transpordi_artiklid/check_weaviate.py

# check_weaviate.py
import json
import re
import weaviate  
from src.weaviate_client import WeaviateClient
import sys

sys.path.insert(0, './src')

def parse_transport_context(context_data):
    """Parsi transpordikonteksti JSON-ist loetavaks"""
    if isinstance(context_data, str):
        # Proovi parsida string JSON-iks
        try:
            context_data = json.loads(context_data)
        except json.JSONDecodeError:
            # Kui ei õnnestu, tagasta algne string
            return context_data
    
    if isinstance(context_data, dict):
        # Kontrolli, kas on "analysis" väli
        analysis_text = context_data.get('analysis', '')
        relevance_score = context_data.get('relevance_score', 'N/A')
        
        # Eemalda markdowni koodiblokid (```json ja ```)
        analysis_text = re.sub(r'^```json\s*', '', analysis_text, flags=re.IGNORECASE)
        analysis_text = re.sub(r'\s*```$', '', analysis_text)
        
        # Proovi parsida analysis JSON-iks
        try:
            analysis_data = json.loads(analysis_text.strip())
            return {
                'theoretical_contribution': analysis_data.get('theoretical_contribution', ''),
                'practical_applicability': analysis_data.get('practical_applicability', ''),
                'problem_solving': analysis_data.get('problem_solving', ''),
                'limitations': analysis_data.get('limitations', ''),
                'relevance_score': relevance_score,
                'original_relevance': analysis_data.get('relevance_score', 'N/A')
            }
        except json.JSONDecodeError:
            # Kui ei õnnestu parsida, tagasta algne tekst
            return {
                'raw_analysis': analysis_text[:200] + '...' if len(analysis_text) > 200 else analysis_text,
                'relevance_score': relevance_score
            }
    
    return context_data

def format_context_for_display(parsed_context):
    """Vorminda parsitud kontekst ilusaks kuvamiseks"""
    if isinstance(parsed_context, dict):
        formatted = []
        
        if 'theoretical_contribution' in parsed_context:
            formatted.append("📚 TEOREETILINE PANUS:")
            formatted.append(f"   {parsed_context['theoretical_contribution'][:300]}...")
            formatted.append("")
        
        if 'practical_applicability' in parsed_context:
            formatted.append("🔧 PRAKTILINE RAKENDATAVUS:")
            formatted.append(f"   {parsed_context['practical_applicability'][:300]}...")
            formatted.append("")
        
        if 'problem_solving' in parsed_context:
            formatted.append("🎯 PROBLEEMILAHDUS:")
            formatted.append(f"   {parsed_context['problem_solving'][:300]}...")
            formatted.append("")
        
        if 'limitations' in parsed_context:
            formatted.append("⚠️ PIIRANGUD:")
            formatted.append(f"   {parsed_context['limitations'][:300]}...")
            formatted.append("")
        
        formatted.append(f"⭐ RELEVANTSUSE SKOOR: {parsed_context.get('relevance_score', 'N/A')}")
        
        if 'original_relevance' in parsed_context:
            formatted.append(f"   (Algne skoor: {parsed_context['original_relevance']})")
        
        return "\n".join(formatted)
    else:
        return str(parsed_context)[:500] + "..." if len(str(parsed_context)) > 500 else str(parsed_context)

def main():
    client = WeaviateClient()
    
    try:
        collection = client.client.collections.get("ScientificArticle")
        
        # Loendi kokku
        count_response = collection.aggregate.over_all(total_count=True)
        total = count_response.total_count
        print(f"\n✅ Weaviate'is on {total} artiklit.")
        
        # Võta mõni näidis välja
        if total > 0:
            print("\n📄 ESIMESED 3 ARTIKLIT:")
            print("=" * 80)
            response = collection.query.fetch_objects(limit=3)
            
            for i, obj in enumerate(response.objects):
                print(f"\n{i+1}. ID: {obj.properties.get('article_id', 'N/A')}")
                print(f"   📝 Pealkiri: {obj.properties.get('title', 'N/A')}")
                print(f"   👥 Autorid: {', '.join(obj.properties.get('authors', ['N/A']))}")
                print(f"   📅 Aasta: {obj.properties.get('year', 'N/A')}")
                print(f"   📖 Ajakiri: {obj.properties.get('journal', 'N/A')}")
                
                doi = obj.properties.get('doi', '')
                if doi:
                    print(f"   🔗 DOI: https://doi.org/{doi}")
                
                # Töötle konteksti
                context = obj.properties.get('transport_context', '')
                if context:
                    print("\n   🚗 TRANSPORDI KONTEKST:")
                    print("   " + "-" * 50)
                    
                    parsed_context = parse_transport_context(context)
                    formatted_context = format_context_for_display(parsed_context)
                    
                    # Prindi rea kaupa, et oleks loetavam
                    for line in formatted_context.split('\n'):
                        print(f"   {line}")
                
                print(f"\n   🏷️ Võtmesõnad: {', '.join(obj.properties.get('key_concepts', ['N/A']))}")
                print(f"   📊 Meetodid: {', '.join(obj.properties.get('methods_used', ['N/A']))}")
                
                if i < len(response.objects) - 1:
                    print("\n" + "-" * 80)
        
        # Näita lisastatistikat
        print(f"\n📊 STATISTIKA:")
        print(f"   • Artikleid kokku: {total}")
        
        # Kui on rohkem kui 3 artiklit, näita lisavalikuid
        if total > 3:
            print(f"\n🔍 SOOVIKSID VAADATA:")
            print("   1. Viimaseid lisatud artikleid")
            print("   2. Kõrgeima relevantsusega artikleid")
            print("   3. Kindla autoriga artikleid")
            print("   4. Kindla aastaga artikleid")
            
            valik = input("\nVali number (vajuta Enter jätkamiseks): ")
            
            if valik == "1":
                response = collection.query.fetch_objects(
                    limit=3,
                    sort=weaviate.classes.query.Sort.by_property("processing_date", ascending=False)
                )
                print("\n⏰ VIIMASED 3 ARTIKLIT:")
                for obj in response.objects:
                    print(f"   • {obj.properties.get('title', 'N/A')}")
                    print(f"     (Lisatud: {obj.properties.get('processing_date', 'N/A')})")
                    print()
            
            elif valik == "2":
                response = collection.query.fetch_objects(
                    limit=3,
                    sort=weaviate.classes.query.Sort.by_property("relevance_score", ascending=False)
                )
                print("\n⭐ KÕRGEIMA RELEVANTSUSEGA ARTIKLID:")
                for obj in response.objects:
                    print(f"   • {obj.properties.get('title', 'N/A')}")
                    print(f"     (Relevantsus: {obj.properties.get('relevance_score', 'N/A')}/10)")
                    print()
        
    except Exception as e:
        print(f"\n❌ VIGA: {e}")
        import traceback
        traceback.print_exc()
    finally:
        client.close()
        print("\n👋 Ühendus Weaviate'iga suletud.")

if __name__ == "__main__":
    main()