# MCP PDF Tools Configuration

# Tesseract OCR configuration
# Path to Tesseract data directory (for language files)
# Ubuntu/Debian: /usr/share/tesseract-ocr/5/tessdata
# macOS (Homebrew): /usr/local/share/tessdata
# Windows: C:\Program Files\Tesseract-OCR\tessdata
TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata

# Temporary directory for PDF processing
# Used for intermediate files during conversion
PDF_TEMP_DIR=/tmp/pdf_processing

# Poppler utilities path (for pdf2image)
# Only needed if poppler-utils is not in PATH
# Ubuntu/Debian: Usually in PATH
# macOS: /usr/local/bin (if installed via Homebrew)
# Windows: C:\Program Files\poppler-0.68.0\bin
# POPPLER_PATH=/usr/local/bin

# Java home for Tabula (table extraction)
# Only needed if Java is not in PATH
# JAVA_HOME=/usr/lib/jvm/java-11-openjdk

# Debug mode
# Set to true for verbose logging
DEBUG=false

# Maximum file size in MB
# PDFs larger than this will be rejected
MAX_PDF_SIZE_MB=100

# Default DPI for PDF to image conversion
# Higher values = better quality but slower processing
DEFAULT_DPI=300

# Default OCR languages (comma-separated)
# Common codes: eng (English), fra (French), deu (German), spa (Spanish)
DEFAULT_OCR_LANGUAGES=eng