normalizer-audit.json 904 B

12345678910111213141516171819202122232425262728293031323334353637
  1. {
  2. "generatedAt": "2026-04-29T13:10:23.898Z",
  3. "inputDir": "E:\\workspace\\openclaw-voc-skill\\demo\\xiaohongshu",
  4. "outputDir": "E:\\workspace\\openclaw-voc-skill\\demo\\xiaohongshu\\normalized",
  5. "files": [
  6. "raw-comments.json",
  7. "raw-notes.json"
  8. ],
  9. "sources": [
  10. {
  11. "file": "raw-comments.json",
  12. "platform": "xiaohongshu",
  13. "itemCount": 0,
  14. "commentCount": 105
  15. },
  16. {
  17. "file": "raw-notes.json",
  18. "platform": "xiaohongshu",
  19. "itemCount": 30,
  20. "commentCount": 0
  21. }
  22. ],
  23. "rawItemCount": 30,
  24. "rawVocCount": 105,
  25. "validItemCount": 30,
  26. "validVocCount": 105,
  27. "duplicateItemCount": 0,
  28. "duplicateVocCount": 0,
  29. "emptyItemDroppedCount": 0,
  30. "emptyVocDroppedCount": 0,
  31. "missingRequired": {
  32. "items": [],
  33. "comments": []
  34. },
  35. "errors": [],
  36. "dedupeRule": "platform + id/commentId + first 120 normalized text characters"
  37. }