rss-news/backend/tests/test_wordpress.py
Oliver Giertz f0d10112ad
feat(wordpress): set post category from title and tag rules
Published articles carried no category, so WordPress filed all of them
under the catch-all "Allgemein" - 941 of 955 posts by the time this was
noticed. The rules here mirror the one-off backfill of 2026-07-31 and
reproduce its result on all 955 posts exactly.

Matching is done on word boundaries rather than plain substrings, which
otherwise filed a campsite in Klagenfurt under "Recht & Vorschriften" via
the keyword "klage". German compounds opt in explicitly with a trailing
"*". A clear discount signal takes precedence over the product topic,
because product tags otherwise outnumber it.

Unknown slugs are never auto-created: unlike tags, the category set is
curated in WordPress, so a mismatch should surface rather than spawn a
new category. Articles that match no rule stay uncategorised on purpose.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-31 08:00:32 +02:00

215 lines
10 KiB
Python

import os
import unittest
from unittest.mock import patch
from backend.app import config as config_module
from backend.app import wordpress as wordpress_module
from backend.app.wordpress import publish_article_draft
class TestWordpressPublish(unittest.TestCase):
def setUp(self) -> None:
os.environ["WORDPRESS_BASE_URL"] = "https://example.org"
os.environ["WORDPRESS_USERNAME"] = "wp-user"
os.environ["WORDPRESS_APP_PASSWORD"] = "wp-pass"
config_module.get_settings.cache_clear()
# The category lookup is cached for the process lifetime; without this
# one test would resolve a slug that the next one expects to be missing.
wordpress_module._category_id_cache.clear()
def tearDown(self) -> None:
for key in ("WORDPRESS_BASE_URL", "WORDPRESS_USERNAME", "WORDPRESS_APP_PASSWORD"):
os.environ.pop(key, None)
config_module.get_settings.cache_clear()
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_sets_featured_media_when_selected_image_exists(self, mock_wp_request, mock_upload_media) -> None:
mock_upload_media.return_value = 456
mock_wp_request.return_value = {"id": 321, "link": "https://example.org/?p=321"}
article = {
"title": "Testartikel",
"content_raw": "Inhalt",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": '{"image_review":{"selected_url":"https://example.com/image.jpg"}}',
}
post_id, post_url = publish_article_draft(article)
self.assertEqual(post_id, 321)
self.assertIn("?p=321", post_url or "")
self.assertTrue(mock_upload_media.called)
payload = mock_wp_request.call_args.kwargs["payload"]
self.assertEqual(payload.get("featured_media"), 456)
self.assertIn("<!-- wp:paragraph -->", payload.get("content", ""))
self.assertIn("<p>Inhalt</p>", payload.get("content", ""))
self.assertNotIn("excerpt", payload)
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_without_selected_image_has_no_featured_media(self, mock_wp_request, mock_upload_media) -> None:
mock_wp_request.return_value = {"id": 654, "link": "https://example.org/?p=654"}
article = {
"title": "Testartikel",
"content_raw": "Inhalt",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": "{}",
}
post_id, _ = publish_article_draft(article)
self.assertEqual(post_id, 654)
self.assertFalse(mock_upload_media.called)
payload = mock_wp_request.call_args.kwargs["payload"]
self.assertNotIn("featured_media", payload)
self.assertIn("<p>Inhalt</p>", payload.get("content", ""))
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_strips_feed_header_and_press_contact(self, mock_wp_request, mock_upload_media) -> None:
mock_wp_request.return_value = {"id": 100, "link": "https://example.org/?p=100"}
article = {
"title": "Header Test",
"content_raw": "21.02.2026 10:00\nFirma GmbH\n(ots)\nDas ist der eigentliche Text.\nPressekontakt: Test Person",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": "{}",
}
publish_article_draft(article)
payload = mock_wp_request.call_args.kwargs["payload"]
content = payload.get("content", "")
self.assertNotIn("Firma GmbH", content)
self.assertNotIn("Pressekontakt", content)
self.assertIn("eigentliche Text", content)
self.assertNotIn("Artikeldetails", content)
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_resolves_and_sets_tags(self, mock_wp_request, mock_upload_media) -> None:
def _fake_wp_request(**kwargs):
endpoint = kwargs.get("endpoint", "")
method = kwargs.get("method", "")
if method == "GET" and endpoint.startswith("tags?search="):
if "Rheingas" in endpoint:
