trading-system-docs/tolaria/c4b-search-service/server.py

"""
TOLARIA SEARCH SERVICE — HTTP Server (C4B)
================================================================
Bietet:
  POST /api/search          — Suche (exact/keyword/metadata), Honest Mode
  GET  /api/search          — convenience (query/mode via query-params)
  GET  /api/search/health   — Search-Health (ehrlich: supported_modes)
  POST /api/search/rebuild  — Rebuild aus Forgejo-Source (kontrolliert)

Storage: derived rebuildbarer JSON-Index. Kein pgvector/Postgres (C4D).
Keine automatisch öffentliche Rebuild-Admin ohne Auth-Header. Vault-APIs bleiben
unangetastet (Backward-Compatibility).
"""

from __future__ import annotations

import json
import os
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from urllib.parse import urlparse, parse_qs

from search_api import TolariaSearch, SearchError, SUPPORTED_MODES

DATA_DIR = os.path.join(os.path.dirname(__file__), "data")
# C5D: Source-Pfad env-konfigurierbar. Default = bisheriger baked-in Pfad,
# aber C5D schreibt den frischen derived Snapshot an den konfigurierten Pfad.
SOURCE_JSON = os.environ.get("TOLARIA_SEARCH_SOURCE",
                             os.path.join(os.path.dirname(__file__), "index_source.json"))
INDEX_JSON = os.path.join(DATA_DIR, "search_index.json")
REBUILD_TOKEN = os.environ.get("TOLARIA_SEARCH_REBUILD_TOKEN", "")

engine = TolariaSearch(index_path=INDEX_JSON)


def load_or_rebuild():
    """Lädt persistierten Index oder rebuildet aus Source."""
    if os.path.exists(INDEX_JSON):
        try:
            with open(INDEX_JSON) as f:
                payload = json.load(f)
            # Rebuild in memory aus persistierten docs
            from search_engine import Doc
            docs = []
            for d in payload["docs"]:
                docs.append(Doc(
                    path=d["path"], title=d["title"], id=d.get("id"),
                    type=d.get("type"), role=d.get("role"),
                    representation=d.get("representation"), state=d.get("state"),
                    content_hash=d.get("content_hash", ""),
                    body=d.get("body", "") or "",
                    aliases=d.get("aliases", []), tags=d.get("tags", []),
                    derived_from=d.get("derived_from"),
                    is_legacy=d.get("is_legacy", False),
                ))
            engine.index.build(docs, secret_filter=True)
            engine.built_at = payload.get("built_at_ms")
            engine.source_head = payload.get("source_head")
            engine.object_count = payload.get("object_count", len(docs))
            engine.secret_blocked_objects = payload.get("secret_blocked", [])
            # C5D: Objekt-Set aus persistiertem Index wiederherstellen (Read-Back).
            engine.indexed_object_ids = payload.get("indexed_object_ids", [])
            engine.indexed_paths = payload.get("indexed_paths", [])
            return "loaded"
        except Exception as e:
            pass
    if os.path.exists(SOURCE_JSON):
        engine.rebuild_from_source(SOURCE_JSON)
        return "rebuilt"
    return "none"


def do_rebuild():
    return engine.rebuild_from_source(SOURCE_JSON)


class Handler(BaseHTTPRequestHandler):
    def log_message(self, fmt, *args):
        pass

    def _send(self, obj, code=200):
        body = json.dumps(obj, ensure_ascii=False).encode("utf-8")
        self.send_response(code)
        self.send_header("Content-Type", "application/json; charset=utf-8")
        self.send_header("Content-Length", str(len(body)))
        self.end_headers()
        self.wfile.write(body)

    def _read_json(self):
        length = int(self.headers.get("Content-Length", 0))
        if length <= 0:
            return {}
        try:
            return json.loads(self.rfile.read(length).decode("utf-8"))
        except Exception:
            return {}

    def do_GET(self):
        parsed = urlparse(self.path)
        if parsed.path == "/api/search":
            qs = parse_qs(parsed.query)
            req = {
                "query": qs.get("query", [""])[0],
                "mode": qs.get("mode", ["hybrid"])[0],
            }
            for k in ("limit", "offset"):
                if k in qs:
                    req[k] = int(qs[k][0])
            if "include_historical" in qs:
                req["include_historical"] = qs["include_historical"][0].lower() == "true"
            self._send(self._dispatch(req))
        elif parsed.path == "/api/search/health":
            self._send(engine.health())
        else:
            self._send({"error": {"code": "not_found", "reason": self.path}}, 404)

    def do_POST(self):
        parsed = urlparse(self.path)
        if parsed.path == "/api/search":
            self._send(self._dispatch(self._read_json()))
        elif parsed.path == "/api/search/rebuild":
            # kontrolliert: nur mit Token
            auth = self.headers.get("Authorization", "")
            expected = "Bearer " + REBUILD_TOKEN
            if not REBUILD_TOKEN or auth.strip() != expected:
                self._send({"error": {"code": "unauthorized", "reason": "rebuild requires token"}}, 403)
                return
            res = do_rebuild()
            self._send({"status": "ok", "rebuilt": res})
        else:
            self._send({"error": {"code": "not_found", "reason": self.path}}, 404)

    def _dispatch(self, req):
        try:
            return engine.search(req)
        except SearchError as e:
            return {"error": {"code": e.code, "reason": e.reason}}
        except Exception as e:
            return {"error": {"code": "internal_error", "reason": str(e)[:200]}}

    def _send(self, obj, code=200):
        body = json.dumps(obj, ensure_ascii=False).encode("utf-8")
        self.send_response(code)
        self.send_header("Content-Type", "application/json; charset=utf-8")
        self.send_header("Content-Length", str(len(body)))
        self.end_headers()
        self.wfile.write(body)


def main():
    load_or_rebuild()
    port = int(os.environ.get("TOLARIA_SEARCH_PORT", "8325"))
    httpd = ThreadingHTTPServer(("0.0.0.0", port), Handler)
    print(f"TOLARIA SEARCH SERVICE listening on :{port} (supported={SUPPORTED_MODES})",
          flush=True)
    httpd.serve_forever()


if __name__ == "__main__":
    from search_api import SUPPORTED_MODES
    main()