Class: S3

Inherits:
Object
  • Object
show all
Includes:
AWS
Defined in:
lib/OriginalAWS/S3.rb

Constant Summary collapse

S3_ENDPOINT = 
"s3.amazonaws.com"
XMLNS = 
'http://s3.amazonaws.com/doc/2006-03-01/'

Instance Method Summary collapse

Instance Method Details

#build_post_form(bucket_name, key, options = {}) ⇒ Object 



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
544
545
546
547
548
549
550
551
552
553
554
555
556
557
 
# File 'lib/OriginalAWS/S3.rb', line 499

def build_post_form(bucket_name, key, options={})
  fields = []

  # Form is only authenticated if a policy is specified.
  if options[:expiration] or options[:conditions]
    # Generate policy document
    policy = build_post_policy(options[:expiration], options[:conditions])
    puts "POST Policy\n===========\n#{policy}\n\n" if @debug

    # Add the base64-encoded policy document as the 'policy' field
    policy_b64 = encode_base64(policy)
    fields << %{<input type="hidden" name="policy" value="#{policy_b64}">}

    # Add the AWS access key as the 'AWSAccessKeyId' field
    fields << %{<input type="hidden" name="AWSAccessKeyId"
                                     value="#{@aws_access_key}">}

    # Add signature for encoded policy document as the 'AWSAccessKeyId' field
    signature = generate_signature(policy_b64)
    fields << %{<input type="hidden" name="signature" value="#{signature}">}
  end

  # Include any additional fields
  options[:fields].each_pair do |n,v|
    if v.nil?
      # Allow users to provide their own <input> fields as text.
      fields << n
    else
      fields << %{<input type="hidden" name="#{n}" value="#{v}">}
    end
  end if options[:fields]

  # Add the vital 'file' input item, which may be a textarea or file.
  if options[:text_input]
    # Use the text_input option which should specify a textarea or text
    # input field. For example:
    # '<textarea name="file" cols="80" rows="5">Default Text</textarea>'
    fields << options[:text_input]
  else
    fields << %{<input name="file" type="file">}
  end

  # Construct a sub-domain URL to refer to the target bucket. The
  # HTTPS protocol will be used if the secure HTTP option is enabled.
  url = "http#{@secure_http ? 's' : ''}://#{bucket_name}.s3.amazonaws.com/"

  # Construct the entire form.
  form = %{
    <form action="#{url}" method="post" enctype="multipart/form-data">
      <input type="hidden" name="key" value="#{key}">
      #{fields.join("\n")}
      <br>
      <input type="submit" value="Upload to Amazon S3">
    </form>
    }
  puts "POST Form\n=========\n#{form}\n" if @debug

  return form
end

#build_post_policy(expiration_time, conditions) ⇒ Object 



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
 
# File 'lib/OriginalAWS/S3.rb', line 466

def build_post_policy(expiration_time, conditions)
  if expiration_time.nil? or not expiration_time.respond_to?(:getutc)
    raise 'Policy document must include a valid expiration Time object'
  end
  if conditions.nil? or not conditions.class == Hash
    raise 'Policy document must include a valid conditions Hash object'
  end

  # Convert conditions object mappings to condition statements
  conds = []
  conditions.each_pair do |name,test|
    if test.nil?
      # A nil condition value means allow anything.
      conds << %{["starts-with", "$#{name}", ""]}
    elsif test.is_a? String
      conds << %{{"#{name}": "#{test}"}}
    elsif test.is_a? Array
      conds << %{{"#{name}": "#{test.join(',')}"}}
    elsif test.is_a? Hash
      operation = test[:op]
      value = test[:value]
      conds << %{["#{operation}", "$#{name}", "#{value}"]}
    elsif test.is_a? Range
      conds << %{["#{name}", #{test.begin}, #{test.end}]}
    else
      raise "Unexpected value type for condition '#{name}': #{test.class}"
    end
  end

  return %{{"expiration": "#{expiration_time.getutc.iso8601}",
            "conditions": [#{conds.join(",")}]}}
end

#copy_object(source_bucket_name, source_object_key, dest_bucket_name, dest_object_key, acl = nil, new_metadata = nil) ⇒ Object

