despamilator 0.4 → 0.5

Sign up to get free protection for your applications and to get access to all the features.
data/History.txt CHANGED
@@ -19,3 +19,7 @@
19
19
  * urls.rb
20
20
 
21
21
  * Added spam and non-spam samples.
22
+
23
+ === 0.5 2010-08-31
24
+
25
+ * Added Rails validation sugar (despamilator/validation).
data/Manifest.txt CHANGED
@@ -19,6 +19,7 @@ lib/despamilator/filter/shouting.rb
19
19
  lib/despamilator/filter/square_brackets.rb
20
20
  lib/despamilator/filter/urls.rb
21
21
  lib/despamilator/filter_base.rb
22
+ lib/despamilator/validation.rb
22
23
  scripts/despamilator_score.rb
23
24
  spec/clean_corpus/101.txt.gz
24
25
  spec/clean_corpus/103.txt.gz
@@ -127,6 +128,7 @@ spec/clean_corpus/97.txt.gz
127
128
  spec/clean_corpus/99.txt.gz
128
129
  spec/clean_corpus_spec.rb
129
130
  spec/despamilator_spec.rb
131
+ spec/despamilator_validation_spec.rb
130
132
  spec/filters/funky_consonant_spec.rb
131
133
  spec/filters/html_tags_spec.rb
132
134
  spec/filters/ip_address_url_spec.rb
data/README.rdoc CHANGED
@@ -10,7 +10,7 @@ some commonly used heuristics from the world of anti-spam to help you decide whe
10
10
 
11
11
  == FEATURES/PROBLEMS:
12
12
 
13
- * rspec will be run twice. How annoying?!
13
+ * Added sexy rails validation!! :D
14
14
 
15
15
  == SYNOPSIS:
16
16
 
@@ -44,6 +44,15 @@ some commonly used heuristics from the world of anti-spam to help you decide whe
44
44
  end
45
45
  end
46
46
 
47
+ == RAILS SYNOPSIS:
48
+
49
+ # in your environment.rb
50
+ require 'despamilator/validation'
51
+
52
+ # in your model
53
+ validates_despamilation_of :some_field, :threshold => 1
54
+
55
+
47
56
  == FILTERING:
48
57
 
49
58
  As stated, this is a heuristic scanner so its up to the user to decide the thresholds of the scanner. I usually
data/Rakefile CHANGED
@@ -29,5 +29,5 @@ task :install => [:install_gem]
29
29
 
30
30
  task :cultivate do
31
31
  system "touch Manifest.txt; rake check_manifest | grep -v \"(in \" | patch"
32
- system "rake debug_gem | grep -v \"(in \" > `basename \\`pwd\\``.gemspec"
32
+ system "rake debug_gem | grep -v \"(in \" > `basename \\`pwd\\``.gemspec |grep -v _spec.rb |grep -v _corpus"
33
33
  end
data/despamliator.gemspec CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  Gem::Specification.new do |s|
4
4
  s.name = %q{despamilator}
5
- s.version = "0.4"
5
+ s.version = "0.5"
6
6
 
7
7
  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
8
8
  s.authors = ["Stephen Hardisty"]
@@ -12,7 +12,7 @@ Spam being submitted in my web forms and CAPTCHAS being intrusive. Despamilator
12
12
  some commonly used heuristics from the world of anti-spam to help you decide whether your users are human or machine.}
13
13
  s.email = ["moowahaha@hotmail.com"]
14
14
  s.extra_rdoc_files = ["History.txt", "Manifest.txt", "PostInstall.txt"]
15
- s.files = ["History.txt", "Manifest.txt", "PostInstall.txt", "README.rdoc", "Rakefile", "despamilator.gemspec", "despamliator.gemspec", "lib/despamilator.rb", "lib/despamilator/filter.rb", "lib/despamilator/filter/funky_consonant.rb", "lib/despamilator/filter/html_tags.rb", "lib/despamilator/filter/ip_address_url.rb", "lib/despamilator/filter/long_words.rb", "lib/despamilator/filter/naughty_q.rb", "lib/despamilator/filter/naughty_words.rb", "lib/despamilator/filter/numbers_and_words.rb", "lib/despamilator/filter/script_tag.rb", "lib/despamilator/filter/shouting.rb", "lib/despamilator/filter/square_brackets.rb", "lib/despamilator/filter/urls.rb", "lib/despamilator/filter_base.rb", "scripts/despamilator_score.rb", "spec/clean_corpus/101.txt.gz", "spec/clean_corpus/103.txt.gz", "spec/clean_corpus/105.txt.gz", "spec/clean_corpus/107.txt.gz", "spec/clean_corpus/109.txt.gz", "spec/clean_corpus/111.txt.gz", "spec/clean_corpus/113.txt.gz", "spec/clean_corpus/115.txt.gz", "spec/clean_corpus/117.txt.gz", "spec/clean_corpus/119.txt.gz", "spec/clean_corpus/121.txt.gz", "spec/clean_corpus/123.txt.gz", "spec/clean_corpus/125.txt.gz", "spec/clean_corpus/127.txt.gz", "spec/clean_corpus/129.txt.gz", "spec/clean_corpus/131.txt.gz", "spec/clean_corpus/133.txt.gz", "spec/clean_corpus/135.txt.gz", "spec/clean_corpus/137.txt.gz", "spec/clean_corpus/139.txt.gz", "spec/clean_corpus/141.txt.gz", "spec/clean_corpus/143.txt.gz", "spec/clean_corpus/145.txt.gz", "spec/clean_corpus/147.txt.gz", "spec/clean_corpus/149.txt.gz", "spec/clean_corpus/151.txt.gz", "spec/clean_corpus/153.txt.gz", "spec/clean_corpus/155.txt.gz", "spec/clean_corpus/157.txt.gz", "spec/clean_corpus/159.txt.gz", "spec/clean_corpus/161.txt.gz", "spec/clean_corpus/163.txt.gz", "spec/clean_corpus/165.txt.gz", "spec/clean_corpus/167.txt.gz", "spec/clean_corpus/169.txt.gz", "spec/clean_corpus/171.txt.gz", "spec/clean_corpus/173.txt.gz", "spec/clean_corpus/175.txt.gz", "spec/clean_corpus/177.txt.gz", "spec/clean_corpus/179.txt.gz", "spec/clean_corpus/18.txt.gz", "spec/clean_corpus/181.txt.gz", "spec/clean_corpus/183.txt.gz", "spec/clean_corpus/185.txt.gz", "spec/clean_corpus/187.txt.gz", "spec/clean_corpus/189.txt.gz", "spec/clean_corpus/191.txt.gz", "spec/clean_corpus/193.txt.gz", "spec/clean_corpus/195.txt.gz", "spec/clean_corpus/197.txt.gz", "spec/clean_corpus/199.txt.gz", "spec/clean_corpus/20.txt.gz", "spec/clean_corpus/201.txt.gz", "spec/clean_corpus/203.txt.gz", "spec/clean_corpus/205.txt.gz", "spec/clean_corpus/207.txt.gz", "spec/clean_corpus/209.txt.gz", "spec/clean_corpus/211.txt.gz", "spec/clean_corpus/213.txt.gz", "spec/clean_corpus/215.txt.gz", "spec/clean_corpus/217.txt.gz", "spec/clean_corpus/219.txt.gz", "spec/clean_corpus/22.txt.gz", "spec/clean_corpus/221.txt.gz", "spec/clean_corpus/223.txt.gz", "spec/clean_corpus/225.txt.gz", "spec/clean_corpus/24.txt.gz", "spec/clean_corpus/26.txt.gz", "spec/clean_corpus/27.txt.gz", "spec/clean_corpus/29.txt.gz", "spec/clean_corpus/31.txt.gz", "spec/clean_corpus/33.txt.gz", "spec/clean_corpus/35.txt.gz", "spec/clean_corpus/37.txt.gz", "spec/clean_corpus/39.txt.gz", "spec/clean_corpus/41.txt.gz", "spec/clean_corpus/43.txt.gz", "spec/clean_corpus/45.txt.gz", "spec/clean_corpus/47.txt.gz", "spec/clean_corpus/49.txt.gz", "spec/clean_corpus/51.txt.gz", "spec/clean_corpus/53.txt.gz", "spec/clean_corpus/55.txt.gz", "spec/clean_corpus/57.txt.gz", "spec/clean_corpus/59.txt.gz", "spec/clean_corpus/61.txt.gz", "spec/clean_corpus/63.txt.gz", "spec/clean_corpus/65.txt.gz", "spec/clean_corpus/67.txt.gz", "spec/clean_corpus/69.txt.gz", "spec/clean_corpus/71.txt.gz", "spec/clean_corpus/73.txt.gz", "spec/clean_corpus/75.txt.gz", "spec/clean_corpus/77.txt.gz", "spec/clean_corpus/79.txt.gz", "spec/clean_corpus/81.txt.gz", "spec/clean_corpus/83.txt.gz", "spec/clean_corpus/85.txt.gz", "spec/clean_corpus/87.txt.gz", "spec/clean_corpus/89.txt.gz", "spec/clean_corpus/91.txt.gz", "spec/clean_corpus/93.txt.gz", "spec/clean_corpus/95.txt.gz", "spec/clean_corpus/97.txt.gz", "spec/clean_corpus/99.txt.gz", "spec/clean_corpus_spec.rb", "spec/despamilator_spec.rb", "spec/filters/funky_consonant_spec.rb", "spec/filters/html_tags_spec.rb", "spec/filters/ip_address_url_spec.rb", "spec/filters/long_words_spec.rb", "spec/filters/naughty_q_spec.rb", "spec/filters/naughty_words_spec.rb", "spec/filters/numbers_and_words_spec.rb", "spec/filters/script_tag_spec.rb", "spec/filters/shouting_spec.rb", "spec/filters/square_brackets_spec.rb", "spec/filters/urls_spec.rb", "spec/spam_corpus/0.txt.gz", "spec/spam_corpus/1.txt.gz", "spec/spam_corpus/10.txt.gz", "spec/spam_corpus/100.txt.gz", "spec/spam_corpus/102.txt.gz", "spec/spam_corpus/104.txt.gz", "spec/spam_corpus/106.txt.gz", "spec/spam_corpus/108.txt.gz", "spec/spam_corpus/11.txt.gz", "spec/spam_corpus/110.txt.gz", "spec/spam_corpus/112.txt.gz", "spec/spam_corpus/114.txt.gz", "spec/spam_corpus/116.txt.gz", "spec/spam_corpus/118.txt.gz", "spec/spam_corpus/12.txt.gz", "spec/spam_corpus/120.txt.gz", "spec/spam_corpus/122.txt.gz", "spec/spam_corpus/124.txt.gz", "spec/spam_corpus/126.txt.gz", "spec/spam_corpus/128.txt.gz", "spec/spam_corpus/13.txt.gz", "spec/spam_corpus/130.txt.gz", "spec/spam_corpus/132.txt.gz", "spec/spam_corpus/134.txt.gz", "spec/spam_corpus/136.txt.gz", "spec/spam_corpus/138.txt.gz", "spec/spam_corpus/14.txt.gz", "spec/spam_corpus/140.txt.gz", "spec/spam_corpus/142.txt.gz", "spec/spam_corpus/144.txt.gz", "spec/spam_corpus/146.txt.gz", "spec/spam_corpus/148.txt.gz", "spec/spam_corpus/15.txt.gz", "spec/spam_corpus/150.txt.gz", "spec/spam_corpus/152.txt.gz", "spec/spam_corpus/154.txt.gz", "spec/spam_corpus/156.txt.gz", "spec/spam_corpus/158.txt.gz", "spec/spam_corpus/16.txt.gz", "spec/spam_corpus/160.txt.gz", "spec/spam_corpus/162.txt.gz", "spec/spam_corpus/164.txt.gz", "spec/spam_corpus/166.txt.gz", "spec/spam_corpus/168.txt.gz", "spec/spam_corpus/170.txt.gz", "spec/spam_corpus/172.txt.gz", "spec/spam_corpus/174.txt.gz", "spec/spam_corpus/176.txt.gz", "spec/spam_corpus/178.txt.gz", "spec/spam_corpus/180.txt.gz", "spec/spam_corpus/182.txt.gz", "spec/spam_corpus/184.txt.gz", "spec/spam_corpus/186.txt.gz", "spec/spam_corpus/188.txt.gz", "spec/spam_corpus/190.txt.gz", "spec/spam_corpus/192.txt.gz", "spec/spam_corpus/194.txt.gz", "spec/spam_corpus/196.txt.gz", "spec/spam_corpus/198.txt.gz", "spec/spam_corpus/2.txt.gz", "spec/spam_corpus/200.txt.gz", "spec/spam_corpus/202.txt.gz", "spec/spam_corpus/204.txt.gz", "spec/spam_corpus/206.txt.gz", "spec/spam_corpus/208.txt.gz", "spec/spam_corpus/210.txt.gz", "spec/spam_corpus/212.txt.gz", "spec/spam_corpus/214.txt.gz", "spec/spam_corpus/216.txt.gz", "spec/spam_corpus/218.txt.gz", "spec/spam_corpus/220.txt.gz", "spec/spam_corpus/222.txt.gz", "spec/spam_corpus/224.txt.gz", "spec/spam_corpus/226.txt.gz", "spec/spam_corpus/228.txt.gz", "spec/spam_corpus/230.txt.gz", "spec/spam_corpus/232.txt.gz", "spec/spam_corpus/234.txt.gz", "spec/spam_corpus/236.txt.gz", "spec/spam_corpus/238.txt.gz", "spec/spam_corpus/240.txt.gz", "spec/spam_corpus/242.txt.gz", "spec/spam_corpus/244.txt.gz", "spec/spam_corpus/246.txt.gz", "spec/spam_corpus/248.txt.gz", "spec/spam_corpus/250.txt.gz", "spec/spam_corpus/252.txt.gz", "spec/spam_corpus/254.txt.gz", "spec/spam_corpus/256.txt.gz", "spec/spam_corpus/258.txt.gz", "spec/spam_corpus/260.txt.gz", "spec/spam_corpus/262.txt.gz", "spec/spam_corpus/264.txt.gz", "spec/spam_corpus/266.txt.gz", "spec/spam_corpus/268.txt.gz", "spec/spam_corpus/270.txt.gz", "spec/spam_corpus/272.txt.gz", "spec/spam_corpus/274.txt.gz", "spec/spam_corpus/276.txt.gz", "spec/spam_corpus/278.txt.gz", "spec/spam_corpus/28.txt.gz", "spec/spam_corpus/280.txt.gz", "spec/spam_corpus/282.txt.gz", "spec/spam_corpus/284.txt.gz", "spec/spam_corpus/286.txt.gz", "spec/spam_corpus/288.txt.gz", "spec/spam_corpus/290.txt.gz", "spec/spam_corpus/292.txt.gz", "spec/spam_corpus/294.txt.gz", "spec/spam_corpus/296.txt.gz", "spec/spam_corpus/298.txt.gz", "spec/spam_corpus/3.txt.gz", "spec/spam_corpus/30.txt.gz", "spec/spam_corpus/300.txt.gz", "spec/spam_corpus/302.txt.gz", "spec/spam_corpus/304.txt.gz", "spec/spam_corpus/306.txt.gz", "spec/spam_corpus/308.txt.gz", "spec/spam_corpus/310.txt.gz", "spec/spam_corpus/312.txt.gz", "spec/spam_corpus/314.txt.gz", "spec/spam_corpus/316.txt.gz", "spec/spam_corpus/318.txt.gz", "spec/spam_corpus/32.txt.gz", "spec/spam_corpus/320.txt.gz", "spec/spam_corpus/322.txt.gz", "spec/spam_corpus/324.txt.gz", "spec/spam_corpus/326.txt.gz", "spec/spam_corpus/328.txt.gz", "spec/spam_corpus/330.txt.gz", "spec/spam_corpus/332.txt.gz", "spec/spam_corpus/334.txt.gz", "spec/spam_corpus/336.txt.gz", "spec/spam_corpus/338.txt.gz", "spec/spam_corpus/34.txt.gz", "spec/spam_corpus/340.txt.gz", "spec/spam_corpus/342.txt.gz", "spec/spam_corpus/344.txt.gz", "spec/spam_corpus/346.txt.gz", "spec/spam_corpus/348.txt.gz", "spec/spam_corpus/350.txt.gz", "spec/spam_corpus/352.txt.gz", "spec/spam_corpus/354.txt.gz", "spec/spam_corpus/356.txt.gz", "spec/spam_corpus/358.txt.gz", "spec/spam_corpus/36.txt.gz", "spec/spam_corpus/360.txt.gz", "spec/spam_corpus/362.txt.gz", "spec/spam_corpus/364.txt.gz", "spec/spam_corpus/366.txt.gz", "spec/spam_corpus/368.txt.gz", "spec/spam_corpus/370.txt.gz", "spec/spam_corpus/372.txt.gz", "spec/spam_corpus/374.txt.gz", "spec/spam_corpus/376.txt.gz", "spec/spam_corpus/378.txt.gz", "spec/spam_corpus/38.txt.gz", "spec/spam_corpus/380.txt.gz", "spec/spam_corpus/382.txt.gz", "spec/spam_corpus/384.txt.gz", "spec/spam_corpus/386.txt.gz", "spec/spam_corpus/388.txt.gz", "spec/spam_corpus/390.txt.gz", "spec/spam_corpus/392.txt.gz", "spec/spam_corpus/394.txt.gz", "spec/spam_corpus/396.txt.gz", "spec/spam_corpus/398.txt.gz", "spec/spam_corpus/4.txt.gz", "spec/spam_corpus/40.txt.gz", "spec/spam_corpus/400.txt.gz", "spec/spam_corpus/402.txt.gz", "spec/spam_corpus/404.txt.gz", "spec/spam_corpus/406.txt.gz", "spec/spam_corpus/408.txt.gz", "spec/spam_corpus/410.txt.gz", "spec/spam_corpus/412.txt.gz", "spec/spam_corpus/414.txt.gz", "spec/spam_corpus/416.txt.gz", "spec/spam_corpus/418.txt.gz", "spec/spam_corpus/42.txt.gz", "spec/spam_corpus/420.txt.gz", "spec/spam_corpus/422.txt.gz", "spec/spam_corpus/424.txt.gz", "spec/spam_corpus/426.txt.gz", "spec/spam_corpus/428.txt.gz", "spec/spam_corpus/430.txt.gz", "spec/spam_corpus/432.txt.gz", "spec/spam_corpus/434.txt.gz", "spec/spam_corpus/436.txt.gz", "spec/spam_corpus/438.txt.gz", "spec/spam_corpus/44.txt.gz", "spec/spam_corpus/440.txt.gz", "spec/spam_corpus/442.txt.gz", "spec/spam_corpus/444.txt.gz", "spec/spam_corpus/446.txt.gz", "spec/spam_corpus/448.txt.gz", "spec/spam_corpus/450.txt.gz", "spec/spam_corpus/452.txt.gz", "spec/spam_corpus/454.txt.gz", "spec/spam_corpus/456.txt.gz", "spec/spam_corpus/458.txt.gz", "spec/spam_corpus/46.txt.gz", "spec/spam_corpus/460.txt.gz", "spec/spam_corpus/462.txt.gz", "spec/spam_corpus/464.txt.gz", "spec/spam_corpus/466.txt.gz", "spec/spam_corpus/468.txt.gz", "spec/spam_corpus/470.txt.gz", "spec/spam_corpus/472.txt.gz", "spec/spam_corpus/474.txt.gz", "spec/spam_corpus/476.txt.gz", "spec/spam_corpus/478.txt.gz", "spec/spam_corpus/48.txt.gz", "spec/spam_corpus/480.txt.gz", "spec/spam_corpus/482.txt.gz", "spec/spam_corpus/484.txt.gz", "spec/spam_corpus/486.txt.gz", "spec/spam_corpus/488.txt.gz", "spec/spam_corpus/490.txt.gz", "spec/spam_corpus/492.txt.gz", "spec/spam_corpus/494.txt.gz", "spec/spam_corpus/496.txt.gz", "spec/spam_corpus/498.txt.gz", "spec/spam_corpus/5.txt.gz", "spec/spam_corpus/50.txt.gz", "spec/spam_corpus/500.txt.gz", "spec/spam_corpus/502.txt.gz", "spec/spam_corpus/504.txt.gz", "spec/spam_corpus/506.txt.gz", "spec/spam_corpus/508.txt.gz", "spec/spam_corpus/510.txt.gz", "spec/spam_corpus/512.txt.gz", "spec/spam_corpus/514.txt.gz", "spec/spam_corpus/516.txt.gz", "spec/spam_corpus/518.txt.gz", "spec/spam_corpus/52.txt.gz", "spec/spam_corpus/520.txt.gz", "spec/spam_corpus/522.txt.gz", "spec/spam_corpus/524.txt.gz", "spec/spam_corpus/526.txt.gz", "spec/spam_corpus/528.txt.gz", "spec/spam_corpus/530.txt.gz", "spec/spam_corpus/532.txt.gz", "spec/spam_corpus/534.txt.gz", "spec/spam_corpus/536.txt.gz", "spec/spam_corpus/538.txt.gz", "spec/spam_corpus/54.txt.gz", "spec/spam_corpus/540.txt.gz", "spec/spam_corpus/542.txt.gz", "spec/spam_corpus/544.txt.gz", "spec/spam_corpus/546.txt.gz", "spec/spam_corpus/548.txt.gz", "spec/spam_corpus/550.txt.gz", "spec/spam_corpus/552.txt.gz", "spec/spam_corpus/554.txt.gz", "spec/spam_corpus/556.txt.gz", "spec/spam_corpus/558.txt.gz", "spec/spam_corpus/56.txt.gz", "spec/spam_corpus/560.txt.gz", "spec/spam_corpus/562.txt.gz", "spec/spam_corpus/564.txt.gz", "spec/spam_corpus/566.txt.gz", "spec/spam_corpus/568.txt.gz", "spec/spam_corpus/570.txt.gz", "spec/spam_corpus/572.txt.gz", "spec/spam_corpus/574.txt.gz", "spec/spam_corpus/576.txt.gz", "spec/spam_corpus/578.txt.gz", "spec/spam_corpus/58.txt.gz", "spec/spam_corpus/580.txt.gz", "spec/spam_corpus/582.txt.gz", "spec/spam_corpus/584.txt.gz", "spec/spam_corpus/586.txt.gz", "spec/spam_corpus/588.txt.gz", "spec/spam_corpus/590.txt.gz", "spec/spam_corpus/592.txt.gz", "spec/spam_corpus/594.txt.gz", "spec/spam_corpus/596.txt.gz", "spec/spam_corpus/598.txt.gz", "spec/spam_corpus/6.txt.gz", "spec/spam_corpus/60.txt.gz", "spec/spam_corpus/600.txt.gz", "spec/spam_corpus/602.txt.gz", "spec/spam_corpus/604.txt.gz", "spec/spam_corpus/606.txt.gz", "spec/spam_corpus/608.txt.gz", "spec/spam_corpus/610.txt.gz", "spec/spam_corpus/612.txt.gz", "spec/spam_corpus/614.txt.gz", "spec/spam_corpus/616.txt.gz", "spec/spam_corpus/618.txt.gz", "spec/spam_corpus/62.txt.gz", "spec/spam_corpus/620.txt.gz", "spec/spam_corpus/622.txt.gz", "spec/spam_corpus/624.txt.gz", "spec/spam_corpus/626.txt.gz", "spec/spam_corpus/628.txt.gz", "spec/spam_corpus/630.txt.gz", "spec/spam_corpus/632.txt.gz", "spec/spam_corpus/634.txt.gz", "spec/spam_corpus/636.txt.gz", "spec/spam_corpus/638.txt.gz", "spec/spam_corpus/64.txt.gz", "spec/spam_corpus/640.txt.gz", "spec/spam_corpus/642.txt.gz", "spec/spam_corpus/644.txt.gz", "spec/spam_corpus/646.txt.gz", "spec/spam_corpus/648.txt.gz", "spec/spam_corpus/650.txt.gz", "spec/spam_corpus/652.txt.gz", "spec/spam_corpus/654.txt.gz", "spec/spam_corpus/656.txt.gz", "spec/spam_corpus/658.txt.gz", "spec/spam_corpus/66