nfcollector 3.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (60) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +17 -0
  3. data/.rspec +3 -0
  4. data/.rvmrc +1 -0
  5. data/Gemfile +8 -0
  6. data/LICENSE.txt +22 -0
  7. data/README.md +29 -0
  8. data/Rakefile +1 -0
  9. data/lib/nfcollector.rb +41 -0
  10. data/lib/nfcollector/attribute_validator.rb +59 -0
  11. data/lib/nfcollector/attributes.rb +99 -0
  12. data/lib/nfcollector/categoriser.rb +43 -0
  13. data/lib/nfcollector/category_partition.rb +17 -0
  14. data/lib/nfcollector/configuration.rb +24 -0
  15. data/lib/nfcollector/copy_file_writer.rb +47 -0
  16. data/lib/nfcollector/domain_parser.rb +49 -0
  17. data/lib/nfcollector/input_definition.rb +31 -0
  18. data/lib/nfcollector/mapping.rb +7 -0
  19. data/lib/nfcollector/mapping/categories_processor.rb +36 -0
  20. data/lib/nfcollector/mapping/column_transpiler.rb +29 -0
  21. data/lib/nfcollector/mapping/default_output.rb +45 -0
  22. data/lib/nfcollector/mapping/effective_tld_names.dat +4394 -0
  23. data/lib/nfcollector/mapping/indexer.rb +21 -0
  24. data/lib/nfcollector/mapping/mapped_row.rb +21 -0
  25. data/lib/nfcollector/mapping/output.rb +59 -0
  26. data/lib/nfcollector/mapping/transpiler.rb +92 -0
  27. data/lib/nfcollector/nfcollector_exception.rb +4 -0
  28. data/lib/nfcollector/partition.rb +76 -0
  29. data/lib/nfcollector/partitioner.rb +37 -0
  30. data/lib/nfcollector/payload_processor.rb +46 -0
  31. data/lib/nfcollector/sequence_generator.rb +11 -0
  32. data/lib/nfcollector/version.rb +3 -0
  33. data/lib/nfcollector/weblog_partition.rb +26 -0
  34. data/nfcollector.gemspec +30 -0
  35. data/spec/attribute_validator_spec.rb +23 -0
  36. data/spec/attributes_spec.rb +15 -0
  37. data/spec/command_parser_spec.rb +81 -0
  38. data/spec/copy_file_writer_spec.rb +95 -0
  39. data/spec/input_definition_spec.rb +18 -0
  40. data/spec/nfcollector/category_partitioner_spec.rb +51 -0
  41. data/spec/nfcollector/date_partitioner_spec.rb +19 -0
  42. data/spec/nfcollector/input_definition_spec.rb +32 -0
  43. data/spec/nfcollector/mapping/column_transpiler_spec.rb +26 -0
  44. data/spec/nfcollector/mapping/output_spec.rb +76 -0
  45. data/spec/nfcollector/mapping/transpiler_spec.rb +47 -0
  46. data/spec/payload_job_spec.rb +11 -0
  47. data/spec/payload_processor_spec.rb +114 -0
  48. data/spec/spec_helper.rb +89 -0
  49. data/test/domains_hosts +194826 -0
  50. data/test/generate_input.rb +79 -0
  51. data/test/input/input-1000.csv +1000 -0
  52. data/test/input/input-100000.csv +100000 -0
  53. data/test/input/input-100000.dat +64039 -0
  54. data/test/input/input-no-tags.csv +3 -0
  55. data/test/input/input-no-tags.dat +3 -0
  56. data/test/input/input-no-tags.gz +0 -0
  57. data/test/input/input-with-tags.csv.gz +0 -0
  58. data/test/test_helper.rb +15 -0
  59. data/test/tester.rb +32 -0
  60. metadata +252 -0
@@ -0,0 +1,3 @@
1
+ 10.1.1.56,A,www.google.com,/search,macbook01.local,2011-07-11 14:56:10.000,ddraper,200,text/html,5576,1
2
+ 10.1.1.56,A,www.google.com,/search,macbook01.local,2011-07-11 14:56:10.000,ddraper,200,text/html,5576,1
3
+ 10.1.1.56,A,www.google.com,/search,macbook01.local,2011-07-12 14:56:10.000,ddraper,200,text/html,5576,1
@@ -0,0 +1,3 @@
1
+ eJzVzUEKgzAURdF5V9EFPL//iYngrEtJY1Bowi9pIF1+3UKHcod3cKjCM+fx
2
+ QO9ddrM9J4lWMH5SqPFACfFp9lJKthgyJiUHXQbyznl1fqWKqmLbaninen5F
3
+ S982Hq1kOLd48MYLONMfzg8+4Fmo
@@ -0,0 +1,15 @@
1
+ require 'byebug'
2
+ require 'stringio'
3
+ require 'shoulda'
4
+ require 'timecop'
5
+ require 'differ'
6
+
7
+ require "test/unit"
8
+ require "mocha"
9
+
10
+ require File.dirname(__FILE__) + '/../lib/nfcollector'
11
+
12
+ def assert_strings_equal(expected, actual)
13
+ message = "Expected:\n#{expected}\n#{"-"*20}\nActual:\n#{actual}\n#{"-"*20}\nDiff:\n#{Differ.diff_by_line(actual, expected).format_as(:color)}"
14
+ assert(expected == actual, message)
15
+ end
@@ -0,0 +1,32 @@
1
+ #!/usr/bin/ruby
2
+
3
+ # Ensure local load path
4
+ $: << "."
