guesser

Documentation

Index

• func GuessDocument(ctx context.Context, d *processor.Document) (processor.DocumentType, processor.FormatType, error)
• func GuessEncoding(ctx context.Context, d *processor.Document) error
• func RegisterDocumentFormatGuesser(g DocumentFormatGuesser, name string) error
• func RegisterDocumentTypeGuesser(g DocumentTypeGuesser, name string) error
• type DocumentFormatGuesser
• type DocumentTypeGuesser
• type IngestPredicatesGuesser
  • func (_ *IngestPredicatesGuesser) GuessDocumentType(blob []byte, format processor.FormatType) processor.DocumentType

Functions

func GuessDocument

func GuessDocument(ctx context.Context, d *processor.Document) (processor.DocumentType, processor.FormatType, error)

func GuessEncoding

func GuessEncoding(ctx context.Context, d *processor.Document) error

func RegisterDocumentFormatGuesser

func RegisterDocumentFormatGuesser(g DocumentFormatGuesser, name string) error

func RegisterDocumentTypeGuesser

func RegisterDocumentTypeGuesser(g DocumentTypeGuesser, name string) error

Types

type DocumentFormatGuesser

type DocumentFormatGuesser interface {
	// GuessFormat returns the format type guessed to processor.FormatUnknown if
	// it is unable to.
	GuessFormat(blob []byte) processor.FormatType
}

DocumentFormatGuesser guesses the format of the document given a blob

type DocumentTypeGuesser

type DocumentTypeGuesser interface {
	// GuessDocumentType returns the document type guessed or processor.DocumentUnknown if
	// it is unable to. Format provided may be processor.FormatUnknown.
	GuessDocumentType(blob []byte, format processor.FormatType) processor.DocumentType
}

DocumentTypeGuesser guesses the document type based on the blob and format given

type IngestPredicatesGuesser

type IngestPredicatesGuesser struct{}

func (*IngestPredicatesGuesser) GuessDocumentType

func (_ *IngestPredicatesGuesser) GuessDocumentType(blob []byte, format processor.FormatType) processor.DocumentType