ocrd-tool.json

{
  "version": "0.0.2",
  "git_url": "https://github.com/jkamlah/ocrd_pagetopdf",
  "tools": {
    "ocrd-pagetopdf": {
      "executable": "ocrd-pagetopdf",
      "description": "Convert text and layout annotations to PDF format (overlaying original image with text layer and polygon outlines)",
      "categories": [
        "Long-term preservation"
      ],
      "steps": [
        "postprocessing/format-conversion"
      ],
      "input_file_grp": [
        "OCR-D-OCR-PAGE"
      ],
      "output_file_grp": [
        "OCR-D-OCR-PDF"
      ],
      "parameters": {
        "font": {
          "description": "Font file to be used in PDF file. If unset, AletheiaSans.ttf is used. (Make sure to pick a font which covers all glyphs!)",
          "type": "string",
          "format": "uri",
          "content-type": "application/x-font-ttf",
          "default": ""
        },
       "outlines": {
          "description": "What segment hierarchy to draw coordinate outlines for. If unset, no outlines are drawn.",
          "type": "string",
          "default": "",
          "enum": [
            "",
            "region",
            "line",
            "word",
            "glyph"
          ]
        },
        "textequiv_level": {
          "description": "What segment hierarchy level to render text output from. If unset, no text is rendered.",
          "type": "string",
          "default": "",
          "enum": [
            "",
            "region",
            "line",
            "word",
            "glyph"
          ]
        },
        "negative2zero": {
            "description": "Set all negative box values to 0",
            "type": "boolean",
            "default": false
        },
        "ext": {
          "description": "Output filename extension",
          "type": "string",
          "default": ".pdf"
        },
        "multipage": {
            "description": "Merge all PDFs into one multipage file. The value is used as filename for the pdf.",
            "type": "string",
            "default": ""
        },
        "pagelabel": {
            "description": "Parameter for 'multipage': Set the page information, which will be used as pagelabel. Default is 'pageId', e.g. the option 'pagenumber' will create numbered pagelabel consecutively",
            "type": "string",
            "default": "pageId",
            "enum": [
            "pagenumber",
            "pageId",
            "basename",
            "basename_without_extension",
            "local_filename",
            "ID",
            "url"
             ]
        },
        "script-args": {
          "description": "Extra arguments to PageToPdf (see https://github.com/PRImA-Research-Lab/prima-page-to-pdf)",
          "type": "string",
          "default": ""
        }
      }
    }
  }
}