feat(taps): Implement reference paginators

docs/classes/singer_sdk.pagination.BaseAPIPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.BaseAPIPaginator
+======================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: BaseAPIPaginator
+    :members:

docs/classes/singer_sdk.pagination.BaseHATEOASPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.BaseHATEOASPaginator
+==========================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: BaseHATEOASPaginator
+    :members:

docs/classes/singer_sdk.pagination.BaseOffsetPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.BaseOffsetPaginator
+=========================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: BaseOffsetPaginator
+    :members:

docs/classes/singer_sdk.pagination.BasePageNumberPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.BasePageNumberPaginator
+=============================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: BasePageNumberPaginator
+    :members:

docs/classes/singer_sdk.pagination.HeaderLinkPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.HeaderLinkPaginator
+=========================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: HeaderLinkPaginator
+    :members:

docs/classes/singer_sdk.pagination.JSONPathPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.JSONPathPaginator
+=======================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: JSONPathPaginator
+    :members:

docs/classes/singer_sdk.pagination.LegacyPaginatedStreamProtocol.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.LegacyPaginatedStreamProtocol
+===================================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: LegacyPaginatedStreamProtocol
+    :members:

docs/classes/singer_sdk.pagination.LegacyStreamPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.LegacyStreamPaginator
+===========================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: LegacyStreamPaginator
+    :members:

docs/classes/singer_sdk.pagination.SimpleHeaderPaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.SimpleHeaderPaginator
+===========================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: SimpleHeaderPaginator
+    :members:

docs/classes/singer_sdk.pagination.SinglePagePaginator.rst

@@ -0,0 +1,7 @@
+singer_sdk.pagination.SinglePagePaginator
+=========================================
+
+.. currentmodule:: singer_sdk.pagination
+
+.. autoclass:: SinglePagePaginator
+    :members:

docs/porting.md

@@ -103,10 +103,82 @@ _Important: If you've gotten this far, this is a good time to commit your code b
 
 Pagination is generally unique for almost every API. There's no single method that solves for very different API's approach to pagination.
 
-Most likely you will use `get_next_page_token` to parse and return whatever the "next page" token is for your source, and you'll use `get_url_params` to define how to pass the "next page" token back to the API when asking for subsequent pages.
+Most likely you will use [get_new_paginator](singer_sdk.RESTStream.get_new_paginator) to instantiate a [pagination class](./classes/singer_sdk.pagination.BaseAPIPaginator) for your source, and you'll use `get_url_params` to define how to pass the "next page" token back to the API when asking for subsequent pages.
 
 When you think you have it right, run `poetry run tap-mysource` again, and debug until you are confident the result is including multiple pages back from the API.
 
+You can also add unit tests for your pagination implementation for additional confidence:
+
+```python
+from singer_sdk.pagination import BaseHATEOASPaginator, first
+
+
+class CustomHATEOASPaginator(BaseHATEOASPaginator):
+   """Paginator for HATEOAS APIs - or "Hypermedia as the Engine of Application State".
+
+   This paginator expects responses to have a key "next" with a value
+   like "https://api.com/link/to/next-item".
+   """"
+
+   def get_next_url(self, response: Response) -> str | None:
+      """Get a parsed HATEOAS link for the next, if the response has one."""
+
+      try:
+            return first(
+               extract_jsonpath("$.links[?(@.rel=='next')].href", response.json())
+            )
+      except StopIteration:
+            return None
+
+
+def test_paginator_custom_hateoas():
+   """Validate paginator that my custom paginator."""
+
+   resource_path = "/path/to/resource"
+   response = Response()
+   paginator = CustomHATEOASPaginator()
+   assert not paginator.finished
+   assert paginator.current_value is None
+   assert paginator.count == 0
+
+   response._content = json.dumps(
+      {
+         "links": [
+               {
+                  "rel": "next",
+                  "href": f"{resource_path}?page=2&limit=100",
+               }
+         ]
+      }
+   ).encode()
+   paginator.advance(response)
+   assert not paginator.finished
+   assert paginator.current_value.path == resource_path
+   assert paginator.current_value.query == "page=2&limit=100"
+   assert paginator.count == 1
+
+   response._content = json.dumps(
+      {
+         "links": [
+               {
+                  "rel": "next",
+                  "href": f"{resource_path}?page=3&limit=100",
+               }
+         ]
+      }
+   ).encode()
+   paginator.advance(response)
+   assert not paginator.finished
+   assert paginator.current_value.path == resource_path
+   assert paginator.current_value.query == "page=3&limit=100"
+   assert paginator.count == 2
+
+   response._content = json.dumps({"links": []}).encode()
+   paginator.advance(response)
+   assert paginator.finished
+   assert paginator.count == 3
+```
+
 Note: Depending on how well the API is designed, this could take 5 minutes or multiple hours. If you need help, sometimes [PostMan](https://postman.com) or [Thunder Client](https://marketplace.visualstudio.com/items?itemName=rangav.vscode-thunder-client) can be helpful in debugging the APIs specific quirks.
 