5
+
6
+ require "rubygems"
7
+ require "bundler/setup"
8
+
9
+ require 'logger'
10
+ require 'zlib'
11
+
12
+ require 'payload_processor'
13
+
14
+ logger = Logger.new(STDOUT)
15
+
16
+ begin
17
+ processor = PayloadProcessor.new
18
+
19
+ processor.account_id = 40
20
+ processor.process_attribute_codes(">a,Rr,Rh,Rp,>A,t,Un,Hs,mt,<s,Cs,Rc")
21
+
22
+ contents = File.new('input/input-100000.csv').read
23
+ contents = Base64.encode64(Zlib::Deflate::deflate(contents)).tr("+/", "-_")
24
+ processor.io = StringIO.new(contents)
25
+
26
+ start_time = Time.now
27
+ processor.process_payload
28
+ end_time = Time.now
29
+ puts "Processing Time: #{end_time - start_time}"
30
+ rescue
31
+ logger.error $!
32
+ end
metadata ADDED
@@ -0,0 +1,252 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: nfcollector
3
+ version: !ruby/object:Gem::Version
4
+ version: 3.2.0
5
+ platform: ruby
6
+ authors:
7
+ - Dan Draper
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-09-13 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: test-unit
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: '0'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ">="
25
+ - !ruby/object:Gem::Version
26
+ version: '0'
27
+ - !ruby/object:Gem::Dependency
28
+ name: rspec
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ">="
32
+ - !ruby/object:Gem::Version
33
+ version: '0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ">="
39
+ - !ruby/object:Gem::Version
40
+ version: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: shoulda
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: timecop
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: differ
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: byebug
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: activerecord
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ - !ruby/object:Gem::Dependency
112
+ name: domainatrix
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - ">="
116
+ - !ruby/object:Gem::Version
117
+ version: 0.0.10
118
+ type: :runtime
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - ">="
123
+ - !ruby/object:Gem::Version
124
+ version: 0.0.10
125
+ - !ruby/object:Gem::Dependency
126
+ name: activesupport
127
+ requirement: !ruby/object:Gem::Requirement
128
+ requirements:
129
+ - - ">="
130
+ - !ruby/object:Gem::Version
131
+ version: '3.2'
132
+ type: :runtime
133
+ prerelease: false
134
+ version_requirements: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - ">="
137
+ - !ruby/object:Gem::Version
138
+ version: '3.2'
139
+ description: Data collection system for NetFox
140
+ email:
141
+ - daniel@codefire.com
142
+ executables: []
143
+ extensions: []
144
+ extra_rdoc_files: []
145
+ files:
146
+ - ".gitignore"
147
+ - ".rspec"
148
+ - ".rvmrc"
149
+ - Gemfile
150
+ - LICENSE.txt
151
+ - README.md
152
+ - Rakefile
153
+ - lib/nfcollector.rb
154
+ - lib/nfcollector/attribute_validator.rb
155
+ - lib/nfcollector/attributes.rb
156
+ - lib/nfcollector/categoriser.rb
157
+ - lib/nfcollector/category_partition.rb
158
+ - lib/nfcollector/configuration.rb
159
+ - lib/nfcollector/copy_file_writer.rb
160
+ - lib/nfcollector/domain_parser.rb
161
+ - lib/nfcollector/input_definition.rb
162
+ - lib/nfcollector/mapping.rb
163
