#!/usr/bin/env python3
"""Phase 0 extraction test."""

import sys
import time
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent / "ontology_platform"))

from ont_platform.core.extractors.web_extractor import extract_web_content
from ont_platform.core.extraction.lightweight_extractor import LightweightExtractor


def test_extraction(url: str):
    """Test Phase 0 extraction."""
    print(f"\nURL: {url}\n")

    start = time.time()

    try:
        print("1. Extracting content with Trafilatura...")
        extracted = extract_web_content(url=url)
        print(f"   Title: {extracted.title}")
        print(f"   Length: {len(extracted.text)} chars")

        print("\n2. Extracting JSON candidates...")
        extractor = LightweightExtractor(use_llm=False)
        result = extractor.extract(
            text=extracted.text,
            project_id="test",
            document_id="test",
        )

        elapsed = time.time() - start

        print(f"   Entities: {len(result.entities)}")
        print(f"   Relations: {len(result.relations)}")
        print(f"   Time: {elapsed:.2f}s")

        if result.entities:
            print(f"\n   Top entities:")
            for e in result.entities[:3]:
                print(f"   - {e['label']} ({e['type']}) [{e['confidence']}]")

        if elapsed <= 30:
            print(f"\nSUCCESS: {elapsed:.2f}s <= 30s target")
            return True
        else:
            print(f"\nFAIL: {elapsed:.2f}s > 30s target")
            return False

    except Exception as e:
        print(f"ERROR: {e}")
        import traceback
        traceback.print_exc()
        return False


if __name__ == "__main__":
    url = sys.argv[1] if len(sys.argv) > 1 else "https://example.com"
    success = test_extraction(url)
    sys.exit(0 if success else 1)