Protokoll #15686

{
    "event": "PreToolUse",
    "tool_name": "Write",
    "tool_input": {
        "file_path": "\/var\/www\/scripts\/pipeline\/step_load.py",
        "content": "\"\"\"\nLoad Step Module\nHandles database persistence operations for documents and chunks.\n\nPart of modularized pipeline architecture.\n\"\"\"\n\nimport json\n\n\nclass LoadStep:\n    \"\"\"Step: Load documents and chunks into database.\"\"\"\n\n    def __init__(self, db, progress=None):\n        \"\"\"\n        Initialize load step.\n\n        Args:\n            db: Database instance\n            progress: Optional PipelineProgress instance\n        \"\"\"\n        self.db = db\n        self.progress = progress\n\n    def create_document(self, file_info):\n        \"\"\"\n        Create document record in database.\n\n        Args:\n            file_info: Dict with path, name, type, size, hash\n\n        Returns:\n            int: Document ID\n        \"\"\"\n        doc_id = self.db.insert_document(\n            file_path=file_info[\"path\"],\n            title=file_info[\"name\"],\n            file_type=file_info[\"type\"],\n            file_size=file_info[\"size\"],\n            file_hash=file_info[\"hash\"],\n        )\n\n        self.db.log(\"INFO\", f\"Created document: {doc_id}\")\n\n        return doc_id\n\n    def store_chunks(self, doc_id, chunks):\n        \"\"\"\n        Store chunks in database.\n\n        Args:\n            doc_id: Document ID\n            chunks: List of chunk dictionaries\n\n        Returns:\n            list: Chunks with db_id added\n        \"\"\"\n        for i, chunk in enumerate(chunks):\n            chunk_id = self.db.insert_chunk(\n                doc_id=doc_id,\n                chunk_index=i,\n                content=chunk[\"content\"],\n                heading_path=json.dumps(chunk.get(\"heading_path\", [])),\n                position_start=chunk.get(\"position_start\", 0),\n                position_end=chunk.get(\"position_end\", 0),\n                metadata=json.dumps(chunk.get(\"metadata\", {})),\n            )\n            chunk[\"db_id\"] = chunk_id\n\n        return chunks\n\n    def update_document_status(self, doc_id, status):\n        \"\"\"\n        Update document processing status.\n\n        Args:\n            doc_id: Document ID\n            status: New status (processing, done, failed)\n        \"\"\"\n        self.db.update_document_status(doc_id, status)\n\n    def check_document_exists(self, file_path):\n        \"\"\"\n        Check if document already exists.\n\n        Args:\n            file_path: Path to file\n\n        Returns:\n            int|None: Document ID if exists, None otherwise\n        \"\"\"\n        return self.db.document_exists(file_path)\n\n    def check_document_done(self, file_path):\n        \"\"\"\n        Check if document is already fully processed.\n\n        Args:\n            file_path: Path to file\n\n        Returns:\n            bool: True if document is done\n        \"\"\"\n        return self.db.document_is_done(file_path)\n"
    }
}

{
    "tool_response": {
        "type": "create",
        "filePath": "\/var\/www\/scripts\/pipeline\/step_load.py",
        "content": "\"\"\"\nLoad Step Module\nHandles database persistence operations for documents and chunks.\n\nPart of modularized pipeline architecture.\n\"\"\"\n\nimport json\n\n\nclass LoadStep:\n    \"\"\"Step: Load documents and chunks into database.\"\"\"\n\n    def __init__(self, db, progress=None):\n        \"\"\"\n        Initialize load step.\n\n        Args:\n            db: Database instance\n            progress: Optional PipelineProgress instance\n        \"\"\"\n        self.db = db\n        self.progress = progress\n\n    def create_document(self, file_info):\n        \"\"\"\n        Create document record in database.\n\n        Args:\n            file_info: Dict with path, name, type, size, hash\n\n        Returns:\n            int: Document ID\n        \"\"\"\n        doc_id = self.db.insert_document(\n            file_path=file_info[\"path\"],\n            title=file_info[\"name\"],\n            file_type=file_info[\"type\"],\n            file_size=file_info[\"size\"],\n            file_hash=file_info[\"hash\"],\n        )\n\n        self.db.log(\"INFO\", f\"Created document: {doc_id}\")\n\n        return doc_id\n\n    def store_chunks(self, doc_id, chunks):\n        \"\"\"\n        Store chunks in database.\n\n        Args:\n            doc_id: Document ID\n            chunks: List of chunk dictionaries\n\n        Returns:\n            list: Chunks with db_id added\n        \"\"\"\n        for i, chunk in enumerate(chunks):\n            chunk_id = self.db.insert_chunk(\n                doc_id=doc_id,\n                chunk_index=i,\n                content=chunk[\"content\"],\n                heading_path=json.dumps(chunk.get(\"heading_path\", [])),\n                position_start=chunk.get(\"position_start\", 0),\n                position_end=chunk.get(\"position_end\", 0),\n                metadata=json.dumps(chunk.get(\"metadata\", {})),\n            )\n            chunk[\"db_id\"] = chunk_id\n\n        return chunks\n\n    def update_document_status(self, doc_id, status):\n        \"\"\"\n        Update document processing status.\n\n        Args:\n            doc_id: Document ID\n            status: New status (processing, done, failed)\n        \"\"\"\n        self.db.update_document_status(doc_id, status)\n\n    def check_document_exists(self, file_path):\n        \"\"\"\n        Check if document already exists.\n\n        Args:\n            file_path: Path to file\n\n        Returns:\n            int|None: Document ID if exists, None otherwise\n        \"\"\"\n        return self.db.document_exists(file_path)\n\n    def check_document_done(self, file_path):\n        \"\"\"\n        Check if document is already fully processed.\n\n        Args:\n            file_path: Path to file\n\n        Returns:\n            bool: True if document is done\n        \"\"\"\n        return self.db.document_is_done(file_path)\n",
        "structuredPatch": [],
        "originalFile": null
    }
}