feat(projekt-matching): deterministic misc rules, match calc, description markdown

projekt-matching/tests/test_rules.py

@@ -0,0 +1,96 @@
+import datetime as dt
+
+from projektmatch import rules
+
+TODAY = dt.date(2026, 7, 9)
+
+
+def geo_munich(place):
+    return (48.137, 11.575)          # ~40 km from Sauerlach
+
+
+def geo_hamburg(place):
+    return (53.551, 9.994)           # ~600 km
+
+
+def geo_fail(place):
+    raise OSError("network down")
+
+
+def misc(**kw):
+    base = {"miscType": "other", "startDate": None, "workloadPercent": None,
+            "remotePercent": None, "onsiteLocation": None}
+    base.update(kw)
+    return base
+
+
+def test_security_is_always_no():
+    assert rules.eval_misc(misc(miscType="security"), TODAY) == rules.NO
+
+
+def test_start_within_8_weeks_yes_after_no_missing_unknown():
+    assert rules.eval_misc(misc(miscType="start", startDate="2026-08-01"), TODAY) == rules.YES
+    assert rules.eval_misc(misc(miscType="start", startDate="2026-12-01"), TODAY) == rules.NO
+    assert rules.eval_misc(misc(miscType="start"), TODAY) == rules.UNKNOWN
+    assert rules.eval_misc(misc(miscType="start", startDate="asap"), TODAY) == rules.UNKNOWN
+
+
+def test_workload():
+    assert rules.eval_misc(misc(miscType="workload", workloadPercent=100), TODAY) == rules.YES
+    assert rules.eval_misc(misc(miscType="workload", workloadPercent=50), TODAY) == rules.UNKNOWN
+    assert rules.eval_misc(misc(miscType="workload"), TODAY) == rules.UNKNOWN
+
+
+def test_duration_always_yes():
+    assert rules.eval_misc(misc(miscType="duration"), TODAY) == rules.YES
+
+
+def test_location_rules():
+    full_remote = misc(miscType="location", remotePercent=100)
+    assert rules.eval_misc(full_remote, TODAY) == rules.YES
+    hybrid_near = misc(miscType="location", remotePercent=60, onsiteLocation="München")
+    assert rules.eval_misc(hybrid_near, TODAY, geocode_fn=geo_munich) == rules.YES
+    hybrid_far = misc(miscType="location", remotePercent=60, onsiteLocation="Hamburg")
+    assert rules.eval_misc(hybrid_far, TODAY, geocode_fn=geo_hamburg) == rules.NO
+    unclear = misc(miscType="location")
+    assert rules.eval_misc(unclear, TODAY) == rules.NO
+    geo_broken = misc(miscType="location", remotePercent=40, onsiteLocation="Xyzstadt")
+    assert rules.eval_misc(geo_broken, TODAY, geocode_fn=geo_fail) == rules.UNKNOWN
+
+
+def test_calc_match_and_rounding():
+    rows = [{"kat": "Must", "rating": "yes", "text": "a"},
+            {"kat": "Must", "rating": "yes", "text": "b"},
+            {"kat": "Must", "rating": "unknown", "text": "c"},
+            {"kat": "Nice", "rating": "no", "text": "d"},
+            {"kat": "Misc", "rating": "yes", "text": "e"}]
+    assert rules.calc_match(rows, "Must") == 75          # (100+100+25)/3
+    assert rules.calc_match(rows, "Nice") == 0
+    assert rules.calc_match([], "Nice") is None
+    # commercial rounding, half up (not banker's): (100+25)/2 = 62.5 -> 63
+    two = [{"kat": "Must", "rating": "yes", "text": "a"},
+           {"kat": "Must", "rating": "unknown", "text": "b"}]
+    assert rules.calc_match(two, "Must") == 63
+
+
+def test_build_description_exact_format():
+    rows = [{"kat": "Misc", "rating": "yes", "text": "Hybrid: 60 % remote"},
+            {"kat": "Must", "rating": "no", "text": "Mehrjährige LLM-Plattform-Erfahrung"},
+            {"kat": "Must", "rating": "yes", "text": "RAG-Systeme"},
+            {"kat": "Nice", "rating": "yes", "text": "vLLM"}]
+    text = rules.build_description(rules.order_rows(rows))
+    assert text == (
+        "Must-have-Match: 50 % · Nice-to-have-Match: 100 %\n"
+        "\n"
+        "| Nr. | Kat. | ❔ | Anforderung |\n"
+        "|---|---|---|---|\n"
+        "| 1 | Must | ❌ | Mehrjährige LLM-Plattform-Erfahrung |\n"
+        "| 2 | Must | ✅ | RAG-Systeme |\n"
+        "| 3 | Nice | ✅ | vLLM |\n"
+        "| 4 | Misc | ✅ | Hybrid: 60 % remote |")
+
+
+def test_empty_category_dash():
+    rows = [{"kat": "Must", "rating": "yes", "text": "a"}]
+    assert rules.build_description(rows).startswith(
+        "Must-have-Match: 100 % · Nice-to-have-Match: –")