[low-code-connectors] Replace JelloExtractor with DpathExtractor (#15514

)

* Handle extracting no records from root

* handle missing keys

* record extractor interface

* dpath extractor

* docstring

* handle extract root array

* Update airbyte-cdk/python/airbyte_cdk/sources/declarative/extractors/jello.py

Co-authored-by: Sherif A. Nada <snadalive@gmail.com>

* Update airbyte-cdk/python/airbyte_cdk/sources/declarative/extractors/record_selector.py

Co-authored-by: Sherif A. Nada <snadalive@gmail.com>

* update docstring

* respect extractor interface

* edge case handling

* document

* use dpath by default

* delete jello extractor

* bump cdk version

* delete jello dependency

* Update reference docs templates

* update template

Co-authored-by: Sherif A. Nada <snadalive@gmail.com>

airbyte-cdk/python/CHANGELOG.md

@@ -1,5 +1,8 @@
 # Changelog
 
+## 0.1.74
+- Replace JelloRecordExtractor with DpathRecordExtractor
+
 ## 0.1.73
 - Bugfix: Fix bug in DatetimeStreamSlicer's parsing method
 

airbyte-cdk/python/airbyte_cdk/sources/declarative/extractors/__init__.py

@@ -2,9 +2,9 @@
 # Copyright (c) 2022 Airbyte, Inc., all rights reserved.
 #
 
+from airbyte_cdk.sources.declarative.extractors.dpath_extractor import DpathExtractor
 from airbyte_cdk.sources.declarative.extractors.http_selector import HttpSelector
-from airbyte_cdk.sources.declarative.extractors.jello import JelloExtractor
 from airbyte_cdk.sources.declarative.extractors.record_filter import RecordFilter
 from airbyte_cdk.sources.declarative.extractors.record_selector import RecordSelector
 
-__all__ = ["HttpSelector", "JelloExtractor", "RecordFilter", "RecordSelector"]
+__all__ = ["HttpSelector", "DpathExtractor", "RecordFilter", "RecordSelector"]

airbyte-cdk/python/airbyte_cdk/sources/declarative/extractors/dpath_extractor.py

@@ -0,0 +1,79 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+from dataclasses import InitVar, dataclass
+from typing import Any, List, Mapping, Union
+
+import dpath.util
+import requests
+from airbyte_cdk.sources.declarative.decoders.decoder import Decoder
+from airbyte_cdk.sources.declarative.decoders.json_decoder import JsonDecoder
+from airbyte_cdk.sources.declarative.extractors.record_extractor import RecordExtractor
+from airbyte_cdk.sources.declarative.interpolation.interpolated_string import InterpolatedString
+from airbyte_cdk.sources.declarative.types import Config, Record
+from dataclasses_jsonschema import JsonSchemaMixin
+
+
+@dataclass
+class DpathExtractor(RecordExtractor, JsonSchemaMixin):
+    """
+    Record extractor that searches a decoded response over a path defined as an array of fields.
+
+    If the field pointer points to an array, that array is returned.
+    If the field pointer points to an object, that object is returned wrapped as an array.
+    If the field pointer points to an empty object, an empty array is returned.
+    If the field pointer points to a non-existing path, an empty array is returned.
+
+    Examples of instantiating this transform:
+    ```
+      extractor:
+        type: DpathExtractor
+        field_pointer:
+          - "root"
+          - "data"
+    ```
+
+    ```
+      extractor:
+        type: DpathExtractor
+        field_pointer:
+          - "root"
+          - "{{ options['field'] }}"
+    ```
+
+    ```
+      extractor:
+        type: DpathExtractor
+        field_pointer: []
+    ```
+
+    Attributes:
+        transform (Union[InterpolatedString, str]): Pointer to the field that should be extracted
+        config (Config): The user-provided configuration as specified by the source's spec
+        decoder (Decoder): The decoder responsible to transfom the response in a Mapping
+    """
+
+    field_pointer: List[Union[InterpolatedString, str]]
+    config: Config
+    options: InitVar[Mapping[str, Any]]
+    decoder: Decoder = JsonDecoder(options={})
+
+    def __post_init__(self, options: Mapping[str, Any]):
+        for pointer_index in range(len(self.field_pointer)):
+            if isinstance(self.field_pointer[pointer_index], str):
+                self.field_pointer[pointer_index] = InterpolatedString.create(self.field_pointer[pointer_index], options=options)
+
+    def extract_records(self, response: requests.Response) -> List[Record]:
+        response_body = self.decoder.decode(response)
+        if len(self.field_pointer) == 0:
+            extracted = response_body
+        else:
+            pointer = [pointer.eval(self.config) for pointer in self.field_pointer]
+            extracted = dpath.util.get(response_body, pointer, default=[])
+        if isinstance(extracted, list):
+            return extracted
+        elif extracted:
+            return [extracted]
+        else:
+            return []