+ - lib/nfcollector/mapping/categories_processor.rb
164
+ - lib/nfcollector/mapping/column_transpiler.rb
165
+ - lib/nfcollector/mapping/default_output.rb
166
+ - lib/nfcollector/mapping/effective_tld_names.dat
167
+ - lib/nfcollector/mapping/indexer.rb
168
+ - lib/nfcollector/mapping/mapped_row.rb
169
+ - lib/nfcollector/mapping/output.rb
170
+ - lib/nfcollector/mapping/transpiler.rb
171
+ - lib/nfcollector/nfcollector_exception.rb
172
+ - lib/nfcollector/partition.rb
173
+ - lib/nfcollector/partitioner.rb
174
+ - lib/nfcollector/payload_processor.rb
175
+ - lib/nfcollector/sequence_generator.rb
176
+ - lib/nfcollector/version.rb
177
+ - lib/nfcollector/weblog_partition.rb
178
+ - nfcollector.gemspec
179
+ - spec/attribute_validator_spec.rb
180
+ - spec/attributes_spec.rb
181
+ - spec/command_parser_spec.rb
182
+ - spec/copy_file_writer_spec.rb
183
+ - spec/input_definition_spec.rb
184
+ - spec/nfcollector/category_partitioner_spec.rb
185
+ - spec/nfcollector/date_partitioner_spec.rb
186
+ - spec/nfcollector/input_definition_spec.rb
187
+ - spec/nfcollector/mapping/column_transpiler_spec.rb
188
+ - spec/nfcollector/mapping/output_spec.rb
189
+ - spec/nfcollector/mapping/transpiler_spec.rb
190
+ - spec/payload_job_spec.rb
191
+ - spec/payload_processor_spec.rb
192
+ - spec/spec_helper.rb
193
+ - test/domains_hosts
194
+ - test/generate_input.rb
195
+ - test/input/input-1000.csv
196
+ - test/input/input-100000.csv
197
+ - test/input/input-100000.dat
198
+ - test/input/input-no-tags.csv
199
+ - test/input/input-no-tags.dat
200
+ - test/input/input-no-tags.gz
201
+ - test/input/input-with-tags.csv.gz
202
+ - test/test_helper.rb
203
+ - test/tester.rb
204
+ homepage: ''
205
+ licenses: []
206
+ metadata: {}
207
+ post_install_message:
208
+ rdoc_options: []
209
+ require_paths:
210
+ - lib
211
+ required_ruby_version: !ruby/object:Gem::Requirement
212
+ requirements:
213
+ - - ">="
214
+ - !ruby/object:Gem::Version
215
+ version: '0'
216
+ required_rubygems_version: !ruby/object:Gem::Requirement
217
+ requirements:
218
+ - - ">="
219
+ - !ruby/object:Gem::Version
220
+ version: '0'
221
+ requirements: []
222
+ rubyforge_project:
223
+ rubygems_version: 2.2.2
224
+ signing_key:
225
+ specification_version: 4
226
+ summary: Data Collection
227
+ test_files:
228
+ - spec/attribute_validator_spec.rb
229
+ - spec/attributes_spec.rb
230
+ - spec/command_parser_spec.rb
231
+ - spec/copy_file_writer_spec.rb
232
+ - spec/input_definition_spec.rb
233
+ - spec/nfcollector/category_partitioner_spec.rb
234
+ - spec/nfcollector/date_partitioner_spec.rb
235
+ - spec/nfcollector/input_definition_spec.rb
236
+ - spec/nfcollector/mapping/column_transpiler_spec.rb
237
+ - spec/nfcollector/mapping/output_spec.rb
238
+ - spec/nfcollector/mapping/transpiler_spec.rb
239
+ - spec/payload_job_spec.rb
240
+ - spec/payload_processor_spec.rb
241
+ - spec/spec_helper.rb
242
+ - test/domains_hosts
243
+ - test/generate_input.rb
244
+ - test/input/input-1000.csv
245
+ - test/input/input-100000.csv
246
+ - test/input/input-100000.dat
247
+ - test/input/input-no-tags.csv
248
+ - test/input/input-no-tags.dat
249
+ - test/input/input-no-tags.gz
250
+ - test/input/input-with-tags.csv.gz
251
+ - test/test_helper.rb
252
+ - test/tester.rb