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

projekt-matching/projektmatch/rules.py

@@ -0,0 +1,106 @@
+"""Deterministic rules: Misc evaluation, match calculation, description markdown.
+
+Replicates SKILL.md Schritt 3b/4/5. No LLM here — the numbers written to the
+CRM must never be hallucinated.
+"""
+from __future__ import annotations
+
+import datetime as dt
+import json
+import urllib.parse
+import urllib.request
+from math import asin, cos, radians, sin, sqrt
+
+SAUERLACH = (47.9721357, 11.6528398)
+NOMINATIM_UA = "projekt-matching/1.0 (Thomas.Langer@destengs.com)"
+
+YES, NO, UNKNOWN = "yes", "no", "unknown"
+SYMBOL = {YES: "✅", NO: "❌", UNKNOWN: "❔"}
+RATING_VALUE = {YES: 100, UNKNOWN: 25, NO: 0}
+KAT_ORDER = {"Must": 0, "Nice": 1, "Misc": 2}
+
+
+def geocode(place: str):
+    """Nominatim lookup -> (lat, lon) or None. Policy: max 1 request/s."""
+    url = "https://nominatim.openstreetmap.org/search?" + urllib.parse.urlencode(
+        {"q": place, "format": "json", "countrycodes": "de", "limit": 1})
+    req = urllib.request.Request(url, headers={"User-Agent": NOMINATIM_UA})
+    data = json.load(urllib.request.urlopen(req, timeout=20))
+    return (float(data[0]["lat"]), float(data[0]["lon"])) if data else None
+
+
+def distance_to_sauerlach_km(place: str, geocode_fn=geocode):
+    """Haversine distance; None on geocoding failure/ambiguity."""
+    try:
+        pos = geocode_fn(place)
+    except Exception:
+        return None
+    if pos is None:
+        return None
+    dlat = radians(pos[0] - SAUERLACH[0])
+    dlon = radians(pos[1] - SAUERLACH[1])
+    h = (sin(dlat / 2) ** 2
+         + cos(radians(SAUERLACH[0])) * cos(radians(pos[0])) * sin(dlon / 2) ** 2)
+    return 2 * 6371 * asin(sqrt(h))
+
+
+def eval_misc(item: dict, today: dt.date, geocode_fn=geocode) -> str:
+    kind = item.get("miscType") or "other"
+    if kind == "security":
+        return NO                          # K.-o.-Kriterium (SÜ dauert >= 3 Monate)
+    if kind == "start":
+        iso = item.get("startDate")
+        if not iso:
+            return UNKNOWN
+        try:
+            start = dt.date.fromisoformat(iso)
+        except ValueError:
+            return UNKNOWN
+        return YES if start <= today + dt.timedelta(days=56) else NO
+    if kind == "workload":
+        pct = item.get("workloadPercent")
+        if pct is None:
+            return UNKNOWN
+        return YES if 75 <= pct <= 100 else UNKNOWN
+    if kind == "duration":
+        return YES
+    if kind == "location":
+        if item.get("remotePercent") == 100:
+            return YES
+        place = item.get("onsiteLocation")
+        if not place:
+            return NO                      # Einsatzort/Remote-Anteil unklar
+        km = distance_to_sauerlach_km(place, geocode_fn)
+        if km is None:
+            return UNKNOWN
+        if km <= 50:
+            return YES
+        if km <= 60:
+            return UNKNOWN
+        return NO
+    return UNKNOWN
+
+
+def calc_match(rows: list, kat: str):
+    vals = [RATING_VALUE[r["rating"]] for r in rows if r["kat"] == kat]
+    if not vals:
+        return None
+    return int(sum(vals) / len(vals) + 0.5)    # half-up, not banker's rounding
+
+
+def fmt_match(value):
+    return "–" if value is None else f"{value} %"
+
+
+def order_rows(rows: list) -> list:
+    return sorted(rows, key=lambda r: KAT_ORDER[r["kat"]])   # stable sort
+
+
+def build_description(rows: list) -> str:
+    """rows already ordered Must -> Nice -> Misc (use order_rows)."""
+    must, nice = calc_match(rows, "Must"), calc_match(rows, "Nice")
+    lines = [f"Must-have-Match: {fmt_match(must)} · Nice-to-have-Match: {fmt_match(nice)}",
+             "", "| Nr. | Kat. | ❔ | Anforderung |", "|---|---|---|---|"]
+    for i, r in enumerate(rows, 1):
+        lines.append(f"| {i} | {r['kat']} | {SYMBOL[r['rating']]} | {r['text']} |")
+    return "\n".join(lines)