Class: Tabula::ObjectExtractor::RulingReceiver

Inherits:
Object
  • Object
show all
Defined in:
lib/tabula/pdf/object_extractor.rb

Overview

Receiver for extracting ruling lines from PDF graphics

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(page_height, y_inverted: false) ⇒ RulingReceiver

Returns a new instance of RulingReceiver.



199
200
201
202
203
204
205
206
207
 
# File 'lib/tabula/pdf/object_extractor.rb', line 199

def initialize(page_height, y_inverted: false)
  @page_height = page_height
  @y_inverted = y_inverted
  @rulings = []
  @current_path = []
  @subpaths = [] # Collect all subpaths for filling
  @ctm = [[1, 0, 0], [0, 1, 0], [0, 0, 1]]
  @graphics_state_stack = []
end

Instance Attribute Details

#rulings ⇒ Object (readonly)

Returns the value of attribute rulings.



197
198
199
 
# File 'lib/tabula/pdf/object_extractor.rb', line 197

def rulings
  @rulings
end

Instance Method Details

#append_line(x, y) ⇒ Object 



216
217
218
 
# File 'lib/tabula/pdf/object_extractor.rb', line 216

def append_line(x, y)
  @current_path << [transform_point(x, y), :line]
end

#append_rectangle(x, y, width, height) ⇒ Object 



220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
 
# File 'lib/tabula/pdf/object_extractor.rb', line 220

def append_rectangle(x, y, width, height)
  # Convert rectangle to four lines
  p1 = transform_point(x, y)
  p2 = transform_point(x + width, y)
  p3 = transform_point(x + width, y + height)
  p4 = transform_point(x, y + height)

  @current_path = [
    [p1, :move],
    [p2, :line],
    [p3, :line],
    [p4, :line],
    [p1, :line]
  ]
end

#begin_new_subpath(x, y) ⇒ Object

Path construction



210
211
212
213
214
 
# File 'lib/tabula/pdf/object_extractor.rb', line 210

def begin_new_subpath(x, y)
  # Save current subpath if it has content
  @subpaths << @current_path.dup if @current_path.any?
  @current_path = [[transform_point(x, y), :move]]
end

#close_and_stroke_path ⇒ Object 



270
271
272
273
 
# File 'lib/tabula/pdf/object_extractor.rb', line 270

def close_and_stroke_path
  close_path
  stroke_path
end

#close_fill_stroke ⇒ Object 



275
276
277
278
 
# File 'lib/tabula/pdf/object_extractor.rb', line 275

def close_fill_stroke
  close_path
  stroke_path
end

#close_path ⇒ Object 



284
285
286
287
288
289
 
# File 'lib/tabula/pdf/object_extractor.rb', line 284

def close_path
  return if @current_path.empty?

  first_point = @current_path.first[0]
  @current_path << [first_point, :line]
end

#concatenate_matrix(a, b, c, d, e, f) ⇒ Object

CTM operations



292
293
294
295
 
# File 'lib/tabula/pdf/object_extractor.rb', line 292

def concatenate_matrix(a, b, c, d, e, f)
  matrix = [[a, b, 0], [c, d, 0], [e, f, 1]]
  @ctm = matrix_multiply(matrix, @ctm)
end

#end_path ⇒ Object 



280
281
282
 
# File 'lib/tabula/pdf/object_extractor.rb', line 280

def end_path
  @current_path = []
end

#fill_path_with_even_odd ⇒ Object 



256
257
258
259
260
261
262
263
264
265
266
267
268
 
# File 'lib/tabula/pdf/object_extractor.rb', line 256

def fill_path_with_even_odd
  # Include current path
  @subpaths << @current_path.dup if @current_path.any?

  # Process all subpaths
  @subpaths.each do |subpath|
    @current_path = subpath
    extract_rulings_from_filled_path
  end

  @current_path = []
  @subpaths = []
end

#fill_path_with_nonzero ⇒ Object 



242
243
244
245
246
247
248
249
250
251
252
253
254
 
# File 'lib/tabula/pdf/object_extractor.rb', line 242

def fill_path_with_nonzero
  # Include current path
  @subpaths << @current_path.dup if @current_path.any?

  # Process all subpaths
  @subpaths.each do |subpath|
    @current_path = subpath
    extract_rulings_from_filled_path
  end

  @current_path = []
  @subpaths = []
end

#restore_graphics_state ⇒ Object 



301
302
303
 
# File 'lib/tabula/pdf/object_extractor.rb', line 301

def restore_graphics_state
  @ctm = @graphics_state_stack.pop || [[1, 0, 0], [0, 1, 0], [0, 0, 1]]
end

#save_graphics_state ⇒ Object 



297
298
299
 
# File 'lib/tabula/pdf/object_extractor.rb', line 297

def save_graphics_state
  @graphics_state_stack.push(@ctm.map(&:dup))
end

#stroke_path ⇒ Object

Path painting



237
238
239
240
 
# File 'lib/tabula/pdf/object_extractor.rb', line 237

def stroke_path
  extract_lines_from_path
  @current_path = []
end