Class: ContentData::ContentData

Inherits:
Object
  • Object
show all
Defined in:
lib/content_data/content_data.rb

Overview

Content Data(CD) object holds files information as contents and instances Files info retrieved from hardware: checksum, size, time modification, server, device and path Those attributes are divided into content and instance attributes:

unique checksum, size are content attributes
time modification, server, device and path are instance attributes

The relationship between content and instances is 1:many meaning that a content can have instances in many servers. content also has time attribute, which has the value of the time of the first instance. This can be changed by using unify_time method which sets all time attributes for a content and it’s instances to the min time off all. Different files(instances) with same content(checksum), are grouped together under that content. Interface methods include:

iterate over contents and instances info,
unify time, add/remove instance, queries, merge, remove directory and more.

Content info data structure:

@contents_info = { Checksum -> [size, *instances*, content_modification_time] }
  *instances* = {[server,path] -> [instance_modification_time,index_time] }

Notes:

1. content_modification_time is the instance_modification_time of the first
   instances which was added to @contents_info

Constant Summary collapse

CHUNK_SIZE = 
5000

Instance Method Summary collapse

Constructor Details

#initialize(other = nil) ⇒ ContentData

NOTE Cloning is time/memory expensive operation. It is highly recomended to avoid it.



38
39
40
41
42
43
44
45
46
47
48
 
# File 'lib/content_data/content_data.rb', line 38

def initialize(other = nil)
  if other.nil?
    @contents_info = {}  # Checksum --> [size, paths-->time(instance), time(content)]
    @instances_info = {}  # location --> checksum to optimize instances query
    @symlinks_info = {}  # [server,symlink path] -> target
  else
    @contents_info = other.clone_contents_info
    @instances_info = other.clone_instances_info  # location --> checksum to optimize instances query
    @symlinks_info =  other.clone_symlinks_info
  end
end

Instance Method Details

#==(other) ⇒ Object 



284
285
286
287
 
# File 'lib/content_data/content_data.rb', line 284

def ==(other)
  return nil if other.nil?  # for this case: content_data == nil
  unique_id  == other.unique_id
end

#add_instance(checksum, size, server, path, modification_time, index_time = Time.now.to_i) ⇒ Object 



187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
 
# File 'lib/content_data/content_data.rb', line 187

def add_instance(checksum, size, server, path, modification_time, index_time=Time.now.to_i)
  location = [server, path]

  # file was changed but remove_instance was not called
  if (@instances_info.include?(location) && @instances_info[location] != checksum)
    Log.warning("#{server}:#{path} file already exists with different checksum")
    remove_instance(server, path)
  end

  content_info = @contents_info[checksum]
  if content_info.nil?
    @contents_info[checksum] = [size,
                                {location => [modification_time,index_time]},
                                modification_time]
  else
    if size != content_info[0]
      Log.warning('File size different from content size while same checksum')
      Log.warning("instance location:server:'#{location[0]}'  path:'#{location[1]}'")
      Log.warning("instance mod time:'#{modification_time}'")
    end
    #override file if needed
    content_info[0] = size
    instances = content_info[1]
    instances[location] = [modification_time, index_time]
  end
  @instances_info[location] = checksum
end

#add_symlink(server, path, target) ⇒ Object 



215
216
217
 
# File 'lib/content_data/content_data.rb', line 215

def add_symlink(server, path, target)
  @symlinks_info[[server,path]] = target
end

#checksum_instances_size(checksum) ⇒ Object 



173
174
175
176
177
 
# File 'lib/content_data/content_data.rb', line 173

def checksum_instances_size(checksum)
  content_info = @contents_info[checksum]
  return 0 if content_info.nil?
  content_info[1].length
end