.txt.gz", "spec/spam_corpus/660.txt.gz", "spec/spam_corpus/662.txt.gz", "spec/spam_corpus/664.txt.gz", "spec/spam_corpus/666.txt.gz", "spec/spam_corpus/668.txt.gz", "spec/spam_corpus/670.txt.gz", "spec/spam_corpus/672.txt.gz", "spec/spam_corpus/674.txt.gz", "spec/spam_corpus/676.txt.gz", "spec/spam_corpus/678.txt.gz", "spec/spam_corpus/68.txt.gz", "spec/spam_corpus/680.txt.gz", "spec/spam_corpus/682.txt.gz", "spec/spam_corpus/684.txt.gz", "spec/spam_corpus/686.txt.gz", "spec/spam_corpus/688.txt.gz", "spec/spam_corpus/690.txt.gz", "spec/spam_corpus/692.txt.gz", "spec/spam_corpus/694.txt.gz", "spec/spam_corpus/696.txt.gz", "spec/spam_corpus/698.txt.gz", "spec/spam_corpus/7.txt.gz", "spec/spam_corpus/70.txt.gz", "spec/spam_corpus/700.txt.gz", "spec/spam_corpus/702.txt.gz", "spec/spam_corpus/704.txt.gz", "spec/spam_corpus/706.txt.gz", "spec/spam_corpus/708.txt.gz", "spec/spam_corpus/710.txt.gz", "spec/spam_corpus/712.txt.gz", "spec/spam_corpus/714.txt.gz", "spec/spam_corpus/716.txt.gz", "spec/spam_corpus/718.txt.gz", "spec/spam_corpus/72.txt.gz", "spec/spam_corpus/720.txt.gz", "spec/spam_corpus/722.txt.gz", "spec/spam_corpus/724.txt.gz", "spec/spam_corpus/726.txt.gz", "spec/spam_corpus/728.txt.gz", "spec/spam_corpus/730.txt.gz", "spec/spam_corpus/732.txt.gz", "spec/spam_corpus/734.txt.gz", "spec/spam_corpus/736.txt.gz", "spec/spam_corpus/738.txt.gz", "spec/spam_corpus/74.txt.gz", "spec/spam_corpus/740.txt.gz", "spec/spam_corpus/742.txt.gz", "spec/spam_corpus/744.txt.gz", "spec/spam_corpus/746.txt.gz", "spec/spam_corpus/748.txt.gz", "spec/spam_corpus/750.txt.gz", "spec/spam_corpus/752.txt.gz", "spec/spam_corpus/754.txt.gz", "spec/spam_corpus/756.txt.gz", "spec/spam_corpus/758.txt.gz", "spec/spam_corpus/76.txt.gz", "spec/spam_corpus/760.txt.gz", "spec/spam_corpus/762.txt.gz", "spec/spam_corpus/764.txt.gz", "spec/spam_corpus/766.txt.gz", "spec/spam_corpus/768.txt.gz", "spec/spam_corpus/770.txt.gz", "spec/spam_corpus/772.txt.gz", "spec/spam_corpus/774.txt.gz", "spec/spam_corpus/776.txt.gz", "spec/spam_corpus/778.txt.gz", "spec/spam_corpus/78.txt.gz", "spec/spam_corpus/780.txt.gz", "spec/spam_corpus/782.txt.gz", "spec/spam_corpus/784.txt.gz", "spec/spam_corpus/786.txt.gz", "spec/spam_corpus/788.txt.gz", "spec/spam_corpus/790.txt.gz", "spec/spam_corpus/792.txt.gz", "spec/spam_corpus/794.txt.gz", "spec/spam_corpus/796.txt.gz", "spec/spam_corpus/798.txt.gz", "spec/spam_corpus/8.txt.gz", "spec/spam_corpus/80.txt.gz", "spec/spam_corpus/800.txt.gz", "spec/spam_corpus/802.txt.gz", "spec/spam_corpus/804.txt.gz", "spec/spam_corpus/806.txt.gz", "spec/spam_corpus/808.txt.gz", "spec/spam_corpus/810.txt.gz", "spec/spam_corpus/812.txt.gz", "spec/spam_corpus/814.txt.gz", "spec/spam_corpus/816.txt.gz", "spec/spam_corpus/818.txt.gz", "spec/spam_corpus/82.txt.gz", "spec/spam_corpus/820.txt.gz", "spec/spam_corpus/822.txt.gz", "spec/spam_corpus/824.txt.gz", "spec/spam_corpus/826.txt.gz", "spec/spam_corpus/828.txt.gz", "spec/spam_corpus/830.txt.gz", "spec/spam_corpus/832.txt.gz", "spec/spam_corpus/834.txt.gz", "spec/spam_corpus/836.txt.gz", "spec/spam_corpus/838.txt.gz", "spec/spam_corpus/84.txt.gz", "spec/spam_corpus/840.txt.gz", "spec/spam_corpus/842.txt.gz", "spec/spam_corpus/844.txt.gz", "spec/spam_corpus/846.txt.gz", "spec/spam_corpus/848.txt.gz", "spec/spam_corpus/850.txt.gz", "spec/spam_corpus/852.txt.gz", "spec/spam_corpus/854.txt.gz", "spec/spam_corpus/856.txt.gz", "spec/spam_corpus/858.txt.gz", "spec/spam_corpus/86.txt.gz", "spec/spam_corpus/860.txt.gz", "spec/spam_corpus/862.txt.gz", "spec/spam_corpus/864.txt.gz", "spec/spam_corpus/866.txt.gz", "spec/spam_corpus/868.txt.gz", "spec/spam_corpus/870.txt.gz", "spec/spam_corpus/872.txt.gz", "spec/spam_corpus/874.txt.gz", "spec/spam_corpus/876.txt.gz", "spec/spam_corpus/878.txt.gz", "spec/spam_corpus/88.txt.gz", "spec/spam_corpus/880.txt.gz", "spec/spam_corpus/882.txt.gz", "spec/spam_corpus/884.txt.gz", "spec/spam_corpus/886.txt.gz", "spec/spam_corpus/888.txt.gz", "spec/spam_corpus/890.txt.gz", "spec/spam_corpus/892.txt.gz", "spec/spam_corpus/894.txt.gz", "spec/spam_corpus/896.txt.gz", "spec/spam_corpus/898.txt.gz", "spec/spam_corpus/9.txt.gz", "spec/spam_corpus/90.txt.gz", "spec/spam_corpus/900.txt.gz", "spec/spam_corpus/902.txt.gz", "spec/spam_corpus/904.txt.gz", "spec/spam_corpus/906.txt.gz", "spec/spam_corpus/908.txt.gz", "spec/spam_corpus/910.txt.gz", "spec/spam_corpus/912.txt.gz", "spec/spam_corpus/914.txt.gz", "spec/spam_corpus/916.txt.gz", "spec/spam_corpus/918.txt.gz", "spec/spam_corpus/92.txt.gz", "spec/spam_corpus/920.txt.gz", "spec/spam_corpus/922.txt.gz", "spec/spam_corpus/924.txt.gz", "spec/spam_corpus/926.txt.gz", "spec/spam_corpus/928.txt.gz", "spec/spam_corpus/930.txt.gz", "spec/spam_corpus/932.txt.gz", "spec/spam_corpus/934.txt.gz", "spec/spam_corpus/936.txt.gz", "spec/spam_corpus/938.txt.gz", "spec/spam_corpus/94.txt.gz", "spec/spam_corpus/940.txt.gz", "spec/spam_corpus/942.txt.gz", "spec/spam_corpus/944.txt.gz", "spec/spam_corpus/946.txt.gz", "spec/spam_corpus/948.txt.gz", "spec/spam_corpus/950.txt.gz", "spec/spam_corpus/952.txt.gz", "spec/spam_corpus/954.txt.gz", "spec/spam_corpus/956.txt.gz", "spec/spam_corpus/958.txt.gz", "spec/spam_corpus/96.txt.gz", "spec/spam_corpus/960.txt.gz", "spec/spam_corpus/962.txt.gz", "spec/spam_corpus/964.txt.gz", "spec/spam_corpus/966.txt.gz", "spec/spam_corpus/968.txt.gz", "spec/spam_corpus/970.txt.gz", "spec/spam_corpus/972.txt.gz", "spec/spam_corpus/974.txt.gz", "spec/spam_corpus/98.txt.gz", "spec/spam_corpus/debugyouradd.com.txt.gz", "spec/spam_corpus/humandesignconsulting.comm.txt.gz", "spec/spam_corpus_spec.rb", "spec/spec.opts", "spec/spec_helper.rb", "tasks/rspec.rake"]
15
