Jens/VacatureRadar
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix release blockers and deployment build
deploy / deploy (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
Jens
2026-07-21 21:22:29 +02:00
parent b8091e59bd
commit a4eced8be5
64 changed files with 1011 additions and 675 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/unit/test_discovery_rss.py
+12 -7
View File
@@ -38,12 +38,15 @@ def test_discovery_from_html_includes_jsonld_and_feed_links():
assert candidate_urls["https://example.org/werken-bij"] == "html"
assert candidate_urls["https://jobs.example.org/vacatures/"] == "html"
assert candidate_urls["https://jobs.example.org/vacatures/data-engineer"] == "html-jsonld"
assert candidate_urls["https://jobs.example.org/vacatures/data-engineer/solliciteer"] == "html-jsonld"
assert candidate_urls["https://example.org/feed/jobs.xml"] == "html"
assert candidate_urls["https://jobs.example.org/vacatures/data-engineer"].startswith("html-jsonld")
assert any(
c.source_type == Source.Type.RSS and c.reason == "feed" for c in result
assert (
candidate_urls["https://jobs.example.org/vacatures/data-engineer/solliciteer"]
== "html-jsonld"
)
assert candidate_urls["https://example.org/feed/jobs.xml"] == "html"
assert candidate_urls["https://jobs.example.org/vacatures/data-engineer"].startswith(
"html-jsonld"
)
assert any(c.source_type == Source.Type.RSS and c.reason == "feed" for c in result)
assert any(
c.source_type == Source.Type.EMPLOYER and c.url == "https://example.org/werken-bij"
for c in result
@@ -69,14 +72,16 @@ def test_discovery_from_sitemap_prefers_candidates_and_filters_private_or_denied
assert len(index_candidates) == 1
assert index_candidates[0].url == "https://jobs.example.org/sitemap-jobs.xml"
assert len(urlset_candidates) >= 2
assert any(item.url == "https://jobs.example.org/vacatures/data-engineer" for item in urlset_candidates)
assert any(
item.url == "https://jobs.example.org/vacatures/data-engineer" for item in urlset_candidates
)
assert all("linkedin.com" not in item.url for item in index_candidates + urlset_candidates)
def test_discovery_from_email_extracts_employer_domain_root():
raw = Path("fixtures/emails/sample_alert.eml").read_bytes()
result = discover_from_email(raw)
assert [item.url for item in result] == ["https://jobs.example.org"]
assert [item.url for item in result] == ["https://jobs.example.org/"]
assert result[0].source_type == Source.Type.EMPLOYER