Add bin and edit workflow

bin/gems/pdf-reader-2.14.1/examples/callbacks.rb

@@ -0,0 +1,23 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# List all callbacks generated by each page
+#
+# 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'
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-basic.pdf"
+
+PDF::Reader.open(filename) do |reader|
+  reader.pages.each do |page|
+    receiver = PDF::Reader::RegisterReceiver.new
+    page.walk(receiver)
+    
+    receiver.callbacks.each do |cb|
+      puts cb
+    end
+  end
+end

bin/gems/pdf-reader-2.14.1/examples/extract_bates.rb

@@ -0,0 +1,50 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# A sample script that attempts to extract bates numbers from a PDF file.
+# Bates numbers are often used to markup documents being used in legal
+# cases. For more info, see http://en.wikipedia.org/wiki/Bates_numbering
+#
+# Acrobat 9 introduced a markup syntax that directly specifies the bates
+# number for each page. For earlier versions, the easiest way to find
+# the number is to look for words that match a pattern.
+#
+# This example attempts to extract numbers using the Acrobat 9 syntax.
+# As a fall back, you can use a regular expression to look for words
+# that match the numbers you expect in the page content.
+
+require 'rubygems'
+require 'pdf/reader'
+
+class BatesReceiver
+
+  attr_reader :numbers
+
+  def initialize
+    @numbers = []
+  end
+
+  def begin_marked_content(*args)
+    return unless args.size >= 2
+    return unless args.first == :Artifact
+    return unless args[1][:Subtype] == :BatesN
+
+    @numbers << args[1][:Contents]
+  end
+  alias :begin_marked_content_with_pl :begin_marked_content
+
+end
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-basic.pdf"
+
+PDF::Reader.open(filename) do |reader|
+  reader.pages.each do |page|
+    receiver = BatesReceiver.new
+    page.walk(receiver)
+    if receiver.numbers.empty?
+      puts page.text.scan(/CC.+/)
+    else
+      puts receiver.numbers.inspect
+    end
+  end
+end

bin/gems/pdf-reader-2.14.1/examples/extract_fonts.rb

@@ -0,0 +1,82 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# This demonstrates a way to extract TTF fonts from a PDF. It could be expanded
+# to support extra font formats if required. Be aware that many PDFs subset
+# fonts before they're embedded so glyphs may be missing or re-arranged.
+
+require 'pdf/reader'
+
+module ExtractFonts
+
+  class Extractor
+
+    def page(page)
+      count = 0
+
+      return count if page.fonts.nil? || page.fonts.empty?
+
+      page.fonts.each do |label, font|
+        next if complete_refs[label]
+        complete_refs[label] = true
+
+        process_font(page, font)
+
+        count += 1
+      end
+
+      count
+    end
+
+    private
+
+    def process_font(page, font)
+      font = page.objects.deref(font)
+
+      case font[:Subtype]
+      when :Type0 then
+        font[:DescendantFonts].each { |f| process_font(page, f) }
+      when :TrueType, :CIDFontType2 then
+        ExtractFonts::TTF.new(page.objects, font).save("#{font[:BaseFont]}.ttf")
+      else
+        $stderr.puts "unsupported font type #{font[:Subtype]} for #{font[:BaseFont]}"
+      end
+    end
+
+    def complete_refs
+      @complete_refs ||= {}
+    end
+
+  end
+
+  class TTF
+
+    def initialize(objects, font)
+      @objects, @font = objects, font
+      @descriptor = @objects.deref(@font[:FontDescriptor])
+    end
+
+    def save(filename)
+      puts "#{filename}"
+      if @descriptor && @descriptor[:FontFile2]
+        stream = @objects.deref(@descriptor[:FontFile2])
+        File.open(filename, "wb") { |file| file.write stream.unfiltered_data }
+      else
+        $stderr.puts "- TTF font not embedded"
+      end
+    end
+  end
+end
+
+if ARGV.size == 0 # default file name
+  ARGV << File.expand_path(File.join(File.dirname(__dir__), "spec", "data", "cairo-unicode.pdf")) 
+end
+
+extractor = ExtractFonts::Extractor.new
+
+ARGV.each do |arg|
+  PDF::Reader.open(arg) do |reader|
+    page = reader.page(1)
+    extractor.page(page)
+  end
+end

bin/gems/pdf-reader-2.14.1/examples/extract_images.rb

@@ -0,0 +1,231 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# This demonstrates a way to extract some images (those based on the JPG or
+# TIFF formats) from a PDF. There are other ways to store images, so
+# it may need to be expanded for real world usage, but it should serve
+# as a good guide.
+#
+# Thanks to Jack Rusher for the initial version of this example.
+
+require 'pdf/reader'
+
+module ExtractImages
+
+  class Extractor
+
+    def page(page)
+      process_page(page, 0)
+    end
+
+    private
+
+    def complete_refs
+      @complete_refs ||= {}
+    end
+
+    def process_page(page, count)
+      xobjects = page.xobjects
+      return count if xobjects.empty?
+
+      xobjects.each do |name, stream|
+        case stream.hash[:Subtype]
+        when :Image then
+          count += 1
+
+          case stream.hash[:Filter]
+          when :CCITTFaxDecode then
+            ExtractImages::Tiff.new(stream).save("#{page.number}-#{count}-#{name}.tif")
+          when :DCTDecode      then
+            ExtractImages::Jpg.new(stream).save("#{page.number}-#{count}-#{name}.jpg")
+          else
+            ExtractImages::Raw.new(stream).save("#{page.number}-#{count}-#{name}.tif")
+          end
+        when :Form then
+          count = process_page(PDF::Reader::FormXObject.new(page, stream), count)
+        end
+      end
+      count
+    end
+
+  end
+
+  class Raw
+    attr_reader :stream
+
+    def initialize(stream)
+      @stream = stream
+    end
+
+    def save(filename)
+      case @stream.hash[:ColorSpace]
+      when :DeviceCMYK then save_cmyk(filename)
+      when :DeviceGray then save_gray(filename)
+      when :DeviceRGB  then save_rgb(filename)
+      else
+        $stderr.puts "unsupport color depth #{@stream.hash[:ColorSpace]} #{filename}"
+      end
+    end
+
+    private
+
+    def save_cmyk(filename)
+      h    = stream.hash[:Height]
+      w    = stream.hash[:Width]
+      bpc  = stream.hash[:BitsPerComponent]
+      len  = stream.hash[:Length]
+      puts "#{filename}: h=#{h}, w=#{w}, bpc=#{bpc}, len=#{len}"
+
+      # Synthesize a TIFF header
+      long_tag  = lambda {|tag, count, value| [ tag, 4, count, value ].pack( "ssII" ) }
+      short_tag = lambda {|tag, count, value| [ tag, 3, count, value ].pack( "ssII" ) }
+      # header = byte order, version magic, offset of directory, directory count,
+      # followed by a series of tags containing metadata.
+      tag_count = 10
+      header = [ 73, 73, 42, 8, tag_count ].pack("ccsIs")
+      tiff = header.dup
+      tiff << short_tag.call( 256, 1, w ) # image width
+      tiff << short_tag.call( 257, 1, h ) # image height
+      tiff << long_tag.call( 258, 4, (header.size + (tag_count*12) + 4)) # bits per pixel
+      tiff << short_tag.call( 259, 1, 1 ) # compression
+      tiff << short_tag.call( 262, 1, 5 ) # colorspace - separation
+      tiff << long_tag.call( 273, 1, (10 + (tag_count*12) + 20) ) # data offset
+      tiff << short_tag.call( 277, 1, 4 ) # samples per pixel
+      tiff << long_tag.call( 279, 1, stream.unfiltered_data.size) # data byte size
+      tiff << short_tag.call( 284, 1, 1 ) # planer config
+      tiff << long_tag.call( 332, 1, 1)   # inkset - CMYK
+      tiff << [0].pack("I") # next IFD pointer
+      tiff << [bpc, bpc, bpc, bpc].pack("IIII")
+      tiff << stream.unfiltered_data
+      File.open(filename, "wb") { |file| file.write tiff }
+    end
+
+    def save_gray(filename)
+      h    = stream.hash[:Height]
+      w    = stream.hash[:Width]
+      bpc  = stream.hash[:BitsPerComponent]
+      len  = stream.hash[:Length]
+      puts "#{filename}: h=#{h}, w=#{w}, bpc=#{bpc}, len=#{len}"
+
+      # Synthesize a TIFF header
+      long_tag  = lambda {|tag, count, value| [ tag, 4, count, value ].pack( "ssII" ) }
+      short_tag = lambda {|tag, count, value| [ tag, 3, count, value ].pack( "ssII" ) }
+      # header = byte order, version magic, offset of directory, directory count,
+      # followed by a series of tags containing metadata.
+      tag_count = 9
+      header = [ 73, 73, 42, 8, tag_count ].pack("ccsIs")
+      tiff = header.dup
+      tiff << short_tag.call( 256, 1, w ) # image width