airbyte-cdk/python/airbyte_cdk/sources/declarative/extractors/record_extractor.py

@@ -0,0 +1,29 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from typing import List
+
+import requests
+from airbyte_cdk.sources.declarative.types import Record
+
+
+@dataclass
+class RecordExtractor(ABC):
+    """
+    Responsible for translating an HTTP response into a list of records by extracting records from the response.
+    """
+
+    @abstractmethod
+    def extract_records(
+        self,
+        response: requests.Response,
+    ) -> List[Record]:
+        """
+        Selects records from the response
+        :param response: The response to extract the records from
+        :return: List of Records extracted from the response
+        """
+        pass

airbyte-cdk/python/airbyte_cdk/sources/declarative/extractors/record_selector.py

@@ -7,7 +7,7 @@
 
 import requests
 from airbyte_cdk.sources.declarative.extractors.http_selector import HttpSelector
-from airbyte_cdk.sources.declarative.extractors.jello import JelloExtractor
+from airbyte_cdk.sources.declarative.extractors.record_extractor import RecordExtractor
 from airbyte_cdk.sources.declarative.extractors.record_filter import RecordFilter
 from airbyte_cdk.sources.declarative.types import Record, StreamSlice, StreamState
 from dataclasses_jsonschema import JsonSchemaMixin
@@ -20,11 +20,11 @@ class RecordSelector(HttpSelector, JsonSchemaMixin):
     records based on a heuristic.
 
     Attributes:
-        extractor (JelloExtractor): The record extractor responsible for extracting records from a response
+        extractor (RecordExtractor): The record extractor responsible for extracting records from a response
         record_filter (RecordFilter): The record filter responsible for filtering extracted records
     """
 
-    extractor: JelloExtractor
+    extractor: RecordExtractor
     options: InitVar[Mapping[str, Any]]
     record_filter: RecordFilter = None
 
@@ -39,9 +39,6 @@ def select_records(
         next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> List[Record]:
         all_records = self.extractor.extract_records(response)
-        # Some APIs don't wrap single records in a list
-        if not isinstance(all_records, list):
-            all_records = [all_records]
         if self.record_filter:
             return self.record_filter.filter_records(
                 all_records, stream_state=stream_state, stream_slice=stream_slice, next_page_token=next_page_token

airbyte-cdk/python/airbyte_cdk/sources/declarative/parsers/class_types_registry.py

