page

Documentation

Index

• Constants
• type Line
  • func (l Line) FindWordByID(id string) (Word, bool)
  • func (w Line) ID() string
  • func (l Line) Polygon() (Polygon, error)
  • func (l Line) TextEquivUnicodeAt(pos int) (string, bool)
  • func (l Line) Words() []Word
• type Match
  • func (m Match) String() string
• type Page
  • func Open(path string) (Page, error)
  • func (p Page) Find(m Match) (TextRegion, bool)
  • func (p Page) FindRegionByID(id string) (Region, bool)
  • func (p Page) Regions() []Region
• type Polygon
  • func (p Polygon) Rectangle() image.Rectangle
• type Region
  • func (r Region) FindLineByID(id string) (Line, bool)
  • func (w Region) ID() string
  • func (r Region) Lines() []Line
  • func (r Region) Polygon() (Polygon, error)
  • func (r Region) TextEquivUnicodeAt(pos int) (string, bool)
• type TextRegion
• type Word
  • func (w Word) ID() string
  • func (w Word) Polygon() (Polygon, error)
  • 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 {
	// 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) ID

func (w Line) ID() string

ID returns the line's ID.

func (Line) Polygon

func (l Line) Polygon() (Polygon, error)

Polygon returns the line's polygon of coordinates.

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 Match

type Match struct {
	RegionID, LineID, WordID string
}

Match is used to match text regions. If any of the IDs is the empty string, the according region is ignored.

func (Match) String

func (m Match) String() string

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) Find

func (p Page) Find(m Match) (TextRegion, bool)

Find searches for a given {region,line,word}-ID in the PAGE-XML (IDs are assumed to be unique).

func (Page) FindRegionByID

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

FindRegionByID returns the region with the given ID.

func (Page) Regions

func (p Page) Regions() []Region

Regions returns a slice with all RegionRefIndexed elements

type Polygon

type Polygon []image.Point

Polygon is used to represent the polygons of <Coords points='...'/> points in the PAGE-XML.

func (Polygon) Rectangle

func (p Polygon) Rectangle() image.Rectangle

Rectangle returns the bounding rectangle of the polygon.

type Region

type Region struct {
	// 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) ID

func (w Region) ID() string

ID returns the region's ID.

func (Region) Lines

func (r Region) Lines() []Line

Lines Returns all lines in a region.

func (Region) Polygon

func (r Region) Polygon() (Polygon, error)

Polygon returns the region's polygon of coordinates.

func (Region) TextEquivUnicodeAt

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

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

type TextRegion

type TextRegion interface {
	ID() string
	TextEquivUnicodeAt(int) (string, bool)
	Polygon() (Polygon, error)
}

TextRegion defines an interface for abstract text regions in a PAGE-XML document.

type Word

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

Word represents a word on a line.

func (Word) ID

func (w Word) ID() string

ID returns the word's ID.

func (Word) Polygon

func (w Word) Polygon() (Polygon, error)

Polygon returns the word's polygon of coordinates.

func (Word) TextEquivUnicodeAt

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

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