The copy object feature was added to the S3 API after the release of “Programming Amazon Web Services” so it is not discussed in the book’s text. For more details, see: www.jamesmurty.com/2008/05/06/s3-copy-object-in-beta/



241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
 
# File 'lib/OriginalAWS/S3.rb', line 241

def copy_object(source_bucket_name, source_object_key, 
  dest_bucket_name, dest_object_key, acl=nil, new_metadata=nil)

  headers = {}

  # Identify the source object
  headers['x-amz-copy-source'] = CGI::escape(
    source_bucket_name + '/' + source_object_key)

  # Copy metadata from original object, or replace the metadata.
  if new_metadata.nil?
    headers['x-amz-metadata-directive'] = 'COPY'
  else
    headers['x-amz-metadata-directive'] = 'REPLACE'
    headers.merge!(new_metadata)
  end

  # The Content-Length header must always be set when data is uploaded.
  headers['Content-Length'] = '0'

  # Set the canned policy, may be: 'private', 'public-read',
  # 'public-read-write', 'authenticated-read'
  headers['x-amz-acl'] = acl if acl

  uri = generate_s3_uri(dest_bucket_name, dest_object_key)
  do_rest('PUT', uri, nil, headers)
  return true
end

#create_bucket(bucket_name, location = nil) ⇒ Object 



102
103
104
105
106
107
108
109
110
111
112
113
114
115
 
# File 'lib/OriginalAWS/S3.rb', line 102

def create_bucket(bucket_name, location=nil)
  uri = generate_s3_uri(bucket_name)

  if location
    xml_doc = REXML::Document.new("<CreateBucketConfiguration/>")
    xml_doc.root.add_attribute('xmlns', XMLNS)
    xml_doc.root.add_element('LocationConstraint').text = location
    do_rest('PUT', uri, xml_doc.to_s, {'Content-Type'=>'text/xml'})
  else
    do_rest('PUT', uri)
  end

  return true
end

#create_object(bucket_name, object_key, opts = {}) ⇒ Object 



190
191
192
193
194
195
196
197
198
199
200
201
202
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
 
# File 'lib/OriginalAWS/S3.rb', line 190

def create_object(bucket_name, object_key, opts={})
  # Initialize local variables for the provided option items
  data = (opts[:data] ? opts[:data] : '')
  headers = (opts[:headers] ? opts[:headers].clone : {})
  metadata = (opts[:metadata] ? opts[:metadata].clone : {})

  # The Content-Length header must always be set when data is uploaded.
  headers['Content-Length'] =
        (data.respond_to?(:stat) ? data.stat.size : data.size).to_s

  # Calculate an md5 hash of the data for upload verification
  if data.respond_to?(:stat)
    # Generate MD5 digest from file data one chunk at a time
    md5_digest = Digest::MD5.new
    File.open(data.path, 'rb') do |io|
      buffer = ''
      md5_digest.update(buffer) while io.read(4096, buffer)
    end
    md5_hash = md5_digest.digest
  else
    md5_hash = Digest::MD5.digest(data)
  end
  headers['Content-MD5'] = encode_base64(md5_hash)

  # Set the canned policy, may be: 'private', 'public-read',
  # 'public-read-write', 'authenticated-read'
  headers['x-amz-acl'] = opts[:policy] if opts[:policy]

  # Set an explicit content type if none is provided, otherwise the
  # ruby HTTP library will use its own default type
  # 'application/x-www-form-urlencoded'
  if not headers['Content-Type']
    headers['Content-Type'] =
      data.respond_to?(:to_str) ? 'text/plain' : 'application/octet-stream'
  end

  # Convert metadata items to headers using the
  # S3 metadata header name prefix.
  metadata.each do |n,v|
    headers["x-amz-meta-#{n}"] = v
  end

  uri = generate_s3_uri(bucket_name, object_key)
  do_rest('PUT', uri, data, headers)
  return true
end

#delete_bucket(bucket_name) ⇒ Object 



117
118
119
120
121
 
# File 'lib/OriginalAWS/S3.rb', line 117

def delete_bucket(bucket_name)
  uri = generate_s3_uri(bucket_name)
  do_rest('DELETE', uri)
  return true
end

#delete_object(bucket_name, object_key) ⇒ Object 



270
271
272
273
274
 
# File 'lib/OriginalAWS/S3.rb', line 270

def delete_object(bucket_name, object_key)
  uri = generate_s3_uri(bucket_name, object_key)
  do_rest('DELETE', uri)
  return true
end

