Add the wiki publishing workflow
Validate workflows / validate (pull_request) Successful in 15s

Add tools/publish_wiki.py and the Publish wiki workflow, which make the
Gitea wiki equal wiki/ through the wiki REST API when a change to wiki/ is
merged to main. It needs its own secret TOKEN_FOR_GITEA_WIKI, refuses an
empty source and checks that the English pages are current first.

Document the secret in the credentials and troubleshooting guides and
regenerate the affected wiki pages.

Task: MIL-005#8
This commit is contained in:
2026-10-10 09:06:13 +08:00
parent 334b214a12
commit 1472513421
9 changed files with 585 additions and 0 deletions
+262
View File
@@ -0,0 +1,262 @@
"""Offline tests for tools/publish_wiki.py and its workflow."""
import base64
import importlib.util
import io
import json
import urllib.error
from pathlib import Path
import pytest
import yaml
REPO_ROOT = Path(__file__).resolve().parent.parent
WORKFLOW = REPO_ROOT / ".gitea" / "workflows" / "publish-wiki.yml"
_SPEC = importlib.util.spec_from_file_location(
"publish_wiki", REPO_ROOT / "tools" / "publish_wiki.py"
)
assert _SPEC is not None and _SPEC.loader is not None
publish_wiki = importlib.util.module_from_spec(_SPEC)
_SPEC.loader.exec_module(publish_wiki)
API = "https://git.example.test/api/v1"
REPO_URL = f"{API}/repos/TirSystem/repo"
WIKI_URL = f"{REPO_URL}/wiki"
def b64(text: str) -> str:
return base64.b64encode(text.encode()).decode()
class TestParseGiteaToken:
def test_accepts_bare_token(self):
assert publish_wiki.parse_gitea_token(" abc ") == "abc"
def test_accepts_json_object_and_string(self):
assert publish_wiki.parse_gitea_token('{"GITEA_TOKEN": "abc"}') == "abc"
assert publish_wiki.parse_gitea_token('"abc"') == "abc"
@pytest.mark.parametrize("raw", [None, "", " ", "{}", '{"GITEA_TOKEN": ""}', "[1]"])
def test_rejects_missing_or_empty_token(self, raw):
with pytest.raises(publish_wiki.WorkflowError) as caught:
publish_wiki.parse_gitea_token(raw)
assert caught.value.category == "configuration"
assert "TOKEN_FOR_GITEA_WIKI" in str(caught.value)
class TestReadPages:
def test_reads_markdown_files_by_stem(self, tmp_path):
(tmp_path / "Home.md").write_bytes(b"home")
(tmp_path / "Notes.txt").write_bytes(b"ignored")
assert publish_wiki.read_pages(tmp_path) == {"Home": b"home"}
def test_rejects_missing_directory(self, tmp_path):
with pytest.raises(publish_wiki.WorkflowError, match="missing"):
publish_wiki.read_pages(tmp_path / "nope")
def test_rejects_empty_directory_so_the_wiki_is_never_wiped(self, tmp_path):
with pytest.raises(publish_wiki.WorkflowError, match="no Markdown pages"):
publish_wiki.read_pages(tmp_path)
class FakeGitea:
"""Answers like the Gitea repository and wiki endpoints."""
def __init__(self, wiki=None, has_wiki=True, wiki_initialised=True):
self.wiki = dict(wiki or {})
self.has_wiki = has_wiki
self.wiki_initialised = wiki_initialised
self.calls = []
def __call__(self, url, method="GET", headers=None, body=None):
self.calls.append((method, url, body))
if url == REPO_URL:
return {"has_wiki": self.has_wiki}
if url.startswith(f"{WIKI_URL}/pages"):
if not self.wiki_initialised:
raise publish_wiki.WorkflowError("configuration", "404")
return [{"title": title} for title in self.wiki]
if method == "POST" and url == f"{WIKI_URL}/new":
self.wiki[body["title"]] = body["content_base64"]
return None
title = url.rsplit("/", 1)[-1]
if method == "GET":
return {"title": title, "content_base64": self.wiki[title]}
if method == "PATCH":
self.wiki[title] = body["content_base64"]
return None
if method == "DELETE":
del self.wiki[title]
return None
raise AssertionError(f"unexpected request {method} {url}")
@pytest.fixture()
def environment(monkeypatch, tmp_path):
wiki_dir = tmp_path / "wiki"
wiki_dir.mkdir()
(wiki_dir / "Home.md").write_text("home v2", encoding="utf-8")
(wiki_dir / "Credentials.md").write_text("credentials", encoding="utf-8")
monkeypatch.setenv("WIKI_DIR", str(wiki_dir))
monkeypatch.setenv("GITEA_API_URL", f"{API}/")
monkeypatch.setenv("SOURCE_REPOSITORY", "TirSystem/repo")
monkeypatch.setenv("WIKI_CREDENTIALS", "wiki-token")
return wiki_dir
def run_main(monkeypatch, gitea):
monkeypatch.setattr(publish_wiki, "request_json", gitea)
return publish_wiki.main()
class TestMain:
def test_creates_updates_and_deletes_to_match_the_source(
self, monkeypatch, environment, capsys
):
gitea = FakeGitea(
wiki={"Home": b64("home v1"), "Credentials": b64("credentials"), "Old": b64("x")}
)
assert run_main(monkeypatch, gitea) == 0
assert gitea.wiki == {"Home": b64("home v2"), "Credentials": b64("credentials")}
