docs: search plan + counters for v1.2.0; tools/search-parity (parity + latency vs a brute-force reference)

tools/search-parity/parity.py

@@ -0,0 +1,178 @@
+"""Search parity check for the meta-core Redis -> SQLite cut-over.
+
+  parity.py <meta-core.db>
+
+Builds a query set from real records, computes the EXPECTED result of each
+query by brute force — one streaming pass over every record in the database,
+evaluated with a line-by-line port of the Go matchers (api.recordMatchesFilter,
+api.matchAllTokens, storage.Haystack) — and diffs it against what the live
+POST /api/metadata/search returns. A miss means the SQL candidate superset
+dropped a real match; that is the failure this exists to catch.
+"""
+import json, random, sqlite3, sys, time, urllib.request
+
+BASE = "http://127.0.0.1:9000"
+LIMIT = 2000
+DB = sys.argv[1]
+
+
+def post(body):
+    req = urllib.request.Request(BASE + "/api/metadata/search", data=json.dumps(body).encode(),
+                                 headers={"Content-Type": "application/json"})
+    t0 = time.time()
+    with urllib.request.urlopen(req, timeout=300) as resp:
+        data = json.load(resp)
+    return [r["hashId"] for r in data["results"]], time.time() - t0
+
+
+SEARCH_FIELDS = ["title", "fileName", "originaltitle", "showtitle", "filePath"]
+
+
+def haystack(f):
+    parts = [f[k].lower() for k in SEARCH_FIELDS if f.get(k)]
+    names = []
+    for k, v in f.items():
+        if k.startswith("titles/") and v not in ("", "false"):
+            rest = k[len("titles/"):]
+            if "/" in rest:
+                name = rest.split("/", 1)[1]
+                if name:
+                    names.append(name.replace("∕", "/"))
+    parts += [n.lower() for n in sorted(names)]
+    return "".join(p + "\n" for p in parts)
+
+
+def truthy(v):
+    v = (v or "").strip().lower()
+    return v not in ("", "false", "0")
+
+
+def match_filter(f, flt):
+    values = [v.strip() for v in flt.get("values", []) if v.strip()]
+    prop = flt["property"]
+    if not prop or not values:
+        return True
+    for v in values:
+        if truthy(f.get(prop + "/" + v)):
+            return True
+    wanted = {v.lower() for v in values}
+    prefix = prop.lower() + "/"
+    for k, val in f.items():
+        if len(k) > len(prefix) and k[:len(prefix)].lower() == prefix:
+            if k[len(prefix):].lower() in wanted and truthy(val):
+                return True
+    if prop not in f:
+        return False
+    for piece in f[prop].split(","):
+        piece = piece.strip()
+        if not piece:
+            continue
+        for v in values:
+            if flt.get("exact"):
+                if piece.lower() == v.lower():
+                    return True
+            elif v.lower() in piece.lower():
+                return True
+    return False
+
+
+def match(rid, f, q):
+    query = q.get("query", "")
+    if query:
+        tokens = query.lower().split()
+        hay = haystack(f)
+        if not all(t in hay for t in tokens) and query.lower() not in rid.lower():
+            return False
+    return all(match_filter(f, flt) for flt in q.get("filters", []))
+
+
+def records(db):
+    cur = db.execute("SELECT k, v FROM kv WHERE k >= 'file:' AND k < 'file;' ORDER BY k")
+    rid, fields = None, {}
+    for k, v in cur:
+        r, sep, field = k[5:].partition("/")
+        if not sep or not field:
+            continue
+        if r != rid:
+            if rid is not None:
+                yield rid, fields
+            rid, fields = r, {}
+        fields[field] = v
+    if rid is not None:
+        yield rid, fields
+
+
+def build_queries(db):
+    random.seed(7)
+    roots = [r for (r,) in db.execute("SELECT substr(k, 11) FROM kv WHERE k >= 'idx:roots/' AND k < 'idx:roots0'")]
+    sample = []
+    for rid in random.sample(roots, 80):
+        f = {k[len(rid) + 6:]: v for k, v in db.execute(
+            "SELECT k, v FROM kv WHERE k >= ? AND k < ?", (f"file:{rid}/", f"file:{rid}0"))}
+        sample.append(f)
+    qs = [{}]
+    for fld in ("fileType", "contentKind", "domain", "workForm", "videoType", "provenance", "quality", "indexer"):
+        for v in sorted({m[fld] for m in sample if m.get(fld)})[:3]:
+            qs.append({"filters": [{"property": fld, "values": [v], "exact": True}]})
+            qs.append({"filters": [{"property": fld, "values": [v.upper()[:3]]}]})
+    for m in sample[:30]:
+        for k in sorted(m):
+            if k.startswith(("genres/", "categories/", "source/", "titles/")) and k.count("/") == 1:
+                p, v = k.split("/", 1)
+                qs.append({"filters": [{"property": p, "values": [v.lower()]}]})
+                break
+        for idf in ("tmdbid", "imdbid", "season"):
+            if m.get(idf):
+                qs.append({"filters": [{"property": idf, "values": [m[idf]], "exact": True}]})
+        words = (m.get("title") or "").split()
+        if words:
+            w = max(words, key=len)
+            qs.append({"query": w})
+            qs.append({"query": w[:2]})
+            qs.append({"query": " ".join(words[:2])})
+            if m.get("fileType"):
+                qs.append({"query": w, "filters": [{"property": "fileType", "values": [m["fileType"]]}]})
+    for m in sample[30:45]:
+        words = (m.get("title") or "").split()
+        if words and m.get("contentKind"):
+            qs.append({"query": max(words, key=len), "filters": [{"property": "contentKind", "values": [m["contentKind"]], "exact": True}]})
+            qs.append({"query": max(words, key=len), "filters": [{"property": "fileType", "values": ["video"]}, {"property": "contentKind", "values": [m["contentKind"]]}]})
+    qs += [{"query": "s01e01"}, {"query": "1080p", "filters": [{"property": "fileType", "values": ["video"], "exact": True}]},
+           {"filters": [{"property": "genres", "values": ["action", "comedy"]}, {"property": "fileType", "values": ["video"], "exact": True}]}]
+    for q in qs:
+        q["limit"] = LIMIT
+    return qs
+
+
+def main():
+    db = sqlite3.connect(f"file:{DB}?mode=ro", uri=True)
+    qs = build_queries(db)
+    print(f"{len(qs)} queries; computing reference over every record...", flush=True)
+    t0 = time.time()
+    expected = [[] for _ in qs]
+    n = 0
+    for rid, f in records(db):
+        n += 1
+        for i, q in enumerate(qs):
+            if match(rid, f, q):
+                expected[i].append(rid)
+    print(f"reference: {n} records in {time.time() - t0:.0f}s", flush=True)
+
+    bad = 0
+    for q, exp in zip(qs, expected):
+        exp = sorted(exp)[:LIMIT]
+        got, secs = post(q)
+        lost, extra = set(exp) - set(got), set(got) - set(exp)
+        order_ok = got == sorted(got)
+        status = "OK  " if not lost and not extra and order_ok else "DIFF"
+        bad += status != "OK  "
+        print(f"{status} want={len(exp):5d} got={len(got):5d} lost={len(lost):4d} extra={len(extra):4d} "
+              f"{secs*1000:7.1f}ms  {json.dumps({k: v for k, v in q.items() if k != 'limit'})[:100]}", flush=True)
+        if lost:
+            print("     lost e.g.", sorted(lost)[:4])
+        if extra:
+            print("     extra e.g.", sorted(extra)[:4])
+    print(f"\n{bad} of {len(qs)} queries differ")
+
+
+main()