PDFParser Configuration

{
  "parsers": [
    {
      "pdf-parser": {
        "extractInlineImages": true,
        "sortByPosition": true
      }
    },
    {
      // Keep Tika's other default parsers. Without this, this config is PDF-only.
      "default-parser": {}
    }
  ]
}

{
  // A "parsers" list loads ONLY the parsers it names; the "default-parser" entry at
  // the bottom keeps all the others. Windows paths in JSON need forward slashes or
  // escaped backslashes.
  "parsers": [
    {
      "pdf-parser": {
        // Enforce the PDF's access permissions. DONT_CHECK ignores them.
        // Options: DONT_CHECK, ALLOW_EXTRACTION_FOR_ACCESSIBILITY, IGNORE_ACCESSIBILITY_ALLOWANCE
        "accessCheckMode": "DONT_CHECK",
        // Character-width tolerance for inserting spaces (PDFBox).
        "averageCharTolerance": 0.3,
        // Collect per-stream IOExceptions in metadata and rethrow after parsing.
        "catchIntermediateIOExceptions": true,
        // Detect and correct rotated (angled) text runs within a page.
        "detectAngles": false,
        // Line-height multiple that starts a new paragraph (PDFBox).
        "dropThreshold": 2.5,
        // Estimate where spaces belong between words (most PDFs lack explicit spaces).
        "enableAutoSpace": true,
        // Extract AcroForm field content.
        "extractAcroFormContent": true,
        // Extract PDF actions; JavaScript macros become embedded documents.
        "extractActions": false,
        // Extract annotation text (comments, form-field captions).
        "extractAnnotationText": true,
        // Extract outline / bookmark text.
        "extractBookmarksText": true,
        // Record font names in metadata.
        "extractFontNames": false,
        // Record metadata about incremental updates (whether present, how many).
        "extractIncrementalUpdateInfo": true,
        // Record inline-image metadata only, without rendering (faster than extractInlineImages).
        "extractInlineImageMetadataOnly": false,
        // Render and extract inline images from content streams.
        "extractInlineImages": false,
        // Extract marked-content / structure tags, falling back to plain text.
        "extractMarkedContent": false,
        // Emit each unique inline image (by object id) only once.
        "extractUniqueInlineImagesOnly": true,
        // If the PDF has an XFA form, process only it.
        "ifXFAExtractOnlyXFA": false,
        // Ignore content-stream space glyphs; rely on the spacing algorithm (PDFBOX-3774).
        "ignoreContentStreamSpaceGlyphs": false,
        // EXPERT: replace the inline-image factory; give a class implementing
        // ImageGraphicsEngineFactory, e.g.:
        //   "imageGraphicsEngineFactoryClass": "com.example.MyImageGraphicsEngineFactory"
        // How to render page images; NONE renders nothing.
        // Options: NONE, RAW_IMAGES, RENDER_PAGES_BEFORE_PARSE, RENDER_PAGES_AT_PAGE_END
        "imageStrategy": "NONE",
        // Max incremental updates to parse when parseIncrementalUpdates is true.
        "maxIncrementalUpdates": 10,
        // Max memory to load a PDF before buffering to a temp file (default 512MB).
        "maxMainMemoryBytes": 536870912,
        // Max pages to process; -1 = no limit.
        "maxPages": -1,
        // OCR settings. Requires an OCR engine (e.g. Tesseract) installed.
        "ocr": {
          // Render resolution (dpi) for OCR.
          "dpi": 300,
          // Image format sent to the OCR engine.
          // Options: PNG, TIFF, JPEG
          "imageFormat": "PNG",
          // Image quality (0.0-1.0) for lossy formats.
          "imageQuality": 1.0,
          // Rendered-image color model.
          // Options: RGB, GRAY
          "imageType": "GRAY",
          // Skip OCR for rendered pages larger than this area (w x h); -1 = no limit.
          "maxImagePixels": 100000000,
          // Max pages to OCR per document; -1 = no limit.
          "maxPagesToOcr": -1,
          // Which page content to render for OCR.
          // Options: NO_TEXT, TEXT_ONLY, VECTOR_GRAPHICS_ONLY, ALL
          "renderingStrategy": "ALL",
          // When to run OCR; AUTO runs it only on text-poor pages.
          // Options: AUTO, NO_OCR, OCR_ONLY, OCR_AND_TEXT_EXTRACTION
          "strategy": "AUTO",
          // Per-page character thresholds that trigger AUTO OCR.
          "strategyAuto": {
            "totalCharsPerPage": 10,
            "unmappedUnicodeCharsPerPage": 10
          }
        },
        // Parse prior incremental-update versions as embedded documents.
        "parseIncrementalUpdates": false,
        // EXPERT: set the Sun KCMS color-management system property. Default false.
        "setKCMS": false,
        // Sort text by x/y position; helps some PDFs, can interleave columns in others.
        "sortByPosition": false,
        // Space-width tolerance for inserting spaces (PDFBox).
        "spacingTolerance": 0.5,
        // Remove text drawn twice over the same region (faked bold); can be slow.
        "suppressDuplicateOverlappingText": false,
        // Throw on an encrypted payload instead of skipping it.
        "throwOnEncryptedPayload": false
      }
    },
    {
      // Keep Tika's other default parsers. Without this, this config is PDF-only.
      "default-parser": {}
    }
  ]
}