#clone_contents_info ⇒ Object 



66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
 
# File 'lib/content_data/content_data.rb', line 66

def clone_contents_info
  clone_contents_info = {}
  contents_info_enum = @contents_info.each_key
  loop {
    checksum = contents_info_enum.next rescue break
    instances = @contents_info[checksum]
    size = instances[0]
    content_time = instances[2]
    instances_db = instances[1]
    instances_db_cloned = {}
    instances_db_enum = instances_db.each_key
    loop {
      location =  instances_db_enum.next rescue break
      inst_mod_times = instances_db[location]
      # we use deep clone for location since map key is using shallow clone.
      # we dont want references between new content data
      # and orig object. This will help the GC dispose the orig object if not used any more.
      instances_db_cloned[[location[0].clone,location[1].clone]] = inst_mod_times.clone
    }
    clone_contents_info[checksum] = [size,
                          instances_db_cloned,
                          content_time]
  }
  clone_contents_info
end

#clone_instances_info ⇒ Object 



56
57
58
59
60
61
62
63
64
 
# File 'lib/content_data/content_data.rb', line 56

def clone_instances_info
  clone_instances_info = {}
  instances_info_enum = @instances_info.each_key
  loop {
    location = instances_info_enum.next rescue break
    clone_instances_info[[location[0].clone, location[1].clone]] = @instances_info[location].clone
  }
  clone_instances_info
end

#clone_symlinks_info ⇒ Object 



92
93
94
95
96
97
98
99
100
 
# File 'lib/content_data/content_data.rb', line 92

def clone_symlinks_info
  symlinks_info_enum = @symlinks_info.each_key
  cloned_symlinks = {}
  loop {
    symlink_key = symlinks_info_enum.next rescue break
    cloned_symlinks[[symlink_key[0].clone, symlink_key[0].clone]] = @symlinks_info[symlink_key].clone
  }
  cloned_symlinks
end

#content_each_instance(checksum, &block) ⇒ Object

iterator of instances over specific content block is provided with: checksum, size, content modification time,

instance modification time, server and file path



137
138
139
140
141
142
143
144
145
146
147
148
 
# File 'lib/content_data/content_data.rb', line 137

def content_each_instance(checksum, &block)
  content_info = @contents_info[checksum]
  instances_db_enum = content_info[1].each_key
  loop {
    location = instances_db_enum.next rescue break
    # provide the block with: checksum, size, content modification time,instance modification time,
    #   server and path.
    inst_mod_time,_ = content_info[1][location]
    block.call(checksum,content_info[0], content_info[2], inst_mod_time,
               location[0], location[1])
  }
end

#content_exists(checksum) ⇒ Object 



227
228
229
 
# File 'lib/content_data/content_data.rb', line 227

def content_exists(checksum)
  @contents_info.has_key?(checksum)
end

#contents_size ⇒ Object 



161
162
163
 
# File 'lib/content_data/content_data.rb', line 161

def contents_size()
  @contents_info.length
end

#each_content(&block) ⇒ Object

iterator over @contents_info data structure (not including instances) block is provided with: checksum, size and content modification time



104
105
106
107
108
109
110
111
112
 
# File 'lib/content_data/content_data.rb', line 104

def each_content(&block)
  contents_enum = @contents_info.each_key
  loop {
    checksum = contents_enum.next rescue break
    content_val = @contents_info[checksum]
    # provide checksum, size and content modification time to the block
    block.call(checksum,content_val[0], content_val[2])
  }
end

#each_instance(&block) ⇒ Object

iterator over @contents_info data structure (including instances) block is provided with: checksum, size, content modification time,

instance modification time, server and file path



117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
# File 'lib/content_data/content_data.rb', line 117

def each_instance(&block)
  contents_enum = @contents_info.each_key
  loop {
    checksum = contents_enum.next rescue break
    content_info = @contents_info[checksum]
    content_info_enum = content_info[1].each_key
    loop {
      location = content_info_enum.next rescue break
      # provide the block with: checksum, size, content modification time,instance modification time,
      #   server and path.
      inst_mod_time, inst_index_time = content_info[1][location]
      block.call(checksum,content_info[0], content_info[2], inst_mod_time,
                 location[0], location[1], inst_index_time)
    }
  }
end

#each_symlink(&block) ⇒ Object

iterator over @symlinks_info data structure block is provided with: server, file path and target



