Merge branch 'MeltanoLabs:main' into diffs-stream-fix

Author: angelachenn

.github/CODEOWNERS

@@ -0,0 +1,2 @@
+# Global owner
+*       @MeltanoLabs/tap-github

.github/dependabot.yml

@@ -10,8 +10,6 @@ updates:
     schedule:
       interval: weekly
       day: monday
-    reviewers:
-      - "edgarrmondragon"
     versioning-strategy: increase-if-necessary
     groups:
       development-dependencies:
@@ -25,8 +23,6 @@ updates:
     schedule:
       interval: weekly
       day: monday
-    reviewers:
-      - "edgarrmondragon"
     groups:
       actions:
         patterns:

.github/workflows/release.yml

@@ -30,7 +30,7 @@ jobs:
     if: startsWith(github.ref, 'refs/tags/')
 
     steps:
-    - uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # v4.2.1
+    - uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
       with:
         name: Packages
         path: dist

.github/workflows/test_tap.yml

@@ -16,6 +16,10 @@ on:
     - poetry.lock
     - pyproject.toml
     - 'tap_github/**'
+  workflow_dispatch:
+  schedule:
+  # Every 6 hours
+  - cron: "0 */6 * * *"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -68,14 +72,19 @@ jobs:
         virtualenvs-create: true
         virtualenvs-in-project: true
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
+      uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
       with:
         python-version: ${{ matrix.python-version }}
         cache: poetry
     - name: Install dependencies
       run: |
         poetry env use ${{ matrix.python-version }}
         poetry install
+    - name: Type check with mypy
+      id: type_check
+      continue-on-error: true
+      run: |
+        poetry run mypy tap_github
     - name: Test with pytest
       id: test_pytest
       continue-on-error: true

.pre-commit-config.yaml

@@ -16,18 +16,8 @@ repos:
 
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.9.9
+  rev: v0.11.8
   hooks:
     - id: ruff
       args: [ --fix ]
     - id: ruff-format
-
-- repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v1.15.0
-  hooks:
-  - id: mypy
-    pass_filenames: true
-    additional_dependencies:
-    - types-requests
-    - types-simplejson
-    - types-python-dateutil

README.md

@@ -2,18 +2,19 @@
 
 `tap-github` is a Singer tap for GitHub.
 
-Build with the [Singer SDK](https://gitlab.com/meltano/singer-sdk).
+Built with the [Singer SDK](https://gitlab.com/meltano/singer-sdk).
 
 ## Installation
 
 ```bash
-pipx install git+https://github.com/MeltanoLabs/tap-github.git
-```
+# use uv (https://docs.astral.sh/uv/)
+uv tool install meltanolabs-tap-github
 
-Or better yet, please pin to a [release version](https://github.com/MeltanoLabs/tap-github/releases) for a stable experience:
+# or pipx (https://pipx.pypa.io/stable/)
+pipx install meltanolabs-tap-github
 
-```bash
-pipx install git+https://github.com/MeltanoLabs/tap-github.git@vX.Y.Z
+# or Meltano
+meltano add extractor tap-github
 ```
 
 A list of release versions is available at https://github.com/MeltanoLabs/tap-github/releases

poetry.lock

@@ -33,17 +33,18 @@ packages = [
 
 [tool.poetry.dependencies]
 beautifulsoup4 = "~=4.13.3"
-cryptography = { version = "~=44.0.0", python = ">3.9.0,<3.9.1 || >3.9.1" }
+cryptography = { version = "~=45.0.2", python = ">3.9.0,<3.9.1 || >3.9.1" }
 nested-lookup = "~=0.2.25"
 PyJWT = "2.10.1"
 python = ">=3.9"
 python-dateutil = "~=2.9"
 requests = "~=2.32.3"
 # For local SDK dev:
 # singer-sdk = {path = "../singer-sdk", develop = true}
-singer-sdk = "~=0.44.0"
+singer-sdk = "~=0.46.0"
 
 [tool.poetry.group.dev.dependencies]
+mypy = ">=1.15.0"
 pytest = ">=7.3.1"
 requests-cache = ">=1.0.1"
 types-beautifulsoup4 = ">=4.12.0"
@@ -55,13 +56,16 @@ types-simplejson = "~=3.20.0"
 enable = true
 
 [[tool.mypy.overrides]]
-module = ["backoff"]
+module = [
+	"backoff",
+	"nested_lookup",
+]
 ignore_missing_imports = true
 
 [build-system]
 requires = [
 	"poetry-core==2.1.1",
-	"poetry-dynamic-versioning==1.7.1",
+	"poetry-dynamic-versioning==1.8.2",
 
 ]
 build-backend = "poetry_dynamic_versioning.backend"

pyproject.toml

@@ -6,7 +6,6 @@
 import inspect
 import random
 import time
-from types import FrameType
 from typing import TYPE_CHECKING, Any, ClassVar, cast
 from urllib.parse import parse_qs, urlparse
 
@@ -20,9 +19,11 @@
 
 if TYPE_CHECKING:
     from collections.abc import Iterable
+    from types import FrameType
 
     import requests
     from backoff.types import Details
+    from singer_sdk.helpers.types import Context
 
