distillery 0.2.3 → 0.2.4
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/lib/distillery/document.rb +2 -2
- data/lib/distillery/version.rb +1 -1
- data/spec/acceptance_spec.rb +1 -0
- data/spec/lib/distillery/document_spec.rb +5 -0
- metadata +17 -17
data/lib/distillery/document.rb
CHANGED
|
@@ -169,8 +169,8 @@ module Distillery
|
|
|
169
169
|
top_score = scores[top_element.path]
|
|
170
170
|
identical = identical_attrubutes?(top_element, sibling)
|
|
171
171
|
|
|
172
|
-
related = (score > top_score*0.25 &&
|
|
173
|
-
|
|
172
|
+
related = (score > top_score*0.25 || (identical && score > top_score*0.05)) &&
|
|
173
|
+
sibling.path != top_element.path
|
|
174
174
|
end
|
|
175
175
|
|
|
176
176
|
def identical_attrubutes?(a, b)
|
data/lib/distillery/version.rb
CHANGED
data/spec/acceptance_spec.rb
CHANGED
|
@@ -118,6 +118,7 @@ distillation_of 'bourbon_balls.html' do
|
|
|
118
118
|
end
|
|
119
119
|
|
|
120
120
|
distillation_of 'bulgogi.html' do
|
|
121
|
+
subject.scan(/American to not fuss about the origin/).should have(1).result
|
|
121
122
|
should =~ /early-season barbecue/
|
|
122
123
|
should =~ /Still, it is American to not fuss/
|
|
123
124
|
end
|
|
@@ -290,6 +290,11 @@ module Distillery
|
|
|
290
290
|
doc.distill!.should =~ /me_too/
|
|
291
291
|
end
|
|
292
292
|
|
|
293
|
+
it "returns sibling elements to the top scoring one that have the same class or style and 5% of the top element's score" do
|
|
294
|
+
doc = document_of("<div id='winner'><div>#{'f,'*100}</div></div><div id='winner'><div class='me_too'>#{'m,'*6}</div></div>")
|
|
295
|
+
doc.distill!.should =~ /me_too/
|
|
296
|
+
end
|
|
297
|
+
|
|
293
298
|
end
|
|
294
299
|
|
|
295
300
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: distillery
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.4
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -13,7 +13,7 @@ date: 2011-07-31 00:00:00.000000000Z
|
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: nokogiri
|
|
16
|
-
requirement: &
|
|
16
|
+
requirement: &2169722880 !ruby/object:Gem::Requirement
|
|
17
17
|
none: false
|
|
18
18
|
requirements:
|
|
19
19
|
- - ! '>'
|
|
@@ -21,10 +21,10 @@ dependencies:
|
|
|
21
21
|
version: '1.0'
|
|
22
22
|
type: :runtime
|
|
23
23
|
prerelease: false
|
|
24
|
-
version_requirements: *
|
|
24
|
+
version_requirements: *2169722880
|
|
25
25
|
- !ruby/object:Gem::Dependency
|
|
26
26
|
name: slop
|
|
27
|
-
requirement: &
|
|
27
|
+
requirement: &2169722380 !ruby/object:Gem::Requirement
|
|
28
28
|
none: false
|
|
29
29
|
requirements:
|
|
30
30
|
- - ! '>'
|
|
@@ -32,10 +32,10 @@ dependencies:
|
|
|
32
32
|
version: '1.0'
|
|
33
33
|
type: :runtime
|
|
34
34
|
prerelease: false
|
|
35
|
-
version_requirements: *
|
|
35
|
+
version_requirements: *2169722380
|
|
36
36
|
- !ruby/object:Gem::Dependency
|
|
37
37
|
name: rspec
|
