Module: Pdfrb::Task::ExtractImages

Defined in:
lib/pdfrb/task/extract_images.rb

Overview

Walk each page's /Resources/XObject for Image XObjects and yield (page, name, image_stream). Returns a flat list when no block.

Defined Under Namespace

Classes: ImageInfo

Class Method Summary collapse

Class Method Details

.call(document) ⇒ Object 



13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
 
# File 'lib/pdfrb/task/extract_images.rb', line 13

def call(document)
  results = []
  document.pages.each_with_index do |page, idx|
    xobjects = xobject_map(page, document)
    xobjects&.each do |name, ref|
      stream = ref.is_a?(Pdfrb::Model::Reference) ?
                 document.object(ref) : ref
      next unless stream.is_a?(Pdfrb::Model::Cos::Stream)
      next unless stream.value[:Subtype] == :Image

      info = ImageInfo.new(
        page_index: idx,
        name: name.to_s,
        stream: stream,
        width: stream.value[:Width],
        height: stream.value[:Height],
        filter: stream.value[:Filter]
      )
      block_given? ? yield(info) : (results << info)
    end
  end
  block_given? ? document : results
end

.xobject_map(page, document) ⇒ Object 



37
38
39
40
41
42
43
44
45
46
47
48
49
 
# File 'lib/pdfrb/task/extract_images.rb', line 37

def xobject_map(page, document)
  # /Resources can be inheritable from a parent Pages node.
  resources = page.value[:Resources]
  if resources.nil?
    parent_ref = page.value[:Parent]
    parent = parent_ref && document.object(parent_ref)
    resources = parent&.value&.dig(:Resources) if parent
  end
  return nil unless resources

  resources = resources.value if resources.is_a?(Pdfrb::Model::Cos::Dictionary)
  resources[:XObject]
end