152
153
154
155
156
157
158
159
 
# File 'lib/content_data/content_data.rb', line 152

def each_symlink(&block)
  symlink_enum = @symlinks_info.each_key
  loop {
    symlink_key = symlink_enum.next rescue break
    symlink_target = @symlinks_info[symlink_key]
    block.call(symlink_key[0], symlink_key[1], symlink_target)
  }
end

#empty? ⇒ Boolean

Returns:

  • (Boolean) 


223
224
225
 
# File 'lib/content_data/content_data.rb', line 223

def empty?
  @contents_info.empty? and @symlinks_info.empty?
end

#from_file(filename) ⇒ Object

Imports content data from file. This method will throw an exception if the file is not in correct format.



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
 
# File 'lib/content_data/content_data.rb', line 343

def from_file(filename)
  unless File.exists? filename
    raise ArgumentError.new "No such a file #{filename}"
  end

  number_of_instances = nil
  number_of_symlinks = nil
  Zlib::GzipReader.open(filename) { |gz|
    gz.each_line do |line|
      row = line.parse_csv
      if number_of_instances == nil
        begin
          # get number of instances
          number_of_instances = row[0].to_i
        rescue ArgumentError
          raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
                "number of instances should be a Number. We got:#{number_of_instances}")
        end
      elsif number_of_instances > 0
        if (6 != row.length)
          raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
                    "Expected to read 6 fields ('<' separated) but got #{row.length}.\nLine:#{instance_line}")
        end
        add_instance(row[0],        #checksum
                     row[1].to_i,   # size
                     row[2],        # server
                     row[3],        # path
                     row[4].to_i,   # mod time
                     row[5].to_i)   # index time
        number_of_instances -= 1
      elsif number_of_symlinks == nil
        begin
          # get number of symlinks
          number_of_symlinks = row[0].to_i
        rescue ArgumentError
          raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
                "number of symlinks should be a Number. We got:#{number_of_symlinks}")
        end
      elsif number_of_symlinks > 0
        if (3 != row.length)
          raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
                "Expected to read 3 fields ('<' separated) but got #{row.length}.\nLine:#{symlinks_line}")
        end
        @symlinks_info[[row[0], row[1]]] = row[2]
        number_of_symlinks -= 1 
      end
    end
  }
end

#from_file_old(filename) ⇒ Object

TODO validation that file indeed contains ContentData missing TODO class level method? Loading db from file using chunks for better memory performance



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
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
 
# File 'lib/content_data/content_data.rb', line 466

def from_file_old(filename)
  # read first line (number of contents)
  # calculate line number (number of instances)
  # read number of instances.
  # loop over instances lines (using chunks) and add instances

  unless File.exists? filename
    raise ArgumentError.new "No such a file #{filename}"
  end

  File.open(filename, 'r') { |file|
    # Get number of contents (at first line)
    number_of_contents = file.gets  # this gets the next line or return nil at EOF
    unless (number_of_contents and number_of_contents.match(/^[\d]+$/))  # check that line is of Number format
      raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
            "number of contents should be a number. We got:#{number_of_contents}")
    end
    number_of_contents = number_of_contents.to_i
    # advance file lines over all contents. We need only the instances data to build the content data object
    # use chunks and GC
    contents_chunks = number_of_contents / CHUNK_SIZE
    contents_chunks += 1 if (contents_chunks * CHUNK_SIZE < number_of_contents)
    chunk_index = 0
    while chunk_index < contents_chunks
      chunk_size = CHUNK_SIZE
      if chunk_index + 1 == contents_chunks
        # update last chunk size
        chunk_size = number_of_contents - (chunk_index * CHUNK_SIZE)
      end
      return unless read_old_contents_chunk(filename, file, chunk_size)
      GC.start
      chunk_index += 1
    end