@@ -7,7 +7,7 @@
 from airbyte_cdk.sources.declarative.auth.token import ApiKeyAuthenticator, BasicHttpAuthenticator, BearerAuthenticator
 from airbyte_cdk.sources.declarative.datetime.min_max_datetime import MinMaxDatetime
 from airbyte_cdk.sources.declarative.declarative_stream import DeclarativeStream
-from airbyte_cdk.sources.declarative.extractors.jello import JelloExtractor
+from airbyte_cdk.sources.declarative.extractors.dpath_extractor import DpathExtractor
 from airbyte_cdk.sources.declarative.extractors.record_selector import RecordSelector
 from airbyte_cdk.sources.declarative.interpolation.interpolated_boolean import InterpolatedBoolean
 from airbyte_cdk.sources.declarative.interpolation.interpolated_string import InterpolatedString
@@ -46,11 +46,11 @@
     "DatetimeStreamSlicer": DatetimeStreamSlicer,
     "DeclarativeStream": DeclarativeStream,
     "DefaultErrorHandler": DefaultErrorHandler,
+    "DpathExtractor": DpathExtractor,
     "ExponentialBackoffStrategy": ExponentialBackoffStrategy,
     "HttpRequester": HttpRequester,
     "InterpolatedBoolean": InterpolatedBoolean,
     "InterpolatedString": InterpolatedString,
-    "JelloExtractor": JelloExtractor,
     "JsonSchema": JsonSchema,
     "LimitPaginator": LimitPaginator,
     "ListStreamSlicer": ListStreamSlicer,

airbyte-cdk/python/airbyte_cdk/sources/declarative/parsers/default_implementation_registry.py

@@ -10,7 +10,9 @@
 from airbyte_cdk.sources.declarative.declarative_stream import DeclarativeStream
 from airbyte_cdk.sources.declarative.decoders.decoder import Decoder
 from airbyte_cdk.sources.declarative.decoders.json_decoder import JsonDecoder
+from airbyte_cdk.sources.declarative.extractors.dpath_extractor import DpathExtractor
 from airbyte_cdk.sources.declarative.extractors.http_selector import HttpSelector
+from airbyte_cdk.sources.declarative.extractors.record_extractor import RecordExtractor
 from airbyte_cdk.sources.declarative.extractors.record_selector import RecordSelector
 from airbyte_cdk.sources.declarative.interpolation.interpolated_boolean import InterpolatedBoolean
 from airbyte_cdk.sources.declarative.interpolation.interpolated_string import InterpolatedString
@@ -50,11 +52,12 @@
     InterpolatedString: InterpolatedString,
     MinMaxDatetime: MinMaxDatetime,
     Paginator: NoPagination,
+    ParentStreamConfig: ParentStreamConfig,
+    RecordExtractor: DpathExtractor,
     RequestOption: RequestOption,
     RequestOptionsProvider: InterpolatedRequestOptionsProvider,
     Requester: HttpRequester,
     Retriever: SimpleRetriever,
-    ParentStreamConfig: ParentStreamConfig,
     SchemaLoader: JsonSchema,
     Stream: DeclarativeStream,
     StreamSlicer: SingleSlice,

airbyte-cdk/python/reference_docs/_source/api/airbyte_cdk.sources.declarative.datetime.rst

@@ -2,6 +2,14 @@
 Submodules
 ----------
 
+airbyte\_cdk.sources.declarative.datetime.datetime\_parser module
+-----------------------------------------------------------------
+
+.. automodule:: airbyte_cdk.sources.declarative.datetime.datetime_parser
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 airbyte\_cdk.sources.declarative.datetime.min\_max\_datetime module
 -------------------------------------------------------------------
 

airbyte-cdk/python/reference_docs/_source/api/airbyte_cdk.sources.declarative.extractors.rst

@@ -2,6 +2,14 @@
 Submodules
 ----------
 
+airbyte\_cdk.sources.declarative.extractors.dpath\_extractor module
+-------------------------------------------------------------------
+
+.. automodule:: airbyte_cdk.sources.declarative.extractors.dpath_extractor
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 airbyte\_cdk.sources.declarative.extractors.http\_selector module
 -----------------------------------------------------------------
 
@@ -10,10 +18,10 @@ airbyte\_cdk.sources.declarative.extractors.http\_selector module
    :undoc-members:
    :show-inheritance:
 
-airbyte\_cdk.sources.declarative.extractors.jello module
---------------------------------------------------------
+airbyte\_cdk.sources.declarative.extractors.record\_extractor module
+--------------------------------------------------------------------
 
