#!/usr/bin/env python3
"""
Ingest downloaded TRBS/TRGS/ASR PDFs into Qdrant via RAG Service.

Reads the source_registry.json and uploads each PDF to the RAG service.

Usage:
  python3 ingest_to_qdrant.py                    # ingest all
  python3 ingest_to_qdrant.py --category trbs    # only TRBS
  python3 ingest_to_qdrant.py --dry-run           # list without uploading
"""

import argparse
import json
import logging
import time
from pathlib import Path

import httpx

logging.basicConfig(
    level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s"
)
logger = logging.getLogger("ingest-trbs")

REGISTRY_FILE = Path(__file__).parent / "source_registry.json"
RAG_URL = "https://macmini:8097/api/v1/documents/upload"
COLLECTION = "bp_compliance_ce"  # Same collection as other CE documents


def ingest_pdf(entry: dict) -> dict:
    """Upload a single PDF to the RAG service."""
    local_path = entry.get("local_path", "")
    if not local_path or not Path(local_path).exists():
        return {"status": "skipped", "reason": "no local file"}

    pdf_path = Path(local_path)
    category = entry.get("category", "unknown")
    filename = entry.get("filename", pdf_path.name)
    title = entry.get("title", filename)

    metadata = {
        "source": title,
        "regulation_id": f"{category}_{filename}".lower().replace("-", "_"),
        "jurisdiction": "DE",
        "source_type": "technical_rule",
        "license_rule": 1,
        "category": category,
        "legal_basis": entry.get("legal_basis", ""),
    }

    try:
        with open(pdf_path, "rb") as f:
            files = {"file": (pdf_path.name, f, "application/pdf")}
            data = {
                "collection": COLLECTION,
                "data_type": "legal",
                "use_case": "compliance",
                "year": "2026",
                "chunk_size": "512",
                "chunk_overlap": "50",
                "metadata_json": json.dumps(metadata),
            }
            resp = httpx.post(RAG_URL, files=files, data=data, timeout=300.0, verify=False)
            resp.raise_for_status()
            result = resp.json()
            return {
                "status": "ok",
                "document_id": result.get("document_id", ""),
                "chunks": result.get("chunks_count", 0),
            }
    except Exception as e:
        return {"status": "error", "reason": str(e)}


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--category", choices=["trbs", "trgs", "asr"])
    parser.add_argument("--dry-run", action="store_true")
    args = parser.parse_args()

    registry = json.loads(REGISTRY_FILE.read_text())
    if args.category:
        registry = [e for e in registry if e.get("category") == args.category]

    logger.info("Ingesting %d documents into Qdrant (%s)", len(registry), COLLECTION)

    total_ok = 0
    total_chunks = 0
    total_err = 0

    for i, entry in enumerate(registry):
        if not entry.get("local_path"):
            continue

        if args.dry_run:
            logger.info("[%d/%d] %s — %s (dry-run)",
                        i + 1, len(registry), entry["filename"], entry.get("title", "")[:60])
            continue

        logger.info("[%d/%d] %s", i + 1, len(registry), entry["filename"])
        result = ingest_pdf(entry)

        if result["status"] == "ok":
            total_ok += 1
            total_chunks += result["chunks"]
            logger.info("  → %d chunks indexed", result["chunks"])
        else:
            total_err += 1
            logger.error("  → %s: %s", result["status"], result.get("reason", ""))

        time.sleep(1)  # Be gentle

    logger.info("\nDone: %d OK (%d chunks), %d errors, %d total",
                total_ok, total_chunks, total_err, len(registry))


if __name__ == "__main__":
    main()