 EMPTY_REPO_ERROR_STATUS = 409
 
@@ -61,7 +62,7 @@ def url_base(self) -> str:
     def http_headers(self) -> dict[str, str]:
         """Return the http headers needed."""
         headers = {"Accept": "application/vnd.github.v3+json"}
-        headers["User-Agent"] = cast(str, self.config.get("user_agent", "tap-github"))
+        headers["User-Agent"] = cast("str", self.config.get("user_agent", "tap-github"))
         return headers
 
     def get_next_page_token(
@@ -74,7 +75,8 @@ def get_next_page_token(
             previous_token
             and self.MAX_RESULTS_LIMIT
             and (
-                cast(int, previous_token) * self.MAX_PER_PAGE >= self.MAX_RESULTS_LIMIT
+                cast("int", previous_token) * self.MAX_PER_PAGE
+                >= self.MAX_RESULTS_LIMIT
             )
         ):
             return None
@@ -139,7 +141,7 @@ def get_next_page_token(
 
     def get_url_params(
         self,
-        context: dict | None,
+        context: Context | None,
         next_page_token: Any | None,  # noqa: ANN401
     ) -> dict[str, Any]:
         """Return a dictionary of values to be used in URL parameterization."""
@@ -172,7 +174,7 @@ def get_url_params(
             params[since_key] = since.isoformat(sep="T")
             # Leverage conditional requests to save API quotas
             # https://github.community/t/how-does-if-modified-since-work/139627
-            self._http_headers["If-modified-since"] = email.utils.format_datetime(since)
+            self.http_headers["If-modified-since"] = email.utils.format_datetime(since)
         return params
 
     def validate_response(self, response: requests.Response) -> None:
@@ -270,7 +272,7 @@ def parse_response(self, response: requests.Response) -> Iterable[dict]:
 
         yield from results
 
-    def post_process(self, row: dict, context: dict[str, str] | None = None) -> dict:
+    def post_process(self, row: dict, context: Context | None = None) -> dict:
         """Add `repo_id` by default to all streams."""
         if context is not None and "repo_id" in context:
             row["repo_id"] = context["repo_id"]
@@ -283,8 +285,8 @@ def backoff_handler(self, details: Details) -> None:
         # FIXME: replace this once https://github.com/litl/backoff/issues/158
         # is fixed
         exc = cast(
-            FrameType,
-            cast(FrameType, cast(FrameType, inspect.currentframe()).f_back).f_back,
+            "FrameType",
+            cast("FrameType", cast("FrameType", inspect.currentframe()).f_back).f_back,
         ).f_locals["e"]
         if (
             exc.response is not None
@@ -300,7 +302,7 @@ def calculate_sync_cost(
         self,
         request: requests.PreparedRequest,
         response: requests.Response,
-        context: dict | None,
+        context: Context | None,
     ) -> dict[str, int]:
         """Return the cost of the last REST API call."""
         return {"rest": 1, "graphql": 0, "search": 0}
@@ -448,11 +450,11 @@ def get_next_page_token(
 
     def get_url_params(
         self,
-        context: dict | None,
+        context: Context | None,
         next_page_token: Any | None,  # noqa: ANN401
     ) -> dict[str, Any]:
         """Return a dictionary of values to be used in URL parameterization."""
-        params = context.copy() if context else {}
+        params = dict(context) if context else {}
         params["per_page"] = self.MAX_PER_PAGE
         if next_page_token:
             params.update(next_page_token)
@@ -467,7 +469,7 @@ def calculate_sync_cost(
         self,
         request: requests.PreparedRequest,
         response: requests.Response,
-        context: dict | None,
+        context: Context | None,
     ) -> dict[str, int]:
         """Return the cost of the last graphql API call."""
         costgen = extract_jsonpath("$.data.rateLimit.cost", input=response.json())

tap_github/client.py

@@ -11,6 +11,8 @@
 if TYPE_CHECKING:
     from collections.abc import Iterable
 
+    from singer_sdk.helpers.types import Context
+
 
 class OrganizationStream(GitHubRestStream):
     """Defines a GitHub Organization Stream.
@@ -24,12 +26,12 @@ class OrganizationStream(GitHubRestStream):
     def partitions(self) -> list[dict] | None:
         return [{"org": org} for org in self.config["organizations"]]
 
-    def get_child_context(self, record: dict, context: dict | None) -> dict:
+    def get_child_context(self, record: dict, context: Context | None) -> dict:
         return {
             "org": record["login"],
         }
 
-    def get_records(self, context: dict | None) -> Iterable[dict[str, Any]]:
+    def get_records(self, context: Context | None) -> Iterable[dict[str, Any]]:
         """
         Override the parent method to allow skipping API calls
         if the stream is deselected and skip_parent_streams is True in config.
@@ -106,7 +108,7 @@ class TeamsStream(GitHubRestStream):
     parent_stream_type = OrganizationStream
     state_partitioning_keys: ClassVar[list[str]] = ["org"]
 
-    def get_child_context(self, record: dict, context: dict | None) -> dict:
+    def get_child_context(self, record: dict, context: Context | None) -> dict:
         new_context = {"team_slug": record["slug"]}
         if context:
             return {
@@ -161,7 +163,7 @@ class TeamMembersStream(GitHubRestStream):
     parent_stream_type = TeamsStream
     state_partitioning_keys: ClassVar[list[str]] = ["team_slug", "org"]
 
-    def get_child_context(self, record: dict, context: dict | None) -> dict:
+    def get_child_context(self, record: dict, context: Context | None) -> dict:
         new_context = {"username": record["login"]}
         if context:
             return {