matlock 0.1.0
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.
- data/README.md +40 -0
- data/bin/matlock +40 -0
- data/lib/matlock.rb +76 -0
- data/lib/matlock/data.rb +113 -0
- data/lib/matlock/data/cities.txt +148 -0
- data/lib/matlock/data/common.txt +8565 -0
- data/lib/matlock/data/names.female.txt +4186 -0
- data/lib/matlock/data/names.male.txt +1164 -0
- data/lib/matlock/data/names.surname.txt +87167 -0
- data/lib/matlock/data/states.txt +50 -0
- data/lib/matlock/data/tmp.txt +4186 -0
- data/lib/matlock/ext/string.rb +13 -0
- data/lib/matlock/version.rb +3 -0
- data/test/data_test.rb +47 -0
- data/test/matlock_test.rb +24 -0
- data/test/test_helper.rb +4 -0
- metadata +177 -0
data/test/data_test.rb
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
require 'test_helper'
|
|
2
|
+
|
|
3
|
+
class TestData < MiniTest::Unit::TestCase
|
|
4
|
+
def setup
|
|
5
|
+
@matlock = Matlock.new()
|
|
6
|
+
end
|
|
7
|
+
|
|
8
|
+
######################################
|
|
9
|
+
# Names
|
|
10
|
+
######################################
|
|
11
|
+
|
|
12
|
+
def test_is_surname
|
|
13
|
+
assert Matlock::Data.surname?("Johnson")
|
|
14
|
+
assert Matlock::Data.surname?("Smith")
|
|
15
|
+
assert !Matlock::Data.surname?("Crabapple")
|
|
16
|
+
end
|
|
17
|
+
|
|
18
|
+
def test_is_first_name
|
|
19
|
+
assert Matlock::Data.first_name?("Ben")
|
|
20
|
+
assert Matlock::Data.first_name?("Jennifer")
|
|
21
|
+
assert !Matlock::Data.first_name?("Smith")
|
|
22
|
+
end
|
|
23
|
+
|
|
24
|
+
def test_is_male_name
|
|
25
|
+
assert Matlock::Data.male_name?("John")
|
|
26
|
+
assert Matlock::Data.male_name?("Jacob")
|
|
27
|
+
assert !Matlock::Data.male_name?("Jennifer")
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
def test_is_female_name
|
|
31
|
+
assert Matlock::Data.female_name?("Jennifer")
|
|
32
|
+
assert Matlock::Data.female_name?("Susan")
|
|
33
|
+
assert !Matlock::Data.female_name?("Mike")
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
######################################
|
|
37
|
+
# Remove Common Words from Name Data
|
|
38
|
+
######################################
|
|
39
|
+
|
|
40
|
+
def test_no_common_words_in_name_files
|
|
41
|
+
Matlock::Data.common_words.keys.each do |word|
|
|
42
|
+
assert Matlock::Data.surnames[word].nil?, "Common word found in surnames: #{word}"
|
|
43
|
+
assert Matlock::Data.male_names[word].nil?, "Common word found in males names: #{word}"
|
|
44
|
+
assert Matlock::Data.female_names[word].nil?, "Common word found in female names: #{word}"
|
|
45
|
+
end
|
|
46
|
+
end
|
|
47
|
+
end
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
require 'test_helper'
|
|
2
|
+
|
|
3
|
+
class TestMatlock < MiniTest::Unit::TestCase
|
|
4
|
+
def setup
|
|
5
|
+
@matlock = Matlock.new()
|
|
6
|
+
end
|
|
7
|
+
|
|
8
|
+
######################################
|
|
9
|
+
# Extract Names
|
|
10
|
+
######################################
|
|
11
|
+
|
|
12
|
+
def test_extract_names
|
|
13
|
+
