gocropy

README

Gocropy

Library to process ocropy's hocr files

Documentation

Index

• type Bbox
  • func TokenizeChars(chars []Char) (string, Bbox)
  • func (bbox *Bbox) Add(other Bbox)
  • func (bbox *Bbox) AddSlice(bboxes []Bbox)
  • func (bbox *Bbox) Sanitize(page Bbox)
  • func (bbox *Bbox) Scan(state fmt.ScanState, verb rune) error
  • func (bbox Bbox) String() string
• type Char
  • func CharsFromLlocs(llocs []Lloc, bbox Bbox) []Char
  • func (char Char) String() string
• type HOCR
  • func MustReadHOCR(file string) *HOCR
  • func ReadHOCR(file string) (*HOCR, error)
  • func (hocr *HOCR) ConvertToHOCR(dir string) error
  • func (hocr *HOCR) MustConvertToHOCR(dir string)
  • func (hocr *HOCR) ReadImageFileBbox() (*Bbox, error)
• type HOCRBody
• type HOCRClass
• type HOCRDiv
• type HOCRHead
• type HOCRMeta
• type HOCRSpan
• type HOCRTitle
  • func (title HOCRTitle) GetBbox() Bbox
  • func (title HOCRTitle) GetFile() string
  • func (title *HOCRTitle) SetBbox(bbox Bbox)
  • func (title *HOCRTitle) SetCuts(chars []Char)
  • func (title *HOCRTitle) SetFile(file string)
• type Lloc
  • func MustReadLlocs(file string) []Lloc
  • func ReadLlocs(file string) ([]Lloc, error)
  • func (lloc Lloc) String() string

Types

type Bbox

type Bbox struct {
	Left, Top, Right, Bottom int
}

func TokenizeChars

func TokenizeChars(chars []Char) (string, Bbox)

func (*Bbox) Add

func (bbox *Bbox) Add(other Bbox)

func (*Bbox) AddSlice

func (bbox *Bbox) AddSlice(bboxes []Bbox)

func (*Bbox) Sanitize

func (bbox *Bbox) Sanitize(page Bbox)

func (*Bbox) Scan

func (bbox *Bbox) Scan(state fmt.ScanState, verb rune) error

func (Bbox) String

func (bbox Bbox) String() string

type Char

type Char struct {
	Box  Bbox
	Rune rune
}

func CharsFromLlocs

func CharsFromLlocs(llocs []Lloc, bbox Bbox) []Char

func (Char) String

func (char Char) String() string

type HOCR

type HOCR struct {
	XMLName xml.Name
	Head    HOCRHead `xml:"head"`
	Body    HOCRBody `xml:"body"`
	File    string   `xml:"-"`
}

func MustReadHOCR

func MustReadHOCR(file string) *HOCR

func ReadHOCR

func ReadHOCR(file string) (*HOCR, error)

func (*HOCR) ConvertToHOCR

func (hocr *HOCR) ConvertToHOCR(dir string) error

func (*HOCR) MustConvertToHOCR

func (hocr *HOCR) MustConvertToHOCR(dir string)

func (*HOCR) ReadImageFileBbox

func (hocr *HOCR) ReadImageFileBbox() (*Bbox, error)

type HOCRBody

type HOCRBody struct {
	Div HOCRDiv `xml:"div"`
}

type HOCRClass

type HOCRClass struct {
	Class string `xml:"class,attr"`
}

type HOCRDiv

type HOCRDiv struct {
	HOCRClass
	HOCRTitle
	Spans []HOCRSpan `xml:"span"`
}

type HOCRHead

type HOCRHead struct {
	Title string     `xml:"title"`
	Metas []HOCRMeta `xml:"meta"`
}

type HOCRMeta

type HOCRMeta struct {
	HttpEquiv string `xml:"http-equiv,attr,omitempty"`
	Name      string `xml:"name,attr,omitempty"`
	Content   string `xml:"content,attr"`
}

type HOCRSpan

type HOCRSpan struct {
	HOCRClass
	HOCRTitle
	Data  string     `xml:",chardata"`
	Token []HOCRSpan `xml:"span"`
}

type HOCRTitle

type HOCRTitle struct {
	Title string `xml:"title,attr"`
}

func (HOCRTitle) GetBbox

func (title HOCRTitle) GetBbox() Bbox

func (HOCRTitle) GetFile

func (title HOCRTitle) GetFile() string

func (*HOCRTitle) SetBbox

func (title *HOCRTitle) SetBbox(bbox Bbox)

func (*HOCRTitle) SetCuts

func (title *HOCRTitle) SetCuts(chars []Char)

func (*HOCRTitle) SetFile

func (title *HOCRTitle) SetFile(file string)

type Lloc

type Lloc struct {
	Codepoint  rune
	Adjustment float64
}

func MustReadLlocs

func MustReadLlocs(file string) []Lloc

func ReadLlocs

func ReadLlocs(file string) ([]Lloc, error)

func (Lloc) String

func (lloc Lloc) String() string