|
38
|
-
requirement: &
|
|
38
|
+
requirement: &2169721920 !ruby/object:Gem::Requirement
|
|
39
39
|
none: false
|
|
40
40
|
requirements:
|
|
41
41
|
- - ! '>'
|
|
@@ -43,10 +43,10 @@ dependencies:
|
|
|
43
43
|
version: '2.0'
|
|
44
44
|
type: :development
|
|
45
45
|
prerelease: false
|
|
46
|
-
version_requirements: *
|
|
46
|
+
version_requirements: *2169721920
|
|
47
47
|
- !ruby/object:Gem::Dependency
|
|
48
48
|
name: guard
|
|
49
|
-
requirement: &
|
|
49
|
+
requirement: &2169721540 !ruby/object:Gem::Requirement
|
|
50
50
|
none: false
|
|
51
51
|
requirements:
|
|
52
52
|
- - ! '>='
|
|
@@ -54,10 +54,10 @@ dependencies:
|
|
|
54
54
|
version: '0'
|
|
55
55
|
type: :development
|
|
56
56
|
prerelease: false
|
|
57
|
-
version_requirements: *
|
|
57
|
+
version_requirements: *2169721540
|
|
58
58
|
- !ruby/object:Gem::Dependency
|
|
59
59
|
name: guard-rspec
|
|
60
|
-
requirement: &
|
|
60
|
+
requirement: &2169721080 !ruby/object:Gem::Requirement
|
|
61
61
|
none: false
|
|
62
62
|
requirements:
|
|
63
63
|
- - ! '>='
|
|
@@ -65,10 +65,10 @@ dependencies:
|
|
|
65
65
|
version: '0'
|
|
66
66
|
type: :development
|
|
67
67
|
prerelease: false
|
|
68
|
-
version_requirements: *
|
|
68
|
+
version_requirements: *2169721080
|
|
69
69
|
- !ruby/object:Gem::Dependency
|
|
70
70
|
name: ruby-debug19
|
|
71
|
-
requirement: &
|
|
71
|
+
requirement: &2169720660 !ruby/object:Gem::Requirement
|
|
72
72
|
none: false
|
|
73
73
|
requirements:
|
|
74
74
|
- - ! '>='
|
|
@@ -76,10 +76,10 @@ dependencies:
|
|
|
76
76
|
version: '0'
|
|
77
77
|
type: :development
|
|
78
78
|
prerelease: false
|
|
79
|
-
version_requirements: *
|
|
79
|
+
version_requirements: *2169720660
|
|
80
80
|
- !ruby/object:Gem::Dependency
|
|
81
81
|
name: rb-fsevent
|
|
82
|
-
requirement: &
|
|
82
|
+
requirement: &2169720240 !ruby/object:Gem::Requirement
|
|
83
83
|
none: false
|
|
84
84
|
requirements:
|
|
85
85
|
- - ! '>='
|
|
@@ -87,10 +87,10 @@ dependencies:
|
|
|
87
87
|
version: '0'
|
|
88
88
|
type: :development
|
|
89
89
|
prerelease: false
|
|
90
|
-
version_requirements: *
|
|
90
|
+
version_requirements: *2169720240
|
|
91
91
|
- !ruby/object:Gem::Dependency
|
|
92
92
|
name: growl
|
|
93
|
-
requirement: &
|
|
93
|
+
requirement: &2169719820 !ruby/object:Gem::Requirement
|
|
94
94
|
none: false
|
|
95
95
|
requirements:
|
|
96
96
|
- - ! '>='
|
|
@@ -98,7 +98,7 @@ dependencies:
|
|
|
98
98
|
version: '0'
|
|
99
99
|
type: :development
|
|
100
100
|
prerelease: false
|
|
101
|
-
version_requirements: *
|
|
101
|
+
version_requirements: *2169719820
|
|
102
102
|
description: Distillery extracts the "content" portion out of an HTML document. It
|
|
103
103
|
applies heuristics based on element type, location, class/id name and other attributes
|
|
104
104
|
to try and find the content part of the HTML document and return it.
|