    # get number of instances
    number_of_instances = file.gets
    unless (number_of_instances and number_of_instances.match(/^[\d]+$/))  # check that line is of Number format
      raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
            "number of instances should be a Number. We got:#{number_of_instances}")
    end
    number_of_instances = number_of_instances.to_i
    # read in instances chunks and GC
    instances_chunks = number_of_instances / CHUNK_SIZE
    instances_chunks += 1 if (instances_chunks * CHUNK_SIZE < number_of_instances)
    chunk_index = 0
    while chunk_index < instances_chunks
      chunk_size = CHUNK_SIZE
      if chunk_index + 1 == instances_chunks
        # update last chunk size
        chunk_size = number_of_instances - (chunk_index * CHUNK_SIZE)
      end
      return unless read_old_instances_chunk(filename, file, chunk_size)
      GC.start
      chunk_index += 1
    end

    # get number of symlinks
    number_of_symlinks = file.gets
    unless (number_of_symlinks and number_of_symlinks.match(/^[\d]+$/))  # check that line is of Number format
      raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
                "number of symlinks should be a Number. We got:#{number_of_symlinks}")
    end
    number_of_symlinks.to_i.times {
      symlinks_line = file.gets.strip
      unless symlinks_line
        raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
               "Expected to read symlink line but reached EOF")
      end
      parameters = symlinks_line.split(',')
      if (3 != parameters.length)
        raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
              "Expected to read 3 fields (comma separated) but got #{parameters.length}.\nLine:#{symlinks_line}")
      end

      @symlinks_info[[parameters[0],parameters[1]]] = parameters[2]
    }
  }
end

#get_instance_mod_time(checksum, location) ⇒ Object 



179
180
181
182
183
184
185
 
# File 'lib/content_data/content_data.rb', line 179

def get_instance_mod_time(checksum, location)
  content_info = @contents_info[checksum]
  return nil if content_info.nil?
  instances = content_info[1]
  instance_time,_ = instances[location]
  instance_time
end

#get_query(variable, params) ⇒ Object

TODO simplify conditions This mehod is experimental and shouldn't be used nil is used to define +/- infinity for to/from method arguments from/to values are exlusive in condition’a calculations Need to take care about ‘==’ operation that is used for object’s comparison. In need of case user should define it’s own ‘==’ implemementation.



754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
 
# File 'lib/content_data/content_data.rb', line 754

def get_query(variable, params)
  raise RuntimeError.new 'This method is experimental and shouldn\'t be used'

  exact = params['exact'].nil? ? Array.new : params['exact']
  from = params['from']
  to = params ['to']
  is_inside = params['is_inside']

  unless ContentInstance.new.instance_variable_defined?("@#{attribute}")
    raise ArgumentError "#{variable} isn't a ContentInstance variable"
  end

  if (exact.nil? && from.nil? && to.nil?)
    raise ArgumentError 'At least one of the argiments {exact, from, to} must be defined'
  end

  if (!(from.nil? || to.nil?) && from.kind_of?(to.class))
    raise ArgumentError 'to and from arguments should be comparable one with another'
  end

  # FIXME add support for from/to for Strings
  if ((!from.nil? && !from.kind_of?(Numeric.new.class))\
        || (!to.nil? && to.kind_of?(Numeric.new.class)))
    raise ArgumentError 'from and to options supported only for numeric values'
  end

  if (!exact.empty? && (!from.nil? || !to.nil?))
    raise ArgumentError 'exact and from/to options are mutually exclusive'
  end

  result_index = ContentData.new
  instances.each_value do |instance|
    is_match = false
    var_value = instance.instance_variable_get("@#{variable}")

    if exact.include? var_value
      is_match = true
    elsif (from.nil? || var_value > from) && (to.nil? || var_value < to)
      is_match = true
    end

    if (is_match && is_inside) || (!is_match && !is_inside)
      checksum = instance.checksum
      result_index.add_content(contents[checksum]) unless result_index.content_exists(checksum)
      result_index.add_instance instance
    end
  end
  result_index
end

