feat(projekt-matching): flow-1 ingest with lock, dedup, dispatch, alert aggregation

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

projekt-matching/tests/test_ingest.py

@@ -0,0 +1,97 @@
+import json
+from unittest import mock
+
+from projektmatch import ingest
+from projektmatch.config import Cfg
+
+
+PROJECT_HTML = ('<a href="https://www.freelancermap.de/nproj/1.html?x=1">'
+                'Projekt Eins</a>')
+
+
+def cfg(tmp_path):
+    return Cfg(imap_password="pw", alert_to="a@x", flow2_id="F2",
+               langflow_api_key="key", data_dir=str(tmp_path))
+
+
+def run(tmp_path, mails, dup=None, dispatch_result=None):
+    box = mock.Mock()
+    box.unchecked_uids.return_value = list(mails)
+    box.fetch.side_effect = lambda uid: mails[uid]
+    espo = mock.Mock()
+    espo.find_opportunity_by_link.return_value = dup
+    sent = []
+    with mock.patch("projektmatch.ingest.mailparse.bodies",
+                    side_effect=lambda m: (m["html"], "")), \
+         mock.patch("projektmatch.ingest.mailer.send_mail",
+                    lambda *a: sent.append(a)):
+        summary = ingest.run_ingest(
+            cfg(tmp_path), mailbox=box, espo=espo,
+            resolve=lambda url: "https://www.freelancermap.de/projekt/eins",
+            dispatch=lambda item: dispatch_result or {"status": "created"})
+    return summary, box, sent
+
+
+def mail(subject, html=""):
+    return {"Subject": subject, "html": html}
+
+
+def test_non_project_mail_flagged_not_trashed(tmp_path):
+    mails = {"1": mail("Newsletter", "<p>Hallo</p>")}
+    summary, box, sent = run(tmp_path, mails)
+    box.flag_checked.assert_called_once_with("1")
+    box.move_to_trash.assert_not_called()
+    assert summary["mails"] == 0 and not sent
+
+
+def test_own_mail_skipped(tmp_path):
+    mails = {"1": mail("[Projekt-Match] Freelancermap — 90 % — X",
+                       PROJECT_HTML)}
+    summary, box, sent = run(tmp_path, mails)
+    box.flag_checked.assert_called_once_with("1")
+    box.move_to_trash.assert_not_called()
+
+
+def test_project_mail_created_and_trashed(tmp_path):
+    mails = {"1": mail("Example 1 for Langflow process", PROJECT_HTML)}
+    summary, box, sent = run(tmp_path, mails)
+    assert summary == {"mails": 1, "projects": 1, "created": 1,
+                       "rejected": 0, "duplicate": 0, "failed": 0}
+    box.move_to_trash.assert_called_once_with("1")
+    assert not sent
+
+
+def test_duplicate_skips_dispatch(tmp_path):
+    mails = {"1": mail("Mail", PROJECT_HTML)}
+    summary, box, sent = run(tmp_path, mails, dup={"id": "X"})
+    assert summary["duplicate"] == 1 and summary["created"] == 0
+    box.move_to_trash.assert_called_once()
+
+
+def test_failed_dispatch_alerts_and_trashes(tmp_path):
+    mails = {"1": mail("Mail", PROJECT_HTML)}
+    summary, box, sent = run(tmp_path, mails,
+                             dispatch_result={"status": "failed",
+                                              "error": "vLLM down"})
+    assert summary["failed"] == 1
+    assert len(sent) == 1
+    _, _, to, subject, body = sent[0]
+    assert to == "a@x"
+    assert subject == "[Projekt-Match-Fehler] Freelancermap — 1 Projekt(e)"
+    assert "vLLM down" in body
+    box.move_to_trash.assert_called_once()
+
+
+def test_lock_prevents_second_run(tmp_path):
+    lock = ingest.acquire_lock(str(tmp_path))
+    assert lock is not None
+    summary = ingest.run_ingest(cfg(tmp_path), mailbox=mock.Mock())
+    assert summary == {"skipped": "locked"}
+    ingest.release_lock(lock)
+
+
+def test_parse_run_result_finds_status_json():
+    inner = json.dumps({"status": "created", "mustMatch": 90})
+    payload = {"outputs": [{"outputs": [{"results": {"text": {
+        "data": {"text": inner}}}}]}]}
+    assert ingest.parse_run_result(payload)["status"] == "created"