{
"event": "PreToolUse",
"tool_name": "Read",
"tool_input": {
"file_path": "\/var\/www\/scripts\/pipeline\/analyzers\/entity_extractor.py",
"offset": 1,
"limit": 50
}
}
{
"tool_response": {
"type": "text",
"file": {
"filePath": "\/var\/www\/scripts\/pipeline\/analyzers\/entity_extractor.py",
"content": "\"\"\"\nEntity Extraction - Extract and store entities from text.\n\"\"\"\n\nimport json\nimport re\nimport sys\nimport time\nimport unicodedata\n\nimport requests\n\nsys.path.insert(0, \"\/var\/www\/scripts\/pipeline\")\n\nfrom config import ANTHROPIC_MODEL, OLLAMA_HOST\nfrom db import db\nfrom protokoll import protokoll\n\n\ndef normalize_name(name: str) -> str:\n \"\"\"Generate canonical_name from entity name.\n\n Rules:\n - Lowercase\n - German umlauts: ä→ae, ö→oe, ü→ue, ß→ss\n - Replace spaces with underscores\n - Remove special characters except underscores\n - Collapse multiple underscores\n \"\"\"\n if not name:\n return \"\"\n\n result = name.lower()\n\n replacements = {\n \"ä\": \"ae\", \"ö\": \"oe\", \"ü\": \"ue\", \"ß\": \"ss\",\n \"Ä\": \"ae\", \"Ö\": \"oe\", \"Ü\": \"ue\",\n }\n for old, new in replacements.items():\n result = result.replace(old, new)\n\n result = unicodedata.normalize(\"NFKD\", result)\n result = result.encode(\"ascii\", \"ignore\").decode(\"ascii\")\n result = re.sub(r\"[\\s\\-]+\", \"_\", result)\n result = re.sub(r\"[^a-z0-9_]\", \"\", result)\n result = re.sub(r\"_+\", \"_\", result)\n result = result.strip(\"_\")\n\n return result\n",
"numLines": 50,
"startLine": 1,
"totalLines": 444
}
}
}