#generate_s3_uri(bucket_name = '', object_name = '', params = []) ⇒ Object 



33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
 
# File 'lib/OriginalAWS/S3.rb', line 33

def generate_s3_uri(bucket_name='', object_name='', params=[])
  # Decide between the default and sub-domain host name formats
  if valid_dns_name(bucket_name)
    hostname = bucket_name + "." + S3_ENDPOINT
  else
    hostname = S3_ENDPOINT
  end

  # Build an initial secure or non-secure URI for the end point.
  request_uri = (@secure_http ? "https://" : "http://") + hostname;

  # Include the bucket name in the URI except for alternative hostnames
  if hostname == S3_ENDPOINT
    request_uri << '/' + URI.escape(bucket_name) if bucket_name != ''
  end

  # Add object name component to URI if present
  request_uri << '/' + URI.escape(object_name) if object_name != ''

  # Add request parameters to the URI. Each item in the params variable
  # is a hash dictionary containing multiple keys.
  query = ""
  params.each do |hash|
    hash.each do |name, value|
      query << '&' if query.length > 0

      if value.nil?
        query << "#{name}"
      else
        query << "#{name}=#{CGI::escape(value.to_s)}"
      end
    end
  end
  request_uri << "?" + query if query.length > 0

  return URI.parse(request_uri)
end

#get_acl(bucket_name, object_key = '') ⇒ Object 



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/OriginalAWS/S3.rb', line 360

def get_acl(bucket_name, object_key='')
  uri = generate_s3_uri(bucket_name, object_key, [:acl=>nil])
  response = do_rest('GET', uri)

  xml_doc = REXML::Document.new(response.body)

  grants = []

  xml_doc.elements.each('//Grant') do |grant|
    grantee = {}

    grantee[:type] = grant.elements['Grantee'].attributes['type']

    if grantee[:type] == 'Group'
      grantee[:uri] = grant.elements['Grantee/URI'].text
    else
      grantee[:id] = grant.elements['Grantee/ID'].text
      grantee[:display_name] = grant.elements['Grantee/DisplayName'].text
    end

    grants << {
      :grantee => grantee,
      :permission => grant.elements['Permission'].text
    }
  end

  return {
    :owner_id => xml_doc.elements['//Owner/ID'].text,
    :owner_name => xml_doc.elements['//Owner/DisplayName'].text,
    :grants => grants
  }
end

#get_bucket_location(bucket_name) ⇒ Object 



123
124
125
126
127
128
129
 
# File 'lib/OriginalAWS/S3.rb', line 123

def get_bucket_location(bucket_name)
  uri = generate_s3_uri(bucket_name, '', [:location=>nil])
  response = do_rest('GET', uri)

  xml_doc = REXML::Document.new(response.body)
  return xml_doc.elements['LocationConstraint'].text
end

#get_logging(bucket_name) ⇒ Object 



326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
 
# File 'lib/OriginalAWS/S3.rb', line 326

def get_logging(bucket_name)
  uri = generate_s3_uri(bucket_name, '', [:logging=>nil])
  response = do_rest('GET', uri)

  xml_doc = REXML::Document.new(response.body)

  if xml_doc.elements['//LoggingEnabled']
    return {
      :target_bucket => xml_doc.elements['//TargetBucket'].text,
      :target_prefix => xml_doc.elements['//TargetPrefix'].text
    }
  else
    # Logging is not enabled
    return nil
  end
end

#get_object(bucket_name, object_key, headers = {}) ⇒ Object 



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
 
# File 'lib/OriginalAWS/S3.rb', line 297

def get_object(bucket_name, object_key, headers={})
  uri = generate_s3_uri(bucket_name, object_key)

  if block_given?
    response = do_rest('GET', uri, nil, headers) {|segment| yield(segment)}
  else
    response = do_rest('GET', uri, nil, headers)
  end

  response_headers = {}
  metadata = {}

  response.each_header do |name,value|
    if name.index('x-amz-meta-') == 0
      metadata[name['x-amz-meta-'.length..-1]] = value
    else
      response_headers[name] = value
    end
  end

  result = {
    :metadata => metadata,
    :headers => response_headers
  }
  result[:body] = response.body if not block_given?

