Module: Xqsr3::XML::Utilities::Compare::Internal_Compare_

Extended by:
Quality::ParameterChecking
Includes:
Navigation
Defined in:
lib/xqsr3/xml/utilities/compare.rb

Constant Summary collapse

DEFAULT_OPTIONS = 
{

  debug: false,
#     element_order: false,
  equate_nil_and_empty: false,
  ignore_attributes: false,
  ignore_attribute_order: true,
  ignore_child_node_order: true,
  ignore_content: false,
  ignore_content_case: false,
  ignore_xml_declarations: true,
  normalise_whitespace: true,
#     normalize_whitespace: true,
  validate_params: true,
}
ORDER_OPTIONS_SYMBOLS = 
[

  :element_order,
  :ignore_attribute_order,
  :ignore_child_node_order,
  :ignore_content,
  :ignore_content_case,
]
WHITESPACE_OPTIONS_SYMBOLS = 
[

  :normalise_whitespace,
  :normalize_whitespace,
]

Class Method Summary collapse

Methods included from Navigation

#get_descendants, get_descendants, included

Class Method Details

.derive_options_(given_options) ⇒ Object 



203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
 
# File 'lib/xqsr3/xml/utilities/compare.rb', line 203

def self.derive_options_ given_options

  default_options  =  DEFAULT_OPTIONS
  derived_options  =  {}.merge given_options


  # sort whitespace

  if WHITESPACE_OPTIONS_SYMBOLS.any? { |sym| given_options.has_key? sym }

    default_options = default_options.reject { |k, v| WHITESPACE_OPTIONS_SYMBOLS.include? k }
  end

  if given_options.has_key? :normalise_whitespace

    derived_options.delete :normalize_whitespace
  elsif given_options.has_key? :normalize_whitespace

    derived_options[:normalise_whitespace] = given_options[:normalize_whitespace]

    derived_options.delete :normalize_whitespace
  end


  # sort element-order

  if ORDER_OPTIONS_SYMBOLS.any? { |sym| given_options.has_key? sym }

    default_options = default_options.reject { |k, v| ORDER_OPTIONS_SYMBOLS.include? k }
  end

  if given_options.has_key? :element_order

    element_order = given_options[:element_order]

    derived_options[:ignore_attribute_order]  =  !element_order
    derived_options[:ignore_child_node_order] = !element_order
  end

  derived_options[:ignore_attribute_order] = given_options[:ignore_attribute_order] if given_options.has_key? :ignore_attribute_order
  derived_options[:ignore_child_node_order]  =  given_options[:ignore_child_node_order] if given_options.has_key? :ignore_child_node_order

  default_options.merge derived_options
end

.one_line_(s) ⇒ Object 



248
249
250
251
 
# File 'lib/xqsr3/xml/utilities/compare.rb', line 248

def self.one_line_ s

  s = s.to_s.gsub(/\s+/, ' ')
end

.xml_compare_(lhs, rhs, options) ⇒ Object

:debug :element_order :equate_nil_and_empty :ignore_attributes :ignore_attribute_order :ignore_xml_declarations :normalise_whitespace :normalize_whitespace :validate_params



265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
 
# File 'lib/xqsr3/xml/utilities/compare.rb', line 265

def self.xml_compare_ lhs, rhs, options

  $stderr.puts "#{self}#{__method__}(lhs (#{lhs.class})=#{self.one_line_ lhs}, rhs (#{rhs.class})=#{self.one_line_ rhs}, options (#{options.class})=#{options})" if $DEBUG

  # validate parameter(s)

  check_parameter options, 'options', type: ::Hash if $DEBUG

  validate_params  =  $DEBUG || options[:debug] || options[:validate_params]

  check_parameter lhs, 'lhs', types: [ ::String, ::Nokogiri::XML::Node ], allow_nil: true if validate_params
  check_parameter rhs, 'rhs', types: [ ::String, ::Nokogiri::XML::Node ], allow_nil: true if validate_params

  options      =  self.derive_options_ options

  # deal with nil(s)

  return Result.same if lhs.nil? && rhs.nil?

  if lhs.nil?

    return Result.same if options[:equate_nil_and_empty] && ::String === rhs && rhs.empty?

    return Result.different :parameter_is_nil
  end

  if rhs.nil?

    return Result.same if options[:equate_nil_and_empty] && ::String === lhs && lhs.empty?

    return Result.different :parameter_is_nil
  end


  # deal with string(s)

  lhs  =  Nokogiri::XML(lhs) if ::String === lhs
  rhs  =  Nokogiri::XML(rhs) if ::String === rhs



  # deal with XML Declaration(s)

  if options[:ignore_xml_declarations]

    if ::Nokogiri::XML::Document === lhs

      lhs_root = lhs.root
      lhs      =  lhs_root if lhs_root
    end

    if ::Nokogiri::XML::Document === rhs

      rhs_root = rhs.root
      rhs      =  rhs_root if rhs_root
    end
  end


  self.xml_compare_nodes_ lhs, rhs, options
end

.xml_compare_nodes_(lhs, rhs, options) ⇒ Object 



327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
 
# File 'lib/xqsr3/xml/utilities/compare.rb', line 327

def self.xml_compare_nodes_ lhs, rhs, options

  $stderr.puts "#{self}#{__method__}(lhs (#{lhs.class})=#{self.one_line_ lhs}, rhs (#{rhs.class})=#{self.one_line_ rhs}, options (#{options.class})=#{options})" if $DEBUG


