page

Documentation

Index

• Constants
• type Line
  • func (l Line) FindWordByID(id string) (Word, bool)
  • func (l Line) TextEquivUnicodeAt(pos int) (string, bool)
  • func (l Line) Words() []Word
• type Page
  • func Open(path string) (Page, error)
  • func (p Page) FindRegionByID(id string) (Region, bool)
  • func (p Page) Regions() []Region
• type Region
  • func (r Region) FindLineByID(id string) (Line, bool)
  • func (r Region) Lines() []Line
  • func (r Region) TextEquivUnicodeAt(pos int) (string, bool)
• type Word
  • func (w Word) TextEquivUnicodeAt(pos int) (string, bool)

Constants

const (
	// MIMEType defines the mime-type of page XML files.
	// See: https://github.com/PRImA-Research-Lab/PAGE-XML
	MIMEType = "application/alto+xml"
)

Types

type Line

type Line struct {
	ID string
	// contains filtered or unexported fields
}

Line represents a line of text in the page XML file.

func (Line) FindWordByID

func (l Line) FindWordByID(id string) (Word, bool)

FindWordByID searches for a line with the given ID.

func (Line) TextEquivUnicodeAt

func (l Line) TextEquivUnicodeAt(pos int) (string, bool)

TextEquivUnicodeAt returns the i-th TextEquiv/Unicode entry (indexing is zero-based).

func (Line) Words

func (l Line) Words() []Word

Words returns all words in a line.

type Page

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

Page represents an open page XML file.

func Open

func Open(path string) (Page, error)

Open opens a page XML file

func (Page) FindRegionByID

func (p Page) FindRegionByID(id string) (Region, bool)

FindRegionByID returns the region with the given refID.

func (Page) Regions

func (p Page) Regions() []Region

Regions returns a slice with all RegionRefIndexed elements

type Region

type Region struct {
	ID string
	// contains filtered or unexported fields
}

Region defines a text region in the page XML file.

func (Region) FindLineByID

func (r Region) FindLineByID(id string) (Line, bool)

FindLineByID searches for a line with the given ID.

func (Region) Lines

func (r Region) Lines() []Line

Lines Returns all lines in a region.

func (Region) TextEquivUnicodeAt

func (r Region) TextEquivUnicodeAt(pos int) (string, bool)

TextEquivUnicodeAt returns the i-th TextEquiv/Unicode entry (indexing is zero-based).

type Word

type Word struct {
	ID string
	// contains filtered or unexported fields
}

Word represents a word on a line.

func (Word) TextEquivUnicodeAt

func (w Word) TextEquivUnicodeAt(pos int) (string, bool)

TextEquivUnicodeAt returns the i-th TextEquiv/Unicode element (the indexing is zero-based).