+ s.files = ["History.txt", "Manifest.txt", "PostInstall.txt", "README.rdoc", "Rakefile", "despamilator.gemspec", "despamliator.gemspec", "lib/despamilator.rb", "lib/despamilator/filter.rb", "lib/despamilator/filter/funky_consonant.rb", "lib/despamilator/filter/html_tags.rb", "lib/despamilator/filter/ip_address_url.rb", "lib/despamilator/filter/long_words.rb", "lib/despamilator/filter/naughty_q.rb", "lib/despamilator/filter/naughty_words.rb", "lib/despamilator/filter/numbers_and_words.rb", "lib/despamilator/filter/script_tag.rb", "lib/despamilator/filter/shouting.rb", "lib/despamilator/filter/square_brackets.rb", "lib/despamilator/filter/urls.rb", "lib/despamilator/filter_base.rb", "lib/despamilator/validation.rb", "scripts/despamilator_score.rb", "spec/clean_corpus/101.txt.gz", "spec/clean_corpus/103.txt.gz", "spec/clean_corpus/105.txt.gz", "spec/clean_corpus/107.txt.gz", "spec/clean_corpus/109.txt.gz", "spec/clean_corpus/111.txt.gz", "spec/clean_corpus/113.txt.gz", "spec/clean_corpus/115.txt.gz", "spec/clean_corpus/117.txt.gz", "spec/clean_corpus/119.txt.gz", "spec/clean_corpus/121.txt.gz", "spec/clean_corpus/123.txt.gz", "spec/clean_corpus/125.txt.gz", "spec/clean_corpus/127.txt.gz", "spec/clean_corpus/129.txt.gz", "spec/clean_corpus/131.txt.gz", "spec/clean_corpus/133.txt.gz", "spec/clean_corpus/135.txt.gz", "spec/clean_corpus/137.txt.gz", "spec/clean_corpus/139.txt.gz", "spec/clean_corpus/141.txt.gz", "spec/clean_corpus/143.txt.gz", "spec/clean_corpus/145.txt.gz", "spec/clean_corpus/147.txt.gz", "spec/clean_corpus/149.txt.gz", "spec/clean_corpus/151.txt.gz", "spec/clean_corpus/153.txt.gz", "spec/clean_corpus/155.txt.gz", "spec/clean_corpus/157.txt.gz", "spec/clean_corpus/159.txt.gz", "spec/clean_corpus/161.txt.gz", "spec/clean_corpus/163.txt.gz", "spec/clean_corpus/165.txt.gz", "spec/clean_corpus/167.txt.gz", "spec/clean_corpus/169.txt.gz", "spec/clean_corpus/171.txt.gz", "spec/clean_corpus/173.txt.gz", "spec/clean_corpus/175.txt.gz", "spec/clean_corpus/177.txt.gz", "spec/clean_corpus/179.txt.gz", "spec/clean_corpus/18.txt.gz", "spec/clean_corpus/181.txt.gz", "spec/clean_corpus/183.txt.gz", "spec/clean_corpus/185.txt.gz", "spec/clean_corpus/187.txt.gz", "spec/clean_corpus/189.txt.gz", "spec/clean_corpus/191.txt.gz", "spec/clean_corpus/193.txt.gz", "spec/clean_corpus/195.txt.gz", "spec/clean_corpus/197.txt.gz", "spec/clean_corpus/199.txt.gz", "spec/clean_corpus/20.txt.gz", "spec/clean_corpus/201.txt.gz", "spec/clean_corpus/203.txt.gz", "spec/clean_corpus/205.txt.gz", "spec/clean_corpus/207.txt.gz", "spec/clean_corpus/209.txt.gz", "spec/clean_corpus/211.txt.gz", "spec/clean_corpus/213.txt.gz", "spec/clean_corpus/215.txt.gz", "spec/clean_corpus/217.txt.gz", "spec/clean_corpus/219.txt.gz", "spec/clean_corpus/22.txt.gz", "spec/clean_corpus/221.txt.gz", "spec/clean_corpus/223.txt.gz", "spec/clean_corpus/225.txt.gz", "spec/clean_corpus/24.txt.gz", "spec/clean_corpus/26.txt.gz", "spec/clean_corpus/27.txt.gz", "spec/clean_corpus/29.txt.gz", "spec/clean_corpus/31.txt.gz", "spec/clean_corpus/33.txt.gz", "spec/clean_corpus/35.txt.gz", "spec/clean_corpus/37.txt.gz", "spec/clean_corpus/39.txt.gz", "spec/clean_corpus/41.txt.gz", "spec/clean_corpus/43.txt.gz", "spec/clean_corpus/45.txt.gz", "spec/clean_corpus/47.txt.gz", "spec/clean_corpus/49.txt.gz", "spec/clean_corpus/51.txt.gz", "spec/clean_corpus/53.txt.gz", "spec/clean_corpus/55.txt.gz", "spec/clean_corpus/57.txt.gz", "spec/clean_corpus/59.txt.gz", "spec/clean_corpus/61.txt.gz", "spec/clean_corpus/63.txt.gz", "spec/clean_corpus/65.txt.gz", "spec/clean_corpus/67.txt.gz", "spec/clean_corpus/69.txt.gz", "spec/clean_corpus/71.txt.gz", "spec/clean_corpus/73.txt.gz", "spec/clean_corpus/75.txt.gz", "spec/clean_corpus/77.txt.gz", "spec/clean_corpus/79.txt.gz", "spec/clean_corpus/81.txt.gz", "spec/clean_corpus/83.txt.gz", "spec/clean_corpus/85.txt.gz", "spec/clean_corpus/87.txt.gz", "spec/clean_corpus/89.txt.gz", "spec/clean_corpus/91.txt.gz", "spec/clean_corpus/93.txt.gz", "spec/clean_corpus/95.txt.gz", "spec/clean_corpus/97.txt.gz", "spec/clean_corpus/99.txt.gz", "spec/clean_corpus_spec.rb", "spec/despamilator_spec.rb", "spec/despamilator_validation_spec.rb", "spec/filters/funky_consonant_spec.rb", "spec/filters/html_tags_spec.rb", "spec/filters/ip_address_url_spec.rb", "spec/filters/long_words_spec.rb", "spec/filters/naughty_q_spec.rb", "spec/filters/naughty_words_spec.rb", "spec/filters/numbers_and_words_spec.rb", "spec/filters/script_tag_spec.rb", "spec/filters/shouting_spec.rb", "spec/filters/square_brackets_spec.rb", "spec/filters/urls_spec.rb", "spec/spam_corpus/0.txt.gz", "spec/spam_corpus/1.txt.gz", "spec/spam_corpus/10.txt.gz", "spec/spam_corpus/100.txt.gz", "spec/spam_corpus/102.txt.gz", "spec/spam_corpus/104.txt.gz", "spec/spam_corpus/106.txt.gz", "spec/spam_corpus/108.txt.gz", "spec/spam_corpus/11.txt.gz", "spec/spam_corpus/110.txt.gz", "spec/spam_corpus/112.txt.gz", "spec/spam_corpus/114.txt.gz", "spec/spam_corpus/116.txt.gz", "spec/spam_corpus/118.txt.gz", "spec/spam_corpus/12.txt.gz", "spec/spam_corpus/120.txt.gz", "spec/spam_corpus/122.txt.gz", "spec/spam_corpus/124.txt.gz", "spec/spam_corpus/126.txt.gz", "spec/spam_corpus/128.txt.gz", "spec/spam_corpus/13.txt.gz", "spec/spam_corpus/130.txt.gz", "spec/spam_corpus/132.txt.gz", "spec/spam_corpus/134.txt.gz", "spec/spam_corpus/136.txt.gz", "spec/spam_corpus/138.txt.gz", "spec/spam_corpus/14.txt.gz", "spec/spam_corpus/140.txt.gz", "spec/spam_corpus/142.txt.gz", "spec/spam_corpus/144.txt.gz", "spec/spam_corpus/146.txt.gz", "spec/spam_corpus/148.txt.gz", "spec/spam_corpus/15.txt.gz", "spec/spam_corpus/150.txt.gz", "spec/spam_corpus/152.txt.gz", "spec/spam_corpus/154.txt.gz", "spec/spam_corpus/156.txt.gz", "spec/spam_corpus/158.txt.gz", "spec/spam_corpus/16.txt.gz", "spec/spam_corpus/160.txt.gz", "spec/spam_corpus/162.txt.gz", "spec/spam_corpus/164.txt.gz", "spec/spam_corpus/166.txt.gz", "spec/spam_corpus/168.txt.gz", "spec/spam_corpus/170.txt.gz", "spec/spam_corpus/172.txt.gz", "spec/spam_corpus/174.txt.gz", "spec/spam_corpus/176.txt.gz", "spec/spam_corpus/178.txt.gz", "spec/spam_corpus/180.txt.gz", "spec/spam_corpus/182.txt.gz", "spec/spam_corpus/184.txt.gz", "spec/spam_corpus/186.txt.gz", "spec/spam_corpus/188.txt.gz", "spec/spam_corpus/190.txt.gz", "spec/spam_corpus/192.txt.gz", "spec/spam_corpus/194.txt.gz", "spec/spam_corpus/196.txt.gz", "spec/spam_corpus/198.txt.gz", "spec/spam_corpus/2.txt.gz", "spec/spam_corpus/200.txt.gz", "spec/spam_corpus/202.txt.gz", "spec/spam_corpus/204.txt.gz", "spec/spam_corpus/206.txt.gz", "spec/spam_corpus/208.txt.gz", "spec/spam_corpus/210.txt.gz", "spec/spam_corpus/212.txt.gz", "spec/spam_corpus/214.txt.gz", "spec/spam_corpus/216.txt.gz", "spec/spam_corpus/218.txt.gz", "spec/spam_corpus/220.txt.gz", "spec/spam_corpus/222.txt.gz", "spec/spam_corpus/224.txt.gz", "spec/spam_corpus/226.txt.gz", "spec/spam_corpus/228.txt.gz", "spec/spam_corpus/230.txt.gz", "spec/spam_corpus/232.txt.gz", "spec/spam_corpus/234.txt.gz", "spec/spam_corpus/236.txt.gz", "spec/spam_corpus/238.txt.gz", "spec/spam_corpus/240.txt.gz", "spec/spam_corpus/242.txt.gz", "spec/spam_corpus/244.txt.gz", "spec/spam_corpus/246.txt.gz", "spec/spam_corpus/248.txt.gz", "spec/spam_corpus/250.txt.gz", "spec/spam_corpus/252.txt.gz", "spec/spam_corpus/254.txt.gz", "spec/spam_corpus/256.txt.gz", "spec/spam_corpus/258.txt.gz", "spec/spam_corpus/260.txt.gz", "spec/spam_corpus/262.txt.gz", "spec/spam_corpus/264.txt.gz", "spec/spam_corpus/266.txt.gz", "spec/spam_corpus/268.txt.gz", "spec/spam_corpus/270.txt.gz", "spec/spam_corpus/272.txt.gz", "spec/spam_corpus/274.txt.gz", "spec/spam_corpus/276.txt.gz", "spec/spam_corpus/278.txt.gz", "spec/spam_corpus/28.txt.gz", "spec/spam_corpus/280.txt.gz", "spec/spam_corpus/282.txt.gz", "spec/spam_corpus/284.txt.gz", "spec/spam_corpus/286.txt.gz", "spec/spam_corpus/288.txt.gz", "spec/spam_corpus/290.txt.gz", "spec/spam_corpus/292.txt.gz", "spec/spam_corpus/294.txt.gz", "spec/spam_corpus/296.txt.gz", "spec/spam_corpus/298.txt.gz", "spec/spam_corpus/3.txt.gz", "spec/spam_corpus/30.txt.gz", "spec/spam_corpus/300.txt.gz", "spec/spam_corpus/302.txt.gz", "spec/spam_corpus/304.txt.gz", "spec/spam_corpus/306.txt.gz", "spec/spam_corpus/308.txt.gz", "spec/spam_corpus/310.txt.gz", "spec/spam_corpus/312.txt.gz", "spec/spam_corpus/314.txt.gz", "spec/spam_corpus/316.txt.gz", "spec/spam_corpus/318.txt.gz", "spec/spam_corpus/32.txt.gz", "spec/spam_corpus/320.txt.gz", "spec/spam_corpus/322.txt.gz", "spec/spam_corpus/324.txt.gz", "spec/spam_corpus/326.txt.gz", "spec/spam_corpus/328.txt.gz", "spec/spam_corpus/330.txt.gz", "spec/spam_corpus/332.txt.gz", "spec/spam_corpus/334.txt.gz", "spec/spam_corpus/336.txt.gz", "spec/spam_corpus/338.txt.gz", "spec/spam_corpus/34.txt.gz", "spec/spam_corpus/340.txt.gz", "spec/spam_corpus/342.txt.gz", "spec/spam_corpus/344.txt.gz", "spec/spam_corpus/346.txt.gz", "spec/spam_corpus/348.txt.gz", "spec/spam_corpus/350.txt.gz", "spec/spam_corpus/352.txt.gz", "spec/spam_corpus/354.txt.gz", "spec/spam_corpus/356.txt.gz", "spec/spam_corpus/358.txt.gz", "spec/spam_corpus/36.txt.gz", "spec/spam_corpus/360.txt.gz", "spec/spam_corpus/362.txt.gz", "spec/spam_corpus/364.txt.gz", "spec/spam_corpus/366.txt.gz", "spec/spam_corpus/368.txt.gz", "spec/spam_corpus/370.txt.gz", "spec/spam_corpus/372.txt.gz", "spec/spam_corpus/374.txt.gz", "spec/spam_corpus/376.txt.gz", "spec/spam_corpus/378.txt.gz", "spec/spam_corpus/38.txt.gz", "spec/spam_corpus/380.txt.gz", "spec/spam_corpus/382.txt.gz", "spec/spam_corpus/384.txt.gz", "spec/spam_corpus/386.txt.gz", "spec/spam_corpus/388.txt.gz", "spec/spam_corpus/390.txt.gz", "spec/spam_corpus/392.txt.gz", "spec/spam_corpus/394.txt.gz", "spec/spam_corpus/396.txt.gz", "spec/spam_corpus/398.txt.gz", "spec/spam_corpus/4.txt.gz", "spec/spam_corpus/40.txt.gz", "spec/spam_corpus/400.txt.gz", "spec/spam_corpus/402.txt.gz", "spec/spam_corpus/404.txt.gz", "spec/spam_corpus/406.txt.gz", "spec/spam_corpus/408.txt.gz", "spec/spam_corpus/410.txt.gz", "spec/spam_corpus/412.txt.gz", "spec/spam_corpus/414.txt.gz", "spec/spam_corpus/416.txt.gz", "spec/spam_corpus/418.txt.gz", "spec/spam_corpus/42.txt.gz", "spec/spam_corpus/420.txt.gz", "spec/spam_corpus/422.txt.gz", "spec/spam_corpus/424.txt.gz", "spec/spam_corpus/426.txt.gz", "spec/spam_corpus/428.txt.gz", "spec/spam_corpus/430.txt.gz", "spec/spam_corpus/432.txt.gz", "spec/spam_corpus/434.txt.gz", "spec/spam_corpus/436.txt.gz", "spec/spam_corpus/438.txt.gz", "spec/spam_corpus/44.txt.gz", "spec/spam_corpus/440.txt.gz", "spec/spam_corpus/442.txt.gz", "spec/spam_corpus/444.txt.gz", "spec/spam_corpus/446.txt.gz", "spec/spam_corpus/448.txt.gz", "spec/spam_corpus/450.txt.gz", "spec/spam_corpus/452.txt.gz", "spec/spam_corpus/454.txt.gz", "spec/spam_corpus/456.txt.gz", "spec/spam_corpus/458.txt.gz", "spec/spam_corpus/46.txt.gz", "spec/spam_corpus/460.txt.gz", "spec/spam_corpus/462.txt.gz", "spec/spam_corpus/464.txt.gz", "spec/spam_corpus/466.txt.gz", "spec/spam_corpus/468.txt.gz", "spec/spam_corpus/470.txt.gz", "spec/spam_corpus/472.txt.gz", "spec/spam_corpus/474.txt.gz", "spec/spam_corpus/476.txt.gz", "spec/spam_corpus/478.txt.gz", "spec/spam_corpus/48.txt.gz", "spec/spam_corpus/480.txt.gz", "spec/spam_corpus/482.txt.gz", "spec/spam_corpus/484.txt.gz", "spec/spam_corpus/486.txt.gz", "spec/spam_corpus/488.txt.gz", "spec/spam_corpus/490.txt.gz", "spec/spam_corpus/492.txt.gz", "spec/spam_corpus/494.txt.gz", "spec/spam_corpus/496.txt.gz", "spec/spam_corpus/498.txt.gz", "spec/spam_corpus/5.txt.gz", "spec/spam_corpus/50.txt.gz", "spec/spam_corpus/500.txt.gz", "spec/spam_corpus/502.txt.gz", "spec/spam_corpus/504.txt.gz", "spec/spam_corpus/506.txt.gz", "spec/spam_corpus/508.txt.gz", "spec/spam_corpus/510.txt.gz", "spec/spam_corpus/512.txt.gz", "spec/spam_corpus/514.txt.gz", "spec/spam_corpus/516.txt.gz", "spec/spam_corpus/518.txt.gz", "spec/spam_corpus/52.txt.gz", "spec/spam_corpus/520.txt.gz", "spec/spam_corpus/522.txt.gz", "spec/spam_corpus/524.txt.gz", "spec/spam_corpus/526.txt.gz", "spec/spam_corpus/528.txt.gz", "spec/spam_corpus/530.txt.gz", "spec/spam_corpus/532.txt.gz", "spec/spam_corpus/534.txt.gz", "spec/spam_corpus/536.txt.gz", "spec/spam_corpus/538.txt.gz", "spec/spam_corpus/54.txt.gz", "spec/spam_corpus/540.txt.gz", "spec/spam_corpus/542.txt.gz", "spec/spam_corpus/544.txt.gz", "spec/spam_corpus/546.txt.gz", "spec/spam_corpus/548.txt.gz", "spec/spam_corpus/550.txt.gz", "spec/spam_corpus/552.txt.gz", "spec/spam_corpus/554.txt.gz", "spec/spam_corpus/556.txt.gz", "spec/spam_corpus/558.txt.gz", "spec/spam_corpus/56.txt.gz", "spec/spam_corpus/560.txt.gz", "spec/spam_corpus/562.txt.gz", "spec/spam_corpus/564.txt.gz", "spec/spam_corpus/566.txt.gz", "spec/spam_corpus/568.txt.gz", "spec/spam_corpus/570.txt.gz", "spec/spam_corpus/572.txt.gz", "spec/spam_corpus/574.txt.gz", "spec/spam_corpus/576.txt.gz", "spec/spam_corpus/578.txt.gz", "spec/spam_corpus/58.txt.gz", "spec/spam_corpus/580.txt.gz", "spec/spam_corpus/582.txt.gz", "spec/spam_corpus/584.txt.gz", "spec/spam_corpus/586.txt.gz", "spec/spam_corpus/588.txt.gz", "spec/spam_corpus/590.txt.gz", "spec/spam_corpus/592.txt.gz", "spec/spam_corpus/594.txt.gz", "spec/spam_corpus/596.txt.gz", "spec/spam_corpus/598.txt.gz", "spec/spam_corpus/6.txt.gz", "spec/spam_corpus/60.txt.gz", "spec/spam_corpus/600.txt.gz", "spec/spam_corpus/602.txt.gz", "spec/spam_corpus/604.txt.gz", "spec/spam_corpus/606.txt.gz", "spec/spam_corpus/608.txt.gz", "spec/spam_corpus/610.txt.gz", "spec/spam_corpus/612.txt.gz", "spec/spam_corpus/614.txt.gz", "spec/spam_corpus/616.txt.gz", "spec/spam_corpus/618.txt.gz", "spec/spam_corpus/62.txt.gz", "spec/spam_corpus/620.txt.gz", "spec/spam_corpus/622.txt.gz", "spec/spam_corpus/624.txt.gz", "spec/spam_corpus/626.txt.gz", "spec/spam_corpus/628.txt.gz", "spec/spam_corpus/630.txt.gz", "spec/spam_corpus/632.txt.gz", "spec/spam_corpus/634.txt.gz", "spec/spam_corpus/636.txt.gz", "spec/spam_corpus/638.txt.gz", "spec/spam_corpus/64.txt.gz", "spec/spam_corpus/640.txt.gz", "spec/spam_corpus/642.txt.gz", "spec/spam_corpus/644.txt.gz", "spec/spam_corpus/646.txt.gz", "spec/spam_corpus/648.txt.gz", "spec/spam_corpus/650.txt.gz", "spec/spam_corpus/652.txt.gz", "spec/spam_corpus/654.txt.gz", "spec/spam_corpus/656.txt.gz", "spec/spam_corpus/658.txt.gz", "spec/spam_corpus/66.txt.gz", "spec/spam_corpus/660.txt.gz", "spec/spam_corpus/662.txt.gz", "spec/spam_corpus/664.txt.gz", "spec/spam_corpus/666.txt.gz", "spec/spam_corpus/668.txt.gz", "spec/spam_corpus/670.txt.gz", "spec/spam_corpus/672.txt.gz", "spec/spam_corpus/674.txt.gz", "spec/spam_corpus/676.txt.gz", "spec/spam_corpus/678.txt.gz", "spec/spam_corpus/68.txt.gz", "spec/spam_corpus/680.txt.gz", "spec/spam_corpus/682.txt.gz", "spec/spam_corpus/684.txt.gz", "spec/spam_corpus/686.txt.gz", "spec/spam_corpus/688.txt.gz", "spec/spam_corpus/690.txt.gz", "spec/spam_corpus/692.txt.gz", "spec/spam_corpus/694.txt.gz", "spec/spam_corpus/696.txt.gz", "spec/spam_corpus/698.txt.gz", "spec/spam_corpus/7.txt.gz", "spec/spam_corpus/70.txt.gz", "spec/spam_corpus/700.txt.gz", "spec/spam_corpus/702.txt.gz", "spec/spam_corpus/704.txt.gz", "spec/spam_corpus/706.txt.gz", "spec/spam_corpus/708.txt.gz", "spec/spam_corpus/710.txt.gz", "spec/spam_corpus/712.txt.gz", "spec/spam_corpus/714.txt.gz", "spec/spam_corpus/716.txt.gz", "spec/spam_corpus/718.txt.gz", "spec/spam_corpus/72.txt.gz", "spec/spam_corpus/720.txt.gz", "spec/spam_corpus/722.txt.gz", "spec/spam_corpus/724.txt.gz", "spec/spam_corpus/726.txt.gz", "spec/spam_corpus/728.txt.gz", "spec/spam_corpus/730.txt.gz", "spec/spam_corpus/732.txt.gz", "spec/spam_corpus/734.txt.gz", "spec/spam_corpus/736.txt.gz", "spec/spam_corpus/738.txt.gz", "spec/spam_corpus/74.txt.gz", "spec/spam_corpus/740.txt.gz", "spec/spam_corpus/742.txt.gz", "spec/spam_corpus/744.txt.gz", "spec/spam_corpus/746.txt.gz", "spec/spam_corpus/748.txt.gz", "spec/spam_corpus/750.txt.gz", "spec/spam_corpus/752.txt.gz", "spec/spam_corpus/754.txt.gz", "spec/spam_corpus/756.txt.gz", "spec/spam_corpus/758.txt.gz", "spec/spam_corpus/76.txt.gz", "spec/spam_corpus/760.txt.gz", "spec/spam_corpus/762.txt.gz", "spec/spam_corpus/764.txt.gz", "spec/spam_corpus/766.txt.gz", "spec/spam_corpus/768.txt.gz", "spec/spam_corpus/770.txt.gz", "spec/spam_corpus/772.txt.gz", "spec/spam_corpus/774.txt.gz", "spec/spam_corpus/776.txt.gz", "spec/spam_corpus/778.txt.gz", "spec/spam_corpus/78.txt.gz", "spec/spam_corpus/780.txt.gz", "spec/spam_corpus/782.txt.gz", "spec/spam_corpus/784.txt.gz", "spec/spam_corpus/786.txt.gz", "spec/spam_corpus/788.txt.gz", "spec/spam_corpus/790.txt.gz", "spec/spam_corpus/792.txt.gz", "spec/spam_corpus/794.txt.gz", "spec/spam_corpus/796.txt.gz", "spec/spam_corpus/798.txt.gz", "spec/spam_corpus/8.txt.gz", "spec/spam_corpus/80.txt.gz", "spec/spam_corpus/800.txt.gz", "spec/spam_corpus/802.txt.gz", "spec/spam_corpus/804.txt.gz", "spec/spam_corpus/806.txt.gz", "spec/spam_corpus/808.txt.gz", "spec/spam_corpus/810.txt.gz", "spec/spam_corpus/812.txt.gz", "spec/spam_corpus/814.txt.gz", "spec/spam_corpus/816.txt.gz", "spec/spam_corpus/818.txt.gz", "spec/