auth.declarative_authenticator import DeclarativeAuthenticator
-from .sources.declarative.auth.declarative_authenticator import NoAuth
+from .sources.declarative.auth.declarative_authenticator import DeclarativeAuthenticator, NoAuth
 from .sources.declarative.auth.oauth import DeclarativeSingleUseRefreshTokenOauth2Authenticator
-from .sources.declarative.auth.token import BasicHttpAuthenticator, BearerAuthenticator, ApiKeyAuthenticator
+from .sources.declarative.auth.token import (
+    ApiKeyAuthenticator,
+    BasicHttpAuthenticator,
+    BearerAuthenticator,
+)
 from .sources.declarative.datetime.min_max_datetime import MinMaxDatetime
 from .sources.declarative.declarative_stream import DeclarativeStream
 from .sources.declarative.decoders import Decoder, JsonDecoder
@@ -77,48 +96,89 @@ from .sources.declarative.extractors import DpathExtractor, RecordSelector
 from .sources.declarative.extractors.record_extractor import RecordExtractor
 from .sources.declarative.extractors.record_filter import RecordFilter
 from .sources.declarative.incremental import DatetimeBasedCursor
-from .sources.declarative.interpolation import InterpolatedString, InterpolatedBoolean
+from .sources.declarative.interpolation import InterpolatedBoolean, InterpolatedString
 from .sources.declarative.manifest_declarative_source import ManifestDeclarativeSource
-from .sources.declarative.migrations.legacy_to_per_partition_state_migration import LegacyToPerPartitionStateMigration
-
-from .sources.declarative.partition_routers import CartesianProductStreamSlicer, SinglePartitionRouter, SubstreamPartitionRouter
+from .sources.declarative.migrations.legacy_to_per_partition_state_migration import (
+    LegacyToPerPartitionStateMigration,
+)
+from .sources.declarative.partition_routers import (
+    CartesianProductStreamSlicer,
+    SinglePartitionRouter,
+    SubstreamPartitionRouter,
+)
 from .sources.declarative.partition_routers.substream_partition_router import ParentStreamConfig
-from .sources.declarative.requesters import Requester, HttpRequester
-
+from .sources.declarative.requesters import HttpRequester, Requester
 from .sources.declarative.requesters.error_handlers import BackoffStrategy
 from .sources.declarative.requesters.paginators import DefaultPaginator, PaginationStrategy
-from .sources.declarative.requesters.paginators.strategies import OffsetIncrement, CursorPaginationStrategy, PageIncrement, StopConditionPaginationStrategyDecorator
-
+from .sources.declarative.requesters.paginators.strategies import (
+    CursorPaginationStrategy,
+    OffsetIncrement,
+    PageIncrement,
+    StopConditionPaginationStrategyDecorator,
+)
 from .sources.declarative.requesters.request_option import RequestOption, RequestOptionType
-
-from .sources.declarative.requesters.request_options.default_request_options_provider import DefaultRequestOptionsProvider
-from .sources.declarative.requesters.request_options.interpolated_request_input_provider import InterpolatedRequestInputProvider
+from .sources.declarative.requesters.request_options.default_request_options_provider import (
+    DefaultRequestOptionsProvider,
+)
+from .sources.declarative.requesters.request_options.interpolated_request_input_provider import (
+    InterpolatedRequestInputProvider,
+)
 from .sources.declarative.requesters.requester import HttpMethod
 from .sources.declarative.retrievers import SimpleRetriever
 from .sources.declarative.schema import JsonFileSchemaLoader
-from .sources.declarative.transformations.add_fields import AddFields, AddedFieldDefinition
