Protokoll #17460

{
    "event": "PostToolUse",
    "tool_name": "Read",
    "tool_response": {
        "type": "text",
        "file": {
            "filePath": "\/var\/www\/scripts\/pipeline\/semantic_chunk_analyzer.py",
            "content": "#!\/usr\/bin\/env python3\n\"\"\"\nSemantic Chunk Analyzer - Chunk-Level Semantic Analysis Pipeline\n\nAnalysiert Chunks aus der ki_system.chunks Tabelle und befüllt:\n- chunk_semantics (summary, keywords, sentiment, topics, language)\n- entities (extrahierte Entitäten)\n- chunk_entities (Verknüpfung Chunk <-> Entity)\n- entity_relations (Beziehungen zwischen Entitäten)\n- taxonomy_terms + chunk_taxonomy (Kategorisierung)\n\nBACKWARD COMPATIBILITY WRAPPER - Logic moved to semantic_chunk\/ package.\n\nUsage:\n    python semantic_chunk_analyzer.py analyze [--limit N]\n    python semantic_chunk_analyzer.py status\n    python semantic_chunk_analyzer.py reset\n\"\"\"\n\nimport sys\n\nfrom db import db\n\n# Re-export for backward compatibility\nfrom semantic_chunk import (\n    ANALYSIS_MODEL,\n    BATCH_SIZE,\n    ChunkRepository,\n    ChunkSemantics,\n    Entity,\n    EntityExtractor,\n    EntityRepository,\n    OllamaService,\n    Relation,\n    RelationExtractor,\n    SemanticChunkPipeline,\n    SemanticsAnalyzer,\n    SemanticsRepository,\n    TaxonomyClassifier,\n    TaxonomyRepository,\n)\n\n__all__ = [\n    \"ChunkSemantics\",\n    \"Entity\",\n    \"Relation\",\n    \"OllamaService\",\n    \"ANALYSIS_MODEL\",\n    \"SemanticsAnalyzer\",\n    \"EntityExtractor\",\n    \"RelationExtractor\",\n    \"TaxonomyClassifier\",\n    \"ChunkRepository\",\n    \"SemanticsRepository\",\n    \"EntityRepository\",\n    \"TaxonomyRepository\",\n    \"SemanticChunkPipeline\",\n    \"BATCH_SIZE\",\n]\n\n\ndef main():\n    \"\"\"CLI Entry Point.\"\"\"\n    if len(sys.argv) < 2:\n        print(__doc__)\n        return\n\n    command = sys.argv[1].lower()\n\n    db.connect()\n\n    try:\n        pipeline = SemanticChunkPipeline()\n\n        if command == \"analyze\":\n            limit = BATCH_SIZE\n            if len(sys.argv) > 2 and sys.argv[2] == \"--limit\":\n                limit = int(sys.argv[3]) if len(sys.argv) > 3 else BATCH_SIZE\n\n            result = pipeline.run(limit)\n            print(f\"\\nErgebnis: {result['success']}\/{result['processed']} erfolgreich\")\n\n        elif command == \"status\":\n            stats = pipeline.status()\n            print(f\"Chunks gesamt: {stats['total']}\")\n            print(f\"Analysiert:    {stats['analyzed']}\")\n            print(f\"Entitäten:     {stats['entities']}\")\n            print(f\"Ausstehend:    {stats['total'] - stats['analyzed']}\")\n\n        elif command == \"reset\":\n            confirm = input(\"Alle Semantik-Daten löschen? (ja\/nein): \")\n            if confirm.lower() == \"ja\":\n                for table in [\n                    \"chunk_semantics\",\n                    \"chunk_entities\",\n                    \"chunk_taxonomy\",\n                    \"entity_relations\",\n                    \"entities\",\n                    \"taxonomy_terms\",\n                ]:\n                    db.execute(f\"TRUNCATE TABLE {table}\")\n                    db.commit()\n                print(\"Alle Semantik-Tabellen geleert.\")\n\n        else:\n            print(f\"Unbekannter Befehl: {command}\")\n            print(__doc__)\n\n    except Exception as e:\n        db.log(\"ERROR\", f\"Pipeline error: {e}\")\n        print(f\"Fehler: {e}\")\n        raise\n    finally:\n        db.disconnect()\n\n\nif __name__ == \"__main__\":\n    main()\n",
            "numLines": 119,
            "startLine": 1,
            "totalLines": 119
        }
    }
}

-