From 0ec7eabf600ab5d6b41001ad1ce70489a9e6d171 Mon Sep 17 00:00:00 2001
From: Jon Massey <jon.massey@thedatalab.org>
Date: Fri, 10 May 2024 17:03:37 +0100
Subject: [PATCH] GitHub query, dataclass, and test

Spec of fields to extract from API response taken from discussion
in https://github.com/opensafely-core/codespaces-initiative/issues/42
---
 INSTALL.md                          |  7 +++++++
 dotenv-sample                       |  1 +
 metrics/github/client.py            |  5 +++++
 metrics/github/github.py            | 22 ++++++++++++++++++++++
 metrics/github/query.py             | 12 ++++++++++++
 tests/metrics/github/test_github.py | 17 +++++++++++++++++
 6 files changed, 64 insertions(+)

diff --git a/INSTALL.md b/INSTALL.md
index a80e61dd..761a8798 100644
--- a/INSTALL.md
+++ b/INSTALL.md
@@ -9,6 +9,7 @@ dokku$ dokku git:set metrics deploy-branch main
 ```bash
 dokku config:set metrics GITHUB_EBMDATALAB_TOKEN='xxx'
 dokku config:set metrics GITHUB_OS_CORE_TOKEN='xxx'
+dokku config:set metrics GITHUB_OS_TOKEN='xxx'
 dokku config:set metrics SLACK_SIGNING_SECRET='xxx'
 dokku config:set metrics SLACK_TECH_SUPPORT_CHANNEL_ID='xxx'
 dokku config:set metrics SLACK_TOKEN='xxx'
@@ -22,6 +23,12 @@ Each token is assigned to a single organisation and should have the following *r
 * *all repositories* owned by the organisation with the following permissions:
 Code scanning alerts, Dependabot alerts, Metadata, Pull requests and Repository security advisories
 
+The `GITHUB_OS_TOKEN` is a fine-grained GitHub personal access token that is used for authenticating with the GitHub REST API.
+It is assigned to a single organisation and should have the following *read-only* permissions:
+* organisation permissions: codespaces
+* *all repositories* owned by the organisation with the following permissions:
+Codespaces and Metadata
+
 ## Disable checks
 Dokku performs health checks on apps during deploy by sending requests to port 80.
 This tool isn't a web app so it can't accept requests on a port.
diff --git a/dotenv-sample b/dotenv-sample
index bba73f88..7032b7ba 100644
--- a/dotenv-sample
+++ b/dotenv-sample
@@ -4,6 +4,7 @@ TIMESCALEDB_URL=postgresql://user:pass@localhost:5433/metrics
 # API tokens for pulling data from Github
 GITHUB_EBMDATALAB_TOKEN=
 GITHUB_OS_CORE_TOKEN=
+GITHUB_OS_TOKEN=
 
 # Slack API access credentials.
 # The slack app used for this will need the following OAuth scopes:
diff --git a/metrics/github/client.py b/metrics/github/client.py
index ce3512c8..96dea7a6 100644
--- a/metrics/github/client.py
+++ b/metrics/github/client.py
@@ -52,6 +52,11 @@ def rest_query(self, path, **variables):
             data = response.json()
             if isinstance(data, list):
                 yield from data
+            # unlike the PRs/Issues/Commits GitHub API endpoints
+            # the codespaces endpoint returns a dict containing a
+            # count of codespaces, and a list thereof (what we want)
+            if "codespaces" in path and isinstance(data, dict):
+                yield from data["codespaces"]
             else:
                 raise RuntimeError("Unexpected response format:", data)
 
diff --git a/metrics/github/github.py b/metrics/github/github.py
index 50d4f5e6..08270a12 100644
--- a/metrics/github/github.py
+++ b/metrics/github/github.py
@@ -108,6 +108,28 @@ def from_dict(cls, data, repo):
         )
 
 
+@dataclass(frozen=True)
+class Codespace:
+    org: str
+    # The Repo type requires fields neither returned by the codespaces
+    # endpoint, nor required for codespaces metrics so str for repo name
+    repo: str
+    user: str
+    created_at: datetime.datetime
+    last_used_at: datetime.datetime
+
+    @classmethod
+    def from_dict(cls, **kwargs):
+        return cls(**kwargs)
+
+
+def codespaces(org):
+    return [
+        Codespace.from_dict(**({"org": org} | codespace))
+        for codespace in query.codespaces(org)
+    ]
+
+
 def tech_prs():
     tech_team_members = _tech_team_members()
     return [
diff --git a/metrics/github/query.py b/metrics/github/query.py
index e3a69f51..8cb7061a 100644
--- a/metrics/github/query.py
+++ b/metrics/github/query.py
@@ -141,11 +141,23 @@ def issues(org, repo):
     )
 
 
+def codespaces(org):
+    codespaces = _client().rest_query("/orgs/{org}/codespaces", org=org)
+    for codespace in codespaces:
+        yield {
+            "user": codespace["owner"]["login"],
+            "repo": codespace["repository"]["name"],
+            "created_at": codespace["created_at"],
+            "last_used_at": codespace["last_used_at"],
+        }
+
+
 def _client():
     return GitHubClient(
         tokens={
             "ebmdatalab": os.environ["GITHUB_EBMDATALAB_TOKEN"],
             "opensafely-core": os.environ["GITHUB_OS_CORE_TOKEN"],
+            "opensafely": os.environ["GITHUB_OS_TOKEN"],
         }
     )
 
diff --git a/tests/metrics/github/test_github.py b/tests/metrics/github/test_github.py
index 6fe76fe7..18d69240 100644
--- a/tests/metrics/github/test_github.py
+++ b/tests/metrics/github/test_github.py
@@ -35,6 +35,23 @@ def fake(*keys):
     return patch
 
 
+def test_codespaces(patch):
+    patch(
+        "codespaces",
+        {
+            "opensafely": [
+                {
+                    "user": "testuser",
+                    "repo": "testrepo",
+                    "created_at": datetime.datetime.now().isoformat(),
+                    "last_used_at": datetime.datetime.now().isoformat(),
+                },
+            ]
+        },
+    )
+    assert len(github.codespaces("opensafely")) == 1
+
+
 def test_includes_tech_owned_repos(patch):
     patch(
         "team_repos",