  # Compare:
  #
  # - name
  # - attributes
  # - content
  # - children
  # - 


  # ##########################
  # name

  lhs_name = lhs.name
  rhs_name = rhs.name

  return Result.different :different_node_names, lhs_node: lhs, rhs_node: rhs if lhs_name != rhs_name


  # ##########################
  # attributes

  unless options[:ignore_attributes]

    lhs_attributes  =  lhs.attribute_nodes
    rhs_attributes  =  rhs.attribute_nodes

    return Result.different :different_attribute_count, lhs_node: lhs, rhs_node: rhs if lhs_attributes.count != rhs_attributes.count


    lhs_attr_list = lhs_attributes.map { |attr| [ attr.name, attr.content ] }
    rhs_attr_list = rhs_attributes.map { |attr| [ attr.name, attr.content ] }

    if lhs_attr_list != rhs_attr_list

      # do the sort first

      lhs_attr_list.sort! { |l, r| l[0] <=> r[0] }
      rhs_attr_list.sort! { |l, r| l[0] <=> r[0] }

      # Now there are four possibiliies:
      #
      # 1. Different attributes
      # 2. Different attribute order
      # 3. Same (when reordered)

      if lhs_attr_list == rhs_attr_list

        if options[:ignore_attribute_order]

          # 3
        else

          # 2

          return Result.different :different_attribute_order, lhs_node: lhs, rhs_node: rhs
        end
      else

        return Result.different :different_attributes, lhs_node: lhs, rhs_node: rhs
      end
    end
  end

  # ##########################
  # content

  unless options[:ignore_content]

    lhs_texts   =  self.get_descendants(lhs).select { |el| el.text? }.map { |el| el.content }
    rhs_texts   =  self.get_descendants(rhs).select { |el| el.text? }.map { |el| el.content }

    content_same  =  lhs_texts == rhs_texts

    unless content_same

      if options[:normalise_whitespace]

        lhs_texts   =  lhs_texts.reject { |s| s.strip.empty? }
        rhs_texts   =  rhs_texts.reject { |s| s.strip.empty? }

        content_same  =  lhs_texts == rhs_texts
      end
    end

    unless content_same

      if options[:ignore_content_case]

        lhs_texts   =  lhs_texts.reject { |s| s.downcase }
        rhs_texts   =  rhs_texts.reject { |s| s.downcase }

        content_same  =  lhs_texts == rhs_texts
      end
    end

    unless content_same

      if options[:ignore_child_node_order]

        lhs_texts   =  lhs_texts.sort
        rhs_texts   =  rhs_texts.sort

        content_same  =  lhs_texts == rhs_texts
      end
    end

    return Result.different :different_node_contents, lhs_node: lhs, rhs_node: rhs unless content_same
  end


  # ##########################
  # children (preparation)

  lhs_children   =  lhs.children.to_a
  rhs_children   =  rhs.children.to_a

  lhs_children.reject! { |child| child.text? && child.content.strip.empty? }
  rhs_children.reject! { |child| child.text? && child.content.strip.empty? }


  # ##########################
  # children - count

  lhs_children_count = lhs_children.count
  rhs_children_count = rhs_children.count

  return Result.different :different_child_node_count, lhs_node: lhs, rhs_node: rhs if lhs_children_count != rhs_children_count


  # ##########################
  # children - names

  lhs_children_names = lhs_children.map { |ch| ch.name }
  rhs_children_names = rhs_children.map { |ch| ch.name }

  if lhs_children_names != rhs_children_names

    # At this point, the lists of names of child elements are
    # different. This may be because there are different
    # elements or because they are in a different order. Either
    # way, in order to provide detailed reasons for
    # inequivalency, we must do an order-independent comparison

    children_sorted_lhs = lhs_children.sort { |x, y| x.name <=> y.name }
    children_sorted_rhs = rhs_children.sort { |x, y| x.name <=> y.name }

    ch_names_sorted_lhs = children_sorted_lhs.map { |ch| ch.name }
    ch_names_sorted_rhs = children_sorted_rhs.map { |ch| ch.name }

    ignore_order    = options[:ignore_child_node_order]

    if ignore_order

      return Result.different :different_child_nodes, lhs_node: lhs, rhs_node: rhs if ch_names_sorted_lhs != ch_names_sorted_rhs

      # Since they are the same (when reordered), we need to
      # adopt the ordered sequences so that the comparison of
      # the children are meaningful

      lhs_children = children_sorted_lhs
      rhs_children = children_sorted_rhs
    else

      # failed, so need to determine whether it's due to
      # different nodes or different order

      if ch_names_sorted_lhs == ch_names_sorted_rhs

        return Result.different :different_child_node_order, lhs_node: lhs, rhs_node: rhs
      else

        return Result.different :different_child_nodes, lhs_node: lhs, rhs_node: rhs
      end
    end
  end

  (0 ... lhs_children.count).each do |index|

    ch_lhs  =  lhs_children[index]
    ch_rhs  =  rhs_children[index]

    r = self.xml_compare_nodes_ ch_lhs, ch_rhs, options

    return r unless r.status
  end

  return Result.same
end