+from .sources.declarative.transformations.add_fields import AddedFieldDefinition, AddFields
 from .sources.declarative.transformations.transformation import RecordTransformation
 from .sources.declarative.types import FieldPointer
 from .sources.declarative.yaml_declarative_source import YamlDeclarativeSource
 from .sources.message import InMemoryMessageRepository, MessageRepository
 from .sources.source import TState
 from .sources.streams.availability_strategy import AvailabilityStrategy
-from .sources.streams.call_rate import AbstractAPIBudget, HttpAPIBudget, HttpRequestMatcher, MovingWindowCallRatePolicy, Rate, CachedLimiterSession, LimiterSession
+from .sources.streams.call_rate import (
+    AbstractAPIBudget,
+    CachedLimiterSession,
+    HttpAPIBudget,
+    HttpRequestMatcher,
+    LimiterSession,
+    MovingWindowCallRatePolicy,
+    Rate,
+)
 from .sources.streams.checkpoint import Cursor as LegacyCursor
 from .sources.streams.checkpoint import ResumableFullRefreshCursor
 from .sources.streams.concurrent.adapters import StreamFacade
-from .sources.streams.concurrent.cursor import ConcurrentCursor, CursorField, FinalStateCursor
-from .sources.streams.concurrent.cursor import Cursor
-from .sources.streams.concurrent.state_converters.datetime_stream_state_converter import EpochValueConcurrentStreamStateConverter, IsoMillisConcurrentStreamStateConverter
-from .sources.streams.core import Stream, IncrementalMixin, package_name_from_class
+from .sources.streams.concurrent.cursor import (
+    ConcurrentCursor,
+    Cursor,
+    CursorField,
+    FinalStateCursor,
+)
+from .sources.streams.concurrent.state_converters.datetime_stream_state_converter import (
+    EpochValueConcurrentStreamStateConverter,
+    IsoMillisConcurrentStreamStateConverter,
+)
+from .sources.streams.core import IncrementalMixin, Stream, package_name_from_class
 from .sources.streams.http import HttpStream, HttpSubStream
 from .sources.streams.http.availability_strategy import HttpAvailabilityStrategy
-from .sources.streams.http.exceptions import BaseBackoffException, DefaultBackoffException, UserDefinedBackoffException
+from .sources.streams.http.exceptions import (
+    BaseBackoffException,
+    DefaultBackoffException,
+    UserDefinedBackoffException,
+)
 from .sources.streams.http.rate_limiting import default_backoff_handler
-from .sources.streams.http.requests_native_auth import Oauth2Authenticator, TokenAuthenticator, SingleUseRefreshTokenOauth2Authenticator
+from .sources.streams.http.requests_native_auth import (
+    Oauth2Authenticator,
+    SingleUseRefreshTokenOauth2Authenticator,
+    TokenAuthenticator,
+)
 from .sources.streams.http.requests_native_auth.abstract_token import AbstractHeaderAuthenticator
+from .sources.types import Config, Record, StreamSlice
 from .sources.utils import casing
-from .sources.utils.schema_helpers import InternalConfig, ResourceSchemaLoader, check_config_against_spec_or_exit, split_config, expand_refs
+from .sources.utils.schema_helpers import (
+    InternalConfig,
+    ResourceSchemaLoader,
+    check_config_against_spec_or_exit,
+    expand_refs,
+    split_config,
+)
 from .sources.utils.transform import TransformConfig, TypeTransformer
 from .utils import AirbyteTracedException, is_cloud_environment
 from .utils.constants import ENV_REQUEST_CACHE_PATH
@@ -127,7 +187,6 @@ from .utils.oneof_option_config import OneOfOptionConfig
 from .utils.spec_schema_transformations import resolve_refs
 from .utils.stream_status_utils import as_airbyte_message
 