+      tiff << short_tag.call( 257, 1, h ) # image height
+      tiff << short_tag.call( 258, 1, 8 ) # bits per pixel
+      tiff << short_tag.call( 259, 1, 1 ) # compression
+      tiff << short_tag.call( 262, 1, 1 ) # colorspace - grayscale
+      tiff << long_tag.call( 273, 1, (10 + (tag_count*12) + 4) ) # data offset
+      tiff << short_tag.call( 277, 1, 1 ) # samples per pixel
+      tiff << long_tag.call( 279, 1, stream.unfiltered_data.size) # data byte size
+      tiff << short_tag.call( 284, 1, 1 ) # planer config
+      tiff << [0].pack("I") # next IFD pointer
+      p stream.unfiltered_data.size
+      tiff << stream.unfiltered_data
+      File.open(filename, "wb") { |file| file.write tiff }
+    end
+
+    def save_rgb(filename)
+      h    = stream.hash[:Height]
+      w    = stream.hash[:Width]
+      bpc  = stream.hash[:BitsPerComponent]
+      len  = stream.hash[:Length]
+      puts "#{filename}: h=#{h}, w=#{w}, bpc=#{bpc}, len=#{len}"
+
+      # Synthesize a TIFF header
+      long_tag  = lambda {|tag, count, value| [ tag, 4, count, value ].pack( "ssII" ) }
+      short_tag = lambda {|tag, count, value| [ tag, 3, count, value ].pack( "ssII" ) }
+      # header = byte order, version magic, offset of directory, directory count,
+      # followed by a series of tags containing metadata.
+      tag_count = 8
+      header = [ 73, 73, 42, 8, tag_count ].pack("ccsIs")
+      tiff = header.dup
+      tiff << short_tag.call( 256, 1, w ) # image width
+      tiff << short_tag.call( 257, 1, h ) # image height
+      tiff << long_tag.call( 258, 3, (header.size + (tag_count*12) + 4)) # bits per pixel
+      tiff << short_tag.call( 259, 1, 1 ) # compression
+      tiff << short_tag.call( 262, 1, 2 ) # colorspace - RGB
+      tiff << long_tag.call( 273, 1, (header.size + (tag_count*12) + 16) ) # data offset
+      tiff << short_tag.call( 277, 1, 3 ) # samples per pixel
+      tiff << long_tag.call( 279, 1, stream.unfiltered_data.size) # data byte size
+      tiff << [0].pack("I") # next IFD pointer
+      tiff << [bpc, bpc, bpc].pack("III")
+      tiff << stream.unfiltered_data
+      File.open(filename, "wb") { |file| file.write tiff }
+    end
+  end
+
+  class Jpg
+    attr_reader :stream
+
+    def initialize(stream)
+      @stream = stream
+    end
+
+    def save(filename)
+      w = stream.hash[:Width]
+      h = stream.hash[:Height]
+      puts "#{filename}: h=#{h}, w=#{w}"
+      File.open(filename, "wb") { |file| file.write stream.data }
+    end
+  end
+
+  class Tiff
+    attr_reader :stream
+
+    def initialize(stream)
+      @stream = stream
+    end
+
+    def save(filename)
+      if stream.hash[:DecodeParms][:K] <= 0
+        save_group_four(filename)
+      else
+        $stderr.puts "#{filename}: CCITT non-group 4/2D image."
+      end
+    end
+
+    private
+
+    # Group 4, 2D
+    def save_group_four(filename)
+      k    = stream.hash[:DecodeParms][:K]
+      h    = stream.hash[:Height]
+      w    = stream.hash[:Width]
+      bpc  = stream.hash[:BitsPerComponent]
+      mask = stream.hash[:ImageMask]
+      len  = stream.hash[:Length]
+      cols = stream.hash[:DecodeParms][:Columns]
+      puts "#{filename}: h=#{h}, w=#{w}, bpc=#{bpc}, mask=#{mask}, len=#{len}, cols=#{cols}, k=#{k}"
+
+      # Synthesize a TIFF header
+      long_tag  = lambda {|tag, value| [ tag, 4, 1, value ].pack( "ssII" ) }
+      short_tag = lambda {|tag, value| [ tag, 3, 1, value ].pack( "ssII" ) }
+      # header = byte order, version magic, offset of directory, directory count,
+      # followed by a series of tags containing metadata: 259 is a magic number for
+      # the compression type; 273 is the offset of the image data.
+      tiff = [ 73, 73, 42, 8, 5 ].pack("ccsIs") \
+      + short_tag.call( 256, cols ) \
+      + short_tag.call( 257, h ) \
+      + short_tag.call( 259, 4 ) \
+      + long_tag.call( 273, (10 + (5*12) + 4) ) \
+      + long_tag.call( 279, len) \
+      + [0].pack("I") \
+      + stream.data
+      File.open(filename, "wb") { |file| file.write tiff }
+    end
+  end
+end
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/adobe_sample.pdf"
+extractor = ExtractImages::Extractor.new
+
+PDF::Reader.open(filename) do |reader|
+  page = reader.page(1)
+  extractor.page(page)
+end

