{
  "$schema": "./config.schema.json",
  "custom_adapters": [
    {
      "name": "tesseract",
      "version": 1,
      "description": "Использует Tesseract OCR для распознавания текста на изображениях",
      "extensions": ["jpg", "jpeg", "jpe", "png", "webp", "gif", "tif", "tiff", "jp2", "j2k", "jpf", "jpm", "jpg2", "jpg2000", "jpeg2000", "j2c", "jpc", "jpx", "bmp", "pnm"],
      "mimetypes": ["image/jpeg", "image/png", "image/webp", "image/gif", "image/tiff", "image/jp2", "image/jpx", "image/jpm", "image/bmp", "image/x-portable-anymap"],
      "binary": "tesseract",
      "args": ["--psm", "1", "-l", "eng+rus+ukr", "-", "-"],
      "disabled_by_default": false,
      "match_only_by_mime": false
    },
    {
      "name": "antiword",
      "version": 1,
      "description": "Использует antiword для извлечения текста из файлов DOC",
      "extensions": ["doc"],
      "mimetypes": ["application/msword"],
      "binary": "antiword",
      "args": ["-"],
      "disabled_by_default": false,
      "match_only_by_mime": false,
      "output_path_hint": "${input_virtual_path}.txt"
    }
  ]
}