-
 __all__ = [
     # Availability strategy
     "AvailabilityStrategy",

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/cli/source_declarative_manifest/__init__.py

@@ -1,6 +1,5 @@
 from airbyte_cdk.cli.source_declarative_manifest._run import run
 
-
 __all__ = [
     "run",
 ]

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/models/__init__.py

@@ -7,7 +7,6 @@
 # of airbyte-cdk rather than a standalone package.
 from .airbyte_protocol import (
     AdvancedAuth,
-    AirbyteStateStats,
     AirbyteAnalyticsTraceMessage,
     AirbyteCatalog,
     AirbyteConnectionStatus,
@@ -22,13 +21,14 @@ from .airbyte_protocol import (
     AirbyteRecordMessage,
     AirbyteStateBlob,
     AirbyteStateMessage,
+    AirbyteStateStats,
     AirbyteStateType,
     AirbyteStream,
     AirbyteStreamState,
     AirbyteStreamStatus,
-    AirbyteStreamStatusTraceMessage,
     AirbyteStreamStatusReason,
     AirbyteStreamStatusReasonType,
+    AirbyteStreamStatusTraceMessage,
     AirbyteTraceMessage,
     AuthFlowType,
     ConfiguredAirbyteCatalog,
@@ -48,6 +48,14 @@ from .airbyte_protocol import (
     TraceType,
     Type,
 )
+from .airbyte_protocol_serializers import (
+    AirbyteMessageSerializer,
+    AirbyteStateMessageSerializer,
+    AirbyteStreamStateSerializer,
+    ConfiguredAirbyteCatalogSerializer,
+    ConfiguredAirbyteStreamSerializer,
+    ConnectorSpecificationSerializer,
+)
 from .well_known_types import (
     BinaryData,
     Boolean,
@@ -61,12 +69,3 @@ from .well_known_types import (
     TimeWithoutTimezone,
     TimeWithTimezone,
 )
-
-from .airbyte_protocol_serializers import (
-AirbyteStreamStateSerializer,
-AirbyteStateMessageSerializer,
-AirbyteMessageSerializer,
-ConfiguredAirbyteCatalogSerializer,
-ConfiguredAirbyteStreamSerializer,
-ConnectorSpecificationSerializer,
-)

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/sources/declarative/async_job/job_orchestrator.py

@@ -20,7 +20,6 @@ from typing import (
     TypeVar,
 )
 
-from airbyte_cdk import StreamSlice
 from airbyte_cdk.logger import lazy_log
 from airbyte_cdk.models import FailureType
 from airbyte_cdk.sources.declarative.async_job.job import AsyncJob
@@ -31,6 +30,7 @@ from airbyte_cdk.sources.declarative.async_job.job_tracker import (
 from airbyte_cdk.sources.declarative.async_job.repository import AsyncJobRepository
 from airbyte_cdk.sources.declarative.async_job.status import AsyncJobStatus
 from airbyte_cdk.sources.message import MessageRepository
+from airbyte_cdk.sources.types import StreamSlice
 from airbyte_cdk.utils.airbyte_secrets_utils import filter_secrets
 from airbyte_cdk.utils.traced_exception import AirbyteTracedException
 

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/sources/declarative/auth/__init__.py

@@ -2,10 +2,7 @@
 # Copyright (c) 2023 Airbyte, Inc., all rights reserved.
 #
 
-from airbyte_cdk.sources.declarative.auth.oauth import DeclarativeOauth2Authenticator
 from airbyte_cdk.sources.declarative.auth.jwt import JwtAuthenticator
+from airbyte_cdk.sources.declarative.auth.oauth import DeclarativeOauth2Authenticator
 
-__all__ = [
-    "DeclarativeOauth2Authenticator",
-    "JwtAuthenticator"
-]
+__all__ = ["DeclarativeOauth2Authenticator", "JwtAuthenticator"]

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -2766,9 +2766,64 @@ definitions:
           - "$ref": "#/definitions/IterableDecoder"
           - "$ref": "#/definitions/XmlDecoder"
           - "$ref": "#/definitions/GzipJsonDecoder"
+          - "$ref": "#/definitions/CompositeRawDecoder"
       $parameters:
         type: object
         additionalProperties: true
+  CompositeRawDecoder:
+    description: "(This is experimental, use at your own risk)"
+    type: object
+    required:
+      - type
+      - parser
+    properties:
+      type:
+        type: string
+        enum: [CompositeRawDecoder]
+      parser:
+        anyOf:
+          - "$ref": "#/definitions/GzipParser"
+          - "$ref": "#/definitions/JsonLineParser"
+          - "$ref": "#/definitions/CsvParser"
+  #    PARSERS
+  GzipParser:
+    type: object
+    required:
+      - type
+      - inner_parser
+    properties:
+      type:
+        type: string
+        enum: [GzipParser]
+      inner_parser:
+        anyOf:
+          - "$ref": "#/definitions/JsonLineParser"
+          - "$ref": "#/definitions/CsvParser"
+  JsonLineParser:
+    type: object
+    required:
+      - type
+    properties:
+      type:
+        type: string
+        enum: [JsonLineParser]
+      encoding:
+        type: string
+        default: utf-8
+  CsvParser:
+    type: object
+    required:
+      - type
+    properties:
+      type:
+        type: string
+        enum: [CsvParser]
+      encoding:
+        type: string
+        default: utf-8
+      delimiter:
+        type: string
+        default: ","
   AsyncJobStatusMap:
     description: Matches the api job status to Async Job Status.
     type: object