html = <<-BLOCK
|
|
14
|
+
<html>
|
|
15
|
+
<body>
|
|
16
|
+
<p>Once upon a time there was a linebacker named Jeremy Wilson who played with Jenny Smith who played with the Denver Broncos.</p>
|
|
17
|
+
</body>
|
|
18
|
+
</html>
|
|
19
|
+
BLOCK
|
|
20
|
+
|
|
21
|
+
names = @matlock.extract_names(html)
|
|
22
|
+
assert_equal ["Jeremy Wilson", "Jenny Smith"], names
|
|
23
|
+
end
|
|
24
|
+
end
|
data/test/test_helper.rb
ADDED
metadata
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: matlock
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
prerelease:
|
|
6
|
+
platform: ruby
|
|
7
|
+
authors:
|
|
8
|
+
- Ben Johnson
|
|
9
|
+
autorequire:
|
|
10
|
+
bindir: bin
|
|
11
|
+
cert_chain: []
|
|
12
|
+
date: 2013-01-07 00:00:00.000000000 Z
|
|
13
|
+
dependencies:
|
|
14
|
+
- !ruby/object:Gem::Dependency
|
|
15
|
+
name: mechanize
|
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
|
17
|
+
none: false
|
|
18
|
+
requirements:
|
|
19
|
+
- - ~>
|
|
20
|
+
- !ruby/object:Gem::Version
|
|
21
|
+
version: 2.5.1
|
|
22
|
+
type: :runtime
|
|
23
|
+
prerelease: false
|
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
25
|
+
none: false
|
|
26
|
+
requirements:
|
|
27
|
+
- - ~>
|
|
28
|
+
- !ruby/object:Gem::Version
|
|
29
|
+
version: 2.5.1
|
|
30
|
+
- !ruby/object:Gem::Dependency
|
|
31
|
+
name: commander
|
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
|
33
|
+
none: false
|
|
34
|
+
requirements:
|
|
35
|
+
- - ~>
|
|
36
|
+
- !ruby/object:Gem::Version
|
|
37
|
+
version: 4.1.3
|
|
38
|
+
type: :runtime
|
|
39
|
+
prerelease: false
|
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
41
|
+
none: false
|
|
42
|
+
requirements:
|
|
43
|
+
- - ~>
|
|
44
|
+
- !ruby/object:Gem::Version
|
|
45
|
+
version: 4.1.3
|
|
46
|
+
- !ruby/object:Gem::Dependency
|
|
47
|
+
name: active_support
|
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
|
49
|
+
none: false
|
|
50
|
+
requirements:
|
|
51
|
+
- - '='
|
|
52
|
+
- !ruby/object:Gem::Version
|
|
53
|
+
version: 3.0.0
|
|
54
|
+
type: :runtime
|
|
55
|
+
prerelease: false
|
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
57
|
+
none: false
|
|
58
|
+
requirements:
|
|
59
|
+
- - '='
|
|
60
|
+
- !ruby/object:Gem::Version
|
|
61
|
+
version: 3.0.0
|
|
62
|
+
- !ruby/object:Gem::Dependency
|
|
63
|
+
name: rake
|
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
|
65
|
+
none: false
|
|
66
|
+
requirements:
|
|
67
|
+
- - ~>
|
|
68
|
+
- !ruby/object:Gem::Version
|
|
69
|
+
version: 10.0.3
|
|
70
|
+
type: :development
|
|
71
|
+
prerelease: false
|
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
73
|
+
none: false
|
|
74
|
+
requirements:
|
|
75
|
+
- - ~>
|
|
76
|
+
- !ruby/object:Gem::Version
|
|
77
|
+
version: 10.0.3
|
|
78
|
+
- !ruby/object:Gem::Dependency
|
|
79
|
+
name: minitest
|
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
|
81
|
+
none: false
|
|
82
|
+
requirements:
|
|
83
|
+
- - ~>
|
|
84
|
+
- !ruby/object:Gem::Version
|
|
85
|
+
