examples/callbacks.rb examples/extract_bates.rb examples/metadata.rb examples/page_counter_improved.rb examples/page_counter_naive.rb examples/rspec.rb examples/text.rb @@ -88,177 +88,7 @@ http://groups.google.com/group/pdf-reader = Examples The easiest way to explain how this works in practice is to show some examples. - -== Naïve Page Counter - -A simple app to count the number of pages in a PDF File. - - require 'rubygems' - require 'pdf/reader' - - class PageReceiver - attr_accessor :counter - - def initialize - @counter = 0 - end - - # Called when page parsing ends - def end_page - @counter += 1 - end - end - - receiver = PageReceiver.new - pdf = PDF::Reader.file("somefile.pdf", receiver) - puts "#{receiver.counter} pages" - -== List all callbacks generated by a single PDF - -WARNING: this will generate a *lot* of output, so you probably want to pipe -it through less or to a text file. - - require 'rubygems' - require 'pdf/reader' - - receiver = PDF::Reader::RegisterReceiver.new - pdf = PDF::Reader.file("somefile.pdf", receiver) - receiver.callbacks.each do |cb| - puts cb - end - -== Extract all text from a single PDF - - class PageTextReceiver - attr_accessor :content - - def initialize - @content = [] - end - - # Called when page parsing starts - def begin_page(arg = nil) - @content << "" - end - - # record text that is drawn on the page - def show_text(string, *params) - @content.last << string.strip - end - - # there's a few text callbacks, so make sure we process them all - alias :super_show_text :show_text - alias :move_to_next_line_and_show_text :show_text - alias :set_spacing_next_line_show_text :show_text - - # this final text callback takes slightly different arguments - def show_text_with_positioning(*params) - params = params.first - params.each { |str| show_text(str) if str.kind_of?(String)} - end - end - - receiver = PageTextReceiver.new - pdf = PDF::Reader.file("somefile.pdf", receiver) - puts receiver.content.inspect - -== Extract metadata only - - require 'rubygems' - require 'pdf/reader' - - class MetaDataReceiver - attr_accessor :regular - attr_accessor :xml - - def metadata(data) - @regular = data - end - - def metadata_xml(data) - @xml = data - end - end - - receiver = MetaDataReceiver.new - pdf = PDF::Reader.file(ARGV.shift, receiver, :pages => false, :metadata => true) - puts receiver.regular.inspect - puts receiver.xml.inspect - -== Improved Page Counter - -A simple app to display the number of pages in a PDF File. - - require 'rubygems' - require 'pdf/reader' - - class PageReceiver - attr_accessor :pages - - # Called when page parsing ends - def page_count(arg) - @pages = arg - end - end - - receiver = PageReceiver.new - pdf = PDF::Reader.file("somefile.pdf", receiver, :pages => false) - puts "#{receiver.pages} pages" - -== Basic RSpec of a generated PDF - - require 'rubygems' - require 'pdf/reader' - require 'pdf/writer' - require 'spec' - - class PageTextReceiver - attr_accessor :content - - def initialize - @content = [] - end - - # Called when page parsing starts - def begin_page(arg = nil) - @content << "" - end - - def show_text(string, *params) - @content.last << string.strip - end - - # there's a few text callbacks, so make sure we process them all - alias :super_show_text :show_text - alias :move_to_next_line_and_show_text :show_text - alias :set_spacing_next_line_show_text :show_text - - def show_text_with_positioning(*params) - params = params.first - params.each { |str| show_text(str) if str.kind_of?(String)} - end - end - - context "My generated PDF" do - specify "should have the correct text on 2 pages" do - - # generate our PDF - pdf = PDF::Writer.new - pdf.text "Chunky", :font_size => 32, :justification => :center - pdf.start_new_page - pdf.text "Bacon", :font_size => 32, :justification => :center - pdf.save_as("chunkybacon.pdf") - - # process the PDF - receiver = PageTextReceiver.new - PDF::Reader.file("chunkybacon.pdf", receiver) - - # confirm the text appears on the correct pages - receiver.content.size.should eql(2) - receiver.content[0].should eql("Chunky") - receiver.content[1].should eql("Bacon") - end - end +Check out the examples/ directory for a few files. = Known Limitations README.rdoc 4629647d04186bb77703d6a5d1719bee80e98332 James Healy jimmy@deefa.com http://github.com/yob/pdf-reader/commit/c4da18053b35130caeea2d5f3401afc9434d70c6 c4da18053b35130caeea2d5f3401afc9434d70c6 2009-09-11T02:01:21-07:00 2009-09-11T02:01:21-07:00 moving examples out into a seperate dir 27478ee0fb57a29f1f744716b4b59d8bd0b5e2f8 James Healy jimmy@deefa.com