#instance_exists(path, server) ⇒ Object 



231
232
233
 
# File 'lib/content_data/content_data.rb', line 231

def instance_exists(path, server)
  @instances_info.has_key?([server, path])
end

#instances_size ⇒ Object 



165
166
167
 
# File 'lib/content_data/content_data.rb', line 165

def instances_size()
  @instances_info.length
end

#read_old_contents_chunk(filename, file, chunk_size) ⇒ Object 



545
546
547
548
549
550
551
552
553
554
555
 
# File 'lib/content_data/content_data.rb', line 545

def read_old_contents_chunk(filename, file, chunk_size)
  chunk_index = 0
  while chunk_index < chunk_size
    unless file.gets
      raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
            "Expecting content line but reached end of file")
    end
    chunk_index += 1
  end
  true
end

#read_old_instances_chunk(filename, file, chunk_size) ⇒ Object 



557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
 
# File 'lib/content_data/content_data.rb', line 557

def read_old_instances_chunk(filename, file, chunk_size)
  chunk_index = 0
  while chunk_index < chunk_size
    instance_line = file.gets
    unless instance_line
      raise("Parse error of content data file:#{filename}  line ##{$.}\n" +
            "Expected to read Instance line but reached EOF")
    end

    parameters = instance_line.split(',')
    # bugfix: if file name consist a comma then parsing based on comma separating fails
    if (parameters.size > 6)
      (4..parameters.size-3).each do |i|
        parameters[3] = [parameters[3], parameters[i]].join(",")
      end
      (4..parameters.size-3).each do |i|
        parameters.delete_at(4)
      end
    end

    add_instance(parameters[0],        #checksum
                 parameters[1].to_i,   # size
                 parameters[2],        # server
                 parameters[3],        # path
                 parameters[4].to_i,   # mod time
                 parameters[5].to_i)   # index time
    chunk_index += 1
  end
  true
end

#remove_content(checksum) ⇒ Object 



289
290
291
292
293
294
295
296
297
 
# File 'lib/content_data/content_data.rb', line 289

def remove_content(checksum)
  content_info = @contents_info[checksum]
  if content_info
    content_info[1].each_key { |location|
      @instances_info.delete(location)
    }
    @contents_info.delete(checksum)
  end
end

#remove_directory(dir_to_remove, server) ⇒ Object

removes all instances records which are located under input param: dir_to_remove. found records are removed from @contents_info , @instances_info and @symlinks_info input params: server & dir_to_remove - are used to check each instance unique key (called location) removes also contents, if a contents becomes empty after removing instances



258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
 
# File 'lib/content_data/content_data.rb', line 258

def remove_directory(dir_to_remove, server)
  contents_enum = @contents_info.each_key
  loop {
    checksum = contents_enum.next rescue break
    instances =  @contents_info[checksum][1]
    instances_enum = instances.each_key
    loop {
      location = instances_enum.next rescue break
      if location[0] == server and location[1].scan(dir_to_remove).size > 0
        instances.delete(location)
        @instances_info.delete(location)
      end
    }
    @contents_info.delete(checksum) if instances.empty?
  }

  # handle symlinks
  symlinks_enum = @symlinks_info.each_key
  loop {
    symlink_key = symlinks_enum.next rescue break
    if symlink_key[0] == server and symlink_key[1].scan(dir_to_remove).size > 0
      @symlinks_info.delete(symlink_key)
    end
  }
end

#remove_instance(server, path) ⇒ Object

removes an instance record both in @instances_info and @instances_info. input params: server & path - are the instance unique key (called location) removes also the content, if content becomes empty after removing the instance



243
244
245
246
247
248
249
250
251
252
 
# File 'lib/content_data/content_data.rb', line 243

def remove_instance(server, path)
  location = [server, path]
  checksum = @instances_info[location]
  content_info = @contents_info[checksum]
  return nil if content_info.nil?
  instances = content_info[1]
  instances.delete(location)
  @contents_info.delete(checksum) if instances.empty?
  @instances_info.delete(location)
end

#remove_symlink(server, path) ⇒ Object 



219
220
221
 
# File 'lib/content_data/content_data.rb', line 219

def remove_symlink(server, path)
  @symlinks_info.delete([server,path])
end

#symlink_exists(path, server) ⇒ Object 



235
236
237
 
# File 'lib/content_data/content_data.rb', line 235

def symlink_exists(path, server)
  @symlinks_info.has_key?([server, path])
end

#symlinks_size ⇒ Object 



169
170
171
 
# File 'lib/content_data/content_data.rb', line 169

def symlinks_size()
  @symlinks_info.length
end

#to_file(filename) ⇒ Object

Write content data to file.



