fix: (CDK) (HttpRequester) - Make the HttpRequester.path optional (#370)

Author: Baz

airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -1794,7 +1794,6 @@ definitions:
     type: object
     required:
       - type
-      - path
       - url_base
     properties:
       type:
@@ -1806,9 +1805,18 @@ definitions:
         type: string
         interpolation_context:
           - config
+          - next_page_token
+          - stream_interval
+          - stream_partition
+          - stream_slice
+          - creation_response
+          - polling_response
+          - download_target
         examples:
           - "https://connect.squareup.com/v2"
-          - "{{ config['base_url'] or 'https://app.posthog.com'}}/api/"
+          - "{{ config['base_url'] or 'https://app.posthog.com'}}/api"
+          - "https://connect.squareup.com/v2/quotes/{{ stream_partition['id'] }}/quote_line_groups"
+          - "https://example.com/api/v1/resource/{{ next_page_token['id'] }}"
       path:
         title: URL Path
         description: Path the specific API endpoint that this stream represents. Do not put sensitive information (e.g. API tokens) into this field - Use the Authentication component for this.

airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -939,7 +939,7 @@ class MinMaxDatetime(BaseModel):
     )
     datetime_format: Optional[str] = Field(
         "",
-        description='Format of the datetime value. Defaults to "%Y-%m-%dT%H:%M:%S.%f%z" if left empty. Use placeholders starting with "%" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`, `000001`, ..., `999999`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (Sunday as first day) - `00`, `01`, ..., `53`\n  * **%W**: Week number of the year (Monday as first day) - `00`, `01`, ..., `53`\n  * **%c**: Date and time representation - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date representation - `08/16/1988`\n  * **%X**: Time representation - `21:30:00`\n  * **%%**: Literal \'%\' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n',
+        description='Format of the datetime value. Defaults to "%Y-%m-%dT%H:%M:%S.%f%z" if left empty. Use placeholders starting with "%" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`, `000001`, ..., `999999`\n  * **%_ms**: Millisecond (zero-padded to 3 digits) - `000`, `001`, ..., `999`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (Sunday as first day) - `00`, `01`, ..., `53`\n  * **%W**: Week number of the year (Monday as first day) - `00`, `01`, ..., `53`\n  * **%c**: Date and time representation - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date representation - `08/16/1988`\n  * **%X**: Time representation - `21:30:00`\n  * **%%**: Literal \'%\' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n',
         examples=["%Y-%m-%dT%H:%M:%S.%f%z", "%Y-%m-%d", "%s"],
         title="Datetime Format",
     )
@@ -1545,7 +1545,7 @@ class DatetimeBasedCursor(BaseModel):
     )
     datetime_format: str = Field(
         ...,
-        description="The datetime format used to format the datetime values that are sent in outgoing requests to the API. Use placeholders starting with \"%\" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp (milliseconds) - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (starting Sunday) - `00`, ..., `53`\n  * **%W**: Week number of the year (starting Monday) - `00`, ..., `53`\n  * **%c**: Date and time - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date standard format - `08/16/1988`\n  * **%X**: Time standard format - `21:30:00`\n  * **%%**: Literal '%' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n",
+        description="The datetime format used to format the datetime values that are sent in outgoing requests to the API. Use placeholders starting with \"%\" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp (milliseconds) - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`\n  * **%_ms**: Millisecond (zero-padded to 3 digits) - `000`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (starting Sunday) - `00`, ..., `53`\n  * **%W**: Week number of the year (starting Monday) - `00`, ..., `53`\n  * **%c**: Date and time - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date standard format - `08/16/1988`\n  * **%X**: Time standard format - `21:30:00`\n  * **%%**: Literal '%' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n",
         examples=["%Y-%m-%dT%H:%M:%S.%f%z", "%Y-%m-%d", "%s", "%ms", "%s_as_float"],
         title="Outgoing Datetime Format",
     )
@@ -2072,12 +2072,14 @@ class HttpRequester(BaseModel):
         description="Base URL of the API source. Do not put sensitive information (e.g. API tokens) into this field - Use the Authentication component for this.",
         examples=[
             "https://connect.squareup.com/v2",
-            "{{ config['base_url'] or 'https://app.posthog.com'}}/api/",
+            "{{ config['base_url'] or 'https://app.posthog.com'}}/api",
+            "https://connect.squareup.com/v2/quotes/{{ stream_partition['id'] }}/quote_line_groups",
+            "https://example.com/api/v1/resource/{{ next_page_token['id'] }}",
         ],
         title="API Base URL",
     )
-    path: str = Field(
-        ...,
+    path: Optional[str] = Field(
+        None,
         description="Path the specific API endpoint that this stream represents. Do not put sensitive information (e.g. API tokens) into this field - Use the Authentication component for this.",
         examples=[
             "/products",