  return result
end

#get_object_metadata(bucket_name, object_key, headers = {}) ⇒ Object 



276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
 
# File 'lib/OriginalAWS/S3.rb', line 276

def get_object_metadata(bucket_name, object_key, headers={})
  uri = generate_s3_uri(bucket_name, object_key)
  response = do_rest('HEAD', uri, nil, headers)

  response_headers = {}
  metadata = {}

  response.each_header do |name,value|
    if name.index('x-amz-meta-') == 0
      metadata[name['x-amz-meta-'.length..-1]] = value
    else
      response_headers[name] = value
    end
  end

  return {
    :metadata => metadata,
    :headers => response_headers
  }
end

#get_owner_id ⇒ Object 



72
73
74
75
76
77
78
79
 
# File 'lib/OriginalAWS/S3.rb', line 72

def get_owner_id
  uri = generate_s3_uri()
  response = do_rest('GET', uri)
  buckets = []

  xml_doc = REXML::Document.new(response.body)
  xml_doc.elements['//Owner/ID'].text
end

#get_torrent(bucket_name, object_key, output) ⇒ Object 



440
441
442
443
444
 
# File 'lib/OriginalAWS/S3.rb', line 440

def get_torrent(bucket_name, object_key, output)
  uri = generate_s3_uri(bucket_name, object_key, [:torrent=>nil])
  response = do_rest('GET', uri)
  output.write(response.body)
end

#list_buckets ⇒ Object 



81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'lib/OriginalAWS/S3.rb', line 81

def list_buckets
  uri = generate_s3_uri()
  response = do_rest('GET', uri)
  buckets = []

  xml_doc = REXML::Document.new(response.body)

  xml_doc.elements.each('//Buckets/Bucket') do |bucket|
    buckets << {
      :name => bucket.elements['Name'].text,
      :creation_date => bucket.elements['CreationDate'].text
    }
  end

  return {
    :owner_id => xml_doc.elements['//Owner/ID'].text,
    :display_name => xml_doc.elements['//Owner/DisplayName'].text,
    :buckets => buckets
  }
end

#list_objects(bucket_name, *params) ⇒ Object 



131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
 
# File 'lib/OriginalAWS/S3.rb', line 131

def list_objects(bucket_name, *params)
  is_truncated = true

  objects = []
  prefixes = []

  while is_truncated
    uri = generate_s3_uri(bucket_name, '', params)
    response = do_rest('GET', uri)

    xml_doc = REXML::Document.new(response.body)

    xml_doc.elements.each('//Contents') do |contents|
      objects << {
        :key => contents.elements['Key'].text,
        :size => contents.elements['Size'].text,
        :last_modified => contents.elements['LastModified'].text,
        :etag => contents.elements['ETag'].text,
        :owner_id => contents.elements['Owner/ID'].text,
        :owner_name => contents.elements['Owner/DisplayName'].text
      }
    end

    cps = xml_doc.elements.to_a('//CommonPrefixes')
    if cps.length > 0
      cps.each do |cp|
        prefixes << cp.elements['Prefix'].text
      end
    end

    # Determine whether listing is truncated
    is_truncated = 'true' == xml_doc.elements['//IsTruncated'].text

    # Remove any existing marker value
    params.delete_if {|p| p[:marker]}

    # Set the marker parameter to the NextMarker if possible,
    # otherwise set it to the last key name in the listing
    next_marker_elem = xml_doc.elements['//NextMarker']
    last_key_elem = xml_doc.elements['//Contents/Key[last()]']

    if next_marker_elem
      params << {:marker => next_marker_elem.text}
    elsif last_key_elem
      params << {:marker => last_key_elem.text}
    else
      params << {:marker => ''}
    end

  end

  return {
    :bucket_name => bucket_name,
    :objects => objects,
    :prefixes => prefixes
  }
end

#set_acl(owner_id, bucket_name, object_key = '', grants = [owner_id=>'FULL_CONTROL']) ⇒ Object 



