docfactory

Documentation

Index

• Variables
• type DocFactory
  • func New(tesconfig *config.TesConfig, logger *slog.Logger) *DocFactory
  • func (df *DocFactory) NewDocFromForkedProcess(r io.Reader, origin string) (*ForkedDoc, error)
  • func (df *DocFactory) NewDocFromForkedProcessPath(path, origin string) (*ForkedDoc, error)
  • func (df *DocFactory) NewDocFromStream(r io.Reader, size int64, origin string) (cache.Document, error)
  • func (df *DocFactory) NewFromBytes(data []byte, origin string) (cache.Document, error)
  • func (df *DocFactory) NewFromPath(path, origin string) (cache.Document, error)
  • func (df *DocFactory) NewPdfFromBytes(data []byte, origin string) (doc cache.Document, err error)
  • func (df *DocFactory) NewPdfFromPath(path, origin string) (doc cache.Document, err error)
  • func (df *DocFactory) PdfImpl() pdfImplementation
• type ForkedDoc
  • func (d *ForkedDoc) Close()
  • func (d *ForkedDoc) Data() *[]byte
  • func (d *ForkedDoc) HasNewlines() bool
  • func (d *ForkedDoc) MetadataMap() map[string]string
  • func (d *ForkedDoc) Pages() int
  • func (d *ForkedDoc) Path() string
  • func (d *ForkedDoc) StreamText(w io.Writer) error
  • func (d *ForkedDoc) Text(i int) (string, bool)
• type PooledDoc
  • func (d *PooledDoc) Close()
  • func (d *PooledDoc) HasNewlines() bool

Variables

var AlienationErr error = errors.New("don't know who I am")

AlienationErr indicates that forking a new process is not possible because TES could not find out its own FS path (this is unlikely)

Types

type DocFactory

type DocFactory struct {
	MaxInMemoryBytes uint64
	MaxFileSizeBytes uint64
	// contains filtered or unexported fields
}

func New

func New(tesconfig *config.TesConfig, logger *slog.Logger) *DocFactory

func (*DocFactory) NewDocFromForkedProcess

func (df *DocFactory) NewDocFromForkedProcess(r io.Reader, origin string) (*ForkedDoc, error)

NewDocFromForkedProcess creates a Document whose content and metadata is being extracted by a forked subprocess

func (*DocFactory) NewDocFromForkedProcessPath

func (df *DocFactory) NewDocFromForkedProcessPath(path, origin string) (*ForkedDoc, error)

func (*DocFactory) NewDocFromStream

func (df *DocFactory) NewDocFromStream(r io.Reader, size int64, origin string) (cache.Document, error)

func (*DocFactory) NewFromBytes

func (df *DocFactory) NewFromBytes(data []byte, origin string) (cache.Document, error)

func (*DocFactory) NewFromPath

func (df *DocFactory) NewFromPath(path, origin string) (cache.Document, error)

func (*DocFactory) NewPdfFromBytes

func (df *DocFactory) NewPdfFromBytes(data []byte, origin string) (doc cache.Document, err error)

NewPdfFromBytes returns a PDF Document parsed by the particular PDF lib that was loaded before

func (*DocFactory) NewPdfFromPath

func (df *DocFactory) NewPdfFromPath(path, origin string) (doc cache.Document, err error)

NewPdfFromPath returns a PDF Document parsed by the particular PDF lib that was loaded before

func (*DocFactory) PdfImpl

func (df *DocFactory) PdfImpl() pdfImplementation

type ForkedDoc

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

ForkedDoc represents a Document processed by forked subprocess of this service

func (*ForkedDoc) Close

func (d *ForkedDoc) Close()

func (*ForkedDoc) Data

func (d *ForkedDoc) Data() *[]byte

func (*ForkedDoc) HasNewlines

func (d *ForkedDoc) HasNewlines() bool

func (*ForkedDoc) MetadataMap

func (d *ForkedDoc) MetadataMap() map[string]string

func (*ForkedDoc) Pages

func (d *ForkedDoc) Pages() int

func (*ForkedDoc) Path

func (d *ForkedDoc) Path() string

func (*ForkedDoc) StreamText

func (d *ForkedDoc) StreamText(w io.Writer) error

StreamText may only be invoked once!

func (*ForkedDoc) Text

func (d *ForkedDoc) Text(i int) (string, bool)

type PooledDoc

type PooledDoc struct {
	cache.Document
	// contains filtered or unexported fields
}

func (*PooledDoc) Close

func (d *PooledDoc) Close()

func (*PooledDoc) HasNewlines

func (d *PooledDoc) HasNewlines() bool