airbyte_cdk/sources/declarative/requesters/http_requester.py

@@ -25,8 +25,8 @@
 from airbyte_cdk.sources.streams.call_rate import APIBudget
 from airbyte_cdk.sources.streams.http import HttpClient
 from airbyte_cdk.sources.streams.http.error_handlers import ErrorHandler
-from airbyte_cdk.sources.types import Config, StreamSlice, StreamState
-from airbyte_cdk.utils.mapping_helpers import combine_mappings
+from airbyte_cdk.sources.types import Config, EmptyString, StreamSlice, StreamState
+from airbyte_cdk.utils.mapping_helpers import combine_mappings, get_interpolation_context
 
 
 @dataclass
@@ -49,9 +49,10 @@ class HttpRequester(Requester):
 
     name: str
     url_base: Union[InterpolatedString, str]
-    path: Union[InterpolatedString, str]
     config: Config
     parameters: InitVar[Mapping[str, Any]]
+
+    path: Optional[Union[InterpolatedString, str]] = None
     authenticator: Optional[DeclarativeAuthenticator] = None
     http_method: Union[str, HttpMethod] = HttpMethod.GET
     request_options_provider: Optional[InterpolatedRequestOptionsProvider] = None
@@ -66,7 +67,9 @@ class HttpRequester(Requester):
 
     def __post_init__(self, parameters: Mapping[str, Any]) -> None:
         self._url_base = InterpolatedString.create(self.url_base, parameters=parameters)
-        self._path = InterpolatedString.create(self.path, parameters=parameters)
+        self._path = InterpolatedString.create(
+            self.path if self.path else EmptyString, parameters=parameters
+        )
         if self.request_options_provider is None:
             self._request_options_provider = InterpolatedRequestOptionsProvider(
                 config=self.config, parameters=parameters
@@ -112,27 +115,33 @@ def exit_on_rate_limit(self, value: bool) -> None:
     def get_authenticator(self) -> DeclarativeAuthenticator:
         return self._authenticator
 
-    def get_url_base(self) -> str:
-        return os.path.join(self._url_base.eval(self.config), "")
+    def get_url_base(
+        self,
+        *,
+        stream_state: Optional[StreamState] = None,
+        stream_slice: Optional[StreamSlice] = None,
+        next_page_token: Optional[Mapping[str, Any]] = None,
+    ) -> str:
+        interpolation_context = get_interpolation_context(
+            stream_state=stream_state,
+            stream_slice=stream_slice,
+            next_page_token=next_page_token,
+        )
+        return os.path.join(self._url_base.eval(self.config, **interpolation_context), EmptyString)
 
     def get_path(
         self,
         *,
-        stream_state: Optional[StreamState],
-        stream_slice: Optional[StreamSlice],
-        next_page_token: Optional[Mapping[str, Any]],
+        stream_state: Optional[StreamState] = None,
+        stream_slice: Optional[StreamSlice] = None,
+        next_page_token: Optional[Mapping[str, Any]] = None,
     ) -> str:
-        kwargs = {
-            "stream_slice": stream_slice,
-            "next_page_token": next_page_token,
-            # update the interpolation context with extra fields, if passed.
-            **(
-                stream_slice.extra_fields
-                if stream_slice is not None and hasattr(stream_slice, "extra_fields")
-                else {}
-            ),
-        }
-        path = str(self._path.eval(self.config, **kwargs))
+        interpolation_context = get_interpolation_context(
+            stream_state=stream_state,
+            stream_slice=stream_slice,
+            next_page_token=next_page_token,
+        )
+        path = str(self._path.eval(self.config, **interpolation_context))
         return path.lstrip("/")
 