return [{"id": 11, "name": "Rheingas"}]
return []
if method == "POST" and endpoint == "tags":
name = (kwargs.get("payload") or {}).get("name")
if name == "Gasflasche":
return {"id": 12, "name": "Gasflasche"}
return {"id": 13, "name": str(name)}
if method == "POST" and endpoint == "posts":
return {"id": 900, "link": "https://example.org/?p=900"}
return {}
mock_wp_request.side_effect = _fake_wp_request
article = {
"title": "Tag Test",
"content_raw": "Inhalt",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": '{"generated_tags":["Rheingas","Gasflasche"]}',
}
post_id, _ = publish_article_draft(article)
self.assertEqual(post_id, 900)
post_calls = [call for call in mock_wp_request.call_args_list if call.kwargs.get("endpoint") == "posts"]
self.assertEqual(len(post_calls), 1)
payload = post_calls[0].kwargs.get("payload", {})
self.assertEqual(payload.get("tags"), [11, 12])
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_converts_html_to_wp_blocks_without_html_block(self, mock_wp_request, mock_upload_media) -> None:
mock_wp_request.return_value = {"id": 111, "link": "https://example.org/?p=111"}
article = {
"title": "Block Test",
"content_rewritten": "<h2>Überschrift</h2><p>Absatz 1</p><ul><li>A</li><li>B</li></ul>",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": "{}",
}
publish_article_draft(article)
payload = mock_wp_request.call_args.kwargs["payload"]
content = payload.get("content", "")
self.assertIn("<!-- wp:heading", content)
self.assertIn("<!-- wp:paragraph -->", content)
self.assertIn("<!-- wp:list -->", content)
self.assertNotIn("<!-- wp:html -->", content)
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_sets_category_from_rules(self, mock_wp_request, mock_upload_media) -> None:
def _fake_wp_request(**kwargs):
endpoint = kwargs.get("endpoint", "")
method = kwargs.get("method", "")
if method == "GET" and endpoint.startswith("tags?search="):
return [{"id": 21, "name": "Kühlbox"}]
if method == "GET" and endpoint.startswith("categories?slug=ausruestung-tests"):
return [{"id": 77, "slug": "ausruestung-tests"}]
if method == "POST" and endpoint == "posts":
return {"id": 901, "link": "https://example.org/?p=901"}
return {}
mock_wp_request.side_effect = _fake_wp_request
article = {
"title": "Dometic CFX5 45 im Test: Top-Kühlbox für unterwegs",
"content_raw": "Inhalt",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": '{"generated_tags":["Kühlbox"]}',
}
post_id, _ = publish_article_draft(article)
self.assertEqual(post_id, 901)
payload = [c for c in mock_wp_request.call_args_list if c.kwargs.get("endpoint") == "posts"][0].kwargs["payload"]
self.assertEqual(payload.get("categories"), [77])
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_omits_category_when_no_rule_matches(self, mock_wp_request, mock_upload_media) -> None:
def _fake_wp_request(**kwargs):
if kwargs.get("method") == "POST" and kwargs.get("endpoint") == "posts":
return {"id": 902, "link": "https://example.org/?p=902"}
return {}
mock_wp_request.side_effect = _fake_wp_request
article = {
"title": "Weihnachten 2021",
"content_raw": "Inhalt",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": '{"generated_tags":[]}',
}
publish_article_draft(article)
payload = [c for c in mock_wp_request.call_args_list if c.kwargs.get("endpoint") == "posts"][0].kwargs["payload"]
self.assertNotIn("categories", payload)
self.assertFalse(any("categories?slug=" in (c.kwargs.get("endpoint") or "")
for c in mock_wp_request.call_args_list))
@patch("backend.app.wordpress._upload_featured_media")
@patch("backend.app.wordpress._wp_request")
def test_publish_skips_category_when_slug_is_missing_in_wordpress(self, mock_wp_request, mock_upload_media) -> None:
def _fake_wp_request(**kwargs):
endpoint = kwargs.get("endpoint", "")
if kwargs.get("method") == "GET" and endpoint.startswith("categories?slug="):
return []
if kwargs.get("method") == "POST" and endpoint == "posts":
return {"id": 903, "link": "https://example.org/?p=903"}
return {}
mock_wp_request.side_effect = _fake_wp_request
article = {
"title": "Dometic CFX5 45 im Test: Top-Kühlbox für unterwegs",
"content_raw": "Inhalt",
"source_url": "https://example.com/source",
"canonical_url": "https://example.com/source",
"meta_json": '{"generated_tags":[]}',
}
publish_article_draft(article)
payload = [c for c in mock_wp_request.call_args_list if c.kwargs.get("endpoint") == "posts"][0].kwargs["payload"]
self.assertNotIn("categories", payload)
if __name__ == "__main__":
unittest.main()