pdfextract

type OCRBackend interface {
	// Available returns true if the OCR backend is installed and executable.
	Available() bool
	// ValidateLang checks if the configured language data is available.
	ValidateLang(ctx context.Context) error
	// OCRPage performs OCR on the specified image file and returns the extracted text.
	OCRPage(ctx context.Context, imagePath string) (string, error)
}

type PDFBackend interface {
	// ExtractText extracts text from the PDF file, returning a slice where each element is a page's text.
	ExtractText(ctx context.Context, filePath string) ([]string, error)
	// RenderPage renders the specified page (1-indexed) to a temporary image file and returns the path.
	RenderPage(ctx context.Context, filePath string, pageNum int) (string, error)
	// Close releases any resources associated with the backend.
	Close() error
}

type PDFChunk struct {
	PageNum int
	Text    string
}

type PDFiumBackend struct {
	// contains filtered or unexported fields
}

type TesseractBackend struct {
	BinPath string
	Lang    string
}