airbyte_cdk-6.13.0/airbyte_cdk/sources/declarative/decoders/__init__.py

@@ -0,0 +1,29 @@
+#
+# Copyright (c) 2023 Airbyte, Inc., all rights reserved.
+#
+
+from airbyte_cdk.sources.declarative.decoders.composite_raw_decoder import CompositeRawDecoder
+from airbyte_cdk.sources.declarative.decoders.decoder import Decoder
+from airbyte_cdk.sources.declarative.decoders.json_decoder import (
+    GzipJsonDecoder,
+    IterableDecoder,
+    JsonDecoder,
+    JsonlDecoder,
+)
+from airbyte_cdk.sources.declarative.decoders.noop_decoder import NoopDecoder
+from airbyte_cdk.sources.declarative.decoders.pagination_decoder_decorator import (
+    PaginationDecoderDecorator,
+)
+from airbyte_cdk.sources.declarative.decoders.xml_decoder import XmlDecoder
+
+__all__ = [
+    "Decoder",
+    "CompositeRawDecoder",
+    "JsonDecoder",
+    "JsonlDecoder",
+    "IterableDecoder",
+    "GzipJsonDecoder",
+    "NoopDecoder",
+    "PaginationDecoderDecorator",
+    "XmlDecoder",
+]

airbyte_cdk-6.13.0/airbyte_cdk/sources/declarative/decoders/composite_raw_decoder.py

@@ -0,0 +1,97 @@
+import csv
+import gzip
+import json
+import logging
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from io import BufferedIOBase, TextIOWrapper
+from typing import Any, Generator, MutableMapping, Optional
+
+import requests
+
+from airbyte_cdk.sources.declarative.decoders.decoder import Decoder
+
+logger = logging.getLogger("airbyte")
+
+
+@dataclass
+class Parser(ABC):
+    @abstractmethod
+    def parse(
+        self,
+        data: BufferedIOBase,
+    ) -> Generator[MutableMapping[str, Any], None, None]:
+        """
+        Parse data and yield dictionaries.
+        """
+        pass
+
+
+@dataclass
+class GzipParser(Parser):
+    inner_parser: Parser
+
+    def parse(
+        self,
+        data: BufferedIOBase,
+    ) -> Generator[MutableMapping[str, Any], None, None]:
+        """
+        Decompress gzipped bytes and pass decompressed data to the inner parser.
+        """
+        with gzip.GzipFile(fileobj=data, mode="rb") as gzipobj:
+            yield from self.inner_parser.parse(gzipobj)
+
+
+@dataclass
+class JsonLineParser(Parser):
+    encoding: Optional[str] = "utf-8"
+
+    def parse(
+        self,
+        data: BufferedIOBase,
+    ) -> Generator[MutableMapping[str, Any], None, None]:
+        for line in data:
+            try:
+                yield json.loads(line.decode(encoding=self.encoding or "utf-8"))
+            except json.JSONDecodeError as e:
+                logger.warning(f"Cannot decode/parse line {line!r} as JSON, error: {e}")
+
+
+@dataclass
+class CsvParser(Parser):
+    # TODO: migrate implementation to re-use file-base classes
+    encoding: Optional[str] = "utf-8"
+    delimiter: Optional[str] = ","
+
+    def parse(
+        self,
+        data: BufferedIOBase,
+    ) -> Generator[MutableMapping[str, Any], None, None]:
+        """
+        Parse CSV data from decompressed bytes.
+        """
+        text_data = TextIOWrapper(data, encoding=self.encoding)  # type: ignore
+        reader = csv.DictReader(text_data, delimiter=self.delimiter or ",")
+        yield from reader
+
+
+@dataclass
+class CompositeRawDecoder(Decoder):
+    """
+    Decoder strategy to transform a requests.Response into a Generator[MutableMapping[str, Any], None, None]
+    passed response.raw to parser(s).
+    Note: response.raw is not decoded/decompressed by default.
+    parsers should be instantiated recursively.
+    Example:
+    composite_raw_decoder = CompositeRawDecoder(parser=GzipParser(inner_parser=JsonLineParser(encoding="iso-8859-1")))
+    """
+
+    parser: Parser
+
+    def is_stream_response(self) -> bool:
+        return True
+
+    def decode(
+        self, response: requests.Response
+    ) -> Generator[MutableMapping[str, Any], None, None]:
+        yield from self.parser.parse(data=response.raw)  # type: ignore[arg-type]