326
327
328
329
330
331
332
333
334
335
336
337
338
339
 
# File 'lib/content_data/content_data.rb', line 326

def to_file(filename)
  content_data_dir = File.dirname(filename)
  FileUtils.makedirs(content_data_dir) unless File.directory?(content_data_dir)
  Zlib::GzipWriter.open(filename) do |gz| 
    gz.write [@instances_info.length].to_csv
    each_instance { |checksum, size, content_mod_time, instance_mod_time, server, path, inst_index_time|
      gz.write [checksum, size, server, path, instance_mod_time, inst_index_time].to_csv
    }
    gz.write [@symlinks_info.length].to_csv
    each_symlink { |file, path, target|
      gz.write [file, path, target].to_csv
    }
  end
end

#to_file_old(filename) ⇒ Object

Deprecated.

DEPRECATED: Old deprecated from/to file methods still needed for migration purposes Write content data to file. Write is using chunks (for both content chunks and instances chunks) Chunk is used to maximize GC affect. The temporary memory of each chunk is GCed. Without the chunks used in a dipper stack level, GC keeps the temporary objects as part of the stack context.



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
 
# File 'lib/content_data/content_data.rb', line 399

def to_file_old(filename)
  content_data_dir = File.dirname(filename)
  FileUtils.makedirs(content_data_dir) unless File.directory?(content_data_dir)
  File.open(filename, 'w') { |file|
    # Write contents
    file.write("#{@contents_info.length}\n")
    contents_enum = @contents_info.each_key
    content_chunks = @contents_info.length / CHUNK_SIZE + 1
    chunks_counter = 0
    while chunks_counter < content_chunks
      to_old_file_contents_chunk(file,contents_enum, CHUNK_SIZE)
      GC.start
      chunks_counter += 1
    end

    # Write instances
    file.write("#{@instances_info.length}\n")
    contents_enum = @contents_info.each_key
    chunks_counter = 0
    while chunks_counter < content_chunks
      to_old_file_instances_chunk(file,contents_enum, CHUNK_SIZE)
      GC.start
      chunks_counter += 1
    end

    # Write symlinks
    symlinks_info_enum = @symlinks_info.each_key
    file.write("#{@symlinks_info.length}\n")
    loop {
      symlink_key = symlinks_info_enum.next rescue break
      file.write("#{symlink_key[0]},#{symlink_key[1]},#{@symlinks_info[symlink_key]}\n")
    }
  }
end

#to_old_file_contents_chunk(file, contents_enum, chunk_size) ⇒ Object 



434
435
436
437
438
439
440
441
442
 
# File 'lib/content_data/content_data.rb', line 434

def to_old_file_contents_chunk(file, contents_enum, chunk_size)
  chunk_counter = 0
  while chunk_counter < chunk_size
    checksum = contents_enum.next rescue return
    content_info = @contents_info[checksum]
    file.write("#{checksum},#{content_info[0]},#{content_info[2]}\n")
    chunk_counter += 1
  end
end

#to_old_file_instances_chunk(file, contents_enum, chunk_size) ⇒ Object 



444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
 
# File 'lib/content_data/content_data.rb', line 444

def to_old_file_instances_chunk(file, contents_enum, chunk_size)
  chunk_counter = 0
  while chunk_counter < chunk_size
    checksum = contents_enum.next rescue return
    content_info = @contents_info[checksum]
    instances_db_enum = content_info[1].each_key
    loop {
      location = instances_db_enum.next rescue break
      # provide the block with: checksum, size, content modification time,instance modification time,
      #   server and path.
      instance_modification_time,instance_index_time = content_info[1][location]
      file.write("#{checksum},#{content_info[0]},#{location[0]},#{location[1]}," +
                 "#{instance_modification_time},#{instance_index_time}\n")
    }
    chunk_counter += 1
    break if chunk_counter == chunk_size
  end
end

#to_s ⇒ Object

Don’t use in production, only for testing.



