feat(projekt-matching): mail parsing, project splitting, canonical URLs

2026-07-09 10:11:25 +02:00
parent 3bbf6631fd
commit 6c4cd1a4c3
2 changed files with 152 additions and 0 deletions
--- a/projekt-matching/tests/test_mailparse.py
+++ b/projekt-matching/tests/test_mailparse.py
@@ -0,0 +1,69 @@
+import email
+from email.policy import default as default_policy
+from unittest import mock
+
+from projektmatch import mailparse
+
+HTML = """
+<html><body>
+<h2><a href="https://www.freelancermap.de/nproj/3020338.html?utm_source=x&t=1">
+Python Entwickler für eine KI-Anwendung (m/w/d)</a></h2>
+<p>Beschreibung ...</p>
+<a href="https://www.freelancermap.de/nproj/3020338.html?utm_source=x&t=1">Zum Projekt</a>
+<h2><a href="https://www.freelancermap.de/nproj/3020995.html?agent=2">
+Test Engineer (m/w/d)</a></h2>
+<a href="https://www.freelancermap.de/other/page.html">Impressum</a>
+</body></html>
+"""
+
+TEXT = """Neue Projekte fuer Sie:
+
+Python Entwickler für eine KI-Anwendung (m/w/d)
+https://www.freelancermap.de/nproj/3020338.html?utm_source=x
+
+Test Engineer (m/w/d)
+https://www.freelancermap.de/nproj/3020995.html?agent=2
+"""
+
+
+def test_is_own_mail():
+    assert mailparse.is_own_mail("[Projekt-Match] Freelancermap — 86 % — X")
+    assert mailparse.is_own_mail("[Projekt-Match-Fehler] Freelancermap — 2 Projekt(e)")
+    assert not mailparse.is_own_mail("Example 1 for Langflow process")
+    assert not mailparse.is_own_mail(None)
+
+
+def test_split_projects_html_dedupes_and_prefers_long_title():
+    items = mailparse.split_projects(HTML, "")
+    assert [i["title"] for i in items] == [
+        "Python Entwickler für eine KI-Anwendung (m/w/d)", "Test Engineer (m/w/d)"]
+    assert "3020338" in items[0]["url"]
+
+
+def test_split_projects_text_fallback():
+    items = mailparse.split_projects("", TEXT)
+    assert len(items) == 2
+    assert items[0]["title"] == "Python Entwickler für eine KI-Anwendung (m/w/d)"
+
+
+def test_split_projects_none_for_normal_mail():
+    assert mailparse.split_projects("<p>Hallo</p>", "Hallo") == []
+
+
+def test_bodies_multipart():
+    msg = email.message.EmailMessage(policy=default_policy)
+    msg["Subject"] = "x"
+    msg.set_content("plain body")
+    msg.add_alternative("<p>html body</p>", subtype="html")
+    html, text = mailparse.bodies(msg)
+    assert "html body" in html and "plain body" in text
+
+
+def test_canonical_url_strips_query():
+    session = mock.Mock()
+    session.get.return_value = mock.Mock(
+        url="https://www.freelancermap.de/projekt/python-entwickler?ref=1",
+        raise_for_status=lambda: None)
+    out = mailparse.canonical_url("https://www.freelancermap.de/nproj/1.html?x=1",
+                                  session=session)
+    assert out == "https://www.freelancermap.de/projekt/python-entwickler"