spam_corpus/82.txt.gz", "spec/spam_corpus/820.txt.gz", "spec/spam_corpus/822.txt.gz", "spec/spam_corpus/824.txt.gz", "spec/spam_corpus/826.txt.gz", "spec/spam_corpus/828.txt.gz", "spec/spam_corpus/830.txt.gz", "spec/spam_corpus/832.txt.gz", "spec/spam_corpus/834.txt.gz", "spec/spam_corpus/836.txt.gz", "spec/spam_corpus/838.txt.gz", "spec/spam_corpus/84.txt.gz", "spec/spam_corpus/840.txt.gz", "spec/spam_corpus/842.txt.gz", "spec/spam_corpus/844.txt.gz", "spec/spam_corpus/846.txt.gz", "spec/spam_corpus/848.txt.gz", "spec/spam_corpus/850.txt.gz", "spec/spam_corpus/852.txt.gz", "spec/spam_corpus/854.txt.gz", "spec/spam_corpus/856.txt.gz", "spec/spam_corpus/858.txt.gz", "spec/spam_corpus/86.txt.gz", "spec/spam_corpus/860.txt.gz", "spec/spam_corpus/862.txt.gz", "spec/spam_corpus/864.txt.gz", "spec/spam_corpus/866.txt.gz", "spec/spam_corpus/868.txt.gz", "spec/spam_corpus/870.txt.gz", "spec/spam_corpus/872.txt.gz", "spec/spam_corpus/874.txt.gz", "spec/spam_corpus/876.txt.gz", "spec/spam_corpus/878.txt.gz", "spec/spam_corpus/88.txt.gz", "spec/spam_corpus/880.txt.gz", "spec/spam_corpus/882.txt.gz", "spec/spam_corpus/884.txt.gz", "spec/spam_corpus/886.txt.gz", "spec/spam_corpus/888.txt.gz", "spec/spam_corpus/890.txt.gz", "spec/spam_corpus/892.txt.gz", "spec/spam_corpus/894.txt.gz", "spec/spam_corpus/896.txt.gz", "spec/spam_corpus/898.txt.gz", "spec/spam_corpus/9.txt.gz", "spec/spam_corpus/90.txt.gz", "spec/spam_corpus/900.txt.gz", "spec/spam_corpus/902.txt.gz", "spec/spam_corpus/904.txt.gz", "spec/spam_corpus/906.txt.gz", "spec/spam_corpus/908.txt.gz", "spec/spam_corpus/910.txt.gz", "spec/spam_corpus/912.txt.gz", "spec/spam_corpus/914.txt.gz", "spec/spam_corpus/916.txt.gz", "spec/spam_corpus/918.txt.gz", "spec/spam_corpus/92.txt.gz", "spec/spam_corpus/920.txt.gz", "spec/spam_corpus/922.txt.gz", "spec/spam_corpus/924.txt.gz", "spec/spam_corpus/926.txt.gz", "spec/spam_corpus/928.txt.gz", "spec/spam_corpus/930.txt.gz", "spec/spam_corpus/932.txt.gz", "spec/spam_corpus/934.txt.gz", "spec/spam_corpus/936.txt.gz", "spec/spam_corpus/938.txt.gz", "spec/spam_corpus/94.txt.gz", "spec/spam_corpus/940.txt.gz", "spec/spam_corpus/942.txt.gz", "spec/spam_corpus/944.txt.gz", "spec/spam_corpus/946.txt.gz", "spec/spam_corpus/948.txt.gz", "spec/spam_corpus/950.txt.gz", "spec/spam_corpus/952.txt.gz", "spec/spam_corpus/954.txt.gz", "spec/spam_corpus/956.txt.gz", "spec/spam_corpus/958.txt.gz", "spec/spam_corpus/96.txt.gz", "spec/spam_corpus/960.txt.gz", "spec/spam_corpus/962.txt.gz", "spec/spam_corpus/964.txt.gz", "spec/spam_corpus/966.txt.gz", "spec/spam_corpus/968.txt.gz", "spec/spam_corpus/970.txt.gz", "spec/spam_corpus/972.txt.gz", "spec/spam_corpus/974.txt.gz", "spec/spam_corpus/98.txt.gz", "spec/spam_corpus/debugyouradd.com.txt.gz", "spec/spam_corpus/humandesignconsulting.comm.txt.gz", "spec/spam_corpus_spec.rb", "spec/spec.opts", "spec/spec_helper.rb", "tasks/rspec.rake"]
16
16
  s.homepage = %q{http://github.com/moowahaha/despamliator}
17
17
  s.post_install_message = %q{PostInstall.txt}
18
18
  s.rdoc_options = ["--main", "README.rdoc"]
data/lib/despamilator.rb CHANGED
@@ -3,7 +3,7 @@ $:.unshift(File.dirname(__FILE__)) unless $:.include?(File.dirname(__FILE__)) ||
3
3
  require 'despamilator/filter'
4
4
 
5
5
  class Despamilator
6
- VERSION = "0.4"
6
+ VERSION = "0.5"
7
7
 
8
8
  def initialize text
9
9
  @filters = Despamilator::Filter.new text
@@ -16,4 +16,4 @@ class Despamilator
16
16
  def matched_by
17
17
  @filters.matches
18
18
  end
19
- end
19
+ end
@@ -0,0 +1,20 @@
1
+ require 'despamilator'
2
+
3
+ module ActiveRecord
4
+ module Validations
5
+ module ClassMethods
6
+ def validates_despamilation_of(* attr_names)
7
+ threshold = attr_names.pop[:threshold] || raise('A threshold score must be supplied')
8
+
9
+ configuration = {
10
+ :message => "has exceeded the spam threshold of #{threshold}",
11
+ :on => :save
12
+ }
13
+
14
+ validates_each(attr_names, configuration) do |record, attr_name, value|
15
+ record.errors.add(attr_name, configuration[:message]) if Despamilator.new(value).score >= threshold
16
+ end
17
+ end
18
+ end
19
+ end
20
+ end
@@ -0,0 +1,20 @@
1
+ require File.dirname(__FILE__) + '/spec_helper.rb'
2
+ require File.dirname(__FILE__) + '/../lib/despamilator/validation.rb'
3
+
4
+ class TestClass
5
+ include ActiveRecord::Validations::ClassMethods
6
+ end
7
+
8
+ describe 'despamilator validation' do
9
+
10
+ # worst test i have ever written?
11
+ it "should validate my field" do
12
+ fake_record = mock('fake record')
13
+
14
+ tc = TestClass.new
15
+ tc.should_receive(:validates_each).with([:something], {:on=>:save, :message=>"has exceeded the spam threshold of 1"}).and_yield(fake_record, :something, 'bob')
16
+
17
+ tc.validates_despamilation_of :something, :threshold => 1
18
+ end
19
+
20
+ end
metadata CHANGED
@@ -4,8 +4,8 @@ version: !ruby/object:Gem::Version
4
4
  prerelease: false
5
5
  segments:
6
6
  - 0
7
- - 4
8
- version: "0.4"
7
+ - 5
8
+ version: "0.5"
9
9
  platform: ruby
10
10
  authors:
11
11
  - Stephen Hardisty
@@ -80,6 +80,7 @@ files:
80
80
  - lib/despamilator/filter/square_brackets.rb
81
81
  - lib/despamilator/filter/urls.rb
82
82
  - lib/despamilator/filter_base.rb
83
+ - lib/despamilator/validation.rb
83
84
  - scripts/despamilator_score.rb
84
85
  - spec/clean_corpus/101.txt.gz
85
86
  - spec/clean_corpus/103.txt.gz
@@ -188,6 +189,7 @@ files:
188
189
  - spec/clean_corpus/99.txt.gz
189
190
  - spec/clean_corpus_spec.rb
190
191
  - spec/despamilator_spec.rb
192
+ - spec/despamilator_validation_spec.rb
191
193
  - spec/filters/funky_consonant_spec.rb
192
194
  - spec/filters/html_tags_spec.rb
193
195
  - spec/filters/ip_address_url_spec.rb