ocrd-tool.json

{
  "version": "1.4.1",
  "git_url": "https://github.com/kba/page-to-alto",
  "tools": {
    "ocrd-page2alto-transform": {
      "executable": "ocrd-page2alto-transform",
      "categories": ["Layout analysis"],
      "description": "Transform PAGE-XML to ALTO",
      "input_file_grp": ["OBSOLETE"],
      "output_file_grp": ["ALSO-OBSOLETE"],
      "steps": ["whatevs"],
      "parameters": {
        "check_border": {
          "type": "boolean",
          "description": "Whether to create full-page WIDTH/HEIGHT etc. if no border/pagespace present",
          "default": false
        },
        "check_words": {
          "type": "boolean",
          "description": "Check whether PAGE-XML contains any Words and fail if not",
          "default": true
        },
        "skip_empty_lines": {
          "type": "boolean",
          "description": "Whether to omit or keep empty lines in PAGE-XML",
          "default": false
        },
        "trailing_dash_to_hyp": {
          "type": "boolean",
          "description": "Whether to add a <HYP/> element if the last word in a line ends in '-'",
          "default": false
        },
        "dummy_word": {
          "type": "boolean",
          "description": "Whether to create a Word for TextLine that have TextEquiv/Unicode but no Word",
          "default": true
        },
        "dummy_textline": {
          "type": "boolean",
          "description": "Whether to create a TextLine for regions that have TextEquiv/Unicode but no TextLine",
          "default": true
        },
        "textequiv_index": {
          "type": "number",
          "description": "If multiple textequiv, use the n-th TextEquiv by @index",
          "default": 0
        },
        "region_order": {
          "type": "string",
          "description": "Order in which to iterate over the regions",
          "enum": ["document", "reading-order", "reading-order-only"],
          "default": "document"
        },
        "textline_order": {
          "type": "string",
          "description": "Order in which to iterate over the textlines",
          "enum": ["document", "index", "textline-order"],
          "default": "document"
        },
        "textequiv_fallback_strategy": {
          "type": "string",
          "description": "What to do if selected TextEquiv @index is not available: 'raise' will lead to a runtime error, 'first' will use the first TextEquiv, 'last' will use the last TextEquiv on the element",
          "enum": ["raise", "first", "last"],
          "default": "first"
        },
        "alto_version": {
          "type": "string",
          "description": "Whether to create full-page WIDTH/HEIGHT etc. if no border/pagespace present",
          "default": "v4.2",
          "enum": ["v4.2", "v4.1", "v4.0", "v3.1", "v3.0", "v2.1", "v2.0"]
        },
        "timestamp_src": {
          "type": "string",
          "description": "Which element to use for the timestamp",
          "default": "LastChange",
          "enum": ["Created", "LastChange", "none"]
        }
      },
      "resources": []
    }
  }
}