     def get_method(self) -> HttpMethod:
@@ -330,7 +339,20 @@ def _request_body_json(
 
     @classmethod
     def _join_url(cls, url_base: str, path: str) -> str:
-        return urljoin(url_base, path)
+        """
+        Joins a base URL with a given path and returns the resulting URL with any trailing slash removed.
+
+        This method ensures that there are no duplicate slashes when concatenating the base URL and the path,
+        which is useful when the full URL is provided from an interpolation context.
+
+        Args:
+            url_base (str): The base URL to which the path will be appended.
+            path (str): The path to join with the base URL.
+
+        Returns:
+            str: The concatenated URL with the trailing slash (if any) removed.
+        """
+        return urljoin(url_base, path).rstrip("/")
 
     def send_request(
         self,
@@ -347,7 +369,11 @@ def send_request(
         request, response = self._http_client.send_request(
             http_method=self.get_method().value,
             url=self._join_url(
-                self.get_url_base(),
+                self.get_url_base(
+                    stream_state=stream_state,
+                    stream_slice=stream_slice,
+                    next_page_token=next_page_token,
+                ),
                 path
                 or self.get_path(
                     stream_state=stream_state,

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

@@ -25,6 +25,7 @@
 from airbyte_cdk.sources.types import Config, Record, StreamSlice, StreamState
 from airbyte_cdk.utils.mapping_helpers import (
     _validate_component_request_option_paths,
+    get_interpolation_context,
 )
 
 
@@ -150,11 +151,22 @@ def next_page_token(
         else:
             return None
 
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
+    def path(
+        self,
+        next_page_token: Optional[Mapping[str, Any]],
+        stream_state: Optional[Mapping[str, Any]] = None,
+        stream_slice: Optional[StreamSlice] = None,
+    ) -> 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):
+            # make additional interpolation context
+            interpolation_context = get_interpolation_context(
+                stream_state=stream_state,
+                stream_slice=stream_slice,
+                next_page_token=next_page_token,
+            )
             # 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(token).replace(self.url_base.eval(self.config, **interpolation_context), "")  # type: ignore # url_base is casted to a InterpolatedString in __post_init__
         else:
             return None
 
@@ -258,8 +270,17 @@ def next_page_token(
             response, last_page_size, last_record, last_page_token_value
         )
 
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
-        return self._decorated.path(next_page_token)
+    def path(
+        self,
+        next_page_token: Optional[Mapping[str, Any]],
+        stream_state: Optional[Mapping[str, Any]] = None,
+        stream_slice: Optional[StreamSlice] = None,
+    ) -> Optional[str]:
+        return self._decorated.path(
+            next_page_token=next_page_token,
+            stream_state=stream_state,
+            stream_slice=stream_slice,
+        )
 
     def get_request_params(
         self,

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

@@ -19,7 +19,12 @@ class NoPagination(Paginator):
 
     parameters: InitVar[Mapping[str, Any]]
 
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
+    def path(
+        self,
+        next_page_token: Optional[Mapping[str, Any]],
+        stream_state: Optional[Mapping[str, Any]] = None,
+        stream_slice: Optional[StreamSlice] = None,
+    ) -> Optional[str]:
         return None
 
     def get_request_params(

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

@@ -11,7 +11,7 @@
 from airbyte_cdk.sources.declarative.requesters.request_options.request_options_provider import (
     RequestOptionsProvider,
 )
-from airbyte_cdk.sources.types import Record
+from airbyte_cdk.sources.types import Record, StreamSlice
 
 
 @dataclass
@@ -49,7 +49,12 @@ def next_page_token(
         pass
 
     @abstractmethod
-    def path(self, next_page_token: Optional[Mapping[str, Any]]) -> Optional[str]:
+    def path(
+        self,
+        next_page_token: Optional[Mapping[str, Any]],
+        stream_state: Optional[Mapping[str, Any]] = None,
+        stream_slice: Optional[StreamSlice] = None,
+    ) -> Optional[str]:
         """
         Returns the URL path to hit to fetch the next page of records
 

airbyte_cdk/sources/declarative/requesters/requester.py

@@ -35,7 +35,13 @@ def get_authenticator(self) -> DeclarativeAuthenticator:
         pass
 
     @abstractmethod
-    def get_url_base(self) -> str:
+    def get_url_base(
+        self,
+        *,
+        stream_state: Optional[StreamState],
+        stream_slice: Optional[StreamSlice],
+        next_page_token: Optional[Mapping[str, Any]],
+    ) -> str:
         """
         :return: URL base for the  API endpoint e.g: if you wanted to hit https://myapi.com/v1/some_entity then this should return "https://myapi.com/v1/"
         """