-.. automodule:: airbyte_cdk.sources.declarative.extractors.jello
+.. automodule:: airbyte_cdk.sources.declarative.extractors.record_extractor
    :members:
    :undoc-members:
    :show-inheritance:

airbyte-cdk/python/reference_docs/_source/api/airbyte_cdk.sources.declarative.requesters.paginators.rst

@@ -26,14 +26,6 @@ airbyte\_cdk.sources.declarative.requesters.paginators.no\_pagination module
    :undoc-members:
    :show-inheritance:
 
-airbyte\_cdk.sources.declarative.requesters.paginators.pagination\_strategy module
-----------------------------------------------------------------------------------
-
-.. automodule:: airbyte_cdk.sources.declarative.requesters.paginators.pagination_strategy
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
 airbyte\_cdk.sources.declarative.requesters.paginators.paginator module
 -----------------------------------------------------------------------
 

airbyte-cdk/python/reference_docs/_source/api/airbyte_cdk.sources.declarative.requesters.paginators.strategies.rst

@@ -26,6 +26,14 @@ airbyte\_cdk.sources.declarative.requesters.paginators.strategies.page\_incremen
    :undoc-members:
    :show-inheritance:
 
+airbyte\_cdk.sources.declarative.requesters.paginators.strategies.pagination\_strategy module
+---------------------------------------------------------------------------------------------
+
+.. automodule:: airbyte_cdk.sources.declarative.requesters.paginators.strategies.pagination_strategy
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 Module contents
 ---------------
 

airbyte-cdk/python/reference_docs/_source/api/airbyte_cdk.sources.declarative.requesters.request_options.rst

@@ -2,6 +2,14 @@
 Submodules
 ----------
 
+airbyte\_cdk.sources.declarative.requesters.request\_options.interpolated\_request\_input\_provider module
+----------------------------------------------------------------------------------------------------------
+
+.. automodule:: airbyte_cdk.sources.declarative.requesters.request_options.interpolated_request_input_provider
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 airbyte\_cdk.sources.declarative.requesters.request\_options.interpolated\_request\_options\_provider module
 ------------------------------------------------------------------------------------------------------------
 

airbyte-cdk/python/reference_docs/_source/api/airbyte_cdk.sources.declarative.requesters.rst

@@ -20,14 +20,6 @@ airbyte\_cdk.sources.declarative.requesters.http\_requester module
    :undoc-members:
    :show-inheritance:
 
-airbyte\_cdk.sources.declarative.requesters.interpolated\_request\_input\_provider module
------------------------------------------------------------------------------------------
-
-.. automodule:: airbyte_cdk.sources.declarative.requesters.interpolated_request_input_provider
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
 airbyte\_cdk.sources.declarative.requesters.request\_option module
 ------------------------------------------------------------------
 

airbyte-cdk/python/reference_docs/_source/api/airbyte_cdk.sources.declarative.rst

@@ -45,10 +45,10 @@ airbyte\_cdk.sources.declarative.declarative\_stream module
    :undoc-members:
    :show-inheritance:
 
-airbyte\_cdk.sources.declarative.read\_exception module
--------------------------------------------------------
+airbyte\_cdk.sources.declarative.exceptions module
+--------------------------------------------------
 
-.. automodule:: airbyte_cdk.sources.declarative.read_exception
+.. automodule:: airbyte_cdk.sources.declarative.exceptions
    :members:
    :undoc-members:
    :show-inheritance:

airbyte-cdk/python/setup.py

@@ -15,7 +15,7 @@
 
 setup(
     name="airbyte-cdk",
-    version="0.1.73",
+    version="0.1.74",
     description="A framework for writing Airbyte Connectors.",
     long_description=README,
     long_description_content_type="text/markdown",
@@ -55,7 +55,6 @@
         "vcrpy",
         "Deprecated~=1.2",
         "Jinja2~=3.1.2",
-        "jello~=1.5.2",
     ],
     python_requires=">=3.9",
     extras_require={