bin/gems/pdf-reader-2.14.1/examples/fuzzy_paragraphs.rb

@@ -0,0 +1,24 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# Extract an (imperfect) array of paragraphs divided somewhat
+# arbitrarily on line length. 
+
+require 'pdf/reader'
+
+reader = PDF::Reader.new('somefile.pdf')
+
+paragraph = ""
+paragraphs = []
+reader.pages.each do |page|
+  lines = page.text.scan(/^.+/)
+  lines.each do |line|
+    if line.length > 55
+      paragraph += " #{line}"
+    else
+      paragraph += " #{line}"
+      paragraphs << paragraph
+      paragraph = ""
+    end
+  end
+end

bin/gems/pdf-reader-2.14.1/examples/hash.rb

@@ -0,0 +1,12 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# get direct access to PDF objects
+
+require 'pdf/reader'
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-unicode.pdf"
+
+reader = PDF::Reader.new(filename)
+puts reader.objects[3]
+puts reader.objects[4]

bin/gems/pdf-reader-2.14.1/examples/metadata.rb

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# Extract metadata only
+
+require 'rubygems'
+require 'pdf/reader'
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cross_ref_stream.pdf"
+
+PDF::Reader.open(filename) do |reader|
+  puts reader.info.inspect
+  puts reader.metadata.inspect
+end

bin/gems/pdf-reader-2.14.1/examples/page_count.rb

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# A simple app to count the number of pages in a PDF File.
+
+require 'rubygems'
+require 'pdf/reader'
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cross_ref_stream.pdf"
+
+PDF::Reader.open(filename) do |reader|
+  puts "#{reader.page_count} page(s)"
+end

bin/gems/pdf-reader-2.14.1/examples/rspec.rb

@@ -0,0 +1,34 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+# typed: ignore
+
+#  Basic RSpec of a generated PDF
+#
+#  USAGE: rspec -c examples/rspec.rb
+
+require 'rubygems'
+require 'pdf/reader'
+require 'rspec'
+require 'prawn'
+require 'stringio'
+
+describe "My generated PDF" do
+  it "should have the correct text on 2 pages" do
+
+    # generate our PDF
+    pdf = Prawn::Document.new
+    pdf.text "Chunky"
+    pdf.start_new_page
+    pdf.text "Bacon"
+    io = StringIO.new(pdf.render)
+
+    # process the PDF
+    PDF::Reader.open(io) do |reader|
+      reader.page_count.should eql(2)          # correct page count
+
+      reader.page(1).text.should eql("Chunky") # correct content
+      reader.page(2).text.should eql("Bacon")  # correct content
+    end
+
+  end
+end

bin/gems/pdf-reader-2.14.1/examples/text.rb

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# Extract all text from a single PDF
+
+require 'rubygems'
+require 'pdf/reader'
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-unicode.pdf"
+
+PDF::Reader.open(filename) do |reader|
+  reader.pages.each do |page|
+    puts page.text
+  end
+end

bin/gems/pdf-reader-2.14.1/examples/version.rb

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+# coding: utf-8
+
+# Determine the PDF version of a file
+
+require 'rubygems'
+require 'pdf/reader'
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-basic.pdf"
+
+PDF::Reader.open(filename) do |reader|
+  puts reader.pdf_version
+end