version: 4.3.3
|
|
86
|
+
type: :development
|
|
87
|
+
prerelease: false
|
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
89
|
+
none: false
|
|
90
|
+
requirements:
|
|
91
|
+
- - ~>
|
|
92
|
+
- !ruby/object:Gem::Version
|
|
93
|
+
version: 4.3.3
|
|
94
|
+
- !ruby/object:Gem::Dependency
|
|
95
|
+
name: mocha
|
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
|
97
|
+
none: false
|
|
98
|
+
requirements:
|
|
99
|
+
- - ~>
|
|
100
|
+
- !ruby/object:Gem::Version
|
|
101
|
+
version: 0.13.1
|
|
102
|
+
type: :development
|
|
103
|
+
prerelease: false
|
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
105
|
+
none: false
|
|
106
|
+
requirements:
|
|
107
|
+
- - ~>
|
|
108
|
+
- !ruby/object:Gem::Version
|
|
109
|
+
version: 0.13.1
|
|
110
|
+
- !ruby/object:Gem::Dependency
|
|
111
|
+
name: unindentable
|
|
112
|
+
requirement: !ruby/object:Gem::Requirement
|
|
113
|
+
none: false
|
|
114
|
+
requirements:
|
|
115
|
+
- - ~>
|
|
116
|
+
- !ruby/object:Gem::Version
|
|
117
|
+
version: 0.1.0
|
|
118
|
+
type: :development
|
|
119
|
+
prerelease: false
|
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
121
|
+
none: false
|
|
122
|
+
requirements:
|
|
123
|
+
- - ~>
|
|
124
|
+
- !ruby/object:Gem::Version
|
|
125
|
+
version: 0.1.0
|
|
126
|
+
description:
|
|
127
|
+
email:
|
|
128
|
+
- benbjohnson@yahoo.com
|
|
129
|
+
executables:
|
|
130
|
+
- matlock
|
|
131
|
+
extensions: []
|
|
132
|
+
extra_rdoc_files: []
|
|
133
|
+
files:
|
|
134
|
+
- lib/matlock/data/cities.txt
|
|
135
|
+
- lib/matlock/data/common.txt
|
|
136
|
+
- lib/matlock/data/names.female.txt
|
|
137
|
+
- lib/matlock/data/names.male.txt
|
|
138
|
+
- lib/matlock/data/names.surname.txt
|
|
139
|
+
- lib/matlock/data/states.txt
|
|
140
|
+
- lib/matlock/data/tmp.txt
|
|
141
|
+
- lib/matlock/data.rb
|
|
142
|
+
- lib/matlock/ext/string.rb
|
|
143
|
+
- lib/matlock/version.rb
|
|
144
|
+
- lib/matlock.rb
|
|
145
|
+
- README.md
|
|
146
|
+
- test/data_test.rb
|
|
147
|
+
- test/matlock_test.rb
|
|
148
|
+
- test/test_helper.rb
|
|
149
|
+
- bin/matlock
|
|
150
|
+
homepage: http://github.com/benbjohnson/matlock
|
|
151
|
+
licenses: []
|
|
152
|
+
post_install_message:
|
|
153
|
+
rdoc_options: []
|
|
154
|
+
require_paths:
|
|
155
|
+
- lib
|
|
156
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
157
|
+
none: false
|
|
158
|
+
requirements:
|
|
159
|
+
- - ! '>='
|
|
160
|
+
- !ruby/object:Gem::Version
|
|
161
|
+
version: '0'
|
|
162
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
163
|
+
none: false
|
|
164
|
+
requirements:
|
|
165
|
+
- - ! '>='
|
|
166
|
+
- !ruby/object:Gem::Version
|
|
167
|
+
version: '0'
|
|
168
|
+
requirements: []
|
|
169
|
+
rubyforge_project:
|
|
170
|
+
rubygems_version: 1.8.24
|
|
171
|
+
signing_key:
|
|
172
|
+
specification_version: 3
|
|
173
|
+
summary: An intelligent web scraper
|
|
174
|
+
test_files:
|
|
175
|
+
- test/data_test.rb
|
|
176
|
+
- test/matlock_test.rb
|
|
177
|
+
- test/test_helper.rb
|