methods = [(call[0], call[1].rsplit("/", 1)[-1]) for call in gitea.calls]
assert ("PATCH", "Home") in methods
assert ("DELETE", "Old") in methods
assert ("PATCH", "Credentials") not in methods
assert "0 created, 1 updated, 1 deleted" in capsys.readouterr().out
def test_creates_every_page_when_the_wiki_was_never_written(
self, monkeypatch, environment
):
gitea = FakeGitea(wiki_initialised=False)
assert run_main(monkeypatch, gitea) == 0
assert set(gitea.wiki) == {"Home", "Credentials"}
assert [call[0] for call in gitea.calls].count("POST") == 2
def test_does_nothing_when_the_wiki_is_already_current(self, monkeypatch, environment):
gitea = FakeGitea(wiki={"Home": b64("home v2"), "Credentials": b64("credentials")})
assert run_main(monkeypatch, gitea) == 0
assert all(call[0] == "GET" for call in gitea.calls)
def test_sends_the_token_and_never_prints_it(self, monkeypatch, environment, capsys):
seen = []
class Recording(FakeGitea):
def __call__(self, url, method="GET", headers=None, body=None):
seen.append(headers["Authorization"])
return super().__call__(url, method, headers, body)
assert run_main(monkeypatch, Recording()) == 0
assert set(seen) == {"token wiki-token"}
output = capsys.readouterr()
assert "wiki-token" not in output.out + output.err
def test_fails_when_the_wiki_is_not_enabled(self, monkeypatch, environment):
gitea = FakeGitea(has_wiki=False)
with pytest.raises(publish_wiki.WorkflowError) as caught:
run_main(monkeypatch, gitea)
assert caught.value.category == "configuration"
assert all(call[0] == "GET" for call in gitea.calls)
def test_fails_before_any_request_when_the_secret_is_missing(
self, monkeypatch, environment
):
monkeypatch.setenv("WIKI_CREDENTIALS", "")
gitea = FakeGitea()
with pytest.raises(publish_wiki.WorkflowError, match="TOKEN_FOR_GITEA_WIKI"):
run_main(monkeypatch, gitea)
assert gitea.calls == []
def test_fails_before_any_request_when_the_source_is_empty(
self, monkeypatch, environment
):
for path in environment.glob("*.md"):
path.unlink()
gitea = FakeGitea(wiki={"Home": b64("keep me")})
with pytest.raises(publish_wiki.WorkflowError, match="no Markdown pages"):
run_main(monkeypatch, gitea)
assert gitea.calls == []
assert gitea.wiki == {"Home": b64("keep me")}
class TestRequestJson:
@staticmethod
def raise_http_error(monkeypatch, code, reason):
def fake_urlopen(request, timeout):
raise urllib.error.HTTPError(
request.full_url, code, reason, {}, io.BytesIO(b"secret detail")
)
monkeypatch.setattr(publish_wiki.urllib.request, "urlopen", fake_urlopen)
@pytest.mark.parametrize(
("code", "reason", "category"),
[
(401, "Unauthorized", "credentials"),
(403, "Forbidden", "permissions"),
(404, "Not Found", "configuration"),
(500, "Server Error", "api"),
],
)
def test_categorizes_http_errors(self, monkeypatch, code, reason, category):
self.raise_http_error(monkeypatch, code, reason)
with pytest.raises(publish_wiki.WorkflowError) as caught:
publish_wiki.request_json(REPO_URL)
assert caught.value.category == category
assert f"HTTP {code}" in str(caught.value)
assert "secret detail" not in str(caught.value)
def test_reports_unreachable_service_as_api_failure(self, monkeypatch):
def fake_urlopen(request, timeout):
raise urllib.error.URLError("no route")
monkeypatch.setattr(publish_wiki.urllib.request, "urlopen", fake_urlopen)
with pytest.raises(publish_wiki.WorkflowError) as caught:
publish_wiki.request_json(REPO_URL)
assert caught.value.category == "api"
class TestWorkflow:
@pytest.fixture()
def document(self):
return yaml.safe_load(WORKFLOW.read_text(encoding="utf-8"))
def test_runs_only_on_main_when_wiki_changes_or_by_hand(self, document):
triggers = document[True] # PyYAML reads the key `on` as True
assert triggers["push"]["branches"] == ["main"]
assert triggers["push"]["paths"] == ["wiki/**"]
assert "workflow_dispatch" in triggers
def test_job_has_read_only_permissions(self, document):
job = document["jobs"]["publish-wiki"]
assert job["permissions"] == {"contents": "read"}
def test_checks_the_pages_before_publishing_them(self, document):
runs = [step.get("run", "") for step in document["jobs"]["publish-wiki"]["steps"]]
assert runs.index("python3 tools/build_wiki.py --check") < runs.index(
"python3 tools/publish_wiki.py"
)
def test_secret_is_passed_only_through_the_environment(self, document):
text = WORKFLOW.read_text(encoding="utf-8")
assert text.count("secrets.TOKEN_FOR_GITEA_WIKI") == 1
steps = document["jobs"]["publish-wiki"]["steps"]
publish_step = steps[-1]
assert publish_step["env"]["WIKI_CREDENTIALS"] == "${{ secrets.TOKEN_FOR_GITEA_WIKI }}"
assert "secrets" not in publish_step["run"]