pdfread

README

go-pdfreader

Quick & Dirty copy of https://code.google.com/p/pdfreader/ to run under Go1.4

Example how to use it

package main

import (
	"code.google.com/p/pdfreader"
	"flag"
	"fmt"
	"path"
)

func main() {

	fileFlag := flag.String("file", "", "File to use")
	flag.Parse()

	if *fileFlag == "" {
		return
	}

	pd := pdfread.Load(*fileFlag)
	if pd != nil {
		pg := pd.Pages()
		fmt.Printf("        %s PagesCount=%d\n\n", path.Base(*fileFlag), len(pg))
		for k := range pg {
			fmt.Printf("Page %d - MediaBox: %s\n",
				k+1, pd.Att("/MediaBox", pg[k]))
			fonts := pd.PageFonts(pg[k])
			for l := range fonts {
				fontname := pd.Dic(fonts[l])["/BaseFont"]
				fmt.Printf("  %s = \"%s\"\n",
					l, fontname[1:])
			}

		}

	}
}

Documentation

Overview

Access to PDF files.

Index

• Constants
• func Array(s []byte) [][]byte
• type DictionaryT
  • func Dictionary(s []byte) DictionaryT
• type PdfReaderT
  • func Load(fn string) *PdfReaderT
  • func (pd *PdfReaderT) Arr(reference []byte) [][]byte
  • func (pd *PdfReaderT) Att(a string, src []byte) []byte
  • func (pd *PdfReaderT) Attribute(a string, src []byte) []byte
  • func (pd *PdfReaderT) DecodedStream(reference []byte) (DictionaryT, []byte)
  • func (pd *PdfReaderT) Dic(reference []byte) DictionaryT
  • func (pd *PdfReaderT) ForcedArray(reference []byte) [][]byte
  • func (pd *PdfReaderT) Num(reference []byte) int
  • func (pd *PdfReaderT) Obj(reference []byte) []byte
  • func (pd *PdfReaderT) PageFonts(page []byte) DictionaryT
  • func (pd *PdfReaderT) Pages() [][]byte
  • func (pd *PdfReaderT) Resolve(s []byte) (int, []byte)
  • func (pd *PdfReaderT) Stream(reference []byte) (DictionaryT, []byte)

Constants

const (
	MAX_PDF_UPDATES   = 1024
	MAX_PDF_ARRAYSIZE = 1024
)

Functions

func Array

func Array(s []byte) [][]byte

Array() extracts an array from PDF data.

Types

type DictionaryT

type DictionaryT map[string][]byte

func Dictionary

func Dictionary(s []byte) DictionaryT

Dictionary() makes a map/hash from PDF dictionary data.

type PdfReaderT

type PdfReaderT struct {
	File string // name of the file

	Startxref int         // starting of xref table
	Xref      map[int]int // "pointers" of the xref table
	Trailer   DictionaryT // trailer dictionary of the file
	// contains filtered or unexported fields
}

func Load

func Load(fn string) *PdfReaderT

Load() loads a PDF file of a given name.

func (*PdfReaderT) Arr

func (pd *PdfReaderT) Arr(reference []byte) [][]byte

pd.Arr() queries array data from a reference.

func (*PdfReaderT) Att

func (pd *PdfReaderT) Att(a string, src []byte) []byte

pd.Att() tries to get an attribute from a page reference. The attribute will be resolved.

func (*PdfReaderT) Attribute

func (pd *PdfReaderT) Attribute(a string, src []byte) []byte

pd.Attribute() tries to get an attribute definition from a page reference. Note that the attribute definition is not resolved - so it's possible to get back a reference here.

func (*PdfReaderT) DecodedStream

func (pd *PdfReaderT) DecodedStream(reference []byte) (DictionaryT, []byte)

pd.DecodedStream() returns decoded contents of a stream.

func (*PdfReaderT) Dic

func (pd *PdfReaderT) Dic(reference []byte) DictionaryT

pd.Dic() queries dictionary data from a reference.

func (*PdfReaderT) ForcedArray

func (pd *PdfReaderT) ForcedArray(reference []byte) [][]byte

pd.ForcedArray() queries array data. If reference does not refer to an array, reference is taken as element of the returned array.

func (*PdfReaderT) Num

func (pd *PdfReaderT) Num(reference []byte) int

pd.Num() queries integer data from a reference.

func (*PdfReaderT) Obj

func (pd *PdfReaderT) Obj(reference []byte) []byte

pd.Obj() is the universal method to access contents of PDF objects or data tokens in i.e. dictionaries. For reading streams you'll have to utilize pd.Resolve().

func (*PdfReaderT) PageFonts

func (pd *PdfReaderT) PageFonts(page []byte) DictionaryT

pd.PageFonts() returns references to the fonts defined for a page.

func (*PdfReaderT) Pages

func (pd *PdfReaderT) Pages() [][]byte

pd.Pages() returns an array with references to the pages of the PDF.

func (*PdfReaderT) Resolve

func (pd *PdfReaderT) Resolve(s []byte) (int, []byte)

pd.Resolve() resolves a reference in the PDF file. You'll probably need this method for reading streams only.

func (*PdfReaderT) Stream

func (pd *PdfReaderT) Stream(reference []byte) (DictionaryT, []byte)

pd.Stream() returns contents of a stream.