cache

Documentation

Index

• type Cache
• type Document
• type DocumentMetadata
• type ExtractedDocument
• type NopCache
  • func (c *NopCache) GetMetadata(url string) (DocumentMetadata, error)
  • func (c *NopCache) Save(doc ExtractedDocument) (*jetstream.ObjectInfo, error)
  • func (c *NopCache) StreamText(url string, w io.Writer) error
• type ObjectStoreCache
  • func New(conf config.TesConfig, log *slog.Logger, nc *nats.Conn) (*ObjectStoreCache, error)
  • func (store ObjectStoreCache) GetMetadata(url string) (DocumentMetadata, error)
  • func (store ObjectStoreCache) Save(doc ExtractedDocument) (*jetstream.ObjectInfo, error)
  • func (store ObjectStoreCache) StreamText(url string, w io.Writer) error

Types

type Cache

type Cache interface {
	GetMetadata(url string) (DocumentMetadata, error)
	StreamText(url string, w io.Writer) error
	Save(doc ExtractedDocument) (*jetstream.ObjectInfo, error)
}

type Document

type Document interface {
	// StreamText writes all text to w
	StreamText(w io.Writer) error
	// Pages returns the documents number of pages. Returns -1 if the concept is not applicable to the file type.
	Pages() int
	// Text returns a single page's text and true if there is at least one image on the page
	Text(int) (string, bool)
	// Data returns the underlying byte array or nil if the document was loaded from disk
	Data() *[]byte
	// Path returns the filesystem path a document was loaded from or an empty string if it was not loaded from disk
	Path() string
	// MetadataMap returns a map of Document properties, such as Author, Title etc.
	MetadataMap() DocumentMetadata
	// HasNewlines reports if dehyphenation is possible and sensible
	HasNewlines() bool
	// Close releases resources associated with the document
	Close()
}

Document represents any kind of document this service can convert to plain text

type DocumentMetadata

type DocumentMetadata = map[string]string

type ExtractedDocument

type ExtractedDocument struct {
	Url      *string
	Metadata *map[string]string
	Text     []byte
	Doc      Document
}

ExtractedDocument contains pointers to metadata, textual content and URL of origin

type NopCache

type NopCache struct{}

func (*NopCache) GetMetadata

func (c *NopCache) GetMetadata(url string) (DocumentMetadata, error)

func (*NopCache) Save

func (c *NopCache) Save(doc ExtractedDocument) (*jetstream.ObjectInfo, error)

func (*NopCache) StreamText

func (c *NopCache) StreamText(url string, w io.Writer) error

type ObjectStoreCache

type ObjectStoreCache struct {
	jetstream.ObjectStore
	// contains filtered or unexported fields
}

func New

func New(conf config.TesConfig, log *slog.Logger, nc *nats.Conn) (*ObjectStoreCache, error)

func (ObjectStoreCache) GetMetadata

func (store ObjectStoreCache) GetMetadata(url string) (DocumentMetadata, error)

func (ObjectStoreCache) Save

func (store ObjectStoreCache) Save(doc ExtractedDocument) (*jetstream.ObjectInfo, error)

func (ObjectStoreCache) StreamText

func (store ObjectStoreCache) StreamText(url string, w io.Writer) error