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/sources/declarative/extractors/__init__.py

@@ -6,6 +6,14 @@ from airbyte_cdk.sources.declarative.extractors.dpath_extractor import DpathExtr
 from airbyte_cdk.sources.declarative.extractors.http_selector import HttpSelector
 from airbyte_cdk.sources.declarative.extractors.record_filter import RecordFilter
 from airbyte_cdk.sources.declarative.extractors.record_selector import RecordSelector
-from airbyte_cdk.sources.declarative.extractors.response_to_file_extractor import ResponseToFileExtractor
+from airbyte_cdk.sources.declarative.extractors.response_to_file_extractor import (
+    ResponseToFileExtractor,
+)
 
-__all__ = ["HttpSelector", "DpathExtractor", "RecordFilter", "RecordSelector", "ResponseToFileExtractor"]
+__all__ = [
+    "HttpSelector",
+    "DpathExtractor",
+    "RecordFilter",
+    "RecordSelector",
+    "ResponseToFileExtractor",
+]

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/sources/declarative/incremental/__init__.py

@@ -4,9 +4,16 @@
 
 from airbyte_cdk.sources.declarative.incremental.datetime_based_cursor import DatetimeBasedCursor
 from airbyte_cdk.sources.declarative.incremental.declarative_cursor import DeclarativeCursor
-from airbyte_cdk.sources.declarative.incremental.global_substream_cursor import GlobalSubstreamCursor
-from airbyte_cdk.sources.declarative.incremental.per_partition_cursor import CursorFactory, PerPartitionCursor
-from airbyte_cdk.sources.declarative.incremental.per_partition_with_global import PerPartitionWithGlobalCursor
+from airbyte_cdk.sources.declarative.incremental.global_substream_cursor import (
+    GlobalSubstreamCursor,
+)
+from airbyte_cdk.sources.declarative.incremental.per_partition_cursor import (
+    CursorFactory,
+    PerPartitionCursor,
+)
+from airbyte_cdk.sources.declarative.incremental.per_partition_with_global import (
+    PerPartitionWithGlobalCursor,
+)
 from airbyte_cdk.sources.declarative.incremental.resumable_full_refresh_cursor import (
     ChildPartitionResumableFullRefreshCursor,
     ResumableFullRefreshCursor,

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -1125,6 +1125,17 @@ class LegacySessionTokenAuthenticator(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class JsonLineParser(BaseModel):
+    type: Literal["JsonLineParser"]
+    encoding: Optional[str] = "utf-8"
+
+
+class CsvParser(BaseModel):
+    type: Literal["CsvParser"]
+    encoding: Optional[str] = "utf-8"
+    delimiter: Optional[str] = ","
+
+
 class AsyncJobStatusMap(BaseModel):
     type: Optional[Literal["AsyncJobStatusMap"]] = None
     running: List[str]
@@ -1208,6 +1219,8 @@ class ComponentMappingDefinition(BaseModel):
             "{{ components_values['updates'] }}",
             "{{ components_values['MetaData']['LastUpdatedTime'] }}",
             "{{ config['segment_id'] }}",
+            "{{ stream_slice['parent_id'] }}",
+            "{{ stream_slice['extra_fields']['name'] }}",
         ],
         title="Value",
     )
@@ -1504,6 +1517,11 @@ class RecordSelector(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class GzipParser(BaseModel):
+    type: Literal["GzipParser"]
+    inner_parser: Union[JsonLineParser, CsvParser]
+
+
 class Spec(BaseModel):
     type: Literal["Spec"]
     connection_specification: Dict[str, Any] = Field(
@@ -1534,6 +1552,11 @@ class CompositeErrorHandler(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
+class CompositeRawDecoder(BaseModel):
+    type: Literal["CompositeRawDecoder"]
+    parser: Union[GzipParser, JsonLineParser, CsvParser]
+
+
 class DeclarativeSource1(BaseModel):
     class Config:
         extra = Extra.forbid
@@ -1936,6 +1959,7 @@ class SimpleRetriever(BaseModel):
             IterableDecoder,
             XmlDecoder,
             GzipJsonDecoder,
+            CompositeRawDecoder,
         ]
     ] = Field(
         None,

