identity:
  name: "pdf_extract_range"
  author: "yslg"
  label:
    en_US: "Extract Page Range Text"
    zh_Hans: "提取页面范围文本"
    pt_BR: "Extrair Texto do Intervalo de Páginas"
    ja_JP: "ページ範囲テキスト抽出"
description:
  human:
    en_US: "Extract plain text from a specified page range of a PDF file"
    zh_Hans: "从PDF文件的指定页码范围提取纯文本"
    pt_BR: "Extrair texto simples de um intervalo de páginas especificado de um arquivo PDF"
    ja_JP: "PDFファイルの指定ページ範囲からプレーンテキストを抽出"
  llm: "Extract plain text from PDF pages in the given start-end range. Returns concatenated text of all pages in range."
parameters:
  - name: file
    type: file
    required: true
    label:
      en_US: PDF File
      zh_Hans: PDF 文件
      pt_BR: Arquivo PDF
      ja_JP: PDFファイル
    human_description:
      en_US: "PDF file to extract text from"
      zh_Hans: "要提取文本的 PDF 文件"
      pt_BR: "Arquivo PDF para extrair texto"
      ja_JP: "テキストを抽出するPDFファイル"
    llm_description: "PDF file to extract page range text from"
    form: llm
    fileTypes:
      - "pdf"
  - name: start_page
    type: number
    required: true
    label:
      en_US: Start Page
      zh_Hans: 起始页码
      pt_BR: Página Inicial
      ja_JP: 開始ページ
    human_description:
      en_US: "Start page index (0-based)"
      zh_Hans: "起始页码（从0开始）"
      pt_BR: "Índice da página inicial (base 0)"
      ja_JP: "開始ページ番号（0始まり）"
    llm_description: "Start page index (0-based)"
    form: llm
    default: 0
  - name: end_page
    type: number
    required: true
    label:
      en_US: End Page
      zh_Hans: 结束页码
      pt_BR: Página Final
      ja_JP: 終了ページ
    human_description:
      en_US: "End page index (0-based, inclusive)"
      zh_Hans: "结束页码（从0开始，包含该页）"
      pt_BR: "Índice da página final (base 0, inclusivo)"
      ja_JP: "終了ページ番号（0始まり、含む）"
    llm_description: "End page index (0-based, inclusive)"
    form: llm
    default: 0
extra:
  python:
    source: tools/pdf_extract_range.py