 ## Run pytest

docs/reference.rst

@@ -88,3 +88,22 @@ JSON Schema builder classes
     :template: module.rst
 
     typing
+
+
+Pagination
+----------
+
+.. autosummary::
+    :toctree: classes
+    :template: class.rst
+
+    pagination.BaseAPIPaginator
+    pagination.SinglePagePaginator
+    pagination.BaseHATEOASPaginator
+    pagination.HeaderLinkPaginator
+    pagination.JSONPathPaginator
+    pagination.SimpleHeaderPaginator
+    pagination.BasePageNumberPaginator
+    pagination.BaseOffsetPaginator
+    pagination.LegacyPaginatedStreamProtocol
+    pagination.LegacyStreamPaginator

samples/sample_tap_gitlab/gitlab_rest_streams.py

@@ -1,11 +1,12 @@
 """Sample tap stream test for tap-gitlab."""
 
-from pathlib import Path
-from typing import Any, Dict, List, Optional, cast
+from __future__ import annotations
 
-import requests
+from pathlib import Path
+from typing import Any, cast
 
 from singer_sdk.authenticators import SimpleAuthenticator
+from singer_sdk.pagination import SimpleHeaderPaginator
 from singer_sdk.streams.rest import RESTStream
 from singer_sdk.typing import (
     ArrayType,
@@ -21,7 +22,7 @@
 DEFAULT_URL_BASE = "https://gitlab.com/api/v4"
 
 
-class GitlabStream(RESTStream):
+class GitlabStream(RESTStream[str]):
     """Sample tap test for gitlab."""
 
     _LOG_REQUEST_METRIC_URLS = True
@@ -39,8 +40,8 @@ def authenticator(self) -> SimpleAuthenticator:
         )
 
     def get_url_params(
-        self, context: Optional[dict], next_page_token: Optional[Any]
-    ) -> Dict[str, Any]:
+        self, context: dict | None, next_page_token: str | None
+    ) -> dict[str, Any]:
         """Return a dictionary of values to be used in URL parameterization."""
         params: dict = {}
         if next_page_token:
@@ -50,21 +51,20 @@ def get_url_params(
             params["order_by"] = self.replication_key
         return params
 
-    def get_next_page_token(
-        self, response: requests.Response, previous_token: Optional[Any]
-    ) -> Optional[Any]:
-        """Return token for identifying next page or None if not applicable."""
-        next_page_token = response.headers.get("X-Next-Page", None)
-        if next_page_token:
-            self.logger.debug(f"Next page token retrieved: {next_page_token}")
-        return next_page_token
+    def get_new_paginator(self) -> SimpleHeaderPaginator:
+        """Return a new paginator for GitLab API endpoints.
+
+        Returns:
+            A new paginator.
+        """
+        return SimpleHeaderPaginator("X-Next-Page")
 
 
 class ProjectBasedStream(GitlabStream):
     """Base class for streams that are keys based on project ID."""
 
     @property
-    def partitions(self) -> List[dict]:
+    def partitions(self) -> list[dict]:
         """Return a list of partition key dicts (if applicable), otherwise None."""
         if "{project_id}" in self.path:
             return [
@@ -162,7 +162,7 @@ class EpicsStream(ProjectBasedStream):
 
     # schema_filepath = SCHEMAS_DIR / "epics.json"
 
-    def get_child_context(self, record: dict, context: Optional[dict]) -> dict:
+    def get_child_context(self, record: dict, context: dict | None) -> dict:
         """Perform post processing, including queuing up any child stream types."""
         # Ensure child state record(s) are created
         return {
@@ -183,8 +183,8 @@ class EpicIssuesStream(GitlabStream):
     parent_stream_type = EpicsStream  # Stream should wait for parents to complete.
 
     def get_url_params(
-        self, context: Optional[dict], next_page_token: Optional[Any]
-    ) -> Dict[str, Any]:
+        self, context: dict | None, next_page_token: str | None
+    ) -> dict[str, Any]:
         """Return a dictionary of values to be used in parameterization."""
         result = super().get_url_params(context, next_page_token)
         if not context or "epic_id" not in context: