From beecfc853f4c7471635a40a78deed0238dd9c489 Mon Sep 17 00:00:00 2001
From: Simeon David Schaub <simeon@schaub.rocks>
Date: Mon, 23 Sep 2024 13:02:26 +0200
Subject: [PATCH] Handle if registry toml is larger than 1MB  (#356)

* Try fixing #350

!!! This is untested!

This is according to https://github.com/PyGithub/PyGithub/issues/2345#issuecomment-1835376705

Locally I tested that the following works correctly:

```python
In [24]: from github import Github, Auth

In [25]: auth = Auth.Token(token)

In [26]: g = Github(auth=auth)

In [27]: repo = g.get_repo("JuliaRegistries/General")

In [28]: registry_toml = repo.get_contents("Registry.toml")

In [39]: blob = repo.get_git_blob(registry_toml.sha)

In [40]: b64 = base64.b64decode(blob.content)

In [41]: b64.decode("utf8")
```

* Update test_repo.py

* fix formatting
---
 tagbot/action/repo.py    | 13 +++----------
 test/action/test_repo.py | 11 +++++++----
 2 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/tagbot/action/repo.py b/tagbot/action/repo.py
index 92c3037..4b9d5d6 100644
--- a/tagbot/action/repo.py
+++ b/tagbot/action/repo.py
@@ -156,16 +156,9 @@ def _registry_path(self) -> Optional[str]:
                 registry = toml.load(f)
         else:
             contents = self._only(self._registry.get_contents("Registry.toml"))
-            # show file contents if cannot be decoded
-            try:
-                string_contents = contents.decoded_content.decode()
-            except AssertionError:
-                logger.info(
-                    f"Registry.toml could not be decoded. Raw contents: {contents}"
-                )
-                # rethrow now we've logged info
-                raise
-
+            blob = self._registry.get_git_blob(contents.sha)
+            b64 = b64decode(blob.content)
+            string_contents = b64.decode("utf8")
             registry = toml.loads(string_contents)
 
         if uuid in registry["packages"]:
diff --git a/test/action/test_repo.py b/test/action/test_repo.py
index ceb30a5..d5d2396 100644
--- a/test/action/test_repo.py
+++ b/test/action/test_repo.py
@@ -101,10 +101,13 @@ def test_project_subdir():
 def test_registry_path():
     r = _repo()
     r._registry = Mock()
-    r._registry.get_contents.return_value.decoded_content = b"""
-    [packages]
-    abc-def = { path = "B/Bar" }
-    """
+    r._registry.get_contents.return_value.sha = "123"
+    r._registry.get_git_blob.return_value.content = b64encode(
+        b"""
+        [packages]
+        abc-def = { path = "B/Bar" }
+        """
+    )
     r._project = lambda _k: "abc-ddd"
     assert r._registry_path is None
     r._project = lambda _k: "abc-def"