extractor

type Extractor ¶

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

Extractor stores and offers functionality for extracting content from PDF pages.

func New(page *model.PdfPage) (*Extractor, error)

func (e *Extractor) ExtractPageImages(options *ImageExtractOptions) (*PageImages, error)

func (e *Extractor) ExtractPageText() (*PageText, int, int, error)

func (e *Extractor) ExtractText() (string, error)

func (e *Extractor) ExtractTextWithStats() (extracted string, numChars int, numMisses int, err error)

type ImageExtractOptions ¶

type ImageExtractOptions struct {
	IncludeInlineStencilMasks bool
}

ImageExtractOptions contains options for controlling image extraction from PDF pages.

type ImageMark ¶

type ImageMark struct {
	Image *model.Image

	// Dimensions of the image as displayed in the PDF.
	Width  float64
	Height float64

	// Position of the image in PDF coordinates (lower left corner).
	X float64
	Y float64

	// Angle in degrees, if rotated.
	Angle float64
}

ImageMark represents an image drawn on a page and its position in device coordinates. All coordinates are in device coordinates.

type PageImages ¶

type PageImages struct {
	Images []ImageMark
}

PageImages represents extracted images on a PDF page with spatial information: display position and size.

type PageText ¶

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

PageText represents the layout of text on a device page.

func (pt PageText) Marks() *TextMarkArray

func (pt PageText) String() string

func (pt PageText) Text() string

func (pt PageText) ToText() string

type RenderMode ¶

type RenderMode int

RenderMode specifies the text rendering mode (Tmode), which determines whether showing text shall cause glyph outlines to be stroked, filled, used as a clipping boundary, or some combination of the three. Stroking, filling, and clipping shall have the same effects for a text object as they do for a path object (see 8.5.3, "Path-Painting Operators" and 8.5.4, "Clipping Path Operators").

const (
	RenderModeStroke RenderMode = 1 << iota // Stroke
	RenderModeFill                          // Fill
	RenderModeClip                          // Clip
)

type TextMark ¶

type TextMark struct {
	// Text is the extracted text. It has been decoded to Unicode via ToUnicode().
	Text string
	// Original is the text in the PDF. It has not been decoded like `Text`.
	Original string
	// BBox is the bounding box of the text.
	BBox model.PdfRectangle
	// Font is the font the text was drawn with.
	Font *model.PdfFont
	// FontSize is the font size the text was drawn with.
	FontSize float64
	// Offset is the offset of the start of TextMark.Text in the extracted text. If you do this
	//   text, textMarks := pageText.Text(), pageText.Marks()
	//   marks := textMarks.Elements()
	// then marks[i].Offset is the offset of marks[i].Text in text.
	Offset int
	// Meta is set true for spaces and line breaks that we insert in the extracted text. We insert
	// spaces (line breaks) when we see characters that are over a threshold horizontal (vertical)
	//  distance  apart. See wordJoiner (lineJoiner) in PageText.computeViews().
	Meta bool
}

TextMark represents extracted text on a page with information regarding both textual content, formatting (font and size) and positioning. It is the smallest unit of text on a PDF page, typically a single character.

getBBox() in test_text.go shows how to compute bounding boxes of substrings of extracted text. The following code extracts the text on PDF page `page` into `text` then finds the bounding box `bbox` of substring `term` in `text`.

ex, _ := New(page)
// handle errors
pageText, _, _, err := ex.ExtractPageText()
// handle errors
text := pageText.Text()
textMarks := pageText.Marks()

	start := strings.Index(text, term)
 end := start + len(term)
 spanMarks, err := textMarks.RangeOffset(start, end)
 // handle errors
 bbox, ok := spanMarks.BBox()
 // handle errors

func (tm TextMark) String() string

type TextMarkArray ¶

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

TextMarkArray is a collection of TextMarks.

func (ma *TextMarkArray) Append(mark TextMark)

func (ma *TextMarkArray) BBox() (model.PdfRectangle, bool)

func (ma *TextMarkArray) Elements() []TextMark

func (ma *TextMarkArray) Len() int

func (ma *TextMarkArray) RangeOffset(start, end int) (*TextMarkArray, error)

func (ma TextMarkArray) String() string