Class: Pdfrb::Task::ExtractText::TextCollector

Inherits:
Content::Processor show all
Defined in:
lib/pdfrb/task/extract_text.rb

Overview

Internal: collects bytes from Tj / TJ / ' / +"'. Tracks text-matrix y to insert line breaks at vertical moves. Resolves glyph codes to Unicode via the active font's /ToUnicode CMap or /Encoding.

Instance Attribute Summary collapse

Attributes inherited from Content::Processor

#graphics_state, #state_stack

Instance Method Summary collapse

Methods inherited from Content::Processor

#apply_extgstate, #begin_marked_content, #end_marked_content, #marked_content_point, #paint_path, #path_close, #path_curve_to, #path_end, #path_line_to, #path_move_to, #path_rectangle, #pop_graphics_state, #process, #push_graphics_state, #set_text_matrix, #update_graphics_state

Constructor Details

#initialize(document, page) ⇒ TextCollector

Returns a new instance of TextCollector.



41
42
43
44
45
46
47
48
 
# File 'lib/pdfrb/task/extract_text.rb', line 41

def initialize(document, page)
  super()
  @document = document
  @page = page
  @text = +""
  @last_y = nil
  @font_resolver = FontResolver.new(document, page)
end

Instance Attribute Details

#text ⇒ Object (readonly)

Returns the value of attribute text.



39
40
41
 
# File 'lib/pdfrb/task/extract_text.rb', line 39

def text
  @text
end

Instance Method Details

#move_text(tx, ty) ⇒ Object 



65
66
67
68
 
# File 'lib/pdfrb/task/extract_text.rb', line 65

def move_text(tx, ty, **)
  super
  check_line_break
end

#show_text(str) ⇒ Object 



50
51
52
53
 
# File 'lib/pdfrb/task/extract_text.rb', line 50

def show_text(str)
  check_line_break
  @text << decode(str)
end

#show_text_array(arr) ⇒ Object 



55
56
57
58
59
60
61
62
63
 
# File 'lib/pdfrb/task/extract_text.rb', line 55

def show_text_array(arr)
  check_line_break
  arr.each do |e|
    case e
    when ::String then @text << decode(e)
    when Numeric then next # kerning adjustment; ignore
    end
  end
end

#update_text_state(**overrides) ⇒ Object 



70
71
72
73
 
# File 'lib/pdfrb/task/extract_text.rb', line 70

def update_text_state(**overrides)
  super
  @font_resolver.activate(graphics_state.text_state.font_name) if overrides.key?(:font_name)
end