Excluded Docling blocks

这里是差集：Docling 全量解析 text block 减去最终会进入正文的 block。优先人工检查 risk=high / medium。

layout_review.html excluded_blocks.json excluded_blocks.tsv final_body_blocks.tsv visual_assets.tsv original.pdf

Diff Summary

{
  "parsed_text_blocks": 242,
  "final_body_blocks": 44,
  "excluded_blocks": {
    "count": 198,
    "by_reason": {
      "outside_body_flow_list_item": 79,
      "outside_body_flow_body_candidate": 29,
      "docling_page_footer": 21,
      "docling_page_header": 21,
      "body_heading": 19,
      "empty_after_cleaning": 8,
      "docling_caption": 5,
      "outside_body_flow_caption": 5,
      "docling_footnote": 4,
      "inside_front_matter": 2,
      "outside_body_flow": 2,
      "before_body_started": 1,
      "non_body_heading": 1,
      "outside_body_flow_page_header": 1
    },
    "by_role_guess": {
      "unknown_text": 87,
      "body_candidate_excluded": 34,
      "page_header": 22,
      "page_footer": 21,
      "body_heading": 19,
      "caption": 10,
      "footnote": 4,
      "title_candidate": 1
    },
    "by_risk_level": {
      "high": 94,
      "low": 78,
      "medium": 26
    },
    "high_risk_count": 94,
    "medium_risk_count": 26
  },
  "char_counts": {
    "parsed_text_chars": 29928,
    "final_body_chars": 14975,
    "excluded_chars": 14953
  }
}

Truncation

{
  "truncated": false,
  "message": "",
  "truncated_block_count": 0
}

Excluded Page Overlays

这些框显示被排除块，同时叠加真实图表资产框。青色虚线表示该 text block 被图表资产 caption 吸收；红色 STOP 是截断触发点，红色框是截断后被排除的块。

Page 1

Page 2

Page 3

Page 4

Page 5

Page 6

Page 7

Page 8

Page 9

Page 10

Page 11

Visual Assets

这是实际图表资产输出，不是审计层重新推断。

Excluded Blocks