TesseractOCRParser Configuration

{
  "parsers": [
    {
      "tesseract-ocr-parser": {
        "language": "eng",
        "timeoutMillis": 120000
      }
    },
    {
      // Keep Tika's other default parsers. Without this, only image files are OCR'd.
      "default-parser": {}
    }
  ]
}

{
  // A "parsers" list loads ONLY the parsers it names; the "default-parser" entry at
  // the bottom keeps all the others (needed so PDFs/Office docs still reach OCR).
  // Windows paths in JSON need forward slashes or escaped backslashes.
  "parsers": [
    {
      "tesseract-ocr-parser": {
        // Calculate skew and rotate (via ImageMagick) before OCR. Needs ImageMagick.
        "applyRotation": false,
        // Colorspace of the preprocessed image (preprocessing only).
        "colorspace": "gray",
        // Resolution (dpi) of the preprocessed image.
        "density": 300,
        // Bits per color sample in the preprocessed image.
        "depth": 4,
        // Run ImageMagick preprocessing (density/depth/colorspace/filter/resize) before OCR.
        "enableImagePreprocessing": false,
        // ImageMagick resize filter.
        "filter": "triangle",
        // Directory holding the ImageMagick program (empty = on PATH). ImageMagick is
        // OPTIONAL -- used only when enableImagePreprocessing or applyRotation is true.
        "imageMagickPath": "",
        // Write OCR output from embedded images inline into the parent document.
        "inlineContent": false,
        // Tesseract language(s); join multiple with '+', e.g. "eng+fra".
        "language": "eng",
        // Skip OCR for files larger than this many bytes.
        "maxFileSizeToOcr": 2147483647,
        // Skip OCR for files smaller than this many bytes.
        "minFileSizeToOcr": 0,
        // Additional raw Tesseract config variables (key-value).
        "otherTesseractConfig": {
          "preserve_interword_spaces": "1",
          "textord_initialx_ile": "0.75",
          "textord_noise_hfract": "0.15625"
        },
        // Tesseract output format.
        // Options: TXT, HOCR
        "outputType": "TXT",
        // Inserted between OCR'd pages (empty overrides Tesseract 4's form-feed).
        "pageSeparator": "",
        // Page segmentation mode (0-13); 1 = auto with orientation/script detection.
        "pageSegMode": "1",
        // Load Tesseract language data at startup instead of on first use.
        "preloadLangs": false,
        // Preserve interword spacing in the output.
        "preserveInterwordSpacing": false,
        // Scale percent (100-900) applied during preprocessing.
        "resize": 200,
        // Runtime kill-switch to disable OCR.
        "skipOcr": false,
        // Directory with tessdata language files (empty = Tesseract default).
        "tessdataPath": "",
        // Directory with the tesseract binary (empty = on PATH).
        "tesseractPath": "",
        // Max seconds to wait for the OCR process.
        "timeoutMillis": 120000
      }
    },
    {
      // Keep Tika's other default parsers. Without this, only image files are OCR'd.
      "default-parser": {}
    }
  ]
}