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
 
# File 'lib/OriginalAWS/S3.rb', line 393

def set_acl(owner_id, bucket_name, object_key='',
            grants=[owner_id=>'FULL_CONTROL'])

  xml_doc = REXML::Document.new("<AccessControlPolicy xmlns='#{XMLNS}'/>")
  xml_doc.root.add_element('Owner').add_element('ID').text = owner_id
  grant_list = xml_doc.root.add_element('AccessControlList')

  grants.each do |hash|
    hash.each do |grantee_id, permission|

      grant = grant_list.add_element('Grant')
      grant.add_element('Permission').text = permission

      # Grantee may be of type email, group, or canonical user
      if grantee_id.index('@')
        # Email grantee
        grantee = grant.add_element('Grantee',
          {'xmlns:xsi'=>'http://www.w3.org/2001/XMLSchema-instance',
           'xsi:type'=>'AmazonCustomerByEmail'})
        grantee.add_element('EmailAddress').text = grantee_id
      elsif grantee_id.index('://')
        # Group grantee
        grantee = grant.add_element('Grantee',
          {'xmlns:xsi'=>'http://www.w3.org/2001/XMLSchema-instance',
           'xsi:type'=>'Group'})
        grantee.add_element('URI').text = grantee_id
      else
        # Canonical user grantee
        grantee = grant.add_element('Grantee',
          {'xmlns:xsi'=>'http://www.w3.org/2001/XMLSchema-instance',
           'xsi:type'=>'CanonicalUser'})
        grantee.add_element('ID').text = grantee_id
      end
    end
  end

  uri = generate_s3_uri(bucket_name, object_key, [:acl=>nil])
  do_rest('PUT', uri, xml_doc.to_s, {'Content-Type'=>'application/xml'})
  return true
end

#set_canned_acl(canned_acl, bucket_name, object_key = '') ⇒ Object 



434
435
436
437
438
 
# File 'lib/OriginalAWS/S3.rb', line 434

def set_canned_acl(canned_acl, bucket_name, object_key='')
  uri = generate_s3_uri(bucket_name, object_key, [:acl=>nil])
  response = do_rest('PUT', uri, nil, {'x-amz-acl'=>canned_acl})
  return true
end

#set_logging(bucket_name, target_bucket = nil, target_prefix = "#{bucket_name}.") ⇒ Object 



343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
 
# File 'lib/OriginalAWS/S3.rb', line 343

def set_logging(bucket_name, target_bucket=nil,
                target_prefix="#{bucket_name}.")

  # Build BucketLoggingStatus XML document
  xml_doc = REXML::Document.new("<BucketLoggingStatus xmlns='#{XMLNS}'/>")

  if target_bucket
    logging_enabled = xml_doc.root.add_element('LoggingEnabled')
    logging_enabled.add_element('TargetBucket').text = target_bucket
    logging_enabled.add_element('TargetPrefix').text = target_prefix
  end

  uri = generate_s3_uri(bucket_name, '', [:logging=>nil])
  do_rest('PUT', uri, xml_doc.to_s, {'Content-Type'=>'application/xml'})
  return true
end

#sign_uri(method, expires, bucket_name, object_key = '', opts = {}) ⇒ Object 



446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
 
# File 'lib/OriginalAWS/S3.rb', line 446

def sign_uri(method, expires, bucket_name, object_key='', opts={})
  parameters = opts[:parameters] || []
  headers = opts[:headers] || {}

  headers['Date'] = expires

  uri = generate_s3_uri(bucket_name, object_key, parameters)
  signature = generate_rest_signature(method, uri, headers)

  uri.query = (uri.query.nil? ? '' : "#{uri.query}&")
  uri.query << "Signature=" + CGI::escape(signature)
  uri.query << "&Expires=" + expires.to_s
  uri.query << "&AWSAccessKeyId=" + @aws_access_key

  uri.host = bucket_name if opts[:is_virtual_host]

  return uri.to_s
end

#valid_dns_name(bucket_name) ⇒ Object 



16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
 
# File 'lib/OriginalAWS/S3.rb', line 16

def valid_dns_name(bucket_name)
  if bucket_name.size > 63 or bucket_name.size < 3
    return false
  end

  return false unless bucket_name =~ /^[a-z0-9][a-z0-9.-]+$/

  return false unless bucket_name =~ /[a-z]/ # Cannot be an IP address

  bucket_name.split('.').each do |fragment|
    return false if fragment =~ /^-/ or fragment =~ /-$/ or fragment =~ /^$/
  end

  return true
end