300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
 
# File 'lib/content_data/content_data.rb', line 300

def to_s
  return_str = ""
  contents_str = ""
  instances_str = ""
  each_content { |checksum, size, content_mod_time|
    contents_str << "%s,%d,%d\n" % [checksum, size, content_mod_time]
  }
  each_instance { |checksum, size, content_mod_time, instance_mod_time, server, path|
    instances_str <<  "%s,%d,%s,%s,%d\n" % [checksum, size, server, path, instance_mod_time]
  }
  return_str << "%d\n" % [@contents_info.length]
  return_str << contents_str
  return_str << "%d\n" % [@instances_info.length]
  return_str << instances_str


  symlinks_str = ""
  each_symlink { |server, path, target|
    symlinks_str << "%s,%s,%s\n" % [server, path, target]
  }
  return_str << symlinks_str

  return_str
end

#unify_time ⇒ Object

for each content, all time fields (content and instances) are replaced with the min time found, while going through all time fields.



591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
 
# File 'lib/content_data/content_data.rb', line 591

def unify_time()
  contents_enum = @contents_info.each_key
  loop {
    checksum = contents_enum.next rescue break
    content_info = @contents_info[checksum]
    min_time_per_checksum = content_info[2]
    instances = content_info[1]
    instances_enum = instances.each_key
    loop {
      location = instances_enum.next rescue break
      instance_mod_time = instances[location][0]
      if instance_mod_time < min_time_per_checksum
        min_time_per_checksum = instance_mod_time
      end
    }
    # update all instances with min time
    instances_enum = instances.each_key
    loop {
      location = instances_enum.next rescue break
      instances[location][0] = min_time_per_checksum
    }
    # update content time with min time
    content_info[2] = min_time_per_checksum
  }
end

#unique_id ⇒ ID

Content Data unique identification

Returns:

  • (ID) —

    hash identification



52
53
54
 
# File 'lib/content_data/content_data.rb', line 52

def unique_id
  [@contents_info.hash,@symlinks_info.hash]
end

#validate(params = nil) ⇒ Boolean

Validates index against file system that all instances hold a correct data regarding files that they represents.

There are two levels of validation, controlled by instance_check_level system parameter:

  • shallow - quick, tests instance for file existence and attributes.

  • deep - can take more time, in addition to shallow recalculates hash sum.

Parameters:

  • params (Hash) (defaults to: nil) —

    hash of parameters of validation, can be used to return additional data.

    Supported key/value combinations:

    • key is :failed value is ContentData used to return failed instances

Returns:

  • (Boolean) —

    true when index is correct, false otherwise

Raises:

  • (ArgumentError) —

    when instance_check_level is incorrect



629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
 
# File 'lib/content_data/content_data.rb', line 629

def validate(params = nil)
  # used to answer whether specific param was set
  param_exists = Proc.new do |param|
    !(params.nil? || params[param].nil?)
  end

  # used to process method parameters centrally
  process_params = Proc.new do |values|
    if param_exists.call(:failed)
      info = values[:details]
      unless info.nil?
        checksum = info[0]
        content_mtime = info[1]
        size = info[2]
        inst_mtime = info[3]
        server = info[4]
        file_path = info[5]
        params[:failed].add_instance(checksum, size, server, file_path, inst_mtime)
      end
    end
  end

  is_valid = true
  contents_enum = @contents_info.each_key
  loop {
    checksum = contents_enum.next rescue break
    instances = @contents_info[checksum]
    content_size = instances[0]
    content_mtime = instances[2]
    instances_enum = instances[1].each_key
    loop {
      unique_path = instances_enum.next rescue break
      instance_mtime = instances[1][unique_path][0]
      instance_info = [checksum, content_mtime, content_size, instance_mtime]
      instance_info.concat(unique_path)
      unless check_instance(instance_info)
        is_valid = false

        unless params.nil? || params.empty?
          process_params.call({:details => instance_info})
        end
      end
    }
  }
  is_valid
end