{airbyte_cdk-6.12.4 → airbyte_cdk-6.13.0}/airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py

@@ -67,6 +67,12 @@ from airbyte_cdk.sources.declarative.decoders import (
     PaginationDecoderDecorator,
     XmlDecoder,
 )
+from airbyte_cdk.sources.declarative.decoders.composite_raw_decoder import (
+    CompositeRawDecoder,
+    CsvParser,
+    GzipParser,
+    JsonLineParser,
+)
 from airbyte_cdk.sources.declarative.extractors import (
     DpathExtractor,
     RecordFilter,
@@ -125,6 +131,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     CompositeErrorHandler as CompositeErrorHandlerModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    CompositeRawDecoder as CompositeRawDecoderModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     ConcurrencyLevel as ConcurrencyLevelModel,
 )
@@ -134,6 +143,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     ConstantBackoffStrategy as ConstantBackoffStrategyModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    CsvParser as CsvParserModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     CursorPagination as CursorPaginationModel,
 )
@@ -203,6 +215,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     GzipJsonDecoder as GzipJsonDecoderModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    GzipParser as GzipParserModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     HttpComponentsResolver as HttpComponentsResolverModel,
 )
@@ -227,6 +242,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     JsonlDecoder as JsonlDecoderModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    JsonLineParser as JsonLineParserModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     JwtAuthenticator as JwtAuthenticatorModel,
 )
@@ -455,6 +473,7 @@ class ModelToComponentFactory:
             BearerAuthenticatorModel: self.create_bearer_authenticator,
             CheckStreamModel: self.create_check_stream,
             CompositeErrorHandlerModel: self.create_composite_error_handler,
+            CompositeRawDecoderModel: self.create_composite_raw_decoder,
             ConcurrencyLevelModel: self.create_concurrency_level,
             ConstantBackoffStrategyModel: self.create_constant_backoff_strategy,
             CursorPaginationModel: self.create_cursor_pagination,
@@ -485,7 +504,9 @@ class ModelToComponentFactory:
             InlineSchemaLoaderModel: self.create_inline_schema_loader,
             JsonDecoderModel: self.create_json_decoder,
             JsonlDecoderModel: self.create_jsonl_decoder,
+            JsonLineParserModel: self.create_json_line_parser,
             GzipJsonDecoderModel: self.create_gzipjson_decoder,
+            GzipParserModel: self.create_gzip_parser,
             KeysToLowerModel: self.create_keys_to_lower_transformation,
             KeysToSnakeCaseModel: self.create_keys_to_snake_transformation,
             FlattenFieldsModel: self.create_flatten_fields,
@@ -1701,6 +1722,12 @@ class ModelToComponentFactory:
     ) -> JsonlDecoder:
         return JsonlDecoder(parameters={})
 
+    @staticmethod
+    def create_json_line_parser(
+        model: JsonLineParserModel, config: Config, **kwargs: Any
+    ) -> JsonLineParser:
+        return JsonLineParser(encoding=model.encoding)
+
     @staticmethod
     def create_iterable_decoder(
         model: IterableDecoderModel, config: Config, **kwargs: Any
@@ -1717,6 +1744,22 @@ class ModelToComponentFactory:
     ) -> GzipJsonDecoder:
         return GzipJsonDecoder(parameters={}, encoding=model.encoding)
 
+    def create_gzip_parser(
+        self, model: GzipParserModel, config: Config, **kwargs: Any
+    ) -> GzipParser:
+        inner_parser = self._create_component_from_model(model=model.inner_parser, config=config)
+        return GzipParser(inner_parser=inner_parser)
+
+    @staticmethod
+    def create_csv_parser(model: CsvParserModel, config: Config, **kwargs: Any) -> CsvParser:
+        return CsvParser(encoding=model.encoding, delimiter=model.delimiter)
+
+    def create_composite_raw_decoder(
+        self, model: CompositeRawDecoderModel, config: Config, **kwargs: Any
+    ) -> CompositeRawDecoder:
+        parser = self._create_component_from_model(model=model.parser, config=config)
+        return CompositeRawDecoder(parser=parser)
+
     @staticmethod
     def create_json_file_schema_loader(
         model: JsonFileSchemaLoaderModel, config: Config, **kwargs: Any