kind: page_index
display_name: PageIndex — Hierarchical table of contents
config:
  kind: page_index
  entity:
    description: >-
      You are a robust Table-of-Contents (TOC) extractor.
    fields:
      - type: title
        description: the heading text (clean, no page numbers or leader dots)
        rule: |
          - Length restriction:
              • Chinese heading: ≤25 characters
              • English heading: ≤80 characters
          - "title" must be non-empty (or exactly "-1").
          - If any part of a chunk has no valid heading, output that part as {"title":"-1", ...}.
          - If a chunk contains multiple headings, expand them in order:
              - Each heading → {"title":"...","chunk_id":"<chunk_ID>"}.
          - When ambiguous, prefer "-1" unless the text strongly looks like a heading.
          - Keep language of "title" the same as the input.
          - Prefix like following must be titles: 第x章, 第N条, 第N节, 1, 1.1, 1.1.1 ...
  relation:
    description: >-
      You are an expert logical reasoning assistant specializing in hierarchical titles.
    fields:
      - type: include
        description: Upper-level title includes lower-level title.
        rule: |
          - "-1" is an invalid title; it does not belong to or include any other titles.
          - Must follow the hierarchical index/numbering (e.g., "1", "2.1", "3.2.5") when present.
          - Keep language of "title" the same as the input.
          - 第N章 must include 第N条 or 第N节.
  global_rules: ''